From 8a7e2d2ea080d10a189a1d611344b0330468ebc3 Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Tue, 28 Aug 2018 11:31:18 +0200
Subject: cpupower: remove stringop-truncation waring
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The strncpy doesn't null terminate the string because the size is too
short by one byte.

parse.c: In function ‘prepare_default_config’:
parse.c:148:2: warning: ‘strncpy’ output truncated before terminating
    nul copying 8 bytes from a string of the same length
    [-Wstringop-truncation]
  strncpy(config->governor, "ondemand", 8);
  ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

The normal method of passing the length of the destination buffer works
correctly here.

Fixes: 7fe2f6399a84 ("cpupowerutils - cpufrequtils extended with quite some features")
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/power/cpupower/bench/parse.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/power/cpupower/bench/parse.c b/tools/power/cpupower/bench/parse.c
index 9ba8a44ad2a7..84caee38418f 100644
--- a/tools/power/cpupower/bench/parse.c
+++ b/tools/power/cpupower/bench/parse.c
@@ -145,7 +145,7 @@ struct config *prepare_default_config()
 	config->cpu = 0;
 	config->prio = SCHED_HIGH;
 	config->verbose = 0;
-	strncpy(config->governor, "ondemand", 8);
+	strncpy(config->governor, "ondemand", sizeof(config->governor));
 
 	config->output = stdout;
 
-- 
cgit v1.2.3


From b5d83fec732dc98e37b22e8b20a7943aa0bb55d9 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Tue, 28 Aug 2018 09:10:45 -0700
Subject: bpf: sockmap test remove shutdown() calls

Currently, we do a shutdown(sk, SHUT_RDWR) on both peer sockets and
a shutdown on the sender as well. However, this is incorrect and can
occasionally cause issues if you happen to have bad timing. First
peer1 or peer2 may still be in use depending on the test and timing.
Second we really should only be closing the read side and/or write
side depending on if the test is receiving or sending.

But, really none of this is needed just remove the shutdown calls.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_sockmap.c | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 0c7d9e556b47..a0e77c6bb0cf 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -469,8 +469,6 @@ static int sendmsg_test(struct sockmap_options *opt)
 			fprintf(stderr,
 				"msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n",
 				iov_count, iov_buf, cnt, err);
-		shutdown(p2, SHUT_RDWR);
-		shutdown(p1, SHUT_RDWR);
 		if (s.end.tv_sec - s.start.tv_sec) {
 			sent_Bps = sentBps(s);
 			recvd_Bps = recvdBps(s);
@@ -500,7 +498,6 @@ static int sendmsg_test(struct sockmap_options *opt)
 			fprintf(stderr,
 				"msg_loop_tx: iov_count %i iov_buf %i cnt %i err %i\n",
 				iov_count, iov_buf, cnt, err);
-		shutdown(c1, SHUT_RDWR);
 		if (s.end.tv_sec - s.start.tv_sec) {
 			sent_Bps = sentBps(s);
 			recvd_Bps = recvdBps(s);
-- 
cgit v1.2.3


From 7d2c6cfc5411207f1094e7ca5e63e711dc76d1ff Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Tue, 28 Aug 2018 09:10:50 -0700
Subject: bpf: use --cgroup in test_suite if supplied

If the user supplies a --cgroup value in the arguments when running
the test_suite go ahaead and run the self tests there. I use this
to test with multiple cgroup users.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_sockmap.c | 53 +++++++++++++++++-------------
 1 file changed, 31 insertions(+), 22 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index a0e77c6bb0cf..ac7de38e5c63 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1345,9 +1345,9 @@ static int populate_progs(char *bpf_file)
 	return 0;
 }
 
-static int __test_suite(char *bpf_file)
+static int __test_suite(int cg_fd, char *bpf_file)
 {
-	int cg_fd, err;
+	int err, cleanup = cg_fd;
 
 	err = populate_progs(bpf_file);
 	if (err < 0) {
@@ -1355,22 +1355,24 @@ static int __test_suite(char *bpf_file)
 		return err;
 	}
 
-	if (setup_cgroup_environment()) {
-		fprintf(stderr, "ERROR: cgroup env failed\n");
-		return -EINVAL;
-	}
-
-	cg_fd = create_and_get_cgroup(CG_PATH);
 	if (cg_fd < 0) {
-		fprintf(stderr,
-			"ERROR: (%i) open cg path failed: %s\n",
-			cg_fd, optarg);
-		return cg_fd;
-	}
+		if (setup_cgroup_environment()) {
+			fprintf(stderr, "ERROR: cgroup env failed\n");
+			return -EINVAL;
+		}
+
+		cg_fd = create_and_get_cgroup(CG_PATH);
+		if (cg_fd < 0) {
+			fprintf(stderr,
+				"ERROR: (%i) open cg path failed: %s\n",
+				cg_fd, optarg);
+			return cg_fd;
+		}
 
-	if (join_cgroup(CG_PATH)) {
-		fprintf(stderr, "ERROR: failed to join cgroup\n");
-		return -EINVAL;
+		if (join_cgroup(CG_PATH)) {
+			fprintf(stderr, "ERROR: failed to join cgroup\n");
+			return -EINVAL;
+		}
 	}
 
 	/* Tests basic commands and APIs with range of iov values */
@@ -1391,20 +1393,24 @@ static int __test_suite(char *bpf_file)
 
 out:
 	printf("Summary: %i PASSED %i FAILED\n", passed, failed);
-	cleanup_cgroup_environment();
-	close(cg_fd);
+	if (cleanup < 0) {
+		cleanup_cgroup_environment();
+		close(cg_fd);
+	}
 	return err;
 }
 
-static int test_suite(void)
+static int test_suite(int cg_fd)
 {
 	int err;
 
-	err = __test_suite(BPF_SOCKMAP_FILENAME);
+	err = __test_suite(cg_fd, BPF_SOCKMAP_FILENAME);
 	if (err)
 		goto out;
-	err = __test_suite(BPF_SOCKHASH_FILENAME);
+	err = __test_suite(cg_fd, BPF_SOCKHASH_FILENAME);
 out:
+	if (cg_fd > -1)
+		close(cg_fd);
 	return err;
 }
 
@@ -1417,7 +1423,7 @@ int main(int argc, char **argv)
 	int test = PING_PONG;
 
 	if (argc < 2)
-		return test_suite();
+		return test_suite(-1);
 
 	while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:",
 				  long_options, &longindex)) != -1) {
@@ -1483,6 +1489,9 @@ int main(int argc, char **argv)
 		}
 	}
 
+	if (argc <= 3 && cg_fd)
+		return test_suite(cg_fd);
+
 	if (!cg_fd) {
 		fprintf(stderr, "%s requires cgroup option: --cgroup <path>\n",
 			argv[0]);
-- 
cgit v1.2.3


From 31e7490741566d6f72be3a68bf9259a3bc2bc21d Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sun, 1 Jul 2018 05:48:46 -0700
Subject: torture: Stop overwriting Make.out file with obsolete version

The old approach placed all the build products into the b* directories,
which meant that some of these build products needed to be copied to
the proper directory in the res hierarchy.  The new approach leaves
things like .config and the .o files in the b1 directory, but directs
build output and diagnostics directly to the proper directory in the
res hierarchy.  Unfortunately, one of the copies was still carried out,
which could (and sometimes did) overwrite the build output and diagnostics
with obsolete output remaining in the b1 directory.

This commit therefore removes the offending "cp" command.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh | 1 -
 1 file changed, 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index f7247ee00514..58ca758a5786 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -120,7 +120,6 @@ then
 	parse-build.sh $resdir/Make.out $title
 else
 	# Build failed.
-	cp $builddir/Make*.out $resdir
 	cp $builddir/.config $resdir || :
 	echo Build failed, not running KVM, see $resdir.
 	if test -f $builddir.wait
-- 
cgit v1.2.3


From a52d14addf06c00cfca4f1698e254955942be754 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 7 Jul 2018 10:30:28 -0700
Subject: rcutorture: Remove TREE06 and TREE08 from the default test list

Now that there is only one RCU flavor to rule them all, the TREE06
and TREE08 test scenarios are redundant.  This commit therefore removes
them.  Later changes will rebalance and renumber the tests.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 tools/testing/selftests/rcutorture/configs/rcu/CFLIST | 2 --
 1 file changed, 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
index 6a0b9f69faad..c3c1fb5a9e1f 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
+++ b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
@@ -3,9 +3,7 @@ TREE02
 TREE03
 TREE04
 TREE05
-TREE06
 TREE07
-TREE08
 TREE09
 SRCU-N
 SRCU-P
-- 
cgit v1.2.3


From 02c7f38b7ace9f1b2ddb7a88139127eef4cf8706 Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Tue, 28 Aug 2018 11:36:20 -0700
Subject: selftests/net: add ip_defrag selftest

This test creates a raw IPv4 socket, fragments a largish UDP
datagram and sends the fragments out of order.

Then repeats in a loop with different message and fragment lengths.

Then does the same with overlapping fragments (with overlapping
fragments the expectation is that the recv times out).

Tested:

root@<host># time ./ip_defrag.sh
ipv4 defrag
PASS
ipv4 defrag with overlaps
PASS

real    1m7.679s
user    0m0.628s
sys     0m2.242s

A similar test for IPv6 is to follow.

Signed-off-by: Peter Oskolkov <posk@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/.gitignore   |   1 +
 tools/testing/selftests/net/Makefile     |   4 +-
 tools/testing/selftests/net/ip_defrag.c  | 313 +++++++++++++++++++++++++++++++
 tools/testing/selftests/net/ip_defrag.sh |  28 +++
 4 files changed, 344 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/net/ip_defrag.c
 create mode 100755 tools/testing/selftests/net/ip_defrag.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 78b24cf76f40..8cf22b3c2563 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -14,3 +14,4 @@ udpgso_bench_rx
 udpgso_bench_tx
 tcp_inq
 tls
+ip_defrag
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 9cca68e440a0..cccdb2295567 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -5,13 +5,13 @@ CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g
 CFLAGS += -I../../../../usr/include/
 
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
-TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh
+TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
 TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
 TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd
-TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx
+TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
 
diff --git a/tools/testing/selftests/net/ip_defrag.c b/tools/testing/selftests/net/ip_defrag.c
new file mode 100644
index 000000000000..55fdcdc78eef
--- /dev/null
+++ b/tools/testing/selftests/net/ip_defrag.c
@@ -0,0 +1,313 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <linux/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+
+static bool		cfg_do_ipv4;
+static bool		cfg_do_ipv6;
+static bool		cfg_verbose;
+static bool		cfg_overlap;
+static unsigned short	cfg_port = 9000;
+
+const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) };
+
+#define IP4_HLEN	(sizeof(struct iphdr))
+#define IP6_HLEN	(sizeof(struct ip6_hdr))
+#define UDP_HLEN	(sizeof(struct udphdr))
+
+static int msg_len;
+static int max_frag_len;
+
+#define MSG_LEN_MAX	60000	/* Max UDP payload length. */
+
+#define IP4_MF		(1u << 13)  /* IPv4 MF flag. */
+
+static uint8_t udp_payload[MSG_LEN_MAX];
+static uint8_t ip_frame[IP_MAXPACKET];
+static uint16_t ip_id = 0xabcd;
+static int msg_counter;
+static int frag_counter;
+static unsigned int seed;
+
+/* Receive a UDP packet. Validate it matches udp_payload. */
+static void recv_validate_udp(int fd_udp)
+{
+	ssize_t ret;
+	static uint8_t recv_buff[MSG_LEN_MAX];
+
+	ret = recv(fd_udp, recv_buff, msg_len, 0);
+	msg_counter++;
+
+	if (cfg_overlap) {
+		if (ret != -1)
+			error(1, 0, "recv: expected timeout; got %d; seed = %u",
+				(int)ret, seed);
+		if (errno != ETIMEDOUT && errno != EAGAIN)
+			error(1, errno, "recv: expected timeout: %d; seed = %u",
+				 errno, seed);
+		return;  /* OK */
+	}
+
+	if (ret == -1)
+		error(1, errno, "recv: msg_len = %d max_frag_len = %d",
+			msg_len, max_frag_len);
+	if (ret != msg_len)
+		error(1, 0, "recv: wrong size: %d vs %d", (int)ret, msg_len);
+	if (memcmp(udp_payload, recv_buff, msg_len))
+		error(1, 0, "recv: wrong data");
+}
+
+static uint32_t raw_checksum(uint8_t *buf, int len, uint32_t sum)
+{
+	int i;
+
+	for (i = 0; i < (len & ~1U); i += 2) {
+		sum += (u_int16_t)ntohs(*((u_int16_t *)(buf + i)));
+		if (sum > 0xffff)
+			sum -= 0xffff;
+	}
+
+	if (i < len) {
+		sum += buf[i] << 8;
+		if (sum > 0xffff)
+			sum -= 0xffff;
+	}
+
+	return sum;
+}
+
+static uint16_t udp_checksum(struct ip *iphdr, struct udphdr *udphdr)
+{
+	uint32_t sum = 0;
+
+	sum = raw_checksum((uint8_t *)&iphdr->ip_src, 2 * sizeof(iphdr->ip_src),
+				IPPROTO_UDP + (uint32_t)(UDP_HLEN + msg_len));
+	sum = raw_checksum((uint8_t *)udp_payload, msg_len, sum);
+	sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum);
+	return htons(0xffff & ~sum);
+}
+
+static void send_fragment(int fd_raw, struct sockaddr *addr, socklen_t alen,
+				struct ip *iphdr, int offset)
+{
+	int frag_len;
+	int res;
+
+	if (msg_len - offset <= max_frag_len) {
+		/* This is the last fragment. */
+		frag_len = IP4_HLEN + msg_len - offset;
+		iphdr->ip_off = htons((offset + UDP_HLEN) / 8);
+	} else {
+		frag_len = IP4_HLEN + max_frag_len;
+		iphdr->ip_off = htons((offset + UDP_HLEN) / 8 | IP4_MF);
+	}
+	iphdr->ip_len = htons(frag_len);
+	memcpy(ip_frame + IP4_HLEN, udp_payload + offset,
+		 frag_len - IP4_HLEN);
+
+	res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
+	if (res < 0)
+		error(1, errno, "send_fragment");
+	if (res != frag_len)
+		error(1, 0, "send_fragment: %d vs %d", res, frag_len);
+
+	frag_counter++;
+}
+
+static void send_udp_frags_v4(int fd_raw, struct sockaddr *addr, socklen_t alen)
+{
+	struct ip *iphdr = (struct ip *)ip_frame;
+	struct udphdr udphdr;
+	int res;
+	int offset;
+	int frag_len;
+
+	/* Send the UDP datagram using raw IP fragments: the 0th fragment
+	 * has the UDP header; other fragments are pieces of udp_payload
+	 * split in chunks of frag_len size.
+	 *
+	 * Odd fragments (1st, 3rd, 5th, etc.) are sent out first, then
+	 * even fragments (0th, 2nd, etc.) are sent out.
+	 */
+	memset(iphdr, 0, sizeof(*iphdr));
+	iphdr->ip_hl = 5;
+	iphdr->ip_v = 4;
+	iphdr->ip_tos = 0;
+	iphdr->ip_id = htons(ip_id++);
+	iphdr->ip_ttl = 0x40;
+	iphdr->ip_p = IPPROTO_UDP;
+	iphdr->ip_src.s_addr = htonl(INADDR_LOOPBACK);
+	iphdr->ip_dst = addr4;
+	iphdr->ip_sum = 0;
+
+	/* Odd fragments. */
+	offset = 0;
+	while (offset < msg_len) {
+		send_fragment(fd_raw, addr, alen, iphdr, offset);
+		offset += 2 * max_frag_len;
+	}
+
+	if (cfg_overlap) {
+		/* Send an extra random fragment. */
+		offset = rand() % (UDP_HLEN + msg_len - 1);
+		/* sendto() returns EINVAL if offset + frag_len is too small. */
+		frag_len = IP4_HLEN + UDP_HLEN + rand() % 256;
+		iphdr->ip_off = htons(offset / 8 | IP4_MF);
+		iphdr->ip_len = htons(frag_len);
+		res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
+		if (res < 0)
+			error(1, errno, "sendto overlap");
+		if (res != frag_len)
+			error(1, 0, "sendto overlap: %d vs %d", (int)res, frag_len);
+		frag_counter++;
+	}
+
+	/* Zeroth fragment (UDP header). */
+	frag_len = IP4_HLEN + UDP_HLEN;
+	iphdr->ip_len = htons(frag_len);
+	iphdr->ip_off = htons(IP4_MF);
+
+	udphdr.source = htons(cfg_port + 1);
+	udphdr.dest = htons(cfg_port);
+	udphdr.len = htons(UDP_HLEN + msg_len);
+	udphdr.check = 0;
+	udphdr.check = udp_checksum(iphdr, &udphdr);
+
+	memcpy(ip_frame + IP4_HLEN, &udphdr, UDP_HLEN);
+	res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
+	if (res < 0)
+		error(1, errno, "sendto UDP header");
+	if (res != frag_len)
+		error(1, 0, "sendto UDP header: %d vs %d", (int)res, frag_len);
+	frag_counter++;
+
+	/* Even fragments. */
+	offset = max_frag_len;
+	while (offset < msg_len) {
+		send_fragment(fd_raw, addr, alen, iphdr, offset);
+		offset += 2 * max_frag_len;
+	}
+}
+
+static void run_test(struct sockaddr *addr, socklen_t alen)
+{
+	int fd_tx_udp, fd_tx_raw, fd_rx_udp;
+	struct timeval tv = { .tv_sec = 0, .tv_usec = 10 * 1000 };
+	int idx;
+
+	/* Initialize the payload. */
+	for (idx = 0; idx < MSG_LEN_MAX; ++idx)
+		udp_payload[idx] = idx % 256;
+
+	/* Open sockets. */
+	fd_tx_udp = socket(addr->sa_family, SOCK_DGRAM, 0);
+	if (fd_tx_udp == -1)
+		error(1, errno, "socket tx_udp");
+
+	fd_tx_raw = socket(addr->sa_family, SOCK_RAW, IPPROTO_RAW);
+	if (fd_tx_raw == -1)
+		error(1, errno, "socket tx_raw");
+
+	fd_rx_udp = socket(addr->sa_family, SOCK_DGRAM, 0);
+	if (fd_rx_udp == -1)
+		error(1, errno, "socket rx_udp");
+	if (bind(fd_rx_udp, addr, alen))
+		error(1, errno, "bind");
+	/* Fail fast. */
+	if (setsockopt(fd_rx_udp, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+		error(1, errno, "setsockopt rcv timeout");
+
+	for (msg_len = 1; msg_len < MSG_LEN_MAX; msg_len += (rand() % 4096)) {
+		if (cfg_verbose)
+			printf("msg_len: %d\n", msg_len);
+		max_frag_len = addr->sa_family == AF_INET ? 8 : 1280;
+		for (; max_frag_len < 1500 && max_frag_len <= msg_len;
+				max_frag_len += 8) {
+			send_udp_frags_v4(fd_tx_raw, addr, alen);
+			recv_validate_udp(fd_rx_udp);
+		}
+	}
+
+	/* Cleanup. */
+	if (close(fd_tx_raw))
+		error(1, errno, "close tx_raw");
+	if (close(fd_tx_udp))
+		error(1, errno, "close tx_udp");
+	if (close(fd_rx_udp))
+		error(1, errno, "close rx_udp");
+
+	if (cfg_verbose)
+		printf("processed %d messages, %d fragments\n",
+			msg_counter, frag_counter);
+
+	fprintf(stderr, "PASS\n");
+}
+
+
+static void run_test_v4(void)
+{
+	struct sockaddr_in addr = {0};
+
+	addr.sin_family = AF_INET;
+	addr.sin_port = htons(cfg_port);
+	addr.sin_addr = addr4;
+
+	run_test((void *)&addr, sizeof(addr));
+}
+
+static void run_test_v6(void)
+{
+	fprintf(stderr, "NOT IMPL.\n");
+	exit(1);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int c;
+
+	while ((c = getopt(argc, argv, "46ov")) != -1) {
+		switch (c) {
+		case '4':
+			cfg_do_ipv4 = true;
+			break;
+		case '6':
+			cfg_do_ipv6 = true;
+			break;
+		case 'o':
+			cfg_overlap = true;
+			break;
+		case 'v':
+			cfg_verbose = true;
+			break;
+		default:
+			error(1, 0, "%s: parse error", argv[0]);
+		}
+	}
+}
+
+int main(int argc, char **argv)
+{
+	parse_opts(argc, argv);
+	seed = time(NULL);
+	srand(seed);
+
+	if (cfg_do_ipv4)
+		run_test_v4();
+	if (cfg_do_ipv6)
+		run_test_v6();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh
new file mode 100755
index 000000000000..78743adcca9e
--- /dev/null
+++ b/tools/testing/selftests/net/ip_defrag.sh
@@ -0,0 +1,28 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a couple of IP defragmentation tests.
+
+set +x
+set -e
+
+echo "ipv4 defrag"
+
+run_v4() {
+sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null
+sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null
+./ip_defrag -4
+}
+export -f run_v4
+
+./in_netns.sh "run_v4"
+
+echo "ipv4 defrag with overlaps"
+run_v4o() {
+sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null
+sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null
+./ip_defrag -4o
+}
+export -f run_v4o
+
+./in_netns.sh "run_v4o"
-- 
cgit v1.2.3


From 6493ebf7242d9b9a2c50db91b9baeb0543990736 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Wed, 29 Aug 2018 14:43:14 -0700
Subject: tools/bpf: add bpffs percpu map pretty print tests in test_btf

The bpf selftest test_btf is extended to test bpffs
percpu map pretty print for percpu array, percpu hash and
percpu lru hash.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_btf.c | 179 ++++++++++++++++++++++++++-------
 1 file changed, 144 insertions(+), 35 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 6b5cfeb7a9cc..f42b3396d622 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <linux/btf.h>
 #include <linux/err.h>
+#include <linux/kernel.h>
 #include <bpf/bpf.h>
 #include <sys/resource.h>
 #include <libelf.h>
@@ -45,7 +46,6 @@ static int count_result(int err)
 	return err;
 }
 
-#define min(a, b) ((a) < (b) ? (a) : (b))
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 
 __printf(1, 2)
@@ -130,6 +130,7 @@ struct btf_raw_test {
 	bool map_create_err;
 	bool ordered_map;
 	bool lossless_map;
+	bool percpu_map;
 	int hdr_len_delta;
 	int type_off_delta;
 	int str_off_delta;
@@ -2157,6 +2158,7 @@ static struct btf_pprint_test_meta {
 	const char *map_name;
 	bool ordered_map;
 	bool lossless_map;
+	bool percpu_map;
 } pprint_tests_meta[] = {
 {
 	.descr = "BTF pretty print array",
@@ -2164,6 +2166,7 @@ static struct btf_pprint_test_meta {
 	.map_name = "pprint_test_array",
 	.ordered_map = true,
 	.lossless_map = true,
+	.percpu_map = false,
 },
 
 {
@@ -2172,6 +2175,7 @@ static struct btf_pprint_test_meta {
 	.map_name = "pprint_test_hash",
 	.ordered_map = false,
 	.lossless_map = true,
+	.percpu_map = false,
 },
 
 {
@@ -2180,30 +2184,83 @@ static struct btf_pprint_test_meta {
 	.map_name = "pprint_test_lru_hash",
 	.ordered_map = false,
 	.lossless_map = false,
+	.percpu_map = false,
+},
+
+{
+	.descr = "BTF pretty print percpu array",
+	.map_type = BPF_MAP_TYPE_PERCPU_ARRAY,
+	.map_name = "pprint_test_percpu_array",
+	.ordered_map = true,
+	.lossless_map = true,
+	.percpu_map = true,
+},
+
+{
+	.descr = "BTF pretty print percpu hash",
+	.map_type = BPF_MAP_TYPE_PERCPU_HASH,
+	.map_name = "pprint_test_percpu_hash",
+	.ordered_map = false,
+	.lossless_map = true,
+	.percpu_map = true,
+},
+
+{
+	.descr = "BTF pretty print lru percpu hash",
+	.map_type = BPF_MAP_TYPE_LRU_PERCPU_HASH,
+	.map_name = "pprint_test_lru_percpu_hash",
+	.ordered_map = false,
+	.lossless_map = false,
+	.percpu_map = true,
 },
 
 };
 
 
-static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i)
+static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i,
+			    int num_cpus, int rounded_value_size)
 {
-	v->ui32 = i;
-	v->si32 = -i;
-	v->unused_bits2a = 3;
-	v->bits28 = i;
-	v->unused_bits2b = 3;
-	v->ui64 = i;
-	v->aenum = i & 0x03;
+	int cpu;
+
+	for (cpu = 0; cpu < num_cpus; cpu++) {
+		v->ui32 = i + cpu;
+		v->si32 = -i;
+		v->unused_bits2a = 3;
+		v->bits28 = i;
+		v->unused_bits2b = 3;
+		v->ui64 = i;
+		v->aenum = i & 0x03;
+		v = (void *)v + rounded_value_size;
+	}
 }
 
+static int check_line(const char *expected_line, int nexpected_line,
+		      int expected_line_len, const char *line)
+{
+	if (CHECK(nexpected_line == expected_line_len,
+		  "expected_line is too long"))
+		return -1;
+
+	if (strcmp(expected_line, line)) {
+		fprintf(stderr, "unexpected pprint output\n");
+		fprintf(stderr, "expected: %s", expected_line);
+		fprintf(stderr, "    read: %s", line);
+		return -1;
+	}
+
+	return 0;
+}
+
+
 static int do_test_pprint(void)
 {
 	const struct btf_raw_test *test = &pprint_test_template;
 	struct bpf_create_map_attr create_attr = {};
+	bool ordered_map, lossless_map, percpu_map;
+	int err, ret, num_cpus, rounded_value_size;
+	struct pprint_mapv *mapv = NULL;
 	unsigned int key, nr_read_elems;
-	bool ordered_map, lossless_map;
 	int map_fd = -1, btf_fd = -1;
-	struct pprint_mapv mapv = {};
 	unsigned int raw_btf_size;
 	char expected_line[255];
 	FILE *pin_file = NULL;
@@ -2212,7 +2269,6 @@ static int do_test_pprint(void)
 	char *line = NULL;
 	uint8_t *raw_btf;
 	ssize_t nread;
-	int err, ret;
 
 	fprintf(stderr, "%s......", test->descr);
 	raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
@@ -2261,9 +2317,18 @@ static int do_test_pprint(void)
 	if (CHECK(err, "bpf_obj_pin(%s): errno:%d.", pin_path, errno))
 		goto done;
 
+	percpu_map = test->percpu_map;
+	num_cpus = percpu_map ? bpf_num_possible_cpus() : 1;
+	rounded_value_size = round_up(sizeof(struct pprint_mapv), 8);
+	mapv = calloc(num_cpus, rounded_value_size);
+	if (CHECK(!mapv, "mapv allocation failure")) {
+		err = -1;
+		goto done;
+	}
+
 	for (key = 0; key < test->max_entries; key++) {
-		set_pprint_mapv(&mapv, key);
-		bpf_map_update_elem(map_fd, &key, &mapv, 0);
+		set_pprint_mapv(mapv, key, num_cpus, rounded_value_size);
+		bpf_map_update_elem(map_fd, &key, mapv, 0);
 	}
 
 	pin_file = fopen(pin_path, "r");
@@ -2286,33 +2351,74 @@ static int do_test_pprint(void)
 	ordered_map = test->ordered_map;
 	lossless_map = test->lossless_map;
 	do {
+		struct pprint_mapv *cmapv;
 		ssize_t nexpected_line;
 		unsigned int next_key;
+		int cpu;
 
 		next_key = ordered_map ? nr_read_elems : atoi(line);
-		set_pprint_mapv(&mapv, next_key);
-		nexpected_line = snprintf(expected_line, sizeof(expected_line),
-					  "%u: {%u,0,%d,0x%x,0x%x,0x%x,{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n",
-					  next_key,
-					  mapv.ui32, mapv.si32,
-					  mapv.unused_bits2a, mapv.bits28, mapv.unused_bits2b,
-					  mapv.ui64,
-					  mapv.ui8a[0], mapv.ui8a[1], mapv.ui8a[2], mapv.ui8a[3],
-					  mapv.ui8a[4], mapv.ui8a[5], mapv.ui8a[6], mapv.ui8a[7],
-					  pprint_enum_str[mapv.aenum]);
-
-		if (CHECK(nexpected_line == sizeof(expected_line),
-			  "expected_line is too long")) {
-			err = -1;
-			goto done;
+		set_pprint_mapv(mapv, next_key, num_cpus, rounded_value_size);
+		cmapv = mapv;
+
+		for (cpu = 0; cpu < num_cpus; cpu++) {
+			if (percpu_map) {
+				/* for percpu map, the format looks like:
+				 * <key>: {
+				 *	cpu0: <value_on_cpu0>
+				 *	cpu1: <value_on_cpu1>
+				 *	...
+				 *	cpun: <value_on_cpun>
+				 * }
+				 *
+				 * let us verify the line containing the key here.
+				 */
+				if (cpu == 0) {
+					nexpected_line = snprintf(expected_line,
+								  sizeof(expected_line),
+								  "%u: {\n",
+								  next_key);
+
+					err = check_line(expected_line, nexpected_line,
+							 sizeof(expected_line), line);
+					if (err == -1)
+						goto done;
+				}
+
+				/* read value@cpu */
+				nread = getline(&line, &line_len, pin_file);
+				if (nread < 0)
+					break;
+			}
+
+			nexpected_line = snprintf(expected_line, sizeof(expected_line),
+						  "%s%u: {%u,0,%d,0x%x,0x%x,0x%x,"
+						  "{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n",
+						  percpu_map ? "\tcpu" : "",
+						  percpu_map ? cpu : next_key,
+						  cmapv->ui32, cmapv->si32,
+						  cmapv->unused_bits2a,
+						  cmapv->bits28,
+						  cmapv->unused_bits2b,
+						  cmapv->ui64,
+						  cmapv->ui8a[0], cmapv->ui8a[1],
+						  cmapv->ui8a[2], cmapv->ui8a[3],
+						  cmapv->ui8a[4], cmapv->ui8a[5],
+						  cmapv->ui8a[6], cmapv->ui8a[7],
+						  pprint_enum_str[cmapv->aenum]);
+
+			err = check_line(expected_line, nexpected_line,
+					 sizeof(expected_line), line);
+			if (err == -1)
+				goto done;
+
+			cmapv = (void *)cmapv + rounded_value_size;
 		}
 
-		if (strcmp(expected_line, line)) {
-			err = -1;
-			fprintf(stderr, "unexpected pprint output\n");
-			fprintf(stderr, "expected: %s", expected_line);
-			fprintf(stderr, "    read: %s", line);
-			goto done;
+		if (percpu_map) {
+			/* skip the last bracket for the percpu map */
+			nread = getline(&line, &line_len, pin_file);
+			if (nread < 0)
+				break;
 		}
 
 		nread = getline(&line, &line_len, pin_file);
@@ -2334,6 +2440,8 @@ static int do_test_pprint(void)
 	err = 0;
 
 done:
+	if (mapv)
+		free(mapv);
 	if (!err)
 		fprintf(stderr, "OK");
 	if (*btf_log_buf && (err || args.always_log))
@@ -2361,6 +2469,7 @@ static int test_pprint(void)
 		pprint_test_template.map_name = pprint_tests_meta[i].map_name;
 		pprint_test_template.ordered_map = pprint_tests_meta[i].ordered_map;
 		pprint_test_template.lossless_map = pprint_tests_meta[i].lossless_map;
+		pprint_test_template.percpu_map = pprint_tests_meta[i].percpu_map;
 
 		err |= count_result(do_test_pprint());
 	}
-- 
cgit v1.2.3


From 1a86ad89da1c06b2a326953309dcb99f0d079a32 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Wed, 29 Aug 2018 14:43:15 -0700
Subject: tools/bpf: bpftool: add btf percpu map formated dump

The btf pretty print is added to percpu arraymap,
percpu hashmap and percpu lru hashmap.
For each <key, value> pair, the following will be
added to plain/json output:

   {
       "key": <pretty_print_key>,
       "values": [{
             "cpu": 0,
             "value": <pretty_print_value_on_cpu0>
          },{
             "cpu": 1,
             "value": <pretty_print_value_on_cpu1>
          },{
          ....
          },{
             "cpu": n,
             "value": <pretty_print_value_on_cpun>
          }
       ]
   }

For example, the following could be part of plain or json formatted
output:
    {
        "key": 0,
        "values": [{
                "cpu": 0,
                "value": {
                    "ui32": 0,
                    "ui16": 0,
                }
            },{
                "cpu": 1,
                "value": {
                    "ui32": 1,
                    "ui16": 0,
                }
            },{
                "cpu": 2,
                "value": {
                    "ui32": 2,
                    "ui16": 0,
                }
            },{
                "cpu": 3,
                "value": {
                    "ui32": 3,
                    "ui16": 0,
                }
            }
        ]
    }

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/map.c | 33 +++++++++++++++++++++++++++++++--
 1 file changed, 31 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index b2ec20e562bd..df175bc33c5d 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -169,9 +169,28 @@ static int do_dump_btf(const struct btf_dumper *d,
 	if (ret)
 		goto err_end_obj;
 
-	jsonw_name(d->jw, "value");
+	if (!map_is_per_cpu(map_info->type)) {
+		jsonw_name(d->jw, "value");
+		ret = btf_dumper_type(d, map_info->btf_value_type_id, value);
+	} else {
+		unsigned int i, n, step;
 
-	ret = btf_dumper_type(d, map_info->btf_value_type_id, value);
+		jsonw_name(d->jw, "values");
+		jsonw_start_array(d->jw);
+		n = get_possible_cpus();
+		step = round_up(map_info->value_size, 8);
+		for (i = 0; i < n; i++) {
+			jsonw_start_object(d->jw);
+			jsonw_int_field(d->jw, "cpu", i);
+			jsonw_name(d->jw, "value");
+			ret = btf_dumper_type(d, map_info->btf_value_type_id,
+					      value + i * step);
+			jsonw_end_object(d->jw);
+			if (ret)
+				break;
+		}
+		jsonw_end_array(d->jw);
+	}
 
 err_end_obj:
 	/* end of key-value pair */
@@ -298,6 +317,16 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
 			jsonw_end_object(json_wtr);
 		}
 		jsonw_end_array(json_wtr);
+		if (btf) {
+			struct btf_dumper d = {
+				.btf = btf,
+				.jw = json_wtr,
+				.is_plain_text = false,
+			};
+
+			jsonw_name(json_wtr, "formatted");
+			do_dump_btf(&d, info, key, value);
+		}
 	}
 
 	jsonw_end_object(json_wtr);
-- 
cgit v1.2.3


From 7a983a0fe2a29ec849f6748d6bd86904d6e88eea Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 20 Aug 2018 17:58:17 -0300
Subject: perf trace: Pass augmented args to the arg formatters when available

If the tracepoint payload is bigger than what a syscall expected from
what is in its format file in tracefs, then that will be used as
augmented args, i.e. the expansion of syscall arg pointers, with things
like a filename, structs, etc.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-bsbqx7xi2ot4q9bf570f7tqs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c       | 28 ++++++++++++++++++++++------
 tools/perf/trace/beauty/beauty.h | 29 +++++++++++++++++++++++++++++
 2 files changed, 51 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 22ab8e67c760..7deae6c8cb25 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -856,10 +856,12 @@ static struct syscall_fmt *syscall_fmt__find(const char *name)
 /*
  * is_exit: is this "exit" or "exit_group"?
  * is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter.
+ * args_size: sum of the sizes of the syscall arguments, anything after that is augmented stuff: pathname for openat, etc.
  */
 struct syscall {
 	struct event_format *tp_format;
 	int		    nr_args;
+	int		    args_size;
 	bool		    is_exit;
 	bool		    is_open;
 	struct format_field *args;
@@ -1258,10 +1260,12 @@ static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args)
 
 static int syscall__set_arg_fmts(struct syscall *sc)
 {
-	struct format_field *field;
+	struct format_field *field, *last_field = NULL;
 	int idx = 0, len;
 
 	for (field = sc->args; field; field = field->next, ++idx) {
+		last_field = field;
+
 		if (sc->fmt && sc->fmt->arg[idx].scnprintf)
 			continue;
 
@@ -1292,6 +1296,9 @@ static int syscall__set_arg_fmts(struct syscall *sc)
 		}
 	}
 
+	if (last_field)
+		sc->args_size = last_field->offset + last_field->size;
+
 	return 0;
 }
 
@@ -1472,14 +1479,18 @@ static size_t syscall__scnprintf_val(struct syscall *sc, char *bf, size_t size,
 }
 
 static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
-				      unsigned char *args, struct trace *trace,
-				      struct thread *thread)
+				      unsigned char *args, void *augmented_args, int augmented_args_size,
+				      struct trace *trace, struct thread *thread)
 {
 	size_t printed = 0;
 	unsigned long val;
 	u8 bit = 1;
 	struct syscall_arg arg = {
 		.args	= args,
+		.augmented = {
+			.size = augmented_args_size,
+			.args = augmented_args,
+		},
 		.idx	= 0,
 		.mask	= 0,
 		.trace  = trace,
@@ -1692,7 +1703,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name);
 
 	printed += syscall__scnprintf_args(sc, msg + printed, trace__entry_str_size - printed,
-					   args, trace, thread);
+					   args, NULL, 0, trace, thread);
 
 	if (sc->is_exit) {
 		if (!(trace->duration_filter || trace->summary_only || trace->failure_only || trace->min_stack)) {
@@ -1723,7 +1734,8 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
 	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
 	struct syscall *sc = trace__syscall_info(trace, evsel, id);
 	char msg[1024];
-	void *args;
+	void *args, *augmented_args = NULL;
+	int augmented_args_size;
 
 	if (sc == NULL)
 		return -1;
@@ -1738,7 +1750,11 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
 		goto out_put;
 
 	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
-	syscall__scnprintf_args(sc, msg, sizeof(msg), args, trace, thread);
+	augmented_args_size = sample->raw_size - sc->args_size;
+	if (augmented_args_size > 0)
+		augmented_args = sample->raw_data + sc->args_size;
+
+	syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
 	fprintf(trace->output, "%s", msg);
 	err = 0;
 out_put:
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 9615af5d412b..6ca044d3d851 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -30,9 +30,34 @@ struct thread;
 
 size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_t size);
 
+/**
+ * augmented_arg: extra payload for syscall pointer arguments
+ 
+ * If perf_sample->raw_size is more than what a syscall sys_enter_FOO puts,
+ * then its the arguments contents, so that we can show more than just a
+ * pointer. This will be done initially with eBPF, the start of that is at the
+ * tools/perf/examples/bpf/augmented_syscalls.c example for the openat, but
+ * will eventually be done automagically caching the running kernel tracefs
+ * events data into an eBPF C script, that then gets compiled and its .o file
+ * cached for subsequent use. For char pointers like the ones for 'open' like
+ * syscalls its easy, for the rest we should use DWARF or better, BTF, much
+ * more compact.
+ *
+ * @size: 8 if all we need is an integer, otherwise all of the augmented arg.
+ * @int_arg: will be used for integer like pointer contents, like 'accept's 'upeer_addrlen'
+ * @value: u64 aligned, for structs, pathnames
+ */
+struct augmented_arg {
+	int  size;
+	int  int_arg;
+	u64  value[];
+};
+
 /**
  * @val: value of syscall argument being formatted
  * @args: All the args, use syscall_args__val(arg, nth) to access one
+ * @augmented_args: Extra data that can be collected, for instance, with eBPF for expanding the pathname for open, etc
+ * @augmented_args_size: augmented_args total payload size
  * @thread: tid state (maps, pid, tid, etc)
  * @trace: 'perf trace' internals: all threads, etc
  * @parm: private area, may be an strarray, for instance
@@ -43,6 +68,10 @@ size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_
 struct syscall_arg {
 	unsigned long val;
 	unsigned char *args;
+	struct {
+		struct augmented_arg *args;
+		int		     size;
+	} augmented;
 	struct thread *thread;
 	struct trace  *trace;
 	void	      *parm;
-- 
cgit v1.2.3


From 6ccc18a9a17a1189b8b157176ce4a58c458c9eee Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 21 Aug 2018 11:14:15 -0300
Subject: perf trace: Make the augmented_syscalls filter out the tracepoint
 event

When we attach a eBPF object to a tracepoint, if we return 1, then that
tracepoint will be stored in the perf's ring buffer. In the
augmented_syscalls.c case we want to just attach and _override_ the
tracepoint payload with an augmented, extended one.

In this example, tools/perf/examples/bpf/augmented_syscalls.c, we are
attaching to the 'openat' syscall, and adding, after the
syscalls:sys_enter_openat usual payload as defined by
/sys/kernel/debug/tracing/events/syscalls/sys_enter_openat/format, a
snapshot of its sole pointer arg:

  # grep 'field:.*\*' /sys/kernel/debug/tracing/events/syscalls/sys_enter_openat/format
	field:const char * filename;	offset:24;	size:8;	signed:0;
  #

For now this is not being considered, the next csets will make use of
it, but as this is overriding the syscall tracepoint enter, we don't
want that event appearing on the ring buffer, just our synthesized one.

Before:

  # perf trace -e ~acme/git/perf/tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
     0.000 (         ): __augmented_syscalls__:dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC
     0.006 (         ): syscalls:sys_enter_openat:dfd: CWD, filename: , flags: CLOEXEC
     0.007 ( 0.004 ms): cat/24044 openat(dfd: CWD, filename: 0x216dda8, flags: CLOEXEC                  ) = 3
     0.028 (         ): __augmented_syscalls__:dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC
     0.030 (         ): syscalls:sys_enter_openat:dfd: CWD, filename: , flags: CLOEXEC
     0.031 ( 0.006 ms): cat/24044 openat(dfd: CWD, filename: 0x2375ce0, flags: CLOEXEC                  ) = 3
     0.291 (         ): __augmented_syscalls__:dfd: CWD, filename: /etc/passwd
     0.293 (         ): syscalls:sys_enter_openat:dfd: CWD, filename:
     0.294 ( 0.004 ms): cat/24044 openat(dfd: CWD, filename: 0x637db06b                                 ) = 3
  #

After:

  # perf trace -e ~acme/git/perf/tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
     0.000 (         ): __augmented_syscalls__:dfd: CWD, filename: 0x9c6a1da8, flags: CLOEXEC
     0.005 ( 0.015 ms): cat/27341 openat(dfd: CWD, filename: 0x9c6a1da8, flags: CLOEXEC                 ) = 3
     0.040 (         ): __augmented_syscalls__:dfd: CWD, filename: 0x9c8a9ce0, flags: CLOEXEC
     0.041 ( 0.006 ms): cat/27341 openat(dfd: CWD, filename: 0x9c8a9ce0, flags: CLOEXEC                 ) = 3
     0.294 (         ): __augmented_syscalls__:dfd: CWD, filename: 0x482a706b
     0.296 ( 0.067 ms): cat/27341 openat(dfd: CWD, filename: 0x482a706b                                 ) = 3
  #

Now lets replace that __augmented_syscalls__ name with the syscall name,
using:

  # grep 'field:.*syscall_nr' /sys/kernel/debug/tracing/events/syscalls/sys_enter_openat/format
	field:int __syscall_nr;	offset:8;	size:4;	signed:1;
  #

That the synthesized payload has exactly where the syscall enter
tracepoint puts it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-og4r9k87mzp9hv7el046idmd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/examples/bpf/augmented_syscalls.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index 69a31386d8cd..10e7997ab481 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -49,7 +49,7 @@ int syscall_enter(openat)(struct syscall_enter_openat_args *args)
 	probe_read_str(&augmented_args.filename, sizeof(augmented_args.filename), args->filename_ptr);
 	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU,
 			  &augmented_args, sizeof(augmented_args));
-	return 1;
+	return 0;
 }
 
 license(GPL);
-- 
cgit v1.2.3


From 1cdf618f23867dd1dae58f10f1f82839f2bf73b4 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 21 Aug 2018 11:44:23 -0300
Subject: perf trace: Print the syscall name for augmented_syscalls

Since we copy all the payload for raw_syscalls:sys_enter plus add
expanded pointers, we can use the syscall id to get its name, etc:

  # grep 'field:.* id' /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
	field:long id;	offset:8;	size:8;	signed:1;
  #

Before:

  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
     0.000 (         ): __augmented_syscalls__:dfd: CWD, filename: 0xec9f9da8, flags: CLOEXEC
     0.006 ( 0.006 ms): cat/2395 openat(dfd: CWD, filename: 0xec9f9da8, flags: CLOEXEC) = 3
     0.041 (         ): __augmented_syscalls__:dfd: CWD, filename: 0xecc01ce0, flags: CLOEXEC
     0.042 ( 0.007 ms): cat/2395 openat(dfd: CWD, filename: 0xecc01ce0, flags: CLOEXEC) = 3
     0.376 (         ): __augmented_syscalls__:dfd: CWD, filename: 0xac0a806b
     0.379 ( 0.006 ms): cat/2395 openat(dfd: CWD, filename: 0xac0a806b) = 3
  #

After:

  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
     0.000 (         ): openat(dfd: CWD, filename: 0x31b6dda8, flags: CLOEXEC)
     0.009 ( 0.009 ms): cat/3619 openat(dfd: CWD, filename: 0x31b6dda8, flags: CLOEXEC) = 3
     0.051 (         ): openat(dfd: CWD, filename: 0x31d75ce0, flags: CLOEXEC)
     0.054 ( 0.010 ms): cat/3619 openat(dfd: CWD, filename: 0x31d75ce0, flags: CLOEXEC) = 3
     0.539 (         ): openat(dfd: CWD, filename: 0xca71506b)
     0.543 ( 0.115 ms): cat/3619 openat(dfd: CWD, filename: 0xca71506b) = 3
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-epz6y9i0eavmerc5ha98t7gn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 29 +++++++++++++++++++++++++----
 1 file changed, 25 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 7deae6c8cb25..bcf882afd6d0 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2055,13 +2055,33 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 	if (trace->trace_syscalls)
 		fprintf(trace->output, "(         ): ");
 
+	if (evsel == trace->syscalls.events.augmented) {
+		int id = perf_evsel__sc_tp_uint(evsel, id, sample);
+		struct syscall *sc = trace__syscall_info(trace, evsel, id);
+
+		if (sc) {
+			struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+
+			if (thread) {
+				fprintf(trace->output, "%s(", sc->name);
+				trace__fprintf_sys_enter(trace, evsel, sample);
+				fputc(')', trace->output);
+				thread__put(thread);
+				goto newline;
+			}
+		}
+
+		/*
+		 * XXX: Not having the associated syscall info or not finding/adding
+		 * 	the thread should never happen, but if it does...
+		 * 	fall thru and print it as a bpf_output event.
+		 */
+	}
+
 	fprintf(trace->output, "%s:", evsel->name);
 
 	if (perf_evsel__is_bpf_output(evsel)) {
-		if (evsel == trace->syscalls.events.augmented)
-			trace__fprintf_sys_enter(trace, evsel, sample);
-		else
-			bpf_output__fprintf(trace, sample);
+		bpf_output__fprintf(trace, sample);
 	} else if (evsel->tp_format) {
 		if (strncmp(evsel->tp_format->name, "sys_enter_", 10) ||
 		    trace__fprintf_sys_enter(trace, evsel, sample)) {
@@ -2071,6 +2091,7 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 		}
 	}
 
+newline:
 	fprintf(trace->output, "\n");
 
 	if (callchain_ret > 0)
-- 
cgit v1.2.3


From 6dcbd212ff4988d8e6caa0b6700bd1c1d317dc02 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 21 Aug 2018 11:40:09 -0300
Subject: perf trace: Extract the comm/tid printing for syscall enter

Will be used with augmented syscalls, where we haven't transitioned
completely to combining sys_enter_FOO with sys_exit_FOO, so we'll go
as far as having it similar to the end result, strace like, as possible.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-canomaoiybkswwnhj69u9ae4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index bcf882afd6d0..92488edd00eb 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1144,11 +1144,9 @@ static void sig_handler(int sig)
 	interrupted = sig == SIGINT;
 }
 
-static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
-					u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
+static size_t trace__fprintf_comm_tid(struct trace *trace, struct thread *thread, FILE *fp)
 {
-	size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
-	printed += fprintf_duration(duration, duration_calculated, fp);
+	size_t printed = 0;
 
 	if (trace->multiple_threads) {
 		if (trace->show_comm)
@@ -1159,6 +1157,14 @@ static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thre
 	return printed;
 }
 
+static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
+					u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
+{
+	size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
+	printed += fprintf_duration(duration, duration_calculated, fp);
+	return printed + trace__fprintf_comm_tid(trace, thread, fp);
+}
+
 static int trace__process_event(struct trace *trace, struct machine *machine,
 				union perf_event *event, struct perf_sample *sample)
 {
-- 
cgit v1.2.3


From c96f4edcc3560a7dc910271d30d91c54a422d46c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 21 Aug 2018 11:47:44 -0300
Subject: perf trace: Show comm/tid for augmented_syscalls

To get us a bit more like the sys_enter + sys_exit combo:

  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
     0.000 (         ): openat(dfd: CWD, filename: 0x31b6dda8, flags: CLOEXEC)
     0.009 ( 0.009 ms): cat/3619 openat(dfd: CWD, filename: 0x31b6dda8, flags: CLOEXEC) = 3
     0.051 (         ): openat(dfd: CWD, filename: 0x31d75ce0, flags: CLOEXEC)
     0.054 ( 0.010 ms): cat/3619 openat(dfd: CWD, filename: 0x31d75ce0, flags: CLOEXEC) = 3
     0.539 (         ): openat(dfd: CWD, filename: 0xca71506b)
     0.543 ( 0.115 ms): cat/3619 openat(dfd: CWD, filename: 0xca71506b) = 3
  #

After:

  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
     0.000 (         ): cat/4919 openat(dfd: CWD, filename: 0xc8358da8, flags: CLOEXEC)
     0.007 ( 0.005 ms): cat/4919 openat(dfd: CWD, filename: 0xc8358da8, flags: CLOEXEC) = 3
     0.032 (         ): cat/4919 openat(dfd: CWD, filename: 0xc8560ce0, flags: CLOEXEC)
     0.033 ( 0.006 ms): cat/4919 openat(dfd: CWD, filename: 0xc8560ce0, flags: CLOEXEC) = 3
     0.301 (         ): cat/4919 openat(dfd: CWD, filename: 0x91fa306b)
     0.304 ( 0.004 ms): cat/4919 openat(dfd: CWD, filename: 0x91fa306b) = 3
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-6w8ytyo5y655a1hsyfpfily6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 92488edd00eb..e46ac9009172 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2069,6 +2069,7 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 			struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 
 			if (thread) {
+				trace__fprintf_comm_tid(trace, thread, trace->output);
 				fprintf(trace->output, "%s(", sc->name);
 				trace__fprintf_sys_enter(trace, evsel, sample);
 				fputc(')', trace->output);
-- 
cgit v1.2.3


From 75d1e30681d006f4dc148c153395fb938acfc7c0 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 21 Aug 2018 12:00:39 -0300
Subject: perf trace: Use the augmented filename, expanding syscall enter
 pointers

This is the final touch in showing how a syscall argument beautifier can
access the augmented args put in place by the
tools/perf/examples/bpf/augmented_syscalls.c eBPF script, right after
the regular raw syscall args, i.e. the up to 6 long integer values in
the syscall interface.

With this we are able to show the 'openat' syscall arg, now with up to
64 bytes, but in time this will be configurable, just like with the
'strace -s strsize' argument, from 'strace''s man page:

  -s strsize  Specify the maximum string size to print (the default is 32).

This actually is the maximum string to _collect_ and store in the ring
buffer, not just print.

Before:

  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
     0.000 (         ): cat/9658 openat(dfd: CWD, filename: 0x6626eda8, flags: CLOEXEC)
     0.017 ( 0.007 ms): cat/9658 openat(dfd: CWD, filename: 0x6626eda8, flags: CLOEXEC) = 3
     0.049 (         ): cat/9658 openat(dfd: CWD, filename: 0x66476ce0, flags: CLOEXEC)
     0.051 ( 0.007 ms): cat/9658 openat(dfd: CWD, filename: 0x66476ce0, flags: CLOEXEC) = 3
     0.377 (         ): cat/9658 openat(dfd: CWD, filename: 0x1e8f806b)
     0.379 ( 0.005 ms): cat/9658 openat(dfd: CWD, filename: 0x1e8f806b) = 3
  #

After:

  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
     0.000 (         ): cat/11966 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
     0.006 ( 0.006 ms): cat/11966 openat(dfd: CWD, filename: 0x4bfdcda8, flags: CLOEXEC) = 3
     0.034 (         ): cat/11966 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC)
     0.036 ( 0.008 ms): cat/11966 openat(dfd: CWD, filename: 0x4c1e4ce0, flags: CLOEXEC) = 3
     0.375 (         ): cat/11966 openat(dfd: CWD, filename: /etc/passwd)
     0.377 ( 0.005 ms): cat/11966 openat(dfd: CWD, filename: 0xe87906b) = 3
  #

This cset should show all the aspects of establishing a protocol between
an eBPF syscall arg augmenter program, tools/perf/examples/bpf/augmented_syscalls.c and
a 'perf trace' beautifier, the one associated with all 'char *' point
syscall args with names that can heuristically be associated with
filenames.

Now to wire up 'open' to show a second syscall using this scheme, all we
have to do now is to change tools/perf/examples/bpf/augmented_syscalls.c,
as 'perf trace' will notice that the perf_sample.raw_size is more than
what is expected for a particular syscall payload as defined by its
tracefs format file and will then use the augmented payload in the
'filename' syscall arg beautifier.

The same protocol will be used for structs such as 'struct sockaddr *',
'struct pollfd', etc, with additions for handling arrays.

This will all be done under the hood when 'perf trace' realizes the
system has the necessary components, and also can be done by providing
a precompiled augmented_syscalls.c eBPF ELF object.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-gj9kqb61wo7m3shtpzercbcr@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c                   | 10 ++++++++++
 tools/perf/examples/bpf/augmented_syscalls.c | 17 +++++++++++++----
 2 files changed, 23 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e46ac9009172..5d841114a745 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1097,11 +1097,21 @@ static void thread__set_filename_pos(struct thread *thread, const char *bf,
 	ttrace->filename.entry_str_pos = bf - ttrace->entry_str;
 }
 
+static size_t syscall_arg__scnprintf_augmented_string(struct syscall_arg *arg, char *bf, size_t size)
+{
+	struct augmented_arg *augmented_arg = arg->augmented.args;
+
+	return scnprintf(bf, size, "%.*s", augmented_arg->size, augmented_arg->value);
+}
+
 static size_t syscall_arg__scnprintf_filename(char *bf, size_t size,
 					      struct syscall_arg *arg)
 {
 	unsigned long ptr = arg->val;
 
+	if (arg->augmented.args)
+		return syscall_arg__scnprintf_augmented_string(arg, bf, size);
+
 	if (!arg->trace->vfs_getname)
 		return scnprintf(bf, size, "%#x", ptr);
 
diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index 10e7997ab481..93960e891478 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -27,6 +27,12 @@ struct bpf_map SEC("maps") __augmented_syscalls__ = {
        .max_entries = __NR_CPUS__,
 };
 
+struct augmented_filename {
+	int	size;
+	int	reserved;
+	char	value[256];
+};
+
 struct syscall_enter_openat_args {
 	unsigned long long common_tp_fields;
 	long		   syscall_nr;
@@ -38,17 +44,20 @@ struct syscall_enter_openat_args {
 
 struct augmented_enter_openat_args {
 	struct syscall_enter_openat_args args;
-	char				 filename[64];
+	struct augmented_filename	 filename;
 };
 
 int syscall_enter(openat)(struct syscall_enter_openat_args *args)
 {
-	struct augmented_enter_openat_args augmented_args;
+	struct augmented_enter_openat_args augmented_args = { .filename.reserved = 0, };
 
 	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
-	probe_read_str(&augmented_args.filename, sizeof(augmented_args.filename), args->filename_ptr);
+	augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
+						      sizeof(augmented_args.filename.value),
+						      args->filename_ptr);
 	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU,
-			  &augmented_args, sizeof(augmented_args));
+			  &augmented_args,
+			  sizeof(augmented_args) - sizeof(augmented_args.filename.value) + augmented_args.filename.size);
 	return 0;
 }
 
-- 
cgit v1.2.3


From daa1284af3b9a8d73b1dadaa12bc4068a4ce22ab Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 21 Aug 2018 12:20:06 -0300
Subject: perf trace: Augment the 'open' syscall 'filename' arg

As described in the previous cset, all we had to do was to touch the
augmented_syscalls.c eBPF program, fire up 'perf trace' with that new
eBPF script in system wide mode and wait for 'open' syscalls, in
addition to 'openat' ones to see that it works:

  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c
       0.000 StreamT~s #200/16150 openat(dfd: CWD, filename: /home/acme/.mozilla/firefox/fqxhj76d.default/prefs.js, flags: CREAT|EXCL|TRUNC|WRONLY, mode: IRUSR|IWUSR)
       0.065 StreamT~s #200/16150 openat(dfd: CWD, filename: /home/acme/.mozilla/firefox/fqxhj76d.default/prefs-1.js, flags: CREAT|EXCL|TRUNC|WRONLY, mode: IRUSR|IWUSR)
       0.435 StreamT~s #200/16150 openat(dfd: CWD, filename: /home/acme/.mozilla/firefox/fqxhj76d.default/prefs-1.js, flags: CREAT|TRUNC|WRONLY, mode: IRUSR|IWUSR)
       1.875 perf/16772 openat(dfd: CWD, filename: /sys/kernel/debug/tracing/events/syscalls/sys_enter_openat/form)
    1227.260 gnome-shell/1463 openat(dfd: CWD, filename: /proc/self/stat)
    1227.397 gnome-shell/2125 openat(dfd: CWD, filename: /proc/self/stat)
    7227.619 gnome-shell/1463 openat(dfd: CWD, filename: /proc/self/stat)
    7227.661 gnome-shell/2125 openat(dfd: CWD, filename: /proc/self/stat)
   10018.079 gnome-shell/1463 openat(dfd: CWD, filename: /proc/self/stat)
   10018.514 perf/16772 openat(dfd: CWD, filename: /proc/1237/status)
   10018.568 perf/16772 openat(dfd: CWD, filename: /proc/1237/status)
   10022.409 gnome-shell/2125 openat(dfd: CWD, filename: /proc/self/stat)
   10090.044 NetworkManager/1237 openat(dfd: CWD, filename: /proc/2125/stat)
   10090.351 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   10090.407 perf/16772 openat(dfd: CWD, filename: /sys/kernel/debug/tracing/events/syscalls/sys_enter_open/format)
   10091.763 NetworkManager/1237 openat(dfd: CWD, filename: /proc/2125/stat)
   10091.812 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   10092.807 NetworkManager/1237 openat(dfd: CWD, filename: /proc/2125/stat)
   10092.851 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   10094.650 NetworkManager/1237 openat(dfd: CWD, filename: /proc/1463/stat)
   10094.926 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   10096.010 NetworkManager/1237 openat(dfd: CWD, filename: /proc/1463/stat)
   10096.057 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   10097.056 NetworkManager/1237 openat(dfd: CWD, filename: /proc/1463/stat)
   10097.099 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   13228.345 gnome-shell/1463 openat(dfd: CWD, filename: /proc/self/stat)
   13232.734 gnome-shell/2125 openat(dfd: CWD, filename: /proc/self/stat)
   15198.956 lighttpd/16748 open(filename: /proc/loadavg, mode: ISGID|IXOTH)
  ^C#

It even catches 'perf' itself looking at the sys_enter_open and
sys_enter_openat tracefs format dictionaries when it first finds them in
the trace... :-)

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-upmogc57uatljr6el6u8537l@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/examples/bpf/augmented_syscalls.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index 93960e891478..154379463c95 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -61,4 +61,31 @@ int syscall_enter(openat)(struct syscall_enter_openat_args *args)
 	return 0;
 }
 
+struct syscall_enter_open_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	char		   *filename_ptr;
+	long		   flags;
+	long		   mode;
+};
+
+struct augmented_enter_open_args {
+	struct syscall_enter_open_args args;
+	struct augmented_filename      filename;
+};
+
+int syscall_enter(open)(struct syscall_enter_open_args *args)
+{
+	struct augmented_enter_open_args augmented_args = { .filename.reserved = 0, };
+
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
+	augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
+						      sizeof(augmented_args.filename.value),
+						      args->filename_ptr);
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU,
+			  &augmented_args,
+			  sizeof(augmented_args) - sizeof(augmented_args.filename.value) + augmented_args.filename.size);
+	return 0;
+}
+
 license(GPL);
-- 
cgit v1.2.3


From 9779fc021410e7d8433d923a2202dac7e1384b05 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 21 Aug 2018 13:21:36 -0300
Subject: perf trace: Augment inotify_add_watch pathname syscall arg

Again, just changing tools/perf/examples/bpf/augmented_syscalls.c, that
is starting to have too much boilerplate, some macro will come to the
rescue.

  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c
     0.000 gmain/2590 inotify_add_watch(fd: 3<anon_inode:inotify>, pathname: /var/cache/app-info/yaml, mask: 16789454)
     0.023 gmain/2590 inotify_add_watch(fd: 3<anon_inode:inotify>, pathname: /var/lib/app-info/xmls, mask: 16789454)
     0.028 gmain/2590 inotify_add_watch(fd: 3<anon_inode:inotify>, pathname: /var/lib/app-info/yaml, mask: 16789454)
     0.032 gmain/2590 inotify_add_watch(fd: 3<anon_inode:inotify>, pathname: /usr/share/app-info/yaml, mask: 16789454)
     0.039 gmain/2590 inotify_add_watch(fd: 3<anon_inode:inotify>, pathname: /usr/local/share/app-info/xmls, mask: 16789454)
     0.045 gmain/2590 inotify_add_watch(fd: 3<anon_inode:inotify>, pathname: /usr/local/share/app-info/yaml, mask: 16789454)
     0.049 gmain/2590 inotify_add_watch(fd: 3<anon_inode:inotify>, pathname: /home/acme/.local/share/app-info/yaml, mask: 16789454)
     0.056 gmain/2590 inotify_add_watch(fd: 3<anon_inode:inotify>, pathname: , mask: 16789454)
     0.010 gmain/2245 inotify_add_watch(fd: 7<anon_inode:inotify>, pathname: /home/acme/~, mask: 16789454)
     0.087 perf/20116 openat(dfd: CWD, filename: /sys/kernel/debug/tracing/events/syscalls/sys_enter_inotify_add)
     0.436 perf/20116 openat(dfd: CWD, filename: /sys/kernel/debug/tracing/events/syscalls/sys_enter_openat/form)
    56.042 gmain/2791 inotify_add_watch(fd: 4<anon_inode:inotify>, pathname: /var/lib/fwupd/remotes.d/lvfs-testing, mask: 16789454)
   113.986 gmain/1721 inotify_add_watch(fd: 3<anon_inode:inotify>, pathname: /var/lib/gdm/~, mask: 16789454)
  3777.265 gsd-color/2408 openat(dfd: CWD, filename: /etc/localtime)
  3777.550 gsd-color/2408 openat(dfd: CWD, filename: /etc/localtime)
^C[root@jouet perf]#

Still not combining raw_syscalls:sys_enter + raw_syscalls:sys_exit, to
get it strace-like, but that probably will come very naturally with some
more wiring up...

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ol83juin2cht9vzquynec5hz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/examples/bpf/augmented_syscalls.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index 154379463c95..6ec327850a15 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -88,4 +88,31 @@ int syscall_enter(open)(struct syscall_enter_open_args *args)
 	return 0;
 }
 
+struct syscall_enter_inotify_add_watch_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   fd;
+	char		   *pathname_ptr;
+	long		   mask;
+};
+
+struct augmented_enter_inotify_add_watch_args {
+	struct syscall_enter_inotify_add_watch_args args;
+	struct augmented_filename		    pathname;
+};
+
+int syscall_enter(inotify_add_watch)(struct syscall_enter_inotify_add_watch_args *args)
+{
+	struct augmented_enter_inotify_add_watch_args augmented_args = { .pathname.reserved = 0, };
+
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
+	augmented_args.pathname.size = probe_read_str(&augmented_args.pathname.value,
+						      sizeof(augmented_args.pathname.value),
+						      args->pathname_ptr);
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU,
+			  &augmented_args,
+			  sizeof(augmented_args) - sizeof(augmented_args.pathname.value) + augmented_args.pathname.size);
+	return 0;
+}
+
 license(GPL);
-- 
cgit v1.2.3


From f6618ce6c024ec90b156700fc39eb313ec117881 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 21 Aug 2018 13:44:49 -0300
Subject: perf trace: Introduce augmented_filename_syscall_enter() declarator

Helping with tons of boilerplate for syscalls that only want to augment
a filename. Now supporting one such syscall is just a matter of
declaring its arguments struct + using:

  augmented_filename_syscall_enter(openat);

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ls7ojdseu8fxw7fvj77ejpao@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/examples/bpf/augmented_syscalls.c | 78 ++++++++--------------------
 1 file changed, 23 insertions(+), 55 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index 6ec327850a15..e8486e8597de 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -33,6 +33,25 @@ struct augmented_filename {
 	char	value[256];
 };
 
+#define augmented_filename_syscall_enter(syscall) 							\
+struct augmented_enter_##syscall##_args {			 				\
+	struct syscall_enter_##syscall##_args	args;				 		\
+	struct augmented_filename		filename;				 	\
+};												\
+int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
+{												\
+	struct augmented_enter_##syscall##_args augmented_args = { .filename.reserved = 0, }; 	\
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);			\
+	augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, 		\
+						      sizeof(augmented_args.filename.value), 	\
+						      args->filename_ptr); 			\
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\
+			  &augmented_args, 							\
+			  (sizeof(augmented_args) - sizeof(augmented_args.filename.value) +	\
+			   augmented_args.filename.size));					\
+	return 0;										\
+}
+
 struct syscall_enter_openat_args {
 	unsigned long long common_tp_fields;
 	long		   syscall_nr;
@@ -42,24 +61,7 @@ struct syscall_enter_openat_args {
 	long		   mode;
 };
 
-struct augmented_enter_openat_args {
-	struct syscall_enter_openat_args args;
-	struct augmented_filename	 filename;
-};
-
-int syscall_enter(openat)(struct syscall_enter_openat_args *args)
-{
-	struct augmented_enter_openat_args augmented_args = { .filename.reserved = 0, };
-
-	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
-	augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
-						      sizeof(augmented_args.filename.value),
-						      args->filename_ptr);
-	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU,
-			  &augmented_args,
-			  sizeof(augmented_args) - sizeof(augmented_args.filename.value) + augmented_args.filename.size);
-	return 0;
-}
+augmented_filename_syscall_enter(openat);
 
 struct syscall_enter_open_args {
 	unsigned long long common_tp_fields;
@@ -69,50 +71,16 @@ struct syscall_enter_open_args {
 	long		   mode;
 };
 
-struct augmented_enter_open_args {
-	struct syscall_enter_open_args args;
-	struct augmented_filename      filename;
-};
-
-int syscall_enter(open)(struct syscall_enter_open_args *args)
-{
-	struct augmented_enter_open_args augmented_args = { .filename.reserved = 0, };
-
-	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
-	augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
-						      sizeof(augmented_args.filename.value),
-						      args->filename_ptr);
-	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU,
-			  &augmented_args,
-			  sizeof(augmented_args) - sizeof(augmented_args.filename.value) + augmented_args.filename.size);
-	return 0;
-}
+augmented_filename_syscall_enter(open);
 
 struct syscall_enter_inotify_add_watch_args {
 	unsigned long long common_tp_fields;
 	long		   syscall_nr;
 	long		   fd;
-	char		   *pathname_ptr;
+	char		   *filename_ptr;
 	long		   mask;
 };
 
-struct augmented_enter_inotify_add_watch_args {
-	struct syscall_enter_inotify_add_watch_args args;
-	struct augmented_filename		    pathname;
-};
-
-int syscall_enter(inotify_add_watch)(struct syscall_enter_inotify_add_watch_args *args)
-{
-	struct augmented_enter_inotify_add_watch_args augmented_args = { .pathname.reserved = 0, };
-
-	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
-	augmented_args.pathname.size = probe_read_str(&augmented_args.pathname.value,
-						      sizeof(augmented_args.pathname.value),
-						      args->pathname_ptr);
-	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU,
-			  &augmented_args,
-			  sizeof(augmented_args) - sizeof(augmented_args.pathname.value) + augmented_args.pathname.size);
-	return 0;
-}
+augmented_filename_syscall_enter(inotify_add_watch);
 
 license(GPL);
-- 
cgit v1.2.3


From 16cc63593f67477e9ca62f10182e74e949af1acb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 21 Aug 2018 13:55:50 -0300
Subject: perf trace: Augment 'newstat' (aka 'stat') filename ptr

This one will need some more work, that 'statbuf' pointer requires a
beautifier in 'perf trace'.

  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c
     0.000 weechat/3596 stat(filename: /etc/localtime, statbuf: 0x7ffd87d11f60)
     0.186 perf/29818 openat(dfd: CWD, filename: /sys/kernel/debug/tracing/events/syscalls/sys_enter_stat/format)
     0.279 perf/29818 openat(dfd: CWD, filename: /sys/kernel/debug/tracing/events/syscalls/sys_enter_newstat/for)
     0.670 perf/29818 openat(dfd: CWD, filename: /sys/kernel/debug/tracing/events/syscalls/sys_enter_openat/form)
    60.805 DNS Res~er #20/21308 stat(filename: /etc/resolv.conf, statbuf: 0x7ffa733fe4a0)
    60.836 DNS Res~er #20/21308 open(filename: /etc/hosts, flags: CLOEXEC)
    60.931 perf/29818 openat(dfd: CWD, filename: /sys/kernel/debug/tracing/events/syscalls/sys_enter_open/format)
   607.070 DNS Res~er #21/29812 stat(filename: /etc/resolv.conf, statbuf: 0x7ffa5e1fe3f0)
   607.098 DNS Res~er #21/29812 open(filename: /etc/hosts, flags: CLOEXEC)
   999.336 weechat/3596 stat(filename: /etc/localtime, statbuf: 0x7ffd87d11f60)
^C#

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-4lhabe7m4uzo76lnqpyfmnvk@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/examples/bpf/augmented_syscalls.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index e8486e8597de..a9695c7f7aab 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -83,4 +83,15 @@ struct syscall_enter_inotify_add_watch_args {
 
 augmented_filename_syscall_enter(inotify_add_watch);
 
+struct statbuf;
+
+struct syscall_enter_newstat_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	char		   *filename_ptr;
+	struct stat	   *statbuf;
+};
+
+augmented_filename_syscall_enter(newstat);
+
 license(GPL);
-- 
cgit v1.2.3


From 9ab5aadebeddc77fccfdf94a048259315ce95fe1 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 21 Aug 2018 15:02:09 -0300
Subject: perf trace: Add a etcsnoop.c augmented syscalls eBPF utility

We need to put common stuff into a separate header in tools/perf/include/bpf/
for these augmented syscalls, but I couldn't resist adding a etcsnoop.c tool,
combining augmented syscalls + filtering, that in the future will be passed
from 'perf trace''s command line, to use in building the eBPF program to do
that specific filtering at the source, inside the kernel:

  Running system wide: (hope there isn't any embarassing stuff here...  ;-) )

  # perf trace -e tools/perf/examples/bpf/etcsnoop.c
       0.000 sed/21878 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
    1741.473 cat/21883 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
    1741.892 cat/21883 openat(dfd: CWD, filename: /etc/passwd)
    1748.948 sed/21886 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
    1777.136 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1777.738 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1778.158 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1778.528 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1778.595 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1778.901 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1778.939 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1778.966 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1778.992 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.019 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.045 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.071 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.095 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.121 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.148 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.175 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.202 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.229 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.254 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.279 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.309 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.336 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.363 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.388 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.414 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.442 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.470 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.500 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.529 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.557 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.586 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.617 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.648 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.679 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.706 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.739 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.769 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.798 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.823 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.844 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.862 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.880 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.911 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.942 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1779.972 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1780.004 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
    1780.035 gvfs-udisks2-v/2302 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
   13059.154 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   13060.739 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   13061.990 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   13063.177 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   13064.265 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   13065.483 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   13067.383 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   13068.902 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   13069.922 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   13070.915 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   13072.612 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   13074.816 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   13077.343 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   13078.731 NetworkManager/1237 open(filename: /etc/passwd, flags: CLOEXEC)
   13559.064 DNS Res~er #22/21054 open(filename: /etc/hosts, flags: CLOEXEC)
   22419.522 sed/21896 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   24473.313 git/21900 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   24491.988 less/21901 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   24493.793 git/21901 openat(dfd: CWD, filename: /etc/sysless)
   24565.772 sed/21924 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   25878.752 git/21928 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   26075.666 git/21928 open(filename: /etc/localtime, flags: CLOEXEC)
   26075.565 less/21929 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   26076.060 less/21929 openat(dfd: CWD, filename: /etc/sysless)
   26346.395 sed/21932 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   26483.583 sed/21938 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   26954.890 sed/21944 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   27016.165 gsd-color/1762 openat(dfd: CWD, filename: /etc/localtime)
   27016.414 gsd-color/1762 openat(dfd: CWD, filename: /etc/localtime)
   27712.313 gsd-color/2408 openat(dfd: CWD, filename: /etc/localtime)
   27712.616 gsd-color/2408 openat(dfd: CWD, filename: /etc/localtime)
   27829.035 gnome-shell/2125 openat(dfd: CWD, filename: /etc/localtime)
   27829.368 gnome-shell/2125 openat(dfd: CWD, filename: /etc/localtime)
   27829.584 gnome-shell/2125 openat(dfd: CWD, filename: /etc/localtime)
   27829.800 gnome-shell/2125 openat(dfd: CWD, filename: /etc/localtime)
   27830.107 gnome-shell/2125 openat(dfd: CWD, filename: /etc/localtime)
   27830.521 gnome-shell/2125 openat(dfd: CWD, filename: /etc/localtime)
   27961.516 git/21948 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   27987.568 less/21949 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   27988.948 bash/21949 openat(dfd: CWD, filename: /etc/sysless)
   28043.536 sed/21972 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   28736.008 sed/21978 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   34882.664 git/21991 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   34882.664 sort/21990 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   34884.441 uniq/21992 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   35593.098 git/21997 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   35638.839 git/21997 openat(dfd: CWD, filename: /etc/gitattributes)
   35702.851 sed/22000 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   36076.039 sed/22006 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   37569.049 git/22014 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   37673.712 git/22014 open(filename: /etc/localtime, flags: CLOEXEC)
   37781.710 vim/22040 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   37783.667 git/22040 openat(dfd: CWD, filename: /etc/vimrc)
   37792.394 git/22040 open(filename: /etc/nsswitch.conf, flags: CLOEXEC)
   37792.436 git/22040 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   37792.580 git/22040 open(filename: /etc/passwd, flags: CLOEXEC)
   43893.625 DNS Res~er #23/21365 open(filename: /etc/hosts, flags: CLOEXEC)
   48060.409 nm-dhcp-helper/22044 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48071.745 systemd/1 openat(dfd: CWD, filename: /etc/systemd/system/dbus-org.freedesktop.nm-dispatcher.service, flags: CLOEXEC|NOFOLLOW|NOCTTY)
   48082.780 nm-dispatcher/22049 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48111.418 systemd/22049 open(filename: /etc/NetworkManager/dispatcher.d, flags: CLOEXEC|DIRECTORY|NONBLOCK)
   48111.904 systemd/22049 open(filename: /etc/localtime, flags: CLOEXEC)
   48118.357 00-netreport/22052 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48119.668 systemd/22052 open(filename: /etc/nsswitch.conf, flags: CLOEXEC)
   48119.762 systemd/22052 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48119.887 systemd/22052 open(filename: /etc/passwd, flags: CLOEXEC)
   48120.025 systemd/22052 openat(dfd: CWD, filename: /etc/NetworkManager/dispatcher.d/00-netreport)
   48124.144 hostname/22054 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48125.492 systemd/22052 openat(dfd: CWD, filename: /etc/init.d/functions)
   48127.253 systemd/22052 openat(dfd: CWD, filename: /etc/profile.d/lang.sh)
   48127.388 systemd/22052 openat(dfd: CWD, filename: /etc/locale.conf)
   48137.749 cat/22056 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48143.519 04-iscsi/22058 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48144.438 04-iscsi/22058 open(filename: /etc/nsswitch.conf, flags: CLOEXEC)
   48144.478 04-iscsi/22058 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48144.577 04-iscsi/22058 open(filename: /etc/passwd, flags: CLOEXEC)
   48144.819 04-iscsi/22058 openat(dfd: CWD, filename: /etc/NetworkManager/dispatcher.d/04-iscsi)
   48145.620 10-ifcfg-rh-ro/22059 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48146.169 systemd/22059 open(filename: /etc/nsswitch.conf, flags: CLOEXEC)
   48146.207 systemd/22059 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48146.287 systemd/22059 open(filename: /etc/passwd, flags: CLOEXEC)
   48146.387 systemd/22059 openat(dfd: CWD, filename: /etc/NetworkManager/dispatcher.d/10-ifcfg-rh-routes.sh)
   48147.215 11-dhclient/22060 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48147.787 11-dhclient/22060 open(filename: /etc/nsswitch.conf, flags: CLOEXEC)
   48147.813 11-dhclient/22060 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48147.929 11-dhclient/22060 open(filename: /etc/passwd, flags: CLOEXEC)
   48148.016 11-dhclient/22060 openat(dfd: CWD, filename: /etc/NetworkManager/dispatcher.d/11-dhclient)
   48148.906 grep/22063 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48151.165 11-dhclient/22060 openat(dfd: CWD, filename: /etc/sysconfig/network)
   48151.560 11-dhclient/22060 open(filename: /etc/dhcp/dhclient.d/, flags: CLOEXEC|DIRECTORY|NONBLOCK)
   48151.704 11-dhclient/22060 openat(dfd: CWD, filename: /etc/dhcp/dhclient.d/chrony.sh)
   48153.593 20-chrony/22065 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48154.695 20-chrony/22065 open(filename: /etc/nsswitch.conf, flags: CLOEXEC)
   48154.756 20-chrony/22065 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48154.914 20-chrony/22065 open(filename: /etc/passwd, flags: CLOEXEC)
   48155.067 20-chrony/22065 openat(dfd: CWD, filename: /etc/NetworkManager/dispatcher.d/20-chrony)
   48156.962 25-polipo/22066 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48157.824 systemd/22066 open(filename: /etc/nsswitch.conf, flags: CLOEXEC)
   48157.866 systemd/22066 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
   48157.981 systemd/22066 open(filename: /etc/passwd, flags: CLOEXEC)
   48158.090 systemd/22066 openat(dfd: CWD, filename: /etc/NetworkManager/dispatcher.d/25-polipo)
   48533.616 gsd-housekeepi/2412 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC)
   87122.021 gsd-color/1762 openat(dfd: CWD, filename: /etc/localtime)
   87122.146 gsd-color/1762 openat(dfd: CWD, filename: /etc/localtime)
   87825.582 gsd-color/2408 openat(dfd: CWD, filename: /etc/localtime)
   87825.844 gsd-color/2408 openat(dfd: CWD, filename: /etc/localtime)
   87829.524 gnome-shell/2125 openat(dfd: CWD, filename: /etc/localtime)
   87830.531 gnome-shell/2125 openat(dfd: CWD, filename: /etc/localtime)
   87831.288 gnome-shell/2125 openat(dfd: CWD, filename: /etc/localtime)
   87832.011 gnome-shell/2125 openat(dfd: CWD, filename: /etc/localtime)
   87832.672 gnome-shell/2125 openat(dfd: CWD, filename: /etc/localtime)
   87833.276 gnome-shell/2125 openat(dfd: CWD, filename: /etc/localtime)
   ^C#

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-0o770jvdcy04ee6vhv6v471m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/examples/bpf/etcsnoop.c | 80 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 80 insertions(+)
 create mode 100644 tools/perf/examples/bpf/etcsnoop.c

(limited to 'tools')

diff --git a/tools/perf/examples/bpf/etcsnoop.c b/tools/perf/examples/bpf/etcsnoop.c
new file mode 100644
index 000000000000..b59e8812ee8c
--- /dev/null
+++ b/tools/perf/examples/bpf/etcsnoop.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Augment the filename syscalls with the contents of the filename pointer argument
+ * filtering only those that do not start with /etc/.
+ *
+ * Test it with:
+ *
+ * perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null
+ *
+ * It'll catch some openat syscalls related to the dynamic linked and
+ * the last one should be the one for '/etc/passwd'.
+ *
+ * This matches what is marshalled into the raw_syscall:sys_enter payload
+ * expected by the 'perf trace' beautifiers, and can be used by them unmodified,
+ * which will be done as that feature is implemented in the next csets, for now
+ * it will appear in a dump done by the default tracepoint handler in 'perf trace',
+ * that uses bpf_output__fprintf() to just dump those contents, as done with
+ * the bpf-output event associated with the __bpf_output__ map declared in
+ * tools/perf/include/bpf/stdio.h.
+ */
+
+#include <stdio.h>
+
+struct bpf_map SEC("maps") __augmented_syscalls__ = {
+       .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+       .key_size = sizeof(int),
+       .value_size = sizeof(u32),
+       .max_entries = __NR_CPUS__,
+};
+
+struct augmented_filename {
+	int	size;
+	int	reserved;
+	char	value[64];
+};
+
+#define augmented_filename_syscall_enter(syscall) 						\
+struct augmented_enter_##syscall##_args {			 				\
+	struct syscall_enter_##syscall##_args	args;				 		\
+	struct augmented_filename		filename;				 	\
+};												\
+int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
+{												\
+	char etc[6] = "/etc/";									\
+	struct augmented_enter_##syscall##_args augmented_args = { .filename.reserved = 0, }; 	\
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);			\
+	augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, 		\
+						      sizeof(augmented_args.filename.value), 	\
+						      args->filename_ptr); 			\
+	if (__builtin_memcmp(augmented_args.filename.value, etc, 4) != 0)			\
+		return 0;									\
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\
+			  &augmented_args, 							\
+			  (sizeof(augmented_args) - sizeof(augmented_args.filename.value) +	\
+			   augmented_args.filename.size));					\
+	return 0;										\
+}
+
+struct syscall_enter_openat_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   dfd;
+	char		   *filename_ptr;
+	long		   flags;
+	long		   mode;
+};
+
+augmented_filename_syscall_enter(openat);
+
+struct syscall_enter_open_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	char		   *filename_ptr;
+	long		   flags;
+	long		   mode;
+};
+
+augmented_filename_syscall_enter(open);
+
+license(GPL);
-- 
cgit v1.2.3


From d35b168c3dcdf103c2b2d694ad8513a669781703 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 29 Aug 2018 23:53:22 -0300
Subject: perf bpf: Give precedence to bpf header dir

I need to check the need for $KERNEL_INC_OPTIONS when building eBPF
restricted C programs, for now just give precedence to
$PERF_BPF_INC_OPTIONS so that we can get a linux/socket.h usable
in eBPF programs.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-5z7qw529sdebrn9y1xxqw9hf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/llvm-utils.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 19262f98cd4e..5b0b60f00275 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -19,7 +19,7 @@
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
 		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
 		"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "	\
-		"$CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS " \
+		"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
 		"-Wno-unused-value -Wno-pointer-sign "		\
 		"-working-directory $WORKING_DIR "		\
 		"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
-- 
cgit v1.2.3


From 403f833d15a33bfd8e50dd79fa8e25fb4aa132f6 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 29 Aug 2018 17:41:53 -0300
Subject: perf bpf: Add linux/socket.h to the headers accessible to bpf
 proggies

So that we don't have to define sockaddr_storage in the
augmented_syscalls.c bpf example when hooking into syscalls needing it,
idea is to mimic the system headers. Eventually we probably need to have
sys/socket.h, etc.  Start by having at least linux/socket.h.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-yhzarcvsjue8pgpvkjhqgioc@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.perf              |  4 +++-
 tools/perf/include/bpf/linux/socket.h | 24 ++++++++++++++++++++++++
 2 files changed, 27 insertions(+), 1 deletion(-)
 create mode 100644 tools/perf/include/bpf/linux/socket.h

(limited to 'tools')

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5224ade3d5af..92514fb3689f 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -779,7 +779,9 @@ endif
 ifndef NO_LIBBPF
 	$(call QUIET_INSTALL, bpf-headers) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
-		$(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'; \
+		$(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
+		$(INSTALL) include/bpf/linux/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'
 	$(call QUIET_INSTALL, bpf-examples) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \
 		$(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
diff --git a/tools/perf/include/bpf/linux/socket.h b/tools/perf/include/bpf/linux/socket.h
new file mode 100644
index 000000000000..7f844568dab8
--- /dev/null
+++ b/tools/perf/include/bpf/linux/socket.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_SOCKET_H
+#define _UAPI_LINUX_SOCKET_H
+
+/*
+ * Desired design of maximum size and alignment (see RFC2553)
+ */
+#define _K_SS_MAXSIZE	128	/* Implementation specific max size */
+#define _K_SS_ALIGNSIZE	(__alignof__ (struct sockaddr *))
+				/* Implementation specific desired alignment */
+
+typedef unsigned short __kernel_sa_family_t;
+
+struct __kernel_sockaddr_storage {
+	__kernel_sa_family_t	ss_family;		/* address family */
+	/* Following field(s) are implementation specific */
+	char		__data[_K_SS_MAXSIZE - sizeof(unsigned short)];
+				/* space to achieve desired size, */
+				/* _SS_MAXSIZE value minus size of ss_family */
+} __attribute__ ((aligned(_K_SS_ALIGNSIZE)));	/* force desired alignment */
+
+#define sockaddr_storage __kernel_sockaddr_storage
+
+#endif /* _UAPI_LINUX_SOCKET_H */
-- 
cgit v1.2.3


From d5a7e6613b00d46a4971e8b69e18e2cfd7b00df3 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 28 Aug 2018 16:24:44 -0300
Subject: perf trace augmented_syscalls: Augment connect's 'sockaddr' arg

As the first example of augmenting something other than a 'filename',
augment the 'struct sockaddr' argument for the 'connect' syscall:

  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c ssh -6 fedorapeople.org
     0.000 ssh/29669 connect(fd: 3, uservaddr: { .family: LOCAL, path: /var/run/nscd/socket }, addrlen: 110)
     0.042 ssh/29669 connect(fd: 3, uservaddr: { .family: LOCAL, path: /var/run/nscd/socket }, addrlen: 110)
     1.329 ssh/29669 connect(fd: 3, uservaddr: { .family: LOCAL, path: /var/run/nscd/socket }, addrlen: 110)
     1.362 ssh/29669 connect(fd: 3, uservaddr: { .family: LOCAL, path: /var/run/nscd/socket }, addrlen: 110)
     1.458 ssh/29669 connect(fd: 3, uservaddr: { .family: LOCAL, path: /var/run/nscd/socket }, addrlen: 110)
     1.478 ssh/29669 connect(fd: 3, uservaddr: { .family: LOCAL, path: /var/run/nscd/socket }, addrlen: 110)
     1.683 ssh/29669 connect(fd: 3<socket:[125942]>, uservaddr: { .family: INET, port: 53, addr: 192.168.43.1 }, addrlen: 16)
     4.710 ssh/29669 connect(fd: 3<socket:[125942]>, uservaddr: { .family: INET6, port: 22, addr: 2610:28:3090:3001:5054:ff:fea7:9474 }, addrlen: 28)
  root@fedorapeople.org: Permission denied (publickey).
  #

This is still just augmenting the syscalls:sys_enter_connect part, later
we'll wire this up to augment the enter+exit combo, like in the
tradicional 'perf trace' and 'strace' outputs.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-s7l541cbiqb22ifio6z7dpf6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c                   | 12 +-----
 tools/perf/examples/bpf/augmented_syscalls.c | 34 +++++++++++++++-
 tools/perf/trace/beauty/Build                |  1 +
 tools/perf/trace/beauty/beauty.h             |  5 +++
 tools/perf/trace/beauty/sockaddr.c           | 58 ++++++++++++++++++++++++++++
 5 files changed, 99 insertions(+), 11 deletions(-)
 create mode 100644 tools/perf/trace/beauty/sockaddr.c

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 5d841114a745..ab2ed30b8dcc 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -498,16 +498,6 @@ static const char *clockid[] = {
 };
 static DEFINE_STRARRAY(clockid);
 
-static const char *socket_families[] = {
-	"UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM",
-	"BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI",
-	"SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC",
-	"RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC",
-	"BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF",
-	"ALG", "NFC", "VSOCK",
-};
-static DEFINE_STRARRAY(socket_families);
-
 static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size,
 						 struct syscall_arg *arg)
 {
@@ -645,6 +635,8 @@ static struct syscall_fmt {
 		   [4] = { .name = "tls",	    .scnprintf = SCA_HEX, }, }, },
 	{ .name	    = "close",
 	  .arg = { [0] = { .scnprintf = SCA_CLOSE_FD, /* fd */ }, }, },
+	{ .name	    = "connect",
+	  .arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* servaddr */ }, }, },
 	{ .name	    = "epoll_ctl",
 	  .arg = { [1] = STRARRAY(op, epoll_ctl_ops), }, },
 	{ .name	    = "eventfd2",
diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index a9695c7f7aab..6dfead0be74e 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -19,6 +19,7 @@
  */
 
 #include <stdio.h>
+#include <linux/socket.h>
 
 struct bpf_map SEC("maps") __augmented_syscalls__ = {
        .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
@@ -33,7 +34,7 @@ struct augmented_filename {
 	char	value[256];
 };
 
-#define augmented_filename_syscall_enter(syscall) 							\
+#define augmented_filename_syscall_enter(syscall)						\
 struct augmented_enter_##syscall##_args {			 				\
 	struct syscall_enter_##syscall##_args	args;				 		\
 	struct augmented_filename		filename;				 	\
@@ -94,4 +95,35 @@ struct syscall_enter_newstat_args {
 
 augmented_filename_syscall_enter(newstat);
 
+struct sockaddr;
+
+struct syscall_enter_connect_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   fd;
+	struct sockaddr	   *addr_ptr;
+	unsigned long	   addrlen;
+};
+
+struct augmented_enter_connect_args {
+	struct syscall_enter_connect_args args;
+	struct sockaddr_storage		  addr;
+};
+
+int syscall_enter(connect)(struct syscall_enter_connect_args *args)
+{
+	struct augmented_enter_connect_args augmented_args;
+	unsigned long addrlen = sizeof(augmented_args.addr);
+
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
+#ifdef FIXME_CLANG_OPTIMIZATION_THAT_ACCESSES_USER_CONTROLLED_ADDRLEN_DESPITE_THIS_CHECK
+	if (addrlen > augmented_args.args.addrlen)
+		addrlen = augmented_args.args.addrlen;
+#endif
+	probe_read(&augmented_args.addr, addrlen, args->addr_ptr); 
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, 
+			  sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen);
+	return 0;
+}
+
 license(GPL);
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index f528ba35e140..c3b0afd67760 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -7,5 +7,6 @@ endif
 libperf-y += kcmp.o
 libperf-y += pkey_alloc.o
 libperf-y += prctl.o
+libperf-y += sockaddr.o
 libperf-y += socket.o
 libperf-y += statx.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 6ca044d3d851..2570152d3909 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -30,6 +30,8 @@ struct thread;
 
 size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_t size);
 
+extern struct strarray strarray__socket_families;
+
 /**
  * augmented_arg: extra payload for syscall pointer arguments
  
@@ -135,6 +137,9 @@ size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_a
 size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3
 
+size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_SOCKADDR syscall_arg__scnprintf_sockaddr
+
 size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol
 
diff --git a/tools/perf/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c
new file mode 100644
index 000000000000..3944a7d54d3c
--- /dev/null
+++ b/tools/perf/trace/beauty/sockaddr.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+
+#include "trace/beauty/beauty.h"
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <arpa/inet.h>
+
+static const char *socket_families[] = {
+	"UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM",
+	"BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI",
+	"SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC",
+	"RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC",
+	"BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF",
+	"ALG", "NFC", "VSOCK",
+};
+DEFINE_STRARRAY(socket_families);
+
+static size_t syscall_arg__scnprintf_augmented_sockaddr(struct syscall_arg *arg, char *bf, size_t size)
+{
+	struct sockaddr_in *sin = (struct sockaddr_in *)arg->augmented.args;
+	char family[32];
+	size_t printed;
+
+	strarray__scnprintf(&strarray__socket_families, family, sizeof(family), "%d", sin->sin_family);
+	printed = scnprintf(bf, size, "{ .family: %s", family);
+
+	if (sin->sin_family == AF_INET) {
+		char tmp[512];
+		printed += scnprintf(bf + printed, size - printed, ", port: %d, addr: %s", ntohs(sin->sin_port),
+				     inet_ntop(sin->sin_family, &sin->sin_addr, tmp, sizeof(tmp)));
+	} else if (sin->sin_family == AF_INET6) {
+		struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sin;
+		u32 flowinfo = ntohl(sin6->sin6_flowinfo);
+		char tmp[512];
+
+		printed += scnprintf(bf + printed, size - printed, ", port: %d, addr: %s", ntohs(sin6->sin6_port),
+				     inet_ntop(sin6->sin6_family, &sin6->sin6_addr, tmp, sizeof(tmp)));
+		if (flowinfo != 0)
+			printed += scnprintf(bf + printed, size - printed, ", flowinfo: %lu", flowinfo);
+		if (sin6->sin6_scope_id != 0)
+			printed += scnprintf(bf + printed, size - printed, ", scope_id: %lu", sin6->sin6_scope_id);
+	} else if (sin->sin_family == AF_LOCAL) {
+		struct sockaddr_un *sun = (struct sockaddr_un *)sin;
+		printed += scnprintf(bf + printed, size - printed, ", path: %s", sun->sun_path);
+	}
+
+	return printed + scnprintf(bf + printed, size - printed, " }");
+}
+
+size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg *arg)
+{
+	if (arg->augmented.args)
+		return syscall_arg__scnprintf_augmented_sockaddr(arg, bf, size);
+
+	return scnprintf(bf, size, "%#x", arg->val);
+}
-- 
cgit v1.2.3


From 24a6c2cd1dbd85bd5624a6d0b05de891d0f07696 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 28 Aug 2018 16:39:11 -0300
Subject: perf trace augmented_syscalls: Add augmented_sockaddr_syscall_enter()

From the one for 'connect', so that we can use it with sendto and others
that receive a 'struct sockaddr'.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-8bdqv1q0ndcjl1nqns5r5je2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/examples/bpf/augmented_syscalls.c | 46 ++++++++++++++++------------
 1 file changed, 26 insertions(+), 20 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index 6dfead0be74e..5f417e528419 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -95,6 +95,31 @@ struct syscall_enter_newstat_args {
 
 augmented_filename_syscall_enter(newstat);
 
+#ifndef _K_SS_MAXSIZE
+#define _K_SS_MAXSIZE 128
+#endif
+
+#define augmented_sockaddr_syscall_enter(syscall)						\
+struct augmented_enter_##syscall##_args {			 				\
+	struct syscall_enter_##syscall##_args	args;				 		\
+	struct sockaddr_storage			addr;						\
+};												\
+int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
+{												\
+	struct augmented_enter_##syscall##_args augmented_args;				 	\
+	unsigned long addrlen = sizeof(augmented_args.addr);					\
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);			\
+/* FIXME_CLANG_OPTIMIZATION_THAT_ACCESSES_USER_CONTROLLED_ADDRLEN_DESPITE_THIS_CHECK */		\
+/*	if (addrlen > augmented_args.args.addrlen)				     */		\
+/*		addrlen = augmented_args.args.addrlen;				     */		\
+/*										     */		\
+	probe_read(&augmented_args.addr, addrlen, args->addr_ptr); 				\
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\
+			  &augmented_args, 							\
+			  sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen);	\
+	return 0;										\
+}
+
 struct sockaddr;
 
 struct syscall_enter_connect_args {
@@ -105,25 +130,6 @@ struct syscall_enter_connect_args {
 	unsigned long	   addrlen;
 };
 
-struct augmented_enter_connect_args {
-	struct syscall_enter_connect_args args;
-	struct sockaddr_storage		  addr;
-};
-
-int syscall_enter(connect)(struct syscall_enter_connect_args *args)
-{
-	struct augmented_enter_connect_args augmented_args;
-	unsigned long addrlen = sizeof(augmented_args.addr);
-
-	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
-#ifdef FIXME_CLANG_OPTIMIZATION_THAT_ACCESSES_USER_CONTROLLED_ADDRLEN_DESPITE_THIS_CHECK
-	if (addrlen > augmented_args.args.addrlen)
-		addrlen = augmented_args.args.addrlen;
-#endif
-	probe_read(&augmented_args.addr, addrlen, args->addr_ptr); 
-	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, 
-			  sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen);
-	return 0;
-}
+augmented_sockaddr_syscall_enter(connect);
 
 license(GPL);
-- 
cgit v1.2.3


From 02ef288420775542316e41dc610a6a88725aa83a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 28 Aug 2018 17:03:53 -0300
Subject: perf trace augmented_syscalls: Augment bind's 'myaddr' sockaddr arg

One more, to reuse the augmented_sockaddr_syscall_enter() macro
introduced from the augmentation of connect's sockaddr arg, also to get
a subset of the struct arg augmentations done using the manual method,
before switching to something automatic, using tracefs's format file or,
even better, BTF containing the syscall args structs.

  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c
     0.000 sshd/11479 bind(fd: 3<socket:[170336]>, umyaddr: { .family: NETLINK }, addrlen: 12)
     1.752 sshd/11479 bind(fd: 3<socket:[170336]>, umyaddr: { .family: INET, port: 22, addr: 0.0.0.0 }, addrlen: 16)
     1.924 sshd/11479 bind(fd: 4<socket:[170338]>, umyaddr: { .family: INET6, port: 22, addr: :: }, addrlen: 28)
  ^C#

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-a2drqpahpmc7uwb3n3gj2plu@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c                   |  2 ++
 tools/perf/examples/bpf/augmented_syscalls.c | 10 ++++++++++
 2 files changed, 12 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index ab2ed30b8dcc..537bb30895df 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -621,6 +621,8 @@ static struct syscall_fmt {
 } syscall_fmts[] = {
 	{ .name	    = "access",
 	  .arg = { [1] = { .scnprintf = SCA_ACCMODE,  /* mode */ }, }, },
+	{ .name	    = "bind",
+	  .arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* umyaddr */ }, }, },
 	{ .name	    = "bpf",
 	  .arg = { [0] = STRARRAY(cmd, bpf_cmd), }, },
 	{ .name	    = "brk",	    .hexret = true,
diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index 5f417e528419..71edb7ad8698 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -122,6 +122,16 @@ int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
 
 struct sockaddr;
 
+struct syscall_enter_bind_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   fd;
+	struct sockaddr	   *addr_ptr;
+	unsigned long	   addrlen;
+};
+
+augmented_sockaddr_syscall_enter(bind);
+
 struct syscall_enter_connect_args {
 	unsigned long long common_tp_fields;
 	long		   syscall_nr;
-- 
cgit v1.2.3


From 6ebb686225a83200b94777cfc651c94f4e0f6f50 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 29 Aug 2018 08:47:08 -0300
Subject: perf trace augmented_syscalls: Augment sendto's 'addr' arg

Its a 'struct sockaddr' pointer, augment it with the same beautifier as
for 'connect' and 'bind', that all receive from userspace that pointer.

Doing it in the other direction remains to be done, hooking at the
syscalls:sys_exit_{accept4?,recvmsg} tracepoints somehow.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-k2eu68lsphnm2fthc32gq76c@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c                   |  3 ++-
 tools/perf/examples/bpf/augmented_syscalls.c | 13 +++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 537bb30895df..759d14e3fe6b 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -795,7 +795,8 @@ static struct syscall_fmt {
 	{ .name	    = "sendmsg",
 	  .arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
 	{ .name	    = "sendto",
-	  .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
+	  .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ },
+		   [4] = { .scnprintf = SCA_SOCKADDR, /* addr */ }, }, },
 	{ .name	    = "set_tid_address", .errpid = true, },
 	{ .name	    = "setitimer",
 	  .arg = { [0] = STRARRAY(which, itimers), }, },
diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index 71edb7ad8698..be06d2c9e8c9 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -142,4 +142,17 @@ struct syscall_enter_connect_args {
 
 augmented_sockaddr_syscall_enter(connect);
 
+struct syscall_enter_sendto_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   fd;
+	void		   *buff;
+	long		   len;
+	unsigned long	   flags;
+	struct sockaddr	   *addr_ptr;
+	long		   addr_len;
+};
+
+augmented_sockaddr_syscall_enter(sendto);
+
 license(GPL);
-- 
cgit v1.2.3


From b043cb524d2892be75c78bc348e83863829d50a0 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 29 Aug 2018 17:11:33 -0300
Subject: perf trace beauty: Reorganize 'struct sockaddr *' beautifier

Use an array to multiplex by sockaddr->sa_family, this way adding new
families gets a bit easier and tidy.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-v3s85ra659tc40g1s1xaqoun@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/sockaddr.c | 60 +++++++++++++++++++++++++-------------
 1 file changed, 39 insertions(+), 21 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c
index 3944a7d54d3c..71a79f72d9d9 100644
--- a/tools/perf/trace/beauty/sockaddr.c
+++ b/tools/perf/trace/beauty/sockaddr.c
@@ -17,34 +17,52 @@ static const char *socket_families[] = {
 };
 DEFINE_STRARRAY(socket_families);
 
+static size_t af_inet__scnprintf(struct sockaddr *sa, char *bf, size_t size)
+{
+	struct sockaddr_in *sin = (struct sockaddr_in *)sa;
+	char tmp[16];
+	return scnprintf(bf, size, ", port: %d, addr: %s", ntohs(sin->sin_port),
+			 inet_ntop(sin->sin_family, &sin->sin_addr, tmp, sizeof(tmp)));
+}
+
+static size_t af_inet6__scnprintf(struct sockaddr *sa, char *bf, size_t size)
+{
+	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sa;
+	u32 flowinfo = ntohl(sin6->sin6_flowinfo);
+	char tmp[512];
+	size_t printed = scnprintf(bf, size, ", port: %d, addr: %s", ntohs(sin6->sin6_port),
+				   inet_ntop(sin6->sin6_family, &sin6->sin6_addr, tmp, sizeof(tmp)));
+	if (flowinfo != 0)
+		printed += scnprintf(bf + printed, size - printed, ", flowinfo: %lu", flowinfo);
+	if (sin6->sin6_scope_id != 0)
+		printed += scnprintf(bf + printed, size - printed, ", scope_id: %lu", sin6->sin6_scope_id);
+
+	return printed;
+}
+
+static size_t af_local__scnprintf(struct sockaddr *sa, char *bf, size_t size)
+{
+	struct sockaddr_un *sun = (struct sockaddr_un *)sa;
+	return scnprintf(bf, size, ", path: %s", sun->sun_path);
+}
+
+static size_t (*af_scnprintfs[])(struct sockaddr *sa, char *bf, size_t size) = {
+	[AF_LOCAL] = af_local__scnprintf,
+	[AF_INET]  = af_inet__scnprintf,
+	[AF_INET6] = af_inet6__scnprintf,
+};
+
 static size_t syscall_arg__scnprintf_augmented_sockaddr(struct syscall_arg *arg, char *bf, size_t size)
 {
-	struct sockaddr_in *sin = (struct sockaddr_in *)arg->augmented.args;
+	struct sockaddr *sa = (struct sockaddr *)arg->augmented.args;
 	char family[32];
 	size_t printed;
 
-	strarray__scnprintf(&strarray__socket_families, family, sizeof(family), "%d", sin->sin_family);
+	strarray__scnprintf(&strarray__socket_families, family, sizeof(family), "%d", sa->sa_family);
 	printed = scnprintf(bf, size, "{ .family: %s", family);
 
-	if (sin->sin_family == AF_INET) {
-		char tmp[512];
-		printed += scnprintf(bf + printed, size - printed, ", port: %d, addr: %s", ntohs(sin->sin_port),
-				     inet_ntop(sin->sin_family, &sin->sin_addr, tmp, sizeof(tmp)));
-	} else if (sin->sin_family == AF_INET6) {
-		struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sin;
-		u32 flowinfo = ntohl(sin6->sin6_flowinfo);
-		char tmp[512];
-
-		printed += scnprintf(bf + printed, size - printed, ", port: %d, addr: %s", ntohs(sin6->sin6_port),
-				     inet_ntop(sin6->sin6_family, &sin6->sin6_addr, tmp, sizeof(tmp)));
-		if (flowinfo != 0)
-			printed += scnprintf(bf + printed, size - printed, ", flowinfo: %lu", flowinfo);
-		if (sin6->sin6_scope_id != 0)
-			printed += scnprintf(bf + printed, size - printed, ", scope_id: %lu", sin6->sin6_scope_id);
-	} else if (sin->sin_family == AF_LOCAL) {
-		struct sockaddr_un *sun = (struct sockaddr_un *)sin;
-		printed += scnprintf(bf + printed, size - printed, ", path: %s", sun->sun_path);
-	}
+	if (sa->sa_family < ARRAY_SIZE(af_scnprintfs) && af_scnprintfs[sa->sa_family])
+		printed += af_scnprintfs[sa->sa_family](sa, bf + printed, size - printed);
 
 	return printed + scnprintf(bf + printed, size - printed, " }");
 }
-- 
cgit v1.2.3


From 766e0618e49490bf67a35542880bcecbcee2e5fa Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Thu, 9 Aug 2018 06:56:50 +0200
Subject: perf report: Create auxiliary trace data files for s390

Create auxiliary trace data log files when invoked with option
--itrace=d as in:

  [root@s35lp76 perf] perf report -i perf.data.aux1 --stdio --itrace=d

perf report creates several data files in the current directory named
aux.smp.## where ## is a 2 digit hex number with leading zeros
representing the CPU number this trace data was recorded from. The file
contents is binary and contains the CPU-Measurement Sampling Data Blocks
(SDBs).

The directory to save the auxiliary trace buffer can be changed using
the perf config file and command. Specify section 'auxtrace' keyword
'dumpdir' and assign it a valid directory name. If the directory does
not exist or has the wrong file type, the current directory is used.

  [root@p23lp27 perf]# perf config auxtrace.dumpdir=/tmp
  [root@p23lp27 perf]# perf config --user -l auxtrace.dumpdir=/tmp
  [root@p23lp27 perf]# perf report ...
  [root@p23lp27 perf]# ll /tmp/aux.smp.00
  -rw-r--r-- 1 root root 204800 Aug  2 13:48 /tmp/aux.smp.00
  [root@p23lp27 perf]#

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Link: http://lkml.kernel.org/r/20180809045650.89197-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/s390-cpumsf.c | 94 +++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 91 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index d2c78ffd9fee..a2eeebbfb25f 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -147,6 +147,9 @@
 #include <linux/bitops.h>
 #include <linux/log2.h>
 
+#include <sys/stat.h>
+#include <sys/types.h>
+
 #include "cpumap.h"
 #include "color.h"
 #include "evsel.h"
@@ -159,6 +162,7 @@
 #include "auxtrace.h"
 #include "s390-cpumsf.h"
 #include "s390-cpumsf-kernel.h"
+#include "config.h"
 
 struct s390_cpumsf {
 	struct auxtrace		auxtrace;
@@ -170,6 +174,8 @@ struct s390_cpumsf {
 	u32			pmu_type;
 	u16			machine_type;
 	bool			data_queued;
+	bool			use_logfile;
+	char			*logdir;
 };
 
 struct s390_cpumsf_queue {
@@ -177,6 +183,7 @@ struct s390_cpumsf_queue {
 	unsigned int		queue_nr;
 	struct auxtrace_buffer	*buffer;
 	int			cpu;
+	FILE			*logfile;
 };
 
 /* Display s390 CPU measurement facility basic-sampling data entry */
@@ -595,6 +602,12 @@ static int s390_cpumsf_run_decoder(struct s390_cpumsf_queue *sfq,
 			buffer->use_size = buffer->size;
 			buffer->use_data = buffer->data;
 		}
+		if (sfq->logfile) {	/* Write into log file */
+			size_t rc = fwrite(buffer->data, buffer->size, 1,
+					   sfq->logfile);
+			if (rc != 1)
+				pr_err("Failed to write auxiliary data\n");
+		}
 	} else
 		buffer = sfq->buffer;
 
@@ -606,6 +619,13 @@ static int s390_cpumsf_run_decoder(struct s390_cpumsf_queue *sfq,
 			return -ENOMEM;
 		buffer->use_size = buffer->size;
 		buffer->use_data = buffer->data;
+
+		if (sfq->logfile) {	/* Write into log file */
+			size_t rc = fwrite(buffer->data, buffer->size, 1,
+					   sfq->logfile);
+			if (rc != 1)
+				pr_err("Failed to write auxiliary data\n");
+		}
 	}
 	pr_debug4("%s queue_nr:%d buffer:%" PRId64 " offset:%#" PRIx64 " size:%#zx rest:%#zx\n",
 		  __func__, sfq->queue_nr, buffer->buffer_nr, buffer->offset,
@@ -640,6 +660,23 @@ s390_cpumsf_alloc_queue(struct s390_cpumsf *sf, unsigned int queue_nr)
 	sfq->sf = sf;
 	sfq->queue_nr = queue_nr;
 	sfq->cpu = -1;
+	if (sf->use_logfile) {
+		char *name;
+		int rc;
+
+		rc = (sf->logdir)
+			? asprintf(&name, "%s/aux.smp.%02x",
+				 sf->logdir, queue_nr)
+			: asprintf(&name, "aux.smp.%02x", queue_nr);
+		if (rc > 0)
+			sfq->logfile = fopen(name, "w");
+		if (sfq->logfile == NULL) {
+			pr_err("Failed to open auxiliary log file %s,"
+			       "continue...\n", name);
+			sf->use_logfile = false;
+		}
+		free(name);
+	}
 	return sfq;
 }
 
@@ -850,8 +887,16 @@ static void s390_cpumsf_free_queues(struct perf_session *session)
 	struct auxtrace_queues *queues = &sf->queues;
 	unsigned int i;
 
-	for (i = 0; i < queues->nr_queues; i++)
+	for (i = 0; i < queues->nr_queues; i++) {
+		struct s390_cpumsf_queue *sfq = (struct s390_cpumsf_queue *)
+						queues->queue_array[i].priv;
+
+		if (sfq != NULL && sfq->logfile) {
+			fclose(sfq->logfile);
+			sfq->logfile = NULL;
+		}
 		zfree(&queues->queue_array[i].priv);
+	}
 	auxtrace_queues__free(queues);
 }
 
@@ -864,6 +909,7 @@ static void s390_cpumsf_free(struct perf_session *session)
 	auxtrace_heap__free(&sf->heap);
 	s390_cpumsf_free_queues(session);
 	session->auxtrace = NULL;
+	free(sf->logdir);
 	free(sf);
 }
 
@@ -877,17 +923,55 @@ static int s390_cpumsf_get_type(const char *cpuid)
 
 /* Check itrace options set on perf report command.
  * Return true, if none are set or all options specified can be
- * handled on s390.
+ * handled on s390 (currently only option 'd' for logging.
  * Return false otherwise.
  */
 static bool check_auxtrace_itrace(struct itrace_synth_opts *itops)
 {
+	bool ison = false;
+
 	if (!itops || !itops->set)
 		return true;
-	pr_err("No --itrace options supported\n");
+	ison = itops->inject || itops->instructions || itops->branches ||
+		itops->transactions || itops->ptwrites ||
+		itops->pwr_events || itops->errors ||
+		itops->dont_decode || itops->calls || itops->returns ||
+		itops->callchain || itops->thread_stack ||
+		itops->last_branch;
+	if (!ison)
+		return true;
+	pr_err("Unsupported --itrace options specified\n");
 	return false;
 }
 
+/* Check for AUXTRACE dump directory if it is needed.
+ * On failure print an error message but continue.
+ * Return 0 on wrong keyword in config file and 1 otherwise.
+ */
+static int s390_cpumsf__config(const char *var, const char *value, void *cb)
+{
+	struct s390_cpumsf *sf = cb;
+	struct stat stbuf;
+	int rc;
+
+	if (strcmp(var, "auxtrace.dumpdir"))
+		return 0;
+	sf->logdir = strdup(value);
+	if (sf->logdir == NULL) {
+		pr_err("Failed to find auxtrace log directory %s,"
+		       " continue with current directory...\n", value);
+		return 1;
+	}
+	rc = stat(sf->logdir, &stbuf);
+	if (rc == -1 || !S_ISDIR(stbuf.st_mode)) {
+		pr_err("Missing auxtrace log directory %s,"
+		       " continue with current directory...\n", value);
+		free(sf->logdir);
+		sf->logdir = NULL;
+	}
+	return 1;
+}
+
 int s390_cpumsf_process_auxtrace_info(union perf_event *event,
 				      struct perf_session *session)
 {
@@ -906,6 +990,9 @@ int s390_cpumsf_process_auxtrace_info(union perf_event *event,
 		err = -EINVAL;
 		goto err_free;
 	}
+	sf->use_logfile = session->itrace_synth_opts->log;
+	if (sf->use_logfile)
+		perf_config(s390_cpumsf__config, sf);
 
 	err = auxtrace_queues__init(&sf->queues);
 	if (err)
@@ -940,6 +1027,7 @@ err_free_queues:
 	auxtrace_queues__free(&sf->queues);
 	session->auxtrace = NULL;
 err_free:
+	free(sf->logdir);
 	free(sf);
 	return err;
 }
-- 
cgit v1.2.3


From 266b851cc2874774a59f04a7b3b059ca0f26569b Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Tue, 28 Aug 2018 18:50:38 -0400
Subject: tools lib traceevent, perf tools: Split trace-seq related APIs in a
 separate header file

In order to make libtraceevent into a proper library, all its APIs
should be defined in corresponding header files.  This patch splits
trace-seq related APIs in a separate header file: trace-seq.h

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/20180828185038.2dcb2743@gandalf.local.home
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.c         |  1 +
 tools/lib/traceevent/event-parse.h         | 46 ++-----------------------
 tools/lib/traceevent/event-plugin.c        |  1 +
 tools/lib/traceevent/plugin_function.c     |  1 +
 tools/lib/traceevent/plugin_hrtimer.c      |  1 +
 tools/lib/traceevent/plugin_jbd2.c         |  1 +
 tools/lib/traceevent/plugin_kmem.c         |  1 +
 tools/lib/traceevent/plugin_kvm.c          |  1 +
 tools/lib/traceevent/plugin_mac80211.c     |  1 +
 tools/lib/traceevent/plugin_sched_switch.c |  1 +
 tools/lib/traceevent/plugin_scsi.c         |  1 +
 tools/lib/traceevent/plugin_xen.c          |  1 +
 tools/lib/traceevent/trace-seq.c           |  2 ++
 tools/lib/traceevent/trace-seq.h           | 55 ++++++++++++++++++++++++++++++
 tools/perf/util/trace-event.h              |  1 +
 15 files changed, 71 insertions(+), 44 deletions(-)
 create mode 100644 tools/lib/traceevent/trace-seq.h

(limited to 'tools')

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index ce1e20227c64..70a42bec6931 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -24,6 +24,7 @@
 #include <netinet/in.h>
 #include "event-parse.h"
 #include "event-utils.h"
+#include "trace-seq.h"
 
 static const char *input_buf;
 static unsigned long long input_buf_ptr;
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 44b7c2d41f9f..fa665c66bfa4 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -26,17 +26,12 @@
 #include <regex.h>
 #include <string.h>
 
+#include "trace-seq.h"
+
 #ifndef __maybe_unused
 #define __maybe_unused __attribute__((unused))
 #endif
 
-/* ----------------------- trace_seq ----------------------- */
-
-
-#ifndef TRACE_SEQ_BUF_SIZE
-#define TRACE_SEQ_BUF_SIZE 4096
-#endif
-
 #ifndef DEBUG_RECORD
 #define DEBUG_RECORD 0
 #endif
@@ -59,43 +54,6 @@ struct tep_record {
 #endif
 };
 
-enum trace_seq_fail {
-	TRACE_SEQ__GOOD,
-	TRACE_SEQ__BUFFER_POISONED,
-	TRACE_SEQ__MEM_ALLOC_FAILED,
-};
-
-/*
- * Trace sequences are used to allow a function to call several other functions
- * to create a string of data to use (up to a max of PAGE_SIZE).
- */
-
-struct trace_seq {
-	char			*buffer;
-	unsigned int		buffer_size;
-	unsigned int		len;
-	unsigned int		readpos;
-	enum trace_seq_fail	state;
-};
-
-void trace_seq_init(struct trace_seq *s);
-void trace_seq_reset(struct trace_seq *s);
-void trace_seq_destroy(struct trace_seq *s);
-
-extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
-	__attribute__ ((format (printf, 2, 3)));
-extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
-	__attribute__ ((format (printf, 2, 0)));
-
-extern int trace_seq_puts(struct trace_seq *s, const char *str);
-extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
-
-extern void trace_seq_terminate(struct trace_seq *s);
-
-extern int trace_seq_do_fprintf(struct trace_seq *s, FILE *fp);
-extern int trace_seq_do_printf(struct trace_seq *s);
-
-
 /* ----------------------- pevent ----------------------- */
 
 struct tep_handle;
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
index f17e25097e1e..ec16a103c0cc 100644
--- a/tools/lib/traceevent/event-plugin.c
+++ b/tools/lib/traceevent/event-plugin.c
@@ -15,6 +15,7 @@
 #include <dirent.h>
 #include "event-parse.h"
 #include "event-utils.h"
+#include "trace-seq.h"
 
 #define LOCAL_PLUGIN_DIR ".traceevent/plugins"
 
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
index 424747475d37..2919042e7dc2 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugin_function.c
@@ -23,6 +23,7 @@
 
 #include "event-parse.h"
 #include "event-utils.h"
+#include "trace-seq.h"
 
 static struct func_stack {
 	int size;
diff --git a/tools/lib/traceevent/plugin_hrtimer.c b/tools/lib/traceevent/plugin_hrtimer.c
index b43bfec565d8..29b608076ea0 100644
--- a/tools/lib/traceevent/plugin_hrtimer.c
+++ b/tools/lib/traceevent/plugin_hrtimer.c
@@ -23,6 +23,7 @@
 #include <string.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 static int timer_expire_handler(struct trace_seq *s,
 				struct tep_record *record,
diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugin_jbd2.c
index 45a9acd19640..a5e34135dd6a 100644
--- a/tools/lib/traceevent/plugin_jbd2.c
+++ b/tools/lib/traceevent/plugin_jbd2.c
@@ -22,6 +22,7 @@
 #include <string.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 #define MINORBITS	20
 #define MINORMASK	((1U << MINORBITS) - 1)
diff --git a/tools/lib/traceevent/plugin_kmem.c b/tools/lib/traceevent/plugin_kmem.c
index 73966b05abce..a7a162575e2c 100644
--- a/tools/lib/traceevent/plugin_kmem.c
+++ b/tools/lib/traceevent/plugin_kmem.c
@@ -22,6 +22,7 @@
 #include <string.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 static int call_site_handler(struct trace_seq *s, struct tep_record *record,
 			     struct event_format *event, void *context)
diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c
index 1d0d15906225..a0dfd3d0f197 100644
--- a/tools/lib/traceevent/plugin_kvm.c
+++ b/tools/lib/traceevent/plugin_kvm.c
@@ -23,6 +23,7 @@
 #include <stdint.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 #ifdef HAVE_UDIS86
 
diff --git a/tools/lib/traceevent/plugin_mac80211.c b/tools/lib/traceevent/plugin_mac80211.c
index de50a5316203..0b7779444b63 100644
--- a/tools/lib/traceevent/plugin_mac80211.c
+++ b/tools/lib/traceevent/plugin_mac80211.c
@@ -22,6 +22,7 @@
 #include <string.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 #define INDENT 65
 
diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c
index eecb4bd95c11..582d3be2849b 100644
--- a/tools/lib/traceevent/plugin_sched_switch.c
+++ b/tools/lib/traceevent/plugin_sched_switch.c
@@ -22,6 +22,7 @@
 #include <string.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 static void write_state(struct trace_seq *s, int val)
 {
diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c
index 5ec346f6b842..4eba25cc1431 100644
--- a/tools/lib/traceevent/plugin_scsi.c
+++ b/tools/lib/traceevent/plugin_scsi.c
@@ -3,6 +3,7 @@
 #include <string.h>
 #include <inttypes.h>
 #include "event-parse.h"
+#include "trace-seq.h"
 
 typedef unsigned long sector_t;
 typedef uint64_t u64;
diff --git a/tools/lib/traceevent/plugin_xen.c b/tools/lib/traceevent/plugin_xen.c
index b2acbd6e9c86..bc0496e4c296 100644
--- a/tools/lib/traceevent/plugin_xen.c
+++ b/tools/lib/traceevent/plugin_xen.c
@@ -3,6 +3,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include "event-parse.h"
+#include "trace-seq.h"
 
 #define __HYPERVISOR_set_trap_table			0
 #define __HYPERVISOR_mmu_update				1
diff --git a/tools/lib/traceevent/trace-seq.c b/tools/lib/traceevent/trace-seq.c
index e3bac4543d3b..8ff1d55954d1 100644
--- a/tools/lib/traceevent/trace-seq.c
+++ b/tools/lib/traceevent/trace-seq.c
@@ -3,6 +3,8 @@
  * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
  *
  */
+#include "trace-seq.h"
+
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
diff --git a/tools/lib/traceevent/trace-seq.h b/tools/lib/traceevent/trace-seq.h
new file mode 100644
index 000000000000..d68ec69f8d1a
--- /dev/null
+++ b/tools/lib/traceevent/trace-seq.h
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+
+#ifndef _TRACE_SEQ_H
+#define _TRACE_SEQ_H
+
+#include <stdarg.h>
+#include <stdio.h>
+
+/* ----------------------- trace_seq ----------------------- */
+
+#ifndef TRACE_SEQ_BUF_SIZE
+#define TRACE_SEQ_BUF_SIZE 4096
+#endif
+
+enum trace_seq_fail {
+	TRACE_SEQ__GOOD,
+	TRACE_SEQ__BUFFER_POISONED,
+	TRACE_SEQ__MEM_ALLOC_FAILED,
+};
+
+/*
+ * Trace sequences are used to allow a function to call several other functions
+ * to create a string of data to use (up to a max of PAGE_SIZE).
+ */
+
+struct trace_seq {
+	char			*buffer;
+	unsigned int		buffer_size;
+	unsigned int		len;
+	unsigned int		readpos;
+	enum trace_seq_fail	state;
+};
+
+void trace_seq_init(struct trace_seq *s);
+void trace_seq_reset(struct trace_seq *s);
+void trace_seq_destroy(struct trace_seq *s);
+
+extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+	__attribute__ ((format (printf, 2, 0)));
+
+extern int trace_seq_puts(struct trace_seq *s, const char *str);
+extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
+
+extern void trace_seq_terminate(struct trace_seq *s);
+
+extern int trace_seq_do_fprintf(struct trace_seq *s, FILE *fp);
+extern int trace_seq_do_printf(struct trace_seq *s);
+
+#endif /* _TRACE_SEQ_H */
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 40204ec3a7a2..c69d77d7cf55 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -3,6 +3,7 @@
 #define _PERF_UTIL_TRACE_EVENT_H
 
 #include <traceevent/event-parse.h>
+#include <traceevent/trace-seq.h>
 #include "parse-events.h"
 
 struct machine;
-- 
cgit v1.2.3


From 664b6a95d771a6dcd7069996c825a03be411ef99 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 30 Aug 2018 08:48:44 -0300
Subject: perf bpf: Add syscall_exit() helper

So that we can hook to the syscalls:sys_exit_SYSCALL tracepoints in
addition to the syscalls:sys_enter_SYSCALL we hook using the
syscall_enter() helper.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-6qh8aph1jklyvdu7w89c0izc@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/include/bpf/bpf.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h
index 47897d65e799..52b6d87fe822 100644
--- a/tools/perf/include/bpf/bpf.h
+++ b/tools/perf/include/bpf/bpf.h
@@ -26,6 +26,9 @@ struct bpf_map {
 #define syscall_enter(name) \
 	SEC("syscalls:sys_enter_" #name) syscall_enter_ ## name
 
+#define syscall_exit(name) \
+	SEC("syscalls:sys_exit_" #name) syscall_exit_ ## name
+
 #define license(name) \
 char _license[] SEC("license") = #name; \
 int _version SEC("version") = LINUX_VERSION_CODE;
-- 
cgit v1.2.3


From 5e2d8a5acc99e7b9df9be216f0a73855e865f9a5 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 30 Aug 2018 10:02:23 -0300
Subject: perf augmented_syscalls: Update the header comments

Reflecting the fact that it now augments more than syscalls:sys_enter_SYSCALL
tracepoints that have filename strings as args. Also mention how the
extra data is handled by the by now modified 'perf trace' beautifiers,
that will use special "augmented" beautifiers when extra data is found
after the expected syscall enter/exit tracepoints.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ybskanehmdilj5fs7080nz1g@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/examples/bpf/augmented_syscalls.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index be06d2c9e8c9..bfa28eaf27b3 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Augment the openat syscall with the contents of the filename pointer argument.
+ * Augment syscalls with the contents of the pointer arguments.
  *
  * Test it with:
  *
@@ -10,12 +10,10 @@
  * the last one should be the one for '/etc/passwd'.
  *
  * This matches what is marshalled into the raw_syscall:sys_enter payload
- * expected by the 'perf trace' beautifiers, and can be used by them unmodified,
- * which will be done as that feature is implemented in the next csets, for now
- * it will appear in a dump done by the default tracepoint handler in 'perf trace',
- * that uses bpf_output__fprintf() to just dump those contents, as done with
- * the bpf-output event associated with the __bpf_output__ map declared in
- * tools/perf/include/bpf/stdio.h.
+ * expected by the 'perf trace' beautifiers, and can be used by them, that will
+ * check if perf_sample->raw_data is more than what is expected for each
+ * syscalls:sys_{enter,exit}_SYSCALL tracepoint, uing the extra data as the
+ * contents of pointer arguments.
  */
 
 #include <stdio.h>
-- 
cgit v1.2.3


From 4c8f0a726ef808244788a237e52ce3c612bff8c3 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 30 Aug 2018 11:50:21 -0300
Subject: perf trace augmented_syscalls: Rename augmented_*_syscall__enter to
 just *_syscall

As we'll also hook into the syscalls:sys_exit_SYSCALL for which there
are enter hooks.

This way we'll be able to iterate the ELF file for the eBPF program,
find the syscalls that have hooks and filter them out from the general
raw_syscalls:sys_{enter,exit} tracepoint for not-yet-augmented (the ones
with pointer arguments not yet being attached to the usual syscalls
tracepoint payload) and non augmentable syscalls (syscalls without
pointer arguments).

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-cl1xyghwb1usp500354mv37h@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/examples/bpf/augmented_syscalls.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index bfa28eaf27b3..253b3ccbd17d 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -32,7 +32,7 @@ struct augmented_filename {
 	char	value[256];
 };
 
-#define augmented_filename_syscall_enter(syscall)						\
+#define augmented_filename_syscall(syscall)							\
 struct augmented_enter_##syscall##_args {			 				\
 	struct syscall_enter_##syscall##_args	args;				 		\
 	struct augmented_filename		filename;				 	\
@@ -60,7 +60,7 @@ struct syscall_enter_openat_args {
 	long		   mode;
 };
 
-augmented_filename_syscall_enter(openat);
+augmented_filename_syscall(openat);
 
 struct syscall_enter_open_args {
 	unsigned long long common_tp_fields;
@@ -70,7 +70,7 @@ struct syscall_enter_open_args {
 	long		   mode;
 };
 
-augmented_filename_syscall_enter(open);
+augmented_filename_syscall(open);
 
 struct syscall_enter_inotify_add_watch_args {
 	unsigned long long common_tp_fields;
@@ -80,7 +80,7 @@ struct syscall_enter_inotify_add_watch_args {
 	long		   mask;
 };
 
-augmented_filename_syscall_enter(inotify_add_watch);
+augmented_filename_syscall(inotify_add_watch);
 
 struct statbuf;
 
@@ -91,13 +91,13 @@ struct syscall_enter_newstat_args {
 	struct stat	   *statbuf;
 };
 
-augmented_filename_syscall_enter(newstat);
+augmented_filename_syscall(newstat);
 
 #ifndef _K_SS_MAXSIZE
 #define _K_SS_MAXSIZE 128
 #endif
 
-#define augmented_sockaddr_syscall_enter(syscall)						\
+#define augmented_sockaddr_syscall(syscall)						\
 struct augmented_enter_##syscall##_args {			 				\
 	struct syscall_enter_##syscall##_args	args;				 		\
 	struct sockaddr_storage			addr;						\
@@ -128,7 +128,7 @@ struct syscall_enter_bind_args {
 	unsigned long	   addrlen;
 };
 
-augmented_sockaddr_syscall_enter(bind);
+augmented_sockaddr_syscall(bind);
 
 struct syscall_enter_connect_args {
 	unsigned long long common_tp_fields;
@@ -138,7 +138,7 @@ struct syscall_enter_connect_args {
 	unsigned long	   addrlen;
 };
 
-augmented_sockaddr_syscall_enter(connect);
+augmented_sockaddr_syscall(connect);
 
 struct syscall_enter_sendto_args {
 	unsigned long long common_tp_fields;
@@ -151,6 +151,6 @@ struct syscall_enter_sendto_args {
 	long		   addr_len;
 };
 
-augmented_sockaddr_syscall_enter(sendto);
+augmented_sockaddr_syscall(sendto);
 
 license(GPL);
-- 
cgit v1.2.3


From f5b076dc01e77fa016de8439f8ac21d1c310c5be Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 30 Aug 2018 12:32:35 -0300
Subject: perf trace augmented_syscalls: Hook into syscalls:sys_exit_SYSCALL
 too

Hook the pair enter/exit when using augmented_{filename,sockaddr,etc}_syscall(),
this way we'll be able to see what entries are in the ELF sections generated
from augmented_syscalls.c and filter them out from the main raw_syscalls:*
tracepoints used by 'perf trace'.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-cyav42qj5yylolw4attcw99z@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/examples/bpf/augmented_syscalls.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index 253b3ccbd17d..1419a9186937 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -26,6 +26,12 @@ struct bpf_map SEC("maps") __augmented_syscalls__ = {
        .max_entries = __NR_CPUS__,
 };
 
+struct syscall_exit_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   ret;
+};
+
 struct augmented_filename {
 	int	size;
 	int	reserved;
@@ -49,6 +55,10 @@ int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
 			  (sizeof(augmented_args) - sizeof(augmented_args.filename.value) +	\
 			   augmented_args.filename.size));					\
 	return 0;										\
+}												\
+int syscall_exit(syscall)(struct syscall_exit_args *args)					\
+{												\
+       return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */	\
 }
 
 struct syscall_enter_openat_args {
@@ -116,6 +126,10 @@ int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
 			  &augmented_args, 							\
 			  sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen);	\
 	return 0;										\
+}												\
+int syscall_exit(syscall)(struct syscall_exit_args *args)					\
+{												\
+       return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */	\
 }
 
 struct sockaddr;
-- 
cgit v1.2.3


From c4191e55b8741f72d44c7c1435c340681ae1ea4e Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 30 Aug 2018 13:37:28 -0300
Subject: perf trace: Show comm and tid for tracepoint events

So that all events have that info, improving reading by having
information better aligned, etc.

Before:

  # echo 1 > /proc/sys/vm/drop_caches
  # perf trace -e block:*,ext4:*,tools/perf/examples/bpf/augmented_syscalls.c,close cat tools/perf/examples/bpf/hello.c
       0.000 (         ): #include <stdio.h>

  int syscall_enter(openat)(void *args)
  {
  	puts("Hello, world\n");
  	return 0;
  }

  license(GPL);
  cat/2731 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
       0.025 (         ): syscalls:sys_exit_openat:0x3
       0.063 ( 0.022 ms): cat/2731 close(fd: 3) = 0
       0.110 (         ): cat/2731 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC)
       0.123 (         ): syscalls:sys_exit_openat:0x3
       0.243 ( 0.008 ms): cat/2731 close(fd: 3) = 0
       0.485 (         ): cat/2731 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC)
       0.500 (         ): syscalls:sys_exit_open:0x3
       0.531 ( 0.017 ms): cat/2731 close(fd: 3) = 0
       0.587 (         ): cat/2731 openat(dfd: CWD, filename: tools/perf/examples/bpf/hello.c)
       0.601 (         ): syscalls:sys_exit_openat:0x3
       0.631 (         ): ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 1311399 lblk 0
       0.639 (         ): ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 1311399 found 1 [0/1) 5276651 W0x10
       0.654 (         ): block:block_bio_queue:253,2 R 42213208 + 8 [cat]
       0.663 (         ): block:block_bio_remap:8,0 R 58206040 + 8 <- (253,2) 42213208
       0.671 (         ): block:block_bio_remap:8,0 R 175570776 + 8 <- (8,6) 58206040
       0.678 (         ): block:block_bio_queue:8,0 R 175570776 + 8 [cat]
       0.692 (         ): block:block_getrq:8,0 R 175570776 + 8 [cat]
       0.700 (         ): block:block_plug:[cat]
       0.708 (         ): block:block_rq_insert:8,0 R 4096 () 175570776 + 8 [cat]
       0.713 (         ): block:block_unplug:[cat] 1
       0.716 (         ): block:block_rq_issue:8,0 R 4096 () 175570776 + 8 [cat]
       0.949 ( 0.007 ms): cat/2731 close(fd: 3) = 0
       0.969 ( 0.006 ms): cat/2731 close(fd: 1) = 0
       0.982 ( 0.006 ms): cat/2731 close(fd: 2) = 0
  #

After:

  # echo 1 > /proc/sys/vm/drop_caches
  # perf trace -e block:*,ext4:*,tools/perf/examples/bpf/augmented_syscalls.c,close cat tools/perf/examples/bpf/hello.c
       0.000 (         ): cat/1380 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)#include <stdio.h>

  int syscall_enter(openat)(void *args)
  {
  	puts("Hello, world\n");
  	return 0;
  }

  license(GPL);

       0.024 (         ): cat/1380 syscalls:sys_exit_openat:0x3
       0.063 ( 0.024 ms): cat/1380 close(fd: 3) = 0
       0.114 (         ): cat/1380 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC)
       0.127 (         ): cat/1380 syscalls:sys_exit_openat:0x3
       0.247 ( 0.009 ms): cat/1380 close(fd: 3) = 0
       0.484 (         ): cat/1380 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC)
       0.499 (         ): cat/1380 syscalls:sys_exit_open:0x3
       0.613 ( 0.010 ms): cat/1380 close(fd: 3) = 0
       0.662 (         ): cat/1380 openat(dfd: CWD, filename: tools/perf/examples/bpf/hello.c)
       0.678 (         ): cat/1380 syscalls:sys_exit_openat:0x3
       0.712 (         ): cat/1380 ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 1311399 lblk 0
       0.721 (         ): cat/1380 ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 1311399 found 1 [0/1) 5276651 W0x10
       0.734 (         ): cat/1380 block:block_bio_queue:253,2 R 42213208 + 8 [cat]
       0.745 (         ): cat/1380 block:block_bio_remap:8,0 R 58206040 + 8 <- (253,2) 42213208
       0.754 (         ): cat/1380 block:block_bio_remap:8,0 R 175570776 + 8 <- (8,6) 58206040
       0.761 (         ): cat/1380 block:block_bio_queue:8,0 R 175570776 + 8 [cat]
       0.780 (         ): cat/1380 block:block_getrq:8,0 R 175570776 + 8 [cat]
       0.791 (         ): cat/1380 block:block_plug:[cat]
       0.802 (         ): cat/1380 block:block_rq_insert:8,0 R 4096 () 175570776 + 8 [cat]
       0.806 (         ): cat/1380 block:block_unplug:[cat] 1
       0.810 (         ): cat/1380 block:block_rq_issue:8,0 R 4096 () 175570776 + 8 [cat]
       1.005 ( 0.011 ms): cat/1380 close(fd: 3) = 0
       1.031 ( 0.008 ms): cat/1380 close(fd: 1) = 0
       1.048 ( 0.008 ms): cat/1380 close(fd: 2) = 0
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-us1mwsupxffs4jlm3uqm5dvj@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 759d14e3fe6b..97ace635bed8 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2049,6 +2049,7 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 				union perf_event *event __maybe_unused,
 				struct perf_sample *sample)
 {
+	struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 	int callchain_ret = 0;
 
 	if (sample->callchain) {
@@ -2066,21 +2067,18 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 	if (trace->trace_syscalls)
 		fprintf(trace->output, "(         ): ");
 
+	if (thread)
+		trace__fprintf_comm_tid(trace, thread, trace->output);
+
 	if (evsel == trace->syscalls.events.augmented) {
 		int id = perf_evsel__sc_tp_uint(evsel, id, sample);
 		struct syscall *sc = trace__syscall_info(trace, evsel, id);
 
 		if (sc) {
-			struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
-
-			if (thread) {
-				trace__fprintf_comm_tid(trace, thread, trace->output);
-				fprintf(trace->output, "%s(", sc->name);
-				trace__fprintf_sys_enter(trace, evsel, sample);
-				fputc(')', trace->output);
-				thread__put(thread);
-				goto newline;
-			}
+			fprintf(trace->output, "%s(", sc->name);
+			trace__fprintf_sys_enter(trace, evsel, sample);
+			fputc(')', trace->output);
+			goto newline;
 		}
 
 		/*
@@ -2110,6 +2108,7 @@ newline:
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
 		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
+	thread__put(thread);
 out:
 	return 0;
 }
-- 
cgit v1.2.3


From d50ed0ce820414dbe249a6ad5c9830e29cc46fcc Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:10 +0200
Subject: perf stat: Use evsel->threads in create_perf_stat_counter()

Get rid of the evsel_list dependency, here we can use the evsel->threads
copy of the struct thread_map.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-2-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index d097b5b47eb8..d389ed623715 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -293,7 +293,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 	if (target__has_cpu(&target) && !target__has_per_thread(&target))
 		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
 
-	return perf_evsel__open_per_thread(evsel, evsel_list->threads);
+	return perf_evsel__open_per_thread(evsel, evsel->threads);
 }
 
 static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
-- 
cgit v1.2.3


From 728c0ee0a896fcb0957b496afdb78bf195397645 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:11 +0200
Subject: perf stat: Move 'initial_delay' to 'struct perf_stat_config'

Move the static 'initial_delay' variable to 'struct perf_stat_config',
so it can be passed around and used outside the 'perf stat' command.

Add 'struct perf_stat_config' argument to create_perf_stat_counter() and
use its 'initial_delay' member instead of the static one.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-3-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 16 ++++++++--------
 tools/perf/util/stat.h    | 18 ++++++++++--------
 2 files changed, 18 insertions(+), 16 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index d389ed623715..719abdd3b7de 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -164,7 +164,6 @@ static bool			group				= false;
 static const char		*pre_cmd			= NULL;
 static const char		*post_cmd			= NULL;
 static bool			sync_run			= false;
-static unsigned int		initial_delay			= 0;
 static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
 static bool			metric_only			= false;
@@ -236,7 +235,8 @@ static void perf_stat__reset_stats(void)
 		perf_stat__reset_shadow_per_stat(&stat_config.stats[i]);
 }
 
-static int create_perf_stat_counter(struct perf_evsel *evsel)
+static int create_perf_stat_counter(struct perf_evsel *evsel,
+				    struct perf_stat_config *config)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	struct perf_evsel *leader = evsel->leader;
@@ -286,7 +286,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 		 * In case of initial_delay we enable tracee
 		 * events manually.
 		 */
-		if (target__none(&target) && !initial_delay)
+		if (target__none(&target) && !config->initial_delay)
 			attr->enable_on_exec = 1;
 	}
 
@@ -428,15 +428,15 @@ static void process_interval(void)
 
 static void enable_counters(void)
 {
-	if (initial_delay)
-		usleep(initial_delay * USEC_PER_MSEC);
+	if (stat_config.initial_delay)
+		usleep(stat_config.initial_delay * USEC_PER_MSEC);
 
 	/*
 	 * We need to enable counters only if:
 	 * - we don't have tracee (attaching to task or cpu)
 	 * - we have initial delay configured
 	 */
-	if (!target__none(&target) || initial_delay)
+	if (!target__none(&target) || stat_config.initial_delay)
 		perf_evlist__enable(evsel_list);
 }
 
@@ -609,7 +609,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 
 	evlist__for_each_entry(evsel_list, counter) {
 try_again:
-		if (create_perf_stat_counter(counter) < 0) {
+		if (create_perf_stat_counter(counter, &stat_config) < 0) {
 
 			/* Weak group failed. Reset the group. */
 			if ((errno == EINVAL || errno == EBADF) &&
@@ -2027,7 +2027,7 @@ static const struct option stat_options[] = {
 		     "aggregate counts per physical processor core", AGGR_CORE),
 	OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode,
 		     "aggregate counts per thread", AGGR_THREAD),
-	OPT_UINTEGER('D', "delay", &initial_delay,
+	OPT_UINTEGER('D', "delay", &stat_config.initial_delay,
 		     "ms to wait before starting measurement after program start"),
 	OPT_CALLBACK_NOOPT(0, "metric-only", &metric_only, NULL,
 			"Only print computed metrics. No raw values", enable_metric_only),
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 36efb986f7fc..91e6609fce6e 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -6,6 +6,7 @@
 #include <stdio.h>
 #include "xyarray.h"
 #include "rblist.h"
+#include "perf.h"
 
 struct stats {
 	double n, mean, M2;
@@ -85,14 +86,15 @@ struct runtime_stat {
 };
 
 struct perf_stat_config {
-	enum aggr_mode	aggr_mode;
-	bool		scale;
-	FILE		*output;
-	unsigned int	interval;
-	unsigned int	timeout;
-	int		times;
-	struct runtime_stat *stats;
-	int		stats_num;
+	enum aggr_mode		 aggr_mode;
+	bool			 scale;
+	FILE			*output;
+	unsigned int		 interval;
+	unsigned int		 timeout;
+	unsigned int		 initial_delay;
+	int			 times;
+	struct runtime_stat	*stats;
+	int			 stats_num;
 };
 
 void update_stats(struct stats *stats, u64 val);
-- 
cgit v1.2.3


From 5698f26b46e4f47f2371418eb92732048fa4fa66 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:12 +0200
Subject: perf stat: Move 'no_inherit' to 'struct perf_stat_config'

Move the static 'no_inherit' variable to 'struct perf_stat_config', so
it can be passed around and used outside the 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-4-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 5 ++---
 tools/perf/util/stat.h    | 1 +
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 719abdd3b7de..84dbac526925 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -148,7 +148,6 @@ typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu);
 #define METRIC_ONLY_LEN 20
 
 static int			run_count			=  1;
-static bool			no_inherit			= false;
 static volatile pid_t		child_pid			= -1;
 static bool			null_run			=  false;
 static int			detailed_run			=  0;
@@ -254,7 +253,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel,
 	if (leader->nr_members > 1)
 		attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP;
 
-	attr->inherit = !no_inherit;
+	attr->inherit = !config->no_inherit;
 
 	/*
 	 * Some events get initialized with sample_(period/type) set,
@@ -1969,7 +1968,7 @@ static const struct option stat_options[] = {
 		     parse_events_option),
 	OPT_CALLBACK(0, "filter", &evsel_list, "filter",
 		     "event filter", parse_filter),
-	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
+	OPT_BOOLEAN('i', "no-inherit", &stat_config.no_inherit,
 		    "child tasks do not inherit counters"),
 	OPT_STRING('p', "pid", &target.pid, "pid",
 		   "stat events on existing process id"),
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 91e6609fce6e..53b2415ba3f3 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -88,6 +88,7 @@ struct runtime_stat {
 struct perf_stat_config {
 	enum aggr_mode		 aggr_mode;
 	bool			 scale;
+	bool			 no_inherit;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
-- 
cgit v1.2.3


From 35386233fcf78f20cb8a51199518da9f81eca280 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:13 +0200
Subject: perf stat: Use local config arg for scale in
 create_perf_stat_counter()

Use the local 'scale' member in the 'struct perf_stat_config' argument
instead of the global 'stat_config' variable, to make the function
independent.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-5-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 84dbac526925..47789558899a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -240,7 +240,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel,
 	struct perf_event_attr *attr = &evsel->attr;
 	struct perf_evsel *leader = evsel->leader;
 
-	if (stat_config.scale) {
+	if (config->scale) {
 		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
 				    PERF_FORMAT_TOTAL_TIME_RUNNING;
 	}
-- 
cgit v1.2.3


From 7d9ad16afe2bfc73b8967cc2aa2dc30f0170a8e2 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:14 +0200
Subject: perf stat: Add 'identifier' flag to 'struct perf_stat_config'

Add 'identifier' flag to 'struct perf_stat_config' to carry the info
whether to use PERF_SAMPLE_IDENTIFIER for events.

This makes create_perf_stat_counter() independent.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-6-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 22 ++++++++++++----------
 tools/perf/util/stat.h    |  1 +
 2 files changed, 13 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 47789558899a..48c88f568fe1 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -261,16 +261,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel,
 	 */
 	attr->sample_period = 0;
 
-	/*
-	 * But set sample_type to PERF_SAMPLE_IDENTIFIER, which should be harmless
-	 * while avoiding that older tools show confusing messages.
-	 *
-	 * However for pipe sessions we need to keep it zero,
-	 * because script's perf_evsel__check_attr is triggered
-	 * by attr->sample_type != 0, and we can't run it on
-	 * stat sessions.
-	 */
-	if (!(STAT_RECORD && perf_stat.data.is_pipe))
+	if (config->identifier)
 		attr->sample_type = PERF_SAMPLE_IDENTIFIER;
 
 	/*
@@ -3064,6 +3055,17 @@ int cmd_stat(int argc, const char **argv)
 	if (perf_stat_init_aggr_mode())
 		goto out;
 
+	/*
+	 * Set sample_type to PERF_SAMPLE_IDENTIFIER, which should be harmless
+	 * while avoiding that older tools show confusing messages.
+	 *
+	 * However for pipe sessions we need to keep it zero,
+	 * because script's perf_evsel__check_attr is triggered
+	 * by attr->sample_type != 0, and we can't run it on
+	 * stat sessions.
+	 */
+	stat_config.identifier = !(STAT_RECORD && perf_stat.data.is_pipe);
+
 	/*
 	 * We dont want to block the signals - that would cause
 	 * child tasks to inherit that and Ctrl-C would not work.
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 53b2415ba3f3..918cde064cdc 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -89,6 +89,7 @@ struct perf_stat_config {
 	enum aggr_mode		 aggr_mode;
 	bool			 scale;
 	bool			 no_inherit;
+	bool			 identifier;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
-- 
cgit v1.2.3


From 318ec1841a3f26799fe663d8f979a57623c0c470 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:15 +0200
Subject: perf tools: Switch 'session' argument to 'evlist' in
 perf_event__synthesize_attrs()

To be able to pass in other than session's evlist.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-7-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c | 2 +-
 tools/perf/builtin-stat.c   | 2 +-
 tools/perf/util/header.c    | 6 +++---
 tools/perf/util/header.h    | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 22ebeb92ac51..9853552bcf16 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -758,7 +758,7 @@ static int record__synthesize(struct record *rec, bool tail)
 		 * We need to synthesize events first, because some
 		 * features works on top of them (on report side).
 		 */
-		err = perf_event__synthesize_attrs(tool, session,
+		err = perf_event__synthesize_attrs(tool, rec->evlist,
 						   process_synthesized_event);
 		if (err < 0) {
 			pr_err("Couldn't synthesize attrs.\n");
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 48c88f568fe1..8291f503d0cc 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -459,7 +459,7 @@ static int perf_stat_synthesize_config(bool is_pipe)
 	int err;
 
 	if (is_pipe) {
-		err = perf_event__synthesize_attrs(NULL, perf_stat.session,
+		err = perf_event__synthesize_attrs(NULL, evsel_list,
 						   process_synthesized_event);
 		if (err < 0) {
 			pr_err("Couldn't synthesize attrs.\n");
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 3cadc252dd89..91e6d9cfd906 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3637,13 +3637,13 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
 }
 
 int perf_event__synthesize_attrs(struct perf_tool *tool,
-				   struct perf_session *session,
-				   perf_event__handler_t process)
+				 struct perf_evlist *evlist,
+				 perf_event__handler_t process)
 {
 	struct perf_evsel *evsel;
 	int err = 0;
 
-	evlist__for_each_entry(session->evlist, evsel) {
+	evlist__for_each_entry(evlist, evsel) {
 		err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids,
 						  evsel->id, process);
 		if (err) {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 6d7fe44aadc0..ff2a1263fb9b 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -124,7 +124,7 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
 				struct perf_event_attr *attr, u32 ids, u64 *id,
 				perf_event__handler_t process);
 int perf_event__synthesize_attrs(struct perf_tool *tool,
-				 struct perf_session *session,
+				 struct perf_evlist *evlist,
 				 perf_event__handler_t process);
 int perf_event__synthesize_event_update_unit(struct perf_tool *tool,
 					     struct perf_evsel *evsel,
-- 
cgit v1.2.3


From 650d622046024623e71fea1f28acf1edb7e61a81 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:16 +0200
Subject: perf evsel: Introduce perf_evsel__store_ids()

Add perf_evsel__store_ids() from stat's store_counter_ids() code to the
evsel class, so that it can be used globally.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-8-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 33 +--------------------------------
 tools/perf/util/evsel.c   | 29 +++++++++++++++++++++++++++++
 tools/perf/util/evsel.h   |  1 +
 3 files changed, 31 insertions(+), 32 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 8291f503d0cc..45bbd156d496 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -497,37 +497,6 @@ static int perf_stat_synthesize_config(bool is_pipe)
 	return 0;
 }
 
-#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
-
-static int __store_counter_ids(struct perf_evsel *counter)
-{
-	int cpu, thread;
-
-	for (cpu = 0; cpu < xyarray__max_x(counter->fd); cpu++) {
-		for (thread = 0; thread < xyarray__max_y(counter->fd);
-		     thread++) {
-			int fd = FD(counter, cpu, thread);
-
-			if (perf_evlist__id_add_fd(evsel_list, counter,
-						   cpu, thread, fd) < 0)
-				return -1;
-		}
-	}
-
-	return 0;
-}
-
-static int store_counter_ids(struct perf_evsel *counter)
-{
-	struct cpu_map *cpus = counter->cpus;
-	struct thread_map *threads = counter->threads;
-
-	if (perf_evsel__alloc_id(counter, cpus->nr, threads->nr))
-		return -ENOMEM;
-
-	return __store_counter_ids(counter);
-}
-
 static bool perf_evsel__should_store_id(struct perf_evsel *counter)
 {
 	return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID;
@@ -658,7 +627,7 @@ try_again:
 			unit_width = l;
 
 		if (perf_evsel__should_store_id(counter) &&
-		    store_counter_ids(counter))
+		    perf_evsel__store_ids(counter, evsel_list))
 			return -1;
 	}
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1a61628a1c12..4ec909d57e9c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2940,3 +2940,32 @@ struct perf_env *perf_evsel__env(struct perf_evsel *evsel)
 		return evsel->evlist->env;
 	return NULL;
 }
+
+static int store_evsel_ids(struct perf_evsel *evsel, struct perf_evlist *evlist)
+{
+	int cpu, thread;
+
+	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+		for (thread = 0; thread < xyarray__max_y(evsel->fd);
+		     thread++) {
+			int fd = FD(evsel, cpu, thread);
+
+			if (perf_evlist__id_add_fd(evlist, evsel,
+						   cpu, thread, fd) < 0)
+				return -1;
+		}
+	}
+
+	return 0;
+}
+
+int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist)
+{
+	struct cpu_map *cpus = evsel->cpus;
+	struct thread_map *threads = evsel->threads;
+
+	if (perf_evsel__alloc_id(evsel, cpus->nr, threads->nr))
+		return -ENOMEM;
+
+	return store_evsel_ids(evsel, evlist);
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 163c960614d3..4f8430a85531 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -481,4 +481,5 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 
 struct perf_env *perf_evsel__env(struct perf_evsel *evsel);
 
+int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist);
 #endif /* __PERF_EVSEL_H */
-- 
cgit v1.2.3


From d09cefd2ef9945b4b767bb67f473a0eb2066374f Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:17 +0200
Subject: perf stat: Move create_perf_stat_counter() to stat.c

Move create_perf_stat_counter() to the 'stat' class, so that we can use
it globally.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-9-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 54 +----------------------------------------------
 tools/perf/util/stat.c    | 53 ++++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/stat.h    |  4 ++++
 3 files changed, 58 insertions(+), 53 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 45bbd156d496..142cff8eb12b 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -234,58 +234,6 @@ static void perf_stat__reset_stats(void)
 		perf_stat__reset_shadow_per_stat(&stat_config.stats[i]);
 }
 
-static int create_perf_stat_counter(struct perf_evsel *evsel,
-				    struct perf_stat_config *config)
-{
-	struct perf_event_attr *attr = &evsel->attr;
-	struct perf_evsel *leader = evsel->leader;
-
-	if (config->scale) {
-		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
-				    PERF_FORMAT_TOTAL_TIME_RUNNING;
-	}
-
-	/*
-	 * The event is part of non trivial group, let's enable
-	 * the group read (for leader) and ID retrieval for all
-	 * members.
-	 */
-	if (leader->nr_members > 1)
-		attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP;
-
-	attr->inherit = !config->no_inherit;
-
-	/*
-	 * Some events get initialized with sample_(period/type) set,
-	 * like tracepoints. Clear it up for counting.
-	 */
-	attr->sample_period = 0;
-
-	if (config->identifier)
-		attr->sample_type = PERF_SAMPLE_IDENTIFIER;
-
-	/*
-	 * Disabling all counters initially, they will be enabled
-	 * either manually by us or by kernel via enable_on_exec
-	 * set later.
-	 */
-	if (perf_evsel__is_group_leader(evsel)) {
-		attr->disabled = 1;
-
-		/*
-		 * In case of initial_delay we enable tracee
-		 * events manually.
-		 */
-		if (target__none(&target) && !config->initial_delay)
-			attr->enable_on_exec = 1;
-	}
-
-	if (target__has_cpu(&target) && !target__has_per_thread(&target))
-		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
-
-	return perf_evsel__open_per_thread(evsel, evsel->threads);
-}
-
 static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
 				     union perf_event *event,
 				     struct perf_sample *sample __maybe_unused,
@@ -568,7 +516,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 
 	evlist__for_each_entry(evsel_list, counter) {
 try_again:
-		if (create_perf_stat_counter(counter, &stat_config) < 0) {
+		if (create_perf_stat_counter(counter, &stat_config, &target) < 0) {
 
 			/* Weak group failed. Reset the group. */
 			if ((errno == EINVAL || errno == EBADF) &&
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index a0061e0b0fad..3bd24255376a 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -435,3 +435,56 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
 
 	return ret;
 }
+
+int create_perf_stat_counter(struct perf_evsel *evsel,
+			     struct perf_stat_config *config,
+			     struct target *target)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+	struct perf_evsel *leader = evsel->leader;
+
+	if (config->scale) {
+		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
+				    PERF_FORMAT_TOTAL_TIME_RUNNING;
+	}
+
+	/*
+	 * The event is part of non trivial group, let's enable
+	 * the group read (for leader) and ID retrieval for all
+	 * members.
+	 */
+	if (leader->nr_members > 1)
+		attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP;
+
+	attr->inherit = !config->no_inherit;
+
+	/*
+	 * Some events get initialized with sample_(period/type) set,
+	 * like tracepoints. Clear it up for counting.
+	 */
+	attr->sample_period = 0;
+
+	if (config->identifier)
+		attr->sample_type = PERF_SAMPLE_IDENTIFIER;
+
+	/*
+	 * Disabling all counters initially, they will be enabled
+	 * either manually by us or by kernel via enable_on_exec
+	 * set later.
+	 */
+	if (perf_evsel__is_group_leader(evsel)) {
+		attr->disabled = 1;
+
+		/*
+		 * In case of initial_delay we enable tracee
+		 * events manually.
+		 */
+		if (target__none(target) && !config->initial_delay)
+			attr->enable_on_exec = 1;
+	}
+
+	if (target__has_cpu(target) && !target__has_per_thread(target))
+		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
+
+	return perf_evsel__open_per_thread(evsel, evsel->threads);
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 918cde064cdc..8fb596641545 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -175,4 +175,8 @@ int perf_event__process_stat_event(struct perf_tool *tool,
 size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
+
+int create_perf_stat_counter(struct perf_evsel *evsel,
+			     struct perf_stat_config *config,
+			     struct target *target);
 #endif
-- 
cgit v1.2.3


From 491073a6126644d3c60b677b777006deb3c0e16b Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:18 +0200
Subject: perf stat: Rename 'is_pipe' argument to 'attrs' in
 perf_stat_synthesize_config()

The attrs name makes more sense.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-10-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 142cff8eb12b..0a358c2e1a93 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -402,11 +402,11 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
 	workload_exec_errno = info->si_value.sival_int;
 }
 
-static int perf_stat_synthesize_config(bool is_pipe)
+static int perf_stat_synthesize_config(bool attrs)
 {
 	int err;
 
-	if (is_pipe) {
+	if (attrs) {
 		err = perf_event__synthesize_attrs(NULL, evsel_list,
 						   process_synthesized_event);
 		if (err < 0) {
@@ -418,7 +418,7 @@ static int perf_stat_synthesize_config(bool is_pipe)
 	err = perf_event__synthesize_extra_attr(NULL,
 						evsel_list,
 						process_synthesized_event,
-						is_pipe);
+						attrs);
 
 	err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads,
 						process_synthesized_event,
-- 
cgit v1.2.3


From 73d586c3917d5109bb547c16d90d0eb97203986a Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:19 +0200
Subject: perf stat: Add 'struct perf_stat_config' argument to
 perf_stat_synthesize_config()

Add a 'struct perf_stat_config' argument to perf_stat_synthesize_config(),
so we could synthesize arbitrary config.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-11-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 0a358c2e1a93..d0d19a5ffa85 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -402,7 +402,8 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
 	workload_exec_errno = info->si_value.sival_int;
 }
 
-static int perf_stat_synthesize_config(bool attrs)
+static int perf_stat_synthesize_config(struct perf_stat_config *config,
+				       bool attrs)
 {
 	int err;
 
@@ -435,7 +436,7 @@ static int perf_stat_synthesize_config(bool attrs)
 		return err;
 	}
 
-	err = perf_event__synthesize_stat_config(NULL, &stat_config,
+	err = perf_event__synthesize_stat_config(NULL, config,
 						 process_synthesized_event, NULL);
 	if (err < 0) {
 		pr_err("Couldn't synthesize config.\n");
@@ -606,7 +607,7 @@ try_again:
 		if (err < 0)
 			return err;
 
-		err = perf_stat_synthesize_config(is_pipe);
+		err = perf_stat_synthesize_config(&stat_config, is_pipe);
 		if (err < 0)
 			return err;
 	}
-- 
cgit v1.2.3


From 1821f4eb480bdd3c7c2a1863431ba539c7b0c1f8 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:20 +0200
Subject: perf stat: Add 'struct perf_tool' argument to
 perf_stat_synthesize_config()

So that we can use the function outside the 'perf stat' command with standard
synthesize functions, that take 'struct perf_tool *' argument.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-12-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index d0d19a5ffa85..ae5029875e87 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -403,12 +403,13 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
 }
 
 static int perf_stat_synthesize_config(struct perf_stat_config *config,
+				       struct perf_tool *tool,
 				       bool attrs)
 {
 	int err;
 
 	if (attrs) {
-		err = perf_event__synthesize_attrs(NULL, evsel_list,
+		err = perf_event__synthesize_attrs(tool, evsel_list,
 						   process_synthesized_event);
 		if (err < 0) {
 			pr_err("Couldn't synthesize attrs.\n");
@@ -416,12 +417,12 @@ static int perf_stat_synthesize_config(struct perf_stat_config *config,
 		}
 	}
 
-	err = perf_event__synthesize_extra_attr(NULL,
+	err = perf_event__synthesize_extra_attr(tool,
 						evsel_list,
 						process_synthesized_event,
 						attrs);
 
-	err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads,
+	err = perf_event__synthesize_thread_map2(tool, evsel_list->threads,
 						process_synthesized_event,
 						NULL);
 	if (err < 0) {
@@ -429,14 +430,14 @@ static int perf_stat_synthesize_config(struct perf_stat_config *config,
 		return err;
 	}
 
-	err = perf_event__synthesize_cpu_map(NULL, evsel_list->cpus,
+	err = perf_event__synthesize_cpu_map(tool, evsel_list->cpus,
 					     process_synthesized_event, NULL);
 	if (err < 0) {
 		pr_err("Couldn't synthesize thread map.\n");
 		return err;
 	}
 
-	err = perf_event__synthesize_stat_config(NULL, config,
+	err = perf_event__synthesize_stat_config(tool, config,
 						 process_synthesized_event, NULL);
 	if (err < 0) {
 		pr_err("Couldn't synthesize config.\n");
@@ -607,7 +608,7 @@ try_again:
 		if (err < 0)
 			return err;
 
-		err = perf_stat_synthesize_config(&stat_config, is_pipe);
+		err = perf_stat_synthesize_config(&stat_config, NULL, is_pipe);
 		if (err < 0)
 			return err;
 	}
-- 
cgit v1.2.3


From 1c21e9899d6a9ea72d4d678faa7b0ec22bcf59a9 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:21 +0200
Subject: perf stat: Add 'struct perf_evlist' argument to
 perf_stat_synthesize_config()

Get rid of the 'evsel_list' global variable dependency, here in
perf_stat_synthesize_config() we are adding the 'evlist' arg.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-13-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index ae5029875e87..cb36344c25b7 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -404,12 +404,13 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
 
 static int perf_stat_synthesize_config(struct perf_stat_config *config,
 				       struct perf_tool *tool,
+				       struct perf_evlist *evlist,
 				       bool attrs)
 {
 	int err;
 
 	if (attrs) {
-		err = perf_event__synthesize_attrs(tool, evsel_list,
+		err = perf_event__synthesize_attrs(tool, evlist,
 						   process_synthesized_event);
 		if (err < 0) {
 			pr_err("Couldn't synthesize attrs.\n");
@@ -417,12 +418,11 @@ static int perf_stat_synthesize_config(struct perf_stat_config *config,
 		}
 	}
 
-	err = perf_event__synthesize_extra_attr(tool,
-						evsel_list,
+	err = perf_event__synthesize_extra_attr(tool, evlist,
 						process_synthesized_event,
 						attrs);
 
-	err = perf_event__synthesize_thread_map2(tool, evsel_list->threads,
+	err = perf_event__synthesize_thread_map2(tool, evlist->threads,
 						process_synthesized_event,
 						NULL);
 	if (err < 0) {
@@ -430,7 +430,7 @@ static int perf_stat_synthesize_config(struct perf_stat_config *config,
 		return err;
 	}
 
-	err = perf_event__synthesize_cpu_map(tool, evsel_list->cpus,
+	err = perf_event__synthesize_cpu_map(tool, evlist->cpus,
 					     process_synthesized_event, NULL);
 	if (err < 0) {
 		pr_err("Couldn't synthesize thread map.\n");
@@ -608,7 +608,8 @@ try_again:
 		if (err < 0)
 			return err;
 
-		err = perf_stat_synthesize_config(&stat_config, NULL, is_pipe);
+		err = perf_stat_synthesize_config(&stat_config, NULL, evsel_list,
+						  is_pipe);
 		if (err < 0)
 			return err;
 	}
-- 
cgit v1.2.3


From c2c247f2dd87706961fa16d033f9dbf173145e70 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:22 +0200
Subject: perf stat: Add 'perf_event__handler_t' argument to
 perf_stat_synthesize_config()

So that it's completely independent and can be used outside the 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-14-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index cb36344c25b7..1171d4e00276 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -405,40 +405,37 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
 static int perf_stat_synthesize_config(struct perf_stat_config *config,
 				       struct perf_tool *tool,
 				       struct perf_evlist *evlist,
+				       perf_event__handler_t process,
 				       bool attrs)
 {
 	int err;
 
 	if (attrs) {
-		err = perf_event__synthesize_attrs(tool, evlist,
-						   process_synthesized_event);
+		err = perf_event__synthesize_attrs(tool, evlist, process);
 		if (err < 0) {
 			pr_err("Couldn't synthesize attrs.\n");
 			return err;
 		}
 	}
 
-	err = perf_event__synthesize_extra_attr(tool, evlist,
-						process_synthesized_event,
+	err = perf_event__synthesize_extra_attr(tool, evlist, process,
 						attrs);
 
 	err = perf_event__synthesize_thread_map2(tool, evlist->threads,
-						process_synthesized_event,
-						NULL);
+						 process, NULL);
 	if (err < 0) {
 		pr_err("Couldn't synthesize thread map.\n");
 		return err;
 	}
 
 	err = perf_event__synthesize_cpu_map(tool, evlist->cpus,
-					     process_synthesized_event, NULL);
+					     process, NULL);
 	if (err < 0) {
 		pr_err("Couldn't synthesize thread map.\n");
 		return err;
 	}
 
-	err = perf_event__synthesize_stat_config(tool, config,
-						 process_synthesized_event, NULL);
+	err = perf_event__synthesize_stat_config(tool, config, process, NULL);
 	if (err < 0) {
 		pr_err("Couldn't synthesize config.\n");
 		return err;
@@ -609,7 +606,7 @@ try_again:
 			return err;
 
 		err = perf_stat_synthesize_config(&stat_config, NULL, evsel_list,
-						  is_pipe);
+						  process_synthesized_event, is_pipe);
 		if (err < 0)
 			return err;
 	}
-- 
cgit v1.2.3


From 0a4e64d391a2c771ae33e648cf84d4492369560c Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:23 +0200
Subject: perf stat: Move perf_stat_synthesize_config() to stat.c

So that it can be used globally.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-15-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 42 ------------------------------------------
 tools/perf/util/stat.c    | 42 ++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/stat.h    |  6 ++++++
 3 files changed, 48 insertions(+), 42 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 1171d4e00276..54768ec15dbc 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -402,48 +402,6 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
 	workload_exec_errno = info->si_value.sival_int;
 }
 
-static int perf_stat_synthesize_config(struct perf_stat_config *config,
-				       struct perf_tool *tool,
-				       struct perf_evlist *evlist,
-				       perf_event__handler_t process,
-				       bool attrs)
-{
-	int err;
-
-	if (attrs) {
-		err = perf_event__synthesize_attrs(tool, evlist, process);
-		if (err < 0) {
-			pr_err("Couldn't synthesize attrs.\n");
-			return err;
-		}
-	}
-
-	err = perf_event__synthesize_extra_attr(tool, evlist, process,
-						attrs);
-
-	err = perf_event__synthesize_thread_map2(tool, evlist->threads,
-						 process, NULL);
-	if (err < 0) {
-		pr_err("Couldn't synthesize thread map.\n");
-		return err;
-	}
-
-	err = perf_event__synthesize_cpu_map(tool, evlist->cpus,
-					     process, NULL);
-	if (err < 0) {
-		pr_err("Couldn't synthesize thread map.\n");
-		return err;
-	}
-
-	err = perf_event__synthesize_stat_config(tool, config, process, NULL);
-	if (err < 0) {
-		pr_err("Couldn't synthesize config.\n");
-		return err;
-	}
-
-	return 0;
-}
-
 static bool perf_evsel__should_store_id(struct perf_evsel *counter)
 {
 	return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID;
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 3bd24255376a..5d3172bcc4ae 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -488,3 +488,45 @@ int create_perf_stat_counter(struct perf_evsel *evsel,
 
 	return perf_evsel__open_per_thread(evsel, evsel->threads);
 }
+
+int perf_stat_synthesize_config(struct perf_stat_config *config,
+				struct perf_tool *tool,
+				struct perf_evlist *evlist,
+				perf_event__handler_t process,
+				bool attrs)
+{
+	int err;
+
+	if (attrs) {
+		err = perf_event__synthesize_attrs(tool, evlist, process);
+		if (err < 0) {
+			pr_err("Couldn't synthesize attrs.\n");
+			return err;
+		}
+	}
+
+	err = perf_event__synthesize_extra_attr(tool, evlist, process,
+						attrs);
+
+	err = perf_event__synthesize_thread_map2(tool, evlist->threads,
+						 process, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_cpu_map(tool, evlist->cpus,
+					     process, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_stat_config(tool, config, process, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize config.\n");
+		return err;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 8fb596641545..da6a706daecc 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -7,6 +7,7 @@
 #include "xyarray.h"
 #include "rblist.h"
 #include "perf.h"
+#include "event.h"
 
 struct stats {
 	double n, mean, M2;
@@ -179,4 +180,9 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
 int create_perf_stat_counter(struct perf_evsel *evsel,
 			     struct perf_stat_config *config,
 			     struct target *target);
+int perf_stat_synthesize_config(struct perf_stat_config *config,
+				struct perf_tool *tool,
+				struct perf_evlist *evlist,
+				perf_event__handler_t process,
+				bool attrs);
 #endif
-- 
cgit v1.2.3


From a5a9eac1a018ad3bfcf9a3ec11eae99fd35f466b Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:24 +0200
Subject: perf stat: Introduce perf_evlist__print_counters()

To be in charge of printing out the stat output. It will be moved out of
the 'perf stat' command in the following patches.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-16-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 54768ec15dbc..db11832bbdbc 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1692,7 +1692,10 @@ static void print_footer(void)
 			"the same PMU. Try reorganizing the group.\n");
 }
 
-static void print_counters(struct timespec *ts, int argc, const char **argv)
+static void
+perf_evlist__print_counters(struct perf_evlist *evlist,
+			    struct timespec *ts,
+			    int argc, const char **argv)
 {
 	int interval = stat_config.interval;
 	struct perf_evsel *counter;
@@ -1724,14 +1727,14 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 		print_aggr(prefix);
 		break;
 	case AGGR_THREAD:
-		evlist__for_each_entry(evsel_list, counter) {
+		evlist__for_each_entry(evlist, counter) {
 			if (is_duration_time(counter))
 				continue;
 			print_aggr_thread(counter, prefix);
 		}
 		break;
 	case AGGR_GLOBAL:
-		evlist__for_each_entry(evsel_list, counter) {
+		evlist__for_each_entry(evlist, counter) {
 			if (is_duration_time(counter))
 				continue;
 			print_counter_aggr(counter, prefix);
@@ -1743,7 +1746,7 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 		if (metric_only)
 			print_no_aggr_metric(prefix);
 		else {
-			evlist__for_each_entry(evsel_list, counter) {
+			evlist__for_each_entry(evlist, counter) {
 				if (is_duration_time(counter))
 					continue;
 				print_counter(counter, prefix);
@@ -1761,6 +1764,11 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	fflush(stat_config.output);
 }
 
+static void print_counters(struct timespec *ts, int argc, const char **argv)
+{
+	perf_evlist__print_counters(evsel_list, ts, argc, argv);
+}
+
 static volatile int signr = -1;
 
 static void skip_signal(int signo)
-- 
cgit v1.2.3


From 0174820a8ba108f2e72dac5caaea3500c8ca6323 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:25 +0200
Subject: perf stat: Move STAT_RECORD out of perf_evlist__print_counters()

It's stat related and should stay in the 'perf stat' command.  The
perf_evlist__print_counters function will be moved out in the following
patches.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-17-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index db11832bbdbc..4ffbb6594eb6 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1701,10 +1701,6 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 	struct perf_evsel *counter;
 	char buf[64], *prefix = NULL;
 
-	/* Do not print anything if we record to the pipe. */
-	if (STAT_RECORD && perf_stat.data.is_pipe)
-		return;
-
 	if (interval)
 		print_interval(prefix = buf, ts);
 	else
@@ -1766,6 +1762,10 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 
 static void print_counters(struct timespec *ts, int argc, const char **argv)
 {
+	/* Do not print anything if we record to the pipe. */
+	if (STAT_RECORD && perf_stat.data.is_pipe)
+		return;
+
 	perf_evlist__print_counters(evsel_list, ts, argc, argv);
 }
 
-- 
cgit v1.2.3


From b64df7f33743cd6095b4a007f5f15ff4432fbcf5 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:26 +0200
Subject: perf stat: Add 'struct perf_stat_config' argument to
 perf_evlist__print_counters()

Add a 'struct perf_stat_config' argument to perf_evlist__print_counters(),
so that it can be moved out of the 'perf stat' command to generic object
in the following patches.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-18-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 4ffbb6594eb6..f340641fe63a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1694,10 +1694,11 @@ static void print_footer(void)
 
 static void
 perf_evlist__print_counters(struct perf_evlist *evlist,
+			    struct perf_stat_config *config,
 			    struct timespec *ts,
 			    int argc, const char **argv)
 {
-	int interval = stat_config.interval;
+	int interval = config->interval;
 	struct perf_evsel *counter;
 	char buf[64], *prefix = NULL;
 
@@ -1713,11 +1714,11 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 			print_metric_headers(prefix, false);
 		if (num_print_iv++ == 25)
 			num_print_iv = 0;
-		if (stat_config.aggr_mode == AGGR_GLOBAL && prefix)
-			fprintf(stat_config.output, "%s", prefix);
+		if (config->aggr_mode == AGGR_GLOBAL && prefix)
+			fprintf(config->output, "%s", prefix);
 	}
 
-	switch (stat_config.aggr_mode) {
+	switch (config->aggr_mode) {
 	case AGGR_CORE:
 	case AGGR_SOCKET:
 		print_aggr(prefix);
@@ -1736,7 +1737,7 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 			print_counter_aggr(counter, prefix);
 		}
 		if (metric_only)
-			fputc('\n', stat_config.output);
+			fputc('\n', config->output);
 		break;
 	case AGGR_NONE:
 		if (metric_only)
@@ -1757,7 +1758,7 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 	if (!interval && !csv_output)
 		print_footer();
 
-	fflush(stat_config.output);
+	fflush(config->output);
 }
 
 static void print_counters(struct timespec *ts, int argc, const char **argv)
@@ -1766,7 +1767,8 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	if (STAT_RECORD && perf_stat.data.is_pipe)
 		return;
 
-	perf_evlist__print_counters(evsel_list, ts, argc, argv);
+	perf_evlist__print_counters(evsel_list, &stat_config,
+				    ts, argc, argv);
 }
 
 static volatile int signr = -1;
-- 
cgit v1.2.3


From f3ca50e61ff4aebfbefc666be2e064d277ad524c Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:27 +0200
Subject: perf stat: Pass 'struct perf_stat_config' argument to local print
 functions

Add 'struct perf_stat_config' argument to print functions, so that those
functions can be moved out of the 'perf stat' command to a generic class
in the following patches.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-19-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 149 +++++++++++++++++++++++++---------------------
 1 file changed, 80 insertions(+), 69 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f340641fe63a..f56da22abccc 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -660,30 +660,33 @@ static int run_perf_stat(int argc, const char **argv, int run_idx)
 	return ret;
 }
 
-static void print_running(u64 run, u64 ena)
+static void print_running(struct perf_stat_config *config,
+			  u64 run, u64 ena)
 {
 	if (csv_output) {
-		fprintf(stat_config.output, "%s%" PRIu64 "%s%.2f",
+		fprintf(config->output, "%s%" PRIu64 "%s%.2f",
 					csv_sep,
 					run,
 					csv_sep,
 					ena ? 100.0 * run / ena : 100.0);
 	} else if (run != ena) {
-		fprintf(stat_config.output, "  (%.2f%%)", 100.0 * run / ena);
+		fprintf(config->output, "  (%.2f%%)", 100.0 * run / ena);
 	}
 }
 
-static void print_noise_pct(double total, double avg)
+static void print_noise_pct(struct perf_stat_config *config,
+			    double total, double avg)
 {
 	double pct = rel_stddev_stats(total, avg);
 
 	if (csv_output)
-		fprintf(stat_config.output, "%s%.2f%%", csv_sep, pct);
+		fprintf(config->output, "%s%.2f%%", csv_sep, pct);
 	else if (pct)
-		fprintf(stat_config.output, "  ( +-%6.2f%% )", pct);
+		fprintf(config->output, "  ( +-%6.2f%% )", pct);
 }
 
-static void print_noise(struct perf_evsel *evsel, double avg)
+static void print_noise(struct perf_stat_config *config,
+			struct perf_evsel *evsel, double avg)
 {
 	struct perf_stat_evsel *ps;
 
@@ -691,7 +694,7 @@ static void print_noise(struct perf_evsel *evsel, double avg)
 		return;
 
 	ps = evsel->stats;
-	print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
+	print_noise_pct(config, stddev_stats(&ps->res_stats[0]), avg);
 }
 
 static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
@@ -987,13 +990,14 @@ static bool is_mixed_hw_group(struct perf_evsel *counter)
 	return false;
 }
 
-static void printout(int id, int nr, struct perf_evsel *counter, double uval,
+static void printout(struct perf_stat_config *config, int id, int nr,
+		     struct perf_evsel *counter, double uval,
 		     char *prefix, u64 run, u64 ena, double noise,
 		     struct runtime_stat *st)
 {
 	struct perf_stat_output_ctx out;
 	struct outstate os = {
-		.fh = stat_config.output,
+		.fh = config->output,
 		.prefix = prefix ? prefix : "",
 		.id = id,
 		.nr = nr,
@@ -1023,7 +1027,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 		pm = print_metric_csv;
 		nl = new_line_csv;
 		os.nfields = 3;
-		os.nfields += aggr_fields[stat_config.aggr_mode];
+		os.nfields += aggr_fields[config->aggr_mode];
 		if (counter->cgrp)
 			os.nfields++;
 	}
@@ -1034,7 +1038,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 		}
 		aggr_printout(counter, id, nr);
 
-		fprintf(stat_config.output, "%*s%s",
+		fprintf(config->output, "%*s%s",
 			csv_output ? 0 : 18,
 			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
 			csv_sep);
@@ -1045,22 +1049,22 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 				print_mixed_hw_group_error = 1;
 		}
 
-		fprintf(stat_config.output, "%-*s%s",
+		fprintf(config->output, "%-*s%s",
 			csv_output ? 0 : unit_width,
 			counter->unit, csv_sep);
 
-		fprintf(stat_config.output, "%*s",
+		fprintf(config->output, "%*s",
 			csv_output ? 0 : -25,
 			perf_evsel__name(counter));
 
 		if (counter->cgrp)
-			fprintf(stat_config.output, "%s%s",
+			fprintf(config->output, "%s%s",
 				csv_sep, counter->cgrp->name);
 
 		if (!csv_output)
 			pm(&os, NULL, NULL, "", 0);
-		print_noise(counter, noise);
-		print_running(run, ena);
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
 		if (csv_output)
 			pm(&os, NULL, NULL, "", 0);
 		return;
@@ -1075,16 +1079,16 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	out.force_header = false;
 
 	if (csv_output && !metric_only) {
-		print_noise(counter, noise);
-		print_running(run, ena);
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
 	}
 
 	perf_stat__print_shadow_stats(counter, uval,
 				first_shadow_cpu(counter, id),
 				&out, &metric_events, st);
 	if (!csv_output && !metric_only) {
-		print_noise(counter, noise);
-		print_running(run, ena);
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
 	}
 }
 
@@ -1211,9 +1215,10 @@ static void aggr_cb(struct perf_evsel *counter, void *data, bool first)
 	}
 }
 
-static void print_aggr(char *prefix)
+static void print_aggr(struct perf_stat_config *config,
+		       char *prefix)
 {
-	FILE *output = stat_config.output;
+	FILE *output = config->output;
 	struct perf_evsel *counter;
 	int s, id, nr;
 	double uval;
@@ -1256,8 +1261,8 @@ static void print_aggr(char *prefix)
 				fprintf(output, "%s", prefix);
 
 			uval = val * counter->scale;
-			printout(id, nr, counter, uval, prefix, run, ena, 1.0,
-				 &rt_stat);
+			printout(config, id, nr, counter, uval, prefix,
+				 run, ena, 1.0, &rt_stat);
 			if (!metric_only)
 				fputc('\n', output);
 		}
@@ -1320,9 +1325,10 @@ static struct perf_aggr_thread_value *sort_aggr_thread(
 	return buf;
 }
 
-static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
+static void print_aggr_thread(struct perf_stat_config *config,
+			      struct perf_evsel *counter, char *prefix)
 {
-	FILE *output = stat_config.output;
+	FILE *output = config->output;
 	int nthreads = thread_map__nr(counter->threads);
 	int ncpus = cpu_map__nr(counter->cpus);
 	int thread, sorted_threads, id;
@@ -1339,12 +1345,12 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		id = buf[thread].id;
-		if (stat_config.stats)
-			printout(id, 0, buf[thread].counter, buf[thread].uval,
+		if (config->stats)
+			printout(config, id, 0, buf[thread].counter, buf[thread].uval,
 				 prefix, buf[thread].run, buf[thread].ena, 1.0,
-				 &stat_config.stats[id]);
+				 &config->stats[id]);
 		else
-			printout(id, 0, buf[thread].counter, buf[thread].uval,
+			printout(config, id, 0, buf[thread].counter, buf[thread].uval,
 				 prefix, buf[thread].run, buf[thread].ena, 1.0,
 				 &rt_stat);
 		fputc('\n', output);
@@ -1372,9 +1378,10 @@ static void counter_aggr_cb(struct perf_evsel *counter, void *data,
  * Print out the results of a single counter:
  * aggregated counts in system-wide mode
  */
-static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
+static void print_counter_aggr(struct perf_stat_config *config,
+			       struct perf_evsel *counter, char *prefix)
 {
-	FILE *output = stat_config.output;
+	FILE *output = config->output;
 	double uval;
 	struct caggr_data cd = { .avg = 0.0 };
 
@@ -1385,7 +1392,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 		fprintf(output, "%s", prefix);
 
 	uval = cd.avg * counter->scale;
-	printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
+	printout(config, -1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
 		 cd.avg, &rt_stat);
 	if (!metric_only)
 		fprintf(output, "\n");
@@ -1405,9 +1412,10 @@ static void counter_cb(struct perf_evsel *counter, void *data,
  * Print out the results of a single counter:
  * does not use aggregated count in system-wide
  */
-static void print_counter(struct perf_evsel *counter, char *prefix)
+static void print_counter(struct perf_stat_config *config,
+			  struct perf_evsel *counter, char *prefix)
 {
-	FILE *output = stat_config.output;
+	FILE *output = config->output;
 	u64 ena, run, val;
 	double uval;
 	int cpu;
@@ -1425,14 +1433,15 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		uval = val * counter->scale;
-		printout(cpu, 0, counter, uval, prefix, run, ena, 1.0,
+		printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
 			 &rt_stat);
 
 		fputc('\n', output);
 	}
 }
 
-static void print_no_aggr_metric(char *prefix)
+static void print_no_aggr_metric(struct perf_stat_config *config,
+				 char *prefix)
 {
 	int cpu;
 	int nrcpus = 0;
@@ -1445,7 +1454,7 @@ static void print_no_aggr_metric(char *prefix)
 		bool first = true;
 
 		if (prefix)
-			fputs(prefix, stat_config.output);
+			fputs(prefix, config->output);
 		evlist__for_each_entry(evsel_list, counter) {
 			if (is_duration_time(counter))
 				continue;
@@ -1458,10 +1467,10 @@ static void print_no_aggr_metric(char *prefix)
 			run = perf_counts(counter->counts, cpu, 0)->run;
 
 			uval = val * counter->scale;
-			printout(cpu, 0, counter, uval, prefix, run, ena, 1.0,
+			printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
 				 &rt_stat);
 		}
-		fputc('\n', stat_config.output);
+		fputc('\n', config->output);
 	}
 }
 
@@ -1481,25 +1490,25 @@ static const char *aggr_header_csv[] = {
 	[AGGR_GLOBAL] 	=	""
 };
 
-static void print_metric_headers(const char *prefix, bool no_indent)
+static void print_metric_headers(struct perf_stat_config *config,
+				 const char *prefix, bool no_indent)
 {
 	struct perf_stat_output_ctx out;
 	struct perf_evsel *counter;
 	struct outstate os = {
-		.fh = stat_config.output
+		.fh = config->output
 	};
 
 	if (prefix)
-		fprintf(stat_config.output, "%s", prefix);
+		fprintf(config->output, "%s", prefix);
 
 	if (!csv_output && !no_indent)
-		fprintf(stat_config.output, "%*s",
-			aggr_header_lens[stat_config.aggr_mode], "");
+		fprintf(config->output, "%*s",
+			aggr_header_lens[config->aggr_mode], "");
 	if (csv_output) {
-		if (stat_config.interval)
-			fputs("time,", stat_config.output);
-		fputs(aggr_header_csv[stat_config.aggr_mode],
-			stat_config.output);
+		if (config->interval)
+			fputs("time,", config->output);
+		fputs(aggr_header_csv[config->aggr_mode], config->output);
 	}
 
 	/* Print metrics headers only */
@@ -1518,12 +1527,13 @@ static void print_metric_headers(const char *prefix, bool no_indent)
 					      &metric_events,
 					      &rt_stat);
 	}
-	fputc('\n', stat_config.output);
+	fputc('\n', config->output);
 }
 
-static void print_interval(char *prefix, struct timespec *ts)
+static void print_interval(struct perf_stat_config *config,
+			   char *prefix, struct timespec *ts)
 {
-	FILE *output = stat_config.output;
+	FILE *output = config->output;
 	static int num_print_interval;
 
 	if (interval_clear)
@@ -1532,7 +1542,7 @@ static void print_interval(char *prefix, struct timespec *ts)
 	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
 
 	if ((num_print_interval == 0 && !csv_output) || interval_clear) {
-		switch (stat_config.aggr_mode) {
+		switch (config->aggr_mode) {
 		case AGGR_SOCKET:
 			fprintf(output, "#           time socket cpus");
 			if (!metric_only)
@@ -1564,14 +1574,15 @@ static void print_interval(char *prefix, struct timespec *ts)
 	}
 
 	if ((num_print_interval == 0 || interval_clear) && metric_only)
-		print_metric_headers(" ", true);
+		print_metric_headers(config, " ", true);
 	if (++num_print_interval == 25)
 		num_print_interval = 0;
 }
 
-static void print_header(int argc, const char **argv)
+static void print_header(struct perf_stat_config *config,
+			 int argc, const char **argv)
 {
-	FILE *output = stat_config.output;
+	FILE *output = config->output;
 	int i;
 
 	fflush(stdout);
@@ -1639,10 +1650,10 @@ static double timeval2double(struct timeval *t)
 	return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC;
 }
 
-static void print_footer(void)
+static void print_footer(struct perf_stat_config *config)
 {
 	double avg = avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC;
-	FILE *output = stat_config.output;
+	FILE *output = config->output;
 	int n;
 
 	if (!null_run)
@@ -1673,7 +1684,7 @@ static void print_footer(void)
 		fprintf(output, " %17.*f +- %.*f seconds time elapsed",
 			precision, avg, precision, sd);
 
-		print_noise_pct(sd, avg);
+		print_noise_pct(config, sd, avg);
 	}
 	fprintf(output, "\n\n");
 
@@ -1703,15 +1714,15 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 	char buf[64], *prefix = NULL;
 
 	if (interval)
-		print_interval(prefix = buf, ts);
+		print_interval(config, prefix = buf, ts);
 	else
-		print_header(argc, argv);
+		print_header(config, argc, argv);
 
 	if (metric_only) {
 		static int num_print_iv;
 
 		if (num_print_iv == 0 && !interval)
-			print_metric_headers(prefix, false);
+			print_metric_headers(config, prefix, false);
 		if (num_print_iv++ == 25)
 			num_print_iv = 0;
 		if (config->aggr_mode == AGGR_GLOBAL && prefix)
@@ -1721,32 +1732,32 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 	switch (config->aggr_mode) {
 	case AGGR_CORE:
 	case AGGR_SOCKET:
-		print_aggr(prefix);
+		print_aggr(config, prefix);
 		break;
 	case AGGR_THREAD:
 		evlist__for_each_entry(evlist, counter) {
 			if (is_duration_time(counter))
 				continue;
-			print_aggr_thread(counter, prefix);
+			print_aggr_thread(config, counter, prefix);
 		}
 		break;
 	case AGGR_GLOBAL:
 		evlist__for_each_entry(evlist, counter) {
 			if (is_duration_time(counter))
 				continue;
-			print_counter_aggr(counter, prefix);
+			print_counter_aggr(config, counter, prefix);
 		}
 		if (metric_only)
 			fputc('\n', config->output);
 		break;
 	case AGGR_NONE:
 		if (metric_only)
-			print_no_aggr_metric(prefix);
+			print_no_aggr_metric(config, prefix);
 		else {
 			evlist__for_each_entry(evlist, counter) {
 				if (is_duration_time(counter))
 					continue;
-				print_counter(counter, prefix);
+				print_counter(config, counter, prefix);
 			}
 		}
 		break;
@@ -1756,7 +1767,7 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 	}
 
 	if (!interval && !csv_output)
-		print_footer();
+		print_footer(config);
 
 	fflush(config->output);
 }
-- 
cgit v1.2.3


From 6ca9a082b1908ff7f8adedf08166043b83b266f6 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:28 +0200
Subject: perf stat: Pass a 'struct perf_stat_config' argument to global print
 functions

Add 'struct perf_stat_config' argument to the global print functions, so
that these functions can be used out of the 'perf stat' command code.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-20-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c   |   8 ++-
 tools/perf/builtin-stat.c     |  74 ++++++++++++---------
 tools/perf/util/stat-shadow.c | 147 +++++++++++++++++++++++-------------------
 tools/perf/util/stat.h        |   8 ++-
 4 files changed, 131 insertions(+), 106 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ba481d73f910..6176bae177c2 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1544,7 +1544,8 @@ struct metric_ctx {
 	FILE 			*fp;
 };
 
-static void script_print_metric(void *ctx, const char *color,
+static void script_print_metric(struct perf_stat_config *config __maybe_unused,
+				void *ctx, const char *color,
 			        const char *fmt,
 			        const char *unit, double val)
 {
@@ -1562,7 +1563,8 @@ static void script_print_metric(void *ctx, const char *color,
 	fprintf(mctx->fp, " %s\n", unit);
 }
 
-static void script_new_line(void *ctx)
+static void script_new_line(struct perf_stat_config *config __maybe_unused,
+			    void *ctx)
 {
 	struct metric_ctx *mctx = ctx;
 
@@ -1608,7 +1610,7 @@ static void perf_sample__fprint_metric(struct perf_script *script,
 	evsel_script(evsel)->val = val;
 	if (evsel_script(evsel->leader)->gnum == evsel->leader->nr_members) {
 		for_each_group_member (ev2, evsel->leader) {
-			perf_stat__print_shadow_stats(ev2,
+			perf_stat__print_shadow_stats(&stat_config, ev2,
 						      evsel_script(ev2)->val,
 						      sample->cpu,
 						      &ctx,
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f56da22abccc..7a3361308e61 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -697,11 +697,12 @@ static void print_noise(struct perf_stat_config *config,
 	print_noise_pct(config, stddev_stats(&ps->res_stats[0]), avg);
 }
 
-static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
+static void aggr_printout(struct perf_stat_config *config,
+			  struct perf_evsel *evsel, int id, int nr)
 {
-	switch (stat_config.aggr_mode) {
+	switch (config->aggr_mode) {
 	case AGGR_CORE:
-		fprintf(stat_config.output, "S%d-C%*d%s%*d%s",
+		fprintf(config->output, "S%d-C%*d%s%*d%s",
 			cpu_map__id_to_socket(id),
 			csv_output ? 0 : -8,
 			cpu_map__id_to_cpu(id),
@@ -711,7 +712,7 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 			csv_sep);
 		break;
 	case AGGR_SOCKET:
-		fprintf(stat_config.output, "S%*d%s%*d%s",
+		fprintf(config->output, "S%*d%s%*d%s",
 			csv_output ? 0 : -5,
 			id,
 			csv_sep,
@@ -720,12 +721,12 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 			csv_sep);
 			break;
 	case AGGR_NONE:
-		fprintf(stat_config.output, "CPU%*d%s",
+		fprintf(config->output, "CPU%*d%s",
 			csv_output ? 0 : -4,
 			perf_evsel__cpus(evsel)->map[id], csv_sep);
 		break;
 	case AGGR_THREAD:
-		fprintf(stat_config.output, "%*s-%*d%s",
+		fprintf(config->output, "%*s-%*d%s",
 			csv_output ? 0 : 16,
 			thread_map__comm(evsel->threads, id),
 			csv_output ? 0 : -8,
@@ -750,24 +751,27 @@ struct outstate {
 
 #define METRIC_LEN  35
 
-static void new_line_std(void *ctx)
+static void new_line_std(struct perf_stat_config *config __maybe_unused,
+			 void *ctx)
 {
 	struct outstate *os = ctx;
 
 	os->newline = true;
 }
 
-static void do_new_line_std(struct outstate *os)
+static void do_new_line_std(struct perf_stat_config *config,
+			    struct outstate *os)
 {
 	fputc('\n', os->fh);
 	fputs(os->prefix, os->fh);
-	aggr_printout(os->evsel, os->id, os->nr);
-	if (stat_config.aggr_mode == AGGR_NONE)
+	aggr_printout(config, os->evsel, os->id, os->nr);
+	if (config->aggr_mode == AGGR_NONE)
 		fprintf(os->fh, "        ");
 	fprintf(os->fh, "                                                 ");
 }
 
-static void print_metric_std(void *ctx, const char *color, const char *fmt,
+static void print_metric_std(struct perf_stat_config *config,
+			     void *ctx, const char *color, const char *fmt,
 			     const char *unit, double val)
 {
 	struct outstate *os = ctx;
@@ -783,7 +787,7 @@ static void print_metric_std(void *ctx, const char *color, const char *fmt,
 	}
 
 	if (newline)
-		do_new_line_std(os);
+		do_new_line_std(config, os);
 
 	n = fprintf(out, " # ");
 	if (color)
@@ -793,7 +797,7 @@ static void print_metric_std(void *ctx, const char *color, const char *fmt,
 	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
 }
 
-static void new_line_csv(void *ctx)
+static void new_line_csv(struct perf_stat_config *config, void *ctx)
 {
 	struct outstate *os = ctx;
 	int i;
@@ -801,12 +805,13 @@ static void new_line_csv(void *ctx)
 	fputc('\n', os->fh);
 	if (os->prefix)
 		fprintf(os->fh, "%s%s", os->prefix, csv_sep);
-	aggr_printout(os->evsel, os->id, os->nr);
+	aggr_printout(config, os->evsel, os->id, os->nr);
 	for (i = 0; i < os->nfields; i++)
 		fputs(csv_sep, os->fh);
 }
 
-static void print_metric_csv(void *ctx,
+static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
+			     void *ctx,
 			     const char *color __maybe_unused,
 			     const char *fmt, const char *unit, double val)
 {
@@ -853,7 +858,8 @@ static const char *fixunit(char *buf, struct perf_evsel *evsel,
 	return unit;
 }
 
-static void print_metric_only(void *ctx, const char *color, const char *fmt,
+static void print_metric_only(struct perf_stat_config *config __maybe_unused,
+			      void *ctx, const char *color, const char *fmt,
 			      const char *unit, double val)
 {
 	struct outstate *os = ctx;
@@ -874,7 +880,8 @@ static void print_metric_only(void *ctx, const char *color, const char *fmt,
 	fprintf(out, "%*s ", mlen, str);
 }
 
-static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
+static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused,
+				  void *ctx, const char *color __maybe_unused,
 				  const char *fmt,
 				  const char *unit, double val)
 {
@@ -894,11 +901,13 @@ static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
 	fprintf(out, "%s%s", vals, csv_sep);
 }
 
-static void new_line_metric(void *ctx __maybe_unused)
+static void new_line_metric(struct perf_stat_config *config __maybe_unused,
+			    void *ctx __maybe_unused)
 {
 }
 
-static void print_metric_header(void *ctx, const char *color __maybe_unused,
+static void print_metric_header(struct perf_stat_config *config __maybe_unused,
+				void *ctx, const char *color __maybe_unused,
 				const char *fmt __maybe_unused,
 				const char *unit, double val __maybe_unused)
 {
@@ -936,9 +945,10 @@ static int first_shadow_cpu(struct perf_evsel *evsel, int id)
 	return 0;
 }
 
-static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
+static void abs_printout(struct perf_stat_config *config,
+			 int id, int nr, struct perf_evsel *evsel, double avg)
 {
-	FILE *output = stat_config.output;
+	FILE *output = config->output;
 	double sc =  evsel->scale;
 	const char *fmt;
 
@@ -951,7 +961,7 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 			fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
 	}
 
-	aggr_printout(evsel, id, nr);
+	aggr_printout(config, evsel, id, nr);
 
 	fprintf(output, fmt, avg, csv_sep);
 
@@ -1004,7 +1014,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 		.evsel = counter,
 	};
 	print_metric_t pm = print_metric_std;
-	void (*nl)(void *);
+	new_line_t nl;
 
 	if (metric_only) {
 		nl = new_line_metric;
@@ -1033,10 +1043,10 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 	}
 	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
 		if (metric_only) {
-			pm(&os, NULL, "", "", 0);
+			pm(config, &os, NULL, "", "", 0);
 			return;
 		}
-		aggr_printout(counter, id, nr);
+		aggr_printout(config, counter, id, nr);
 
 		fprintf(config->output, "%*s%s",
 			csv_output ? 0 : 18,
@@ -1062,16 +1072,16 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 				csv_sep, counter->cgrp->name);
 
 		if (!csv_output)
-			pm(&os, NULL, NULL, "", 0);
+			pm(config, &os, NULL, NULL, "", 0);
 		print_noise(config, counter, noise);
 		print_running(config, run, ena);
 		if (csv_output)
-			pm(&os, NULL, NULL, "", 0);
+			pm(config, &os, NULL, NULL, "", 0);
 		return;
 	}
 
 	if (!metric_only)
-		abs_printout(id, nr, counter, uval);
+		abs_printout(config, id, nr, counter, uval);
 
 	out.print_metric = pm;
 	out.new_line = nl;
@@ -1083,7 +1093,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 		print_running(config, run, ena);
 	}
 
-	perf_stat__print_shadow_stats(counter, uval,
+	perf_stat__print_shadow_stats(config, counter, uval,
 				first_shadow_cpu(counter, id),
 				&out, &metric_events, st);
 	if (!csv_output && !metric_only) {
@@ -1255,7 +1265,7 @@ static void print_aggr(struct perf_stat_config *config,
 			val = ad.val;
 			if (first && metric_only) {
 				first = false;
-				aggr_printout(counter, id, nr);
+				aggr_printout(config, counter, id, nr);
 			}
 			if (prefix && !metric_only)
 				fprintf(output, "%s", prefix);
@@ -1459,7 +1469,7 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
 			if (is_duration_time(counter))
 				continue;
 			if (first) {
-				aggr_printout(counter, cpu, 0);
+				aggr_printout(config, counter, cpu, 0);
 				first = false;
 			}
 			val = perf_counts(counter->counts, cpu, 0)->val;
@@ -1521,7 +1531,7 @@ static void print_metric_headers(struct perf_stat_config *config,
 		out.new_line = new_line_metric;
 		out.force_header = true;
 		os.evsel = counter;
-		perf_stat__print_shadow_stats(counter, 0,
+		perf_stat__print_shadow_stats(config, counter, 0,
 					      0,
 					      &out,
 					      &metric_events,
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 99990f5f2512..8ad32763cfff 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -410,7 +410,8 @@ static double runtime_stat_n(struct runtime_stat *st,
 	return v->stats.n;
 }
 
-static void print_stalled_cycles_frontend(int cpu,
+static void print_stalled_cycles_frontend(struct perf_stat_config *config,
+					  int cpu,
 					  struct perf_evsel *evsel, double avg,
 					  struct perf_stat_output_ctx *out,
 					  struct runtime_stat *st)
@@ -427,13 +428,14 @@ static void print_stalled_cycles_frontend(int cpu,
 	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
 
 	if (ratio)
-		out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+		out->print_metric(config, out->ctx, color, "%7.2f%%", "frontend cycles idle",
 				  ratio);
 	else
-		out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
+		out->print_metric(config, out->ctx, NULL, NULL, "frontend cycles idle", 0);
 }
 
-static void print_stalled_cycles_backend(int cpu,
+static void print_stalled_cycles_backend(struct perf_stat_config *config,
+					 int cpu,
 					 struct perf_evsel *evsel, double avg,
 					 struct perf_stat_output_ctx *out,
 					 struct runtime_stat *st)
@@ -449,10 +451,11 @@ static void print_stalled_cycles_backend(int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-	out->print_metric(out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
 }
 
-static void print_branch_misses(int cpu,
+static void print_branch_misses(struct perf_stat_config *config,
+				int cpu,
 				struct perf_evsel *evsel,
 				double avg,
 				struct perf_stat_output_ctx *out,
@@ -469,10 +472,11 @@ static void print_branch_misses(int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all branches", ratio);
 }
 
-static void print_l1_dcache_misses(int cpu,
+static void print_l1_dcache_misses(struct perf_stat_config *config,
+				   int cpu,
 				   struct perf_evsel *evsel,
 				   double avg,
 				   struct perf_stat_output_ctx *out,
@@ -490,10 +494,11 @@ static void print_l1_dcache_misses(int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
 }
 
-static void print_l1_icache_misses(int cpu,
+static void print_l1_icache_misses(struct perf_stat_config *config,
+				   int cpu,
 				   struct perf_evsel *evsel,
 				   double avg,
 				   struct perf_stat_output_ctx *out,
@@ -510,10 +515,11 @@ static void print_l1_icache_misses(int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
 }
 
-static void print_dtlb_cache_misses(int cpu,
+static void print_dtlb_cache_misses(struct perf_stat_config *config,
+				    int cpu,
 				    struct perf_evsel *evsel,
 				    double avg,
 				    struct perf_stat_output_ctx *out,
@@ -529,10 +535,11 @@ static void print_dtlb_cache_misses(int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
 }
 
-static void print_itlb_cache_misses(int cpu,
+static void print_itlb_cache_misses(struct perf_stat_config *config,
+				    int cpu,
 				    struct perf_evsel *evsel,
 				    double avg,
 				    struct perf_stat_output_ctx *out,
@@ -548,10 +555,11 @@ static void print_itlb_cache_misses(int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
 }
 
-static void print_ll_cache_misses(int cpu,
+static void print_ll_cache_misses(struct perf_stat_config *config,
+				  int cpu,
 				  struct perf_evsel *evsel,
 				  double avg,
 				  struct perf_stat_output_ctx *out,
@@ -567,7 +575,7 @@ static void print_ll_cache_misses(int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
 }
 
 /*
@@ -674,7 +682,8 @@ static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
 	return sanitize_val(1.0 - sum);
 }
 
-static void print_smi_cost(int cpu, struct perf_evsel *evsel,
+static void print_smi_cost(struct perf_stat_config *config,
+			   int cpu, struct perf_evsel *evsel,
 			   struct perf_stat_output_ctx *out,
 			   struct runtime_stat *st)
 {
@@ -694,11 +703,12 @@ static void print_smi_cost(int cpu, struct perf_evsel *evsel,
 
 	if (cost > 10)
 		color = PERF_COLOR_RED;
-	out->print_metric(out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
-	out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num);
+	out->print_metric(config, out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
+	out->print_metric(config, out->ctx, NULL, "%4.0f", "SMI#", smi_num);
 }
 
-static void generic_metric(const char *metric_expr,
+static void generic_metric(struct perf_stat_config *config,
+			   const char *metric_expr,
 			   struct perf_evsel **metric_events,
 			   char *name,
 			   const char *metric_name,
@@ -737,20 +747,21 @@ static void generic_metric(const char *metric_expr,
 		const char *p = metric_expr;
 
 		if (expr__parse(&ratio, &pctx, &p) == 0)
-			print_metric(ctxp, NULL, "%8.1f",
+			print_metric(config, ctxp, NULL, "%8.1f",
 				metric_name ?
 				metric_name :
 				out->force_header ?  name : "",
 				ratio);
 		else
-			print_metric(ctxp, NULL, NULL,
+			print_metric(config, ctxp, NULL, NULL,
 				     out->force_header ?
 				     (metric_name ? metric_name : name) : "", 0);
 	} else
-		print_metric(ctxp, NULL, NULL, "", 0);
+		print_metric(config, ctxp, NULL, NULL, "", 0);
 }
 
-void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+void perf_stat__print_shadow_stats(struct perf_stat_config *config,
+				   struct perf_evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out,
 				   struct rblist *metric_events,
@@ -769,10 +780,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 
 		if (total) {
 			ratio = avg / total;
-			print_metric(ctxp, NULL, "%7.2f ",
+			print_metric(config, ctxp, NULL, "%7.2f ",
 					"insn per cycle", ratio);
 		} else {
-			print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
+			print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
 		}
 
 		total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT,
@@ -783,20 +794,20 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 						    ctx, cpu));
 
 		if (total && avg) {
-			out->new_line(ctxp);
+			out->new_line(config, ctxp);
 			ratio = total / avg;
-			print_metric(ctxp, NULL, "%7.2f ",
+			print_metric(config, ctxp, NULL, "%7.2f ",
 					"stalled cycles per insn",
 					ratio);
 		} else if (have_frontend_stalled) {
-			print_metric(ctxp, NULL, NULL,
+			print_metric(config, ctxp, NULL, NULL,
 				     "stalled cycles per insn", 0);
 		}
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
 		if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
-			print_branch_misses(cpu, evsel, avg, out, st);
+			print_branch_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all branches", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all branches", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
@@ -804,9 +815,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
-			print_l1_dcache_misses(cpu, evsel, avg, out, st);
+			print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all L1-dcache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
@@ -814,9 +825,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
-			print_l1_icache_misses(cpu, evsel, avg, out, st);
+			print_l1_icache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all L1-icache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
@@ -824,9 +835,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
-			print_dtlb_cache_misses(cpu, evsel, avg, out, st);
+			print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all dTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
@@ -834,9 +845,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
-			print_itlb_cache_misses(cpu, evsel, avg, out, st);
+			print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all iTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
@@ -844,9 +855,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
-			print_ll_cache_misses(cpu, evsel, avg, out, st);
+			print_ll_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all LL-cache hits", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
 		total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
 
@@ -854,32 +865,32 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			ratio = avg * 100 / total;
 
 		if (runtime_stat_n(st, STAT_CACHEREFS, ctx, cpu) != 0)
-			print_metric(ctxp, NULL, "%8.3f %%",
+			print_metric(config, ctxp, NULL, "%8.3f %%",
 				     "of all cache refs", ratio);
 		else
-			print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(cpu, evsel, avg, out, st);
+		print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(cpu, evsel, avg, out, st);
+		print_stalled_cycles_backend(config, cpu, evsel, avg, out, st);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
 		total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
 
 		if (total) {
 			ratio = avg / total;
-			print_metric(ctxp, NULL, "%8.3f", "GHz", ratio);
+			print_metric(config, ctxp, NULL, "%8.3f", "GHz", ratio);
 		} else {
-			print_metric(ctxp, NULL, NULL, "Ghz", 0);
+			print_metric(config, ctxp, NULL, NULL, "Ghz", 0);
 		}
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
 		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
 
 		if (total)
-			print_metric(ctxp, NULL,
+			print_metric(config, ctxp, NULL,
 					"%7.2f%%", "transactional cycles",
 					100.0 * (avg / total));
 		else
-			print_metric(ctxp, NULL, NULL, "transactional cycles",
+			print_metric(config, ctxp, NULL, NULL, "transactional cycles",
 				     0);
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
 		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
@@ -888,10 +899,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		if (total2 < avg)
 			total2 = avg;
 		if (total)
-			print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles",
+			print_metric(config, ctxp, NULL, "%7.2f%%", "aborted cycles",
 				100.0 * ((total2-avg) / total));
 		else
-			print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
+			print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0);
 	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
 		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
 					 ctx, cpu);
@@ -900,10 +911,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			ratio = total / avg;
 
 		if (runtime_stat_n(st, STAT_CYCLES_IN_TX, ctx, cpu) != 0)
-			print_metric(ctxp, NULL, "%8.0f",
+			print_metric(config, ctxp, NULL, "%8.0f",
 				     "cycles / transaction", ratio);
 		else
-			print_metric(ctxp, NULL, NULL, "cycles / transaction",
+			print_metric(config, ctxp, NULL, NULL, "cycles / transaction",
 				      0);
 	} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
 		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
@@ -912,33 +923,33 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		if (avg)
 			ratio = total / avg;
 
-		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
+		print_metric(config, ctxp, NULL, "%8.0f", "cycles / elision", ratio);
 	} else if (perf_evsel__is_clock(evsel)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
-			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+			print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized",
 				     avg / (ratio * evsel->scale));
 		else
-			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
+			print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
 		double fe_bound = td_fe_bound(ctx, cpu, st);
 
 		if (fe_bound > 0.2)
 			color = PERF_COLOR_RED;
-		print_metric(ctxp, color, "%8.1f%%", "frontend bound",
+		print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
 				fe_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
 		double retiring = td_retiring(ctx, cpu, st);
 
 		if (retiring > 0.7)
 			color = PERF_COLOR_GREEN;
-		print_metric(ctxp, color, "%8.1f%%", "retiring",
+		print_metric(config, ctxp, color, "%8.1f%%", "retiring",
 				retiring * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
 		double bad_spec = td_bad_spec(ctx, cpu, st);
 
 		if (bad_spec > 0.1)
 			color = PERF_COLOR_RED;
-		print_metric(ctxp, color, "%8.1f%%", "bad speculation",
+		print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
 				bad_spec * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
 		double be_bound = td_be_bound(ctx, cpu, st);
@@ -955,12 +966,12 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		if (be_bound > 0.2)
 			color = PERF_COLOR_RED;
 		if (td_total_slots(ctx, cpu, st) > 0)
-			print_metric(ctxp, color, "%8.1f%%", name,
+			print_metric(config, ctxp, color, "%8.1f%%", name,
 					be_bound * 100.);
 		else
-			print_metric(ctxp, NULL, NULL, name, 0);
+			print_metric(config, ctxp, NULL, NULL, name, 0);
 	} else if (evsel->metric_expr) {
-		generic_metric(evsel->metric_expr, evsel->metric_events, evsel->name,
+		generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name,
 				evsel->metric_name, avg, cpu, out, st);
 	} else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
 		char unit = 'M';
@@ -975,9 +986,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			unit = 'K';
 		}
 		snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
-		print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
+		print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
 	} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
-		print_smi_cost(cpu, evsel, out, st);
+		print_smi_cost(config, cpu, evsel, out, st);
 	} else {
 		num = 0;
 	}
@@ -987,12 +998,12 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 
 		list_for_each_entry (mexp, &me->head, nd) {
 			if (num++ > 0)
-				out->new_line(ctxp);
-			generic_metric(mexp->metric_expr, mexp->metric_events,
+				out->new_line(config, ctxp);
+			generic_metric(config, mexp->metric_expr, mexp->metric_events,
 					evsel->name, mexp->metric_name,
 					avg, cpu, out, st);
 		}
 	}
 	if (num == 0)
-		print_metric(ctxp, NULL, NULL, NULL, 0);
+		print_metric(config, ctxp, NULL, NULL, NULL, 0);
 }
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index da6a706daecc..dffcf2110706 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -135,9 +135,10 @@ bool __perf_evsel_stat__is(struct perf_evsel *evsel,
 extern struct runtime_stat rt_stat;
 extern struct stats walltime_nsecs_stats;
 
-typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
+typedef void (*print_metric_t)(struct perf_stat_config *config,
+			       void *ctx, const char *color, const char *unit,
 			       const char *fmt, double val);
-typedef void (*new_line_t )(void *ctx);
+typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx);
 
 void runtime_stat__init(struct runtime_stat *st);
 void runtime_stat__exit(struct runtime_stat *st);
@@ -153,7 +154,8 @@ struct perf_stat_output_ctx {
 	bool force_header;
 };
 
-void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+void perf_stat__print_shadow_stats(struct perf_stat_config *config,
+				   struct perf_evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out,
 				   struct rblist *metric_events,
-- 
cgit v1.2.3


From fa7070a38676d660c0a71ab6981bfdca3b340ccd Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:29 +0200
Subject: perf stat: Move csv_* to 'struct perf_stat_config'

Move the static csv_* variables to 'struct perf_stat_config', so that it
can be passed around and used outside the 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-21-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 114 +++++++++++++++++++++++-----------------------
 tools/perf/util/stat.h    |   2 +
 2 files changed, 58 insertions(+), 58 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7a3361308e61..4c29e5065e02 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -157,8 +157,6 @@ static bool			smi_cost			= false;
 static bool			smi_reset			= false;
 static bool			big_num				=  true;
 static int			big_num_opt			=  -1;
-static const char		*csv_sep			= NULL;
-static bool			csv_output			= false;
 static bool			group				= false;
 static const char		*pre_cmd			= NULL;
 static const char		*post_cmd			= NULL;
@@ -663,11 +661,11 @@ static int run_perf_stat(int argc, const char **argv, int run_idx)
 static void print_running(struct perf_stat_config *config,
 			  u64 run, u64 ena)
 {
-	if (csv_output) {
+	if (config->csv_output) {
 		fprintf(config->output, "%s%" PRIu64 "%s%.2f",
-					csv_sep,
+					config->csv_sep,
 					run,
-					csv_sep,
+					config->csv_sep,
 					ena ? 100.0 * run / ena : 100.0);
 	} else if (run != ena) {
 		fprintf(config->output, "  (%.2f%%)", 100.0 * run / ena);
@@ -679,8 +677,8 @@ static void print_noise_pct(struct perf_stat_config *config,
 {
 	double pct = rel_stddev_stats(total, avg);
 
-	if (csv_output)
-		fprintf(config->output, "%s%.2f%%", csv_sep, pct);
+	if (config->csv_output)
+		fprintf(config->output, "%s%.2f%%", config->csv_sep, pct);
 	else if (pct)
 		fprintf(config->output, "  ( +-%6.2f%% )", pct);
 }
@@ -704,34 +702,34 @@ static void aggr_printout(struct perf_stat_config *config,
 	case AGGR_CORE:
 		fprintf(config->output, "S%d-C%*d%s%*d%s",
 			cpu_map__id_to_socket(id),
-			csv_output ? 0 : -8,
+			config->csv_output ? 0 : -8,
 			cpu_map__id_to_cpu(id),
-			csv_sep,
-			csv_output ? 0 : 4,
+			config->csv_sep,
+			config->csv_output ? 0 : 4,
 			nr,
-			csv_sep);
+			config->csv_sep);
 		break;
 	case AGGR_SOCKET:
 		fprintf(config->output, "S%*d%s%*d%s",
-			csv_output ? 0 : -5,
+			config->csv_output ? 0 : -5,
 			id,
-			csv_sep,
-			csv_output ? 0 : 4,
+			config->csv_sep,
+			config->csv_output ? 0 : 4,
 			nr,
-			csv_sep);
+			config->csv_sep);
 			break;
 	case AGGR_NONE:
 		fprintf(config->output, "CPU%*d%s",
-			csv_output ? 0 : -4,
-			perf_evsel__cpus(evsel)->map[id], csv_sep);
+			config->csv_output ? 0 : -4,
+			perf_evsel__cpus(evsel)->map[id], config->csv_sep);
 		break;
 	case AGGR_THREAD:
 		fprintf(config->output, "%*s-%*d%s",
-			csv_output ? 0 : 16,
+			config->csv_output ? 0 : 16,
 			thread_map__comm(evsel->threads, id),
-			csv_output ? 0 : -8,
+			config->csv_output ? 0 : -8,
 			thread_map__pid(evsel->threads, id),
-			csv_sep);
+			config->csv_sep);
 		break;
 	case AGGR_GLOBAL:
 	case AGGR_UNSET:
@@ -804,10 +802,10 @@ static void new_line_csv(struct perf_stat_config *config, void *ctx)
 
 	fputc('\n', os->fh);
 	if (os->prefix)
-		fprintf(os->fh, "%s%s", os->prefix, csv_sep);
+		fprintf(os->fh, "%s%s", os->prefix, config->csv_sep);
 	aggr_printout(config, os->evsel, os->id, os->nr);
 	for (i = 0; i < os->nfields; i++)
-		fputs(csv_sep, os->fh);
+		fputs(config->csv_sep, os->fh);
 }
 
 static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
@@ -820,7 +818,7 @@ static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
 	char buf[64], *vals, *ends;
 
 	if (unit == NULL || fmt == NULL) {
-		fprintf(out, "%s%s", csv_sep, csv_sep);
+		fprintf(out, "%s%s", config->csv_sep, config->csv_sep);
 		return;
 	}
 	snprintf(buf, sizeof(buf), fmt, val);
@@ -830,7 +828,7 @@ static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
 	*ends = 0;
 	while (isspace(*unit))
 		unit++;
-	fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
+	fprintf(out, "%s%s%s%s", config->csv_sep, vals, config->csv_sep, unit);
 }
 
 /* Filter out some columns that don't work well in metrics only mode */
@@ -898,7 +896,7 @@ static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused
 	while (isdigit(*ends) || *ends == '.')
 		ends++;
 	*ends = 0;
-	fprintf(out, "%s%s", vals, csv_sep);
+	fprintf(out, "%s%s", vals, config->csv_sep);
 }
 
 static void new_line_metric(struct perf_stat_config *config __maybe_unused,
@@ -917,8 +915,8 @@ static void print_metric_header(struct perf_stat_config *config __maybe_unused,
 	if (!valid_only_metric(unit))
 		return;
 	unit = fixunit(tbuf, os->evsel, unit);
-	if (csv_output)
-		fprintf(os->fh, "%s%s", unit, csv_sep);
+	if (config->csv_output)
+		fprintf(os->fh, "%s%s", unit, config->csv_sep);
 	else
 		fprintf(os->fh, "%*s ", metric_only_len, unit);
 }
@@ -952,7 +950,7 @@ static void abs_printout(struct perf_stat_config *config,
 	double sc =  evsel->scale;
 	const char *fmt;
 
-	if (csv_output) {
+	if (config->csv_output) {
 		fmt = floor(sc) != sc ?  "%.2f%s" : "%.0f%s";
 	} else {
 		if (big_num)
@@ -963,17 +961,17 @@ static void abs_printout(struct perf_stat_config *config,
 
 	aggr_printout(config, evsel, id, nr);
 
-	fprintf(output, fmt, avg, csv_sep);
+	fprintf(output, fmt, avg, config->csv_sep);
 
 	if (evsel->unit)
 		fprintf(output, "%-*s%s",
-			csv_output ? 0 : unit_width,
-			evsel->unit, csv_sep);
+			config->csv_output ? 0 : unit_width,
+			evsel->unit, config->csv_sep);
 
-	fprintf(output, "%-*s", csv_output ? 0 : 25, perf_evsel__name(evsel));
+	fprintf(output, "%-*s", config->csv_output ? 0 : 25, perf_evsel__name(evsel));
 
 	if (evsel->cgrp)
-		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
+		fprintf(output, "%s%s", config->csv_sep, evsel->cgrp->name);
 }
 
 static bool is_mixed_hw_group(struct perf_evsel *counter)
@@ -1018,14 +1016,14 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 
 	if (metric_only) {
 		nl = new_line_metric;
-		if (csv_output)
+		if (config->csv_output)
 			pm = print_metric_only_csv;
 		else
 			pm = print_metric_only;
 	} else
 		nl = new_line_std;
 
-	if (csv_output && !metric_only) {
+	if (config->csv_output && !metric_only) {
 		static int aggr_fields[] = {
 			[AGGR_GLOBAL] = 0,
 			[AGGR_THREAD] = 1,
@@ -1049,9 +1047,9 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 		aggr_printout(config, counter, id, nr);
 
 		fprintf(config->output, "%*s%s",
-			csv_output ? 0 : 18,
+			config->csv_output ? 0 : 18,
 			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-			csv_sep);
+			config->csv_sep);
 
 		if (counter->supported) {
 			print_free_counters_hint = 1;
@@ -1060,22 +1058,22 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 		}
 
 		fprintf(config->output, "%-*s%s",
-			csv_output ? 0 : unit_width,
-			counter->unit, csv_sep);
+			config->csv_output ? 0 : unit_width,
+			counter->unit, config->csv_sep);
 
 		fprintf(config->output, "%*s",
-			csv_output ? 0 : -25,
+			config->csv_output ? 0 : -25,
 			perf_evsel__name(counter));
 
 		if (counter->cgrp)
 			fprintf(config->output, "%s%s",
-				csv_sep, counter->cgrp->name);
+				config->csv_sep, counter->cgrp->name);
 
-		if (!csv_output)
+		if (!config->csv_output)
 			pm(config, &os, NULL, NULL, "", 0);
 		print_noise(config, counter, noise);
 		print_running(config, run, ena);
-		if (csv_output)
+		if (config->csv_output)
 			pm(config, &os, NULL, NULL, "", 0);
 		return;
 	}
@@ -1088,7 +1086,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 	out.ctx = &os;
 	out.force_header = false;
 
-	if (csv_output && !metric_only) {
+	if (config->csv_output && !metric_only) {
 		print_noise(config, counter, noise);
 		print_running(config, run, ena);
 	}
@@ -1096,7 +1094,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 	perf_stat__print_shadow_stats(config, counter, uval,
 				first_shadow_cpu(counter, id),
 				&out, &metric_events, st);
-	if (!csv_output && !metric_only) {
+	if (!config->csv_output && !metric_only) {
 		print_noise(config, counter, noise);
 		print_running(config, run, ena);
 	}
@@ -1512,10 +1510,10 @@ static void print_metric_headers(struct perf_stat_config *config,
 	if (prefix)
 		fprintf(config->output, "%s", prefix);
 
-	if (!csv_output && !no_indent)
+	if (!config->csv_output && !no_indent)
 		fprintf(config->output, "%*s",
 			aggr_header_lens[config->aggr_mode], "");
-	if (csv_output) {
+	if (config->csv_output) {
 		if (config->interval)
 			fputs("time,", config->output);
 		fputs(aggr_header_csv[config->aggr_mode], config->output);
@@ -1549,9 +1547,9 @@ static void print_interval(struct perf_stat_config *config,
 	if (interval_clear)
 		puts(CONSOLE_CLEAR);
 
-	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
+	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep);
 
-	if ((num_print_interval == 0 && !csv_output) || interval_clear) {
+	if ((num_print_interval == 0 && !config->csv_output) || interval_clear) {
 		switch (config->aggr_mode) {
 		case AGGR_SOCKET:
 			fprintf(output, "#           time socket cpus");
@@ -1597,7 +1595,7 @@ static void print_header(struct perf_stat_config *config,
 
 	fflush(stdout);
 
-	if (!csv_output) {
+	if (!config->csv_output) {
 		fprintf(output, "\n");
 		fprintf(output, " Performance counter stats for ");
 		if (target.system_wide)
@@ -1776,7 +1774,7 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 		break;
 	}
 
-	if (!interval && !csv_output)
+	if (!interval && !config->csv_output)
 		print_footer(config);
 
 	fflush(config->output);
@@ -1896,7 +1894,7 @@ static const struct option stat_options[] = {
 	OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
 		    "disable CPU count aggregation", AGGR_NONE),
 	OPT_BOOLEAN(0, "no-merge", &no_merge, "Do not merge identical named events"),
-	OPT_STRING('x', "field-separator", &csv_sep, "separator",
+	OPT_STRING('x', "field-separator", &stat_config.csv_sep, "separator",
 		   "print counts with custom separator"),
 	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
 		     "monitor event in cgroup name only", parse_cgroups),
@@ -2749,12 +2747,12 @@ int cmd_stat(int argc, const char **argv)
 	perf_stat__collect_metric_expr(evsel_list);
 	perf_stat__init_shadow_stats();
 
-	if (csv_sep) {
-		csv_output = true;
-		if (!strcmp(csv_sep, "\\t"))
-			csv_sep = "\t";
+	if (stat_config.csv_sep) {
+		stat_config.csv_output = true;
+		if (!strcmp(stat_config.csv_sep, "\\t"))
+			stat_config.csv_sep = "\t";
 	} else
-		csv_sep = DEFAULT_SEPARATOR;
+		stat_config.csv_sep = DEFAULT_SEPARATOR;
 
 	if (argc && !strncmp(argv[0], "rec", 3)) {
 		argc = __cmd_record(argc, argv);
@@ -2827,7 +2825,7 @@ int cmd_stat(int argc, const char **argv)
 	/*
 	 * let the spreadsheet do the pretty-printing
 	 */
-	if (csv_output) {
+	if (stat_config.csv_output) {
 		/* User explicitly passed -B? */
 		if (big_num_opt == 1) {
 			fprintf(stderr, "-B option not supported with -x\n");
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index dffcf2110706..18546d8b0279 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -91,6 +91,7 @@ struct perf_stat_config {
 	bool			 scale;
 	bool			 no_inherit;
 	bool			 identifier;
+	bool			 csv_output;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
@@ -98,6 +99,7 @@ struct perf_stat_config {
 	int			 times;
 	struct runtime_stat	*stats;
 	int			 stats_num;
+	const char		*csv_sep;
 };
 
 void update_stats(struct stats *stats, u64 val);
-- 
cgit v1.2.3


From 132c6ba3c440fd21a45ff7f9d7a1f53813f4d0e3 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:30 +0200
Subject: perf stat: Move 'interval_clear' to 'struct perf_stat_config'

Move the static 'interval_clear' variable to 'struct perf_stat_config',
so it can be passed around and used outside the 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-22-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 9 ++++-----
 tools/perf/util/stat.h    | 1 +
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 4c29e5065e02..89297ab77d21 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -172,7 +172,6 @@ static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
 static bool			append_file;
 static bool			interval_count;
-static bool			interval_clear;
 static const char		*output_name;
 static int			output_fd;
 static int			print_free_counters_hint;
@@ -1544,12 +1543,12 @@ static void print_interval(struct perf_stat_config *config,
 	FILE *output = config->output;
 	static int num_print_interval;
 
-	if (interval_clear)
+	if (config->interval_clear)
 		puts(CONSOLE_CLEAR);
 
 	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep);
 
-	if ((num_print_interval == 0 && !config->csv_output) || interval_clear) {
+	if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) {
 		switch (config->aggr_mode) {
 		case AGGR_SOCKET:
 			fprintf(output, "#           time socket cpus");
@@ -1581,7 +1580,7 @@ static void print_interval(struct perf_stat_config *config,
 		}
 	}
 
-	if ((num_print_interval == 0 || interval_clear) && metric_only)
+	if ((num_print_interval == 0 || config->interval_clear) && metric_only)
 		print_metric_headers(config, " ", true);
 	if (++num_print_interval == 25)
 		num_print_interval = 0;
@@ -1911,7 +1910,7 @@ static const struct option stat_options[] = {
 		    "(overhead is possible for values <= 100ms)"),
 	OPT_INTEGER(0, "interval-count", &stat_config.times,
 		    "print counts for fixed number of times"),
-	OPT_BOOLEAN(0, "interval-clear", &interval_clear,
+	OPT_BOOLEAN(0, "interval-clear", &stat_config.interval_clear,
 		    "clear screen in between new interval"),
 	OPT_UINTEGER(0, "timeout", &stat_config.timeout,
 		    "stop workload and print counts after a timeout period in ms (>= 10ms)"),
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 18546d8b0279..470ab37601be 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -92,6 +92,7 @@ struct perf_stat_config {
 	bool			 no_inherit;
 	bool			 identifier;
 	bool			 csv_output;
+	bool			 interval_clear;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
-- 
cgit v1.2.3


From 0ce5aa0266604c77ee64882b70c980e843629177 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:31 +0200
Subject: perf stat: Move 'metric_only' to 'struct perf_stat_config'

Move the static 'metric_only' variable to 'struct perf_stat_config', so
it can be passed around and used outside the 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-23-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 29 ++++++++++++++++-------------
 tools/perf/util/stat.h    |  1 +
 2 files changed, 17 insertions(+), 13 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 89297ab77d21..397cb4f28d7f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -163,7 +163,6 @@ static const char		*post_cmd			= NULL;
 static bool			sync_run			= false;
 static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
-static bool			metric_only			= false;
 static bool			force_metric_only		= false;
 static bool			no_merge			= false;
 static bool			walltime_run_table		= false;
@@ -1013,7 +1012,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 	print_metric_t pm = print_metric_std;
 	new_line_t nl;
 
-	if (metric_only) {
+	if (config->metric_only) {
 		nl = new_line_metric;
 		if (config->csv_output)
 			pm = print_metric_only_csv;
@@ -1022,7 +1021,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 	} else
 		nl = new_line_std;
 
-	if (config->csv_output && !metric_only) {
+	if (config->csv_output && !config->metric_only) {
 		static int aggr_fields[] = {
 			[AGGR_GLOBAL] = 0,
 			[AGGR_THREAD] = 1,
@@ -1039,7 +1038,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 			os.nfields++;
 	}
 	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
-		if (metric_only) {
+		if (config->metric_only) {
 			pm(config, &os, NULL, "", "", 0);
 			return;
 		}
@@ -1077,7 +1076,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 		return;
 	}
 
-	if (!metric_only)
+	if (!config->metric_only)
 		abs_printout(config, id, nr, counter, uval);
 
 	out.print_metric = pm;
@@ -1085,7 +1084,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 	out.ctx = &os;
 	out.force_header = false;
 
-	if (config->csv_output && !metric_only) {
+	if (config->csv_output && !config->metric_only) {
 		print_noise(config, counter, noise);
 		print_running(config, run, ena);
 	}
@@ -1093,7 +1092,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 	perf_stat__print_shadow_stats(config, counter, uval,
 				first_shadow_cpu(counter, id),
 				&out, &metric_events, st);
-	if (!config->csv_output && !metric_only) {
+	if (!config->csv_output && !config->metric_only) {
 		print_noise(config, counter, noise);
 		print_running(config, run, ena);
 	}
@@ -1225,6 +1224,7 @@ static void aggr_cb(struct perf_evsel *counter, void *data, bool first)
 static void print_aggr(struct perf_stat_config *config,
 		       char *prefix)
 {
+	bool metric_only = config->metric_only;
 	FILE *output = config->output;
 	struct perf_evsel *counter;
 	int s, id, nr;
@@ -1388,6 +1388,7 @@ static void counter_aggr_cb(struct perf_evsel *counter, void *data,
 static void print_counter_aggr(struct perf_stat_config *config,
 			       struct perf_evsel *counter, char *prefix)
 {
+	bool metric_only = config->metric_only;
 	FILE *output = config->output;
 	double uval;
 	struct caggr_data cd = { .avg = 0.0 };
@@ -1540,6 +1541,7 @@ static void print_metric_headers(struct perf_stat_config *config,
 static void print_interval(struct perf_stat_config *config,
 			   char *prefix, struct timespec *ts)
 {
+	bool metric_only = config->metric_only;
 	FILE *output = config->output;
 	static int num_print_interval;
 
@@ -1716,6 +1718,7 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 			    struct timespec *ts,
 			    int argc, const char **argv)
 {
+	bool metric_only = config->metric_only;
 	int interval = config->interval;
 	struct perf_evsel *counter;
 	char buf[64], *prefix = NULL;
@@ -1843,7 +1846,7 @@ static int enable_metric_only(const struct option *opt __maybe_unused,
 			      const char *s __maybe_unused, int unset)
 {
 	force_metric_only = true;
-	metric_only = !unset;
+	stat_config.metric_only = !unset;
 	return 0;
 }
 
@@ -1922,7 +1925,7 @@ static const struct option stat_options[] = {
 		     "aggregate counts per thread", AGGR_THREAD),
 	OPT_UINTEGER('D', "delay", &stat_config.initial_delay,
 		     "ms to wait before starting measurement after program start"),
-	OPT_CALLBACK_NOOPT(0, "metric-only", &metric_only, NULL,
+	OPT_CALLBACK_NOOPT(0, "metric-only", &stat_config.metric_only, NULL,
 			"Only print computed metrics. No raw values", enable_metric_only),
 	OPT_BOOLEAN(0, "topdown", &topdown_run,
 			"measure topdown level 1 statistics"),
@@ -2345,7 +2348,7 @@ static int add_default_attributes(void)
 		if (pmu_have_event("msr", "aperf") &&
 		    pmu_have_event("msr", "smi")) {
 			if (!force_metric_only)
-				metric_only = true;
+				stat_config.metric_only = true;
 			err = parse_events(evsel_list, smi_cost_attrs, &errinfo);
 		} else {
 			fprintf(stderr, "To measure SMI cost, it needs "
@@ -2376,7 +2379,7 @@ static int add_default_attributes(void)
 		}
 
 		if (!force_metric_only)
-			metric_only = true;
+			stat_config.metric_only = true;
 		if (topdown_filter_events(topdown_attrs, &str,
 				arch_topdown_check_group(&warn)) < 0) {
 			pr_err("Out of memory\n");
@@ -2776,12 +2779,12 @@ int cmd_stat(int argc, const char **argv)
 		goto out;
 	}
 
-	if (metric_only && stat_config.aggr_mode == AGGR_THREAD) {
+	if (stat_config.metric_only && stat_config.aggr_mode == AGGR_THREAD) {
 		fprintf(stderr, "--metric-only is not supported with --per-thread\n");
 		goto out;
 	}
 
-	if (metric_only && run_count > 1) {
+	if (stat_config.metric_only && run_count > 1) {
 		fprintf(stderr, "--metric-only is not supported with -r\n");
 		goto out;
 	}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 470ab37601be..da838182b99c 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -93,6 +93,7 @@ struct perf_stat_config {
 	bool			 identifier;
 	bool			 csv_output;
 	bool			 interval_clear;
+	bool			 metric_only;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
-- 
cgit v1.2.3


From df4f7b4d4b1e61e6b16ac2e3760be46bac86e4f4 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:32 +0200
Subject: perf stat: Move 'unit_width' to 'struct perf_stat_config'

Move the static 'unit_width' variable to 'struct perf_stat_config',
so it can be passed around and used outside the 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-24-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 11 ++++++-----
 tools/perf/util/stat.h    |  1 +
 2 files changed, 7 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 397cb4f28d7f..24171aa6c41f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -161,7 +161,6 @@ static bool			group				= false;
 static const char		*pre_cmd			= NULL;
 static const char		*post_cmd			= NULL;
 static bool			sync_run			= false;
-static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
 static bool			force_metric_only		= false;
 static bool			no_merge			= false;
@@ -200,6 +199,7 @@ static volatile int done = 0;
 static struct perf_stat_config stat_config = {
 	.aggr_mode	= AGGR_GLOBAL,
 	.scale		= true,
+	.unit_width	= 4, /* strlen("unit") */
 };
 
 static bool is_duration_time(struct perf_evsel *evsel)
@@ -524,8 +524,8 @@ try_again:
 		counter->supported = true;
 
 		l = strlen(counter->unit);
-		if (l > unit_width)
-			unit_width = l;
+		if (l > stat_config.unit_width)
+			stat_config.unit_width = l;
 
 		if (perf_evsel__should_store_id(counter) &&
 		    perf_evsel__store_ids(counter, evsel_list))
@@ -963,7 +963,7 @@ static void abs_printout(struct perf_stat_config *config,
 
 	if (evsel->unit)
 		fprintf(output, "%-*s%s",
-			config->csv_output ? 0 : unit_width,
+			config->csv_output ? 0 : config->unit_width,
 			evsel->unit, config->csv_sep);
 
 	fprintf(output, "%-*s", config->csv_output ? 0 : 25, perf_evsel__name(evsel));
@@ -1056,7 +1056,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 		}
 
 		fprintf(config->output, "%-*s%s",
-			config->csv_output ? 0 : unit_width,
+			config->csv_output ? 0 : config->unit_width,
 			counter->unit, config->csv_sep);
 
 		fprintf(config->output, "%*s",
@@ -1542,6 +1542,7 @@ static void print_interval(struct perf_stat_config *config,
 			   char *prefix, struct timespec *ts)
 {
 	bool metric_only = config->metric_only;
+	unsigned int unit_width = config->unit_width;
 	FILE *output = config->output;
 	static int num_print_interval;
 
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index da838182b99c..2dc66e0ba4b8 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -98,6 +98,7 @@ struct perf_stat_config {
 	unsigned int		 interval;
 	unsigned int		 timeout;
 	unsigned int		 initial_delay;
+	unsigned int		 unit_width;
 	int			 times;
 	struct runtime_stat	*stats;
 	int			 stats_num;
-- 
cgit v1.2.3


From c512e0eae4c63be8c5964c3942b2e9c04dcd459e Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:33 +0200
Subject: perf stat: Add 'target' argument to perf_evlist__print_counters()

Add 'struct target' argument to perf_evlist__print_counters(), so the
function does not depend on the 'perf stat' command object local target
and can be moved out.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-25-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 24171aa6c41f..528f85146b59 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1590,6 +1590,7 @@ static void print_interval(struct perf_stat_config *config,
 }
 
 static void print_header(struct perf_stat_config *config,
+			 struct target *_target,
 			 int argc, const char **argv)
 {
 	FILE *output = config->output;
@@ -1600,18 +1601,18 @@ static void print_header(struct perf_stat_config *config,
 	if (!config->csv_output) {
 		fprintf(output, "\n");
 		fprintf(output, " Performance counter stats for ");
-		if (target.system_wide)
+		if (_target->system_wide)
 			fprintf(output, "\'system wide");
-		else if (target.cpu_list)
-			fprintf(output, "\'CPU(s) %s", target.cpu_list);
-		else if (!target__has_task(&target)) {
+		else if (_target->cpu_list)
+			fprintf(output, "\'CPU(s) %s", _target->cpu_list);
+		else if (!target__has_task(_target)) {
 			fprintf(output, "\'%s", argv ? argv[0] : "pipe");
 			for (i = 1; argv && (i < argc); i++)
 				fprintf(output, " %s", argv[i]);
-		} else if (target.pid)
-			fprintf(output, "process id \'%s", target.pid);
+		} else if (_target->pid)
+			fprintf(output, "process id \'%s", _target->pid);
 		else
-			fprintf(output, "thread id \'%s", target.tid);
+			fprintf(output, "thread id \'%s", _target->tid);
 
 		fprintf(output, "\'");
 		if (run_count > 1)
@@ -1716,6 +1717,7 @@ static void print_footer(struct perf_stat_config *config)
 static void
 perf_evlist__print_counters(struct perf_evlist *evlist,
 			    struct perf_stat_config *config,
+			    struct target *_target,
 			    struct timespec *ts,
 			    int argc, const char **argv)
 {
@@ -1727,7 +1729,7 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 	if (interval)
 		print_interval(config, prefix = buf, ts);
 	else
-		print_header(config, argc, argv);
+		print_header(config, _target, argc, argv);
 
 	if (metric_only) {
 		static int num_print_iv;
@@ -1789,7 +1791,7 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	if (STAT_RECORD && perf_stat.data.is_pipe)
 		return;
 
-	perf_evlist__print_counters(evsel_list, &stat_config,
+	perf_evlist__print_counters(evsel_list, &stat_config, &target,
 				    ts, argc, argv);
 }
 
-- 
cgit v1.2.3


From bc0bcda201e87d62f0922fa664376355b0fc77ff Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:34 +0200
Subject: perf stat: Pass 'evlist' argument to print functions

Add 'evlist' argument to print functions to get rid of the global
'evsel_list' variable dependency.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-26-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 528f85146b59..46181ac492c5 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1222,6 +1222,7 @@ static void aggr_cb(struct perf_evsel *counter, void *data, bool first)
 }
 
 static void print_aggr(struct perf_stat_config *config,
+		       struct perf_evlist *evlist,
 		       char *prefix)
 {
 	bool metric_only = config->metric_only;
@@ -1248,7 +1249,7 @@ static void print_aggr(struct perf_stat_config *config,
 
 		ad.id = id = aggr_map->map[s];
 		first = true;
-		evlist__for_each_entry(evsel_list, counter) {
+		evlist__for_each_entry(evlist, counter) {
 			if (is_duration_time(counter))
 				continue;
 
@@ -1449,6 +1450,7 @@ static void print_counter(struct perf_stat_config *config,
 }
 
 static void print_no_aggr_metric(struct perf_stat_config *config,
+				 struct perf_evlist *evlist,
 				 char *prefix)
 {
 	int cpu;
@@ -1457,13 +1459,13 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
 	u64 ena, run, val;
 	double uval;
 
-	nrcpus = evsel_list->cpus->nr;
+	nrcpus = evlist->cpus->nr;
 	for (cpu = 0; cpu < nrcpus; cpu++) {
 		bool first = true;
 
 		if (prefix)
 			fputs(prefix, config->output);
-		evlist__for_each_entry(evsel_list, counter) {
+		evlist__for_each_entry(evlist, counter) {
 			if (is_duration_time(counter))
 				continue;
 			if (first) {
@@ -1499,6 +1501,7 @@ static const char *aggr_header_csv[] = {
 };
 
 static void print_metric_headers(struct perf_stat_config *config,
+				 struct perf_evlist *evlist,
 				 const char *prefix, bool no_indent)
 {
 	struct perf_stat_output_ctx out;
@@ -1520,7 +1523,7 @@ static void print_metric_headers(struct perf_stat_config *config,
 	}
 
 	/* Print metrics headers only */
-	evlist__for_each_entry(evsel_list, counter) {
+	evlist__for_each_entry(evlist, counter) {
 		if (is_duration_time(counter))
 			continue;
 		os.evsel = counter;
@@ -1539,6 +1542,7 @@ static void print_metric_headers(struct perf_stat_config *config,
 }
 
 static void print_interval(struct perf_stat_config *config,
+			   struct perf_evlist *evlist,
 			   char *prefix, struct timespec *ts)
 {
 	bool metric_only = config->metric_only;
@@ -1584,7 +1588,7 @@ static void print_interval(struct perf_stat_config *config,
 	}
 
 	if ((num_print_interval == 0 || config->interval_clear) && metric_only)
-		print_metric_headers(config, " ", true);
+		print_metric_headers(config, evlist, " ", true);
 	if (++num_print_interval == 25)
 		num_print_interval = 0;
 }
@@ -1727,7 +1731,7 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 	char buf[64], *prefix = NULL;
 
 	if (interval)
-		print_interval(config, prefix = buf, ts);
+		print_interval(config, evlist, prefix = buf, ts);
 	else
 		print_header(config, _target, argc, argv);
 
@@ -1735,7 +1739,7 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 		static int num_print_iv;
 
 		if (num_print_iv == 0 && !interval)
-			print_metric_headers(config, prefix, false);
+			print_metric_headers(config, evlist, prefix, false);
 		if (num_print_iv++ == 25)
 			num_print_iv = 0;
 		if (config->aggr_mode == AGGR_GLOBAL && prefix)
@@ -1745,7 +1749,7 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 	switch (config->aggr_mode) {
 	case AGGR_CORE:
 	case AGGR_SOCKET:
-		print_aggr(config, prefix);
+		print_aggr(config, evlist, prefix);
 		break;
 	case AGGR_THREAD:
 		evlist__for_each_entry(evlist, counter) {
@@ -1765,7 +1769,7 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 		break;
 	case AGGR_NONE:
 		if (metric_only)
-			print_no_aggr_metric(config, prefix);
+			print_no_aggr_metric(config, evlist, prefix);
 		else {
 			evlist__for_each_entry(evlist, counter) {
 				if (is_duration_time(counter))
-- 
cgit v1.2.3


From 0c538a9462953dfcde2fe961aca2cf75c2747040 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:35 +0200
Subject: perf stat: Use 'evsel->evlist' instead of 'evsel_list' in
 collect_all_aliases()

Use 'evsel->evlist' instead of 'evsel_list' in collect_all_aliases(), to
get rid of the global 'evsel_list' variable dependency.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-27-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 46181ac492c5..11741f3a8342 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1154,10 +1154,11 @@ static void collect_all_aliases(struct perf_evsel *counter,
 				       bool first),
 			    void *data)
 {
+	struct perf_evlist *evlist = counter->evlist;
 	struct perf_evsel *alias;
 
-	alias = list_prepare_entry(counter, &(evsel_list->entries), node);
-	list_for_each_entry_continue (alias, &evsel_list->entries, node) {
+	alias = list_prepare_entry(counter, &(evlist->entries), node);
+	list_for_each_entry_continue (alias, &evlist->entries, node) {
 		if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
 		    alias->scale != counter->scale ||
 		    alias->cgrp != counter->cgrp ||
-- 
cgit v1.2.3


From d97ae04b3d5263be242a6a9f9eef6422fc86326a Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:36 +0200
Subject: perf stat: Move 'run_count' to 'struct perf_stat_config'

Move the static 'run_count' variable to 'struct perf_stat_config', so
that it can be passed around and used outside the 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-28-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 39 ++++++++++++++++++++-------------------
 tools/perf/util/stat.h    |  1 +
 2 files changed, 21 insertions(+), 19 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 11741f3a8342..1276596840c9 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -147,7 +147,6 @@ typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu);
 
 #define METRIC_ONLY_LEN 20
 
-static int			run_count			=  1;
 static volatile pid_t		child_pid			= -1;
 static bool			null_run			=  false;
 static int			detailed_run			=  0;
@@ -200,6 +199,7 @@ static struct perf_stat_config stat_config = {
 	.aggr_mode	= AGGR_GLOBAL,
 	.scale		= true,
 	.unit_width	= 4, /* strlen("unit") */
+	.run_count	= 1,
 };
 
 static bool is_duration_time(struct perf_evsel *evsel)
@@ -686,7 +686,7 @@ static void print_noise(struct perf_stat_config *config,
 {
 	struct perf_stat_evsel *ps;
 
-	if (run_count == 1)
+	if (config->run_count == 1)
 		return;
 
 	ps = evsel->stats;
@@ -1620,8 +1620,8 @@ static void print_header(struct perf_stat_config *config,
 			fprintf(output, "thread id \'%s", _target->tid);
 
 		fprintf(output, "\'");
-		if (run_count > 1)
-			fprintf(output, " (%d runs)", run_count);
+		if (config->run_count > 1)
+			fprintf(output, " (%d runs)", config->run_count);
 		fprintf(output, ":\n\n");
 	}
 }
@@ -1634,7 +1634,8 @@ static int get_precision(double num)
 	return lround(ceil(-log10(num)));
 }
 
-static void print_table(FILE *output, int precision, double avg)
+static void print_table(struct perf_stat_config *config,
+			FILE *output, int precision, double avg)
 {
 	char tmp[64];
 	int idx, indent = 0;
@@ -1645,7 +1646,7 @@ static void print_table(FILE *output, int precision, double avg)
 
 	fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
 
-	for (idx = 0; idx < run_count; idx++) {
+	for (idx = 0; idx < config->run_count; idx++) {
 		double run = (double) walltime_run[idx] / NSEC_PER_SEC;
 		int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
 
@@ -1675,7 +1676,7 @@ static void print_footer(struct perf_stat_config *config)
 	if (!null_run)
 		fprintf(output, "\n");
 
-	if (run_count == 1) {
+	if (config->run_count == 1) {
 		fprintf(output, " %17.9f seconds time elapsed", avg);
 
 		if (ru_display) {
@@ -1695,7 +1696,7 @@ static void print_footer(struct perf_stat_config *config)
 		int precision = get_precision(sd) + 2;
 
 		if (walltime_run_table)
-			print_table(output, precision, avg);
+			print_table(config, output, precision, avg);
 
 		fprintf(output, " %17.*f +- %.*f seconds time elapsed",
 			precision, avg, precision, sd);
@@ -1886,7 +1887,7 @@ static const struct option stat_options[] = {
 	OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
-	OPT_INTEGER('r', "repeat", &run_count,
+	OPT_INTEGER('r', "repeat", &stat_config.run_count,
 		    "repeat command and print average + stddev (max: 100, forever: 0)"),
 	OPT_BOOLEAN(0, "table", &walltime_run_table,
 		    "display details about each run (only with -r option)"),
@@ -2484,7 +2485,7 @@ static int __cmd_record(int argc, const char **argv)
 	if (output_name)
 		data->file.path = output_name;
 
-	if (run_count != 1 || forever) {
+	if (stat_config.run_count != 1 || forever) {
 		pr_err("Cannot use -r option with perf stat record.\n");
 		return -1;
 	}
@@ -2792,12 +2793,12 @@ int cmd_stat(int argc, const char **argv)
 		goto out;
 	}
 
-	if (stat_config.metric_only && run_count > 1) {
+	if (stat_config.metric_only && stat_config.run_count > 1) {
 		fprintf(stderr, "--metric-only is not supported with -r\n");
 		goto out;
 	}
 
-	if (walltime_run_table && run_count <= 1) {
+	if (walltime_run_table && stat_config.run_count <= 1) {
 		fprintf(stderr, "--table is only supported with -r\n");
 		parse_options_usage(stat_usage, stat_options, "r", 1);
 		parse_options_usage(NULL, stat_options, "table", 0);
@@ -2853,20 +2854,20 @@ int cmd_stat(int argc, const char **argv)
 	 * Display user/system times only for single
 	 * run and when there's specified tracee.
 	 */
-	if ((run_count == 1) && target__none(&target))
+	if ((stat_config.run_count == 1) && target__none(&target))
 		ru_display = true;
 
-	if (run_count < 0) {
+	if (stat_config.run_count < 0) {
 		pr_err("Run count must be a positive number\n");
 		parse_options_usage(stat_usage, stat_options, "r", 1);
 		goto out;
-	} else if (run_count == 0) {
+	} else if (stat_config.run_count == 0) {
 		forever = true;
-		run_count = 1;
+		stat_config.run_count = 1;
 	}
 
 	if (walltime_run_table) {
-		walltime_run = zalloc(run_count * sizeof(walltime_run[0]));
+		walltime_run = zalloc(stat_config.run_count * sizeof(walltime_run[0]));
 		if (!walltime_run) {
 			pr_err("failed to setup -r option");
 			goto out;
@@ -2994,8 +2995,8 @@ int cmd_stat(int argc, const char **argv)
 	signal(SIGABRT, skip_signal);
 
 	status = 0;
-	for (run_idx = 0; forever || run_idx < run_count; run_idx++) {
-		if (run_count != 1 && verbose > 0)
+	for (run_idx = 0; forever || run_idx < stat_config.run_count; run_idx++) {
+		if (stat_config.run_count != 1 && verbose > 0)
 			fprintf(output, "[ perf stat: executing run #%d ... ]\n",
 				run_idx + 1);
 
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 2dc66e0ba4b8..351a36f5f5b0 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -100,6 +100,7 @@ struct perf_stat_config {
 	unsigned int		 initial_delay;
 	unsigned int		 unit_width;
 	int			 times;
+	int			 run_count;
 	struct runtime_stat	*stats;
 	int			 stats_num;
 	const char		*csv_sep;
-- 
cgit v1.2.3


From ee1760e2cf623bc6834fc3e4e89c6ad030a25dfd Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:37 +0200
Subject: perf stat: Move 'metric_only_len' to 'struct perf_stat_config'

Move the static 'metric_only_len' variable to 'struct perf_stat_config',
so that it can be passed around and used outside the 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-29-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 10 +++++-----
 tools/perf/util/stat.h    |  1 +
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 1276596840c9..e96cef526ef0 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -176,7 +176,6 @@ static int			print_mixed_hw_group_error;
 static u64			*walltime_run;
 static bool			ru_display			= false;
 static struct rusage		ru_data;
-static unsigned int		metric_only_len			= METRIC_ONLY_LEN;
 
 struct perf_stat {
 	bool			 record;
@@ -200,6 +199,7 @@ static struct perf_stat_config stat_config = {
 	.scale		= true,
 	.unit_width	= 4, /* strlen("unit") */
 	.run_count	= 1,
+	.metric_only_len = METRIC_ONLY_LEN,
 };
 
 static bool is_duration_time(struct perf_evsel *evsel)
@@ -854,14 +854,14 @@ static const char *fixunit(char *buf, struct perf_evsel *evsel,
 	return unit;
 }
 
-static void print_metric_only(struct perf_stat_config *config __maybe_unused,
+static void print_metric_only(struct perf_stat_config *config,
 			      void *ctx, const char *color, const char *fmt,
 			      const char *unit, double val)
 {
 	struct outstate *os = ctx;
 	FILE *out = os->fh;
 	char buf[1024], str[1024];
-	unsigned mlen = metric_only_len;
+	unsigned mlen = config->metric_only_len;
 
 	if (!valid_only_metric(unit))
 		return;
@@ -902,7 +902,7 @@ static void new_line_metric(struct perf_stat_config *config __maybe_unused,
 {
 }
 
-static void print_metric_header(struct perf_stat_config *config __maybe_unused,
+static void print_metric_header(struct perf_stat_config *config,
 				void *ctx, const char *color __maybe_unused,
 				const char *fmt __maybe_unused,
 				const char *unit, double val __maybe_unused)
@@ -916,7 +916,7 @@ static void print_metric_header(struct perf_stat_config *config __maybe_unused,
 	if (config->csv_output)
 		fprintf(os->fh, "%s%s", unit, config->csv_sep);
 	else
-		fprintf(os->fh, "%*s ", metric_only_len, unit);
+		fprintf(os->fh, "%*s ", config->metric_only_len, unit);
 }
 
 static int first_shadow_cpu(struct perf_evsel *evsel, int id)
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 351a36f5f5b0..e70e6d93ee1b 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -99,6 +99,7 @@ struct perf_stat_config {
 	unsigned int		 timeout;
 	unsigned int		 initial_delay;
 	unsigned int		 unit_width;
+	unsigned int		 metric_only_len;
 	int			 times;
 	int			 run_count;
 	struct runtime_stat	*stats;
-- 
cgit v1.2.3


From ae2d7da554f0dda837b6639d247665f6df90e41f Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:38 +0200
Subject: perf stat: Pass 'struct perf_stat_config' to first_shadow_cpu()

Pass a 'struct perf_stat_config' arg to first_shadow_cpu(), so that the
function does not depend on the 'perf stat' command object local
'stat_config' variable and can then be moved out.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-30-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e96cef526ef0..f5ac6545af34 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -919,17 +919,18 @@ static void print_metric_header(struct perf_stat_config *config,
 		fprintf(os->fh, "%*s ", config->metric_only_len, unit);
 }
 
-static int first_shadow_cpu(struct perf_evsel *evsel, int id)
+static int first_shadow_cpu(struct perf_stat_config *config,
+			    struct perf_evsel *evsel, int id)
 {
 	int i;
 
 	if (!aggr_get_id)
 		return 0;
 
-	if (stat_config.aggr_mode == AGGR_NONE)
+	if (config->aggr_mode == AGGR_NONE)
 		return id;
 
-	if (stat_config.aggr_mode == AGGR_GLOBAL)
+	if (config->aggr_mode == AGGR_GLOBAL)
 		return 0;
 
 	for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
@@ -1090,7 +1091,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 	}
 
 	perf_stat__print_shadow_stats(config, counter, uval,
-				first_shadow_cpu(counter, id),
+				first_shadow_cpu(config, counter, id),
 				&out, &metric_events, st);
 	if (!config->csv_output && !config->metric_only) {
 		print_noise(config, counter, noise);
@@ -1098,7 +1099,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 	}
 }
 
-static void aggr_update_shadow(void)
+static void aggr_update_shadow(struct perf_stat_config *config)
 {
 	int cpu, s2, id, s;
 	u64 val;
@@ -1115,7 +1116,7 @@ static void aggr_update_shadow(void)
 				val += perf_counts(counter->counts, cpu, 0)->val;
 			}
 			perf_stat__update_shadow_stats(counter, val,
-					first_shadow_cpu(counter, id),
+					first_shadow_cpu(config, counter, id),
 					&rt_stat);
 		}
 	}
@@ -1237,7 +1238,7 @@ static void print_aggr(struct perf_stat_config *config,
 	if (!(aggr_map || aggr_get_id))
 		return;
 
-	aggr_update_shadow();
+	aggr_update_shadow(config);
 
 	/*
 	 * With metric_only everything is on a single line.
-- 
cgit v1.2.3


From 77e0faf8552c9329d58a4de460928e03252647c6 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:39 +0200
Subject: perf stat: Pass 'evlist' to aggr_update_shadow()

Pass a 'evlist' argument to aggr_update_shadow(), to get rid of the
global 'evsel_list' variable dependency.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-31-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f5ac6545af34..2711d8f6e4b8 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1099,7 +1099,8 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 	}
 }
 
-static void aggr_update_shadow(struct perf_stat_config *config)
+static void aggr_update_shadow(struct perf_stat_config *config,
+			       struct perf_evlist *evlist)
 {
 	int cpu, s2, id, s;
 	u64 val;
@@ -1107,7 +1108,7 @@ static void aggr_update_shadow(struct perf_stat_config *config)
 
 	for (s = 0; s < aggr_map->nr; s++) {
 		id = aggr_map->map[s];
-		evlist__for_each_entry(evsel_list, counter) {
+		evlist__for_each_entry(evlist, counter) {
 			val = 0;
 			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
 				s2 = aggr_get_id(evsel_list->cpus, cpu);
@@ -1238,7 +1239,7 @@ static void print_aggr(struct perf_stat_config *config,
 	if (!(aggr_map || aggr_get_id))
 		return;
 
-	aggr_update_shadow(config);
+	aggr_update_shadow(config, evlist);
 
 	/*
 	 * With metric_only everything is on a single line.
-- 
cgit v1.2.3


From 26893a6018f88779c0aded934e99e0ebb6859a58 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:40 +0200
Subject: perf stat: Add 'walltime_nsecs_stats' pointer to 'struct
 perf_stat_config'

Add 'walltime_nsecs_stats' pointer to 'struct perf_stat_config', so that
it can be passed around and used outside the 'perf stat' command.

It's initialized to point to stat's walltime_nsecs_stats value.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-32-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 15 ++++++++-------
 tools/perf/util/stat.h    |  1 +
 2 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 2711d8f6e4b8..381549a989b4 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -195,11 +195,12 @@ static struct perf_stat		perf_stat;
 static volatile int done = 0;
 
 static struct perf_stat_config stat_config = {
-	.aggr_mode	= AGGR_GLOBAL,
-	.scale		= true,
-	.unit_width	= 4, /* strlen("unit") */
-	.run_count	= 1,
-	.metric_only_len = METRIC_ONLY_LEN,
+	.aggr_mode		= AGGR_GLOBAL,
+	.scale			= true,
+	.unit_width		= 4, /* strlen("unit") */
+	.run_count		= 1,
+	.metric_only_len	= METRIC_ONLY_LEN,
+	.walltime_nsecs_stats	= &walltime_nsecs_stats,
 };
 
 static bool is_duration_time(struct perf_evsel *evsel)
@@ -1671,7 +1672,7 @@ static double timeval2double(struct timeval *t)
 
 static void print_footer(struct perf_stat_config *config)
 {
-	double avg = avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC;
+	double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
 	FILE *output = config->output;
 	int n;
 
@@ -1690,7 +1691,7 @@ static void print_footer(struct perf_stat_config *config)
 			fprintf(output, " %17.9f seconds sys\n", ru_stime);
 		}
 	} else {
-		double sd = stddev_stats(&walltime_nsecs_stats) / NSEC_PER_SEC;
+		double sd = stddev_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
 		/*
 		 * Display at most 2 more significant
 		 * digits than the stddev inaccuracy.
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index e70e6d93ee1b..35550e3efd81 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -105,6 +105,7 @@ struct perf_stat_config {
 	struct runtime_stat	*stats;
 	int			 stats_num;
 	const char		*csv_sep;
+	struct stats		*walltime_nsecs_stats;
 };
 
 void update_stats(struct stats *stats, u64 val);
-- 
cgit v1.2.3


From aea0dca1629c72128cf7174d1d3f3807f7297005 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:41 +0200
Subject: perf stat: Move 'null_run' to 'struct perf_stat_config'

Move the static 'null_run' variable to 'struct perf_stat_config', so
that it can be passed around and used outside the 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-33-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 7 +++----
 tools/perf/util/stat.h    | 1 +
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 381549a989b4..844c755564e3 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -148,7 +148,6 @@ typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu);
 #define METRIC_ONLY_LEN 20
 
 static volatile pid_t		child_pid			= -1;
-static bool			null_run			=  false;
 static int			detailed_run			=  0;
 static bool			transaction_run;
 static bool			topdown_run			= false;
@@ -1676,7 +1675,7 @@ static void print_footer(struct perf_stat_config *config)
 	FILE *output = config->output;
 	int n;
 
-	if (!null_run)
+	if (!config->null_run)
 		fprintf(output, "\n");
 
 	if (config->run_count == 1) {
@@ -1894,7 +1893,7 @@ static const struct option stat_options[] = {
 		    "repeat command and print average + stddev (max: 100, forever: 0)"),
 	OPT_BOOLEAN(0, "table", &walltime_run_table,
 		    "display details about each run (only with -r option)"),
-	OPT_BOOLEAN('n', "null", &null_run,
+	OPT_BOOLEAN('n', "null", &stat_config.null_run,
 		    "null run - dont start any counters"),
 	OPT_INCR('d', "detailed", &detailed_run,
 		    "detailed run - start a lot of events"),
@@ -2309,7 +2308,7 @@ static int add_default_attributes(void)
 	struct parse_events_error errinfo;
 
 	/* Set attrs if no event is selected and !null_run: */
-	if (null_run)
+	if (stat_config.null_run)
 		return 0;
 
 	if (transaction_run) {
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 35550e3efd81..c198926c0e27 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -94,6 +94,7 @@ struct perf_stat_config {
 	bool			 csv_output;
 	bool			 interval_clear;
 	bool			 metric_only;
+	bool			 null_run;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
-- 
cgit v1.2.3


From 31084123c1962dd4235655c1839a50c9cf6c709b Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:42 +0200
Subject: perf stat: Move 'print_free_counters_hint' to 'struct
 perf_stat_config'

Move the 'print_free_counters_hint' variable to 'struct perf_stat_config',
so that it can be passed around and used outside the 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-34-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 5 ++---
 tools/perf/util/stat.h    | 1 +
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 844c755564e3..8748bb5e5403 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -170,7 +170,6 @@ static bool			append_file;
 static bool			interval_count;
 static const char		*output_name;
 static int			output_fd;
-static int			print_free_counters_hint;
 static int			print_mixed_hw_group_error;
 static u64			*walltime_run;
 static bool			ru_display			= false;
@@ -1051,7 +1050,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 			config->csv_sep);
 
 		if (counter->supported) {
-			print_free_counters_hint = 1;
+			config->print_free_counters_hint = 1;
 			if (is_mixed_hw_group(counter))
 				print_mixed_hw_group_error = 1;
 		}
@@ -1707,7 +1706,7 @@ static void print_footer(struct perf_stat_config *config)
 	}
 	fprintf(output, "\n\n");
 
-	if (print_free_counters_hint &&
+	if (config->print_free_counters_hint &&
 	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
 	    n > 0)
 		fprintf(output,
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index c198926c0e27..8cad17363e90 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -103,6 +103,7 @@ struct perf_stat_config {
 	unsigned int		 metric_only_len;
 	int			 times;
 	int			 run_count;
+	int			 print_free_counters_hint;
 	struct runtime_stat	*stats;
 	int			 stats_num;
 	const char		*csv_sep;
-- 
cgit v1.2.3


From 3b3cd9a41c2b5d97309099ba6eae69b2d3177226 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:43 +0200
Subject: perf stat: Move 'print_mixed_hw_group_error' to 'struct
 perf_stat_config'

Move the 'print_mixed_hw_group_error' global variable to 'struct perf_stat_config',
so that it can be passed around and used outside the 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-35-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 5 ++---
 tools/perf/util/stat.h    | 1 +
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 8748bb5e5403..f61c2dc8c7e8 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -170,7 +170,6 @@ static bool			append_file;
 static bool			interval_count;
 static const char		*output_name;
 static int			output_fd;
-static int			print_mixed_hw_group_error;
 static u64			*walltime_run;
 static bool			ru_display			= false;
 static struct rusage		ru_data;
@@ -1052,7 +1051,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 		if (counter->supported) {
 			config->print_free_counters_hint = 1;
 			if (is_mixed_hw_group(counter))
-				print_mixed_hw_group_error = 1;
+				config->print_mixed_hw_group_error = 1;
 		}
 
 		fprintf(config->output, "%-*s%s",
@@ -1715,7 +1714,7 @@ static void print_footer(struct perf_stat_config *config)
 "	perf stat ...\n"
 "	echo 1 > /proc/sys/kernel/nmi_watchdog\n");
 
-	if (print_mixed_hw_group_error)
+	if (config->print_mixed_hw_group_error)
 		fprintf(output,
 			"The events in group usually have to be from "
 			"the same PMU. Try reorganizing the group.\n");
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 8cad17363e90..6fb4dac26ccc 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -104,6 +104,7 @@ struct perf_stat_config {
 	int			 times;
 	int			 run_count;
 	int			 print_free_counters_hint;
+	int			 print_mixed_hw_group_error;
 	struct runtime_stat	*stats;
 	int			 stats_num;
 	const char		*csv_sep;
-- 
cgit v1.2.3


From 8897a8916efb29fa8bbe9e5f6e5d56362aedf64e Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:44 +0200
Subject: perf stat: Move ru_* data to 'struct perf_stat_config'

Move the 'ru_*' global variables to 'struct perf_stat_config', so that
it can be passed around and used outside the 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-36-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 12 +++++-------
 tools/perf/util/stat.h    |  6 ++++++
 2 files changed, 11 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f61c2dc8c7e8..942ebfd8ef2e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -171,8 +171,6 @@ static bool			interval_count;
 static const char		*output_name;
 static int			output_fd;
 static u64			*walltime_run;
-static bool			ru_display			= false;
-static struct rusage		ru_data;
 
 struct perf_stat {
 	bool			 record;
@@ -583,7 +581,7 @@ try_again:
 					break;
 			}
 		}
-		wait4(child_pid, &status, 0, &ru_data);
+		wait4(child_pid, &status, 0, &stat_config.ru_data);
 
 		if (workload_exec_errno) {
 			const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
@@ -1679,9 +1677,9 @@ static void print_footer(struct perf_stat_config *config)
 	if (config->run_count == 1) {
 		fprintf(output, " %17.9f seconds time elapsed", avg);
 
-		if (ru_display) {
-			double ru_utime = timeval2double(&ru_data.ru_utime);
-			double ru_stime = timeval2double(&ru_data.ru_stime);
+		if (config->ru_display) {
+			double ru_utime = timeval2double(&config->ru_data.ru_utime);
+			double ru_stime = timeval2double(&config->ru_data.ru_stime);
 
 			fprintf(output, "\n\n");
 			fprintf(output, " %17.9f seconds user\n", ru_utime);
@@ -2855,7 +2853,7 @@ int cmd_stat(int argc, const char **argv)
 	 * run and when there's specified tracee.
 	 */
 	if ((stat_config.run_count == 1) && target__none(&target))
-		ru_display = true;
+		stat_config.ru_display = true;
 
 	if (stat_config.run_count < 0) {
 		pr_err("Run count must be a positive number\n");
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 6fb4dac26ccc..1fd0b7e196c6 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -4,6 +4,10 @@
 
 #include <linux/types.h>
 #include <stdio.h>
+#include <sys/types.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <sys/wait.h>
 #include "xyarray.h"
 #include "rblist.h"
 #include "perf.h"
@@ -95,6 +99,7 @@ struct perf_stat_config {
 	bool			 interval_clear;
 	bool			 metric_only;
 	bool			 null_run;
+	bool			 ru_display;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
@@ -109,6 +114,7 @@ struct perf_stat_config {
 	int			 stats_num;
 	const char		*csv_sep;
 	struct stats		*walltime_nsecs_stats;
+	struct rusage		 ru_data;
 };
 
 void update_stats(struct stats *stats, u64 val);
-- 
cgit v1.2.3


From 6f6b6594b5f380b0a972b66b275caa6c54bb1fea Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:45 +0200
Subject: perf stat: Move *_aggr_* data to 'struct perf_stat_config'

Move the *_aggr_* global variables to 'struct perf_stat_config', so that
it can be passed around and used outside 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-37-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 112 ++++++++++++++++++++++++----------------------
 tools/perf/util/stat.h    |   6 +++
 2 files changed, 64 insertions(+), 54 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 942ebfd8ef2e..2f606f76b66a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -143,8 +143,6 @@ static struct target target = {
 	.uid	= UINT_MAX,
 };
 
-typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu);
-
 #define METRIC_ONLY_LEN 20
 
 static volatile pid_t		child_pid			= -1;
@@ -164,8 +162,6 @@ static bool			force_metric_only		= false;
 static bool			no_merge			= false;
 static bool			walltime_run_table		= false;
 static struct timespec		ref_time;
-static struct cpu_map		*aggr_map;
-static aggr_get_id_t		aggr_get_id;
 static bool			append_file;
 static bool			interval_count;
 static const char		*output_name;
@@ -920,7 +916,7 @@ static int first_shadow_cpu(struct perf_stat_config *config,
 {
 	int i;
 
-	if (!aggr_get_id)
+	if (!config->aggr_get_id)
 		return 0;
 
 	if (config->aggr_mode == AGGR_NONE)
@@ -932,7 +928,7 @@ static int first_shadow_cpu(struct perf_stat_config *config,
 	for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
 		int cpu2 = perf_evsel__cpus(evsel)->map[i];
 
-		if (aggr_get_id(evsel_list->cpus, cpu2) == id)
+		if (config->aggr_get_id(config, evsel_list->cpus, cpu2) == id)
 			return cpu2;
 	}
 	return 0;
@@ -1102,12 +1098,12 @@ static void aggr_update_shadow(struct perf_stat_config *config,
 	u64 val;
 	struct perf_evsel *counter;
 
-	for (s = 0; s < aggr_map->nr; s++) {
-		id = aggr_map->map[s];
+	for (s = 0; s < config->aggr_map->nr; s++) {
+		id = config->aggr_map->map[s];
 		evlist__for_each_entry(evlist, counter) {
 			val = 0;
 			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-				s2 = aggr_get_id(evsel_list->cpus, cpu);
+				s2 = config->aggr_get_id(config, evsel_list->cpus, cpu);
 				if (s2 != id)
 					continue;
 				val += perf_counts(counter->counts, cpu, 0)->val;
@@ -1147,8 +1143,8 @@ static void uniquify_event_name(struct perf_evsel *counter)
 	counter->uniquified_name = true;
 }
 
-static void collect_all_aliases(struct perf_evsel *counter,
-			    void (*cb)(struct perf_evsel *counter, void *data,
+static void collect_all_aliases(struct perf_stat_config *config, struct perf_evsel *counter,
+			    void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data,
 				       bool first),
 			    void *data)
 {
@@ -1164,22 +1160,22 @@ static void collect_all_aliases(struct perf_evsel *counter,
 		    perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
 			break;
 		alias->merged_stat = true;
-		cb(alias, data, false);
+		cb(config, alias, data, false);
 	}
 }
 
-static bool collect_data(struct perf_evsel *counter,
-			    void (*cb)(struct perf_evsel *counter, void *data,
+static bool collect_data(struct perf_stat_config *config, struct perf_evsel *counter,
+			    void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data,
 				       bool first),
 			    void *data)
 {
 	if (counter->merged_stat)
 		return false;
-	cb(counter, data, true);
+	cb(config, counter, data, true);
 	if (no_merge)
 		uniquify_event_name(counter);
 	else if (counter->auto_merge_stats)
-		collect_all_aliases(counter, cb, data);
+		collect_all_aliases(config, counter, cb, data);
 	return true;
 }
 
@@ -1190,7 +1186,8 @@ struct aggr_data {
 	int cpu;
 };
 
-static void aggr_cb(struct perf_evsel *counter, void *data, bool first)
+static void aggr_cb(struct perf_stat_config *config,
+		    struct perf_evsel *counter, void *data, bool first)
 {
 	struct aggr_data *ad = data;
 	int cpu, s2;
@@ -1198,7 +1195,7 @@ static void aggr_cb(struct perf_evsel *counter, void *data, bool first)
 	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
 		struct perf_counts_values *counts;
 
-		s2 = aggr_get_id(perf_evsel__cpus(counter), cpu);
+		s2 = config->aggr_get_id(config, perf_evsel__cpus(counter), cpu);
 		if (s2 != ad->id)
 			continue;
 		if (first)
@@ -1232,7 +1229,7 @@ static void print_aggr(struct perf_stat_config *config,
 	u64 ena, run, val;
 	bool first;
 
-	if (!(aggr_map || aggr_get_id))
+	if (!(config->aggr_map || config->aggr_get_id))
 		return;
 
 	aggr_update_shadow(config, evlist);
@@ -1241,12 +1238,12 @@ static void print_aggr(struct perf_stat_config *config,
 	 * With metric_only everything is on a single line.
 	 * Without each counter has its own line.
 	 */
-	for (s = 0; s < aggr_map->nr; s++) {
+	for (s = 0; s < config->aggr_map->nr; s++) {
 		struct aggr_data ad;
 		if (prefix && metric_only)
 			fprintf(output, "%s", prefix);
 
-		ad.id = id = aggr_map->map[s];
+		ad.id = id = config->aggr_map->map[s];
 		first = true;
 		evlist__for_each_entry(evlist, counter) {
 			if (is_duration_time(counter))
@@ -1254,7 +1251,7 @@ static void print_aggr(struct perf_stat_config *config,
 
 			ad.val = ad.ena = ad.run = 0;
 			ad.nr = 0;
-			if (!collect_data(counter, aggr_cb, &ad))
+			if (!collect_data(config, counter, aggr_cb, &ad))
 				continue;
 			nr = ad.nr;
 			ena = ad.ena;
@@ -1370,7 +1367,8 @@ struct caggr_data {
 	double avg, avg_enabled, avg_running;
 };
 
-static void counter_aggr_cb(struct perf_evsel *counter, void *data,
+static void counter_aggr_cb(struct perf_stat_config *config __maybe_unused,
+			    struct perf_evsel *counter, void *data,
 			    bool first __maybe_unused)
 {
 	struct caggr_data *cd = data;
@@ -1393,7 +1391,7 @@ static void print_counter_aggr(struct perf_stat_config *config,
 	double uval;
 	struct caggr_data cd = { .avg = 0.0 };
 
-	if (!collect_data(counter, counter_aggr_cb, &cd))
+	if (!collect_data(config, counter, counter_aggr_cb, &cd))
 		return;
 
 	if (prefix && !metric_only)
@@ -1406,7 +1404,8 @@ static void print_counter_aggr(struct perf_stat_config *config,
 		fprintf(output, "\n");
 }
 
-static void counter_cb(struct perf_evsel *counter, void *data,
+static void counter_cb(struct perf_stat_config *config __maybe_unused,
+		       struct perf_evsel *counter, void *data,
 		       bool first __maybe_unused)
 {
 	struct aggr_data *ad = data;
@@ -1431,7 +1430,7 @@ static void print_counter(struct perf_stat_config *config,
 	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
 		struct aggr_data ad = { .cpu = cpu };
 
-		if (!collect_data(counter, counter_cb, &ad))
+		if (!collect_data(config, counter, counter_cb, &ad))
 			return;
 		val = ad.val;
 		ena = ad.ena;
@@ -1944,12 +1943,14 @@ static const struct option stat_options[] = {
 	OPT_END()
 };
 
-static int perf_stat__get_socket(struct cpu_map *map, int cpu)
+static int perf_stat__get_socket(struct perf_stat_config *config __maybe_unused,
+				 struct cpu_map *map, int cpu)
 {
 	return cpu_map__get_socket(map, cpu, NULL);
 }
 
-static int perf_stat__get_core(struct cpu_map *map, int cpu)
+static int perf_stat__get_core(struct perf_stat_config *config __maybe_unused,
+			       struct cpu_map *map, int cpu)
 {
 	return cpu_map__get_core(map, cpu, NULL);
 }
@@ -1966,9 +1967,8 @@ static int cpu_map__get_max(struct cpu_map *map)
 	return max;
 }
 
-static struct cpu_map *cpus_aggr_map;
-
-static int perf_stat__get_aggr(aggr_get_id_t get_id, struct cpu_map *map, int idx)
+static int perf_stat__get_aggr(struct perf_stat_config *config,
+			       aggr_get_id_t get_id, struct cpu_map *map, int idx)
 {
 	int cpu;
 
@@ -1977,20 +1977,22 @@ static int perf_stat__get_aggr(aggr_get_id_t get_id, struct cpu_map *map, int id
 
 	cpu = map->map[idx];
 
-	if (cpus_aggr_map->map[cpu] == -1)
-		cpus_aggr_map->map[cpu] = get_id(map, idx);
+	if (config->cpus_aggr_map->map[cpu] == -1)
+		config->cpus_aggr_map->map[cpu] = get_id(config, map, idx);
 
-	return cpus_aggr_map->map[cpu];
+	return config->cpus_aggr_map->map[cpu];
 }
 
-static int perf_stat__get_socket_cached(struct cpu_map *map, int idx)
+static int perf_stat__get_socket_cached(struct perf_stat_config *config,
+					struct cpu_map *map, int idx)
 {
-	return perf_stat__get_aggr(perf_stat__get_socket, map, idx);
+	return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx);
 }
 
-static int perf_stat__get_core_cached(struct cpu_map *map, int idx)
+static int perf_stat__get_core_cached(struct perf_stat_config *config,
+				      struct cpu_map *map, int idx)
 {
-	return perf_stat__get_aggr(perf_stat__get_core, map, idx);
+	return perf_stat__get_aggr(config, perf_stat__get_core, map, idx);
 }
 
 static int perf_stat_init_aggr_mode(void)
@@ -1999,18 +2001,18 @@ static int perf_stat_init_aggr_mode(void)
 
 	switch (stat_config.aggr_mode) {
 	case AGGR_SOCKET:
-		if (cpu_map__build_socket_map(evsel_list->cpus, &aggr_map)) {
+		if (cpu_map__build_socket_map(evsel_list->cpus, &stat_config.aggr_map)) {
 			perror("cannot build socket map");
 			return -1;
 		}
-		aggr_get_id = perf_stat__get_socket_cached;
+		stat_config.aggr_get_id = perf_stat__get_socket_cached;
 		break;
 	case AGGR_CORE:
-		if (cpu_map__build_core_map(evsel_list->cpus, &aggr_map)) {
+		if (cpu_map__build_core_map(evsel_list->cpus, &stat_config.aggr_map)) {
 			perror("cannot build core map");
 			return -1;
 		}
-		aggr_get_id = perf_stat__get_core_cached;
+		stat_config.aggr_get_id = perf_stat__get_core_cached;
 		break;
 	case AGGR_NONE:
 	case AGGR_GLOBAL:
@@ -2026,16 +2028,16 @@ static int perf_stat_init_aggr_mode(void)
 	 * the aggregation translate cpumap.
 	 */
 	nr = cpu_map__get_max(evsel_list->cpus);
-	cpus_aggr_map = cpu_map__empty_new(nr + 1);
-	return cpus_aggr_map ? 0 : -ENOMEM;
+	stat_config.cpus_aggr_map = cpu_map__empty_new(nr + 1);
+	return stat_config.cpus_aggr_map ? 0 : -ENOMEM;
 }
 
 static void perf_stat__exit_aggr_mode(void)
 {
-	cpu_map__put(aggr_map);
-	cpu_map__put(cpus_aggr_map);
-	aggr_map = NULL;
-	cpus_aggr_map = NULL;
+	cpu_map__put(stat_config.aggr_map);
+	cpu_map__put(stat_config.cpus_aggr_map);
+	stat_config.aggr_map = NULL;
+	stat_config.cpus_aggr_map = NULL;
 }
 
 static inline int perf_env__get_cpu(struct perf_env *env, struct cpu_map *map, int idx)
@@ -2093,12 +2095,14 @@ static int perf_env__build_core_map(struct perf_env *env, struct cpu_map *cpus,
 	return cpu_map__build_map(cpus, corep, perf_env__get_core, env);
 }
 
-static int perf_stat__get_socket_file(struct cpu_map *map, int idx)
+static int perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused,
+				      struct cpu_map *map, int idx)
 {
 	return perf_env__get_socket(map, idx, &perf_stat.session->header.env);
 }
 
-static int perf_stat__get_core_file(struct cpu_map *map, int idx)
+static int perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused,
+				    struct cpu_map *map, int idx)
 {
 	return perf_env__get_core(map, idx, &perf_stat.session->header.env);
 }
@@ -2109,18 +2113,18 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
 
 	switch (stat_config.aggr_mode) {
 	case AGGR_SOCKET:
-		if (perf_env__build_socket_map(env, evsel_list->cpus, &aggr_map)) {
+		if (perf_env__build_socket_map(env, evsel_list->cpus, &stat_config.aggr_map)) {
 			perror("cannot build socket map");
 			return -1;
 		}
-		aggr_get_id = perf_stat__get_socket_file;
+		stat_config.aggr_get_id = perf_stat__get_socket_file;
 		break;
 	case AGGR_CORE:
-		if (perf_env__build_core_map(env, evsel_list->cpus, &aggr_map)) {
+		if (perf_env__build_core_map(env, evsel_list->cpus, &stat_config.aggr_map)) {
 			perror("cannot build core map");
 			return -1;
 		}
-		aggr_get_id = perf_stat__get_core_file;
+		stat_config.aggr_get_id = perf_stat__get_core_file;
 		break;
 	case AGGR_NONE:
 	case AGGR_GLOBAL:
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 1fd0b7e196c6..be202b066e62 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -90,6 +90,9 @@ struct runtime_stat {
 	struct rblist value_list;
 };
 
+typedef int (*aggr_get_id_t)(struct perf_stat_config *config,
+			     struct cpu_map *m, int cpu);
+
 struct perf_stat_config {
 	enum aggr_mode		 aggr_mode;
 	bool			 scale;
@@ -115,6 +118,9 @@ struct perf_stat_config {
 	const char		*csv_sep;
 	struct stats		*walltime_nsecs_stats;
 	struct rusage		 ru_data;
+	struct cpu_map		*aggr_map;
+	aggr_get_id_t		 aggr_get_id;
+	struct cpu_map		*cpus_aggr_map;
 };
 
 void update_stats(struct stats *stats, u64 val);
-- 
cgit v1.2.3


From a138af663500a07742bb27793302625135a0f6c4 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:46 +0200
Subject: perf stat: Do not use the global 'evsel_list' in print functions

Get rid of the the 'evsel_list' global variable dependency, here we can
use the 'evlist' pointer from the evsel.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-38-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 2f606f76b66a..445673f688de 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -914,6 +914,7 @@ static void print_metric_header(struct perf_stat_config *config,
 static int first_shadow_cpu(struct perf_stat_config *config,
 			    struct perf_evsel *evsel, int id)
 {
+	struct perf_evlist *evlist = evsel->evlist;
 	int i;
 
 	if (!config->aggr_get_id)
@@ -928,7 +929,7 @@ static int first_shadow_cpu(struct perf_stat_config *config,
 	for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
 		int cpu2 = perf_evsel__cpus(evsel)->map[i];
 
-		if (config->aggr_get_id(config, evsel_list->cpus, cpu2) == id)
+		if (config->aggr_get_id(config, evlist->cpus, cpu2) == id)
 			return cpu2;
 	}
 	return 0;
@@ -1103,7 +1104,7 @@ static void aggr_update_shadow(struct perf_stat_config *config,
 		evlist__for_each_entry(evlist, counter) {
 			val = 0;
 			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-				s2 = config->aggr_get_id(config, evsel_list->cpus, cpu);
+				s2 = config->aggr_get_id(config, evlist->cpus, cpu);
 				if (s2 != id)
 					continue;
 				val += perf_counts(counter->counts, cpu, 0)->val;
-- 
cgit v1.2.3


From 34ff0866d46ae206de884f54e7235f57096e5588 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:47 +0200
Subject: perf stat: Move 'big_num' data to 'struct perf_stat_config'

Move the static variable 'big_num' to 'struct perf_stat_config', so that
it can be passed around and used outside 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-39-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 8 ++++----
 tools/perf/util/stat.h    | 1 +
 2 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 445673f688de..8ca85017a973 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -151,7 +151,6 @@ static bool			transaction_run;
 static bool			topdown_run			= false;
 static bool			smi_cost			= false;
 static bool			smi_reset			= false;
-static bool			big_num				=  true;
 static int			big_num_opt			=  -1;
 static bool			group				= false;
 static const char		*pre_cmd			= NULL;
@@ -192,6 +191,7 @@ static struct perf_stat_config stat_config = {
 	.run_count		= 1,
 	.metric_only_len	= METRIC_ONLY_LEN,
 	.walltime_nsecs_stats	= &walltime_nsecs_stats,
+	.big_num		= true,
 };
 
 static bool is_duration_time(struct perf_evsel *evsel)
@@ -945,7 +945,7 @@ static void abs_printout(struct perf_stat_config *config,
 	if (config->csv_output) {
 		fmt = floor(sc) != sc ?  "%.2f%s" : "%.0f%s";
 	} else {
-		if (big_num)
+		if (config->big_num)
 			fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
 		else
 			fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
@@ -2847,9 +2847,9 @@ int cmd_stat(int argc, const char **argv)
 			parse_options_usage(NULL, stat_options, "x", 1);
 			goto out;
 		} else /* Nope, so disable big number formatting */
-			big_num = false;
+			stat_config.big_num = false;
 	} else if (big_num_opt == 0) /* User passed --no-big-num */
-		big_num = false;
+		stat_config.big_num = false;
 
 	setup_system_wide(argc);
 
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index be202b066e62..843672214cca 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -103,6 +103,7 @@ struct perf_stat_config {
 	bool			 metric_only;
 	bool			 null_run;
 	bool			 ru_display;
+	bool			 big_num;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
-- 
cgit v1.2.3


From fdee335b00b0807e8d65b8e3d81214556f07bed3 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:48 +0200
Subject: perf stat: Move 'no_merge' data to 'struct perf_stat_config'

Move the static variable 'no_merge' to 'struct perf_stat_config', so
that it can be passed around and used outside 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-40-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 5 ++---
 tools/perf/util/stat.h    | 1 +
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 8ca85017a973..c4df076f1e54 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -158,7 +158,6 @@ static const char		*post_cmd			= NULL;
 static bool			sync_run			= false;
 static bool			forever				= false;
 static bool			force_metric_only		= false;
-static bool			no_merge			= false;
 static bool			walltime_run_table		= false;
 static struct timespec		ref_time;
 static bool			append_file;
@@ -1173,7 +1172,7 @@ static bool collect_data(struct perf_stat_config *config, struct perf_evsel *cou
 	if (counter->merged_stat)
 		return false;
 	cb(config, counter, data, true);
-	if (no_merge)
+	if (config->no_merge)
 		uniquify_event_name(counter);
 	else if (counter->auto_merge_stats)
 		collect_all_aliases(config, counter, cb, data);
@@ -1902,7 +1901,7 @@ static const struct option stat_options[] = {
 		    "list of cpus to monitor in system-wide"),
 	OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
 		    "disable CPU count aggregation", AGGR_NONE),
-	OPT_BOOLEAN(0, "no-merge", &no_merge, "Do not merge identical named events"),
+	OPT_BOOLEAN(0, "no-merge", &stat_config.no_merge, "Do not merge identical named events"),
 	OPT_STRING('x', "field-separator", &stat_config.csv_sep, "separator",
 		   "print counts with custom separator"),
 	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 843672214cca..0758107fe56f 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -104,6 +104,7 @@ struct perf_stat_config {
 	bool			 null_run;
 	bool			 ru_display;
 	bool			 big_num;
+	bool			 no_merge;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
-- 
cgit v1.2.3


From be54d59325314be9d4d53852cbfbeeaebc3b9239 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:49 +0200
Subject: perf stat: Propagate 'struct target' arg to sort_aggr_thread()

Propagate the 'struct target' arg to sort_aggr_thread() so that the
function does not depend on the 'perf stat' command object local
variable 'target' and can be moved out.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-41-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index c4df076f1e54..486b0cf7818d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1284,7 +1284,8 @@ static int cmp_val(const void *a, const void *b)
 static struct perf_aggr_thread_value *sort_aggr_thread(
 					struct perf_evsel *counter,
 					int nthreads, int ncpus,
-					int *ret)
+					int *ret,
+					struct target *_target)
 {
 	int cpu, thread, i = 0;
 	double uval;
@@ -1309,7 +1310,7 @@ static struct perf_aggr_thread_value *sort_aggr_thread(
 		 * Skip value 0 when enabling --per-thread globally,
 		 * otherwise too many 0 output.
 		 */
-		if (uval == 0.0 && target__has_per_thread(&target))
+		if (uval == 0.0 && target__has_per_thread(_target))
 			continue;
 
 		buf[i].counter = counter;
@@ -1330,6 +1331,7 @@ static struct perf_aggr_thread_value *sort_aggr_thread(
 }
 
 static void print_aggr_thread(struct perf_stat_config *config,
+			      struct target *_target,
 			      struct perf_evsel *counter, char *prefix)
 {
 	FILE *output = config->output;
@@ -1338,7 +1340,7 @@ static void print_aggr_thread(struct perf_stat_config *config,
 	int thread, sorted_threads, id;
 	struct perf_aggr_thread_value *buf;
 
-	buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads);
+	buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads, _target);
 	if (!buf) {
 		perror("cannot sort aggr thread");
 		return;
@@ -1754,7 +1756,7 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 		evlist__for_each_entry(evlist, counter) {
 			if (is_duration_time(counter))
 				continue;
-			print_aggr_thread(config, counter, prefix);
+			print_aggr_thread(config, _target, counter, prefix);
 		}
 		break;
 	case AGGR_GLOBAL:
-- 
cgit v1.2.3


From 54ac0b1bd25cbdeda226b32a0459e09de46157b3 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:50 +0200
Subject: perf stat: Move 'walltime_*' data to 'struct perf_stat_config'

Move the static variables 'walltime_*' to 'struct perf_stat_config', so
that it can be passed around and used outside 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-42-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 22 ++++++++++------------
 tools/perf/util/stat.h    |  2 ++
 2 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 486b0cf7818d..8a4979748cbb 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -158,13 +158,11 @@ static const char		*post_cmd			= NULL;
 static bool			sync_run			= false;
 static bool			forever				= false;
 static bool			force_metric_only		= false;
-static bool			walltime_run_table		= false;
 static struct timespec		ref_time;
 static bool			append_file;
 static bool			interval_count;
 static const char		*output_name;
 static int			output_fd;
-static u64			*walltime_run;
 
 struct perf_stat {
 	bool			 record;
@@ -604,8 +602,8 @@ try_again:
 
 	t1 = rdclock();
 
-	if (walltime_run_table)
-		walltime_run[run_idx] = t1 - t0;
+	if (stat_config.walltime_run_table)
+		stat_config.walltime_run[run_idx] = t1 - t0;
 
 	update_stats(&walltime_nsecs_stats, t1 - t0);
 
@@ -1646,7 +1644,7 @@ static void print_table(struct perf_stat_config *config,
 	fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
 
 	for (idx = 0; idx < config->run_count; idx++) {
-		double run = (double) walltime_run[idx] / NSEC_PER_SEC;
+		double run = (double) config->walltime_run[idx] / NSEC_PER_SEC;
 		int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
 
 		fprintf(output, " %17.*f (%+.*f) ",
@@ -1694,7 +1692,7 @@ static void print_footer(struct perf_stat_config *config)
 		 */
 		int precision = get_precision(sd) + 2;
 
-		if (walltime_run_table)
+		if (config->walltime_run_table)
 			print_table(config, output, precision, avg);
 
 		fprintf(output, " %17.*f +- %.*f seconds time elapsed",
@@ -1888,7 +1886,7 @@ static const struct option stat_options[] = {
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_INTEGER('r', "repeat", &stat_config.run_count,
 		    "repeat command and print average + stddev (max: 100, forever: 0)"),
-	OPT_BOOLEAN(0, "table", &walltime_run_table,
+	OPT_BOOLEAN(0, "table", &stat_config.walltime_run_table,
 		    "display details about each run (only with -r option)"),
 	OPT_BOOLEAN('n', "null", &stat_config.null_run,
 		    "null run - dont start any counters"),
@@ -2802,7 +2800,7 @@ int cmd_stat(int argc, const char **argv)
 		goto out;
 	}
 
-	if (walltime_run_table && stat_config.run_count <= 1) {
+	if (stat_config.walltime_run_table && stat_config.run_count <= 1) {
 		fprintf(stderr, "--table is only supported with -r\n");
 		parse_options_usage(stat_usage, stat_options, "r", 1);
 		parse_options_usage(NULL, stat_options, "table", 0);
@@ -2870,9 +2868,9 @@ int cmd_stat(int argc, const char **argv)
 		stat_config.run_count = 1;
 	}
 
-	if (walltime_run_table) {
-		walltime_run = zalloc(stat_config.run_count * sizeof(walltime_run[0]));
-		if (!walltime_run) {
+	if (stat_config.walltime_run_table) {
+		stat_config.walltime_run = zalloc(stat_config.run_count * sizeof(stat_config.walltime_run[0]));
+		if (!stat_config.walltime_run) {
 			pr_err("failed to setup -r option");
 			goto out;
 		}
@@ -3052,7 +3050,7 @@ int cmd_stat(int argc, const char **argv)
 	perf_stat__exit_aggr_mode();
 	perf_evlist__free_stats(evsel_list);
 out:
-	free(walltime_run);
+	free(stat_config.walltime_run);
 
 	if (smi_cost && smi_reset)
 		sysfs__write_int(FREEZE_ON_SMI_PATH, 0);
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 0758107fe56f..5193cbf6e4c6 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -105,6 +105,7 @@ struct perf_stat_config {
 	bool			 ru_display;
 	bool			 big_num;
 	bool			 no_merge;
+	bool			 walltime_run_table;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
@@ -123,6 +124,7 @@ struct perf_stat_config {
 	struct cpu_map		*aggr_map;
 	aggr_get_id_t		 aggr_get_id;
 	struct cpu_map		*cpus_aggr_map;
+	u64			*walltime_run;
 };
 
 void update_stats(struct stats *stats, u64 val);
-- 
cgit v1.2.3


From d0192fdba09a8901db133fe5a1fcd22d40fcf545 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:51 +0200
Subject: perf stat: Move 'metric_events' to 'struct perf_stat_config'

Move the static variable 'metric_events' to 'struct perf_stat_config',
so that it can be passed around and used outside 'perf stat' command.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-43-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 10 ++++------
 tools/perf/util/stat.h    |  1 +
 2 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 8a4979748cbb..f4ddedc8619b 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -137,8 +137,6 @@ static const char *smi_cost_attrs = {
 
 static struct perf_evlist	*evsel_list;
 
-static struct rblist		 metric_events;
-
 static struct target target = {
 	.uid	= UINT_MAX,
 };
@@ -1082,7 +1080,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 
 	perf_stat__print_shadow_stats(config, counter, uval,
 				first_shadow_cpu(config, counter, id),
-				&out, &metric_events, st);
+				&out, &config->metric_events, st);
 	if (!config->csv_output && !config->metric_only) {
 		print_noise(config, counter, noise);
 		print_running(config, run, ena);
@@ -1533,7 +1531,7 @@ static void print_metric_headers(struct perf_stat_config *config,
 		perf_stat__print_shadow_stats(config, counter, 0,
 					      0,
 					      &out,
-					      &metric_events,
+					      &config->metric_events,
 					      &rt_stat);
 	}
 	fputc('\n', config->output);
@@ -1860,7 +1858,7 @@ static int parse_metric_groups(const struct option *opt,
 			       const char *str,
 			       int unset __maybe_unused)
 {
-	return metricgroup__parse_groups(opt, str, &metric_events);
+	return metricgroup__parse_groups(opt, str, &stat_config.metric_events);
 }
 
 static const struct option stat_options[] = {
@@ -2321,7 +2319,7 @@ static int add_default_attributes(void)
 			struct option opt = { .value = &evsel_list };
 
 			return metricgroup__parse_groups(&opt, "transaction",
-							 &metric_events);
+							 &stat_config.metric_events);
 		}
 
 		if (pmu_have_event("cpu", "cycles-ct") &&
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 5193cbf6e4c6..8d3354e21e19 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -125,6 +125,7 @@ struct perf_stat_config {
 	aggr_get_id_t		 aggr_get_id;
 	struct cpu_map		*cpus_aggr_map;
 	u64			*walltime_run;
+	struct rblist		 metric_events;
 };
 
 void update_stats(struct stats *stats, u64 val);
-- 
cgit v1.2.3


From 088519f318be3a41d1afe8d628c4a1eb5a50b4c0 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 30 Aug 2018 08:32:52 +0200
Subject: perf stat: Move the display functions to stat-display.c

Move perf_evlist__print_counters() with all its dependency functions to
the stat-display.c object.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180830063252.23729-44-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c      | 1150 ---------------------------------------
 tools/perf/util/Build          |    1 +
 tools/perf/util/stat-display.c | 1166 ++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/stat.h         |    6 +
 4 files changed, 1173 insertions(+), 1150 deletions(-)
 create mode 100644 tools/perf/util/stat-display.c

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f4ddedc8619b..0b0e3961d511 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -88,8 +88,6 @@
 #include "sane_ctype.h"
 
 #define DEFAULT_SEPARATOR	" "
-#define CNTR_NOT_SUPPORTED	"<not supported>"
-#define CNTR_NOT_COUNTED	"<not counted>"
 #define FREEZE_ON_SMI_PATH	"devices/cpu/freeze_on_smi"
 
 static void print_counters(struct timespec *ts, int argc, const char **argv);
@@ -189,11 +187,6 @@ static struct perf_stat_config stat_config = {
 	.big_num		= true,
 };
 
-static bool is_duration_time(struct perf_evsel *evsel)
-{
-	return !strcmp(evsel->name, "duration_time");
-}
-
 static inline void diff_timespec(struct timespec *r, struct timespec *a,
 				 struct timespec *b)
 {
@@ -643,1149 +636,6 @@ static int run_perf_stat(int argc, const char **argv, int run_idx)
 	return ret;
 }
 
-static void print_running(struct perf_stat_config *config,
-			  u64 run, u64 ena)
-{
-	if (config->csv_output) {
-		fprintf(config->output, "%s%" PRIu64 "%s%.2f",
-					config->csv_sep,
-					run,
-					config->csv_sep,
-					ena ? 100.0 * run / ena : 100.0);
-	} else if (run != ena) {
-		fprintf(config->output, "  (%.2f%%)", 100.0 * run / ena);
-	}
-}
-
-static void print_noise_pct(struct perf_stat_config *config,
-			    double total, double avg)
-{
-	double pct = rel_stddev_stats(total, avg);
-
-	if (config->csv_output)
-		fprintf(config->output, "%s%.2f%%", config->csv_sep, pct);
-	else if (pct)
-		fprintf(config->output, "  ( +-%6.2f%% )", pct);
-}
-
-static void print_noise(struct perf_stat_config *config,
-			struct perf_evsel *evsel, double avg)
-{
-	struct perf_stat_evsel *ps;
-
-	if (config->run_count == 1)
-		return;
-
-	ps = evsel->stats;
-	print_noise_pct(config, stddev_stats(&ps->res_stats[0]), avg);
-}
-
-static void aggr_printout(struct perf_stat_config *config,
-			  struct perf_evsel *evsel, int id, int nr)
-{
-	switch (config->aggr_mode) {
-	case AGGR_CORE:
-		fprintf(config->output, "S%d-C%*d%s%*d%s",
-			cpu_map__id_to_socket(id),
-			config->csv_output ? 0 : -8,
-			cpu_map__id_to_cpu(id),
-			config->csv_sep,
-			config->csv_output ? 0 : 4,
-			nr,
-			config->csv_sep);
-		break;
-	case AGGR_SOCKET:
-		fprintf(config->output, "S%*d%s%*d%s",
-			config->csv_output ? 0 : -5,
-			id,
-			config->csv_sep,
-			config->csv_output ? 0 : 4,
-			nr,
-			config->csv_sep);
-			break;
-	case AGGR_NONE:
-		fprintf(config->output, "CPU%*d%s",
-			config->csv_output ? 0 : -4,
-			perf_evsel__cpus(evsel)->map[id], config->csv_sep);
-		break;
-	case AGGR_THREAD:
-		fprintf(config->output, "%*s-%*d%s",
-			config->csv_output ? 0 : 16,
-			thread_map__comm(evsel->threads, id),
-			config->csv_output ? 0 : -8,
-			thread_map__pid(evsel->threads, id),
-			config->csv_sep);
-		break;
-	case AGGR_GLOBAL:
-	case AGGR_UNSET:
-	default:
-		break;
-	}
-}
-
-struct outstate {
-	FILE *fh;
-	bool newline;
-	const char *prefix;
-	int  nfields;
-	int  id, nr;
-	struct perf_evsel *evsel;
-};
-
-#define METRIC_LEN  35
-
-static void new_line_std(struct perf_stat_config *config __maybe_unused,
-			 void *ctx)
-{
-	struct outstate *os = ctx;
-
-	os->newline = true;
-}
-
-static void do_new_line_std(struct perf_stat_config *config,
-			    struct outstate *os)
-{
-	fputc('\n', os->fh);
-	fputs(os->prefix, os->fh);
-	aggr_printout(config, os->evsel, os->id, os->nr);
-	if (config->aggr_mode == AGGR_NONE)
-		fprintf(os->fh, "        ");
-	fprintf(os->fh, "                                                 ");
-}
-
-static void print_metric_std(struct perf_stat_config *config,
-			     void *ctx, const char *color, const char *fmt,
-			     const char *unit, double val)
-{
-	struct outstate *os = ctx;
-	FILE *out = os->fh;
-	int n;
-	bool newline = os->newline;
-
-	os->newline = false;
-
-	if (unit == NULL || fmt == NULL) {
-		fprintf(out, "%-*s", METRIC_LEN, "");
-		return;
-	}
-
-	if (newline)
-		do_new_line_std(config, os);
-
-	n = fprintf(out, " # ");
-	if (color)
-		n += color_fprintf(out, color, fmt, val);
-	else
-		n += fprintf(out, fmt, val);
-	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
-}
-
-static void new_line_csv(struct perf_stat_config *config, void *ctx)
-{
-	struct outstate *os = ctx;
-	int i;
-
-	fputc('\n', os->fh);
-	if (os->prefix)
-		fprintf(os->fh, "%s%s", os->prefix, config->csv_sep);
-	aggr_printout(config, os->evsel, os->id, os->nr);
-	for (i = 0; i < os->nfields; i++)
-		fputs(config->csv_sep, os->fh);
-}
-
-static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
-			     void *ctx,
-			     const char *color __maybe_unused,
-			     const char *fmt, const char *unit, double val)
-{
-	struct outstate *os = ctx;
-	FILE *out = os->fh;
-	char buf[64], *vals, *ends;
-
-	if (unit == NULL || fmt == NULL) {
-		fprintf(out, "%s%s", config->csv_sep, config->csv_sep);
-		return;
-	}
-	snprintf(buf, sizeof(buf), fmt, val);
-	ends = vals = ltrim(buf);
-	while (isdigit(*ends) || *ends == '.')
-		ends++;
-	*ends = 0;
-	while (isspace(*unit))
-		unit++;
-	fprintf(out, "%s%s%s%s", config->csv_sep, vals, config->csv_sep, unit);
-}
-
-/* Filter out some columns that don't work well in metrics only mode */
-
-static bool valid_only_metric(const char *unit)
-{
-	if (!unit)
-		return false;
-	if (strstr(unit, "/sec") ||
-	    strstr(unit, "hz") ||
-	    strstr(unit, "Hz") ||
-	    strstr(unit, "CPUs utilized"))
-		return false;
-	return true;
-}
-
-static const char *fixunit(char *buf, struct perf_evsel *evsel,
-			   const char *unit)
-{
-	if (!strncmp(unit, "of all", 6)) {
-		snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
-			 unit);
-		return buf;
-	}
-	return unit;
-}
-
-static void print_metric_only(struct perf_stat_config *config,
-			      void *ctx, const char *color, const char *fmt,
-			      const char *unit, double val)
-{
-	struct outstate *os = ctx;
-	FILE *out = os->fh;
-	char buf[1024], str[1024];
-	unsigned mlen = config->metric_only_len;
-
-	if (!valid_only_metric(unit))
-		return;
-	unit = fixunit(buf, os->evsel, unit);
-	if (mlen < strlen(unit))
-		mlen = strlen(unit) + 1;
-
-	if (color)
-		mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
-
-	color_snprintf(str, sizeof(str), color ?: "", fmt, val);
-	fprintf(out, "%*s ", mlen, str);
-}
-
-static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused,
-				  void *ctx, const char *color __maybe_unused,
-				  const char *fmt,
-				  const char *unit, double val)
-{
-	struct outstate *os = ctx;
-	FILE *out = os->fh;
-	char buf[64], *vals, *ends;
-	char tbuf[1024];
-
-	if (!valid_only_metric(unit))
-		return;
-	unit = fixunit(tbuf, os->evsel, unit);
-	snprintf(buf, sizeof buf, fmt, val);
-	ends = vals = ltrim(buf);
-	while (isdigit(*ends) || *ends == '.')
-		ends++;
-	*ends = 0;
-	fprintf(out, "%s%s", vals, config->csv_sep);
-}
-
-static void new_line_metric(struct perf_stat_config *config __maybe_unused,
-			    void *ctx __maybe_unused)
-{
-}
-
-static void print_metric_header(struct perf_stat_config *config,
-				void *ctx, const char *color __maybe_unused,
-				const char *fmt __maybe_unused,
-				const char *unit, double val __maybe_unused)
-{
-	struct outstate *os = ctx;
-	char tbuf[1024];
-
-	if (!valid_only_metric(unit))
-		return;
-	unit = fixunit(tbuf, os->evsel, unit);
-	if (config->csv_output)
-		fprintf(os->fh, "%s%s", unit, config->csv_sep);
-	else
-		fprintf(os->fh, "%*s ", config->metric_only_len, unit);
-}
-
-static int first_shadow_cpu(struct perf_stat_config *config,
-			    struct perf_evsel *evsel, int id)
-{
-	struct perf_evlist *evlist = evsel->evlist;
-	int i;
-
-	if (!config->aggr_get_id)
-		return 0;
-
-	if (config->aggr_mode == AGGR_NONE)
-		return id;
-
-	if (config->aggr_mode == AGGR_GLOBAL)
-		return 0;
-
-	for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
-		int cpu2 = perf_evsel__cpus(evsel)->map[i];
-
-		if (config->aggr_get_id(config, evlist->cpus, cpu2) == id)
-			return cpu2;
-	}
-	return 0;
-}
-
-static void abs_printout(struct perf_stat_config *config,
-			 int id, int nr, struct perf_evsel *evsel, double avg)
-{
-	FILE *output = config->output;
-	double sc =  evsel->scale;
-	const char *fmt;
-
-	if (config->csv_output) {
-		fmt = floor(sc) != sc ?  "%.2f%s" : "%.0f%s";
-	} else {
-		if (config->big_num)
-			fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
-		else
-			fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
-	}
-
-	aggr_printout(config, evsel, id, nr);
-
-	fprintf(output, fmt, avg, config->csv_sep);
-
-	if (evsel->unit)
-		fprintf(output, "%-*s%s",
-			config->csv_output ? 0 : config->unit_width,
-			evsel->unit, config->csv_sep);
-
-	fprintf(output, "%-*s", config->csv_output ? 0 : 25, perf_evsel__name(evsel));
-
-	if (evsel->cgrp)
-		fprintf(output, "%s%s", config->csv_sep, evsel->cgrp->name);
-}
-
-static bool is_mixed_hw_group(struct perf_evsel *counter)
-{
-	struct perf_evlist *evlist = counter->evlist;
-	u32 pmu_type = counter->attr.type;
-	struct perf_evsel *pos;
-
-	if (counter->nr_members < 2)
-		return false;
-
-	evlist__for_each_entry(evlist, pos) {
-		/* software events can be part of any hardware group */
-		if (pos->attr.type == PERF_TYPE_SOFTWARE)
-			continue;
-		if (pmu_type == PERF_TYPE_SOFTWARE) {
-			pmu_type = pos->attr.type;
-			continue;
-		}
-		if (pmu_type != pos->attr.type)
-			return true;
-	}
-
-	return false;
-}
-
-static void printout(struct perf_stat_config *config, int id, int nr,
-		     struct perf_evsel *counter, double uval,
-		     char *prefix, u64 run, u64 ena, double noise,
-		     struct runtime_stat *st)
-{
-	struct perf_stat_output_ctx out;
-	struct outstate os = {
-		.fh = config->output,
-		.prefix = prefix ? prefix : "",
-		.id = id,
-		.nr = nr,
-		.evsel = counter,
-	};
-	print_metric_t pm = print_metric_std;
-	new_line_t nl;
-
-	if (config->metric_only) {
-		nl = new_line_metric;
-		if (config->csv_output)
-			pm = print_metric_only_csv;
-		else
-			pm = print_metric_only;
-	} else
-		nl = new_line_std;
-
-	if (config->csv_output && !config->metric_only) {
-		static int aggr_fields[] = {
-			[AGGR_GLOBAL] = 0,
-			[AGGR_THREAD] = 1,
-			[AGGR_NONE] = 1,
-			[AGGR_SOCKET] = 2,
-			[AGGR_CORE] = 2,
-		};
-
-		pm = print_metric_csv;
-		nl = new_line_csv;
-		os.nfields = 3;
-		os.nfields += aggr_fields[config->aggr_mode];
-		if (counter->cgrp)
-			os.nfields++;
-	}
-	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
-		if (config->metric_only) {
-			pm(config, &os, NULL, "", "", 0);
-			return;
-		}
-		aggr_printout(config, counter, id, nr);
-
-		fprintf(config->output, "%*s%s",
-			config->csv_output ? 0 : 18,
-			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-			config->csv_sep);
-
-		if (counter->supported) {
-			config->print_free_counters_hint = 1;
-			if (is_mixed_hw_group(counter))
-				config->print_mixed_hw_group_error = 1;
-		}
-
-		fprintf(config->output, "%-*s%s",
-			config->csv_output ? 0 : config->unit_width,
-			counter->unit, config->csv_sep);
-
-		fprintf(config->output, "%*s",
-			config->csv_output ? 0 : -25,
-			perf_evsel__name(counter));
-
-		if (counter->cgrp)
-			fprintf(config->output, "%s%s",
-				config->csv_sep, counter->cgrp->name);
-
-		if (!config->csv_output)
-			pm(config, &os, NULL, NULL, "", 0);
-		print_noise(config, counter, noise);
-		print_running(config, run, ena);
-		if (config->csv_output)
-			pm(config, &os, NULL, NULL, "", 0);
-		return;
-	}
-
-	if (!config->metric_only)
-		abs_printout(config, id, nr, counter, uval);
-
-	out.print_metric = pm;
-	out.new_line = nl;
-	out.ctx = &os;
-	out.force_header = false;
-
-	if (config->csv_output && !config->metric_only) {
-		print_noise(config, counter, noise);
-		print_running(config, run, ena);
-	}
-
-	perf_stat__print_shadow_stats(config, counter, uval,
-				first_shadow_cpu(config, counter, id),
-				&out, &config->metric_events, st);
-	if (!config->csv_output && !config->metric_only) {
-		print_noise(config, counter, noise);
-		print_running(config, run, ena);
-	}
-}
-
-static void aggr_update_shadow(struct perf_stat_config *config,
-			       struct perf_evlist *evlist)
-{
-	int cpu, s2, id, s;
-	u64 val;
-	struct perf_evsel *counter;
-
-	for (s = 0; s < config->aggr_map->nr; s++) {
-		id = config->aggr_map->map[s];
-		evlist__for_each_entry(evlist, counter) {
-			val = 0;
-			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-				s2 = config->aggr_get_id(config, evlist->cpus, cpu);
-				if (s2 != id)
-					continue;
-				val += perf_counts(counter->counts, cpu, 0)->val;
-			}
-			perf_stat__update_shadow_stats(counter, val,
-					first_shadow_cpu(config, counter, id),
-					&rt_stat);
-		}
-	}
-}
-
-static void uniquify_event_name(struct perf_evsel *counter)
-{
-	char *new_name;
-	char *config;
-
-	if (counter->uniquified_name ||
-	    !counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
-					   strlen(counter->pmu_name)))
-		return;
-
-	config = strchr(counter->name, '/');
-	if (config) {
-		if (asprintf(&new_name,
-			     "%s%s", counter->pmu_name, config) > 0) {
-			free(counter->name);
-			counter->name = new_name;
-		}
-	} else {
-		if (asprintf(&new_name,
-			     "%s [%s]", counter->name, counter->pmu_name) > 0) {
-			free(counter->name);
-			counter->name = new_name;
-		}
-	}
-
-	counter->uniquified_name = true;
-}
-
-static void collect_all_aliases(struct perf_stat_config *config, struct perf_evsel *counter,
-			    void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data,
-				       bool first),
-			    void *data)
-{
-	struct perf_evlist *evlist = counter->evlist;
-	struct perf_evsel *alias;
-
-	alias = list_prepare_entry(counter, &(evlist->entries), node);
-	list_for_each_entry_continue (alias, &evlist->entries, node) {
-		if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
-		    alias->scale != counter->scale ||
-		    alias->cgrp != counter->cgrp ||
-		    strcmp(alias->unit, counter->unit) ||
-		    perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
-			break;
-		alias->merged_stat = true;
-		cb(config, alias, data, false);
-	}
-}
-
-static bool collect_data(struct perf_stat_config *config, struct perf_evsel *counter,
-			    void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data,
-				       bool first),
-			    void *data)
-{
-	if (counter->merged_stat)
-		return false;
-	cb(config, counter, data, true);
-	if (config->no_merge)
-		uniquify_event_name(counter);
-	else if (counter->auto_merge_stats)
-		collect_all_aliases(config, counter, cb, data);
-	return true;
-}
-
-struct aggr_data {
-	u64 ena, run, val;
-	int id;
-	int nr;
-	int cpu;
-};
-
-static void aggr_cb(struct perf_stat_config *config,
-		    struct perf_evsel *counter, void *data, bool first)
-{
-	struct aggr_data *ad = data;
-	int cpu, s2;
-
-	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		struct perf_counts_values *counts;
-
-		s2 = config->aggr_get_id(config, perf_evsel__cpus(counter), cpu);
-		if (s2 != ad->id)
-			continue;
-		if (first)
-			ad->nr++;
-		counts = perf_counts(counter->counts, cpu, 0);
-		/*
-		 * When any result is bad, make them all to give
-		 * consistent output in interval mode.
-		 */
-		if (counts->ena == 0 || counts->run == 0 ||
-		    counter->counts->scaled == -1) {
-			ad->ena = 0;
-			ad->run = 0;
-			break;
-		}
-		ad->val += counts->val;
-		ad->ena += counts->ena;
-		ad->run += counts->run;
-	}
-}
-
-static void print_aggr(struct perf_stat_config *config,
-		       struct perf_evlist *evlist,
-		       char *prefix)
-{
-	bool metric_only = config->metric_only;
-	FILE *output = config->output;
-	struct perf_evsel *counter;
-	int s, id, nr;
-	double uval;
-	u64 ena, run, val;
-	bool first;
-
-	if (!(config->aggr_map || config->aggr_get_id))
-		return;
-
-	aggr_update_shadow(config, evlist);
-
-	/*
-	 * With metric_only everything is on a single line.
-	 * Without each counter has its own line.
-	 */
-	for (s = 0; s < config->aggr_map->nr; s++) {
-		struct aggr_data ad;
-		if (prefix && metric_only)
-			fprintf(output, "%s", prefix);
-
-		ad.id = id = config->aggr_map->map[s];
-		first = true;
-		evlist__for_each_entry(evlist, counter) {
-			if (is_duration_time(counter))
-				continue;
-
-			ad.val = ad.ena = ad.run = 0;
-			ad.nr = 0;
-			if (!collect_data(config, counter, aggr_cb, &ad))
-				continue;
-			nr = ad.nr;
-			ena = ad.ena;
-			run = ad.run;
-			val = ad.val;
-			if (first && metric_only) {
-				first = false;
-				aggr_printout(config, counter, id, nr);
-			}
-			if (prefix && !metric_only)
-				fprintf(output, "%s", prefix);
-
-			uval = val * counter->scale;
-			printout(config, id, nr, counter, uval, prefix,
-				 run, ena, 1.0, &rt_stat);
-			if (!metric_only)
-				fputc('\n', output);
-		}
-		if (metric_only)
-			fputc('\n', output);
-	}
-}
-
-static int cmp_val(const void *a, const void *b)
-{
-	return ((struct perf_aggr_thread_value *)b)->val -
-		((struct perf_aggr_thread_value *)a)->val;
-}
-
-static struct perf_aggr_thread_value *sort_aggr_thread(
-					struct perf_evsel *counter,
-					int nthreads, int ncpus,
-					int *ret,
-					struct target *_target)
-{
-	int cpu, thread, i = 0;
-	double uval;
-	struct perf_aggr_thread_value *buf;
-
-	buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value));
-	if (!buf)
-		return NULL;
-
-	for (thread = 0; thread < nthreads; thread++) {
-		u64 ena = 0, run = 0, val = 0;
-
-		for (cpu = 0; cpu < ncpus; cpu++) {
-			val += perf_counts(counter->counts, cpu, thread)->val;
-			ena += perf_counts(counter->counts, cpu, thread)->ena;
-			run += perf_counts(counter->counts, cpu, thread)->run;
-		}
-
-		uval = val * counter->scale;
-
-		/*
-		 * Skip value 0 when enabling --per-thread globally,
-		 * otherwise too many 0 output.
-		 */
-		if (uval == 0.0 && target__has_per_thread(_target))
-			continue;
-
-		buf[i].counter = counter;
-		buf[i].id = thread;
-		buf[i].uval = uval;
-		buf[i].val = val;
-		buf[i].run = run;
-		buf[i].ena = ena;
-		i++;
-	}
-
-	qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val);
-
-	if (ret)
-		*ret = i;
-
-	return buf;
-}
-
-static void print_aggr_thread(struct perf_stat_config *config,
-			      struct target *_target,
-			      struct perf_evsel *counter, char *prefix)
-{
-	FILE *output = config->output;
-	int nthreads = thread_map__nr(counter->threads);
-	int ncpus = cpu_map__nr(counter->cpus);
-	int thread, sorted_threads, id;
-	struct perf_aggr_thread_value *buf;
-
-	buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads, _target);
-	if (!buf) {
-		perror("cannot sort aggr thread");
-		return;
-	}
-
-	for (thread = 0; thread < sorted_threads; thread++) {
-		if (prefix)
-			fprintf(output, "%s", prefix);
-
-		id = buf[thread].id;
-		if (config->stats)
-			printout(config, id, 0, buf[thread].counter, buf[thread].uval,
-				 prefix, buf[thread].run, buf[thread].ena, 1.0,
-				 &config->stats[id]);
-		else
-			printout(config, id, 0, buf[thread].counter, buf[thread].uval,
-				 prefix, buf[thread].run, buf[thread].ena, 1.0,
-				 &rt_stat);
-		fputc('\n', output);
-	}
-
-	free(buf);
-}
-
-struct caggr_data {
-	double avg, avg_enabled, avg_running;
-};
-
-static void counter_aggr_cb(struct perf_stat_config *config __maybe_unused,
-			    struct perf_evsel *counter, void *data,
-			    bool first __maybe_unused)
-{
-	struct caggr_data *cd = data;
-	struct perf_stat_evsel *ps = counter->stats;
-
-	cd->avg += avg_stats(&ps->res_stats[0]);
-	cd->avg_enabled += avg_stats(&ps->res_stats[1]);
-	cd->avg_running += avg_stats(&ps->res_stats[2]);
-}
-
-/*
- * Print out the results of a single counter:
- * aggregated counts in system-wide mode
- */
-static void print_counter_aggr(struct perf_stat_config *config,
-			       struct perf_evsel *counter, char *prefix)
-{
-	bool metric_only = config->metric_only;
-	FILE *output = config->output;
-	double uval;
-	struct caggr_data cd = { .avg = 0.0 };
-
-	if (!collect_data(config, counter, counter_aggr_cb, &cd))
-		return;
-
-	if (prefix && !metric_only)
-		fprintf(output, "%s", prefix);
-
-	uval = cd.avg * counter->scale;
-	printout(config, -1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
-		 cd.avg, &rt_stat);
-	if (!metric_only)
-		fprintf(output, "\n");
-}
-
-static void counter_cb(struct perf_stat_config *config __maybe_unused,
-		       struct perf_evsel *counter, void *data,
-		       bool first __maybe_unused)
-{
-	struct aggr_data *ad = data;
-
-	ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
-	ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
-	ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
-}
-
-/*
- * Print out the results of a single counter:
- * does not use aggregated count in system-wide
- */
-static void print_counter(struct perf_stat_config *config,
-			  struct perf_evsel *counter, char *prefix)
-{
-	FILE *output = config->output;
-	u64 ena, run, val;
-	double uval;
-	int cpu;
-
-	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		struct aggr_data ad = { .cpu = cpu };
-
-		if (!collect_data(config, counter, counter_cb, &ad))
-			return;
-		val = ad.val;
-		ena = ad.ena;
-		run = ad.run;
-
-		if (prefix)
-			fprintf(output, "%s", prefix);
-
-		uval = val * counter->scale;
-		printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
-			 &rt_stat);
-
-		fputc('\n', output);
-	}
-}
-
-static void print_no_aggr_metric(struct perf_stat_config *config,
-				 struct perf_evlist *evlist,
-				 char *prefix)
-{
-	int cpu;
-	int nrcpus = 0;
-	struct perf_evsel *counter;
-	u64 ena, run, val;
-	double uval;
-
-	nrcpus = evlist->cpus->nr;
-	for (cpu = 0; cpu < nrcpus; cpu++) {
-		bool first = true;
-
-		if (prefix)
-			fputs(prefix, config->output);
-		evlist__for_each_entry(evlist, counter) {
-			if (is_duration_time(counter))
-				continue;
-			if (first) {
-				aggr_printout(config, counter, cpu, 0);
-				first = false;
-			}
-			val = perf_counts(counter->counts, cpu, 0)->val;
-			ena = perf_counts(counter->counts, cpu, 0)->ena;
-			run = perf_counts(counter->counts, cpu, 0)->run;
-
-			uval = val * counter->scale;
-			printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
-				 &rt_stat);
-		}
-		fputc('\n', config->output);
-	}
-}
-
-static int aggr_header_lens[] = {
-	[AGGR_CORE] = 18,
-	[AGGR_SOCKET] = 12,
-	[AGGR_NONE] = 6,
-	[AGGR_THREAD] = 24,
-	[AGGR_GLOBAL] = 0,
-};
-
-static const char *aggr_header_csv[] = {
-	[AGGR_CORE] 	= 	"core,cpus,",
-	[AGGR_SOCKET] 	= 	"socket,cpus",
-	[AGGR_NONE] 	= 	"cpu,",
-	[AGGR_THREAD] 	= 	"comm-pid,",
-	[AGGR_GLOBAL] 	=	""
-};
-
-static void print_metric_headers(struct perf_stat_config *config,
-				 struct perf_evlist *evlist,
-				 const char *prefix, bool no_indent)
-{
-	struct perf_stat_output_ctx out;
-	struct perf_evsel *counter;
-	struct outstate os = {
-		.fh = config->output
-	};
-
-	if (prefix)
-		fprintf(config->output, "%s", prefix);
-
-	if (!config->csv_output && !no_indent)
-		fprintf(config->output, "%*s",
-			aggr_header_lens[config->aggr_mode], "");
-	if (config->csv_output) {
-		if (config->interval)
-			fputs("time,", config->output);
-		fputs(aggr_header_csv[config->aggr_mode], config->output);
-	}
-
-	/* Print metrics headers only */
-	evlist__for_each_entry(evlist, counter) {
-		if (is_duration_time(counter))
-			continue;
-		os.evsel = counter;
-		out.ctx = &os;
-		out.print_metric = print_metric_header;
-		out.new_line = new_line_metric;
-		out.force_header = true;
-		os.evsel = counter;
-		perf_stat__print_shadow_stats(config, counter, 0,
-					      0,
-					      &out,
-					      &config->metric_events,
-					      &rt_stat);
-	}
-	fputc('\n', config->output);
-}
-
-static void print_interval(struct perf_stat_config *config,
-			   struct perf_evlist *evlist,
-			   char *prefix, struct timespec *ts)
-{
-	bool metric_only = config->metric_only;
-	unsigned int unit_width = config->unit_width;
-	FILE *output = config->output;
-	static int num_print_interval;
-
-	if (config->interval_clear)
-		puts(CONSOLE_CLEAR);
-
-	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep);
-
-	if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) {
-		switch (config->aggr_mode) {
-		case AGGR_SOCKET:
-			fprintf(output, "#           time socket cpus");
-			if (!metric_only)
-				fprintf(output, "             counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_CORE:
-			fprintf(output, "#           time core         cpus");
-			if (!metric_only)
-				fprintf(output, "             counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_NONE:
-			fprintf(output, "#           time CPU    ");
-			if (!metric_only)
-				fprintf(output, "                counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_THREAD:
-			fprintf(output, "#           time             comm-pid");
-			if (!metric_only)
-				fprintf(output, "                  counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_GLOBAL:
-		default:
-			fprintf(output, "#           time");
-			if (!metric_only)
-				fprintf(output, "             counts %*s events\n", unit_width, "unit");
-		case AGGR_UNSET:
-			break;
-		}
-	}
-
-	if ((num_print_interval == 0 || config->interval_clear) && metric_only)
-		print_metric_headers(config, evlist, " ", true);
-	if (++num_print_interval == 25)
-		num_print_interval = 0;
-}
-
-static void print_header(struct perf_stat_config *config,
-			 struct target *_target,
-			 int argc, const char **argv)
-{
-	FILE *output = config->output;
-	int i;
-
-	fflush(stdout);
-
-	if (!config->csv_output) {
-		fprintf(output, "\n");
-		fprintf(output, " Performance counter stats for ");
-		if (_target->system_wide)
-			fprintf(output, "\'system wide");
-		else if (_target->cpu_list)
-			fprintf(output, "\'CPU(s) %s", _target->cpu_list);
-		else if (!target__has_task(_target)) {
-			fprintf(output, "\'%s", argv ? argv[0] : "pipe");
-			for (i = 1; argv && (i < argc); i++)
-				fprintf(output, " %s", argv[i]);
-		} else if (_target->pid)
-			fprintf(output, "process id \'%s", _target->pid);
-		else
-			fprintf(output, "thread id \'%s", _target->tid);
-
-		fprintf(output, "\'");
-		if (config->run_count > 1)
-			fprintf(output, " (%d runs)", config->run_count);
-		fprintf(output, ":\n\n");
-	}
-}
-
-static int get_precision(double num)
-{
-	if (num > 1)
-		return 0;
-
-	return lround(ceil(-log10(num)));
-}
-
-static void print_table(struct perf_stat_config *config,
-			FILE *output, int precision, double avg)
-{
-	char tmp[64];
-	int idx, indent = 0;
-
-	scnprintf(tmp, 64, " %17.*f", precision, avg);
-	while (tmp[indent] == ' ')
-		indent++;
-
-	fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
-
-	for (idx = 0; idx < config->run_count; idx++) {
-		double run = (double) config->walltime_run[idx] / NSEC_PER_SEC;
-		int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
-
-		fprintf(output, " %17.*f (%+.*f) ",
-			precision, run, precision, run - avg);
-
-		for (h = 0; h < n; h++)
-			fprintf(output, "#");
-
-		fprintf(output, "\n");
-	}
-
-	fprintf(output, "\n%*s# Final result:\n", indent, "");
-}
-
-static double timeval2double(struct timeval *t)
-{
-	return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC;
-}
-
-static void print_footer(struct perf_stat_config *config)
-{
-	double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
-	FILE *output = config->output;
-	int n;
-
-	if (!config->null_run)
-		fprintf(output, "\n");
-
-	if (config->run_count == 1) {
-		fprintf(output, " %17.9f seconds time elapsed", avg);
-
-		if (config->ru_display) {
-			double ru_utime = timeval2double(&config->ru_data.ru_utime);
-			double ru_stime = timeval2double(&config->ru_data.ru_stime);
-
-			fprintf(output, "\n\n");
-			fprintf(output, " %17.9f seconds user\n", ru_utime);
-			fprintf(output, " %17.9f seconds sys\n", ru_stime);
-		}
-	} else {
-		double sd = stddev_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
-		/*
-		 * Display at most 2 more significant
-		 * digits than the stddev inaccuracy.
-		 */
-		int precision = get_precision(sd) + 2;
-
-		if (config->walltime_run_table)
-			print_table(config, output, precision, avg);
-
-		fprintf(output, " %17.*f +- %.*f seconds time elapsed",
-			precision, avg, precision, sd);
-
-		print_noise_pct(config, sd, avg);
-	}
-	fprintf(output, "\n\n");
-
-	if (config->print_free_counters_hint &&
-	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
-	    n > 0)
-		fprintf(output,
-"Some events weren't counted. Try disabling the NMI watchdog:\n"
-"	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
-"	perf stat ...\n"
-"	echo 1 > /proc/sys/kernel/nmi_watchdog\n");
-
-	if (config->print_mixed_hw_group_error)
-		fprintf(output,
-			"The events in group usually have to be from "
-			"the same PMU. Try reorganizing the group.\n");
-}
-
-static void
-perf_evlist__print_counters(struct perf_evlist *evlist,
-			    struct perf_stat_config *config,
-			    struct target *_target,
-			    struct timespec *ts,
-			    int argc, const char **argv)
-{
-	bool metric_only = config->metric_only;
-	int interval = config->interval;
-	struct perf_evsel *counter;
-	char buf[64], *prefix = NULL;
-
-	if (interval)
-		print_interval(config, evlist, prefix = buf, ts);
-	else
-		print_header(config, _target, argc, argv);
-
-	if (metric_only) {
-		static int num_print_iv;
-
-		if (num_print_iv == 0 && !interval)
-			print_metric_headers(config, evlist, prefix, false);
-		if (num_print_iv++ == 25)
-			num_print_iv = 0;
-		if (config->aggr_mode == AGGR_GLOBAL && prefix)
-			fprintf(config->output, "%s", prefix);
-	}
-
-	switch (config->aggr_mode) {
-	case AGGR_CORE:
-	case AGGR_SOCKET:
-		print_aggr(config, evlist, prefix);
-		break;
-	case AGGR_THREAD:
-		evlist__for_each_entry(evlist, counter) {
-			if (is_duration_time(counter))
-				continue;
-			print_aggr_thread(config, _target, counter, prefix);
-		}
-		break;
-	case AGGR_GLOBAL:
-		evlist__for_each_entry(evlist, counter) {
-			if (is_duration_time(counter))
-				continue;
-			print_counter_aggr(config, counter, prefix);
-		}
-		if (metric_only)
-			fputc('\n', config->output);
-		break;
-	case AGGR_NONE:
-		if (metric_only)
-			print_no_aggr_metric(config, evlist, prefix);
-		else {
-			evlist__for_each_entry(evlist, counter) {
-				if (is_duration_time(counter))
-					continue;
-				print_counter(config, counter, prefix);
-			}
-		}
-		break;
-	case AGGR_UNSET:
-	default:
-		break;
-	}
-
-	if (!interval && !config->csv_output)
-		print_footer(config);
-
-	fflush(config->output);
-}
-
 static void print_counters(struct timespec *ts, int argc, const char **argv)
 {
 	/* Do not print anything if we record to the pipe. */
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 7efe15b9618d..ecd9f9ceda77 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -73,6 +73,7 @@ libperf-y += vdso.o
 libperf-y += counts.o
 libperf-y += stat.o
 libperf-y += stat-shadow.o
+libperf-y += stat-display.o
 libperf-y += record.o
 libperf-y += srcline.o
 libperf-y += data.o
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
new file mode 100644
index 000000000000..e7b4c44ebb62
--- /dev/null
+++ b/tools/perf/util/stat-display.c
@@ -0,0 +1,1166 @@
+#include <stdio.h>
+#include <inttypes.h>
+#include <linux/time64.h>
+#include <math.h>
+#include "evlist.h"
+#include "evsel.h"
+#include "stat.h"
+#include "top.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "string2.h"
+#include "sane_ctype.h"
+#include "cgroup.h"
+#include <math.h>
+#include <api/fs/fs.h>
+
+#define CNTR_NOT_SUPPORTED	"<not supported>"
+#define CNTR_NOT_COUNTED	"<not counted>"
+
+static bool is_duration_time(struct perf_evsel *evsel)
+{
+	return !strcmp(evsel->name, "duration_time");
+}
+
+static void print_running(struct perf_stat_config *config,
+			  u64 run, u64 ena)
+{
+	if (config->csv_output) {
+		fprintf(config->output, "%s%" PRIu64 "%s%.2f",
+					config->csv_sep,
+					run,
+					config->csv_sep,
+					ena ? 100.0 * run / ena : 100.0);
+	} else if (run != ena) {
+		fprintf(config->output, "  (%.2f%%)", 100.0 * run / ena);
+	}
+}
+
+static void print_noise_pct(struct perf_stat_config *config,
+			    double total, double avg)
+{
+	double pct = rel_stddev_stats(total, avg);
+
+	if (config->csv_output)
+		fprintf(config->output, "%s%.2f%%", config->csv_sep, pct);
+	else if (pct)
+		fprintf(config->output, "  ( +-%6.2f%% )", pct);
+}
+
+static void print_noise(struct perf_stat_config *config,
+			struct perf_evsel *evsel, double avg)
+{
+	struct perf_stat_evsel *ps;
+
+	if (config->run_count == 1)
+		return;
+
+	ps = evsel->stats;
+	print_noise_pct(config, stddev_stats(&ps->res_stats[0]), avg);
+}
+
+static void aggr_printout(struct perf_stat_config *config,
+			  struct perf_evsel *evsel, int id, int nr)
+{
+	switch (config->aggr_mode) {
+	case AGGR_CORE:
+		fprintf(config->output, "S%d-C%*d%s%*d%s",
+			cpu_map__id_to_socket(id),
+			config->csv_output ? 0 : -8,
+			cpu_map__id_to_cpu(id),
+			config->csv_sep,
+			config->csv_output ? 0 : 4,
+			nr,
+			config->csv_sep);
+		break;
+	case AGGR_SOCKET:
+		fprintf(config->output, "S%*d%s%*d%s",
+			config->csv_output ? 0 : -5,
+			id,
+			config->csv_sep,
+			config->csv_output ? 0 : 4,
+			nr,
+			config->csv_sep);
+			break;
+	case AGGR_NONE:
+		fprintf(config->output, "CPU%*d%s",
+			config->csv_output ? 0 : -4,
+			perf_evsel__cpus(evsel)->map[id], config->csv_sep);
+		break;
+	case AGGR_THREAD:
+		fprintf(config->output, "%*s-%*d%s",
+			config->csv_output ? 0 : 16,
+			thread_map__comm(evsel->threads, id),
+			config->csv_output ? 0 : -8,
+			thread_map__pid(evsel->threads, id),
+			config->csv_sep);
+		break;
+	case AGGR_GLOBAL:
+	case AGGR_UNSET:
+	default:
+		break;
+	}
+}
+
+struct outstate {
+	FILE *fh;
+	bool newline;
+	const char *prefix;
+	int  nfields;
+	int  id, nr;
+	struct perf_evsel *evsel;
+};
+
+#define METRIC_LEN  35
+
+static void new_line_std(struct perf_stat_config *config __maybe_unused,
+			 void *ctx)
+{
+	struct outstate *os = ctx;
+
+	os->newline = true;
+}
+
+static void do_new_line_std(struct perf_stat_config *config,
+			    struct outstate *os)
+{
+	fputc('\n', os->fh);
+	fputs(os->prefix, os->fh);
+	aggr_printout(config, os->evsel, os->id, os->nr);
+	if (config->aggr_mode == AGGR_NONE)
+		fprintf(os->fh, "        ");
+	fprintf(os->fh, "                                                 ");
+}
+
+static void print_metric_std(struct perf_stat_config *config,
+			     void *ctx, const char *color, const char *fmt,
+			     const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	int n;
+	bool newline = os->newline;
+
+	os->newline = false;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%-*s", METRIC_LEN, "");
+		return;
+	}
+
+	if (newline)
+		do_new_line_std(config, os);
+
+	n = fprintf(out, " # ");
+	if (color)
+		n += color_fprintf(out, color, fmt, val);
+	else
+		n += fprintf(out, fmt, val);
+	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
+}
+
+static void new_line_csv(struct perf_stat_config *config, void *ctx)
+{
+	struct outstate *os = ctx;
+	int i;
+
+	fputc('\n', os->fh);
+	if (os->prefix)
+		fprintf(os->fh, "%s%s", os->prefix, config->csv_sep);
+	aggr_printout(config, os->evsel, os->id, os->nr);
+	for (i = 0; i < os->nfields; i++)
+		fputs(config->csv_sep, os->fh);
+}
+
+static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
+			     void *ctx,
+			     const char *color __maybe_unused,
+			     const char *fmt, const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%s%s", config->csv_sep, config->csv_sep);
+		return;
+	}
+	snprintf(buf, sizeof(buf), fmt, val);
+	ends = vals = ltrim(buf);
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	while (isspace(*unit))
+		unit++;
+	fprintf(out, "%s%s%s%s", config->csv_sep, vals, config->csv_sep, unit);
+}
+
+/* Filter out some columns that don't work well in metrics only mode */
+
+static bool valid_only_metric(const char *unit)
+{
+	if (!unit)
+		return false;
+	if (strstr(unit, "/sec") ||
+	    strstr(unit, "hz") ||
+	    strstr(unit, "Hz") ||
+	    strstr(unit, "CPUs utilized"))
+		return false;
+	return true;
+}
+
+static const char *fixunit(char *buf, struct perf_evsel *evsel,
+			   const char *unit)
+{
+	if (!strncmp(unit, "of all", 6)) {
+		snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
+			 unit);
+		return buf;
+	}
+	return unit;
+}
+
+static void print_metric_only(struct perf_stat_config *config,
+			      void *ctx, const char *color, const char *fmt,
+			      const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[1024], str[1024];
+	unsigned mlen = config->metric_only_len;
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(buf, os->evsel, unit);
+	if (mlen < strlen(unit))
+		mlen = strlen(unit) + 1;
+
+	if (color)
+		mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
+
+	color_snprintf(str, sizeof(str), color ?: "", fmt, val);
+	fprintf(out, "%*s ", mlen, str);
+}
+
+static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused,
+				  void *ctx, const char *color __maybe_unused,
+				  const char *fmt,
+				  const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	snprintf(buf, sizeof buf, fmt, val);
+	ends = vals = ltrim(buf);
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	fprintf(out, "%s%s", vals, config->csv_sep);
+}
+
+static void new_line_metric(struct perf_stat_config *config __maybe_unused,
+			    void *ctx __maybe_unused)
+{
+}
+
+static void print_metric_header(struct perf_stat_config *config,
+				void *ctx, const char *color __maybe_unused,
+				const char *fmt __maybe_unused,
+				const char *unit, double val __maybe_unused)
+{
+	struct outstate *os = ctx;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	if (config->csv_output)
+		fprintf(os->fh, "%s%s", unit, config->csv_sep);
+	else
+		fprintf(os->fh, "%*s ", config->metric_only_len, unit);
+}
+
+static int first_shadow_cpu(struct perf_stat_config *config,
+			    struct perf_evsel *evsel, int id)
+{
+	struct perf_evlist *evlist = evsel->evlist;
+	int i;
+
+	if (!config->aggr_get_id)
+		return 0;
+
+	if (config->aggr_mode == AGGR_NONE)
+		return id;
+
+	if (config->aggr_mode == AGGR_GLOBAL)
+		return 0;
+
+	for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
+		int cpu2 = perf_evsel__cpus(evsel)->map[i];
+
+		if (config->aggr_get_id(config, evlist->cpus, cpu2) == id)
+			return cpu2;
+	}
+	return 0;
+}
+
+static void abs_printout(struct perf_stat_config *config,
+			 int id, int nr, struct perf_evsel *evsel, double avg)
+{
+	FILE *output = config->output;
+	double sc =  evsel->scale;
+	const char *fmt;
+
+	if (config->csv_output) {
+		fmt = floor(sc) != sc ?  "%.2f%s" : "%.0f%s";
+	} else {
+		if (config->big_num)
+			fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
+		else
+			fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
+	}
+
+	aggr_printout(config, evsel, id, nr);
+
+	fprintf(output, fmt, avg, config->csv_sep);
+
+	if (evsel->unit)
+		fprintf(output, "%-*s%s",
+			config->csv_output ? 0 : config->unit_width,
+			evsel->unit, config->csv_sep);
+
+	fprintf(output, "%-*s", config->csv_output ? 0 : 25, perf_evsel__name(evsel));
+
+	if (evsel->cgrp)
+		fprintf(output, "%s%s", config->csv_sep, evsel->cgrp->name);
+}
+
+static bool is_mixed_hw_group(struct perf_evsel *counter)
+{
+	struct perf_evlist *evlist = counter->evlist;
+	u32 pmu_type = counter->attr.type;
+	struct perf_evsel *pos;
+
+	if (counter->nr_members < 2)
+		return false;
+
+	evlist__for_each_entry(evlist, pos) {
+		/* software events can be part of any hardware group */
+		if (pos->attr.type == PERF_TYPE_SOFTWARE)
+			continue;
+		if (pmu_type == PERF_TYPE_SOFTWARE) {
+			pmu_type = pos->attr.type;
+			continue;
+		}
+		if (pmu_type != pos->attr.type)
+			return true;
+	}
+
+	return false;
+}
+
+static void printout(struct perf_stat_config *config, int id, int nr,
+		     struct perf_evsel *counter, double uval,
+		     char *prefix, u64 run, u64 ena, double noise,
+		     struct runtime_stat *st)
+{
+	struct perf_stat_output_ctx out;
+	struct outstate os = {
+		.fh = config->output,
+		.prefix = prefix ? prefix : "",
+		.id = id,
+		.nr = nr,
+		.evsel = counter,
+	};
+	print_metric_t pm = print_metric_std;
+	new_line_t nl;
+
+	if (config->metric_only) {
+		nl = new_line_metric;
+		if (config->csv_output)
+			pm = print_metric_only_csv;
+		else
+			pm = print_metric_only;
+	} else
+		nl = new_line_std;
+
+	if (config->csv_output && !config->metric_only) {
+		static int aggr_fields[] = {
+			[AGGR_GLOBAL] = 0,
+			[AGGR_THREAD] = 1,
+			[AGGR_NONE] = 1,
+			[AGGR_SOCKET] = 2,
+			[AGGR_CORE] = 2,
+		};
+
+		pm = print_metric_csv;
+		nl = new_line_csv;
+		os.nfields = 3;
+		os.nfields += aggr_fields[config->aggr_mode];
+		if (counter->cgrp)
+			os.nfields++;
+	}
+	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
+		if (config->metric_only) {
+			pm(config, &os, NULL, "", "", 0);
+			return;
+		}
+		aggr_printout(config, counter, id, nr);
+
+		fprintf(config->output, "%*s%s",
+			config->csv_output ? 0 : 18,
+			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+			config->csv_sep);
+
+		if (counter->supported) {
+			config->print_free_counters_hint = 1;
+			if (is_mixed_hw_group(counter))
+				config->print_mixed_hw_group_error = 1;
+		}
+
+		fprintf(config->output, "%-*s%s",
+			config->csv_output ? 0 : config->unit_width,
+			counter->unit, config->csv_sep);
+
+		fprintf(config->output, "%*s",
+			config->csv_output ? 0 : -25,
+			perf_evsel__name(counter));
+
+		if (counter->cgrp)
+			fprintf(config->output, "%s%s",
+				config->csv_sep, counter->cgrp->name);
+
+		if (!config->csv_output)
+			pm(config, &os, NULL, NULL, "", 0);
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
+		if (config->csv_output)
+			pm(config, &os, NULL, NULL, "", 0);
+		return;
+	}
+
+	if (!config->metric_only)
+		abs_printout(config, id, nr, counter, uval);
+
+	out.print_metric = pm;
+	out.new_line = nl;
+	out.ctx = &os;
+	out.force_header = false;
+
+	if (config->csv_output && !config->metric_only) {
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
+	}
+
+	perf_stat__print_shadow_stats(config, counter, uval,
+				first_shadow_cpu(config, counter, id),
+				&out, &config->metric_events, st);
+	if (!config->csv_output && !config->metric_only) {
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
+	}
+}
+
+static void aggr_update_shadow(struct perf_stat_config *config,
+			       struct perf_evlist *evlist)
+{
+	int cpu, s2, id, s;
+	u64 val;
+	struct perf_evsel *counter;
+
+	for (s = 0; s < config->aggr_map->nr; s++) {
+		id = config->aggr_map->map[s];
+		evlist__for_each_entry(evlist, counter) {
+			val = 0;
+			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+				s2 = config->aggr_get_id(config, evlist->cpus, cpu);
+				if (s2 != id)
+					continue;
+				val += perf_counts(counter->counts, cpu, 0)->val;
+			}
+			perf_stat__update_shadow_stats(counter, val,
+					first_shadow_cpu(config, counter, id),
+					&rt_stat);
+		}
+	}
+}
+
+static void uniquify_event_name(struct perf_evsel *counter)
+{
+	char *new_name;
+	char *config;
+
+	if (counter->uniquified_name ||
+	    !counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
+					   strlen(counter->pmu_name)))
+		return;
+
+	config = strchr(counter->name, '/');
+	if (config) {
+		if (asprintf(&new_name,
+			     "%s%s", counter->pmu_name, config) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	} else {
+		if (asprintf(&new_name,
+			     "%s [%s]", counter->name, counter->pmu_name) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	}
+
+	counter->uniquified_name = true;
+}
+
+static void collect_all_aliases(struct perf_stat_config *config, struct perf_evsel *counter,
+			    void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data,
+				       bool first),
+			    void *data)
+{
+	struct perf_evlist *evlist = counter->evlist;
+	struct perf_evsel *alias;
+
+	alias = list_prepare_entry(counter, &(evlist->entries), node);
+	list_for_each_entry_continue (alias, &evlist->entries, node) {
+		if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
+		    alias->scale != counter->scale ||
+		    alias->cgrp != counter->cgrp ||
+		    strcmp(alias->unit, counter->unit) ||
+		    perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
+			break;
+		alias->merged_stat = true;
+		cb(config, alias, data, false);
+	}
+}
+
+static bool collect_data(struct perf_stat_config *config, struct perf_evsel *counter,
+			    void (*cb)(struct perf_stat_config *config, struct perf_evsel *counter, void *data,
+				       bool first),
+			    void *data)
+{
+	if (counter->merged_stat)
+		return false;
+	cb(config, counter, data, true);
+	if (config->no_merge)
+		uniquify_event_name(counter);
+	else if (counter->auto_merge_stats)
+		collect_all_aliases(config, counter, cb, data);
+	return true;
+}
+
+struct aggr_data {
+	u64 ena, run, val;
+	int id;
+	int nr;
+	int cpu;
+};
+
+static void aggr_cb(struct perf_stat_config *config,
+		    struct perf_evsel *counter, void *data, bool first)
+{
+	struct aggr_data *ad = data;
+	int cpu, s2;
+
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+		struct perf_counts_values *counts;
+
+		s2 = config->aggr_get_id(config, perf_evsel__cpus(counter), cpu);
+		if (s2 != ad->id)
+			continue;
+		if (first)
+			ad->nr++;
+		counts = perf_counts(counter->counts, cpu, 0);
+		/*
+		 * When any result is bad, make them all to give
+		 * consistent output in interval mode.
+		 */
+		if (counts->ena == 0 || counts->run == 0 ||
+		    counter->counts->scaled == -1) {
+			ad->ena = 0;
+			ad->run = 0;
+			break;
+		}
+		ad->val += counts->val;
+		ad->ena += counts->ena;
+		ad->run += counts->run;
+	}
+}
+
+static void print_aggr(struct perf_stat_config *config,
+		       struct perf_evlist *evlist,
+		       char *prefix)
+{
+	bool metric_only = config->metric_only;
+	FILE *output = config->output;
+	struct perf_evsel *counter;
+	int s, id, nr;
+	double uval;
+	u64 ena, run, val;
+	bool first;
+
+	if (!(config->aggr_map || config->aggr_get_id))
+		return;
+
+	aggr_update_shadow(config, evlist);
+
+	/*
+	 * With metric_only everything is on a single line.
+	 * Without each counter has its own line.
+	 */
+	for (s = 0; s < config->aggr_map->nr; s++) {
+		struct aggr_data ad;
+		if (prefix && metric_only)
+			fprintf(output, "%s", prefix);
+
+		ad.id = id = config->aggr_map->map[s];
+		first = true;
+		evlist__for_each_entry(evlist, counter) {
+			if (is_duration_time(counter))
+				continue;
+
+			ad.val = ad.ena = ad.run = 0;
+			ad.nr = 0;
+			if (!collect_data(config, counter, aggr_cb, &ad))
+				continue;
+			nr = ad.nr;
+			ena = ad.ena;
+			run = ad.run;
+			val = ad.val;
+			if (first && metric_only) {
+				first = false;
+				aggr_printout(config, counter, id, nr);
+			}
+			if (prefix && !metric_only)
+				fprintf(output, "%s", prefix);
+
+			uval = val * counter->scale;
+			printout(config, id, nr, counter, uval, prefix,
+				 run, ena, 1.0, &rt_stat);
+			if (!metric_only)
+				fputc('\n', output);
+		}
+		if (metric_only)
+			fputc('\n', output);
+	}
+}
+
+static int cmp_val(const void *a, const void *b)
+{
+	return ((struct perf_aggr_thread_value *)b)->val -
+		((struct perf_aggr_thread_value *)a)->val;
+}
+
+static struct perf_aggr_thread_value *sort_aggr_thread(
+					struct perf_evsel *counter,
+					int nthreads, int ncpus,
+					int *ret,
+					struct target *_target)
+{
+	int cpu, thread, i = 0;
+	double uval;
+	struct perf_aggr_thread_value *buf;
+
+	buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value));
+	if (!buf)
+		return NULL;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		u64 ena = 0, run = 0, val = 0;
+
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			val += perf_counts(counter->counts, cpu, thread)->val;
+			ena += perf_counts(counter->counts, cpu, thread)->ena;
+			run += perf_counts(counter->counts, cpu, thread)->run;
+		}
+
+		uval = val * counter->scale;
+
+		/*
+		 * Skip value 0 when enabling --per-thread globally,
+		 * otherwise too many 0 output.
+		 */
+		if (uval == 0.0 && target__has_per_thread(_target))
+			continue;
+
+		buf[i].counter = counter;
+		buf[i].id = thread;
+		buf[i].uval = uval;
+		buf[i].val = val;
+		buf[i].run = run;
+		buf[i].ena = ena;
+		i++;
+	}
+
+	qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val);
+
+	if (ret)
+		*ret = i;
+
+	return buf;
+}
+
+static void print_aggr_thread(struct perf_stat_config *config,
+			      struct target *_target,
+			      struct perf_evsel *counter, char *prefix)
+{
+	FILE *output = config->output;
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = cpu_map__nr(counter->cpus);
+	int thread, sorted_threads, id;
+	struct perf_aggr_thread_value *buf;
+
+	buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads, _target);
+	if (!buf) {
+		perror("cannot sort aggr thread");
+		return;
+	}
+
+	for (thread = 0; thread < sorted_threads; thread++) {
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		id = buf[thread].id;
+		if (config->stats)
+			printout(config, id, 0, buf[thread].counter, buf[thread].uval,
+				 prefix, buf[thread].run, buf[thread].ena, 1.0,
+				 &config->stats[id]);
+		else
+			printout(config, id, 0, buf[thread].counter, buf[thread].uval,
+				 prefix, buf[thread].run, buf[thread].ena, 1.0,
+				 &rt_stat);
+		fputc('\n', output);
+	}
+
+	free(buf);
+}
+
+struct caggr_data {
+	double avg, avg_enabled, avg_running;
+};
+
+static void counter_aggr_cb(struct perf_stat_config *config __maybe_unused,
+			    struct perf_evsel *counter, void *data,
+			    bool first __maybe_unused)
+{
+	struct caggr_data *cd = data;
+	struct perf_stat_evsel *ps = counter->stats;
+
+	cd->avg += avg_stats(&ps->res_stats[0]);
+	cd->avg_enabled += avg_stats(&ps->res_stats[1]);
+	cd->avg_running += avg_stats(&ps->res_stats[2]);
+}
+
+/*
+ * Print out the results of a single counter:
+ * aggregated counts in system-wide mode
+ */
+static void print_counter_aggr(struct perf_stat_config *config,
+			       struct perf_evsel *counter, char *prefix)
+{
+	bool metric_only = config->metric_only;
+	FILE *output = config->output;
+	double uval;
+	struct caggr_data cd = { .avg = 0.0 };
+
+	if (!collect_data(config, counter, counter_aggr_cb, &cd))
+		return;
+
+	if (prefix && !metric_only)
+		fprintf(output, "%s", prefix);
+
+	uval = cd.avg * counter->scale;
+	printout(config, -1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
+		 cd.avg, &rt_stat);
+	if (!metric_only)
+		fprintf(output, "\n");
+}
+
+static void counter_cb(struct perf_stat_config *config __maybe_unused,
+		       struct perf_evsel *counter, void *data,
+		       bool first __maybe_unused)
+{
+	struct aggr_data *ad = data;
+
+	ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
+	ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
+	ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
+}
+
+/*
+ * Print out the results of a single counter:
+ * does not use aggregated count in system-wide
+ */
+static void print_counter(struct perf_stat_config *config,
+			  struct perf_evsel *counter, char *prefix)
+{
+	FILE *output = config->output;
+	u64 ena, run, val;
+	double uval;
+	int cpu;
+
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+		struct aggr_data ad = { .cpu = cpu };
+
+		if (!collect_data(config, counter, counter_cb, &ad))
+			return;
+		val = ad.val;
+		ena = ad.ena;
+		run = ad.run;
+
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		uval = val * counter->scale;
+		printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
+			 &rt_stat);
+
+		fputc('\n', output);
+	}
+}
+
+static void print_no_aggr_metric(struct perf_stat_config *config,
+				 struct perf_evlist *evlist,
+				 char *prefix)
+{
+	int cpu;
+	int nrcpus = 0;
+	struct perf_evsel *counter;
+	u64 ena, run, val;
+	double uval;
+
+	nrcpus = evlist->cpus->nr;
+	for (cpu = 0; cpu < nrcpus; cpu++) {
+		bool first = true;
+
+		if (prefix)
+			fputs(prefix, config->output);
+		evlist__for_each_entry(evlist, counter) {
+			if (is_duration_time(counter))
+				continue;
+			if (first) {
+				aggr_printout(config, counter, cpu, 0);
+				first = false;
+			}
+			val = perf_counts(counter->counts, cpu, 0)->val;
+			ena = perf_counts(counter->counts, cpu, 0)->ena;
+			run = perf_counts(counter->counts, cpu, 0)->run;
+
+			uval = val * counter->scale;
+			printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
+				 &rt_stat);
+		}
+		fputc('\n', config->output);
+	}
+}
+
+static int aggr_header_lens[] = {
+	[AGGR_CORE] = 18,
+	[AGGR_SOCKET] = 12,
+	[AGGR_NONE] = 6,
+	[AGGR_THREAD] = 24,
+	[AGGR_GLOBAL] = 0,
+};
+
+static const char *aggr_header_csv[] = {
+	[AGGR_CORE] 	= 	"core,cpus,",
+	[AGGR_SOCKET] 	= 	"socket,cpus",
+	[AGGR_NONE] 	= 	"cpu,",
+	[AGGR_THREAD] 	= 	"comm-pid,",
+	[AGGR_GLOBAL] 	=	""
+};
+
+static void print_metric_headers(struct perf_stat_config *config,
+				 struct perf_evlist *evlist,
+				 const char *prefix, bool no_indent)
+{
+	struct perf_stat_output_ctx out;
+	struct perf_evsel *counter;
+	struct outstate os = {
+		.fh = config->output
+	};
+
+	if (prefix)
+		fprintf(config->output, "%s", prefix);
+
+	if (!config->csv_output && !no_indent)
+		fprintf(config->output, "%*s",
+			aggr_header_lens[config->aggr_mode], "");
+	if (config->csv_output) {
+		if (config->interval)
+			fputs("time,", config->output);
+		fputs(aggr_header_csv[config->aggr_mode], config->output);
+	}
+
+	/* Print metrics headers only */
+	evlist__for_each_entry(evlist, counter) {
+		if (is_duration_time(counter))
+			continue;
+		os.evsel = counter;
+		out.ctx = &os;
+		out.print_metric = print_metric_header;
+		out.new_line = new_line_metric;
+		out.force_header = true;
+		os.evsel = counter;
+		perf_stat__print_shadow_stats(config, counter, 0,
+					      0,
+					      &out,
+					      &config->metric_events,
+					      &rt_stat);
+	}
+	fputc('\n', config->output);
+}
+
+static void print_interval(struct perf_stat_config *config,
+			   struct perf_evlist *evlist,
+			   char *prefix, struct timespec *ts)
+{
+	bool metric_only = config->metric_only;
+	unsigned int unit_width = config->unit_width;
+	FILE *output = config->output;
+	static int num_print_interval;
+
+	if (config->interval_clear)
+		puts(CONSOLE_CLEAR);
+
+	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep);
+
+	if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) {
+		switch (config->aggr_mode) {
+		case AGGR_SOCKET:
+			fprintf(output, "#           time socket cpus");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_CORE:
+			fprintf(output, "#           time core         cpus");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_NONE:
+			fprintf(output, "#           time CPU    ");
+			if (!metric_only)
+				fprintf(output, "                counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_THREAD:
+			fprintf(output, "#           time             comm-pid");
+			if (!metric_only)
+				fprintf(output, "                  counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_GLOBAL:
+		default:
+			fprintf(output, "#           time");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+		case AGGR_UNSET:
+			break;
+		}
+	}
+
+	if ((num_print_interval == 0 || config->interval_clear) && metric_only)
+		print_metric_headers(config, evlist, " ", true);
+	if (++num_print_interval == 25)
+		num_print_interval = 0;
+}
+
+static void print_header(struct perf_stat_config *config,
+			 struct target *_target,
+			 int argc, const char **argv)
+{
+	FILE *output = config->output;
+	int i;
+
+	fflush(stdout);
+
+	if (!config->csv_output) {
+		fprintf(output, "\n");
+		fprintf(output, " Performance counter stats for ");
+		if (_target->system_wide)
+			fprintf(output, "\'system wide");
+		else if (_target->cpu_list)
+			fprintf(output, "\'CPU(s) %s", _target->cpu_list);
+		else if (!target__has_task(_target)) {
+			fprintf(output, "\'%s", argv ? argv[0] : "pipe");
+			for (i = 1; argv && (i < argc); i++)
+				fprintf(output, " %s", argv[i]);
+		} else if (_target->pid)
+			fprintf(output, "process id \'%s", _target->pid);
+		else
+			fprintf(output, "thread id \'%s", _target->tid);
+
+		fprintf(output, "\'");
+		if (config->run_count > 1)
+			fprintf(output, " (%d runs)", config->run_count);
+		fprintf(output, ":\n\n");
+	}
+}
+
+static int get_precision(double num)
+{
+	if (num > 1)
+		return 0;
+
+	return lround(ceil(-log10(num)));
+}
+
+static void print_table(struct perf_stat_config *config,
+			FILE *output, int precision, double avg)
+{
+	char tmp[64];
+	int idx, indent = 0;
+
+	scnprintf(tmp, 64, " %17.*f", precision, avg);
+	while (tmp[indent] == ' ')
+		indent++;
+
+	fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
+
+	for (idx = 0; idx < config->run_count; idx++) {
+		double run = (double) config->walltime_run[idx] / NSEC_PER_SEC;
+		int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
+
+		fprintf(output, " %17.*f (%+.*f) ",
+			precision, run, precision, run - avg);
+
+		for (h = 0; h < n; h++)
+			fprintf(output, "#");
+
+		fprintf(output, "\n");
+	}
+
+	fprintf(output, "\n%*s# Final result:\n", indent, "");
+}
+
+static double timeval2double(struct timeval *t)
+{
+	return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC;
+}
+
+static void print_footer(struct perf_stat_config *config)
+{
+	double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
+	FILE *output = config->output;
+	int n;
+
+	if (!config->null_run)
+		fprintf(output, "\n");
+
+	if (config->run_count == 1) {
+		fprintf(output, " %17.9f seconds time elapsed", avg);
+
+		if (config->ru_display) {
+			double ru_utime = timeval2double(&config->ru_data.ru_utime);
+			double ru_stime = timeval2double(&config->ru_data.ru_stime);
+
+			fprintf(output, "\n\n");
+			fprintf(output, " %17.9f seconds user\n", ru_utime);
+			fprintf(output, " %17.9f seconds sys\n", ru_stime);
+		}
+	} else {
+		double sd = stddev_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
+		/*
+		 * Display at most 2 more significant
+		 * digits than the stddev inaccuracy.
+		 */
+		int precision = get_precision(sd) + 2;
+
+		if (config->walltime_run_table)
+			print_table(config, output, precision, avg);
+
+		fprintf(output, " %17.*f +- %.*f seconds time elapsed",
+			precision, avg, precision, sd);
+
+		print_noise_pct(config, sd, avg);
+	}
+	fprintf(output, "\n\n");
+
+	if (config->print_free_counters_hint &&
+	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
+	    n > 0)
+		fprintf(output,
+"Some events weren't counted. Try disabling the NMI watchdog:\n"
+"	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
+"	perf stat ...\n"
+"	echo 1 > /proc/sys/kernel/nmi_watchdog\n");
+
+	if (config->print_mixed_hw_group_error)
+		fprintf(output,
+			"The events in group usually have to be from "
+			"the same PMU. Try reorganizing the group.\n");
+}
+
+void
+perf_evlist__print_counters(struct perf_evlist *evlist,
+			    struct perf_stat_config *config,
+			    struct target *_target,
+			    struct timespec *ts,
+			    int argc, const char **argv)
+{
+	bool metric_only = config->metric_only;
+	int interval = config->interval;
+	struct perf_evsel *counter;
+	char buf[64], *prefix = NULL;
+
+	if (interval)
+		print_interval(config, evlist, prefix = buf, ts);
+	else
+		print_header(config, _target, argc, argv);
+
+	if (metric_only) {
+		static int num_print_iv;
+
+		if (num_print_iv == 0 && !interval)
+			print_metric_headers(config, evlist, prefix, false);
+		if (num_print_iv++ == 25)
+			num_print_iv = 0;
+		if (config->aggr_mode == AGGR_GLOBAL && prefix)
+			fprintf(config->output, "%s", prefix);
+	}
+
+	switch (config->aggr_mode) {
+	case AGGR_CORE:
+	case AGGR_SOCKET:
+		print_aggr(config, evlist, prefix);
+		break;
+	case AGGR_THREAD:
+		evlist__for_each_entry(evlist, counter) {
+			if (is_duration_time(counter))
+				continue;
+			print_aggr_thread(config, _target, counter, prefix);
+		}
+		break;
+	case AGGR_GLOBAL:
+		evlist__for_each_entry(evlist, counter) {
+			if (is_duration_time(counter))
+				continue;
+			print_counter_aggr(config, counter, prefix);
+		}
+		if (metric_only)
+			fputc('\n', config->output);
+		break;
+	case AGGR_NONE:
+		if (metric_only)
+			print_no_aggr_metric(config, evlist, prefix);
+		else {
+			evlist__for_each_entry(evlist, counter) {
+				if (is_duration_time(counter))
+					continue;
+				print_counter(config, counter, prefix);
+			}
+		}
+		break;
+	case AGGR_UNSET:
+	default:
+		break;
+	}
+
+	if (!interval && !config->csv_output)
+		print_footer(config);
+
+	fflush(config->output);
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 8d3354e21e19..3a13a6dc5a62 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -215,4 +215,10 @@ int perf_stat_synthesize_config(struct perf_stat_config *config,
 				struct perf_evlist *evlist,
 				perf_event__handler_t process,
 				bool attrs);
+void
+perf_evlist__print_counters(struct perf_evlist *evlist,
+			    struct perf_stat_config *config,
+			    struct target *_target,
+			    struct timespec *ts,
+			    int argc, const char **argv);
 #endif
-- 
cgit v1.2.3


From 3de3e8bbf302545ef9acebb9f900939ac5c3820f Mon Sep 17 00:00:00 2001
From: Benjamin Peterson <benjamin@python.org>
Date: Mon, 27 Aug 2018 20:53:44 -0700
Subject: perf trace beauty: Alias 'umount' to 'umount2'

Before:

  # perf trace -e *mount* umount /dev/mapper/fedora-home /s
    11.576 ( 0.004 ms) umount/3138 umount2(arg0: 94501956754656, arg1: 0, arg2: 1, arg3: 140051050083104, arg4: 4, arg5: 94501956755136) = -1 EINVAL Invalid argument
  #

After:

  # perf trace -e *mount* umount /s
     0.000 ( 9.241 ms): umount/5251 umount2(name: 0x55f74a986480) = 0

Signed-off-by: Benjamin Peterson <benjamin@python.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180828035344.31500-1-benjamin@python.org
[ split from a larger patch ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 97ace635bed8..c106189f4066 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -825,6 +825,7 @@ static struct syscall_fmt {
 	  .arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
 	{ .name	    = "tkill",
 	  .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
+	{ .name     = "umount2", .alias = "umount", },
 	{ .name	    = "uname", .alias = "newuname", },
 	{ .name	    = "unlinkat",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
-- 
cgit v1.2.3


From 58094c48f4079cfc784f53a73caaa446db436389 Mon Sep 17 00:00:00 2001
From: Kim Phillips <kim.phillips@arm.com>
Date: Mon, 27 Aug 2018 15:08:07 -0500
Subject: perf annotate: Handle arm64 move instructions

Add default handler for non-jump instructions.  This really only has an
effect on instructions that compute a PC-relative address, such as
'adrp,' as seen in these couple of examples:

BEFORE: adrp   x0, ffff20000aa11000 <kallsyms_token_index+0xce000>
AFTER:  adrp   x0, kallsyms_token_index+0xce000

BEFORE: adrp   x23, ffff20000ae94000 <__per_cpu_load>
AFTER:  adrp   x23, __per_cpu_load

The implementation is identical to that of s390, but with a slight
adjustment for objdump whitespace propagation (arm64 objdump puts spaces
after commas, whereas s390's presumably doesn't).

The mov__scnprintf() declaration is moved from s390's to arm64's
instructions.c because arm64's gets included before s390's.

Committer testing:

Ran 'perf annotate --stdio2 > /tmp/{before,after}' no diff.

Signed-off-by: Kim Phillips <kim.phillips@arm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/20180827150807.304110d2e9919a17c832ca48@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm64/annotate/instructions.c | 59 ++++++++++++++++++++++++++-
 tools/perf/arch/s390/annotate/instructions.c  |  2 -
 2 files changed, 58 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c
index 6688977e4ac7..76c6345a57d5 100644
--- a/tools/perf/arch/arm64/annotate/instructions.c
+++ b/tools/perf/arch/arm64/annotate/instructions.c
@@ -8,6 +8,63 @@ struct arm64_annotate {
 		jump_insn;
 };
 
+static int arm64_mov__parse(struct arch *arch __maybe_unused,
+			    struct ins_operands *ops,
+			    struct map_symbol *ms __maybe_unused)
+{
+	char *s = strchr(ops->raw, ','), *target, *endptr;
+
+	if (s == NULL)
+		return -1;
+
+	*s = '\0';
+	ops->source.raw = strdup(ops->raw);
+	*s = ',';
+
+	if (ops->source.raw == NULL)
+		return -1;
+
+	target = ++s;
+	ops->target.raw = strdup(target);
+	if (ops->target.raw == NULL)
+		goto out_free_source;
+
+	ops->target.addr = strtoull(target, &endptr, 16);
+	if (endptr == target)
+		goto out_free_target;
+
+	s = strchr(endptr, '<');
+	if (s == NULL)
+		goto out_free_target;
+	endptr = strchr(s + 1, '>');
+	if (endptr == NULL)
+		goto out_free_target;
+
+	*endptr = '\0';
+	*s = ' ';
+	ops->target.name = strdup(s);
+	*s = '<';
+	*endptr = '>';
+	if (ops->target.name == NULL)
+		goto out_free_target;
+
+	return 0;
+
+out_free_target:
+	zfree(&ops->target.raw);
+out_free_source:
+	zfree(&ops->source.raw);
+	return -1;
+}
+
+static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
+			  struct ins_operands *ops);
+
+static struct ins_ops arm64_mov_ops = {
+	.parse	   = arm64_mov__parse,
+	.scnprintf = mov__scnprintf,
+};
+
 static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const char *name)
 {
 	struct arm64_annotate *arm = arch->priv;
@@ -21,7 +78,7 @@ static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const
 	else if (!strcmp(name, "ret"))
 		ops = &ret_ops;
 	else
-		return NULL;
+		ops = &arm64_mov_ops;
 
 	arch__associate_ins_ops(arch, name, ops);
 	return ops;
diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index cee4e2f7c057..de0dd66dbb48 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -100,8 +100,6 @@ out_free_source:
 	return -1;
 }
 
-static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
-			  struct ins_operands *ops);
 
 static struct ins_ops s390_mov_ops = {
 	.parse	   = s390_mov__parse,
-- 
cgit v1.2.3


From 72ce30dd1f9bdbd6913ba868d0d2ca55c268eff3 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 7 Jul 2018 10:24:23 -0700
Subject: rcu: Stop testing RCU-bh and RCU-sched

Now that the RCU-bh and RCU-sched update-side functions are simple
wrappers around their RCU counterparts, there isn't a whole lot of
point in testing them.  This commit therefore removes the self-test
capability and removes the corresponding kernel-boot parameters.
It also updates the various rcutorture .boot files to remove the
kernel boot parameters that call for testing RCU-bh and RCU-sched.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 Documentation/admin-guide/kernel-parameters.txt    |  6 ----
 kernel/rcu/update.c                                | 38 +---------------------
 .../selftests/rcutorture/configs/rcu/TINY02.boot   |  2 --
 .../selftests/rcutorture/configs/rcu/TREE01.boot   |  2 +-
 .../selftests/rcutorture/configs/rcu/TREE04.boot   |  2 +-
 .../selftests/rcutorture/configs/rcu/TREE05.boot   |  2 --
 .../selftests/rcutorture/configs/rcu/TREE06.boot   |  2 --
 .../selftests/rcutorture/configs/rcu/TREE08.boot   |  2 --
 8 files changed, 3 insertions(+), 53 deletions(-)

(limited to 'tools')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 9871e649ffef..aa96e669bcb8 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3863,12 +3863,6 @@
 	rcupdate.rcu_self_test= [KNL]
 			Run the RCU early boot self tests
 
-	rcupdate.rcu_self_test_bh= [KNL]
-			Run the RCU bh early boot self tests
-
-	rcupdate.rcu_self_test_sched= [KNL]
-			Run the RCU sched early boot self tests
-
 	rdinit=		[KNL]
 			Format: <full_path>
 			Run specified binary instead of /init from the ramdisk,
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 9ea87d0aa386..ee366faecea6 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -203,11 +203,7 @@ void rcu_test_sync_prims(void)
 	if (!IS_ENABLED(CONFIG_PROVE_RCU))
 		return;
 	synchronize_rcu();
-	synchronize_rcu_bh();
-	synchronize_sched();
 	synchronize_rcu_expedited();
-	synchronize_rcu_bh_expedited();
-	synchronize_sched_expedited();
 }
 
 #if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU)
@@ -870,15 +866,10 @@ static void __init rcu_tasks_bootup_oddness(void)
 #ifdef CONFIG_PROVE_RCU
 
 /*
- * Early boot self test parameters, one for each flavor
+ * Early boot self test parameters.
  */
 static bool rcu_self_test;
-static bool rcu_self_test_bh;
-static bool rcu_self_test_sched;
-
 module_param(rcu_self_test, bool, 0444);
-module_param(rcu_self_test_bh, bool, 0444);
-module_param(rcu_self_test_sched, bool, 0444);
 
 static int rcu_self_test_counter;
 
@@ -895,30 +886,12 @@ static void early_boot_test_call_rcu(void)
 	call_rcu(&head, test_callback);
 }
 
-static void early_boot_test_call_rcu_bh(void)
-{
-	static struct rcu_head head;
-
-	call_rcu_bh(&head, test_callback);
-}
-
-static void early_boot_test_call_rcu_sched(void)
-{
-	static struct rcu_head head;
-
-	call_rcu_sched(&head, test_callback);
-}
-
 void rcu_early_boot_tests(void)
 {
 	pr_info("Running RCU self tests\n");
 
 	if (rcu_self_test)
 		early_boot_test_call_rcu();
-	if (rcu_self_test_bh)
-		early_boot_test_call_rcu_bh();
-	if (rcu_self_test_sched)
-		early_boot_test_call_rcu_sched();
 	rcu_test_sync_prims();
 }
 
@@ -931,15 +904,6 @@ static int rcu_verify_early_boot_tests(void)
 		early_boot_test_counter++;
 		rcu_barrier();
 	}
-	if (rcu_self_test_bh) {
-		early_boot_test_counter++;
-		rcu_barrier_bh();
-	}
-	if (rcu_self_test_sched) {
-		early_boot_test_counter++;
-		rcu_barrier_sched();
-	}
-
 	if (rcu_self_test_counter != early_boot_test_counter) {
 		WARN_ON(1);
 		ret = -1;
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot
index 6c1a292a65fb..b39f1553a478 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02.boot
@@ -1,3 +1 @@
 rcupdate.rcu_self_test=1
-rcupdate.rcu_self_test_bh=1
-rcutorture.torture_type=rcu_bh
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
index 9f3a4d28e508..ea47da95374b 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
@@ -1,4 +1,4 @@
-rcutorture.torture_type=rcu_bh maxcpus=8 nr_cpus=43
+maxcpus=8 nr_cpus=43
 rcutree.gp_preinit_delay=3
 rcutree.gp_init_delay=3
 rcutree.gp_cleanup_delay=3
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot
index e6071bb96c7d..5adc6756792a 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot
@@ -1 +1 @@
-rcutorture.torture_type=rcu_bh rcutree.rcu_fanout_leaf=4 nohz_full=1-7
+rcutree.rcu_fanout_leaf=4 nohz_full=1-7
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
index c7fd050dfcd9..779f1aed4606 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
@@ -1,5 +1,3 @@
-rcutorture.torture_type=sched
-rcupdate.rcu_self_test_sched=1
 rcutree.gp_preinit_delay=3
 rcutree.gp_init_delay=3
 rcutree.gp_cleanup_delay=3
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot
index ad18b52a2cad..055f4aa79077 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06.boot
@@ -1,6 +1,4 @@
 rcupdate.rcu_self_test=1
-rcupdate.rcu_self_test_bh=1
-rcupdate.rcu_self_test_sched=1
 rcutree.rcu_fanout_exact=1
 rcutree.gp_preinit_delay=3
 rcutree.gp_init_delay=3
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
index 1bd8efc4141e..22478fd3a865 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot
@@ -1,5 +1,3 @@
-rcutorture.torture_type=sched
 rcupdate.rcu_self_test=1
-rcupdate.rcu_self_test_sched=1
 rcutree.rcu_fanout_exact=1
 rcu_nocbs=0-7
-- 
cgit v1.2.3


From 55cda2290bf9d8510fbe7c1939a36680476c69c4 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 14 Aug 2018 09:19:05 -0700
Subject: rcutorture: Test early boot call_srcu()

Now that SRCU permits call_srcu() to be invoked at early boot, this
commit ensures that the rcutorture scripting tests early boot call_srcu().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot | 1 +
 tools/testing/selftests/rcutorture/configs/rcu/SRCU-u.boot | 1 +
 tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot | 1 +
 3 files changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
index 84a7d51b7481..ce48c7b82673 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
@@ -1 +1,2 @@
 rcutorture.torture_type=srcud
+rcupdate.rcu_self_test=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u.boot
index 84a7d51b7481..ce48c7b82673 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u.boot
@@ -1 +1,2 @@
 rcutorture.torture_type=srcud
+rcupdate.rcu_self_test=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
index c7fd050dfcd9..dfebc82932ca 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05.boot
@@ -3,3 +3,4 @@ rcupdate.rcu_self_test_sched=1
 rcutree.gp_preinit_delay=3
 rcutree.gp_init_delay=3
 rcutree.gp_cleanup_delay=3
+rcupdate.rcu_self_test=1
-- 
cgit v1.2.3


From 9746b1ee2edcabfb8f40d5311f23ac2f01f152ed Mon Sep 17 00:00:00 2001
From: "Nikita V. Shirokov" <tehnerd@fb.com>
Date: Fri, 31 Aug 2018 09:43:47 -0700
Subject: bpf: add selftest for bpf's (set|get)_sockopt for SAVE_SYN

adding selftest for feature, introduced in commit 9452048c79404 ("bpf:
add TCP_SAVE_SYN/TCP_SAVED_SYN options for bpf_(set|get)sockopt").

Signed-off-by: Nikita V. Shirokov <tehnerd@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_tcpbpf_kern.c | 38 ++++++++++++++++++++++++--
 tools/testing/selftests/bpf/test_tcpbpf_user.c | 31 ++++++++++++++++++++-
 2 files changed, 65 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
index 4b7fd540cea9..74f73b33a7b0 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
@@ -5,6 +5,7 @@
 #include <linux/if_ether.h>
 #include <linux/if_packet.h>
 #include <linux/ip.h>
+#include <linux/ipv6.h>
 #include <linux/types.h>
 #include <linux/socket.h>
 #include <linux/tcp.h>
@@ -17,6 +18,13 @@ struct bpf_map_def SEC("maps") global_map = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(__u32),
 	.value_size = sizeof(struct tcpbpf_globals),
+	.max_entries = 4,
+};
+
+struct bpf_map_def SEC("maps") sockopt_results = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(int),
 	.max_entries = 2,
 };
 
@@ -45,11 +53,14 @@ int _version SEC("version") = 1;
 SEC("sockops")
 int bpf_testcb(struct bpf_sock_ops *skops)
 {
-	int rv = -1;
-	int bad_call_rv = 0;
+	char header[sizeof(struct ipv6hdr) + sizeof(struct tcphdr)];
+	struct tcphdr *thdr;
 	int good_call_rv = 0;
-	int op;
+	int bad_call_rv = 0;
+	int save_syn = 1;
+	int rv = -1;
 	int v = 0;
+	int op;
 
 	op = (int) skops->op;
 
@@ -82,6 +93,21 @@ int bpf_testcb(struct bpf_sock_ops *skops)
 		v = 0xff;
 		rv = bpf_setsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v,
 				    sizeof(v));
+		if (skops->family == AF_INET6) {
+			v = bpf_getsockopt(skops, IPPROTO_TCP, TCP_SAVED_SYN,
+					   header, (sizeof(struct ipv6hdr) +
+						    sizeof(struct tcphdr)));
+			if (!v) {
+				int offset = sizeof(struct ipv6hdr);
+
+				thdr = (struct tcphdr *)(header + offset);
+				v = thdr->syn;
+				__u32 key = 1;
+
+				bpf_map_update_elem(&sockopt_results, &key, &v,
+						    BPF_ANY);
+			}
+		}
 		break;
 	case BPF_SOCK_OPS_RTO_CB:
 		break;
@@ -111,6 +137,12 @@ int bpf_testcb(struct bpf_sock_ops *skops)
 		break;
 	case BPF_SOCK_OPS_TCP_LISTEN_CB:
 		bpf_sock_ops_cb_flags_set(skops, BPF_SOCK_OPS_STATE_CB_FLAG);
+		v = bpf_setsockopt(skops, IPPROTO_TCP, TCP_SAVE_SYN,
+				   &save_syn, sizeof(save_syn));
+		/* Update global map w/ result of setsock opt */
+		__u32 key = 0;
+
+		bpf_map_update_elem(&sockopt_results, &key, &v, BPF_ANY);
 		break;
 	default:
 		rv = -1;
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c
index a275c2971376..e6eebda7d112 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_user.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c
@@ -54,6 +54,26 @@ err:
 	return -1;
 }
 
+int verify_sockopt_result(int sock_map_fd)
+{
+	__u32 key = 0;
+	int res;
+	int rv;
+
+	/* check setsockopt for SAVE_SYN */
+	rv = bpf_map_lookup_elem(sock_map_fd, &key, &res);
+	EXPECT_EQ(0, rv, "d");
+	EXPECT_EQ(0, res, "d");
+	key = 1;
+	/* check getsockopt for SAVED_SYN */
+	rv = bpf_map_lookup_elem(sock_map_fd, &key, &res);
+	EXPECT_EQ(0, rv, "d");
+	EXPECT_EQ(1, res, "d");
+	return 0;
+err:
+	return -1;
+}
+
 static int bpf_find_map(const char *test, struct bpf_object *obj,
 			const char *name)
 {
@@ -70,11 +90,11 @@ static int bpf_find_map(const char *test, struct bpf_object *obj,
 int main(int argc, char **argv)
 {
 	const char *file = "test_tcpbpf_kern.o";
+	int prog_fd, map_fd, sock_map_fd;
 	struct tcpbpf_globals g = {0};
 	const char *cg_path = "/foo";
 	int error = EXIT_FAILURE;
 	struct bpf_object *obj;
-	int prog_fd, map_fd;
 	int cg_fd = -1;
 	__u32 key = 0;
 	int rv;
@@ -110,6 +130,10 @@ int main(int argc, char **argv)
 	if (map_fd < 0)
 		goto err;
 
+	sock_map_fd = bpf_find_map(__func__, obj, "sockopt_results");
+	if (sock_map_fd < 0)
+		goto err;
+
 	rv = bpf_map_lookup_elem(map_fd, &key, &g);
 	if (rv != 0) {
 		printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
@@ -121,6 +145,11 @@ int main(int argc, char **argv)
 		goto err;
 	}
 
+	if (verify_sockopt_result(sock_map_fd)) {
+		printf("FAILED: Wrong sockopt stats\n");
+		goto err;
+	}
+
 	printf("PASSED!\n");
 	error = 0;
 err:
-- 
cgit v1.2.3


From c2ad647c6442cf6730ffd86cbadbbce101dea937 Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Wed, 29 Aug 2018 15:30:14 +0530
Subject: selftests/tls: Add test for recv(PEEK) spanning across multiple
 records

Added test case to receive multiple records with a single recvmsg()
operation with a MSG_PEEK set.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/tls.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index b3ebf2646e52..07daff076ce0 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -502,6 +502,28 @@ TEST_F(tls, recv_peek_multiple)
 	EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
 }
 
+TEST_F(tls, recv_peek_large_buf_mult_recs)
+{
+	char const *test_str = "test_read_peek_mult_recs";
+	char const *test_str_first = "test_read_peek";
+	char const *test_str_second = "_mult_recs";
+	int len;
+	char buf[64];
+
+	len = strlen(test_str_first);
+	EXPECT_EQ(send(self->fd, test_str_first, len, 0), len);
+
+	len = strlen(test_str_second) + 1;
+	EXPECT_EQ(send(self->fd, test_str_second, len, 0), len);
+
+	len = sizeof(buf);
+	memset(buf, 0, len);
+	EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1);
+
+	len = strlen(test_str) + 1;
+	EXPECT_EQ(memcmp(test_str, buf, len), 0);
+}
+
 TEST_F(tls, pollin)
 {
 	char const *test_str = "test_poll";
-- 
cgit v1.2.3


From 21d7eb9a24739cdc5ea19c90a79e5a585866ba35 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 3 Sep 2018 15:02:22 -0300
Subject: perf augmented_syscalls: Check probe_read_str() return separately

Using a value returned from probe_read_str() to tell how many bytes to
copy using perf_event_output() has issues in some older kernels, like
4.17.17-100.fc27.x86_64, so separate the bounds checking done on how
many bytes to copy to a separate variable, so that the next patch has
only what is being done to make the test pass on older BPF validators.

For reference, see the discussion in this thread:

  https://www.spinics.net/lists/netdev/msg480099.html

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Yonghong Song <yhs@fb.com>
Link: https://lkml.kernel.org/n/tip-jtsapwibyxrnv1xjfsgzp0fj@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/examples/bpf/augmented_syscalls.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index 1419a9186937..0decbcfa8b90 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -33,9 +33,9 @@ struct syscall_exit_args {
 };
 
 struct augmented_filename {
-	int	size;
-	int	reserved;
-	char	value[256];
+	unsigned int	size;
+	int		reserved;
+	char		value[256];
 };
 
 #define augmented_filename_syscall(syscall)							\
@@ -46,14 +46,15 @@ struct augmented_enter_##syscall##_args {			 				\
 int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
 {												\
 	struct augmented_enter_##syscall##_args augmented_args = { .filename.reserved = 0, }; 	\
+	unsigned int len = sizeof(augmented_args);						\
 	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);			\
 	augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, 		\
 						      sizeof(augmented_args.filename.value), 	\
 						      args->filename_ptr); 			\
+	if (augmented_args.filename.size < sizeof(augmented_args.filename.value))		\
+		len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size;	\
 	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\
-			  &augmented_args, 							\
-			  (sizeof(augmented_args) - sizeof(augmented_args.filename.value) +	\
-			   augmented_args.filename.size));					\
+			  &augmented_args, len);						\
 	return 0;										\
 }												\
 int syscall_exit(syscall)(struct syscall_exit_args *args)					\
-- 
cgit v1.2.3


From 7538d16397dfc72d8b61a99c32c592a75ae7f157 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 3 Sep 2018 15:18:37 -0300
Subject: perf augmented_syscalls: Avoid optimization to pass older BPF
 validators

See https://www.spinics.net/lists/netdev/msg480099.html for the whole
discussio, but to make the augmented_syscalls.c BPF program to get built
and loaded successfully in a greater range of kernels, add an extra
check.

Related patch:

  a60dd35d2e39 ("bpf: change bpf_perf_event_output arg5 type to ARG_CONST_SIZE_OR_ZERO")

That is in the kernel since v4.15, I couldn't figure why this is hitting
me with 4.17.17, but adding the workaround discussed there makes this
work with this fedora kernel and with 4.18.recent.

Before:

  # uname -a
  Linux seventh 4.17.17-100.fc27.x86_64 #1 SMP Mon Aug 20 15:53:11 UTC 2018 x86_64 x86_64 x86_64 GNU/Linux
  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null
  libbpf: load bpf program failed: Permission denied
  libbpf: -- BEGIN DUMP LOG ---
  libbpf:
  0: (bf) r6 = r1
  1: (b7) r1 = 0
  2: (7b) *(u64 *)(r10 -8) = r1
  3: (7b) *(u64 *)(r10 -16) = r1
  4: (7b) *(u64 *)(r10 -24) = r1
  5: (7b) *(u64 *)(r10 -32) = r1
  6: (7b) *(u64 *)(r10 -40) = r1
  7: (7b) *(u64 *)(r10 -48) = r1
  8: (7b) *(u64 *)(r10 -56) = r1
  9: (7b) *(u64 *)(r10 -64) = r1
  10: (7b) *(u64 *)(r10 -72) = r1
  11: (7b) *(u64 *)(r10 -80) = r1
  12: (7b) *(u64 *)(r10 -88) = r1
  13: (7b) *(u64 *)(r10 -96) = r1
  14: (7b) *(u64 *)(r10 -104) = r1
  15: (7b) *(u64 *)(r10 -112) = r1
  16: (7b) *(u64 *)(r10 -120) = r1
  17: (7b) *(u64 *)(r10 -128) = r1
  18: (7b) *(u64 *)(r10 -136) = r1
  19: (7b) *(u64 *)(r10 -144) = r1
  20: (7b) *(u64 *)(r10 -152) = r1
  21: (7b) *(u64 *)(r10 -160) = r1
  22: (7b) *(u64 *)(r10 -168) = r1
  23: (7b) *(u64 *)(r10 -176) = r1
  24: (7b) *(u64 *)(r10 -184) = r1
  25: (7b) *(u64 *)(r10 -192) = r1
  26: (7b) *(u64 *)(r10 -200) = r1
  27: (7b) *(u64 *)(r10 -208) = r1
  28: (7b) *(u64 *)(r10 -216) = r1
  29: (7b) *(u64 *)(r10 -224) = r1
  30: (7b) *(u64 *)(r10 -232) = r1
  31: (7b) *(u64 *)(r10 -240) = r1
  32: (7b) *(u64 *)(r10 -248) = r1
  33: (7b) *(u64 *)(r10 -256) = r1
  34: (7b) *(u64 *)(r10 -264) = r1
  35: (7b) *(u64 *)(r10 -272) = r1
  36: (7b) *(u64 *)(r10 -280) = r1
  37: (7b) *(u64 *)(r10 -288) = r1
  38: (7b) *(u64 *)(r10 -296) = r1
  39: (7b) *(u64 *)(r10 -304) = r1
  40: (7b) *(u64 *)(r10 -312) = r1
  41: (bf) r7 = r10
  42: (07) r7 += -312
  43: (bf) r1 = r7
  44: (b7) r2 = 48
  45: (bf) r3 = r6
  46: (85) call bpf_probe_read#4
  47: (79) r3 = *(u64 *)(r6 +24)
  48: (bf) r1 = r10
  49: (07) r1 += -256
  50: (b7) r8 = 256
  51: (b7) r2 = 256
  52: (85) call bpf_probe_read_str#45
  53: (bf) r1 = r0
  54: (67) r1 <<= 32
  55: (77) r1 >>= 32
  56: (bf) r5 = r0
  57: (07) r5 += 56
  58: (2d) if r8 > r1 goto pc+1
   R0=inv(id=0) R1=inv(id=0,umin_value=256,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R5=inv(id=0) R6=ctx(id=0,off=0,imm=0) R7=fp-312,call_-1 R8=inv256 R10=fp0,call_-1 fp-264=0
  59: (b7) r5 = 312
  60: (63) *(u32 *)(r10 -264) = r0
  61: (67) r5 <<= 32
  62: (77) r5 >>= 32
  63: (bf) r1 = r6
  64: (18) r2 = 0xffff8b9120cc8500
  66: (18) r3 = 0xffffffff
  68: (bf) r4 = r7
  69: (85) call bpf_perf_event_output#25
  70: (b7) r0 = 0
  71: (95) exit

  from 58 to 60: R0=inv(id=0) R1=inv(id=0,umax_value=255,var_off=(0x0; 0xff)) R5=inv(id=0) R6=ctx(id=0,off=0,imm=0) R7=fp-312,call_-1 R8=inv256 R10=fp0,call_-1 fp-264=0
  60: (63) *(u32 *)(r10 -264) = r0
  61: (67) r5 <<= 32
  62: (77) r5 >>= 32
  63: (bf) r1 = r6
  64: (18) r2 = 0xffff8b9120cc8500
  66: (18) r3 = 0xffffffff
  68: (bf) r4 = r7
  69: (85) call bpf_perf_event_output#25
  R5 unbounded memory access, use 'var &= const' or 'if (var < const)'

  libbpf: -- END LOG --
  libbpf: failed to load program 'syscalls:sys_enter_openat'
  libbpf: failed to load object 'tools/perf/examples/bpf/augmented_syscalls.c'
  bpf: load objects failed: err=-4007: (Kernel verifier blocks program loading)
  event syntax error: 'tools/perf/examples/bpf/augmented_syscalls.c'
                       \___ Kernel verifier blocks program loading

After:

  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null
     0.000 cat/29249 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
     0.008 cat/29249 syscalls:sys_exit_openat:0x3
     0.021 cat/29249 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC)
     0.025 cat/29249 syscalls:sys_exit_openat:0x3
     0.180 cat/29249 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC)
     0.185 cat/29249 syscalls:sys_exit_open:0x3
     0.242 cat/29249 openat(dfd: CWD, filename: /etc/passwd)
     0.245 cat/29249 syscalls:sys_exit_openat:0x3
  #

It also works with a more recent kernel:

  # uname -a
  Linux jouet 4.18.0-00014-g4e67b2a5df5d #6 SMP Thu Aug 30 17:34:17 -03 2018 x86_64 x86_64 x86_64 GNU/Linux
  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null
     0.000 cat/26451 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
     0.020 cat/26451 syscalls:sys_exit_openat:0x3
     0.039 cat/26451 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC)
     0.044 cat/26451 syscalls:sys_exit_openat:0x3
     0.231 cat/26451 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC)
     0.238 cat/26451 syscalls:sys_exit_open:0x3
     0.278 cat/26451 openat(dfd: CWD, filename: /etc/passwd)
     0.282 cat/26451 syscalls:sys_exit_openat:0x3
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: Gianluca Borello <g.borello@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Yonghong Song <yhs@fb.com>
Link: https://lkml.kernel.org/n/tip-wkpsivs1a9afwldbul46btbv@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/examples/bpf/augmented_syscalls.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index 0decbcfa8b90..2ae44813ef2d 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -51,8 +51,10 @@ int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
 	augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, 		\
 						      sizeof(augmented_args.filename.value), 	\
 						      args->filename_ptr); 			\
-	if (augmented_args.filename.size < sizeof(augmented_args.filename.value))		\
+	if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) {		\
 		len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size;	\
+		len &= sizeof(augmented_args.filename.value) - 1;				\
+	}											\
 	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\
 			  &augmented_args, len);						\
 	return 0;										\
-- 
cgit v1.2.3


From 8a041f86a83f9783ba23a423a2d5a51b48136850 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 3 Sep 2018 16:07:53 -0300
Subject: perf trace: Introduce syscall__augmented_args() method

That will be used by trace__sys_enter when we start combining the
augmented syscalls:sys_enter_FOO + syscalls:sys_exit_FOO.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-iiseo3s0qbf9i3rzn8k597bv@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index c106189f4066..12356deb6046 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1677,6 +1677,17 @@ static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel,
 	return printed;
 }
 
+static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size)
+{
+	void *augmented_args = NULL;
+
+	*augmented_args_size = sample->raw_size - sc->args_size;
+	if (*augmented_args_size > 0)
+		augmented_args = sample->raw_data + sc->args_size;
+
+	return augmented_args;
+}
+
 static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 			    union perf_event *event __maybe_unused,
 			    struct perf_sample *sample)
@@ -1762,10 +1773,7 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
 		goto out_put;
 
 	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
-	augmented_args_size = sample->raw_size - sc->args_size;
-	if (augmented_args_size > 0)
-		augmented_args = sample->raw_data + sc->args_size;
-
+	augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
 	syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
 	fprintf(trace->output, "%s", msg);
 	err = 0;
-- 
cgit v1.2.3


From 35386dfd13b746daf36a393bdf066dbe9b9b7aed Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Mon, 3 Sep 2018 19:33:23 +0200
Subject: spi: spidev_test: Improve decoded text part of hex dump

- Print spaces as spaces,
  - Do not print characters > 126, as they will be shown as garbage
    in the modern UTF-8 era,
  - Use a normal period instead of its hexadecimal ASCII value,
  - Delimit the text part with pipe symbols on both sides (was left side
    only), without any spaces, to make it clear where the decoded text
    starts and ends,
  - Drop a useless comment.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 tools/spi/spidev_test.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/spi/spidev_test.c b/tools/spi/spidev_test.c
index 8c590cd1171a..4c12e6aea5d5 100644
--- a/tools/spi/spidev_test.c
+++ b/tools/spi/spidev_test.c
@@ -73,12 +73,12 @@ static void hex_dump(const void *src, size_t length, size_t line_size,
 				while (i++ % line_size)
 					printf("__ ");
 			}
-			printf(" | ");  /* right close */
+			printf(" |");
 			while (line < address) {
 				c = *line++;
-				printf("%c", (c < 33 || c == 255) ? 0x2E : c);
+				printf("%c", (c < 32 || c > 126) ? '.' : c);
 			}
-			printf("\n");
+			printf("|\n");
 			if (length > 0)
 				printf("%s | ", prefix);
 		}
-- 
cgit v1.2.3


From db2da3f85cd6314321b6a9441a5af8841c93394d Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 3 Sep 2018 16:24:09 -0300
Subject: perf trace: Setup augmented_args in the raw_syscalls:sys_enter
 handler

Without using something to augment the raw_syscalls:sys_enter tracepoint
payload with the pointer contents, this will work just like before, i.e.
the augmented_args arg will be NULL and the augmented_args_size will be
0.

This just paves the way for the next cset where we will associate the
trace__sys_enter tracepoint handler with the augmented "bpf-output"
event named "__augmented_args__".

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-p8uvt2a6ug3uwlhja3cno4la@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 12356deb6046..2b99a02355cf 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1697,6 +1697,8 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	size_t printed = 0;
 	struct thread *thread;
 	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
+	int augmented_args_size = 0;
+	void *augmented_args = NULL;
 	struct syscall *sc = trace__syscall_info(trace, evsel, id);
 	struct thread_trace *ttrace;
 
@@ -1720,13 +1722,24 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 
 	if (!(trace->duration_filter || trace->summary_only || trace->min_stack))
 		trace__printf_interrupted_entry(trace);
-
+	/*
+	 * If this is raw_syscalls.sys_enter, then it always comes with the 6 possible
+	 * arguments, even if the syscall being handled, say "openat", uses only 4 arguments
+	 * this breaks syscall__augmented_args() check for augmented args, as we calculate
+	 * syscall->args_size using each syscalls:sys_enter_NAME tracefs format file,
+	 * so when handling, say the openat syscall, we end up getting 6 args for the
+	 * raw_syscalls:sys_enter event, when we expected just 4, we end up mistakenly
+	 * thinking that the extra 2 u64 args are the augmented filename, so just check
+	 * here and avoid using augmented syscalls when the evsel is the raw_syscalls one.
+	 */
+	if (evsel != trace->syscalls.events.sys_enter)
+		augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
 	ttrace->entry_time = sample->time;
 	msg = ttrace->entry_str;
 	printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name);
 
 	printed += syscall__scnprintf_args(sc, msg + printed, trace__entry_str_size - printed,
-					   args, NULL, 0, trace, thread);
+					   args, augmented_args, augmented_args_size, trace, thread);
 
 	if (sc->is_exit) {
 		if (!(trace->duration_filter || trace->summary_only || trace->failure_only || trace->min_stack)) {
-- 
cgit v1.2.3


From b1a9e2535e20cdd6cd14eec8128278bc5d97843c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 3 Sep 2018 16:29:39 -0300
Subject: perf trace: Use the raw_syscalls:sys_enter for the augmented syscalls

Now we combine what comes from the "bpf-output" event, i.e. what is
added in the augmented_syscalls.c BPF program via the
__augmented_syscalls__ BPF map, i.e. the payload we get with
raw_syscalls:sys_enter tracepoints plus the pointer contents, right
after that payload, with the raw_syscall:sys_exit also added, without
augmentation, in the augmented_syscalls.c program.

The end result is that for the hooked syscalls, we get strace like
output with pointer expansion, something that wasn't possible before
with just raw_syscalls:sys_enter + raw_syscalls:sys_exit.

E.g.:

  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c ping -c 2 ::1
     0.000 ( 0.008 ms): ping/19573 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
     0.036 ( 0.006 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libcap.so.2, flags: CLOEXEC) = 3
     0.070 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libidn.so.11, flags: CLOEXEC) = 3
     0.095 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libcrypto.so.1.1, flags: CLOEXEC) = 3
     0.127 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libresolv.so.2, flags: CLOEXEC) = 3
     0.156 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libm.so.6, flags: CLOEXEC) = 3
     0.181 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
     0.212 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libz.so.1, flags: CLOEXEC) = 3
     0.242 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libdl.so.2, flags: CLOEXEC) = 3
     0.266 ( 0.003 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libpthread.so.0, flags: CLOEXEC) = 3
     0.709 ( 0.006 ms): ping/19573 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
  PING ::1(::1) 56 data bytes
     1.133 ( 0.011 ms): ping/19573 connect(fd: 5, uservaddr: { .family: INET6, port: 1025, addr: ::1 }, addrlen: 28) = 0
  64 bytes from ::1: icmp_seq=1 ttl=64 time=0.033 ms
     1.234 ( 0.036 ms): ping/19573 sendto(fd: 4<socket:[1498931]>, buff: 0x555e5b975720, len: 64, addr: { .family: INET6, port: 58, addr: ::1 }, addr_len: 28) = 64
  64 bytes from ::1: icmp_seq=2 ttl=64 time=0.120 ms

  --- ::1 ping statistics ---
  2 packets transmitted, 2 received, 0% packet loss, time 1000ms
  rtt min/avg/max/mdev = 0.033/0.076/0.120/0.044 ms
  1002.060 ( 0.129 ms): ping/19573 sendto(fd: 4<socket:[1498931]>, buff: 0x555e5b975720, len: 64, flags: CONFIRM, addr: { .family: INET6, port: 58, addr: ::1 }, addr_len: 28) = 64
  #
  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat tools/perf/examples/bpf/hello.c
  #include <stdio.h>

  int syscall_enter(openat)(void *args)
  {
	  puts("Hello, world\n");
	  return 0;
  }

  license(GPL);
     0.000 ( 0.008 ms): cat/20054 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
     0.020 ( 0.005 ms): cat/20054 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
     0.176 ( 0.011 ms): cat/20054 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
     0.243 ( 0.006 ms): cat/20054 openat(dfd: CWD, filename: tools/perf/examples/bpf/hello.c) = 3
  #

Now to think how to hook on all syscalls, fallbacking to the non-augmented
raw_syscalls:sys_enter payload.

Probably the best way is to use a BPF_MAP_TYPE_PROG_ARRAY just like
samples/bpf/tracex5_kern.c does.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-nlt60y69o26xi59z5vtpdrj5@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 41 ++++++++++++++++++++++++++++++++++++-----
 1 file changed, 36 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 2b99a02355cf..7ce277d22a91 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -288,6 +288,13 @@ static int perf_evsel__init_augmented_syscall_tp_args(struct perf_evsel *evsel)
 	return __tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64));
 }
 
+static int perf_evsel__init_augmented_syscall_tp_ret(struct perf_evsel *evsel)
+{
+	struct syscall_tp *sc = evsel->priv;
+
+	return __tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap);
+}
+
 static int perf_evsel__init_raw_syscall_tp(struct perf_evsel *evsel, void *handler)
 {
 	evsel->priv = malloc(sizeof(struct syscall_tp));
@@ -3346,12 +3353,8 @@ int cmd_trace(int argc, const char **argv)
 		goto out;
 	}
 
-	if (evsel) {
-		if (perf_evsel__init_augmented_syscall_tp(evsel) ||
-		    perf_evsel__init_augmented_syscall_tp_args(evsel))
-			goto out;
+	if (evsel)
 		trace.syscalls.events.augmented = evsel;
-	}
 
 	err = bpf__setup_stdout(trace.evlist);
 	if (err) {
@@ -3396,6 +3399,34 @@ int cmd_trace(int argc, const char **argv)
 		}
 	}
 
+	/*
+	 * If we are augmenting syscalls, then combine what we put in the
+	 * __augmented_syscalls__ BPF map with what is in the
+	 * syscalls:sys_exit_FOO tracepoints, i.e. just like we do without BPF,
+	 * combining raw_syscalls:sys_enter with raw_syscalls:sys_exit.
+	 *
+	 * We'll switch to look at two BPF maps, one for sys_enter and the
+	 * other for sys_exit when we start augmenting the sys_exit paths with
+	 * buffers that are being copied from kernel to userspace, think 'read'
+	 * syscall.
+	 */
+	if (trace.syscalls.events.augmented) {
+		evsel = trace.syscalls.events.augmented;
+
+		if (perf_evsel__init_augmented_syscall_tp(evsel) ||
+		    perf_evsel__init_augmented_syscall_tp_args(evsel))
+			goto out;
+		evsel->handler = trace__sys_enter;
+
+		evlist__for_each_entry(trace.evlist, evsel) {
+			if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) {
+				perf_evsel__init_augmented_syscall_tp(evsel);
+				perf_evsel__init_augmented_syscall_tp_ret(evsel);
+				evsel->handler = trace__sys_exit;
+			}
+		}
+	}
+
 	if ((argc >= 1) && (strcmp(argv[0], "record") == 0))
 		return trace__record(&trace, argc-1, &argv[1]);
 
-- 
cgit v1.2.3


From d8e75a110df7e3318990c9fb207ae0aa7812895a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 4 Sep 2018 10:43:07 -0300
Subject: perf map: Turn some pr_warning() to pr_debug()

Annoying when using it with --stdio/--stdio2, so just turn them debug,
we can get those using -v.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-t3684lkugnf1w4lwcmpj9ivm@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/map.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 36d0763311ef..3f07a587c8e6 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -320,12 +320,11 @@ int map__load(struct map *map)
 			build_id__sprintf(map->dso->build_id,
 					  sizeof(map->dso->build_id),
 					  sbuild_id);
-			pr_warning("%s with build id %s not found",
-				   name, sbuild_id);
+			pr_debug("%s with build id %s not found", name, sbuild_id);
 		} else
-			pr_warning("Failed to open %s", name);
+			pr_debug("Failed to open %s", name);
 
-		pr_warning(", continuing without symbols\n");
+		pr_debug(", continuing without symbols\n");
 		return -1;
 	} else if (nr == 0) {
 #ifdef HAVE_LIBELF_SUPPORT
@@ -334,12 +333,11 @@ int map__load(struct map *map)
 
 		if (len > sizeof(DSO__DELETED) &&
 		    strcmp(name + real_len + 1, DSO__DELETED) == 0) {
-			pr_warning("%.*s was updated (is prelink enabled?). "
+			pr_debug("%.*s was updated (is prelink enabled?). "
 				"Restart the long running apps that use it!\n",
 				   (int)real_len, name);
 		} else {
-			pr_warning("no symbols found in %s, maybe install "
-				   "a debug package?\n", name);
+			pr_debug("no symbols found in %s, maybe install a debug package?\n", name);
 		}
 #endif
 		return -1;
@@ -701,8 +699,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 		if (verbose >= 2) {
 
 			if (use_browser) {
-				pr_warning("overlapping maps in %s "
-					   "(disable tui for more info)\n",
+				pr_debug("overlapping maps in %s (disable tui for more info)\n",
 					   map->dso->name);
 			} else {
 				fputs("overlapping maps:\n", fp);
-- 
cgit v1.2.3


From 1632936480a53d85ef3012cd9f290e247251cbb9 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 5 Sep 2018 10:47:56 -0300
Subject: perf tests: Fix record+probe_libc_inet_pton.sh without ping's
 debuginfo

When we don't have the iputils-debuginfo package installed, i.e. when we
don't have the DWARF information needed to resolve ping's samples, we
end up failing this 'perf test' entry:

  # perf test ping
  62: probe libc's inet_pton & backtrace it with ping       : Ok
  # rpm -e iputils-debuginfo
  # perf test ping
  62: probe libc's inet_pton & backtrace it with ping       : FAILED!
  #

Fix it to accept "[unknown]" where the symbol + offset, when resolved,
is expected.

I think this will fail in the other arches as well, but since I can't
test now, I'm leaving s390x and ppc cases as-is.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Sandipan Das <sandipan@linux.vnet.ibm.com>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: 7903a7086723 ("perf script: Show symbol offsets by default")
Link: https://lkml.kernel.org/n/tip-hnizqwqrs03vcq1b74yao0f6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/record+probe_libc_inet_pton.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 3013ac8f83d0..cab7b0aea6ea 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -48,7 +48,7 @@ trace_libc_inet_pton_backtrace() {
 	*)
 		eventattr='max-stack=3'
 		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
-		echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+		echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
 	esac
 
-- 
cgit v1.2.3


From 69495d2a52957c415d11312fe37844062a48fd32 Mon Sep 17 00:00:00 2001
From: Taeung Song <treeze.taeung@gmail.com>
Date: Mon, 3 Sep 2018 08:30:07 +0900
Subject: libbpf: Remove the duplicate checking of function storage

After the commit eac7d84519a3 ("tools: libbpf: don't return '.text'
as a program for multi-function programs"), bpf_program__next()
in bpf_object__for_each_program skips the function storage such as .text,
so eliminate the duplicate checking.

Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2abd0f112627..8476da7f2720 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2336,7 +2336,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 		bpf_program__set_expected_attach_type(prog,
 						      expected_attach_type);
 
-		if (!bpf_program__is_function_storage(prog, obj) && !first_prog)
+		if (!first_prog)
 			first_prog = prog;
 	}
 
-- 
cgit v1.2.3


From 19d8f1ad12fd746e60707a58d954980013c7a35a Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian@brauner.io>
Date: Tue, 4 Sep 2018 21:53:52 +0200
Subject: if_link: add IFLA_TARGET_NETNSID alias

This adds IFLA_TARGET_NETNSID as an alias for IFLA_IF_NETNSID for
RTM_*LINK requests.
The new name is clearer and also aligns with the newly introduced
IFA_TARGET_NETNSID propert for RTM_*ADDR requests.

Signed-off-by: Christian Brauner <christian@brauner.io>
Suggested-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_link.h       | 1 +
 tools/include/uapi/linux/if_link.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'tools')

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 43391e2d1153..29d49b989acd 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -161,6 +161,7 @@ enum {
 	IFLA_EVENT,
 	IFLA_NEW_NETNSID,
 	IFLA_IF_NETNSID,
+	IFLA_TARGET_NETNSID = IFLA_IF_NETNSID, /* new alias */
 	IFLA_CARRIER_UP_COUNT,
 	IFLA_CARRIER_DOWN_COUNT,
 	IFLA_NEW_IFINDEX,
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index cf01b6824244..1c73d63068b1 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -161,6 +161,7 @@ enum {
 	IFLA_EVENT,
 	IFLA_NEW_NETNSID,
 	IFLA_IF_NETNSID,
+	IFLA_TARGET_NETNSID = IFLA_IF_NETNSID, /* new alias */
 	IFLA_CARRIER_UP_COUNT,
 	IFLA_CARRIER_DOWN_COUNT,
 	IFLA_NEW_IFINDEX,
-- 
cgit v1.2.3


From ad1242d8a063ceb8c6e1b9c1a63b73ec94fa0295 Mon Sep 17 00:00:00 2001
From: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Date: Mon, 3 Sep 2018 18:05:27 +0200
Subject: selftests/bpf: add missing executables to .gitignore

Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/.gitignore | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 49938d72cf63..4d789c1e5167 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -19,3 +19,7 @@ test_btf
 test_sockmap
 test_lirc_mode2_user
 get_cgroup_id_user
+test_skb_cgroup_id_user
+test_socket_cookie
+test_cgroup_storage
+test_select_reuseport
-- 
cgit v1.2.3


From f5bd3948eb07e76fcd73d0b8ab7b3265be226038 Mon Sep 17 00:00:00 2001
From: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Date: Mon, 3 Sep 2018 19:01:59 +0200
Subject: selftests/bpf/test_progs: do not check errno == 0

The errno man page states: "The value in errno is significant only when
the return value of the call indicated an error..." then it is not correct
to check it, it could be different than zero even if the function
succeeded.

It causes some false positives if errno is set by a previous function.

Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_progs.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 0ef68204c84b..63a671803ed6 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -112,13 +112,13 @@ static void test_pkt_access(void)
 
 	err = bpf_prog_test_run(prog_fd, 100000, &pkt_v4, sizeof(pkt_v4),
 				NULL, NULL, &retval, &duration);
-	CHECK(err || errno || retval, "ipv4",
+	CHECK(err || retval, "ipv4",
 	      "err %d errno %d retval %d duration %d\n",
 	      err, errno, retval, duration);
 
 	err = bpf_prog_test_run(prog_fd, 100000, &pkt_v6, sizeof(pkt_v6),
 				NULL, NULL, &retval, &duration);
-	CHECK(err || errno || retval, "ipv6",
+	CHECK(err || retval, "ipv6",
 	      "err %d errno %d retval %d duration %d\n",
 	      err, errno, retval, duration);
 	bpf_object__close(obj);
@@ -153,14 +153,14 @@ static void test_xdp(void)
 	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
 				buf, &size, &retval, &duration);
 
-	CHECK(err || errno || retval != XDP_TX || size != 74 ||
+	CHECK(err || retval != XDP_TX || size != 74 ||
 	      iph->protocol != IPPROTO_IPIP, "ipv4",
 	      "err %d errno %d retval %d size %d\n",
 	      err, errno, retval, size);
 
 	err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
 				buf, &size, &retval, &duration);
-	CHECK(err || errno || retval != XDP_TX || size != 114 ||
+	CHECK(err || retval != XDP_TX || size != 114 ||
 	      iph6->nexthdr != IPPROTO_IPV6, "ipv6",
 	      "err %d errno %d retval %d size %d\n",
 	      err, errno, retval, size);
@@ -185,13 +185,13 @@ static void test_xdp_adjust_tail(void)
 	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
 				buf, &size, &retval, &duration);
 
-	CHECK(err || errno || retval != XDP_DROP,
+	CHECK(err || retval != XDP_DROP,
 	      "ipv4", "err %d errno %d retval %d size %d\n",
 	      err, errno, retval, size);
 
 	err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
 				buf, &size, &retval, &duration);
-	CHECK(err || errno || retval != XDP_TX || size != 54,
+	CHECK(err || retval != XDP_TX || size != 54,
 	      "ipv6", "err %d errno %d retval %d size %d\n",
 	      err, errno, retval, size);
 	bpf_object__close(obj);
@@ -254,14 +254,14 @@ static void test_l4lb(const char *file)
 
 	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4),
 				buf, &size, &retval, &duration);
-	CHECK(err || errno || retval != 7/*TC_ACT_REDIRECT*/ || size != 54 ||
+	CHECK(err || retval != 7/*TC_ACT_REDIRECT*/ || size != 54 ||
 	      *magic != MAGIC_VAL, "ipv4",
 	      "err %d errno %d retval %d size %d magic %x\n",
 	      err, errno, retval, size, *magic);
 
 	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6),
 				buf, &size, &retval, &duration);
-	CHECK(err || errno || retval != 7/*TC_ACT_REDIRECT*/ || size != 74 ||
+	CHECK(err || retval != 7/*TC_ACT_REDIRECT*/ || size != 74 ||
 	      *magic != MAGIC_VAL, "ipv6",
 	      "err %d errno %d retval %d size %d magic %x\n",
 	      err, errno, retval, size, *magic);
@@ -343,14 +343,14 @@ static void test_xdp_noinline(void)
 
 	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4),
 				buf, &size, &retval, &duration);
-	CHECK(err || errno || retval != 1 || size != 54 ||
+	CHECK(err || retval != 1 || size != 54 ||
 	      *magic != MAGIC_VAL, "ipv4",
 	      "err %d errno %d retval %d size %d magic %x\n",
 	      err, errno, retval, size, *magic);
 
 	err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6),
 				buf, &size, &retval, &duration);
-	CHECK(err || errno || retval != 1 || size != 74 ||
+	CHECK(err || retval != 1 || size != 74 ||
 	      *magic != MAGIC_VAL, "ipv6",
 	      "err %d errno %d retval %d size %d magic %x\n",
 	      err, errno, retval, size, *magic);
-- 
cgit v1.2.3


From 52b7b7843d9523ebc3c60c51c7afc4a45cc10aad Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Wed, 5 Sep 2018 16:58:03 -0700
Subject: tools/bpf: sync kernel uapi header if_link.h to tools

Among others, this header will be used later for
bpftool net support.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/if_link.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index cf01b6824244..43391e2d1153 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -164,6 +164,8 @@ enum {
 	IFLA_CARRIER_UP_COUNT,
 	IFLA_CARRIER_DOWN_COUNT,
 	IFLA_NEW_IFINDEX,
+	IFLA_MIN_MTU,
+	IFLA_MAX_MTU,
 	__IFLA_MAX
 };
 
@@ -334,6 +336,7 @@ enum {
 	IFLA_BRPORT_GROUP_FWD_MASK,
 	IFLA_BRPORT_NEIGH_SUPPRESS,
 	IFLA_BRPORT_ISOLATED,
+	IFLA_BRPORT_BACKUP_PORT,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -459,6 +462,16 @@ enum {
 
 #define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1)
 
+/* XFRM section */
+enum {
+	IFLA_XFRM_UNSPEC,
+	IFLA_XFRM_LINK,
+	IFLA_XFRM_IF_ID,
+	__IFLA_XFRM_MAX
+};
+
+#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1)
+
 enum macsec_validation_type {
 	MACSEC_VALIDATE_DISABLED = 0,
 	MACSEC_VALIDATE_CHECK = 1,
@@ -920,6 +933,7 @@ enum {
 	XDP_ATTACHED_DRV,
 	XDP_ATTACHED_SKB,
 	XDP_ATTACHED_HW,
+	XDP_ATTACHED_MULTI,
 };
 
 enum {
@@ -928,6 +942,9 @@ enum {
 	IFLA_XDP_ATTACHED,
 	IFLA_XDP_FLAGS,
 	IFLA_XDP_PROG_ID,
+	IFLA_XDP_DRV_PROG_ID,
+	IFLA_XDP_SKB_PROG_ID,
+	IFLA_XDP_HW_PROG_ID,
 	__IFLA_XDP_MAX,
 };
 
-- 
cgit v1.2.3


From f7010770fbac47b1fc9fb723b1d2019eb23c04f2 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Wed, 5 Sep 2018 16:58:04 -0700
Subject: tools/bpf: move bpf/lib netlink related functions into a new file

There are no functionality change for this patch.

In the subsequent patches, more netlink related library functions
will be added and a separate file is better than cluttering bpf.c.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/Build     |   2 +-
 tools/lib/bpf/bpf.c     | 129 -------------------------------------
 tools/lib/bpf/netlink.c | 165 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 166 insertions(+), 130 deletions(-)
 create mode 100644 tools/lib/bpf/netlink.c

(limited to 'tools')

diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 13a861135127..512b2c0ba0d2 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o netlink.o
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 60aa4ca8b2c5..3878a26a2071 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -28,16 +28,8 @@
 #include <linux/bpf.h>
 #include "bpf.h"
 #include "libbpf.h"
-#include "nlattr.h"
-#include <linux/rtnetlink.h>
-#include <linux/if_link.h>
-#include <sys/socket.h>
 #include <errno.h>
 
-#ifndef SOL_NETLINK
-#define SOL_NETLINK 270
-#endif
-
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
  * required to be defined explicitly.
@@ -499,127 +491,6 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 	return sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
 }
 
-int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
-{
-	struct sockaddr_nl sa;
-	int sock, seq = 0, len, ret = -1;
-	char buf[4096];
-	struct nlattr *nla, *nla_xdp;
-	struct {
-		struct nlmsghdr  nh;
-		struct ifinfomsg ifinfo;
-		char             attrbuf[64];
-	} req;
-	struct nlmsghdr *nh;
-	struct nlmsgerr *err;
-	socklen_t addrlen;
-	int one = 1;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.nl_family = AF_NETLINK;
-
-	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
-	if (sock < 0) {
-		return -errno;
-	}
-
-	if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
-		       &one, sizeof(one)) < 0) {
-		fprintf(stderr, "Netlink error reporting not supported\n");
-	}
-
-	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
-		ret = -errno;
-		goto cleanup;
-	}
-
-	addrlen = sizeof(sa);
-	if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) {
-		ret = -errno;
-		goto cleanup;
-	}
-
-	if (addrlen != sizeof(sa)) {
-		ret = -LIBBPF_ERRNO__INTERNAL;
-		goto cleanup;
-	}
-
-	memset(&req, 0, sizeof(req));
-	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
-	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
-	req.nh.nlmsg_type = RTM_SETLINK;
-	req.nh.nlmsg_pid = 0;
-	req.nh.nlmsg_seq = ++seq;
-	req.ifinfo.ifi_family = AF_UNSPEC;
-	req.ifinfo.ifi_index = ifindex;
-
-	/* started nested attribute for XDP */
-	nla = (struct nlattr *)(((char *)&req)
-				+ NLMSG_ALIGN(req.nh.nlmsg_len));
-	nla->nla_type = NLA_F_NESTED | IFLA_XDP;
-	nla->nla_len = NLA_HDRLEN;
-
-	/* add XDP fd */
-	nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-	nla_xdp->nla_type = IFLA_XDP_FD;
-	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
-	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
-	nla->nla_len += nla_xdp->nla_len;
-
-	/* if user passed in any flags, add those too */
-	if (flags) {
-		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-		nla_xdp->nla_type = IFLA_XDP_FLAGS;
-		nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
-		memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
-		nla->nla_len += nla_xdp->nla_len;
-	}
-
-	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
-
-	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
-		ret = -errno;
-		goto cleanup;
-	}
-
-	len = recv(sock, buf, sizeof(buf), 0);
-	if (len < 0) {
-		ret = -errno;
-		goto cleanup;
-	}
-
-	for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
-	     nh = NLMSG_NEXT(nh, len)) {
-		if (nh->nlmsg_pid != sa.nl_pid) {
-			ret = -LIBBPF_ERRNO__WRNGPID;
-			goto cleanup;
-		}
-		if (nh->nlmsg_seq != seq) {
-			ret = -LIBBPF_ERRNO__INVSEQ;
-			goto cleanup;
-		}
-		switch (nh->nlmsg_type) {
-		case NLMSG_ERROR:
-			err = (struct nlmsgerr *)NLMSG_DATA(nh);
-			if (!err->error)
-				continue;
-			ret = err->error;
-			nla_dump_errormsg(nh);
-			goto cleanup;
-		case NLMSG_DONE:
-			break;
-		default:
-			break;
-		}
-	}
-
-	ret = 0;
-
-cleanup:
-	close(sock);
-	return ret;
-}
-
 int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
 		 bool do_log)
 {
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
new file mode 100644
index 000000000000..ccaa991fe9d8
--- /dev/null
+++ b/tools/lib/bpf/netlink.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: LGPL-2.1
+/* Copyright (c) 2018 Facebook */
+
+#include <stdlib.h>
+#include <memory.h>
+#include <unistd.h>
+#include <linux/bpf.h>
+#include <linux/rtnetlink.h>
+#include <sys/socket.h>
+#include <errno.h>
+#include <time.h>
+
+#include "bpf.h"
+#include "libbpf.h"
+#include "nlattr.h"
+
+#ifndef SOL_NETLINK
+#define SOL_NETLINK 270
+#endif
+
+static int bpf_netlink_open(__u32 *nl_pid)
+{
+	struct sockaddr_nl sa;
+	socklen_t addrlen;
+	int one = 1, ret;
+	int sock;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.nl_family = AF_NETLINK;
+
+	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (sock < 0)
+		return -errno;
+
+	if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
+		       &one, sizeof(one)) < 0) {
+		fprintf(stderr, "Netlink error reporting not supported\n");
+	}
+
+	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
+		ret = -errno;
+		goto cleanup;
+	}
+
+	addrlen = sizeof(sa);
+	if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) {
+		ret = -errno;
+		goto cleanup;
+	}
+
+	if (addrlen != sizeof(sa)) {
+		ret = -LIBBPF_ERRNO__INTERNAL;
+		goto cleanup;
+	}
+
+	*nl_pid = sa.nl_pid;
+	return sock;
+
+cleanup:
+	close(sock);
+	return ret;
+}
+
+static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq)
+{
+	struct nlmsgerr *err;
+	struct nlmsghdr *nh;
+	char buf[4096];
+	int len, ret;
+
+	while (1) {
+		len = recv(sock, buf, sizeof(buf), 0);
+		if (len < 0) {
+			ret = -errno;
+			goto done;
+		}
+
+		for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
+		     nh = NLMSG_NEXT(nh, len)) {
+			if (nh->nlmsg_pid != nl_pid) {
+				ret = -LIBBPF_ERRNO__WRNGPID;
+				goto done;
+			}
+			if (nh->nlmsg_seq != seq) {
+				ret = -LIBBPF_ERRNO__INVSEQ;
+				goto done;
+			}
+			switch (nh->nlmsg_type) {
+			case NLMSG_ERROR:
+				err = (struct nlmsgerr *)NLMSG_DATA(nh);
+				if (!err->error)
+					continue;
+				ret = err->error;
+				nla_dump_errormsg(nh);
+				goto done;
+			case NLMSG_DONE:
+				return 0;
+			default:
+				break;
+			}
+		}
+	}
+	ret = 0;
+done:
+	return ret;
+}
+
+int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+{
+	int sock, seq = 0, ret;
+	struct nlattr *nla, *nla_xdp;
+	struct {
+		struct nlmsghdr  nh;
+		struct ifinfomsg ifinfo;
+		char             attrbuf[64];
+	} req;
+	__u32 nl_pid;
+
+	sock = bpf_netlink_open(&nl_pid);
+	if (sock < 0)
+		return sock;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_type = RTM_SETLINK;
+	req.nh.nlmsg_pid = 0;
+	req.nh.nlmsg_seq = ++seq;
+	req.ifinfo.ifi_family = AF_UNSPEC;
+	req.ifinfo.ifi_index = ifindex;
+
+	/* started nested attribute for XDP */
+	nla = (struct nlattr *)(((char *)&req)
+				+ NLMSG_ALIGN(req.nh.nlmsg_len));
+	nla->nla_type = NLA_F_NESTED | IFLA_XDP;
+	nla->nla_len = NLA_HDRLEN;
+
+	/* add XDP fd */
+	nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+	nla_xdp->nla_type = IFLA_XDP_FD;
+	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
+	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
+	nla->nla_len += nla_xdp->nla_len;
+
+	/* if user passed in any flags, add those too */
+	if (flags) {
+		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+		nla_xdp->nla_type = IFLA_XDP_FLAGS;
+		nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
+		memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
+		nla->nla_len += nla_xdp->nla_len;
+	}
+
+	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
+
+	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		ret = -errno;
+		goto cleanup;
+	}
+	ret = bpf_netlink_recv(sock, nl_pid, seq);
+
+cleanup:
+	close(sock);
+	return ret;
+}
-- 
cgit v1.2.3


From 36f1678d9e0b5d2e0236046d9659e0348b4719a8 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Wed, 5 Sep 2018 16:58:05 -0700
Subject: tools/bpf: add more netlink functionalities in lib/bpf

This patch added a few netlink attribute parsing functions
and the netlink API functions to query networking links, tc classes,
tc qdiscs and tc filters. For example, the following API is
to get networking links:
  int nl_get_link(int sock, unsigned int nl_pid,
                  dump_nlmsg_t dump_link_nlmsg,
                  void *cookie);

Note that when the API is called, the user also provided a
callback function with the following signature:
  int (*dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);

The "cookie" is the parameter the user passed to the API and will
be available for the callback function.
The "msg" is the information about the result, e.g., ifinfomsg or
tcmsg. The "tb" is the parsed netlink attributes.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.h       |  16 +++++
 tools/lib/bpf/libbpf_errno.c |   1 +
 tools/lib/bpf/netlink.c      | 165 ++++++++++++++++++++++++++++++++++++++++++-
 tools/lib/bpf/nlattr.c       |  33 +++++----
 tools/lib/bpf/nlattr.h       |  38 ++++++++++
 5 files changed, 238 insertions(+), 15 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 96c55fac54c3..e3b00e23e181 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -46,6 +46,7 @@ enum libbpf_errno {
 	LIBBPF_ERRNO__PROGTYPE,	/* Kernel doesn't support this program type */
 	LIBBPF_ERRNO__WRNGPID,	/* Wrong pid in netlink message */
 	LIBBPF_ERRNO__INVSEQ,	/* Invalid netlink sequence */
+	LIBBPF_ERRNO__NLPARSE,	/* netlink parsing error */
 	__LIBBPF_ERRNO__END,
 };
 
@@ -297,4 +298,19 @@ int bpf_perf_event_read_simple(void *mem, unsigned long size,
 			       unsigned long page_size,
 			       void **buf, size_t *buf_len,
 			       bpf_perf_event_print_t fn, void *priv);
+
+struct nlmsghdr;
+struct nlattr;
+typedef int (*dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
+typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, dump_nlmsg_t,
+			      void *cookie);
+int bpf_netlink_open(unsigned int *nl_pid);
+int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg,
+		void *cookie);
+int nl_get_class(int sock, unsigned int nl_pid, int ifindex,
+		 dump_nlmsg_t dump_class_nlmsg, void *cookie);
+int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
+		 dump_nlmsg_t dump_qdisc_nlmsg, void *cookie);
+int nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
+		  dump_nlmsg_t dump_filter_nlmsg, void *cookie);
 #endif
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
index d9ba851bd7f9..2464ade3b326 100644
--- a/tools/lib/bpf/libbpf_errno.c
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -42,6 +42,7 @@ static const char *libbpf_strerror_table[NR_ERRNO] = {
 	[ERRCODE_OFFSET(PROGTYPE)]	= "Kernel doesn't support this program type",
 	[ERRCODE_OFFSET(WRNGPID)]	= "Wrong pid in netlink message",
 	[ERRCODE_OFFSET(INVSEQ)]	= "Invalid netlink sequence",
+	[ERRCODE_OFFSET(NLPARSE)]	= "Incorrect netlink message parsing",
 };
 
 int libbpf_strerror(int err, char *buf, size_t size)
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index ccaa991fe9d8..469e068dd0c5 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -18,7 +18,7 @@
 #define SOL_NETLINK 270
 #endif
 
-static int bpf_netlink_open(__u32 *nl_pid)
+int bpf_netlink_open(__u32 *nl_pid)
 {
 	struct sockaddr_nl sa;
 	socklen_t addrlen;
@@ -61,7 +61,9 @@ cleanup:
 	return ret;
 }
 
-static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq)
+static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
+			    __dump_nlmsg_t _fn, dump_nlmsg_t fn,
+			    void *cookie)
 {
 	struct nlmsgerr *err;
 	struct nlmsghdr *nh;
@@ -98,6 +100,11 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq)
 			default:
 				break;
 			}
+			if (_fn) {
+				ret = _fn(nh, fn, cookie);
+				if (ret)
+					return ret;
+			}
 		}
 	}
 	ret = 0;
@@ -157,9 +164,161 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 		ret = -errno;
 		goto cleanup;
 	}
-	ret = bpf_netlink_recv(sock, nl_pid, seq);
+	ret = bpf_netlink_recv(sock, nl_pid, seq, NULL, NULL, NULL);
 
 cleanup:
 	close(sock);
 	return ret;
 }
+
+static int __dump_link_nlmsg(struct nlmsghdr *nlh, dump_nlmsg_t dump_link_nlmsg,
+			     void *cookie)
+{
+	struct nlattr *tb[IFLA_MAX + 1], *attr;
+	struct ifinfomsg *ifi = NLMSG_DATA(nlh);
+	int len;
+
+	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi));
+	attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi)));
+	if (nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0)
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	return dump_link_nlmsg(cookie, ifi, tb);
+}
+
+int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg,
+		void *cookie)
+{
+	struct {
+		struct nlmsghdr nlh;
+		struct ifinfomsg ifm;
+	} req = {
+		.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
+		.nlh.nlmsg_type = RTM_GETLINK,
+		.nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+		.ifm.ifi_family = AF_PACKET,
+	};
+	int seq = time(NULL);
+
+	req.nlh.nlmsg_seq = seq;
+	if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+		return -errno;
+
+	return bpf_netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg,
+				dump_link_nlmsg, cookie);
+}
+
+static int __dump_class_nlmsg(struct nlmsghdr *nlh,
+			      dump_nlmsg_t dump_class_nlmsg, void *cookie)
+{
+	struct nlattr *tb[TCA_MAX + 1], *attr;
+	struct tcmsg *t = NLMSG_DATA(nlh);
+	int len;
+
+	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
+	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
+	if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	return dump_class_nlmsg(cookie, t, tb);
+}
+
+int nl_get_class(int sock, unsigned int nl_pid, int ifindex,
+		 dump_nlmsg_t dump_class_nlmsg, void *cookie)
+{
+	struct {
+		struct nlmsghdr nlh;
+		struct tcmsg t;
+	} req = {
+		.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)),
+		.nlh.nlmsg_type = RTM_GETTCLASS,
+		.nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+		.t.tcm_family = AF_UNSPEC,
+		.t.tcm_ifindex = ifindex,
+	};
+	int seq = time(NULL);
+
+	req.nlh.nlmsg_seq = seq;
+	if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+		return -errno;
+
+	return bpf_netlink_recv(sock, nl_pid, seq, __dump_class_nlmsg,
+				dump_class_nlmsg, cookie);
+}
+
+static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh,
+			      dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
+{
+	struct nlattr *tb[TCA_MAX + 1], *attr;
+	struct tcmsg *t = NLMSG_DATA(nlh);
+	int len;
+
+	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
+	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
+	if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	return dump_qdisc_nlmsg(cookie, t, tb);
+}
+
+int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
+		 dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
+{
+	struct {
+		struct nlmsghdr nlh;
+		struct tcmsg t;
+	} req = {
+		.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)),
+		.nlh.nlmsg_type = RTM_GETQDISC,
+		.nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+		.t.tcm_family = AF_UNSPEC,
+		.t.tcm_ifindex = ifindex,
+	};
+	int seq = time(NULL);
+
+	req.nlh.nlmsg_seq = seq;
+	if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+		return -errno;
+
+	return bpf_netlink_recv(sock, nl_pid, seq, __dump_qdisc_nlmsg,
+				dump_qdisc_nlmsg, cookie);
+}
+
+static int __dump_filter_nlmsg(struct nlmsghdr *nlh,
+			       dump_nlmsg_t dump_filter_nlmsg, void *cookie)
+{
+	struct nlattr *tb[TCA_MAX + 1], *attr;
+	struct tcmsg *t = NLMSG_DATA(nlh);
+	int len;
+
+	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
+	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
+	if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	return dump_filter_nlmsg(cookie, t, tb);
+}
+
+int nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
+		  dump_nlmsg_t dump_filter_nlmsg, void *cookie)
+{
+	struct {
+		struct nlmsghdr nlh;
+		struct tcmsg t;
+	} req = {
+		.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)),
+		.nlh.nlmsg_type = RTM_GETTFILTER,
+		.nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+		.t.tcm_family = AF_UNSPEC,
+		.t.tcm_ifindex = ifindex,
+		.t.tcm_parent = handle,
+	};
+	int seq = time(NULL);
+
+	req.nlh.nlmsg_seq = seq;
+	if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+		return -errno;
+
+	return bpf_netlink_recv(sock, nl_pid, seq, __dump_filter_nlmsg,
+				dump_filter_nlmsg, cookie);
+}
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
index 4719434278b2..49f514119bdb 100644
--- a/tools/lib/bpf/nlattr.c
+++ b/tools/lib/bpf/nlattr.c
@@ -26,11 +26,6 @@ static uint16_t nla_attr_minlen[NLA_TYPE_MAX+1] = {
 	[NLA_FLAG]	= 0,
 };
 
-static int nla_len(const struct nlattr *nla)
-{
-	return nla->nla_len - NLA_HDRLEN;
-}
-
 static struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
 {
 	int totlen = NLA_ALIGN(nla->nla_len);
@@ -46,11 +41,6 @@ static int nla_ok(const struct nlattr *nla, int remaining)
 	       nla->nla_len <= remaining;
 }
 
-static void *nla_data(const struct nlattr *nla)
-{
-	return (char *) nla + NLA_HDRLEN;
-}
-
 static int nla_type(const struct nlattr *nla)
 {
 	return nla->nla_type & NLA_TYPE_MASK;
@@ -114,8 +104,8 @@ static inline int nlmsg_len(const struct nlmsghdr *nlh)
  * @see nla_validate
  * @return 0 on success or a negative error code.
  */
-static int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
-		     struct nla_policy *policy)
+int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
+	      struct nla_policy *policy)
 {
 	struct nlattr *nla;
 	int rem, err;
@@ -146,6 +136,25 @@ errout:
 	return err;
 }
 
+/**
+ * Create attribute index based on nested attribute
+ * @arg tb              Index array to be filled (maxtype+1 elements).
+ * @arg maxtype         Maximum attribute type expected and accepted.
+ * @arg nla             Nested Attribute.
+ * @arg policy          Attribute validation policy.
+ *
+ * Feeds the stream of attributes nested into the specified attribute
+ * to nla_parse().
+ *
+ * @see nla_parse
+ * @return 0 on success or a negative error code.
+ */
+int nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
+		     struct nla_policy *policy)
+{
+	return nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy);
+}
+
 /* dump netlink extended ack error message */
 int nla_dump_errormsg(struct nlmsghdr *nlh)
 {
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
index 931a71f68f93..a6e2396bce7c 100644
--- a/tools/lib/bpf/nlattr.h
+++ b/tools/lib/bpf/nlattr.h
@@ -67,6 +67,44 @@ struct nla_policy {
 	     nla_ok(pos, rem); \
 	     pos = nla_next(pos, &(rem)))
 
+/**
+ * nla_data - head of payload
+ * @nla: netlink attribute
+ */
+static inline void *nla_data(const struct nlattr *nla)
+{
+	return (char *) nla + NLA_HDRLEN;
+}
+
+static inline uint8_t nla_getattr_u8(const struct nlattr *nla)
+{
+	return *(uint8_t *)nla_data(nla);
+}
+
+static inline uint32_t nla_getattr_u32(const struct nlattr *nla)
+{
+	return *(uint32_t *)nla_data(nla);
+}
+
+static inline const char *nla_getattr_str(const struct nlattr *nla)
+{
+	return (const char *)nla_data(nla);
+}
+
+/**
+ * nla_len - length of payload
+ * @nla: netlink attribute
+ */
+static inline int nla_len(const struct nlattr *nla)
+{
+	return nla->nla_len - NLA_HDRLEN;
+}
+
+int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
+	      struct nla_policy *policy);
+int nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
+		     struct nla_policy *policy);
+
 int nla_dump_errormsg(struct nlmsghdr *nlh);
 
 #endif /* __NLATTR_H */
-- 
cgit v1.2.3


From f6f3bac08ff9855d803081a353a1fafaa8845739 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Wed, 5 Sep 2018 16:58:06 -0700
Subject: tools/bpf: bpftool: add net support

Add "bpftool net" support. Networking devices are enumerated
to dump device index/name associated with xdp progs.

For each networking device, tc classes and qdiscs are enumerated
in order to check their bpf filters.
In addition, root handle and clsact ingress/egress are also checked for
bpf filters.  Not all filter information is printed out. Only ifindex,
kind, filter name, prog_id and tag are printed out, which are good
enough to show attachment information. If the filter action
is a bpf action, its bpf program id, bpf name and tag will be
printed out as well.

For example,
  $ ./bpftool net
  xdp [
  ifindex 2 devname eth0 prog_id 198
  ]
  tc_filters [
  ifindex 2 kind qdisc_htb name prefix_matcher.o:[cls_prefix_matcher_htb]
            prog_id 111727 tag d08fe3b4319bc2fd act []
  ifindex 2 kind qdisc_clsact_ingress name fbflow_icmp
            prog_id 130246 tag 3f265c7f26db62c9 act []
  ifindex 2 kind qdisc_clsact_egress name prefix_matcher.o:[cls_prefix_matcher_clsact]
            prog_id 111726 tag 99a197826974c876
  ifindex 2 kind qdisc_clsact_egress name cls_fg_dscp
            prog_id 108619 tag dc4630674fd72dcc act []
  ifindex 2 kind qdisc_clsact_egress name fbflow_egress
            prog_id 130245 tag 72d2d830d6888d2c
  ]
  $ ./bpftool -jp net
  [{
        "xdp": [{
                "ifindex": 2,
                "devname": "eth0",
                "prog_id": 198
            }
        ],
        "tc_filters": [{
                "ifindex": 2,
                "kind": "qdisc_htb",
                "name": "prefix_matcher.o:[cls_prefix_matcher_htb]",
                "prog_id": 111727,
                "tag": "d08fe3b4319bc2fd",
                "act": []
            },{
                "ifindex": 2,
                "kind": "qdisc_clsact_ingress",
                "name": "fbflow_icmp",
                "prog_id": 130246,
                "tag": "3f265c7f26db62c9",
                "act": []
            },{
                "ifindex": 2,
                "kind": "qdisc_clsact_egress",
                "name": "prefix_matcher.o:[cls_prefix_matcher_clsact]",
                "prog_id": 111726,
                "tag": "99a197826974c876"
            },{
                "ifindex": 2,
                "kind": "qdisc_clsact_egress",
                "name": "cls_fg_dscp",
                "prog_id": 108619,
                "tag": "dc4630674fd72dcc",
                "act": []
            },{
                "ifindex": 2,
                "kind": "qdisc_clsact_egress",
                "name": "fbflow_egress",
                "prog_id": 130245,
                "tag": "72d2d830d6888d2c"
            }
        ]
    }
  ]

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/Documentation/bpftool-net.rst | 133 ++++++++++++++
 tools/bpf/bpftool/Documentation/bpftool.rst     |   6 +-
 tools/bpf/bpftool/bash-completion/bpftool       |  17 +-
 tools/bpf/bpftool/main.c                        |   3 +-
 tools/bpf/bpftool/main.h                        |   7 +
 tools/bpf/bpftool/net.c                         | 233 ++++++++++++++++++++++++
 tools/bpf/bpftool/netlink_dumper.c              | 181 ++++++++++++++++++
 tools/bpf/bpftool/netlink_dumper.h              | 103 +++++++++++
 8 files changed, 676 insertions(+), 7 deletions(-)
 create mode 100644 tools/bpf/bpftool/Documentation/bpftool-net.rst
 create mode 100644 tools/bpf/bpftool/net.c
 create mode 100644 tools/bpf/bpftool/netlink_dumper.c
 create mode 100644 tools/bpf/bpftool/netlink_dumper.h

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst
new file mode 100644
index 000000000000..48a61837a264
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst
@@ -0,0 +1,133 @@
+================
+bpftool-net
+================
+-------------------------------------------------------------------------------
+tool for inspection of netdev/tc related bpf prog attachments
+-------------------------------------------------------------------------------
+
+:Manual section: 8
+
+SYNOPSIS
+========
+
+	**bpftool** [*OPTIONS*] **net** *COMMAND*
+
+	*OPTIONS* := { [{ **-j** | **--json** }] [{ **-p** | **--pretty** }] }
+
+	*COMMANDS* :=
+	{ **show** | **list** } [ **dev** name ] | **help**
+
+NET COMMANDS
+============
+
+|	**bpftool** **net { show | list } [ dev name ]**
+|	**bpftool** **net help**
+
+DESCRIPTION
+===========
+	**bpftool net { show | list } [ dev name ]**
+		  List all networking device driver and tc attachment in the system.
+
+                  Output will start with all xdp program attachment, followed by
+                  all tc class/qdisc bpf program attachments. Both xdp programs and
+                  tc programs are ordered based on ifindex number. If multiple bpf
+                  programs attached to the same networking device through **tc filter**,
+                  the order will be first all bpf programs attached to tc classes, then
+                  all bpf programs attached to non clsact qdiscs, and finally all
+                  bpf programs attached to root and clsact qdisc.
+
+	**bpftool net help**
+		  Print short help message.
+
+OPTIONS
+=======
+	-h, --help
+		  Print short generic help message (similar to **bpftool help**).
+
+	-v, --version
+		  Print version number (similar to **bpftool version**).
+
+	-j, --json
+		  Generate JSON output. For commands that cannot produce JSON, this
+		  option has no effect.
+
+	-p, --pretty
+		  Generate human-readable JSON output. Implies **-j**.
+
+EXAMPLES
+========
+
+| **# bpftool net**
+
+::
+
+      xdp [
+      ifindex 2 devname eth0 prog_id 198
+      ]
+      tc_filters [
+      ifindex 2 kind qdisc_htb name prefix_matcher.o:[cls_prefix_matcher_htb]
+                prog_id 111727 tag d08fe3b4319bc2fd act []
+      ifindex 2 kind qdisc_clsact_ingress name fbflow_icmp
+                prog_id 130246 tag 3f265c7f26db62c9 act []
+      ifindex 2 kind qdisc_clsact_egress name prefix_matcher.o:[cls_prefix_matcher_clsact]
+                prog_id 111726 tag 99a197826974c876
+      ifindex 2 kind qdisc_clsact_egress name cls_fg_dscp
+                prog_id 108619 tag dc4630674fd72dcc act []
+      ifindex 2 kind qdisc_clsact_egress name fbflow_egress
+                prog_id 130245 tag 72d2d830d6888d2c
+      ]
+
+|
+| **# bpftool -jp net**
+
+::
+
+    [{
+            "xdp": [{
+                    "ifindex": 2,
+                    "devname": "eth0",
+                    "prog_id": 198
+                }
+            ],
+            "tc_filters": [{
+                    "ifindex": 2,
+                    "kind": "qdisc_htb",
+                    "name": "prefix_matcher.o:[cls_prefix_matcher_htb]",
+                    "prog_id": 111727,
+                    "tag": "d08fe3b4319bc2fd",
+                    "act": []
+                },{
+                    "ifindex": 2,
+                    "kind": "qdisc_clsact_ingress",
+                    "name": "fbflow_icmp",
+                    "prog_id": 130246,
+                    "tag": "3f265c7f26db62c9",
+                    "act": []
+                },{
+                    "ifindex": 2,
+                    "kind": "qdisc_clsact_egress",
+                    "name": "prefix_matcher.o:[cls_prefix_matcher_clsact]",
+                    "prog_id": 111726,
+                    "tag": "99a197826974c876"
+                },{
+                    "ifindex": 2,
+                    "kind": "qdisc_clsact_egress",
+                    "name": "cls_fg_dscp",
+                    "prog_id": 108619,
+                    "tag": "dc4630674fd72dcc",
+                    "act": []
+                },{
+                    "ifindex": 2,
+                    "kind": "qdisc_clsact_egress",
+                    "name": "fbflow_egress",
+                    "prog_id": 130245,
+                    "tag": "72d2d830d6888d2c"
+                }
+            ]
+        }
+    ]
+
+
+SEE ALSO
+========
+	**bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index b6f5d560460d..8dda77daeda9 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -16,7 +16,7 @@ SYNOPSIS
 
 	**bpftool** **version**
 
-	*OBJECT* := { **map** | **program** | **cgroup** | **perf** }
+	*OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** }
 
 	*OPTIONS* := { { **-V** | **--version** } | { **-h** | **--help** }
 	| { **-j** | **--json** } [{ **-p** | **--pretty** }] }
@@ -32,6 +32,8 @@ SYNOPSIS
 
 	*PERF-COMMANDS* := { **show** | **list** | **help** }
 
+	*NET-COMMANDS* := { **show** | **list** | **help** }
+
 DESCRIPTION
 ===========
 	*bpftool* allows for inspection and simple modification of BPF objects
@@ -58,4 +60,4 @@ OPTIONS
 SEE ALSO
 ========
 	**bpftool-map**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8)
-        **bpftool-perf**\ (8)
+        **bpftool-perf**\ (8), **bpftool-net**\ (8)
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 598066c40191..df1060b852c1 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -494,10 +494,10 @@ _bpftool()
                     _filedir
                     return 0
                     ;;
-		tree)
-		    _filedir
-		    return 0
-		    ;;
+                tree)
+                    _filedir
+                    return 0
+                    ;;
                 attach|detach)
                     local ATTACH_TYPES='ingress egress sock_create sock_ops \
                         device bind4 bind6 post_bind4 post_bind6 connect4 \
@@ -552,6 +552,15 @@ _bpftool()
                     ;;
             esac
             ;;
+        net)
+            case $command in
+                *)
+                    [[ $prev == $object ]] && \
+                        COMPREPLY=( $( compgen -W 'help \
+                            show list' -- "$cur" ) )
+                    ;;
+            esac
+            ;;
     esac
 } &&
 complete -F _bpftool bpftool
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index d15a62be6cf0..79dc3f193547 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -85,7 +85,7 @@ static int do_help(int argc, char **argv)
 		"       %s batch file FILE\n"
 		"       %s version\n"
 		"\n"
-		"       OBJECT := { prog | map | cgroup | perf }\n"
+		"       OBJECT := { prog | map | cgroup | perf | net }\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",
 		bin_name, bin_name, bin_name);
@@ -215,6 +215,7 @@ static const struct cmd cmds[] = {
 	{ "map",	do_map },
 	{ "cgroup",	do_cgroup },
 	{ "perf",	do_perf },
+	{ "net",	do_net },
 	{ "version",	do_version },
 	{ 0 }
 };
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 238e734d75b3..02dfbcb92a23 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -136,6 +136,7 @@ int do_map(int argc, char **arg);
 int do_event_pipe(int argc, char **argv);
 int do_cgroup(int argc, char **arg);
 int do_perf(int argc, char **arg);
+int do_net(int argc, char **arg);
 
 int prog_parse_fd(int *argc, char ***argv);
 int map_parse_fd(int *argc, char ***argv);
@@ -165,4 +166,10 @@ struct btf_dumper {
  */
 int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
 		    const void *data);
+
+struct nlattr;
+struct ifinfomsg;
+struct tcmsg;
+int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb);
+int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind);
 #endif
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
new file mode 100644
index 000000000000..77dd73dd9ade
--- /dev/null
+++ b/tools/bpf/bpftool/net.c
@@ -0,0 +1,233 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (C) 2018 Facebook
+
+#define _GNU_SOURCE
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <libbpf.h>
+#include <net/if.h>
+#include <linux/if.h>
+#include <linux/rtnetlink.h>
+#include <linux/tc_act/tc_bpf.h>
+#include <sys/socket.h>
+
+#include <bpf.h>
+#include <nlattr.h>
+#include "main.h"
+#include "netlink_dumper.h"
+
+struct bpf_netdev_t {
+	int	*ifindex_array;
+	int	used_len;
+	int	array_len;
+	int	filter_idx;
+};
+
+struct tc_kind_handle {
+	char	kind[64];
+	int	handle;
+};
+
+struct bpf_tcinfo_t {
+	struct tc_kind_handle	*handle_array;
+	int			used_len;
+	int			array_len;
+	bool			is_qdisc;
+};
+
+static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb)
+{
+	struct bpf_netdev_t *netinfo = cookie;
+	struct ifinfomsg *ifinfo = msg;
+
+	if (netinfo->filter_idx > 0 && netinfo->filter_idx != ifinfo->ifi_index)
+		return 0;
+
+	if (netinfo->used_len == netinfo->array_len) {
+		netinfo->ifindex_array = realloc(netinfo->ifindex_array,
+			(netinfo->array_len + 16) * sizeof(int));
+		netinfo->array_len += 16;
+	}
+	netinfo->ifindex_array[netinfo->used_len++] = ifinfo->ifi_index;
+
+	return do_xdp_dump(ifinfo, tb);
+}
+
+static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
+{
+	struct bpf_tcinfo_t *tcinfo = cookie;
+	struct tcmsg *info = msg;
+
+	if (tcinfo->is_qdisc) {
+		/* skip clsact qdisc */
+		if (tb[TCA_KIND] &&
+		    strcmp(nla_data(tb[TCA_KIND]), "clsact") == 0)
+			return 0;
+		if (info->tcm_handle == 0)
+			return 0;
+	}
+
+	if (tcinfo->used_len == tcinfo->array_len) {
+		tcinfo->handle_array = realloc(tcinfo->handle_array,
+			(tcinfo->array_len + 16) * sizeof(struct tc_kind_handle));
+		tcinfo->array_len += 16;
+	}
+	tcinfo->handle_array[tcinfo->used_len].handle = info->tcm_handle;
+	snprintf(tcinfo->handle_array[tcinfo->used_len].kind,
+		 sizeof(tcinfo->handle_array[tcinfo->used_len].kind),
+		 "%s_%s",
+		 tcinfo->is_qdisc ? "qdisc" : "class",
+		 tb[TCA_KIND] ? nla_getattr_str(tb[TCA_KIND]) : "unknown");
+	tcinfo->used_len++;
+
+	return 0;
+}
+
+static int dump_filter_nlmsg(void *cookie, void *msg, struct nlattr **tb)
+{
+	const char *kind = cookie;
+
+	return do_filter_dump((struct tcmsg *)msg, tb, kind);
+}
+
+static int show_dev_tc_bpf(int sock, unsigned int nl_pid, int ifindex)
+{
+	struct bpf_tcinfo_t tcinfo;
+	int i, handle, ret;
+
+	tcinfo.handle_array = NULL;
+	tcinfo.used_len = 0;
+	tcinfo.array_len = 0;
+
+	tcinfo.is_qdisc = false;
+	ret = nl_get_class(sock, nl_pid, ifindex, dump_class_qdisc_nlmsg,
+			   &tcinfo);
+	if (ret)
+		return ret;
+
+	tcinfo.is_qdisc = true;
+	ret = nl_get_qdisc(sock, nl_pid, ifindex, dump_class_qdisc_nlmsg,
+			   &tcinfo);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < tcinfo.used_len; i++) {
+		ret = nl_get_filter(sock, nl_pid, ifindex,
+				    tcinfo.handle_array[i].handle,
+				    dump_filter_nlmsg,
+				    tcinfo.handle_array[i].kind);
+		if (ret)
+			return ret;
+	}
+
+	/* root, ingress and egress handle */
+	handle = TC_H_ROOT;
+	ret = nl_get_filter(sock, nl_pid, ifindex, handle, dump_filter_nlmsg,
+			    "root");
+	if (ret)
+		return ret;
+
+	handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS);
+	ret = nl_get_filter(sock, nl_pid, ifindex, handle, dump_filter_nlmsg,
+			    "qdisc_clsact_ingress");
+	if (ret)
+		return ret;
+
+	handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_EGRESS);
+	ret = nl_get_filter(sock, nl_pid, ifindex, handle, dump_filter_nlmsg,
+			    "qdisc_clsact_egress");
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int do_show(int argc, char **argv)
+{
+	int i, sock, ret, filter_idx = -1;
+	struct bpf_netdev_t dev_array;
+	unsigned int nl_pid;
+	char err_buf[256];
+
+	if (argc == 2) {
+		if (strcmp(argv[0], "dev") != 0)
+			usage();
+		filter_idx = if_nametoindex(argv[1]);
+		if (filter_idx == 0) {
+			fprintf(stderr, "invalid dev name %s\n", argv[1]);
+			return -1;
+		}
+	} else if (argc != 0) {
+		usage();
+	}
+
+	sock = bpf_netlink_open(&nl_pid);
+	if (sock < 0) {
+		fprintf(stderr, "failed to open netlink sock\n");
+		return -1;
+	}
+
+	dev_array.ifindex_array = NULL;
+	dev_array.used_len = 0;
+	dev_array.array_len = 0;
+	dev_array.filter_idx = filter_idx;
+
+	if (json_output)
+		jsonw_start_array(json_wtr);
+	NET_START_OBJECT;
+	NET_START_ARRAY("xdp", "\n");
+	ret = nl_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array);
+	NET_END_ARRAY("\n");
+
+	if (!ret) {
+		NET_START_ARRAY("tc_filters", "\n");
+		for (i = 0; i < dev_array.used_len; i++) {
+			ret = show_dev_tc_bpf(sock, nl_pid,
+					      dev_array.ifindex_array[i]);
+			if (ret)
+				break;
+		}
+		NET_END_ARRAY("\n");
+	}
+	NET_END_OBJECT;
+	if (json_output)
+		jsonw_end_array(json_wtr);
+
+	if (ret) {
+		if (json_output)
+			jsonw_null(json_wtr);
+		libbpf_strerror(ret, err_buf, sizeof(err_buf));
+		fprintf(stderr, "Error: %s\n", err_buf);
+	}
+	free(dev_array.ifindex_array);
+	close(sock);
+	return ret;
+}
+
+static int do_help(int argc, char **argv)
+{
+	if (json_output) {
+		jsonw_null(json_wtr);
+		return 0;
+	}
+
+	fprintf(stderr,
+		"Usage: %s %s { show | list } [dev <devname>]\n"
+		"       %s %s help\n",
+		bin_name, argv[-2], bin_name, argv[-2]);
+
+	return 0;
+}
+
+static const struct cmd cmds[] = {
+	{ "show",	do_show },
+	{ "list",	do_show },
+	{ "help",	do_help },
+	{ 0 }
+};
+
+int do_net(int argc, char **argv)
+{
+	return cmd_select(cmds, argc, argv, do_help);
+}
diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c
new file mode 100644
index 000000000000..e12494fd1d2e
--- /dev/null
+++ b/tools/bpf/bpftool/netlink_dumper.c
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (C) 2018 Facebook
+
+#include <stdlib.h>
+#include <string.h>
+#include <libbpf.h>
+#include <linux/rtnetlink.h>
+#include <linux/tc_act/tc_bpf.h>
+
+#include <nlattr.h>
+#include "main.h"
+#include "netlink_dumper.h"
+
+static void xdp_dump_prog_id(struct nlattr **tb, int attr,
+			     const char *type)
+{
+	if (!tb[attr])
+		return;
+
+	NET_DUMP_UINT(type, nla_getattr_u32(tb[attr]))
+}
+
+static int do_xdp_dump_one(struct nlattr *attr, unsigned int ifindex,
+			   const char *name)
+{
+	struct nlattr *tb[IFLA_XDP_MAX + 1];
+	unsigned char mode;
+
+	if (nla_parse_nested(tb, IFLA_XDP_MAX, attr, NULL) < 0)
+		return -1;
+
+	if (!tb[IFLA_XDP_ATTACHED])
+		return 0;
+
+	mode = nla_getattr_u8(tb[IFLA_XDP_ATTACHED]);
+	if (mode == XDP_ATTACHED_NONE)
+		return 0;
+
+	NET_START_OBJECT;
+	NET_DUMP_UINT("ifindex", ifindex);
+
+	if (name)
+		NET_DUMP_STR("devname", name);
+
+	if (tb[IFLA_XDP_PROG_ID])
+		NET_DUMP_UINT("prog_id", nla_getattr_u32(tb[IFLA_XDP_PROG_ID]));
+
+	if (mode == XDP_ATTACHED_MULTI) {
+		xdp_dump_prog_id(tb, IFLA_XDP_SKB_PROG_ID, "generic_prog_id");
+		xdp_dump_prog_id(tb, IFLA_XDP_DRV_PROG_ID, "drv_prog_id");
+		xdp_dump_prog_id(tb, IFLA_XDP_HW_PROG_ID, "offload_prog_id");
+	}
+
+	NET_END_OBJECT_FINAL;
+	return 0;
+}
+
+int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb)
+{
+	if (!tb[IFLA_XDP])
+		return 0;
+
+	return do_xdp_dump_one(tb[IFLA_XDP], ifinfo->ifi_index,
+			       nla_getattr_str(tb[IFLA_IFNAME]));
+}
+
+static char *hexstring_n2a(const unsigned char *str, int len,
+			   char *buf, int blen)
+{
+	char *ptr = buf;
+	int i;
+
+	for (i = 0; i < len; i++) {
+		if (blen < 3)
+			break;
+		sprintf(ptr, "%02x", str[i]);
+		ptr += 2;
+		blen -= 2;
+	}
+	return buf;
+}
+
+static int do_bpf_dump_one_act(struct nlattr *attr)
+{
+	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
+	char buf[256];
+
+	if (nla_parse_nested(tb, TCA_ACT_BPF_MAX, attr, NULL) < 0)
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	if (!tb[TCA_ACT_BPF_PARMS])
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	NET_START_OBJECT_NESTED2;
+	if (tb[TCA_ACT_BPF_NAME])
+		NET_DUMP_STR("name", nla_getattr_str(tb[TCA_ACT_BPF_NAME]));
+	if (tb[TCA_ACT_BPF_ID])
+		NET_DUMP_UINT("bpf_id", nla_getattr_u32(tb[TCA_ACT_BPF_ID]));
+	if (tb[TCA_ACT_BPF_TAG])
+		NET_DUMP_STR("tag", hexstring_n2a(nla_data(tb[TCA_ACT_BPF_TAG]),
+						  nla_len(tb[TCA_ACT_BPF_TAG]),
+						  buf, sizeof(buf)));
+	NET_END_OBJECT_NESTED;
+	return 0;
+}
+
+static int do_dump_one_act(struct nlattr *attr)
+{
+	struct nlattr *tb[TCA_ACT_MAX + 1];
+
+	if (!attr)
+		return 0;
+
+	if (nla_parse_nested(tb, TCA_ACT_MAX, attr, NULL) < 0)
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	if (tb[TCA_ACT_KIND] && strcmp(nla_data(tb[TCA_ACT_KIND]), "bpf") == 0)
+		return do_bpf_dump_one_act(tb[TCA_ACT_OPTIONS]);
+
+	return 0;
+}
+
+static int do_bpf_act_dump(struct nlattr *attr)
+{
+	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
+	int act, ret;
+
+	if (nla_parse_nested(tb, TCA_ACT_MAX_PRIO, attr, NULL) < 0)
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	NET_START_ARRAY("act", "");
+	for (act = 0; act <= TCA_ACT_MAX_PRIO; act++) {
+		ret = do_dump_one_act(tb[act]);
+		if (ret)
+			break;
+	}
+	NET_END_ARRAY(" ");
+
+	return ret;
+}
+
+static int do_bpf_filter_dump(struct nlattr *attr)
+{
+	struct nlattr *tb[TCA_BPF_MAX + 1];
+	char buf[256];
+	int ret;
+
+	if (nla_parse_nested(tb, TCA_BPF_MAX, attr, NULL) < 0)
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	if (tb[TCA_BPF_NAME])
+		NET_DUMP_STR("name", nla_getattr_str(tb[TCA_BPF_NAME]));
+	if (tb[TCA_BPF_ID])
+		NET_DUMP_UINT("prog_id", nla_getattr_u32(tb[TCA_BPF_ID]));
+	if (tb[TCA_BPF_TAG])
+		NET_DUMP_STR("tag", hexstring_n2a(nla_data(tb[TCA_BPF_TAG]),
+						  nla_len(tb[TCA_BPF_TAG]),
+						  buf, sizeof(buf)));
+	if (tb[TCA_BPF_ACT]) {
+		ret = do_bpf_act_dump(tb[TCA_BPF_ACT]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+int do_filter_dump(struct tcmsg *info, struct nlattr **tb, const char *kind)
+{
+	int ret = 0;
+
+	if (tb[TCA_OPTIONS] && strcmp(nla_data(tb[TCA_KIND]), "bpf") == 0) {
+		NET_START_OBJECT;
+		NET_DUMP_UINT("ifindex", info->tcm_ifindex);
+		NET_DUMP_STR("kind", kind);
+		ret = do_bpf_filter_dump(tb[TCA_OPTIONS]);
+		NET_END_OBJECT_FINAL;
+	}
+
+	return ret;
+}
diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h
new file mode 100644
index 000000000000..552d8851ac06
--- /dev/null
+++ b/tools/bpf/bpftool/netlink_dumper.h
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (C) 2018 Facebook
+
+#ifndef _NETLINK_DUMPER_H_
+#define _NETLINK_DUMPER_H_
+
+#define NET_START_OBJECT				\
+{							\
+	if (json_output)				\
+		jsonw_start_object(json_wtr);		\
+}
+
+#define NET_START_OBJECT_NESTED(name)			\
+{							\
+	if (json_output) {				\
+		jsonw_name(json_wtr, name);		\
+		jsonw_start_object(json_wtr);		\
+	} else {					\
+		fprintf(stderr, "%s {", name);		\
+	}						\
+}
+
+#define NET_START_OBJECT_NESTED2			\
+{							\
+	if (json_output)				\
+		jsonw_start_object(json_wtr);		\
+	else						\
+		fprintf(stderr, "{");			\
+}
+
+#define NET_END_OBJECT_NESTED				\
+{							\
+	if (json_output)				\
+		jsonw_end_object(json_wtr);		\
+	else						\
+		fprintf(stderr, "}");			\
+}
+
+#define NET_END_OBJECT					\
+{							\
+	if (json_output)				\
+		jsonw_end_object(json_wtr);		\
+}
+
+#define NET_END_OBJECT_FINAL				\
+{							\
+	if (json_output)				\
+		jsonw_end_object(json_wtr);		\
+	else						\
+		fprintf(stderr, "\n");			\
+}
+
+#define NET_START_ARRAY(name, newline)			\
+{							\
+	if (json_output) {				\
+		jsonw_name(json_wtr, name);		\
+		jsonw_start_array(json_wtr);		\
+	} else {					\
+		fprintf(stderr, "%s [%s", name, newline);\
+	}						\
+}
+
+#define NET_END_ARRAY(endstr)				\
+{							\
+	if (json_output)				\
+		jsonw_end_array(json_wtr);		\
+	else						\
+		fprintf(stderr, "]%s", endstr);		\
+}
+
+#define NET_DUMP_UINT(name, val)			\
+{							\
+	if (json_output)				\
+		jsonw_uint_field(json_wtr, name, val);	\
+	else						\
+		fprintf(stderr, "%s %d ", name, val);	\
+}
+
+#define NET_DUMP_LLUINT(name, val)			\
+{							\
+	if (json_output)				\
+		jsonw_lluint_field(json_wtr, name, val);\
+	else						\
+		fprintf(stderr, "%s %lld ", name, val);	\
+}
+
+#define NET_DUMP_STR(name, str)				\
+{							\
+	if (json_output)				\
+		jsonw_string_field(json_wtr, name, str);\
+	else						\
+		fprintf(stderr, "%s %s ", name, str);	\
+}
+
+#define NET_DUMP_STR_ONLY(str)				\
+{							\
+	if (json_output)				\
+		jsonw_string(json_wtr, str);		\
+	else						\
+		fprintf(stderr, "%s ", str);		\
+}
+
+#endif
-- 
cgit v1.2.3


From 4a60aa05a0634241ce17f957bf9fb5ac1eed6576 Mon Sep 17 00:00:00 2001
From: Allan Xavier <allan.x.xavier@oracle.com>
Date: Fri, 7 Sep 2018 08:12:01 -0500
Subject: objtool: Support per-function rodata sections

Add support for processing switch jump tables in objects with multiple
.rodata sections, such as those created by '-ffunction-sections' and
'-fdata-sections'.  Currently, objtool always looks in .rodata for jump
table information, which results in many "sibling call from callable
instruction with modified stack frame" warnings with objects compiled
using those flags.

The fix is comprised of three parts:

1. Flagging all .rodata sections when importing ELF information for
   easier checking later.

2. Keeping a reference to the section each relocation is from in order
   to get the list_head for the other relocations in that section.

3. Finding jump tables by following relocations to .rodata sections,
   rather than always referencing a single global .rodata section.

The patch has been tested without data sections enabled and no
differences in the resulting orc unwind information were seen.

Note that as objtool adds terminators to end of each .text section the
unwind information generated between a function+data sections build and
a normal build aren't directly comparable. Manual inspection suggests
that objtool is now generating the correct information, or at least
making more of an effort to do so than it did previously.

Signed-off-by: Allan Xavier <allan.x.xavier@oracle.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/099bdc375195c490dda04db777ee0b95d566ded1.1536325914.git.jpoimboe@redhat.com
---
 tools/objtool/check.c | 38 ++++++++++++++++++++++++++++++++------
 tools/objtool/check.h |  4 ++--
 tools/objtool/elf.c   |  1 +
 tools/objtool/elf.h   |  3 ++-
 4 files changed, 37 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 2928939b98ec..0414a0d52262 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -836,7 +836,7 @@ static int add_switch_table(struct objtool_file *file, struct instruction *insn,
 	struct symbol *pfunc = insn->func->pfunc;
 	unsigned int prev_offset = 0;
 
-	list_for_each_entry_from(rela, &file->rodata->rela->rela_list, list) {
+	list_for_each_entry_from(rela, &table->rela_sec->rela_list, list) {
 		if (rela == next_table)
 			break;
 
@@ -926,6 +926,7 @@ static struct rela *find_switch_table(struct objtool_file *file,
 {
 	struct rela *text_rela, *rodata_rela;
 	struct instruction *orig_insn = insn;
+	struct section *rodata_sec;
 	unsigned long table_offset;
 
 	/*
@@ -953,10 +954,13 @@ static struct rela *find_switch_table(struct objtool_file *file,
 		/* look for a relocation which references .rodata */
 		text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
 						    insn->len);
-		if (!text_rela || text_rela->sym != file->rodata->sym)
+		if (!text_rela || text_rela->sym->type != STT_SECTION ||
+		    !text_rela->sym->sec->rodata)
 			continue;
 
 		table_offset = text_rela->addend;
+		rodata_sec = text_rela->sym->sec;
+
 		if (text_rela->type == R_X86_64_PC32)
 			table_offset += 4;
 
@@ -964,10 +968,10 @@ static struct rela *find_switch_table(struct objtool_file *file,
 		 * Make sure the .rodata address isn't associated with a
 		 * symbol.  gcc jump tables are anonymous data.
 		 */
-		if (find_symbol_containing(file->rodata, table_offset))
+		if (find_symbol_containing(rodata_sec, table_offset))
 			continue;
 
-		rodata_rela = find_rela_by_dest(file->rodata, table_offset);
+		rodata_rela = find_rela_by_dest(rodata_sec, table_offset);
 		if (rodata_rela) {
 			/*
 			 * Use of RIP-relative switch jumps is quite rare, and
@@ -1052,7 +1056,7 @@ static int add_switch_table_alts(struct objtool_file *file)
 	struct symbol *func;
 	int ret;
 
-	if (!file->rodata || !file->rodata->rela)
+	if (!file->rodata)
 		return 0;
 
 	for_each_sec(file, sec) {
@@ -1198,10 +1202,33 @@ static int read_retpoline_hints(struct objtool_file *file)
 	return 0;
 }
 
+static void mark_rodata(struct objtool_file *file)
+{
+	struct section *sec;
+	bool found = false;
+
+	/*
+	 * This searches for the .rodata section or multiple .rodata.func_name
+	 * sections if -fdata-sections is being used. The .str.1.1 and .str.1.8
+	 * rodata sections are ignored as they don't contain jump tables.
+	 */
+	for_each_sec(file, sec) {
+		if (!strncmp(sec->name, ".rodata", 7) &&
+		    !strstr(sec->name, ".str1.")) {
+			sec->rodata = true;
+			found = true;
+		}
+	}
+
+	file->rodata = found;
+}
+
 static int decode_sections(struct objtool_file *file)
 {
 	int ret;
 
+	mark_rodata(file);
+
 	ret = decode_instructions(file);
 	if (ret)
 		return ret;
@@ -2171,7 +2198,6 @@ int check(const char *_objname, bool orc)
 	INIT_LIST_HEAD(&file.insn_list);
 	hash_init(file.insn_hash);
 	file.whitelist = find_section_by_name(file.elf, ".discard.func_stack_frame_non_standard");
-	file.rodata = find_section_by_name(file.elf, ".rodata");
 	file.c_file = find_section_by_name(file.elf, ".comment");
 	file.ignore_unreachables = no_unreachable;
 	file.hints = false;
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index 95700a2bcb7c..e6e8a655b556 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -60,8 +60,8 @@ struct objtool_file {
 	struct elf *elf;
 	struct list_head insn_list;
 	DECLARE_HASHTABLE(insn_hash, 16);
-	struct section *rodata, *whitelist;
-	bool ignore_unreachables, c_file, hints;
+	struct section *whitelist;
+	bool ignore_unreachables, c_file, hints, rodata;
 };
 
 int check(const char *objname, bool orc);
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 7ec85d567598..f7082de1ee82 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -379,6 +379,7 @@ static int read_relas(struct elf *elf)
 			rela->offset = rela->rela.r_offset;
 			symndx = GELF_R_SYM(rela->rela.r_info);
 			rela->sym = find_symbol_by_index(elf, symndx);
+			rela->rela_sec = sec;
 			if (!rela->sym) {
 				WARN("can't find rela entry symbol %d for %s",
 				     symndx, sec->name);
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index de5cd2ddded9..bc97ed86b9cd 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -48,7 +48,7 @@ struct section {
 	char *name;
 	int idx;
 	unsigned int len;
-	bool changed, text;
+	bool changed, text, rodata;
 };
 
 struct symbol {
@@ -68,6 +68,7 @@ struct rela {
 	struct list_head list;
 	struct hlist_node hash;
 	GElf_Rela rela;
+	struct section *rela_sec;
 	struct symbol *sym;
 	unsigned int type;
 	unsigned long offset;
-- 
cgit v1.2.3


From ad3338d2508cd7752accdd39881deced1ec2b8a1 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 6 Sep 2018 17:26:05 -0700
Subject: tools/bpf: bpftool: support prog array map and map of maps

Currently, prog array map and map of maps are not supported
in bpftool. This patch added the support.
Different from other map types, for prog array map and
map of maps, the key returned bpf_get_next_key() may not
point to a valid value. So for these two map types,
no error will be printed out when such a scenario happens.

The following is the plain and json dump if btf is not available:
  $ ./bpftool map dump id 10
    key: 08 00 00 00  value: 5c 01 00 00
    Found 1 element
  $ ./bpftool -jp map dump id 10
    [{
        "key": ["0x08","0x00","0x00","0x00"
        ],
        "value": ["0x5c","0x01","0x00","0x00"
        ]
    }]

If the BTF is available, the dump looks below:
  $ ./bpftool map dump id 2
    [{
            "key": 0,
            "value": 7
        }
    ]
  $ ./bpftool -jp map dump id 2
    [{
        "key": ["0x00","0x00","0x00","0x00"
        ],
        "value": ["0x07","0x00","0x00","0x00"
        ],
        "formatted": {
            "key": 0,
            "value": 7
        }
    }]

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/map.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 9c55077ca5dd..af8ad32fa6e9 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -673,12 +673,6 @@ static int do_dump(int argc, char **argv)
 	if (fd < 0)
 		return -1;
 
-	if (map_is_map_of_maps(info.type) || map_is_map_of_progs(info.type)) {
-		p_err("Dumping maps of maps and program maps not supported");
-		close(fd);
-		return -1;
-	}
-
 	key = malloc(info.key_size);
 	value = alloc_value(&info);
 	if (!key || !value) {
@@ -732,7 +726,9 @@ static int do_dump(int argc, char **argv)
 				} else {
 					print_entry_plain(&info, key, value);
 				}
-		} else {
+			num_elems++;
+		} else if (!map_is_map_of_maps(info.type) &&
+			   !map_is_map_of_progs(info.type)) {
 			if (json_output) {
 				jsonw_name(json_wtr, "key");
 				print_hex_data_json(key, info.key_size);
@@ -749,7 +745,6 @@ static int do_dump(int argc, char **argv)
 		}
 
 		prev_key = key;
-		num_elems++;
 	}
 
 	if (json_output)
-- 
cgit v1.2.3


From 9d0b3c1f1451d1b9a33de3c70ae3d50ccd77db1a Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 11 Sep 2018 14:09:11 -0700
Subject: tools/bpf: fix a netlink recv issue
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit f7010770fbac ("tools/bpf: move bpf/lib netlink related
functions into a new file") introduced a while loop for the
netlink recv path. This while loop is needed since the
buffer in recv syscall may not be enough to hold all the
information and in such cases multiple recv calls are needed.

There is a bug introduced by the above commit as
the while loop may block on recv syscall if there is no
more messages are expected. The netlink message header
flag NLM_F_MULTI is used to indicate that more messages
are expected and this patch fixed the bug by doing
further recv syscall only if multipart message is expected.

The patch added another fix regarding to message length of 0.
When netlink recv returns message length of 0, there will be
no more messages for returning data so the while loop
can end.

Fixes: f7010770fbac ("tools/bpf: move bpf/lib netlink related functions into a new file")
Reported-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/netlink.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 469e068dd0c5..fde1d7bf8199 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -65,18 +65,23 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 			    __dump_nlmsg_t _fn, dump_nlmsg_t fn,
 			    void *cookie)
 {
+	bool multipart = true;
 	struct nlmsgerr *err;
 	struct nlmsghdr *nh;
 	char buf[4096];
 	int len, ret;
 
-	while (1) {
+	while (multipart) {
+		multipart = false;
 		len = recv(sock, buf, sizeof(buf), 0);
 		if (len < 0) {
 			ret = -errno;
 			goto done;
 		}
 
+		if (len == 0)
+			break;
+
 		for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
 		     nh = NLMSG_NEXT(nh, len)) {
 			if (nh->nlmsg_pid != nl_pid) {
@@ -87,6 +92,8 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 				ret = -LIBBPF_ERRNO__INVSEQ;
 				goto done;
 			}
+			if (nh->nlmsg_flags & NLM_F_MULTI)
+				multipart = true;
 			switch (nh->nlmsg_type) {
 			case NLMSG_ERROR:
 				err = (struct nlmsgerr *)NLMSG_DATA(nh);
-- 
cgit v1.2.3


From 52d0d404d39dd9eac71a181615d6ca15e23d8e38 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 12 Sep 2018 10:04:21 +0800
Subject: geneve: add ttl inherit support

Similar with commit 72f6d71e491e6 ("vxlan: add ttl inherit support"),
currently ttl == 0 means "use whatever default value" on geneve instead
of inherit inner ttl. To respect compatibility with old behavior, let's
add a new IFLA_GENEVE_TTL_INHERIT for geneve ttl inherit support.

Reported-by: Jianlin Shi <jishi@redhat.com>
Suggested-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c               | 41 ++++++++++++++++++++++++++++++--------
 include/uapi/linux/if_link.h       |  1 +
 tools/include/uapi/linux/if_link.h |  1 +
 3 files changed, 35 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 6acb6b5718b9..6625fabe2c88 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -69,6 +69,7 @@ struct geneve_dev {
 	struct gro_cells   gro_cells;
 	bool		   collect_md;
 	bool		   use_udp6_rx_checksums;
+	bool		   ttl_inherit;
 };
 
 struct geneve_sock {
@@ -843,7 +844,11 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		ttl = key->ttl;
 	} else {
 		tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, ip_hdr(skb), skb);
-		ttl = key->ttl ? : ip4_dst_hoplimit(&rt->dst);
+		if (geneve->ttl_inherit)
+			ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb);
+		else
+			ttl = key->ttl;
+		ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
 	}
 	df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
 
@@ -889,7 +894,11 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	} else {
 		prio = ip_tunnel_ecn_encap(ip6_tclass(fl6.flowlabel),
 					   ip_hdr(skb), skb);
-		ttl = key->ttl ? : ip6_dst_hoplimit(dst);
+		if (geneve->ttl_inherit)
+			ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb);
+		else
+			ttl = key->ttl;
+		ttl = ttl ? : ip6_dst_hoplimit(dst);
 	}
 	err = geneve_build_skb(dst, skb, info, xnet, sizeof(struct ipv6hdr));
 	if (unlikely(err))
@@ -1091,6 +1100,7 @@ static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = {
 	[IFLA_GENEVE_UDP_CSUM]		= { .type = NLA_U8 },
 	[IFLA_GENEVE_UDP_ZERO_CSUM6_TX]	= { .type = NLA_U8 },
 	[IFLA_GENEVE_UDP_ZERO_CSUM6_RX]	= { .type = NLA_U8 },
+	[IFLA_GENEVE_TTL_INHERIT]	= { .type = NLA_U8 },
 };
 
 static int geneve_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -1170,7 +1180,8 @@ static bool geneve_dst_addr_equal(struct ip_tunnel_info *a,
 static int geneve_configure(struct net *net, struct net_device *dev,
 			    struct netlink_ext_ack *extack,
 			    const struct ip_tunnel_info *info,
-			    bool metadata, bool ipv6_rx_csum)
+			    bool metadata, bool ipv6_rx_csum,
+			    bool ttl_inherit)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_dev *t, *geneve = netdev_priv(dev);
@@ -1219,6 +1230,7 @@ static int geneve_configure(struct net *net, struct net_device *dev,
 	geneve->info = *info;
 	geneve->collect_md = metadata;
 	geneve->use_udp6_rx_checksums = ipv6_rx_csum;
+	geneve->ttl_inherit = ttl_inherit;
 
 	err = register_netdevice(dev);
 	if (err)
@@ -1237,7 +1249,8 @@ static void init_tnl_info(struct ip_tunnel_info *info, __u16 dst_port)
 static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[],
 			  struct netlink_ext_ack *extack,
 			  struct ip_tunnel_info *info, bool *metadata,
-			  bool *use_udp6_rx_checksums, bool changelink)
+			  bool *use_udp6_rx_checksums, bool *ttl_inherit,
+			  bool changelink)
 {
 	int attrtype;
 
@@ -1315,6 +1328,9 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[],
 	if (data[IFLA_GENEVE_TTL])
 		info->key.ttl = nla_get_u8(data[IFLA_GENEVE_TTL]);
 
+	if (data[IFLA_GENEVE_TTL_INHERIT])
+		*ttl_inherit = true;
+
 	if (data[IFLA_GENEVE_TOS])
 		info->key.tos = nla_get_u8(data[IFLA_GENEVE_TOS]);
 
@@ -1438,17 +1454,18 @@ static int geneve_newlink(struct net *net, struct net_device *dev,
 {
 	bool use_udp6_rx_checksums = false;
 	struct ip_tunnel_info info;
+	bool ttl_inherit = false;
 	bool metadata = false;
 	int err;
 
 	init_tnl_info(&info, GENEVE_UDP_PORT);
 	err = geneve_nl2info(tb, data, extack, &info, &metadata,
-			     &use_udp6_rx_checksums, false);
+			     &use_udp6_rx_checksums, &ttl_inherit, false);
 	if (err)
 		return err;
 
 	err = geneve_configure(net, dev, extack, &info, metadata,
-			       use_udp6_rx_checksums);
+			       use_udp6_rx_checksums, ttl_inherit);
 	if (err)
 		return err;
 
@@ -1511,6 +1528,7 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct ip_tunnel_info info;
 	bool metadata;
 	bool use_udp6_rx_checksums;
+	bool ttl_inherit;
 	int err;
 
 	/* If the geneve device is configured for metadata (or externally
@@ -1523,8 +1541,9 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
 	memcpy(&info, &geneve->info, sizeof(info));
 	metadata = geneve->collect_md;
 	use_udp6_rx_checksums = geneve->use_udp6_rx_checksums;
+	ttl_inherit = geneve->ttl_inherit;
 	err = geneve_nl2info(tb, data, extack, &info, &metadata,
-			     &use_udp6_rx_checksums, true);
+			     &use_udp6_rx_checksums, &ttl_inherit, true);
 	if (err)
 		return err;
 
@@ -1537,6 +1556,7 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
 	geneve->info = info;
 	geneve->collect_md = metadata;
 	geneve->use_udp6_rx_checksums = use_udp6_rx_checksums;
+	geneve->ttl_inherit = ttl_inherit;
 	geneve_unquiesce(geneve, gs4, gs6);
 
 	return 0;
@@ -1562,6 +1582,7 @@ static size_t geneve_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_CSUM */
 		nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_TX */
 		nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_RX */
+		nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL_INHERIT */
 		0;
 }
 
@@ -1569,6 +1590,7 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
 	struct ip_tunnel_info *info = &geneve->info;
+	bool ttl_inherit = geneve->ttl_inherit;
 	bool metadata = geneve->collect_md;
 	__u8 tmp_vni[3];
 	__u32 vni;
@@ -1614,6 +1636,9 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 		goto nla_put_failure;
 #endif
 
+	if (nla_put_u8(skb, IFLA_GENEVE_TTL_INHERIT, ttl_inherit))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
@@ -1650,7 +1675,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 		return dev;
 
 	init_tnl_info(&info, dst_port);
-	err = geneve_configure(net, dev, NULL, &info, true, true);
+	err = geneve_configure(net, dev, NULL, &info, true, true, false);
 	if (err) {
 		free_netdev(dev);
 		return ERR_PTR(err);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 29d49b989acd..58faab897201 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -555,6 +555,7 @@ enum {
 	IFLA_GENEVE_UDP_ZERO_CSUM6_TX,
 	IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
 	IFLA_GENEVE_LABEL,
+	IFLA_GENEVE_TTL_INHERIT,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 1c73d63068b1..141cbfdc5865 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -542,6 +542,7 @@ enum {
 	IFLA_GENEVE_UDP_ZERO_CSUM6_TX,
 	IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
 	IFLA_GENEVE_LABEL,
+	IFLA_GENEVE_TTL_INHERIT,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
-- 
cgit v1.2.3


From 2f965e3fcd4b4159a5ea832d4b5e9ff2550fa571 Mon Sep 17 00:00:00 2001
From: Petar Penkov <ppenkov@google.com>
Date: Fri, 14 Sep 2018 07:46:19 -0700
Subject: bpf: sync bpf.h uapi with tools/

This patch syncs tools/include/uapi/linux/bpf.h with the flow dissector
definitions from include/uapi/linux/bpf.h

Signed-off-by: Petar Penkov <ppenkov@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/bpf.h | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 66917a4eba27..aa5ccd2385ed 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -152,6 +152,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_LWT_SEG6LOCAL,
 	BPF_PROG_TYPE_LIRC_MODE2,
 	BPF_PROG_TYPE_SK_REUSEPORT,
+	BPF_PROG_TYPE_FLOW_DISSECTOR,
 };
 
 enum bpf_attach_type {
@@ -172,6 +173,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_UDP4_SENDMSG,
 	BPF_CGROUP_UDP6_SENDMSG,
 	BPF_LIRC_MODE2,
+	BPF_FLOW_DISSECTOR,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -2333,6 +2335,7 @@ struct __sk_buff {
 	/* ... here. */
 
 	__u32 data_meta;
+	struct bpf_flow_keys *flow_keys;
 };
 
 struct bpf_tunnel_key {
@@ -2778,4 +2781,27 @@ enum bpf_task_fd_type {
 	BPF_FD_TYPE_URETPROBE,		/* filename + offset */
 };
 
+struct bpf_flow_keys {
+	__u16	nhoff;
+	__u16	thoff;
+	__u16	addr_proto;			/* ETH_P_* of valid addrs */
+	__u8	is_frag;
+	__u8	is_first_frag;
+	__u8	is_encap;
+	__u8	ip_proto;
+	__be16	n_proto;
+	__be16	sport;
+	__be16	dport;
+	union {
+		struct {
+			__be32	ipv4_src;
+			__be32	ipv4_dst;
+		};
+		struct {
+			__u32	ipv6_src[4];	/* in6_addr; network order */
+			__u32	ipv6_dst[4];	/* in6_addr; network order */
+		};
+	};
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
-- 
cgit v1.2.3


From c22fbae76c9fdef5b7406b27754db1758e041991 Mon Sep 17 00:00:00 2001
From: Petar Penkov <ppenkov@google.com>
Date: Fri, 14 Sep 2018 07:46:20 -0700
Subject: bpf: support flow dissector in libbpf and bpftool

This patch extends libbpf and bpftool to work with programs of type
BPF_PROG_TYPE_FLOW_DISSECTOR.

Signed-off-by: Petar Penkov <ppenkov@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/prog.c | 1 +
 tools/lib/bpf/libbpf.c   | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index dce960d22106..b1cd3bc8db70 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -74,6 +74,7 @@ static const char * const prog_type_name[] = {
 	[BPF_PROG_TYPE_RAW_TRACEPOINT]	= "raw_tracepoint",
 	[BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr",
 	[BPF_PROG_TYPE_LIRC_MODE2]	= "lirc_mode2",
+	[BPF_PROG_TYPE_FLOW_DISSECTOR]	= "flow_dissector",
 };
 
 static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 8476da7f2720..9ca8e0e624d8 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1502,6 +1502,7 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
 	case BPF_PROG_TYPE_LIRC_MODE2:
 	case BPF_PROG_TYPE_SK_REUSEPORT:
+	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 		return false;
 	case BPF_PROG_TYPE_UNSPEC:
 	case BPF_PROG_TYPE_KPROBE:
@@ -2121,6 +2122,7 @@ static const struct {
 	BPF_PROG_SEC("sk_skb",		BPF_PROG_TYPE_SK_SKB),
 	BPF_PROG_SEC("sk_msg",		BPF_PROG_TYPE_SK_MSG),
 	BPF_PROG_SEC("lirc_mode2",	BPF_PROG_TYPE_LIRC_MODE2),
+	BPF_PROG_SEC("flow_dissector",	BPF_PROG_TYPE_FLOW_DISSECTOR),
 	BPF_SA_PROG_SEC("cgroup/bind4",	BPF_CGROUP_INET4_BIND),
 	BPF_SA_PROG_SEC("cgroup/bind6",	BPF_CGROUP_INET6_BIND),
 	BPF_SA_PROG_SEC("cgroup/connect4", BPF_CGROUP_INET4_CONNECT),
-- 
cgit v1.2.3


From 9c98b13cc3bb5d90ee2ec047d591272b382468fd Mon Sep 17 00:00:00 2001
From: Petar Penkov <ppenkov@google.com>
Date: Fri, 14 Sep 2018 07:46:21 -0700
Subject: flow_dissector: implements eBPF parser

This eBPF program extracts basic/control/ip address/ports keys from
incoming packets. It supports recursive parsing for IP encapsulation,
and VLAN, along with IPv4/IPv6 and extension headers.  This program is
meant to show how flow dissection and key extraction can be done in
eBPF.

Link: http://vger.kernel.org/netconf2017_files/rx_hardening_and_udp_gso.pdf
Signed-off-by: Petar Penkov <ppenkov@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/Makefile   |   2 +-
 tools/testing/selftests/bpf/bpf_flow.c | 373 +++++++++++++++++++++++++++++++++
 2 files changed, 374 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/bpf_flow.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index fff7fb1285fc..e65f50f9185e 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -35,7 +35,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
 	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
-	test_skb_cgroup_id_kern.o
+	test_skb_cgroup_id_kern.o bpf_flow.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
diff --git a/tools/testing/selftests/bpf/bpf_flow.c b/tools/testing/selftests/bpf/bpf_flow.c
new file mode 100644
index 000000000000..5fb809d95867
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_flow.c
@@ -0,0 +1,373 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <limits.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/pkt_cls.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/icmp.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/if_packet.h>
+#include <sys/socket.h>
+#include <linux/if_tunnel.h>
+#include <linux/mpls.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+int _version SEC("version") = 1;
+#define PROG(F) SEC(#F) int bpf_func_##F
+
+/* These are the identifiers of the BPF programs that will be used in tail
+ * calls. Name is limited to 16 characters, with the terminating character and
+ * bpf_func_ above, we have only 6 to work with, anything after will be cropped.
+ */
+enum {
+	IP,
+	IPV6,
+	IPV6OP,	/* Destination/Hop-by-Hop Options IPv6 Extension header */
+	IPV6FR,	/* Fragmentation IPv6 Extension Header */
+	MPLS,
+	VLAN,
+};
+
+#define IP_MF		0x2000
+#define IP_OFFSET	0x1FFF
+#define IP6_MF		0x0001
+#define IP6_OFFSET	0xFFF8
+
+struct vlan_hdr {
+	__be16 h_vlan_TCI;
+	__be16 h_vlan_encapsulated_proto;
+};
+
+struct gre_hdr {
+	__be16 flags;
+	__be16 proto;
+};
+
+struct frag_hdr {
+	__u8 nexthdr;
+	__u8 reserved;
+	__be16 frag_off;
+	__be32 identification;
+};
+
+struct bpf_map_def SEC("maps") jmp_table = {
+	.type = BPF_MAP_TYPE_PROG_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u32),
+	.max_entries = 8
+};
+
+static __always_inline void *bpf_flow_dissect_get_header(struct __sk_buff *skb,
+							 __u16 hdr_size,
+							 void *buffer)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	__u16 nhoff = skb->flow_keys->nhoff;
+	__u8 *hdr;
+
+	/* Verifies this variable offset does not overflow */
+	if (nhoff > (USHRT_MAX - hdr_size))
+		return NULL;
+
+	hdr = data + nhoff;
+	if (hdr + hdr_size <= data_end)
+		return hdr;
+
+	if (bpf_skb_load_bytes(skb, nhoff, buffer, hdr_size))
+		return NULL;
+
+	return buffer;
+}
+
+/* Dispatches on ETHERTYPE */
+static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
+{
+	struct bpf_flow_keys *keys = skb->flow_keys;
+
+	keys->n_proto = proto;
+	switch (proto) {
+	case bpf_htons(ETH_P_IP):
+		bpf_tail_call(skb, &jmp_table, IP);
+		break;
+	case bpf_htons(ETH_P_IPV6):
+		bpf_tail_call(skb, &jmp_table, IPV6);
+		break;
+	case bpf_htons(ETH_P_MPLS_MC):
+	case bpf_htons(ETH_P_MPLS_UC):
+		bpf_tail_call(skb, &jmp_table, MPLS);
+		break;
+	case bpf_htons(ETH_P_8021Q):
+	case bpf_htons(ETH_P_8021AD):
+		bpf_tail_call(skb, &jmp_table, VLAN);
+		break;
+	default:
+		/* Protocol not supported */
+		return BPF_DROP;
+	}
+
+	return BPF_DROP;
+}
+
+SEC("dissect")
+int dissect(struct __sk_buff *skb)
+{
+	if (!skb->vlan_present)
+		return parse_eth_proto(skb, skb->protocol);
+	else
+		return parse_eth_proto(skb, skb->vlan_proto);
+}
+
+/* Parses on IPPROTO_* */
+static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto)
+{
+	struct bpf_flow_keys *keys = skb->flow_keys;
+	void *data_end = (void *)(long)skb->data_end;
+	struct icmphdr *icmp, _icmp;
+	struct gre_hdr *gre, _gre;
+	struct ethhdr *eth, _eth;
+	struct tcphdr *tcp, _tcp;
+	struct udphdr *udp, _udp;
+
+	keys->ip_proto = proto;
+	switch (proto) {
+	case IPPROTO_ICMP:
+		icmp = bpf_flow_dissect_get_header(skb, sizeof(*icmp), &_icmp);
+		if (!icmp)
+			return BPF_DROP;
+		return BPF_OK;
+	case IPPROTO_IPIP:
+		keys->is_encap = true;
+		return parse_eth_proto(skb, bpf_htons(ETH_P_IP));
+	case IPPROTO_IPV6:
+		keys->is_encap = true;
+		return parse_eth_proto(skb, bpf_htons(ETH_P_IPV6));
+	case IPPROTO_GRE:
+		gre = bpf_flow_dissect_get_header(skb, sizeof(*gre), &_gre);
+		if (!gre)
+			return BPF_DROP;
+
+		if (bpf_htons(gre->flags & GRE_VERSION))
+			/* Only inspect standard GRE packets with version 0 */
+			return BPF_OK;
+
+		keys->nhoff += sizeof(*gre); /* Step over GRE Flags and Proto */
+		if (GRE_IS_CSUM(gre->flags))
+			keys->nhoff += 4; /* Step over chksum and Padding */
+		if (GRE_IS_KEY(gre->flags))
+			keys->nhoff += 4; /* Step over key */
+		if (GRE_IS_SEQ(gre->flags))
+			keys->nhoff += 4; /* Step over sequence number */
+
+		keys->is_encap = true;
+
+		if (gre->proto == bpf_htons(ETH_P_TEB)) {
+			eth = bpf_flow_dissect_get_header(skb, sizeof(*eth),
+							  &_eth);
+			if (!eth)
+				return BPF_DROP;
+
+			keys->nhoff += sizeof(*eth);
+
+			return parse_eth_proto(skb, eth->h_proto);
+		} else {
+			return parse_eth_proto(skb, gre->proto);
+		}
+	case IPPROTO_TCP:
+		tcp = bpf_flow_dissect_get_header(skb, sizeof(*tcp), &_tcp);
+		if (!tcp)
+			return BPF_DROP;
+
+		if (tcp->doff < 5)
+			return BPF_DROP;
+
+		if ((__u8 *)tcp + (tcp->doff << 2) > data_end)
+			return BPF_DROP;
+
+		keys->thoff = keys->nhoff;
+		keys->sport = tcp->source;
+		keys->dport = tcp->dest;
+		return BPF_OK;
+	case IPPROTO_UDP:
+	case IPPROTO_UDPLITE:
+		udp = bpf_flow_dissect_get_header(skb, sizeof(*udp), &_udp);
+		if (!udp)
+			return BPF_DROP;
+
+		keys->thoff = keys->nhoff;
+		keys->sport = udp->source;
+		keys->dport = udp->dest;
+		return BPF_OK;
+	default:
+		return BPF_DROP;
+	}
+
+	return BPF_DROP;
+}
+
+static __always_inline int parse_ipv6_proto(struct __sk_buff *skb, __u8 nexthdr)
+{
+	struct bpf_flow_keys *keys = skb->flow_keys;
+
+	keys->ip_proto = nexthdr;
+	switch (nexthdr) {
+	case IPPROTO_HOPOPTS:
+	case IPPROTO_DSTOPTS:
+		bpf_tail_call(skb, &jmp_table, IPV6OP);
+		break;
+	case IPPROTO_FRAGMENT:
+		bpf_tail_call(skb, &jmp_table, IPV6FR);
+		break;
+	default:
+		return parse_ip_proto(skb, nexthdr);
+	}
+
+	return BPF_DROP;
+}
+
+PROG(IP)(struct __sk_buff *skb)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	struct bpf_flow_keys *keys = skb->flow_keys;
+	void *data = (void *)(long)skb->data;
+	struct iphdr *iph, _iph;
+	bool done = false;
+
+	iph = bpf_flow_dissect_get_header(skb, sizeof(*iph), &_iph);
+	if (!iph)
+		return BPF_DROP;
+
+	/* IP header cannot be smaller than 20 bytes */
+	if (iph->ihl < 5)
+		return BPF_DROP;
+
+	keys->addr_proto = ETH_P_IP;
+	keys->ipv4_src = iph->saddr;
+	keys->ipv4_dst = iph->daddr;
+
+	keys->nhoff += iph->ihl << 2;
+	if (data + keys->nhoff > data_end)
+		return BPF_DROP;
+
+	if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET)) {
+		keys->is_frag = true;
+		if (iph->frag_off & bpf_htons(IP_OFFSET))
+			/* From second fragment on, packets do not have headers
+			 * we can parse.
+			 */
+			done = true;
+		else
+			keys->is_first_frag = true;
+	}
+
+	if (done)
+		return BPF_OK;
+
+	return parse_ip_proto(skb, iph->protocol);
+}
+
+PROG(IPV6)(struct __sk_buff *skb)
+{
+	struct bpf_flow_keys *keys = skb->flow_keys;
+	struct ipv6hdr *ip6h, _ip6h;
+
+	ip6h = bpf_flow_dissect_get_header(skb, sizeof(*ip6h), &_ip6h);
+	if (!ip6h)
+		return BPF_DROP;
+
+	keys->addr_proto = ETH_P_IPV6;
+	memcpy(&keys->ipv6_src, &ip6h->saddr, 2*sizeof(ip6h->saddr));
+
+	keys->nhoff += sizeof(struct ipv6hdr);
+
+	return parse_ipv6_proto(skb, ip6h->nexthdr);
+}
+
+PROG(IPV6OP)(struct __sk_buff *skb)
+{
+	struct ipv6_opt_hdr *ip6h, _ip6h;
+
+	ip6h = bpf_flow_dissect_get_header(skb, sizeof(*ip6h), &_ip6h);
+	if (!ip6h)
+		return BPF_DROP;
+
+	/* hlen is in 8-octets and does not include the first 8 bytes
+	 * of the header
+	 */
+	skb->flow_keys->nhoff += (1 + ip6h->hdrlen) << 3;
+
+	return parse_ipv6_proto(skb, ip6h->nexthdr);
+}
+
+PROG(IPV6FR)(struct __sk_buff *skb)
+{
+	struct bpf_flow_keys *keys = skb->flow_keys;
+	struct frag_hdr *fragh, _fragh;
+
+	fragh = bpf_flow_dissect_get_header(skb, sizeof(*fragh), &_fragh);
+	if (!fragh)
+		return BPF_DROP;
+
+	keys->nhoff += sizeof(*fragh);
+	keys->is_frag = true;
+	if (!(fragh->frag_off & bpf_htons(IP6_OFFSET)))
+		keys->is_first_frag = true;
+
+	return parse_ipv6_proto(skb, fragh->nexthdr);
+}
+
+PROG(MPLS)(struct __sk_buff *skb)
+{
+	struct mpls_label *mpls, _mpls;
+
+	mpls = bpf_flow_dissect_get_header(skb, sizeof(*mpls), &_mpls);
+	if (!mpls)
+		return BPF_DROP;
+
+	return BPF_OK;
+}
+
+PROG(VLAN)(struct __sk_buff *skb)
+{
+	struct bpf_flow_keys *keys = skb->flow_keys;
+	struct vlan_hdr *vlan, _vlan;
+	__be16 proto;
+
+	/* Peek back to see if single or double-tagging */
+	if (bpf_skb_load_bytes(skb, keys->nhoff - sizeof(proto), &proto,
+			       sizeof(proto)))
+		return BPF_DROP;
+
+	/* Account for double-tagging */
+	if (proto == bpf_htons(ETH_P_8021AD)) {
+		vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan);
+		if (!vlan)
+			return BPF_DROP;
+
+		if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q))
+			return BPF_DROP;
+
+		keys->nhoff += sizeof(*vlan);
+	}
+
+	vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan);
+	if (!vlan)
+		return BPF_DROP;
+
+	keys->nhoff += sizeof(*vlan);
+	/* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/
+	if (vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021AD) ||
+	    vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q))
+		return BPF_DROP;
+
+	return parse_eth_proto(skb, vlan->h_vlan_encapsulated_proto);
+}
+
+char __license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 50b3ed57dee9cd0e06c59826cec8af14b51bab3e Mon Sep 17 00:00:00 2001
From: Petar Penkov <ppenkov@google.com>
Date: Fri, 14 Sep 2018 07:46:22 -0700
Subject: selftests/bpf: test bpf flow dissection

Adds a test that sends different types of packets over multiple
tunnels and verifies that valid packets are dissected correctly.  To do
so, a tc-flower rule is added to drop packets on UDP src port 9, and
packets are sent from ports 8, 9, and 10. Only the packets on port 9
should be dropped. Because tc-flower relies on the flow dissector to
match flows, correct classification demonstrates correct dissection.

Also add support logic to load the BPF program and to inject the test
packets.

Signed-off-by: Petar Penkov <ppenkov@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/.gitignore             |   2 +
 tools/testing/selftests/bpf/Makefile               |   6 +-
 tools/testing/selftests/bpf/config                 |   1 +
 tools/testing/selftests/bpf/flow_dissector_load.c  | 140 ++++
 tools/testing/selftests/bpf/test_flow_dissector.c  | 782 +++++++++++++++++++++
 tools/testing/selftests/bpf/test_flow_dissector.sh | 115 +++
 tools/testing/selftests/bpf/with_addr.sh           |  54 ++
 tools/testing/selftests/bpf/with_tunnels.sh        |  36 +
 8 files changed, 1134 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/flow_dissector_load.c
 create mode 100644 tools/testing/selftests/bpf/test_flow_dissector.c
 create mode 100755 tools/testing/selftests/bpf/test_flow_dissector.sh
 create mode 100755 tools/testing/selftests/bpf/with_addr.sh
 create mode 100755 tools/testing/selftests/bpf/with_tunnels.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 4d789c1e5167..8a60c9b9892d 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -23,3 +23,5 @@ test_skb_cgroup_id_user
 test_socket_cookie
 test_cgroup_storage
 test_select_reuseport
+test_flow_dissector
+flow_dissector_load
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e65f50f9185e..fd3851d5c079 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -47,10 +47,12 @@ TEST_PROGS := test_kmod.sh \
 	test_tunnel.sh \
 	test_lwt_seg6local.sh \
 	test_lirc_mode2.sh \
-	test_skb_cgroup_id.sh
+	test_skb_cgroup_id.sh \
+	test_flow_dissector.sh
 
 # Compile but not part of 'make run_tests'
-TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user
+TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user \
+	flow_dissector_load test_flow_dissector
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index b4994a94968b..3655508f95fd 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -18,3 +18,4 @@ CONFIG_CRYPTO_HMAC=m
 CONFIG_CRYPTO_SHA256=m
 CONFIG_VXLAN=y
 CONFIG_GENEVE=y
+CONFIG_NET_CLS_FLOWER=m
diff --git a/tools/testing/selftests/bpf/flow_dissector_load.c b/tools/testing/selftests/bpf/flow_dissector_load.c
new file mode 100644
index 000000000000..d3273b5b3173
--- /dev/null
+++ b/tools/testing/selftests/bpf/flow_dissector_load.c
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <error.h>
+#include <errno.h>
+#include <getopt.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+const char *cfg_pin_path = "/sys/fs/bpf/flow_dissector";
+const char *cfg_map_name = "jmp_table";
+bool cfg_attach = true;
+char *cfg_section_name;
+char *cfg_path_name;
+
+static void load_and_attach_program(void)
+{
+	struct bpf_program *prog, *main_prog;
+	struct bpf_map *prog_array;
+	int i, fd, prog_fd, ret;
+	struct bpf_object *obj;
+	int prog_array_fd;
+
+	ret = bpf_prog_load(cfg_path_name, BPF_PROG_TYPE_FLOW_DISSECTOR, &obj,
+			    &prog_fd);
+	if (ret)
+		error(1, 0, "bpf_prog_load %s", cfg_path_name);
+
+	main_prog = bpf_object__find_program_by_title(obj, cfg_section_name);
+	if (!main_prog)
+		error(1, 0, "bpf_object__find_program_by_title %s",
+		      cfg_section_name);
+
+	prog_fd = bpf_program__fd(main_prog);
+	if (prog_fd < 0)
+		error(1, 0, "bpf_program__fd");
+
+	prog_array = bpf_object__find_map_by_name(obj, cfg_map_name);
+	if (!prog_array)
+		error(1, 0, "bpf_object__find_map_by_name %s", cfg_map_name);
+
+	prog_array_fd = bpf_map__fd(prog_array);
+	if (prog_array_fd < 0)
+		error(1, 0, "bpf_map__fd %s", cfg_map_name);
+
+	i = 0;
+	bpf_object__for_each_program(prog, obj) {
+		fd = bpf_program__fd(prog);
+		if (fd < 0)
+			error(1, 0, "bpf_program__fd");
+
+		if (fd != prog_fd) {
+			printf("%d: %s\n", i, bpf_program__title(prog, false));
+			bpf_map_update_elem(prog_array_fd, &i, &fd, BPF_ANY);
+			++i;
+		}
+	}
+
+	ret = bpf_prog_attach(prog_fd, 0 /* Ignore */, BPF_FLOW_DISSECTOR, 0);
+	if (ret)
+		error(1, 0, "bpf_prog_attach %s", cfg_path_name);
+
+	ret = bpf_object__pin(obj, cfg_pin_path);
+	if (ret)
+		error(1, 0, "bpf_object__pin %s", cfg_pin_path);
+
+}
+
+static void detach_program(void)
+{
+	char command[64];
+	int ret;
+
+	ret = bpf_prog_detach(0, BPF_FLOW_DISSECTOR);
+	if (ret)
+		error(1, 0, "bpf_prog_detach");
+
+	/* To unpin, it is necessary and sufficient to just remove this dir */
+	sprintf(command, "rm -r %s", cfg_pin_path);
+	ret = system(command);
+	if (ret)
+		error(1, errno, command);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	bool attach = false;
+	bool detach = false;
+	int c;
+
+	while ((c = getopt(argc, argv, "adp:s:")) != -1) {
+		switch (c) {
+		case 'a':
+			if (detach)
+				error(1, 0, "attach/detach are exclusive");
+			attach = true;
+			break;
+		case 'd':
+			if (attach)
+				error(1, 0, "attach/detach are exclusive");
+			detach = true;
+			break;
+		case 'p':
+			if (cfg_path_name)
+				error(1, 0, "only one prog name can be given");
+
+			cfg_path_name = optarg;
+			break;
+		case 's':
+			if (cfg_section_name)
+				error(1, 0, "only one section can be given");
+
+			cfg_section_name = optarg;
+			break;
+		}
+	}
+
+	if (detach)
+		cfg_attach = false;
+
+	if (cfg_attach && !cfg_path_name)
+		error(1, 0, "must provide a path to the BPF program");
+
+	if (cfg_attach && !cfg_section_name)
+		error(1, 0, "must provide a section name");
+}
+
+int main(int argc, char **argv)
+{
+	parse_opts(argc, argv);
+	if (cfg_attach)
+		load_and_attach_program();
+	else
+		detach_program();
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_flow_dissector.c b/tools/testing/selftests/bpf/test_flow_dissector.c
new file mode 100644
index 000000000000..12b784afba31
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_flow_dissector.c
@@ -0,0 +1,782 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Inject packets with all sorts of encapsulation into the kernel.
+ *
+ * IPv4/IPv6	outer layer 3
+ * GRE/GUE/BARE outer layer 4, where bare is IPIP/SIT/IPv4-in-IPv6/..
+ * IPv4/IPv6    inner layer 3
+ */
+
+#define _GNU_SOURCE
+
+#include <stddef.h>
+#include <arpa/inet.h>
+#include <asm/byteorder.h>
+#include <error.h>
+#include <errno.h>
+#include <linux/if_packet.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ipv6.h>
+#include <netinet/ip.h>
+#include <netinet/in.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#define CFG_PORT_INNER	8000
+
+/* Add some protocol definitions that do not exist in userspace */
+
+struct grehdr {
+	uint16_t unused;
+	uint16_t protocol;
+} __attribute__((packed));
+
+struct guehdr {
+	union {
+		struct {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+			__u8	hlen:5,
+				control:1,
+				version:2;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+			__u8	version:2,
+				control:1,
+				hlen:5;
+#else
+#error  "Please fix <asm/byteorder.h>"
+#endif
+			__u8	proto_ctype;
+			__be16	flags;
+		};
+		__be32	word;
+	};
+};
+
+static uint8_t	cfg_dsfield_inner;
+static uint8_t	cfg_dsfield_outer;
+static uint8_t	cfg_encap_proto;
+static bool	cfg_expect_failure = false;
+static int	cfg_l3_extra = AF_UNSPEC;	/* optional SIT prefix */
+static int	cfg_l3_inner = AF_UNSPEC;
+static int	cfg_l3_outer = AF_UNSPEC;
+static int	cfg_num_pkt = 10;
+static int	cfg_num_secs = 0;
+static char	cfg_payload_char = 'a';
+static int	cfg_payload_len = 100;
+static int	cfg_port_gue = 6080;
+static bool	cfg_only_rx;
+static bool	cfg_only_tx;
+static int	cfg_src_port = 9;
+
+static char	buf[ETH_DATA_LEN];
+
+#define INIT_ADDR4(name, addr4, port)				\
+	static struct sockaddr_in name = {			\
+		.sin_family = AF_INET,				\
+		.sin_port = __constant_htons(port),		\
+		.sin_addr.s_addr = __constant_htonl(addr4),	\
+	};
+
+#define INIT_ADDR6(name, addr6, port)				\
+	static struct sockaddr_in6 name = {			\
+		.sin6_family = AF_INET6,			\
+		.sin6_port = __constant_htons(port),		\
+		.sin6_addr = addr6,				\
+	};
+
+INIT_ADDR4(in_daddr4, INADDR_LOOPBACK, CFG_PORT_INNER)
+INIT_ADDR4(in_saddr4, INADDR_LOOPBACK + 2, 0)
+INIT_ADDR4(out_daddr4, INADDR_LOOPBACK, 0)
+INIT_ADDR4(out_saddr4, INADDR_LOOPBACK + 1, 0)
+INIT_ADDR4(extra_daddr4, INADDR_LOOPBACK, 0)
+INIT_ADDR4(extra_saddr4, INADDR_LOOPBACK + 1, 0)
+
+INIT_ADDR6(in_daddr6, IN6ADDR_LOOPBACK_INIT, CFG_PORT_INNER)
+INIT_ADDR6(in_saddr6, IN6ADDR_LOOPBACK_INIT, 0)
+INIT_ADDR6(out_daddr6, IN6ADDR_LOOPBACK_INIT, 0)
+INIT_ADDR6(out_saddr6, IN6ADDR_LOOPBACK_INIT, 0)
+INIT_ADDR6(extra_daddr6, IN6ADDR_LOOPBACK_INIT, 0)
+INIT_ADDR6(extra_saddr6, IN6ADDR_LOOPBACK_INIT, 0)
+
+static unsigned long util_gettime(void)
+{
+	struct timeval tv;
+
+	gettimeofday(&tv, NULL);
+	return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static void util_printaddr(const char *msg, struct sockaddr *addr)
+{
+	unsigned long off = 0;
+	char nbuf[INET6_ADDRSTRLEN];
+
+	switch (addr->sa_family) {
+	case PF_INET:
+		off = __builtin_offsetof(struct sockaddr_in, sin_addr);
+		break;
+	case PF_INET6:
+		off = __builtin_offsetof(struct sockaddr_in6, sin6_addr);
+		break;
+	default:
+		error(1, 0, "printaddr: unsupported family %u\n",
+		      addr->sa_family);
+	}
+
+	if (!inet_ntop(addr->sa_family, ((void *) addr) + off, nbuf,
+		       sizeof(nbuf)))
+		error(1, errno, "inet_ntop");
+
+	fprintf(stderr, "%s: %s\n", msg, nbuf);
+}
+
+static unsigned long add_csum_hword(const uint16_t *start, int num_u16)
+{
+	unsigned long sum = 0;
+	int i;
+
+	for (i = 0; i < num_u16; i++)
+		sum += start[i];
+
+	return sum;
+}
+
+static uint16_t build_ip_csum(const uint16_t *start, int num_u16,
+			      unsigned long sum)
+{
+	sum += add_csum_hword(start, num_u16);
+
+	while (sum >> 16)
+		sum = (sum & 0xffff) + (sum >> 16);
+
+	return ~sum;
+}
+
+static void build_ipv4_header(void *header, uint8_t proto,
+			      uint32_t src, uint32_t dst,
+			      int payload_len, uint8_t tos)
+{
+	struct iphdr *iph = header;
+
+	iph->ihl = 5;
+	iph->version = 4;
+	iph->tos = tos;
+	iph->ttl = 8;
+	iph->tot_len = htons(sizeof(*iph) + payload_len);
+	iph->id = htons(1337);
+	iph->protocol = proto;
+	iph->saddr = src;
+	iph->daddr = dst;
+	iph->check = build_ip_csum((void *) iph, iph->ihl << 1, 0);
+}
+
+static void ipv6_set_dsfield(struct ipv6hdr *ip6h, uint8_t dsfield)
+{
+	uint16_t val, *ptr = (uint16_t *)ip6h;
+
+	val = ntohs(*ptr);
+	val &= 0xF00F;
+	val |= ((uint16_t) dsfield) << 4;
+	*ptr = htons(val);
+}
+
+static void build_ipv6_header(void *header, uint8_t proto,
+			      struct sockaddr_in6 *src,
+			      struct sockaddr_in6 *dst,
+			      int payload_len, uint8_t dsfield)
+{
+	struct ipv6hdr *ip6h = header;
+
+	ip6h->version = 6;
+	ip6h->payload_len = htons(payload_len);
+	ip6h->nexthdr = proto;
+	ip6h->hop_limit = 8;
+	ipv6_set_dsfield(ip6h, dsfield);
+
+	memcpy(&ip6h->saddr, &src->sin6_addr, sizeof(ip6h->saddr));
+	memcpy(&ip6h->daddr, &dst->sin6_addr, sizeof(ip6h->daddr));
+}
+
+static uint16_t build_udp_v4_csum(const struct iphdr *iph,
+				  const struct udphdr *udph,
+				  int num_words)
+{
+	unsigned long pseudo_sum;
+	int num_u16 = sizeof(iph->saddr);	/* halfwords: twice byte len */
+
+	pseudo_sum = add_csum_hword((void *) &iph->saddr, num_u16);
+	pseudo_sum += htons(IPPROTO_UDP);
+	pseudo_sum += udph->len;
+	return build_ip_csum((void *) udph, num_words, pseudo_sum);
+}
+
+static uint16_t build_udp_v6_csum(const struct ipv6hdr *ip6h,
+				  const struct udphdr *udph,
+				  int num_words)
+{
+	unsigned long pseudo_sum;
+	int num_u16 = sizeof(ip6h->saddr);	/* halfwords: twice byte len */
+
+	pseudo_sum = add_csum_hword((void *) &ip6h->saddr, num_u16);
+	pseudo_sum += htons(ip6h->nexthdr);
+	pseudo_sum += ip6h->payload_len;
+	return build_ip_csum((void *) udph, num_words, pseudo_sum);
+}
+
+static void build_udp_header(void *header, int payload_len,
+			     uint16_t dport, int family)
+{
+	struct udphdr *udph = header;
+	int len = sizeof(*udph) + payload_len;
+
+	udph->source = htons(cfg_src_port);
+	udph->dest = htons(dport);
+	udph->len = htons(len);
+	udph->check = 0;
+	if (family == AF_INET)
+		udph->check = build_udp_v4_csum(header - sizeof(struct iphdr),
+						udph, len >> 1);
+	else
+		udph->check = build_udp_v6_csum(header - sizeof(struct ipv6hdr),
+						udph, len >> 1);
+}
+
+static void build_gue_header(void *header, uint8_t proto)
+{
+	struct guehdr *gueh = header;
+
+	gueh->proto_ctype = proto;
+}
+
+static void build_gre_header(void *header, uint16_t proto)
+{
+	struct grehdr *greh = header;
+
+	greh->protocol = htons(proto);
+}
+
+static int l3_length(int family)
+{
+	if (family == AF_INET)
+		return sizeof(struct iphdr);
+	else
+		return sizeof(struct ipv6hdr);
+}
+
+static int build_packet(void)
+{
+	int ol3_len = 0, ol4_len = 0, il3_len = 0, il4_len = 0;
+	int el3_len = 0;
+
+	if (cfg_l3_extra)
+		el3_len = l3_length(cfg_l3_extra);
+
+	/* calculate header offsets */
+	if (cfg_encap_proto) {
+		ol3_len = l3_length(cfg_l3_outer);
+
+		if (cfg_encap_proto == IPPROTO_GRE)
+			ol4_len = sizeof(struct grehdr);
+		else if (cfg_encap_proto == IPPROTO_UDP)
+			ol4_len = sizeof(struct udphdr) + sizeof(struct guehdr);
+	}
+
+	il3_len = l3_length(cfg_l3_inner);
+	il4_len = sizeof(struct udphdr);
+
+	if (el3_len + ol3_len + ol4_len + il3_len + il4_len + cfg_payload_len >=
+	    sizeof(buf))
+		error(1, 0, "packet too large\n");
+
+	/*
+	 * Fill packet from inside out, to calculate correct checksums.
+	 * But create ip before udp headers, as udp uses ip for pseudo-sum.
+	 */
+	memset(buf + el3_len + ol3_len + ol4_len + il3_len + il4_len,
+	       cfg_payload_char, cfg_payload_len);
+
+	/* add zero byte for udp csum padding */
+	buf[el3_len + ol3_len + ol4_len + il3_len + il4_len + cfg_payload_len] = 0;
+
+	switch (cfg_l3_inner) {
+	case PF_INET:
+		build_ipv4_header(buf + el3_len + ol3_len + ol4_len,
+				  IPPROTO_UDP,
+				  in_saddr4.sin_addr.s_addr,
+				  in_daddr4.sin_addr.s_addr,
+				  il4_len + cfg_payload_len,
+				  cfg_dsfield_inner);
+		break;
+	case PF_INET6:
+		build_ipv6_header(buf + el3_len + ol3_len + ol4_len,
+				  IPPROTO_UDP,
+				  &in_saddr6, &in_daddr6,
+				  il4_len + cfg_payload_len,
+				  cfg_dsfield_inner);
+		break;
+	}
+
+	build_udp_header(buf + el3_len + ol3_len + ol4_len + il3_len,
+			 cfg_payload_len, CFG_PORT_INNER, cfg_l3_inner);
+
+	if (!cfg_encap_proto)
+		return il3_len + il4_len + cfg_payload_len;
+
+	switch (cfg_l3_outer) {
+	case PF_INET:
+		build_ipv4_header(buf + el3_len, cfg_encap_proto,
+				  out_saddr4.sin_addr.s_addr,
+				  out_daddr4.sin_addr.s_addr,
+				  ol4_len + il3_len + il4_len + cfg_payload_len,
+				  cfg_dsfield_outer);
+		break;
+	case PF_INET6:
+		build_ipv6_header(buf + el3_len, cfg_encap_proto,
+				  &out_saddr6, &out_daddr6,
+				  ol4_len + il3_len + il4_len + cfg_payload_len,
+				  cfg_dsfield_outer);
+		break;
+	}
+
+	switch (cfg_encap_proto) {
+	case IPPROTO_UDP:
+		build_gue_header(buf + el3_len + ol3_len + ol4_len -
+				 sizeof(struct guehdr),
+				 cfg_l3_inner == PF_INET ? IPPROTO_IPIP
+							 : IPPROTO_IPV6);
+		build_udp_header(buf + el3_len + ol3_len,
+				 sizeof(struct guehdr) + il3_len + il4_len +
+				 cfg_payload_len,
+				 cfg_port_gue, cfg_l3_outer);
+		break;
+	case IPPROTO_GRE:
+		build_gre_header(buf + el3_len + ol3_len,
+				 cfg_l3_inner == PF_INET ? ETH_P_IP
+							 : ETH_P_IPV6);
+		break;
+	}
+
+	switch (cfg_l3_extra) {
+	case PF_INET:
+		build_ipv4_header(buf,
+				  cfg_l3_outer == PF_INET ? IPPROTO_IPIP
+							  : IPPROTO_IPV6,
+				  extra_saddr4.sin_addr.s_addr,
+				  extra_daddr4.sin_addr.s_addr,
+				  ol3_len + ol4_len + il3_len + il4_len +
+				  cfg_payload_len, 0);
+		break;
+	case PF_INET6:
+		build_ipv6_header(buf,
+				  cfg_l3_outer == PF_INET ? IPPROTO_IPIP
+							  : IPPROTO_IPV6,
+				  &extra_saddr6, &extra_daddr6,
+				  ol3_len + ol4_len + il3_len + il4_len +
+				  cfg_payload_len, 0);
+		break;
+	}
+
+	return el3_len + ol3_len + ol4_len + il3_len + il4_len +
+	       cfg_payload_len;
+}
+
+/* sender transmits encapsulated over RAW or unencap'd over UDP */
+static int setup_tx(void)
+{
+	int family, fd, ret;
+
+	if (cfg_l3_extra)
+		family = cfg_l3_extra;
+	else if (cfg_l3_outer)
+		family = cfg_l3_outer;
+	else
+		family = cfg_l3_inner;
+
+	fd = socket(family, SOCK_RAW, IPPROTO_RAW);
+	if (fd == -1)
+		error(1, errno, "socket tx");
+
+	if (cfg_l3_extra) {
+		if (cfg_l3_extra == PF_INET)
+			ret = connect(fd, (void *) &extra_daddr4,
+				      sizeof(extra_daddr4));
+		else
+			ret = connect(fd, (void *) &extra_daddr6,
+				      sizeof(extra_daddr6));
+		if (ret)
+			error(1, errno, "connect tx");
+	} else if (cfg_l3_outer) {
+		/* connect to destination if not encapsulated */
+		if (cfg_l3_outer == PF_INET)
+			ret = connect(fd, (void *) &out_daddr4,
+				      sizeof(out_daddr4));
+		else
+			ret = connect(fd, (void *) &out_daddr6,
+				      sizeof(out_daddr6));
+		if (ret)
+			error(1, errno, "connect tx");
+	} else {
+		/* otherwise using loopback */
+		if (cfg_l3_inner == PF_INET)
+			ret = connect(fd, (void *) &in_daddr4,
+				      sizeof(in_daddr4));
+		else
+			ret = connect(fd, (void *) &in_daddr6,
+				      sizeof(in_daddr6));
+		if (ret)
+			error(1, errno, "connect tx");
+	}
+
+	return fd;
+}
+
+/* receiver reads unencapsulated UDP */
+static int setup_rx(void)
+{
+	int fd, ret;
+
+	fd = socket(cfg_l3_inner, SOCK_DGRAM, 0);
+	if (fd == -1)
+		error(1, errno, "socket rx");
+
+	if (cfg_l3_inner == PF_INET)
+		ret = bind(fd, (void *) &in_daddr4, sizeof(in_daddr4));
+	else
+		ret = bind(fd, (void *) &in_daddr6, sizeof(in_daddr6));
+	if (ret)
+		error(1, errno, "bind rx");
+
+	return fd;
+}
+
+static int do_tx(int fd, const char *pkt, int len)
+{
+	int ret;
+
+	ret = write(fd, pkt, len);
+	if (ret == -1)
+		error(1, errno, "send");
+	if (ret != len)
+		error(1, errno, "send: len (%d < %d)\n", ret, len);
+
+	return 1;
+}
+
+static int do_poll(int fd, short events, int timeout)
+{
+	struct pollfd pfd;
+	int ret;
+
+	pfd.fd = fd;
+	pfd.events = events;
+
+	ret = poll(&pfd, 1, timeout);
+	if (ret == -1)
+		error(1, errno, "poll");
+	if (ret && !(pfd.revents & POLLIN))
+		error(1, errno, "poll: unexpected event 0x%x\n", pfd.revents);
+
+	return ret;
+}
+
+static int do_rx(int fd)
+{
+	char rbuf;
+	int ret, num = 0;
+
+	while (1) {
+		ret = recv(fd, &rbuf, 1, MSG_DONTWAIT);
+		if (ret == -1 && errno == EAGAIN)
+			break;
+		if (ret == -1)
+			error(1, errno, "recv");
+		if (rbuf != cfg_payload_char)
+			error(1, 0, "recv: payload mismatch");
+		num++;
+	};
+
+	return num;
+}
+
+static int do_main(void)
+{
+	unsigned long tstop, treport, tcur;
+	int fdt = -1, fdr = -1, len, tx = 0, rx = 0;
+
+	if (!cfg_only_tx)
+		fdr = setup_rx();
+	if (!cfg_only_rx)
+		fdt = setup_tx();
+
+	len = build_packet();
+
+	tcur = util_gettime();
+	treport = tcur + 1000;
+	tstop = tcur + (cfg_num_secs * 1000);
+
+	while (1) {
+		if (!cfg_only_rx)
+			tx += do_tx(fdt, buf, len);
+
+		if (!cfg_only_tx)
+			rx += do_rx(fdr);
+
+		if (cfg_num_secs) {
+			tcur = util_gettime();
+			if (tcur >= tstop)
+				break;
+			if (tcur >= treport) {
+				fprintf(stderr, "pkts: tx=%u rx=%u\n", tx, rx);
+				tx = 0;
+				rx = 0;
+				treport = tcur + 1000;
+			}
+		} else {
+			if (tx == cfg_num_pkt)
+				break;
+		}
+	}
+
+	/* read straggler packets, if any */
+	if (rx < tx) {
+		tstop = util_gettime() + 100;
+		while (rx < tx) {
+			tcur = util_gettime();
+			if (tcur >= tstop)
+				break;
+
+			do_poll(fdr, POLLIN, tstop - tcur);
+			rx += do_rx(fdr);
+		}
+	}
+
+	fprintf(stderr, "pkts: tx=%u rx=%u\n", tx, rx);
+
+	if (fdr != -1 && close(fdr))
+		error(1, errno, "close rx");
+	if (fdt != -1 && close(fdt))
+		error(1, errno, "close tx");
+
+	/*
+	 * success (== 0) only if received all packets
+	 * unless failure is expected, in which case none must arrive.
+	 */
+	if (cfg_expect_failure)
+		return rx != 0;
+	else
+		return rx != tx;
+}
+
+
+static void __attribute__((noreturn)) usage(const char *filepath)
+{
+	fprintf(stderr, "Usage: %s [-e gre|gue|bare|none] [-i 4|6] [-l len] "
+			"[-O 4|6] [-o 4|6] [-n num] [-t secs] [-R] [-T] "
+			"[-s <osrc> [-d <odst>] [-S <isrc>] [-D <idst>] "
+			"[-x <otos>] [-X <itos>] [-f <isport>] [-F]\n",
+		filepath);
+	exit(1);
+}
+
+static void parse_addr(int family, void *addr, const char *optarg)
+{
+	int ret;
+
+	ret = inet_pton(family, optarg, addr);
+	if (ret == -1)
+		error(1, errno, "inet_pton");
+	if (ret == 0)
+		error(1, 0, "inet_pton: bad string");
+}
+
+static void parse_addr4(struct sockaddr_in *addr, const char *optarg)
+{
+	parse_addr(AF_INET, &addr->sin_addr, optarg);
+}
+
+static void parse_addr6(struct sockaddr_in6 *addr, const char *optarg)
+{
+	parse_addr(AF_INET6, &addr->sin6_addr, optarg);
+}
+
+static int parse_protocol_family(const char *filepath, const char *optarg)
+{
+	if (!strcmp(optarg, "4"))
+		return PF_INET;
+	if (!strcmp(optarg, "6"))
+		return PF_INET6;
+
+	usage(filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int c;
+
+	while ((c = getopt(argc, argv, "d:D:e:f:Fhi:l:n:o:O:Rs:S:t:Tx:X:")) != -1) {
+		switch (c) {
+		case 'd':
+			if (cfg_l3_outer == AF_UNSPEC)
+				error(1, 0, "-d must be preceded by -o");
+			if (cfg_l3_outer == AF_INET)
+				parse_addr4(&out_daddr4, optarg);
+			else
+				parse_addr6(&out_daddr6, optarg);
+			break;
+		case 'D':
+			if (cfg_l3_inner == AF_UNSPEC)
+				error(1, 0, "-D must be preceded by -i");
+			if (cfg_l3_inner == AF_INET)
+				parse_addr4(&in_daddr4, optarg);
+			else
+				parse_addr6(&in_daddr6, optarg);
+			break;
+		case 'e':
+			if (!strcmp(optarg, "gre"))
+				cfg_encap_proto = IPPROTO_GRE;
+			else if (!strcmp(optarg, "gue"))
+				cfg_encap_proto = IPPROTO_UDP;
+			else if (!strcmp(optarg, "bare"))
+				cfg_encap_proto = IPPROTO_IPIP;
+			else if (!strcmp(optarg, "none"))
+				cfg_encap_proto = IPPROTO_IP;	/* == 0 */
+			else
+				usage(argv[0]);
+			break;
+		case 'f':
+			cfg_src_port = strtol(optarg, NULL, 0);
+			break;
+		case 'F':
+			cfg_expect_failure = true;
+			break;
+		case 'h':
+			usage(argv[0]);
+			break;
+		case 'i':
+			if (!strcmp(optarg, "4"))
+				cfg_l3_inner = PF_INET;
+			else if (!strcmp(optarg, "6"))
+				cfg_l3_inner = PF_INET6;
+			else
+				usage(argv[0]);
+			break;
+		case 'l':
+			cfg_payload_len = strtol(optarg, NULL, 0);
+			break;
+		case 'n':
+			cfg_num_pkt = strtol(optarg, NULL, 0);
+			break;
+		case 'o':
+			cfg_l3_outer = parse_protocol_family(argv[0], optarg);
+			break;
+		case 'O':
+			cfg_l3_extra = parse_protocol_family(argv[0], optarg);
+			break;
+		case 'R':
+			cfg_only_rx = true;
+			break;
+		case 's':
+			if (cfg_l3_outer == AF_INET)
+				parse_addr4(&out_saddr4, optarg);
+			else
+				parse_addr6(&out_saddr6, optarg);
+			break;
+		case 'S':
+			if (cfg_l3_inner == AF_INET)
+				parse_addr4(&in_saddr4, optarg);
+			else
+				parse_addr6(&in_saddr6, optarg);
+			break;
+		case 't':
+			cfg_num_secs = strtol(optarg, NULL, 0);
+			break;
+		case 'T':
+			cfg_only_tx = true;
+			break;
+		case 'x':
+			cfg_dsfield_outer = strtol(optarg, NULL, 0);
+			break;
+		case 'X':
+			cfg_dsfield_inner = strtol(optarg, NULL, 0);
+			break;
+		}
+	}
+
+	if (cfg_only_rx && cfg_only_tx)
+		error(1, 0, "options: cannot combine rx-only and tx-only");
+
+	if (cfg_encap_proto && cfg_l3_outer == AF_UNSPEC)
+		error(1, 0, "options: must specify outer with encap");
+	else if ((!cfg_encap_proto) && cfg_l3_outer != AF_UNSPEC)
+		error(1, 0, "options: cannot combine no-encap and outer");
+	else if ((!cfg_encap_proto) && cfg_l3_extra != AF_UNSPEC)
+		error(1, 0, "options: cannot combine no-encap and extra");
+
+	if (cfg_l3_inner == AF_UNSPEC)
+		cfg_l3_inner = AF_INET6;
+	if (cfg_l3_inner == AF_INET6 && cfg_encap_proto == IPPROTO_IPIP)
+		cfg_encap_proto = IPPROTO_IPV6;
+
+	/* RFC 6040 4.2:
+	 *   on decap, if outer encountered congestion (CE == 0x3),
+	 *   but inner cannot encode ECN (NoECT == 0x0), then drop packet.
+	 */
+	if (((cfg_dsfield_outer & 0x3) == 0x3) &&
+	    ((cfg_dsfield_inner & 0x3) == 0x0))
+		cfg_expect_failure = true;
+}
+
+static void print_opts(void)
+{
+	if (cfg_l3_inner == PF_INET6) {
+		util_printaddr("inner.dest6", (void *) &in_daddr6);
+		util_printaddr("inner.source6", (void *) &in_saddr6);
+	} else {
+		util_printaddr("inner.dest4", (void *) &in_daddr4);
+		util_printaddr("inner.source4", (void *) &in_saddr4);
+	}
+
+	if (!cfg_l3_outer)
+		return;
+
+	fprintf(stderr, "encap proto:   %u\n", cfg_encap_proto);
+
+	if (cfg_l3_outer == PF_INET6) {
+		util_printaddr("outer.dest6", (void *) &out_daddr6);
+		util_printaddr("outer.source6", (void *) &out_saddr6);
+	} else {
+		util_printaddr("outer.dest4", (void *) &out_daddr4);
+		util_printaddr("outer.source4", (void *) &out_saddr4);
+	}
+
+	if (!cfg_l3_extra)
+		return;
+
+	if (cfg_l3_outer == PF_INET6) {
+		util_printaddr("extra.dest6", (void *) &extra_daddr6);
+		util_printaddr("extra.source6", (void *) &extra_saddr6);
+	} else {
+		util_printaddr("extra.dest4", (void *) &extra_daddr4);
+		util_printaddr("extra.source4", (void *) &extra_saddr4);
+	}
+
+}
+
+int main(int argc, char **argv)
+{
+	parse_opts(argc, argv);
+	print_opts();
+	return do_main();
+}
diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh
new file mode 100755
index 000000000000..c0fb073b5eab
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_flow_dissector.sh
@@ -0,0 +1,115 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Load BPF flow dissector and verify it correctly dissects traffic
+export TESTNAME=test_flow_dissector
+unmount=0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ $UID != 0 ]; then
+	echo $msg please run this as root >&2
+	exit $ksft_skip
+fi
+
+# This test needs to be run in a network namespace with in_netns.sh. Check if
+# this is the case and run it with in_netns.sh if it is being run in the root
+# namespace.
+if [[ -z $(ip netns identify $$) ]]; then
+	../net/in_netns.sh "$0" "$@"
+	exit $?
+fi
+
+# Determine selftest success via shell exit code
+exit_handler()
+{
+	if (( $? == 0 )); then
+		echo "selftests: $TESTNAME [PASS]";
+	else
+		echo "selftests: $TESTNAME [FAILED]";
+	fi
+
+	set +e
+
+	# Cleanup
+	tc filter del dev lo ingress pref 1337 2> /dev/null
+	tc qdisc del dev lo ingress 2> /dev/null
+	./flow_dissector_load -d 2> /dev/null
+	if [ $unmount -ne 0 ]; then
+		umount bpffs 2> /dev/null
+	fi
+}
+
+# Exit script immediately (well catched by trap handler) if any
+# program/thing exits with a non-zero status.
+set -e
+
+# (Use 'trap -l' to list meaning of numbers)
+trap exit_handler 0 2 3 6 9
+
+# Mount BPF file system
+if /bin/mount | grep /sys/fs/bpf > /dev/null; then
+	echo "bpffs already mounted"
+else
+	echo "bpffs not mounted. Mounting..."
+	unmount=1
+	/bin/mount bpffs /sys/fs/bpf -t bpf
+fi
+
+# Attach BPF program
+./flow_dissector_load -p bpf_flow.o -s dissect
+
+# Setup
+tc qdisc add dev lo ingress
+
+echo "Testing IPv4..."
+# Drops all IP/UDP packets coming from port 9
+tc filter add dev lo parent ffff: protocol ip pref 1337 flower ip_proto \
+	udp src_port 9 action drop
+
+# Send 10 IPv4/UDP packets from port 8. Filter should not drop any.
+./test_flow_dissector -i 4 -f 8
+# Send 10 IPv4/UDP packets from port 9. Filter should drop all.
+./test_flow_dissector -i 4 -f 9 -F
+# Send 10 IPv4/UDP packets from port 10. Filter should not drop any.
+./test_flow_dissector -i 4 -f 10
+
+echo "Testing IPIP..."
+# Send 10 IPv4/IPv4/UDP packets from port 8. Filter should not drop any.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 8
+# Send 10 IPv4/IPv4/UDP packets from port 9. Filter should drop all.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 9 -F
+# Send 10 IPv4/IPv4/UDP packets from port 10. Filter should not drop any.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 10
+
+echo "Testing IPv4 + GRE..."
+# Send 10 IPv4/GRE/IPv4/UDP packets from port 8. Filter should not drop any.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 8
+# Send 10 IPv4/GRE/IPv4/UDP packets from port 9. Filter should drop all.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 9 -F
+# Send 10 IPv4/GRE/IPv4/UDP packets from port 10. Filter should not drop any.
+./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \
+	-D 192.168.0.1 -S 1.1.1.1 -f 10
+
+tc filter del dev lo ingress pref 1337
+
+echo "Testing IPv6..."
+# Drops all IPv6/UDP packets coming from port 9
+tc filter add dev lo parent ffff: protocol ipv6 pref 1337 flower ip_proto \
+	udp src_port 9 action drop
+
+# Send 10 IPv6/UDP packets from port 8. Filter should not drop any.
+./test_flow_dissector -i 6 -f 8
+# Send 10 IPv6/UDP packets from port 9. Filter should drop all.
+./test_flow_dissector -i 6 -f 9 -F
+# Send 10 IPv6/UDP packets from port 10. Filter should not drop any.
+./test_flow_dissector -i 6 -f 10
+
+exit 0
diff --git a/tools/testing/selftests/bpf/with_addr.sh b/tools/testing/selftests/bpf/with_addr.sh
new file mode 100755
index 000000000000..ffcd3953f94c
--- /dev/null
+++ b/tools/testing/selftests/bpf/with_addr.sh
@@ -0,0 +1,54 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# add private ipv4 and ipv6 addresses to loopback
+
+readonly V6_INNER='100::a/128'
+readonly V4_INNER='192.168.0.1/32'
+
+if getopts ":s" opt; then
+  readonly SIT_DEV_NAME='sixtofourtest0'
+  readonly V6_SIT='2::/64'
+  readonly V4_SIT='172.17.0.1/32'
+  shift
+fi
+
+fail() {
+  echo "error: $*" 1>&2
+  exit 1
+}
+
+setup() {
+  ip -6 addr add "${V6_INNER}" dev lo || fail 'failed to setup v6 address'
+  ip -4 addr add "${V4_INNER}" dev lo || fail 'failed to setup v4 address'
+
+  if [[ -n "${V6_SIT}" ]]; then
+    ip link add "${SIT_DEV_NAME}" type sit remote any local any \
+	    || fail 'failed to add sit'
+    ip link set dev "${SIT_DEV_NAME}" up \
+	    || fail 'failed to bring sit device up'
+    ip -6 addr add "${V6_SIT}" dev "${SIT_DEV_NAME}" \
+	    || fail 'failed to setup v6 SIT address'
+    ip -4 addr add "${V4_SIT}" dev "${SIT_DEV_NAME}" \
+	    || fail 'failed to setup v4 SIT address'
+  fi
+
+  sleep 2	# avoid race causing bind to fail
+}
+
+cleanup() {
+  if [[ -n "${V6_SIT}" ]]; then
+    ip -4 addr del "${V4_SIT}" dev "${SIT_DEV_NAME}"
+    ip -6 addr del "${V6_SIT}" dev "${SIT_DEV_NAME}"
+    ip link del "${SIT_DEV_NAME}"
+  fi
+
+  ip -4 addr del "${V4_INNER}" dev lo
+  ip -6 addr del "${V6_INNER}" dev lo
+}
+
+trap cleanup EXIT
+
+setup
+"$@"
+exit "$?"
diff --git a/tools/testing/selftests/bpf/with_tunnels.sh b/tools/testing/selftests/bpf/with_tunnels.sh
new file mode 100755
index 000000000000..e24949ed3a20
--- /dev/null
+++ b/tools/testing/selftests/bpf/with_tunnels.sh
@@ -0,0 +1,36 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# setup tunnels for flow dissection test
+
+readonly SUFFIX="test_$(mktemp -u XXXX)"
+CONFIG="remote 127.0.0.2 local 127.0.0.1 dev lo"
+
+setup() {
+  ip link add "ipip_${SUFFIX}" type ipip ${CONFIG}
+  ip link add "gre_${SUFFIX}" type gre ${CONFIG}
+  ip link add "sit_${SUFFIX}" type sit ${CONFIG}
+
+  echo "tunnels before test:"
+  ip tunnel show
+
+  ip link set "ipip_${SUFFIX}" up
+  ip link set "gre_${SUFFIX}" up
+  ip link set "sit_${SUFFIX}" up
+}
+
+
+cleanup() {
+  ip tunnel del "ipip_${SUFFIX}"
+  ip tunnel del "gre_${SUFFIX}"
+  ip tunnel del "sit_${SUFFIX}"
+
+  echo "tunnels after test:"
+  ip tunnel show
+}
+
+trap cleanup EXIT
+
+setup
+"$@"
+exit "$?"
-- 
cgit v1.2.3


From 70e88c758a6b8544b5e0d982e55d1e36f9aa0b85 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Fri, 14 Sep 2018 12:09:05 -0700
Subject: selftests/bpf: fix bpf_flow.c build

fix the following build error:
clang -I. -I./include/uapi -I../../../include/uapi -idirafter /usr/local/include -idirafter /data/users/ast/llvm/bld/lib/clang/7.0.0/include -idirafter /usr/include -Wno-compare-distinct-pointer-types \
	 -O2 -target bpf -emit-llvm -c bpf_flow.c -o - |      \
llc -march=bpf -mcpu=generic  -filetype=obj -o /data/users/ast/bpf-next/tools/testing/selftests/bpf/bpf_flow.o
LLVM ERROR: 'dissect' label emitted multiple times to assembly file
make: *** [/data/users/ast/bpf-next/tools/testing/selftests/bpf/bpf_flow.o] Error 1

Fixes: 9c98b13cc3bb ("flow_dissector: implements eBPF parser")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/bpf_flow.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/bpf_flow.c b/tools/testing/selftests/bpf/bpf_flow.c
index 5fb809d95867..107350a7821d 100644
--- a/tools/testing/selftests/bpf/bpf_flow.c
+++ b/tools/testing/selftests/bpf/bpf_flow.c
@@ -117,7 +117,7 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
 }
 
 SEC("dissect")
-int dissect(struct __sk_buff *skb)
+int _dissect(struct __sk_buff *skb)
 {
 	if (!skb->vlan_present)
 		return parse_eth_proto(skb, skb->protocol);
-- 
cgit v1.2.3


From 693b31b2fc1636f0aa7af53136d3b49f6ad9ff39 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 31 Jul 2018 17:55:57 -0300
Subject: powerpc/selftests: Wait all threads to join

Test tm-tmspr might exit before all threads stop executing, because it just
waits for the very last thread to join before proceeding/exiting.

This patch makes sure that all threads that were created will join before
proceeding/exiting.

This patch also guarantees that the amount of threads being created is equal
to thread_num.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/tm/tm-tmspr.c | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/tm/tm-tmspr.c b/tools/testing/selftests/powerpc/tm/tm-tmspr.c
index 2bda81c7bf23..df1d7d4b1c89 100644
--- a/tools/testing/selftests/powerpc/tm/tm-tmspr.c
+++ b/tools/testing/selftests/powerpc/tm/tm-tmspr.c
@@ -98,7 +98,7 @@ void texasr(void *in)
 
 int test_tmspr()
 {
-	pthread_t 	thread;
+	pthread_t	*thread;
 	int	   	thread_num;
 	unsigned long	i;
 
@@ -107,21 +107,28 @@ int test_tmspr()
 	/* To cause some context switching */
 	thread_num = 10 * sysconf(_SC_NPROCESSORS_ONLN);
 
+	thread = malloc(thread_num * sizeof(pthread_t));
+	if (thread == NULL)
+		return EXIT_FAILURE;
+
 	/* Test TFIAR and TFHAR */
-	for (i = 0 ; i < thread_num ; i += 2){
-		if (pthread_create(&thread, NULL, (void*)tfiar_tfhar, (void *)i))
+	for (i = 0; i < thread_num; i += 2) {
+		if (pthread_create(&thread[i], NULL, (void *)tfiar_tfhar,
+				   (void *)i))
 			return EXIT_FAILURE;
 	}
-	if (pthread_join(thread, NULL) != 0)
-		return EXIT_FAILURE;
-
 	/* Test TEXASR */
-	for (i = 0 ; i < thread_num ; i++){
-		if (pthread_create(&thread, NULL, (void*)texasr, (void *)i))
+	for (i = 1; i < thread_num; i += 2) {
+		if (pthread_create(&thread[i], NULL, (void *)texasr, (void *)i))
 			return EXIT_FAILURE;
 	}
-	if (pthread_join(thread, NULL) != 0)
-		return EXIT_FAILURE;
+
+	for (i = 0; i < thread_num; i++) {
+		if (pthread_join(thread[i], NULL) != 0)
+			return EXIT_FAILURE;
+	}
+
+	free(thread);
 
 	if (passed)
 		return 0;
-- 
cgit v1.2.3


From 0185e2e69f8e640defb77380b6b0d054c2ec12e4 Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Sun, 16 Sep 2018 10:04:28 +0530
Subject: selftests/tls: Add MSG_WAITALL in recv() syscall

A number of tls selftests rely upon recv() to return an exact number of
data bytes. When tls record crypto is done using an async accelerator,
it is possible that recv() returns lesser than expected number bytes.
This leads to failure of many test cases. To fix it, MSG_WAITALL has
been used in flags passed to recv() syscall.

Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/tls.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 07daff076ce0..96fc6fe70293 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -121,11 +121,11 @@ TEST_F(tls, send_then_sendfile)
 	buf = (char *)malloc(st.st_size);
 
 	EXPECT_EQ(send(self->fd, test_str, to_send, 0), to_send);
-	EXPECT_EQ(recv(self->cfd, recv_buf, to_send, 0), to_send);
+	EXPECT_EQ(recv(self->cfd, recv_buf, to_send, MSG_WAITALL), to_send);
 	EXPECT_EQ(memcmp(test_str, recv_buf, to_send), 0);
 
 	EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0);
-	EXPECT_EQ(recv(self->cfd, buf, st.st_size, 0), st.st_size);
+	EXPECT_EQ(recv(self->cfd, buf, st.st_size, MSG_WAITALL), st.st_size);
 }
 
 TEST_F(tls, recv_max)
@@ -160,7 +160,7 @@ TEST_F(tls, msg_more)
 	EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len);
 	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1);
 	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
-	EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_DONTWAIT),
+	EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_WAITALL),
 		  send_len * 2);
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 }
@@ -180,7 +180,7 @@ TEST_F(tls, sendmsg_single)
 	msg.msg_iov = &vec;
 	msg.msg_iovlen = 1;
 	EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len);
-	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len);
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 }
 
@@ -306,7 +306,7 @@ TEST_F(tls, splice_from_pipe2)
 	EXPECT_GE(splice(p[0], NULL, self->fd, NULL, 8000, 0), 0);
 	EXPECT_GE(write(p2[1], mem_send + 8000, 8000), 0);
 	EXPECT_GE(splice(p2[0], NULL, self->fd, NULL, 8000, 0), 0);
-	EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+	EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len);
 	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
 }
 
@@ -436,7 +436,7 @@ TEST_F(tls, multiple_send_single_recv)
 	EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0);
 	EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0);
 	memset(recv_mem, 0, total_len);
-	EXPECT_EQ(recv(self->cfd, recv_mem, total_len, 0), total_len);
+	EXPECT_EQ(recv(self->cfd, recv_mem, total_len, MSG_WAITALL), total_len);
 
 	EXPECT_EQ(memcmp(send_mem, recv_mem, send_len), 0);
 	EXPECT_EQ(memcmp(send_mem, recv_mem + send_len, send_len), 0);
@@ -537,7 +537,7 @@ TEST_F(tls, pollin)
 
 	EXPECT_EQ(poll(&fd, 1, 20), 1);
 	EXPECT_EQ(fd.revents & POLLIN, 1);
-	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len);
 	/* Test timing out */
 	EXPECT_EQ(poll(&fd, 1, 20), 0);
 }
@@ -555,7 +555,7 @@ TEST_F(tls, poll_wait)
 	/* Set timeout to inf. secs */
 	EXPECT_EQ(poll(&fd, 1, -1), 1);
 	EXPECT_EQ(fd.revents & POLLIN, 1);
-	EXPECT_EQ(recv(self->cfd, recv_mem, send_len, 0), send_len);
+	EXPECT_EQ(recv(self->cfd, recv_mem, send_len, MSG_WAITALL), send_len);
 }
 
 TEST_F(tls, blocking)
@@ -701,7 +701,7 @@ TEST_F(tls, control_msg)
 	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
 
 	vec.iov_base = buf;
-	EXPECT_EQ(recvmsg(self->cfd, &msg, 0), send_len);
+	EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL), send_len);
 	cmsg = CMSG_FIRSTHDR(&msg);
 	EXPECT_NE(cmsg, NULL);
 	EXPECT_EQ(cmsg->cmsg_level, SOL_TLS);
-- 
cgit v1.2.3


From 7900efc19214e326913dc0f0e8ded24adc0018f2 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 17 Sep 2018 16:13:00 -0700
Subject: tools/bpf: bpftool: improve output format for bpftool net

This is a followup patch for Commit f6f3bac08ff9
("tools/bpf: bpftool: add net support").
Some improvements are made for the bpftool net output.
Specially, plain output is more concise such that
per attachment should nicely fit in one line.
Compared to previous output, the prog tag is removed
since it can be easily obtained with program id.
Similar to xdp attachments, the device name is added
to tc attachments.

The bpf program attached through shared block
mechanism is supported as well.
  $ ip link add dev v1 type veth peer name v2
  $ tc qdisc add dev v1 ingress_block 10 egress_block 20 clsact
  $ tc qdisc add dev v2 ingress_block 10 egress_block 20 clsact
  $ tc filter add block 10 protocol ip prio 25 bpf obj bpf_shared.o sec ingress flowid 1:1
  $ tc filter add block 20 protocol ip prio 30 bpf obj bpf_cyclic.o sec classifier flowid 1:1
  $ bpftool net
  xdp:

  tc:
  v2(7) clsact/ingress bpf_shared.o:[ingress] id 23
  v2(7) clsact/egress bpf_cyclic.o:[classifier] id 24
  v1(8) clsact/ingress bpf_shared.o:[ingress] id 23
  v1(8) clsact/egress bpf_cyclic.o:[classifier] id 24

The documentation and "bpftool net help" are updated
to make it clear that current implementation only
supports xdp and tc attachments. For programs
attached to cgroups, "bpftool cgroup" can be used
to dump attachments. For other programs e.g.
sk_{filter,skb,msg,reuseport} and lwt/seg6,
iproute2 tools should be used.

The new output:
  $ bpftool net
  xdp:
  eth0(2) driver id 198

  tc:
  eth0(2) clsact/ingress fbflow_icmp id 335 act [{icmp_action id 336}]
  eth0(2) clsact/egress fbflow_egress id 334
  $ bpftool -jp net
  [{
        "xdp": [{
                "devname": "eth0",
                "ifindex": 2,
                "mode": "driver",
                "id": 198
            }
        ],
        "tc": [{
                "devname": "eth0",
                "ifindex": 2,
                "kind": "clsact/ingress",
                "name": "fbflow_icmp",
                "id": 335,
                "act": [{
                        "name": "icmp_action",
                        "id": 336
                    }
                ]
            },{
                "devname": "eth0",
                "ifindex": 2,
                "kind": "clsact/egress",
                "name": "fbflow_egress",
                "id": 334
            }
        ]
    }
  ]

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Documentation/bpftool-net.rst |  78 +++++++++---------
 tools/bpf/bpftool/main.h                        |   3 +-
 tools/bpf/bpftool/net.c                         | 103 ++++++++++++++++--------
 tools/bpf/bpftool/netlink_dumper.c              |  85 +++++++++----------
 tools/bpf/bpftool/netlink_dumper.h              |  22 ++---
 5 files changed, 161 insertions(+), 130 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst
index 48a61837a264..408ec30d8872 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-net.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst
@@ -26,9 +26,20 @@ NET COMMANDS
 DESCRIPTION
 ===========
 	**bpftool net { show | list } [ dev name ]**
-		  List all networking device driver and tc attachment in the system.
-
-                  Output will start with all xdp program attachment, followed by
+                  List bpf program attachments in the kernel networking subsystem.
+
+                  Currently, only device driver xdp attachments and tc filter
+                  classification/action attachments are implemented, i.e., for
+                  program types **BPF_PROG_TYPE_SCHED_CLS**,
+                  **BPF_PROG_TYPE_SCHED_ACT** and **BPF_PROG_TYPE_XDP**.
+                  For programs attached to a particular cgroup, e.g.,
+                  **BPF_PROG_TYPE_CGROUP_SKB**, **BPF_PROG_TYPE_CGROUP_SOCK**,
+                  **BPF_PROG_TYPE_SOCK_OPS** and **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**,
+                  users can use **bpftool cgroup** to dump cgroup attachments.
+                  For sk_{filter, skb, msg, reuseport} and lwt/seg6
+                  bpf programs, users should consult other tools, e.g., iproute2.
+
+                  The current output will start with all xdp program attachments, followed by
                   all tc class/qdisc bpf program attachments. Both xdp programs and
                   tc programs are ordered based on ifindex number. If multiple bpf
                   programs attached to the same networking device through **tc filter**,
@@ -61,21 +72,15 @@ EXAMPLES
 
 ::
 
-      xdp [
-      ifindex 2 devname eth0 prog_id 198
-      ]
-      tc_filters [
-      ifindex 2 kind qdisc_htb name prefix_matcher.o:[cls_prefix_matcher_htb]
-                prog_id 111727 tag d08fe3b4319bc2fd act []
-      ifindex 2 kind qdisc_clsact_ingress name fbflow_icmp
-                prog_id 130246 tag 3f265c7f26db62c9 act []
-      ifindex 2 kind qdisc_clsact_egress name prefix_matcher.o:[cls_prefix_matcher_clsact]
-                prog_id 111726 tag 99a197826974c876
-      ifindex 2 kind qdisc_clsact_egress name cls_fg_dscp
-                prog_id 108619 tag dc4630674fd72dcc act []
-      ifindex 2 kind qdisc_clsact_egress name fbflow_egress
-                prog_id 130245 tag 72d2d830d6888d2c
-      ]
+      xdp:
+      eth0(2) driver id 198
+
+      tc:
+      eth0(2) htb name prefix_matcher.o:[cls_prefix_matcher_htb] id 111727 act []
+      eth0(2) clsact/ingress fbflow_icmp id 130246 act []
+      eth0(2) clsact/egress prefix_matcher.o:[cls_prefix_matcher_clsact] id 111726
+      eth0(2) clsact/egress cls_fg_dscp id 108619 act []
+      eth0(2) clsact/egress fbflow_egress id 130245
 
 |
 | **# bpftool -jp net**
@@ -84,44 +89,45 @@ EXAMPLES
 
     [{
             "xdp": [{
-                    "ifindex": 2,
                     "devname": "eth0",
-                    "prog_id": 198
+                    "ifindex": 2,
+                    "mode": "driver",
+                    "id": 198
                 }
             ],
-            "tc_filters": [{
+            "tc": [{
+                    "devname": "eth0",
                     "ifindex": 2,
-                    "kind": "qdisc_htb",
+                    "kind": "htb",
                     "name": "prefix_matcher.o:[cls_prefix_matcher_htb]",
-                    "prog_id": 111727,
-                    "tag": "d08fe3b4319bc2fd",
+                    "id": 111727,
                     "act": []
                 },{
+                    "devname": "eth0",
                     "ifindex": 2,
-                    "kind": "qdisc_clsact_ingress",
+                    "kind": "clsact/ingress",
                     "name": "fbflow_icmp",
-                    "prog_id": 130246,
-                    "tag": "3f265c7f26db62c9",
+                    "id": 130246,
                     "act": []
                 },{
+                    "devname": "eth0",
                     "ifindex": 2,
-                    "kind": "qdisc_clsact_egress",
+                    "kind": "clsact/egress",
                     "name": "prefix_matcher.o:[cls_prefix_matcher_clsact]",
-                    "prog_id": 111726,
-                    "tag": "99a197826974c876"
+                    "id": 111726,
                 },{
+                    "devname": "eth0",
                     "ifindex": 2,
-                    "kind": "qdisc_clsact_egress",
+                    "kind": "clsact/egress",
                     "name": "cls_fg_dscp",
-                    "prog_id": 108619,
-                    "tag": "dc4630674fd72dcc",
+                    "id": 108619,
                     "act": []
                 },{
+                    "devname": "eth0",
                     "ifindex": 2,
-                    "kind": "qdisc_clsact_egress",
+                    "kind": "clsact/egress",
                     "name": "fbflow_egress",
-                    "prog_id": 130245,
-                    "tag": "72d2d830d6888d2c"
+                    "id": 130245,
                 }
             ]
         }
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 02dfbcb92a23..40492cdc4e53 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -171,5 +171,6 @@ struct nlattr;
 struct ifinfomsg;
 struct tcmsg;
 int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb);
-int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind);
+int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind,
+		   const char *devname, int ifindex);
 #endif
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index 77dd73dd9ade..ed205ee57655 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -2,6 +2,7 @@
 // Copyright (C) 2018 Facebook
 
 #define _GNU_SOURCE
+#include <errno.h>
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
@@ -17,8 +18,13 @@
 #include "main.h"
 #include "netlink_dumper.h"
 
+struct ip_devname_ifindex {
+	char	devname[64];
+	int	ifindex;
+};
+
 struct bpf_netdev_t {
-	int	*ifindex_array;
+	struct ip_devname_ifindex *devices;
 	int	used_len;
 	int	array_len;
 	int	filter_idx;
@@ -36,6 +42,12 @@ struct bpf_tcinfo_t {
 	bool			is_qdisc;
 };
 
+struct bpf_filter_t {
+	const char	*kind;
+	const char	*devname;
+	int		ifindex;
+};
+
 static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 {
 	struct bpf_netdev_t *netinfo = cookie;
@@ -45,11 +57,20 @@ static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 		return 0;
 
 	if (netinfo->used_len == netinfo->array_len) {
-		netinfo->ifindex_array = realloc(netinfo->ifindex_array,
-			(netinfo->array_len + 16) * sizeof(int));
+		netinfo->devices = realloc(netinfo->devices,
+			(netinfo->array_len + 16) *
+			sizeof(struct ip_devname_ifindex));
+		if (!netinfo->devices)
+			return -ENOMEM;
+
 		netinfo->array_len += 16;
 	}
-	netinfo->ifindex_array[netinfo->used_len++] = ifinfo->ifi_index;
+	netinfo->devices[netinfo->used_len].ifindex = ifinfo->ifi_index;
+	snprintf(netinfo->devices[netinfo->used_len].devname,
+		 sizeof(netinfo->devices[netinfo->used_len].devname),
+		 "%s",
+		 tb[IFLA_IFNAME] ? nla_getattr_str(tb[IFLA_IFNAME]) : "");
+	netinfo->used_len++;
 
 	return do_xdp_dump(ifinfo, tb);
 }
@@ -71,13 +92,15 @@ static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 	if (tcinfo->used_len == tcinfo->array_len) {
 		tcinfo->handle_array = realloc(tcinfo->handle_array,
 			(tcinfo->array_len + 16) * sizeof(struct tc_kind_handle));
+		if (!tcinfo->handle_array)
+			return -ENOMEM;
+
 		tcinfo->array_len += 16;
 	}
 	tcinfo->handle_array[tcinfo->used_len].handle = info->tcm_handle;
 	snprintf(tcinfo->handle_array[tcinfo->used_len].kind,
 		 sizeof(tcinfo->handle_array[tcinfo->used_len].kind),
-		 "%s_%s",
-		 tcinfo->is_qdisc ? "qdisc" : "class",
+		 "%s",
 		 tb[TCA_KIND] ? nla_getattr_str(tb[TCA_KIND]) : "unknown");
 	tcinfo->used_len++;
 
@@ -86,60 +109,71 @@ static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 
 static int dump_filter_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 {
-	const char *kind = cookie;
+	const struct bpf_filter_t *filter_info = cookie;
 
-	return do_filter_dump((struct tcmsg *)msg, tb, kind);
+	return do_filter_dump((struct tcmsg *)msg, tb, filter_info->kind,
+			      filter_info->devname, filter_info->ifindex);
 }
 
-static int show_dev_tc_bpf(int sock, unsigned int nl_pid, int ifindex)
+static int show_dev_tc_bpf(int sock, unsigned int nl_pid,
+			   struct ip_devname_ifindex *dev)
 {
+	struct bpf_filter_t filter_info;
 	struct bpf_tcinfo_t tcinfo;
-	int i, handle, ret;
+	int i, handle, ret = 0;
 
 	tcinfo.handle_array = NULL;
 	tcinfo.used_len = 0;
 	tcinfo.array_len = 0;
 
 	tcinfo.is_qdisc = false;
-	ret = nl_get_class(sock, nl_pid, ifindex, dump_class_qdisc_nlmsg,
+	ret = nl_get_class(sock, nl_pid, dev->ifindex, dump_class_qdisc_nlmsg,
 			   &tcinfo);
 	if (ret)
-		return ret;
+		goto out;
 
 	tcinfo.is_qdisc = true;
-	ret = nl_get_qdisc(sock, nl_pid, ifindex, dump_class_qdisc_nlmsg,
+	ret = nl_get_qdisc(sock, nl_pid, dev->ifindex, dump_class_qdisc_nlmsg,
 			   &tcinfo);
 	if (ret)
-		return ret;
+		goto out;
 
+	filter_info.devname = dev->devname;
+	filter_info.ifindex = dev->ifindex;
 	for (i = 0; i < tcinfo.used_len; i++) {
-		ret = nl_get_filter(sock, nl_pid, ifindex,
+		filter_info.kind = tcinfo.handle_array[i].kind;
+		ret = nl_get_filter(sock, nl_pid, dev->ifindex,
 				    tcinfo.handle_array[i].handle,
 				    dump_filter_nlmsg,
-				    tcinfo.handle_array[i].kind);
+				    &filter_info);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	/* root, ingress and egress handle */
 	handle = TC_H_ROOT;
-	ret = nl_get_filter(sock, nl_pid, ifindex, handle, dump_filter_nlmsg,
-			    "root");
+	filter_info.kind = "root";
+	ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+			    dump_filter_nlmsg, &filter_info);
 	if (ret)
-		return ret;
+		goto out;
 
 	handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS);
-	ret = nl_get_filter(sock, nl_pid, ifindex, handle, dump_filter_nlmsg,
-			    "qdisc_clsact_ingress");
+	filter_info.kind = "clsact/ingress";
+	ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+			    dump_filter_nlmsg, &filter_info);
 	if (ret)
-		return ret;
+		goto out;
 
 	handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_EGRESS);
-	ret = nl_get_filter(sock, nl_pid, ifindex, handle, dump_filter_nlmsg,
-			    "qdisc_clsact_egress");
+	filter_info.kind = "clsact/egress";
+	ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+			    dump_filter_nlmsg, &filter_info);
 	if (ret)
-		return ret;
+		goto out;
 
+out:
+	free(tcinfo.handle_array);
 	return 0;
 }
 
@@ -168,7 +202,7 @@ static int do_show(int argc, char **argv)
 		return -1;
 	}
 
-	dev_array.ifindex_array = NULL;
+	dev_array.devices = NULL;
 	dev_array.used_len = 0;
 	dev_array.array_len = 0;
 	dev_array.filter_idx = filter_idx;
@@ -176,15 +210,15 @@ static int do_show(int argc, char **argv)
 	if (json_output)
 		jsonw_start_array(json_wtr);
 	NET_START_OBJECT;
-	NET_START_ARRAY("xdp", "\n");
+	NET_START_ARRAY("xdp", "%s:\n");
 	ret = nl_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array);
 	NET_END_ARRAY("\n");
 
 	if (!ret) {
-		NET_START_ARRAY("tc_filters", "\n");
+		NET_START_ARRAY("tc", "%s:\n");
 		for (i = 0; i < dev_array.used_len; i++) {
 			ret = show_dev_tc_bpf(sock, nl_pid,
-					      dev_array.ifindex_array[i]);
+					      &dev_array.devices[i]);
 			if (ret)
 				break;
 		}
@@ -200,7 +234,7 @@ static int do_show(int argc, char **argv)
 		libbpf_strerror(ret, err_buf, sizeof(err_buf));
 		fprintf(stderr, "Error: %s\n", err_buf);
 	}
-	free(dev_array.ifindex_array);
+	free(dev_array.devices);
 	close(sock);
 	return ret;
 }
@@ -214,7 +248,12 @@ static int do_help(int argc, char **argv)
 
 	fprintf(stderr,
 		"Usage: %s %s { show | list } [dev <devname>]\n"
-		"       %s %s help\n",
+		"       %s %s help\n"
+		"Note: Only xdp and tc attachments are supported now.\n"
+		"      For progs attached to cgroups, use \"bpftool cgroup\"\n"
+		"      to dump program attachments. For program types\n"
+		"      sk_{filter,skb,msg,reuseport} and lwt/seg6, please\n"
+		"      consult iproute2.\n",
 		bin_name, argv[-2], bin_name, argv[-2]);
 
 	return 0;
diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c
index e12494fd1d2e..6f5e9cc6836c 100644
--- a/tools/bpf/bpftool/netlink_dumper.c
+++ b/tools/bpf/bpftool/netlink_dumper.c
@@ -12,12 +12,18 @@
 #include "netlink_dumper.h"
 
 static void xdp_dump_prog_id(struct nlattr **tb, int attr,
-			     const char *type)
+			     const char *mode,
+			     bool new_json_object)
 {
 	if (!tb[attr])
 		return;
 
-	NET_DUMP_UINT(type, nla_getattr_u32(tb[attr]))
+	if (new_json_object)
+		NET_START_OBJECT
+	NET_DUMP_STR("mode", " %s", mode);
+	NET_DUMP_UINT("id", " id %u", nla_getattr_u32(tb[attr]))
+	if (new_json_object)
+		NET_END_OBJECT
 }
 
 static int do_xdp_dump_one(struct nlattr *attr, unsigned int ifindex,
@@ -37,18 +43,26 @@ static int do_xdp_dump_one(struct nlattr *attr, unsigned int ifindex,
 		return 0;
 
 	NET_START_OBJECT;
-	NET_DUMP_UINT("ifindex", ifindex);
-
 	if (name)
-		NET_DUMP_STR("devname", name);
-
-	if (tb[IFLA_XDP_PROG_ID])
-		NET_DUMP_UINT("prog_id", nla_getattr_u32(tb[IFLA_XDP_PROG_ID]));
+		NET_DUMP_STR("devname", "%s", name);
+	NET_DUMP_UINT("ifindex", "(%d)", ifindex);
 
 	if (mode == XDP_ATTACHED_MULTI) {
-		xdp_dump_prog_id(tb, IFLA_XDP_SKB_PROG_ID, "generic_prog_id");
-		xdp_dump_prog_id(tb, IFLA_XDP_DRV_PROG_ID, "drv_prog_id");
-		xdp_dump_prog_id(tb, IFLA_XDP_HW_PROG_ID, "offload_prog_id");
+		if (json_output) {
+			jsonw_name(json_wtr, "multi_attachments");
+			jsonw_start_array(json_wtr);
+		}
+		xdp_dump_prog_id(tb, IFLA_XDP_SKB_PROG_ID, "generic", true);
+		xdp_dump_prog_id(tb, IFLA_XDP_DRV_PROG_ID, "driver", true);
+		xdp_dump_prog_id(tb, IFLA_XDP_HW_PROG_ID, "offload", true);
+		if (json_output)
+			jsonw_end_array(json_wtr);
+	} else if (mode == XDP_ATTACHED_DRV) {
+		xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "driver", false);
+	} else if (mode == XDP_ATTACHED_SKB) {
+		xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "generic", false);
+	} else if (mode == XDP_ATTACHED_HW) {
+		xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "offload", false);
 	}
 
 	NET_END_OBJECT_FINAL;
@@ -64,26 +78,9 @@ int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb)
 			       nla_getattr_str(tb[IFLA_IFNAME]));
 }
 
-static char *hexstring_n2a(const unsigned char *str, int len,
-			   char *buf, int blen)
-{
-	char *ptr = buf;
-	int i;
-
-	for (i = 0; i < len; i++) {
-		if (blen < 3)
-			break;
-		sprintf(ptr, "%02x", str[i]);
-		ptr += 2;
-		blen -= 2;
-	}
-	return buf;
-}
-
 static int do_bpf_dump_one_act(struct nlattr *attr)
 {
 	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
-	char buf[256];
 
 	if (nla_parse_nested(tb, TCA_ACT_BPF_MAX, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
@@ -93,13 +90,11 @@ static int do_bpf_dump_one_act(struct nlattr *attr)
 
 	NET_START_OBJECT_NESTED2;
 	if (tb[TCA_ACT_BPF_NAME])
-		NET_DUMP_STR("name", nla_getattr_str(tb[TCA_ACT_BPF_NAME]));
+		NET_DUMP_STR("name", "%s",
+			     nla_getattr_str(tb[TCA_ACT_BPF_NAME]));
 	if (tb[TCA_ACT_BPF_ID])
-		NET_DUMP_UINT("bpf_id", nla_getattr_u32(tb[TCA_ACT_BPF_ID]));
-	if (tb[TCA_ACT_BPF_TAG])
-		NET_DUMP_STR("tag", hexstring_n2a(nla_data(tb[TCA_ACT_BPF_TAG]),
-						  nla_len(tb[TCA_ACT_BPF_TAG]),
-						  buf, sizeof(buf)));
+		NET_DUMP_UINT("id", " id %u",
+			      nla_getattr_u32(tb[TCA_ACT_BPF_ID]));
 	NET_END_OBJECT_NESTED;
 	return 0;
 }
@@ -128,13 +123,13 @@ static int do_bpf_act_dump(struct nlattr *attr)
 	if (nla_parse_nested(tb, TCA_ACT_MAX_PRIO, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
-	NET_START_ARRAY("act", "");
+	NET_START_ARRAY("act", " %s [");
 	for (act = 0; act <= TCA_ACT_MAX_PRIO; act++) {
 		ret = do_dump_one_act(tb[act]);
 		if (ret)
 			break;
 	}
-	NET_END_ARRAY(" ");
+	NET_END_ARRAY("] ");
 
 	return ret;
 }
@@ -142,20 +137,15 @@ static int do_bpf_act_dump(struct nlattr *attr)
 static int do_bpf_filter_dump(struct nlattr *attr)
 {
 	struct nlattr *tb[TCA_BPF_MAX + 1];
-	char buf[256];
 	int ret;
 
 	if (nla_parse_nested(tb, TCA_BPF_MAX, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	if (tb[TCA_BPF_NAME])
-		NET_DUMP_STR("name", nla_getattr_str(tb[TCA_BPF_NAME]));
+		NET_DUMP_STR("name", " %s", nla_getattr_str(tb[TCA_BPF_NAME]));
 	if (tb[TCA_BPF_ID])
-		NET_DUMP_UINT("prog_id", nla_getattr_u32(tb[TCA_BPF_ID]));
-	if (tb[TCA_BPF_TAG])
-		NET_DUMP_STR("tag", hexstring_n2a(nla_data(tb[TCA_BPF_TAG]),
-						  nla_len(tb[TCA_BPF_TAG]),
-						  buf, sizeof(buf)));
+		NET_DUMP_UINT("id", " id %u", nla_getattr_u32(tb[TCA_BPF_ID]));
 	if (tb[TCA_BPF_ACT]) {
 		ret = do_bpf_act_dump(tb[TCA_BPF_ACT]);
 		if (ret)
@@ -165,14 +155,17 @@ static int do_bpf_filter_dump(struct nlattr *attr)
 	return 0;
 }
 
-int do_filter_dump(struct tcmsg *info, struct nlattr **tb, const char *kind)
+int do_filter_dump(struct tcmsg *info, struct nlattr **tb, const char *kind,
+		   const char *devname, int ifindex)
 {
 	int ret = 0;
 
 	if (tb[TCA_OPTIONS] && strcmp(nla_data(tb[TCA_KIND]), "bpf") == 0) {
 		NET_START_OBJECT;
-		NET_DUMP_UINT("ifindex", info->tcm_ifindex);
-		NET_DUMP_STR("kind", kind);
+		if (devname[0] != '\0')
+			NET_DUMP_STR("devname", "%s", devname);
+		NET_DUMP_UINT("ifindex", "(%u)", ifindex);
+		NET_DUMP_STR("kind", " %s", kind);
 		ret = do_bpf_filter_dump(tb[TCA_OPTIONS]);
 		NET_END_OBJECT_FINAL;
 	}
diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h
index 552d8851ac06..0788cfbbed0e 100644
--- a/tools/bpf/bpftool/netlink_dumper.h
+++ b/tools/bpf/bpftool/netlink_dumper.h
@@ -50,13 +50,13 @@
 		fprintf(stderr, "\n");			\
 }
 
-#define NET_START_ARRAY(name, newline)			\
+#define NET_START_ARRAY(name, fmt_str)			\
 {							\
 	if (json_output) {				\
 		jsonw_name(json_wtr, name);		\
 		jsonw_start_array(json_wtr);		\
 	} else {					\
-		fprintf(stderr, "%s [%s", name, newline);\
+		fprintf(stderr, fmt_str, name);		\
 	}						\
 }
 
@@ -65,31 +65,23 @@
 	if (json_output)				\
 		jsonw_end_array(json_wtr);		\
 	else						\
-		fprintf(stderr, "]%s", endstr);		\
+		fprintf(stderr, "%s", endstr);		\
 }
 
-#define NET_DUMP_UINT(name, val)			\
+#define NET_DUMP_UINT(name, fmt_str, val)		\
 {							\
 	if (json_output)				\
 		jsonw_uint_field(json_wtr, name, val);	\
 	else						\
-		fprintf(stderr, "%s %d ", name, val);	\
+		fprintf(stderr, fmt_str, val);		\
 }
 
-#define NET_DUMP_LLUINT(name, val)			\
-{							\
-	if (json_output)				\
-		jsonw_lluint_field(json_wtr, name, val);\
-	else						\
-		fprintf(stderr, "%s %lld ", name, val);	\
-}
-
-#define NET_DUMP_STR(name, str)				\
+#define NET_DUMP_STR(name, fmt_str, str)		\
 {							\
 	if (json_output)				\
 		jsonw_string_field(json_wtr, name, str);\
 	else						\
-		fprintf(stderr, "%s %s ", name, str);	\
+		fprintf(stderr, fmt_str, str);		\
 }
 
 #define NET_DUMP_STR_ONLY(str)				\
-- 
cgit v1.2.3


From 2e85d5979e8d2866db6185de231461b21159ef6f Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Date: Wed, 12 Sep 2018 11:42:29 +0530
Subject: perf test: Add watchpoint test

We don't have a 'perf test' entry available to test the watchpoint
functionality.

Add a simple set of tests:

 - Read only watchpoint
 - Write only watchpoint
 - Read / Write watchpoint
 - Runtime watchpoint modification

Ex.: on powerpc:

  $ sudo perf test 22
  22: Watchpoint                                            :
  22.1: Read Only Watchpoint                                : Ok
  22.2: Write Only Watchpoint                               : Ok
  22.3: Read / Write Watchpoint                             : Ok
  22.4: Modify Watchpoint                                   : Ok

Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Hendrik Brueckner <brueckner@linux.ibm.com>
Cc: Kate Stewart <kstewart@linuxfoundation.org>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Sandipan Das <sandipan@linux.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: http://lkml.kernel.org/r/20180912061229.22832-1-ravi.bangoria@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/Build          |   1 +
 tools/perf/tests/builtin-test.c |   9 ++
 tools/perf/tests/tests.h        |   3 +
 tools/perf/tests/wp.c           | 229 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 242 insertions(+)
 create mode 100644 tools/perf/tests/wp.c

(limited to 'tools')

diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 6c108fa79ae3..0b2b8305c965 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -21,6 +21,7 @@ perf-y += python-use.o
 perf-y += bp_signal.o
 perf-y += bp_signal_overflow.o
 perf-y += bp_account.o
+perf-y += wp.o
 perf-y += task-exit.o
 perf-y += sw-clock.o
 perf-y += mmap-thread-lookup.o
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index d7a5e1b9aa6f..54ca7d87236f 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -120,6 +120,15 @@ static struct test generic_tests[] = {
 		.func = test__bp_accounting,
 		.is_supported = test__bp_signal_is_supported,
 	},
+	{
+		.desc = "Watchpoint",
+		.func = test__wp,
+		.subtest = {
+			.skip_if_fail	= false,
+			.get_nr		= test__wp_subtest_get_nr,
+			.get_desc	= test__wp_subtest_get_desc,
+		},
+	},
 	{
 		.desc = "Number of exit events of a simple workload",
 		.func = test__task_exit,
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index a9760e790563..8e26a4148f30 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -59,6 +59,9 @@ int test__python_use(struct test *test, int subtest);
 int test__bp_signal(struct test *test, int subtest);
 int test__bp_signal_overflow(struct test *test, int subtest);
 int test__bp_accounting(struct test *test, int subtest);
+int test__wp(struct test *test, int subtest);
+const char *test__wp_subtest_get_desc(int subtest);
+int test__wp_subtest_get_nr(void);
 int test__task_exit(struct test *test, int subtest);
 int test__mem(struct test *test, int subtest);
 int test__sw_clock_freq(struct test *test, int subtest);
diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c
new file mode 100644
index 000000000000..017a99317f94
--- /dev/null
+++ b/tools/perf/tests/wp.c
@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdlib.h>
+#include <sys/ioctl.h>
+#include <linux/hw_breakpoint.h>
+#include "tests.h"
+#include "debug.h"
+#include "cloexec.h"
+
+#define WP_TEST_ASSERT_VAL(fd, text, val)       \
+do {                                            \
+	long long count;                        \
+	wp_read(fd, &count, sizeof(long long)); \
+	TEST_ASSERT_VAL(text, count == val);    \
+} while (0)
+
+volatile u64 data1;
+volatile u8 data2[3];
+
+static int wp_read(int fd, long long *count, int size)
+{
+	int ret = read(fd, count, size);
+
+	if (ret != size) {
+		pr_debug("failed to read: %d\n", ret);
+		return -1;
+	}
+	return 0;
+}
+
+static void get__perf_event_attr(struct perf_event_attr *attr, int wp_type,
+				 void *wp_addr, unsigned long wp_len)
+{
+	memset(attr, 0, sizeof(struct perf_event_attr));
+	attr->type           = PERF_TYPE_BREAKPOINT;
+	attr->size           = sizeof(struct perf_event_attr);
+	attr->config         = 0;
+	attr->bp_type        = wp_type;
+	attr->bp_addr        = (unsigned long)wp_addr;
+	attr->bp_len         = wp_len;
+	attr->sample_period  = 1;
+	attr->sample_type    = PERF_SAMPLE_IP;
+	attr->exclude_kernel = 1;
+	attr->exclude_hv     = 1;
+}
+
+static int __event(int wp_type, void *wp_addr, unsigned long wp_len)
+{
+	int fd;
+	struct perf_event_attr attr;
+
+	get__perf_event_attr(&attr, wp_type, wp_addr, wp_len);
+	fd = sys_perf_event_open(&attr, 0, -1, -1,
+				 perf_event_open_cloexec_flag());
+	if (fd < 0)
+		pr_debug("failed opening event %x\n", attr.bp_type);
+
+	return fd;
+}
+
+static int wp_ro_test(void)
+{
+	int fd;
+	unsigned long tmp, tmp1 = rand();
+
+	fd = __event(HW_BREAKPOINT_R, (void *)&data1, sizeof(data1));
+	if (fd < 0)
+		return -1;
+
+	tmp = data1;
+	WP_TEST_ASSERT_VAL(fd, "RO watchpoint", 1);
+
+	data1 = tmp1 + tmp;
+	WP_TEST_ASSERT_VAL(fd, "RO watchpoint", 1);
+
+	close(fd);
+	return 0;
+}
+
+static int wp_wo_test(void)
+{
+	int fd;
+	unsigned long tmp, tmp1 = rand();
+
+	fd = __event(HW_BREAKPOINT_W, (void *)&data1, sizeof(data1));
+	if (fd < 0)
+		return -1;
+
+	tmp = data1;
+	WP_TEST_ASSERT_VAL(fd, "WO watchpoint", 0);
+
+	data1 = tmp1 + tmp;
+	WP_TEST_ASSERT_VAL(fd, "WO watchpoint", 1);
+
+	close(fd);
+	return 0;
+}
+
+static int wp_rw_test(void)
+{
+	int fd;
+	unsigned long tmp, tmp1 = rand();
+
+	fd = __event(HW_BREAKPOINT_R | HW_BREAKPOINT_W, (void *)&data1,
+		     sizeof(data1));
+	if (fd < 0)
+		return -1;
+
+	tmp = data1;
+	WP_TEST_ASSERT_VAL(fd, "RW watchpoint", 1);
+
+	data1 = tmp1 + tmp;
+	WP_TEST_ASSERT_VAL(fd, "RW watchpoint", 2);
+
+	close(fd);
+	return 0;
+}
+
+static int wp_modify_test(void)
+{
+	int fd, ret;
+	unsigned long tmp = rand();
+	struct perf_event_attr new_attr;
+
+	fd = __event(HW_BREAKPOINT_W, (void *)&data1, sizeof(data1));
+	if (fd < 0)
+		return -1;
+
+	data1 = tmp;
+	WP_TEST_ASSERT_VAL(fd, "Modify watchpoint", 1);
+
+	/* Modify watchpoint with disabled = 1 */
+	get__perf_event_attr(&new_attr, HW_BREAKPOINT_W, (void *)&data2[0],
+			     sizeof(u8) * 2);
+	new_attr.disabled = 1;
+	ret = ioctl(fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &new_attr);
+	if (ret < 0) {
+		pr_debug("ioctl(PERF_EVENT_IOC_MODIFY_ATTRIBUTES) failed\n");
+		close(fd);
+		return ret;
+	}
+
+	data2[1] = tmp; /* Not Counted */
+	WP_TEST_ASSERT_VAL(fd, "Modify watchpoint", 1);
+
+	/* Enable the event */
+	ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
+	if (ret < 0) {
+		pr_debug("Failed to enable event\n");
+		close(fd);
+		return ret;
+	}
+
+	data2[1] = tmp; /* Counted */
+	WP_TEST_ASSERT_VAL(fd, "Modify watchpoint", 2);
+
+	data2[2] = tmp; /* Not Counted */
+	WP_TEST_ASSERT_VAL(fd, "Modify watchpoint", 2);
+
+	close(fd);
+	return 0;
+}
+
+static bool wp_ro_supported(void)
+{
+#if defined (__x86_64__) || defined (__i386__)
+	return false;
+#else
+	return true;
+#endif
+}
+
+static void wp_ro_skip_msg(void)
+{
+#if defined (__x86_64__) || defined (__i386__)
+	pr_debug("Hardware does not support read only watchpoints.\n");
+#endif
+}
+
+static struct {
+	const char *desc;
+	int (*target_func)(void);
+	bool (*is_supported)(void);
+	void (*skip_msg)(void);
+} wp_testcase_table[] = {
+	{
+		.desc = "Read Only Watchpoint",
+		.target_func = &wp_ro_test,
+		.is_supported = &wp_ro_supported,
+		.skip_msg = &wp_ro_skip_msg,
+	},
+	{
+		.desc = "Write Only Watchpoint",
+		.target_func = &wp_wo_test,
+	},
+	{
+		.desc = "Read / Write Watchpoint",
+		.target_func = &wp_rw_test,
+	},
+	{
+		.desc = "Modify Watchpoint",
+		.target_func = &wp_modify_test,
+	},
+};
+
+int test__wp_subtest_get_nr(void)
+{
+	return (int)ARRAY_SIZE(wp_testcase_table);
+}
+
+const char *test__wp_subtest_get_desc(int i)
+{
+	if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table))
+		return NULL;
+	return wp_testcase_table[i].desc;
+}
+
+int test__wp(struct test *test __maybe_unused, int i)
+{
+	if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table))
+		return TEST_FAIL;
+
+	if (wp_testcase_table[i].is_supported &&
+	    !wp_testcase_table[i].is_supported()) {
+		wp_testcase_table[i].skip_msg();
+		return TEST_SKIP;
+	}
+
+	return !wp_testcase_table[i].target_func() ? TEST_OK : TEST_FAIL;
+}
-- 
cgit v1.2.3


From 44d947eff19d64384efc06069509db7a0a1103b0 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 12 Sep 2018 17:31:05 -0300
Subject: selftests/powerpc: Do not fail with reschedule

There are cases where the test is not expecting to have the transaction
aborted, but, the test process might have been rescheduled, either in the
OS level or by KVM (if it is running on a KVM guest machine). The process
reschedule will cause a treclaim/recheckpoint which will cause the
transaction to doom, aborting the transaction as soon as the process is
rescheduled back to the CPU. This might cause the test to fail, but this is
not a failure in essence.

If that is the case, TEXASR[FC] is indicated with either
TM_CAUSE_RESCHEDULE or TM_CAUSE_KVM_RESCHEDULE for KVM interruptions.

In this scenario, ignore these two failures and avoid the whole test to
return failure.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Gustavo Romero <gromero@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/tm/tm-unavailable.c | 9 ++++++---
 tools/testing/selftests/powerpc/tm/tm.h             | 9 +++++++++
 2 files changed, 15 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/tm/tm-unavailable.c b/tools/testing/selftests/powerpc/tm/tm-unavailable.c
index 156c8e750259..09894f4ff62e 100644
--- a/tools/testing/selftests/powerpc/tm/tm-unavailable.c
+++ b/tools/testing/selftests/powerpc/tm/tm-unavailable.c
@@ -236,7 +236,8 @@ void *tm_una_ping(void *input)
 	}
 
 	/* Check if we were not expecting a failure and a it occurred. */
-	if (!expecting_failure() && is_failure(cr_)) {
+	if (!expecting_failure() && is_failure(cr_) &&
+	    !failure_is_reschedule()) {
 		printf("\n\tUnexpected transaction failure 0x%02lx\n\t",
 			failure_code());
 		return (void *) -1;
@@ -244,9 +245,11 @@ void *tm_una_ping(void *input)
 
 	/*
 	 * Check if TM failed due to the cause we were expecting. 0xda is a
-	 * TM_CAUSE_FAC_UNAV cause, otherwise it's an unexpected cause.
+	 * TM_CAUSE_FAC_UNAV cause, otherwise it's an unexpected cause, unless
+	 * it was caused by a reschedule.
 	 */
-	if (is_failure(cr_) && !failure_is_unavailable()) {
+	if (is_failure(cr_) && !failure_is_unavailable() &&
+	    !failure_is_reschedule()) {
 		printf("\n\tUnexpected failure cause 0x%02lx\n\t",
 			failure_code());
 		return (void *) -1;
diff --git a/tools/testing/selftests/powerpc/tm/tm.h b/tools/testing/selftests/powerpc/tm/tm.h
index df4204247d45..5518b1d4ef8b 100644
--- a/tools/testing/selftests/powerpc/tm/tm.h
+++ b/tools/testing/selftests/powerpc/tm/tm.h
@@ -52,6 +52,15 @@ static inline bool failure_is_unavailable(void)
 	return (failure_code() & TM_CAUSE_FAC_UNAV) == TM_CAUSE_FAC_UNAV;
 }
 
+static inline bool failure_is_reschedule(void)
+{
+	if ((failure_code() & TM_CAUSE_RESCHED) == TM_CAUSE_RESCHED ||
+	    (failure_code() & TM_CAUSE_KVM_RESCHED) == TM_CAUSE_KVM_RESCHED)
+		return true;
+
+	return false;
+}
+
 static inline bool failure_is_nesting(void)
 {
 	return (__builtin_get_texasru() & 0x400000);
-- 
cgit v1.2.3


From d5ceb62b36545b597e89adb5eb778c3e15431c10 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Fri, 7 Sep 2018 12:24:54 +0200
Subject: perf ordered_events: Add 'struct ordered_events_buffer' layer

When ordering events, we use preallocated buffers to store separate
events.  Those buffers currently don't have their own struct, but since
they are basically an array of 'struct ordered_event' objects, we use
the first event to hold buffers data - list head, that holds all buffers
together:

   struct ordered_events {
     ...
     struct ordered_event *buffer;
     ...
   };

   struct ordered_event {
     u64               timestamp;
     u64               file_offset;
     union perf_event  *event;
     struct list_head  list;
   };

This is quite convoluted and error prone as demonstrated by free-ing
issue discovered and fixed by Stephane in here [1].

This patch adds the 'struct ordered_events_buffer' object, that holds
the buffer data and frees it up properly.

[1] - https://marc.info/?l=linux-kernel&m=153376761329335&w=2

Reported-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Stephane Eranian <eranian@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180907102455.7030-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/ordered-events.c | 83 +++++++++++++++++++++++++++++++++-------
 tools/perf/util/ordered-events.h | 37 ++++++++++--------
 2 files changed, 91 insertions(+), 29 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index bad9e0296e9a..84ce25272c13 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -80,14 +80,20 @@ static union perf_event *dup_event(struct ordered_events *oe,
 	return oe->copy_on_queue ? __dup_event(oe, event) : event;
 }
 
-static void free_dup_event(struct ordered_events *oe, union perf_event *event)
+static void __free_dup_event(struct ordered_events *oe, union perf_event *event)
 {
-	if (event && oe->copy_on_queue) {
+	if (event) {
 		oe->cur_alloc_size -= event->header.size;
 		free(event);
 	}
 }
 
+static void free_dup_event(struct ordered_events *oe, union perf_event *event)
+{
+	if (oe->copy_on_queue)
+		__free_dup_event(oe, event);
+}
+
 #define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct ordered_event))
 static struct ordered_event *alloc_event(struct ordered_events *oe,
 					 union perf_event *event)
@@ -100,15 +106,43 @@ static struct ordered_event *alloc_event(struct ordered_events *oe,
 	if (!new_event)
 		return NULL;
 
+	/*
+	 * We maintain the following scheme of buffers for ordered
+	 * event allocation:
+	 *
+	 *   to_free list -> buffer1 (64K)
+	 *                   buffer2 (64K)
+	 *                   ...
+	 *
+	 * Each buffer keeps an array of ordered events objects:
+	 *    buffer -> event[0]
+	 *              event[1]
+	 *              ...
+	 *
+	 * Each allocated ordered event is linked to one of
+	 * following lists:
+	 *   - time ordered list 'events'
+	 *   - list of currently removed events 'cache'
+	 *
+	 * Allocation of the ordered event uses the following order
+	 * to get the memory:
+	 *   - use recently removed object from 'cache' list
+	 *   - use available object in current allocation buffer
+	 *   - allocate new buffer if the current buffer is full
+	 *
+	 * Removal of ordered event object moves it from events to
+	 * the cache list.
+	 */
 	if (!list_empty(cache)) {
 		new = list_entry(cache->next, struct ordered_event, list);
 		list_del(&new->list);
 	} else if (oe->buffer) {
-		new = oe->buffer + oe->buffer_idx;
+		new = &oe->buffer->event[oe->buffer_idx];
 		if (++oe->buffer_idx == MAX_SAMPLE_BUFFER)
 			oe->buffer = NULL;
 	} else if (oe->cur_alloc_size < oe->max_alloc_size) {
-		size_t size = MAX_SAMPLE_BUFFER * sizeof(*new);
+		size_t size = sizeof(*oe->buffer) +
+			      MAX_SAMPLE_BUFFER * sizeof(*new);
 
 		oe->buffer = malloc(size);
 		if (!oe->buffer) {
@@ -122,11 +156,11 @@ static struct ordered_event *alloc_event(struct ordered_events *oe,
 		oe->cur_alloc_size += size;
 		list_add(&oe->buffer->list, &oe->to_free);
 
-		/* First entry is abused to maintain the to_free list. */
-		oe->buffer_idx = 2;
-		new = oe->buffer + 1;
+		oe->buffer_idx = 1;
+		new = &oe->buffer->event[0];
 	} else {
 		pr("allocation limit reached %" PRIu64 "B\n", oe->max_alloc_size);
+		return NULL;
 	}
 
 	new->event = new_event;
@@ -300,15 +334,38 @@ void ordered_events__init(struct ordered_events *oe, ordered_events__deliver_t d
 	oe->deliver	   = deliver;
 }
 
+static void
+ordered_events_buffer__free(struct ordered_events_buffer *buffer,
+			    unsigned int max, struct ordered_events *oe)
+{
+	if (oe->copy_on_queue) {
+		unsigned int i;
+
+		for (i = 0; i < max; i++)
+			__free_dup_event(oe, buffer->event[i].event);
+	}
+
+	free(buffer);
+}
+
 void ordered_events__free(struct ordered_events *oe)
 {
-	while (!list_empty(&oe->to_free)) {
-		struct ordered_event *event;
+	struct ordered_events_buffer *buffer, *tmp;
 
-		event = list_entry(oe->to_free.next, struct ordered_event, list);
-		list_del(&event->list);
-		free_dup_event(oe, event->event);
-		free(event);
+	if (list_empty(&oe->to_free))
+		return;
+
+	/*
+	 * Current buffer might not have all the events allocated
+	 * yet, we need to free only allocated ones ...
+	 */
+	list_del(&oe->buffer->list);
+	ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe);
+
+	/* ... and continue with the rest */
+	list_for_each_entry_safe(buffer, tmp, &oe->to_free, list) {
+		list_del(&buffer->list);
+		ordered_events_buffer__free(buffer, MAX_SAMPLE_BUFFER, oe);
 	}
 }
 
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
index 8c7a2948593e..1338d5c345dc 100644
--- a/tools/perf/util/ordered-events.h
+++ b/tools/perf/util/ordered-events.h
@@ -25,23 +25,28 @@ struct ordered_events;
 typedef int (*ordered_events__deliver_t)(struct ordered_events *oe,
 					 struct ordered_event *event);
 
+struct ordered_events_buffer {
+	struct list_head	list;
+	struct ordered_event	event[0];
+};
+
 struct ordered_events {
-	u64			last_flush;
-	u64			next_flush;
-	u64			max_timestamp;
-	u64			max_alloc_size;
-	u64			cur_alloc_size;
-	struct list_head	events;
-	struct list_head	cache;
-	struct list_head	to_free;
-	struct ordered_event	*buffer;
-	struct ordered_event	*last;
-	ordered_events__deliver_t deliver;
-	int			buffer_idx;
-	unsigned int		nr_events;
-	enum oe_flush		last_flush_type;
-	u32			nr_unordered_events;
-	bool                    copy_on_queue;
+	u64				 last_flush;
+	u64				 next_flush;
+	u64				 max_timestamp;
+	u64				 max_alloc_size;
+	u64				 cur_alloc_size;
+	struct list_head		 events;
+	struct list_head		 cache;
+	struct list_head		 to_free;
+	struct ordered_events_buffer	*buffer;
+	struct ordered_event		*last;
+	ordered_events__deliver_t	 deliver;
+	int				 buffer_idx;
+	unsigned int			 nr_events;
+	enum oe_flush			 last_flush_type;
+	u32				 nr_unordered_events;
+	bool				 copy_on_queue;
 };
 
 int ordered_events__queue(struct ordered_events *oe, union perf_event *event,
-- 
cgit v1.2.3


From 53da12e013498c4eca592939bb18a5dbd1d228c9 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Fri, 7 Sep 2018 12:24:55 +0200
Subject: perf ordered_events: Prevent crossing max_alloc_size

Stephane reported a possible issue in the ordered events code, which
could lead to allocating more memory than guarded by max_alloc_size.

He also suggested the fix to properly check that the new size is below
the max_alloc_size limit.

Reported-by: Stephane Eranian <eranian@google.com>
Suggested-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180907102455.7030-2-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/ordered-events.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index 84ce25272c13..1904e7f6ec84 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -101,6 +101,7 @@ static struct ordered_event *alloc_event(struct ordered_events *oe,
 	struct list_head *cache = &oe->cache;
 	struct ordered_event *new = NULL;
 	union perf_event *new_event;
+	size_t size;
 
 	new_event = dup_event(oe, event);
 	if (!new_event)
@@ -133,6 +134,8 @@ static struct ordered_event *alloc_event(struct ordered_events *oe,
 	 * Removal of ordered event object moves it from events to
 	 * the cache list.
 	 */
+	size = sizeof(*oe->buffer) + MAX_SAMPLE_BUFFER * sizeof(*new);
+
 	if (!list_empty(cache)) {
 		new = list_entry(cache->next, struct ordered_event, list);
 		list_del(&new->list);
@@ -140,10 +143,7 @@ static struct ordered_event *alloc_event(struct ordered_events *oe,
 		new = &oe->buffer->event[oe->buffer_idx];
 		if (++oe->buffer_idx == MAX_SAMPLE_BUFFER)
 			oe->buffer = NULL;
-	} else if (oe->cur_alloc_size < oe->max_alloc_size) {
-		size_t size = sizeof(*oe->buffer) +
-			      MAX_SAMPLE_BUFFER * sizeof(*new);
-
+	} else if ((oe->cur_alloc_size + size) < oe->max_alloc_size) {
 		oe->buffer = malloc(size);
 		if (!oe->buffer) {
 			free_dup_event(oe, new_event);
-- 
cgit v1.2.3


From 01ab2e91103b8c23dfedfeb799bc8b810d585bd0 Mon Sep 17 00:00:00 2001
From: Ding Xiang <dingxiang@cmss.chinamobile.com>
Date: Fri, 7 Sep 2018 09:34:41 +0800
Subject: tools include: Adopt PTR_ERR_OR_ZERO from the kernel err.h header

Add PTR_ERR_OR_ZERO, so that tools can use it, just like the kernel.

Signed-off-by: Ding Xiang <dingxiang@cmss.chinamobile.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1536284082-23466-1-git-send-email-dingxiang@cmss.chinamobile.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/err.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'tools')

diff --git a/tools/include/linux/err.h b/tools/include/linux/err.h
index 7a8b61ad44cb..094649667bae 100644
--- a/tools/include/linux/err.h
+++ b/tools/include/linux/err.h
@@ -52,4 +52,11 @@ static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr)
 	return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr);
 }
 
+static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr)
+{
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
+	else
+		return 0;
+}
 #endif /* _LINUX_ERR_H */
-- 
cgit v1.2.3


From e381d1c21eea186daed6834af444575e06841355 Mon Sep 17 00:00:00 2001
From: Ding Xiang <dingxiang@cmss.chinamobile.com>
Date: Fri, 7 Sep 2018 09:34:42 +0800
Subject: perf bpf-loader: use PTR_ERR_OR_ZERO inetead of return code

Use PTR_ERR_OR_ZERO() in bpf__setup_stdout() return code instead of open
coded equivalent.

Signed-off-by: Ding Xiang <dingxiang@cmss.chinamobile.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1536284082-23466-2-git-send-email-dingxiang@cmss.chinamobile.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/bpf-loader.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 47aac41349a2..f9ae1a993806 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -1615,7 +1615,7 @@ struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const cha
 int bpf__setup_stdout(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel = bpf__setup_output_event(evlist, "__bpf_stdout__");
-	return IS_ERR(evsel) ? PTR_ERR(evsel) : 0;
+	return PTR_ERR_OR_ZERO(evsel);
 }
 
 #define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
-- 
cgit v1.2.3


From 89f1688a57a8f0b685fccd648e601a1f830fa744 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 13 Sep 2018 14:54:03 +0200
Subject: perf tools: Remove perf_tool from event_op2

Now that we keep a perf_tool pointer inside perf_session, there's no
need to have a perf_tool argument in the event_op2 callback. Remove it.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180913125450.21342-2-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-annotate.c |  7 ++---
 tools/perf/builtin-inject.c   | 26 +++++++----------
 tools/perf/builtin-report.c   |  9 +++---
 tools/perf/builtin-script.c   | 38 ++++++++++++------------
 tools/perf/builtin-stat.c     | 23 +++++++--------
 tools/perf/util/auxtrace.c    | 10 +++----
 tools/perf/util/auxtrace.h    | 10 +++----
 tools/perf/util/header.c      | 16 +++++------
 tools/perf/util/header.h      | 15 ++++------
 tools/perf/util/session.c     | 67 ++++++++++++++++++-------------------------
 tools/perf/util/session.h     |  5 ++--
 tools/perf/util/stat.c        |  5 ++--
 tools/perf/util/stat.h        |  5 ++--
 tools/perf/util/tool.h        |  3 +-
 14 files changed, 103 insertions(+), 136 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 830481b8db26..93d679eaf1f4 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -283,12 +283,11 @@ out_put:
 	return ret;
 }
 
-static int process_feature_event(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session)
+static int process_feature_event(struct perf_session *session,
+				 union perf_event *event)
 {
 	if (event->feat.feat_id < HEADER_LAST_FEATURE)
-		return perf_event__process_feature(tool, event, session);
+		return perf_event__process_feature(session, event);
 	return 0;
 }
 
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index a3b346359ba0..d77ed2aea95a 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -86,12 +86,10 @@ static int perf_event__drop_oe(struct perf_tool *tool __maybe_unused,
 }
 #endif
 
-static int perf_event__repipe_op2_synth(struct perf_tool *tool,
-					union perf_event *event,
-					struct perf_session *session
-					__maybe_unused)
+static int perf_event__repipe_op2_synth(struct perf_session *session,
+					union perf_event *event)
 {
-	return perf_event__repipe_synth(tool, event);
+	return perf_event__repipe_synth(session->tool, event);
 }
 
 static int perf_event__repipe_attr(struct perf_tool *tool,
@@ -362,26 +360,24 @@ static int perf_event__repipe_exit(struct perf_tool *tool,
 	return err;
 }
 
-static int perf_event__repipe_tracing_data(struct perf_tool *tool,
-					   union perf_event *event,
-					   struct perf_session *session)
+static int perf_event__repipe_tracing_data(struct perf_session *session,
+					   union perf_event *event)
 {
 	int err;
 
-	perf_event__repipe_synth(tool, event);
-	err = perf_event__process_tracing_data(tool, event, session);
+	perf_event__repipe_synth(session->tool, event);
+	err = perf_event__process_tracing_data(session, event);
 
 	return err;
 }
 
-static int perf_event__repipe_id_index(struct perf_tool *tool,
-				       union perf_event *event,
-				       struct perf_session *session)
+static int perf_event__repipe_id_index(struct perf_session *session,
+				       union perf_event *event)
 {
 	int err;
 
-	perf_event__repipe_synth(tool, event);
-	err = perf_event__process_id_index(tool, event, session);
+	perf_event__repipe_synth(session->tool, event);
+	err = perf_event__process_id_index(session, event);
 
 	return err;
 }
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 76e12bcd1765..7507e4d6dce1 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -201,14 +201,13 @@ static void setup_forced_leader(struct report *report,
 		perf_evlist__force_leader(evlist);
 }
 
-static int process_feature_event(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session __maybe_unused)
+static int process_feature_event(struct perf_session *session,
+				 union perf_event *event)
 {
-	struct report *rep = container_of(tool, struct report, tool);
+	struct report *rep = container_of(session->tool, struct report, tool);
 
 	if (event->feat.feat_id < HEADER_LAST_FEATURE)
-		return perf_event__process_feature(tool, event, session);
+		return perf_event__process_feature(session, event);
 
 	if (event->feat.feat_id != HEADER_LAST_FEATURE) {
 		pr_err("failed: wrong feature ID: %" PRIu64 "\n",
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 6176bae177c2..765391b6c88c 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2965,9 +2965,8 @@ static void script__setup_sample_type(struct perf_script *script)
 	}
 }
 
-static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
-				    union perf_event *event,
-				    struct perf_session *session)
+static int process_stat_round_event(struct perf_session *session,
+				    union perf_event *event)
 {
 	struct stat_round_event *round = &event->stat_round;
 	struct perf_evsel *counter;
@@ -2981,9 +2980,8 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int process_stat_config_event(struct perf_tool *tool __maybe_unused,
-				     union perf_event *event,
-				     struct perf_session *session __maybe_unused)
+static int process_stat_config_event(struct perf_session *session __maybe_unused,
+				     union perf_event *event)
 {
 	perf_event__read_stat_config(&stat_config, &event->stat_config);
 	return 0;
@@ -3009,10 +3007,10 @@ static int set_maps(struct perf_script *script)
 }
 
 static
-int process_thread_map_event(struct perf_tool *tool,
-			     union perf_event *event,
-			     struct perf_session *session __maybe_unused)
+int process_thread_map_event(struct perf_session *session,
+			     union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 
 	if (script->threads) {
@@ -3028,10 +3026,10 @@ int process_thread_map_event(struct perf_tool *tool,
 }
 
 static
-int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
-			  union perf_event *event,
-			  struct perf_session *session __maybe_unused)
+int process_cpu_map_event(struct perf_session *session,
+			  union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 
 	if (script->cpus) {
@@ -3046,21 +3044,21 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(script);
 }
 
-static int process_feature_event(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session)
+static int process_feature_event(struct perf_session *session,
+				 union perf_event *event)
 {
 	if (event->feat.feat_id < HEADER_LAST_FEATURE)
-		return perf_event__process_feature(tool, event, session);
+		return perf_event__process_feature(session, event);
 	return 0;
 }
 
 #ifdef HAVE_AUXTRACE_SUPPORT
-static int perf_script__process_auxtrace_info(struct perf_tool *tool,
-					      union perf_event *event,
-					      struct perf_session *session)
+static int perf_script__process_auxtrace_info(struct perf_session *session,
+					      union perf_event *event)
 {
-	int ret = perf_event__process_auxtrace_info(tool, event, session);
+	struct perf_tool *tool = session->tool;
+
+	int ret = perf_event__process_auxtrace_info(session, event);
 
 	if (ret == 0) {
 		struct perf_script *script = container_of(tool, struct perf_script, tool);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 0b0e3961d511..b86aba1c8028 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1354,9 +1354,8 @@ static int __cmd_record(int argc, const char **argv)
 	return argc;
 }
 
-static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
-				    union perf_event *event,
-				    struct perf_session *session)
+static int process_stat_round_event(struct perf_session *session,
+				    union perf_event *event)
 {
 	struct stat_round_event *stat_round = &event->stat_round;
 	struct perf_evsel *counter;
@@ -1381,10 +1380,10 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_stat_config_event(struct perf_tool *tool,
-			      union perf_event *event,
-			      struct perf_session *session __maybe_unused)
+int process_stat_config_event(struct perf_session *session,
+			      union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_stat *st = container_of(tool, struct perf_stat, tool);
 
 	perf_event__read_stat_config(&stat_config, &event->stat_config);
@@ -1424,10 +1423,10 @@ static int set_maps(struct perf_stat *st)
 }
 
 static
-int process_thread_map_event(struct perf_tool *tool,
-			     union perf_event *event,
-			     struct perf_session *session __maybe_unused)
+int process_thread_map_event(struct perf_session *session,
+			     union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_stat *st = container_of(tool, struct perf_stat, tool);
 
 	if (st->threads) {
@@ -1443,10 +1442,10 @@ int process_thread_map_event(struct perf_tool *tool,
 }
 
 static
-int process_cpu_map_event(struct perf_tool *tool,
-			  union perf_event *event,
-			  struct perf_session *session __maybe_unused)
+int process_cpu_map_event(struct perf_session *session,
+			  union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_stat *st = container_of(tool, struct perf_stat, tool);
 	struct cpu_map *cpus;
 
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index db1511359c5e..86f0bc445f93 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -906,9 +906,8 @@ out_free:
 	return err;
 }
 
-int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
-				      union perf_event *event,
-				      struct perf_session *session)
+int perf_event__process_auxtrace_info(struct perf_session *session,
+				      union perf_event *event)
 {
 	enum auxtrace_type type = event->auxtrace_info.type;
 
@@ -1185,9 +1184,8 @@ void events_stats__auxtrace_error_warn(const struct events_stats *stats)
 	}
 }
 
-int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
-				       union perf_event *event,
-				       struct perf_session *session)
+int perf_event__process_auxtrace_error(struct perf_session *session,
+				       union perf_event *event)
 {
 	if (auxtrace__dont_decode(session))
 		return 0;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 71fc3bd74299..97776470a52e 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -517,15 +517,13 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
 					 struct perf_tool *tool,
 					 struct perf_session *session,
 					 perf_event__handler_t process);
-int perf_event__process_auxtrace_info(struct perf_tool *tool,
-				      union perf_event *event,
-				      struct perf_session *session);
+int perf_event__process_auxtrace_info(struct perf_session *session,
+				      union perf_event *event);
 s64 perf_event__process_auxtrace(struct perf_tool *tool,
 				 union perf_event *event,
 				 struct perf_session *session);
-int perf_event__process_auxtrace_error(struct perf_tool *tool,
-				       union perf_event *event,
-				       struct perf_session *session);
+int perf_event__process_auxtrace_error(struct perf_session *session,
+				       union perf_event *event);
 int itrace_parse_synth_opts(const struct option *opt, const char *str,
 			    int unset);
 void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 91e6d9cfd906..c78051ad1fcc 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3448,10 +3448,10 @@ int perf_event__synthesize_features(struct perf_tool *tool,
 	return ret;
 }
 
-int perf_event__process_feature(struct perf_tool *tool,
-				union perf_event *event,
-				struct perf_session *session __maybe_unused)
+int perf_event__process_feature(struct perf_session *session,
+				union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct feat_fd ff = { .fd = 0 };
 	struct feature_event *fe = (struct feature_event *)event;
 	int type = fe->header.type;
@@ -3856,9 +3856,8 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
 	return aligned_size;
 }
 
-int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
-				     union perf_event *event,
-				     struct perf_session *session)
+int perf_event__process_tracing_data(struct perf_session *session,
+				     union perf_event *event)
 {
 	ssize_t size_read, padding, size = event->tracing_data.size;
 	int fd = perf_data__fd(session->data);
@@ -3924,9 +3923,8 @@ int perf_event__synthesize_build_id(struct perf_tool *tool,
 	return err;
 }
 
-int perf_event__process_build_id(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event,
-				 struct perf_session *session)
+int perf_event__process_build_id(struct perf_session *session,
+				 union perf_event *event)
 {
 	__event_process_build_id(&event->build_id,
 				 event->build_id.filename,
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index ff2a1263fb9b..e17903caa71d 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -116,9 +116,8 @@ int perf_event__synthesize_extra_attr(struct perf_tool *tool,
 				      perf_event__handler_t process,
 				      bool is_pipe);
 
-int perf_event__process_feature(struct perf_tool *tool,
-				union perf_event *event,
-				struct perf_session *session);
+int perf_event__process_feature(struct perf_session *session,
+				union perf_event *event);
 
 int perf_event__synthesize_attr(struct perf_tool *tool,
 				struct perf_event_attr *attr, u32 ids, u64 *id,
@@ -148,17 +147,15 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp);
 int perf_event__synthesize_tracing_data(struct perf_tool *tool,
 					int fd, struct perf_evlist *evlist,
 					perf_event__handler_t process);
-int perf_event__process_tracing_data(struct perf_tool *tool,
-				     union perf_event *event,
-				     struct perf_session *session);
+int perf_event__process_tracing_data(struct perf_session *session,
+				     union perf_event *event);
 
 int perf_event__synthesize_build_id(struct perf_tool *tool,
 				    struct dso *pos, u16 misc,
 				    perf_event__handler_t process,
 				    struct machine *machine);
-int perf_event__process_build_id(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session);
+int perf_event__process_build_id(struct perf_session *session,
+				 union perf_event *event);
 bool is_perf_magic(u64 magic);
 
 #define NAME_ALIGN 64
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8b9369303561..e781cdba845c 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -199,12 +199,10 @@ void perf_session__delete(struct perf_session *session)
 	free(session);
 }
 
-static int process_event_synth_tracing_data_stub(struct perf_tool *tool
+static int process_event_synth_tracing_data_stub(struct perf_session *session
 						 __maybe_unused,
 						 union perf_event *event
-						 __maybe_unused,
-						 struct perf_session *session
-						__maybe_unused)
+						 __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -288,9 +286,8 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
 	return event->auxtrace.size;
 }
 
-static int process_event_op2_stub(struct perf_tool *tool __maybe_unused,
-				  union perf_event *event __maybe_unused,
-				  struct perf_session *session __maybe_unused)
+static int process_event_op2_stub(struct perf_session *session __maybe_unused,
+				  union perf_event *event __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -298,9 +295,8 @@ static int process_event_op2_stub(struct perf_tool *tool __maybe_unused,
 
 
 static
-int process_event_thread_map_stub(struct perf_tool *tool __maybe_unused,
-				  union perf_event *event __maybe_unused,
-				  struct perf_session *session __maybe_unused)
+int process_event_thread_map_stub(struct perf_session *session __maybe_unused,
+				  union perf_event *event __maybe_unused)
 {
 	if (dump_trace)
 		perf_event__fprintf_thread_map(event, stdout);
@@ -310,9 +306,8 @@ int process_event_thread_map_stub(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_event_cpu_map_stub(struct perf_tool *tool __maybe_unused,
-			       union perf_event *event __maybe_unused,
-			       struct perf_session *session __maybe_unused)
+int process_event_cpu_map_stub(struct perf_session *session __maybe_unused,
+			       union perf_event *event __maybe_unused)
 {
 	if (dump_trace)
 		perf_event__fprintf_cpu_map(event, stdout);
@@ -322,9 +317,8 @@ int process_event_cpu_map_stub(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_event_stat_config_stub(struct perf_tool *tool __maybe_unused,
-				   union perf_event *event __maybe_unused,
-				   struct perf_session *session __maybe_unused)
+int process_event_stat_config_stub(struct perf_session *session __maybe_unused,
+				   union perf_event *event __maybe_unused)
 {
 	if (dump_trace)
 		perf_event__fprintf_stat_config(event, stdout);
@@ -333,10 +327,8 @@ int process_event_stat_config_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int process_stat_stub(struct perf_tool *tool __maybe_unused,
-			     union perf_event *event __maybe_unused,
-			     struct perf_session *perf_session
-			     __maybe_unused)
+static int process_stat_stub(struct perf_session *perf_session __maybe_unused,
+			     union perf_event *event)
 {
 	if (dump_trace)
 		perf_event__fprintf_stat(event, stdout);
@@ -345,10 +337,8 @@ static int process_stat_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int process_stat_round_stub(struct perf_tool *tool __maybe_unused,
-				   union perf_event *event __maybe_unused,
-				   struct perf_session *perf_session
-				   __maybe_unused)
+static int process_stat_round_stub(struct perf_session *perf_session __maybe_unused,
+				   union perf_event *event)
 {
 	if (dump_trace)
 		perf_event__fprintf_stat_round(event, stdout);
@@ -1374,37 +1364,37 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	case PERF_RECORD_HEADER_TRACING_DATA:
 		/* setup for reading amidst mmap */
 		lseek(fd, file_offset, SEEK_SET);
-		return tool->tracing_data(tool, event, session);
+		return tool->tracing_data(session, event);
 	case PERF_RECORD_HEADER_BUILD_ID:
-		return tool->build_id(tool, event, session);
+		return tool->build_id(session, event);
 	case PERF_RECORD_FINISHED_ROUND:
 		return tool->finished_round(tool, event, oe);
 	case PERF_RECORD_ID_INDEX:
-		return tool->id_index(tool, event, session);
+		return tool->id_index(session, event);
 	case PERF_RECORD_AUXTRACE_INFO:
-		return tool->auxtrace_info(tool, event, session);
+		return tool->auxtrace_info(session, event);
 	case PERF_RECORD_AUXTRACE:
 		/* setup for reading amidst mmap */
 		lseek(fd, file_offset + event->header.size, SEEK_SET);
 		return tool->auxtrace(tool, event, session);
 	case PERF_RECORD_AUXTRACE_ERROR:
 		perf_session__auxtrace_error_inc(session, event);
-		return tool->auxtrace_error(tool, event, session);
+		return tool->auxtrace_error(session, event);
 	case PERF_RECORD_THREAD_MAP:
-		return tool->thread_map(tool, event, session);
+		return tool->thread_map(session, event);
 	case PERF_RECORD_CPU_MAP:
-		return tool->cpu_map(tool, event, session);
+		return tool->cpu_map(session, event);
 	case PERF_RECORD_STAT_CONFIG:
-		return tool->stat_config(tool, event, session);
+		return tool->stat_config(session, event);
 	case PERF_RECORD_STAT:
-		return tool->stat(tool, event, session);
+		return tool->stat(session, event);
 	case PERF_RECORD_STAT_ROUND:
-		return tool->stat_round(tool, event, session);
+		return tool->stat_round(session, event);
 	case PERF_RECORD_TIME_CONV:
 		session->time_conv = event->time_conv;
-		return tool->time_conv(tool, event, session);
+		return tool->time_conv(session, event);
 	case PERF_RECORD_HEADER_FEATURE:
-		return tool->feature(tool, event, session);
+		return tool->feature(session, event);
 	default:
 		return -EINVAL;
 	}
@@ -2133,9 +2123,8 @@ out:
 	return err;
 }
 
-int perf_event__process_id_index(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event,
-				 struct perf_session *session)
+int perf_event__process_id_index(struct perf_session *session,
+				 union perf_event *event)
 {
 	struct perf_evlist *evlist = session->evlist;
 	struct id_index_event *ie = &event->id_index;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index da40b4b380ca..d96eccd7d27f 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -120,9 +120,8 @@ int perf_session__deliver_synth_event(struct perf_session *session,
 				      union perf_event *event,
 				      struct perf_sample *sample);
 
-int perf_event__process_id_index(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session);
+int perf_event__process_id_index(struct perf_session *session,
+				 union perf_event *event);
 
 int perf_event__synthesize_id_index(struct perf_tool *tool,
 				    perf_event__handler_t process,
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 5d3172bcc4ae..4d40515307b8 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -374,9 +374,8 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	return 0;
 }
 
-int perf_event__process_stat_event(struct perf_tool *tool __maybe_unused,
-				   union perf_event *event,
-				   struct perf_session *session)
+int perf_event__process_stat_event(struct perf_session *session,
+				   union perf_event *event)
 {
 	struct perf_counts_values count;
 	struct stat_event *st = &event->stat;
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 3a13a6dc5a62..2f9c9159a364 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -199,9 +199,8 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 struct perf_tool;
 union perf_event;
 struct perf_session;
-int perf_event__process_stat_event(struct perf_tool *tool,
-				   union perf_event *event,
-				   struct perf_session *session);
+int perf_event__process_stat_event(struct perf_session *session,
+				   union perf_event *event);
 
 size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp);
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 183c91453522..9c7f78d76275 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -26,8 +26,7 @@ typedef int (*event_attr_op)(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_evlist **pevlist);
 
-typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event,
-			 struct perf_session *session);
+typedef int (*event_op2)(struct perf_session *session, union perf_event *event);
 
 typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event,
 			struct ordered_events *oe);
-- 
cgit v1.2.3


From 7336555a682c09fd9a3fdf38724493e52653be50 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 13 Sep 2018 14:54:04 +0200
Subject: perf tools: Remove perf_tool from event_op3

Now that we keep a perf_tool pointer inside perf_session, there's no need
to have a perf_tool argument in the event_op3 callback. Remove it.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180913125450.21342-3-jolsa@kernel.org
[ Fix the builtin-inject.c build for !HAVE_AUXTRACE_SUPPORT ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-inject.c | 11 +++++------
 tools/perf/util/auxtrace.c  |  7 +++----
 tools/perf/util/auxtrace.h  |  5 ++---
 tools/perf/util/session.c   |  8 +++-----
 tools/perf/util/tool.h      |  4 +---
 5 files changed, 14 insertions(+), 21 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index d77ed2aea95a..b4a29f435b06 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -131,10 +131,10 @@ static int copy_bytes(struct perf_inject *inject, int fd, off_t size)
 	return 0;
 }
 
-static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
-				       union perf_event *event,
-				       struct perf_session *session)
+static s64 perf_event__repipe_auxtrace(struct perf_session *session,
+				       union perf_event *event)
 {
+	struct perf_tool *tool = session->tool;
 	struct perf_inject *inject = container_of(tool, struct perf_inject,
 						  tool);
 	int ret;
@@ -172,9 +172,8 @@ static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
 #else
 
 static s64
-perf_event__repipe_auxtrace(struct perf_tool *tool __maybe_unused,
-			    union perf_event *event __maybe_unused,
-			    struct perf_session *session __maybe_unused)
+perf_event__repipe_auxtrace(struct perf_session *session __maybe_unused,
+			    union perf_event *event __maybe_unused)
 {
 	pr_err("AUX area tracing not supported\n");
 	return -EINVAL;
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 86f0bc445f93..3017b205a157 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -931,9 +931,8 @@ int perf_event__process_auxtrace_info(struct perf_session *session,
 	}
 }
 
-s64 perf_event__process_auxtrace(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session)
+s64 perf_event__process_auxtrace(struct perf_session *session,
+				 union perf_event *event)
 {
 	s64 err;
 
@@ -949,7 +948,7 @@ s64 perf_event__process_auxtrace(struct perf_tool *tool,
 	if (!session->auxtrace || event->header.type != PERF_RECORD_AUXTRACE)
 		return -EINVAL;
 
-	err = session->auxtrace->process_auxtrace_event(session, event, tool);
+	err = session->auxtrace->process_auxtrace_event(session, event, session->tool);
 	if (err < 0)
 		return err;
 
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 97776470a52e..6be89776358c 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -519,9 +519,8 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
 					 perf_event__handler_t process);
 int perf_event__process_auxtrace_info(struct perf_session *session,
 				      union perf_event *event);
-s64 perf_event__process_auxtrace(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session);
+s64 perf_event__process_auxtrace(struct perf_session *session,
+				 union perf_event *event);
 int perf_event__process_auxtrace_error(struct perf_session *session,
 				       union perf_event *event);
 int itrace_parse_synth_opts(const struct option *opt, const char *str,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index e781cdba845c..7d2c8ce6cfad 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -275,10 +275,8 @@ static int skipn(int fd, off_t n)
 	return 0;
 }
 
-static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
-				       union perf_event *event,
-				       struct perf_session *session
-				       __maybe_unused)
+static s64 process_event_auxtrace_stub(struct perf_session *session __maybe_unused,
+				       union perf_event *event)
 {
 	dump_printf(": unhandled!\n");
 	if (perf_data__is_pipe(session->data))
@@ -1376,7 +1374,7 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	case PERF_RECORD_AUXTRACE:
 		/* setup for reading amidst mmap */
 		lseek(fd, file_offset + event->header.size, SEEK_SET);
-		return tool->auxtrace(tool, event, session);
+		return tool->auxtrace(session, event);
 	case PERF_RECORD_AUXTRACE_ERROR:
 		perf_session__auxtrace_error_inc(session, event);
 		return tool->auxtrace_error(session, event);
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 9c7f78d76275..56e4ca54020a 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -27,13 +27,11 @@ typedef int (*event_attr_op)(struct perf_tool *tool,
 			     struct perf_evlist **pevlist);
 
 typedef int (*event_op2)(struct perf_session *session, union perf_event *event);
+typedef s64 (*event_op3)(struct perf_session *session, union perf_event *event);
 
 typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event,
 			struct ordered_events *oe);
 
-typedef s64 (*event_op3)(struct perf_tool *tool, union perf_event *event,
-			 struct perf_session *session);
-
 enum show_feature_header {
 	SHOW_FEAT_NO_HEADER = 0,
 	SHOW_FEAT_HEADER,
-- 
cgit v1.2.3


From e035f4ca2ac97c30842fb03101198a86730de3ad Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 13 Sep 2018 14:54:05 +0200
Subject: perf auxtrace: Pass struct perf_mmap into mmap__read* functions

The perf_mmap struct will hold a file pointer to write the mmap's
contents, so we need to propagate it down the stack to record__write
callers instead of its member the auxtrace_mmap struct.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180913125450.21342-4-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c | 27 +++++++++++++--------------
 tools/perf/util/auxtrace.c  | 11 ++++++-----
 tools/perf/util/auxtrace.h  |  5 +++--
 3 files changed, 22 insertions(+), 21 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 9853552bcf16..fd8b12c5f4ae 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -207,11 +207,11 @@ static int record__process_auxtrace(struct perf_tool *tool,
 }
 
 static int record__auxtrace_mmap_read(struct record *rec,
-				      struct auxtrace_mmap *mm)
+				      struct perf_mmap *map)
 {
 	int ret;
 
-	ret = auxtrace_mmap__read(mm, rec->itr, &rec->tool,
+	ret = auxtrace_mmap__read(map, rec->itr, &rec->tool,
 				  record__process_auxtrace);
 	if (ret < 0)
 		return ret;
@@ -223,11 +223,11 @@ static int record__auxtrace_mmap_read(struct record *rec,
 }
 
 static int record__auxtrace_mmap_read_snapshot(struct record *rec,
-					       struct auxtrace_mmap *mm)
+					       struct perf_mmap *map)
 {
 	int ret;
 
-	ret = auxtrace_mmap__read_snapshot(mm, rec->itr, &rec->tool,
+	ret = auxtrace_mmap__read_snapshot(map, rec->itr, &rec->tool,
 					   record__process_auxtrace,
 					   rec->opts.auxtrace_snapshot_size);
 	if (ret < 0)
@@ -245,13 +245,12 @@ static int record__auxtrace_read_snapshot_all(struct record *rec)
 	int rc = 0;
 
 	for (i = 0; i < rec->evlist->nr_mmaps; i++) {
-		struct auxtrace_mmap *mm =
-				&rec->evlist->mmap[i].auxtrace_mmap;
+		struct perf_mmap *map = &rec->evlist->mmap[i];
 
-		if (!mm->base)
+		if (!map->auxtrace_mmap.base)
 			continue;
 
-		if (record__auxtrace_mmap_read_snapshot(rec, mm) != 0) {
+		if (record__auxtrace_mmap_read_snapshot(rec, map) != 0) {
 			rc = -1;
 			goto out;
 		}
@@ -295,7 +294,7 @@ static int record__auxtrace_init(struct record *rec)
 
 static inline
 int record__auxtrace_mmap_read(struct record *rec __maybe_unused,
-			       struct auxtrace_mmap *mm __maybe_unused)
+			       struct perf_mmap *map __maybe_unused)
 {
 	return 0;
 }
@@ -529,17 +528,17 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 		return 0;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		struct auxtrace_mmap *mm = &maps[i].auxtrace_mmap;
+		struct perf_mmap *map = &maps[i];
 
-		if (maps[i].base) {
-			if (perf_mmap__push(&maps[i], rec, record__pushfn) != 0) {
+		if (map->base) {
+			if (perf_mmap__push(map, rec, record__pushfn) != 0) {
 				rc = -1;
 				goto out;
 			}
 		}
 
-		if (mm->base && !rec->opts.auxtrace_snapshot_mode &&
-		    record__auxtrace_mmap_read(rec, mm) != 0) {
+		if (map->auxtrace_mmap.base && !rec->opts.auxtrace_snapshot_mode &&
+		    record__auxtrace_mmap_read(rec, map) != 0) {
 			rc = -1;
 			goto out;
 		}
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 3017b205a157..2fecee57f555 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1193,11 +1193,12 @@ int perf_event__process_auxtrace_error(struct perf_session *session,
 	return 0;
 }
 
-static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
+static int __auxtrace_mmap__read(struct perf_mmap *map,
 				 struct auxtrace_record *itr,
 				 struct perf_tool *tool, process_auxtrace_t fn,
 				 bool snapshot, size_t snapshot_size)
 {
+	struct auxtrace_mmap *mm = &map->auxtrace_mmap;
 	u64 head, old = mm->prev, offset, ref;
 	unsigned char *data = mm->base;
 	size_t size, head_off, old_off, len1, len2, padding;
@@ -1303,18 +1304,18 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
 	return 1;
 }
 
-int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+int auxtrace_mmap__read(struct perf_mmap *map, struct auxtrace_record *itr,
 			struct perf_tool *tool, process_auxtrace_t fn)
 {
-	return __auxtrace_mmap__read(mm, itr, tool, fn, false, 0);
+	return __auxtrace_mmap__read(map, itr, tool, fn, false, 0);
 }
 
-int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+int auxtrace_mmap__read_snapshot(struct perf_mmap *map,
 				 struct auxtrace_record *itr,
 				 struct perf_tool *tool, process_auxtrace_t fn,
 				 size_t snapshot_size)
 {
-	return __auxtrace_mmap__read(mm, itr, tool, fn, true, snapshot_size);
+	return __auxtrace_mmap__read(map, itr, tool, fn, true, snapshot_size);
 }
 
 /**
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 6be89776358c..7eeb141361b9 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -33,6 +33,7 @@ union perf_event;
 struct perf_session;
 struct perf_evlist;
 struct perf_tool;
+struct perf_mmap;
 struct option;
 struct record_opts;
 struct auxtrace_info_event;
@@ -437,10 +438,10 @@ typedef int (*process_auxtrace_t)(struct perf_tool *tool,
 				  union perf_event *event, void *data1,
 				  size_t len1, void *data2, size_t len2);
 
-int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+int auxtrace_mmap__read(struct perf_mmap *map, struct auxtrace_record *itr,
 			struct perf_tool *tool, process_auxtrace_t fn);
 
-int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+int auxtrace_mmap__read_snapshot(struct perf_mmap *map,
 				 struct auxtrace_record *itr,
 				 struct perf_tool *tool, process_auxtrace_t fn,
 				 size_t snapshot_size);
-- 
cgit v1.2.3


From ded2b8fe2e431d8029ab50238744fcce06a2f0c6 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 13 Sep 2018 14:54:06 +0200
Subject: perf tools: Add 'struct perf_mmap' arg to record__write()

The struct perf_mmap map argument will hold the file pointer to write
the data to.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180913125450.21342-5-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c | 24 ++++++++++++++----------
 tools/perf/util/auxtrace.c  |  2 +-
 tools/perf/util/auxtrace.h  |  1 +
 tools/perf/util/mmap.c      |  6 +++---
 tools/perf/util/mmap.h      |  2 +-
 5 files changed, 20 insertions(+), 15 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index fd8b12c5f4ae..0980dfe3396b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -106,9 +106,12 @@ static bool switch_output_time(struct record *rec)
 	       trigger_is_ready(&switch_output_trigger);
 }
 
-static int record__write(struct record *rec, void *bf, size_t size)
+static int record__write(struct record *rec, struct perf_mmap *map __maybe_unused,
+			 void *bf, size_t size)
 {
-	if (perf_data__write(rec->session->data, bf, size) < 0) {
+	struct perf_data_file *file = &rec->session->data->file;
+
+	if (perf_data_file__write(file, bf, size) < 0) {
 		pr_err("failed to write perf data, error: %m\n");
 		return -1;
 	}
@@ -127,15 +130,15 @@ static int process_synthesized_event(struct perf_tool *tool,
 				     struct machine *machine __maybe_unused)
 {
 	struct record *rec = container_of(tool, struct record, tool);
-	return record__write(rec, event, event->header.size);
+	return record__write(rec, NULL, event, event->header.size);
 }
 
-static int record__pushfn(void *to, void *bf, size_t size)
+static int record__pushfn(struct perf_mmap *map, void *to, void *bf, size_t size)
 {
 	struct record *rec = to;
 
 	rec->samples++;
-	return record__write(rec, bf, size);
+	return record__write(rec, map, bf, size);
 }
 
 static volatile int done;
@@ -170,6 +173,7 @@ static void record__sig_exit(void)
 #ifdef HAVE_AUXTRACE_SUPPORT
 
 static int record__process_auxtrace(struct perf_tool *tool,
+				    struct perf_mmap *map,
 				    union perf_event *event, void *data1,
 				    size_t len1, void *data2, size_t len2)
 {
@@ -197,11 +201,11 @@ static int record__process_auxtrace(struct perf_tool *tool,
 	if (padding)
 		padding = 8 - padding;
 
-	record__write(rec, event, event->header.size);
-	record__write(rec, data1, len1);
+	record__write(rec, map, event, event->header.size);
+	record__write(rec, map, data1, len1);
 	if (len2)
-		record__write(rec, data2, len2);
-	record__write(rec, &pad, padding);
+		record__write(rec, map, data2, len2);
+	record__write(rec, map, &pad, padding);
 
 	return 0;
 }
@@ -549,7 +553,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 	 * at least one event.
 	 */
 	if (bytes_written != rec->bytes_written)
-		rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
+		rc = record__write(rec, NULL, &finished_round_event, sizeof(finished_round_event));
 
 	if (overwrite)
 		perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 2fecee57f555..c4617bcfd521 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1285,7 +1285,7 @@ static int __auxtrace_mmap__read(struct perf_mmap *map,
 	ev.auxtrace.tid = mm->tid;
 	ev.auxtrace.cpu = mm->cpu;
 
-	if (fn(tool, &ev, data1, len1, data2, len2))
+	if (fn(tool, map, &ev, data1, len1, data2, len2))
 		return -1;
 
 	mm->prev = head;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 7eeb141361b9..a86b7eab6673 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -435,6 +435,7 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
 				   bool per_cpu);
 
 typedef int (*process_auxtrace_t)(struct perf_tool *tool,
+				  struct perf_mmap *map,
 				  union perf_event *event, void *data1,
 				  size_t len1, void *data2, size_t len2);
 
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 215f69f41672..cdb95b3a1213 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -281,7 +281,7 @@ int perf_mmap__read_init(struct perf_mmap *map)
 }
 
 int perf_mmap__push(struct perf_mmap *md, void *to,
-		    int push(void *to, void *buf, size_t size))
+		    int push(struct perf_mmap *map, void *to, void *buf, size_t size))
 {
 	u64 head = perf_mmap__read_head(md);
 	unsigned char *data = md->base + page_size;
@@ -300,7 +300,7 @@ int perf_mmap__push(struct perf_mmap *md, void *to,
 		size = md->mask + 1 - (md->start & md->mask);
 		md->start += size;
 
-		if (push(to, buf, size) < 0) {
+		if (push(md, to, buf, size) < 0) {
 			rc = -1;
 			goto out;
 		}
@@ -310,7 +310,7 @@ int perf_mmap__push(struct perf_mmap *md, void *to,
 	size = md->end - md->start;
 	md->start += size;
 
-	if (push(to, buf, size) < 0) {
+	if (push(md, to, buf, size) < 0) {
 		rc = -1;
 		goto out;
 	}
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 05a6d47c7956..e603314dc792 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -93,7 +93,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
 union perf_event *perf_mmap__read_event(struct perf_mmap *map);
 
 int perf_mmap__push(struct perf_mmap *md, void *to,
-		    int push(void *to, void *buf, size_t size));
+		    int push(struct perf_mmap *map, void *to, void *buf, size_t size));
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
 
-- 
cgit v1.2.3


From ed93d0a26012a4a12231c16b18628a324079dc45 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 13 Sep 2018 14:54:11 +0200
Subject: perf util: Make copyfile_offset() global

It will be used outside of util object in following patches.

Committer note:

We need to have the header with the definition for loff_t in util.h
since we now use it in the copyfile_offset() signature.

Also move that prototype closer to the other copyfile_ prefixed
functions.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180913125450.21342-10-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/util.c | 2 +-
 tools/perf/util/util.h | 2 ++
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index eac5b858a371..093352e93d50 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -221,7 +221,7 @@ out:
 	return err;
 }
 
-static int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
+int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
 {
 	void *ptr;
 	loff_t pgoff;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index dc58254a2b69..14508ee7707a 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -6,6 +6,7 @@
 /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */
 #define _DEFAULT_SOURCE 1
 
+#include <fcntl.h>
 #include <stdbool.h>
 #include <stddef.h>
 #include <stdlib.h>
@@ -35,6 +36,7 @@ bool lsdir_no_dot_filter(const char *name, struct dirent *d);
 int copyfile(const char *from, const char *to);
 int copyfile_mode(const char *from, const char *to, mode_t mode);
 int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi);
+int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size);
 
 ssize_t readn(int fd, void *buf, size_t n);
 ssize_t writen(int fd, const void *buf, size_t n);
-- 
cgit v1.2.3


From c04c859f439fb4de9039246370d60a07b9b5bcb5 Mon Sep 17 00:00:00 2001
From: Jérémie Galarneau <jeremie.galarneau@efficios.com>
Date: Wed, 29 Aug 2018 16:16:48 -0400
Subject: perf tools: Initialize perf_data_file fd field
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Building the perf CTF converter fails with gcc 4.8.4 on Ubuntu 14.04
with the following error:

  error: missing initializer for field ‘fd’ of ‘struct perf_data_file’
  [-Werror=missing-field-initializers]

Per 4b838b0db4e9 ("perf tools: Add compression id into 'struct
kmod_path'") and the ensuing discussion on the mailing list, it appears
that this affects other distributions and gcc versions.

Signed-off-by: Jeremie Galarneau <jeremie.galarneau@efficios.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180829201648.19588-1-jeremie.galarneau@efficios.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/data-convert-bt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index abd38abf1d91..f75d4aa612c5 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1578,7 +1578,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 {
 	struct perf_session *session;
 	struct perf_data data = {
-		.file.path = input,
+		.file      = { .path = input, .fd = -1 },
 		.mode      = PERF_DATA_MODE_READ,
 		.force     = opts->force,
 	};
-- 
cgit v1.2.3


From 24ef0fd0a1f389b156e6ef0edd71072728831bd9 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 18 Sep 2018 16:08:02 -0300
Subject: perf python: Use -Wno-redundant-decls to build with PYTHON=python3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When building in ClearLinux using 'make PYTHON=python3' with gcc 8.2.1
it fails with:

    GEN      /tmp/build/perf/python/perf.so
  In file included from /usr/include/python3.7m/Python.h:126,
                   from /git/linux/tools/perf/util/python.c:2:
  /usr/include/python3.7m/import.h:58:24: error: redundant redeclaration of ‘_PyImport_AddModuleObject’ [-Werror=redundant-decls]
   PyAPI_FUNC(PyObject *) _PyImport_AddModuleObject(PyObject *, PyObject *);
                          ^~~~~~~~~~~~~~~~~~~~~~~~~
  /usr/include/python3.7m/import.h:47:24: note: previous declaration of ‘_PyImport_AddModuleObject’ was here
   PyAPI_FUNC(PyObject *) _PyImport_AddModuleObject(PyObject *name,
                          ^~~~~~~~~~~~~~~~~~~~~~~~~
  cc1: all warnings being treated as errors
  error: command 'gcc' failed with exit status 1

And indeed there is a redundant declaration in that Python.h file, one
with parameter names and the other without, so just add
-Wno-error=redundant-decls to the python setup instructions.

Now perf builds with gcc in ClearLinux with the following Dockerfile:

  # docker.io/acmel/linux-perf-tools-build-clearlinux:latest
  FROM docker.io/clearlinux:latest
  MAINTAINER Arnaldo Carvalho de Melo <acme@kernel.org>
  RUN swupd update && \
      swupd bundle-add sysadmin-basic-dev
  RUN mkdir -m 777 -p /git /tmp/build/perf /tmp/build/objtool /tmp/build/linux && \
      groupadd -r perfbuilder && \
      useradd -m -r -g perfbuilder perfbuilder && \
      chown -R perfbuilder.perfbuilder /tmp/build/ /git/
  USER perfbuilder
  COPY rx_and_build.sh /
  ENV EXTRA_MAKE_ARGS=PYTHON=python3
  ENTRYPOINT ["/rx_and_build.sh"]

Now to figure out why the build fails with clang, that is present in the
above container as detected by the rx_and_build.sh script:

  clang version 6.0.1 (tags/RELEASE_601/final)
  Target: x86_64-unknown-linux-gnu
  Thread model: posix
  InstalledDir: /usr/sbin
  make: Entering directory '/git/linux/tools/perf'
    BUILD:   Doing 'make -j4' parallel build
    HOSTCC   /tmp/build/perf/fixdep.o
    HOSTLD   /tmp/build/perf/fixdep-in.o
    LINK     /tmp/build/perf/fixdep

  Auto-detecting system features:
  ...                         dwarf: [ OFF ]
  ...            dwarf_getlocations: [ OFF ]
  ...                         glibc: [ OFF ]
  ...                          gtk2: [ OFF ]
  ...                      libaudit: [ OFF ]
  ...                        libbfd: [ OFF ]
  ...                        libelf: [ OFF ]
  ...                       libnuma: [ OFF ]
  ...        numa_num_possible_cpus: [ OFF ]
  ...                       libperl: [ OFF ]
  ...                     libpython: [ OFF ]
  ...                      libslang: [ OFF ]
  ...                     libcrypto: [ OFF ]
  ...                     libunwind: [ OFF ]
  ...            libdw-dwarf-unwind: [ OFF ]
  ...                          zlib: [ OFF ]
  ...                          lzma: [ OFF ]
  ...                     get_cpuid: [ OFF ]
  ...                           bpf: [ OFF ]

  Makefile.config:331: *** No gnu/libc-version.h found, please install glibc-dev[el].  Stop.
  make[1]: *** [Makefile.perf:206: sub-make] Error 2
  make: *** [Makefile:70: all] Error 2
  make: Leaving directory '/git/linux/tools/perf'

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thiago Macieira <thiago.macieira@intel.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-c3khb9ac86s00qxzjrueomme@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/setup.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 97efbcad076e..1942f6dd24f6 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -35,7 +35,7 @@ class install_lib(_install_lib):
 
 cflags = getenv('CFLAGS', '').split()
 # switch off several checks (need to be at the end of cflags list)
-cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ]
+cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls' ]
 if cc != "clang":
     cflags += ['-Wno-cast-function-type' ]
 
-- 
cgit v1.2.3


From 3b9c25c0a04675c5d8d4390d9d9b661135751b27 Mon Sep 17 00:00:00 2001
From: Sangwon Hong <qpakzk@gmail.com>
Date: Wed, 19 Sep 2018 00:49:11 -0700
Subject: perf help: Add missing subcommand `version`

There isn't subcommand `version` when typing `perf help`.

Before :

  $ perf help | grep version
   usage: perf [--version] [--help] [OPTIONS] COMMAND [ARGS]

So add perf-version in command-list.txt for listing it when typing `perf
help`.

After :

$ perf help | grep version

 usage: perf [--version] [--help] [OPTIONS] COMMAND [ARGS]
   version         display the version of perf binary

Signed-off-by: Sangwon Hong <qpakzk@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/20180919074911.41931-1-qpakzk@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/command-list.txt | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 2d0caf20ff3a..bc6c585f74fc 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -30,3 +30,4 @@ perf-test			mainporcelain common
 perf-timechart			mainporcelain common
 perf-top			mainporcelain common
 perf-trace			mainporcelain audit
+perf-version			mainporcelain common
-- 
cgit v1.2.3


From c12e039d1233f24ab2726945f883037f47b26f1d Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Thu, 13 Sep 2018 20:10:31 -0700
Subject: perf tools: Report itrace options in help

I often forget all the options that --itrace accepts. Instead of burying
them in the man page only report them in the normal command line help
too to make them easier accessible.

v2: Align

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kim Phillips <kim.phillips@arm.com>
Link: http://lkml.kernel.org/r/20180914031038.4160-2-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-inject.c |  3 ++-
 tools/perf/builtin-report.c |  2 +-
 tools/perf/builtin-script.c |  2 +-
 tools/perf/util/auxtrace.h  | 19 +++++++++++++++++++
 4 files changed, 23 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index b4a29f435b06..eda41673c4f3 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -798,7 +798,8 @@ int cmd_inject(int argc, const char **argv)
 			   "kallsyms pathname"),
 		OPT_BOOLEAN('f', "force", &data.force, "don't complain, do it"),
 		OPT_CALLBACK_OPTARG(0, "itrace", &inject.itrace_synth_opts,
-				    NULL, "opts", "Instruction Tracing options",
+				    NULL, "opts", "Instruction Tracing options\n"
+				    ITRACE_HELP,
 				    itrace_parse_synth_opts),
 		OPT_BOOLEAN(0, "strip", &inject.strip,
 			    "strip non-synthesized events (use with --itrace)"),
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 7507e4d6dce1..c0703979c51d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1104,7 +1104,7 @@ int cmd_report(int argc, const char **argv)
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
 		     "how to display percentage of filtered entries", parse_filter_percentage),
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
-			    "Instruction Tracing options",
+			    "Instruction Tracing options\n" ITRACE_HELP,
 			    itrace_parse_synth_opts),
 	OPT_BOOLEAN(0, "full-source-path", &srcline_full_filename,
 			"Show full source file name path for source lines"),
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 765391b6c88c..66699dd351e0 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3193,7 +3193,7 @@ int cmd_script(int argc, const char **argv)
 	OPT_BOOLEAN(0, "ns", &nanosecs,
 		    "Use 9 decimal places when displaying time"),
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
-			    "Instruction Tracing options",
+			    "Instruction Tracing options\n" ITRACE_HELP,
 			    itrace_parse_synth_opts),
 	OPT_BOOLEAN(0, "full-source-path", &srcline_full_filename,
 			"Show full source file name path for source lines"),
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index a86b7eab6673..0a6ce9c4fc11 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -576,6 +576,23 @@ static inline void auxtrace__free(struct perf_session *session)
 	return session->auxtrace->free(session);
 }
 
+#define ITRACE_HELP \
+"				i:	    		synthesize instructions events\n"		\
+"				b:	    		synthesize branches events\n"		\
+"				c:	    		synthesize branches events (calls only)\n"	\
+"				r:	    		synthesize branches events (returns only)\n" \
+"				x:	    		synthesize transactions events\n"		\
+"				w:	    		synthesize ptwrite events\n"		\
+"				p:	    		synthesize power events\n"			\
+"				e:	    		synthesize error events\n"			\
+"				d:	    		create a debug log\n"			\
+"				g[len]:     		synthesize a call chain (use with i or x)\n" \
+"				l[len]:     		synthesize last branch entries (use with i or x)\n" \
+"				sNUMBER:    		skip initial number of events\n"		\
+"				PERIOD[ns|us|ms|i|t]:   specify period to sample stream\n" \
+"				concatenate multiple options. Default is ibxwpe or cewp\n"
+
+
 #else
 
 static inline struct auxtrace_record *
@@ -716,6 +733,8 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
 				   struct perf_evlist *evlist, int idx,
 				   bool per_cpu);
 
+#define ITRACE_HELP ""
+
 #endif
 
 #endif
-- 
cgit v1.2.3


From 03a1f49f26482cf832e7f0157ae5da716d927701 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Tue, 18 Sep 2018 05:32:07 -0700
Subject: tools lib subcmd: Support overwriting the pager

Add an interface to the auto pager code that allows callers to overwrite
the pager.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/20180918123214.26728-3-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/subcmd/pager.c | 11 ++++++++++-
 tools/lib/subcmd/pager.h |  1 +
 2 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/lib/subcmd/pager.c b/tools/lib/subcmd/pager.c
index 9997a8805a82..e3d47b59b14d 100644
--- a/tools/lib/subcmd/pager.c
+++ b/tools/lib/subcmd/pager.c
@@ -23,6 +23,13 @@ void pager_init(const char *pager_env)
 	subcmd_config.pager_env = pager_env;
 }
 
+static const char *forced_pager;
+
+void force_pager(const char *pager)
+{
+	forced_pager = pager;
+}
+
 static void pager_preexec(void)
 {
 	/*
@@ -66,7 +73,9 @@ void setup_pager(void)
 	const char *pager = getenv(subcmd_config.pager_env);
 	struct winsize sz;
 
-	if (!isatty(1))
+	if (forced_pager)
+		pager = forced_pager;
+	if (!isatty(1) && !forced_pager)
 		return;
 	if (ioctl(1, TIOCGWINSZ, &sz) == 0)
 		pager_columns = sz.ws_col;
diff --git a/tools/lib/subcmd/pager.h b/tools/lib/subcmd/pager.h
index f1a53cf29880..a818964693ab 100644
--- a/tools/lib/subcmd/pager.h
+++ b/tools/lib/subcmd/pager.h
@@ -7,5 +7,6 @@ extern void pager_init(const char *pager_env);
 extern void setup_pager(void);
 extern int pager_in_use(void);
 extern int pager_get_columns(void);
+extern void force_pager(const char *);
 
 #endif /* __SUBCMD_PAGER_H */
-- 
cgit v1.2.3


From 37fed3de555199733805a2d3e03aee7727c09ea4 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Tue, 18 Sep 2018 05:32:09 -0700
Subject: perf script: Allow sym and dso without ip, addr

Currently sym and dso require printing ip and addr because the print
function is tied to those outputs. With callindent it makes sense to
print the symbol or dso without numerical IP or ADDR. So change the
dependency check to only check the underlying attribute.

Also the branch target output relies on the user_set flag to determine
if the branch target should be implicitely printed. When modifying the
fields with + or - also set user_set, so that ADDR can be removed. We
also need to set wildcard_set to make the initial sanity check pass.

This allows to remove a lot of noise in callindent output by dropping
the numerical addresses, which are not all that useful.

Before

% perf script --itrace=cr -F +callindent
         swapper     0 [000] 156546.354971:          1   branches: pt_config                                       0 [unknown] ([unknown]) => ffffffff81010486 pt_config ([kernel.kallsyms])
         swapper     0 [000] 156546.354971:          1   branches:     pt_config                    ffffffff81010499 pt_config ([kernel.kallsyms]) => ffffffff8101063e pt_event_add ([kernel.kallsyms])
         swapper     0 [000] 156546.354971:          1   branches:     pt_event_add                 ffffffff81010635 pt_event_add ([kernel.kallsyms]) => ffffffff8115e687 event_sched_in.isra.107 ([kernel.kallsyms])
         swapper     0 [000] 156546.354971:          1   branches:     perf_pmu_enable              ffffffff8115e726 event_sched_in.isra.107 ([kernel.kallsyms]) => ffffffff811579b0 perf_pmu_enable ([kernel.kallsyms])
         swapper     0 [000] 156546.354971:          1   branches:     perf_pmu_nop_void            ffffffff81151730 perf_pmu_nop_void ([kernel.kallsyms]) => ffffffff8115e72b event_sched_in.isra.107 ([kernel.kallsyms])
         swapper     0 [000] 156546.354971:          1   branches:     event_sched_in.isra.107      ffffffff8115e737 event_sched_in.isra.107 ([kernel.kallsyms]) => ffffffff8115e7a5 group_sched_in ([kernel.kallsyms])
         swapper     0 [000] 156546.354971:          1   branches:     __x86_indirect_thunk_rax     ffffffff8115e7f6 group_sched_in ([kernel.kallsyms]) => ffffffff81a03000 __x86_indirect_thunk_rax ([kernel.kallsyms])

After

% perf script --itrace=cr -F +callindent,-ip,-sym,-symoff
       swapper     0 [000] 156546.354971:          1   branches:  pt_config
         swapper     0 [000] 156546.354971:          1   branches:      pt_config
         swapper     0 [000] 156546.354971:          1   branches:      pt_event_add
         swapper     0 [000] 156546.354971:          1   branches:       perf_pmu_enable
         swapper     0 [000] 156546.354971:          1   branches:       perf_pmu_nop_void
         swapper     0 [000] 156546.354971:          1   branches:       event_sched_in.isra.107
         swapper     0 [000] 156546.354971:          1   branches:       __x86_indirect_thunk_rax
         swapper     0 [000] 156546.354971:          1   branches:       perf_pmu_nop_int
         swapper     0 [000] 156546.354971:          1   branches:       group_sched_in
         swapper     0 [000] 156546.354971:          1   branches:       event_filter_match
         swapper     0 [000] 156546.354971:          1   branches:       event_filter_match
         swapper     0 [000] 156546.354971:          1   branches:       group_sched_in

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kim Phillips <kim.phillips@arm.com>
Link: http://lkml.kernel.org/r/20180918123214.26728-5-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 66699dd351e0..7aa59696e97a 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -406,9 +406,10 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 					PERF_OUTPUT_WEIGHT))
 		return -EINVAL;
 
-	if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
+	if (PRINT_FIELD(SYM) &&
+		!(evsel->attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) {
 		pr_err("Display of symbols requested but neither sample IP nor "
-			   "sample address\nis selected. Hence, no addresses to convert "
+			   "sample address\navailable. Hence, no addresses to convert "
 		       "to symbols.\n");
 		return -EINVAL;
 	}
@@ -417,10 +418,9 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		       "selected.\n");
 		return -EINVAL;
 	}
-	if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR) &&
-	    !PRINT_FIELD(BRSTACK) && !PRINT_FIELD(BRSTACKSYM) && !PRINT_FIELD(BRSTACKOFF)) {
-		pr_err("Display of DSO requested but no address to convert.  Select\n"
-		       "sample IP, sample address, brstack, brstacksym, or brstackoff.\n");
+	if (PRINT_FIELD(DSO) &&
+		!(evsel->attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) {
+		pr_err("Display of DSO requested but no address to convert.\n");
 		return -EINVAL;
 	}
 	if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) {
@@ -2491,6 +2491,8 @@ parse:
 						output[j].fields &= ~all_output_options[i].field;
 					else
 						output[j].fields |= all_output_options[i].field;
+					output[j].user_set = true;
+					output[j].wildcard_set = true;
 				}
 			}
 		} else {
@@ -2501,7 +2503,8 @@ parse:
 				rc = -EINVAL;
 				goto out;
 			}
-			output[type].fields |= all_output_options[i].field;
+			output[type].user_set = true;
+			output[type].wildcard_set = true;
 		}
 	}
 
-- 
cgit v1.2.3


From a78cdee6fbb136694334ade4cedb331a9d0b4d5e Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Tue, 18 Sep 2018 05:32:10 -0700
Subject: perf script: Print DSO for callindent

Now that we don't need to print the IP/ADDR for callindent the DSO is
also not printed. It's useful for some cases, so add an own DSO printout
for callindent for the case when IP/ADDR is not enabled.

Before:

% perf script --itrace=cr -F +callindent,-ip,-sym,-symoff,-addr
         swapper     0 [000]  3377.917072:          1   branches: pt_config
         swapper     0 [000]  3377.917072:          1   branches:     pt_config
         swapper     0 [000]  3377.917072:          1   branches:     pt_event_add
         swapper     0 [000]  3377.917072:          1   branches:     perf_pmu_enable
         swapper     0 [000]  3377.917072:          1   branches:     perf_pmu_nop_void
         swapper     0 [000]  3377.917072:          1   branches:     event_sched_in.isra.107
         swapper     0 [000]  3377.917072:          1   branches:     __x86_indirect_thunk_rax
         swapper     0 [000]  3377.917072:          1   branches:     perf_pmu_nop_int
         swapper     0 [000]  3377.917072:          1   branches:     group_sched_in
         swapper     0 [000]  3377.917072:          1   branches:     event_filter_match
         swapper     0 [000]  3377.917072:          1   branches:     event_filter_match
         swapper     0 [000]  3377.917072:          1   branches:     group_sched_in

After:

         swapper     0 [000]  3377.917072:          1   branches: ([unknown])   pt_config
         swapper     0 [000]  3377.917072:          1   branches: ([kernel.kallsyms])       pt_config
         swapper     0 [000]  3377.917072:          1   branches: ([kernel.kallsyms])       pt_event_add
         swapper     0 [000]  3377.917072:          1   branches: ([kernel.kallsyms])       perf_pmu_enable
         swapper     0 [000]  3377.917072:          1   branches: ([kernel.kallsyms])       perf_pmu_nop_void
         swapper     0 [000]  3377.917072:          1   branches: ([kernel.kallsyms])       event_sched_in.isra.107
         swapper     0 [000]  3377.917072:          1   branches: ([kernel.kallsyms])       __x86_indirect_thunk_rax
         swapper     0 [000]  3377.917072:          1   branches: ([kernel.kallsyms])       perf_pmu_nop_int
         swapper     0 [000]  3377.917072:          1   branches: ([kernel.kallsyms])       group_sched_in
         swapper     0 [000]  3377.917072:          1   branches: ([kernel.kallsyms])       event_filter_match
         swapper     0 [000]  3377.917072:          1   branches: ([kernel.kallsyms])       event_filter_match
         swapper     0 [000]  3377.917072:          1   branches: ([kernel.kallsyms])       group_sched_in
         swapper     0 [000]  3377.917072:          1   branches: ([kernel.kallsyms])           __x86_indirect_thunk_rax
         swapper     0 [000]  3377.917072:          1   branches: ([kernel.kallsyms])           perf_pmu_nop_txn
         swapper     0 [000]  3377.917072:          1   branches: ([kernel.kallsyms])           event_sched_in.isra.107

(in the kernel case of course it's not very useful, but it's important
with user programs where symbols are not unique)

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kim Phillips <kim.phillips@arm.com>
Link: http://lkml.kernel.org/r/20180918123214.26728-6-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 7aa59696e97a..7732346bd9dd 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1115,6 +1115,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 	const char *name = NULL;
 	static int spacing;
 	int len = 0;
+	int dlen = 0;
 	u64 ip = 0;
 
 	/*
@@ -1141,6 +1142,12 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 			ip = sample->ip;
 	}
 
+	if (PRINT_FIELD(DSO) && !(PRINT_FIELD(IP) || PRINT_FIELD(ADDR))) {
+		dlen += fprintf(fp, "(");
+		dlen += map__fprintf_dsoname(al->map, fp);
+		dlen += fprintf(fp, ")\t");
+	}
+
 	if (name)
 		len = fprintf(fp, "%*s%s", (int)depth * 4, "", name);
 	else if (ip)
@@ -1159,7 +1166,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 	if (len < spacing)
 		len += fprintf(fp, "%*s", spacing - len, "");
 
-	return len;
+	return len + dlen;
 }
 
 static int perf_sample__fprintf_insn(struct perf_sample *sample,
-- 
cgit v1.2.3


From 4963b0f88bb91ed0122f7b08876ae89fcafb2842 Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Wed, 19 Sep 2018 14:56:44 -0400
Subject: tools lib traceevent, perf tools: Rename struct event_format to
 struct tep_event_format

In order to make libtraceevent into a proper library, variables, data
structures and functions require a unique prefix to prevent name space
conflicts. That prefix will be "tep_". This renames struct event_format
to struct tep_event_format

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lkml.kernel.org/r/20180919185722.495820809@goodmis.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.c                 | 186 ++++++++++-----------
 tools/lib/traceevent/event-parse.h                 |  66 ++++----
 tools/lib/traceevent/parse-filter.c                |  42 ++---
 tools/lib/traceevent/plugin_function.c             |   2 +-
 tools/lib/traceevent/plugin_hrtimer.c              |   4 +-
 tools/lib/traceevent/plugin_kmem.c                 |   2 +-
 tools/lib/traceevent/plugin_kvm.c                  |  14 +-
 tools/lib/traceevent/plugin_mac80211.c             |   4 +-
 tools/lib/traceevent/plugin_sched_switch.c         |   4 +-
 tools/perf/builtin-trace.c                         |   2 +-
 tools/perf/util/evsel.h                            |   4 +-
 tools/perf/util/header.c                           |   2 +-
 tools/perf/util/python.c                           |   4 +-
 .../perf/util/scripting-engines/trace-event-perl.c |   6 +-
 .../util/scripting-engines/trace-event-python.c    |   8 +-
 tools/perf/util/trace-event-parse.c                |  14 +-
 tools/perf/util/trace-event.c                      |   8 +-
 tools/perf/util/trace-event.h                      |  16 +-
 18 files changed, 194 insertions(+), 194 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 70a42bec6931..bb2ebb322124 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -95,7 +95,7 @@ struct tep_function_handler {
 
 static unsigned long long
 process_defined_func(struct trace_seq *s, void *data, int size,
-		     struct event_format *event, struct print_arg *arg);
+		     struct tep_event_format *event, struct print_arg *arg);
 
 static void free_func_handle(struct tep_function_handler *func);
 
@@ -738,16 +738,16 @@ void tep_print_printk(struct tep_handle *pevent)
 	}
 }
 
-static struct event_format *alloc_event(void)
+static struct tep_event_format *alloc_event(void)
 {
-	return calloc(1, sizeof(struct event_format));
+	return calloc(1, sizeof(struct tep_event_format));
 }
 
-static int add_event(struct tep_handle *pevent, struct event_format *event)
+static int add_event(struct tep_handle *pevent, struct tep_event_format *event)
 {
 	int i;
-	struct event_format **events = realloc(pevent->events, sizeof(event) *
-					       (pevent->nr_events + 1));
+	struct tep_event_format **events = realloc(pevent->events, sizeof(event) *
+						  (pevent->nr_events + 1));
 	if (!events)
 		return -1;
 
@@ -1354,7 +1354,7 @@ static unsigned int type_size(const char *name)
 	return 0;
 }
 
-static int event_read_fields(struct event_format *event, struct format_field **fields)
+static int event_read_fields(struct tep_event_format *event, struct format_field **fields)
 {
 	struct format_field *field = NULL;
 	enum event_type type;
@@ -1641,7 +1641,7 @@ fail_expect:
 	return -1;
 }
 
-static int event_read_format(struct event_format *event)
+static int event_read_format(struct tep_event_format *event)
 {
 	char *token;
 	int ret;
@@ -1674,11 +1674,11 @@ static int event_read_format(struct event_format *event)
 }
 
 static enum event_type
-process_arg_token(struct event_format *event, struct print_arg *arg,
+process_arg_token(struct tep_event_format *event, struct print_arg *arg,
 		  char **tok, enum event_type type);
 
 static enum event_type
-process_arg(struct event_format *event, struct print_arg *arg, char **tok)
+process_arg(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
 	enum event_type type;
 	char *token;
@@ -1690,14 +1690,14 @@ process_arg(struct event_format *event, struct print_arg *arg, char **tok)
 }
 
 static enum event_type
-process_op(struct event_format *event, struct print_arg *arg, char **tok);
+process_op(struct tep_event_format *event, struct print_arg *arg, char **tok);
 
 /*
  * For __print_symbolic() and __print_flags, we need to completely
  * evaluate the first argument, which defines what to print next.
  */
 static enum event_type
-process_field_arg(struct event_format *event, struct print_arg *arg, char **tok)
+process_field_arg(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
 	enum event_type type;
 
@@ -1711,7 +1711,7 @@ process_field_arg(struct event_format *event, struct print_arg *arg, char **tok)
 }
 
 static enum event_type
-process_cond(struct event_format *event, struct print_arg *top, char **tok)
+process_cond(struct tep_event_format *event, struct print_arg *top, char **tok)
 {
 	struct print_arg *arg, *left, *right;
 	enum event_type type;
@@ -1767,7 +1767,7 @@ out_free:
 }
 
 static enum event_type
-process_array(struct event_format *event, struct print_arg *top, char **tok)
+process_array(struct tep_event_format *event, struct print_arg *top, char **tok)
 {
 	struct print_arg *arg;
 	enum event_type type;
@@ -1869,7 +1869,7 @@ static int set_op_prio(struct print_arg *arg)
 
 /* Note, *tok does not get freed, but will most likely be saved */
 static enum event_type
-process_op(struct event_format *event, struct print_arg *arg, char **tok)
+process_op(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
 	struct print_arg *left, *right = NULL;
 	enum event_type type;
@@ -2070,7 +2070,7 @@ out_free:
 }
 
 static enum event_type
-process_entry(struct event_format *event __maybe_unused, struct print_arg *arg,
+process_entry(struct tep_event_format *event __maybe_unused, struct print_arg *arg,
 	      char **tok)
 {
 	enum event_type type;
@@ -2109,7 +2109,7 @@ process_entry(struct event_format *event __maybe_unused, struct print_arg *arg,
 	return EVENT_ERROR;
 }
 
-static int alloc_and_process_delim(struct event_format *event, char *next_token,
+static int alloc_and_process_delim(struct tep_event_format *event, char *next_token,
 				   struct print_arg **print_arg)
 {
 	struct print_arg *field;
@@ -2444,7 +2444,7 @@ static char *arg_eval (struct print_arg *arg)
 }
 
 static enum event_type
-process_fields(struct event_format *event, struct print_flag_sym **list, char **tok)
+process_fields(struct tep_event_format *event, struct print_flag_sym **list, char **tok)
 {
 	enum event_type type;
 	struct print_arg *arg = NULL;
@@ -2525,7 +2525,7 @@ out_free:
 }
 
 static enum event_type
-process_flags(struct event_format *event, struct print_arg *arg, char **tok)
+process_flags(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
 	struct print_arg *field;
 	enum event_type type;
@@ -2578,7 +2578,7 @@ out_free:
 }
 
 static enum event_type
-process_symbols(struct event_format *event, struct print_arg *arg, char **tok)
+process_symbols(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
 	struct print_arg *field;
 	enum event_type type;
@@ -2617,7 +2617,7 @@ out_free:
 }
 
 static enum event_type
-process_hex_common(struct event_format *event, struct print_arg *arg,
+process_hex_common(struct tep_event_format *event, struct print_arg *arg,
 		   char **tok, enum print_arg_type type)
 {
 	memset(arg, 0, sizeof(*arg));
@@ -2640,20 +2640,20 @@ out:
 }
 
 static enum event_type
-process_hex(struct event_format *event, struct print_arg *arg, char **tok)
+process_hex(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
 	return process_hex_common(event, arg, tok, PRINT_HEX);
 }
 
 static enum event_type
-process_hex_str(struct event_format *event, struct print_arg *arg,
+process_hex_str(struct tep_event_format *event, struct print_arg *arg,
 		char **tok)
 {
 	return process_hex_common(event, arg, tok, PRINT_HEX_STR);
 }
 
 static enum event_type
-process_int_array(struct event_format *event, struct print_arg *arg, char **tok)
+process_int_array(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
 	memset(arg, 0, sizeof(*arg));
 	arg->type = PRINT_INT_ARRAY;
@@ -2681,7 +2681,7 @@ out:
 }
 
 static enum event_type
-process_dynamic_array(struct event_format *event, struct print_arg *arg, char **tok)
+process_dynamic_array(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
 	struct format_field *field;
 	enum event_type type;
@@ -2745,7 +2745,7 @@ process_dynamic_array(struct event_format *event, struct print_arg *arg, char **
 }
 
 static enum event_type
-process_dynamic_array_len(struct event_format *event, struct print_arg *arg,
+process_dynamic_array_len(struct tep_event_format *event, struct print_arg *arg,
 			  char **tok)
 {
 	struct format_field *field;
@@ -2781,7 +2781,7 @@ process_dynamic_array_len(struct event_format *event, struct print_arg *arg,
 }
 
 static enum event_type
-process_paren(struct event_format *event, struct print_arg *arg, char **tok)
+process_paren(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
 	struct print_arg *item_arg;
 	enum event_type type;
@@ -2844,7 +2844,7 @@ process_paren(struct event_format *event, struct print_arg *arg, char **tok)
 
 
 static enum event_type
-process_str(struct event_format *event __maybe_unused, struct print_arg *arg,
+process_str(struct tep_event_format *event __maybe_unused, struct print_arg *arg,
 	    char **tok)
 {
 	enum event_type type;
@@ -2873,8 +2873,8 @@ process_str(struct event_format *event __maybe_unused, struct print_arg *arg,
 }
 
 static enum event_type
-process_bitmask(struct event_format *event __maybe_unused, struct print_arg *arg,
-	    char **tok)
+process_bitmask(struct tep_event_format *event __maybe_unused, struct print_arg *arg,
+		char **tok)
 {
 	enum event_type type;
 	char *token;
@@ -2934,7 +2934,7 @@ static void remove_func_handler(struct tep_handle *pevent, char *func_name)
 }
 
 static enum event_type
-process_func_handler(struct event_format *event, struct tep_function_handler *func,
+process_func_handler(struct tep_event_format *event, struct tep_function_handler *func,
 		     struct print_arg *arg, char **tok)
 {
 	struct print_arg **next_arg;
@@ -2992,7 +2992,7 @@ err:
 }
 
 static enum event_type
-process_function(struct event_format *event, struct print_arg *arg,
+process_function(struct tep_event_format *event, struct print_arg *arg,
 		 char *token, char **tok)
 {
 	struct tep_function_handler *func;
@@ -3048,7 +3048,7 @@ process_function(struct event_format *event, struct print_arg *arg,
 }
 
 static enum event_type
-process_arg_token(struct event_format *event, struct print_arg *arg,
+process_arg_token(struct tep_event_format *event, struct print_arg *arg,
 		  char **tok, enum event_type type)
 {
 	char *token;
@@ -3136,7 +3136,7 @@ process_arg_token(struct event_format *event, struct print_arg *arg,
 	return type;
 }
 
-static int event_read_print_args(struct event_format *event, struct print_arg **list)
+static int event_read_print_args(struct tep_event_format *event, struct print_arg **list)
 {
 	enum event_type type = EVENT_ERROR;
 	struct print_arg *arg;
@@ -3194,7 +3194,7 @@ static int event_read_print_args(struct event_format *event, struct print_arg **
 	return args;
 }
 
-static int event_read_print(struct event_format *event)
+static int event_read_print(struct tep_event_format *event)
 {
 	enum event_type type;
 	char *token;
@@ -3260,7 +3260,7 @@ static int event_read_print(struct event_format *event)
  * This only searchs the common fields and not all field.
  */
 struct format_field *
-tep_find_common_field(struct event_format *event, const char *name)
+tep_find_common_field(struct tep_event_format *event, const char *name)
 {
 	struct format_field *format;
 
@@ -3282,7 +3282,7 @@ tep_find_common_field(struct event_format *event, const char *name)
  * This does not search common fields.
  */
 struct format_field *
-tep_find_field(struct event_format *event, const char *name)
+tep_find_field(struct tep_event_format *event, const char *name)
 {
 	struct format_field *format;
 
@@ -3305,7 +3305,7 @@ tep_find_field(struct event_format *event, const char *name)
  * the non-common ones if a common one was not found.
  */
 struct format_field *
-tep_find_any_field(struct event_format *event, const char *name)
+tep_find_any_field(struct tep_event_format *event, const char *name)
 {
 	struct format_field *format;
 
@@ -3374,7 +3374,7 @@ int tep_read_number_field(struct format_field *field, const void *data,
 static int get_common_info(struct tep_handle *pevent,
 			   const char *type, int *offset, int *size)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	struct format_field *field;
 
 	/*
@@ -3461,11 +3461,11 @@ static int events_id_cmp(const void *a, const void *b);
  *
  * Returns an event that has a given @id.
  */
-struct event_format *tep_find_event(struct tep_handle *pevent, int id)
+struct tep_event_format *tep_find_event(struct tep_handle *pevent, int id)
 {
-	struct event_format **eventptr;
-	struct event_format key;
-	struct event_format *pkey = &key;
+	struct tep_event_format **eventptr;
+	struct tep_event_format key;
+	struct tep_event_format *pkey = &key;
 
 	/* Check cache first */
 	if (pevent->last_event && pevent->last_event->id == id)
@@ -3493,11 +3493,11 @@ struct event_format *tep_find_event(struct tep_handle *pevent, int id)
  * This returns an event with a given @name and under the system
  * @sys. If @sys is NULL the first event with @name is returned.
  */
-struct event_format *
+struct tep_event_format *
 tep_find_event_by_name(struct tep_handle *pevent,
 		       const char *sys, const char *name)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	int i;
 
 	if (pevent->last_event &&
@@ -3522,7 +3522,7 @@ tep_find_event_by_name(struct tep_handle *pevent,
 }
 
 static unsigned long long
-eval_num_arg(void *data, int size, struct event_format *event, struct print_arg *arg)
+eval_num_arg(void *data, int size, struct tep_event_format *event, struct print_arg *arg)
 {
 	struct tep_handle *pevent = event->pevent;
 	unsigned long long val = 0;
@@ -3862,7 +3862,7 @@ static void print_bitmask_to_seq(struct tep_handle *pevent,
 }
 
 static void print_str_arg(struct trace_seq *s, void *data, int size,
-			  struct event_format *event, const char *format,
+			  struct tep_event_format *event, const char *format,
 			  int len_arg, struct print_arg *arg)
 {
 	struct tep_handle *pevent = event->pevent;
@@ -4117,7 +4117,7 @@ out_warning_field:
 
 static unsigned long long
 process_defined_func(struct trace_seq *s, void *data, int size,
-		     struct event_format *event, struct print_arg *arg)
+		     struct tep_event_format *event, struct print_arg *arg)
 {
 	struct tep_function_handler *func_handle = arg->func.func;
 	struct func_params *param;
@@ -4212,7 +4212,7 @@ static void free_args(struct print_arg *args)
 	}
 }
 
-static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struct event_format *event)
+static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struct tep_event_format *event)
 {
 	struct tep_handle *pevent = event->pevent;
 	struct format_field *field, *ip_field;
@@ -4389,7 +4389,7 @@ out_free:
 
 static char *
 get_bprint_format(void *data, int size __maybe_unused,
-		  struct event_format *event)
+		  struct tep_event_format *event)
 {
 	struct tep_handle *pevent = event->pevent;
 	unsigned long long addr;
@@ -4424,7 +4424,7 @@ get_bprint_format(void *data, int size __maybe_unused,
 }
 
 static void print_mac_arg(struct trace_seq *s, int mac, void *data, int size,
-			  struct event_format *event, struct print_arg *arg)
+			  struct tep_event_format *event, struct print_arg *arg)
 {
 	unsigned char *buf;
 	const char *fmt = "%.2x:%.2x:%.2x:%.2x:%.2x:%.2x";
@@ -4577,7 +4577,7 @@ static void print_ip6_addr(struct trace_seq *s, char i, unsigned char *buf)
  * %pISpc print an IP address based on sockaddr; p adds port.
  */
 static int print_ipv4_arg(struct trace_seq *s, const char *ptr, char i,
-			  void *data, int size, struct event_format *event,
+			  void *data, int size, struct tep_event_format *event,
 			  struct print_arg *arg)
 {
 	unsigned char *buf;
@@ -4614,7 +4614,7 @@ static int print_ipv4_arg(struct trace_seq *s, const char *ptr, char i,
 }
 
 static int print_ipv6_arg(struct trace_seq *s, const char *ptr, char i,
-			  void *data, int size, struct event_format *event,
+			  void *data, int size, struct tep_event_format *event,
 			  struct print_arg *arg)
 {
 	char have_c = 0;
@@ -4664,7 +4664,7 @@ static int print_ipv6_arg(struct trace_seq *s, const char *ptr, char i,
 }
 
 static int print_ipsa_arg(struct trace_seq *s, const char *ptr, char i,
-			  void *data, int size, struct event_format *event,
+			  void *data, int size, struct tep_event_format *event,
 			  struct print_arg *arg)
 {
 	char have_c = 0, have_p = 0;
@@ -4746,7 +4746,7 @@ static int print_ipsa_arg(struct trace_seq *s, const char *ptr, char i,
 }
 
 static int print_ip_arg(struct trace_seq *s, const char *ptr,
-			void *data, int size, struct event_format *event,
+			void *data, int size, struct tep_event_format *event,
 			struct print_arg *arg)
 {
 	char i = *ptr;  /* 'i' or 'I' */
@@ -4853,7 +4853,7 @@ void tep_print_field(struct trace_seq *s, void *data,
 }
 
 void tep_print_fields(struct trace_seq *s, void *data,
-		      int size __maybe_unused, struct event_format *event)
+		      int size __maybe_unused, struct tep_event_format *event)
 {
 	struct format_field *field;
 
@@ -4865,7 +4865,7 @@ void tep_print_fields(struct trace_seq *s, void *data,
 	}
 }
 
-static void pretty_print(struct trace_seq *s, void *data, int size, struct event_format *event)
+static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_event_format *event)
 {
 	struct tep_handle *pevent = event->pevent;
 	struct print_fmt *print_fmt = &event->print_fmt;
@@ -5228,7 +5228,7 @@ int tep_data_type(struct tep_handle *pevent, struct tep_record *rec)
  *
  * This returns the event form a given @type;
  */
-struct event_format *tep_data_event_from_type(struct tep_handle *pevent, int type)
+struct tep_event_format *tep_data_event_from_type(struct tep_handle *pevent, int type)
 {
 	return tep_find_event(pevent, type);
 }
@@ -5386,7 +5386,7 @@ int tep_cmdline_pid(struct tep_handle *pevent, struct cmdline *cmdline)
  * This parses the raw @data using the given @event information and
  * writes the print format into the trace_seq.
  */
-void tep_event_info(struct trace_seq *s, struct event_format *event,
+void tep_event_info(struct trace_seq *s, struct tep_event_format *event,
 		    struct tep_record *record)
 {
 	int print_pretty = 1;
@@ -5427,7 +5427,7 @@ static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock)
  * Returns the associated event for a given record, or NULL if non is
  * is found.
  */
-struct event_format *
+struct tep_event_format *
 tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record)
 {
 	int type;
@@ -5452,7 +5452,7 @@ tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record)
  * Writes the tasks comm, pid and CPU to @s.
  */
 void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
-			  struct event_format *event,
+			  struct tep_event_format *event,
 			  struct tep_record *record)
 {
 	void *data = record->data;
@@ -5480,7 +5480,7 @@ void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
  * Writes the timestamp of the record into @s.
  */
 void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
-			  struct event_format *event,
+			  struct tep_event_format *event,
 			  struct tep_record *record,
 			  bool use_trace_clock)
 {
@@ -5530,7 +5530,7 @@ void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
  * Writes the parsing of the record's data to @s.
  */
 void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
-			  struct event_format *event,
+			  struct tep_event_format *event,
 			  struct tep_record *record)
 {
 	static const char *spaces = "                    "; /* 20 spaces */
@@ -5549,7 +5549,7 @@ void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
 void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
 		     struct tep_record *record, bool use_trace_clock)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 
 	event = tep_find_event_by_record(pevent, record);
 	if (!event) {
@@ -5571,8 +5571,8 @@ void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
 
 static int events_id_cmp(const void *a, const void *b)
 {
-	struct event_format * const * ea = a;
-	struct event_format * const * eb = b;
+	struct tep_event_format * const * ea = a;
+	struct tep_event_format * const * eb = b;
 
 	if ((*ea)->id < (*eb)->id)
 		return -1;
@@ -5585,8 +5585,8 @@ static int events_id_cmp(const void *a, const void *b)
 
 static int events_name_cmp(const void *a, const void *b)
 {
-	struct event_format * const * ea = a;
-	struct event_format * const * eb = b;
+	struct tep_event_format * const * ea = a;
+	struct tep_event_format * const * eb = b;
 	int res;
 
 	res = strcmp((*ea)->name, (*eb)->name);
@@ -5602,8 +5602,8 @@ static int events_name_cmp(const void *a, const void *b)
 
 static int events_system_cmp(const void *a, const void *b)
 {
-	struct event_format * const * ea = a;
-	struct event_format * const * eb = b;
+	struct tep_event_format * const * ea = a;
+	struct tep_event_format * const * eb = b;
 	int res;
 
 	res = strcmp((*ea)->system, (*eb)->system);
@@ -5617,9 +5617,9 @@ static int events_system_cmp(const void *a, const void *b)
 	return events_id_cmp(a, b);
 }
 
-struct event_format **tep_list_events(struct tep_handle *pevent, enum event_sort_type sort_type)
+struct tep_event_format **tep_list_events(struct tep_handle *pevent, enum event_sort_type sort_type)
 {
-	struct event_format **events;
+	struct tep_event_format **events;
 	int (*sort)(const void *a, const void *b);
 
 	events = pevent->sort_events;
@@ -5702,7 +5702,7 @@ get_event_fields(const char *type, const char *name,
  * Returns an allocated array of fields. The last item in the array is NULL.
  * The array must be freed with free().
  */
-struct format_field **tep_event_common_fields(struct event_format *event)
+struct format_field **tep_event_common_fields(struct tep_event_format *event)
 {
 	return get_event_fields("common", event->name,
 				event->format.nr_common,
@@ -5716,7 +5716,7 @@ struct format_field **tep_event_common_fields(struct event_format *event)
  * Returns an allocated array of fields. The last item in the array is NULL.
  * The array must be freed with free().
  */
-struct format_field **tep_event_fields(struct event_format *event)
+struct format_field **tep_event_fields(struct tep_event_format *event)
 {
 	return get_event_fields("event", event->name,
 				event->format.nr_fields,
@@ -5958,7 +5958,7 @@ int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long si
 	return 0;
 }
 
-static int event_matches(struct event_format *event,
+static int event_matches(struct tep_event_format *event,
 			 int id, const char *sys_name,
 			 const char *event_name)
 {
@@ -5981,7 +5981,7 @@ static void free_handler(struct event_handler *handle)
 	free(handle);
 }
 
-static int find_event_handle(struct tep_handle *pevent, struct event_format *event)
+static int find_event_handle(struct tep_handle *pevent, struct tep_event_format *event)
 {
 	struct event_handler *handle, **next;
 
@@ -6022,11 +6022,11 @@ static int find_event_handle(struct tep_handle *pevent, struct event_format *eve
  *
  * /sys/kernel/debug/tracing/events/.../.../format
  */
-enum tep_errno __tep_parse_format(struct event_format **eventp,
+enum tep_errno __tep_parse_format(struct tep_event_format **eventp,
 				  struct tep_handle *pevent, const char *buf,
 				  unsigned long size, const char *sys)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	int ret;
 
 	init_input_buf(buf, size);
@@ -6131,12 +6131,12 @@ enum tep_errno __tep_parse_format(struct event_format **eventp,
 
 static enum tep_errno
 __parse_event(struct tep_handle *pevent,
-	      struct event_format **eventp,
+	      struct tep_event_format **eventp,
 	      const char *buf, unsigned long size,
 	      const char *sys)
 {
 	int ret = __tep_parse_format(eventp, pevent, buf, size, sys);
-	struct event_format *event = *eventp;
+	struct tep_event_format *event = *eventp;
 
 	if (event == NULL)
 		return ret;
@@ -6173,7 +6173,7 @@ event_add_failed:
  * /sys/kernel/debug/tracing/events/.../.../format
  */
 enum tep_errno tep_parse_format(struct tep_handle *pevent,
-				struct event_format **eventp,
+				struct tep_event_format **eventp,
 				const char *buf,
 				unsigned long size, const char *sys)
 {
@@ -6197,7 +6197,7 @@ enum tep_errno tep_parse_format(struct tep_handle *pevent,
 enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf,
 			       unsigned long size, const char *sys)
 {
-	struct event_format *event = NULL;
+	struct tep_event_format *event = NULL;
 	return __parse_event(pevent, &event, buf, size, sys);
 }
 
@@ -6263,7 +6263,7 @@ int get_field_val(struct trace_seq *s, struct format_field *field,
  *
  * On failure, it returns NULL.
  */
-void *tep_get_field_raw(struct trace_seq *s, struct event_format *event,
+void *tep_get_field_raw(struct trace_seq *s, struct tep_event_format *event,
 			const char *name, struct tep_record *record,
 			int *len, int err)
 {
@@ -6310,7 +6310,7 @@ void *tep_get_field_raw(struct trace_seq *s, struct event_format *event,
  *
  * Returns 0 on success -1 on field not found.
  */
-int tep_get_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_field_val(struct trace_seq *s, struct tep_event_format *event,
 		      const char *name, struct tep_record *record,
 		      unsigned long long *val, int err)
 {
@@ -6335,7 +6335,7 @@ int tep_get_field_val(struct trace_seq *s, struct event_format *event,
  *
  * Returns 0 on success -1 on field not found.
  */
-int tep_get_common_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_common_field_val(struct trace_seq *s, struct tep_event_format *event,
 			     const char *name, struct tep_record *record,
 			     unsigned long long *val, int err)
 {
@@ -6360,7 +6360,7 @@ int tep_get_common_field_val(struct trace_seq *s, struct event_format *event,
  *
  * Returns 0 on success -1 on field not found.
  */
-int tep_get_any_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_any_field_val(struct trace_seq *s, struct tep_event_format *event,
 			  const char *name, struct tep_record *record,
 			  unsigned long long *val, int err)
 {
@@ -6386,7 +6386,7 @@ int tep_get_any_field_val(struct trace_seq *s, struct event_format *event,
  * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
  */
 int tep_print_num_field(struct trace_seq *s, const char *fmt,
-			struct event_format *event, const char *name,
+			struct tep_event_format *event, const char *name,
 			struct tep_record *record, int err)
 {
 	struct format_field *field = tep_find_field(event, name);
@@ -6418,7 +6418,7 @@ int tep_print_num_field(struct trace_seq *s, const char *fmt,
  * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
  */
 int tep_print_func_field(struct trace_seq *s, const char *fmt,
-			 struct event_format *event, const char *name,
+			 struct tep_event_format *event, const char *name,
 			 struct tep_record *record, int err)
 {
 	struct format_field *field = tep_find_field(event, name);
@@ -6578,11 +6578,11 @@ int tep_unregister_print_function(struct tep_handle *pevent,
 	return -1;
 }
 
-static struct event_format *search_event(struct tep_handle *pevent, int id,
+static struct tep_event_format *search_event(struct tep_handle *pevent, int id,
 					 const char *sys_name,
 					 const char *event_name)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 
 	if (id >= 0) {
 		/* search by id */
@@ -6622,7 +6622,7 @@ int tep_register_event_handler(struct tep_handle *pevent, int id,
 			       const char *sys_name, const char *event_name,
 			       tep_event_handler_func func, void *context)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	struct event_handler *handle;
 
 	event = search_event(pevent, id, sys_name, event_name);
@@ -6706,7 +6706,7 @@ int tep_unregister_event_handler(struct tep_handle *pevent, int id,
 				 const char *sys_name, const char *event_name,
 				 tep_event_handler_func func, void *context)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	struct event_handler *handle;
 	struct event_handler **next;
 
@@ -6784,7 +6784,7 @@ static void free_formats(struct format *format)
 	free_format_fields(format->fields);
 }
 
-void tep_free_format(struct event_format *event)
+void tep_free_format(struct tep_event_format *event)
 {
 	free(event->name);
 	free(event->system);
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index fa665c66bfa4..82de69c2b054 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -54,14 +54,14 @@ struct tep_record {
 #endif
 };
 
-/* ----------------------- pevent ----------------------- */
+/* ----------------------- tep ----------------------- */
 
 struct tep_handle;
-struct event_format;
+struct tep_event_format;
 
 typedef int (*tep_event_handler_func)(struct trace_seq *s,
 				      struct tep_record *record,
-				      struct event_format *event,
+				      struct tep_event_format *event,
 				      void *context);
 
 typedef int (*tep_plugin_load_func)(struct tep_handle *pevent);
@@ -143,7 +143,7 @@ enum format_flags {
 
 struct format_field {
 	struct format_field	*next;
-	struct event_format	*event;
+	struct tep_event_format	*event;
 	char			*type;
 	char			*name;
 	char			*alias;
@@ -277,7 +277,7 @@ struct print_fmt {
 	struct print_arg	*args;
 };
 
-struct event_format {
+struct tep_event_format {
 	struct tep_handle	*pevent;
 	char			*name;
 	int			id;
@@ -451,9 +451,9 @@ struct tep_handle {
 	unsigned int printk_count;
 
 
-	struct event_format **events;
+	struct tep_event_format **events;
 	int nr_events;
-	struct event_format **sort_events;
+	struct tep_event_format **sort_events;
 	enum event_sort_type last_type;
 
 	int type_offset;
@@ -485,7 +485,7 @@ struct tep_handle {
 	struct tep_function_handler *func_handlers;
 
 	/* cache */
-	struct event_format *last_event;
+	struct tep_event_format *last_event;
 
 	char *trace_clock;
 };
@@ -585,14 +585,14 @@ int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
 int tep_pid_is_registered(struct tep_handle *pevent, int pid);
 
 void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
-			  struct event_format *event,
+			  struct tep_event_format *event,
 			  struct tep_record *record);
 void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
-			  struct event_format *event,
+			  struct tep_event_format *event,
 			  struct tep_record *record,
 			  bool use_trace_clock);
 void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
-			  struct event_format *event,
+			  struct tep_event_format *event,
 			  struct tep_record *record);
 void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
 		     struct tep_record *record, bool use_trace_clock);
@@ -603,32 +603,32 @@ int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long si
 enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf,
 			       unsigned long size, const char *sys);
 enum tep_errno tep_parse_format(struct tep_handle *pevent,
-				struct event_format **eventp,
+				struct tep_event_format **eventp,
 				const char *buf,
 				unsigned long size, const char *sys);
-void tep_free_format(struct event_format *event);
+void tep_free_format(struct tep_event_format *event);
 void tep_free_format_field(struct format_field *field);
 
-void *tep_get_field_raw(struct trace_seq *s, struct event_format *event,
+void *tep_get_field_raw(struct trace_seq *s, struct tep_event_format *event,
 			const char *name, struct tep_record *record,
 			int *len, int err);
 
-int tep_get_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_field_val(struct trace_seq *s, struct tep_event_format *event,
 		      const char *name, struct tep_record *record,
 		      unsigned long long *val, int err);
-int tep_get_common_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_common_field_val(struct trace_seq *s, struct tep_event_format *event,
 			     const char *name, struct tep_record *record,
 			     unsigned long long *val, int err);
-int tep_get_any_field_val(struct trace_seq *s, struct event_format *event,
+int tep_get_any_field_val(struct trace_seq *s, struct tep_event_format *event,
 			  const char *name, struct tep_record *record,
 			  unsigned long long *val, int err);
 
 int tep_print_num_field(struct trace_seq *s, const char *fmt,
-			   struct event_format *event, const char *name,
-			   struct tep_record *record, int err);
+			struct tep_event_format *event, const char *name,
+			struct tep_record *record, int err);
 
 int tep_print_func_field(struct trace_seq *s, const char *fmt,
-			 struct event_format *event, const char *name,
+			 struct tep_event_format *event, const char *name,
 			 struct tep_record *record, int err);
 
 int tep_register_event_handler(struct tep_handle *pevent, int id,
@@ -644,9 +644,9 @@ int tep_register_print_function(struct tep_handle *pevent,
 int tep_unregister_print_function(struct tep_handle *pevent,
 				  tep_func_handler func, char *name);
 
-struct format_field *tep_find_common_field(struct event_format *event, const char *name);
-struct format_field *tep_find_field(struct event_format *event, const char *name);
-struct format_field *tep_find_any_field(struct event_format *event, const char *name);
+struct format_field *tep_find_common_field(struct tep_event_format *event, const char *name);
+struct format_field *tep_find_field(struct tep_event_format *event, const char *name);
+struct format_field *tep_find_any_field(struct tep_event_format *event, const char *name);
 
 const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr);
 unsigned long long
@@ -655,18 +655,18 @@ unsigned long long tep_read_number(struct tep_handle *pevent, const void *ptr, i
 int tep_read_number_field(struct format_field *field, const void *data,
 			  unsigned long long *value);
 
-struct event_format *tep_find_event(struct tep_handle *pevent, int id);
+struct tep_event_format *tep_find_event(struct tep_handle *pevent, int id);
 
-struct event_format *
+struct tep_event_format *
 tep_find_event_by_name(struct tep_handle *pevent, const char *sys, const char *name);
 
-struct event_format *
+struct tep_event_format *
 tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record);
 
 void tep_data_lat_fmt(struct tep_handle *pevent,
 		      struct trace_seq *s, struct tep_record *record);
 int tep_data_type(struct tep_handle *pevent, struct tep_record *rec);
-struct event_format *tep_data_event_from_type(struct tep_handle *pevent, int type);
+struct tep_event_format *tep_data_event_from_type(struct tep_handle *pevent, int type);
 int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec);
 int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec);
 int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec);
@@ -679,15 +679,15 @@ int tep_cmdline_pid(struct tep_handle *pevent, struct cmdline *cmdline);
 void tep_print_field(struct trace_seq *s, void *data,
 		     struct format_field *field);
 void tep_print_fields(struct trace_seq *s, void *data,
-		      int size __maybe_unused, struct event_format *event);
-void tep_event_info(struct trace_seq *s, struct event_format *event,
+		      int size __maybe_unused, struct tep_event_format *event);
+void tep_event_info(struct trace_seq *s, struct tep_event_format *event,
 		       struct tep_record *record);
 int tep_strerror(struct tep_handle *pevent, enum tep_errno errnum,
 		    char *buf, size_t buflen);
 
-struct event_format **tep_list_events(struct tep_handle *pevent, enum event_sort_type);
-struct format_field **tep_event_common_fields(struct event_format *event);
-struct format_field **tep_event_fields(struct event_format *event);
+struct tep_event_format **tep_list_events(struct tep_handle *pevent, enum event_sort_type);
+struct format_field **tep_event_common_fields(struct tep_event_format *event);
+struct format_field **tep_event_fields(struct tep_event_format *event);
 
 static inline int tep_get_cpus(struct tep_handle *pevent)
 {
@@ -884,7 +884,7 @@ struct filter_arg {
 
 struct filter_type {
 	int			event_id;
-	struct event_format	*event;
+	struct tep_event_format	*event;
 	struct filter_arg	*filter;
 };
 
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index e76154c02ee7..5572756307ab 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -26,7 +26,7 @@ static struct format_field cpu = {
 
 struct event_list {
 	struct event_list	*next;
-	struct event_format	*event;
+	struct tep_event_format	*event;
 };
 
 static void show_error(char *error_buf, const char *fmt, ...)
@@ -228,7 +228,7 @@ static void free_arg(struct filter_arg *arg)
 }
 
 static int add_event(struct event_list **events,
-		      struct event_format *event)
+		     struct tep_event_format *event)
 {
 	struct event_list *list;
 
@@ -242,7 +242,7 @@ static int add_event(struct event_list **events,
 	return 0;
 }
 
-static int event_match(struct event_format *event,
+static int event_match(struct tep_event_format *event,
 		       regex_t *sreg, regex_t *ereg)
 {
 	if (sreg) {
@@ -258,7 +258,7 @@ static enum tep_errno
 find_event(struct tep_handle *pevent, struct event_list **events,
 	   char *sys_name, char *event_name)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	regex_t ereg;
 	regex_t sreg;
 	int match = 0;
@@ -333,7 +333,7 @@ static void free_events(struct event_list *events)
 }
 
 static enum tep_errno
-create_arg_item(struct event_format *event, const char *token,
+create_arg_item(struct tep_event_format *event, const char *token,
 		enum event_type type, struct filter_arg **parg, char *error_str)
 {
 	struct format_field *field;
@@ -939,7 +939,7 @@ static int collapse_tree(struct filter_arg *arg,
 }
 
 static enum tep_errno
-process_filter(struct event_format *event, struct filter_arg **parg,
+process_filter(struct tep_event_format *event, struct filter_arg **parg,
 	       char *error_str, int not)
 {
 	enum event_type type;
@@ -1179,7 +1179,7 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 }
 
 static enum tep_errno
-process_event(struct event_format *event, const char *filter_str,
+process_event(struct tep_event_format *event, const char *filter_str,
 	      struct filter_arg **parg, char *error_str)
 {
 	int ret;
@@ -1204,7 +1204,7 @@ process_event(struct event_format *event, const char *filter_str,
 }
 
 static enum tep_errno
-filter_event(struct event_filter *filter, struct event_format *event,
+filter_event(struct event_filter *filter, struct tep_event_format *event,
 	     const char *filter_str, char *error_str)
 {
 	struct filter_type *filter_type;
@@ -1456,7 +1456,7 @@ static int copy_filter_type(struct event_filter *filter,
 			     struct filter_type *filter_type)
 {
 	struct filter_arg *arg;
-	struct event_format *event;
+	struct tep_event_format *event;
 	const char *sys;
 	const char *name;
 	char *str;
@@ -1538,7 +1538,7 @@ int tep_update_trivial(struct event_filter *dest, struct event_filter *source,
 {
 	struct tep_handle *src_pevent;
 	struct tep_handle *dest_pevent;
-	struct event_format *event;
+	struct tep_event_format *event;
 	struct filter_type *filter_type;
 	struct filter_arg *arg;
 	char *str;
@@ -1682,11 +1682,11 @@ int tep_filter_event_has_trivial(struct event_filter *filter,
 	}
 }
 
-static int test_filter(struct event_format *event, struct filter_arg *arg,
+static int test_filter(struct tep_event_format *event, struct filter_arg *arg,
 		       struct tep_record *record, enum tep_errno *err);
 
 static const char *
-get_comm(struct event_format *event, struct tep_record *record)
+get_comm(struct tep_event_format *event, struct tep_record *record)
 {
 	const char *comm;
 	int pid;
@@ -1697,7 +1697,7 @@ get_comm(struct event_format *event, struct tep_record *record)
 }
 
 static unsigned long long
-get_value(struct event_format *event,
+get_value(struct tep_event_format *event,
 	  struct format_field *field, struct tep_record *record)
 {
 	unsigned long long val;
@@ -1733,11 +1733,11 @@ get_value(struct event_format *event,
 }
 
 static unsigned long long
-get_arg_value(struct event_format *event, struct filter_arg *arg,
+get_arg_value(struct tep_event_format *event, struct filter_arg *arg,
 	      struct tep_record *record, enum tep_errno *err);
 
 static unsigned long long
-get_exp_value(struct event_format *event, struct filter_arg *arg,
+get_exp_value(struct tep_event_format *event, struct filter_arg *arg,
 	      struct tep_record *record, enum tep_errno *err)
 {
 	unsigned long long lval, rval;
@@ -1792,7 +1792,7 @@ get_exp_value(struct event_format *event, struct filter_arg *arg,
 }
 
 static unsigned long long
-get_arg_value(struct event_format *event, struct filter_arg *arg,
+get_arg_value(struct tep_event_format *event, struct filter_arg *arg,
 	      struct tep_record *record, enum tep_errno *err)
 {
 	switch (arg->type) {
@@ -1816,7 +1816,7 @@ get_arg_value(struct event_format *event, struct filter_arg *arg,
 	return 0;
 }
 
-static int test_num(struct event_format *event, struct filter_arg *arg,
+static int test_num(struct tep_event_format *event, struct filter_arg *arg,
 		    struct tep_record *record, enum tep_errno *err)
 {
 	unsigned long long lval, rval;
@@ -1859,7 +1859,7 @@ static int test_num(struct event_format *event, struct filter_arg *arg,
 
 static const char *get_field_str(struct filter_arg *arg, struct tep_record *record)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	struct tep_handle *pevent;
 	unsigned long long addr;
 	const char *val = NULL;
@@ -1907,7 +1907,7 @@ static const char *get_field_str(struct filter_arg *arg, struct tep_record *reco
 	return val;
 }
 
-static int test_str(struct event_format *event, struct filter_arg *arg,
+static int test_str(struct tep_event_format *event, struct filter_arg *arg,
 		    struct tep_record *record, enum tep_errno *err)
 {
 	const char *val;
@@ -1938,7 +1938,7 @@ static int test_str(struct event_format *event, struct filter_arg *arg,
 	}
 }
 
-static int test_op(struct event_format *event, struct filter_arg *arg,
+static int test_op(struct tep_event_format *event, struct filter_arg *arg,
 		   struct tep_record *record, enum tep_errno *err)
 {
 	switch (arg->op.type) {
@@ -1960,7 +1960,7 @@ static int test_op(struct event_format *event, struct filter_arg *arg,
 	}
 }
 
-static int test_filter(struct event_format *event, struct filter_arg *arg,
+static int test_filter(struct tep_event_format *event, struct filter_arg *arg,
 		       struct tep_record *record, enum tep_errno *err)
 {
 	if (*err) {
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
index 2919042e7dc2..528acc75d81a 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugin_function.c
@@ -124,7 +124,7 @@ static int add_and_get_index(const char *parent, const char *child, int cpu)
 }
 
 static int function_handler(struct trace_seq *s, struct tep_record *record,
-			    struct event_format *event, void *context)
+			    struct tep_event_format *event, void *context)
 {
 	struct tep_handle *pevent = event->pevent;
 	unsigned long long function;
diff --git a/tools/lib/traceevent/plugin_hrtimer.c b/tools/lib/traceevent/plugin_hrtimer.c
index 29b608076ea0..9aa05b4ca811 100644
--- a/tools/lib/traceevent/plugin_hrtimer.c
+++ b/tools/lib/traceevent/plugin_hrtimer.c
@@ -27,7 +27,7 @@
 
 static int timer_expire_handler(struct trace_seq *s,
 				struct tep_record *record,
-				struct event_format *event, void *context)
+				struct tep_event_format *event, void *context)
 {
 	trace_seq_printf(s, "hrtimer=");
 
@@ -47,7 +47,7 @@ static int timer_expire_handler(struct trace_seq *s,
 
 static int timer_start_handler(struct trace_seq *s,
 			       struct tep_record *record,
-			       struct event_format *event, void *context)
+			       struct tep_event_format *event, void *context)
 {
 	trace_seq_printf(s, "hrtimer=");
 
diff --git a/tools/lib/traceevent/plugin_kmem.c b/tools/lib/traceevent/plugin_kmem.c
index a7a162575e2c..5632aff43aba 100644
--- a/tools/lib/traceevent/plugin_kmem.c
+++ b/tools/lib/traceevent/plugin_kmem.c
@@ -25,7 +25,7 @@
 #include "trace-seq.h"
 
 static int call_site_handler(struct trace_seq *s, struct tep_record *record,
-			     struct event_format *event, void *context)
+			     struct tep_event_format *event, void *context)
 {
 	struct format_field *field;
 	unsigned long long val, addr;
diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c
index a0dfd3d0f197..d13c22846fa9 100644
--- a/tools/lib/traceevent/plugin_kvm.c
+++ b/tools/lib/traceevent/plugin_kvm.c
@@ -249,7 +249,7 @@ static const char *find_exit_reason(unsigned isa, int val)
 }
 
 static int print_exit_reason(struct trace_seq *s, struct tep_record *record,
-			     struct event_format *event, const char *field)
+			     struct tep_event_format *event, const char *field)
 {
 	unsigned long long isa;
 	unsigned long long val;
@@ -270,7 +270,7 @@ static int print_exit_reason(struct trace_seq *s, struct tep_record *record,
 }
 
 static int kvm_exit_handler(struct trace_seq *s, struct tep_record *record,
-			    struct event_format *event, void *context)
+			    struct tep_event_format *event, void *context)
 {
 	unsigned long long info1 = 0, info2 = 0;
 
@@ -293,7 +293,7 @@ static int kvm_exit_handler(struct trace_seq *s, struct tep_record *record,
 
 static int kvm_emulate_insn_handler(struct trace_seq *s,
 				    struct tep_record *record,
-				    struct event_format *event, void *context)
+				    struct tep_event_format *event, void *context)
 {
 	unsigned long long rip, csbase, len, flags, failed;
 	int llen;
@@ -332,7 +332,7 @@ static int kvm_emulate_insn_handler(struct trace_seq *s,
 
 
 static int kvm_nested_vmexit_inject_handler(struct trace_seq *s, struct tep_record *record,
-					    struct event_format *event, void *context)
+					    struct tep_event_format *event, void *context)
 {
 	if (print_exit_reason(s, record, event, "exit_code") < 0)
 		return -1;
@@ -346,7 +346,7 @@ static int kvm_nested_vmexit_inject_handler(struct trace_seq *s, struct tep_reco
 }
 
 static int kvm_nested_vmexit_handler(struct trace_seq *s, struct tep_record *record,
-				     struct event_format *event, void *context)
+				     struct tep_event_format *event, void *context)
 {
 	tep_print_num_field(s, "rip %llx ", event, "rip", record, 1);
 
@@ -372,7 +372,7 @@ union kvm_mmu_page_role {
 };
 
 static int kvm_mmu_print_role(struct trace_seq *s, struct tep_record *record,
-			      struct event_format *event, void *context)
+			      struct tep_event_format *event, void *context)
 {
 	unsigned long long val;
 	static const char *access_str[] = {
@@ -419,7 +419,7 @@ static int kvm_mmu_print_role(struct trace_seq *s, struct tep_record *record,
 
 static int kvm_mmu_get_page_handler(struct trace_seq *s,
 				    struct tep_record *record,
-				    struct event_format *event, void *context)
+				    struct tep_event_format *event, void *context)
 {
 	unsigned long long val;
 
diff --git a/tools/lib/traceevent/plugin_mac80211.c b/tools/lib/traceevent/plugin_mac80211.c
index 0b7779444b63..c16469614690 100644
--- a/tools/lib/traceevent/plugin_mac80211.c
+++ b/tools/lib/traceevent/plugin_mac80211.c
@@ -26,7 +26,7 @@
 
 #define INDENT 65
 
-static void print_string(struct trace_seq *s, struct event_format *event,
+static void print_string(struct trace_seq *s, struct tep_event_format *event,
 			 const char *name, const void *data)
 {
 	struct format_field *f = tep_find_field(event, name);
@@ -60,7 +60,7 @@ static void print_string(struct trace_seq *s, struct event_format *event,
 
 static int drv_bss_info_changed(struct trace_seq *s,
 				struct tep_record *record,
-				struct event_format *event, void *context)
+				struct tep_event_format *event, void *context)
 {
 	void *data = record->data;
 
diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c
index 582d3be2849b..a7eeb42894ae 100644
--- a/tools/lib/traceevent/plugin_sched_switch.c
+++ b/tools/lib/traceevent/plugin_sched_switch.c
@@ -67,7 +67,7 @@ static void write_and_save_comm(struct format_field *field,
 
 static int sched_wakeup_handler(struct trace_seq *s,
 				struct tep_record *record,
-				struct event_format *event, void *context)
+				struct tep_event_format *event, void *context)
 {
 	struct format_field *field;
 	unsigned long long val;
@@ -96,7 +96,7 @@ static int sched_wakeup_handler(struct trace_seq *s,
 
 static int sched_switch_handler(struct trace_seq *s,
 				struct tep_record *record,
-				struct event_format *event, void *context)
+				struct tep_event_format *event, void *context)
 {
 	struct format_field *field;
 	unsigned long long val;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 7ce277d22a91..9f8c365dacb1 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -862,7 +862,7 @@ static struct syscall_fmt *syscall_fmt__find(const char *name)
  * args_size: sum of the sizes of the syscall arguments, anything after that is augmented stuff: pathname for openat, etc.
  */
 struct syscall {
-	struct event_format *tp_format;
+	struct tep_event_format *tp_format;
 	int		    nr_args;
 	int		    args_size;
 	bool		    is_exit;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4f8430a85531..c0f275cf96ee 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -102,7 +102,7 @@ struct perf_evsel {
 	char			*name;
 	double			scale;
 	const char		*unit;
-	struct event_format	*tp_format;
+	struct tep_event_format	*tp_format;
 	off_t			id_offset;
 	struct perf_stat_evsel  *stats;
 	void			*priv;
@@ -211,7 +211,7 @@ static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char *
 
 struct perf_evsel *perf_evsel__new_cycles(bool precise);
 
-struct event_format *event_format__new(const char *sys, const char *name);
+struct tep_event_format *event_format__new(const char *sys, const char *name);
 
 void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index c78051ad1fcc..1ec1d9bc2d63 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3206,7 +3206,7 @@ static int read_attr(int fd, struct perf_header *ph,
 static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel,
 						struct tep_handle *pevent)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	char bf[128];
 
 	/* already prepared */
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index ce501ba14b08..6714d2c517db 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -386,7 +386,7 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
 	struct format_field *field;
 
 	if (!evsel->tp_format) {
-		struct event_format *tp_format;
+		struct tep_event_format *tp_format;
 
 		tp_format = trace_event__tp_format_id(evsel->attr.config);
 		if (!tp_format)
@@ -1240,7 +1240,7 @@ static struct {
 static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel,
 				  PyObject *args, PyObject *kwargs)
 {
-	struct event_format *tp_format;
+	struct tep_event_format *tp_format;
 	static char *kwlist[] = { "sys", "name", NULL };
 	char *sys  = NULL;
 	char *name = NULL;
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 45484f0f7292..370cc60f0afa 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -189,7 +189,7 @@ static void define_flag_field(const char *ev_name,
 	LEAVE;
 }
 
-static void define_event_symbols(struct event_format *event,
+static void define_event_symbols(struct tep_event_format *event,
 				 const char *ev_name,
 				 struct print_arg *args)
 {
@@ -338,7 +338,7 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 				    struct addr_location *al)
 {
 	struct thread *thread = al->thread;
-	struct event_format *event = evsel->tp_format;
+	struct tep_event_format *event = evsel->tp_format;
 	struct format_field *field;
 	static char handler[256];
 	unsigned long long val;
@@ -537,7 +537,7 @@ static int perl_stop_script(void)
 
 static int perl_generate_script(struct tep_handle *pevent, const char *outfile)
 {
-	struct event_format *event = NULL;
+	struct tep_event_format *event = NULL;
 	struct format_field *f;
 	char fname[PATH_MAX];
 	int not_first, count;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index dfc6093f118c..9a8a7b7ff64a 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -264,7 +264,7 @@ static void define_field(enum print_arg_type field_type,
 	Py_DECREF(t);
 }
 
-static void define_event_symbols(struct event_format *event,
+static void define_event_symbols(struct tep_event_format *event,
 				 const char *ev_name,
 				 struct print_arg *args)
 {
@@ -332,7 +332,7 @@ static void define_event_symbols(struct event_format *event,
 		define_event_symbols(event, ev_name, args->next);
 }
 
-static PyObject *get_field_numeric_entry(struct event_format *event,
+static PyObject *get_field_numeric_entry(struct tep_event_format *event,
 		struct format_field *field, void *data)
 {
 	bool is_array = field->flags & FIELD_IS_ARRAY;
@@ -790,7 +790,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 				      struct perf_evsel *evsel,
 				      struct addr_location *al)
 {
-	struct event_format *event = evsel->tp_format;
+	struct tep_event_format *event = evsel->tp_format;
 	PyObject *handler, *context, *t, *obj = NULL, *callchain;
 	PyObject *dict = NULL, *all_entries_dict = NULL;
 	static char handler_name[256];
@@ -1590,7 +1590,7 @@ static int python_stop_script(void)
 
 static int python_generate_script(struct tep_handle *pevent, const char *outfile)
 {
-	struct event_format *event = NULL;
+	struct tep_event_format *event = NULL;
 	struct format_field *f;
 	char fname[PATH_MAX];
 	int not_first, count;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index e76214f8d596..643cf28e1345 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -33,7 +33,7 @@ static int get_common_field(struct scripting_context *context,
 			    int *offset, int *size, const char *type)
 {
 	struct tep_handle *pevent = context->pevent;
-	struct event_format *event;
+	struct tep_event_format *event;
 	struct format_field *field;
 
 	if (!*size) {
@@ -94,7 +94,7 @@ int common_pc(struct scripting_context *context)
 }
 
 unsigned long long
-raw_field_value(struct event_format *event, const char *name, void *data)
+raw_field_value(struct tep_event_format *event, const char *name, void *data)
 {
 	struct format_field *field;
 	unsigned long long val;
@@ -108,12 +108,12 @@ raw_field_value(struct event_format *event, const char *name, void *data)
 	return val;
 }
 
-unsigned long long read_size(struct event_format *event, void *ptr, int size)
+unsigned long long read_size(struct tep_event_format *event, void *ptr, int size)
 {
 	return tep_read_number(event->pevent, ptr, size);
 }
 
-void event_format__fprintf(struct event_format *event,
+void event_format__fprintf(struct tep_event_format *event,
 			   int cpu, void *data, int size, FILE *fp)
 {
 	struct tep_record record;
@@ -130,7 +130,7 @@ void event_format__fprintf(struct event_format *event,
 	trace_seq_destroy(&s);
 }
 
-void event_format__print(struct event_format *event,
+void event_format__print(struct tep_event_format *event,
 			 int cpu, void *data, int size)
 {
 	return event_format__fprintf(event, cpu, data, size, stdout);
@@ -188,8 +188,8 @@ int parse_event_file(struct tep_handle *pevent,
 	return tep_parse_event(pevent, buf, size, sys);
 }
 
-struct event_format *trace_find_next_event(struct tep_handle *pevent,
-					   struct event_format *event)
+struct tep_event_format *trace_find_next_event(struct tep_handle *pevent,
+					       struct tep_event_format *event)
 {
 	static int idx;
 
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 58bb72f266f3..95664b2f771e 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -72,12 +72,12 @@ void trace_event__cleanup(struct trace_event *t)
 /*
  * Returns pointer with encoded error via <linux/err.h> interface.
  */
-static struct event_format*
+static struct tep_event_format*
 tp_format(const char *sys, const char *name)
 {
 	char *tp_dir = get_events_file(sys);
 	struct tep_handle *pevent = tevent.pevent;
-	struct event_format *event = NULL;
+	struct tep_event_format *event = NULL;
 	char path[PATH_MAX];
 	size_t size;
 	char *data;
@@ -102,7 +102,7 @@ tp_format(const char *sys, const char *name)
 /*
  * Returns pointer with encoded error via <linux/err.h> interface.
  */
-struct event_format*
+struct tep_event_format*
 trace_event__tp_format(const char *sys, const char *name)
 {
 	if (!tevent_initialized && trace_event__init2())
@@ -111,7 +111,7 @@ trace_event__tp_format(const char *sys, const char *name)
 	return tp_format(sys, name);
 }
 
-struct event_format *trace_event__tp_format_id(int id)
+struct tep_event_format *trace_event__tp_format_id(int id)
 {
 	if (!tevent_initialized && trace_event__init2())
 		return ERR_PTR(-ENOMEM);
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index c69d77d7cf55..2da6eff0caaf 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -22,17 +22,17 @@ int trace_event__init(struct trace_event *t);
 void trace_event__cleanup(struct trace_event *t);
 int trace_event__register_resolver(struct machine *machine,
 				   tep_func_resolver_t *func);
-struct event_format*
+struct tep_event_format*
 trace_event__tp_format(const char *sys, const char *name);
 
-struct event_format *trace_event__tp_format_id(int id);
+struct tep_event_format *trace_event__tp_format_id(int id);
 
 int bigendian(void);
 
-void event_format__fprintf(struct event_format *event,
+void event_format__fprintf(struct tep_event_format *event,
 			   int cpu, void *data, int size, FILE *fp);
 
-void event_format__print(struct event_format *event,
+void event_format__print(struct tep_event_format *event,
 			 int cpu, void *data, int size);
 
 int parse_ftrace_file(struct tep_handle *pevent, char *buf, unsigned long size);
@@ -40,7 +40,7 @@ int parse_event_file(struct tep_handle *pevent,
 		     char *buf, unsigned long size, char *sys);
 
 unsigned long long
-raw_field_value(struct event_format *event, const char *name, void *data);
+raw_field_value(struct tep_event_format *event, const char *name, void *data);
 
 void parse_proc_kallsyms(struct tep_handle *pevent, char *file, unsigned int size);
 void parse_ftrace_printk(struct tep_handle *pevent, char *file, unsigned int size);
@@ -48,9 +48,9 @@ void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int siz
 
 ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
 
-struct event_format *trace_find_next_event(struct tep_handle *pevent,
-					   struct event_format *event);
-unsigned long long read_size(struct event_format *event, void *ptr, int size);
+struct tep_event_format *trace_find_next_event(struct tep_handle *pevent,
+					       struct tep_event_format *event);
+unsigned long long read_size(struct tep_event_format *event, void *ptr, int size);
 unsigned long long eval_flag(const char *flag);
 
 int read_tracing_data(int fd, struct list_head *pattrs);
-- 
cgit v1.2.3


From 2c92f9828b3ca4e82e7ceffeea76c6fba4044acc Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Wed, 19 Sep 2018 14:56:45 -0400
Subject: tools lib traceevent, perf tools: Rename struct format{_field} to
 struct tep_format{_field}

In order to make libtraceevent into a proper library, variables, data
structures and functions require a unique prefix to prevent name space
conflicts. That prefix will be "tep_". This renames struct format to
struct tep_format and struct format_field to struct tep_format_field

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lkml.kernel.org/r/20180919185722.661319373@goodmis.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.c                 | 82 +++++++++++-----------
 tools/lib/traceevent/event-parse.h                 | 42 +++++------
 tools/lib/traceevent/parse-filter.c                |  8 +--
 tools/lib/traceevent/plugin_kmem.c                 |  2 +-
 tools/lib/traceevent/plugin_mac80211.c             |  2 +-
 tools/lib/traceevent/plugin_sched_switch.c         |  6 +-
 tools/perf/builtin-trace.c                         | 14 ++--
 tools/perf/tests/evsel-tp-sched.c                  |  2 +-
 tools/perf/util/data-convert-bt.c                  | 22 +++---
 tools/perf/util/evsel.c                            |  8 +--
 tools/perf/util/evsel.h                            |  6 +-
 tools/perf/util/evsel_fprintf.c                    |  2 +-
 tools/perf/util/python.c                           |  4 +-
 .../perf/util/scripting-engines/trace-event-perl.c |  4 +-
 .../util/scripting-engines/trace-event-python.c    |  6 +-
 tools/perf/util/sort.c                             | 18 ++---
 tools/perf/util/trace-event-parse.c                |  4 +-
 17 files changed, 116 insertions(+), 116 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index bb2ebb322124..32547abb6500 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1299,7 +1299,7 @@ static int event_read_id(void)
 	return -1;
 }
 
-static int field_is_string(struct format_field *field)
+static int field_is_string(struct tep_format_field *field)
 {
 	if ((field->flags & FIELD_IS_ARRAY) &&
 	    (strstr(field->type, "char") || strstr(field->type, "u8") ||
@@ -1309,7 +1309,7 @@ static int field_is_string(struct format_field *field)
 	return 0;
 }
 
-static int field_is_dynamic(struct format_field *field)
+static int field_is_dynamic(struct tep_format_field *field)
 {
 	if (strncmp(field->type, "__data_loc", 10) == 0)
 		return 1;
@@ -1317,7 +1317,7 @@ static int field_is_dynamic(struct format_field *field)
 	return 0;
 }
 
-static int field_is_long(struct format_field *field)
+static int field_is_long(struct tep_format_field *field)
 {
 	/* includes long long */
 	if (strstr(field->type, "long"))
@@ -1354,9 +1354,9 @@ static unsigned int type_size(const char *name)
 	return 0;
 }
 
-static int event_read_fields(struct tep_event_format *event, struct format_field **fields)
+static int event_read_fields(struct tep_event_format *event, struct tep_format_field **fields)
 {
-	struct format_field *field = NULL;
+	struct tep_format_field *field = NULL;
 	enum event_type type;
 	char *token;
 	char *last_token;
@@ -2683,7 +2683,7 @@ out:
 static enum event_type
 process_dynamic_array(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	enum event_type type;
 	char *token;
 
@@ -2748,7 +2748,7 @@ static enum event_type
 process_dynamic_array_len(struct tep_event_format *event, struct print_arg *arg,
 			  char **tok)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	enum event_type type;
 	char *token;
 
@@ -3259,10 +3259,10 @@ static int event_read_print(struct tep_event_format *event)
  * Returns a common field from the event by the given @name.
  * This only searchs the common fields and not all field.
  */
-struct format_field *
+struct tep_format_field *
 tep_find_common_field(struct tep_event_format *event, const char *name)
 {
-	struct format_field *format;
+	struct tep_format_field *format;
 
 	for (format = event->format.common_fields;
 	     format; format = format->next) {
@@ -3281,10 +3281,10 @@ tep_find_common_field(struct tep_event_format *event, const char *name)
  * Returns a non-common field by the given @name.
  * This does not search common fields.
  */
-struct format_field *
+struct tep_format_field *
 tep_find_field(struct tep_event_format *event, const char *name)
 {
-	struct format_field *format;
+	struct tep_format_field *format;
 
 	for (format = event->format.fields;
 	     format; format = format->next) {
@@ -3304,10 +3304,10 @@ tep_find_field(struct tep_event_format *event, const char *name)
  * This searchs the common field names first, then
  * the non-common ones if a common one was not found.
  */
-struct format_field *
+struct tep_format_field *
 tep_find_any_field(struct tep_event_format *event, const char *name)
 {
-	struct format_field *format;
+	struct tep_format_field *format;
 
 	format = tep_find_common_field(event, name);
 	if (format)
@@ -3353,7 +3353,7 @@ unsigned long long tep_read_number(struct tep_handle *pevent,
  *
  * Returns 0 on success, -1 otherwise.
  */
-int tep_read_number_field(struct format_field *field, const void *data,
+int tep_read_number_field(struct tep_format_field *field, const void *data,
 			  unsigned long long *value)
 {
 	if (!field)
@@ -3375,7 +3375,7 @@ static int get_common_info(struct tep_handle *pevent,
 			   const char *type, int *offset, int *size)
 {
 	struct tep_event_format *event;
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	/*
 	 * All events should have the same common elements.
@@ -3867,7 +3867,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 {
 	struct tep_handle *pevent = event->pevent;
 	struct print_flag_sym *flag;
-	struct format_field *field;
+	struct tep_format_field *field;
 	struct printk_map *printk;
 	long long val, fval;
 	unsigned long long addr;
@@ -4008,7 +4008,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 
 		if (arg->int_array.field->type == PRINT_DYNAMIC_ARRAY) {
 			unsigned long offset;
-			struct format_field *field =
+			struct tep_format_field *field =
 				arg->int_array.field->dynarray.field;
 			offset = tep_read_number(pevent,
 						 data + field->offset,
@@ -4056,7 +4056,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		int str_offset;
 
 		if (arg->string.offset == -1) {
-			struct format_field *f;
+			struct tep_format_field *f;
 
 			f = tep_find_any_field(event, arg->string.string);
 			arg->string.offset = f->offset;
@@ -4074,7 +4074,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		int bitmask_size;
 
 		if (arg->bitmask.offset == -1) {
-			struct format_field *f;
+			struct tep_format_field *f;
 
 			f = tep_find_any_field(event, arg->bitmask.bitmask);
 			arg->bitmask.offset = f->offset;
@@ -4215,7 +4215,7 @@ static void free_args(struct print_arg *args)
 static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struct tep_event_format *event)
 {
 	struct tep_handle *pevent = event->pevent;
-	struct format_field *field, *ip_field;
+	struct tep_format_field *field, *ip_field;
 	struct print_arg *args, *arg, **next;
 	unsigned long long ip, val;
 	char *ptr;
@@ -4393,7 +4393,7 @@ get_bprint_format(void *data, int size __maybe_unused,
 {
 	struct tep_handle *pevent = event->pevent;
 	unsigned long long addr;
-	struct format_field *field;
+	struct tep_format_field *field;
 	struct printk_map *printk;
 	char *format;
 
@@ -4788,7 +4788,7 @@ static int is_printable_array(char *p, unsigned int len)
 }
 
 void tep_print_field(struct trace_seq *s, void *data,
-		     struct format_field *field)
+		     struct tep_format_field *field)
 {
 	unsigned long long val;
 	unsigned int offset, len, i;
@@ -4855,7 +4855,7 @@ void tep_print_field(struct trace_seq *s, void *data,
 void tep_print_fields(struct trace_seq *s, void *data,
 		      int size __maybe_unused, struct tep_event_format *event)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	field = event->format.fields;
 	while (field) {
@@ -5664,12 +5664,12 @@ struct tep_event_format **tep_list_events(struct tep_handle *pevent, enum event_
 	return events;
 }
 
-static struct format_field **
+static struct tep_format_field **
 get_event_fields(const char *type, const char *name,
-		 int count, struct format_field *list)
+		 int count, struct tep_format_field *list)
 {
-	struct format_field **fields;
-	struct format_field *field;
+	struct tep_format_field **fields;
+	struct tep_format_field *field;
 	int i = 0;
 
 	fields = malloc(sizeof(*fields) * (count + 1));
@@ -5702,7 +5702,7 @@ get_event_fields(const char *type, const char *name,
  * Returns an allocated array of fields. The last item in the array is NULL.
  * The array must be freed with free().
  */
-struct format_field **tep_event_common_fields(struct tep_event_format *event)
+struct tep_format_field **tep_event_common_fields(struct tep_event_format *event)
 {
 	return get_event_fields("common", event->name,
 				event->format.nr_common,
@@ -5716,7 +5716,7 @@ struct format_field **tep_event_common_fields(struct tep_event_format *event)
  * Returns an allocated array of fields. The last item in the array is NULL.
  * The array must be freed with free().
  */
-struct format_field **tep_event_fields(struct tep_event_format *event)
+struct tep_format_field **tep_event_fields(struct tep_event_format *event)
 {
 	return get_event_fields("event", event->name,
 				event->format.nr_fields,
@@ -6090,7 +6090,7 @@ enum tep_errno __tep_parse_format(struct tep_event_format **eventp,
 	}
 
 	if (!ret && (event->flags & EVENT_FL_ISFTRACE)) {
-		struct format_field *field;
+		struct tep_format_field *field;
 		struct print_arg *arg, **list;
 
 		/* old ftrace had no args */
@@ -6230,7 +6230,7 @@ int tep_strerror(struct tep_handle *pevent __maybe_unused,
 	return 0;
 }
 
-int get_field_val(struct trace_seq *s, struct format_field *field,
+int get_field_val(struct trace_seq *s, struct tep_format_field *field,
 		  const char *name, struct tep_record *record,
 		  unsigned long long *val, int err)
 {
@@ -6267,7 +6267,7 @@ void *tep_get_field_raw(struct trace_seq *s, struct tep_event_format *event,
 			const char *name, struct tep_record *record,
 			int *len, int err)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	void *data = record->data;
 	unsigned offset;
 	int dummy;
@@ -6314,7 +6314,7 @@ int tep_get_field_val(struct trace_seq *s, struct tep_event_format *event,
 		      const char *name, struct tep_record *record,
 		      unsigned long long *val, int err)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	if (!event)
 		return -1;
@@ -6339,7 +6339,7 @@ int tep_get_common_field_val(struct trace_seq *s, struct tep_event_format *event
 			     const char *name, struct tep_record *record,
 			     unsigned long long *val, int err)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	if (!event)
 		return -1;
@@ -6364,7 +6364,7 @@ int tep_get_any_field_val(struct trace_seq *s, struct tep_event_format *event,
 			  const char *name, struct tep_record *record,
 			  unsigned long long *val, int err)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	if (!event)
 		return -1;
@@ -6389,7 +6389,7 @@ int tep_print_num_field(struct trace_seq *s, const char *fmt,
 			struct tep_event_format *event, const char *name,
 			struct tep_record *record, int err)
 {
-	struct format_field *field = tep_find_field(event, name);
+	struct tep_format_field *field = tep_find_field(event, name);
 	unsigned long long val;
 
 	if (!field)
@@ -6421,7 +6421,7 @@ int tep_print_func_field(struct trace_seq *s, const char *fmt,
 			 struct tep_event_format *event, const char *name,
 			 struct tep_record *record, int err)
 {
-	struct format_field *field = tep_find_field(event, name);
+	struct tep_format_field *field = tep_find_field(event, name);
 	struct tep_handle *pevent = event->pevent;
 	unsigned long long val;
 	struct func_map *func;
@@ -6758,7 +6758,7 @@ void tep_ref(struct tep_handle *pevent)
 	pevent->ref_count++;
 }
 
-void tep_free_format_field(struct format_field *field)
+void tep_free_format_field(struct tep_format_field *field)
 {
 	free(field->type);
 	if (field->alias != field->name)
@@ -6767,9 +6767,9 @@ void tep_free_format_field(struct format_field *field)
 	free(field);
 }
 
-static void free_format_fields(struct format_field *field)
+static void free_format_fields(struct tep_format_field *field)
 {
-	struct format_field *next;
+	struct tep_format_field *next;
 
 	while (field) {
 		next = field->next;
@@ -6778,7 +6778,7 @@ static void free_format_fields(struct format_field *field)
 	}
 }
 
-static void free_formats(struct format *format)
+static void free_formats(struct tep_format *format)
 {
 	free_format_fields(format->common_fields);
 	free_format_fields(format->fields);
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 82de69c2b054..aba859056867 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -141,8 +141,8 @@ enum format_flags {
 	FIELD_IS_SYMBOLIC	= 128,
 };
 
-struct format_field {
-	struct format_field	*next;
+struct tep_format_field {
+	struct tep_format_field	*next;
 	struct tep_event_format	*event;
 	char			*type;
 	char			*name;
@@ -154,11 +154,11 @@ struct format_field {
 	unsigned long		flags;
 };
 
-struct format {
+struct tep_format {
 	int			nr_common;
 	int			nr_fields;
-	struct format_field	*common_fields;
-	struct format_field	*fields;
+	struct tep_format_field	*common_fields;
+	struct tep_format_field	*fields;
 };
 
 struct print_arg_atom {
@@ -177,7 +177,7 @@ struct print_arg_bitmask {
 
 struct print_arg_field {
 	char			*name;
-	struct format_field	*field;
+	struct tep_format_field	*field;
 };
 
 struct print_flag_sym {
@@ -214,7 +214,7 @@ struct print_arg_int_array {
 };
 
 struct print_arg_dynarray {
-	struct format_field	*field;
+	struct tep_format_field	*field;
 	struct print_arg	*index;
 };
 
@@ -282,7 +282,7 @@ struct tep_event_format {
 	char			*name;
 	int			id;
 	int			flags;
-	struct format		format;
+	struct tep_format	format;
 	struct print_fmt	print_fmt;
 	char			*system;
 	tep_event_handler_func	handler;
@@ -477,9 +477,9 @@ struct tep_handle {
 
 	int flags;
 
-	struct format_field *bprint_ip_field;
-	struct format_field *bprint_fmt_field;
-	struct format_field *bprint_buf_field;
+	struct tep_format_field *bprint_ip_field;
+	struct tep_format_field *bprint_fmt_field;
+	struct tep_format_field *bprint_buf_field;
 
 	struct event_handler *handlers;
 	struct tep_function_handler *func_handlers;
@@ -607,7 +607,7 @@ enum tep_errno tep_parse_format(struct tep_handle *pevent,
 				const char *buf,
 				unsigned long size, const char *sys);
 void tep_free_format(struct tep_event_format *event);
-void tep_free_format_field(struct format_field *field);
+void tep_free_format_field(struct tep_format_field *field);
 
 void *tep_get_field_raw(struct trace_seq *s, struct tep_event_format *event,
 			const char *name, struct tep_record *record,
@@ -644,15 +644,15 @@ int tep_register_print_function(struct tep_handle *pevent,
 int tep_unregister_print_function(struct tep_handle *pevent,
 				  tep_func_handler func, char *name);
 
-struct format_field *tep_find_common_field(struct tep_event_format *event, const char *name);
-struct format_field *tep_find_field(struct tep_event_format *event, const char *name);
-struct format_field *tep_find_any_field(struct tep_event_format *event, const char *name);
+struct tep_format_field *tep_find_common_field(struct tep_event_format *event, const char *name);
+struct tep_format_field *tep_find_field(struct tep_event_format *event, const char *name);
+struct tep_format_field *tep_find_any_field(struct tep_event_format *event, const char *name);
 
 const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr);
 unsigned long long
 tep_find_function_address(struct tep_handle *pevent, unsigned long long addr);
 unsigned long long tep_read_number(struct tep_handle *pevent, const void *ptr, int size);
-int tep_read_number_field(struct format_field *field, const void *data,
+int tep_read_number_field(struct tep_format_field *field, const void *data,
 			  unsigned long long *value);
 
 struct tep_event_format *tep_find_event(struct tep_handle *pevent, int id);
@@ -677,7 +677,7 @@ struct cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *co
 int tep_cmdline_pid(struct tep_handle *pevent, struct cmdline *cmdline);
 
 void tep_print_field(struct trace_seq *s, void *data,
-		     struct format_field *field);
+		     struct tep_format_field *field);
 void tep_print_fields(struct trace_seq *s, void *data,
 		      int size __maybe_unused, struct tep_event_format *event);
 void tep_event_info(struct trace_seq *s, struct tep_event_format *event,
@@ -686,8 +686,8 @@ int tep_strerror(struct tep_handle *pevent, enum tep_errno errnum,
 		    char *buf, size_t buflen);
 
 struct tep_event_format **tep_list_events(struct tep_handle *pevent, enum event_sort_type);
-struct format_field **tep_event_common_fields(struct tep_event_format *event);
-struct format_field **tep_event_fields(struct tep_event_format *event);
+struct tep_format_field **tep_event_common_fields(struct tep_event_format *event);
+struct tep_format_field **tep_event_fields(struct tep_event_format *event);
 
 static inline int tep_get_cpus(struct tep_handle *pevent)
 {
@@ -832,7 +832,7 @@ struct filter_arg_boolean {
 };
 
 struct filter_arg_field {
-	struct format_field	*field;
+	struct tep_format_field	*field;
 };
 
 struct filter_arg_value {
@@ -863,7 +863,7 @@ struct filter_arg_num {
 
 struct filter_arg_str {
 	enum filter_cmp_type	type;
-	struct format_field	*field;
+	struct tep_format_field	*field;
 	char			*val;
 	char			*buffer;
 	regex_t			reg;
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 5572756307ab..a0353f2c051a 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -16,11 +16,11 @@
 #define COMM "COMM"
 #define CPU "CPU"
 
-static struct format_field comm = {
+static struct tep_format_field comm = {
 	.name = "COMM",
 };
 
-static struct format_field cpu = {
+static struct tep_format_field cpu = {
 	.name = "CPU",
 };
 
@@ -336,7 +336,7 @@ static enum tep_errno
 create_arg_item(struct tep_event_format *event, const char *token,
 		enum event_type type, struct filter_arg **parg, char *error_str)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	struct filter_arg *arg;
 
 	arg = allocate_arg();
@@ -1698,7 +1698,7 @@ get_comm(struct tep_event_format *event, struct tep_record *record)
 
 static unsigned long long
 get_value(struct tep_event_format *event,
-	  struct format_field *field, struct tep_record *record)
+	  struct tep_format_field *field, struct tep_record *record)
 {
 	unsigned long long val;
 
diff --git a/tools/lib/traceevent/plugin_kmem.c b/tools/lib/traceevent/plugin_kmem.c
index 5632aff43aba..1beb4eaddfdf 100644
--- a/tools/lib/traceevent/plugin_kmem.c
+++ b/tools/lib/traceevent/plugin_kmem.c
@@ -27,7 +27,7 @@
 static int call_site_handler(struct trace_seq *s, struct tep_record *record,
 			     struct tep_event_format *event, void *context)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned long long val, addr;
 	void *data = record->data;
 	const char *func;
diff --git a/tools/lib/traceevent/plugin_mac80211.c b/tools/lib/traceevent/plugin_mac80211.c
index c16469614690..da3855e7b86f 100644
--- a/tools/lib/traceevent/plugin_mac80211.c
+++ b/tools/lib/traceevent/plugin_mac80211.c
@@ -29,7 +29,7 @@
 static void print_string(struct trace_seq *s, struct tep_event_format *event,
 			 const char *name, const void *data)
 {
-	struct format_field *f = tep_find_field(event, name);
+	struct tep_format_field *f = tep_find_field(event, name);
 	int offset;
 	int length;
 
diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c
index a7eeb42894ae..77882272672f 100644
--- a/tools/lib/traceevent/plugin_sched_switch.c
+++ b/tools/lib/traceevent/plugin_sched_switch.c
@@ -45,7 +45,7 @@ static void write_state(struct trace_seq *s, int val)
 		trace_seq_putc(s, 'R');
 }
 
-static void write_and_save_comm(struct format_field *field,
+static void write_and_save_comm(struct tep_format_field *field,
 				struct tep_record *record,
 				struct trace_seq *s, int pid)
 {
@@ -69,7 +69,7 @@ static int sched_wakeup_handler(struct trace_seq *s,
 				struct tep_record *record,
 				struct tep_event_format *event, void *context)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned long long val;
 
 	if (tep_get_field_val(s, event, "pid", record, &val, 1))
@@ -98,7 +98,7 @@ static int sched_switch_handler(struct trace_seq *s,
 				struct tep_record *record,
 				struct tep_event_format *event, void *context)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned long long val;
 
 	if (tep_get_field_val(s, event, "prev_pid", record, &val, 1))
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 9f8c365dacb1..95f3c255d977 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -181,7 +181,7 @@ static int __tp_field__init_uint(struct tp_field *field, int size, int offset, b
 	return 0;
 }
 
-static int tp_field__init_uint(struct tp_field *field, struct format_field *format_field, bool needs_swap)
+static int tp_field__init_uint(struct tp_field *field, struct tep_format_field *format_field, bool needs_swap)
 {
 	return __tp_field__init_uint(field, format_field->size, format_field->offset, needs_swap);
 }
@@ -198,7 +198,7 @@ static int __tp_field__init_ptr(struct tp_field *field, int offset)
 	return 0;
 }
 
-static int tp_field__init_ptr(struct tp_field *field, struct format_field *format_field)
+static int tp_field__init_ptr(struct tp_field *field, struct tep_format_field *format_field)
 {
 	return __tp_field__init_ptr(field, format_field->offset);
 }
@@ -214,7 +214,7 @@ static int perf_evsel__init_tp_uint_field(struct perf_evsel *evsel,
 					  struct tp_field *field,
 					  const char *name)
 {
-	struct format_field *format_field = perf_evsel__field(evsel, name);
+	struct tep_format_field *format_field = perf_evsel__field(evsel, name);
 
 	if (format_field == NULL)
 		return -1;
@@ -230,7 +230,7 @@ static int perf_evsel__init_tp_ptr_field(struct perf_evsel *evsel,
 					 struct tp_field *field,
 					 const char *name)
 {
-	struct format_field *format_field = perf_evsel__field(evsel, name);
+	struct tep_format_field *format_field = perf_evsel__field(evsel, name);
 
 	if (format_field == NULL)
 		return -1;
@@ -867,7 +867,7 @@ struct syscall {
 	int		    args_size;
 	bool		    is_exit;
 	bool		    is_open;
-	struct format_field *args;
+	struct tep_format_field *args;
 	const char	    *name;
 	struct syscall_fmt  *fmt;
 	struct syscall_arg_fmt *arg_fmt;
@@ -1279,7 +1279,7 @@ static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args)
 
 static int syscall__set_arg_fmts(struct syscall *sc)
 {
-	struct format_field *field, *last_field = NULL;
+	struct tep_format_field *field, *last_field = NULL;
 	int idx = 0, len;
 
 	for (field = sc->args; field; field = field->next, ++idx) {
@@ -1525,7 +1525,7 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
 	ttrace->ret_scnprintf = NULL;
 
 	if (sc->args != NULL) {
-		struct format_field *field;
+		struct tep_format_field *field;
 
 		for (field = sc->args; field;
 		     field = field->next, ++arg.idx, bit <<= 1) {
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 699561fa512c..da9d3c0f8ead 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -8,7 +8,7 @@
 static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
 				  int size, bool should_be_signed)
 {
-	struct format_field *field = perf_evsel__field(evsel, name);
+	struct tep_format_field *field = perf_evsel__field(evsel, name);
 	int is_signed;
 	int ret = 0;
 
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index f75d4aa612c5..1817bbcc4a62 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -182,7 +182,7 @@ err_put_field:
 }
 
 static struct bt_ctf_field_type*
-get_tracepoint_field_type(struct ctf_writer *cw, struct format_field *field)
+get_tracepoint_field_type(struct ctf_writer *cw, struct tep_format_field *field)
 {
 	unsigned long flags = field->flags;
 
@@ -287,7 +287,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 				      struct bt_ctf_event_class *event_class,
 				      struct bt_ctf_event *event,
 				      struct perf_sample *sample,
-				      struct format_field *fmtf)
+				      struct tep_format_field *fmtf)
 {
 	struct bt_ctf_field_type *type;
 	struct bt_ctf_field *array_field;
@@ -396,10 +396,10 @@ err_put_field:
 static int add_tracepoint_fields_values(struct ctf_writer *cw,
 					struct bt_ctf_event_class *event_class,
 					struct bt_ctf_event *event,
-					struct format_field *fields,
+					struct tep_format_field *fields,
 					struct perf_sample *sample)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	int ret;
 
 	for (field = fields; field; field = field->next) {
@@ -417,8 +417,8 @@ static int add_tracepoint_values(struct ctf_writer *cw,
 				 struct perf_evsel *evsel,
 				 struct perf_sample *sample)
 {
-	struct format_field *common_fields = evsel->tp_format->format.common_fields;
-	struct format_field *fields        = evsel->tp_format->format.fields;
+	struct tep_format_field *common_fields = evsel->tp_format->format.common_fields;
+	struct tep_format_field *fields        = evsel->tp_format->format.fields;
 	int ret;
 
 	ret = add_tracepoint_fields_values(cw, event_class, event,
@@ -970,7 +970,7 @@ out:
 
 static int event_class_add_field(struct bt_ctf_event_class *event_class,
 		struct bt_ctf_field_type *type,
-		struct format_field *field)
+		struct tep_format_field *field)
 {
 	struct bt_ctf_field_type *t = NULL;
 	char *name;
@@ -1009,10 +1009,10 @@ static int event_class_add_field(struct bt_ctf_event_class *event_class,
 }
 
 static int add_tracepoint_fields_types(struct ctf_writer *cw,
-				       struct format_field *fields,
+				       struct tep_format_field *fields,
 				       struct bt_ctf_event_class *event_class)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	int ret;
 
 	for (field = fields; field; field = field->next) {
@@ -1055,8 +1055,8 @@ static int add_tracepoint_types(struct ctf_writer *cw,
 				struct perf_evsel *evsel,
 				struct bt_ctf_event_class *class)
 {
-	struct format_field *common_fields = evsel->tp_format->format.common_fields;
-	struct format_field *fields        = evsel->tp_format->format.fields;
+	struct tep_format_field *common_fields = evsel->tp_format->format.common_fields;
+	struct tep_format_field *fields        = evsel->tp_format->format.fields;
 	int ret;
 
 	ret = add_tracepoint_fields_types(cw, common_fields, class);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 4ec909d57e9c..751c98a2e336 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2682,7 +2682,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 	return 0;
 }
 
-struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name)
+struct tep_format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name)
 {
 	return tep_find_field(evsel->tp_format, name);
 }
@@ -2690,7 +2690,7 @@ struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *nam
 void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
 			 const char *name)
 {
-	struct format_field *field = perf_evsel__field(evsel, name);
+	struct tep_format_field *field = perf_evsel__field(evsel, name);
 	int offset;
 
 	if (!field)
@@ -2706,7 +2706,7 @@ void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
 	return sample->raw_data + offset;
 }
 
-u64 format_field__intval(struct format_field *field, struct perf_sample *sample,
+u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample,
 			 bool needs_swap)
 {
 	u64 value;
@@ -2748,7 +2748,7 @@ u64 format_field__intval(struct format_field *field, struct perf_sample *sample,
 u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
 		       const char *name)
 {
-	struct format_field *field = perf_evsel__field(evsel, name);
+	struct tep_format_field *field = perf_evsel__field(evsel, name);
 
 	if (!field)
 		return 0;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index c0f275cf96ee..4107c39f4a54 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -296,11 +296,11 @@ static inline char *perf_evsel__strval(struct perf_evsel *evsel,
 	return perf_evsel__rawptr(evsel, sample, name);
 }
 
-struct format_field;
+struct tep_format_field;
 
-u64 format_field__intval(struct format_field *field, struct perf_sample *sample, bool needs_swap);
+u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample, bool needs_swap);
 
-struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name);
+struct tep_format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name);
 
 #define perf_evsel__match(evsel, t, c)		\
 	(evsel->attr.type == PERF_TYPE_##t &&	\
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 06dfb027879d..0d0a4c6f368b 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -73,7 +73,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 	}
 
 	if (details->trace_fields) {
-		struct format_field *field;
+		struct tep_format_field *field;
 
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
 			printed += comma_fprintf(fp, &first, " (not a tracepoint)");
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 6714d2c517db..ebf84fe8cd29 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -340,7 +340,7 @@ static bool is_tracepoint(struct pyrf_event *pevent)
 }
 
 static PyObject*
-tracepoint_field(struct pyrf_event *pe, struct format_field *field)
+tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field)
 {
 	struct tep_handle *pevent = field->event->pevent;
 	void *data = pe->sample.raw_data;
@@ -383,7 +383,7 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
 {
 	const char *str = _PyUnicode_AsString(PyObject_Str(attr_name));
 	struct perf_evsel *evsel = pevent->evsel;
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	if (!evsel->tp_format) {
 		struct tep_event_format *tp_format;
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 370cc60f0afa..1bb0b0c685b7 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -339,7 +339,7 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 {
 	struct thread *thread = al->thread;
 	struct tep_event_format *event = evsel->tp_format;
-	struct format_field *field;
+	struct tep_format_field *field;
 	static char handler[256];
 	unsigned long long val;
 	unsigned long s, ns;
@@ -538,7 +538,7 @@ static int perl_stop_script(void)
 static int perl_generate_script(struct tep_handle *pevent, const char *outfile)
 {
 	struct tep_event_format *event = NULL;
-	struct format_field *f;
+	struct tep_format_field *f;
 	char fname[PATH_MAX];
 	int not_first, count;
 	FILE *ofp;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 9a8a7b7ff64a..dc26e58a791e 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -333,7 +333,7 @@ static void define_event_symbols(struct tep_event_format *event,
 }
 
 static PyObject *get_field_numeric_entry(struct tep_event_format *event,
-		struct format_field *field, void *data)
+		struct tep_format_field *field, void *data)
 {
 	bool is_array = field->flags & FIELD_IS_ARRAY;
 	PyObject *obj = NULL, *list = NULL;
@@ -794,7 +794,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	PyObject *handler, *context, *t, *obj = NULL, *callchain;
 	PyObject *dict = NULL, *all_entries_dict = NULL;
 	static char handler_name[256];
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned long s, ns;
 	unsigned n = 0;
 	int pid;
@@ -1591,7 +1591,7 @@ static int python_stop_script(void)
 static int python_generate_script(struct tep_handle *pevent, const char *outfile)
 {
 	struct tep_event_format *event = NULL;
-	struct format_field *f;
+	struct tep_format_field *f;
 	char fname[PATH_MAX];
 	int not_first, count;
 	FILE *ofp;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index b284276ec963..5e3179d995f9 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1884,7 +1884,7 @@ static int __sort_dimension__add_hpp_output(struct sort_dimension *sd,
 struct hpp_dynamic_entry {
 	struct perf_hpp_fmt hpp;
 	struct perf_evsel *evsel;
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned dynamic_len;
 	bool raw_trace;
 };
@@ -1915,7 +1915,7 @@ static void update_dynamic_len(struct hpp_dynamic_entry *hde,
 			       struct hist_entry *he)
 {
 	char *str, *pos;
-	struct format_field *field = hde->field;
+	struct tep_format_field *field = hde->field;
 	size_t namelen;
 	bool last = false;
 
@@ -2000,7 +2000,7 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	struct hpp_dynamic_entry *hde;
 	size_t len = fmt->user_len;
 	char *str, *pos;
-	struct format_field *field;
+	struct tep_format_field *field;
 	size_t namelen;
 	bool last = false;
 	int ret;
@@ -2060,7 +2060,7 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 			       struct hist_entry *a, struct hist_entry *b)
 {
 	struct hpp_dynamic_entry *hde;
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned offset, size;
 
 	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
@@ -2117,7 +2117,7 @@ static void hde_free(struct perf_hpp_fmt *fmt)
 }
 
 static struct hpp_dynamic_entry *
-__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field,
+__alloc_dynamic_entry(struct perf_evsel *evsel, struct tep_format_field *field,
 		      int level)
 {
 	struct hpp_dynamic_entry *hde;
@@ -2252,7 +2252,7 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam
 }
 
 static int __dynamic_dimension__add(struct perf_evsel *evsel,
-				    struct format_field *field,
+				    struct tep_format_field *field,
 				    bool raw_trace, int level)
 {
 	struct hpp_dynamic_entry *hde;
@@ -2270,7 +2270,7 @@ static int __dynamic_dimension__add(struct perf_evsel *evsel,
 static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace, int level)
 {
 	int ret;
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	field = evsel->tp_format->format.fields;
 	while (field) {
@@ -2305,7 +2305,7 @@ static int add_all_matching_fields(struct perf_evlist *evlist,
 {
 	int ret = -ESRCH;
 	struct perf_evsel *evsel;
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
@@ -2327,7 +2327,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok,
 {
 	char *str, *event_name, *field_name, *opt_name;
 	struct perf_evsel *evsel;
-	struct format_field *field;
+	struct tep_format_field *field;
 	bool raw_trace = symbol_conf.raw_trace;
 	int ret = 0;
 
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 643cf28e1345..a4d7de1c96d1 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -34,7 +34,7 @@ static int get_common_field(struct scripting_context *context,
 {
 	struct tep_handle *pevent = context->pevent;
 	struct tep_event_format *event;
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	if (!*size) {
 		if (!pevent->events)
@@ -96,7 +96,7 @@ int common_pc(struct scripting_context *context)
 unsigned long long
 raw_field_value(struct tep_event_format *event, const char *name, void *data)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned long long val;
 
 	field = tep_find_any_field(event, name);
-- 
cgit v1.2.3


From bb39ccb204cc2e8135660b9cb768ffcf242bf33e Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Wed, 19 Sep 2018 14:56:46 -0400
Subject: tools lib traceevent, perf tools: Rename enum format_flags to enum
 tep_format_flags

In order to make libtraceevent into a proper library, variables, data
structures and functions require a unique prefix to prevent name space
conflicts. That prefix will be "tep_". This renames enum format_flags
to enum tep_format_flags and adds prefix TEP_ to all of its members.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lkml.kernel.org/r/20180919185722.803127871@goodmis.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.c                 | 48 +++++++++++-----------
 tools/lib/traceevent/event-parse.h                 | 18 ++++----
 tools/lib/traceevent/parse-filter.c                |  8 ++--
 tools/perf/builtin-trace.c                         |  2 +-
 tools/perf/tests/evsel-tp-sched.c                  |  2 +-
 tools/perf/util/data-convert-bt.c                  | 34 +++++++--------
 tools/perf/util/evsel.c                            |  2 +-
 tools/perf/util/python.c                           | 12 +++---
 .../perf/util/scripting-engines/trace-event-perl.c | 18 ++++----
 .../util/scripting-engines/trace-event-python.c    | 26 ++++++------
 tools/perf/util/sort.c                             |  4 +-
 11 files changed, 87 insertions(+), 87 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 32547abb6500..508c89365c90 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1301,7 +1301,7 @@ static int event_read_id(void)
 
 static int field_is_string(struct tep_format_field *field)
 {
-	if ((field->flags & FIELD_IS_ARRAY) &&
+	if ((field->flags & TEP_FIELD_IS_ARRAY) &&
 	    (strstr(field->type, "char") || strstr(field->type, "u8") ||
 	     strstr(field->type, "s8")))
 		return 1;
@@ -1328,7 +1328,7 @@ static int field_is_long(struct tep_format_field *field)
 
 static unsigned int type_size(const char *name)
 {
-	/* This covers all FIELD_IS_STRING types. */
+	/* This covers all TEP_FIELD_IS_STRING types. */
 	static struct {
 		const char *type;
 		unsigned int size;
@@ -1416,7 +1416,7 @@ static int event_read_fields(struct tep_event_format *event, struct tep_format_f
 			     type == EVENT_OP && strcmp(token, ".") == 0)) {
 
 				if (strcmp(token, "*") == 0)
-					field->flags |= FIELD_IS_POINTER;
+					field->flags |= TEP_FIELD_IS_POINTER;
 
 				if (field->type) {
 					char *new_type;
@@ -1455,7 +1455,7 @@ static int event_read_fields(struct tep_event_format *event, struct tep_format_f
 			char *new_brackets;
 			int len;
 
-			field->flags |= FIELD_IS_ARRAY;
+			field->flags |= TEP_FIELD_IS_ARRAY;
 
 			type = read_token(&token);
 
@@ -1544,11 +1544,11 @@ static int event_read_fields(struct tep_event_format *event, struct tep_format_f
 		}
 
 		if (field_is_string(field))
-			field->flags |= FIELD_IS_STRING;
+			field->flags |= TEP_FIELD_IS_STRING;
 		if (field_is_dynamic(field))
-			field->flags |= FIELD_IS_DYNAMIC;
+			field->flags |= TEP_FIELD_IS_DYNAMIC;
 		if (field_is_long(field))
-			field->flags |= FIELD_IS_LONG;
+			field->flags |= TEP_FIELD_IS_LONG;
 
 		if (test_type_token(type, token,  EVENT_OP, ";"))
 			goto fail;
@@ -1597,7 +1597,7 @@ static int event_read_fields(struct tep_event_format *event, struct tep_format_f
 				goto fail;
 
 			if (strtoul(token, NULL, 0))
-				field->flags |= FIELD_IS_SIGNED;
+				field->flags |= TEP_FIELD_IS_SIGNED;
 
 			free_token(token);
 			if (read_expected(EVENT_OP, ";") < 0)
@@ -1609,14 +1609,14 @@ static int event_read_fields(struct tep_event_format *event, struct tep_format_f
 
 		free_token(token);
 
-		if (field->flags & FIELD_IS_ARRAY) {
+		if (field->flags & TEP_FIELD_IS_ARRAY) {
 			if (field->arraylen)
 				field->elementsize = field->size / field->arraylen;
-			else if (field->flags & FIELD_IS_DYNAMIC)
+			else if (field->flags & TEP_FIELD_IS_DYNAMIC)
 				field->elementsize = size_dynamic;
-			else if (field->flags & FIELD_IS_STRING)
+			else if (field->flags & TEP_FIELD_IS_STRING)
 				field->elementsize = 1;
-			else if (field->flags & FIELD_IS_LONG)
+			else if (field->flags & TEP_FIELD_IS_LONG)
 				field->elementsize = event->pevent ?
 						     event->pevent->long_size :
 						     sizeof(long);
@@ -2089,11 +2089,11 @@ process_entry(struct tep_event_format *event __maybe_unused, struct print_arg *a
 
 	if (is_flag_field) {
 		arg->field.field = tep_find_any_field(event, arg->field.name);
-		arg->field.field->flags |= FIELD_IS_FLAG;
+		arg->field.field->flags |= TEP_FIELD_IS_FLAG;
 		is_flag_field = 0;
 	} else if (is_symbolic_field) {
 		arg->field.field = tep_find_any_field(event, arg->field.name);
-		arg->field.field->flags |= FIELD_IS_SYMBOLIC;
+		arg->field.field->flags |= TEP_FIELD_IS_SYMBOLIC;
 		is_symbolic_field = 0;
 	}
 
@@ -3901,7 +3901,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		 * and the size is the same as long_size, assume that it
 		 * is a pointer.
 		 */
-		if (!(field->flags & FIELD_IS_ARRAY) &&
+		if (!(field->flags & TEP_FIELD_IS_ARRAY) &&
 		    field->size == pevent->long_size) {
 
 			/* Handle heterogeneous recording and processing
@@ -4794,16 +4794,16 @@ void tep_print_field(struct trace_seq *s, void *data,
 	unsigned int offset, len, i;
 	struct tep_handle *pevent = field->event->pevent;
 
-	if (field->flags & FIELD_IS_ARRAY) {
+	if (field->flags & TEP_FIELD_IS_ARRAY) {
 		offset = field->offset;
 		len = field->size;
-		if (field->flags & FIELD_IS_DYNAMIC) {
+		if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 			val = tep_read_number(pevent, data + offset, len);
 			offset = val;
 			len = offset >> 16;
 			offset &= 0xffff;
 		}
-		if (field->flags & FIELD_IS_STRING &&
+		if (field->flags & TEP_FIELD_IS_STRING &&
 		    is_printable_array(data + offset, len)) {
 			trace_seq_printf(s, "%s", (char *)data + offset);
 		} else {
@@ -4815,21 +4815,21 @@ void tep_print_field(struct trace_seq *s, void *data,
 						 *((unsigned char *)data + offset + i));
 			}
 			trace_seq_putc(s, ']');
-			field->flags &= ~FIELD_IS_STRING;
+			field->flags &= ~TEP_FIELD_IS_STRING;
 		}
 	} else {
 		val = tep_read_number(pevent, data + field->offset,
 				      field->size);
-		if (field->flags & FIELD_IS_POINTER) {
+		if (field->flags & TEP_FIELD_IS_POINTER) {
 			trace_seq_printf(s, "0x%llx", val);
-		} else if (field->flags & FIELD_IS_SIGNED) {
+		} else if (field->flags & TEP_FIELD_IS_SIGNED) {
 			switch (field->size) {
 			case 4:
 				/*
 				 * If field is long then print it in hex.
 				 * A long usually stores pointers.
 				 */
-				if (field->flags & FIELD_IS_LONG)
+				if (field->flags & TEP_FIELD_IS_LONG)
 					trace_seq_printf(s, "0x%x", (int)val);
 				else
 					trace_seq_printf(s, "%d", (int)val);
@@ -4844,7 +4844,7 @@ void tep_print_field(struct trace_seq *s, void *data,
 				trace_seq_printf(s, "%lld", val);
 			}
 		} else {
-			if (field->flags & FIELD_IS_LONG)
+			if (field->flags & TEP_FIELD_IS_LONG)
 				trace_seq_printf(s, "0x%llx", val);
 			else
 				trace_seq_printf(s, "%llu", val);
@@ -6288,7 +6288,7 @@ void *tep_get_field_raw(struct trace_seq *s, struct tep_event_format *event,
 		len = &dummy;
 
 	offset = field->offset;
-	if (field->flags & FIELD_IS_DYNAMIC) {
+	if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 		offset = tep_read_number(event->pevent,
 					    data + offset, field->size);
 		*len = offset >> 16;
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index aba859056867..f1e1baee8cbd 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -130,15 +130,15 @@ struct tep_plugin_option {
 #define TEP_PLUGIN_OPTIONS_NAME MAKE_STR(TEP_PLUGIN_OPTIONS)
 #define TEP_PLUGIN_ALIAS_NAME MAKE_STR(TEP_PLUGIN_ALIAS)
 
-enum format_flags {
-	FIELD_IS_ARRAY		= 1,
-	FIELD_IS_POINTER	= 2,
-	FIELD_IS_SIGNED		= 4,
-	FIELD_IS_STRING		= 8,
-	FIELD_IS_DYNAMIC	= 16,
-	FIELD_IS_LONG		= 32,
-	FIELD_IS_FLAG		= 64,
-	FIELD_IS_SYMBOLIC	= 128,
+enum tep_format_flags {
+	TEP_FIELD_IS_ARRAY	= 1,
+	TEP_FIELD_IS_POINTER	= 2,
+	TEP_FIELD_IS_SIGNED	= 4,
+	TEP_FIELD_IS_STRING	= 8,
+	TEP_FIELD_IS_DYNAMIC	= 16,
+	TEP_FIELD_IS_LONG	= 32,
+	TEP_FIELD_IS_FLAG	= 64,
+	TEP_FIELD_IS_SYMBOLIC	= 128,
 };
 
 struct tep_format_field {
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index a0353f2c051a..dcd97acbbc49 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -1716,7 +1716,7 @@ get_value(struct tep_event_format *event,
 
 	tep_read_number_field(field, record->data, &val);
 
-	if (!(field->flags & FIELD_IS_SIGNED))
+	if (!(field->flags & TEP_FIELD_IS_SIGNED))
 		return val;
 
 	switch (field->size) {
@@ -1867,11 +1867,11 @@ static const char *get_field_str(struct filter_arg *arg, struct tep_record *reco
 	char hex[64];
 
 	/* If the field is not a string convert it */
-	if (arg->str.field->flags & FIELD_IS_STRING) {
+	if (arg->str.field->flags & TEP_FIELD_IS_STRING) {
 		val = record->data + arg->str.field->offset;
 		size = arg->str.field->size;
 
-		if (arg->str.field->flags & FIELD_IS_DYNAMIC) {
+		if (arg->str.field->flags & TEP_FIELD_IS_DYNAMIC) {
 			addr = *(unsigned int *)val;
 			val = record->data + (addr & 0xffff);
 			size = addr >> 16;
@@ -1893,7 +1893,7 @@ static const char *get_field_str(struct filter_arg *arg, struct tep_record *reco
 		pevent = event->pevent;
 		addr = get_value(event, arg->str.field, record);
 
-		if (arg->str.field->flags & (FIELD_IS_POINTER | FIELD_IS_LONG))
+		if (arg->str.field->flags & (TEP_FIELD_IS_POINTER | TEP_FIELD_IS_LONG))
 			/* convert to a kernel symbol */
 			val = tep_find_function(pevent, addr);
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 95f3c255d977..90289f31dd87 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1293,7 +1293,7 @@ static int syscall__set_arg_fmts(struct syscall *sc)
 			  strcmp(field->name, "path") == 0 ||
 			  strcmp(field->name, "pathname") == 0))
 			sc->arg_fmt[idx].scnprintf = SCA_FILENAME;
-		else if (field->flags & FIELD_IS_POINTER)
+		else if (field->flags & TEP_FIELD_IS_POINTER)
 			sc->arg_fmt[idx].scnprintf = syscall_arg__scnprintf_hex;
 		else if (strcmp(field->type, "pid_t") == 0)
 			sc->arg_fmt[idx].scnprintf = SCA_PID;
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index da9d3c0f8ead..5f8501c68da4 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -17,7 +17,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
 		return -1;
 	}
 
-	is_signed = !!(field->flags | FIELD_IS_SIGNED);
+	is_signed = !!(field->flags | TEP_FIELD_IS_SIGNED);
 	if (should_be_signed && !is_signed) {
 		pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n",
 			 evsel->name, name, is_signed, should_be_signed);
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 1817bbcc4a62..2a36fab76994 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -186,16 +186,16 @@ get_tracepoint_field_type(struct ctf_writer *cw, struct tep_format_field *field)
 {
 	unsigned long flags = field->flags;
 
-	if (flags & FIELD_IS_STRING)
+	if (flags & TEP_FIELD_IS_STRING)
 		return cw->data.string;
 
-	if (!(flags & FIELD_IS_SIGNED)) {
+	if (!(flags & TEP_FIELD_IS_SIGNED)) {
 		/* unsigned long are mostly pointers */
-		if (flags & FIELD_IS_LONG || flags & FIELD_IS_POINTER)
+		if (flags & TEP_FIELD_IS_LONG || flags & TEP_FIELD_IS_POINTER)
 			return cw->data.u64_hex;
 	}
 
-	if (flags & FIELD_IS_SIGNED) {
+	if (flags & TEP_FIELD_IS_SIGNED) {
 		if (field->size == 8)
 			return cw->data.s64;
 		else
@@ -304,10 +304,10 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	name = fmtf->alias;
 	offset = fmtf->offset;
 	len = fmtf->size;
-	if (flags & FIELD_IS_STRING)
-		flags &= ~FIELD_IS_ARRAY;
+	if (flags & TEP_FIELD_IS_STRING)
+		flags &= ~TEP_FIELD_IS_ARRAY;
 
-	if (flags & FIELD_IS_DYNAMIC) {
+	if (flags & TEP_FIELD_IS_DYNAMIC) {
 		unsigned long long tmp_val;
 
 		tmp_val = tep_read_number(fmtf->event->pevent,
@@ -317,7 +317,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 		offset &= 0xffff;
 	}
 
-	if (flags & FIELD_IS_ARRAY) {
+	if (flags & TEP_FIELD_IS_ARRAY) {
 
 		type = bt_ctf_event_class_get_field_by_name(
 				event_class, name);
@@ -338,7 +338,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	type = get_tracepoint_field_type(cw, fmtf);
 
 	for (i = 0; i < n_items; i++) {
-		if (flags & FIELD_IS_ARRAY)
+		if (flags & TEP_FIELD_IS_ARRAY)
 			field = bt_ctf_field_array_get_field(array_field, i);
 		else
 			field = bt_ctf_field_create(type);
@@ -348,7 +348,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 			return -1;
 		}
 
-		if (flags & FIELD_IS_STRING)
+		if (flags & TEP_FIELD_IS_STRING)
 			ret = string_set_value(field, data + offset + i * len);
 		else {
 			unsigned long long value_int;
@@ -357,7 +357,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 					fmtf->event->pevent,
 					data + offset + i * len, len);
 
-			if (!(flags & FIELD_IS_SIGNED))
+			if (!(flags & TEP_FIELD_IS_SIGNED))
 				ret = bt_ctf_field_unsigned_integer_set_value(
 						field, value_int);
 			else
@@ -369,7 +369,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 			pr_err("failed to set file value %s\n", name);
 			goto err_put_field;
 		}
-		if (!(flags & FIELD_IS_ARRAY)) {
+		if (!(flags & TEP_FIELD_IS_ARRAY)) {
 			ret = bt_ctf_event_set_payload(event, name, field);
 			if (ret) {
 				pr_err("failed to set payload %s\n", name);
@@ -378,7 +378,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 		}
 		bt_ctf_field_put(field);
 	}
-	if (flags & FIELD_IS_ARRAY) {
+	if (flags & TEP_FIELD_IS_ARRAY) {
 		ret = bt_ctf_event_set_payload(event, name, array_field);
 		if (ret) {
 			pr_err("Failed add payload array %s\n", name);
@@ -1030,15 +1030,15 @@ static int add_tracepoint_fields_types(struct ctf_writer *cw,
 		 * type and don't care that it is an array. What we don't
 		 * support is an array of strings.
 		 */
-		if (flags & FIELD_IS_STRING)
-			flags &= ~FIELD_IS_ARRAY;
+		if (flags & TEP_FIELD_IS_STRING)
+			flags &= ~TEP_FIELD_IS_ARRAY;
 
-		if (flags & FIELD_IS_ARRAY)
+		if (flags & TEP_FIELD_IS_ARRAY)
 			type = bt_ctf_field_type_array_create(type, field->arraylen);
 
 		ret = event_class_add_field(event_class, type, field);
 
-		if (flags & FIELD_IS_ARRAY)
+		if (flags & TEP_FIELD_IS_ARRAY)
 			bt_ctf_field_type_put(type);
 
 		if (ret) {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 751c98a2e336..cb7f01059940 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2698,7 +2698,7 @@ void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
 
 	offset = field->offset;
 
-	if (field->flags & FIELD_IS_DYNAMIC) {
+	if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 		offset = *(int *)(sample->raw_data + field->offset);
 		offset &= 0xffff;
 	}
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index ebf84fe8cd29..50150dfc0cdf 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -348,28 +348,28 @@ tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field)
 	unsigned long long val;
 	unsigned int offset, len;
 
-	if (field->flags & FIELD_IS_ARRAY) {
+	if (field->flags & TEP_FIELD_IS_ARRAY) {
 		offset = field->offset;
 		len    = field->size;
-		if (field->flags & FIELD_IS_DYNAMIC) {
+		if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 			val     = tep_read_number(pevent, data + offset, len);
 			offset  = val;
 			len     = offset >> 16;
 			offset &= 0xffff;
 		}
-		if (field->flags & FIELD_IS_STRING &&
+		if (field->flags & TEP_FIELD_IS_STRING &&
 		    is_printable_array(data + offset, len)) {
 			ret = _PyUnicode_FromString((char *)data + offset);
 		} else {
 			ret = PyByteArray_FromStringAndSize((const char *) data + offset, len);
-			field->flags &= ~FIELD_IS_STRING;
+			field->flags &= ~TEP_FIELD_IS_STRING;
 		}
 	} else {
 		val = tep_read_number(pevent, data + field->offset,
 				      field->size);
-		if (field->flags & FIELD_IS_POINTER)
+		if (field->flags & TEP_FIELD_IS_POINTER)
 			ret = PyLong_FromUnsignedLong((unsigned long) val);
-		else if (field->flags & FIELD_IS_SIGNED)
+		else if (field->flags & TEP_FIELD_IS_SIGNED)
 			ret = PyLong_FromLong((long) val);
 		else
 			ret = PyLong_FromUnsignedLong((unsigned long) val);
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 1bb0b0c685b7..5d6a55183ad6 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -388,9 +388,9 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 	/* common fields other than pid can be accessed via xsub fns */
 
 	for (field = event->format.fields; field; field = field->next) {
-		if (field->flags & FIELD_IS_STRING) {
+		if (field->flags & TEP_FIELD_IS_STRING) {
 			int offset;
-			if (field->flags & FIELD_IS_DYNAMIC) {
+			if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 				offset = *(int *)(data + field->offset);
 				offset &= 0xffff;
 			} else
@@ -399,7 +399,7 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 		} else { /* FIELD_IS_NUMERIC */
 			val = read_size(event, data + field->offset,
 					field->size);
-			if (field->flags & FIELD_IS_SIGNED) {
+			if (field->flags & TEP_FIELD_IS_SIGNED) {
 				XPUSHs(sv_2mortal(newSViv(val)));
 			} else {
 				XPUSHs(sv_2mortal(newSVuv(val)));
@@ -646,11 +646,11 @@ sub print_backtrace\n\
 			count++;
 
 			fprintf(ofp, "%s=", f->name);
-			if (f->flags & FIELD_IS_STRING ||
-			    f->flags & FIELD_IS_FLAG ||
-			    f->flags & FIELD_IS_SYMBOLIC)
+			if (f->flags & TEP_FIELD_IS_STRING ||
+			    f->flags & TEP_FIELD_IS_FLAG ||
+			    f->flags & TEP_FIELD_IS_SYMBOLIC)
 				fprintf(ofp, "%%s");
-			else if (f->flags & FIELD_IS_SIGNED)
+			else if (f->flags & TEP_FIELD_IS_SIGNED)
 				fprintf(ofp, "%%d");
 			else
 				fprintf(ofp, "%%u");
@@ -668,7 +668,7 @@ sub print_backtrace\n\
 			if (++count % 5 == 0)
 				fprintf(ofp, "\n\t       ");
 
-			if (f->flags & FIELD_IS_FLAG) {
+			if (f->flags & TEP_FIELD_IS_FLAG) {
 				if ((count - 1) % 5 != 0) {
 					fprintf(ofp, "\n\t       ");
 					count = 4;
@@ -678,7 +678,7 @@ sub print_backtrace\n\
 					event->name);
 				fprintf(ofp, "\"%s\", $%s)", f->name,
 					f->name);
-			} else if (f->flags & FIELD_IS_SYMBOLIC) {
+			} else if (f->flags & TEP_FIELD_IS_SYMBOLIC) {
 				if ((count - 1) % 5 != 0) {
 					fprintf(ofp, "\n\t       ");
 					count = 4;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index dc26e58a791e..ba191def1ea9 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -335,7 +335,7 @@ static void define_event_symbols(struct tep_event_format *event,
 static PyObject *get_field_numeric_entry(struct tep_event_format *event,
 		struct tep_format_field *field, void *data)
 {
-	bool is_array = field->flags & FIELD_IS_ARRAY;
+	bool is_array = field->flags & TEP_FIELD_IS_ARRAY;
 	PyObject *obj = NULL, *list = NULL;
 	unsigned long long val;
 	unsigned int item_size, n_items, i;
@@ -353,7 +353,7 @@ static PyObject *get_field_numeric_entry(struct tep_event_format *event,
 
 		val = read_size(event, data + field->offset + i * item_size,
 				item_size);
-		if (field->flags & FIELD_IS_SIGNED) {
+		if (field->flags & TEP_FIELD_IS_SIGNED) {
 			if ((long long)val >= LONG_MIN &&
 					(long long)val <= LONG_MAX)
 				obj = _PyLong_FromLong(val);
@@ -867,22 +867,22 @@ static void python_process_tracepoint(struct perf_sample *sample,
 		unsigned int offset, len;
 		unsigned long long val;
 
-		if (field->flags & FIELD_IS_ARRAY) {
+		if (field->flags & TEP_FIELD_IS_ARRAY) {
 			offset = field->offset;
 			len    = field->size;
-			if (field->flags & FIELD_IS_DYNAMIC) {
+			if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 				val     = tep_read_number(scripting_context->pevent,
 							  data + offset, len);
 				offset  = val;
 				len     = offset >> 16;
 				offset &= 0xffff;
 			}
-			if (field->flags & FIELD_IS_STRING &&
+			if (field->flags & TEP_FIELD_IS_STRING &&
 			    is_printable_array(data + offset, len)) {
 				obj = _PyUnicode_FromString((char *) data + offset);
 			} else {
 				obj = PyByteArray_FromStringAndSize((const char *) data + offset, len);
-				field->flags &= ~FIELD_IS_STRING;
+				field->flags &= ~TEP_FIELD_IS_STRING;
 			}
 		} else { /* FIELD_IS_NUMERIC */
 			obj = get_field_numeric_entry(event, field, data);
@@ -1686,12 +1686,12 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile
 			count++;
 
 			fprintf(ofp, "%s=", f->name);
-			if (f->flags & FIELD_IS_STRING ||
-			    f->flags & FIELD_IS_FLAG ||
-			    f->flags & FIELD_IS_ARRAY ||
-			    f->flags & FIELD_IS_SYMBOLIC)
+			if (f->flags & TEP_FIELD_IS_STRING ||
+			    f->flags & TEP_FIELD_IS_FLAG ||
+			    f->flags & TEP_FIELD_IS_ARRAY ||
+			    f->flags & TEP_FIELD_IS_SYMBOLIC)
 				fprintf(ofp, "%%s");
-			else if (f->flags & FIELD_IS_SIGNED)
+			else if (f->flags & TEP_FIELD_IS_SIGNED)
 				fprintf(ofp, "%%d");
 			else
 				fprintf(ofp, "%%u");
@@ -1709,7 +1709,7 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile
 			if (++count % 5 == 0)
 				fprintf(ofp, "\n\t\t");
 
-			if (f->flags & FIELD_IS_FLAG) {
+			if (f->flags & TEP_FIELD_IS_FLAG) {
 				if ((count - 1) % 5 != 0) {
 					fprintf(ofp, "\n\t\t");
 					count = 4;
@@ -1719,7 +1719,7 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile
 					event->name);
 				fprintf(ofp, "\"%s\", %s)", f->name,
 					f->name);
-			} else if (f->flags & FIELD_IS_SYMBOLIC) {
+			} else if (f->flags & TEP_FIELD_IS_SYMBOLIC) {
 				if ((count - 1) % 5 != 0) {
 					fprintf(ofp, "\n\t\t");
 					count = 4;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 5e3179d995f9..f96c005b3c41 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1899,7 +1899,7 @@ static int hde_width(struct hpp_dynamic_entry *hde)
 		if (namelen > len)
 			len = namelen;
 
-		if (!(hde->field->flags & FIELD_IS_STRING)) {
+		if (!(hde->field->flags & TEP_FIELD_IS_STRING)) {
 			/* length for print hex numbers */
 			fieldlen = hde->field->size * 2 + 2;
 		}
@@ -2071,7 +2071,7 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 	}
 
 	field = hde->field;
-	if (field->flags & FIELD_IS_DYNAMIC) {
+	if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 		unsigned long long dyn;
 
 		tep_read_number_field(field, a->raw_data, &dyn);
-- 
cgit v1.2.3


From f25d9e09e9354bded677d21b51a7b1879cfa02a8 Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Wed, 19 Sep 2018 14:56:47 -0400
Subject: tools lib traceevent: Rename enum event_{sort_}type to enum
 tep_event_{sort_}type

In order to make libtraceevent into a proper library, variables, data
structures and functions require a unique prefix to prevent name space
conflicts. That prefix will be "tep_". This renames enum event_type to
enum tep_event_type, enum event_sort_type to enum tep_event_sort_type
and add prefix TEP_ to all enum's members

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lkml.kernel.org/r/20180919185722.961022207@goodmis.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.c  | 488 ++++++++++++++++++------------------
 tools/lib/traceevent/event-parse.h  |  34 +--
 tools/lib/traceevent/parse-filter.c |  36 +--
 3 files changed, 279 insertions(+), 279 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 508c89365c90..1696dd9534bc 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -770,12 +770,12 @@ static int add_event(struct tep_handle *pevent, struct tep_event_format *event)
 	return 0;
 }
 
-static int event_item_type(enum event_type type)
+static int event_item_type(enum tep_event_type type)
 {
 	switch (type) {
-	case EVENT_ITEM ... EVENT_SQUOTE:
+	case TEP_EVENT_ITEM ... TEP_EVENT_SQUOTE:
 		return 1;
-	case EVENT_ERROR ... EVENT_DELIM:
+	case TEP_EVENT_ERROR ... TEP_EVENT_DELIM:
 	default:
 		return 0;
 	}
@@ -863,24 +863,24 @@ static void free_arg(struct print_arg *arg)
 	free(arg);
 }
 
-static enum event_type get_type(int ch)
+static enum tep_event_type get_type(int ch)
 {
 	if (ch == '\n')
-		return EVENT_NEWLINE;
+		return TEP_EVENT_NEWLINE;
 	if (isspace(ch))
-		return EVENT_SPACE;
+		return TEP_EVENT_SPACE;
 	if (isalnum(ch) || ch == '_')
-		return EVENT_ITEM;
+		return TEP_EVENT_ITEM;
 	if (ch == '\'')
-		return EVENT_SQUOTE;
+		return TEP_EVENT_SQUOTE;
 	if (ch == '"')
-		return EVENT_DQUOTE;
+		return TEP_EVENT_DQUOTE;
 	if (!isprint(ch))
-		return EVENT_NONE;
+		return TEP_EVENT_NONE;
 	if (ch == '(' || ch == ')' || ch == ',')
-		return EVENT_DELIM;
+		return TEP_EVENT_DELIM;
 
-	return EVENT_OP;
+	return TEP_EVENT_OP;
 }
 
 static int __read_char(void)
@@ -928,38 +928,38 @@ static int extend_token(char **tok, char *buf, int size)
 	return 0;
 }
 
-static enum event_type force_token(const char *str, char **tok);
+static enum tep_event_type force_token(const char *str, char **tok);
 
-static enum event_type __read_token(char **tok)
+static enum tep_event_type __read_token(char **tok)
 {
 	char buf[BUFSIZ];
 	int ch, last_ch, quote_ch, next_ch;
 	int i = 0;
 	int tok_size = 0;
-	enum event_type type;
+	enum tep_event_type type;
 
 	*tok = NULL;
 
 
 	ch = __read_char();
 	if (ch < 0)
-		return EVENT_NONE;
+		return TEP_EVENT_NONE;
 
 	type = get_type(ch);
-	if (type == EVENT_NONE)
+	if (type == TEP_EVENT_NONE)
 		return type;
 
 	buf[i++] = ch;
 
 	switch (type) {
-	case EVENT_NEWLINE:
-	case EVENT_DELIM:
+	case TEP_EVENT_NEWLINE:
+	case TEP_EVENT_DELIM:
 		if (asprintf(tok, "%c", ch) < 0)
-			return EVENT_ERROR;
+			return TEP_EVENT_ERROR;
 
 		return type;
 
-	case EVENT_OP:
+	case TEP_EVENT_OP:
 		switch (ch) {
 		case '-':
 			next_ch = __peek_char();
@@ -1002,8 +1002,8 @@ static enum event_type __read_token(char **tok)
 			buf[i++] = __read_char();
 		goto out;
 
-	case EVENT_DQUOTE:
-	case EVENT_SQUOTE:
+	case TEP_EVENT_DQUOTE:
+	case TEP_EVENT_SQUOTE:
 		/* don't keep quotes */
 		i--;
 		quote_ch = ch;
@@ -1015,7 +1015,7 @@ static enum event_type __read_token(char **tok)
 				tok_size += BUFSIZ;
 
 				if (extend_token(tok, buf, tok_size) < 0)
-					return EVENT_NONE;
+					return TEP_EVENT_NONE;
 				i = 0;
 			}
 			last_ch = ch;
@@ -1032,7 +1032,7 @@ static enum event_type __read_token(char **tok)
 		 * For strings (double quotes) check the next token.
 		 * If it is another string, concatinate the two.
 		 */
-		if (type == EVENT_DQUOTE) {
+		if (type == TEP_EVENT_DQUOTE) {
 			unsigned long long save_input_buf_ptr = input_buf_ptr;
 
 			do {
@@ -1045,8 +1045,8 @@ static enum event_type __read_token(char **tok)
 
 		goto out;
 
-	case EVENT_ERROR ... EVENT_SPACE:
-	case EVENT_ITEM:
+	case TEP_EVENT_ERROR ... TEP_EVENT_SPACE:
+	case TEP_EVENT_ITEM:
 	default:
 		break;
 	}
@@ -1057,7 +1057,7 @@ static enum event_type __read_token(char **tok)
 			tok_size += BUFSIZ;
 
 			if (extend_token(tok, buf, tok_size) < 0)
-				return EVENT_NONE;
+				return TEP_EVENT_NONE;
 			i = 0;
 		}
 		ch = __read_char();
@@ -1067,9 +1067,9 @@ static enum event_type __read_token(char **tok)
  out:
 	buf[i] = 0;
 	if (extend_token(tok, buf, tok_size + i + 1) < 0)
-		return EVENT_NONE;
+		return TEP_EVENT_NONE;
 
-	if (type == EVENT_ITEM) {
+	if (type == TEP_EVENT_ITEM) {
 		/*
 		 * Older versions of the kernel has a bug that
 		 * creates invalid symbols and will break the mac80211
@@ -1096,12 +1096,12 @@ static enum event_type __read_token(char **tok)
 	return type;
 }
 
-static enum event_type force_token(const char *str, char **tok)
+static enum tep_event_type force_token(const char *str, char **tok)
 {
 	const char *save_input_buf;
 	unsigned long long save_input_buf_ptr;
 	unsigned long long save_input_buf_siz;
-	enum event_type type;
+	enum tep_event_type type;
 	
 	/* save off the current input pointers */
 	save_input_buf = input_buf;
@@ -1126,13 +1126,13 @@ static void free_token(char *tok)
 		free(tok);
 }
 
-static enum event_type read_token(char **tok)
+static enum tep_event_type read_token(char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 
 	for (;;) {
 		type = __read_token(tok);
-		if (type != EVENT_SPACE)
+		if (type != TEP_EVENT_SPACE)
 			return type;
 
 		free_token(*tok);
@@ -1140,7 +1140,7 @@ static enum event_type read_token(char **tok)
 
 	/* not reached */
 	*tok = NULL;
-	return EVENT_NONE;
+	return TEP_EVENT_NONE;
 }
 
 /**
@@ -1152,7 +1152,7 @@ static enum event_type read_token(char **tok)
  *
  * Returns the token type.
  */
-enum event_type tep_read_token(char **tok)
+enum tep_event_type tep_read_token(char **tok)
 {
 	return read_token(tok);
 }
@@ -1167,13 +1167,13 @@ void tep_free_token(char *token)
 }
 
 /* no newline */
-static enum event_type read_token_item(char **tok)
+static enum tep_event_type read_token_item(char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 
 	for (;;) {
 		type = __read_token(tok);
-		if (type != EVENT_SPACE && type != EVENT_NEWLINE)
+		if (type != TEP_EVENT_SPACE && type != TEP_EVENT_NEWLINE)
 			return type;
 		free_token(*tok);
 		*tok = NULL;
@@ -1181,10 +1181,10 @@ static enum event_type read_token_item(char **tok)
 
 	/* not reached */
 	*tok = NULL;
-	return EVENT_NONE;
+	return TEP_EVENT_NONE;
 }
 
-static int test_type(enum event_type type, enum event_type expect)
+static int test_type(enum tep_event_type type, enum tep_event_type expect)
 {
 	if (type != expect) {
 		do_warning("Error: expected type %d but read %d",
@@ -1194,8 +1194,8 @@ static int test_type(enum event_type type, enum event_type expect)
 	return 0;
 }
 
-static int test_type_token(enum event_type type, const char *token,
-		    enum event_type expect, const char *expect_tok)
+static int test_type_token(enum tep_event_type type, const char *token,
+		    enum tep_event_type expect, const char *expect_tok)
 {
 	if (type != expect) {
 		do_warning("Error: expected type %d but read %d",
@@ -1211,9 +1211,9 @@ static int test_type_token(enum event_type type, const char *token,
 	return 0;
 }
 
-static int __read_expect_type(enum event_type expect, char **tok, int newline_ok)
+static int __read_expect_type(enum tep_event_type expect, char **tok, int newline_ok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 
 	if (newline_ok)
 		type = read_token(tok);
@@ -1222,15 +1222,15 @@ static int __read_expect_type(enum event_type expect, char **tok, int newline_ok
 	return test_type(type, expect);
 }
 
-static int read_expect_type(enum event_type expect, char **tok)
+static int read_expect_type(enum tep_event_type expect, char **tok)
 {
 	return __read_expect_type(expect, tok, 1);
 }
 
-static int __read_expected(enum event_type expect, const char *str,
+static int __read_expected(enum tep_event_type expect, const char *str,
 			   int newline_ok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 	int ret;
 
@@ -1246,12 +1246,12 @@ static int __read_expected(enum event_type expect, const char *str,
 	return ret;
 }
 
-static int read_expected(enum event_type expect, const char *str)
+static int read_expected(enum tep_event_type expect, const char *str)
 {
 	return __read_expected(expect, str, 1);
 }
 
-static int read_expected_item(enum event_type expect, const char *str)
+static int read_expected_item(enum tep_event_type expect, const char *str)
 {
 	return __read_expected(expect, str, 0);
 }
@@ -1260,13 +1260,13 @@ static char *event_read_name(void)
 {
 	char *token;
 
-	if (read_expected(EVENT_ITEM, "name") < 0)
+	if (read_expected(TEP_EVENT_ITEM, "name") < 0)
 		return NULL;
 
-	if (read_expected(EVENT_OP, ":") < 0)
+	if (read_expected(TEP_EVENT_OP, ":") < 0)
 		return NULL;
 
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto fail;
 
 	return token;
@@ -1281,13 +1281,13 @@ static int event_read_id(void)
 	char *token;
 	int id;
 
-	if (read_expected_item(EVENT_ITEM, "ID") < 0)
+	if (read_expected_item(TEP_EVENT_ITEM, "ID") < 0)
 		return -1;
 
-	if (read_expected(EVENT_OP, ":") < 0)
+	if (read_expected(TEP_EVENT_OP, ":") < 0)
 		return -1;
 
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto fail;
 
 	id = strtoul(token, NULL, 0);
@@ -1357,7 +1357,7 @@ static unsigned int type_size(const char *name)
 static int event_read_fields(struct tep_event_format *event, struct tep_format_field **fields)
 {
 	struct tep_format_field *field = NULL;
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 	char *last_token;
 	int count = 0;
@@ -1366,14 +1366,14 @@ static int event_read_fields(struct tep_event_format *event, struct tep_format_f
 		unsigned int size_dynamic = 0;
 
 		type = read_token(&token);
-		if (type == EVENT_NEWLINE) {
+		if (type == TEP_EVENT_NEWLINE) {
 			free_token(token);
 			return count;
 		}
 
 		count++;
 
-		if (test_type_token(type, token, EVENT_ITEM, "field"))
+		if (test_type_token(type, token, TEP_EVENT_ITEM, "field"))
 			goto fail;
 		free_token(token);
 
@@ -1383,16 +1383,16 @@ static int event_read_fields(struct tep_event_format *event, struct tep_format_f
 		 * Just ignore it.
 		 */
 		if (event->flags & EVENT_FL_ISFTRACE &&
-		    type == EVENT_ITEM && strcmp(token, "special") == 0) {
+		    type == TEP_EVENT_ITEM && strcmp(token, "special") == 0) {
 			free_token(token);
 			type = read_token(&token);
 		}
 
-		if (test_type_token(type, token, EVENT_OP, ":") < 0)
+		if (test_type_token(type, token, TEP_EVENT_OP, ":") < 0)
 			goto fail;
 
 		free_token(token);
-		if (read_expect_type(EVENT_ITEM, &token) < 0)
+		if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 			goto fail;
 
 		last_token = token;
@@ -1406,14 +1406,14 @@ static int event_read_fields(struct tep_event_format *event, struct tep_format_f
 		/* read the rest of the type */
 		for (;;) {
 			type = read_token(&token);
-			if (type == EVENT_ITEM ||
-			    (type == EVENT_OP && strcmp(token, "*") == 0) ||
+			if (type == TEP_EVENT_ITEM ||
+			    (type == TEP_EVENT_OP && strcmp(token, "*") == 0) ||
 			    /*
 			     * Some of the ftrace fields are broken and have
 			     * an illegal "." in them.
 			     */
 			    (event->flags & EVENT_FL_ISFTRACE &&
-			     type == EVENT_OP && strcmp(token, ".") == 0)) {
+			     type == TEP_EVENT_OP && strcmp(token, ".") == 0)) {
 
 				if (strcmp(token, "*") == 0)
 					field->flags |= TEP_FIELD_IS_POINTER;
@@ -1446,11 +1446,11 @@ static int event_read_fields(struct tep_event_format *event, struct tep_format_f
 		}
 		field->name = field->alias = last_token;
 
-		if (test_type(type, EVENT_OP))
+		if (test_type(type, TEP_EVENT_OP))
 			goto fail;
 
 		if (strcmp(token, "[") == 0) {
-			enum event_type last_type = type;
+			enum tep_event_type last_type = type;
 			char *brackets = token;
 			char *new_brackets;
 			int len;
@@ -1459,14 +1459,14 @@ static int event_read_fields(struct tep_event_format *event, struct tep_format_f
 
 			type = read_token(&token);
 
-			if (type == EVENT_ITEM)
+			if (type == TEP_EVENT_ITEM)
 				field->arraylen = strtoul(token, NULL, 0);
 			else
 				field->arraylen = 0;
 
 		        while (strcmp(token, "]") != 0) {
-				if (last_type == EVENT_ITEM &&
-				    type == EVENT_ITEM)
+				if (last_type == TEP_EVENT_ITEM &&
+				    type == TEP_EVENT_ITEM)
 					len = 2;
 				else
 					len = 1;
@@ -1487,7 +1487,7 @@ static int event_read_fields(struct tep_event_format *event, struct tep_format_f
 				field->arraylen = strtoul(token, NULL, 0);
 				free_token(token);
 				type = read_token(&token);
-				if (type == EVENT_NONE) {
+				if (type == TEP_EVENT_NONE) {
 					do_warning_event(event, "failed to find token");
 					goto fail;
 				}
@@ -1510,7 +1510,7 @@ static int event_read_fields(struct tep_event_format *event, struct tep_format_f
 			 * If the next token is not an OP, then it is of
 			 * the format: type [] item;
 			 */
-			if (type == EVENT_ITEM) {
+			if (type == TEP_EVENT_ITEM) {
 				char *new_type;
 				new_type = realloc(field->type,
 						   strlen(field->type) +
@@ -1550,60 +1550,60 @@ static int event_read_fields(struct tep_event_format *event, struct tep_format_f
 		if (field_is_long(field))
 			field->flags |= TEP_FIELD_IS_LONG;
 
-		if (test_type_token(type, token,  EVENT_OP, ";"))
+		if (test_type_token(type, token,  TEP_EVENT_OP, ";"))
 			goto fail;
 		free_token(token);
 
-		if (read_expected(EVENT_ITEM, "offset") < 0)
+		if (read_expected(TEP_EVENT_ITEM, "offset") < 0)
 			goto fail_expect;
 
-		if (read_expected(EVENT_OP, ":") < 0)
+		if (read_expected(TEP_EVENT_OP, ":") < 0)
 			goto fail_expect;
 
-		if (read_expect_type(EVENT_ITEM, &token))
+		if (read_expect_type(TEP_EVENT_ITEM, &token))
 			goto fail;
 		field->offset = strtoul(token, NULL, 0);
 		free_token(token);
 
-		if (read_expected(EVENT_OP, ";") < 0)
+		if (read_expected(TEP_EVENT_OP, ";") < 0)
 			goto fail_expect;
 
-		if (read_expected(EVENT_ITEM, "size") < 0)
+		if (read_expected(TEP_EVENT_ITEM, "size") < 0)
 			goto fail_expect;
 
-		if (read_expected(EVENT_OP, ":") < 0)
+		if (read_expected(TEP_EVENT_OP, ":") < 0)
 			goto fail_expect;
 
-		if (read_expect_type(EVENT_ITEM, &token))
+		if (read_expect_type(TEP_EVENT_ITEM, &token))
 			goto fail;
 		field->size = strtoul(token, NULL, 0);
 		free_token(token);
 
-		if (read_expected(EVENT_OP, ";") < 0)
+		if (read_expected(TEP_EVENT_OP, ";") < 0)
 			goto fail_expect;
 
 		type = read_token(&token);
-		if (type != EVENT_NEWLINE) {
+		if (type != TEP_EVENT_NEWLINE) {
 			/* newer versions of the kernel have a "signed" type */
-			if (test_type_token(type, token, EVENT_ITEM, "signed"))
+			if (test_type_token(type, token, TEP_EVENT_ITEM, "signed"))
 				goto fail;
 
 			free_token(token);
 
-			if (read_expected(EVENT_OP, ":") < 0)
+			if (read_expected(TEP_EVENT_OP, ":") < 0)
 				goto fail_expect;
 
-			if (read_expect_type(EVENT_ITEM, &token))
+			if (read_expect_type(TEP_EVENT_ITEM, &token))
 				goto fail;
 
 			if (strtoul(token, NULL, 0))
 				field->flags |= TEP_FIELD_IS_SIGNED;
 
 			free_token(token);
-			if (read_expected(EVENT_OP, ";") < 0)
+			if (read_expected(TEP_EVENT_OP, ";") < 0)
 				goto fail_expect;
 
-			if (read_expect_type(EVENT_NEWLINE, &token))
+			if (read_expect_type(TEP_EVENT_NEWLINE, &token))
 				goto fail;
 		}
 
@@ -1646,13 +1646,13 @@ static int event_read_format(struct tep_event_format *event)
 	char *token;
 	int ret;
 
-	if (read_expected_item(EVENT_ITEM, "format") < 0)
+	if (read_expected_item(TEP_EVENT_ITEM, "format") < 0)
 		return -1;
 
-	if (read_expected(EVENT_OP, ":") < 0)
+	if (read_expected(TEP_EVENT_OP, ":") < 0)
 		return -1;
 
-	if (read_expect_type(EVENT_NEWLINE, &token))
+	if (read_expect_type(TEP_EVENT_NEWLINE, &token))
 		goto fail;
 	free_token(token);
 
@@ -1673,14 +1673,14 @@ static int event_read_format(struct tep_event_format *event)
 	return -1;
 }
 
-static enum event_type
+static enum tep_event_type
 process_arg_token(struct tep_event_format *event, struct print_arg *arg,
-		  char **tok, enum event_type type);
+		  char **tok, enum tep_event_type type);
 
-static enum event_type
+static enum tep_event_type
 process_arg(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 
 	type = read_token(&token);
@@ -1689,32 +1689,32 @@ process_arg(struct tep_event_format *event, struct print_arg *arg, char **tok)
 	return process_arg_token(event, arg, tok, type);
 }
 
-static enum event_type
+static enum tep_event_type
 process_op(struct tep_event_format *event, struct print_arg *arg, char **tok);
 
 /*
  * For __print_symbolic() and __print_flags, we need to completely
  * evaluate the first argument, which defines what to print next.
  */
-static enum event_type
+static enum tep_event_type
 process_field_arg(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 
 	type = process_arg(event, arg, tok);
 
-	while (type == EVENT_OP) {
+	while (type == TEP_EVENT_OP) {
 		type = process_op(event, arg, tok);
 	}
 
 	return type;
 }
 
-static enum event_type
+static enum tep_event_type
 process_cond(struct tep_event_format *event, struct print_arg *top, char **tok)
 {
 	struct print_arg *arg, *left, *right;
-	enum event_type type;
+	enum tep_event_type type;
 	char *token = NULL;
 
 	arg = alloc_arg();
@@ -1737,16 +1737,16 @@ process_cond(struct tep_event_format *event, struct print_arg *top, char **tok)
 	type = process_arg(event, left, &token);
 
  again:
-	if (type == EVENT_ERROR)
+	if (type == TEP_EVENT_ERROR)
 		goto out_free;
 
 	/* Handle other operations in the arguments */
-	if (type == EVENT_OP && strcmp(token, ":") != 0) {
+	if (type == TEP_EVENT_OP && strcmp(token, ":") != 0) {
 		type = process_op(event, left, &token);
 		goto again;
 	}
 
-	if (test_type_token(type, token, EVENT_OP, ":"))
+	if (test_type_token(type, token, TEP_EVENT_OP, ":"))
 		goto out_free;
 
 	arg->op.op = token;
@@ -1763,14 +1763,14 @@ out_free:
 	top->op.right = NULL;
 	free_token(token);
 	free_arg(arg);
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
+static enum tep_event_type
 process_array(struct tep_event_format *event, struct print_arg *top, char **tok)
 {
 	struct print_arg *arg;
-	enum event_type type;
+	enum tep_event_type type;
 	char *token = NULL;
 
 	arg = alloc_arg();
@@ -1778,12 +1778,12 @@ process_array(struct tep_event_format *event, struct print_arg *top, char **tok)
 		do_warning_event(event, "%s: not enough memory!", __func__);
 		/* '*tok' is set to top->op.op.  No need to free. */
 		*tok = NULL;
-		return EVENT_ERROR;
+		return TEP_EVENT_ERROR;
 	}
 
 	*tok = NULL;
 	type = process_arg(event, arg, &token);
-	if (test_type_token(type, token, EVENT_OP, "]"))
+	if (test_type_token(type, token, TEP_EVENT_OP, "]"))
 		goto out_free;
 
 	top->op.right = arg;
@@ -1797,7 +1797,7 @@ process_array(struct tep_event_format *event, struct print_arg *top, char **tok)
 out_free:
 	free_token(token);
 	free_arg(arg);
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
 static int get_op_prio(char *op)
@@ -1868,11 +1868,11 @@ static int set_op_prio(struct print_arg *arg)
 }
 
 /* Note, *tok does not get freed, but will most likely be saved */
-static enum event_type
+static enum tep_event_type
 process_op(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
 	struct print_arg *left, *right = NULL;
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 
 	/* the op is passed in via tok */
@@ -1974,7 +1974,7 @@ process_op(struct tep_event_format *event, struct print_arg *arg, char **tok)
 
 		/* could just be a type pointer */
 		if ((strcmp(arg->op.op, "*") == 0) &&
-		    type == EVENT_DELIM && (strcmp(token, ")") == 0)) {
+		    type == TEP_EVENT_DELIM && (strcmp(token, ")") == 0)) {
 			char *new_atom;
 
 			if (left->type != PRINT_ATOM) {
@@ -2000,7 +2000,7 @@ process_op(struct tep_event_format *event, struct print_arg *arg, char **tok)
 			goto out_warn_free;
 
 		type = process_arg_token(event, right, tok, type);
-		if (type == EVENT_ERROR) {
+		if (type == TEP_EVENT_ERROR) {
 			free_arg(right);
 			/* token was freed in process_arg_token() via *tok */
 			token = NULL;
@@ -2047,7 +2047,7 @@ process_op(struct tep_event_format *event, struct print_arg *arg, char **tok)
 		goto out_free;
 	}
 
-	if (type == EVENT_OP && strcmp(*tok, ":") != 0) {
+	if (type == TEP_EVENT_OP && strcmp(*tok, ":") != 0) {
 		int prio;
 
 		/* higher prios need to be closer to the root */
@@ -2066,21 +2066,21 @@ out_warn_free:
 out_free:
 	free_token(token);
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
+static enum tep_event_type
 process_entry(struct tep_event_format *event __maybe_unused, struct print_arg *arg,
 	      char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	char *field;
 	char *token;
 
-	if (read_expected(EVENT_OP, "->") < 0)
+	if (read_expected(TEP_EVENT_OP, "->") < 0)
 		goto out_err;
 
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto out_free;
 	field = token;
 
@@ -2106,14 +2106,14 @@ process_entry(struct tep_event_format *event __maybe_unused, struct print_arg *a
 	free_token(token);
  out_err:
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
 static int alloc_and_process_delim(struct tep_event_format *event, char *next_token,
 				   struct print_arg **print_arg)
 {
 	struct print_arg *field;
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 	int ret = 0;
 
@@ -2126,7 +2126,7 @@ static int alloc_and_process_delim(struct tep_event_format *event, char *next_to
 
 	type = process_arg(event, field, &token);
 
-	if (test_type_token(type, token, EVENT_DELIM, next_token)) {
+	if (test_type_token(type, token, TEP_EVENT_DELIM, next_token)) {
 		errno = EINVAL;
 		ret = -1;
 		free_arg(field);
@@ -2443,10 +2443,10 @@ static char *arg_eval (struct print_arg *arg)
 	return NULL;
 }
 
-static enum event_type
+static enum tep_event_type
 process_fields(struct tep_event_format *event, struct print_flag_sym **list, char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	struct print_arg *arg = NULL;
 	struct print_flag_sym *field;
 	char *token = *tok;
@@ -2455,7 +2455,7 @@ process_fields(struct tep_event_format *event, struct print_flag_sym **list, cha
 	do {
 		free_token(token);
 		type = read_token_item(&token);
-		if (test_type_token(type, token, EVENT_OP, "{"))
+		if (test_type_token(type, token, TEP_EVENT_OP, "{"))
 			break;
 
 		arg = alloc_arg();
@@ -2465,13 +2465,13 @@ process_fields(struct tep_event_format *event, struct print_flag_sym **list, cha
 		free_token(token);
 		type = process_arg(event, arg, &token);
 
-		if (type == EVENT_OP)
+		if (type == TEP_EVENT_OP)
 			type = process_op(event, arg, &token);
 
-		if (type == EVENT_ERROR)
+		if (type == TEP_EVENT_ERROR)
 			goto out_free;
 
-		if (test_type_token(type, token, EVENT_DELIM, ","))
+		if (test_type_token(type, token, TEP_EVENT_DELIM, ","))
 			goto out_free;
 
 		field = calloc(1, sizeof(*field));
@@ -2492,7 +2492,7 @@ process_fields(struct tep_event_format *event, struct print_flag_sym **list, cha
 
 		free_token(token);
 		type = process_arg(event, arg, &token);
-		if (test_type_token(type, token, EVENT_OP, "}"))
+		if (test_type_token(type, token, TEP_EVENT_OP, "}"))
 			goto out_free_field;
 
 		value = arg_eval(arg);
@@ -2509,7 +2509,7 @@ process_fields(struct tep_event_format *event, struct print_flag_sym **list, cha
 
 		free_token(token);
 		type = read_token_item(&token);
-	} while (type == EVENT_DELIM && strcmp(token, ",") == 0);
+	} while (type == TEP_EVENT_DELIM && strcmp(token, ",") == 0);
 
 	*tok = token;
 	return type;
@@ -2521,14 +2521,14 @@ out_free:
 	free_token(token);
 	*tok = NULL;
 
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
+static enum tep_event_type
 process_flags(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
 	struct print_arg *field;
-	enum event_type type;
+	enum tep_event_type type;
 	char *token = NULL;
 
 	memset(arg, 0, sizeof(*arg));
@@ -2543,10 +2543,10 @@ process_flags(struct tep_event_format *event, struct print_arg *arg, char **tok)
 	type = process_field_arg(event, field, &token);
 
 	/* Handle operations in the first argument */
-	while (type == EVENT_OP)
+	while (type == TEP_EVENT_OP)
 		type = process_op(event, field, &token);
 
-	if (test_type_token(type, token, EVENT_DELIM, ","))
+	if (test_type_token(type, token, TEP_EVENT_DELIM, ","))
 		goto out_free_field;
 	free_token(token);
 
@@ -2558,11 +2558,11 @@ process_flags(struct tep_event_format *event, struct print_arg *arg, char **tok)
 		type = read_token_item(&token);
 	}
 
-	if (test_type_token(type, token, EVENT_DELIM, ","))
+	if (test_type_token(type, token, TEP_EVENT_DELIM, ","))
 		goto out_free;
 
 	type = process_fields(event, &arg->flags.flags, &token);
-	if (test_type_token(type, token, EVENT_DELIM, ")"))
+	if (test_type_token(type, token, TEP_EVENT_DELIM, ")"))
 		goto out_free;
 
 	free_token(token);
@@ -2574,14 +2574,14 @@ out_free_field:
 out_free:
 	free_token(token);
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
+static enum tep_event_type
 process_symbols(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
 	struct print_arg *field;
-	enum event_type type;
+	enum tep_event_type type;
 	char *token = NULL;
 
 	memset(arg, 0, sizeof(*arg));
@@ -2595,13 +2595,13 @@ process_symbols(struct tep_event_format *event, struct print_arg *arg, char **to
 
 	type = process_field_arg(event, field, &token);
 
-	if (test_type_token(type, token, EVENT_DELIM, ","))
+	if (test_type_token(type, token, TEP_EVENT_DELIM, ","))
 		goto out_free_field;
 
 	arg->symbol.field = field;
 
 	type = process_fields(event, &arg->symbol.symbols, &token);
-	if (test_type_token(type, token, EVENT_DELIM, ")"))
+	if (test_type_token(type, token, TEP_EVENT_DELIM, ")"))
 		goto out_free;
 
 	free_token(token);
@@ -2613,10 +2613,10 @@ out_free_field:
 out_free:
 	free_token(token);
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
+static enum tep_event_type
 process_hex_common(struct tep_event_format *event, struct print_arg *arg,
 		   char **tok, enum print_arg_type type)
 {
@@ -2636,23 +2636,23 @@ free_field:
 	arg->hex.field = NULL;
 out:
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
+static enum tep_event_type
 process_hex(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
 	return process_hex_common(event, arg, tok, PRINT_HEX);
 }
 
-static enum event_type
+static enum tep_event_type
 process_hex_str(struct tep_event_format *event, struct print_arg *arg,
 		char **tok)
 {
 	return process_hex_common(event, arg, tok, PRINT_HEX_STR);
 }
 
-static enum event_type
+static enum tep_event_type
 process_int_array(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
 	memset(arg, 0, sizeof(*arg));
@@ -2677,14 +2677,14 @@ free_field:
 	arg->int_array.field = NULL;
 out:
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
+static enum tep_event_type
 process_dynamic_array(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
 	struct tep_format_field *field;
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 
 	memset(arg, 0, sizeof(*arg));
@@ -2696,7 +2696,7 @@ process_dynamic_array(struct tep_event_format *event, struct print_arg *arg, cha
 	 */
 	type = read_token(&token);
 	*tok = token;
-	if (type != EVENT_ITEM)
+	if (type != TEP_EVENT_ITEM)
 		goto out_free;
 
 	/* Find the field */
@@ -2708,13 +2708,13 @@ process_dynamic_array(struct tep_event_format *event, struct print_arg *arg, cha
 	arg->dynarray.field = field;
 	arg->dynarray.index = 0;
 
-	if (read_expected(EVENT_DELIM, ")") < 0)
+	if (read_expected(TEP_EVENT_DELIM, ")") < 0)
 		goto out_free;
 
 	free_token(token);
 	type = read_token_item(&token);
 	*tok = token;
-	if (type != EVENT_OP || strcmp(token, "[") != 0)
+	if (type != TEP_EVENT_OP || strcmp(token, "[") != 0)
 		return type;
 
 	free_token(token);
@@ -2722,14 +2722,14 @@ process_dynamic_array(struct tep_event_format *event, struct print_arg *arg, cha
 	if (!arg) {
 		do_warning_event(event, "%s: not enough memory!", __func__);
 		*tok = NULL;
-		return EVENT_ERROR;
+		return TEP_EVENT_ERROR;
 	}
 
 	type = process_arg(event, arg, &token);
-	if (type == EVENT_ERROR)
+	if (type == TEP_EVENT_ERROR)
 		goto out_free_arg;
 
-	if (!test_type_token(type, token, EVENT_OP, "]"))
+	if (!test_type_token(type, token, TEP_EVENT_OP, "]"))
 		goto out_free_arg;
 
 	free_token(token);
@@ -2741,18 +2741,18 @@ process_dynamic_array(struct tep_event_format *event, struct print_arg *arg, cha
  out_free:
 	free_token(token);
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
+static enum tep_event_type
 process_dynamic_array_len(struct tep_event_format *event, struct print_arg *arg,
 			  char **tok)
 {
 	struct tep_format_field *field;
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto out_free;
 
 	arg->type = PRINT_DYNAMIC_ARRAY_LEN;
@@ -2765,7 +2765,7 @@ process_dynamic_array_len(struct tep_event_format *event, struct print_arg *arg,
 	arg->dynarray.field = field;
 	arg->dynarray.index = 0;
 
-	if (read_expected(EVENT_DELIM, ")") < 0)
+	if (read_expected(TEP_EVENT_DELIM, ")") < 0)
 		goto out_err;
 
 	type = read_token(&token);
@@ -2777,28 +2777,28 @@ process_dynamic_array_len(struct tep_event_format *event, struct print_arg *arg,
 	free_token(token);
  out_err:
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
+static enum tep_event_type
 process_paren(struct tep_event_format *event, struct print_arg *arg, char **tok)
 {
 	struct print_arg *item_arg;
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 
 	type = process_arg(event, arg, &token);
 
-	if (type == EVENT_ERROR)
+	if (type == TEP_EVENT_ERROR)
 		goto out_free;
 
-	if (type == EVENT_OP)
+	if (type == TEP_EVENT_OP)
 		type = process_op(event, arg, &token);
 
-	if (type == EVENT_ERROR)
+	if (type == TEP_EVENT_ERROR)
 		goto out_free;
 
-	if (test_type_token(type, token, EVENT_DELIM, ")"))
+	if (test_type_token(type, token, TEP_EVENT_DELIM, ")"))
 		goto out_free;
 
 	free_token(token);
@@ -2809,7 +2809,7 @@ process_paren(struct tep_event_format *event, struct print_arg *arg, char **tok)
 	 * this was a typecast.
 	 */
 	if (event_item_type(type) ||
-	    (type == EVENT_DELIM && strcmp(token, "(") == 0)) {
+	    (type == TEP_EVENT_DELIM && strcmp(token, "(") == 0)) {
 
 		/* make this a typecast and contine */
 
@@ -2839,25 +2839,25 @@ process_paren(struct tep_event_format *event, struct print_arg *arg, char **tok)
  out_free:
 	free_token(token);
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
 
-static enum event_type
+static enum tep_event_type
 process_str(struct tep_event_format *event __maybe_unused, struct print_arg *arg,
 	    char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto out_free;
 
 	arg->type = PRINT_STRING;
 	arg->string.string = token;
 	arg->string.offset = -1;
 
-	if (read_expected(EVENT_DELIM, ")") < 0)
+	if (read_expected(TEP_EVENT_DELIM, ")") < 0)
 		goto out_err;
 
 	type = read_token(&token);
@@ -2869,24 +2869,24 @@ process_str(struct tep_event_format *event __maybe_unused, struct print_arg *arg
 	free_token(token);
  out_err:
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
+static enum tep_event_type
 process_bitmask(struct tep_event_format *event __maybe_unused, struct print_arg *arg,
 		char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto out_free;
 
 	arg->type = PRINT_BITMASK;
 	arg->bitmask.bitmask = token;
 	arg->bitmask.offset = -1;
 
-	if (read_expected(EVENT_DELIM, ")") < 0)
+	if (read_expected(TEP_EVENT_DELIM, ")") < 0)
 		goto out_err;
 
 	type = read_token(&token);
@@ -2898,7 +2898,7 @@ process_bitmask(struct tep_event_format *event __maybe_unused, struct print_arg
 	free_token(token);
  out_err:
 	*tok = NULL;
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
 static struct tep_function_handler *
@@ -2933,13 +2933,13 @@ static void remove_func_handler(struct tep_handle *pevent, char *func_name)
 	}
 }
 
-static enum event_type
+static enum tep_event_type
 process_func_handler(struct tep_event_format *event, struct tep_function_handler *func,
 		     struct print_arg *arg, char **tok)
 {
 	struct print_arg **next_arg;
 	struct print_arg *farg;
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 	int i;
 
@@ -2954,12 +2954,12 @@ process_func_handler(struct tep_event_format *event, struct tep_function_handler
 		if (!farg) {
 			do_warning_event(event, "%s: not enough memory!",
 					 __func__);
-			return EVENT_ERROR;
+			return TEP_EVENT_ERROR;
 		}
 
 		type = process_arg(event, farg, &token);
 		if (i < (func->nr_args - 1)) {
-			if (type != EVENT_DELIM || strcmp(token, ",") != 0) {
+			if (type != TEP_EVENT_DELIM || strcmp(token, ",") != 0) {
 				do_warning_event(event,
 					"Error: function '%s()' expects %d arguments but event %s only uses %d",
 					func->name, func->nr_args,
@@ -2967,7 +2967,7 @@ process_func_handler(struct tep_event_format *event, struct tep_function_handler
 				goto err;
 			}
 		} else {
-			if (type != EVENT_DELIM || strcmp(token, ")") != 0) {
+			if (type != TEP_EVENT_DELIM || strcmp(token, ")") != 0) {
 				do_warning_event(event,
 					"Error: function '%s()' only expects %d arguments but event %s has more",
 					func->name, func->nr_args, event->name);
@@ -2988,10 +2988,10 @@ process_func_handler(struct tep_event_format *event, struct tep_function_handler
 err:
 	free_arg(farg);
 	free_token(token);
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
+static enum tep_event_type
 process_function(struct tep_event_format *event, struct print_arg *arg,
 		 char *token, char **tok)
 {
@@ -3044,12 +3044,12 @@ process_function(struct tep_event_format *event, struct print_arg *arg,
 
 	do_warning_event(event, "function %s not defined", token);
 	free_token(token);
-	return EVENT_ERROR;
+	return TEP_EVENT_ERROR;
 }
 
-static enum event_type
+static enum tep_event_type
 process_arg_token(struct tep_event_format *event, struct print_arg *arg,
-		  char **tok, enum event_type type)
+		  char **tok, enum tep_event_type type)
 {
 	char *token;
 	char *atom;
@@ -3057,7 +3057,7 @@ process_arg_token(struct tep_event_format *event, struct print_arg *arg,
 	token = *tok;
 
 	switch (type) {
-	case EVENT_ITEM:
+	case TEP_EVENT_ITEM:
 		if (strcmp(token, "REC") == 0) {
 			free_token(token);
 			type = process_entry(event, arg, &token);
@@ -3071,7 +3071,7 @@ process_arg_token(struct tep_event_format *event, struct print_arg *arg,
 		 * If the next token is a parenthesis, then this
 		 * is a function.
 		 */
-		if (type == EVENT_DELIM && strcmp(token, "(") == 0) {
+		if (type == TEP_EVENT_DELIM && strcmp(token, "(") == 0) {
 			free_token(token);
 			token = NULL;
 			/* this will free atom. */
@@ -3079,7 +3079,7 @@ process_arg_token(struct tep_event_format *event, struct print_arg *arg,
 			break;
 		}
 		/* atoms can be more than one token long */
-		while (type == EVENT_ITEM) {
+		while (type == TEP_EVENT_ITEM) {
 			char *new_atom;
 			new_atom = realloc(atom,
 					   strlen(atom) + strlen(token) + 2);
@@ -3087,7 +3087,7 @@ process_arg_token(struct tep_event_format *event, struct print_arg *arg,
 				free(atom);
 				*tok = NULL;
 				free_token(token);
-				return EVENT_ERROR;
+				return TEP_EVENT_ERROR;
 			}
 			atom = new_atom;
 			strcat(atom, " ");
@@ -3100,19 +3100,19 @@ process_arg_token(struct tep_event_format *event, struct print_arg *arg,
 		arg->atom.atom = atom;
 		break;
 
-	case EVENT_DQUOTE:
-	case EVENT_SQUOTE:
+	case TEP_EVENT_DQUOTE:
+	case TEP_EVENT_SQUOTE:
 		arg->type = PRINT_ATOM;
 		arg->atom.atom = token;
 		type = read_token_item(&token);
 		break;
-	case EVENT_DELIM:
+	case TEP_EVENT_DELIM:
 		if (strcmp(token, "(") == 0) {
 			free_token(token);
 			type = process_paren(event, arg, &token);
 			break;
 		}
-	case EVENT_OP:
+	case TEP_EVENT_OP:
 		/* handle single ops */
 		arg->type = PRINT_OP;
 		arg->op.op = token;
@@ -3120,16 +3120,16 @@ process_arg_token(struct tep_event_format *event, struct print_arg *arg,
 		type = process_op(event, arg, &token);
 
 		/* On error, the op is freed */
-		if (type == EVENT_ERROR)
+		if (type == TEP_EVENT_ERROR)
 			arg->op.op = NULL;
 
 		/* return error type if errored */
 		break;
 
-	case EVENT_ERROR ... EVENT_NEWLINE:
+	case TEP_EVENT_ERROR ... TEP_EVENT_NEWLINE:
 	default:
 		do_warning_event(event, "unexpected type %d", type);
-		return EVENT_ERROR;
+		return TEP_EVENT_ERROR;
 	}
 	*tok = token;
 
@@ -3138,13 +3138,13 @@ process_arg_token(struct tep_event_format *event, struct print_arg *arg,
 
 static int event_read_print_args(struct tep_event_format *event, struct print_arg **list)
 {
-	enum event_type type = EVENT_ERROR;
+	enum tep_event_type type = TEP_EVENT_ERROR;
 	struct print_arg *arg;
 	char *token;
 	int args = 0;
 
 	do {
-		if (type == EVENT_NEWLINE) {
+		if (type == TEP_EVENT_NEWLINE) {
 			type = read_token_item(&token);
 			continue;
 		}
@@ -3158,7 +3158,7 @@ static int event_read_print_args(struct tep_event_format *event, struct print_ar
 
 		type = process_arg(event, arg, &token);
 
-		if (type == EVENT_ERROR) {
+		if (type == TEP_EVENT_ERROR) {
 			free_token(token);
 			free_arg(arg);
 			return -1;
@@ -3167,10 +3167,10 @@ static int event_read_print_args(struct tep_event_format *event, struct print_ar
 		*list = arg;
 		args++;
 
-		if (type == EVENT_OP) {
+		if (type == TEP_EVENT_OP) {
 			type = process_op(event, arg, &token);
 			free_token(token);
-			if (type == EVENT_ERROR) {
+			if (type == TEP_EVENT_ERROR) {
 				*list = NULL;
 				free_arg(arg);
 				return -1;
@@ -3179,16 +3179,16 @@ static int event_read_print_args(struct tep_event_format *event, struct print_ar
 			continue;
 		}
 
-		if (type == EVENT_DELIM && strcmp(token, ",") == 0) {
+		if (type == TEP_EVENT_DELIM && strcmp(token, ",") == 0) {
 			free_token(token);
 			*list = arg;
 			list = &arg->next;
 			continue;
 		}
 		break;
-	} while (type != EVENT_NONE);
+	} while (type != TEP_EVENT_NONE);
 
-	if (type != EVENT_NONE && type != EVENT_ERROR)
+	if (type != TEP_EVENT_NONE && type != TEP_EVENT_ERROR)
 		free_token(token);
 
 	return args;
@@ -3196,20 +3196,20 @@ static int event_read_print_args(struct tep_event_format *event, struct print_ar
 
 static int event_read_print(struct tep_event_format *event)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	char *token;
 	int ret;
 
-	if (read_expected_item(EVENT_ITEM, "print") < 0)
+	if (read_expected_item(TEP_EVENT_ITEM, "print") < 0)
 		return -1;
 
-	if (read_expected(EVENT_ITEM, "fmt") < 0)
+	if (read_expected(TEP_EVENT_ITEM, "fmt") < 0)
 		return -1;
 
-	if (read_expected(EVENT_OP, ":") < 0)
+	if (read_expected(TEP_EVENT_OP, ":") < 0)
 		return -1;
 
-	if (read_expect_type(EVENT_DQUOTE, &token) < 0)
+	if (read_expect_type(TEP_EVENT_DQUOTE, &token) < 0)
 		goto fail;
 
  concat:
@@ -3219,11 +3219,11 @@ static int event_read_print(struct tep_event_format *event)
 	/* ok to have no arg */
 	type = read_token_item(&token);
 
-	if (type == EVENT_NONE)
+	if (type == TEP_EVENT_NONE)
 		return 0;
 
 	/* Handle concatenation of print lines */
-	if (type == EVENT_DQUOTE) {
+	if (type == TEP_EVENT_DQUOTE) {
 		char *cat;
 
 		if (asprintf(&cat, "%s%s", event->print_fmt.format, token) < 0)
@@ -3235,7 +3235,7 @@ static int event_read_print(struct tep_event_format *event)
 		goto concat;
 	}
 			     
-	if (test_type_token(type, token, EVENT_DELIM, ","))
+	if (test_type_token(type, token, TEP_EVENT_DELIM, ","))
 		goto fail;
 
 	free_token(token);
@@ -5617,7 +5617,7 @@ static int events_system_cmp(const void *a, const void *b)
 	return events_id_cmp(a, b);
 }
 
-struct tep_event_format **tep_list_events(struct tep_handle *pevent, enum event_sort_type sort_type)
+struct tep_event_format **tep_list_events(struct tep_handle *pevent, enum tep_event_sort_type sort_type)
 {
 	struct tep_event_format **events;
 	int (*sort)(const void *a, const void *b);
@@ -5638,20 +5638,20 @@ struct tep_event_format **tep_list_events(struct tep_handle *pevent, enum event_
 		pevent->sort_events = events;
 
 		/* the internal events are sorted by id */
-		if (sort_type == EVENT_SORT_ID) {
+		if (sort_type == TEP_EVENT_SORT_ID) {
 			pevent->last_type = sort_type;
 			return events;
 		}
 	}
 
 	switch (sort_type) {
-	case EVENT_SORT_ID:
+	case TEP_EVENT_SORT_ID:
 		sort = events_id_cmp;
 		break;
-	case EVENT_SORT_NAME:
+	case TEP_EVENT_SORT_NAME:
 		sort = events_name_cmp;
 		break;
-	case EVENT_SORT_SYSTEM:
+	case TEP_EVENT_SORT_SYSTEM:
 		sort = events_system_cmp;
 		break;
 	default:
@@ -5834,13 +5834,13 @@ static void parse_header_field(const char *field,
 	save_input_buf_ptr = input_buf_ptr;
 	save_input_buf_siz = input_buf_siz;
 
-	if (read_expected(EVENT_ITEM, "field") < 0)
+	if (read_expected(TEP_EVENT_ITEM, "field") < 0)
 		return;
-	if (read_expected(EVENT_OP, ":") < 0)
+	if (read_expected(TEP_EVENT_OP, ":") < 0)
 		return;
 
 	/* type */
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto fail;
 	free_token(token);
 
@@ -5848,42 +5848,42 @@ static void parse_header_field(const char *field,
 	 * If this is not a mandatory field, then test it first.
 	 */
 	if (mandatory) {
-		if (read_expected(EVENT_ITEM, field) < 0)
+		if (read_expected(TEP_EVENT_ITEM, field) < 0)
 			return;
 	} else {
-		if (read_expect_type(EVENT_ITEM, &token) < 0)
+		if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 			goto fail;
 		if (strcmp(token, field) != 0)
 			goto discard;
 		free_token(token);
 	}
 
-	if (read_expected(EVENT_OP, ";") < 0)
+	if (read_expected(TEP_EVENT_OP, ";") < 0)
 		return;
-	if (read_expected(EVENT_ITEM, "offset") < 0)
+	if (read_expected(TEP_EVENT_ITEM, "offset") < 0)
 		return;
-	if (read_expected(EVENT_OP, ":") < 0)
+	if (read_expected(TEP_EVENT_OP, ":") < 0)
 		return;
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto fail;
 	*offset = atoi(token);
 	free_token(token);
-	if (read_expected(EVENT_OP, ";") < 0)
+	if (read_expected(TEP_EVENT_OP, ";") < 0)
 		return;
-	if (read_expected(EVENT_ITEM, "size") < 0)
+	if (read_expected(TEP_EVENT_ITEM, "size") < 0)
 		return;
-	if (read_expected(EVENT_OP, ":") < 0)
+	if (read_expected(TEP_EVENT_OP, ":") < 0)
 		return;
-	if (read_expect_type(EVENT_ITEM, &token) < 0)
+	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto fail;
 	*size = atoi(token);
 	free_token(token);
-	if (read_expected(EVENT_OP, ";") < 0)
+	if (read_expected(TEP_EVENT_OP, ";") < 0)
 		return;
 	type = read_token(&token);
-	if (type != EVENT_NEWLINE) {
+	if (type != TEP_EVENT_NEWLINE) {
 		/* newer versions of the kernel have a "signed" type */
-		if (type != EVENT_ITEM)
+		if (type != TEP_EVENT_ITEM)
 			goto fail;
 
 		if (strcmp(token, "signed") != 0)
@@ -5891,17 +5891,17 @@ static void parse_header_field(const char *field,
 
 		free_token(token);
 
-		if (read_expected(EVENT_OP, ":") < 0)
+		if (read_expected(TEP_EVENT_OP, ":") < 0)
 			return;
 
-		if (read_expect_type(EVENT_ITEM, &token))
+		if (read_expect_type(TEP_EVENT_ITEM, &token))
 			goto fail;
 
 		free_token(token);
-		if (read_expected(EVENT_OP, ";") < 0)
+		if (read_expected(TEP_EVENT_OP, ";") < 0)
 			return;
 
-		if (read_expect_type(EVENT_NEWLINE, &token))
+		if (read_expect_type(TEP_EVENT_NEWLINE, &token))
 			goto fail;
 	}
  fail:
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index f1e1baee8cbd..10aaeda34c6b 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -301,22 +301,22 @@ enum {
 	EVENT_FL_FAILED		= 0x80000000
 };
 
-enum event_sort_type {
-	EVENT_SORT_ID,
-	EVENT_SORT_NAME,
-	EVENT_SORT_SYSTEM,
+enum tep_event_sort_type {
+	TEP_EVENT_SORT_ID,
+	TEP_EVENT_SORT_NAME,
+	TEP_EVENT_SORT_SYSTEM,
 };
 
-enum event_type {
-	EVENT_ERROR,
-	EVENT_NONE,
-	EVENT_SPACE,
-	EVENT_NEWLINE,
-	EVENT_OP,
-	EVENT_DELIM,
-	EVENT_ITEM,
-	EVENT_DQUOTE,
-	EVENT_SQUOTE,
+enum tep_event_type {
+	TEP_EVENT_ERROR,
+	TEP_EVENT_NONE,
+	TEP_EVENT_SPACE,
+	TEP_EVENT_NEWLINE,
+	TEP_EVENT_OP,
+	TEP_EVENT_DELIM,
+	TEP_EVENT_ITEM,
+	TEP_EVENT_DQUOTE,
+	TEP_EVENT_SQUOTE,
 };
 
 typedef unsigned long long (*tep_func_handler)(struct trace_seq *s,
@@ -454,7 +454,7 @@ struct tep_handle {
 	struct tep_event_format **events;
 	int nr_events;
 	struct tep_event_format **sort_events;
-	enum event_sort_type last_type;
+	enum tep_event_sort_type last_type;
 
 	int type_offset;
 	int type_size;
@@ -685,7 +685,7 @@ void tep_event_info(struct trace_seq *s, struct tep_event_format *event,
 int tep_strerror(struct tep_handle *pevent, enum tep_errno errnum,
 		    char *buf, size_t buflen);
 
-struct tep_event_format **tep_list_events(struct tep_handle *pevent, enum event_sort_type);
+struct tep_event_format **tep_list_events(struct tep_handle *pevent, enum tep_event_sort_type);
 struct tep_format_field **tep_event_common_fields(struct tep_event_format *event);
 struct tep_format_field **tep_event_fields(struct tep_event_format *event);
 
@@ -756,7 +756,7 @@ void tep_unref(struct tep_handle *pevent);
 
 /* access to the internal parser */
 void tep_buffer_init(const char *buf, unsigned long long size);
-enum event_type tep_read_token(char **tok);
+enum tep_event_type tep_read_token(char **tok);
 void tep_free_token(char *token);
 int tep_peek_char(void);
 const char *tep_get_input_buf(void);
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index dcd97acbbc49..153e248de75b 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -61,15 +61,15 @@ static void free_token(char *token)
 	tep_free_token(token);
 }
 
-static enum event_type read_token(char **tok)
+static enum tep_event_type read_token(char **tok)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	char *token = NULL;
 
 	do {
 		free_token(token);
 		type = tep_read_token(&token);
-	} while (type == EVENT_NEWLINE || type == EVENT_SPACE);
+	} while (type == TEP_EVENT_NEWLINE || type == TEP_EVENT_SPACE);
 
 	/* If token is = or ! check to see if the next char is ~ */
 	if (token &&
@@ -79,7 +79,7 @@ static enum event_type read_token(char **tok)
 		*tok = malloc(3);
 		if (*tok == NULL) {
 			free_token(token);
-			return EVENT_ERROR;
+			return TEP_EVENT_ERROR;
 		}
 		sprintf(*tok, "%c%c", *token, '~');
 		free_token(token);
@@ -334,7 +334,7 @@ static void free_events(struct event_list *events)
 
 static enum tep_errno
 create_arg_item(struct tep_event_format *event, const char *token,
-		enum event_type type, struct filter_arg **parg, char *error_str)
+		enum tep_event_type type, struct filter_arg **parg, char *error_str)
 {
 	struct tep_format_field *field;
 	struct filter_arg *arg;
@@ -347,11 +347,11 @@ create_arg_item(struct tep_event_format *event, const char *token,
 
 	switch (type) {
 
-	case EVENT_SQUOTE:
-	case EVENT_DQUOTE:
+	case TEP_EVENT_SQUOTE:
+	case TEP_EVENT_DQUOTE:
 		arg->type = FILTER_ARG_VALUE;
 		arg->value.type =
-			type == EVENT_DQUOTE ? FILTER_STRING : FILTER_CHAR;
+			type == TEP_EVENT_DQUOTE ? FILTER_STRING : FILTER_CHAR;
 		arg->value.str = strdup(token);
 		if (!arg->value.str) {
 			free_arg(arg);
@@ -359,7 +359,7 @@ create_arg_item(struct tep_event_format *event, const char *token,
 			return TEP_ERRNO__MEM_ALLOC_FAILED;
 		}
 		break;
-	case EVENT_ITEM:
+	case TEP_EVENT_ITEM:
 		/* if it is a number, then convert it */
 		if (isdigit(token[0])) {
 			arg->type = FILTER_ARG_VALUE;
@@ -942,7 +942,7 @@ static enum tep_errno
 process_filter(struct tep_event_format *event, struct filter_arg **parg,
 	       char *error_str, int not)
 {
-	enum event_type type;
+	enum tep_event_type type;
 	char *token = NULL;
 	struct filter_arg *current_op = NULL;
 	struct filter_arg *current_exp = NULL;
@@ -960,9 +960,9 @@ process_filter(struct tep_event_format *event, struct filter_arg **parg,
 		free(token);
 		type = read_token(&token);
 		switch (type) {
-		case EVENT_SQUOTE:
-		case EVENT_DQUOTE:
-		case EVENT_ITEM:
+		case TEP_EVENT_SQUOTE:
+		case TEP_EVENT_DQUOTE:
+		case TEP_EVENT_ITEM:
 			ret = create_arg_item(event, token, type, &arg, error_str);
 			if (ret < 0)
 				goto fail;
@@ -987,7 +987,7 @@ process_filter(struct tep_event_format *event, struct filter_arg **parg,
 			arg = NULL;
 			break;
 
-		case EVENT_DELIM:
+		case TEP_EVENT_DELIM:
 			if (*token == ',') {
 				show_error(error_str, "Illegal token ','");
 				ret = TEP_ERRNO__ILLEGAL_TOKEN;
@@ -1054,7 +1054,7 @@ process_filter(struct tep_event_format *event, struct filter_arg **parg,
 			}
 			break;
 
-		case EVENT_OP:
+		case TEP_EVENT_OP:
 			op_type = process_op(token, &btype, &ctype, &etype);
 
 			/* All expect a left arg except for NOT */
@@ -1139,14 +1139,14 @@ process_filter(struct tep_event_format *event, struct filter_arg **parg,
 			if (ret < 0)
 				goto fail_syntax;
 			break;
-		case EVENT_NONE:
+		case TEP_EVENT_NONE:
 			break;
-		case EVENT_ERROR:
+		case TEP_EVENT_ERROR:
 			goto fail_alloc;
 		default:
 			goto fail_syntax;
 		}
-	} while (type != EVENT_NONE);
+	} while (type != TEP_EVENT_NONE);
 
 	if (!current_op && !current_exp)
 		goto fail_syntax;
-- 
cgit v1.2.3


From c1953bcc73115b5f1f7e8a45f124cf9f434494cd Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Wed, 19 Sep 2018 14:56:48 -0400
Subject: tools lib traceevent: Add prefix TEP_ to all EVENT_FL_* flags

In order to make libtraceevent into a proper library, variables, data
structures and functions require a unique prefix to prevent name space
conflicts. That prefix will be "tep_". This adds prefix TEP_
to all members of nameless enum EVENT_FL_*

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lkml.kernel.org/r/20180919185723.116643250@goodmis.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.c | 42 +++++++++++++++++++-------------------
 tools/lib/traceevent/event-parse.h | 18 ++++++++--------
 2 files changed, 30 insertions(+), 30 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 1696dd9534bc..a651c3323f2c 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1382,7 +1382,7 @@ static int event_read_fields(struct tep_event_format *event, struct tep_format_f
 		 * The ftrace fields may still use the "special" name.
 		 * Just ignore it.
 		 */
-		if (event->flags & EVENT_FL_ISFTRACE &&
+		if (event->flags & TEP_EVENT_FL_ISFTRACE &&
 		    type == TEP_EVENT_ITEM && strcmp(token, "special") == 0) {
 			free_token(token);
 			type = read_token(&token);
@@ -1412,7 +1412,7 @@ static int event_read_fields(struct tep_event_format *event, struct tep_format_f
 			     * Some of the ftrace fields are broken and have
 			     * an illegal "." in them.
 			     */
-			    (event->flags & EVENT_FL_ISFTRACE &&
+			    (event->flags & TEP_EVENT_FL_ISFTRACE &&
 			     type == TEP_EVENT_OP && strcmp(token, ".") == 0)) {
 
 				if (strcmp(token, "*") == 0)
@@ -1963,7 +1963,7 @@ process_op(struct tep_event_format *event, struct print_arg *arg, char **tok)
 		arg->op.right = NULL;
 
 		if (set_op_prio(arg) == -1) {
-			event->flags |= EVENT_FL_FAILED;
+			event->flags |= TEP_EVENT_FL_FAILED;
 			/* arg->op.op (= token) will be freed at out_free */
 			arg->op.op = NULL;
 			goto out_free;
@@ -2042,7 +2042,7 @@ process_op(struct tep_event_format *event, struct print_arg *arg, char **tok)
 
 	} else {
 		do_warning_event(event, "unknown op '%s'", token);
-		event->flags |= EVENT_FL_FAILED;
+		event->flags |= TEP_EVENT_FL_FAILED;
 		/* the arg is now the left side */
 		goto out_free;
 	}
@@ -4884,13 +4884,13 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
 	int len;
 	int ls;
 
-	if (event->flags & EVENT_FL_FAILED) {
+	if (event->flags & TEP_EVENT_FL_FAILED) {
 		trace_seq_printf(s, "[FAILED TO PARSE]");
 		tep_print_fields(s, data, size, event);
 		return;
 	}
 
-	if (event->flags & EVENT_FL_ISBPRINT) {
+	if (event->flags & TEP_EVENT_FL_ISBPRINT) {
 		bprint_fmt = get_bprint_format(data, size, event);
 		args = make_bprint_args(bprint_fmt, data, size, event);
 		arg = args;
@@ -4945,7 +4945,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
 				/* The argument is the length. */
 				if (!arg) {
 					do_warning_event(event, "no argument match");
-					event->flags |= EVENT_FL_FAILED;
+					event->flags |= TEP_EVENT_FL_FAILED;
 					goto out_failed;
 				}
 				len_arg = eval_num_arg(data, size, event, arg);
@@ -4998,7 +4998,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
 			case 'u':
 				if (!arg) {
 					do_warning_event(event, "no argument match");
-					event->flags |= EVENT_FL_FAILED;
+					event->flags |= TEP_EVENT_FL_FAILED;
 					goto out_failed;
 				}
 
@@ -5008,7 +5008,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
 				/* should never happen */
 				if (len > 31) {
 					do_warning_event(event, "bad format!");
-					event->flags |= EVENT_FL_FAILED;
+					event->flags |= TEP_EVENT_FL_FAILED;
 					len = 31;
 				}
 
@@ -5074,13 +5074,13 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
 					break;
 				default:
 					do_warning_event(event, "bad count (%d)", ls);
-					event->flags |= EVENT_FL_FAILED;
+					event->flags |= TEP_EVENT_FL_FAILED;
 				}
 				break;
 			case 's':
 				if (!arg) {
 					do_warning_event(event, "no matching argument");
-					event->flags |= EVENT_FL_FAILED;
+					event->flags |= TEP_EVENT_FL_FAILED;
 					goto out_failed;
 				}
 
@@ -5090,7 +5090,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
 				/* should never happen */
 				if (len > 31) {
 					do_warning_event(event, "bad format!");
-					event->flags |= EVENT_FL_FAILED;
+					event->flags |= TEP_EVENT_FL_FAILED;
 					len = 31;
 				}
 
@@ -5115,7 +5115,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
 			trace_seq_putc(s, *ptr);
 	}
 
-	if (event->flags & EVENT_FL_FAILED) {
+	if (event->flags & TEP_EVENT_FL_FAILED) {
 out_failed:
 		trace_seq_printf(s, "[FAILED TO PARSE]");
 	}
@@ -5391,11 +5391,11 @@ void tep_event_info(struct trace_seq *s, struct tep_event_format *event,
 {
 	int print_pretty = 1;
 
-	if (event->pevent->print_raw || (event->flags & EVENT_FL_PRINTRAW))
+	if (event->pevent->print_raw || (event->flags & TEP_EVENT_FL_PRINTRAW))
 		tep_print_fields(s, record->data, record->size, event);
 	else {
 
-		if (event->handler && !(event->flags & EVENT_FL_NOHANDLE))
+		if (event->handler && !(event->flags & TEP_EVENT_FL_NOHANDLE))
 			print_pretty = event->handler(s, record, event,
 						      event->context);
 
@@ -6043,10 +6043,10 @@ enum tep_errno __tep_parse_format(struct tep_event_format **eventp,
 	}
 
 	if (strcmp(sys, "ftrace") == 0) {
-		event->flags |= EVENT_FL_ISFTRACE;
+		event->flags |= TEP_EVENT_FL_ISFTRACE;
 
 		if (strcmp(event->name, "bprint") == 0)
-			event->flags |= EVENT_FL_ISBPRINT;
+			event->flags |= TEP_EVENT_FL_ISBPRINT;
 	}
 		
 	event->id = event_read_id();
@@ -6089,7 +6089,7 @@ enum tep_errno __tep_parse_format(struct tep_event_format **eventp,
 		goto event_parse_failed;
 	}
 
-	if (!ret && (event->flags & EVENT_FL_ISFTRACE)) {
+	if (!ret && (event->flags & TEP_EVENT_FL_ISFTRACE)) {
 		struct tep_format_field *field;
 		struct print_arg *arg, **list;
 
@@ -6098,13 +6098,13 @@ enum tep_errno __tep_parse_format(struct tep_event_format **eventp,
 		for (field = event->format.fields; field; field = field->next) {
 			arg = alloc_arg();
 			if (!arg) {
-				event->flags |= EVENT_FL_FAILED;
+				event->flags |= TEP_EVENT_FL_FAILED;
 				return TEP_ERRNO__OLD_FTRACE_ARG_FAILED;
 			}
 			arg->type = PRINT_FIELD;
 			arg->field.name = strdup(field->name);
 			if (!arg->field.name) {
-				event->flags |= EVENT_FL_FAILED;
+				event->flags |= TEP_EVENT_FL_FAILED;
 				free_arg(arg);
 				return TEP_ERRNO__OLD_FTRACE_ARG_FAILED;
 			}
@@ -6118,7 +6118,7 @@ enum tep_errno __tep_parse_format(struct tep_event_format **eventp,
 	return 0;
 
  event_parse_failed:
-	event->flags |= EVENT_FL_FAILED;
+	event->flags |= TEP_EVENT_FL_FAILED;
 	return ret;
 
  event_alloc_failed:
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 10aaeda34c6b..b7798d91607e 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -290,15 +290,15 @@ struct tep_event_format {
 };
 
 enum {
-	EVENT_FL_ISFTRACE	= 0x01,
-	EVENT_FL_ISPRINT	= 0x02,
-	EVENT_FL_ISBPRINT	= 0x04,
-	EVENT_FL_ISFUNCENT	= 0x10,
-	EVENT_FL_ISFUNCRET	= 0x20,
-	EVENT_FL_NOHANDLE	= 0x40,
-	EVENT_FL_PRINTRAW	= 0x80,
-
-	EVENT_FL_FAILED		= 0x80000000
+	TEP_EVENT_FL_ISFTRACE	= 0x01,
+	TEP_EVENT_FL_ISPRINT	= 0x02,
+	TEP_EVENT_FL_ISBPRINT	= 0x04,
+	TEP_EVENT_FL_ISFUNCENT	= 0x10,
+	TEP_EVENT_FL_ISFUNCRET	= 0x20,
+	TEP_EVENT_FL_NOHANDLE	= 0x40,
+	TEP_EVENT_FL_PRINTRAW	= 0x80,
+
+	TEP_EVENT_FL_FAILED	= 0x80000000
 };
 
 enum tep_event_sort_type {
-- 
cgit v1.2.3


From 5647f94b90f6681bcc6f37abeb3bc3d1850b12cb Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Wed, 19 Sep 2018 14:56:49 -0400
Subject: tools lib traceevent, perf tools: Add prefix tep_ to all print_*
 structures

In order to make libtraceevent into a proper library, variables, data
structures and functions require a unique prefix to prevent name space
conflicts. That prefix will be "tep_". This adds prefix tep_ to all
print_* structures

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lkml.kernel.org/r/20180919185723.381753268@goodmis.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.c                 | 144 ++++++++++-----------
 tools/lib/traceevent/event-parse.h                 |  98 +++++++-------
 .../perf/util/scripting-engines/trace-event-perl.c |   6 +-
 .../util/scripting-engines/trace-event-python.c    |   4 +-
 4 files changed, 126 insertions(+), 126 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index a651c3323f2c..3beab91afded 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -95,7 +95,7 @@ struct tep_function_handler {
 
 static unsigned long long
 process_defined_func(struct trace_seq *s, void *data, int size,
-		     struct tep_event_format *event, struct print_arg *arg);
+		     struct tep_event_format *event, struct tep_print_arg *arg);
 
 static void free_func_handle(struct tep_function_handler *func);
 
@@ -118,9 +118,9 @@ void breakpoint(void)
 	x++;
 }
 
-struct print_arg *alloc_arg(void)
+struct tep_print_arg *alloc_arg(void)
 {
-	return calloc(1, sizeof(struct print_arg));
+	return calloc(1, sizeof(struct tep_print_arg));
 }
 
 struct cmdline {
@@ -781,9 +781,9 @@ static int event_item_type(enum tep_event_type type)
 	}
 }
 
-static void free_flag_sym(struct print_flag_sym *fsym)
+static void free_flag_sym(struct tep_print_flag_sym *fsym)
 {
-	struct print_flag_sym *next;
+	struct tep_print_flag_sym *next;
 
 	while (fsym) {
 		next = fsym->next;
@@ -794,9 +794,9 @@ static void free_flag_sym(struct print_flag_sym *fsym)
 	}
 }
 
-static void free_arg(struct print_arg *arg)
+static void free_arg(struct tep_print_arg *arg)
 {
-	struct print_arg *farg;
+	struct tep_print_arg *farg;
 
 	if (!arg)
 		return;
@@ -1674,11 +1674,11 @@ static int event_read_format(struct tep_event_format *event)
 }
 
 static enum tep_event_type
-process_arg_token(struct tep_event_format *event, struct print_arg *arg,
+process_arg_token(struct tep_event_format *event, struct tep_print_arg *arg,
 		  char **tok, enum tep_event_type type);
 
 static enum tep_event_type
-process_arg(struct tep_event_format *event, struct print_arg *arg, char **tok)
+process_arg(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
 	enum tep_event_type type;
 	char *token;
@@ -1690,14 +1690,14 @@ process_arg(struct tep_event_format *event, struct print_arg *arg, char **tok)
 }
 
 static enum tep_event_type
-process_op(struct tep_event_format *event, struct print_arg *arg, char **tok);
+process_op(struct tep_event_format *event, struct tep_print_arg *arg, char **tok);
 
 /*
  * For __print_symbolic() and __print_flags, we need to completely
  * evaluate the first argument, which defines what to print next.
  */
 static enum tep_event_type
-process_field_arg(struct tep_event_format *event, struct print_arg *arg, char **tok)
+process_field_arg(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
 	enum tep_event_type type;
 
@@ -1711,9 +1711,9 @@ process_field_arg(struct tep_event_format *event, struct print_arg *arg, char **
 }
 
 static enum tep_event_type
-process_cond(struct tep_event_format *event, struct print_arg *top, char **tok)
+process_cond(struct tep_event_format *event, struct tep_print_arg *top, char **tok)
 {
-	struct print_arg *arg, *left, *right;
+	struct tep_print_arg *arg, *left, *right;
 	enum tep_event_type type;
 	char *token = NULL;
 
@@ -1767,9 +1767,9 @@ out_free:
 }
 
 static enum tep_event_type
-process_array(struct tep_event_format *event, struct print_arg *top, char **tok)
+process_array(struct tep_event_format *event, struct tep_print_arg *top, char **tok)
 {
-	struct print_arg *arg;
+	struct tep_print_arg *arg;
 	enum tep_event_type type;
 	char *token = NULL;
 
@@ -1855,7 +1855,7 @@ static int get_op_prio(char *op)
 	}
 }
 
-static int set_op_prio(struct print_arg *arg)
+static int set_op_prio(struct tep_print_arg *arg)
 {
 
 	/* single ops are the greatest */
@@ -1869,9 +1869,9 @@ static int set_op_prio(struct print_arg *arg)
 
 /* Note, *tok does not get freed, but will most likely be saved */
 static enum tep_event_type
-process_op(struct tep_event_format *event, struct print_arg *arg, char **tok)
+process_op(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
-	struct print_arg *left, *right = NULL;
+	struct tep_print_arg *left, *right = NULL;
 	enum tep_event_type type;
 	char *token;
 
@@ -2009,7 +2009,7 @@ process_op(struct tep_event_format *event, struct print_arg *arg, char **tok)
 
 		if (right->type == PRINT_OP &&
 		    get_op_prio(arg->op.op) < get_op_prio(right->op.op)) {
-			struct print_arg tmp;
+			struct tep_print_arg tmp;
 
 			/* rotate ops according to the priority */
 			arg->op.right = right->op.left;
@@ -2070,7 +2070,7 @@ out_free:
 }
 
 static enum tep_event_type
-process_entry(struct tep_event_format *event __maybe_unused, struct print_arg *arg,
+process_entry(struct tep_event_format *event __maybe_unused, struct tep_print_arg *arg,
 	      char **tok)
 {
 	enum tep_event_type type;
@@ -2110,9 +2110,9 @@ process_entry(struct tep_event_format *event __maybe_unused, struct print_arg *a
 }
 
 static int alloc_and_process_delim(struct tep_event_format *event, char *next_token,
-				   struct print_arg **print_arg)
+				   struct tep_print_arg **print_arg)
 {
-	struct print_arg *field;
+	struct tep_print_arg *field;
 	enum tep_event_type type;
 	char *token;
 	int ret = 0;
@@ -2141,7 +2141,7 @@ out_free_token:
 	return ret;
 }
 
-static char *arg_eval (struct print_arg *arg);
+static char *arg_eval (struct tep_print_arg *arg);
 
 static unsigned long long
 eval_type_str(unsigned long long val, const char *type, int pointer)
@@ -2238,7 +2238,7 @@ eval_type_str(unsigned long long val, const char *type, int pointer)
  * Try to figure out the type.
  */
 static unsigned long long
-eval_type(unsigned long long val, struct print_arg *arg, int pointer)
+eval_type(unsigned long long val, struct tep_print_arg *arg, int pointer)
 {
 	if (arg->type != PRINT_TYPE) {
 		do_warning("expected type argument");
@@ -2248,7 +2248,7 @@ eval_type(unsigned long long val, struct print_arg *arg, int pointer)
 	return eval_type_str(val, arg->typecast.type, pointer);
 }
 
-static int arg_num_eval(struct print_arg *arg, long long *val)
+static int arg_num_eval(struct tep_print_arg *arg, long long *val)
 {
 	long long left, right;
 	int ret = 1;
@@ -2414,7 +2414,7 @@ static int arg_num_eval(struct print_arg *arg, long long *val)
 	return ret;
 }
 
-static char *arg_eval (struct print_arg *arg)
+static char *arg_eval (struct tep_print_arg *arg)
 {
 	long long val;
 	static char buf[20];
@@ -2444,11 +2444,11 @@ static char *arg_eval (struct print_arg *arg)
 }
 
 static enum tep_event_type
-process_fields(struct tep_event_format *event, struct print_flag_sym **list, char **tok)
+process_fields(struct tep_event_format *event, struct tep_print_flag_sym **list, char **tok)
 {
 	enum tep_event_type type;
-	struct print_arg *arg = NULL;
-	struct print_flag_sym *field;
+	struct tep_print_arg *arg = NULL;
+	struct tep_print_flag_sym *field;
 	char *token = *tok;
 	char *value;
 
@@ -2525,9 +2525,9 @@ out_free:
 }
 
 static enum tep_event_type
-process_flags(struct tep_event_format *event, struct print_arg *arg, char **tok)
+process_flags(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
-	struct print_arg *field;
+	struct tep_print_arg *field;
 	enum tep_event_type type;
 	char *token = NULL;
 
@@ -2578,9 +2578,9 @@ out_free:
 }
 
 static enum tep_event_type
-process_symbols(struct tep_event_format *event, struct print_arg *arg, char **tok)
+process_symbols(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
-	struct print_arg *field;
+	struct tep_print_arg *field;
 	enum tep_event_type type;
 	char *token = NULL;
 
@@ -2617,7 +2617,7 @@ out_free:
 }
 
 static enum tep_event_type
-process_hex_common(struct tep_event_format *event, struct print_arg *arg,
+process_hex_common(struct tep_event_format *event, struct tep_print_arg *arg,
 		   char **tok, enum print_arg_type type)
 {
 	memset(arg, 0, sizeof(*arg));
@@ -2640,20 +2640,20 @@ out:
 }
 
 static enum tep_event_type
-process_hex(struct tep_event_format *event, struct print_arg *arg, char **tok)
+process_hex(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
 	return process_hex_common(event, arg, tok, PRINT_HEX);
 }
 
 static enum tep_event_type
-process_hex_str(struct tep_event_format *event, struct print_arg *arg,
+process_hex_str(struct tep_event_format *event, struct tep_print_arg *arg,
 		char **tok)
 {
 	return process_hex_common(event, arg, tok, PRINT_HEX_STR);
 }
 
 static enum tep_event_type
-process_int_array(struct tep_event_format *event, struct print_arg *arg, char **tok)
+process_int_array(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
 	memset(arg, 0, sizeof(*arg));
 	arg->type = PRINT_INT_ARRAY;
@@ -2681,7 +2681,7 @@ out:
 }
 
 static enum tep_event_type
-process_dynamic_array(struct tep_event_format *event, struct print_arg *arg, char **tok)
+process_dynamic_array(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
 	struct tep_format_field *field;
 	enum tep_event_type type;
@@ -2745,7 +2745,7 @@ process_dynamic_array(struct tep_event_format *event, struct print_arg *arg, cha
 }
 
 static enum tep_event_type
-process_dynamic_array_len(struct tep_event_format *event, struct print_arg *arg,
+process_dynamic_array_len(struct tep_event_format *event, struct tep_print_arg *arg,
 			  char **tok)
 {
 	struct tep_format_field *field;
@@ -2781,9 +2781,9 @@ process_dynamic_array_len(struct tep_event_format *event, struct print_arg *arg,
 }
 
 static enum tep_event_type
-process_paren(struct tep_event_format *event, struct print_arg *arg, char **tok)
+process_paren(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
-	struct print_arg *item_arg;
+	struct tep_print_arg *item_arg;
 	enum tep_event_type type;
 	char *token;
 
@@ -2844,7 +2844,7 @@ process_paren(struct tep_event_format *event, struct print_arg *arg, char **tok)
 
 
 static enum tep_event_type
-process_str(struct tep_event_format *event __maybe_unused, struct print_arg *arg,
+process_str(struct tep_event_format *event __maybe_unused, struct tep_print_arg *arg,
 	    char **tok)
 {
 	enum tep_event_type type;
@@ -2873,7 +2873,7 @@ process_str(struct tep_event_format *event __maybe_unused, struct print_arg *arg
 }
 
 static enum tep_event_type
-process_bitmask(struct tep_event_format *event __maybe_unused, struct print_arg *arg,
+process_bitmask(struct tep_event_format *event __maybe_unused, struct tep_print_arg *arg,
 		char **tok)
 {
 	enum tep_event_type type;
@@ -2935,10 +2935,10 @@ static void remove_func_handler(struct tep_handle *pevent, char *func_name)
 
 static enum tep_event_type
 process_func_handler(struct tep_event_format *event, struct tep_function_handler *func,
-		     struct print_arg *arg, char **tok)
+		     struct tep_print_arg *arg, char **tok)
 {
-	struct print_arg **next_arg;
-	struct print_arg *farg;
+	struct tep_print_arg **next_arg;
+	struct tep_print_arg *farg;
 	enum tep_event_type type;
 	char *token;
 	int i;
@@ -2992,7 +2992,7 @@ err:
 }
 
 static enum tep_event_type
-process_function(struct tep_event_format *event, struct print_arg *arg,
+process_function(struct tep_event_format *event, struct tep_print_arg *arg,
 		 char *token, char **tok)
 {
 	struct tep_function_handler *func;
@@ -3048,7 +3048,7 @@ process_function(struct tep_event_format *event, struct print_arg *arg,
 }
 
 static enum tep_event_type
-process_arg_token(struct tep_event_format *event, struct print_arg *arg,
+process_arg_token(struct tep_event_format *event, struct tep_print_arg *arg,
 		  char **tok, enum tep_event_type type)
 {
 	char *token;
@@ -3136,10 +3136,10 @@ process_arg_token(struct tep_event_format *event, struct print_arg *arg,
 	return type;
 }
 
-static int event_read_print_args(struct tep_event_format *event, struct print_arg **list)
+static int event_read_print_args(struct tep_event_format *event, struct tep_print_arg **list)
 {
 	enum tep_event_type type = TEP_EVENT_ERROR;
-	struct print_arg *arg;
+	struct tep_print_arg *arg;
 	char *token;
 	int args = 0;
 
@@ -3522,13 +3522,13 @@ tep_find_event_by_name(struct tep_handle *pevent,
 }
 
 static unsigned long long
-eval_num_arg(void *data, int size, struct tep_event_format *event, struct print_arg *arg)
+eval_num_arg(void *data, int size, struct tep_event_format *event, struct tep_print_arg *arg)
 {
 	struct tep_handle *pevent = event->pevent;
 	unsigned long long val = 0;
 	unsigned long long left, right;
-	struct print_arg *typearg = NULL;
-	struct print_arg *larg;
+	struct tep_print_arg *typearg = NULL;
+	struct tep_print_arg *larg;
 	unsigned long offset;
 	unsigned int field_size;
 
@@ -3863,10 +3863,10 @@ static void print_bitmask_to_seq(struct tep_handle *pevent,
 
 static void print_str_arg(struct trace_seq *s, void *data, int size,
 			  struct tep_event_format *event, const char *format,
-			  int len_arg, struct print_arg *arg)
+			  int len_arg, struct tep_print_arg *arg)
 {
 	struct tep_handle *pevent = event->pevent;
-	struct print_flag_sym *flag;
+	struct tep_print_flag_sym *flag;
 	struct tep_format_field *field;
 	struct printk_map *printk;
 	long long val, fval;
@@ -4117,13 +4117,13 @@ out_warning_field:
 
 static unsigned long long
 process_defined_func(struct trace_seq *s, void *data, int size,
-		     struct tep_event_format *event, struct print_arg *arg)
+		     struct tep_event_format *event, struct tep_print_arg *arg)
 {
 	struct tep_function_handler *func_handle = arg->func.func;
 	struct func_params *param;
 	unsigned long long *args;
 	unsigned long long ret;
-	struct print_arg *farg;
+	struct tep_print_arg *farg;
 	struct trace_seq str;
 	struct save_str {
 		struct save_str *next;
@@ -4200,9 +4200,9 @@ out_free:
 	return ret;
 }
 
-static void free_args(struct print_arg *args)
+static void free_args(struct tep_print_arg *args)
 {
-	struct print_arg *next;
+	struct tep_print_arg *next;
 
 	while (args) {
 		next = args->next;
@@ -4212,11 +4212,11 @@ static void free_args(struct print_arg *args)
 	}
 }
 
-static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struct tep_event_format *event)
+static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, struct tep_event_format *event)
 {
 	struct tep_handle *pevent = event->pevent;
 	struct tep_format_field *field, *ip_field;
-	struct print_arg *args, *arg, **next;
+	struct tep_print_arg *args, *arg, **next;
 	unsigned long long ip, val;
 	char *ptr;
 	void *bptr;
@@ -4424,7 +4424,7 @@ get_bprint_format(void *data, int size __maybe_unused,
 }
 
 static void print_mac_arg(struct trace_seq *s, int mac, void *data, int size,
-			  struct tep_event_format *event, struct print_arg *arg)
+			  struct tep_event_format *event, struct tep_print_arg *arg)
 {
 	unsigned char *buf;
 	const char *fmt = "%.2x:%.2x:%.2x:%.2x:%.2x:%.2x";
@@ -4578,7 +4578,7 @@ static void print_ip6_addr(struct trace_seq *s, char i, unsigned char *buf)
  */
 static int print_ipv4_arg(struct trace_seq *s, const char *ptr, char i,
 			  void *data, int size, struct tep_event_format *event,
-			  struct print_arg *arg)
+			  struct tep_print_arg *arg)
 {
 	unsigned char *buf;
 
@@ -4615,7 +4615,7 @@ static int print_ipv4_arg(struct trace_seq *s, const char *ptr, char i,
 
 static int print_ipv6_arg(struct trace_seq *s, const char *ptr, char i,
 			  void *data, int size, struct tep_event_format *event,
-			  struct print_arg *arg)
+			  struct tep_print_arg *arg)
 {
 	char have_c = 0;
 	unsigned char *buf;
@@ -4665,7 +4665,7 @@ static int print_ipv6_arg(struct trace_seq *s, const char *ptr, char i,
 
 static int print_ipsa_arg(struct trace_seq *s, const char *ptr, char i,
 			  void *data, int size, struct tep_event_format *event,
-			  struct print_arg *arg)
+			  struct tep_print_arg *arg)
 {
 	char have_c = 0, have_p = 0;
 	unsigned char *buf;
@@ -4747,7 +4747,7 @@ static int print_ipsa_arg(struct trace_seq *s, const char *ptr, char i,
 
 static int print_ip_arg(struct trace_seq *s, const char *ptr,
 			void *data, int size, struct tep_event_format *event,
-			struct print_arg *arg)
+			struct tep_print_arg *arg)
 {
 	char i = *ptr;  /* 'i' or 'I' */
 	char ver;
@@ -4868,9 +4868,9 @@ void tep_print_fields(struct trace_seq *s, void *data,
 static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_event_format *event)
 {
 	struct tep_handle *pevent = event->pevent;
-	struct print_fmt *print_fmt = &event->print_fmt;
-	struct print_arg *arg = print_fmt->args;
-	struct print_arg *args = NULL;
+	struct tep_print_fmt *print_fmt = &event->print_fmt;
+	struct tep_print_arg *arg = print_fmt->args;
+	struct tep_print_arg *args = NULL;
 	const char *ptr = print_fmt->format;
 	unsigned long long val;
 	struct func_map *func;
@@ -5723,7 +5723,7 @@ struct tep_format_field **tep_event_fields(struct tep_event_format *event)
 				event->format.fields);
 }
 
-static void print_fields(struct trace_seq *s, struct print_flag_sym *field)
+static void print_fields(struct trace_seq *s, struct tep_print_flag_sym *field)
 {
 	trace_seq_printf(s, "{ %s, %s }", field->value, field->str);
 	if (field->next) {
@@ -5733,7 +5733,7 @@ static void print_fields(struct trace_seq *s, struct print_flag_sym *field)
 }
 
 /* for debugging */
-static void print_args(struct print_arg *args)
+static void print_args(struct tep_print_arg *args)
 {
 	int print_paren = 1;
 	struct trace_seq s;
@@ -6091,7 +6091,7 @@ enum tep_errno __tep_parse_format(struct tep_event_format **eventp,
 
 	if (!ret && (event->flags & TEP_EVENT_FL_ISFTRACE)) {
 		struct tep_format_field *field;
-		struct print_arg *arg, **list;
+		struct tep_print_arg *arg, **list;
 
 		/* old ftrace had no args */
 		list = &event->print_fmt.args;
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index b7798d91607e..21923a11c9c0 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -161,77 +161,77 @@ struct tep_format {
 	struct tep_format_field	*fields;
 };
 
-struct print_arg_atom {
+struct tep_print_arg_atom {
 	char			*atom;
 };
 
-struct print_arg_string {
+struct tep_print_arg_string {
 	char			*string;
 	int			offset;
 };
 
-struct print_arg_bitmask {
+struct tep_print_arg_bitmask {
 	char			*bitmask;
 	int			offset;
 };
 
-struct print_arg_field {
+struct tep_print_arg_field {
 	char			*name;
 	struct tep_format_field	*field;
 };
 
-struct print_flag_sym {
-	struct print_flag_sym	*next;
-	char			*value;
-	char			*str;
+struct tep_print_flag_sym {
+	struct tep_print_flag_sym	*next;
+	char				*value;
+	char				*str;
 };
 
-struct print_arg_typecast {
+struct tep_print_arg_typecast {
 	char 			*type;
-	struct print_arg	*item;
+	struct tep_print_arg	*item;
 };
 
-struct print_arg_flags {
-	struct print_arg	*field;
-	char			*delim;
-	struct print_flag_sym	*flags;
+struct tep_print_arg_flags {
+	struct tep_print_arg		*field;
+	char				*delim;
+	struct tep_print_flag_sym	*flags;
 };
 
-struct print_arg_symbol {
-	struct print_arg	*field;
-	struct print_flag_sym	*symbols;
+struct tep_print_arg_symbol {
+	struct tep_print_arg		*field;
+	struct tep_print_flag_sym	*symbols;
 };
 
-struct print_arg_hex {
-	struct print_arg	*field;
-	struct print_arg	*size;
+struct tep_print_arg_hex {
+	struct tep_print_arg	*field;
+	struct tep_print_arg	*size;
 };
 
-struct print_arg_int_array {
-	struct print_arg	*field;
-	struct print_arg	*count;
-	struct print_arg	*el_size;
+struct tep_print_arg_int_array {
+	struct tep_print_arg	*field;
+	struct tep_print_arg	*count;
+	struct tep_print_arg	*el_size;
 };
 
-struct print_arg_dynarray {
+struct tep_print_arg_dynarray {
 	struct tep_format_field	*field;
-	struct print_arg	*index;
+	struct tep_print_arg	*index;
 };
 
-struct print_arg;
+struct tep_print_arg;
 
-struct print_arg_op {
+struct tep_print_arg_op {
 	char			*op;
 	int			prio;
-	struct print_arg	*left;
-	struct print_arg	*right;
+	struct tep_print_arg	*left;
+	struct tep_print_arg	*right;
 };
 
 struct tep_function_handler;
 
-struct print_arg_func {
+struct tep_print_arg_func {
 	struct tep_function_handler	*func;
-	struct print_arg		*args;
+	struct tep_print_arg		*args;
 };
 
 enum print_arg_type {
@@ -253,28 +253,28 @@ enum print_arg_type {
 	PRINT_HEX_STR,
 };
 
-struct print_arg {
-	struct print_arg		*next;
+struct tep_print_arg {
+	struct tep_print_arg		*next;
 	enum print_arg_type		type;
 	union {
-		struct print_arg_atom		atom;
-		struct print_arg_field		field;
-		struct print_arg_typecast	typecast;
-		struct print_arg_flags		flags;
-		struct print_arg_symbol		symbol;
-		struct print_arg_hex		hex;
-		struct print_arg_int_array	int_array;
-		struct print_arg_func		func;
-		struct print_arg_string		string;
-		struct print_arg_bitmask	bitmask;
-		struct print_arg_op		op;
-		struct print_arg_dynarray	dynarray;
+		struct tep_print_arg_atom	atom;
+		struct tep_print_arg_field	field;
+		struct tep_print_arg_typecast	typecast;
+		struct tep_print_arg_flags	flags;
+		struct tep_print_arg_symbol	symbol;
+		struct tep_print_arg_hex	hex;
+		struct tep_print_arg_int_array	int_array;
+		struct tep_print_arg_func	func;
+		struct tep_print_arg_string	string;
+		struct tep_print_arg_bitmask	bitmask;
+		struct tep_print_arg_op		op;
+		struct tep_print_arg_dynarray	dynarray;
 	};
 };
 
-struct print_fmt {
+struct tep_print_fmt {
 	char			*format;
-	struct print_arg	*args;
+	struct tep_print_arg	*args;
 };
 
 struct tep_event_format {
@@ -283,7 +283,7 @@ struct tep_event_format {
 	int			id;
 	int			flags;
 	struct tep_format	format;
-	struct print_fmt	print_fmt;
+	struct tep_print_fmt	print_fmt;
 	char			*system;
 	tep_event_handler_func	handler;
 	void			*context;
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 5d6a55183ad6..481a1ecb1eaf 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -99,7 +99,7 @@ static void define_symbolic_value(const char *ev_name,
 	LEAVE;
 }
 
-static void define_symbolic_values(struct print_flag_sym *field,
+static void define_symbolic_values(struct tep_print_flag_sym *field,
 				   const char *ev_name,
 				   const char *field_name)
 {
@@ -157,7 +157,7 @@ static void define_flag_value(const char *ev_name,
 	LEAVE;
 }
 
-static void define_flag_values(struct print_flag_sym *field,
+static void define_flag_values(struct tep_print_flag_sym *field,
 			       const char *ev_name,
 			       const char *field_name)
 {
@@ -191,7 +191,7 @@ static void define_flag_field(const char *ev_name,
 
 static void define_event_symbols(struct tep_event_format *event,
 				 const char *ev_name,
-				 struct print_arg *args)
+				 struct tep_print_arg *args)
 {
 	if (args == NULL)
 		return;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index ba191def1ea9..35dc5f3b581b 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -224,7 +224,7 @@ static void define_value(enum print_arg_type field_type,
 }
 
 static void define_values(enum print_arg_type field_type,
-			  struct print_flag_sym *field,
+			  struct tep_print_flag_sym *field,
 			  const char *ev_name,
 			  const char *field_name)
 {
@@ -266,7 +266,7 @@ static void define_field(enum print_arg_type field_type,
 
 static void define_event_symbols(struct tep_event_format *event,
 				 const char *ev_name,
-				 struct print_arg *args)
+				 struct tep_print_arg *args)
 {
 	if (args == NULL)
 		return;
-- 
cgit v1.2.3


From 1e97216f20330fb001f57d0f6f48e76c060bfd16 Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Wed, 19 Sep 2018 14:56:50 -0400
Subject: tools lib traceevent, perf tools: Rename enum print_arg_type to enum
 tep_print_arg_type

In order to make libtraceevent into a proper library, variables, data
structures and functions require a unique prefix to prevent name space
conflicts. That prefix will be "tep_". This renames enum print_arg_type to
enum tep_print_arg_type and add prefix TEP_ to all its members.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lkml.kernel.org/r/20180919185723.533960748@goodmis.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.c                 | 248 ++++++++++-----------
 tools/lib/traceevent/event-parse.h                 |  36 +--
 .../perf/util/scripting-engines/trace-event-perl.c |  32 +--
 .../util/scripting-engines/trace-event-python.c    |  56 ++---
 4 files changed, 186 insertions(+), 186 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 3beab91afded..055bee7b738a 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -802,52 +802,52 @@ static void free_arg(struct tep_print_arg *arg)
 		return;
 
 	switch (arg->type) {
-	case PRINT_ATOM:
+	case TEP_PRINT_ATOM:
 		free(arg->atom.atom);
 		break;
-	case PRINT_FIELD:
+	case TEP_PRINT_FIELD:
 		free(arg->field.name);
 		break;
-	case PRINT_FLAGS:
+	case TEP_PRINT_FLAGS:
 		free_arg(arg->flags.field);
 		free(arg->flags.delim);
 		free_flag_sym(arg->flags.flags);
 		break;
-	case PRINT_SYMBOL:
+	case TEP_PRINT_SYMBOL:
 		free_arg(arg->symbol.field);
 		free_flag_sym(arg->symbol.symbols);
 		break;
-	case PRINT_HEX:
-	case PRINT_HEX_STR:
+	case TEP_PRINT_HEX:
+	case TEP_PRINT_HEX_STR:
 		free_arg(arg->hex.field);
 		free_arg(arg->hex.size);
 		break;
-	case PRINT_INT_ARRAY:
+	case TEP_PRINT_INT_ARRAY:
 		free_arg(arg->int_array.field);
 		free_arg(arg->int_array.count);
 		free_arg(arg->int_array.el_size);
 		break;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		free(arg->typecast.type);
 		free_arg(arg->typecast.item);
 		break;
-	case PRINT_STRING:
-	case PRINT_BSTRING:
+	case TEP_PRINT_STRING:
+	case TEP_PRINT_BSTRING:
 		free(arg->string.string);
 		break;
-	case PRINT_BITMASK:
+	case TEP_PRINT_BITMASK:
 		free(arg->bitmask.bitmask);
 		break;
-	case PRINT_DYNAMIC_ARRAY:
-	case PRINT_DYNAMIC_ARRAY_LEN:
+	case TEP_PRINT_DYNAMIC_ARRAY:
+	case TEP_PRINT_DYNAMIC_ARRAY_LEN:
 		free(arg->dynarray.index);
 		break;
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		free(arg->op.op);
 		free_arg(arg->op.left);
 		free_arg(arg->op.right);
 		break;
-	case PRINT_FUNC:
+	case TEP_PRINT_FUNC:
 		while (arg->func.args) {
 			farg = arg->func.args;
 			arg->func.args = farg->next;
@@ -855,7 +855,7 @@ static void free_arg(struct tep_print_arg *arg)
 		}
 		break;
 
-	case PRINT_NULL:
+	case TEP_PRINT_NULL:
 	default:
 		break;
 	}
@@ -1729,7 +1729,7 @@ process_cond(struct tep_event_format *event, struct tep_print_arg *top, char **t
 		goto out_free;
 	}
 
-	arg->type = PRINT_OP;
+	arg->type = TEP_PRINT_OP;
 	arg->op.left = left;
 	arg->op.right = right;
 
@@ -1859,7 +1859,7 @@ static int set_op_prio(struct tep_print_arg *arg)
 {
 
 	/* single ops are the greatest */
-	if (!arg->op.left || arg->op.left->type == PRINT_NULL)
+	if (!arg->op.left || arg->op.left->type == TEP_PRINT_NULL)
 		arg->op.prio = 0;
 	else
 		arg->op.prio = get_op_prio(arg->op.op);
@@ -1878,7 +1878,7 @@ process_op(struct tep_event_format *event, struct tep_print_arg *arg, char **tok
 	/* the op is passed in via tok */
 	token = *tok;
 
-	if (arg->type == PRINT_OP && !arg->op.left) {
+	if (arg->type == TEP_PRINT_OP && !arg->op.left) {
 		/* handle single op */
 		if (token[1]) {
 			do_warning_event(event, "bad op token %s", token);
@@ -1901,7 +1901,7 @@ process_op(struct tep_event_format *event, struct tep_print_arg *arg, char **tok
 		if (!left)
 			goto out_warn_free;
 
-		left->type = PRINT_NULL;
+		left->type = TEP_PRINT_NULL;
 		arg->op.left = left;
 
 		right = alloc_arg();
@@ -1923,7 +1923,7 @@ process_op(struct tep_event_format *event, struct tep_print_arg *arg, char **tok
 		/* copy the top arg to the left */
 		*left = *arg;
 
-		arg->type = PRINT_OP;
+		arg->type = TEP_PRINT_OP;
 		arg->op.op = token;
 		arg->op.left = left;
 		arg->op.prio = 0;
@@ -1957,7 +1957,7 @@ process_op(struct tep_event_format *event, struct tep_print_arg *arg, char **tok
 		/* copy the top arg to the left */
 		*left = *arg;
 
-		arg->type = PRINT_OP;
+		arg->type = TEP_PRINT_OP;
 		arg->op.op = token;
 		arg->op.left = left;
 		arg->op.right = NULL;
@@ -1977,7 +1977,7 @@ process_op(struct tep_event_format *event, struct tep_print_arg *arg, char **tok
 		    type == TEP_EVENT_DELIM && (strcmp(token, ")") == 0)) {
 			char *new_atom;
 
-			if (left->type != PRINT_ATOM) {
+			if (left->type != TEP_PRINT_ATOM) {
 				do_warning_event(event, "bad pointer type");
 				goto out_free;
 			}
@@ -2007,7 +2007,7 @@ process_op(struct tep_event_format *event, struct tep_print_arg *arg, char **tok
 			goto out_free;
 		}
 
-		if (right->type == PRINT_OP &&
+		if (right->type == TEP_PRINT_OP &&
 		    get_op_prio(arg->op.op) < get_op_prio(right->op.op)) {
 			struct tep_print_arg tmp;
 
@@ -2031,7 +2031,7 @@ process_op(struct tep_event_format *event, struct tep_print_arg *arg, char **tok
 
 		*left = *arg;
 
-		arg->type = PRINT_OP;
+		arg->type = TEP_PRINT_OP;
 		arg->op.op = token;
 		arg->op.left = left;
 
@@ -2084,7 +2084,7 @@ process_entry(struct tep_event_format *event __maybe_unused, struct tep_print_ar
 		goto out_free;
 	field = token;
 
-	arg->type = PRINT_FIELD;
+	arg->type = TEP_PRINT_FIELD;
 	arg->field.name = field;
 
 	if (is_flag_field) {
@@ -2240,7 +2240,7 @@ eval_type_str(unsigned long long val, const char *type, int pointer)
 static unsigned long long
 eval_type(unsigned long long val, struct tep_print_arg *arg, int pointer)
 {
-	if (arg->type != PRINT_TYPE) {
+	if (arg->type != TEP_PRINT_TYPE) {
 		do_warning("expected type argument");
 		return 0;
 	}
@@ -2254,16 +2254,16 @@ static int arg_num_eval(struct tep_print_arg *arg, long long *val)
 	int ret = 1;
 
 	switch (arg->type) {
-	case PRINT_ATOM:
+	case TEP_PRINT_ATOM:
 		*val = strtoll(arg->atom.atom, NULL, 0);
 		break;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		ret = arg_num_eval(arg->typecast.item, val);
 		if (!ret)
 			break;
 		*val = eval_type(*val, arg, 0);
 		break;
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		switch (arg->op.op[0]) {
 		case '|':
 			ret = arg_num_eval(arg->op.left, &left);
@@ -2366,7 +2366,7 @@ static int arg_num_eval(struct tep_print_arg *arg, long long *val)
 			break;
 		case '-':
 			/* check for negative */
-			if (arg->op.left->type == PRINT_NULL)
+			if (arg->op.left->type == TEP_PRINT_NULL)
 				left = 0;
 			else
 				ret = arg_num_eval(arg->op.left, &left);
@@ -2378,7 +2378,7 @@ static int arg_num_eval(struct tep_print_arg *arg, long long *val)
 			*val = left - right;
 			break;
 		case '+':
-			if (arg->op.left->type == PRINT_NULL)
+			if (arg->op.left->type == TEP_PRINT_NULL)
 				left = 0;
 			else
 				ret = arg_num_eval(arg->op.left, &left);
@@ -2401,11 +2401,11 @@ static int arg_num_eval(struct tep_print_arg *arg, long long *val)
 		}
 		break;
 
-	case PRINT_NULL:
-	case PRINT_FIELD ... PRINT_SYMBOL:
-	case PRINT_STRING:
-	case PRINT_BSTRING:
-	case PRINT_BITMASK:
+	case TEP_PRINT_NULL:
+	case TEP_PRINT_FIELD ... TEP_PRINT_SYMBOL:
+	case TEP_PRINT_STRING:
+	case TEP_PRINT_BSTRING:
+	case TEP_PRINT_BITMASK:
 	default:
 		do_warning("invalid eval type %d", arg->type);
 		ret = 0;
@@ -2420,21 +2420,21 @@ static char *arg_eval (struct tep_print_arg *arg)
 	static char buf[20];
 
 	switch (arg->type) {
-	case PRINT_ATOM:
+	case TEP_PRINT_ATOM:
 		return arg->atom.atom;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		return arg_eval(arg->typecast.item);
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		if (!arg_num_eval(arg, &val))
 			break;
 		sprintf(buf, "%lld", val);
 		return buf;
 
-	case PRINT_NULL:
-	case PRINT_FIELD ... PRINT_SYMBOL:
-	case PRINT_STRING:
-	case PRINT_BSTRING:
-	case PRINT_BITMASK:
+	case TEP_PRINT_NULL:
+	case TEP_PRINT_FIELD ... TEP_PRINT_SYMBOL:
+	case TEP_PRINT_STRING:
+	case TEP_PRINT_BSTRING:
+	case TEP_PRINT_BITMASK:
 	default:
 		do_warning("invalid eval type %d", arg->type);
 		break;
@@ -2532,7 +2532,7 @@ process_flags(struct tep_event_format *event, struct tep_print_arg *arg, char **
 	char *token = NULL;
 
 	memset(arg, 0, sizeof(*arg));
-	arg->type = PRINT_FLAGS;
+	arg->type = TEP_PRINT_FLAGS;
 
 	field = alloc_arg();
 	if (!field) {
@@ -2585,7 +2585,7 @@ process_symbols(struct tep_event_format *event, struct tep_print_arg *arg, char
 	char *token = NULL;
 
 	memset(arg, 0, sizeof(*arg));
-	arg->type = PRINT_SYMBOL;
+	arg->type = TEP_PRINT_SYMBOL;
 
 	field = alloc_arg();
 	if (!field) {
@@ -2618,7 +2618,7 @@ out_free:
 
 static enum tep_event_type
 process_hex_common(struct tep_event_format *event, struct tep_print_arg *arg,
-		   char **tok, enum print_arg_type type)
+		   char **tok, enum tep_print_arg_type type)
 {
 	memset(arg, 0, sizeof(*arg));
 	arg->type = type;
@@ -2642,21 +2642,21 @@ out:
 static enum tep_event_type
 process_hex(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
-	return process_hex_common(event, arg, tok, PRINT_HEX);
+	return process_hex_common(event, arg, tok, TEP_PRINT_HEX);
 }
 
 static enum tep_event_type
 process_hex_str(struct tep_event_format *event, struct tep_print_arg *arg,
 		char **tok)
 {
-	return process_hex_common(event, arg, tok, PRINT_HEX_STR);
+	return process_hex_common(event, arg, tok, TEP_PRINT_HEX_STR);
 }
 
 static enum tep_event_type
 process_int_array(struct tep_event_format *event, struct tep_print_arg *arg, char **tok)
 {
 	memset(arg, 0, sizeof(*arg));
-	arg->type = PRINT_INT_ARRAY;
+	arg->type = TEP_PRINT_INT_ARRAY;
 
 	if (alloc_and_process_delim(event, ",", &arg->int_array.field))
 		goto out;
@@ -2688,7 +2688,7 @@ process_dynamic_array(struct tep_event_format *event, struct tep_print_arg *arg,
 	char *token;
 
 	memset(arg, 0, sizeof(*arg));
-	arg->type = PRINT_DYNAMIC_ARRAY;
+	arg->type = TEP_PRINT_DYNAMIC_ARRAY;
 
 	/*
 	 * The item within the parenthesis is another field that holds
@@ -2755,7 +2755,7 @@ process_dynamic_array_len(struct tep_event_format *event, struct tep_print_arg *
 	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto out_free;
 
-	arg->type = PRINT_DYNAMIC_ARRAY_LEN;
+	arg->type = TEP_PRINT_DYNAMIC_ARRAY_LEN;
 
 	/* Find the field */
 	field = tep_find_field(event, token);
@@ -2814,8 +2814,8 @@ process_paren(struct tep_event_format *event, struct tep_print_arg *arg, char **
 		/* make this a typecast and contine */
 
 		/* prevous must be an atom */
-		if (arg->type != PRINT_ATOM) {
-			do_warning_event(event, "previous needed to be PRINT_ATOM");
+		if (arg->type != TEP_PRINT_ATOM) {
+			do_warning_event(event, "previous needed to be TEP_PRINT_ATOM");
 			goto out_free;
 		}
 
@@ -2826,7 +2826,7 @@ process_paren(struct tep_event_format *event, struct tep_print_arg *arg, char **
 			goto out_free;
 		}
 
-		arg->type = PRINT_TYPE;
+		arg->type = TEP_PRINT_TYPE;
 		arg->typecast.type = arg->atom.atom;
 		arg->typecast.item = item_arg;
 		type = process_arg_token(event, item_arg, &token, type);
@@ -2853,7 +2853,7 @@ process_str(struct tep_event_format *event __maybe_unused, struct tep_print_arg
 	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto out_free;
 
-	arg->type = PRINT_STRING;
+	arg->type = TEP_PRINT_STRING;
 	arg->string.string = token;
 	arg->string.offset = -1;
 
@@ -2882,7 +2882,7 @@ process_bitmask(struct tep_event_format *event __maybe_unused, struct tep_print_
 	if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
 		goto out_free;
 
-	arg->type = PRINT_BITMASK;
+	arg->type = TEP_PRINT_BITMASK;
 	arg->bitmask.bitmask = token;
 	arg->bitmask.offset = -1;
 
@@ -2943,7 +2943,7 @@ process_func_handler(struct tep_event_format *event, struct tep_function_handler
 	char *token;
 	int i;
 
-	arg->type = PRINT_FUNC;
+	arg->type = TEP_PRINT_FUNC;
 	arg->func.func = func;
 
 	*tok = NULL;
@@ -3096,13 +3096,13 @@ process_arg_token(struct tep_event_format *event, struct tep_print_arg *arg,
 			type = read_token_item(&token);
 		}
 
-		arg->type = PRINT_ATOM;
+		arg->type = TEP_PRINT_ATOM;
 		arg->atom.atom = atom;
 		break;
 
 	case TEP_EVENT_DQUOTE:
 	case TEP_EVENT_SQUOTE:
-		arg->type = PRINT_ATOM;
+		arg->type = TEP_PRINT_ATOM;
 		arg->atom.atom = token;
 		type = read_token_item(&token);
 		break;
@@ -3114,7 +3114,7 @@ process_arg_token(struct tep_event_format *event, struct tep_print_arg *arg,
 		}
 	case TEP_EVENT_OP:
 		/* handle single ops */
-		arg->type = PRINT_OP;
+		arg->type = TEP_PRINT_OP;
 		arg->op.op = token;
 		arg->op.left = NULL;
 		type = process_op(event, arg, &token);
@@ -3533,12 +3533,12 @@ eval_num_arg(void *data, int size, struct tep_event_format *event, struct tep_pr
 	unsigned int field_size;
 
 	switch (arg->type) {
-	case PRINT_NULL:
+	case TEP_PRINT_NULL:
 		/* ?? */
 		return 0;
-	case PRINT_ATOM:
+	case TEP_PRINT_ATOM:
 		return strtoull(arg->atom.atom, NULL, 0);
-	case PRINT_FIELD:
+	case TEP_PRINT_FIELD:
 		if (!arg->field.field) {
 			arg->field.field = tep_find_any_field(event, arg->field.name);
 			if (!arg->field.field)
@@ -3549,27 +3549,27 @@ eval_num_arg(void *data, int size, struct tep_event_format *event, struct tep_pr
 		val = tep_read_number(pevent, data + arg->field.field->offset,
 				      arg->field.field->size);
 		break;
-	case PRINT_FLAGS:
-	case PRINT_SYMBOL:
-	case PRINT_INT_ARRAY:
-	case PRINT_HEX:
-	case PRINT_HEX_STR:
+	case TEP_PRINT_FLAGS:
+	case TEP_PRINT_SYMBOL:
+	case TEP_PRINT_INT_ARRAY:
+	case TEP_PRINT_HEX:
+	case TEP_PRINT_HEX_STR:
 		break;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		val = eval_num_arg(data, size, event, arg->typecast.item);
 		return eval_type(val, arg, 0);
-	case PRINT_STRING:
-	case PRINT_BSTRING:
-	case PRINT_BITMASK:
+	case TEP_PRINT_STRING:
+	case TEP_PRINT_BSTRING:
+	case TEP_PRINT_BITMASK:
 		return 0;
-	case PRINT_FUNC: {
+	case TEP_PRINT_FUNC: {
 		struct trace_seq s;
 		trace_seq_init(&s);
 		val = process_defined_func(&s, data, size, event, arg);
 		trace_seq_destroy(&s);
 		return val;
 	}
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		if (strcmp(arg->op.op, "[") == 0) {
 			/*
 			 * Arrays are special, since we don't want
@@ -3579,7 +3579,7 @@ eval_num_arg(void *data, int size, struct tep_event_format *event, struct tep_pr
 
 			/* handle typecasts */
 			larg = arg->op.left;
-			while (larg->type == PRINT_TYPE) {
+			while (larg->type == TEP_PRINT_TYPE) {
 				if (!typearg)
 					typearg = larg;
 				larg = larg->typecast.item;
@@ -3589,7 +3589,7 @@ eval_num_arg(void *data, int size, struct tep_event_format *event, struct tep_pr
 			field_size = pevent->long_size;
 
 			switch (larg->type) {
-			case PRINT_DYNAMIC_ARRAY:
+			case TEP_PRINT_DYNAMIC_ARRAY:
 				offset = tep_read_number(pevent,
 						   data + larg->dynarray.field->offset,
 						   larg->dynarray.field->size);
@@ -3603,7 +3603,7 @@ eval_num_arg(void *data, int size, struct tep_event_format *event, struct tep_pr
 				offset &= 0xffff;
 				offset += right;
 				break;
-			case PRINT_FIELD:
+			case TEP_PRINT_FIELD:
 				if (!larg->field.field) {
 					larg->field.field =
 						tep_find_any_field(event, larg->field.name);
@@ -3719,7 +3719,7 @@ eval_num_arg(void *data, int size, struct tep_event_format *event, struct tep_pr
 			goto out_warning_op;
 		}
 		break;
-	case PRINT_DYNAMIC_ARRAY_LEN:
+	case TEP_PRINT_DYNAMIC_ARRAY_LEN:
 		offset = tep_read_number(pevent,
 					 data + arg->dynarray.field->offset,
 					 arg->dynarray.field->size);
@@ -3730,7 +3730,7 @@ eval_num_arg(void *data, int size, struct tep_event_format *event, struct tep_pr
 		 */
 		val = (unsigned long long)(offset >> 16);
 		break;
-	case PRINT_DYNAMIC_ARRAY:
+	case TEP_PRINT_DYNAMIC_ARRAY:
 		/* Without [], we pass the address to the dynamic data */
 		offset = tep_read_number(pevent,
 					 data + arg->dynarray.field->offset,
@@ -3877,13 +3877,13 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 	int i, len;
 
 	switch (arg->type) {
-	case PRINT_NULL:
+	case TEP_PRINT_NULL:
 		/* ?? */
 		return;
-	case PRINT_ATOM:
+	case TEP_PRINT_ATOM:
 		print_str_to_seq(s, format, len_arg, arg->atom.atom);
 		return;
-	case PRINT_FIELD:
+	case TEP_PRINT_FIELD:
 		field = arg->field.field;
 		if (!field) {
 			field = tep_find_any_field(event, arg->field.name);
@@ -3940,7 +3940,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		print_str_to_seq(s, format, len_arg, str);
 		free(str);
 		break;
-	case PRINT_FLAGS:
+	case TEP_PRINT_FLAGS:
 		val = eval_num_arg(data, size, event, arg->flags.field);
 		print = 0;
 		for (flag = arg->flags.flags; flag; flag = flag->next) {
@@ -3963,7 +3963,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			trace_seq_printf(s, "0x%llx", val);
 		}
 		break;
-	case PRINT_SYMBOL:
+	case TEP_PRINT_SYMBOL:
 		val = eval_num_arg(data, size, event, arg->symbol.field);
 		for (flag = arg->symbol.symbols; flag; flag = flag->next) {
 			fval = eval_flag(flag->value);
@@ -3975,9 +3975,9 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		if (!flag)
 			trace_seq_printf(s, "0x%llx", val);
 		break;
-	case PRINT_HEX:
-	case PRINT_HEX_STR:
-		if (arg->hex.field->type == PRINT_DYNAMIC_ARRAY) {
+	case TEP_PRINT_HEX:
+	case TEP_PRINT_HEX_STR:
+		if (arg->hex.field->type == TEP_PRINT_DYNAMIC_ARRAY) {
 			unsigned long offset;
 			offset = tep_read_number(pevent,
 				data + arg->hex.field->dynarray.field->offset,
@@ -3996,17 +3996,17 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		}
 		len = eval_num_arg(data, size, event, arg->hex.size);
 		for (i = 0; i < len; i++) {
-			if (i && arg->type == PRINT_HEX)
+			if (i && arg->type == TEP_PRINT_HEX)
 				trace_seq_putc(s, ' ');
 			trace_seq_printf(s, "%02x", hex[i]);
 		}
 		break;
 
-	case PRINT_INT_ARRAY: {
+	case TEP_PRINT_INT_ARRAY: {
 		void *num;
 		int el_size;
 
-		if (arg->int_array.field->type == PRINT_DYNAMIC_ARRAY) {
+		if (arg->int_array.field->type == TEP_PRINT_DYNAMIC_ARRAY) {
 			unsigned long offset;
 			struct tep_format_field *field =
 				arg->int_array.field->dynarray.field;
@@ -4050,9 +4050,9 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		}
 		break;
 	}
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		break;
-	case PRINT_STRING: {
+	case TEP_PRINT_STRING: {
 		int str_offset;
 
 		if (arg->string.offset == -1) {
@@ -4066,10 +4066,10 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		print_str_to_seq(s, format, len_arg, ((char *)data) + str_offset);
 		break;
 	}
-	case PRINT_BSTRING:
+	case TEP_PRINT_BSTRING:
 		print_str_to_seq(s, format, len_arg, arg->string.string);
 		break;
-	case PRINT_BITMASK: {
+	case TEP_PRINT_BITMASK: {
 		int bitmask_offset;
 		int bitmask_size;
 
@@ -4086,7 +4086,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 				     data + bitmask_offset, bitmask_size);
 		break;
 	}
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		/*
 		 * The only op for string should be ? :
 		 */
@@ -4100,7 +4100,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			print_str_arg(s, data, size, event,
 				      format, len_arg, arg->op.right->op.right);
 		break;
-	case PRINT_FUNC:
+	case TEP_PRINT_FUNC:
 		process_defined_func(s, data, size, event, arg);
 		break;
 	default:
@@ -4255,7 +4255,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
 	arg->next = NULL;
 	next = &arg->next;
 
-	arg->type = PRINT_ATOM;
+	arg->type = TEP_PRINT_ATOM;
 		
 	if (asprintf(&arg->atom.atom, "%lld", ip) < 0)
 		goto out_free;
@@ -4343,7 +4343,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
 					goto out_free;
 				}
 				arg->next = NULL;
-				arg->type = PRINT_ATOM;
+				arg->type = TEP_PRINT_ATOM;
 				if (asprintf(&arg->atom.atom, "%lld", val) < 0) {
 					free(arg);
 					goto out_free;
@@ -4367,7 +4367,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
 					goto out_free;
 				}
 				arg->next = NULL;
-				arg->type = PRINT_BSTRING;
+				arg->type = TEP_PRINT_BSTRING;
 				arg->string.string = strdup(bptr);
 				if (!arg->string.string)
 					goto out_free;
@@ -4429,12 +4429,12 @@ static void print_mac_arg(struct trace_seq *s, int mac, void *data, int size,
 	unsigned char *buf;
 	const char *fmt = "%.2x:%.2x:%.2x:%.2x:%.2x:%.2x";
 
-	if (arg->type == PRINT_FUNC) {
+	if (arg->type == TEP_PRINT_FUNC) {
 		process_defined_func(s, data, size, event, arg);
 		return;
 	}
 
-	if (arg->type != PRINT_FIELD) {
+	if (arg->type != TEP_PRINT_FIELD) {
 		trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d",
 				 arg->type);
 		return;
@@ -4582,12 +4582,12 @@ static int print_ipv4_arg(struct trace_seq *s, const char *ptr, char i,
 {
 	unsigned char *buf;
 
-	if (arg->type == PRINT_FUNC) {
+	if (arg->type == TEP_PRINT_FUNC) {
 		process_defined_func(s, data, size, event, arg);
 		return 0;
 	}
 
-	if (arg->type != PRINT_FIELD) {
+	if (arg->type != TEP_PRINT_FIELD) {
 		trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type);
 		return 0;
 	}
@@ -4628,12 +4628,12 @@ static int print_ipv6_arg(struct trace_seq *s, const char *ptr, char i,
 		rc++;
 	}
 
-	if (arg->type == PRINT_FUNC) {
+	if (arg->type == TEP_PRINT_FUNC) {
 		process_defined_func(s, data, size, event, arg);
 		return rc;
 	}
 
-	if (arg->type != PRINT_FIELD) {
+	if (arg->type != TEP_PRINT_FIELD) {
 		trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type);
 		return rc;
 	}
@@ -4686,12 +4686,12 @@ static int print_ipsa_arg(struct trace_seq *s, const char *ptr, char i,
 		}
 	}
 
-	if (arg->type == PRINT_FUNC) {
+	if (arg->type == TEP_PRINT_FUNC) {
 		process_defined_func(s, data, size, event, arg);
 		return rc;
 	}
 
-	if (arg->type != PRINT_FIELD) {
+	if (arg->type != TEP_PRINT_FIELD) {
 		trace_seq_printf(s, "ARG TYPE NOT FIELD BUT %d", arg->type);
 		return rc;
 	}
@@ -4967,7 +4967,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
 				if (isalnum(ptr[1]))
 					ptr++;
 
-				if (arg->type == PRINT_BSTRING) {
+				if (arg->type == TEP_PRINT_BSTRING) {
 					trace_seq_puts(s, arg->string.string);
 					break;
 				}
@@ -5739,16 +5739,16 @@ static void print_args(struct tep_print_arg *args)
 	struct trace_seq s;
 
 	switch (args->type) {
-	case PRINT_NULL:
+	case TEP_PRINT_NULL:
 		printf("null");
 		break;
-	case PRINT_ATOM:
+	case TEP_PRINT_ATOM:
 		printf("%s", args->atom.atom);
 		break;
-	case PRINT_FIELD:
+	case TEP_PRINT_FIELD:
 		printf("REC->%s", args->field.name);
 		break;
-	case PRINT_FLAGS:
+	case TEP_PRINT_FLAGS:
 		printf("__print_flags(");
 		print_args(args->flags.field);
 		printf(", %s, ", args->flags.delim);
@@ -5758,7 +5758,7 @@ static void print_args(struct tep_print_arg *args)
 		trace_seq_destroy(&s);
 		printf(")");
 		break;
-	case PRINT_SYMBOL:
+	case TEP_PRINT_SYMBOL:
 		printf("__print_symbolic(");
 		print_args(args->symbol.field);
 		printf(", ");
@@ -5768,21 +5768,21 @@ static void print_args(struct tep_print_arg *args)
 		trace_seq_destroy(&s);
 		printf(")");
 		break;
-	case PRINT_HEX:
+	case TEP_PRINT_HEX:
 		printf("__print_hex(");
 		print_args(args->hex.field);
 		printf(", ");
 		print_args(args->hex.size);
 		printf(")");
 		break;
-	case PRINT_HEX_STR:
+	case TEP_PRINT_HEX_STR:
 		printf("__print_hex_str(");
 		print_args(args->hex.field);
 		printf(", ");
 		print_args(args->hex.size);
 		printf(")");
 		break;
-	case PRINT_INT_ARRAY:
+	case TEP_PRINT_INT_ARRAY:
 		printf("__print_array(");
 		print_args(args->int_array.field);
 		printf(", ");
@@ -5791,18 +5791,18 @@ static void print_args(struct tep_print_arg *args)
 		print_args(args->int_array.el_size);
 		printf(")");
 		break;
-	case PRINT_STRING:
-	case PRINT_BSTRING:
+	case TEP_PRINT_STRING:
+	case TEP_PRINT_BSTRING:
 		printf("__get_str(%s)", args->string.string);
 		break;
-	case PRINT_BITMASK:
+	case TEP_PRINT_BITMASK:
 		printf("__get_bitmask(%s)", args->bitmask.bitmask);
 		break;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		printf("(%s)", args->typecast.type);
 		print_args(args->typecast.item);
 		break;
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		if (strcmp(args->op.op, ":") == 0)
 			print_paren = 0;
 		if (print_paren)
@@ -6101,7 +6101,7 @@ enum tep_errno __tep_parse_format(struct tep_event_format **eventp,
 				event->flags |= TEP_EVENT_FL_FAILED;
 				return TEP_ERRNO__OLD_FTRACE_ARG_FAILED;
 			}
-			arg->type = PRINT_FIELD;
+			arg->type = TEP_PRINT_FIELD;
 			arg->field.name = strdup(field->name);
 			if (!arg->field.name) {
 				event->flags |= TEP_EVENT_FL_FAILED;
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 21923a11c9c0..7c4bf915d09a 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -234,28 +234,28 @@ struct tep_print_arg_func {
 	struct tep_print_arg		*args;
 };
 
-enum print_arg_type {
-	PRINT_NULL,
-	PRINT_ATOM,
-	PRINT_FIELD,
-	PRINT_FLAGS,
-	PRINT_SYMBOL,
-	PRINT_HEX,
-	PRINT_INT_ARRAY,
-	PRINT_TYPE,
-	PRINT_STRING,
-	PRINT_BSTRING,
-	PRINT_DYNAMIC_ARRAY,
-	PRINT_OP,
-	PRINT_FUNC,
-	PRINT_BITMASK,
-	PRINT_DYNAMIC_ARRAY_LEN,
-	PRINT_HEX_STR,
+enum tep_print_arg_type {
+	TEP_PRINT_NULL,
+	TEP_PRINT_ATOM,
+	TEP_PRINT_FIELD,
+	TEP_PRINT_FLAGS,
+	TEP_PRINT_SYMBOL,
+	TEP_PRINT_HEX,
+	TEP_PRINT_INT_ARRAY,
+	TEP_PRINT_TYPE,
+	TEP_PRINT_STRING,
+	TEP_PRINT_BSTRING,
+	TEP_PRINT_DYNAMIC_ARRAY,
+	TEP_PRINT_OP,
+	TEP_PRINT_FUNC,
+	TEP_PRINT_BITMASK,
+	TEP_PRINT_DYNAMIC_ARRAY_LEN,
+	TEP_PRINT_HEX_STR,
 };
 
 struct tep_print_arg {
 	struct tep_print_arg		*next;
-	enum print_arg_type		type;
+	enum tep_print_arg_type		type;
 	union {
 		struct tep_print_arg_atom	atom;
 		struct tep_print_arg_field	field;
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 481a1ecb1eaf..89cb887648f9 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -197,54 +197,54 @@ static void define_event_symbols(struct tep_event_format *event,
 		return;
 
 	switch (args->type) {
-	case PRINT_NULL:
+	case TEP_PRINT_NULL:
 		break;
-	case PRINT_ATOM:
+	case TEP_PRINT_ATOM:
 		define_flag_value(ev_name, cur_field_name, "0",
 				  args->atom.atom);
 		zero_flag_atom = 0;
 		break;
-	case PRINT_FIELD:
+	case TEP_PRINT_FIELD:
 		free(cur_field_name);
 		cur_field_name = strdup(args->field.name);
 		break;
-	case PRINT_FLAGS:
+	case TEP_PRINT_FLAGS:
 		define_event_symbols(event, ev_name, args->flags.field);
 		define_flag_field(ev_name, cur_field_name, args->flags.delim);
 		define_flag_values(args->flags.flags, ev_name, cur_field_name);
 		break;
-	case PRINT_SYMBOL:
+	case TEP_PRINT_SYMBOL:
 		define_event_symbols(event, ev_name, args->symbol.field);
 		define_symbolic_field(ev_name, cur_field_name);
 		define_symbolic_values(args->symbol.symbols, ev_name,
 				       cur_field_name);
 		break;
-	case PRINT_HEX:
-	case PRINT_HEX_STR:
+	case TEP_PRINT_HEX:
+	case TEP_PRINT_HEX_STR:
 		define_event_symbols(event, ev_name, args->hex.field);
 		define_event_symbols(event, ev_name, args->hex.size);
 		break;
-	case PRINT_INT_ARRAY:
+	case TEP_PRINT_INT_ARRAY:
 		define_event_symbols(event, ev_name, args->int_array.field);
 		define_event_symbols(event, ev_name, args->int_array.count);
 		define_event_symbols(event, ev_name, args->int_array.el_size);
 		break;
-	case PRINT_BSTRING:
-	case PRINT_DYNAMIC_ARRAY:
-	case PRINT_DYNAMIC_ARRAY_LEN:
-	case PRINT_STRING:
-	case PRINT_BITMASK:
+	case TEP_PRINT_BSTRING:
+	case TEP_PRINT_DYNAMIC_ARRAY:
+	case TEP_PRINT_DYNAMIC_ARRAY_LEN:
+	case TEP_PRINT_STRING:
+	case TEP_PRINT_BITMASK:
 		break;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		define_event_symbols(event, ev_name, args->typecast.item);
 		break;
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		if (strcmp(args->op.op, ":") == 0)
 			zero_flag_atom = 1;
 		define_event_symbols(event, ev_name, args->op.left);
 		define_event_symbols(event, ev_name, args->op.right);
 		break;
-	case PRINT_FUNC:
+	case TEP_PRINT_FUNC:
 	default:
 		pr_err("Unsupported print arg type\n");
 		/* we should warn... */
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 35dc5f3b581b..69aa93d4ee99 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -193,7 +193,7 @@ static void try_call_object(const char *handler_name, PyObject *args)
 		call_object(handler, args, handler_name);
 }
 
-static void define_value(enum print_arg_type field_type,
+static void define_value(enum tep_print_arg_type field_type,
 			 const char *ev_name,
 			 const char *field_name,
 			 const char *field_value,
@@ -204,7 +204,7 @@ static void define_value(enum print_arg_type field_type,
 	unsigned long long value;
 	unsigned n = 0;
 
-	if (field_type == PRINT_SYMBOL)
+	if (field_type == TEP_PRINT_SYMBOL)
 		handler_name = "define_symbolic_value";
 
 	t = PyTuple_New(4);
@@ -223,7 +223,7 @@ static void define_value(enum print_arg_type field_type,
 	Py_DECREF(t);
 }
 
-static void define_values(enum print_arg_type field_type,
+static void define_values(enum tep_print_arg_type field_type,
 			  struct tep_print_flag_sym *field,
 			  const char *ev_name,
 			  const char *field_name)
@@ -235,7 +235,7 @@ static void define_values(enum print_arg_type field_type,
 		define_values(field_type, field->next, ev_name, field_name);
 }
 
-static void define_field(enum print_arg_type field_type,
+static void define_field(enum tep_print_arg_type field_type,
 			 const char *ev_name,
 			 const char *field_name,
 			 const char *delim)
@@ -244,10 +244,10 @@ static void define_field(enum print_arg_type field_type,
 	PyObject *t;
 	unsigned n = 0;
 
-	if (field_type == PRINT_SYMBOL)
+	if (field_type == TEP_PRINT_SYMBOL)
 		handler_name = "define_symbolic_field";
 
-	if (field_type == PRINT_FLAGS)
+	if (field_type == TEP_PRINT_FLAGS)
 		t = PyTuple_New(3);
 	else
 		t = PyTuple_New(2);
@@ -256,7 +256,7 @@ static void define_field(enum print_arg_type field_type,
 
 	PyTuple_SetItem(t, n++, _PyUnicode_FromString(ev_name));
 	PyTuple_SetItem(t, n++, _PyUnicode_FromString(field_name));
-	if (field_type == PRINT_FLAGS)
+	if (field_type == TEP_PRINT_FLAGS)
 		PyTuple_SetItem(t, n++, _PyUnicode_FromString(delim));
 
 	try_call_object(handler_name, t);
@@ -272,46 +272,46 @@ static void define_event_symbols(struct tep_event_format *event,
 		return;
 
 	switch (args->type) {
-	case PRINT_NULL:
+	case TEP_PRINT_NULL:
 		break;
-	case PRINT_ATOM:
-		define_value(PRINT_FLAGS, ev_name, cur_field_name, "0",
+	case TEP_PRINT_ATOM:
+		define_value(TEP_PRINT_FLAGS, ev_name, cur_field_name, "0",
 			     args->atom.atom);
 		zero_flag_atom = 0;
 		break;
-	case PRINT_FIELD:
+	case TEP_PRINT_FIELD:
 		free(cur_field_name);
 		cur_field_name = strdup(args->field.name);
 		break;
-	case PRINT_FLAGS:
+	case TEP_PRINT_FLAGS:
 		define_event_symbols(event, ev_name, args->flags.field);
-		define_field(PRINT_FLAGS, ev_name, cur_field_name,
+		define_field(TEP_PRINT_FLAGS, ev_name, cur_field_name,
 			     args->flags.delim);
-		define_values(PRINT_FLAGS, args->flags.flags, ev_name,
+		define_values(TEP_PRINT_FLAGS, args->flags.flags, ev_name,
 			      cur_field_name);
 		break;
-	case PRINT_SYMBOL:
+	case TEP_PRINT_SYMBOL:
 		define_event_symbols(event, ev_name, args->symbol.field);
-		define_field(PRINT_SYMBOL, ev_name, cur_field_name, NULL);
-		define_values(PRINT_SYMBOL, args->symbol.symbols, ev_name,
+		define_field(TEP_PRINT_SYMBOL, ev_name, cur_field_name, NULL);
+		define_values(TEP_PRINT_SYMBOL, args->symbol.symbols, ev_name,
 			      cur_field_name);
 		break;
-	case PRINT_HEX:
-	case PRINT_HEX_STR:
+	case TEP_PRINT_HEX:
+	case TEP_PRINT_HEX_STR:
 		define_event_symbols(event, ev_name, args->hex.field);
 		define_event_symbols(event, ev_name, args->hex.size);
 		break;
-	case PRINT_INT_ARRAY:
+	case TEP_PRINT_INT_ARRAY:
 		define_event_symbols(event, ev_name, args->int_array.field);
 		define_event_symbols(event, ev_name, args->int_array.count);
 		define_event_symbols(event, ev_name, args->int_array.el_size);
 		break;
-	case PRINT_STRING:
+	case TEP_PRINT_STRING:
 		break;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		define_event_symbols(event, ev_name, args->typecast.item);
 		break;
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		if (strcmp(args->op.op, ":") == 0)
 			zero_flag_atom = 1;
 		define_event_symbols(event, ev_name, args->op.left);
@@ -319,11 +319,11 @@ static void define_event_symbols(struct tep_event_format *event,
 		break;
 	default:
 		/* gcc warns for these? */
-	case PRINT_BSTRING:
-	case PRINT_DYNAMIC_ARRAY:
-	case PRINT_DYNAMIC_ARRAY_LEN:
-	case PRINT_FUNC:
-	case PRINT_BITMASK:
+	case TEP_PRINT_BSTRING:
+	case TEP_PRINT_DYNAMIC_ARRAY:
+	case TEP_PRINT_DYNAMIC_ARRAY_LEN:
+	case TEP_PRINT_FUNC:
+	case TEP_PRINT_BITMASK:
 		/* we should warn... */
 		return;
 	}
-- 
cgit v1.2.3


From e906bb788f2c4e870787f09b831923ca893a4671 Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Wed, 19 Sep 2018 14:56:51 -0400
Subject: tools lib traceevent: Add prefix tep_ to enums
 filter_{boolean,op,cmp}_type

In order to make libtraceevent into a proper library, variables, data
structures and functions require a unique prefix to prevent name space
conflicts. That prefix will be "tep_". This adds prefix tep_ to enums
filter_boolean_type, filter_op_type, filter_cmp_type and all enum's members

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lkml.kernel.org/r/20180919185723.680572508@goodmis.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.h  |  46 ++++++------
 tools/lib/traceevent/parse-filter.c | 144 ++++++++++++++++++------------------
 2 files changed, 95 insertions(+), 95 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 7c4bf915d09a..c9d7c5376fc2 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -768,29 +768,29 @@ void tep_print_printk(struct tep_handle *pevent);
 
 /* ----------------------- filtering ----------------------- */
 
-enum filter_boolean_type {
-	FILTER_FALSE,
-	FILTER_TRUE,
+enum tep_filter_boolean_type {
+	TEP_FILTER_FALSE,
+	TEP_FILTER_TRUE,
 };
 
-enum filter_op_type {
-	FILTER_OP_AND = 1,
-	FILTER_OP_OR,
-	FILTER_OP_NOT,
+enum tep_filter_op_type {
+	TEP_FILTER_OP_AND = 1,
+	TEP_FILTER_OP_OR,
+	TEP_FILTER_OP_NOT,
 };
 
-enum filter_cmp_type {
-	FILTER_CMP_NONE,
-	FILTER_CMP_EQ,
-	FILTER_CMP_NE,
-	FILTER_CMP_GT,
-	FILTER_CMP_LT,
-	FILTER_CMP_GE,
-	FILTER_CMP_LE,
-	FILTER_CMP_MATCH,
-	FILTER_CMP_NOT_MATCH,
-	FILTER_CMP_REGEX,
-	FILTER_CMP_NOT_REGEX,
+enum tep_filter_cmp_type {
+	TEP_FILTER_CMP_NONE,
+	TEP_FILTER_CMP_EQ,
+	TEP_FILTER_CMP_NE,
+	TEP_FILTER_CMP_GT,
+	TEP_FILTER_CMP_LT,
+	TEP_FILTER_CMP_GE,
+	TEP_FILTER_CMP_LE,
+	TEP_FILTER_CMP_MATCH,
+	TEP_FILTER_CMP_NOT_MATCH,
+	TEP_FILTER_CMP_REGEX,
+	TEP_FILTER_CMP_NOT_REGEX,
 };
 
 enum filter_exp_type {
@@ -828,7 +828,7 @@ enum filter_value_type {
 struct fliter_arg;
 
 struct filter_arg_boolean {
-	enum filter_boolean_type	value;
+	enum tep_filter_boolean_type	value;
 };
 
 struct filter_arg_field {
@@ -844,7 +844,7 @@ struct filter_arg_value {
 };
 
 struct filter_arg_op {
-	enum filter_op_type	type;
+	enum tep_filter_op_type	type;
 	struct filter_arg	*left;
 	struct filter_arg	*right;
 };
@@ -856,13 +856,13 @@ struct filter_arg_exp {
 };
 
 struct filter_arg_num {
-	enum filter_cmp_type	type;
+	enum tep_filter_cmp_type	type;
 	struct filter_arg	*left;
 	struct filter_arg	*right;
 };
 
 struct filter_arg_str {
-	enum filter_cmp_type	type;
+	enum tep_filter_cmp_type	type;
 	struct tep_format_field	*field;
 	char			*val;
 	char			*buffer;
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 153e248de75b..55ce8e603485 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -378,7 +378,7 @@ create_arg_item(struct tep_event_format *event, const char *token,
 			} else {
 				/* not a field, Make it false */
 				arg->type = FILTER_ARG_BOOLEAN;
-				arg->boolean.value = FILTER_FALSE;
+				arg->boolean.value = TEP_FILTER_FALSE;
 				break;
 			}
 		}
@@ -395,7 +395,7 @@ create_arg_item(struct tep_event_format *event, const char *token,
 }
 
 static struct filter_arg *
-create_arg_op(enum filter_op_type btype)
+create_arg_op(enum tep_filter_op_type btype)
 {
 	struct filter_arg *arg;
 
@@ -425,7 +425,7 @@ create_arg_exp(enum filter_exp_type etype)
 }
 
 static struct filter_arg *
-create_arg_cmp(enum filter_cmp_type ctype)
+create_arg_cmp(enum tep_filter_cmp_type ctype)
 {
 	struct filter_arg *arg;
 
@@ -488,8 +488,8 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 			 * is not a REGEX.
 			 */
 			if (strlen(arg->value.str) == 1 &&
-			    op->num.type != FILTER_CMP_REGEX &&
-			    op->num.type != FILTER_CMP_NOT_REGEX) {
+			    op->num.type != TEP_FILTER_CMP_REGEX &&
+			    op->num.type != TEP_FILTER_CMP_NOT_REGEX) {
 				arg->value.type = FILTER_NUMBER;
 				goto do_int;
 			}
@@ -512,7 +512,7 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 				free_arg(left);
 				free_arg(arg);
 				op->type = FILTER_ARG_BOOLEAN;
-				op->boolean.value = FILTER_FALSE;
+				op->boolean.value = TEP_FILTER_FALSE;
 				break;
 			}
 
@@ -525,15 +525,15 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 
 			/* Make sure this is a valid string compare */
 			switch (op_type) {
-			case FILTER_CMP_EQ:
-				op_type = FILTER_CMP_MATCH;
+			case TEP_FILTER_CMP_EQ:
+				op_type = TEP_FILTER_CMP_MATCH;
 				break;
-			case FILTER_CMP_NE:
-				op_type = FILTER_CMP_NOT_MATCH;
+			case TEP_FILTER_CMP_NE:
+				op_type = TEP_FILTER_CMP_NOT_MATCH;
 				break;
 
-			case FILTER_CMP_REGEX:
-			case FILTER_CMP_NOT_REGEX:
+			case TEP_FILTER_CMP_REGEX:
+			case TEP_FILTER_CMP_NOT_REGEX:
 				ret = regcomp(&op->str.reg, str, REG_ICASE|REG_NOSUB);
 				if (ret) {
 					show_error(error_str,
@@ -577,8 +577,8 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 
  do_int:
 			switch (op->num.type) {
-			case FILTER_CMP_REGEX:
-			case FILTER_CMP_NOT_REGEX:
+			case TEP_FILTER_CMP_REGEX:
+			case TEP_FILTER_CMP_NOT_REGEX:
 				show_error(error_str,
 					   "Op not allowed with integers");
 				return TEP_ERRNO__ILLEGAL_INTEGER_CMP;
@@ -652,22 +652,22 @@ enum op_type {
 };
 
 static enum op_type process_op(const char *token,
-			       enum filter_op_type *btype,
-			       enum filter_cmp_type *ctype,
+			       enum tep_filter_op_type *btype,
+			       enum tep_filter_cmp_type *ctype,
 			       enum filter_exp_type *etype)
 {
-	*btype = FILTER_OP_NOT;
+	*btype = TEP_FILTER_OP_NOT;
 	*etype = FILTER_EXP_NONE;
-	*ctype = FILTER_CMP_NONE;
+	*ctype = TEP_FILTER_CMP_NONE;
 
 	if (strcmp(token, "&&") == 0)
-		*btype = FILTER_OP_AND;
+		*btype = TEP_FILTER_OP_AND;
 	else if (strcmp(token, "||") == 0)
-		*btype = FILTER_OP_OR;
+		*btype = TEP_FILTER_OP_OR;
 	else if (strcmp(token, "!") == 0)
 		return OP_NOT;
 
-	if (*btype != FILTER_OP_NOT)
+	if (*btype != TEP_FILTER_OP_NOT)
 		return OP_BOOL;
 
 	/* Check for value expressions */
@@ -699,21 +699,21 @@ static enum op_type process_op(const char *token,
 
 	/* Check for compares */
 	if (strcmp(token, "==") == 0)
-		*ctype = FILTER_CMP_EQ;
+		*ctype = TEP_FILTER_CMP_EQ;
 	else if (strcmp(token, "!=") == 0)
-		*ctype = FILTER_CMP_NE;
+		*ctype = TEP_FILTER_CMP_NE;
 	else if (strcmp(token, "<") == 0)
-		*ctype = FILTER_CMP_LT;
+		*ctype = TEP_FILTER_CMP_LT;
 	else if (strcmp(token, ">") == 0)
-		*ctype = FILTER_CMP_GT;
+		*ctype = TEP_FILTER_CMP_GT;
 	else if (strcmp(token, "<=") == 0)
-		*ctype = FILTER_CMP_LE;
+		*ctype = TEP_FILTER_CMP_LE;
 	else if (strcmp(token, ">=") == 0)
-		*ctype = FILTER_CMP_GE;
+		*ctype = TEP_FILTER_CMP_GE;
 	else if (strcmp(token, "=~") == 0)
-		*ctype = FILTER_CMP_REGEX;
+		*ctype = TEP_FILTER_CMP_REGEX;
 	else if (strcmp(token, "!~") == 0)
-		*ctype = FILTER_CMP_NOT_REGEX;
+		*ctype = TEP_FILTER_CMP_NOT_REGEX;
 	else
 		return OP_NONE;
 
@@ -840,13 +840,13 @@ static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
 		return FILTER_VAL_NORM;
 
 	case FILTER_ARG_OP:
-		if (arg->op.type != FILTER_OP_NOT) {
+		if (arg->op.type != TEP_FILTER_OP_NOT) {
 			lval = test_arg(arg, arg->op.left, error_str);
 			switch (lval) {
 			case FILTER_VAL_NORM:
 				break;
 			case FILTER_VAL_TRUE:
-				if (arg->op.type == FILTER_OP_OR)
+				if (arg->op.type == TEP_FILTER_OP_OR)
 					return FILTER_VAL_TRUE;
 				rval = test_arg(arg, arg->op.right, error_str);
 				if (rval != FILTER_VAL_NORM)
@@ -856,7 +856,7 @@ static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
 						       error_str);
 
 			case FILTER_VAL_FALSE:
-				if (arg->op.type == FILTER_OP_AND)
+				if (arg->op.type == TEP_FILTER_OP_AND)
 					return FILTER_VAL_FALSE;
 				rval = test_arg(arg, arg->op.right, error_str);
 				if (rval != FILTER_VAL_NORM)
@@ -877,18 +877,18 @@ static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
 			break;
 
 		case FILTER_VAL_TRUE:
-			if (arg->op.type == FILTER_OP_OR)
+			if (arg->op.type == TEP_FILTER_OP_OR)
 				return FILTER_VAL_TRUE;
-			if (arg->op.type == FILTER_OP_NOT)
+			if (arg->op.type == TEP_FILTER_OP_NOT)
 				return FILTER_VAL_FALSE;
 
 			return reparent_op_arg(parent, arg, arg->op.left,
 					       error_str);
 
 		case FILTER_VAL_FALSE:
-			if (arg->op.type == FILTER_OP_AND)
+			if (arg->op.type == TEP_FILTER_OP_AND)
 				return FILTER_VAL_FALSE;
-			if (arg->op.type == FILTER_OP_NOT)
+			if (arg->op.type == TEP_FILTER_OP_NOT)
 				return FILTER_VAL_TRUE;
 
 			return reparent_op_arg(parent, arg, arg->op.left,
@@ -949,9 +949,9 @@ process_filter(struct tep_event_format *event, struct filter_arg **parg,
 	struct filter_arg *left_item = NULL;
 	struct filter_arg *arg = NULL;
 	enum op_type op_type;
-	enum filter_op_type btype;
+	enum tep_filter_op_type btype;
 	enum filter_exp_type etype;
-	enum filter_cmp_type ctype;
+	enum tep_filter_cmp_type ctype;
 	enum tep_errno ret;
 
 	*parg = NULL;
@@ -1197,7 +1197,7 @@ process_event(struct tep_event_format *event, const char *filter_str,
 			return TEP_ERRNO__MEM_ALLOC_FAILED;
 
 		(*parg)->type = FILTER_ARG_BOOLEAN;
-		(*parg)->boolean.value = FILTER_FALSE;
+		(*parg)->boolean.value = TEP_FILTER_FALSE;
 	}
 
 	return 0;
@@ -1223,7 +1223,7 @@ filter_event(struct event_filter *filter, struct tep_event_format *event,
 			return TEP_ERRNO__MEM_ALLOC_FAILED;
 
 		arg->type = FILTER_ARG_BOOLEAN;
-		arg->boolean.value = FILTER_TRUE;
+		arg->boolean.value = TEP_FILTER_TRUE;
 	}
 
 	filter_type = add_filter_type(filter, event->id);
@@ -1832,22 +1832,22 @@ static int test_num(struct tep_event_format *event, struct filter_arg *arg,
 	}
 
 	switch (arg->num.type) {
-	case FILTER_CMP_EQ:
+	case TEP_FILTER_CMP_EQ:
 		return lval == rval;
 
-	case FILTER_CMP_NE:
+	case TEP_FILTER_CMP_NE:
 		return lval != rval;
 
-	case FILTER_CMP_GT:
+	case TEP_FILTER_CMP_GT:
 		return lval > rval;
 
-	case FILTER_CMP_LT:
+	case TEP_FILTER_CMP_LT:
 		return lval < rval;
 
-	case FILTER_CMP_GE:
+	case TEP_FILTER_CMP_GE:
 		return lval >= rval;
 
-	case FILTER_CMP_LE:
+	case TEP_FILTER_CMP_LE:
 		return lval <= rval;
 
 	default:
@@ -1918,17 +1918,17 @@ static int test_str(struct tep_event_format *event, struct filter_arg *arg,
 		val = get_field_str(arg, record);
 
 	switch (arg->str.type) {
-	case FILTER_CMP_MATCH:
+	case TEP_FILTER_CMP_MATCH:
 		return strcmp(val, arg->str.val) == 0;
 
-	case FILTER_CMP_NOT_MATCH:
+	case TEP_FILTER_CMP_NOT_MATCH:
 		return strcmp(val, arg->str.val) != 0;
 
-	case FILTER_CMP_REGEX:
+	case TEP_FILTER_CMP_REGEX:
 		/* Returns zero on match */
 		return !regexec(&arg->str.reg, val, 0, NULL, 0);
 
-	case FILTER_CMP_NOT_REGEX:
+	case TEP_FILTER_CMP_NOT_REGEX:
 		return regexec(&arg->str.reg, val, 0, NULL, 0);
 
 	default:
@@ -1942,15 +1942,15 @@ static int test_op(struct tep_event_format *event, struct filter_arg *arg,
 		   struct tep_record *record, enum tep_errno *err)
 {
 	switch (arg->op.type) {
-	case FILTER_OP_AND:
+	case TEP_FILTER_OP_AND:
 		return test_filter(event, arg->op.left, record, err) &&
 			test_filter(event, arg->op.right, record, err);
 
-	case FILTER_OP_OR:
+	case TEP_FILTER_OP_OR:
 		return test_filter(event, arg->op.left, record, err) ||
 			test_filter(event, arg->op.right, record, err);
 
-	case FILTER_OP_NOT:
+	case TEP_FILTER_OP_NOT:
 		return !test_filter(event, arg->op.right, record, err);
 
 	default:
@@ -2070,10 +2070,10 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 	int val;
 
 	switch (arg->op.type) {
-	case FILTER_OP_AND:
+	case TEP_FILTER_OP_AND:
 		op = "&&";
 		/* fall through */
-	case FILTER_OP_OR:
+	case TEP_FILTER_OP_OR:
 		if (!op)
 			op = "||";
 
@@ -2094,8 +2094,8 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 			right_val = 0;
 
 		if (left_val >= 0) {
-			if ((arg->op.type == FILTER_OP_AND && !left_val) ||
-			    (arg->op.type == FILTER_OP_OR && left_val)) {
+			if ((arg->op.type == TEP_FILTER_OP_AND && !left_val) ||
+			    (arg->op.type == TEP_FILTER_OP_OR && left_val)) {
 				/* Just return left value */
 				str = left;
 				left = NULL;
@@ -2105,10 +2105,10 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 				/* just evaluate this. */
 				val = 0;
 				switch (arg->op.type) {
-				case FILTER_OP_AND:
+				case TEP_FILTER_OP_AND:
 					val = left_val && right_val;
 					break;
-				case FILTER_OP_OR:
+				case TEP_FILTER_OP_OR:
 					val = left_val || right_val;
 					break;
 				default:
@@ -2119,8 +2119,8 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 			}
 		}
 		if (right_val >= 0) {
-			if ((arg->op.type == FILTER_OP_AND && !right_val) ||
-			    (arg->op.type == FILTER_OP_OR && right_val)) {
+			if ((arg->op.type == TEP_FILTER_OP_AND && !right_val) ||
+			    (arg->op.type == TEP_FILTER_OP_OR && right_val)) {
 				/* Just return right value */
 				str = right;
 				right = NULL;
@@ -2135,7 +2135,7 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 		asprintf(&str, "(%s) %s (%s)", left, op, right);
 		break;
 
-	case FILTER_OP_NOT:
+	case TEP_FILTER_OP_NOT:
 		op = "!";
 		right = arg_to_str(filter, arg->op.right);
 		if (!right)
@@ -2246,26 +2246,26 @@ static char *num_to_str(struct event_filter *filter, struct filter_arg *arg)
 		goto out;
 
 	switch (arg->num.type) {
-	case FILTER_CMP_EQ:
+	case TEP_FILTER_CMP_EQ:
 		op = "==";
 		/* fall through */
-	case FILTER_CMP_NE:
+	case TEP_FILTER_CMP_NE:
 		if (!op)
 			op = "!=";
 		/* fall through */
-	case FILTER_CMP_GT:
+	case TEP_FILTER_CMP_GT:
 		if (!op)
 			op = ">";
 		/* fall through */
-	case FILTER_CMP_LT:
+	case TEP_FILTER_CMP_LT:
 		if (!op)
 			op = "<";
 		/* fall through */
-	case FILTER_CMP_GE:
+	case TEP_FILTER_CMP_GE:
 		if (!op)
 			op = ">=";
 		/* fall through */
-	case FILTER_CMP_LE:
+	case TEP_FILTER_CMP_LE:
 		if (!op)
 			op = "<=";
 
@@ -2289,18 +2289,18 @@ static char *str_to_str(struct event_filter *filter, struct filter_arg *arg)
 	char *op = NULL;
 
 	switch (arg->str.type) {
-	case FILTER_CMP_MATCH:
+	case TEP_FILTER_CMP_MATCH:
 		op = "==";
 		/* fall through */
-	case FILTER_CMP_NOT_MATCH:
+	case TEP_FILTER_CMP_NOT_MATCH:
 		if (!op)
 			op = "!=";
 		/* fall through */
-	case FILTER_CMP_REGEX:
+	case TEP_FILTER_CMP_REGEX:
 		if (!op)
 			op = "=~";
 		/* fall through */
-	case FILTER_CMP_NOT_REGEX:
+	case TEP_FILTER_CMP_NOT_REGEX:
 		if (!op)
 			op = "!~";
 
-- 
cgit v1.2.3


From 4746d22a4c1b12993540924f8cca12a256646614 Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Wed, 19 Sep 2018 14:56:52 -0400
Subject: tools lib traceevent: Add prefix tep_ to enums filter_{exp,arg}_type

In order to make libtraceevent into a proper library, variables, data
structures and functions require a unique prefix to prevent name space
conflicts. That prefix will be "tep_". This adds prefix tep_ to enums
filter_exp_type, filter_arg_type and all enum's members

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lkml.kernel.org/r/20180919185723.824559046@goodmis.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.h  |  56 +++++-----
 tools/lib/traceevent/parse-filter.c | 210 ++++++++++++++++++------------------
 2 files changed, 133 insertions(+), 133 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index c9d7c5376fc2..5e55c83d43fe 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -793,30 +793,30 @@ enum tep_filter_cmp_type {
 	TEP_FILTER_CMP_NOT_REGEX,
 };
 
-enum filter_exp_type {
-	FILTER_EXP_NONE,
-	FILTER_EXP_ADD,
-	FILTER_EXP_SUB,
-	FILTER_EXP_MUL,
-	FILTER_EXP_DIV,
-	FILTER_EXP_MOD,
-	FILTER_EXP_RSHIFT,
-	FILTER_EXP_LSHIFT,
-	FILTER_EXP_AND,
-	FILTER_EXP_OR,
-	FILTER_EXP_XOR,
-	FILTER_EXP_NOT,
-};
-
-enum filter_arg_type {
-	FILTER_ARG_NONE,
-	FILTER_ARG_BOOLEAN,
-	FILTER_ARG_VALUE,
-	FILTER_ARG_FIELD,
-	FILTER_ARG_EXP,
-	FILTER_ARG_OP,
-	FILTER_ARG_NUM,
-	FILTER_ARG_STR,
+enum tep_filter_exp_type {
+	TEP_FILTER_EXP_NONE,
+	TEP_FILTER_EXP_ADD,
+	TEP_FILTER_EXP_SUB,
+	TEP_FILTER_EXP_MUL,
+	TEP_FILTER_EXP_DIV,
+	TEP_FILTER_EXP_MOD,
+	TEP_FILTER_EXP_RSHIFT,
+	TEP_FILTER_EXP_LSHIFT,
+	TEP_FILTER_EXP_AND,
+	TEP_FILTER_EXP_OR,
+	TEP_FILTER_EXP_XOR,
+	TEP_FILTER_EXP_NOT,
+};
+
+enum tep_filter_arg_type {
+	TEP_FILTER_ARG_NONE,
+	TEP_FILTER_ARG_BOOLEAN,
+	TEP_FILTER_ARG_VALUE,
+	TEP_FILTER_ARG_FIELD,
+	TEP_FILTER_ARG_EXP,
+	TEP_FILTER_ARG_OP,
+	TEP_FILTER_ARG_NUM,
+	TEP_FILTER_ARG_STR,
 };
 
 enum filter_value_type {
@@ -850,9 +850,9 @@ struct filter_arg_op {
 };
 
 struct filter_arg_exp {
-	enum filter_exp_type	type;
-	struct filter_arg	*left;
-	struct filter_arg	*right;
+	enum tep_filter_exp_type	type;
+	struct filter_arg		*left;
+	struct filter_arg		*right;
 };
 
 struct filter_arg_num {
@@ -870,7 +870,7 @@ struct filter_arg_str {
 };
 
 struct filter_arg {
-	enum filter_arg_type	type;
+	enum tep_filter_arg_type		type;
 	union {
 		struct filter_arg_boolean	boolean;
 		struct filter_arg_field		field;
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 55ce8e603485..d1e0dd5b63ea 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -191,33 +191,33 @@ static void free_arg(struct filter_arg *arg)
 		return;
 
 	switch (arg->type) {
-	case FILTER_ARG_NONE:
-	case FILTER_ARG_BOOLEAN:
+	case TEP_FILTER_ARG_NONE:
+	case TEP_FILTER_ARG_BOOLEAN:
 		break;
 
-	case FILTER_ARG_NUM:
+	case TEP_FILTER_ARG_NUM:
 		free_arg(arg->num.left);
 		free_arg(arg->num.right);
 		break;
 
-	case FILTER_ARG_EXP:
+	case TEP_FILTER_ARG_EXP:
 		free_arg(arg->exp.left);
 		free_arg(arg->exp.right);
 		break;
 
-	case FILTER_ARG_STR:
+	case TEP_FILTER_ARG_STR:
 		free(arg->str.val);
 		regfree(&arg->str.reg);
 		free(arg->str.buffer);
 		break;
 
-	case FILTER_ARG_VALUE:
+	case TEP_FILTER_ARG_VALUE:
 		if (arg->value.type == FILTER_STRING ||
 		    arg->value.type == FILTER_CHAR)
 			free(arg->value.str);
 		break;
 
-	case FILTER_ARG_OP:
+	case TEP_FILTER_ARG_OP:
 		free_arg(arg->op.left);
 		free_arg(arg->op.right);
 	default:
@@ -349,7 +349,7 @@ create_arg_item(struct tep_event_format *event, const char *token,
 
 	case TEP_EVENT_SQUOTE:
 	case TEP_EVENT_DQUOTE:
-		arg->type = FILTER_ARG_VALUE;
+		arg->type = TEP_FILTER_ARG_VALUE;
 		arg->value.type =
 			type == TEP_EVENT_DQUOTE ? FILTER_STRING : FILTER_CHAR;
 		arg->value.str = strdup(token);
@@ -362,7 +362,7 @@ create_arg_item(struct tep_event_format *event, const char *token,
 	case TEP_EVENT_ITEM:
 		/* if it is a number, then convert it */
 		if (isdigit(token[0])) {
-			arg->type = FILTER_ARG_VALUE;
+			arg->type = TEP_FILTER_ARG_VALUE;
 			arg->value.type = FILTER_NUMBER;
 			arg->value.val = strtoull(token, NULL, 0);
 			break;
@@ -377,12 +377,12 @@ create_arg_item(struct tep_event_format *event, const char *token,
 				field = &cpu;
 			} else {
 				/* not a field, Make it false */
-				arg->type = FILTER_ARG_BOOLEAN;
+				arg->type = TEP_FILTER_ARG_BOOLEAN;
 				arg->boolean.value = TEP_FILTER_FALSE;
 				break;
 			}
 		}
-		arg->type = FILTER_ARG_FIELD;
+		arg->type = TEP_FILTER_ARG_FIELD;
 		arg->field.field = field;
 		break;
 	default:
@@ -403,14 +403,14 @@ create_arg_op(enum tep_filter_op_type btype)
 	if (!arg)
 		return NULL;
 
-	arg->type = FILTER_ARG_OP;
+	arg->type = TEP_FILTER_ARG_OP;
 	arg->op.type = btype;
 
 	return arg;
 }
 
 static struct filter_arg *
-create_arg_exp(enum filter_exp_type etype)
+create_arg_exp(enum tep_filter_exp_type etype)
 {
 	struct filter_arg *arg;
 
@@ -418,7 +418,7 @@ create_arg_exp(enum filter_exp_type etype)
 	if (!arg)
 		return NULL;
 
-	arg->type = FILTER_ARG_EXP;
+	arg->type = TEP_FILTER_ARG_EXP;
 	arg->exp.type = etype;
 
 	return arg;
@@ -434,7 +434,7 @@ create_arg_cmp(enum tep_filter_cmp_type ctype)
 		return NULL;
 
 	/* Use NUM and change if necessary */
-	arg->type = FILTER_ARG_NUM;
+	arg->type = TEP_FILTER_ARG_NUM;
 	arg->num.type = ctype;
 
 	return arg;
@@ -449,27 +449,27 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 	int ret;
 
 	switch (op->type) {
-	case FILTER_ARG_EXP:
+	case TEP_FILTER_ARG_EXP:
 		if (op->exp.right)
 			goto out_fail;
 		op->exp.right = arg;
 		break;
 
-	case FILTER_ARG_OP:
+	case TEP_FILTER_ARG_OP:
 		if (op->op.right)
 			goto out_fail;
 		op->op.right = arg;
 		break;
 
-	case FILTER_ARG_NUM:
+	case TEP_FILTER_ARG_NUM:
 		if (op->op.right)
 			goto out_fail;
 		/*
 		 * The arg must be num, str, or field
 		 */
 		switch (arg->type) {
-		case FILTER_ARG_VALUE:
-		case FILTER_ARG_FIELD:
+		case TEP_FILTER_ARG_VALUE:
+		case TEP_FILTER_ARG_FIELD:
 			break;
 		default:
 			show_error(error_str, "Illegal rvalue");
@@ -508,16 +508,16 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 			 * If left arg was a field not found then
 			 * NULL the entire op.
 			 */
-			if (left->type == FILTER_ARG_BOOLEAN) {
+			if (left->type == TEP_FILTER_ARG_BOOLEAN) {
 				free_arg(left);
 				free_arg(arg);
-				op->type = FILTER_ARG_BOOLEAN;
+				op->type = TEP_FILTER_ARG_BOOLEAN;
 				op->boolean.value = TEP_FILTER_FALSE;
 				break;
 			}
 
 			/* Left arg must be a field */
-			if (left->type != FILTER_ARG_FIELD) {
+			if (left->type != TEP_FILTER_ARG_FIELD) {
 				show_error(error_str,
 					   "Illegal lvalue for string comparison");
 				return TEP_ERRNO__ILLEGAL_LVALUE;
@@ -548,7 +548,7 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 				return TEP_ERRNO__ILLEGAL_STRING_CMP;
 			}
 
-			op->type = FILTER_ARG_STR;
+			op->type = TEP_FILTER_ARG_STR;
 			op->str.type = op_type;
 			op->str.field = left->field.field;
 			op->str.val = strdup(str);
@@ -618,22 +618,22 @@ rotate_op_right(struct filter_arg *a, struct filter_arg *b)
 static enum tep_errno add_left(struct filter_arg *op, struct filter_arg *arg)
 {
 	switch (op->type) {
-	case FILTER_ARG_EXP:
-		if (arg->type == FILTER_ARG_OP)
+	case TEP_FILTER_ARG_EXP:
+		if (arg->type == TEP_FILTER_ARG_OP)
 			arg = rotate_op_right(arg, op);
 		op->exp.left = arg;
 		break;
 
-	case FILTER_ARG_OP:
+	case TEP_FILTER_ARG_OP:
 		op->op.left = arg;
 		break;
-	case FILTER_ARG_NUM:
-		if (arg->type == FILTER_ARG_OP)
+	case TEP_FILTER_ARG_NUM:
+		if (arg->type == TEP_FILTER_ARG_OP)
 			arg = rotate_op_right(arg, op);
 
 		/* left arg of compares must be a field */
-		if (arg->type != FILTER_ARG_FIELD &&
-		    arg->type != FILTER_ARG_BOOLEAN)
+		if (arg->type != TEP_FILTER_ARG_FIELD &&
+		    arg->type != TEP_FILTER_ARG_BOOLEAN)
 			return TEP_ERRNO__INVALID_ARG_TYPE;
 		op->num.left = arg;
 		break;
@@ -654,10 +654,10 @@ enum op_type {
 static enum op_type process_op(const char *token,
 			       enum tep_filter_op_type *btype,
 			       enum tep_filter_cmp_type *ctype,
-			       enum filter_exp_type *etype)
+			       enum tep_filter_exp_type *etype)
 {
 	*btype = TEP_FILTER_OP_NOT;
-	*etype = FILTER_EXP_NONE;
+	*etype = TEP_FILTER_EXP_NONE;
 	*ctype = TEP_FILTER_CMP_NONE;
 
 	if (strcmp(token, "&&") == 0)
@@ -672,29 +672,29 @@ static enum op_type process_op(const char *token,
 
 	/* Check for value expressions */
 	if (strcmp(token, "+") == 0) {
-		*etype = FILTER_EXP_ADD;
+		*etype = TEP_FILTER_EXP_ADD;
 	} else if (strcmp(token, "-") == 0) {
-		*etype = FILTER_EXP_SUB;
+		*etype = TEP_FILTER_EXP_SUB;
 	} else if (strcmp(token, "*") == 0) {
-		*etype = FILTER_EXP_MUL;
+		*etype = TEP_FILTER_EXP_MUL;
 	} else if (strcmp(token, "/") == 0) {
-		*etype = FILTER_EXP_DIV;
+		*etype = TEP_FILTER_EXP_DIV;
 	} else if (strcmp(token, "%") == 0) {
-		*etype = FILTER_EXP_MOD;
+		*etype = TEP_FILTER_EXP_MOD;
 	} else if (strcmp(token, ">>") == 0) {
-		*etype = FILTER_EXP_RSHIFT;
+		*etype = TEP_FILTER_EXP_RSHIFT;
 	} else if (strcmp(token, "<<") == 0) {
-		*etype = FILTER_EXP_LSHIFT;
+		*etype = TEP_FILTER_EXP_LSHIFT;
 	} else if (strcmp(token, "&") == 0) {
-		*etype = FILTER_EXP_AND;
+		*etype = TEP_FILTER_EXP_AND;
 	} else if (strcmp(token, "|") == 0) {
-		*etype = FILTER_EXP_OR;
+		*etype = TEP_FILTER_EXP_OR;
 	} else if (strcmp(token, "^") == 0) {
-		*etype = FILTER_EXP_XOR;
+		*etype = TEP_FILTER_EXP_XOR;
 	} else if (strcmp(token, "~") == 0)
-		*etype = FILTER_EXP_NOT;
+		*etype = TEP_FILTER_EXP_NOT;
 
-	if (*etype != FILTER_EXP_NONE)
+	if (*etype != TEP_FILTER_EXP_NONE)
 		return OP_EXP;
 
 	/* Check for compares */
@@ -723,20 +723,20 @@ static enum op_type process_op(const char *token,
 static int check_op_done(struct filter_arg *arg)
 {
 	switch (arg->type) {
-	case FILTER_ARG_EXP:
+	case TEP_FILTER_ARG_EXP:
 		return arg->exp.right != NULL;
 
-	case FILTER_ARG_OP:
+	case TEP_FILTER_ARG_OP:
 		return arg->op.right != NULL;
 
-	case FILTER_ARG_NUM:
+	case TEP_FILTER_ARG_NUM:
 		return arg->num.right != NULL;
 
-	case FILTER_ARG_STR:
+	case TEP_FILTER_ARG_STR:
 		/* A string conversion is always done */
 		return 1;
 
-	case FILTER_ARG_BOOLEAN:
+	case TEP_FILTER_ARG_BOOLEAN:
 		/* field not found, is ok */
 		return 1;
 
@@ -758,8 +758,8 @@ reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
 	struct filter_arg *other_child;
 	struct filter_arg **ptr;
 
-	if (parent->type != FILTER_ARG_OP &&
-	    arg->type != FILTER_ARG_OP) {
+	if (parent->type != TEP_FILTER_ARG_OP &&
+	    arg->type != TEP_FILTER_ARG_OP) {
 		show_error(error_str, "can not reparent other than OP");
 		return TEP_ERRNO__REPARENT_NOT_OP;
 	}
@@ -812,16 +812,16 @@ static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
 	switch (arg->type) {
 
 		/* bad case */
-	case FILTER_ARG_BOOLEAN:
+	case TEP_FILTER_ARG_BOOLEAN:
 		return FILTER_VAL_FALSE + arg->boolean.value;
 
 		/* good cases: */
-	case FILTER_ARG_STR:
-	case FILTER_ARG_VALUE:
-	case FILTER_ARG_FIELD:
+	case TEP_FILTER_ARG_STR:
+	case TEP_FILTER_ARG_VALUE:
+	case TEP_FILTER_ARG_FIELD:
 		return FILTER_VAL_NORM;
 
-	case FILTER_ARG_EXP:
+	case TEP_FILTER_ARG_EXP:
 		lval = test_arg(arg, arg->exp.left, error_str);
 		if (lval != FILTER_VAL_NORM)
 			return lval;
@@ -830,7 +830,7 @@ static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
 			return rval;
 		return FILTER_VAL_NORM;
 
-	case FILTER_ARG_NUM:
+	case TEP_FILTER_ARG_NUM:
 		lval = test_arg(arg, arg->num.left, error_str);
 		if (lval != FILTER_VAL_NORM)
 			return lval;
@@ -839,7 +839,7 @@ static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
 			return rval;
 		return FILTER_VAL_NORM;
 
-	case FILTER_ARG_OP:
+	case TEP_FILTER_ARG_OP:
 		if (arg->op.type != TEP_FILTER_OP_NOT) {
 			lval = test_arg(arg, arg->op.left, error_str);
 			switch (lval) {
@@ -919,7 +919,7 @@ static int collapse_tree(struct filter_arg *arg,
 		free_arg(arg);
 		arg = allocate_arg();
 		if (arg) {
-			arg->type = FILTER_ARG_BOOLEAN;
+			arg->type = TEP_FILTER_ARG_BOOLEAN;
 			arg->boolean.value = ret == FILTER_VAL_TRUE;
 		} else {
 			show_error(error_str, "Failed to allocate filter arg");
@@ -950,7 +950,7 @@ process_filter(struct tep_event_format *event, struct filter_arg **parg,
 	struct filter_arg *arg = NULL;
 	enum op_type op_type;
 	enum tep_filter_op_type btype;
-	enum filter_exp_type etype;
+	enum tep_filter_exp_type etype;
 	enum tep_filter_cmp_type ctype;
 	enum tep_errno ret;
 
@@ -1196,7 +1196,7 @@ process_event(struct tep_event_format *event, const char *filter_str,
 		if (*parg == NULL)
 			return TEP_ERRNO__MEM_ALLOC_FAILED;
 
-		(*parg)->type = FILTER_ARG_BOOLEAN;
+		(*parg)->type = TEP_FILTER_ARG_BOOLEAN;
 		(*parg)->boolean.value = TEP_FILTER_FALSE;
 	}
 
@@ -1222,7 +1222,7 @@ filter_event(struct event_filter *filter, struct tep_event_format *event,
 		if (arg == NULL)
 			return TEP_ERRNO__MEM_ALLOC_FAILED;
 
-		arg->type = FILTER_ARG_BOOLEAN;
+		arg->type = TEP_FILTER_ARG_BOOLEAN;
 		arg->boolean.value = TEP_FILTER_TRUE;
 	}
 
@@ -1478,7 +1478,7 @@ static int copy_filter_type(struct event_filter *filter,
 		if (arg == NULL)
 			return -1;
 
-		arg->type = FILTER_ARG_BOOLEAN;
+		arg->type = TEP_FILTER_ARG_BOOLEAN;
 		if (strcmp(str, "TRUE") == 0)
 			arg->boolean.value = 1;
 		else
@@ -1554,7 +1554,7 @@ int tep_update_trivial(struct event_filter *dest, struct event_filter *source,
 	for (i = 0; i < dest->filters; i++) {
 		filter_type = &dest->event_filters[i];
 		arg = filter_type->filter;
-		if (arg->type != FILTER_ARG_BOOLEAN)
+		if (arg->type != TEP_FILTER_ARG_BOOLEAN)
 			continue;
 		if ((arg->boolean.value && type == FILTER_TRIVIAL_FALSE) ||
 		    (!arg->boolean.value && type == FILTER_TRIVIAL_TRUE))
@@ -1611,7 +1611,7 @@ int tep_filter_clear_trivial(struct event_filter *filter,
 		int *new_ids;
 
 		filter_type = &filter->event_filters[i];
-		if (filter_type->filter->type != FILTER_ARG_BOOLEAN)
+		if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN)
 			continue;
 		switch (type) {
 		case FILTER_TRIVIAL_FALSE:
@@ -1668,7 +1668,7 @@ int tep_filter_event_has_trivial(struct event_filter *filter,
 	if (!filter_type)
 		return 0;
 
-	if (filter_type->filter->type != FILTER_ARG_BOOLEAN)
+	if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN)
 		return 0;
 
 	switch (type) {
@@ -1753,37 +1753,37 @@ get_exp_value(struct tep_event_format *event, struct filter_arg *arg,
 	}
 
 	switch (arg->exp.type) {
-	case FILTER_EXP_ADD:
+	case TEP_FILTER_EXP_ADD:
 		return lval + rval;
 
-	case FILTER_EXP_SUB:
+	case TEP_FILTER_EXP_SUB:
 		return lval - rval;
 
-	case FILTER_EXP_MUL:
+	case TEP_FILTER_EXP_MUL:
 		return lval * rval;
 
-	case FILTER_EXP_DIV:
+	case TEP_FILTER_EXP_DIV:
 		return lval / rval;
 
-	case FILTER_EXP_MOD:
+	case TEP_FILTER_EXP_MOD:
 		return lval % rval;
 
-	case FILTER_EXP_RSHIFT:
+	case TEP_FILTER_EXP_RSHIFT:
 		return lval >> rval;
 
-	case FILTER_EXP_LSHIFT:
+	case TEP_FILTER_EXP_LSHIFT:
 		return lval << rval;
 
-	case FILTER_EXP_AND:
+	case TEP_FILTER_EXP_AND:
 		return lval & rval;
 
-	case FILTER_EXP_OR:
+	case TEP_FILTER_EXP_OR:
 		return lval | rval;
 
-	case FILTER_EXP_XOR:
+	case TEP_FILTER_EXP_XOR:
 		return lval ^ rval;
 
-	case FILTER_EXP_NOT:
+	case TEP_FILTER_EXP_NOT:
 	default:
 		if (!*err)
 			*err = TEP_ERRNO__INVALID_EXP_TYPE;
@@ -1796,17 +1796,17 @@ get_arg_value(struct tep_event_format *event, struct filter_arg *arg,
 	      struct tep_record *record, enum tep_errno *err)
 {
 	switch (arg->type) {
-	case FILTER_ARG_FIELD:
+	case TEP_FILTER_ARG_FIELD:
 		return get_value(event, arg->field.field, record);
 
-	case FILTER_ARG_VALUE:
+	case TEP_FILTER_ARG_VALUE:
 		if (arg->value.type != FILTER_NUMBER) {
 			if (!*err)
 				*err = TEP_ERRNO__NOT_A_NUMBER;
 		}
 		return arg->value.val;
 
-	case FILTER_ARG_EXP:
+	case TEP_FILTER_ARG_EXP:
 		return get_exp_value(event, arg, record, err);
 
 	default:
@@ -1971,22 +1971,22 @@ static int test_filter(struct tep_event_format *event, struct filter_arg *arg,
 	}
 
 	switch (arg->type) {
-	case FILTER_ARG_BOOLEAN:
+	case TEP_FILTER_ARG_BOOLEAN:
 		/* easy case */
 		return arg->boolean.value;
 
-	case FILTER_ARG_OP:
+	case TEP_FILTER_ARG_OP:
 		return test_op(event, arg, record, err);
 
-	case FILTER_ARG_NUM:
+	case TEP_FILTER_ARG_NUM:
 		return test_num(event, arg, record, err);
 
-	case FILTER_ARG_STR:
+	case TEP_FILTER_ARG_STR:
 		return test_str(event, arg, record, err);
 
-	case FILTER_ARG_EXP:
-	case FILTER_ARG_VALUE:
-	case FILTER_ARG_FIELD:
+	case TEP_FILTER_ARG_EXP:
+	case TEP_FILTER_ARG_VALUE:
+	case TEP_FILTER_ARG_FIELD:
 		/*
 		 * Expressions, fields and values evaluate
 		 * to true if they return non zero
@@ -2190,34 +2190,34 @@ static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg)
 		goto out;
 
 	switch (arg->exp.type) {
-	case FILTER_EXP_ADD:
+	case TEP_FILTER_EXP_ADD:
 		op = "+";
 		break;
-	case FILTER_EXP_SUB:
+	case TEP_FILTER_EXP_SUB:
 		op = "-";
 		break;
-	case FILTER_EXP_MUL:
+	case TEP_FILTER_EXP_MUL:
 		op = "*";
 		break;
-	case FILTER_EXP_DIV:
+	case TEP_FILTER_EXP_DIV:
 		op = "/";
 		break;
-	case FILTER_EXP_MOD:
+	case TEP_FILTER_EXP_MOD:
 		op = "%";
 		break;
-	case FILTER_EXP_RSHIFT:
+	case TEP_FILTER_EXP_RSHIFT:
 		op = ">>";
 		break;
-	case FILTER_EXP_LSHIFT:
+	case TEP_FILTER_EXP_LSHIFT:
 		op = "<<";
 		break;
-	case FILTER_EXP_AND:
+	case TEP_FILTER_EXP_AND:
 		op = "&";
 		break;
-	case FILTER_EXP_OR:
+	case TEP_FILTER_EXP_OR:
 		op = "|";
 		break;
-	case FILTER_EXP_XOR:
+	case TEP_FILTER_EXP_XOR:
 		op = "^";
 		break;
 	default:
@@ -2320,26 +2320,26 @@ static char *arg_to_str(struct event_filter *filter, struct filter_arg *arg)
 	char *str = NULL;
 
 	switch (arg->type) {
-	case FILTER_ARG_BOOLEAN:
+	case TEP_FILTER_ARG_BOOLEAN:
 		asprintf(&str, arg->boolean.value ? "TRUE" : "FALSE");
 		return str;
 
-	case FILTER_ARG_OP:
+	case TEP_FILTER_ARG_OP:
 		return op_to_str(filter, arg);
 
-	case FILTER_ARG_NUM:
+	case TEP_FILTER_ARG_NUM:
 		return num_to_str(filter, arg);
 
-	case FILTER_ARG_STR:
+	case TEP_FILTER_ARG_STR:
 		return str_to_str(filter, arg);
 
-	case FILTER_ARG_VALUE:
+	case TEP_FILTER_ARG_VALUE:
 		return val_to_str(filter, arg);
 
-	case FILTER_ARG_FIELD:
+	case TEP_FILTER_ARG_FIELD:
 		return field_to_str(filter, arg);
 
-	case FILTER_ARG_EXP:
+	case TEP_FILTER_ARG_EXP:
 		return exp_to_str(filter, arg);
 
 	default:
-- 
cgit v1.2.3


From 0515ca53caa681ad945fbea218e691e8637b4d7d Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Wed, 19 Sep 2018 14:56:53 -0400
Subject: tools lib traceevent: Add prefix tep_ to struct
 filter_{arg,value_type}

In order to make libtraceevent into a proper library, variables, data
structures and functions require a unique prefix to prevent name space
conflicts. That prefix will be "tep_". This adds prefix tep_ to
struct filter_arg, enum filter_value_type and all enum's members.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lkml.kernel.org/r/20180919185723.972818215@goodmis.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.h  |  28 ++++-----
 tools/lib/traceevent/parse-filter.c | 120 ++++++++++++++++++------------------
 2 files changed, 74 insertions(+), 74 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 5e55c83d43fe..64ce3eb0dcbc 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -819,13 +819,13 @@ enum tep_filter_arg_type {
 	TEP_FILTER_ARG_STR,
 };
 
-enum filter_value_type {
-	FILTER_NUMBER,
-	FILTER_STRING,
-	FILTER_CHAR
+enum tep_filter_value_type {
+	TEP_FILTER_NUMBER,
+	TEP_FILTER_STRING,
+	TEP_FILTER_CHAR
 };
 
-struct fliter_arg;
+struct tep_filter_arg;
 
 struct filter_arg_boolean {
 	enum tep_filter_boolean_type	value;
@@ -836,7 +836,7 @@ struct filter_arg_field {
 };
 
 struct filter_arg_value {
-	enum filter_value_type	type;
+	enum tep_filter_value_type	type;
 	union {
 		char			*str;
 		unsigned long long	val;
@@ -845,20 +845,20 @@ struct filter_arg_value {
 
 struct filter_arg_op {
 	enum tep_filter_op_type	type;
-	struct filter_arg	*left;
-	struct filter_arg	*right;
+	struct tep_filter_arg	*left;
+	struct tep_filter_arg	*right;
 };
 
 struct filter_arg_exp {
 	enum tep_filter_exp_type	type;
-	struct filter_arg		*left;
-	struct filter_arg		*right;
+	struct tep_filter_arg		*left;
+	struct tep_filter_arg		*right;
 };
 
 struct filter_arg_num {
 	enum tep_filter_cmp_type	type;
-	struct filter_arg	*left;
-	struct filter_arg	*right;
+	struct tep_filter_arg	*left;
+	struct tep_filter_arg	*right;
 };
 
 struct filter_arg_str {
@@ -869,7 +869,7 @@ struct filter_arg_str {
 	regex_t			reg;
 };
 
-struct filter_arg {
+struct tep_filter_arg {
 	enum tep_filter_arg_type		type;
 	union {
 		struct filter_arg_boolean	boolean;
@@ -885,7 +885,7 @@ struct filter_arg {
 struct filter_type {
 	int			event_id;
 	struct tep_event_format	*event;
-	struct filter_arg	*filter;
+	struct tep_filter_arg	*filter;
 };
 
 #define TEP_FILTER_ERROR_BUFSZ  1024
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index d1e0dd5b63ea..b9ca1b9e14e4 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -180,12 +180,12 @@ struct event_filter *tep_filter_alloc(struct tep_handle *pevent)
 	return filter;
 }
 
-static struct filter_arg *allocate_arg(void)
+static struct tep_filter_arg *allocate_arg(void)
 {
-	return calloc(1, sizeof(struct filter_arg));
+	return calloc(1, sizeof(struct tep_filter_arg));
 }
 
-static void free_arg(struct filter_arg *arg)
+static void free_arg(struct tep_filter_arg *arg)
 {
 	if (!arg)
 		return;
@@ -212,8 +212,8 @@ static void free_arg(struct filter_arg *arg)
 		break;
 
 	case TEP_FILTER_ARG_VALUE:
-		if (arg->value.type == FILTER_STRING ||
-		    arg->value.type == FILTER_CHAR)
+		if (arg->value.type == TEP_FILTER_STRING ||
+		    arg->value.type == TEP_FILTER_CHAR)
 			free(arg->value.str);
 		break;
 
@@ -334,10 +334,10 @@ static void free_events(struct event_list *events)
 
 static enum tep_errno
 create_arg_item(struct tep_event_format *event, const char *token,
-		enum tep_event_type type, struct filter_arg **parg, char *error_str)
+		enum tep_event_type type, struct tep_filter_arg **parg, char *error_str)
 {
 	struct tep_format_field *field;
-	struct filter_arg *arg;
+	struct tep_filter_arg *arg;
 
 	arg = allocate_arg();
 	if (arg == NULL) {
@@ -351,7 +351,7 @@ create_arg_item(struct tep_event_format *event, const char *token,
 	case TEP_EVENT_DQUOTE:
 		arg->type = TEP_FILTER_ARG_VALUE;
 		arg->value.type =
-			type == TEP_EVENT_DQUOTE ? FILTER_STRING : FILTER_CHAR;
+			type == TEP_EVENT_DQUOTE ? TEP_FILTER_STRING : TEP_FILTER_CHAR;
 		arg->value.str = strdup(token);
 		if (!arg->value.str) {
 			free_arg(arg);
@@ -363,7 +363,7 @@ create_arg_item(struct tep_event_format *event, const char *token,
 		/* if it is a number, then convert it */
 		if (isdigit(token[0])) {
 			arg->type = TEP_FILTER_ARG_VALUE;
-			arg->value.type = FILTER_NUMBER;
+			arg->value.type = TEP_FILTER_NUMBER;
 			arg->value.val = strtoull(token, NULL, 0);
 			break;
 		}
@@ -394,10 +394,10 @@ create_arg_item(struct tep_event_format *event, const char *token,
 	return 0;
 }
 
-static struct filter_arg *
+static struct tep_filter_arg *
 create_arg_op(enum tep_filter_op_type btype)
 {
-	struct filter_arg *arg;
+	struct tep_filter_arg *arg;
 
 	arg = allocate_arg();
 	if (!arg)
@@ -409,10 +409,10 @@ create_arg_op(enum tep_filter_op_type btype)
 	return arg;
 }
 
-static struct filter_arg *
+static struct tep_filter_arg *
 create_arg_exp(enum tep_filter_exp_type etype)
 {
-	struct filter_arg *arg;
+	struct tep_filter_arg *arg;
 
 	arg = allocate_arg();
 	if (!arg)
@@ -424,10 +424,10 @@ create_arg_exp(enum tep_filter_exp_type etype)
 	return arg;
 }
 
-static struct filter_arg *
+static struct tep_filter_arg *
 create_arg_cmp(enum tep_filter_cmp_type ctype)
 {
-	struct filter_arg *arg;
+	struct tep_filter_arg *arg;
 
 	arg = allocate_arg();
 	if (!arg)
@@ -441,9 +441,9 @@ create_arg_cmp(enum tep_filter_cmp_type ctype)
 }
 
 static enum tep_errno
-add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
+add_right(struct tep_filter_arg *op, struct tep_filter_arg *arg, char *error_str)
 {
-	struct filter_arg *left;
+	struct tep_filter_arg *left;
 	char *str;
 	int op_type;
 	int ret;
@@ -481,7 +481,7 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 		 * convert this to a string or regex.
 		 */
 		switch (arg->value.type) {
-		case FILTER_CHAR:
+		case TEP_FILTER_CHAR:
 			/*
 			 * A char should be converted to number if
 			 * the string is 1 byte, and the compare
@@ -490,11 +490,11 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 			if (strlen(arg->value.str) == 1 &&
 			    op->num.type != TEP_FILTER_CMP_REGEX &&
 			    op->num.type != TEP_FILTER_CMP_NOT_REGEX) {
-				arg->value.type = FILTER_NUMBER;
+				arg->value.type = TEP_FILTER_NUMBER;
 				goto do_int;
 			}
 			/* fall through */
-		case FILTER_STRING:
+		case TEP_FILTER_STRING:
 
 			/* convert op to a string arg */
 			op_type = op->num.type;
@@ -573,7 +573,7 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 
 			break;
 
-		case FILTER_NUMBER:
+		case TEP_FILTER_NUMBER:
 
  do_int:
 			switch (op->num.type) {
@@ -605,17 +605,17 @@ add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 	return TEP_ERRNO__SYNTAX_ERROR;
 }
 
-static struct filter_arg *
-rotate_op_right(struct filter_arg *a, struct filter_arg *b)
+static struct tep_filter_arg *
+rotate_op_right(struct tep_filter_arg *a, struct tep_filter_arg *b)
 {
-	struct filter_arg *arg;
+	struct tep_filter_arg *arg;
 
 	arg = a->op.right;
 	a->op.right = b;
 	return arg;
 }
 
-static enum tep_errno add_left(struct filter_arg *op, struct filter_arg *arg)
+static enum tep_errno add_left(struct tep_filter_arg *op, struct tep_filter_arg *arg)
 {
 	switch (op->type) {
 	case TEP_FILTER_ARG_EXP:
@@ -720,7 +720,7 @@ static enum op_type process_op(const char *token,
 	return OP_CMP;
 }
 
-static int check_op_done(struct filter_arg *arg)
+static int check_op_done(struct tep_filter_arg *arg)
 {
 	switch (arg->type) {
 	case TEP_FILTER_ARG_EXP:
@@ -752,11 +752,11 @@ enum filter_vals {
 };
 
 static enum tep_errno
-reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
-		struct filter_arg *arg, char *error_str)
+reparent_op_arg(struct tep_filter_arg *parent, struct tep_filter_arg *old_child,
+		struct tep_filter_arg *arg, char *error_str)
 {
-	struct filter_arg *other_child;
-	struct filter_arg **ptr;
+	struct tep_filter_arg *other_child;
+	struct tep_filter_arg **ptr;
 
 	if (parent->type != TEP_FILTER_ARG_OP &&
 	    arg->type != TEP_FILTER_ARG_OP) {
@@ -804,7 +804,7 @@ reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
 }
 
 /* Returns either filter_vals (success) or tep_errno (failfure) */
-static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
+static int test_arg(struct tep_filter_arg *parent, struct tep_filter_arg *arg,
 		    char *error_str)
 {
 	int lval, rval;
@@ -904,8 +904,8 @@ static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
 }
 
 /* Remove any unknown event fields */
-static int collapse_tree(struct filter_arg *arg,
-			 struct filter_arg **arg_collapsed, char *error_str)
+static int collapse_tree(struct tep_filter_arg *arg,
+			 struct tep_filter_arg **arg_collapsed, char *error_str)
 {
 	int ret;
 
@@ -939,15 +939,15 @@ static int collapse_tree(struct filter_arg *arg,
 }
 
 static enum tep_errno
-process_filter(struct tep_event_format *event, struct filter_arg **parg,
+process_filter(struct tep_event_format *event, struct tep_filter_arg **parg,
 	       char *error_str, int not)
 {
 	enum tep_event_type type;
 	char *token = NULL;
-	struct filter_arg *current_op = NULL;
-	struct filter_arg *current_exp = NULL;
-	struct filter_arg *left_item = NULL;
-	struct filter_arg *arg = NULL;
+	struct tep_filter_arg *current_op = NULL;
+	struct tep_filter_arg *current_exp = NULL;
+	struct tep_filter_arg *left_item = NULL;
+	struct tep_filter_arg *arg = NULL;
 	enum op_type op_type;
 	enum tep_filter_op_type btype;
 	enum tep_filter_exp_type etype;
@@ -1180,7 +1180,7 @@ process_filter(struct tep_event_format *event, struct filter_arg **parg,
 
 static enum tep_errno
 process_event(struct tep_event_format *event, const char *filter_str,
-	      struct filter_arg **parg, char *error_str)
+	      struct tep_filter_arg **parg, char *error_str)
 {
 	int ret;
 
@@ -1208,7 +1208,7 @@ filter_event(struct event_filter *filter, struct tep_event_format *event,
 	     const char *filter_str, char *error_str)
 {
 	struct filter_type *filter_type;
-	struct filter_arg *arg;
+	struct tep_filter_arg *arg;
 	enum tep_errno ret;
 
 	if (filter_str) {
@@ -1449,13 +1449,13 @@ void tep_filter_free(struct event_filter *filter)
 	free(filter);
 }
 
-static char *arg_to_str(struct event_filter *filter, struct filter_arg *arg);
+static char *arg_to_str(struct event_filter *filter, struct tep_filter_arg *arg);
 
 static int copy_filter_type(struct event_filter *filter,
 			     struct event_filter *source,
 			     struct filter_type *filter_type)
 {
-	struct filter_arg *arg;
+	struct tep_filter_arg *arg;
 	struct tep_event_format *event;
 	const char *sys;
 	const char *name;
@@ -1540,7 +1540,7 @@ int tep_update_trivial(struct event_filter *dest, struct event_filter *source,
 	struct tep_handle *dest_pevent;
 	struct tep_event_format *event;
 	struct filter_type *filter_type;
-	struct filter_arg *arg;
+	struct tep_filter_arg *arg;
 	char *str;
 	int i;
 
@@ -1682,7 +1682,7 @@ int tep_filter_event_has_trivial(struct event_filter *filter,
 	}
 }
 
-static int test_filter(struct tep_event_format *event, struct filter_arg *arg,
+static int test_filter(struct tep_event_format *event, struct tep_filter_arg *arg,
 		       struct tep_record *record, enum tep_errno *err);
 
 static const char *
@@ -1733,11 +1733,11 @@ get_value(struct tep_event_format *event,
 }
 
 static unsigned long long
-get_arg_value(struct tep_event_format *event, struct filter_arg *arg,
+get_arg_value(struct tep_event_format *event, struct tep_filter_arg *arg,
 	      struct tep_record *record, enum tep_errno *err);
 
 static unsigned long long
-get_exp_value(struct tep_event_format *event, struct filter_arg *arg,
+get_exp_value(struct tep_event_format *event, struct tep_filter_arg *arg,
 	      struct tep_record *record, enum tep_errno *err)
 {
 	unsigned long long lval, rval;
@@ -1792,7 +1792,7 @@ get_exp_value(struct tep_event_format *event, struct filter_arg *arg,
 }
 
 static unsigned long long
-get_arg_value(struct tep_event_format *event, struct filter_arg *arg,
+get_arg_value(struct tep_event_format *event, struct tep_filter_arg *arg,
 	      struct tep_record *record, enum tep_errno *err)
 {
 	switch (arg->type) {
@@ -1800,7 +1800,7 @@ get_arg_value(struct tep_event_format *event, struct filter_arg *arg,
 		return get_value(event, arg->field.field, record);
 
 	case TEP_FILTER_ARG_VALUE:
-		if (arg->value.type != FILTER_NUMBER) {
+		if (arg->value.type != TEP_FILTER_NUMBER) {
 			if (!*err)
 				*err = TEP_ERRNO__NOT_A_NUMBER;
 		}
@@ -1816,7 +1816,7 @@ get_arg_value(struct tep_event_format *event, struct filter_arg *arg,
 	return 0;
 }
 
-static int test_num(struct tep_event_format *event, struct filter_arg *arg,
+static int test_num(struct tep_event_format *event, struct tep_filter_arg *arg,
 		    struct tep_record *record, enum tep_errno *err)
 {
 	unsigned long long lval, rval;
@@ -1857,7 +1857,7 @@ static int test_num(struct tep_event_format *event, struct filter_arg *arg,
 	}
 }
 
-static const char *get_field_str(struct filter_arg *arg, struct tep_record *record)
+static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record *record)
 {
 	struct tep_event_format *event;
 	struct tep_handle *pevent;
@@ -1907,7 +1907,7 @@ static const char *get_field_str(struct filter_arg *arg, struct tep_record *reco
 	return val;
 }
 
-static int test_str(struct tep_event_format *event, struct filter_arg *arg,
+static int test_str(struct tep_event_format *event, struct tep_filter_arg *arg,
 		    struct tep_record *record, enum tep_errno *err)
 {
 	const char *val;
@@ -1938,7 +1938,7 @@ static int test_str(struct tep_event_format *event, struct filter_arg *arg,
 	}
 }
 
-static int test_op(struct tep_event_format *event, struct filter_arg *arg,
+static int test_op(struct tep_event_format *event, struct tep_filter_arg *arg,
 		   struct tep_record *record, enum tep_errno *err)
 {
 	switch (arg->op.type) {
@@ -1960,7 +1960,7 @@ static int test_op(struct tep_event_format *event, struct filter_arg *arg,
 	}
 }
 
-static int test_filter(struct tep_event_format *event, struct filter_arg *arg,
+static int test_filter(struct tep_event_format *event, struct tep_filter_arg *arg,
 		       struct tep_record *record, enum tep_errno *err)
 {
 	if (*err) {
@@ -2059,7 +2059,7 @@ enum tep_errno tep_filter_match(struct event_filter *filter,
 	return ret ? TEP_ERRNO__FILTER_MATCH : TEP_ERRNO__FILTER_MISS;
 }
 
-static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *op_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *str = NULL;
 	char *left = NULL;
@@ -2163,7 +2163,7 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 	return str;
 }
 
-static char *val_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *val_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *str = NULL;
 
@@ -2172,12 +2172,12 @@ static char *val_to_str(struct event_filter *filter, struct filter_arg *arg)
 	return str;
 }
 
-static char *field_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *field_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
 {
 	return strdup(arg->field.field->name);
 }
 
-static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *exp_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *lstr;
 	char *rstr;
@@ -2233,7 +2233,7 @@ out:
 	return str;
 }
 
-static char *num_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *num_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *lstr;
 	char *rstr;
@@ -2283,7 +2283,7 @@ out:
 	return str;
 }
 
-static char *str_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *str_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *str = NULL;
 	char *op = NULL;
@@ -2315,7 +2315,7 @@ static char *str_to_str(struct event_filter *filter, struct filter_arg *arg)
 	return str;
 }
 
-static char *arg_to_str(struct event_filter *filter, struct filter_arg *arg)
+static char *arg_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *str = NULL;
 
-- 
cgit v1.2.3


From 88e6c21a11c5464ebdaefeb18822ab55f37a6473 Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Wed, 19 Sep 2018 14:56:54 -0400
Subject: tools lib traceevent: Add prefix tep_ to various structs
 filter_arg_*.

In order to make libtraceevent into a proper library, variables, data
structures and functions require a unique prefix to prevent name space
conflicts. That prefix will be "tep_". This adds prefix tep_ to
to various structs filter_arg_*..

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lkml.kernel.org/r/20180919185724.152948543@goodmis.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.h | 48 +++++++++++++++++++-------------------
 1 file changed, 24 insertions(+), 24 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 64ce3eb0dcbc..1330fca2da1e 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -827,15 +827,15 @@ enum tep_filter_value_type {
 
 struct tep_filter_arg;
 
-struct filter_arg_boolean {
+struct tep_filter_arg_boolean {
 	enum tep_filter_boolean_type	value;
 };
 
-struct filter_arg_field {
-	struct tep_format_field	*field;
+struct tep_filter_arg_field {
+	struct tep_format_field		*field;
 };
 
-struct filter_arg_value {
+struct tep_filter_arg_value {
 	enum tep_filter_value_type	type;
 	union {
 		char			*str;
@@ -843,42 +843,42 @@ struct filter_arg_value {
 	};
 };
 
-struct filter_arg_op {
-	enum tep_filter_op_type	type;
-	struct tep_filter_arg	*left;
-	struct tep_filter_arg	*right;
+struct tep_filter_arg_op {
+	enum tep_filter_op_type		type;
+	struct tep_filter_arg		*left;
+	struct tep_filter_arg		*right;
 };
 
-struct filter_arg_exp {
+struct tep_filter_arg_exp {
 	enum tep_filter_exp_type	type;
 	struct tep_filter_arg		*left;
 	struct tep_filter_arg		*right;
 };
 
-struct filter_arg_num {
+struct tep_filter_arg_num {
 	enum tep_filter_cmp_type	type;
-	struct tep_filter_arg	*left;
-	struct tep_filter_arg	*right;
+	struct tep_filter_arg		*left;
+	struct tep_filter_arg		*right;
 };
 
-struct filter_arg_str {
+struct tep_filter_arg_str {
 	enum tep_filter_cmp_type	type;
-	struct tep_format_field	*field;
-	char			*val;
-	char			*buffer;
-	regex_t			reg;
+	struct tep_format_field		*field;
+	char				*val;
+	char				*buffer;
+	regex_t				reg;
 };
 
 struct tep_filter_arg {
 	enum tep_filter_arg_type		type;
 	union {
-		struct filter_arg_boolean	boolean;
-		struct filter_arg_field		field;
-		struct filter_arg_value		value;
-		struct filter_arg_op		op;
-		struct filter_arg_exp		exp;
-		struct filter_arg_num		num;
-		struct filter_arg_str		str;
+		struct tep_filter_arg_boolean	boolean;
+		struct tep_filter_arg_field	field;
+		struct tep_filter_arg_value	value;
+		struct tep_filter_arg_op	op;
+		struct tep_filter_arg_exp	exp;
+		struct tep_filter_arg_num	num;
+		struct tep_filter_arg_str	str;
 	};
 };
 
-- 
cgit v1.2.3


From 9334c9616b71202c751a12edf5f83f51ec5a1663 Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Wed, 19 Sep 2018 14:56:55 -0400
Subject: tools lib traceevent: Add prefix tep_ to structs filter_type and
 event_filter

In order to make libtraceevent into a proper library, variables, data
structures and functions require a unique prefix to prevent name space
conflicts. That prefix will be "tep_". This adds prefix tep_ to
structs filter_type and event_filter

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lkml.kernel.org/r/20180919185724.309837130@goodmis.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.h  | 34 ++++++-------
 tools/lib/traceevent/parse-filter.c | 96 ++++++++++++++++++-------------------
 2 files changed, 65 insertions(+), 65 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 1330fca2da1e..1abf15882460 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -882,7 +882,7 @@ struct tep_filter_arg {
 	};
 };
 
-struct filter_type {
+struct tep_filter_type {
 	int			event_id;
 	struct tep_event_format	*event;
 	struct tep_filter_arg	*filter;
@@ -890,14 +890,14 @@ struct filter_type {
 
 #define TEP_FILTER_ERROR_BUFSZ  1024
 
-struct event_filter {
+struct tep_event_filter {
 	struct tep_handle	*pevent;
 	int			filters;
-	struct filter_type	*event_filters;
+	struct tep_filter_type	*event_filters;
 	char			error_buffer[TEP_FILTER_ERROR_BUFSZ];
 };
 
-struct event_filter *tep_filter_alloc(struct tep_handle *pevent);
+struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent);
 
 /* for backward compatibility */
 #define FILTER_NONE		TEP_ERRNO__NO_FILTER
@@ -911,39 +911,39 @@ enum filter_trivial_type {
 	FILTER_TRIVIAL_BOTH,
 };
 
-enum tep_errno tep_filter_add_filter_str(struct event_filter *filter,
+enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
 					 const char *filter_str);
 
-enum tep_errno tep_filter_match(struct event_filter *filter,
+enum tep_errno tep_filter_match(struct tep_event_filter *filter,
 				struct tep_record *record);
 
-int tep_filter_strerror(struct event_filter *filter, enum tep_errno err,
+int tep_filter_strerror(struct tep_event_filter *filter, enum tep_errno err,
 			char *buf, size_t buflen);
 
-int tep_event_filtered(struct event_filter *filter,
+int tep_event_filtered(struct tep_event_filter *filter,
 		       int event_id);
 
-void tep_filter_reset(struct event_filter *filter);
+void tep_filter_reset(struct tep_event_filter *filter);
 
-int tep_filter_clear_trivial(struct event_filter *filter,
+int tep_filter_clear_trivial(struct tep_event_filter *filter,
 			     enum filter_trivial_type type);
 
-void tep_filter_free(struct event_filter *filter);
+void tep_filter_free(struct tep_event_filter *filter);
 
-char *tep_filter_make_string(struct event_filter *filter, int event_id);
+char *tep_filter_make_string(struct tep_event_filter *filter, int event_id);
 
-int tep_filter_remove_event(struct event_filter *filter,
+int tep_filter_remove_event(struct tep_event_filter *filter,
 			    int event_id);
 
-int tep_filter_event_has_trivial(struct event_filter *filter,
+int tep_filter_event_has_trivial(struct tep_event_filter *filter,
 				 int event_id,
 				 enum filter_trivial_type type);
 
-int tep_filter_copy(struct event_filter *dest, struct event_filter *source);
+int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *source);
 
-int tep_update_trivial(struct event_filter *dest, struct event_filter *source,
+int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source,
 			enum filter_trivial_type type);
 
-int tep_filter_compare(struct event_filter *filter1, struct event_filter *filter2);
+int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter *filter2);
 
 #endif /* _PARSE_EVENTS_H */
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index b9ca1b9e14e4..875bfaf79771 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -94,8 +94,8 @@ static enum tep_event_type read_token(char **tok)
 
 static int filter_cmp(const void *a, const void *b)
 {
-	const struct filter_type *ea = a;
-	const struct filter_type *eb = b;
+	const struct tep_filter_type *ea = a;
+	const struct tep_filter_type *eb = b;
 
 	if (ea->event_id < eb->event_id)
 		return -1;
@@ -106,11 +106,11 @@ static int filter_cmp(const void *a, const void *b)
 	return 0;
 }
 
-static struct filter_type *
-find_filter_type(struct event_filter *filter, int id)
+static struct tep_filter_type *
+find_filter_type(struct tep_event_filter *filter, int id)
 {
-	struct filter_type *filter_type;
-	struct filter_type key;
+	struct tep_filter_type *filter_type;
+	struct tep_filter_type key;
 
 	key.event_id = id;
 
@@ -122,10 +122,10 @@ find_filter_type(struct event_filter *filter, int id)
 	return filter_type;
 }
 
-static struct filter_type *
-add_filter_type(struct event_filter *filter, int id)
+static struct tep_filter_type *
+add_filter_type(struct tep_event_filter *filter, int id)
 {
-	struct filter_type *filter_type;
+	struct tep_filter_type *filter_type;
 	int i;
 
 	filter_type = find_filter_type(filter, id);
@@ -165,9 +165,9 @@ add_filter_type(struct event_filter *filter, int id)
  * tep_filter_alloc - create a new event filter
  * @pevent: The pevent that this filter is associated with
  */
-struct event_filter *tep_filter_alloc(struct tep_handle *pevent)
+struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent)
 {
-	struct event_filter *filter;
+	struct tep_event_filter *filter;
 
 	filter = malloc(sizeof(*filter));
 	if (filter == NULL)
@@ -1204,10 +1204,10 @@ process_event(struct tep_event_format *event, const char *filter_str,
 }
 
 static enum tep_errno
-filter_event(struct event_filter *filter, struct tep_event_format *event,
+filter_event(struct tep_event_filter *filter, struct tep_event_format *event,
 	     const char *filter_str, char *error_str)
 {
-	struct filter_type *filter_type;
+	struct tep_filter_type *filter_type;
 	struct tep_filter_arg *arg;
 	enum tep_errno ret;
 
@@ -1237,7 +1237,7 @@ filter_event(struct event_filter *filter, struct tep_event_format *event,
 	return 0;
 }
 
-static void filter_init_error_buf(struct event_filter *filter)
+static void filter_init_error_buf(struct tep_event_filter *filter)
 {
 	/* clear buffer to reset show error */
 	tep_buffer_init("", 0);
@@ -1253,7 +1253,7 @@ static void filter_init_error_buf(struct event_filter *filter)
  * negative error code.  Use tep_filter_strerror() to see
  * actual error message in case of error.
  */
-enum tep_errno tep_filter_add_filter_str(struct event_filter *filter,
+enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
 					 const char *filter_str)
 {
 	struct tep_handle *pevent = filter->pevent;
@@ -1351,7 +1351,7 @@ enum tep_errno tep_filter_add_filter_str(struct event_filter *filter,
 	return rtn;
 }
 
-static void free_filter_type(struct filter_type *filter_type)
+static void free_filter_type(struct tep_filter_type *filter_type)
 {
 	free_arg(filter_type->filter);
 }
@@ -1365,7 +1365,7 @@ static void free_filter_type(struct filter_type *filter_type)
  *
  * Returns 0 if message was filled successfully, -1 if error
  */
-int tep_filter_strerror(struct event_filter *filter, enum tep_errno err,
+int tep_filter_strerror(struct tep_event_filter *filter, enum tep_errno err,
 			char *buf, size_t buflen)
 {
 	if (err <= __TEP_ERRNO__START || err >= __TEP_ERRNO__END)
@@ -1393,10 +1393,10 @@ int tep_filter_strerror(struct event_filter *filter, enum tep_errno err,
  * Returns 1: if an event was removed
  *   0: if the event was not found
  */
-int tep_filter_remove_event(struct event_filter *filter,
+int tep_filter_remove_event(struct tep_event_filter *filter,
 			    int event_id)
 {
-	struct filter_type *filter_type;
+	struct tep_filter_type *filter_type;
 	unsigned long len;
 
 	if (!filter->filters)
@@ -1428,7 +1428,7 @@ int tep_filter_remove_event(struct event_filter *filter,
  *
  * Removes all filters from a filter and resets it.
  */
-void tep_filter_reset(struct event_filter *filter)
+void tep_filter_reset(struct tep_event_filter *filter)
 {
 	int i;
 
@@ -1440,7 +1440,7 @@ void tep_filter_reset(struct event_filter *filter)
 	filter->event_filters = NULL;
 }
 
-void tep_filter_free(struct event_filter *filter)
+void tep_filter_free(struct tep_event_filter *filter)
 {
 	tep_unref(filter->pevent);
 
@@ -1449,11 +1449,11 @@ void tep_filter_free(struct event_filter *filter)
 	free(filter);
 }
 
-static char *arg_to_str(struct event_filter *filter, struct tep_filter_arg *arg);
+static char *arg_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg);
 
-static int copy_filter_type(struct event_filter *filter,
-			     struct event_filter *source,
-			     struct filter_type *filter_type)
+static int copy_filter_type(struct tep_event_filter *filter,
+			    struct tep_event_filter *source,
+			    struct tep_filter_type *filter_type)
 {
 	struct tep_filter_arg *arg;
 	struct tep_event_format *event;
@@ -1507,7 +1507,7 @@ static int copy_filter_type(struct event_filter *filter,
  *
  * Returns 0 on success and -1 if not all filters were copied
  */
-int tep_filter_copy(struct event_filter *dest, struct event_filter *source)
+int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *source)
 {
 	int ret = 0;
 	int i;
@@ -1533,13 +1533,13 @@ int tep_filter_copy(struct event_filter *dest, struct event_filter *source)
  * Returns 0 on success and -1 if there was a problem updating, but
  *   events may have still been updated on error.
  */
-int tep_update_trivial(struct event_filter *dest, struct event_filter *source,
+int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source,
 		       enum filter_trivial_type type)
 {
 	struct tep_handle *src_pevent;
 	struct tep_handle *dest_pevent;
 	struct tep_event_format *event;
-	struct filter_type *filter_type;
+	struct tep_filter_type *filter_type;
 	struct tep_filter_arg *arg;
 	char *str;
 	int i;
@@ -1592,10 +1592,10 @@ int tep_update_trivial(struct event_filter *dest, struct event_filter *source,
  *
  * Returns 0 on success and -1 if there was a problem.
  */
-int tep_filter_clear_trivial(struct event_filter *filter,
+int tep_filter_clear_trivial(struct tep_event_filter *filter,
 			     enum filter_trivial_type type)
 {
-	struct filter_type *filter_type;
+	struct tep_filter_type *filter_type;
 	int count = 0;
 	int *ids = NULL;
 	int i;
@@ -1654,11 +1654,11 @@ int tep_filter_clear_trivial(struct event_filter *filter,
  * Returns 1 if the event contains a matching trivial type
  *  otherwise 0.
  */
-int tep_filter_event_has_trivial(struct event_filter *filter,
+int tep_filter_event_has_trivial(struct tep_event_filter *filter,
 				 int event_id,
 				 enum filter_trivial_type type)
 {
-	struct filter_type *filter_type;
+	struct tep_filter_type *filter_type;
 
 	if (!filter->filters)
 		return 0;
@@ -2008,9 +2008,9 @@ static int test_filter(struct tep_event_format *event, struct tep_filter_arg *ar
  * Returns 1 if filter found for @event_id
  *   otherwise 0;
  */
-int tep_event_filtered(struct event_filter *filter, int event_id)
+int tep_event_filtered(struct tep_event_filter *filter, int event_id)
 {
-	struct filter_type *filter_type;
+	struct tep_filter_type *filter_type;
 
 	if (!filter->filters)
 		return 0;
@@ -2032,11 +2032,11 @@ int tep_event_filtered(struct event_filter *filter, int event_id)
  * NO_FILTER - if no filters exist
  * otherwise - error occurred during test
  */
-enum tep_errno tep_filter_match(struct event_filter *filter,
+enum tep_errno tep_filter_match(struct tep_event_filter *filter,
 				struct tep_record *record)
 {
 	struct tep_handle *pevent = filter->pevent;
-	struct filter_type *filter_type;
+	struct tep_filter_type *filter_type;
 	int event_id;
 	int ret;
 	enum tep_errno err = 0;
@@ -2059,7 +2059,7 @@ enum tep_errno tep_filter_match(struct event_filter *filter,
 	return ret ? TEP_ERRNO__FILTER_MATCH : TEP_ERRNO__FILTER_MISS;
 }
 
-static char *op_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
+static char *op_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *str = NULL;
 	char *left = NULL;
@@ -2163,7 +2163,7 @@ static char *op_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
 	return str;
 }
 
-static char *val_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
+static char *val_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *str = NULL;
 
@@ -2172,12 +2172,12 @@ static char *val_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
 	return str;
 }
 
-static char *field_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
+static char *field_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
 {
 	return strdup(arg->field.field->name);
 }
 
-static char *exp_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
+static char *exp_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *lstr;
 	char *rstr;
@@ -2233,7 +2233,7 @@ out:
 	return str;
 }
 
-static char *num_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
+static char *num_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *lstr;
 	char *rstr;
@@ -2283,7 +2283,7 @@ out:
 	return str;
 }
 
-static char *str_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
+static char *str_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *str = NULL;
 	char *op = NULL;
@@ -2315,7 +2315,7 @@ static char *str_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
 	return str;
 }
 
-static char *arg_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
+static char *arg_to_str(struct tep_event_filter *filter, struct tep_filter_arg *arg)
 {
 	char *str = NULL;
 
@@ -2359,9 +2359,9 @@ static char *arg_to_str(struct event_filter *filter, struct tep_filter_arg *arg)
  *  NULL is returned if no filter is found or allocation failed.
  */
 char *
-tep_filter_make_string(struct event_filter *filter, int event_id)
+tep_filter_make_string(struct tep_event_filter *filter, int event_id)
 {
-	struct filter_type *filter_type;
+	struct tep_filter_type *filter_type;
 
 	if (!filter->filters)
 		return NULL;
@@ -2383,10 +2383,10 @@ tep_filter_make_string(struct event_filter *filter, int event_id)
  *  1 if the two filters hold the same content.
  *  0 if they do not.
  */
-int tep_filter_compare(struct event_filter *filter1, struct event_filter *filter2)
+int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter *filter2)
 {
-	struct filter_type *filter_type1;
-	struct filter_type *filter_type2;
+	struct tep_filter_type *filter_type1;
+	struct tep_filter_type *filter_type2;
 	char *str1, *str2;
 	int result;
 	int i;
-- 
cgit v1.2.3


From 785be0c98d24aaf417588322c74999520ea790a4 Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Wed, 19 Sep 2018 14:56:56 -0400
Subject: tools lib traceevent: Rename struct plugin_list to struct
 tep_plugin_list

In order to make libtraceevent into a proper library, variables, data
structures and functions require a unique prefix to prevent name space
conflicts. That prefix will be "tep_". This renames struct plugin_list
to struct tep_plugin_list

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lkml.kernel.org/r/20180919185724.586889128@goodmis.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.h  |  8 ++++----
 tools/lib/traceevent/event-plugin.c | 18 +++++++++---------
 tools/perf/util/trace-event.h       |  4 ++--
 3 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 1abf15882460..2a7b0a857f39 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -389,12 +389,12 @@ enum tep_errno {
 };
 #undef _PE
 
-struct plugin_list;
+struct tep_plugin_list;
 
 #define INVALID_PLUGIN_LIST_OPTION	((char **)((unsigned long)-1))
 
-struct plugin_list *tep_load_plugins(struct tep_handle *pevent);
-void tep_unload_plugins(struct plugin_list *plugin_list,
+struct tep_plugin_list *tep_load_plugins(struct tep_handle *pevent);
+void tep_unload_plugins(struct tep_plugin_list *plugin_list,
 			struct tep_handle *pevent);
 char **tep_plugin_list_options(void);
 void tep_plugin_free_options_list(char **list);
@@ -403,7 +403,7 @@ int tep_plugin_add_options(const char *name,
 void tep_plugin_remove_options(struct tep_plugin_option *options);
 void tep_print_plugins(struct trace_seq *s,
 			const char *prefix, const char *suffix,
-			const struct plugin_list *list);
+			const struct tep_plugin_list *list);
 
 struct cmdline;
 struct cmdline_list;
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
index ec16a103c0cc..46eb64eb0c2e 100644
--- a/tools/lib/traceevent/event-plugin.c
+++ b/tools/lib/traceevent/event-plugin.c
@@ -31,8 +31,8 @@ static struct trace_plugin_options {
 	char				*value;
 } *trace_plugin_options;
 
-struct plugin_list {
-	struct plugin_list	*next;
+struct tep_plugin_list {
+	struct tep_plugin_list	*next;
 	char			*name;
 	void			*handle;
 };
@@ -259,7 +259,7 @@ void tep_plugin_remove_options(struct tep_plugin_option *options)
  */
 void tep_print_plugins(struct trace_seq *s,
 		       const char *prefix, const char *suffix,
-		       const struct plugin_list *list)
+		       const struct tep_plugin_list *list)
 {
 	while (list) {
 		trace_seq_printf(s, "%s%s%s", prefix, list->name, suffix);
@@ -271,9 +271,9 @@ static void
 load_plugin(struct tep_handle *pevent, const char *path,
 	    const char *file, void *data)
 {
-	struct plugin_list **plugin_list = data;
+	struct tep_plugin_list **plugin_list = data;
 	tep_plugin_load_func func;
-	struct plugin_list *list;
+	struct tep_plugin_list *list;
 	const char *alias;
 	char *plugin;
 	void *handle;
@@ -417,20 +417,20 @@ load_plugins(struct tep_handle *pevent, const char *suffix,
 	free(path);
 }
 
-struct plugin_list*
+struct tep_plugin_list*
 tep_load_plugins(struct tep_handle *pevent)
 {
-	struct plugin_list *list = NULL;
+	struct tep_plugin_list *list = NULL;
 
 	load_plugins(pevent, ".so", load_plugin, &list);
 	return list;
 }
 
 void
-tep_unload_plugins(struct plugin_list *plugin_list, struct tep_handle *pevent)
+tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *pevent)
 {
 	tep_plugin_unload_func func;
-	struct plugin_list *list;
+	struct tep_plugin_list *list;
 
 	while (plugin_list) {
 		list = plugin_list;
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 2da6eff0caaf..f024d73bfc40 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -11,11 +11,11 @@ struct perf_sample;
 union perf_event;
 struct perf_tool;
 struct thread;
-struct plugin_list;
+struct tep_plugin_list;
 
 struct trace_event {
 	struct tep_handle	*pevent;
-	struct plugin_list	*plugin_list;
+	struct tep_plugin_list	*plugin_list;
 };
 
 int trace_event__init(struct trace_event *t);
-- 
cgit v1.2.3


From 1affd34f192a516436a2e0cec15a97bc1001678a Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Wed, 19 Sep 2018 14:56:57 -0400
Subject: tools lib traceevent: Rename data2host*() APIs

In order to make libtraceevent into a proper library, variables, data
structures and functions require a unique prefix to prevent name space
conflicts. That prefix will be "tep_". This renames data2host*() APIs

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lkml.kernel.org/r/20180919185724.751088939@goodmis.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.c | 10 +++++-----
 tools/lib/traceevent/event-parse.h | 14 +++++++-------
 tools/perf/util/trace-event-read.c |  4 ++--
 3 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 055bee7b738a..7980fc6c3bac 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -3331,11 +3331,11 @@ unsigned long long tep_read_number(struct tep_handle *pevent,
 	case 1:
 		return *(unsigned char *)ptr;
 	case 2:
-		return data2host2(pevent, ptr);
+		return tep_data2host2(pevent, ptr);
 	case 4:
-		return data2host4(pevent, ptr);
+		return tep_data2host4(pevent, ptr);
 	case 8:
-		return data2host8(pevent, ptr);
+		return tep_data2host8(pevent, ptr);
 	default:
 		/* BUG! */
 		return 0;
@@ -4061,7 +4061,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			f = tep_find_any_field(event, arg->string.string);
 			arg->string.offset = f->offset;
 		}
-		str_offset = data2host4(pevent, data + arg->string.offset);
+		str_offset = tep_data2host4(pevent, data + arg->string.offset);
 		str_offset &= 0xffff;
 		print_str_to_seq(s, format, len_arg, ((char *)data) + str_offset);
 		break;
@@ -4079,7 +4079,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			f = tep_find_any_field(event, arg->bitmask.bitmask);
 			arg->bitmask.offset = f->offset;
 		}
-		bitmask_offset = data2host4(pevent, data + arg->bitmask.offset);
+		bitmask_offset = tep_data2host4(pevent, data + arg->bitmask.offset);
 		bitmask_size = bitmask_offset >> 16;
 		bitmask_offset &= 0xffff;
 		print_bitmask_to_seq(pevent, s, format, len_arg,
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 2a7b0a857f39..830147dc6b21 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -496,7 +496,7 @@ static inline void tep_set_flag(struct tep_handle *pevent, int flag)
 }
 
 static inline unsigned short
-__data2host2(struct tep_handle *pevent, unsigned short data)
+__tep_data2host2(struct tep_handle *pevent, unsigned short data)
 {
 	unsigned short swap;
 
@@ -510,7 +510,7 @@ __data2host2(struct tep_handle *pevent, unsigned short data)
 }
 
 static inline unsigned int
-__data2host4(struct tep_handle *pevent, unsigned int data)
+__tep_data2host4(struct tep_handle *pevent, unsigned int data)
 {
 	unsigned int swap;
 
@@ -526,7 +526,7 @@ __data2host4(struct tep_handle *pevent, unsigned int data)
 }
 
 static inline unsigned long long
-__data2host8(struct tep_handle *pevent, unsigned long long data)
+__tep_data2host8(struct tep_handle *pevent, unsigned long long data)
 {
 	unsigned long long swap;
 
@@ -545,14 +545,14 @@ __data2host8(struct tep_handle *pevent, unsigned long long data)
 	return swap;
 }
 
-#define data2host2(pevent, ptr)		__data2host2(pevent, *(unsigned short *)(ptr))
-#define data2host4(pevent, ptr)		__data2host4(pevent, *(unsigned int *)(ptr))
-#define data2host8(pevent, ptr)					\
+#define tep_data2host2(pevent, ptr)		__tep_data2host2(pevent, *(unsigned short *)(ptr))
+#define tep_data2host4(pevent, ptr)		__tep_data2host4(pevent, *(unsigned int *)(ptr))
+#define tep_data2host8(pevent, ptr)					\
 ({								\
 	unsigned long long __val;				\
 								\
 	memcpy(&__val, (ptr), sizeof(unsigned long long));	\
-	__data2host8(pevent, __val);				\
+	__tep_data2host8(pevent, __val);				\
 })
 
 static inline int tep_host_bigendian(void)
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 3dfc1db6b25b..b98ee2a2eb44 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -102,7 +102,7 @@ static unsigned int read4(struct tep_handle *pevent)
 
 	if (do_read(&data, 4) < 0)
 		return 0;
-	return __data2host4(pevent, data);
+	return __tep_data2host4(pevent, data);
 }
 
 static unsigned long long read8(struct tep_handle *pevent)
@@ -111,7 +111,7 @@ static unsigned long long read8(struct tep_handle *pevent)
 
 	if (do_read(&data, 8) < 0)
 		return 0;
-	return __data2host8(pevent, data);
+	return __tep_data2host8(pevent, data);
 }
 
 static char *read_string(void)
-- 
cgit v1.2.3


From 035c450ffa0483e715fc7b14a2e8b744bf8a740a Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Wed, 19 Sep 2018 14:56:58 -0400
Subject: tools lib traceevent: Add prefix tep_ to enum filter_trivial_type

In order to make libtraceevent into a proper library, variables, data
structures and functions require a unique prefix to prevent name space
conflicts. That prefix will be "tep_". This adds prefix tep_ to
enum filter_trivial_type and all its members.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lkml.kernel.org/r/20180919185725.076387655@goodmis.org
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/event-parse.h  | 14 +++++++-------
 tools/lib/traceevent/parse-filter.c | 22 +++++++++++-----------
 2 files changed, 18 insertions(+), 18 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 830147dc6b21..9c29a5f7aa39 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -905,10 +905,10 @@ struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent);
 #define FILTER_MISS		TEP_ERRNO__FILTER_MISS
 #define FILTER_MATCH		TEP_ERRNO__FILTER_MATCH
 
-enum filter_trivial_type {
-	FILTER_TRIVIAL_FALSE,
-	FILTER_TRIVIAL_TRUE,
-	FILTER_TRIVIAL_BOTH,
+enum tep_filter_trivial_type {
+	TEP_FILTER_TRIVIAL_FALSE,
+	TEP_FILTER_TRIVIAL_TRUE,
+	TEP_FILTER_TRIVIAL_BOTH,
 };
 
 enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
@@ -926,7 +926,7 @@ int tep_event_filtered(struct tep_event_filter *filter,
 void tep_filter_reset(struct tep_event_filter *filter);
 
 int tep_filter_clear_trivial(struct tep_event_filter *filter,
-			     enum filter_trivial_type type);
+			     enum tep_filter_trivial_type type);
 
 void tep_filter_free(struct tep_event_filter *filter);
 
@@ -937,12 +937,12 @@ int tep_filter_remove_event(struct tep_event_filter *filter,
 
 int tep_filter_event_has_trivial(struct tep_event_filter *filter,
 				 int event_id,
-				 enum filter_trivial_type type);
+				 enum tep_filter_trivial_type type);
 
 int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *source);
 
 int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source,
-			enum filter_trivial_type type);
+			enum tep_filter_trivial_type type);
 
 int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter *filter2);
 
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 875bfaf79771..d64b6128fa7d 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -1534,7 +1534,7 @@ int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *sour
  *   events may have still been updated on error.
  */
 int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source,
-		       enum filter_trivial_type type)
+		       enum tep_filter_trivial_type type)
 {
 	struct tep_handle *src_pevent;
 	struct tep_handle *dest_pevent;
@@ -1556,8 +1556,8 @@ int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *s
 		arg = filter_type->filter;
 		if (arg->type != TEP_FILTER_ARG_BOOLEAN)
 			continue;
-		if ((arg->boolean.value && type == FILTER_TRIVIAL_FALSE) ||
-		    (!arg->boolean.value && type == FILTER_TRIVIAL_TRUE))
+		if ((arg->boolean.value && type == TEP_FILTER_TRIVIAL_FALSE) ||
+		    (!arg->boolean.value && type == TEP_FILTER_TRIVIAL_TRUE))
 			continue;
 
 		event = filter_type->event;
@@ -1593,7 +1593,7 @@ int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *s
  * Returns 0 on success and -1 if there was a problem.
  */
 int tep_filter_clear_trivial(struct tep_event_filter *filter,
-			     enum filter_trivial_type type)
+			     enum tep_filter_trivial_type type)
 {
 	struct tep_filter_type *filter_type;
 	int count = 0;
@@ -1614,11 +1614,11 @@ int tep_filter_clear_trivial(struct tep_event_filter *filter,
 		if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN)
 			continue;
 		switch (type) {
-		case FILTER_TRIVIAL_FALSE:
+		case TEP_FILTER_TRIVIAL_FALSE:
 			if (filter_type->filter->boolean.value)
 				continue;
 			break;
-		case FILTER_TRIVIAL_TRUE:
+		case TEP_FILTER_TRIVIAL_TRUE:
 			if (!filter_type->filter->boolean.value)
 				continue;
 		default:
@@ -1656,7 +1656,7 @@ int tep_filter_clear_trivial(struct tep_event_filter *filter,
  */
 int tep_filter_event_has_trivial(struct tep_event_filter *filter,
 				 int event_id,
-				 enum filter_trivial_type type)
+				 enum tep_filter_trivial_type type)
 {
 	struct tep_filter_type *filter_type;
 
@@ -1672,10 +1672,10 @@ int tep_filter_event_has_trivial(struct tep_event_filter *filter,
 		return 0;
 
 	switch (type) {
-	case FILTER_TRIVIAL_FALSE:
+	case TEP_FILTER_TRIVIAL_FALSE:
 		return !filter_type->filter->boolean.value;
 
-	case FILTER_TRIVIAL_TRUE:
+	case TEP_FILTER_TRIVIAL_TRUE:
 		return filter_type->filter->boolean.value;
 	default:
 		return 1;
@@ -2409,8 +2409,8 @@ int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter
 		if (filter_type1->filter->type != filter_type2->filter->type)
 			break;
 		switch (filter_type1->filter->type) {
-		case FILTER_TRIVIAL_FALSE:
-		case FILTER_TRIVIAL_TRUE:
+		case TEP_FILTER_TRIVIAL_FALSE:
+		case TEP_FILTER_TRIVIAL_TRUE:
 			/* trivial types just need the type compared */
 			continue;
 		default:
-- 
cgit v1.2.3


From 62cb1b8868a70c932b15959a98594df537df2ffc Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 20 Sep 2018 16:00:43 +0300
Subject: perf script: Enhance sample flags for trace begin / end

Allow for different combinations of sample flags with "trace begin" or
"trace end".

Previously, the Intel PT decoder would indicate begin / end by a branch
from / to zero. That hides useful information, in particular when a
trace ends with a call. Before remedying that, prepare 'perf script' to
display sample flags with more combinations that include trace begin /
end. In those cases display 'tr start' and 'tr end' separately.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20180920130048.31432-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c | 36 +++++++++++++++++++++++++++---------
 1 file changed, 27 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 7732346bd9dd..4da5e32b9e03 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1262,6 +1262,18 @@ static struct {
 	{0, NULL}
 };
 
+static const char *sample_flags_to_name(u32 flags)
+{
+	int i;
+
+	for (i = 0; sample_flags[i].name ; i++) {
+		if (sample_flags[i].flags == flags)
+			return sample_flags[i].name;
+	}
+
+	return NULL;
+}
+
 static int perf_sample__fprintf_flags(u32 flags, FILE *fp)
 {
 	const char *chars = PERF_IP_FLAG_CHARS;
@@ -1271,11 +1283,20 @@ static int perf_sample__fprintf_flags(u32 flags, FILE *fp)
 	char str[33];
 	int i, pos = 0;
 
-	for (i = 0; sample_flags[i].name ; i++) {
-		if (sample_flags[i].flags == (flags & ~PERF_IP_FLAG_IN_TX)) {
-			name = sample_flags[i].name;
-			break;
-		}
+	name = sample_flags_to_name(flags & ~PERF_IP_FLAG_IN_TX);
+	if (name)
+		return fprintf(fp, "  %-15s%4s ", name, in_tx ? "(x)" : "");
+
+	if (flags & PERF_IP_FLAG_TRACE_BEGIN) {
+		name = sample_flags_to_name(flags & ~(PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_TRACE_BEGIN));
+		if (name)
+			return fprintf(fp, "  tr strt %-7s%4s ", name, in_tx ? "(x)" : "");
+	}
+
+	if (flags & PERF_IP_FLAG_TRACE_END) {
+		name = sample_flags_to_name(flags & ~(PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_TRACE_END));
+		if (name)
+			return fprintf(fp, "  tr end  %-7s%4s ", name, in_tx ? "(x)" : "");
 	}
 
 	for (i = 0; i < n; i++, flags >>= 1) {
@@ -1288,10 +1309,7 @@ static int perf_sample__fprintf_flags(u32 flags, FILE *fp)
 	}
 	str[pos] = 0;
 
-	if (name)
-		return fprintf(fp, "  %-7s%4s ", name, in_tx ? "(x)" : "");
-
-	return fprintf(fp, "  %-11s ", str);
+	return fprintf(fp, "  %-19s ", str);
 }
 
 struct printer_data {
-- 
cgit v1.2.3


From ff645daf30cafb6fa74bee9a73733700bac2aff7 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 20 Sep 2018 16:00:44 +0300
Subject: perf db-export: Add trace begin / end branch type variants

Add branch types to cover different combinations with "trace begin" or
"trace end".

Previously, the Intel PT decoder would indicate begin / end by a branch
from / to zero. That hides useful information, in particular when a
trace ends with a call. Before remedying that, prepare the database
export to export branch types with more combinations that include trace
begin / end.  In those cases extend the descriptions to include 'trace
begin' and 'trace end' separately.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20180920130048.31432-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/db-export.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 7123746edcf4..69fbb0a72d0c 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -463,6 +463,28 @@ int db_export__branch_types(struct db_export *dbe)
 		if (err)
 			break;
 	}
+
+	/* Add trace begin / end variants */
+	for (i = 0; branch_types[i].name ; i++) {
+		const char *name = branch_types[i].name;
+		u32 type = branch_types[i].branch_type;
+		char buf[64];
+
+		if (type == PERF_IP_FLAG_BRANCH ||
+		    (type & (PERF_IP_FLAG_TRACE_BEGIN | PERF_IP_FLAG_TRACE_END)))
+			continue;
+
+		snprintf(buf, sizeof(buf), "trace begin / %s", name);
+		err = db_export__branch_type(dbe, type | PERF_IP_FLAG_TRACE_BEGIN, buf);
+		if (err)
+			break;
+
+		snprintf(buf, sizeof(buf), "%s / trace end", name);
+		err = db_export__branch_type(dbe, type | PERF_IP_FLAG_TRACE_END, buf);
+		if (err)
+			break;
+	}
+
 	return err;
 }
 
-- 
cgit v1.2.3


From 3136a3698804f55a26f68e8c897d7ccf254923ad Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 20 Sep 2018 09:21:34 +0300
Subject: selftests: forwarding: lib: Add ethtool_stats_get()

Add a new service function to obtain ethtool counters.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index ca53b539aa2d..4c2351996a7f 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -494,6 +494,14 @@ tc_rule_stats_get()
 	    | jq '.[1].options.actions[].stats.packets'
 }
 
+ethtool_stats_get()
+{
+	local dev=$1; shift
+	local stat=$1; shift
+
+	ethtool -S $dev | grep "^ *$stat:" | head -n 1 | cut -d: -f2
+}
+
 mac_get()
 {
 	local if_name=$1
-- 
cgit v1.2.3


From a381ed12ea33888a08f0e3e5ba22a255fa5f7257 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 20 Sep 2018 09:21:35 +0300
Subject: selftests: forwarding: lib: Add mtu_set(), mtu_restore()

Some selftests need to tweak MTU of an interface, and naturally should
at teardown restore the MTU back to the original value. Add two
functions to facilitate this MTU handling: mtu_set() to change MTU
value, and mtu_reset() to change it back to what it was before.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 4c2351996a7f..0e73698b2048 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -549,6 +549,23 @@ forwarding_restore()
 	sysctl_restore net.ipv4.conf.all.forwarding
 }
 
+declare -A MTU_ORIG
+mtu_set()
+{
+	local dev=$1; shift
+	local mtu=$1; shift
+
+	MTU_ORIG["$dev"]=$(ip -j link show dev $dev | jq -e '.[].mtu')
+	ip link set dev $dev mtu $mtu
+}
+
+mtu_restore()
+{
+	local dev=$1; shift
+
+	ip link set dev $dev mtu ${MTU_ORIG["$dev"]}
+}
+
 tc_offload_check()
 {
 	local num_netifs=${1:-$NUM_NETIFS}
-- 
cgit v1.2.3


From b5638d46c90a6998859a4fc9ea697b264da96092 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 20 Sep 2018 09:21:36 +0300
Subject: selftests: mlxsw: Add a test for UC behavior under MC flood

A so-called "MC-aware" mode has recently been enabled in mlxsw. In
MC-aware mode, BUM traffic is handled in a special way so that when a
switch is flooded with BUM, UC performance isn't unduly impacted.
Without enablement of this mode, a stream of BUM traffic can cause
sustained UC throughput drop in excess of 99 %.

Add a test for this behavior. Compare how much UC throughput degrades as
a stream of broadcast frames floods the switch. A minimal degradation is
tolerated to cover for glitches in traffic injection performance.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/qos_mc_aware.sh    | 347 +++++++++++++++++++++
 1 file changed, 347 insertions(+)
 create mode 100644 tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
new file mode 100644
index 000000000000..0150bb2741eb
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
@@ -0,0 +1,347 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# A test for switch behavior under MC overload. An issue in Spectrum chips
+# causes throughput of UC traffic to drop severely when a switch is under heavy
+# MC load. This issue can be overcome by putting the switch to MC-aware mode.
+# This test verifies that UC performance stays intact even as the switch is
+# under MC flood, and therefore that the MC-aware mode is enabled and correctly
+# configured.
+#
+# Because mlxsw throttles CPU port, the traffic can't actually reach userspace
+# at full speed. That makes it impossible to use iperf3 to simply measure the
+# throughput, because many packets (that reach $h3) don't get to the kernel at
+# all even in UDP mode (the situation is even worse in TCP mode, where one can't
+# hope to see more than a couple Mbps).
+#
+# So instead we send traffic with mausezahn and use RX ethtool counters at $h3.
+# Multicast traffic is untagged, unicast traffic is tagged with PCP 1. Therefore
+# each gets a different priority and we can use per-prio ethtool counters to
+# measure the throughput. In order to avoid prioritizing unicast traffic, prio
+# qdisc is installed on $swp3 and maps all priorities to the same band #7 (and
+# thus TC 0).
+#
+# Mausezahn can't actually saturate the links unless it's using large frames.
+# Thus we set MTU to 10K on all involved interfaces. Then both unicast and
+# multicast traffic uses 8K frames.
+#
+# +-----------------------+                +----------------------------------+
+# | H1                    |                |                               H2 |
+# |                       |                |  unicast --> + $h2.111           |
+# |                       |                |  traffic     | 192.0.2.129/28    |
+# |          multicast    |                |              | e-qos-map 0:1     |
+# |          traffic      |                |              |                   |
+# | $h1 + <-----          |                |              + $h2               |
+# +-----|-----------------+                +--------------|-------------------+
+#       |                                                 |
+# +-----|-------------------------------------------------|-------------------+
+# |     + $swp1                                           + $swp2             |
+# |     | >1Gbps                                          | >1Gbps            |
+# | +---|----------------+                     +----------|----------------+  |
+# | |   + $swp1.1        |                     |          + $swp2.111      |  |
+# | |                BR1 |             SW      | BR111                     |  |
+# | |   + $swp3.1        |                     |          + $swp3.111      |  |
+# | +---|----------------+                     +----------|----------------+  |
+# |     \_________________________________________________/                   |
+# |                                    |                                      |
+# |                                    + $swp3                                |
+# |                                    | 1Gbps bottleneck                     |
+# |                                    | prio qdisc: {0..7} -> 7              |
+# +------------------------------------|--------------------------------------+
+#                                      |
+#                                   +--|-----------------+
+#                                   |  + $h3          H3 |
+#                                   |  |                 |
+#                                   |  + $h3.111         |
+#                                   |    192.0.2.130/28  |
+#                                   +--------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	test_mc_aware
+"
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+NUM_NETIFS=6
+source $lib_dir/lib.sh
+
+h1_create()
+{
+	simple_if_init $h1
+	mtu_set $h1 10000
+}
+
+h1_destroy()
+{
+	mtu_restore $h1
+	simple_if_fini $h1
+}
+
+h2_create()
+{
+	simple_if_init $h2
+	mtu_set $h2 10000
+
+	vlan_create $h2 111 v$h2 192.0.2.129/28
+	ip link set dev $h2.111 type vlan egress-qos-map 0:1
+}
+
+h2_destroy()
+{
+	vlan_destroy $h2 111
+
+	mtu_restore $h2
+	simple_if_fini $h2
+}
+
+h3_create()
+{
+	simple_if_init $h3
+	mtu_set $h3 10000
+
+	vlan_create $h3 111 v$h3 192.0.2.130/28
+}
+
+h3_destroy()
+{
+	vlan_destroy $h3 111
+
+	mtu_restore $h3
+	simple_if_fini $h3
+}
+
+switch_create()
+{
+	ip link set dev $swp1 up
+	mtu_set $swp1 10000
+
+	ip link set dev $swp2 up
+	mtu_set $swp2 10000
+
+	ip link set dev $swp3 up
+	mtu_set $swp3 10000
+
+	vlan_create $swp2 111
+	vlan_create $swp3 111
+
+	ethtool -s $swp3 speed 1000 autoneg off
+	tc qdisc replace dev $swp3 root handle 3: \
+	   prio bands 8 priomap 7 7 7 7 7 7 7 7
+
+	ip link add name br1 type bridge vlan_filtering 0
+	ip link set dev br1 up
+	ip link set dev $swp1 master br1
+	ip link set dev $swp3 master br1
+
+	ip link add name br111 type bridge vlan_filtering 0
+	ip link set dev br111 up
+	ip link set dev $swp2.111 master br111
+	ip link set dev $swp3.111 master br111
+}
+
+switch_destroy()
+{
+	ip link del dev br111
+	ip link del dev br1
+
+	tc qdisc del dev $swp3 root handle 3:
+	ethtool -s $swp3 autoneg on
+
+	vlan_destroy $swp3 111
+	vlan_destroy $swp2 111
+
+	mtu_restore $swp3
+	ip link set dev $swp3 down
+
+	mtu_restore $swp2
+	ip link set dev $swp2 down
+
+	mtu_restore $swp1
+	ip link set dev $swp1 down
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	h3mac=$(mac_get $h3)
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+	h3_create
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	switch_destroy
+	h3_destroy
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h2 192.0.2.130
+}
+
+humanize()
+{
+	local speed=$1; shift
+
+	for unit in bps Kbps Mbps Gbps; do
+		if (($(echo "$speed < 1024" | bc))); then
+			break
+		fi
+
+		speed=$(echo "scale=1; $speed / 1024" | bc)
+	done
+
+	echo "$speed${unit}"
+}
+
+rate()
+{
+	local t0=$1; shift
+	local t1=$1; shift
+	local interval=$1; shift
+
+	echo $((8 * (t1 - t0) / interval))
+}
+
+check_rate()
+{
+	local rate=$1; shift
+	local min=$1; shift
+	local what=$1; shift
+
+	if ((rate > min)); then
+		return 0
+	fi
+
+	echo "$what $(humanize $ir) < $(humanize $min_ingress)" > /dev/stderr
+	return 1
+}
+
+measure_uc_rate()
+{
+	local what=$1; shift
+
+	local interval=10
+	local i
+	local ret=0
+
+	# Dips in performance might cause momentary ingress rate to drop below
+	# 1Gbps. That wouldn't saturate egress and MC would thus get through,
+	# seemingly winning bandwidth on account of UC. Demand at least 2Gbps
+	# average ingress rate to somewhat mitigate this.
+	local min_ingress=2147483648
+
+	mausezahn $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \
+		-a own -b $h3mac -t udp -q &
+	sleep 1
+
+	for i in {5..0}; do
+		local t0=$(ethtool_stats_get $h3 rx_octets_prio_1)
+		local u0=$(ethtool_stats_get $swp2 rx_octets_prio_1)
+		sleep $interval
+		local t1=$(ethtool_stats_get $h3 rx_octets_prio_1)
+		local u1=$(ethtool_stats_get $swp2 rx_octets_prio_1)
+
+		local ir=$(rate $u0 $u1 $interval)
+		local er=$(rate $t0 $t1 $interval)
+
+		if check_rate $ir $min_ingress "$what ingress rate"; then
+			break
+		fi
+
+		# Fail the test if we can't get the throughput.
+		if ((i == 0)); then
+			ret=1
+		fi
+	done
+
+	# Suppress noise from killing mausezahn.
+	{ kill %% && wait; } 2>/dev/null
+
+	echo $ir $er
+	exit $ret
+}
+
+test_mc_aware()
+{
+	RET=0
+
+	local -a uc_rate
+	uc_rate=($(measure_uc_rate "UC-only"))
+	check_err $? "Could not get high enough UC-only ingress rate"
+	local ucth1=${uc_rate[1]}
+
+	mausezahn $h1 -p 8000 -c 0 -a own -b bc -t udp -q &
+
+	local d0=$(date +%s)
+	local t0=$(ethtool_stats_get $h3 rx_octets_prio_0)
+	local u0=$(ethtool_stats_get $swp1 rx_octets_prio_0)
+
+	local -a uc_rate_2
+	uc_rate_2=($(measure_uc_rate "UC+MC"))
+	check_err $? "Could not get high enough UC+MC ingress rate"
+	local ucth2=${uc_rate_2[1]}
+
+	local d1=$(date +%s)
+	local t1=$(ethtool_stats_get $h3 rx_octets_prio_0)
+	local u1=$(ethtool_stats_get $swp1 rx_octets_prio_0)
+
+	local deg=$(bc <<< "
+			scale=2
+			ret = 100 * ($ucth1 - $ucth2) / $ucth1
+			if (ret > 0) { ret } else { 0 }
+		    ")
+	check_err $(bc <<< "$deg > 10")
+
+	local interval=$((d1 - d0))
+	local mc_ir=$(rate $u0 $u1 $interval)
+	local mc_er=$(rate $t0 $t1 $interval)
+
+	# Suppress noise from killing mausezahn.
+	{ kill %% && wait; } 2>/dev/null
+
+	log_test "UC performace under MC overload"
+
+	echo "UC-only throughput  $(humanize $ucth1)"
+	echo "UC+MC throughput    $(humanize $ucth2)"
+	echo "Degradation         $deg %"
+	echo
+	echo "Full report:"
+	echo "  UC only:"
+	echo "    ingress UC throughput $(humanize ${uc_rate[0]})"
+	echo "    egress UC throughput  $(humanize ${uc_rate[1]})"
+	echo "  UC+MC:"
+	echo "    ingress UC throughput $(humanize ${uc_rate_2[0]})"
+	echo "    egress UC throughput  $(humanize ${uc_rate_2[1]})"
+	echo "    ingress MC throughput $(humanize $mc_ir)"
+	echo "    egress MC throughput  $(humanize $mc_er)"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 4d60e5e36aa6f11b4d9eadc5d2b94128f24870c7 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 20 Sep 2018 16:00:45 +0300
Subject: perf tools: Improve thread_stack__event() for trace begin / end

thread_stack__event() is used to create call stacks, by keeping track of
calls and returns. Improve the handling of trace begin / end to allow
for a trace that ends in a call.

Previously, the Intel PT decoder would indicate begin / end by a branch
from / to zero. That hides useful information, in particular when a
trace ends with a call. Before remedying that, enhance the thread stack
so that it does not expect to see the 'return' for a 'call' that ends
the trace.

Committer notes:

Added this:

                return thread_stack__push(thread->ts, ret_addr,
-                                         flags && PERF_IP_FLAG_TRACE_END);
+                                         flags & PERF_IP_FLAG_TRACE_END);

To fix problem spotted by:

debian:9:            clang version 3.8.1-24 (tags/RELEASE_381/final)
debian:experimental: clang version 6.0.1-6 (tags/RELEASE_601/final)

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20180920130048.31432-4-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/thread-stack.c | 35 ++++++++++++++++++++++++++++++-----
 1 file changed, 30 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index dd17d6a38d3a..e3f7dfecafa9 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -36,6 +36,7 @@
  * @branch_count: the branch count when the entry was created
  * @cp: call path
  * @no_call: a 'call' was not seen
+ * @trace_end: a 'call' but trace ended
  */
 struct thread_stack_entry {
 	u64 ret_addr;
@@ -44,6 +45,7 @@ struct thread_stack_entry {
 	u64 branch_count;
 	struct call_path *cp;
 	bool no_call;
+	bool trace_end;
 };
 
 /**
@@ -112,7 +114,8 @@ static struct thread_stack *thread_stack__new(struct thread *thread,
 	return ts;
 }
 
-static int thread_stack__push(struct thread_stack *ts, u64 ret_addr)
+static int thread_stack__push(struct thread_stack *ts, u64 ret_addr,
+			      bool trace_end)
 {
 	int err = 0;
 
@@ -124,6 +127,7 @@ static int thread_stack__push(struct thread_stack *ts, u64 ret_addr)
 		}
 	}
 
+	ts->stack[ts->cnt].trace_end = trace_end;
 	ts->stack[ts->cnt++].ret_addr = ret_addr;
 
 	return err;
@@ -150,6 +154,18 @@ static void thread_stack__pop(struct thread_stack *ts, u64 ret_addr)
 	}
 }
 
+static void thread_stack__pop_trace_end(struct thread_stack *ts)
+{
+	size_t i;
+
+	for (i = ts->cnt; i; ) {
+		if (ts->stack[--i].trace_end)
+			ts->cnt = i;
+		else
+			return;
+	}
+}
+
 static bool thread_stack__in_kernel(struct thread_stack *ts)
 {
 	if (!ts->cnt)
@@ -254,10 +270,19 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 		ret_addr = from_ip + insn_len;
 		if (ret_addr == to_ip)
 			return 0; /* Zero-length calls are excluded */
-		return thread_stack__push(thread->ts, ret_addr);
-	} else if (flags & PERF_IP_FLAG_RETURN) {
-		if (!from_ip)
-			return 0;
+		return thread_stack__push(thread->ts, ret_addr,
+					  flags & PERF_IP_FLAG_TRACE_END);
+	} else if (flags & PERF_IP_FLAG_TRACE_BEGIN) {
+		/*
+		 * If the caller did not change the trace number (which would
+		 * have flushed the stack) then try to make sense of the stack.
+		 * Possibly, tracing began after returning to the current
+		 * address, so try to pop that. Also, do not expect a call made
+		 * when the trace ended, to return, so pop that.
+		 */
+		thread_stack__pop(thread->ts, to_ip);
+		thread_stack__pop_trace_end(thread->ts);
+	} else if ((flags & PERF_IP_FLAG_RETURN) && from_ip) {
 		thread_stack__pop(thread->ts, to_ip);
 	}
 
-- 
cgit v1.2.3


From 2dcde4e152a3e319cc7e76c7c6b8548a3c72310d Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 20 Sep 2018 16:00:46 +0300
Subject: perf tools: Improve thread_stack__process() for trace begin / end

thread_stack__process() is used to create call paths for database
export.  Improve the handling of trace begin / end to allow for a trace
that ends in a call.

Previously, the Intel PT decoder would indicate begin / end by a branch
from / to zero. That hides useful information, in particular when a
trace ends with a call. Before remedying that, enhance the thread stack
so that it identifies the trace end by the flag instead of by ip == 0.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20180920130048.31432-5-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/thread-stack.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index e3f7dfecafa9..c091635bf7dc 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -357,7 +357,7 @@ void call_return_processor__free(struct call_return_processor *crp)
 
 static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
 				 u64 timestamp, u64 ref, struct call_path *cp,
-				 bool no_call)
+				 bool no_call, bool trace_end)
 {
 	struct thread_stack_entry *tse;
 	int err;
@@ -375,6 +375,7 @@ static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
 	tse->branch_count = ts->branch_count;
 	tse->cp = cp;
 	tse->no_call = no_call;
+	tse->trace_end = trace_end;
 
 	return 0;
 }
@@ -448,7 +449,7 @@ static int thread_stack__bottom(struct thread *thread, struct thread_stack *ts,
 		return -ENOMEM;
 
 	return thread_stack__push_cp(thread->ts, ip, sample->time, ref, cp,
-				     true);
+				     true, false);
 }
 
 static int thread_stack__no_call_return(struct thread *thread,
@@ -480,7 +481,7 @@ static int thread_stack__no_call_return(struct thread *thread,
 			if (!cp)
 				return -ENOMEM;
 			return thread_stack__push_cp(ts, 0, sample->time, ref,
-						     cp, true);
+						     cp, true, false);
 		}
 	} else if (thread_stack__in_kernel(ts) && sample->ip < ks) {
 		/* Return to userspace, so pop all kernel addresses */
@@ -505,7 +506,7 @@ static int thread_stack__no_call_return(struct thread *thread,
 		return -ENOMEM;
 
 	err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp,
-				    true);
+				    true, false);
 	if (err)
 		return err;
 
@@ -525,7 +526,7 @@ static int thread_stack__trace_begin(struct thread *thread,
 
 	/* Pop trace end */
 	tse = &ts->stack[ts->cnt - 1];
-	if (tse->cp->sym == NULL && tse->cp->ip == 0) {
+	if (tse->trace_end) {
 		err = thread_stack__call_return(thread, ts, --ts->cnt,
 						timestamp, ref, false);
 		if (err)
@@ -554,7 +555,7 @@ static int thread_stack__trace_end(struct thread_stack *ts,
 	ret_addr = sample->ip + sample->insn_len;
 
 	return thread_stack__push_cp(ts, ret_addr, sample->time, ref, cp,
-				     false);
+				     false, true);
 }
 
 int thread_stack__process(struct thread *thread, struct comm *comm,
@@ -604,6 +605,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 	ts->last_time = sample->time;
 
 	if (sample->flags & PERF_IP_FLAG_CALL) {
+		bool trace_end = sample->flags & PERF_IP_FLAG_TRACE_END;
 		struct call_path_root *cpr = ts->crp->cpr;
 		struct call_path *cp;
 		u64 ret_addr;
@@ -621,7 +623,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 		if (!cp)
 			return -ENOMEM;
 		err = thread_stack__push_cp(ts, ret_addr, sample->time, ref,
-					    cp, false);
+					    cp, false, trace_end);
 	} else if (sample->flags & PERF_IP_FLAG_RETURN) {
 		if (!sample->ip || !sample->addr)
 			return 0;
-- 
cgit v1.2.3


From c6b5da093a8ba740b71dd0052f3846016986fd21 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 20 Sep 2018 16:00:47 +0300
Subject: perf intel-pt: Add decoder flags for trace begin / end

Previously, the decoder would indicate begin / end by a branch from / to
zero. That hides useful information, in particular when a trace ends
with a call. To prepare for remedying that, add Intel PT decoder flags
for trace begin / end and map them to the existing sample flags.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20180920130048.31432-6-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt-decoder/intel-pt-decoder.h | 2 ++
 tools/perf/util/intel-pt.c                          | 5 +++++
 2 files changed, 7 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
index 51c18d67f4ca..ed088d4726ba 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -37,6 +37,8 @@ enum intel_pt_sample_type {
 	INTEL_PT_EX_STOP	= 1 << 6,
 	INTEL_PT_PWR_EXIT	= 1 << 7,
 	INTEL_PT_CBR_CHG	= 1 << 8,
+	INTEL_PT_TRACE_BEGIN	= 1 << 9,
+	INTEL_PT_TRACE_END	= 1 << 10,
 };
 
 enum intel_pt_period_type {
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index aec68908d604..48c1d415c6b0 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -908,6 +908,11 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
 		ptq->insn_len = ptq->state->insn_len;
 		memcpy(ptq->insn, ptq->state->insn, INTEL_PT_INSN_BUF_SZ);
 	}
+
+	if (ptq->state->type & INTEL_PT_TRACE_BEGIN)
+		ptq->flags |= PERF_IP_FLAG_TRACE_BEGIN;
+	if (ptq->state->type & INTEL_PT_TRACE_END)
+		ptq->flags |= PERF_IP_FLAG_TRACE_END;
 }
 
 static int intel_pt_setup_queue(struct intel_pt *pt,
-- 
cgit v1.2.3


From bea6385789b8b5e1e3228a281978ca6c4a8c70a0 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 20 Sep 2018 16:00:48 +0300
Subject: perf intel-pt: Implement decoder flags for trace begin / end

Have the Intel PT decoder implement the new Intel PT decoder flags for
trace begin / end.

Previously, the decoder would indicate begin / end by a branch from / to
zero. That hides useful information, in particular when a trace ends
with a call. That happens when using address filters, for example:

  $ perf record -e intel_pt/cyc,mtc_period=0,noretcomp/u --filter='filter main @ /bin/uname ' uname Linux
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.031 MB perf.data ]

Before:

  $ perf script --itrace=cre -Ftime,flags,ip,sym,symoff,addr --ns
   7249.622183310:   tr strt         0 [unknown] =>   401590 main+0x0
   7249.622183311:   call       4015b9 main+0x29 =>        0 [unknown]
   7249.622183711:   tr strt         0 [unknown] =>   4015be main+0x2e
   7249.622183714:   call       4015c8 main+0x38 =>        0 [unknown]
   7249.622247731:   tr strt         0 [unknown] =>   4015cd main+0x3d
   7249.622247760:   call       4015d7 main+0x47 =>        0 [unknown]
   7249.622248340:   tr strt         0 [unknown] =>   4015dc main+0x4c
   7249.622248341:   call       4015e1 main+0x51 =>        0 [unknown]
   7249.622248681:   tr strt         0 [unknown] =>   4015e6 main+0x56
   7249.622248682:   call       4015eb main+0x5b =>        0 [unknown]
   7249.622248970:   tr strt         0 [unknown] =>   4015f0 main+0x60
   7249.622248971:   call       401612 main+0x82 =>        0 [unknown]
   7249.622249757:   tr strt         0 [unknown] =>   401617 main+0x87
   7249.622249770:   call       401847 main+0x2b7 =>        0 [unknown]
   7249.622250606:   tr strt         0 [unknown] =>   40184c main+0x2bc
   7249.622250612:   call       4019bf main+0x42f =>        0 [unknown]
   7249.622256823:   tr strt         0 [unknown] =>   4019c4 main+0x434
   7249.622256863:   call       4019f5 main+0x465 =>        0 [unknown]
   7249.622264217:   tr strt         0 [unknown] =>   4019fa main+0x46a
   7249.622264235:   call       401832 main+0x2a2 =>        0 [unknown]

After:

  $ perf script --itrace=cre -Ftime,flags,ip,sym,symoff,addr --ns
   7249.622183310:   tr strt              0 [unknown] =>   401590 main+0x0
   7249.622183311:   tr end  call    4015b9 main+0x29 =>   401ef0 set_program_name+0x0
   7249.622183711:   tr strt              0 [unknown] =>   4015be main+0x2e
   7249.622183714:   tr end  call    4015c8 main+0x38 =>   4014b0 setlocale@plt+0x0
   7249.622247731:   tr strt              0 [unknown] =>   4015cd main+0x3d
   7249.622247760:   tr end  call    4015d7 main+0x47 =>   4012d0 bindtextdomain@plt+0x0
   7249.622248340:   tr strt              0 [unknown] =>   4015dc main+0x4c
   7249.622248341:   tr end  call    4015e1 main+0x51 =>   4012b0 textdomain@plt+0x0
   7249.622248681:   tr strt              0 [unknown] =>   4015e6 main+0x56
   7249.622248682:   tr end  call    4015eb main+0x5b =>   404340 atexit+0x0
   7249.622248970:   tr strt              0 [unknown] =>   4015f0 main+0x60
   7249.622248971:   tr end  call    401612 main+0x82 =>   401320 getopt_long@plt+0x0
   7249.622249757:   tr strt              0 [unknown] =>   401617 main+0x87
   7249.622249770:   tr end  call    401847 main+0x2b7 =>   401360 uname@plt+0x0
   7249.622250606:   tr strt              0 [unknown] =>   40184c main+0x2bc
   7249.622250612:   tr end  call    4019bf main+0x42f =>   401b10 print_element+0x0
   7249.622256823:   tr strt              0 [unknown] =>   4019c4 main+0x434
   7249.622256863:   tr end  call    4019f5 main+0x465 =>   401340 __overflow@plt+0x0
   7249.622264217:   tr strt              0 [unknown] =>   4019fa main+0x46a
   7249.622264235:   tr end  call    401832 main+0x2a2 =>   401520 exit@plt+0x0

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20180920130048.31432-7-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../perf/util/intel-pt-decoder/intel-pt-decoder.c  | 34 +++++++++++++++-------
 1 file changed, 23 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index d404bed7003a..58f6a9ceb590 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1165,7 +1165,7 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
 		decoder->pge = false;
 		decoder->continuous_period = false;
 		decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
-		decoder->state.to_ip = 0;
+		decoder->state.type |= INTEL_PT_TRACE_END;
 		return 0;
 	}
 	if (err == INTEL_PT_RETURN)
@@ -1179,9 +1179,13 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
 			decoder->continuous_period = false;
 			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			decoder->state.from_ip = decoder->ip;
-			decoder->state.to_ip = 0;
-			if (decoder->packet.count != 0)
+			if (decoder->packet.count == 0) {
+				decoder->state.to_ip = 0;
+			} else {
+				decoder->state.to_ip = decoder->last_ip;
 				decoder->ip = decoder->last_ip;
+			}
+			decoder->state.type |= INTEL_PT_TRACE_END;
 		} else {
 			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			decoder->state.from_ip = decoder->ip;
@@ -1208,7 +1212,8 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
 			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			decoder->ip = to_ip;
 			decoder->state.from_ip = decoder->ip;
-			decoder->state.to_ip = 0;
+			decoder->state.to_ip = to_ip;
+			decoder->state.type |= INTEL_PT_TRACE_END;
 			return 0;
 		}
 		intel_pt_log_at("ERROR: Conditional branch when expecting indirect branch",
@@ -1640,14 +1645,15 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 
 		case INTEL_PT_TIP_PGD:
 			decoder->state.from_ip = decoder->ip;
-			decoder->state.to_ip = 0;
-			if (decoder->packet.count != 0) {
+			if (decoder->packet.count == 0) {
+				decoder->state.to_ip = 0;
+			} else {
 				intel_pt_set_ip(decoder);
-				intel_pt_log("Omitting PGD ip " x64_fmt "\n",
-					     decoder->ip);
+				decoder->state.to_ip = decoder->ip;
 			}
 			decoder->pge = false;
 			decoder->continuous_period = false;
+			decoder->state.type |= INTEL_PT_TRACE_END;
 			return 0;
 
 		case INTEL_PT_TIP_PGE:
@@ -1661,6 +1667,7 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 				intel_pt_set_ip(decoder);
 				decoder->state.to_ip = decoder->ip;
 			}
+			decoder->state.type |= INTEL_PT_TRACE_BEGIN;
 			return 0;
 
 		case INTEL_PT_TIP:
@@ -1739,6 +1746,7 @@ next:
 			intel_pt_set_ip(decoder);
 			decoder->state.from_ip = 0;
 			decoder->state.to_ip = decoder->ip;
+			decoder->state.type |= INTEL_PT_TRACE_BEGIN;
 			return 0;
 		}
 
@@ -2077,9 +2085,13 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 			decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
 			if (intel_pt_have_ip(decoder))
 				intel_pt_set_ip(decoder);
-			if (decoder->ip)
-				return 0;
-			break;
+			if (!decoder->ip)
+				break;
+			if (decoder->packet.type == INTEL_PT_TIP_PGE)
+				decoder->state.type |= INTEL_PT_TRACE_BEGIN;
+			if (decoder->packet.type == INTEL_PT_TIP_PGD)
+				decoder->state.type |= INTEL_PT_TRACE_END;
+			return 0;
 
 		case INTEL_PT_FUP:
 			if (intel_pt_have_ip(decoder))
-- 
cgit v1.2.3


From d35c595bf0053b7df80ef9d44140ac5da6cc698b Mon Sep 17 00:00:00 2001
From: Sean V Kelley <seanvk.dev@oregontracks.org>
Date: Sun, 16 Sep 2018 15:12:03 -0700
Subject: perf vendor events arm64: Revise core JSON events for eMAG

Split the PMU events into meaningful functional groups.  Update core pmu
events based on supported ARMv8 recommended IMPLEMENTATION DEFINED
events.

The JSON files are updated with reference to a PMU table shared here:

  https://github.com/AmpereComputing/ampere-centos-kernel/blob/amp-centos-7.5-kernel/Documentation/arm64/eMAG-ARM-CoreImpDefined.pdf

Changes in v3:
- Removed CHAIN event as it wouldn't be useful in Perf - William
- Will factor out events 0x00-0x38 in a follow-on patch - William
- to armv8-recommended.json
Changes in V2:
- Provided documentation for changes - John, William
- Broke up into meaningful groups - William

Signed-off-by: Sean V Kelley <seanvk.dev@oregontracks.org>
Reviewed-by: William Cohen <wcohen@redhat.com>
Cc: John Garry <john.garry@huawei.com>
Cc: linux-arm-kernel@lists.infradead.org
LPU-Reference: 20180916221203.7935-1-seanvk.dev@oregontracks.org
Link: https://lkml.kernel.org/n/tip-tzvs1ip6srcv2et0ny58e0wy@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../pmu-events/arch/arm64/ampere/emag/branch.json  |  23 +++
 .../pmu-events/arch/arm64/ampere/emag/bus.json     |  26 +++
 .../pmu-events/arch/arm64/ampere/emag/cache.json   | 191 +++++++++++++++++++++
 .../pmu-events/arch/arm64/ampere/emag/clock.json   |  20 +++
 .../arch/arm64/ampere/emag/core-imp-def.json       |  32 ----
 .../arch/arm64/ampere/emag/exception.json          |  50 ++++++
 .../arch/arm64/ampere/emag/instruction.json        |  89 ++++++++++
 .../arch/arm64/ampere/emag/intrinsic.json          |  14 ++
 .../pmu-events/arch/arm64/ampere/emag/memory.json  |  29 ++++
 .../arch/arm64/ampere/emag/pipeline.json           |  50 ++++++
 10 files changed, 492 insertions(+), 32 deletions(-)
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json
 delete mode 100644 tools/perf/pmu-events/arch/arm64/ampere/emag/core-imp-def.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/emag/intrinsic.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json
 create mode 100644 tools/perf/pmu-events/arch/arm64/ampere/emag/pipeline.json

(limited to 'tools')

diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json
new file mode 100644
index 000000000000..abc98b018446
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json
@@ -0,0 +1,23 @@
+[
+    {
+        "ArchStdEvent": "BR_IMMED_SPEC",
+    },
+    {
+        "ArchStdEvent": "BR_RETURN_SPEC",
+    },
+    {
+        "ArchStdEvent": "BR_INDIRECT_SPEC",
+    },
+    {
+        "PublicDescription": "Mispredicted or not predicted branch speculatively executed",
+        "EventCode": "0x10",
+        "EventName": "BR_MIS_PRED",
+        "BriefDescription": "Branch mispredicted"
+    },
+    {
+        "PublicDescription": "Predictable branch speculatively executed",
+        "EventCode": "0x12",
+        "EventName": "BR_PRED",
+        "BriefDescription": "Predictable branch"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json
new file mode 100644
index 000000000000..687b2629e1d1
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json
@@ -0,0 +1,26 @@
+[
+    {
+        "ArchStdEvent": "BUS_ACCESS_RD",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_WR",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_SHARED",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_NOT_SHARED",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_NORMAL",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_PERIPH",
+    },
+    {
+        "PublicDescription": "Bus access",
+        "EventCode": "0x19",
+        "EventName": "BUS_ACCESS",
+        "BriefDescription": "Bus access"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json
new file mode 100644
index 000000000000..df9201434cb6
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json
@@ -0,0 +1,191 @@
+[
+    {
+        "ArchStdEvent": "L1D_CACHE_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WR",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_VICTIM",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_CLEAN",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_INVAL",
+    },
+    {
+        "PublicDescription": "Level 1 instruction cache refill",
+        "EventCode": "0x01",
+        "EventName": "L1I_CACHE_REFILL",
+        "BriefDescription": "L1I cache refill"
+    },
+    {
+        "PublicDescription": "Level 1 instruction TLB refill",
+        "EventCode": "0x02",
+        "EventName": "L1I_TLB_REFILL",
+        "BriefDescription": "L1I TLB refill"
+    },
+    {
+        "PublicDescription": "Level 1 data cache refill",
+        "EventCode": "0x03",
+        "EventName": "L1D_CACHE_REFILL",
+        "BriefDescription": "L1D cache refill"
+    },
+    {
+        "PublicDescription": "Level 1 data cache access",
+        "EventCode": "0x04",
+        "EventName": "L1D_CACHE_ACCESS",
+        "BriefDescription": "L1D cache access"
+    },
+    {
+        "PublicDescription": "Level 1 data TLB refill",
+        "EventCode": "0x05",
+        "EventName": "L1D_TLB_REFILL",
+        "BriefDescription": "L1D TLB refill"
+    },
+    {
+        "PublicDescription": "Level 1 instruction cache access",
+        "EventCode": "0x14",
+        "EventName": "L1I_CACHE_ACCESS",
+        "BriefDescription": "L1I cache access"
+    },
+    {
+        "PublicDescription": "Level 2 data cache access",
+        "EventCode": "0x16",
+        "EventName": "L2D_CACHE_ACCESS",
+        "BriefDescription": "L2D cache access"
+    },
+    {
+        "PublicDescription": "Level 2 data refill",
+        "EventCode": "0x17",
+        "EventName": "L2D_CACHE_REFILL",
+        "BriefDescription": "L2D cache refill"
+    },
+    {
+        "PublicDescription": "Level 2 data cache, Write-Back",
+        "EventCode": "0x18",
+        "EventName": "L2D_CACHE_WB",
+        "BriefDescription": "L2D cache Write-Back"
+    },
+    {
+        "PublicDescription": "Level 1 data TLB access. This event counts any load or store operation which accesses the data L1 TLB",
+        "EventCode": "0x25",
+        "EventName": "L1D_TLB_ACCESS",
+        "BriefDescription": "L1D TLB access"
+    },
+    {
+        "PublicDescription": "Level 1 instruction TLB access. This event counts any instruction fetch which accesses the instruction L1 TLB",
+        "EventCode": "0x26",
+        "EventName": "L1I_TLB_ACCESS",
+        "BriefDescription": "L1I TLB access"
+    },
+    {
+        "PublicDescription": "Level 2 access to data TLB that caused a page table walk. This event counts on any data access which causes L2D_TLB_REFILL to count",
+        "EventCode": "0x34",
+        "EventName": "L2D_TLB_ACCESS",
+        "BriefDescription": "L2D TLB access"
+    },
+    {
+        "PublicDescription": "Level 2 access to instruciton TLB that caused a page table walk. This event counts on any instruciton access which causes L2I_TLB_REFILL to count",
+        "EventCode": "0x35",
+        "EventName": "L2I_TLB_ACCESS",
+        "BriefDescription": "L2D TLB access"
+    },
+    {
+        "PublicDescription": "Branch target buffer misprediction",
+        "EventCode": "0x102",
+        "EventName": "BTB_MIS_PRED",
+        "BriefDescription": "BTB misprediction"
+    },
+    {
+        "PublicDescription": "ITB miss",
+        "EventCode": "0x103",
+        "EventName": "ITB_MISS",
+        "BriefDescription": "ITB miss"
+    },
+    {
+        "PublicDescription": "DTB miss",
+        "EventCode": "0x104",
+        "EventName": "DTB_MISS",
+        "BriefDescription": "DTB miss"
+    },
+    {
+        "PublicDescription": "Level 1 data cache late miss",
+        "EventCode": "0x105",
+        "EventName": "L1D_CACHE_LATE_MISS",
+        "BriefDescription": "L1D cache late miss"
+    },
+    {
+        "PublicDescription": "Level 1 data cache prefetch request",
+        "EventCode": "0x106",
+        "EventName": "L1D_CACHE_PREFETCH",
+        "BriefDescription": "L1D cache prefetch"
+    },
+    {
+        "PublicDescription": "Level 2 data cache prefetch request",
+        "EventCode": "0x107",
+        "EventName": "L2D_CACHE_PREFETCH",
+        "BriefDescription": "L2D cache prefetch"
+    },
+    {
+        "PublicDescription": "Level 1 stage 2 TLB refill",
+        "EventCode": "0x111",
+        "EventName": "L1_STAGE2_TLB_REFILL",
+        "BriefDescription": "L1 stage 2 TLB refill"
+    },
+    {
+        "PublicDescription": "Page walk cache level-0 stage-1 hit",
+        "EventCode": "0x112",
+        "EventName": "PAGE_WALK_L0_STAGE1_HIT",
+        "BriefDescription": "Page walk, L0 stage-1 hit"
+    },
+    {
+        "PublicDescription": "Page walk cache level-1 stage-1 hit",
+        "EventCode": "0x113",
+        "EventName": "PAGE_WALK_L1_STAGE1_HIT",
+        "BriefDescription": "Page walk, L1 stage-1 hit"
+    },
+    {
+        "PublicDescription": "Page walk cache level-2 stage-1 hit",
+        "EventCode": "0x114",
+        "EventName": "PAGE_WALK_L2_STAGE1_HIT",
+        "BriefDescription": "Page walk, L2 stage-1 hit"
+    },
+    {
+        "PublicDescription": "Page walk cache level-1 stage-2 hit",
+        "EventCode": "0x115",
+        "EventName": "PAGE_WALK_L1_STAGE2_HIT",
+        "BriefDescription": "Page walk, L1 stage-2 hit"
+    },
+    {
+        "PublicDescription": "Page walk cache level-2 stage-2 hit",
+        "EventCode": "0x116",
+        "EventName": "PAGE_WALK_L2_STAGE2_HIT",
+        "BriefDescription": "Page walk, L2 stage-2 hit"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json
new file mode 100644
index 000000000000..38cd1f1a70dc
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json
@@ -0,0 +1,20 @@
+[
+    {
+        "PublicDescription": "The number of core clock cycles",
+        "EventCode": "0x11",
+        "EventName": "CPU_CYCLES",
+        "BriefDescription": "Clock cycles"
+    },
+    {
+        "PublicDescription": "FSU clocking gated off cycle",
+        "EventCode": "0x101",
+        "EventName": "FSU_CLOCK_OFF_CYCLES",
+        "BriefDescription": "FSU clocking gated off cycle"
+    },
+    {
+        "PublicDescription": "Wait state cycle",
+        "EventCode": "0x110",
+        "EventName": "Wait_CYCLES",
+        "BriefDescription": "Wait state cycle"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/core-imp-def.json
deleted file mode 100644
index bc03c06c3918..000000000000
--- a/tools/perf/pmu-events/arch/arm64/ampere/emag/core-imp-def.json
+++ /dev/null
@@ -1,32 +0,0 @@
-[
-    {
-        "ArchStdEvent": "L1D_CACHE_RD",
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_WR",
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_REFILL_RD",
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_REFILL_WR",
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_REFILL_RD",
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_REFILL_WR",
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_RD",
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_WR",
-    },
-    {
-        "ArchStdEvent": "BUS_ACCESS_RD",
-   },
-   {
-        "ArchStdEvent": "BUS_ACCESS_WR",
-   }
-]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json
new file mode 100644
index 000000000000..3720dc28a15f
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json
@@ -0,0 +1,50 @@
+[
+    {
+        "ArchStdEvent": "EXC_UNDEF",
+    },
+    {
+        "ArchStdEvent": "EXC_SVC",
+    },
+    {
+        "ArchStdEvent": "EXC_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_FIQ",
+    },
+    {
+        "ArchStdEvent": "EXC_HVC",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_OTHER",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_FIQ",
+    },
+    {
+        "PublicDescription": "Exception taken",
+        "EventCode": "0x09",
+        "EventName": "EXC_TAKEN",
+        "BriefDescription": "Exception taken"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, condition check pass, exception return",
+        "EventCode": "0x0a",
+        "EventName": "EXC_RETURN",
+        "BriefDescription": "Exception return"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json
new file mode 100644
index 000000000000..82cf753e6472
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json
@@ -0,0 +1,89 @@
+[
+    {
+        "ArchStdEvent": "LD_SPEC",
+    },
+    {
+        "ArchStdEvent": "ST_SPEC",
+    },
+    {
+        "ArchStdEvent": "LDST_SPEC",
+    },
+    {
+        "ArchStdEvent": "DP_SPEC",
+    },
+    {
+        "ArchStdEvent": "ASE_SPEC",
+    },
+    {
+        "ArchStdEvent": "VFP_SPEC",
+    },
+    {
+        "ArchStdEvent": "PC_WRITE_SPEC",
+    },
+    {
+        "ArchStdEvent": "CRYPTO_SPEC",
+    },
+    {
+        "ArchStdEvent": "ISB_SPEC",
+    },
+    {
+        "ArchStdEvent": "DSB_SPEC",
+    },
+    {
+        "ArchStdEvent": "DMB_SPEC",
+    },
+    {
+        "ArchStdEvent": "RC_LD_SPEC",
+    },
+    {
+        "ArchStdEvent": "RC_ST_SPEC",
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, software increment",
+        "EventCode": "0x00",
+        "EventName": "SW_INCR",
+        "BriefDescription": "Software increment"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed",
+        "EventCode": "0x08",
+        "EventName": "INST_RETIRED",
+        "BriefDescription": "Instruction retired"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR",
+        "EventCode": "0x0b",
+        "EventName": "CID_WRITE_RETIRED",
+        "BriefDescription": "Write to CONTEXTIDR"
+    },
+    {
+        "PublicDescription": "Operation speculatively executed",
+        "EventCode": "0x1b",
+        "EventName": "INST_SPEC",
+        "BriefDescription": "Speculatively executed"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed (condition check pass), write to TTBR",
+        "EventCode": "0x1c",
+        "EventName": "TTBR_WRITE_RETIRED",
+        "BriefDescription": "Instruction executed, TTBR write"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, branch. This event counts all branches, taken or not. This excludes exception entries, debug entries and CCFAIL branches",
+        "EventCode": "0x21",
+        "EventName": "BR_RETIRED",
+        "BriefDescription": "Branch retired"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, mispredicted branch. This event counts any branch counted by BR_RETIRED which is not correctly predicted and causes a pipeline flush",
+        "EventCode": "0x22",
+        "EventName": "BR_MISPRED_RETIRED",
+        "BriefDescription": "Mispredicted branch retired"
+    },
+    {
+        "PublicDescription": "Operation speculatively executed, NOP",
+        "EventCode": "0x100",
+        "EventName": "NOP_SPEC",
+        "BriefDescription": "Speculatively executed, NOP"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/intrinsic.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/intrinsic.json
new file mode 100644
index 000000000000..2aecc5c2347d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/intrinsic.json
@@ -0,0 +1,14 @@
+[
+    {
+        "ArchStdEvent": "LDREX_SPEC",
+    },
+    {
+        "ArchStdEvent": "STREX_PASS_SPEC",
+    },
+    {
+        "ArchStdEvent": "STREX_FAIL_SPEC",
+    },
+    {
+        "ArchStdEvent": "STREX_SPEC",
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json
new file mode 100644
index 000000000000..08508697b318
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json
@@ -0,0 +1,29 @@
+[
+    {
+        "ArchStdEvent": "MEM_ACCESS_RD",
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_WR",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LD_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_ST_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LDST_SPEC",
+    },
+    {
+        "PublicDescription": "Data memory access",
+        "EventCode": "0x13",
+        "EventName": "MEM_ACCESS",
+        "BriefDescription": "Memory access"
+    },
+    {
+        "PublicDescription": "Local memory error. This event counts any correctable or uncorrectable memory error (ECC or parity) in the protected core RAMs",
+        "EventCode": "0x1a",
+        "EventName": "MEM_ERROR",
+        "BriefDescription": "Memory error"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/pipeline.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/pipeline.json
new file mode 100644
index 000000000000..e2087de586bf
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/pipeline.json
@@ -0,0 +1,50 @@
+[
+    {
+        "PublicDescription": "Decode starved for instruction cycle",
+        "EventCode": "0x108",
+        "EventName": "DECODE_STALL",
+        "BriefDescription": "Decode starved"
+    },
+    {
+        "PublicDescription": "Op dispatch stalled cycle",
+        "EventCode": "0x109",
+        "EventName": "DISPATCH_STALL",
+        "BriefDescription": "Dispatch stalled"
+    },
+    {
+        "PublicDescription": "IXA Op non-issue",
+        "EventCode": "0x10a",
+        "EventName": "IXA_STALL",
+        "BriefDescription": "IXA stalled"
+    },
+    {
+        "PublicDescription": "IXB Op non-issue",
+        "EventCode": "0x10b",
+        "EventName": "IXB_STALL",
+        "BriefDescription": "IXB stalled"
+    },
+    {
+        "PublicDescription": "BX Op non-issue",
+        "EventCode": "0x10c",
+        "EventName": "BX_STALL",
+        "BriefDescription": "BX stalled"
+    },
+    {
+        "PublicDescription": "LX Op non-issue",
+        "EventCode": "0x10d",
+        "EventName": "LX_STALL",
+        "BriefDescription": "LX stalled"
+    },
+    {
+        "PublicDescription": "SX Op non-issue",
+        "EventCode": "0x10e",
+        "EventName": "SX_STALL",
+        "BriefDescription": "SX stalled"
+    },
+    {
+        "PublicDescription": "FX Op non-issue",
+        "EventCode": "0x10f",
+        "EventName": "FX_STALL",
+        "BriefDescription": "FX stalled"
+    },
+]
-- 
cgit v1.2.3


From bccc17118bcf3c62c947361d51760334f6602f43 Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Fri, 21 Sep 2018 11:17:17 -0700
Subject: selftests/net: add ipv6 tests to ip_defrag selftest

This patch adds ipv6 defragmentation tests to ip_defrag selftest,
to complement existing ipv4 tests.

Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/ip_defrag.c  | 249 ++++++++++++++++++++-----------
 tools/testing/selftests/net/ip_defrag.sh |  39 +++--
 2 files changed, 190 insertions(+), 98 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/ip_defrag.c b/tools/testing/selftests/net/ip_defrag.c
index 55fdcdc78eef..2366dc6bce71 100644
--- a/tools/testing/selftests/net/ip_defrag.c
+++ b/tools/testing/selftests/net/ip_defrag.c
@@ -23,21 +23,28 @@ static bool		cfg_overlap;
 static unsigned short	cfg_port = 9000;
 
 const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) };
+const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT;
 
 #define IP4_HLEN	(sizeof(struct iphdr))
 #define IP6_HLEN	(sizeof(struct ip6_hdr))
 #define UDP_HLEN	(sizeof(struct udphdr))
 
-static int msg_len;
+/* IPv6 fragment header lenth. */
+#define FRAG_HLEN	8
+
+static int payload_len;
 static int max_frag_len;
 
 #define MSG_LEN_MAX	60000	/* Max UDP payload length. */
 
 #define IP4_MF		(1u << 13)  /* IPv4 MF flag. */
+#define IP6_MF		(1)  /* IPv6 MF flag. */
+
+#define CSUM_MANGLED_0 (0xffff)
 
 static uint8_t udp_payload[MSG_LEN_MAX];
 static uint8_t ip_frame[IP_MAXPACKET];
-static uint16_t ip_id = 0xabcd;
+static uint32_t ip_id = 0xabcd;
 static int msg_counter;
 static int frag_counter;
 static unsigned int seed;
@@ -48,25 +55,25 @@ static void recv_validate_udp(int fd_udp)
 	ssize_t ret;
 	static uint8_t recv_buff[MSG_LEN_MAX];
 
-	ret = recv(fd_udp, recv_buff, msg_len, 0);
+	ret = recv(fd_udp, recv_buff, payload_len, 0);
 	msg_counter++;
 
 	if (cfg_overlap) {
 		if (ret != -1)
-			error(1, 0, "recv: expected timeout; got %d; seed = %u",
-				(int)ret, seed);
+			error(1, 0, "recv: expected timeout; got %d",
+				(int)ret);
 		if (errno != ETIMEDOUT && errno != EAGAIN)
-			error(1, errno, "recv: expected timeout: %d; seed = %u",
-				 errno, seed);
+			error(1, errno, "recv: expected timeout: %d",
+				 errno);
 		return;  /* OK */
 	}
 
 	if (ret == -1)
-		error(1, errno, "recv: msg_len = %d max_frag_len = %d",
-			msg_len, max_frag_len);
-	if (ret != msg_len)
-		error(1, 0, "recv: wrong size: %d vs %d", (int)ret, msg_len);
-	if (memcmp(udp_payload, recv_buff, msg_len))
+		error(1, errno, "recv: payload_len = %d max_frag_len = %d",
+			payload_len, max_frag_len);
+	if (ret != payload_len)
+		error(1, 0, "recv: wrong size: %d vs %d", (int)ret, payload_len);
+	if (memcmp(udp_payload, recv_buff, payload_len))
 		error(1, 0, "recv: wrong data");
 }
 
@@ -92,31 +99,95 @@ static uint32_t raw_checksum(uint8_t *buf, int len, uint32_t sum)
 static uint16_t udp_checksum(struct ip *iphdr, struct udphdr *udphdr)
 {
 	uint32_t sum = 0;
+	uint16_t res;
 
 	sum = raw_checksum((uint8_t *)&iphdr->ip_src, 2 * sizeof(iphdr->ip_src),
-				IPPROTO_UDP + (uint32_t)(UDP_HLEN + msg_len));
-	sum = raw_checksum((uint8_t *)udp_payload, msg_len, sum);
+				IPPROTO_UDP + (uint32_t)(UDP_HLEN + payload_len));
+	sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum);
+	sum = raw_checksum((uint8_t *)udp_payload, payload_len, sum);
+	res = 0xffff & ~sum;
+	if (res)
+		return htons(res);
+	else
+		return CSUM_MANGLED_0;
+}
+
+static uint16_t udp6_checksum(struct ip6_hdr *iphdr, struct udphdr *udphdr)
+{
+	uint32_t sum = 0;
+	uint16_t res;
+
+	sum = raw_checksum((uint8_t *)&iphdr->ip6_src, 2 * sizeof(iphdr->ip6_src),
+				IPPROTO_UDP);
+	sum = raw_checksum((uint8_t *)&udphdr->len, sizeof(udphdr->len), sum);
 	sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum);
-	return htons(0xffff & ~sum);
+	sum = raw_checksum((uint8_t *)udp_payload, payload_len, sum);
+	res = 0xffff & ~sum;
+	if (res)
+		return htons(res);
+	else
+		return CSUM_MANGLED_0;
 }
 
 static void send_fragment(int fd_raw, struct sockaddr *addr, socklen_t alen,
-				struct ip *iphdr, int offset)
+				int offset, bool ipv6)
 {
 	int frag_len;
 	int res;
+	int payload_offset = offset > 0 ? offset - UDP_HLEN : 0;
+	uint8_t *frag_start = ipv6 ? ip_frame + IP6_HLEN + FRAG_HLEN :
+					ip_frame + IP4_HLEN;
+
+	if (offset == 0) {
+		struct udphdr udphdr;
+		udphdr.source = htons(cfg_port + 1);
+		udphdr.dest = htons(cfg_port);
+		udphdr.len = htons(UDP_HLEN + payload_len);
+		udphdr.check = 0;
+		if (ipv6)
+			udphdr.check = udp6_checksum((struct ip6_hdr *)ip_frame, &udphdr);
+		else
+			udphdr.check = udp_checksum((struct ip *)ip_frame, &udphdr);
+		memcpy(frag_start, &udphdr, UDP_HLEN);
+	}
 
-	if (msg_len - offset <= max_frag_len) {
-		/* This is the last fragment. */
-		frag_len = IP4_HLEN + msg_len - offset;
-		iphdr->ip_off = htons((offset + UDP_HLEN) / 8);
+	if (ipv6) {
+		struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame;
+		struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN);
+		if (payload_len - payload_offset <= max_frag_len && offset > 0) {
+			/* This is the last fragment. */
+			frag_len = FRAG_HLEN + payload_len - payload_offset;
+			fraghdr->ip6f_offlg = htons(offset);
+		} else {
+			frag_len = FRAG_HLEN + max_frag_len;
+			fraghdr->ip6f_offlg = htons(offset | IP6_MF);
+		}
+		ip6hdr->ip6_plen = htons(frag_len);
+		if (offset == 0)
+			memcpy(frag_start + UDP_HLEN, udp_payload,
+				frag_len - FRAG_HLEN - UDP_HLEN);
+		else
+			memcpy(frag_start, udp_payload + payload_offset,
+				frag_len - FRAG_HLEN);
+		frag_len += IP6_HLEN;
 	} else {
-		frag_len = IP4_HLEN + max_frag_len;
-		iphdr->ip_off = htons((offset + UDP_HLEN) / 8 | IP4_MF);
+		struct ip *iphdr = (struct ip *)ip_frame;
+		if (payload_len - payload_offset <= max_frag_len && offset > 0) {
+			/* This is the last fragment. */
+			frag_len = IP4_HLEN + payload_len - payload_offset;
+			iphdr->ip_off = htons(offset / 8);
+		} else {
+			frag_len = IP4_HLEN + max_frag_len;
+			iphdr->ip_off = htons(offset / 8 | IP4_MF);
+		}
+		iphdr->ip_len = htons(frag_len);
+		if (offset == 0)
+			memcpy(frag_start + UDP_HLEN, udp_payload,
+				frag_len - IP4_HLEN - UDP_HLEN);
+		else
+			memcpy(frag_start, udp_payload + payload_offset,
+				frag_len - IP4_HLEN);
 	}
-	iphdr->ip_len = htons(frag_len);
-	memcpy(ip_frame + IP4_HLEN, udp_payload + offset,
-		 frag_len - IP4_HLEN);
 
 	res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
 	if (res < 0)
@@ -127,9 +198,11 @@ static void send_fragment(int fd_raw, struct sockaddr *addr, socklen_t alen,
 	frag_counter++;
 }
 
-static void send_udp_frags_v4(int fd_raw, struct sockaddr *addr, socklen_t alen)
+static void send_udp_frags(int fd_raw, struct sockaddr *addr,
+				socklen_t alen, bool ipv6)
 {
 	struct ip *iphdr = (struct ip *)ip_frame;
+	struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame;
 	struct udphdr udphdr;
 	int res;
 	int offset;
@@ -142,31 +215,55 @@ static void send_udp_frags_v4(int fd_raw, struct sockaddr *addr, socklen_t alen)
 	 * Odd fragments (1st, 3rd, 5th, etc.) are sent out first, then
 	 * even fragments (0th, 2nd, etc.) are sent out.
 	 */
-	memset(iphdr, 0, sizeof(*iphdr));
-	iphdr->ip_hl = 5;
-	iphdr->ip_v = 4;
-	iphdr->ip_tos = 0;
-	iphdr->ip_id = htons(ip_id++);
-	iphdr->ip_ttl = 0x40;
-	iphdr->ip_p = IPPROTO_UDP;
-	iphdr->ip_src.s_addr = htonl(INADDR_LOOPBACK);
-	iphdr->ip_dst = addr4;
-	iphdr->ip_sum = 0;
+	if (ipv6) {
+		struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN);
+		((struct sockaddr_in6 *)addr)->sin6_port = 0;
+		memset(ip6hdr, 0, sizeof(*ip6hdr));
+		ip6hdr->ip6_flow = htonl(6<<28);  /* Version. */
+		ip6hdr->ip6_nxt = IPPROTO_FRAGMENT;
+		ip6hdr->ip6_hops = 255;
+		ip6hdr->ip6_src = addr6;
+		ip6hdr->ip6_dst = addr6;
+		fraghdr->ip6f_nxt = IPPROTO_UDP;
+		fraghdr->ip6f_reserved = 0;
+		fraghdr->ip6f_ident = htonl(ip_id++);
+	} else {
+		memset(iphdr, 0, sizeof(*iphdr));
+		iphdr->ip_hl = 5;
+		iphdr->ip_v = 4;
+		iphdr->ip_tos = 0;
+		iphdr->ip_id = htons(ip_id++);
+		iphdr->ip_ttl = 0x40;
+		iphdr->ip_p = IPPROTO_UDP;
+		iphdr->ip_src.s_addr = htonl(INADDR_LOOPBACK);
+		iphdr->ip_dst = addr4;
+		iphdr->ip_sum = 0;
+	}
 
 	/* Odd fragments. */
-	offset = 0;
-	while (offset < msg_len) {
-		send_fragment(fd_raw, addr, alen, iphdr, offset);
+	offset = max_frag_len;
+	while (offset < (UDP_HLEN + payload_len)) {
+		send_fragment(fd_raw, addr, alen, offset, ipv6);
 		offset += 2 * max_frag_len;
 	}
 
 	if (cfg_overlap) {
 		/* Send an extra random fragment. */
-		offset = rand() % (UDP_HLEN + msg_len - 1);
+		offset = rand() % (UDP_HLEN + payload_len - 1);
 		/* sendto() returns EINVAL if offset + frag_len is too small. */
-		frag_len = IP4_HLEN + UDP_HLEN + rand() % 256;
-		iphdr->ip_off = htons(offset / 8 | IP4_MF);
-		iphdr->ip_len = htons(frag_len);
+		if (ipv6) {
+			struct ip6_frag *fraghdr = (struct ip6_frag *)(ip_frame + IP6_HLEN);
+			frag_len = max_frag_len + rand() % 256;
+			/* In IPv6 if !!(frag_len % 8), the fragment is dropped. */
+			frag_len &= ~0x7;
+			fraghdr->ip6f_offlg = htons(offset / 8 | IP6_MF);
+			ip6hdr->ip6_plen = htons(frag_len);
+			frag_len += IP6_HLEN;
+		} else {
+			frag_len = IP4_HLEN + UDP_HLEN + rand() % 256;
+			iphdr->ip_off = htons(offset / 8 | IP4_MF);
+			iphdr->ip_len = htons(frag_len);
+		}
 		res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
 		if (res < 0)
 			error(1, errno, "sendto overlap");
@@ -175,48 +272,26 @@ static void send_udp_frags_v4(int fd_raw, struct sockaddr *addr, socklen_t alen)
 		frag_counter++;
 	}
 
-	/* Zeroth fragment (UDP header). */
-	frag_len = IP4_HLEN + UDP_HLEN;
-	iphdr->ip_len = htons(frag_len);
-	iphdr->ip_off = htons(IP4_MF);
-
-	udphdr.source = htons(cfg_port + 1);
-	udphdr.dest = htons(cfg_port);
-	udphdr.len = htons(UDP_HLEN + msg_len);
-	udphdr.check = 0;
-	udphdr.check = udp_checksum(iphdr, &udphdr);
-
-	memcpy(ip_frame + IP4_HLEN, &udphdr, UDP_HLEN);
-	res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen);
-	if (res < 0)
-		error(1, errno, "sendto UDP header");
-	if (res != frag_len)
-		error(1, 0, "sendto UDP header: %d vs %d", (int)res, frag_len);
-	frag_counter++;
-
-	/* Even fragments. */
-	offset = max_frag_len;
-	while (offset < msg_len) {
-		send_fragment(fd_raw, addr, alen, iphdr, offset);
+	/* Event fragments. */
+	offset = 0;
+	while (offset < (UDP_HLEN + payload_len)) {
+		send_fragment(fd_raw, addr, alen, offset, ipv6);
 		offset += 2 * max_frag_len;
 	}
 }
 
-static void run_test(struct sockaddr *addr, socklen_t alen)
+static void run_test(struct sockaddr *addr, socklen_t alen, bool ipv6)
 {
-	int fd_tx_udp, fd_tx_raw, fd_rx_udp;
+	int fd_tx_raw, fd_rx_udp;
 	struct timeval tv = { .tv_sec = 0, .tv_usec = 10 * 1000 };
 	int idx;
+	int min_frag_len = ipv6 ? 1280 : 8;
 
 	/* Initialize the payload. */
 	for (idx = 0; idx < MSG_LEN_MAX; ++idx)
 		udp_payload[idx] = idx % 256;
 
 	/* Open sockets. */
-	fd_tx_udp = socket(addr->sa_family, SOCK_DGRAM, 0);
-	if (fd_tx_udp == -1)
-		error(1, errno, "socket tx_udp");
-
 	fd_tx_raw = socket(addr->sa_family, SOCK_RAW, IPPROTO_RAW);
 	if (fd_tx_raw == -1)
 		error(1, errno, "socket tx_raw");
@@ -230,22 +305,21 @@ static void run_test(struct sockaddr *addr, socklen_t alen)
 	if (setsockopt(fd_rx_udp, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
 		error(1, errno, "setsockopt rcv timeout");
 
-	for (msg_len = 1; msg_len < MSG_LEN_MAX; msg_len += (rand() % 4096)) {
+	for (payload_len = min_frag_len; payload_len < MSG_LEN_MAX;
+			payload_len += (rand() % 4096)) {
 		if (cfg_verbose)
-			printf("msg_len: %d\n", msg_len);
-		max_frag_len = addr->sa_family == AF_INET ? 8 : 1280;
-		for (; max_frag_len < 1500 && max_frag_len <= msg_len;
-				max_frag_len += 8) {
-			send_udp_frags_v4(fd_tx_raw, addr, alen);
+			printf("payload_len: %d\n", payload_len);
+		max_frag_len = min_frag_len;
+		do {
+			send_udp_frags(fd_tx_raw, addr, alen, ipv6);
 			recv_validate_udp(fd_rx_udp);
-		}
+			max_frag_len += 8 * (rand() % 8);
+		} while (max_frag_len < (1500 - FRAG_HLEN) && max_frag_len <= payload_len);
 	}
 
 	/* Cleanup. */
 	if (close(fd_tx_raw))
 		error(1, errno, "close tx_raw");
-	if (close(fd_tx_udp))
-		error(1, errno, "close tx_udp");
 	if (close(fd_rx_udp))
 		error(1, errno, "close rx_udp");
 
@@ -265,13 +339,18 @@ static void run_test_v4(void)
 	addr.sin_port = htons(cfg_port);
 	addr.sin_addr = addr4;
 
-	run_test((void *)&addr, sizeof(addr));
+	run_test((void *)&addr, sizeof(addr), false /* !ipv6 */);
 }
 
 static void run_test_v6(void)
 {
-	fprintf(stderr, "NOT IMPL.\n");
-	exit(1);
+	struct sockaddr_in6 addr = {0};
+
+	addr.sin6_family = AF_INET6;
+	addr.sin6_port = htons(cfg_port);
+	addr.sin6_addr = addr6;
+
+	run_test((void *)&addr, sizeof(addr), true /* ipv6 */);
 }
 
 static void parse_opts(int argc, char **argv)
@@ -303,6 +382,8 @@ int main(int argc, char **argv)
 	parse_opts(argc, argv);
 	seed = time(NULL);
 	srand(seed);
+	/* Print the seed to track/reproduce potential failures. */
+	printf("seed = %d\n", seed);
 
 	if (cfg_do_ipv4)
 		run_test_v4();
diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh
index 78743adcca9e..3a4042d918f0 100755
--- a/tools/testing/selftests/net/ip_defrag.sh
+++ b/tools/testing/selftests/net/ip_defrag.sh
@@ -6,23 +6,34 @@
 set +x
 set -e
 
-echo "ipv4 defrag"
+readonly NETNS="ns-$(mktemp -u XXXXXX)"
+
+setup() {
+	ip netns add "${NETNS}"
+	ip -netns "${NETNS}" link set lo up
+	ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null
+	ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null
+	ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_high_thresh=9000000 &> /dev/null
+	ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_low_thresh=7000000 &> /dev/null
+}
 
-run_v4() {
-sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null
-sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null
-./ip_defrag -4
+cleanup() {
+	ip netns del "${NETNS}"
 }
-export -f run_v4
 
-./in_netns.sh "run_v4"
+trap cleanup EXIT
+setup
+
+echo "ipv4 defrag"
+ip netns exec "${NETNS}" ./ip_defrag -4
+
 
 echo "ipv4 defrag with overlaps"
-run_v4o() {
-sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null
-sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null
-./ip_defrag -4o
-}
-export -f run_v4o
+ip netns exec "${NETNS}" ./ip_defrag -4o
+
+echo "ipv6 defrag"
+ip netns exec "${NETNS}" ./ip_defrag -6
+
+echo "ipv6 defrag with overlaps"
+ip netns exec "${NETNS}" ./ip_defrag -6o
 
-./in_netns.sh "run_v4o"
-- 
cgit v1.2.3


From 5a5e3d3ceae2121590d67258a4e658d938b4a46d Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Date: Mon, 20 Aug 2018 10:12:50 +0530
Subject: perf probe: Support SDT markers having reference counter (semaphore)

With this, perf buildid-cache will save SDT markers with reference
counter in probe cache. Perf probe will be able to probe markers
having reference counter. Ex,

  # readelf -n /tmp/tick | grep -A1 loop2
    Name: loop2
    ... Semaphore: 0x0000000010020036

  # ./perf buildid-cache --add /tmp/tick
  # ./perf probe sdt_tick:loop2
  # ./perf stat -e sdt_tick:loop2 /tmp/tick
    hi: 0
    hi: 1
    hi: 2
    ^C
     Performance counter stats for '/tmp/tick':
                 3      sdt_tick:loop2
       2.561851452 seconds time elapsed

Link: http://lkml.kernel.org/r/20180820044250.11659-5-ravi.bangoria@linux.ibm.com

Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Reviewed-by: Song Liu <songliubraving@fb.com>
Tested-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 tools/perf/util/probe-event.c | 39 ++++++++++++++++++++++++++++++++----
 tools/perf/util/probe-event.h |  1 +
 tools/perf/util/probe-file.c  | 34 ++++++++++++++++++++++++++------
 tools/perf/util/probe-file.h  |  1 +
 tools/perf/util/symbol-elf.c  | 46 ++++++++++++++++++++++++++++++++-----------
 tools/perf/util/symbol.h      |  7 +++++++
 6 files changed, 106 insertions(+), 22 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index f119eb628dbb..e86f8be89157 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1819,6 +1819,12 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev)
 			tp->offset = strtoul(fmt2_str, NULL, 10);
 	}
 
+	if (tev->uprobes) {
+		fmt2_str = strchr(p, '(');
+		if (fmt2_str)
+			tp->ref_ctr_offset = strtoul(fmt2_str + 1, NULL, 0);
+	}
+
 	tev->nargs = argc - 2;
 	tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
 	if (tev->args == NULL) {
@@ -2012,6 +2018,22 @@ static int synthesize_probe_trace_arg(struct probe_trace_arg *arg,
 	return err;
 }
 
+static int
+synthesize_uprobe_trace_def(struct probe_trace_event *tev, struct strbuf *buf)
+{
+	struct probe_trace_point *tp = &tev->point;
+	int err;
+
+	err = strbuf_addf(buf, "%s:0x%lx", tp->module, tp->address);
+
+	if (err >= 0 && tp->ref_ctr_offset) {
+		if (!uprobe_ref_ctr_is_supported())
+			return -1;
+		err = strbuf_addf(buf, "(0x%lx)", tp->ref_ctr_offset);
+	}
+	return err >= 0 ? 0 : -1;
+}
+
 char *synthesize_probe_trace_command(struct probe_trace_event *tev)
 {
 	struct probe_trace_point *tp = &tev->point;
@@ -2041,15 +2063,17 @@ char *synthesize_probe_trace_command(struct probe_trace_event *tev)
 	}
 
 	/* Use the tp->address for uprobes */
-	if (tev->uprobes)
-		err = strbuf_addf(&buf, "%s:0x%lx", tp->module, tp->address);
-	else if (!strncmp(tp->symbol, "0x", 2))
+	if (tev->uprobes) {
+		err = synthesize_uprobe_trace_def(tev, &buf);
+	} else if (!strncmp(tp->symbol, "0x", 2)) {
 		/* Absolute address. See try_to_find_absolute_address() */
 		err = strbuf_addf(&buf, "%s%s0x%lx", tp->module ?: "",
 				  tp->module ? ":" : "", tp->address);
-	else
+	} else {
 		err = strbuf_addf(&buf, "%s%s%s+%lu", tp->module ?: "",
 				tp->module ? ":" : "", tp->symbol, tp->offset);
+	}
+
 	if (err)
 		goto error;
 
@@ -2633,6 +2657,13 @@ static void warn_uprobe_event_compat(struct probe_trace_event *tev)
 {
 	int i;
 	char *buf = synthesize_probe_trace_command(tev);
+	struct probe_trace_point *tp = &tev->point;
+
+	if (tp->ref_ctr_offset && !uprobe_ref_ctr_is_supported()) {
+		pr_warning("A semaphore is associated with %s:%s and "
+			   "seems your kernel doesn't support it.\n",
+			   tev->group, tev->event);
+	}
 
 	/* Old uprobe event doesn't support memory dereference */
 	if (!tev->uprobes || tev->nargs == 0 || !buf)
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 45b14f020558..15a98c3a2a2f 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -27,6 +27,7 @@ struct probe_trace_point {
 	char		*symbol;	/* Base symbol */
 	char		*module;	/* Module name */
 	unsigned long	offset;		/* Offset from symbol */
+	unsigned long	ref_ctr_offset;	/* SDT reference counter offset */
 	unsigned long	address;	/* Actual address of the trace point */
 	bool		retprobe;	/* Return probe flag */
 };
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index b76088fadf3d..aac7817d9e14 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -696,8 +696,16 @@ out_err:
 #ifdef HAVE_GELF_GETNOTE_SUPPORT
 static unsigned long long sdt_note__get_addr(struct sdt_note *note)
 {
-	return note->bit32 ? (unsigned long long)note->addr.a32[0]
-		 : (unsigned long long)note->addr.a64[0];
+	return note->bit32 ?
+		(unsigned long long)note->addr.a32[SDT_NOTE_IDX_LOC] :
+		(unsigned long long)note->addr.a64[SDT_NOTE_IDX_LOC];
+}
+
+static unsigned long long sdt_note__get_ref_ctr_offset(struct sdt_note *note)
+{
+	return note->bit32 ?
+		(unsigned long long)note->addr.a32[SDT_NOTE_IDX_REFCTR] :
+		(unsigned long long)note->addr.a64[SDT_NOTE_IDX_REFCTR];
 }
 
 static const char * const type_to_suffix[] = {
@@ -775,14 +783,21 @@ static char *synthesize_sdt_probe_command(struct sdt_note *note,
 {
 	struct strbuf buf;
 	char *ret = NULL, **args;
-	int i, args_count;
+	int i, args_count, err;
+	unsigned long long ref_ctr_offset;
 
 	if (strbuf_init(&buf, 32) < 0)
 		return NULL;
 
-	if (strbuf_addf(&buf, "p:%s/%s %s:0x%llx",
-				sdtgrp, note->name, pathname,
-				sdt_note__get_addr(note)) < 0)
+	err = strbuf_addf(&buf, "p:%s/%s %s:0x%llx",
+			sdtgrp, note->name, pathname,
+			sdt_note__get_addr(note));
+
+	ref_ctr_offset = sdt_note__get_ref_ctr_offset(note);
+	if (ref_ctr_offset && err >= 0)
+		err = strbuf_addf(&buf, "(0x%llx)", ref_ctr_offset);
+
+	if (err < 0)
 		goto error;
 
 	if (!note->args)
@@ -998,6 +1013,7 @@ int probe_cache__show_all_caches(struct strfilter *filter)
 enum ftrace_readme {
 	FTRACE_README_PROBE_TYPE_X = 0,
 	FTRACE_README_KRETPROBE_OFFSET,
+	FTRACE_README_UPROBE_REF_CTR,
 	FTRACE_README_END,
 };
 
@@ -1009,6 +1025,7 @@ static struct {
 	[idx] = {.pattern = pat, .avail = false}
 	DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"),
 	DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"),
+	DEFINE_TYPE(FTRACE_README_UPROBE_REF_CTR, "*ref_ctr_offset*"),
 };
 
 static bool scan_ftrace_readme(enum ftrace_readme type)
@@ -1064,3 +1081,8 @@ bool kretprobe_offset_is_supported(void)
 {
 	return scan_ftrace_readme(FTRACE_README_KRETPROBE_OFFSET);
 }
+
+bool uprobe_ref_ctr_is_supported(void)
+{
+	return scan_ftrace_readme(FTRACE_README_UPROBE_REF_CTR);
+}
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index 63f29b1d22c1..2a249182f2a6 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -69,6 +69,7 @@ struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache,
 int probe_cache__show_all_caches(struct strfilter *filter);
 bool probe_type_is_available(enum probe_type type);
 bool kretprobe_offset_is_supported(void);
+bool uprobe_ref_ctr_is_supported(void);
 #else	/* ! HAVE_LIBELF_SUPPORT */
 static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused, struct nsinfo *nsi __maybe_unused)
 {
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 29770ea61768..0281d5e2cd67 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1947,6 +1947,34 @@ void kcore_extract__delete(struct kcore_extract *kce)
 }
 
 #ifdef HAVE_GELF_GETNOTE_SUPPORT
+
+static void sdt_adjust_loc(struct sdt_note *tmp, GElf_Addr base_off)
+{
+	if (!base_off)
+		return;
+
+	if (tmp->bit32)
+		tmp->addr.a32[SDT_NOTE_IDX_LOC] =
+			tmp->addr.a32[SDT_NOTE_IDX_LOC] + base_off -
+			tmp->addr.a32[SDT_NOTE_IDX_BASE];
+	else
+		tmp->addr.a64[SDT_NOTE_IDX_LOC] =
+			tmp->addr.a64[SDT_NOTE_IDX_LOC] + base_off -
+			tmp->addr.a64[SDT_NOTE_IDX_BASE];
+}
+
+static void sdt_adjust_refctr(struct sdt_note *tmp, GElf_Addr base_addr,
+			      GElf_Addr base_off)
+{
+	if (!base_off)
+		return;
+
+	if (tmp->bit32 && tmp->addr.a32[SDT_NOTE_IDX_REFCTR])
+		tmp->addr.a32[SDT_NOTE_IDX_REFCTR] -= (base_addr - base_off);
+	else if (tmp->addr.a64[SDT_NOTE_IDX_REFCTR])
+		tmp->addr.a64[SDT_NOTE_IDX_REFCTR] -= (base_addr - base_off);
+}
+
 /**
  * populate_sdt_note : Parse raw data and identify SDT note
  * @elf: elf of the opened file
@@ -1964,7 +1992,6 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len,
 	const char *provider, *name, *args;
 	struct sdt_note *tmp = NULL;
 	GElf_Ehdr ehdr;
-	GElf_Addr base_off = 0;
 	GElf_Shdr shdr;
 	int ret = -EINVAL;
 
@@ -2060,17 +2087,12 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len,
 	 * base address in the description of the SDT note. If its different,
 	 * then accordingly, adjust the note location.
 	 */
-	if (elf_section_by_name(*elf, &ehdr, &shdr, SDT_BASE_SCN, NULL)) {
-		base_off = shdr.sh_offset;
-		if (base_off) {
-			if (tmp->bit32)
-				tmp->addr.a32[0] = tmp->addr.a32[0] + base_off -
-					tmp->addr.a32[1];
-			else
-				tmp->addr.a64[0] = tmp->addr.a64[0] + base_off -
-					tmp->addr.a64[1];
-		}
-	}
+	if (elf_section_by_name(*elf, &ehdr, &shdr, SDT_BASE_SCN, NULL))
+		sdt_adjust_loc(tmp, shdr.sh_offset);
+
+	/* Adjust reference counter offset */
+	if (elf_section_by_name(*elf, &ehdr, &shdr, SDT_PROBES_SCN, NULL))
+		sdt_adjust_refctr(tmp, shdr.sh_addr, shdr.sh_offset);
 
 	list_add_tail(&tmp->note_list, sdt_notes);
 	return 0;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index f25fae4b5743..20f49779116b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -379,12 +379,19 @@ int get_sdt_note_list(struct list_head *head, const char *target);
 int cleanup_sdt_note_list(struct list_head *sdt_notes);
 int sdt_notes__get_count(struct list_head *start);
 
+#define SDT_PROBES_SCN ".probes"
 #define SDT_BASE_SCN ".stapsdt.base"
 #define SDT_NOTE_SCN  ".note.stapsdt"
 #define SDT_NOTE_TYPE 3
 #define SDT_NOTE_NAME "stapsdt"
 #define NR_ADDR 3
 
+enum {
+	SDT_NOTE_IDX_LOC = 0,
+	SDT_NOTE_IDX_BASE,
+	SDT_NOTE_IDX_REFCTR,
+};
+
 struct mem_info *mem_info__new(void);
 struct mem_info *mem_info__get(struct mem_info *mi);
 void   mem_info__put(struct mem_info *mi);
-- 
cgit v1.2.3


From 25e11700b54c7b6b5ebfc4361981dae12299557b Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 11 Sep 2018 14:45:03 +0300
Subject: perf script python: Fix export-to-postgresql.py occasional failure

Occasional export failures were found to be caused by truncating 64-bit
pointers to 32-bits. Fix by explicitly setting types for all ctype
arguments and results.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/20180911114504.28516-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/export-to-postgresql.py | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index efcaf6cac2eb..e46f51b17513 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -204,14 +204,23 @@ from ctypes import *
 libpq = CDLL("libpq.so.5")
 PQconnectdb = libpq.PQconnectdb
 PQconnectdb.restype = c_void_p
+PQconnectdb.argtypes = [ c_char_p ]
 PQfinish = libpq.PQfinish
+PQfinish.argtypes = [ c_void_p ]
 PQstatus = libpq.PQstatus
+PQstatus.restype = c_int
+PQstatus.argtypes = [ c_void_p ]
 PQexec = libpq.PQexec
 PQexec.restype = c_void_p
+PQexec.argtypes = [ c_void_p, c_char_p ]
 PQresultStatus = libpq.PQresultStatus
+PQresultStatus.restype = c_int
+PQresultStatus.argtypes = [ c_void_p ]
 PQputCopyData = libpq.PQputCopyData
+PQputCopyData.restype = c_int
 PQputCopyData.argtypes = [ c_void_p, c_void_p, c_int ]
 PQputCopyEnd = libpq.PQputCopyEnd
+PQputCopyEnd.restype = c_int
 PQputCopyEnd.argtypes = [ c_void_p, c_void_p ]
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
-- 
cgit v1.2.3


From d005efe18db0b4a123dd92ea8e77e27aee8f99fd Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 11 Sep 2018 14:45:04 +0300
Subject: perf script python: Fix export-to-sqlite.py sample columns

With the "branches" export option, not all sample columns are exported.
However the unwanted columns are not at the end of the tuple, as assumed
by the code. Fix by taking the first 15 and last 3 values, instead of
the first 18.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/20180911114504.28516-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/export-to-sqlite.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
index f827bf77e9d2..e4bb82c8aba9 100644
--- a/tools/perf/scripts/python/export-to-sqlite.py
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -440,7 +440,11 @@ def branch_type_table(*x):
 
 def sample_table(*x):
 	if branches:
-		bind_exec(sample_query, 18, x)
+		for xx in x[0:15]:
+			sample_query.addBindValue(str(xx))
+		for xx in x[19:22]:
+			sample_query.addBindValue(str(xx))
+		do_query_(sample_query)
 	else:
 		bind_exec(sample_query, 22, x)
 
-- 
cgit v1.2.3


From 7ea3c40605e9acf12f2dda26e28cd82c0dba6923 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 21 Sep 2018 22:47:20 +0000
Subject: bpftool: add support for BPF_MAP_TYPE_REUSEPORT_SOCKARRAY maps

Add BPF_MAP_TYPE_REUSEPORT_SOCKARRAY map type to the list
of maps types which bpftool recognizes.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Cc: Yonghong Song <yhs@fb.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/map.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index af8ad32fa6e9..e22fbe8b975f 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -71,6 +71,7 @@ static const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_XSKMAP]           = "xskmap",
 	[BPF_MAP_TYPE_SOCKHASH]		= "sockhash",
 	[BPF_MAP_TYPE_CGROUP_STORAGE]	= "cgroup_storage",
+	[BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray",
 };
 
 static bool map_is_per_cpu(__u32 type)
-- 
cgit v1.2.3


From b34006c4258c9c86597b6b7123d6a9a3513d6cd7 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Tue, 18 Sep 2018 23:51:41 -0700
Subject: x86/jump_table: Use relative references

Similar to the arm64 case, 64-bit x86 can benefit from using relative
references rather than absolute ones when emitting struct jump_entry
instances. Not only does this reduce the memory footprint of the entries
themselves by 33%, it also removes the need for carrying relocation
metadata on relocatable builds (i.e., for KASLR) which saves a fair
chunk of .init space as well (although the savings are not as dramatic
as on arm64)

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-s390@vger.kernel.org
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Jessica Yu <jeyu@kernel.org>
Link: https://lkml.kernel.org/r/20180919065144.25010-7-ard.biesheuvel@linaro.org
---
 arch/x86/Kconfig                  |  1 +
 arch/x86/include/asm/jump_label.h | 24 ++++++++----------------
 tools/objtool/special.c           |  4 ++--
 3 files changed, 11 insertions(+), 18 deletions(-)

(limited to 'tools')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1a0be022f91d..603f374f871d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -119,6 +119,7 @@ config X86
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_HUGE_VMAP		if X86_64 || X86_PAE
 	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_JUMP_LABEL_RELATIVE
 	select HAVE_ARCH_KASAN			if X86_64
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_MMAP_RND_BITS		if MMU
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 8c0de4282659..21efc9d07ed9 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -37,7 +37,8 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran
 		".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
 		".pushsection __jump_table,  \"aw\" \n\t"
 		_ASM_ALIGN "\n\t"
-		_ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t"
+		".long 1b - ., %l[l_yes] - . \n\t"
+		_ASM_PTR "%c0 + %c1 - .\n\t"
 		".popsection \n\t"
 		: :  "i" (key), "i" (branch) : : l_yes);
 
@@ -53,7 +54,8 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key, bool
 		"2:\n\t"
 		".pushsection __jump_table,  \"aw\" \n\t"
 		_ASM_ALIGN "\n\t"
-		_ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t"
+		".long 1b - ., %l[l_yes] - . \n\t"
+		_ASM_PTR "%c0 + %c1 - .\n\t"
 		".popsection \n\t"
 		: :  "i" (key), "i" (branch) : : l_yes);
 
@@ -62,18 +64,6 @@ l_yes:
 	return true;
 }
 
-#ifdef CONFIG_X86_64
-typedef u64 jump_label_t;
-#else
-typedef u32 jump_label_t;
-#endif
-
-struct jump_entry {
-	jump_label_t code;
-	jump_label_t target;
-	jump_label_t key;
-};
-
 #else	/* __ASSEMBLY__ */
 
 .macro STATIC_JUMP_IF_TRUE target, key, def
@@ -88,7 +78,8 @@ struct jump_entry {
 	.endif
 	.pushsection __jump_table, "aw"
 	_ASM_ALIGN
-	_ASM_PTR	.Lstatic_jump_\@, \target, \key
+	.long		.Lstatic_jump_\@ - ., \target - .
+	_ASM_PTR	\key - .
 	.popsection
 .endm
 
@@ -104,7 +95,8 @@ struct jump_entry {
 	.endif
 	.pushsection __jump_table, "aw"
 	_ASM_ALIGN
-	_ASM_PTR	.Lstatic_jump_\@, \target, \key + 1
+	.long		.Lstatic_jump_\@ - ., \target - .
+	_ASM_PTR	\key + 1 - .
 	.popsection
 .endm
 
diff --git a/tools/objtool/special.c b/tools/objtool/special.c
index 84f001d52322..50af4e1274b3 100644
--- a/tools/objtool/special.c
+++ b/tools/objtool/special.c
@@ -30,9 +30,9 @@
 #define EX_ORIG_OFFSET		0
 #define EX_NEW_OFFSET		4
 
-#define JUMP_ENTRY_SIZE		24
+#define JUMP_ENTRY_SIZE		16
 #define JUMP_ORIG_OFFSET	0
-#define JUMP_NEW_OFFSET		8
+#define JUMP_NEW_OFFSET		4
 
 #define ALT_ENTRY_SIZE		13
 #define ALT_ORIG_OFFSET		0
-- 
cgit v1.2.3


From ce01a1575f45bf319e374592656441021a7f5823 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Date: Thu, 27 Sep 2018 14:39:19 -0400
Subject: rseq/selftests: fix parametrized test with -fpie

On x86-64, the parametrized selftest code for rseq crashes with a
segmentation fault when compiled with -fpie. This happens when the
param_test binary is loaded at an address beyond 32-bit on x86-64.

The issue is caused by use of a 32-bit register to hold the address
of the loop counter variable.

Fix this by using a 64-bit register to calculate the address of the
loop counter variables as an offset from rip.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: <stable@vger.kernel.org> # v4.18
Cc: Shuah Khan <shuah@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: linux-kselftest@vger.kernel.org
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/rseq/param_test.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 642d4e12abea..eec2663261f2 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -56,15 +56,13 @@ unsigned int yield_mod_cnt, nr_abort;
 			printf(fmt, ## __VA_ARGS__);	\
 	} while (0)
 
-#if defined(__x86_64__) || defined(__i386__)
+#ifdef __i386__
 
 #define INJECT_ASM_REG	"eax"
 
 #define RSEQ_INJECT_CLOBBER \
 	, INJECT_ASM_REG
 
-#ifdef __i386__
-
 #define RSEQ_INJECT_ASM(n) \
 	"mov asm_loop_cnt_" #n ", %%" INJECT_ASM_REG "\n\t" \
 	"test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \
@@ -76,9 +74,16 @@ unsigned int yield_mod_cnt, nr_abort;
 
 #elif defined(__x86_64__)
 
+#define INJECT_ASM_REG_P	"rax"
+#define INJECT_ASM_REG		"eax"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG_P \
+	, INJECT_ASM_REG
+
 #define RSEQ_INJECT_ASM(n) \
-	"lea asm_loop_cnt_" #n "(%%rip), %%" INJECT_ASM_REG "\n\t" \
-	"mov (%%" INJECT_ASM_REG "), %%" INJECT_ASM_REG "\n\t" \
+	"lea asm_loop_cnt_" #n "(%%rip), %%" INJECT_ASM_REG_P "\n\t" \
+	"mov (%%" INJECT_ASM_REG_P "), %%" INJECT_ASM_REG "\n\t" \
 	"test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \
 	"jz 333f\n\t" \
 	"222:\n\t" \
@@ -86,10 +91,6 @@ unsigned int yield_mod_cnt, nr_abort;
 	"jnz 222b\n\t" \
 	"333:\n\t"
 
-#else
-#error "Unsupported architecture"
-#endif
-
 #elif defined(__s390__)
 
 #define RSEQ_INJECT_INPUT \
-- 
cgit v1.2.3


From ff4ce2885af8f9e8e99864d78dbeb4673f089c76 Mon Sep 17 00:00:00 2001
From: Milian Wolff <milian.wolff@kdab.com>
Date: Wed, 26 Sep 2018 15:52:05 +0200
Subject: perf report: Don't try to map ip to invalid map

Fixes a crash when the report encounters an address that could not be
associated with an mmaped region:

  #0  0x00005555557bdc4a in callchain_srcline (ip=<error reading variable: Cannot access memory at address 0x38>, sym=0x0, map=0x0) at util/machine.c:2329
  #1  unwind_entry (entry=entry@entry=0x7fffffff9180, arg=arg@entry=0x7ffff5642498) at util/machine.c:2329
  #2  0x00005555558370af in entry (arg=0x7ffff5642498, cb=0x5555557bdb50 <unwind_entry>, thread=<optimized out>, ip=18446744073709551615) at util/unwind-libunwind-local.c:586
  #3  get_entries (ui=ui@entry=0x7fffffff9620, cb=0x5555557bdb50 <unwind_entry>, arg=0x7ffff5642498, max_stack=<optimized out>) at util/unwind-libunwind-local.c:703
  #4  0x0000555555837192 in _unwind__get_entries (cb=<optimized out>, arg=<optimized out>, thread=<optimized out>, data=<optimized out>, max_stack=<optimized out>) at util/unwind-libunwind-local.c:725
  #5  0x00005555557c310f in thread__resolve_callchain_unwind (max_stack=127, sample=0x7fffffff9830, evsel=0x555555c7b3b0, cursor=0x7ffff5642498, thread=0x555555c7f6f0) at util/machine.c:2351
  #6  thread__resolve_callchain (thread=0x555555c7f6f0, cursor=0x7ffff5642498, evsel=0x555555c7b3b0, sample=0x7fffffff9830, parent=0x7fffffff97b8, root_al=0x7fffffff9750, max_stack=127) at util/machine.c:2378
  #7  0x00005555557ba4ee in sample__resolve_callchain (sample=<optimized out>, cursor=<optimized out>, parent=parent@entry=0x7fffffff97b8, evsel=<optimized out>, al=al@entry=0x7fffffff9750,
      max_stack=<optimized out>) at util/callchain.c:1085

Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Tested-by: Sandipan Das <sandipan@linux.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Fixes: 2a9d5050dc84 ("perf script: Show correct offsets for DWARF-based unwinding")
Link: http://lkml.kernel.org/r/20180926135207.30263-1-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/machine.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c4acd2001db0..0cb4f8bf3ca7 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2312,7 +2312,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
 	struct callchain_cursor *cursor = arg;
 	const char *srcline = NULL;
-	u64 addr;
+	u64 addr = entry->ip;
 
 	if (symbol_conf.hide_unresolved && entry->sym == NULL)
 		return 0;
@@ -2324,7 +2324,8 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	 * Convert entry->ip from a virtual address to an offset in
 	 * its corresponding binary.
 	 */
-	addr = map__map_ip(entry->map, entry->ip);
+	if (entry->map)
+		addr = map__map_ip(entry->map, entry->ip);
 
 	srcline = callchain_srcline(entry->map, entry->sym, addr);
 	return callchain_cursor_append(cursor, entry->ip,
-- 
cgit v1.2.3


From 53d6eb08e9f185834231d5c32499b10310cce3aa Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Tue, 25 Sep 2018 15:20:37 -0700
Subject: bpftool: Fix bpftool net output

Print `bpftool net` output to stdout instead of stderr. Only errors
should be printed to stderr. Regular output should go to stdout and this
is what all other subcommands of bpftool do, including --json and
--pretty formats of `bpftool net` itself.

Fixes: commit f6f3bac08ff9 ("tools/bpf: bpftool: add net support")
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/netlink_dumper.h | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h
index 0788cfbbed0e..e3516b586a34 100644
--- a/tools/bpf/bpftool/netlink_dumper.h
+++ b/tools/bpf/bpftool/netlink_dumper.h
@@ -16,7 +16,7 @@
 		jsonw_name(json_wtr, name);		\
 		jsonw_start_object(json_wtr);		\
 	} else {					\
-		fprintf(stderr, "%s {", name);		\
+		fprintf(stdout, "%s {", name);		\
 	}						\
 }
 
@@ -25,7 +25,7 @@
 	if (json_output)				\
 		jsonw_start_object(json_wtr);		\
 	else						\
-		fprintf(stderr, "{");			\
+		fprintf(stdout, "{");			\
 }
 
 #define NET_END_OBJECT_NESTED				\
@@ -33,7 +33,7 @@
 	if (json_output)				\
 		jsonw_end_object(json_wtr);		\
 	else						\
-		fprintf(stderr, "}");			\
+		fprintf(stdout, "}");			\
 }
 
 #define NET_END_OBJECT					\
@@ -47,7 +47,7 @@
 	if (json_output)				\
 		jsonw_end_object(json_wtr);		\
 	else						\
-		fprintf(stderr, "\n");			\
+		fprintf(stdout, "\n");			\
 }
 
 #define NET_START_ARRAY(name, fmt_str)			\
@@ -56,7 +56,7 @@
 		jsonw_name(json_wtr, name);		\
 		jsonw_start_array(json_wtr);		\
 	} else {					\
-		fprintf(stderr, fmt_str, name);		\
+		fprintf(stdout, fmt_str, name);		\
 	}						\
 }
 
@@ -65,7 +65,7 @@
 	if (json_output)				\
 		jsonw_end_array(json_wtr);		\
 	else						\
-		fprintf(stderr, "%s", endstr);		\
+		fprintf(stdout, "%s", endstr);		\
 }
 
 #define NET_DUMP_UINT(name, fmt_str, val)		\
@@ -73,7 +73,7 @@
 	if (json_output)				\
 		jsonw_uint_field(json_wtr, name, val);	\
 	else						\
-		fprintf(stderr, fmt_str, val);		\
+		fprintf(stdout, fmt_str, val);		\
 }
 
 #define NET_DUMP_STR(name, fmt_str, str)		\
@@ -81,7 +81,7 @@
 	if (json_output)				\
 		jsonw_string_field(json_wtr, name, str);\
 	else						\
-		fprintf(stderr, fmt_str, str);		\
+		fprintf(stdout, fmt_str, str);		\
 }
 
 #define NET_DUMP_STR_ONLY(str)				\
@@ -89,7 +89,7 @@
 	if (json_output)				\
 		jsonw_string(json_wtr, str);		\
 	else						\
-		fprintf(stderr, "%s ", str);		\
+		fprintf(stdout, "%s ", str);		\
 }
 
 #endif
-- 
cgit v1.2.3


From 956b620fcf0b64de403cd26a56bc41e6e4826ea6 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 26 Sep 2018 15:24:53 -0700
Subject: libbpf: Introduce libbpf_attach_type_by_name

There is a common use-case when ELF object contains multiple BPF
programs and every program has its own section name. If it's cgroup-bpf
then programs have to be 1) loaded and 2) attached to a cgroup.

It's convenient to have information necessary to load BPF program
together with program itself. This is where section name works fine in
conjunction with libbpf_prog_type_by_name that identifies prog_type and
expected_attach_type and these can be used with BPF_PROG_LOAD.

But there is currently no way to identify attach_type by section name
and it leads to messy code in user space that reinvents guessing logic
every time it has to identify attach type to use with BPF_PROG_ATTACH.

The patch introduces libbpf_attach_type_by_name that guesses attach type
by section name if a program can be attached.

The difference between expected_attach_type provided by
libbpf_prog_type_by_name and attach_type provided by
libbpf_attach_type_by_name is the former is used at BPF_PROG_LOAD time
and can be zero if a program of prog_type X has only one corresponding
attach type Y whether the latter provides specific attach type to use
with BPF_PROG_ATTACH.

No new section names were added to section_names array. Only existing
ones were reorganized and attach_type was added where appropriate.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 121 +++++++++++++++++++++++++++++++++----------------
 tools/lib/bpf/libbpf.h |   2 +
 2 files changed, 84 insertions(+), 39 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 4f8d43ae20d2..59e589a64d5c 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2085,58 +2085,82 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 	prog->expected_attach_type = type;
 }
 
-#define BPF_PROG_SEC_FULL(string, ptype, atype) \
-	{ string, sizeof(string) - 1, ptype, atype }
+#define BPF_PROG_SEC_IMPL(string, ptype, eatype, atype) \
+	{ string, sizeof(string) - 1, ptype, eatype, atype }
 
-#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_FULL(string, ptype, 0)
+/* Programs that can NOT be attached. */
+#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, -EINVAL)
 
-#define BPF_S_PROG_SEC(string, ptype) \
-	BPF_PROG_SEC_FULL(string, BPF_PROG_TYPE_CGROUP_SOCK, ptype)
+/* Programs that can be attached. */
+#define BPF_APROG_SEC(string, ptype, atype) \
+	BPF_PROG_SEC_IMPL(string, ptype, 0, atype)
 
-#define BPF_SA_PROG_SEC(string, ptype) \
-	BPF_PROG_SEC_FULL(string, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, ptype)
+/* Programs that must specify expected attach type at load time. */
+#define BPF_EAPROG_SEC(string, ptype, eatype) \
+	BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype)
+
+/* Programs that can be attached but attach type can't be identified by section
+ * name. Kept for backward compatibility.
+ */
+#define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype)
 
 static const struct {
 	const char *sec;
 	size_t len;
 	enum bpf_prog_type prog_type;
 	enum bpf_attach_type expected_attach_type;
+	enum bpf_attach_type attach_type;
 } section_names[] = {
-	BPF_PROG_SEC("socket",		BPF_PROG_TYPE_SOCKET_FILTER),
-	BPF_PROG_SEC("kprobe/",		BPF_PROG_TYPE_KPROBE),
-	BPF_PROG_SEC("kretprobe/",	BPF_PROG_TYPE_KPROBE),
-	BPF_PROG_SEC("classifier",	BPF_PROG_TYPE_SCHED_CLS),
-	BPF_PROG_SEC("action",		BPF_PROG_TYPE_SCHED_ACT),
-	BPF_PROG_SEC("tracepoint/",	BPF_PROG_TYPE_TRACEPOINT),
-	BPF_PROG_SEC("raw_tracepoint/",	BPF_PROG_TYPE_RAW_TRACEPOINT),
-	BPF_PROG_SEC("xdp",		BPF_PROG_TYPE_XDP),
-	BPF_PROG_SEC("perf_event",	BPF_PROG_TYPE_PERF_EVENT),
-	BPF_PROG_SEC("cgroup/skb",	BPF_PROG_TYPE_CGROUP_SKB),
-	BPF_PROG_SEC("cgroup/sock",	BPF_PROG_TYPE_CGROUP_SOCK),
-	BPF_PROG_SEC("cgroup/dev",	BPF_PROG_TYPE_CGROUP_DEVICE),
-	BPF_PROG_SEC("lwt_in",		BPF_PROG_TYPE_LWT_IN),
-	BPF_PROG_SEC("lwt_out",		BPF_PROG_TYPE_LWT_OUT),
-	BPF_PROG_SEC("lwt_xmit",	BPF_PROG_TYPE_LWT_XMIT),
-	BPF_PROG_SEC("lwt_seg6local",	BPF_PROG_TYPE_LWT_SEG6LOCAL),
-	BPF_PROG_SEC("sockops",		BPF_PROG_TYPE_SOCK_OPS),
-	BPF_PROG_SEC("sk_skb",		BPF_PROG_TYPE_SK_SKB),
-	BPF_PROG_SEC("sk_msg",		BPF_PROG_TYPE_SK_MSG),
-	BPF_PROG_SEC("lirc_mode2",	BPF_PROG_TYPE_LIRC_MODE2),
-	BPF_PROG_SEC("flow_dissector",	BPF_PROG_TYPE_FLOW_DISSECTOR),
-	BPF_SA_PROG_SEC("cgroup/bind4",	BPF_CGROUP_INET4_BIND),
-	BPF_SA_PROG_SEC("cgroup/bind6",	BPF_CGROUP_INET6_BIND),
-	BPF_SA_PROG_SEC("cgroup/connect4", BPF_CGROUP_INET4_CONNECT),
-	BPF_SA_PROG_SEC("cgroup/connect6", BPF_CGROUP_INET6_CONNECT),
-	BPF_SA_PROG_SEC("cgroup/sendmsg4", BPF_CGROUP_UDP4_SENDMSG),
-	BPF_SA_PROG_SEC("cgroup/sendmsg6", BPF_CGROUP_UDP6_SENDMSG),
-	BPF_S_PROG_SEC("cgroup/post_bind4", BPF_CGROUP_INET4_POST_BIND),
-	BPF_S_PROG_SEC("cgroup/post_bind6", BPF_CGROUP_INET6_POST_BIND),
+	BPF_PROG_SEC("socket",			BPF_PROG_TYPE_SOCKET_FILTER),
+	BPF_PROG_SEC("kprobe/",			BPF_PROG_TYPE_KPROBE),
+	BPF_PROG_SEC("kretprobe/",		BPF_PROG_TYPE_KPROBE),
+	BPF_PROG_SEC("classifier",		BPF_PROG_TYPE_SCHED_CLS),
+	BPF_PROG_SEC("action",			BPF_PROG_TYPE_SCHED_ACT),
+	BPF_PROG_SEC("tracepoint/",		BPF_PROG_TYPE_TRACEPOINT),
+	BPF_PROG_SEC("raw_tracepoint/",		BPF_PROG_TYPE_RAW_TRACEPOINT),
+	BPF_PROG_SEC("xdp",			BPF_PROG_TYPE_XDP),
+	BPF_PROG_SEC("perf_event",		BPF_PROG_TYPE_PERF_EVENT),
+	BPF_PROG_SEC("lwt_in",			BPF_PROG_TYPE_LWT_IN),
+	BPF_PROG_SEC("lwt_out",			BPF_PROG_TYPE_LWT_OUT),
+	BPF_PROG_SEC("lwt_xmit",		BPF_PROG_TYPE_LWT_XMIT),
+	BPF_PROG_SEC("lwt_seg6local",		BPF_PROG_TYPE_LWT_SEG6LOCAL),
+	BPF_APROG_COMPAT("cgroup/skb",		BPF_PROG_TYPE_CGROUP_SKB),
+	BPF_APROG_SEC("cgroup/sock",		BPF_PROG_TYPE_CGROUP_SOCK,
+						BPF_CGROUP_INET_SOCK_CREATE),
+	BPF_EAPROG_SEC("cgroup/post_bind4",	BPF_PROG_TYPE_CGROUP_SOCK,
+						BPF_CGROUP_INET4_POST_BIND),
+	BPF_EAPROG_SEC("cgroup/post_bind6",	BPF_PROG_TYPE_CGROUP_SOCK,
+						BPF_CGROUP_INET6_POST_BIND),
+	BPF_APROG_SEC("cgroup/dev",		BPF_PROG_TYPE_CGROUP_DEVICE,
+						BPF_CGROUP_DEVICE),
+	BPF_APROG_SEC("sockops",		BPF_PROG_TYPE_SOCK_OPS,
+						BPF_CGROUP_SOCK_OPS),
+	BPF_APROG_COMPAT("sk_skb",		BPF_PROG_TYPE_SK_SKB),
+	BPF_APROG_SEC("sk_msg",			BPF_PROG_TYPE_SK_MSG,
+						BPF_SK_MSG_VERDICT),
+	BPF_APROG_SEC("lirc_mode2",		BPF_PROG_TYPE_LIRC_MODE2,
+						BPF_LIRC_MODE2),
+	BPF_APROG_SEC("flow_dissector",		BPF_PROG_TYPE_FLOW_DISSECTOR,
+						BPF_FLOW_DISSECTOR),
+	BPF_EAPROG_SEC("cgroup/bind4",		BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+						BPF_CGROUP_INET4_BIND),
+	BPF_EAPROG_SEC("cgroup/bind6",		BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+						BPF_CGROUP_INET6_BIND),
+	BPF_EAPROG_SEC("cgroup/connect4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+						BPF_CGROUP_INET4_CONNECT),
+	BPF_EAPROG_SEC("cgroup/connect6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+						BPF_CGROUP_INET6_CONNECT),
+	BPF_EAPROG_SEC("cgroup/sendmsg4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+						BPF_CGROUP_UDP4_SENDMSG),
+	BPF_EAPROG_SEC("cgroup/sendmsg6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+						BPF_CGROUP_UDP6_SENDMSG),
 };
 
+#undef BPF_PROG_SEC_IMPL
 #undef BPF_PROG_SEC
-#undef BPF_PROG_SEC_FULL
-#undef BPF_S_PROG_SEC
-#undef BPF_SA_PROG_SEC
+#undef BPF_APROG_SEC
+#undef BPF_EAPROG_SEC
+#undef BPF_APROG_COMPAT
 
 int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 			     enum bpf_attach_type *expected_attach_type)
@@ -2156,6 +2180,25 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 	return -EINVAL;
 }
 
+int libbpf_attach_type_by_name(const char *name,
+			       enum bpf_attach_type *attach_type)
+{
+	int i;
+
+	if (!name)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(section_names); i++) {
+		if (strncmp(name, section_names[i].sec, section_names[i].len))
+			continue;
+		if (section_names[i].attach_type == -EINVAL)
+			return -EINVAL;
+		*attach_type = section_names[i].attach_type;
+		return 0;
+	}
+	return -EINVAL;
+}
+
 static int
 bpf_program__identify_section(struct bpf_program *prog,
 			      enum bpf_prog_type *prog_type,
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e3b00e23e181..511c1294dcbf 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -104,6 +104,8 @@ void *bpf_object__priv(struct bpf_object *prog);
 
 int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 			     enum bpf_attach_type *expected_attach_type);
+int libbpf_attach_type_by_name(const char *name,
+			       enum bpf_attach_type *attach_type);
 
 /* Accessors of bpf_program */
 struct bpf_program;
-- 
cgit v1.2.3


From bafa7afe63391419c7cb8e42f1ba9f8dddd7c8fb Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 26 Sep 2018 15:24:54 -0700
Subject: libbpf: Support cgroup_skb/{e,in}gress section names

Add section names for BPF_CGROUP_INET_INGRESS and BPF_CGROUP_INET_EGRESS
attach types to be able to identify them in libbpf_attach_type_by_name.

"cgroup_skb" is used instead of "cgroup/skb" mostly to easy possible
unifying of how libbpf and bpftool works with section names:
* bpftool uses "cgroup_skb" to in "prog list" sub-command;
* bpftool uses "ingress" and "egress" in "cgroup list" sub-command;
* having two parts instead of three in a string like "cgroup_skb/ingress"
  can be leveraged to split it to prog_type part and attach_type part,
  or vise versa: use two parts to make a section name.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 59e589a64d5c..51edf6cd390e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2124,6 +2124,10 @@ static const struct {
 	BPF_PROG_SEC("lwt_out",			BPF_PROG_TYPE_LWT_OUT),
 	BPF_PROG_SEC("lwt_xmit",		BPF_PROG_TYPE_LWT_XMIT),
 	BPF_PROG_SEC("lwt_seg6local",		BPF_PROG_TYPE_LWT_SEG6LOCAL),
+	BPF_APROG_SEC("cgroup_skb/ingress",	BPF_PROG_TYPE_CGROUP_SKB,
+						BPF_CGROUP_INET_INGRESS),
+	BPF_APROG_SEC("cgroup_skb/egress",	BPF_PROG_TYPE_CGROUP_SKB,
+						BPF_CGROUP_INET_EGRESS),
 	BPF_APROG_COMPAT("cgroup/skb",		BPF_PROG_TYPE_CGROUP_SKB),
 	BPF_APROG_SEC("cgroup/sock",		BPF_PROG_TYPE_CGROUP_SOCK,
 						BPF_CGROUP_INET_SOCK_CREATE),
-- 
cgit v1.2.3


From c6f6851b28ae26000352598f01968b3ff7dcf588 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 26 Sep 2018 15:24:55 -0700
Subject: libbpf: Support sk_skb/stream_{parser, verdict} section names

Add section names for BPF_SK_SKB_STREAM_PARSER and
BPF_SK_SKB_STREAM_VERDICT attach types to be able to identify them in
libbpf_attach_type_by_name.

"stream_parser" and "stream_verdict" are used instead of simple "parser"
and "verdict" just to avoid possible confusion in a place where attach
type is used alone (e.g. in bpftool's show sub-commands) since there is
another attach point that can be named as "verdict": BPF_SK_MSG_VERDICT.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 51edf6cd390e..425d5ca45c97 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2139,6 +2139,10 @@ static const struct {
 						BPF_CGROUP_DEVICE),
 	BPF_APROG_SEC("sockops",		BPF_PROG_TYPE_SOCK_OPS,
 						BPF_CGROUP_SOCK_OPS),
+	BPF_APROG_SEC("sk_skb/stream_parser",	BPF_PROG_TYPE_SK_SKB,
+						BPF_SK_SKB_STREAM_PARSER),
+	BPF_APROG_SEC("sk_skb/stream_verdict",	BPF_PROG_TYPE_SK_SKB,
+						BPF_SK_SKB_STREAM_VERDICT),
 	BPF_APROG_COMPAT("sk_skb",		BPF_PROG_TYPE_SK_SKB),
 	BPF_APROG_SEC("sk_msg",			BPF_PROG_TYPE_SK_MSG,
 						BPF_SK_MSG_VERDICT),
-- 
cgit v1.2.3


From c9bf507d0acba950e5d85ef27727ce61458ef5aa Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 26 Sep 2018 15:24:56 -0700
Subject: selftests/bpf: Use libbpf_attach_type_by_name in test_socket_cookie

Use newly introduced libbpf_attach_type_by_name in test_socket_cookie
selftest.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_socket_cookie.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_socket_cookie.c b/tools/testing/selftests/bpf/test_socket_cookie.c
index 68e108e4687a..b6c2c605d8c0 100644
--- a/tools/testing/selftests/bpf/test_socket_cookie.c
+++ b/tools/testing/selftests/bpf/test_socket_cookie.c
@@ -158,11 +158,7 @@ static int run_test(int cgfd)
 	bpf_object__for_each_program(prog, pobj) {
 		prog_name = bpf_program__title(prog, /*needs_copy*/ false);
 
-		if (strcmp(prog_name, "cgroup/connect6") == 0) {
-			attach_type = BPF_CGROUP_INET6_CONNECT;
-		} else if (strcmp(prog_name, "sockops") == 0) {
-			attach_type = BPF_CGROUP_SOCK_OPS;
-		} else {
+		if (libbpf_attach_type_by_name(prog_name, &attach_type)) {
 			log_err("Unexpected prog: %s", prog_name);
 			goto err;
 		}
-- 
cgit v1.2.3


From 370920c47b26ae3a837f7c46f0795804ae2940f7 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 26 Sep 2018 15:24:57 -0700
Subject: selftests/bpf: Test libbpf_{prog,attach}_type_by_name

Add selftest for libbpf functions libbpf_prog_type_by_name and
libbpf_attach_type_by_name.

Example of output:
  % ./tools/testing/selftests/bpf/test_section_names
  Summary: 35 PASSED, 0 FAILED

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile             |   2 +-
 tools/testing/selftests/bpf/test_section_names.c | 208 +++++++++++++++++++++++
 2 files changed, 209 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/test_section_names.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index fd3851d5c079..059d64a0f897 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -23,7 +23,7 @@ $(TEST_CUSTOM_PROGS): $(OUTPUT)/%: %.c
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
 	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
 	test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
-	test_socket_cookie test_cgroup_storage test_select_reuseport
+	test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
 	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
diff --git a/tools/testing/selftests/bpf/test_section_names.c b/tools/testing/selftests/bpf/test_section_names.c
new file mode 100644
index 000000000000..7c4f41572b1c
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_section_names.c
@@ -0,0 +1,208 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <err.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_util.h"
+
+struct sec_name_test {
+	const char sec_name[32];
+	struct {
+		int rc;
+		enum bpf_prog_type prog_type;
+		enum bpf_attach_type expected_attach_type;
+	} expected_load;
+	struct {
+		int rc;
+		enum bpf_attach_type attach_type;
+	} expected_attach;
+};
+
+static struct sec_name_test tests[] = {
+	{"InvAliD", {-EINVAL, 0, 0}, {-EINVAL, 0} },
+	{"cgroup", {-EINVAL, 0, 0}, {-EINVAL, 0} },
+	{"socket", {0, BPF_PROG_TYPE_SOCKET_FILTER, 0}, {-EINVAL, 0} },
+	{"kprobe/", {0, BPF_PROG_TYPE_KPROBE, 0}, {-EINVAL, 0} },
+	{"kretprobe/", {0, BPF_PROG_TYPE_KPROBE, 0}, {-EINVAL, 0} },
+	{"classifier", {0, BPF_PROG_TYPE_SCHED_CLS, 0}, {-EINVAL, 0} },
+	{"action", {0, BPF_PROG_TYPE_SCHED_ACT, 0}, {-EINVAL, 0} },
+	{"tracepoint/", {0, BPF_PROG_TYPE_TRACEPOINT, 0}, {-EINVAL, 0} },
+	{
+		"raw_tracepoint/",
+		{0, BPF_PROG_TYPE_RAW_TRACEPOINT, 0},
+		{-EINVAL, 0},
+	},
+	{"xdp", {0, BPF_PROG_TYPE_XDP, 0}, {-EINVAL, 0} },
+	{"perf_event", {0, BPF_PROG_TYPE_PERF_EVENT, 0}, {-EINVAL, 0} },
+	{"lwt_in", {0, BPF_PROG_TYPE_LWT_IN, 0}, {-EINVAL, 0} },
+	{"lwt_out", {0, BPF_PROG_TYPE_LWT_OUT, 0}, {-EINVAL, 0} },
+	{"lwt_xmit", {0, BPF_PROG_TYPE_LWT_XMIT, 0}, {-EINVAL, 0} },
+	{"lwt_seg6local", {0, BPF_PROG_TYPE_LWT_SEG6LOCAL, 0}, {-EINVAL, 0} },
+	{
+		"cgroup_skb/ingress",
+		{0, BPF_PROG_TYPE_CGROUP_SKB, 0},
+		{0, BPF_CGROUP_INET_INGRESS},
+	},
+	{
+		"cgroup_skb/egress",
+		{0, BPF_PROG_TYPE_CGROUP_SKB, 0},
+		{0, BPF_CGROUP_INET_EGRESS},
+	},
+	{"cgroup/skb", {0, BPF_PROG_TYPE_CGROUP_SKB, 0}, {-EINVAL, 0} },
+	{
+		"cgroup/sock",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK, 0},
+		{0, BPF_CGROUP_INET_SOCK_CREATE},
+	},
+	{
+		"cgroup/post_bind4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND},
+		{0, BPF_CGROUP_INET4_POST_BIND},
+	},
+	{
+		"cgroup/post_bind6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND},
+		{0, BPF_CGROUP_INET6_POST_BIND},
+	},
+	{
+		"cgroup/dev",
+		{0, BPF_PROG_TYPE_CGROUP_DEVICE, 0},
+		{0, BPF_CGROUP_DEVICE},
+	},
+	{"sockops", {0, BPF_PROG_TYPE_SOCK_OPS, 0}, {0, BPF_CGROUP_SOCK_OPS} },
+	{
+		"sk_skb/stream_parser",
+		{0, BPF_PROG_TYPE_SK_SKB, 0},
+		{0, BPF_SK_SKB_STREAM_PARSER},
+	},
+	{
+		"sk_skb/stream_verdict",
+		{0, BPF_PROG_TYPE_SK_SKB, 0},
+		{0, BPF_SK_SKB_STREAM_VERDICT},
+	},
+	{"sk_skb", {0, BPF_PROG_TYPE_SK_SKB, 0}, {-EINVAL, 0} },
+	{"sk_msg", {0, BPF_PROG_TYPE_SK_MSG, 0}, {0, BPF_SK_MSG_VERDICT} },
+	{"lirc_mode2", {0, BPF_PROG_TYPE_LIRC_MODE2, 0}, {0, BPF_LIRC_MODE2} },
+	{
+		"flow_dissector",
+		{0, BPF_PROG_TYPE_FLOW_DISSECTOR, 0},
+		{0, BPF_FLOW_DISSECTOR},
+	},
+	{
+		"cgroup/bind4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND},
+		{0, BPF_CGROUP_INET4_BIND},
+	},
+	{
+		"cgroup/bind6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND},
+		{0, BPF_CGROUP_INET6_BIND},
+	},
+	{
+		"cgroup/connect4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT},
+		{0, BPF_CGROUP_INET4_CONNECT},
+	},
+	{
+		"cgroup/connect6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT},
+		{0, BPF_CGROUP_INET6_CONNECT},
+	},
+	{
+		"cgroup/sendmsg4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG},
+		{0, BPF_CGROUP_UDP4_SENDMSG},
+	},
+	{
+		"cgroup/sendmsg6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG},
+		{0, BPF_CGROUP_UDP6_SENDMSG},
+	},
+};
+
+static int test_prog_type_by_name(const struct sec_name_test *test)
+{
+	enum bpf_attach_type expected_attach_type;
+	enum bpf_prog_type prog_type;
+	int rc;
+
+	rc = libbpf_prog_type_by_name(test->sec_name, &prog_type,
+				      &expected_attach_type);
+
+	if (rc != test->expected_load.rc) {
+		warnx("prog: unexpected rc=%d for %s", rc, test->sec_name);
+		return -1;
+	}
+
+	if (rc)
+		return 0;
+
+	if (prog_type != test->expected_load.prog_type) {
+		warnx("prog: unexpected prog_type=%d for %s", prog_type,
+		      test->sec_name);
+		return -1;
+	}
+
+	if (expected_attach_type != test->expected_load.expected_attach_type) {
+		warnx("prog: unexpected expected_attach_type=%d for %s",
+		      expected_attach_type, test->sec_name);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int test_attach_type_by_name(const struct sec_name_test *test)
+{
+	enum bpf_attach_type attach_type;
+	int rc;
+
+	rc = libbpf_attach_type_by_name(test->sec_name, &attach_type);
+
+	if (rc != test->expected_attach.rc) {
+		warnx("attach: unexpected rc=%d for %s", rc, test->sec_name);
+		return -1;
+	}
+
+	if (rc)
+		return 0;
+
+	if (attach_type != test->expected_attach.attach_type) {
+		warnx("attach: unexpected attach_type=%d for %s", attach_type,
+		      test->sec_name);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int run_test_case(const struct sec_name_test *test)
+{
+	if (test_prog_type_by_name(test))
+		return -1;
+	if (test_attach_type_by_name(test))
+		return -1;
+	return 0;
+}
+
+static int run_tests(void)
+{
+	int passes = 0;
+	int fails = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(tests); ++i) {
+		if (run_test_case(&tests[i]))
+			++fails;
+		else
+			++passes;
+	}
+	printf("Summary: %d PASSED, %d FAILED\n", passes, fails);
+	return fails ? -1 : 0;
+}
+
+int main(int argc, char **argv)
+{
+	return run_tests();
+}
-- 
cgit v1.2.3


From a6f37cee6e4f6fa9d61962efbcb06a032efed1ba Mon Sep 17 00:00:00 2001
From: Corentin Labbe <clabbe@baylibre.com>
Date: Wed, 19 Sep 2018 10:10:55 +0000
Subject: crypto: tools - Add cryptostat userspace

This patch adds an userspace tool for displaying kernel crypto API
statistics.

Signed-off-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 tools/crypto/getstat.c | 294 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 294 insertions(+)
 create mode 100644 tools/crypto/getstat.c

(limited to 'tools')

diff --git a/tools/crypto/getstat.c b/tools/crypto/getstat.c
new file mode 100644
index 000000000000..24115173a483
--- /dev/null
+++ b/tools/crypto/getstat.c
@@ -0,0 +1,294 @@
+/* Heavily copied from libkcapi 2015 - 2017, Stephan Mueller <smueller@chronox.de> */
+#include <errno.h>
+#include <linux/cryptouser.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+
+#define CR_RTA(x)  ((struct rtattr *)(((char *)(x)) + NLMSG_ALIGN(sizeof(struct crypto_user_alg))))
+
+static int get_stat(const char *drivername)
+{
+	struct {
+		struct nlmsghdr n;
+		struct crypto_user_alg cru;
+	} req;
+	struct sockaddr_nl nl;
+	int sd = 0, ret;
+	socklen_t addr_len;
+	struct iovec iov;
+	struct msghdr msg;
+	char buf[4096];
+	struct nlmsghdr *res_n = (struct nlmsghdr *)buf;
+	struct crypto_user_alg *cru_res = NULL;
+	int res_len = 0;
+	struct rtattr *tb[CRYPTOCFGA_MAX + 1];
+	struct rtattr *rta;
+	struct nlmsgerr *errmsg;
+
+	memset(&req, 0, sizeof(req));
+	memset(&buf, 0, sizeof(buf));
+	memset(&msg, 0, sizeof(msg));
+
+	req.n.nlmsg_len = NLMSG_LENGTH(sizeof(req.cru));
+	req.n.nlmsg_flags = NLM_F_REQUEST;
+	req.n.nlmsg_type = CRYPTO_MSG_GETSTAT;
+	req.n.nlmsg_seq = time(NULL);
+
+	strncpy(req.cru.cru_driver_name, drivername, strlen(drivername));
+
+	sd =  socket(AF_NETLINK, SOCK_RAW, NETLINK_CRYPTO);
+	if (sd < 0) {
+		fprintf(stderr, "Netlink error: cannot open netlink socket");
+		return -errno;
+	}
+	memset(&nl, 0, sizeof(nl));
+	nl.nl_family = AF_NETLINK;
+	if (bind(sd, (struct sockaddr *)&nl, sizeof(nl)) < 0) {
+		ret = -errno;
+		fprintf(stderr, "Netlink error: cannot bind netlink socket");
+		goto out;
+	}
+
+	/* sanity check that netlink socket was successfully opened */
+	addr_len = sizeof(nl);
+	if (getsockname(sd, (struct sockaddr *)&nl, &addr_len) < 0) {
+		ret = -errno;
+		printf("Netlink error: cannot getsockname");
+		goto out;
+	}
+	if (addr_len != sizeof(nl)) {
+		ret = -errno;
+		printf("Netlink error: wrong address length %d", addr_len);
+		goto out;
+	}
+	if (nl.nl_family != AF_NETLINK) {
+		ret = -errno;
+		printf("Netlink error: wrong address family %d",
+				nl.nl_family);
+		goto out;
+	}
+
+	memset(&nl, 0, sizeof(nl));
+	nl.nl_family = AF_NETLINK;
+	iov.iov_base = (void *)&req.n;
+	iov.iov_len = req.n.nlmsg_len;
+	msg.msg_name = &nl;
+	msg.msg_namelen = sizeof(nl);
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+	if (sendmsg(sd, &msg, 0) < 0) {
+		ret = -errno;
+		printf("Netlink error: sendmsg failed");
+		goto out;
+	}
+	memset(buf, 0, sizeof(buf));
+	iov.iov_base = buf;
+	while (1) {
+		iov.iov_len = sizeof(buf);
+		ret = recvmsg(sd, &msg, 0);
+		if (ret < 0) {
+			if (errno == EINTR || errno == EAGAIN)
+				continue;
+			ret = -errno;
+			printf("Netlink error: netlink receive error");
+			goto out;
+		}
+		if (ret == 0) {
+			ret = -errno;
+			printf("Netlink error: no data");
+			goto out;
+		}
+		if (ret > sizeof(buf)) {
+			ret = -errno;
+			printf("Netlink error: received too much data");
+			goto out;
+		}
+		break;
+	}
+
+	ret = -EFAULT;
+	res_len = res_n->nlmsg_len;
+	if (res_n->nlmsg_type == NLMSG_ERROR) {
+		errmsg = NLMSG_DATA(res_n);
+		fprintf(stderr, "Fail with %d\n", errmsg->error);
+		ret = errmsg->error;
+		goto out;
+	}
+
+	if (res_n->nlmsg_type == CRYPTO_MSG_GETSTAT) {
+		cru_res = NLMSG_DATA(res_n);
+		res_len -= NLMSG_SPACE(sizeof(*cru_res));
+	}
+	if (res_len < 0) {
+		printf("Netlink error: nlmsg len %d\n", res_len);
+		goto out;
+	}
+
+	if (!cru_res) {
+		ret = -EFAULT;
+		printf("Netlink error: no cru_res\n");
+		goto out;
+	}
+
+	rta = CR_RTA(cru_res);
+	memset(tb, 0, sizeof(struct rtattr *) * (CRYPTOCFGA_MAX + 1));
+	while (RTA_OK(rta, res_len)) {
+		if ((rta->rta_type <= CRYPTOCFGA_MAX) && (!tb[rta->rta_type]))
+			tb[rta->rta_type] = rta;
+		rta = RTA_NEXT(rta, res_len);
+	}
+	if (res_len) {
+		printf("Netlink error: unprocessed data %d",
+				res_len);
+		goto out;
+	}
+
+	if (tb[CRYPTOCFGA_STAT_HASH]) {
+		struct rtattr *rta = tb[CRYPTOCFGA_STAT_HASH];
+		struct crypto_stat *rhash =
+			(struct crypto_stat *)RTA_DATA(rta);
+		printf("%s\tHash\n\tHash: %u bytes: %llu\n\tErrors: %u\n",
+			drivername,
+			rhash->stat_hash_cnt, rhash->stat_hash_tlen,
+			rhash->stat_hash_err_cnt);
+	} else if (tb[CRYPTOCFGA_STAT_COMPRESS]) {
+		struct rtattr *rta = tb[CRYPTOCFGA_STAT_COMPRESS];
+		struct crypto_stat *rblk =
+			(struct crypto_stat *)RTA_DATA(rta);
+		printf("%s\tCompress\n\tCompress: %u bytes: %llu\n\tDecompress: %u bytes: %llu\n\tErrors: %u\n",
+			drivername,
+			rblk->stat_compress_cnt, rblk->stat_compress_tlen,
+			rblk->stat_decompress_cnt, rblk->stat_decompress_tlen,
+			rblk->stat_compress_err_cnt);
+	} else if (tb[CRYPTOCFGA_STAT_ACOMP]) {
+		struct rtattr *rta = tb[CRYPTOCFGA_STAT_ACOMP];
+		struct crypto_stat *rcomp =
+			(struct crypto_stat *)RTA_DATA(rta);
+		printf("%s\tACompress\n\tCompress: %u bytes: %llu\n\tDecompress: %u bytes: %llu\n\tErrors: %u\n",
+			drivername,
+			rcomp->stat_compress_cnt, rcomp->stat_compress_tlen,
+			rcomp->stat_decompress_cnt, rcomp->stat_decompress_tlen,
+			rcomp->stat_compress_err_cnt);
+	} else if (tb[CRYPTOCFGA_STAT_AEAD]) {
+		struct rtattr *rta = tb[CRYPTOCFGA_STAT_AEAD];
+		struct crypto_stat *raead =
+			(struct crypto_stat *)RTA_DATA(rta);
+		printf("%s\tAEAD\n\tEncrypt: %u bytes: %llu\n\tDecrypt: %u bytes: %llu\n\tErrors: %u\n",
+			drivername,
+			raead->stat_encrypt_cnt, raead->stat_encrypt_tlen,
+			raead->stat_decrypt_cnt, raead->stat_decrypt_tlen,
+			raead->stat_aead_err_cnt);
+	} else if (tb[CRYPTOCFGA_STAT_BLKCIPHER]) {
+		struct rtattr *rta = tb[CRYPTOCFGA_STAT_BLKCIPHER];
+		struct crypto_stat *rblk =
+			(struct crypto_stat *)RTA_DATA(rta);
+		printf("%s\tCipher\n\tEncrypt: %u bytes: %llu\n\tDecrypt: %u bytes: %llu\n\tErrors: %u\n",
+			drivername,
+			rblk->stat_encrypt_cnt, rblk->stat_encrypt_tlen,
+			rblk->stat_decrypt_cnt, rblk->stat_decrypt_tlen,
+			rblk->stat_cipher_err_cnt);
+	} else if (tb[CRYPTOCFGA_STAT_AKCIPHER]) {
+		struct rtattr *rta = tb[CRYPTOCFGA_STAT_AKCIPHER];
+		struct crypto_stat *rblk =
+			(struct crypto_stat *)RTA_DATA(rta);
+		printf("%s\tAkcipher\n\tEncrypt: %u bytes: %llu\n\tDecrypt: %u bytes: %llu\n\tSign: %u\n\tVerify: %u\n\tErrors: %u\n",
+			drivername,
+			rblk->stat_encrypt_cnt, rblk->stat_encrypt_tlen,
+			rblk->stat_decrypt_cnt, rblk->stat_decrypt_tlen,
+			rblk->stat_sign_cnt, rblk->stat_verify_cnt,
+			rblk->stat_akcipher_err_cnt);
+	} else if (tb[CRYPTOCFGA_STAT_CIPHER]) {
+		struct rtattr *rta = tb[CRYPTOCFGA_STAT_CIPHER];
+		struct crypto_stat *rblk =
+			(struct crypto_stat *)RTA_DATA(rta);
+		printf("%s\tcipher\n\tEncrypt: %u bytes: %llu\n\tDecrypt: %u bytes: %llu\n\tErrors: %u\n",
+			drivername,
+			rblk->stat_encrypt_cnt, rblk->stat_encrypt_tlen,
+			rblk->stat_decrypt_cnt, rblk->stat_decrypt_tlen,
+			rblk->stat_cipher_err_cnt);
+	} else if (tb[CRYPTOCFGA_STAT_RNG]) {
+		struct rtattr *rta = tb[CRYPTOCFGA_STAT_RNG];
+		struct crypto_stat *rrng =
+			(struct crypto_stat *)RTA_DATA(rta);
+		printf("%s\tRNG\n\tSeed: %u\n\tGenerate: %u bytes: %llu\n\tErrors: %u\n",
+			drivername,
+			rrng->stat_seed_cnt,
+			rrng->stat_generate_cnt, rrng->stat_generate_tlen,
+			rrng->stat_rng_err_cnt);
+	} else if (tb[CRYPTOCFGA_STAT_KPP]) {
+		struct rtattr *rta = tb[CRYPTOCFGA_STAT_KPP];
+		struct crypto_stat *rkpp =
+			(struct crypto_stat *)RTA_DATA(rta);
+		printf("%s\tKPP\n\tSetsecret: %u\n\tGenerate public key: %u\n\tCompute_shared_secret: %u\n\tErrors: %u\n",
+			drivername,
+			rkpp->stat_setsecret_cnt,
+			rkpp->stat_generate_public_key_cnt,
+			rkpp->stat_compute_shared_secret_cnt,
+			rkpp->stat_kpp_err_cnt);
+	} else {
+		fprintf(stderr, "%s is of an unknown algorithm\n", drivername);
+	}
+	ret = 0;
+out:
+	close(sd);
+	return ret;
+}
+
+int main(int argc, const char *argv[])
+{
+	char buf[4096];
+	FILE *procfd;
+	int i, lastspace;
+	int ret;
+
+	procfd = fopen("/proc/crypto", "r");
+	if (!procfd) {
+		ret = errno;
+		fprintf(stderr, "Cannot open /proc/crypto %s\n", strerror(errno));
+		return ret;
+	}
+	if (argc > 1) {
+		if (!strcmp(argv[1], "-h") || !strcmp(argv[1], "--help")) {
+			printf("Usage: %s [-h|--help] display this help\n", argv[0]);
+			printf("Usage: %s display all crypto statistics\n", argv[0]);
+			printf("Usage: %s drivername1 drivername2 ... = display crypto statistics about drivername1 ...\n", argv[0]);
+			return 0;
+		}
+		for (i = 1; i < argc; i++) {
+			ret = get_stat(argv[i]);
+			if (ret) {
+				fprintf(stderr, "Failed with %s\n", strerror(-ret));
+				return ret;
+			}
+		}
+		return 0;
+	}
+
+	while (fgets(buf, sizeof(buf), procfd)) {
+		if (!strncmp(buf, "driver", 6)) {
+			lastspace = 0;
+			i = 0;
+			while (i < strlen(buf)) {
+				i++;
+				if (buf[i] == ' ')
+					lastspace = i;
+			}
+			buf[strlen(buf) - 1] = '\0';
+			ret = get_stat(buf + lastspace + 1);
+			if (ret) {
+				fprintf(stderr, "Failed with %s\n", strerror(-ret));
+				goto out;
+			}
+		}
+	}
+out:
+	fclose(procfd);
+	return ret;
+}
-- 
cgit v1.2.3


From a804e5e21875418af03e0a413a633f4643739c90 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Thu, 27 Sep 2018 16:35:13 +0300
Subject: selftests: forwarding: test for bridge sticky flag

This test adds an fdb entry with the sticky flag and sends traffic from
a different port with the same mac as a source address expecting the entry
to not change ports if the flag is operating correctly.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/bridge_sticky_fdb.sh  | 69 ++++++++++++++++++++++
 1 file changed, 69 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh b/tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh
new file mode 100755
index 000000000000..1f8ef0eff862
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/bridge_sticky_fdb.sh
@@ -0,0 +1,69 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="sticky"
+NUM_NETIFS=4
+TEST_MAC=de:ad:be:ef:13:37
+source lib.sh
+
+switch_create()
+{
+	ip link add dev br0 type bridge
+
+	ip link set dev $swp1 master br0
+	ip link set dev $swp2 master br0
+
+	ip link set dev br0 up
+	ip link set dev $h1 up
+	ip link set dev $swp1 up
+	ip link set dev $h2 up
+	ip link set dev $swp2 up
+}
+
+switch_destroy()
+{
+	ip link set dev $swp2 down
+	ip link set dev $h2 down
+	ip link set dev $swp1 down
+	ip link set dev $h1 down
+
+	ip link del dev br0
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+	h2=${NETIFS[p3]}
+	swp2=${NETIFS[p4]}
+
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+	switch_destroy
+}
+
+sticky()
+{
+	bridge fdb add $TEST_MAC dev $swp1 master static sticky
+	check_err $? "Could not add fdb entry"
+	bridge fdb del $TEST_MAC dev $swp1 vlan 1 master static sticky
+	$MZ $h2 -c 1 -a $TEST_MAC -t arp "request" -q
+	bridge -j fdb show br br0 brport $swp1\
+		| jq -e ".[] | select(.mac == \"$TEST_MAC\")" &> /dev/null
+	check_err $? "Did not find FDB record when should"
+
+	log_test "Sticky fdb entry"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 66ee620f06f99d72475db6eb638559ba608c7dee Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Mon, 25 Jun 2018 06:56:50 -0400
Subject: idr: Permit any valid kernel pointer to be stored

An upcoming change to the encoding of internal entries will set the bottom
two bits to 0b10.  Unfortunately, m68k only aligns some data structures
to 2 bytes, so the IDR will interpret them as internal entries and things
will go badly wrong.

Change the radix tree so that it stops either when the node indicates
that it's the bottom of the tree (shift == 0) or when the entry is not an
internal entry.  This means we cannot insert an arbitrary kernel pointer
as a multiorder entry, but the IDR does not permit multiorder entries.

Annoyingly, this means the IDR can no longer take advantage of the radix
tree's ability to store a single entry at offset 0 without allocating
memory.  A pointer which is 2-byte aligned cannot be stored directly in
the root as it would be indistinguishable from a node, so we must allocate
a node in order to store a 2-byte pointer at index 0.  The idr_replace()
function does not take a GFP flags argument, so cannot allocate memory.
If a user inserts a 4-byte aligned pointer at index 0 and then replaces
it with a 2-byte aligned pointer, we must be able to store it.

Arbitrary pointer values are still not permitted; pointers of the
form 2 + (i * 4) for values of i between 0 and 1023 are reserved for
the implementation.  These are not valid kernel pointers as they would
point into the zero page.

This change does cause a runtime memory consumption regression for
the IDA.  I will recover that later.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Tested-by: Guenter Roeck <linux@roeck-us.net>
---
 lib/idr.c                           |  4 ---
 lib/radix-tree.c                    | 21 +++++++++----
 tools/testing/radix-tree/idr-test.c | 63 +++++++++++++++++++++++++++++++++++++
 3 files changed, 78 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/lib/idr.c b/lib/idr.c
index fab2fd5bc326..729e381e23b4 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -39,8 +39,6 @@ int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid,
 	unsigned int base = idr->idr_base;
 	unsigned int id = *nextid;
 
-	if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr)))
-		return -EINVAL;
 	if (WARN_ON_ONCE(!(idr->idr_rt.gfp_mask & ROOT_IS_IDR)))
 		idr->idr_rt.gfp_mask |= IDR_RT_MARKER;
 
@@ -295,8 +293,6 @@ void *idr_replace(struct idr *idr, void *ptr, unsigned long id)
 	void __rcu **slot = NULL;
 	void *entry;
 
-	if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr)))
-		return ERR_PTR(-EINVAL);
 	id -= idr->idr_base;
 
 	entry = __radix_tree_lookup(&idr->idr_rt, id, &node, &slot);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index bc03ecc4dfd2..a904a8ddd174 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -703,6 +703,14 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root,
 		if (!radix_tree_is_internal_node(child) && node->shift)
 			break;
 
+		/*
+		 * For an IDR, we must not shrink entry 0 into the root in
+		 * case somebody calls idr_replace() with a pointer that
+		 * appears to be an internal entry
+		 */
+		if (!node->shift && is_idr(root))
+			break;
+
 		if (radix_tree_is_internal_node(child))
 			entry_to_node(child)->parent = NULL;
 
@@ -875,8 +883,8 @@ static void radix_tree_free_nodes(struct radix_tree_node *node)
 
 	for (;;) {
 		void *entry = rcu_dereference_raw(child->slots[offset]);
-		if (radix_tree_is_internal_node(entry) &&
-					!is_sibling_entry(child, entry)) {
+		if (radix_tree_is_internal_node(entry) && child->shift &&
+				!is_sibling_entry(child, entry)) {
 			child = entry_to_node(entry);
 			offset = 0;
 			continue;
@@ -1049,6 +1057,8 @@ void *__radix_tree_lookup(const struct radix_tree_root *root,
 		parent = entry_to_node(node);
 		offset = radix_tree_descend(parent, &node, index);
 		slot = parent->slots + offset;
+		if (parent->shift == 0)
+			break;
 	}
 
 	if (nodep)
@@ -1123,9 +1133,6 @@ static inline void replace_sibling_entries(struct radix_tree_node *node,
 static void replace_slot(void __rcu **slot, void *item,
 		struct radix_tree_node *node, int count, int exceptional)
 {
-	if (WARN_ON_ONCE(radix_tree_is_internal_node(item)))
-		return;
-
 	if (node && (count || exceptional)) {
 		node->count += count;
 		node->exceptional += exceptional;
@@ -1784,7 +1791,7 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root,
 			goto restart;
 		if (child == RADIX_TREE_RETRY)
 			break;
-	} while (radix_tree_is_internal_node(child));
+	} while (node->shift && radix_tree_is_internal_node(child));
 
 	/* Update the iterator state */
 	iter->index = (index &~ node_maxindex(node)) | (offset << node->shift);
@@ -2150,6 +2157,8 @@ void __rcu **idr_get_free(struct radix_tree_root *root,
 		shift = error;
 		child = rcu_dereference_raw(root->rnode);
 	}
+	if (start == 0 && shift == 0)
+		shift = RADIX_TREE_MAP_SHIFT;
 
 	while (shift) {
 		shift -= RADIX_TREE_MAP_SHIFT;
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index 321ba92c70d2..f620c831a4b5 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -227,6 +227,66 @@ void idr_u32_test(int base)
 	idr_u32_test1(&idr, 0xffffffff);
 }
 
+static void idr_align_test(struct idr *idr)
+{
+	char name[] = "Motorola 68000";
+	int i, id;
+	void *entry;
+
+	for (i = 0; i < 9; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != i);
+		idr_for_each_entry(idr, entry, id);
+	}
+	idr_destroy(idr);
+
+	for (i = 1; i < 10; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != i - 1);
+		idr_for_each_entry(idr, entry, id);
+	}
+	idr_destroy(idr);
+
+	for (i = 2; i < 11; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != i - 2);
+		idr_for_each_entry(idr, entry, id);
+	}
+	idr_destroy(idr);
+
+	for (i = 3; i < 12; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != i - 3);
+		idr_for_each_entry(idr, entry, id);
+	}
+	idr_destroy(idr);
+
+	for (i = 0; i < 8; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != 0);
+		BUG_ON(idr_alloc(idr, &name[i + 1], 0, 0, GFP_KERNEL) != 1);
+		idr_for_each_entry(idr, entry, id);
+		idr_remove(idr, 1);
+		idr_for_each_entry(idr, entry, id);
+		idr_remove(idr, 0);
+		BUG_ON(!idr_is_empty(idr));
+	}
+
+	for (i = 0; i < 8; i++) {
+		BUG_ON(idr_alloc(idr, NULL, 0, 0, GFP_KERNEL) != 0);
+		idr_for_each_entry(idr, entry, id);
+		idr_replace(idr, &name[i], 0);
+		idr_for_each_entry(idr, entry, id);
+		BUG_ON(idr_find(idr, 0) != &name[i]);
+		idr_remove(idr, 0);
+	}
+
+	for (i = 0; i < 8; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != 0);
+		BUG_ON(idr_alloc(idr, NULL, 0, 0, GFP_KERNEL) != 1);
+		idr_remove(idr, 1);
+		idr_for_each_entry(idr, entry, id);
+		idr_replace(idr, &name[i + 1], 0);
+		idr_for_each_entry(idr, entry, id);
+		idr_remove(idr, 0);
+	}
+}
+
 void idr_checks(void)
 {
 	unsigned long i;
@@ -307,6 +367,7 @@ void idr_checks(void)
 	idr_u32_test(4);
 	idr_u32_test(1);
 	idr_u32_test(0);
+	idr_align_test(&idr);
 }
 
 #define module_init(x)
@@ -341,6 +402,7 @@ void ida_check_nomem(void)
  */
 void ida_check_conv_user(void)
 {
+#if 0
 	DEFINE_IDA(ida);
 	unsigned long i;
 
@@ -358,6 +420,7 @@ void ida_check_conv_user(void)
 		IDA_BUG_ON(&ida, id != i);
 	}
 	ida_destroy(&ida);
+#endif
 }
 
 void ida_check_random(void)
-- 
cgit v1.2.3


From 3159f943aafdbacb2f94c38fdaadabf2bbde2a14 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Fri, 3 Nov 2017 13:30:42 -0400
Subject: xarray: Replace exceptional entries

Introduce xarray value entries and tagged pointers to replace radix
tree exceptional entries.  This is a slight change in encoding to allow
the use of an extra bit (we can now store BITS_PER_LONG - 1 bits in a
value entry).  It is also a change in emphasis; exceptional entries are
intimidating and different.  As the comment explains, you can choose
to store values or pointers in the xarray and they are both first-class
citizens.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: Josef Bacik <jbacik@fb.com>
---
 arch/powerpc/include/asm/book3s/64/pgtable.h |   4 +-
 arch/powerpc/include/asm/nohash/64/pgtable.h |   4 +-
 drivers/gpu/drm/i915/i915_gem.c              |  17 ++--
 drivers/staging/erofs/utils.c                |  18 ++---
 fs/btrfs/compression.c                       |   2 +-
 fs/dax.c                                     | 112 +++++++++++++--------------
 fs/proc/task_mmu.c                           |   2 +-
 include/linux/radix-tree.h                   |  36 ++-------
 include/linux/swapops.h                      |  19 ++---
 include/linux/xarray.h                       | 102 ++++++++++++++++++++++++
 lib/idr.c                                    |  60 ++++++--------
 lib/radix-tree.c                             |  21 +++--
 mm/filemap.c                                 |  10 +--
 mm/khugepaged.c                              |   2 +-
 mm/madvise.c                                 |   2 +-
 mm/memcontrol.c                              |   2 +-
 mm/mincore.c                                 |   2 +-
 mm/readahead.c                               |   2 +-
 mm/shmem.c                                   |  10 +--
 mm/swap.c                                    |   2 +-
 mm/truncate.c                                |  12 +--
 mm/workingset.c                              |  13 ++--
 tools/testing/radix-tree/idr-test.c          |   6 +-
 tools/testing/radix-tree/linux/radix-tree.h  |   1 -
 tools/testing/radix-tree/multiorder.c        |  47 ++++++-----
 tools/testing/radix-tree/test.c              |   2 +-
 26 files changed, 278 insertions(+), 232 deletions(-)

(limited to 'tools')

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 2fdc865ca374..62039e557ac0 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -723,9 +723,7 @@ static inline bool pte_user(pte_t pte)
 	BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \
 	BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY);	\
 	} while (0)
-/*
- * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT;
- */
+
 #define SWP_TYPE_BITS 5
 #define __swp_type(x)		(((x).val >> _PAGE_BIT_SWAP_TYPE) \
 				& ((1UL << SWP_TYPE_BITS) - 1))
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index 7cd6809f4d33..05765c2d2c1f 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -313,9 +313,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
 #define MAX_SWAPFILES_CHECK() do { \
 	BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \
 	} while (0)
-/*
- * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT;
- */
+
 #define SWP_TYPE_BITS 5
 #define __swp_type(x)		(((x).val >> _PAGE_BIT_SWAP_TYPE) \
 				& ((1UL << SWP_TYPE_BITS) - 1))
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index fcc73a6ab503..316730b45f84 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5996,7 +5996,8 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
 	count = __sg_page_count(sg);
 
 	while (idx + count <= n) {
-		unsigned long exception, i;
+		void *entry;
+		unsigned long i;
 		int ret;
 
 		/* If we cannot allocate and insert this entry, or the
@@ -6011,12 +6012,9 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
 		if (ret && ret != -EEXIST)
 			goto scan;
 
-		exception =
-			RADIX_TREE_EXCEPTIONAL_ENTRY |
-			idx << RADIX_TREE_EXCEPTIONAL_SHIFT;
+		entry = xa_mk_value(idx);
 		for (i = 1; i < count; i++) {
-			ret = radix_tree_insert(&iter->radix, idx + i,
-						(void *)exception);
+			ret = radix_tree_insert(&iter->radix, idx + i, entry);
 			if (ret && ret != -EEXIST)
 				goto scan;
 		}
@@ -6054,15 +6052,14 @@ lookup:
 	GEM_BUG_ON(!sg);
 
 	/* If this index is in the middle of multi-page sg entry,
-	 * the radixtree will contain an exceptional entry that points
+	 * the radix tree will contain a value entry that points
 	 * to the start of that range. We will return the pointer to
 	 * the base page and the offset of this page within the
 	 * sg entry's range.
 	 */
 	*offset = 0;
-	if (unlikely(radix_tree_exception(sg))) {
-		unsigned long base =
-			(unsigned long)sg >> RADIX_TREE_EXCEPTIONAL_SHIFT;
+	if (unlikely(xa_is_value(sg))) {
+		unsigned long base = xa_to_value(sg);
 
 		sg = radix_tree_lookup(&iter->radix, base);
 		GEM_BUG_ON(!sg);
diff --git a/drivers/staging/erofs/utils.c b/drivers/staging/erofs/utils.c
index 595cf90af9bb..bdee9bd09f11 100644
--- a/drivers/staging/erofs/utils.c
+++ b/drivers/staging/erofs/utils.c
@@ -35,7 +35,6 @@ static atomic_long_t erofs_global_shrink_cnt;
 
 #ifdef CONFIG_EROFS_FS_ZIP
 
-/* radix_tree and the future XArray both don't use tagptr_t yet */
 struct erofs_workgroup *erofs_find_workgroup(
 	struct super_block *sb, pgoff_t index, bool *tag)
 {
@@ -47,9 +46,8 @@ repeat:
 	rcu_read_lock();
 	grp = radix_tree_lookup(&sbi->workstn_tree, index);
 	if (grp != NULL) {
-		*tag = radix_tree_exceptional_entry(grp);
-		grp = (void *)((unsigned long)grp &
-			~RADIX_TREE_EXCEPTIONAL_ENTRY);
+		*tag = xa_pointer_tag(grp);
+		grp = xa_untag_pointer(grp);
 
 		if (erofs_workgroup_get(grp, &oldcount)) {
 			/* prefer to relax rcu read side */
@@ -83,9 +81,7 @@ int erofs_register_workgroup(struct super_block *sb,
 	sbi = EROFS_SB(sb);
 	erofs_workstn_lock(sbi);
 
-	if (tag)
-		grp = (void *)((unsigned long)grp |
-			1UL << RADIX_TREE_EXCEPTIONAL_SHIFT);
+	grp = xa_tag_pointer(grp, tag);
 
 	err = radix_tree_insert(&sbi->workstn_tree,
 		grp->index, grp);
@@ -131,9 +127,7 @@ repeat:
 
 	for (i = 0; i < found; ++i) {
 		int cnt;
-		struct erofs_workgroup *grp = (void *)
-			((unsigned long)batch[i] &
-				~RADIX_TREE_EXCEPTIONAL_ENTRY);
+		struct erofs_workgroup *grp = xa_untag_pointer(batch[i]);
 
 		first_index = grp->index + 1;
 
@@ -150,8 +144,8 @@ repeat:
 #endif
 			continue;
 
-		if (radix_tree_delete(&sbi->workstn_tree,
-			grp->index) != grp) {
+		if (xa_untag_pointer(radix_tree_delete(&sbi->workstn_tree,
+			grp->index)) != grp) {
 #ifdef EROFS_FS_HAS_MANAGED_CACHE
 skip:
 			erofs_workgroup_unfreeze(grp, 1);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 9bfa66592aa7..fd25e125303c 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -440,7 +440,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		rcu_read_lock();
 		page = radix_tree_lookup(&mapping->i_pages, pg_index);
 		rcu_read_unlock();
-		if (page && !radix_tree_exceptional_entry(page)) {
+		if (page && !xa_is_value(page)) {
 			misses++;
 			if (misses > 4)
 				break;
diff --git a/fs/dax.c b/fs/dax.c
index b68ce484e1be..ebcec36335eb 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -59,56 +59,57 @@ static int __init init_dax_wait_table(void)
 fs_initcall(init_dax_wait_table);
 
 /*
- * We use lowest available bit in exceptional entry for locking, one bit for
- * the entry size (PMD) and two more to tell us if the entry is a zero page or
- * an empty entry that is just used for locking.  In total four special bits.
+ * DAX pagecache entries use XArray value entries so they can't be mistaken
+ * for pages.  We use one bit for locking, one bit for the entry size (PMD)
+ * and two more to tell us if the entry is a zero page or an empty entry that
+ * is just used for locking.  In total four special bits.
  *
  * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the ZERO_PAGE
  * and EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
  * block allocation.
  */
-#define RADIX_DAX_SHIFT		(RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
-#define RADIX_DAX_ENTRY_LOCK	(1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
-#define RADIX_DAX_PMD		(1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
-#define RADIX_DAX_ZERO_PAGE	(1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
-#define RADIX_DAX_EMPTY		(1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
+#define DAX_SHIFT	(4)
+#define DAX_LOCKED	(1UL << 0)
+#define DAX_PMD		(1UL << 1)
+#define DAX_ZERO_PAGE	(1UL << 2)
+#define DAX_EMPTY	(1UL << 3)
 
 static unsigned long dax_radix_pfn(void *entry)
 {
-	return (unsigned long)entry >> RADIX_DAX_SHIFT;
+	return xa_to_value(entry) >> DAX_SHIFT;
 }
 
 static void *dax_radix_locked_entry(unsigned long pfn, unsigned long flags)
 {
-	return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
-			(pfn << RADIX_DAX_SHIFT) | RADIX_DAX_ENTRY_LOCK);
+	return xa_mk_value(flags | ((unsigned long)pfn << DAX_SHIFT) |
+			DAX_LOCKED);
 }
 
 static unsigned int dax_radix_order(void *entry)
 {
-	if ((unsigned long)entry & RADIX_DAX_PMD)
+	if (xa_to_value(entry) & DAX_PMD)
 		return PMD_SHIFT - PAGE_SHIFT;
 	return 0;
 }
 
 static int dax_is_pmd_entry(void *entry)
 {
-	return (unsigned long)entry & RADIX_DAX_PMD;
+	return xa_to_value(entry) & DAX_PMD;
 }
 
 static int dax_is_pte_entry(void *entry)
 {
-	return !((unsigned long)entry & RADIX_DAX_PMD);
+	return !(xa_to_value(entry) & DAX_PMD);
 }
 
 static int dax_is_zero_entry(void *entry)
 {
-	return (unsigned long)entry & RADIX_DAX_ZERO_PAGE;
+	return xa_to_value(entry) & DAX_ZERO_PAGE;
 }
 
 static int dax_is_empty_entry(void *entry)
 {
-	return (unsigned long)entry & RADIX_DAX_EMPTY;
+	return xa_to_value(entry) & DAX_EMPTY;
 }
 
 /*
@@ -186,9 +187,9 @@ static void dax_wake_mapping_entry_waiter(struct address_space *mapping,
  */
 static inline int slot_locked(struct address_space *mapping, void **slot)
 {
-	unsigned long entry = (unsigned long)
-		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
-	return entry & RADIX_DAX_ENTRY_LOCK;
+	unsigned long entry = xa_to_value(
+		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock));
+	return entry & DAX_LOCKED;
 }
 
 /*
@@ -196,12 +197,11 @@ static inline int slot_locked(struct address_space *mapping, void **slot)
  */
 static inline void *lock_slot(struct address_space *mapping, void **slot)
 {
-	unsigned long entry = (unsigned long)
-		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
-
-	entry |= RADIX_DAX_ENTRY_LOCK;
-	radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry);
-	return (void *)entry;
+	unsigned long v = xa_to_value(
+		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock));
+	void *entry = xa_mk_value(v | DAX_LOCKED);
+	radix_tree_replace_slot(&mapping->i_pages, slot, entry);
+	return entry;
 }
 
 /*
@@ -209,17 +209,16 @@ static inline void *lock_slot(struct address_space *mapping, void **slot)
  */
 static inline void *unlock_slot(struct address_space *mapping, void **slot)
 {
-	unsigned long entry = (unsigned long)
-		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
-
-	entry &= ~(unsigned long)RADIX_DAX_ENTRY_LOCK;
-	radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry);
-	return (void *)entry;
+	unsigned long v = xa_to_value(
+		radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock));
+	void *entry = xa_mk_value(v & ~DAX_LOCKED);
+	radix_tree_replace_slot(&mapping->i_pages, slot, entry);
+	return entry;
 }
 
 /*
  * Lookup entry in radix tree, wait for it to become unlocked if it is
- * exceptional entry and return it. The caller must call
+ * a DAX entry and return it. The caller must call
  * put_unlocked_mapping_entry() when he decided not to lock the entry or
  * put_locked_mapping_entry() when he locked the entry and now wants to
  * unlock it.
@@ -242,7 +241,7 @@ static void *__get_unlocked_mapping_entry(struct address_space *mapping,
 		entry = __radix_tree_lookup(&mapping->i_pages, index, NULL,
 					  &slot);
 		if (!entry ||
-		    WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)) ||
+		    WARN_ON_ONCE(!xa_is_value(entry)) ||
 		    !slot_locked(mapping, slot)) {
 			if (slotp)
 				*slotp = slot;
@@ -283,7 +282,7 @@ static void unlock_mapping_entry(struct address_space *mapping, pgoff_t index)
 
 	xa_lock_irq(&mapping->i_pages);
 	entry = __radix_tree_lookup(&mapping->i_pages, index, NULL, &slot);
-	if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry) ||
+	if (WARN_ON_ONCE(!entry || !xa_is_value(entry) ||
 			 !slot_locked(mapping, slot))) {
 		xa_unlock_irq(&mapping->i_pages);
 		return;
@@ -472,12 +471,11 @@ void dax_unlock_mapping_entry(struct page *page)
 }
 
 /*
- * Find radix tree entry at given index. If it points to an exceptional entry,
- * return it with the radix tree entry locked. If the radix tree doesn't
- * contain given index, create an empty exceptional entry for the index and
- * return with it locked.
+ * Find radix tree entry at given index. If it is a DAX entry, return it
+ * with the radix tree entry locked. If the radix tree doesn't contain the
+ * given index, create an empty entry for the index and return with it locked.
  *
- * When requesting an entry with size RADIX_DAX_PMD, grab_mapping_entry() will
+ * When requesting an entry with size DAX_PMD, grab_mapping_entry() will
  * either return that locked entry or will return an error.  This error will
  * happen if there are any 4k entries within the 2MiB range that we are
  * requesting.
@@ -507,13 +505,13 @@ restart:
 	xa_lock_irq(&mapping->i_pages);
 	entry = get_unlocked_mapping_entry(mapping, index, &slot);
 
-	if (WARN_ON_ONCE(entry && !radix_tree_exceptional_entry(entry))) {
+	if (WARN_ON_ONCE(entry && !xa_is_value(entry))) {
 		entry = ERR_PTR(-EIO);
 		goto out_unlock;
 	}
 
 	if (entry) {
-		if (size_flag & RADIX_DAX_PMD) {
+		if (size_flag & DAX_PMD) {
 			if (dax_is_pte_entry(entry)) {
 				put_unlocked_mapping_entry(mapping, index,
 						entry);
@@ -584,7 +582,7 @@ restart:
 					true);
 		}
 
-		entry = dax_radix_locked_entry(0, size_flag | RADIX_DAX_EMPTY);
+		entry = dax_radix_locked_entry(0, size_flag | DAX_EMPTY);
 
 		err = __radix_tree_insert(&mapping->i_pages, index,
 				dax_radix_order(entry), entry);
@@ -673,8 +671,7 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 			if (index >= end)
 				break;
 
-			if (WARN_ON_ONCE(
-			     !radix_tree_exceptional_entry(pvec_ent)))
+			if (WARN_ON_ONCE(!xa_is_value(pvec_ent)))
 				continue;
 
 			xa_lock_irq(&mapping->i_pages);
@@ -713,7 +710,7 @@ static int __dax_invalidate_mapping_entry(struct address_space *mapping,
 
 	xa_lock_irq(pages);
 	entry = get_unlocked_mapping_entry(mapping, index, NULL);
-	if (!entry || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)))
+	if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
 		goto out;
 	if (!trunc &&
 	    (radix_tree_tag_get(pages, index, PAGECACHE_TAG_DIRTY) ||
@@ -729,8 +726,8 @@ out:
 	return ret;
 }
 /*
- * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree
- * entry to get unlocked before deleting it.
+ * Delete DAX entry at @index from @mapping.  Wait for it
+ * to be unlocked before deleting it.
  */
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 {
@@ -740,7 +737,7 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 	 * This gets called from truncate / punch_hole path. As such, the caller
 	 * must hold locks protecting against concurrent modifications of the
 	 * radix tree (usually fs-private i_mmap_sem for writing). Since the
-	 * caller has seen exceptional entry for this index, we better find it
+	 * caller has seen a DAX entry for this index, we better find it
 	 * at that index as well...
 	 */
 	WARN_ON_ONCE(!ret);
@@ -748,7 +745,7 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 }
 
 /*
- * Invalidate exceptional DAX entry if it is clean.
+ * Invalidate DAX entry if it is clean.
  */
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index)
@@ -802,7 +799,7 @@ static void *dax_insert_mapping_entry(struct address_space *mapping,
 	if (dirty)
 		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 
-	if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_ZERO_PAGE)) {
+	if (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE)) {
 		/* we are replacing a zero page with block mapping */
 		if (dax_is_pmd_entry(entry))
 			unmap_mapping_pages(mapping, index & ~PG_PMD_COLOUR,
@@ -940,13 +937,13 @@ static int dax_writeback_one(struct dax_device *dax_dev,
 	 * A page got tagged dirty in DAX mapping? Something is seriously
 	 * wrong.
 	 */
-	if (WARN_ON(!radix_tree_exceptional_entry(entry)))
+	if (WARN_ON(!xa_is_value(entry)))
 		return -EIO;
 
 	xa_lock_irq(pages);
 	entry2 = get_unlocked_mapping_entry(mapping, index, &slot);
 	/* Entry got punched out / reallocated? */
-	if (!entry2 || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry2)))
+	if (!entry2 || WARN_ON_ONCE(!xa_is_value(entry2)))
 		goto put_unlocked;
 	/*
 	 * Entry got reallocated elsewhere? No need to writeback. We have to
@@ -1123,8 +1120,9 @@ static vm_fault_t dax_load_hole(struct address_space *mapping, void *entry,
 	pfn_t pfn = pfn_to_pfn_t(my_zero_pfn(vaddr));
 	vm_fault_t ret;
 
-	dax_insert_mapping_entry(mapping, vmf, entry, pfn, RADIX_DAX_ZERO_PAGE,
-			false);
+	dax_insert_mapping_entry(mapping, vmf, entry, pfn,
+			DAX_ZERO_PAGE, false);
+
 	ret = vmf_insert_mixed(vmf->vma, vaddr, pfn);
 	trace_dax_load_hole(inode, vmf, ret);
 	return ret;
@@ -1514,7 +1512,7 @@ static vm_fault_t dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
 
 	pfn = page_to_pfn_t(zero_page);
 	ret = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
-			RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE, false);
+			DAX_PMD | DAX_ZERO_PAGE, false);
 
 	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
 	if (!pmd_none(*(vmf->pmd))) {
@@ -1597,7 +1595,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	 * is already in the tree, for instance), it will return -EEXIST and
 	 * we just fall back to 4k entries.
 	 */
-	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
+	entry = grab_mapping_entry(mapping, pgoff, DAX_PMD);
 	if (IS_ERR(entry))
 		goto fallback;
 
@@ -1635,7 +1633,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 			goto finish_iomap;
 
 		entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
-						RADIX_DAX_PMD, write && !sync);
+						DAX_PMD, write && !sync);
 
 		/*
 		 * If we are doing synchronous page fault and inode needs fsync,
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 5ea1d64cb0b4..669abb617321 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -521,7 +521,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 		if (!page)
 			return;
 
-		if (radix_tree_exceptional_entry(page))
+		if (xa_is_value(page))
 			mss->swap += PAGE_SIZE;
 		else
 			put_page(page);
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 34149e8b5f73..e9e76ab4fbbf 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -28,34 +28,26 @@
 #include <linux/rcupdate.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
+#include <linux/xarray.h>
 
 /*
  * The bottom two bits of the slot determine how the remaining bits in the
  * slot are interpreted:
  *
  * 00 - data pointer
- * 01 - internal entry
- * 10 - exceptional entry
- * 11 - this bit combination is currently unused/reserved
+ * 10 - internal entry
+ * x1 - value entry
  *
  * The internal entry may be a pointer to the next level in the tree, a
  * sibling entry, or an indicator that the entry in this slot has been moved
  * to another location in the tree and the lookup should be restarted.  While
  * NULL fits the 'data pointer' pattern, it means that there is no entry in
  * the tree for this index (no matter what level of the tree it is found at).
- * This means that you cannot store NULL in the tree as a value for the index.
+ * This means that storing a NULL entry in the tree is the same as deleting
+ * the entry from the tree.
  */
 #define RADIX_TREE_ENTRY_MASK		3UL
-#define RADIX_TREE_INTERNAL_NODE	1UL
-
-/*
- * Most users of the radix tree store pointers but shmem/tmpfs stores swap
- * entries in the same tree.  They are marked as exceptional entries to
- * distinguish them from pointers to struct page.
- * EXCEPTIONAL_ENTRY tests the bit, EXCEPTIONAL_SHIFT shifts content past it.
- */
-#define RADIX_TREE_EXCEPTIONAL_ENTRY	2
-#define RADIX_TREE_EXCEPTIONAL_SHIFT	2
+#define RADIX_TREE_INTERNAL_NODE	2UL
 
 static inline bool radix_tree_is_internal_node(void *ptr)
 {
@@ -83,11 +75,10 @@ static inline bool radix_tree_is_internal_node(void *ptr)
 
 /*
  * @count is the count of every non-NULL element in the ->slots array
- * whether that is an exceptional entry, a retry entry, a user pointer,
+ * whether that is a value entry, a retry entry, a user pointer,
  * a sibling entry or a pointer to the next level of the tree.
  * @exceptional is the count of every element in ->slots which is
- * either radix_tree_exceptional_entry() or is a sibling entry for an
- * exceptional entry.
+ * either a value entry or a sibling of a value entry.
  */
 struct radix_tree_node {
 	unsigned char	shift;		/* Bits remaining in each slot */
@@ -268,17 +259,6 @@ static inline int radix_tree_deref_retry(void *arg)
 	return unlikely(radix_tree_is_internal_node(arg));
 }
 
-/**
- * radix_tree_exceptional_entry	- radix_tree_deref_slot gave exceptional entry?
- * @arg:	value returned by radix_tree_deref_slot
- * Returns:	0 if well-aligned pointer, non-0 if exceptional entry.
- */
-static inline int radix_tree_exceptional_entry(void *arg)
-{
-	/* Not unlikely because radix_tree_exception often tested first */
-	return (unsigned long)arg & RADIX_TREE_EXCEPTIONAL_ENTRY;
-}
-
 /**
  * radix_tree_exception	- radix_tree_deref_slot returned either exception?
  * @arg:	value returned by radix_tree_deref_slot
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 22af9d8a84ae..4d961668e5fc 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -18,9 +18,8 @@
  *
  * swp_entry_t's are *never* stored anywhere in their arch-dependent format.
  */
-#define SWP_TYPE_SHIFT(e)	((sizeof(e.val) * 8) - \
-			(MAX_SWAPFILES_SHIFT + RADIX_TREE_EXCEPTIONAL_SHIFT))
-#define SWP_OFFSET_MASK(e)	((1UL << SWP_TYPE_SHIFT(e)) - 1)
+#define SWP_TYPE_SHIFT	(BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT)
+#define SWP_OFFSET_MASK	((1UL << SWP_TYPE_SHIFT) - 1)
 
 /*
  * Store a type+offset into a swp_entry_t in an arch-independent format
@@ -29,8 +28,7 @@ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset)
 {
 	swp_entry_t ret;
 
-	ret.val = (type << SWP_TYPE_SHIFT(ret)) |
-			(offset & SWP_OFFSET_MASK(ret));
+	ret.val = (type << SWP_TYPE_SHIFT) | (offset & SWP_OFFSET_MASK);
 	return ret;
 }
 
@@ -40,7 +38,7 @@ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset)
  */
 static inline unsigned swp_type(swp_entry_t entry)
 {
-	return (entry.val >> SWP_TYPE_SHIFT(entry));
+	return (entry.val >> SWP_TYPE_SHIFT);
 }
 
 /*
@@ -49,7 +47,7 @@ static inline unsigned swp_type(swp_entry_t entry)
  */
 static inline pgoff_t swp_offset(swp_entry_t entry)
 {
-	return entry.val & SWP_OFFSET_MASK(entry);
+	return entry.val & SWP_OFFSET_MASK;
 }
 
 #ifdef CONFIG_MMU
@@ -90,16 +88,13 @@ static inline swp_entry_t radix_to_swp_entry(void *arg)
 {
 	swp_entry_t entry;
 
-	entry.val = (unsigned long)arg >> RADIX_TREE_EXCEPTIONAL_SHIFT;
+	entry.val = xa_to_value(arg);
 	return entry;
 }
 
 static inline void *swp_to_radix_entry(swp_entry_t entry)
 {
-	unsigned long value;
-
-	value = entry.val << RADIX_TREE_EXCEPTIONAL_SHIFT;
-	return (void *)(value | RADIX_TREE_EXCEPTIONAL_ENTRY);
+	return xa_mk_value(entry.val);
 }
 
 #if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 9e4c86853fa4..5c8acfc4ff55 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -5,9 +5,111 @@
  * eXtensible Arrays
  * Copyright (c) 2017 Microsoft Corporation
  * Author: Matthew Wilcox <willy@infradead.org>
+ *
+ * See Documentation/core-api/xarray.rst for how to use the XArray.
  */
 
+#include <linux/bug.h>
 #include <linux/spinlock.h>
+#include <linux/types.h>
+
+/*
+ * The bottom two bits of the entry determine how the XArray interprets
+ * the contents:
+ *
+ * 00: Pointer entry
+ * 10: Internal entry
+ * x1: Value entry or tagged pointer
+ *
+ * Attempting to store internal entries in the XArray is a bug.
+ */
+
+#define BITS_PER_XA_VALUE	(BITS_PER_LONG - 1)
+
+/**
+ * xa_mk_value() - Create an XArray entry from an integer.
+ * @v: Value to store in XArray.
+ *
+ * Context: Any context.
+ * Return: An entry suitable for storing in the XArray.
+ */
+static inline void *xa_mk_value(unsigned long v)
+{
+	WARN_ON((long)v < 0);
+	return (void *)((v << 1) | 1);
+}
+
+/**
+ * xa_to_value() - Get value stored in an XArray entry.
+ * @entry: XArray entry.
+ *
+ * Context: Any context.
+ * Return: The value stored in the XArray entry.
+ */
+static inline unsigned long xa_to_value(const void *entry)
+{
+	return (unsigned long)entry >> 1;
+}
+
+/**
+ * xa_is_value() - Determine if an entry is a value.
+ * @entry: XArray entry.
+ *
+ * Context: Any context.
+ * Return: True if the entry is a value, false if it is a pointer.
+ */
+static inline bool xa_is_value(const void *entry)
+{
+	return (unsigned long)entry & 1;
+}
+
+/**
+ * xa_tag_pointer() - Create an XArray entry for a tagged pointer.
+ * @p: Plain pointer.
+ * @tag: Tag value (0, 1 or 3).
+ *
+ * If the user of the XArray prefers, they can tag their pointers instead
+ * of storing value entries.  Three tags are available (0, 1 and 3).
+ * These are distinct from the xa_mark_t as they are not replicated up
+ * through the array and cannot be searched for.
+ *
+ * Context: Any context.
+ * Return: An XArray entry.
+ */
+static inline void *xa_tag_pointer(void *p, unsigned long tag)
+{
+	return (void *)((unsigned long)p | tag);
+}
+
+/**
+ * xa_untag_pointer() - Turn an XArray entry into a plain pointer.
+ * @entry: XArray entry.
+ *
+ * If you have stored a tagged pointer in the XArray, call this function
+ * to get the untagged version of the pointer.
+ *
+ * Context: Any context.
+ * Return: A pointer.
+ */
+static inline void *xa_untag_pointer(void *entry)
+{
+	return (void *)((unsigned long)entry & ~3UL);
+}
+
+/**
+ * xa_pointer_tag() - Get the tag stored in an XArray entry.
+ * @entry: XArray entry.
+ *
+ * If you have stored a tagged pointer in the XArray, call this function
+ * to get the tag of that pointer.
+ *
+ * Context: Any context.
+ * Return: A tag.
+ */
+static inline unsigned int xa_pointer_tag(void *entry)
+{
+	return (unsigned long)entry & 3UL;
+}
 
 #define xa_trylock(xa)		spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)		spin_lock(&(xa)->xa_lock)
diff --git a/lib/idr.c b/lib/idr.c
index 729e381e23b4..88419fbc5737 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -338,11 +338,8 @@ EXPORT_SYMBOL(idr_replace);
  * by the number of bits in the leaf bitmap before doing a radix tree lookup.
  *
  * As an optimisation, if there are only a few low bits set in any given
- * leaf, instead of allocating a 128-byte bitmap, we use the 'exceptional
- * entry' functionality of the radix tree to store BITS_PER_LONG - 2 bits
- * directly in the entry.  By being really tricksy, we could store
- * BITS_PER_LONG - 1 bits, but there're diminishing returns after optimising
- * for 0-3 allocated IDs.
+ * leaf, instead of allocating a 128-byte bitmap, we store the bits
+ * directly in the entry.
  *
  * We allow the radix tree 'exceptional' count to get out of date.  Nothing
  * in the IDA nor the radix tree code checks it.  If it becomes important
@@ -366,12 +363,11 @@ static int ida_get_new_above(struct ida *ida, int start)
 	struct radix_tree_iter iter;
 	struct ida_bitmap *bitmap;
 	unsigned long index;
-	unsigned bit, ebit;
+	unsigned bit;
 	int new;
 
 	index = start / IDA_BITMAP_BITS;
 	bit = start % IDA_BITMAP_BITS;
-	ebit = bit + RADIX_TREE_EXCEPTIONAL_SHIFT;
 
 	slot = radix_tree_iter_init(&iter, index);
 	for (;;) {
@@ -386,25 +382,23 @@ static int ida_get_new_above(struct ida *ida, int start)
 				return PTR_ERR(slot);
 			}
 		}
-		if (iter.index > index) {
+		if (iter.index > index)
 			bit = 0;
-			ebit = RADIX_TREE_EXCEPTIONAL_SHIFT;
-		}
 		new = iter.index * IDA_BITMAP_BITS;
 		bitmap = rcu_dereference_raw(*slot);
-		if (radix_tree_exception(bitmap)) {
-			unsigned long tmp = (unsigned long)bitmap;
-			ebit = find_next_zero_bit(&tmp, BITS_PER_LONG, ebit);
-			if (ebit < BITS_PER_LONG) {
-				tmp |= 1UL << ebit;
-				rcu_assign_pointer(*slot, (void *)tmp);
-				return new + ebit -
-					RADIX_TREE_EXCEPTIONAL_SHIFT;
+		if (xa_is_value(bitmap)) {
+			unsigned long tmp = xa_to_value(bitmap);
+			int vbit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE,
+							bit);
+			if (vbit < BITS_PER_XA_VALUE) {
+				tmp |= 1UL << vbit;
+				rcu_assign_pointer(*slot, xa_mk_value(tmp));
+				return new + vbit;
 			}
 			bitmap = this_cpu_xchg(ida_bitmap, NULL);
 			if (!bitmap)
 				return -EAGAIN;
-			bitmap->bitmap[0] = tmp >> RADIX_TREE_EXCEPTIONAL_SHIFT;
+			bitmap->bitmap[0] = tmp;
 			rcu_assign_pointer(*slot, bitmap);
 		}
 
@@ -425,17 +419,14 @@ static int ida_get_new_above(struct ida *ida, int start)
 			new += bit;
 			if (new < 0)
 				return -ENOSPC;
-			if (ebit < BITS_PER_LONG) {
-				bitmap = (void *)((1UL << ebit) |
-						RADIX_TREE_EXCEPTIONAL_ENTRY);
-				radix_tree_iter_replace(root, &iter, slot,
-						bitmap);
-				return new;
+			if (bit < BITS_PER_XA_VALUE) {
+				bitmap = xa_mk_value(1UL << bit);
+			} else {
+				bitmap = this_cpu_xchg(ida_bitmap, NULL);
+				if (!bitmap)
+					return -EAGAIN;
+				__set_bit(bit, bitmap->bitmap);
 			}
-			bitmap = this_cpu_xchg(ida_bitmap, NULL);
-			if (!bitmap)
-				return -EAGAIN;
-			__set_bit(bit, bitmap->bitmap);
 			radix_tree_iter_replace(root, &iter, slot, bitmap);
 		}
 
@@ -457,9 +448,9 @@ static void ida_remove(struct ida *ida, int id)
 		goto err;
 
 	bitmap = rcu_dereference_raw(*slot);
-	if (radix_tree_exception(bitmap)) {
+	if (xa_is_value(bitmap)) {
 		btmp = (unsigned long *)slot;
-		offset += RADIX_TREE_EXCEPTIONAL_SHIFT;
+		offset += 1; /* Intimate knowledge of the value encoding */
 		if (offset >= BITS_PER_LONG)
 			goto err;
 	} else {
@@ -470,9 +461,8 @@ static void ida_remove(struct ida *ida, int id)
 
 	__clear_bit(offset, btmp);
 	radix_tree_iter_tag_set(&ida->ida_rt, &iter, IDR_FREE);
-	if (radix_tree_exception(bitmap)) {
-		if (rcu_dereference_raw(*slot) ==
-					(void *)RADIX_TREE_EXCEPTIONAL_ENTRY)
+	if (xa_is_value(bitmap)) {
+		if (xa_to_value(rcu_dereference_raw(*slot)) == 0)
 			radix_tree_iter_delete(&ida->ida_rt, &iter, slot);
 	} else if (bitmap_empty(btmp, IDA_BITMAP_BITS)) {
 		kfree(bitmap);
@@ -503,7 +493,7 @@ void ida_destroy(struct ida *ida)
 	xa_lock_irqsave(&ida->ida_rt, flags);
 	radix_tree_for_each_slot(slot, &ida->ida_rt, &iter, 0) {
 		struct ida_bitmap *bitmap = rcu_dereference_raw(*slot);
-		if (!radix_tree_exception(bitmap))
+		if (!xa_is_value(bitmap))
 			kfree(bitmap);
 		radix_tree_iter_delete(&ida->ida_rt, &iter, slot);
 	}
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index a904a8ddd174..b6c0e7f3a894 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -340,14 +340,12 @@ static void dump_ida_node(void *entry, unsigned long index)
 		for (i = 0; i < RADIX_TREE_MAP_SIZE; i++)
 			dump_ida_node(node->slots[i],
 					index | (i << node->shift));
-	} else if (radix_tree_exceptional_entry(entry)) {
+	} else if (xa_is_value(entry)) {
 		pr_debug("ida excp: %p offset %d indices %lu-%lu data %lx\n",
 				entry, (int)(index & RADIX_TREE_MAP_MASK),
 				index * IDA_BITMAP_BITS,
-				index * IDA_BITMAP_BITS + BITS_PER_LONG -
-					RADIX_TREE_EXCEPTIONAL_SHIFT,
-				(unsigned long)entry >>
-					RADIX_TREE_EXCEPTIONAL_SHIFT);
+				index * IDA_BITMAP_BITS + BITS_PER_XA_VALUE,
+				xa_to_value(entry));
 	} else {
 		struct ida_bitmap *bitmap = entry;
 
@@ -656,7 +654,7 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp,
 		BUG_ON(shift > BITS_PER_LONG);
 		if (radix_tree_is_internal_node(entry)) {
 			entry_to_node(entry)->parent = node;
-		} else if (radix_tree_exceptional_entry(entry)) {
+		} else if (xa_is_value(entry)) {
 			/* Moving an exceptional root->rnode to a node */
 			node->exceptional = 1;
 		}
@@ -955,12 +953,12 @@ static inline int insert_entries(struct radix_tree_node *node,
 					!is_sibling_entry(node, old) &&
 					(old != RADIX_TREE_RETRY))
 			radix_tree_free_nodes(old);
-		if (radix_tree_exceptional_entry(old))
+		if (xa_is_value(old))
 			node->exceptional--;
 	}
 	if (node) {
 		node->count += n;
-		if (radix_tree_exceptional_entry(item))
+		if (xa_is_value(item))
 			node->exceptional += n;
 	}
 	return n;
@@ -974,7 +972,7 @@ static inline int insert_entries(struct radix_tree_node *node,
 	rcu_assign_pointer(*slot, item);
 	if (node) {
 		node->count++;
-		if (radix_tree_exceptional_entry(item))
+		if (xa_is_value(item))
 			node->exceptional++;
 	}
 	return 1;
@@ -1190,8 +1188,7 @@ void __radix_tree_replace(struct radix_tree_root *root,
 			  radix_tree_update_node_t update_node)
 {
 	void *old = rcu_dereference_raw(*slot);
-	int exceptional = !!radix_tree_exceptional_entry(item) -
-				!!radix_tree_exceptional_entry(old);
+	int exceptional = !!xa_is_value(item) - !!xa_is_value(old);
 	int count = calculate_count(root, node, slot, item, old);
 
 	/*
@@ -1992,7 +1989,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root,
 				struct radix_tree_node *node, void __rcu **slot)
 {
 	void *old = rcu_dereference_raw(*slot);
-	int exceptional = radix_tree_exceptional_entry(old) ? -1 : 0;
+	int exceptional = xa_is_value(old) ? -1 : 0;
 	unsigned offset = get_slot_offset(node, slot);
 	int tag;
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 52517f28e6f4..4de14e75c4ec 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -127,7 +127,7 @@ static int page_cache_tree_insert(struct address_space *mapping,
 
 		p = radix_tree_deref_slot_protected(slot,
 						    &mapping->i_pages.xa_lock);
-		if (!radix_tree_exceptional_entry(p))
+		if (!xa_is_value(p))
 			return -EEXIST;
 
 		mapping->nrexceptional--;
@@ -336,7 +336,7 @@ page_cache_tree_delete_batch(struct address_space *mapping,
 			break;
 		page = radix_tree_deref_slot_protected(slot,
 						       &mapping->i_pages.xa_lock);
-		if (radix_tree_exceptional_entry(page))
+		if (xa_is_value(page))
 			continue;
 		if (!tail_pages) {
 			/*
@@ -1355,7 +1355,7 @@ pgoff_t page_cache_next_hole(struct address_space *mapping,
 		struct page *page;
 
 		page = radix_tree_lookup(&mapping->i_pages, index);
-		if (!page || radix_tree_exceptional_entry(page))
+		if (!page || xa_is_value(page))
 			break;
 		index++;
 		if (index == 0)
@@ -1396,7 +1396,7 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping,
 		struct page *page;
 
 		page = radix_tree_lookup(&mapping->i_pages, index);
-		if (!page || radix_tree_exceptional_entry(page))
+		if (!page || xa_is_value(page))
 			break;
 		index--;
 		if (index == ULONG_MAX)
@@ -1539,7 +1539,7 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
 
 repeat:
 	page = find_get_entry(mapping, offset);
-	if (radix_tree_exceptional_entry(page))
+	if (xa_is_value(page))
 		page = NULL;
 	if (!page)
 		goto no_page;
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index a31d740e6cd1..4820e4adf853 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1369,7 +1369,7 @@ static void collapse_shmem(struct mm_struct *mm,
 
 		page = radix_tree_deref_slot_protected(slot,
 				&mapping->i_pages.xa_lock);
-		if (radix_tree_exceptional_entry(page) || !PageUptodate(page)) {
+		if (xa_is_value(page) || !PageUptodate(page)) {
 			xa_unlock_irq(&mapping->i_pages);
 			/* swap in or instantiate fallocated page */
 			if (shmem_getpage(mapping->host, index, &page,
diff --git a/mm/madvise.c b/mm/madvise.c
index 972a9eaa898b..9d802566c494 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -251,7 +251,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
 		index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 
 		page = find_get_entry(mapping, index);
-		if (!radix_tree_exceptional_entry(page)) {
+		if (!xa_is_value(page)) {
 			if (page)
 				put_page(page);
 			continue;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e79cb59552d9..29d9d1a69b36 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4750,7 +4750,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
 	/* shmem/tmpfs may report page out on swap: account for that too. */
 	if (shmem_mapping(mapping)) {
 		page = find_get_entry(mapping, pgoff);
-		if (radix_tree_exceptional_entry(page)) {
+		if (xa_is_value(page)) {
 			swp_entry_t swp = radix_to_swp_entry(page);
 			if (do_memsw_account())
 				*entry = swp;
diff --git a/mm/mincore.c b/mm/mincore.c
index fc37afe226e6..4985965aa20a 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -66,7 +66,7 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
 		 * shmem/tmpfs may return swap: account for swapcache
 		 * page too.
 		 */
-		if (radix_tree_exceptional_entry(page)) {
+		if (xa_is_value(page)) {
 			swp_entry_t swp = radix_to_swp_entry(page);
 			page = find_get_page(swap_address_space(swp),
 					     swp_offset(swp));
diff --git a/mm/readahead.c b/mm/readahead.c
index 4e630143a0ba..de657077d41d 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -179,7 +179,7 @@ unsigned int __do_page_cache_readahead(struct address_space *mapping,
 		rcu_read_lock();
 		page = radix_tree_lookup(&mapping->i_pages, page_offset);
 		rcu_read_unlock();
-		if (page && !radix_tree_exceptional_entry(page)) {
+		if (page && !xa_is_value(page)) {
 			/*
 			 * Page already present?  Kick off the current batch of
 			 * contiguous pages before continuing with the next
diff --git a/mm/shmem.c b/mm/shmem.c
index 446942677cd4..c1062760fe41 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -709,7 +709,7 @@ unsigned long shmem_partial_swap_usage(struct address_space *mapping,
 			continue;
 		}
 
-		if (radix_tree_exceptional_entry(page))
+		if (xa_is_value(page))
 			swapped++;
 
 		if (need_resched()) {
@@ -824,7 +824,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			if (index >= end)
 				break;
 
-			if (radix_tree_exceptional_entry(page)) {
+			if (xa_is_value(page)) {
 				if (unfalloc)
 					continue;
 				nr_swaps_freed += !shmem_free_swap(mapping,
@@ -921,7 +921,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			if (index >= end)
 				break;
 
-			if (radix_tree_exceptional_entry(page)) {
+			if (xa_is_value(page)) {
 				if (unfalloc)
 					continue;
 				if (shmem_free_swap(mapping, index, page)) {
@@ -1643,7 +1643,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 repeat:
 	swap.val = 0;
 	page = find_lock_entry(mapping, index);
-	if (radix_tree_exceptional_entry(page)) {
+	if (xa_is_value(page)) {
 		swap = radix_to_swp_entry(page);
 		page = NULL;
 	}
@@ -2578,7 +2578,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
 				index = indices[i];
 			}
 			page = pvec.pages[i];
-			if (page && !radix_tree_exceptional_entry(page)) {
+			if (page && !xa_is_value(page)) {
 				if (!PageUptodate(page))
 					page = NULL;
 			}
diff --git a/mm/swap.c b/mm/swap.c
index 26fc9b5f1b6c..4c5c7fcc6e46 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -965,7 +965,7 @@ void pagevec_remove_exceptionals(struct pagevec *pvec)
 
 	for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
-		if (!radix_tree_exceptional_entry(page))
+		if (!xa_is_value(page))
 			pvec->pages[j++] = page;
 	}
 	pvec->nr = j;
diff --git a/mm/truncate.c b/mm/truncate.c
index 1d2fb2dca96f..ed778555c9f3 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -70,7 +70,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping,
 		return;
 
 	for (j = 0; j < pagevec_count(pvec); j++)
-		if (radix_tree_exceptional_entry(pvec->pages[j]))
+		if (xa_is_value(pvec->pages[j]))
 			break;
 
 	if (j == pagevec_count(pvec))
@@ -85,7 +85,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping,
 		struct page *page = pvec->pages[i];
 		pgoff_t index = indices[i];
 
-		if (!radix_tree_exceptional_entry(page)) {
+		if (!xa_is_value(page)) {
 			pvec->pages[j++] = page;
 			continue;
 		}
@@ -347,7 +347,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			if (index >= end)
 				break;
 
-			if (radix_tree_exceptional_entry(page))
+			if (xa_is_value(page))
 				continue;
 
 			if (!trylock_page(page))
@@ -442,7 +442,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 				break;
 			}
 
-			if (radix_tree_exceptional_entry(page))
+			if (xa_is_value(page))
 				continue;
 
 			lock_page(page);
@@ -561,7 +561,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 			if (index > end)
 				break;
 
-			if (radix_tree_exceptional_entry(page)) {
+			if (xa_is_value(page)) {
 				invalidate_exceptional_entry(mapping, index,
 							     page);
 				continue;
@@ -692,7 +692,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 			if (index > end)
 				break;
 
-			if (radix_tree_exceptional_entry(page)) {
+			if (xa_is_value(page)) {
 				if (!invalidate_exceptional_entry2(mapping,
 								   index, page))
 					ret = -EBUSY;
diff --git a/mm/workingset.c b/mm/workingset.c
index 4516dd790129..bb109b3afac2 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -155,8 +155,8 @@
  * refault distance will immediately activate the refaulting page.
  */
 
-#define EVICTION_SHIFT	(RADIX_TREE_EXCEPTIONAL_ENTRY + \
-			 NODES_SHIFT +	\
+#define EVICTION_SHIFT	((BITS_PER_LONG - BITS_PER_XA_VALUE) +	\
+			 NODES_SHIFT +				\
 			 MEM_CGROUP_ID_SHIFT)
 #define EVICTION_MASK	(~0UL >> EVICTION_SHIFT)
 
@@ -173,20 +173,19 @@ static unsigned int bucket_order __read_mostly;
 static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction)
 {
 	eviction >>= bucket_order;
+	eviction &= EVICTION_MASK;
 	eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
 	eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
-	eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT);
 
-	return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY);
+	return xa_mk_value(eviction);
 }
 
 static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
 			  unsigned long *evictionp)
 {
-	unsigned long entry = (unsigned long)shadow;
+	unsigned long entry = xa_to_value(shadow);
 	int memcgid, nid;
 
-	entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT;
 	nid = entry & ((1UL << NODES_SHIFT) - 1);
 	entry >>= NODES_SHIFT;
 	memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1);
@@ -453,7 +452,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 		goto out_invalid;
 	for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
 		if (node->slots[i]) {
-			if (WARN_ON_ONCE(!radix_tree_exceptional_entry(node->slots[i])))
+			if (WARN_ON_ONCE(!xa_is_value(node->slots[i])))
 				goto out_invalid;
 			if (WARN_ON_ONCE(!node->exceptional))
 				goto out_invalid;
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index f620c831a4b5..a5a4494922a6 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -19,7 +19,7 @@
 
 #include "test.h"
 
-#define DUMMY_PTR	((void *)0x12)
+#define DUMMY_PTR	((void *)0x10)
 
 int item_idr_free(int id, void *p, void *data)
 {
@@ -411,11 +411,11 @@ void ida_check_conv_user(void)
 		int id = ida_alloc(&ida, GFP_NOWAIT);
 		if (id == -ENOMEM) {
 			IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) !=
-					BITS_PER_LONG - 2);
+					BITS_PER_XA_VALUE);
 			id = ida_alloc(&ida, GFP_KERNEL);
 		} else {
 			IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) ==
-					BITS_PER_LONG - 2);
+					BITS_PER_XA_VALUE);
 		}
 		IDA_BUG_ON(&ida, id != i);
 	}
diff --git a/tools/testing/radix-tree/linux/radix-tree.h b/tools/testing/radix-tree/linux/radix-tree.h
index 24f13d27a8da..d1635a5bef02 100644
--- a/tools/testing/radix-tree/linux/radix-tree.h
+++ b/tools/testing/radix-tree/linux/radix-tree.h
@@ -2,7 +2,6 @@
 #ifndef _TEST_RADIX_TREE_H
 #define _TEST_RADIX_TREE_H
 
-#include "generated/map-shift.h"
 #include "../../../../include/linux/radix-tree.h"
 
 extern int kmalloc_verbose;
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 7bf405638b0b..2b4f4dba1882 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -39,12 +39,11 @@ static void __multiorder_tag_test(int index, int order)
 
 	/*
 	 * Verify we get collisions for covered indices.  We try and fail to
-	 * insert an exceptional entry so we don't leak memory via
+	 * insert a value entry so we don't leak memory via
 	 * item_insert_order().
 	 */
 	for_each_index(i, base, order) {
-		err = __radix_tree_insert(&tree, i, order,
-				(void *)(0xA0 | RADIX_TREE_EXCEPTIONAL_ENTRY));
+		err = __radix_tree_insert(&tree, i, order, xa_mk_value(0xA0));
 		assert(err == -EEXIST);
 	}
 
@@ -380,8 +379,8 @@ static void multiorder_join1(unsigned long index,
 }
 
 /*
- * Check that the accounting of exceptional entries is handled correctly
- * by joining an exceptional entry to a normal pointer.
+ * Check that the accounting of value entries is handled correctly
+ * by joining a value entry to a normal pointer.
  */
 static void multiorder_join2(unsigned order1, unsigned order2)
 {
@@ -391,9 +390,9 @@ static void multiorder_join2(unsigned order1, unsigned order2)
 	void *item2;
 
 	item_insert_order(&tree, 0, order2);
-	radix_tree_insert(&tree, 1 << order2, (void *)0x12UL);
+	radix_tree_insert(&tree, 1 << order2, xa_mk_value(5));
 	item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL);
-	assert(item2 == (void *)0x12UL);
+	assert(item2 == xa_mk_value(5));
 	assert(node->exceptional == 1);
 
 	item2 = radix_tree_lookup(&tree, 0);
@@ -407,7 +406,7 @@ static void multiorder_join2(unsigned order1, unsigned order2)
 }
 
 /*
- * This test revealed an accounting bug for exceptional entries at one point.
+ * This test revealed an accounting bug for value entries at one point.
  * Nodes were being freed back into the pool with an elevated exception count
  * by radix_tree_join() and then radix_tree_split() was failing to zero the
  * count of exceptional entries.
@@ -421,16 +420,16 @@ static void multiorder_join3(unsigned int order)
 	unsigned long i;
 
 	for (i = 0; i < (1 << order); i++) {
-		radix_tree_insert(&tree, i, (void *)0x12UL);
+		radix_tree_insert(&tree, i, xa_mk_value(5));
 	}
 
-	radix_tree_join(&tree, 0, order, (void *)0x16UL);
+	radix_tree_join(&tree, 0, order, xa_mk_value(7));
 	rcu_barrier();
 
 	radix_tree_split(&tree, 0, 0);
 
 	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		radix_tree_iter_replace(&tree, &iter, slot, (void *)0x12UL);
+		radix_tree_iter_replace(&tree, &iter, slot, xa_mk_value(5));
 	}
 
 	__radix_tree_lookup(&tree, 0, &node, NULL);
@@ -517,10 +516,10 @@ static void __multiorder_split2(int old_order, int new_order)
 	struct radix_tree_node *node;
 	void *item;
 
-	__radix_tree_insert(&tree, 0, old_order, (void *)0x12);
+	__radix_tree_insert(&tree, 0, old_order, xa_mk_value(5));
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == (void *)0x12);
+	assert(item == xa_mk_value(5));
 	assert(node->exceptional > 0);
 
 	radix_tree_split(&tree, 0, new_order);
@@ -530,7 +529,7 @@ static void __multiorder_split2(int old_order, int new_order)
 	}
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item != (void *)0x12);
+	assert(item != xa_mk_value(5));
 	assert(node->exceptional == 0);
 
 	item_kill_tree(&tree);
@@ -544,40 +543,40 @@ static void __multiorder_split3(int old_order, int new_order)
 	struct radix_tree_node *node;
 	void *item;
 
-	__radix_tree_insert(&tree, 0, old_order, (void *)0x12);
+	__radix_tree_insert(&tree, 0, old_order, xa_mk_value(5));
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == (void *)0x12);
+	assert(item == xa_mk_value(5));
 	assert(node->exceptional > 0);
 
 	radix_tree_split(&tree, 0, new_order);
 	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		radix_tree_iter_replace(&tree, &iter, slot, (void *)0x16);
+		radix_tree_iter_replace(&tree, &iter, slot, xa_mk_value(7));
 	}
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == (void *)0x16);
+	assert(item == xa_mk_value(7));
 	assert(node->exceptional > 0);
 
 	item_kill_tree(&tree);
 
-	__radix_tree_insert(&tree, 0, old_order, (void *)0x12);
+	__radix_tree_insert(&tree, 0, old_order, xa_mk_value(5));
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == (void *)0x12);
+	assert(item == xa_mk_value(5));
 	assert(node->exceptional > 0);
 
 	radix_tree_split(&tree, 0, new_order);
 	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
 		if (iter.index == (1 << new_order))
 			radix_tree_iter_replace(&tree, &iter, slot,
-						(void *)0x16);
+						xa_mk_value(7));
 		else
 			radix_tree_iter_replace(&tree, &iter, slot, NULL);
 	}
 
 	item = __radix_tree_lookup(&tree, 1 << new_order, &node, NULL);
-	assert(item == (void *)0x16);
+	assert(item == xa_mk_value(7));
 	assert(node->count == node->exceptional);
 	do {
 		node = node->parent;
@@ -610,13 +609,13 @@ static void multiorder_account(void)
 
 	item_insert_order(&tree, 0, 5);
 
-	__radix_tree_insert(&tree, 1 << 5, 5, (void *)0x12);
+	__radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5));
 	__radix_tree_lookup(&tree, 0, &node, NULL);
 	assert(node->count == node->exceptional * 2);
 	radix_tree_delete(&tree, 1 << 5);
 	assert(node->exceptional == 0);
 
-	__radix_tree_insert(&tree, 1 << 5, 5, (void *)0x12);
+	__radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5));
 	__radix_tree_lookup(&tree, 1 << 5, &node, &slot);
 	assert(node->count == node->exceptional * 2);
 	__radix_tree_replace(&tree, node, slot, NULL, NULL);
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index def6015570b2..62de66c314b7 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -295,7 +295,7 @@ void item_kill_tree(struct radix_tree_root *root)
 	int nfound;
 
 	radix_tree_for_each_slot(slot, root, &iter, 0) {
-		if (radix_tree_exceptional_entry(*slot))
+		if (xa_is_value(*slot))
 			radix_tree_delete(root, iter.index);
 	}
 
-- 
cgit v1.2.3


From 02c02bf12c5d838603eed44195d3e91f094e2ab2 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Fri, 3 Nov 2017 23:09:45 -0400
Subject: xarray: Change definition of sibling entries

Instead of storing a pointer to the slot containing the canonical entry,
store the offset of the slot.  Produces slightly more efficient code
(~300 bytes) and simplifies the implementation.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: Josef Bacik <jbacik@fb.com>
---
 include/linux/radix-tree.h                    |  5 +-
 include/linux/xarray.h                        | 92 +++++++++++++++++++++++++++
 lib/Kconfig                                   |  7 ++
 lib/radix-tree.c                              | 64 ++++++-------------
 tools/testing/radix-tree/Makefile             |  2 +-
 tools/testing/radix-tree/generated/autoconf.h |  1 +
 6 files changed, 121 insertions(+), 50 deletions(-)

(limited to 'tools')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index e9e76ab4fbbf..60f3d8eb2cb7 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -59,10 +59,7 @@ static inline bool radix_tree_is_internal_node(void *ptr)
 
 #define RADIX_TREE_MAX_TAGS 3
 
-#ifndef RADIX_TREE_MAP_SHIFT
-#define RADIX_TREE_MAP_SHIFT	(CONFIG_BASE_SMALL ? 4 : 6)
-#endif
-
+#define RADIX_TREE_MAP_SHIFT	XA_CHUNK_SHIFT
 #define RADIX_TREE_MAP_SIZE	(1UL << RADIX_TREE_MAP_SHIFT)
 #define RADIX_TREE_MAP_MASK	(RADIX_TREE_MAP_SIZE-1)
 
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 5c8acfc4ff55..4d1cd7a083e8 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -22,6 +22,12 @@
  * x1: Value entry or tagged pointer
  *
  * Attempting to store internal entries in the XArray is a bug.
+ *
+ * Most internal entries are pointers to the next node in the tree.
+ * The following internal entries have a special meaning:
+ *
+ * 0-62: Sibling entries
+ * 256: Retry entry
  */
 
 #define BITS_PER_XA_VALUE	(BITS_PER_LONG - 1)
@@ -111,6 +117,42 @@ static inline unsigned int xa_pointer_tag(void *entry)
 	return (unsigned long)entry & 3UL;
 }
 
+/*
+ * xa_mk_internal() - Create an internal entry.
+ * @v: Value to turn into an internal entry.
+ *
+ * Context: Any context.
+ * Return: An XArray internal entry corresponding to this value.
+ */
+static inline void *xa_mk_internal(unsigned long v)
+{
+	return (void *)((v << 2) | 2);
+}
+
+/*
+ * xa_to_internal() - Extract the value from an internal entry.
+ * @entry: XArray entry.
+ *
+ * Context: Any context.
+ * Return: The value which was stored in the internal entry.
+ */
+static inline unsigned long xa_to_internal(const void *entry)
+{
+	return (unsigned long)entry >> 2;
+}
+
+/*
+ * xa_is_internal() - Is the entry an internal entry?
+ * @entry: XArray entry.
+ *
+ * Context: Any context.
+ * Return: %true if the entry is an internal entry.
+ */
+static inline bool xa_is_internal(const void *entry)
+{
+	return ((unsigned long)entry & 3) == 2;
+}
+
 #define xa_trylock(xa)		spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)		spin_lock(&(xa)->xa_lock)
 #define xa_unlock(xa)		spin_unlock(&(xa)->xa_lock)
@@ -123,4 +165,54 @@ static inline unsigned int xa_pointer_tag(void *entry)
 #define xa_unlock_irqrestore(xa, flags) \
 				spin_unlock_irqrestore(&(xa)->xa_lock, flags)
 
+/* Everything below here is the Advanced API.  Proceed with caution. */
+
+/*
+ * The xarray is constructed out of a set of 'chunks' of pointers.  Choosing
+ * the best chunk size requires some tradeoffs.  A power of two recommends
+ * itself so that we can walk the tree based purely on shifts and masks.
+ * Generally, the larger the better; as the number of slots per level of the
+ * tree increases, the less tall the tree needs to be.  But that needs to be
+ * balanced against the memory consumption of each node.  On a 64-bit system,
+ * xa_node is currently 576 bytes, and we get 7 of them per 4kB page.  If we
+ * doubled the number of slots per node, we'd get only 3 nodes per 4kB page.
+ */
+#ifndef XA_CHUNK_SHIFT
+#define XA_CHUNK_SHIFT		(CONFIG_BASE_SMALL ? 4 : 6)
+#endif
+#define XA_CHUNK_SIZE		(1UL << XA_CHUNK_SHIFT)
+#define XA_CHUNK_MASK		(XA_CHUNK_SIZE - 1)
+
+/* Private */
+static inline bool xa_is_node(const void *entry)
+{
+	return xa_is_internal(entry) && (unsigned long)entry > 4096;
+}
+
+/* Private */
+static inline void *xa_mk_sibling(unsigned int offset)
+{
+	return xa_mk_internal(offset);
+}
+
+/* Private */
+static inline unsigned long xa_to_sibling(const void *entry)
+{
+	return xa_to_internal(entry);
+}
+
+/**
+ * xa_is_sibling() - Is the entry a sibling entry?
+ * @entry: Entry retrieved from the XArray
+ *
+ * Return: %true if the entry is a sibling entry.
+ */
+static inline bool xa_is_sibling(const void *entry)
+{
+	return IS_ENABLED(CONFIG_XARRAY_MULTI) && xa_is_internal(entry) &&
+		(entry < xa_mk_sibling(XA_CHUNK_SIZE - 1));
+}
+
+#define XA_RETRY_ENTRY		xa_mk_internal(256)
+
 #endif /* _LINUX_XARRAY_H */
diff --git a/lib/Kconfig b/lib/Kconfig
index a3928d4438b5..40bfa6ccd294 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -399,8 +399,15 @@ config INTERVAL_TREE
 
 	  for more information.
 
+config XARRAY_MULTI
+	bool
+	help
+	  Support entries which occupy multiple consecutive indices in the
+	  XArray.
+
 config RADIX_TREE_MULTIORDER
 	bool
+	select XARRAY_MULTI
 
 config ASSOCIATIVE_ARRAY
 	bool
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index b6c0e7f3a894..59b28111eabc 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -38,6 +38,7 @@
 #include <linux/rcupdate.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/xarray.h>
 
 
 /* Number of nodes in fully populated tree of given height */
@@ -98,24 +99,7 @@ static inline void *node_to_entry(void *ptr)
 	return (void *)((unsigned long)ptr | RADIX_TREE_INTERNAL_NODE);
 }
 
-#define RADIX_TREE_RETRY	node_to_entry(NULL)
-
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-/* Sibling slots point directly to another slot in the same node */
-static inline
-bool is_sibling_entry(const struct radix_tree_node *parent, void *node)
-{
-	void __rcu **ptr = node;
-	return (parent->slots <= ptr) &&
-			(ptr < parent->slots + RADIX_TREE_MAP_SIZE);
-}
-#else
-static inline
-bool is_sibling_entry(const struct radix_tree_node *parent, void *node)
-{
-	return false;
-}
-#endif
+#define RADIX_TREE_RETRY	XA_RETRY_ENTRY
 
 static inline unsigned long
 get_slot_offset(const struct radix_tree_node *parent, void __rcu **slot)
@@ -129,16 +113,10 @@ static unsigned int radix_tree_descend(const struct radix_tree_node *parent,
 	unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK;
 	void __rcu **entry = rcu_dereference_raw(parent->slots[offset]);
 
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-	if (radix_tree_is_internal_node(entry)) {
-		if (is_sibling_entry(parent, entry)) {
-			void __rcu **sibentry;
-			sibentry = (void __rcu **) entry_to_node(entry);
-			offset = get_slot_offset(parent, sibentry);
-			entry = rcu_dereference_raw(*sibentry);
-		}
+	if (xa_is_sibling(entry)) {
+		offset = xa_to_sibling(entry);
+		entry = rcu_dereference_raw(parent->slots[offset]);
 	}
-#endif
 
 	*nodep = (void *)entry;
 	return offset;
@@ -300,10 +278,10 @@ static void dump_node(struct radix_tree_node *node, unsigned long index)
 		} else if (!radix_tree_is_internal_node(entry)) {
 			pr_debug("radix entry %p offset %ld indices %lu-%lu parent %p\n",
 					entry, i, first, last, node);
-		} else if (is_sibling_entry(node, entry)) {
+		} else if (xa_is_sibling(entry)) {
 			pr_debug("radix sblng %p offset %ld indices %lu-%lu parent %p val %p\n",
 					entry, i, first, last, node,
-					*(void **)entry_to_node(entry));
+					node->slots[xa_to_sibling(entry)]);
 		} else {
 			dump_node(entry_to_node(entry), first);
 		}
@@ -881,8 +859,7 @@ static void radix_tree_free_nodes(struct radix_tree_node *node)
 
 	for (;;) {
 		void *entry = rcu_dereference_raw(child->slots[offset]);
-		if (radix_tree_is_internal_node(entry) && child->shift &&
-				!is_sibling_entry(child, entry)) {
+		if (xa_is_node(entry) && child->shift) {
 			child = entry_to_node(entry);
 			offset = 0;
 			continue;
@@ -904,7 +881,7 @@ static void radix_tree_free_nodes(struct radix_tree_node *node)
 static inline int insert_entries(struct radix_tree_node *node,
 		void __rcu **slot, void *item, unsigned order, bool replace)
 {
-	struct radix_tree_node *child;
+	void *sibling;
 	unsigned i, n, tag, offset, tags = 0;
 
 	if (node) {
@@ -922,7 +899,7 @@ static inline int insert_entries(struct radix_tree_node *node,
 		offset = offset & ~(n - 1);
 		slot = &node->slots[offset];
 	}
-	child = node_to_entry(slot);
+	sibling = xa_mk_sibling(offset);
 
 	for (i = 0; i < n; i++) {
 		if (slot[i]) {
@@ -939,7 +916,7 @@ static inline int insert_entries(struct radix_tree_node *node,
 	for (i = 0; i < n; i++) {
 		struct radix_tree_node *old = rcu_dereference_raw(slot[i]);
 		if (i) {
-			rcu_assign_pointer(slot[i], child);
+			rcu_assign_pointer(slot[i], sibling);
 			for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
 				if (tags & (1 << tag))
 					tag_clear(node, tag, offset + i);
@@ -949,9 +926,7 @@ static inline int insert_entries(struct radix_tree_node *node,
 				if (tags & (1 << tag))
 					tag_set(node, tag, offset);
 		}
-		if (radix_tree_is_internal_node(old) &&
-					!is_sibling_entry(node, old) &&
-					(old != RADIX_TREE_RETRY))
+		if (xa_is_node(old))
 			radix_tree_free_nodes(old);
 		if (xa_is_value(old))
 			node->exceptional--;
@@ -1112,10 +1087,10 @@ static inline void replace_sibling_entries(struct radix_tree_node *node,
 				void __rcu **slot, int count, int exceptional)
 {
 #ifdef CONFIG_RADIX_TREE_MULTIORDER
-	void *ptr = node_to_entry(slot);
-	unsigned offset = get_slot_offset(node, slot) + 1;
+	unsigned offset = get_slot_offset(node, slot);
+	void *ptr = xa_mk_sibling(offset);
 
-	while (offset < RADIX_TREE_MAP_SIZE) {
+	while (++offset < RADIX_TREE_MAP_SIZE) {
 		if (rcu_dereference_raw(node->slots[offset]) != ptr)
 			break;
 		if (count < 0) {
@@ -1123,7 +1098,6 @@ static inline void replace_sibling_entries(struct radix_tree_node *node,
 			node->count--;
 		}
 		node->exceptional += exceptional;
-		offset++;
 	}
 #endif
 }
@@ -1319,8 +1293,7 @@ int radix_tree_split(struct radix_tree_root *root, unsigned long index,
 			tags |= 1 << tag;
 
 	for (end = offset + 1; end < RADIX_TREE_MAP_SIZE; end++) {
-		if (!is_sibling_entry(parent,
-				rcu_dereference_raw(parent->slots[end])))
+		if (!xa_is_sibling(rcu_dereference_raw(parent->slots[end])))
 			break;
 		for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
 			if (tags & (1 << tag))
@@ -1618,7 +1591,7 @@ static void __rcu **skip_siblings(struct radix_tree_node **nodep,
 {
 	while (iter->index < iter->next_index) {
 		*nodep = rcu_dereference_raw(*slot);
-		if (*nodep && !is_sibling_entry(iter->node, *nodep))
+		if (*nodep && !xa_is_sibling(*nodep))
 			return slot;
 		slot++;
 		iter->index = __radix_tree_iter_add(iter, 1);
@@ -1769,7 +1742,7 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root,
 				while (++offset	< RADIX_TREE_MAP_SIZE) {
 					void *slot = rcu_dereference_raw(
 							node->slots[offset]);
-					if (is_sibling_entry(node, slot))
+					if (xa_is_sibling(slot))
 						continue;
 					if (slot)
 						break;
@@ -2283,6 +2256,7 @@ void __init radix_tree_init(void)
 
 	BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32);
 	BUILD_BUG_ON(ROOT_IS_IDR & ~GFP_ZONEMASK);
+	BUILD_BUG_ON(XA_CHUNK_SIZE > 255);
 	radix_tree_node_cachep = kmem_cache_create("radix_tree_node",
 			sizeof(struct radix_tree_node), 0,
 			SLAB_PANIC | SLAB_RECLAIM_ACCOUNT,
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index 37baecc3766f..12adcf9ffe86 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -46,6 +46,6 @@ idr.c: ../../../lib/idr.c
 
 generated/map-shift.h:
 	@if ! grep -qws $(SHIFT) generated/map-shift.h; then		\
-		echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" >		\
+		echo "#define XA_CHUNK_SHIFT $(SHIFT)" >		\
 				generated/map-shift.h;			\
 	fi
diff --git a/tools/testing/radix-tree/generated/autoconf.h b/tools/testing/radix-tree/generated/autoconf.h
index cf88dc5b8832..ca8e03ad19ac 100644
--- a/tools/testing/radix-tree/generated/autoconf.h
+++ b/tools/testing/radix-tree/generated/autoconf.h
@@ -1 +1,2 @@
 #define CONFIG_RADIX_TREE_MULTIORDER 1
+#define CONFIG_XARRAY_MULTI 1
-- 
cgit v1.2.3


From c2d68afba86d1ff01e7300c68bc16a9234dcd8e9 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Mon, 17 Sep 2018 04:14:55 +0000
Subject: tools: hv: fcopy: set 'error' in case an unknown operation was
 requested

'error' variable is left uninitialized in case we see an unknown operation.
As we don't immediately return and proceed to pwrite() we need to set it
to something, HV_E_FAIL sounds good enough.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 tools/hv/hv_fcopy_daemon.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c
index d78aed86af09..8ff8cb1a11f4 100644
--- a/tools/hv/hv_fcopy_daemon.c
+++ b/tools/hv/hv_fcopy_daemon.c
@@ -234,6 +234,7 @@ int main(int argc, char *argv[])
 			break;
 
 		default:
+			error = HV_E_FAIL;
 			syslog(LOG_ERR, "Unknown operation: %d",
 				buffer.hdr.operation);
 
-- 
cgit v1.2.3


From fe804cd6774938814242aa67bb7e7cbc934b1203 Mon Sep 17 00:00:00 2001
From: Stefan Raspl <stefan.raspl@de.ibm.com>
Date: Tue, 25 Sep 2018 09:19:36 +0200
Subject: tools/kvm_stat: cut down decimal places in update interval dialog

We currently display the default number of decimal places for floats in
_show_set_update_interval(), which is quite pointless. Cutting down to a
single decimal place.

Signed-off-by: Stefan Raspl <raspl@linux.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/kvm/kvm_stat/kvm_stat | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index 439b8a27488d..195ba486640f 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -1325,7 +1325,7 @@ class Tui(object):
         msg = ''
         while True:
             self.screen.erase()
-            self.screen.addstr(0, 0, 'Set update interval (defaults to %fs).' %
+            self.screen.addstr(0, 0, 'Set update interval (defaults to %.1fs).' %
                                DELAY_DEFAULT, curses.A_BOLD)
             self.screen.addstr(4, 0, msg)
             self.screen.addstr(2, 0, 'Change delay from %.1fs to ' %
-- 
cgit v1.2.3


From 25025e0aab2f91a93a1557b299a79814559b4dc2 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 28 Sep 2018 14:45:48 +0000
Subject: bpf: sync include/uapi/linux/bpf.h to tools/include/uapi/linux/bpf.h

The sync is required due to the appearance of a new map type:
BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, which implements per-cpu
cgroup local storage.

Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/bpf.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index aa5ccd2385ed..e2070d819e04 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -127,6 +127,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_SOCKHASH,
 	BPF_MAP_TYPE_CGROUP_STORAGE,
 	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
+	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
 };
 
 enum bpf_prog_type {
-- 
cgit v1.2.3


From e54870924f4c51a8228be9ad427274f1032e0683 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 28 Sep 2018 14:45:51 +0000
Subject: bpftool: add support for PERCPU_CGROUP_STORAGE maps

This commit adds support for BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE
map type.

Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/map.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index e22fbe8b975f..6003e9598973 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -72,13 +72,15 @@ static const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_SOCKHASH]		= "sockhash",
 	[BPF_MAP_TYPE_CGROUP_STORAGE]	= "cgroup_storage",
 	[BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray",
+	[BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE]	= "percpu_cgroup_storage",
 };
 
 static bool map_is_per_cpu(__u32 type)
 {
 	return type == BPF_MAP_TYPE_PERCPU_HASH ||
 	       type == BPF_MAP_TYPE_PERCPU_ARRAY ||
-	       type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
+	       type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
+	       type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE;
 }
 
 static bool map_is_map_of_maps(__u32 type)
-- 
cgit v1.2.3


From a3c6054f81e2c436d6b53b8060df996fec0cbfdb Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 28 Sep 2018 14:45:53 +0000
Subject: selftests/bpf: add verifier per-cpu cgroup storage tests

This commits adds verifier tests covering per-cpu cgroup storage
functionality. There are 6 new tests, which are exactly the same
as for shared cgroup storage, but do use per-cpu cgroup storage
map.

Expected output:
  $ ./test_verifier
  #0/u add+sub+mul OK
  #0/p add+sub+mul OK
  ...
  #286/p invalid cgroup storage access 6 OK
  #287/p valid per-cpu cgroup storage access OK
  #288/p invalid per-cpu cgroup storage access 1 OK
  #289/p invalid per-cpu cgroup storage access 2 OK
  #290/p invalid per-cpu cgroup storage access 3 OK
  #291/p invalid per-cpu cgroup storage access 4 OK
  #292/p invalid per-cpu cgroup storage access 5 OK
  #293/p invalid per-cpu cgroup storage access 6 OK
  #294/p multiple registers share map_lookup_elem result OK
  ...
  #662/p mov64 src == dst OK
  #663/p mov64 src != dst OK
  Summary: 914 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 139 ++++++++++++++++++++++++++--
 1 file changed, 133 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 67c412d19c09..c7d25f23baf9 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -68,6 +68,7 @@ struct bpf_test {
 	int fixup_prog2[MAX_FIXUPS];
 	int fixup_map_in_map[MAX_FIXUPS];
 	int fixup_cgroup_storage[MAX_FIXUPS];
+	int fixup_percpu_cgroup_storage[MAX_FIXUPS];
 	const char *errstr;
 	const char *errstr_unpriv;
 	uint32_t retval;
@@ -4676,7 +4677,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 	},
 	{
-		"invalid per-cgroup storage access 3",
+		"invalid cgroup storage access 3",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_2, 0),
 			BPF_LD_MAP_FD(BPF_REG_1, 0),
@@ -4743,6 +4744,121 @@ static struct bpf_test tests[] = {
 		.errstr = "get_local_storage() doesn't support non-zero flags",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 	},
+	{
+		"valid per-cpu cgroup storage access",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_percpu_cgroup_storage = { 1 },
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 1 },
+		.result = REJECT,
+		.errstr = "cannot pass map_type 1 into func bpf_get_local_storage",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 2",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "fd 1 is not pointing to valid bpf_map",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 3",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 256),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_percpu_cgroup_storage = { 1 },
+		.result = REJECT,
+		.errstr = "invalid access to map value, value_size=64 off=256 size=4",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 4",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, -2),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_cgroup_storage = { 1 },
+		.result = REJECT,
+		.errstr = "invalid access to map value, value_size=64 off=-2 size=4",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 5",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 7),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_percpu_cgroup_storage = { 1 },
+		.result = REJECT,
+		.errstr = "get_local_storage() doesn't support non-zero flags",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cpu cgroup storage access 6",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_percpu_cgroup_storage = { 1 },
+		.result = REJECT,
+		.errstr = "get_local_storage() doesn't support non-zero flags",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
 	{
 		"multiple registers share map_lookup_elem result",
 		.insns = {
@@ -12615,15 +12731,17 @@ static int create_map_in_map(void)
 	return outer_map_fd;
 }
 
-static int create_cgroup_storage(void)
+static int create_cgroup_storage(bool percpu)
 {
+	enum bpf_map_type type = percpu ? BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE :
+		BPF_MAP_TYPE_CGROUP_STORAGE;
 	int fd;
 
-	fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE,
-			    sizeof(struct bpf_cgroup_storage_key),
+	fd = bpf_create_map(type, sizeof(struct bpf_cgroup_storage_key),
 			    TEST_DATA_LEN, 0, 0);
 	if (fd < 0)
-		printf("Failed to create array '%s'!\n", strerror(errno));
+		printf("Failed to create cgroup storage '%s'!\n",
+		       strerror(errno));
 
 	return fd;
 }
@@ -12641,6 +12759,7 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 	int *fixup_prog2 = test->fixup_prog2;
 	int *fixup_map_in_map = test->fixup_map_in_map;
 	int *fixup_cgroup_storage = test->fixup_cgroup_storage;
+	int *fixup_percpu_cgroup_storage = test->fixup_percpu_cgroup_storage;
 
 	if (test->fill_helper)
 		test->fill_helper(test);
@@ -12710,12 +12829,20 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 	}
 
 	if (*fixup_cgroup_storage) {
-		map_fds[7] = create_cgroup_storage();
+		map_fds[7] = create_cgroup_storage(false);
 		do {
 			prog[*fixup_cgroup_storage].imm = map_fds[7];
 			fixup_cgroup_storage++;
 		} while (*fixup_cgroup_storage);
 	}
+
+	if (*fixup_percpu_cgroup_storage) {
+		map_fds[8] = create_cgroup_storage(true);
+		do {
+			prog[*fixup_percpu_cgroup_storage].imm = map_fds[8];
+			fixup_percpu_cgroup_storage++;
+		} while (*fixup_percpu_cgroup_storage);
+	}
 }
 
 static void do_test_single(struct bpf_test *test, bool unpriv,
-- 
cgit v1.2.3


From 919646d2a3a90465cf8b30a7616c63005bef7570 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 28 Sep 2018 14:45:55 +0000
Subject: selftests/bpf: extend the storage test to test per-cpu cgroup storage

This test extends the cgroup storage test to use per-cpu flavor
of the cgroup storage as well.

The test initializes a per-cpu cgroup storage to some non-zero initial
value (1000), and then simple bumps a per-cpu counter each time
the shared counter is atomically incremented. Then it reads all
per-cpu areas from the userspace side, and checks that the sum
of values adds to the expected sum.

Expected output:
  $ ./test_cgroup_storage
  test_cgroup_storage:PASS

Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_cgroup_storage.c | 60 +++++++++++++++++++++--
 1 file changed, 57 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c
index 4e196e3bfecf..f44834155f25 100644
--- a/tools/testing/selftests/bpf/test_cgroup_storage.c
+++ b/tools/testing/selftests/bpf/test_cgroup_storage.c
@@ -4,6 +4,7 @@
 #include <linux/filter.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <sys/sysinfo.h>
 
 #include "bpf_rlimit.h"
 #include "cgroup_helpers.h"
@@ -15,6 +16,14 @@ char bpf_log_buf[BPF_LOG_BUF_SIZE];
 int main(int argc, char **argv)
 {
 	struct bpf_insn prog[] = {
+		BPF_LD_MAP_FD(BPF_REG_1, 0), /* percpu map fd */
+		BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+			     BPF_FUNC_get_local_storage),
+		BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1),
+		BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0),
+
 		BPF_LD_MAP_FD(BPF_REG_1, 0), /* map fd */
 		BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */
 		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
@@ -28,9 +37,18 @@ int main(int argc, char **argv)
 	};
 	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
 	int error = EXIT_FAILURE;
-	int map_fd, prog_fd, cgroup_fd;
+	int map_fd, percpu_map_fd, prog_fd, cgroup_fd;
 	struct bpf_cgroup_storage_key key;
 	unsigned long long value;
+	unsigned long long *percpu_value;
+	int cpu, nproc;
+
+	nproc = get_nprocs_conf();
+	percpu_value = malloc(sizeof(*percpu_value) * nproc);
+	if (!percpu_value) {
+		printf("Not enough memory for per-cpu area (%d cpus)\n", nproc);
+		goto err;
+	}
 
 	map_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, sizeof(key),
 				sizeof(value), 0, 0);
@@ -39,7 +57,15 @@ int main(int argc, char **argv)
 		goto out;
 	}
 
-	prog[0].imm = map_fd;
+	percpu_map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+				       sizeof(key), sizeof(value), 0, 0);
+	if (percpu_map_fd < 0) {
+		printf("Failed to create map: %s\n", strerror(errno));
+		goto out;
+	}
+
+	prog[0].imm = percpu_map_fd;
+	prog[7].imm = map_fd;
 	prog_fd = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
 				   prog, insns_cnt, "GPL", 0,
 				   bpf_log_buf, BPF_LOG_BUF_SIZE);
@@ -77,7 +103,15 @@ int main(int argc, char **argv)
 	}
 
 	if (bpf_map_lookup_elem(map_fd, &key, &value)) {
-		printf("Failed to lookup cgroup storage\n");
+		printf("Failed to lookup cgroup storage 0\n");
+		goto err;
+	}
+
+	for (cpu = 0; cpu < nproc; cpu++)
+		percpu_value[cpu] = 1000;
+
+	if (bpf_map_update_elem(percpu_map_fd, &key, percpu_value, 0)) {
+		printf("Failed to update the data in the cgroup storage\n");
 		goto err;
 	}
 
@@ -120,11 +154,31 @@ int main(int argc, char **argv)
 		goto err;
 	}
 
+	/* Check the final value of the counter in the percpu local storage */
+
+	for (cpu = 0; cpu < nproc; cpu++)
+		percpu_value[cpu] = 0;
+
+	if (bpf_map_lookup_elem(percpu_map_fd, &key, percpu_value)) {
+		printf("Failed to lookup the per-cpu cgroup storage\n");
+		goto err;
+	}
+
+	value = 0;
+	for (cpu = 0; cpu < nproc; cpu++)
+		value += percpu_value[cpu];
+
+	if (value != nproc * 1000 + 6) {
+		printf("Unexpected data in the per-cpu cgroup storage\n");
+		goto err;
+	}
+
 	error = 0;
 	printf("test_cgroup_storage:PASS\n");
 
 err:
 	cleanup_cgroup_environment();
+	free(percpu_value);
 
 out:
 	return error;
-- 
cgit v1.2.3


From 371e4fcc9d96ab1c8d72d59ca4ee3537402d1584 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 28 Sep 2018 14:46:00 +0000
Subject: selftests/bpf: cgroup local storage-based network counters

This commit adds a bpf kselftest, which demonstrates how percpu
and shared cgroup local storage can be used for efficient lookup-free
network accounting.

Cgroup local storage provides generic memory area with a very efficient
lookup free access. To avoid expensive atomic operations for each
packet, per-cpu cgroup local storage is used. Each packet is initially
charged to a per-cpu counter, and only if the counter reaches certain
value (32 in this case), the charge is moved into the global atomic
counter. This allows to amortize atomic operations, keeping reasonable
accuracy.

The test also implements a naive network traffic throttling, mostly to
demonstrate the possibility of bpf cgroup--based network bandwidth
control.

Expected output:
  ./test_netcnt
  test_netcnt:PASS

Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile        |   6 +-
 tools/testing/selftests/bpf/netcnt_common.h |  24 +++++
 tools/testing/selftests/bpf/netcnt_prog.c   |  71 +++++++++++++
 tools/testing/selftests/bpf/test_netcnt.c   | 158 ++++++++++++++++++++++++++++
 4 files changed, 257 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/netcnt_common.h
 create mode 100644 tools/testing/selftests/bpf/netcnt_prog.c
 create mode 100644 tools/testing/selftests/bpf/test_netcnt.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 059d64a0f897..f802de526f57 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -23,7 +23,8 @@ $(TEST_CUSTOM_PROGS): $(OUTPUT)/%: %.c
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
 	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
 	test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
-	test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names
+	test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names \
+	test_netcnt
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
 	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
@@ -35,7 +36,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
 	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
-	test_skb_cgroup_id_kern.o bpf_flow.o
+	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
@@ -72,6 +73,7 @@ $(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
 $(OUTPUT)/test_progs: trace_helpers.c
 $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
 $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
+$(OUTPUT)/test_netcnt: cgroup_helpers.c
 
 .PHONY: force
 
diff --git a/tools/testing/selftests/bpf/netcnt_common.h b/tools/testing/selftests/bpf/netcnt_common.h
new file mode 100644
index 000000000000..81084c1c2c23
--- /dev/null
+++ b/tools/testing/selftests/bpf/netcnt_common.h
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __NETCNT_COMMON_H
+#define __NETCNT_COMMON_H
+
+#include <linux/types.h>
+
+#define MAX_PERCPU_PACKETS 32
+
+struct percpu_net_cnt {
+	__u64 packets;
+	__u64 bytes;
+
+	__u64 prev_ts;
+
+	__u64 prev_packets;
+	__u64 prev_bytes;
+};
+
+struct net_cnt {
+	__u64 packets;
+	__u64 bytes;
+};
+
+#endif
diff --git a/tools/testing/selftests/bpf/netcnt_prog.c b/tools/testing/selftests/bpf/netcnt_prog.c
new file mode 100644
index 000000000000..1198abca1360
--- /dev/null
+++ b/tools/testing/selftests/bpf/netcnt_prog.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/version.h>
+
+#include "bpf_helpers.h"
+#include "netcnt_common.h"
+
+#define MAX_BPS	(3 * 1024 * 1024)
+
+#define REFRESH_TIME_NS	100000000
+#define NS_PER_SEC	1000000000
+
+struct bpf_map_def SEC("maps") percpu_netcnt = {
+	.type = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+	.key_size = sizeof(struct bpf_cgroup_storage_key),
+	.value_size = sizeof(struct percpu_net_cnt),
+};
+
+struct bpf_map_def SEC("maps") netcnt = {
+	.type = BPF_MAP_TYPE_CGROUP_STORAGE,
+	.key_size = sizeof(struct bpf_cgroup_storage_key),
+	.value_size = sizeof(struct net_cnt),
+};
+
+SEC("cgroup/skb")
+int bpf_nextcnt(struct __sk_buff *skb)
+{
+	struct percpu_net_cnt *percpu_cnt;
+	char fmt[] = "%d %llu %llu\n";
+	struct net_cnt *cnt;
+	__u64 ts, dt;
+	int ret;
+
+	cnt = bpf_get_local_storage(&netcnt, 0);
+	percpu_cnt = bpf_get_local_storage(&percpu_netcnt, 0);
+
+	percpu_cnt->packets++;
+	percpu_cnt->bytes += skb->len;
+
+	if (percpu_cnt->packets > MAX_PERCPU_PACKETS) {
+		__sync_fetch_and_add(&cnt->packets,
+				     percpu_cnt->packets);
+		percpu_cnt->packets = 0;
+
+		__sync_fetch_and_add(&cnt->bytes,
+				     percpu_cnt->bytes);
+		percpu_cnt->bytes = 0;
+	}
+
+	ts = bpf_ktime_get_ns();
+	dt = ts - percpu_cnt->prev_ts;
+
+	dt *= MAX_BPS;
+	dt /= NS_PER_SEC;
+
+	if (cnt->bytes + percpu_cnt->bytes - percpu_cnt->prev_bytes < dt)
+		ret = 1;
+	else
+		ret = 0;
+
+	if (dt > REFRESH_TIME_NS) {
+		percpu_cnt->prev_ts = ts;
+		percpu_cnt->prev_packets = cnt->packets;
+		percpu_cnt->prev_bytes = cnt->bytes;
+	}
+
+	return !!ret;
+}
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/testing/selftests/bpf/test_netcnt.c b/tools/testing/selftests/bpf/test_netcnt.c
new file mode 100644
index 000000000000..7887df693399
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_netcnt.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <assert.h>
+#include <sys/sysinfo.h>
+#include <sys/time.h>
+
+#include <linux/bpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "cgroup_helpers.h"
+#include "bpf_rlimit.h"
+#include "netcnt_common.h"
+
+#define BPF_PROG "./netcnt_prog.o"
+#define TEST_CGROUP "/test-network-counters/"
+
+static int bpf_find_map(const char *test, struct bpf_object *obj,
+			const char *name)
+{
+	struct bpf_map *map;
+
+	map = bpf_object__find_map_by_name(obj, name);
+	if (!map) {
+		printf("%s:FAIL:map '%s' not found\n", test, name);
+		return -1;
+	}
+	return bpf_map__fd(map);
+}
+
+int main(int argc, char **argv)
+{
+	struct percpu_net_cnt *percpu_netcnt;
+	struct bpf_cgroup_storage_key key;
+	int map_fd, percpu_map_fd;
+	int error = EXIT_FAILURE;
+	struct net_cnt netcnt;
+	struct bpf_object *obj;
+	int prog_fd, cgroup_fd;
+	unsigned long packets;
+	unsigned long bytes;
+	int cpu, nproc;
+	__u32 prog_cnt;
+
+	nproc = get_nprocs_conf();
+	percpu_netcnt = malloc(sizeof(*percpu_netcnt) * nproc);
+	if (!percpu_netcnt) {
+		printf("Not enough memory for per-cpu area (%d cpus)\n", nproc);
+		goto err;
+	}
+
+	if (bpf_prog_load(BPF_PROG, BPF_PROG_TYPE_CGROUP_SKB,
+			  &obj, &prog_fd)) {
+		printf("Failed to load bpf program\n");
+		goto out;
+	}
+
+	if (setup_cgroup_environment()) {
+		printf("Failed to load bpf program\n");
+		goto err;
+	}
+
+	/* Create a cgroup, get fd, and join it */
+	cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
+	if (!cgroup_fd) {
+		printf("Failed to create test cgroup\n");
+		goto err;
+	}
+
+	if (join_cgroup(TEST_CGROUP)) {
+		printf("Failed to join cgroup\n");
+		goto err;
+	}
+
+	/* Attach bpf program */
+	if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) {
+		printf("Failed to attach bpf program");
+		goto err;
+	}
+
+	assert(system("ping localhost -6 -c 10000 -f -q > /dev/null") == 0);
+
+	if (bpf_prog_query(cgroup_fd, BPF_CGROUP_INET_EGRESS, 0, NULL, NULL,
+			   &prog_cnt)) {
+		printf("Failed to query attached programs");
+		goto err;
+	}
+
+	map_fd = bpf_find_map(__func__, obj, "netcnt");
+	if (map_fd < 0) {
+		printf("Failed to find bpf map with net counters");
+		goto err;
+	}
+
+	percpu_map_fd = bpf_find_map(__func__, obj, "percpu_netcnt");
+	if (percpu_map_fd < 0) {
+		printf("Failed to find bpf map with percpu net counters");
+		goto err;
+	}
+
+	if (bpf_map_get_next_key(map_fd, NULL, &key)) {
+		printf("Failed to get key in cgroup storage\n");
+		goto err;
+	}
+
+	if (bpf_map_lookup_elem(map_fd, &key, &netcnt)) {
+		printf("Failed to lookup cgroup storage\n");
+		goto err;
+	}
+
+	if (bpf_map_lookup_elem(percpu_map_fd, &key, &percpu_netcnt[0])) {
+		printf("Failed to lookup percpu cgroup storage\n");
+		goto err;
+	}
+
+	/* Some packets can be still in per-cpu cache, but not more than
+	 * MAX_PERCPU_PACKETS.
+	 */
+	packets = netcnt.packets;
+	bytes = netcnt.bytes;
+	for (cpu = 0; cpu < nproc; cpu++) {
+		if (percpu_netcnt[cpu].packets > MAX_PERCPU_PACKETS) {
+			printf("Unexpected percpu value: %llu\n",
+			       percpu_netcnt[cpu].packets);
+			goto err;
+		}
+
+		packets += percpu_netcnt[cpu].packets;
+		bytes += percpu_netcnt[cpu].bytes;
+	}
+
+	/* No packets should be lost */
+	if (packets != 10000) {
+		printf("Unexpected packet count: %lu\n", packets);
+		goto err;
+	}
+
+	/* Let's check that bytes counter matches the number of packets
+	 * multiplied by the size of ipv6 ICMP packet.
+	 */
+	if (bytes != packets * 104) {
+		printf("Unexpected bytes count: %lu\n", bytes);
+		goto err;
+	}
+
+	error = 0;
+	printf("test_netcnt:PASS\n");
+
+err:
+	cleanup_cgroup_environment();
+	free(percpu_netcnt);
+
+out:
+	return error;
+}
-- 
cgit v1.2.3


From 0ed3015c9964dab7a1693b3e40650f329c16691e Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Fri, 28 Sep 2018 21:48:08 +0530
Subject: selftests/tls: Fix recv(MSG_PEEK) & splice() test cases

TLS test cases splice_from_pipe, send_and_splice &
recv_peek_multiple_records expect to receive a given nummber of bytes
and then compare them against the number of bytes which were sent.
Therefore, system call recv() must not return before receiving the
requested number of bytes, otherwise the subsequent memcmp() fails.
This patch passes MSG_WAITALL flag to recv() so that it does not return
prematurely before requested number of bytes are copied to receive
buffer.

Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/tls.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 11d54c36ae49..fac68d710f35 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -288,7 +288,7 @@ TEST_F(tls, splice_from_pipe)
 	ASSERT_GE(pipe(p), 0);
 	EXPECT_GE(write(p[1], mem_send, send_len), 0);
 	EXPECT_GE(splice(p[0], NULL, self->fd, NULL, send_len, 0), 0);
-	EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+	EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len);
 	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
 }
 
@@ -322,13 +322,13 @@ TEST_F(tls, send_and_splice)
 
 	ASSERT_GE(pipe(p), 0);
 	EXPECT_EQ(send(self->fd, test_str, send_len2, 0), send_len2);
-	EXPECT_NE(recv(self->cfd, buf, send_len2, 0), -1);
+	EXPECT_EQ(recv(self->cfd, buf, send_len2, MSG_WAITALL), send_len2);
 	EXPECT_EQ(memcmp(test_str, buf, send_len2), 0);
 
 	EXPECT_GE(write(p[1], mem_send, send_len), send_len);
 	EXPECT_GE(splice(p[0], NULL, self->fd, NULL, send_len, 0), send_len);
 
-	EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+	EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len);
 	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
 }
 
@@ -516,17 +516,17 @@ TEST_F(tls, recv_peek_multiple_records)
 	len = strlen(test_str_second) + 1;
 	EXPECT_EQ(send(self->fd, test_str_second, len, 0), len);
 
-	len = sizeof(buf);
+	len = strlen(test_str_first);
 	memset(buf, 0, len);
-	EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1);
+	EXPECT_EQ(recv(self->cfd, buf, len, MSG_PEEK | MSG_WAITALL), len);
 
 	/* MSG_PEEK can only peek into the current record. */
-	len = strlen(test_str_first) + 1;
+	len = strlen(test_str_first);
 	EXPECT_EQ(memcmp(test_str_first, buf, len), 0);
 
-	len = sizeof(buf);
+	len = strlen(test_str) + 1;
 	memset(buf, 0, len);
-	EXPECT_NE(recv(self->cfd, buf, len, 0), -1);
+	EXPECT_EQ(recv(self->cfd, buf, len, MSG_WAITALL), len);
 
 	/* Non-MSG_PEEK will advance strparser (and therefore record)
 	 * however.
@@ -543,9 +543,9 @@ TEST_F(tls, recv_peek_multiple_records)
 	len = strlen(test_str_second) + 1;
 	EXPECT_EQ(send(self->fd, test_str_second, len, 0), len);
 
-	len = sizeof(buf);
+	len = strlen(test_str) + 1;
 	memset(buf, 0, len);
-	EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1);
+	EXPECT_EQ(recv(self->cfd, buf, len, MSG_PEEK | MSG_WAITALL), len);
 
 	len = strlen(test_str) + 1;
 	EXPECT_EQ(memcmp(test_str, buf, len), 0);
-- 
cgit v1.2.3


From 7c03e7035ac1cf2a6165754e4f3a49c2f1977838 Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@kernel.org>
Date: Mon, 1 Oct 2018 12:52:16 -0700
Subject: selftests/x86: Add clock_gettime() tests to test_vdso

Now that the vDSO implementation of clock_gettime() is getting
reworked, add a selftest for it.  This tests that its output is
consistent with the syscall version.

This is marked for stable to serve as a test for commit

  715bd9d12f84 ("x86/vdso: Fix asm constraints on vDSO syscall fallbacks")

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/082399674de2619b2befd8c0dde49b260605b126.1538422295.git.luto@kernel.org
---
 tools/testing/selftests/x86/test_vdso.c | 99 +++++++++++++++++++++++++++++++++
 1 file changed, 99 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/x86/test_vdso.c b/tools/testing/selftests/x86/test_vdso.c
index 235259011704..49f7294fb382 100644
--- a/tools/testing/selftests/x86/test_vdso.c
+++ b/tools/testing/selftests/x86/test_vdso.c
@@ -17,6 +17,7 @@
 #include <errno.h>
 #include <sched.h>
 #include <stdbool.h>
+#include <limits.h>
 
 #ifndef SYS_getcpu
 # ifdef __x86_64__
@@ -31,6 +32,10 @@
 
 int nerrs = 0;
 
+typedef int (*vgettime_t)(clockid_t, struct timespec *);
+
+vgettime_t vdso_clock_gettime;
+
 typedef long (*getcpu_t)(unsigned *, unsigned *, void *);
 
 getcpu_t vgetcpu;
@@ -95,6 +100,10 @@ static void fill_function_pointers()
 		printf("Warning: failed to find getcpu in vDSO\n");
 
 	vgetcpu = (getcpu_t) vsyscall_getcpu();
+
+	vdso_clock_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime");
+	if (!vdso_clock_gettime)
+		printf("Warning: failed to find clock_gettime in vDSO\n");
 }
 
 static long sys_getcpu(unsigned * cpu, unsigned * node,
@@ -103,6 +112,11 @@ static long sys_getcpu(unsigned * cpu, unsigned * node,
 	return syscall(__NR_getcpu, cpu, node, cache);
 }
 
+static inline int sys_clock_gettime(clockid_t id, struct timespec *ts)
+{
+	return syscall(__NR_clock_gettime, id, ts);
+}
+
 static void test_getcpu(void)
 {
 	printf("[RUN]\tTesting getcpu...\n");
@@ -155,10 +169,95 @@ static void test_getcpu(void)
 	}
 }
 
+static bool ts_leq(const struct timespec *a, const struct timespec *b)
+{
+	if (a->tv_sec != b->tv_sec)
+		return a->tv_sec < b->tv_sec;
+	else
+		return a->tv_nsec <= b->tv_nsec;
+}
+
+static char const * const clocknames[] = {
+	[0] = "CLOCK_REALTIME",
+	[1] = "CLOCK_MONOTONIC",
+	[2] = "CLOCK_PROCESS_CPUTIME_ID",
+	[3] = "CLOCK_THREAD_CPUTIME_ID",
+	[4] = "CLOCK_MONOTONIC_RAW",
+	[5] = "CLOCK_REALTIME_COARSE",
+	[6] = "CLOCK_MONOTONIC_COARSE",
+	[7] = "CLOCK_BOOTTIME",
+	[8] = "CLOCK_REALTIME_ALARM",
+	[9] = "CLOCK_BOOTTIME_ALARM",
+	[10] = "CLOCK_SGI_CYCLE",
+	[11] = "CLOCK_TAI",
+};
+
+static void test_one_clock_gettime(int clock, const char *name)
+{
+	struct timespec start, vdso, end;
+	int vdso_ret, end_ret;
+
+	printf("[RUN]\tTesting clock_gettime for clock %s (%d)...\n", name, clock);
+
+	if (sys_clock_gettime(clock, &start) < 0) {
+		if (errno == EINVAL) {
+			vdso_ret = vdso_clock_gettime(clock, &vdso);
+			if (vdso_ret == -EINVAL) {
+				printf("[OK]\tNo such clock.\n");
+			} else {
+				printf("[FAIL]\tNo such clock, but __vdso_clock_gettime returned %d\n", vdso_ret);
+				nerrs++;
+			}
+		} else {
+			printf("[WARN]\t clock_gettime(%d) syscall returned error %d\n", clock, errno);
+		}
+		return;
+	}
+
+	vdso_ret = vdso_clock_gettime(clock, &vdso);
+	end_ret = sys_clock_gettime(clock, &end);
+
+	if (vdso_ret != 0 || end_ret != 0) {
+		printf("[FAIL]\tvDSO returned %d, syscall errno=%d\n",
+		       vdso_ret, errno);
+		nerrs++;
+		return;
+	}
+
+	printf("\t%llu.%09ld %llu.%09ld %llu.%09ld\n",
+	       (unsigned long long)start.tv_sec, start.tv_nsec,
+	       (unsigned long long)vdso.tv_sec, vdso.tv_nsec,
+	       (unsigned long long)end.tv_sec, end.tv_nsec);
+
+	if (!ts_leq(&start, &vdso) || !ts_leq(&vdso, &end)) {
+		printf("[FAIL]\tTimes are out of sequence\n");
+		nerrs++;
+	}
+}
+
+static void test_clock_gettime(void)
+{
+	for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]);
+	     clock++) {
+		test_one_clock_gettime(clock, clocknames[clock]);
+	}
+
+	/* Also test some invalid clock ids */
+	test_one_clock_gettime(-1, "invalid");
+	test_one_clock_gettime(INT_MIN, "invalid");
+	test_one_clock_gettime(INT_MAX, "invalid");
+}
+
 int main(int argc, char **argv)
 {
 	fill_function_pointers();
 
+	test_clock_gettime();
+
+	/*
+	 * Test getcpu() last so that, if something goes wrong setting affinity,
+	 * we still run the other tests.
+	 */
 	test_getcpu();
 
 	return nerrs ? 1 : 0;
-- 
cgit v1.2.3


From f2c4db1bd80720cd8cb2a5aa220d9bc9f374f04e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 7 Aug 2018 10:17:27 -0700
Subject: x86/cpu: Sanitize FAM6_ATOM naming

Going primarily by:

  https://en.wikipedia.org/wiki/List_of_Intel_Atom_microprocessors

with additional information gleaned from other related pages; notably:

 - Bonnell shrink was called Saltwell
 - Moorefield is the Merriefield refresh which makes it Airmont

The general naming scheme is: FAM6_ATOM_UARCH_SOCTYPE

  for i in `git grep -l FAM6_ATOM` ; do
	sed -i  -e 's/ATOM_PINEVIEW/ATOM_BONNELL/g'		\
		-e 's/ATOM_LINCROFT/ATOM_BONNELL_MID/'		\
		-e 's/ATOM_PENWELL/ATOM_SALTWELL_MID/g'		\
		-e 's/ATOM_CLOVERVIEW/ATOM_SALTWELL_TABLET/g'	\
		-e 's/ATOM_CEDARVIEW/ATOM_SALTWELL/g'		\
		-e 's/ATOM_SILVERMONT1/ATOM_SILVERMONT/g'	\
		-e 's/ATOM_SILVERMONT2/ATOM_SILVERMONT_X/g'	\
		-e 's/ATOM_MERRIFIELD/ATOM_SILVERMONT_MID/g'	\
		-e 's/ATOM_MOOREFIELD/ATOM_AIRMONT_MID/g'	\
		-e 's/ATOM_DENVERTON/ATOM_GOLDMONT_X/g'		\
		-e 's/ATOM_GEMINI_LAKE/ATOM_GOLDMONT_PLUS/g' ${i}
  done

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: dave.hansen@linux.intel.com
Cc: len.brown@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/intel/core.c                       | 20 +++++-----
 arch/x86/events/intel/cstate.c                     |  8 ++--
 arch/x86/events/intel/rapl.c                       |  4 +-
 arch/x86/events/msr.c                              |  8 ++--
 arch/x86/include/asm/intel-family.h                | 33 ++++++++--------
 arch/x86/kernel/cpu/common.c                       | 28 ++++++-------
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c        |  4 +-
 arch/x86/kernel/tsc.c                              |  2 +-
 arch/x86/kernel/tsc_msr.c                          | 10 ++---
 arch/x86/platform/atom/punit_atom_debug.c          |  4 +-
 .../platform/intel-mid/device_libs/platform_bt.c   |  2 +-
 drivers/acpi/acpi_lpss.c                           |  2 +-
 drivers/acpi/x86/utils.c                           |  2 +-
 drivers/cpufreq/intel_pstate.c                     |  4 +-
 drivers/edac/pnd2_edac.c                           |  2 +-
 drivers/idle/intel_idle.c                          | 18 ++++-----
 drivers/mmc/host/sdhci-acpi.c                      |  2 +-
 drivers/pci/pci-mid.c                              |  4 +-
 drivers/platform/x86/intel_int0002_vgpio.c         |  2 +-
 drivers/platform/x86/intel_mid_powerbtn.c          |  4 +-
 drivers/platform/x86/intel_telemetry_debugfs.c     |  2 +-
 drivers/platform/x86/intel_telemetry_pltdrv.c      |  2 +-
 drivers/powercap/intel_rapl.c                      | 10 ++---
 drivers/thermal/intel_soc_dts_thermal.c            |  2 +-
 sound/soc/intel/boards/bytcr_rt5651.c              |  2 +-
 tools/power/x86/turbostat/turbostat.c              | 46 +++++++++++-----------
 26 files changed, 115 insertions(+), 112 deletions(-)

(limited to 'tools')

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index bd3b8f3600b2..f17cf6c3ec6f 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4121,11 +4121,11 @@ __init int intel_pmu_init(void)
 		name = "nehalem";
 		break;
 
-	case INTEL_FAM6_ATOM_PINEVIEW:
-	case INTEL_FAM6_ATOM_LINCROFT:
-	case INTEL_FAM6_ATOM_PENWELL:
-	case INTEL_FAM6_ATOM_CLOVERVIEW:
-	case INTEL_FAM6_ATOM_CEDARVIEW:
+	case INTEL_FAM6_ATOM_BONNELL:
+	case INTEL_FAM6_ATOM_BONNELL_MID:
+	case INTEL_FAM6_ATOM_SALTWELL:
+	case INTEL_FAM6_ATOM_SALTWELL_MID:
+	case INTEL_FAM6_ATOM_SALTWELL_TABLET:
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -4138,9 +4138,11 @@ __init int intel_pmu_init(void)
 		name = "bonnell";
 		break;
 
-	case INTEL_FAM6_ATOM_SILVERMONT1:
-	case INTEL_FAM6_ATOM_SILVERMONT2:
+	case INTEL_FAM6_ATOM_SILVERMONT:
+	case INTEL_FAM6_ATOM_SILVERMONT_X:
+	case INTEL_FAM6_ATOM_SILVERMONT_MID:
 	case INTEL_FAM6_ATOM_AIRMONT:
+	case INTEL_FAM6_ATOM_AIRMONT_MID:
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
@@ -4159,7 +4161,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_ATOM_DENVERTON:
+	case INTEL_FAM6_ATOM_GOLDMONT_X:
 		memcpy(hw_cache_event_ids, glm_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs,
@@ -4185,7 +4187,7 @@ __init int intel_pmu_init(void)
 		name = "goldmont";
 		break;
 
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
 		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs,
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 9f8084f18d58..d2e780705c5a 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -559,8 +559,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_ULT, hswult_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT1, slm_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT2, slm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT, slm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT_X, slm_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_AIRMONT,     slm_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_CORE,   snb_cstates),
@@ -581,9 +581,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_DENVERTON, glm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_X, glm_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GEMINI_LAKE, glm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 32f3e9423e99..91039ffed633 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -777,9 +777,9 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_MOBILE,  skl_rapl_init),
 
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_DENVERTON, hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, hsw_rapl_init),
 
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GEMINI_LAKE, hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init),
 	{},
 };
 
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index b4771a6ddbc1..1b9f85abf9bc 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -69,14 +69,14 @@ static bool test_intel(int idx)
 	case INTEL_FAM6_BROADWELL_GT3E:
 	case INTEL_FAM6_BROADWELL_X:
 
-	case INTEL_FAM6_ATOM_SILVERMONT1:
-	case INTEL_FAM6_ATOM_SILVERMONT2:
+	case INTEL_FAM6_ATOM_SILVERMONT:
+	case INTEL_FAM6_ATOM_SILVERMONT_X:
 	case INTEL_FAM6_ATOM_AIRMONT:
 
 	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_ATOM_DENVERTON:
+	case INTEL_FAM6_ATOM_GOLDMONT_X:
 
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
 
 	case INTEL_FAM6_XEON_PHI_KNL:
 	case INTEL_FAM6_XEON_PHI_KNM:
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 7ed08a7c3398..0dd6b0f4000e 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -8,9 +8,6 @@
  * The "_X" parts are generally the EP and EX Xeons, or the
  * "Extreme" ones, like Broadwell-E.
  *
- * Things ending in "2" are usually because we have no better
- * name for them.  There's no processor called "SILVERMONT2".
- *
  * While adding a new CPUID for a new microarchitecture, add a new
  * group to keep logically sorted out in chronological order. Within
  * that group keep the CPUID for the variants sorted by model number.
@@ -57,19 +54,23 @@
 
 /* "Small Core" Processors (Atom) */
 
-#define INTEL_FAM6_ATOM_PINEVIEW	0x1C
-#define INTEL_FAM6_ATOM_LINCROFT	0x26
-#define INTEL_FAM6_ATOM_PENWELL		0x27
-#define INTEL_FAM6_ATOM_CLOVERVIEW	0x35
-#define INTEL_FAM6_ATOM_CEDARVIEW	0x36
-#define INTEL_FAM6_ATOM_SILVERMONT1	0x37 /* BayTrail/BYT / Valleyview */
-#define INTEL_FAM6_ATOM_SILVERMONT2	0x4D /* Avaton/Rangely */
-#define INTEL_FAM6_ATOM_AIRMONT		0x4C /* CherryTrail / Braswell */
-#define INTEL_FAM6_ATOM_MERRIFIELD	0x4A /* Tangier */
-#define INTEL_FAM6_ATOM_MOOREFIELD	0x5A /* Anniedale */
-#define INTEL_FAM6_ATOM_GOLDMONT	0x5C
-#define INTEL_FAM6_ATOM_DENVERTON	0x5F /* Goldmont Microserver */
-#define INTEL_FAM6_ATOM_GEMINI_LAKE	0x7A
+#define INTEL_FAM6_ATOM_BONNELL		0x1C /* Diamondville, Pineview */
+#define INTEL_FAM6_ATOM_BONNELL_MID	0x26 /* Silverthorne, Lincroft */
+
+#define INTEL_FAM6_ATOM_SALTWELL	0x36 /* Cedarview */
+#define INTEL_FAM6_ATOM_SALTWELL_MID	0x27 /* Penwell */
+#define INTEL_FAM6_ATOM_SALTWELL_TABLET	0x35 /* Cloverview */
+
+#define INTEL_FAM6_ATOM_SILVERMONT	0x37 /* Bay Trail, Valleyview */
+#define INTEL_FAM6_ATOM_SILVERMONT_X	0x4D /* Avaton, Rangely */
+#define INTEL_FAM6_ATOM_SILVERMONT_MID	0x4A /* Merriefield */
+
+#define INTEL_FAM6_ATOM_AIRMONT		0x4C /* Cherry Trail, Braswell */
+#define INTEL_FAM6_ATOM_AIRMONT_MID	0x5A /* Moorefield */
+
+#define INTEL_FAM6_ATOM_GOLDMONT	0x5C /* Apollo Lake */
+#define INTEL_FAM6_ATOM_GOLDMONT_X	0x5F /* Denverton */
+#define INTEL_FAM6_ATOM_GOLDMONT_PLUS	0x7A /* Gemini Lake */
 
 /* Xeon Phi */
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 44c4ef3d989b..10e5ccfa9278 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -949,11 +949,11 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 }
 
 static const __initconst struct x86_cpu_id cpu_no_speculation[] = {
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_CEDARVIEW,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_CLOVERVIEW,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_LINCROFT,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_PENWELL,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_PINEVIEW,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_TABLET,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_BONNELL_MID,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_MID,	X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_BONNELL,	X86_FEATURE_ANY },
 	{ X86_VENDOR_CENTAUR,	5 },
 	{ X86_VENDOR_INTEL,	5 },
 	{ X86_VENDOR_NSC,	5 },
@@ -968,10 +968,10 @@ static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
 
 /* Only list CPUs which speculate but are non susceptible to SSB */
 static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT1	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT	},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT2	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_MERRIFIELD	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_X	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_MID	},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_CORE_YONAH		},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
@@ -984,14 +984,14 @@ static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
 
 static const __initconst struct x86_cpu_id cpu_no_l1tf[] = {
 	/* in addition to cpu_no_speculation */
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT1	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT2	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_X	},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_MERRIFIELD	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_MOOREFIELD	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_MID	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT_MID	},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_DENVERTON	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GEMINI_LAKE	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT_X	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT_PLUS	},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
 	{}
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index d68836139cf9..676c8a3ecdb2 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -93,7 +93,7 @@ static u64 get_prefetch_disable_bits(void)
 		 */
 		return 0xF;
 	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
 		/*
 		 * SDM defines bits of MSR_MISC_FEATURE_CONTROL register
 		 * as:
@@ -1068,7 +1068,7 @@ static int measure_l2_residency(void *_plr)
 	 */
 	switch (boot_cpu_data.x86_model) {
 	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
 		perf_miss_attr.config = X86_CONFIG(.event = 0xd1,
 						   .umask = 0x10);
 		perf_hit_attr.config = X86_CONFIG(.event = 0xd1,
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 6490f618e096..dd6b564f65e3 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -635,7 +635,7 @@ unsigned long native_calibrate_tsc(void)
 		case INTEL_FAM6_KABYLAKE_DESKTOP:
 			crystal_khz = 24000;	/* 24.0 MHz */
 			break;
-		case INTEL_FAM6_ATOM_DENVERTON:
+		case INTEL_FAM6_ATOM_GOLDMONT_X:
 			crystal_khz = 25000;	/* 25.0 MHz */
 			break;
 		case INTEL_FAM6_ATOM_GOLDMONT:
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 27ef714d886c..3d0e9aeea7c8 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -59,12 +59,12 @@ static const struct freq_desc freq_desc_ann = {
 };
 
 static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
-	INTEL_CPU_FAM6(ATOM_PENWELL,		freq_desc_pnw),
-	INTEL_CPU_FAM6(ATOM_CLOVERVIEW,		freq_desc_clv),
-	INTEL_CPU_FAM6(ATOM_SILVERMONT1,	freq_desc_byt),
+	INTEL_CPU_FAM6(ATOM_SALTWELL_MID,	freq_desc_pnw),
+	INTEL_CPU_FAM6(ATOM_SALTWELL_TABLET,	freq_desc_clv),
+	INTEL_CPU_FAM6(ATOM_SILVERMONT,		freq_desc_byt),
+	INTEL_CPU_FAM6(ATOM_SILVERMONT_MID,	freq_desc_tng),
 	INTEL_CPU_FAM6(ATOM_AIRMONT,		freq_desc_cht),
-	INTEL_CPU_FAM6(ATOM_MERRIFIELD,		freq_desc_tng),
-	INTEL_CPU_FAM6(ATOM_MOOREFIELD,		freq_desc_ann),
+	INTEL_CPU_FAM6(ATOM_AIRMONT_MID,	freq_desc_ann),
 	{}
 };
 
diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c
index 034813d4ab1e..41dae0f0d898 100644
--- a/arch/x86/platform/atom/punit_atom_debug.c
+++ b/arch/x86/platform/atom/punit_atom_debug.c
@@ -143,8 +143,8 @@ static void punit_dbgfs_unregister(void)
 	  (kernel_ulong_t)&drv_data }
 
 static const struct x86_cpu_id intel_punit_cpu_ids[] = {
-	ICPU(INTEL_FAM6_ATOM_SILVERMONT1, punit_device_byt),
-	ICPU(INTEL_FAM6_ATOM_MERRIFIELD,  punit_device_tng),
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT, punit_device_byt),
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID,  punit_device_tng),
 	ICPU(INTEL_FAM6_ATOM_AIRMONT,	  punit_device_cht),
 	{}
 };
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bt.c b/arch/x86/platform/intel-mid/device_libs/platform_bt.c
index 5a0483e7bf66..31dce781364c 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_bt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_bt.c
@@ -68,7 +68,7 @@ static struct bt_sfi_data tng_bt_sfi_data __initdata = {
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (kernel_ulong_t)&ddata }
 
 static const struct x86_cpu_id bt_sfi_cpu_ids[] = {
-	ICPU(INTEL_FAM6_ATOM_MERRIFIELD, tng_bt_sfi_data),
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID, tng_bt_sfi_data),
 	{}
 };
 
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index bf64cfa30feb..9efa3a588620 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -292,7 +292,7 @@ static const struct lpss_device_desc bsw_spi_dev_desc = {
 #define ICPU(model)	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, }
 
 static const struct x86_cpu_id lpss_cpu_ids[] = {
-	ICPU(INTEL_FAM6_ATOM_SILVERMONT1),	/* Valleyview, Bay Trail */
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT),	/* Valleyview, Bay Trail */
 	ICPU(INTEL_FAM6_ATOM_AIRMONT),	/* Braswell, Cherry Trail */
 	{}
 };
diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c
index 06c31ec3cc70..9a8e286dd86f 100644
--- a/drivers/acpi/x86/utils.c
+++ b/drivers/acpi/x86/utils.c
@@ -54,7 +54,7 @@ static const struct always_present_id always_present_ids[] = {
 	 * Bay / Cherry Trail PWM directly poked by GPU driver in win10,
 	 * but Linux uses a separate PWM driver, harmless if not used.
 	 */
-	ENTRY("80860F09", "1", ICPU(INTEL_FAM6_ATOM_SILVERMONT1), {}),
+	ENTRY("80860F09", "1", ICPU(INTEL_FAM6_ATOM_SILVERMONT), {}),
 	ENTRY("80862288", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {}),
 	/*
 	 * The INT0002 device is necessary to clear wakeup interrupt sources
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index b6a1aadaff9f..75140dd07037 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1778,7 +1778,7 @@ static const struct pstate_funcs knl_funcs = {
 static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(INTEL_FAM6_SANDYBRIDGE, 		core_funcs),
 	ICPU(INTEL_FAM6_SANDYBRIDGE_X,		core_funcs),
-	ICPU(INTEL_FAM6_ATOM_SILVERMONT1,	silvermont_funcs),
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT,	silvermont_funcs),
 	ICPU(INTEL_FAM6_IVYBRIDGE,		core_funcs),
 	ICPU(INTEL_FAM6_HASWELL_CORE,		core_funcs),
 	ICPU(INTEL_FAM6_BROADWELL_CORE,		core_funcs),
@@ -1795,7 +1795,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(INTEL_FAM6_XEON_PHI_KNL,		knl_funcs),
 	ICPU(INTEL_FAM6_XEON_PHI_KNM,		knl_funcs),
 	ICPU(INTEL_FAM6_ATOM_GOLDMONT,		core_funcs),
-	ICPU(INTEL_FAM6_ATOM_GEMINI_LAKE,       core_funcs),
+	ICPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS,     core_funcs),
 	ICPU(INTEL_FAM6_SKYLAKE_X,		core_funcs),
 	{}
 };
diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c
index df28b65358d2..903a4f1fadcc 100644
--- a/drivers/edac/pnd2_edac.c
+++ b/drivers/edac/pnd2_edac.c
@@ -1541,7 +1541,7 @@ static struct dunit_ops dnv_ops = {
 
 static const struct x86_cpu_id pnd2_cpuids[] = {
 	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT, 0, (kernel_ulong_t)&apl_ops },
-	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_DENVERTON, 0, (kernel_ulong_t)&dnv_ops },
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT_X, 0, (kernel_ulong_t)&dnv_ops },
 	{ }
 };
 MODULE_DEVICE_TABLE(x86cpu, pnd2_cpuids);
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index b2ccce5fb071..c4bb67ed8da3 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -1076,14 +1076,14 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	ICPU(INTEL_FAM6_WESTMERE,		idle_cpu_nehalem),
 	ICPU(INTEL_FAM6_WESTMERE_EP,		idle_cpu_nehalem),
 	ICPU(INTEL_FAM6_NEHALEM_EX,		idle_cpu_nehalem),
-	ICPU(INTEL_FAM6_ATOM_PINEVIEW,		idle_cpu_atom),
-	ICPU(INTEL_FAM6_ATOM_LINCROFT,		idle_cpu_lincroft),
+	ICPU(INTEL_FAM6_ATOM_BONNELL,		idle_cpu_atom),
+	ICPU(INTEL_FAM6_ATOM_BONNELL_MID,		idle_cpu_lincroft),
 	ICPU(INTEL_FAM6_WESTMERE_EX,		idle_cpu_nehalem),
 	ICPU(INTEL_FAM6_SANDYBRIDGE,		idle_cpu_snb),
 	ICPU(INTEL_FAM6_SANDYBRIDGE_X,		idle_cpu_snb),
-	ICPU(INTEL_FAM6_ATOM_CEDARVIEW,		idle_cpu_atom),
-	ICPU(INTEL_FAM6_ATOM_SILVERMONT1,	idle_cpu_byt),
-	ICPU(INTEL_FAM6_ATOM_MERRIFIELD,	idle_cpu_tangier),
+	ICPU(INTEL_FAM6_ATOM_SALTWELL,		idle_cpu_atom),
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT,	idle_cpu_byt),
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID,	idle_cpu_tangier),
 	ICPU(INTEL_FAM6_ATOM_AIRMONT,		idle_cpu_cht),
 	ICPU(INTEL_FAM6_IVYBRIDGE,		idle_cpu_ivb),
 	ICPU(INTEL_FAM6_IVYBRIDGE_X,		idle_cpu_ivt),
@@ -1091,7 +1091,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	ICPU(INTEL_FAM6_HASWELL_X,		idle_cpu_hsw),
 	ICPU(INTEL_FAM6_HASWELL_ULT,		idle_cpu_hsw),
 	ICPU(INTEL_FAM6_HASWELL_GT3E,		idle_cpu_hsw),
-	ICPU(INTEL_FAM6_ATOM_SILVERMONT2,	idle_cpu_avn),
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT_X,	idle_cpu_avn),
 	ICPU(INTEL_FAM6_BROADWELL_CORE,		idle_cpu_bdw),
 	ICPU(INTEL_FAM6_BROADWELL_GT3E,		idle_cpu_bdw),
 	ICPU(INTEL_FAM6_BROADWELL_X,		idle_cpu_bdw),
@@ -1104,8 +1104,8 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	ICPU(INTEL_FAM6_XEON_PHI_KNL,		idle_cpu_knl),
 	ICPU(INTEL_FAM6_XEON_PHI_KNM,		idle_cpu_knl),
 	ICPU(INTEL_FAM6_ATOM_GOLDMONT,		idle_cpu_bxt),
-	ICPU(INTEL_FAM6_ATOM_GEMINI_LAKE,	idle_cpu_bxt),
-	ICPU(INTEL_FAM6_ATOM_DENVERTON,		idle_cpu_dnv),
+	ICPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS,	idle_cpu_bxt),
+	ICPU(INTEL_FAM6_ATOM_GOLDMONT_X,	idle_cpu_dnv),
 	{}
 };
 
@@ -1322,7 +1322,7 @@ static void intel_idle_state_table_update(void)
 		ivt_idle_state_table_update();
 		break;
 	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
 		bxt_idle_state_table_update();
 		break;
 	case INTEL_FAM6_SKYLAKE_DESKTOP:
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index 32321bd596d8..cca6cde1b7e8 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -246,7 +246,7 @@ static const struct sdhci_acpi_chip sdhci_acpi_chip_int = {
 static bool sdhci_acpi_byt(void)
 {
 	static const struct x86_cpu_id byt[] = {
-		{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 },
+		{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT },
 		{}
 	};
 
diff --git a/drivers/pci/pci-mid.c b/drivers/pci/pci-mid.c
index 314e135014dc..30fbe2ea6eab 100644
--- a/drivers/pci/pci-mid.c
+++ b/drivers/pci/pci-mid.c
@@ -62,8 +62,8 @@ static const struct pci_platform_pm_ops mid_pci_platform_pm = {
  * arch/x86/platform/intel-mid/pwr.c.
  */
 static const struct x86_cpu_id lpss_cpu_ids[] = {
-	ICPU(INTEL_FAM6_ATOM_PENWELL),
-	ICPU(INTEL_FAM6_ATOM_MERRIFIELD),
+	ICPU(INTEL_FAM6_ATOM_SALTWELL_MID),
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID),
 	{}
 };
 
diff --git a/drivers/platform/x86/intel_int0002_vgpio.c b/drivers/platform/x86/intel_int0002_vgpio.c
index a473dc51b18d..e89ad4964dc1 100644
--- a/drivers/platform/x86/intel_int0002_vgpio.c
+++ b/drivers/platform/x86/intel_int0002_vgpio.c
@@ -60,7 +60,7 @@ static const struct x86_cpu_id int0002_cpu_ids[] = {
 /*
  * Limit ourselves to Cherry Trail for now, until testing shows we
  * need to handle the INT0002 device on Baytrail too.
- *	ICPU(INTEL_FAM6_ATOM_SILVERMONT1),	 * Valleyview, Bay Trail *
+ *	ICPU(INTEL_FAM6_ATOM_SILVERMONT),	 * Valleyview, Bay Trail *
  */
 	ICPU(INTEL_FAM6_ATOM_AIRMONT),		/* Braswell, Cherry Trail */
 	{}
diff --git a/drivers/platform/x86/intel_mid_powerbtn.c b/drivers/platform/x86/intel_mid_powerbtn.c
index d79fbf924b13..5ad44204a9c3 100644
--- a/drivers/platform/x86/intel_mid_powerbtn.c
+++ b/drivers/platform/x86/intel_mid_powerbtn.c
@@ -125,8 +125,8 @@ static const struct mid_pb_ddata mrfld_ddata = {
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (kernel_ulong_t)&ddata }
 
 static const struct x86_cpu_id mid_pb_cpu_ids[] = {
-	ICPU(INTEL_FAM6_ATOM_PENWELL,		mfld_ddata),
-	ICPU(INTEL_FAM6_ATOM_MERRIFIELD,	mrfld_ddata),
+	ICPU(INTEL_FAM6_ATOM_SALTWELL_MID,		mfld_ddata),
+	ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID,	mrfld_ddata),
 	{}
 };
 
diff --git a/drivers/platform/x86/intel_telemetry_debugfs.c b/drivers/platform/x86/intel_telemetry_debugfs.c
index ffd0474b0531..cee08f236292 100644
--- a/drivers/platform/x86/intel_telemetry_debugfs.c
+++ b/drivers/platform/x86/intel_telemetry_debugfs.c
@@ -320,7 +320,7 @@ static struct telemetry_debugfs_conf telem_apl_debugfs_conf = {
 
 static const struct x86_cpu_id telemetry_debugfs_cpu_ids[] = {
 	TELEM_DEBUGFS_CPU(INTEL_FAM6_ATOM_GOLDMONT, telem_apl_debugfs_conf),
-	TELEM_DEBUGFS_CPU(INTEL_FAM6_ATOM_GEMINI_LAKE, telem_apl_debugfs_conf),
+	TELEM_DEBUGFS_CPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS, telem_apl_debugfs_conf),
 	{}
 };
 
diff --git a/drivers/platform/x86/intel_telemetry_pltdrv.c b/drivers/platform/x86/intel_telemetry_pltdrv.c
index 2f889d6c270e..fcc6bee51a42 100644
--- a/drivers/platform/x86/intel_telemetry_pltdrv.c
+++ b/drivers/platform/x86/intel_telemetry_pltdrv.c
@@ -192,7 +192,7 @@ static struct telemetry_plt_config telem_glk_config = {
 
 static const struct x86_cpu_id telemetry_cpu_ids[] = {
 	TELEM_CPU(INTEL_FAM6_ATOM_GOLDMONT, telem_apl_config),
-	TELEM_CPU(INTEL_FAM6_ATOM_GEMINI_LAKE, telem_glk_config),
+	TELEM_CPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS, telem_glk_config),
 	{}
 };
 
diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c
index 295d8dcba48c..8cbfcce57a06 100644
--- a/drivers/powercap/intel_rapl.c
+++ b/drivers/powercap/intel_rapl.c
@@ -1164,13 +1164,13 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
 	RAPL_CPU(INTEL_FAM6_KABYLAKE_DESKTOP,	rapl_defaults_core),
 	RAPL_CPU(INTEL_FAM6_CANNONLAKE_MOBILE,	rapl_defaults_core),
 
-	RAPL_CPU(INTEL_FAM6_ATOM_SILVERMONT1,	rapl_defaults_byt),
+	RAPL_CPU(INTEL_FAM6_ATOM_SILVERMONT,	rapl_defaults_byt),
 	RAPL_CPU(INTEL_FAM6_ATOM_AIRMONT,	rapl_defaults_cht),
-	RAPL_CPU(INTEL_FAM6_ATOM_MERRIFIELD,	rapl_defaults_tng),
-	RAPL_CPU(INTEL_FAM6_ATOM_MOOREFIELD,	rapl_defaults_ann),
+	RAPL_CPU(INTEL_FAM6_ATOM_SILVERMONT_MID,	rapl_defaults_tng),
+	RAPL_CPU(INTEL_FAM6_ATOM_AIRMONT_MID,	rapl_defaults_ann),
 	RAPL_CPU(INTEL_FAM6_ATOM_GOLDMONT,	rapl_defaults_core),
-	RAPL_CPU(INTEL_FAM6_ATOM_GEMINI_LAKE,	rapl_defaults_core),
-	RAPL_CPU(INTEL_FAM6_ATOM_DENVERTON,	rapl_defaults_core),
+	RAPL_CPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS,	rapl_defaults_core),
+	RAPL_CPU(INTEL_FAM6_ATOM_GOLDMONT_X,	rapl_defaults_core),
 
 	RAPL_CPU(INTEL_FAM6_XEON_PHI_KNL,	rapl_defaults_hsw_server),
 	RAPL_CPU(INTEL_FAM6_XEON_PHI_KNM,	rapl_defaults_hsw_server),
diff --git a/drivers/thermal/intel_soc_dts_thermal.c b/drivers/thermal/intel_soc_dts_thermal.c
index 1e47511a6bd5..d748527d7a38 100644
--- a/drivers/thermal/intel_soc_dts_thermal.c
+++ b/drivers/thermal/intel_soc_dts_thermal.c
@@ -45,7 +45,7 @@ static irqreturn_t soc_irq_thread_fn(int irq, void *dev_data)
 }
 
 static const struct x86_cpu_id soc_thermal_ids[] = {
-	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1, 0,
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT, 0,
 		BYT_SOC_DTS_APIC_IRQ},
 	{}
 };
diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index f8a68bdb3885..6af02bf879ac 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -787,7 +787,7 @@ static struct snd_soc_card byt_rt5651_card = {
 };
 
 static const struct x86_cpu_id baytrail_cpu_ids[] = {
-	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, /* Valleyview */
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT }, /* Valleyview */
 	{}
 };
 
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 980bd9d20646..328f62e6ea02 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -2082,7 +2082,7 @@ int has_turbo_ratio_group_limits(int family, int model)
 	switch (model) {
 	case INTEL_FAM6_ATOM_GOLDMONT:
 	case INTEL_FAM6_SKYLAKE_X:
-	case INTEL_FAM6_ATOM_DENVERTON:
+	case INTEL_FAM6_ATOM_GOLDMONT_X:
 		return 1;
 	}
 	return 0;
@@ -3149,9 +3149,9 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 		pkg_cstate_limits = skx_pkg_cstate_limits;
 		has_misc_feature_control = 1;
 		break;
-	case INTEL_FAM6_ATOM_SILVERMONT1:	/* BYT */
+	case INTEL_FAM6_ATOM_SILVERMONT:	/* BYT */
 		no_MSR_MISC_PWR_MGMT = 1;
-	case INTEL_FAM6_ATOM_SILVERMONT2:	/* AVN */
+	case INTEL_FAM6_ATOM_SILVERMONT_X:	/* AVN */
 		pkg_cstate_limits = slv_pkg_cstate_limits;
 		break;
 	case INTEL_FAM6_ATOM_AIRMONT:	/* AMT */
@@ -3163,8 +3163,8 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 		pkg_cstate_limits = phi_pkg_cstate_limits;
 		break;
 	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
-	case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+	case INTEL_FAM6_ATOM_GOLDMONT_X:	/* DNV */
 		pkg_cstate_limits = bxt_pkg_cstate_limits;
 		break;
 	default:
@@ -3193,9 +3193,9 @@ int has_slv_msrs(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case INTEL_FAM6_ATOM_SILVERMONT1:
-	case INTEL_FAM6_ATOM_MERRIFIELD:
-	case INTEL_FAM6_ATOM_MOOREFIELD:
+	case INTEL_FAM6_ATOM_SILVERMONT:
+	case INTEL_FAM6_ATOM_SILVERMONT_MID:
+	case INTEL_FAM6_ATOM_AIRMONT_MID:
 		return 1;
 	}
 	return 0;
@@ -3207,7 +3207,7 @@ int is_dnv(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case INTEL_FAM6_ATOM_DENVERTON:
+	case INTEL_FAM6_ATOM_GOLDMONT_X:
 		return 1;
 	}
 	return 0;
@@ -3724,8 +3724,8 @@ double get_tdp(unsigned int model)
 			return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units;
 
 	switch (model) {
-	case INTEL_FAM6_ATOM_SILVERMONT1:
-	case INTEL_FAM6_ATOM_SILVERMONT2:
+	case INTEL_FAM6_ATOM_SILVERMONT:
+	case INTEL_FAM6_ATOM_SILVERMONT_X:
 		return 30.0;
 	default:
 		return 135.0;
@@ -3791,7 +3791,7 @@ void rapl_probe(unsigned int family, unsigned int model)
 		}
 		break;
 	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
 		do_rapl = RAPL_PKG | RAPL_PKG_POWER_INFO;
 		if (rapl_joules)
 			BIC_PRESENT(BIC_Pkg_J);
@@ -3850,8 +3850,8 @@ void rapl_probe(unsigned int family, unsigned int model)
 			BIC_PRESENT(BIC_RAMWatt);
 		}
 		break;
-	case INTEL_FAM6_ATOM_SILVERMONT1:	/* BYT */
-	case INTEL_FAM6_ATOM_SILVERMONT2:	/* AVN */
+	case INTEL_FAM6_ATOM_SILVERMONT:	/* BYT */
+	case INTEL_FAM6_ATOM_SILVERMONT_X:	/* AVN */
 		do_rapl = RAPL_PKG | RAPL_CORES;
 		if (rapl_joules) {
 			BIC_PRESENT(BIC_Pkg_J);
@@ -3861,7 +3861,7 @@ void rapl_probe(unsigned int family, unsigned int model)
 			BIC_PRESENT(BIC_CorWatt);
 		}
 		break;
-	case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
+	case INTEL_FAM6_ATOM_GOLDMONT_X:	/* DNV */
 		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO | RAPL_CORES_ENERGY_STATUS;
 		BIC_PRESENT(BIC_PKG__);
 		BIC_PRESENT(BIC_RAM__);
@@ -3884,7 +3884,7 @@ void rapl_probe(unsigned int family, unsigned int model)
 		return;
 
 	rapl_power_units = 1.0 / (1 << (msr & 0xF));
-	if (model == INTEL_FAM6_ATOM_SILVERMONT1)
+	if (model == INTEL_FAM6_ATOM_SILVERMONT)
 		rapl_energy_units = 1.0 * (1 << (msr >> 8 & 0x1F)) / 1000000;
 	else
 		rapl_energy_units = 1.0 / (1 << (msr >> 8 & 0x1F));
@@ -4141,8 +4141,8 @@ int has_snb_msrs(unsigned int family, unsigned int model)
 	case INTEL_FAM6_CANNONLAKE_MOBILE:	/* CNL */
 	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
 	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
-	case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+	case INTEL_FAM6_ATOM_GOLDMONT_X:	/* DNV */
 		return 1;
 	}
 	return 0;
@@ -4174,7 +4174,7 @@ int has_hsw_msrs(unsigned int family, unsigned int model)
 	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 	case INTEL_FAM6_CANNONLAKE_MOBILE:	/* CNL */
 	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
 		return 1;
 	}
 	return 0;
@@ -4209,8 +4209,8 @@ int is_slm(unsigned int family, unsigned int model)
 	if (!genuine_intel)
 		return 0;
 	switch (model) {
-	case INTEL_FAM6_ATOM_SILVERMONT1:	/* BYT */
-	case INTEL_FAM6_ATOM_SILVERMONT2:	/* AVN */
+	case INTEL_FAM6_ATOM_SILVERMONT:	/* BYT */
+	case INTEL_FAM6_ATOM_SILVERMONT_X:	/* AVN */
 		return 1;
 	}
 	return 0;
@@ -4581,11 +4581,11 @@ void process_cpuid()
 				case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 					crystal_hz = 24000000;	/* 24.0 MHz */
 					break;
-				case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
+				case INTEL_FAM6_ATOM_GOLDMONT_X:	/* DNV */
 					crystal_hz = 25000000;	/* 25.0 MHz */
 					break;
 				case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
-				case INTEL_FAM6_ATOM_GEMINI_LAKE:
+				case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
 					crystal_hz = 19200000;	/* 19.2 MHz */
 					break;
 				default:
-- 
cgit v1.2.3


From c4f790f244070dbab486805276ba4d1f87a057af Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 26 Sep 2018 11:29:16 -0700
Subject: tools/memory-model: Add litmus-test naming scheme

This commit documents the scheme used to generate the names for the
litmus tests.

[ paulmck: Apply feedback from Andrea Parri and Will Deacon. ]
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: akiyks@gmail.com
Cc: boqun.feng@gmail.com
Cc: dhowells@redhat.com
Cc: j.alglave@ucl.ac.uk
Cc: linux-arch@vger.kernel.org
Cc: luc.maranget@inria.fr
Cc: npiggin@gmail.com
Cc: parri.andrea@gmail.com
Cc: stern@rowland.harvard.edu
Link: http://lkml.kernel.org/r/20180926182920.27644-1-paulmck@linux.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/memory-model/litmus-tests/README | 104 ++++++++++++++++++++++++++++++++-
 1 file changed, 102 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/memory-model/litmus-tests/README b/tools/memory-model/litmus-tests/README
index 4581ec2d3c57..5ee08f129094 100644
--- a/tools/memory-model/litmus-tests/README
+++ b/tools/memory-model/litmus-tests/README
@@ -1,4 +1,6 @@
-This directory contains the following litmus tests:
+============
+LITMUS TESTS
+============
 
 CoRR+poonceonce+Once.litmus
 	Test of read-read coherence, that is, whether or not two
@@ -36,7 +38,7 @@ IRIW+poonceonces+OnceOnce.litmus
 ISA2+pooncelock+pooncelock+pombonce.litmus
 	Tests whether the ordering provided by a lock-protected S
 	litmus test is visible to an external process whose accesses are
-	separated by smp_mb().	This addition of an external process to
+	separated by smp_mb().  This addition of an external process to
 	S is otherwise known as ISA2.
 
 ISA2+poonceonces.litmus
@@ -151,3 +153,101 @@ Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
 A great many more litmus tests are available here:
 
 	https://github.com/paulmckrcu/litmus
+
+==================
+LITMUS TEST NAMING
+==================
+
+Litmus tests are usually named based on their contents, which means that
+looking at the name tells you what the litmus test does.  The naming
+scheme covers litmus tests having a single cycle that passes through
+each process exactly once, so litmus tests not fitting this description
+are named on an ad-hoc basis.
+
+The structure of a litmus-test name is the litmus-test class, a plus
+sign ("+"), and one string for each process, separated by plus signs.
+The end of the name is ".litmus".
+
+The litmus-test classes may be found in the infamous test6.pdf:
+https://www.cl.cam.ac.uk/~pes20/ppc-supplemental/test6.pdf
+Each class defines the pattern of accesses and of the variables accessed.
+For example, if the one process writes to a pair of variables, and
+the other process reads from these same variables, the corresponding
+litmus-test class is "MP" (message passing), which may be found on the
+left-hand end of the second row of tests on page one of test6.pdf.
+
+The strings used to identify the actions carried out by each process are
+complex due to a desire to have short(er) names.  Thus, there is a tool to
+generate these strings from a given litmus test's actions.  For example,
+consider the processes from SB+rfionceonce-poonceonces.litmus:
+
+	P0(int *x, int *y)
+	{
+		int r1;
+		int r2;
+
+		WRITE_ONCE(*x, 1);
+		r1 = READ_ONCE(*x);
+		r2 = READ_ONCE(*y);
+	}
+
+	P1(int *x, int *y)
+	{
+		int r3;
+		int r4;
+
+		WRITE_ONCE(*y, 1);
+		r3 = READ_ONCE(*y);
+		r4 = READ_ONCE(*x);
+	}
+
+The next step is to construct a space-separated list of descriptors,
+interleaving descriptions of the relation between a pair of consecutive
+accesses with descriptions of the second access in the pair.
+
+P0()'s WRITE_ONCE() is read by its first READ_ONCE(), which is a
+reads-from link (rf) and internal to the P0() process.  This is
+"rfi", which is an abbreviation for "reads-from internal".  Because
+some of the tools string these abbreviations together with space
+characters separating processes, the first character is capitalized,
+resulting in "Rfi".
+
+P0()'s second access is a READ_ONCE(), as opposed to (for example)
+smp_load_acquire(), so next is "Once".  Thus far, we have "Rfi Once".
+
+P0()'s third access is also a READ_ONCE(), but to y rather than x.
+This is related to P0()'s second access by program order ("po"),
+to a different variable ("d"), and both accesses are reads ("RR").
+The resulting descriptor is "PodRR".  Because P0()'s third access is
+READ_ONCE(), we add another "Once" descriptor.
+
+A from-read ("fre") relation links P0()'s third to P1()'s first
+access, and the resulting descriptor is "Fre".  P1()'s first access is
+WRITE_ONCE(), which as before gives the descriptor "Once".  The string
+thus far is thus "Rfi Once PodRR Once Fre Once".
+
+The remainder of P1() is similar to P0(), which means we add
+"Rfi Once PodRR Once".  Another fre links P1()'s last access to
+P0()'s first access, which is WRITE_ONCE(), so we add "Fre Once".
+The full string is thus:
+
+	Rfi Once PodRR Once Fre Once Rfi Once PodRR Once Fre Once
+
+This string can be given to the "norm7" and "classify7" tools to
+produce the name:
+
+	$ norm7 -bell linux-kernel.bell \
+		Rfi Once PodRR Once Fre Once Rfi Once PodRR Once Fre Once | \
+	  sed -e 's/:.*//g'
+	SB+rfionceonce-poonceonces
+
+Adding the ".litmus" suffix: SB+rfionceonce-poonceonces.litmus
+
+The descriptors that describe connections between consecutive accesses
+within the cycle through a given litmus test can be provided by the herd
+tool (Rfi, Po, Fre, and so on) or by the linux-kernel.bell file (Once,
+Release, Acquire, and so on).
+
+To see the full list of descriptors, execute the following command:
+
+	$ diyone7 -bell linux-kernel.bell -show edges
-- 
cgit v1.2.3


From 6e89e831a90172bc3d34ecbba52af5b9c4a447d1 Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Wed, 26 Sep 2018 11:29:17 -0700
Subject: tools/memory-model: Add extra ordering for locks and remove it for
 ordinary release/acquire

More than one kernel developer has expressed the opinion that the LKMM
should enforce ordering of writes by locking.  In other words, given
the following code:

	WRITE_ONCE(x, 1);
	spin_unlock(&s):
	spin_lock(&s);
	WRITE_ONCE(y, 1);

the stores to x and y should be propagated in order to all other CPUs,
even though those other CPUs might not access the lock s.  In terms of
the memory model, this means expanding the cumul-fence relation.

Locks should also provide read-read (and read-write) ordering in a
similar way.  Given:

	READ_ONCE(x);
	spin_unlock(&s);
	spin_lock(&s);
	READ_ONCE(y);		// or WRITE_ONCE(y, 1);

the load of x should be executed before the load of (or store to) y.
The LKMM already provides this ordering, but it provides it even in
the case where the two accesses are separated by a release/acquire
pair of fences rather than unlock/lock.  This would prevent
architectures from using weakly ordered implementations of release and
acquire, which seems like an unnecessary restriction.  The patch
therefore removes the ordering requirement from the LKMM for that
case.

There are several arguments both for and against this change.  Let us
refer to these enhanced ordering properties by saying that the LKMM
would require locks to be RCtso (a bit of a misnomer, but analogous to
RCpc and RCsc) and it would require ordinary acquire/release only to
be RCpc.  (Note: In the following, the phrase "all supported
architectures" is meant not to include RISC-V.  Although RISC-V is
indeed supported by the kernel, the implementation is still somewhat
in a state of flux and therefore statements about it would be
premature.)

Pros:

	The kernel already provides RCtso ordering for locks on all
	supported architectures, even though this is not stated
	explicitly anywhere.  Therefore the LKMM should formalize it.

	In theory, guaranteeing RCtso ordering would reduce the need
	for additional barrier-like constructs meant to increase the
	ordering strength of locks.

	Will Deacon and Peter Zijlstra are strongly in favor of
	formalizing the RCtso requirement.  Linus Torvalds and Will
	would like to go even further, requiring locks to have RCsc
	behavior (ordering preceding writes against later reads), but
	they recognize that this would incur a noticeable performance
	degradation on the POWER architecture.  Linus also points out
	that people have made the mistake, in the past, of assuming
	that locking has stronger ordering properties than is
	currently guaranteed, and this change would reduce the
	likelihood of such mistakes.

	Not requiring ordinary acquire/release to be any stronger than
	RCpc may prove advantageous for future architectures, allowing
	them to implement smp_load_acquire() and smp_store_release()
	with more efficient machine instructions than would be
	possible if the operations had to be RCtso.  Will and Linus
	approve this rationale, hypothetical though it is at the
	moment (it may end up affecting the RISC-V implementation).
	The same argument may or may not apply to RMW-acquire/release;
	see also the second Con entry below.

	Linus feels that locks should be easy for people to use
	without worrying about memory consistency issues, since they
	are so pervasive in the kernel, whereas acquire/release is
	much more of an "experts only" tool.  Requiring locks to be
	RCtso is a step in this direction.

Cons:

	Andrea Parri and Luc Maranget think that locks should have the
	same ordering properties as ordinary acquire/release (indeed,
	Luc points out that the names "acquire" and "release" derive
	from the usage of locks).  Andrea points out that having
	different ordering properties for different forms of acquires
	and releases is not only unnecessary, it would also be
	confusing and unmaintainable.

	Locks are constructed from lower-level primitives, typically
	RMW-acquire (for locking) and ordinary release (for unlock).
	It is illogical to require stronger ordering properties from
	the high-level operations than from the low-level operations
	they comprise.  Thus, this change would make

		while (cmpxchg_acquire(&s, 0, 1) != 0)
			cpu_relax();

	an incorrect implementation of spin_lock(&s) as far as the
	LKMM is concerned.  In theory this weakness can be ameliorated
	by changing the LKMM even further, requiring
	RMW-acquire/release also to be RCtso (which it already is on
	all supported architectures).

	As far as I know, nobody has singled out any examples of code
	in the kernel that actually relies on locks being RCtso.
	(People mumble about RCU and the scheduler, but nobody has
	pointed to any actual code.  If there are any real cases,
	their number is likely quite small.)  If RCtso ordering is not
	needed, why require it?

	A handful of locking constructs (qspinlocks, qrwlocks, and
	mcs_spinlocks) are built on top of smp_cond_load_acquire()
	instead of an RMW-acquire instruction.  It currently provides
	only the ordinary acquire semantics, not the stronger ordering
	this patch would require of locks.  In theory this could be
	ameliorated by requiring smp_cond_load_acquire() in
	combination with ordinary release also to be RCtso (which is
	currently true on all supported architectures).

	On future weakly ordered architectures, people may be able to
	implement locks in a non-RCtso fashion with significant
	performance improvement.  Meeting the RCtso requirement would
	necessarily add run-time overhead.

Overall, the technical aspects of these arguments seem relatively
minor, and it appears mostly to boil down to a matter of opinion.
Since the opinions of senior kernel maintainers such as Linus,
Peter, and Will carry more weight than those of Luc and Andrea, this
patch changes the model in accordance with the maintainers' wishes.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Reviewed-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: akiyks@gmail.com
Cc: boqun.feng@gmail.com
Cc: dhowells@redhat.com
Cc: j.alglave@ucl.ac.uk
Cc: linux-arch@vger.kernel.org
Cc: luc.maranget@inria.fr
Cc: npiggin@gmail.com
Cc: parri.andrea@gmail.com
Link: http://lkml.kernel.org/r/20180926182920.27644-2-paulmck@linux.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/memory-model/Documentation/explanation.txt   | 186 ++++++++++++++++-----
 tools/memory-model/linux-kernel.cat                |   8 +-
 .../ISA2+pooncelock+pooncelock+pombonce.litmus     |   7 +-
 3 files changed, 150 insertions(+), 51 deletions(-)

(limited to 'tools')

diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt
index 0cbd1ef8f86d..35bff92cc773 100644
--- a/tools/memory-model/Documentation/explanation.txt
+++ b/tools/memory-model/Documentation/explanation.txt
@@ -28,7 +28,8 @@ Explanation of the Linux-Kernel Memory Consistency Model
   20. THE HAPPENS-BEFORE RELATION: hb
   21. THE PROPAGATES-BEFORE RELATION: pb
   22. RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb
-  23. ODDS AND ENDS
+  23. LOCKING
+  24. ODDS AND ENDS
 
 
 
@@ -1067,28 +1068,6 @@ allowing out-of-order writes like this to occur.  The model avoided
 violating the write-write coherence rule by requiring the CPU not to
 send the W write to the memory subsystem at all!)
 
-There is one last example of preserved program order in the LKMM: when
-a load-acquire reads from an earlier store-release.  For example:
-
-	smp_store_release(&x, 123);
-	r1 = smp_load_acquire(&x);
-
-If the smp_load_acquire() ends up obtaining the 123 value that was
-stored by the smp_store_release(), the LKMM says that the load must be
-executed after the store; the store cannot be forwarded to the load.
-This requirement does not arise from the operational model, but it
-yields correct predictions on all architectures supported by the Linux
-kernel, although for differing reasons.
-
-On some architectures, including x86 and ARMv8, it is true that the
-store cannot be forwarded to the load.  On others, including PowerPC
-and ARMv7, smp_store_release() generates object code that starts with
-a fence and smp_load_acquire() generates object code that ends with a
-fence.  The upshot is that even though the store may be forwarded to
-the load, it is still true that any instruction preceding the store
-will be executed before the load or any following instructions, and
-the store will be executed before any instruction following the load.
-
 
 AND THEN THERE WAS ALPHA
 ------------------------
@@ -1766,6 +1745,147 @@ before it does, and the critical section in P2 both starts after P1's
 grace period does and ends after it does.
 
 
+LOCKING
+-------
+
+The LKMM includes locking.  In fact, there is special code for locking
+in the formal model, added in order to make tools run faster.
+However, this special code is intended to be more or less equivalent
+to concepts we have already covered.  A spinlock_t variable is treated
+the same as an int, and spin_lock(&s) is treated almost the same as:
+
+	while (cmpxchg_acquire(&s, 0, 1) != 0)
+		cpu_relax();
+
+This waits until s is equal to 0 and then atomically sets it to 1,
+and the read part of the cmpxchg operation acts as an acquire fence.
+An alternate way to express the same thing would be:
+
+	r = xchg_acquire(&s, 1);
+
+along with a requirement that at the end, r = 0.  Similarly,
+spin_trylock(&s) is treated almost the same as:
+
+	return !cmpxchg_acquire(&s, 0, 1);
+
+which atomically sets s to 1 if it is currently equal to 0 and returns
+true if it succeeds (the read part of the cmpxchg operation acts as an
+acquire fence only if the operation is successful).  spin_unlock(&s)
+is treated almost the same as:
+
+	smp_store_release(&s, 0);
+
+The "almost" qualifiers above need some explanation.  In the LKMM, the
+store-release in a spin_unlock() and the load-acquire which forms the
+first half of the atomic rmw update in a spin_lock() or a successful
+spin_trylock() -- we can call these things lock-releases and
+lock-acquires -- have two properties beyond those of ordinary releases
+and acquires.
+
+First, when a lock-acquire reads from a lock-release, the LKMM
+requires that every instruction po-before the lock-release must
+execute before any instruction po-after the lock-acquire.  This would
+naturally hold if the release and acquire operations were on different
+CPUs, but the LKMM says it holds even when they are on the same CPU.
+For example:
+
+	int x, y;
+	spinlock_t s;
+
+	P0()
+	{
+		int r1, r2;
+
+		spin_lock(&s);
+		r1 = READ_ONCE(x);
+		spin_unlock(&s);
+		spin_lock(&s);
+		r2 = READ_ONCE(y);
+		spin_unlock(&s);
+	}
+
+	P1()
+	{
+		WRITE_ONCE(y, 1);
+		smp_wmb();
+		WRITE_ONCE(x, 1);
+	}
+
+Here the second spin_lock() reads from the first spin_unlock(), and
+therefore the load of x must execute before the load of y.  Thus we
+cannot have r1 = 1 and r2 = 0 at the end (this is an instance of the
+MP pattern).
+
+This requirement does not apply to ordinary release and acquire
+fences, only to lock-related operations.  For instance, suppose P0()
+in the example had been written as:
+
+	P0()
+	{
+		int r1, r2, r3;
+
+		r1 = READ_ONCE(x);
+		smp_store_release(&s, 1);
+		r3 = smp_load_acquire(&s);
+		r2 = READ_ONCE(y);
+	}
+
+Then the CPU would be allowed to forward the s = 1 value from the
+smp_store_release() to the smp_load_acquire(), executing the
+instructions in the following order:
+
+		r3 = smp_load_acquire(&s);	// Obtains r3 = 1
+		r2 = READ_ONCE(y);
+		r1 = READ_ONCE(x);
+		smp_store_release(&s, 1);	// Value is forwarded
+
+and thus it could load y before x, obtaining r2 = 0 and r1 = 1.
+
+Second, when a lock-acquire reads from a lock-release, and some other
+stores W and W' occur po-before the lock-release and po-after the
+lock-acquire respectively, the LKMM requires that W must propagate to
+each CPU before W' does.  For example, consider:
+
+	int x, y;
+	spinlock_t x;
+
+	P0()
+	{
+		spin_lock(&s);
+		WRITE_ONCE(x, 1);
+		spin_unlock(&s);
+	}
+
+	P1()
+	{
+		int r1;
+
+		spin_lock(&s);
+		r1 = READ_ONCE(x);
+		WRITE_ONCE(y, 1);
+		spin_unlock(&s);
+	}
+
+	P2()
+	{
+		int r2, r3;
+
+		r2 = READ_ONCE(y);
+		smp_rmb();
+		r3 = READ_ONCE(x);
+	}
+
+If r1 = 1 at the end then the spin_lock() in P1 must have read from
+the spin_unlock() in P0.  Hence the store to x must propagate to P2
+before the store to y does, so we cannot have r2 = 1 and r3 = 0.
+
+These two special requirements for lock-release and lock-acquire do
+not arise from the operational model.  Nevertheless, kernel developers
+have come to expect and rely on them because they do hold on all
+architectures supported by the Linux kernel, albeit for various
+differing reasons.
+
+
 ODDS AND ENDS
 -------------
 
@@ -1831,26 +1951,6 @@ they behave as follows:
 	events and the events preceding them against all po-later
 	events.
 
-The LKMM includes locking.  In fact, there is special code for locking
-in the formal model, added in order to make tools run faster.
-However, this special code is intended to be exactly equivalent to
-concepts we have already covered.  A spinlock_t variable is treated
-the same as an int, and spin_lock(&s) is treated the same as:
-
-	while (cmpxchg_acquire(&s, 0, 1) != 0)
-		cpu_relax();
-
-which waits until s is equal to 0 and then atomically sets it to 1,
-and where the read part of the atomic update is also an acquire fence.
-An alternate way to express the same thing would be:
-
-	r = xchg_acquire(&s, 1);
-
-along with a requirement that at the end, r = 0.  spin_unlock(&s) is
-treated the same as:
-
-	smp_store_release(&s, 0);
-
 Interestingly, RCU and locking each introduce the possibility of
 deadlock.  When faced with code sequences such as:
 
diff --git a/tools/memory-model/linux-kernel.cat b/tools/memory-model/linux-kernel.cat
index 59b5cbe6b624..882fc33274ac 100644
--- a/tools/memory-model/linux-kernel.cat
+++ b/tools/memory-model/linux-kernel.cat
@@ -38,7 +38,7 @@ let strong-fence = mb | gp
 (* Release Acquire *)
 let acq-po = [Acquire] ; po ; [M]
 let po-rel = [M] ; po ; [Release]
-let rfi-rel-acq = [Release] ; rfi ; [Acquire]
+let po-unlock-rf-lock-po = po ; [UL] ; rf ; [LKR] ; po
 
 (**********************************)
 (* Fundamental coherence ordering *)
@@ -60,13 +60,13 @@ let dep = addr | data
 let rwdep = (dep | ctrl) ; [W]
 let overwrite = co | fr
 let to-w = rwdep | (overwrite & int)
-let to-r = addr | (dep ; rfi) | rfi-rel-acq
+let to-r = addr | (dep ; rfi)
 let fence = strong-fence | wmb | po-rel | rmb | acq-po
-let ppo = to-r | to-w | fence
+let ppo = to-r | to-w | fence | (po-unlock-rf-lock-po & int)
 
 (* Propagation: Ordering from release operations and strong fences. *)
 let A-cumul(r) = rfe? ; r
-let cumul-fence = A-cumul(strong-fence | po-rel) | wmb
+let cumul-fence = A-cumul(strong-fence | po-rel) | wmb | po-unlock-rf-lock-po
 let prop = (overwrite & ext)? ; cumul-fence* ; rfe?
 
 (*
diff --git a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
index 0f749e419b34..094d58df7789 100644
--- a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
+++ b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
@@ -1,11 +1,10 @@
 C ISA2+pooncelock+pooncelock+pombonce
 
 (*
- * Result: Sometimes
+ * Result: Never
  *
- * This test shows that the ordering provided by a lock-protected S
- * litmus test (P0() and P1()) are not visible to external process P2().
- * This is likely to change soon.
+ * This test shows that write-write ordering provided by locks
+ * (in P0() and P1()) is visible to external process P2().
  *)
 
 {}
-- 
cgit v1.2.3


From 3d2046a6fa2106584cf1080c2c08a6e8e79cbbb4 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj38.park@gmail.com>
Date: Wed, 26 Sep 2018 11:29:18 -0700
Subject: tools/memory-model: Fix a README typo

This commit fixes a duplicate-"the" typo in README.

Signed-off-by: SeongJae Park <sj38.park@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: akiyks@gmail.com
Cc: boqun.feng@gmail.com
Cc: dhowells@redhat.com
Cc: j.alglave@ucl.ac.uk
Cc: linux-arch@vger.kernel.org
Cc: luc.maranget@inria.fr
Cc: npiggin@gmail.com
Cc: parri.andrea@gmail.com
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/20180926182920.27644-3-paulmck@linux.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/memory-model/Documentation/recipes.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/memory-model/Documentation/recipes.txt b/tools/memory-model/Documentation/recipes.txt
index af72700cc20a..7fe8d7aa3029 100644
--- a/tools/memory-model/Documentation/recipes.txt
+++ b/tools/memory-model/Documentation/recipes.txt
@@ -311,7 +311,7 @@ The smp_wmb() macro orders prior stores against later stores, and the
 smp_rmb() macro orders prior loads against later loads.  Therefore, if
 the final value of r0 is 1, the final value of r1 must also be 1.
 
-The the xlog_state_switch_iclogs() function in fs/xfs/xfs_log.c contains
+The xlog_state_switch_iclogs() function in fs/xfs/xfs_log.c contains
 the following write-side code fragment:
 
 	log->l_curr_block -= log->l_logBBsize;
-- 
cgit v1.2.3


From d8fa25c4efde0e5f31a427202e583d73d3f021c4 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 26 Sep 2018 11:29:19 -0700
Subject: tools/memory-model: Add more LKMM limitations

This commit adds more detail about compiler optimizations and
not-yet-modeled Linux-kernel APIs.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: akiyks@gmail.com
Cc: boqun.feng@gmail.com
Cc: dhowells@redhat.com
Cc: j.alglave@ucl.ac.uk
Cc: linux-arch@vger.kernel.org
Cc: luc.maranget@inria.fr
Cc: npiggin@gmail.com
Cc: parri.andrea@gmail.com
Cc: stern@rowland.harvard.edu
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/20180926182920.27644-4-paulmck@linux.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/memory-model/README | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

(limited to 'tools')

diff --git a/tools/memory-model/README b/tools/memory-model/README
index ee987ce20aae..acf9077cffaa 100644
--- a/tools/memory-model/README
+++ b/tools/memory-model/README
@@ -171,6 +171,12 @@ The Linux-kernel memory model has the following limitations:
 	particular, the "THE PROGRAM ORDER RELATION: po AND po-loc"
 	and "A WARNING" sections).
 
+	Note that this limitation in turn limits LKMM's ability to
+	accurately model address, control, and data dependencies.
+	For example, if the compiler can deduce the value of some variable
+	carrying a dependency, then the compiler can break that dependency
+	by substituting a constant of that value.
+
 2.	Multiple access sizes for a single variable are not supported,
 	and neither are misaligned or partially overlapping accesses.
 
@@ -190,6 +196,36 @@ The Linux-kernel memory model has the following limitations:
 	However, a substantial amount of support is provided for these
 	operations, as shown in the linux-kernel.def file.
 
+	a.	When rcu_assign_pointer() is passed NULL, the Linux
+		kernel provides no ordering, but LKMM models this
+		case as a store release.
+
+	b.	The "unless" RMW operations are not currently modeled:
+		atomic_long_add_unless(), atomic_add_unless(),
+		atomic_inc_unless_negative(), and
+		atomic_dec_unless_positive().  These can be emulated
+		in litmus tests, for example, by using atomic_cmpxchg().
+
+	c.	The call_rcu() function is not modeled.  It can be
+		emulated in litmus tests by adding another process that
+		invokes synchronize_rcu() and the body of the callback
+		function, with (for example) a release-acquire from
+		the site of the emulated call_rcu() to the beginning
+		of the additional process.
+
+	d.	The rcu_barrier() function is not modeled.  It can be
+		emulated in litmus tests emulating call_rcu() via
+		(for example) a release-acquire from the end of each
+		additional call_rcu() process to the site of the
+		emulated rcu-barrier().
+
+	e.	Sleepable RCU (SRCU) is not modeled.  It can be
+		emulated, but perhaps not simply.
+
+	f.	Reader-writer locking is not modeled.  It can be
+		emulated in litmus tests using atomic read-modify-write
+		operations.
+
 The "herd7" tool has some additional limitations of its own, apart from
 the memory model:
 
@@ -204,3 +240,6 @@ the memory model:
 Some of these limitations may be overcome in the future, but others are
 more likely to be addressed by incorporating the Linux-kernel memory model
 into other tools.
+
+Finally, please note that LKMM is subject to change as hardware, use cases,
+and compilers evolve.
-- 
cgit v1.2.3


From e0a2e73e501c77037c8756137e87b12c7c3c9793 Mon Sep 17 00:00:00 2001
From: Maciej Żenczykowski <maze@google.com>
Date: Thu, 20 Sep 2018 13:29:42 -0700
Subject: usbip: fix vhci_hcd controller counting
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Without this usbip fails on a machine with devices
that lexicographically come after vhci_hcd.

ie.
  $ ls -l /sys/devices/platform
  ...
  drwxr-xr-x. 4 root root    0 Sep 19 16:21 serial8250
  -rw-r--r--. 1 root root 4096 Sep 19 23:50 uevent
  drwxr-xr-x. 6 root root    0 Sep 20 13:15 vhci_hcd.0
  drwxr-xr-x. 4 root root    0 Sep 19 16:22 w83627hf.656

Because it detects 'w83627hf.656' as another vhci_hcd controller,
and then fails to be able to talk to it.

Note: this doesn't actually fix usbip's support for multiple
controllers... that's still broken for other reasons
("vhci_hcd.0" is hardcoded in a string macro), but is enough to
actually make it work on the above machine.

See also:
  https://bugzilla.redhat.com/show_bug.cgi?id=1631148

Cc: Jonathan Dieter <jdieter@gmail.com>
Cc: Valentina Manea <valentina.manea.m@gmail.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: linux-usb@vger.kernel.org
Signed-off-by: Maciej Żenczykowski <zenczykowski@gmail.com>
Acked-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
Tested-by: Jonathan Dieter <jdieter@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 tools/usb/usbip/libsrc/vhci_driver.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c
index 4204359c9fee..8159fd98680b 100644
--- a/tools/usb/usbip/libsrc/vhci_driver.c
+++ b/tools/usb/usbip/libsrc/vhci_driver.c
@@ -150,7 +150,7 @@ static int get_nports(struct udev_device *hc_device)
 
 static int vhci_hcd_filter(const struct dirent *dirent)
 {
-	return strcmp(dirent->d_name, "vhci_hcd") >= 0;
+	return !strncmp(dirent->d_name, "vhci_hcd.", 9);
 }
 
 static int get_ncontrollers(void)
-- 
cgit v1.2.3


From aad2eeaf46973a0968a75640cd1f8f1c650322a0 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@wand.net.nz>
Date: Tue, 2 Oct 2018 13:35:30 -0700
Subject: bpf: Simplify ptr_min_max_vals adjustment

An upcoming commit will add another two pointer types that need very
similar behaviour, so generalise this function now.

Signed-off-by: Joe Stringer <joe@wand.net.nz>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c                       | 22 ++++++++++------------
 tools/testing/selftests/bpf/test_verifier.c | 14 +++++++-------
 2 files changed, 17 insertions(+), 19 deletions(-)

(limited to 'tools')

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9c82d8f58085..abf567200574 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2669,20 +2669,18 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		return -EACCES;
 	}
 
-	if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
-		verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n",
-			dst);
-		return -EACCES;
-	}
-	if (ptr_reg->type == CONST_PTR_TO_MAP) {
-		verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n",
-			dst);
+	switch (ptr_reg->type) {
+	case PTR_TO_MAP_VALUE_OR_NULL:
+		verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n",
+			dst, reg_type_str[ptr_reg->type]);
 		return -EACCES;
-	}
-	if (ptr_reg->type == PTR_TO_PACKET_END) {
-		verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n",
-			dst);
+	case CONST_PTR_TO_MAP:
+	case PTR_TO_PACKET_END:
+		verbose(env, "R%d pointer arithmetic on %s prohibited\n",
+			dst, reg_type_str[ptr_reg->type]);
 		return -EACCES;
+	default:
+		break;
 	}
 
 	/* In case of 'scalar += pointer', dst_reg inherits pointer type and id.
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index c7d25f23baf9..a90be44f61e0 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -3638,7 +3638,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END",
+		.errstr = "R3 pointer arithmetic on pkt_end",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -4896,7 +4896,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map1 = { 4 },
-		.errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL",
+		.errstr = "R4 pointer arithmetic on map_value_or_null",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
 	},
@@ -4917,7 +4917,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map1 = { 4 },
-		.errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL",
+		.errstr = "R4 pointer arithmetic on map_value_or_null",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
 	},
@@ -4938,7 +4938,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map1 = { 4 },
-		.errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL",
+		.errstr = "R4 pointer arithmetic on map_value_or_null",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
 	},
@@ -7253,7 +7253,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map_in_map = { 3 },
-		.errstr = "R1 pointer arithmetic on CONST_PTR_TO_MAP prohibited",
+		.errstr = "R1 pointer arithmetic on map_ptr prohibited",
 		.result = REJECT,
 	},
 	{
@@ -8927,7 +8927,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END",
+		.errstr = "R3 pointer arithmetic on pkt_end",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
@@ -8946,7 +8946,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END",
+		.errstr = "R3 pointer arithmetic on pkt_end",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
-- 
cgit v1.2.3


From 9d2be44a7f33d5ec4fbd3368317bcf5f404bb8f7 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@wand.net.nz>
Date: Tue, 2 Oct 2018 13:35:31 -0700
Subject: bpf: Reuse canonical string formatter for ctx errs

The array "reg_type_str" provides canonical formatting of register
types, however a couple of places would previously check whether a
register represented the context and write the name "context" directly.
An upcoming commit will add another pointer type to these statements, so
to provide more accurate error messages in the verifier, update these
error messages to use "reg_type_str" instead.

Signed-off-by: Joe Stringer <joe@wand.net.nz>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c                       |  7 +++----
 tools/testing/selftests/bpf/test_verifier.c | 10 +++++-----
 2 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index abf567200574..8b4e70eeced2 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1763,8 +1763,7 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
 	if (is_ctx_reg(env, insn->dst_reg) ||
 	    is_pkt_reg(env, insn->dst_reg)) {
 		verbose(env, "BPF_XADD stores into R%d %s is not allowed\n",
-			insn->dst_reg, is_ctx_reg(env, insn->dst_reg) ?
-			"context" : "packet");
+			insn->dst_reg, reg_type_str[insn->dst_reg]);
 		return -EACCES;
 	}
 
@@ -4871,8 +4870,8 @@ static int do_check(struct bpf_verifier_env *env)
 				return err;
 
 			if (is_ctx_reg(env, insn->dst_reg)) {
-				verbose(env, "BPF_ST stores into R%d context is not allowed\n",
-					insn->dst_reg);
+				verbose(env, "BPF_ST stores into R%d %s is not allowed\n",
+					insn->dst_reg, reg_type_str[insn->dst_reg]);
 				return -EACCES;
 			}
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index a90be44f61e0..6e0b3f148cdb 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -3276,7 +3276,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_1, offsetof(struct __sk_buff, mark), 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_ST stores into R1 context is not allowed",
+		.errstr = "BPF_ST stores into R1 inv is not allowed",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -3288,7 +3288,7 @@ static struct bpf_test tests[] = {
 				     BPF_REG_0, offsetof(struct __sk_buff, mark), 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_XADD stores into R1 context is not allowed",
+		.errstr = "BPF_XADD stores into R1 inv is not allowed",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -5266,7 +5266,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R2 leaks addr into mem",
 		.result_unpriv = REJECT,
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R1 context is not allowed",
+		.errstr = "BPF_XADD stores into R1 inv is not allowed",
 	},
 	{
 		"leak pointer into ctx 2",
@@ -5281,7 +5281,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R10 leaks addr into mem",
 		.result_unpriv = REJECT,
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R1 context is not allowed",
+		.errstr = "BPF_XADD stores into R1 inv is not allowed",
 	},
 	{
 		"leak pointer into ctx 3",
@@ -12230,7 +12230,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R2 packet",
+		.errstr = "BPF_XADD stores into R2 ctx",
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
 	{
-- 
cgit v1.2.3


From 6acc9b432e6714d72d7d77ec7c27f6f8358d0c71 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@wand.net.nz>
Date: Tue, 2 Oct 2018 13:35:36 -0700
Subject: bpf: Add helper to retrieve socket in BPF

This patch adds new BPF helper functions, bpf_sk_lookup_tcp() and
bpf_sk_lookup_udp() which allows BPF programs to find out if there is a
socket listening on this host, and returns a socket pointer which the
BPF program can then access to determine, for instance, whether to
forward or drop traffic. bpf_sk_lookup_xxx() may take a reference on the
socket, so when a BPF program makes use of this function, it must
subsequently pass the returned pointer into the newly added sk_release()
to return the reference.

By way of example, the following pseudocode would filter inbound
connections at XDP if there is no corresponding service listening for
the traffic:

  struct bpf_sock_tuple tuple;
  struct bpf_sock_ops *sk;

  populate_tuple(ctx, &tuple); // Extract the 5tuple from the packet
  sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof tuple, netns, 0);
  if (!sk) {
    // Couldn't find a socket listening for this traffic. Drop.
    return TC_ACT_SHOT;
  }
  bpf_sk_release(sk, 0);
  return TC_ACT_OK;

Signed-off-by: Joe Stringer <joe@wand.net.nz>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h                  |  93 +++++++++++++++++-
 kernel/bpf/verifier.c                     |   8 +-
 net/core/filter.c                         | 151 ++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h            |  93 +++++++++++++++++-
 tools/testing/selftests/bpf/bpf_helpers.h |  12 +++
 5 files changed, 354 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e2070d819e04..f9187b41dff6 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2144,6 +2144,77 @@ union bpf_attr {
  *		request in the skb.
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ *	Description
+ *		Look for TCP socket matching *tuple*, optionally in a child
+ *		network namespace *netns*. The return value must be checked,
+ *		and if non-NULL, released via **bpf_sk_release**\ ().
+ *
+ *		The *ctx* should point to the context of the program, such as
+ *		the skb or socket (depending on the hook in use). This is used
+ *		to determine the base network namespace for the lookup.
+ *
+ *		*tuple_size* must be one of:
+ *
+ *		**sizeof**\ (*tuple*\ **->ipv4**)
+ *			Look for an IPv4 socket.
+ *		**sizeof**\ (*tuple*\ **->ipv6**)
+ *			Look for an IPv6 socket.
+ *
+ *		If the *netns* is zero, then the socket lookup table in the
+ *		netns associated with the *ctx* will be used. For the TC hooks,
+ *		this in the netns of the device in the skb. For socket hooks,
+ *		this in the netns of the socket. If *netns* is non-zero, then
+ *		it specifies the ID of the netns relative to the netns
+ *		associated with the *ctx*.
+ *
+ *		All values for *flags* are reserved for future usage, and must
+ *		be left at zero.
+ *
+ *		This helper is available only if the kernel was compiled with
+ *		**CONFIG_NET** configuration option.
+ *	Return
+ *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *
+ * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ *	Description
+ *		Look for UDP socket matching *tuple*, optionally in a child
+ *		network namespace *netns*. The return value must be checked,
+ *		and if non-NULL, released via **bpf_sk_release**\ ().
+ *
+ *		The *ctx* should point to the context of the program, such as
+ *		the skb or socket (depending on the hook in use). This is used
+ *		to determine the base network namespace for the lookup.
+ *
+ *		*tuple_size* must be one of:
+ *
+ *		**sizeof**\ (*tuple*\ **->ipv4**)
+ *			Look for an IPv4 socket.
+ *		**sizeof**\ (*tuple*\ **->ipv6**)
+ *			Look for an IPv6 socket.
+ *
+ *		If the *netns* is zero, then the socket lookup table in the
+ *		netns associated with the *ctx* will be used. For the TC hooks,
+ *		this in the netns of the device in the skb. For socket hooks,
+ *		this in the netns of the socket. If *netns* is non-zero, then
+ *		it specifies the ID of the netns relative to the netns
+ *		associated with the *ctx*.
+ *
+ *		All values for *flags* are reserved for future usage, and must
+ *		be left at zero.
+ *
+ *		This helper is available only if the kernel was compiled with
+ *		**CONFIG_NET** configuration option.
+ *	Return
+ *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *
+ * int bpf_sk_release(struct bpf_sock *sk)
+ *	Description
+ *		Release the reference held by *sock*. *sock* must be a non-NULL
+ *		pointer that was returned from bpf_sk_lookup_xxx\ ().
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2229,7 +2300,10 @@ union bpf_attr {
 	FN(get_current_cgroup_id),	\
 	FN(get_local_storage),		\
 	FN(sk_select_reuseport),	\
-	FN(skb_ancestor_cgroup_id),
+	FN(skb_ancestor_cgroup_id),	\
+	FN(sk_lookup_tcp),		\
+	FN(sk_lookup_udp),		\
+	FN(sk_release),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2399,6 +2473,23 @@ struct bpf_sock {
 				 */
 };
 
+struct bpf_sock_tuple {
+	union {
+		struct {
+			__be32 saddr;
+			__be32 daddr;
+			__be16 sport;
+			__be16 dport;
+		} ipv4;
+		struct {
+			__be32 saddr[4];
+			__be32 daddr[4];
+			__be16 sport;
+			__be16 dport;
+		} ipv6;
+	};
+};
+
 #define XDP_PACKET_HEADROOM 256
 
 /* User return codes for XDP prog type.
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index cd0d8bc00bd1..73c81bef6ae8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -153,6 +153,12 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
  * PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL becomes PTR_TO_SOCKET when the type
  * passes through a NULL-check conditional. For the branch wherein the state is
  * changed to CONST_IMM, the verifier releases the reference.
+ *
+ * For each helper function that allocates a reference, such as
+ * bpf_sk_lookup_tcp(), there is a corresponding release function, such as
+ * bpf_sk_release(). When a reference type passes into the release function,
+ * the verifier also releases the reference. If any unchecked or unreleased
+ * reference remains at the end of the program, the verifier rejects it.
  */
 
 /* verifier_state + insn_idx are pushed to stack when branch is encountered */
@@ -300,7 +306,7 @@ static bool arg_type_is_refcounted(enum bpf_arg_type type)
  */
 static bool is_release_function(enum bpf_func_id func_id)
 {
-	return false;
+	return func_id == BPF_FUNC_sk_release;
 }
 
 /* string representation of 'enum bpf_reg_type' */
diff --git a/net/core/filter.c b/net/core/filter.c
index b2cb186252e4..591c698bc517 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -58,13 +58,17 @@
 #include <net/busy_poll.h>
 #include <net/tcp.h>
 #include <net/xfrm.h>
+#include <net/udp.h>
 #include <linux/bpf_trace.h>
 #include <net/xdp_sock.h>
 #include <linux/inetdevice.h>
+#include <net/inet_hashtables.h>
+#include <net/inet6_hashtables.h>
 #include <net/ip_fib.h>
 #include <net/flow.h>
 #include <net/arp.h>
 #include <net/ipv6.h>
+#include <net/net_namespace.h>
 #include <linux/seg6_local.h>
 #include <net/seg6.h>
 #include <net/seg6_local.h>
@@ -4813,6 +4817,141 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
 };
 #endif /* CONFIG_IPV6_SEG6_BPF */
 
+struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
+		       struct sk_buff *skb, u8 family, u8 proto)
+{
+	int dif = skb->dev->ifindex;
+	bool refcounted = false;
+	struct sock *sk = NULL;
+
+	if (family == AF_INET) {
+		__be32 src4 = tuple->ipv4.saddr;
+		__be32 dst4 = tuple->ipv4.daddr;
+		int sdif = inet_sdif(skb);
+
+		if (proto == IPPROTO_TCP)
+			sk = __inet_lookup(net, &tcp_hashinfo, skb, 0,
+					   src4, tuple->ipv4.sport,
+					   dst4, tuple->ipv4.dport,
+					   dif, sdif, &refcounted);
+		else
+			sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport,
+					       dst4, tuple->ipv4.dport,
+					       dif, sdif, &udp_table, skb);
+#if IS_ENABLED(CONFIG_IPV6)
+	} else {
+		struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr;
+		struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr;
+		int sdif = inet6_sdif(skb);
+
+		if (proto == IPPROTO_TCP)
+			sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0,
+					    src6, tuple->ipv6.sport,
+					    dst6, tuple->ipv6.dport,
+					    dif, sdif, &refcounted);
+		else
+			sk = __udp6_lib_lookup(net, src6, tuple->ipv6.sport,
+					       dst6, tuple->ipv6.dport,
+					       dif, sdif, &udp_table, skb);
+#endif
+	}
+
+	if (unlikely(sk && !refcounted && !sock_flag(sk, SOCK_RCU_FREE))) {
+		WARN_ONCE(1, "Found non-RCU, unreferenced socket!");
+		sk = NULL;
+	}
+	return sk;
+}
+
+/* bpf_sk_lookup performs the core lookup for different types of sockets,
+ * taking a reference on the socket if it doesn't have the flag SOCK_RCU_FREE.
+ * Returns the socket as an 'unsigned long' to simplify the casting in the
+ * callers to satisfy BPF_CALL declarations.
+ */
+static unsigned long
+bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+	      u8 proto, u64 netns_id, u64 flags)
+{
+	struct net *caller_net;
+	struct sock *sk = NULL;
+	u8 family = AF_UNSPEC;
+	struct net *net;
+
+	family = len == sizeof(tuple->ipv4) ? AF_INET : AF_INET6;
+	if (unlikely(family == AF_UNSPEC || netns_id > U32_MAX || flags))
+		goto out;
+
+	if (skb->dev)
+		caller_net = dev_net(skb->dev);
+	else
+		caller_net = sock_net(skb->sk);
+	if (netns_id) {
+		net = get_net_ns_by_id(caller_net, netns_id);
+		if (unlikely(!net))
+			goto out;
+		sk = sk_lookup(net, tuple, skb, family, proto);
+		put_net(net);
+	} else {
+		net = caller_net;
+		sk = sk_lookup(net, tuple, skb, family, proto);
+	}
+
+	if (sk)
+		sk = sk_to_full_sk(sk);
+out:
+	return (unsigned long) sk;
+}
+
+BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb,
+	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+	return bpf_sk_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = {
+	.func		= bpf_sk_lookup_tcp,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_5(bpf_sk_lookup_udp, struct sk_buff *, skb,
+	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+	return bpf_sk_lookup(skb, tuple, len, IPPROTO_UDP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
+	.func		= bpf_sk_lookup_udp,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_1(bpf_sk_release, struct sock *, sk)
+{
+	if (!sock_flag(sk, SOCK_RCU_FREE))
+		sock_gen_put(sk);
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_sk_release_proto = {
+	.func		= bpf_sk_release,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_SOCKET,
+};
+
 bool bpf_helper_changes_pkt_data(void *func)
 {
 	if (func == bpf_skb_vlan_push ||
@@ -5019,6 +5158,12 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_ancestor_cgroup_id:
 		return &bpf_skb_ancestor_cgroup_id_proto;
 #endif
+	case BPF_FUNC_sk_lookup_tcp:
+		return &bpf_sk_lookup_tcp_proto;
+	case BPF_FUNC_sk_lookup_udp:
+		return &bpf_sk_lookup_udp_proto;
+	case BPF_FUNC_sk_release:
+		return &bpf_sk_release_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -5119,6 +5264,12 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_redirect_hash_proto;
 	case BPF_FUNC_get_local_storage:
 		return &bpf_get_local_storage_proto;
+	case BPF_FUNC_sk_lookup_tcp:
+		return &bpf_sk_lookup_tcp_proto;
+	case BPF_FUNC_sk_lookup_udp:
+		return &bpf_sk_lookup_udp_proto;
+	case BPF_FUNC_sk_release:
+		return &bpf_sk_release_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e2070d819e04..f9187b41dff6 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2144,6 +2144,77 @@ union bpf_attr {
  *		request in the skb.
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ *	Description
+ *		Look for TCP socket matching *tuple*, optionally in a child
+ *		network namespace *netns*. The return value must be checked,
+ *		and if non-NULL, released via **bpf_sk_release**\ ().
+ *
+ *		The *ctx* should point to the context of the program, such as
+ *		the skb or socket (depending on the hook in use). This is used
+ *		to determine the base network namespace for the lookup.
+ *
+ *		*tuple_size* must be one of:
+ *
+ *		**sizeof**\ (*tuple*\ **->ipv4**)
+ *			Look for an IPv4 socket.
+ *		**sizeof**\ (*tuple*\ **->ipv6**)
+ *			Look for an IPv6 socket.
+ *
+ *		If the *netns* is zero, then the socket lookup table in the
+ *		netns associated with the *ctx* will be used. For the TC hooks,
+ *		this in the netns of the device in the skb. For socket hooks,
+ *		this in the netns of the socket. If *netns* is non-zero, then
+ *		it specifies the ID of the netns relative to the netns
+ *		associated with the *ctx*.
+ *
+ *		All values for *flags* are reserved for future usage, and must
+ *		be left at zero.
+ *
+ *		This helper is available only if the kernel was compiled with
+ *		**CONFIG_NET** configuration option.
+ *	Return
+ *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *
+ * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ *	Description
+ *		Look for UDP socket matching *tuple*, optionally in a child
+ *		network namespace *netns*. The return value must be checked,
+ *		and if non-NULL, released via **bpf_sk_release**\ ().
+ *
+ *		The *ctx* should point to the context of the program, such as
+ *		the skb or socket (depending on the hook in use). This is used
+ *		to determine the base network namespace for the lookup.
+ *
+ *		*tuple_size* must be one of:
+ *
+ *		**sizeof**\ (*tuple*\ **->ipv4**)
+ *			Look for an IPv4 socket.
+ *		**sizeof**\ (*tuple*\ **->ipv6**)
+ *			Look for an IPv6 socket.
+ *
+ *		If the *netns* is zero, then the socket lookup table in the
+ *		netns associated with the *ctx* will be used. For the TC hooks,
+ *		this in the netns of the device in the skb. For socket hooks,
+ *		this in the netns of the socket. If *netns* is non-zero, then
+ *		it specifies the ID of the netns relative to the netns
+ *		associated with the *ctx*.
+ *
+ *		All values for *flags* are reserved for future usage, and must
+ *		be left at zero.
+ *
+ *		This helper is available only if the kernel was compiled with
+ *		**CONFIG_NET** configuration option.
+ *	Return
+ *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *
+ * int bpf_sk_release(struct bpf_sock *sk)
+ *	Description
+ *		Release the reference held by *sock*. *sock* must be a non-NULL
+ *		pointer that was returned from bpf_sk_lookup_xxx\ ().
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2229,7 +2300,10 @@ union bpf_attr {
 	FN(get_current_cgroup_id),	\
 	FN(get_local_storage),		\
 	FN(sk_select_reuseport),	\
-	FN(skb_ancestor_cgroup_id),
+	FN(skb_ancestor_cgroup_id),	\
+	FN(sk_lookup_tcp),		\
+	FN(sk_lookup_udp),		\
+	FN(sk_release),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2399,6 +2473,23 @@ struct bpf_sock {
 				 */
 };
 
+struct bpf_sock_tuple {
+	union {
+		struct {
+			__be32 saddr;
+			__be32 daddr;
+			__be16 sport;
+			__be16 dport;
+		} ipv4;
+		struct {
+			__be32 saddr[4];
+			__be32 daddr[4];
+			__be16 sport;
+			__be16 dport;
+		} ipv6;
+	};
+};
+
 #define XDP_PACKET_HEADROOM 256
 
 /* User return codes for XDP prog type.
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index e4be7730222d..1d407b3494f9 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -143,6 +143,18 @@ static unsigned long long (*bpf_skb_cgroup_id)(void *ctx) =
 	(void *) BPF_FUNC_skb_cgroup_id;
 static unsigned long long (*bpf_skb_ancestor_cgroup_id)(void *ctx, int level) =
 	(void *) BPF_FUNC_skb_ancestor_cgroup_id;
+static struct bpf_sock *(*bpf_sk_lookup_tcp)(void *ctx,
+					     struct bpf_sock_tuple *tuple,
+					     int size, unsigned int netns_id,
+					     unsigned long long flags) =
+	(void *) BPF_FUNC_sk_lookup_tcp;
+static struct bpf_sock *(*bpf_sk_lookup_udp)(void *ctx,
+					     struct bpf_sock_tuple *tuple,
+					     int size, unsigned int netns_id,
+					     unsigned long long flags) =
+	(void *) BPF_FUNC_sk_lookup_udp;
+static int (*bpf_sk_release)(struct bpf_sock *sk) =
+	(void *) BPF_FUNC_sk_release;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
-- 
cgit v1.2.3


From 0c586079f852187d19fea60c9a4981ad29e22ba8 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@wand.net.nz>
Date: Tue, 2 Oct 2018 13:35:37 -0700
Subject: selftests/bpf: Generalize dummy program types

Don't hardcode the dummy program types to SOCKET_FILTER type, as this
prevents testing bpf_tail_call in conjunction with other program types.
Instead, use the program type specified in the test case.

Signed-off-by: Joe Stringer <joe@wand.net.nz>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 31 ++++++++++++++++-------------
 1 file changed, 17 insertions(+), 14 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 6e0b3f148cdb..163fd1c0062c 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -12652,18 +12652,18 @@ static int create_map(uint32_t type, uint32_t size_key,
 	return fd;
 }
 
-static int create_prog_dummy1(void)
+static int create_prog_dummy1(enum bpf_map_type prog_type)
 {
 	struct bpf_insn prog[] = {
 		BPF_MOV64_IMM(BPF_REG_0, 42),
 		BPF_EXIT_INSN(),
 	};
 
-	return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog,
+	return bpf_load_program(prog_type, prog,
 				ARRAY_SIZE(prog), "GPL", 0, NULL, 0);
 }
 
-static int create_prog_dummy2(int mfd, int idx)
+static int create_prog_dummy2(enum bpf_map_type prog_type, int mfd, int idx)
 {
 	struct bpf_insn prog[] = {
 		BPF_MOV64_IMM(BPF_REG_3, idx),
@@ -12674,11 +12674,12 @@ static int create_prog_dummy2(int mfd, int idx)
 		BPF_EXIT_INSN(),
 	};
 
-	return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog,
+	return bpf_load_program(prog_type, prog,
 				ARRAY_SIZE(prog), "GPL", 0, NULL, 0);
 }
 
-static int create_prog_array(uint32_t max_elem, int p1key)
+static int create_prog_array(enum bpf_map_type prog_type, uint32_t max_elem,
+			     int p1key)
 {
 	int p2key = 1;
 	int mfd, p1fd, p2fd;
@@ -12690,8 +12691,8 @@ static int create_prog_array(uint32_t max_elem, int p1key)
 		return -1;
 	}
 
-	p1fd = create_prog_dummy1();
-	p2fd = create_prog_dummy2(mfd, p2key);
+	p1fd = create_prog_dummy1(prog_type);
+	p2fd = create_prog_dummy2(prog_type, mfd, p2key);
 	if (p1fd < 0 || p2fd < 0)
 		goto out;
 	if (bpf_map_update_elem(mfd, &p1key, &p1fd, BPF_ANY) < 0)
@@ -12748,8 +12749,8 @@ static int create_cgroup_storage(bool percpu)
 
 static char bpf_vlog[UINT_MAX >> 8];
 
-static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
-			  int *map_fds)
+static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type,
+			  struct bpf_insn *prog, int *map_fds)
 {
 	int *fixup_map1 = test->fixup_map1;
 	int *fixup_map2 = test->fixup_map2;
@@ -12805,7 +12806,7 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 	}
 
 	if (*fixup_prog1) {
-		map_fds[4] = create_prog_array(4, 0);
+		map_fds[4] = create_prog_array(prog_type, 4, 0);
 		do {
 			prog[*fixup_prog1].imm = map_fds[4];
 			fixup_prog1++;
@@ -12813,7 +12814,7 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 	}
 
 	if (*fixup_prog2) {
-		map_fds[5] = create_prog_array(8, 7);
+		map_fds[5] = create_prog_array(prog_type, 8, 7);
 		do {
 			prog[*fixup_prog2].imm = map_fds[5];
 			fixup_prog2++;
@@ -12859,11 +12860,13 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	for (i = 0; i < MAX_NR_MAPS; i++)
 		map_fds[i] = -1;
 
-	do_test_fixup(test, prog, map_fds);
+	if (!prog_type)
+		prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	do_test_fixup(test, prog_type, prog, map_fds);
 	prog_len = probe_filter_length(prog);
 
-	fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
-				     prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT,
+	fd_prog = bpf_verify_program(prog_type, prog, prog_len,
+				     test->flags & F_LOAD_WITH_STRICT_ALIGNMENT,
 				     "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 1);
 
 	expected_ret = unpriv && test->result_unpriv != UNDEF ?
-- 
cgit v1.2.3


From b584ab8840fdc17f0d75ac62510396b8f657ed8f Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@wand.net.nz>
Date: Tue, 2 Oct 2018 13:35:38 -0700
Subject: selftests/bpf: Add tests for reference tracking

reference tracking: leak potential reference
reference tracking: leak potential reference on stack
reference tracking: leak potential reference on stack 2
reference tracking: zero potential reference
reference tracking: copy and zero potential references
reference tracking: release reference without check
reference tracking: release reference
reference tracking: release reference twice
reference tracking: release reference twice inside branch
reference tracking: alloc, check, free in one subbranch
reference tracking: alloc, check, free in both subbranches
reference tracking in call: free reference in subprog
reference tracking in call: free reference in subprog and outside
reference tracking in call: alloc & leak reference in subprog
reference tracking in call: alloc in subprog, release outside
reference tracking in call: sk_ptr leak into caller stack
reference tracking in call: sk_ptr spill into caller stack
reference tracking: allow LD_ABS
reference tracking: forbid LD_ABS while holding reference
reference tracking: allow LD_IND
reference tracking: forbid LD_IND while holding reference
reference tracking: check reference or tail call
reference tracking: release reference then tail call
reference tracking: leak possible reference over tail call
reference tracking: leak checked reference over tail call
reference tracking: mangle and release sock_or_null
reference tracking: mangle and release sock
reference tracking: access member
reference tracking: write to member
reference tracking: invalid 64-bit access of member
reference tracking: access after release
reference tracking: direct access for lookup
unpriv: spill/fill of different pointers stx - ctx and sock
unpriv: spill/fill of different pointers stx - leak sock
unpriv: spill/fill of different pointers stx - sock and ctx (read)
unpriv: spill/fill of different pointers stx - sock and ctx (write)

Signed-off-by: Joe Stringer <joe@wand.net.nz>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 759 ++++++++++++++++++++++++++++
 1 file changed, 759 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 163fd1c0062c..bc9cd8537467 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -3,6 +3,7 @@
  *
  * Copyright (c) 2014 PLUMgrid, http://plumgrid.com
  * Copyright (c) 2017 Facebook
+ * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -178,6 +179,24 @@ static void bpf_fill_rand_ld_dw(struct bpf_test *self)
 	self->retval = (uint32_t)res;
 }
 
+/* BPF_SK_LOOKUP contains 13 instructions, if you need to fix up maps */
+#define BPF_SK_LOOKUP							\
+	/* struct bpf_sock_tuple tuple = {} */				\
+	BPF_MOV64_IMM(BPF_REG_2, 0),					\
+	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8),			\
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -16),		\
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -24),		\
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -32),		\
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -40),		\
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -48),		\
+	/* sk = sk_lookup_tcp(ctx, &tuple, sizeof tuple, 0, 0) */	\
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),				\
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -48),				\
+	BPF_MOV64_IMM(BPF_REG_3, sizeof(struct bpf_sock_tuple)),	\
+	BPF_MOV64_IMM(BPF_REG_4, 0),					\
+	BPF_MOV64_IMM(BPF_REG_5, 0),					\
+	BPF_EMIT_CALL(BPF_FUNC_sk_lookup_tcp)
+
 static struct bpf_test tests[] = {
 	{
 		"add+sub+mul",
@@ -2707,6 +2726,137 @@ static struct bpf_test tests[] = {
 		.errstr = "same insn cannot be used with different pointers",
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
+	{
+		"unpriv: spill/fill of different pointers stx - ctx and sock",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
+			/* struct bpf_sock *sock = bpf_sock_lookup(...); */
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			/* u64 foo; */
+			/* void *target = &foo; */
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+			/* if (skb == NULL) *target = sock; */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
+			/* else *target = skb; */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+			/* struct __sk_buff *skb = *target; */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
+			/* skb->mark = 42; */
+			BPF_MOV64_IMM(BPF_REG_3, 42),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
+				    offsetof(struct __sk_buff, mark)),
+			/* if (sk) bpf_sk_release(sk) */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+				BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "type=ctx expected=sock",
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"unpriv: spill/fill of different pointers stx - leak sock",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
+			/* struct bpf_sock *sock = bpf_sock_lookup(...); */
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			/* u64 foo; */
+			/* void *target = &foo; */
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+			/* if (skb == NULL) *target = sock; */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
+			/* else *target = skb; */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+			/* struct __sk_buff *skb = *target; */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
+			/* skb->mark = 42; */
+			BPF_MOV64_IMM(BPF_REG_3, 42),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		//.errstr = "same insn cannot be used with different pointers",
+		.errstr = "Unreleased reference",
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"unpriv: spill/fill of different pointers stx - sock and ctx (read)",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
+			/* struct bpf_sock *sock = bpf_sock_lookup(...); */
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			/* u64 foo; */
+			/* void *target = &foo; */
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+			/* if (skb) *target = skb */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+			/* else *target = sock */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
+			/* struct bpf_sock *sk = *target; */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
+			/* if (sk) u32 foo = sk->mark; bpf_sk_release(sk); */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 2),
+				BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+					    offsetof(struct bpf_sock, mark)),
+				BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "same insn cannot be used with different pointers",
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"unpriv: spill/fill of different pointers stx - sock and ctx (write)",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
+			/* struct bpf_sock *sock = bpf_sock_lookup(...); */
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+			/* u64 foo; */
+			/* void *target = &foo; */
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+			/* if (skb) *target = skb */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+			/* else *target = sock */
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
+				BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
+			/* struct bpf_sock *sk = *target; */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
+			/* if (sk) sk->mark = 42; bpf_sk_release(sk); */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3),
+				BPF_MOV64_IMM(BPF_REG_3, 42),
+				BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
+					    offsetof(struct bpf_sock, mark)),
+				BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		//.errstr = "same insn cannot be used with different pointers",
+		.errstr = "cannot write into socket",
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
 	{
 		"unpriv: spill/fill of different pointers ldx",
 		.insns = {
@@ -12557,6 +12707,214 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
 	},
+	{
+		"reference tracking: leak potential reference",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), /* leak reference */
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: leak potential reference on stack",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: leak potential reference on stack 2",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: zero potential reference",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_IMM(BPF_REG_0, 0), /* leak reference */
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: copy and zero potential references",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_7, 0), /* leak reference */
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: release reference without check",
+		.insns = {
+			BPF_SK_LOOKUP,
+			/* reference in r0 may be NULL */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "type=sock_or_null expected=sock",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: release reference",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: release reference 2",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+			BPF_EXIT_INSN(),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: release reference twice",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "type=inv expected=sock",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: release reference twice inside branch",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), /* goto end */
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "type=inv expected=sock",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: alloc, check, free in one subbranch",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 16),
+			/* if (offsetof(skb, mark) > data_len) exit; */
+			BPF_JMP_REG(BPF_JLE, BPF_REG_0, BPF_REG_3, 1),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_2,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_SK_LOOKUP,
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 1), /* mark == 0? */
+			/* Leak reference in R0 */
+			BPF_EXIT_INSN(),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), /* sk NULL? */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: alloc, check, free in both subbranches",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 16),
+			/* if (offsetof(skb, mark) > data_len) exit; */
+			BPF_JMP_REG(BPF_JLE, BPF_REG_0, BPF_REG_3, 1),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_2,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_SK_LOOKUP,
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 4), /* mark == 0? */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), /* sk NULL? */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), /* sk NULL? */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking in call: free reference in subprog",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), /* unchecked reference */
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_2, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
 	{
 		"pass modified ctx pointer to helper, 1",
 		.insns = {
@@ -12627,6 +12985,407 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
 	},
+	{
+		"reference tracking in call: free reference in subprog and outside",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), /* unchecked reference */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_2, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "type=inv expected=sock",
+		.result = REJECT,
+	},
+	{
+		"reference tracking in call: alloc & leak reference in subprog",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_4),
+			BPF_SK_LOOKUP,
+			/* spill unchecked sk_ptr into stack of caller */
+			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking in call: alloc in subprog, release outside",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_SK_LOOKUP,
+			BPF_EXIT_INSN(), /* return sk */
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.retval = POINTER_VALUE,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking in call: sk_ptr leak into caller stack",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5),
+			/* spill unchecked sk_ptr into stack of caller */
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_5, 0),
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 2 */
+			BPF_SK_LOOKUP,
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "Unreleased reference",
+		.result = REJECT,
+	},
+	{
+		"reference tracking in call: sk_ptr spill into caller stack",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+
+			/* subprog 1 */
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 8),
+			/* spill unchecked sk_ptr into stack of caller */
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_5, 0),
+			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			/* now the sk_ptr is verified, free the reference */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_4, 0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+
+			/* subprog 2 */
+			BPF_SK_LOOKUP,
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: allow LD_ABS",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_LD_ABS(BPF_B, 0),
+			BPF_LD_ABS(BPF_H, 0),
+			BPF_LD_ABS(BPF_W, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: forbid LD_ABS while holding reference",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			BPF_LD_ABS(BPF_B, 0),
+			BPF_LD_ABS(BPF_H, 0),
+			BPF_LD_ABS(BPF_W, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "BPF_LD_[ABS|IND] cannot be mixed with socket references",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: allow LD_IND",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_MOV64_IMM(BPF_REG_7, 1),
+			BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"reference tracking: forbid LD_IND while holding reference",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_7, 1),
+			BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_4),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "BPF_LD_[ABS|IND] cannot be mixed with socket references",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: check reference or tail call",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			/* if (sk) bpf_sk_release() */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 7),
+			/* bpf_tail_call() */
+			BPF_MOV64_IMM(BPF_REG_3, 2),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_tail_call),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog1 = { 17 },
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: release reference then tail call",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
+			BPF_SK_LOOKUP,
+			/* if (sk) bpf_sk_release() */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			/* bpf_tail_call() */
+			BPF_MOV64_IMM(BPF_REG_3, 2),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_tail_call),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog1 = { 18 },
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: leak possible reference over tail call",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
+			/* Look up socket and store in REG_6 */
+			BPF_SK_LOOKUP,
+			/* bpf_tail_call() */
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_3, 2),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_tail_call),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			/* if (sk) bpf_sk_release() */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog1 = { 16 },
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "tail_call would lead to reference leak",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: leak checked reference over tail call",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
+			/* Look up socket and store in REG_6 */
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			/* if (!sk) goto end */
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+			/* bpf_tail_call() */
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_tail_call),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog1 = { 17 },
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "tail_call would lead to reference leak",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: mangle and release sock_or_null",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 5),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "R1 pointer arithmetic on sock_or_null prohibited",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: mangle and release sock",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 5),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "R1 pointer arithmetic on sock prohibited",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: access member",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_0, 4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"reference tracking: write to member",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_LD_IMM64(BPF_REG_2, 42),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_2,
+				    offsetof(struct bpf_sock, mark)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_LD_IMM64(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "cannot write into socket",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: invalid 64-bit access of member",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "invalid bpf_sock access off=0 size=8",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: access after release",
+		.insns = {
+			BPF_SK_LOOKUP,
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.errstr = "!read_ok",
+		.result = REJECT,
+	},
+	{
+		"reference tracking: direct access for lookup",
+		.insns = {
+			/* Check that the packet is at least 64B long */
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 64),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 9),
+			/* sk = sk_lookup_tcp(ctx, skb->data, ...) */
+			BPF_MOV64_IMM(BPF_REG_3, sizeof(struct bpf_sock_tuple)),
+			BPF_MOV64_IMM(BPF_REG_4, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_EMIT_CALL(BPF_FUNC_sk_lookup_tcp),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_0, 4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_EMIT_CALL(BPF_FUNC_sk_release),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
-- 
cgit v1.2.3


From 29cd77f41620dca22bdee092217c16b49ece8915 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@wand.net.nz>
Date: Tue, 2 Oct 2018 13:35:39 -0700
Subject: libbpf: Support loading individual progs

Allow the individual program load to be invoked. This will help with
testing, where a single ELF may contain several sections, some of which
denote subprograms that are expected to fail verification, along with
some which are expected to pass verification. By allowing programs to be
iterated and individually loaded, each program can be independently
checked against its expected verification result.

Signed-off-by: Joe Stringer <joe@wand.net.nz>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 4 ++--
 tools/lib/bpf/libbpf.h | 3 +++
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 425d5ca45c97..9e68fd9fcfca 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -228,7 +228,7 @@ struct bpf_object {
 };
 #define obj_elf_valid(o)	((o)->efile.elf)
 
-static void bpf_program__unload(struct bpf_program *prog)
+void bpf_program__unload(struct bpf_program *prog)
 {
 	int i;
 
@@ -1375,7 +1375,7 @@ out:
 	return ret;
 }
 
-static int
+int
 bpf_program__load(struct bpf_program *prog,
 		  char *license, u32 kern_version)
 {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 511c1294dcbf..2ed24d3f80b3 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -128,10 +128,13 @@ void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex);
 
 const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
 
+int bpf_program__load(struct bpf_program *prog, char *license,
+		      u32 kern_version);
 int bpf_program__fd(struct bpf_program *prog);
 int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 			      int instance);
 int bpf_program__pin(struct bpf_program *prog, const char *path);
+void bpf_program__unload(struct bpf_program *prog);
 
 struct bpf_insn;
 
-- 
cgit v1.2.3


From de375f4e91e3074a09ad337ac4b32a2f21c24d96 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@wand.net.nz>
Date: Tue, 2 Oct 2018 13:35:40 -0700
Subject: selftests/bpf: Add C tests for reference tracking

Add some tests that demonstrate and test the balanced lookup/free
nature of socket lookup. Section names that start with "fail" represent
programs that are expected to fail verification; all others should
succeed.

Signed-off-by: Joe Stringer <joe@wand.net.nz>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile              |   2 +-
 tools/testing/selftests/bpf/test_progs.c          |  38 +++++
 tools/testing/selftests/bpf/test_sk_lookup_kern.c | 180 ++++++++++++++++++++++
 3 files changed, 219 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/test_sk_lookup_kern.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index f802de526f57..1381ab81099c 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -36,7 +36,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
 	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
-	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o
+	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o test_sk_lookup_kern.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 63a671803ed6..e8becca9c521 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1698,6 +1698,43 @@ static void test_task_fd_query_tp(void)
 				   "sys_enter_read");
 }
 
+static void test_reference_tracking()
+{
+	const char *file = "./test_sk_lookup_kern.o";
+	struct bpf_object *obj;
+	struct bpf_program *prog;
+	__u32 duration;
+	int err = 0;
+
+	obj = bpf_object__open(file);
+	if (IS_ERR(obj)) {
+		error_cnt++;
+		return;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		const char *title;
+
+		/* Ignore .text sections */
+		title = bpf_program__title(prog, false);
+		if (strstr(title, ".text") != NULL)
+			continue;
+
+		bpf_program__set_type(prog, BPF_PROG_TYPE_SCHED_CLS);
+
+		/* Expect verifier failure if test name has 'fail' */
+		if (strstr(title, "fail") != NULL) {
+			libbpf_set_print(NULL, NULL, NULL);
+			err = !bpf_program__load(prog, "GPL", 0);
+			libbpf_set_print(printf, printf, NULL);
+		} else {
+			err = bpf_program__load(prog, "GPL", 0);
+		}
+		CHECK(err, title, "\n");
+	}
+	bpf_object__close(obj);
+}
+
 int main(void)
 {
 	jit_enabled = is_jit_enabled();
@@ -1719,6 +1756,7 @@ int main(void)
 	test_get_stack_raw_tp();
 	test_task_fd_query_rawtp();
 	test_task_fd_query_tp();
+	test_reference_tracking();
 
 	printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
 	return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
diff --git a/tools/testing/selftests/bpf/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/test_sk_lookup_kern.c
new file mode 100644
index 000000000000..b745bdc08c2b
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_sk_lookup_kern.c
@@ -0,0 +1,180 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
+
+#include <stddef.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/pkt_cls.h>
+#include <linux/tcp.h>
+#include <sys/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
+
+/* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */
+static struct bpf_sock_tuple *get_tuple(void *data, __u64 nh_off,
+					void *data_end, __u16 eth_proto,
+					bool *ipv4)
+{
+	struct bpf_sock_tuple *result;
+	__u8 proto = 0;
+	__u64 ihl_len;
+
+	if (eth_proto == bpf_htons(ETH_P_IP)) {
+		struct iphdr *iph = (struct iphdr *)(data + nh_off);
+
+		if (iph + 1 > data_end)
+			return NULL;
+		ihl_len = iph->ihl * 4;
+		proto = iph->protocol;
+		*ipv4 = true;
+		result = (struct bpf_sock_tuple *)&iph->saddr;
+	} else if (eth_proto == bpf_htons(ETH_P_IPV6)) {
+		struct ipv6hdr *ip6h = (struct ipv6hdr *)(data + nh_off);
+
+		if (ip6h + 1 > data_end)
+			return NULL;
+		ihl_len = sizeof(*ip6h);
+		proto = ip6h->nexthdr;
+		*ipv4 = true;
+		result = (struct bpf_sock_tuple *)&ip6h->saddr;
+	}
+
+	if (data + nh_off + ihl_len > data_end || proto != IPPROTO_TCP)
+		return NULL;
+
+	return result;
+}
+
+SEC("sk_lookup_success")
+int bpf_sk_lookup_test0(struct __sk_buff *skb)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	struct ethhdr *eth = (struct ethhdr *)(data);
+	struct bpf_sock_tuple *tuple;
+	struct bpf_sock *sk;
+	size_t tuple_len;
+	bool ipv4;
+
+	if (eth + 1 > data_end)
+		return TC_ACT_SHOT;
+
+	tuple = get_tuple(data, sizeof(*eth), data_end, eth->h_proto, &ipv4);
+	if (!tuple || tuple + sizeof *tuple > data_end)
+		return TC_ACT_SHOT;
+
+	tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6);
+	sk = bpf_sk_lookup_tcp(skb, tuple, tuple_len, 0, 0);
+	if (sk)
+		bpf_sk_release(sk);
+	return sk ? TC_ACT_OK : TC_ACT_UNSPEC;
+}
+
+SEC("sk_lookup_success_simple")
+int bpf_sk_lookup_test1(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	if (sk)
+		bpf_sk_release(sk);
+	return 0;
+}
+
+SEC("fail_use_after_free")
+int bpf_sk_lookup_uaf(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+	__u32 family = 0;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	if (sk) {
+		bpf_sk_release(sk);
+		family = sk->family;
+	}
+	return family;
+}
+
+SEC("fail_modify_sk_pointer")
+int bpf_sk_lookup_modptr(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+	__u32 family;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	if (sk) {
+		sk += 1;
+		bpf_sk_release(sk);
+	}
+	return 0;
+}
+
+SEC("fail_modify_sk_or_null_pointer")
+int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+	__u32 family;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	sk += 1;
+	if (sk)
+		bpf_sk_release(sk);
+	return 0;
+}
+
+SEC("fail_no_release")
+int bpf_sk_lookup_test2(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+
+	bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	return 0;
+}
+
+SEC("fail_release_twice")
+int bpf_sk_lookup_test3(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	bpf_sk_release(sk);
+	bpf_sk_release(sk);
+	return 0;
+}
+
+SEC("fail_release_unchecked")
+int bpf_sk_lookup_test4(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	struct bpf_sock *sk;
+
+	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+	bpf_sk_release(sk);
+	return 0;
+}
+
+void lookup_no_release(struct __sk_buff *skb)
+{
+	struct bpf_sock_tuple tuple = {};
+	bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0);
+}
+
+SEC("fail_no_release_subcall")
+int bpf_sk_lookup_test5(struct __sk_buff *skb)
+{
+	lookup_no_release(skb);
+	return 0;
+}
-- 
cgit v1.2.3


From fc35ef12dc8ba8633a99c9d9df03a5bb53f1dda3 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 20 Sep 2018 13:45:07 -0300
Subject: selftests/powerpc: New PTRACE_SYSEMU test

This patch adds a new test for the new PTRACE_SYSEMU ptrace request.

This test also relies on PTRACE_GETREGS and PTRACE_SETREGS requests to
run properly, since the trace instruction (gettid() syscall) is being
modified at run-time (by PTRACE_SETREGS) and re-executed three times.
PTRACE_GETREGS is being used to check that the registers are still
sane.

This test basically creates a child process that executes syscalls
and the parent process check if it is being traced appropriately.  The
parent process guarantees that the SYSCALLs are being traced, with
PTRACE_SYSEMU, and ptrace stops the child application before a syscall is
executed. The way the tests validates it, is by guaranteeing that the
system calls arguments, as argv[0] (r3) which is the same register that
will have the syscall return value on powerpc, are not being corrupted on
PTRACE_SYSEMU with a return value, i.e, it continues to have the current
arguments instead, meaning that the registers where not clobbered.

This test is basically the same test for x86 located at
tools/testing/selftests/x86/ptrace_syscall.c, limited to test PTRACE_SYSEMU
request, and ported to PowerPC.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/ptrace/Makefile    |   2 +-
 .../selftests/powerpc/ptrace/ptrace-syscall.c      | 228 +++++++++++++++++++++
 2 files changed, 229 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/powerpc/ptrace/ptrace-syscall.c

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile
index 28f5b781a553..1ee59978508d 100644
--- a/tools/testing/selftests/powerpc/ptrace/Makefile
+++ b/tools/testing/selftests/powerpc/ptrace/Makefile
@@ -2,7 +2,7 @@
 TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \
               ptrace-tar ptrace-tm-tar ptrace-tm-spd-tar ptrace-vsx ptrace-tm-vsx \
               ptrace-tm-spd-vsx ptrace-tm-spr ptrace-hwbreak ptrace-pkey core-pkey \
-              perf-hwbreak
+              perf-hwbreak ptrace-syscall
 
 include ../../lib.mk
 
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-syscall.c b/tools/testing/selftests/powerpc/ptrace/ptrace-syscall.c
new file mode 100644
index 000000000000..3353210dcdbd
--- /dev/null
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-syscall.c
@@ -0,0 +1,228 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A ptrace test for testing PTRACE_SYSEMU, PTRACE_SETREGS and
+ * PTRACE_GETREG.  This test basically create a child process that executes
+ * syscalls and the parent process check if it is being traced appropriated.
+ *
+ * This test is heavily based on tools/testing/selftests/x86/ptrace_syscall.c
+ * test, and it was adapted to run on Powerpc by
+ * Breno Leitao <leitao@debian.org>
+ */
+#define _GNU_SOURCE
+
+#include <sys/ptrace.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/syscall.h>
+#include <sys/user.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <err.h>
+#include <string.h>
+#include <sys/auxv.h>
+#include "utils.h"
+
+/* Bitness-agnostic defines for user_regs_struct fields. */
+#define user_syscall_nr	gpr[0]
+#define user_arg0		gpr[3]
+#define user_arg1		gpr[4]
+#define user_arg2		gpr[5]
+#define user_arg3		gpr[6]
+#define user_arg4		gpr[7]
+#define user_arg5		gpr[8]
+#define user_ip		nip
+
+#define PTRACE_SYSEMU		0x1d
+
+static int nerrs;
+
+static void wait_trap(pid_t chld)
+{
+	siginfo_t si;
+
+	if (waitid(P_PID, chld, &si, WEXITED|WSTOPPED) != 0)
+		err(1, "waitid");
+	if (si.si_pid != chld)
+		errx(1, "got unexpected pid in event\n");
+	if (si.si_code != CLD_TRAPPED)
+		errx(1, "got unexpected event type %d\n", si.si_code);
+}
+
+static void test_ptrace_syscall_restart(void)
+{
+	int status;
+	struct pt_regs regs;
+	pid_t chld;
+
+	printf("[RUN]\tptrace-induced syscall restart\n");
+
+	chld = fork();
+	if (chld < 0)
+		err(1, "fork");
+
+	/*
+	 * Child process is running 4 syscalls after ptrace.
+	 *
+	 * 1) getpid()
+	 * 2) gettid()
+	 * 3) tgkill() -> Send SIGSTOP
+	 * 4) gettid() -> Where the tests will happen essentially
+	 */
+	if (chld == 0) {
+		if (ptrace(PTRACE_TRACEME, 0, 0, 0) != 0)
+			err(1, "PTRACE_TRACEME");
+
+		pid_t pid = getpid(), tid = syscall(SYS_gettid);
+
+		printf("\tChild will make one syscall\n");
+		syscall(SYS_tgkill, pid, tid, SIGSTOP);
+
+		syscall(SYS_gettid, 10, 11, 12, 13, 14, 15);
+		_exit(0);
+	}
+	/* Parent process below */
+
+	/* Wait for SIGSTOP sent by tgkill above. */
+	if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status))
+		err(1, "waitpid");
+
+	printf("[RUN]\tSYSEMU\n");
+	if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
+		err(1, "PTRACE_SYSEMU");
+	wait_trap(chld);
+
+	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	/*
+	 * Ptrace trapped prior to executing the syscall, thus r3 still has
+	 * the syscall number instead of the sys_gettid() result
+	 */
+	if (regs.user_syscall_nr != SYS_gettid ||
+	    regs.user_arg0 != 10 || regs.user_arg1 != 11 ||
+	    regs.user_arg2 != 12 || regs.user_arg3 != 13 ||
+	    regs.user_arg4 != 14 || regs.user_arg5 != 15) {
+		printf("[FAIL]\tInitial args are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n",
+			(unsigned long)regs.user_syscall_nr,
+			(unsigned long)regs.user_arg0,
+			(unsigned long)regs.user_arg1,
+			(unsigned long)regs.user_arg2,
+			(unsigned long)regs.user_arg3,
+			(unsigned long)regs.user_arg4,
+			(unsigned long)regs.user_arg5);
+		 nerrs++;
+	} else {
+		printf("[OK]\tInitial nr and args are correct\n"); }
+
+	printf("[RUN]\tRestart the syscall (ip = 0x%lx)\n",
+	       (unsigned long)regs.user_ip);
+
+	/*
+	 * Rewind to retry the same syscall again. This will basically test
+	 * the rewind process together with PTRACE_SETREGS and PTRACE_GETREGS.
+	 */
+	regs.user_ip -= 4;
+	if (ptrace(PTRACE_SETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_SETREGS");
+
+	if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
+		err(1, "PTRACE_SYSEMU");
+	wait_trap(chld);
+
+	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	if (regs.user_syscall_nr != SYS_gettid ||
+	    regs.user_arg0 != 10 || regs.user_arg1 != 11 ||
+	    regs.user_arg2 != 12 || regs.user_arg3 != 13 ||
+	    regs.user_arg4 != 14 || regs.user_arg5 != 15) {
+		printf("[FAIL]\tRestart nr or args are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n",
+			(unsigned long)regs.user_syscall_nr,
+			(unsigned long)regs.user_arg0,
+			(unsigned long)regs.user_arg1,
+			(unsigned long)regs.user_arg2,
+			(unsigned long)regs.user_arg3,
+			(unsigned long)regs.user_arg4,
+			(unsigned long)regs.user_arg5);
+		nerrs++;
+	} else {
+		printf("[OK]\tRestarted nr and args are correct\n");
+	}
+
+	printf("[RUN]\tChange nr and args and restart the syscall (ip = 0x%lx)\n",
+	       (unsigned long)regs.user_ip);
+
+	/*
+	 * Inject a new syscall (getpid) in the same place the previous
+	 * syscall (gettid), rewind and re-execute.
+	 */
+	regs.user_syscall_nr = SYS_getpid;
+	regs.user_arg0 = 20;
+	regs.user_arg1 = 21;
+	regs.user_arg2 = 22;
+	regs.user_arg3 = 23;
+	regs.user_arg4 = 24;
+	regs.user_arg5 = 25;
+	regs.user_ip -= 4;
+
+	if (ptrace(PTRACE_SETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_SETREGS");
+
+	if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
+		err(1, "PTRACE_SYSEMU");
+	wait_trap(chld);
+
+	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	/* Check that ptrace stopped at the new syscall that was
+	 * injected, and guarantee that it haven't executed, i.e, user_args
+	 * contain the arguments and not the syscall return value, for
+	 * instance.
+	 */
+	if (regs.user_syscall_nr != SYS_getpid
+		|| regs.user_arg0 != 20 || regs.user_arg1 != 21
+		|| regs.user_arg2 != 22 || regs.user_arg3 != 23
+		|| regs.user_arg4 != 24 || regs.user_arg5 != 25) {
+
+		printf("[FAIL]\tRestart nr or args are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n",
+			(unsigned long)regs.user_syscall_nr,
+			(unsigned long)regs.user_arg0,
+			(unsigned long)regs.user_arg1,
+			(unsigned long)regs.user_arg2,
+			(unsigned long)regs.user_arg3,
+			(unsigned long)regs.user_arg4,
+			(unsigned long)regs.user_arg5);
+		nerrs++;
+	} else {
+		printf("[OK]\tReplacement nr and args are correct\n");
+	}
+
+	if (ptrace(PTRACE_CONT, chld, 0, 0) != 0)
+		err(1, "PTRACE_CONT");
+
+	if (waitpid(chld, &status, 0) != chld)
+		err(1, "waitpid");
+
+	/* Guarantee that the process executed properly, returning 0 */
+	if (!WIFEXITED(status) || WEXITSTATUS(status) != 0) {
+		printf("[FAIL]\tChild failed\n");
+		nerrs++;
+	} else {
+		printf("[OK]\tChild exited cleanly\n");
+	}
+}
+
+int ptrace_syscall(void)
+{
+	test_ptrace_syscall_restart();
+
+	return nerrs;
+}
+
+int main(void)
+{
+	return test_harness(ptrace_syscall, "ptrace_syscall");
+}
-- 
cgit v1.2.3


From fef31ecaaf2c5c54db85b35e893bf8abec96b93f Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Date: Thu, 23 Aug 2018 13:34:53 +0200
Subject: tools: PCI: Fix compilation warnings

Current compilation produces the following warnings:

tools/pci/pcitest.c: In function 'run_test':
tools/pci/pcitest.c:56:9: warning: unused variable 'time'
[-Wunused-variable]
  double time;
         ^~~~
tools/pci/pcitest.c:55:25: warning: unused variable 'end'
[-Wunused-variable]
  struct timespec start, end;
                         ^~~
tools/pci/pcitest.c:55:18: warning: unused variable 'start'
[-Wunused-variable]
  struct timespec start, end;
                  ^~~~~
tools/pci/pcitest.c:146:1: warning: control reaches end of non-void
function [-Wreturn-type]
 }
 ^

Fix them:
 - remove unused variables
 - change function return from int to void, since it's not used

Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
[lorenzo.pieralisi@arm.com: rewrote the commit log]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 tools/pci/pcitest.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/pci/pcitest.c b/tools/pci/pcitest.c
index af146bb03b4d..ec4d51f3308b 100644
--- a/tools/pci/pcitest.c
+++ b/tools/pci/pcitest.c
@@ -23,7 +23,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <sys/ioctl.h>
-#include <time.h>
 #include <unistd.h>
 
 #include <linux/pcitest.h>
@@ -48,17 +47,15 @@ struct pci_test {
 	unsigned long	size;
 };
 
-static int run_test(struct pci_test *test)
+static void run_test(struct pci_test *test)
 {
 	long ret;
 	int fd;
-	struct timespec start, end;
-	double time;
 
 	fd = open(test->device, O_RDWR);
 	if (fd < 0) {
 		perror("can't open PCI Endpoint Test device");
-		return fd;
+		return;
 	}
 
 	if (test->barnum >= 0 && test->barnum <= 5) {
-- 
cgit v1.2.3


From 1ce78ce09430a5ffb987015ab2e24d145690b9a3 Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Date: Thu, 23 Aug 2018 13:55:15 +0200
Subject: tools: PCI: Change pcitest compiling process

Change tool compiling process in order to be build using the same
mechanism used in other linux tools (e.g. iio, perf, etc). This will
allow in future the buildroot tool to build and integrate this tool in
a more expeditious way.

Update documentation accordingly.

Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 Documentation/PCI/endpoint/pci-test-howto.txt | 19 ++++++----
 tools/Makefile                                | 13 ++++---
 tools/pci/Build                               |  1 +
 tools/pci/Makefile                            | 53 +++++++++++++++++++++++++++
 4 files changed, 72 insertions(+), 14 deletions(-)
 create mode 100644 tools/pci/Build
 create mode 100644 tools/pci/Makefile

(limited to 'tools')

diff --git a/Documentation/PCI/endpoint/pci-test-howto.txt b/Documentation/PCI/endpoint/pci-test-howto.txt
index e40cf0fb58d7..040479f437a5 100644
--- a/Documentation/PCI/endpoint/pci-test-howto.txt
+++ b/Documentation/PCI/endpoint/pci-test-howto.txt
@@ -99,17 +99,20 @@ Note that the devices listed here correspond to the value populated in 1.4 above
 2.2 Using Endpoint Test function Device
 
 pcitest.sh added in tools/pci/ can be used to run all the default PCI endpoint
-tests. Before pcitest.sh can be used pcitest.c should be compiled using the
-following commands.
+tests. To compile this tool the following commands should be used:
 
-	cd <kernel-dir>
-	make headers_install ARCH=arm
-	arm-linux-gnueabihf-gcc -Iusr/include tools/pci/pcitest.c -o pcitest
-	cp pcitest  <rootfs>/usr/sbin/
-	cp tools/pci/pcitest.sh <rootfs>
+	# cd <kernel-dir>
+	# make -C tools/pci
+
+or if you desire to compile and install in your system:
+
+	# cd <kernel-dir>
+	# make -C tools/pci install
+
+The tool and script will be located in <rootfs>/usr/bin/
 
 2.2.1 pcitest.sh Output
-	# ./pcitest.sh
+	# pcitest.sh
 	BAR tests
 
 	BAR0:           OKAY
diff --git a/tools/Makefile b/tools/Makefile
index be02c8b904db..abb358a70ad0 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -21,6 +21,7 @@ help:
 	@echo '  leds                   - LEDs  tools'
 	@echo '  liblockdep             - user-space wrapper for kernel locking-validator'
 	@echo '  bpf                    - misc BPF tools'
+	@echo '  pci                    - PCI tools'
 	@echo '  perf                   - Linux performance measurement and analysis tool'
 	@echo '  selftests              - various kernel selftests'
 	@echo '  spi                    - spi tools'
@@ -59,7 +60,7 @@ acpi: FORCE
 cpupower: FORCE
 	$(call descend,power/$@)
 
-cgroup firewire hv guest spi usb virtio vm bpf iio gpio objtool leds wmi: FORCE
+cgroup firewire hv guest spi usb virtio vm bpf iio gpio objtool leds wmi pci: FORCE
 	$(call descend,$@)
 
 liblockdep: FORCE
@@ -94,7 +95,7 @@ kvm_stat: FORCE
 all: acpi cgroup cpupower gpio hv firewire liblockdep \
 		perf selftests spi turbostat usb \
 		virtio vm bpf x86_energy_perf_policy \
-		tmon freefall iio objtool kvm_stat wmi
+		tmon freefall iio objtool kvm_stat wmi pci
 
 acpi_install:
 	$(call descend,power/$(@:_install=),install)
@@ -102,7 +103,7 @@ acpi_install:
 cpupower_install:
 	$(call descend,power/$(@:_install=),install)
 
-cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install bpf_install objtool_install wmi_install:
+cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install bpf_install objtool_install wmi_install pci_install:
 	$(call descend,$(@:_install=),install)
 
 liblockdep_install:
@@ -128,7 +129,7 @@ install: acpi_install cgroup_install cpupower_install gpio_install \
 		perf_install selftests_install turbostat_install usb_install \
 		virtio_install vm_install bpf_install x86_energy_perf_policy_install \
 		tmon_install freefall_install objtool_install kvm_stat_install \
-		wmi_install
+		wmi_install pci_install
 
 acpi_clean:
 	$(call descend,power/acpi,clean)
@@ -136,7 +137,7 @@ acpi_clean:
 cpupower_clean:
 	$(call descend,power/cpupower,clean)
 
-cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean:
+cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean pci_clean:
 	$(call descend,$(@:_clean=),clean)
 
 liblockdep_clean:
@@ -174,6 +175,6 @@ clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean \
 		perf_clean selftests_clean turbostat_clean spi_clean usb_clean virtio_clean \
 		vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
 		freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \
-		gpio_clean objtool_clean leds_clean wmi_clean
+		gpio_clean objtool_clean leds_clean wmi_clean pci_clean
 
 .PHONY: FORCE
diff --git a/tools/pci/Build b/tools/pci/Build
new file mode 100644
index 000000000000..c375aea21790
--- /dev/null
+++ b/tools/pci/Build
@@ -0,0 +1 @@
+pcitest-y += pcitest.o
diff --git a/tools/pci/Makefile b/tools/pci/Makefile
new file mode 100644
index 000000000000..46e4c2f318c9
--- /dev/null
+++ b/tools/pci/Makefile
@@ -0,0 +1,53 @@
+# SPDX-License-Identifier: GPL-2.0
+include ../scripts/Makefile.include
+
+bindir ?= /usr/bin
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+endif
+
+# Do not use make's built-in rules
+# (this improves performance and avoids hard-to-debug behaviour);
+MAKEFLAGS += -r
+
+CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
+
+ALL_TARGETS := pcitest pcitest.sh
+ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
+
+all: $(ALL_PROGRAMS)
+
+export srctree OUTPUT CC LD CFLAGS
+include $(srctree)/tools/build/Makefile.include
+
+#
+# We need the following to be outside of kernel tree
+#
+$(OUTPUT)include/linux/: ../../include/uapi/linux/
+	mkdir -p $(OUTPUT)include/linux/ 2>&1 || true
+	ln -sf $(CURDIR)/../../include/uapi/linux/pcitest.h $@
+
+prepare: $(OUTPUT)include/linux/
+
+PCITEST_IN := $(OUTPUT)pcitest-in.o
+$(PCITEST_IN): prepare FORCE
+	$(Q)$(MAKE) $(build)=pcitest
+$(OUTPUT)pcitest: $(PCITEST_IN)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
+
+clean:
+	rm -f $(ALL_PROGRAMS)
+	rm -rf $(OUTPUT)include/
+	find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete
+
+install: $(ALL_PROGRAMS)
+	install -d -m 755 $(DESTDIR)$(bindir);		\
+	for program in $(ALL_PROGRAMS); do		\
+		install $$program $(DESTDIR)$(bindir);	\
+	done
+
+FORCE:
+
+.PHONY: all install clean FORCE prepare
-- 
cgit v1.2.3


From 02e425668f5c9deb42787d10001a3b605993ad15 Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@kernel.org>
Date: Wed, 3 Oct 2018 16:23:49 -0700
Subject: x86/vdso: Fix vDSO syscall fallback asm constraint regression

When I added the missing memory outputs, I failed to update the
index of the first argument (ebx) on 32-bit builds, which broke the
fallbacks.  Somehow I must have screwed up my testing or gotten
lucky.

Add another test to cover gettimeofday() as well.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Fixes: 715bd9d12f84 ("x86/vdso: Fix asm constraints on vDSO syscall fallbacks")
Link: http://lkml.kernel.org/r/21bd45ab04b6d838278fa5bebfa9163eceffa13c.1538608971.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/entry/vdso/vclock_gettime.c    |  8 ++--
 tools/testing/selftests/x86/test_vdso.c | 73 +++++++++++++++++++++++++++++++++
 2 files changed, 77 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 134e2d2e8add..e48ca3afa091 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -68,11 +68,11 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 
 	asm (
 		"mov %%ebx, %%edx \n"
-		"mov %2, %%ebx \n"
+		"mov %[clock], %%ebx \n"
 		"call __kernel_vsyscall \n"
 		"mov %%edx, %%ebx \n"
 		: "=a" (ret), "=m" (*ts)
-		: "0" (__NR_clock_gettime), "g" (clock), "c" (ts)
+		: "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts)
 		: "memory", "edx");
 	return ret;
 }
@@ -83,11 +83,11 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
 
 	asm (
 		"mov %%ebx, %%edx \n"
-		"mov %2, %%ebx \n"
+		"mov %[tv], %%ebx \n"
 		"call __kernel_vsyscall \n"
 		"mov %%edx, %%ebx \n"
 		: "=a" (ret), "=m" (*tv), "=m" (*tz)
-		: "0" (__NR_gettimeofday), "g" (tv), "c" (tz)
+		: "0" (__NR_gettimeofday), [tv] "g" (tv), "c" (tz)
 		: "memory", "edx");
 	return ret;
 }
diff --git a/tools/testing/selftests/x86/test_vdso.c b/tools/testing/selftests/x86/test_vdso.c
index 49f7294fb382..35edd61d1663 100644
--- a/tools/testing/selftests/x86/test_vdso.c
+++ b/tools/testing/selftests/x86/test_vdso.c
@@ -36,6 +36,10 @@ typedef int (*vgettime_t)(clockid_t, struct timespec *);
 
 vgettime_t vdso_clock_gettime;
 
+typedef long (*vgtod_t)(struct timeval *tv, struct timezone *tz);
+
+vgtod_t vdso_gettimeofday;
+
 typedef long (*getcpu_t)(unsigned *, unsigned *, void *);
 
 getcpu_t vgetcpu;
@@ -104,6 +108,11 @@ static void fill_function_pointers()
 	vdso_clock_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime");
 	if (!vdso_clock_gettime)
 		printf("Warning: failed to find clock_gettime in vDSO\n");
+
+	vdso_gettimeofday = (vgtod_t)dlsym(vdso, "__vdso_gettimeofday");
+	if (!vdso_gettimeofday)
+		printf("Warning: failed to find gettimeofday in vDSO\n");
+
 }
 
 static long sys_getcpu(unsigned * cpu, unsigned * node,
@@ -117,6 +126,11 @@ static inline int sys_clock_gettime(clockid_t id, struct timespec *ts)
 	return syscall(__NR_clock_gettime, id, ts);
 }
 
+static inline int sys_gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+	return syscall(__NR_gettimeofday, tv, tz);
+}
+
 static void test_getcpu(void)
 {
 	printf("[RUN]\tTesting getcpu...\n");
@@ -177,6 +191,14 @@ static bool ts_leq(const struct timespec *a, const struct timespec *b)
 		return a->tv_nsec <= b->tv_nsec;
 }
 
+static bool tv_leq(const struct timeval *a, const struct timeval *b)
+{
+	if (a->tv_sec != b->tv_sec)
+		return a->tv_sec < b->tv_sec;
+	else
+		return a->tv_usec <= b->tv_usec;
+}
+
 static char const * const clocknames[] = {
 	[0] = "CLOCK_REALTIME",
 	[1] = "CLOCK_MONOTONIC",
@@ -248,11 +270,62 @@ static void test_clock_gettime(void)
 	test_one_clock_gettime(INT_MAX, "invalid");
 }
 
+static void test_gettimeofday(void)
+{
+	struct timeval start, vdso, end;
+	struct timezone sys_tz, vdso_tz;
+	int vdso_ret, end_ret;
+
+	if (!vdso_gettimeofday)
+		return;
+
+	printf("[RUN]\tTesting gettimeofday...\n");
+
+	if (sys_gettimeofday(&start, &sys_tz) < 0) {
+		printf("[FAIL]\tsys_gettimeofday failed (%d)\n", errno);
+		nerrs++;
+		return;
+	}
+
+	vdso_ret = vdso_gettimeofday(&vdso, &vdso_tz);
+	end_ret = sys_gettimeofday(&end, NULL);
+
+	if (vdso_ret != 0 || end_ret != 0) {
+		printf("[FAIL]\tvDSO returned %d, syscall errno=%d\n",
+		       vdso_ret, errno);
+		nerrs++;
+		return;
+	}
+
+	printf("\t%llu.%06ld %llu.%06ld %llu.%06ld\n",
+	       (unsigned long long)start.tv_sec, start.tv_usec,
+	       (unsigned long long)vdso.tv_sec, vdso.tv_usec,
+	       (unsigned long long)end.tv_sec, end.tv_usec);
+
+	if (!tv_leq(&start, &vdso) || !tv_leq(&vdso, &end)) {
+		printf("[FAIL]\tTimes are out of sequence\n");
+		nerrs++;
+	}
+
+	if (sys_tz.tz_minuteswest == vdso_tz.tz_minuteswest &&
+	    sys_tz.tz_dsttime == vdso_tz.tz_dsttime) {
+		printf("[OK]\ttimezones match: minuteswest=%d, dsttime=%d\n",
+		       sys_tz.tz_minuteswest, sys_tz.tz_dsttime);
+	} else {
+		printf("[FAIL]\ttimezones do not match\n");
+		nerrs++;
+	}
+
+	/* And make sure that passing NULL for tz doesn't crash. */
+	vdso_gettimeofday(&vdso, NULL);
+}
+
 int main(int argc, char **argv)
 {
 	fill_function_pointers();
 
 	test_clock_gettime();
+	test_gettimeofday();
 
 	/*
 	 * Test getcpu() last so that, if something goes wrong setting affinity,
-- 
cgit v1.2.3


From 995d5f64b62f20f05b8e0972f07ec4d6c23333c9 Mon Sep 17 00:00:00 2001
From: Pu Wen <puwen@hygon.cn>
Date: Thu, 4 Oct 2018 09:21:43 +0800
Subject: tools/cpupower: Add Hygon Dhyana support

The tool cpupower is useful to get CPU frequency information and monitor
power stats on the Hygon Dhyana platform. So add Hygon Dhyana support to
it by checking vendor and family to share the code path of AMD family
17h.

Signed-off-by: Pu Wen <puwen@hygon.cn>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
CC: Prarit Bhargava <prarit@redhat.com>
CC: Shuah Khan <shuah@kernel.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Thomas Renninger <trenn@suse.com>
CC: linux-pm@vger.kernel.org
Link: http://lkml.kernel.org/r/5ce86123a7b9dad925ac583d88d2f921040e859b.1538583282.git.puwen@hygon.cn
---
 tools/power/cpupower/utils/cpufreq-info.c               | 6 ++++--
 tools/power/cpupower/utils/helpers/amd.c                | 4 ++--
 tools/power/cpupower/utils/helpers/cpuid.c              | 8 +++++---
 tools/power/cpupower/utils/helpers/helpers.h            | 2 +-
 tools/power/cpupower/utils/helpers/misc.c               | 2 +-
 tools/power/cpupower/utils/idle_monitor/mperf_monitor.c | 3 ++-
 6 files changed, 15 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c
index df43cd45d810..56e54eabc65c 100644
--- a/tools/power/cpupower/utils/cpufreq-info.c
+++ b/tools/power/cpupower/utils/cpufreq-info.c
@@ -170,6 +170,7 @@ static int get_boost_mode(unsigned int cpu)
 	unsigned long pstates[MAX_HW_PSTATES] = {0,};
 
 	if (cpupower_cpu_info.vendor != X86_VENDOR_AMD &&
+	    cpupower_cpu_info.vendor != X86_VENDOR_HYGON &&
 	    cpupower_cpu_info.vendor != X86_VENDOR_INTEL)
 		return 0;
 
@@ -190,8 +191,9 @@ static int get_boost_mode(unsigned int cpu)
 	printf(_("    Supported: %s\n"), support ? _("yes") : _("no"));
 	printf(_("    Active: %s\n"), active ? _("yes") : _("no"));
 
-	if (cpupower_cpu_info.vendor == X86_VENDOR_AMD &&
-	    cpupower_cpu_info.family >= 0x10) {
+	if ((cpupower_cpu_info.vendor == X86_VENDOR_AMD &&
+	     cpupower_cpu_info.family >= 0x10) ||
+	     cpupower_cpu_info.vendor == X86_VENDOR_HYGON) {
 		ret = decode_pstates(cpu, cpupower_cpu_info.family, b_states,
 				     pstates, &pstate_no);
 		if (ret)
diff --git a/tools/power/cpupower/utils/helpers/amd.c b/tools/power/cpupower/utils/helpers/amd.c
index bb41cdd0df6b..65beaeefeef0 100644
--- a/tools/power/cpupower/utils/helpers/amd.c
+++ b/tools/power/cpupower/utils/helpers/amd.c
@@ -45,7 +45,7 @@ static int get_did(int family, union msr_pstate pstate)
 
 	if (family == 0x12)
 		t = pstate.val & 0xf;
-	else if (family == 0x17)
+	else if (family == 0x17 || family == 0x18)
 		t = pstate.fam17h_bits.did;
 	else
 		t = pstate.bits.did;
@@ -59,7 +59,7 @@ static int get_cof(int family, union msr_pstate pstate)
 	int fid, did, cof;
 
 	did = get_did(family, pstate);
-	if (family == 0x17) {
+	if (family == 0x17 || family == 0x18) {
 		fid = pstate.fam17h_bits.fid;
 		cof = 200 * fid / did;
 	} else {
diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c
index 732b0b41ba26..5cc39d4e23ed 100644
--- a/tools/power/cpupower/utils/helpers/cpuid.c
+++ b/tools/power/cpupower/utils/helpers/cpuid.c
@@ -8,7 +8,7 @@
 #include "helpers/helpers.h"
 
 static const char *cpu_vendor_table[X86_VENDOR_MAX] = {
-	"Unknown", "GenuineIntel", "AuthenticAMD",
+	"Unknown", "GenuineIntel", "AuthenticAMD", "HygonGenuine",
 };
 
 #if defined(__i386__) || defined(__x86_64__)
@@ -109,6 +109,7 @@ out:
 	fclose(fp);
 	/* Get some useful CPU capabilities from cpuid */
 	if (cpu_info->vendor != X86_VENDOR_AMD &&
+	    cpu_info->vendor != X86_VENDOR_HYGON &&
 	    cpu_info->vendor != X86_VENDOR_INTEL)
 		return ret;
 
@@ -124,8 +125,9 @@ out:
 	if (cpuid_level >= 6 && (cpuid_ecx(6) & 0x1))
 		cpu_info->caps |= CPUPOWER_CAP_APERF;
 
-	/* AMD Boost state enable/disable register */
-	if (cpu_info->vendor == X86_VENDOR_AMD) {
+	/* AMD or Hygon Boost state enable/disable register */
+	if (cpu_info->vendor == X86_VENDOR_AMD ||
+	    cpu_info->vendor == X86_VENDOR_HYGON) {
 		if (ext_cpuid_level >= 0x80000007 &&
 		    (cpuid_edx(0x80000007) & (1 << 9)))
 			cpu_info->caps |= CPUPOWER_CAP_AMD_CBP;
diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h
index 41da392be448..902139689315 100644
--- a/tools/power/cpupower/utils/helpers/helpers.h
+++ b/tools/power/cpupower/utils/helpers/helpers.h
@@ -61,7 +61,7 @@ extern int be_verbose;
 
 /* cpuid and cpuinfo helpers  **************************/
 enum cpupower_cpu_vendor {X86_VENDOR_UNKNOWN = 0, X86_VENDOR_INTEL,
-			  X86_VENDOR_AMD, X86_VENDOR_MAX};
+			  X86_VENDOR_AMD, X86_VENDOR_HYGON, X86_VENDOR_MAX};
 
 #define CPUPOWER_CAP_INV_TSC		0x00000001
 #define CPUPOWER_CAP_APERF		0x00000002
diff --git a/tools/power/cpupower/utils/helpers/misc.c b/tools/power/cpupower/utils/helpers/misc.c
index 80fdf55f414d..f406adc40bad 100644
--- a/tools/power/cpupower/utils/helpers/misc.c
+++ b/tools/power/cpupower/utils/helpers/misc.c
@@ -26,7 +26,7 @@ int cpufreq_has_boost_support(unsigned int cpu, int *support, int *active,
 		 * has Hardware determined variable increments instead.
 		 */
 
-		if (cpu_info.family == 0x17) {
+		if (cpu_info.family == 0x17 || cpu_info.family == 0x18) {
 			if (!read_msr(cpu, MSR_AMD_HWCR, &val)) {
 				if (!(val & CPUPOWER_AMD_CPBDIS))
 					*active = 1;
diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c
index d7c2a6d13dea..f2a7e9cfd577 100644
--- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c
+++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c
@@ -241,7 +241,8 @@ static int init_maxfreq_mode(void)
 	if (!(cpupower_cpu_info.caps & CPUPOWER_CAP_INV_TSC))
 		goto use_sysfs;
 
-	if (cpupower_cpu_info.vendor == X86_VENDOR_AMD) {
+	if (cpupower_cpu_info.vendor == X86_VENDOR_AMD ||
+	    cpupower_cpu_info.vendor == X86_VENDOR_HYGON) {
 		/* MSR_AMD_HWCR tells us whether TSC runs at P0/mperf
 		 * freq.
 		 * A test whether hwcr is accessable/available would be:
-- 
cgit v1.2.3


From 434fe9d4b4bfa8becb0959ef32b9b9fa628ef6fe Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 3 Oct 2018 15:26:38 -0700
Subject: libbpf: Move __dump_nlmsg_t from API to implementation

This typedef is used only by implementation in netlink.c. Nothing uses
it in public API. Move it to netlink.c.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.h  | 3 ---
 tools/lib/bpf/netlink.c | 3 +++
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 2ed24d3f80b3..8388be525388 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -304,11 +304,8 @@ int bpf_perf_event_read_simple(void *mem, unsigned long size,
 			       void **buf, size_t *buf_len,
 			       bpf_perf_event_print_t fn, void *priv);
 
-struct nlmsghdr;
 struct nlattr;
 typedef int (*dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
-typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, dump_nlmsg_t,
-			      void *cookie);
 int bpf_netlink_open(unsigned int *nl_pid);
 int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg,
 		void *cookie);
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index fde1d7bf8199..da46d9358d9d 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -18,6 +18,9 @@
 #define SOL_NETLINK 270
 #endif
 
+typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, dump_nlmsg_t,
+			      void *cookie);
+
 int bpf_netlink_open(__u32 *nl_pid)
 {
 	struct sockaddr_nl sa;
-- 
cgit v1.2.3


From aae57780107d92de2463e605cb054656ebd233d1 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 3 Oct 2018 15:26:39 -0700
Subject: libbpf: Consistent prefixes for interfaces in libbpf.h.

libbpf is used more and more outside kernel tree. That means the library
should follow good practices in library design and implementation to
play well with third party code that uses it.

One of such practices is to have a common prefix (or a few) for every
interface, function or data structure, library provides. I helps to
avoid name conflicts with other libraries and keeps API consistent.

Inconsistent names in libbpf already cause problems in real life. E.g.
an application can't use both libbpf and libnl due to conflicting
symbols.

Having common prefix will help to fix current and avoid future problems.

libbpf already uses the following prefixes for its interfaces:
* bpf_ for bpf system call wrappers, program/map/elf-object
  abstractions and a few other things;
* btf_ for BTF related API;
* libbpf_ for everything else.

The patch adds libbpf_ prefix to functions and typedef in libbpf.h that
use none of mentioned above prefixes and doesn't fit well into the first
two categories.

Since affected part of API is used in bpftool, the patch applies
corresponding change to bpftool as well. Having it in a separate patch
will cause a state of tree where bpftool is broken what may not be a
good idea.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/net.c | 31 +++++++++++++++----------------
 tools/lib/bpf/libbpf.h  | 20 ++++++++++----------
 tools/lib/bpf/netlink.c | 37 ++++++++++++++++++++-----------------
 3 files changed, 45 insertions(+), 43 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index ed205ee57655..ef83e8a08490 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -127,14 +127,14 @@ static int show_dev_tc_bpf(int sock, unsigned int nl_pid,
 	tcinfo.array_len = 0;
 
 	tcinfo.is_qdisc = false;
-	ret = nl_get_class(sock, nl_pid, dev->ifindex, dump_class_qdisc_nlmsg,
-			   &tcinfo);
+	ret = libbpf_nl_get_class(sock, nl_pid, dev->ifindex,
+				  dump_class_qdisc_nlmsg, &tcinfo);
 	if (ret)
 		goto out;
 
 	tcinfo.is_qdisc = true;
-	ret = nl_get_qdisc(sock, nl_pid, dev->ifindex, dump_class_qdisc_nlmsg,
-			   &tcinfo);
+	ret = libbpf_nl_get_qdisc(sock, nl_pid, dev->ifindex,
+				  dump_class_qdisc_nlmsg, &tcinfo);
 	if (ret)
 		goto out;
 
@@ -142,10 +142,9 @@ static int show_dev_tc_bpf(int sock, unsigned int nl_pid,
 	filter_info.ifindex = dev->ifindex;
 	for (i = 0; i < tcinfo.used_len; i++) {
 		filter_info.kind = tcinfo.handle_array[i].kind;
-		ret = nl_get_filter(sock, nl_pid, dev->ifindex,
-				    tcinfo.handle_array[i].handle,
-				    dump_filter_nlmsg,
-				    &filter_info);
+		ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex,
+					   tcinfo.handle_array[i].handle,
+					   dump_filter_nlmsg, &filter_info);
 		if (ret)
 			goto out;
 	}
@@ -153,22 +152,22 @@ static int show_dev_tc_bpf(int sock, unsigned int nl_pid,
 	/* root, ingress and egress handle */
 	handle = TC_H_ROOT;
 	filter_info.kind = "root";
-	ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
-			    dump_filter_nlmsg, &filter_info);
+	ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+				   dump_filter_nlmsg, &filter_info);
 	if (ret)
 		goto out;
 
 	handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS);
 	filter_info.kind = "clsact/ingress";
-	ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
-			    dump_filter_nlmsg, &filter_info);
+	ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+				   dump_filter_nlmsg, &filter_info);
 	if (ret)
 		goto out;
 
 	handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_EGRESS);
 	filter_info.kind = "clsact/egress";
-	ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
-			    dump_filter_nlmsg, &filter_info);
+	ret = libbpf_nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+				   dump_filter_nlmsg, &filter_info);
 	if (ret)
 		goto out;
 
@@ -196,7 +195,7 @@ static int do_show(int argc, char **argv)
 		usage();
 	}
 
-	sock = bpf_netlink_open(&nl_pid);
+	sock = libbpf_netlink_open(&nl_pid);
 	if (sock < 0) {
 		fprintf(stderr, "failed to open netlink sock\n");
 		return -1;
@@ -211,7 +210,7 @@ static int do_show(int argc, char **argv)
 		jsonw_start_array(json_wtr);
 	NET_START_OBJECT;
 	NET_START_ARRAY("xdp", "%s:\n");
-	ret = nl_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array);
+	ret = libbpf_nl_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array);
 	NET_END_ARRAY("\n");
 
 	if (!ret) {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 8388be525388..710ff5724980 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -305,14 +305,14 @@ int bpf_perf_event_read_simple(void *mem, unsigned long size,
 			       bpf_perf_event_print_t fn, void *priv);
 
 struct nlattr;
-typedef int (*dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
-int bpf_netlink_open(unsigned int *nl_pid);
-int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg,
-		void *cookie);
-int nl_get_class(int sock, unsigned int nl_pid, int ifindex,
-		 dump_nlmsg_t dump_class_nlmsg, void *cookie);
-int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
-		 dump_nlmsg_t dump_qdisc_nlmsg, void *cookie);
-int nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
-		  dump_nlmsg_t dump_filter_nlmsg, void *cookie);
+typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
+int libbpf_netlink_open(unsigned int *nl_pid);
+int libbpf_nl_get_link(int sock, unsigned int nl_pid,
+		       libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie);
+int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex,
+			libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie);
+int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
+			libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie);
+int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
+			 libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie);
 #endif
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index da46d9358d9d..506bdfdbcab0 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -18,10 +18,10 @@
 #define SOL_NETLINK 270
 #endif
 
-typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, dump_nlmsg_t,
+typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, libbpf_dump_nlmsg_t,
 			      void *cookie);
 
-int bpf_netlink_open(__u32 *nl_pid)
+int libbpf_netlink_open(__u32 *nl_pid)
 {
 	struct sockaddr_nl sa;
 	socklen_t addrlen;
@@ -65,7 +65,7 @@ cleanup:
 }
 
 static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
-			    __dump_nlmsg_t _fn, dump_nlmsg_t fn,
+			    __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn,
 			    void *cookie)
 {
 	bool multipart = true;
@@ -133,7 +133,7 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 	} req;
 	__u32 nl_pid;
 
-	sock = bpf_netlink_open(&nl_pid);
+	sock = libbpf_netlink_open(&nl_pid);
 	if (sock < 0)
 		return sock;
 
@@ -181,8 +181,8 @@ cleanup:
 	return ret;
 }
 
-static int __dump_link_nlmsg(struct nlmsghdr *nlh, dump_nlmsg_t dump_link_nlmsg,
-			     void *cookie)
+static int __dump_link_nlmsg(struct nlmsghdr *nlh,
+			     libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
 {
 	struct nlattr *tb[IFLA_MAX + 1], *attr;
 	struct ifinfomsg *ifi = NLMSG_DATA(nlh);
@@ -196,8 +196,8 @@ static int __dump_link_nlmsg(struct nlmsghdr *nlh, dump_nlmsg_t dump_link_nlmsg,
 	return dump_link_nlmsg(cookie, ifi, tb);
 }
 
-int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg,
-		void *cookie)
+int libbpf_nl_get_link(int sock, unsigned int nl_pid,
+		       libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
 {
 	struct {
 		struct nlmsghdr nlh;
@@ -219,7 +219,8 @@ int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg,
 }
 
 static int __dump_class_nlmsg(struct nlmsghdr *nlh,
-			      dump_nlmsg_t dump_class_nlmsg, void *cookie)
+			      libbpf_dump_nlmsg_t dump_class_nlmsg,
+			      void *cookie)
 {
 	struct nlattr *tb[TCA_MAX + 1], *attr;
 	struct tcmsg *t = NLMSG_DATA(nlh);
@@ -233,8 +234,8 @@ static int __dump_class_nlmsg(struct nlmsghdr *nlh,
 	return dump_class_nlmsg(cookie, t, tb);
 }
 
-int nl_get_class(int sock, unsigned int nl_pid, int ifindex,
-		 dump_nlmsg_t dump_class_nlmsg, void *cookie)
+int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex,
+			libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie)
 {
 	struct {
 		struct nlmsghdr nlh;
@@ -257,7 +258,8 @@ int nl_get_class(int sock, unsigned int nl_pid, int ifindex,
 }
 
 static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh,
-			      dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
+			      libbpf_dump_nlmsg_t dump_qdisc_nlmsg,
+			      void *cookie)
 {
 	struct nlattr *tb[TCA_MAX + 1], *attr;
 	struct tcmsg *t = NLMSG_DATA(nlh);
@@ -271,8 +273,8 @@ static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh,
 	return dump_qdisc_nlmsg(cookie, t, tb);
 }
 
-int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
-		 dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
+int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
+			libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
 {
 	struct {
 		struct nlmsghdr nlh;
@@ -295,7 +297,8 @@ int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
 }
 
 static int __dump_filter_nlmsg(struct nlmsghdr *nlh,
-			       dump_nlmsg_t dump_filter_nlmsg, void *cookie)
+			       libbpf_dump_nlmsg_t dump_filter_nlmsg,
+			       void *cookie)
 {
 	struct nlattr *tb[TCA_MAX + 1], *attr;
 	struct tcmsg *t = NLMSG_DATA(nlh);
@@ -309,8 +312,8 @@ static int __dump_filter_nlmsg(struct nlmsghdr *nlh,
 	return dump_filter_nlmsg(cookie, t, tb);
 }
 
-int nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
-		  dump_nlmsg_t dump_filter_nlmsg, void *cookie)
+int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
+			 libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie)
 {
 	struct {
 		struct nlmsghdr nlh;
-- 
cgit v1.2.3


From f04bc8a436e1b32f842a631ff889954bdf56b720 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 3 Oct 2018 15:26:40 -0700
Subject: libbpf: Consistent prefixes for interfaces in nlattr.h.

libbpf is used more and more outside kernel tree. That means the library
should follow good practices in library design and implementation to
play well with third party code that uses it.

One of such practices is to have a common prefix (or a few) for every
interface, function or data structure, library provides. I helps to
avoid name conflicts with other libraries and keeps API consistent.

Inconsistent names in libbpf already cause problems in real life. E.g.
an application can't use both libbpf and libnl due to conflicting
symbols.

Having common prefix will help to fix current and avoid future problems.

libbpf already uses the following prefixes for its interfaces:
* bpf_ for bpf system call wrappers, program/map/elf-object
  abstractions and a few other things;
* btf_ for BTF related API;
* libbpf_ for everything else.

The patch adds libbpf_ prefix to interfaces in nlattr.h that use none of
mentioned above prefixes and doesn't fit well into the first two
categories.

Since affected part of API is used in bpftool, the patch applies
corresponding change to bpftool as well. Having it in a separate patch
will cause a state of tree where bpftool is broken what may not be a
good idea.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/net.c            | 10 ++++--
 tools/bpf/bpftool/netlink_dumper.c | 32 ++++++++++---------
 tools/lib/bpf/netlink.c            | 10 +++---
 tools/lib/bpf/nlattr.c             | 64 ++++++++++++++++++++------------------
 tools/lib/bpf/nlattr.h             | 59 ++++++++++++++++++-----------------
 5 files changed, 94 insertions(+), 81 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index ef83e8a08490..d441bb7035ca 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -69,7 +69,9 @@ static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 	snprintf(netinfo->devices[netinfo->used_len].devname,
 		 sizeof(netinfo->devices[netinfo->used_len].devname),
 		 "%s",
-		 tb[IFLA_IFNAME] ? nla_getattr_str(tb[IFLA_IFNAME]) : "");
+		 tb[IFLA_IFNAME]
+			 ? libbpf_nla_getattr_str(tb[IFLA_IFNAME])
+			 : "");
 	netinfo->used_len++;
 
 	return do_xdp_dump(ifinfo, tb);
@@ -83,7 +85,7 @@ static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 	if (tcinfo->is_qdisc) {
 		/* skip clsact qdisc */
 		if (tb[TCA_KIND] &&
-		    strcmp(nla_data(tb[TCA_KIND]), "clsact") == 0)
+		    strcmp(libbpf_nla_data(tb[TCA_KIND]), "clsact") == 0)
 			return 0;
 		if (info->tcm_handle == 0)
 			return 0;
@@ -101,7 +103,9 @@ static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 	snprintf(tcinfo->handle_array[tcinfo->used_len].kind,
 		 sizeof(tcinfo->handle_array[tcinfo->used_len].kind),
 		 "%s",
-		 tb[TCA_KIND] ? nla_getattr_str(tb[TCA_KIND]) : "unknown");
+		 tb[TCA_KIND]
+			 ? libbpf_nla_getattr_str(tb[TCA_KIND])
+			 : "unknown");
 	tcinfo->used_len++;
 
 	return 0;
diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c
index 6f5e9cc6836c..4e9f4531269f 100644
--- a/tools/bpf/bpftool/netlink_dumper.c
+++ b/tools/bpf/bpftool/netlink_dumper.c
@@ -21,7 +21,7 @@ static void xdp_dump_prog_id(struct nlattr **tb, int attr,
 	if (new_json_object)
 		NET_START_OBJECT
 	NET_DUMP_STR("mode", " %s", mode);
-	NET_DUMP_UINT("id", " id %u", nla_getattr_u32(tb[attr]))
+	NET_DUMP_UINT("id", " id %u", libbpf_nla_getattr_u32(tb[attr]))
 	if (new_json_object)
 		NET_END_OBJECT
 }
@@ -32,13 +32,13 @@ static int do_xdp_dump_one(struct nlattr *attr, unsigned int ifindex,
 	struct nlattr *tb[IFLA_XDP_MAX + 1];
 	unsigned char mode;
 
-	if (nla_parse_nested(tb, IFLA_XDP_MAX, attr, NULL) < 0)
+	if (libbpf_nla_parse_nested(tb, IFLA_XDP_MAX, attr, NULL) < 0)
 		return -1;
 
 	if (!tb[IFLA_XDP_ATTACHED])
 		return 0;
 
-	mode = nla_getattr_u8(tb[IFLA_XDP_ATTACHED]);
+	mode = libbpf_nla_getattr_u8(tb[IFLA_XDP_ATTACHED]);
 	if (mode == XDP_ATTACHED_NONE)
 		return 0;
 
@@ -75,14 +75,14 @@ int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb)
 		return 0;
 
 	return do_xdp_dump_one(tb[IFLA_XDP], ifinfo->ifi_index,
-			       nla_getattr_str(tb[IFLA_IFNAME]));
+			       libbpf_nla_getattr_str(tb[IFLA_IFNAME]));
 }
 
 static int do_bpf_dump_one_act(struct nlattr *attr)
 {
 	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
 
-	if (nla_parse_nested(tb, TCA_ACT_BPF_MAX, attr, NULL) < 0)
+	if (libbpf_nla_parse_nested(tb, TCA_ACT_BPF_MAX, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	if (!tb[TCA_ACT_BPF_PARMS])
@@ -91,10 +91,10 @@ static int do_bpf_dump_one_act(struct nlattr *attr)
 	NET_START_OBJECT_NESTED2;
 	if (tb[TCA_ACT_BPF_NAME])
 		NET_DUMP_STR("name", "%s",
-			     nla_getattr_str(tb[TCA_ACT_BPF_NAME]));
+			     libbpf_nla_getattr_str(tb[TCA_ACT_BPF_NAME]));
 	if (tb[TCA_ACT_BPF_ID])
 		NET_DUMP_UINT("id", " id %u",
-			      nla_getattr_u32(tb[TCA_ACT_BPF_ID]));
+			      libbpf_nla_getattr_u32(tb[TCA_ACT_BPF_ID]));
 	NET_END_OBJECT_NESTED;
 	return 0;
 }
@@ -106,10 +106,11 @@ static int do_dump_one_act(struct nlattr *attr)
 	if (!attr)
 		return 0;
 
-	if (nla_parse_nested(tb, TCA_ACT_MAX, attr, NULL) < 0)
+	if (libbpf_nla_parse_nested(tb, TCA_ACT_MAX, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
-	if (tb[TCA_ACT_KIND] && strcmp(nla_data(tb[TCA_ACT_KIND]), "bpf") == 0)
+	if (tb[TCA_ACT_KIND] &&
+	    strcmp(libbpf_nla_data(tb[TCA_ACT_KIND]), "bpf") == 0)
 		return do_bpf_dump_one_act(tb[TCA_ACT_OPTIONS]);
 
 	return 0;
@@ -120,7 +121,7 @@ static int do_bpf_act_dump(struct nlattr *attr)
 	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
 	int act, ret;
 
-	if (nla_parse_nested(tb, TCA_ACT_MAX_PRIO, attr, NULL) < 0)
+	if (libbpf_nla_parse_nested(tb, TCA_ACT_MAX_PRIO, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	NET_START_ARRAY("act", " %s [");
@@ -139,13 +140,15 @@ static int do_bpf_filter_dump(struct nlattr *attr)
 	struct nlattr *tb[TCA_BPF_MAX + 1];
 	int ret;
 
-	if (nla_parse_nested(tb, TCA_BPF_MAX, attr, NULL) < 0)
+	if (libbpf_nla_parse_nested(tb, TCA_BPF_MAX, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	if (tb[TCA_BPF_NAME])
-		NET_DUMP_STR("name", " %s", nla_getattr_str(tb[TCA_BPF_NAME]));
+		NET_DUMP_STR("name", " %s",
+			     libbpf_nla_getattr_str(tb[TCA_BPF_NAME]));
 	if (tb[TCA_BPF_ID])
-		NET_DUMP_UINT("id", " id %u", nla_getattr_u32(tb[TCA_BPF_ID]));
+		NET_DUMP_UINT("id", " id %u",
+			      libbpf_nla_getattr_u32(tb[TCA_BPF_ID]));
 	if (tb[TCA_BPF_ACT]) {
 		ret = do_bpf_act_dump(tb[TCA_BPF_ACT]);
 		if (ret)
@@ -160,7 +163,8 @@ int do_filter_dump(struct tcmsg *info, struct nlattr **tb, const char *kind,
 {
 	int ret = 0;
 
-	if (tb[TCA_OPTIONS] && strcmp(nla_data(tb[TCA_KIND]), "bpf") == 0) {
+	if (tb[TCA_OPTIONS] &&
+	    strcmp(libbpf_nla_data(tb[TCA_KIND]), "bpf") == 0) {
 		NET_START_OBJECT;
 		if (devname[0] != '\0')
 			NET_DUMP_STR("devname", "%s", devname);
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 506bdfdbcab0..2d2edbbd8ae8 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -103,7 +103,7 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 				if (!err->error)
 					continue;
 				ret = err->error;
-				nla_dump_errormsg(nh);
+				libbpf_nla_dump_errormsg(nh);
 				goto done;
 			case NLMSG_DONE:
 				return 0;
@@ -190,7 +190,7 @@ static int __dump_link_nlmsg(struct nlmsghdr *nlh,
 
 	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi));
 	attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi)));
-	if (nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0)
+	if (libbpf_nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	return dump_link_nlmsg(cookie, ifi, tb);
@@ -228,7 +228,7 @@ static int __dump_class_nlmsg(struct nlmsghdr *nlh,
 
 	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
 	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
-	if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+	if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	return dump_class_nlmsg(cookie, t, tb);
@@ -267,7 +267,7 @@ static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh,
 
 	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
 	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
-	if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+	if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	return dump_qdisc_nlmsg(cookie, t, tb);
@@ -306,7 +306,7 @@ static int __dump_filter_nlmsg(struct nlmsghdr *nlh,
 
 	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
 	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
-	if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+	if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	return dump_filter_nlmsg(cookie, t, tb);
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
index 49f514119bdb..e52257a7367a 100644
--- a/tools/lib/bpf/nlattr.c
+++ b/tools/lib/bpf/nlattr.c
@@ -17,13 +17,13 @@
 #include <string.h>
 #include <stdio.h>
 
-static uint16_t nla_attr_minlen[NLA_TYPE_MAX+1] = {
-	[NLA_U8]	= sizeof(uint8_t),
-	[NLA_U16]	= sizeof(uint16_t),
-	[NLA_U32]	= sizeof(uint32_t),
-	[NLA_U64]	= sizeof(uint64_t),
-	[NLA_STRING]	= 1,
-	[NLA_FLAG]	= 0,
+static uint16_t nla_attr_minlen[LIBBPF_NLA_TYPE_MAX+1] = {
+	[LIBBPF_NLA_U8]		= sizeof(uint8_t),
+	[LIBBPF_NLA_U16]	= sizeof(uint16_t),
+	[LIBBPF_NLA_U32]	= sizeof(uint32_t),
+	[LIBBPF_NLA_U64]	= sizeof(uint64_t),
+	[LIBBPF_NLA_STRING]	= 1,
+	[LIBBPF_NLA_FLAG]	= 0,
 };
 
 static struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
@@ -47,9 +47,9 @@ static int nla_type(const struct nlattr *nla)
 }
 
 static int validate_nla(struct nlattr *nla, int maxtype,
-			struct nla_policy *policy)
+			struct libbpf_nla_policy *policy)
 {
-	struct nla_policy *pt;
+	struct libbpf_nla_policy *pt;
 	unsigned int minlen = 0;
 	int type = nla_type(nla);
 
@@ -58,23 +58,24 @@ static int validate_nla(struct nlattr *nla, int maxtype,
 
 	pt = &policy[type];
 
-	if (pt->type > NLA_TYPE_MAX)
+	if (pt->type > LIBBPF_NLA_TYPE_MAX)
 		return 0;
 
 	if (pt->minlen)
 		minlen = pt->minlen;
-	else if (pt->type != NLA_UNSPEC)
+	else if (pt->type != LIBBPF_NLA_UNSPEC)
 		minlen = nla_attr_minlen[pt->type];
 
-	if (nla_len(nla) < minlen)
+	if (libbpf_nla_len(nla) < minlen)
 		return -1;
 
-	if (pt->maxlen && nla_len(nla) > pt->maxlen)
+	if (pt->maxlen && libbpf_nla_len(nla) > pt->maxlen)
 		return -1;
 
-	if (pt->type == NLA_STRING) {
-		char *data = nla_data(nla);
-		if (data[nla_len(nla) - 1] != '\0')
+	if (pt->type == LIBBPF_NLA_STRING) {
+		char *data = libbpf_nla_data(nla);
+
+		if (data[libbpf_nla_len(nla) - 1] != '\0')
 			return -1;
 	}
 
@@ -104,15 +105,15 @@ static inline int nlmsg_len(const struct nlmsghdr *nlh)
  * @see nla_validate
  * @return 0 on success or a negative error code.
  */
-int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
-	      struct nla_policy *policy)
+int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head,
+		     int len, struct libbpf_nla_policy *policy)
 {
 	struct nlattr *nla;
 	int rem, err;
 
 	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
 
-	nla_for_each_attr(nla, head, len, rem) {
+	libbpf_nla_for_each_attr(nla, head, len, rem) {
 		int type = nla_type(nla);
 
 		if (type > maxtype)
@@ -144,23 +145,25 @@ errout:
  * @arg policy          Attribute validation policy.
  *
  * Feeds the stream of attributes nested into the specified attribute
- * to nla_parse().
+ * to libbpf_nla_parse().
  *
- * @see nla_parse
+ * @see libbpf_nla_parse
  * @return 0 on success or a negative error code.
  */
-int nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
-		     struct nla_policy *policy)
+int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype,
+			    struct nlattr *nla,
+			    struct libbpf_nla_policy *policy)
 {
-	return nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy);
+	return libbpf_nla_parse(tb, maxtype, libbpf_nla_data(nla),
+				libbpf_nla_len(nla), policy);
 }
 
 /* dump netlink extended ack error message */
-int nla_dump_errormsg(struct nlmsghdr *nlh)
+int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh)
 {
-	struct nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = {
-		[NLMSGERR_ATTR_MSG]	= { .type = NLA_STRING },
-		[NLMSGERR_ATTR_OFFS]	= { .type = NLA_U32 },
+	struct libbpf_nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = {
+		[NLMSGERR_ATTR_MSG]	= { .type = LIBBPF_NLA_STRING },
+		[NLMSGERR_ATTR_OFFS]	= { .type = LIBBPF_NLA_U32 },
 	};
 	struct nlattr *tb[NLMSGERR_ATTR_MAX + 1], *attr;
 	struct nlmsgerr *err;
@@ -181,14 +184,15 @@ int nla_dump_errormsg(struct nlmsghdr *nlh)
 	attr = (struct nlattr *) ((void *) err + hlen);
 	alen = nlh->nlmsg_len - hlen;
 
-	if (nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, extack_policy) != 0) {
+	if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen,
+			     extack_policy) != 0) {
 		fprintf(stderr,
 			"Failed to parse extended error attributes\n");
 		return 0;
 	}
 
 	if (tb[NLMSGERR_ATTR_MSG])
-		errmsg = (char *) nla_data(tb[NLMSGERR_ATTR_MSG]);
+		errmsg = (char *) libbpf_nla_data(tb[NLMSGERR_ATTR_MSG]);
 
 	fprintf(stderr, "Kernel error message: %s\n", errmsg);
 
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
index a6e2396bce7c..755a3312c87f 100644
--- a/tools/lib/bpf/nlattr.h
+++ b/tools/lib/bpf/nlattr.h
@@ -23,19 +23,19 @@
  * Standard attribute types to specify validation policy
  */
 enum {
-	NLA_UNSPEC,	/**< Unspecified type, binary data chunk */
-	NLA_U8,		/**< 8 bit integer */
-	NLA_U16,	/**< 16 bit integer */
-	NLA_U32,	/**< 32 bit integer */
-	NLA_U64,	/**< 64 bit integer */
-	NLA_STRING,	/**< NUL terminated character string */
-	NLA_FLAG,	/**< Flag */
-	NLA_MSECS,	/**< Micro seconds (64bit) */
-	NLA_NESTED,	/**< Nested attributes */
-	__NLA_TYPE_MAX,
+	LIBBPF_NLA_UNSPEC,	/**< Unspecified type, binary data chunk */
+	LIBBPF_NLA_U8,		/**< 8 bit integer */
+	LIBBPF_NLA_U16,		/**< 16 bit integer */
+	LIBBPF_NLA_U32,		/**< 32 bit integer */
+	LIBBPF_NLA_U64,		/**< 64 bit integer */
+	LIBBPF_NLA_STRING,	/**< NUL terminated character string */
+	LIBBPF_NLA_FLAG,	/**< Flag */
+	LIBBPF_NLA_MSECS,	/**< Micro seconds (64bit) */
+	LIBBPF_NLA_NESTED,	/**< Nested attributes */
+	__LIBBPF_NLA_TYPE_MAX,
 };
 
-#define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1)
+#define LIBBPF_NLA_TYPE_MAX (__LIBBPF_NLA_TYPE_MAX - 1)
 
 /**
  * @ingroup attr
@@ -43,8 +43,8 @@ enum {
  *
  * See section @core_doc{core_attr_parse,Attribute Parsing} for more details.
  */
-struct nla_policy {
-	/** Type of attribute or NLA_UNSPEC */
+struct libbpf_nla_policy {
+	/** Type of attribute or LIBBPF_NLA_UNSPEC */
 	uint16_t	type;
 
 	/** Minimal length of payload required */
@@ -62,49 +62,50 @@ struct nla_policy {
  * @arg len	length of attribute stream
  * @arg rem	initialized to len, holds bytes currently remaining in stream
  */
-#define nla_for_each_attr(pos, head, len, rem) \
+#define libbpf_nla_for_each_attr(pos, head, len, rem) \
 	for (pos = head, rem = len; \
 	     nla_ok(pos, rem); \
 	     pos = nla_next(pos, &(rem)))
 
 /**
- * nla_data - head of payload
+ * libbpf_nla_data - head of payload
  * @nla: netlink attribute
  */
-static inline void *nla_data(const struct nlattr *nla)
+static inline void *libbpf_nla_data(const struct nlattr *nla)
 {
 	return (char *) nla + NLA_HDRLEN;
 }
 
-static inline uint8_t nla_getattr_u8(const struct nlattr *nla)
+static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla)
 {
-	return *(uint8_t *)nla_data(nla);
+	return *(uint8_t *)libbpf_nla_data(nla);
 }
 
-static inline uint32_t nla_getattr_u32(const struct nlattr *nla)
+static inline uint32_t libbpf_nla_getattr_u32(const struct nlattr *nla)
 {
-	return *(uint32_t *)nla_data(nla);
+	return *(uint32_t *)libbpf_nla_data(nla);
 }
 
-static inline const char *nla_getattr_str(const struct nlattr *nla)
+static inline const char *libbpf_nla_getattr_str(const struct nlattr *nla)
 {
-	return (const char *)nla_data(nla);
+	return (const char *)libbpf_nla_data(nla);
 }
 
 /**
- * nla_len - length of payload
+ * libbpf_nla_len - length of payload
  * @nla: netlink attribute
  */
-static inline int nla_len(const struct nlattr *nla)
+static inline int libbpf_nla_len(const struct nlattr *nla)
 {
 	return nla->nla_len - NLA_HDRLEN;
 }
 
-int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
-	      struct nla_policy *policy);
-int nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
-		     struct nla_policy *policy);
+int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head,
+		     int len, struct libbpf_nla_policy *policy);
+int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype,
+			    struct nlattr *nla,
+			    struct libbpf_nla_policy *policy);
 
-int nla_dump_errormsg(struct nlmsghdr *nlh);
+int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh);
 
 #endif /* __NLATTR_H */
-- 
cgit v1.2.3


From 24d6a8084259e22acf9a80d4de3606a031f42f6d Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 3 Oct 2018 15:26:41 -0700
Subject: libbpf: Consistent prefixes for interfaces in str_error.h.

libbpf is used more and more outside kernel tree. That means the library
should follow good practices in library design and implementation to
play well with third party code that uses it.

One of such practices is to have a common prefix (or a few) for every
interface, function or data structure, library provides. I helps to
avoid name conflicts with other libraries and keeps API consistent.

Inconsistent names in libbpf already cause problems in real life. E.g.
an application can't use both libbpf and libnl due to conflicting
symbols.

Having common prefix will help to fix current and avoid future problems.

libbpf already uses the following prefixes for its interfaces:
* bpf_ for bpf system call wrappers, program/map/elf-object
  abstractions and a few other things;
* btf_ for BTF related API;
* libbpf_ for everything else.

The patch renames function in str_error.h to have libbpf_ prefix since it
misses one and doesn't fit well into the first two categories.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c    | 20 +++++++++++---------
 tools/lib/bpf/str_error.c |  2 +-
 tools/lib/bpf/str_error.h |  2 +-
 3 files changed, 13 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 9e68fd9fcfca..02888d36b805 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -470,7 +470,8 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 		obj->efile.fd = open(obj->path, O_RDONLY);
 		if (obj->efile.fd < 0) {
 			char errmsg[STRERR_BUFSIZE];
-			char *cp = str_error(errno, errmsg, sizeof(errmsg));
+			char *cp = libbpf_strerror_r(errno, errmsg,
+						     sizeof(errmsg));
 
 			pr_warning("failed to open %s: %s\n", obj->path, cp);
 			return -errno;
@@ -811,7 +812,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 						      data->d_size, name, idx);
 			if (err) {
 				char errmsg[STRERR_BUFSIZE];
-				char *cp = str_error(-err, errmsg, sizeof(errmsg));
+				char *cp = libbpf_strerror_r(-err, errmsg,
+							     sizeof(errmsg));
 
 				pr_warning("failed to alloc program %s (%s): %s",
 					   name, obj->path, cp);
@@ -1140,7 +1142,7 @@ bpf_object__create_maps(struct bpf_object *obj)
 
 		*pfd = bpf_create_map_xattr(&create_attr);
 		if (*pfd < 0 && create_attr.btf_key_type_id) {
-			cp = str_error(errno, errmsg, sizeof(errmsg));
+			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 			pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
 				   map->name, cp, errno);
 			create_attr.btf_fd = 0;
@@ -1155,7 +1157,7 @@ bpf_object__create_maps(struct bpf_object *obj)
 			size_t j;
 
 			err = *pfd;
-			cp = str_error(errno, errmsg, sizeof(errmsg));
+			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 			pr_warning("failed to create map (name: '%s'): %s\n",
 				   map->name, cp);
 			for (j = 0; j < i; j++)
@@ -1339,7 +1341,7 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
 	}
 
 	ret = -LIBBPF_ERRNO__LOAD;
-	cp = str_error(errno, errmsg, sizeof(errmsg));
+	cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 	pr_warning("load bpf program failed: %s\n", cp);
 
 	if (log_buf && log_buf[0] != '\0') {
@@ -1655,7 +1657,7 @@ static int check_path(const char *path)
 
 	dir = dirname(dname);
 	if (statfs(dir, &st_fs)) {
-		cp = str_error(errno, errmsg, sizeof(errmsg));
+		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 		pr_warning("failed to statfs %s: %s\n", dir, cp);
 		err = -errno;
 	}
@@ -1691,7 +1693,7 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 	}
 
 	if (bpf_obj_pin(prog->instances.fds[instance], path)) {
-		cp = str_error(errno, errmsg, sizeof(errmsg));
+		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 		pr_warning("failed to pin program: %s\n", cp);
 		return -errno;
 	}
@@ -1709,7 +1711,7 @@ static int make_dir(const char *path)
 		err = -errno;
 
 	if (err) {
-		cp = str_error(-err, errmsg, sizeof(errmsg));
+		cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
 		pr_warning("failed to mkdir %s: %s\n", path, cp);
 	}
 	return err;
@@ -1771,7 +1773,7 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 	}
 
 	if (bpf_obj_pin(map->fd, path)) {
-		cp = str_error(errno, errmsg, sizeof(errmsg));
+		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 		pr_warning("failed to pin map: %s\n", cp);
 		return -errno;
 	}
diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c
index b8798114a357..3d211b642cb5 100644
--- a/tools/lib/bpf/str_error.c
+++ b/tools/lib/bpf/str_error.c
@@ -9,7 +9,7 @@
  * libc, while checking strerror_r() return to avoid having to check this in
  * all places calling it.
  */
-char *str_error(int err, char *dst, int len)
+char *libbpf_strerror_r(int err, char *dst, int len)
 {
 	int ret = strerror_r(err, dst, len);
 	if (ret)
diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h
index 355b1db571d1..998eff7d6710 100644
--- a/tools/lib/bpf/str_error.h
+++ b/tools/lib/bpf/str_error.h
@@ -2,5 +2,5 @@
 #ifndef BPF_STR_ERROR
 #define BPF_STR_ERROR
 
-char *str_error(int err, char *dst, int len);
+char *libbpf_strerror_r(int err, char *dst, int len);
 #endif // BPF_STR_ERROR
-- 
cgit v1.2.3


From eff8190880c005e754d7d1bd315fc53a3ae9f876 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 3 Oct 2018 15:26:42 -0700
Subject: libbpf: Make include guards consistent

Rename include guards to have consistent names "__LIBBPF_<header_name>".

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/bpf.h       | 6 +++---
 tools/lib/bpf/btf.h       | 6 +++---
 tools/lib/bpf/libbpf.h    | 6 +++---
 tools/lib/bpf/nlattr.h    | 6 +++---
 tools/lib/bpf/str_error.h | 6 +++---
 5 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 6f38164b2618..4c78f61b7c71 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -20,8 +20,8 @@
  * You should have received a copy of the GNU Lesser General Public
  * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
-#ifndef __BPF_BPF_H
-#define __BPF_BPF_H
+#ifndef __LIBBPF_BPF_H
+#define __LIBBPF_BPF_H
 
 #include <linux/bpf.h>
 #include <stdbool.h>
@@ -111,4 +111,4 @@ int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
 int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
 		      __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset,
 		      __u64 *probe_addr);
-#endif
+#endif /* __LIBBPF_BPF_H */
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 4897e0724d4e..d5d20682eeb6 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -1,8 +1,8 @@
 /* SPDX-License-Identifier: LGPL-2.1 */
 /* Copyright (c) 2018 Facebook */
 
-#ifndef __BPF_BTF_H
-#define __BPF_BTF_H
+#ifndef __LIBBPF_BTF_H
+#define __LIBBPF_BTF_H
 
 #include <linux/types.h>
 
@@ -23,4 +23,4 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id);
 int btf__fd(const struct btf *btf);
 const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
 
-#endif
+#endif /* __LIBBPF_BTF_H */
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 710ff5724980..28f83dd6022b 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -20,8 +20,8 @@
  * You should have received a copy of the GNU Lesser General Public
  * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
-#ifndef __BPF_LIBBPF_H
-#define __BPF_LIBBPF_H
+#ifndef __LIBBPF_LIBBPF_H
+#define __LIBBPF_LIBBPF_H
 
 #include <stdio.h>
 #include <stdint.h>
@@ -315,4 +315,4 @@ int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
 			libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie);
 int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
 			 libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie);
-#endif
+#endif /* __LIBBPF_LIBBPF_H */
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
index 755a3312c87f..7198584a3040 100644
--- a/tools/lib/bpf/nlattr.h
+++ b/tools/lib/bpf/nlattr.h
@@ -11,8 +11,8 @@
  * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch>
  */
 
-#ifndef __NLATTR_H
-#define __NLATTR_H
+#ifndef __LIBBPF_NLATTR_H
+#define __LIBBPF_NLATTR_H
 
 #include <stdint.h>
 #include <linux/netlink.h>
@@ -108,4 +108,4 @@ int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype,
 
 int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh);
 
-#endif /* __NLATTR_H */
+#endif /* __LIBBPF_NLATTR_H */
diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h
index 998eff7d6710..b9157f5eebde 100644
--- a/tools/lib/bpf/str_error.h
+++ b/tools/lib/bpf/str_error.h
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: LGPL-2.1
-#ifndef BPF_STR_ERROR
-#define BPF_STR_ERROR
+#ifndef __LIBBPF_STR_ERROR_H
+#define __LIBBPF_STR_ERROR_H
 
 char *libbpf_strerror_r(int err, char *dst, int len);
-#endif // BPF_STR_ERROR
+#endif /* __LIBBPF_STR_ERROR_H */
-- 
cgit v1.2.3


From e5b0863c2064f2d40de9de4862317f9db4ccffff Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 3 Oct 2018 15:26:43 -0700
Subject: libbpf: Use __u32 instead of u32 in bpf_program__load
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make bpf_program__load consistent with other interfaces: use __u32
instead of u32. That in turn fixes build of samples:

In file included from ./samples/bpf/trace_output_user.c:21:0:
./tools/lib/bpf/libbpf.h:132:9: error: unknown type name ‘u32’
         u32 kern_version);
         ^

Fixes: commit 29cd77f41620d ("libbpf: Support loading individual progs")
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 2 +-
 tools/lib/bpf/libbpf.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 02888d36b805..85de1ebd4cb0 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1379,7 +1379,7 @@ out:
 
 int
 bpf_program__load(struct bpf_program *prog,
-		  char *license, u32 kern_version)
+		  char *license, __u32 kern_version)
 {
 	int err = 0, fd, i;
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 28f83dd6022b..fbfc2aec0f0d 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -129,7 +129,7 @@ void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex);
 const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
 
 int bpf_program__load(struct bpf_program *prog, char *license,
-		      u32 kern_version);
+		      __u32 kern_version);
 int bpf_program__fd(struct bpf_program *prog);
 int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 			      int instance);
-- 
cgit v1.2.3


From a0e11da78f487bc26ca7b14e4c9b40638623ebf6 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 4 Oct 2018 20:07:55 -0700
Subject: fib_tests: Add tests for metrics on routes

Add ipv4 and ipv6 test cases for metrics (mtu) when fib entries are
created. Can be used with kmemleak to see leaks with both fib entries
and dst_entry.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_tests.sh | 157 +++++++++++++++++++++++++++----
 1 file changed, 138 insertions(+), 19 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 0f45633bd634..491332713dd9 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -9,11 +9,11 @@ ret=0
 ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
-TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric"
+TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics"
 VERBOSE=0
 PAUSE_ON_FAIL=no
 PAUSE=no
-IP="ip -netns testns"
+IP="ip -netns ns1"
 
 log_test()
 {
@@ -47,8 +47,10 @@ log_test()
 setup()
 {
 	set -e
-	ip netns add testns
+	ip netns add ns1
 	$IP link set dev lo up
+	ip netns exec ns1 sysctl -qw net.ipv4.ip_forward=1
+	ip netns exec ns1 sysctl -qw net.ipv6.conf.all.forwarding=1
 
 	$IP link add dummy0 type dummy
 	$IP link set dev dummy0 up
@@ -61,7 +63,8 @@ setup()
 cleanup()
 {
 	$IP link del dev dummy0 &> /dev/null
-	ip netns del testns
+	ip netns del ns1
+	ip netns del ns2 &> /dev/null
 }
 
 get_linklocal()
@@ -639,11 +642,14 @@ add_initial_route6()
 
 check_route6()
 {
-	local pfx="2001:db8:104::/64"
+	local pfx
 	local expected="$1"
 	local out
 	local rc=0
 
+	set -- $expected
+	pfx=$1
+
 	out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//')
 	[ "${out}" = "${expected}" ] && return 0
 
@@ -690,28 +696,33 @@ route_setup()
 	[ "${VERBOSE}" = "1" ] && set -x
 	set -e
 
-	$IP li add red up type vrf table 101
+	ip netns add ns2
+	ip -netns ns2 link set dev lo up
+	ip netns exec ns2 sysctl -qw net.ipv4.ip_forward=1
+	ip netns exec ns2 sysctl -qw net.ipv6.conf.all.forwarding=1
+
 	$IP li add veth1 type veth peer name veth2
 	$IP li add veth3 type veth peer name veth4
 
 	$IP li set veth1 up
 	$IP li set veth3 up
-	$IP li set veth2 vrf red up
-	$IP li set veth4 vrf red up
-	$IP li add dummy1 type dummy
-	$IP li set dummy1 vrf red up
+	$IP li set veth2 netns ns2 up
+	$IP li set veth4 netns ns2 up
+	ip -netns ns2 li add dummy1 type dummy
+	ip -netns ns2 li set dummy1 up
 
 	$IP -6 addr add 2001:db8:101::1/64 dev veth1
-	$IP -6 addr add 2001:db8:101::2/64 dev veth2
 	$IP -6 addr add 2001:db8:103::1/64 dev veth3
-	$IP -6 addr add 2001:db8:103::2/64 dev veth4
-	$IP -6 addr add 2001:db8:104::1/64 dev dummy1
-
 	$IP addr add 172.16.101.1/24 dev veth1
-	$IP addr add 172.16.101.2/24 dev veth2
 	$IP addr add 172.16.103.1/24 dev veth3
-	$IP addr add 172.16.103.2/24 dev veth4
-	$IP addr add 172.16.104.1/24 dev dummy1
+
+	ip -netns ns2 -6 addr add 2001:db8:101::2/64 dev veth2
+	ip -netns ns2 -6 addr add 2001:db8:103::2/64 dev veth4
+	ip -netns ns2 -6 addr add 2001:db8:104::1/64 dev dummy1
+
+	ip -netns ns2 addr add 172.16.101.2/24 dev veth2
+	ip -netns ns2 addr add 172.16.103.2/24 dev veth4
+	ip -netns ns2 addr add 172.16.104.1/24 dev dummy1
 
 	set +ex
 }
@@ -944,7 +955,7 @@ ipv6_addr_metric_test()
 	log_test $rc 0 "Modify metric of address"
 
 	# verify prefix route removed on down
-	run_cmd "ip netns exec testns sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1"
+	run_cmd "ip netns exec ns1 sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1"
 	run_cmd "$IP li set dev dummy2 down"
 	rc=$?
 	if [ $rc -eq 0 ]; then
@@ -967,6 +978,74 @@ ipv6_addr_metric_test()
 	cleanup
 }
 
+ipv6_route_metrics_test()
+{
+	local rc
+
+	echo
+	echo "IPv6 routes with metrics"
+
+	route_setup
+
+	#
+	# single path with metrics
+	#
+	run_cmd "$IP -6 ro add 2001:db8:111::/64 via 2001:db8:101::2 mtu 1400"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6  "2001:db8:111::/64 via 2001:db8:101::2 dev veth1 metric 1024 mtu 1400"
+		rc=$?
+	fi
+	log_test $rc 0 "Single path route with mtu metric"
+
+
+	#
+	# multipath via separate routes with metrics
+	#
+	run_cmd "$IP -6 ro add 2001:db8:112::/64 via 2001:db8:101::2 mtu 1400"
+	run_cmd "$IP -6 ro append 2001:db8:112::/64 via 2001:db8:103::2"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6 "2001:db8:112::/64 metric 1024 mtu 1400 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+		rc=$?
+	fi
+	log_test $rc 0 "Multipath route via 2 single routes with mtu metric on first"
+
+	# second route is coalesced to first to make a multipath route.
+	# MTU of the second path is hidden from display!
+	run_cmd "$IP -6 ro add 2001:db8:113::/64 via 2001:db8:101::2"
+	run_cmd "$IP -6 ro append 2001:db8:113::/64 via 2001:db8:103::2 mtu 1400"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6 "2001:db8:113::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+		rc=$?
+	fi
+	log_test $rc 0 "Multipath route via 2 single routes with mtu metric on 2nd"
+
+	run_cmd "$IP -6 ro del 2001:db8:113::/64 via 2001:db8:101::2"
+	if [ $? -eq 0 ]; then
+		check_route6 "2001:db8:113::/64 via 2001:db8:103::2 dev veth3 metric 1024 mtu 1400"
+		log_test $? 0 "    MTU of second leg"
+	fi
+
+	#
+	# multipath with metrics
+	#
+	run_cmd "$IP -6 ro add 2001:db8:115::/64 mtu 1400 nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route6  "2001:db8:115::/64 metric 1024 mtu 1400 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+		rc=$?
+	fi
+	log_test $rc 0 "Multipath route with mtu metric"
+
+	$IP -6 ro add 2001:db8:104::/64 via 2001:db8:101::2 mtu 1300
+	run_cmd "ip netns exec ns1 ping6 -w1 -c1 -s 1500 2001:db8:104::1"
+	log_test $? 0 "Using route with mtu metric"
+
+	route_cleanup
+}
+
 # add route for a prefix, flushing any existing routes first
 # expected to be the first step of a test
 add_route()
@@ -1005,11 +1084,15 @@ add_initial_route()
 
 check_route()
 {
-	local pfx="172.16.104.0/24"
+	local pfx
 	local expected="$1"
 	local out
 	local rc=0
 
+	set -- $expected
+	pfx=$1
+	[ "${pfx}" = "unreachable" ] && pfx=$2
+
 	out=$($IP ro ls match ${pfx})
 	[ "${out}" = "${expected}" ] && return 0
 
@@ -1319,6 +1402,40 @@ ipv4_addr_metric_test()
 	cleanup
 }
 
+ipv4_route_metrics_test()
+{
+	local rc
+
+	echo
+	echo "IPv4 route add / append tests"
+
+	route_setup
+
+	run_cmd "$IP ro add 172.16.111.0/24 via 172.16.101.2 mtu 1400"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route "172.16.111.0/24 via 172.16.101.2 dev veth1 mtu 1400"
+		rc=$?
+	fi
+	log_test $rc 0 "Single path route with mtu metric"
+
+
+	run_cmd "$IP ro add 172.16.112.0/24 mtu 1400 nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route "172.16.112.0/24 mtu 1400 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1"
+		rc=$?
+	fi
+	log_test $rc 0 "Multipath route with mtu metric"
+
+	$IP ro add 172.16.104.0/24 via 172.16.101.2 mtu 1300
+	run_cmd "ip netns exec ns1 ping -w1 -c1 -s 1500 172.16.104.1"
+	log_test $? 0 "Using route with mtu metric"
+
+	route_cleanup
+}
+
+
 ################################################################################
 # usage
 
@@ -1385,6 +1502,8 @@ do
 	ipv4_route_test|ipv4_rt)	ipv4_route_test;;
 	ipv6_addr_metric)		ipv6_addr_metric_test;;
 	ipv4_addr_metric)		ipv4_addr_metric_test;;
+	ipv6_route_metrics)		ipv6_route_metrics_test;;
+	ipv4_route_metrics)		ipv4_route_metrics_test;;
 
 	help) echo "Test names: $TESTS"; exit 0;;
 	esac
-- 
cgit v1.2.3


From 05a2f54679861deb188750ba2a70187000b2c71f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 18 Sep 2018 16:08:02 -0300
Subject: perf python: Use -Wno-redundant-decls to build with PYTHON=python3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When building in ClearLinux using 'make PYTHON=python3' with gcc 8.2.1
it fails with:

    GEN      /tmp/build/perf/python/perf.so
  In file included from /usr/include/python3.7m/Python.h:126,
                   from /git/linux/tools/perf/util/python.c:2:
  /usr/include/python3.7m/import.h:58:24: error: redundant redeclaration of ‘_PyImport_AddModuleObject’ [-Werror=redundant-decls]
   PyAPI_FUNC(PyObject *) _PyImport_AddModuleObject(PyObject *, PyObject *);
                          ^~~~~~~~~~~~~~~~~~~~~~~~~
  /usr/include/python3.7m/import.h:47:24: note: previous declaration of ‘_PyImport_AddModuleObject’ was here
   PyAPI_FUNC(PyObject *) _PyImport_AddModuleObject(PyObject *name,
                          ^~~~~~~~~~~~~~~~~~~~~~~~~
  cc1: all warnings being treated as errors
  error: command 'gcc' failed with exit status 1

And indeed there is a redundant declaration in that Python.h file, one
with parameter names and the other without, so just add
-Wno-error=redundant-decls to the python setup instructions.

Now perf builds with gcc in ClearLinux with the following Dockerfile:

  # docker.io/acmel/linux-perf-tools-build-clearlinux:latest
  FROM docker.io/clearlinux:latest
  MAINTAINER Arnaldo Carvalho de Melo <acme@kernel.org>
  RUN swupd update && \
      swupd bundle-add sysadmin-basic-dev
  RUN mkdir -m 777 -p /git /tmp/build/perf /tmp/build/objtool /tmp/build/linux && \
      groupadd -r perfbuilder && \
      useradd -m -r -g perfbuilder perfbuilder && \
      chown -R perfbuilder.perfbuilder /tmp/build/ /git/
  USER perfbuilder
  COPY rx_and_build.sh /
  ENV EXTRA_MAKE_ARGS=PYTHON=python3
  ENTRYPOINT ["/rx_and_build.sh"]

Now to figure out why the build fails with clang, that is present in the
above container as detected by the rx_and_build.sh script:

  clang version 6.0.1 (tags/RELEASE_601/final)
  Target: x86_64-unknown-linux-gnu
  Thread model: posix
  InstalledDir: /usr/sbin
  make: Entering directory '/git/linux/tools/perf'
    BUILD:   Doing 'make -j4' parallel build
    HOSTCC   /tmp/build/perf/fixdep.o
    HOSTLD   /tmp/build/perf/fixdep-in.o
    LINK     /tmp/build/perf/fixdep

  Auto-detecting system features:
  ...                         dwarf: [ OFF ]
  ...            dwarf_getlocations: [ OFF ]
  ...                         glibc: [ OFF ]
  ...                          gtk2: [ OFF ]
  ...                      libaudit: [ OFF ]
  ...                        libbfd: [ OFF ]
  ...                        libelf: [ OFF ]
  ...                       libnuma: [ OFF ]
  ...        numa_num_possible_cpus: [ OFF ]
  ...                       libperl: [ OFF ]
  ...                     libpython: [ OFF ]
  ...                      libslang: [ OFF ]
  ...                     libcrypto: [ OFF ]
  ...                     libunwind: [ OFF ]
  ...            libdw-dwarf-unwind: [ OFF ]
  ...                          zlib: [ OFF ]
  ...                          lzma: [ OFF ]
  ...                     get_cpuid: [ OFF ]
  ...                           bpf: [ OFF ]

  Makefile.config:331: *** No gnu/libc-version.h found, please install glibc-dev[el].  Stop.
  make[1]: *** [Makefile.perf:206: sub-make] Error 2
  make: *** [Makefile:70: all] Error 2
  make: Leaving directory '/git/linux/tools/perf'

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thiago Macieira <thiago.macieira@intel.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-c3khb9ac86s00qxzjrueomme@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/setup.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 97efbcad076e..1942f6dd24f6 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -35,7 +35,7 @@ class install_lib(_install_lib):
 
 cflags = getenv('CFLAGS', '').split()
 # switch off several checks (need to be at the end of cflags list)
-cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ]
+cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls' ]
 if cc != "clang":
     cflags += ['-Wno-cast-function-type' ]
 
-- 
cgit v1.2.3


From 7a8a8fcf7b860e4b2d4edc787c844d41cad9dfcf Mon Sep 17 00:00:00 2001
From: Milian Wolff <milian.wolff@kdab.com>
Date: Wed, 26 Sep 2018 15:52:06 +0200
Subject: perf record: Use unmapped IP for inline callchain cursors

Only use the mapped IP to find inline frames, but keep using the
unmapped IP for the callchain cursor. This ensures we properly show the
unmapped IP when displaying a frame we received via the
dso__parse_addr_inlines API for a module which does not contain
sufficient debug symbols to show the srcline.

This is another follow-up to commit 19610184693c ("perf script: Show
virtual addresses instead of offsets").

Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Sandipan Das <sandipan@linux.ibm.com>
Fixes: 19610184693c ("perf script: Show virtual addresses instead of offsets")
Link: http://lkml.kernel.org/r/20180926135207.30263-2-milian.wolff@kdab.com
Link: http://lkml.kernel.org/r/20181002073949.3297-1-milian.wolff@kdab.com
[ Squashed a fix from Milian for a problem reported by Ravi, fixed up space damage ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/machine.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 0cb4f8bf3ca7..111ae858cbcb 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2286,7 +2286,8 @@ static int append_inlines(struct callchain_cursor *cursor,
 	if (!symbol_conf.inline_name || !map || !sym)
 		return ret;
 
-	addr = map__rip_2objdump(map, ip);
+	addr = map__map_ip(map, ip);
+	addr = map__rip_2objdump(map, addr);
 
 	inline_node = inlines__tree_find(&map->dso->inlined_nodes, addr);
 	if (!inline_node) {
-- 
cgit v1.2.3


From 226407dd0311eebfb55a63deae9a9dcf71f920af Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 5 Oct 2018 10:01:19 -0700
Subject: fib_tests: Add tests for invalid metric on route

Add ipv4 and ipv6 test cases with an invalid metrics option causing
ip_metrics_convert to fail. Tests clean up path during route add.

Also, add nodad to to ipv6 address add. When running ipv6_route_metrics
directly seeing an occasional failure on the "Using route with mtu metric"
test case.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_tests.sh | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 491332713dd9..802b4af18729 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -711,14 +711,14 @@ route_setup()
 	ip -netns ns2 li add dummy1 type dummy
 	ip -netns ns2 li set dummy1 up
 
-	$IP -6 addr add 2001:db8:101::1/64 dev veth1
-	$IP -6 addr add 2001:db8:103::1/64 dev veth3
+	$IP -6 addr add 2001:db8:101::1/64 dev veth1 nodad
+	$IP -6 addr add 2001:db8:103::1/64 dev veth3 nodad
 	$IP addr add 172.16.101.1/24 dev veth1
 	$IP addr add 172.16.103.1/24 dev veth3
 
-	ip -netns ns2 -6 addr add 2001:db8:101::2/64 dev veth2
-	ip -netns ns2 -6 addr add 2001:db8:103::2/64 dev veth4
-	ip -netns ns2 -6 addr add 2001:db8:104::1/64 dev dummy1
+	ip -netns ns2 -6 addr add 2001:db8:101::2/64 dev veth2 nodad
+	ip -netns ns2 -6 addr add 2001:db8:103::2/64 dev veth4 nodad
+	ip -netns ns2 -6 addr add 2001:db8:104::1/64 dev dummy1 nodad
 
 	ip -netns ns2 addr add 172.16.101.2/24 dev veth2
 	ip -netns ns2 addr add 172.16.103.2/24 dev veth4
@@ -1043,6 +1043,9 @@ ipv6_route_metrics_test()
 	run_cmd "ip netns exec ns1 ping6 -w1 -c1 -s 1500 2001:db8:104::1"
 	log_test $? 0 "Using route with mtu metric"
 
+	run_cmd "$IP -6 ro add 2001:db8:114::/64 via  2001:db8:101::2  congctl lock foo"
+	log_test $? 2 "Invalid metric (fails metric_convert)"
+
 	route_cleanup
 }
 
@@ -1432,6 +1435,9 @@ ipv4_route_metrics_test()
 	run_cmd "ip netns exec ns1 ping -w1 -c1 -s 1500 172.16.104.1"
 	log_test $? 0 "Using route with mtu metric"
 
+	run_cmd "$IP ro add 172.16.111.0/24 via 172.16.101.2 congctl lock foo"
+	log_test $? 2 "Invalid metric (fails metric_convert)"
+
 	route_cleanup
 }
 
-- 
cgit v1.2.3


From cf5eafbfa586d030f9321cee516b91d089e38280 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 4 Oct 2018 18:34:38 +0200
Subject: tc-testing: fix build of eBPF programs

rely on uAPI headers in the current kernel tree, rather than requiring the
correct version installed on the test system. While at it, group all
sections in a single binary and test the 'section' parameter.

Reported-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/bpf/Makefile    | 29 ++++++++++++++++++++++
 tools/testing/selftests/tc-testing/bpf/action.c    | 23 +++++++++++++++++
 .../selftests/tc-testing/tc-tests/actions/bpf.json | 16 ++++++------
 tools/testing/selftests/tc-testing/tdc_config.py   |  4 ++-
 4 files changed, 63 insertions(+), 9 deletions(-)
 create mode 100644 tools/testing/selftests/tc-testing/bpf/Makefile
 create mode 100644 tools/testing/selftests/tc-testing/bpf/action.c

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/bpf/Makefile b/tools/testing/selftests/tc-testing/bpf/Makefile
new file mode 100644
index 000000000000..dc92eb271d9a
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/bpf/Makefile
@@ -0,0 +1,29 @@
+# SPDX-License-Identifier: GPL-2.0
+
+APIDIR := ../../../../include/uapi
+TEST_GEN_FILES = action.o
+
+top_srcdir = ../../../../..
+include ../../lib.mk
+
+CLANG ?= clang
+LLC   ?= llc
+PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1)
+
+ifeq ($(PROBE),)
+  CPU ?= probe
+else
+  CPU ?= generic
+endif
+
+CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \
+	| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }')
+
+CLANG_FLAGS = -I. -I$(APIDIR) \
+	      $(CLANG_SYS_INCLUDES) \
+	      -Wno-compare-distinct-pointer-types
+
+$(OUTPUT)/%.o: %.c
+	$(CLANG) $(CLANG_FLAGS) \
+		 -O2 -target bpf -emit-llvm -c $< -o - |      \
+	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
diff --git a/tools/testing/selftests/tc-testing/bpf/action.c b/tools/testing/selftests/tc-testing/bpf/action.c
new file mode 100644
index 000000000000..c32b99b80e19
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/bpf/action.c
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Copyright (c) 2018 Davide Caratti, Red Hat inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+
+__attribute__((section("action-ok"),used)) int action_ok(struct __sk_buff *s)
+{
+	return TC_ACT_OK;
+}
+
+__attribute__((section("action-ko"),used)) int action_ko(struct __sk_buff *s)
+{
+	s->data = 0x0;
+	return TC_ACT_OK;
+}
+
+char _license[] __attribute__((section("license"),used)) = "GPL";
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
index 6f289a49e5ec..1a9b282dd0be 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
@@ -55,7 +55,7 @@
             "bpf"
         ],
         "setup": [
-            "printf '#include <linux/bpf.h>\nchar l[] __attribute__((section(\"license\"),used))=\"GPL\"; __attribute__((section(\"action\"),used)) int m(struct __sk_buff *s) { return 2; }' | clang -O2 -x c -c - -target bpf -o _b.o",
+            "make -C bpf",
             [
                 "$TC action flush action bpf",
                 0,
@@ -63,14 +63,14 @@
                 255
             ]
         ],
-        "cmdUnderTest": "$TC action add action bpf object-file _b.o index 667",
+        "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ok index 667",
         "expExitCode": "0",
         "verifyCmd": "$TC action get action bpf index 667",
-        "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c( jited)? default-action pipe.*index 667 ref",
+        "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9]* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref",
         "matchCount": "1",
         "teardown": [
             "$TC action flush action bpf",
-            "rm -f _b.o"
+            "make -C bpf clean"
         ]
     },
     {
@@ -81,7 +81,7 @@
             "bpf"
         ],
         "setup": [
-            "printf '#include <linux/bpf.h>\nchar l[] __attribute__((section(\"license\"),used))=\"GPL\"; __attribute__((section(\"action\"),used)) int m(struct __sk_buff *s) { s->data = 0x0; return 2; }' | clang -O2 -x c -c - -target bpf -o _c.o",
+            "make -C bpf",
             [
                 "$TC action flush action bpf",
                 0,
@@ -89,10 +89,10 @@
                 255
             ]
         ],
-        "cmdUnderTest": "$TC action add action bpf object-file _c.o index 667",
+        "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ko index 667",
         "expExitCode": "255",
         "verifyCmd": "$TC action get action bpf index 667",
-        "matchPattern": "action order [0-9]*: bpf _c.o:\\[action\\] id [0-9].*index 667 ref",
+        "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ko\\] id [0-9].*index 667 ref",
         "matchCount": "0",
         "teardown": [
             [
@@ -101,7 +101,7 @@
                 1,
                 255
             ],
-            "rm -f _c.o"
+            "make -C bpf clean"
         ]
     },
     {
diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py
index a023d0d62b25..d651bc1501bd 100644
--- a/tools/testing/selftests/tc-testing/tdc_config.py
+++ b/tools/testing/selftests/tc-testing/tdc_config.py
@@ -16,7 +16,9 @@ NAMES = {
           'DEV2': '',
           'BATCH_FILE': './batch.txt',
           # Name of the namespace to use
-          'NS': 'tcut'
+          'NS': 'tcut',
+          # Directory containing eBPF test programs
+          'EBPFDIR': './bpf'
         }
 
 
-- 
cgit v1.2.3


From 4c2d39bd40c1f34975bec070a8e43fa573a9c327 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 4 Oct 2018 18:34:39 +0200
Subject: tc-testing: use a plugin to build eBPF program

use a TDC plugin, instead of building eBPF programs in the 'setup' stage.
'-B' argument can be used to build eBPF programs in $EBPFDIR directory,
in the 'pre-suite' stage. Binaries are then cleaned in 'post-suite' stage.

Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/README          |  2 +
 .../tc-testing/plugin-lib/buildebpfPlugin.py       | 66 ++++++++++++++++++++++
 .../selftests/tc-testing/tc-tests/actions/bpf.json |  8 +--
 3 files changed, 70 insertions(+), 6 deletions(-)
 create mode 100644 tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/README b/tools/testing/selftests/tc-testing/README
index 49a6f8c3fdae..f9281e8aa313 100644
--- a/tools/testing/selftests/tc-testing/README
+++ b/tools/testing/selftests/tc-testing/README
@@ -232,6 +232,8 @@ directory:
       and the other is a test whether the command leaked memory or not.
       (This one is a preliminary version, it may not work quite right yet,
       but the overall template is there and it should only need tweaks.)
+  - buildebpfPlugin.py:
+      builds all programs in $EBPFDIR.
 
 
 ACKNOWLEDGEMENTS
diff --git a/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py
new file mode 100644
index 000000000000..9f0ba10c44b4
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py
@@ -0,0 +1,66 @@
+'''
+build ebpf program
+'''
+
+import os
+import signal
+from string import Template
+import subprocess
+import time
+from TdcPlugin import TdcPlugin
+from tdc_config import *
+
+class SubPlugin(TdcPlugin):
+    def __init__(self):
+        self.sub_class = 'buildebpf/SubPlugin'
+        self.tap = ''
+        super().__init__()
+
+    def pre_suite(self, testcount, testidlist):
+        super().pre_suite(testcount, testidlist)
+
+        if self.args.buildebpf:
+            self._ebpf_makeall()
+
+    def post_suite(self, index):
+        super().post_suite(index)
+
+        self._ebpf_makeclean()
+
+    def add_args(self, parser):
+        super().add_args(parser)
+
+        self.argparser_group = self.argparser.add_argument_group(
+            'buildebpf',
+            'options for buildebpfPlugin')
+        self.argparser_group.add_argument(
+            '-B', '--buildebpf', action='store_true',
+            help='build eBPF programs')
+
+        return self.argparser
+
+    def _ebpf_makeall(self):
+        if self.args.buildebpf:
+            self._make('all')
+
+    def _ebpf_makeclean(self):
+        if self.args.buildebpf:
+            self._make('clean')
+
+    def _make(self, target):
+        command = 'make -C {} {}'.format(self.args.NAMES['EBPFDIR'], target)
+        proc = subprocess.Popen(command,
+            shell=True,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            env=ENVIR)
+        (rawout, serr) = proc.communicate()
+
+        if proc.returncode != 0 and len(serr) > 0:
+            foutput = serr.decode("utf-8")
+        else:
+            foutput = rawout.decode("utf-8")
+
+        proc.stdout.close()
+        proc.stderr.close()
+        return proc, foutput
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
index 1a9b282dd0be..5970cee6d05f 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
@@ -55,7 +55,6 @@
             "bpf"
         ],
         "setup": [
-            "make -C bpf",
             [
                 "$TC action flush action bpf",
                 0,
@@ -69,8 +68,7 @@
         "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9]* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref",
         "matchCount": "1",
         "teardown": [
-            "$TC action flush action bpf",
-            "make -C bpf clean"
+            "$TC action flush action bpf"
         ]
     },
     {
@@ -81,7 +79,6 @@
             "bpf"
         ],
         "setup": [
-            "make -C bpf",
             [
                 "$TC action flush action bpf",
                 0,
@@ -100,8 +97,7 @@
                 0,
                 1,
                 255
-            ],
-            "make -C bpf clean"
+            ]
         ]
     },
     {
-- 
cgit v1.2.3


From 6f8474922b443fd4a89a5dd5b891a3c6a144b9c7 Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jakub@cloudflare.com>
Date: Fri, 5 Oct 2018 10:19:57 +0200
Subject: selftests: net: Clean up an unused variable

Address compiler warning:

ip_defrag.c: In function 'send_udp_frags':
ip_defrag.c:206:16: warning: unused variable 'udphdr' [-Wunused-variable]
  struct udphdr udphdr;
                ^~~~~~

Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/ip_defrag.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/ip_defrag.c b/tools/testing/selftests/net/ip_defrag.c
index 2366dc6bce71..61ae2782388e 100644
--- a/tools/testing/selftests/net/ip_defrag.c
+++ b/tools/testing/selftests/net/ip_defrag.c
@@ -203,7 +203,6 @@ static void send_udp_frags(int fd_raw, struct sockaddr *addr,
 {
 	struct ip *iphdr = (struct ip *)ip_frame;
 	struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame;
-	struct udphdr udphdr;
 	int res;
 	int offset;
 	int frag_len;
-- 
cgit v1.2.3


From 1bc38b8ff6cc54b1cd925525c0a9ffa7eef4d23b Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Fri, 5 Oct 2018 16:40:00 -0700
Subject: libbpf: relicense libbpf as LGPL-2.1 OR BSD-2-Clause
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

libbpf is maturing as a library and gaining features that no other bpf libraries support
(BPF Type Format, bpf to bpf calls, etc)
Many Apache2 licensed projects (like bcc, bpftrace, gobpf, cilium, etc)
would like to use libbpf, but cannot do this yet, since Apache Foundation explicitly
states that LGPL is incompatible with Apache2.
Hence let's relicense libbpf as dual license LGPL-2.1 or BSD-2-Clause,
since BSD-2 is compatible with Apache2.
Dual LGPL or Apache2 is invalid combination.
Fix license mistake in Makefile as well.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: David Beckett <david.beckett@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Joe Stringer <joe@ovn.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Acked-by: Roman Gushchin <guro@fb.com>
Acked-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/Makefile       |  2 +-
 tools/lib/bpf/bpf.c          |  2 +-
 tools/lib/bpf/bpf.h          |  2 +-
 tools/lib/bpf/btf.c          |  2 +-
 tools/lib/bpf/btf.h          |  2 +-
 tools/lib/bpf/libbpf.c       | 15 +--------------
 tools/lib/bpf/libbpf.h       | 15 +--------------
 tools/lib/bpf/libbpf_errno.c | 15 +--------------
 tools/lib/bpf/netlink.c      |  2 +-
 tools/lib/bpf/nlattr.c       |  7 +------
 tools/lib/bpf/nlattr.h       |  7 +------
 tools/lib/bpf/str_error.c    |  2 +-
 tools/lib/bpf/str_error.h    |  2 +-
 13 files changed, 13 insertions(+), 62 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index d49902e818b5..6ad27257fd67 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 # Most of this file is copied from tools/lib/traceevent/Makefile
 
 BPF_VERSION = 0
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 3878a26a2071..d70a255cb05e 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
 /*
  * common eBPF ELF operations.
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 4c78f61b7c71..87520a87a75f 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 
 /*
  * common eBPF ELF operations.
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index cf94b0770522..449591aa9900 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 /* Copyright (c) 2018 Facebook */
 
 #include <stdlib.h>
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index d5d20682eeb6..6db5462bb2ef 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 /* Copyright (c) 2018 Facebook */
 
 #ifndef __LIBBPF_BTF_H
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 85de1ebd4cb0..ceb918c14d80 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
 /*
  * Common eBPF ELF object loading operations.
@@ -7,19 +7,6 @@
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015 Huawei Inc.
  * Copyright (C) 2017 Nicira, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation;
- * version 2.1 of the License (not later!)
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
 
 #define _GNU_SOURCE
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index fbfc2aec0f0d..8af8d3663991 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 
 /*
  * Common eBPF ELF object loading operations.
@@ -6,19 +6,6 @@
  * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015 Huawei Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation;
- * version 2.1 of the License (not later!)
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
 #ifndef __LIBBPF_LIBBPF_H
 #define __LIBBPF_LIBBPF_H
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
index 2464ade3b326..d83b17f8435c 100644
--- a/tools/lib/bpf/libbpf_errno.c
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -1,23 +1,10 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
 /*
  * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015 Huawei Inc.
  * Copyright (C) 2017 Nicira, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation;
- * version 2.1 of the License (not later!)
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
 
 #include <stdio.h>
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 2d2edbbd8ae8..0ce67aea8f3b 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 /* Copyright (c) 2018 Facebook */
 
 #include <stdlib.h>
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
index e52257a7367a..1e69c0c8d413 100644
--- a/tools/lib/bpf/nlattr.c
+++ b/tools/lib/bpf/nlattr.c
@@ -1,13 +1,8 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 
 /*
  * NETLINK      Netlink attributes
  *
- *	This library is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU Lesser General Public
- *	License as published by the Free Software Foundation version 2.1
- *	of the License.
- *
  * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch>
  */
 
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
index 7198584a3040..6cc3ac91690f 100644
--- a/tools/lib/bpf/nlattr.h
+++ b/tools/lib/bpf/nlattr.h
@@ -1,13 +1,8 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 
 /*
  * NETLINK      Netlink attributes
  *
- *	This library is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU Lesser General Public
- *	License as published by the Free Software Foundation version 2.1
- *	of the License.
- *
  * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch>
  */
 
diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c
index 3d211b642cb5..00e48ac5b806 100644
--- a/tools/lib/bpf/str_error.c
+++ b/tools/lib/bpf/str_error.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 #undef _GNU_SOURCE
 #include <string.h>
 #include <stdio.h>
diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h
index b9157f5eebde..a139334d57b6 100644
--- a/tools/lib/bpf/str_error.h
+++ b/tools/lib/bpf/str_error.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: LGPL-2.1
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 #ifndef __LIBBPF_STR_ERROR_H
 #define __LIBBPF_STR_ERROR_H
 
-- 
cgit v1.2.3


From 262f9d811c7608f1e74258ceecfe1fa213bdf912 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 5 Oct 2018 19:38:46 -0700
Subject: bpf: do not blindly change rlimit in reuseport net selftest

If the current process has unlimited RLIMIT_MEMLOCK,
we should should leave it as is.

Fixes: 941ff6f11c02 ("bpf: fix rlimit in reuseport net selftest")
Signed-off-by: John Sperbeck <jsperbeck@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/net/reuseport_bpf.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/reuseport_bpf.c b/tools/testing/selftests/net/reuseport_bpf.c
index cad14cd0ea92..b5277106df1f 100644
--- a/tools/testing/selftests/net/reuseport_bpf.c
+++ b/tools/testing/selftests/net/reuseport_bpf.c
@@ -437,14 +437,19 @@ void enable_fastopen(void)
 	}
 }
 
-static struct rlimit rlim_old, rlim_new;
+static struct rlimit rlim_old;
 
 static  __attribute__((constructor)) void main_ctor(void)
 {
 	getrlimit(RLIMIT_MEMLOCK, &rlim_old);
-	rlim_new.rlim_cur = rlim_old.rlim_cur + (1UL << 20);
-	rlim_new.rlim_max = rlim_old.rlim_max + (1UL << 20);
-	setrlimit(RLIMIT_MEMLOCK, &rlim_new);
+
+	if (rlim_old.rlim_cur != RLIM_INFINITY) {
+		struct rlimit rlim_new;
+
+		rlim_new.rlim_cur = rlim_old.rlim_cur + (1UL << 20);
+		rlim_new.rlim_max = rlim_old.rlim_max + (1UL << 20);
+		setrlimit(RLIMIT_MEMLOCK, &rlim_new);
+	}
 }
 
 static __attribute__((destructor)) void main_dtor(void)
-- 
cgit v1.2.3


From 4312f2ab136a5f1a7b247f6e4a75b95afaf9d23b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 8 Oct 2018 12:04:51 -0300
Subject: tools arch uapi: Sync the x86 kvm.h copy

To get the changes in:

  d1766202779e ("x86/kvm/lapic: always disable MMIO interface in x2APIC mode")

That at this time will not generate changes in tools such as 'perf trace',
that still needs more work in tools/perf/examples/bpf/augmented_syscalls.c
to need such id -> string tables.

This silences the following perf build warning:

  Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/kvm.h' differs from latest version at 'arch/x86/include/uapi/asm/kvm.h'
  diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-yadntj2ok6zpzjwi656onuh0@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/uapi/asm/kvm.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 86299efa804a..fd23d5778ea1 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -377,6 +377,7 @@ struct kvm_sync_regs {
 
 #define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)
 #define KVM_X86_QUIRK_CD_NW_CLEARED	(1 << 1)
+#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE	(1 << 2)
 
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
-- 
cgit v1.2.3


From 25fe15e54fe5e15b4963fe101f7cd8bad4f11393 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 8 Oct 2018 12:09:14 -0300
Subject: tools headers uapi: Sync kvm.h copy

To pick up the changes introduced in:

  6fbbde9a1969 ("KVM: x86: Control guest reads of MSR_PLATFORM_INFO")

That is not yet used in tools such as 'perf trace'.

The type of the change in this file, a simple integer parameter to the
KVM_CHECK_EXTENSION ioctl should be easier to implement tho, adding to
the libbeauty TODO list.

This silences this perf build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h'
  diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Drew Schmitt <dasch@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-67h1bio5bihi1q6dy7hgwwx8@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/kvm.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 07548de5c988..251be353f950 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -952,6 +952,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_HPAGE_1M 156
 #define KVM_CAP_NESTED_STATE 157
 #define KVM_CAP_ARM_INJECT_SERROR_ESR 158
+#define KVM_CAP_MSR_PLATFORM_INFO 159
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3


From 8c22e2f695920ebd94f9a53bcf2a65eb36d4dba1 Mon Sep 17 00:00:00 2001
From: Prarit Bhargava <prarit@redhat.com>
Date: Mon, 8 Oct 2018 11:06:18 -0400
Subject: cpupower: Fix AMD Family 0x17 msr_pstate size

The msr_pstate data is only 63 bits long and should be 64 bits.

Add in the missing bit from res1 for AMD Family 0x17.

Reference: https://www.amd.com/system/files/TechDocs/54945_PPR_Family_17h_Models_00h-0Fh.pdf, page 138.

Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Stafford Horne <shorne@gmail.com>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/power/cpupower/utils/helpers/amd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/power/cpupower/utils/helpers/amd.c b/tools/power/cpupower/utils/helpers/amd.c
index bb41cdd0df6b..eed31b27909b 100644
--- a/tools/power/cpupower/utils/helpers/amd.c
+++ b/tools/power/cpupower/utils/helpers/amd.c
@@ -33,7 +33,7 @@ union msr_pstate {
 		unsigned vid:8;
 		unsigned iddval:8;
 		unsigned idddiv:2;
-		unsigned res1:30;
+		unsigned res1:31;
 		unsigned en:1;
 	} fam17h_bits;
 	unsigned long long val;
-- 
cgit v1.2.3


From f69ffc5d3db8f1f03fd6d1df5930f9a1fbd787b6 Mon Sep 17 00:00:00 2001
From: Prarit Bhargava <prarit@redhat.com>
Date: Mon, 8 Oct 2018 11:06:19 -0400
Subject: cpupower: Fix coredump on VMWare

cpupower crashes on VMWare guests.  The guests have the AMD PStateDef MSR
(0xC0010064 + state number) set to zero.  As a result fid and did are zero
and the crash occurs because of a divide by zero (cof = fid/did).  This
can be prevented by checking the enable bit in the PStateDef MSR before
calculating cof.  By doing this the value of pstate[i] remains zero and
the value can be tested before displaying the active Pstates.

Check the enable bit in the PstateDef register for all supported families
and only print out enabled Pstates.

Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Stafford Horne <shorne@gmail.com>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/power/cpupower/utils/cpufreq-info.c | 2 ++
 tools/power/cpupower/utils/helpers/amd.c  | 5 +++++
 2 files changed, 7 insertions(+)

(limited to 'tools')

diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c
index df43cd45d810..ccd08dd00996 100644
--- a/tools/power/cpupower/utils/cpufreq-info.c
+++ b/tools/power/cpupower/utils/cpufreq-info.c
@@ -200,6 +200,8 @@ static int get_boost_mode(unsigned int cpu)
 		printf(_("    Boost States: %d\n"), b_states);
 		printf(_("    Total States: %d\n"), pstate_no);
 		for (i = 0; i < pstate_no; i++) {
+			if (!pstates[i])
+				continue;
 			if (i < b_states)
 				printf(_("    Pstate-Pb%d: %luMHz (boost state)"
 					 "\n"), i, pstates[i]);
diff --git a/tools/power/cpupower/utils/helpers/amd.c b/tools/power/cpupower/utils/helpers/amd.c
index eed31b27909b..9607ada5b29a 100644
--- a/tools/power/cpupower/utils/helpers/amd.c
+++ b/tools/power/cpupower/utils/helpers/amd.c
@@ -119,6 +119,11 @@ int decode_pstates(unsigned int cpu, unsigned int cpu_family,
 		}
 		if (read_msr(cpu, MSR_AMD_PSTATE + i, &pstate.val))
 			return -1;
+		if ((cpu_family == 0x17) && (!pstate.fam17h_bits.en))
+			continue;
+		else if (!pstate.bits.en)
+			continue;
+
 		pstates[i] = get_cof(cpu_family, pstate);
 	}
 	*no = i;
-- 
cgit v1.2.3


From ba4aa02b417f08a0bee5e7b8ed70cac788a7c854 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 25 Sep 2018 10:55:59 -0300
Subject: tools include: Adopt linux/bits.h

So that we reduce the difference of tools/include/linux/bitops.h to the
original kernel file, include/linux/bitops.h, trying to remove the need
to define BITS_PER_LONG, to avoid clashes with asm/bitsperlong.h.

And the things removed from tools/include/linux/bitops.h are really in
linux/bits.h, so that we can have a copy and then
tools/perf/check_headers.sh will tell us when new stuff gets added to
linux/bits.h so that we can check if it is useful and if any adjustment
needs to be done to the tools/{include,arch}/ copies.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-y1sqyydvfzo0bjjoj4zsl562@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/bitops.h |  7 ++-----
 tools/include/linux/bits.h   | 26 ++++++++++++++++++++++++++
 tools/perf/check-headers.sh  |  1 +
 3 files changed, 29 insertions(+), 5 deletions(-)
 create mode 100644 tools/include/linux/bits.h

(limited to 'tools')

diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h
index acc704bd3998..0b0ef3abc966 100644
--- a/tools/include/linux/bitops.h
+++ b/tools/include/linux/bitops.h
@@ -3,8 +3,6 @@
 #define _TOOLS_LINUX_BITOPS_H_
 
 #include <asm/types.h>
-#include <linux/compiler.h>
-
 #ifndef __WORDSIZE
 #define __WORDSIZE (__SIZEOF_LONG__ * 8)
 #endif
@@ -12,10 +10,9 @@
 #ifndef BITS_PER_LONG
 # define BITS_PER_LONG __WORDSIZE
 #endif
+#include <linux/bits.h>
+#include <linux/compiler.h>
 
-#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
-#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
-#define BITS_PER_BYTE		8
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
 #define BITS_TO_U64(nr)		DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
 #define BITS_TO_U32(nr)		DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
new file mode 100644
index 000000000000..2b7b532c1d51
--- /dev/null
+++ b/tools/include/linux/bits.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_BITS_H
+#define __LINUX_BITS_H
+#include <asm/bitsperlong.h>
+
+#define BIT(nr)			(1UL << (nr))
+#define BIT_ULL(nr)		(1ULL << (nr))
+#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
+#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
+#define BIT_ULL_MASK(nr)	(1ULL << ((nr) % BITS_PER_LONG_LONG))
+#define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
+#define BITS_PER_BYTE		8
+
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
+ */
+#define GENMASK(h, l) \
+	(((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
+
+#define GENMASK_ULL(h, l) \
+	(((~0ULL) - (1ULL << (l)) + 1) & \
+	 (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
+
+#endif	/* __LINUX_BITS_H */
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 466540ee8ea7..c72cc73a6b09 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -14,6 +14,7 @@ include/uapi/linux/sched.h
 include/uapi/linux/stat.h
 include/uapi/linux/vhost.h
 include/uapi/sound/asound.h
+include/linux/bits.h
 include/linux/hash.h
 include/uapi/linux/hw_breakpoint.h
 arch/x86/include/asm/disabled-features.h
-- 
cgit v1.2.3


From 291ed51deee49ff35d0824fb7050538b449964d6 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 25 Sep 2018 11:52:10 -0300
Subject: perf auxtrace: Include missing asm/bitsperlong.h to get BITS_PER_LONG

The auxtrace.h header references BITS_PER_LONG without including the
header where it is defined, getting it by luck from some other header,
fix it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-v04ydmbh7tvpcctf3zld9j9s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/auxtrace.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 0a6ce9c4fc11..d88f6e9eb461 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -23,6 +23,7 @@
 #include <linux/list.h>
 #include <linux/perf_event.h>
 #include <linux/types.h>
+#include <asm/bitsperlong.h>
 
 #include "../perf.h"
 #include "event.h"
-- 
cgit v1.2.3


From 0e24147d69c9357b1ccb54a9bc028eb9a9f9ed1a Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Fri, 28 Sep 2018 12:53:35 +0200
Subject: perf test: S390 does not support watchpoints in test 22

S390 does not support the perf_event_open system call for
attribute type PERF_TYPE_BREAKPOINT. This results in test
failure for test 22:

  [root@s8360046 perf]# ./perf test 22
  22: Watchpoint                                :
  22.1: Read Only Watchpoint                    : FAILED!
  22.2: Write Only Watchpoint                   : FAILED!
  22.3: Read / Write Watchpoint                 : FAILED!
  22.4: Modify Watchpoint                       : FAILED!
  [root@s8360046 perf]#

Add s390 support to avoid these tests being executed on
s390 platform:

  [root@s8360046 perf]# ./perf test 22
  [root@s8360046 perf]# ./perf test -v 22
  22: Watchpoint                                : Disabled
  [root@s8360046 perf]#

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Link: http://lkml.kernel.org/r/20180928105335.67179-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/builtin-test.c |  1 +
 tools/perf/tests/tests.h        |  1 +
 tools/perf/tests/wp.c           | 12 ++++++++++++
 3 files changed, 14 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 54ca7d87236f..12c09e0ece71 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -123,6 +123,7 @@ static struct test generic_tests[] = {
 	{
 		.desc = "Watchpoint",
 		.func = test__wp,
+		.is_supported = test__wp_is_supported,
 		.subtest = {
 			.skip_if_fail	= false,
 			.get_nr		= test__wp_subtest_get_nr,
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 8e26a4148f30..b82f55fcc294 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -109,6 +109,7 @@ int test__unit_number__scnprint(struct test *test, int subtest);
 int test__mem2node(struct test *t, int subtest);
 
 bool test__bp_signal_is_supported(void);
+bool test__wp_is_supported(void);
 
 #if defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c
index 017a99317f94..f89e6806557b 100644
--- a/tools/perf/tests/wp.c
+++ b/tools/perf/tests/wp.c
@@ -227,3 +227,15 @@ int test__wp(struct test *test __maybe_unused, int i)
 
 	return !wp_testcase_table[i].target_func() ? TEST_OK : TEST_FAIL;
 }
+
+/* The s390 so far does not have support for
+ * instruction breakpoint using the perf_event_open() system call.
+ */
+bool test__wp_is_supported(void)
+{
+#if defined(__s390x__)
+	return false;
+#else
+	return true;
+#endif
+}
-- 
cgit v1.2.3


From ce49d8436cffa9b7a6a5f110879d53e89dbc6746 Mon Sep 17 00:00:00 2001
From: Sanskriti Sharma <sansharm@redhat.com>
Date: Tue, 2 Oct 2018 10:29:10 -0400
Subject: perf strbuf: Match va_{add,copy} with va_end

Ensure that all code paths in strbuf_addv() call va_end() on the
ap_saved copy that was made.

Fixes the following coverity complaint:

  Error: VARARGS (CWE-237): [#def683]
  tools/perf/util/strbuf.c:106: missing_va_end: va_end was not called
  for "ap_saved".

Signed-off-by: Sanskriti Sharma <sansharm@redhat.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Joe Lawrence <joe.lawrence@redhat.com>
Link: http://lkml.kernel.org/r/1538490554-8161-2-git-send-email-sansharm@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/strbuf.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 3d1cf5bf7f18..9005fbe0780e 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -98,19 +98,25 @@ static int strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap)
 
 	va_copy(ap_saved, ap);
 	len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
-	if (len < 0)
+	if (len < 0) {
+		va_end(ap_saved);
 		return len;
+	}
 	if (len > strbuf_avail(sb)) {
 		ret = strbuf_grow(sb, len);
-		if (ret)
+		if (ret) {
+			va_end(ap_saved);
 			return ret;
+		}
 		len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap_saved);
 		va_end(ap_saved);
 		if (len > strbuf_avail(sb)) {
 			pr_debug("this should not happen, your vsnprintf is broken");
+			va_end(ap_saved);
 			return -EINVAL;
 		}
 	}
+	va_end(ap_saved);
 	return strbuf_setlen(sb, sb->len + len);
 }
 
-- 
cgit v1.2.3


From faedbf3fd19f2511a39397f76359e4cc6ee93072 Mon Sep 17 00:00:00 2001
From: Sanskriti Sharma <sansharm@redhat.com>
Date: Tue, 2 Oct 2018 10:29:11 -0400
Subject: perf tools: Cleanup trace-event-info 'tdata' leak

Free tracing_data structure in tracing_data_get() error paths.

Fixes the following coverity complaint:

  Error: RESOURCE_LEAK (CWE-772):
  leaked_storage: Variable "tdata" going out of scope leaks the storage

Signed-off-by: Sanskriti Sharma <sansharm@redhat.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Joe Lawrence <joe.lawrence@redhat.com>
Link: http://lkml.kernel.org/r/1538490554-8161-3-git-send-email-sansharm@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/trace-event-info.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 7b0ca7cbb7de..8ad8e755127b 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -531,12 +531,14 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs,
 			 "/tmp/perf-XXXXXX");
 		if (!mkstemp(tdata->temp_file)) {
 			pr_debug("Can't make temp file");
+			free(tdata);
 			return NULL;
 		}
 
 		temp_fd = open(tdata->temp_file, O_RDWR);
 		if (temp_fd < 0) {
 			pr_debug("Can't read '%s'", tdata->temp_file);
+			free(tdata);
 			return NULL;
 		}
 
-- 
cgit v1.2.3


From 9c8a182e5a73e01afd11742a2ab887bf338fdafd Mon Sep 17 00:00:00 2001
From: Sanskriti Sharma <sansharm@redhat.com>
Date: Tue, 2 Oct 2018 10:29:12 -0400
Subject: perf tools: Free 'printk' string in parse_ftrace_printk()

parse_ftrace_printk() tokenizes and parses a line, calling strdup() each
iteration.  Add code to free this temporary format string duplicate.

Fixes the following coverity complaints:

  Error: RESOURCE_LEAK (CWE-772):
  tools/perf/util/trace-event-parse.c:158: overwrite_var: Overwriting
  "printk" in "printk = strdup(fmt + 1)" leaks the storage that "printk"
  points to.

  tools/perf/util/trace-event-parse.c:162: leaked_storage: Variable
  "printk" going out of scope leaks the storage it points to.

Signed-off-by: Sanskriti Sharma <sansharm@redhat.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Joe Lawrence <joe.lawrence@redhat.com>
Link: http://lkml.kernel.org/r/1538490554-8161-4-git-send-email-sansharm@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/trace-event-parse.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index a4d7de1c96d1..02f97f5dd588 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -158,6 +158,7 @@ void parse_ftrace_printk(struct tep_handle *pevent,
 		printk = strdup(fmt+1);
 		line = strtok_r(NULL, "\n", &next);
 		tep_register_print_string(pevent, printk, addr);
+		free(printk);
 	}
 }
 
-- 
cgit v1.2.3


From 470c8f7c88de013d266e1b61044efe8937728b7f Mon Sep 17 00:00:00 2001
From: Sanskriti Sharma <sansharm@redhat.com>
Date: Tue, 2 Oct 2018 10:29:13 -0400
Subject: perf tools: Avoid double free in read_event_file()

The temporary 'buf' buffer allocated in read_event_file() may be freed
twice.  Move the free() call to the common function exit point.

Fixes the following coverity complaints:

  Error: USE_AFTER_FREE (CWE-825):
  tools/perf/util/trace-event-read.c:309: double_free: Calling "free"
  frees pointer "buf" which has already been freed.

Signed-off-by: Sanskriti Sharma <sansharm@redhat.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Joe Lawrence <joe.lawrence@redhat.com>
Link: http://lkml.kernel.org/r/1538490554-8161-5-git-send-email-sansharm@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/trace-event-read.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index b98ee2a2eb44..a278e1eee5f5 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -297,10 +297,8 @@ static int read_event_file(struct tep_handle *pevent, char *sys,
 	}
 
 	ret = do_read(buf, size);
-	if (ret < 0) {
-		free(buf);
+	if (ret < 0)
 		goto out;
-	}
 
 	ret = parse_event_file(pevent, buf, size, sys);
 	if (ret < 0)
-- 
cgit v1.2.3


From 1e44224fb0528b4c0cc176bde2bb31e9127eb14b Mon Sep 17 00:00:00 2001
From: Sanskriti Sharma <sansharm@redhat.com>
Date: Tue, 2 Oct 2018 10:29:14 -0400
Subject: perf tools: Free temporary 'sys' string in read_event_files()

For each system in a given pevent, read_event_files() reads in a
temporary 'sys' string.  Be sure to free this string before moving onto
to the next system and/or leaving read_event_files().

Fixes the following coverity complaints:

  Error: RESOURCE_LEAK (CWE-772):

  tools/perf/util/trace-event-read.c:343: overwrite_var: Overwriting
  "sys" in "sys = read_string()" leaks the storage that "sys" points to.

  tools/perf/util/trace-event-read.c:353: leaked_storage: Variable "sys"
  going out of scope leaks the storage it points to.

Signed-off-by: Sanskriti Sharma <sansharm@redhat.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Joe Lawrence <joe.lawrence@redhat.com>
Link: http://lkml.kernel.org/r/1538490554-8161-6-git-send-email-sansharm@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/trace-event-read.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index a278e1eee5f5..add8441de579 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -347,9 +347,12 @@ static int read_event_files(struct tep_handle *pevent)
 		for (x=0; x < count; x++) {
 			size = read8(pevent);
 			ret = read_event_file(pevent, sys, size);
-			if (ret)
+			if (ret) {
+				free(sys);
 				return ret;
+			}
 		}
+		free(sys);
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From e13a5d69c31d35538e80176d54d95b6addf4dcbf Mon Sep 17 00:00:00 2001
From: Eduardo Habkost <ehabkost@redhat.com>
Date: Fri, 5 Oct 2018 17:40:57 -0300
Subject: perf python: Make clang_has_option() work on Python 3

Use a bytes literal so it works with Python 3's version of Popen().
Note that the b"..." syntax requires Python 2.6+.

Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20181005204058.7966-2-ehabkost@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/setup.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 1942f6dd24f6..261a55e7e1b2 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -5,7 +5,7 @@ from subprocess import Popen, PIPE
 from re import sub
 
 def clang_has_option(option):
-    return [o for o in Popen(['clang', option], stderr=PIPE).stderr.readlines() if "unknown argument" in o] == [ ]
+    return [o for o in Popen(['clang', option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ]
 
 cc = getenv("CC")
 if cc == "clang":
-- 
cgit v1.2.3


From 8b2f245faa6238e28a1d801e8633515251d1acfc Mon Sep 17 00:00:00 2001
From: Eduardo Habkost <ehabkost@redhat.com>
Date: Fri, 5 Oct 2018 17:40:58 -0300
Subject: perf python: More portable way to make CFLAGS work with clang

The existing code that tries to make CFLAGS compatible with clang
doesn't work with Python 3.

Instead of trying to touch _sysconfigdata.build_time_vars directly,
change the dictionary returned by disutils.sysconfig.get_config_vars().
This works on both Python 2 and Python 3.

Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20181005204058.7966-3-ehabkost@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/setup.py | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 261a55e7e1b2..63f758c655d5 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -9,12 +9,14 @@ def clang_has_option(option):
 
 cc = getenv("CC")
 if cc == "clang":
-    from _sysconfigdata import build_time_vars
-    build_time_vars["CFLAGS"] = sub("-specs=[^ ]+", "", build_time_vars["CFLAGS"])
-    if not clang_has_option("-mcet"):
-        build_time_vars["CFLAGS"] = sub("-mcet", "", build_time_vars["CFLAGS"])
-    if not clang_has_option("-fcf-protection"):
-        build_time_vars["CFLAGS"] = sub("-fcf-protection", "", build_time_vars["CFLAGS"])
+    from distutils.sysconfig import get_config_vars
+    vars = get_config_vars()
+    for var in ('CFLAGS', 'OPT'):
+        vars[var] = sub("-specs=[^ ]+", "", vars[var])
+        if not clang_has_option("-mcet"):
+            vars[var] = sub("-mcet", "", vars[var])
+        if not clang_has_option("-fcf-protection"):
+            vars[var] = sub("-fcf-protection", "", vars[var])
 
 from distutils.core import setup, Extension
 
-- 
cgit v1.2.3


From bbbab191c2c474d183e93799d008b412e97f5936 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Fri, 5 Oct 2018 12:18:16 -0400
Subject: tools lib traceevent: Separate out tep_strerror() for strerror_r()
 issues

While working on having PowerTop use libtracevent as a shared object
library, Tzvetomir hit "str_error_r not defined". This was added by commit
c3cec9e68f12d ("tools lib traceevent: Use str_error_r()") because
strerror_r() has two definitions, where one is GNU specific, and the other
is XSI complient. The strerror_r() is in a wrapper str_error_r() to keep the
code from having to worry about which compiler is being used.

The problem is that str_error_r() is external to libtraceevent, and not part
of the library. If it is used as a shared object then the tools using it
will need to define that function. I do not want that function defined in
libtraceevent itself, as it is out of scope for that library.

As there's only a single instance of this call, and its in the traceevent
library's own tep_strerror() function, we can copy what was done in perf,
and create yet another external file that undefs _GNU_SOURCE to use the more
portable version of the function. We don't need to worry about the errors
that strerror_r() returns. If the buffer isn't big enough, we simply
truncate it.

Reported-by: Tzvetomir Stoyanov <tstoyanov@vmware.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: linux trace devel <linux-trace-devel@vger.kernel.org>
Link: http://lkml.kernel.org/r/20181005121816.484e654f@gandalf.local.home
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/Build          |  1 +
 tools/lib/traceevent/event-parse.c  | 30 ---------------------
 tools/lib/traceevent/tep_strerror.c | 53 +++++++++++++++++++++++++++++++++++++
 3 files changed, 54 insertions(+), 30 deletions(-)
 create mode 100644 tools/lib/traceevent/tep_strerror.c

(limited to 'tools')

diff --git a/tools/lib/traceevent/Build b/tools/lib/traceevent/Build
index c681d0575d16..0050c145d806 100644
--- a/tools/lib/traceevent/Build
+++ b/tools/lib/traceevent/Build
@@ -4,6 +4,7 @@ libtraceevent-y += trace-seq.o
 libtraceevent-y += parse-filter.o
 libtraceevent-y += parse-utils.o
 libtraceevent-y += kbuffer-parse.o
+libtraceevent-y += tep_strerror.o
 
 plugin_jbd2-y         += plugin_jbd2.o
 plugin_hrtimer-y      += plugin_hrtimer.o
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 7980fc6c3bac..233179a712d6 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -18,7 +18,6 @@
 #include <errno.h>
 #include <stdint.h>
 #include <limits.h>
-#include <linux/string.h>
 #include <linux/time64.h>
 
 #include <netinet/in.h>
@@ -6201,35 +6200,6 @@ enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf,
 	return __parse_event(pevent, &event, buf, size, sys);
 }
 
-#undef _PE
-#define _PE(code, str) str
-static const char * const tep_error_str[] = {
-	TEP_ERRORS
-};
-#undef _PE
-
-int tep_strerror(struct tep_handle *pevent __maybe_unused,
-		 enum tep_errno errnum, char *buf, size_t buflen)
-{
-	int idx;
-	const char *msg;
-
-	if (errnum >= 0) {
-		str_error_r(errnum, buf, buflen);
-		return 0;
-	}
-
-	if (errnum <= __TEP_ERRNO__START ||
-	    errnum >= __TEP_ERRNO__END)
-		return -1;
-
-	idx = errnum - __TEP_ERRNO__START - 1;
-	msg = tep_error_str[idx];
-	snprintf(buf, buflen, "%s", msg);
-
-	return 0;
-}
-
 int get_field_val(struct trace_seq *s, struct tep_format_field *field,
 		  const char *name, struct tep_record *record,
 		  unsigned long long *val, int err)
diff --git a/tools/lib/traceevent/tep_strerror.c b/tools/lib/traceevent/tep_strerror.c
new file mode 100644
index 000000000000..4ac26445b2f6
--- /dev/null
+++ b/tools/lib/traceevent/tep_strerror.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: LGPL-2.1
+#undef _GNU_SOURCE
+#include <string.h>
+#include <stdio.h>
+
+#include "event-parse.h"
+
+#undef _PE
+#define _PE(code, str) str
+static const char * const tep_error_str[] = {
+	TEP_ERRORS
+};
+#undef _PE
+
+/*
+ * The tools so far have been using the strerror_r() GNU variant, that returns
+ * a string, be it the buffer passed or something else.
+ *
+ * But that, besides being tricky in cases where we expect that the function
+ * using strerror_r() returns the error formatted in a provided buffer (we have
+ * to check if it returned something else and copy that instead), breaks the
+ * build on systems not using glibc, like Alpine Linux, where musl libc is
+ * used.
+ *
+ * So, introduce yet another wrapper, str_error_r(), that has the GNU
+ * interface, but uses the portable XSI variant of strerror_r(), so that users
+ * rest asured that the provided buffer is used and it is what is returned.
+ */
+int tep_strerror(struct tep_handle *tep __maybe_unused,
+		 enum tep_errno errnum, char *buf, size_t buflen)
+{
+	const char *msg;
+	int idx;
+
+	if (!buflen)
+		return 0;
+
+	if (errnum >= 0) {
+		int err = strerror_r(errnum, buf, buflen);
+		buf[buflen - 1] = 0;
+		return err;
+	}
+
+	if (errnum <= __TEP_ERRNO__START ||
+	    errnum >= __TEP_ERRNO__END)
+		return -1;
+
+	idx = errnum - __TEP_ERRNO__START - 1;
+	msg = tep_error_str[idx];
+	snprintf(buf, buflen, "%s", msg);
+
+	return 0;
+}
-- 
cgit v1.2.3


From 1e0a720779531cd2860777534e3674b518ac0a69 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Mon, 8 Oct 2018 14:37:03 +0200
Subject: selftests: pmtu: Introduce check_pmtu_value()

Introduce and use a function that checks PMTU values against
expected values and logs error messages, to remove some clutter.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 49 +++++++++++++++++--------------------
 1 file changed, 22 insertions(+), 27 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 0ab9423d009f..6c38a7637744 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -229,6 +229,19 @@ route_get_dst_pmtu_from_exception() {
 	mtu_parse "$(route_get_dst_exception "${ns_cmd}" ${dst})"
 }
 
+check_pmtu_value() {
+	expected="${1}"
+	value="${2}"
+	event="${3}"
+
+	[ "${expected}" = "any" ] && [ -n "${value}" ] && return 0
+	[ "${value}" = "${expected}" ] && return 0
+	[ -z "${value}" ] &&    err "  PMTU exception wasn't created after ${event}" && return 1
+	[ -z "${expected}" ] && err "  PMTU exception shouldn't exist after ${event}" && return 1
+	err "  found PMTU exception with incorrect MTU ${value}, expected ${expected}, after ${event}"
+	return 1
+}
+
 test_pmtu_vti4_exception() {
 	setup namespaces veth vti4 xfrm4 || return 2
 
@@ -248,24 +261,13 @@ test_pmtu_vti4_exception() {
 	# exception is created
 	${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${vti4_b_addr} > /dev/null
 	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})"
-	if [ "${pmtu}" != "" ]; then
-		err "  unexpected exception created with PMTU ${pmtu} for IP payload length ${esp_payload_rfc4106}"
-		return 1
-	fi
+	check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
 
 	# Now exceed link layer MTU by one byte, check that exception is created
+	# with the right PMTU value
 	${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${vti4_b_addr} > /dev/null
 	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})"
-	if [ "${pmtu}" = "" ]; then
-		err "  exception not created for IP payload length $((esp_payload_rfc4106 + 1))"
-		return 1
-	fi
-
-	# ...with the right PMTU value
-	if [ ${pmtu} -ne ${esp_payload_rfc4106} ]; then
-		err "  wrong PMTU ${pmtu} in exception, expected: ${esp_payload_rfc4106}"
-		return 1
-	fi
+	check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
 }
 
 test_pmtu_vti6_exception() {
@@ -280,25 +282,18 @@ test_pmtu_vti6_exception() {
 	${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null
 
 	# Check that exception was created
-	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" = "" ]; then
-		err "  tunnel exceeding link layer MTU didn't create route exception"
-		return 1
-	fi
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1
 
 	# Decrease tunnel MTU, check for PMTU decrease in route exception
 	mtu "${ns_a}" vti6_a 3000
-
-	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 3000 ]; then
-		err "  decreasing tunnel MTU didn't decrease route exception PMTU"
-		fail=1
-	fi
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1
 
 	# Increase tunnel MTU, check for PMTU increase in route exception
 	mtu "${ns_a}" vti6_a 9000
-	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 9000 ]; then
-		err "  increasing tunnel MTU didn't increase route exception PMTU"
-		fail=1
-	fi
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1
 
 	return ${fail}
 }
-- 
cgit v1.2.3


From 72ebddd7fff81e03a0617754d3f5c45ae49cea43 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 8 Oct 2018 14:37:04 +0200
Subject: selftests: pmtu: extend MTU parsing helper to locked MTU

The mtu_parse helper introduced in commit f2c929feeccd ("selftests:
pmtu: Factor out MTU parsing helper") can only handle "mtu 1234", but
not "mtu lock 1234". Extend it, so that we can do IPv4 tests with PMTU
smaller than net.ipv4.route.min_pmtu

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 6c38a7637744..03e56a27f69c 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -196,7 +196,9 @@ mtu_parse() {
 
 	next=0
 	for i in ${input}; do
+		[ ${next} -eq 1 -a "${i}" = "lock" ] && next=2 && continue
 		[ ${next} -eq 1 ] && echo "${i}" && return
+		[ ${next} -eq 2 ] && echo "lock ${i}" && return
 		[ "${i}" = "mtu" ] && next=1
 	done
 }
-- 
cgit v1.2.3


From e44e428f59e4299bd060ac5c1618c4ac8e77c75a Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 8 Oct 2018 14:37:05 +0200
Subject: selftests: pmtu: add basic IPv4 and IPv6 PMTU tests

Commit d1f1b9cbf34c ("selftests: net: Introduce first PMTU test") and
follow-ups introduced some PMTU tests, but they all rely on tunneling,
and, particularly, on VTI.

These new tests use simple routing to exercise the generation and
update of PMTU exceptions in IPv4 and IPv6.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 207 +++++++++++++++++++++++++++++++++++-
 1 file changed, 203 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 03e56a27f69c..b9cdb68df4c5 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -6,6 +6,26 @@
 #
 # Tests currently implemented:
 #
+# - pmtu_ipv4
+#	Set up two namespaces, A and B, with two paths between them over routers
+#	R1 and R2 (also implemented with namespaces), with different MTUs:
+#
+#	  segment a_r1    segment b_r1		a_r1: 2000
+#	.--------------R1--------------.	a_r2: 1500
+#	A                               B	a_r3: 2000
+#	'--------------R2--------------'	a_r4: 1400
+#	  segment a_r2    segment b_r2
+#
+#	Check that PMTU exceptions with the correct PMTU are created. Then
+#	decrease and increase the MTU of the local link for one of the paths,
+#	A to R1, checking that route exception PMTU changes accordingly over
+#	this path. Also check that locked exceptions are created when an ICMP
+#	message advertising a PMTU smaller than net.ipv4.route.min_pmtu is
+#	received
+#
+# - pmtu_ipv6
+#	Same as pmtu_ipv4, except for locked PMTU tests, using IPv6
+#
 # - pmtu_vti4_exception
 #	Set up vti tunnel on top of veth, with xfrm states and policies, in two
 #	namespaces with matching endpoints. Check that route exception is not
@@ -50,6 +70,8 @@ ksft_skip=4
 which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
 
 tests="
+	pmtu_ipv4_exception		ipv4: PMTU exceptions
+	pmtu_ipv6_exception		ipv6: PMTU exceptions
 	pmtu_vti6_exception		vti6: PMTU exceptions
 	pmtu_vti4_exception		vti4: PMTU exceptions
 	pmtu_vti4_default_mtu		vti4: default MTU assignment
@@ -60,8 +82,45 @@ tests="
 
 NS_A="ns-$(mktemp -u XXXXXX)"
 NS_B="ns-$(mktemp -u XXXXXX)"
+NS_R1="ns-$(mktemp -u XXXXXX)"
+NS_R2="ns-$(mktemp -u XXXXXX)"
 ns_a="ip netns exec ${NS_A}"
 ns_b="ip netns exec ${NS_B}"
+ns_r1="ip netns exec ${NS_R1}"
+ns_r2="ip netns exec ${NS_R2}"
+
+# Addressing and routing for tests with routers: four network segments, with
+# index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an
+# identifier ID, which is 1 for hosts (A and B), 2 for routers (R1 and R2).
+# Addresses are:
+# - IPv4: PREFIX4.SEGMENT.ID (/24)
+# - IPv6: PREFIX6:SEGMENT::ID (/64)
+prefix4="192.168"
+prefix6="fd00"
+a_r1=1
+a_r2=2
+b_r1=3
+b_r2=4
+#	ns	peer	segment
+routing_addrs="
+	A	R1	${a_r1}
+	A	R2	${a_r2}
+	B	R1	${b_r1}
+	B	R2	${b_r2}
+"
+# Traffic from A to B goes through R1 by default, and through R2, if destined to
+# B's address on the b_r2 segment.
+# Traffic from B to A goes through R1.
+#	ns	destination		gateway
+routes="
+	A	default			${prefix4}.${a_r1}.2
+	A	${prefix4}.${b_r2}.1	${prefix4}.${a_r2}.2
+	B	default			${prefix4}.${b_r1}.2
+
+	A	default			${prefix6}:${a_r1}::2
+	A	${prefix6}:${b_r2}::1	${prefix6}:${a_r2}::2
+	B	default			${prefix6}:${b_r1}::2
+"
 
 veth4_a_addr="192.168.1.1"
 veth4_b_addr="192.168.1.2"
@@ -94,9 +153,15 @@ err_flush() {
 	err_buf=
 }
 
+# Find the auto-generated name for this namespace
+nsname() {
+	eval echo \$NS_$1
+}
+
 setup_namespaces() {
-	ip netns add ${NS_A} || return 1
-	ip netns add ${NS_B}
+	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
+		ip netns add ${n} || return 1
+	done
 }
 
 setup_veth() {
@@ -167,6 +232,49 @@ setup_xfrm6() {
 	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr}
 }
 
+setup_routing() {
+	for i in ${NS_R1} ${NS_R2}; do
+		ip netns exec ${i} sysctl -q net/ipv4/ip_forward=1
+		ip netns exec ${i} sysctl -q net/ipv6/conf/all/forwarding=1
+	done
+
+	for i in ${routing_addrs}; do
+		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
+		[ "${peer}" = "" ]	&& peer="${i}"		&& continue
+		[ "${segment}" = "" ]	&& segment="${i}"
+
+		ns_name="$(nsname ${ns})"
+		peer_name="$(nsname ${peer})"
+		if="veth_${ns}-${peer}"
+		ifpeer="veth_${peer}-${ns}"
+
+		# Create veth links
+		ip link add ${if} up netns ${ns_name} type veth peer name ${ifpeer} netns ${peer_name} || return 1
+		ip -n ${peer_name} link set dev ${ifpeer} up
+
+		# Add addresses
+		ip -n ${ns_name}   addr add ${prefix4}.${segment}.1/24  dev ${if}
+		ip -n ${ns_name}   addr add ${prefix6}:${segment}::1/64 dev ${if}
+
+		ip -n ${peer_name} addr add ${prefix4}.${segment}.2/24  dev ${ifpeer}
+		ip -n ${peer_name} addr add ${prefix6}:${segment}::2/64 dev ${ifpeer}
+
+		ns=""; peer=""; segment=""
+	done
+
+	for i in ${routes}; do
+		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
+		[ "${addr}" = "" ]	&& addr="${i}"		&& continue
+		[ "${gw}" = "" ]	&& gw="${i}"
+
+		ns_name="$(nsname ${ns})"
+
+		ip -n ${ns_name} route add ${addr} via ${gw}
+
+		ns=""; addr=""; gw=""
+	done
+}
+
 setup() {
 	[ "$(id -u)" -ne 0 ] && echo "  need to run as root" && return $ksft_skip
 
@@ -178,8 +286,9 @@ setup() {
 
 cleanup() {
 	[ ${cleanup_done} -eq 1 ] && return
-	ip netns del ${NS_A} 2> /dev/null
-	ip netns del ${NS_B} 2> /dev/null
+	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
+		ip netns del ${n} 2> /dev/null
+	done
 	cleanup_done=1
 }
 
@@ -244,6 +353,96 @@ check_pmtu_value() {
 	return 1
 }
 
+test_pmtu_ipvX() {
+	family=${1}
+
+	setup namespaces routing || return 2
+
+	if [ ${family} -eq 4 ]; then
+		ping=ping
+		dst1="${prefix4}.${b_r1}.1"
+		dst2="${prefix4}.${b_r2}.1"
+	else
+		ping=${ping6}
+		dst1="${prefix6}:${b_r1}::1"
+		dst2="${prefix6}:${b_r2}::1"
+	fi
+
+	# Set up initial MTU values
+	mtu "${ns_a}"  veth_A-R1 2000
+	mtu "${ns_r1}" veth_R1-A 2000
+	mtu "${ns_r1}" veth_R1-B 1400
+	mtu "${ns_b}"  veth_B-R1 1400
+
+	mtu "${ns_a}"  veth_A-R2 2000
+	mtu "${ns_r2}" veth_R2-A 2000
+	mtu "${ns_r2}" veth_R2-B 1500
+	mtu "${ns_b}"  veth_B-R2 1500
+
+	# Create route exceptions
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1800 ${dst1} > /dev/null
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1800 ${dst2} > /dev/null
+
+	# Check that exceptions have been created with the correct PMTU
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
+	check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1
+
+	# Decrease local MTU below PMTU, check for PMTU decrease in route exception
+	mtu "${ns_a}"  veth_A-R1 1300
+	mtu "${ns_r1}" veth_R1-A 1300
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
+	check_pmtu_value "1300" "${pmtu_1}" "decreasing local MTU" || return 1
+	# Second exception shouldn't be modified
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "changing local MTU on a link not on this path" || return 1
+
+	# Increase MTU, check for PMTU increase in route exception
+	mtu "${ns_a}"  veth_A-R1 1700
+	mtu "${ns_r1}" veth_R1-A 1700
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
+	check_pmtu_value "1700" "${pmtu_1}" "increasing local MTU" || return 1
+	# Second exception shouldn't be modified
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "changing local MTU on a link not on this path" || return 1
+
+	# Skip PMTU locking tests for IPv6
+	[ $family -eq 6 ] && return 0
+
+	# Decrease remote MTU on path via R2, get new exception
+	mtu "${ns_r2}" veth_R2-B 400
+	mtu "${ns_b}"  veth_B-R2 400
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1400 ${dst2} > /dev/null
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1
+
+	# Decrease local MTU below PMTU
+	mtu "${ns_a}"  veth_A-R2 500
+	mtu "${ns_r2}" veth_R2-A 500
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "500" "${pmtu_2}" "decreasing local MTU" || return 1
+
+	# Increase local MTU
+	mtu "${ns_a}"  veth_A-R2 1500
+	mtu "${ns_r2}" veth_R2-A 1500
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "increasing local MTU" || return 1
+
+	# Get new exception
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1400 ${dst2} > /dev/null
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1
+}
+
+test_pmtu_ipv4_exception() {
+	test_pmtu_ipvX 4
+}
+
+test_pmtu_ipv6_exception() {
+	test_pmtu_ipvX 6
+}
+
 test_pmtu_vti4_exception() {
 	setup namespaces veth vti4 xfrm4 || return 2
 
-- 
cgit v1.2.3


From bb3dd7e7c4d5e024d607c0ec06c2a2fb9408cc99 Mon Sep 17 00:00:00 2001
From: Tzvetomir Stoyanov <tstoyanov@vmware.com>
Date: Fri, 5 Oct 2018 12:22:25 -0400
Subject: tools lib traceevent, perf tools: Move struct tep_handler definition
 in a local header file

As traceevent is going to be transferred into a proper library,
its local data should be protected from the library users.
This patch encapsulates struct tep_handler into a local header,
not visible outside of the library. It implements also a bunch
of new APIs, which library users can use to access tep_handler members.

Signed-off-by: Tzvetomir Stoyanov <tstoyanov@vmware.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linux trace devel <linux-trace-devel@vger.kernel.org>
Cc: tzvetomir stoyanov <tstoyanov@vmware.com>
Link: http://lkml.kernel.org/r/20181005122225.522155df@gandalf.local.home
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/traceevent/Build               |   1 +
 tools/lib/traceevent/event-parse-api.c   | 275 +++++++++++++++++++++++++++++++
 tools/lib/traceevent/event-parse-local.h |  92 +++++++++++
 tools/lib/traceevent/event-parse.c       |   2 +
 tools/lib/traceevent/event-parse.h       | 228 ++++---------------------
 tools/lib/traceevent/event-plugin.c      |   1 +
 tools/lib/traceevent/parse-filter.c      |   1 +
 tools/perf/util/trace-event-parse.c      |  25 +--
 tools/perf/util/trace-event-read.c       |   2 +-
 9 files changed, 416 insertions(+), 211 deletions(-)
 create mode 100644 tools/lib/traceevent/event-parse-api.c
 create mode 100644 tools/lib/traceevent/event-parse-local.h

(limited to 'tools')

diff --git a/tools/lib/traceevent/Build b/tools/lib/traceevent/Build
index 0050c145d806..ba54bfce0b0b 100644
--- a/tools/lib/traceevent/Build
+++ b/tools/lib/traceevent/Build
@@ -5,6 +5,7 @@ libtraceevent-y += parse-filter.o
 libtraceevent-y += parse-utils.o
 libtraceevent-y += kbuffer-parse.o
 libtraceevent-y += tep_strerror.o
+libtraceevent-y += event-parse-api.o
 
 plugin_jbd2-y         += plugin_jbd2.o
 plugin_hrtimer-y      += plugin_hrtimer.o
diff --git a/tools/lib/traceevent/event-parse-api.c b/tools/lib/traceevent/event-parse-api.c
new file mode 100644
index 000000000000..61f7149085ee
--- /dev/null
+++ b/tools/lib/traceevent/event-parse-api.c
@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+
+#include "event-parse.h"
+#include "event-parse-local.h"
+#include "event-utils.h"
+
+/**
+ * tep_get_first_event - returns the first event in the events array
+ * @tep: a handle to the tep_handle
+ *
+ * This returns pointer to the first element of the events array
+ * If @tep is NULL, NULL is returned.
+ */
+struct tep_event_format *tep_get_first_event(struct tep_handle *tep)
+{
+	if (tep && tep->events)
+		return tep->events[0];
+
+	return NULL;
+}
+
+/**
+ * tep_get_events_count - get the number of defined events
+ * @tep: a handle to the tep_handle
+ *
+ * This returns number of elements in event array
+ * If @tep is NULL, 0 is returned.
+ */
+int tep_get_events_count(struct tep_handle *tep)
+{
+	if(tep)
+		return tep->nr_events;
+	return 0;
+}
+
+/**
+ * tep_set_flag - set event parser flag
+ * @tep: a handle to the tep_handle
+ * @flag: flag, or combination of flags to be set
+ * can be any combination from enum tep_flag
+ *
+ * This sets a flag or mbination of flags  from enum tep_flag
+  */
+void tep_set_flag(struct tep_handle *tep, int flag)
+{
+	if(tep)
+		tep->flags |= flag;
+}
+
+unsigned short __tep_data2host2(struct tep_handle *pevent, unsigned short data)
+{
+	unsigned short swap;
+
+	if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+		return data;
+
+	swap = ((data & 0xffULL) << 8) |
+		((data & (0xffULL << 8)) >> 8);
+
+	return swap;
+}
+
+unsigned int __tep_data2host4(struct tep_handle *pevent, unsigned int data)
+{
+	unsigned int swap;
+
+	if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+		return data;
+
+	swap = ((data & 0xffULL) << 24) |
+		((data & (0xffULL << 8)) << 8) |
+		((data & (0xffULL << 16)) >> 8) |
+		((data & (0xffULL << 24)) >> 24);
+
+	return swap;
+}
+
+unsigned long long
+__tep_data2host8(struct tep_handle *pevent, unsigned long long data)
+{
+	unsigned long long swap;
+
+	if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+		return data;
+
+	swap = ((data & 0xffULL) << 56) |
+		((data & (0xffULL << 8)) << 40) |
+		((data & (0xffULL << 16)) << 24) |
+		((data & (0xffULL << 24)) << 8) |
+		((data & (0xffULL << 32)) >> 8) |
+		((data & (0xffULL << 40)) >> 24) |
+		((data & (0xffULL << 48)) >> 40) |
+		((data & (0xffULL << 56)) >> 56);
+
+	return swap;
+}
+
+/**
+ * tep_get_header_page_size - get size of the header page
+ * @pevent: a handle to the tep_handle
+ *
+ * This returns size of the header page
+ * If @pevent is NULL, 0 is returned.
+ */
+int tep_get_header_page_size(struct tep_handle *pevent)
+{
+	if(pevent)
+		return pevent->header_page_size_size;
+	return 0;
+}
+
+/**
+ * tep_get_cpus - get the number of CPUs
+ * @pevent: a handle to the tep_handle
+ *
+ * This returns the number of CPUs
+ * If @pevent is NULL, 0 is returned.
+ */
+int tep_get_cpus(struct tep_handle *pevent)
+{
+	if(pevent)
+		return pevent->cpus;
+	return 0;
+}
+
+/**
+ * tep_set_cpus - set the number of CPUs
+ * @pevent: a handle to the tep_handle
+ *
+ * This sets the number of CPUs
+ */
+void tep_set_cpus(struct tep_handle *pevent, int cpus)
+{
+	if(pevent)
+		pevent->cpus = cpus;
+}
+
+/**
+ * tep_get_long_size - get the size of a long integer on the current machine
+ * @pevent: a handle to the tep_handle
+ *
+ * This returns the size of a long integer on the current machine
+ * If @pevent is NULL, 0 is returned.
+ */
+int tep_get_long_size(struct tep_handle *pevent)
+{
+	if(pevent)
+		return pevent->long_size;
+	return 0;
+}
+
+/**
+ * tep_set_long_size - set the size of a long integer on the current machine
+ * @pevent: a handle to the tep_handle
+ * @size: size, in bytes, of a long integer
+ *
+ * This sets the size of a long integer on the current machine
+ */
+void tep_set_long_size(struct tep_handle *pevent, int long_size)
+{
+	if(pevent)
+		pevent->long_size = long_size;
+}
+
+/**
+ * tep_get_page_size - get the size of a memory page on the current machine
+ * @pevent: a handle to the tep_handle
+ *
+ * This returns the size of a memory page on the current machine
+ * If @pevent is NULL, 0 is returned.
+ */
+int tep_get_page_size(struct tep_handle *pevent)
+{
+	if(pevent)
+		return pevent->page_size;
+	return 0;
+}
+
+/**
+ * tep_set_page_size - set the size of a memory page on the current machine
+ * @pevent: a handle to the tep_handle
+ * @_page_size: size of a memory page, in bytes
+ *
+ * This sets the size of a memory page on the current machine
+ */
+void tep_set_page_size(struct tep_handle *pevent, int _page_size)
+{
+	if(pevent)
+		pevent->page_size = _page_size;
+}
+
+/**
+ * tep_is_file_bigendian - get if the file is in big endian order
+ * @pevent: a handle to the tep_handle
+ *
+ * This returns if the file is in big endian order
+ * If @pevent is NULL, 0 is returned.
+ */
+int tep_is_file_bigendian(struct tep_handle *pevent)
+{
+	if(pevent)
+		return pevent->file_bigendian;
+	return 0;
+}
+
+/**
+ * tep_set_file_bigendian - set if the file is in big endian order
+ * @pevent: a handle to the tep_handle
+ * @endian: non zero, if the file is in big endian order
+ *
+ * This sets if the file is in big endian order
+ */
+void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian)
+{
+	if(pevent)
+		pevent->file_bigendian = endian;
+}
+
+/**
+ * tep_is_host_bigendian - get if the order of the current host is big endian
+ * @pevent: a handle to the tep_handle
+ *
+ * This gets if the order of the current host is big endian
+ * If @pevent is NULL, 0 is returned.
+ */
+int tep_is_host_bigendian(struct tep_handle *pevent)
+{
+	if(pevent)
+		return pevent->host_bigendian;
+	return 0;
+}
+
+/**
+ * tep_set_host_bigendian - set the order of the local host
+ * @pevent: a handle to the tep_handle
+ * @endian: non zero, if the local host has big endian order
+ *
+ * This sets the order of the local host
+ */
+void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian)
+{
+	if(pevent)
+		pevent->host_bigendian = endian;
+}
+
+/**
+ * tep_is_latency_format - get if the latency output format is configured
+ * @pevent: a handle to the tep_handle
+ *
+ * This gets if the latency output format is configured
+ * If @pevent is NULL, 0 is returned.
+ */
+int tep_is_latency_format(struct tep_handle *pevent)
+{
+	if(pevent)
+		return pevent->latency_format;
+	return 0;
+}
+
+/**
+ * tep_set_latency_format - set the latency output format
+ * @pevent: a handle to the tep_handle
+ * @lat: non zero for latency output format
+ *
+ * This sets the latency output format
+  */
+void tep_set_latency_format(struct tep_handle *pevent, int lat)
+{
+	if(pevent)
+		pevent->latency_format = lat;
+}
diff --git a/tools/lib/traceevent/event-parse-local.h b/tools/lib/traceevent/event-parse-local.h
new file mode 100644
index 000000000000..b9bddde577f8
--- /dev/null
+++ b/tools/lib/traceevent/event-parse-local.h
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+
+#ifndef _PARSE_EVENTS_INT_H
+#define _PARSE_EVENTS_INT_H
+
+struct cmdline;
+struct cmdline_list;
+struct func_map;
+struct func_list;
+struct event_handler;
+struct func_resolver;
+
+struct tep_handle {
+	int ref_count;
+
+	int header_page_ts_offset;
+	int header_page_ts_size;
+	int header_page_size_offset;
+	int header_page_size_size;
+	int header_page_data_offset;
+	int header_page_data_size;
+	int header_page_overwrite;
+
+	enum tep_endian file_bigendian;
+	enum tep_endian host_bigendian;
+
+	int latency_format;
+
+	int old_format;
+
+	int cpus;
+	int long_size;
+	int page_size;
+
+	struct cmdline *cmdlines;
+	struct cmdline_list *cmdlist;
+	int cmdline_count;
+
+	struct func_map *func_map;
+	struct func_resolver *func_resolver;
+	struct func_list *funclist;
+	unsigned int func_count;
+
+	struct printk_map *printk_map;
+	struct printk_list *printklist;
+	unsigned int printk_count;
+
+
+	struct tep_event_format **events;
+	int nr_events;
+	struct tep_event_format **sort_events;
+	enum tep_event_sort_type last_type;
+
+	int type_offset;
+	int type_size;
+
+	int pid_offset;
+	int pid_size;
+
+	int pc_offset;
+	int pc_size;
+
+	int flags_offset;
+	int flags_size;
+
+	int ld_offset;
+	int ld_size;
+
+	int print_raw;
+
+	int test_filters;
+
+	int flags;
+
+	struct tep_format_field *bprint_ip_field;
+	struct tep_format_field *bprint_fmt_field;
+	struct tep_format_field *bprint_buf_field;
+
+	struct event_handler *handlers;
+	struct tep_function_handler *func_handlers;
+
+	/* cache */
+	struct tep_event_format *last_event;
+
+	char *trace_clock;
+};
+
+#endif /* _PARSE_EVENTS_INT_H */
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 233179a712d6..3692f29fee46 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -22,6 +22,8 @@
 
 #include <netinet/in.h>
 #include "event-parse.h"
+
+#include "event-parse-local.h"
 #include "event-utils.h"
 #include "trace-seq.h"
 
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 9c29a5f7aa39..16bf4c890b6f 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -405,149 +405,18 @@ void tep_print_plugins(struct trace_seq *s,
 			const char *prefix, const char *suffix,
 			const struct tep_plugin_list *list);
 
-struct cmdline;
-struct cmdline_list;
-struct func_map;
-struct func_list;
-struct event_handler;
-struct func_resolver;
-
+/* tep_handle */
 typedef char *(tep_func_resolver_t)(void *priv,
 				    unsigned long long *addrp, char **modp);
+void tep_set_flag(struct tep_handle *tep, int flag);
+unsigned short __tep_data2host2(struct tep_handle *pevent, unsigned short data);
+unsigned int __tep_data2host4(struct tep_handle *pevent, unsigned int data);
+unsigned long long
+__tep_data2host8(struct tep_handle *pevent, unsigned long long data);
 
-struct tep_handle {
-	int ref_count;
-
-	int header_page_ts_offset;
-	int header_page_ts_size;
-	int header_page_size_offset;
-	int header_page_size_size;
-	int header_page_data_offset;
-	int header_page_data_size;
-	int header_page_overwrite;
-
-	int file_bigendian;
-	int host_bigendian;
-
-	int latency_format;
-
-	int old_format;
-
-	int cpus;
-	int long_size;
-	int page_size;
-
-	struct cmdline *cmdlines;
-	struct cmdline_list *cmdlist;
-	int cmdline_count;
-
-	struct func_map *func_map;
-	struct func_resolver *func_resolver;
-	struct func_list *funclist;
-	unsigned int func_count;
-
-	struct printk_map *printk_map;
-	struct printk_list *printklist;
-	unsigned int printk_count;
-
-
-	struct tep_event_format **events;
-	int nr_events;
-	struct tep_event_format **sort_events;
-	enum tep_event_sort_type last_type;
-
-	int type_offset;
-	int type_size;
-
-	int pid_offset;
-	int pid_size;
-
- 	int pc_offset;
-	int pc_size;
-
-	int flags_offset;
-	int flags_size;
-
-	int ld_offset;
-	int ld_size;
-
-	int print_raw;
-
-	int test_filters;
-
-	int flags;
-
-	struct tep_format_field *bprint_ip_field;
-	struct tep_format_field *bprint_fmt_field;
-	struct tep_format_field *bprint_buf_field;
-
-	struct event_handler *handlers;
-	struct tep_function_handler *func_handlers;
-
-	/* cache */
-	struct tep_event_format *last_event;
-
-	char *trace_clock;
-};
-
-static inline void tep_set_flag(struct tep_handle *pevent, int flag)
-{
-	pevent->flags |= flag;
-}
-
-static inline unsigned short
-__tep_data2host2(struct tep_handle *pevent, unsigned short data)
-{
-	unsigned short swap;
-
-	if (pevent->host_bigendian == pevent->file_bigendian)
-		return data;
-
-	swap = ((data & 0xffULL) << 8) |
-		((data & (0xffULL << 8)) >> 8);
-
-	return swap;
-}
-
-static inline unsigned int
-__tep_data2host4(struct tep_handle *pevent, unsigned int data)
-{
-	unsigned int swap;
-
-	if (pevent->host_bigendian == pevent->file_bigendian)
-		return data;
-
-	swap = ((data & 0xffULL) << 24) |
-		((data & (0xffULL << 8)) << 8) |
-		((data & (0xffULL << 16)) >> 8) |
-		((data & (0xffULL << 24)) >> 24);
-
-	return swap;
-}
-
-static inline unsigned long long
-__tep_data2host8(struct tep_handle *pevent, unsigned long long data)
-{
-	unsigned long long swap;
-
-	if (pevent->host_bigendian == pevent->file_bigendian)
-		return data;
-
-	swap = ((data & 0xffULL) << 56) |
-		((data & (0xffULL << 8)) << 40) |
-		((data & (0xffULL << 16)) << 24) |
-		((data & (0xffULL << 24)) << 8) |
-		((data & (0xffULL << 32)) >> 8) |
-		((data & (0xffULL << 40)) >> 24) |
-		((data & (0xffULL << 48)) >> 40) |
-		((data & (0xffULL << 56)) >> 56);
-
-	return swap;
-}
-
-#define tep_data2host2(pevent, ptr)		__tep_data2host2(pevent, *(unsigned short *)(ptr))
-#define tep_data2host4(pevent, ptr)		__tep_data2host4(pevent, *(unsigned int *)(ptr))
-#define tep_data2host8(pevent, ptr)					\
+#define tep_data2host2(pevent, ptr)	__tep_data2host2(pevent, *(unsigned short *)(ptr))
+#define tep_data2host4(pevent, ptr)	__tep_data2host4(pevent, *(unsigned int *)(ptr))
+#define tep_data2host8(pevent, ptr)	\
 ({								\
 	unsigned long long __val;				\
 								\
@@ -655,11 +524,12 @@ unsigned long long tep_read_number(struct tep_handle *pevent, const void *ptr, i
 int tep_read_number_field(struct tep_format_field *field, const void *data,
 			  unsigned long long *value);
 
+struct tep_event_format *tep_get_first_event(struct tep_handle *tep);
+int tep_get_events_count(struct tep_handle *tep);
 struct tep_event_format *tep_find_event(struct tep_handle *pevent, int id);
 
 struct tep_event_format *
 tep_find_event_by_name(struct tep_handle *pevent, const char *sys, const char *name);
-
 struct tep_event_format *
 tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record);
 
@@ -689,65 +559,23 @@ struct tep_event_format **tep_list_events(struct tep_handle *pevent, enum tep_ev
 struct tep_format_field **tep_event_common_fields(struct tep_event_format *event);
 struct tep_format_field **tep_event_fields(struct tep_event_format *event);
 
-static inline int tep_get_cpus(struct tep_handle *pevent)
-{
-	return pevent->cpus;
-}
-
-static inline void tep_set_cpus(struct tep_handle *pevent, int cpus)
-{
-	pevent->cpus = cpus;
-}
-
-static inline int tep_get_long_size(struct tep_handle *pevent)
-{
-	return pevent->long_size;
-}
-
-static inline void tep_set_long_size(struct tep_handle *pevent, int long_size)
-{
-	pevent->long_size = long_size;
-}
-
-static inline int tep_get_page_size(struct tep_handle *pevent)
-{
-	return pevent->page_size;
-}
-
-static inline void tep_set_page_size(struct tep_handle *pevent, int _page_size)
-{
-	pevent->page_size = _page_size;
-}
-
-static inline int tep_is_file_bigendian(struct tep_handle *pevent)
-{
-	return pevent->file_bigendian;
-}
-
-static inline void tep_set_file_bigendian(struct tep_handle *pevent, int endian)
-{
-	pevent->file_bigendian = endian;
-}
-
-static inline int tep_is_host_bigendian(struct tep_handle *pevent)
-{
-	return pevent->host_bigendian;
-}
-
-static inline void tep_set_host_bigendian(struct tep_handle *pevent, int endian)
-{
-	pevent->host_bigendian = endian;
-}
-
-static inline int tep_is_latency_format(struct tep_handle *pevent)
-{
-	return pevent->latency_format;
-}
-
-static inline void tep_set_latency_format(struct tep_handle *pevent, int lat)
-{
-	pevent->latency_format = lat;
-}
+enum tep_endian {
+        TEP_LITTLE_ENDIAN = 0,
+        TEP_BIG_ENDIAN
+};
+int tep_get_cpus(struct tep_handle *pevent);
+void tep_set_cpus(struct tep_handle *pevent, int cpus);
+int tep_get_long_size(struct tep_handle *pevent);
+void tep_set_long_size(struct tep_handle *pevent, int long_size);
+int tep_get_page_size(struct tep_handle *pevent);
+void tep_set_page_size(struct tep_handle *pevent, int _page_size);
+int tep_is_file_bigendian(struct tep_handle *pevent);
+void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian);
+int tep_is_host_bigendian(struct tep_handle *pevent);
+void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian);
+int tep_is_latency_format(struct tep_handle *pevent);
+void tep_set_latency_format(struct tep_handle *pevent, int lat);
+int tep_get_header_page_size(struct tep_handle *pevent);
 
 struct tep_handle *tep_alloc(void);
 void tep_free(struct tep_handle *pevent);
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
index 46eb64eb0c2e..e74f16c88398 100644
--- a/tools/lib/traceevent/event-plugin.c
+++ b/tools/lib/traceevent/event-plugin.c
@@ -14,6 +14,7 @@
 #include <unistd.h>
 #include <dirent.h>
 #include "event-parse.h"
+#include "event-parse-local.h"
 #include "event-utils.h"
 #include "trace-seq.h"
 
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index d64b6128fa7d..ed87cb56713d 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -11,6 +11,7 @@
 #include <sys/types.h>
 
 #include "event-parse.h"
+#include "event-parse-local.h"
 #include "event-utils.h"
 
 #define COMM "COMM"
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 02f97f5dd588..32e558a65af3 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -37,10 +37,11 @@ static int get_common_field(struct scripting_context *context,
 	struct tep_format_field *field;
 
 	if (!*size) {
-		if (!pevent->events)
+
+		event = tep_get_first_event(pevent);
+		if (!event)
 			return 0;
 
-		event = pevent->events[0];
 		field = tep_find_common_field(event, type);
 		if (!field)
 			return 0;
@@ -193,25 +194,29 @@ struct tep_event_format *trace_find_next_event(struct tep_handle *pevent,
 					       struct tep_event_format *event)
 {
 	static int idx;
+	int events_count;
+	struct tep_event_format *all_events;
 
-	if (!pevent || !pevent->events)
+	all_events = tep_get_first_event(pevent);
+	events_count = tep_get_events_count(pevent);
+	if (!pevent || !all_events || events_count < 1)
 		return NULL;
 
 	if (!event) {
 		idx = 0;
-		return pevent->events[0];
+		return all_events;
 	}
 
-	if (idx < pevent->nr_events && event == pevent->events[idx]) {
+	if (idx < events_count && event == (all_events + idx)) {
 		idx++;
-		if (idx == pevent->nr_events)
+		if (idx == events_count)
 			return NULL;
-		return pevent->events[idx];
+		return (all_events + idx);
 	}
 
-	for (idx = 1; idx < pevent->nr_events; idx++) {
-		if (event == pevent->events[idx - 1])
-			return pevent->events[idx];
+	for (idx = 1; idx < events_count; idx++) {
+		if (event == (all_events + (idx - 1)))
+			return (all_events + idx);
 	}
 	return NULL;
 }
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index add8441de579..76f12c705ef9 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -241,7 +241,7 @@ static int read_header_files(struct tep_handle *pevent)
 		 * The commit field in the page is of type long,
 		 * use that instead, since it represents the kernel.
 		 */
-		tep_set_long_size(pevent, pevent->header_page_size_size);
+		tep_set_long_size(pevent, tep_get_header_page_size(pevent));
 	}
 	free(header_page);
 
-- 
cgit v1.2.3


From d24ea8a7336a2c392728e2cf909d607a680feb7b Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@ozlabs.org>
Date: Mon, 8 Oct 2018 16:30:48 +1100
Subject: KVM: PPC: Book3S: Simplify external interrupt handling

Currently we use two bits in the vcpu pending_exceptions bitmap to
indicate that an external interrupt is pending for the guest, one
for "one-shot" interrupts that are cleared when delivered, and one
for interrupts that persist until cleared by an explicit action of
the OS (e.g. an acknowledge to an interrupt controller).  The
BOOK3S_IRQPRIO_EXTERNAL bit is used for one-shot interrupt requests
and BOOK3S_IRQPRIO_EXTERNAL_LEVEL is used for persisting interrupts.

In practice BOOK3S_IRQPRIO_EXTERNAL never gets used, because our
Book3S platforms generally, and pseries in particular, expect
external interrupt requests to persist until they are acknowledged
at the interrupt controller.  That combined with the confusion
introduced by having two bits for what is essentially the same thing
makes it attractive to simplify things by only using one bit.  This
patch does that.

With this patch there is only BOOK3S_IRQPRIO_EXTERNAL, and by default
it has the semantics of a persisting interrupt.  In order to avoid
breaking the ABI, we introduce a new "external_oneshot" flag which
preserves the behaviour of the KVM_INTERRUPT ioctl with the
KVM_INTERRUPT_SET argument.

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/kvm_asm.h             |  4 +--
 arch/powerpc/include/asm/kvm_host.h            |  1 +
 arch/powerpc/kvm/book3s.c                      | 43 ++++++++++++++++++++------
 arch/powerpc/kvm/book3s_hv_rm_xics.c           |  5 ++-
 arch/powerpc/kvm/book3s_hv_rmhandlers.S        |  4 +--
 arch/powerpc/kvm/book3s_pr.c                   |  1 -
 arch/powerpc/kvm/book3s_xics.c                 | 11 +++----
 arch/powerpc/kvm/book3s_xive_template.c        |  2 +-
 arch/powerpc/kvm/trace_book3s.h                |  1 -
 tools/perf/arch/powerpc/util/book3s_hv_exits.h |  1 -
 10 files changed, 44 insertions(+), 29 deletions(-)

(limited to 'tools')

diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index a790d5cf6ea3..1f321914676d 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -84,7 +84,6 @@
 #define BOOK3S_INTERRUPT_INST_STORAGE	0x400
 #define BOOK3S_INTERRUPT_INST_SEGMENT	0x480
 #define BOOK3S_INTERRUPT_EXTERNAL	0x500
-#define BOOK3S_INTERRUPT_EXTERNAL_LEVEL	0x501
 #define BOOK3S_INTERRUPT_EXTERNAL_HV	0x502
 #define BOOK3S_INTERRUPT_ALIGNMENT	0x600
 #define BOOK3S_INTERRUPT_PROGRAM	0x700
@@ -134,8 +133,7 @@
 #define BOOK3S_IRQPRIO_EXTERNAL			14
 #define BOOK3S_IRQPRIO_DECREMENTER		15
 #define BOOK3S_IRQPRIO_PERFORMANCE_MONITOR	16
-#define BOOK3S_IRQPRIO_EXTERNAL_LEVEL		17
-#define BOOK3S_IRQPRIO_MAX			18
+#define BOOK3S_IRQPRIO_MAX			17
 
 #define BOOK3S_HFLAG_DCBZ32			0x1
 #define BOOK3S_HFLAG_SLB			0x2
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 906bcbdfd2a1..3cd0b9f45c2a 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -707,6 +707,7 @@ struct kvm_vcpu_arch {
 	u8 hcall_needed;
 	u8 epr_flags; /* KVMPPC_EPR_xxx */
 	u8 epr_needed;
+	u8 external_oneshot;	/* clear external irq after delivery */
 
 	u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */
 
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 87348e498c89..66a55218e8dd 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -150,7 +150,6 @@ static int kvmppc_book3s_vec2irqprio(unsigned int vec)
 	case 0x400: prio = BOOK3S_IRQPRIO_INST_STORAGE;		break;
 	case 0x480: prio = BOOK3S_IRQPRIO_INST_SEGMENT;		break;
 	case 0x500: prio = BOOK3S_IRQPRIO_EXTERNAL;		break;
-	case 0x501: prio = BOOK3S_IRQPRIO_EXTERNAL_LEVEL;	break;
 	case 0x600: prio = BOOK3S_IRQPRIO_ALIGNMENT;		break;
 	case 0x700: prio = BOOK3S_IRQPRIO_PROGRAM;		break;
 	case 0x800: prio = BOOK3S_IRQPRIO_FP_UNAVAIL;		break;
@@ -236,18 +235,35 @@ EXPORT_SYMBOL_GPL(kvmppc_core_dequeue_dec);
 void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                 struct kvm_interrupt *irq)
 {
-	unsigned int vec = BOOK3S_INTERRUPT_EXTERNAL;
-
-	if (irq->irq == KVM_INTERRUPT_SET_LEVEL)
-		vec = BOOK3S_INTERRUPT_EXTERNAL_LEVEL;
+	/*
+	 * This case (KVM_INTERRUPT_SET) should never actually arise for
+	 * a pseries guest (because pseries guests expect their interrupt
+	 * controllers to continue asserting an external interrupt request
+	 * until it is acknowledged at the interrupt controller), but is
+	 * included to avoid ABI breakage and potentially for other
+	 * sorts of guest.
+	 *
+	 * There is a subtlety here: HV KVM does not test the
+	 * external_oneshot flag in the code that synthesizes
+	 * external interrupts for the guest just before entering
+	 * the guest.  That is OK even if userspace did do a
+	 * KVM_INTERRUPT_SET on a pseries guest vcpu, because the
+	 * caller (kvm_vcpu_ioctl_interrupt) does a kvm_vcpu_kick()
+	 * which ends up doing a smp_send_reschedule(), which will
+	 * pull the guest all the way out to the host, meaning that
+	 * we will call kvmppc_core_prepare_to_enter() before entering
+	 * the guest again, and that will handle the external_oneshot
+	 * flag correctly.
+	 */
+	if (irq->irq == KVM_INTERRUPT_SET)
+		vcpu->arch.external_oneshot = 1;
 
-	kvmppc_book3s_queue_irqprio(vcpu, vec);
+	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
 }
 
 void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu)
 {
 	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
-	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
 }
 
 void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu, ulong dar,
@@ -278,7 +294,6 @@ static int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu,
 		vec = BOOK3S_INTERRUPT_DECREMENTER;
 		break;
 	case BOOK3S_IRQPRIO_EXTERNAL:
-	case BOOK3S_IRQPRIO_EXTERNAL_LEVEL:
 		deliver = (kvmppc_get_msr(vcpu) & MSR_EE) && !crit;
 		vec = BOOK3S_INTERRUPT_EXTERNAL;
 		break;
@@ -352,8 +367,16 @@ static bool clear_irqprio(struct kvm_vcpu *vcpu, unsigned int priority)
 		case BOOK3S_IRQPRIO_DECREMENTER:
 			/* DEC interrupts get cleared by mtdec */
 			return false;
-		case BOOK3S_IRQPRIO_EXTERNAL_LEVEL:
-			/* External interrupts get cleared by userspace */
+		case BOOK3S_IRQPRIO_EXTERNAL:
+			/*
+			 * External interrupts get cleared by userspace
+			 * except when set by the KVM_INTERRUPT ioctl with
+			 * KVM_INTERRUPT_SET (not KVM_INTERRUPT_SET_LEVEL).
+			 */
+			if (vcpu->arch.external_oneshot) {
+				vcpu->arch.external_oneshot = 0;
+				return true;
+			}
 			return false;
 	}
 
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index 758d1d23215e..8b9f35689648 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -136,7 +136,7 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu,
 
 	/* Mark the target VCPU as having an interrupt pending */
 	vcpu->stat.queue_intr++;
-	set_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL, &vcpu->arch.pending_exceptions);
+	set_bit(BOOK3S_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions);
 
 	/* Kick self ? Just set MER and return */
 	if (vcpu == this_vcpu) {
@@ -170,8 +170,7 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu,
 static void icp_rm_clr_vcpu_irq(struct kvm_vcpu *vcpu)
 {
 	/* Note: Only called on self ! */
-	clear_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL,
-		  &vcpu->arch.pending_exceptions);
+	clear_bit(BOOK3S_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions);
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_MER);
 }
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 1d14046124a0..77960e68f7b0 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1122,11 +1122,11 @@ kvmppc_cede_reentry:		/* r4 = vcpu, r13 = paca */
 
 	/* Check if we can deliver an external or decrementer interrupt now */
 	ld	r0, VCPU_PENDING_EXC(r4)
-	rldicl	r0, r0, 64 - BOOK3S_IRQPRIO_EXTERNAL_LEVEL, 63
+	rldicl	r0, r0, 64 - BOOK3S_IRQPRIO_EXTERNAL, 63
 	cmpdi	cr1, r0, 0
 	andi.	r8, r11, MSR_EE
 	mfspr	r8, SPRN_LPCR
-	/* Insert EXTERNAL_LEVEL bit into LPCR at the MER bit position */
+	/* Insert EXTERNAL bit into LPCR at the MER bit position */
 	rldimi	r8, r0, LPCR_MER_SH, 63 - LPCR_MER_SH
 	mtspr	SPRN_LPCR, r8
 	isync
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 614ebb4261f7..059683e4e67a 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1246,7 +1246,6 @@ int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = RESUME_GUEST;
 		break;
 	case BOOK3S_INTERRUPT_EXTERNAL:
-	case BOOK3S_INTERRUPT_EXTERNAL_LEVEL:
 	case BOOK3S_INTERRUPT_EXTERNAL_HV:
 	case BOOK3S_INTERRUPT_H_VIRT:
 		vcpu->stat.ext_intr_exits++;
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index b8356cdc0c04..d9ba1b06d0f5 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -310,7 +310,7 @@ static inline bool icp_try_update(struct kvmppc_icp *icp,
 	 */
 	if (new.out_ee) {
 		kvmppc_book3s_queue_irqprio(icp->vcpu,
-					    BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
+					    BOOK3S_INTERRUPT_EXTERNAL);
 		if (!change_self)
 			kvmppc_fast_vcpu_kick(icp->vcpu);
 	}
@@ -593,8 +593,7 @@ static noinline unsigned long kvmppc_h_xirr(struct kvm_vcpu *vcpu)
 	u32 xirr;
 
 	/* First, remove EE from the processor */
-	kvmppc_book3s_dequeue_irqprio(icp->vcpu,
-				      BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
+	kvmppc_book3s_dequeue_irqprio(icp->vcpu, BOOK3S_INTERRUPT_EXTERNAL);
 
 	/*
 	 * ICP State: Accept_Interrupt
@@ -754,8 +753,7 @@ static noinline void kvmppc_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
 	 * We can remove EE from the current processor, the update
 	 * transaction will set it again if needed
 	 */
-	kvmppc_book3s_dequeue_irqprio(icp->vcpu,
-				      BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
+	kvmppc_book3s_dequeue_irqprio(icp->vcpu, BOOK3S_INTERRUPT_EXTERNAL);
 
 	do {
 		old_state = new_state = READ_ONCE(icp->state);
@@ -1167,8 +1165,7 @@ int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval)
 	 * Deassert the CPU interrupt request.
 	 * icp_try_update will reassert it if necessary.
 	 */
-	kvmppc_book3s_dequeue_irqprio(icp->vcpu,
-				      BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
+	kvmppc_book3s_dequeue_irqprio(icp->vcpu, BOOK3S_INTERRUPT_EXTERNAL);
 
 	/*
 	 * Note that if we displace an interrupt from old_state.xisr,
diff --git a/arch/powerpc/kvm/book3s_xive_template.c b/arch/powerpc/kvm/book3s_xive_template.c
index 4171ede8722b..203ea654c81e 100644
--- a/arch/powerpc/kvm/book3s_xive_template.c
+++ b/arch/powerpc/kvm/book3s_xive_template.c
@@ -285,7 +285,7 @@ X_STATIC unsigned long GLUE(X_PFX,h_xirr)(struct kvm_vcpu *vcpu)
 	 * set by pull or an escalation interrupts).
 	 */
 	if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions))
-		clear_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL,
+		clear_bit(BOOK3S_IRQPRIO_EXTERNAL,
 			  &vcpu->arch.pending_exceptions);
 
 	pr_devel(" new pending=0x%02x hw_cppr=%d cppr=%d\n",
diff --git a/arch/powerpc/kvm/trace_book3s.h b/arch/powerpc/kvm/trace_book3s.h
index f3b23759e017..372a82fa2de3 100644
--- a/arch/powerpc/kvm/trace_book3s.h
+++ b/arch/powerpc/kvm/trace_book3s.h
@@ -14,7 +14,6 @@
 	{0x400, "INST_STORAGE"}, \
 	{0x480, "INST_SEGMENT"}, \
 	{0x500, "EXTERNAL"}, \
-	{0x501, "EXTERNAL_LEVEL"}, \
 	{0x502, "EXTERNAL_HV"}, \
 	{0x600, "ALIGNMENT"}, \
 	{0x700, "PROGRAM"}, \
diff --git a/tools/perf/arch/powerpc/util/book3s_hv_exits.h b/tools/perf/arch/powerpc/util/book3s_hv_exits.h
index 853b95d1e139..2011376c7ab5 100644
--- a/tools/perf/arch/powerpc/util/book3s_hv_exits.h
+++ b/tools/perf/arch/powerpc/util/book3s_hv_exits.h
@@ -15,7 +15,6 @@
 	{0x400, "INST_STORAGE"}, \
 	{0x480, "INST_SEGMENT"}, \
 	{0x500, "EXTERNAL"}, \
-	{0x501, "EXTERNAL_LEVEL"}, \
 	{0x502, "EXTERNAL_HV"}, \
 	{0x600, "ALIGNMENT"}, \
 	{0x700, "PROGRAM"}, \
-- 
cgit v1.2.3


From 5484f0334439701900121a107709c461215cadb6 Mon Sep 17 00:00:00 2001
From: Todd Brandt <todd.e.brandt@linux.intel.com>
Date: Mon, 8 Oct 2018 15:56:31 -0700
Subject: PM / tools: sleepgraph: first batch of v5.2 changes

general:
- add battery charge data before and after test
- remove special s0i3 handling
- remove melding of dmesg & ftrace data in old kernels, use one only
- updates to various kprobes in trace (ksys_sync, etc)
- enable pm_debug_messages during the test
- instrument more subsystems with dev functions (phy0)

error handling:
- return codes for tool show the status of the test run
- 0: success, 1: general error (no timeline), 2: fail (suspend aborted)
- monitor output of /sys/power/state, mark as failure if exception occurs
- add signal handler when using -result to catch tool exceptions

display control
- add -x commands for testing xset with mode settings and status
- allow display setting to on, off, suspend, standby
- add display mode change info to the log, along with a warning on fail

s2idle (freeze)
- remove fixed 10-phase dependency, allow any phase order & any count
- multiple phase occurences show as phase_nameN e.g. suspend_noirq3
- if multiple freezes occur, print multiple time values in header

summary:
- add new columns to summary output: issues, worst suspend/resume devices
- worst device: includes summation of all phases of suspend or resume
- issues: includes WARNING/ERROR/BUG from dmesg log, and other issues
- s2idle: multiple freezes show as FREEZExN in the issues column

Signed-off-by: Todd Brandt <todd.e.brandt@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 tools/power/pm-graph/Makefile      |    4 +-
 tools/power/pm-graph/sleepgraph.8  |   13 +-
 tools/power/pm-graph/sleepgraph.py | 1378 +++++++++++++++++++-----------------
 3 files changed, 760 insertions(+), 635 deletions(-)

(limited to 'tools')

diff --git a/tools/power/pm-graph/Makefile b/tools/power/pm-graph/Makefile
index c1899cd72c80..845541544570 100644
--- a/tools/power/pm-graph/Makefile
+++ b/tools/power/pm-graph/Makefile
@@ -23,8 +23,8 @@ install : uninstall
 	install -m 644 config/suspend-x2-proc.cfg $(DESTDIR)$(PREFIX)/lib/pm-graph/config
 
 	install -d  $(DESTDIR)$(PREFIX)/bin
-	ln -s $(DESTDIR)$(PREFIX)/lib/pm-graph/bootgraph.py $(DESTDIR)$(PREFIX)/bin/bootgraph
-	ln -s $(DESTDIR)$(PREFIX)/lib/pm-graph/sleepgraph.py $(DESTDIR)$(PREFIX)/bin/sleepgraph
+	ln -s ../lib/pm-graph/bootgraph.py $(DESTDIR)$(PREFIX)/bin/bootgraph
+	ln -s ../lib/pm-graph/sleepgraph.py $(DESTDIR)$(PREFIX)/bin/sleepgraph
 
 	install -d  $(DESTDIR)$(PREFIX)/share/man/man8
 	install bootgraph.8 $(DESTDIR)$(PREFIX)/share/man/man8
diff --git a/tools/power/pm-graph/sleepgraph.8 b/tools/power/pm-graph/sleepgraph.8
index 070be2cf7f74..24a2e7d0ae63 100644
--- a/tools/power/pm-graph/sleepgraph.8
+++ b/tools/power/pm-graph/sleepgraph.8
@@ -65,9 +65,9 @@ During test, enable/disable runtime suspend for all devices. The test is delayed
 by 5 seconds to allow runtime suspend changes to occur. The settings are restored
 after the test is complete.
 .TP
-\fB-display \fIon/off\fR
-Turn the display on or off for the test using the xset command. This helps
-maintain the consistecy of test data for better comparison.
+\fB-display \fIon/off/standby/suspend\fR
+Switch the display to the requested mode for the test using the xset command.
+This helps maintain the consistency of test data for better comparison.
 .TP
 \fB-skiphtml\fR
 Run the test and capture the trace logs, but skip the timeline generation.
@@ -183,6 +183,13 @@ Print out the contents of the ACPI Firmware Performance Data Table.
 \fB-battery\fR
 Print out battery status and current charge.
 .TP
+\fB-xon/-xoff/-xstandby/-xsuspend\fR
+Test xset by attempting to switch the display to the given mode. This
+is the same command which will be issued by \fB-display \fImode\fR.
+.TP
+\fB-xstat\fR
+Get the current DPMS display mode.
+.TP
 \fB-sysinfo\fR
 Print out system info extracted from BIOS. Reads /dev/mem directly instead of going through dmidecode.
 .TP
diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py
index 0c760478f7d7..343e8000d9ca 100755
--- a/tools/power/pm-graph/sleepgraph.py
+++ b/tools/power/pm-graph/sleepgraph.py
@@ -54,6 +54,7 @@ import os
 import string
 import re
 import platform
+import signal
 from datetime import datetime
 import struct
 import ConfigParser
@@ -72,7 +73,7 @@ class SystemValues:
 	version = '5.1'
 	ansi = False
 	rs = 0
-	display = 0
+	display = ''
 	gzip = False
 	sync = False
 	verbose = False
@@ -99,6 +100,7 @@ class SystemValues:
 	tpath = '/sys/kernel/debug/tracing/'
 	fpdtpath = '/sys/firmware/acpi/tables/FPDT'
 	epath = '/sys/kernel/debug/tracing/events/power/'
+	pmdpath = '/sys/power/pm_debug_messages'
 	traceevents = [
 		'suspend_resume',
 		'device_pm_callback_end',
@@ -141,12 +143,10 @@ class SystemValues:
 	devprops = dict()
 	predelay = 0
 	postdelay = 0
-	procexecfmt = 'ps - (?P<ps>.*)$'
-	devpropfmt = '# Device Properties: .*'
-	tracertypefmt = '# tracer: (?P<t>.*)'
-	firmwarefmt = '# fwsuspend (?P<s>[0-9]*) fwresume (?P<r>[0-9]*)$'
+	pmdebug = ''
 	tracefuncs = {
 		'sys_sync': {},
+		'ksys_sync': {},
 		'__pm_notifier_call_chain': {},
 		'pm_prepare_console': {},
 		'pm_notifier_call_chain': {},
@@ -187,7 +187,6 @@ class SystemValues:
 	dev_tracefuncs = {
 		# general wait/delay/sleep
 		'msleep': { 'args_x86_64': {'time':'%di:s32'}, 'ub': 1 },
-		'schedule_timeout_uninterruptible': { 'args_x86_64': {'timeout':'%di:s32'}, 'ub': 1 },
 		'schedule_timeout': { 'args_x86_64': {'timeout':'%di:s32'}, 'ub': 1 },
 		'udelay': { 'func':'__const_udelay', 'args_x86_64': {'loops':'%di:s32'}, 'ub': 1 },
 		'usleep_range': { 'args_x86_64': {'min':'%di:s32', 'max':'%si:s32'}, 'ub': 1 },
@@ -199,6 +198,9 @@ class SystemValues:
 		# filesystem
 		'ext4_sync_fs': {},
 		# 80211
+		'ath10k_bmi_read_memory': { 'args_x86_64': {'length':'%cx:s32'} },
+		'ath10k_bmi_write_memory': { 'args_x86_64': {'length':'%cx:s32'} },
+		'ath10k_bmi_fast_download': { 'args_x86_64': {'length':'%cx:s32'} },
 		'iwlagn_mac_start': {},
 		'iwlagn_alloc_bcast_station': {},
 		'iwl_trans_pcie_start_hw': {},
@@ -241,6 +243,7 @@ class SystemValues:
 	timeformat = '%.3f'
 	cmdline = '%s %s' % \
 			(os.path.basename(sys.argv[0]), ' '.join(sys.argv[1:]))
+	sudouser = ''
 	def __init__(self):
 		self.archargs = 'args_'+platform.machine()
 		self.hostname = platform.node()
@@ -256,10 +259,32 @@ class SystemValues:
 		if (hasattr(sys.stdout, 'isatty') and sys.stdout.isatty()):
 			self.ansi = True
 		self.testdir = datetime.now().strftime('suspend-%y%m%d-%H%M%S')
+		if os.getuid() == 0 and 'SUDO_USER' in os.environ and \
+			os.environ['SUDO_USER']:
+			self.sudouser = os.environ['SUDO_USER']
 	def vprint(self, msg):
 		self.logmsg += msg+'\n'
-		if(self.verbose):
+		if self.verbose or msg.startswith('WARNING:'):
 			print(msg)
+	def signalHandler(self, signum, frame):
+		if not self.result:
+			return
+		signame = self.signames[signum] if signum in self.signames else 'UNKNOWN'
+		msg = 'Signal %s caused a tool exit, line %d' % (signame, frame.f_lineno)
+		sysvals.outputResult({'error':msg})
+		sys.exit(3)
+	def signalHandlerInit(self):
+		capture = ['BUS', 'SYS', 'XCPU', 'XFSZ', 'PWR', 'HUP', 'INT', 'QUIT',
+			'ILL', 'ABRT', 'FPE', 'SEGV', 'TERM', 'TSTP']
+		self.signames = dict()
+		for i in capture:
+			s = 'SIG'+i
+			try:
+				signum = getattr(signal, s)
+				signal.signal(signum, self.signalHandler)
+			except:
+				continue
+			self.signames[signum] = s
 	def rootCheck(self, fatal=True):
 		if(os.access(self.powerfile, os.W_OK)):
 			return True
@@ -267,7 +292,7 @@ class SystemValues:
 			msg = 'This command requires sysfs mount and root access'
 			print('ERROR: %s\n') % msg
 			self.outputResult({'error':msg})
-			sys.exit()
+			sys.exit(1)
 		return False
 	def rootUser(self, fatal=False):
 		if 'USER' in os.environ and os.environ['USER'] == 'root':
@@ -276,7 +301,7 @@ class SystemValues:
 			msg = 'This command must be run as root'
 			print('ERROR: %s\n') % msg
 			self.outputResult({'error':msg})
-			sys.exit()
+			sys.exit(1)
 		return False
 	def getExec(self, cmd):
 		dirlist = ['/sbin', '/bin', '/usr/sbin', '/usr/bin',
@@ -406,8 +431,8 @@ class SystemValues:
 				ktime = m.group('ktime')
 		fp.close()
 		self.dmesgstart = float(ktime)
-	def getdmesg(self, fwdata=[]):
-		op = self.writeDatafileHeader(sysvals.dmesgfile, fwdata)
+	def getdmesg(self, testdata):
+		op = self.writeDatafileHeader(sysvals.dmesgfile, testdata)
 		# store all new dmesg lines since initdmesg was called
 		fp = Popen('dmesg', stdout=PIPE).stdout
 		for line in fp:
@@ -619,6 +644,8 @@ class SystemValues:
 			self.fsetVal('0', 'events/kprobes/enable')
 			self.fsetVal('', 'kprobe_events')
 			self.fsetVal('1024', 'buffer_size_kb')
+		if self.pmdebug:
+			self.setVal(self.pmdebug, self.pmdpath)
 	def setupAllKprobes(self):
 		for name in self.tracefuncs:
 			self.defaultKprobe(name, self.tracefuncs[name])
@@ -641,6 +668,11 @@ class SystemValues:
 		# turn trace off
 		self.fsetVal('0', 'tracing_on')
 		self.cleanupFtrace()
+		# pm debug messages
+		pv = self.getVal(self.pmdpath)
+		if pv != '1':
+			self.setVal('1', self.pmdpath)
+			self.pmdebug = pv
 		# set the trace clock to global
 		self.fsetVal('global', 'trace_clock')
 		self.fsetVal('nop', 'current_tracer')
@@ -728,19 +760,24 @@ class SystemValues:
 		if not self.ansi:
 			return str
 		return '\x1B[%d;40m%s\x1B[m' % (color, str)
-	def writeDatafileHeader(self, filename, fwdata=[]):
+	def writeDatafileHeader(self, filename, testdata):
 		fp = self.openlog(filename, 'w')
 		fp.write('%s\n%s\n# command | %s\n' % (self.teststamp, self.sysstamp, self.cmdline))
-		if(self.suspendmode == 'mem' or self.suspendmode == 'command'):
-			for fw in fwdata:
+		for test in testdata:
+			if 'fw' in test:
+				fw = test['fw']
 				if(fw):
 					fp.write('# fwsuspend %u fwresume %u\n' % (fw[0], fw[1]))
+			if 'bat' in test:
+				(a1, c1), (a2, c2) = test['bat']
+				fp.write('# battery %s %d %s %d\n' % (a1, c1, a2, c2))
+			if test['error'] or len(testdata) > 1:
+				fp.write('# enter_sleep_error %s\n' % test['error'])
 		return fp
-	def sudouser(self, dir):
-		if os.path.exists(dir) and os.getuid() == 0 and \
-			'SUDO_USER' in os.environ:
+	def sudoUserchown(self, dir):
+		if os.path.exists(dir) and self.sudouser:
 			cmd = 'chown -R {0}:{0} {1} > /dev/null 2>&1'
-			call(cmd.format(os.environ['SUDO_USER'], dir), shell=True)
+			call(cmd.format(self.sudouser, dir), shell=True)
 	def outputResult(self, testdata, num=0):
 		if not self.result:
 			return
@@ -762,7 +799,7 @@ class SystemValues:
 		if 'bugurl' in testdata:
 			fp.write('url%s: %s\n' % (n, testdata['bugurl']))
 		fp.close()
-		self.sudouser(self.result)
+		self.sudoUserchown(self.result)
 	def configFile(self, file):
 		dir = os.path.dirname(os.path.realpath(__file__))
 		if os.path.exists(file):
@@ -800,11 +837,12 @@ suspendmodename = {
 #	 Simple class which holds property values collected
 #	 for all the devices used in the timeline.
 class DevProps:
-	syspath = ''
-	altname = ''
-	async = True
-	xtraclass = ''
-	xtrainfo = ''
+	def __init__(self):
+		self.syspath = ''
+		self.altname = ''
+		self.async = True
+		self.xtraclass = ''
+		self.xtrainfo = ''
 	def out(self, dev):
 		return '%s,%s,%d;' % (dev, self.altname, self.async)
 	def debug(self, dev):
@@ -831,9 +869,6 @@ class DevProps:
 #	 A container used to create a device hierachy, with a single root node
 #	 and a tree of child nodes. Used by Data.deviceTopology()
 class DeviceNode:
-	name = ''
-	children = 0
-	depth = 0
 	def __init__(self, nodename, nodedepth):
 		self.name = nodename
 		self.children = []
@@ -861,71 +896,78 @@ class DeviceNode:
 #	}
 #
 class Data:
-	dmesg = {}  # root data structure
-	phases = [] # ordered list of phases
-	start = 0.0 # test start
-	end = 0.0   # test end
-	tSuspended = 0.0 # low-level suspend start
-	tResumed = 0.0   # low-level resume start
-	tKernSus = 0.0   # kernel level suspend start
-	tKernRes = 0.0   # kernel level resume end
-	tLow = 0.0       # time spent in low-level suspend (standby/freeze)
-	fwValid = False  # is firmware data available
-	fwSuspend = 0    # time spent in firmware suspend
-	fwResume = 0     # time spent in firmware resume
-	dmesgtext = []   # dmesg text file in memory
-	pstl = 0         # process timeline
-	testnumber = 0
-	idstr = ''
-	html_device_id = 0
-	stamp = 0
-	outfile = ''
-	devpids = []
-	kerror = False
+	phasedef = {
+		'suspend_prepare': {'order': 0, 'color': '#CCFFCC'},
+		        'suspend': {'order': 1, 'color': '#88FF88'},
+		   'suspend_late': {'order': 2, 'color': '#00AA00'},
+		  'suspend_noirq': {'order': 3, 'color': '#008888'},
+		'suspend_machine': {'order': 4, 'color': '#0000FF'},
+		 'resume_machine': {'order': 5, 'color': '#FF0000'},
+		   'resume_noirq': {'order': 6, 'color': '#FF9900'},
+		   'resume_early': {'order': 7, 'color': '#FFCC00'},
+		         'resume': {'order': 8, 'color': '#FFFF88'},
+		'resume_complete': {'order': 9, 'color': '#FFFFCC'},
+	}
+	errlist = {
+		'HWERROR' : '.*\[ *Hardware Error *\].*',
+		'FWBUG'   : '.*\[ *Firmware Bug *\].*',
+		'BUG'     : '.*BUG.*',
+		'ERROR'   : '.*ERROR.*',
+		'WARNING' : '.*WARNING.*',
+		'IRQ'     : '.*genirq: .*',
+		'TASKFAIL': '.*Freezing of tasks failed.*',
+	}
 	def __init__(self, num):
 		idchar = 'abcdefghij'
-		self.pstl = dict()
+		self.start = 0.0 # test start
+		self.end = 0.0   # test end
+		self.tSuspended = 0.0 # low-level suspend start
+		self.tResumed = 0.0   # low-level resume start
+		self.tKernSus = 0.0   # kernel level suspend start
+		self.tKernRes = 0.0   # kernel level resume end
+		self.fwValid = False  # is firmware data available
+		self.fwSuspend = 0    # time spent in firmware suspend
+		self.fwResume = 0     # time spent in firmware resume
+		self.html_device_id = 0
+		self.stamp = 0
+		self.outfile = ''
+		self.kerror = False
+		self.battery = 0
+		self.enterfail = ''
+		self.currphase = ''
+		self.pstl = dict()    # process timeline
 		self.testnumber = num
 		self.idstr = idchar[num]
-		self.dmesgtext = []
-		self.phases = []
-		self.dmesg = { # fixed list of 10 phases
-			'suspend_prepare': {'list': dict(), 'start': -1.0, 'end': -1.0,
-								'row': 0, 'color': '#CCFFCC', 'order': 0},
-			        'suspend': {'list': dict(), 'start': -1.0, 'end': -1.0,
-								'row': 0, 'color': '#88FF88', 'order': 1},
-			   'suspend_late': {'list': dict(), 'start': -1.0, 'end': -1.0,
-								'row': 0, 'color': '#00AA00', 'order': 2},
-			  'suspend_noirq': {'list': dict(), 'start': -1.0, 'end': -1.0,
-								'row': 0, 'color': '#008888', 'order': 3},
-		    'suspend_machine': {'list': dict(), 'start': -1.0, 'end': -1.0,
-								'row': 0, 'color': '#0000FF', 'order': 4},
-			 'resume_machine': {'list': dict(), 'start': -1.0, 'end': -1.0,
-								'row': 0, 'color': '#FF0000', 'order': 5},
-			   'resume_noirq': {'list': dict(), 'start': -1.0, 'end': -1.0,
-								'row': 0, 'color': '#FF9900', 'order': 6},
-			   'resume_early': {'list': dict(), 'start': -1.0, 'end': -1.0,
-								'row': 0, 'color': '#FFCC00', 'order': 7},
-			         'resume': {'list': dict(), 'start': -1.0, 'end': -1.0,
-								'row': 0, 'color': '#FFFF88', 'order': 8},
-			'resume_complete': {'list': dict(), 'start': -1.0, 'end': -1.0,
-								'row': 0, 'color': '#FFFFCC', 'order': 9}
-		}
-		self.phases = self.sortedPhases()
+		self.dmesgtext = []   # dmesg text file in memory
+		self.dmesg = dict()   # root data structure
+		self.errorinfo = {'suspend':[],'resume':[]}
+		self.tLow = []        # time spent in low-level suspends (standby/freeze)
+		self.devpids = []
+		self.devicegroups = 0
+	def sortedPhases(self):
+		return sorted(self.dmesg, key=lambda k:self.dmesg[k]['order'])
+	def initDevicegroups(self):
+		# called when phases are all finished being added
+		for phase in self.dmesg.keys():
+			if '*' in phase:
+				p = phase.split('*')
+				pnew = '%s%d' % (p[0], len(p))
+				self.dmesg[pnew] = self.dmesg.pop(phase)
 		self.devicegroups = []
-		for phase in self.phases:
+		for phase in self.sortedPhases():
 			self.devicegroups.append([phase])
-		self.errorinfo = {'suspend':[],'resume':[]}
+	def nextPhase(self, phase, offset):
+		order = self.dmesg[phase]['order'] + offset
+		for p in self.dmesg:
+			if self.dmesg[p]['order'] == order:
+				return p
+		return ''
+	def lastPhase(self):
+		plist = self.sortedPhases()
+		if len(plist) < 1:
+			return ''
+		return plist[-1]
 	def extractErrorInfo(self):
-		elist = {
-			'HWERROR' : '.*\[ *Hardware Error *\].*',
-			'FWBUG'   : '.*\[ *Firmware Bug *\].*',
-			'BUG'     : '.*BUG.*',
-			'ERROR'   : '.*ERROR.*',
-			'WARNING' : '.*WARNING.*',
-			'IRQ'     : '.*genirq: .*',
-			'TASKFAIL': '.*Freezing of tasks failed.*',
-		}
 		lf = sysvals.openlog(sysvals.dmesgfile, 'r')
 		i = 0
 		list = []
@@ -939,8 +981,8 @@ class Data:
 				continue
 			dir = 'suspend' if t < self.tSuspended else 'resume'
 			msg = m.group('msg')
-			for err in elist:
-				if re.match(elist[err], msg):
+			for err in self.errlist:
+				if re.match(self.errlist[err], msg):
 					list.append((err, dir, t, i, i))
 					self.kerror = True
 					break
@@ -956,7 +998,7 @@ class Data:
 	def setEnd(self, time):
 		self.end = time
 	def isTraceEventOutsideDeviceCalls(self, pid, time):
-		for phase in self.phases:
+		for phase in self.sortedPhases():
 			list = self.dmesg[phase]['list']
 			for dev in list:
 				d = list[dev]
@@ -964,16 +1006,10 @@ class Data:
 					time < d['end']):
 					return False
 		return True
-	def phaseCollision(self, phase, isbegin, line):
-		key = 'end'
-		if isbegin:
-			key = 'start'
-		if self.dmesg[phase][key] >= 0:
-			sysvals.vprint('IGNORE: %s' % line.strip())
-			return True
-		return False
 	def sourcePhase(self, start):
-		for phase in self.phases:
+		for phase in self.sortedPhases():
+			if 'machine' in phase:
+				continue
 			pend = self.dmesg[phase]['end']
 			if start <= pend:
 				return phase
@@ -1004,14 +1040,15 @@ class Data:
 		return tgtdev
 	def addDeviceFunctionCall(self, displayname, kprobename, proc, pid, start, end, cdata, rdata):
 		# try to place the call in a device
-		tgtdev = self.sourceDevice(self.phases, start, end, pid, 'device')
+		phases = self.sortedPhases()
+		tgtdev = self.sourceDevice(phases, start, end, pid, 'device')
 		# calls with device pids that occur outside device bounds are dropped
 		# TODO: include these somehow
 		if not tgtdev and pid in self.devpids:
 			return False
 		# try to place the call in a thread
 		if not tgtdev:
-			tgtdev = self.sourceDevice(self.phases, start, end, pid, 'thread')
+			tgtdev = self.sourceDevice(phases, start, end, pid, 'thread')
 		# create new thread blocks, expand as new calls are found
 		if not tgtdev:
 			if proc == '<...>':
@@ -1053,7 +1090,7 @@ class Data:
 	def overflowDevices(self):
 		# get a list of devices that extend beyond the end of this test run
 		devlist = []
-		for phase in self.phases:
+		for phase in self.sortedPhases():
 			list = self.dmesg[phase]['list']
 			for devname in list:
 				dev = list[devname]
@@ -1064,7 +1101,7 @@ class Data:
 		# merge any devices that overlap devlist
 		for dev in devlist:
 			devname = dev['name']
-			for phase in self.phases:
+			for phase in self.sortedPhases():
 				list = self.dmesg[phase]['list']
 				if devname not in list:
 					continue
@@ -1079,7 +1116,7 @@ class Data:
 				del list[devname]
 	def usurpTouchingThread(self, name, dev):
 		# the caller test has priority of this thread, give it to him
-		for phase in self.phases:
+		for phase in self.sortedPhases():
 			list = self.dmesg[phase]['list']
 			if name in list:
 				tdev = list[name]
@@ -1093,7 +1130,7 @@ class Data:
 				break
 	def stitchTouchingThreads(self, testlist):
 		# merge any threads between tests that touch
-		for phase in self.phases:
+		for phase in self.sortedPhases():
 			list = self.dmesg[phase]['list']
 			for devname in list:
 				dev = list[devname]
@@ -1103,7 +1140,7 @@ class Data:
 					data.usurpTouchingThread(devname, dev)
 	def optimizeDevSrc(self):
 		# merge any src call loops to reduce timeline size
-		for phase in self.phases:
+		for phase in self.sortedPhases():
 			list = self.dmesg[phase]['list']
 			for dev in list:
 				if 'src' not in list[dev]:
@@ -1141,7 +1178,7 @@ class Data:
 		self.tKernSus = self.trimTimeVal(self.tKernSus, t0, dT, left)
 		self.tKernRes = self.trimTimeVal(self.tKernRes, t0, dT, left)
 		self.end = self.trimTimeVal(self.end, t0, dT, left)
-		for phase in self.phases:
+		for phase in self.sortedPhases():
 			p = self.dmesg[phase]
 			p['start'] = self.trimTimeVal(p['start'], t0, dT, left)
 			p['end'] = self.trimTimeVal(p['end'], t0, dT, left)
@@ -1150,6 +1187,7 @@ class Data:
 				d = list[name]
 				d['start'] = self.trimTimeVal(d['start'], t0, dT, left)
 				d['end'] = self.trimTimeVal(d['end'], t0, dT, left)
+				d['length'] = d['end'] - d['start']
 				if('ftrace' in d):
 					cg = d['ftrace']
 					cg.start = self.trimTimeVal(cg.start, t0, dT, left)
@@ -1166,30 +1204,59 @@ class Data:
 				tm = self.trimTimeVal(tm, t0, dT, left)
 				list.append((type, tm, idx1, idx2))
 			self.errorinfo[dir] = list
-	def normalizeTime(self, tZero):
+	def trimFreezeTime(self, tZero):
 		# trim out any standby or freeze clock time
-		if(self.tSuspended != self.tResumed):
-			if(self.tResumed > tZero):
-				self.trimTime(self.tSuspended, \
-					self.tResumed-self.tSuspended, True)
-			else:
-				self.trimTime(self.tSuspended, \
-					self.tResumed-self.tSuspended, False)
+		lp = ''
+		for phase in self.sortedPhases():
+			if 'resume_machine' in phase and 'suspend_machine' in lp:
+				tS, tR = self.dmesg[lp]['end'], self.dmesg[phase]['start']
+				tL = tR - tS
+				if tL > 0:
+					left = True if tR > tZero else False
+					self.trimTime(tS, tL, left)
+					self.tLow.append('%.0f'%(tL*1000))
+			lp = phase
 	def getTimeValues(self):
-		sktime = (self.dmesg['suspend_machine']['end'] - \
-			self.tKernSus) * 1000
-		rktime = (self.dmesg['resume_complete']['end'] - \
-			self.dmesg['resume_machine']['start']) * 1000
+		if 'suspend_machine' in self.dmesg:
+			sktime = (self.dmesg['suspend_machine']['end'] - \
+				self.tKernSus) * 1000
+		else:
+			sktime = (self.tSuspended - self.tKernSus) * 1000
+		if 'resume_machine' in self.dmesg:
+			rktime = (self.tKernRes - \
+				self.dmesg['resume_machine']['start']) * 1000
+		else:
+			rktime = (self.tKernRes - self.tResumed) * 1000
 		return (sktime, rktime)
-	def setPhase(self, phase, ktime, isbegin):
+	def setPhase(self, phase, ktime, isbegin, order=-1):
 		if(isbegin):
+			# phase start over current phase
+			if self.currphase:
+				if 'resume_machine' not in self.currphase:
+					sysvals.vprint('WARNING: phase %s failed to end' % self.currphase)
+				self.dmesg[self.currphase]['end'] = ktime
+			phases = self.dmesg.keys()
+			color = self.phasedef[phase]['color']
+			count = len(phases) if order < 0 else order
+			# create unique name for every new phase
+			while phase in phases:
+				phase += '*'
+			self.dmesg[phase] = {'list': dict(), 'start': -1.0, 'end': -1.0,
+				'row': 0, 'color': color, 'order': count}
 			self.dmesg[phase]['start'] = ktime
+			self.currphase = phase
 		else:
+			# phase end without a start
+			if phase not in self.currphase:
+				if self.currphase:
+					sysvals.vprint('WARNING: %s ended instead of %s, ftrace corruption?' % (phase, self.currphase))
+				else:
+					sysvals.vprint('WARNING: %s ended without a start, ftrace corruption?' % phase)
+					return phase
+			phase = self.currphase
 			self.dmesg[phase]['end'] = ktime
-	def dmesgSortVal(self, phase):
-		return self.dmesg[phase]['order']
-	def sortedPhases(self):
-		return sorted(self.dmesg, key=self.dmesgSortVal)
+			self.currphase = ''
+		return phase
 	def sortedDevices(self, phase):
 		list = self.dmesg[phase]['list']
 		slist = []
@@ -1208,13 +1275,13 @@ class Data:
 		for devname in phaselist:
 			dev = phaselist[devname]
 			if(dev['end'] < 0):
-				for p in self.phases:
+				for p in self.sortedPhases():
 					if self.dmesg[p]['end'] > dev['start']:
 						dev['end'] = self.dmesg[p]['end']
 						break
 				sysvals.vprint('%s (%s): callback didnt return' % (devname, phase))
 	def deviceFilter(self, devicefilter):
-		for phase in self.phases:
+		for phase in self.sortedPhases():
 			list = self.dmesg[phase]['list']
 			rmlist = []
 			for name in list:
@@ -1229,7 +1296,7 @@ class Data:
 				del list[name]
 	def fixupInitcallsThatDidntReturn(self):
 		# if any calls never returned, clip them at system resume end
-		for phase in self.phases:
+		for phase in self.sortedPhases():
 			self.fixupInitcalls(phase)
 	def phaseOverlap(self, phases):
 		rmgroups = []
@@ -1248,17 +1315,18 @@ class Data:
 		self.devicegroups.append(newgroup)
 	def newActionGlobal(self, name, start, end, pid=-1, color=''):
 		# which phase is this device callback or action in
+		phases = self.sortedPhases()
 		targetphase = 'none'
 		htmlclass = ''
 		overlap = 0.0
-		phases = []
-		for phase in self.phases:
+		myphases = []
+		for phase in phases:
 			pstart = self.dmesg[phase]['start']
 			pend = self.dmesg[phase]['end']
 			# see if the action overlaps this phase
 			o = max(0, min(end, pend) - max(start, pstart))
 			if o > 0:
-				phases.append(phase)
+				myphases.append(phase)
 			# set the target phase to the one that overlaps most
 			if o > overlap:
 				if overlap > 0 and phase == 'post_resume':
@@ -1267,19 +1335,19 @@ class Data:
 				overlap = o
 		# if no target phase was found, pin it to the edge
 		if targetphase == 'none':
-			p0start = self.dmesg[self.phases[0]]['start']
+			p0start = self.dmesg[phases[0]]['start']
 			if start <= p0start:
-				targetphase = self.phases[0]
+				targetphase = phases[0]
 			else:
-				targetphase = self.phases[-1]
+				targetphase = phases[-1]
 		if pid == -2:
 			htmlclass = ' bg'
 		elif pid == -3:
 			htmlclass = ' ps'
-		if len(phases) > 1:
+		if len(myphases) > 1:
 			htmlclass = ' bg'
-			self.phaseOverlap(phases)
-		if targetphase in self.phases:
+			self.phaseOverlap(myphases)
+		if targetphase in phases:
 			newname = self.newAction(targetphase, name, pid, '', start, end, '', htmlclass, color)
 			return (targetphase, newname)
 		return False
@@ -1315,7 +1383,7 @@ class Data:
 		sysvals.vprint('Timeline Details:')
 		sysvals.vprint('          test start: %f' % self.start)
 		sysvals.vprint('kernel suspend start: %f' % self.tKernSus)
-		for phase in self.phases:
+		for phase in self.sortedPhases():
 			dc = len(self.dmesg[phase]['list'])
 			sysvals.vprint('    %16s: %f - %f (%d devices)' % (phase, \
 				self.dmesg[phase]['start'], self.dmesg[phase]['end'], dc))
@@ -1323,7 +1391,7 @@ class Data:
 		sysvals.vprint('            test end: %f' % self.end)
 	def deviceChildrenAllPhases(self, devname):
 		devlist = []
-		for phase in self.phases:
+		for phase in self.sortedPhases():
 			list = self.deviceChildren(devname, phase)
 			for dev in list:
 				if dev not in devlist:
@@ -1344,7 +1412,7 @@ class Data:
 		if node.name:
 			info = ''
 			drv = ''
-			for phase in self.phases:
+			for phase in self.sortedPhases():
 				list = self.dmesg[phase]['list']
 				if node.name in list:
 					s = list[node.name]['start']
@@ -1478,8 +1546,29 @@ class Data:
 			c = self.addProcessUsageEvent(ps, tres)
 			if c > 0:
 				sysvals.vprint('%25s (res): %d' % (ps, c))
+	def handleEndMarker(self, time):
+		dm = self.dmesg
+		self.setEnd(time)
+		self.initDevicegroups()
+		# give suspend_prepare an end if needed
+		if 'suspend_prepare' in dm and dm['suspend_prepare']['end'] < 0:
+			dm['suspend_prepare']['end'] = time
+		# assume resume machine ends at next phase start
+		if 'resume_machine' in dm and dm['resume_machine']['end'] < 0:
+			np = self.nextPhase('resume_machine', 1)
+			if np:
+				dm['resume_machine']['end'] = dm[np]['start']
+		# if kernel resume end not found, assume its the end marker
+		if self.tKernRes == 0.0:
+			self.tKernRes = time
+		# if kernel suspend start not found, assume its the end marker
+		if self.tKernSus == 0.0:
+			self.tKernSus = time
+		# set resume complete to end at end marker
+		if 'resume_complete' in dm:
+			dm['resume_complete']['end'] = time
 	def debugPrint(self):
-		for p in self.phases:
+		for p in self.sortedPhases():
 			list = self.dmesg[p]['list']
 			for devname in list:
 				dev = list[devname]
@@ -1490,9 +1579,9 @@ class Data:
 # Description:
 #	 A container for kprobe function data we want in the dev timeline
 class DevFunction:
-	row = 0
-	count = 1
 	def __init__(self, name, args, caller, ret, start, end, u, proc, pid, color):
+		self.row = 0
+		self.count = 1
 		self.name = name
 		self.args = args
 		self.caller = caller
@@ -1546,16 +1635,15 @@ class DevFunction:
 #			 suspend_resume: phase or custom exec block data
 #			 device_pm_callback: device callback info
 class FTraceLine:
-	time = 0.0
-	length = 0.0
-	fcall = False
-	freturn = False
-	fevent = False
-	fkprobe = False
-	depth = 0
-	name = ''
-	type = ''
 	def __init__(self, t, m='', d=''):
+		self.length = 0.0
+		self.fcall = False
+		self.freturn = False
+		self.fevent = False
+		self.fkprobe = False
+		self.depth = 0
+		self.name = ''
+		self.type = ''
 		self.time = float(t)
 		if not m and not d:
 			return
@@ -1675,19 +1763,13 @@ class FTraceLine:
 #	 Each instance is tied to a single device in a single phase, and is
 #	 comprised of an ordered list of FTraceLine objects
 class FTraceCallGraph:
-	id = ''
-	start = -1.0
-	end = -1.0
-	list = []
-	invalid = False
-	depth = 0
-	pid = 0
-	name = ''
-	partial = False
 	vfname = 'missing_function_name'
-	ignore = False
-	sv = 0
 	def __init__(self, pid, sv):
+		self.id = ''
+		self.invalid = False
+		self.name = ''
+		self.partial = False
+		self.ignore = False
 		self.start = -1.0
 		self.end = -1.0
 		self.list = []
@@ -1943,7 +2025,7 @@ class FTraceCallGraph:
 						dev['ftrace'] = cg
 					found = devname
 			return found
-		for p in data.phases:
+		for p in data.sortedPhases():
 			if(data.dmesg[p]['start'] <= self.start and
 				self.start <= data.dmesg[p]['end']):
 				list = data.dmesg[p]['list']
@@ -1966,7 +2048,7 @@ class FTraceCallGraph:
 		if fs < data.start or fe > data.end:
 			return
 		phase = ''
-		for p in data.phases:
+		for p in data.sortedPhases():
 			if(data.dmesg[p]['start'] <= self.start and
 				self.start < data.dmesg[p]['end']):
 				phase = p
@@ -2008,23 +2090,20 @@ class DevItem:
 #	 A container for a device timeline which calculates
 #	 all the html properties to display it correctly
 class Timeline:
-	html = ''
-	height = 0	# total timeline height
-	scaleH = 20	# timescale (top) row height
-	rowH = 30	# device row height
-	bodyH = 0	# body height
-	rows = 0	# total timeline rows
-	rowlines = dict()
-	rowheight = dict()
 	html_tblock = '<div id="block{0}" class="tblock" style="left:{1}%;width:{2}%;"><div class="tback" style="height:{3}px"></div>\n'
 	html_device = '<div id="{0}" title="{1}" class="thread{7}" style="left:{2}%;top:{3}px;height:{4}px;width:{5}%;{8}">{6}</div>\n'
 	html_phase = '<div class="phase" style="left:{0}%;width:{1}%;top:{2}px;height:{3}px;background:{4}">{5}</div>\n'
 	html_phaselet = '<div id="{0}" class="phaselet" style="left:{1}%;width:{2}%;background:{3}"></div>\n'
 	html_legend = '<div id="p{3}" class="square" style="left:{0}%;background:{1}">&nbsp;{2}</div>\n'
 	def __init__(self, rowheight, scaleheight):
-		self.rowH = rowheight
-		self.scaleH = scaleheight
 		self.html = ''
+		self.height = 0  # total timeline height
+		self.scaleH = scaleheight # timescale (top) row height
+		self.rowH = rowheight     # device row height
+		self.bodyH = 0   # body height
+		self.rows = 0    # total timeline rows
+		self.rowlines = dict()
+		self.rowheight = dict()
 	def createHeader(self, sv, stamp):
 		if(not stamp['time']):
 			return
@@ -2251,18 +2330,18 @@ class Timeline:
 # Description:
 #	 A list of values describing the properties of these test runs
 class TestProps:
-	stamp = ''
-	sysinfo = ''
-	cmdline = ''
-	kparams = ''
-	S0i3 = False
-	fwdata = []
 	stampfmt = '# [a-z]*-(?P<m>[0-9]{2})(?P<d>[0-9]{2})(?P<y>[0-9]{2})-'+\
 				'(?P<H>[0-9]{2})(?P<M>[0-9]{2})(?P<S>[0-9]{2})'+\
 				' (?P<host>.*) (?P<mode>.*) (?P<kernel>.*)$'
+	batteryfmt = '^# battery (?P<a1>\w*) (?P<c1>\d*) (?P<a2>\w*) (?P<c2>\d*)'
+	testerrfmt = '^# enter_sleep_error (?P<e>.*)'
 	sysinfofmt = '^# sysinfo .*'
 	cmdlinefmt = '^# command \| (?P<cmd>.*)'
 	kparamsfmt = '^# kparams \| (?P<kp>.*)'
+	devpropfmt = '# Device Properties: .*'
+	tracertypefmt = '# tracer: (?P<t>.*)'
+	firmwarefmt = '# fwsuspend (?P<s>[0-9]*) fwresume (?P<r>[0-9]*)$'
+	procexecfmt = 'ps - (?P<ps>.*)$'
 	ftrace_line_fmt_fg = \
 		'^ *(?P<time>[0-9\.]*) *\| *(?P<cpu>[0-9]*)\)'+\
 		' *(?P<proc>.*)-(?P<pid>[0-9]*) *\|'+\
@@ -2271,11 +2350,17 @@ class TestProps:
 		' *(?P<proc>.*)-(?P<pid>[0-9]*) *\[(?P<cpu>[0-9]*)\] *'+\
 		'(?P<flags>.{4}) *(?P<time>[0-9\.]*): *'+\
 		'(?P<msg>.*)'
-	ftrace_line_fmt = ftrace_line_fmt_nop
-	cgformat = False
-	data = 0
-	ktemp = dict()
 	def __init__(self):
+		self.stamp = ''
+		self.sysinfo = ''
+		self.cmdline = ''
+		self.kparams = ''
+		self.testerror = []
+		self.battery = []
+		self.fwdata = []
+		self.ftrace_line_fmt = self.ftrace_line_fmt_nop
+		self.cgformat = False
+		self.data = 0
 		self.ktemp = dict()
 	def setTracerType(self, tracer):
 		if(tracer == 'function_graph'):
@@ -2286,6 +2371,7 @@ class TestProps:
 		else:
 			doError('Invalid tracer format: [%s]' % tracer)
 	def parseStamp(self, data, sv):
+		# global test data
 		m = re.match(self.stampfmt, self.stamp)
 		data.stamp = {'time': '', 'host': '', 'mode': ''}
 		dt = datetime(int(m.group('y'))+2000, int(m.group('m')),
@@ -2324,23 +2410,36 @@ class TestProps:
 				sv.kparams = m.group('kp')
 		if not sv.stamp:
 			sv.stamp = data.stamp
+		# firmware data
+		if sv.suspendmode == 'mem' and len(self.fwdata) > data.testnumber:
+			data.fwSuspend, data.fwResume = self.fwdata[data.testnumber]
+			if(data.fwSuspend > 0 or data.fwResume > 0):
+				data.fwValid = True
+		# battery data
+		if len(self.battery) > data.testnumber:
+			m = re.match(self.batteryfmt, self.battery[data.testnumber])
+			if m:
+				data.battery = m.groups()
+		# sleep mode enter errors
+		if len(self.testerror) > data.testnumber:
+			m = re.match(self.testerrfmt, self.testerror[data.testnumber])
+			if m:
+				data.enterfail = m.group('e')
 
 # Class: TestRun
 # Description:
 #	 A container for a suspend/resume test run. This is necessary as
 #	 there could be more than one, and they need to be separate.
 class TestRun:
-	ftemp = dict()
-	ttemp = dict()
-	data = 0
 	def __init__(self, dataobj):
 		self.data = dataobj
 		self.ftemp = dict()
 		self.ttemp = dict()
 
 class ProcessMonitor:
-	proclist = dict()
-	running = False
+	def __init__(self):
+		self.proclist = dict()
+		self.running = False
 	def procstat(self):
 		c = ['cat /proc/[1-9]*/stat 2>/dev/null']
 		process = Popen(c, shell=True, stdout=PIPE)
@@ -2391,8 +2490,8 @@ class ProcessMonitor:
 #	 markers, and/or kprobes required for primary parsing.
 def doesTraceLogHaveTraceEvents():
 	kpcheck = ['_cal: (', '_cpu_down()']
-	techeck = ['suspend_resume']
-	tmcheck = ['SUSPEND START', 'RESUME COMPLETE']
+	techeck = ['suspend_resume', 'device_pm_callback']
+	tmcheck = ['tracing_mark_write']
 	sysvals.usekprobes = False
 	fp = sysvals.openlog(sysvals.ftracefile, 'r')
 	for line in fp:
@@ -2414,23 +2513,14 @@ def doesTraceLogHaveTraceEvents():
 				check.remove(i)
 		tmcheck = check
 	fp.close()
-	if len(techeck) == 0:
-		sysvals.usetraceevents = True
-	else:
-		sysvals.usetraceevents = False
-	if len(tmcheck) == 0:
-		sysvals.usetracemarkers = True
-	else:
-		sysvals.usetracemarkers = False
+	sysvals.usetraceevents = True if len(techeck) < 2 else False
+	sysvals.usetracemarkers = True if len(tmcheck) == 0 else False
 
 # Function: appendIncompleteTraceLog
 # Description:
 #	 [deprecated for kernel 3.15 or newer]
-#	 Legacy support of ftrace outputs that lack the device_pm_callback
-#	 and/or suspend_resume trace events. The primary data should be
-#	 taken from dmesg, and this ftrace is used only for callgraph data
-#	 or custom actions in the timeline. The data is appended to the Data
-#	 objects provided.
+#	 Adds callgraph data which lacks trace event data. This is only
+#	 for timelines generated from 3.15 or older
 # Arguments:
 #	 testruns: the array of Data objects obtained from parseKernelLog
 def appendIncompleteTraceLog(testruns):
@@ -2460,13 +2550,19 @@ def appendIncompleteTraceLog(testruns):
 		elif re.match(tp.cmdlinefmt, line):
 			tp.cmdline = line
 			continue
+		elif re.match(tp.batteryfmt, line):
+			tp.battery.append(line)
+			continue
+		elif re.match(tp.testerrfmt, line):
+			tp.testerror.append(line)
+			continue
 		# determine the trace data type (required for further parsing)
-		m = re.match(sysvals.tracertypefmt, line)
+		m = re.match(tp.tracertypefmt, line)
 		if(m):
 			tp.setTracerType(m.group('t'))
 			continue
 		# device properties line
-		if(re.match(sysvals.devpropfmt, line)):
+		if(re.match(tp.devpropfmt, line)):
 			devProps(line)
 			continue
 		# parse only valid lines, if this is not one move on
@@ -2506,87 +2602,7 @@ def appendIncompleteTraceLog(testruns):
 			continue
 		# trace event processing
 		if(t.fevent):
-			# general trace events have two types, begin and end
-			if(re.match('(?P<name>.*) begin$', t.name)):
-				isbegin = True
-			elif(re.match('(?P<name>.*) end$', t.name)):
-				isbegin = False
-			else:
-				continue
-			m = re.match('(?P<name>.*)\[(?P<val>[0-9]*)\] .*', t.name)
-			if(m):
-				val = m.group('val')
-				if val == '0':
-					name = m.group('name')
-				else:
-					name = m.group('name')+'['+val+']'
-			else:
-				m = re.match('(?P<name>.*) .*', t.name)
-				name = m.group('name')
-			# special processing for trace events
-			if re.match('dpm_prepare\[.*', name):
-				continue
-			elif re.match('machine_suspend.*', name):
-				continue
-			elif re.match('suspend_enter\[.*', name):
-				if(not isbegin):
-					data.dmesg['suspend_prepare']['end'] = t.time
-				continue
-			elif re.match('dpm_suspend\[.*', name):
-				if(not isbegin):
-					data.dmesg['suspend']['end'] = t.time
-				continue
-			elif re.match('dpm_suspend_late\[.*', name):
-				if(isbegin):
-					data.dmesg['suspend_late']['start'] = t.time
-				else:
-					data.dmesg['suspend_late']['end'] = t.time
-				continue
-			elif re.match('dpm_suspend_noirq\[.*', name):
-				if(isbegin):
-					data.dmesg['suspend_noirq']['start'] = t.time
-				else:
-					data.dmesg['suspend_noirq']['end'] = t.time
-				continue
-			elif re.match('dpm_resume_noirq\[.*', name):
-				if(isbegin):
-					data.dmesg['resume_machine']['end'] = t.time
-					data.dmesg['resume_noirq']['start'] = t.time
-				else:
-					data.dmesg['resume_noirq']['end'] = t.time
-				continue
-			elif re.match('dpm_resume_early\[.*', name):
-				if(isbegin):
-					data.dmesg['resume_early']['start'] = t.time
-				else:
-					data.dmesg['resume_early']['end'] = t.time
-				continue
-			elif re.match('dpm_resume\[.*', name):
-				if(isbegin):
-					data.dmesg['resume']['start'] = t.time
-				else:
-					data.dmesg['resume']['end'] = t.time
-				continue
-			elif re.match('dpm_complete\[.*', name):
-				if(isbegin):
-					data.dmesg['resume_complete']['start'] = t.time
-				else:
-					data.dmesg['resume_complete']['end'] = t.time
-				continue
-			# skip trace events inside devices calls
-			if(not data.isTraceEventOutsideDeviceCalls(pid, t.time)):
-				continue
-			# global events (outside device calls) are simply graphed
-			if(isbegin):
-				# store each trace event in ttemp
-				if(name not in testrun[testidx].ttemp):
-					testrun[testidx].ttemp[name] = []
-				testrun[testidx].ttemp[name].append(\
-					{'begin': t.time, 'end': t.time})
-			else:
-				# finish off matching trace event in ttemp
-				if(name in testrun[testidx].ttemp):
-					testrun[testidx].ttemp[name][-1]['end'] = t.time
+			continue
 		# call/return processing
 		elif sysvals.usecallgraph:
 			# create a callgraph object for the data
@@ -2603,12 +2619,6 @@ def appendIncompleteTraceLog(testruns):
 	tf.close()
 
 	for test in testrun:
-		# add the traceevent data to the device hierarchy
-		if(sysvals.usetraceevents):
-			for name in test.ttemp:
-				for event in test.ttemp[name]:
-					test.data.newActionGlobal(name, event['begin'], event['end'])
-
 		# add the callgraph data to the device hierarchy
 		for pid in test.ftemp:
 			for cg in test.ftemp[pid]:
@@ -2621,7 +2631,7 @@ def appendIncompleteTraceLog(testruns):
 					continue
 				callstart = cg.start
 				callend = cg.end
-				for p in test.data.phases:
+				for p in test.data.sortedPhases():
 					if(test.data.dmesg[p]['start'] <= callstart and
 						callstart <= test.data.dmesg[p]['end']):
 						list = test.data.dmesg[p]['list']
@@ -2648,10 +2658,12 @@ def parseTraceLog(live=False):
 		doError('%s does not exist' % sysvals.ftracefile)
 	if not live:
 		sysvals.setupAllKprobes()
+	krescalls = ['pm_notifier_call_chain', 'pm_restore_console']
 	tracewatch = []
 	if sysvals.usekprobes:
 		tracewatch += ['sync_filesystems', 'freeze_processes', 'syscore_suspend',
-			'syscore_resume', 'resume_console', 'thaw_processes', 'CPU_ON', 'CPU_OFF']
+			'syscore_resume', 'resume_console', 'thaw_processes', 'CPU_ON',
+			'CPU_OFF', 'timekeeping_freeze', 'acpi_suspend']
 
 	# extract the callgraph and traceevent data
 	tp = TestProps()
@@ -2674,18 +2686,24 @@ def parseTraceLog(live=False):
 		elif re.match(tp.cmdlinefmt, line):
 			tp.cmdline = line
 			continue
+		elif re.match(tp.batteryfmt, line):
+			tp.battery.append(line)
+			continue
+		elif re.match(tp.testerrfmt, line):
+			tp.testerror.append(line)
+			continue
 		# firmware line: pull out any firmware data
-		m = re.match(sysvals.firmwarefmt, line)
+		m = re.match(tp.firmwarefmt, line)
 		if(m):
 			tp.fwdata.append((int(m.group('s')), int(m.group('r'))))
 			continue
 		# tracer type line: determine the trace data type
-		m = re.match(sysvals.tracertypefmt, line)
+		m = re.match(tp.tracertypefmt, line)
 		if(m):
 			tp.setTracerType(m.group('t'))
 			continue
 		# device properties line
-		if(re.match(sysvals.devpropfmt, line)):
+		if(re.match(tp.devpropfmt, line)):
 			devProps(line)
 			continue
 		# ignore all other commented lines
@@ -2714,20 +2732,19 @@ def parseTraceLog(live=False):
 			continue
 		# find the start of suspend
 		if(t.startMarker()):
-			phase = 'suspend_prepare'
 			data = Data(len(testdata))
 			testdata.append(data)
 			testrun = TestRun(data)
 			testruns.append(testrun)
 			tp.parseStamp(data, sysvals)
 			data.setStart(t.time)
-			data.tKernSus = t.time
+			phase = data.setPhase('suspend_prepare', t.time, True)
 			continue
 		if(not data):
 			continue
 		# process cpu exec line
 		if t.type == 'tracing_mark_write':
-			m = re.match(sysvals.procexecfmt, t.name)
+			m = re.match(tp.procexecfmt, t.name)
 			if(m):
 				proclist = dict()
 				for ps in m.group('ps').split(','):
@@ -2740,28 +2757,17 @@ def parseTraceLog(live=False):
 				continue
 		# find the end of resume
 		if(t.endMarker()):
-			data.setEnd(t.time)
-			if data.tKernRes == 0.0:
-				data.tKernRes = t.time
-			if data.dmesg['resume_complete']['end'] < 0:
-				data.dmesg['resume_complete']['end'] = t.time
-			if sysvals.suspendmode == 'mem' and len(tp.fwdata) > data.testnumber:
-				data.fwSuspend, data.fwResume = tp.fwdata[data.testnumber]
-				if(data.tSuspended != 0 and data.tResumed != 0 and \
-					(data.fwSuspend > 0 or data.fwResume > 0)):
-					data.fwValid = True
+			data.handleEndMarker(t.time)
 			if(not sysvals.usetracemarkers):
 				# no trace markers? then quit and be sure to finish recording
 				# the event we used to trigger resume end
-				if(len(testrun.ttemp['thaw_processes']) > 0):
+				if('thaw_processes' in testrun.ttemp and len(testrun.ttemp['thaw_processes']) > 0):
 					# if an entry exists, assume this is its end
 					testrun.ttemp['thaw_processes'][-1]['end'] = t.time
 				break
 			continue
 		# trace event processing
 		if(t.fevent):
-			if(phase == 'post_resume'):
-				data.setEnd(t.time)
 			if(t.type == 'suspend_resume'):
 				# suspend_resume trace events have two types, begin and end
 				if(re.match('(?P<name>.*) begin$', t.name)):
@@ -2786,86 +2792,61 @@ def parseTraceLog(live=False):
 				# -- phase changes --
 				# start of kernel suspend
 				if(re.match('suspend_enter\[.*', t.name)):
-					if(isbegin and data.start == data.tKernSus):
-						data.dmesg[phase]['start'] = t.time
+					if(isbegin):
 						data.tKernSus = t.time
 					continue
 				# suspend_prepare start
 				elif(re.match('dpm_prepare\[.*', t.name)):
 					phase = 'suspend_prepare'
-					if(not isbegin):
-						data.dmesg[phase]['end'] = t.time
-						if data.dmesg[phase]['start'] < 0:
-							data.dmesg[phase]['start'] = data.start
+					if not isbegin:
+						data.setPhase(phase, t.time, isbegin)
+					if isbegin and data.tKernSus == 0:
+						data.tKernSus = t.time
 					continue
 				# suspend start
 				elif(re.match('dpm_suspend\[.*', t.name)):
-					phase = 'suspend'
-					data.setPhase(phase, t.time, isbegin)
+					phase = data.setPhase('suspend', t.time, isbegin)
 					continue
 				# suspend_late start
 				elif(re.match('dpm_suspend_late\[.*', t.name)):
-					phase = 'suspend_late'
-					data.setPhase(phase, t.time, isbegin)
+					phase = data.setPhase('suspend_late', t.time, isbegin)
 					continue
 				# suspend_noirq start
 				elif(re.match('dpm_suspend_noirq\[.*', t.name)):
-					if data.phaseCollision('suspend_noirq', isbegin, line):
-						continue
-					phase = 'suspend_noirq'
-					data.setPhase(phase, t.time, isbegin)
-					if(not isbegin):
-						phase = 'suspend_machine'
-						data.dmesg[phase]['start'] = t.time
+					phase = data.setPhase('suspend_noirq', t.time, isbegin)
 					continue
 				# suspend_machine/resume_machine
 				elif(re.match('machine_suspend\[.*', t.name)):
 					if(isbegin):
-						phase = 'suspend_machine'
-						data.dmesg[phase]['end'] = t.time
-						data.tSuspended = t.time
-					else:
-						if(sysvals.suspendmode in ['mem', 'disk'] and not tp.S0i3):
-							data.dmesg['suspend_machine']['end'] = t.time
+						lp = data.lastPhase()
+						phase = data.setPhase('suspend_machine', data.dmesg[lp]['end'], True)
+						data.setPhase(phase, t.time, False)
+						if data.tSuspended == 0:
 							data.tSuspended = t.time
-						phase = 'resume_machine'
-						data.dmesg[phase]['start'] = t.time
-						data.tResumed = t.time
-						data.tLow = data.tResumed - data.tSuspended
-					continue
-				# acpi_suspend
-				elif(re.match('acpi_suspend\[.*', t.name)):
-					# acpi_suspend[0] S0i3
-					if(re.match('acpi_suspend\[0\] begin', t.name)):
-						if(sysvals.suspendmode == 'mem'):
-							tp.S0i3 = True
-							data.dmesg['suspend_machine']['end'] = t.time
+					else:
+						phase = data.setPhase('resume_machine', t.time, True)
+						if(sysvals.suspendmode in ['mem', 'disk']):
+							if 'suspend_machine' in data.dmesg:
+								data.dmesg['suspend_machine']['end'] = t.time
 							data.tSuspended = t.time
+						if data.tResumed == 0:
+							data.tResumed = t.time
 					continue
 				# resume_noirq start
 				elif(re.match('dpm_resume_noirq\[.*', t.name)):
-					if data.phaseCollision('resume_noirq', isbegin, line):
-						continue
-					phase = 'resume_noirq'
-					data.setPhase(phase, t.time, isbegin)
-					if(isbegin):
-						data.dmesg['resume_machine']['end'] = t.time
+					phase = data.setPhase('resume_noirq', t.time, isbegin)
 					continue
 				# resume_early start
 				elif(re.match('dpm_resume_early\[.*', t.name)):
-					phase = 'resume_early'
-					data.setPhase(phase, t.time, isbegin)
+					phase = data.setPhase('resume_early', t.time, isbegin)
 					continue
 				# resume start
 				elif(re.match('dpm_resume\[.*', t.name)):
-					phase = 'resume'
-					data.setPhase(phase, t.time, isbegin)
+					phase = data.setPhase('resume', t.time, isbegin)
 					continue
 				# resume complete start
 				elif(re.match('dpm_complete\[.*', t.name)):
-					phase = 'resume_complete'
-					if(isbegin):
-						data.dmesg[phase]['start'] = t.time
+					phase = data.setPhase('resume_complete', t.time, isbegin)
 					continue
 				# skip trace events inside devices calls
 				if(not data.isTraceEventOutsideDeviceCalls(pid, t.time)):
@@ -2881,13 +2862,10 @@ def parseTraceLog(live=False):
 					if(len(testrun.ttemp[name]) > 0):
 						# if an entry exists, assume this is its end
 						testrun.ttemp[name][-1]['end'] = t.time
-					elif(phase == 'post_resume'):
-						# post resume events can just have ends
-						testrun.ttemp[name].append({
-							'begin': data.dmesg[phase]['start'],
-							'end': t.time})
 			# device callback start
 			elif(t.type == 'device_pm_callback_start'):
+				if phase not in data.dmesg:
+					continue
 				m = re.match('(?P<drv>.*) (?P<d>.*), parent: *(?P<p>.*), .*',\
 					t.name);
 				if(not m):
@@ -2901,6 +2879,8 @@ def parseTraceLog(live=False):
 						data.devpids.append(pid)
 			# device callback finish
 			elif(t.type == 'device_pm_callback_end'):
+				if phase not in data.dmesg:
+					continue
 				m = re.match('(?P<drv>.*) (?P<d>.*), err.*', t.name);
 				if(not m):
 					continue
@@ -2941,9 +2921,9 @@ def parseTraceLog(live=False):
 					e['end'] = t.time
 					e['rdata'] = kprobedata
 				# end of kernel resume
-				if(kprobename == 'pm_notifier_call_chain' or \
-					kprobename == 'pm_restore_console'):
-					data.dmesg[phase]['end'] = t.time
+				if(phase != 'suspend_prepare' and kprobename in krescalls):
+					if phase in data.dmesg:
+						data.dmesg[phase]['end'] = t.time
 					data.tKernRes = t.time
 
 		# callgraph processing
@@ -2961,10 +2941,13 @@ def parseTraceLog(live=False):
 			if(res == -1):
 				testrun.ftemp[key][-1].addLine(t)
 	tf.close()
+	if data and not data.devicegroups:
+		sysvals.vprint('WARNING: end marker is missing')
+		data.handleEndMarker(t.time)
 
 	if sysvals.suspendmode == 'command':
 		for test in testruns:
-			for p in test.data.phases:
+			for p in test.data.sortedPhases():
 				if p == 'suspend_prepare':
 					test.data.dmesg[p]['start'] = test.data.start
 					test.data.dmesg[p]['end'] = test.data.end
@@ -2973,7 +2956,6 @@ def parseTraceLog(live=False):
 					test.data.dmesg[p]['end'] = test.data.end
 			test.data.tSuspended = test.data.end
 			test.data.tResumed = test.data.end
-			test.data.tLow = 0
 			test.data.fwValid = False
 
 	# dev source and procmon events can be unreadable with mixed phase height
@@ -3040,8 +3022,8 @@ def parseTraceLog(live=False):
 						sortkey = '%f%f%d' % (cg.start, cg.end, pid)
 						sortlist[sortkey] = cg
 					elif len(cg.list) > 1000000:
-						print 'WARNING: the callgraph for %s is massive (%d lines)' %\
-							(devname, len(cg.list))
+						sysvals.vprint('WARNING: the callgraph for %s is massive (%d lines)' %\
+							(devname, len(cg.list)))
 			# create blocks for orphan cg data
 			for sortkey in sorted(sortlist):
 				cg = sortlist[sortkey]
@@ -3057,25 +3039,34 @@ def parseTraceLog(live=False):
 	for data in testdata:
 		tn = '' if len(testdata) == 1 else ('%d' % (data.testnumber + 1))
 		terr = ''
-		lp = data.phases[0]
-		for p in data.phases:
-			if(data.dmesg[p]['start'] < 0 and data.dmesg[p]['end'] < 0):
+		phasedef = data.phasedef
+		lp = 'suspend_prepare'
+		for p in sorted(phasedef, key=lambda k:phasedef[k]['order']):
+			if p not in data.dmesg:
 				if not terr:
 					print 'TEST%s FAILED: %s failed in %s phase' % (tn, sysvals.suspendmode, lp)
 					terr = '%s%s failed in %s phase' % (sysvals.suspendmode, tn, lp)
 					error.append(terr)
+					if data.tSuspended == 0:
+						data.tSuspended = data.dmesg[lp]['end']
+					if data.tResumed == 0:
+						data.tResumed = data.dmesg[lp]['end']
+					data.fwValid = False
 				sysvals.vprint('WARNING: phase "%s" is missing!' % p)
-			if(data.dmesg[p]['start'] < 0):
-				data.dmesg[p]['start'] = data.dmesg[lp]['end']
-				if(p == 'resume_machine'):
-					data.tSuspended = data.dmesg[lp]['end']
-					data.tResumed = data.dmesg[lp]['end']
-					data.tLow = 0
-			if(data.dmesg[p]['end'] < 0):
-				data.dmesg[p]['end'] = data.dmesg[p]['start']
+			lp = p
+		if not terr and data.enterfail:
+			print 'test%s FAILED: enter %s failed with %s' % (tn, sysvals.suspendmode, data.enterfail)
+			terr = 'test%s failed to enter %s mode' % (tn, sysvals.suspendmode)
+			error.append(terr)
+		lp = data.sortedPhases()[0]
+		for p in data.sortedPhases():
 			if(p != lp and not ('machine' in p and 'machine' in lp)):
 				data.dmesg[lp]['end'] = data.dmesg[p]['start']
 			lp = p
+		if data.tSuspended == 0:
+			data.tSuspended = data.tKernRes
+		if data.tResumed == 0:
+			data.tResumed = data.tSuspended
 
 		if(len(sysvals.devicefilter) > 0):
 			data.deviceFilter(sysvals.devicefilter)
@@ -3127,7 +3118,13 @@ def loadKernelLog():
 		elif re.match(tp.cmdlinefmt, line):
 			tp.cmdline = line
 			continue
-		m = re.match(sysvals.firmwarefmt, line)
+		elif re.match(tp.batteryfmt, line):
+			tp.battery.append(line)
+			continue
+		elif re.match(tp.testerrfmt, line):
+			tp.testerror.append(line)
+			continue
+		m = re.match(tp.firmwarefmt, line)
 		if(m):
 			tp.fwdata.append((int(m.group('s')), int(m.group('r'))))
 			continue
@@ -3140,10 +3137,6 @@ def loadKernelLog():
 				testruns.append(data)
 			data = Data(len(testruns))
 			tp.parseStamp(data, sysvals)
-			if len(tp.fwdata) > data.testnumber:
-				data.fwSuspend, data.fwResume = tp.fwdata[data.testnumber]
-				if(data.fwSuspend > 0 or data.fwResume > 0):
-					data.fwValid = True
 		if(not data):
 			continue
 		m = re.match('.* *(?P<k>[0-9]\.[0-9]{2}\.[0-9]-.*) .*', msg)
@@ -3199,30 +3192,30 @@ def parseKernelLog(data):
 
 	# dmesg phase match table
 	dm = {
-		'suspend_prepare': 'PM: Syncing filesystems.*',
-		        'suspend': 'PM: Entering [a-z]* sleep.*',
-		   'suspend_late': 'PM: suspend of devices complete after.*',
-		  'suspend_noirq': 'PM: late suspend of devices complete after.*',
-		'suspend_machine': 'PM: noirq suspend of devices complete after.*',
-		 'resume_machine': 'ACPI: Low-level resume complete.*',
-		   'resume_noirq': 'ACPI: Waking up from system sleep state.*',
-		   'resume_early': 'PM: noirq resume of devices complete after.*',
-		         'resume': 'PM: early resume of devices complete after.*',
-		'resume_complete': 'PM: resume of devices complete after.*',
-		    'post_resume': '.*Restarting tasks \.\.\..*',
+		'suspend_prepare': ['PM: Syncing filesystems.*'],
+		        'suspend': ['PM: Entering [a-z]* sleep.*', 'Suspending console.*'],
+		   'suspend_late': ['PM: suspend of devices complete after.*'],
+		  'suspend_noirq': ['PM: late suspend of devices complete after.*'],
+		'suspend_machine': ['PM: noirq suspend of devices complete after.*'],
+		 'resume_machine': ['ACPI: Low-level resume complete.*'],
+		   'resume_noirq': ['ACPI: Waking up from system sleep state.*'],
+		   'resume_early': ['PM: noirq resume of devices complete after.*'],
+		         'resume': ['PM: early resume of devices complete after.*'],
+		'resume_complete': ['PM: resume of devices complete after.*'],
+		    'post_resume': ['.*Restarting tasks \.\.\..*'],
 	}
 	if(sysvals.suspendmode == 'standby'):
-		dm['resume_machine'] = 'PM: Restoring platform NVS memory'
+		dm['resume_machine'] = ['PM: Restoring platform NVS memory']
 	elif(sysvals.suspendmode == 'disk'):
-		dm['suspend_late'] = 'PM: freeze of devices complete after.*'
-		dm['suspend_noirq'] = 'PM: late freeze of devices complete after.*'
-		dm['suspend_machine'] = 'PM: noirq freeze of devices complete after.*'
-		dm['resume_machine'] = 'PM: Restoring platform NVS memory'
-		dm['resume_early'] = 'PM: noirq restore of devices complete after.*'
-		dm['resume'] = 'PM: early restore of devices complete after.*'
-		dm['resume_complete'] = 'PM: restore of devices complete after.*'
+		dm['suspend_late'] = ['PM: freeze of devices complete after.*']
+		dm['suspend_noirq'] = ['PM: late freeze of devices complete after.*']
+		dm['suspend_machine'] = ['PM: noirq freeze of devices complete after.*']
+		dm['resume_machine'] = ['PM: Restoring platform NVS memory']
+		dm['resume_early'] = ['PM: noirq restore of devices complete after.*']
+		dm['resume'] = ['PM: early restore of devices complete after.*']
+		dm['resume_complete'] = ['PM: restore of devices complete after.*']
 	elif(sysvals.suspendmode == 'freeze'):
-		dm['resume_machine'] = 'ACPI: resume from mwait'
+		dm['resume_machine'] = ['ACPI: resume from mwait']
 
 	# action table (expected events that occur and show up in dmesg)
 	at = {
@@ -3264,81 +3257,89 @@ def parseKernelLog(data):
 		else:
 			continue
 
+		# check for a phase change line
+		phasechange = False
+		for p in dm:
+			for s in dm[p]:
+				if(re.match(s, msg)):
+					phasechange, phase = True, p
+					break
+
 		# hack for determining resume_machine end for freeze
 		if(not sysvals.usetraceevents and sysvals.suspendmode == 'freeze' \
 			and phase == 'resume_machine' and \
 			re.match('calling  (?P<f>.*)\+ @ .*, parent: .*', msg)):
-			data.dmesg['resume_machine']['end'] = ktime
+			data.setPhase(phase, ktime, False)
 			phase = 'resume_noirq'
-			data.dmesg[phase]['start'] = ktime
-
-		# suspend start
-		if(re.match(dm['suspend_prepare'], msg)):
-			phase = 'suspend_prepare'
-			data.dmesg[phase]['start'] = ktime
-			data.setStart(ktime)
-			data.tKernSus = ktime
-		# suspend start
-		elif(re.match(dm['suspend'], msg)):
-			data.dmesg['suspend_prepare']['end'] = ktime
-			phase = 'suspend'
-			data.dmesg[phase]['start'] = ktime
-		# suspend_late start
-		elif(re.match(dm['suspend_late'], msg)):
-			data.dmesg['suspend']['end'] = ktime
-			phase = 'suspend_late'
-			data.dmesg[phase]['start'] = ktime
-		# suspend_noirq start
-		elif(re.match(dm['suspend_noirq'], msg)):
-			data.dmesg['suspend_late']['end'] = ktime
-			phase = 'suspend_noirq'
-			data.dmesg[phase]['start'] = ktime
-		# suspend_machine start
-		elif(re.match(dm['suspend_machine'], msg)):
-			data.dmesg['suspend_noirq']['end'] = ktime
-			phase = 'suspend_machine'
-			data.dmesg[phase]['start'] = ktime
-		# resume_machine start
-		elif(re.match(dm['resume_machine'], msg)):
-			if(sysvals.suspendmode in ['freeze', 'standby']):
-				data.tSuspended = prevktime
-				data.dmesg['suspend_machine']['end'] = prevktime
-			else:
-				data.tSuspended = ktime
-				data.dmesg['suspend_machine']['end'] = ktime
-			phase = 'resume_machine'
-			data.tResumed = ktime
-			data.tLow = data.tResumed - data.tSuspended
-			data.dmesg[phase]['start'] = ktime
-		# resume_noirq start
-		elif(re.match(dm['resume_noirq'], msg)):
-			data.dmesg['resume_machine']['end'] = ktime
-			phase = 'resume_noirq'
-			data.dmesg[phase]['start'] = ktime
-		# resume_early start
-		elif(re.match(dm['resume_early'], msg)):
-			data.dmesg['resume_noirq']['end'] = ktime
-			phase = 'resume_early'
-			data.dmesg[phase]['start'] = ktime
-		# resume start
-		elif(re.match(dm['resume'], msg)):
-			data.dmesg['resume_early']['end'] = ktime
-			phase = 'resume'
-			data.dmesg[phase]['start'] = ktime
-		# resume complete start
-		elif(re.match(dm['resume_complete'], msg)):
-			data.dmesg['resume']['end'] = ktime
-			phase = 'resume_complete'
-			data.dmesg[phase]['start'] = ktime
-		# post resume start
-		elif(re.match(dm['post_resume'], msg)):
-			data.dmesg['resume_complete']['end'] = ktime
-			data.setEnd(ktime)
-			data.tKernRes = ktime
-			break
+			data.setPhase(phase, ktime, True)
+
+		if phasechange:
+			if phase == 'suspend_prepare':
+				data.setPhase(phase, ktime, True)
+				data.setStart(ktime)
+				data.tKernSus = ktime
+			elif phase == 'suspend':
+				lp = data.lastPhase()
+				if lp:
+					data.setPhase(lp, ktime, False)
+				data.setPhase(phase, ktime, True)
+			elif phase == 'suspend_late':
+				lp = data.lastPhase()
+				if lp:
+					data.setPhase(lp, ktime, False)
+				data.setPhase(phase, ktime, True)
+			elif phase == 'suspend_noirq':
+				lp = data.lastPhase()
+				if lp:
+					data.setPhase(lp, ktime, False)
+				data.setPhase(phase, ktime, True)
+			elif phase == 'suspend_machine':
+				lp = data.lastPhase()
+				if lp:
+					data.setPhase(lp, ktime, False)
+				data.setPhase(phase, ktime, True)
+			elif phase == 'resume_machine':
+				lp = data.lastPhase()
+				if(sysvals.suspendmode in ['freeze', 'standby']):
+					data.tSuspended = prevktime
+					if lp:
+						data.setPhase(lp, prevktime, False)
+				else:
+					data.tSuspended = ktime
+					if lp:
+						data.setPhase(lp, prevktime, False)
+				data.tResumed = ktime
+				data.setPhase(phase, ktime, True)
+			elif phase == 'resume_noirq':
+				lp = data.lastPhase()
+				if lp:
+					data.setPhase(lp, ktime, False)
+				data.setPhase(phase, ktime, True)
+			elif phase == 'resume_early':
+				lp = data.lastPhase()
+				if lp:
+					data.setPhase(lp, ktime, False)
+				data.setPhase(phase, ktime, True)
+			elif phase == 'resume':
+				lp = data.lastPhase()
+				if lp:
+					data.setPhase(lp, ktime, False)
+				data.setPhase(phase, ktime, True)
+			elif phase == 'resume_complete':
+				lp = data.lastPhase()
+				if lp:
+					data.setPhase(lp, ktime, False)
+				data.setPhase(phase, ktime, True)
+			elif phase == 'post_resume':
+				lp = data.lastPhase()
+				if lp:
+					data.setPhase(lp, ktime, False)
+				data.setEnd(ktime)
+				data.tKernRes = ktime
+				break
 
 		# -- device callbacks --
-		if(phase in data.phases):
+		if(phase in data.sortedPhases()):
 			# device init call
 			if(re.match('calling  (?P<f>.*)\+ @ .*, parent: .*', msg)):
 				sm = re.match('calling  (?P<f>.*)\+ @ '+\
@@ -3396,24 +3397,31 @@ def parseKernelLog(data):
 				actions[cpu].append({'begin': cpu_start, 'end': ktime})
 				cpu_start = ktime
 		prevktime = ktime
+	data.initDevicegroups()
 
 	# fill in any missing phases
-	lp = data.phases[0]
-	for p in data.phases:
-		if(data.dmesg[p]['start'] < 0 and data.dmesg[p]['end'] < 0):
-			print('WARNING: phase "%s" is missing, something went wrong!' % p)
-			print('    In %s, this dmesg line denotes the start of %s:' % \
-				(sysvals.suspendmode, p))
-			print('        "%s"' % dm[p])
-		if(data.dmesg[p]['start'] < 0):
-			data.dmesg[p]['start'] = data.dmesg[lp]['end']
-			if(p == 'resume_machine'):
-				data.tSuspended = data.dmesg[lp]['end']
-				data.tResumed = data.dmesg[lp]['end']
-				data.tLow = 0
-		if(data.dmesg[p]['end'] < 0):
-			data.dmesg[p]['end'] = data.dmesg[p]['start']
+	phasedef = data.phasedef
+	terr, lp = '', 'suspend_prepare'
+	for p in sorted(phasedef, key=lambda k:phasedef[k]['order']):
+		if p not in data.dmesg:
+			if not terr:
+				print 'TEST FAILED: %s failed in %s phase' % (sysvals.suspendmode, lp)
+				terr = '%s failed in %s phase' % (sysvals.suspendmode, lp)
+				if data.tSuspended == 0:
+					data.tSuspended = data.dmesg[lp]['end']
+				if data.tResumed == 0:
+					data.tResumed = data.dmesg[lp]['end']
+			sysvals.vprint('WARNING: phase "%s" is missing!' % p)
+		lp = p
+	lp = data.sortedPhases()[0]
+	for p in data.sortedPhases():
+		if(p != lp and not ('machine' in p and 'machine' in lp)):
+			data.dmesg[lp]['end'] = data.dmesg[p]['start']
 		lp = p
+	if data.tSuspended == 0:
+		data.tSuspended = data.tKernRes
+	if data.tResumed == 0:
+		data.tResumed = data.tSuspended
 
 	# fill in any actions we've found
 	for name in actions:
@@ -3462,7 +3470,7 @@ def addCallgraphs(sv, hf, data):
 	hf.write('<section id="callgraphs" class="callgraph">\n')
 	# write out the ftrace data converted to html
 	num = 0
-	for p in data.phases:
+	for p in data.sortedPhases():
 		if sv.cgphase and p != sv.cgphase:
 			continue
 		list = data.dmesg[p]['list']
@@ -3505,7 +3513,7 @@ def createHTMLSummarySimple(testruns, htmlfile, folder):
 		table {width:100%;border-collapse: collapse;}\n\
 		.summary {border:1px solid;}\n\
 		th {border: 1px solid black;background:#222;color:white;}\n\
-		td {font: 16px "Times New Roman";text-align: center;}\n\
+		td {font: 14px "Times New Roman";text-align: center;}\n\
 		tr.head td {border: 1px solid black;background:#aaa;}\n\
 		tr.alt {background-color:#ddd;}\n\
 		tr.notice {color:red;}\n\
@@ -3521,7 +3529,7 @@ def createHTMLSummarySimple(testruns, htmlfile, folder):
 	iMin, iMed, iMax = [0, 0], [0, 0], [0, 0]
 	num = 0
 	lastmode = ''
-	cnt = {'pass':0, 'fail':0, 'hang':0}
+	cnt = dict()
 	for data in sorted(testruns, key=lambda v:(v['mode'], v['host'], v['kernel'], v['time'])):
 		mode = data['mode']
 		if mode not in list:
@@ -3541,10 +3549,14 @@ def createHTMLSummarySimple(testruns, htmlfile, folder):
 		tVal = [float(data['suspend']), float(data['resume'])]
 		list[mode]['data'].append([data['host'], data['kernel'],
 			data['time'], tVal[0], tVal[1], data['url'], data['result'],
-			data['issues']])
+			data['issues'], data['sus_worst'], data['sus_worsttime'],
+			data['res_worst'], data['res_worsttime']])
 		idx = len(list[mode]['data']) - 1
+		if data['result'] not in cnt:
+			cnt[data['result']] = 1
+		else:
+			cnt[data['result']] += 1
 		if data['result'] == 'pass':
-			cnt['pass'] += 1
 			for i in range(2):
 				tMed[i].append(tVal[i])
 				tAvg[i] += tVal[i]
@@ -3555,10 +3567,6 @@ def createHTMLSummarySimple(testruns, htmlfile, folder):
 					iMax[i] = idx
 					tMax[i] = tVal[i]
 			num += 1
-		elif data['result'] == 'hang':
-			cnt['hang'] += 1
-		elif data['result'] == 'fail':
-			cnt['fail'] += 1
 		lastmode = mode
 	if lastmode and num > 0:
 		for i in range(2):
@@ -3585,11 +3593,14 @@ def createHTMLSummarySimple(testruns, htmlfile, folder):
 	html += '<table class="summary">\n<tr>\n' + th.format('#') +\
 		th.format('Mode') + th.format('Host') + th.format('Kernel') +\
 		th.format('Test Time') + th.format('Result') + th.format('Issues') +\
-		th.format('Suspend') + th.format('Resume') + th.format('Detail') + '</tr>\n'
+		th.format('Suspend') + th.format('Resume') +\
+		th.format('Worst Suspend Device') + th.format('SD Time') +\
+		th.format('Worst Resume Device') + th.format('RD Time') +\
+		th.format('Detail') + '</tr>\n'
 
 	# export list into html
 	head = '<tr class="head"><td>{0}</td><td>{1}</td>'+\
-		'<td colspan=8 class="sus">Suspend Avg={2} '+\
+		'<td colspan=12 class="sus">Suspend Avg={2} '+\
 		'<span class=minval><a href="#s{10}min">Min={3}</a></span> '+\
 		'<span class=medval><a href="#s{10}med">Med={4}</a></span> '+\
 		'<span class=maxval><a href="#s{10}max">Max={5}</a></span> '+\
@@ -3598,7 +3609,7 @@ def createHTMLSummarySimple(testruns, htmlfile, folder):
 		'<span class=medval><a href="#r{10}med">Med={8}</a></span> '+\
 		'<span class=maxval><a href="#r{10}max">Max={9}</a></span></td>'+\
 		'</tr>\n'
-	headnone = '<tr class="head"><td>{0}</td><td>{1}</td><td colspan=8></td></tr>\n'
+	headnone = '<tr class="head"><td>{0}</td><td>{1}</td><td colspan=12></td></tr>\n'
 	for mode in list:
 		# header line for each suspend mode
 		num = 0
@@ -3641,6 +3652,10 @@ def createHTMLSummarySimple(testruns, htmlfile, folder):
 			html += td.format(d[7])										# issues
 			html += tdh.format('%.3f ms' % d[3], tHigh[0]) if d[3] else td.format('')	# suspend
 			html += tdh.format('%.3f ms' % d[4], tHigh[1]) if d[4] else td.format('')	# resume
+			html += td.format(d[8])										# sus_worst
+			html += td.format('%.3f ms' % d[9])	if d[9] else td.format('')		# sus_worst time
+			html += td.format(d[10])									# res_worst
+			html += td.format('%.3f ms' % d[11]) if d[11] else td.format('')	# res_worst time
 			html += tdlink.format(d[5]) if d[5] else td.format('')		# url
 			html += '</tr>\n'
 			num += 1
@@ -3677,7 +3692,8 @@ def createHTML(testruns, testfail):
 	for data in testruns:
 		if data.kerror:
 			kerror = True
-		data.normalizeTime(testruns[-1].tSuspended)
+		if(sysvals.suspendmode in ['freeze', 'standby']):
+			data.trimFreezeTime(testruns[-1].tSuspended)
 
 	# html function templates
 	html_error = '<div id="{1}" title="kernel error/warning" class="err" style="right:{0}%">{2}&rarr;</div>\n'
@@ -3721,8 +3737,8 @@ def createHTML(testruns, testfail):
 		sktime, rktime = data.getTimeValues()
 		if(tTotal == 0):
 			doError('No timeline data')
-		if(data.tLow > 0):
-			low_time = '%.0f'%(data.tLow*1000)
+		if(len(data.tLow) > 0):
+			low_time = '|'.join(data.tLow)
 		if sysvals.suspendmode == 'command':
 			run_time = '%.0f'%((data.end-data.start)*1000)
 			if sysvals.testcommand:
@@ -3743,7 +3759,7 @@ def createHTML(testruns, testfail):
 			if(len(testruns) > 1):
 				testdesc1 = testdesc2 = ordinal(data.testnumber+1)
 				testdesc2 += ' '
-			if(data.tLow == 0):
+			if(len(data.tLow) == 0):
 				thtml = html_timetotal.format(suspend_time, \
 					resume_time, testdesc1, stitle, rtitle)
 			else:
@@ -3762,7 +3778,7 @@ def createHTML(testruns, testfail):
 			rtitle = 'time from firmware mode to return from kernel enter_state(%s) [kernel time only]' % sysvals.suspendmode
 			if(len(testruns) > 1):
 				testdesc = ordinal(data.testnumber+1)+' '+testdesc
-			if(data.tLow == 0):
+			if(len(data.tLow) == 0):
 				thtml = html_timetotal.format(suspend_time, \
 					resume_time, testdesc, stitle, rtitle)
 			else:
@@ -3820,15 +3836,14 @@ def createHTML(testruns, testfail):
 
 	# draw the full timeline
 	devtl.createZoomBox(sysvals.suspendmode, len(testruns))
-	phases = {'suspend':[],'resume':[]}
-	for phase in data.dmesg:
-		if 'resume' in phase:
-			phases['resume'].append(phase)
-		else:
-			phases['suspend'].append(phase)
-
-	# draw each test run chronologically
 	for data in testruns:
+		# draw each test run and block chronologically
+		phases = {'suspend':[],'resume':[]}
+		for phase in data.sortedPhases():
+			if data.dmesg[phase]['start'] >= data.tSuspended:
+				phases['resume'].append(phase)
+			else:
+				phases['suspend'].append(phase)
 		# now draw the actual timeline blocks
 		for dir in phases:
 			# draw suspend and resume blocks separately
@@ -3850,7 +3865,7 @@ def createHTML(testruns, testfail):
 				continue
 			width = '%f' % (((mTotal*100.0)-sysvals.srgap/2)/tTotal)
 			devtl.html += devtl.html_tblock.format(bname, left, width, devtl.scaleH)
-			for b in sorted(phases[dir]):
+			for b in phases[dir]:
 				# draw the phase color background
 				phase = data.dmesg[b]
 				length = phase['end']-phase['start']
@@ -3865,7 +3880,7 @@ def createHTML(testruns, testfail):
 				id = '%d_%d' % (idx1, idx2)
 				right = '%f' % (((mMax-t)*100.0)/mTotal)
 				devtl.html += html_error.format(right, id, type)
-			for b in sorted(phases[dir]):
+			for b in phases[dir]:
 				# draw the devices for this phase
 				phaselist = data.dmesg[b]['list']
 				for d in data.tdevlist[b]:
@@ -3942,19 +3957,17 @@ def createHTML(testruns, testfail):
 
 	# draw a legend which describes the phases by color
 	if sysvals.suspendmode != 'command':
-		data = testruns[-1]
+		phasedef = testruns[-1].phasedef
 		devtl.html += '<div class="legend">\n'
-		pdelta = 100.0/len(data.phases)
+		pdelta = 100.0/len(phasedef.keys())
 		pmargin = pdelta / 4.0
-		for phase in data.phases:
-			tmp = phase.split('_')
-			id = tmp[0][0]
-			if(len(tmp) > 1):
-				id += tmp[1][0]
-			order = '%.2f' % ((data.dmesg[phase]['order'] * pdelta) + pmargin)
+		for phase in sorted(phasedef, key=lambda k:phasedef[k]['order']):
+			id, p = '', phasedef[phase]
+			for word in phase.split('_'):
+				id += word[0]
+			order = '%.2f' % ((p['order'] * pdelta) + pmargin)
 			name = string.replace(phase, '_', ' &nbsp;')
-			devtl.html += devtl.html_legend.format(order, \
-				data.dmesg[phase]['color'], name, id)
+			devtl.html += devtl.html_legend.format(order, p['color'], name, id)
 		devtl.html += '</div>\n'
 
 	hf = open(sysvals.htmlfile, 'w')
@@ -3970,7 +3983,7 @@ def createHTML(testruns, testfail):
 		pscolor = 'linear-gradient(to top left, #ccc, #eee)'
 		hf.write(devtl.html_phaselet.format('pre_suspend_process', \
 			'0', '0', pscolor))
-		for b in data.phases:
+		for b in data.sortedPhases():
 			phase = data.dmesg[b]
 			length = phase['end']-phase['start']
 			left = '%.3f' % (((phase['start']-t0)*100.0)/tTotal)
@@ -4542,16 +4555,12 @@ def setRuntimeSuspend(before=True):
 def executeSuspend():
 	pm = ProcessMonitor()
 	tp = sysvals.tpath
-	fwdata = []
+	testdata = []
+	battery = True if getBattery() else False
 	# run these commands to prepare the system for suspend
 	if sysvals.display:
-		if sysvals.display > 0:
-			print('TURN DISPLAY ON')
-			call('xset -d :0.0 dpms force suspend', shell=True)
-			call('xset -d :0.0 dpms force on', shell=True)
-		else:
-			print('TURN DISPLAY OFF')
-			call('xset -d :0.0 dpms force suspend', shell=True)
+		print('SET DISPLAY TO %s' % sysvals.display.upper())
+		displayControl(sysvals.display)
 		time.sleep(1)
 	if sysvals.sync:
 		print('SYNCING FILESYSTEMS')
@@ -4579,6 +4588,7 @@ def executeSuspend():
 				print('SUSPEND START')
 			else:
 				print('SUSPEND START (press a key to resume)')
+		bat1 = getBattery() if battery else False
 		# set rtcwake
 		if(sysvals.rtcwake):
 			print('will issue an rtcwake in %d seconds' % sysvals.rtcwaketime)
@@ -4592,8 +4602,11 @@ def executeSuspend():
 			time.sleep(sysvals.predelay/1000.0)
 			sysvals.fsetVal('WAIT END', 'trace_marker')
 		# initiate suspend or command
+		tdata = {'error': ''}
 		if sysvals.testcommand != '':
-			call(sysvals.testcommand+' 2>&1', shell=True);
+			res = call(sysvals.testcommand+' 2>&1', shell=True);
+			if res != 0:
+				tdata['error'] = 'cmd returned %d' % res
 		else:
 			mode = sysvals.suspendmode
 			if sysvals.memmode and os.path.exists(sysvals.mempowerfile):
@@ -4606,8 +4619,8 @@ def executeSuspend():
 			# execution will pause here
 			try:
 				pf.close()
-			except:
-				pass
+			except Exception as e:
+				tdata['error'] = str(e)
 		if(sysvals.rtcwake):
 			sysvals.rtcWakeAlarmOff()
 		# postdelay delay
@@ -4620,23 +4633,29 @@ def executeSuspend():
 		if(sysvals.usecallgraph or sysvals.usetraceevents):
 			sysvals.fsetVal('RESUME COMPLETE', 'trace_marker')
 		if(sysvals.suspendmode == 'mem' or sysvals.suspendmode == 'command'):
-			fwdata.append(getFPDT(False))
+			tdata['fw'] = getFPDT(False)
+		bat2 = getBattery() if battery else False
+		if battery and bat1 and bat2:
+			tdata['bat'] = (bat1, bat2)
+		testdata.append(tdata)
 	# stop ftrace
 	if(sysvals.usecallgraph or sysvals.usetraceevents):
 		if sysvals.useprocmon:
 			pm.stop()
 		sysvals.fsetVal('0', 'tracing_on')
+	# grab a copy of the dmesg output
+	print('CAPTURING DMESG')
+	sysvals.getdmesg(testdata)
+	# grab a copy of the ftrace output
+	if(sysvals.usecallgraph or sysvals.usetraceevents):
 		print('CAPTURING TRACE')
-		op = sysvals.writeDatafileHeader(sysvals.ftracefile, fwdata)
+		op = sysvals.writeDatafileHeader(sysvals.ftracefile, testdata)
 		fp = open(tp+'trace', 'r')
 		for line in fp:
 			op.write(line)
 		op.close()
 		sysvals.fsetVal('', 'trace')
 		devProps()
-	# grab a copy of the dmesg output
-	print('CAPTURING DMESG')
-	sysvals.getdmesg(fwdata)
 
 def readFile(file):
 	if os.path.islink(file):
@@ -4766,7 +4785,7 @@ def devProps(data=0):
 			alreadystamped = True
 			continue
 		# determine the trace data type (required for further parsing)
-		m = re.match(sysvals.tracertypefmt, line)
+		m = re.match(tp.tracertypefmt, line)
 		if(m):
 			tp.setTracerType(m.group('t'))
 			continue
@@ -4994,8 +5013,9 @@ def dmidecode(mempath, fatal=False):
 	return out
 
 def getBattery():
-	p = '/sys/class/power_supply'
-	bat = dict()
+	p, charge, bat = '/sys/class/power_supply', 0, {}
+	if not os.path.exists(p):
+		return False
 	for d in os.listdir(p):
 		type = sysvals.getVal(os.path.join(p, d, 'type')).strip().lower()
 		if type != 'battery':
@@ -5003,15 +5023,42 @@ def getBattery():
 		for v in ['status', 'energy_now', 'capacity_now']:
 			bat[v] = sysvals.getVal(os.path.join(p, d, v)).strip().lower()
 		break
-	ac = True
-	if 'status' in bat and 'discharging' in bat['status']:
-		ac = False
-	charge = 0
+	if 'status' not in bat:
+		return False
+	ac = False if 'discharging' in bat['status'] else True
 	for v in ['energy_now', 'capacity_now']:
 		if v in bat and bat[v]:
 			charge = int(bat[v])
 	return (ac, charge)
 
+def displayControl(cmd):
+	xset, ret = 'xset -d :0.0 {0}', 0
+	if sysvals.sudouser:
+		xset = 'sudo -u %s %s' % (sysvals.sudouser, xset)
+	if cmd == 'init':
+		ret = call(xset.format('dpms 0 0 0'), shell=True)
+		ret = call(xset.format('s off'), shell=True)
+	elif cmd == 'reset':
+		ret = call(xset.format('s reset'), shell=True)
+	elif cmd in ['on', 'off', 'standby', 'suspend']:
+		b4 = displayControl('stat')
+		ret = call(xset.format('dpms force %s' % cmd), shell=True)
+		curr = displayControl('stat')
+		sysvals.vprint('Display Switched: %s -> %s' % (b4, curr))
+		if curr != cmd:
+			sysvals.vprint('WARNING: Display failed to change to %s' % cmd)
+	elif cmd == 'stat':
+		fp = Popen(xset.format('q').split(' '), stdout=PIPE).stdout
+		ret = 'unknown'
+		for line in fp:
+			m = re.match('[\s]*Monitor is (?P<m>.*)', line)
+			if(m and len(m.group('m')) >= 2):
+				out = m.group('m').lower()
+				ret = out[3:] if out[0:2] == 'in' else out
+				break
+		fp.close()
+	return ret
+
 # Function: getFPDT
 # Description:
 #	 Read the acpi bios tables and pull out FPDT, the firmware data
@@ -5149,7 +5196,7 @@ def getFPDT(output):
 # Output:
 #	 True if the test will work, False if not
 def statusCheck(probecheck=False):
-	status = True
+	status = ''
 
 	print('Checking this system (%s)...' % platform.node())
 
@@ -5160,7 +5207,7 @@ def statusCheck(probecheck=False):
 	print('    have root access: %s' % res)
 	if(res != 'YES'):
 		print('    Try running this script with sudo')
-		return False
+		return 'missing root access'
 
 	# check sysfs is mounted
 	res = sysvals.colorText('NO (No features of this tool will work!)')
@@ -5168,7 +5215,7 @@ def statusCheck(probecheck=False):
 		res = 'YES'
 	print('    is sysfs mounted: %s' % res)
 	if(res != 'YES'):
-		return False
+		return 'sysfs is missing'
 
 	# check target mode is a valid mode
 	if sysvals.suspendmode != 'command':
@@ -5177,7 +5224,7 @@ def statusCheck(probecheck=False):
 		if(sysvals.suspendmode in modes):
 			res = 'YES'
 		else:
-			status = False
+			status = '%s mode is not supported' % sysvals.suspendmode
 		print('    is "%s" a valid power mode: %s' % (sysvals.suspendmode, res))
 		if(res == 'NO'):
 			print('      valid power modes are: %s' % modes)
@@ -5189,7 +5236,7 @@ def statusCheck(probecheck=False):
 	if(ftgood):
 		res = 'YES'
 	elif(sysvals.usecallgraph):
-		status = False
+		status = 'ftrace is not properly supported'
 	print('    is ftrace supported: %s' % res)
 
 	# check if kprobes are available
@@ -5217,7 +5264,7 @@ def statusCheck(probecheck=False):
 	if(sysvals.rtcpath != ''):
 		res = 'YES'
 	elif(sysvals.rtcwake):
-		status = False
+		status = 'rtcwake is not properly supported'
 	print('    is rtcwake supported: %s' % res)
 
 	if not probecheck:
@@ -5245,7 +5292,7 @@ def doError(msg, help=False):
 		printHelp()
 	print('ERROR: %s\n') % msg
 	sysvals.outputResult({'error':msg})
-	sys.exit()
+	sys.exit(1)
 
 # Function: getArgInt
 # Description:
@@ -5301,11 +5348,16 @@ def processData(live=False):
 			appendIncompleteTraceLog(testruns)
 	sysvals.vprint('Command:\n    %s' % sysvals.cmdline)
 	for data in testruns:
+		if data.battery:
+			a1, c1, a2, c2 = data.battery
+			s = 'Battery:\n    Before - AC: %s, Charge: %d\n     After - AC: %s, Charge: %d' % \
+				(a1, int(c1), a2, int(c2))
+			sysvals.vprint(s)
 		data.printDetails()
 	if sysvals.cgdump:
 		for data in testruns:
 			data.debugPrint()
-		sys.exit()
+		sys.exit(0)
 	if len(testruns) < 1:
 		return (testruns, {'error': 'timeline generation failed'})
 	sysvals.vprint('Creating the html timeline (%s)...' % sysvals.htmlfile)
@@ -5335,6 +5387,7 @@ def rerunTest():
 		elif not os.access(sysvals.htmlfile, os.W_OK):
 			doError('missing permission to write to %s' % sysvals.htmlfile)
 	testruns, stamp = processData(False)
+	sysvals.logmsg = ''
 	return stamp
 
 # Function: runTest
@@ -5349,13 +5402,16 @@ def runTest(n=0):
 	executeSuspend()
 	sysvals.cleanupFtrace()
 	if sysvals.skiphtml:
-		sysvals.sudouser(sysvals.testdir)
+		sysvals.sudoUserchown(sysvals.testdir)
 		return
 	testruns, stamp = processData(True)
 	for data in testruns:
 		del data
-	sysvals.sudouser(sysvals.testdir)
+	sysvals.sudoUserchown(sysvals.testdir)
 	sysvals.outputResult(stamp, n)
+	if 'error' in stamp:
+		return 2
+	return 0
 
 def find_in_html(html, start, end, firstonly=True):
 	n, out = 0, []
@@ -5380,14 +5436,86 @@ def find_in_html(html, start, end, firstonly=True):
 		return ''
 	return out
 
+def data_from_html(file, outpath, devlist=False):
+	html = open(file, 'r').read()
+	suspend = find_in_html(html, 'Kernel Suspend', 'ms')
+	resume = find_in_html(html, 'Kernel Resume', 'ms')
+	line = find_in_html(html, '<div class="stamp">', '</div>')
+	stmp = line.split()
+	if not suspend or not resume or len(stmp) != 8:
+		return False
+	try:
+		dt = datetime.strptime(' '.join(stmp[3:]), '%B %d %Y, %I:%M:%S %p')
+	except:
+		return False
+	tstr = dt.strftime('%Y/%m/%d %H:%M:%S')
+	error = find_in_html(html, '<table class="testfail"><tr><td>', '</td>')
+	if error:
+		m = re.match('[a-z]* failed in (?P<p>[a-z0-9_]*) phase', error)
+		if m:
+			result = 'fail in %s' % m.group('p')
+		else:
+			result = 'fail'
+	else:
+		result = 'pass'
+	ilist = []
+	e = find_in_html(html, 'class="err"[\w=":;\.%\- ]*>', '&rarr;</div>', False)
+	for i in list(set(e)):
+		ilist.append('%sx%d' % (i, e.count(i)) if e.count(i) > 1 else i)
+	low = find_in_html(html, 'freeze time: <b>', ' ms</b>')
+	if low and '|' in low:
+		ilist.append('FREEZEx%d' % len(low.split('|')))
+	devices = dict()
+	for line in html.split('\n'):
+		m = re.match(' *<div id=\"[a,0-9]*\" *title=\"(?P<title>.*)\" class=\"thread.*', line)
+		if not m or 'thread kth' in line or 'thread sec' in line:
+			continue
+		m = re.match('(?P<n>.*) \((?P<t>[0-9,\.]*) ms\) (?P<p>.*)', m.group('title'))
+		if not m:
+			continue
+		name, time, phase = m.group('n'), m.group('t'), m.group('p')
+		if ' async' in name or ' sync' in name:
+			name = ' '.join(name.split(' ')[:-1])
+		d = phase.split('_')[0]
+		if d not in devices:
+			devices[d] = dict()
+		if name not in devices[d]:
+			devices[d][name] = 0.0
+		devices[d][name] += float(time)
+	worst  = {'suspend': {'name':'', 'time': 0.0},
+		'resume': {'name':'', 'time': 0.0}}
+	for d in devices:
+		if d not in worst:
+			worst[d] = dict()
+		dev = devices[d]
+		if len(dev.keys()) > 0:
+			n = sorted(dev, key=dev.get, reverse=True)[0]
+			worst[d]['name'], worst[d]['time'] = n, dev[n]
+	data = {
+		'mode': stmp[2],
+		'host': stmp[0],
+		'kernel': stmp[1],
+		'time': tstr,
+		'result': result,
+		'issues': ' '.join(ilist),
+		'suspend': suspend,
+		'resume': resume,
+		'sus_worst': worst['suspend']['name'],
+		'sus_worsttime': worst['suspend']['time'],
+		'res_worst': worst['resume']['name'],
+		'res_worsttime': worst['resume']['time'],
+		'url': os.path.relpath(file, outpath),
+	}
+	if devlist:
+		data['devlist'] = devices
+	return data
+
 # Function: runSummary
 # Description:
 #	 create a summary of tests in a sub-directory
 def runSummary(subdir, local=True, genhtml=False):
 	inpath = os.path.abspath(subdir)
-	outpath = inpath
-	if local:
-		outpath = os.path.abspath('.')
+	outpath = os.path.abspath('.') if local else inpath
 	print('Generating a summary of folder "%s"' % inpath)
 	if genhtml:
 		for dirname, dirnames, filenames in os.walk(subdir):
@@ -5409,36 +5537,9 @@ def runSummary(subdir, local=True, genhtml=False):
 		for filename in filenames:
 			if(not re.match('.*.html', filename)):
 				continue
-			file = os.path.join(dirname, filename)
-			html = open(file, 'r').read()
-			suspend = find_in_html(html, 'Kernel Suspend', 'ms')
-			resume = find_in_html(html, 'Kernel Resume', 'ms')
-			line = find_in_html(html, '<div class="stamp">', '</div>')
-			stmp = line.split()
-			if not suspend or not resume or len(stmp) != 8:
+			data = data_from_html(os.path.join(dirname, filename), outpath)
+			if(not data):
 				continue
-			try:
-				dt = datetime.strptime(' '.join(stmp[3:]), '%B %d %Y, %I:%M:%S %p')
-			except:
-				continue
-			tstr = dt.strftime('%Y/%m/%d %H:%M:%S')
-			error = find_in_html(html, '<table class="testfail"><tr><td>', '</td>')
-			result = 'fail' if error else 'pass'
-			ilist = []
-			e = find_in_html(html, 'class="err"[\w=":;\.%\- ]*>', '&rarr;</div>', False)
-			for i in list(set(e)):
-				ilist.append('%sx%d' % (i, e.count(i)) if e.count(i) > 1 else i)
-			data = {
-				'mode': stmp[2],
-				'host': stmp[0],
-				'kernel': stmp[1],
-				'time': tstr,
-				'result': result,
-				'issues': ','.join(ilist),
-				'suspend': suspend,
-				'resume': resume,
-				'url': os.path.relpath(file, outpath),
-			}
 			testruns.append(data)
 	outfile = os.path.join(outpath, 'summary.html')
 	print('Summary file: %s' % outfile)
@@ -5499,13 +5600,10 @@ def configFromFile(file):
 				else:
 					doError('invalid value --> (%s: %s), use "enable/disable"' % (option, value), True)
 			elif(option == 'display'):
-				if value in switchvalues:
-					if value in switchoff:
-						sysvals.display = -1
-					else:
-						sysvals.display = 1
-				else:
-					doError('invalid value --> (%s: %s), use "on/off"' % (option, value), True)
+				disopt = ['on', 'off', 'standby', 'suspend']
+				if value not in disopt:
+					doError('invalid value --> (%s: %s), use %s' % (option, value, disopt), True)
+				sysvals.display = value
 			elif(option == 'gzip'):
 				sysvals.gzip = checkArgBool(option, value)
 			elif(option == 'cgfilter'):
@@ -5521,9 +5619,9 @@ def configFromFile(file):
 				sysvals.cgtest = getArgInt('cgtest', value, 0, 1, False)
 			elif(option == 'cgphase'):
 				d = Data(0)
-				if value not in d.phases:
+				if value not in d.sortedPhases():
 					doError('invalid phase --> (%s: %s), valid phases are %s'\
-						% (option, value, d.phases), True)
+						% (option, value, d.sortedPhases()), True)
 				sysvals.cgphase = value
 			elif(option == 'fadd'):
 				file = sysvals.configFile(value)
@@ -5697,7 +5795,7 @@ def printHelp():
 	print('  [testprep]')
 	print('   -sync        Sync the filesystems before starting the test')
 	print('   -rs on/off   Enable/disable runtime suspend for all devices, restore all after test')
-	print('   -display on/off  Turn the display on or off for the test')
+	print('   -display m   Change the display mode to m for the test (on/off/standby/suspend)')
 	print('  [advanced]')
 	print('   -gzip        Gzip the trace and dmesg logs to save space')
 	print('   -cmd {s}     Run the timeline over a custom command, e.g. "sync -d"')
@@ -5729,6 +5827,7 @@ def printHelp():
 	print('   -status      Test to see if the system is enabled to run this tool')
 	print('   -fpdt        Print out the contents of the ACPI Firmware Performance Data Table')
 	print('   -battery     Print out battery info (if available)')
+	print('   -x<mode>     Test xset by toggling the given mode (on/off/standby/suspend)')
 	print('   -sysinfo     Print out system info extracted from BIOS')
 	print('   -devinfo     Print out the pm settings of all devices which support runtime suspend')
 	print('   -flist       Print the list of functions currently being captured in ftrace')
@@ -5745,7 +5844,9 @@ def printHelp():
 if __name__ == '__main__':
 	genhtml = False
 	cmd = ''
-	simplecmds = ['-sysinfo', '-modes', '-fpdt', '-flist', '-flistall', '-devinfo', '-status', '-battery']
+	simplecmds = ['-sysinfo', '-modes', '-fpdt', '-flist', '-flistall',
+		'-devinfo', '-status', '-battery', '-xon', '-xoff', '-xstandby',
+		'-xsuspend', '-xinit', '-xreset', '-xstat']
 	if '-f' in sys.argv:
 		sysvals.cgskip = sysvals.configFile('cgskip.txt')
 	# loop through the command line arguments
@@ -5763,10 +5864,10 @@ if __name__ == '__main__':
 			cmd = arg[1:]
 		elif(arg == '-h'):
 			printHelp()
-			sys.exit()
+			sys.exit(0)
 		elif(arg == '-v'):
 			print("Version %s" % sysvals.version)
-			sys.exit()
+			sys.exit(0)
 		elif(arg == '-x2'):
 			sysvals.execcount = 2
 		elif(arg == '-x2delay'):
@@ -5785,6 +5886,10 @@ if __name__ == '__main__':
 			genhtml = True
 		elif(arg == '-addlogs'):
 			sysvals.dmesglog = sysvals.ftracelog = True
+		elif(arg == '-addlogdmesg'):
+			sysvals.dmesglog = True
+		elif(arg == '-addlogftrace'):
+			sysvals.ftracelog = True
 		elif(arg == '-verbose'):
 			sysvals.verbose = True
 		elif(arg == '-proc'):
@@ -5811,14 +5916,11 @@ if __name__ == '__main__':
 			try:
 				val = args.next()
 			except:
-				doError('-display requires "on" or "off"', True)
-			if val.lower() in switchvalues:
-				if val.lower() in switchoff:
-					sysvals.display = -1
-				else:
-					sysvals.display = 1
-			else:
-				doError('invalid option: %s, use "on/off"' % val, True)
+				doError('-display requires an mode value', True)
+			disopt = ['on', 'off', 'standby', 'suspend']
+			if val.lower() not in disopt:
+				doError('valid display mode values are %s' % disopt, True)
+			sysvals.display = val.lower()
 		elif(arg == '-maxdepth'):
 			sysvals.max_graph_depth = getArgInt('-maxdepth', args, 0, 1000)
 		elif(arg == '-rtcwake'):
@@ -5847,9 +5949,9 @@ if __name__ == '__main__':
 			except:
 				doError('No phase name supplied', True)
 			d = Data(0)
-			if val not in d.phases:
+			if val not in d.phasedef:
 				doError('invalid phase --> (%s: %s), valid phases are %s'\
-					% (arg, val, d.phases), True)
+					% (arg, val, d.phasedef.keys()), True)
 			sysvals.cgphase = val
 		elif(arg == '-cgfilter'):
 			try:
@@ -5951,6 +6053,7 @@ if __name__ == '__main__':
 			except:
 				doError('No result file supplied', True)
 			sysvals.result = val
+			sysvals.signalHandlerInit()
 		else:
 			doError('Invalid argument: '+arg, True)
 
@@ -5975,12 +6078,20 @@ if __name__ == '__main__':
 
 	# just run a utility command and exit
 	if(cmd != ''):
+		ret = 0
 		if(cmd == 'status'):
-			statusCheck(True)
+			if not statusCheck(True):
+				ret = 1
 		elif(cmd == 'fpdt'):
-			getFPDT(True)
+			if not getFPDT(True):
+				ret = 1
 		elif(cmd == 'battery'):
-			print 'AC Connect: %s\nCharge: %d' % getBattery()
+			out = getBattery()
+			if out:
+				print 'AC Connect    : %s\nBattery Charge: %d' % out
+			else:
+				print 'no battery found'
+				ret = 1
 		elif(cmd == 'sysinfo'):
 			sysvals.printSystemInfo(True)
 		elif(cmd == 'devinfo'):
@@ -5993,17 +6104,23 @@ if __name__ == '__main__':
 			sysvals.getFtraceFilterFunctions(False)
 		elif(cmd == 'summary'):
 			runSummary(sysvals.outdir, True, genhtml)
-		sys.exit()
+		elif(cmd in ['xon', 'xoff', 'xstandby', 'xsuspend', 'xinit', 'xreset']):
+			sysvals.verbose = True
+			ret = displayControl(cmd[1:])
+		elif(cmd == 'xstat'):
+			print 'Display Status: %s' % displayControl('stat').upper()
+		sys.exit(ret)
 
 	# if instructed, re-analyze existing data files
 	if(sysvals.notestrun):
 		stamp = rerunTest()
 		sysvals.outputResult(stamp)
-		sys.exit()
+		sys.exit(0)
 
 	# verify that we can run a test
-	if(not statusCheck()):
-		doError('Check FAILED, aborting the test run!')
+	error = statusCheck()
+	if(error):
+		doError(error)
 
 	# extract mem modes and convert
 	mode = sysvals.suspendmode
@@ -6025,8 +6142,8 @@ if __name__ == '__main__':
 
 	setRuntimeSuspend(True)
 	if sysvals.display:
-		call('xset -d :0.0 dpms 0 0 0', shell=True)
-		call('xset -d :0.0 s off', shell=True)
+		displayControl('init')
+	ret = 0
 	if sysvals.multitest['run']:
 		# run multiple tests in a separate subdirectory
 		if not sysvals.outdir:
@@ -6041,17 +6158,18 @@ if __name__ == '__main__':
 			print('TEST (%d/%d) START' % (i+1, sysvals.multitest['count']))
 			fmt = 'suspend-%y%m%d-%H%M%S'
 			sysvals.testdir = os.path.join(sysvals.outdir, datetime.now().strftime(fmt))
-			runTest(i+1)
+			ret = runTest(i+1)
 			print('TEST (%d/%d) COMPLETE' % (i+1, sysvals.multitest['count']))
 			sysvals.logmsg = ''
 		if not sysvals.skiphtml:
 			runSummary(sysvals.outdir, False, False)
-		sysvals.sudouser(sysvals.outdir)
+		sysvals.sudoUserchown(sysvals.outdir)
 	else:
 		if sysvals.outdir:
 			sysvals.testdir = sysvals.outdir
 		# run the test in the current directory
-		runTest()
+		ret = runTest()
 	if sysvals.display:
-		call('xset -d :0.0 s reset', shell=True)
+		displayControl('reset')
 	setRuntimeSuspend(False)
+	sys.exit(ret)
-- 
cgit v1.2.3


From 18d3f8fc0c2c5a55d40d1bedcf46865ecb87d84e Mon Sep 17 00:00:00 2001
From: Todd Brandt <todd.e.brandt@linux.intel.com>
Date: Mon, 8 Oct 2018 15:56:32 -0700
Subject: PM / tools: sleepgraph and bootgraph: upgrade to v5.2

bootgraph & sleepgraph:
- funnel all prints through the pprint function
- remove superfluous print calls, arrange them in single blocks
- flush stdout on every print, enables log capture on hang

sleepgraph:
- in -summary, if all tests have the same host+kernel+mode, add to title
- update verbose device detail print to include machine suspend/resume
- match tKernSus and tKernRes to pm_prepare/restore_console
- fully support multiple suspend/resumes in a single timeline
- enable various disk modes (disk-suspend, disk-test_resume, etc)
- add warnings when -display (xset) fails

Signed-off-by: Todd Brandt <todd.e.brandt@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 tools/power/pm-graph/bootgraph.py                  | 125 ++---
 tools/power/pm-graph/config/cgskip.txt             |   1 +
 .../pm-graph/config/custom-timeline-functions.cfg  |   4 +-
 tools/power/pm-graph/sleepgraph.py                 | 532 ++++++++++++---------
 4 files changed, 364 insertions(+), 298 deletions(-)

(limited to 'tools')

diff --git a/tools/power/pm-graph/bootgraph.py b/tools/power/pm-graph/bootgraph.py
index 8ee626c0f6a5..6dae57041537 100755
--- a/tools/power/pm-graph/bootgraph.py
+++ b/tools/power/pm-graph/bootgraph.py
@@ -34,6 +34,10 @@ from datetime import datetime, timedelta
 from subprocess import call, Popen, PIPE
 import sleepgraph as aslib
 
+def pprint(msg):
+	print(msg)
+	sys.stdout.flush()
+
 # ----------------- CLASSES --------------------
 
 # Class: SystemValues
@@ -157,11 +161,11 @@ class SystemValues(aslib.SystemValues):
 		return cmdline
 	def manualRebootRequired(self):
 		cmdline = self.kernelParams()
-		print 'To generate a new timeline manually, follow these steps:\n'
-		print '1. Add the CMDLINE string to your kernel command line.'
-		print '2. Reboot the system.'
-		print '3. After reboot, re-run this tool with the same arguments but no command (w/o -reboot or -manual).\n'
-		print 'CMDLINE="%s"' % cmdline
+		pprint('To generate a new timeline manually, follow these steps:\n\n'\
+		'1. Add the CMDLINE string to your kernel command line.\n'\
+		'2. Reboot the system.\n'\
+		'3. After reboot, re-run this tool with the same arguments but no command (w/o -reboot or -manual).\n\n'\
+		'CMDLINE="%s"' % cmdline)
 		sys.exit()
 	def blGrub(self):
 		blcmd = ''
@@ -431,7 +435,7 @@ def parseTraceLog(data):
 			if len(cg.list) < 1 or cg.invalid or (cg.end - cg.start == 0):
 				continue
 			if(not cg.postProcess()):
-				print('Sanity check failed for %s-%d' % (proc, pid))
+				pprint('Sanity check failed for %s-%d' % (proc, pid))
 				continue
 			# match cg data to devices
 			devname = data.deviceMatch(pid, cg)
@@ -442,8 +446,8 @@ def parseTraceLog(data):
 				sysvals.vprint('%s callgraph found for %s %s-%d [%f - %f]' %\
 					(kind, cg.name, proc, pid, cg.start, cg.end))
 			elif len(cg.list) > 1000000:
-				print 'WARNING: the callgraph found for %s is massive! (%d lines)' %\
-					(devname, len(cg.list))
+				pprint('WARNING: the callgraph found for %s is massive! (%d lines)' %\
+					(devname, len(cg.list)))
 
 # Function: retrieveLogs
 # Description:
@@ -528,7 +532,7 @@ def createBootGraph(data):
 	tMax = data.end
 	tTotal = tMax - t0
 	if(tTotal == 0):
-		print('ERROR: No timeline data')
+		pprint('ERROR: No timeline data')
 		return False
 	user_mode = '%.0f'%(data.tUserMode*1000)
 	last_init = '%.0f'%(tTotal*1000)
@@ -734,7 +738,7 @@ def updateCron(restore=False):
 		op.close()
 		res = call([cmd, cronfile])
 	except Exception, e:
-		print 'Exception: %s' % str(e)
+		pprint('Exception: %s' % str(e))
 		shutil.move(backfile, cronfile)
 		res = -1
 	if res != 0:
@@ -750,7 +754,7 @@ def updateGrub(restore=False):
 			call(sysvals.blexec, stderr=PIPE, stdout=PIPE,
 				env={'PATH': '.:/sbin:/usr/sbin:/usr/bin:/sbin:/bin'})
 		except Exception, e:
-			print 'Exception: %s\n' % str(e)
+			pprint('Exception: %s\n' % str(e))
 		return
 	# extract the option and create a grub config without it
 	sysvals.rootUser(True)
@@ -797,7 +801,7 @@ def updateGrub(restore=False):
 		res = call(sysvals.blexec)
 		os.remove(grubfile)
 	except Exception, e:
-		print 'Exception: %s' % str(e)
+		pprint('Exception: %s' % str(e))
 		res = -1
 	# cleanup
 	shutil.move(tempfile, grubfile)
@@ -821,7 +825,7 @@ def updateKernelParams(restore=False):
 def doError(msg, help=False):
 	if help == True:
 		printHelp()
-	print 'ERROR: %s\n' % msg
+	pprint('ERROR: %s\n' % msg)
 	sysvals.outputResult({'error':msg})
 	sys.exit()
 
@@ -829,52 +833,51 @@ def doError(msg, help=False):
 # Description:
 #	 print out the help text
 def printHelp():
-	print('')
-	print('%s v%s' % (sysvals.title, sysvals.version))
-	print('Usage: bootgraph <options> <command>')
-	print('')
-	print('Description:')
-	print('  This tool reads in a dmesg log of linux kernel boot and')
-	print('  creates an html representation of the boot timeline up to')
-	print('  the start of the init process.')
-	print('')
-	print('  If no specific command is given the tool reads the current dmesg')
-	print('  and/or ftrace log and creates a timeline')
-	print('')
-	print('  Generates output files in subdirectory: boot-yymmdd-HHMMSS')
-	print('   HTML output:                    <hostname>_boot.html')
-	print('   raw dmesg output:               <hostname>_boot_dmesg.txt')
-	print('   raw ftrace output:              <hostname>_boot_ftrace.txt')
-	print('')
-	print('Options:')
-	print('  -h            Print this help text')
-	print('  -v            Print the current tool version')
-	print('  -verbose      Print extra information during execution and analysis')
-	print('  -addlogs      Add the dmesg log to the html output')
-	print('  -result fn    Export a results table to a text file for parsing.')
-	print('  -o name       Overrides the output subdirectory name when running a new test')
-	print('                default: boot-{date}-{time}')
-	print(' [advanced]')
-	print('  -fstat        Use ftrace to add function detail and statistics (default: disabled)')
-	print('  -f/-callgraph Add callgraph detail, can be very large (default: disabled)')
-	print('  -maxdepth N   limit the callgraph data to N call levels (default: 2)')
-	print('  -mincg ms     Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)')
-	print('  -timeprec N   Number of significant digits in timestamps (0:S, 3:ms, [6:us])')
-	print('  -expandcg     pre-expand the callgraph data in the html output (default: disabled)')
-	print('  -func list    Limit ftrace to comma-delimited list of functions (default: do_one_initcall)')
-	print('  -cgfilter S   Filter the callgraph output in the timeline')
-	print('  -cgskip file  Callgraph functions to skip, off to disable (default: cgskip.txt)')
-	print('  -bl name      Use the following boot loader for kernel params (default: grub)')
-	print('  -reboot       Reboot the machine automatically and generate a new timeline')
-	print('  -manual       Show the steps to generate a new timeline manually (used with -reboot)')
-	print('')
-	print('Other commands:')
-	print('  -flistall     Print all functions capable of being captured in ftrace')
-	print('  -sysinfo      Print out system info extracted from BIOS')
-	print(' [redo]')
-	print('  -dmesg file   Create HTML output using dmesg input (used with -ftrace)')
-	print('  -ftrace file  Create HTML output using ftrace input (used with -dmesg)')
-	print('')
+	pprint('\n%s v%s\n'\
+	'Usage: bootgraph <options> <command>\n'\
+	'\n'\
+	'Description:\n'\
+	'  This tool reads in a dmesg log of linux kernel boot and\n'\
+	'  creates an html representation of the boot timeline up to\n'\
+	'  the start of the init process.\n'\
+	'\n'\
+	'  If no specific command is given the tool reads the current dmesg\n'\
+	'  and/or ftrace log and creates a timeline\n'\
+	'\n'\
+	'  Generates output files in subdirectory: boot-yymmdd-HHMMSS\n'\
+	'   HTML output:                    <hostname>_boot.html\n'\
+	'   raw dmesg output:               <hostname>_boot_dmesg.txt\n'\
+	'   raw ftrace output:              <hostname>_boot_ftrace.txt\n'\
+	'\n'\
+	'Options:\n'\
+	'  -h            Print this help text\n'\
+	'  -v            Print the current tool version\n'\
+	'  -verbose      Print extra information during execution and analysis\n'\
+	'  -addlogs      Add the dmesg log to the html output\n'\
+	'  -result fn    Export a results table to a text file for parsing.\n'\
+	'  -o name       Overrides the output subdirectory name when running a new test\n'\
+	'                default: boot-{date}-{time}\n'\
+	' [advanced]\n'\
+	'  -fstat        Use ftrace to add function detail and statistics (default: disabled)\n'\
+	'  -f/-callgraph Add callgraph detail, can be very large (default: disabled)\n'\
+	'  -maxdepth N   limit the callgraph data to N call levels (default: 2)\n'\
+	'  -mincg ms     Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)\n'\
+	'  -timeprec N   Number of significant digits in timestamps (0:S, 3:ms, [6:us])\n'\
+	'  -expandcg     pre-expand the callgraph data in the html output (default: disabled)\n'\
+	'  -func list    Limit ftrace to comma-delimited list of functions (default: do_one_initcall)\n'\
+	'  -cgfilter S   Filter the callgraph output in the timeline\n'\
+	'  -cgskip file  Callgraph functions to skip, off to disable (default: cgskip.txt)\n'\
+	'  -bl name      Use the following boot loader for kernel params (default: grub)\n'\
+	'  -reboot       Reboot the machine automatically and generate a new timeline\n'\
+	'  -manual       Show the steps to generate a new timeline manually (used with -reboot)\n'\
+	'\n'\
+	'Other commands:\n'\
+	'  -flistall     Print all functions capable of being captured in ftrace\n'\
+	'  -sysinfo      Print out system info extracted from BIOS\n'\
+	' [redo]\n'\
+	'  -dmesg file   Create HTML output using dmesg input (used with -ftrace)\n'\
+	'  -ftrace file  Create HTML output using ftrace input (used with -dmesg)\n'\
+	'' % (sysvals.title, sysvals.version))
 	return True
 
 # ----------------- MAIN --------------------
@@ -895,7 +898,7 @@ if __name__ == '__main__':
 			printHelp()
 			sys.exit()
 		elif(arg == '-v'):
-			print("Version %s" % sysvals.version)
+			pprint("Version %s" % sysvals.version)
 			sys.exit()
 		elif(arg == '-verbose'):
 			sysvals.verbose = True
@@ -1016,7 +1019,7 @@ if __name__ == '__main__':
 				print f
 		elif cmd == 'checkbl':
 			sysvals.getBootLoader()
-			print 'Boot Loader: %s\n%s' % (sysvals.bootloader, sysvals.blexec)
+			pprint('Boot Loader: %s\n%s' % (sysvals.bootloader, sysvals.blexec))
 		elif(cmd == 'sysinfo'):
 			sysvals.printSystemInfo(True)
 		sys.exit()
diff --git a/tools/power/pm-graph/config/cgskip.txt b/tools/power/pm-graph/config/cgskip.txt
index e48d588fbfb4..9ff88e7e2300 100644
--- a/tools/power/pm-graph/config/cgskip.txt
+++ b/tools/power/pm-graph/config/cgskip.txt
@@ -27,6 +27,7 @@ ktime_get
 # console calls
 printk
 dev_printk
+__dev_printk
 console_unlock
 
 # memory handling
diff --git a/tools/power/pm-graph/config/custom-timeline-functions.cfg b/tools/power/pm-graph/config/custom-timeline-functions.cfg
index f8fcb06fd68b..4f80ad7d7275 100644
--- a/tools/power/pm-graph/config/custom-timeline-functions.cfg
+++ b/tools/power/pm-graph/config/custom-timeline-functions.cfg
@@ -105,7 +105,7 @@ override-dev-timeline-functions: true
 #       example: [color=#CC00CC]
 #
 #   arglist: A list of arguments from registers/stack addresses. See URL:
-#            https://www.kernel.org/doc/Documentation/trace/kprobetrace.rst
+#            https://www.kernel.org/doc/Documentation/trace/kprobetrace.txt
 #
 #       example: cpu=%di:s32
 #
@@ -170,7 +170,7 @@ pm_restore_console:
 #       example: [color=#CC00CC]
 #
 #   arglist: A list of arguments from registers/stack addresses. See URL:
-#            https://www.kernel.org/doc/Documentation/trace/kprobetrace.rst
+#            https://www.kernel.org/doc/Documentation/trace/kprobetrace.txt
 #
 #       example: port=+36(%di):s32
 #
diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py
index 343e8000d9ca..52618f3444d4 100755
--- a/tools/power/pm-graph/sleepgraph.py
+++ b/tools/power/pm-graph/sleepgraph.py
@@ -62,6 +62,10 @@ import gzip
 from threading import Thread
 from subprocess import call, Popen, PIPE
 
+def pprint(msg):
+	print(msg)
+	sys.stdout.flush()
+
 # ----------------- CLASSES --------------------
 
 # Class: SystemValues
@@ -70,7 +74,7 @@ from subprocess import call, Popen, PIPE
 #	 store system values and test parameters
 class SystemValues:
 	title = 'SleepGraph'
-	version = '5.1'
+	version = '5.2'
 	ansi = False
 	rs = 0
 	display = ''
@@ -111,8 +115,10 @@ class SystemValues:
 	mempath = '/dev/mem'
 	powerfile = '/sys/power/state'
 	mempowerfile = '/sys/power/mem_sleep'
+	diskpowerfile = '/sys/power/disk'
 	suspendmode = 'mem'
 	memmode = ''
+	diskmode = ''
 	hostname = 'localhost'
 	prefix = 'test'
 	teststamp = ''
@@ -139,6 +145,7 @@ class SystemValues:
 	useprocmon = False
 	notestrun = False
 	cgdump = False
+	devdump = False
 	mixedphaseheight = True
 	devprops = dict()
 	predelay = 0
@@ -265,7 +272,7 @@ class SystemValues:
 	def vprint(self, msg):
 		self.logmsg += msg+'\n'
 		if self.verbose or msg.startswith('WARNING:'):
-			print(msg)
+			pprint(msg)
 	def signalHandler(self, signum, frame):
 		if not self.result:
 			return
@@ -290,7 +297,7 @@ class SystemValues:
 			return True
 		if fatal:
 			msg = 'This command requires sysfs mount and root access'
-			print('ERROR: %s\n') % msg
+			pprint('ERROR: %s\n' % msg)
 			self.outputResult({'error':msg})
 			sys.exit(1)
 		return False
@@ -299,7 +306,7 @@ class SystemValues:
 			return True
 		if fatal:
 			msg = 'This command must be run as root'
-			print('ERROR: %s\n') % msg
+			pprint('ERROR: %s\n' % msg)
 			self.outputResult({'error':msg})
 			sys.exit(1)
 		return False
@@ -560,7 +567,7 @@ class SystemValues:
 		if len(self.kprobes) < 1:
 			return
 		if output:
-			print('    kprobe functions in this kernel:')
+			pprint('    kprobe functions in this kernel:')
 		# first test each kprobe
 		rejects = []
 		# sort kprobes: trace, ub-dev, custom, dev
@@ -582,7 +589,7 @@ class SystemValues:
 				else:
 					kpl[2].append(name)
 			if output:
-				print('         %s: %s' % (name, res))
+				pprint('         %s: %s' % (name, res))
 		kplist = kpl[0] + kpl[1] + kpl[2] + kpl[3]
 		# remove all failed ones from the list
 		for name in rejects:
@@ -596,7 +603,7 @@ class SystemValues:
 		if output:
 			check = self.fgetVal('kprobe_events')
 			linesack = (len(check.split('\n')) - 1) / 2
-			print('    kprobe functions enabled: %d/%d' % (linesack, linesout))
+			pprint('    kprobe functions enabled: %d/%d' % (linesack, linesout))
 		self.fsetVal('1', 'events/kprobes/enable')
 	def testKprobe(self, kname, kprobe):
 		self.fsetVal('0', 'events/kprobes/enable')
@@ -664,7 +671,7 @@ class SystemValues:
 		return False
 	def initFtrace(self):
 		self.printSystemInfo(False)
-		print('INITIALIZING FTRACE...')
+		pprint('INITIALIZING FTRACE...')
 		# turn trace off
 		self.fsetVal('0', 'tracing_on')
 		self.cleanupFtrace()
@@ -681,7 +688,8 @@ class SystemValues:
 		if self.bufsize > 0:
 			tgtsize = self.bufsize
 		elif self.usecallgraph or self.usedevsrc:
-			tgtsize = min(self.memfree, 3*1024*1024)
+			bmax = (1*1024*1024) if self.suspendmode == 'disk' else (3*1024*1024)
+			tgtsize = min(self.memfree, bmax)
 		else:
 			tgtsize = 65536
 		while not self.fsetVal('%d' % (tgtsize / cpus), 'buffer_size_kb'):
@@ -690,7 +698,7 @@ class SystemValues:
 			if tgtsize < 65536:
 				tgtsize = int(self.fgetVal('buffer_size_kb')) * cpus
 				break
-		print 'Setting trace buffers to %d kB (%d kB per cpu)' % (tgtsize, tgtsize/cpus)
+		pprint('Setting trace buffers to %d kB (%d kB per cpu)' % (tgtsize, tgtsize/cpus))
 		# initialize the callgraph trace
 		if(self.usecallgraph):
 			# set trace type
@@ -723,7 +731,7 @@ class SystemValues:
 			if self.usedevsrc:
 				for name in self.dev_tracefuncs:
 					self.defaultKprobe(name, self.dev_tracefuncs[name])
-			print('INITIALIZING KPROBES...')
+			pprint('INITIALIZING KPROBES...')
 			self.addKprobes(self.verbose)
 		if(self.usetraceevents):
 			# turn trace events on
@@ -846,7 +854,7 @@ class DevProps:
 	def out(self, dev):
 		return '%s,%s,%d;' % (dev, self.altname, self.async)
 	def debug(self, dev):
-		print '%s:\n\taltname = %s\n\t  async = %s' % (dev, self.altname, self.async)
+		pprint('%s:\n\taltname = %s\n\t  async = %s' % (dev, self.altname, self.async))
 	def altName(self, dev):
 		if not self.altname or self.altname == dev:
 			return dev
@@ -1217,16 +1225,8 @@ class Data:
 					self.tLow.append('%.0f'%(tL*1000))
 			lp = phase
 	def getTimeValues(self):
-		if 'suspend_machine' in self.dmesg:
-			sktime = (self.dmesg['suspend_machine']['end'] - \
-				self.tKernSus) * 1000
-		else:
-			sktime = (self.tSuspended - self.tKernSus) * 1000
-		if 'resume_machine' in self.dmesg:
-			rktime = (self.tKernRes - \
-				self.dmesg['resume_machine']['start']) * 1000
-		else:
-			rktime = (self.tKernRes - self.tResumed) * 1000
+		sktime = (self.tSuspended - self.tKernSus) * 1000
+		rktime = (self.tKernRes - self.tResumed) * 1000
 		return (sktime, rktime)
 	def setPhase(self, phase, ktime, isbegin, order=-1):
 		if(isbegin):
@@ -1379,14 +1379,38 @@ class Data:
 			if(list[child]['par'] == devname):
 				devlist.append(child)
 		return devlist
+	def maxDeviceNameSize(self, phase):
+		size = 0
+		for name in self.dmesg[phase]['list']:
+			if len(name) > size:
+				size = len(name)
+		return size
 	def printDetails(self):
 		sysvals.vprint('Timeline Details:')
 		sysvals.vprint('          test start: %f' % self.start)
 		sysvals.vprint('kernel suspend start: %f' % self.tKernSus)
+		tS = tR = False
 		for phase in self.sortedPhases():
-			dc = len(self.dmesg[phase]['list'])
-			sysvals.vprint('    %16s: %f - %f (%d devices)' % (phase, \
-				self.dmesg[phase]['start'], self.dmesg[phase]['end'], dc))
+			devlist = self.dmesg[phase]['list']
+			dc, ps, pe = len(devlist), self.dmesg[phase]['start'], self.dmesg[phase]['end']
+			if not tS and ps >= self.tSuspended:
+				sysvals.vprint('   machine suspended: %f' % self.tSuspended)
+				tS = True
+			if not tR and ps >= self.tResumed:
+				sysvals.vprint('     machine resumed: %f' % self.tResumed)
+				tR = True
+			sysvals.vprint('%20s: %f - %f (%d devices)' % (phase, ps, pe, dc))
+			if sysvals.devdump:
+				sysvals.vprint(''.join('-' for i in range(80)))
+				maxname = '%d' % self.maxDeviceNameSize(phase)
+				fmt = '%3d) %'+maxname+'s - %f - %f'
+				c = 1
+				for name in devlist:
+					s = devlist[name]['start']
+					e = devlist[name]['end']
+					sysvals.vprint(fmt % (c, name, s, e))
+					c += 1
+				sysvals.vprint(''.join('-' for i in range(80)))
 		sysvals.vprint('   kernel resume end: %f' % self.tKernRes)
 		sysvals.vprint('            test end: %f' % self.end)
 	def deviceChildrenAllPhases(self, devname):
@@ -1721,13 +1745,13 @@ class FTraceLine:
 		return len(str)/2
 	def debugPrint(self, info=''):
 		if self.isLeaf():
-			print(' -- %12.6f (depth=%02d): %s(); (%.3f us) %s' % (self.time, \
+			pprint(' -- %12.6f (depth=%02d): %s(); (%.3f us) %s' % (self.time, \
 				self.depth, self.name, self.length*1000000, info))
 		elif self.freturn:
-			print(' -- %12.6f (depth=%02d): %s} (%.3f us) %s' % (self.time, \
+			pprint(' -- %12.6f (depth=%02d): %s} (%.3f us) %s' % (self.time, \
 				self.depth, self.name, self.length*1000000, info))
 		else:
-			print(' -- %12.6f (depth=%02d): %s() { (%.3f us) %s' % (self.time, \
+			pprint(' -- %12.6f (depth=%02d): %s() { (%.3f us) %s' % (self.time, \
 				self.depth, self.name, self.length*1000000, info))
 	def startMarker(self):
 		# Is this the starting line of a suspend?
@@ -1868,7 +1892,7 @@ class FTraceCallGraph:
 			if warning and ('[make leaf]', line) not in info:
 				info.append(('', line))
 		if warning:
-			print 'WARNING: ftrace data missing, corrections made:'
+			pprint('WARNING: ftrace data missing, corrections made:')
 			for i in info:
 				t, obj = i
 				if obj:
@@ -1928,10 +1952,10 @@ class FTraceCallGraph:
 		id = 'task %s' % (self.pid)
 		window = '(%f - %f)' % (self.start, line.time)
 		if(self.depth < 0):
-			print('Data misalignment for '+id+\
+			pprint('Data misalignment for '+id+\
 				' (buffer overflow), ignoring this callback')
 		else:
-			print('Too much data for '+id+\
+			pprint('Too much data for '+id+\
 				' '+window+', ignoring this callback')
 	def slice(self, dev):
 		minicg = FTraceCallGraph(dev['pid'], self.sv)
@@ -1984,7 +2008,7 @@ class FTraceCallGraph:
 			elif l.isReturn():
 				if(l.depth not in stack):
 					if self.sv.verbose:
-						print 'Post Process Error: Depth missing'
+						pprint('Post Process Error: Depth missing')
 						l.debugPrint()
 					return False
 				# calculate call length from call/return lines
@@ -2001,7 +2025,7 @@ class FTraceCallGraph:
 			return True
 		elif(cnt < 0):
 			if self.sv.verbose:
-				print 'Post Process Error: Depth is less than 0'
+				pprint('Post Process Error: Depth is less than 0')
 			return False
 		# trace ended before call tree finished
 		return self.repair(cnt)
@@ -2060,20 +2084,20 @@ class FTraceCallGraph:
 			phase, myname = out
 			data.dmesg[phase]['list'][myname]['ftrace'] = self
 	def debugPrint(self, info=''):
-		print('%s pid=%d [%f - %f] %.3f us') % \
+		pprint('%s pid=%d [%f - %f] %.3f us' % \
 			(self.name, self.pid, self.start, self.end,
-			(self.end - self.start)*1000000)
+			(self.end - self.start)*1000000))
 		for l in self.list:
 			if l.isLeaf():
-				print('%f (%02d): %s(); (%.3f us)%s' % (l.time, \
+				pprint('%f (%02d): %s(); (%.3f us)%s' % (l.time, \
 					l.depth, l.name, l.length*1000000, info))
 			elif l.freturn:
-				print('%f (%02d): %s} (%.3f us)%s' % (l.time, \
+				pprint('%f (%02d): %s} (%.3f us)%s' % (l.time, \
 					l.depth, l.name, l.length*1000000, info))
 			else:
-				print('%f (%02d): %s() { (%.3f us)%s' % (l.time, \
+				pprint('%f (%02d): %s() { (%.3f us)%s' % (l.time, \
 					l.depth, l.name, l.length*1000000, info))
-		print(' ')
+		pprint(' ')
 
 class DevItem:
 	def __init__(self, test, phase, dev):
@@ -2658,7 +2682,8 @@ def parseTraceLog(live=False):
 		doError('%s does not exist' % sysvals.ftracefile)
 	if not live:
 		sysvals.setupAllKprobes()
-	krescalls = ['pm_notifier_call_chain', 'pm_restore_console']
+	ksuscalls = ['pm_prepare_console']
+	krescalls = ['pm_restore_console']
 	tracewatch = []
 	if sysvals.usekprobes:
 		tracewatch += ['sync_filesystems', 'freeze_processes', 'syscore_suspend',
@@ -2738,6 +2763,7 @@ def parseTraceLog(live=False):
 			testruns.append(testrun)
 			tp.parseStamp(data, sysvals)
 			data.setStart(t.time)
+			data.first_suspend_prepare = True
 			phase = data.setPhase('suspend_prepare', t.time, True)
 			continue
 		if(not data):
@@ -2797,11 +2823,12 @@ def parseTraceLog(live=False):
 					continue
 				# suspend_prepare start
 				elif(re.match('dpm_prepare\[.*', t.name)):
-					phase = 'suspend_prepare'
-					if not isbegin:
-						data.setPhase(phase, t.time, isbegin)
-					if isbegin and data.tKernSus == 0:
-						data.tKernSus = t.time
+					if isbegin and data.first_suspend_prepare:
+						data.first_suspend_prepare = False
+						if data.tKernSus == 0:
+							data.tKernSus = t.time
+						continue
+					phase = data.setPhase('suspend_prepare', t.time, isbegin)
 					continue
 				# suspend start
 				elif(re.match('dpm_suspend\[.*', t.name)):
@@ -2826,11 +2853,11 @@ def parseTraceLog(live=False):
 					else:
 						phase = data.setPhase('resume_machine', t.time, True)
 						if(sysvals.suspendmode in ['mem', 'disk']):
-							if 'suspend_machine' in data.dmesg:
-								data.dmesg['suspend_machine']['end'] = t.time
+							susp = phase.replace('resume', 'suspend')
+							if susp in data.dmesg:
+								data.dmesg[susp]['end'] = t.time
 							data.tSuspended = t.time
-						if data.tResumed == 0:
-							data.tResumed = t.time
+						data.tResumed = t.time
 					continue
 				# resume_noirq start
 				elif(re.match('dpm_resume_noirq\[.*', t.name)):
@@ -2911,6 +2938,9 @@ def parseTraceLog(live=False):
 					'cdata': kprobedata,
 					'proc': m_proc,
 				})
+				# start of kernel resume
+				if(phase == 'suspend_prepare' and kprobename in ksuscalls):
+					data.tKernSus = t.time
 			elif(t.freturn):
 				if(key not in tp.ktemp) or len(tp.ktemp[key]) < 1:
 					continue
@@ -2962,6 +2992,14 @@ def parseTraceLog(live=False):
 	if sysvals.usedevsrc or sysvals.useprocmon:
 		sysvals.mixedphaseheight = False
 
+	# expand phase boundaries so there are no gaps
+	for data in testdata:
+		lp = data.sortedPhases()[0]
+		for p in data.sortedPhases():
+			if(p != lp and not ('machine' in p and 'machine' in lp)):
+				data.dmesg[lp]['end'] = data.dmesg[p]['start']
+			lp = p
+
 	for i in range(len(testruns)):
 		test = testruns[i]
 		data = test.data
@@ -3044,7 +3082,7 @@ def parseTraceLog(live=False):
 		for p in sorted(phasedef, key=lambda k:phasedef[k]['order']):
 			if p not in data.dmesg:
 				if not terr:
-					print 'TEST%s FAILED: %s failed in %s phase' % (tn, sysvals.suspendmode, lp)
+					pprint('TEST%s FAILED: %s failed in %s phase' % (tn, sysvals.suspendmode, lp))
 					terr = '%s%s failed in %s phase' % (sysvals.suspendmode, tn, lp)
 					error.append(terr)
 					if data.tSuspended == 0:
@@ -3055,14 +3093,9 @@ def parseTraceLog(live=False):
 				sysvals.vprint('WARNING: phase "%s" is missing!' % p)
 			lp = p
 		if not terr and data.enterfail:
-			print 'test%s FAILED: enter %s failed with %s' % (tn, sysvals.suspendmode, data.enterfail)
+			pprint('test%s FAILED: enter %s failed with %s' % (tn, sysvals.suspendmode, data.enterfail))
 			terr = 'test%s failed to enter %s mode' % (tn, sysvals.suspendmode)
 			error.append(terr)
-		lp = data.sortedPhases()[0]
-		for p in data.sortedPhases():
-			if(p != lp and not ('machine' in p and 'machine' in lp)):
-				data.dmesg[lp]['end'] = data.dmesg[p]['start']
-			lp = p
 		if data.tSuspended == 0:
 			data.tSuspended = data.tKernRes
 		if data.tResumed == 0:
@@ -3151,7 +3184,7 @@ def loadKernelLog():
 	if data:
 		testruns.append(data)
 	if len(testruns) < 1:
-		print('ERROR: dmesg log has no suspend/resume data: %s' \
+		pprint('ERROR: dmesg log has no suspend/resume data: %s' \
 			% sysvals.dmesgfile)
 
 	# fix lines with same timestamp/function with the call and return swapped
@@ -3405,7 +3438,7 @@ def parseKernelLog(data):
 	for p in sorted(phasedef, key=lambda k:phasedef[k]['order']):
 		if p not in data.dmesg:
 			if not terr:
-				print 'TEST FAILED: %s failed in %s phase' % (sysvals.suspendmode, lp)
+				pprint('TEST FAILED: %s failed in %s phase' % (sysvals.suspendmode, lp))
 				terr = '%s failed in %s phase' % (sysvals.suspendmode, lp)
 				if data.tSuspended == 0:
 					data.tSuspended = data.dmesg[lp]['end']
@@ -3503,7 +3536,7 @@ def addCallgraphs(sv, hf, data):
 #	 Create summary html file for a series of tests
 # Arguments:
 #	 testruns: array of Data objects from parseTraceLog
-def createHTMLSummarySimple(testruns, htmlfile, folder):
+def createHTMLSummarySimple(testruns, htmlfile, title):
 	# write the html header first (html head, css code, up to body start)
 	html = '<!DOCTYPE html>\n<html>\n<head>\n\
 	<meta http-equiv="content-type" content="text/html; charset=UTF-8">\n\
@@ -3583,7 +3616,7 @@ def createHTMLSummarySimple(testruns, htmlfile, folder):
 	for ilk in sorted(cnt, reverse=True):
 		if cnt[ilk] > 0:
 			desc.append('%d %s' % (cnt[ilk], ilk))
-	html += '<div class="stamp">%s (%d tests: %s)</div>\n' % (folder, len(testruns), ', '.join(desc))
+	html += '<div class="stamp">%s (%d tests: %s)</div>\n' % (title, len(testruns), ', '.join(desc))
 	th = '\t<th>{0}</th>\n'
 	td = '\t<td>{0}</td>\n'
 	tdh = '\t<td{1}>{0}</td>\n'
@@ -3685,7 +3718,7 @@ def ordinal(value):
 #	 True if the html file was created, false if it failed
 def createHTML(testruns, testfail):
 	if len(testruns) < 1:
-		print('ERROR: Not enough test data to build a timeline')
+		pprint('ERROR: Not enough test data to build a timeline')
 		return
 
 	kerror = False
@@ -4535,18 +4568,18 @@ def setRuntimeSuspend(before=True):
 			sv.rstgt, sv.rsval, sv.rsdir = 'on', 'auto', 'enabled'
 		else:
 			sv.rstgt, sv.rsval, sv.rsdir = 'auto', 'on', 'disabled'
-		print('CONFIGURING RUNTIME SUSPEND...')
+		pprint('CONFIGURING RUNTIME SUSPEND...')
 		sv.rslist = deviceInfo(sv.rstgt)
 		for i in sv.rslist:
 			sv.setVal(sv.rsval, i)
-		print('runtime suspend %s on all devices (%d changed)' % (sv.rsdir, len(sv.rslist)))
-		print('waiting 5 seconds...')
+		pprint('runtime suspend %s on all devices (%d changed)' % (sv.rsdir, len(sv.rslist)))
+		pprint('waiting 5 seconds...')
 		time.sleep(5)
 	else:
 		# runtime suspend re-enable or re-disable
 		for i in sv.rslist:
 			sv.setVal(sv.rstgt, i)
-		print('runtime suspend settings restored on %d devices' % len(sv.rslist))
+		pprint('runtime suspend settings restored on %d devices' % len(sv.rslist))
 
 # Function: executeSuspend
 # Description:
@@ -4559,17 +4592,17 @@ def executeSuspend():
 	battery = True if getBattery() else False
 	# run these commands to prepare the system for suspend
 	if sysvals.display:
-		print('SET DISPLAY TO %s' % sysvals.display.upper())
+		pprint('SET DISPLAY TO %s' % sysvals.display.upper())
 		displayControl(sysvals.display)
 		time.sleep(1)
 	if sysvals.sync:
-		print('SYNCING FILESYSTEMS')
+		pprint('SYNCING FILESYSTEMS')
 		call('sync', shell=True)
 	# mark the start point in the kernel ring buffer just as we start
 	sysvals.initdmesg()
 	# start ftrace
 	if(sysvals.usecallgraph or sysvals.usetraceevents):
-		print('START TRACING')
+		pprint('START TRACING')
 		sysvals.fsetVal('1', 'tracing_on')
 		if sysvals.useprocmon:
 			pm.start()
@@ -4582,16 +4615,16 @@ def executeSuspend():
 			sysvals.fsetVal('WAIT END', 'trace_marker')
 		# start message
 		if sysvals.testcommand != '':
-			print('COMMAND START')
+			pprint('COMMAND START')
 		else:
 			if(sysvals.rtcwake):
-				print('SUSPEND START')
+				pprint('SUSPEND START')
 			else:
-				print('SUSPEND START (press a key to resume)')
+				pprint('SUSPEND START (press a key to resume)')
 		bat1 = getBattery() if battery else False
 		# set rtcwake
 		if(sysvals.rtcwake):
-			print('will issue an rtcwake in %d seconds' % sysvals.rtcwaketime)
+			pprint('will issue an rtcwake in %d seconds' % sysvals.rtcwaketime)
 			sysvals.rtcWakeAlarmOn()
 		# start of suspend trace marker
 		if(sysvals.usecallgraph or sysvals.usetraceevents):
@@ -4614,6 +4647,11 @@ def executeSuspend():
 				pf = open(sysvals.mempowerfile, 'w')
 				pf.write(sysvals.memmode)
 				pf.close()
+			if sysvals.diskmode and os.path.exists(sysvals.diskpowerfile):
+				mode = 'disk'
+				pf = open(sysvals.diskpowerfile, 'w')
+				pf.write(sysvals.diskmode)
+				pf.close()
 			pf = open(sysvals.powerfile, 'w')
 			pf.write(mode)
 			# execution will pause here
@@ -4629,7 +4667,7 @@ def executeSuspend():
 			time.sleep(sysvals.postdelay/1000.0)
 			sysvals.fsetVal('WAIT END', 'trace_marker')
 		# return from suspend
-		print('RESUME COMPLETE')
+		pprint('RESUME COMPLETE')
 		if(sysvals.usecallgraph or sysvals.usetraceevents):
 			sysvals.fsetVal('RESUME COMPLETE', 'trace_marker')
 		if(sysvals.suspendmode == 'mem' or sysvals.suspendmode == 'command'):
@@ -4644,11 +4682,11 @@ def executeSuspend():
 			pm.stop()
 		sysvals.fsetVal('0', 'tracing_on')
 	# grab a copy of the dmesg output
-	print('CAPTURING DMESG')
+	pprint('CAPTURING DMESG')
 	sysvals.getdmesg(testdata)
 	# grab a copy of the ftrace output
 	if(sysvals.usecallgraph or sysvals.usetraceevents):
-		print('CAPTURING TRACE')
+		pprint('CAPTURING TRACE')
 		op = sysvals.writeDatafileHeader(sysvals.ftracefile, testdata)
 		fp = open(tp+'trace', 'r')
 		for line in fp:
@@ -4692,15 +4730,15 @@ def yesno(val):
 #	 a list of USB device names to sysvals for better timeline readability
 def deviceInfo(output=''):
 	if not output:
-		print('LEGEND')
-		print('---------------------------------------------------------------------------------------------')
-		print('  A = async/sync PM queue (A/S)               C = runtime active children')
-		print('  R = runtime suspend enabled/disabled (E/D)  rACTIVE = runtime active (min/sec)')
-		print('  S = runtime status active/suspended (A/S)   rSUSPEND = runtime suspend (min/sec)')
-		print('  U = runtime usage count')
-		print('---------------------------------------------------------------------------------------------')
-		print('DEVICE                     NAME                       A R S U C    rACTIVE   rSUSPEND')
-		print('---------------------------------------------------------------------------------------------')
+		pprint('LEGEND\n'\
+		'---------------------------------------------------------------------------------------------\n'\
+		'  A = async/sync PM queue (A/S)               C = runtime active children\n'\
+		'  R = runtime suspend enabled/disabled (E/D)  rACTIVE = runtime active (min/sec)\n'\
+		'  S = runtime status active/suspended (A/S)   rSUSPEND = runtime suspend (min/sec)\n'\
+		'  U = runtime usage count\n'\
+		'---------------------------------------------------------------------------------------------\n'\
+		'DEVICE                     NAME                       A R S U C    rACTIVE   rSUSPEND\n'\
+		'---------------------------------------------------------------------------------------------')
 
 	res = []
 	tgtval = 'runtime_status'
@@ -4889,6 +4927,11 @@ def getModes():
 		fp.close()
 		if 'mem' in modes and not deep:
 			modes.remove('mem')
+	if('disk' in modes and os.path.exists(sysvals.diskpowerfile)):
+		fp = open(sysvals.diskpowerfile, 'r')
+		for m in string.split(fp.read()):
+			modes.append('disk-%s' % m.strip('[]'))
+		fp.close()
 	return modes
 
 # Function: dmidecode
@@ -5037,16 +5080,21 @@ def displayControl(cmd):
 		xset = 'sudo -u %s %s' % (sysvals.sudouser, xset)
 	if cmd == 'init':
 		ret = call(xset.format('dpms 0 0 0'), shell=True)
-		ret = call(xset.format('s off'), shell=True)
+		if not ret:
+			ret = call(xset.format('s off'), shell=True)
 	elif cmd == 'reset':
 		ret = call(xset.format('s reset'), shell=True)
 	elif cmd in ['on', 'off', 'standby', 'suspend']:
 		b4 = displayControl('stat')
 		ret = call(xset.format('dpms force %s' % cmd), shell=True)
-		curr = displayControl('stat')
-		sysvals.vprint('Display Switched: %s -> %s' % (b4, curr))
-		if curr != cmd:
-			sysvals.vprint('WARNING: Display failed to change to %s' % cmd)
+		if not ret:
+			curr = displayControl('stat')
+			sysvals.vprint('Display Switched: %s -> %s' % (b4, curr))
+			if curr != cmd:
+				sysvals.vprint('WARNING: Display failed to change to %s' % cmd)
+		if ret:
+			sysvals.vprint('WARNING: Display failed to change to %s with xset' % cmd)
+			return ret
 	elif cmd == 'stat':
 		fp = Popen(xset.format('q').split(' '), stdout=PIPE).stdout
 		ret = 'unknown'
@@ -5102,18 +5150,19 @@ def getFPDT(output):
 
 	table = struct.unpack('4sIBB6s8sI4sI', buf[0:36])
 	if(output):
-		print('')
-		print('Firmware Performance Data Table (%s)' % table[0])
-		print('                  Signature : %s' % table[0])
-		print('               Table Length : %u' % table[1])
-		print('                   Revision : %u' % table[2])
-		print('                   Checksum : 0x%x' % table[3])
-		print('                     OEM ID : %s' % table[4])
-		print('               OEM Table ID : %s' % table[5])
-		print('               OEM Revision : %u' % table[6])
-		print('                 Creator ID : %s' % table[7])
-		print('           Creator Revision : 0x%x' % table[8])
-		print('')
+		pprint('\n'\
+		'Firmware Performance Data Table (%s)\n'\
+		'                  Signature : %s\n'\
+		'               Table Length : %u\n'\
+		'                   Revision : %u\n'\
+		'                   Checksum : 0x%x\n'\
+		'                     OEM ID : %s\n'\
+		'               OEM Table ID : %s\n'\
+		'               OEM Revision : %u\n'\
+		'                 Creator ID : %s\n'\
+		'           Creator Revision : 0x%x\n'\
+		'' % (table[0], table[0], table[1], table[2], table[3],
+			table[4], table[5], table[6], table[7], table[8]))
 
 	if(table[0] != 'FPDT'):
 		if(output):
@@ -5139,22 +5188,24 @@ def getFPDT(output):
 			first = fp.read(8)
 		except:
 			if(output):
-				print('Bad address 0x%x in %s' % (addr, sysvals.mempath))
+				pprint('Bad address 0x%x in %s' % (addr, sysvals.mempath))
 			return [0, 0]
 		rechead = struct.unpack('4sI', first)
 		recdata = fp.read(rechead[1]-8)
 		if(rechead[0] == 'FBPT'):
 			record = struct.unpack('HBBIQQQQQ', recdata)
 			if(output):
-				print('%s (%s)' % (rectype[header[0]], rechead[0]))
-				print('                  Reset END : %u ns' % record[4])
-				print('  OS Loader LoadImage Start : %u ns' % record[5])
-				print(' OS Loader StartImage Start : %u ns' % record[6])
-				print('     ExitBootServices Entry : %u ns' % record[7])
-				print('      ExitBootServices Exit : %u ns' % record[8])
+				pprint('%s (%s)\n'\
+				'                  Reset END : %u ns\n'\
+				'  OS Loader LoadImage Start : %u ns\n'\
+				' OS Loader StartImage Start : %u ns\n'\
+				'     ExitBootServices Entry : %u ns\n'\
+				'      ExitBootServices Exit : %u ns'\
+				'' % (rectype[header[0]], rechead[0], record[4], record[5],
+					record[6], record[7], record[8]))
 		elif(rechead[0] == 'S3PT'):
 			if(output):
-				print('%s (%s)' % (rectype[header[0]], rechead[0]))
+				pprint('%s (%s)' % (rectype[header[0]], rechead[0]))
 			j = 0
 			while(j < len(recdata)):
 				prechead = struct.unpack('HBB', recdata[j:j+4])
@@ -5164,27 +5215,26 @@ def getFPDT(output):
 					record = struct.unpack('IIQQ', recdata[j:j+prechead[1]])
 					fwData[1] = record[2]
 					if(output):
-						print('    %s' % prectype[prechead[0]])
-						print('               Resume Count : %u' % \
-							record[1])
-						print('                 FullResume : %u ns' % \
-							record[2])
-						print('              AverageResume : %u ns' % \
-							record[3])
+						pprint('    %s\n'\
+						'               Resume Count : %u\n'\
+						'                 FullResume : %u ns\n'\
+						'              AverageResume : %u ns'\
+						'' % (prectype[prechead[0]], record[1],
+								record[2], record[3]))
 				elif(prechead[0] == 1):
 					record = struct.unpack('QQ', recdata[j+4:j+prechead[1]])
 					fwData[0] = record[1] - record[0]
 					if(output):
-						print('    %s' % prectype[prechead[0]])
-						print('               SuspendStart : %u ns' % \
-							record[0])
-						print('                 SuspendEnd : %u ns' % \
-							record[1])
-						print('                SuspendTime : %u ns' % \
-							fwData[0])
+						pprint('    %s\n'\
+						'               SuspendStart : %u ns\n'\
+						'                 SuspendEnd : %u ns\n'\
+						'                SuspendTime : %u ns'\
+						'' % (prectype[prechead[0]], record[0],
+								record[1], fwData[0]))
+
 				j += prechead[1]
 		if(output):
-			print('')
+			pprint('')
 		i += header[1]
 	fp.close()
 	return fwData
@@ -5198,22 +5248,22 @@ def getFPDT(output):
 def statusCheck(probecheck=False):
 	status = ''
 
-	print('Checking this system (%s)...' % platform.node())
+	pprint('Checking this system (%s)...' % platform.node())
 
 	# check we have root access
 	res = sysvals.colorText('NO (No features of this tool will work!)')
 	if(sysvals.rootCheck(False)):
 		res = 'YES'
-	print('    have root access: %s' % res)
+	pprint('    have root access: %s' % res)
 	if(res != 'YES'):
-		print('    Try running this script with sudo')
+		pprint('    Try running this script with sudo')
 		return 'missing root access'
 
 	# check sysfs is mounted
 	res = sysvals.colorText('NO (No features of this tool will work!)')
 	if(os.path.exists(sysvals.powerfile)):
 		res = 'YES'
-	print('    is sysfs mounted: %s' % res)
+	pprint('    is sysfs mounted: %s' % res)
 	if(res != 'YES'):
 		return 'sysfs is missing'
 
@@ -5225,10 +5275,10 @@ def statusCheck(probecheck=False):
 			res = 'YES'
 		else:
 			status = '%s mode is not supported' % sysvals.suspendmode
-		print('    is "%s" a valid power mode: %s' % (sysvals.suspendmode, res))
+		pprint('    is "%s" a valid power mode: %s' % (sysvals.suspendmode, res))
 		if(res == 'NO'):
-			print('      valid power modes are: %s' % modes)
-			print('      please choose one with -m')
+			pprint('      valid power modes are: %s' % modes)
+			pprint('      please choose one with -m')
 
 	# check if ftrace is available
 	res = sysvals.colorText('NO')
@@ -5237,7 +5287,7 @@ def statusCheck(probecheck=False):
 		res = 'YES'
 	elif(sysvals.usecallgraph):
 		status = 'ftrace is not properly supported'
-	print('    is ftrace supported: %s' % res)
+	pprint('    is ftrace supported: %s' % res)
 
 	# check if kprobes are available
 	res = sysvals.colorText('NO')
@@ -5246,7 +5296,7 @@ def statusCheck(probecheck=False):
 		res = 'YES'
 	else:
 		sysvals.usedevsrc = False
-	print('    are kprobes supported: %s' % res)
+	pprint('    are kprobes supported: %s' % res)
 
 	# what data source are we using
 	res = 'DMESG'
@@ -5257,7 +5307,7 @@ def statusCheck(probecheck=False):
 				sysvals.usetraceevents = False
 		if(sysvals.usetraceevents):
 			res = 'FTRACE (all trace events found)'
-	print('    timeline data source: %s' % res)
+	pprint('    timeline data source: %s' % res)
 
 	# check if rtcwake
 	res = sysvals.colorText('NO')
@@ -5265,7 +5315,7 @@ def statusCheck(probecheck=False):
 		res = 'YES'
 	elif(sysvals.rtcwake):
 		status = 'rtcwake is not properly supported'
-	print('    is rtcwake supported: %s' % res)
+	pprint('    is rtcwake supported: %s' % res)
 
 	if not probecheck:
 		return status
@@ -5290,7 +5340,7 @@ def statusCheck(probecheck=False):
 def doError(msg, help=False):
 	if(help == True):
 		printHelp()
-	print('ERROR: %s\n') % msg
+	pprint('ERROR: %s\n' % msg)
 	sysvals.outputResult({'error':msg})
 	sys.exit(1)
 
@@ -5333,7 +5383,7 @@ def getArgFloat(name, args, min, max, main=True):
 	return val
 
 def processData(live=False):
-	print('PROCESSING DATA')
+	pprint('PROCESSING DATA')
 	error = ''
 	if(sysvals.usetraceevents):
 		testruns, error = parseTraceLog(live)
@@ -5359,10 +5409,11 @@ def processData(live=False):
 			data.debugPrint()
 		sys.exit(0)
 	if len(testruns) < 1:
+		pprint('ERROR: Not enough test data to build a timeline')
 		return (testruns, {'error': 'timeline generation failed'})
 	sysvals.vprint('Creating the html timeline (%s)...' % sysvals.htmlfile)
 	createHTML(testruns, error)
-	print('DONE')
+	pprint('DONE')
 	data = testruns[0]
 	stamp = data.stamp
 	stamp['suspend'], stamp['resume'] = data.getTimeValues()
@@ -5516,7 +5567,7 @@ def data_from_html(file, outpath, devlist=False):
 def runSummary(subdir, local=True, genhtml=False):
 	inpath = os.path.abspath(subdir)
 	outpath = os.path.abspath('.') if local else inpath
-	print('Generating a summary of folder "%s"' % inpath)
+	pprint('Generating a summary of folder "%s"' % inpath)
 	if genhtml:
 		for dirname, dirnames, filenames in os.walk(subdir):
 			sysvals.dmesgfile = sysvals.ftracefile = sysvals.htmlfile = ''
@@ -5528,11 +5579,12 @@ def runSummary(subdir, local=True, genhtml=False):
 			sysvals.setOutputFile()
 			if sysvals.ftracefile and sysvals.htmlfile and \
 				not os.path.exists(sysvals.htmlfile):
-				print('FTRACE: %s' % sysvals.ftracefile)
+				pprint('FTRACE: %s' % sysvals.ftracefile)
 				if sysvals.dmesgfile:
-					print('DMESG : %s' % sysvals.dmesgfile)
+					pprint('DMESG : %s' % sysvals.dmesgfile)
 				rerunTest()
 	testruns = []
+	desc = {'host':[],'mode':[],'kernel':[]}
 	for dirname, dirnames, filenames in os.walk(subdir):
 		for filename in filenames:
 			if(not re.match('.*.html', filename)):
@@ -5541,9 +5593,16 @@ def runSummary(subdir, local=True, genhtml=False):
 			if(not data):
 				continue
 			testruns.append(data)
+			for key in desc:
+				if data[key] not in desc[key]:
+					desc[key].append(data[key])
 	outfile = os.path.join(outpath, 'summary.html')
-	print('Summary file: %s' % outfile)
-	createHTMLSummarySimple(testruns, outfile, inpath)
+	pprint('Summary file: %s' % outfile)
+	if len(desc['host']) == len(desc['mode']) == len(desc['kernel']) == 1:
+		title = '%s %s %s' % (desc['host'][0], desc['kernel'][0], desc['mode'][0])
+	else:
+		title = inpath
+	createHTMLSummarySimple(testruns, outfile, title)
 
 # Function: checkArgBool
 # Description:
@@ -5758,85 +5817,86 @@ def configFromFile(file):
 # Description:
 #	 print out the help text
 def printHelp():
-	print('')
-	print('%s v%s' % (sysvals.title, sysvals.version))
-	print('Usage: sudo sleepgraph <options> <commands>')
-	print('')
-	print('Description:')
-	print('  This tool is designed to assist kernel and OS developers in optimizing')
-	print('  their linux stack\'s suspend/resume time. Using a kernel image built')
-	print('  with a few extra options enabled, the tool will execute a suspend and')
-	print('  capture dmesg and ftrace data until resume is complete. This data is')
-	print('  transformed into a device timeline and an optional callgraph to give')
-	print('  a detailed view of which devices/subsystems are taking the most')
-	print('  time in suspend/resume.')
-	print('')
-	print('  If no specific command is given, the default behavior is to initiate')
-	print('  a suspend/resume and capture the dmesg/ftrace output as an html timeline.')
-	print('')
-	print('  Generates output files in subdirectory: suspend-yymmdd-HHMMSS')
-	print('   HTML output:                    <hostname>_<mode>.html')
-	print('   raw dmesg output:               <hostname>_<mode>_dmesg.txt')
-	print('   raw ftrace output:              <hostname>_<mode>_ftrace.txt')
-	print('')
-	print('Options:')
-	print('   -h           Print this help text')
-	print('   -v           Print the current tool version')
-	print('   -config fn   Pull arguments and config options from file fn')
-	print('   -verbose     Print extra information during execution and analysis')
-	print('   -m mode      Mode to initiate for suspend (default: %s)') % (sysvals.suspendmode)
-	print('   -o name      Overrides the output subdirectory name when running a new test')
-	print('                default: suspend-{date}-{time}')
-	print('   -rtcwake t   Wakeup t seconds after suspend, set t to "off" to disable (default: 15)')
-	print('   -addlogs     Add the dmesg and ftrace logs to the html output')
-	print('   -srgap       Add a visible gap in the timeline between sus/res (default: disabled)')
-	print('   -skiphtml    Run the test and capture the trace logs, but skip the timeline (default: disabled)')
-	print('   -result fn   Export a results table to a text file for parsing.')
-	print('  [testprep]')
-	print('   -sync        Sync the filesystems before starting the test')
-	print('   -rs on/off   Enable/disable runtime suspend for all devices, restore all after test')
-	print('   -display m   Change the display mode to m for the test (on/off/standby/suspend)')
-	print('  [advanced]')
-	print('   -gzip        Gzip the trace and dmesg logs to save space')
-	print('   -cmd {s}     Run the timeline over a custom command, e.g. "sync -d"')
-	print('   -proc        Add usermode process info into the timeline (default: disabled)')
-	print('   -dev         Add kernel function calls and threads to the timeline (default: disabled)')
-	print('   -x2          Run two suspend/resumes back to back (default: disabled)')
-	print('   -x2delay t   Include t ms delay between multiple test runs (default: 0 ms)')
-	print('   -predelay t  Include t ms delay before 1st suspend (default: 0 ms)')
-	print('   -postdelay t Include t ms delay after last resume (default: 0 ms)')
-	print('   -mindev ms   Discard all device blocks shorter than ms milliseconds (e.g. 0.001 for us)')
-	print('   -multi n d   Execute <n> consecutive tests at <d> seconds intervals. The outputs will')
-	print('                be created in a new subdirectory with a summary page.')
-	print('  [debug]')
-	print('   -f           Use ftrace to create device callgraphs (default: disabled)')
-	print('   -maxdepth N  limit the callgraph data to N call levels (default: 0=all)')
-	print('   -expandcg    pre-expand the callgraph data in the html output (default: disabled)')
-	print('   -fadd file   Add functions to be graphed in the timeline from a list in a text file')
-	print('   -filter "d1,d2,..." Filter out all but this comma-delimited list of device names')
-	print('   -mincg  ms   Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)')
-	print('   -cgphase P   Only show callgraph data for phase P (e.g. suspend_late)')
-	print('   -cgtest N    Only show callgraph data for test N (e.g. 0 or 1 in an x2 run)')
-	print('   -timeprec N  Number of significant digits in timestamps (0:S, [3:ms], 6:us)')
-	print('   -cgfilter S  Filter the callgraph output in the timeline')
-	print('   -cgskip file Callgraph functions to skip, off to disable (default: cgskip.txt)')
-	print('   -bufsize N   Set trace buffer size to N kilo-bytes (default: all of free memory)')
-	print('')
-	print('Other commands:')
-	print('   -modes       List available suspend modes')
-	print('   -status      Test to see if the system is enabled to run this tool')
-	print('   -fpdt        Print out the contents of the ACPI Firmware Performance Data Table')
-	print('   -battery     Print out battery info (if available)')
-	print('   -x<mode>     Test xset by toggling the given mode (on/off/standby/suspend)')
-	print('   -sysinfo     Print out system info extracted from BIOS')
-	print('   -devinfo     Print out the pm settings of all devices which support runtime suspend')
-	print('   -flist       Print the list of functions currently being captured in ftrace')
-	print('   -flistall    Print all functions capable of being captured in ftrace')
-	print('   -summary dir Create a summary of tests in this dir [-genhtml builds missing html]')
-	print('  [redo]')
-	print('   -ftrace ftracefile  Create HTML output using ftrace input (used with -dmesg)')
-	print('   -dmesg dmesgfile    Create HTML output using dmesg (used with -ftrace)')
-	print('')
+	pprint('\n%s v%s\n'\
+	'Usage: sudo sleepgraph <options> <commands>\n'\
+	'\n'\
+	'Description:\n'\
+	'  This tool is designed to assist kernel and OS developers in optimizing\n'\
+	'  their linux stack\'s suspend/resume time. Using a kernel image built\n'\
+	'  with a few extra options enabled, the tool will execute a suspend and\n'\
+	'  capture dmesg and ftrace data until resume is complete. This data is\n'\
+	'  transformed into a device timeline and an optional callgraph to give\n'\
+	'  a detailed view of which devices/subsystems are taking the most\n'\
+	'  time in suspend/resume.\n'\
+	'\n'\
+	'  If no specific command is given, the default behavior is to initiate\n'\
+	'  a suspend/resume and capture the dmesg/ftrace output as an html timeline.\n'\
+	'\n'\
+	'  Generates output files in subdirectory: suspend-yymmdd-HHMMSS\n'\
+	'   HTML output:                    <hostname>_<mode>.html\n'\
+	'   raw dmesg output:               <hostname>_<mode>_dmesg.txt\n'\
+	'   raw ftrace output:              <hostname>_<mode>_ftrace.txt\n'\
+	'\n'\
+	'Options:\n'\
+	'   -h           Print this help text\n'\
+	'   -v           Print the current tool version\n'\
+	'   -config fn   Pull arguments and config options from file fn\n'\
+	'   -verbose     Print extra information during execution and analysis\n'\
+	'   -m mode      Mode to initiate for suspend (default: %s)\n'\
+	'   -o name      Overrides the output subdirectory name when running a new test\n'\
+	'                default: suspend-{date}-{time}\n'\
+	'   -rtcwake t   Wakeup t seconds after suspend, set t to "off" to disable (default: 15)\n'\
+	'   -addlogs     Add the dmesg and ftrace logs to the html output\n'\
+	'   -srgap       Add a visible gap in the timeline between sus/res (default: disabled)\n'\
+	'   -skiphtml    Run the test and capture the trace logs, but skip the timeline (default: disabled)\n'\
+	'   -result fn   Export a results table to a text file for parsing.\n'\
+	'  [testprep]\n'\
+	'   -sync        Sync the filesystems before starting the test\n'\
+	'   -rs on/off   Enable/disable runtime suspend for all devices, restore all after test\n'\
+	'   -display m   Change the display mode to m for the test (on/off/standby/suspend)\n'\
+	'  [advanced]\n'\
+	'   -gzip        Gzip the trace and dmesg logs to save space\n'\
+	'   -cmd {s}     Run the timeline over a custom command, e.g. "sync -d"\n'\
+	'   -proc        Add usermode process info into the timeline (default: disabled)\n'\
+	'   -dev         Add kernel function calls and threads to the timeline (default: disabled)\n'\
+	'   -x2          Run two suspend/resumes back to back (default: disabled)\n'\
+	'   -x2delay t   Include t ms delay between multiple test runs (default: 0 ms)\n'\
+	'   -predelay t  Include t ms delay before 1st suspend (default: 0 ms)\n'\
+	'   -postdelay t Include t ms delay after last resume (default: 0 ms)\n'\
+	'   -mindev ms   Discard all device blocks shorter than ms milliseconds (e.g. 0.001 for us)\n'\
+	'   -multi n d   Execute <n> consecutive tests at <d> seconds intervals. The outputs will\n'\
+	'                be created in a new subdirectory with a summary page.\n'\
+	'  [debug]\n'\
+	'   -f           Use ftrace to create device callgraphs (default: disabled)\n'\
+	'   -maxdepth N  limit the callgraph data to N call levels (default: 0=all)\n'\
+	'   -expandcg    pre-expand the callgraph data in the html output (default: disabled)\n'\
+	'   -fadd file   Add functions to be graphed in the timeline from a list in a text file\n'\
+	'   -filter "d1,d2,..." Filter out all but this comma-delimited list of device names\n'\
+	'   -mincg  ms   Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)\n'\
+	'   -cgphase P   Only show callgraph data for phase P (e.g. suspend_late)\n'\
+	'   -cgtest N    Only show callgraph data for test N (e.g. 0 or 1 in an x2 run)\n'\
+	'   -timeprec N  Number of significant digits in timestamps (0:S, [3:ms], 6:us)\n'\
+	'   -cgfilter S  Filter the callgraph output in the timeline\n'\
+	'   -cgskip file Callgraph functions to skip, off to disable (default: cgskip.txt)\n'\
+	'   -bufsize N   Set trace buffer size to N kilo-bytes (default: all of free memory)\n'\
+	'   -devdump     Print out all the raw device data for each phase\n'\
+	'   -cgdump      Print out all the raw callgraph data\n'\
+	'\n'\
+	'Other commands:\n'\
+	'   -modes       List available suspend modes\n'\
+	'   -status      Test to see if the system is enabled to run this tool\n'\
+	'   -fpdt        Print out the contents of the ACPI Firmware Performance Data Table\n'\
+	'   -battery     Print out battery info (if available)\n'\
+	'   -x<mode>     Test xset by toggling the given mode (on/off/standby/suspend)\n'\
+	'   -sysinfo     Print out system info extracted from BIOS\n'\
+	'   -devinfo     Print out the pm settings of all devices which support runtime suspend\n'\
+	'   -flist       Print the list of functions currently being captured in ftrace\n'\
+	'   -flistall    Print all functions capable of being captured in ftrace\n'\
+	'   -summary dir Create a summary of tests in this dir [-genhtml builds missing html]\n'\
+	'  [redo]\n'\
+	'   -ftrace ftracefile  Create HTML output using ftrace input (used with -dmesg)\n'\
+	'   -dmesg dmesgfile    Create HTML output using dmesg (used with -ftrace)\n'\
+	'' % (sysvals.title, sysvals.version, sysvals.suspendmode))
 	return True
 
 # ----------------- MAIN --------------------
@@ -5866,7 +5926,7 @@ if __name__ == '__main__':
 			printHelp()
 			sys.exit(0)
 		elif(arg == '-v'):
-			print("Version %s" % sysvals.version)
+			pprint("Version %s" % sysvals.version)
 			sys.exit(0)
 		elif(arg == '-x2'):
 			sysvals.execcount = 2
@@ -5882,6 +5942,8 @@ if __name__ == '__main__':
 			sysvals.skiphtml = True
 		elif(arg == '-cgdump'):
 			sysvals.cgdump = True
+		elif(arg == '-devdump'):
+			sysvals.devdump = True
 		elif(arg == '-genhtml'):
 			genhtml = True
 		elif(arg == '-addlogs'):
@@ -6088,9 +6150,9 @@ if __name__ == '__main__':
 		elif(cmd == 'battery'):
 			out = getBattery()
 			if out:
-				print 'AC Connect    : %s\nBattery Charge: %d' % out
+				pprint('AC Connect    : %s\nBattery Charge: %d' % out)
 			else:
-				print 'no battery found'
+				pprint('no battery found')
 				ret = 1
 		elif(cmd == 'sysinfo'):
 			sysvals.printSystemInfo(True)
@@ -6108,7 +6170,7 @@ if __name__ == '__main__':
 			sysvals.verbose = True
 			ret = displayControl(cmd[1:])
 		elif(cmd == 'xstat'):
-			print 'Display Status: %s' % displayControl('stat').upper()
+			pprint('Display Status: %s' % displayControl('stat').upper())
 		sys.exit(ret)
 
 	# if instructed, re-analyze existing data files
@@ -6122,13 +6184,10 @@ if __name__ == '__main__':
 	if(error):
 		doError(error)
 
-	# extract mem modes and convert
+	# extract mem/disk extra modes and convert
 	mode = sysvals.suspendmode
-	if 'mem' == mode[:3]:
-		if '-' in mode:
-			memmode = mode.split('-')[-1]
-		else:
-			memmode = 'deep'
+	if mode.startswith('mem'):
+		memmode = mode.split('-', 1)[-1] if '-' in mode else 'deep'
 		if memmode == 'shallow':
 			mode = 'standby'
 		elif memmode ==  's2idle':
@@ -6137,6 +6196,9 @@ if __name__ == '__main__':
 			mode = 'mem'
 		sysvals.memmode = memmode
 		sysvals.suspendmode = mode
+	if mode.startswith('disk-'):
+		sysvals.diskmode = mode.split('-', 1)[-1]
+		sysvals.suspendmode = 'disk'
 
 	sysvals.systemInfo(dmidecode(sysvals.mempath))
 
@@ -6153,13 +6215,13 @@ if __name__ == '__main__':
 			os.mkdir(sysvals.outdir)
 		for i in range(sysvals.multitest['count']):
 			if(i != 0):
-				print('Waiting %d seconds...' % (sysvals.multitest['delay']))
+				pprint('Waiting %d seconds...' % (sysvals.multitest['delay']))
 				time.sleep(sysvals.multitest['delay'])
-			print('TEST (%d/%d) START' % (i+1, sysvals.multitest['count']))
+			pprint('TEST (%d/%d) START' % (i+1, sysvals.multitest['count']))
 			fmt = 'suspend-%y%m%d-%H%M%S'
 			sysvals.testdir = os.path.join(sysvals.outdir, datetime.now().strftime(fmt))
 			ret = runTest(i+1)
-			print('TEST (%d/%d) COMPLETE' % (i+1, sysvals.multitest['count']))
+			pprint('TEST (%d/%d) COMPLETE' % (i+1, sysvals.multitest['count']))
 			sysvals.logmsg = ''
 		if not sysvals.skiphtml:
 			runSummary(sysvals.outdir, False, False)
-- 
cgit v1.2.3


From 1b9caa10b31dda0866f4028e4bfb923fb6e4072f Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 3 Oct 2018 09:20:46 +0200
Subject: Revert "perf tools: Fix PMU term format max value calculation"

This reverts commit ac0e2cd555373ae6f8f3a3ad3fbbf5b6d1e7aaaa.

Michael reported an issue with oversized terms values assignment
and I noticed there was actually a misunderstanding of the max
value check in the past.

The above commit's changelog says:

  If bit 21 is set, there is parsing issues as below.

    $ perf stat -a -e uncore_qpi_0/event=0x200002,umask=0x8/
    event syntax error: '..pi_0/event=0x200002,umask=0x8/'
                                      \___ value too big for format, maximum is 511

But there's no issue there, because the event value is distributed
along the value defined by the format. Even if the format defines
separated bit, the value is treated as a continual number, which
should follow the format definition.

In above case it's 9-bit value with last bit separated:
  $ cat uncore_qpi_0/format/event
  config:0-7,21

Hence the value 0x200002 is correctly reported as format violation,
because it exceeds 9 bits. It should have been 0x102 instead, which
sets the 9th bit - the bit 21 of the format.

  $ perf stat -vv -a -e uncore_qpi_0/event=0x102,umask=0x8/
  Using CPUID GenuineIntel-6-2D
  ...
  ------------------------------------------------------------
  perf_event_attr:
    type                             10
    size                             112
    config                           0x200802
    sample_type                      IDENTIFIER
  ...

Reported-by: Michael Petlan <mpetlan@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Fixes: ac0e2cd55537 ("perf tools: Fix PMU term format max value calculation")
Link: http://lkml.kernel.org/r/20181003072046.29276-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/pmu.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index afd68524ffa9..7799788f662f 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -930,13 +930,14 @@ static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v,
 
 static __u64 pmu_format_max_value(const unsigned long *format)
 {
-	__u64 w = 0;
-	int fbit;
-
-	for_each_set_bit(fbit, format, PERF_PMU_FORMAT_BITS)
-		w |= (1ULL << fbit);
+	int w;
 
-	return w;
+	w = bitmap_weight(format, PERF_PMU_FORMAT_BITS);
+	if (!w)
+		return 0;
+	if (w < 64)
+		return (1ULL << w) - 1;
+	return -1;
 }
 
 /*
-- 
cgit v1.2.3


From 4b0aaacee51eb6592a03fdefd5ce97558518e291 Mon Sep 17 00:00:00 2001
From: "Shuah Khan (Samsung OSG)" <shuah@kernel.org>
Date: Fri, 5 Oct 2018 16:17:43 -0600
Subject: selftests: usbip: add wait after attach and before checking port
 status

Add sleep between attach and "usbip port" check to make sure status is
updated. Running attach and query back shows incorrect status.

Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 tools/testing/selftests/drivers/usb/usbip/usbip_test.sh | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh b/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh
index a72df93cf1f8..128f0ab24307 100755
--- a/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh
+++ b/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh
@@ -141,6 +141,10 @@ echo "Import devices from localhost - should work"
 src/usbip attach -r localhost -b $busid;
 echo "=============================================================="
 
+# Wait for sysfs file to be updated. Without this sleep, usbip port
+# shows no imported devices.
+sleep 3;
+
 echo "List imported devices - expect to see imported devices";
 src/usbip port;
 echo "=============================================================="
-- 
cgit v1.2.3


From 18a781daa93e67b795976353a6b5d120939c50bc Mon Sep 17 00:00:00 2001
From: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Date: Tue, 9 Oct 2018 10:04:51 +0900
Subject: tools/bpf: bpftool, split the function do_dump()

do_dump() function in bpftool/map.c has deep indentations. In order
to reduce deep indent, let's move element printing code out of
do_dump() into dump_map_elem() function.

Signed-off-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/map.c | 83 +++++++++++++++++++++++++++++--------------------
 1 file changed, 49 insertions(+), 34 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 6003e9598973..28d365435fea 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -658,6 +658,54 @@ static int do_show(int argc, char **argv)
 	return errno == ENOENT ? 0 : -1;
 }
 
+static int dump_map_elem(int fd, void *key, void *value,
+			 struct bpf_map_info *map_info, struct btf *btf,
+			 json_writer_t *btf_wtr)
+{
+	int num_elems = 0;
+
+	if (!bpf_map_lookup_elem(fd, key, value)) {
+		if (json_output) {
+			print_entry_json(map_info, key, value, btf);
+		} else {
+			if (btf) {
+				struct btf_dumper d = {
+					.btf = btf,
+					.jw = btf_wtr,
+					.is_plain_text = true,
+				};
+
+				do_dump_btf(&d, map_info, key, value);
+			} else {
+				print_entry_plain(map_info, key, value);
+			}
+			num_elems++;
+		}
+		return num_elems;
+	}
+
+	/* lookup error handling */
+	if (map_is_map_of_maps(map_info->type) ||
+	    map_is_map_of_progs(map_info->type))
+		return 0;
+
+	if (json_output) {
+		jsonw_name(json_wtr, "key");
+		print_hex_data_json(key, map_info->key_size);
+		jsonw_name(json_wtr, "value");
+		jsonw_start_object(json_wtr);
+		jsonw_string_field(json_wtr, "error",
+				   "can't lookup element");
+		jsonw_end_object(json_wtr);
+	} else {
+		p_info("can't lookup element with key: ");
+		fprint_hex(stderr, key, map_info->key_size, " ");
+		fprintf(stderr, "\n");
+	}
+
+	return 0;
+}
+
 static int do_dump(int argc, char **argv)
 {
 	struct bpf_map_info info = {};
@@ -713,40 +761,7 @@ static int do_dump(int argc, char **argv)
 				err = 0;
 			break;
 		}
-
-		if (!bpf_map_lookup_elem(fd, key, value)) {
-			if (json_output)
-				print_entry_json(&info, key, value, btf);
-			else
-				if (btf) {
-					struct btf_dumper d = {
-						.btf = btf,
-						.jw = btf_wtr,
-						.is_plain_text = true,
-					};
-
-					do_dump_btf(&d, &info, key, value);
-				} else {
-					print_entry_plain(&info, key, value);
-				}
-			num_elems++;
-		} else if (!map_is_map_of_maps(info.type) &&
-			   !map_is_map_of_progs(info.type)) {
-			if (json_output) {
-				jsonw_name(json_wtr, "key");
-				print_hex_data_json(key, info.key_size);
-				jsonw_name(json_wtr, "value");
-				jsonw_start_object(json_wtr);
-				jsonw_string_field(json_wtr, "error",
-						   "can't lookup element");
-				jsonw_end_object(json_wtr);
-			} else {
-				p_info("can't lookup element with key: ");
-				fprint_hex(stderr, key, info.key_size, " ");
-				fprintf(stderr, "\n");
-			}
-		}
-
+		num_elems += dump_map_elem(fd, key, value, &info, btf, btf_wtr);
 		prev_key = key;
 	}
 
-- 
cgit v1.2.3


From 8ec92dc22e0e3460cfd29263731c6214d283ea28 Mon Sep 17 00:00:00 2001
From: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Date: Tue, 9 Oct 2018 10:04:52 +0900
Subject: tools/bpf: bpftool, print strerror when map lookup error occurs

Since map lookup error can be ENOENT or EOPNOTSUPP, let's print
strerror() as error message in normal and JSON output.

This patch adds helper function print_entry_error() to print
entry from lookup error occurs

Example: Following example dumps a map which does not support lookup.

Output before:
root# bpftool map -jp dump id 40
[
    "key": ["0x0a","0x00","0x00","0x00"
    ],
    "value": {
        "error": "can\'t lookup element"
    },
    "key": ["0x0b","0x00","0x00","0x00"
    ],
    "value": {
        "error": "can\'t lookup element"
    }
]

root# bpftool map dump id 40
can't lookup element with key:
0a 00 00 00
can't lookup element with key:
0b 00 00 00
Found 0 elements

Output after changes:
root# bpftool map dump -jp  id 45
[
    "key": ["0x0a","0x00","0x00","0x00"
    ],
    "value": {
        "error": "Operation not supported"
    },
    "key": ["0x0b","0x00","0x00","0x00"
    ],
    "value": {
        "error": "Operation not supported"
    }
]

root# bpftool map dump id 45
key:
0a 00 00 00
value:
Operation not supported
key:
0b 00 00 00
value:
Operation not supported
Found 0 elements

Signed-off-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/map.c | 29 ++++++++++++++++++++++++-----
 1 file changed, 24 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 28d365435fea..9f5de48f8a99 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -336,6 +336,25 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
 	jsonw_end_object(json_wtr);
 }
 
+static void print_entry_error(struct bpf_map_info *info, unsigned char *key,
+			      const char *value)
+{
+	int value_size = strlen(value);
+	bool single_line, break_names;
+
+	break_names = info->key_size > 16 || value_size > 16;
+	single_line = info->key_size + value_size <= 24 && !break_names;
+
+	printf("key:%c", break_names ? '\n' : ' ');
+	fprint_hex(stdout, key, info->key_size, " ");
+
+	printf(single_line ? "  " : "\n");
+
+	printf("value:%c%s", break_names ? '\n' : ' ', value);
+
+	printf("\n");
+}
+
 static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
 			      unsigned char *value)
 {
@@ -663,6 +682,7 @@ static int dump_map_elem(int fd, void *key, void *value,
 			 json_writer_t *btf_wtr)
 {
 	int num_elems = 0;
+	int lookup_errno;
 
 	if (!bpf_map_lookup_elem(fd, key, value)) {
 		if (json_output) {
@@ -685,6 +705,8 @@ static int dump_map_elem(int fd, void *key, void *value,
 	}
 
 	/* lookup error handling */
+	lookup_errno = errno;
+
 	if (map_is_map_of_maps(map_info->type) ||
 	    map_is_map_of_progs(map_info->type))
 		return 0;
@@ -694,13 +716,10 @@ static int dump_map_elem(int fd, void *key, void *value,
 		print_hex_data_json(key, map_info->key_size);
 		jsonw_name(json_wtr, "value");
 		jsonw_start_object(json_wtr);
-		jsonw_string_field(json_wtr, "error",
-				   "can't lookup element");
+		jsonw_string_field(json_wtr, "error", strerror(lookup_errno));
 		jsonw_end_object(json_wtr);
 	} else {
-		p_info("can't lookup element with key: ");
-		fprint_hex(stderr, key, map_info->key_size, " ");
-		fprintf(stderr, "\n");
+		print_entry_error(map_info, key, strerror(lookup_errno));
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 908142e61b2e9c2411e8bc4e5092a6ab06eca8e4 Mon Sep 17 00:00:00 2001
From: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Date: Tue, 9 Oct 2018 10:04:53 +0900
Subject: selftests/bpf: test_verifier, change names of fixup maps

Currently fixup map are named like fixup_map1, fixup_map2, and so on.
As suggested by Alexei let's change change map names such that we can
identify map type by looking at the name.

This patch is basically a find and replace change:
fixup_map1  ->  fixup_map_hash_8b
fixup_map2  ->  fixup_map_hash_48b
fixup_map3  ->  fixup_map_hash_16b
fixup_map4  ->  fixup_map_array_48b

Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 380 ++++++++++++++--------------
 1 file changed, 190 insertions(+), 190 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index bc9cd8537467..65ae44c85d27 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -61,10 +61,10 @@ static bool unpriv_disabled = false;
 struct bpf_test {
 	const char *descr;
 	struct bpf_insn	insns[MAX_INSNS];
-	int fixup_map1[MAX_FIXUPS];
-	int fixup_map2[MAX_FIXUPS];
-	int fixup_map3[MAX_FIXUPS];
-	int fixup_map4[MAX_FIXUPS];
+	int fixup_map_hash_8b[MAX_FIXUPS];
+	int fixup_map_hash_48b[MAX_FIXUPS];
+	int fixup_map_hash_16b[MAX_FIXUPS];
+	int fixup_map_array_48b[MAX_FIXUPS];
 	int fixup_prog1[MAX_FIXUPS];
 	int fixup_prog2[MAX_FIXUPS];
 	int fixup_map_in_map[MAX_FIXUPS];
@@ -876,7 +876,7 @@ static struct bpf_test tests[] = {
 				     BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 2 },
+		.fixup_map_hash_8b = { 2 },
 		.errstr = "invalid indirect read from stack",
 		.result = REJECT,
 	},
@@ -1110,7 +1110,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "R0 invalid mem access 'map_value_or_null'",
 		.result = REJECT,
 	},
@@ -1127,7 +1127,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 4, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "misaligned value access",
 		.result = REJECT,
 		.flags = F_LOAD_WITH_STRICT_ALIGNMENT,
@@ -1147,7 +1147,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 1),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "R0 invalid mem access",
 		.errstr_unpriv = "R0 leaks addr",
 		.result = REJECT,
@@ -1237,7 +1237,7 @@ static struct bpf_test tests[] = {
 				     BPF_FUNC_map_delete_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 24 },
+		.fixup_map_hash_8b = { 24 },
 		.errstr_unpriv = "R1 pointer comparison",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -1391,7 +1391,7 @@ static struct bpf_test tests[] = {
 				    offsetof(struct __sk_buff, pkt_type)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.errstr = "different pointers",
 		.errstr_unpriv = "R1 pointer comparison",
 		.result = REJECT,
@@ -1414,7 +1414,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 			BPF_JMP_IMM(BPF_JA, 0, 0, -12),
 		},
-		.fixup_map1 = { 6 },
+		.fixup_map_hash_8b = { 6 },
 		.errstr = "different pointers",
 		.errstr_unpriv = "R1 pointer comparison",
 		.result = REJECT,
@@ -1438,7 +1438,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 			BPF_JMP_IMM(BPF_JA, 0, 0, -13),
 		},
-		.fixup_map1 = { 7 },
+		.fixup_map_hash_8b = { 7 },
 		.errstr = "different pointers",
 		.errstr_unpriv = "R1 pointer comparison",
 		.result = REJECT,
@@ -2575,7 +2575,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr_unpriv = "R4 leaks addr",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -2592,7 +2592,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "invalid indirect read from stack off -8+0 size 8",
 		.result = REJECT,
 	},
@@ -2894,7 +2894,7 @@ static struct bpf_test tests[] = {
 			BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -2934,7 +2934,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 1 },
+		.fixup_map_hash_8b = { 1 },
 		.errstr_unpriv = "R1 pointer comparison",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -4073,7 +4073,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 5 },
+		.fixup_map_hash_8b = { 5 },
 		.result_unpriv = ACCEPT,
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_XDP,
@@ -4089,7 +4089,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 1 },
+		.fixup_map_hash_8b = { 1 },
 		.result = REJECT,
 		.errstr = "invalid access to packet",
 		.prog_type = BPF_PROG_TYPE_XDP,
@@ -4117,7 +4117,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 11 },
+		.fixup_map_hash_8b = { 11 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
@@ -4139,7 +4139,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 7 },
+		.fixup_map_hash_8b = { 7 },
 		.result = REJECT,
 		.errstr = "invalid access to packet",
 		.prog_type = BPF_PROG_TYPE_XDP,
@@ -4161,7 +4161,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 6 },
+		.fixup_map_hash_8b = { 6 },
 		.result = REJECT,
 		.errstr = "invalid access to packet",
 		.prog_type = BPF_PROG_TYPE_XDP,
@@ -4184,7 +4184,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 5 },
+		.fixup_map_hash_8b = { 5 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -4199,7 +4199,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 1 },
+		.fixup_map_hash_8b = { 1 },
 		.result = REJECT,
 		.errstr = "invalid access to packet",
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
@@ -4227,7 +4227,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 11 },
+		.fixup_map_hash_8b = { 11 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -4249,7 +4249,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 7 },
+		.fixup_map_hash_8b = { 7 },
 		.result = REJECT,
 		.errstr = "invalid access to packet",
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
@@ -4271,7 +4271,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 6 },
+		.fixup_map_hash_8b = { 6 },
 		.result = REJECT,
 		.errstr = "invalid access to packet",
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
@@ -4555,7 +4555,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -4577,7 +4577,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -4601,7 +4601,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -4629,7 +4629,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -4649,7 +4649,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "invalid access to map value, value_size=48 off=48 size=8",
 		.result = REJECT,
 	},
@@ -4670,7 +4670,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 min value is outside of the array range",
 		.result = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -4692,7 +4692,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 unbounded memory access, make sure to bounds check any array access into a map",
 		.result = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -4717,7 +4717,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.errstr = "R0 unbounded memory access",
 		.result_unpriv = REJECT,
@@ -4744,7 +4744,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.errstr = "invalid access to map value, value_size=48 off=44 size=8",
 		.result_unpriv = REJECT,
@@ -4774,7 +4774,7 @@ static struct bpf_test tests[] = {
 				    offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3, 11 },
+		.fixup_map_hash_48b = { 3, 11 },
 		.errstr = "R0 pointer += pointer",
 		.result = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -4807,7 +4807,7 @@ static struct bpf_test tests[] = {
 			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 1 },
+		.fixup_map_hash_8b = { 1 },
 		.result = REJECT,
 		.errstr = "cannot pass map_type 1 into func bpf_get_local_storage",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
@@ -4922,7 +4922,7 @@ static struct bpf_test tests[] = {
 			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 1 },
+		.fixup_map_hash_8b = { 1 },
 		.result = REJECT,
 		.errstr = "cannot pass map_type 1 into func bpf_get_local_storage",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
@@ -5024,7 +5024,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
 	},
@@ -5045,7 +5045,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.errstr = "R4 pointer arithmetic on map_value_or_null",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
@@ -5066,7 +5066,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.errstr = "R4 pointer arithmetic on map_value_or_null",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
@@ -5087,7 +5087,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.errstr = "R4 pointer arithmetic on map_value_or_null",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
@@ -5113,7 +5113,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.result = REJECT,
 		.errstr = "R4 !read_ok",
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
@@ -5141,7 +5141,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS
 	},
@@ -5162,7 +5162,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 unbounded memory access",
 		.result = REJECT,
 		.errstr_unpriv = "R0 leaks addr",
@@ -5412,7 +5412,7 @@ static struct bpf_test tests[] = {
 				      offsetof(struct __sk_buff, cb[0])),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 2 },
+		.fixup_map_hash_8b = { 2 },
 		.errstr_unpriv = "R2 leaks addr into mem",
 		.result_unpriv = REJECT,
 		.result = REJECT,
@@ -5442,7 +5442,7 @@ static struct bpf_test tests[] = {
 				      offsetof(struct __sk_buff, cb[0])),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 1 },
+		.fixup_map_hash_8b = { 1 },
 		.errstr_unpriv = "R2 leaks addr into ctx",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -5464,7 +5464,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.errstr_unpriv = "R6 leaks addr into mem",
 		.result_unpriv = REJECT,
 		.result = ACCEPT,
@@ -5484,7 +5484,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5503,7 +5503,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5521,7 +5521,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_trace_printk),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "invalid access to map value, value_size=48 off=0 size=0",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5541,7 +5541,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "invalid access to map value, value_size=48 off=0 size=56",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5561,7 +5561,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R2 min value is negative",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5585,7 +5585,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5606,7 +5606,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5626,7 +5626,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_trace_printk),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "invalid access to map value, value_size=48 off=4 size=0",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5650,7 +5650,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "invalid access to map value, value_size=48 off=4 size=52",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5672,7 +5672,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R2 min value is negative",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5694,7 +5694,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R2 min value is negative",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5719,7 +5719,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5741,7 +5741,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5761,7 +5761,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_trace_printk),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R1 min value is outside of the array range",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5786,7 +5786,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "invalid access to map value, value_size=48 off=4 size=52",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5809,7 +5809,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R2 min value is negative",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5832,7 +5832,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R2 min value is negative",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5858,7 +5858,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5881,7 +5881,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5903,7 +5903,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_trace_printk),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R1 min value is outside of the array range",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5925,7 +5925,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R1 unbounded memory access",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5951,7 +5951,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "invalid access to map value, value_size=48 off=4 size=45",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -5975,7 +5975,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5998,7 +5998,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = REJECT,
 		.errstr = "R1 unbounded memory access",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6022,7 +6022,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6045,7 +6045,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = REJECT,
 		.errstr = "R1 unbounded memory access",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6070,7 +6070,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6094,7 +6094,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6118,7 +6118,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = REJECT,
 		.errstr = "R1 min value is negative",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6143,7 +6143,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6167,7 +6167,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6191,7 +6191,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = REJECT,
 		.errstr = "R1 min value is negative",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6210,7 +6210,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 8 },
+		.fixup_map_hash_16b = { 3, 8 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6230,7 +6230,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_update_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 10 },
+		.fixup_map_hash_16b = { 3, 10 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6250,8 +6250,8 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_update_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
-		.fixup_map3 = { 10 },
+		.fixup_map_hash_8b = { 3 },
+		.fixup_map_hash_16b = { 10 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=8 off=0 size=16",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6272,7 +6272,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 9 },
+		.fixup_map_hash_16b = { 3, 9 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6292,7 +6292,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 9 },
+		.fixup_map_hash_16b = { 3, 9 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=16 off=12 size=8",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6312,7 +6312,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 9 },
+		.fixup_map_hash_16b = { 3, 9 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=16 off=-4 size=8",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6334,7 +6334,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 10 },
+		.fixup_map_hash_16b = { 3, 10 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6355,7 +6355,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 10 },
+		.fixup_map_hash_16b = { 3, 10 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=16 off=12 size=8",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6376,7 +6376,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 10 },
+		.fixup_map_hash_16b = { 3, 10 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=16 off=-4 size=8",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6399,7 +6399,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 11 },
+		.fixup_map_hash_16b = { 3, 11 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6419,7 +6419,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 10 },
+		.fixup_map_hash_16b = { 3, 10 },
 		.result = REJECT,
 		.errstr = "R2 unbounded memory access, make sure to bounds check any array access into a map",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6442,7 +6442,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map3 = { 3, 11 },
+		.fixup_map_hash_16b = { 3, 11 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=16 off=9 size=8",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6464,7 +6464,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result = ACCEPT,
 		.result_unpriv = REJECT,
@@ -6485,7 +6485,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result = ACCEPT,
 		.result_unpriv = REJECT,
@@ -6502,7 +6502,7 @@ static struct bpf_test tests[] = {
 			BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R1 !read_ok",
 		.errstr = "R1 !read_ok",
 		.result = REJECT,
@@ -6536,7 +6536,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_7, -4, 24),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result = ACCEPT,
 		.result_unpriv = REJECT,
@@ -6564,7 +6564,7 @@ static struct bpf_test tests[] = {
 			BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 4),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result = ACCEPT,
 		.result_unpriv = REJECT,
@@ -6583,7 +6583,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 bitwise operator &= on pointer",
 		.result = REJECT,
 	},
@@ -6600,7 +6600,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 32-bit pointer arithmetic prohibited",
 		.result = REJECT,
 	},
@@ -6617,7 +6617,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 pointer arithmetic with /= operator",
 		.result = REJECT,
 	},
@@ -6634,7 +6634,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 pointer arithmetic prohibited",
 		.errstr = "invalid mem access 'inv'",
 		.result = REJECT,
@@ -6658,7 +6658,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 invalid mem access 'inv'",
 		.result = REJECT,
 	},
@@ -6681,7 +6681,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.result = ACCEPT,
 		.result_unpriv = REJECT,
@@ -6927,7 +6927,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -6953,7 +6953,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "invalid access to map value, value_size=48 off=0 size=49",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -6981,7 +6981,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -7008,7 +7008,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R1 min value is outside of the array range",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -7080,7 +7080,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_csum_diff),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -7105,7 +7105,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_csum_diff),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -7128,7 +7128,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_csum_diff),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -7209,7 +7209,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -7230,7 +7230,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -7250,7 +7250,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -7325,7 +7325,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 max value is outside of the array range",
 		.result = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -7355,7 +7355,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_REG(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr = "R0 max value is outside of the array range",
 		.result = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -7708,7 +7708,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -7732,7 +7732,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -7758,7 +7758,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -7783,7 +7783,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -7807,7 +7807,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 	},
 	{
@@ -7831,7 +7831,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -7877,7 +7877,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 	},
 	{
@@ -7902,7 +7902,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -7928,7 +7928,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 	},
 	{
@@ -7953,7 +7953,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -7980,7 +7980,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -8006,7 +8006,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -8035,7 +8035,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 	},
@@ -8065,7 +8065,7 @@ static struct bpf_test tests[] = {
 			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, -3),
 			BPF_JMP_IMM(BPF_JA, 0, 0, -7),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.errstr = "R0 invalid mem access 'inv'",
 		.result = REJECT,
 	},
@@ -8093,7 +8093,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "unbounded min value",
 		.result = REJECT,
 		.result_unpriv = REJECT,
@@ -8120,7 +8120,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "R0 max value is outside of the array range",
 		.result = REJECT,
 	},
@@ -8145,7 +8145,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
 		.result = REJECT,
 	},
@@ -8171,7 +8171,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT
 	},
 	{
@@ -8196,7 +8196,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "map_value pointer and 4294967295",
 		.result = REJECT
 	},
@@ -8222,7 +8222,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "R0 min value is outside of the array range",
 		.result = REJECT
 	},
@@ -8246,7 +8246,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.errstr = "value_size=8 off=1073741825",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
@@ -8271,7 +8271,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 4 },
+		.fixup_map_hash_8b = { 4 },
 		.errstr = "value 1073741823",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
@@ -8307,7 +8307,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT
 	},
 	{
@@ -8346,7 +8346,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		/* not actually fully unbounded, but the bound is very high */
 		.errstr = "R0 unbounded memory access",
 		.result = REJECT
@@ -8389,7 +8389,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		/* not actually fully unbounded, but the bound is very high */
 		.errstr = "R0 unbounded memory access",
 		.result = REJECT
@@ -8418,7 +8418,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT
 	},
 	{
@@ -8445,7 +8445,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "R0 max value is outside of the array range",
 		.result = REJECT
 	},
@@ -8475,7 +8475,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "R0 unbounded memory access",
 		.result = REJECT
 	},
@@ -8495,7 +8495,7 @@ static struct bpf_test tests[] = {
 			BPF_JMP_A(0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "map_value pointer and 2147483646",
 		.result = REJECT
 	},
@@ -8517,7 +8517,7 @@ static struct bpf_test tests[] = {
 			BPF_JMP_A(0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "pointer offset 1073741822",
 		.result = REJECT
 	},
@@ -8538,7 +8538,7 @@ static struct bpf_test tests[] = {
 			BPF_JMP_A(0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "pointer offset -1073741822",
 		.result = REJECT
 	},
@@ -8560,7 +8560,7 @@ static struct bpf_test tests[] = {
 			BPF_JMP_A(0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "map_value pointer and 1000000000000",
 		.result = REJECT
 	},
@@ -8580,7 +8580,7 @@ static struct bpf_test tests[] = {
 			BPF_JMP_A(0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 		.retval = POINTER_VALUE,
 		.result_unpriv = REJECT,
@@ -8601,7 +8601,7 @@ static struct bpf_test tests[] = {
 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = ACCEPT,
 		.retval = POINTER_VALUE,
 		.result_unpriv = REJECT,
@@ -8669,7 +8669,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 5 },
+		.fixup_map_hash_8b = { 5 },
 		.errstr = "variable stack read R2",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_LWT_IN,
@@ -8750,7 +8750,7 @@ static struct bpf_test tests[] = {
 				   offsetof(struct test_val, foo)),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 3 },
+		.fixup_map_hash_48b = { 3 },
 		.errstr_unpriv = "R0 leaks addr",
 		.errstr = "R0 unbounded memory access",
 		.result_unpriv = REJECT,
@@ -10284,7 +10284,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-		.fixup_map1 = { 16 },
+		.fixup_map_hash_8b = { 16 },
 		.result = REJECT,
 		.errstr = "R0 min value is outside of the array range",
 	},
@@ -11235,7 +11235,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(), /* return 0 */
 		},
 		.prog_type = BPF_PROG_TYPE_XDP,
-		.fixup_map1 = { 23 },
+		.fixup_map_hash_8b = { 23 },
 		.result = ACCEPT,
 	},
 	{
@@ -11290,7 +11290,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(), /* return 1 */
 		},
 		.prog_type = BPF_PROG_TYPE_XDP,
-		.fixup_map1 = { 23 },
+		.fixup_map_hash_8b = { 23 },
 		.result = ACCEPT,
 	},
 	{
@@ -11345,7 +11345,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(), /* return 1 */
 		},
 		.prog_type = BPF_PROG_TYPE_XDP,
-		.fixup_map1 = { 23 },
+		.fixup_map_hash_8b = { 23 },
 		.result = REJECT,
 		.errstr = "invalid read from stack off -16+0 size 8",
 	},
@@ -11417,7 +11417,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-		.fixup_map1 = { 12, 22 },
+		.fixup_map_hash_8b = { 12, 22 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=8 off=2 size=8",
 	},
@@ -11489,7 +11489,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-		.fixup_map1 = { 12, 22 },
+		.fixup_map_hash_8b = { 12, 22 },
 		.result = ACCEPT,
 	},
 	{
@@ -11560,7 +11560,7 @@ static struct bpf_test tests[] = {
 			BPF_JMP_IMM(BPF_JA, 0, 0, -8),
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-		.fixup_map1 = { 12, 22 },
+		.fixup_map_hash_8b = { 12, 22 },
 		.result = REJECT,
 		.errstr = "invalid access to map value, value_size=8 off=2 size=8",
 	},
@@ -11632,7 +11632,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-		.fixup_map1 = { 12, 22 },
+		.fixup_map_hash_8b = { 12, 22 },
 		.result = ACCEPT,
 	},
 	{
@@ -11703,7 +11703,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-		.fixup_map1 = { 12, 22 },
+		.fixup_map_hash_8b = { 12, 22 },
 		.result = REJECT,
 		.errstr = "R0 invalid mem access 'inv'",
 	},
@@ -12048,7 +12048,7 @@ static struct bpf_test tests[] = {
 			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 13 },
+		.fixup_map_hash_8b = { 13 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
@@ -12075,7 +12075,7 @@ static struct bpf_test tests[] = {
 				     BPF_FUNC_map_lookup_elem),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 6 },
+		.fixup_map_hash_48b = { 6 },
 		.errstr = "invalid indirect read from stack off -8+0 size 8",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_XDP,
@@ -12107,8 +12107,8 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-		.fixup_map2 = { 13 },
-		.fixup_map4 = { 16 },
+		.fixup_map_hash_48b = { 13 },
+		.fixup_map_array_48b = { 16 },
 		.result = ACCEPT,
 		.retval = 1,
 	},
@@ -12140,7 +12140,7 @@ static struct bpf_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.fixup_map_in_map = { 16 },
-		.fixup_map4 = { 13 },
+		.fixup_map_array_48b = { 13 },
 		.result = REJECT,
 		.errstr = "R0 invalid mem access 'map_ptr'",
 	},
@@ -12208,7 +12208,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_6, 0, 0xdead),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "R6 invalid mem access 'inv'",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -12232,7 +12232,7 @@ static struct bpf_test tests[] = {
 			BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -16),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.errstr = "invalid read from stack off -16+0 size 8",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -12354,7 +12354,7 @@ static struct bpf_test tests[] = {
 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 3),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map1 = { 3 },
+		.fixup_map_hash_8b = { 3 },
 		.result = REJECT,
 		.errstr = "misaligned value access off",
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
@@ -12464,7 +12464,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_get_stack),
 			BPF_EXIT_INSN(),
 		},
-		.fixup_map2 = { 4 },
+		.fixup_map_hash_48b = { 4 },
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -13511,10 +13511,10 @@ static char bpf_vlog[UINT_MAX >> 8];
 static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type,
 			  struct bpf_insn *prog, int *map_fds)
 {
-	int *fixup_map1 = test->fixup_map1;
-	int *fixup_map2 = test->fixup_map2;
-	int *fixup_map3 = test->fixup_map3;
-	int *fixup_map4 = test->fixup_map4;
+	int *fixup_map_hash_8b = test->fixup_map_hash_8b;
+	int *fixup_map_hash_48b = test->fixup_map_hash_48b;
+	int *fixup_map_hash_16b = test->fixup_map_hash_16b;
+	int *fixup_map_array_48b = test->fixup_map_array_48b;
 	int *fixup_prog1 = test->fixup_prog1;
 	int *fixup_prog2 = test->fixup_prog2;
 	int *fixup_map_in_map = test->fixup_map_in_map;
@@ -13528,40 +13528,40 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type,
 	 * for verifier and not do a runtime lookup, so the only thing
 	 * that really matters is value size in this case.
 	 */
-	if (*fixup_map1) {
+	if (*fixup_map_hash_8b) {
 		map_fds[0] = create_map(BPF_MAP_TYPE_HASH, sizeof(long long),
 					sizeof(long long), 1);
 		do {
-			prog[*fixup_map1].imm = map_fds[0];
-			fixup_map1++;
-		} while (*fixup_map1);
+			prog[*fixup_map_hash_8b].imm = map_fds[0];
+			fixup_map_hash_8b++;
+		} while (*fixup_map_hash_8b);
 	}
 
-	if (*fixup_map2) {
+	if (*fixup_map_hash_48b) {
 		map_fds[1] = create_map(BPF_MAP_TYPE_HASH, sizeof(long long),
 					sizeof(struct test_val), 1);
 		do {
-			prog[*fixup_map2].imm = map_fds[1];
-			fixup_map2++;
-		} while (*fixup_map2);
+			prog[*fixup_map_hash_48b].imm = map_fds[1];
+			fixup_map_hash_48b++;
+		} while (*fixup_map_hash_48b);
 	}
 
-	if (*fixup_map3) {
+	if (*fixup_map_hash_16b) {
 		map_fds[2] = create_map(BPF_MAP_TYPE_HASH, sizeof(long long),
 					sizeof(struct other_val), 1);
 		do {
-			prog[*fixup_map3].imm = map_fds[2];
-			fixup_map3++;
-		} while (*fixup_map3);
+			prog[*fixup_map_hash_16b].imm = map_fds[2];
+			fixup_map_hash_16b++;
+		} while (*fixup_map_hash_16b);
 	}
 
-	if (*fixup_map4) {
+	if (*fixup_map_array_48b) {
 		map_fds[3] = create_map(BPF_MAP_TYPE_ARRAY, sizeof(int),
 					sizeof(struct test_val), 1);
 		do {
-			prog[*fixup_map4].imm = map_fds[3];
-			fixup_map4++;
-		} while (*fixup_map4);
+			prog[*fixup_map_array_48b].imm = map_fds[3];
+			fixup_map_array_48b++;
+		} while (*fixup_map_array_48b);
 	}
 
 	if (*fixup_prog1) {
-- 
cgit v1.2.3


From 7c85c448e7d74c4ddd759440a2141eab663567cf Mon Sep 17 00:00:00 2001
From: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Date: Tue, 9 Oct 2018 10:04:54 +0900
Subject: selftests/bpf: test_verifier, check bpf_map_lookup_elem access in bpf
 prog

map_lookup_elem isn't supported by certain map types like:
- BPF_MAP_TYPE_PROG_ARRAY
- BPF_MAP_TYPE_STACK_TRACE
- BPF_MAP_TYPE_XSKMAP
- BPF_MAP_TYPE_SOCKMAP/BPF_MAP_TYPE_SOCKHASH
Let's add verfier tests to check whether verifier prevents
bpf_map_lookup_elem call on above programs from bpf program.

Signed-off-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 121 +++++++++++++++++++++++++++-
 1 file changed, 120 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 65ae44c85d27..cf4cd32b6772 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -48,7 +48,7 @@
 
 #define MAX_INSNS	BPF_MAXINSNS
 #define MAX_FIXUPS	8
-#define MAX_NR_MAPS	8
+#define MAX_NR_MAPS	13
 #define POINTER_VALUE	0xcafe4all
 #define TEST_DATA_LEN	64
 
@@ -65,6 +65,10 @@ struct bpf_test {
 	int fixup_map_hash_48b[MAX_FIXUPS];
 	int fixup_map_hash_16b[MAX_FIXUPS];
 	int fixup_map_array_48b[MAX_FIXUPS];
+	int fixup_map_sockmap[MAX_FIXUPS];
+	int fixup_map_sockhash[MAX_FIXUPS];
+	int fixup_map_xskmap[MAX_FIXUPS];
+	int fixup_map_stacktrace[MAX_FIXUPS];
 	int fixup_prog1[MAX_FIXUPS];
 	int fixup_prog2[MAX_FIXUPS];
 	int fixup_map_in_map[MAX_FIXUPS];
@@ -4541,6 +4545,85 @@ static struct bpf_test tests[] = {
 		.errstr = "invalid access to packet",
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
+	{
+		"prevent map lookup in sockmap",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_sockmap = { 3 },
+		.result = REJECT,
+		.errstr = "cannot pass map_type 15 into func bpf_map_lookup_elem",
+		.prog_type = BPF_PROG_TYPE_SOCK_OPS,
+	},
+	{
+		"prevent map lookup in sockhash",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_sockhash = { 3 },
+		.result = REJECT,
+		.errstr = "cannot pass map_type 18 into func bpf_map_lookup_elem",
+		.prog_type = BPF_PROG_TYPE_SOCK_OPS,
+	},
+	{
+		"prevent map lookup in xskmap",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_xskmap = { 3 },
+		.result = REJECT,
+		.errstr = "cannot pass map_type 17 into func bpf_map_lookup_elem",
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"prevent map lookup in stack trace",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_stacktrace = { 3 },
+		.result = REJECT,
+		.errstr = "cannot pass map_type 7 into func bpf_map_lookup_elem",
+		.prog_type = BPF_PROG_TYPE_PERF_EVENT,
+	},
+	{
+		"prevent map lookup in prog array",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_prog2 = { 3 },
+		.result = REJECT,
+		.errstr = "cannot pass map_type 3 into func bpf_map_lookup_elem",
+	},
 	{
 		"valid map access into an array with a constant",
 		.insns = {
@@ -13515,6 +13598,10 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type,
 	int *fixup_map_hash_48b = test->fixup_map_hash_48b;
 	int *fixup_map_hash_16b = test->fixup_map_hash_16b;
 	int *fixup_map_array_48b = test->fixup_map_array_48b;
+	int *fixup_map_sockmap = test->fixup_map_sockmap;
+	int *fixup_map_sockhash = test->fixup_map_sockhash;
+	int *fixup_map_xskmap = test->fixup_map_xskmap;
+	int *fixup_map_stacktrace = test->fixup_map_stacktrace;
 	int *fixup_prog1 = test->fixup_prog1;
 	int *fixup_prog2 = test->fixup_prog2;
 	int *fixup_map_in_map = test->fixup_map_in_map;
@@ -13603,6 +13690,38 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type,
 			fixup_percpu_cgroup_storage++;
 		} while (*fixup_percpu_cgroup_storage);
 	}
+	if (*fixup_map_sockmap) {
+		map_fds[9] = create_map(BPF_MAP_TYPE_SOCKMAP, sizeof(int),
+					sizeof(int), 1);
+		do {
+			prog[*fixup_map_sockmap].imm = map_fds[9];
+			fixup_map_sockmap++;
+		} while (*fixup_map_sockmap);
+	}
+	if (*fixup_map_sockhash) {
+		map_fds[10] = create_map(BPF_MAP_TYPE_SOCKHASH, sizeof(int),
+					sizeof(int), 1);
+		do {
+			prog[*fixup_map_sockhash].imm = map_fds[10];
+			fixup_map_sockhash++;
+		} while (*fixup_map_sockhash);
+	}
+	if (*fixup_map_xskmap) {
+		map_fds[11] = create_map(BPF_MAP_TYPE_XSKMAP, sizeof(int),
+					sizeof(int), 1);
+		do {
+			prog[*fixup_map_xskmap].imm = map_fds[11];
+			fixup_map_xskmap++;
+		} while (*fixup_map_xskmap);
+	}
+	if (*fixup_map_stacktrace) {
+		map_fds[12] = create_map(BPF_MAP_TYPE_STACK_TRACE, sizeof(u32),
+					 sizeof(u64), 1);
+		do {
+			prog[*fixup_map_stacktrace].imm = map_fds[12];
+			fixup_map_stacktrace++;
+		} while (fixup_map_stacktrace);
+	}
 }
 
 static void do_test_single(struct bpf_test *test, bool unpriv,
-- 
cgit v1.2.3


From 4f775448f4d79e2db5791fcc3aa708373497d7e6 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Tue, 9 Oct 2018 12:04:48 +0200
Subject: bpf: make TC vlan bpf_helpers avail to selftests

The helper bpf_skb_vlan_push is needed by next patch, and the helper
bpf_skb_vlan_pop is added for completeness, regarding VLAN helpers.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/bpf_helpers.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 1d407b3494f9..fda8c162d0df 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -155,6 +155,10 @@ static struct bpf_sock *(*bpf_sk_lookup_udp)(void *ctx,
 	(void *) BPF_FUNC_sk_lookup_udp;
 static int (*bpf_sk_release)(struct bpf_sock *sk) =
 	(void *) BPF_FUNC_sk_release;
+static int (*bpf_skb_vlan_push)(void *ctx, __be16 vlan_proto, __u16 vlan_tci) =
+	(void *) BPF_FUNC_skb_vlan_push;
+static int (*bpf_skb_vlan_pop)(void *ctx) =
+	(void *) BPF_FUNC_skb_vlan_pop;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
-- 
cgit v1.2.3


From 97396ff0bc2d31f8fcb29cbb57d2e0bbcb96d6c5 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Tue, 9 Oct 2018 12:04:53 +0200
Subject: selftests/bpf: add XDP selftests for modifying and popping VLAN
 headers

This XDP selftest also contain a small TC-bpf component. It provoke
the generic-XDP bug fixed in previous commit.

The selftest itself shows how to do VLAN manipulation from XDP and TC.
The test demonstrate how XDP ingress can remove a VLAN tag, and how TC
egress can add back a VLAN tag.

This use-case originates from a production need by ISP (kviknet.dk),
who gets DSL-lines terminated as VLAN Q-in-Q tagged packets, and want
to avoid having an net_device for every end-customer on the box doing
the L2 to L3 termination.
  The test-setup is done via a veth-pair and creating two network
namespaces (ns1 and ns2).  The 'ns1' simulate the ISP network that are
loading the BPF-progs stripping and adding VLAN IDs.  The 'ns2'
simulate the DSL-customer that are using VLAN tagged packets.

Running the script with --interactive, will simply not call the
cleanup function.  This gives the effect of creating a testlab, that
the users can inspect and play with.  The --verbose option will simply
request that the shell will print input lines as they are read, this
include comments, which in effect make the comments visible docs.

Reported-by: Yoel Caspersen <yoel@kviknet.dk>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/Makefile         |   6 +-
 tools/testing/selftests/bpf/test_xdp_vlan.c  | 292 +++++++++++++++++++++++++++
 tools/testing/selftests/bpf/test_xdp_vlan.sh | 195 ++++++++++++++++++
 3 files changed, 491 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/test_xdp_vlan.c
 create mode 100755 tools/testing/selftests/bpf/test_xdp_vlan.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 1381ab81099c..d24afe8b821d 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -36,7 +36,8 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
 	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
-	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o test_sk_lookup_kern.o
+	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o \
+	test_sk_lookup_kern.o test_xdp_vlan.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
@@ -49,7 +50,8 @@ TEST_PROGS := test_kmod.sh \
 	test_lwt_seg6local.sh \
 	test_lirc_mode2.sh \
 	test_skb_cgroup_id.sh \
-	test_flow_dissector.sh
+	test_flow_dissector.sh \
+	test_xdp_vlan.sh
 
 # Compile but not part of 'make run_tests'
 TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user \
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.c b/tools/testing/selftests/bpf/test_xdp_vlan.c
new file mode 100644
index 000000000000..365a7d2d9f5c
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_vlan.c
@@ -0,0 +1,292 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *  Copyright(c) 2018 Jesper Dangaard Brouer.
+ *
+ * XDP/TC VLAN manipulation example
+ *
+ * GOTCHA: Remember to disable NIC hardware offloading of VLANs,
+ * else the VLAN tags are NOT inlined in the packet payload:
+ *
+ *  # ethtool -K ixgbe2 rxvlan off
+ *
+ * Verify setting:
+ *  # ethtool -k ixgbe2 | grep rx-vlan-offload
+ *  rx-vlan-offload: off
+ *
+ */
+#include <stddef.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/in.h>
+#include <linux/pkt_cls.h>
+
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+/* linux/if_vlan.h have not exposed this as UAPI, thus mirror some here
+ *
+ *	struct vlan_hdr - vlan header
+ *	@h_vlan_TCI: priority and VLAN ID
+ *	@h_vlan_encapsulated_proto: packet type ID or len
+ */
+struct _vlan_hdr {
+	__be16 h_vlan_TCI;
+	__be16 h_vlan_encapsulated_proto;
+};
+#define VLAN_PRIO_MASK		0xe000 /* Priority Code Point */
+#define VLAN_PRIO_SHIFT		13
+#define VLAN_CFI_MASK		0x1000 /* Canonical Format Indicator */
+#define VLAN_TAG_PRESENT	VLAN_CFI_MASK
+#define VLAN_VID_MASK		0x0fff /* VLAN Identifier */
+#define VLAN_N_VID		4096
+
+struct parse_pkt {
+	__u16 l3_proto;
+	__u16 l3_offset;
+	__u16 vlan_outer;
+	__u16 vlan_inner;
+	__u8  vlan_outer_offset;
+	__u8  vlan_inner_offset;
+};
+
+char _license[] SEC("license") = "GPL";
+
+static __always_inline
+bool parse_eth_frame(struct ethhdr *eth, void *data_end, struct parse_pkt *pkt)
+{
+	__u16 eth_type;
+	__u8 offset;
+
+	offset = sizeof(*eth);
+	/* Make sure packet is large enough for parsing eth + 2 VLAN headers */
+	if ((void *)eth + offset + (2*sizeof(struct _vlan_hdr)) > data_end)
+		return false;
+
+	eth_type = eth->h_proto;
+
+	/* Handle outer VLAN tag */
+	if (eth_type == bpf_htons(ETH_P_8021Q)
+	    || eth_type == bpf_htons(ETH_P_8021AD)) {
+		struct _vlan_hdr *vlan_hdr;
+
+		vlan_hdr = (void *)eth + offset;
+		pkt->vlan_outer_offset = offset;
+		pkt->vlan_outer = bpf_ntohs(vlan_hdr->h_vlan_TCI)
+				& VLAN_VID_MASK;
+		eth_type        = vlan_hdr->h_vlan_encapsulated_proto;
+		offset += sizeof(*vlan_hdr);
+	}
+
+	/* Handle inner (double) VLAN tag */
+	if (eth_type == bpf_htons(ETH_P_8021Q)
+	    || eth_type == bpf_htons(ETH_P_8021AD)) {
+		struct _vlan_hdr *vlan_hdr;
+
+		vlan_hdr = (void *)eth + offset;
+		pkt->vlan_inner_offset = offset;
+		pkt->vlan_inner = bpf_ntohs(vlan_hdr->h_vlan_TCI)
+				& VLAN_VID_MASK;
+		eth_type        = vlan_hdr->h_vlan_encapsulated_proto;
+		offset += sizeof(*vlan_hdr);
+	}
+
+	pkt->l3_proto = bpf_ntohs(eth_type); /* Convert to host-byte-order */
+	pkt->l3_offset = offset;
+
+	return true;
+}
+
+/* Hint, VLANs are choosen to hit network-byte-order issues */
+#define TESTVLAN 4011 /* 0xFAB */
+// #define TO_VLAN  4000 /* 0xFA0 (hint 0xOA0 = 160) */
+
+SEC("xdp_drop_vlan_4011")
+int  xdp_prognum0(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct parse_pkt pkt = { 0 };
+
+	if (!parse_eth_frame(data, data_end, &pkt))
+		return XDP_ABORTED;
+
+	/* Drop specific VLAN ID example */
+	if (pkt.vlan_outer == TESTVLAN)
+		return XDP_ABORTED;
+	/*
+	 * Using XDP_ABORTED makes it possible to record this event,
+	 * via tracepoint xdp:xdp_exception like:
+	 *  # perf record -a -e xdp:xdp_exception
+	 *  # perf script
+	 */
+	return XDP_PASS;
+}
+/*
+Commands to setup VLAN on Linux to test packets gets dropped:
+
+ export ROOTDEV=ixgbe2
+ export VLANID=4011
+ ip link add link $ROOTDEV name $ROOTDEV.$VLANID type vlan id $VLANID
+ ip link set dev  $ROOTDEV.$VLANID up
+
+ ip link set dev $ROOTDEV mtu 1508
+ ip addr add 100.64.40.11/24 dev $ROOTDEV.$VLANID
+
+Load prog with ip tool:
+
+ ip link set $ROOTDEV xdp off
+ ip link set $ROOTDEV xdp object xdp_vlan01_kern.o section xdp_drop_vlan_4011
+
+*/
+
+/* Changing VLAN to zero, have same practical effect as removing the VLAN. */
+#define TO_VLAN	0
+
+SEC("xdp_vlan_change")
+int  xdp_prognum1(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct parse_pkt pkt = { 0 };
+
+	if (!parse_eth_frame(data, data_end, &pkt))
+		return XDP_ABORTED;
+
+	/* Change specific VLAN ID */
+	if (pkt.vlan_outer == TESTVLAN) {
+		struct _vlan_hdr *vlan_hdr = data + pkt.vlan_outer_offset;
+
+		/* Modifying VLAN, preserve top 4 bits */
+		vlan_hdr->h_vlan_TCI =
+			bpf_htons((bpf_ntohs(vlan_hdr->h_vlan_TCI) & 0xf000)
+				  | TO_VLAN);
+	}
+
+	return XDP_PASS;
+}
+
+/*
+ * Show XDP+TC can cooperate, on creating a VLAN rewriter.
+ * 1. Create a XDP prog that can "pop"/remove a VLAN header.
+ * 2. Create a TC-bpf prog that egress can add a VLAN header.
+ */
+
+#ifndef ETH_ALEN /* Ethernet MAC address length */
+#define ETH_ALEN	6	/* bytes */
+#endif
+#define VLAN_HDR_SZ	4	/* bytes */
+
+SEC("xdp_vlan_remove_outer")
+int  xdp_prognum2(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct parse_pkt pkt = { 0 };
+	char *dest;
+
+	if (!parse_eth_frame(data, data_end, &pkt))
+		return XDP_ABORTED;
+
+	/* Skip packet if no outer VLAN was detected */
+	if (pkt.vlan_outer_offset == 0)
+		return XDP_PASS;
+
+	/* Moving Ethernet header, dest overlap with src, memmove handle this */
+	dest = data;
+	dest+= VLAN_HDR_SZ;
+	/*
+	 * Notice: Taking over vlan_hdr->h_vlan_encapsulated_proto, by
+	 * only moving two MAC addrs (12 bytes), not overwriting last 2 bytes
+	 */
+	__builtin_memmove(dest, data, ETH_ALEN * 2);
+	/* Note: LLVM built-in memmove inlining require size to be constant */
+
+	/* Move start of packet header seen by Linux kernel stack */
+	bpf_xdp_adjust_head(ctx, VLAN_HDR_SZ);
+
+	return XDP_PASS;
+}
+
+static __always_inline
+void shift_mac_4bytes_16bit(void *data)
+{
+	__u16 *p = data;
+
+	p[7] = p[5]; /* delete p[7] was vlan_hdr->h_vlan_TCI */
+	p[6] = p[4]; /* delete p[6] was ethhdr->h_proto */
+	p[5] = p[3];
+	p[4] = p[2];
+	p[3] = p[1];
+	p[2] = p[0];
+}
+
+static __always_inline
+void shift_mac_4bytes_32bit(void *data)
+{
+	__u32 *p = data;
+
+	/* Assuming VLAN hdr present. The 4 bytes in p[3] that gets
+	 * overwritten, is ethhdr->h_proto and vlan_hdr->h_vlan_TCI.
+	 * The vlan_hdr->h_vlan_encapsulated_proto take over role as
+	 * ethhdr->h_proto.
+	 */
+	p[3] = p[2];
+	p[2] = p[1];
+	p[1] = p[0];
+}
+
+SEC("xdp_vlan_remove_outer2")
+int  xdp_prognum3(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct ethhdr *orig_eth = data;
+	struct parse_pkt pkt = { 0 };
+
+	if (!parse_eth_frame(orig_eth, data_end, &pkt))
+		return XDP_ABORTED;
+
+	/* Skip packet if no outer VLAN was detected */
+	if (pkt.vlan_outer_offset == 0)
+		return XDP_PASS;
+
+	/* Simply shift down MAC addrs 4 bytes, overwrite h_proto + TCI */
+	shift_mac_4bytes_32bit(data);
+
+	/* Move start of packet header seen by Linux kernel stack */
+	bpf_xdp_adjust_head(ctx, VLAN_HDR_SZ);
+
+	return XDP_PASS;
+}
+
+/*=====================================
+ *  BELOW: TC-hook based ebpf programs
+ * ====================================
+ * The TC-clsact eBPF programs (currently) need to be attach via TC commands
+ */
+
+SEC("tc_vlan_push")
+int _tc_progA(struct __sk_buff *ctx)
+{
+	bpf_skb_vlan_push(ctx, bpf_htons(ETH_P_8021Q), TESTVLAN);
+
+	return TC_ACT_OK;
+}
+/*
+Commands to setup TC to use above bpf prog:
+
+export ROOTDEV=ixgbe2
+export FILE=xdp_vlan01_kern.o
+
+# Re-attach clsact to clear/flush existing role
+tc qdisc del dev $ROOTDEV clsact 2> /dev/null ;\
+tc qdisc add dev $ROOTDEV clsact
+
+# Attach BPF prog EGRESS
+tc filter add dev $ROOTDEV egress \
+  prio 1 handle 1 bpf da obj $FILE sec tc_vlan_push
+
+tc filter show dev $ROOTDEV egress
+*/
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh
new file mode 100755
index 000000000000..51a3a31d1aac
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh
@@ -0,0 +1,195 @@
+#!/bin/bash
+
+TESTNAME=xdp_vlan
+
+usage() {
+  echo "Testing XDP + TC eBPF VLAN manipulations: $TESTNAME"
+  echo ""
+  echo "Usage: $0 [-vfh]"
+  echo "  -v | --verbose : Verbose"
+  echo "  --flush        : Flush before starting (e.g. after --interactive)"
+  echo "  --interactive  : Keep netns setup running after test-run"
+  echo ""
+}
+
+cleanup()
+{
+	local status=$?
+
+	if [ "$status" = "0" ]; then
+		echo "selftests: $TESTNAME [PASS]";
+	else
+		echo "selftests: $TESTNAME [FAILED]";
+	fi
+
+	if [ -n "$INTERACTIVE" ]; then
+		echo "Namespace setup still active explore with:"
+		echo " ip netns exec ns1 bash"
+		echo " ip netns exec ns2 bash"
+		exit $status
+	fi
+
+	set +e
+	ip link del veth1 2> /dev/null
+	ip netns del ns1 2> /dev/null
+	ip netns del ns2 2> /dev/null
+}
+
+# Using external program "getopt" to get --long-options
+OPTIONS=$(getopt -o hvfi: \
+    --long verbose,flush,help,interactive,debug -- "$@")
+if (( $? != 0 )); then
+    usage
+    echo "selftests: $TESTNAME [FAILED] Error calling getopt, unknown option?"
+    exit 2
+fi
+eval set -- "$OPTIONS"
+
+##  --- Parse command line arguments / parameters ---
+while true; do
+	case "$1" in
+	    -v | --verbose)
+		export VERBOSE=yes
+		shift
+		;;
+	    -i | --interactive | --debug )
+		INTERACTIVE=yes
+		shift
+		;;
+	    -f | --flush )
+		cleanup
+		shift
+		;;
+	    -- )
+		shift
+		break
+		;;
+	    -h | --help )
+		usage;
+		echo "selftests: $TESTNAME [SKIP] usage help info requested"
+		exit 0
+		;;
+	    * )
+		shift
+		break
+		;;
+	esac
+done
+
+if [ "$EUID" -ne 0 ]; then
+	echo "selftests: $TESTNAME [FAILED] need root privileges"
+	exit 1
+fi
+
+ip link set dev lo xdp off 2>/dev/null > /dev/null
+if [ $? -ne 0 ];then
+	echo "selftests: $TESTNAME [SKIP] need ip xdp support"
+	exit 0
+fi
+
+# Interactive mode likely require us to cleanup netns
+if [ -n "$INTERACTIVE" ]; then
+	ip link del veth1 2> /dev/null
+	ip netns del ns1 2> /dev/null
+	ip netns del ns2 2> /dev/null
+fi
+
+# Exit on failure
+set -e
+
+# Some shell-tools dependencies
+which ip > /dev/null
+which tc > /dev/null
+which ethtool > /dev/null
+
+# Make rest of shell verbose, showing comments as doc/info
+if [ -n "$VERBOSE" ]; then
+    set -v
+fi
+
+# Create two namespaces
+ip netns add ns1
+ip netns add ns2
+
+# Run cleanup if failing or on kill
+trap cleanup 0 2 3 6 9
+
+# Create veth pair
+ip link add veth1 type veth peer name veth2
+
+# Move veth1 and veth2 into the respective namespaces
+ip link set veth1 netns ns1
+ip link set veth2 netns ns2
+
+# NOTICE: XDP require VLAN header inside packet payload
+#  - Thus, disable VLAN offloading driver features
+#  - For veth REMEMBER TX side VLAN-offload
+#
+# Disable rx-vlan-offload (mostly needed on ns1)
+ip netns exec ns1 ethtool -K veth1 rxvlan off
+ip netns exec ns2 ethtool -K veth2 rxvlan off
+#
+# Disable tx-vlan-offload (mostly needed on ns2)
+ip netns exec ns2 ethtool -K veth2 txvlan off
+ip netns exec ns1 ethtool -K veth1 txvlan off
+
+export IPADDR1=100.64.41.1
+export IPADDR2=100.64.41.2
+
+# In ns1/veth1 add IP-addr on plain net_device
+ip netns exec ns1 ip addr add ${IPADDR1}/24 dev veth1
+ip netns exec ns1 ip link set veth1 up
+
+# In ns2/veth2 create VLAN device
+export VLAN=4011
+export DEVNS2=veth2
+ip netns exec ns2 ip link add link $DEVNS2 name $DEVNS2.$VLAN type vlan id $VLAN
+ip netns exec ns2 ip addr add ${IPADDR2}/24 dev $DEVNS2.$VLAN
+ip netns exec ns2 ip link set $DEVNS2 up
+ip netns exec ns2 ip link set $DEVNS2.$VLAN up
+
+# Bringup lo in netns (to avoids confusing people using --interactive)
+ip netns exec ns1 ip link set lo up
+ip netns exec ns2 ip link set lo up
+
+# At this point, the hosts cannot reach each-other,
+# because ns2 are using VLAN tags on the packets.
+
+ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Okay ping fails"'
+
+
+# Now we can use the test_xdp_vlan.c program to pop/push these VLAN tags
+# ----------------------------------------------------------------------
+# In ns1: ingress use XDP to remove VLAN tags
+export DEVNS1=veth1
+export FILE=test_xdp_vlan.o
+
+# First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change"
+export XDP_PROG=xdp_vlan_change
+ip netns exec ns1 ip link set $DEVNS1 xdp object $FILE section $XDP_PROG
+
+# In ns1: egress use TC to add back VLAN tag 4011
+#  (del cmd)
+#  tc qdisc del dev $DEVNS1 clsact 2> /dev/null
+#
+ip netns exec ns1 tc qdisc add dev $DEVNS1 clsact
+ip netns exec ns1 tc filter add dev $DEVNS1 egress \
+  prio 1 handle 1 bpf da obj $FILE sec tc_vlan_push
+
+# Now the namespaces can reach each-other, test with ping:
+ip netns exec ns2 ping -W 2 -c 3 $IPADDR1
+ip netns exec ns1 ping -W 2 -c 3 $IPADDR2
+
+# Second test: Replace xdp prog, that fully remove vlan header
+#
+# Catch kernel bug for generic-XDP, that does didn't allow us to
+# remove a VLAN header, because skb->protocol still contain VLAN
+# ETH_P_8021Q indication, and this cause overwriting of our changes.
+#
+export XDP_PROG=xdp_vlan_remove_outer2
+ip netns exec ns1 ip link set $DEVNS1 xdp off
+ip netns exec ns1 ip link set $DEVNS1 xdp object $FILE section $XDP_PROG
+
+# Now the namespaces should still be able reach each-other, test with ping:
+ip netns exec ns2 ping -W 2 -c 3 $IPADDR1
+ip netns exec ns1 ping -W 2 -c 3 $IPADDR2
-- 
cgit v1.2.3


From 438363c0feb831ac3f66646939b3833362750d94 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 9 Oct 2018 16:14:47 -0700
Subject: tools/bpf: use proper type and uapi perf_event.h header for libbpf

Use __u32 instead u32 in libbpf.c and also use
uapi perf_event.h instead of tools/perf/perf-sys.h.

Signed-off-by: Yonghong Song <yhs@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/Makefile | 2 +-
 tools/lib/bpf/libbpf.c | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 6ad27257fd67..79d84413ddf2 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -69,7 +69,7 @@ FEATURE_USER = .libbpf
 FEATURE_TESTS = libelf libelf-mmap bpf reallocarray
 FEATURE_DISPLAY = libelf bpf
 
-INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi -I$(srctree)/tools/perf
+INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi
 FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES)
 
 check_feat := 1
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ceb918c14d80..176cf5523728 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -19,7 +19,6 @@
 #include <unistd.h>
 #include <fcntl.h>
 #include <errno.h>
-#include <perf-sys.h>
 #include <asm/unistd.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
@@ -27,6 +26,7 @@
 #include <linux/btf.h>
 #include <linux/list.h>
 #include <linux/limits.h>
+#include <linux/perf_event.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/vfs.h>
@@ -169,7 +169,7 @@ static LIST_HEAD(bpf_objects_list);
 
 struct bpf_object {
 	char license[64];
-	u32 kern_version;
+	__u32 kern_version;
 
 	struct bpf_program *programs;
 	size_t nr_programs;
@@ -540,7 +540,7 @@ static int
 bpf_object__init_kversion(struct bpf_object *obj,
 			  void *data, size_t size)
 {
-	u32 kver;
+	__u32 kver;
 
 	if (size != sizeof(kver)) {
 		pr_warning("invalid kver section in %s\n", obj->path);
@@ -1295,7 +1295,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 static int
 load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
 	     const char *name, struct bpf_insn *insns, int insns_cnt,
-	     char *license, u32 kern_version, int *pfd, int prog_ifindex)
+	     char *license, __u32 kern_version, int *pfd, int prog_ifindex)
 {
 	struct bpf_load_program_attr load_attr;
 	char *cp, errmsg[STRERR_BUFSIZE];
-- 
cgit v1.2.3


From 372809055f6c830ff978564e09f58bcb9e9b937c Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 8 Oct 2018 18:50:41 +0000
Subject: selftests: forwarding: Have lldpad_app_wait_set() wait for unknown,
 too

Immediately after mlxsw module is probed and lldpad started, added APP
entries are briefly in "unknown" state before becoming "pending". That's
the state that lldpad_app_wait_set() typically sees, and since there are
no pending entries at that time, it bails out. However the entries have
not been pushed to the kernel yet at that point, and thus the test case
fails.

Fix by waiting for both unknown and pending entries to disappear before
proceeding.

Fixes: d159261f3662 ("selftests: mlxsw: Add test for trust-DSCP")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 0e73698b2048..85d253546684 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -251,7 +251,7 @@ lldpad_app_wait_set()
 {
 	local dev=$1; shift
 
-	while lldptool -t -i $dev -V APP -c app | grep -q pending; do
+	while lldptool -t -i $dev -V APP -c app | grep -Eq "pending|unknown"; do
 		echo "$dev: waiting for lldpad to push pending APP updates"
 		sleep 5
 	done
-- 
cgit v1.2.3


From 970152591d5552fb52ddbf50af8d26b61f02bf39 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 8 Oct 2018 18:50:42 +0000
Subject: selftests: mlxsw: qos_mc_aware: Make executable

This is a self-standing test and as such should be itself executable.

Fixes: b5638d46c90a ("selftests: mlxsw: Add a test for UC behavior under MC flood")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 mode change 100644 => 100755 tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
old mode 100644
new mode 100755
-- 
cgit v1.2.3


From 0ef6bf39f09832866fd581cbafafbad9b2469eb3 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 8 Oct 2018 10:22:58 +0200
Subject: bpftool: Allow to add compiler flags via EXTRA_CFLAGS variable

Adding EXTRA_CFLAGS allowing user to specify extra flags
for CFLAGS variable.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Makefile | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 74288a2197ab..5bfa07e3f2f7 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -46,6 +46,10 @@ CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \
 	-I$(srctree)/tools/lib/bpf \
 	-I$(srctree)/tools/perf
 CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"'
+ifneq ($(EXTRA_CFLAGS),)
+CFLAGS += $(EXTRA_CFLAGS)
+endif
+
 LIBS = -lelf -lbfd -lopcodes $(LIBBPF)
 
 INSTALL ?= install
-- 
cgit v1.2.3


From c85061657e1c45d7063d718c7e21b880e3b1411e Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 8 Oct 2018 10:22:59 +0200
Subject: bpftool: Allow add linker flags via EXTRA_LDFLAGS variable

Adding EXTRA_LDFLAGS allowing user to specify extra flags
for LD_FLAGS variable. Also adding LDFLAGS to build command
line.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Makefile | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 5bfa07e3f2f7..dac7eff4c7e5 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -49,6 +49,9 @@ CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"'
 ifneq ($(EXTRA_CFLAGS),)
 CFLAGS += $(EXTRA_CFLAGS)
 endif
+ifneq ($(EXTRA_LDFLAGS),)
+LDFLAGS += $(EXTRA_LDFLAGS)
+endif
 
 LIBS = -lelf -lbfd -lopcodes $(LIBBPF)
 
@@ -94,7 +97,7 @@ $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
 	$(QUIET_CC)$(COMPILE.c) -MMD -o $@ $<
 
 $(OUTPUT)bpftool: $(OBJS) $(LIBBPF)
-	$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^ $(LIBS)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $^ $(LIBS)
 
 $(OUTPUT)%.o: %.c
 	$(QUIET_CC)$(COMPILE.c) -MMD -o $@ $<
-- 
cgit v1.2.3


From d3c72d7a20d8ebb0618d06fc49e83a4d74d96205 Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Wed, 10 Oct 2018 11:21:23 +0200
Subject: selftests: bpf: add config fragment LWTUNNEL

When test_lwt_seg6local.sh was added commit c99a84eac026
("selftests/bpf: test for seg6local End.BPF action") config fragment
wasn't added, and without CONFIG_LWTUNNEL enabled we see this:
Error: CONFIG_LWTUNNEL is not enabled in this kernel.
selftests: test_lwt_seg6local [FAILED]

Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/config | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 3655508f95fd..dd49df5e2df4 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -19,3 +19,4 @@ CONFIG_CRYPTO_SHA256=m
 CONFIG_VXLAN=y
 CONFIG_GENEVE=y
 CONFIG_NET_CLS_FLOWER=m
+CONFIG_LWTUNNEL=y
-- 
cgit v1.2.3


From ef4ab8447aa2639d7a80a50f23d9f27c5c0db276 Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Wed, 10 Oct 2018 16:27:04 +0200
Subject: selftests: bpf: install script with_addr.sh

When test_flow_dissector.sh runs it complains that it can't find script
with_addr.sh:

./test_flow_dissector.sh: line 81: ./with_addr.sh: No such file or
directory

Rework so that with_addr.sh gets installed, add it to
TEST_PROGS_EXTENDED variable.

Fixes: 50b3ed57dee9 ("selftests/bpf: test bpf flow dissection")
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index d24afe8b821d..d99dd6fc3fbe 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -53,6 +53,8 @@ TEST_PROGS := test_kmod.sh \
 	test_flow_dissector.sh \
 	test_xdp_vlan.sh
 
+TEST_PROGS_EXTENDED := with_addr.sh
+
 # Compile but not part of 'make run_tests'
 TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user \
 	flow_dissector_load test_flow_dissector
-- 
cgit v1.2.3


From 94aafb74cee0002e2f2eb6dc5376f54d5951ab4d Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Wed, 10 Oct 2018 10:03:39 +0200
Subject: perf vendor events intel: Fix wrong filter_band* values for uncore
 events

Michael reported that he could not stat following event:

  $ perf stat -e unc_p_freq_ge_1200mhz_cycles -a -- ls
  event syntax error: '..e_1200mhz_cycles'
                                    \___ value too big for format, maximum is 255
  Run 'perf list' for a list of valid events

The event is unwrapped into:

  uncore_pcu/event=0xb,filter_band0=1200/

where filter_band0 format says it's one byte only:

  # cat uncore_pcu/format/filter_band0
  config1:0-7

while JSON files specifies bigger number:

  "Filter": "filter_band0=1200",

all the filter_band* formats show 1 byte width:

  # cat uncore_pcu/format/filter_band1
  config1:8-15
  # cat uncore_pcu/format/filter_band2
  config1:16-23
  # cat uncore_pcu/format/filter_band3
  config1:24-31

The reason of the issue is that filter_band* values are supposed to be
in 100Mhz units.. it's stated in the JSON help for the events, like:

  filter_band3=XXX, with XXX in 100Mhz units

This patch divides the filter_band* values by 100, plus there's couple
of changes that actually change the number completely, like:

  -        "Filter": "edge=1,filter_band2=4000",
  +        "Filter": "edge=1,filter_band2=30",

Reported-by: Michael Petlan <mpetlan@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Andi Kleen <ak@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20181010080339.GB15790@krava
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json | 16 ++++++++--------
 .../perf/pmu-events/arch/x86/jaketown/uncore-power.json  | 16 ++++++++--------
 2 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
index d40498f2cb1e..635c09fda1d9 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
@@ -188,7 +188,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xb",
         "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
-        "Filter": "filter_band0=1200",
+        "Filter": "filter_band0=12",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
@@ -199,7 +199,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xc",
         "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
-        "Filter": "filter_band1=2000",
+        "Filter": "filter_band1=20",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
@@ -210,7 +210,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
-        "Filter": "filter_band2=3000",
+        "Filter": "filter_band2=30",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
@@ -221,7 +221,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xe",
         "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
-        "Filter": "filter_band3=4000",
+        "Filter": "filter_band3=40",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
@@ -232,7 +232,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xb",
         "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band0=1200",
+        "Filter": "edge=1,filter_band0=12",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
@@ -243,7 +243,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xc",
         "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band1=2000",
+        "Filter": "edge=1,filter_band1=20",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
@@ -254,7 +254,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band2=4000",
+        "Filter": "edge=1,filter_band2=30",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
@@ -265,7 +265,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xe",
         "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band3=4000",
+        "Filter": "edge=1,filter_band3=40",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
index 16034bfd06dd..8755693d86c6 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
@@ -187,7 +187,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xb",
         "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
-        "Filter": "filter_band0=1200",
+        "Filter": "filter_band0=12",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
@@ -198,7 +198,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xc",
         "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
-        "Filter": "filter_band1=2000",
+        "Filter": "filter_band1=20",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
@@ -209,7 +209,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
-        "Filter": "filter_band2=3000",
+        "Filter": "filter_band2=30",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
@@ -220,7 +220,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xe",
         "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
-        "Filter": "filter_band3=4000",
+        "Filter": "filter_band3=40",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
@@ -231,7 +231,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xb",
         "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band0=1200",
+        "Filter": "edge=1,filter_band0=12",
         "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_1200mhz_cycles %",
         "PerPkg": "1",
@@ -242,7 +242,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xc",
         "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band1=2000",
+        "Filter": "edge=1,filter_band1=20",
         "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_2000mhz_cycles %",
         "PerPkg": "1",
@@ -253,7 +253,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd",
         "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band2=4000",
+        "Filter": "edge=1,filter_band2=30",
         "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_3000mhz_cycles %",
         "PerPkg": "1",
@@ -264,7 +264,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xe",
         "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
-        "Filter": "edge=1,filter_band3=4000",
+        "Filter": "edge=1,filter_band3=40",
         "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
         "MetricName": "freq_ge_4000mhz_cycles %",
         "PerPkg": "1",
-- 
cgit v1.2.3


From 3c718e677c2b35b449992adc36ecce883c467e98 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 11 Oct 2018 10:54:52 +0200
Subject: selftests: rtnetlink.sh explicitly requires bash.

the script rtnetlink.sh requires a bash-only features (sleep with sub-second
precision). This may cause random test failure if the default shell is not
bash.
Address the above explicitly requiring bash as the script interpreter.

Fixes: 33b01b7b4f19 ("selftests: add rtnetlink test script")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 08c341b49760..e101af52d1d6 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 #
 # This test is for checking rtnetlink callpaths, and get as much coverage as possible.
 #
-- 
cgit v1.2.3


From 12a2ea962c06efb30764c47b140d2ec9d3cd7cb0 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 11 Oct 2018 10:54:53 +0200
Subject: selftests: udpgso_bench.sh explicitly requires bash

The udpgso_bench.sh script requires several bash-only features. This
may cause random failures if the default shell is not bash.
Address the above explicitly requiring bash as the script interpreter

Fixes: 3a687bef148d ("selftests: udp gso benchmark")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/udpgso_bench.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
index 850767befa47..99e537ab5ad9 100755
--- a/tools/testing/selftests/net/udpgso_bench.sh
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 #
 # Run a series of udpgso benchmarks
-- 
cgit v1.2.3


From 9dffa76c21268f6188b04b966089b5110a7447ef Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 11 Oct 2018 11:17:37 +0200
Subject: selftests: use posix-style redirection in ip_defrag.sh

The ip_defrag.sh script requires bash-style output redirection but
use the default shell. This may cause random failures if the default
shell is not bash.
Address the above using posix compliant output redirection.

Fixes: 02c7f38b7ace ("selftests/net: add ip_defrag selftest")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/ip_defrag.sh | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh
index 3a4042d918f0..f34672796044 100755
--- a/tools/testing/selftests/net/ip_defrag.sh
+++ b/tools/testing/selftests/net/ip_defrag.sh
@@ -11,10 +11,10 @@ readonly NETNS="ns-$(mktemp -u XXXXXX)"
 setup() {
 	ip netns add "${NETNS}"
 	ip -netns "${NETNS}" link set lo up
-	ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null
-	ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null
-	ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_high_thresh=9000000 &> /dev/null
-	ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_low_thresh=7000000 &> /dev/null
+	ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_high_thresh=9000000 >/dev/null 2>&1
+	ip netns exec "${NETNS}" sysctl -w net.ipv4.ipfrag_low_thresh=7000000 >/dev/null 2>&1
+	ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_high_thresh=9000000 >/dev/null 2>&1
+	ip netns exec "${NETNS}" sysctl -w net.ipv6.ip6frag_low_thresh=7000000 >/dev/null 2>&1
 }
 
 cleanup() {
-- 
cgit v1.2.3


From e9dd904708c463ff57d019f4482c48d057fa4d7e Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sat, 13 Oct 2018 02:46:02 +0200
Subject: bpf: add tls support for testing in test_sockmap

This adds a --ktls option to test_sockmap in order to enable the
combination of ktls and sockmap to run, which makes for another
batch of 648 test cases for both in combination.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_sockmap.c | 89 ++++++++++++++++++++++++++++++
 1 file changed, 89 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index ac7de38e5c63..10a5fa83c75a 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -71,6 +71,7 @@ int txmsg_start;
 int txmsg_end;
 int txmsg_ingress;
 int txmsg_skb;
+int ktls;
 
 static const struct option long_options[] = {
 	{"help",	no_argument,		NULL, 'h' },
@@ -92,6 +93,7 @@ static const struct option long_options[] = {
 	{"txmsg_end",	required_argument,	NULL, 'e'},
 	{"txmsg_ingress", no_argument,		&txmsg_ingress, 1 },
 	{"txmsg_skb", no_argument,		&txmsg_skb, 1 },
+	{"ktls", no_argument,			&ktls, 1 },
 	{0, 0, NULL, 0 }
 };
 
@@ -112,6 +114,76 @@ static void usage(char *argv[])
 	printf("\n");
 }
 
+#define TCP_ULP 31
+#define TLS_TX 1
+#define TLS_RX 2
+#include <linux/tls.h>
+
+char *sock_to_string(int s)
+{
+	if (s == c1)
+		return "client1";
+	else if (s == c2)
+		return "client2";
+	else if (s == s1)
+		return "server1";
+	else if (s == s2)
+		return "server2";
+	else if (s == p1)
+		return "peer1";
+	else if (s == p2)
+		return "peer2";
+	else
+		return "unknown";
+}
+
+static int sockmap_init_ktls(int verbose, int s)
+{
+	struct tls12_crypto_info_aes_gcm_128 tls_tx = {
+		.info = {
+			.version     = TLS_1_2_VERSION,
+			.cipher_type = TLS_CIPHER_AES_GCM_128,
+		},
+	};
+	struct tls12_crypto_info_aes_gcm_128 tls_rx = {
+		.info = {
+			.version     = TLS_1_2_VERSION,
+			.cipher_type = TLS_CIPHER_AES_GCM_128,
+		},
+	};
+	int so_buf = 6553500;
+	int err;
+
+	err = setsockopt(s, 6, TCP_ULP, "tls", sizeof("tls"));
+	if (err) {
+		fprintf(stderr, "setsockopt: TCP_ULP(%s) failed with error %i\n", sock_to_string(s), err);
+		return -EINVAL;
+	}
+	err = setsockopt(s, SOL_TLS, TLS_TX, (void *)&tls_tx, sizeof(tls_tx));
+	if (err) {
+		fprintf(stderr, "setsockopt: TLS_TX(%s) failed with error %i\n", sock_to_string(s), err);
+		return -EINVAL;
+	}
+	err = setsockopt(s, SOL_TLS, TLS_RX, (void *)&tls_rx, sizeof(tls_rx));
+	if (err) {
+		fprintf(stderr, "setsockopt: TLS_RX(%s) failed with error %i\n", sock_to_string(s), err);
+		return -EINVAL;
+	}
+	err = setsockopt(s, SOL_SOCKET, SO_SNDBUF, &so_buf, sizeof(so_buf));
+	if (err) {
+		fprintf(stderr, "setsockopt: (%s) failed sndbuf with error %i\n", sock_to_string(s), err);
+		return -EINVAL;
+	}
+	err = setsockopt(s, SOL_SOCKET, SO_RCVBUF, &so_buf, sizeof(so_buf));
+	if (err) {
+		fprintf(stderr, "setsockopt: (%s) failed rcvbuf with error %i\n", sock_to_string(s), err);
+		return -EINVAL;
+	}
+
+	if (verbose)
+		fprintf(stdout, "socket(%s) kTLS enabled\n", sock_to_string(s));
+	return 0;
+}
 static int sockmap_init_sockets(int verbose)
 {
 	int i, err, one = 1;
@@ -456,6 +528,21 @@ static int sendmsg_test(struct sockmap_options *opt)
 	else
 		rx_fd = p2;
 
+	if (ktls) {
+		/* Redirecting into non-TLS socket which sends into a TLS
+		 * socket is not a valid test. So in this case lets not
+		 * enable kTLS but still run the test.
+		 */
+		if (!txmsg_redir || (txmsg_redir && txmsg_ingress)) {
+			err = sockmap_init_ktls(opt->verbose, rx_fd);
+			if (err)
+				return err;
+		}
+		err = sockmap_init_ktls(opt->verbose, c1);
+		if (err)
+			return err;
+	}
+
 	rxpid = fork();
 	if (rxpid == 0) {
 		if (opt->drop_expected)
@@ -907,6 +994,8 @@ static void test_options(char *options)
 		strncat(options, "ingress,", OPTSTRING);
 	if (txmsg_skb)
 		strncat(options, "skb,", OPTSTRING);
+	if (ktls)
+		strncat(options, "ktls,", OPTSTRING);
 }
 
 static int __test_exec(int cgrp, int test, struct sockmap_options *opt)
-- 
cgit v1.2.3


From b7d3826c2ed6c3e626e7ae796c5df2c0d2551c6a Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Mon, 15 Oct 2018 11:19:50 -0700
Subject: bpf: bpftool, add support for attaching programs to maps

Sock map/hash introduce support for attaching programs to maps. To
date I have been doing this with custom tooling but this is less than
ideal as we shift to using bpftool as the single CLI for our BPF uses.
This patch adds new sub commands 'attach' and 'detach' to the 'prog'
command to attach programs to maps and then detach them.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst | 11 +++
 tools/bpf/bpftool/Documentation/bpftool.rst      |  2 +-
 tools/bpf/bpftool/bash-completion/bpftool        | 19 ++++-
 tools/bpf/bpftool/prog.c                         | 99 +++++++++++++++++++++++-
 4 files changed, 128 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 64156a16d530..12c803003ab2 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -25,6 +25,8 @@ MAP COMMANDS
 |	**bpftool** **prog dump jited**  *PROG* [{**file** *FILE* | **opcodes**}]
 |	**bpftool** **prog pin** *PROG* *FILE*
 |	**bpftool** **prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
+|       **bpftool** **prog attach** *PROG* *ATTACH_TYPE* *MAP*
+|       **bpftool** **prog detach** *PROG* *ATTACH_TYPE* *MAP*
 |	**bpftool** **prog help**
 |
 |	*MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
@@ -37,6 +39,7 @@ MAP COMMANDS
 |		**cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** |
 |		**cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6**
 |	}
+|       *ATTACH_TYPE* := { **msg_verdict** | **skb_verdict** | **skb_parse** }
 
 
 DESCRIPTION
@@ -90,6 +93,14 @@ DESCRIPTION
 
 		  Note: *FILE* must be located in *bpffs* mount.
 
+        **bpftool prog attach** *PROG* *ATTACH_TYPE* *MAP*
+                  Attach bpf program *PROG* (with type specified by *ATTACH_TYPE*)
+                  to the map *MAP*.
+
+        **bpftool prog detach** *PROG* *ATTACH_TYPE* *MAP*
+                  Detach bpf program *PROG* (with type specified by *ATTACH_TYPE*)
+                  from the map *MAP*.
+
 	**bpftool prog help**
 		  Print short help message.
 
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 8dda77daeda9..25c08728ca80 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -26,7 +26,7 @@ SYNOPSIS
 	| **pin** | **event_pipe** | **help** }
 
 	*PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin**
-	| **load** | **help** }
+	| **load** | **attach** | **detach** | **help** }
 
 	*CGROUP-COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** }
 
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index df1060b852c1..082651931824 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -292,6 +292,23 @@ _bpftool()
                     fi
                     return 0
                     ;;
+                attach|detach)
+                    if [[ ${#words[@]} == 7 ]]; then
+                        COMPREPLY=( $( compgen -W "id pinned" -- "$cur" ) )
+                        return 0
+                    fi
+
+                    if [[ ${#words[@]} == 6 ]]; then
+                        COMPREPLY=( $( compgen -W "msg_verdict skb_verdict skb_parse" -- "$cur" ) )
+                        return 0
+                    fi
+
+                    if [[ $prev == "$command" ]]; then
+                        COMPREPLY=( $( compgen -W "id pinned" -- "$cur" ) )
+                        return 0
+                    fi
+                    return 0
+                    ;;
                 load)
                     local obj
 
@@ -347,7 +364,7 @@ _bpftool()
                     ;;
                 *)
                     [[ $prev == $object ]] && \
-                        COMPREPLY=( $( compgen -W 'dump help pin load \
+                        COMPREPLY=( $( compgen -W 'dump help pin attach detach load \
                             show list' -- "$cur" ) )
                     ;;
             esac
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index b1cd3bc8db70..99ab42c56724 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -77,6 +77,26 @@ static const char * const prog_type_name[] = {
 	[BPF_PROG_TYPE_FLOW_DISSECTOR]	= "flow_dissector",
 };
 
+static const char * const attach_type_strings[] = {
+	[BPF_SK_SKB_STREAM_PARSER] = "stream_parser",
+	[BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict",
+	[BPF_SK_MSG_VERDICT] = "msg_verdict",
+	[__MAX_BPF_ATTACH_TYPE] = NULL,
+};
+
+enum bpf_attach_type parse_attach_type(const char *str)
+{
+	enum bpf_attach_type type;
+
+	for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) {
+		if (attach_type_strings[type] &&
+		    is_prefix(str, attach_type_strings[type]))
+			return type;
+	}
+
+	return __MAX_BPF_ATTACH_TYPE;
+}
+
 static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
 {
 	struct timespec real_time_ts, boot_time_ts;
@@ -697,6 +717,77 @@ int map_replace_compar(const void *p1, const void *p2)
 	return a->idx - b->idx;
 }
 
+static int do_attach(int argc, char **argv)
+{
+	enum bpf_attach_type attach_type;
+	int err, mapfd, progfd;
+
+	if (!REQ_ARGS(5)) {
+		p_err("too few parameters for map attach");
+		return -EINVAL;
+	}
+
+	progfd = prog_parse_fd(&argc, &argv);
+	if (progfd < 0)
+		return progfd;
+
+	attach_type = parse_attach_type(*argv);
+	if (attach_type == __MAX_BPF_ATTACH_TYPE) {
+		p_err("invalid attach type");
+		return -EINVAL;
+	}
+	NEXT_ARG();
+
+	mapfd = map_parse_fd(&argc, &argv);
+	if (mapfd < 0)
+		return mapfd;
+
+	err = bpf_prog_attach(progfd, mapfd, attach_type, 0);
+	if (err) {
+		p_err("failed prog attach to map");
+		return -EINVAL;
+	}
+
+	if (json_output)
+		jsonw_null(json_wtr);
+	return 0;
+}
+
+static int do_detach(int argc, char **argv)
+{
+	enum bpf_attach_type attach_type;
+	int err, mapfd, progfd;
+
+	if (!REQ_ARGS(5)) {
+		p_err("too few parameters for map detach");
+		return -EINVAL;
+	}
+
+	progfd = prog_parse_fd(&argc, &argv);
+	if (progfd < 0)
+		return progfd;
+
+	attach_type = parse_attach_type(*argv);
+	if (attach_type == __MAX_BPF_ATTACH_TYPE) {
+		p_err("invalid attach type");
+		return -EINVAL;
+	}
+	NEXT_ARG();
+
+	mapfd = map_parse_fd(&argc, &argv);
+	if (mapfd < 0)
+		return mapfd;
+
+	err = bpf_prog_detach2(progfd, mapfd, attach_type);
+	if (err) {
+		p_err("failed prog detach from map");
+		return -EINVAL;
+	}
+
+	if (json_output)
+		jsonw_null(json_wtr);
+	return 0;
+}
 static int do_load(int argc, char **argv)
 {
 	enum bpf_attach_type expected_attach_type;
@@ -942,6 +1033,8 @@ static int do_help(int argc, char **argv)
 		"       %s %s pin   PROG FILE\n"
 		"       %s %s load  OBJ  FILE [type TYPE] [dev NAME] \\\n"
 		"                         [map { idx IDX | name NAME } MAP]\n"
+		"       %s %s attach PROG ATTACH_TYPE MAP\n"
+		"       %s %s detach PROG ATTACH_TYPE MAP\n"
 		"       %s %s help\n"
 		"\n"
 		"       " HELP_SPEC_MAP "\n"
@@ -953,10 +1046,12 @@ static int do_help(int argc, char **argv)
 		"                 cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
 		"                 cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
 		"                 cgroup/sendmsg4 | cgroup/sendmsg6 }\n"
+		"       ATTACH_TYPE := { msg_verdict | skb_verdict | skb_parse }\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
-		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]);
+		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
+		bin_name, argv[-2], bin_name, argv[-2]);
 
 	return 0;
 }
@@ -968,6 +1063,8 @@ static const struct cmd cmds[] = {
 	{ "dump",	do_dump },
 	{ "pin",	do_pin },
 	{ "load",	do_load },
+	{ "attach",	do_attach },
+	{ "detach",	do_detach },
 	{ 0 }
 };
 
-- 
cgit v1.2.3


From c034a177d3c898f370f52877e7252da8c4f8235c Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Mon, 15 Oct 2018 11:19:55 -0700
Subject: bpf: bpftool, add flag to allow non-compat map definitions

Multiple map definition structures exist and user may have non-zero
fields in their definition that are not recognized by bpftool and
libbpf. The normal behavior is to then fail loading the map. Although
this is a good default behavior users may still want to load the map
for debugging or other reasons. This patch adds a --mapcompat flag
that can be used to override the default behavior and allow loading
the map even when it has additional non-zero fields.

For now the only user is 'bpftool prog' we can switch over other
subcommands as needed. The library exposes an API that consumes
a flags field now but I kept the original API around also in case
users of the API don't want to expose this. The flags field is an
int in case we need more control over how the API call handles
errors/features/etc in the future.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/Documentation/bpftool.rst |  4 ++++
 tools/bpf/bpftool/bash-completion/bpftool   |  2 +-
 tools/bpf/bpftool/main.c                    |  7 ++++++-
 tools/bpf/bpftool/main.h                    |  3 ++-
 tools/bpf/bpftool/prog.c                    |  2 +-
 tools/lib/bpf/bpf.h                         |  3 +++
 tools/lib/bpf/libbpf.c                      | 27 ++++++++++++++++++---------
 tools/lib/bpf/libbpf.h                      |  2 ++
 8 files changed, 37 insertions(+), 13 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 25c08728ca80..65488317fefa 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -57,6 +57,10 @@ OPTIONS
 	-p, --pretty
 		  Generate human-readable JSON output. Implies **-j**.
 
+	-m, --mapcompat
+		  Allow loading maps with unknown map definitions.
+
+
 SEE ALSO
 ========
 	**bpftool-map**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8)
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 082651931824..ac85207cba8d 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -184,7 +184,7 @@ _bpftool()
 
     # Deal with options
     if [[ ${words[cword]} == -* ]]; then
-        local c='--version --json --pretty --bpffs'
+        local c='--version --json --pretty --bpffs --mapcompat'
         COMPREPLY=( $( compgen -W "$c" -- "$cur" ) )
         return 0
     fi
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 79dc3f193547..828dde30e9ec 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -55,6 +55,7 @@ json_writer_t *json_wtr;
 bool pretty_output;
 bool json_output;
 bool show_pinned;
+int bpf_flags;
 struct pinned_obj_table prog_table;
 struct pinned_obj_table map_table;
 
@@ -341,6 +342,7 @@ int main(int argc, char **argv)
 		{ "pretty",	no_argument,	NULL,	'p' },
 		{ "version",	no_argument,	NULL,	'V' },
 		{ "bpffs",	no_argument,	NULL,	'f' },
+		{ "mapcompat",	no_argument,	NULL,	'm' },
 		{ 0 }
 	};
 	int opt, ret;
@@ -355,7 +357,7 @@ int main(int argc, char **argv)
 	hash_init(map_table.table);
 
 	opterr = 0;
-	while ((opt = getopt_long(argc, argv, "Vhpjf",
+	while ((opt = getopt_long(argc, argv, "Vhpjfm",
 				  options, NULL)) >= 0) {
 		switch (opt) {
 		case 'V':
@@ -379,6 +381,9 @@ int main(int argc, char **argv)
 		case 'f':
 			show_pinned = true;
 			break;
+		case 'm':
+			bpf_flags = MAPS_RELAX_COMPAT;
+			break;
 		default:
 			p_err("unrecognized option '%s'", argv[optind - 1]);
 			if (json_output)
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 40492cdc4e53..91fd697303cb 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -74,7 +74,7 @@
 #define HELP_SPEC_PROGRAM						\
 	"PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }"
 #define HELP_SPEC_OPTIONS						\
-	"OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} }"
+	"OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} | {-m|--mapcompat}"
 #define HELP_SPEC_MAP							\
 	"MAP := { id MAP_ID | pinned FILE }"
 
@@ -89,6 +89,7 @@ extern const char *bin_name;
 extern json_writer_t *json_wtr;
 extern bool json_output;
 extern bool show_pinned;
+extern int bpf_flags;
 extern struct pinned_obj_table prog_table;
 extern struct pinned_obj_table map_table;
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 99ab42c56724..335028968dfb 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -908,7 +908,7 @@ static int do_load(int argc, char **argv)
 		}
 	}
 
-	obj = bpf_object__open_xattr(&attr);
+	obj = __bpf_object__open_xattr(&attr, bpf_flags);
 	if (IS_ERR_OR_NULL(obj)) {
 		p_err("failed to open object file");
 		goto err_free_reuse_maps;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 87520a87a75f..69a4d40c4227 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -69,6 +69,9 @@ struct bpf_load_program_attr {
 	__u32 prog_ifindex;
 };
 
+/* Flags to direct loading requirements */
+#define MAPS_RELAX_COMPAT	0x01
+
 /* Recommend log buffer size */
 #define BPF_LOG_BUF_SIZE (256 * 1024)
 int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 176cf5523728..bd71efcc53be 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -562,8 +562,9 @@ static int compare_bpf_map(const void *_a, const void *_b)
 }
 
 static int
-bpf_object__init_maps(struct bpf_object *obj)
+bpf_object__init_maps(struct bpf_object *obj, int flags)
 {
+	bool strict = !(flags & MAPS_RELAX_COMPAT);
 	int i, map_idx, map_def_sz, nr_maps = 0;
 	Elf_Scn *scn;
 	Elf_Data *data;
@@ -685,7 +686,8 @@ bpf_object__init_maps(struct bpf_object *obj)
 						   "has unrecognized, non-zero "
 						   "options\n",
 						   obj->path, map_name);
-					return -EINVAL;
+					if (strict)
+						return -EINVAL;
 				}
 			}
 			memcpy(&obj->maps[map_idx].def, def,
@@ -716,7 +718,7 @@ static bool section_have_execinstr(struct bpf_object *obj, int idx)
 	return false;
 }
 
-static int bpf_object__elf_collect(struct bpf_object *obj)
+static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 {
 	Elf *elf = obj->efile.elf;
 	GElf_Ehdr *ep = &obj->efile.ehdr;
@@ -843,7 +845,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		return LIBBPF_ERRNO__FORMAT;
 	}
 	if (obj->efile.maps_shndx >= 0) {
-		err = bpf_object__init_maps(obj);
+		err = bpf_object__init_maps(obj, flags);
 		if (err)
 			goto out;
 	}
@@ -1515,7 +1517,7 @@ static int bpf_object__validate(struct bpf_object *obj, bool needs_kver)
 
 static struct bpf_object *
 __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
-		   bool needs_kver)
+		   bool needs_kver, int flags)
 {
 	struct bpf_object *obj;
 	int err;
@@ -1531,7 +1533,7 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
 
 	CHECK_ERR(bpf_object__elf_init(obj), err, out);
 	CHECK_ERR(bpf_object__check_endianness(obj), err, out);
-	CHECK_ERR(bpf_object__elf_collect(obj), err, out);
+	CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out);
 	CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
 	CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out);
 
@@ -1542,7 +1544,8 @@ out:
 	return ERR_PTR(err);
 }
 
-struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr)
+struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
+					    int flags)
 {
 	/* param validation */
 	if (!attr->file)
@@ -1551,7 +1554,13 @@ struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr)
 	pr_debug("loading %s\n", attr->file);
 
 	return __bpf_object__open(attr->file, NULL, 0,
-				  bpf_prog_type__needs_kver(attr->prog_type));
+				  bpf_prog_type__needs_kver(attr->prog_type),
+				  flags);
+}
+
+struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr)
+{
+	return __bpf_object__open_xattr(attr, 0);
 }
 
 struct bpf_object *bpf_object__open(const char *path)
@@ -1584,7 +1593,7 @@ struct bpf_object *bpf_object__open_buffer(void *obj_buf,
 	pr_debug("loading object '%s' from buffer\n",
 		 name);
 
-	return __bpf_object__open(name, obj_buf, obj_buf_sz, true);
+	return __bpf_object__open(name, obj_buf, obj_buf_sz, true, true);
 }
 
 int bpf_object__unload(struct bpf_object *obj)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 8af8d3663991..7e9c801a9fdd 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -61,6 +61,8 @@ struct bpf_object_open_attr {
 
 struct bpf_object *bpf_object__open(const char *path);
 struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr);
+struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
+					    int flags);
 struct bpf_object *bpf_object__open_buffer(void *obj_buf,
 					   size_t obj_buf_sz,
 					   const char *name);
-- 
cgit v1.2.3


From 0b592b5a01bef5416472ec610d3191e019c144a5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 15 Oct 2018 16:30:36 -0700
Subject: tools: bpftool: add map create command

Add a way of creating maps from user space.  The command takes
as parameters most of the attributes of the map creation system
call command.  After map is created its pinned to bpffs.  This makes
it possible to easily and dynamically (without rebuilding programs)
test various corner cases related to map creation.

Map type names are taken from bpftool's array used for printing.
In general these days we try to make use of libbpf type names, but
there are no map type names in libbpf as of today.

As with most features I add the motivation is testing (offloads) :)

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/Documentation/bpftool-map.rst |  15 +++-
 tools/bpf/bpftool/Documentation/bpftool.rst     |   4 +-
 tools/bpf/bpftool/bash-completion/bpftool       |  38 +++++++-
 tools/bpf/bpftool/common.c                      |  21 +++++
 tools/bpf/bpftool/main.h                        |   1 +
 tools/bpf/bpftool/map.c                         | 110 +++++++++++++++++++++++-
 6 files changed, 183 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index a6258bc8ec4f..3497f2d80328 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -15,13 +15,15 @@ SYNOPSIS
 	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } }
 
 	*COMMANDS* :=
-	{ **show** | **list** | **dump** | **update** | **lookup** | **getnext** | **delete**
-	| **pin** | **help** }
+	{ **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext**
+	| **delete** | **pin** | **help** }
 
 MAP COMMANDS
 =============
 
 |	**bpftool** **map { show | list }**   [*MAP*]
+|	**bpftool** **map create**     *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* \
+|		**entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**dev** *NAME*]
 |	**bpftool** **map dump**       *MAP*
 |	**bpftool** **map update**     *MAP*  **key** *DATA*   **value** *VALUE* [*UPDATE_FLAGS*]
 |	**bpftool** **map lookup**     *MAP*  **key** *DATA*
@@ -36,6 +38,11 @@ MAP COMMANDS
 |	*PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
 |	*VALUE* := { *DATA* | *MAP* | *PROG* }
 |	*UPDATE_FLAGS* := { **any** | **exist** | **noexist** }
+|	*TYPE* := { **hash** | **array** | **prog_array** | **perf_event_array** | **percpu_hash**
+|		| **percpu_array** | **stack_trace** | **cgroup_array** | **lru_hash**
+|		| **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps**
+|		| **devmap** | **sockmap** | **cpumap** | **xskmap** | **sockhash**
+|		| **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** }
 
 DESCRIPTION
 ===========
@@ -47,6 +54,10 @@ DESCRIPTION
 		  Output will start with map ID followed by map type and
 		  zero or more named attributes (depending on kernel version).
 
+	**bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE*  **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**dev** *NAME*]
+		  Create a new map with given parameters and pin it to *bpffs*
+		  as *FILE*.
+
 	**bpftool map dump**    *MAP*
 		  Dump all entries in a given *MAP*.
 
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 65488317fefa..04cd4f92ab89 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -22,8 +22,8 @@ SYNOPSIS
 	| { **-j** | **--json** } [{ **-p** | **--pretty** }] }
 
 	*MAP-COMMANDS* :=
-	{ **show** | **list** | **dump** | **update** | **lookup** | **getnext** | **delete**
-	| **pin** | **event_pipe** | **help** }
+	{ **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext**
+	| **delete** | **pin** | **event_pipe** | **help** }
 
 	*PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin**
 	| **load** | **attach** | **detach** | **help** }
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index ac85207cba8d..c56545e87b0d 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -387,6 +387,42 @@ _bpftool()
                             ;;
                     esac
                     ;;
+                create)
+                    case $prev in
+                        $command)
+                            _filedir
+                            return 0
+                            ;;
+                        type)
+                            COMPREPLY=( $( compgen -W 'hash array prog_array \
+                                perf_event_array percpu_hash percpu_array \
+                                stack_trace cgroup_array lru_hash \
+                                lru_percpu_hash lpm_trie array_of_maps \
+                                hash_of_maps devmap sockmap cpumap xskmap \
+                                sockhash cgroup_storage reuseport_sockarray \
+                                percpu_cgroup_storage' -- \
+                                                   "$cur" ) )
+                            return 0
+                            ;;
+                        key|value|flags|name|entries)
+                            return 0
+                            ;;
+                        dev)
+                            _sysfs_get_netdevs
+                            return 0
+                            ;;
+                        *)
+                            _bpftool_once_attr 'type'
+                            _bpftool_once_attr 'key'
+                            _bpftool_once_attr 'value'
+                            _bpftool_once_attr 'entries'
+                            _bpftool_once_attr 'name'
+                            _bpftool_once_attr 'flags'
+                            _bpftool_once_attr 'dev'
+                            return 0
+                            ;;
+                    esac
+                    ;;
                 lookup|getnext|delete)
                     case $prev in
                         $command)
@@ -500,7 +536,7 @@ _bpftool()
                 *)
                     [[ $prev == $object ]] && \
                         COMPREPLY=( $( compgen -W 'delete dump getnext help \
-                            lookup pin event_pipe show list update' -- \
+                            lookup pin event_pipe show list update create' -- \
                             "$cur" ) )
                     ;;
             esac
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index b3a0709ea7ed..3318da8060bd 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -618,3 +618,24 @@ void print_dev_json(__u32 ifindex, __u64 ns_dev, __u64 ns_inode)
 		jsonw_string_field(json_wtr, "ifname", name);
 	jsonw_end_object(json_wtr);
 }
+
+int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what)
+{
+	char *endptr;
+
+	NEXT_ARGP();
+
+	if (*val) {
+		p_err("%s already specified", what);
+		return -1;
+	}
+
+	*val = strtoul(**argv, &endptr, 0);
+	if (*endptr) {
+		p_err("can't parse %s as %s", **argv, what);
+		return -1;
+	}
+	NEXT_ARGP();
+
+	return 0;
+}
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 91fd697303cb..28ee769bd11b 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -139,6 +139,7 @@ int do_cgroup(int argc, char **arg);
 int do_perf(int argc, char **arg);
 int do_net(int argc, char **arg);
 
+int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what);
 int prog_parse_fd(int *argc, char ***argv);
 int map_parse_fd(int *argc, char ***argv);
 int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len);
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 9f5de48f8a99..7bf38f0e152e 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -36,6 +36,7 @@
 #include <fcntl.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
+#include <net/if.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -94,6 +95,17 @@ static bool map_is_map_of_progs(__u32 type)
 	return type == BPF_MAP_TYPE_PROG_ARRAY;
 }
 
+static int map_type_from_str(const char *type)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(map_type_name); i++)
+		/* Don't allow prefixing in case of possible future shadowing */
+		if (map_type_name[i] && !strcmp(map_type_name[i], type))
+			return i;
+	return -1;
+}
+
 static void *alloc_value(struct bpf_map_info *info)
 {
 	if (map_is_per_cpu(info->type))
@@ -1058,6 +1070,92 @@ static int do_pin(int argc, char **argv)
 	return err;
 }
 
+static int do_create(int argc, char **argv)
+{
+	struct bpf_create_map_attr attr = { NULL, };
+	const char *pinfile;
+	int err, fd;
+
+	if (!REQ_ARGS(7))
+		return -1;
+	pinfile = GET_ARG();
+
+	while (argc) {
+		if (!REQ_ARGS(2))
+			return -1;
+
+		if (is_prefix(*argv, "type")) {
+			NEXT_ARG();
+
+			if (attr.map_type) {
+				p_err("map type already specified");
+				return -1;
+			}
+
+			attr.map_type = map_type_from_str(*argv);
+			if ((int)attr.map_type < 0) {
+				p_err("unrecognized map type: %s", *argv);
+				return -1;
+			}
+			NEXT_ARG();
+		} else if (is_prefix(*argv, "name")) {
+			NEXT_ARG();
+			attr.name = GET_ARG();
+		} else if (is_prefix(*argv, "key")) {
+			if (parse_u32_arg(&argc, &argv, &attr.key_size,
+					  "key size"))
+				return -1;
+		} else if (is_prefix(*argv, "value")) {
+			if (parse_u32_arg(&argc, &argv, &attr.value_size,
+					  "value size"))
+				return -1;
+		} else if (is_prefix(*argv, "entries")) {
+			if (parse_u32_arg(&argc, &argv, &attr.max_entries,
+					  "max entries"))
+				return -1;
+		} else if (is_prefix(*argv, "flags")) {
+			if (parse_u32_arg(&argc, &argv, &attr.map_flags,
+					  "flags"))
+				return -1;
+		} else if (is_prefix(*argv, "dev")) {
+			NEXT_ARG();
+
+			if (attr.map_ifindex) {
+				p_err("offload device already specified");
+				return -1;
+			}
+
+			attr.map_ifindex = if_nametoindex(*argv);
+			if (!attr.map_ifindex) {
+				p_err("unrecognized netdevice '%s': %s",
+				      *argv, strerror(errno));
+				return -1;
+			}
+			NEXT_ARG();
+		}
+	}
+
+	if (!attr.name) {
+		p_err("map name not specified");
+		return -1;
+	}
+
+	fd = bpf_create_map_xattr(&attr);
+	if (fd < 0) {
+		p_err("map create failed: %s", strerror(errno));
+		return -1;
+	}
+
+	err = do_pin_fd(fd, pinfile);
+	close(fd);
+	if (err)
+		return err;
+
+	if (json_output)
+		jsonw_null(json_wtr);
+	return 0;
+}
+
 static int do_help(int argc, char **argv)
 {
 	if (json_output) {
@@ -1067,6 +1165,9 @@ static int do_help(int argc, char **argv)
 
 	fprintf(stderr,
 		"Usage: %s %s { show | list }   [MAP]\n"
+		"       %s %s create     FILE type TYPE key KEY_SIZE value VALUE_SIZE \\\n"
+		"                              entries MAX_ENTRIES name NAME [flags FLAGS] \\\n"
+		"                              [dev NAME]\n"
 		"       %s %s dump       MAP\n"
 		"       %s %s update     MAP  key DATA value VALUE [UPDATE_FLAGS]\n"
 		"       %s %s lookup     MAP  key DATA\n"
@@ -1081,11 +1182,17 @@ static int do_help(int argc, char **argv)
 		"       " HELP_SPEC_PROGRAM "\n"
 		"       VALUE := { DATA | MAP | PROG }\n"
 		"       UPDATE_FLAGS := { any | exist | noexist }\n"
+		"       TYPE := { hash | array | prog_array | perf_event_array | percpu_hash |\n"
+		"                 percpu_array | stack_trace | cgroup_array | lru_hash |\n"
+		"                 lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n"
+		"                 devmap | sockmap | cpumap | xskmap | sockhash |\n"
+		"                 cgroup_storage | reuseport_sockarray | percpu_cgroup_storage }\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
-		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]);
+		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
+		bin_name, argv[-2]);
 
 	return 0;
 }
@@ -1101,6 +1208,7 @@ static const struct cmd cmds[] = {
 	{ "delete",	do_delete },
 	{ "pin",	do_pin },
 	{ "event_pipe",	do_event_pipe },
+	{ "create",	do_create },
 	{ 0 }
 };
 
-- 
cgit v1.2.3


From 55bbc8ff4987d05b7d2f2d513caabd0a58fec021 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Fri, 12 Oct 2018 23:54:13 +0200
Subject: selftests: pmtu: Allow selection of single tests

As number of tests is growing, it's quite convenient to allow
single tests to be run.

Display usage when the script is run with any invalid argument,
keep existing semantics when no arguments are passed so that
automated runs won't break.

Instead of just looping on the list of requested tests, if any,
check first that they exist, and go through them in a nested
loop to keep the existing way to display test descriptions.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index b9cdb68df4c5..8278a24f5ba6 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -641,6 +641,20 @@ test_pmtu_vti6_link_change_mtu() {
 	return ${fail}
 }
 
+usage() {
+	echo
+	echo "$0 [TEST]..."
+	echo "If no TEST argument is given, all tests will be run."
+	echo
+	echo "Available tests${tests}"
+	exit 1
+}
+
+for arg do
+	# Check first that all requested tests are available before running any
+	command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; }
+done
+
 trap cleanup EXIT
 
 exitcode=0
@@ -650,6 +664,13 @@ IFS="
 for t in ${tests}; do
 	[ $desc -eq 0 ] && name="${t}" && desc=1 && continue || desc=0
 
+	run_this=1
+	for arg do
+		[ "${arg}" = "${name}" ] && run_this=1 && break
+		run_this=0
+	done
+	[ $run_this -eq 0 ] && continue
+
 	(
 		unset IFS
 		eval test_${name}
-- 
cgit v1.2.3


From bb059fb20447c869970ebd296010c1a822706c58 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Fri, 12 Oct 2018 23:54:14 +0200
Subject: selftests: pmtu: Add optional traffic captures for single tests

If --trace is passed as an option and tcpdump is available,
capture traffic for all relevant interfaces to per-test pcap
files named <test>_<interface>.pcap.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 60 ++++++++++++++++++++++++++++++++-----
 1 file changed, 53 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 8278a24f5ba6..a369d616b390 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -142,6 +142,7 @@ dummy6_mask="64"
 
 cleanup_done=1
 err_buf=
+tcpdump_pids=
 
 err() {
 	err_buf="${err_buf}${1}
@@ -284,7 +285,24 @@ setup() {
 	done
 }
 
+trace() {
+	[ $tracing -eq 0 ] && return
+
+	for arg do
+		[ "${ns_cmd}" = "" ] && ns_cmd="${arg}" && continue
+		${ns_cmd} tcpdump -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null &
+		tcpdump_pids="${tcpdump_pids} $!"
+		ns_cmd=
+	done
+	sleep 1
+}
+
 cleanup() {
+	for pid in ${tcpdump_pids}; do
+		kill ${pid}
+	done
+	tcpdump_pids=
+
 	[ ${cleanup_done} -eq 1 ] && return
 	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
 		ip netns del ${n} 2> /dev/null
@@ -357,6 +375,10 @@ test_pmtu_ipvX() {
 	family=${1}
 
 	setup namespaces routing || return 2
+	trace "${ns_a}"  veth_A-R1    "${ns_r1}" veth_R1-A \
+	      "${ns_r1}" veth_R1-B    "${ns_b}"  veth_B-R1 \
+	      "${ns_a}"  veth_A-R2    "${ns_r2}" veth_R2-A \
+	      "${ns_r2}" veth_R2-B    "${ns_b}"  veth_B-R2
 
 	if [ ${family} -eq 4 ]; then
 		ping=ping
@@ -445,6 +467,8 @@ test_pmtu_ipv6_exception() {
 
 test_pmtu_vti4_exception() {
 	setup namespaces veth vti4 xfrm4 || return 2
+	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
+	      "${ns_a}" vti4_a    "${ns_b}" vti4_b
 
 	veth_mtu=1500
 	vti_mtu=$((veth_mtu - 20))
@@ -473,6 +497,8 @@ test_pmtu_vti4_exception() {
 
 test_pmtu_vti6_exception() {
 	setup namespaces veth vti6 xfrm6 || return 2
+	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
+	      "${ns_a}" vti6_a    "${ns_b}" vti6_b
 	fail=0
 
 	# Create route exception by exceeding link layer MTU
@@ -643,29 +669,49 @@ test_pmtu_vti6_link_change_mtu() {
 
 usage() {
 	echo
-	echo "$0 [TEST]..."
+	echo "$0 [OPTIONS] [TEST]..."
 	echo "If no TEST argument is given, all tests will be run."
 	echo
+	echo "Options"
+	echo "  --trace: capture traffic to TEST_INTERFACE.pcap"
+	echo
 	echo "Available tests${tests}"
 	exit 1
 }
 
+exitcode=0
+desc=0
+IFS="	
+"
+
+tracing=0
 for arg do
-	# Check first that all requested tests are available before running any
-	command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; }
+	if [ "${arg}" != "${arg#--*}" ]; then
+		opt="${arg#--}"
+		if [ "${opt}" = "trace" ]; then
+			if which tcpdump > /dev/null 2>&1; then
+				tracing=1
+			else
+				echo "=== tcpdump not available, tracing disabled"
+			fi
+		else
+			usage
+		fi
+	else
+		# Check first that all requested tests are available before
+		# running any
+		command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; }
+	fi
 done
 
 trap cleanup EXIT
 
-exitcode=0
-desc=0
-IFS="	
-"
 for t in ${tests}; do
 	[ $desc -eq 0 ] && name="${t}" && desc=1 && continue || desc=0
 
 	run_this=1
 	for arg do
+		[ "${arg}" != "${arg#--*}" ] && continue
 		[ "${arg}" = "${name}" ] && run_this=1 && break
 		run_this=0
 	done
-- 
cgit v1.2.3


From 4ab8455f8bd83298bf7f67ab9357e3b1cc765c7d Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Wed, 3 Oct 2018 23:20:52 +0200
Subject: perf evsel: Store ids for events with their own cpus
 perf_event__synthesize_event_update_cpus

John reported crash when recording on an event under PMU with cpumask defined:

  root@localhost:~# ./perf_debug_ record -e armv8_pmuv3_0/br_mis_pred/ sleep 1
  perf: Segmentation fault
  Obtained 9 stack frames.
  ./perf_debug_() [0x4c5ef8]
  [0xffff82ba267c]
  ./perf_debug_() [0x4bc5a8]
  ./perf_debug_() [0x419550]
  ./perf_debug_() [0x41a928]
  ./perf_debug_() [0x472f58]
  ./perf_debug_() [0x473210]
  ./perf_debug_() [0x4070f4]
  /lib/aarch64-linux-gnu/libc.so.6(__libc_start_main+0xe0) [0xffff8294c8a0]
  Segmentation fault (core dumped)

We synthesize an update event that needs to touch the evsel id array, which is
not defined at that time. Fixing this by forcing the id allocation for events
with their own cpus.

Reported-by: John Garry <john.garry@huawei.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: John Garry <john.garry@huawei.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linuxarm@huawei.com
Fixes: bfd8f72c2778 ("perf record: Synthesize unit/scale/... in event update")
Link: http://lkml.kernel.org/r/20181003212052.GA32371@krava
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-report.c | 1 +
 tools/perf/util/evsel.c     | 3 +++
 2 files changed, 4 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 76e12bcd1765..b2188e623e22 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -981,6 +981,7 @@ int cmd_report(int argc, const char **argv)
 			.id_index	 = perf_event__process_id_index,
 			.auxtrace_info	 = perf_event__process_auxtrace_info,
 			.auxtrace	 = perf_event__process_auxtrace,
+			.event_update	 = perf_event__process_event_update,
 			.feature	 = process_feature_event,
 			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1a61628a1c12..e596ae358c4d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1089,6 +1089,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		attr->exclude_user   = 1;
 	}
 
+	if (evsel->own_cpus)
+		evsel->attr.read_format |= PERF_FORMAT_ID;
+
 	/*
 	 * Apply event specific term settings,
 	 * it overloads any global configuration.
-- 
cgit v1.2.3


From 36b8d4628d3cc8f5a748e508cce8673bc00fc63c Mon Sep 17 00:00:00 2001
From: Jarod Wilson <jarod@redhat.com>
Date: Thu, 6 Sep 2018 18:18:12 -0400
Subject: perf tools: Fix use of alternatives to find JDIR

When a build is run from something like a cron job, the user's $PATH is
rather minimal, of note, not including /usr/sbin in my own case. Because
of that, an automated rpm package build ultimately fails to find
libperf-jvmti.so, because somewhere within the build, this happens...

  /bin/sh: alternatives: command not found
  /bin/sh: alternatives: command not found
  Makefile.config:849: No openjdk development package found, please install
  JDK package, e.g. openjdk-8-jdk, java-1.8.0-openjdk-devel

...and while the build continues, libperf-jvmti.so isn't built, and
things fall down when rpm tries to find all the %files specified. Exact
same system builds everything just fine when the job is launched from a
login shell instead of a cron job, since alternatives is in $PATH, so
openjdk is actually found.

The test required to get into this section of code actually specifies
the full path, as does a block just above it, so let's do that here too.

Signed-off-by: Jarod Wilson <jarod@redhat.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: William Cohen <wcohen@redhat.com>
Fixes: d4dfdf00d43e ("perf jvmti: Plug compilation into perf build")
Link: http://lkml.kernel.org/r/20180906221812.11167-1-jarod@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.config | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index f6d1a03c7523..e30d20fb482d 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -833,7 +833,7 @@ ifndef NO_JVMTI
     JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | awk '{print $$3}')
   else
     ifneq (,$(wildcard /usr/sbin/alternatives))
-      JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
+      JDIR=$(shell /usr/sbin/alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
     endif
   endif
   ifndef JDIR
-- 
cgit v1.2.3


From 421f4292f46e871cdcf8bdc3e6fdfcefe2e81a9d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 16 Oct 2018 15:59:36 +0200
Subject: bpf, tls: add tls header to tools infrastructure

Andrey reported a build error for the BPF kselftest suite when compiled on
a machine which does not have tls related header bits installed natively:

  test_sockmap.c:120:23: fatal error: linux/tls.h: No such file or directory
   #include <linux/tls.h>
                         ^
  compilation terminated.

Fix it by adding the header to the tools include infrastructure and add
definitions such as SOL_TLS that could potentially be missing.

Fixes: e9dd904708c4 ("bpf: add tls support for testing in test_sockmap")
Reported-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/tls.h             | 78 ++++++++++++++++++++++++++++++
 tools/testing/selftests/bpf/test_sockmap.c | 13 +++--
 2 files changed, 86 insertions(+), 5 deletions(-)
 create mode 100644 tools/include/uapi/linux/tls.h

(limited to 'tools')

diff --git a/tools/include/uapi/linux/tls.h b/tools/include/uapi/linux/tls.h
new file mode 100644
index 000000000000..ff02287495ac
--- /dev/null
+++ b/tools/include/uapi/linux/tls.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
+/*
+ * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _UAPI_LINUX_TLS_H
+#define _UAPI_LINUX_TLS_H
+
+#include <linux/types.h>
+
+/* TLS socket options */
+#define TLS_TX			1	/* Set transmit parameters */
+#define TLS_RX			2	/* Set receive parameters */
+
+/* Supported versions */
+#define TLS_VERSION_MINOR(ver)	((ver) & 0xFF)
+#define TLS_VERSION_MAJOR(ver)	(((ver) >> 8) & 0xFF)
+
+#define TLS_VERSION_NUMBER(id)	((((id##_VERSION_MAJOR) & 0xFF) << 8) |	\
+				 ((id##_VERSION_MINOR) & 0xFF))
+
+#define TLS_1_2_VERSION_MAJOR	0x3
+#define TLS_1_2_VERSION_MINOR	0x3
+#define TLS_1_2_VERSION		TLS_VERSION_NUMBER(TLS_1_2)
+
+/* Supported ciphers */
+#define TLS_CIPHER_AES_GCM_128				51
+#define TLS_CIPHER_AES_GCM_128_IV_SIZE			8
+#define TLS_CIPHER_AES_GCM_128_KEY_SIZE		16
+#define TLS_CIPHER_AES_GCM_128_SALT_SIZE		4
+#define TLS_CIPHER_AES_GCM_128_TAG_SIZE		16
+#define TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE		8
+
+#define TLS_SET_RECORD_TYPE	1
+#define TLS_GET_RECORD_TYPE	2
+
+struct tls_crypto_info {
+	__u16 version;
+	__u16 cipher_type;
+};
+
+struct tls12_crypto_info_aes_gcm_128 {
+	struct tls_crypto_info info;
+	unsigned char iv[TLS_CIPHER_AES_GCM_128_IV_SIZE];
+	unsigned char key[TLS_CIPHER_AES_GCM_128_KEY_SIZE];
+	unsigned char salt[TLS_CIPHER_AES_GCM_128_SALT_SIZE];
+	unsigned char rec_seq[TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE];
+};
+
+#endif /* _UAPI_LINUX_TLS_H */
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 10a5fa83c75a..7cb69ce6dfa2 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -28,6 +28,7 @@
 #include <linux/sock_diag.h>
 #include <linux/bpf.h>
 #include <linux/if_link.h>
+#include <linux/tls.h>
 #include <assert.h>
 #include <libgen.h>
 
@@ -43,6 +44,13 @@
 int running;
 static void running_handler(int a);
 
+#ifndef TCP_ULP
+# define TCP_ULP 31
+#endif
+#ifndef SOL_TLS
+# define SOL_TLS 282
+#endif
+
 /* randomly selected ports for testing on lo */
 #define S1_PORT 10000
 #define S2_PORT 10001
@@ -114,11 +122,6 @@ static void usage(char *argv[])
 	printf("\n");
 }
 
-#define TCP_ULP 31
-#define TLS_TX 1
-#define TLS_RX 2
-#include <linux/tls.h>
-
 char *sock_to_string(int s)
 {
 	if (s == c1)
-- 
cgit v1.2.3


From c458a6206d2a8600934617ccf88ba7d3a030faba Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 16 Oct 2018 13:48:18 +0200
Subject: perf tools: Fix tracing_path_mount proper path

If there's no tracefs (RHEL7) support the tracing_path_mount
returns debugfs path which results in following fail:

  # perf probe sys_write
  kprobe_events file does not exist - please rebuild kernel with CONFIG_KPROBE_EVENTS.
  Error: Failed to add events.

In tracing_path_debugfs_mount function we need to return the
'tracing' path instead of just the mount to make it work:

  # perf probe sys_write
  Added new event:
    probe:sys_write      (on sys_write)

  You can now use it in all perf tools, such as:

          perf record -e probe:sys_write -aR sleep 1

Adding the 'return tracing_path;' also to tracing_path_tracefs_mount
function just for consistency with tracing_path_debugfs_mount.

Upstream keeps working, because it has the tracefs support.

Link: http://lkml.kernel.org/n/tip-yiwkzexq9fk1ey1xg3gnjlw4@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Fixes: 23773ca18b39 ("perf tools: Make perf aware of tracefs")
Link: http://lkml.kernel.org/r/20181016114818.3595-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/api/fs/tracing_path.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c
index 120037496f77..5afb11b30fca 100644
--- a/tools/lib/api/fs/tracing_path.c
+++ b/tools/lib/api/fs/tracing_path.c
@@ -36,7 +36,7 @@ static const char *tracing_path_tracefs_mount(void)
 
 	__tracing_path_set("", mnt);
 
-	return mnt;
+	return tracing_path;
 }
 
 static const char *tracing_path_debugfs_mount(void)
@@ -49,7 +49,7 @@ static const char *tracing_path_debugfs_mount(void)
 
 	__tracing_path_set("tracing/", mnt);
 
-	return mnt;
+	return tracing_path;
 }
 
 const char *tracing_path_mount(void)
-- 
cgit v1.2.3


From 0ed149cf5239cc6e7e65bf00f769e8f1e91076c0 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Thu, 11 Oct 2018 22:46:55 -0700
Subject: perf cpu_map: Align cpu map synthesized events properly.

The size of the resulting cpu map can be smaller than a multiple of
sizeof(u64), resulting in SIGBUS on cpus like Sparc as the next event
will not be aligned properly.

Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Fixes: 6c872901af07 ("perf cpu_map: Add cpu_map event synthesize function")
Link: http://lkml.kernel.org/r/20181011.224655.716771175766946817.davem@davemloft.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/event.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 0cd42150f712..0988eb3b844b 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1081,6 +1081,7 @@ void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max
 	}
 
 	*size += sizeof(struct cpu_map_data);
+	*size = PERF_ALIGN(*size, sizeof(u64));
 	return zalloc(*size);
 }
 
-- 
cgit v1.2.3


From d4046e8e17b9f378cb861982ef71c63911b5dff3 Mon Sep 17 00:00:00 2001
From: Milian Wolff <milian.wolff@kdab.com>
Date: Wed, 26 Sep 2018 15:52:07 +0200
Subject: perf report: Don't crash on invalid inline debug information

When the function name for an inline frame is invalid, we must not try
to demangle this symbol, otherwise we crash with:

  #0  0x0000555555895c01 in bfd_demangle ()
  #1  0x0000555555823262 in demangle_sym (dso=0x555555d92b90, elf_name=0x0, kmodule=0) at util/symbol-elf.c:215
  #2  dso__demangle_sym (dso=dso@entry=0x555555d92b90, kmodule=<optimized out>, kmodule@entry=0, elf_name=elf_name@entry=0x0) at util/symbol-elf.c:400
  #3  0x00005555557fef4b in new_inline_sym (funcname=0x0, base_sym=0x555555d92b90, dso=0x555555d92b90) at util/srcline.c:89
  #4  inline_list__append_dso_a2l (dso=dso@entry=0x555555c7bb00, node=node@entry=0x555555e31810, sym=sym@entry=0x555555d92b90) at util/srcline.c:264
  #5  0x00005555557ff27f in addr2line (dso_name=dso_name@entry=0x555555d92430 "/home/milian/.debug/.build-id/f7/186d14bb94f3c6161c010926da66033d24fce5/elf", addr=addr@entry=2888, file=file@entry=0x0,
      line=line@entry=0x0, dso=dso@entry=0x555555c7bb00, unwind_inlines=unwind_inlines@entry=true, node=0x555555e31810, sym=0x555555d92b90) at util/srcline.c:313
  #6  0x00005555557ffe7c in addr2inlines (sym=0x555555d92b90, dso=0x555555c7bb00, addr=2888, dso_name=0x555555d92430 "/home/milian/.debug/.build-id/f7/186d14bb94f3c6161c010926da66033d24fce5/elf")
      at util/srcline.c:358

So instead handle the case where we get invalid function names for
inlined frames and use a fallback '??' function name instead.

While this crash was originally reported by Hadrien for rust code, I can
now also reproduce it with trivial C++ code. Indeed, it seems like
libbfd fails to interpret the debug information for the inline frame
symbol name:

  $ addr2line -e /home/milian/.debug/.build-id/f7/186d14bb94f3c6161c010926da66033d24fce5/elf -if b48
  main
  /usr/include/c++/8.2.1/complex:610
  ??
  /usr/include/c++/8.2.1/complex:618
  ??
  /usr/include/c++/8.2.1/complex:675
  ??
  /usr/include/c++/8.2.1/complex:685
  main
  /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39

I've reported this bug upstream and also attached a patch there which
should fix this issue:

https://sourceware.org/bugzilla/show_bug.cgi?id=23715

Reported-by: Hadrien Grasland <grasland@lal.in2p3.fr>
Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Fixes: a64489c56c30 ("perf report: Find the inline stack for a given address")
[ The above 'Fixes:' cset is where originally the problem was
  introduced, i.e.  using a2l->funcname without checking if it is NULL,
  but this current patch fixes the current codebase, i.e. multiple csets
  were applied after a64489c56c30 before the problem was reported by Hadrien ]
Link: http://lkml.kernel.org/r/20180926135207.30263-3-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/srcline.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 09d6746e6ec8..e767c4a9d4d2 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -85,6 +85,9 @@ static struct symbol *new_inline_sym(struct dso *dso,
 	struct symbol *inline_sym;
 	char *demangled = NULL;
 
+	if (!funcname)
+		funcname = "??";
+
 	if (dso) {
 		demangled = dso__demangle_sym(dso, 0, funcname);
 		if (demangled)
-- 
cgit v1.2.3


From 298faf53200fc02af38d32715697df6e661c1257 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 16 Oct 2018 17:06:07 +0200
Subject: perf tools: Pass build flags to traceevent build

So the extra user build flags are propagated to libtraceevent.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: "Herton R. Krzesinski" <herton@redhat.com>
Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Cc: Yordan Karadzhov (VMware) <y.karadz@gmail.com>
Link: http://lkml.kernel.org/r/20181016150614.21260-3-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.perf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5224ade3d5af..0be411695379 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -635,7 +635,7 @@ $(LIBPERF_IN): prepare FORCE
 $(LIB_FILE): $(LIBPERF_IN)
 	$(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBPERF_IN) $(LIB_OBJS)
 
-LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ)
+LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) 'EXTRA_CFLAGS=$(EXTRA_CFLAGS)' 'LDFLAGS=$(LDFLAGS)'
 
 $(LIBTRACEEVENT): FORCE
 	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a
-- 
cgit v1.2.3


From ab9e084821221b2eda57a512535fe35b49e672d8 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Mon, 15 Oct 2018 22:50:34 -0700
Subject: libbpf: Per-symbol visibility for DSO

Make global symbols in libbpf DSO hidden by default with
-fvisibility=hidden and export symbols that are part of ABI explicitly
with __attribute__((visibility("default"))).

This is common practice that should prevent from accidentally exporting
a symbol, that is not supposed to be a part of ABI what, in turn,
improves both libbpf developer- and user-experiences. See [1] for more
details.

Export control becomes more important since more and more projects use
libbpf.

The patch doesn't export a bunch of netlink related functions since as
agreed in [2] they'll be reworked. That doesn't break bpftool since
bpftool links libbpf statically.

[1] https://www.akkadia.org/drepper/dsohowto.pdf (2.2 Export Control)
[2] https://www.mail-archive.com/netdev@vger.kernel.org/msg251434.html

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/Makefile |   1 +
 tools/lib/bpf/bpf.h    | 118 +++++++++++++++++--------------
 tools/lib/bpf/btf.h    |  22 +++---
 tools/lib/bpf/libbpf.h | 186 ++++++++++++++++++++++++++-----------------------
 4 files changed, 179 insertions(+), 148 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 79d84413ddf2..425b480bda75 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -125,6 +125,7 @@ override CFLAGS += $(EXTRA_WARNINGS)
 override CFLAGS += -Werror -Wall
 override CFLAGS += -fPIC
 override CFLAGS += $(INCLUDES)
+override CFLAGS += -fvisibility=hidden
 
 ifeq ($(VERBOSE),1)
   Q =
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 69a4d40c4227..258c3c178333 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -27,6 +27,10 @@
 #include <stdbool.h>
 #include <stddef.h>
 
+#ifndef LIBBPF_API
+#define LIBBPF_API __attribute__((visibility("default")))
+#endif
+
 struct bpf_create_map_attr {
 	const char *name;
 	enum bpf_map_type map_type;
@@ -42,21 +46,24 @@ struct bpf_create_map_attr {
 	__u32 inner_map_fd;
 };
 
-int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
-int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
-			int key_size, int value_size, int max_entries,
-			__u32 map_flags, int node);
-int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
-			int key_size, int value_size, int max_entries,
-			__u32 map_flags);
-int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
-		   int max_entries, __u32 map_flags);
-int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
-			       int key_size, int inner_map_fd, int max_entries,
-			       __u32 map_flags, int node);
-int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name,
-			  int key_size, int inner_map_fd, int max_entries,
-			  __u32 map_flags);
+LIBBPF_API int
+bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
+LIBBPF_API int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
+				   int key_size, int value_size,
+				   int max_entries, __u32 map_flags, int node);
+LIBBPF_API int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
+				   int key_size, int value_size,
+				   int max_entries, __u32 map_flags);
+LIBBPF_API int bpf_create_map(enum bpf_map_type map_type, int key_size,
+			      int value_size, int max_entries, __u32 map_flags);
+LIBBPF_API int bpf_create_map_in_map_node(enum bpf_map_type map_type,
+					  const char *name, int key_size,
+					  int inner_map_fd, int max_entries,
+					  __u32 map_flags, int node);
+LIBBPF_API int bpf_create_map_in_map(enum bpf_map_type map_type,
+				     const char *name, int key_size,
+				     int inner_map_fd, int max_entries,
+				     __u32 map_flags);
 
 struct bpf_load_program_attr {
 	enum bpf_prog_type prog_type;
@@ -74,44 +81,49 @@ struct bpf_load_program_attr {
 
 /* Recommend log buffer size */
 #define BPF_LOG_BUF_SIZE (256 * 1024)
-int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
-			   char *log_buf, size_t log_buf_sz);
-int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
-		     size_t insns_cnt, const char *license,
-		     __u32 kern_version, char *log_buf,
-		     size_t log_buf_sz);
-int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
-		       size_t insns_cnt, int strict_alignment,
-		       const char *license, __u32 kern_version,
-		       char *log_buf, size_t log_buf_sz, int log_level);
+LIBBPF_API int
+bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
+		       char *log_buf, size_t log_buf_sz);
+LIBBPF_API int bpf_load_program(enum bpf_prog_type type,
+				const struct bpf_insn *insns, size_t insns_cnt,
+				const char *license, __u32 kern_version,
+				char *log_buf, size_t log_buf_sz);
+LIBBPF_API int bpf_verify_program(enum bpf_prog_type type,
+				  const struct bpf_insn *insns,
+				  size_t insns_cnt, int strict_alignment,
+				  const char *license, __u32 kern_version,
+				  char *log_buf, size_t log_buf_sz,
+				  int log_level);
 
-int bpf_map_update_elem(int fd, const void *key, const void *value,
-			__u64 flags);
+LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value,
+				   __u64 flags);
 
-int bpf_map_lookup_elem(int fd, const void *key, void *value);
-int bpf_map_delete_elem(int fd, const void *key);
-int bpf_map_get_next_key(int fd, const void *key, void *next_key);
-int bpf_obj_pin(int fd, const char *pathname);
-int bpf_obj_get(const char *pathname);
-int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
-		    unsigned int flags);
-int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
-int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type);
-int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
-		      void *data_out, __u32 *size_out, __u32 *retval,
-		      __u32 *duration);
-int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id);
-int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
-int bpf_prog_get_fd_by_id(__u32 id);
-int bpf_map_get_fd_by_id(__u32 id);
-int bpf_btf_get_fd_by_id(__u32 id);
-int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
-int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
-		   __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt);
-int bpf_raw_tracepoint_open(const char *name, int prog_fd);
-int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
-		 bool do_log);
-int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
-		      __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset,
-		      __u64 *probe_addr);
+LIBBPF_API int bpf_map_lookup_elem(int fd, const void *key, void *value);
+LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
+LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
+LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
+LIBBPF_API int bpf_obj_get(const char *pathname);
+LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd,
+			       enum bpf_attach_type type, unsigned int flags);
+LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
+LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd,
+				enum bpf_attach_type type);
+LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data,
+				 __u32 size, void *data_out, __u32 *size_out,
+				 __u32 *retval, __u32 *duration);
+LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id);
+LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
+LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_map_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
+LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type,
+			      __u32 query_flags, __u32 *attach_flags,
+			      __u32 *prog_ids, __u32 *prog_cnt);
+LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd);
+LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf,
+			    __u32 log_buf_size, bool do_log);
+LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
+				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
+				 __u64 *probe_offset, __u64 *probe_addr);
 #endif /* __LIBBPF_BPF_H */
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 6db5462bb2ef..b77e7080f7e7 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -6,6 +6,10 @@
 
 #include <linux/types.h>
 
+#ifndef LIBBPF_API
+#define LIBBPF_API __attribute__((visibility("default")))
+#endif
+
 #define BTF_ELF_SEC ".BTF"
 
 struct btf;
@@ -14,13 +18,15 @@ struct btf_type;
 typedef int (*btf_print_fn_t)(const char *, ...)
 	__attribute__((format(printf, 1, 2)));
 
-void btf__free(struct btf *btf);
-struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
-__s32 btf__find_by_name(const struct btf *btf, const char *type_name);
-const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id);
-__s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
-int btf__resolve_type(const struct btf *btf, __u32 type_id);
-int btf__fd(const struct btf *btf);
-const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
+LIBBPF_API void btf__free(struct btf *btf);
+LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
+LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
+				   const char *type_name);
+LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf,
+						  __u32 id);
+LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
+LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id);
+LIBBPF_API int btf__fd(const struct btf *btf);
+LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
 
 #endif /* __LIBBPF_BTF_H */
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 7e9c801a9fdd..1354cc9f8cba 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -16,6 +16,10 @@
 #include <sys/types.h>  // for size_t
 #include <linux/bpf.h>
 
+#ifndef LIBBPF_API
+#define LIBBPF_API __attribute__((visibility("default")))
+#endif
+
 enum libbpf_errno {
 	__LIBBPF_ERRNO__START = 4000,
 
@@ -37,7 +41,7 @@ enum libbpf_errno {
 	__LIBBPF_ERRNO__END,
 };
 
-int libbpf_strerror(int err, char *buf, size_t size);
+LIBBPF_API int libbpf_strerror(int err, char *buf, size_t size);
 
 /*
  * __printf is defined in include/linux/compiler-gcc.h. However,
@@ -47,9 +51,9 @@ int libbpf_strerror(int err, char *buf, size_t size);
 typedef int (*libbpf_print_fn_t)(const char *, ...)
 	__attribute__((format(printf, 1, 2)));
 
-void libbpf_set_print(libbpf_print_fn_t warn,
-		      libbpf_print_fn_t info,
-		      libbpf_print_fn_t debug);
+LIBBPF_API void libbpf_set_print(libbpf_print_fn_t warn,
+				 libbpf_print_fn_t info,
+				 libbpf_print_fn_t debug);
 
 /* Hide internal to user */
 struct bpf_object;
@@ -59,27 +63,28 @@ struct bpf_object_open_attr {
 	enum bpf_prog_type prog_type;
 };
 
-struct bpf_object *bpf_object__open(const char *path);
-struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr);
+LIBBPF_API struct bpf_object *bpf_object__open(const char *path);
+LIBBPF_API struct bpf_object *
+bpf_object__open_xattr(struct bpf_object_open_attr *attr);
 struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
 					    int flags);
-struct bpf_object *bpf_object__open_buffer(void *obj_buf,
-					   size_t obj_buf_sz,
-					   const char *name);
-int bpf_object__pin(struct bpf_object *object, const char *path);
-void bpf_object__close(struct bpf_object *object);
+LIBBPF_API struct bpf_object *bpf_object__open_buffer(void *obj_buf,
+						      size_t obj_buf_sz,
+						      const char *name);
+LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path);
+LIBBPF_API void bpf_object__close(struct bpf_object *object);
 
 /* Load/unload object into/from kernel */
-int bpf_object__load(struct bpf_object *obj);
-int bpf_object__unload(struct bpf_object *obj);
-const char *bpf_object__name(struct bpf_object *obj);
-unsigned int bpf_object__kversion(struct bpf_object *obj);
-int bpf_object__btf_fd(const struct bpf_object *obj);
+LIBBPF_API int bpf_object__load(struct bpf_object *obj);
+LIBBPF_API int bpf_object__unload(struct bpf_object *obj);
+LIBBPF_API const char *bpf_object__name(struct bpf_object *obj);
+LIBBPF_API unsigned int bpf_object__kversion(struct bpf_object *obj);
+LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj);
 
-struct bpf_program *
+LIBBPF_API struct bpf_program *
 bpf_object__find_program_by_title(struct bpf_object *obj, const char *title);
 
-struct bpf_object *bpf_object__next(struct bpf_object *prev);
+LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev);
 #define bpf_object__for_each_safe(pos, tmp)			\
 	for ((pos) = bpf_object__next(NULL),		\
 		(tmp) = bpf_object__next(pos);		\
@@ -87,19 +92,20 @@ struct bpf_object *bpf_object__next(struct bpf_object *prev);
 	     (pos) = (tmp), (tmp) = bpf_object__next(tmp))
 
 typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *);
-int bpf_object__set_priv(struct bpf_object *obj, void *priv,
-			 bpf_object_clear_priv_t clear_priv);
-void *bpf_object__priv(struct bpf_object *prog);
+LIBBPF_API int bpf_object__set_priv(struct bpf_object *obj, void *priv,
+				    bpf_object_clear_priv_t clear_priv);
+LIBBPF_API void *bpf_object__priv(struct bpf_object *prog);
 
-int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
-			     enum bpf_attach_type *expected_attach_type);
-int libbpf_attach_type_by_name(const char *name,
-			       enum bpf_attach_type *attach_type);
+LIBBPF_API int
+libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
+			 enum bpf_attach_type *expected_attach_type);
+LIBBPF_API int libbpf_attach_type_by_name(const char *name,
+					  enum bpf_attach_type *attach_type);
 
 /* Accessors of bpf_program */
 struct bpf_program;
-struct bpf_program *bpf_program__next(struct bpf_program *prog,
-				      struct bpf_object *obj);
+LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog,
+						 struct bpf_object *obj);
 
 #define bpf_object__for_each_program(pos, obj)		\
 	for ((pos) = bpf_program__next(NULL, (obj));	\
@@ -109,21 +115,24 @@ struct bpf_program *bpf_program__next(struct bpf_program *prog,
 typedef void (*bpf_program_clear_priv_t)(struct bpf_program *,
 					 void *);
 
-int bpf_program__set_priv(struct bpf_program *prog, void *priv,
-			  bpf_program_clear_priv_t clear_priv);
+LIBBPF_API int bpf_program__set_priv(struct bpf_program *prog, void *priv,
+				     bpf_program_clear_priv_t clear_priv);
 
-void *bpf_program__priv(struct bpf_program *prog);
-void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex);
+LIBBPF_API void *bpf_program__priv(struct bpf_program *prog);
+LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog,
+					 __u32 ifindex);
 
-const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
+LIBBPF_API const char *bpf_program__title(struct bpf_program *prog,
+					  bool needs_copy);
 
-int bpf_program__load(struct bpf_program *prog, char *license,
-		      __u32 kern_version);
-int bpf_program__fd(struct bpf_program *prog);
-int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
-			      int instance);
-int bpf_program__pin(struct bpf_program *prog, const char *path);
-void bpf_program__unload(struct bpf_program *prog);
+LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license,
+				 __u32 kern_version);
+LIBBPF_API int bpf_program__fd(struct bpf_program *prog);
+LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog,
+					 const char *path,
+					 int instance);
+LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path);
+LIBBPF_API void bpf_program__unload(struct bpf_program *prog);
 
 struct bpf_insn;
 
@@ -184,34 +193,36 @@ typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n,
 				  struct bpf_insn *insns, int insns_cnt,
 				  struct bpf_prog_prep_result *res);
 
-int bpf_program__set_prep(struct bpf_program *prog, int nr_instance,
-			  bpf_program_prep_t prep);
+LIBBPF_API int bpf_program__set_prep(struct bpf_program *prog, int nr_instance,
+				     bpf_program_prep_t prep);
 
-int bpf_program__nth_fd(struct bpf_program *prog, int n);
+LIBBPF_API int bpf_program__nth_fd(struct bpf_program *prog, int n);
 
 /*
  * Adjust type of BPF program. Default is kprobe.
  */
-int bpf_program__set_socket_filter(struct bpf_program *prog);
-int bpf_program__set_tracepoint(struct bpf_program *prog);
-int bpf_program__set_raw_tracepoint(struct bpf_program *prog);
-int bpf_program__set_kprobe(struct bpf_program *prog);
-int bpf_program__set_sched_cls(struct bpf_program *prog);
-int bpf_program__set_sched_act(struct bpf_program *prog);
-int bpf_program__set_xdp(struct bpf_program *prog);
-int bpf_program__set_perf_event(struct bpf_program *prog);
-void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type);
-void bpf_program__set_expected_attach_type(struct bpf_program *prog,
-					   enum bpf_attach_type type);
-
-bool bpf_program__is_socket_filter(struct bpf_program *prog);
-bool bpf_program__is_tracepoint(struct bpf_program *prog);
-bool bpf_program__is_raw_tracepoint(struct bpf_program *prog);
-bool bpf_program__is_kprobe(struct bpf_program *prog);
-bool bpf_program__is_sched_cls(struct bpf_program *prog);
-bool bpf_program__is_sched_act(struct bpf_program *prog);
-bool bpf_program__is_xdp(struct bpf_program *prog);
-bool bpf_program__is_perf_event(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_socket_filter(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_tracepoint(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_raw_tracepoint(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_kprobe(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog);
+LIBBPF_API void bpf_program__set_type(struct bpf_program *prog,
+				      enum bpf_prog_type type);
+LIBBPF_API void
+bpf_program__set_expected_attach_type(struct bpf_program *prog,
+				      enum bpf_attach_type type);
+
+LIBBPF_API bool bpf_program__is_socket_filter(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_tracepoint(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_raw_tracepoint(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_kprobe(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_sched_cls(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_sched_act(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_xdp(struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_perf_event(struct bpf_program *prog);
 
 /*
  * No need for __attribute__((packed)), all members of 'bpf_map_def'
@@ -232,39 +243,39 @@ struct bpf_map_def {
  * so no need to worry about a name clash.
  */
 struct bpf_map;
-struct bpf_map *
+LIBBPF_API struct bpf_map *
 bpf_object__find_map_by_name(struct bpf_object *obj, const char *name);
 
 /*
  * Get bpf_map through the offset of corresponding struct bpf_map_def
  * in the BPF object file.
  */
-struct bpf_map *
+LIBBPF_API struct bpf_map *
 bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset);
 
-struct bpf_map *
+LIBBPF_API struct bpf_map *
 bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
 #define bpf_map__for_each(pos, obj)		\
 	for ((pos) = bpf_map__next(NULL, (obj));	\
 	     (pos) != NULL;				\
 	     (pos) = bpf_map__next((pos), (obj)))
 
-int bpf_map__fd(struct bpf_map *map);
-const struct bpf_map_def *bpf_map__def(struct bpf_map *map);
-const char *bpf_map__name(struct bpf_map *map);
-__u32 bpf_map__btf_key_type_id(const struct bpf_map *map);
-__u32 bpf_map__btf_value_type_id(const struct bpf_map *map);
+LIBBPF_API int bpf_map__fd(struct bpf_map *map);
+LIBBPF_API const struct bpf_map_def *bpf_map__def(struct bpf_map *map);
+LIBBPF_API const char *bpf_map__name(struct bpf_map *map);
+LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map);
+LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map);
 
 typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
-int bpf_map__set_priv(struct bpf_map *map, void *priv,
-		      bpf_map_clear_priv_t clear_priv);
-void *bpf_map__priv(struct bpf_map *map);
-int bpf_map__reuse_fd(struct bpf_map *map, int fd);
-bool bpf_map__is_offload_neutral(struct bpf_map *map);
-void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
-int bpf_map__pin(struct bpf_map *map, const char *path);
+LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv,
+				 bpf_map_clear_priv_t clear_priv);
+LIBBPF_API void *bpf_map__priv(struct bpf_map *map);
+LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
+LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map);
+LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
+LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
 
-long libbpf_get_error(const void *ptr);
+LIBBPF_API long libbpf_get_error(const void *ptr);
 
 struct bpf_prog_load_attr {
 	const char *file;
@@ -273,12 +284,12 @@ struct bpf_prog_load_attr {
 	int ifindex;
 };
 
-int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
-			struct bpf_object **pobj, int *prog_fd);
-int bpf_prog_load(const char *file, enum bpf_prog_type type,
-		  struct bpf_object **pobj, int *prog_fd);
+LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
+				   struct bpf_object **pobj, int *prog_fd);
+LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type,
+			     struct bpf_object **pobj, int *prog_fd);
 
-int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
+LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
 
 enum bpf_perf_event_ret {
 	LIBBPF_PERF_EVENT_DONE	= 0,
@@ -288,10 +299,11 @@ enum bpf_perf_event_ret {
 
 typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(void *event,
 							  void *priv);
-int bpf_perf_event_read_simple(void *mem, unsigned long size,
-			       unsigned long page_size,
-			       void **buf, size_t *buf_len,
-			       bpf_perf_event_print_t fn, void *priv);
+LIBBPF_API int bpf_perf_event_read_simple(void *mem, unsigned long size,
+					  unsigned long page_size,
+					  void **buf, size_t *buf_len,
+					  bpf_perf_event_print_t fn,
+					  void *priv);
 
 struct nlattr;
 typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
-- 
cgit v1.2.3


From 6c930268bcc4cef62194daf151097d2b94f67718 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:24 +0200
Subject: kvm: selftests: vcpu_setup: set cr4.osfxsr

Guest code may want to call functions that have variable arguments.
To do so, we either need to compile with -mno-sse or enable SSE in
the VCPUs. As it should be pretty safe to turn on the feature, and
-mno-sse would make linking test code with standard libraries
difficult, we choose the feature enabling.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/lib/x86.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/lib/x86.c b/tools/testing/selftests/kvm/lib/x86.c
index a3122f1949a8..bb6c65ebfa77 100644
--- a/tools/testing/selftests/kvm/lib/x86.c
+++ b/tools/testing/selftests/kvm/lib/x86.c
@@ -626,7 +626,7 @@ void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
 	switch (vm->mode) {
 	case VM_MODE_FLAT48PG:
 		sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG;
-		sregs.cr4 |= X86_CR4_PAE;
+		sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
 		sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
 
 		kvm_seg_set_unusable(&sregs.ldt);
-- 
cgit v1.2.3


From 14c47b7530e2db1ab1d42ebbe99b2a58b8443ce7 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:25 +0200
Subject: kvm: selftests: introduce ucall

Rework the guest exit to userspace code to generalize the concept
into what it is, a "hypercall to userspace", and provide two
implementations of it: the PortIO version currently used, but only
useable by x86, and an MMIO version that other architectures (except
s390) can use.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/Makefile               |   2 +-
 tools/testing/selftests/kvm/cr4_cpuid_sync_test.c  |  12 +-
 tools/testing/selftests/kvm/dirty_log_test.c       |   5 +-
 tools/testing/selftests/kvm/include/kvm_util.h     |  76 ++++++-----
 tools/testing/selftests/kvm/lib/kvm_util.c         |  15 +--
 .../testing/selftests/kvm/lib/kvm_util_internal.h  |   1 +
 tools/testing/selftests/kvm/lib/ucall.c            | 144 +++++++++++++++++++++
 tools/testing/selftests/kvm/platform_info_test.c   |  12 +-
 tools/testing/selftests/kvm/state_test.c           |  23 ++--
 tools/testing/selftests/kvm/vmx_tsc_adjust_test.c  |  17 ++-
 10 files changed, 222 insertions(+), 85 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/lib/ucall.c

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index ec32dad3c3f0..08426f036353 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -3,7 +3,7 @@ all:
 top_srcdir = ../../../../
 UNAME_M := $(shell uname -m)
 
-LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c
+LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/ucall.c lib/sparsebit.c
 LIBKVM_x86_64 = lib/x86.c lib/vmx.c
 
 TEST_GEN_PROGS_x86_64 = platform_info_test
diff --git a/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c
index 11ec358bf969..fd4f419fe9ab 100644
--- a/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c
+++ b/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c
@@ -67,6 +67,7 @@ int main(int argc, char *argv[])
 	struct kvm_vm *vm;
 	struct kvm_sregs sregs;
 	struct kvm_cpuid_entry2 *entry;
+	struct ucall uc;
 	int rc;
 
 	entry = kvm_get_supported_cpuid_entry(1);
@@ -87,21 +88,20 @@ int main(int argc, char *argv[])
 		rc = _vcpu_run(vm, VCPU_ID);
 
 		if (run->exit_reason == KVM_EXIT_IO) {
-			switch (run->io.port) {
-			case GUEST_PORT_SYNC:
+			switch (get_ucall(vm, VCPU_ID, &uc)) {
+			case UCALL_SYNC:
 				/* emulate hypervisor clearing CR4.OSXSAVE */
 				vcpu_sregs_get(vm, VCPU_ID, &sregs);
 				sregs.cr4 &= ~X86_CR4_OSXSAVE;
 				vcpu_sregs_set(vm, VCPU_ID, &sregs);
 				break;
-			case GUEST_PORT_ABORT:
+			case UCALL_ABORT:
 				TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
 				break;
-			case GUEST_PORT_DONE:
+			case UCALL_DONE:
 				goto done;
 			default:
-				TEST_ASSERT(false, "Unknown port 0x%x.",
-					    run->io.port);
+				TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
 			}
 		}
 	}
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 0c2cdc105f96..7cf3e4ae6046 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -110,7 +110,7 @@ void *vcpu_worker(void *data)
 	uint64_t loops, *guest_array, pages_count = 0;
 	struct kvm_vm *vm = data;
 	struct kvm_run *run;
-	struct guest_args args;
+	struct ucall uc;
 
 	run = vcpu_state(vm, VCPU_ID);
 
@@ -124,9 +124,8 @@ void *vcpu_worker(void *data)
 	while (!READ_ONCE(host_quit)) {
 		/* Let the guest to dirty these random pages */
 		ret = _vcpu_run(vm, VCPU_ID);
-		guest_args_read(vm, VCPU_ID, &args);
 		if (run->exit_reason == KVM_EXIT_IO &&
-		    args.port == GUEST_PORT_SYNC) {
+		    get_ucall(vm, VCPU_ID, &uc) == UCALL_SYNC) {
 			pages_count += TEST_PAGES_PER_LOOP;
 			generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
 		} else {
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 3acf9a91704c..22667dd48a9c 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -152,43 +152,49 @@ allocate_kvm_dirty_log(struct kvm_userspace_memory_region *region);
 
 int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd);
 
-#define GUEST_PORT_SYNC         0x1000
-#define GUEST_PORT_ABORT        0x1001
-#define GUEST_PORT_DONE         0x1002
-
-static inline void __exit_to_l0(uint16_t port, uint64_t arg0, uint64_t arg1)
-{
-	__asm__ __volatile__("in %[port], %%al"
-			     :
-			     : [port]"d"(port), "D"(arg0), "S"(arg1)
-			     : "rax");
-}
-
-/*
- * Allows to pass three arguments to the host: port is 16bit wide,
- * arg0 & arg1 are 64bit wide
- */
-#define GUEST_SYNC_ARGS(_port, _arg0, _arg1) \
-	__exit_to_l0(_port, (uint64_t) (_arg0), (uint64_t) (_arg1))
-
-#define GUEST_ASSERT(_condition) do {				\
-		if (!(_condition))				\
-			GUEST_SYNC_ARGS(GUEST_PORT_ABORT,	\
-					"Failed guest assert: "	\
-					#_condition, __LINE__);	\
-	} while (0)
-
-#define GUEST_SYNC(stage)  GUEST_SYNC_ARGS(GUEST_PORT_SYNC, "hello", stage)
+#define sync_global_to_guest(vm, g) ({				\
+	typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g));	\
+	memcpy(_p, &(g), sizeof(g));				\
+})
+
+#define sync_global_from_guest(vm, g) ({			\
+	typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g));	\
+	memcpy(&(g), _p, sizeof(g));				\
+})
+
+/* ucall implementation types */
+typedef enum {
+	UCALL_PIO,
+	UCALL_MMIO,
+} ucall_type_t;
+
+/* Common ucalls */
+enum {
+	UCALL_NONE,
+	UCALL_SYNC,
+	UCALL_ABORT,
+	UCALL_DONE,
+};
 
-#define GUEST_DONE()  GUEST_SYNC_ARGS(GUEST_PORT_DONE, 0, 0)
+#define UCALL_MAX_ARGS 6
 
-struct guest_args {
-	uint64_t arg0;
-	uint64_t arg1;
-	uint16_t port;
-} __attribute__ ((packed));
+struct ucall {
+	uint64_t cmd;
+	uint64_t args[UCALL_MAX_ARGS];
+};
 
-void guest_args_read(struct kvm_vm *vm, uint32_t vcpu_id,
-		     struct guest_args *args);
+void ucall_init(struct kvm_vm *vm, ucall_type_t type, void *arg);
+void ucall_uninit(struct kvm_vm *vm);
+void ucall(uint64_t cmd, int nargs, ...);
+uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc);
+
+#define GUEST_SYNC(stage)	ucall(UCALL_SYNC, 2, "hello", stage)
+#define GUEST_DONE()		ucall(UCALL_DONE, 0)
+#define GUEST_ASSERT(_condition) do {			\
+	if (!(_condition))				\
+		ucall(UCALL_ABORT, 2,			\
+			"Failed guest assert: "		\
+			#_condition, __LINE__);		\
+} while (0)
 
 #endif /* SELFTEST_KVM_UTIL_H */
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 6fd8c089cafc..4bd31bf04f53 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -133,6 +133,7 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	case VM_MODE_FLAT48PG:
 		vm->page_size = 0x1000;
 		vm->page_shift = 12;
+		vm->va_bits = 48;
 
 		/* Limit to 48-bit canonical virtual addresses. */
 		vm->vpages_valid = sparsebit_alloc();
@@ -1669,17 +1670,3 @@ void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva)
 {
 	return addr_gpa2hva(vm, addr_gva2gpa(vm, gva));
 }
-
-void guest_args_read(struct kvm_vm *vm, uint32_t vcpu_id,
-		     struct guest_args *args)
-{
-	struct kvm_run *run = vcpu_state(vm, vcpu_id);
-	struct kvm_regs regs;
-
-	memset(&regs, 0, sizeof(regs));
-	vcpu_regs_get(vm, vcpu_id, &regs);
-
-	args->port = run->io.port;
-	args->arg0 = regs.rdi;
-	args->arg1 = regs.rsi;
-}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 542ed606b338..8fa7c9f7567a 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -47,6 +47,7 @@ struct kvm_vm {
 	int fd;
 	unsigned int page_size;
 	unsigned int page_shift;
+	unsigned int va_bits;
 	uint64_t max_gfn;
 	struct vcpu *vcpu_head;
 	struct userspace_mem_region *userspace_mem_region_head;
diff --git a/tools/testing/selftests/kvm/lib/ucall.c b/tools/testing/selftests/kvm/lib/ucall.c
new file mode 100644
index 000000000000..4777f9bb5194
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/ucall.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ucall support. A ucall is a "hypercall to userspace".
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+#include "kvm_util.h"
+#include "kvm_util_internal.h"
+
+#define UCALL_PIO_PORT ((uint16_t)0x1000)
+
+static ucall_type_t ucall_type;
+static vm_vaddr_t *ucall_exit_mmio_addr;
+
+static bool ucall_mmio_init(struct kvm_vm *vm, vm_paddr_t gpa)
+{
+	if (kvm_userspace_memory_region_find(vm, gpa, gpa + 1))
+		return false;
+
+	virt_pg_map(vm, gpa, gpa, 0);
+
+	ucall_exit_mmio_addr = (vm_vaddr_t *)gpa;
+	sync_global_to_guest(vm, ucall_exit_mmio_addr);
+
+	return true;
+}
+
+void ucall_init(struct kvm_vm *vm, ucall_type_t type, void *arg)
+{
+	ucall_type = type;
+	sync_global_to_guest(vm, ucall_type);
+
+	if (type == UCALL_PIO)
+		return;
+
+	if (type == UCALL_MMIO) {
+		vm_paddr_t gpa, start, end, step;
+		bool ret;
+
+		if (arg) {
+			gpa = (vm_paddr_t)arg;
+			ret = ucall_mmio_init(vm, gpa);
+			TEST_ASSERT(ret, "Can't set ucall mmio address to %lx", gpa);
+			return;
+		}
+
+		/*
+		 * Find an address within the allowed virtual address space,
+		 * that does _not_ have a KVM memory region associated with it.
+		 * Identity mapping an address like this allows the guest to
+		 * access it, but as KVM doesn't know what to do with it, it
+		 * will assume it's something userspace handles and exit with
+		 * KVM_EXIT_MMIO. Well, at least that's how it works for AArch64.
+		 * Here we start with a guess that the addresses around two
+		 * thirds of the VA space are unmapped and then work both down
+		 * and up from there in 1/6 VA space sized steps.
+		 */
+		start = 1ul << (vm->va_bits * 2 / 3);
+		end = 1ul << vm->va_bits;
+		step = 1ul << (vm->va_bits / 6);
+		for (gpa = start; gpa >= 0; gpa -= step) {
+			if (ucall_mmio_init(vm, gpa & ~(vm->page_size - 1)))
+				return;
+		}
+		for (gpa = start + step; gpa < end; gpa += step) {
+			if (ucall_mmio_init(vm, gpa & ~(vm->page_size - 1)))
+				return;
+		}
+		TEST_ASSERT(false, "Can't find a ucall mmio address");
+	}
+}
+
+void ucall_uninit(struct kvm_vm *vm)
+{
+	ucall_type = 0;
+	sync_global_to_guest(vm, ucall_type);
+	ucall_exit_mmio_addr = 0;
+	sync_global_to_guest(vm, ucall_exit_mmio_addr);
+}
+
+static void ucall_pio_exit(struct ucall *uc)
+{
+#ifdef __x86_64__
+	asm volatile("in %[port], %%al"
+		: : [port] "d" (UCALL_PIO_PORT), "D" (uc) : "rax");
+#endif
+}
+
+static void ucall_mmio_exit(struct ucall *uc)
+{
+	*ucall_exit_mmio_addr = (vm_vaddr_t)uc;
+}
+
+void ucall(uint64_t cmd, int nargs, ...)
+{
+	struct ucall uc = {
+		.cmd = cmd,
+	};
+	va_list va;
+	int i;
+
+	nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS;
+
+	va_start(va, nargs);
+	for (i = 0; i < nargs; ++i)
+		uc.args[i] = va_arg(va, uint64_t);
+	va_end(va);
+
+	switch (ucall_type) {
+	case UCALL_PIO:
+		ucall_pio_exit(&uc);
+		break;
+	case UCALL_MMIO:
+		ucall_mmio_exit(&uc);
+		break;
+	};
+}
+
+uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
+{
+	struct kvm_run *run = vcpu_state(vm, vcpu_id);
+
+	memset(uc, 0, sizeof(*uc));
+
+#ifdef __x86_64__
+	if (ucall_type == UCALL_PIO && run->exit_reason == KVM_EXIT_IO &&
+	    run->io.port == UCALL_PIO_PORT) {
+		struct kvm_regs regs;
+		vcpu_regs_get(vm, vcpu_id, &regs);
+		memcpy(uc, addr_gva2hva(vm, (vm_vaddr_t)regs.rdi), sizeof(*uc));
+		return uc->cmd;
+	}
+#endif
+	if (ucall_type == UCALL_MMIO && run->exit_reason == KVM_EXIT_MMIO &&
+	    run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) {
+		vm_vaddr_t gva;
+		TEST_ASSERT(run->mmio.is_write && run->mmio.len == 8,
+			    "Unexpected ucall exit mmio address access");
+		gva = *(vm_vaddr_t *)run->mmio.data;
+		memcpy(uc, addr_gva2hva(vm, gva), sizeof(*uc));
+	}
+
+	return uc->cmd;
+}
diff --git a/tools/testing/selftests/kvm/platform_info_test.c b/tools/testing/selftests/kvm/platform_info_test.c
index 3764e7121265..aa6a14331461 100644
--- a/tools/testing/selftests/kvm/platform_info_test.c
+++ b/tools/testing/selftests/kvm/platform_info_test.c
@@ -48,7 +48,7 @@ static void set_msr_platform_info_enabled(struct kvm_vm *vm, bool enable)
 static void test_msr_platform_info_enabled(struct kvm_vm *vm)
 {
 	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
-	struct guest_args args;
+	struct ucall uc;
 
 	set_msr_platform_info_enabled(vm, true);
 	vcpu_run(vm, VCPU_ID);
@@ -56,11 +56,11 @@ static void test_msr_platform_info_enabled(struct kvm_vm *vm)
 			"Exit_reason other than KVM_EXIT_IO: %u (%s),\n",
 			run->exit_reason,
 			exit_reason_str(run->exit_reason));
-	guest_args_read(vm, VCPU_ID, &args);
-	TEST_ASSERT(args.port == GUEST_PORT_SYNC,
-			"Received IO from port other than PORT_HOST_SYNC: %u\n",
-			run->io.port);
-	TEST_ASSERT((args.arg1 & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) ==
+	get_ucall(vm, VCPU_ID, &uc);
+	TEST_ASSERT(uc.cmd == UCALL_SYNC,
+			"Received ucall other than UCALL_SYNC: %u\n",
+			ucall);
+	TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) ==
 		MSR_PLATFORM_INFO_MAX_TURBO_RATIO,
 		"Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.",
 		MSR_PLATFORM_INFO_MAX_TURBO_RATIO);
diff --git a/tools/testing/selftests/kvm/state_test.c b/tools/testing/selftests/kvm/state_test.c
index 900e3e9dfb9f..cdf82735d6e7 100644
--- a/tools/testing/selftests/kvm/state_test.c
+++ b/tools/testing/selftests/kvm/state_test.c
@@ -127,6 +127,7 @@ int main(int argc, char *argv[])
 	struct kvm_vm *vm;
 	struct kvm_run *run;
 	struct kvm_x86_state *state;
+	struct ucall uc;
 	int stage;
 
 	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
@@ -155,23 +156,23 @@ int main(int argc, char *argv[])
 
 		memset(&regs1, 0, sizeof(regs1));
 		vcpu_regs_get(vm, VCPU_ID, &regs1);
-		switch (run->io.port) {
-		case GUEST_PORT_ABORT:
-			TEST_ASSERT(false, "%s at %s:%d", (const char *) regs1.rdi,
-				    __FILE__, regs1.rsi);
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
+				    __FILE__, uc.args[1]);
 			/* NOT REACHED */
-		case GUEST_PORT_SYNC:
+		case UCALL_SYNC:
 			break;
-		case GUEST_PORT_DONE:
+		case UCALL_DONE:
 			goto done;
 		default:
-			TEST_ASSERT(false, "Unknown port 0x%x.", run->io.port);
+			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
 		}
 
-		/* PORT_SYNC is handled here.  */
-		TEST_ASSERT(!strcmp((const char *)regs1.rdi, "hello") &&
-			    regs1.rsi == stage, "Unexpected register values vmexit #%lx, got %lx",
-			    stage, (ulong) regs1.rsi);
+		/* UCALL_SYNC is handled here.  */
+		TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+			    uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
+			    stage, (ulong)uc.args[1]);
 
 		state = vcpu_save_state(vm, VCPU_ID);
 		kvm_vm_release(vm);
diff --git a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
index 49bcc68b0235..8d487c78796a 100644
--- a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
@@ -146,26 +146,25 @@ int main(int argc, char *argv[])
 
 	for (;;) {
 		volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
-		struct guest_args args;
+		struct ucall uc;
 
 		vcpu_run(vm, VCPU_ID);
-		guest_args_read(vm, VCPU_ID, &args);
 		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
 			    "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
 			    run->exit_reason,
 			    exit_reason_str(run->exit_reason));
 
-		switch (args.port) {
-		case GUEST_PORT_ABORT:
-			TEST_ASSERT(false, "%s", (const char *) args.arg0);
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "%s", (const char *)uc.args[0]);
 			/* NOT REACHED */
-		case GUEST_PORT_SYNC:
-			report(args.arg1);
+		case UCALL_SYNC:
+			report(uc.args[1]);
 			break;
-		case GUEST_PORT_DONE:
+		case UCALL_DONE:
 			goto done;
 		default:
-			TEST_ASSERT(false, "Unknown port 0x%x.", args.port);
+			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
 		}
 	}
 
-- 
cgit v1.2.3


From cc68765d418721ab854a03626c01e8eb82711922 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:26 +0200
Subject: kvm: selftests: move arch-specific files to arch-specific locations

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/.gitignore             |   13 +-
 tools/testing/selftests/kvm/Makefile               |   22 +-
 tools/testing/selftests/kvm/cr4_cpuid_sync_test.c  |  113 ---
 tools/testing/selftests/kvm/dirty_log_test.c       |  307 ------
 tools/testing/selftests/kvm/include/kvm_util.h     |    2 +-
 tools/testing/selftests/kvm/include/sparsebit.h    |    6 +-
 tools/testing/selftests/kvm/include/test_util.h    |    6 +-
 tools/testing/selftests/kvm/include/vmx.h          |  552 -----------
 tools/testing/selftests/kvm/include/x86.h          | 1047 --------------------
 .../selftests/kvm/include/x86_64/processor.h       | 1047 ++++++++++++++++++++
 tools/testing/selftests/kvm/include/x86_64/vmx.h   |  552 +++++++++++
 tools/testing/selftests/kvm/lib/assert.c           |    2 +-
 .../testing/selftests/kvm/lib/kvm_util_internal.h  |    8 +-
 tools/testing/selftests/kvm/lib/vmx.c              |  283 ------
 tools/testing/selftests/kvm/lib/x86.c              |  888 -----------------
 tools/testing/selftests/kvm/lib/x86_64/processor.c |  888 +++++++++++++++++
 tools/testing/selftests/kvm/lib/x86_64/vmx.c       |  283 ++++++
 tools/testing/selftests/kvm/platform_info_test.c   |  110 --
 tools/testing/selftests/kvm/set_sregs_test.c       |   54 -
 tools/testing/selftests/kvm/state_test.c           |  197 ----
 tools/testing/selftests/kvm/sync_regs_test.c       |  237 -----
 tools/testing/selftests/kvm/vmx_tsc_adjust_test.c  |  174 ----
 .../selftests/kvm/x86_64/cr4_cpuid_sync_test.c     |  113 +++
 .../testing/selftests/kvm/x86_64/dirty_log_test.c  |  307 ++++++
 .../selftests/kvm/x86_64/platform_info_test.c      |  110 ++
 .../testing/selftests/kvm/x86_64/set_sregs_test.c  |   54 +
 tools/testing/selftests/kvm/x86_64/state_test.c    |  197 ++++
 .../testing/selftests/kvm/x86_64/sync_regs_test.c  |  237 +++++
 .../selftests/kvm/x86_64/vmx_tsc_adjust_test.c     |  174 ++++
 29 files changed, 3992 insertions(+), 3991 deletions(-)
 delete mode 100644 tools/testing/selftests/kvm/cr4_cpuid_sync_test.c
 delete mode 100644 tools/testing/selftests/kvm/dirty_log_test.c
 delete mode 100644 tools/testing/selftests/kvm/include/vmx.h
 delete mode 100644 tools/testing/selftests/kvm/include/x86.h
 create mode 100644 tools/testing/selftests/kvm/include/x86_64/processor.h
 create mode 100644 tools/testing/selftests/kvm/include/x86_64/vmx.h
 delete mode 100644 tools/testing/selftests/kvm/lib/vmx.c
 delete mode 100644 tools/testing/selftests/kvm/lib/x86.c
 create mode 100644 tools/testing/selftests/kvm/lib/x86_64/processor.c
 create mode 100644 tools/testing/selftests/kvm/lib/x86_64/vmx.c
 delete mode 100644 tools/testing/selftests/kvm/platform_info_test.c
 delete mode 100644 tools/testing/selftests/kvm/set_sregs_test.c
 delete mode 100644 tools/testing/selftests/kvm/state_test.c
 delete mode 100644 tools/testing/selftests/kvm/sync_regs_test.c
 delete mode 100644 tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
 create mode 100644 tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
 create mode 100644 tools/testing/selftests/kvm/x86_64/dirty_log_test.c
 create mode 100644 tools/testing/selftests/kvm/x86_64/platform_info_test.c
 create mode 100644 tools/testing/selftests/kvm/x86_64/set_sregs_test.c
 create mode 100644 tools/testing/selftests/kvm/x86_64/state_test.c
 create mode 100644 tools/testing/selftests/kvm/x86_64/sync_regs_test.c
 create mode 100644 tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 5c34752e1cff..e0aa5411cf9b 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,6 +1,7 @@
-cr4_cpuid_sync_test
-platform_info_test
-set_sregs_test
-sync_regs_test
-vmx_tsc_adjust_test
-state_test
+/x86_64/cr4_cpuid_sync_test
+/x86_64/platform_info_test
+/x86_64/set_sregs_test
+/x86_64/sync_regs_test
+/x86_64/vmx_tsc_adjust_test
+/x86_64/state_test
+/x86_64/dirty_log_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 08426f036353..734a60da9776 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -1,26 +1,26 @@
 all:
 
-top_srcdir = ../../../../
+top_srcdir = ../../../..
 UNAME_M := $(shell uname -m)
 
 LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/ucall.c lib/sparsebit.c
-LIBKVM_x86_64 = lib/x86.c lib/vmx.c
+LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c
 
-TEST_GEN_PROGS_x86_64 = platform_info_test
-TEST_GEN_PROGS_x86_64 += set_sregs_test
-TEST_GEN_PROGS_x86_64 += sync_regs_test
-TEST_GEN_PROGS_x86_64 += vmx_tsc_adjust_test
-TEST_GEN_PROGS_x86_64 += cr4_cpuid_sync_test
-TEST_GEN_PROGS_x86_64 += state_test
-TEST_GEN_PROGS_x86_64 += dirty_log_test
+TEST_GEN_PROGS_x86_64 = x86_64/platform_info_test
+TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
+TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
+TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
+TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
+TEST_GEN_PROGS_x86_64 += x86_64/state_test
+TEST_GEN_PROGS_x86_64 += x86_64/dirty_log_test
 
 TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
 LIBKVM += $(LIBKVM_$(UNAME_M))
 
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
-LINUX_TOOL_INCLUDE = $(top_srcdir)tools/include
-CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I..
+LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
+CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
 LDFLAGS += -pthread
 
 # After inclusion, $(OUTPUT) is defined and
diff --git a/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c
deleted file mode 100644
index fd4f419fe9ab..000000000000
--- a/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c
+++ /dev/null
@@ -1,113 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * CR4 and CPUID sync test
- *
- * Copyright 2018, Red Hat, Inc. and/or its affiliates.
- *
- * Author:
- *   Wei Huang <wei@redhat.com>
- */
-
-#include <fcntl.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/ioctl.h>
-
-#include "test_util.h"
-
-#include "kvm_util.h"
-#include "x86.h"
-
-#define X86_FEATURE_XSAVE	(1<<26)
-#define X86_FEATURE_OSXSAVE	(1<<27)
-#define VCPU_ID			1
-
-static inline bool cr4_cpuid_is_sync(void)
-{
-	int func, subfunc;
-	uint32_t eax, ebx, ecx, edx;
-	uint64_t cr4;
-
-	func = 0x1;
-	subfunc = 0x0;
-	__asm__ __volatile__("cpuid"
-			     : "=a"(eax), "=b"(ebx), "=c"(ecx), "=d"(edx)
-			     : "a"(func), "c"(subfunc));
-
-	cr4 = get_cr4();
-
-	return (!!(ecx & X86_FEATURE_OSXSAVE)) == (!!(cr4 & X86_CR4_OSXSAVE));
-}
-
-static void guest_code(void)
-{
-	uint64_t cr4;
-
-	/* turn on CR4.OSXSAVE */
-	cr4 = get_cr4();
-	cr4 |= X86_CR4_OSXSAVE;
-	set_cr4(cr4);
-
-	/* verify CR4.OSXSAVE == CPUID.OSXSAVE */
-	GUEST_ASSERT(cr4_cpuid_is_sync());
-
-	/* notify hypervisor to change CR4 */
-	GUEST_SYNC(0);
-
-	/* check again */
-	GUEST_ASSERT(cr4_cpuid_is_sync());
-
-	GUEST_DONE();
-}
-
-int main(int argc, char *argv[])
-{
-	struct kvm_run *run;
-	struct kvm_vm *vm;
-	struct kvm_sregs sregs;
-	struct kvm_cpuid_entry2 *entry;
-	struct ucall uc;
-	int rc;
-
-	entry = kvm_get_supported_cpuid_entry(1);
-	if (!(entry->ecx & X86_FEATURE_XSAVE)) {
-		printf("XSAVE feature not supported, skipping test\n");
-		return 0;
-	}
-
-	/* Tell stdout not to buffer its content */
-	setbuf(stdout, NULL);
-
-	/* Create VM */
-	vm = vm_create_default(VCPU_ID, 0, guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-	run = vcpu_state(vm, VCPU_ID);
-
-	while (1) {
-		rc = _vcpu_run(vm, VCPU_ID);
-
-		if (run->exit_reason == KVM_EXIT_IO) {
-			switch (get_ucall(vm, VCPU_ID, &uc)) {
-			case UCALL_SYNC:
-				/* emulate hypervisor clearing CR4.OSXSAVE */
-				vcpu_sregs_get(vm, VCPU_ID, &sregs);
-				sregs.cr4 &= ~X86_CR4_OSXSAVE;
-				vcpu_sregs_set(vm, VCPU_ID, &sregs);
-				break;
-			case UCALL_ABORT:
-				TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
-				break;
-			case UCALL_DONE:
-				goto done;
-			default:
-				TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
-			}
-		}
-	}
-
-	kvm_vm_free(vm);
-
-done:
-	return 0;
-}
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
deleted file mode 100644
index 7cf3e4ae6046..000000000000
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ /dev/null
@@ -1,307 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * KVM dirty page logging test
- *
- * Copyright (C) 2018, Red Hat, Inc.
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <time.h>
-#include <pthread.h>
-#include <linux/bitmap.h>
-#include <linux/bitops.h>
-
-#include "test_util.h"
-#include "kvm_util.h"
-
-#define  DEBUG                 printf
-
-#define  VCPU_ID                        1
-/* The memory slot index to track dirty pages */
-#define  TEST_MEM_SLOT_INDEX            1
-/*
- * GPA offset of the testing memory slot. Must be bigger than the
- * default vm mem slot, which is DEFAULT_GUEST_PHY_PAGES.
- */
-#define  TEST_MEM_OFFSET                (1ULL << 30) /* 1G */
-/* Size of the testing memory slot */
-#define  TEST_MEM_PAGES                 (1ULL << 18) /* 1G for 4K pages */
-/* How many pages to dirty for each guest loop */
-#define  TEST_PAGES_PER_LOOP            1024
-/* How many host loops to run (one KVM_GET_DIRTY_LOG for each loop) */
-#define  TEST_HOST_LOOP_N               32
-/* Interval for each host loop (ms) */
-#define  TEST_HOST_LOOP_INTERVAL        10
-
-/*
- * Guest variables.  We use these variables to share data between host
- * and guest.  There are two copies of the variables, one in host memory
- * (which is unused) and one in guest memory.  When the host wants to
- * access these variables, it needs to call addr_gva2hva() to access the
- * guest copy.
- */
-uint64_t guest_random_array[TEST_PAGES_PER_LOOP];
-uint64_t guest_iteration;
-uint64_t guest_page_size;
-
-/*
- * Writes to the first byte of a random page within the testing memory
- * region continuously.
- */
-void guest_code(void)
-{
-	int i = 0;
-	uint64_t volatile *array = guest_random_array;
-	uint64_t volatile *guest_addr;
-
-	while (true) {
-		for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
-			/*
-			 * Write to the first 8 bytes of a random page
-			 * on the testing memory region.
-			 */
-			guest_addr = (uint64_t *)
-			    (TEST_MEM_OFFSET +
-			     (array[i] % TEST_MEM_PAGES) * guest_page_size);
-			*guest_addr = guest_iteration;
-		}
-		/* Tell the host that we need more random numbers */
-		GUEST_SYNC(1);
-	}
-}
-
-/*
- * Host variables.  These variables should only be used by the host
- * rather than the guest.
- */
-bool host_quit;
-
-/* Points to the test VM memory region on which we track dirty logs */
-void *host_test_mem;
-
-/* For statistics only */
-uint64_t host_dirty_count;
-uint64_t host_clear_count;
-uint64_t host_track_next_count;
-
-/*
- * We use this bitmap to track some pages that should have its dirty
- * bit set in the _next_ iteration.  For example, if we detected the
- * page value changed to current iteration but at the same time the
- * page bit is cleared in the latest bitmap, then the system must
- * report that write in the next get dirty log call.
- */
-unsigned long *host_bmap_track;
-
-void generate_random_array(uint64_t *guest_array, uint64_t size)
-{
-	uint64_t i;
-
-	for (i = 0; i < size; i++) {
-		guest_array[i] = random();
-	}
-}
-
-void *vcpu_worker(void *data)
-{
-	int ret;
-	uint64_t loops, *guest_array, pages_count = 0;
-	struct kvm_vm *vm = data;
-	struct kvm_run *run;
-	struct ucall uc;
-
-	run = vcpu_state(vm, VCPU_ID);
-
-	/* Retrieve the guest random array pointer and cache it */
-	guest_array = addr_gva2hva(vm, (vm_vaddr_t)guest_random_array);
-
-	DEBUG("VCPU starts\n");
-
-	generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
-
-	while (!READ_ONCE(host_quit)) {
-		/* Let the guest to dirty these random pages */
-		ret = _vcpu_run(vm, VCPU_ID);
-		if (run->exit_reason == KVM_EXIT_IO &&
-		    get_ucall(vm, VCPU_ID, &uc) == UCALL_SYNC) {
-			pages_count += TEST_PAGES_PER_LOOP;
-			generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
-		} else {
-			TEST_ASSERT(false,
-				    "Invalid guest sync status: "
-				    "exit_reason=%s\n",
-				    exit_reason_str(run->exit_reason));
-		}
-	}
-
-	DEBUG("VCPU exits, dirtied %"PRIu64" pages\n", pages_count);
-
-	return NULL;
-}
-
-void vm_dirty_log_verify(unsigned long *bmap, uint64_t iteration)
-{
-	uint64_t page;
-	uint64_t volatile *value_ptr;
-
-	for (page = 0; page < TEST_MEM_PAGES; page++) {
-		value_ptr = host_test_mem + page * getpagesize();
-
-		/* If this is a special page that we were tracking... */
-		if (test_and_clear_bit(page, host_bmap_track)) {
-			host_track_next_count++;
-			TEST_ASSERT(test_bit(page, bmap),
-				    "Page %"PRIu64" should have its dirty bit "
-				    "set in this iteration but it is missing",
-				    page);
-		}
-
-		if (test_bit(page, bmap)) {
-			host_dirty_count++;
-			/*
-			 * If the bit is set, the value written onto
-			 * the corresponding page should be either the
-			 * previous iteration number or the current one.
-			 */
-			TEST_ASSERT(*value_ptr == iteration ||
-				    *value_ptr == iteration - 1,
-				    "Set page %"PRIu64" value %"PRIu64
-				    " incorrect (iteration=%"PRIu64")",
-				    page, *value_ptr, iteration);
-		} else {
-			host_clear_count++;
-			/*
-			 * If cleared, the value written can be any
-			 * value smaller or equals to the iteration
-			 * number.  Note that the value can be exactly
-			 * (iteration-1) if that write can happen
-			 * like this:
-			 *
-			 * (1) increase loop count to "iteration-1"
-			 * (2) write to page P happens (with value
-			 *     "iteration-1")
-			 * (3) get dirty log for "iteration-1"; we'll
-			 *     see that page P bit is set (dirtied),
-			 *     and not set the bit in host_bmap_track
-			 * (4) increase loop count to "iteration"
-			 *     (which is current iteration)
-			 * (5) get dirty log for current iteration,
-			 *     we'll see that page P is cleared, with
-			 *     value "iteration-1".
-			 */
-			TEST_ASSERT(*value_ptr <= iteration,
-				    "Clear page %"PRIu64" value %"PRIu64
-				    " incorrect (iteration=%"PRIu64")",
-				    page, *value_ptr, iteration);
-			if (*value_ptr == iteration) {
-				/*
-				 * This page is _just_ modified; it
-				 * should report its dirtyness in the
-				 * next run
-				 */
-				set_bit(page, host_bmap_track);
-			}
-		}
-	}
-}
-
-void help(char *name)
-{
-	puts("");
-	printf("usage: %s [-i iterations] [-I interval] [-h]\n", name);
-	puts("");
-	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
-	       TEST_HOST_LOOP_N);
-	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
-	       TEST_HOST_LOOP_INTERVAL);
-	puts("");
-	exit(0);
-}
-
-int main(int argc, char *argv[])
-{
-	pthread_t vcpu_thread;
-	struct kvm_vm *vm;
-	uint64_t volatile *psize, *iteration;
-	unsigned long *bmap, iterations = TEST_HOST_LOOP_N,
-	    interval = TEST_HOST_LOOP_INTERVAL;
-	int opt;
-
-	while ((opt = getopt(argc, argv, "hi:I:")) != -1) {
-		switch (opt) {
-		case 'i':
-			iterations = strtol(optarg, NULL, 10);
-			break;
-		case 'I':
-			interval = strtol(optarg, NULL, 10);
-			break;
-		case 'h':
-		default:
-			help(argv[0]);
-			break;
-		}
-	}
-
-	TEST_ASSERT(iterations > 2, "Iteration must be bigger than zero\n");
-	TEST_ASSERT(interval > 0, "Interval must be bigger than zero");
-
-	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
-	      iterations, interval);
-
-	srandom(time(0));
-
-	bmap = bitmap_alloc(TEST_MEM_PAGES);
-	host_bmap_track = bitmap_alloc(TEST_MEM_PAGES);
-
-	vm = vm_create_default(VCPU_ID, TEST_MEM_PAGES, guest_code);
-
-	/* Add an extra memory slot for testing dirty logging */
-	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
-				    TEST_MEM_OFFSET,
-				    TEST_MEM_SLOT_INDEX,
-				    TEST_MEM_PAGES,
-				    KVM_MEM_LOG_DIRTY_PAGES);
-	/* Cache the HVA pointer of the region */
-	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)TEST_MEM_OFFSET);
-
-	/* Do 1:1 mapping for the dirty track memory slot */
-	virt_map(vm, TEST_MEM_OFFSET, TEST_MEM_OFFSET,
-		 TEST_MEM_PAGES * getpagesize(), 0);
-
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-
-	/* Tell the guest about the page size on the system */
-	psize = addr_gva2hva(vm, (vm_vaddr_t)&guest_page_size);
-	*psize = getpagesize();
-
-	/* Start the iterations */
-	iteration = addr_gva2hva(vm, (vm_vaddr_t)&guest_iteration);
-	*iteration = 1;
-
-	/* Start dirtying pages */
-	pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
-
-	while (*iteration < iterations) {
-		/* Give the vcpu thread some time to dirty some pages */
-		usleep(interval * 1000);
-		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
-		vm_dirty_log_verify(bmap, *iteration);
-		(*iteration)++;
-	}
-
-	/* Tell the vcpu thread to quit */
-	host_quit = true;
-	pthread_join(vcpu_thread, NULL);
-
-	DEBUG("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
-	      "track_next (%"PRIu64")\n", host_dirty_count, host_clear_count,
-	      host_track_next_count);
-
-	free(bmap);
-	free(host_bmap_track);
-	kvm_vm_free(vm);
-
-	return 0;
-}
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 22667dd48a9c..7830c46f27d8 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -7,7 +7,7 @@
  *
  */
 #ifndef SELFTEST_KVM_UTIL_H
-#define SELFTEST_KVM_UTIL_H 1
+#define SELFTEST_KVM_UTIL_H
 
 #include "test_util.h"
 
diff --git a/tools/testing/selftests/kvm/include/sparsebit.h b/tools/testing/selftests/kvm/include/sparsebit.h
index 54cfeb6568d3..31e030915c1f 100644
--- a/tools/testing/selftests/kvm/include/sparsebit.h
+++ b/tools/testing/selftests/kvm/include/sparsebit.h
@@ -15,8 +15,8 @@
  * even in the case where most bits are set.
  */
 
-#ifndef _TEST_SPARSEBIT_H_
-#define _TEST_SPARSEBIT_H_
+#ifndef SELFTEST_KVM_SPARSEBIT_H
+#define SELFTEST_KVM_SPARSEBIT_H
 
 #include <stdbool.h>
 #include <stdint.h>
@@ -72,4 +72,4 @@ void sparsebit_validate_internal(struct sparsebit *sbit);
 }
 #endif
 
-#endif /* _TEST_SPARSEBIT_H_ */
+#endif /* SELFTEST_KVM_SPARSEBIT_H */
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 73c3933436ec..c7dafe8bd02c 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -7,8 +7,8 @@
  *
  */
 
-#ifndef TEST_UTIL_H
-#define TEST_UTIL_H 1
+#ifndef SELFTEST_KVM_TEST_UTIL_H
+#define SELFTEST_KVM_TEST_UTIL_H
 
 #include <stdlib.h>
 #include <stdarg.h>
@@ -41,4 +41,4 @@ void test_assert(bool exp, const char *exp_str,
 		    #a, #b, #a, (unsigned long) __a, #b, (unsigned long) __b); \
 } while (0)
 
-#endif /* TEST_UTIL_H */
+#endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/vmx.h b/tools/testing/selftests/kvm/include/vmx.h
deleted file mode 100644
index b9ffe1024d3a..000000000000
--- a/tools/testing/selftests/kvm/include/vmx.h
+++ /dev/null
@@ -1,552 +0,0 @@
-/*
- * tools/testing/selftests/kvm/include/vmx.h
- *
- * Copyright (C) 2018, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- */
-
-#ifndef SELFTEST_KVM_VMX_H
-#define SELFTEST_KVM_VMX_H
-
-#include <stdint.h>
-#include "x86.h"
-
-#define CPUID_VMX_BIT				5
-
-#define CPUID_VMX				(1 << 5)
-
-/*
- * Definitions of Primary Processor-Based VM-Execution Controls.
- */
-#define CPU_BASED_VIRTUAL_INTR_PENDING		0x00000004
-#define CPU_BASED_USE_TSC_OFFSETING		0x00000008
-#define CPU_BASED_HLT_EXITING			0x00000080
-#define CPU_BASED_INVLPG_EXITING		0x00000200
-#define CPU_BASED_MWAIT_EXITING			0x00000400
-#define CPU_BASED_RDPMC_EXITING			0x00000800
-#define CPU_BASED_RDTSC_EXITING			0x00001000
-#define CPU_BASED_CR3_LOAD_EXITING		0x00008000
-#define CPU_BASED_CR3_STORE_EXITING		0x00010000
-#define CPU_BASED_CR8_LOAD_EXITING		0x00080000
-#define CPU_BASED_CR8_STORE_EXITING		0x00100000
-#define CPU_BASED_TPR_SHADOW			0x00200000
-#define CPU_BASED_VIRTUAL_NMI_PENDING		0x00400000
-#define CPU_BASED_MOV_DR_EXITING		0x00800000
-#define CPU_BASED_UNCOND_IO_EXITING		0x01000000
-#define CPU_BASED_USE_IO_BITMAPS		0x02000000
-#define CPU_BASED_MONITOR_TRAP			0x08000000
-#define CPU_BASED_USE_MSR_BITMAPS		0x10000000
-#define CPU_BASED_MONITOR_EXITING		0x20000000
-#define CPU_BASED_PAUSE_EXITING			0x40000000
-#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS	0x80000000
-
-#define CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR	0x0401e172
-
-/*
- * Definitions of Secondary Processor-Based VM-Execution Controls.
- */
-#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
-#define SECONDARY_EXEC_ENABLE_EPT		0x00000002
-#define SECONDARY_EXEC_DESC			0x00000004
-#define SECONDARY_EXEC_RDTSCP			0x00000008
-#define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE	0x00000010
-#define SECONDARY_EXEC_ENABLE_VPID		0x00000020
-#define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
-#define SECONDARY_EXEC_UNRESTRICTED_GUEST	0x00000080
-#define SECONDARY_EXEC_APIC_REGISTER_VIRT	0x00000100
-#define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY	0x00000200
-#define SECONDARY_EXEC_PAUSE_LOOP_EXITING	0x00000400
-#define SECONDARY_EXEC_RDRAND_EXITING		0x00000800
-#define SECONDARY_EXEC_ENABLE_INVPCID		0x00001000
-#define SECONDARY_EXEC_ENABLE_VMFUNC		0x00002000
-#define SECONDARY_EXEC_SHADOW_VMCS		0x00004000
-#define SECONDARY_EXEC_RDSEED_EXITING		0x00010000
-#define SECONDARY_EXEC_ENABLE_PML		0x00020000
-#define SECONDARY_EPT_VE			0x00040000
-#define SECONDARY_ENABLE_XSAV_RESTORE		0x00100000
-#define SECONDARY_EXEC_TSC_SCALING		0x02000000
-
-#define PIN_BASED_EXT_INTR_MASK			0x00000001
-#define PIN_BASED_NMI_EXITING			0x00000008
-#define PIN_BASED_VIRTUAL_NMIS			0x00000020
-#define PIN_BASED_VMX_PREEMPTION_TIMER		0x00000040
-#define PIN_BASED_POSTED_INTR			0x00000080
-
-#define PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR	0x00000016
-
-#define VM_EXIT_SAVE_DEBUG_CONTROLS		0x00000004
-#define VM_EXIT_HOST_ADDR_SPACE_SIZE		0x00000200
-#define VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL	0x00001000
-#define VM_EXIT_ACK_INTR_ON_EXIT		0x00008000
-#define VM_EXIT_SAVE_IA32_PAT			0x00040000
-#define VM_EXIT_LOAD_IA32_PAT			0x00080000
-#define VM_EXIT_SAVE_IA32_EFER			0x00100000
-#define VM_EXIT_LOAD_IA32_EFER			0x00200000
-#define VM_EXIT_SAVE_VMX_PREEMPTION_TIMER	0x00400000
-
-#define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR	0x00036dff
-
-#define VM_ENTRY_LOAD_DEBUG_CONTROLS		0x00000004
-#define VM_ENTRY_IA32E_MODE			0x00000200
-#define VM_ENTRY_SMM				0x00000400
-#define VM_ENTRY_DEACT_DUAL_MONITOR		0x00000800
-#define VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL	0x00002000
-#define VM_ENTRY_LOAD_IA32_PAT			0x00004000
-#define VM_ENTRY_LOAD_IA32_EFER			0x00008000
-
-#define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR	0x000011ff
-
-#define VMX_MISC_PREEMPTION_TIMER_RATE_MASK	0x0000001f
-#define VMX_MISC_SAVE_EFER_LMA			0x00000020
-
-#define EXIT_REASON_FAILED_VMENTRY	0x80000000
-#define EXIT_REASON_EXCEPTION_NMI	0
-#define EXIT_REASON_EXTERNAL_INTERRUPT	1
-#define EXIT_REASON_TRIPLE_FAULT	2
-#define EXIT_REASON_PENDING_INTERRUPT	7
-#define EXIT_REASON_NMI_WINDOW		8
-#define EXIT_REASON_TASK_SWITCH		9
-#define EXIT_REASON_CPUID		10
-#define EXIT_REASON_HLT			12
-#define EXIT_REASON_INVD		13
-#define EXIT_REASON_INVLPG		14
-#define EXIT_REASON_RDPMC		15
-#define EXIT_REASON_RDTSC		16
-#define EXIT_REASON_VMCALL		18
-#define EXIT_REASON_VMCLEAR		19
-#define EXIT_REASON_VMLAUNCH		20
-#define EXIT_REASON_VMPTRLD		21
-#define EXIT_REASON_VMPTRST		22
-#define EXIT_REASON_VMREAD		23
-#define EXIT_REASON_VMRESUME		24
-#define EXIT_REASON_VMWRITE		25
-#define EXIT_REASON_VMOFF		26
-#define EXIT_REASON_VMON		27
-#define EXIT_REASON_CR_ACCESS		28
-#define EXIT_REASON_DR_ACCESS		29
-#define EXIT_REASON_IO_INSTRUCTION	30
-#define EXIT_REASON_MSR_READ		31
-#define EXIT_REASON_MSR_WRITE		32
-#define EXIT_REASON_INVALID_STATE	33
-#define EXIT_REASON_MWAIT_INSTRUCTION	36
-#define EXIT_REASON_MONITOR_INSTRUCTION 39
-#define EXIT_REASON_PAUSE_INSTRUCTION	40
-#define EXIT_REASON_MCE_DURING_VMENTRY	41
-#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
-#define EXIT_REASON_APIC_ACCESS		44
-#define EXIT_REASON_EOI_INDUCED		45
-#define EXIT_REASON_EPT_VIOLATION	48
-#define EXIT_REASON_EPT_MISCONFIG	49
-#define EXIT_REASON_INVEPT		50
-#define EXIT_REASON_RDTSCP		51
-#define EXIT_REASON_PREEMPTION_TIMER	52
-#define EXIT_REASON_INVVPID		53
-#define EXIT_REASON_WBINVD		54
-#define EXIT_REASON_XSETBV		55
-#define EXIT_REASON_APIC_WRITE		56
-#define EXIT_REASON_INVPCID		58
-#define EXIT_REASON_PML_FULL		62
-#define EXIT_REASON_XSAVES		63
-#define EXIT_REASON_XRSTORS		64
-#define LAST_EXIT_REASON		64
-
-enum vmcs_field {
-	VIRTUAL_PROCESSOR_ID		= 0x00000000,
-	POSTED_INTR_NV			= 0x00000002,
-	GUEST_ES_SELECTOR		= 0x00000800,
-	GUEST_CS_SELECTOR		= 0x00000802,
-	GUEST_SS_SELECTOR		= 0x00000804,
-	GUEST_DS_SELECTOR		= 0x00000806,
-	GUEST_FS_SELECTOR		= 0x00000808,
-	GUEST_GS_SELECTOR		= 0x0000080a,
-	GUEST_LDTR_SELECTOR		= 0x0000080c,
-	GUEST_TR_SELECTOR		= 0x0000080e,
-	GUEST_INTR_STATUS		= 0x00000810,
-	GUEST_PML_INDEX			= 0x00000812,
-	HOST_ES_SELECTOR		= 0x00000c00,
-	HOST_CS_SELECTOR		= 0x00000c02,
-	HOST_SS_SELECTOR		= 0x00000c04,
-	HOST_DS_SELECTOR		= 0x00000c06,
-	HOST_FS_SELECTOR		= 0x00000c08,
-	HOST_GS_SELECTOR		= 0x00000c0a,
-	HOST_TR_SELECTOR		= 0x00000c0c,
-	IO_BITMAP_A			= 0x00002000,
-	IO_BITMAP_A_HIGH		= 0x00002001,
-	IO_BITMAP_B			= 0x00002002,
-	IO_BITMAP_B_HIGH		= 0x00002003,
-	MSR_BITMAP			= 0x00002004,
-	MSR_BITMAP_HIGH			= 0x00002005,
-	VM_EXIT_MSR_STORE_ADDR		= 0x00002006,
-	VM_EXIT_MSR_STORE_ADDR_HIGH	= 0x00002007,
-	VM_EXIT_MSR_LOAD_ADDR		= 0x00002008,
-	VM_EXIT_MSR_LOAD_ADDR_HIGH	= 0x00002009,
-	VM_ENTRY_MSR_LOAD_ADDR		= 0x0000200a,
-	VM_ENTRY_MSR_LOAD_ADDR_HIGH	= 0x0000200b,
-	PML_ADDRESS			= 0x0000200e,
-	PML_ADDRESS_HIGH		= 0x0000200f,
-	TSC_OFFSET			= 0x00002010,
-	TSC_OFFSET_HIGH			= 0x00002011,
-	VIRTUAL_APIC_PAGE_ADDR		= 0x00002012,
-	VIRTUAL_APIC_PAGE_ADDR_HIGH	= 0x00002013,
-	APIC_ACCESS_ADDR		= 0x00002014,
-	APIC_ACCESS_ADDR_HIGH		= 0x00002015,
-	POSTED_INTR_DESC_ADDR		= 0x00002016,
-	POSTED_INTR_DESC_ADDR_HIGH	= 0x00002017,
-	EPT_POINTER			= 0x0000201a,
-	EPT_POINTER_HIGH		= 0x0000201b,
-	EOI_EXIT_BITMAP0		= 0x0000201c,
-	EOI_EXIT_BITMAP0_HIGH		= 0x0000201d,
-	EOI_EXIT_BITMAP1		= 0x0000201e,
-	EOI_EXIT_BITMAP1_HIGH		= 0x0000201f,
-	EOI_EXIT_BITMAP2		= 0x00002020,
-	EOI_EXIT_BITMAP2_HIGH		= 0x00002021,
-	EOI_EXIT_BITMAP3		= 0x00002022,
-	EOI_EXIT_BITMAP3_HIGH		= 0x00002023,
-	VMREAD_BITMAP			= 0x00002026,
-	VMREAD_BITMAP_HIGH		= 0x00002027,
-	VMWRITE_BITMAP			= 0x00002028,
-	VMWRITE_BITMAP_HIGH		= 0x00002029,
-	XSS_EXIT_BITMAP			= 0x0000202C,
-	XSS_EXIT_BITMAP_HIGH		= 0x0000202D,
-	TSC_MULTIPLIER			= 0x00002032,
-	TSC_MULTIPLIER_HIGH		= 0x00002033,
-	GUEST_PHYSICAL_ADDRESS		= 0x00002400,
-	GUEST_PHYSICAL_ADDRESS_HIGH	= 0x00002401,
-	VMCS_LINK_POINTER		= 0x00002800,
-	VMCS_LINK_POINTER_HIGH		= 0x00002801,
-	GUEST_IA32_DEBUGCTL		= 0x00002802,
-	GUEST_IA32_DEBUGCTL_HIGH	= 0x00002803,
-	GUEST_IA32_PAT			= 0x00002804,
-	GUEST_IA32_PAT_HIGH		= 0x00002805,
-	GUEST_IA32_EFER			= 0x00002806,
-	GUEST_IA32_EFER_HIGH		= 0x00002807,
-	GUEST_IA32_PERF_GLOBAL_CTRL	= 0x00002808,
-	GUEST_IA32_PERF_GLOBAL_CTRL_HIGH= 0x00002809,
-	GUEST_PDPTR0			= 0x0000280a,
-	GUEST_PDPTR0_HIGH		= 0x0000280b,
-	GUEST_PDPTR1			= 0x0000280c,
-	GUEST_PDPTR1_HIGH		= 0x0000280d,
-	GUEST_PDPTR2			= 0x0000280e,
-	GUEST_PDPTR2_HIGH		= 0x0000280f,
-	GUEST_PDPTR3			= 0x00002810,
-	GUEST_PDPTR3_HIGH		= 0x00002811,
-	GUEST_BNDCFGS			= 0x00002812,
-	GUEST_BNDCFGS_HIGH		= 0x00002813,
-	HOST_IA32_PAT			= 0x00002c00,
-	HOST_IA32_PAT_HIGH		= 0x00002c01,
-	HOST_IA32_EFER			= 0x00002c02,
-	HOST_IA32_EFER_HIGH		= 0x00002c03,
-	HOST_IA32_PERF_GLOBAL_CTRL	= 0x00002c04,
-	HOST_IA32_PERF_GLOBAL_CTRL_HIGH	= 0x00002c05,
-	PIN_BASED_VM_EXEC_CONTROL	= 0x00004000,
-	CPU_BASED_VM_EXEC_CONTROL	= 0x00004002,
-	EXCEPTION_BITMAP		= 0x00004004,
-	PAGE_FAULT_ERROR_CODE_MASK	= 0x00004006,
-	PAGE_FAULT_ERROR_CODE_MATCH	= 0x00004008,
-	CR3_TARGET_COUNT		= 0x0000400a,
-	VM_EXIT_CONTROLS		= 0x0000400c,
-	VM_EXIT_MSR_STORE_COUNT		= 0x0000400e,
-	VM_EXIT_MSR_LOAD_COUNT		= 0x00004010,
-	VM_ENTRY_CONTROLS		= 0x00004012,
-	VM_ENTRY_MSR_LOAD_COUNT		= 0x00004014,
-	VM_ENTRY_INTR_INFO_FIELD	= 0x00004016,
-	VM_ENTRY_EXCEPTION_ERROR_CODE	= 0x00004018,
-	VM_ENTRY_INSTRUCTION_LEN	= 0x0000401a,
-	TPR_THRESHOLD			= 0x0000401c,
-	SECONDARY_VM_EXEC_CONTROL	= 0x0000401e,
-	PLE_GAP				= 0x00004020,
-	PLE_WINDOW			= 0x00004022,
-	VM_INSTRUCTION_ERROR		= 0x00004400,
-	VM_EXIT_REASON			= 0x00004402,
-	VM_EXIT_INTR_INFO		= 0x00004404,
-	VM_EXIT_INTR_ERROR_CODE		= 0x00004406,
-	IDT_VECTORING_INFO_FIELD	= 0x00004408,
-	IDT_VECTORING_ERROR_CODE	= 0x0000440a,
-	VM_EXIT_INSTRUCTION_LEN		= 0x0000440c,
-	VMX_INSTRUCTION_INFO		= 0x0000440e,
-	GUEST_ES_LIMIT			= 0x00004800,
-	GUEST_CS_LIMIT			= 0x00004802,
-	GUEST_SS_LIMIT			= 0x00004804,
-	GUEST_DS_LIMIT			= 0x00004806,
-	GUEST_FS_LIMIT			= 0x00004808,
-	GUEST_GS_LIMIT			= 0x0000480a,
-	GUEST_LDTR_LIMIT		= 0x0000480c,
-	GUEST_TR_LIMIT			= 0x0000480e,
-	GUEST_GDTR_LIMIT		= 0x00004810,
-	GUEST_IDTR_LIMIT		= 0x00004812,
-	GUEST_ES_AR_BYTES		= 0x00004814,
-	GUEST_CS_AR_BYTES		= 0x00004816,
-	GUEST_SS_AR_BYTES		= 0x00004818,
-	GUEST_DS_AR_BYTES		= 0x0000481a,
-	GUEST_FS_AR_BYTES		= 0x0000481c,
-	GUEST_GS_AR_BYTES		= 0x0000481e,
-	GUEST_LDTR_AR_BYTES		= 0x00004820,
-	GUEST_TR_AR_BYTES		= 0x00004822,
-	GUEST_INTERRUPTIBILITY_INFO	= 0x00004824,
-	GUEST_ACTIVITY_STATE		= 0X00004826,
-	GUEST_SYSENTER_CS		= 0x0000482A,
-	VMX_PREEMPTION_TIMER_VALUE	= 0x0000482E,
-	HOST_IA32_SYSENTER_CS		= 0x00004c00,
-	CR0_GUEST_HOST_MASK		= 0x00006000,
-	CR4_GUEST_HOST_MASK		= 0x00006002,
-	CR0_READ_SHADOW			= 0x00006004,
-	CR4_READ_SHADOW			= 0x00006006,
-	CR3_TARGET_VALUE0		= 0x00006008,
-	CR3_TARGET_VALUE1		= 0x0000600a,
-	CR3_TARGET_VALUE2		= 0x0000600c,
-	CR3_TARGET_VALUE3		= 0x0000600e,
-	EXIT_QUALIFICATION		= 0x00006400,
-	GUEST_LINEAR_ADDRESS		= 0x0000640a,
-	GUEST_CR0			= 0x00006800,
-	GUEST_CR3			= 0x00006802,
-	GUEST_CR4			= 0x00006804,
-	GUEST_ES_BASE			= 0x00006806,
-	GUEST_CS_BASE			= 0x00006808,
-	GUEST_SS_BASE			= 0x0000680a,
-	GUEST_DS_BASE			= 0x0000680c,
-	GUEST_FS_BASE			= 0x0000680e,
-	GUEST_GS_BASE			= 0x00006810,
-	GUEST_LDTR_BASE			= 0x00006812,
-	GUEST_TR_BASE			= 0x00006814,
-	GUEST_GDTR_BASE			= 0x00006816,
-	GUEST_IDTR_BASE			= 0x00006818,
-	GUEST_DR7			= 0x0000681a,
-	GUEST_RSP			= 0x0000681c,
-	GUEST_RIP			= 0x0000681e,
-	GUEST_RFLAGS			= 0x00006820,
-	GUEST_PENDING_DBG_EXCEPTIONS	= 0x00006822,
-	GUEST_SYSENTER_ESP		= 0x00006824,
-	GUEST_SYSENTER_EIP		= 0x00006826,
-	HOST_CR0			= 0x00006c00,
-	HOST_CR3			= 0x00006c02,
-	HOST_CR4			= 0x00006c04,
-	HOST_FS_BASE			= 0x00006c06,
-	HOST_GS_BASE			= 0x00006c08,
-	HOST_TR_BASE			= 0x00006c0a,
-	HOST_GDTR_BASE			= 0x00006c0c,
-	HOST_IDTR_BASE			= 0x00006c0e,
-	HOST_IA32_SYSENTER_ESP		= 0x00006c10,
-	HOST_IA32_SYSENTER_EIP		= 0x00006c12,
-	HOST_RSP			= 0x00006c14,
-	HOST_RIP			= 0x00006c16,
-};
-
-struct vmx_msr_entry {
-	uint32_t index;
-	uint32_t reserved;
-	uint64_t value;
-} __attribute__ ((aligned(16)));
-
-static inline int vmxon(uint64_t phys)
-{
-	uint8_t ret;
-
-	__asm__ __volatile__ ("vmxon %[pa]; setna %[ret]"
-		: [ret]"=rm"(ret)
-		: [pa]"m"(phys)
-		: "cc", "memory");
-
-	return ret;
-}
-
-static inline void vmxoff(void)
-{
-	__asm__ __volatile__("vmxoff");
-}
-
-static inline int vmclear(uint64_t vmcs_pa)
-{
-	uint8_t ret;
-
-	__asm__ __volatile__ ("vmclear %[pa]; setna %[ret]"
-		: [ret]"=rm"(ret)
-		: [pa]"m"(vmcs_pa)
-		: "cc", "memory");
-
-	return ret;
-}
-
-static inline int vmptrld(uint64_t vmcs_pa)
-{
-	uint8_t ret;
-
-	__asm__ __volatile__ ("vmptrld %[pa]; setna %[ret]"
-		: [ret]"=rm"(ret)
-		: [pa]"m"(vmcs_pa)
-		: "cc", "memory");
-
-	return ret;
-}
-
-static inline int vmptrst(uint64_t *value)
-{
-	uint64_t tmp;
-	uint8_t ret;
-
-	__asm__ __volatile__("vmptrst %[value]; setna %[ret]"
-		: [value]"=m"(tmp), [ret]"=rm"(ret)
-		: : "cc", "memory");
-
-	*value = tmp;
-	return ret;
-}
-
-/*
- * A wrapper around vmptrst that ignores errors and returns zero if the
- * vmptrst instruction fails.
- */
-static inline uint64_t vmptrstz(void)
-{
-	uint64_t value = 0;
-	vmptrst(&value);
-	return value;
-}
-
-/*
- * No guest state (e.g. GPRs) is established by this vmlaunch.
- */
-static inline int vmlaunch(void)
-{
-	int ret;
-
-	__asm__ __volatile__("push %%rbp;"
-			     "push %%rcx;"
-			     "push %%rdx;"
-			     "push %%rsi;"
-			     "push %%rdi;"
-			     "push $0;"
-			     "vmwrite %%rsp, %[host_rsp];"
-			     "lea 1f(%%rip), %%rax;"
-			     "vmwrite %%rax, %[host_rip];"
-			     "vmlaunch;"
-			     "incq (%%rsp);"
-			     "1: pop %%rax;"
-			     "pop %%rdi;"
-			     "pop %%rsi;"
-			     "pop %%rdx;"
-			     "pop %%rcx;"
-			     "pop %%rbp;"
-			     : [ret]"=&a"(ret)
-			     : [host_rsp]"r"((uint64_t)HOST_RSP),
-			       [host_rip]"r"((uint64_t)HOST_RIP)
-			     : "memory", "cc", "rbx", "r8", "r9", "r10",
-			       "r11", "r12", "r13", "r14", "r15");
-	return ret;
-}
-
-/*
- * No guest state (e.g. GPRs) is established by this vmresume.
- */
-static inline int vmresume(void)
-{
-	int ret;
-
-	__asm__ __volatile__("push %%rbp;"
-			     "push %%rcx;"
-			     "push %%rdx;"
-			     "push %%rsi;"
-			     "push %%rdi;"
-			     "push $0;"
-			     "vmwrite %%rsp, %[host_rsp];"
-			     "lea 1f(%%rip), %%rax;"
-			     "vmwrite %%rax, %[host_rip];"
-			     "vmresume;"
-			     "incq (%%rsp);"
-			     "1: pop %%rax;"
-			     "pop %%rdi;"
-			     "pop %%rsi;"
-			     "pop %%rdx;"
-			     "pop %%rcx;"
-			     "pop %%rbp;"
-			     : [ret]"=&a"(ret)
-			     : [host_rsp]"r"((uint64_t)HOST_RSP),
-			       [host_rip]"r"((uint64_t)HOST_RIP)
-			     : "memory", "cc", "rbx", "r8", "r9", "r10",
-			       "r11", "r12", "r13", "r14", "r15");
-	return ret;
-}
-
-static inline void vmcall(void)
-{
-	/* Currently, L1 destroys our GPRs during vmexits.  */
-	__asm__ __volatile__("push %%rbp; vmcall; pop %%rbp" : : :
-			     "rax", "rbx", "rcx", "rdx",
-			     "rsi", "rdi", "r8", "r9", "r10", "r11", "r12",
-			     "r13", "r14", "r15");
-}
-
-static inline int vmread(uint64_t encoding, uint64_t *value)
-{
-	uint64_t tmp;
-	uint8_t ret;
-
-	__asm__ __volatile__("vmread %[encoding], %[value]; setna %[ret]"
-		: [value]"=rm"(tmp), [ret]"=rm"(ret)
-		: [encoding]"r"(encoding)
-		: "cc", "memory");
-
-	*value = tmp;
-	return ret;
-}
-
-/*
- * A wrapper around vmread that ignores errors and returns zero if the
- * vmread instruction fails.
- */
-static inline uint64_t vmreadz(uint64_t encoding)
-{
-	uint64_t value = 0;
-	vmread(encoding, &value);
-	return value;
-}
-
-static inline int vmwrite(uint64_t encoding, uint64_t value)
-{
-	uint8_t ret;
-
-	__asm__ __volatile__ ("vmwrite %[value], %[encoding]; setna %[ret]"
-		: [ret]"=rm"(ret)
-		: [value]"rm"(value), [encoding]"r"(encoding)
-		: "cc", "memory");
-
-	return ret;
-}
-
-static inline uint32_t vmcs_revision(void)
-{
-	return rdmsr(MSR_IA32_VMX_BASIC);
-}
-
-struct vmx_pages {
-	void *vmxon_hva;
-	uint64_t vmxon_gpa;
-	void *vmxon;
-
-	void *vmcs_hva;
-	uint64_t vmcs_gpa;
-	void *vmcs;
-
-	void *msr_hva;
-	uint64_t msr_gpa;
-	void *msr;
-
-	void *shadow_vmcs_hva;
-	uint64_t shadow_vmcs_gpa;
-	void *shadow_vmcs;
-
-	void *vmread_hva;
-	uint64_t vmread_gpa;
-	void *vmread;
-
-	void *vmwrite_hva;
-	uint64_t vmwrite_gpa;
-	void *vmwrite;
-};
-
-struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva);
-bool prepare_for_vmx_operation(struct vmx_pages *vmx);
-void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp);
-
-#endif /* !SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/include/x86.h b/tools/testing/selftests/kvm/include/x86.h
deleted file mode 100644
index 42c3596815b8..000000000000
--- a/tools/testing/selftests/kvm/include/x86.h
+++ /dev/null
@@ -1,1047 +0,0 @@
-/*
- * tools/testing/selftests/kvm/include/x86.h
- *
- * Copyright (C) 2018, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- */
-
-#ifndef SELFTEST_KVM_X86_H
-#define SELFTEST_KVM_X86_H
-
-#include <assert.h>
-#include <stdint.h>
-
-#define X86_EFLAGS_FIXED	 (1u << 1)
-
-#define X86_CR4_VME		(1ul << 0)
-#define X86_CR4_PVI		(1ul << 1)
-#define X86_CR4_TSD		(1ul << 2)
-#define X86_CR4_DE		(1ul << 3)
-#define X86_CR4_PSE		(1ul << 4)
-#define X86_CR4_PAE		(1ul << 5)
-#define X86_CR4_MCE		(1ul << 6)
-#define X86_CR4_PGE		(1ul << 7)
-#define X86_CR4_PCE		(1ul << 8)
-#define X86_CR4_OSFXSR		(1ul << 9)
-#define X86_CR4_OSXMMEXCPT	(1ul << 10)
-#define X86_CR4_UMIP		(1ul << 11)
-#define X86_CR4_VMXE		(1ul << 13)
-#define X86_CR4_SMXE		(1ul << 14)
-#define X86_CR4_FSGSBASE	(1ul << 16)
-#define X86_CR4_PCIDE		(1ul << 17)
-#define X86_CR4_OSXSAVE		(1ul << 18)
-#define X86_CR4_SMEP		(1ul << 20)
-#define X86_CR4_SMAP		(1ul << 21)
-#define X86_CR4_PKE		(1ul << 22)
-
-/* The enum values match the intruction encoding of each register */
-enum x86_register {
-	RAX = 0,
-	RCX,
-	RDX,
-	RBX,
-	RSP,
-	RBP,
-	RSI,
-	RDI,
-	R8,
-	R9,
-	R10,
-	R11,
-	R12,
-	R13,
-	R14,
-	R15,
-};
-
-struct desc64 {
-	uint16_t limit0;
-	uint16_t base0;
-	unsigned base1:8, s:1, type:4, dpl:2, p:1;
-	unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8;
-	uint32_t base3;
-	uint32_t zero1;
-} __attribute__((packed));
-
-struct desc_ptr {
-	uint16_t size;
-	uint64_t address;
-} __attribute__((packed));
-
-static inline uint64_t get_desc64_base(const struct desc64 *desc)
-{
-	return ((uint64_t)desc->base3 << 32) |
-		(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
-}
-
-static inline uint64_t rdtsc(void)
-{
-	uint32_t eax, edx;
-
-	/*
-	 * The lfence is to wait (on Intel CPUs) until all previous
-	 * instructions have been executed.
-	 */
-	__asm__ __volatile__("lfence; rdtsc" : "=a"(eax), "=d"(edx));
-	return ((uint64_t)edx) << 32 | eax;
-}
-
-static inline uint64_t rdtscp(uint32_t *aux)
-{
-	uint32_t eax, edx;
-
-	__asm__ __volatile__("rdtscp" : "=a"(eax), "=d"(edx), "=c"(*aux));
-	return ((uint64_t)edx) << 32 | eax;
-}
-
-static inline uint64_t rdmsr(uint32_t msr)
-{
-	uint32_t a, d;
-
-	__asm__ __volatile__("rdmsr" : "=a"(a), "=d"(d) : "c"(msr) : "memory");
-
-	return a | ((uint64_t) d << 32);
-}
-
-static inline void wrmsr(uint32_t msr, uint64_t value)
-{
-	uint32_t a = value;
-	uint32_t d = value >> 32;
-
-	__asm__ __volatile__("wrmsr" :: "a"(a), "d"(d), "c"(msr) : "memory");
-}
-
-
-static inline uint16_t inw(uint16_t port)
-{
-	uint16_t tmp;
-
-	__asm__ __volatile__("in %%dx, %%ax"
-		: /* output */ "=a" (tmp)
-		: /* input */ "d" (port));
-
-	return tmp;
-}
-
-static inline uint16_t get_es(void)
-{
-	uint16_t es;
-
-	__asm__ __volatile__("mov %%es, %[es]"
-			     : /* output */ [es]"=rm"(es));
-	return es;
-}
-
-static inline uint16_t get_cs(void)
-{
-	uint16_t cs;
-
-	__asm__ __volatile__("mov %%cs, %[cs]"
-			     : /* output */ [cs]"=rm"(cs));
-	return cs;
-}
-
-static inline uint16_t get_ss(void)
-{
-	uint16_t ss;
-
-	__asm__ __volatile__("mov %%ss, %[ss]"
-			     : /* output */ [ss]"=rm"(ss));
-	return ss;
-}
-
-static inline uint16_t get_ds(void)
-{
-	uint16_t ds;
-
-	__asm__ __volatile__("mov %%ds, %[ds]"
-			     : /* output */ [ds]"=rm"(ds));
-	return ds;
-}
-
-static inline uint16_t get_fs(void)
-{
-	uint16_t fs;
-
-	__asm__ __volatile__("mov %%fs, %[fs]"
-			     : /* output */ [fs]"=rm"(fs));
-	return fs;
-}
-
-static inline uint16_t get_gs(void)
-{
-	uint16_t gs;
-
-	__asm__ __volatile__("mov %%gs, %[gs]"
-			     : /* output */ [gs]"=rm"(gs));
-	return gs;
-}
-
-static inline uint16_t get_tr(void)
-{
-	uint16_t tr;
-
-	__asm__ __volatile__("str %[tr]"
-			     : /* output */ [tr]"=rm"(tr));
-	return tr;
-}
-
-static inline uint64_t get_cr0(void)
-{
-	uint64_t cr0;
-
-	__asm__ __volatile__("mov %%cr0, %[cr0]"
-			     : /* output */ [cr0]"=r"(cr0));
-	return cr0;
-}
-
-static inline uint64_t get_cr3(void)
-{
-	uint64_t cr3;
-
-	__asm__ __volatile__("mov %%cr3, %[cr3]"
-			     : /* output */ [cr3]"=r"(cr3));
-	return cr3;
-}
-
-static inline uint64_t get_cr4(void)
-{
-	uint64_t cr4;
-
-	__asm__ __volatile__("mov %%cr4, %[cr4]"
-			     : /* output */ [cr4]"=r"(cr4));
-	return cr4;
-}
-
-static inline void set_cr4(uint64_t val)
-{
-	__asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory");
-}
-
-static inline uint64_t get_gdt_base(void)
-{
-	struct desc_ptr gdt;
-	__asm__ __volatile__("sgdt %[gdt]"
-			     : /* output */ [gdt]"=m"(gdt));
-	return gdt.address;
-}
-
-static inline uint64_t get_idt_base(void)
-{
-	struct desc_ptr idt;
-	__asm__ __volatile__("sidt %[idt]"
-			     : /* output */ [idt]"=m"(idt));
-	return idt.address;
-}
-
-#define SET_XMM(__var, __xmm) \
-	asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm)
-
-static inline void set_xmm(int n, unsigned long val)
-{
-	switch (n) {
-	case 0:
-		SET_XMM(val, xmm0);
-		break;
-	case 1:
-		SET_XMM(val, xmm1);
-		break;
-	case 2:
-		SET_XMM(val, xmm2);
-		break;
-	case 3:
-		SET_XMM(val, xmm3);
-		break;
-	case 4:
-		SET_XMM(val, xmm4);
-		break;
-	case 5:
-		SET_XMM(val, xmm5);
-		break;
-	case 6:
-		SET_XMM(val, xmm6);
-		break;
-	case 7:
-		SET_XMM(val, xmm7);
-		break;
-	}
-}
-
-typedef unsigned long v1di __attribute__ ((vector_size (8)));
-static inline unsigned long get_xmm(int n)
-{
-	assert(n >= 0 && n <= 7);
-
-	register v1di xmm0 __asm__("%xmm0");
-	register v1di xmm1 __asm__("%xmm1");
-	register v1di xmm2 __asm__("%xmm2");
-	register v1di xmm3 __asm__("%xmm3");
-	register v1di xmm4 __asm__("%xmm4");
-	register v1di xmm5 __asm__("%xmm5");
-	register v1di xmm6 __asm__("%xmm6");
-	register v1di xmm7 __asm__("%xmm7");
-	switch (n) {
-	case 0:
-		return (unsigned long)xmm0;
-	case 1:
-		return (unsigned long)xmm1;
-	case 2:
-		return (unsigned long)xmm2;
-	case 3:
-		return (unsigned long)xmm3;
-	case 4:
-		return (unsigned long)xmm4;
-	case 5:
-		return (unsigned long)xmm5;
-	case 6:
-		return (unsigned long)xmm6;
-	case 7:
-		return (unsigned long)xmm7;
-	}
-	return 0;
-}
-
-struct kvm_x86_state;
-struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid);
-void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *state);
-
-/*
- * Basic CPU control in CR0
- */
-#define X86_CR0_PE          (1UL<<0) /* Protection Enable */
-#define X86_CR0_MP          (1UL<<1) /* Monitor Coprocessor */
-#define X86_CR0_EM          (1UL<<2) /* Emulation */
-#define X86_CR0_TS          (1UL<<3) /* Task Switched */
-#define X86_CR0_ET          (1UL<<4) /* Extension Type */
-#define X86_CR0_NE          (1UL<<5) /* Numeric Error */
-#define X86_CR0_WP          (1UL<<16) /* Write Protect */
-#define X86_CR0_AM          (1UL<<18) /* Alignment Mask */
-#define X86_CR0_NW          (1UL<<29) /* Not Write-through */
-#define X86_CR0_CD          (1UL<<30) /* Cache Disable */
-#define X86_CR0_PG          (1UL<<31) /* Paging */
-
-/*
- * CPU model specific register (MSR) numbers.
- */
-
-/* x86-64 specific MSRs */
-#define MSR_EFER		0xc0000080 /* extended feature register */
-#define MSR_STAR		0xc0000081 /* legacy mode SYSCALL target */
-#define MSR_LSTAR		0xc0000082 /* long mode SYSCALL target */
-#define MSR_CSTAR		0xc0000083 /* compat mode SYSCALL target */
-#define MSR_SYSCALL_MASK	0xc0000084 /* EFLAGS mask for syscall */
-#define MSR_FS_BASE		0xc0000100 /* 64bit FS base */
-#define MSR_GS_BASE		0xc0000101 /* 64bit GS base */
-#define MSR_KERNEL_GS_BASE	0xc0000102 /* SwapGS GS shadow */
-#define MSR_TSC_AUX		0xc0000103 /* Auxiliary TSC */
-
-/* EFER bits: */
-#define EFER_SCE		(1<<0)  /* SYSCALL/SYSRET */
-#define EFER_LME		(1<<8)  /* Long mode enable */
-#define EFER_LMA		(1<<10) /* Long mode active (read-only) */
-#define EFER_NX			(1<<11) /* No execute enable */
-#define EFER_SVME		(1<<12) /* Enable virtualization */
-#define EFER_LMSLE		(1<<13) /* Long Mode Segment Limit Enable */
-#define EFER_FFXSR		(1<<14) /* Enable Fast FXSAVE/FXRSTOR */
-
-/* Intel MSRs. Some also available on other CPUs */
-
-#define MSR_PPIN_CTL			0x0000004e
-#define MSR_PPIN			0x0000004f
-
-#define MSR_IA32_PERFCTR0		0x000000c1
-#define MSR_IA32_PERFCTR1		0x000000c2
-#define MSR_FSB_FREQ			0x000000cd
-#define MSR_PLATFORM_INFO		0x000000ce
-#define MSR_PLATFORM_INFO_CPUID_FAULT_BIT	31
-#define MSR_PLATFORM_INFO_CPUID_FAULT		BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT)
-
-#define MSR_PKG_CST_CONFIG_CONTROL	0x000000e2
-#define NHM_C3_AUTO_DEMOTE		(1UL << 25)
-#define NHM_C1_AUTO_DEMOTE		(1UL << 26)
-#define ATM_LNC_C6_AUTO_DEMOTE		(1UL << 25)
-#define SNB_C1_AUTO_UNDEMOTE		(1UL << 27)
-#define SNB_C3_AUTO_UNDEMOTE		(1UL << 28)
-
-#define MSR_MTRRcap			0x000000fe
-#define MSR_IA32_BBL_CR_CTL		0x00000119
-#define MSR_IA32_BBL_CR_CTL3		0x0000011e
-
-#define MSR_IA32_SYSENTER_CS		0x00000174
-#define MSR_IA32_SYSENTER_ESP		0x00000175
-#define MSR_IA32_SYSENTER_EIP		0x00000176
-
-#define MSR_IA32_MCG_CAP		0x00000179
-#define MSR_IA32_MCG_STATUS		0x0000017a
-#define MSR_IA32_MCG_CTL		0x0000017b
-#define MSR_IA32_MCG_EXT_CTL		0x000004d0
-
-#define MSR_OFFCORE_RSP_0		0x000001a6
-#define MSR_OFFCORE_RSP_1		0x000001a7
-#define MSR_TURBO_RATIO_LIMIT		0x000001ad
-#define MSR_TURBO_RATIO_LIMIT1		0x000001ae
-#define MSR_TURBO_RATIO_LIMIT2		0x000001af
-
-#define MSR_LBR_SELECT			0x000001c8
-#define MSR_LBR_TOS			0x000001c9
-#define MSR_LBR_NHM_FROM		0x00000680
-#define MSR_LBR_NHM_TO			0x000006c0
-#define MSR_LBR_CORE_FROM		0x00000040
-#define MSR_LBR_CORE_TO			0x00000060
-
-#define MSR_LBR_INFO_0			0x00000dc0 /* ... 0xddf for _31 */
-#define LBR_INFO_MISPRED		BIT_ULL(63)
-#define LBR_INFO_IN_TX			BIT_ULL(62)
-#define LBR_INFO_ABORT			BIT_ULL(61)
-#define LBR_INFO_CYCLES			0xffff
-
-#define MSR_IA32_PEBS_ENABLE		0x000003f1
-#define MSR_IA32_DS_AREA		0x00000600
-#define MSR_IA32_PERF_CAPABILITIES	0x00000345
-#define MSR_PEBS_LD_LAT_THRESHOLD	0x000003f6
-
-#define MSR_IA32_RTIT_CTL		0x00000570
-#define MSR_IA32_RTIT_STATUS		0x00000571
-#define MSR_IA32_RTIT_ADDR0_A		0x00000580
-#define MSR_IA32_RTIT_ADDR0_B		0x00000581
-#define MSR_IA32_RTIT_ADDR1_A		0x00000582
-#define MSR_IA32_RTIT_ADDR1_B		0x00000583
-#define MSR_IA32_RTIT_ADDR2_A		0x00000584
-#define MSR_IA32_RTIT_ADDR2_B		0x00000585
-#define MSR_IA32_RTIT_ADDR3_A		0x00000586
-#define MSR_IA32_RTIT_ADDR3_B		0x00000587
-#define MSR_IA32_RTIT_CR3_MATCH		0x00000572
-#define MSR_IA32_RTIT_OUTPUT_BASE	0x00000560
-#define MSR_IA32_RTIT_OUTPUT_MASK	0x00000561
-
-#define MSR_MTRRfix64K_00000		0x00000250
-#define MSR_MTRRfix16K_80000		0x00000258
-#define MSR_MTRRfix16K_A0000		0x00000259
-#define MSR_MTRRfix4K_C0000		0x00000268
-#define MSR_MTRRfix4K_C8000		0x00000269
-#define MSR_MTRRfix4K_D0000		0x0000026a
-#define MSR_MTRRfix4K_D8000		0x0000026b
-#define MSR_MTRRfix4K_E0000		0x0000026c
-#define MSR_MTRRfix4K_E8000		0x0000026d
-#define MSR_MTRRfix4K_F0000		0x0000026e
-#define MSR_MTRRfix4K_F8000		0x0000026f
-#define MSR_MTRRdefType			0x000002ff
-
-#define MSR_IA32_CR_PAT			0x00000277
-
-#define MSR_IA32_DEBUGCTLMSR		0x000001d9
-#define MSR_IA32_LASTBRANCHFROMIP	0x000001db
-#define MSR_IA32_LASTBRANCHTOIP		0x000001dc
-#define MSR_IA32_LASTINTFROMIP		0x000001dd
-#define MSR_IA32_LASTINTTOIP		0x000001de
-
-/* DEBUGCTLMSR bits (others vary by model): */
-#define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
-#define DEBUGCTLMSR_BTF_SHIFT		1
-#define DEBUGCTLMSR_BTF			(1UL <<  1) /* single-step on branches */
-#define DEBUGCTLMSR_TR			(1UL <<  6)
-#define DEBUGCTLMSR_BTS			(1UL <<  7)
-#define DEBUGCTLMSR_BTINT		(1UL <<  8)
-#define DEBUGCTLMSR_BTS_OFF_OS		(1UL <<  9)
-#define DEBUGCTLMSR_BTS_OFF_USR		(1UL << 10)
-#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI	(1UL << 11)
-#define DEBUGCTLMSR_FREEZE_IN_SMM_BIT	14
-#define DEBUGCTLMSR_FREEZE_IN_SMM	(1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT)
-
-#define MSR_PEBS_FRONTEND		0x000003f7
-
-#define MSR_IA32_POWER_CTL		0x000001fc
-
-#define MSR_IA32_MC0_CTL		0x00000400
-#define MSR_IA32_MC0_STATUS		0x00000401
-#define MSR_IA32_MC0_ADDR		0x00000402
-#define MSR_IA32_MC0_MISC		0x00000403
-
-/* C-state Residency Counters */
-#define MSR_PKG_C3_RESIDENCY		0x000003f8
-#define MSR_PKG_C6_RESIDENCY		0x000003f9
-#define MSR_ATOM_PKG_C6_RESIDENCY	0x000003fa
-#define MSR_PKG_C7_RESIDENCY		0x000003fa
-#define MSR_CORE_C3_RESIDENCY		0x000003fc
-#define MSR_CORE_C6_RESIDENCY		0x000003fd
-#define MSR_CORE_C7_RESIDENCY		0x000003fe
-#define MSR_KNL_CORE_C6_RESIDENCY	0x000003ff
-#define MSR_PKG_C2_RESIDENCY		0x0000060d
-#define MSR_PKG_C8_RESIDENCY		0x00000630
-#define MSR_PKG_C9_RESIDENCY		0x00000631
-#define MSR_PKG_C10_RESIDENCY		0x00000632
-
-/* Interrupt Response Limit */
-#define MSR_PKGC3_IRTL			0x0000060a
-#define MSR_PKGC6_IRTL			0x0000060b
-#define MSR_PKGC7_IRTL			0x0000060c
-#define MSR_PKGC8_IRTL			0x00000633
-#define MSR_PKGC9_IRTL			0x00000634
-#define MSR_PKGC10_IRTL			0x00000635
-
-/* Run Time Average Power Limiting (RAPL) Interface */
-
-#define MSR_RAPL_POWER_UNIT		0x00000606
-
-#define MSR_PKG_POWER_LIMIT		0x00000610
-#define MSR_PKG_ENERGY_STATUS		0x00000611
-#define MSR_PKG_PERF_STATUS		0x00000613
-#define MSR_PKG_POWER_INFO		0x00000614
-
-#define MSR_DRAM_POWER_LIMIT		0x00000618
-#define MSR_DRAM_ENERGY_STATUS		0x00000619
-#define MSR_DRAM_PERF_STATUS		0x0000061b
-#define MSR_DRAM_POWER_INFO		0x0000061c
-
-#define MSR_PP0_POWER_LIMIT		0x00000638
-#define MSR_PP0_ENERGY_STATUS		0x00000639
-#define MSR_PP0_POLICY			0x0000063a
-#define MSR_PP0_PERF_STATUS		0x0000063b
-
-#define MSR_PP1_POWER_LIMIT		0x00000640
-#define MSR_PP1_ENERGY_STATUS		0x00000641
-#define MSR_PP1_POLICY			0x00000642
-
-/* Config TDP MSRs */
-#define MSR_CONFIG_TDP_NOMINAL		0x00000648
-#define MSR_CONFIG_TDP_LEVEL_1		0x00000649
-#define MSR_CONFIG_TDP_LEVEL_2		0x0000064A
-#define MSR_CONFIG_TDP_CONTROL		0x0000064B
-#define MSR_TURBO_ACTIVATION_RATIO	0x0000064C
-
-#define MSR_PLATFORM_ENERGY_STATUS	0x0000064D
-
-#define MSR_PKG_WEIGHTED_CORE_C0_RES	0x00000658
-#define MSR_PKG_ANY_CORE_C0_RES		0x00000659
-#define MSR_PKG_ANY_GFXE_C0_RES		0x0000065A
-#define MSR_PKG_BOTH_CORE_GFXE_C0_RES	0x0000065B
-
-#define MSR_CORE_C1_RES			0x00000660
-#define MSR_MODULE_C6_RES_MS		0x00000664
-
-#define MSR_CC6_DEMOTION_POLICY_CONFIG	0x00000668
-#define MSR_MC6_DEMOTION_POLICY_CONFIG	0x00000669
-
-#define MSR_ATOM_CORE_RATIOS		0x0000066a
-#define MSR_ATOM_CORE_VIDS		0x0000066b
-#define MSR_ATOM_CORE_TURBO_RATIOS	0x0000066c
-#define MSR_ATOM_CORE_TURBO_VIDS	0x0000066d
-
-
-#define MSR_CORE_PERF_LIMIT_REASONS	0x00000690
-#define MSR_GFX_PERF_LIMIT_REASONS	0x000006B0
-#define MSR_RING_PERF_LIMIT_REASONS	0x000006B1
-
-/* Hardware P state interface */
-#define MSR_PPERF			0x0000064e
-#define MSR_PERF_LIMIT_REASONS		0x0000064f
-#define MSR_PM_ENABLE			0x00000770
-#define MSR_HWP_CAPABILITIES		0x00000771
-#define MSR_HWP_REQUEST_PKG		0x00000772
-#define MSR_HWP_INTERRUPT		0x00000773
-#define MSR_HWP_REQUEST			0x00000774
-#define MSR_HWP_STATUS			0x00000777
-
-/* CPUID.6.EAX */
-#define HWP_BASE_BIT			(1<<7)
-#define HWP_NOTIFICATIONS_BIT		(1<<8)
-#define HWP_ACTIVITY_WINDOW_BIT		(1<<9)
-#define HWP_ENERGY_PERF_PREFERENCE_BIT	(1<<10)
-#define HWP_PACKAGE_LEVEL_REQUEST_BIT	(1<<11)
-
-/* IA32_HWP_CAPABILITIES */
-#define HWP_HIGHEST_PERF(x)		(((x) >> 0) & 0xff)
-#define HWP_GUARANTEED_PERF(x)		(((x) >> 8) & 0xff)
-#define HWP_MOSTEFFICIENT_PERF(x)	(((x) >> 16) & 0xff)
-#define HWP_LOWEST_PERF(x)		(((x) >> 24) & 0xff)
-
-/* IA32_HWP_REQUEST */
-#define HWP_MIN_PERF(x)			(x & 0xff)
-#define HWP_MAX_PERF(x)			((x & 0xff) << 8)
-#define HWP_DESIRED_PERF(x)		((x & 0xff) << 16)
-#define HWP_ENERGY_PERF_PREFERENCE(x)	(((unsigned long long) x & 0xff) << 24)
-#define HWP_EPP_PERFORMANCE		0x00
-#define HWP_EPP_BALANCE_PERFORMANCE	0x80
-#define HWP_EPP_BALANCE_POWERSAVE	0xC0
-#define HWP_EPP_POWERSAVE		0xFF
-#define HWP_ACTIVITY_WINDOW(x)		((unsigned long long)(x & 0xff3) << 32)
-#define HWP_PACKAGE_CONTROL(x)		((unsigned long long)(x & 0x1) << 42)
-
-/* IA32_HWP_STATUS */
-#define HWP_GUARANTEED_CHANGE(x)	(x & 0x1)
-#define HWP_EXCURSION_TO_MINIMUM(x)	(x & 0x4)
-
-/* IA32_HWP_INTERRUPT */
-#define HWP_CHANGE_TO_GUARANTEED_INT(x)	(x & 0x1)
-#define HWP_EXCURSION_TO_MINIMUM_INT(x)	(x & 0x2)
-
-#define MSR_AMD64_MC0_MASK		0xc0010044
-
-#define MSR_IA32_MCx_CTL(x)		(MSR_IA32_MC0_CTL + 4*(x))
-#define MSR_IA32_MCx_STATUS(x)		(MSR_IA32_MC0_STATUS + 4*(x))
-#define MSR_IA32_MCx_ADDR(x)		(MSR_IA32_MC0_ADDR + 4*(x))
-#define MSR_IA32_MCx_MISC(x)		(MSR_IA32_MC0_MISC + 4*(x))
-
-#define MSR_AMD64_MCx_MASK(x)		(MSR_AMD64_MC0_MASK + (x))
-
-/* These are consecutive and not in the normal 4er MCE bank block */
-#define MSR_IA32_MC0_CTL2		0x00000280
-#define MSR_IA32_MCx_CTL2(x)		(MSR_IA32_MC0_CTL2 + (x))
-
-#define MSR_P6_PERFCTR0			0x000000c1
-#define MSR_P6_PERFCTR1			0x000000c2
-#define MSR_P6_EVNTSEL0			0x00000186
-#define MSR_P6_EVNTSEL1			0x00000187
-
-#define MSR_KNC_PERFCTR0               0x00000020
-#define MSR_KNC_PERFCTR1               0x00000021
-#define MSR_KNC_EVNTSEL0               0x00000028
-#define MSR_KNC_EVNTSEL1               0x00000029
-
-/* Alternative perfctr range with full access. */
-#define MSR_IA32_PMC0			0x000004c1
-
-/* AMD64 MSRs. Not complete. See the architecture manual for a more
-   complete list. */
-
-#define MSR_AMD64_PATCH_LEVEL		0x0000008b
-#define MSR_AMD64_TSC_RATIO		0xc0000104
-#define MSR_AMD64_NB_CFG		0xc001001f
-#define MSR_AMD64_PATCH_LOADER		0xc0010020
-#define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140
-#define MSR_AMD64_OSVW_STATUS		0xc0010141
-#define MSR_AMD64_LS_CFG		0xc0011020
-#define MSR_AMD64_DC_CFG		0xc0011022
-#define MSR_AMD64_BU_CFG2		0xc001102a
-#define MSR_AMD64_IBSFETCHCTL		0xc0011030
-#define MSR_AMD64_IBSFETCHLINAD		0xc0011031
-#define MSR_AMD64_IBSFETCHPHYSAD	0xc0011032
-#define MSR_AMD64_IBSFETCH_REG_COUNT	3
-#define MSR_AMD64_IBSFETCH_REG_MASK	((1UL<<MSR_AMD64_IBSFETCH_REG_COUNT)-1)
-#define MSR_AMD64_IBSOPCTL		0xc0011033
-#define MSR_AMD64_IBSOPRIP		0xc0011034
-#define MSR_AMD64_IBSOPDATA		0xc0011035
-#define MSR_AMD64_IBSOPDATA2		0xc0011036
-#define MSR_AMD64_IBSOPDATA3		0xc0011037
-#define MSR_AMD64_IBSDCLINAD		0xc0011038
-#define MSR_AMD64_IBSDCPHYSAD		0xc0011039
-#define MSR_AMD64_IBSOP_REG_COUNT	7
-#define MSR_AMD64_IBSOP_REG_MASK	((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
-#define MSR_AMD64_IBSCTL		0xc001103a
-#define MSR_AMD64_IBSBRTARGET		0xc001103b
-#define MSR_AMD64_IBSOPDATA4		0xc001103d
-#define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
-#define MSR_AMD64_SEV			0xc0010131
-#define MSR_AMD64_SEV_ENABLED_BIT	0
-#define MSR_AMD64_SEV_ENABLED		BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
-
-/* Fam 17h MSRs */
-#define MSR_F17H_IRPERF			0xc00000e9
-
-/* Fam 16h MSRs */
-#define MSR_F16H_L2I_PERF_CTL		0xc0010230
-#define MSR_F16H_L2I_PERF_CTR		0xc0010231
-#define MSR_F16H_DR1_ADDR_MASK		0xc0011019
-#define MSR_F16H_DR2_ADDR_MASK		0xc001101a
-#define MSR_F16H_DR3_ADDR_MASK		0xc001101b
-#define MSR_F16H_DR0_ADDR_MASK		0xc0011027
-
-/* Fam 15h MSRs */
-#define MSR_F15H_PERF_CTL		0xc0010200
-#define MSR_F15H_PERF_CTR		0xc0010201
-#define MSR_F15H_NB_PERF_CTL		0xc0010240
-#define MSR_F15H_NB_PERF_CTR		0xc0010241
-#define MSR_F15H_PTSC			0xc0010280
-#define MSR_F15H_IC_CFG			0xc0011021
-
-/* Fam 10h MSRs */
-#define MSR_FAM10H_MMIO_CONF_BASE	0xc0010058
-#define FAM10H_MMIO_CONF_ENABLE		(1<<0)
-#define FAM10H_MMIO_CONF_BUSRANGE_MASK	0xf
-#define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
-#define FAM10H_MMIO_CONF_BASE_MASK	0xfffffffULL
-#define FAM10H_MMIO_CONF_BASE_SHIFT	20
-#define MSR_FAM10H_NODE_ID		0xc001100c
-#define MSR_F10H_DECFG			0xc0011029
-#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT	1
-#define MSR_F10H_DECFG_LFENCE_SERIALIZE		BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT)
-
-/* K8 MSRs */
-#define MSR_K8_TOP_MEM1			0xc001001a
-#define MSR_K8_TOP_MEM2			0xc001001d
-#define MSR_K8_SYSCFG			0xc0010010
-#define MSR_K8_SYSCFG_MEM_ENCRYPT_BIT	23
-#define MSR_K8_SYSCFG_MEM_ENCRYPT	BIT_ULL(MSR_K8_SYSCFG_MEM_ENCRYPT_BIT)
-#define MSR_K8_INT_PENDING_MSG		0xc0010055
-/* C1E active bits in int pending message */
-#define K8_INTP_C1E_ACTIVE_MASK		0x18000000
-#define MSR_K8_TSEG_ADDR		0xc0010112
-#define MSR_K8_TSEG_MASK		0xc0010113
-#define K8_MTRRFIXRANGE_DRAM_ENABLE	0x00040000 /* MtrrFixDramEn bit    */
-#define K8_MTRRFIXRANGE_DRAM_MODIFY	0x00080000 /* MtrrFixDramModEn bit */
-#define K8_MTRR_RDMEM_WRMEM_MASK	0x18181818 /* Mask: RdMem|WrMem    */
-
-/* K7 MSRs */
-#define MSR_K7_EVNTSEL0			0xc0010000
-#define MSR_K7_PERFCTR0			0xc0010004
-#define MSR_K7_EVNTSEL1			0xc0010001
-#define MSR_K7_PERFCTR1			0xc0010005
-#define MSR_K7_EVNTSEL2			0xc0010002
-#define MSR_K7_PERFCTR2			0xc0010006
-#define MSR_K7_EVNTSEL3			0xc0010003
-#define MSR_K7_PERFCTR3			0xc0010007
-#define MSR_K7_CLK_CTL			0xc001001b
-#define MSR_K7_HWCR			0xc0010015
-#define MSR_K7_HWCR_SMMLOCK_BIT		0
-#define MSR_K7_HWCR_SMMLOCK		BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
-#define MSR_K7_FID_VID_CTL		0xc0010041
-#define MSR_K7_FID_VID_STATUS		0xc0010042
-
-/* K6 MSRs */
-#define MSR_K6_WHCR			0xc0000082
-#define MSR_K6_UWCCR			0xc0000085
-#define MSR_K6_EPMR			0xc0000086
-#define MSR_K6_PSOR			0xc0000087
-#define MSR_K6_PFIR			0xc0000088
-
-/* Centaur-Hauls/IDT defined MSRs. */
-#define MSR_IDT_FCR1			0x00000107
-#define MSR_IDT_FCR2			0x00000108
-#define MSR_IDT_FCR3			0x00000109
-#define MSR_IDT_FCR4			0x0000010a
-
-#define MSR_IDT_MCR0			0x00000110
-#define MSR_IDT_MCR1			0x00000111
-#define MSR_IDT_MCR2			0x00000112
-#define MSR_IDT_MCR3			0x00000113
-#define MSR_IDT_MCR4			0x00000114
-#define MSR_IDT_MCR5			0x00000115
-#define MSR_IDT_MCR6			0x00000116
-#define MSR_IDT_MCR7			0x00000117
-#define MSR_IDT_MCR_CTRL		0x00000120
-
-/* VIA Cyrix defined MSRs*/
-#define MSR_VIA_FCR			0x00001107
-#define MSR_VIA_LONGHAUL		0x0000110a
-#define MSR_VIA_RNG			0x0000110b
-#define MSR_VIA_BCR2			0x00001147
-
-/* Transmeta defined MSRs */
-#define MSR_TMTA_LONGRUN_CTRL		0x80868010
-#define MSR_TMTA_LONGRUN_FLAGS		0x80868011
-#define MSR_TMTA_LRTI_READOUT		0x80868018
-#define MSR_TMTA_LRTI_VOLT_MHZ		0x8086801a
-
-/* Intel defined MSRs. */
-#define MSR_IA32_P5_MC_ADDR		0x00000000
-#define MSR_IA32_P5_MC_TYPE		0x00000001
-#define MSR_IA32_TSC			0x00000010
-#define MSR_IA32_PLATFORM_ID		0x00000017
-#define MSR_IA32_EBL_CR_POWERON		0x0000002a
-#define MSR_EBC_FREQUENCY_ID		0x0000002c
-#define MSR_SMI_COUNT			0x00000034
-#define MSR_IA32_FEATURE_CONTROL        0x0000003a
-#define MSR_IA32_TSC_ADJUST             0x0000003b
-#define MSR_IA32_BNDCFGS		0x00000d90
-
-#define MSR_IA32_BNDCFGS_RSVD		0x00000ffc
-
-#define MSR_IA32_XSS			0x00000da0
-
-#define FEATURE_CONTROL_LOCKED				(1<<0)
-#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX	(1<<1)
-#define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX	(1<<2)
-#define FEATURE_CONTROL_LMCE				(1<<20)
-
-#define MSR_IA32_APICBASE		0x0000001b
-#define MSR_IA32_APICBASE_BSP		(1<<8)
-#define MSR_IA32_APICBASE_ENABLE	(1<<11)
-#define MSR_IA32_APICBASE_BASE		(0xfffff<<12)
-
-#define MSR_IA32_TSCDEADLINE		0x000006e0
-
-#define MSR_IA32_UCODE_WRITE		0x00000079
-#define MSR_IA32_UCODE_REV		0x0000008b
-
-#define MSR_IA32_SMM_MONITOR_CTL	0x0000009b
-#define MSR_IA32_SMBASE			0x0000009e
-
-#define MSR_IA32_PERF_STATUS		0x00000198
-#define MSR_IA32_PERF_CTL		0x00000199
-#define INTEL_PERF_CTL_MASK		0xffff
-#define MSR_AMD_PSTATE_DEF_BASE		0xc0010064
-#define MSR_AMD_PERF_STATUS		0xc0010063
-#define MSR_AMD_PERF_CTL		0xc0010062
-
-#define MSR_IA32_MPERF			0x000000e7
-#define MSR_IA32_APERF			0x000000e8
-
-#define MSR_IA32_THERM_CONTROL		0x0000019a
-#define MSR_IA32_THERM_INTERRUPT	0x0000019b
-
-#define THERM_INT_HIGH_ENABLE		(1 << 0)
-#define THERM_INT_LOW_ENABLE		(1 << 1)
-#define THERM_INT_PLN_ENABLE		(1 << 24)
-
-#define MSR_IA32_THERM_STATUS		0x0000019c
-
-#define THERM_STATUS_PROCHOT		(1 << 0)
-#define THERM_STATUS_POWER_LIMIT	(1 << 10)
-
-#define MSR_THERM2_CTL			0x0000019d
-
-#define MSR_THERM2_CTL_TM_SELECT	(1ULL << 16)
-
-#define MSR_IA32_MISC_ENABLE		0x000001a0
-
-#define MSR_IA32_TEMPERATURE_TARGET	0x000001a2
-
-#define MSR_MISC_FEATURE_CONTROL	0x000001a4
-#define MSR_MISC_PWR_MGMT		0x000001aa
-
-#define MSR_IA32_ENERGY_PERF_BIAS	0x000001b0
-#define ENERGY_PERF_BIAS_PERFORMANCE		0
-#define ENERGY_PERF_BIAS_BALANCE_PERFORMANCE	4
-#define ENERGY_PERF_BIAS_NORMAL			6
-#define ENERGY_PERF_BIAS_BALANCE_POWERSAVE	8
-#define ENERGY_PERF_BIAS_POWERSAVE		15
-
-#define MSR_IA32_PACKAGE_THERM_STATUS		0x000001b1
-
-#define PACKAGE_THERM_STATUS_PROCHOT		(1 << 0)
-#define PACKAGE_THERM_STATUS_POWER_LIMIT	(1 << 10)
-
-#define MSR_IA32_PACKAGE_THERM_INTERRUPT	0x000001b2
-
-#define PACKAGE_THERM_INT_HIGH_ENABLE		(1 << 0)
-#define PACKAGE_THERM_INT_LOW_ENABLE		(1 << 1)
-#define PACKAGE_THERM_INT_PLN_ENABLE		(1 << 24)
-
-/* Thermal Thresholds Support */
-#define THERM_INT_THRESHOLD0_ENABLE    (1 << 15)
-#define THERM_SHIFT_THRESHOLD0        8
-#define THERM_MASK_THRESHOLD0          (0x7f << THERM_SHIFT_THRESHOLD0)
-#define THERM_INT_THRESHOLD1_ENABLE    (1 << 23)
-#define THERM_SHIFT_THRESHOLD1        16
-#define THERM_MASK_THRESHOLD1          (0x7f << THERM_SHIFT_THRESHOLD1)
-#define THERM_STATUS_THRESHOLD0        (1 << 6)
-#define THERM_LOG_THRESHOLD0           (1 << 7)
-#define THERM_STATUS_THRESHOLD1        (1 << 8)
-#define THERM_LOG_THRESHOLD1           (1 << 9)
-
-/* MISC_ENABLE bits: architectural */
-#define MSR_IA32_MISC_ENABLE_FAST_STRING_BIT		0
-#define MSR_IA32_MISC_ENABLE_FAST_STRING		(1ULL << MSR_IA32_MISC_ENABLE_FAST_STRING_BIT)
-#define MSR_IA32_MISC_ENABLE_TCC_BIT			1
-#define MSR_IA32_MISC_ENABLE_TCC			(1ULL << MSR_IA32_MISC_ENABLE_TCC_BIT)
-#define MSR_IA32_MISC_ENABLE_EMON_BIT			7
-#define MSR_IA32_MISC_ENABLE_EMON			(1ULL << MSR_IA32_MISC_ENABLE_EMON_BIT)
-#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT		11
-#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL		(1ULL << MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT)
-#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT		12
-#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL		(1ULL << MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT)
-#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT	16
-#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP		(1ULL << MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT)
-#define MSR_IA32_MISC_ENABLE_MWAIT_BIT			18
-#define MSR_IA32_MISC_ENABLE_MWAIT			(1ULL << MSR_IA32_MISC_ENABLE_MWAIT_BIT)
-#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT		22
-#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID		(1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT)
-#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT		23
-#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT		34
-#define MSR_IA32_MISC_ENABLE_XD_DISABLE			(1ULL << MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT)
-
-/* MISC_ENABLE bits: model-specific, meaning may vary from core to core */
-#define MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT		2
-#define MSR_IA32_MISC_ENABLE_X87_COMPAT			(1ULL << MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT)
-#define MSR_IA32_MISC_ENABLE_TM1_BIT			3
-#define MSR_IA32_MISC_ENABLE_TM1			(1ULL << MSR_IA32_MISC_ENABLE_TM1_BIT)
-#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT	4
-#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT	6
-#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT		8
-#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK		(1ULL << MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT)
-#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT	9
-#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_FERR_BIT			10
-#define MSR_IA32_MISC_ENABLE_FERR			(1ULL << MSR_IA32_MISC_ENABLE_FERR_BIT)
-#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT		10
-#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX		(1ULL << MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT)
-#define MSR_IA32_MISC_ENABLE_TM2_BIT			13
-#define MSR_IA32_MISC_ENABLE_TM2			(1ULL << MSR_IA32_MISC_ENABLE_TM2_BIT)
-#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT	19
-#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT		20
-#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK		(1ULL << MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT)
-#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT		24
-#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT		(1ULL << MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT)
-#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT	37
-#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT		38
-#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT)
-#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT	39
-#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT)
-
-/* MISC_FEATURES_ENABLES non-architectural features */
-#define MSR_MISC_FEATURES_ENABLES	0x00000140
-
-#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT	0
-#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT		BIT_ULL(MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT)
-#define MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT	1
-
-#define MSR_IA32_TSC_DEADLINE		0x000006E0
-
-/* P4/Xeon+ specific */
-#define MSR_IA32_MCG_EAX		0x00000180
-#define MSR_IA32_MCG_EBX		0x00000181
-#define MSR_IA32_MCG_ECX		0x00000182
-#define MSR_IA32_MCG_EDX		0x00000183
-#define MSR_IA32_MCG_ESI		0x00000184
-#define MSR_IA32_MCG_EDI		0x00000185
-#define MSR_IA32_MCG_EBP		0x00000186
-#define MSR_IA32_MCG_ESP		0x00000187
-#define MSR_IA32_MCG_EFLAGS		0x00000188
-#define MSR_IA32_MCG_EIP		0x00000189
-#define MSR_IA32_MCG_RESERVED		0x0000018a
-
-/* Pentium IV performance counter MSRs */
-#define MSR_P4_BPU_PERFCTR0		0x00000300
-#define MSR_P4_BPU_PERFCTR1		0x00000301
-#define MSR_P4_BPU_PERFCTR2		0x00000302
-#define MSR_P4_BPU_PERFCTR3		0x00000303
-#define MSR_P4_MS_PERFCTR0		0x00000304
-#define MSR_P4_MS_PERFCTR1		0x00000305
-#define MSR_P4_MS_PERFCTR2		0x00000306
-#define MSR_P4_MS_PERFCTR3		0x00000307
-#define MSR_P4_FLAME_PERFCTR0		0x00000308
-#define MSR_P4_FLAME_PERFCTR1		0x00000309
-#define MSR_P4_FLAME_PERFCTR2		0x0000030a
-#define MSR_P4_FLAME_PERFCTR3		0x0000030b
-#define MSR_P4_IQ_PERFCTR0		0x0000030c
-#define MSR_P4_IQ_PERFCTR1		0x0000030d
-#define MSR_P4_IQ_PERFCTR2		0x0000030e
-#define MSR_P4_IQ_PERFCTR3		0x0000030f
-#define MSR_P4_IQ_PERFCTR4		0x00000310
-#define MSR_P4_IQ_PERFCTR5		0x00000311
-#define MSR_P4_BPU_CCCR0		0x00000360
-#define MSR_P4_BPU_CCCR1		0x00000361
-#define MSR_P4_BPU_CCCR2		0x00000362
-#define MSR_P4_BPU_CCCR3		0x00000363
-#define MSR_P4_MS_CCCR0			0x00000364
-#define MSR_P4_MS_CCCR1			0x00000365
-#define MSR_P4_MS_CCCR2			0x00000366
-#define MSR_P4_MS_CCCR3			0x00000367
-#define MSR_P4_FLAME_CCCR0		0x00000368
-#define MSR_P4_FLAME_CCCR1		0x00000369
-#define MSR_P4_FLAME_CCCR2		0x0000036a
-#define MSR_P4_FLAME_CCCR3		0x0000036b
-#define MSR_P4_IQ_CCCR0			0x0000036c
-#define MSR_P4_IQ_CCCR1			0x0000036d
-#define MSR_P4_IQ_CCCR2			0x0000036e
-#define MSR_P4_IQ_CCCR3			0x0000036f
-#define MSR_P4_IQ_CCCR4			0x00000370
-#define MSR_P4_IQ_CCCR5			0x00000371
-#define MSR_P4_ALF_ESCR0		0x000003ca
-#define MSR_P4_ALF_ESCR1		0x000003cb
-#define MSR_P4_BPU_ESCR0		0x000003b2
-#define MSR_P4_BPU_ESCR1		0x000003b3
-#define MSR_P4_BSU_ESCR0		0x000003a0
-#define MSR_P4_BSU_ESCR1		0x000003a1
-#define MSR_P4_CRU_ESCR0		0x000003b8
-#define MSR_P4_CRU_ESCR1		0x000003b9
-#define MSR_P4_CRU_ESCR2		0x000003cc
-#define MSR_P4_CRU_ESCR3		0x000003cd
-#define MSR_P4_CRU_ESCR4		0x000003e0
-#define MSR_P4_CRU_ESCR5		0x000003e1
-#define MSR_P4_DAC_ESCR0		0x000003a8
-#define MSR_P4_DAC_ESCR1		0x000003a9
-#define MSR_P4_FIRM_ESCR0		0x000003a4
-#define MSR_P4_FIRM_ESCR1		0x000003a5
-#define MSR_P4_FLAME_ESCR0		0x000003a6
-#define MSR_P4_FLAME_ESCR1		0x000003a7
-#define MSR_P4_FSB_ESCR0		0x000003a2
-#define MSR_P4_FSB_ESCR1		0x000003a3
-#define MSR_P4_IQ_ESCR0			0x000003ba
-#define MSR_P4_IQ_ESCR1			0x000003bb
-#define MSR_P4_IS_ESCR0			0x000003b4
-#define MSR_P4_IS_ESCR1			0x000003b5
-#define MSR_P4_ITLB_ESCR0		0x000003b6
-#define MSR_P4_ITLB_ESCR1		0x000003b7
-#define MSR_P4_IX_ESCR0			0x000003c8
-#define MSR_P4_IX_ESCR1			0x000003c9
-#define MSR_P4_MOB_ESCR0		0x000003aa
-#define MSR_P4_MOB_ESCR1		0x000003ab
-#define MSR_P4_MS_ESCR0			0x000003c0
-#define MSR_P4_MS_ESCR1			0x000003c1
-#define MSR_P4_PMH_ESCR0		0x000003ac
-#define MSR_P4_PMH_ESCR1		0x000003ad
-#define MSR_P4_RAT_ESCR0		0x000003bc
-#define MSR_P4_RAT_ESCR1		0x000003bd
-#define MSR_P4_SAAT_ESCR0		0x000003ae
-#define MSR_P4_SAAT_ESCR1		0x000003af
-#define MSR_P4_SSU_ESCR0		0x000003be
-#define MSR_P4_SSU_ESCR1		0x000003bf /* guess: not in manual */
-
-#define MSR_P4_TBPU_ESCR0		0x000003c2
-#define MSR_P4_TBPU_ESCR1		0x000003c3
-#define MSR_P4_TC_ESCR0			0x000003c4
-#define MSR_P4_TC_ESCR1			0x000003c5
-#define MSR_P4_U2L_ESCR0		0x000003b0
-#define MSR_P4_U2L_ESCR1		0x000003b1
-
-#define MSR_P4_PEBS_MATRIX_VERT		0x000003f2
-
-/* Intel Core-based CPU performance counters */
-#define MSR_CORE_PERF_FIXED_CTR0	0x00000309
-#define MSR_CORE_PERF_FIXED_CTR1	0x0000030a
-#define MSR_CORE_PERF_FIXED_CTR2	0x0000030b
-#define MSR_CORE_PERF_FIXED_CTR_CTRL	0x0000038d
-#define MSR_CORE_PERF_GLOBAL_STATUS	0x0000038e
-#define MSR_CORE_PERF_GLOBAL_CTRL	0x0000038f
-#define MSR_CORE_PERF_GLOBAL_OVF_CTRL	0x00000390
-
-/* Geode defined MSRs */
-#define MSR_GEODE_BUSCONT_CONF0		0x00001900
-
-/* Intel VT MSRs */
-#define MSR_IA32_VMX_BASIC              0x00000480
-#define MSR_IA32_VMX_PINBASED_CTLS      0x00000481
-#define MSR_IA32_VMX_PROCBASED_CTLS     0x00000482
-#define MSR_IA32_VMX_EXIT_CTLS          0x00000483
-#define MSR_IA32_VMX_ENTRY_CTLS         0x00000484
-#define MSR_IA32_VMX_MISC               0x00000485
-#define MSR_IA32_VMX_CR0_FIXED0         0x00000486
-#define MSR_IA32_VMX_CR0_FIXED1         0x00000487
-#define MSR_IA32_VMX_CR4_FIXED0         0x00000488
-#define MSR_IA32_VMX_CR4_FIXED1         0x00000489
-#define MSR_IA32_VMX_VMCS_ENUM          0x0000048a
-#define MSR_IA32_VMX_PROCBASED_CTLS2    0x0000048b
-#define MSR_IA32_VMX_EPT_VPID_CAP       0x0000048c
-#define MSR_IA32_VMX_TRUE_PINBASED_CTLS  0x0000048d
-#define MSR_IA32_VMX_TRUE_PROCBASED_CTLS 0x0000048e
-#define MSR_IA32_VMX_TRUE_EXIT_CTLS      0x0000048f
-#define MSR_IA32_VMX_TRUE_ENTRY_CTLS     0x00000490
-#define MSR_IA32_VMX_VMFUNC             0x00000491
-
-/* VMX_BASIC bits and bitmasks */
-#define VMX_BASIC_VMCS_SIZE_SHIFT	32
-#define VMX_BASIC_TRUE_CTLS		(1ULL << 55)
-#define VMX_BASIC_64		0x0001000000000000LLU
-#define VMX_BASIC_MEM_TYPE_SHIFT	50
-#define VMX_BASIC_MEM_TYPE_MASK	0x003c000000000000LLU
-#define VMX_BASIC_MEM_TYPE_WB	6LLU
-#define VMX_BASIC_INOUT		0x0040000000000000LLU
-
-/* MSR_IA32_VMX_MISC bits */
-#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
-#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE   0x1F
-/* AMD-V MSRs */
-
-#define MSR_VM_CR                       0xc0010114
-#define MSR_VM_IGNNE                    0xc0010115
-#define MSR_VM_HSAVE_PA                 0xc0010117
-
-#endif /* !SELFTEST_KVM_X86_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
new file mode 100644
index 000000000000..bb76e8db9b2b
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -0,0 +1,1047 @@
+/*
+ * tools/testing/selftests/kvm/include/x86_64/processor.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ */
+
+#ifndef SELFTEST_KVM_PROCESSOR_H
+#define SELFTEST_KVM_PROCESSOR_H
+
+#include <assert.h>
+#include <stdint.h>
+
+#define X86_EFLAGS_FIXED	 (1u << 1)
+
+#define X86_CR4_VME		(1ul << 0)
+#define X86_CR4_PVI		(1ul << 1)
+#define X86_CR4_TSD		(1ul << 2)
+#define X86_CR4_DE		(1ul << 3)
+#define X86_CR4_PSE		(1ul << 4)
+#define X86_CR4_PAE		(1ul << 5)
+#define X86_CR4_MCE		(1ul << 6)
+#define X86_CR4_PGE		(1ul << 7)
+#define X86_CR4_PCE		(1ul << 8)
+#define X86_CR4_OSFXSR		(1ul << 9)
+#define X86_CR4_OSXMMEXCPT	(1ul << 10)
+#define X86_CR4_UMIP		(1ul << 11)
+#define X86_CR4_VMXE		(1ul << 13)
+#define X86_CR4_SMXE		(1ul << 14)
+#define X86_CR4_FSGSBASE	(1ul << 16)
+#define X86_CR4_PCIDE		(1ul << 17)
+#define X86_CR4_OSXSAVE		(1ul << 18)
+#define X86_CR4_SMEP		(1ul << 20)
+#define X86_CR4_SMAP		(1ul << 21)
+#define X86_CR4_PKE		(1ul << 22)
+
+/* The enum values match the intruction encoding of each register */
+enum x86_register {
+	RAX = 0,
+	RCX,
+	RDX,
+	RBX,
+	RSP,
+	RBP,
+	RSI,
+	RDI,
+	R8,
+	R9,
+	R10,
+	R11,
+	R12,
+	R13,
+	R14,
+	R15,
+};
+
+struct desc64 {
+	uint16_t limit0;
+	uint16_t base0;
+	unsigned base1:8, s:1, type:4, dpl:2, p:1;
+	unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8;
+	uint32_t base3;
+	uint32_t zero1;
+} __attribute__((packed));
+
+struct desc_ptr {
+	uint16_t size;
+	uint64_t address;
+} __attribute__((packed));
+
+static inline uint64_t get_desc64_base(const struct desc64 *desc)
+{
+	return ((uint64_t)desc->base3 << 32) |
+		(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
+}
+
+static inline uint64_t rdtsc(void)
+{
+	uint32_t eax, edx;
+
+	/*
+	 * The lfence is to wait (on Intel CPUs) until all previous
+	 * instructions have been executed.
+	 */
+	__asm__ __volatile__("lfence; rdtsc" : "=a"(eax), "=d"(edx));
+	return ((uint64_t)edx) << 32 | eax;
+}
+
+static inline uint64_t rdtscp(uint32_t *aux)
+{
+	uint32_t eax, edx;
+
+	__asm__ __volatile__("rdtscp" : "=a"(eax), "=d"(edx), "=c"(*aux));
+	return ((uint64_t)edx) << 32 | eax;
+}
+
+static inline uint64_t rdmsr(uint32_t msr)
+{
+	uint32_t a, d;
+
+	__asm__ __volatile__("rdmsr" : "=a"(a), "=d"(d) : "c"(msr) : "memory");
+
+	return a | ((uint64_t) d << 32);
+}
+
+static inline void wrmsr(uint32_t msr, uint64_t value)
+{
+	uint32_t a = value;
+	uint32_t d = value >> 32;
+
+	__asm__ __volatile__("wrmsr" :: "a"(a), "d"(d), "c"(msr) : "memory");
+}
+
+
+static inline uint16_t inw(uint16_t port)
+{
+	uint16_t tmp;
+
+	__asm__ __volatile__("in %%dx, %%ax"
+		: /* output */ "=a" (tmp)
+		: /* input */ "d" (port));
+
+	return tmp;
+}
+
+static inline uint16_t get_es(void)
+{
+	uint16_t es;
+
+	__asm__ __volatile__("mov %%es, %[es]"
+			     : /* output */ [es]"=rm"(es));
+	return es;
+}
+
+static inline uint16_t get_cs(void)
+{
+	uint16_t cs;
+
+	__asm__ __volatile__("mov %%cs, %[cs]"
+			     : /* output */ [cs]"=rm"(cs));
+	return cs;
+}
+
+static inline uint16_t get_ss(void)
+{
+	uint16_t ss;
+
+	__asm__ __volatile__("mov %%ss, %[ss]"
+			     : /* output */ [ss]"=rm"(ss));
+	return ss;
+}
+
+static inline uint16_t get_ds(void)
+{
+	uint16_t ds;
+
+	__asm__ __volatile__("mov %%ds, %[ds]"
+			     : /* output */ [ds]"=rm"(ds));
+	return ds;
+}
+
+static inline uint16_t get_fs(void)
+{
+	uint16_t fs;
+
+	__asm__ __volatile__("mov %%fs, %[fs]"
+			     : /* output */ [fs]"=rm"(fs));
+	return fs;
+}
+
+static inline uint16_t get_gs(void)
+{
+	uint16_t gs;
+
+	__asm__ __volatile__("mov %%gs, %[gs]"
+			     : /* output */ [gs]"=rm"(gs));
+	return gs;
+}
+
+static inline uint16_t get_tr(void)
+{
+	uint16_t tr;
+
+	__asm__ __volatile__("str %[tr]"
+			     : /* output */ [tr]"=rm"(tr));
+	return tr;
+}
+
+static inline uint64_t get_cr0(void)
+{
+	uint64_t cr0;
+
+	__asm__ __volatile__("mov %%cr0, %[cr0]"
+			     : /* output */ [cr0]"=r"(cr0));
+	return cr0;
+}
+
+static inline uint64_t get_cr3(void)
+{
+	uint64_t cr3;
+
+	__asm__ __volatile__("mov %%cr3, %[cr3]"
+			     : /* output */ [cr3]"=r"(cr3));
+	return cr3;
+}
+
+static inline uint64_t get_cr4(void)
+{
+	uint64_t cr4;
+
+	__asm__ __volatile__("mov %%cr4, %[cr4]"
+			     : /* output */ [cr4]"=r"(cr4));
+	return cr4;
+}
+
+static inline void set_cr4(uint64_t val)
+{
+	__asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory");
+}
+
+static inline uint64_t get_gdt_base(void)
+{
+	struct desc_ptr gdt;
+	__asm__ __volatile__("sgdt %[gdt]"
+			     : /* output */ [gdt]"=m"(gdt));
+	return gdt.address;
+}
+
+static inline uint64_t get_idt_base(void)
+{
+	struct desc_ptr idt;
+	__asm__ __volatile__("sidt %[idt]"
+			     : /* output */ [idt]"=m"(idt));
+	return idt.address;
+}
+
+#define SET_XMM(__var, __xmm) \
+	asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm)
+
+static inline void set_xmm(int n, unsigned long val)
+{
+	switch (n) {
+	case 0:
+		SET_XMM(val, xmm0);
+		break;
+	case 1:
+		SET_XMM(val, xmm1);
+		break;
+	case 2:
+		SET_XMM(val, xmm2);
+		break;
+	case 3:
+		SET_XMM(val, xmm3);
+		break;
+	case 4:
+		SET_XMM(val, xmm4);
+		break;
+	case 5:
+		SET_XMM(val, xmm5);
+		break;
+	case 6:
+		SET_XMM(val, xmm6);
+		break;
+	case 7:
+		SET_XMM(val, xmm7);
+		break;
+	}
+}
+
+typedef unsigned long v1di __attribute__ ((vector_size (8)));
+static inline unsigned long get_xmm(int n)
+{
+	assert(n >= 0 && n <= 7);
+
+	register v1di xmm0 __asm__("%xmm0");
+	register v1di xmm1 __asm__("%xmm1");
+	register v1di xmm2 __asm__("%xmm2");
+	register v1di xmm3 __asm__("%xmm3");
+	register v1di xmm4 __asm__("%xmm4");
+	register v1di xmm5 __asm__("%xmm5");
+	register v1di xmm6 __asm__("%xmm6");
+	register v1di xmm7 __asm__("%xmm7");
+	switch (n) {
+	case 0:
+		return (unsigned long)xmm0;
+	case 1:
+		return (unsigned long)xmm1;
+	case 2:
+		return (unsigned long)xmm2;
+	case 3:
+		return (unsigned long)xmm3;
+	case 4:
+		return (unsigned long)xmm4;
+	case 5:
+		return (unsigned long)xmm5;
+	case 6:
+		return (unsigned long)xmm6;
+	case 7:
+		return (unsigned long)xmm7;
+	}
+	return 0;
+}
+
+struct kvm_x86_state;
+struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *state);
+
+/*
+ * Basic CPU control in CR0
+ */
+#define X86_CR0_PE          (1UL<<0) /* Protection Enable */
+#define X86_CR0_MP          (1UL<<1) /* Monitor Coprocessor */
+#define X86_CR0_EM          (1UL<<2) /* Emulation */
+#define X86_CR0_TS          (1UL<<3) /* Task Switched */
+#define X86_CR0_ET          (1UL<<4) /* Extension Type */
+#define X86_CR0_NE          (1UL<<5) /* Numeric Error */
+#define X86_CR0_WP          (1UL<<16) /* Write Protect */
+#define X86_CR0_AM          (1UL<<18) /* Alignment Mask */
+#define X86_CR0_NW          (1UL<<29) /* Not Write-through */
+#define X86_CR0_CD          (1UL<<30) /* Cache Disable */
+#define X86_CR0_PG          (1UL<<31) /* Paging */
+
+/*
+ * CPU model specific register (MSR) numbers.
+ */
+
+/* x86-64 specific MSRs */
+#define MSR_EFER		0xc0000080 /* extended feature register */
+#define MSR_STAR		0xc0000081 /* legacy mode SYSCALL target */
+#define MSR_LSTAR		0xc0000082 /* long mode SYSCALL target */
+#define MSR_CSTAR		0xc0000083 /* compat mode SYSCALL target */
+#define MSR_SYSCALL_MASK	0xc0000084 /* EFLAGS mask for syscall */
+#define MSR_FS_BASE		0xc0000100 /* 64bit FS base */
+#define MSR_GS_BASE		0xc0000101 /* 64bit GS base */
+#define MSR_KERNEL_GS_BASE	0xc0000102 /* SwapGS GS shadow */
+#define MSR_TSC_AUX		0xc0000103 /* Auxiliary TSC */
+
+/* EFER bits: */
+#define EFER_SCE		(1<<0)  /* SYSCALL/SYSRET */
+#define EFER_LME		(1<<8)  /* Long mode enable */
+#define EFER_LMA		(1<<10) /* Long mode active (read-only) */
+#define EFER_NX			(1<<11) /* No execute enable */
+#define EFER_SVME		(1<<12) /* Enable virtualization */
+#define EFER_LMSLE		(1<<13) /* Long Mode Segment Limit Enable */
+#define EFER_FFXSR		(1<<14) /* Enable Fast FXSAVE/FXRSTOR */
+
+/* Intel MSRs. Some also available on other CPUs */
+
+#define MSR_PPIN_CTL			0x0000004e
+#define MSR_PPIN			0x0000004f
+
+#define MSR_IA32_PERFCTR0		0x000000c1
+#define MSR_IA32_PERFCTR1		0x000000c2
+#define MSR_FSB_FREQ			0x000000cd
+#define MSR_PLATFORM_INFO		0x000000ce
+#define MSR_PLATFORM_INFO_CPUID_FAULT_BIT	31
+#define MSR_PLATFORM_INFO_CPUID_FAULT		BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT)
+
+#define MSR_PKG_CST_CONFIG_CONTROL	0x000000e2
+#define NHM_C3_AUTO_DEMOTE		(1UL << 25)
+#define NHM_C1_AUTO_DEMOTE		(1UL << 26)
+#define ATM_LNC_C6_AUTO_DEMOTE		(1UL << 25)
+#define SNB_C1_AUTO_UNDEMOTE		(1UL << 27)
+#define SNB_C3_AUTO_UNDEMOTE		(1UL << 28)
+
+#define MSR_MTRRcap			0x000000fe
+#define MSR_IA32_BBL_CR_CTL		0x00000119
+#define MSR_IA32_BBL_CR_CTL3		0x0000011e
+
+#define MSR_IA32_SYSENTER_CS		0x00000174
+#define MSR_IA32_SYSENTER_ESP		0x00000175
+#define MSR_IA32_SYSENTER_EIP		0x00000176
+
+#define MSR_IA32_MCG_CAP		0x00000179
+#define MSR_IA32_MCG_STATUS		0x0000017a
+#define MSR_IA32_MCG_CTL		0x0000017b
+#define MSR_IA32_MCG_EXT_CTL		0x000004d0
+
+#define MSR_OFFCORE_RSP_0		0x000001a6
+#define MSR_OFFCORE_RSP_1		0x000001a7
+#define MSR_TURBO_RATIO_LIMIT		0x000001ad
+#define MSR_TURBO_RATIO_LIMIT1		0x000001ae
+#define MSR_TURBO_RATIO_LIMIT2		0x000001af
+
+#define MSR_LBR_SELECT			0x000001c8
+#define MSR_LBR_TOS			0x000001c9
+#define MSR_LBR_NHM_FROM		0x00000680
+#define MSR_LBR_NHM_TO			0x000006c0
+#define MSR_LBR_CORE_FROM		0x00000040
+#define MSR_LBR_CORE_TO			0x00000060
+
+#define MSR_LBR_INFO_0			0x00000dc0 /* ... 0xddf for _31 */
+#define LBR_INFO_MISPRED		BIT_ULL(63)
+#define LBR_INFO_IN_TX			BIT_ULL(62)
+#define LBR_INFO_ABORT			BIT_ULL(61)
+#define LBR_INFO_CYCLES			0xffff
+
+#define MSR_IA32_PEBS_ENABLE		0x000003f1
+#define MSR_IA32_DS_AREA		0x00000600
+#define MSR_IA32_PERF_CAPABILITIES	0x00000345
+#define MSR_PEBS_LD_LAT_THRESHOLD	0x000003f6
+
+#define MSR_IA32_RTIT_CTL		0x00000570
+#define MSR_IA32_RTIT_STATUS		0x00000571
+#define MSR_IA32_RTIT_ADDR0_A		0x00000580
+#define MSR_IA32_RTIT_ADDR0_B		0x00000581
+#define MSR_IA32_RTIT_ADDR1_A		0x00000582
+#define MSR_IA32_RTIT_ADDR1_B		0x00000583
+#define MSR_IA32_RTIT_ADDR2_A		0x00000584
+#define MSR_IA32_RTIT_ADDR2_B		0x00000585
+#define MSR_IA32_RTIT_ADDR3_A		0x00000586
+#define MSR_IA32_RTIT_ADDR3_B		0x00000587
+#define MSR_IA32_RTIT_CR3_MATCH		0x00000572
+#define MSR_IA32_RTIT_OUTPUT_BASE	0x00000560
+#define MSR_IA32_RTIT_OUTPUT_MASK	0x00000561
+
+#define MSR_MTRRfix64K_00000		0x00000250
+#define MSR_MTRRfix16K_80000		0x00000258
+#define MSR_MTRRfix16K_A0000		0x00000259
+#define MSR_MTRRfix4K_C0000		0x00000268
+#define MSR_MTRRfix4K_C8000		0x00000269
+#define MSR_MTRRfix4K_D0000		0x0000026a
+#define MSR_MTRRfix4K_D8000		0x0000026b
+#define MSR_MTRRfix4K_E0000		0x0000026c
+#define MSR_MTRRfix4K_E8000		0x0000026d
+#define MSR_MTRRfix4K_F0000		0x0000026e
+#define MSR_MTRRfix4K_F8000		0x0000026f
+#define MSR_MTRRdefType			0x000002ff
+
+#define MSR_IA32_CR_PAT			0x00000277
+
+#define MSR_IA32_DEBUGCTLMSR		0x000001d9
+#define MSR_IA32_LASTBRANCHFROMIP	0x000001db
+#define MSR_IA32_LASTBRANCHTOIP		0x000001dc
+#define MSR_IA32_LASTINTFROMIP		0x000001dd
+#define MSR_IA32_LASTINTTOIP		0x000001de
+
+/* DEBUGCTLMSR bits (others vary by model): */
+#define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
+#define DEBUGCTLMSR_BTF_SHIFT		1
+#define DEBUGCTLMSR_BTF			(1UL <<  1) /* single-step on branches */
+#define DEBUGCTLMSR_TR			(1UL <<  6)
+#define DEBUGCTLMSR_BTS			(1UL <<  7)
+#define DEBUGCTLMSR_BTINT		(1UL <<  8)
+#define DEBUGCTLMSR_BTS_OFF_OS		(1UL <<  9)
+#define DEBUGCTLMSR_BTS_OFF_USR		(1UL << 10)
+#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI	(1UL << 11)
+#define DEBUGCTLMSR_FREEZE_IN_SMM_BIT	14
+#define DEBUGCTLMSR_FREEZE_IN_SMM	(1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT)
+
+#define MSR_PEBS_FRONTEND		0x000003f7
+
+#define MSR_IA32_POWER_CTL		0x000001fc
+
+#define MSR_IA32_MC0_CTL		0x00000400
+#define MSR_IA32_MC0_STATUS		0x00000401
+#define MSR_IA32_MC0_ADDR		0x00000402
+#define MSR_IA32_MC0_MISC		0x00000403
+
+/* C-state Residency Counters */
+#define MSR_PKG_C3_RESIDENCY		0x000003f8
+#define MSR_PKG_C6_RESIDENCY		0x000003f9
+#define MSR_ATOM_PKG_C6_RESIDENCY	0x000003fa
+#define MSR_PKG_C7_RESIDENCY		0x000003fa
+#define MSR_CORE_C3_RESIDENCY		0x000003fc
+#define MSR_CORE_C6_RESIDENCY		0x000003fd
+#define MSR_CORE_C7_RESIDENCY		0x000003fe
+#define MSR_KNL_CORE_C6_RESIDENCY	0x000003ff
+#define MSR_PKG_C2_RESIDENCY		0x0000060d
+#define MSR_PKG_C8_RESIDENCY		0x00000630
+#define MSR_PKG_C9_RESIDENCY		0x00000631
+#define MSR_PKG_C10_RESIDENCY		0x00000632
+
+/* Interrupt Response Limit */
+#define MSR_PKGC3_IRTL			0x0000060a
+#define MSR_PKGC6_IRTL			0x0000060b
+#define MSR_PKGC7_IRTL			0x0000060c
+#define MSR_PKGC8_IRTL			0x00000633
+#define MSR_PKGC9_IRTL			0x00000634
+#define MSR_PKGC10_IRTL			0x00000635
+
+/* Run Time Average Power Limiting (RAPL) Interface */
+
+#define MSR_RAPL_POWER_UNIT		0x00000606
+
+#define MSR_PKG_POWER_LIMIT		0x00000610
+#define MSR_PKG_ENERGY_STATUS		0x00000611
+#define MSR_PKG_PERF_STATUS		0x00000613
+#define MSR_PKG_POWER_INFO		0x00000614
+
+#define MSR_DRAM_POWER_LIMIT		0x00000618
+#define MSR_DRAM_ENERGY_STATUS		0x00000619
+#define MSR_DRAM_PERF_STATUS		0x0000061b
+#define MSR_DRAM_POWER_INFO		0x0000061c
+
+#define MSR_PP0_POWER_LIMIT		0x00000638
+#define MSR_PP0_ENERGY_STATUS		0x00000639
+#define MSR_PP0_POLICY			0x0000063a
+#define MSR_PP0_PERF_STATUS		0x0000063b
+
+#define MSR_PP1_POWER_LIMIT		0x00000640
+#define MSR_PP1_ENERGY_STATUS		0x00000641
+#define MSR_PP1_POLICY			0x00000642
+
+/* Config TDP MSRs */
+#define MSR_CONFIG_TDP_NOMINAL		0x00000648
+#define MSR_CONFIG_TDP_LEVEL_1		0x00000649
+#define MSR_CONFIG_TDP_LEVEL_2		0x0000064A
+#define MSR_CONFIG_TDP_CONTROL		0x0000064B
+#define MSR_TURBO_ACTIVATION_RATIO	0x0000064C
+
+#define MSR_PLATFORM_ENERGY_STATUS	0x0000064D
+
+#define MSR_PKG_WEIGHTED_CORE_C0_RES	0x00000658
+#define MSR_PKG_ANY_CORE_C0_RES		0x00000659
+#define MSR_PKG_ANY_GFXE_C0_RES		0x0000065A
+#define MSR_PKG_BOTH_CORE_GFXE_C0_RES	0x0000065B
+
+#define MSR_CORE_C1_RES			0x00000660
+#define MSR_MODULE_C6_RES_MS		0x00000664
+
+#define MSR_CC6_DEMOTION_POLICY_CONFIG	0x00000668
+#define MSR_MC6_DEMOTION_POLICY_CONFIG	0x00000669
+
+#define MSR_ATOM_CORE_RATIOS		0x0000066a
+#define MSR_ATOM_CORE_VIDS		0x0000066b
+#define MSR_ATOM_CORE_TURBO_RATIOS	0x0000066c
+#define MSR_ATOM_CORE_TURBO_VIDS	0x0000066d
+
+
+#define MSR_CORE_PERF_LIMIT_REASONS	0x00000690
+#define MSR_GFX_PERF_LIMIT_REASONS	0x000006B0
+#define MSR_RING_PERF_LIMIT_REASONS	0x000006B1
+
+/* Hardware P state interface */
+#define MSR_PPERF			0x0000064e
+#define MSR_PERF_LIMIT_REASONS		0x0000064f
+#define MSR_PM_ENABLE			0x00000770
+#define MSR_HWP_CAPABILITIES		0x00000771
+#define MSR_HWP_REQUEST_PKG		0x00000772
+#define MSR_HWP_INTERRUPT		0x00000773
+#define MSR_HWP_REQUEST			0x00000774
+#define MSR_HWP_STATUS			0x00000777
+
+/* CPUID.6.EAX */
+#define HWP_BASE_BIT			(1<<7)
+#define HWP_NOTIFICATIONS_BIT		(1<<8)
+#define HWP_ACTIVITY_WINDOW_BIT		(1<<9)
+#define HWP_ENERGY_PERF_PREFERENCE_BIT	(1<<10)
+#define HWP_PACKAGE_LEVEL_REQUEST_BIT	(1<<11)
+
+/* IA32_HWP_CAPABILITIES */
+#define HWP_HIGHEST_PERF(x)		(((x) >> 0) & 0xff)
+#define HWP_GUARANTEED_PERF(x)		(((x) >> 8) & 0xff)
+#define HWP_MOSTEFFICIENT_PERF(x)	(((x) >> 16) & 0xff)
+#define HWP_LOWEST_PERF(x)		(((x) >> 24) & 0xff)
+
+/* IA32_HWP_REQUEST */
+#define HWP_MIN_PERF(x)			(x & 0xff)
+#define HWP_MAX_PERF(x)			((x & 0xff) << 8)
+#define HWP_DESIRED_PERF(x)		((x & 0xff) << 16)
+#define HWP_ENERGY_PERF_PREFERENCE(x)	(((unsigned long long) x & 0xff) << 24)
+#define HWP_EPP_PERFORMANCE		0x00
+#define HWP_EPP_BALANCE_PERFORMANCE	0x80
+#define HWP_EPP_BALANCE_POWERSAVE	0xC0
+#define HWP_EPP_POWERSAVE		0xFF
+#define HWP_ACTIVITY_WINDOW(x)		((unsigned long long)(x & 0xff3) << 32)
+#define HWP_PACKAGE_CONTROL(x)		((unsigned long long)(x & 0x1) << 42)
+
+/* IA32_HWP_STATUS */
+#define HWP_GUARANTEED_CHANGE(x)	(x & 0x1)
+#define HWP_EXCURSION_TO_MINIMUM(x)	(x & 0x4)
+
+/* IA32_HWP_INTERRUPT */
+#define HWP_CHANGE_TO_GUARANTEED_INT(x)	(x & 0x1)
+#define HWP_EXCURSION_TO_MINIMUM_INT(x)	(x & 0x2)
+
+#define MSR_AMD64_MC0_MASK		0xc0010044
+
+#define MSR_IA32_MCx_CTL(x)		(MSR_IA32_MC0_CTL + 4*(x))
+#define MSR_IA32_MCx_STATUS(x)		(MSR_IA32_MC0_STATUS + 4*(x))
+#define MSR_IA32_MCx_ADDR(x)		(MSR_IA32_MC0_ADDR + 4*(x))
+#define MSR_IA32_MCx_MISC(x)		(MSR_IA32_MC0_MISC + 4*(x))
+
+#define MSR_AMD64_MCx_MASK(x)		(MSR_AMD64_MC0_MASK + (x))
+
+/* These are consecutive and not in the normal 4er MCE bank block */
+#define MSR_IA32_MC0_CTL2		0x00000280
+#define MSR_IA32_MCx_CTL2(x)		(MSR_IA32_MC0_CTL2 + (x))
+
+#define MSR_P6_PERFCTR0			0x000000c1
+#define MSR_P6_PERFCTR1			0x000000c2
+#define MSR_P6_EVNTSEL0			0x00000186
+#define MSR_P6_EVNTSEL1			0x00000187
+
+#define MSR_KNC_PERFCTR0               0x00000020
+#define MSR_KNC_PERFCTR1               0x00000021
+#define MSR_KNC_EVNTSEL0               0x00000028
+#define MSR_KNC_EVNTSEL1               0x00000029
+
+/* Alternative perfctr range with full access. */
+#define MSR_IA32_PMC0			0x000004c1
+
+/* AMD64 MSRs. Not complete. See the architecture manual for a more
+   complete list. */
+
+#define MSR_AMD64_PATCH_LEVEL		0x0000008b
+#define MSR_AMD64_TSC_RATIO		0xc0000104
+#define MSR_AMD64_NB_CFG		0xc001001f
+#define MSR_AMD64_PATCH_LOADER		0xc0010020
+#define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140
+#define MSR_AMD64_OSVW_STATUS		0xc0010141
+#define MSR_AMD64_LS_CFG		0xc0011020
+#define MSR_AMD64_DC_CFG		0xc0011022
+#define MSR_AMD64_BU_CFG2		0xc001102a
+#define MSR_AMD64_IBSFETCHCTL		0xc0011030
+#define MSR_AMD64_IBSFETCHLINAD		0xc0011031
+#define MSR_AMD64_IBSFETCHPHYSAD	0xc0011032
+#define MSR_AMD64_IBSFETCH_REG_COUNT	3
+#define MSR_AMD64_IBSFETCH_REG_MASK	((1UL<<MSR_AMD64_IBSFETCH_REG_COUNT)-1)
+#define MSR_AMD64_IBSOPCTL		0xc0011033
+#define MSR_AMD64_IBSOPRIP		0xc0011034
+#define MSR_AMD64_IBSOPDATA		0xc0011035
+#define MSR_AMD64_IBSOPDATA2		0xc0011036
+#define MSR_AMD64_IBSOPDATA3		0xc0011037
+#define MSR_AMD64_IBSDCLINAD		0xc0011038
+#define MSR_AMD64_IBSDCPHYSAD		0xc0011039
+#define MSR_AMD64_IBSOP_REG_COUNT	7
+#define MSR_AMD64_IBSOP_REG_MASK	((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
+#define MSR_AMD64_IBSCTL		0xc001103a
+#define MSR_AMD64_IBSBRTARGET		0xc001103b
+#define MSR_AMD64_IBSOPDATA4		0xc001103d
+#define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
+#define MSR_AMD64_SEV			0xc0010131
+#define MSR_AMD64_SEV_ENABLED_BIT	0
+#define MSR_AMD64_SEV_ENABLED		BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
+
+/* Fam 17h MSRs */
+#define MSR_F17H_IRPERF			0xc00000e9
+
+/* Fam 16h MSRs */
+#define MSR_F16H_L2I_PERF_CTL		0xc0010230
+#define MSR_F16H_L2I_PERF_CTR		0xc0010231
+#define MSR_F16H_DR1_ADDR_MASK		0xc0011019
+#define MSR_F16H_DR2_ADDR_MASK		0xc001101a
+#define MSR_F16H_DR3_ADDR_MASK		0xc001101b
+#define MSR_F16H_DR0_ADDR_MASK		0xc0011027
+
+/* Fam 15h MSRs */
+#define MSR_F15H_PERF_CTL		0xc0010200
+#define MSR_F15H_PERF_CTR		0xc0010201
+#define MSR_F15H_NB_PERF_CTL		0xc0010240
+#define MSR_F15H_NB_PERF_CTR		0xc0010241
+#define MSR_F15H_PTSC			0xc0010280
+#define MSR_F15H_IC_CFG			0xc0011021
+
+/* Fam 10h MSRs */
+#define MSR_FAM10H_MMIO_CONF_BASE	0xc0010058
+#define FAM10H_MMIO_CONF_ENABLE		(1<<0)
+#define FAM10H_MMIO_CONF_BUSRANGE_MASK	0xf
+#define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
+#define FAM10H_MMIO_CONF_BASE_MASK	0xfffffffULL
+#define FAM10H_MMIO_CONF_BASE_SHIFT	20
+#define MSR_FAM10H_NODE_ID		0xc001100c
+#define MSR_F10H_DECFG			0xc0011029
+#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT	1
+#define MSR_F10H_DECFG_LFENCE_SERIALIZE		BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT)
+
+/* K8 MSRs */
+#define MSR_K8_TOP_MEM1			0xc001001a
+#define MSR_K8_TOP_MEM2			0xc001001d
+#define MSR_K8_SYSCFG			0xc0010010
+#define MSR_K8_SYSCFG_MEM_ENCRYPT_BIT	23
+#define MSR_K8_SYSCFG_MEM_ENCRYPT	BIT_ULL(MSR_K8_SYSCFG_MEM_ENCRYPT_BIT)
+#define MSR_K8_INT_PENDING_MSG		0xc0010055
+/* C1E active bits in int pending message */
+#define K8_INTP_C1E_ACTIVE_MASK		0x18000000
+#define MSR_K8_TSEG_ADDR		0xc0010112
+#define MSR_K8_TSEG_MASK		0xc0010113
+#define K8_MTRRFIXRANGE_DRAM_ENABLE	0x00040000 /* MtrrFixDramEn bit    */
+#define K8_MTRRFIXRANGE_DRAM_MODIFY	0x00080000 /* MtrrFixDramModEn bit */
+#define K8_MTRR_RDMEM_WRMEM_MASK	0x18181818 /* Mask: RdMem|WrMem    */
+
+/* K7 MSRs */
+#define MSR_K7_EVNTSEL0			0xc0010000
+#define MSR_K7_PERFCTR0			0xc0010004
+#define MSR_K7_EVNTSEL1			0xc0010001
+#define MSR_K7_PERFCTR1			0xc0010005
+#define MSR_K7_EVNTSEL2			0xc0010002
+#define MSR_K7_PERFCTR2			0xc0010006
+#define MSR_K7_EVNTSEL3			0xc0010003
+#define MSR_K7_PERFCTR3			0xc0010007
+#define MSR_K7_CLK_CTL			0xc001001b
+#define MSR_K7_HWCR			0xc0010015
+#define MSR_K7_HWCR_SMMLOCK_BIT		0
+#define MSR_K7_HWCR_SMMLOCK		BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
+#define MSR_K7_FID_VID_CTL		0xc0010041
+#define MSR_K7_FID_VID_STATUS		0xc0010042
+
+/* K6 MSRs */
+#define MSR_K6_WHCR			0xc0000082
+#define MSR_K6_UWCCR			0xc0000085
+#define MSR_K6_EPMR			0xc0000086
+#define MSR_K6_PSOR			0xc0000087
+#define MSR_K6_PFIR			0xc0000088
+
+/* Centaur-Hauls/IDT defined MSRs. */
+#define MSR_IDT_FCR1			0x00000107
+#define MSR_IDT_FCR2			0x00000108
+#define MSR_IDT_FCR3			0x00000109
+#define MSR_IDT_FCR4			0x0000010a
+
+#define MSR_IDT_MCR0			0x00000110
+#define MSR_IDT_MCR1			0x00000111
+#define MSR_IDT_MCR2			0x00000112
+#define MSR_IDT_MCR3			0x00000113
+#define MSR_IDT_MCR4			0x00000114
+#define MSR_IDT_MCR5			0x00000115
+#define MSR_IDT_MCR6			0x00000116
+#define MSR_IDT_MCR7			0x00000117
+#define MSR_IDT_MCR_CTRL		0x00000120
+
+/* VIA Cyrix defined MSRs*/
+#define MSR_VIA_FCR			0x00001107
+#define MSR_VIA_LONGHAUL		0x0000110a
+#define MSR_VIA_RNG			0x0000110b
+#define MSR_VIA_BCR2			0x00001147
+
+/* Transmeta defined MSRs */
+#define MSR_TMTA_LONGRUN_CTRL		0x80868010
+#define MSR_TMTA_LONGRUN_FLAGS		0x80868011
+#define MSR_TMTA_LRTI_READOUT		0x80868018
+#define MSR_TMTA_LRTI_VOLT_MHZ		0x8086801a
+
+/* Intel defined MSRs. */
+#define MSR_IA32_P5_MC_ADDR		0x00000000
+#define MSR_IA32_P5_MC_TYPE		0x00000001
+#define MSR_IA32_TSC			0x00000010
+#define MSR_IA32_PLATFORM_ID		0x00000017
+#define MSR_IA32_EBL_CR_POWERON		0x0000002a
+#define MSR_EBC_FREQUENCY_ID		0x0000002c
+#define MSR_SMI_COUNT			0x00000034
+#define MSR_IA32_FEATURE_CONTROL        0x0000003a
+#define MSR_IA32_TSC_ADJUST             0x0000003b
+#define MSR_IA32_BNDCFGS		0x00000d90
+
+#define MSR_IA32_BNDCFGS_RSVD		0x00000ffc
+
+#define MSR_IA32_XSS			0x00000da0
+
+#define FEATURE_CONTROL_LOCKED				(1<<0)
+#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX	(1<<1)
+#define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX	(1<<2)
+#define FEATURE_CONTROL_LMCE				(1<<20)
+
+#define MSR_IA32_APICBASE		0x0000001b
+#define MSR_IA32_APICBASE_BSP		(1<<8)
+#define MSR_IA32_APICBASE_ENABLE	(1<<11)
+#define MSR_IA32_APICBASE_BASE		(0xfffff<<12)
+
+#define MSR_IA32_TSCDEADLINE		0x000006e0
+
+#define MSR_IA32_UCODE_WRITE		0x00000079
+#define MSR_IA32_UCODE_REV		0x0000008b
+
+#define MSR_IA32_SMM_MONITOR_CTL	0x0000009b
+#define MSR_IA32_SMBASE			0x0000009e
+
+#define MSR_IA32_PERF_STATUS		0x00000198
+#define MSR_IA32_PERF_CTL		0x00000199
+#define INTEL_PERF_CTL_MASK		0xffff
+#define MSR_AMD_PSTATE_DEF_BASE		0xc0010064
+#define MSR_AMD_PERF_STATUS		0xc0010063
+#define MSR_AMD_PERF_CTL		0xc0010062
+
+#define MSR_IA32_MPERF			0x000000e7
+#define MSR_IA32_APERF			0x000000e8
+
+#define MSR_IA32_THERM_CONTROL		0x0000019a
+#define MSR_IA32_THERM_INTERRUPT	0x0000019b
+
+#define THERM_INT_HIGH_ENABLE		(1 << 0)
+#define THERM_INT_LOW_ENABLE		(1 << 1)
+#define THERM_INT_PLN_ENABLE		(1 << 24)
+
+#define MSR_IA32_THERM_STATUS		0x0000019c
+
+#define THERM_STATUS_PROCHOT		(1 << 0)
+#define THERM_STATUS_POWER_LIMIT	(1 << 10)
+
+#define MSR_THERM2_CTL			0x0000019d
+
+#define MSR_THERM2_CTL_TM_SELECT	(1ULL << 16)
+
+#define MSR_IA32_MISC_ENABLE		0x000001a0
+
+#define MSR_IA32_TEMPERATURE_TARGET	0x000001a2
+
+#define MSR_MISC_FEATURE_CONTROL	0x000001a4
+#define MSR_MISC_PWR_MGMT		0x000001aa
+
+#define MSR_IA32_ENERGY_PERF_BIAS	0x000001b0
+#define ENERGY_PERF_BIAS_PERFORMANCE		0
+#define ENERGY_PERF_BIAS_BALANCE_PERFORMANCE	4
+#define ENERGY_PERF_BIAS_NORMAL			6
+#define ENERGY_PERF_BIAS_BALANCE_POWERSAVE	8
+#define ENERGY_PERF_BIAS_POWERSAVE		15
+
+#define MSR_IA32_PACKAGE_THERM_STATUS		0x000001b1
+
+#define PACKAGE_THERM_STATUS_PROCHOT		(1 << 0)
+#define PACKAGE_THERM_STATUS_POWER_LIMIT	(1 << 10)
+
+#define MSR_IA32_PACKAGE_THERM_INTERRUPT	0x000001b2
+
+#define PACKAGE_THERM_INT_HIGH_ENABLE		(1 << 0)
+#define PACKAGE_THERM_INT_LOW_ENABLE		(1 << 1)
+#define PACKAGE_THERM_INT_PLN_ENABLE		(1 << 24)
+
+/* Thermal Thresholds Support */
+#define THERM_INT_THRESHOLD0_ENABLE    (1 << 15)
+#define THERM_SHIFT_THRESHOLD0        8
+#define THERM_MASK_THRESHOLD0          (0x7f << THERM_SHIFT_THRESHOLD0)
+#define THERM_INT_THRESHOLD1_ENABLE    (1 << 23)
+#define THERM_SHIFT_THRESHOLD1        16
+#define THERM_MASK_THRESHOLD1          (0x7f << THERM_SHIFT_THRESHOLD1)
+#define THERM_STATUS_THRESHOLD0        (1 << 6)
+#define THERM_LOG_THRESHOLD0           (1 << 7)
+#define THERM_STATUS_THRESHOLD1        (1 << 8)
+#define THERM_LOG_THRESHOLD1           (1 << 9)
+
+/* MISC_ENABLE bits: architectural */
+#define MSR_IA32_MISC_ENABLE_FAST_STRING_BIT		0
+#define MSR_IA32_MISC_ENABLE_FAST_STRING		(1ULL << MSR_IA32_MISC_ENABLE_FAST_STRING_BIT)
+#define MSR_IA32_MISC_ENABLE_TCC_BIT			1
+#define MSR_IA32_MISC_ENABLE_TCC			(1ULL << MSR_IA32_MISC_ENABLE_TCC_BIT)
+#define MSR_IA32_MISC_ENABLE_EMON_BIT			7
+#define MSR_IA32_MISC_ENABLE_EMON			(1ULL << MSR_IA32_MISC_ENABLE_EMON_BIT)
+#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT		11
+#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL		(1ULL << MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT)
+#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT		12
+#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL		(1ULL << MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT)
+#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT	16
+#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP		(1ULL << MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT)
+#define MSR_IA32_MISC_ENABLE_MWAIT_BIT			18
+#define MSR_IA32_MISC_ENABLE_MWAIT			(1ULL << MSR_IA32_MISC_ENABLE_MWAIT_BIT)
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT		22
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID		(1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT)
+#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT		23
+#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT		34
+#define MSR_IA32_MISC_ENABLE_XD_DISABLE			(1ULL << MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT)
+
+/* MISC_ENABLE bits: model-specific, meaning may vary from core to core */
+#define MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT		2
+#define MSR_IA32_MISC_ENABLE_X87_COMPAT			(1ULL << MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT)
+#define MSR_IA32_MISC_ENABLE_TM1_BIT			3
+#define MSR_IA32_MISC_ENABLE_TM1			(1ULL << MSR_IA32_MISC_ENABLE_TM1_BIT)
+#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT	4
+#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT	6
+#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT		8
+#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK		(1ULL << MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT)
+#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT	9
+#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_FERR_BIT			10
+#define MSR_IA32_MISC_ENABLE_FERR			(1ULL << MSR_IA32_MISC_ENABLE_FERR_BIT)
+#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT		10
+#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX		(1ULL << MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT)
+#define MSR_IA32_MISC_ENABLE_TM2_BIT			13
+#define MSR_IA32_MISC_ENABLE_TM2			(1ULL << MSR_IA32_MISC_ENABLE_TM2_BIT)
+#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT	19
+#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT		20
+#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK		(1ULL << MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT)
+#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT		24
+#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT		(1ULL << MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT)
+#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT	37
+#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT		38
+#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT	39
+#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT)
+
+/* MISC_FEATURES_ENABLES non-architectural features */
+#define MSR_MISC_FEATURES_ENABLES	0x00000140
+
+#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT	0
+#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT		BIT_ULL(MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT)
+#define MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT	1
+
+#define MSR_IA32_TSC_DEADLINE		0x000006E0
+
+/* P4/Xeon+ specific */
+#define MSR_IA32_MCG_EAX		0x00000180
+#define MSR_IA32_MCG_EBX		0x00000181
+#define MSR_IA32_MCG_ECX		0x00000182
+#define MSR_IA32_MCG_EDX		0x00000183
+#define MSR_IA32_MCG_ESI		0x00000184
+#define MSR_IA32_MCG_EDI		0x00000185
+#define MSR_IA32_MCG_EBP		0x00000186
+#define MSR_IA32_MCG_ESP		0x00000187
+#define MSR_IA32_MCG_EFLAGS		0x00000188
+#define MSR_IA32_MCG_EIP		0x00000189
+#define MSR_IA32_MCG_RESERVED		0x0000018a
+
+/* Pentium IV performance counter MSRs */
+#define MSR_P4_BPU_PERFCTR0		0x00000300
+#define MSR_P4_BPU_PERFCTR1		0x00000301
+#define MSR_P4_BPU_PERFCTR2		0x00000302
+#define MSR_P4_BPU_PERFCTR3		0x00000303
+#define MSR_P4_MS_PERFCTR0		0x00000304
+#define MSR_P4_MS_PERFCTR1		0x00000305
+#define MSR_P4_MS_PERFCTR2		0x00000306
+#define MSR_P4_MS_PERFCTR3		0x00000307
+#define MSR_P4_FLAME_PERFCTR0		0x00000308
+#define MSR_P4_FLAME_PERFCTR1		0x00000309
+#define MSR_P4_FLAME_PERFCTR2		0x0000030a
+#define MSR_P4_FLAME_PERFCTR3		0x0000030b
+#define MSR_P4_IQ_PERFCTR0		0x0000030c
+#define MSR_P4_IQ_PERFCTR1		0x0000030d
+#define MSR_P4_IQ_PERFCTR2		0x0000030e
+#define MSR_P4_IQ_PERFCTR3		0x0000030f
+#define MSR_P4_IQ_PERFCTR4		0x00000310
+#define MSR_P4_IQ_PERFCTR5		0x00000311
+#define MSR_P4_BPU_CCCR0		0x00000360
+#define MSR_P4_BPU_CCCR1		0x00000361
+#define MSR_P4_BPU_CCCR2		0x00000362
+#define MSR_P4_BPU_CCCR3		0x00000363
+#define MSR_P4_MS_CCCR0			0x00000364
+#define MSR_P4_MS_CCCR1			0x00000365
+#define MSR_P4_MS_CCCR2			0x00000366
+#define MSR_P4_MS_CCCR3			0x00000367
+#define MSR_P4_FLAME_CCCR0		0x00000368
+#define MSR_P4_FLAME_CCCR1		0x00000369
+#define MSR_P4_FLAME_CCCR2		0x0000036a
+#define MSR_P4_FLAME_CCCR3		0x0000036b
+#define MSR_P4_IQ_CCCR0			0x0000036c
+#define MSR_P4_IQ_CCCR1			0x0000036d
+#define MSR_P4_IQ_CCCR2			0x0000036e
+#define MSR_P4_IQ_CCCR3			0x0000036f
+#define MSR_P4_IQ_CCCR4			0x00000370
+#define MSR_P4_IQ_CCCR5			0x00000371
+#define MSR_P4_ALF_ESCR0		0x000003ca
+#define MSR_P4_ALF_ESCR1		0x000003cb
+#define MSR_P4_BPU_ESCR0		0x000003b2
+#define MSR_P4_BPU_ESCR1		0x000003b3
+#define MSR_P4_BSU_ESCR0		0x000003a0
+#define MSR_P4_BSU_ESCR1		0x000003a1
+#define MSR_P4_CRU_ESCR0		0x000003b8
+#define MSR_P4_CRU_ESCR1		0x000003b9
+#define MSR_P4_CRU_ESCR2		0x000003cc
+#define MSR_P4_CRU_ESCR3		0x000003cd
+#define MSR_P4_CRU_ESCR4		0x000003e0
+#define MSR_P4_CRU_ESCR5		0x000003e1
+#define MSR_P4_DAC_ESCR0		0x000003a8
+#define MSR_P4_DAC_ESCR1		0x000003a9
+#define MSR_P4_FIRM_ESCR0		0x000003a4
+#define MSR_P4_FIRM_ESCR1		0x000003a5
+#define MSR_P4_FLAME_ESCR0		0x000003a6
+#define MSR_P4_FLAME_ESCR1		0x000003a7
+#define MSR_P4_FSB_ESCR0		0x000003a2
+#define MSR_P4_FSB_ESCR1		0x000003a3
+#define MSR_P4_IQ_ESCR0			0x000003ba
+#define MSR_P4_IQ_ESCR1			0x000003bb
+#define MSR_P4_IS_ESCR0			0x000003b4
+#define MSR_P4_IS_ESCR1			0x000003b5
+#define MSR_P4_ITLB_ESCR0		0x000003b6
+#define MSR_P4_ITLB_ESCR1		0x000003b7
+#define MSR_P4_IX_ESCR0			0x000003c8
+#define MSR_P4_IX_ESCR1			0x000003c9
+#define MSR_P4_MOB_ESCR0		0x000003aa
+#define MSR_P4_MOB_ESCR1		0x000003ab
+#define MSR_P4_MS_ESCR0			0x000003c0
+#define MSR_P4_MS_ESCR1			0x000003c1
+#define MSR_P4_PMH_ESCR0		0x000003ac
+#define MSR_P4_PMH_ESCR1		0x000003ad
+#define MSR_P4_RAT_ESCR0		0x000003bc
+#define MSR_P4_RAT_ESCR1		0x000003bd
+#define MSR_P4_SAAT_ESCR0		0x000003ae
+#define MSR_P4_SAAT_ESCR1		0x000003af
+#define MSR_P4_SSU_ESCR0		0x000003be
+#define MSR_P4_SSU_ESCR1		0x000003bf /* guess: not in manual */
+
+#define MSR_P4_TBPU_ESCR0		0x000003c2
+#define MSR_P4_TBPU_ESCR1		0x000003c3
+#define MSR_P4_TC_ESCR0			0x000003c4
+#define MSR_P4_TC_ESCR1			0x000003c5
+#define MSR_P4_U2L_ESCR0		0x000003b0
+#define MSR_P4_U2L_ESCR1		0x000003b1
+
+#define MSR_P4_PEBS_MATRIX_VERT		0x000003f2
+
+/* Intel Core-based CPU performance counters */
+#define MSR_CORE_PERF_FIXED_CTR0	0x00000309
+#define MSR_CORE_PERF_FIXED_CTR1	0x0000030a
+#define MSR_CORE_PERF_FIXED_CTR2	0x0000030b
+#define MSR_CORE_PERF_FIXED_CTR_CTRL	0x0000038d
+#define MSR_CORE_PERF_GLOBAL_STATUS	0x0000038e
+#define MSR_CORE_PERF_GLOBAL_CTRL	0x0000038f
+#define MSR_CORE_PERF_GLOBAL_OVF_CTRL	0x00000390
+
+/* Geode defined MSRs */
+#define MSR_GEODE_BUSCONT_CONF0		0x00001900
+
+/* Intel VT MSRs */
+#define MSR_IA32_VMX_BASIC              0x00000480
+#define MSR_IA32_VMX_PINBASED_CTLS      0x00000481
+#define MSR_IA32_VMX_PROCBASED_CTLS     0x00000482
+#define MSR_IA32_VMX_EXIT_CTLS          0x00000483
+#define MSR_IA32_VMX_ENTRY_CTLS         0x00000484
+#define MSR_IA32_VMX_MISC               0x00000485
+#define MSR_IA32_VMX_CR0_FIXED0         0x00000486
+#define MSR_IA32_VMX_CR0_FIXED1         0x00000487
+#define MSR_IA32_VMX_CR4_FIXED0         0x00000488
+#define MSR_IA32_VMX_CR4_FIXED1         0x00000489
+#define MSR_IA32_VMX_VMCS_ENUM          0x0000048a
+#define MSR_IA32_VMX_PROCBASED_CTLS2    0x0000048b
+#define MSR_IA32_VMX_EPT_VPID_CAP       0x0000048c
+#define MSR_IA32_VMX_TRUE_PINBASED_CTLS  0x0000048d
+#define MSR_IA32_VMX_TRUE_PROCBASED_CTLS 0x0000048e
+#define MSR_IA32_VMX_TRUE_EXIT_CTLS      0x0000048f
+#define MSR_IA32_VMX_TRUE_ENTRY_CTLS     0x00000490
+#define MSR_IA32_VMX_VMFUNC             0x00000491
+
+/* VMX_BASIC bits and bitmasks */
+#define VMX_BASIC_VMCS_SIZE_SHIFT	32
+#define VMX_BASIC_TRUE_CTLS		(1ULL << 55)
+#define VMX_BASIC_64		0x0001000000000000LLU
+#define VMX_BASIC_MEM_TYPE_SHIFT	50
+#define VMX_BASIC_MEM_TYPE_MASK	0x003c000000000000LLU
+#define VMX_BASIC_MEM_TYPE_WB	6LLU
+#define VMX_BASIC_INOUT		0x0040000000000000LLU
+
+/* MSR_IA32_VMX_MISC bits */
+#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
+#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE   0x1F
+/* AMD-V MSRs */
+
+#define MSR_VM_CR                       0xc0010114
+#define MSR_VM_IGNNE                    0xc0010115
+#define MSR_VM_HSAVE_PA                 0xc0010117
+
+#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
new file mode 100644
index 000000000000..12ebd836f7ef
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -0,0 +1,552 @@
+/*
+ * tools/testing/selftests/kvm/include/x86_64/vmx.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ */
+
+#ifndef SELFTEST_KVM_VMX_H
+#define SELFTEST_KVM_VMX_H
+
+#include <stdint.h>
+#include "processor.h"
+
+#define CPUID_VMX_BIT				5
+
+#define CPUID_VMX				(1 << 5)
+
+/*
+ * Definitions of Primary Processor-Based VM-Execution Controls.
+ */
+#define CPU_BASED_VIRTUAL_INTR_PENDING		0x00000004
+#define CPU_BASED_USE_TSC_OFFSETING		0x00000008
+#define CPU_BASED_HLT_EXITING			0x00000080
+#define CPU_BASED_INVLPG_EXITING		0x00000200
+#define CPU_BASED_MWAIT_EXITING			0x00000400
+#define CPU_BASED_RDPMC_EXITING			0x00000800
+#define CPU_BASED_RDTSC_EXITING			0x00001000
+#define CPU_BASED_CR3_LOAD_EXITING		0x00008000
+#define CPU_BASED_CR3_STORE_EXITING		0x00010000
+#define CPU_BASED_CR8_LOAD_EXITING		0x00080000
+#define CPU_BASED_CR8_STORE_EXITING		0x00100000
+#define CPU_BASED_TPR_SHADOW			0x00200000
+#define CPU_BASED_VIRTUAL_NMI_PENDING		0x00400000
+#define CPU_BASED_MOV_DR_EXITING		0x00800000
+#define CPU_BASED_UNCOND_IO_EXITING		0x01000000
+#define CPU_BASED_USE_IO_BITMAPS		0x02000000
+#define CPU_BASED_MONITOR_TRAP			0x08000000
+#define CPU_BASED_USE_MSR_BITMAPS		0x10000000
+#define CPU_BASED_MONITOR_EXITING		0x20000000
+#define CPU_BASED_PAUSE_EXITING			0x40000000
+#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS	0x80000000
+
+#define CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR	0x0401e172
+
+/*
+ * Definitions of Secondary Processor-Based VM-Execution Controls.
+ */
+#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
+#define SECONDARY_EXEC_ENABLE_EPT		0x00000002
+#define SECONDARY_EXEC_DESC			0x00000004
+#define SECONDARY_EXEC_RDTSCP			0x00000008
+#define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE	0x00000010
+#define SECONDARY_EXEC_ENABLE_VPID		0x00000020
+#define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
+#define SECONDARY_EXEC_UNRESTRICTED_GUEST	0x00000080
+#define SECONDARY_EXEC_APIC_REGISTER_VIRT	0x00000100
+#define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY	0x00000200
+#define SECONDARY_EXEC_PAUSE_LOOP_EXITING	0x00000400
+#define SECONDARY_EXEC_RDRAND_EXITING		0x00000800
+#define SECONDARY_EXEC_ENABLE_INVPCID		0x00001000
+#define SECONDARY_EXEC_ENABLE_VMFUNC		0x00002000
+#define SECONDARY_EXEC_SHADOW_VMCS		0x00004000
+#define SECONDARY_EXEC_RDSEED_EXITING		0x00010000
+#define SECONDARY_EXEC_ENABLE_PML		0x00020000
+#define SECONDARY_EPT_VE			0x00040000
+#define SECONDARY_ENABLE_XSAV_RESTORE		0x00100000
+#define SECONDARY_EXEC_TSC_SCALING		0x02000000
+
+#define PIN_BASED_EXT_INTR_MASK			0x00000001
+#define PIN_BASED_NMI_EXITING			0x00000008
+#define PIN_BASED_VIRTUAL_NMIS			0x00000020
+#define PIN_BASED_VMX_PREEMPTION_TIMER		0x00000040
+#define PIN_BASED_POSTED_INTR			0x00000080
+
+#define PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR	0x00000016
+
+#define VM_EXIT_SAVE_DEBUG_CONTROLS		0x00000004
+#define VM_EXIT_HOST_ADDR_SPACE_SIZE		0x00000200
+#define VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL	0x00001000
+#define VM_EXIT_ACK_INTR_ON_EXIT		0x00008000
+#define VM_EXIT_SAVE_IA32_PAT			0x00040000
+#define VM_EXIT_LOAD_IA32_PAT			0x00080000
+#define VM_EXIT_SAVE_IA32_EFER			0x00100000
+#define VM_EXIT_LOAD_IA32_EFER			0x00200000
+#define VM_EXIT_SAVE_VMX_PREEMPTION_TIMER	0x00400000
+
+#define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR	0x00036dff
+
+#define VM_ENTRY_LOAD_DEBUG_CONTROLS		0x00000004
+#define VM_ENTRY_IA32E_MODE			0x00000200
+#define VM_ENTRY_SMM				0x00000400
+#define VM_ENTRY_DEACT_DUAL_MONITOR		0x00000800
+#define VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL	0x00002000
+#define VM_ENTRY_LOAD_IA32_PAT			0x00004000
+#define VM_ENTRY_LOAD_IA32_EFER			0x00008000
+
+#define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR	0x000011ff
+
+#define VMX_MISC_PREEMPTION_TIMER_RATE_MASK	0x0000001f
+#define VMX_MISC_SAVE_EFER_LMA			0x00000020
+
+#define EXIT_REASON_FAILED_VMENTRY	0x80000000
+#define EXIT_REASON_EXCEPTION_NMI	0
+#define EXIT_REASON_EXTERNAL_INTERRUPT	1
+#define EXIT_REASON_TRIPLE_FAULT	2
+#define EXIT_REASON_PENDING_INTERRUPT	7
+#define EXIT_REASON_NMI_WINDOW		8
+#define EXIT_REASON_TASK_SWITCH		9
+#define EXIT_REASON_CPUID		10
+#define EXIT_REASON_HLT			12
+#define EXIT_REASON_INVD		13
+#define EXIT_REASON_INVLPG		14
+#define EXIT_REASON_RDPMC		15
+#define EXIT_REASON_RDTSC		16
+#define EXIT_REASON_VMCALL		18
+#define EXIT_REASON_VMCLEAR		19
+#define EXIT_REASON_VMLAUNCH		20
+#define EXIT_REASON_VMPTRLD		21
+#define EXIT_REASON_VMPTRST		22
+#define EXIT_REASON_VMREAD		23
+#define EXIT_REASON_VMRESUME		24
+#define EXIT_REASON_VMWRITE		25
+#define EXIT_REASON_VMOFF		26
+#define EXIT_REASON_VMON		27
+#define EXIT_REASON_CR_ACCESS		28
+#define EXIT_REASON_DR_ACCESS		29
+#define EXIT_REASON_IO_INSTRUCTION	30
+#define EXIT_REASON_MSR_READ		31
+#define EXIT_REASON_MSR_WRITE		32
+#define EXIT_REASON_INVALID_STATE	33
+#define EXIT_REASON_MWAIT_INSTRUCTION	36
+#define EXIT_REASON_MONITOR_INSTRUCTION 39
+#define EXIT_REASON_PAUSE_INSTRUCTION	40
+#define EXIT_REASON_MCE_DURING_VMENTRY	41
+#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
+#define EXIT_REASON_APIC_ACCESS		44
+#define EXIT_REASON_EOI_INDUCED		45
+#define EXIT_REASON_EPT_VIOLATION	48
+#define EXIT_REASON_EPT_MISCONFIG	49
+#define EXIT_REASON_INVEPT		50
+#define EXIT_REASON_RDTSCP		51
+#define EXIT_REASON_PREEMPTION_TIMER	52
+#define EXIT_REASON_INVVPID		53
+#define EXIT_REASON_WBINVD		54
+#define EXIT_REASON_XSETBV		55
+#define EXIT_REASON_APIC_WRITE		56
+#define EXIT_REASON_INVPCID		58
+#define EXIT_REASON_PML_FULL		62
+#define EXIT_REASON_XSAVES		63
+#define EXIT_REASON_XRSTORS		64
+#define LAST_EXIT_REASON		64
+
+enum vmcs_field {
+	VIRTUAL_PROCESSOR_ID		= 0x00000000,
+	POSTED_INTR_NV			= 0x00000002,
+	GUEST_ES_SELECTOR		= 0x00000800,
+	GUEST_CS_SELECTOR		= 0x00000802,
+	GUEST_SS_SELECTOR		= 0x00000804,
+	GUEST_DS_SELECTOR		= 0x00000806,
+	GUEST_FS_SELECTOR		= 0x00000808,
+	GUEST_GS_SELECTOR		= 0x0000080a,
+	GUEST_LDTR_SELECTOR		= 0x0000080c,
+	GUEST_TR_SELECTOR		= 0x0000080e,
+	GUEST_INTR_STATUS		= 0x00000810,
+	GUEST_PML_INDEX			= 0x00000812,
+	HOST_ES_SELECTOR		= 0x00000c00,
+	HOST_CS_SELECTOR		= 0x00000c02,
+	HOST_SS_SELECTOR		= 0x00000c04,
+	HOST_DS_SELECTOR		= 0x00000c06,
+	HOST_FS_SELECTOR		= 0x00000c08,
+	HOST_GS_SELECTOR		= 0x00000c0a,
+	HOST_TR_SELECTOR		= 0x00000c0c,
+	IO_BITMAP_A			= 0x00002000,
+	IO_BITMAP_A_HIGH		= 0x00002001,
+	IO_BITMAP_B			= 0x00002002,
+	IO_BITMAP_B_HIGH		= 0x00002003,
+	MSR_BITMAP			= 0x00002004,
+	MSR_BITMAP_HIGH			= 0x00002005,
+	VM_EXIT_MSR_STORE_ADDR		= 0x00002006,
+	VM_EXIT_MSR_STORE_ADDR_HIGH	= 0x00002007,
+	VM_EXIT_MSR_LOAD_ADDR		= 0x00002008,
+	VM_EXIT_MSR_LOAD_ADDR_HIGH	= 0x00002009,
+	VM_ENTRY_MSR_LOAD_ADDR		= 0x0000200a,
+	VM_ENTRY_MSR_LOAD_ADDR_HIGH	= 0x0000200b,
+	PML_ADDRESS			= 0x0000200e,
+	PML_ADDRESS_HIGH		= 0x0000200f,
+	TSC_OFFSET			= 0x00002010,
+	TSC_OFFSET_HIGH			= 0x00002011,
+	VIRTUAL_APIC_PAGE_ADDR		= 0x00002012,
+	VIRTUAL_APIC_PAGE_ADDR_HIGH	= 0x00002013,
+	APIC_ACCESS_ADDR		= 0x00002014,
+	APIC_ACCESS_ADDR_HIGH		= 0x00002015,
+	POSTED_INTR_DESC_ADDR		= 0x00002016,
+	POSTED_INTR_DESC_ADDR_HIGH	= 0x00002017,
+	EPT_POINTER			= 0x0000201a,
+	EPT_POINTER_HIGH		= 0x0000201b,
+	EOI_EXIT_BITMAP0		= 0x0000201c,
+	EOI_EXIT_BITMAP0_HIGH		= 0x0000201d,
+	EOI_EXIT_BITMAP1		= 0x0000201e,
+	EOI_EXIT_BITMAP1_HIGH		= 0x0000201f,
+	EOI_EXIT_BITMAP2		= 0x00002020,
+	EOI_EXIT_BITMAP2_HIGH		= 0x00002021,
+	EOI_EXIT_BITMAP3		= 0x00002022,
+	EOI_EXIT_BITMAP3_HIGH		= 0x00002023,
+	VMREAD_BITMAP			= 0x00002026,
+	VMREAD_BITMAP_HIGH		= 0x00002027,
+	VMWRITE_BITMAP			= 0x00002028,
+	VMWRITE_BITMAP_HIGH		= 0x00002029,
+	XSS_EXIT_BITMAP			= 0x0000202C,
+	XSS_EXIT_BITMAP_HIGH		= 0x0000202D,
+	TSC_MULTIPLIER			= 0x00002032,
+	TSC_MULTIPLIER_HIGH		= 0x00002033,
+	GUEST_PHYSICAL_ADDRESS		= 0x00002400,
+	GUEST_PHYSICAL_ADDRESS_HIGH	= 0x00002401,
+	VMCS_LINK_POINTER		= 0x00002800,
+	VMCS_LINK_POINTER_HIGH		= 0x00002801,
+	GUEST_IA32_DEBUGCTL		= 0x00002802,
+	GUEST_IA32_DEBUGCTL_HIGH	= 0x00002803,
+	GUEST_IA32_PAT			= 0x00002804,
+	GUEST_IA32_PAT_HIGH		= 0x00002805,
+	GUEST_IA32_EFER			= 0x00002806,
+	GUEST_IA32_EFER_HIGH		= 0x00002807,
+	GUEST_IA32_PERF_GLOBAL_CTRL	= 0x00002808,
+	GUEST_IA32_PERF_GLOBAL_CTRL_HIGH= 0x00002809,
+	GUEST_PDPTR0			= 0x0000280a,
+	GUEST_PDPTR0_HIGH		= 0x0000280b,
+	GUEST_PDPTR1			= 0x0000280c,
+	GUEST_PDPTR1_HIGH		= 0x0000280d,
+	GUEST_PDPTR2			= 0x0000280e,
+	GUEST_PDPTR2_HIGH		= 0x0000280f,
+	GUEST_PDPTR3			= 0x00002810,
+	GUEST_PDPTR3_HIGH		= 0x00002811,
+	GUEST_BNDCFGS			= 0x00002812,
+	GUEST_BNDCFGS_HIGH		= 0x00002813,
+	HOST_IA32_PAT			= 0x00002c00,
+	HOST_IA32_PAT_HIGH		= 0x00002c01,
+	HOST_IA32_EFER			= 0x00002c02,
+	HOST_IA32_EFER_HIGH		= 0x00002c03,
+	HOST_IA32_PERF_GLOBAL_CTRL	= 0x00002c04,
+	HOST_IA32_PERF_GLOBAL_CTRL_HIGH	= 0x00002c05,
+	PIN_BASED_VM_EXEC_CONTROL	= 0x00004000,
+	CPU_BASED_VM_EXEC_CONTROL	= 0x00004002,
+	EXCEPTION_BITMAP		= 0x00004004,
+	PAGE_FAULT_ERROR_CODE_MASK	= 0x00004006,
+	PAGE_FAULT_ERROR_CODE_MATCH	= 0x00004008,
+	CR3_TARGET_COUNT		= 0x0000400a,
+	VM_EXIT_CONTROLS		= 0x0000400c,
+	VM_EXIT_MSR_STORE_COUNT		= 0x0000400e,
+	VM_EXIT_MSR_LOAD_COUNT		= 0x00004010,
+	VM_ENTRY_CONTROLS		= 0x00004012,
+	VM_ENTRY_MSR_LOAD_COUNT		= 0x00004014,
+	VM_ENTRY_INTR_INFO_FIELD	= 0x00004016,
+	VM_ENTRY_EXCEPTION_ERROR_CODE	= 0x00004018,
+	VM_ENTRY_INSTRUCTION_LEN	= 0x0000401a,
+	TPR_THRESHOLD			= 0x0000401c,
+	SECONDARY_VM_EXEC_CONTROL	= 0x0000401e,
+	PLE_GAP				= 0x00004020,
+	PLE_WINDOW			= 0x00004022,
+	VM_INSTRUCTION_ERROR		= 0x00004400,
+	VM_EXIT_REASON			= 0x00004402,
+	VM_EXIT_INTR_INFO		= 0x00004404,
+	VM_EXIT_INTR_ERROR_CODE		= 0x00004406,
+	IDT_VECTORING_INFO_FIELD	= 0x00004408,
+	IDT_VECTORING_ERROR_CODE	= 0x0000440a,
+	VM_EXIT_INSTRUCTION_LEN		= 0x0000440c,
+	VMX_INSTRUCTION_INFO		= 0x0000440e,
+	GUEST_ES_LIMIT			= 0x00004800,
+	GUEST_CS_LIMIT			= 0x00004802,
+	GUEST_SS_LIMIT			= 0x00004804,
+	GUEST_DS_LIMIT			= 0x00004806,
+	GUEST_FS_LIMIT			= 0x00004808,
+	GUEST_GS_LIMIT			= 0x0000480a,
+	GUEST_LDTR_LIMIT		= 0x0000480c,
+	GUEST_TR_LIMIT			= 0x0000480e,
+	GUEST_GDTR_LIMIT		= 0x00004810,
+	GUEST_IDTR_LIMIT		= 0x00004812,
+	GUEST_ES_AR_BYTES		= 0x00004814,
+	GUEST_CS_AR_BYTES		= 0x00004816,
+	GUEST_SS_AR_BYTES		= 0x00004818,
+	GUEST_DS_AR_BYTES		= 0x0000481a,
+	GUEST_FS_AR_BYTES		= 0x0000481c,
+	GUEST_GS_AR_BYTES		= 0x0000481e,
+	GUEST_LDTR_AR_BYTES		= 0x00004820,
+	GUEST_TR_AR_BYTES		= 0x00004822,
+	GUEST_INTERRUPTIBILITY_INFO	= 0x00004824,
+	GUEST_ACTIVITY_STATE		= 0X00004826,
+	GUEST_SYSENTER_CS		= 0x0000482A,
+	VMX_PREEMPTION_TIMER_VALUE	= 0x0000482E,
+	HOST_IA32_SYSENTER_CS		= 0x00004c00,
+	CR0_GUEST_HOST_MASK		= 0x00006000,
+	CR4_GUEST_HOST_MASK		= 0x00006002,
+	CR0_READ_SHADOW			= 0x00006004,
+	CR4_READ_SHADOW			= 0x00006006,
+	CR3_TARGET_VALUE0		= 0x00006008,
+	CR3_TARGET_VALUE1		= 0x0000600a,
+	CR3_TARGET_VALUE2		= 0x0000600c,
+	CR3_TARGET_VALUE3		= 0x0000600e,
+	EXIT_QUALIFICATION		= 0x00006400,
+	GUEST_LINEAR_ADDRESS		= 0x0000640a,
+	GUEST_CR0			= 0x00006800,
+	GUEST_CR3			= 0x00006802,
+	GUEST_CR4			= 0x00006804,
+	GUEST_ES_BASE			= 0x00006806,
+	GUEST_CS_BASE			= 0x00006808,
+	GUEST_SS_BASE			= 0x0000680a,
+	GUEST_DS_BASE			= 0x0000680c,
+	GUEST_FS_BASE			= 0x0000680e,
+	GUEST_GS_BASE			= 0x00006810,
+	GUEST_LDTR_BASE			= 0x00006812,
+	GUEST_TR_BASE			= 0x00006814,
+	GUEST_GDTR_BASE			= 0x00006816,
+	GUEST_IDTR_BASE			= 0x00006818,
+	GUEST_DR7			= 0x0000681a,
+	GUEST_RSP			= 0x0000681c,
+	GUEST_RIP			= 0x0000681e,
+	GUEST_RFLAGS			= 0x00006820,
+	GUEST_PENDING_DBG_EXCEPTIONS	= 0x00006822,
+	GUEST_SYSENTER_ESP		= 0x00006824,
+	GUEST_SYSENTER_EIP		= 0x00006826,
+	HOST_CR0			= 0x00006c00,
+	HOST_CR3			= 0x00006c02,
+	HOST_CR4			= 0x00006c04,
+	HOST_FS_BASE			= 0x00006c06,
+	HOST_GS_BASE			= 0x00006c08,
+	HOST_TR_BASE			= 0x00006c0a,
+	HOST_GDTR_BASE			= 0x00006c0c,
+	HOST_IDTR_BASE			= 0x00006c0e,
+	HOST_IA32_SYSENTER_ESP		= 0x00006c10,
+	HOST_IA32_SYSENTER_EIP		= 0x00006c12,
+	HOST_RSP			= 0x00006c14,
+	HOST_RIP			= 0x00006c16,
+};
+
+struct vmx_msr_entry {
+	uint32_t index;
+	uint32_t reserved;
+	uint64_t value;
+} __attribute__ ((aligned(16)));
+
+static inline int vmxon(uint64_t phys)
+{
+	uint8_t ret;
+
+	__asm__ __volatile__ ("vmxon %[pa]; setna %[ret]"
+		: [ret]"=rm"(ret)
+		: [pa]"m"(phys)
+		: "cc", "memory");
+
+	return ret;
+}
+
+static inline void vmxoff(void)
+{
+	__asm__ __volatile__("vmxoff");
+}
+
+static inline int vmclear(uint64_t vmcs_pa)
+{
+	uint8_t ret;
+
+	__asm__ __volatile__ ("vmclear %[pa]; setna %[ret]"
+		: [ret]"=rm"(ret)
+		: [pa]"m"(vmcs_pa)
+		: "cc", "memory");
+
+	return ret;
+}
+
+static inline int vmptrld(uint64_t vmcs_pa)
+{
+	uint8_t ret;
+
+	__asm__ __volatile__ ("vmptrld %[pa]; setna %[ret]"
+		: [ret]"=rm"(ret)
+		: [pa]"m"(vmcs_pa)
+		: "cc", "memory");
+
+	return ret;
+}
+
+static inline int vmptrst(uint64_t *value)
+{
+	uint64_t tmp;
+	uint8_t ret;
+
+	__asm__ __volatile__("vmptrst %[value]; setna %[ret]"
+		: [value]"=m"(tmp), [ret]"=rm"(ret)
+		: : "cc", "memory");
+
+	*value = tmp;
+	return ret;
+}
+
+/*
+ * A wrapper around vmptrst that ignores errors and returns zero if the
+ * vmptrst instruction fails.
+ */
+static inline uint64_t vmptrstz(void)
+{
+	uint64_t value = 0;
+	vmptrst(&value);
+	return value;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmlaunch.
+ */
+static inline int vmlaunch(void)
+{
+	int ret;
+
+	__asm__ __volatile__("push %%rbp;"
+			     "push %%rcx;"
+			     "push %%rdx;"
+			     "push %%rsi;"
+			     "push %%rdi;"
+			     "push $0;"
+			     "vmwrite %%rsp, %[host_rsp];"
+			     "lea 1f(%%rip), %%rax;"
+			     "vmwrite %%rax, %[host_rip];"
+			     "vmlaunch;"
+			     "incq (%%rsp);"
+			     "1: pop %%rax;"
+			     "pop %%rdi;"
+			     "pop %%rsi;"
+			     "pop %%rdx;"
+			     "pop %%rcx;"
+			     "pop %%rbp;"
+			     : [ret]"=&a"(ret)
+			     : [host_rsp]"r"((uint64_t)HOST_RSP),
+			       [host_rip]"r"((uint64_t)HOST_RIP)
+			     : "memory", "cc", "rbx", "r8", "r9", "r10",
+			       "r11", "r12", "r13", "r14", "r15");
+	return ret;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmresume.
+ */
+static inline int vmresume(void)
+{
+	int ret;
+
+	__asm__ __volatile__("push %%rbp;"
+			     "push %%rcx;"
+			     "push %%rdx;"
+			     "push %%rsi;"
+			     "push %%rdi;"
+			     "push $0;"
+			     "vmwrite %%rsp, %[host_rsp];"
+			     "lea 1f(%%rip), %%rax;"
+			     "vmwrite %%rax, %[host_rip];"
+			     "vmresume;"
+			     "incq (%%rsp);"
+			     "1: pop %%rax;"
+			     "pop %%rdi;"
+			     "pop %%rsi;"
+			     "pop %%rdx;"
+			     "pop %%rcx;"
+			     "pop %%rbp;"
+			     : [ret]"=&a"(ret)
+			     : [host_rsp]"r"((uint64_t)HOST_RSP),
+			       [host_rip]"r"((uint64_t)HOST_RIP)
+			     : "memory", "cc", "rbx", "r8", "r9", "r10",
+			       "r11", "r12", "r13", "r14", "r15");
+	return ret;
+}
+
+static inline void vmcall(void)
+{
+	/* Currently, L1 destroys our GPRs during vmexits.  */
+	__asm__ __volatile__("push %%rbp; vmcall; pop %%rbp" : : :
+			     "rax", "rbx", "rcx", "rdx",
+			     "rsi", "rdi", "r8", "r9", "r10", "r11", "r12",
+			     "r13", "r14", "r15");
+}
+
+static inline int vmread(uint64_t encoding, uint64_t *value)
+{
+	uint64_t tmp;
+	uint8_t ret;
+
+	__asm__ __volatile__("vmread %[encoding], %[value]; setna %[ret]"
+		: [value]"=rm"(tmp), [ret]"=rm"(ret)
+		: [encoding]"r"(encoding)
+		: "cc", "memory");
+
+	*value = tmp;
+	return ret;
+}
+
+/*
+ * A wrapper around vmread that ignores errors and returns zero if the
+ * vmread instruction fails.
+ */
+static inline uint64_t vmreadz(uint64_t encoding)
+{
+	uint64_t value = 0;
+	vmread(encoding, &value);
+	return value;
+}
+
+static inline int vmwrite(uint64_t encoding, uint64_t value)
+{
+	uint8_t ret;
+
+	__asm__ __volatile__ ("vmwrite %[value], %[encoding]; setna %[ret]"
+		: [ret]"=rm"(ret)
+		: [value]"rm"(value), [encoding]"r"(encoding)
+		: "cc", "memory");
+
+	return ret;
+}
+
+static inline uint32_t vmcs_revision(void)
+{
+	return rdmsr(MSR_IA32_VMX_BASIC);
+}
+
+struct vmx_pages {
+	void *vmxon_hva;
+	uint64_t vmxon_gpa;
+	void *vmxon;
+
+	void *vmcs_hva;
+	uint64_t vmcs_gpa;
+	void *vmcs;
+
+	void *msr_hva;
+	uint64_t msr_gpa;
+	void *msr;
+
+	void *shadow_vmcs_hva;
+	uint64_t shadow_vmcs_gpa;
+	void *shadow_vmcs;
+
+	void *vmread_hva;
+	uint64_t vmread_gpa;
+	void *vmread;
+
+	void *vmwrite_hva;
+	uint64_t vmwrite_gpa;
+	void *vmwrite;
+};
+
+struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva);
+bool prepare_for_vmx_operation(struct vmx_pages *vmx);
+void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp);
+
+#endif /* SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c
index cd01144d27c8..6398efe67885 100644
--- a/tools/testing/selftests/kvm/lib/assert.c
+++ b/tools/testing/selftests/kvm/lib/assert.c
@@ -13,7 +13,7 @@
 #include <execinfo.h>
 #include <sys/syscall.h>
 
-#include "../../kselftest.h"
+#include "kselftest.h"
 
 /* Dumps the current stack trace to stderr. */
 static void __attribute__((noinline)) test_dump_stack(void);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 8fa7c9f7567a..36367be0fe26 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -1,13 +1,13 @@
 /*
- * tools/testing/selftests/kvm/lib/kvm_util.c
+ * tools/testing/selftests/kvm/lib/kvm_util_internal.h
  *
  * Copyright (C) 2018, Google LLC.
  *
  * This work is licensed under the terms of the GNU GPL, version 2.
  */
 
-#ifndef KVM_UTIL_INTERNAL_H
-#define KVM_UTIL_INTERNAL_H 1
+#ifndef SELFTEST_KVM_UTIL_INTERNAL_H
+#define SELFTEST_KVM_UTIL_INTERNAL_H
 
 #include "sparsebit.h"
 
@@ -70,4 +70,4 @@ void regs_dump(FILE *stream, struct kvm_regs *regs,
 void sregs_dump(FILE *stream, struct kvm_sregs *sregs,
 	uint8_t indent);
 
-#endif
+#endif /* SELFTEST_KVM_UTIL_INTERNAL_H */
diff --git a/tools/testing/selftests/kvm/lib/vmx.c b/tools/testing/selftests/kvm/lib/vmx.c
deleted file mode 100644
index b987c3c970eb..000000000000
--- a/tools/testing/selftests/kvm/lib/vmx.c
+++ /dev/null
@@ -1,283 +0,0 @@
-/*
- * tools/testing/selftests/kvm/lib/x86.c
- *
- * Copyright (C) 2018, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- */
-
-#define _GNU_SOURCE /* for program_invocation_name */
-
-#include "test_util.h"
-#include "kvm_util.h"
-#include "x86.h"
-#include "vmx.h"
-
-/* Allocate memory regions for nested VMX tests.
- *
- * Input Args:
- *   vm - The VM to allocate guest-virtual addresses in.
- *
- * Output Args:
- *   p_vmx_gva - The guest virtual address for the struct vmx_pages.
- *
- * Return:
- *   Pointer to structure with the addresses of the VMX areas.
- */
-struct vmx_pages *
-vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva)
-{
-	vm_vaddr_t vmx_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
-	struct vmx_pages *vmx = addr_gva2hva(vm, vmx_gva);
-
-	/* Setup of a region of guest memory for the vmxon region. */
-	vmx->vmxon = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
-	vmx->vmxon_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmxon);
-	vmx->vmxon_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmxon);
-
-	/* Setup of a region of guest memory for a vmcs. */
-	vmx->vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
-	vmx->vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmcs);
-	vmx->vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmcs);
-
-	/* Setup of a region of guest memory for the MSR bitmap. */
-	vmx->msr = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
-	vmx->msr_hva = addr_gva2hva(vm, (uintptr_t)vmx->msr);
-	vmx->msr_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->msr);
-	memset(vmx->msr_hva, 0, getpagesize());
-
-	/* Setup of a region of guest memory for the shadow VMCS. */
-	vmx->shadow_vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
-	vmx->shadow_vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->shadow_vmcs);
-	vmx->shadow_vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->shadow_vmcs);
-
-	/* Setup of a region of guest memory for the VMREAD and VMWRITE bitmaps. */
-	vmx->vmread = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
-	vmx->vmread_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmread);
-	vmx->vmread_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmread);
-	memset(vmx->vmread_hva, 0, getpagesize());
-
-	vmx->vmwrite = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
-	vmx->vmwrite_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmwrite);
-	vmx->vmwrite_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmwrite);
-	memset(vmx->vmwrite_hva, 0, getpagesize());
-
-	*p_vmx_gva = vmx_gva;
-	return vmx;
-}
-
-bool prepare_for_vmx_operation(struct vmx_pages *vmx)
-{
-	uint64_t feature_control;
-	uint64_t required;
-	unsigned long cr0;
-	unsigned long cr4;
-
-	/*
-	 * Ensure bits in CR0 and CR4 are valid in VMX operation:
-	 * - Bit X is 1 in _FIXED0: bit X is fixed to 1 in CRx.
-	 * - Bit X is 0 in _FIXED1: bit X is fixed to 0 in CRx.
-	 */
-	__asm__ __volatile__("mov %%cr0, %0" : "=r"(cr0) : : "memory");
-	cr0 &= rdmsr(MSR_IA32_VMX_CR0_FIXED1);
-	cr0 |= rdmsr(MSR_IA32_VMX_CR0_FIXED0);
-	__asm__ __volatile__("mov %0, %%cr0" : : "r"(cr0) : "memory");
-
-	__asm__ __volatile__("mov %%cr4, %0" : "=r"(cr4) : : "memory");
-	cr4 &= rdmsr(MSR_IA32_VMX_CR4_FIXED1);
-	cr4 |= rdmsr(MSR_IA32_VMX_CR4_FIXED0);
-	/* Enable VMX operation */
-	cr4 |= X86_CR4_VMXE;
-	__asm__ __volatile__("mov %0, %%cr4" : : "r"(cr4) : "memory");
-
-	/*
-	 * Configure IA32_FEATURE_CONTROL MSR to allow VMXON:
-	 *  Bit 0: Lock bit. If clear, VMXON causes a #GP.
-	 *  Bit 2: Enables VMXON outside of SMX operation. If clear, VMXON
-	 *    outside of SMX causes a #GP.
-	 */
-	required = FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
-	required |= FEATURE_CONTROL_LOCKED;
-	feature_control = rdmsr(MSR_IA32_FEATURE_CONTROL);
-	if ((feature_control & required) != required)
-		wrmsr(MSR_IA32_FEATURE_CONTROL, feature_control | required);
-
-	/* Enter VMX root operation. */
-	*(uint32_t *)(vmx->vmxon) = vmcs_revision();
-	if (vmxon(vmx->vmxon_gpa))
-		return false;
-
-	/* Load a VMCS. */
-	*(uint32_t *)(vmx->vmcs) = vmcs_revision();
-	if (vmclear(vmx->vmcs_gpa))
-		return false;
-
-	if (vmptrld(vmx->vmcs_gpa))
-		return false;
-
-	/* Setup shadow VMCS, do not load it yet. */
-	*(uint32_t *)(vmx->shadow_vmcs) = vmcs_revision() | 0x80000000ul;
-	if (vmclear(vmx->shadow_vmcs_gpa))
-		return false;
-
-	return true;
-}
-
-/*
- * Initialize the control fields to the most basic settings possible.
- */
-static inline void init_vmcs_control_fields(struct vmx_pages *vmx)
-{
-	vmwrite(VIRTUAL_PROCESSOR_ID, 0);
-	vmwrite(POSTED_INTR_NV, 0);
-
-	vmwrite(PIN_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PINBASED_CTLS));
-	if (!vmwrite(SECONDARY_VM_EXEC_CONTROL, 0))
-		vmwrite(CPU_BASED_VM_EXEC_CONTROL,
-			rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS) | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS);
-	else
-		vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS));
-	vmwrite(EXCEPTION_BITMAP, 0);
-	vmwrite(PAGE_FAULT_ERROR_CODE_MASK, 0);
-	vmwrite(PAGE_FAULT_ERROR_CODE_MATCH, -1); /* Never match */
-	vmwrite(CR3_TARGET_COUNT, 0);
-	vmwrite(VM_EXIT_CONTROLS, rdmsr(MSR_IA32_VMX_EXIT_CTLS) |
-		VM_EXIT_HOST_ADDR_SPACE_SIZE);	  /* 64-bit host */
-	vmwrite(VM_EXIT_MSR_STORE_COUNT, 0);
-	vmwrite(VM_EXIT_MSR_LOAD_COUNT, 0);
-	vmwrite(VM_ENTRY_CONTROLS, rdmsr(MSR_IA32_VMX_ENTRY_CTLS) |
-		VM_ENTRY_IA32E_MODE);		  /* 64-bit guest */
-	vmwrite(VM_ENTRY_MSR_LOAD_COUNT, 0);
-	vmwrite(VM_ENTRY_INTR_INFO_FIELD, 0);
-	vmwrite(TPR_THRESHOLD, 0);
-
-	vmwrite(CR0_GUEST_HOST_MASK, 0);
-	vmwrite(CR4_GUEST_HOST_MASK, 0);
-	vmwrite(CR0_READ_SHADOW, get_cr0());
-	vmwrite(CR4_READ_SHADOW, get_cr4());
-
-	vmwrite(MSR_BITMAP, vmx->msr_gpa);
-	vmwrite(VMREAD_BITMAP, vmx->vmread_gpa);
-	vmwrite(VMWRITE_BITMAP, vmx->vmwrite_gpa);
-}
-
-/*
- * Initialize the host state fields based on the current host state, with
- * the exception of HOST_RSP and HOST_RIP, which should be set by vmlaunch
- * or vmresume.
- */
-static inline void init_vmcs_host_state(void)
-{
-	uint32_t exit_controls = vmreadz(VM_EXIT_CONTROLS);
-
-	vmwrite(HOST_ES_SELECTOR, get_es());
-	vmwrite(HOST_CS_SELECTOR, get_cs());
-	vmwrite(HOST_SS_SELECTOR, get_ss());
-	vmwrite(HOST_DS_SELECTOR, get_ds());
-	vmwrite(HOST_FS_SELECTOR, get_fs());
-	vmwrite(HOST_GS_SELECTOR, get_gs());
-	vmwrite(HOST_TR_SELECTOR, get_tr());
-
-	if (exit_controls & VM_EXIT_LOAD_IA32_PAT)
-		vmwrite(HOST_IA32_PAT, rdmsr(MSR_IA32_CR_PAT));
-	if (exit_controls & VM_EXIT_LOAD_IA32_EFER)
-		vmwrite(HOST_IA32_EFER, rdmsr(MSR_EFER));
-	if (exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
-		vmwrite(HOST_IA32_PERF_GLOBAL_CTRL,
-			rdmsr(MSR_CORE_PERF_GLOBAL_CTRL));
-
-	vmwrite(HOST_IA32_SYSENTER_CS, rdmsr(MSR_IA32_SYSENTER_CS));
-
-	vmwrite(HOST_CR0, get_cr0());
-	vmwrite(HOST_CR3, get_cr3());
-	vmwrite(HOST_CR4, get_cr4());
-	vmwrite(HOST_FS_BASE, rdmsr(MSR_FS_BASE));
-	vmwrite(HOST_GS_BASE, rdmsr(MSR_GS_BASE));
-	vmwrite(HOST_TR_BASE,
-		get_desc64_base((struct desc64 *)(get_gdt_base() + get_tr())));
-	vmwrite(HOST_GDTR_BASE, get_gdt_base());
-	vmwrite(HOST_IDTR_BASE, get_idt_base());
-	vmwrite(HOST_IA32_SYSENTER_ESP, rdmsr(MSR_IA32_SYSENTER_ESP));
-	vmwrite(HOST_IA32_SYSENTER_EIP, rdmsr(MSR_IA32_SYSENTER_EIP));
-}
-
-/*
- * Initialize the guest state fields essentially as a clone of
- * the host state fields. Some host state fields have fixed
- * values, and we set the corresponding guest state fields accordingly.
- */
-static inline void init_vmcs_guest_state(void *rip, void *rsp)
-{
-	vmwrite(GUEST_ES_SELECTOR, vmreadz(HOST_ES_SELECTOR));
-	vmwrite(GUEST_CS_SELECTOR, vmreadz(HOST_CS_SELECTOR));
-	vmwrite(GUEST_SS_SELECTOR, vmreadz(HOST_SS_SELECTOR));
-	vmwrite(GUEST_DS_SELECTOR, vmreadz(HOST_DS_SELECTOR));
-	vmwrite(GUEST_FS_SELECTOR, vmreadz(HOST_FS_SELECTOR));
-	vmwrite(GUEST_GS_SELECTOR, vmreadz(HOST_GS_SELECTOR));
-	vmwrite(GUEST_LDTR_SELECTOR, 0);
-	vmwrite(GUEST_TR_SELECTOR, vmreadz(HOST_TR_SELECTOR));
-	vmwrite(GUEST_INTR_STATUS, 0);
-	vmwrite(GUEST_PML_INDEX, 0);
-
-	vmwrite(VMCS_LINK_POINTER, -1ll);
-	vmwrite(GUEST_IA32_DEBUGCTL, 0);
-	vmwrite(GUEST_IA32_PAT, vmreadz(HOST_IA32_PAT));
-	vmwrite(GUEST_IA32_EFER, vmreadz(HOST_IA32_EFER));
-	vmwrite(GUEST_IA32_PERF_GLOBAL_CTRL,
-		vmreadz(HOST_IA32_PERF_GLOBAL_CTRL));
-
-	vmwrite(GUEST_ES_LIMIT, -1);
-	vmwrite(GUEST_CS_LIMIT, -1);
-	vmwrite(GUEST_SS_LIMIT, -1);
-	vmwrite(GUEST_DS_LIMIT, -1);
-	vmwrite(GUEST_FS_LIMIT, -1);
-	vmwrite(GUEST_GS_LIMIT, -1);
-	vmwrite(GUEST_LDTR_LIMIT, -1);
-	vmwrite(GUEST_TR_LIMIT, 0x67);
-	vmwrite(GUEST_GDTR_LIMIT, 0xffff);
-	vmwrite(GUEST_IDTR_LIMIT, 0xffff);
-	vmwrite(GUEST_ES_AR_BYTES,
-		vmreadz(GUEST_ES_SELECTOR) == 0 ? 0x10000 : 0xc093);
-	vmwrite(GUEST_CS_AR_BYTES, 0xa09b);
-	vmwrite(GUEST_SS_AR_BYTES, 0xc093);
-	vmwrite(GUEST_DS_AR_BYTES,
-		vmreadz(GUEST_DS_SELECTOR) == 0 ? 0x10000 : 0xc093);
-	vmwrite(GUEST_FS_AR_BYTES,
-		vmreadz(GUEST_FS_SELECTOR) == 0 ? 0x10000 : 0xc093);
-	vmwrite(GUEST_GS_AR_BYTES,
-		vmreadz(GUEST_GS_SELECTOR) == 0 ? 0x10000 : 0xc093);
-	vmwrite(GUEST_LDTR_AR_BYTES, 0x10000);
-	vmwrite(GUEST_TR_AR_BYTES, 0x8b);
-	vmwrite(GUEST_INTERRUPTIBILITY_INFO, 0);
-	vmwrite(GUEST_ACTIVITY_STATE, 0);
-	vmwrite(GUEST_SYSENTER_CS, vmreadz(HOST_IA32_SYSENTER_CS));
-	vmwrite(VMX_PREEMPTION_TIMER_VALUE, 0);
-
-	vmwrite(GUEST_CR0, vmreadz(HOST_CR0));
-	vmwrite(GUEST_CR3, vmreadz(HOST_CR3));
-	vmwrite(GUEST_CR4, vmreadz(HOST_CR4));
-	vmwrite(GUEST_ES_BASE, 0);
-	vmwrite(GUEST_CS_BASE, 0);
-	vmwrite(GUEST_SS_BASE, 0);
-	vmwrite(GUEST_DS_BASE, 0);
-	vmwrite(GUEST_FS_BASE, vmreadz(HOST_FS_BASE));
-	vmwrite(GUEST_GS_BASE, vmreadz(HOST_GS_BASE));
-	vmwrite(GUEST_LDTR_BASE, 0);
-	vmwrite(GUEST_TR_BASE, vmreadz(HOST_TR_BASE));
-	vmwrite(GUEST_GDTR_BASE, vmreadz(HOST_GDTR_BASE));
-	vmwrite(GUEST_IDTR_BASE, vmreadz(HOST_IDTR_BASE));
-	vmwrite(GUEST_DR7, 0x400);
-	vmwrite(GUEST_RSP, (uint64_t)rsp);
-	vmwrite(GUEST_RIP, (uint64_t)rip);
-	vmwrite(GUEST_RFLAGS, 2);
-	vmwrite(GUEST_PENDING_DBG_EXCEPTIONS, 0);
-	vmwrite(GUEST_SYSENTER_ESP, vmreadz(HOST_IA32_SYSENTER_ESP));
-	vmwrite(GUEST_SYSENTER_EIP, vmreadz(HOST_IA32_SYSENTER_EIP));
-}
-
-void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp)
-{
-	init_vmcs_control_fields(vmx);
-	init_vmcs_host_state();
-	init_vmcs_guest_state(guest_rip, guest_rsp);
-}
diff --git a/tools/testing/selftests/kvm/lib/x86.c b/tools/testing/selftests/kvm/lib/x86.c
deleted file mode 100644
index bb6c65ebfa77..000000000000
--- a/tools/testing/selftests/kvm/lib/x86.c
+++ /dev/null
@@ -1,888 +0,0 @@
-/*
- * tools/testing/selftests/kvm/lib/x86.c
- *
- * Copyright (C) 2018, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- */
-
-#define _GNU_SOURCE /* for program_invocation_name */
-
-#include "test_util.h"
-#include "kvm_util.h"
-#include "kvm_util_internal.h"
-#include "x86.h"
-
-/* Minimum physical address used for virtual translation tables. */
-#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
-
-/* Virtual translation table structure declarations */
-struct pageMapL4Entry {
-	uint64_t present:1;
-	uint64_t writable:1;
-	uint64_t user:1;
-	uint64_t write_through:1;
-	uint64_t cache_disable:1;
-	uint64_t accessed:1;
-	uint64_t ignored_06:1;
-	uint64_t page_size:1;
-	uint64_t ignored_11_08:4;
-	uint64_t address:40;
-	uint64_t ignored_62_52:11;
-	uint64_t execute_disable:1;
-};
-
-struct pageDirectoryPointerEntry {
-	uint64_t present:1;
-	uint64_t writable:1;
-	uint64_t user:1;
-	uint64_t write_through:1;
-	uint64_t cache_disable:1;
-	uint64_t accessed:1;
-	uint64_t ignored_06:1;
-	uint64_t page_size:1;
-	uint64_t ignored_11_08:4;
-	uint64_t address:40;
-	uint64_t ignored_62_52:11;
-	uint64_t execute_disable:1;
-};
-
-struct pageDirectoryEntry {
-	uint64_t present:1;
-	uint64_t writable:1;
-	uint64_t user:1;
-	uint64_t write_through:1;
-	uint64_t cache_disable:1;
-	uint64_t accessed:1;
-	uint64_t ignored_06:1;
-	uint64_t page_size:1;
-	uint64_t ignored_11_08:4;
-	uint64_t address:40;
-	uint64_t ignored_62_52:11;
-	uint64_t execute_disable:1;
-};
-
-struct pageTableEntry {
-	uint64_t present:1;
-	uint64_t writable:1;
-	uint64_t user:1;
-	uint64_t write_through:1;
-	uint64_t cache_disable:1;
-	uint64_t accessed:1;
-	uint64_t dirty:1;
-	uint64_t reserved_07:1;
-	uint64_t global:1;
-	uint64_t ignored_11_09:3;
-	uint64_t address:40;
-	uint64_t ignored_62_52:11;
-	uint64_t execute_disable:1;
-};
-
-/* Register Dump
- *
- * Input Args:
- *   indent - Left margin indent amount
- *   regs - register
- *
- * Output Args:
- *   stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the state of the registers given by regs, to the FILE stream
- * given by steam.
- */
-void regs_dump(FILE *stream, struct kvm_regs *regs,
-	       uint8_t indent)
-{
-	fprintf(stream, "%*srax: 0x%.16llx rbx: 0x%.16llx "
-		"rcx: 0x%.16llx rdx: 0x%.16llx\n",
-		indent, "",
-		regs->rax, regs->rbx, regs->rcx, regs->rdx);
-	fprintf(stream, "%*srsi: 0x%.16llx rdi: 0x%.16llx "
-		"rsp: 0x%.16llx rbp: 0x%.16llx\n",
-		indent, "",
-		regs->rsi, regs->rdi, regs->rsp, regs->rbp);
-	fprintf(stream, "%*sr8:  0x%.16llx r9:  0x%.16llx "
-		"r10: 0x%.16llx r11: 0x%.16llx\n",
-		indent, "",
-		regs->r8, regs->r9, regs->r10, regs->r11);
-	fprintf(stream, "%*sr12: 0x%.16llx r13: 0x%.16llx "
-		"r14: 0x%.16llx r15: 0x%.16llx\n",
-		indent, "",
-		regs->r12, regs->r13, regs->r14, regs->r15);
-	fprintf(stream, "%*srip: 0x%.16llx rfl: 0x%.16llx\n",
-		indent, "",
-		regs->rip, regs->rflags);
-}
-
-/* Segment Dump
- *
- * Input Args:
- *   indent - Left margin indent amount
- *   segment - KVM segment
- *
- * Output Args:
- *   stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the state of the KVM segment given by segment, to the FILE stream
- * given by steam.
- */
-static void segment_dump(FILE *stream, struct kvm_segment *segment,
-			 uint8_t indent)
-{
-	fprintf(stream, "%*sbase: 0x%.16llx limit: 0x%.8x "
-		"selector: 0x%.4x type: 0x%.2x\n",
-		indent, "", segment->base, segment->limit,
-		segment->selector, segment->type);
-	fprintf(stream, "%*spresent: 0x%.2x dpl: 0x%.2x "
-		"db: 0x%.2x s: 0x%.2x l: 0x%.2x\n",
-		indent, "", segment->present, segment->dpl,
-		segment->db, segment->s, segment->l);
-	fprintf(stream, "%*sg: 0x%.2x avl: 0x%.2x "
-		"unusable: 0x%.2x padding: 0x%.2x\n",
-		indent, "", segment->g, segment->avl,
-		segment->unusable, segment->padding);
-}
-
-/* dtable Dump
- *
- * Input Args:
- *   indent - Left margin indent amount
- *   dtable - KVM dtable
- *
- * Output Args:
- *   stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the state of the KVM dtable given by dtable, to the FILE stream
- * given by steam.
- */
-static void dtable_dump(FILE *stream, struct kvm_dtable *dtable,
-			uint8_t indent)
-{
-	fprintf(stream, "%*sbase: 0x%.16llx limit: 0x%.4x "
-		"padding: 0x%.4x 0x%.4x 0x%.4x\n",
-		indent, "", dtable->base, dtable->limit,
-		dtable->padding[0], dtable->padding[1], dtable->padding[2]);
-}
-
-/* System Register Dump
- *
- * Input Args:
- *   indent - Left margin indent amount
- *   sregs - System registers
- *
- * Output Args:
- *   stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the state of the system registers given by sregs, to the FILE stream
- * given by steam.
- */
-void sregs_dump(FILE *stream, struct kvm_sregs *sregs,
-		uint8_t indent)
-{
-	unsigned int i;
-
-	fprintf(stream, "%*scs:\n", indent, "");
-	segment_dump(stream, &sregs->cs, indent + 2);
-	fprintf(stream, "%*sds:\n", indent, "");
-	segment_dump(stream, &sregs->ds, indent + 2);
-	fprintf(stream, "%*ses:\n", indent, "");
-	segment_dump(stream, &sregs->es, indent + 2);
-	fprintf(stream, "%*sfs:\n", indent, "");
-	segment_dump(stream, &sregs->fs, indent + 2);
-	fprintf(stream, "%*sgs:\n", indent, "");
-	segment_dump(stream, &sregs->gs, indent + 2);
-	fprintf(stream, "%*sss:\n", indent, "");
-	segment_dump(stream, &sregs->ss, indent + 2);
-	fprintf(stream, "%*str:\n", indent, "");
-	segment_dump(stream, &sregs->tr, indent + 2);
-	fprintf(stream, "%*sldt:\n", indent, "");
-	segment_dump(stream, &sregs->ldt, indent + 2);
-
-	fprintf(stream, "%*sgdt:\n", indent, "");
-	dtable_dump(stream, &sregs->gdt, indent + 2);
-	fprintf(stream, "%*sidt:\n", indent, "");
-	dtable_dump(stream, &sregs->idt, indent + 2);
-
-	fprintf(stream, "%*scr0: 0x%.16llx cr2: 0x%.16llx "
-		"cr3: 0x%.16llx cr4: 0x%.16llx\n",
-		indent, "",
-		sregs->cr0, sregs->cr2, sregs->cr3, sregs->cr4);
-	fprintf(stream, "%*scr8: 0x%.16llx efer: 0x%.16llx "
-		"apic_base: 0x%.16llx\n",
-		indent, "",
-		sregs->cr8, sregs->efer, sregs->apic_base);
-
-	fprintf(stream, "%*sinterrupt_bitmap:\n", indent, "");
-	for (i = 0; i < (KVM_NR_INTERRUPTS + 63) / 64; i++) {
-		fprintf(stream, "%*s%.16llx\n", indent + 2, "",
-			sregs->interrupt_bitmap[i]);
-	}
-}
-
-void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
-{
-	int rc;
-
-	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
-		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
-
-	/* If needed, create page map l4 table. */
-	if (!vm->pgd_created) {
-		vm_paddr_t paddr = vm_phy_page_alloc(vm,
-			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
-		vm->pgd = paddr;
-		vm->pgd_created = true;
-	}
-}
-
-/* VM Virtual Page Map
- *
- * Input Args:
- *   vm - Virtual Machine
- *   vaddr - VM Virtual Address
- *   paddr - VM Physical Address
- *   pgd_memslot - Memory region slot for new virtual translation tables
- *
- * Output Args: None
- *
- * Return: None
- *
- * Within the VM given by vm, creates a virtual translation for the page
- * starting at vaddr to the page starting at paddr.
- */
-void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
-	uint32_t pgd_memslot)
-{
-	uint16_t index[4];
-	struct pageMapL4Entry *pml4e;
-
-	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
-		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
-
-	TEST_ASSERT((vaddr % vm->page_size) == 0,
-		"Virtual address not on page boundary,\n"
-		"  vaddr: 0x%lx vm->page_size: 0x%x",
-		vaddr, vm->page_size);
-	TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
-		(vaddr >> vm->page_shift)),
-		"Invalid virtual address, vaddr: 0x%lx",
-		vaddr);
-	TEST_ASSERT((paddr % vm->page_size) == 0,
-		"Physical address not on page boundary,\n"
-		"  paddr: 0x%lx vm->page_size: 0x%x",
-		paddr, vm->page_size);
-	TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
-		"Physical address beyond beyond maximum supported,\n"
-		"  paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
-		paddr, vm->max_gfn, vm->page_size);
-
-	index[0] = (vaddr >> 12) & 0x1ffu;
-	index[1] = (vaddr >> 21) & 0x1ffu;
-	index[2] = (vaddr >> 30) & 0x1ffu;
-	index[3] = (vaddr >> 39) & 0x1ffu;
-
-	/* Allocate page directory pointer table if not present. */
-	pml4e = addr_gpa2hva(vm, vm->pgd);
-	if (!pml4e[index[3]].present) {
-		pml4e[index[3]].address = vm_phy_page_alloc(vm,
-			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
-			>> vm->page_shift;
-		pml4e[index[3]].writable = true;
-		pml4e[index[3]].present = true;
-	}
-
-	/* Allocate page directory table if not present. */
-	struct pageDirectoryPointerEntry *pdpe;
-	pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
-	if (!pdpe[index[2]].present) {
-		pdpe[index[2]].address = vm_phy_page_alloc(vm,
-			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
-			>> vm->page_shift;
-		pdpe[index[2]].writable = true;
-		pdpe[index[2]].present = true;
-	}
-
-	/* Allocate page table if not present. */
-	struct pageDirectoryEntry *pde;
-	pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
-	if (!pde[index[1]].present) {
-		pde[index[1]].address = vm_phy_page_alloc(vm,
-			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
-			>> vm->page_shift;
-		pde[index[1]].writable = true;
-		pde[index[1]].present = true;
-	}
-
-	/* Fill in page table entry. */
-	struct pageTableEntry *pte;
-	pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
-	pte[index[0]].address = paddr >> vm->page_shift;
-	pte[index[0]].writable = true;
-	pte[index[0]].present = 1;
-}
-
-/* Virtual Translation Tables Dump
- *
- * Input Args:
- *   vm - Virtual Machine
- *   indent - Left margin indent amount
- *
- * Output Args:
- *   stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps to the FILE stream given by stream, the contents of all the
- * virtual translation tables for the VM given by vm.
- */
-void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
-{
-	struct pageMapL4Entry *pml4e, *pml4e_start;
-	struct pageDirectoryPointerEntry *pdpe, *pdpe_start;
-	struct pageDirectoryEntry *pde, *pde_start;
-	struct pageTableEntry *pte, *pte_start;
-
-	if (!vm->pgd_created)
-		return;
-
-	fprintf(stream, "%*s                                          "
-		"                no\n", indent, "");
-	fprintf(stream, "%*s      index hvaddr         gpaddr         "
-		"addr         w exec dirty\n",
-		indent, "");
-	pml4e_start = (struct pageMapL4Entry *) addr_gpa2hva(vm,
-		vm->pgd);
-	for (uint16_t n1 = 0; n1 <= 0x1ffu; n1++) {
-		pml4e = &pml4e_start[n1];
-		if (!pml4e->present)
-			continue;
-		fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10lx %u "
-			" %u\n",
-			indent, "",
-			pml4e - pml4e_start, pml4e,
-			addr_hva2gpa(vm, pml4e), (uint64_t) pml4e->address,
-			pml4e->writable, pml4e->execute_disable);
-
-		pdpe_start = addr_gpa2hva(vm, pml4e->address
-			* vm->page_size);
-		for (uint16_t n2 = 0; n2 <= 0x1ffu; n2++) {
-			pdpe = &pdpe_start[n2];
-			if (!pdpe->present)
-				continue;
-			fprintf(stream, "%*spdpe  0x%-3zx %p 0x%-12lx 0x%-10lx "
-				"%u  %u\n",
-				indent, "",
-				pdpe - pdpe_start, pdpe,
-				addr_hva2gpa(vm, pdpe),
-				(uint64_t) pdpe->address, pdpe->writable,
-				pdpe->execute_disable);
-
-			pde_start = addr_gpa2hva(vm,
-				pdpe->address * vm->page_size);
-			for (uint16_t n3 = 0; n3 <= 0x1ffu; n3++) {
-				pde = &pde_start[n3];
-				if (!pde->present)
-					continue;
-				fprintf(stream, "%*spde   0x%-3zx %p "
-					"0x%-12lx 0x%-10lx %u  %u\n",
-					indent, "", pde - pde_start, pde,
-					addr_hva2gpa(vm, pde),
-					(uint64_t) pde->address, pde->writable,
-					pde->execute_disable);
-
-				pte_start = addr_gpa2hva(vm,
-					pde->address * vm->page_size);
-				for (uint16_t n4 = 0; n4 <= 0x1ffu; n4++) {
-					pte = &pte_start[n4];
-					if (!pte->present)
-						continue;
-					fprintf(stream, "%*spte   0x%-3zx %p "
-						"0x%-12lx 0x%-10lx %u  %u "
-						"    %u    0x%-10lx\n",
-						indent, "",
-						pte - pte_start, pte,
-						addr_hva2gpa(vm, pte),
-						(uint64_t) pte->address,
-						pte->writable,
-						pte->execute_disable,
-						pte->dirty,
-						((uint64_t) n1 << 27)
-							| ((uint64_t) n2 << 18)
-							| ((uint64_t) n3 << 9)
-							| ((uint64_t) n4));
-				}
-			}
-		}
-	}
-}
-
-/* Set Unusable Segment
- *
- * Input Args: None
- *
- * Output Args:
- *   segp - Pointer to segment register
- *
- * Return: None
- *
- * Sets the segment register pointed to by segp to an unusable state.
- */
-static void kvm_seg_set_unusable(struct kvm_segment *segp)
-{
-	memset(segp, 0, sizeof(*segp));
-	segp->unusable = true;
-}
-
-static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp)
-{
-	void *gdt = addr_gva2hva(vm, vm->gdt);
-	struct desc64 *desc = gdt + (segp->selector >> 3) * 8;
-
-	desc->limit0 = segp->limit & 0xFFFF;
-	desc->base0 = segp->base & 0xFFFF;
-	desc->base1 = segp->base >> 16;
-	desc->s = segp->s;
-	desc->type = segp->type;
-	desc->dpl = segp->dpl;
-	desc->p = segp->present;
-	desc->limit1 = segp->limit >> 16;
-	desc->l = segp->l;
-	desc->db = segp->db;
-	desc->g = segp->g;
-	desc->base2 = segp->base >> 24;
-	if (!segp->s)
-		desc->base3 = segp->base >> 32;
-}
-
-
-/* Set Long Mode Flat Kernel Code Segment
- *
- * Input Args:
- *   vm - VM whose GDT is being filled, or NULL to only write segp
- *   selector - selector value
- *
- * Output Args:
- *   segp - Pointer to KVM segment
- *
- * Return: None
- *
- * Sets up the KVM segment pointed to by segp, to be a code segment
- * with the selector value given by selector.
- */
-static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector,
-	struct kvm_segment *segp)
-{
-	memset(segp, 0, sizeof(*segp));
-	segp->selector = selector;
-	segp->limit = 0xFFFFFFFFu;
-	segp->s = 0x1; /* kTypeCodeData */
-	segp->type = 0x08 | 0x01 | 0x02; /* kFlagCode | kFlagCodeAccessed
-					  * | kFlagCodeReadable
-					  */
-	segp->g = true;
-	segp->l = true;
-	segp->present = 1;
-	if (vm)
-		kvm_seg_fill_gdt_64bit(vm, segp);
-}
-
-/* Set Long Mode Flat Kernel Data Segment
- *
- * Input Args:
- *   vm - VM whose GDT is being filled, or NULL to only write segp
- *   selector - selector value
- *
- * Output Args:
- *   segp - Pointer to KVM segment
- *
- * Return: None
- *
- * Sets up the KVM segment pointed to by segp, to be a data segment
- * with the selector value given by selector.
- */
-static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector,
-	struct kvm_segment *segp)
-{
-	memset(segp, 0, sizeof(*segp));
-	segp->selector = selector;
-	segp->limit = 0xFFFFFFFFu;
-	segp->s = 0x1; /* kTypeCodeData */
-	segp->type = 0x00 | 0x01 | 0x02; /* kFlagData | kFlagDataAccessed
-					  * | kFlagDataWritable
-					  */
-	segp->g = true;
-	segp->present = true;
-	if (vm)
-		kvm_seg_fill_gdt_64bit(vm, segp);
-}
-
-/* Address Guest Virtual to Guest Physical
- *
- * Input Args:
- *   vm - Virtual Machine
- *   gpa - VM virtual address
- *
- * Output Args: None
- *
- * Return:
- *   Equivalent VM physical address
- *
- * Translates the VM virtual address given by gva to a VM physical
- * address and then locates the memory region containing the VM
- * physical address, within the VM given by vm.  When found, the host
- * virtual address providing the memory to the vm physical address is returned.
- * A TEST_ASSERT failure occurs if no region containing translated
- * VM virtual address exists.
- */
-vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
-{
-	uint16_t index[4];
-	struct pageMapL4Entry *pml4e;
-	struct pageDirectoryPointerEntry *pdpe;
-	struct pageDirectoryEntry *pde;
-	struct pageTableEntry *pte;
-	void *hva;
-
-	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
-		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
-
-	index[0] = (gva >> 12) & 0x1ffu;
-	index[1] = (gva >> 21) & 0x1ffu;
-	index[2] = (gva >> 30) & 0x1ffu;
-	index[3] = (gva >> 39) & 0x1ffu;
-
-	if (!vm->pgd_created)
-		goto unmapped_gva;
-	pml4e = addr_gpa2hva(vm, vm->pgd);
-	if (!pml4e[index[3]].present)
-		goto unmapped_gva;
-
-	pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
-	if (!pdpe[index[2]].present)
-		goto unmapped_gva;
-
-	pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
-	if (!pde[index[1]].present)
-		goto unmapped_gva;
-
-	pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
-	if (!pte[index[0]].present)
-		goto unmapped_gva;
-
-	return (pte[index[0]].address * vm->page_size) + (gva & 0xfffu);
-
-unmapped_gva:
-	TEST_ASSERT(false, "No mapping for vm virtual address, "
-		    "gva: 0x%lx", gva);
-}
-
-static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt, int gdt_memslot,
-			  int pgd_memslot)
-{
-	if (!vm->gdt)
-		vm->gdt = vm_vaddr_alloc(vm, getpagesize(),
-			KVM_UTIL_MIN_VADDR, gdt_memslot, pgd_memslot);
-
-	dt->base = vm->gdt;
-	dt->limit = getpagesize();
-}
-
-static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp,
-				int selector, int gdt_memslot,
-				int pgd_memslot)
-{
-	if (!vm->tss)
-		vm->tss = vm_vaddr_alloc(vm, getpagesize(),
-			KVM_UTIL_MIN_VADDR, gdt_memslot, pgd_memslot);
-
-	memset(segp, 0, sizeof(*segp));
-	segp->base = vm->tss;
-	segp->limit = 0x67;
-	segp->selector = selector;
-	segp->type = 0xb;
-	segp->present = 1;
-	kvm_seg_fill_gdt_64bit(vm, segp);
-}
-
-void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
-{
-	struct kvm_sregs sregs;
-
-	/* Set mode specific system register values. */
-	vcpu_sregs_get(vm, vcpuid, &sregs);
-
-	sregs.idt.limit = 0;
-
-	kvm_setup_gdt(vm, &sregs.gdt, gdt_memslot, pgd_memslot);
-
-	switch (vm->mode) {
-	case VM_MODE_FLAT48PG:
-		sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG;
-		sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
-		sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
-
-		kvm_seg_set_unusable(&sregs.ldt);
-		kvm_seg_set_kernel_code_64bit(vm, 0x8, &sregs.cs);
-		kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.ds);
-		kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.es);
-		kvm_setup_tss_64bit(vm, &sregs.tr, 0x18, gdt_memslot, pgd_memslot);
-		break;
-
-	default:
-		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode);
-	}
-
-	sregs.cr3 = vm->pgd;
-	vcpu_sregs_set(vm, vcpuid, &sregs);
-}
-/* Adds a vCPU with reasonable defaults (i.e., a stack)
- *
- * Input Args:
- *   vcpuid - The id of the VCPU to add to the VM.
- *   guest_code - The vCPU's entry point
- */
-void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
-{
-	struct kvm_mp_state mp_state;
-	struct kvm_regs regs;
-	vm_vaddr_t stack_vaddr;
-	stack_vaddr = vm_vaddr_alloc(vm, DEFAULT_STACK_PGS * getpagesize(),
-				     DEFAULT_GUEST_STACK_VADDR_MIN, 0, 0);
-
-	/* Create VCPU */
-	vm_vcpu_add(vm, vcpuid, 0, 0);
-
-	/* Setup guest general purpose registers */
-	vcpu_regs_get(vm, vcpuid, &regs);
-	regs.rflags = regs.rflags | 0x2;
-	regs.rsp = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize());
-	regs.rip = (unsigned long) guest_code;
-	vcpu_regs_set(vm, vcpuid, &regs);
-
-	/* Setup the MP state */
-	mp_state.mp_state = 0;
-	vcpu_set_mp_state(vm, vcpuid, &mp_state);
-}
-
-/* VM VCPU CPUID Set
- *
- * Input Args:
- *   vm - Virtual Machine
- *   vcpuid - VCPU id
- *   cpuid - The CPUID values to set.
- *
- * Output Args: None
- *
- * Return: void
- *
- * Set the VCPU's CPUID.
- */
-void vcpu_set_cpuid(struct kvm_vm *vm,
-		uint32_t vcpuid, struct kvm_cpuid2 *cpuid)
-{
-	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
-	int rc;
-
-	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
-
-	rc = ioctl(vcpu->fd, KVM_SET_CPUID2, cpuid);
-	TEST_ASSERT(rc == 0, "KVM_SET_CPUID2 failed, rc: %i errno: %i",
-		    rc, errno);
-
-}
-/* Create a VM with reasonable defaults
- *
- * Input Args:
- *   vcpuid - The id of the single VCPU to add to the VM.
- *   extra_mem_pages - The size of extra memories to add (this will
- *                     decide how much extra space we will need to
- *                     setup the page tables using mem slot 0)
- *   guest_code - The vCPU's entry point
- *
- * Output Args: None
- *
- * Return:
- *   Pointer to opaque structure that describes the created VM.
- */
-struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
-				 void *guest_code)
-{
-	struct kvm_vm *vm;
-	/*
-	 * For x86 the maximum page table size for a memory region
-	 * will be when only 4K pages are used.  In that case the
-	 * total extra size for page tables (for extra N pages) will
-	 * be: N/512+N/512^2+N/512^3+... which is definitely smaller
-	 * than N/512*2.
-	 */
-	uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
-
-	/* Create VM */
-	vm = vm_create(VM_MODE_FLAT48PG,
-		       DEFAULT_GUEST_PHY_PAGES + extra_pg_pages,
-		       O_RDWR);
-
-	/* Setup guest code */
-	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
-
-	/* Setup IRQ Chip */
-	vm_create_irqchip(vm);
-
-	/* Add the first vCPU. */
-	vm_vcpu_add_default(vm, vcpuid, guest_code);
-
-	return vm;
-}
-
-struct kvm_x86_state {
-	struct kvm_vcpu_events events;
-	struct kvm_mp_state mp_state;
-	struct kvm_regs regs;
-	struct kvm_xsave xsave;
-	struct kvm_xcrs xcrs;
-	struct kvm_sregs sregs;
-	struct kvm_debugregs debugregs;
-	union {
-		struct kvm_nested_state nested;
-		char nested_[16384];
-	};
-	struct kvm_msrs msrs;
-};
-
-static int kvm_get_num_msrs(struct kvm_vm *vm)
-{
-	struct kvm_msr_list nmsrs;
-	int r;
-
-	nmsrs.nmsrs = 0;
-	r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, &nmsrs);
-	TEST_ASSERT(r == -1 && errno == E2BIG, "Unexpected result from KVM_GET_MSR_INDEX_LIST probe, r: %i",
-		r);
-
-	return nmsrs.nmsrs;
-}
-
-struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
-{
-	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
-	struct kvm_msr_list *list;
-	struct kvm_x86_state *state;
-	int nmsrs, r, i;
-	static int nested_size = -1;
-
-	if (nested_size == -1) {
-		nested_size = kvm_check_cap(KVM_CAP_NESTED_STATE);
-		TEST_ASSERT(nested_size <= sizeof(state->nested_),
-			    "Nested state size too big, %i > %zi",
-			    nested_size, sizeof(state->nested_));
-	}
-
-	nmsrs = kvm_get_num_msrs(vm);
-	list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
-	list->nmsrs = nmsrs;
-	r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i",
-                r);
-
-	state = malloc(sizeof(*state) + nmsrs * sizeof(state->msrs.entries[0]));
-	r = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, &state->events);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_VCPU_EVENTS, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_GET_MP_STATE, &state->mp_state);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MP_STATE, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_GET_REGS, &state->regs);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_GET_XSAVE, &state->xsave);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XCRS, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_GET_SREGS, &state->sregs);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i",
-                r);
-
-	if (nested_size) {
-		state->nested.size = sizeof(state->nested_);
-		r = ioctl(vcpu->fd, KVM_GET_NESTED_STATE, &state->nested);
-		TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_NESTED_STATE, r: %i",
-			r);
-		TEST_ASSERT(state->nested.size <= nested_size,
-			"Nested state size too big, %i (KVM_CHECK_CAP gave %i)",
-			state->nested.size, nested_size);
-	} else
-		state->nested.size = 0;
-
-	state->msrs.nmsrs = nmsrs;
-	for (i = 0; i < nmsrs; i++)
-		state->msrs.entries[i].index = list->indices[i];
-	r = ioctl(vcpu->fd, KVM_GET_MSRS, &state->msrs);
-        TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed at %x)",
-                r, r == nmsrs ? -1 : list->indices[r]);
-
-	r = ioctl(vcpu->fd, KVM_GET_DEBUGREGS, &state->debugregs);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_DEBUGREGS, r: %i",
-                r);
-
-	free(list);
-	return state;
-}
-
-void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *state)
-{
-	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
-	int r;
-
-	if (state->nested.size) {
-		r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested);
-		TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i",
-			r);
-	}
-
-	r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XCRS, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_SET_MSRS, &state->msrs);
-        TEST_ASSERT(r == state->msrs.nmsrs, "Unexpected result from KVM_SET_MSRS, r: %i (failed at %x)",
-                r, r == state->msrs.nmsrs ? -1 : state->msrs.entries[r].index);
-
-	r = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, &state->events);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_VCPU_EVENTS, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_SET_MP_STATE, &state->mp_state);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_MP_STATE, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_SET_DEBUGREGS, &state->debugregs);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_DEBUGREGS, r: %i",
-                r);
-
-	r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs);
-        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i",
-                r);
-}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
new file mode 100644
index 000000000000..79c2c5c203c0
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -0,0 +1,888 @@
+/*
+ * tools/testing/selftests/kvm/lib/x86_64/processor.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
+
+/* Minimum physical address used for virtual translation tables. */
+#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
+
+/* Virtual translation table structure declarations */
+struct pageMapL4Entry {
+	uint64_t present:1;
+	uint64_t writable:1;
+	uint64_t user:1;
+	uint64_t write_through:1;
+	uint64_t cache_disable:1;
+	uint64_t accessed:1;
+	uint64_t ignored_06:1;
+	uint64_t page_size:1;
+	uint64_t ignored_11_08:4;
+	uint64_t address:40;
+	uint64_t ignored_62_52:11;
+	uint64_t execute_disable:1;
+};
+
+struct pageDirectoryPointerEntry {
+	uint64_t present:1;
+	uint64_t writable:1;
+	uint64_t user:1;
+	uint64_t write_through:1;
+	uint64_t cache_disable:1;
+	uint64_t accessed:1;
+	uint64_t ignored_06:1;
+	uint64_t page_size:1;
+	uint64_t ignored_11_08:4;
+	uint64_t address:40;
+	uint64_t ignored_62_52:11;
+	uint64_t execute_disable:1;
+};
+
+struct pageDirectoryEntry {
+	uint64_t present:1;
+	uint64_t writable:1;
+	uint64_t user:1;
+	uint64_t write_through:1;
+	uint64_t cache_disable:1;
+	uint64_t accessed:1;
+	uint64_t ignored_06:1;
+	uint64_t page_size:1;
+	uint64_t ignored_11_08:4;
+	uint64_t address:40;
+	uint64_t ignored_62_52:11;
+	uint64_t execute_disable:1;
+};
+
+struct pageTableEntry {
+	uint64_t present:1;
+	uint64_t writable:1;
+	uint64_t user:1;
+	uint64_t write_through:1;
+	uint64_t cache_disable:1;
+	uint64_t accessed:1;
+	uint64_t dirty:1;
+	uint64_t reserved_07:1;
+	uint64_t global:1;
+	uint64_t ignored_11_09:3;
+	uint64_t address:40;
+	uint64_t ignored_62_52:11;
+	uint64_t execute_disable:1;
+};
+
+/* Register Dump
+ *
+ * Input Args:
+ *   indent - Left margin indent amount
+ *   regs - register
+ *
+ * Output Args:
+ *   stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the state of the registers given by regs, to the FILE stream
+ * given by steam.
+ */
+void regs_dump(FILE *stream, struct kvm_regs *regs,
+	       uint8_t indent)
+{
+	fprintf(stream, "%*srax: 0x%.16llx rbx: 0x%.16llx "
+		"rcx: 0x%.16llx rdx: 0x%.16llx\n",
+		indent, "",
+		regs->rax, regs->rbx, regs->rcx, regs->rdx);
+	fprintf(stream, "%*srsi: 0x%.16llx rdi: 0x%.16llx "
+		"rsp: 0x%.16llx rbp: 0x%.16llx\n",
+		indent, "",
+		regs->rsi, regs->rdi, regs->rsp, regs->rbp);
+	fprintf(stream, "%*sr8:  0x%.16llx r9:  0x%.16llx "
+		"r10: 0x%.16llx r11: 0x%.16llx\n",
+		indent, "",
+		regs->r8, regs->r9, regs->r10, regs->r11);
+	fprintf(stream, "%*sr12: 0x%.16llx r13: 0x%.16llx "
+		"r14: 0x%.16llx r15: 0x%.16llx\n",
+		indent, "",
+		regs->r12, regs->r13, regs->r14, regs->r15);
+	fprintf(stream, "%*srip: 0x%.16llx rfl: 0x%.16llx\n",
+		indent, "",
+		regs->rip, regs->rflags);
+}
+
+/* Segment Dump
+ *
+ * Input Args:
+ *   indent - Left margin indent amount
+ *   segment - KVM segment
+ *
+ * Output Args:
+ *   stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the state of the KVM segment given by segment, to the FILE stream
+ * given by steam.
+ */
+static void segment_dump(FILE *stream, struct kvm_segment *segment,
+			 uint8_t indent)
+{
+	fprintf(stream, "%*sbase: 0x%.16llx limit: 0x%.8x "
+		"selector: 0x%.4x type: 0x%.2x\n",
+		indent, "", segment->base, segment->limit,
+		segment->selector, segment->type);
+	fprintf(stream, "%*spresent: 0x%.2x dpl: 0x%.2x "
+		"db: 0x%.2x s: 0x%.2x l: 0x%.2x\n",
+		indent, "", segment->present, segment->dpl,
+		segment->db, segment->s, segment->l);
+	fprintf(stream, "%*sg: 0x%.2x avl: 0x%.2x "
+		"unusable: 0x%.2x padding: 0x%.2x\n",
+		indent, "", segment->g, segment->avl,
+		segment->unusable, segment->padding);
+}
+
+/* dtable Dump
+ *
+ * Input Args:
+ *   indent - Left margin indent amount
+ *   dtable - KVM dtable
+ *
+ * Output Args:
+ *   stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the state of the KVM dtable given by dtable, to the FILE stream
+ * given by steam.
+ */
+static void dtable_dump(FILE *stream, struct kvm_dtable *dtable,
+			uint8_t indent)
+{
+	fprintf(stream, "%*sbase: 0x%.16llx limit: 0x%.4x "
+		"padding: 0x%.4x 0x%.4x 0x%.4x\n",
+		indent, "", dtable->base, dtable->limit,
+		dtable->padding[0], dtable->padding[1], dtable->padding[2]);
+}
+
+/* System Register Dump
+ *
+ * Input Args:
+ *   indent - Left margin indent amount
+ *   sregs - System registers
+ *
+ * Output Args:
+ *   stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the state of the system registers given by sregs, to the FILE stream
+ * given by steam.
+ */
+void sregs_dump(FILE *stream, struct kvm_sregs *sregs,
+		uint8_t indent)
+{
+	unsigned int i;
+
+	fprintf(stream, "%*scs:\n", indent, "");
+	segment_dump(stream, &sregs->cs, indent + 2);
+	fprintf(stream, "%*sds:\n", indent, "");
+	segment_dump(stream, &sregs->ds, indent + 2);
+	fprintf(stream, "%*ses:\n", indent, "");
+	segment_dump(stream, &sregs->es, indent + 2);
+	fprintf(stream, "%*sfs:\n", indent, "");
+	segment_dump(stream, &sregs->fs, indent + 2);
+	fprintf(stream, "%*sgs:\n", indent, "");
+	segment_dump(stream, &sregs->gs, indent + 2);
+	fprintf(stream, "%*sss:\n", indent, "");
+	segment_dump(stream, &sregs->ss, indent + 2);
+	fprintf(stream, "%*str:\n", indent, "");
+	segment_dump(stream, &sregs->tr, indent + 2);
+	fprintf(stream, "%*sldt:\n", indent, "");
+	segment_dump(stream, &sregs->ldt, indent + 2);
+
+	fprintf(stream, "%*sgdt:\n", indent, "");
+	dtable_dump(stream, &sregs->gdt, indent + 2);
+	fprintf(stream, "%*sidt:\n", indent, "");
+	dtable_dump(stream, &sregs->idt, indent + 2);
+
+	fprintf(stream, "%*scr0: 0x%.16llx cr2: 0x%.16llx "
+		"cr3: 0x%.16llx cr4: 0x%.16llx\n",
+		indent, "",
+		sregs->cr0, sregs->cr2, sregs->cr3, sregs->cr4);
+	fprintf(stream, "%*scr8: 0x%.16llx efer: 0x%.16llx "
+		"apic_base: 0x%.16llx\n",
+		indent, "",
+		sregs->cr8, sregs->efer, sregs->apic_base);
+
+	fprintf(stream, "%*sinterrupt_bitmap:\n", indent, "");
+	for (i = 0; i < (KVM_NR_INTERRUPTS + 63) / 64; i++) {
+		fprintf(stream, "%*s%.16llx\n", indent + 2, "",
+			sregs->interrupt_bitmap[i]);
+	}
+}
+
+void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
+{
+	int rc;
+
+	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+
+	/* If needed, create page map l4 table. */
+	if (!vm->pgd_created) {
+		vm_paddr_t paddr = vm_phy_page_alloc(vm,
+			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+		vm->pgd = paddr;
+		vm->pgd_created = true;
+	}
+}
+
+/* VM Virtual Page Map
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vaddr - VM Virtual Address
+ *   paddr - VM Physical Address
+ *   pgd_memslot - Memory region slot for new virtual translation tables
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Within the VM given by vm, creates a virtual translation for the page
+ * starting at vaddr to the page starting at paddr.
+ */
+void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+	uint32_t pgd_memslot)
+{
+	uint16_t index[4];
+	struct pageMapL4Entry *pml4e;
+
+	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+
+	TEST_ASSERT((vaddr % vm->page_size) == 0,
+		"Virtual address not on page boundary,\n"
+		"  vaddr: 0x%lx vm->page_size: 0x%x",
+		vaddr, vm->page_size);
+	TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
+		(vaddr >> vm->page_shift)),
+		"Invalid virtual address, vaddr: 0x%lx",
+		vaddr);
+	TEST_ASSERT((paddr % vm->page_size) == 0,
+		"Physical address not on page boundary,\n"
+		"  paddr: 0x%lx vm->page_size: 0x%x",
+		paddr, vm->page_size);
+	TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
+		"Physical address beyond beyond maximum supported,\n"
+		"  paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+		paddr, vm->max_gfn, vm->page_size);
+
+	index[0] = (vaddr >> 12) & 0x1ffu;
+	index[1] = (vaddr >> 21) & 0x1ffu;
+	index[2] = (vaddr >> 30) & 0x1ffu;
+	index[3] = (vaddr >> 39) & 0x1ffu;
+
+	/* Allocate page directory pointer table if not present. */
+	pml4e = addr_gpa2hva(vm, vm->pgd);
+	if (!pml4e[index[3]].present) {
+		pml4e[index[3]].address = vm_phy_page_alloc(vm,
+			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
+			>> vm->page_shift;
+		pml4e[index[3]].writable = true;
+		pml4e[index[3]].present = true;
+	}
+
+	/* Allocate page directory table if not present. */
+	struct pageDirectoryPointerEntry *pdpe;
+	pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
+	if (!pdpe[index[2]].present) {
+		pdpe[index[2]].address = vm_phy_page_alloc(vm,
+			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
+			>> vm->page_shift;
+		pdpe[index[2]].writable = true;
+		pdpe[index[2]].present = true;
+	}
+
+	/* Allocate page table if not present. */
+	struct pageDirectoryEntry *pde;
+	pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
+	if (!pde[index[1]].present) {
+		pde[index[1]].address = vm_phy_page_alloc(vm,
+			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
+			>> vm->page_shift;
+		pde[index[1]].writable = true;
+		pde[index[1]].present = true;
+	}
+
+	/* Fill in page table entry. */
+	struct pageTableEntry *pte;
+	pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
+	pte[index[0]].address = paddr >> vm->page_shift;
+	pte[index[0]].writable = true;
+	pte[index[0]].present = 1;
+}
+
+/* Virtual Translation Tables Dump
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   indent - Left margin indent amount
+ *
+ * Output Args:
+ *   stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps to the FILE stream given by stream, the contents of all the
+ * virtual translation tables for the VM given by vm.
+ */
+void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
+{
+	struct pageMapL4Entry *pml4e, *pml4e_start;
+	struct pageDirectoryPointerEntry *pdpe, *pdpe_start;
+	struct pageDirectoryEntry *pde, *pde_start;
+	struct pageTableEntry *pte, *pte_start;
+
+	if (!vm->pgd_created)
+		return;
+
+	fprintf(stream, "%*s                                          "
+		"                no\n", indent, "");
+	fprintf(stream, "%*s      index hvaddr         gpaddr         "
+		"addr         w exec dirty\n",
+		indent, "");
+	pml4e_start = (struct pageMapL4Entry *) addr_gpa2hva(vm,
+		vm->pgd);
+	for (uint16_t n1 = 0; n1 <= 0x1ffu; n1++) {
+		pml4e = &pml4e_start[n1];
+		if (!pml4e->present)
+			continue;
+		fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10lx %u "
+			" %u\n",
+			indent, "",
+			pml4e - pml4e_start, pml4e,
+			addr_hva2gpa(vm, pml4e), (uint64_t) pml4e->address,
+			pml4e->writable, pml4e->execute_disable);
+
+		pdpe_start = addr_gpa2hva(vm, pml4e->address
+			* vm->page_size);
+		for (uint16_t n2 = 0; n2 <= 0x1ffu; n2++) {
+			pdpe = &pdpe_start[n2];
+			if (!pdpe->present)
+				continue;
+			fprintf(stream, "%*spdpe  0x%-3zx %p 0x%-12lx 0x%-10lx "
+				"%u  %u\n",
+				indent, "",
+				pdpe - pdpe_start, pdpe,
+				addr_hva2gpa(vm, pdpe),
+				(uint64_t) pdpe->address, pdpe->writable,
+				pdpe->execute_disable);
+
+			pde_start = addr_gpa2hva(vm,
+				pdpe->address * vm->page_size);
+			for (uint16_t n3 = 0; n3 <= 0x1ffu; n3++) {
+				pde = &pde_start[n3];
+				if (!pde->present)
+					continue;
+				fprintf(stream, "%*spde   0x%-3zx %p "
+					"0x%-12lx 0x%-10lx %u  %u\n",
+					indent, "", pde - pde_start, pde,
+					addr_hva2gpa(vm, pde),
+					(uint64_t) pde->address, pde->writable,
+					pde->execute_disable);
+
+				pte_start = addr_gpa2hva(vm,
+					pde->address * vm->page_size);
+				for (uint16_t n4 = 0; n4 <= 0x1ffu; n4++) {
+					pte = &pte_start[n4];
+					if (!pte->present)
+						continue;
+					fprintf(stream, "%*spte   0x%-3zx %p "
+						"0x%-12lx 0x%-10lx %u  %u "
+						"    %u    0x%-10lx\n",
+						indent, "",
+						pte - pte_start, pte,
+						addr_hva2gpa(vm, pte),
+						(uint64_t) pte->address,
+						pte->writable,
+						pte->execute_disable,
+						pte->dirty,
+						((uint64_t) n1 << 27)
+							| ((uint64_t) n2 << 18)
+							| ((uint64_t) n3 << 9)
+							| ((uint64_t) n4));
+				}
+			}
+		}
+	}
+}
+
+/* Set Unusable Segment
+ *
+ * Input Args: None
+ *
+ * Output Args:
+ *   segp - Pointer to segment register
+ *
+ * Return: None
+ *
+ * Sets the segment register pointed to by segp to an unusable state.
+ */
+static void kvm_seg_set_unusable(struct kvm_segment *segp)
+{
+	memset(segp, 0, sizeof(*segp));
+	segp->unusable = true;
+}
+
+static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp)
+{
+	void *gdt = addr_gva2hva(vm, vm->gdt);
+	struct desc64 *desc = gdt + (segp->selector >> 3) * 8;
+
+	desc->limit0 = segp->limit & 0xFFFF;
+	desc->base0 = segp->base & 0xFFFF;
+	desc->base1 = segp->base >> 16;
+	desc->s = segp->s;
+	desc->type = segp->type;
+	desc->dpl = segp->dpl;
+	desc->p = segp->present;
+	desc->limit1 = segp->limit >> 16;
+	desc->l = segp->l;
+	desc->db = segp->db;
+	desc->g = segp->g;
+	desc->base2 = segp->base >> 24;
+	if (!segp->s)
+		desc->base3 = segp->base >> 32;
+}
+
+
+/* Set Long Mode Flat Kernel Code Segment
+ *
+ * Input Args:
+ *   vm - VM whose GDT is being filled, or NULL to only write segp
+ *   selector - selector value
+ *
+ * Output Args:
+ *   segp - Pointer to KVM segment
+ *
+ * Return: None
+ *
+ * Sets up the KVM segment pointed to by segp, to be a code segment
+ * with the selector value given by selector.
+ */
+static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector,
+	struct kvm_segment *segp)
+{
+	memset(segp, 0, sizeof(*segp));
+	segp->selector = selector;
+	segp->limit = 0xFFFFFFFFu;
+	segp->s = 0x1; /* kTypeCodeData */
+	segp->type = 0x08 | 0x01 | 0x02; /* kFlagCode | kFlagCodeAccessed
+					  * | kFlagCodeReadable
+					  */
+	segp->g = true;
+	segp->l = true;
+	segp->present = 1;
+	if (vm)
+		kvm_seg_fill_gdt_64bit(vm, segp);
+}
+
+/* Set Long Mode Flat Kernel Data Segment
+ *
+ * Input Args:
+ *   vm - VM whose GDT is being filled, or NULL to only write segp
+ *   selector - selector value
+ *
+ * Output Args:
+ *   segp - Pointer to KVM segment
+ *
+ * Return: None
+ *
+ * Sets up the KVM segment pointed to by segp, to be a data segment
+ * with the selector value given by selector.
+ */
+static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector,
+	struct kvm_segment *segp)
+{
+	memset(segp, 0, sizeof(*segp));
+	segp->selector = selector;
+	segp->limit = 0xFFFFFFFFu;
+	segp->s = 0x1; /* kTypeCodeData */
+	segp->type = 0x00 | 0x01 | 0x02; /* kFlagData | kFlagDataAccessed
+					  * | kFlagDataWritable
+					  */
+	segp->g = true;
+	segp->present = true;
+	if (vm)
+		kvm_seg_fill_gdt_64bit(vm, segp);
+}
+
+/* Address Guest Virtual to Guest Physical
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   gpa - VM virtual address
+ *
+ * Output Args: None
+ *
+ * Return:
+ *   Equivalent VM physical address
+ *
+ * Translates the VM virtual address given by gva to a VM physical
+ * address and then locates the memory region containing the VM
+ * physical address, within the VM given by vm.  When found, the host
+ * virtual address providing the memory to the vm physical address is returned.
+ * A TEST_ASSERT failure occurs if no region containing translated
+ * VM virtual address exists.
+ */
+vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	uint16_t index[4];
+	struct pageMapL4Entry *pml4e;
+	struct pageDirectoryPointerEntry *pdpe;
+	struct pageDirectoryEntry *pde;
+	struct pageTableEntry *pte;
+	void *hva;
+
+	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+
+	index[0] = (gva >> 12) & 0x1ffu;
+	index[1] = (gva >> 21) & 0x1ffu;
+	index[2] = (gva >> 30) & 0x1ffu;
+	index[3] = (gva >> 39) & 0x1ffu;
+
+	if (!vm->pgd_created)
+		goto unmapped_gva;
+	pml4e = addr_gpa2hva(vm, vm->pgd);
+	if (!pml4e[index[3]].present)
+		goto unmapped_gva;
+
+	pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
+	if (!pdpe[index[2]].present)
+		goto unmapped_gva;
+
+	pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
+	if (!pde[index[1]].present)
+		goto unmapped_gva;
+
+	pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
+	if (!pte[index[0]].present)
+		goto unmapped_gva;
+
+	return (pte[index[0]].address * vm->page_size) + (gva & 0xfffu);
+
+unmapped_gva:
+	TEST_ASSERT(false, "No mapping for vm virtual address, "
+		    "gva: 0x%lx", gva);
+}
+
+static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt, int gdt_memslot,
+			  int pgd_memslot)
+{
+	if (!vm->gdt)
+		vm->gdt = vm_vaddr_alloc(vm, getpagesize(),
+			KVM_UTIL_MIN_VADDR, gdt_memslot, pgd_memslot);
+
+	dt->base = vm->gdt;
+	dt->limit = getpagesize();
+}
+
+static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp,
+				int selector, int gdt_memslot,
+				int pgd_memslot)
+{
+	if (!vm->tss)
+		vm->tss = vm_vaddr_alloc(vm, getpagesize(),
+			KVM_UTIL_MIN_VADDR, gdt_memslot, pgd_memslot);
+
+	memset(segp, 0, sizeof(*segp));
+	segp->base = vm->tss;
+	segp->limit = 0x67;
+	segp->selector = selector;
+	segp->type = 0xb;
+	segp->present = 1;
+	kvm_seg_fill_gdt_64bit(vm, segp);
+}
+
+void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
+{
+	struct kvm_sregs sregs;
+
+	/* Set mode specific system register values. */
+	vcpu_sregs_get(vm, vcpuid, &sregs);
+
+	sregs.idt.limit = 0;
+
+	kvm_setup_gdt(vm, &sregs.gdt, gdt_memslot, pgd_memslot);
+
+	switch (vm->mode) {
+	case VM_MODE_FLAT48PG:
+		sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG;
+		sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
+		sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
+
+		kvm_seg_set_unusable(&sregs.ldt);
+		kvm_seg_set_kernel_code_64bit(vm, 0x8, &sregs.cs);
+		kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.ds);
+		kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.es);
+		kvm_setup_tss_64bit(vm, &sregs.tr, 0x18, gdt_memslot, pgd_memslot);
+		break;
+
+	default:
+		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode);
+	}
+
+	sregs.cr3 = vm->pgd;
+	vcpu_sregs_set(vm, vcpuid, &sregs);
+}
+/* Adds a vCPU with reasonable defaults (i.e., a stack)
+ *
+ * Input Args:
+ *   vcpuid - The id of the VCPU to add to the VM.
+ *   guest_code - The vCPU's entry point
+ */
+void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
+{
+	struct kvm_mp_state mp_state;
+	struct kvm_regs regs;
+	vm_vaddr_t stack_vaddr;
+	stack_vaddr = vm_vaddr_alloc(vm, DEFAULT_STACK_PGS * getpagesize(),
+				     DEFAULT_GUEST_STACK_VADDR_MIN, 0, 0);
+
+	/* Create VCPU */
+	vm_vcpu_add(vm, vcpuid, 0, 0);
+
+	/* Setup guest general purpose registers */
+	vcpu_regs_get(vm, vcpuid, &regs);
+	regs.rflags = regs.rflags | 0x2;
+	regs.rsp = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize());
+	regs.rip = (unsigned long) guest_code;
+	vcpu_regs_set(vm, vcpuid, &regs);
+
+	/* Setup the MP state */
+	mp_state.mp_state = 0;
+	vcpu_set_mp_state(vm, vcpuid, &mp_state);
+}
+
+/* VM VCPU CPUID Set
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU id
+ *   cpuid - The CPUID values to set.
+ *
+ * Output Args: None
+ *
+ * Return: void
+ *
+ * Set the VCPU's CPUID.
+ */
+void vcpu_set_cpuid(struct kvm_vm *vm,
+		uint32_t vcpuid, struct kvm_cpuid2 *cpuid)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	int rc;
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+	rc = ioctl(vcpu->fd, KVM_SET_CPUID2, cpuid);
+	TEST_ASSERT(rc == 0, "KVM_SET_CPUID2 failed, rc: %i errno: %i",
+		    rc, errno);
+
+}
+/* Create a VM with reasonable defaults
+ *
+ * Input Args:
+ *   vcpuid - The id of the single VCPU to add to the VM.
+ *   extra_mem_pages - The size of extra memories to add (this will
+ *                     decide how much extra space we will need to
+ *                     setup the page tables using mem slot 0)
+ *   guest_code - The vCPU's entry point
+ *
+ * Output Args: None
+ *
+ * Return:
+ *   Pointer to opaque structure that describes the created VM.
+ */
+struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
+				 void *guest_code)
+{
+	struct kvm_vm *vm;
+	/*
+	 * For x86 the maximum page table size for a memory region
+	 * will be when only 4K pages are used.  In that case the
+	 * total extra size for page tables (for extra N pages) will
+	 * be: N/512+N/512^2+N/512^3+... which is definitely smaller
+	 * than N/512*2.
+	 */
+	uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
+
+	/* Create VM */
+	vm = vm_create(VM_MODE_FLAT48PG,
+		       DEFAULT_GUEST_PHY_PAGES + extra_pg_pages,
+		       O_RDWR);
+
+	/* Setup guest code */
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+
+	/* Setup IRQ Chip */
+	vm_create_irqchip(vm);
+
+	/* Add the first vCPU. */
+	vm_vcpu_add_default(vm, vcpuid, guest_code);
+
+	return vm;
+}
+
+struct kvm_x86_state {
+	struct kvm_vcpu_events events;
+	struct kvm_mp_state mp_state;
+	struct kvm_regs regs;
+	struct kvm_xsave xsave;
+	struct kvm_xcrs xcrs;
+	struct kvm_sregs sregs;
+	struct kvm_debugregs debugregs;
+	union {
+		struct kvm_nested_state nested;
+		char nested_[16384];
+	};
+	struct kvm_msrs msrs;
+};
+
+static int kvm_get_num_msrs(struct kvm_vm *vm)
+{
+	struct kvm_msr_list nmsrs;
+	int r;
+
+	nmsrs.nmsrs = 0;
+	r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, &nmsrs);
+	TEST_ASSERT(r == -1 && errno == E2BIG, "Unexpected result from KVM_GET_MSR_INDEX_LIST probe, r: %i",
+		r);
+
+	return nmsrs.nmsrs;
+}
+
+struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	struct kvm_msr_list *list;
+	struct kvm_x86_state *state;
+	int nmsrs, r, i;
+	static int nested_size = -1;
+
+	if (nested_size == -1) {
+		nested_size = kvm_check_cap(KVM_CAP_NESTED_STATE);
+		TEST_ASSERT(nested_size <= sizeof(state->nested_),
+			    "Nested state size too big, %i > %zi",
+			    nested_size, sizeof(state->nested_));
+	}
+
+	nmsrs = kvm_get_num_msrs(vm);
+	list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+	list->nmsrs = nmsrs;
+	r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i",
+                r);
+
+	state = malloc(sizeof(*state) + nmsrs * sizeof(state->msrs.entries[0]));
+	r = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, &state->events);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_VCPU_EVENTS, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_GET_MP_STATE, &state->mp_state);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MP_STATE, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_GET_REGS, &state->regs);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_GET_XSAVE, &state->xsave);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XCRS, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_GET_SREGS, &state->sregs);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i",
+                r);
+
+	if (nested_size) {
+		state->nested.size = sizeof(state->nested_);
+		r = ioctl(vcpu->fd, KVM_GET_NESTED_STATE, &state->nested);
+		TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_NESTED_STATE, r: %i",
+			r);
+		TEST_ASSERT(state->nested.size <= nested_size,
+			"Nested state size too big, %i (KVM_CHECK_CAP gave %i)",
+			state->nested.size, nested_size);
+	} else
+		state->nested.size = 0;
+
+	state->msrs.nmsrs = nmsrs;
+	for (i = 0; i < nmsrs; i++)
+		state->msrs.entries[i].index = list->indices[i];
+	r = ioctl(vcpu->fd, KVM_GET_MSRS, &state->msrs);
+        TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed at %x)",
+                r, r == nmsrs ? -1 : list->indices[r]);
+
+	r = ioctl(vcpu->fd, KVM_GET_DEBUGREGS, &state->debugregs);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_DEBUGREGS, r: %i",
+                r);
+
+	free(list);
+	return state;
+}
+
+void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *state)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	int r;
+
+	if (state->nested.size) {
+		r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested);
+		TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i",
+			r);
+	}
+
+	r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XCRS, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_SET_MSRS, &state->msrs);
+        TEST_ASSERT(r == state->msrs.nmsrs, "Unexpected result from KVM_SET_MSRS, r: %i (failed at %x)",
+                r, r == state->msrs.nmsrs ? -1 : state->msrs.entries[r].index);
+
+	r = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, &state->events);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_VCPU_EVENTS, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_SET_MP_STATE, &state->mp_state);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_MP_STATE, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_SET_DEBUGREGS, &state->debugregs);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_DEBUGREGS, r: %i",
+                r);
+
+	r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs);
+        TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i",
+                r);
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
new file mode 100644
index 000000000000..d7c401472247
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -0,0 +1,283 @@
+/*
+ * tools/testing/selftests/kvm/lib/x86_64/vmx.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+/* Allocate memory regions for nested VMX tests.
+ *
+ * Input Args:
+ *   vm - The VM to allocate guest-virtual addresses in.
+ *
+ * Output Args:
+ *   p_vmx_gva - The guest virtual address for the struct vmx_pages.
+ *
+ * Return:
+ *   Pointer to structure with the addresses of the VMX areas.
+ */
+struct vmx_pages *
+vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva)
+{
+	vm_vaddr_t vmx_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	struct vmx_pages *vmx = addr_gva2hva(vm, vmx_gva);
+
+	/* Setup of a region of guest memory for the vmxon region. */
+	vmx->vmxon = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	vmx->vmxon_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmxon);
+	vmx->vmxon_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmxon);
+
+	/* Setup of a region of guest memory for a vmcs. */
+	vmx->vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	vmx->vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmcs);
+	vmx->vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmcs);
+
+	/* Setup of a region of guest memory for the MSR bitmap. */
+	vmx->msr = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	vmx->msr_hva = addr_gva2hva(vm, (uintptr_t)vmx->msr);
+	vmx->msr_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->msr);
+	memset(vmx->msr_hva, 0, getpagesize());
+
+	/* Setup of a region of guest memory for the shadow VMCS. */
+	vmx->shadow_vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	vmx->shadow_vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->shadow_vmcs);
+	vmx->shadow_vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->shadow_vmcs);
+
+	/* Setup of a region of guest memory for the VMREAD and VMWRITE bitmaps. */
+	vmx->vmread = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	vmx->vmread_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmread);
+	vmx->vmread_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmread);
+	memset(vmx->vmread_hva, 0, getpagesize());
+
+	vmx->vmwrite = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	vmx->vmwrite_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmwrite);
+	vmx->vmwrite_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmwrite);
+	memset(vmx->vmwrite_hva, 0, getpagesize());
+
+	*p_vmx_gva = vmx_gva;
+	return vmx;
+}
+
+bool prepare_for_vmx_operation(struct vmx_pages *vmx)
+{
+	uint64_t feature_control;
+	uint64_t required;
+	unsigned long cr0;
+	unsigned long cr4;
+
+	/*
+	 * Ensure bits in CR0 and CR4 are valid in VMX operation:
+	 * - Bit X is 1 in _FIXED0: bit X is fixed to 1 in CRx.
+	 * - Bit X is 0 in _FIXED1: bit X is fixed to 0 in CRx.
+	 */
+	__asm__ __volatile__("mov %%cr0, %0" : "=r"(cr0) : : "memory");
+	cr0 &= rdmsr(MSR_IA32_VMX_CR0_FIXED1);
+	cr0 |= rdmsr(MSR_IA32_VMX_CR0_FIXED0);
+	__asm__ __volatile__("mov %0, %%cr0" : : "r"(cr0) : "memory");
+
+	__asm__ __volatile__("mov %%cr4, %0" : "=r"(cr4) : : "memory");
+	cr4 &= rdmsr(MSR_IA32_VMX_CR4_FIXED1);
+	cr4 |= rdmsr(MSR_IA32_VMX_CR4_FIXED0);
+	/* Enable VMX operation */
+	cr4 |= X86_CR4_VMXE;
+	__asm__ __volatile__("mov %0, %%cr4" : : "r"(cr4) : "memory");
+
+	/*
+	 * Configure IA32_FEATURE_CONTROL MSR to allow VMXON:
+	 *  Bit 0: Lock bit. If clear, VMXON causes a #GP.
+	 *  Bit 2: Enables VMXON outside of SMX operation. If clear, VMXON
+	 *    outside of SMX causes a #GP.
+	 */
+	required = FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+	required |= FEATURE_CONTROL_LOCKED;
+	feature_control = rdmsr(MSR_IA32_FEATURE_CONTROL);
+	if ((feature_control & required) != required)
+		wrmsr(MSR_IA32_FEATURE_CONTROL, feature_control | required);
+
+	/* Enter VMX root operation. */
+	*(uint32_t *)(vmx->vmxon) = vmcs_revision();
+	if (vmxon(vmx->vmxon_gpa))
+		return false;
+
+	/* Load a VMCS. */
+	*(uint32_t *)(vmx->vmcs) = vmcs_revision();
+	if (vmclear(vmx->vmcs_gpa))
+		return false;
+
+	if (vmptrld(vmx->vmcs_gpa))
+		return false;
+
+	/* Setup shadow VMCS, do not load it yet. */
+	*(uint32_t *)(vmx->shadow_vmcs) = vmcs_revision() | 0x80000000ul;
+	if (vmclear(vmx->shadow_vmcs_gpa))
+		return false;
+
+	return true;
+}
+
+/*
+ * Initialize the control fields to the most basic settings possible.
+ */
+static inline void init_vmcs_control_fields(struct vmx_pages *vmx)
+{
+	vmwrite(VIRTUAL_PROCESSOR_ID, 0);
+	vmwrite(POSTED_INTR_NV, 0);
+
+	vmwrite(PIN_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PINBASED_CTLS));
+	if (!vmwrite(SECONDARY_VM_EXEC_CONTROL, 0))
+		vmwrite(CPU_BASED_VM_EXEC_CONTROL,
+			rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS) | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS);
+	else
+		vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS));
+	vmwrite(EXCEPTION_BITMAP, 0);
+	vmwrite(PAGE_FAULT_ERROR_CODE_MASK, 0);
+	vmwrite(PAGE_FAULT_ERROR_CODE_MATCH, -1); /* Never match */
+	vmwrite(CR3_TARGET_COUNT, 0);
+	vmwrite(VM_EXIT_CONTROLS, rdmsr(MSR_IA32_VMX_EXIT_CTLS) |
+		VM_EXIT_HOST_ADDR_SPACE_SIZE);	  /* 64-bit host */
+	vmwrite(VM_EXIT_MSR_STORE_COUNT, 0);
+	vmwrite(VM_EXIT_MSR_LOAD_COUNT, 0);
+	vmwrite(VM_ENTRY_CONTROLS, rdmsr(MSR_IA32_VMX_ENTRY_CTLS) |
+		VM_ENTRY_IA32E_MODE);		  /* 64-bit guest */
+	vmwrite(VM_ENTRY_MSR_LOAD_COUNT, 0);
+	vmwrite(VM_ENTRY_INTR_INFO_FIELD, 0);
+	vmwrite(TPR_THRESHOLD, 0);
+
+	vmwrite(CR0_GUEST_HOST_MASK, 0);
+	vmwrite(CR4_GUEST_HOST_MASK, 0);
+	vmwrite(CR0_READ_SHADOW, get_cr0());
+	vmwrite(CR4_READ_SHADOW, get_cr4());
+
+	vmwrite(MSR_BITMAP, vmx->msr_gpa);
+	vmwrite(VMREAD_BITMAP, vmx->vmread_gpa);
+	vmwrite(VMWRITE_BITMAP, vmx->vmwrite_gpa);
+}
+
+/*
+ * Initialize the host state fields based on the current host state, with
+ * the exception of HOST_RSP and HOST_RIP, which should be set by vmlaunch
+ * or vmresume.
+ */
+static inline void init_vmcs_host_state(void)
+{
+	uint32_t exit_controls = vmreadz(VM_EXIT_CONTROLS);
+
+	vmwrite(HOST_ES_SELECTOR, get_es());
+	vmwrite(HOST_CS_SELECTOR, get_cs());
+	vmwrite(HOST_SS_SELECTOR, get_ss());
+	vmwrite(HOST_DS_SELECTOR, get_ds());
+	vmwrite(HOST_FS_SELECTOR, get_fs());
+	vmwrite(HOST_GS_SELECTOR, get_gs());
+	vmwrite(HOST_TR_SELECTOR, get_tr());
+
+	if (exit_controls & VM_EXIT_LOAD_IA32_PAT)
+		vmwrite(HOST_IA32_PAT, rdmsr(MSR_IA32_CR_PAT));
+	if (exit_controls & VM_EXIT_LOAD_IA32_EFER)
+		vmwrite(HOST_IA32_EFER, rdmsr(MSR_EFER));
+	if (exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+		vmwrite(HOST_IA32_PERF_GLOBAL_CTRL,
+			rdmsr(MSR_CORE_PERF_GLOBAL_CTRL));
+
+	vmwrite(HOST_IA32_SYSENTER_CS, rdmsr(MSR_IA32_SYSENTER_CS));
+
+	vmwrite(HOST_CR0, get_cr0());
+	vmwrite(HOST_CR3, get_cr3());
+	vmwrite(HOST_CR4, get_cr4());
+	vmwrite(HOST_FS_BASE, rdmsr(MSR_FS_BASE));
+	vmwrite(HOST_GS_BASE, rdmsr(MSR_GS_BASE));
+	vmwrite(HOST_TR_BASE,
+		get_desc64_base((struct desc64 *)(get_gdt_base() + get_tr())));
+	vmwrite(HOST_GDTR_BASE, get_gdt_base());
+	vmwrite(HOST_IDTR_BASE, get_idt_base());
+	vmwrite(HOST_IA32_SYSENTER_ESP, rdmsr(MSR_IA32_SYSENTER_ESP));
+	vmwrite(HOST_IA32_SYSENTER_EIP, rdmsr(MSR_IA32_SYSENTER_EIP));
+}
+
+/*
+ * Initialize the guest state fields essentially as a clone of
+ * the host state fields. Some host state fields have fixed
+ * values, and we set the corresponding guest state fields accordingly.
+ */
+static inline void init_vmcs_guest_state(void *rip, void *rsp)
+{
+	vmwrite(GUEST_ES_SELECTOR, vmreadz(HOST_ES_SELECTOR));
+	vmwrite(GUEST_CS_SELECTOR, vmreadz(HOST_CS_SELECTOR));
+	vmwrite(GUEST_SS_SELECTOR, vmreadz(HOST_SS_SELECTOR));
+	vmwrite(GUEST_DS_SELECTOR, vmreadz(HOST_DS_SELECTOR));
+	vmwrite(GUEST_FS_SELECTOR, vmreadz(HOST_FS_SELECTOR));
+	vmwrite(GUEST_GS_SELECTOR, vmreadz(HOST_GS_SELECTOR));
+	vmwrite(GUEST_LDTR_SELECTOR, 0);
+	vmwrite(GUEST_TR_SELECTOR, vmreadz(HOST_TR_SELECTOR));
+	vmwrite(GUEST_INTR_STATUS, 0);
+	vmwrite(GUEST_PML_INDEX, 0);
+
+	vmwrite(VMCS_LINK_POINTER, -1ll);
+	vmwrite(GUEST_IA32_DEBUGCTL, 0);
+	vmwrite(GUEST_IA32_PAT, vmreadz(HOST_IA32_PAT));
+	vmwrite(GUEST_IA32_EFER, vmreadz(HOST_IA32_EFER));
+	vmwrite(GUEST_IA32_PERF_GLOBAL_CTRL,
+		vmreadz(HOST_IA32_PERF_GLOBAL_CTRL));
+
+	vmwrite(GUEST_ES_LIMIT, -1);
+	vmwrite(GUEST_CS_LIMIT, -1);
+	vmwrite(GUEST_SS_LIMIT, -1);
+	vmwrite(GUEST_DS_LIMIT, -1);
+	vmwrite(GUEST_FS_LIMIT, -1);
+	vmwrite(GUEST_GS_LIMIT, -1);
+	vmwrite(GUEST_LDTR_LIMIT, -1);
+	vmwrite(GUEST_TR_LIMIT, 0x67);
+	vmwrite(GUEST_GDTR_LIMIT, 0xffff);
+	vmwrite(GUEST_IDTR_LIMIT, 0xffff);
+	vmwrite(GUEST_ES_AR_BYTES,
+		vmreadz(GUEST_ES_SELECTOR) == 0 ? 0x10000 : 0xc093);
+	vmwrite(GUEST_CS_AR_BYTES, 0xa09b);
+	vmwrite(GUEST_SS_AR_BYTES, 0xc093);
+	vmwrite(GUEST_DS_AR_BYTES,
+		vmreadz(GUEST_DS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+	vmwrite(GUEST_FS_AR_BYTES,
+		vmreadz(GUEST_FS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+	vmwrite(GUEST_GS_AR_BYTES,
+		vmreadz(GUEST_GS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+	vmwrite(GUEST_LDTR_AR_BYTES, 0x10000);
+	vmwrite(GUEST_TR_AR_BYTES, 0x8b);
+	vmwrite(GUEST_INTERRUPTIBILITY_INFO, 0);
+	vmwrite(GUEST_ACTIVITY_STATE, 0);
+	vmwrite(GUEST_SYSENTER_CS, vmreadz(HOST_IA32_SYSENTER_CS));
+	vmwrite(VMX_PREEMPTION_TIMER_VALUE, 0);
+
+	vmwrite(GUEST_CR0, vmreadz(HOST_CR0));
+	vmwrite(GUEST_CR3, vmreadz(HOST_CR3));
+	vmwrite(GUEST_CR4, vmreadz(HOST_CR4));
+	vmwrite(GUEST_ES_BASE, 0);
+	vmwrite(GUEST_CS_BASE, 0);
+	vmwrite(GUEST_SS_BASE, 0);
+	vmwrite(GUEST_DS_BASE, 0);
+	vmwrite(GUEST_FS_BASE, vmreadz(HOST_FS_BASE));
+	vmwrite(GUEST_GS_BASE, vmreadz(HOST_GS_BASE));
+	vmwrite(GUEST_LDTR_BASE, 0);
+	vmwrite(GUEST_TR_BASE, vmreadz(HOST_TR_BASE));
+	vmwrite(GUEST_GDTR_BASE, vmreadz(HOST_GDTR_BASE));
+	vmwrite(GUEST_IDTR_BASE, vmreadz(HOST_IDTR_BASE));
+	vmwrite(GUEST_DR7, 0x400);
+	vmwrite(GUEST_RSP, (uint64_t)rsp);
+	vmwrite(GUEST_RIP, (uint64_t)rip);
+	vmwrite(GUEST_RFLAGS, 2);
+	vmwrite(GUEST_PENDING_DBG_EXCEPTIONS, 0);
+	vmwrite(GUEST_SYSENTER_ESP, vmreadz(HOST_IA32_SYSENTER_ESP));
+	vmwrite(GUEST_SYSENTER_EIP, vmreadz(HOST_IA32_SYSENTER_EIP));
+}
+
+void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp)
+{
+	init_vmcs_control_fields(vmx);
+	init_vmcs_host_state();
+	init_vmcs_guest_state(guest_rip, guest_rsp);
+}
diff --git a/tools/testing/selftests/kvm/platform_info_test.c b/tools/testing/selftests/kvm/platform_info_test.c
deleted file mode 100644
index aa6a14331461..000000000000
--- a/tools/testing/selftests/kvm/platform_info_test.c
+++ /dev/null
@@ -1,110 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Test for x86 KVM_CAP_MSR_PLATFORM_INFO
- *
- * Copyright (C) 2018, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- * Verifies expected behavior of controlling guest access to
- * MSR_PLATFORM_INFO.
- */
-
-#define _GNU_SOURCE /* for program_invocation_short_name */
-#include <fcntl.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/ioctl.h>
-
-#include "test_util.h"
-#include "kvm_util.h"
-#include "x86.h"
-
-#define VCPU_ID 0
-#define MSR_PLATFORM_INFO_MAX_TURBO_RATIO 0xff00
-
-static void guest_code(void)
-{
-	uint64_t msr_platform_info;
-
-	for (;;) {
-		msr_platform_info = rdmsr(MSR_PLATFORM_INFO);
-		GUEST_SYNC(msr_platform_info);
-		asm volatile ("inc %r11");
-	}
-}
-
-static void set_msr_platform_info_enabled(struct kvm_vm *vm, bool enable)
-{
-	struct kvm_enable_cap cap = {};
-
-	cap.cap = KVM_CAP_MSR_PLATFORM_INFO;
-	cap.flags = 0;
-	cap.args[0] = (int)enable;
-	vm_enable_cap(vm, &cap);
-}
-
-static void test_msr_platform_info_enabled(struct kvm_vm *vm)
-{
-	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
-	struct ucall uc;
-
-	set_msr_platform_info_enabled(vm, true);
-	vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-			"Exit_reason other than KVM_EXIT_IO: %u (%s),\n",
-			run->exit_reason,
-			exit_reason_str(run->exit_reason));
-	get_ucall(vm, VCPU_ID, &uc);
-	TEST_ASSERT(uc.cmd == UCALL_SYNC,
-			"Received ucall other than UCALL_SYNC: %u\n",
-			ucall);
-	TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) ==
-		MSR_PLATFORM_INFO_MAX_TURBO_RATIO,
-		"Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.",
-		MSR_PLATFORM_INFO_MAX_TURBO_RATIO);
-}
-
-static void test_msr_platform_info_disabled(struct kvm_vm *vm)
-{
-	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
-
-	set_msr_platform_info_enabled(vm, false);
-	vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
-			"Exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n",
-			run->exit_reason,
-			exit_reason_str(run->exit_reason));
-}
-
-int main(int argc, char *argv[])
-{
-	struct kvm_vm *vm;
-	struct kvm_run *state;
-	int rv;
-	uint64_t msr_platform_info;
-
-	/* Tell stdout not to buffer its content */
-	setbuf(stdout, NULL);
-
-	rv = kvm_check_cap(KVM_CAP_MSR_PLATFORM_INFO);
-	if (!rv) {
-		fprintf(stderr,
-			"KVM_CAP_MSR_PLATFORM_INFO not supported, skip test\n");
-		exit(KSFT_SKIP);
-	}
-
-	vm = vm_create_default(VCPU_ID, 0, guest_code);
-
-	msr_platform_info = vcpu_get_msr(vm, VCPU_ID, MSR_PLATFORM_INFO);
-	vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO,
-		msr_platform_info | MSR_PLATFORM_INFO_MAX_TURBO_RATIO);
-	test_msr_platform_info_disabled(vm);
-	test_msr_platform_info_enabled(vm);
-	vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info);
-
-	kvm_vm_free(vm);
-
-	return 0;
-}
diff --git a/tools/testing/selftests/kvm/set_sregs_test.c b/tools/testing/selftests/kvm/set_sregs_test.c
deleted file mode 100644
index 881419d5746e..000000000000
--- a/tools/testing/selftests/kvm/set_sregs_test.c
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * KVM_SET_SREGS tests
- *
- * Copyright (C) 2018, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- * This is a regression test for the bug fixed by the following commit:
- * d3802286fa0f ("kvm: x86: Disallow illegal IA32_APIC_BASE MSR values")
- *
- * That bug allowed a user-mode program that called the KVM_SET_SREGS
- * ioctl to put a VCPU's local APIC into an invalid state.
- *
- */
-#define _GNU_SOURCE /* for program_invocation_short_name */
-#include <fcntl.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/ioctl.h>
-
-#include "test_util.h"
-
-#include "kvm_util.h"
-#include "x86.h"
-
-#define VCPU_ID                  5
-
-int main(int argc, char *argv[])
-{
-	struct kvm_sregs sregs;
-	struct kvm_vm *vm;
-	int rc;
-
-	/* Tell stdout not to buffer its content */
-	setbuf(stdout, NULL);
-
-	/* Create VM */
-	vm = vm_create_default(VCPU_ID, 0, NULL);
-
-	vcpu_sregs_get(vm, VCPU_ID, &sregs);
-	sregs.apic_base = 1 << 10;
-	rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs);
-	TEST_ASSERT(rc, "Set IA32_APIC_BASE to %llx (invalid)",
-		    sregs.apic_base);
-	sregs.apic_base = 1 << 11;
-	rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs);
-	TEST_ASSERT(!rc, "Couldn't set IA32_APIC_BASE to %llx (valid)",
-		    sregs.apic_base);
-
-	kvm_vm_free(vm);
-
-	return 0;
-}
diff --git a/tools/testing/selftests/kvm/state_test.c b/tools/testing/selftests/kvm/state_test.c
deleted file mode 100644
index cdf82735d6e7..000000000000
--- a/tools/testing/selftests/kvm/state_test.c
+++ /dev/null
@@ -1,197 +0,0 @@
-/*
- * KVM_GET/SET_* tests
- *
- * Copyright (C) 2018, Red Hat, Inc.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- * Tests for vCPU state save/restore, including nested guest state.
- */
-#define _GNU_SOURCE /* for program_invocation_short_name */
-#include <fcntl.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/ioctl.h>
-
-#include "test_util.h"
-
-#include "kvm_util.h"
-#include "x86.h"
-#include "vmx.h"
-
-#define VCPU_ID		5
-
-static bool have_nested_state;
-
-void l2_guest_code(void)
-{
-	GUEST_SYNC(5);
-
-        /* Exit to L1 */
-	vmcall();
-
-	/* L1 has now set up a shadow VMCS for us.  */
-	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
-	GUEST_SYNC(9);
-	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
-	GUEST_ASSERT(!vmwrite(GUEST_RIP, 0xc0fffee));
-	GUEST_SYNC(10);
-	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0fffee);
-	GUEST_ASSERT(!vmwrite(GUEST_RIP, 0xc0ffffee));
-	GUEST_SYNC(11);
-
-	/* Done, exit to L1 and never come back.  */
-	vmcall();
-}
-
-void l1_guest_code(struct vmx_pages *vmx_pages)
-{
-#define L2_GUEST_STACK_SIZE 64
-        unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
-
-	GUEST_ASSERT(vmx_pages->vmcs_gpa);
-	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
-	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
-
-	GUEST_SYNC(3);
-	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
-
-	prepare_vmcs(vmx_pages, l2_guest_code,
-		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
-
-	GUEST_SYNC(4);
-	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
-	GUEST_ASSERT(!vmlaunch());
-	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
-
-	/* Check that the launched state is preserved.  */
-	GUEST_ASSERT(vmlaunch());
-
-	GUEST_ASSERT(!vmresume());
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
-
-	GUEST_SYNC(6);
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
-
-	GUEST_ASSERT(!vmresume());
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
-
-	vmwrite(GUEST_RIP, vmreadz(GUEST_RIP) + 3);
-
-	vmwrite(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS);
-	vmwrite(VMCS_LINK_POINTER, vmx_pages->shadow_vmcs_gpa);
-
-	GUEST_ASSERT(!vmptrld(vmx_pages->shadow_vmcs_gpa));
-	GUEST_ASSERT(vmlaunch());
-	GUEST_SYNC(7);
-	GUEST_ASSERT(vmlaunch());
-	GUEST_ASSERT(vmresume());
-
-	vmwrite(GUEST_RIP, 0xc0ffee);
-	GUEST_SYNC(8);
-	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
-
-	GUEST_ASSERT(!vmptrld(vmx_pages->vmcs_gpa));
-	GUEST_ASSERT(!vmresume());
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
-
-	GUEST_ASSERT(!vmptrld(vmx_pages->shadow_vmcs_gpa));
-	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffffee);
-	GUEST_ASSERT(vmlaunch());
-	GUEST_ASSERT(vmresume());
-	GUEST_SYNC(12);
-	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffffee);
-	GUEST_ASSERT(vmlaunch());
-	GUEST_ASSERT(vmresume());
-}
-
-void guest_code(struct vmx_pages *vmx_pages)
-{
-	GUEST_SYNC(1);
-	GUEST_SYNC(2);
-
-	if (vmx_pages)
-		l1_guest_code(vmx_pages);
-
-	GUEST_DONE();
-}
-
-int main(int argc, char *argv[])
-{
-	struct vmx_pages *vmx_pages = NULL;
-	vm_vaddr_t vmx_pages_gva = 0;
-
-	struct kvm_regs regs1, regs2;
-	struct kvm_vm *vm;
-	struct kvm_run *run;
-	struct kvm_x86_state *state;
-	struct ucall uc;
-	int stage;
-
-	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
-
-	/* Create VM */
-	vm = vm_create_default(VCPU_ID, 0, guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-	run = vcpu_state(vm, VCPU_ID);
-
-	vcpu_regs_get(vm, VCPU_ID, &regs1);
-
-	if (kvm_check_cap(KVM_CAP_NESTED_STATE)) {
-		vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
-		vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
-	} else {
-		printf("will skip nested state checks\n");
-		vcpu_args_set(vm, VCPU_ID, 1, 0);
-	}
-
-	for (stage = 1;; stage++) {
-		_vcpu_run(vm, VCPU_ID);
-		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-			    "Unexpected exit reason: %u (%s),\n",
-			    run->exit_reason,
-			    exit_reason_str(run->exit_reason));
-
-		memset(&regs1, 0, sizeof(regs1));
-		vcpu_regs_get(vm, VCPU_ID, &regs1);
-		switch (get_ucall(vm, VCPU_ID, &uc)) {
-		case UCALL_ABORT:
-			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
-				    __FILE__, uc.args[1]);
-			/* NOT REACHED */
-		case UCALL_SYNC:
-			break;
-		case UCALL_DONE:
-			goto done;
-		default:
-			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
-		}
-
-		/* UCALL_SYNC is handled here.  */
-		TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
-			    uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
-			    stage, (ulong)uc.args[1]);
-
-		state = vcpu_save_state(vm, VCPU_ID);
-		kvm_vm_release(vm);
-
-		/* Restore state in a new VM.  */
-		kvm_vm_restart(vm, O_RDWR);
-		vm_vcpu_add(vm, VCPU_ID, 0, 0);
-		vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-		vcpu_load_state(vm, VCPU_ID, state);
-		run = vcpu_state(vm, VCPU_ID);
-		free(state);
-
-		memset(&regs2, 0, sizeof(regs2));
-		vcpu_regs_get(vm, VCPU_ID, &regs2);
-		TEST_ASSERT(!memcmp(&regs1, &regs2, sizeof(regs2)),
-			    "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx",
-			    (ulong) regs2.rdi, (ulong) regs2.rsi);
-	}
-
-done:
-	kvm_vm_free(vm);
-}
diff --git a/tools/testing/selftests/kvm/sync_regs_test.c b/tools/testing/selftests/kvm/sync_regs_test.c
deleted file mode 100644
index 213343e5dff9..000000000000
--- a/tools/testing/selftests/kvm/sync_regs_test.c
+++ /dev/null
@@ -1,237 +0,0 @@
-/*
- * Test for x86 KVM_CAP_SYNC_REGS
- *
- * Copyright (C) 2018, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- * Verifies expected behavior of x86 KVM_CAP_SYNC_REGS functionality,
- * including requesting an invalid register set, updates to/from values
- * in kvm_run.s.regs when kvm_valid_regs and kvm_dirty_regs are toggled.
- */
-
-#define _GNU_SOURCE /* for program_invocation_short_name */
-#include <fcntl.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/ioctl.h>
-
-#include "test_util.h"
-#include "kvm_util.h"
-#include "x86.h"
-
-#define VCPU_ID 5
-
-void guest_code(void)
-{
-	for (;;) {
-		GUEST_SYNC(0);
-		asm volatile ("inc %r11");
-	}
-}
-
-static void compare_regs(struct kvm_regs *left, struct kvm_regs *right)
-{
-#define REG_COMPARE(reg) \
-	TEST_ASSERT(left->reg == right->reg, \
-		    "Register " #reg \
-		    " values did not match: 0x%llx, 0x%llx\n", \
-		    left->reg, right->reg)
-	REG_COMPARE(rax);
-	REG_COMPARE(rbx);
-	REG_COMPARE(rcx);
-	REG_COMPARE(rdx);
-	REG_COMPARE(rsi);
-	REG_COMPARE(rdi);
-	REG_COMPARE(rsp);
-	REG_COMPARE(rbp);
-	REG_COMPARE(r8);
-	REG_COMPARE(r9);
-	REG_COMPARE(r10);
-	REG_COMPARE(r11);
-	REG_COMPARE(r12);
-	REG_COMPARE(r13);
-	REG_COMPARE(r14);
-	REG_COMPARE(r15);
-	REG_COMPARE(rip);
-	REG_COMPARE(rflags);
-#undef REG_COMPARE
-}
-
-static void compare_sregs(struct kvm_sregs *left, struct kvm_sregs *right)
-{
-}
-
-static void compare_vcpu_events(struct kvm_vcpu_events *left,
-				struct kvm_vcpu_events *right)
-{
-}
-
-#define TEST_SYNC_FIELDS   (KVM_SYNC_X86_REGS|KVM_SYNC_X86_SREGS|KVM_SYNC_X86_EVENTS)
-#define INVALID_SYNC_FIELD 0x80000000
-
-int main(int argc, char *argv[])
-{
-	struct kvm_vm *vm;
-	struct kvm_run *run;
-	struct kvm_regs regs;
-	struct kvm_sregs sregs;
-	struct kvm_vcpu_events events;
-	int rv, cap;
-
-	/* Tell stdout not to buffer its content */
-	setbuf(stdout, NULL);
-
-	cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
-	if ((cap & TEST_SYNC_FIELDS) != TEST_SYNC_FIELDS) {
-		fprintf(stderr, "KVM_CAP_SYNC_REGS not supported, skipping test\n");
-		exit(KSFT_SKIP);
-	}
-	if ((cap & INVALID_SYNC_FIELD) != 0) {
-		fprintf(stderr, "The \"invalid\" field is not invalid, skipping test\n");
-		exit(KSFT_SKIP);
-	}
-
-	/* Create VM */
-	vm = vm_create_default(VCPU_ID, 0, guest_code);
-
-	run = vcpu_state(vm, VCPU_ID);
-
-	/* Request reading invalid register set from VCPU. */
-	run->kvm_valid_regs = INVALID_SYNC_FIELD;
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
-		    rv);
-	vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
-
-	run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
-		    rv);
-	vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
-
-	/* Request setting invalid register set into VCPU. */
-	run->kvm_dirty_regs = INVALID_SYNC_FIELD;
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
-		    rv);
-	vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0;
-
-	run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(rv < 0 && errno == EINVAL,
-		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
-		    rv);
-	vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0;
-
-	/* Request and verify all valid register sets. */
-	/* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */
-	run->kvm_valid_regs = TEST_SYNC_FIELDS;
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-		    "Unexpected exit reason: %u (%s),\n",
-		    run->exit_reason,
-		    exit_reason_str(run->exit_reason));
-
-	vcpu_regs_get(vm, VCPU_ID, &regs);
-	compare_regs(&regs, &run->s.regs.regs);
-
-	vcpu_sregs_get(vm, VCPU_ID, &sregs);
-	compare_sregs(&sregs, &run->s.regs.sregs);
-
-	vcpu_events_get(vm, VCPU_ID, &events);
-	compare_vcpu_events(&events, &run->s.regs.events);
-
-	/* Set and verify various register values. */
-	run->s.regs.regs.r11 = 0xBAD1DEA;
-	run->s.regs.sregs.apic_base = 1 << 11;
-	/* TODO run->s.regs.events.XYZ = ABC; */
-
-	run->kvm_valid_regs = TEST_SYNC_FIELDS;
-	run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS;
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-		    "Unexpected exit reason: %u (%s),\n",
-		    run->exit_reason,
-		    exit_reason_str(run->exit_reason));
-	TEST_ASSERT(run->s.regs.regs.r11 == 0xBAD1DEA + 1,
-		    "r11 sync regs value incorrect 0x%llx.",
-		    run->s.regs.regs.r11);
-	TEST_ASSERT(run->s.regs.sregs.apic_base == 1 << 11,
-		    "apic_base sync regs value incorrect 0x%llx.",
-		    run->s.regs.sregs.apic_base);
-
-	vcpu_regs_get(vm, VCPU_ID, &regs);
-	compare_regs(&regs, &run->s.regs.regs);
-
-	vcpu_sregs_get(vm, VCPU_ID, &sregs);
-	compare_sregs(&sregs, &run->s.regs.sregs);
-
-	vcpu_events_get(vm, VCPU_ID, &events);
-	compare_vcpu_events(&events, &run->s.regs.events);
-
-	/* Clear kvm_dirty_regs bits, verify new s.regs values are
-	 * overwritten with existing guest values.
-	 */
-	run->kvm_valid_regs = TEST_SYNC_FIELDS;
-	run->kvm_dirty_regs = 0;
-	run->s.regs.regs.r11 = 0xDEADBEEF;
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-		    "Unexpected exit reason: %u (%s),\n",
-		    run->exit_reason,
-		    exit_reason_str(run->exit_reason));
-	TEST_ASSERT(run->s.regs.regs.r11 != 0xDEADBEEF,
-		    "r11 sync regs value incorrect 0x%llx.",
-		    run->s.regs.regs.r11);
-
-	/* Clear kvm_valid_regs bits and kvm_dirty_bits.
-	 * Verify s.regs values are not overwritten with existing guest values
-	 * and that guest values are not overwritten with kvm_sync_regs values.
-	 */
-	run->kvm_valid_regs = 0;
-	run->kvm_dirty_regs = 0;
-	run->s.regs.regs.r11 = 0xAAAA;
-	regs.r11 = 0xBAC0;
-	vcpu_regs_set(vm, VCPU_ID, &regs);
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-		    "Unexpected exit reason: %u (%s),\n",
-		    run->exit_reason,
-		    exit_reason_str(run->exit_reason));
-	TEST_ASSERT(run->s.regs.regs.r11 == 0xAAAA,
-		    "r11 sync regs value incorrect 0x%llx.",
-		    run->s.regs.regs.r11);
-	vcpu_regs_get(vm, VCPU_ID, &regs);
-	TEST_ASSERT(regs.r11 == 0xBAC0 + 1,
-		    "r11 guest value incorrect 0x%llx.",
-		    regs.r11);
-
-	/* Clear kvm_valid_regs bits. Verify s.regs values are not overwritten
-	 * with existing guest values but that guest values are overwritten
-	 * with kvm_sync_regs values.
-	 */
-	run->kvm_valid_regs = 0;
-	run->kvm_dirty_regs = TEST_SYNC_FIELDS;
-	run->s.regs.regs.r11 = 0xBBBB;
-	rv = _vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-		    "Unexpected exit reason: %u (%s),\n",
-		    run->exit_reason,
-		    exit_reason_str(run->exit_reason));
-	TEST_ASSERT(run->s.regs.regs.r11 == 0xBBBB,
-		    "r11 sync regs value incorrect 0x%llx.",
-		    run->s.regs.regs.r11);
-	vcpu_regs_get(vm, VCPU_ID, &regs);
-	TEST_ASSERT(regs.r11 == 0xBBBB + 1,
-		    "r11 guest value incorrect 0x%llx.",
-		    regs.r11);
-
-	kvm_vm_free(vm);
-
-	return 0;
-}
diff --git a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
deleted file mode 100644
index 8d487c78796a..000000000000
--- a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
+++ /dev/null
@@ -1,174 +0,0 @@
-/*
- * gtests/tests/vmx_tsc_adjust_test.c
- *
- * Copyright (C) 2018, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- *
- * IA32_TSC_ADJUST test
- *
- * According to the SDM, "if an execution of WRMSR to the
- * IA32_TIME_STAMP_COUNTER MSR adds (or subtracts) value X from the TSC,
- * the logical processor also adds (or subtracts) value X from the
- * IA32_TSC_ADJUST MSR.
- *
- * Note that when L1 doesn't intercept writes to IA32_TSC, a
- * WRMSR(IA32_TSC) from L2 sets L1's TSC value, not L2's perceived TSC
- * value.
- *
- * This test verifies that this unusual case is handled correctly.
- */
-
-#include "test_util.h"
-#include "kvm_util.h"
-#include "x86.h"
-#include "vmx.h"
-
-#include <string.h>
-#include <sys/ioctl.h>
-
-#include "../kselftest.h"
-
-#ifndef MSR_IA32_TSC_ADJUST
-#define MSR_IA32_TSC_ADJUST 0x3b
-#endif
-
-#define PAGE_SIZE	4096
-#define VCPU_ID		5
-
-#define TSC_ADJUST_VALUE (1ll << 32)
-#define TSC_OFFSET_VALUE -(1ll << 48)
-
-enum {
-	PORT_ABORT = 0x1000,
-	PORT_REPORT,
-	PORT_DONE,
-};
-
-enum {
-	VMXON_PAGE = 0,
-	VMCS_PAGE,
-	MSR_BITMAP_PAGE,
-
-	NUM_VMX_PAGES,
-};
-
-struct kvm_single_msr {
-	struct kvm_msrs header;
-	struct kvm_msr_entry entry;
-} __attribute__((packed));
-
-/* The virtual machine object. */
-static struct kvm_vm *vm;
-
-static void check_ia32_tsc_adjust(int64_t max)
-{
-	int64_t adjust;
-
-	adjust = rdmsr(MSR_IA32_TSC_ADJUST);
-	GUEST_SYNC(adjust);
-	GUEST_ASSERT(adjust <= max);
-}
-
-static void l2_guest_code(void)
-{
-	uint64_t l1_tsc = rdtsc() - TSC_OFFSET_VALUE;
-
-	wrmsr(MSR_IA32_TSC, l1_tsc - TSC_ADJUST_VALUE);
-	check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
-
-	/* Exit to L1 */
-	__asm__ __volatile__("vmcall");
-}
-
-static void l1_guest_code(struct vmx_pages *vmx_pages)
-{
-#define L2_GUEST_STACK_SIZE 64
-	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
-	uint32_t control;
-	uintptr_t save_cr3;
-
-	GUEST_ASSERT(rdtsc() < TSC_ADJUST_VALUE);
-	wrmsr(MSR_IA32_TSC, rdtsc() - TSC_ADJUST_VALUE);
-	check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
-
-	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
-
-	/* Prepare the VMCS for L2 execution. */
-	prepare_vmcs(vmx_pages, l2_guest_code,
-		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
-	control = vmreadz(CPU_BASED_VM_EXEC_CONTROL);
-	control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETING;
-	vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
-	vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE);
-
-	/* Jump into L2.  First, test failure to load guest CR3.  */
-	save_cr3 = vmreadz(GUEST_CR3);
-	vmwrite(GUEST_CR3, -1ull);
-	GUEST_ASSERT(!vmlaunch());
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) ==
-		     (EXIT_REASON_FAILED_VMENTRY | EXIT_REASON_INVALID_STATE));
-	check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
-	vmwrite(GUEST_CR3, save_cr3);
-
-	GUEST_ASSERT(!vmlaunch());
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
-
-	check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
-
-	GUEST_DONE();
-}
-
-void report(int64_t val)
-{
-	printf("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n",
-	       val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE);
-}
-
-int main(int argc, char *argv[])
-{
-	struct vmx_pages *vmx_pages;
-	vm_vaddr_t vmx_pages_gva;
-	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
-
-	if (!(entry->ecx & CPUID_VMX)) {
-		fprintf(stderr, "nested VMX not enabled, skipping test\n");
-		exit(KSFT_SKIP);
-	}
-
-	vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-
-	/* Allocate VMX pages and shared descriptors (vmx_pages). */
-	vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
-	vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
-
-	for (;;) {
-		volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
-		struct ucall uc;
-
-		vcpu_run(vm, VCPU_ID);
-		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-			    "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
-			    run->exit_reason,
-			    exit_reason_str(run->exit_reason));
-
-		switch (get_ucall(vm, VCPU_ID, &uc)) {
-		case UCALL_ABORT:
-			TEST_ASSERT(false, "%s", (const char *)uc.args[0]);
-			/* NOT REACHED */
-		case UCALL_SYNC:
-			report(uc.args[1]);
-			break;
-		case UCALL_DONE:
-			goto done;
-		default:
-			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
-		}
-	}
-
-	kvm_vm_free(vm);
-done:
-	return 0;
-}
diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
new file mode 100644
index 000000000000..d503a51fad30
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * CR4 and CPUID sync test
+ *
+ * Copyright 2018, Red Hat, Inc. and/or its affiliates.
+ *
+ * Author:
+ *   Wei Huang <wei@redhat.com>
+ */
+
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+#include "processor.h"
+
+#define X86_FEATURE_XSAVE	(1<<26)
+#define X86_FEATURE_OSXSAVE	(1<<27)
+#define VCPU_ID			1
+
+static inline bool cr4_cpuid_is_sync(void)
+{
+	int func, subfunc;
+	uint32_t eax, ebx, ecx, edx;
+	uint64_t cr4;
+
+	func = 0x1;
+	subfunc = 0x0;
+	__asm__ __volatile__("cpuid"
+			     : "=a"(eax), "=b"(ebx), "=c"(ecx), "=d"(edx)
+			     : "a"(func), "c"(subfunc));
+
+	cr4 = get_cr4();
+
+	return (!!(ecx & X86_FEATURE_OSXSAVE)) == (!!(cr4 & X86_CR4_OSXSAVE));
+}
+
+static void guest_code(void)
+{
+	uint64_t cr4;
+
+	/* turn on CR4.OSXSAVE */
+	cr4 = get_cr4();
+	cr4 |= X86_CR4_OSXSAVE;
+	set_cr4(cr4);
+
+	/* verify CR4.OSXSAVE == CPUID.OSXSAVE */
+	GUEST_ASSERT(cr4_cpuid_is_sync());
+
+	/* notify hypervisor to change CR4 */
+	GUEST_SYNC(0);
+
+	/* check again */
+	GUEST_ASSERT(cr4_cpuid_is_sync());
+
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_run *run;
+	struct kvm_vm *vm;
+	struct kvm_sregs sregs;
+	struct kvm_cpuid_entry2 *entry;
+	struct ucall uc;
+	int rc;
+
+	entry = kvm_get_supported_cpuid_entry(1);
+	if (!(entry->ecx & X86_FEATURE_XSAVE)) {
+		printf("XSAVE feature not supported, skipping test\n");
+		return 0;
+	}
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+	run = vcpu_state(vm, VCPU_ID);
+
+	while (1) {
+		rc = _vcpu_run(vm, VCPU_ID);
+
+		if (run->exit_reason == KVM_EXIT_IO) {
+			switch (get_ucall(vm, VCPU_ID, &uc)) {
+			case UCALL_SYNC:
+				/* emulate hypervisor clearing CR4.OSXSAVE */
+				vcpu_sregs_get(vm, VCPU_ID, &sregs);
+				sregs.cr4 &= ~X86_CR4_OSXSAVE;
+				vcpu_sregs_set(vm, VCPU_ID, &sregs);
+				break;
+			case UCALL_ABORT:
+				TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
+				break;
+			case UCALL_DONE:
+				goto done;
+			default:
+				TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+			}
+		}
+	}
+
+	kvm_vm_free(vm);
+
+done:
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/dirty_log_test.c
new file mode 100644
index 000000000000..7cf3e4ae6046
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/dirty_log_test.c
@@ -0,0 +1,307 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM dirty page logging test
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <time.h>
+#include <pthread.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+
+#define  DEBUG                 printf
+
+#define  VCPU_ID                        1
+/* The memory slot index to track dirty pages */
+#define  TEST_MEM_SLOT_INDEX            1
+/*
+ * GPA offset of the testing memory slot. Must be bigger than the
+ * default vm mem slot, which is DEFAULT_GUEST_PHY_PAGES.
+ */
+#define  TEST_MEM_OFFSET                (1ULL << 30) /* 1G */
+/* Size of the testing memory slot */
+#define  TEST_MEM_PAGES                 (1ULL << 18) /* 1G for 4K pages */
+/* How many pages to dirty for each guest loop */
+#define  TEST_PAGES_PER_LOOP            1024
+/* How many host loops to run (one KVM_GET_DIRTY_LOG for each loop) */
+#define  TEST_HOST_LOOP_N               32
+/* Interval for each host loop (ms) */
+#define  TEST_HOST_LOOP_INTERVAL        10
+
+/*
+ * Guest variables.  We use these variables to share data between host
+ * and guest.  There are two copies of the variables, one in host memory
+ * (which is unused) and one in guest memory.  When the host wants to
+ * access these variables, it needs to call addr_gva2hva() to access the
+ * guest copy.
+ */
+uint64_t guest_random_array[TEST_PAGES_PER_LOOP];
+uint64_t guest_iteration;
+uint64_t guest_page_size;
+
+/*
+ * Writes to the first byte of a random page within the testing memory
+ * region continuously.
+ */
+void guest_code(void)
+{
+	int i = 0;
+	uint64_t volatile *array = guest_random_array;
+	uint64_t volatile *guest_addr;
+
+	while (true) {
+		for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
+			/*
+			 * Write to the first 8 bytes of a random page
+			 * on the testing memory region.
+			 */
+			guest_addr = (uint64_t *)
+			    (TEST_MEM_OFFSET +
+			     (array[i] % TEST_MEM_PAGES) * guest_page_size);
+			*guest_addr = guest_iteration;
+		}
+		/* Tell the host that we need more random numbers */
+		GUEST_SYNC(1);
+	}
+}
+
+/*
+ * Host variables.  These variables should only be used by the host
+ * rather than the guest.
+ */
+bool host_quit;
+
+/* Points to the test VM memory region on which we track dirty logs */
+void *host_test_mem;
+
+/* For statistics only */
+uint64_t host_dirty_count;
+uint64_t host_clear_count;
+uint64_t host_track_next_count;
+
+/*
+ * We use this bitmap to track some pages that should have its dirty
+ * bit set in the _next_ iteration.  For example, if we detected the
+ * page value changed to current iteration but at the same time the
+ * page bit is cleared in the latest bitmap, then the system must
+ * report that write in the next get dirty log call.
+ */
+unsigned long *host_bmap_track;
+
+void generate_random_array(uint64_t *guest_array, uint64_t size)
+{
+	uint64_t i;
+
+	for (i = 0; i < size; i++) {
+		guest_array[i] = random();
+	}
+}
+
+void *vcpu_worker(void *data)
+{
+	int ret;
+	uint64_t loops, *guest_array, pages_count = 0;
+	struct kvm_vm *vm = data;
+	struct kvm_run *run;
+	struct ucall uc;
+
+	run = vcpu_state(vm, VCPU_ID);
+
+	/* Retrieve the guest random array pointer and cache it */
+	guest_array = addr_gva2hva(vm, (vm_vaddr_t)guest_random_array);
+
+	DEBUG("VCPU starts\n");
+
+	generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
+
+	while (!READ_ONCE(host_quit)) {
+		/* Let the guest to dirty these random pages */
+		ret = _vcpu_run(vm, VCPU_ID);
+		if (run->exit_reason == KVM_EXIT_IO &&
+		    get_ucall(vm, VCPU_ID, &uc) == UCALL_SYNC) {
+			pages_count += TEST_PAGES_PER_LOOP;
+			generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
+		} else {
+			TEST_ASSERT(false,
+				    "Invalid guest sync status: "
+				    "exit_reason=%s\n",
+				    exit_reason_str(run->exit_reason));
+		}
+	}
+
+	DEBUG("VCPU exits, dirtied %"PRIu64" pages\n", pages_count);
+
+	return NULL;
+}
+
+void vm_dirty_log_verify(unsigned long *bmap, uint64_t iteration)
+{
+	uint64_t page;
+	uint64_t volatile *value_ptr;
+
+	for (page = 0; page < TEST_MEM_PAGES; page++) {
+		value_ptr = host_test_mem + page * getpagesize();
+
+		/* If this is a special page that we were tracking... */
+		if (test_and_clear_bit(page, host_bmap_track)) {
+			host_track_next_count++;
+			TEST_ASSERT(test_bit(page, bmap),
+				    "Page %"PRIu64" should have its dirty bit "
+				    "set in this iteration but it is missing",
+				    page);
+		}
+
+		if (test_bit(page, bmap)) {
+			host_dirty_count++;
+			/*
+			 * If the bit is set, the value written onto
+			 * the corresponding page should be either the
+			 * previous iteration number or the current one.
+			 */
+			TEST_ASSERT(*value_ptr == iteration ||
+				    *value_ptr == iteration - 1,
+				    "Set page %"PRIu64" value %"PRIu64
+				    " incorrect (iteration=%"PRIu64")",
+				    page, *value_ptr, iteration);
+		} else {
+			host_clear_count++;
+			/*
+			 * If cleared, the value written can be any
+			 * value smaller or equals to the iteration
+			 * number.  Note that the value can be exactly
+			 * (iteration-1) if that write can happen
+			 * like this:
+			 *
+			 * (1) increase loop count to "iteration-1"
+			 * (2) write to page P happens (with value
+			 *     "iteration-1")
+			 * (3) get dirty log for "iteration-1"; we'll
+			 *     see that page P bit is set (dirtied),
+			 *     and not set the bit in host_bmap_track
+			 * (4) increase loop count to "iteration"
+			 *     (which is current iteration)
+			 * (5) get dirty log for current iteration,
+			 *     we'll see that page P is cleared, with
+			 *     value "iteration-1".
+			 */
+			TEST_ASSERT(*value_ptr <= iteration,
+				    "Clear page %"PRIu64" value %"PRIu64
+				    " incorrect (iteration=%"PRIu64")",
+				    page, *value_ptr, iteration);
+			if (*value_ptr == iteration) {
+				/*
+				 * This page is _just_ modified; it
+				 * should report its dirtyness in the
+				 * next run
+				 */
+				set_bit(page, host_bmap_track);
+			}
+		}
+	}
+}
+
+void help(char *name)
+{
+	puts("");
+	printf("usage: %s [-i iterations] [-I interval] [-h]\n", name);
+	puts("");
+	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
+	       TEST_HOST_LOOP_N);
+	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
+	       TEST_HOST_LOOP_INTERVAL);
+	puts("");
+	exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+	pthread_t vcpu_thread;
+	struct kvm_vm *vm;
+	uint64_t volatile *psize, *iteration;
+	unsigned long *bmap, iterations = TEST_HOST_LOOP_N,
+	    interval = TEST_HOST_LOOP_INTERVAL;
+	int opt;
+
+	while ((opt = getopt(argc, argv, "hi:I:")) != -1) {
+		switch (opt) {
+		case 'i':
+			iterations = strtol(optarg, NULL, 10);
+			break;
+		case 'I':
+			interval = strtol(optarg, NULL, 10);
+			break;
+		case 'h':
+		default:
+			help(argv[0]);
+			break;
+		}
+	}
+
+	TEST_ASSERT(iterations > 2, "Iteration must be bigger than zero\n");
+	TEST_ASSERT(interval > 0, "Interval must be bigger than zero");
+
+	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
+	      iterations, interval);
+
+	srandom(time(0));
+
+	bmap = bitmap_alloc(TEST_MEM_PAGES);
+	host_bmap_track = bitmap_alloc(TEST_MEM_PAGES);
+
+	vm = vm_create_default(VCPU_ID, TEST_MEM_PAGES, guest_code);
+
+	/* Add an extra memory slot for testing dirty logging */
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    TEST_MEM_OFFSET,
+				    TEST_MEM_SLOT_INDEX,
+				    TEST_MEM_PAGES,
+				    KVM_MEM_LOG_DIRTY_PAGES);
+	/* Cache the HVA pointer of the region */
+	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)TEST_MEM_OFFSET);
+
+	/* Do 1:1 mapping for the dirty track memory slot */
+	virt_map(vm, TEST_MEM_OFFSET, TEST_MEM_OFFSET,
+		 TEST_MEM_PAGES * getpagesize(), 0);
+
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+	/* Tell the guest about the page size on the system */
+	psize = addr_gva2hva(vm, (vm_vaddr_t)&guest_page_size);
+	*psize = getpagesize();
+
+	/* Start the iterations */
+	iteration = addr_gva2hva(vm, (vm_vaddr_t)&guest_iteration);
+	*iteration = 1;
+
+	/* Start dirtying pages */
+	pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
+
+	while (*iteration < iterations) {
+		/* Give the vcpu thread some time to dirty some pages */
+		usleep(interval * 1000);
+		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
+		vm_dirty_log_verify(bmap, *iteration);
+		(*iteration)++;
+	}
+
+	/* Tell the vcpu thread to quit */
+	host_quit = true;
+	pthread_join(vcpu_thread, NULL);
+
+	DEBUG("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
+	      "track_next (%"PRIu64")\n", host_dirty_count, host_clear_count,
+	      host_track_next_count);
+
+	free(bmap);
+	free(host_bmap_track);
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
new file mode 100644
index 000000000000..eb3e7a838cb4
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test for x86 KVM_CAP_MSR_PLATFORM_INFO
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Verifies expected behavior of controlling guest access to
+ * MSR_PLATFORM_INFO.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define VCPU_ID 0
+#define MSR_PLATFORM_INFO_MAX_TURBO_RATIO 0xff00
+
+static void guest_code(void)
+{
+	uint64_t msr_platform_info;
+
+	for (;;) {
+		msr_platform_info = rdmsr(MSR_PLATFORM_INFO);
+		GUEST_SYNC(msr_platform_info);
+		asm volatile ("inc %r11");
+	}
+}
+
+static void set_msr_platform_info_enabled(struct kvm_vm *vm, bool enable)
+{
+	struct kvm_enable_cap cap = {};
+
+	cap.cap = KVM_CAP_MSR_PLATFORM_INFO;
+	cap.flags = 0;
+	cap.args[0] = (int)enable;
+	vm_enable_cap(vm, &cap);
+}
+
+static void test_msr_platform_info_enabled(struct kvm_vm *vm)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+	struct ucall uc;
+
+	set_msr_platform_info_enabled(vm, true);
+	vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			"Exit_reason other than KVM_EXIT_IO: %u (%s),\n",
+			run->exit_reason,
+			exit_reason_str(run->exit_reason));
+	get_ucall(vm, VCPU_ID, &uc);
+	TEST_ASSERT(uc.cmd == UCALL_SYNC,
+			"Received ucall other than UCALL_SYNC: %u\n",
+			ucall);
+	TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) ==
+		MSR_PLATFORM_INFO_MAX_TURBO_RATIO,
+		"Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.",
+		MSR_PLATFORM_INFO_MAX_TURBO_RATIO);
+}
+
+static void test_msr_platform_info_disabled(struct kvm_vm *vm)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+
+	set_msr_platform_info_enabled(vm, false);
+	vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
+			"Exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n",
+			run->exit_reason,
+			exit_reason_str(run->exit_reason));
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vm *vm;
+	struct kvm_run *state;
+	int rv;
+	uint64_t msr_platform_info;
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	rv = kvm_check_cap(KVM_CAP_MSR_PLATFORM_INFO);
+	if (!rv) {
+		fprintf(stderr,
+			"KVM_CAP_MSR_PLATFORM_INFO not supported, skip test\n");
+		exit(KSFT_SKIP);
+	}
+
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+	msr_platform_info = vcpu_get_msr(vm, VCPU_ID, MSR_PLATFORM_INFO);
+	vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO,
+		msr_platform_info | MSR_PLATFORM_INFO_MAX_TURBO_RATIO);
+	test_msr_platform_info_disabled(vm);
+	test_msr_platform_info_enabled(vm);
+	vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info);
+
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c
new file mode 100644
index 000000000000..35640e8e95bc
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c
@@ -0,0 +1,54 @@
+/*
+ * KVM_SET_SREGS tests
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * This is a regression test for the bug fixed by the following commit:
+ * d3802286fa0f ("kvm: x86: Disallow illegal IA32_APIC_BASE MSR values")
+ *
+ * That bug allowed a user-mode program that called the KVM_SET_SREGS
+ * ioctl to put a VCPU's local APIC into an invalid state.
+ *
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+#include "processor.h"
+
+#define VCPU_ID                  5
+
+int main(int argc, char *argv[])
+{
+	struct kvm_sregs sregs;
+	struct kvm_vm *vm;
+	int rc;
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, NULL);
+
+	vcpu_sregs_get(vm, VCPU_ID, &sregs);
+	sregs.apic_base = 1 << 10;
+	rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs);
+	TEST_ASSERT(rc, "Set IA32_APIC_BASE to %llx (invalid)",
+		    sregs.apic_base);
+	sregs.apic_base = 1 << 11;
+	rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs);
+	TEST_ASSERT(!rc, "Couldn't set IA32_APIC_BASE to %llx (valid)",
+		    sregs.apic_base);
+
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
new file mode 100644
index 000000000000..43df194a7c1e
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -0,0 +1,197 @@
+/*
+ * KVM_GET/SET_* tests
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Tests for vCPU state save/restore, including nested guest state.
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+#define VCPU_ID		5
+
+static bool have_nested_state;
+
+void l2_guest_code(void)
+{
+	GUEST_SYNC(5);
+
+        /* Exit to L1 */
+	vmcall();
+
+	/* L1 has now set up a shadow VMCS for us.  */
+	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
+	GUEST_SYNC(9);
+	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
+	GUEST_ASSERT(!vmwrite(GUEST_RIP, 0xc0fffee));
+	GUEST_SYNC(10);
+	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0fffee);
+	GUEST_ASSERT(!vmwrite(GUEST_RIP, 0xc0ffffee));
+	GUEST_SYNC(11);
+
+	/* Done, exit to L1 and never come back.  */
+	vmcall();
+}
+
+void l1_guest_code(struct vmx_pages *vmx_pages)
+{
+#define L2_GUEST_STACK_SIZE 64
+        unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+	GUEST_ASSERT(vmx_pages->vmcs_gpa);
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
+
+	GUEST_SYNC(3);
+	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
+
+	prepare_vmcs(vmx_pages, l2_guest_code,
+		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	GUEST_SYNC(4);
+	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	/* Check that the launched state is preserved.  */
+	GUEST_ASSERT(vmlaunch());
+
+	GUEST_ASSERT(!vmresume());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	GUEST_SYNC(6);
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	GUEST_ASSERT(!vmresume());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	vmwrite(GUEST_RIP, vmreadz(GUEST_RIP) + 3);
+
+	vmwrite(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS);
+	vmwrite(VMCS_LINK_POINTER, vmx_pages->shadow_vmcs_gpa);
+
+	GUEST_ASSERT(!vmptrld(vmx_pages->shadow_vmcs_gpa));
+	GUEST_ASSERT(vmlaunch());
+	GUEST_SYNC(7);
+	GUEST_ASSERT(vmlaunch());
+	GUEST_ASSERT(vmresume());
+
+	vmwrite(GUEST_RIP, 0xc0ffee);
+	GUEST_SYNC(8);
+	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
+
+	GUEST_ASSERT(!vmptrld(vmx_pages->vmcs_gpa));
+	GUEST_ASSERT(!vmresume());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	GUEST_ASSERT(!vmptrld(vmx_pages->shadow_vmcs_gpa));
+	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffffee);
+	GUEST_ASSERT(vmlaunch());
+	GUEST_ASSERT(vmresume());
+	GUEST_SYNC(12);
+	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffffee);
+	GUEST_ASSERT(vmlaunch());
+	GUEST_ASSERT(vmresume());
+}
+
+void guest_code(struct vmx_pages *vmx_pages)
+{
+	GUEST_SYNC(1);
+	GUEST_SYNC(2);
+
+	if (vmx_pages)
+		l1_guest_code(vmx_pages);
+
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	struct vmx_pages *vmx_pages = NULL;
+	vm_vaddr_t vmx_pages_gva = 0;
+
+	struct kvm_regs regs1, regs2;
+	struct kvm_vm *vm;
+	struct kvm_run *run;
+	struct kvm_x86_state *state;
+	struct ucall uc;
+	int stage;
+
+	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+	run = vcpu_state(vm, VCPU_ID);
+
+	vcpu_regs_get(vm, VCPU_ID, &regs1);
+
+	if (kvm_check_cap(KVM_CAP_NESTED_STATE)) {
+		vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+		vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
+	} else {
+		printf("will skip nested state checks\n");
+		vcpu_args_set(vm, VCPU_ID, 1, 0);
+	}
+
+	for (stage = 1;; stage++) {
+		_vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Unexpected exit reason: %u (%s),\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		memset(&regs1, 0, sizeof(regs1));
+		vcpu_regs_get(vm, VCPU_ID, &regs1);
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
+				    __FILE__, uc.args[1]);
+			/* NOT REACHED */
+		case UCALL_SYNC:
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+		}
+
+		/* UCALL_SYNC is handled here.  */
+		TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+			    uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
+			    stage, (ulong)uc.args[1]);
+
+		state = vcpu_save_state(vm, VCPU_ID);
+		kvm_vm_release(vm);
+
+		/* Restore state in a new VM.  */
+		kvm_vm_restart(vm, O_RDWR);
+		vm_vcpu_add(vm, VCPU_ID, 0, 0);
+		vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+		vcpu_load_state(vm, VCPU_ID, state);
+		run = vcpu_state(vm, VCPU_ID);
+		free(state);
+
+		memset(&regs2, 0, sizeof(regs2));
+		vcpu_regs_get(vm, VCPU_ID, &regs2);
+		TEST_ASSERT(!memcmp(&regs1, &regs2, sizeof(regs2)),
+			    "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx",
+			    (ulong) regs2.rdi, (ulong) regs2.rsi);
+	}
+
+done:
+	kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
new file mode 100644
index 000000000000..c8478ce9ea77
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -0,0 +1,237 @@
+/*
+ * Test for x86 KVM_CAP_SYNC_REGS
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Verifies expected behavior of x86 KVM_CAP_SYNC_REGS functionality,
+ * including requesting an invalid register set, updates to/from values
+ * in kvm_run.s.regs when kvm_valid_regs and kvm_dirty_regs are toggled.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define VCPU_ID 5
+
+void guest_code(void)
+{
+	for (;;) {
+		GUEST_SYNC(0);
+		asm volatile ("inc %r11");
+	}
+}
+
+static void compare_regs(struct kvm_regs *left, struct kvm_regs *right)
+{
+#define REG_COMPARE(reg) \
+	TEST_ASSERT(left->reg == right->reg, \
+		    "Register " #reg \
+		    " values did not match: 0x%llx, 0x%llx\n", \
+		    left->reg, right->reg)
+	REG_COMPARE(rax);
+	REG_COMPARE(rbx);
+	REG_COMPARE(rcx);
+	REG_COMPARE(rdx);
+	REG_COMPARE(rsi);
+	REG_COMPARE(rdi);
+	REG_COMPARE(rsp);
+	REG_COMPARE(rbp);
+	REG_COMPARE(r8);
+	REG_COMPARE(r9);
+	REG_COMPARE(r10);
+	REG_COMPARE(r11);
+	REG_COMPARE(r12);
+	REG_COMPARE(r13);
+	REG_COMPARE(r14);
+	REG_COMPARE(r15);
+	REG_COMPARE(rip);
+	REG_COMPARE(rflags);
+#undef REG_COMPARE
+}
+
+static void compare_sregs(struct kvm_sregs *left, struct kvm_sregs *right)
+{
+}
+
+static void compare_vcpu_events(struct kvm_vcpu_events *left,
+				struct kvm_vcpu_events *right)
+{
+}
+
+#define TEST_SYNC_FIELDS   (KVM_SYNC_X86_REGS|KVM_SYNC_X86_SREGS|KVM_SYNC_X86_EVENTS)
+#define INVALID_SYNC_FIELD 0x80000000
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vm *vm;
+	struct kvm_run *run;
+	struct kvm_regs regs;
+	struct kvm_sregs sregs;
+	struct kvm_vcpu_events events;
+	int rv, cap;
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
+	if ((cap & TEST_SYNC_FIELDS) != TEST_SYNC_FIELDS) {
+		fprintf(stderr, "KVM_CAP_SYNC_REGS not supported, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+	if ((cap & INVALID_SYNC_FIELD) != 0) {
+		fprintf(stderr, "The \"invalid\" field is not invalid, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+	run = vcpu_state(vm, VCPU_ID);
+
+	/* Request reading invalid register set from VCPU. */
+	run->kvm_valid_regs = INVALID_SYNC_FIELD;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(rv < 0 && errno == EINVAL,
+		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+		    rv);
+	vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
+
+	run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(rv < 0 && errno == EINVAL,
+		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+		    rv);
+	vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
+
+	/* Request setting invalid register set into VCPU. */
+	run->kvm_dirty_regs = INVALID_SYNC_FIELD;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(rv < 0 && errno == EINVAL,
+		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+		    rv);
+	vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0;
+
+	run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(rv < 0 && errno == EINVAL,
+		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+		    rv);
+	vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0;
+
+	/* Request and verify all valid register sets. */
+	/* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Unexpected exit reason: %u (%s),\n",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+
+	vcpu_regs_get(vm, VCPU_ID, &regs);
+	compare_regs(&regs, &run->s.regs.regs);
+
+	vcpu_sregs_get(vm, VCPU_ID, &sregs);
+	compare_sregs(&sregs, &run->s.regs.sregs);
+
+	vcpu_events_get(vm, VCPU_ID, &events);
+	compare_vcpu_events(&events, &run->s.regs.events);
+
+	/* Set and verify various register values. */
+	run->s.regs.regs.r11 = 0xBAD1DEA;
+	run->s.regs.sregs.apic_base = 1 << 11;
+	/* TODO run->s.regs.events.XYZ = ABC; */
+
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
+	run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Unexpected exit reason: %u (%s),\n",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+	TEST_ASSERT(run->s.regs.regs.r11 == 0xBAD1DEA + 1,
+		    "r11 sync regs value incorrect 0x%llx.",
+		    run->s.regs.regs.r11);
+	TEST_ASSERT(run->s.regs.sregs.apic_base == 1 << 11,
+		    "apic_base sync regs value incorrect 0x%llx.",
+		    run->s.regs.sregs.apic_base);
+
+	vcpu_regs_get(vm, VCPU_ID, &regs);
+	compare_regs(&regs, &run->s.regs.regs);
+
+	vcpu_sregs_get(vm, VCPU_ID, &sregs);
+	compare_sregs(&sregs, &run->s.regs.sregs);
+
+	vcpu_events_get(vm, VCPU_ID, &events);
+	compare_vcpu_events(&events, &run->s.regs.events);
+
+	/* Clear kvm_dirty_regs bits, verify new s.regs values are
+	 * overwritten with existing guest values.
+	 */
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
+	run->kvm_dirty_regs = 0;
+	run->s.regs.regs.r11 = 0xDEADBEEF;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Unexpected exit reason: %u (%s),\n",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+	TEST_ASSERT(run->s.regs.regs.r11 != 0xDEADBEEF,
+		    "r11 sync regs value incorrect 0x%llx.",
+		    run->s.regs.regs.r11);
+
+	/* Clear kvm_valid_regs bits and kvm_dirty_bits.
+	 * Verify s.regs values are not overwritten with existing guest values
+	 * and that guest values are not overwritten with kvm_sync_regs values.
+	 */
+	run->kvm_valid_regs = 0;
+	run->kvm_dirty_regs = 0;
+	run->s.regs.regs.r11 = 0xAAAA;
+	regs.r11 = 0xBAC0;
+	vcpu_regs_set(vm, VCPU_ID, &regs);
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Unexpected exit reason: %u (%s),\n",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+	TEST_ASSERT(run->s.regs.regs.r11 == 0xAAAA,
+		    "r11 sync regs value incorrect 0x%llx.",
+		    run->s.regs.regs.r11);
+	vcpu_regs_get(vm, VCPU_ID, &regs);
+	TEST_ASSERT(regs.r11 == 0xBAC0 + 1,
+		    "r11 guest value incorrect 0x%llx.",
+		    regs.r11);
+
+	/* Clear kvm_valid_regs bits. Verify s.regs values are not overwritten
+	 * with existing guest values but that guest values are overwritten
+	 * with kvm_sync_regs values.
+	 */
+	run->kvm_valid_regs = 0;
+	run->kvm_dirty_regs = TEST_SYNC_FIELDS;
+	run->s.regs.regs.r11 = 0xBBBB;
+	rv = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Unexpected exit reason: %u (%s),\n",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+	TEST_ASSERT(run->s.regs.regs.r11 == 0xBBBB,
+		    "r11 sync regs value incorrect 0x%llx.",
+		    run->s.regs.regs.r11);
+	vcpu_regs_get(vm, VCPU_ID, &regs);
+	TEST_ASSERT(regs.r11 == 0xBBBB + 1,
+		    "r11 guest value incorrect 0x%llx.",
+		    regs.r11);
+
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
new file mode 100644
index 000000000000..38a91a5f04ac
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
@@ -0,0 +1,174 @@
+/*
+ * vmx_tsc_adjust_test
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ *
+ * IA32_TSC_ADJUST test
+ *
+ * According to the SDM, "if an execution of WRMSR to the
+ * IA32_TIME_STAMP_COUNTER MSR adds (or subtracts) value X from the TSC,
+ * the logical processor also adds (or subtracts) value X from the
+ * IA32_TSC_ADJUST MSR.
+ *
+ * Note that when L1 doesn't intercept writes to IA32_TSC, a
+ * WRMSR(IA32_TSC) from L2 sets L1's TSC value, not L2's perceived TSC
+ * value.
+ *
+ * This test verifies that this unusual case is handled correctly.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "kselftest.h"
+
+#ifndef MSR_IA32_TSC_ADJUST
+#define MSR_IA32_TSC_ADJUST 0x3b
+#endif
+
+#define PAGE_SIZE	4096
+#define VCPU_ID		5
+
+#define TSC_ADJUST_VALUE (1ll << 32)
+#define TSC_OFFSET_VALUE -(1ll << 48)
+
+enum {
+	PORT_ABORT = 0x1000,
+	PORT_REPORT,
+	PORT_DONE,
+};
+
+enum {
+	VMXON_PAGE = 0,
+	VMCS_PAGE,
+	MSR_BITMAP_PAGE,
+
+	NUM_VMX_PAGES,
+};
+
+struct kvm_single_msr {
+	struct kvm_msrs header;
+	struct kvm_msr_entry entry;
+} __attribute__((packed));
+
+/* The virtual machine object. */
+static struct kvm_vm *vm;
+
+static void check_ia32_tsc_adjust(int64_t max)
+{
+	int64_t adjust;
+
+	adjust = rdmsr(MSR_IA32_TSC_ADJUST);
+	GUEST_SYNC(adjust);
+	GUEST_ASSERT(adjust <= max);
+}
+
+static void l2_guest_code(void)
+{
+	uint64_t l1_tsc = rdtsc() - TSC_OFFSET_VALUE;
+
+	wrmsr(MSR_IA32_TSC, l1_tsc - TSC_ADJUST_VALUE);
+	check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
+
+	/* Exit to L1 */
+	__asm__ __volatile__("vmcall");
+}
+
+static void l1_guest_code(struct vmx_pages *vmx_pages)
+{
+#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	uint32_t control;
+	uintptr_t save_cr3;
+
+	GUEST_ASSERT(rdtsc() < TSC_ADJUST_VALUE);
+	wrmsr(MSR_IA32_TSC, rdtsc() - TSC_ADJUST_VALUE);
+	check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
+
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+
+	/* Prepare the VMCS for L2 execution. */
+	prepare_vmcs(vmx_pages, l2_guest_code,
+		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+	control = vmreadz(CPU_BASED_VM_EXEC_CONTROL);
+	control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETING;
+	vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
+	vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE);
+
+	/* Jump into L2.  First, test failure to load guest CR3.  */
+	save_cr3 = vmreadz(GUEST_CR3);
+	vmwrite(GUEST_CR3, -1ull);
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) ==
+		     (EXIT_REASON_FAILED_VMENTRY | EXIT_REASON_INVALID_STATE));
+	check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
+	vmwrite(GUEST_CR3, save_cr3);
+
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
+
+	GUEST_DONE();
+}
+
+void report(int64_t val)
+{
+	printf("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n",
+	       val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE);
+}
+
+int main(int argc, char *argv[])
+{
+	struct vmx_pages *vmx_pages;
+	vm_vaddr_t vmx_pages_gva;
+	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
+
+	if (!(entry->ecx & CPUID_VMX)) {
+		fprintf(stderr, "nested VMX not enabled, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+
+	vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+	/* Allocate VMX pages and shared descriptors (vmx_pages). */
+	vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+	vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
+
+	for (;;) {
+		volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+		struct ucall uc;
+
+		vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "%s", (const char *)uc.args[0]);
+			/* NOT REACHED */
+		case UCALL_SYNC:
+			report(uc.args[1]);
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+		}
+	}
+
+	kvm_vm_free(vm);
+done:
+	return 0;
+}
-- 
cgit v1.2.3


From eea192bfd96db157151d27dd9c5e3e6a50c5d6be Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:27 +0200
Subject: kvm: selftests: add cscope make target

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/Makefile | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 734a60da9776..959be146f789 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -29,7 +29,7 @@ include ../lib.mk
 
 STATIC_LIBS := $(OUTPUT)/libkvm.a
 LIBKVM_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM))
-EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS)
+EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS) cscope.*
 
 x := $(shell mkdir -p $(sort $(dir $(LIBKVM_OBJ))))
 $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c
@@ -41,3 +41,12 @@ $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ)
 all: $(STATIC_LIBS)
 $(TEST_GEN_PROGS): $(STATIC_LIBS)
 $(STATIC_LIBS):| khdr
+
+cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib ..
+cscope:
+	$(RM) cscope.*
+	(find $(include_paths) -name '*.h' \
+		-exec realpath --relative-base=$(PWD) {} \;; \
+	find . -name '*.c' \
+		-exec realpath --relative-base=$(PWD) {} \;) | sort -u > cscope.files
+	cscope -b
-- 
cgit v1.2.3


From eabe7881d264fd8ee074636fe50c8a8af08fedfd Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:28 +0200
Subject: kvm: selftests: tidy up kvm_util

Tidy up kvm-util code: code/comment formatting, remove unused code,
and move x86 specific code out. We also move vcpu_dump() out of
common code, because not all arches (AArch64) have KVM_GET_REGS.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h     |  80 ++--
 .../selftests/kvm/include/x86_64/processor.h       |  20 +-
 tools/testing/selftests/kvm/lib/kvm_util.c         | 438 +++++----------------
 .../testing/selftests/kvm/lib/kvm_util_internal.h  |  22 +-
 tools/testing/selftests/kvm/lib/x86_64/processor.c | 245 ++++++++++++
 .../testing/selftests/kvm/x86_64/dirty_log_test.c  |   1 +
 6 files changed, 407 insertions(+), 399 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 7830c46f27d8..4d5e405ff246 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -17,12 +17,6 @@
 
 #include "sparsebit.h"
 
-/*
- * Memslots can't cover the gfn starting at this gpa otherwise vCPUs can't be
- * created. Only applies to VMs using EPT.
- */
-#define KVM_DEFAULT_IDENTITY_MAP_ADDRESS 0xfffbc000ul
-
 
 /* Callers of kvm_util only have an incomplete/opaque description of the
  * structure kvm_util is using to maintain the state of a VM.
@@ -33,11 +27,11 @@ typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */
 typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
 
 /* Minimum allocated guest virtual and physical addresses */
-#define KVM_UTIL_MIN_VADDR 0x2000
+#define KVM_UTIL_MIN_VADDR		0x2000
 
 #define DEFAULT_GUEST_PHY_PAGES		512
 #define DEFAULT_GUEST_STACK_VADDR_MIN	0xab6000
-#define DEFAULT_STACK_PGS               5
+#define DEFAULT_STACK_PGS		5
 
 enum vm_guest_mode {
 	VM_MODE_FLAT48PG,
@@ -58,15 +52,15 @@ void kvm_vm_restart(struct kvm_vm *vmp, int perm);
 void kvm_vm_release(struct kvm_vm *vmp);
 void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log);
 
-int kvm_memcmp_hva_gva(void *hva,
-	struct kvm_vm *vm, const vm_vaddr_t gva, size_t len);
+int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva,
+		       size_t len);
 
 void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename,
-	uint32_t data_memslot, uint32_t pgd_memslot);
+		     uint32_t data_memslot, uint32_t pgd_memslot);
 
 void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
-void vcpu_dump(FILE *stream, struct kvm_vm *vm,
-	uint32_t vcpuid, uint8_t indent);
+void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid,
+	       uint8_t indent);
 
 void vm_create_irqchip(struct kvm_vm *vm);
 
@@ -75,13 +69,14 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	uint64_t guest_paddr, uint32_t slot, uint64_t npages,
 	uint32_t flags);
 
-void vcpu_ioctl(struct kvm_vm *vm,
-	uint32_t vcpuid, unsigned long ioctl, void *arg);
+void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
+		void *arg);
 void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
 void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
-void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, int gdt_memslot);
+void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot,
+		 int gdt_memslot);
 vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
-	uint32_t data_memslot, uint32_t pgd_memslot);
+			  uint32_t data_memslot, uint32_t pgd_memslot);
 void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 	      size_t size, uint32_t pgd_memslot);
 void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa);
@@ -93,56 +88,33 @@ struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
 int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
-	struct kvm_mp_state *mp_state);
-void vcpu_regs_get(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_regs *regs);
-void vcpu_regs_set(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_regs *regs);
+		       struct kvm_mp_state *mp_state);
+void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
+void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
 void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...);
-void vcpu_sregs_get(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_sregs *sregs);
-void vcpu_sregs_set(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_sregs *sregs);
-int _vcpu_sregs_set(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_sregs *sregs);
+void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid,
+		    struct kvm_sregs *sregs);
+void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
+		    struct kvm_sregs *sregs);
+int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
+		    struct kvm_sregs *sregs);
 void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
-			  struct kvm_vcpu_events *events);
+		     struct kvm_vcpu_events *events);
 void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
-			  struct kvm_vcpu_events *events);
-uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index);
-void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
-	uint64_t msr_value);
+		     struct kvm_vcpu_events *events);
 
 const char *exit_reason_str(unsigned int exit_reason);
 
 void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot);
 void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
-	uint32_t pgd_memslot);
-vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
-	vm_paddr_t paddr_min, uint32_t memslot);
-
-struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
-void vcpu_set_cpuid(
-	struct kvm_vm *vm, uint32_t vcpuid, struct kvm_cpuid2 *cpuid);
-
-struct kvm_cpuid_entry2 *
-kvm_get_supported_cpuid_index(uint32_t function, uint32_t index);
-
-static inline struct kvm_cpuid_entry2 *
-kvm_get_supported_cpuid_entry(uint32_t function)
-{
-	return kvm_get_supported_cpuid_index(function, 0);
-}
+		 uint32_t pgd_memslot);
+vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
+			     uint32_t memslot);
 
 struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_size,
 				 void *guest_code);
 void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code);
 
-typedef void (*vmx_guest_code_t)(vm_vaddr_t vmxon_vaddr,
-				 vm_paddr_t vmxon_paddr,
-				 vm_vaddr_t vmcs_vaddr,
-				 vm_paddr_t vmcs_paddr);
-
 struct kvm_userspace_memory_region *
 kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
 				 uint64_t end);
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index bb76e8db9b2b..e2884c2b81ff 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -305,7 +305,25 @@ static inline unsigned long get_xmm(int n)
 
 struct kvm_x86_state;
 struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid);
-void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *state);
+void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid,
+		     struct kvm_x86_state *state);
+
+struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
+void vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid,
+		    struct kvm_cpuid2 *cpuid);
+
+struct kvm_cpuid_entry2 *
+kvm_get_supported_cpuid_index(uint32_t function, uint32_t index);
+
+static inline struct kvm_cpuid_entry2 *
+kvm_get_supported_cpuid_entry(uint32_t function)
+{
+	return kvm_get_supported_cpuid_index(function, 0);
+}
+
+uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index);
+void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
+	  	  uint64_t msr_value);
 
 /*
  * Basic CPU control in CR0
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 4bd31bf04f53..1a8f8f9e3635 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -16,8 +16,6 @@
 #include <sys/stat.h>
 #include <linux/kernel.h>
 
-#define KVM_DEV_PATH "/dev/kvm"
-
 #define KVM_UTIL_PGS_PER_HUGEPG 512
 #define KVM_UTIL_MIN_PADDR      0x2000
 
@@ -30,7 +28,8 @@ static void *align(void *x, size_t size)
 	return (void *) (((size_t) x + mask) & ~mask);
 }
 
-/* Capability
+/*
+ * Capability
  *
  * Input Args:
  *   cap - Capability
@@ -92,13 +91,13 @@ static void vm_open(struct kvm_vm *vm, int perm)
 	if (vm->kvm_fd < 0)
 		exit(KSFT_SKIP);
 
-	/* Create VM. */
 	vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, NULL);
 	TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, "
 		"rc: %i errno: %i", vm->fd, errno);
 }
 
-/* VM Create
+/*
+ * VM Create
  *
  * Input Args:
  *   mode - VM Mode (e.g. VM_MODE_FLAT48PG)
@@ -121,7 +120,6 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	struct kvm_vm *vm;
 	int kvm_fd;
 
-	/* Allocate memory. */
 	vm = calloc(1, sizeof(*vm));
 	TEST_ASSERT(vm != NULL, "Insufficent Memory");
 
@@ -160,7 +158,8 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	return vm;
 }
 
-/* VM Restart
+/*
+ * VM Restart
  *
  * Input Args:
  *   vm - VM that has been released before
@@ -187,7 +186,8 @@ void kvm_vm_restart(struct kvm_vm *vmp, int perm)
 			    "  rc: %i errno: %i\n"
 			    "  slot: %u flags: 0x%x\n"
 			    "  guest_phys_addr: 0x%lx size: 0x%lx",
-			    ret, errno, region->region.slot, region->region.flags,
+			    ret, errno, region->region.slot,
+			    region->region.flags,
 			    region->region.guest_phys_addr,
 			    region->region.memory_size);
 	}
@@ -203,7 +203,8 @@ void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log)
 		    strerror(-ret));
 }
 
-/* Userspace Memory Region Find
+/*
+ * Userspace Memory Region Find
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -221,8 +222,8 @@ void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log)
  * of the regions is returned.  Null is returned only when no overlapping
  * region exists.
  */
-static struct userspace_mem_region *userspace_mem_region_find(
-	struct kvm_vm *vm, uint64_t start, uint64_t end)
+static struct userspace_mem_region *
+userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end)
 {
 	struct userspace_mem_region *region;
 
@@ -238,7 +239,8 @@ static struct userspace_mem_region *userspace_mem_region_find(
 	return NULL;
 }
 
-/* KVM Userspace Memory Region Find
+/*
+ * KVM Userspace Memory Region Find
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -266,7 +268,8 @@ kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
 	return &region->region;
 }
 
-/* VCPU Find
+/*
+ * VCPU Find
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -281,8 +284,7 @@ kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
  * returns a pointer to it.  Returns NULL if the VM doesn't contain a VCPU
  * for the specified vcpuid.
  */
-struct vcpu *vcpu_find(struct kvm_vm *vm,
-	uint32_t vcpuid)
+struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid)
 {
 	struct vcpu *vcpup;
 
@@ -294,7 +296,8 @@ struct vcpu *vcpu_find(struct kvm_vm *vm,
 	return NULL;
 }
 
-/* VM VCPU Remove
+/*
+ * VM VCPU Remove
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -331,11 +334,9 @@ void kvm_vm_release(struct kvm_vm *vmp)
 {
 	int ret;
 
-	/* Free VCPUs. */
 	while (vmp->vcpu_head)
 		vm_vcpu_rm(vmp, vmp->vcpu_head->id);
 
-	/* Close file descriptor for the VM. */
 	ret = close(vmp->fd);
 	TEST_ASSERT(ret == 0, "Close of vm fd failed,\n"
 		"  vmp->fd: %i rc: %i errno: %i", vmp->fd, ret, errno);
@@ -345,7 +346,8 @@ void kvm_vm_release(struct kvm_vm *vmp)
 		"  vmp->kvm_fd: %i rc: %i errno: %i", vmp->kvm_fd, ret, errno);
 }
 
-/* Destroys and frees the VM pointed to by vmp.
+/*
+ * Destroys and frees the VM pointed to by vmp.
  */
 void kvm_vm_free(struct kvm_vm *vmp)
 {
@@ -384,7 +386,8 @@ void kvm_vm_free(struct kvm_vm *vmp)
 	free(vmp);
 }
 
-/* Memory Compare, host virtual to guest virtual
+/*
+ * Memory Compare, host virtual to guest virtual
  *
  * Input Args:
  *   hva - Starting host virtual address
@@ -406,23 +409,25 @@ void kvm_vm_free(struct kvm_vm *vmp)
  * a length of len, to the guest bytes starting at the guest virtual
  * address given by gva.
  */
-int kvm_memcmp_hva_gva(void *hva,
-	struct kvm_vm *vm, vm_vaddr_t gva, size_t len)
+int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len)
 {
 	size_t amt;
 
-	/* Compare a batch of bytes until either a match is found
+	/*
+	 * Compare a batch of bytes until either a match is found
 	 * or all the bytes have been compared.
 	 */
 	for (uintptr_t offset = 0; offset < len; offset += amt) {
 		uintptr_t ptr1 = (uintptr_t)hva + offset;
 
-		/* Determine host address for guest virtual address
+		/*
+		 * Determine host address for guest virtual address
 		 * at offset.
 		 */
 		uintptr_t ptr2 = (uintptr_t)addr_gva2hva(vm, gva + offset);
 
-		/* Determine amount to compare on this pass.
+		/*
+		 * Determine amount to compare on this pass.
 		 * Don't allow the comparsion to cross a page boundary.
 		 */
 		amt = len - offset;
@@ -434,7 +439,8 @@ int kvm_memcmp_hva_gva(void *hva,
 		assert((ptr1 >> vm->page_shift) == ((ptr1 + amt - 1) >> vm->page_shift));
 		assert((ptr2 >> vm->page_shift) == ((ptr2 + amt - 1) >> vm->page_shift));
 
-		/* Perform the comparison.  If there is a difference
+		/*
+		 * Perform the comparison.  If there is a difference
 		 * return that result to the caller, otherwise need
 		 * to continue on looking for a mismatch.
 		 */
@@ -443,109 +449,15 @@ int kvm_memcmp_hva_gva(void *hva,
 			return ret;
 	}
 
-	/* No mismatch found.  Let the caller know the two memory
+	/*
+	 * No mismatch found.  Let the caller know the two memory
 	 * areas are equal.
 	 */
 	return 0;
 }
 
-/* Allocate an instance of struct kvm_cpuid2
- *
- * Input Args: None
- *
- * Output Args: None
- *
- * Return: A pointer to the allocated struct. The caller is responsible
- * for freeing this struct.
- *
- * Since kvm_cpuid2 uses a 0-length array to allow a the size of the
- * array to be decided at allocation time, allocation is slightly
- * complicated. This function uses a reasonable default length for
- * the array and performs the appropriate allocation.
- */
-static struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
-{
-	struct kvm_cpuid2 *cpuid;
-	int nent = 100;
-	size_t size;
-
-	size = sizeof(*cpuid);
-	size += nent * sizeof(struct kvm_cpuid_entry2);
-	cpuid = malloc(size);
-	if (!cpuid) {
-		perror("malloc");
-		abort();
-	}
-
-	cpuid->nent = nent;
-
-	return cpuid;
-}
-
-/* KVM Supported CPUID Get
- *
- * Input Args: None
- *
- * Output Args:
- *
- * Return: The supported KVM CPUID
- *
- * Get the guest CPUID supported by KVM.
- */
-struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
-{
-	static struct kvm_cpuid2 *cpuid;
-	int ret;
-	int kvm_fd;
-
-	if (cpuid)
-		return cpuid;
-
-	cpuid = allocate_kvm_cpuid2();
-	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
-	if (kvm_fd < 0)
-		exit(KSFT_SKIP);
-
-	ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid);
-	TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n",
-		    ret, errno);
-
-	close(kvm_fd);
-	return cpuid;
-}
-
-/* Locate a cpuid entry.
- *
- * Input Args:
- *   cpuid: The cpuid.
- *   function: The function of the cpuid entry to find.
- *
- * Output Args: None
- *
- * Return: A pointer to the cpuid entry. Never returns NULL.
- */
-struct kvm_cpuid_entry2 *
-kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
-{
-	struct kvm_cpuid2 *cpuid;
-	struct kvm_cpuid_entry2 *entry = NULL;
-	int i;
-
-	cpuid = kvm_get_supported_cpuid();
-	for (i = 0; i < cpuid->nent; i++) {
-		if (cpuid->entries[i].function == function &&
-		    cpuid->entries[i].index == index) {
-			entry = &cpuid->entries[i];
-			break;
-		}
-	}
-
-	TEST_ASSERT(entry, "Guest CPUID entry not found: (EAX=%x, ECX=%x).",
-		    function, index);
-	return entry;
-}
-
-/* VM Userspace Memory Region Add
+/*
+ * VM Userspace Memory Region Add
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -587,7 +499,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 		"  vm->max_gfn: 0x%lx vm->page_size: 0x%x",
 		guest_paddr, npages, vm->max_gfn, vm->page_size);
 
-	/* Confirm a mem region with an overlapping address doesn't
+	/*
+	 * Confirm a mem region with an overlapping address doesn't
 	 * already exist.
 	 */
 	region = (struct userspace_mem_region *) userspace_mem_region_find(
@@ -678,7 +591,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	vm->userspace_mem_region_head = region;
 }
 
-/* Memslot to region
+/*
+ * Memslot to region
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -692,8 +606,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
  *   on error (e.g. currently no memory region using memslot as a KVM
  *   memory slot ID).
  */
-static struct userspace_mem_region *memslot2region(struct kvm_vm *vm,
-	uint32_t memslot)
+static struct userspace_mem_region *
+memslot2region(struct kvm_vm *vm, uint32_t memslot)
 {
 	struct userspace_mem_region *region;
 
@@ -713,7 +627,8 @@ static struct userspace_mem_region *memslot2region(struct kvm_vm *vm,
 	return region;
 }
 
-/* VM Memory Region Flags Set
+/*
+ * VM Memory Region Flags Set
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -731,7 +646,6 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags)
 	int ret;
 	struct userspace_mem_region *region;
 
-	/* Locate memory region. */
 	region = memslot2region(vm, slot);
 
 	region->region.flags = flags;
@@ -743,7 +657,8 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags)
 		ret, errno, slot, flags);
 }
 
-/* VCPU mmap Size
+/*
+ * VCPU mmap Size
  *
  * Input Args: None
  *
@@ -773,7 +688,8 @@ static int vcpu_mmap_sz(void)
 	return ret;
 }
 
-/* VM VCPU Add
+/*
+ * VM VCPU Add
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -786,7 +702,8 @@ static int vcpu_mmap_sz(void)
  * Creates and adds to the VM specified by vm and virtual CPU with
  * the ID given by vcpuid.
  */
-void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, int gdt_memslot)
+void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot,
+		 int gdt_memslot)
 {
 	struct vcpu *vcpu;
 
@@ -824,7 +741,8 @@ void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, int gdt_me
 	vcpu_setup(vm, vcpuid, pgd_memslot, gdt_memslot);
 }
 
-/* VM Virtual Address Unused Gap
+/*
+ * VM Virtual Address Unused Gap
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -844,14 +762,14 @@ void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, int gdt_me
  * sz unallocated bytes >= vaddr_min is available.
  */
 static vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz,
-	vm_vaddr_t vaddr_min)
+				      vm_vaddr_t vaddr_min)
 {
 	uint64_t pages = (sz + vm->page_size - 1) >> vm->page_shift;
 
 	/* Determine lowest permitted virtual page index. */
 	uint64_t pgidx_start = (vaddr_min + vm->page_size - 1) >> vm->page_shift;
 	if ((pgidx_start * vm->page_size) < vaddr_min)
-			goto no_va_found;
+		goto no_va_found;
 
 	/* Loop over section with enough valid virtual page indexes. */
 	if (!sparsebit_is_set_num(vm->vpages_valid,
@@ -910,7 +828,8 @@ va_found:
 	return pgidx_start * vm->page_size;
 }
 
-/* VM Virtual Address Allocate
+/*
+ * VM Virtual Address Allocate
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -931,13 +850,14 @@ va_found:
  * a page.
  */
 vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
-	uint32_t data_memslot, uint32_t pgd_memslot)
+			  uint32_t data_memslot, uint32_t pgd_memslot)
 {
 	uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0);
 
 	virt_pgd_alloc(vm, pgd_memslot);
 
-	/* Find an unused range of virtual page addresses of at least
+	/*
+	 * Find an unused range of virtual page addresses of at least
 	 * pages in length.
 	 */
 	vm_vaddr_t vaddr_start = vm_vaddr_unused_gap(vm, sz, vaddr_min);
@@ -991,7 +911,8 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 	}
 }
 
-/* Address VM Physical to Host Virtual
+/*
+ * Address VM Physical to Host Virtual
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1023,7 +944,8 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
 	return NULL;
 }
 
-/* Address Host Virtual to VM Physical
+/*
+ * Address Host Virtual to VM Physical
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1057,7 +979,8 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva)
 	return -1;
 }
 
-/* VM Create IRQ Chip
+/*
+ * VM Create IRQ Chip
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1079,7 +1002,8 @@ void vm_create_irqchip(struct kvm_vm *vm)
 	vm->has_irqchip = true;
 }
 
-/* VM VCPU State
+/*
+ * VM VCPU State
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1101,7 +1025,8 @@ struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid)
 	return vcpu->state;
 }
 
-/* VM VCPU Run
+/*
+ * VM VCPU Run
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1127,13 +1052,14 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
 	int rc;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
-        do {
+	do {
 		rc = ioctl(vcpu->fd, KVM_RUN, NULL);
 	} while (rc == -1 && errno == EINTR);
 	return rc;
 }
 
-/* VM VCPU Set MP State
+/*
+ * VM VCPU Set MP State
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1148,7 +1074,7 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
  * by mp_state.
  */
 void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
-	struct kvm_mp_state *mp_state)
+		       struct kvm_mp_state *mp_state)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
@@ -1160,7 +1086,8 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
 		"rc: %i errno: %i", ret, errno);
 }
 
-/* VM VCPU Regs Get
+/*
+ * VM VCPU Regs Get
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1174,21 +1101,20 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
  * Obtains the current register state for the VCPU specified by vcpuid
  * and stores it at the location given by regs.
  */
-void vcpu_regs_get(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_regs *regs)
+void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
 
-	/* Get the regs. */
 	ret = ioctl(vcpu->fd, KVM_GET_REGS, regs);
 	TEST_ASSERT(ret == 0, "KVM_GET_REGS failed, rc: %i errno: %i",
 		ret, errno);
 }
 
-/* VM VCPU Regs Set
+/*
+ * VM VCPU Regs Set
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1202,165 +1128,46 @@ void vcpu_regs_get(struct kvm_vm *vm,
  * Sets the regs of the VCPU specified by vcpuid to the values
  * given by regs.
  */
-void vcpu_regs_set(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_regs *regs)
+void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
 
-	/* Set the regs. */
 	ret = ioctl(vcpu->fd, KVM_SET_REGS, regs);
 	TEST_ASSERT(ret == 0, "KVM_SET_REGS failed, rc: %i errno: %i",
 		ret, errno);
 }
 
 void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
-			  struct kvm_vcpu_events *events)
+		     struct kvm_vcpu_events *events)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
 
-	/* Get the regs. */
 	ret = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, events);
 	TEST_ASSERT(ret == 0, "KVM_GET_VCPU_EVENTS, failed, rc: %i errno: %i",
 		ret, errno);
 }
 
 void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
-			  struct kvm_vcpu_events *events)
+		     struct kvm_vcpu_events *events)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
 
-	/* Set the regs. */
 	ret = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, events);
 	TEST_ASSERT(ret == 0, "KVM_SET_VCPU_EVENTS, failed, rc: %i errno: %i",
 		ret, errno);
 }
 
-/* VCPU Get MSR
- *
- * Input Args:
- *   vm - Virtual Machine
- *   vcpuid - VCPU ID
- *   msr_index - Index of MSR
- *
- * Output Args: None
- *
- * Return: On success, value of the MSR. On failure a TEST_ASSERT is produced.
- *
- * Get value of MSR for VCPU.
- */
-uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index)
-{
-	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
-	struct {
-		struct kvm_msrs header;
-		struct kvm_msr_entry entry;
-	} buffer = {};
-	int r;
-
-	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
-	buffer.header.nmsrs = 1;
-	buffer.entry.index = msr_index;
-	r = ioctl(vcpu->fd, KVM_GET_MSRS, &buffer.header);
-	TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n"
-		"  rc: %i errno: %i", r, errno);
-
-	return buffer.entry.data;
-}
-
-/* VCPU Set MSR
- *
- * Input Args:
- *   vm - Virtual Machine
- *   vcpuid - VCPU ID
- *   msr_index - Index of MSR
- *   msr_value - New value of MSR
- *
- * Output Args: None
- *
- * Return: On success, nothing. On failure a TEST_ASSERT is produced.
- *
- * Set value of MSR for VCPU.
- */
-void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
-	uint64_t msr_value)
-{
-	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
-	struct {
-		struct kvm_msrs header;
-		struct kvm_msr_entry entry;
-	} buffer = {};
-	int r;
-
-	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
-	memset(&buffer, 0, sizeof(buffer));
-	buffer.header.nmsrs = 1;
-	buffer.entry.index = msr_index;
-	buffer.entry.data = msr_value;
-	r = ioctl(vcpu->fd, KVM_SET_MSRS, &buffer.header);
-	TEST_ASSERT(r == 1, "KVM_SET_MSRS IOCTL failed,\n"
-		"  rc: %i errno: %i", r, errno);
-}
-
-/* VM VCPU Args Set
- *
- * Input Args:
- *   vm - Virtual Machine
- *   vcpuid - VCPU ID
- *   num - number of arguments
- *   ... - arguments, each of type uint64_t
- *
- * Output Args: None
- *
- * Return: None
- *
- * Sets the first num function input arguments to the values
- * given as variable args.  Each of the variable args is expected to
- * be of type uint64_t.
- */
-void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
-{
-	va_list ap;
-	struct kvm_regs regs;
-
-	TEST_ASSERT(num >= 1 && num <= 6, "Unsupported number of args,\n"
-		    "  num: %u\n",
-		    num);
-
-	va_start(ap, num);
-	vcpu_regs_get(vm, vcpuid, &regs);
-
-	if (num >= 1)
-		regs.rdi = va_arg(ap, uint64_t);
-
-	if (num >= 2)
-		regs.rsi = va_arg(ap, uint64_t);
-
-	if (num >= 3)
-		regs.rdx = va_arg(ap, uint64_t);
-
-	if (num >= 4)
-		regs.rcx = va_arg(ap, uint64_t);
-
-	if (num >= 5)
-		regs.r8 = va_arg(ap, uint64_t);
-
-	if (num >= 6)
-		regs.r9 = va_arg(ap, uint64_t);
-
-	vcpu_regs_set(vm, vcpuid, &regs);
-	va_end(ap);
-}
-
-/* VM VCPU System Regs Get
+/*
+ * VM VCPU System Regs Get
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1374,22 +1181,20 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
  * Obtains the current system register state for the VCPU specified by
  * vcpuid and stores it at the location given by sregs.
  */
-void vcpu_sregs_get(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_sregs *sregs)
+void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
 
-	/* Get the regs. */
-	/* Get the regs. */
 	ret = ioctl(vcpu->fd, KVM_GET_SREGS, sregs);
 	TEST_ASSERT(ret == 0, "KVM_GET_SREGS failed, rc: %i errno: %i",
 		ret, errno);
 }
 
-/* VM VCPU System Regs Set
+/*
+ * VM VCPU System Regs Set
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1403,27 +1208,25 @@ void vcpu_sregs_get(struct kvm_vm *vm,
  * Sets the system regs of the VCPU specified by vcpuid to the values
  * given by sregs.
  */
-void vcpu_sregs_set(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_sregs *sregs)
+void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
 {
 	int ret = _vcpu_sregs_set(vm, vcpuid, sregs);
 	TEST_ASSERT(ret == 0, "KVM_RUN IOCTL failed, "
 		"rc: %i errno: %i", ret, errno);
 }
 
-int _vcpu_sregs_set(struct kvm_vm *vm,
-	uint32_t vcpuid, struct kvm_sregs *sregs)
+int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
 
-	/* Get the regs. */
 	return ioctl(vcpu->fd, KVM_SET_SREGS, sregs);
 }
 
-/* VCPU Ioctl
+/*
+ * VCPU Ioctl
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1435,8 +1238,8 @@ int _vcpu_sregs_set(struct kvm_vm *vm,
  *
  * Issues an arbitrary ioctl on a VCPU fd.
  */
-void vcpu_ioctl(struct kvm_vm *vm,
-	uint32_t vcpuid, unsigned long cmd, void *arg)
+void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid,
+		unsigned long cmd, void *arg)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
@@ -1448,7 +1251,8 @@ void vcpu_ioctl(struct kvm_vm *vm,
 		cmd, ret, errno, strerror(errno));
 }
 
-/* VM Ioctl
+/*
+ * VM Ioctl
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1468,7 +1272,8 @@ void vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
 		cmd, ret, errno, strerror(errno));
 }
 
-/* VM Dump
+/*
+ * VM Dump
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1515,38 +1320,6 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 		vcpu_dump(stream, vm, vcpu->id, indent + 2);
 }
 
-/* VM VCPU Dump
- *
- * Input Args:
- *   vm - Virtual Machine
- *   vcpuid - VCPU ID
- *   indent - Left margin indent amount
- *
- * Output Args:
- *   stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the current state of the VCPU specified by vcpuid, within the VM
- * given by vm, to the FILE stream given by stream.
- */
-void vcpu_dump(FILE *stream, struct kvm_vm *vm,
-	uint32_t vcpuid, uint8_t indent)
-{
-		struct kvm_regs regs;
-		struct kvm_sregs sregs;
-
-		fprintf(stream, "%*scpuid: %u\n", indent, "", vcpuid);
-
-		fprintf(stream, "%*sregs:\n", indent + 2, "");
-		vcpu_regs_get(vm, vcpuid, &regs);
-		regs_dump(stream, &regs, indent + 4);
-
-		fprintf(stream, "%*ssregs:\n", indent + 2, "");
-		vcpu_sregs_get(vm, vcpuid, &sregs);
-		sregs_dump(stream, &sregs, indent + 4);
-}
-
 /* Known KVM exit reasons */
 static struct exit_reason {
 	unsigned int reason;
@@ -1577,7 +1350,8 @@ static struct exit_reason {
 #endif
 };
 
-/* Exit Reason String
+/*
+ * Exit Reason String
  *
  * Input Args:
  *   exit_reason - Exit reason
@@ -1603,7 +1377,8 @@ const char *exit_reason_str(unsigned int exit_reason)
 	return "Unknown";
 }
 
-/* Physical Page Allocate
+/*
+ * Physical Page Allocate
  *
  * Input Args:
  *   vm - Virtual Machine
@@ -1620,8 +1395,8 @@ const char *exit_reason_str(unsigned int exit_reason)
  * and its address is returned.  A TEST_ASSERT failure occurs if no
  * page is available at or above paddr_min.
  */
-vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
-	vm_paddr_t paddr_min, uint32_t memslot)
+vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
+			     uint32_t memslot)
 {
 	struct userspace_mem_region *region;
 	sparsebit_idx_t pg;
@@ -1631,17 +1406,15 @@ vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
 		"  paddr_min: 0x%lx page_size: 0x%x",
 		paddr_min, vm->page_size);
 
-	/* Locate memory region. */
 	region = memslot2region(vm, memslot);
-
-	/* Locate next available physical page at or above paddr_min. */
 	pg = paddr_min >> vm->page_shift;
 
+	/* Locate next available physical page at or above paddr_min. */
 	if (!sparsebit_is_set(region->unused_phy_pages, pg)) {
 		pg = sparsebit_next_set(region->unused_phy_pages, pg);
 		if (pg == 0) {
 			fprintf(stderr, "No guest physical page available, "
-				"paddr_min: 0x%lx page_size: 0x%x memslot: %u",
+				"paddr_min: 0x%lx page_size: 0x%x memslot: %u\n",
 				paddr_min, vm->page_size, memslot);
 			fputs("---- vm dump ----\n", stderr);
 			vm_dump(stderr, vm, 2);
@@ -1655,7 +1428,8 @@ vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
 	return pg * vm->page_size;
 }
 
-/* Address Guest Virtual to Host Virtual
+/*
+ * Address Guest Virtual to Host Virtual
  *
  * Input Args:
  *   vm - Virtual Machine
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 36367be0fe26..3702c560bbf2 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -11,18 +11,19 @@
 
 #include "sparsebit.h"
 
+#define KVM_DEV_PATH		"/dev/kvm"
+
 #ifndef BITS_PER_BYTE
-#define BITS_PER_BYTE           8
+#define BITS_PER_BYTE		8
 #endif
 
 #ifndef BITS_PER_LONG
-#define BITS_PER_LONG (BITS_PER_BYTE * sizeof(long))
+#define BITS_PER_LONG		(BITS_PER_BYTE * sizeof(long))
 #endif
 
 #define DIV_ROUND_UP(n, d)	(((n) + (d) - 1) / (d))
-#define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_LONG)
+#define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_LONG)
 
-/* Concrete definition of struct kvm_vm. */
 struct userspace_mem_region {
 	struct userspace_mem_region *next, *prev;
 	struct kvm_userspace_memory_region region;
@@ -53,7 +54,6 @@ struct kvm_vm {
 	struct userspace_mem_region *userspace_mem_region_head;
 	struct sparsebit *vpages_valid;
 	struct sparsebit *vpages_mapped;
-
 	bool has_irqchip;
 	bool pgd_created;
 	vm_paddr_t pgd;
@@ -61,13 +61,11 @@ struct kvm_vm {
 	vm_vaddr_t tss;
 };
 
-struct vcpu *vcpu_find(struct kvm_vm *vm,
-	uint32_t vcpuid);
-void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot);
+struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot,
+		int gdt_memslot);
 void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
-void regs_dump(FILE *stream, struct kvm_regs *regs,
-	uint8_t indent);
-void sregs_dump(FILE *stream, struct kvm_sregs *sregs,
-	uint8_t indent);
+void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent);
+void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent);
 
 #endif /* SELFTEST_KVM_UTIL_INTERNAL_H */
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 79c2c5c203c0..67f84fbb0ca4 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -672,6 +672,102 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
 	vcpu_set_mp_state(vm, vcpuid, &mp_state);
 }
 
+/* Allocate an instance of struct kvm_cpuid2
+ *
+ * Input Args: None
+ *
+ * Output Args: None
+ *
+ * Return: A pointer to the allocated struct. The caller is responsible
+ * for freeing this struct.
+ *
+ * Since kvm_cpuid2 uses a 0-length array to allow a the size of the
+ * array to be decided at allocation time, allocation is slightly
+ * complicated. This function uses a reasonable default length for
+ * the array and performs the appropriate allocation.
+ */
+static struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
+{
+	struct kvm_cpuid2 *cpuid;
+	int nent = 100;
+	size_t size;
+
+	size = sizeof(*cpuid);
+	size += nent * sizeof(struct kvm_cpuid_entry2);
+	cpuid = malloc(size);
+	if (!cpuid) {
+		perror("malloc");
+		abort();
+	}
+
+	cpuid->nent = nent;
+
+	return cpuid;
+}
+
+/* KVM Supported CPUID Get
+ *
+ * Input Args: None
+ *
+ * Output Args:
+ *
+ * Return: The supported KVM CPUID
+ *
+ * Get the guest CPUID supported by KVM.
+ */
+struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
+{
+	static struct kvm_cpuid2 *cpuid;
+	int ret;
+	int kvm_fd;
+
+	if (cpuid)
+		return cpuid;
+
+	cpuid = allocate_kvm_cpuid2();
+	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
+	if (kvm_fd < 0)
+		exit(KSFT_SKIP);
+
+	ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid);
+	TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n",
+		    ret, errno);
+
+	close(kvm_fd);
+	return cpuid;
+}
+
+/* Locate a cpuid entry.
+ *
+ * Input Args:
+ *   cpuid: The cpuid.
+ *   function: The function of the cpuid entry to find.
+ *
+ * Output Args: None
+ *
+ * Return: A pointer to the cpuid entry. Never returns NULL.
+ */
+struct kvm_cpuid_entry2 *
+kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
+{
+	struct kvm_cpuid2 *cpuid;
+	struct kvm_cpuid_entry2 *entry = NULL;
+	int i;
+
+	cpuid = kvm_get_supported_cpuid();
+	for (i = 0; i < cpuid->nent; i++) {
+		if (cpuid->entries[i].function == function &&
+		    cpuid->entries[i].index == index) {
+			entry = &cpuid->entries[i];
+			break;
+		}
+	}
+
+	TEST_ASSERT(entry, "Guest CPUID entry not found: (EAX=%x, ECX=%x).",
+		    function, index);
+	return entry;
+}
+
 /* VM VCPU CPUID Set
  *
  * Input Args:
@@ -698,6 +794,7 @@ void vcpu_set_cpuid(struct kvm_vm *vm,
 		    rc, errno);
 
 }
+
 /* Create a VM with reasonable defaults
  *
  * Input Args:
@@ -742,6 +839,154 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
 	return vm;
 }
 
+/* VCPU Get MSR
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU ID
+ *   msr_index - Index of MSR
+ *
+ * Output Args: None
+ *
+ * Return: On success, value of the MSR. On failure a TEST_ASSERT is produced.
+ *
+ * Get value of MSR for VCPU.
+ */
+uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	struct {
+		struct kvm_msrs header;
+		struct kvm_msr_entry entry;
+	} buffer = {};
+	int r;
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+	buffer.header.nmsrs = 1;
+	buffer.entry.index = msr_index;
+	r = ioctl(vcpu->fd, KVM_GET_MSRS, &buffer.header);
+	TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n"
+		"  rc: %i errno: %i", r, errno);
+
+	return buffer.entry.data;
+}
+
+/* VCPU Set MSR
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU ID
+ *   msr_index - Index of MSR
+ *   msr_value - New value of MSR
+ *
+ * Output Args: None
+ *
+ * Return: On success, nothing. On failure a TEST_ASSERT is produced.
+ *
+ * Set value of MSR for VCPU.
+ */
+void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
+	uint64_t msr_value)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	struct {
+		struct kvm_msrs header;
+		struct kvm_msr_entry entry;
+	} buffer = {};
+	int r;
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+	memset(&buffer, 0, sizeof(buffer));
+	buffer.header.nmsrs = 1;
+	buffer.entry.index = msr_index;
+	buffer.entry.data = msr_value;
+	r = ioctl(vcpu->fd, KVM_SET_MSRS, &buffer.header);
+	TEST_ASSERT(r == 1, "KVM_SET_MSRS IOCTL failed,\n"
+		"  rc: %i errno: %i", r, errno);
+}
+
+/* VM VCPU Args Set
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU ID
+ *   num - number of arguments
+ *   ... - arguments, each of type uint64_t
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Sets the first num function input arguments to the values
+ * given as variable args.  Each of the variable args is expected to
+ * be of type uint64_t.
+ */
+void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
+{
+	va_list ap;
+	struct kvm_regs regs;
+
+	TEST_ASSERT(num >= 1 && num <= 6, "Unsupported number of args,\n"
+		    "  num: %u\n",
+		    num);
+
+	va_start(ap, num);
+	vcpu_regs_get(vm, vcpuid, &regs);
+
+	if (num >= 1)
+		regs.rdi = va_arg(ap, uint64_t);
+
+	if (num >= 2)
+		regs.rsi = va_arg(ap, uint64_t);
+
+	if (num >= 3)
+		regs.rdx = va_arg(ap, uint64_t);
+
+	if (num >= 4)
+		regs.rcx = va_arg(ap, uint64_t);
+
+	if (num >= 5)
+		regs.r8 = va_arg(ap, uint64_t);
+
+	if (num >= 6)
+		regs.r9 = va_arg(ap, uint64_t);
+
+	vcpu_regs_set(vm, vcpuid, &regs);
+	va_end(ap);
+}
+
+/*
+ * VM VCPU Dump
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU ID
+ *   indent - Left margin indent amount
+ *
+ * Output Args:
+ *   stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the current state of the VCPU specified by vcpuid, within the VM
+ * given by vm, to the FILE stream given by stream.
+ */
+void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
+{
+	struct kvm_regs regs;
+	struct kvm_sregs sregs;
+
+	fprintf(stream, "%*scpuid: %u\n", indent, "", vcpuid);
+
+	fprintf(stream, "%*sregs:\n", indent + 2, "");
+	vcpu_regs_get(vm, vcpuid, &regs);
+	regs_dump(stream, &regs, indent + 4);
+
+	fprintf(stream, "%*ssregs:\n", indent + 2, "");
+	vcpu_sregs_get(vm, vcpuid, &sregs);
+	sregs_dump(stream, &sregs, indent + 4);
+}
+
 struct kvm_x86_state {
 	struct kvm_vcpu_events events;
 	struct kvm_mp_state mp_state;
diff --git a/tools/testing/selftests/kvm/x86_64/dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/dirty_log_test.c
index 7cf3e4ae6046..395a6e07d37c 100644
--- a/tools/testing/selftests/kvm/x86_64/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86_64/dirty_log_test.c
@@ -15,6 +15,7 @@
 
 #include "test_util.h"
 #include "kvm_util.h"
+#include "processor.h"
 
 #define  DEBUG                 printf
 
-- 
cgit v1.2.3


From d5106539cfef362e3870b6aa8b5ca587cd67e93d Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:29 +0200
Subject: kvm: selftests: add vm_phy_pages_alloc

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h |  2 +
 tools/testing/selftests/kvm/lib/kvm_util.c     | 60 ++++++++++++++++----------
 2 files changed, 39 insertions(+), 23 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 4d5e405ff246..e0c9cf4d1c49 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -110,6 +110,8 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 		 uint32_t pgd_memslot);
 vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
 			     uint32_t memslot);
+vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
+			      vm_paddr_t paddr_min, uint32_t memslot);
 
 struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_size,
 				 void *guest_code);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 1a8f8f9e3635..26c3c4350a88 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1378,10 +1378,11 @@ const char *exit_reason_str(unsigned int exit_reason)
 }
 
 /*
- * Physical Page Allocate
+ * Physical Contiguous Page Allocator
  *
  * Input Args:
  *   vm - Virtual Machine
+ *   num - number of pages
  *   paddr_min - Physical address minimum
  *   memslot - Memory region to allocate page from
  *
@@ -1390,16 +1391,18 @@ const char *exit_reason_str(unsigned int exit_reason)
  * Return:
  *   Starting physical address
  *
- * Within the VM specified by vm, locates an available physical page
- * at or above paddr_min.  If found, the page is marked as in use
- * and its address is returned.  A TEST_ASSERT failure occurs if no
- * page is available at or above paddr_min.
+ * Within the VM specified by vm, locates a range of available physical
+ * pages at or above paddr_min. If found, the pages are marked as in use
+ * and thier base address is returned. A TEST_ASSERT failure occurs if
+ * not enough pages are available at or above paddr_min.
  */
-vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
-			     uint32_t memslot)
+vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
+			      vm_paddr_t paddr_min, uint32_t memslot)
 {
 	struct userspace_mem_region *region;
-	sparsebit_idx_t pg;
+	sparsebit_idx_t pg, base;
+
+	TEST_ASSERT(num > 0, "Must allocate at least one page");
 
 	TEST_ASSERT((paddr_min % vm->page_size) == 0, "Min physical address "
 		"not divisible by page size.\n"
@@ -1407,25 +1410,36 @@ vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
 		paddr_min, vm->page_size);
 
 	region = memslot2region(vm, memslot);
-	pg = paddr_min >> vm->page_shift;
-
-	/* Locate next available physical page at or above paddr_min. */
-	if (!sparsebit_is_set(region->unused_phy_pages, pg)) {
-		pg = sparsebit_next_set(region->unused_phy_pages, pg);
-		if (pg == 0) {
-			fprintf(stderr, "No guest physical page available, "
-				"paddr_min: 0x%lx page_size: 0x%x memslot: %u\n",
-				paddr_min, vm->page_size, memslot);
-			fputs("---- vm dump ----\n", stderr);
-			vm_dump(stderr, vm, 2);
-			abort();
+	base = pg = paddr_min >> vm->page_shift;
+
+	do {
+		for (; pg < base + num; ++pg) {
+			if (!sparsebit_is_set(region->unused_phy_pages, pg)) {
+				base = pg = sparsebit_next_set(region->unused_phy_pages, pg);
+				break;
+			}
 		}
+	} while (pg && pg != base + num);
+
+	if (pg == 0) {
+		fprintf(stderr, "No guest physical page available, "
+			"paddr_min: 0x%lx page_size: 0x%x memslot: %u\n",
+			paddr_min, vm->page_size, memslot);
+		fputs("---- vm dump ----\n", stderr);
+		vm_dump(stderr, vm, 2);
+		abort();
 	}
 
-	/* Specify page as in use and return its address. */
-	sparsebit_clear(region->unused_phy_pages, pg);
+	for (pg = base; pg < base + num; ++pg)
+		sparsebit_clear(region->unused_phy_pages, pg);
+
+	return base * vm->page_size;
+}
 
-	return pg * vm->page_size;
+vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
+			     uint32_t memslot)
+{
+	return vm_phy_pages_alloc(vm, 1, paddr_min, memslot);
 }
 
 /*
-- 
cgit v1.2.3


From 7a6629ef746d1a50cc9247bd7c92ce6b38b8ed68 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:30 +0200
Subject: kvm: selftests: add virt mem support for aarch64

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../testing/selftests/kvm/lib/aarch64/processor.c  | 216 +++++++++++++++++++++
 tools/testing/selftests/kvm/lib/kvm_util.c         |   1 +
 .../testing/selftests/kvm/lib/kvm_util_internal.h  |   1 +
 3 files changed, 218 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/lib/aarch64/processor.c

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
new file mode 100644
index 000000000000..464d4d074249
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AArch64 code
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+
+#include "kvm_util.h"
+#include "../kvm_util_internal.h"
+
+#define KVM_GUEST_PAGE_TABLE_MIN_PADDR		0x180000
+
+static uint64_t page_align(struct kvm_vm *vm, uint64_t v)
+{
+	return (v + vm->page_size) & ~(vm->page_size - 1);
+}
+
+static uint64_t pgd_index(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	unsigned int shift = (vm->pgtable_levels - 1) * (vm->page_shift - 3) + vm->page_shift;
+	uint64_t mask = (1UL << (vm->va_bits - shift)) - 1;
+
+	return (gva >> shift) & mask;
+}
+
+static uint64_t pud_index(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	unsigned int shift = 2 * (vm->page_shift - 3) + vm->page_shift;
+	uint64_t mask = (1UL << (vm->page_shift - 3)) - 1;
+
+	TEST_ASSERT(vm->pgtable_levels == 4,
+		"Mode %d does not have 4 page table levels", vm->mode);
+
+	return (gva >> shift) & mask;
+}
+
+static uint64_t pmd_index(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	unsigned int shift = (vm->page_shift - 3) + vm->page_shift;
+	uint64_t mask = (1UL << (vm->page_shift - 3)) - 1;
+
+	TEST_ASSERT(vm->pgtable_levels >= 3,
+		"Mode %d does not have >= 3 page table levels", vm->mode);
+
+	return (gva >> shift) & mask;
+}
+
+static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	uint64_t mask = (1UL << (vm->page_shift - 3)) - 1;
+	return (gva >> vm->page_shift) & mask;
+}
+
+static uint64_t pte_addr(struct kvm_vm *vm, uint64_t entry)
+{
+	uint64_t mask = ((1UL << (vm->va_bits - vm->page_shift)) - 1) << vm->page_shift;
+	return entry & mask;
+}
+
+static uint64_t ptrs_per_pgd(struct kvm_vm *vm)
+{
+	unsigned int shift = (vm->pgtable_levels - 1) * (vm->page_shift - 3) + vm->page_shift;
+	return 1 << (vm->va_bits - shift);
+}
+
+static uint64_t ptrs_per_pte(struct kvm_vm *vm)
+{
+	return 1 << (vm->page_shift - 3);
+}
+
+void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
+{
+	int rc;
+
+	if (!vm->pgd_created) {
+		vm_paddr_t paddr = vm_phy_pages_alloc(vm,
+			page_align(vm, ptrs_per_pgd(vm) * 8) / vm->page_size,
+			KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+		vm->pgd = paddr;
+		vm->pgd_created = true;
+	}
+}
+
+void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+		  uint32_t pgd_memslot, uint64_t flags)
+{
+	uint8_t attr_idx = flags & 7;
+	uint64_t *ptep;
+
+	TEST_ASSERT((vaddr % vm->page_size) == 0,
+		"Virtual address not on page boundary,\n"
+		"  vaddr: 0x%lx vm->page_size: 0x%x", vaddr, vm->page_size);
+	TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
+		(vaddr >> vm->page_shift)),
+		"Invalid virtual address, vaddr: 0x%lx", vaddr);
+	TEST_ASSERT((paddr % vm->page_size) == 0,
+		"Physical address not on page boundary,\n"
+		"  paddr: 0x%lx vm->page_size: 0x%x", paddr, vm->page_size);
+	TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
+		"Physical address beyond beyond maximum supported,\n"
+		"  paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+		paddr, vm->max_gfn, vm->page_size);
+
+	ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, vaddr) * 8;
+	if (!*ptep) {
+		*ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+		*ptep |= 3;
+	}
+
+	switch (vm->pgtable_levels) {
+	case 4:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, vaddr) * 8;
+		if (!*ptep) {
+			*ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+			*ptep |= 3;
+		}
+		/* fall through */
+	case 3:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, vaddr) * 8;
+		if (!*ptep) {
+			*ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+			*ptep |= 3;
+		}
+		/* fall through */
+	case 2:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8;
+		break;
+	default:
+		TEST_ASSERT(false, "Page table levels must be 2, 3, or 4");
+	}
+
+	*ptep = paddr | 3;
+	*ptep |= (attr_idx << 2) | (1 << 10) /* Access Flag */;
+}
+
+void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+		 uint32_t pgd_memslot)
+{
+	uint64_t attr_idx = 4; /* NORMAL (See DEFAULT_MAIR_EL1) */
+
+	_virt_pg_map(vm, vaddr, paddr, pgd_memslot, attr_idx);
+}
+
+vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	uint64_t *ptep;
+
+	if (!vm->pgd_created)
+		goto unmapped_gva;
+
+	ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, gva) * 8;
+	if (!ptep)
+		goto unmapped_gva;
+
+	switch (vm->pgtable_levels) {
+	case 4:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, gva) * 8;
+		if (!ptep)
+			goto unmapped_gva;
+		/* fall through */
+	case 3:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, gva) * 8;
+		if (!ptep)
+			goto unmapped_gva;
+		/* fall through */
+	case 2:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, gva) * 8;
+		if (!ptep)
+			goto unmapped_gva;
+		break;
+	default:
+		TEST_ASSERT(false, "Page table levels must be 2, 3, or 4");
+	}
+
+	return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1));
+
+unmapped_gva:
+	TEST_ASSERT(false, "No mapping for vm virtual address, "
+		    "gva: 0x%lx", gva);
+}
+
+static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t page, int level)
+{
+#ifdef DEBUG_VM
+	static const char * const type[] = { "", "pud", "pmd", "pte" };
+	uint64_t pte, *ptep;
+
+	if (level == 4)
+		return;
+
+	for (pte = page; pte < page + ptrs_per_pte(vm) * 8; pte += 8) {
+		ptep = addr_gpa2hva(vm, pte);
+		if (!*ptep)
+			continue;
+		printf("%*s%s: %lx: %lx at %p\n", indent, "", type[level], pte, *ptep, ptep);
+		pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level + 1);
+	}
+#endif
+}
+
+void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
+{
+	int level = 4 - (vm->pgtable_levels - 1);
+	uint64_t pgd, *ptep;
+
+	if (!vm->pgd_created)
+		return;
+
+	for (pgd = vm->pgd; pgd < vm->pgd + ptrs_per_pgd(vm) * 8; pgd += 8) {
+		ptep = addr_gpa2hva(vm, pgd);
+		if (!*ptep)
+			continue;
+		printf("%*spgd: %lx: %lx at %p\n", indent, "", pgd, *ptep, ptep);
+		pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level);
+	}
+}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 26c3c4350a88..fd346fb82e46 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -129,6 +129,7 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	/* Setup mode specific traits. */
 	switch (vm->mode) {
 	case VM_MODE_FLAT48PG:
+		vm->pgtable_levels = 4;
 		vm->page_size = 0x1000;
 		vm->page_shift = 12;
 		vm->va_bits = 48;
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 3702c560bbf2..d048d7363d66 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -46,6 +46,7 @@ struct kvm_vm {
 	int mode;
 	int kvm_fd;
 	int fd;
+	unsigned int pgtable_levels;
 	unsigned int page_size;
 	unsigned int page_shift;
 	unsigned int va_bits;
-- 
cgit v1.2.3


From 0bec140fb6c106a70aac183e5fa99de0ef1d161a Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:31 +0200
Subject: kvm: selftests: add vcpu support for aarch64

This code adds VM and VCPU setup code for the VM_MODE_FLAT48PG mode.
The VM_MODE_FLAT48PG isn't yet fully supportable, as it defines the
guest physical address limit as 52-bits, and KVM currently only
supports guests with up to 40-bit physical addresses (see
KVM_PHYS_SHIFT). VM_MODE_FLAT48PG will work fine, though, as long as
no >= 40-bit physical addresses are used.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/include/aarch64/processor.h      | 55 ++++++++++++++
 .../testing/selftests/kvm/lib/aarch64/processor.c  | 83 ++++++++++++++++++++++
 2 files changed, 138 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/include/aarch64/processor.h

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
new file mode 100644
index 000000000000..9ef2ab1a0c08
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AArch64 processor specific defines
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+#ifndef SELFTEST_KVM_PROCESSOR_H
+#define SELFTEST_KVM_PROCESSOR_H
+
+#include "kvm_util.h"
+
+
+#define ARM64_CORE_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+			   KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x))
+
+#define CPACR_EL1	3, 0,  1, 0, 2
+#define TCR_EL1		3, 0,  2, 0, 2
+#define MAIR_EL1	3, 0, 10, 2, 0
+#define TTBR0_EL1	3, 0,  2, 0, 0
+#define SCTLR_EL1	3, 0,  1, 0, 0
+
+/*
+ * Default MAIR
+ *                  index   attribute
+ * DEVICE_nGnRnE      0     0000:0000
+ * DEVICE_nGnRE       1     0000:0100
+ * DEVICE_GRE         2     0000:1100
+ * NORMAL_NC          3     0100:0100
+ * NORMAL             4     1111:1111
+ * NORMAL_WT          5     1011:1011
+ */
+#define DEFAULT_MAIR_EL1 ((0x00ul << (0 * 8)) | \
+			  (0x04ul << (1 * 8)) | \
+			  (0x0cul << (2 * 8)) | \
+			  (0x44ul << (3 * 8)) | \
+			  (0xfful << (4 * 8)) | \
+			  (0xbbul << (5 * 8)))
+
+static inline void get_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint64_t *addr)
+{
+	struct kvm_one_reg reg;
+	reg.id = id;
+	reg.addr = (uint64_t)addr;
+	vcpu_ioctl(vm, vcpuid, KVM_GET_ONE_REG, &reg);
+}
+
+static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint64_t val)
+{
+	struct kvm_one_reg reg;
+	reg.id = id;
+	reg.addr = (uint64_t)&val;
+	vcpu_ioctl(vm, vcpuid, KVM_SET_ONE_REG, &reg);
+}
+
+#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 464d4d074249..871fe2173679 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -5,10 +5,14 @@
  * Copyright (C) 2018, Red Hat, Inc.
  */
 
+#define _GNU_SOURCE /* for program_invocation_name */
+
 #include "kvm_util.h"
 #include "../kvm_util_internal.h"
+#include "processor.h"
 
 #define KVM_GUEST_PAGE_TABLE_MIN_PADDR		0x180000
+#define DEFAULT_ARM64_GUEST_STACK_VADDR_MIN	0xac0000
 
 static uint64_t page_align(struct kvm_vm *vm, uint64_t v)
 {
@@ -214,3 +218,82 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 		pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level);
 	}
 }
+
+struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
+				 void *guest_code)
+{
+	uint64_t ptrs_per_4k_pte = 512;
+	uint64_t extra_pg_pages = (extra_mem_pages / ptrs_per_4k_pte) * 2;
+	struct kvm_vm *vm;
+
+	vm = vm_create(VM_MODE_FLAT48PG, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+	vm_vcpu_add_default(vm, vcpuid, guest_code);
+
+	return vm;
+}
+
+void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
+{
+	size_t stack_size = vm->page_size == 4096 ?
+					DEFAULT_STACK_PGS * vm->page_size :
+					vm->page_size;
+	uint64_t stack_vaddr = vm_vaddr_alloc(vm, stack_size,
+					DEFAULT_ARM64_GUEST_STACK_VADDR_MIN, 0, 0);
+
+	vm_vcpu_add(vm, vcpuid, 0, 0);
+
+	set_reg(vm, vcpuid, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size);
+	set_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code);
+}
+
+void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
+{
+	struct kvm_vcpu_init init;
+	uint64_t sctlr_el1, tcr_el1;
+
+	memset(&init, 0, sizeof(init));
+	init.target = KVM_ARM_TARGET_GENERIC_V8;
+	vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_INIT, &init);
+
+	/*
+	 * Enable FP/ASIMD to avoid trapping when accessing Q0-Q15
+	 * registers, which the variable argument list macros do.
+	 */
+	set_reg(vm, vcpuid, ARM64_SYS_REG(CPACR_EL1), 3 << 20);
+
+	get_reg(vm, vcpuid, ARM64_SYS_REG(SCTLR_EL1), &sctlr_el1);
+	get_reg(vm, vcpuid, ARM64_SYS_REG(TCR_EL1), &tcr_el1);
+
+	switch (vm->mode) {
+	case VM_MODE_FLAT48PG:
+		tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
+		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
+		break;
+	default:
+		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode);
+	}
+
+	sctlr_el1 |= (1 << 0) | (1 << 2) | (1 << 12) /* M | C | I */;
+	/* TCR_EL1 |= IRGN0:WBWA | ORGN0:WBWA | SH0:Inner-Shareable */;
+	tcr_el1 |= (1 << 8) | (1 << 10) | (3 << 12);
+	tcr_el1 |= (64 - vm->va_bits) /* T0SZ */;
+
+	set_reg(vm, vcpuid, ARM64_SYS_REG(SCTLR_EL1), sctlr_el1);
+	set_reg(vm, vcpuid, ARM64_SYS_REG(TCR_EL1), tcr_el1);
+	set_reg(vm, vcpuid, ARM64_SYS_REG(MAIR_EL1), DEFAULT_MAIR_EL1);
+	set_reg(vm, vcpuid, ARM64_SYS_REG(TTBR0_EL1), vm->pgd);
+}
+
+void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
+{
+	uint64_t pstate, pc;
+
+	get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pstate), &pstate);
+	get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), &pc);
+
+        fprintf(stream, "%*spstate: 0x%.16llx pc: 0x%.16llx\n",
+                indent, "", pstate, pc);
+
+}
-- 
cgit v1.2.3


From 81d1cca0c062a589953eef7e98f1e68b8222a918 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:33 +0200
Subject: kvm: selftests: introduce new VM mode for 64K pages

Rename VM_MODE_FLAT48PG to be more descriptive of its config and add a
new config that has the same parameters, except with 64K pages.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h     |  7 +++-
 .../testing/selftests/kvm/lib/aarch64/processor.c  |  8 +++-
 tools/testing/selftests/kvm/lib/kvm_util.c         | 46 ++++++++++++++--------
 .../testing/selftests/kvm/lib/kvm_util_internal.h  |  1 +
 tools/testing/selftests/kvm/lib/x86_64/processor.c | 10 ++---
 5 files changed, 47 insertions(+), 25 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index e0c9cf4d1c49..88df26c41845 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -34,9 +34,14 @@ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
 #define DEFAULT_STACK_PGS		5
 
 enum vm_guest_mode {
-	VM_MODE_FLAT48PG,
+	VM_MODE_P52V48_4K,
+	VM_MODE_P52V48_64K,
+	NUM_VM_MODES,
 };
 
+#define vm_guest_mode_string(m) vm_guest_mode_string[m]
+extern const char * const vm_guest_mode_string[];
+
 enum vm_mem_backing_src_type {
 	VM_MEM_SRC_ANONYMOUS,
 	VM_MEM_SRC_ANONYMOUS_THP,
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 871fe2173679..b1dfc0d4b68e 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -226,7 +226,7 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
 	uint64_t extra_pg_pages = (extra_mem_pages / ptrs_per_4k_pte) * 2;
 	struct kvm_vm *vm;
 
-	vm = vm_create(VM_MODE_FLAT48PG, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+	vm = vm_create(VM_MODE_P52V48_4K, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
 
 	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
 	vm_vcpu_add_default(vm, vcpuid, guest_code);
@@ -267,10 +267,14 @@ void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
 	get_reg(vm, vcpuid, ARM64_SYS_REG(TCR_EL1), &tcr_el1);
 
 	switch (vm->mode) {
-	case VM_MODE_FLAT48PG:
+	case VM_MODE_P52V48_4K:
 		tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
 		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
 		break;
+	case VM_MODE_P52V48_64K:
+		tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
+		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
+		break;
 	default:
 		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode);
 	}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index fd346fb82e46..b37e52f4daad 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -17,7 +17,7 @@
 #include <linux/kernel.h>
 
 #define KVM_UTIL_PGS_PER_HUGEPG 512
-#define KVM_UTIL_MIN_PADDR      0x2000
+#define KVM_UTIL_MIN_PFN	2
 
 /* Aligns x up to the next multiple of size. Size must be a power of 2. */
 static void *align(void *x, size_t size)
@@ -96,11 +96,16 @@ static void vm_open(struct kvm_vm *vm, int perm)
 		"rc: %i errno: %i", vm->fd, errno);
 }
 
+const char * const vm_guest_mode_string[] = {
+	"PA-bits:52, VA-bits:48, 4K pages",
+	"PA-bits:52, VA-bits:48, 64K pages",
+};
+
 /*
  * VM Create
  *
  * Input Args:
- *   mode - VM Mode (e.g. VM_MODE_FLAT48PG)
+ *   mode - VM Mode (e.g. VM_MODE_P52V48_4K)
  *   phy_pages - Physical memory pages
  *   perm - permission
  *
@@ -109,7 +114,7 @@ static void vm_open(struct kvm_vm *vm, int perm)
  * Return:
  *   Pointer to opaque structure that describes the created VM.
  *
- * Creates a VM with the mode specified by mode (e.g. VM_MODE_FLAT48PG).
+ * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K).
  * When phy_pages is non-zero, a memory region of phy_pages physical pages
  * is created and mapped starting at guest physical address 0.  The file
  * descriptor to control the created VM is created with the permissions
@@ -128,28 +133,34 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 
 	/* Setup mode specific traits. */
 	switch (vm->mode) {
-	case VM_MODE_FLAT48PG:
+	case VM_MODE_P52V48_4K:
 		vm->pgtable_levels = 4;
 		vm->page_size = 0x1000;
 		vm->page_shift = 12;
 		vm->va_bits = 48;
-
-		/* Limit to 48-bit canonical virtual addresses. */
-		vm->vpages_valid = sparsebit_alloc();
-		sparsebit_set_num(vm->vpages_valid,
-			0, (1ULL << (48 - 1)) >> vm->page_shift);
-		sparsebit_set_num(vm->vpages_valid,
-			(~((1ULL << (48 - 1)) - 1)) >> vm->page_shift,
-			(1ULL << (48 - 1)) >> vm->page_shift);
-
-		/* Limit physical addresses to 52-bits. */
-		vm->max_gfn = ((1ULL << 52) >> vm->page_shift) - 1;
 		break;
-
+	case VM_MODE_P52V48_64K:
+		vm->pgtable_levels = 3;
+		vm->pa_bits = 52;
+		vm->page_size = 0x10000;
+		vm->page_shift = 16;
+		vm->va_bits = 48;
+		break;
 	default:
 		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", mode);
 	}
 
+	/* Limit to VA-bit canonical virtual addresses. */
+	vm->vpages_valid = sparsebit_alloc();
+	sparsebit_set_num(vm->vpages_valid,
+		0, (1ULL << (vm->va_bits - 1)) >> vm->page_shift);
+	sparsebit_set_num(vm->vpages_valid,
+		(~((1ULL << (vm->va_bits - 1)) - 1)) >> vm->page_shift,
+		(1ULL << (vm->va_bits - 1)) >> vm->page_shift);
+
+	/* Limit physical addresses to PA-bits. */
+	vm->max_gfn = ((1ULL << vm->pa_bits) >> vm->page_shift) - 1;
+
 	/* Allocate and setup memory for guest. */
 	vm->vpages_mapped = sparsebit_alloc();
 	if (phy_pages != 0)
@@ -868,7 +879,8 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
 		pages--, vaddr += vm->page_size) {
 		vm_paddr_t paddr;
 
-		paddr = vm_phy_page_alloc(vm, KVM_UTIL_MIN_PADDR, data_memslot);
+		paddr = vm_phy_page_alloc(vm,
+				KVM_UTIL_MIN_PFN * vm->page_size, data_memslot);
 
 		virt_pg_map(vm, vaddr, paddr, pgd_memslot);
 
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index d048d7363d66..52701db0f253 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -49,6 +49,7 @@ struct kvm_vm {
 	unsigned int pgtable_levels;
 	unsigned int page_size;
 	unsigned int page_shift;
+	unsigned int pa_bits;
 	unsigned int va_bits;
 	uint64_t max_gfn;
 	struct vcpu *vcpu_head;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 67f84fbb0ca4..f28127f4a3af 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -231,7 +231,7 @@ void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
 {
 	int rc;
 
-	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+	TEST_ASSERT(vm->mode == VM_MODE_P52V48_4K, "Attempt to use "
 		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
 
 	/* If needed, create page map l4 table. */
@@ -264,7 +264,7 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 	uint16_t index[4];
 	struct pageMapL4Entry *pml4e;
 
-	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+	TEST_ASSERT(vm->mode == VM_MODE_P52V48_4K, "Attempt to use "
 		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
 
 	TEST_ASSERT((vaddr % vm->page_size) == 0,
@@ -551,7 +551,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 	struct pageTableEntry *pte;
 	void *hva;
 
-	TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+	TEST_ASSERT(vm->mode == VM_MODE_P52V48_4K, "Attempt to use "
 		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
 
 	index[0] = (gva >> 12) & 0x1ffu;
@@ -624,7 +624,7 @@ void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
 	kvm_setup_gdt(vm, &sregs.gdt, gdt_memslot, pgd_memslot);
 
 	switch (vm->mode) {
-	case VM_MODE_FLAT48PG:
+	case VM_MODE_P52V48_4K:
 		sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG;
 		sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
 		sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
@@ -823,7 +823,7 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
 	uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
 
 	/* Create VM */
-	vm = vm_create(VM_MODE_FLAT48PG,
+	vm = vm_create(VM_MODE_P52V48_4K,
 		       DEFAULT_GUEST_PHY_PAGES + extra_pg_pages,
 		       O_RDWR);
 
-- 
cgit v1.2.3


From fff8dcd7b4a242e3752d6f316967b02f933031d0 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:32 +0200
Subject: kvm: selftests: port dirty_log_test to aarch64

While we're messing with the code for the port and to support guest
page sizes that are less than the host page size, we also make some
code formatting cleanups and apply sync_global_to_guest().

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/.gitignore             |   2 +-
 tools/testing/selftests/kvm/Makefile               |   5 +-
 tools/testing/selftests/kvm/dirty_log_test.c       | 315 +++++++++++++++++++++
 .../testing/selftests/kvm/x86_64/dirty_log_test.c  | 308 --------------------
 4 files changed, 320 insertions(+), 310 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/dirty_log_test.c
 delete mode 100644 tools/testing/selftests/kvm/x86_64/dirty_log_test.c

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index e0aa5411cf9b..552b0d9a49f4 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -4,4 +4,4 @@
 /x86_64/sync_regs_test
 /x86_64/vmx_tsc_adjust_test
 /x86_64/state_test
-/x86_64/dirty_log_test
+/dirty_log_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 959be146f789..5e23f97ec46f 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -5,6 +5,7 @@ UNAME_M := $(shell uname -m)
 
 LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/ucall.c lib/sparsebit.c
 LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c
+LIBKVM_aarch64 = lib/aarch64/processor.c
 
 TEST_GEN_PROGS_x86_64 = x86_64/platform_info_test
 TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
@@ -12,7 +13,9 @@ TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
 TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += x86_64/state_test
-TEST_GEN_PROGS_x86_64 += x86_64/dirty_log_test
+TEST_GEN_PROGS_x86_64 += dirty_log_test
+
+TEST_GEN_PROGS_aarch64 += dirty_log_test
 
 TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
 LIBKVM += $(LIBKVM_$(UNAME_M))
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
new file mode 100644
index 000000000000..d90f1091f687
--- /dev/null
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM dirty page logging test
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <time.h>
+#include <pthread.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define DEBUG printf
+
+#define VCPU_ID				1
+
+/* The memory slot index to track dirty pages */
+#define TEST_MEM_SLOT_INDEX		1
+
+/*
+ * GPA offset of the testing memory slot. Must be bigger than the
+ * default vm mem slot, which is DEFAULT_GUEST_PHY_PAGES.
+ */
+#define TEST_MEM_OFFSET			(1ul << 30) /* 1G */
+
+/* Size of the testing memory slot */
+#define TEST_MEM_PAGES			(1ul << 18) /* 1G for 4K pages */
+
+/* How many pages to dirty for each guest loop */
+#define TEST_PAGES_PER_LOOP		1024
+
+/* How many host loops to run (one KVM_GET_DIRTY_LOG for each loop) */
+#define TEST_HOST_LOOP_N		32
+
+/* Interval for each host loop (ms) */
+#define TEST_HOST_LOOP_INTERVAL		10
+
+/*
+ * Guest/Host shared variables. Ensure addr_gva2hva() and/or
+ * sync_global_to/from_guest() are used when accessing from
+ * the host. READ/WRITE_ONCE() should also be used with anything
+ * that may change.
+ */
+static uint64_t host_page_size;
+static uint64_t guest_page_size;
+static uint64_t random_array[TEST_PAGES_PER_LOOP];
+static uint64_t iteration;
+
+/*
+ * Continuously write to the first 8 bytes of a random pages within
+ * the testing memory region.
+ */
+static void guest_code(void)
+{
+	int i;
+
+	while (true) {
+		for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
+			uint64_t addr = TEST_MEM_OFFSET;
+			addr += (READ_ONCE(random_array[i]) % TEST_MEM_PAGES)
+				* guest_page_size;
+			addr &= ~(host_page_size - 1);
+			*(uint64_t *)addr = READ_ONCE(iteration);
+		}
+
+		/* Tell the host that we need more random numbers */
+		GUEST_SYNC(1);
+	}
+}
+
+/* Host variables */
+static bool host_quit;
+
+/* Points to the test VM memory region on which we track dirty logs */
+static void *host_test_mem;
+static uint64_t host_num_pages;
+
+/* For statistics only */
+static uint64_t host_dirty_count;
+static uint64_t host_clear_count;
+static uint64_t host_track_next_count;
+
+/*
+ * We use this bitmap to track some pages that should have its dirty
+ * bit set in the _next_ iteration.  For example, if we detected the
+ * page value changed to current iteration but at the same time the
+ * page bit is cleared in the latest bitmap, then the system must
+ * report that write in the next get dirty log call.
+ */
+static unsigned long *host_bmap_track;
+
+static void generate_random_array(uint64_t *guest_array, uint64_t size)
+{
+	uint64_t i;
+
+	for (i = 0; i < size; i++)
+		guest_array[i] = random();
+}
+
+static void *vcpu_worker(void *data)
+{
+	int ret;
+	struct kvm_vm *vm = data;
+	uint64_t *guest_array;
+	uint64_t pages_count = 0;
+	struct kvm_run *run;
+	struct ucall uc;
+
+	run = vcpu_state(vm, VCPU_ID);
+
+	guest_array = addr_gva2hva(vm, (vm_vaddr_t)random_array);
+	generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
+
+	while (!READ_ONCE(host_quit)) {
+		/* Let the guest dirty the random pages */
+		ret = _vcpu_run(vm, VCPU_ID);
+		if (get_ucall(vm, VCPU_ID, &uc) == UCALL_SYNC) {
+			pages_count += TEST_PAGES_PER_LOOP;
+			generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
+		} else {
+			TEST_ASSERT(false,
+				    "Invalid guest sync status: "
+				    "exit_reason=%s\n",
+				    exit_reason_str(run->exit_reason));
+		}
+	}
+
+	DEBUG("Dirtied %"PRIu64" pages\n", pages_count);
+
+	return NULL;
+}
+
+static void vm_dirty_log_verify(unsigned long *bmap)
+{
+	uint64_t page;
+	uint64_t *value_ptr;
+
+	for (page = 0; page < host_num_pages; page++) {
+		value_ptr = host_test_mem + page * host_page_size;
+
+		/* If this is a special page that we were tracking... */
+		if (test_and_clear_bit(page, host_bmap_track)) {
+			host_track_next_count++;
+			TEST_ASSERT(test_bit(page, bmap),
+				    "Page %"PRIu64" should have its dirty bit "
+				    "set in this iteration but it is missing",
+				    page);
+		}
+
+		if (test_bit(page, bmap)) {
+			host_dirty_count++;
+			/*
+			 * If the bit is set, the value written onto
+			 * the corresponding page should be either the
+			 * previous iteration number or the current one.
+			 */
+			TEST_ASSERT(*value_ptr == iteration ||
+				    *value_ptr == iteration - 1,
+				    "Set page %"PRIu64" value %"PRIu64
+				    " incorrect (iteration=%"PRIu64")",
+				    page, *value_ptr, iteration);
+		} else {
+			host_clear_count++;
+			/*
+			 * If cleared, the value written can be any
+			 * value smaller or equals to the iteration
+			 * number.  Note that the value can be exactly
+			 * (iteration-1) if that write can happen
+			 * like this:
+			 *
+			 * (1) increase loop count to "iteration-1"
+			 * (2) write to page P happens (with value
+			 *     "iteration-1")
+			 * (3) get dirty log for "iteration-1"; we'll
+			 *     see that page P bit is set (dirtied),
+			 *     and not set the bit in host_bmap_track
+			 * (4) increase loop count to "iteration"
+			 *     (which is current iteration)
+			 * (5) get dirty log for current iteration,
+			 *     we'll see that page P is cleared, with
+			 *     value "iteration-1".
+			 */
+			TEST_ASSERT(*value_ptr <= iteration,
+				    "Clear page %"PRIu64" value %"PRIu64
+				    " incorrect (iteration=%"PRIu64")",
+				    page, *value_ptr, iteration);
+			if (*value_ptr == iteration) {
+				/*
+				 * This page is _just_ modified; it
+				 * should report its dirtyness in the
+				 * next run
+				 */
+				set_bit(page, host_bmap_track);
+			}
+		}
+	}
+}
+
+static void help(char *name)
+{
+	puts("");
+	printf("usage: %s [-i iterations] [-I interval] [-h]\n", name);
+	puts("");
+	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
+	       TEST_HOST_LOOP_N);
+	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
+	       TEST_HOST_LOOP_INTERVAL);
+	puts("");
+	exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+	pthread_t vcpu_thread;
+	struct kvm_vm *vm;
+	unsigned long iterations = TEST_HOST_LOOP_N;
+	unsigned long interval = TEST_HOST_LOOP_INTERVAL;
+	unsigned long *bmap;
+	int opt;
+
+	while ((opt = getopt(argc, argv, "hi:I:")) != -1) {
+		switch (opt) {
+		case 'i':
+			iterations = strtol(optarg, NULL, 10);
+			break;
+		case 'I':
+			interval = strtol(optarg, NULL, 10);
+			break;
+		case 'h':
+		default:
+			help(argv[0]);
+			break;
+		}
+	}
+
+	TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
+	TEST_ASSERT(interval > 0, "Interval must be greater than zero");
+
+	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
+	      iterations, interval);
+
+	srandom(time(0));
+
+	guest_page_size = 4096;
+	host_page_size = getpagesize();
+	host_num_pages = (TEST_MEM_PAGES * guest_page_size) / host_page_size +
+			 !!((TEST_MEM_PAGES * guest_page_size) % host_page_size);
+
+	bmap = bitmap_alloc(host_num_pages);
+	host_bmap_track = bitmap_alloc(host_num_pages);
+
+	vm = vm_create_default(VCPU_ID, TEST_MEM_PAGES, guest_code);
+
+	/* Add an extra memory slot for testing dirty logging */
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    TEST_MEM_OFFSET,
+				    TEST_MEM_SLOT_INDEX,
+				    TEST_MEM_PAGES,
+				    KVM_MEM_LOG_DIRTY_PAGES);
+
+	/* Do 1:1 mapping for the dirty track memory slot */
+	virt_map(vm, TEST_MEM_OFFSET, TEST_MEM_OFFSET,
+		 TEST_MEM_PAGES * guest_page_size, 0);
+
+	/* Cache the HVA pointer of the region */
+	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)TEST_MEM_OFFSET);
+
+#ifdef __x86_64__
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+#endif
+#ifdef __aarch64__
+	ucall_init(vm, UCALL_MMIO, NULL);
+#endif
+
+	/* Tell the guest about the page sizes */
+	sync_global_to_guest(vm, host_page_size);
+	sync_global_to_guest(vm, guest_page_size);
+
+	/* Start the iterations */
+	iteration = 1;
+	sync_global_to_guest(vm, iteration);
+
+	pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
+
+	while (iteration < iterations) {
+		/* Give the vcpu thread some time to dirty some pages */
+		usleep(interval * 1000);
+		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
+		vm_dirty_log_verify(bmap);
+		iteration++;
+		sync_global_to_guest(vm, iteration);
+	}
+
+	/* Tell the vcpu thread to quit */
+	host_quit = true;
+	pthread_join(vcpu_thread, NULL);
+
+	DEBUG("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
+	      "track_next (%"PRIu64")\n", host_dirty_count, host_clear_count,
+	      host_track_next_count);
+
+	free(bmap);
+	free(host_bmap_track);
+	ucall_uninit(vm);
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/dirty_log_test.c
deleted file mode 100644
index 395a6e07d37c..000000000000
--- a/tools/testing/selftests/kvm/x86_64/dirty_log_test.c
+++ /dev/null
@@ -1,308 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * KVM dirty page logging test
- *
- * Copyright (C) 2018, Red Hat, Inc.
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <time.h>
-#include <pthread.h>
-#include <linux/bitmap.h>
-#include <linux/bitops.h>
-
-#include "test_util.h"
-#include "kvm_util.h"
-#include "processor.h"
-
-#define  DEBUG                 printf
-
-#define  VCPU_ID                        1
-/* The memory slot index to track dirty pages */
-#define  TEST_MEM_SLOT_INDEX            1
-/*
- * GPA offset of the testing memory slot. Must be bigger than the
- * default vm mem slot, which is DEFAULT_GUEST_PHY_PAGES.
- */
-#define  TEST_MEM_OFFSET                (1ULL << 30) /* 1G */
-/* Size of the testing memory slot */
-#define  TEST_MEM_PAGES                 (1ULL << 18) /* 1G for 4K pages */
-/* How many pages to dirty for each guest loop */
-#define  TEST_PAGES_PER_LOOP            1024
-/* How many host loops to run (one KVM_GET_DIRTY_LOG for each loop) */
-#define  TEST_HOST_LOOP_N               32
-/* Interval for each host loop (ms) */
-#define  TEST_HOST_LOOP_INTERVAL        10
-
-/*
- * Guest variables.  We use these variables to share data between host
- * and guest.  There are two copies of the variables, one in host memory
- * (which is unused) and one in guest memory.  When the host wants to
- * access these variables, it needs to call addr_gva2hva() to access the
- * guest copy.
- */
-uint64_t guest_random_array[TEST_PAGES_PER_LOOP];
-uint64_t guest_iteration;
-uint64_t guest_page_size;
-
-/*
- * Writes to the first byte of a random page within the testing memory
- * region continuously.
- */
-void guest_code(void)
-{
-	int i = 0;
-	uint64_t volatile *array = guest_random_array;
-	uint64_t volatile *guest_addr;
-
-	while (true) {
-		for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
-			/*
-			 * Write to the first 8 bytes of a random page
-			 * on the testing memory region.
-			 */
-			guest_addr = (uint64_t *)
-			    (TEST_MEM_OFFSET +
-			     (array[i] % TEST_MEM_PAGES) * guest_page_size);
-			*guest_addr = guest_iteration;
-		}
-		/* Tell the host that we need more random numbers */
-		GUEST_SYNC(1);
-	}
-}
-
-/*
- * Host variables.  These variables should only be used by the host
- * rather than the guest.
- */
-bool host_quit;
-
-/* Points to the test VM memory region on which we track dirty logs */
-void *host_test_mem;
-
-/* For statistics only */
-uint64_t host_dirty_count;
-uint64_t host_clear_count;
-uint64_t host_track_next_count;
-
-/*
- * We use this bitmap to track some pages that should have its dirty
- * bit set in the _next_ iteration.  For example, if we detected the
- * page value changed to current iteration but at the same time the
- * page bit is cleared in the latest bitmap, then the system must
- * report that write in the next get dirty log call.
- */
-unsigned long *host_bmap_track;
-
-void generate_random_array(uint64_t *guest_array, uint64_t size)
-{
-	uint64_t i;
-
-	for (i = 0; i < size; i++) {
-		guest_array[i] = random();
-	}
-}
-
-void *vcpu_worker(void *data)
-{
-	int ret;
-	uint64_t loops, *guest_array, pages_count = 0;
-	struct kvm_vm *vm = data;
-	struct kvm_run *run;
-	struct ucall uc;
-
-	run = vcpu_state(vm, VCPU_ID);
-
-	/* Retrieve the guest random array pointer and cache it */
-	guest_array = addr_gva2hva(vm, (vm_vaddr_t)guest_random_array);
-
-	DEBUG("VCPU starts\n");
-
-	generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
-
-	while (!READ_ONCE(host_quit)) {
-		/* Let the guest to dirty these random pages */
-		ret = _vcpu_run(vm, VCPU_ID);
-		if (run->exit_reason == KVM_EXIT_IO &&
-		    get_ucall(vm, VCPU_ID, &uc) == UCALL_SYNC) {
-			pages_count += TEST_PAGES_PER_LOOP;
-			generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
-		} else {
-			TEST_ASSERT(false,
-				    "Invalid guest sync status: "
-				    "exit_reason=%s\n",
-				    exit_reason_str(run->exit_reason));
-		}
-	}
-
-	DEBUG("VCPU exits, dirtied %"PRIu64" pages\n", pages_count);
-
-	return NULL;
-}
-
-void vm_dirty_log_verify(unsigned long *bmap, uint64_t iteration)
-{
-	uint64_t page;
-	uint64_t volatile *value_ptr;
-
-	for (page = 0; page < TEST_MEM_PAGES; page++) {
-		value_ptr = host_test_mem + page * getpagesize();
-
-		/* If this is a special page that we were tracking... */
-		if (test_and_clear_bit(page, host_bmap_track)) {
-			host_track_next_count++;
-			TEST_ASSERT(test_bit(page, bmap),
-				    "Page %"PRIu64" should have its dirty bit "
-				    "set in this iteration but it is missing",
-				    page);
-		}
-
-		if (test_bit(page, bmap)) {
-			host_dirty_count++;
-			/*
-			 * If the bit is set, the value written onto
-			 * the corresponding page should be either the
-			 * previous iteration number or the current one.
-			 */
-			TEST_ASSERT(*value_ptr == iteration ||
-				    *value_ptr == iteration - 1,
-				    "Set page %"PRIu64" value %"PRIu64
-				    " incorrect (iteration=%"PRIu64")",
-				    page, *value_ptr, iteration);
-		} else {
-			host_clear_count++;
-			/*
-			 * If cleared, the value written can be any
-			 * value smaller or equals to the iteration
-			 * number.  Note that the value can be exactly
-			 * (iteration-1) if that write can happen
-			 * like this:
-			 *
-			 * (1) increase loop count to "iteration-1"
-			 * (2) write to page P happens (with value
-			 *     "iteration-1")
-			 * (3) get dirty log for "iteration-1"; we'll
-			 *     see that page P bit is set (dirtied),
-			 *     and not set the bit in host_bmap_track
-			 * (4) increase loop count to "iteration"
-			 *     (which is current iteration)
-			 * (5) get dirty log for current iteration,
-			 *     we'll see that page P is cleared, with
-			 *     value "iteration-1".
-			 */
-			TEST_ASSERT(*value_ptr <= iteration,
-				    "Clear page %"PRIu64" value %"PRIu64
-				    " incorrect (iteration=%"PRIu64")",
-				    page, *value_ptr, iteration);
-			if (*value_ptr == iteration) {
-				/*
-				 * This page is _just_ modified; it
-				 * should report its dirtyness in the
-				 * next run
-				 */
-				set_bit(page, host_bmap_track);
-			}
-		}
-	}
-}
-
-void help(char *name)
-{
-	puts("");
-	printf("usage: %s [-i iterations] [-I interval] [-h]\n", name);
-	puts("");
-	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
-	       TEST_HOST_LOOP_N);
-	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
-	       TEST_HOST_LOOP_INTERVAL);
-	puts("");
-	exit(0);
-}
-
-int main(int argc, char *argv[])
-{
-	pthread_t vcpu_thread;
-	struct kvm_vm *vm;
-	uint64_t volatile *psize, *iteration;
-	unsigned long *bmap, iterations = TEST_HOST_LOOP_N,
-	    interval = TEST_HOST_LOOP_INTERVAL;
-	int opt;
-
-	while ((opt = getopt(argc, argv, "hi:I:")) != -1) {
-		switch (opt) {
-		case 'i':
-			iterations = strtol(optarg, NULL, 10);
-			break;
-		case 'I':
-			interval = strtol(optarg, NULL, 10);
-			break;
-		case 'h':
-		default:
-			help(argv[0]);
-			break;
-		}
-	}
-
-	TEST_ASSERT(iterations > 2, "Iteration must be bigger than zero\n");
-	TEST_ASSERT(interval > 0, "Interval must be bigger than zero");
-
-	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
-	      iterations, interval);
-
-	srandom(time(0));
-
-	bmap = bitmap_alloc(TEST_MEM_PAGES);
-	host_bmap_track = bitmap_alloc(TEST_MEM_PAGES);
-
-	vm = vm_create_default(VCPU_ID, TEST_MEM_PAGES, guest_code);
-
-	/* Add an extra memory slot for testing dirty logging */
-	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
-				    TEST_MEM_OFFSET,
-				    TEST_MEM_SLOT_INDEX,
-				    TEST_MEM_PAGES,
-				    KVM_MEM_LOG_DIRTY_PAGES);
-	/* Cache the HVA pointer of the region */
-	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)TEST_MEM_OFFSET);
-
-	/* Do 1:1 mapping for the dirty track memory slot */
-	virt_map(vm, TEST_MEM_OFFSET, TEST_MEM_OFFSET,
-		 TEST_MEM_PAGES * getpagesize(), 0);
-
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-
-	/* Tell the guest about the page size on the system */
-	psize = addr_gva2hva(vm, (vm_vaddr_t)&guest_page_size);
-	*psize = getpagesize();
-
-	/* Start the iterations */
-	iteration = addr_gva2hva(vm, (vm_vaddr_t)&guest_iteration);
-	*iteration = 1;
-
-	/* Start dirtying pages */
-	pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
-
-	while (*iteration < iterations) {
-		/* Give the vcpu thread some time to dirty some pages */
-		usleep(interval * 1000);
-		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
-		vm_dirty_log_verify(bmap, *iteration);
-		(*iteration)++;
-	}
-
-	/* Tell the vcpu thread to quit */
-	host_quit = true;
-	pthread_join(vcpu_thread, NULL);
-
-	DEBUG("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
-	      "track_next (%"PRIu64")\n", host_dirty_count, host_clear_count,
-	      host_track_next_count);
-
-	free(bmap);
-	free(host_bmap_track);
-	kvm_vm_free(vm);
-
-	return 0;
-}
-- 
cgit v1.2.3


From e1b376f140ad9cbb1e1976f347377b8ef08a5bc9 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:34 +0200
Subject: kvm: selftests: dirty_log_test: also test 64K pages on aarch64

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/dirty_log_test.c | 183 ++++++++++++++++++++-------
 1 file changed, 137 insertions(+), 46 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index d90f1091f687..3afc7d607a2e 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -5,6 +5,8 @@
  * Copyright (C) 2018, Red Hat, Inc.
  */
 
+#define _GNU_SOURCE /* for program_invocation_name */
+
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
@@ -30,9 +32,6 @@
  */
 #define TEST_MEM_OFFSET			(1ul << 30) /* 1G */
 
-/* Size of the testing memory slot */
-#define TEST_MEM_PAGES			(1ul << 18) /* 1G for 4K pages */
-
 /* How many pages to dirty for each guest loop */
 #define TEST_PAGES_PER_LOOP		1024
 
@@ -50,6 +49,7 @@
  */
 static uint64_t host_page_size;
 static uint64_t guest_page_size;
+static uint64_t guest_num_pages;
 static uint64_t random_array[TEST_PAGES_PER_LOOP];
 static uint64_t iteration;
 
@@ -64,7 +64,7 @@ static void guest_code(void)
 	while (true) {
 		for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
 			uint64_t addr = TEST_MEM_OFFSET;
-			addr += (READ_ONCE(random_array[i]) % TEST_MEM_PAGES)
+			addr += (READ_ONCE(random_array[i]) % guest_num_pages)
 				* guest_page_size;
 			addr &= ~(host_page_size - 1);
 			*(uint64_t *)addr = READ_ONCE(iteration);
@@ -141,8 +141,10 @@ static void vm_dirty_log_verify(unsigned long *bmap)
 {
 	uint64_t page;
 	uint64_t *value_ptr;
+	uint64_t step = host_page_size >= guest_page_size ? 1 :
+				guest_page_size / host_page_size;
 
-	for (page = 0; page < host_num_pages; page++) {
+	for (page = 0; page < host_num_pages; page += step) {
 		value_ptr = host_test_mem + page * host_page_size;
 
 		/* If this is a special page that we were tracking... */
@@ -203,71 +205,64 @@ static void vm_dirty_log_verify(unsigned long *bmap)
 	}
 }
 
-static void help(char *name)
+static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
+				uint64_t extra_mem_pages, void *guest_code)
 {
-	puts("");
-	printf("usage: %s [-i iterations] [-I interval] [-h]\n", name);
-	puts("");
-	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
-	       TEST_HOST_LOOP_N);
-	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
-	       TEST_HOST_LOOP_INTERVAL);
-	puts("");
-	exit(0);
+	struct kvm_vm *vm;
+	uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
+
+	vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+#ifdef __x86_64__
+	vm_create_irqchip(vm);
+#endif
+	vm_vcpu_add_default(vm, vcpuid, guest_code);
+	return vm;
 }
 
-int main(int argc, char *argv[])
+static void run_test(enum vm_guest_mode mode, unsigned long iterations,
+		     unsigned long interval)
 {
+	unsigned int guest_page_shift;
 	pthread_t vcpu_thread;
 	struct kvm_vm *vm;
-	unsigned long iterations = TEST_HOST_LOOP_N;
-	unsigned long interval = TEST_HOST_LOOP_INTERVAL;
 	unsigned long *bmap;
-	int opt;
 
-	while ((opt = getopt(argc, argv, "hi:I:")) != -1) {
-		switch (opt) {
-		case 'i':
-			iterations = strtol(optarg, NULL, 10);
-			break;
-		case 'I':
-			interval = strtol(optarg, NULL, 10);
-			break;
-		case 'h':
-		default:
-			help(argv[0]);
-			break;
-		}
+	switch (mode) {
+	case VM_MODE_P52V48_4K:
+		guest_page_shift = 12;
+		break;
+	case VM_MODE_P52V48_64K:
+		guest_page_shift = 16;
+		break;
+	default:
+		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", mode);
 	}
 
-	TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
-	TEST_ASSERT(interval > 0, "Interval must be greater than zero");
-
-	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
-	      iterations, interval);
-
-	srandom(time(0));
+	DEBUG("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	guest_page_size = 4096;
+	guest_page_size = (1ul << guest_page_shift);
+	/* 1G of guest page sized pages */
+	guest_num_pages = (1ul << (30 - guest_page_shift));
 	host_page_size = getpagesize();
-	host_num_pages = (TEST_MEM_PAGES * guest_page_size) / host_page_size +
-			 !!((TEST_MEM_PAGES * guest_page_size) % host_page_size);
+	host_num_pages = (guest_num_pages * guest_page_size) / host_page_size +
+			 !!((guest_num_pages * guest_page_size) % host_page_size);
 
 	bmap = bitmap_alloc(host_num_pages);
 	host_bmap_track = bitmap_alloc(host_num_pages);
 
-	vm = vm_create_default(VCPU_ID, TEST_MEM_PAGES, guest_code);
+	vm = create_vm(mode, VCPU_ID, guest_num_pages, guest_code);
 
 	/* Add an extra memory slot for testing dirty logging */
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
 				    TEST_MEM_OFFSET,
 				    TEST_MEM_SLOT_INDEX,
-				    TEST_MEM_PAGES,
+				    guest_num_pages,
 				    KVM_MEM_LOG_DIRTY_PAGES);
 
 	/* Do 1:1 mapping for the dirty track memory slot */
 	virt_map(vm, TEST_MEM_OFFSET, TEST_MEM_OFFSET,
-		 TEST_MEM_PAGES * guest_page_size, 0);
+		 guest_num_pages * guest_page_size, 0);
 
 	/* Cache the HVA pointer of the region */
 	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)TEST_MEM_OFFSET);
@@ -279,13 +274,18 @@ int main(int argc, char *argv[])
 	ucall_init(vm, UCALL_MMIO, NULL);
 #endif
 
-	/* Tell the guest about the page sizes */
+	/* Export the shared variables to the guest */
 	sync_global_to_guest(vm, host_page_size);
 	sync_global_to_guest(vm, guest_page_size);
+	sync_global_to_guest(vm, guest_num_pages);
 
 	/* Start the iterations */
 	iteration = 1;
 	sync_global_to_guest(vm, iteration);
+	host_quit = false;
+	host_dirty_count = 0;
+	host_clear_count = 0;
+	host_track_next_count = 0;
 
 	pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
 
@@ -310,6 +310,97 @@ int main(int argc, char *argv[])
 	free(host_bmap_track);
 	ucall_uninit(vm);
 	kvm_vm_free(vm);
+}
+
+static struct vm_guest_modes {
+	enum vm_guest_mode mode;
+	bool supported;
+	bool enabled;
+} vm_guest_modes[NUM_VM_MODES] = {
+	{ VM_MODE_P52V48_4K,	1, 1, },
+#ifdef __aarch64__
+	{ VM_MODE_P52V48_64K,	1, 1, },
+#else
+	{ VM_MODE_P52V48_64K,	0, 0, },
+#endif
+};
+
+static void help(char *name)
+{
+	int i;
+
+	puts("");
+	printf("usage: %s [-h] [-i iterations] [-I interval] [-m mode]\n", name);
+	puts("");
+	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
+	       TEST_HOST_LOOP_N);
+	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
+	       TEST_HOST_LOOP_INTERVAL);
+	printf(" -m: specify the guest mode ID to test "
+	       "(default: test all supported modes)\n"
+	       "     This option may be used multiple times.\n"
+	       "     Guest mode IDs:\n");
+	for (i = 0; i < NUM_VM_MODES; ++i) {
+		printf("         %d:    %s%s\n",
+		       vm_guest_modes[i].mode,
+		       vm_guest_mode_string(vm_guest_modes[i].mode),
+		       vm_guest_modes[i].supported ? " (supported)" : "");
+	}
+	puts("");
+	exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+	unsigned long iterations = TEST_HOST_LOOP_N;
+	unsigned long interval = TEST_HOST_LOOP_INTERVAL;
+	bool mode_selected = false;
+	unsigned int mode;
+	int opt, i;
+
+	while ((opt = getopt(argc, argv, "hi:I:m:")) != -1) {
+		switch (opt) {
+		case 'i':
+			iterations = strtol(optarg, NULL, 10);
+			break;
+		case 'I':
+			interval = strtol(optarg, NULL, 10);
+			break;
+		case 'm':
+			if (!mode_selected) {
+				for (i = 0; i < NUM_VM_MODES; ++i)
+					vm_guest_modes[i].enabled = 0;
+				mode_selected = true;
+			}
+			mode = strtoul(optarg, NULL, 10);
+			TEST_ASSERT(mode < NUM_VM_MODES,
+				    "Guest mode ID %d too big", mode);
+			vm_guest_modes[mode].enabled = 1;
+			break;
+		case 'h':
+		default:
+			help(argv[0]);
+			break;
+		}
+	}
+
+	TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
+	TEST_ASSERT(interval > 0, "Interval must be greater than zero");
+
+	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
+	      iterations, interval);
+
+	srandom(time(0));
+
+	for (i = 0; i < NUM_VM_MODES; ++i) {
+		if (!vm_guest_modes[i].enabled)
+			continue;
+		TEST_ASSERT(vm_guest_modes[i].supported,
+			    "Guest mode ID %d (%s) not supported.",
+			    vm_guest_modes[i].mode,
+			    vm_guest_mode_string(vm_guest_modes[i].mode));
+		run_test(vm_guest_modes[i].mode, iterations, interval);
+	}
 
 	return 0;
 }
-- 
cgit v1.2.3


From e28934e661c1d9425f1cc41b405dcd8626507206 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:35 +0200
Subject: kvm: selftests: stop lying to aarch64 tests about PA-bits

Let's add the 40 PA-bit versions of the VM modes, that AArch64
should have been using, so we can extend the dirty log test without
breaking things.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/dirty_log_test.c        | 13 ++++++++++---
 tools/testing/selftests/kvm/include/kvm_util.h      |  2 ++
 tools/testing/selftests/kvm/lib/aarch64/processor.c |  8 ++++++++
 tools/testing/selftests/kvm/lib/kvm_util.c          | 16 ++++++++++++++++
 4 files changed, 36 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 3afc7d607a2e..61396882ad4e 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -230,9 +230,11 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 
 	switch (mode) {
 	case VM_MODE_P52V48_4K:
+	case VM_MODE_P40V48_4K:
 		guest_page_shift = 12;
 		break;
 	case VM_MODE_P52V48_64K:
+	case VM_MODE_P40V48_64K:
 		guest_page_shift = 16;
 		break;
 	default:
@@ -317,11 +319,16 @@ static struct vm_guest_modes {
 	bool supported;
 	bool enabled;
 } vm_guest_modes[NUM_VM_MODES] = {
+#if defined(__x86_64__)
 	{ VM_MODE_P52V48_4K,	1, 1, },
-#ifdef __aarch64__
-	{ VM_MODE_P52V48_64K,	1, 1, },
-#else
 	{ VM_MODE_P52V48_64K,	0, 0, },
+	{ VM_MODE_P40V48_4K,	0, 0, },
+	{ VM_MODE_P40V48_64K,	0, 0, },
+#elif defined(__aarch64__)
+	{ VM_MODE_P52V48_4K,	0, 0, },
+	{ VM_MODE_P52V48_64K,	0, 0, },
+	{ VM_MODE_P40V48_4K,	1, 1, },
+	{ VM_MODE_P40V48_64K,	1, 1, },
 #endif
 };
 
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 88df26c41845..a4e59e3b4826 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -36,6 +36,8 @@ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
 enum vm_guest_mode {
 	VM_MODE_P52V48_4K,
 	VM_MODE_P52V48_64K,
+	VM_MODE_P40V48_4K,
+	VM_MODE_P40V48_64K,
 	NUM_VM_MODES,
 };
 
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index b1dfc0d4b68e..b6022e2f116e 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -275,6 +275,14 @@ void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
 		tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
 		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
 		break;
+	case VM_MODE_P40V48_4K:
+		tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
+		tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
+		break;
+	case VM_MODE_P40V48_64K:
+		tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
+		tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
+		break;
 	default:
 		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode);
 	}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index b37e52f4daad..8c06da4f03db 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -99,6 +99,8 @@ static void vm_open(struct kvm_vm *vm, int perm)
 const char * const vm_guest_mode_string[] = {
 	"PA-bits:52, VA-bits:48, 4K pages",
 	"PA-bits:52, VA-bits:48, 64K pages",
+	"PA-bits:40, VA-bits:48, 4K pages",
+	"PA-bits:40, VA-bits:48, 64K pages",
 };
 
 /*
@@ -146,6 +148,20 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 		vm->page_shift = 16;
 		vm->va_bits = 48;
 		break;
+	case VM_MODE_P40V48_4K:
+		vm->pgtable_levels = 4;
+		vm->pa_bits = 40;
+		vm->va_bits = 48;
+		vm->page_size = 0x1000;
+		vm->page_shift = 12;
+		break;
+	case VM_MODE_P40V48_64K:
+		vm->pgtable_levels = 3;
+		vm->pa_bits = 40;
+		vm->va_bits = 48;
+		vm->page_size = 0x10000;
+		vm->page_shift = 16;
+		break;
 	default:
 		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", mode);
 	}
-- 
cgit v1.2.3


From 5b8ee8792f6bda46978e6e86fda4650bcbae07ab Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 18 Sep 2018 19:54:36 +0200
Subject: kvm: selftests: support high GPAs in dirty_log_test

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/dirty_log_test.c | 65 +++++++++++++++++++++-------
 1 file changed, 50 insertions(+), 15 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 61396882ad4e..d59820cc2d39 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -26,11 +26,8 @@
 /* The memory slot index to track dirty pages */
 #define TEST_MEM_SLOT_INDEX		1
 
-/*
- * GPA offset of the testing memory slot. Must be bigger than the
- * default vm mem slot, which is DEFAULT_GUEST_PHY_PAGES.
- */
-#define TEST_MEM_OFFSET			(1ul << 30) /* 1G */
+/* Default guest test memory offset, 1G */
+#define DEFAULT_GUEST_TEST_MEM		0x40000000
 
 /* How many pages to dirty for each guest loop */
 #define TEST_PAGES_PER_LOOP		1024
@@ -53,6 +50,12 @@ static uint64_t guest_num_pages;
 static uint64_t random_array[TEST_PAGES_PER_LOOP];
 static uint64_t iteration;
 
+/*
+ * GPA offset of the testing memory slot. Must be bigger than
+ * DEFAULT_GUEST_PHY_PAGES.
+ */
+static uint64_t guest_test_mem = DEFAULT_GUEST_TEST_MEM;
+
 /*
  * Continuously write to the first 8 bytes of a random pages within
  * the testing memory region.
@@ -63,7 +66,7 @@ static void guest_code(void)
 
 	while (true) {
 		for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
-			uint64_t addr = TEST_MEM_OFFSET;
+			uint64_t addr = guest_test_mem;
 			addr += (READ_ONCE(random_array[i]) % guest_num_pages)
 				* guest_page_size;
 			addr &= ~(host_page_size - 1);
@@ -221,20 +224,29 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
 }
 
 static void run_test(enum vm_guest_mode mode, unsigned long iterations,
-		     unsigned long interval)
+		     unsigned long interval, bool top_offset)
 {
-	unsigned int guest_page_shift;
+	unsigned int guest_pa_bits, guest_page_shift;
 	pthread_t vcpu_thread;
 	struct kvm_vm *vm;
+	uint64_t max_gfn;
 	unsigned long *bmap;
 
 	switch (mode) {
 	case VM_MODE_P52V48_4K:
-	case VM_MODE_P40V48_4K:
+		guest_pa_bits = 52;
 		guest_page_shift = 12;
 		break;
 	case VM_MODE_P52V48_64K:
+		guest_pa_bits = 52;
+		guest_page_shift = 16;
+		break;
+	case VM_MODE_P40V48_4K:
+		guest_pa_bits = 40;
+		guest_page_shift = 12;
+		break;
 	case VM_MODE_P40V48_64K:
+		guest_pa_bits = 40;
 		guest_page_shift = 16;
 		break;
 	default:
@@ -243,6 +255,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 
 	DEBUG("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
+	max_gfn = (1ul << (guest_pa_bits - guest_page_shift)) - 1;
 	guest_page_size = (1ul << guest_page_shift);
 	/* 1G of guest page sized pages */
 	guest_num_pages = (1ul << (30 - guest_page_shift));
@@ -250,6 +263,13 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	host_num_pages = (guest_num_pages * guest_page_size) / host_page_size +
 			 !!((guest_num_pages * guest_page_size) % host_page_size);
 
+	if (top_offset) {
+		guest_test_mem = (max_gfn - guest_num_pages) * guest_page_size;
+		guest_test_mem &= ~(host_page_size - 1);
+	}
+
+	DEBUG("guest test mem offset: 0x%lx\n", guest_test_mem);
+
 	bmap = bitmap_alloc(host_num_pages);
 	host_bmap_track = bitmap_alloc(host_num_pages);
 
@@ -257,17 +277,17 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 
 	/* Add an extra memory slot for testing dirty logging */
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
-				    TEST_MEM_OFFSET,
+				    guest_test_mem,
 				    TEST_MEM_SLOT_INDEX,
 				    guest_num_pages,
 				    KVM_MEM_LOG_DIRTY_PAGES);
 
 	/* Do 1:1 mapping for the dirty track memory slot */
-	virt_map(vm, TEST_MEM_OFFSET, TEST_MEM_OFFSET,
+	virt_map(vm, guest_test_mem, guest_test_mem,
 		 guest_num_pages * guest_page_size, 0);
 
 	/* Cache the HVA pointer of the region */
-	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)TEST_MEM_OFFSET);
+	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_mem);
 
 #ifdef __x86_64__
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
@@ -279,6 +299,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	/* Export the shared variables to the guest */
 	sync_global_to_guest(vm, host_page_size);
 	sync_global_to_guest(vm, guest_page_size);
+	sync_global_to_guest(vm, guest_test_mem);
 	sync_global_to_guest(vm, guest_num_pages);
 
 	/* Start the iterations */
@@ -337,12 +358,17 @@ static void help(char *name)
 	int i;
 
 	puts("");
-	printf("usage: %s [-h] [-i iterations] [-I interval] [-m mode]\n", name);
+	printf("usage: %s [-h] [-i iterations] [-I interval] "
+	       "[-o offset] [-t] [-m mode]\n", name);
 	puts("");
 	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
 	       TEST_HOST_LOOP_N);
 	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
 	       TEST_HOST_LOOP_INTERVAL);
+	printf(" -o: guest test memory offset (default: 0x%lx)\n",
+	       DEFAULT_GUEST_TEST_MEM);
+	printf(" -t: map guest test memory at the top of the allowed "
+	       "physical address range\n");
 	printf(" -m: specify the guest mode ID to test "
 	       "(default: test all supported modes)\n"
 	       "     This option may be used multiple times.\n"
@@ -362,10 +388,11 @@ int main(int argc, char *argv[])
 	unsigned long iterations = TEST_HOST_LOOP_N;
 	unsigned long interval = TEST_HOST_LOOP_INTERVAL;
 	bool mode_selected = false;
+	bool top_offset = false;
 	unsigned int mode;
 	int opt, i;
 
-	while ((opt = getopt(argc, argv, "hi:I:m:")) != -1) {
+	while ((opt = getopt(argc, argv, "hi:I:o:tm:")) != -1) {
 		switch (opt) {
 		case 'i':
 			iterations = strtol(optarg, NULL, 10);
@@ -373,6 +400,12 @@ int main(int argc, char *argv[])
 		case 'I':
 			interval = strtol(optarg, NULL, 10);
 			break;
+		case 'o':
+			guest_test_mem = strtoull(optarg, NULL, 0);
+			break;
+		case 't':
+			top_offset = true;
+			break;
 		case 'm':
 			if (!mode_selected) {
 				for (i = 0; i < NUM_VM_MODES; ++i)
@@ -393,6 +426,8 @@ int main(int argc, char *argv[])
 
 	TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
 	TEST_ASSERT(interval > 0, "Interval must be greater than zero");
+	TEST_ASSERT(!top_offset || guest_test_mem == DEFAULT_GUEST_TEST_MEM,
+		    "Cannot use both -o [offset] and -t at the same time");
 
 	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
 	      iterations, interval);
@@ -406,7 +441,7 @@ int main(int argc, char *argv[])
 			    "Guest mode ID %d (%s) not supported.",
 			    vm_guest_modes[i].mode,
 			    vm_guest_mode_string(vm_guest_modes[i].mode));
-		run_test(vm_guest_modes[i].mode, iterations, interval);
+		run_test(vm_guest_modes[i].mode, iterations, interval, top_offset);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 1e7ecd1b3d21a6302f3ee4a3720f682eb2467a3c Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 16 Oct 2018 18:50:08 +0200
Subject: KVM: selftests: state_test: test bare VMXON migration

Split prepare_for_vmx_operation() into prepare_for_vmx_operation() and
load_vmcs() so we can inject GUEST_SYNC() in between.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/x86_64/vmx.h   |  1 +
 tools/testing/selftests/kvm/lib/x86_64/vmx.c       |  5 +++++
 tools/testing/selftests/kvm/x86_64/state_test.c    | 22 ++++++++++++----------
 .../selftests/kvm/x86_64/vmx_tsc_adjust_test.c     |  1 +
 4 files changed, 19 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 12ebd836f7ef..4bbee8560292 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -548,5 +548,6 @@ struct vmx_pages {
 struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva);
 bool prepare_for_vmx_operation(struct vmx_pages *vmx);
 void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp);
+bool load_vmcs(struct vmx_pages *vmx);
 
 #endif /* SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index d7c401472247..cc356da9b3d8 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -107,6 +107,11 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx)
 	if (vmxon(vmx->vmxon_gpa))
 		return false;
 
+	return true;
+}
+
+bool load_vmcs(struct vmx_pages *vmx)
+{
 	/* Load a VMCS. */
 	*(uint32_t *)(vmx->vmcs) = vmcs_revision();
 	if (vmclear(vmx->vmcs_gpa))
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index 43df194a7c1e..03da41f0f736 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -26,20 +26,20 @@ static bool have_nested_state;
 
 void l2_guest_code(void)
 {
-	GUEST_SYNC(5);
+	GUEST_SYNC(6);
 
         /* Exit to L1 */
 	vmcall();
 
 	/* L1 has now set up a shadow VMCS for us.  */
 	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
-	GUEST_SYNC(9);
+	GUEST_SYNC(10);
 	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
 	GUEST_ASSERT(!vmwrite(GUEST_RIP, 0xc0fffee));
-	GUEST_SYNC(10);
+	GUEST_SYNC(11);
 	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0fffee);
 	GUEST_ASSERT(!vmwrite(GUEST_RIP, 0xc0ffffee));
-	GUEST_SYNC(11);
+	GUEST_SYNC(12);
 
 	/* Done, exit to L1 and never come back.  */
 	vmcall();
@@ -52,15 +52,17 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
 
 	GUEST_ASSERT(vmx_pages->vmcs_gpa);
 	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+	GUEST_SYNC(3);
+	GUEST_ASSERT(load_vmcs(vmx_pages));
 	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
 
-	GUEST_SYNC(3);
+	GUEST_SYNC(4);
 	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
 
 	prepare_vmcs(vmx_pages, l2_guest_code,
 		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
 
-	GUEST_SYNC(4);
+	GUEST_SYNC(5);
 	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
 	GUEST_ASSERT(!vmlaunch());
 	GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
@@ -72,7 +74,7 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
 	GUEST_ASSERT(!vmresume());
 	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
 
-	GUEST_SYNC(6);
+	GUEST_SYNC(7);
 	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
 
 	GUEST_ASSERT(!vmresume());
@@ -85,12 +87,12 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
 
 	GUEST_ASSERT(!vmptrld(vmx_pages->shadow_vmcs_gpa));
 	GUEST_ASSERT(vmlaunch());
-	GUEST_SYNC(7);
+	GUEST_SYNC(8);
 	GUEST_ASSERT(vmlaunch());
 	GUEST_ASSERT(vmresume());
 
 	vmwrite(GUEST_RIP, 0xc0ffee);
-	GUEST_SYNC(8);
+	GUEST_SYNC(9);
 	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
 
 	GUEST_ASSERT(!vmptrld(vmx_pages->vmcs_gpa));
@@ -101,7 +103,7 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
 	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffffee);
 	GUEST_ASSERT(vmlaunch());
 	GUEST_ASSERT(vmresume());
-	GUEST_SYNC(12);
+	GUEST_SYNC(13);
 	GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffffee);
 	GUEST_ASSERT(vmlaunch());
 	GUEST_ASSERT(vmresume());
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
index 38a91a5f04ac..18fa64db0d7a 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
@@ -94,6 +94,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
 	check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
 
 	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+	GUEST_ASSERT(load_vmcs(vmx_pages));
 
 	/* Prepare the VMCS for L2 execution. */
 	prepare_vmcs(vmx_pages, l2_guest_code,
-- 
cgit v1.2.3


From c939989d74e27f44229a51d8fe96b5c297965bfa Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 16 Oct 2018 18:50:10 +0200
Subject: tools/headers: update kvm.h

Pick up the latest kvm.h definitions.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/include/uapi/linux/kvm.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 07548de5c988..2875ce85b322 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -719,6 +719,7 @@ struct kvm_ppc_one_seg_page_size {
 
 #define KVM_PPC_PAGE_SIZES_REAL		0x00000001
 #define KVM_PPC_1T_SEGMENTS		0x00000002
+#define KVM_PPC_NO_HASH			0x00000004
 
 struct kvm_ppc_smmu_info {
 	__u64 flags;
@@ -952,6 +953,11 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_HPAGE_1M 156
 #define KVM_CAP_NESTED_STATE 157
 #define KVM_CAP_ARM_INJECT_SERROR_ESR 158
+#define KVM_CAP_MSR_PLATFORM_INFO 159
+#define KVM_CAP_PPC_NESTED_HV 160
+#define KVM_CAP_HYPERV_SEND_IPI 161
+#define KVM_CAP_COALESCED_PIO 162
+#define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3


From 18178ff862170ee4c9fd7450173c6fba9e3c4c3a Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 16 Oct 2018 18:50:11 +0200
Subject: KVM: selftests: add Enlightened VMCS test

Modify test library and add eVMCS test. This includes nVMX save/restore
testing.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/Makefile             |    1 +
 tools/testing/selftests/kvm/include/evmcs.h      | 1098 ++++++++++++++++++++++
 tools/testing/selftests/kvm/include/x86_64/vmx.h |   28 +
 tools/testing/selftests/kvm/lib/x86_64/vmx.c     |   48 +-
 tools/testing/selftests/kvm/x86_64/evmcs_test.c  |  160 ++++
 5 files changed, 1323 insertions(+), 12 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/include/evmcs.h
 create mode 100644 tools/testing/selftests/kvm/x86_64/evmcs_test.c

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 5e23f97ec46f..01a219229238 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -13,6 +13,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
 TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += x86_64/state_test
+TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 
 TEST_GEN_PROGS_aarch64 += dirty_log_test
diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/evmcs.h
new file mode 100644
index 000000000000..4059014d93ea
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/evmcs.h
@@ -0,0 +1,1098 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * tools/testing/selftests/kvm/include/vmx.h
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ *
+ */
+
+#ifndef SELFTEST_KVM_EVMCS_H
+#define SELFTEST_KVM_EVMCS_H
+
+#include <stdint.h>
+#include "vmx.h"
+
+#define u16 uint16_t
+#define u32 uint32_t
+#define u64 uint64_t
+
+extern bool enable_evmcs;
+
+struct hv_vp_assist_page {
+	__u32 apic_assist;
+	__u32 reserved;
+	__u64 vtl_control[2];
+	__u64 nested_enlightenments_control[2];
+	__u32 enlighten_vmentry;
+	__u64 current_nested_vmcs;
+};
+
+struct hv_enlightened_vmcs {
+	u32 revision_id;
+	u32 abort;
+
+	u16 host_es_selector;
+	u16 host_cs_selector;
+	u16 host_ss_selector;
+	u16 host_ds_selector;
+	u16 host_fs_selector;
+	u16 host_gs_selector;
+	u16 host_tr_selector;
+
+	u64 host_ia32_pat;
+	u64 host_ia32_efer;
+
+	u64 host_cr0;
+	u64 host_cr3;
+	u64 host_cr4;
+
+	u64 host_ia32_sysenter_esp;
+	u64 host_ia32_sysenter_eip;
+	u64 host_rip;
+	u32 host_ia32_sysenter_cs;
+
+	u32 pin_based_vm_exec_control;
+	u32 vm_exit_controls;
+	u32 secondary_vm_exec_control;
+
+	u64 io_bitmap_a;
+	u64 io_bitmap_b;
+	u64 msr_bitmap;
+
+	u16 guest_es_selector;
+	u16 guest_cs_selector;
+	u16 guest_ss_selector;
+	u16 guest_ds_selector;
+	u16 guest_fs_selector;
+	u16 guest_gs_selector;
+	u16 guest_ldtr_selector;
+	u16 guest_tr_selector;
+
+	u32 guest_es_limit;
+	u32 guest_cs_limit;
+	u32 guest_ss_limit;
+	u32 guest_ds_limit;
+	u32 guest_fs_limit;
+	u32 guest_gs_limit;
+	u32 guest_ldtr_limit;
+	u32 guest_tr_limit;
+	u32 guest_gdtr_limit;
+	u32 guest_idtr_limit;
+
+	u32 guest_es_ar_bytes;
+	u32 guest_cs_ar_bytes;
+	u32 guest_ss_ar_bytes;
+	u32 guest_ds_ar_bytes;
+	u32 guest_fs_ar_bytes;
+	u32 guest_gs_ar_bytes;
+	u32 guest_ldtr_ar_bytes;
+	u32 guest_tr_ar_bytes;
+
+	u64 guest_es_base;
+	u64 guest_cs_base;
+	u64 guest_ss_base;
+	u64 guest_ds_base;
+	u64 guest_fs_base;
+	u64 guest_gs_base;
+	u64 guest_ldtr_base;
+	u64 guest_tr_base;
+	u64 guest_gdtr_base;
+	u64 guest_idtr_base;
+
+	u64 padding64_1[3];
+
+	u64 vm_exit_msr_store_addr;
+	u64 vm_exit_msr_load_addr;
+	u64 vm_entry_msr_load_addr;
+
+	u64 cr3_target_value0;
+	u64 cr3_target_value1;
+	u64 cr3_target_value2;
+	u64 cr3_target_value3;
+
+	u32 page_fault_error_code_mask;
+	u32 page_fault_error_code_match;
+
+	u32 cr3_target_count;
+	u32 vm_exit_msr_store_count;
+	u32 vm_exit_msr_load_count;
+	u32 vm_entry_msr_load_count;
+
+	u64 tsc_offset;
+	u64 virtual_apic_page_addr;
+	u64 vmcs_link_pointer;
+
+	u64 guest_ia32_debugctl;
+	u64 guest_ia32_pat;
+	u64 guest_ia32_efer;
+
+	u64 guest_pdptr0;
+	u64 guest_pdptr1;
+	u64 guest_pdptr2;
+	u64 guest_pdptr3;
+
+	u64 guest_pending_dbg_exceptions;
+	u64 guest_sysenter_esp;
+	u64 guest_sysenter_eip;
+
+	u32 guest_activity_state;
+	u32 guest_sysenter_cs;
+
+	u64 cr0_guest_host_mask;
+	u64 cr4_guest_host_mask;
+	u64 cr0_read_shadow;
+	u64 cr4_read_shadow;
+	u64 guest_cr0;
+	u64 guest_cr3;
+	u64 guest_cr4;
+	u64 guest_dr7;
+
+	u64 host_fs_base;
+	u64 host_gs_base;
+	u64 host_tr_base;
+	u64 host_gdtr_base;
+	u64 host_idtr_base;
+	u64 host_rsp;
+
+	u64 ept_pointer;
+
+	u16 virtual_processor_id;
+	u16 padding16[3];
+
+	u64 padding64_2[5];
+	u64 guest_physical_address;
+
+	u32 vm_instruction_error;
+	u32 vm_exit_reason;
+	u32 vm_exit_intr_info;
+	u32 vm_exit_intr_error_code;
+	u32 idt_vectoring_info_field;
+	u32 idt_vectoring_error_code;
+	u32 vm_exit_instruction_len;
+	u32 vmx_instruction_info;
+
+	u64 exit_qualification;
+	u64 exit_io_instruction_ecx;
+	u64 exit_io_instruction_esi;
+	u64 exit_io_instruction_edi;
+	u64 exit_io_instruction_eip;
+
+	u64 guest_linear_address;
+	u64 guest_rsp;
+	u64 guest_rflags;
+
+	u32 guest_interruptibility_info;
+	u32 cpu_based_vm_exec_control;
+	u32 exception_bitmap;
+	u32 vm_entry_controls;
+	u32 vm_entry_intr_info_field;
+	u32 vm_entry_exception_error_code;
+	u32 vm_entry_instruction_len;
+	u32 tpr_threshold;
+
+	u64 guest_rip;
+
+	u32 hv_clean_fields;
+	u32 hv_padding_32;
+	u32 hv_synthetic_controls;
+	struct {
+		u32 nested_flush_hypercall:1;
+		u32 msr_bitmap:1;
+		u32 reserved:30;
+	} hv_enlightenments_control;
+	u32 hv_vp_id;
+
+	u64 hv_vm_id;
+	u64 partition_assist_page;
+	u64 padding64_4[4];
+	u64 guest_bndcfgs;
+	u64 padding64_5[7];
+	u64 xss_exit_bitmap;
+	u64 padding64_6[7];
+};
+
+#define HV_X64_MSR_VP_ASSIST_PAGE		0x40000073
+#define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE	0x00000001
+#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT	12
+#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK	\
+		(~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
+
+struct hv_enlightened_vmcs *current_evmcs;
+struct hv_vp_assist_page *current_vp_assist;
+
+static inline int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist)
+{
+	u64 val = (vp_assist_pa & HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK) |
+		HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
+
+	wrmsr(HV_X64_MSR_VP_ASSIST_PAGE, val);
+
+	current_vp_assist = vp_assist;
+
+	enable_evmcs = true;
+
+	return 0;
+}
+
+static inline int evmcs_vmptrld(uint64_t vmcs_pa, void *vmcs)
+{
+	current_vp_assist->current_nested_vmcs = vmcs_pa;
+	current_vp_assist->enlighten_vmentry = 1;
+
+	current_evmcs = vmcs;
+
+	return 0;
+}
+
+static inline int evmcs_vmptrst(uint64_t *value)
+{
+	*value = current_vp_assist->current_nested_vmcs &
+		~HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
+
+	return 0;
+}
+
+static inline int evmcs_vmread(uint64_t encoding, uint64_t *value)
+{
+	switch (encoding) {
+	case GUEST_RIP:
+		*value = current_evmcs->guest_rip;
+		break;
+	case GUEST_RSP:
+		*value = current_evmcs->guest_rsp;
+		break;
+	case GUEST_RFLAGS:
+		*value = current_evmcs->guest_rflags;
+		break;
+	case HOST_IA32_PAT:
+		*value = current_evmcs->host_ia32_pat;
+		break;
+	case HOST_IA32_EFER:
+		*value = current_evmcs->host_ia32_efer;
+		break;
+	case HOST_CR0:
+		*value = current_evmcs->host_cr0;
+		break;
+	case HOST_CR3:
+		*value = current_evmcs->host_cr3;
+		break;
+	case HOST_CR4:
+		*value = current_evmcs->host_cr4;
+		break;
+	case HOST_IA32_SYSENTER_ESP:
+		*value = current_evmcs->host_ia32_sysenter_esp;
+		break;
+	case HOST_IA32_SYSENTER_EIP:
+		*value = current_evmcs->host_ia32_sysenter_eip;
+		break;
+	case HOST_RIP:
+		*value = current_evmcs->host_rip;
+		break;
+	case IO_BITMAP_A:
+		*value = current_evmcs->io_bitmap_a;
+		break;
+	case IO_BITMAP_B:
+		*value = current_evmcs->io_bitmap_b;
+		break;
+	case MSR_BITMAP:
+		*value = current_evmcs->msr_bitmap;
+		break;
+	case GUEST_ES_BASE:
+		*value = current_evmcs->guest_es_base;
+		break;
+	case GUEST_CS_BASE:
+		*value = current_evmcs->guest_cs_base;
+		break;
+	case GUEST_SS_BASE:
+		*value = current_evmcs->guest_ss_base;
+		break;
+	case GUEST_DS_BASE:
+		*value = current_evmcs->guest_ds_base;
+		break;
+	case GUEST_FS_BASE:
+		*value = current_evmcs->guest_fs_base;
+		break;
+	case GUEST_GS_BASE:
+		*value = current_evmcs->guest_gs_base;
+		break;
+	case GUEST_LDTR_BASE:
+		*value = current_evmcs->guest_ldtr_base;
+		break;
+	case GUEST_TR_BASE:
+		*value = current_evmcs->guest_tr_base;
+		break;
+	case GUEST_GDTR_BASE:
+		*value = current_evmcs->guest_gdtr_base;
+		break;
+	case GUEST_IDTR_BASE:
+		*value = current_evmcs->guest_idtr_base;
+		break;
+	case TSC_OFFSET:
+		*value = current_evmcs->tsc_offset;
+		break;
+	case VIRTUAL_APIC_PAGE_ADDR:
+		*value = current_evmcs->virtual_apic_page_addr;
+		break;
+	case VMCS_LINK_POINTER:
+		*value = current_evmcs->vmcs_link_pointer;
+		break;
+	case GUEST_IA32_DEBUGCTL:
+		*value = current_evmcs->guest_ia32_debugctl;
+		break;
+	case GUEST_IA32_PAT:
+		*value = current_evmcs->guest_ia32_pat;
+		break;
+	case GUEST_IA32_EFER:
+		*value = current_evmcs->guest_ia32_efer;
+		break;
+	case GUEST_PDPTR0:
+		*value = current_evmcs->guest_pdptr0;
+		break;
+	case GUEST_PDPTR1:
+		*value = current_evmcs->guest_pdptr1;
+		break;
+	case GUEST_PDPTR2:
+		*value = current_evmcs->guest_pdptr2;
+		break;
+	case GUEST_PDPTR3:
+		*value = current_evmcs->guest_pdptr3;
+		break;
+	case GUEST_PENDING_DBG_EXCEPTIONS:
+		*value = current_evmcs->guest_pending_dbg_exceptions;
+		break;
+	case GUEST_SYSENTER_ESP:
+		*value = current_evmcs->guest_sysenter_esp;
+		break;
+	case GUEST_SYSENTER_EIP:
+		*value = current_evmcs->guest_sysenter_eip;
+		break;
+	case CR0_GUEST_HOST_MASK:
+		*value = current_evmcs->cr0_guest_host_mask;
+		break;
+	case CR4_GUEST_HOST_MASK:
+		*value = current_evmcs->cr4_guest_host_mask;
+		break;
+	case CR0_READ_SHADOW:
+		*value = current_evmcs->cr0_read_shadow;
+		break;
+	case CR4_READ_SHADOW:
+		*value = current_evmcs->cr4_read_shadow;
+		break;
+	case GUEST_CR0:
+		*value = current_evmcs->guest_cr0;
+		break;
+	case GUEST_CR3:
+		*value = current_evmcs->guest_cr3;
+		break;
+	case GUEST_CR4:
+		*value = current_evmcs->guest_cr4;
+		break;
+	case GUEST_DR7:
+		*value = current_evmcs->guest_dr7;
+		break;
+	case HOST_FS_BASE:
+		*value = current_evmcs->host_fs_base;
+		break;
+	case HOST_GS_BASE:
+		*value = current_evmcs->host_gs_base;
+		break;
+	case HOST_TR_BASE:
+		*value = current_evmcs->host_tr_base;
+		break;
+	case HOST_GDTR_BASE:
+		*value = current_evmcs->host_gdtr_base;
+		break;
+	case HOST_IDTR_BASE:
+		*value = current_evmcs->host_idtr_base;
+		break;
+	case HOST_RSP:
+		*value = current_evmcs->host_rsp;
+		break;
+	case EPT_POINTER:
+		*value = current_evmcs->ept_pointer;
+		break;
+	case GUEST_BNDCFGS:
+		*value = current_evmcs->guest_bndcfgs;
+		break;
+	case XSS_EXIT_BITMAP:
+		*value = current_evmcs->xss_exit_bitmap;
+		break;
+	case GUEST_PHYSICAL_ADDRESS:
+		*value = current_evmcs->guest_physical_address;
+		break;
+	case EXIT_QUALIFICATION:
+		*value = current_evmcs->exit_qualification;
+		break;
+	case GUEST_LINEAR_ADDRESS:
+		*value = current_evmcs->guest_linear_address;
+		break;
+	case VM_EXIT_MSR_STORE_ADDR:
+		*value = current_evmcs->vm_exit_msr_store_addr;
+		break;
+	case VM_EXIT_MSR_LOAD_ADDR:
+		*value = current_evmcs->vm_exit_msr_load_addr;
+		break;
+	case VM_ENTRY_MSR_LOAD_ADDR:
+		*value = current_evmcs->vm_entry_msr_load_addr;
+		break;
+	case CR3_TARGET_VALUE0:
+		*value = current_evmcs->cr3_target_value0;
+		break;
+	case CR3_TARGET_VALUE1:
+		*value = current_evmcs->cr3_target_value1;
+		break;
+	case CR3_TARGET_VALUE2:
+		*value = current_evmcs->cr3_target_value2;
+		break;
+	case CR3_TARGET_VALUE3:
+		*value = current_evmcs->cr3_target_value3;
+		break;
+	case TPR_THRESHOLD:
+		*value = current_evmcs->tpr_threshold;
+		break;
+	case GUEST_INTERRUPTIBILITY_INFO:
+		*value = current_evmcs->guest_interruptibility_info;
+		break;
+	case CPU_BASED_VM_EXEC_CONTROL:
+		*value = current_evmcs->cpu_based_vm_exec_control;
+		break;
+	case EXCEPTION_BITMAP:
+		*value = current_evmcs->exception_bitmap;
+		break;
+	case VM_ENTRY_CONTROLS:
+		*value = current_evmcs->vm_entry_controls;
+		break;
+	case VM_ENTRY_INTR_INFO_FIELD:
+		*value = current_evmcs->vm_entry_intr_info_field;
+		break;
+	case VM_ENTRY_EXCEPTION_ERROR_CODE:
+		*value = current_evmcs->vm_entry_exception_error_code;
+		break;
+	case VM_ENTRY_INSTRUCTION_LEN:
+		*value = current_evmcs->vm_entry_instruction_len;
+		break;
+	case HOST_IA32_SYSENTER_CS:
+		*value = current_evmcs->host_ia32_sysenter_cs;
+		break;
+	case PIN_BASED_VM_EXEC_CONTROL:
+		*value = current_evmcs->pin_based_vm_exec_control;
+		break;
+	case VM_EXIT_CONTROLS:
+		*value = current_evmcs->vm_exit_controls;
+		break;
+	case SECONDARY_VM_EXEC_CONTROL:
+		*value = current_evmcs->secondary_vm_exec_control;
+		break;
+	case GUEST_ES_LIMIT:
+		*value = current_evmcs->guest_es_limit;
+		break;
+	case GUEST_CS_LIMIT:
+		*value = current_evmcs->guest_cs_limit;
+		break;
+	case GUEST_SS_LIMIT:
+		*value = current_evmcs->guest_ss_limit;
+		break;
+	case GUEST_DS_LIMIT:
+		*value = current_evmcs->guest_ds_limit;
+		break;
+	case GUEST_FS_LIMIT:
+		*value = current_evmcs->guest_fs_limit;
+		break;
+	case GUEST_GS_LIMIT:
+		*value = current_evmcs->guest_gs_limit;
+		break;
+	case GUEST_LDTR_LIMIT:
+		*value = current_evmcs->guest_ldtr_limit;
+		break;
+	case GUEST_TR_LIMIT:
+		*value = current_evmcs->guest_tr_limit;
+		break;
+	case GUEST_GDTR_LIMIT:
+		*value = current_evmcs->guest_gdtr_limit;
+		break;
+	case GUEST_IDTR_LIMIT:
+		*value = current_evmcs->guest_idtr_limit;
+		break;
+	case GUEST_ES_AR_BYTES:
+		*value = current_evmcs->guest_es_ar_bytes;
+		break;
+	case GUEST_CS_AR_BYTES:
+		*value = current_evmcs->guest_cs_ar_bytes;
+		break;
+	case GUEST_SS_AR_BYTES:
+		*value = current_evmcs->guest_ss_ar_bytes;
+		break;
+	case GUEST_DS_AR_BYTES:
+		*value = current_evmcs->guest_ds_ar_bytes;
+		break;
+	case GUEST_FS_AR_BYTES:
+		*value = current_evmcs->guest_fs_ar_bytes;
+		break;
+	case GUEST_GS_AR_BYTES:
+		*value = current_evmcs->guest_gs_ar_bytes;
+		break;
+	case GUEST_LDTR_AR_BYTES:
+		*value = current_evmcs->guest_ldtr_ar_bytes;
+		break;
+	case GUEST_TR_AR_BYTES:
+		*value = current_evmcs->guest_tr_ar_bytes;
+		break;
+	case GUEST_ACTIVITY_STATE:
+		*value = current_evmcs->guest_activity_state;
+		break;
+	case GUEST_SYSENTER_CS:
+		*value = current_evmcs->guest_sysenter_cs;
+		break;
+	case VM_INSTRUCTION_ERROR:
+		*value = current_evmcs->vm_instruction_error;
+		break;
+	case VM_EXIT_REASON:
+		*value = current_evmcs->vm_exit_reason;
+		break;
+	case VM_EXIT_INTR_INFO:
+		*value = current_evmcs->vm_exit_intr_info;
+		break;
+	case VM_EXIT_INTR_ERROR_CODE:
+		*value = current_evmcs->vm_exit_intr_error_code;
+		break;
+	case IDT_VECTORING_INFO_FIELD:
+		*value = current_evmcs->idt_vectoring_info_field;
+		break;
+	case IDT_VECTORING_ERROR_CODE:
+		*value = current_evmcs->idt_vectoring_error_code;
+		break;
+	case VM_EXIT_INSTRUCTION_LEN:
+		*value = current_evmcs->vm_exit_instruction_len;
+		break;
+	case VMX_INSTRUCTION_INFO:
+		*value = current_evmcs->vmx_instruction_info;
+		break;
+	case PAGE_FAULT_ERROR_CODE_MASK:
+		*value = current_evmcs->page_fault_error_code_mask;
+		break;
+	case PAGE_FAULT_ERROR_CODE_MATCH:
+		*value = current_evmcs->page_fault_error_code_match;
+		break;
+	case CR3_TARGET_COUNT:
+		*value = current_evmcs->cr3_target_count;
+		break;
+	case VM_EXIT_MSR_STORE_COUNT:
+		*value = current_evmcs->vm_exit_msr_store_count;
+		break;
+	case VM_EXIT_MSR_LOAD_COUNT:
+		*value = current_evmcs->vm_exit_msr_load_count;
+		break;
+	case VM_ENTRY_MSR_LOAD_COUNT:
+		*value = current_evmcs->vm_entry_msr_load_count;
+		break;
+	case HOST_ES_SELECTOR:
+		*value = current_evmcs->host_es_selector;
+		break;
+	case HOST_CS_SELECTOR:
+		*value = current_evmcs->host_cs_selector;
+		break;
+	case HOST_SS_SELECTOR:
+		*value = current_evmcs->host_ss_selector;
+		break;
+	case HOST_DS_SELECTOR:
+		*value = current_evmcs->host_ds_selector;
+		break;
+	case HOST_FS_SELECTOR:
+		*value = current_evmcs->host_fs_selector;
+		break;
+	case HOST_GS_SELECTOR:
+		*value = current_evmcs->host_gs_selector;
+		break;
+	case HOST_TR_SELECTOR:
+		*value = current_evmcs->host_tr_selector;
+		break;
+	case GUEST_ES_SELECTOR:
+		*value = current_evmcs->guest_es_selector;
+		break;
+	case GUEST_CS_SELECTOR:
+		*value = current_evmcs->guest_cs_selector;
+		break;
+	case GUEST_SS_SELECTOR:
+		*value = current_evmcs->guest_ss_selector;
+		break;
+	case GUEST_DS_SELECTOR:
+		*value = current_evmcs->guest_ds_selector;
+		break;
+	case GUEST_FS_SELECTOR:
+		*value = current_evmcs->guest_fs_selector;
+		break;
+	case GUEST_GS_SELECTOR:
+		*value = current_evmcs->guest_gs_selector;
+		break;
+	case GUEST_LDTR_SELECTOR:
+		*value = current_evmcs->guest_ldtr_selector;
+		break;
+	case GUEST_TR_SELECTOR:
+		*value = current_evmcs->guest_tr_selector;
+		break;
+	case VIRTUAL_PROCESSOR_ID:
+		*value = current_evmcs->virtual_processor_id;
+		break;
+	default: return 1;
+	}
+
+	return 0;
+}
+
+static inline int evmcs_vmwrite(uint64_t encoding, uint64_t value)
+{
+	switch (encoding) {
+	case GUEST_RIP:
+		current_evmcs->guest_rip = value;
+		break;
+	case GUEST_RSP:
+		current_evmcs->guest_rsp = value;
+		break;
+	case GUEST_RFLAGS:
+		current_evmcs->guest_rflags = value;
+		break;
+	case HOST_IA32_PAT:
+		current_evmcs->host_ia32_pat = value;
+		break;
+	case HOST_IA32_EFER:
+		current_evmcs->host_ia32_efer = value;
+		break;
+	case HOST_CR0:
+		current_evmcs->host_cr0 = value;
+		break;
+	case HOST_CR3:
+		current_evmcs->host_cr3 = value;
+		break;
+	case HOST_CR4:
+		current_evmcs->host_cr4 = value;
+		break;
+	case HOST_IA32_SYSENTER_ESP:
+		current_evmcs->host_ia32_sysenter_esp = value;
+		break;
+	case HOST_IA32_SYSENTER_EIP:
+		current_evmcs->host_ia32_sysenter_eip = value;
+		break;
+	case HOST_RIP:
+		current_evmcs->host_rip = value;
+		break;
+	case IO_BITMAP_A:
+		current_evmcs->io_bitmap_a = value;
+		break;
+	case IO_BITMAP_B:
+		current_evmcs->io_bitmap_b = value;
+		break;
+	case MSR_BITMAP:
+		current_evmcs->msr_bitmap = value;
+		break;
+	case GUEST_ES_BASE:
+		current_evmcs->guest_es_base = value;
+		break;
+	case GUEST_CS_BASE:
+		current_evmcs->guest_cs_base = value;
+		break;
+	case GUEST_SS_BASE:
+		current_evmcs->guest_ss_base = value;
+		break;
+	case GUEST_DS_BASE:
+		current_evmcs->guest_ds_base = value;
+		break;
+	case GUEST_FS_BASE:
+		current_evmcs->guest_fs_base = value;
+		break;
+	case GUEST_GS_BASE:
+		current_evmcs->guest_gs_base = value;
+		break;
+	case GUEST_LDTR_BASE:
+		current_evmcs->guest_ldtr_base = value;
+		break;
+	case GUEST_TR_BASE:
+		current_evmcs->guest_tr_base = value;
+		break;
+	case GUEST_GDTR_BASE:
+		current_evmcs->guest_gdtr_base = value;
+		break;
+	case GUEST_IDTR_BASE:
+		current_evmcs->guest_idtr_base = value;
+		break;
+	case TSC_OFFSET:
+		current_evmcs->tsc_offset = value;
+		break;
+	case VIRTUAL_APIC_PAGE_ADDR:
+		current_evmcs->virtual_apic_page_addr = value;
+		break;
+	case VMCS_LINK_POINTER:
+		current_evmcs->vmcs_link_pointer = value;
+		break;
+	case GUEST_IA32_DEBUGCTL:
+		current_evmcs->guest_ia32_debugctl = value;
+		break;
+	case GUEST_IA32_PAT:
+		current_evmcs->guest_ia32_pat = value;
+		break;
+	case GUEST_IA32_EFER:
+		current_evmcs->guest_ia32_efer = value;
+		break;
+	case GUEST_PDPTR0:
+		current_evmcs->guest_pdptr0 = value;
+		break;
+	case GUEST_PDPTR1:
+		current_evmcs->guest_pdptr1 = value;
+		break;
+	case GUEST_PDPTR2:
+		current_evmcs->guest_pdptr2 = value;
+		break;
+	case GUEST_PDPTR3:
+		current_evmcs->guest_pdptr3 = value;
+		break;
+	case GUEST_PENDING_DBG_EXCEPTIONS:
+		current_evmcs->guest_pending_dbg_exceptions = value;
+		break;
+	case GUEST_SYSENTER_ESP:
+		current_evmcs->guest_sysenter_esp = value;
+		break;
+	case GUEST_SYSENTER_EIP:
+		current_evmcs->guest_sysenter_eip = value;
+		break;
+	case CR0_GUEST_HOST_MASK:
+		current_evmcs->cr0_guest_host_mask = value;
+		break;
+	case CR4_GUEST_HOST_MASK:
+		current_evmcs->cr4_guest_host_mask = value;
+		break;
+	case CR0_READ_SHADOW:
+		current_evmcs->cr0_read_shadow = value;
+		break;
+	case CR4_READ_SHADOW:
+		current_evmcs->cr4_read_shadow = value;
+		break;
+	case GUEST_CR0:
+		current_evmcs->guest_cr0 = value;
+		break;
+	case GUEST_CR3:
+		current_evmcs->guest_cr3 = value;
+		break;
+	case GUEST_CR4:
+		current_evmcs->guest_cr4 = value;
+		break;
+	case GUEST_DR7:
+		current_evmcs->guest_dr7 = value;
+		break;
+	case HOST_FS_BASE:
+		current_evmcs->host_fs_base = value;
+		break;
+	case HOST_GS_BASE:
+		current_evmcs->host_gs_base = value;
+		break;
+	case HOST_TR_BASE:
+		current_evmcs->host_tr_base = value;
+		break;
+	case HOST_GDTR_BASE:
+		current_evmcs->host_gdtr_base = value;
+		break;
+	case HOST_IDTR_BASE:
+		current_evmcs->host_idtr_base = value;
+		break;
+	case HOST_RSP:
+		current_evmcs->host_rsp = value;
+		break;
+	case EPT_POINTER:
+		current_evmcs->ept_pointer = value;
+		break;
+	case GUEST_BNDCFGS:
+		current_evmcs->guest_bndcfgs = value;
+		break;
+	case XSS_EXIT_BITMAP:
+		current_evmcs->xss_exit_bitmap = value;
+		break;
+	case GUEST_PHYSICAL_ADDRESS:
+		current_evmcs->guest_physical_address = value;
+		break;
+	case EXIT_QUALIFICATION:
+		current_evmcs->exit_qualification = value;
+		break;
+	case GUEST_LINEAR_ADDRESS:
+		current_evmcs->guest_linear_address = value;
+		break;
+	case VM_EXIT_MSR_STORE_ADDR:
+		current_evmcs->vm_exit_msr_store_addr = value;
+		break;
+	case VM_EXIT_MSR_LOAD_ADDR:
+		current_evmcs->vm_exit_msr_load_addr = value;
+		break;
+	case VM_ENTRY_MSR_LOAD_ADDR:
+		current_evmcs->vm_entry_msr_load_addr = value;
+		break;
+	case CR3_TARGET_VALUE0:
+		current_evmcs->cr3_target_value0 = value;
+		break;
+	case CR3_TARGET_VALUE1:
+		current_evmcs->cr3_target_value1 = value;
+		break;
+	case CR3_TARGET_VALUE2:
+		current_evmcs->cr3_target_value2 = value;
+		break;
+	case CR3_TARGET_VALUE3:
+		current_evmcs->cr3_target_value3 = value;
+		break;
+	case TPR_THRESHOLD:
+		current_evmcs->tpr_threshold = value;
+		break;
+	case GUEST_INTERRUPTIBILITY_INFO:
+		current_evmcs->guest_interruptibility_info = value;
+		break;
+	case CPU_BASED_VM_EXEC_CONTROL:
+		current_evmcs->cpu_based_vm_exec_control = value;
+		break;
+	case EXCEPTION_BITMAP:
+		current_evmcs->exception_bitmap = value;
+		break;
+	case VM_ENTRY_CONTROLS:
+		current_evmcs->vm_entry_controls = value;
+		break;
+	case VM_ENTRY_INTR_INFO_FIELD:
+		current_evmcs->vm_entry_intr_info_field = value;
+		break;
+	case VM_ENTRY_EXCEPTION_ERROR_CODE:
+		current_evmcs->vm_entry_exception_error_code = value;
+		break;
+	case VM_ENTRY_INSTRUCTION_LEN:
+		current_evmcs->vm_entry_instruction_len = value;
+		break;
+	case HOST_IA32_SYSENTER_CS:
+		current_evmcs->host_ia32_sysenter_cs = value;
+		break;
+	case PIN_BASED_VM_EXEC_CONTROL:
+		current_evmcs->pin_based_vm_exec_control = value;
+		break;
+	case VM_EXIT_CONTROLS:
+		current_evmcs->vm_exit_controls = value;
+		break;
+	case SECONDARY_VM_EXEC_CONTROL:
+		current_evmcs->secondary_vm_exec_control = value;
+		break;
+	case GUEST_ES_LIMIT:
+		current_evmcs->guest_es_limit = value;
+		break;
+	case GUEST_CS_LIMIT:
+		current_evmcs->guest_cs_limit = value;
+		break;
+	case GUEST_SS_LIMIT:
+		current_evmcs->guest_ss_limit = value;
+		break;
+	case GUEST_DS_LIMIT:
+		current_evmcs->guest_ds_limit = value;
+		break;
+	case GUEST_FS_LIMIT:
+		current_evmcs->guest_fs_limit = value;
+		break;
+	case GUEST_GS_LIMIT:
+		current_evmcs->guest_gs_limit = value;
+		break;
+	case GUEST_LDTR_LIMIT:
+		current_evmcs->guest_ldtr_limit = value;
+		break;
+	case GUEST_TR_LIMIT:
+		current_evmcs->guest_tr_limit = value;
+		break;
+	case GUEST_GDTR_LIMIT:
+		current_evmcs->guest_gdtr_limit = value;
+		break;
+	case GUEST_IDTR_LIMIT:
+		current_evmcs->guest_idtr_limit = value;
+		break;
+	case GUEST_ES_AR_BYTES:
+		current_evmcs->guest_es_ar_bytes = value;
+		break;
+	case GUEST_CS_AR_BYTES:
+		current_evmcs->guest_cs_ar_bytes = value;
+		break;
+	case GUEST_SS_AR_BYTES:
+		current_evmcs->guest_ss_ar_bytes = value;
+		break;
+	case GUEST_DS_AR_BYTES:
+		current_evmcs->guest_ds_ar_bytes = value;
+		break;
+	case GUEST_FS_AR_BYTES:
+		current_evmcs->guest_fs_ar_bytes = value;
+		break;
+	case GUEST_GS_AR_BYTES:
+		current_evmcs->guest_gs_ar_bytes = value;
+		break;
+	case GUEST_LDTR_AR_BYTES:
+		current_evmcs->guest_ldtr_ar_bytes = value;
+		break;
+	case GUEST_TR_AR_BYTES:
+		current_evmcs->guest_tr_ar_bytes = value;
+		break;
+	case GUEST_ACTIVITY_STATE:
+		current_evmcs->guest_activity_state = value;
+		break;
+	case GUEST_SYSENTER_CS:
+		current_evmcs->guest_sysenter_cs = value;
+		break;
+	case VM_INSTRUCTION_ERROR:
+		current_evmcs->vm_instruction_error = value;
+		break;
+	case VM_EXIT_REASON:
+		current_evmcs->vm_exit_reason = value;
+		break;
+	case VM_EXIT_INTR_INFO:
+		current_evmcs->vm_exit_intr_info = value;
+		break;
+	case VM_EXIT_INTR_ERROR_CODE:
+		current_evmcs->vm_exit_intr_error_code = value;
+		break;
+	case IDT_VECTORING_INFO_FIELD:
+		current_evmcs->idt_vectoring_info_field = value;
+		break;
+	case IDT_VECTORING_ERROR_CODE:
+		current_evmcs->idt_vectoring_error_code = value;
+		break;
+	case VM_EXIT_INSTRUCTION_LEN:
+		current_evmcs->vm_exit_instruction_len = value;
+		break;
+	case VMX_INSTRUCTION_INFO:
+		current_evmcs->vmx_instruction_info = value;
+		break;
+	case PAGE_FAULT_ERROR_CODE_MASK:
+		current_evmcs->page_fault_error_code_mask = value;
+		break;
+	case PAGE_FAULT_ERROR_CODE_MATCH:
+		current_evmcs->page_fault_error_code_match = value;
+		break;
+	case CR3_TARGET_COUNT:
+		current_evmcs->cr3_target_count = value;
+		break;
+	case VM_EXIT_MSR_STORE_COUNT:
+		current_evmcs->vm_exit_msr_store_count = value;
+		break;
+	case VM_EXIT_MSR_LOAD_COUNT:
+		current_evmcs->vm_exit_msr_load_count = value;
+		break;
+	case VM_ENTRY_MSR_LOAD_COUNT:
+		current_evmcs->vm_entry_msr_load_count = value;
+		break;
+	case HOST_ES_SELECTOR:
+		current_evmcs->host_es_selector = value;
+		break;
+	case HOST_CS_SELECTOR:
+		current_evmcs->host_cs_selector = value;
+		break;
+	case HOST_SS_SELECTOR:
+		current_evmcs->host_ss_selector = value;
+		break;
+	case HOST_DS_SELECTOR:
+		current_evmcs->host_ds_selector = value;
+		break;
+	case HOST_FS_SELECTOR:
+		current_evmcs->host_fs_selector = value;
+		break;
+	case HOST_GS_SELECTOR:
+		current_evmcs->host_gs_selector = value;
+		break;
+	case HOST_TR_SELECTOR:
+		current_evmcs->host_tr_selector = value;
+		break;
+	case GUEST_ES_SELECTOR:
+		current_evmcs->guest_es_selector = value;
+		break;
+	case GUEST_CS_SELECTOR:
+		current_evmcs->guest_cs_selector = value;
+		break;
+	case GUEST_SS_SELECTOR:
+		current_evmcs->guest_ss_selector = value;
+		break;
+	case GUEST_DS_SELECTOR:
+		current_evmcs->guest_ds_selector = value;
+		break;
+	case GUEST_FS_SELECTOR:
+		current_evmcs->guest_fs_selector = value;
+		break;
+	case GUEST_GS_SELECTOR:
+		current_evmcs->guest_gs_selector = value;
+		break;
+	case GUEST_LDTR_SELECTOR:
+		current_evmcs->guest_ldtr_selector = value;
+		break;
+	case GUEST_TR_SELECTOR:
+		current_evmcs->guest_tr_selector = value;
+		break;
+	case VIRTUAL_PROCESSOR_ID:
+		current_evmcs->virtual_processor_id = value;
+		break;
+	default: return 1;
+	}
+
+	return 0;
+}
+
+static inline int evmcs_vmlaunch(void)
+{
+	int ret;
+
+	current_evmcs->hv_clean_fields = 0;
+
+	__asm__ __volatile__("push %%rbp;"
+			     "push %%rcx;"
+			     "push %%rdx;"
+			     "push %%rsi;"
+			     "push %%rdi;"
+			     "push $0;"
+			     "mov %%rsp, (%[host_rsp]);"
+			     "lea 1f(%%rip), %%rax;"
+			     "mov %%rax, (%[host_rip]);"
+			     "vmlaunch;"
+			     "incq (%%rsp);"
+			     "1: pop %%rax;"
+			     "pop %%rdi;"
+			     "pop %%rsi;"
+			     "pop %%rdx;"
+			     "pop %%rcx;"
+			     "pop %%rbp;"
+			     : [ret]"=&a"(ret)
+			     : [host_rsp]"r"
+			       ((uint64_t)&current_evmcs->host_rsp),
+			       [host_rip]"r"
+			       ((uint64_t)&current_evmcs->host_rip)
+			     : "memory", "cc", "rbx", "r8", "r9", "r10",
+			       "r11", "r12", "r13", "r14", "r15");
+	return ret;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmresume.
+ */
+static inline int evmcs_vmresume(void)
+{
+	int ret;
+
+	current_evmcs->hv_clean_fields = 0;
+
+	__asm__ __volatile__("push %%rbp;"
+			     "push %%rcx;"
+			     "push %%rdx;"
+			     "push %%rsi;"
+			     "push %%rdi;"
+			     "push $0;"
+			     "mov %%rsp, (%[host_rsp]);"
+			     "lea 1f(%%rip), %%rax;"
+			     "mov %%rax, (%[host_rip]);"
+			     "vmresume;"
+			     "incq (%%rsp);"
+			     "1: pop %%rax;"
+			     "pop %%rdi;"
+			     "pop %%rsi;"
+			     "pop %%rdx;"
+			     "pop %%rcx;"
+			     "pop %%rbp;"
+			     : [ret]"=&a"(ret)
+			     : [host_rsp]"r"
+			       ((uint64_t)&current_evmcs->host_rsp),
+			       [host_rip]"r"
+			       ((uint64_t)&current_evmcs->host_rip)
+			     : "memory", "cc", "rbx", "r8", "r9", "r10",
+			       "r11", "r12", "r13", "r14", "r15");
+	return ret;
+}
+
+#endif /* !SELFTEST_KVM_EVMCS_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 4bbee8560292..c9bd935b939c 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -339,6 +339,8 @@ struct vmx_msr_entry {
 	uint64_t value;
 } __attribute__ ((aligned(16)));
 
+#include "evmcs.h"
+
 static inline int vmxon(uint64_t phys)
 {
 	uint8_t ret;
@@ -372,6 +374,9 @@ static inline int vmptrld(uint64_t vmcs_pa)
 {
 	uint8_t ret;
 
+	if (enable_evmcs)
+		return -1;
+
 	__asm__ __volatile__ ("vmptrld %[pa]; setna %[ret]"
 		: [ret]"=rm"(ret)
 		: [pa]"m"(vmcs_pa)
@@ -385,6 +390,9 @@ static inline int vmptrst(uint64_t *value)
 	uint64_t tmp;
 	uint8_t ret;
 
+	if (enable_evmcs)
+		return evmcs_vmptrst(value);
+
 	__asm__ __volatile__("vmptrst %[value]; setna %[ret]"
 		: [value]"=m"(tmp), [ret]"=rm"(ret)
 		: : "cc", "memory");
@@ -411,6 +419,9 @@ static inline int vmlaunch(void)
 {
 	int ret;
 
+	if (enable_evmcs)
+		return evmcs_vmlaunch();
+
 	__asm__ __volatile__("push %%rbp;"
 			     "push %%rcx;"
 			     "push %%rdx;"
@@ -443,6 +454,9 @@ static inline int vmresume(void)
 {
 	int ret;
 
+	if (enable_evmcs)
+		return evmcs_vmresume();
+
 	__asm__ __volatile__("push %%rbp;"
 			     "push %%rcx;"
 			     "push %%rdx;"
@@ -482,6 +496,9 @@ static inline int vmread(uint64_t encoding, uint64_t *value)
 	uint64_t tmp;
 	uint8_t ret;
 
+	if (enable_evmcs)
+		return evmcs_vmread(encoding, value);
+
 	__asm__ __volatile__("vmread %[encoding], %[value]; setna %[ret]"
 		: [value]"=rm"(tmp), [ret]"=rm"(ret)
 		: [encoding]"r"(encoding)
@@ -506,6 +523,9 @@ static inline int vmwrite(uint64_t encoding, uint64_t value)
 {
 	uint8_t ret;
 
+	if (enable_evmcs)
+		return evmcs_vmwrite(encoding, value);
+
 	__asm__ __volatile__ ("vmwrite %[value], %[encoding]; setna %[ret]"
 		: [ret]"=rm"(ret)
 		: [value]"rm"(value), [encoding]"r"(encoding)
@@ -543,6 +563,14 @@ struct vmx_pages {
 	void *vmwrite_hva;
 	uint64_t vmwrite_gpa;
 	void *vmwrite;
+
+	void *vp_assist_hva;
+	uint64_t vp_assist_gpa;
+	void *vp_assist;
+
+	void *enlightened_vmcs_hva;
+	uint64_t enlightened_vmcs_gpa;
+	void *enlightened_vmcs;
 };
 
 struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva);
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index cc356da9b3d8..771ba6bf751c 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -13,6 +13,8 @@
 #include "processor.h"
 #include "vmx.h"
 
+bool enable_evmcs;
+
 /* Allocate memory regions for nested VMX tests.
  *
  * Input Args:
@@ -62,6 +64,20 @@ vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva)
 	vmx->vmwrite_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmwrite);
 	memset(vmx->vmwrite_hva, 0, getpagesize());
 
+	/* Setup of a region of guest memory for the VP Assist page. */
+	vmx->vp_assist = (void *)vm_vaddr_alloc(vm, getpagesize(),
+						0x10000, 0, 0);
+	vmx->vp_assist_hva = addr_gva2hva(vm, (uintptr_t)vmx->vp_assist);
+	vmx->vp_assist_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vp_assist);
+
+	/* Setup of a region of guest memory for the enlightened VMCS. */
+	vmx->enlightened_vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(),
+						       0x10000, 0, 0);
+	vmx->enlightened_vmcs_hva =
+		addr_gva2hva(vm, (uintptr_t)vmx->enlightened_vmcs);
+	vmx->enlightened_vmcs_gpa =
+		addr_gva2gpa(vm, (uintptr_t)vmx->enlightened_vmcs);
+
 	*p_vmx_gva = vmx_gva;
 	return vmx;
 }
@@ -112,18 +128,26 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx)
 
 bool load_vmcs(struct vmx_pages *vmx)
 {
-	/* Load a VMCS. */
-	*(uint32_t *)(vmx->vmcs) = vmcs_revision();
-	if (vmclear(vmx->vmcs_gpa))
-		return false;
-
-	if (vmptrld(vmx->vmcs_gpa))
-		return false;
-
-	/* Setup shadow VMCS, do not load it yet. */
-	*(uint32_t *)(vmx->shadow_vmcs) = vmcs_revision() | 0x80000000ul;
-	if (vmclear(vmx->shadow_vmcs_gpa))
-		return false;
+	if (!enable_evmcs) {
+		/* Load a VMCS. */
+		*(uint32_t *)(vmx->vmcs) = vmcs_revision();
+		if (vmclear(vmx->vmcs_gpa))
+			return false;
+
+		if (vmptrld(vmx->vmcs_gpa))
+			return false;
+
+		/* Setup shadow VMCS, do not load it yet. */
+		*(uint32_t *)(vmx->shadow_vmcs) =
+			vmcs_revision() | 0x80000000ul;
+		if (vmclear(vmx->shadow_vmcs_gpa))
+			return false;
+	} else {
+		if (evmcs_vmptrld(vmx->enlightened_vmcs_gpa,
+				  vmx->enlightened_vmcs))
+			return false;
+		current_evmcs->revision_id = vmcs_revision();
+	}
 
 	return true;
 }
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
new file mode 100644
index 000000000000..92c2cfd1b182
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018, Red Hat, Inc.
+ *
+ * Tests for Enlightened VMCS, including nested guest state.
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+
+#include "vmx.h"
+
+#define VCPU_ID		5
+
+static bool have_nested_state;
+
+void l2_guest_code(void)
+{
+	GUEST_SYNC(6);
+
+	GUEST_SYNC(7);
+
+	/* Done, exit to L1 and never come back.  */
+	vmcall();
+}
+
+void l1_guest_code(struct vmx_pages *vmx_pages)
+{
+#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+	enable_vp_assist(vmx_pages->vp_assist_gpa, vmx_pages->vp_assist);
+
+	GUEST_ASSERT(vmx_pages->vmcs_gpa);
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+	GUEST_SYNC(3);
+	GUEST_ASSERT(load_vmcs(vmx_pages));
+	GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+
+	GUEST_SYNC(4);
+	GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+
+	prepare_vmcs(vmx_pages, l2_guest_code,
+		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	GUEST_SYNC(5);
+	GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+	GUEST_SYNC(8);
+	GUEST_ASSERT(!vmresume());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+	GUEST_SYNC(9);
+}
+
+void guest_code(struct vmx_pages *vmx_pages)
+{
+	GUEST_SYNC(1);
+	GUEST_SYNC(2);
+
+	if (vmx_pages)
+		l1_guest_code(vmx_pages);
+
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	struct vmx_pages *vmx_pages = NULL;
+	vm_vaddr_t vmx_pages_gva = 0;
+
+	struct kvm_regs regs1, regs2;
+	struct kvm_vm *vm;
+	struct kvm_run *run;
+	struct kvm_x86_state *state;
+	struct ucall uc;
+	int stage;
+	uint16_t evmcs_ver;
+	struct kvm_enable_cap enable_evmcs_cap = {
+		.cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS,
+		 .args[0] = (unsigned long)&evmcs_ver
+	};
+
+	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+	if (!kvm_check_cap(KVM_CAP_NESTED_STATE) ||
+	    !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
+		printf("capabilities not available, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+
+	vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
+
+	run = vcpu_state(vm, VCPU_ID);
+
+	vcpu_regs_get(vm, VCPU_ID, &regs1);
+
+	vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+	vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
+
+	for (stage = 1;; stage++) {
+		_vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Unexpected exit reason: %u (%s),\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		memset(&regs1, 0, sizeof(regs1));
+		vcpu_regs_get(vm, VCPU_ID, &regs1);
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
+				    __FILE__, uc.args[1]);
+			/* NOT REACHED */
+		case UCALL_SYNC:
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+		}
+
+		/* UCALL_SYNC is handled here.  */
+		TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+			    uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
+			    stage, (ulong)uc.args[1]);
+
+		state = vcpu_save_state(vm, VCPU_ID);
+		kvm_vm_release(vm);
+
+		/* Restore state in a new VM.  */
+		kvm_vm_restart(vm, O_RDWR);
+		vm_vcpu_add(vm, VCPU_ID, 0, 0);
+		vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+		vcpu_load_state(vm, VCPU_ID, state);
+		run = vcpu_state(vm, VCPU_ID);
+		free(state);
+
+		memset(&regs2, 0, sizeof(regs2));
+		vcpu_regs_get(vm, VCPU_ID, &regs2);
+		TEST_ASSERT(!memcmp(&regs1, &regs2, sizeof(regs2)),
+			    "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx",
+			    (ulong) regs2.rdi, (ulong) regs2.rsi);
+	}
+
+done:
+	kvm_vm_free(vm);
+}
-- 
cgit v1.2.3


From 753fb2ee09345e0730e610b2ee3a01964fe22a63 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Tue, 16 Oct 2018 11:08:09 -0700
Subject: bpf: sockmap, add msg_peek tests to test_sockmap

Add tests that do a MSG_PEEK recv followed by a regular receive to
test flag support.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_sockmap.c | 167 ++++++++++++++++++++---------
 1 file changed, 115 insertions(+), 52 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 7cb69ce6dfa2..cbd1c0be8680 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -80,6 +80,7 @@ int txmsg_end;
 int txmsg_ingress;
 int txmsg_skb;
 int ktls;
+int peek_flag;
 
 static const struct option long_options[] = {
 	{"help",	no_argument,		NULL, 'h' },
@@ -102,6 +103,7 @@ static const struct option long_options[] = {
 	{"txmsg_ingress", no_argument,		&txmsg_ingress, 1 },
 	{"txmsg_skb", no_argument,		&txmsg_skb, 1 },
 	{"ktls", no_argument,			&ktls, 1 },
+	{"peek", no_argument,			&peek_flag, 1 },
 	{0, 0, NULL, 0 }
 };
 
@@ -352,33 +354,40 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 	return 0;
 }
 
-static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
-		    struct msg_stats *s, bool tx,
-		    struct sockmap_options *opt)
+static void msg_free_iov(struct msghdr *msg)
 {
-	struct msghdr msg = {0};
-	int err, i, flags = MSG_NOSIGNAL;
+	int i;
+
+	for (i = 0; i < msg->msg_iovlen; i++)
+		free(msg->msg_iov[i].iov_base);
+	free(msg->msg_iov);
+	msg->msg_iov = NULL;
+	msg->msg_iovlen = 0;
+}
+
+static int msg_alloc_iov(struct msghdr *msg,
+			 int iov_count, int iov_length,
+			 bool data, bool xmit)
+{
+	unsigned char k = 0;
 	struct iovec *iov;
-	unsigned char k;
-	bool data_test = opt->data_test;
-	bool drop = opt->drop_expected;
+	int i;
 
 	iov = calloc(iov_count, sizeof(struct iovec));
 	if (!iov)
 		return errno;
 
-	k = 0;
 	for (i = 0; i < iov_count; i++) {
 		unsigned char *d = calloc(iov_length, sizeof(char));
 
 		if (!d) {
 			fprintf(stderr, "iov_count %i/%i OOM\n", i, iov_count);
-			goto out_errno;
+			goto unwind_iov;
 		}
 		iov[i].iov_base = d;
 		iov[i].iov_len = iov_length;
 
-		if (data_test && tx) {
+		if (data && xmit) {
 			int j;
 
 			for (j = 0; j < iov_length; j++)
@@ -386,9 +395,60 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		}
 	}
 
-	msg.msg_iov = iov;
-	msg.msg_iovlen = iov_count;
-	k = 0;
+	msg->msg_iov = iov;
+	msg->msg_iovlen = iov_count;
+
+	return 0;
+unwind_iov:
+	for (i--; i >= 0 ; i--)
+		free(msg->msg_iov[i].iov_base);
+	return -ENOMEM;
+}
+
+static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz)
+{
+	int i, j, bytes_cnt = 0;
+	unsigned char k = 0;
+
+	for (i = 0; i < msg->msg_iovlen; i++) {
+		unsigned char *d = msg->msg_iov[i].iov_base;
+
+		for (j = 0;
+		     j < msg->msg_iov[i].iov_len && size; j++) {
+			if (d[j] != k++) {
+				fprintf(stderr,
+					"detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n",
+					i, j, d[j], k - 1, d[j+1], k);
+				return -EIO;
+			}
+			bytes_cnt++;
+			if (bytes_cnt == chunk_sz) {
+				k = 0;
+				bytes_cnt = 0;
+			}
+			size--;
+		}
+	}
+	return 0;
+}
+
+static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
+		    struct msg_stats *s, bool tx,
+		    struct sockmap_options *opt)
+{
+	struct msghdr msg = {0}, msg_peek = {0};
+	int err, i, flags = MSG_NOSIGNAL;
+	bool drop = opt->drop_expected;
+	bool data = opt->data_test;
+
+	err = msg_alloc_iov(&msg, iov_count, iov_length, data, tx);
+	if (err)
+		goto out_errno;
+	if (peek_flag) {
+		err = msg_alloc_iov(&msg_peek, iov_count, iov_length, data, tx);
+		if (err)
+			goto out_errno;
+	}
 
 	if (tx) {
 		clock_gettime(CLOCK_MONOTONIC, &s->start);
@@ -408,19 +468,12 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		}
 		clock_gettime(CLOCK_MONOTONIC, &s->end);
 	} else {
-		int slct, recv, max_fd = fd;
+		int slct, recvp = 0, recv, max_fd = fd;
 		int fd_flags = O_NONBLOCK;
 		struct timeval timeout;
 		float total_bytes;
-		int bytes_cnt = 0;
-		int chunk_sz;
 		fd_set w;
 
-		if (opt->sendpage)
-			chunk_sz = iov_length * cnt;
-		else
-			chunk_sz = iov_length * iov_count;
-
 		fcntl(fd, fd_flags);
 		total_bytes = (float)iov_count * (float)iov_length * (float)cnt;
 		err = clock_gettime(CLOCK_MONOTONIC, &s->start);
@@ -452,6 +505,19 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 				goto out_errno;
 			}
 
+			errno = 0;
+			if (peek_flag) {
+				flags |= MSG_PEEK;
+				recvp = recvmsg(fd, &msg_peek, flags);
+				if (recvp < 0) {
+					if (errno != EWOULDBLOCK) {
+						clock_gettime(CLOCK_MONOTONIC, &s->end);
+						goto out_errno;
+					}
+				}
+				flags = 0;
+			}
+
 			recv = recvmsg(fd, &msg, flags);
 			if (recv < 0) {
 				if (errno != EWOULDBLOCK) {
@@ -463,27 +529,23 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 
 			s->bytes_recvd += recv;
 
-			if (data_test) {
-				int j;
-
-				for (i = 0; i < msg.msg_iovlen; i++) {
-					unsigned char *d = iov[i].iov_base;
-
-					for (j = 0;
-					     j < iov[i].iov_len && recv; j++) {
-						if (d[j] != k++) {
-							errno = -EIO;
-							fprintf(stderr,
-								"detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n",
-								i, j, d[j], k - 1, d[j+1], k);
-							goto out_errno;
-						}
-						bytes_cnt++;
-						if (bytes_cnt == chunk_sz) {
-							k = 0;
-							bytes_cnt = 0;
-						}
-						recv--;
+			if (data) {
+				int chunk_sz = opt->sendpage ?
+						iov_length * cnt :
+						iov_length * iov_count;
+
+				errno = msg_verify_data(&msg, recv, chunk_sz);
+				if (errno) {
+					perror("data verify msg failed\n");
+					goto out_errno;
+				}
+				if (recvp) {
+					errno = msg_verify_data(&msg_peek,
+								recvp,
+								chunk_sz);
+					if (errno) {
+						perror("data verify msg_peek failed\n");
+						goto out_errno;
 					}
 				}
 			}
@@ -491,14 +553,12 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		clock_gettime(CLOCK_MONOTONIC, &s->end);
 	}
 
-	for (i = 0; i < iov_count; i++)
-		free(iov[i].iov_base);
-	free(iov);
-	return 0;
+	msg_free_iov(&msg);
+	msg_free_iov(&msg_peek);
+	return err;
 out_errno:
-	for (i = 0; i < iov_count; i++)
-		free(iov[i].iov_base);
-	free(iov);
+	msg_free_iov(&msg);
+	msg_free_iov(&msg_peek);
 	return errno;
 }
 
@@ -565,9 +625,10 @@ static int sendmsg_test(struct sockmap_options *opt)
 		}
 		if (opt->verbose)
 			fprintf(stdout,
-				"rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s\n",
+				"rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s %s\n",
 				s.bytes_sent, sent_Bps, sent_Bps/giga,
-				s.bytes_recvd, recvd_Bps, recvd_Bps/giga);
+				s.bytes_recvd, recvd_Bps, recvd_Bps/giga,
+				peek_flag ? "(peek_msg)" : "");
 		if (err && txmsg_cork)
 			err = 0;
 		exit(err ? 1 : 0);
@@ -999,6 +1060,8 @@ static void test_options(char *options)
 		strncat(options, "skb,", OPTSTRING);
 	if (ktls)
 		strncat(options, "ktls,", OPTSTRING);
+	if (peek_flag)
+		strncat(options, "peek,", OPTSTRING);
 }
 
 static int __test_exec(int cgrp, int test, struct sockmap_options *opt)
-- 
cgit v1.2.3


From 59073aaf6de0d2dacc2603cee6d1d6cd5592ac08 Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Tue, 16 Oct 2018 14:29:20 -0700
Subject: kvm: x86: Add exception payload fields to kvm_vcpu_events

The per-VM capability KVM_CAP_EXCEPTION_PAYLOAD (to be introduced in a
later commit) adds the following fields to struct kvm_vcpu_events:
exception_has_payload, exception_payload, and exception.pending.

With this capability set, all of the details of vcpu->arch.exception,
including the payload for a pending exception, are reported to
userspace in response to KVM_GET_VCPU_EVENTS.

With this capability clear, the original ABI is preserved, and the
exception.injected field is set for either pending or injected
exceptions.

When userspace calls KVM_SET_VCPU_EVENTS with
KVM_CAP_EXCEPTION_PAYLOAD clear, exception.injected is no longer
translated to exception.pending. KVM_SET_VCPU_EVENTS can now only
establish a pending exception when KVM_CAP_EXCEPTION_PAYLOAD is set.

Reported-by: Jim Mattson <jmattson@google.com>
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/api.txt     | 24 ++++++++++----
 arch/x86/include/asm/kvm_host.h       |  1 +
 arch/x86/include/uapi/asm/kvm.h       |  7 ++--
 arch/x86/kvm/x86.c                    | 61 ++++++++++++++++++++++++++---------
 tools/arch/x86/include/uapi/asm/kvm.h | 10 ++++--
 5 files changed, 77 insertions(+), 26 deletions(-)

(limited to 'tools')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index cf9422f4f101..e900ac31501c 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -850,7 +850,7 @@ struct kvm_vcpu_events {
 		__u8 injected;
 		__u8 nr;
 		__u8 has_error_code;
-		__u8 pad;
+		__u8 pending;
 		__u32 error_code;
 	} exception;
 	struct {
@@ -873,16 +873,23 @@ struct kvm_vcpu_events {
 		__u8 smm_inside_nmi;
 		__u8 latched_init;
 	} smi;
-	__u32 reserved[9];
+	__u8 reserved[27];
+	__u8 exception_has_payload;
+	__u64 exception_payload;
 };
 
-Only two fields are defined in the flags field:
+The following bits are defined in the flags field:
 
-- KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that
+- KVM_VCPUEVENT_VALID_SHADOW may be set to signal that
   interrupt.shadow contains a valid state.
 
-- KVM_VCPUEVENT_VALID_SMM may be set in the flags field to signal that
-  smi contains a valid state.
+- KVM_VCPUEVENT_VALID_SMM may be set to signal that smi contains a
+  valid state.
+
+- KVM_VCPUEVENT_VALID_PAYLOAD may be set to signal that the
+  exception_has_payload, exception_payload, and exception.pending
+  fields contain a valid state. This bit will be set whenever
+  KVM_CAP_EXCEPTION_PAYLOAD is enabled.
 
 ARM/ARM64:
 
@@ -962,6 +969,11 @@ shall be written into the VCPU.
 
 KVM_VCPUEVENT_VALID_SMM can only be set if KVM_CAP_X86_SMM is available.
 
+If KVM_CAP_EXCEPTION_PAYLOAD is enabled, KVM_VCPUEVENT_VALID_PAYLOAD
+can be set in the flags field to signal that the
+exception_has_payload, exception_payload, and exception.pending fields
+contain a valid state and shall be written into the VCPU.
+
 ARM/ARM64:
 
 Set the pending SError exception state for this VCPU. It is not possible to
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 20f7c994afeb..55e51ff7e421 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -919,6 +919,7 @@ struct kvm_arch {
 	bool x2apic_broadcast_quirk_disabled;
 
 	bool guest_can_read_msr_platform_info;
+	bool exception_payload_enabled;
 };
 
 struct kvm_vm_stat {
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index ab76aa1d3a4d..dabfcf7c3941 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -288,6 +288,7 @@ struct kvm_reinject_control {
 #define KVM_VCPUEVENT_VALID_SIPI_VECTOR	0x00000002
 #define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
 #define KVM_VCPUEVENT_VALID_SMM		0x00000008
+#define KVM_VCPUEVENT_VALID_PAYLOAD	0x00000010
 
 /* Interrupt shadow states */
 #define KVM_X86_SHADOW_INT_MOV_SS	0x01
@@ -299,7 +300,7 @@ struct kvm_vcpu_events {
 		__u8 injected;
 		__u8 nr;
 		__u8 has_error_code;
-		__u8 pad;
+		__u8 pending;
 		__u32 error_code;
 	} exception;
 	struct {
@@ -322,7 +323,9 @@ struct kvm_vcpu_events {
 		__u8 smm_inside_nmi;
 		__u8 latched_init;
 	} smi;
-	__u32 reserved[9];
+	__u8 reserved[27];
+	__u8 exception_has_payload;
+	__u64 exception_payload;
 };
 
 /* for KVM_GET/SET_DEBUGREGS */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 532b660fe497..2ef706574589 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3373,19 +3373,33 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 					       struct kvm_vcpu_events *events)
 {
 	process_nmi(vcpu);
+
 	/*
-	 * FIXME: pass injected and pending separately.  This is only
-	 * needed for nested virtualization, whose state cannot be
-	 * migrated yet.  For now we can combine them.
+	 * The API doesn't provide the instruction length for software
+	 * exceptions, so don't report them. As long as the guest RIP
+	 * isn't advanced, we should expect to encounter the exception
+	 * again.
 	 */
-	events->exception.injected =
-		(vcpu->arch.exception.pending ||
-		 vcpu->arch.exception.injected) &&
-		!kvm_exception_is_soft(vcpu->arch.exception.nr);
+	if (kvm_exception_is_soft(vcpu->arch.exception.nr)) {
+		events->exception.injected = 0;
+		events->exception.pending = 0;
+	} else {
+		events->exception.injected = vcpu->arch.exception.injected;
+		events->exception.pending = vcpu->arch.exception.pending;
+		/*
+		 * For ABI compatibility, deliberately conflate
+		 * pending and injected exceptions when
+		 * KVM_CAP_EXCEPTION_PAYLOAD isn't enabled.
+		 */
+		if (!vcpu->kvm->arch.exception_payload_enabled)
+			events->exception.injected |=
+				vcpu->arch.exception.pending;
+	}
 	events->exception.nr = vcpu->arch.exception.nr;
 	events->exception.has_error_code = vcpu->arch.exception.has_error_code;
-	events->exception.pad = 0;
 	events->exception.error_code = vcpu->arch.exception.error_code;
+	events->exception_has_payload = vcpu->arch.exception.has_payload;
+	events->exception_payload = vcpu->arch.exception.payload;
 
 	events->interrupt.injected =
 		vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft;
@@ -3409,6 +3423,9 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 	events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
 			 | KVM_VCPUEVENT_VALID_SHADOW
 			 | KVM_VCPUEVENT_VALID_SMM);
+	if (vcpu->kvm->arch.exception_payload_enabled)
+		events->flags |= KVM_VCPUEVENT_VALID_PAYLOAD;
+
 	memset(&events->reserved, 0, sizeof(events->reserved));
 }
 
@@ -3420,12 +3437,24 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 	if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
 			      | KVM_VCPUEVENT_VALID_SIPI_VECTOR
 			      | KVM_VCPUEVENT_VALID_SHADOW
-			      | KVM_VCPUEVENT_VALID_SMM))
+			      | KVM_VCPUEVENT_VALID_SMM
+			      | KVM_VCPUEVENT_VALID_PAYLOAD))
 		return -EINVAL;
 
-	if (events->exception.injected &&
-	    (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR ||
-	     is_guest_mode(vcpu)))
+	if (events->flags & KVM_VCPUEVENT_VALID_PAYLOAD) {
+		if (!vcpu->kvm->arch.exception_payload_enabled)
+			return -EINVAL;
+		if (events->exception.pending)
+			events->exception.injected = 0;
+		else
+			events->exception_has_payload = 0;
+	} else {
+		events->exception.pending = 0;
+		events->exception_has_payload = 0;
+	}
+
+	if ((events->exception.injected || events->exception.pending) &&
+	    (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
 		return -EINVAL;
 
 	/* INITs are latched while in SMM */
@@ -3435,13 +3464,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 	process_nmi(vcpu);
-	vcpu->arch.exception.injected = false;
-	vcpu->arch.exception.pending = events->exception.injected;
+	vcpu->arch.exception.injected = events->exception.injected;
+	vcpu->arch.exception.pending = events->exception.pending;
 	vcpu->arch.exception.nr = events->exception.nr;
 	vcpu->arch.exception.has_error_code = events->exception.has_error_code;
 	vcpu->arch.exception.error_code = events->exception.error_code;
-	vcpu->arch.exception.has_payload = false;
-	vcpu->arch.exception.payload = 0;
+	vcpu->arch.exception.has_payload = events->exception_has_payload;
+	vcpu->arch.exception.payload = events->exception_payload;
 
 	vcpu->arch.interrupt.injected = events->interrupt.injected;
 	vcpu->arch.interrupt.nr = events->interrupt.nr;
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 86299efa804a..b09875f580d5 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -288,6 +288,7 @@ struct kvm_reinject_control {
 #define KVM_VCPUEVENT_VALID_SIPI_VECTOR	0x00000002
 #define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
 #define KVM_VCPUEVENT_VALID_SMM		0x00000008
+#define KVM_VCPUEVENT_VALID_PAYLOAD	0x00000010
 
 /* Interrupt shadow states */
 #define KVM_X86_SHADOW_INT_MOV_SS	0x01
@@ -299,7 +300,10 @@ struct kvm_vcpu_events {
 		__u8 injected;
 		__u8 nr;
 		__u8 has_error_code;
-		__u8 pad;
+		union {
+			__u8 pad;
+			__u8 pending;
+		};
 		__u32 error_code;
 	} exception;
 	struct {
@@ -322,7 +326,9 @@ struct kvm_vcpu_events {
 		__u8 smm_inside_nmi;
 		__u8 latched_init;
 	} smi;
-	__u32 reserved[9];
+	__u8 reserved[27];
+	__u8 exception_has_payload;
+	__u64 exception_payload;
 };
 
 /* for KVM_GET/SET_DEBUGREGS */
-- 
cgit v1.2.3


From 0ead11181fe0c9538b185e46a494df21dc7de23a Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Wed, 26 Sep 2018 10:47:15 -0700
Subject: acpi, nfit: Collect shutdown status

Some NVDIMMs, in addition to providing an indication of whether the
previous shutdown was clean, also provide a running count of lifetime
dirty-shutdown events for the device. In anticipation of this
functionality appearing on more devices arrange for the nfit driver to
retrieve / cache this data at DIMM discovery time, and export it via
sysfs.

Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/nfit/core.c              | 77 ++++++++++++++++++++++++++++++++++-
 drivers/acpi/nfit/intel.h             | 38 +++++++++++++++++
 drivers/acpi/nfit/nfit.h              |  3 ++
 tools/testing/nvdimm/test/nfit.c      |  1 +
 tools/testing/nvdimm/test/nfit_test.h | 24 -----------
 5 files changed, 118 insertions(+), 25 deletions(-)
 create mode 100644 drivers/acpi/nfit/intel.h

(limited to 'tools')

diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 308a77b6c837..bf7021bb276c 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -25,6 +25,7 @@
 #include <asm/cacheflush.h>
 #include <acpi/nfit.h>
 #include "nfit.h"
+#include "intel.h"
 
 /*
  * For readq() and writeq() on 32-bit builds, the hi-lo, lo-hi order is
@@ -1551,7 +1552,12 @@ static DEVICE_ATTR_RO(dsm_mask);
 static ssize_t flags_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	u16 flags = to_nfit_memdev(dev)->flags;
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+	u16 flags = __to_nfit_memdev(nfit_mem)->flags;
+
+	if (test_bit(NFIT_MEM_DIRTY, &nfit_mem->flags))
+		flags |= ACPI_NFIT_MEM_FLUSH_FAILED;
 
 	return sprintf(buf, "%s%s%s%s%s%s%s\n",
 		flags & ACPI_NFIT_MEM_SAVE_FAILED ? "save_fail " : "",
@@ -1582,6 +1588,16 @@ static ssize_t id_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(id);
 
+static ssize_t dirty_shutdown_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+
+	return sprintf(buf, "%d\n", nfit_mem->dirty_shutdown);
+}
+static DEVICE_ATTR_RO(dirty_shutdown);
+
 static struct attribute *acpi_nfit_dimm_attributes[] = {
 	&dev_attr_handle.attr,
 	&dev_attr_phys_id.attr,
@@ -1599,6 +1615,7 @@ static struct attribute *acpi_nfit_dimm_attributes[] = {
 	&dev_attr_id.attr,
 	&dev_attr_family.attr,
 	&dev_attr_dsm_mask.attr,
+	&dev_attr_dirty_shutdown.attr,
 	NULL,
 };
 
@@ -1607,6 +1624,7 @@ static umode_t acpi_nfit_dimm_attr_visible(struct kobject *kobj,
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
 	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
 
 	if (!to_nfit_dcr(dev)) {
 		/* Without a dcr only the memdev attributes can be surfaced */
@@ -1620,6 +1638,11 @@ static umode_t acpi_nfit_dimm_attr_visible(struct kobject *kobj,
 
 	if (a == &dev_attr_format1.attr && num_nvdimm_formats(nvdimm) <= 1)
 		return 0;
+
+	if (!test_bit(NFIT_MEM_DIRTY_COUNT, &nfit_mem->flags)
+			&& a == &dev_attr_dirty_shutdown.attr)
+		return 0;
+
 	return a->mode;
 }
 
@@ -1698,6 +1721,56 @@ static bool acpi_nvdimm_has_method(struct acpi_device *adev, char *method)
 	return false;
 }
 
+static void nfit_intel_shutdown_status(struct nfit_mem *nfit_mem)
+{
+	struct nd_intel_smart smart = { 0 };
+	union acpi_object in_buf = {
+		.type = ACPI_TYPE_BUFFER,
+		.buffer.pointer = (char *) &smart,
+		.buffer.length = sizeof(smart),
+	};
+	union acpi_object in_obj = {
+		.type = ACPI_TYPE_PACKAGE,
+		.package.count = 1,
+		.package.elements = &in_buf,
+	};
+	const u8 func = ND_INTEL_SMART;
+	const guid_t *guid = to_nfit_uuid(nfit_mem->family);
+	u8 revid = nfit_dsm_revid(nfit_mem->family, func);
+	struct acpi_device *adev = nfit_mem->adev;
+	acpi_handle handle = adev->handle;
+	union acpi_object *out_obj;
+
+	if ((nfit_mem->dsm_mask & (1 << func)) == 0)
+		return;
+
+	out_obj = acpi_evaluate_dsm(handle, guid, revid, func, &in_obj);
+	if (!out_obj)
+		return;
+
+	if (smart.flags & ND_INTEL_SMART_SHUTDOWN_VALID) {
+		if (smart.shutdown_state)
+			set_bit(NFIT_MEM_DIRTY, &nfit_mem->flags);
+	}
+
+	if (smart.flags & ND_INTEL_SMART_SHUTDOWN_COUNT_VALID) {
+		set_bit(NFIT_MEM_DIRTY_COUNT, &nfit_mem->flags);
+		nfit_mem->dirty_shutdown = smart.shutdown_count;
+	}
+	ACPI_FREE(out_obj);
+}
+
+static void populate_shutdown_status(struct nfit_mem *nfit_mem)
+{
+	/*
+	 * For DIMMs that provide a dynamic facility to retrieve a
+	 * dirty-shutdown status and/or a dirty-shutdown count, cache
+	 * these values in nfit_mem.
+	 */
+	if (nfit_mem->family == NVDIMM_FAMILY_INTEL)
+		nfit_intel_shutdown_status(nfit_mem);
+}
+
 static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_mem *nfit_mem, u32 device_handle)
 {
@@ -1797,6 +1870,8 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 		set_bit(NFIT_MEM_LSW, &nfit_mem->flags);
 	}
 
+	populate_shutdown_status(nfit_mem);
+
 	return 0;
 }
 
diff --git a/drivers/acpi/nfit/intel.h b/drivers/acpi/nfit/intel.h
new file mode 100644
index 000000000000..86746312381f
--- /dev/null
+++ b/drivers/acpi/nfit/intel.h
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright(c) 2018 Intel Corporation. All rights reserved.
+ * Intel specific definitions for NVDIMM Firmware Interface Table - NFIT
+ */
+#ifndef _NFIT_INTEL_H_
+#define _NFIT_INTEL_H_
+
+#define ND_INTEL_SMART 1
+
+#define ND_INTEL_SMART_SHUTDOWN_COUNT_VALID     (1 << 5)
+#define ND_INTEL_SMART_SHUTDOWN_VALID           (1 << 10)
+
+struct nd_intel_smart {
+	u32 status;
+	union {
+		struct {
+			u32 flags;
+			u8 reserved0[4];
+			u8 health;
+			u8 spares;
+			u8 life_used;
+			u8 alarm_flags;
+			u16 media_temperature;
+			u16 ctrl_temperature;
+			u32 shutdown_count;
+			u8 ait_status;
+			u16 pmic_temperature;
+			u8 reserved1[8];
+			u8 shutdown_state;
+			u32 vendor_size;
+			u8 vendor_data[92];
+		} __packed;
+		u8 data[128];
+	};
+} __packed;
+
+#endif
diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
index 111c3c437c80..af73aec547f2 100644
--- a/drivers/acpi/nfit/nfit.h
+++ b/drivers/acpi/nfit/nfit.h
@@ -162,6 +162,8 @@ struct nfit_memdev {
 enum nfit_mem_flags {
 	NFIT_MEM_LSR,
 	NFIT_MEM_LSW,
+	NFIT_MEM_DIRTY,
+	NFIT_MEM_DIRTY_COUNT,
 };
 
 /* assembled tables for a given dimm/memory-device */
@@ -184,6 +186,7 @@ struct nfit_mem {
 	struct resource *flush_wpq;
 	unsigned long dsm_mask;
 	unsigned long flags;
+	u32 dirty_shutdown;
 	int family;
 };
 
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index cffc2c5a778d..f1a2a1a7bb1b 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -24,6 +24,7 @@
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <nd-core.h>
+#include <intel.h>
 #include <nfit.h>
 #include <nd.h>
 #include "nfit_test.h"
diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h
index 33752e06ff8d..ade14fe3837e 100644
--- a/tools/testing/nvdimm/test/nfit_test.h
+++ b/tools/testing/nvdimm/test/nfit_test.h
@@ -117,30 +117,6 @@ struct nd_cmd_ars_err_inj_stat {
 #define ND_INTEL_SMART_INJECT_FATAL		(1 << 2)
 #define ND_INTEL_SMART_INJECT_SHUTDOWN		(1 << 3)
 
-struct nd_intel_smart {
-	__u32 status;
-	union {
-		struct {
-			__u32 flags;
-			__u8 reserved0[4];
-			__u8 health;
-			__u8 spares;
-			__u8 life_used;
-			__u8 alarm_flags;
-			__u16 media_temperature;
-			__u16 ctrl_temperature;
-			__u32 shutdown_count;
-			__u8 ait_status;
-			__u16 pmic_temperature;
-			__u8 reserved1[8];
-			__u8 shutdown_state;
-			__u32 vendor_size;
-			__u8 vendor_data[92];
-		} __packed;
-		__u8 data[128];
-	};
-} __packed;
-
 struct nd_intel_smart_threshold {
 	__u32 status;
 	union {
-- 
cgit v1.2.3


From f110176633d74bbac1f80ab9b9c6b83ea3e1cc23 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Wed, 17 Oct 2018 10:47:19 -0700
Subject: tools/testing/nvdimm: Populate dirty shutdown data

Allow the unit tests to verify the retrieval of the dirty shutdown
count via smart commands, and allow the driver-load-time retrieval of
the smart health payload to be simulated by nfit_test.

Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/nfit/core.c              | 7 +++++--
 tools/testing/nvdimm/Kbuild           | 1 +
 tools/testing/nvdimm/acpi_nfit_test.c | 8 ++++++++
 tools/testing/nvdimm/test/nfit.c      | 3 ++-
 4 files changed, 16 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index bf7021bb276c..ec8fb578fa36 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -1721,7 +1721,7 @@ static bool acpi_nvdimm_has_method(struct acpi_device *adev, char *method)
 	return false;
 }
 
-static void nfit_intel_shutdown_status(struct nfit_mem *nfit_mem)
+__weak void nfit_intel_shutdown_status(struct nfit_mem *nfit_mem)
 {
 	struct nd_intel_smart smart = { 0 };
 	union acpi_object in_buf = {
@@ -1785,8 +1785,11 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 	nfit_mem->dsm_mask = acpi_desc->dimm_cmd_force_en;
 	nfit_mem->family = NVDIMM_FAMILY_INTEL;
 	adev = to_acpi_dev(acpi_desc);
-	if (!adev)
+	if (!adev) {
+		/* unit test case */
+		populate_shutdown_status(nfit_mem);
 		return 0;
+	}
 
 	adev_dimm = acpi_find_child_device(adev, device_handle, false);
 	nfit_mem->adev = adev_dimm;
diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild
index 0392153a0009..778ceb651000 100644
--- a/tools/testing/nvdimm/Kbuild
+++ b/tools/testing/nvdimm/Kbuild
@@ -22,6 +22,7 @@ NVDIMM_SRC := $(DRIVERS)/nvdimm
 ACPI_SRC := $(DRIVERS)/acpi/nfit
 DAX_SRC := $(DRIVERS)/dax
 ccflags-y := -I$(src)/$(NVDIMM_SRC)/
+ccflags-y += -I$(src)/$(ACPI_SRC)/
 
 obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o
 obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o
diff --git a/tools/testing/nvdimm/acpi_nfit_test.c b/tools/testing/nvdimm/acpi_nfit_test.c
index 43521512e577..fec8fb1b7715 100644
--- a/tools/testing/nvdimm/acpi_nfit_test.c
+++ b/tools/testing/nvdimm/acpi_nfit_test.c
@@ -4,5 +4,13 @@
 #include <linux/module.h>
 #include <linux/printk.h>
 #include "watermark.h"
+#include <nfit.h>
 
 nfit_test_watermark(acpi_nfit);
+
+/* strong / override definition of nfit_intel_shutdown_status */
+void nfit_intel_shutdown_status(struct nfit_mem *nfit_mem)
+{
+	set_bit(NFIT_MEM_DIRTY_COUNT, &nfit_mem->flags);
+	nfit_mem->dirty_shutdown = 42;
+}
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index f1a2a1a7bb1b..9527d47a1070 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -149,6 +149,7 @@ static const struct nd_intel_smart smart_def = {
 		| ND_INTEL_SMART_ALARM_VALID
 		| ND_INTEL_SMART_USED_VALID
 		| ND_INTEL_SMART_SHUTDOWN_VALID
+		| ND_INTEL_SMART_SHUTDOWN_COUNT_VALID
 		| ND_INTEL_SMART_MTEMP_VALID
 		| ND_INTEL_SMART_CTEMP_VALID,
 	.health = ND_INTEL_SMART_NON_CRITICAL_HEALTH,
@@ -161,8 +162,8 @@ static const struct nd_intel_smart smart_def = {
 	.ait_status = 1,
 	.life_used = 5,
 	.shutdown_state = 0,
+	.shutdown_count = 42,
 	.vendor_size = 0,
-	.shutdown_count = 100,
 };
 
 struct nfit_test_fw {
-- 
cgit v1.2.3


From edeb0c90df3581b821a764052d185df985f8b8dc Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 16 Oct 2018 17:08:29 -0300
Subject: perf tools: Stop fallbacking to kallsyms for vdso symbols lookup

David reports that:

<quote>
Perf has this hack where it uses the kernel symbol map as a backup when
a symbol can't be found in the user's symbol table(s).

This causes problems because the tests driving this code path use
machine__kernel_ip(), and that is completely meaningless on Sparc.  On
sparc64 the kernel and user live in physically separate virtual address
spaces, rather than a shared one.  And the kernel lives at a virtual
address that overlaps common userspace addresses.  So this test passes
almost all the time when a user symbol lookup fails.

The consequence of this is that, if the unfound user virtual address in
the sample doesn't match up to a kernel symbol either, we trigger things
like this code in builtin-top.c:

	if (al.sym == NULL && al.map != NULL) {
		const char *msg = "Kernel samples will not be resolved.\n";
		/*
		 * As we do lazy loading of symtabs we only will know if the
		 * specified vmlinux file is invalid when we actually have a
		 * hit in kernel space and then try to load it. So if we get
		 * here and there are _no_ symbols in the DSO backing the
		 * kernel map, bail out.
		 *
		 * We may never get here, for instance, if we use -K/
		 * --hide-kernel-symbols, even if the user specifies an
		 * invalid --vmlinux ;-)
		 */
		if (!machine->kptr_restrict_warned && !top->vmlinux_warned &&
		    __map__is_kernel(al.map) && map__has_symbols(al.map)) {
			if (symbol_conf.vmlinux_name) {
				char serr[256];
				dso__strerror_load(al.map->dso, serr, sizeof(serr));
				ui__warning("The %s file can't be used: %s\n%s",
					    symbol_conf.vmlinux_name, serr, msg);
			} else {
				ui__warning("A vmlinux file was not found.\n%s",
					    msg);
			}

			if (use_browser <= 0)
				sleep(5);
			top->vmlinux_warned = true;
		}
	}

When I fire up a compilation on sparc, this triggers immediately.

I'm trying to figure out what the "backup to kernel map" code is
accomplishing.

I see some language in the current code and in the changes that have
happened in this area talking about vdso.  Does that really happen?

The vdso is mapped into userspace virtual addresses, not kernel ones.

More history.  This didn't cause problems on sparc some time ago,
because the kernel IP check used to be "ip < 0" :-) Sparc kernel
addresses are not negative.  But now with machine__kernel_ip(), which
works using the symbol table determined kernel address range, it does
trigger.

What it all boils down to is that on architectures like sparc,
machine__kernel_ip() should always return false in this scenerio, and
therefore this kind of logic:

		if (cpumode == PERF_RECORD_MISC_USER && machine &&
		    mg != &machine->kmaps &&
		    machine__kernel_ip(machine, al->addr)) {

is basically invalid.  PERF_RECORD_MISC_USER implies no kernel address
can possibly match for the sample/event in question (no matter how
hard you try!) :-)
</>

So, I thought something had changed and in the past we would somehow
find that address in the kallsyms, but I couldn't find anything to back
that up, the patch introducing this is over a decade old, lots of things
changed, so I was just thinking I was missing something.

I tried a gtod busy loop to generate vdso activity and added a 'perf
probe' at that branch, on x86_64 to see if it ever gets hit:

Made thread__find_map() noinline, as 'perf probe' in lines of inline
functions seems to not be working, only at function start. (Masami?)

  # perf probe -x ~/bin/perf -L thread__find_map:57
  <thread__find_map@/home/acme/git/perf/tools/perf/util/event.c:57>
     57                 if (cpumode == PERF_RECORD_MISC_USER && machine &&
     58                     mg != &machine->kmaps &&
     59                     machine__kernel_ip(machine, al->addr)) {
     60                         mg = &machine->kmaps;
     61                         load_map = true;
     62                         goto try_again;
                        }
                } else {
                        /*
                         * Kernel maps might be changed when loading
                         * symbols so loading
                         * must be done prior to using kernel maps.
                         */
     69                 if (load_map)
     70                         map__load(al->map);
     71                 al->addr = al->map->map_ip(al->map, al->addr);

  # perf probe -x ~/bin/perf thread__find_map:60
  Added new event:
    probe_perf:thread__find_map (on thread__find_map:60 in /home/acme/bin/perf)

  You can now use it in all perf tools, such as:

	perf record -e probe_perf:thread__find_map -aR sleep 1

  #

  Then used this to see if, system wide, those probe points were being hit:

  # perf trace -e *perf:thread*/max-stack=8/
  ^C[root@jouet ~]#

  No hits when running 'perf top' and:

  # cat gtod.c
  #include <sys/time.h>

  int main(void)
  {
	struct timeval tv;

	while (1)
		gettimeofday(&tv, 0);

	return 0;
  }
  [root@jouet c]# ./gtod
  ^C

  Pressed 'P' in 'perf top' and the [vdso] samples are there:

  62.84%  [vdso]                    [.] __vdso_gettimeofday
   8.13%  gtod                      [.] main
   7.51%  [vdso]                    [.] 0x0000000000000914
   5.78%  [vdso]                    [.] 0x0000000000000917
   5.43%  gtod                      [.] _init
   2.71%  [vdso]                    [.] 0x000000000000092d
   0.35%  [kernel]                  [k] native_io_delay
   0.33%  libc-2.26.so              [.] __memmove_avx_unaligned_erms
   0.20%  [vdso]                    [.] 0x000000000000091d
   0.17%  [i2c_i801]                [k] i801_access
   0.06%  firefox                   [.] free
   0.06%  libglib-2.0.so.0.5400.3   [.] g_source_iter_next
   0.05%  [vdso]                    [.] 0x0000000000000919
   0.05%  libpthread-2.26.so        [.] __pthread_mutex_lock
   0.05%  libpixman-1.so.0.34.0     [.] 0x000000000006d3a7
   0.04%  [kernel]                  [k] entry_SYSCALL_64_trampoline
   0.04%  libxul.so                 [.] style::dom_apis::query_selector_slow
   0.04%  [kernel]                  [k] module_get_kallsym
   0.04%  firefox                   [.] malloc
   0.04%  [vdso]                    [.] 0x0000000000000910

  I added a 'perf probe' to thread__find_map:69, and that surely got tons
  of hits, i.e. for every map found, just to make sure the 'perf probe'
  command was really working.

  In the process I noticed a bug, we're only have records for '[vdso]' for
  pre-existing commands, i.e. ones that are running when we start 'perf top',
  when we will generate the PERF_RECORD_MMAP by looking at /perf/PID/maps.

  I.e. like this, for preexisting processes with a vdso map, again,
  tracing for all the system, only pre-existing processes get a [vdso] map
  (when having one):

  [root@jouet ~]# perf probe -x ~/bin/perf __machine__addnew_vdso
  Added new event:
  probe_perf:__machine__addnew_vdso (on __machine__addnew_vdso in /home/acme/bin/perf)

  You can now use it in all perf tools, such as:

	perf record -e probe_perf:__machine__addnew_vdso -aR sleep 1

  [root@jouet ~]# perf trace -e probe_perf:__machine__addnew_vdso/max-stack=8/
     0.000 probe_perf:__machine__addnew_vdso:(568eb3)
                                       __machine__addnew_vdso (/home/acme/bin/perf)
                                       map__new (/home/acme/bin/perf)
                                       machine__process_mmap2_event (/home/acme/bin/perf)
                                       machine__process_event (/home/acme/bin/perf)
                                       perf_event__process (/home/acme/bin/perf)
                                       perf_tool__process_synth_event (/home/acme/bin/perf)
                                       perf_event__synthesize_mmap_events (/home/acme/bin/perf)
                                       __event__synthesize_thread (/home/acme/bin/perf)

The kernel is generating a PERF_RECORD_MMAP for vDSOs, but somehow
'perf top' is not getting those records while 'perf record' is:

  # perf record ~acme/c/gtod
  ^C[ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.076 MB perf.data (1499 samples) ]

  # perf report -D | grep PERF_RECORD_MMAP2
  71293612401913 0x11b48 [0x70]: PERF_RECORD_MMAP2 25484/25484: [0x400000(0x1000) @ 0 fd:02 1137 541179306]: r-xp /home/acme/c/gtod
  71293612419012 0x11be0 [0x70]: PERF_RECORD_MMAP2 25484/25484: [0x7fa4a2783000(0x227000) @ 0 fd:00 3146370 854107250]: r-xp /usr/lib64/ld-2.26.so
  71293612432110 0x11c50 [0x60]: PERF_RECORD_MMAP2 25484/25484: [0x7ffcdb53a000(0x2000) @ 0 00:00 0 0]: r-xp [vdso]
  71293612509944 0x11cb0 [0x70]: PERF_RECORD_MMAP2 25484/25484: [0x7fa4a23cd000(0x3b6000) @ 0 fd:00 3149723 262067164]: r-xp /usr/lib64/libc-2.26.so
  #
  # perf script | grep vdso | head
      gtod 25484 71293.612768: 2485554 cycles:ppp:  7ffcdb53a914 [unknown] ([vdso])
      gtod 25484 71293.613576: 2149343 cycles:ppp:  7ffcdb53a917 [unknown] ([vdso])
      gtod 25484 71293.614274: 1814652 cycles:ppp:  7ffcdb53aca8 __vdso_gettimeofday+0x98 ([vdso])
      gtod 25484 71293.614862: 1669070 cycles:ppp:  7ffcdb53acc5 __vdso_gettimeofday+0xb5 ([vdso])
      gtod 25484 71293.615404: 1451589 cycles:ppp:  7ffcdb53acc5 __vdso_gettimeofday+0xb5 ([vdso])
      gtod 25484 71293.615999: 1269941 cycles:ppp:  7ffcdb53ace6 __vdso_gettimeofday+0xd6 ([vdso])
      gtod 25484 71293.616405: 1177946 cycles:ppp:  7ffcdb53a914 [unknown] ([vdso])
      gtod 25484 71293.616775: 1121290 cycles:ppp:  7ffcdb53ac47 __vdso_gettimeofday+0x37 ([vdso])
      gtod 25484 71293.617150: 1037721 cycles:ppp:  7ffcdb53ace6 __vdso_gettimeofday+0xd6 ([vdso])
      gtod 25484 71293.617478:  994526 cycles:ppp:  7ffcdb53ace6 __vdso_gettimeofday+0xd6 ([vdso])
  #

The patch is the obvious one and with it we also continue to resolve
vdso symbols for pre-existing processes in 'perf top' and for all
processes in 'perf record' + 'perf report/script'.

Suggested-by: David Miller <davem@davemloft.net>
Acked-by: David Miller <davem@davemloft.net>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-cs7skq9pp0kjypiju6o7trse@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/event.c | 21 ++-------------------
 1 file changed, 2 insertions(+), 19 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 0988eb3b844b..bc646185f8d9 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1561,26 +1561,9 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
 
 		return NULL;
 	}
-try_again:
+
 	al->map = map_groups__find(mg, al->addr);
-	if (al->map == NULL) {
-		/*
-		 * If this is outside of all known maps, and is a negative
-		 * address, try to look it up in the kernel dso, as it might be
-		 * a vsyscall or vdso (which executes in user-mode).
-		 *
-		 * XXX This is nasty, we should have a symbol list in the
-		 * "[vdso]" dso, but for now lets use the old trick of looking
-		 * in the whole kernel symbol list.
-		 */
-		if (cpumode == PERF_RECORD_MISC_USER && machine &&
-		    mg != &machine->kmaps &&
-		    machine__kernel_ip(machine, al->addr)) {
-			mg = &machine->kmaps;
-			load_map = true;
-			goto try_again;
-		}
-	} else {
+	if (al->map != NULL) {
 		/*
 		 * Kernel maps might be changed when loading symbols so loading
 		 * must be done prior to using kernel maps.
-- 
cgit v1.2.3


From b55cbc8d9b44aaee94f19e995a5f241d453763ee Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Wed, 17 Oct 2018 16:24:48 +0200
Subject: bpf: fix doc of bpf_skb_adjust_room() in uapi

len_diff is signed.

Fixes: fa15601ab31e ("bpf: add documentation for eBPF helpers (33-41)")
CC: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h       | 2 +-
 tools/include/uapi/linux/bpf.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f9187b41dff6..5e46f6732781 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1433,7 +1433,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags)
+ * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags)
  * 	Description
  * 		Grow or shrink the room for data in the packet associated to
  * 		*skb* by *len_diff*, and according to the selected *mode*.
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index f9187b41dff6..5e46f6732781 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1433,7 +1433,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags)
+ * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags)
  * 	Description
  * 		Grow or shrink the room for data in the packet associated to
  * 		*skb* by *len_diff*, and according to the selected *mode*.
-- 
cgit v1.2.3


From cf7905165fee15fe26ac4a91ee0a35b966249430 Mon Sep 17 00:00:00 2001
From: Alexey Budankov <alexey.budankov@linux.intel.com>
Date: Tue, 9 Oct 2018 17:36:24 +0300
Subject: perf record: Encode -k clockid frequency into Perf trace

Store -k clockid frequency into Perf trace to enable timestamps
derived metrics conversion into wall clock time on reporting stage.

Below is the example of perf report output:

  tools/perf/perf record -k raw -- ../../matrix/linux/matrix.gcc
  ...
  [ perf record: Captured and wrote 31.222 MB perf.data (818054 samples) ]

  tools/perf/perf report --header
  # ========
  ...
  # event : name = cycles:ppp, , size = 112, { sample_period, sample_freq } = 4000, sample_type = IP|TID|TIME|PERIOD, disabled = 1, inherit = 1, mmap = 1, comm = 1, freq = 1, enable_on_exec = 1, task = 1, precise_ip = 3, sample_id_all = 1, exclude_guest = 1, mmap2 = 1, comm_exec = 1, use_clockid = 1, clockid = 4
  ...
  # clockid frequency: 1000 MHz
  ...
  # ========

Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/23a4a1dc-b160-85a0-347d-40a2ed6d007b@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c | 24 ++++++++++++++++++++++--
 tools/perf/perf.h           |  1 +
 tools/perf/util/env.h       |  1 +
 tools/perf/util/header.c    | 23 +++++++++++++++++++++++
 tools/perf/util/header.h    |  1 +
 5 files changed, 48 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0980dfe3396b..10cf889c6d75 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -592,6 +592,9 @@ static void record__init_features(struct record *rec)
 	if (!rec->opts.full_auxtrace)
 		perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
 
+	if (!(rec->opts.use_clockid && rec->opts.clockid_res_ns))
+		perf_header__clear_feat(&session->header, HEADER_CLOCKID);
+
 	perf_header__clear_feat(&session->header, HEADER_STAT);
 }
 
@@ -897,6 +900,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	record__init_features(rec);
 
+	if (rec->opts.use_clockid && rec->opts.clockid_res_ns)
+		session->header.env.clockid_res_ns = rec->opts.clockid_res_ns;
+
 	if (forks) {
 		err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
 						    argv, data->is_pipe,
@@ -1337,6 +1343,19 @@ static const struct clockid_map clockids[] = {
 	CLOCKID_END,
 };
 
+static int get_clockid_res(clockid_t clk_id, u64 *res_ns)
+{
+	struct timespec res;
+
+	*res_ns = 0;
+	if (!clock_getres(clk_id, &res))
+		*res_ns = res.tv_nsec + res.tv_sec * NSEC_PER_SEC;
+	else
+		pr_warning("WARNING: Failed to determine specified clock resolution.\n");
+
+	return 0;
+}
+
 static int parse_clockid(const struct option *opt, const char *str, int unset)
 {
 	struct record_opts *opts = (struct record_opts *)opt->value;
@@ -1360,7 +1379,7 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
 
 	/* if its a number, we're done */
 	if (sscanf(str, "%d", &opts->clockid) == 1)
-		return 0;
+		return get_clockid_res(opts->clockid, &opts->clockid_res_ns);
 
 	/* allow a "CLOCK_" prefix to the name */
 	if (!strncasecmp(str, "CLOCK_", 6))
@@ -1369,7 +1388,8 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
 	for (cm = clockids; cm->name; cm++) {
 		if (!strcasecmp(str, cm->name)) {
 			opts->clockid = cm->clockid;
-			return 0;
+			return get_clockid_res(opts->clockid,
+					       &opts->clockid_res_ns);
 		}
 	}
 
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 21bf7f5a3cf5..0ed4a34c74c4 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -81,6 +81,7 @@ struct record_opts {
 	unsigned     initial_delay;
 	bool         use_clockid;
 	clockid_t    clockid;
+	u64          clockid_res_ns;
 	unsigned int proc_map_timeout;
 };
 
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 1f3ccc368530..d01b8355f4ca 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -63,6 +63,7 @@ struct perf_env {
 	struct numa_node	*numa_nodes;
 	struct memory_node	*memory_nodes;
 	unsigned long long	 memory_bsize;
+	u64                     clockid_res_ns;
 };
 
 extern struct perf_env perf_env;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 1ec1d9bc2d63..4fd45be95a43 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1034,6 +1034,13 @@ static int write_auxtrace(struct feat_fd *ff,
 	return err;
 }
 
+static int write_clockid(struct feat_fd *ff,
+			 struct perf_evlist *evlist __maybe_unused)
+{
+	return do_write(ff, &ff->ph->env.clockid_res_ns,
+			sizeof(ff->ph->env.clockid_res_ns));
+}
+
 static int cpu_cache_level__sort(const void *a, const void *b)
 {
 	struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a;
@@ -1508,6 +1515,12 @@ static void print_cpu_topology(struct feat_fd *ff, FILE *fp)
 		fprintf(fp, "# Core ID and Socket ID information is not available\n");
 }
 
+static void print_clockid(struct feat_fd *ff, FILE *fp)
+{
+	fprintf(fp, "# clockid frequency: %"PRIu64" MHz\n",
+		ff->ph->env.clockid_res_ns * 1000);
+}
+
 static void free_event_desc(struct perf_evsel *events)
 {
 	struct perf_evsel *evsel;
@@ -2531,6 +2544,15 @@ out:
 	return ret;
 }
 
+static int process_clockid(struct feat_fd *ff,
+			   void *data __maybe_unused)
+{
+	if (do_read_u64(ff, &ff->ph->env.clockid_res_ns))
+		return -1;
+
+	return 0;
+}
+
 struct feature_ops {
 	int (*write)(struct feat_fd *ff, struct perf_evlist *evlist);
 	void (*print)(struct feat_fd *ff, FILE *fp);
@@ -2590,6 +2612,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPN(CACHE,		cache,		true),
 	FEAT_OPR(SAMPLE_TIME,	sample_time,	false),
 	FEAT_OPR(MEM_TOPOLOGY,	mem_topology,	true),
+	FEAT_OPR(CLOCKID,       clockid,        false)
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index e17903caa71d..0d553ddca0a3 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -38,6 +38,7 @@ enum {
 	HEADER_CACHE,
 	HEADER_SAMPLE_TIME,
 	HEADER_MEM_TOPOLOGY,
+	HEADER_CLOCKID,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
-- 
cgit v1.2.3


From 0ab41886648bb75b951bd41d8b5cecaca8e0ad66 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Tue, 16 Oct 2018 20:55:55 -0700
Subject: perf annotate: Add Sparc support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

E.g.:

  $ perf annotate --stdio2
  Samples: 7K of event 'cycles:ppp', 4000 Hz, Event count (approx.): 3086733887
  __gettimeofday  /lib32/libc-2.27.so [Percent: local period]
  Percent│
         │
         │
         │    Disassembly of section .text:
         │
         │    000a6fa0 <__gettimeofday@@GLIBC_2.0>:
    0.47 │      save   %sp, -96, %sp
    0.73 │      sethi  %hi(0xe9000), %l7
         │    → call   __frame_state_for@@GLIBC_2.0+0x480
    0.30 │      add    %l7, 0x58, %l7     ! e9058 <nftw64@@GLIBC_2.3.3+0x818>
    1.33 │      mov    %i0, %o0
         │      mov    %i1, %o1
    0.43 │      mov    0x74, %g1
         │      ta     0x10
   88.92 │    ↓ bcc    30
    2.95 │      clr    %g1
         │      neg    %o0
         │      mov    1, %g1
    0.31 │30:   cmp    %g1, 0
         │      bne,pn %icc, a6fe4 <__gettimeofday@@GLIBC_2.0+0x44>
         │      mov    %o0, %i0
    1.96 │    ← return %i7 + 8
    2.62 │      nop
         │      sethi  %hi(0), %g1
         │      neg    %o0, %g2
         │      add    %g1, 0x160, %g1
         │      ld     [ %l7 + %g1 ], %g1
         │      st     %g2, [ %g7 + %g1 ]
         │    ← return %i7 + 8
         │      mov    -1, %o0

Signed-off-by: David S. Miller <davem@davemloft.net>
Link: http://lkml.kernel.org/r/20181016.205555.1070918198627611771.davem@davemloft.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/sparc/annotate/instructions.c | 169 ++++++++++++++++++++++++++
 tools/perf/util/annotate.c                    |   8 ++
 2 files changed, 177 insertions(+)
 create mode 100644 tools/perf/arch/sparc/annotate/instructions.c

(limited to 'tools')

diff --git a/tools/perf/arch/sparc/annotate/instructions.c b/tools/perf/arch/sparc/annotate/instructions.c
new file mode 100644
index 000000000000..2614c010c235
--- /dev/null
+++ b/tools/perf/arch/sparc/annotate/instructions.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+
+static int is_branch_cond(const char *cond)
+{
+	if (cond[0] == '\0')
+		return 1;
+
+	if (cond[0] == 'a' && cond[1] == '\0')
+		return 1;
+
+	if (cond[0] == 'c' &&
+	    (cond[1] == 'c' || cond[1] == 's') &&
+	    cond[2] == '\0')
+		return 1;
+
+	if (cond[0] == 'e' &&
+	    (cond[1] == '\0' ||
+	     (cond[1] == 'q' && cond[2] == '\0')))
+		return 1;
+
+	if (cond[0] == 'g' &&
+	    (cond[1] == '\0' ||
+	     (cond[1] == 't' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == 'u' && cond[3] == '\0')))
+		return 1;
+
+	if (cond[0] == 'l' &&
+	    (cond[1] == '\0' ||
+	     (cond[1] == 't' && cond[2] == '\0') ||
+	     (cond[1] == 'u' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == 'u' && cond[3] == '\0')))
+		return 1;
+
+	if (cond[0] == 'n' &&
+	    (cond[1] == '\0' ||
+	     (cond[1] == 'e' && cond[2] == '\0') ||
+	     (cond[1] == 'z' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == 'g' && cond[3] == '\0')))
+		return 1;
+
+	if (cond[0] == 'b' &&
+	    cond[1] == 'p' &&
+	    cond[2] == 'o' &&
+	    cond[3] == 's' &&
+	    cond[4] == '\0')
+		return 1;
+
+	if (cond[0] == 'v' &&
+	    (cond[1] == 'c' || cond[1] == 's') &&
+	    cond[2] == '\0')
+		return 1;
+
+	if (cond[0] == 'b' &&
+	    cond[1] == 'z' &&
+	    cond[2] == '\0')
+		return 1;
+
+	return 0;
+}
+
+static int is_branch_reg_cond(const char *cond)
+{
+	if ((cond[0] == 'n' || cond[0] == 'l') &&
+	    cond[1] == 'z' &&
+	    cond[2] == '\0')
+		return 1;
+
+	if (cond[0] == 'z' &&
+	    cond[1] == '\0')
+		return 1;
+
+	if ((cond[0] == 'g' || cond[0] == 'l') &&
+	    cond[1] == 'e' &&
+	    cond[2] == 'z' &&
+	    cond[3] == '\0')
+		return 1;
+
+	if (cond[0] == 'g' &&
+	    cond[1] == 'z' &&
+	    cond[2] == '\0')
+		return 1;
+
+	return 0;
+}
+
+static int is_branch_float_cond(const char *cond)
+{
+	if (cond[0] == '\0')
+		return 1;
+
+	if ((cond[0] == 'a' || cond[0] == 'e' ||
+	     cond[0] == 'z' || cond[0] == 'g' ||
+	     cond[0] == 'l' || cond[0] == 'n' ||
+	     cond[0] == 'o' || cond[0] == 'u') &&
+	    cond[1] == '\0')
+		return 1;
+
+	if (((cond[0] == 'g' && cond[1] == 'e') ||
+	     (cond[0] == 'l' && (cond[1] == 'e' ||
+				 cond[1] == 'g')) ||
+	     (cond[0] == 'n' && (cond[1] == 'e' ||
+				 cond[1] == 'z')) ||
+	     (cond[0] == 'u' && (cond[1] == 'e' ||
+				 cond[1] == 'g' ||
+				 cond[1] == 'l'))) &&
+	    cond[2] == '\0')
+		return 1;
+
+	if (cond[0] == 'u' &&
+	    (cond[1] == 'g' || cond[1] == 'l') &&
+	    cond[2] == 'e' &&
+	    cond[3] == '\0')
+		return 1;
+
+	return 0;
+}
+
+static struct ins_ops *sparc__associate_instruction_ops(struct arch *arch, const char *name)
+{
+	struct ins_ops *ops = NULL;
+
+	if (!strcmp(name, "call") ||
+	    !strcmp(name, "jmp") ||
+	    !strcmp(name, "jmpl")) {
+		ops = &call_ops;
+	} else if (!strcmp(name, "ret") ||
+		   !strcmp(name, "retl") ||
+		   !strcmp(name, "return")) {
+		ops = &ret_ops;
+	} else if (!strcmp(name, "mov")) {
+		ops = &mov_ops;
+	} else {
+		if (name[0] == 'c' &&
+		    (name[1] == 'w' || name[1] == 'x'))
+			name += 2;
+
+		if (name[0] == 'b') {
+			const char *cond = name + 1;
+
+			if (cond[0] == 'r') {
+				if (is_branch_reg_cond(cond + 1))
+					ops = &jump_ops;
+			} else if (is_branch_cond(cond)) {
+				ops = &jump_ops;
+			}
+		} else if (name[0] == 'f' && name[1] == 'b') {
+			if (is_branch_float_cond(name + 2))
+				ops = &jump_ops;
+		}
+	}
+
+	if (ops)
+		arch__associate_ins_ops(arch, name, ops);
+
+	return ops;
+}
+
+static int sparc__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
+{
+	if (!arch->initialized) {
+		arch->initialized = true;
+		arch->associate_instruction_ops = sparc__associate_instruction_ops;
+		arch->objdump.comment_char = '#';
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 28cd6a17491b..6936daf89ddd 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -139,6 +139,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i
 #include "arch/x86/annotate/instructions.c"
 #include "arch/powerpc/annotate/instructions.c"
 #include "arch/s390/annotate/instructions.c"
+#include "arch/sparc/annotate/instructions.c"
 
 static struct arch architectures[] = {
 	{
@@ -170,6 +171,13 @@ static struct arch architectures[] = {
 			.comment_char = '#',
 		},
 	},
+	{
+		.name = "sparc",
+		.init = sparc__annotate_init,
+		.objdump = {
+			.comment_char = '#',
+		},
+	},
 };
 
 static void ins__delete(struct ins_operands *ops)
-- 
cgit v1.2.3


From d87b9790b3deb7601872d34fd05af3da78147583 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Tue, 16 Oct 2018 21:15:45 -0700
Subject: perf jitdump: Add Sparc support.

Signed-off-by: David S. Miller <davem@davemloft.net>
Link: http://lkml.kernel.org/r/20181016.211545.1487970139012324624.davem@davemloft.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/sparc/Makefile | 2 ++
 tools/perf/util/genelf.h       | 6 ++++++
 2 files changed, 8 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/arch/sparc/Makefile b/tools/perf/arch/sparc/Makefile
index 7fbca175099e..275dea7ff59a 100644
--- a/tools/perf/arch/sparc/Makefile
+++ b/tools/perf/arch/sparc/Makefile
@@ -1,3 +1,5 @@
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
+
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index de322d51c7fe..b72440bf9a79 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -29,6 +29,12 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
 #elif defined(__powerpc__)
 #define GEN_ELF_ARCH	EM_PPC
 #define GEN_ELF_CLASS	ELFCLASS32
+#elif defined(__sparc__) && defined(__arch64__)
+#define GEN_ELF_ARCH	EM_SPARCV9
+#define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__sparc__)
+#define GEN_ELF_ARCH	EM_SPARC
+#define GEN_ELF_CLASS	ELFCLASS32
 #else
 #error "unsupported architecture"
 #endif
-- 
cgit v1.2.3


From d6afa561e1471ccfdaf7191230c0c59a37e45a5b Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Wed, 17 Oct 2018 12:08:59 -0700
Subject: perf symbols: Set PLT entry/header sizes properly on Sparc

Using the sh_entsize for both values isn't correct.  It happens to be
correct on x86...

For both 32-bit and 64-bit sparc, there are four PLT entries in the PLT
section.

Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexis Berlemont <alexis.berlemont@gmail.com>
Cc: David Tolnay <dtolnay@gmail.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Hemant Kumar <hemant@linux.vnet.ibm.com>
Cc: Li Bin <huawei.libin@huawei.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: zhangmengting@huawei.com
Fixes: b2f7605076d6 ("perf symbols: Fix plt entry calculation for ARM and AARCH64")
Link: http://lkml.kernel.org/r/20181017.120859.2268840244308635255.davem@davemloft.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/symbol-elf.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 29770ea61768..6e70cc00c161 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -324,7 +324,17 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss)
 			plt_entry_size = 16;
 			break;
 
-		default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/sparc/xtensa need to be checked */
+		case EM_SPARC:
+			plt_header_size = 48;
+			plt_entry_size = 12;
+			break;
+
+		case EM_SPARCV9:
+			plt_header_size = 128;
+			plt_entry_size = 32;
+			break;
+
+		default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/xtensa need to be checked */
 			plt_header_size = shdr_plt.sh_entsize;
 			plt_entry_size = shdr_plt.sh_entsize;
 			break;
-- 
cgit v1.2.3


From e325808c0051b16729ffd472ff887c6cae5c6317 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 16 Oct 2018 19:03:43 +0100
Subject: usbip: tools: fix atoi() on non-null terminated string

Currently the call to atoi is being passed a single char string
that is not null terminated, so there is a potential read overrun
along the stack when parsing for an integer value.  Fix this by
instead using a 2 char string that is initialized to all zeros
to ensure that a 1 char read into the string is always terminated
with a \0.

Detected by cppcheck:
"Invalid atoi() argument nr 1. A nul-terminated string is required."

Fixes: 3391ba0e2792 ("usbip: tools: Extract generic code to be shared with vudc backend")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 tools/usb/usbip/libsrc/usbip_host_common.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/usb/usbip/libsrc/usbip_host_common.c b/tools/usb/usbip/libsrc/usbip_host_common.c
index dc93fadbee96..d79c7581b175 100644
--- a/tools/usb/usbip/libsrc/usbip_host_common.c
+++ b/tools/usb/usbip/libsrc/usbip_host_common.c
@@ -43,7 +43,7 @@ static int32_t read_attr_usbip_status(struct usbip_usb_device *udev)
 	int size;
 	int fd;
 	int length;
-	char status;
+	char status[2] = { 0 };
 	int value = 0;
 
 	size = snprintf(status_attr_path, sizeof(status_attr_path),
@@ -61,14 +61,14 @@ static int32_t read_attr_usbip_status(struct usbip_usb_device *udev)
 		return -1;
 	}
 
-	length = read(fd, &status, 1);
+	length = read(fd, status, 1);
 	if (length < 0) {
 		err("error reading attribute %s", status_attr_path);
 		close(fd);
 		return -1;
 	}
 
-	value = atoi(&status);
+	value = atoi(status);
 
 	return value;
 }
-- 
cgit v1.2.3


From 1bd70d2eba9d90eb787634361f0f6fa2c86b3f6d Mon Sep 17 00:00:00 2001
From: Peng Hao <peng.hao2@zte.com.cn>
Date: Thu, 18 Oct 2018 23:18:36 +0800
Subject: selftests/bpf: fix file resource leak in load_kallsyms

FILE pointer variable f is opened but never closed.

Signed-off-by: Peng Hao <peng.hao2@zte.com.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/trace_helpers.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index cabe2a3a3b30..a3d1dace4a75 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -41,6 +41,7 @@ int load_kallsyms(void)
 		syms[i].name = strdup(func);
 		i++;
 	}
+	fclose(f);
 	sym_cnt = i;
 	qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp);
 	return 0;
-- 
cgit v1.2.3


From 3ddeac6705aba31b7528c7d7a528eabb74475622 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 18 Oct 2018 11:34:55 -0700
Subject: tools: bpftool: use 4 context mode for the NFP disasm

The nfp driver is currently always JITing the BPF for 4 context/thread
mode of the NFP flow processors.  Tell this to the disassembler,
otherwise some registers may be incorrectly decoded.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/common.c     |  5 ++++-
 tools/bpf/bpftool/jit_disasm.c |  4 +++-
 tools/bpf/bpftool/main.h       |  6 ++++--
 tools/bpf/bpftool/prog.c       | 14 +++++++++-----
 4 files changed, 20 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 3318da8060bd..25af85304ebe 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -554,7 +554,9 @@ static int read_sysfs_netdev_hex_int(char *devname, const char *entry_name)
 	return read_sysfs_hex_int(full_path);
 }
 
-const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino)
+const char *
+ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino,
+		      const char **opt)
 {
 	char devname[IF_NAMESIZE];
 	int vendor_id;
@@ -579,6 +581,7 @@ const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino)
 		    device_id != 0x6000 &&
 		    device_id != 0x6003)
 			p_info("Unknown NFP device ID, assuming it is NFP-6xxx arch");
+		*opt = "ctx4";
 		return "NFP-6xxx";
 	default:
 		p_err("Can't get bfd arch name for device vendor id 0x%04x",
diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
index 87439320ef70..c75ffd9ce2bb 100644
--- a/tools/bpf/bpftool/jit_disasm.c
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -77,7 +77,7 @@ static int fprintf_json(void *out, const char *fmt, ...)
 }
 
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
-		       const char *arch)
+		       const char *arch, const char *disassembler_options)
 {
 	disassembler_ftype disassemble;
 	struct disassemble_info info;
@@ -116,6 +116,8 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
 
 	info.arch = bfd_get_arch(bfdf);
 	info.mach = bfd_get_mach(bfdf);
+	if (disassembler_options)
+		info.disassembler_options = disassembler_options;
 	info.buffer = image;
 	info.buffer_length = len;
 
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 28ee769bd11b..28322ace2856 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -145,13 +145,15 @@ int map_parse_fd(int *argc, char ***argv);
 int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len);
 
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
-		       const char *arch);
+		       const char *arch, const char *disassembler_options);
 void print_data_json(uint8_t *data, size_t len);
 void print_hex_data_json(uint8_t *data, size_t len);
 
 unsigned int get_page_size(void);
 unsigned int get_possible_cpus(void);
-const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino);
+const char *
+ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino,
+		      const char **opt);
 
 struct btf_dumper {
 	const struct btf *btf;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 335028968dfb..5302ee282409 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -449,6 +449,7 @@ static int do_dump(int argc, char **argv)
 	unsigned long *func_ksyms = NULL;
 	struct bpf_prog_info info = {};
 	unsigned int *func_lens = NULL;
+	const char *disasm_opt = NULL;
 	unsigned int nr_func_ksyms;
 	unsigned int nr_func_lens;
 	struct dump_data dd = {};
@@ -607,9 +608,10 @@ static int do_dump(int argc, char **argv)
 		const char *name = NULL;
 
 		if (info.ifindex) {
-			name = ifindex_to_bfd_name_ns(info.ifindex,
-						      info.netns_dev,
-						      info.netns_ino);
+			name = ifindex_to_bfd_params(info.ifindex,
+						     info.netns_dev,
+						     info.netns_ino,
+						     &disasm_opt);
 			if (!name)
 				goto err_free;
 		}
@@ -651,7 +653,8 @@ static int do_dump(int argc, char **argv)
 					printf("%s:\n", sym_name);
 				}
 
-				disasm_print_insn(img, lens[i], opcodes, name);
+				disasm_print_insn(img, lens[i], opcodes, name,
+						  disasm_opt);
 				img += lens[i];
 
 				if (json_output)
@@ -663,7 +666,8 @@ static int do_dump(int argc, char **argv)
 			if (json_output)
 				jsonw_end_array(json_wtr);
 		} else {
-			disasm_print_insn(buf, *member_len, opcodes, name);
+			disasm_print_insn(buf, *member_len, opcodes, name,
+					  disasm_opt);
 		}
 	} else if (visual) {
 		if (json_output)
-- 
cgit v1.2.3


From 389373d3306553896a9e218493e5b6175c844eb0 Mon Sep 17 00:00:00 2001
From: Hongxu Jia <hongxu.jia@windriver.com>
Date: Thu, 18 Oct 2018 16:26:13 +0800
Subject: perf arm64: Fix generate system call table failed with /tmp mounted
 with noexec
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When /tmp is mounted with noexec, mksyscalltbl fails.

  [snip]
  |perf-1.0/tools/perf/arch/arm64/entry/syscalls//mksyscalltbl:
  /tmp/create-table-6VGPSt: Permission denied
  [snip]

Add variable TMPDIR as prefix dir of the temporary file, if it is set,
replace default /tmp.

Signed-off-by: Hongxu Jia <hongxu.jia@windriver.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Sébastien Boisvert <sboisvert@gydle.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Fixes: 2b5882435606 ("perf arm64: Generate system call table from asm/unistd.h")
LPU-Reference: 1539851173-14959-1-git-send-email-hongxu.jia@windriver.com
Link: https://lkml.kernel.org/n/tip-1qrgq840ci0c5cy4oww957ge@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm64/entry/syscalls/mksyscalltbl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
index 2dbb8cade048..c88fd32563eb 100755
--- a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
+++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
@@ -23,7 +23,7 @@ create_table_from_c()
 {
 	local sc nr last_sc
 
-	create_table_exe=`mktemp /tmp/create-table-XXXXXX`
+	create_table_exe=`mktemp ${TMPDIR:-/tmp}/create-table-XXXXXX`
 
 	{
 
-- 
cgit v1.2.3


From 4ba8b3ebf4f8f583c2c01da20e4d110a5881ffdd Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 18 Oct 2018 15:24:07 -0300
Subject: tools lib subcmd: Introduce OPTION_ULONG

For completeness, will be used in 'perf trace --max-events'.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-glaj3pwespxfj2fdjs9a20b6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/subcmd/parse-options.c | 19 +++++++++++++++++++
 tools/lib/subcmd/parse-options.h |  2 ++
 2 files changed, 21 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index cb7154eccbdc..dbb9efbf718a 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -116,6 +116,7 @@ static int get_value(struct parse_opt_ctx_t *p,
 		case OPTION_INTEGER:
 		case OPTION_UINTEGER:
 		case OPTION_LONG:
+		case OPTION_ULONG:
 		case OPTION_U64:
 		default:
 			break;
@@ -166,6 +167,7 @@ static int get_value(struct parse_opt_ctx_t *p,
 		case OPTION_INTEGER:
 		case OPTION_UINTEGER:
 		case OPTION_LONG:
+		case OPTION_ULONG:
 		case OPTION_U64:
 		default:
 			break;
@@ -295,6 +297,22 @@ static int get_value(struct parse_opt_ctx_t *p,
 			return opterror(opt, "expects a numerical value", flags);
 		return 0;
 
+	case OPTION_ULONG:
+		if (unset) {
+			*(unsigned long *)opt->value = 0;
+			return 0;
+		}
+		if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+			*(unsigned long *)opt->value = opt->defval;
+			return 0;
+		}
+		if (get_arg(p, opt, flags, &arg))
+			return -1;
+		*(unsigned long *)opt->value = strtoul(arg, (char **)&s, 10);
+		if (*s)
+			return opterror(opt, "expects a numerical value", flags);
+		return 0;
+
 	case OPTION_U64:
 		if (unset) {
 			*(u64 *)opt->value = 0;
@@ -703,6 +721,7 @@ static void print_option_help(const struct option *opts, int full)
 	case OPTION_ARGUMENT:
 		break;
 	case OPTION_LONG:
+	case OPTION_ULONG:
 	case OPTION_U64:
 	case OPTION_INTEGER:
 	case OPTION_UINTEGER:
diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h
index 92fdbe1519f6..6ca2a8bfe716 100644
--- a/tools/lib/subcmd/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -25,6 +25,7 @@ enum parse_opt_type {
 	OPTION_STRING,
 	OPTION_INTEGER,
 	OPTION_LONG,
+	OPTION_ULONG,
 	OPTION_CALLBACK,
 	OPTION_U64,
 	OPTION_UINTEGER,
@@ -133,6 +134,7 @@ struct option {
 #define OPT_INTEGER(s, l, v, h)     { .type = OPTION_INTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) }
 #define OPT_UINTEGER(s, l, v, h)    { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h) }
 #define OPT_LONG(s, l, v, h)        { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
+#define OPT_ULONG(s, l, v, h)        { .type = OPTION_ULONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned long *), .help = (h) }
 #define OPT_U64(s, l, v, h)         { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
 #define OPT_STRING(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h) }
 #define OPT_STRING_OPTARG(s, l, v, a, h, d) \
-- 
cgit v1.2.3


From 5067a8cdd4ce3588fca2e0ee554f0f081650de8f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 18 Oct 2018 16:38:27 -0300
Subject: perf trace: Introduce --max-events
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Allow stopping tracing after a number of events take place, considering
strace-like syscalls formatting as one event per enter/exit pair or when
in a multi-process tracing session a syscall is interrupted and printed
ending with '...'.

Examples included in the documentation:

Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):

  $ perf trace -e open* --max-events 4
  [root@jouet perf]# trace -e open* --max-events 4
  2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
  2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
  3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
  4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
  $

Trace the first minor page fault when running a workload:

  # perf trace -F min --max-stack=7 --max-events 1 sleep 1
     0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
                                       __clear_user ([kernel.kallsyms])
                                       load_elf_binary ([kernel.kallsyms])
                                       search_binary_handler ([kernel.kallsyms])
                                       __do_execve_file.isra.33 ([kernel.kallsyms])
                                       __x64_sys_execve ([kernel.kallsyms])
                                       do_syscall_64 ([kernel.kallsyms])
                                       entry_SYSCALL_64 ([kernel.kallsyms])
  #

Trace the next min page page fault to take place on the first CPU:

  # perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
     0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
                                       js::gc::FreeSpan::initAsEmpty (inlined)
                                       js::gc::Arena::setAsNotAllocated (inlined)
                                       js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
                                       js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
                                       js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
                                       js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
                                       js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
                                       js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
                                       js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
                                       JSThinInlineString::new_<(js::AllowGC)1> (inlined)
                                       AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
                                       js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
                                       [0x18b26e6bc2bd] (/tmp/perf-17136.map)

Tracing the next four ext4 operations on a specific CPU:

  # perf trace -e ext4:*/call-graph=fp/ --max-events 4 --cpu 3
     0.000 mutt/3849 ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 57277 lblk 0
                                       ext4_es_lookup_extent ([kernel.kallsyms])
                                       read (/usr/lib64/libc-2.26.so)
     0.097 mutt/3849 ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 57277 found 0 [0/0) 0
                                       ext4_es_lookup_extent ([kernel.kallsyms])
                                       read (/usr/lib64/libc-2.26.so)
     0.141 mutt/3849 ext4:ext4_ext_map_blocks_enter:dev 253,2 ino 57277 lblk 0 len 1 flags
                                       ext4_ext_map_blocks ([kernel.kallsyms])
                                       read (/usr/lib64/libc-2.26.so)
     0.184 mutt/3849 ext4:ext4_ext_load_extent:dev 253,2 ino 57277 lblk 1516511 pblk 18446744071750013657
                                       __read_extent_tree_block ([kernel.kallsyms])
                                       __read_extent_tree_block ([kernel.kallsyms])
                                       ext4_find_extent ([kernel.kallsyms])
                                       ext4_ext_map_blocks ([kernel.kallsyms])
                                       ext4_map_blocks ([kernel.kallsyms])
                                       ext4_mpage_readpages ([kernel.kallsyms])
                                       read_pages ([kernel.kallsyms])
                                       __do_page_cache_readahead ([kernel.kallsyms])
                                       ondemand_readahead ([kernel.kallsyms])
                                       generic_file_read_iter ([kernel.kallsyms])
                                       __vfs_read ([kernel.kallsyms])
                                       vfs_read ([kernel.kallsyms])
                                       ksys_read ([kernel.kallsyms])
                                       do_syscall_64 ([kernel.kallsyms])
                                       entry_SYSCALL_64 ([kernel.kallsyms])
                                       read (/usr/lib64/libc-2.26.so)
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Rudá Moura <ruda.moura@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-sweh107bs7ol5bzls0m4tqdz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-trace.txt | 47 +++++++++++++++++++++++++++++++++
 tools/perf/builtin-trace.c              | 21 +++++++++++++++
 2 files changed, 68 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 115db9e06ecd..0d1a1cd4d328 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -171,6 +171,11 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --kernel-syscall-graph::
 	 Show the kernel callchains on the syscall exit path.
 
+--max-events=N::
+	Stop after processing N events. Note that strace-like events are considered
+	only at exit time or when a syscall is interrupted, i.e. in those cases this
+	option is equivalent to the number of lines printed.
+
 --max-stack::
         Set the stack depth limit when parsing the callchain, anything
         beyond the specified depth will be ignored. Note that at this point
@@ -238,6 +243,48 @@ Trace syscalls, major and minor pagefaults:
   As you can see, there was major pagefault in python process, from
   CRYPTO_push_info_ routine which faulted somewhere in libcrypto.so.
 
+Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
+
+  $ perf trace -e open* --max-events 4
+  [root@jouet perf]# trace -e open* --max-events 4
+  2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
+  2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
+  3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
+  4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
+  $
+
+Trace the first minor page fault when running a workload:
+
+  # perf trace -F min --max-stack=7 --max-events 1 sleep 1
+     0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
+                                       __clear_user ([kernel.kallsyms])
+                                       load_elf_binary ([kernel.kallsyms])
+                                       search_binary_handler ([kernel.kallsyms])
+                                       __do_execve_file.isra.33 ([kernel.kallsyms])
+                                       __x64_sys_execve ([kernel.kallsyms])
+                                       do_syscall_64 ([kernel.kallsyms])
+                                       entry_SYSCALL_64 ([kernel.kallsyms])
+  #
+
+Trace the next min page page fault to take place on the first CPU:
+
+  # perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
+     0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
+                                       js::gc::FreeSpan::initAsEmpty (inlined)
+                                       js::gc::Arena::setAsNotAllocated (inlined)
+                                       js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
+                                       js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
+                                       js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
+                                       js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
+                                       js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
+                                       js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
+                                       js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
+                                       JSThinInlineString::new_<(js::AllowGC)1> (inlined)
+                                       AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
+                                       js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
+                                       [0x18b26e6bc2bd] (/tmp/perf-17136.map)
+  #
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script[1]
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 90289f31dd87..74638034861c 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -89,6 +89,8 @@ struct trace {
 	u64			base_time;
 	FILE			*output;
 	unsigned long		nr_events;
+	unsigned long		nr_events_printed;
+	unsigned long		max_events;
 	struct strlist		*ev_qualifier;
 	struct {
 		size_t		nr;
@@ -1664,6 +1666,8 @@ static int trace__printf_interrupted_entry(struct trace *trace)
 	printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str);
 	ttrace->entry_pending = false;
 
+	++trace->nr_events_printed;
+
 	return printed;
 }
 
@@ -1940,6 +1944,13 @@ errno_print: {
 
 	fputc('\n', trace->output);
 
+	/*
+	 * We only consider an 'event' for the sake of --max-events a non-filtered
+	 * sys_enter + sys_exit and other tracepoint events.
+	 */
+	if (++trace->nr_events_printed == trace->max_events && trace->max_events != ULONG_MAX)
+		interrupted = true;
+
 	if (callchain_ret > 0)
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
@@ -2072,6 +2083,7 @@ static void bpf_output__fprintf(struct trace *trace,
 {
 	binary__fprintf(sample->raw_data, sample->raw_size, 8,
 			bpf_output__printer, NULL, trace->output);
+	++trace->nr_events_printed;
 }
 
 static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
@@ -2127,6 +2139,7 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 			event_format__fprintf(evsel->tp_format, sample->cpu,
 					      sample->raw_data, sample->raw_size,
 					      trace->output);
+			++trace->nr_events_printed;
 		}
 	}
 
@@ -2225,6 +2238,8 @@ static int trace__pgfault(struct trace *trace,
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
 		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
+
+	++trace->nr_events_printed;
 out:
 	err = 0;
 out_put:
@@ -2402,6 +2417,9 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st
 		tracepoint_handler handler = evsel->handler;
 		handler(trace, evsel, event, sample);
 	}
+
+	if (trace->nr_events_printed >= trace->max_events && trace->max_events != ULONG_MAX)
+		interrupted = true;
 }
 
 static int trace__add_syscall_newtp(struct trace *trace)
@@ -3249,6 +3267,7 @@ int cmd_trace(int argc, const char **argv)
 		.trace_syscalls = false,
 		.kernel_syscallchains = false,
 		.max_stack = UINT_MAX,
+		.max_events = ULONG_MAX,
 	};
 	const char *output_name = NULL;
 	const struct option trace_options[] = {
@@ -3301,6 +3320,8 @@ int cmd_trace(int argc, const char **argv)
 		     &record_parse_callchain_opt),
 	OPT_BOOLEAN(0, "kernel-syscall-graph", &trace.kernel_syscallchains,
 		    "Show the kernel callchains on the syscall exit path"),
+	OPT_ULONG(0, "max-events", &trace.max_events,
+		"Set the maximum number of events to print, exit after that is reached. "),
 	OPT_UINTEGER(0, "min-stack", &trace.min_stack,
 		     "Set the minimum stack depth when parsing the callchain, "
 		     "anything below the specified depth will be ignored."),
-- 
cgit v1.2.3


From f15ac811e80b857a443476de60ce70d3e6049ae5 Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Fri, 19 Oct 2018 16:38:16 +0200
Subject: selftests/kvm: add missing executables to .gitignore

Fixes: 18178ff86217 ("KVM: selftests: add Enlightened VMCS test")
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/.gitignore | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 552b0d9a49f4..6210ba41c29e 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,4 +1,5 @@
 /x86_64/cr4_cpuid_sync_test
+/x86_64/evmcs_test
 /x86_64/platform_info_test
 /x86_64/set_sregs_test
 /x86_64/sync_regs_test
-- 
cgit v1.2.3


From 2fda5ada07f36f6cde39a52e7f05d86ea8ffdc33 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 19 Oct 2018 15:47:34 -0300
Subject: perf evsel: Introduce per event max_events property

This simply adds the field to 'struct perf_evsel' and allows setting
it via the event parser, to test it lets trace trace:

First look at where in a function that receives an evsel we can put a probe
to read how evsel->max_events was setup:

  # perf probe -x ~/bin/perf -L trace__event_handler
  <trace__event_handler@/home/acme/git/perf/tools/perf/builtin-trace.c:0>
        0  static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
                                          union perf_event *event __maybe_unused,
                                          struct perf_sample *sample)
        3  {
        4         struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
        5         int callchain_ret = 0;

        7         if (sample->callchain) {
        8                 callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
        9                 if (callchain_ret == 0) {
       10                         if (callchain_cursor.nr < trace->min_stack)
       11                                 goto out;
       12                         callchain_ret = 1;
                          }
                  }

See what variables we can probe at line 7:

  # perf probe -x ~/bin/perf -V trace__event_handler:7
  Available variables at trace__event_handler:7
          @<trace__event_handler+89>
                  int     callchain_ret
                  struct perf_evsel*      evsel
                  struct perf_sample*     sample
                  struct thread*  thread
                  struct trace*   trace
                  union perf_event*       event

Add a probe at that line asking for evsel->max_events to be collected and named
as "max_events":

  # perf probe -x ~/bin/perf trace__event_handler:7 'max_events=evsel->max_events'
  Added new event:
    probe_perf:trace__event_handler (on trace__event_handler:7 in /home/acme/bin/perf with max_events=evsel->max_events)

  You can now use it in all perf tools, such as:

  	perf record -e probe_perf:trace__event_handler -aR sleep 1

Now use 'perf trace', here aliased to just 'trace' and trace trace, i.e.
the first 'trace' is tracing just that 'probe_perf:trace__event_handler' event,
while the traced trace is tracing all scheduler tracepoints, will stop at two
events (--max-events 2) and will just set evsel->max_events for all the sched
tracepoints to 9, we will see the output of both traces intermixed:

  # trace -e *perf:*event_handler trace --max-events 2 -e sched:*/nr=9/
       0.000 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=000
       0.009 :0/0 sched:sched_wakeup:comm=rcu_sched pid=10 prio=120 target_cpu=000
       0.000 trace/23949 probe_perf:trace__event_handler:(48c34a) max_events=0x9
       0.046 trace/23949 probe_perf:trace__event_handler:(48c34a) max_events=0x9
  #

Now, if the traced trace sends its output to /dev/null, we'll see just
what the first level trace outputs: that evsel->max_events is indeed
being set to 9:

  # trace -e *perf:*event_handler trace -o /dev/null --max-events 2 -e sched:*/nr=9/
       0.000 trace/23961 probe_perf:trace__event_handler:(48c34a) max_events=0x9
       0.030 trace/23961 probe_perf:trace__event_handler:(48c34a) max_events=0x9
  #

Now that we can set evsel->max_events, we can go to the next step, honour that
per-event property in 'perf trace'.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-og00yasj276joem6e14l1eas@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evsel.c        | 4 ++++
 tools/perf/util/evsel.h        | 3 +++
 tools/perf/util/parse-events.c | 8 ++++++++
 tools/perf/util/parse-events.h | 1 +
 tools/perf/util/parse-events.l | 1 +
 5 files changed, 17 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 29d7b97f66fb..7e95ec1c19a8 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -232,6 +232,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->leader	   = evsel;
 	evsel->unit	   = "";
 	evsel->scale	   = 1.0;
+	evsel->max_events  = ULONG_MAX;
 	evsel->evlist	   = NULL;
 	evsel->bpf_fd	   = -1;
 	INIT_LIST_HEAD(&evsel->node);
@@ -793,6 +794,9 @@ static void apply_config_terms(struct perf_evsel *evsel,
 		case PERF_EVSEL__CONFIG_TERM_MAX_STACK:
 			max_stack = term->val.max_stack;
 			break;
+		case PERF_EVSEL__CONFIG_TERM_MAX_EVENTS:
+			evsel->max_events = term->val.max_events;
+			break;
 		case PERF_EVSEL__CONFIG_TERM_INHERIT:
 			/*
 			 * attr->inherit should has already been set by
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4107c39f4a54..ad5d615c6db6 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -46,6 +46,7 @@ enum term_type {
 	PERF_EVSEL__CONFIG_TERM_STACK_USER,
 	PERF_EVSEL__CONFIG_TERM_INHERIT,
 	PERF_EVSEL__CONFIG_TERM_MAX_STACK,
+	PERF_EVSEL__CONFIG_TERM_MAX_EVENTS,
 	PERF_EVSEL__CONFIG_TERM_OVERWRITE,
 	PERF_EVSEL__CONFIG_TERM_DRV_CFG,
 	PERF_EVSEL__CONFIG_TERM_BRANCH,
@@ -65,6 +66,7 @@ struct perf_evsel_config_term {
 		bool	inherit;
 		bool	overwrite;
 		char	*branch;
+		unsigned long max_events;
 	} val;
 	bool weak;
 };
@@ -99,6 +101,7 @@ struct perf_evsel {
 	struct perf_counts	*prev_raw_counts;
 	int			idx;
 	u32			ids;
+	unsigned long		max_events;
 	char			*name;
 	double			scale;
 	const char		*unit;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f8cd3e7c9186..59be3466d64d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -926,6 +926,7 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
 	[PARSE_EVENTS__TERM_TYPE_NOINHERIT]		= "no-inherit",
 	[PARSE_EVENTS__TERM_TYPE_INHERIT]		= "inherit",
 	[PARSE_EVENTS__TERM_TYPE_MAX_STACK]		= "max-stack",
+	[PARSE_EVENTS__TERM_TYPE_MAX_EVENTS]		= "nr",
 	[PARSE_EVENTS__TERM_TYPE_OVERWRITE]		= "overwrite",
 	[PARSE_EVENTS__TERM_TYPE_NOOVERWRITE]		= "no-overwrite",
 	[PARSE_EVENTS__TERM_TYPE_DRV_CFG]		= "driver-config",
@@ -1037,6 +1038,9 @@ do {									   \
 	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
 		CHECK_TYPE_VAL(NUM);
 		break;
+	case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
+		CHECK_TYPE_VAL(NUM);
+		break;
 	default:
 		err->str = strdup("unknown term");
 		err->idx = term->err_term;
@@ -1084,6 +1088,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 	case PARSE_EVENTS__TERM_TYPE_INHERIT:
 	case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
 	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+	case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
 	case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
 	case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
 		return config_term_common(attr, term, err);
@@ -1162,6 +1167,9 @@ do {								\
 		case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
 			ADD_CONFIG_TERM(MAX_STACK, max_stack, term->val.num);
 			break;
+		case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
+			ADD_CONFIG_TERM(MAX_EVENTS, max_events, term->val.num);
+			break;
 		case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
 			ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 1 : 0);
 			break;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 4473dac27aee..5ed035cbcbb7 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -71,6 +71,7 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_NOINHERIT,
 	PARSE_EVENTS__TERM_TYPE_INHERIT,
 	PARSE_EVENTS__TERM_TYPE_MAX_STACK,
+	PARSE_EVENTS__TERM_TYPE_MAX_EVENTS,
 	PARSE_EVENTS__TERM_TYPE_NOOVERWRITE,
 	PARSE_EVENTS__TERM_TYPE_OVERWRITE,
 	PARSE_EVENTS__TERM_TYPE_DRV_CFG,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 5f761f3ed0f3..7805c71aaae2 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -269,6 +269,7 @@ time			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_TIME); }
 call-graph		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CALLGRAPH); }
 stack-size		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_STACKSIZE); }
 max-stack		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_STACK); }
+nr			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_EVENTS); }
 inherit			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_INHERIT); }
 no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
 overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); }
-- 
cgit v1.2.3


From da4e1b15f67613eca7ae998abd996cfee7cff1ba Mon Sep 17 00:00:00 2001
From: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Date: Thu, 18 Oct 2018 15:16:36 +0200
Subject: Sync uapi/bpf.h to tools/include

Sync both files.

Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/bpf.h | 30 +++++++++++++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 5e46f6732781..a2fb333290dc 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -103,6 +103,7 @@ enum bpf_cmd {
 	BPF_BTF_LOAD,
 	BPF_BTF_GET_FD_BY_ID,
 	BPF_TASK_FD_QUERY,
+	BPF_MAP_LOOKUP_AND_DELETE_ELEM,
 };
 
 enum bpf_map_type {
@@ -128,6 +129,8 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_CGROUP_STORAGE,
 	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
 	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+	BPF_MAP_TYPE_QUEUE,
+	BPF_MAP_TYPE_STACK,
 };
 
 enum bpf_prog_type {
@@ -462,6 +465,28 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
+ * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
+ * 	Description
+ * 		Push an element *value* in *map*. *flags* is one of:
+ *
+ * 		**BPF_EXIST**
+ * 		If the queue/stack is full, the oldest element is removed to
+ * 		make room for this.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_pop_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Pop an element from *map*.
+ * Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_peek_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Get an element from *map* without removing it.
+ * Return
+ * 		0 on success, or a negative error in case of failure.
+ *
  * int bpf_probe_read(void *dst, u32 size, const void *src)
  * 	Description
  * 		For tracing programs, safely attempt to read *size* bytes from
@@ -2303,7 +2328,10 @@ union bpf_attr {
 	FN(skb_ancestor_cgroup_id),	\
 	FN(sk_lookup_tcp),		\
 	FN(sk_lookup_udp),		\
-	FN(sk_release),
+	FN(sk_release),			\
+	FN(map_push_elem),		\
+	FN(map_pop_elem),		\
+	FN(map_peek_elem),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
-- 
cgit v1.2.3


From 43b987d23d6bd08db41a9c4a85aacfb3f0b2a94c Mon Sep 17 00:00:00 2001
From: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Date: Thu, 18 Oct 2018 15:16:41 +0200
Subject: selftests/bpf: add test cases for queue and stack maps

test_maps:
Tests that queue/stack maps are behaving correctly even in corner cases

test_progs:
Tests new ebpf helpers

Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/bpf.c                                |  12 ++
 tools/lib/bpf/bpf.h                                |   2 +
 tools/testing/selftests/bpf/Makefile               |   5 +-
 tools/testing/selftests/bpf/bpf_helpers.h          |   7 ++
 tools/testing/selftests/bpf/test_maps.c            | 122 +++++++++++++++++++++
 tools/testing/selftests/bpf/test_progs.c           |  99 +++++++++++++++++
 tools/testing/selftests/bpf/test_queue_map.c       |   4 +
 tools/testing/selftests/bpf/test_queue_stack_map.h |  59 ++++++++++
 tools/testing/selftests/bpf/test_stack_map.c       |   4 +
 9 files changed, 313 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/test_queue_map.c
 create mode 100644 tools/testing/selftests/bpf/test_queue_stack_map.h
 create mode 100644 tools/testing/selftests/bpf/test_stack_map.c

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index d70a255cb05e..03f9bcc4ef50 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -278,6 +278,18 @@ int bpf_map_lookup_elem(int fd, const void *key, void *value)
 	return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
 }
 
+int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.map_fd = fd;
+	attr.key = ptr_to_u64(key);
+	attr.value = ptr_to_u64(value);
+
+	return sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
+}
+
 int bpf_map_delete_elem(int fd, const void *key)
 {
 	union bpf_attr attr;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 258c3c178333..26a51538213c 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -99,6 +99,8 @@ LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value,
 				   __u64 flags);
 
 LIBBPF_API int bpf_map_lookup_elem(int fd, const void *key, void *value);
+LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
+					      void *value);
 LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
 LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
 LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index d99dd6fc3fbe..e39dfb4e7970 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -37,7 +37,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
 	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
 	test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o \
-	test_sk_lookup_kern.o test_xdp_vlan.o
+	test_sk_lookup_kern.o test_xdp_vlan.o test_queue_map.o test_stack_map.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
@@ -118,6 +118,9 @@ CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \
 $(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline
 $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
 
+$(OUTPUT)/test_queue_map.o: test_queue_stack_map.h
+$(OUTPUT)/test_stack_map.o: test_queue_stack_map.h
+
 BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
 BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
 BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index fda8c162d0df..6407a3df0f3b 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -16,6 +16,13 @@ static int (*bpf_map_update_elem)(void *map, void *key, void *value,
 	(void *) BPF_FUNC_map_update_elem;
 static int (*bpf_map_delete_elem)(void *map, void *key) =
 	(void *) BPF_FUNC_map_delete_elem;
+static int (*bpf_map_push_elem)(void *map, void *value,
+				unsigned long long flags) =
+	(void *) BPF_FUNC_map_push_elem;
+static int (*bpf_map_pop_elem)(void *map, void *value) =
+	(void *) BPF_FUNC_map_pop_elem;
+static int (*bpf_map_peek_elem)(void *map, void *value) =
+	(void *) BPF_FUNC_map_peek_elem;
 static int (*bpf_probe_read)(void *dst, int size, void *unsafe_ptr) =
 	(void *) BPF_FUNC_probe_read;
 static unsigned long long (*bpf_ktime_get_ns)(void) =
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 9b552c0fc47d..4db2116e52be 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -15,6 +15,7 @@
 #include <string.h>
 #include <assert.h>
 #include <stdlib.h>
+#include <time.h>
 
 #include <sys/wait.h>
 #include <sys/socket.h>
@@ -471,6 +472,122 @@ static void test_devmap(int task, void *data)
 	close(fd);
 }
 
+static void test_queuemap(int task, void *data)
+{
+	const int MAP_SIZE = 32;
+	__u32 vals[MAP_SIZE + MAP_SIZE/2], val;
+	int fd, i;
+
+	/* Fill test values to be used */
+	for (i = 0; i < MAP_SIZE + MAP_SIZE/2; i++)
+		vals[i] = rand();
+
+	/* Invalid key size */
+	fd = bpf_create_map(BPF_MAP_TYPE_QUEUE, 4, sizeof(val), MAP_SIZE,
+			    map_flags);
+	assert(fd < 0 && errno == EINVAL);
+
+	fd = bpf_create_map(BPF_MAP_TYPE_QUEUE, 0, sizeof(val), MAP_SIZE,
+			    map_flags);
+	/* Queue map does not support BPF_F_NO_PREALLOC */
+	if (map_flags & BPF_F_NO_PREALLOC) {
+		assert(fd < 0 && errno == EINVAL);
+		return;
+	}
+	if (fd < 0) {
+		printf("Failed to create queuemap '%s'!\n", strerror(errno));
+		exit(1);
+	}
+
+	/* Push MAP_SIZE elements */
+	for (i = 0; i < MAP_SIZE; i++)
+		assert(bpf_map_update_elem(fd, NULL, &vals[i], 0) == 0);
+
+	/* Check that element cannot be pushed due to max_entries limit */
+	assert(bpf_map_update_elem(fd, NULL, &val, 0) == -1 &&
+	       errno == E2BIG);
+
+	/* Peek element */
+	assert(bpf_map_lookup_elem(fd, NULL, &val) == 0 && val == vals[0]);
+
+	/* Replace half elements */
+	for (i = MAP_SIZE; i < MAP_SIZE + MAP_SIZE/2; i++)
+		assert(bpf_map_update_elem(fd, NULL, &vals[i], BPF_EXIST) == 0);
+
+	/* Pop all elements */
+	for (i = MAP_SIZE/2; i < MAP_SIZE + MAP_SIZE/2; i++)
+		assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == 0 &&
+		       val == vals[i]);
+
+	/* Check that there are not elements left */
+	assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == -1 &&
+	       errno == ENOENT);
+
+	/* Check that non supported functions set errno to EINVAL */
+	assert(bpf_map_delete_elem(fd, NULL) == -1 && errno == EINVAL);
+	assert(bpf_map_get_next_key(fd, NULL, NULL) == -1 && errno == EINVAL);
+
+	close(fd);
+}
+
+static void test_stackmap(int task, void *data)
+{
+	const int MAP_SIZE = 32;
+	__u32 vals[MAP_SIZE + MAP_SIZE/2], val;
+	int fd, i;
+
+	/* Fill test values to be used */
+	for (i = 0; i < MAP_SIZE + MAP_SIZE/2; i++)
+		vals[i] = rand();
+
+	/* Invalid key size */
+	fd = bpf_create_map(BPF_MAP_TYPE_STACK, 4, sizeof(val), MAP_SIZE,
+			    map_flags);
+	assert(fd < 0 && errno == EINVAL);
+
+	fd = bpf_create_map(BPF_MAP_TYPE_STACK, 0, sizeof(val), MAP_SIZE,
+			    map_flags);
+	/* Stack map does not support BPF_F_NO_PREALLOC */
+	if (map_flags & BPF_F_NO_PREALLOC) {
+		assert(fd < 0 && errno == EINVAL);
+		return;
+	}
+	if (fd < 0) {
+		printf("Failed to create stackmap '%s'!\n", strerror(errno));
+		exit(1);
+	}
+
+	/* Push MAP_SIZE elements */
+	for (i = 0; i < MAP_SIZE; i++)
+		assert(bpf_map_update_elem(fd, NULL, &vals[i], 0) == 0);
+
+	/* Check that element cannot be pushed due to max_entries limit */
+	assert(bpf_map_update_elem(fd, NULL, &val, 0) == -1 &&
+	       errno == E2BIG);
+
+	/* Peek element */
+	assert(bpf_map_lookup_elem(fd, NULL, &val) == 0 && val == vals[i - 1]);
+
+	/* Replace half elements */
+	for (i = MAP_SIZE; i < MAP_SIZE + MAP_SIZE/2; i++)
+		assert(bpf_map_update_elem(fd, NULL, &vals[i], BPF_EXIST) == 0);
+
+	/* Pop all elements */
+	for (i = MAP_SIZE + MAP_SIZE/2 - 1; i >= MAP_SIZE/2; i--)
+		assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == 0 &&
+		       val == vals[i]);
+
+	/* Check that there are not elements left */
+	assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == -1 &&
+	       errno == ENOENT);
+
+	/* Check that non supported functions set errno to EINVAL */
+	assert(bpf_map_delete_elem(fd, NULL) == -1 && errno == EINVAL);
+	assert(bpf_map_get_next_key(fd, NULL, NULL) == -1 && errno == EINVAL);
+
+	close(fd);
+}
+
 #include <sys/socket.h>
 #include <sys/ioctl.h>
 #include <arpa/inet.h>
@@ -1434,10 +1551,15 @@ static void run_all_tests(void)
 	test_map_wronly();
 
 	test_reuseport_array();
+
+	test_queuemap(0, NULL);
+	test_stackmap(0, NULL);
 }
 
 int main(void)
 {
+	srand(time(NULL));
+
 	map_flags = 0;
 	run_all_tests();
 
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index e8becca9c521..2d3c04f45530 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1735,8 +1735,105 @@ static void test_reference_tracking()
 	bpf_object__close(obj);
 }
 
+enum {
+	QUEUE,
+	STACK,
+};
+
+static void test_queue_stack_map(int type)
+{
+	const int MAP_SIZE = 32;
+	__u32 vals[MAP_SIZE], duration, retval, size, val;
+	int i, err, prog_fd, map_in_fd, map_out_fd;
+	char file[32], buf[128];
+	struct bpf_object *obj;
+	struct iphdr *iph = (void *)buf + sizeof(struct ethhdr);
+
+	/* Fill test values to be used */
+	for (i = 0; i < MAP_SIZE; i++)
+		vals[i] = rand();
+
+	if (type == QUEUE)
+		strncpy(file, "./test_queue_map.o", sizeof(file));
+	else if (type == STACK)
+		strncpy(file, "./test_stack_map.o", sizeof(file));
+	else
+		return;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
+	if (err) {
+		error_cnt++;
+		return;
+	}
+
+	map_in_fd = bpf_find_map(__func__, obj, "map_in");
+	if (map_in_fd < 0)
+		goto out;
+
+	map_out_fd = bpf_find_map(__func__, obj, "map_out");
+	if (map_out_fd < 0)
+		goto out;
+
+	/* Push 32 elements to the input map */
+	for (i = 0; i < MAP_SIZE; i++) {
+		err = bpf_map_update_elem(map_in_fd, NULL, &vals[i], 0);
+		if (err) {
+			error_cnt++;
+			goto out;
+		}
+	}
+
+	/* The eBPF program pushes iph.saddr in the output map,
+	 * pops the input map and saves this value in iph.daddr
+	 */
+	for (i = 0; i < MAP_SIZE; i++) {
+		if (type == QUEUE) {
+			val = vals[i];
+			pkt_v4.iph.saddr = vals[i] * 5;
+		} else if (type == STACK) {
+			val = vals[MAP_SIZE - 1 - i];
+			pkt_v4.iph.saddr = vals[MAP_SIZE - 1 - i] * 5;
+		}
+
+		err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+					buf, &size, &retval, &duration);
+		if (err || retval || size != sizeof(pkt_v4) ||
+		    iph->daddr != val)
+			break;
+	}
+
+	CHECK(err || retval || size != sizeof(pkt_v4) || iph->daddr != val,
+	      "bpf_map_pop_elem",
+	      "err %d errno %d retval %d size %d iph->daddr %u\n",
+	      err, errno, retval, size, iph->daddr);
+
+	/* Queue is empty, program should return TC_ACT_SHOT */
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				buf, &size, &retval, &duration);
+	CHECK(err || retval != 2 /* TC_ACT_SHOT */|| size != sizeof(pkt_v4),
+	      "check-queue-stack-map-empty",
+	      "err %d errno %d retval %d size %d\n",
+	      err, errno, retval, size);
+
+	/* Check that the program pushed elements correctly */
+	for (i = 0; i < MAP_SIZE; i++) {
+		err = bpf_map_lookup_and_delete_elem(map_out_fd, NULL, &val);
+		if (err || val != vals[i] * 5)
+			break;
+	}
+
+	CHECK(i != MAP_SIZE && (err || val != vals[i] * 5),
+	      "bpf_map_push_elem", "err %d value %u\n", err, val);
+
+out:
+	pkt_v4.iph.saddr = 0;
+	bpf_object__close(obj);
+}
+
 int main(void)
 {
+	srand(time(NULL));
+
 	jit_enabled = is_jit_enabled();
 
 	test_pkt_access();
@@ -1757,6 +1854,8 @@ int main(void)
 	test_task_fd_query_rawtp();
 	test_task_fd_query_tp();
 	test_reference_tracking();
+	test_queue_stack_map(QUEUE);
+	test_queue_stack_map(STACK);
 
 	printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
 	return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
diff --git a/tools/testing/selftests/bpf/test_queue_map.c b/tools/testing/selftests/bpf/test_queue_map.c
new file mode 100644
index 000000000000..87db1f9da33d
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_queue_map.c
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Politecnico di Torino
+#define MAP_TYPE BPF_MAP_TYPE_QUEUE
+#include "test_queue_stack_map.h"
diff --git a/tools/testing/selftests/bpf/test_queue_stack_map.h b/tools/testing/selftests/bpf/test_queue_stack_map.h
new file mode 100644
index 000000000000..295b9b3bc5c7
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_queue_stack_map.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (c) 2018 Politecnico di Torino
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/pkt_cls.h>
+#include "bpf_helpers.h"
+
+int _version SEC("version") = 1;
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) map_in = {
+	.type = MAP_TYPE,
+	.key_size = 0,
+	.value_size = sizeof(__u32),
+	.max_entries = 32,
+	.map_flags = 0,
+};
+
+struct bpf_map_def __attribute__ ((section("maps"), used)) map_out = {
+	.type = MAP_TYPE,
+	.key_size = 0,
+	.value_size = sizeof(__u32),
+	.max_entries = 32,
+	.map_flags = 0,
+};
+
+SEC("test")
+int _test(struct __sk_buff *skb)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	struct ethhdr *eth = (struct ethhdr *)(data);
+	__u32 value;
+	int err;
+
+	if (eth + 1 > data_end)
+		return TC_ACT_SHOT;
+
+	struct iphdr *iph = (struct iphdr *)(eth + 1);
+
+	if (iph + 1 > data_end)
+		return TC_ACT_SHOT;
+
+	err = bpf_map_pop_elem(&map_in, &value);
+	if (err)
+		return TC_ACT_SHOT;
+
+	iph->daddr = value;
+
+	err = bpf_map_push_elem(&map_out, &iph->saddr, 0);
+	if (err)
+		return TC_ACT_SHOT;
+
+	return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_stack_map.c b/tools/testing/selftests/bpf/test_stack_map.c
new file mode 100644
index 000000000000..31c3880e6da0
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_stack_map.c
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Politecnico di Torino
+#define MAP_TYPE BPF_MAP_TYPE_STACK
+#include "test_queue_stack_map.h"
-- 
cgit v1.2.3


From 78de35460a5cc206d42a239cb215c966a83ac283 Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Fri, 19 Oct 2018 16:24:36 +0200
Subject: selftests/bpf: add missing executables to .gitignore

Fixes: 371e4fcc9d96 ("selftests/bpf: cgroup local storage-based network counters")
Fixes: 370920c47b26 ("selftests/bpf: Test libbpf_{prog,attach}_type_by_name")
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/.gitignore | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 8a60c9b9892d..1b799e30c06d 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -25,3 +25,5 @@ test_cgroup_storage
 test_select_reuseport
 test_flow_dissector
 flow_dissector_load
+test_netcnt
+test_section_names
-- 
cgit v1.2.3


From 09d62154f61316f7e97eae3f31ef8770c7e4b386 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 19 Oct 2018 15:51:02 +0200
Subject: tools, perf: add and use optimized ring_buffer_{read_head,
 write_tail} helpers

Currently, on x86-64, perf uses LFENCE and MFENCE (rmb() and mb(),
respectively) when processing events from the perf ring buffer which
is unnecessarily expensive as we can do more lightweight in particular
given this is critical fast-path in perf.

According to Peter rmb()/mb() were added back then via a94d342b9cb0
("tools/perf: Add required memory barriers") at a time where kernel
still supported chips that needed it, but nowadays support for these
has been ditched completely, therefore we can fix them up as well.

While for x86-64, replacing rmb() and mb() with smp_*() variants would
result in just a compiler barrier for the former and LOCK + ADD for
the latter (__sync_synchronize() uses slower MFENCE by the way), Peter
suggested we can use smp_{load_acquire,store_release}() instead for
architectures where its implementation doesn't resolve in slower smp_mb().
Thus, e.g. in x86-64 we would be able to avoid CPU barrier entirely due
to TSO. For architectures where the latter needs to use smp_mb() e.g.
on arm, we stick to cheaper smp_rmb() variant for fetching the head.

This work adds helpers ring_buffer_read_head() and ring_buffer_write_tail()
for tools infrastructure that either switches to smp_load_acquire() for
architectures where it is cheaper or uses READ_ONCE() + smp_rmb() barrier
for those where it's not in order to fetch the data_head from the perf
control page, and it uses smp_store_release() to write the data_tail.
Latter is smp_mb() + WRITE_ONCE() combination or a cheaper variant if
architecture allows for it. Those that rely on smp_rmb() and smp_mb() can
further improve performance in a follow up step by implementing the two
under tools/arch/*/include/asm/barrier.h such that they don't have to
fallback to rmb() and mb() in tools/include/asm/barrier.h.

Switch perf to use ring_buffer_read_head() and ring_buffer_write_tail()
so it can make use of the optimizations. Later, we convert libbpf as
well to use the same helpers.

Side note [0]: the topic has been raised of whether one could simply use
the C11 gcc builtins [1] for the smp_load_acquire() and smp_store_release()
instead:

  __atomic_load_n(ptr, __ATOMIC_ACQUIRE);
  __atomic_store_n(ptr, val, __ATOMIC_RELEASE);

Kernel and (presumably) tooling shipped along with the kernel has a
minimum requirement of being able to build with gcc-4.6 and the latter
does not have C11 builtins. While generally the C11 memory models don't
align with the kernel's, the C11 load-acquire and store-release alone
/could/ suffice, however. Issue is that this is implementation dependent
on how the load-acquire and store-release is done by the compiler and
the mapping of supported compilers must align to be compatible with the
kernel's implementation, and thus needs to be verified/tracked on a
case by case basis whether they match (unless an architecture uses them
also from kernel side). The implementations for smp_load_acquire() and
smp_store_release() in this patch have been adapted from the kernel side
ones to have a concrete and compatible mapping in place.

  [0] http://patchwork.ozlabs.org/patch/985422/
  [1] https://gcc.gnu.org/onlinedocs/gcc/_005f_005fatomic-Builtins.html

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/arch/arm64/include/asm/barrier.h    | 70 +++++++++++++++++++++++++++++
 tools/arch/ia64/include/asm/barrier.h     | 13 ++++++
 tools/arch/powerpc/include/asm/barrier.h  | 16 +++++++
 tools/arch/s390/include/asm/barrier.h     | 13 ++++++
 tools/arch/sparc/include/asm/barrier_64.h | 13 ++++++
 tools/arch/x86/include/asm/barrier.h      | 14 ++++++
 tools/include/asm/barrier.h               | 35 +++++++++++++++
 tools/include/linux/ring_buffer.h         | 73 +++++++++++++++++++++++++++++++
 tools/perf/util/mmap.h                    | 15 ++-----
 9 files changed, 250 insertions(+), 12 deletions(-)
 create mode 100644 tools/include/linux/ring_buffer.h

(limited to 'tools')

diff --git a/tools/arch/arm64/include/asm/barrier.h b/tools/arch/arm64/include/asm/barrier.h
index 40bde6b23501..12835ea0e417 100644
--- a/tools/arch/arm64/include/asm/barrier.h
+++ b/tools/arch/arm64/include/asm/barrier.h
@@ -14,4 +14,74 @@
 #define wmb()		asm volatile("dmb ishst" ::: "memory")
 #define rmb()		asm volatile("dmb ishld" ::: "memory")
 
+#define smp_store_release(p, v)					\
+do {								\
+	union { typeof(*p) __val; char __c[1]; } __u =		\
+		{ .__val = (__force typeof(*p)) (v) }; 		\
+								\
+	switch (sizeof(*p)) {					\
+	case 1:							\
+		asm volatile ("stlrb %w1, %0"			\
+				: "=Q" (*p)			\
+				: "r" (*(__u8 *)__u.__c)	\
+				: "memory");			\
+		break;						\
+	case 2:							\
+		asm volatile ("stlrh %w1, %0"			\
+				: "=Q" (*p)			\
+				: "r" (*(__u16 *)__u.__c)	\
+				: "memory");			\
+		break;						\
+	case 4:							\
+		asm volatile ("stlr %w1, %0"			\
+				: "=Q" (*p)			\
+				: "r" (*(__u32 *)__u.__c)	\
+				: "memory");			\
+		break;						\
+	case 8:							\
+		asm volatile ("stlr %1, %0"			\
+				: "=Q" (*p)			\
+				: "r" (*(__u64 *)__u.__c)	\
+				: "memory");			\
+		break;						\
+	default:						\
+		/* Only to shut up gcc ... */			\
+		mb();						\
+		break;						\
+	}							\
+} while (0)
+
+#define smp_load_acquire(p)					\
+({								\
+	union { typeof(*p) __val; char __c[1]; } __u;		\
+								\
+	switch (sizeof(*p)) {					\
+	case 1:							\
+		asm volatile ("ldarb %w0, %1"			\
+			: "=r" (*(__u8 *)__u.__c)		\
+			: "Q" (*p) : "memory");			\
+		break;						\
+	case 2:							\
+		asm volatile ("ldarh %w0, %1"			\
+			: "=r" (*(__u16 *)__u.__c)		\
+			: "Q" (*p) : "memory");			\
+		break;						\
+	case 4:							\
+		asm volatile ("ldar %w0, %1"			\
+			: "=r" (*(__u32 *)__u.__c)		\
+			: "Q" (*p) : "memory");			\
+		break;						\
+	case 8:							\
+		asm volatile ("ldar %0, %1"			\
+			: "=r" (*(__u64 *)__u.__c)		\
+			: "Q" (*p) : "memory");			\
+		break;						\
+	default:						\
+		/* Only to shut up gcc ... */			\
+		mb();						\
+		break;						\
+	}							\
+	__u.__val;						\
+})
+
 #endif /* _TOOLS_LINUX_ASM_AARCH64_BARRIER_H */
diff --git a/tools/arch/ia64/include/asm/barrier.h b/tools/arch/ia64/include/asm/barrier.h
index d808ee0e77b5..4d471d9511a5 100644
--- a/tools/arch/ia64/include/asm/barrier.h
+++ b/tools/arch/ia64/include/asm/barrier.h
@@ -46,4 +46,17 @@
 #define rmb()		mb()
 #define wmb()		mb()
 
+#define smp_store_release(p, v)			\
+do {						\
+	barrier();				\
+	WRITE_ONCE(*p, v);			\
+} while (0)
+
+#define smp_load_acquire(p)			\
+({						\
+	typeof(*p) ___p1 = READ_ONCE(*p);	\
+	barrier();				\
+	___p1;					\
+})
+
 #endif /* _TOOLS_LINUX_ASM_IA64_BARRIER_H */
diff --git a/tools/arch/powerpc/include/asm/barrier.h b/tools/arch/powerpc/include/asm/barrier.h
index a634da05bc97..905a2c66d96d 100644
--- a/tools/arch/powerpc/include/asm/barrier.h
+++ b/tools/arch/powerpc/include/asm/barrier.h
@@ -27,4 +27,20 @@
 #define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
 #define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
 
+#if defined(__powerpc64__)
+#define smp_lwsync()	__asm__ __volatile__ ("lwsync" : : : "memory")
+
+#define smp_store_release(p, v)			\
+do {						\
+	smp_lwsync();				\
+	WRITE_ONCE(*p, v);			\
+} while (0)
+
+#define smp_load_acquire(p)			\
+({						\
+	typeof(*p) ___p1 = READ_ONCE(*p);	\
+	smp_lwsync();				\
+	___p1;					\
+})
+#endif /* defined(__powerpc64__) */
 #endif /* _TOOLS_LINUX_ASM_POWERPC_BARRIER_H */
diff --git a/tools/arch/s390/include/asm/barrier.h b/tools/arch/s390/include/asm/barrier.h
index 5030c99f47d2..de362fa664d4 100644
--- a/tools/arch/s390/include/asm/barrier.h
+++ b/tools/arch/s390/include/asm/barrier.h
@@ -28,4 +28,17 @@
 #define rmb()				mb()
 #define wmb()				mb()
 
+#define smp_store_release(p, v)			\
+do {						\
+	barrier();				\
+	WRITE_ONCE(*p, v);			\
+} while (0)
+
+#define smp_load_acquire(p)			\
+({						\
+	typeof(*p) ___p1 = READ_ONCE(*p);	\
+	barrier();				\
+	___p1;					\
+})
+
 #endif /* __TOOLS_LIB_ASM_BARRIER_H */
diff --git a/tools/arch/sparc/include/asm/barrier_64.h b/tools/arch/sparc/include/asm/barrier_64.h
index ba61344287d5..cfb0fdc8ccf0 100644
--- a/tools/arch/sparc/include/asm/barrier_64.h
+++ b/tools/arch/sparc/include/asm/barrier_64.h
@@ -40,4 +40,17 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
 #define rmb()	__asm__ __volatile__("":::"memory")
 #define wmb()	__asm__ __volatile__("":::"memory")
 
+#define smp_store_release(p, v)			\
+do {						\
+	barrier();				\
+	WRITE_ONCE(*p, v);			\
+} while (0)
+
+#define smp_load_acquire(p)			\
+({						\
+	typeof(*p) ___p1 = READ_ONCE(*p);	\
+	barrier();				\
+	___p1;					\
+})
+
 #endif /* !(__TOOLS_LINUX_SPARC64_BARRIER_H) */
diff --git a/tools/arch/x86/include/asm/barrier.h b/tools/arch/x86/include/asm/barrier.h
index 8774dee27471..58919868473c 100644
--- a/tools/arch/x86/include/asm/barrier.h
+++ b/tools/arch/x86/include/asm/barrier.h
@@ -26,4 +26,18 @@
 #define wmb()	asm volatile("sfence" ::: "memory")
 #endif
 
+#if defined(__x86_64__)
+#define smp_store_release(p, v)			\
+do {						\
+	barrier();				\
+	WRITE_ONCE(*p, v);			\
+} while (0)
+
+#define smp_load_acquire(p)			\
+({						\
+	typeof(*p) ___p1 = READ_ONCE(*p);	\
+	barrier();				\
+	___p1;					\
+})
+#endif /* defined(__x86_64__) */
 #endif /* _TOOLS_LINUX_ASM_X86_BARRIER_H */
diff --git a/tools/include/asm/barrier.h b/tools/include/asm/barrier.h
index 391d942536e5..8d378c57cb01 100644
--- a/tools/include/asm/barrier.h
+++ b/tools/include/asm/barrier.h
@@ -1,4 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/compiler.h>
 #if defined(__i386__) || defined(__x86_64__)
 #include "../../arch/x86/include/asm/barrier.h"
 #elif defined(__arm__)
@@ -26,3 +27,37 @@
 #else
 #include <asm-generic/barrier.h>
 #endif
+
+/*
+ * Generic fallback smp_*() definitions for archs that haven't
+ * been updated yet.
+ */
+
+#ifndef smp_rmb
+# define smp_rmb()	rmb()
+#endif
+
+#ifndef smp_wmb
+# define smp_wmb()	wmb()
+#endif
+
+#ifndef smp_mb
+# define smp_mb()	mb()
+#endif
+
+#ifndef smp_store_release
+# define smp_store_release(p, v)		\
+do {						\
+	smp_mb();				\
+	WRITE_ONCE(*p, v);			\
+} while (0)
+#endif
+
+#ifndef smp_load_acquire
+# define smp_load_acquire(p)			\
+({						\
+	typeof(*p) ___p1 = READ_ONCE(*p);	\
+	smp_mb();				\
+	___p1;					\
+})
+#endif
diff --git a/tools/include/linux/ring_buffer.h b/tools/include/linux/ring_buffer.h
new file mode 100644
index 000000000000..9a083ae60473
--- /dev/null
+++ b/tools/include/linux/ring_buffer.h
@@ -0,0 +1,73 @@
+#ifndef _TOOLS_LINUX_RING_BUFFER_H_
+#define _TOOLS_LINUX_RING_BUFFER_H_
+
+#include <asm/barrier.h>
+
+/*
+ * Contract with kernel for walking the perf ring buffer from
+ * user space requires the following barrier pairing (quote
+ * from kernel/events/ring_buffer.c):
+ *
+ *   Since the mmap() consumer (userspace) can run on a
+ *   different CPU:
+ *
+ *   kernel                             user
+ *
+ *   if (LOAD ->data_tail) {            LOAD ->data_head
+ *                      (A)             smp_rmb()       (C)
+ *      STORE $data                     LOAD $data
+ *      smp_wmb()       (B)             smp_mb()        (D)
+ *      STORE ->data_head               STORE ->data_tail
+ *   }
+ *
+ *   Where A pairs with D, and B pairs with C.
+ *
+ *   In our case A is a control dependency that separates the
+ *   load of the ->data_tail and the stores of $data. In case
+ *   ->data_tail indicates there is no room in the buffer to
+ *   store $data we do not.
+ *
+ *   D needs to be a full barrier since it separates the data
+ *   READ from the tail WRITE.
+ *
+ *   For B a WMB is sufficient since it separates two WRITEs,
+ *   and for C an RMB is sufficient since it separates two READs.
+ *
+ * Note, instead of B, C, D we could also use smp_store_release()
+ * in B and D as well as smp_load_acquire() in C.
+ *
+ * However, this optimization does not make sense for all kernel
+ * supported architectures since for a fair number it would
+ * resolve into READ_ONCE() + smp_mb() pair for smp_load_acquire(),
+ * and smp_mb() + WRITE_ONCE() pair for smp_store_release().
+ *
+ * Thus for those smp_wmb() in B and smp_rmb() in C would still
+ * be less expensive. For the case of D this has either the same
+ * cost or is less expensive, for example, due to TSO x86 can
+ * avoid the CPU barrier entirely.
+ */
+
+static inline u64 ring_buffer_read_head(struct perf_event_mmap_page *base)
+{
+/*
+ * Architectures where smp_load_acquire() does not fallback to
+ * READ_ONCE() + smp_mb() pair.
+ */
+#if defined(__x86_64__) || defined(__aarch64__) || defined(__powerpc64__) || \
+    defined(__ia64__) || defined(__sparc__) && defined(__arch64__)
+	return smp_load_acquire(&base->data_head);
+#else
+	u64 head = READ_ONCE(base->data_head);
+
+	smp_rmb();
+	return head;
+#endif
+}
+
+static inline void ring_buffer_write_tail(struct perf_event_mmap_page *base,
+					  u64 tail)
+{
+	smp_store_release(&base->data_tail, tail);
+}
+
+#endif /* _TOOLS_LINUX_RING_BUFFER_H_ */
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 05a6d47c7956..8f6531fd4dad 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -4,7 +4,7 @@
 #include <linux/compiler.h>
 #include <linux/refcount.h>
 #include <linux/types.h>
-#include <asm/barrier.h>
+#include <linux/ring_buffer.h>
 #include <stdbool.h>
 #include "auxtrace.h"
 #include "event.h"
@@ -71,21 +71,12 @@ void perf_mmap__consume(struct perf_mmap *map);
 
 static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
 {
-	struct perf_event_mmap_page *pc = mm->base;
-	u64 head = READ_ONCE(pc->data_head);
-	rmb();
-	return head;
+	return ring_buffer_read_head(mm->base);
 }
 
 static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
 {
-	struct perf_event_mmap_page *pc = md->base;
-
-	/*
-	 * ensure all reads are done before we write the tail out.
-	 */
-	mb();
-	pc->data_tail = tail;
+	ring_buffer_write_tail(md->base, tail);
 }
 
 union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
-- 
cgit v1.2.3


From a64af0ef1c1dbd1e8be65a6ebbf5950305b27e48 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 19 Oct 2018 15:51:03 +0200
Subject: bpf, libbpf: use correct barriers in perf ring buffer walk

Given libbpf is a generic library and not restricted to x86-64 only,
the compiler barrier in bpf_perf_event_read_simple() after fetching
the head needs to be replaced with smp_rmb() at minimum. Also, writing
out the tail we should use WRITE_ONCE() to avoid store tearing.

Now that we have the logic in place in ring_buffer_read_head() and
ring_buffer_write_tail() helper also used by perf tool which would
select the correct and best variant for a given architecture (e.g.
x86-64 can avoid CPU barriers entirely), make use of these in order
to fix bpf_perf_event_read_simple().

Fixes: d0cabbb021be ("tools: bpf: move the event reading loop to libbpf")
Fixes: 39111695b1b8 ("samples: bpf: add bpf_perf_event_output example")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index bd71efcc53be..0c21355f04a7 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -27,6 +27,7 @@
 #include <linux/list.h>
 #include <linux/limits.h>
 #include <linux/perf_event.h>
+#include <linux/ring_buffer.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/vfs.h>
@@ -2418,13 +2419,12 @@ bpf_perf_event_read_simple(void *mem, unsigned long size,
 			   unsigned long page_size, void **buf, size_t *buf_len,
 			   bpf_perf_event_print_t fn, void *priv)
 {
-	volatile struct perf_event_mmap_page *header = mem;
+	struct perf_event_mmap_page *header = mem;
+	__u64 data_head = ring_buffer_read_head(header);
 	__u64 data_tail = header->data_tail;
-	__u64 data_head = header->data_head;
 	int ret = LIBBPF_PERF_EVENT_ERROR;
 	void *base, *begin, *end;
 
-	asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */
 	if (data_head == data_tail)
 		return LIBBPF_PERF_EVENT_CONT;
 
@@ -2467,8 +2467,6 @@ bpf_perf_event_read_simple(void *mem, unsigned long size,
 		data_tail += ehdr->size;
 	}
 
-	__sync_synchronize(); /* smp_mb() */
-	header->data_tail = data_tail;
-
+	ring_buffer_write_tail(header, data_tail);
 	return ret;
 }
-- 
cgit v1.2.3


From 2cb494a36c98279c5c6ce8e99cf9776f15449ade Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Fri, 19 Oct 2018 09:57:58 -0700
Subject: bpf: add tests for direct packet access from CGROUP_SKB

Tests are added to make sure CGROUP_SKB cannot access:
  tc_classid, data_meta, flow_keys

and can read and write:
  mark, prority, and cb[0-4]

and can read other fields.

To make selftest with skb->sk work, a dummy sk is added in
bpf_prog_test_run_skb().

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/bpf/test_run.c                          |  15 +++
 tools/testing/selftests/bpf/test_verifier.c | 171 ++++++++++++++++++++++++++++
 2 files changed, 186 insertions(+)

(limited to 'tools')

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 0c423b8cd75c..c89c22c49015 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -10,6 +10,8 @@
 #include <linux/etherdevice.h>
 #include <linux/filter.h>
 #include <linux/sched/signal.h>
+#include <net/sock.h>
+#include <net/tcp.h>
 
 static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx,
 		struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE])
@@ -115,6 +117,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	u32 retval, duration;
 	int hh_len = ETH_HLEN;
 	struct sk_buff *skb;
+	struct sock *sk;
 	void *data;
 	int ret;
 
@@ -137,11 +140,21 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 		break;
 	}
 
+	sk = kzalloc(sizeof(struct sock), GFP_USER);
+	if (!sk) {
+		kfree(data);
+		return -ENOMEM;
+	}
+	sock_net_set(sk, current->nsproxy->net_ns);
+	sock_init_data(NULL, sk);
+
 	skb = build_skb(data, 0);
 	if (!skb) {
 		kfree(data);
+		kfree(sk);
 		return -ENOMEM;
 	}
+	skb->sk = sk;
 
 	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
 	__skb_put(skb, size);
@@ -159,6 +172,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 
 			if (pskb_expand_head(skb, nhead, 0, GFP_USER)) {
 				kfree_skb(skb);
+				kfree(sk);
 				return -ENOMEM;
 			}
 		}
@@ -171,6 +185,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 		size = skb_headlen(skb);
 	ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration);
 	kfree_skb(skb);
+	kfree(sk);
 	return ret;
 }
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index cf4cd32b6772..f1ae8d09770f 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -4862,6 +4862,177 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
+	{
+		"direct packet read test#1 for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct __sk_buff, len)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, pkt_type)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff, queue_mapping)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+				    offsetof(struct __sk_buff, protocol)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
+				    offsetof(struct __sk_buff, vlan_present)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"direct packet read test#2 for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct __sk_buff, vlan_tci)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, vlan_proto)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, priority)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				    offsetof(struct __sk_buff, priority)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff,
+					     ingress_ifindex)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+				    offsetof(struct __sk_buff, tc_index)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
+				    offsetof(struct __sk_buff, hash)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"direct packet read test#3 for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[0])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[1])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[2])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[3])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[4])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
+				    offsetof(struct __sk_buff, napi_id)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_4,
+				    offsetof(struct __sk_buff, cb[0])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_5,
+				    offsetof(struct __sk_buff, cb[1])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				    offsetof(struct __sk_buff, cb[2])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_7,
+				    offsetof(struct __sk_buff, cb[3])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_8,
+				    offsetof(struct __sk_buff, cb[4])),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"direct packet read test#4 for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, family)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip4)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip4)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip6[0])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip6[1])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip6[2])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip6[3])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip6[0])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip6[1])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip6[2])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip6[3])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_port)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_port)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid access of tc_classid for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, tc_classid)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid bpf_context access",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid access of data_meta for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_meta)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid bpf_context access",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid access of flow_keys for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, flow_keys)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid bpf_context access",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid write access to napi_id for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
+				    offsetof(struct __sk_buff, napi_id)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_9,
+				    offsetof(struct __sk_buff, napi_id)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid bpf_context access",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
 	{
 		"valid cgroup storage access",
 		.insns = {
-- 
cgit v1.2.3


From ba0e41ca81b935b958006c7120466e2217357827 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 18 Oct 2018 22:13:02 +0900
Subject: selftests: ftrace: Add synthetic event syntax testcase

Add a testcase to check the syntax and field types for
synthetic_events interface.

Link: http://lkml.kernel.org/r/153986838264.18251.16627517536956299922.stgit@devbox

Acked-by: Shuah Khan <shuah@kernel.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 .../inter-event/trigger-synthetic-event-syntax.tc  | 80 ++++++++++++++++++++++
 1 file changed, 80 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-syntax.tc

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-syntax.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-syntax.tc
new file mode 100644
index 000000000000..88e6c3f43006
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-syntax.tc
@@ -0,0 +1,80 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: event trigger - test synthetic_events syntax parser
+
+do_reset() {
+    reset_trigger
+    echo > set_event
+    clear_trace
+}
+
+fail() { #msg
+    do_reset
+    echo $1
+    exit_fail
+}
+
+if [ ! -f set_event ]; then
+    echo "event tracing is not supported"
+    exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+    echo "synthetic event is not supported"
+    exit_unsupported
+fi
+
+reset_tracer
+do_reset
+
+echo "Test synthetic_events syntax parser"
+
+echo > synthetic_events
+
+# synthetic event must have a field
+! echo "myevent" >> synthetic_events
+echo "myevent u64 var1" >> synthetic_events
+
+# synthetic event must be found in synthetic_events
+grep "myevent[[:space:]]u64 var1" synthetic_events
+
+# it is not possible to add same name event
+! echo "myevent u64 var2" >> synthetic_events
+
+# Non-append open will cleanup all events and add new one
+echo "myevent u64 var2" > synthetic_events
+
+# multiple fields with different spaces
+echo "myevent u64 var1; u64 var2;" > synthetic_events
+grep "myevent[[:space:]]u64 var1; u64 var2" synthetic_events
+echo "myevent u64 var1 ; u64 var2 ;" > synthetic_events
+grep "myevent[[:space:]]u64 var1; u64 var2" synthetic_events
+echo "myevent u64 var1 ;u64 var2" > synthetic_events
+grep "myevent[[:space:]]u64 var1; u64 var2" synthetic_events
+
+# test field types
+echo "myevent u32 var" > synthetic_events
+echo "myevent u16 var" > synthetic_events
+echo "myevent u8 var" > synthetic_events
+echo "myevent s64 var" > synthetic_events
+echo "myevent s32 var" > synthetic_events
+echo "myevent s16 var" > synthetic_events
+echo "myevent s8 var" > synthetic_events
+
+echo "myevent char var" > synthetic_events
+echo "myevent int var" > synthetic_events
+echo "myevent long var" > synthetic_events
+echo "myevent pid_t var" > synthetic_events
+
+echo "myevent unsigned char var" > synthetic_events
+echo "myevent unsigned int var" > synthetic_events
+echo "myevent unsigned long var" > synthetic_events
+grep "myevent[[:space:]]unsigned long var" synthetic_events
+
+# test string type
+echo "myevent char var[10]" > synthetic_events
+grep "myevent[[:space:]]char\[10\] var" synthetic_events
+
+do_reset
+
+exit 0
-- 
cgit v1.2.3


From db3848515aff369404c31ef5a63699799913518f Mon Sep 17 00:00:00 2001
From: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Date: Mon, 21 May 2018 20:43:56 +0530
Subject: selftests/powerpc: Move UCONTEXT_NIA() into utils.h

... so that it can be used by others.

Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/include/utils.h                   | 8 ++++++++
 .../testing/selftests/powerpc/primitives/load_unaligned_zeropad.c | 8 --------
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h
index c58c370828b4..da1b963cdb32 100644
--- a/tools/testing/selftests/powerpc/include/utils.h
+++ b/tools/testing/selftests/powerpc/include/utils.h
@@ -80,4 +80,12 @@ do {								\
 #define PPC_FEATURE2_ARCH_3_00 0x00800000
 #endif
 
+#if defined(__powerpc64__)
+#define UCONTEXT_NIA(UC)	(UC)->uc_mcontext.gp_regs[PT_NIP]
+#elif defined(__powerpc__)
+#define UCONTEXT_NIA(UC)	(UC)->uc_mcontext.uc_regs->gregs[PT_NIP]
+#else
+#error implement UCONTEXT_NIA
+#endif
+
 #endif /* _SELFTESTS_POWERPC_UTILS_H */
diff --git a/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c b/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c
index ed3239bbfae2..ee1e9ca22f0d 100644
--- a/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c
+++ b/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c
@@ -65,14 +65,6 @@ static int unprotect_region(void)
 extern char __start___ex_table[];
 extern char __stop___ex_table[];
 
-#if defined(__powerpc64__)
-#define UCONTEXT_NIA(UC)	(UC)->uc_mcontext.gp_regs[PT_NIP]
-#elif defined(__powerpc__)
-#define UCONTEXT_NIA(UC)	(UC)->uc_mcontext.uc_regs->gregs[PT_NIP]
-#else
-#error implement UCONTEXT_NIA
-#endif
-
 struct extbl_entry {
 	int insn;
 	int fixup;
-- 
cgit v1.2.3


From d2bf793237b3aa9c4275a466eef3893eef593691 Mon Sep 17 00:00:00 2001
From: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Date: Mon, 21 May 2018 20:43:57 +0530
Subject: selftests/powerpc: Add test to verify rfi flush across a system call

This adds a test to verify proper functioning of the rfi flush
capability implemented to mitigate meltdown. The test works by
measuring the number of L1d cache misses encountered while loading
data from memory. Across a system call, since the L1d cache is flushed
when rfi_flush is enabled, the number of cache misses is expected to
be relative to the number of cachelines corresponding to the data
being loaded.

The current system setting is reflected via powerpc/rfi_flush under
debugfs (assumed to be /sys/kernel/debug/). This test verifies the
expected result with rfi_flush enabled as well as when it is disabled.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
[mpe: Add SPDX tags, clang format, skip if the debugfs is missing, use
 __u64 and SANE_USERSPACE_TYPES to avoid printf() build errors.]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/Makefile           |   3 +-
 tools/testing/selftests/powerpc/include/utils.h    |  10 ++
 tools/testing/selftests/powerpc/security/Makefile  |   9 ++
 .../testing/selftests/powerpc/security/rfi_flush.c | 132 ++++++++++++++++++
 tools/testing/selftests/powerpc/utils.c            | 152 +++++++++++++++++++++
 5 files changed, 305 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/powerpc/security/Makefile
 create mode 100644 tools/testing/selftests/powerpc/security/rfi_flush.c

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index 201b598558b9..b3ad909aefbc 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -28,7 +28,8 @@ SUB_DIRS = alignment		\
 	   tm			\
 	   vphn         \
 	   math		\
-	   ptrace
+	   ptrace	\
+	   security
 
 endif
 
diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h
index da1b963cdb32..49621822d7c3 100644
--- a/tools/testing/selftests/powerpc/include/utils.h
+++ b/tools/testing/selftests/powerpc/include/utils.h
@@ -11,6 +11,7 @@
 #include <stdint.h>
 #include <stdbool.h>
 #include <linux/auxvec.h>
+#include <linux/perf_event.h>
 #include "reg.h"
 
 /* Avoid headaches with PRI?64 - just use %ll? always */
@@ -31,6 +32,15 @@ void *get_auxv_entry(int type);
 
 int pick_online_cpu(void);
 
+int read_debugfs_file(char *debugfs_file, int *result);
+int write_debugfs_file(char *debugfs_file, int result);
+void set_dscr(unsigned long val);
+int perf_event_open_counter(unsigned int type,
+			    unsigned long config, int group_fd);
+int perf_event_enable(int fd);
+int perf_event_disable(int fd);
+int perf_event_reset(int fd);
+
 static inline bool have_hwcap(unsigned long ftr)
 {
 	return ((unsigned long)get_auxv_entry(AT_HWCAP) & ftr) == ftr;
diff --git a/tools/testing/selftests/powerpc/security/Makefile b/tools/testing/selftests/powerpc/security/Makefile
new file mode 100644
index 000000000000..44690f1bb26a
--- /dev/null
+++ b/tools/testing/selftests/powerpc/security/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0+
+
+TEST_GEN_PROGS := rfi_flush
+
+CFLAGS += -I../../../../../usr/include
+
+include ../../lib.mk
+
+$(TEST_GEN_PROGS): ../harness.c ../utils.c
diff --git a/tools/testing/selftests/powerpc/security/rfi_flush.c b/tools/testing/selftests/powerpc/security/rfi_flush.c
new file mode 100644
index 000000000000..564ed45bbf73
--- /dev/null
+++ b/tools/testing/selftests/powerpc/security/rfi_flush.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+/*
+ * Copyright 2018 IBM Corporation.
+ */
+
+#define __SANE_USERSPACE_TYPES__
+
+#include <sys/types.h>
+#include <stdint.h>
+#include <malloc.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+#include "utils.h"
+
+#define CACHELINE_SIZE 128
+
+struct perf_event_read {
+	__u64 nr;
+	__u64 l1d_misses;
+};
+
+static inline __u64 load(void *addr)
+{
+	__u64 tmp;
+
+	asm volatile("ld %0,0(%1)" : "=r"(tmp) : "b"(addr));
+
+	return tmp;
+}
+
+static void syscall_loop(char *p, unsigned long iterations,
+			 unsigned long zero_size)
+{
+	for (unsigned long i = 0; i < iterations; i++) {
+		for (unsigned long j = 0; j < zero_size; j += CACHELINE_SIZE)
+			load(p + j);
+		getppid();
+	}
+}
+
+int rfi_flush_test(void)
+{
+	char *p;
+	int repetitions = 10;
+	int fd, passes = 0, iter, rc = 0;
+	struct perf_event_read v;
+	__u64 l1d_misses_total = 0;
+	unsigned long iterations = 100000, zero_size = 24 * 1024;
+	int rfi_flush_org, rfi_flush;
+
+	SKIP_IF(geteuid() != 0);
+
+	if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_org)) {
+		perror("Unable to read powerpc/rfi_flush debugfs file");
+		SKIP_IF(1);
+	}
+
+	rfi_flush = rfi_flush_org;
+
+	fd = perf_event_open_counter(PERF_TYPE_RAW, /* L1d miss */ 0x400f0, -1);
+	FAIL_IF(fd < 0);
+
+	p = (char *)memalign(zero_size, CACHELINE_SIZE);
+
+	FAIL_IF(perf_event_enable(fd));
+
+	set_dscr(1);
+
+	iter = repetitions;
+
+again:
+	FAIL_IF(perf_event_reset(fd));
+
+	syscall_loop(p, iterations, zero_size);
+
+	FAIL_IF(read(fd, &v, sizeof(v)) != sizeof(v));
+
+	/* Expect at least zero_size/CACHELINE_SIZE misses per iteration */
+	if (v.l1d_misses >= (iterations * zero_size / CACHELINE_SIZE) && rfi_flush)
+		passes++;
+	else if (v.l1d_misses < iterations && !rfi_flush)
+		passes++;
+
+	l1d_misses_total += v.l1d_misses;
+
+	while (--iter)
+		goto again;
+
+	if (passes < repetitions) {
+		printf("FAIL (L1D misses with rfi_flush=%d: %llu %c %lu) [%d/%d failures]\n",
+		       rfi_flush, l1d_misses_total, rfi_flush ? '<' : '>',
+		       rfi_flush ? (repetitions * iterations * zero_size / CACHELINE_SIZE) : iterations,
+		       repetitions - passes, repetitions);
+		rc = 1;
+	} else
+		printf("PASS (L1D misses with rfi_flush=%d: %llu %c %lu) [%d/%d pass]\n",
+		       rfi_flush, l1d_misses_total, rfi_flush ? '>' : '<',
+		       rfi_flush ? (repetitions * iterations * zero_size / CACHELINE_SIZE) : iterations,
+		       passes, repetitions);
+
+	if (rfi_flush == rfi_flush_org) {
+		rfi_flush = !rfi_flush_org;
+		if (write_debugfs_file("powerpc/rfi_flush", rfi_flush) < 0) {
+			perror("error writing to powerpc/rfi_flush debugfs file");
+			return 1;
+		}
+		iter = repetitions;
+		l1d_misses_total = 0;
+		passes = 0;
+		goto again;
+	}
+
+	perf_event_disable(fd);
+	close(fd);
+
+	set_dscr(0);
+
+	if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_org) < 0) {
+		perror("unable to restore original value of powerpc/rfi_flush debugfs file");
+		return 1;
+	}
+
+	return rc;
+}
+
+int main(int argc, char *argv[])
+{
+	return test_harness(rfi_flush_test, "rfi_flush_test");
+}
diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c
index aa8fc1e6365b..43c342845be0 100644
--- a/tools/testing/selftests/powerpc/utils.c
+++ b/tools/testing/selftests/powerpc/utils.c
@@ -10,16 +10,22 @@
 #include <fcntl.h>
 #include <link.h>
 #include <sched.h>
+#include <signal.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <string.h>
+#include <sys/ioctl.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/utsname.h>
 #include <unistd.h>
+#include <asm/unistd.h>
+#include <linux/limits.h>
 
 #include "utils.h"
 
 static char auxv[4096];
+extern unsigned int dscr_insn[];
 
 int read_auxv(char *buf, ssize_t buf_size)
 {
@@ -121,3 +127,149 @@ bool is_ppc64le(void)
 
 	return strcmp(uts.machine, "ppc64le") == 0;
 }
+
+int read_debugfs_file(char *debugfs_file, int *result)
+{
+	int rc = -1, fd;
+	char path[PATH_MAX];
+	char value[16];
+
+	strcpy(path, "/sys/kernel/debug/");
+	strncat(path, debugfs_file, PATH_MAX - strlen(path) - 1);
+
+	if ((fd = open(path, O_RDONLY)) < 0)
+		return rc;
+
+	if ((rc = read(fd, value, sizeof(value))) < 0)
+		return rc;
+
+	value[15] = 0;
+	*result = atoi(value);
+	close(fd);
+
+	return 0;
+}
+
+int write_debugfs_file(char *debugfs_file, int result)
+{
+	int rc = -1, fd;
+	char path[PATH_MAX];
+	char value[16];
+
+	strcpy(path, "/sys/kernel/debug/");
+	strncat(path, debugfs_file, PATH_MAX - strlen(path) - 1);
+
+	if ((fd = open(path, O_WRONLY)) < 0)
+		return rc;
+
+	snprintf(value, 16, "%d", result);
+
+	if ((rc = write(fd, value, strlen(value))) < 0)
+		return rc;
+
+	close(fd);
+
+	return 0;
+}
+
+static long perf_event_open(struct perf_event_attr *hw_event, pid_t pid,
+		int cpu, int group_fd, unsigned long flags)
+{
+	return syscall(__NR_perf_event_open, hw_event, pid, cpu,
+		      group_fd, flags);
+}
+
+static void perf_event_attr_init(struct perf_event_attr *event_attr,
+					unsigned int type,
+					unsigned long config)
+{
+	memset(event_attr, 0, sizeof(*event_attr));
+
+	event_attr->type = type;
+	event_attr->size = sizeof(struct perf_event_attr);
+	event_attr->config = config;
+	event_attr->read_format = PERF_FORMAT_GROUP;
+	event_attr->disabled = 1;
+	event_attr->exclude_kernel = 1;
+	event_attr->exclude_hv = 1;
+	event_attr->exclude_guest = 1;
+}
+
+int perf_event_open_counter(unsigned int type,
+			    unsigned long config, int group_fd)
+{
+	int fd;
+	struct perf_event_attr event_attr;
+
+	perf_event_attr_init(&event_attr, type, config);
+
+	fd = perf_event_open(&event_attr, 0, -1, group_fd, 0);
+
+	if (fd < 0)
+		perror("perf_event_open() failed");
+
+	return fd;
+}
+
+int perf_event_enable(int fd)
+{
+	if (ioctl(fd, PERF_EVENT_IOC_ENABLE, PERF_IOC_FLAG_GROUP) == -1) {
+		perror("error while enabling perf events");
+		return -1;
+	}
+
+	return 0;
+}
+
+int perf_event_disable(int fd)
+{
+	if (ioctl(fd, PERF_EVENT_IOC_DISABLE, PERF_IOC_FLAG_GROUP) == -1) {
+		perror("error disabling perf events");
+		return -1;
+	}
+
+	return 0;
+}
+
+int perf_event_reset(int fd)
+{
+	if (ioctl(fd, PERF_EVENT_IOC_RESET, PERF_IOC_FLAG_GROUP) == -1) {
+		perror("error resetting perf events");
+		return -1;
+	}
+
+	return 0;
+}
+
+static void sigill_handler(int signr, siginfo_t *info, void *unused)
+{
+	static int warned = 0;
+	ucontext_t *ctx = (ucontext_t *)unused;
+	unsigned long *pc = &UCONTEXT_NIA(ctx);
+
+	if (*pc == (unsigned long)&dscr_insn) {
+		if (!warned++)
+			printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n");
+		*pc += 4;
+	} else {
+		printf("SIGILL at %p\n", pc);
+		abort();
+	}
+}
+
+void set_dscr(unsigned long val)
+{
+	static int init = 0;
+	struct sigaction sa;
+
+	if (!init) {
+		memset(&sa, 0, sizeof(sa));
+		sa.sa_sigaction = sigill_handler;
+		sa.sa_flags = SA_SIGINFO;
+		if (sigaction(SIGILL, &sa, NULL))
+			perror("sigill_handler");
+		init = 1;
+	}
+
+	asm volatile("dscr_insn: mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR));
+}
-- 
cgit v1.2.3


From d8a2fe29d3c97038c8efcc328d5e7940c5310565 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Fri, 19 Oct 2018 00:11:33 +1100
Subject: selftests/powerpc: Fix out-of-tree build errors

Some of our Makefiles don't do the right thing when building the
selftests with O=, fix them up.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/cache_shape/Makefile   | 2 --
 tools/testing/selftests/powerpc/ptrace/Makefile        | 2 --
 tools/testing/selftests/powerpc/signal/Makefile        | 2 --
 tools/testing/selftests/powerpc/switch_endian/Makefile | 1 +
 4 files changed, 1 insertion(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/cache_shape/Makefile b/tools/testing/selftests/powerpc/cache_shape/Makefile
index ede4d3dae750..62e947ca9921 100644
--- a/tools/testing/selftests/powerpc/cache_shape/Makefile
+++ b/tools/testing/selftests/powerpc/cache_shape/Makefile
@@ -1,8 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := cache_shape
 
-all: $(TEST_PROGS)
-
 $(TEST_PROGS): ../harness.c ../utils.c
 
 top_srcdir = ../../../../..
diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile
index 9b35ca8e8f13..6ac71b629276 100644
--- a/tools/testing/selftests/powerpc/ptrace/Makefile
+++ b/tools/testing/selftests/powerpc/ptrace/Makefile
@@ -7,8 +7,6 @@ TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \
 top_srcdir = ../../../../..
 include ../../lib.mk
 
-all: $(TEST_PROGS)
-
 CFLAGS += -m64 -I../../../../../usr/include -I../tm -mhtm -fno-pie
 
 ptrace-pkey core-pkey: child.h
diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile
index 1fca25c6ace0..d34a7c7710db 100644
--- a/tools/testing/selftests/powerpc/signal/Makefile
+++ b/tools/testing/selftests/powerpc/signal/Makefile
@@ -1,8 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := signal signal_tm
 
-all: $(TEST_PROGS)
-
 $(TEST_PROGS): ../harness.c ../utils.c signal.S
 
 CFLAGS += -maltivec
diff --git a/tools/testing/selftests/powerpc/switch_endian/Makefile b/tools/testing/selftests/powerpc/switch_endian/Makefile
index fcd2dcb8972b..bdc081afedb0 100644
--- a/tools/testing/selftests/powerpc/switch_endian/Makefile
+++ b/tools/testing/selftests/powerpc/switch_endian/Makefile
@@ -8,6 +8,7 @@ EXTRA_CLEAN = $(OUTPUT)/*.o $(OUTPUT)/check-reversed.S
 top_srcdir = ../../../../..
 include ../../lib.mk
 
+$(OUTPUT)/switch_endian_test: ASFLAGS += -I $(OUTPUT)
 $(OUTPUT)/switch_endian_test: $(OUTPUT)/check-reversed.S
 
 $(OUTPUT)/check-reversed.o: $(OUTPUT)/check.o
-- 
cgit v1.2.3


From b7683fc66eba91674e52c30f4d8e596bfb5cbcf4 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Tue, 24 Jul 2018 15:53:22 +1000
Subject: selftests/powerpc: Add a test of wild bctr

This tests that a bctr (Branch to counter and link), ie. a function
call, to a wildly out-of-bounds address is handled correctly.

Some old kernel versions didn't handle it correctly, see eg:

  "powerpc/slb: Force a full SLB flush when we insert for a bad EA"
  https://lists.ozlabs.org/pipermail/linuxppc-dev/2017-April/157397.html

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/include/reg.h  |   1 +
 tools/testing/selftests/powerpc/mm/.gitignore  |   3 +-
 tools/testing/selftests/powerpc/mm/Makefile    |   4 +-
 tools/testing/selftests/powerpc/mm/wild_bctr.c | 155 +++++++++++++++++++++++++
 4 files changed, 161 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/powerpc/mm/wild_bctr.c

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/include/reg.h b/tools/testing/selftests/powerpc/include/reg.h
index 7f348c059bc2..52b4710469d2 100644
--- a/tools/testing/selftests/powerpc/include/reg.h
+++ b/tools/testing/selftests/powerpc/include/reg.h
@@ -17,6 +17,7 @@
 				    : "memory")
 
 #define mb()		asm volatile("sync" : : : "memory");
+#define barrier()	asm volatile("" : : : "memory");
 
 #define SPRN_MMCR2     769
 #define SPRN_MMCRA     770
diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore
index 7d7c42ed6de9..ba919308fe30 100644
--- a/tools/testing/selftests/powerpc/mm/.gitignore
+++ b/tools/testing/selftests/powerpc/mm/.gitignore
@@ -2,4 +2,5 @@ hugetlb_vs_thp_test
 subpage_prot
 tempfile
 prot_sao
-segv_errors
\ No newline at end of file
+segv_errors
+wild_bctr
\ No newline at end of file
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index 33ced6e0ad25..43d68420e363 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -2,7 +2,7 @@
 noarg:
 	$(MAKE) -C ../
 
-TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors
+TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr
 TEST_GEN_FILES := tempfile
 
 top_srcdir = ../../../../..
@@ -12,6 +12,8 @@ $(TEST_GEN_PROGS): ../harness.c
 
 $(OUTPUT)/prot_sao: ../utils.c
 
+$(OUTPUT)/wild_bctr: CFLAGS += -m64
+
 $(OUTPUT)/tempfile:
 	dd if=/dev/zero of=$@ bs=64k count=1
 
diff --git a/tools/testing/selftests/powerpc/mm/wild_bctr.c b/tools/testing/selftests/powerpc/mm/wild_bctr.c
new file mode 100644
index 000000000000..1b0e9e9a2ddc
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/wild_bctr.c
@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright 2018, Michael Ellerman, IBM Corp.
+ *
+ * Test that an out-of-bounds branch to counter behaves as expected.
+ */
+
+#include <setjmp.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <ucontext.h>
+#include <unistd.h>
+
+#include "utils.h"
+
+
+#define BAD_NIP	0x788c545a18000000ull
+
+static struct pt_regs signal_regs;
+static jmp_buf setjmp_env;
+
+static void save_regs(ucontext_t *ctxt)
+{
+	struct pt_regs *regs = ctxt->uc_mcontext.regs;
+
+	memcpy(&signal_regs, regs, sizeof(signal_regs));
+}
+
+static void segv_handler(int signum, siginfo_t *info, void *ctxt_v)
+{
+	save_regs(ctxt_v);
+	longjmp(setjmp_env, 1);
+}
+
+static void usr2_handler(int signum, siginfo_t *info, void *ctxt_v)
+{
+	save_regs(ctxt_v);
+}
+
+static int ok(void)
+{
+	printf("Everything is OK in here.\n");
+	return 0;
+}
+
+#define REG_POISON	0x5a5aUL
+#define POISONED_REG(n)	((REG_POISON << 48) | ((n) << 32) | (REG_POISON << 16) | (n))
+
+static inline void poison_regs(void)
+{
+	#define POISON_REG(n)	\
+	  "lis  " __stringify(n) "," __stringify(REG_POISON) ";" \
+	  "addi " __stringify(n) "," __stringify(n) "," __stringify(n) ";" \
+	  "sldi " __stringify(n) "," __stringify(n) ", 32 ;" \
+	  "oris " __stringify(n) "," __stringify(n) "," __stringify(REG_POISON) ";" \
+	  "addi " __stringify(n) "," __stringify(n) "," __stringify(n) ";"
+
+	asm (POISON_REG(15)
+	     POISON_REG(16)
+	     POISON_REG(17)
+	     POISON_REG(18)
+	     POISON_REG(19)
+	     POISON_REG(20)
+	     POISON_REG(21)
+	     POISON_REG(22)
+	     POISON_REG(23)
+	     POISON_REG(24)
+	     POISON_REG(25)
+	     POISON_REG(26)
+	     POISON_REG(27)
+	     POISON_REG(28)
+	     POISON_REG(29)
+	     : // inputs
+	     : // outputs
+	     : "15", "16", "17", "18", "19", "20", "21", "22", "23", "24", "25",
+	       "26", "27", "28", "29"
+	);
+	#undef POISON_REG
+}
+
+static int check_regs(void)
+{
+	unsigned long i;
+
+	for (i = 15; i <= 29; i++)
+		FAIL_IF(signal_regs.gpr[i] != POISONED_REG(i));
+
+	printf("Regs OK\n");
+	return 0;
+}
+
+static void dump_regs(void)
+{
+	for (int i = 0; i < 32; i += 4) {
+		printf("r%02d 0x%016lx  r%02d 0x%016lx  " \
+		       "r%02d 0x%016lx  r%02d 0x%016lx\n",
+		       i, signal_regs.gpr[i],
+		       i+1, signal_regs.gpr[i+1],
+		       i+2, signal_regs.gpr[i+2],
+		       i+3, signal_regs.gpr[i+3]);
+	}
+}
+
+int test_wild_bctr(void)
+{
+	int (*func_ptr)(void);
+	struct sigaction segv = {
+		.sa_sigaction = segv_handler,
+		.sa_flags = SA_SIGINFO
+	};
+	struct sigaction usr2 = {
+		.sa_sigaction = usr2_handler,
+		.sa_flags = SA_SIGINFO
+	};
+
+	FAIL_IF(sigaction(SIGSEGV, &segv, NULL));
+	FAIL_IF(sigaction(SIGUSR2, &usr2, NULL));
+
+	bzero(&signal_regs, sizeof(signal_regs));
+
+	if (setjmp(setjmp_env) == 0) {
+		func_ptr = ok;
+		func_ptr();
+
+		kill(getpid(), SIGUSR2);
+		printf("Regs before:\n");
+		dump_regs();
+		bzero(&signal_regs, sizeof(signal_regs));
+
+		poison_regs();
+
+		func_ptr = (int (*)(void))BAD_NIP;
+		func_ptr();
+
+		FAIL_IF(1); /* we didn't segv? */
+	}
+
+	FAIL_IF(signal_regs.nip != BAD_NIP);
+
+	printf("All good - took SEGV as expected branching to 0x%llx\n", BAD_NIP);
+
+	dump_regs();
+	FAIL_IF(check_regs());
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(test_wild_bctr, "wild_bctr");
+}
-- 
cgit v1.2.3


From f908d26b2c41d9a924371099c4979e4b5d385165 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Fri, 19 Oct 2018 19:56:50 -0700
Subject: bpf: libbpf support for msg_push_data

Add support for new bpf_msg_push_data in libbpf.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/bpf.h            | 20 +++++++++++++++++++-
 tools/testing/selftests/bpf/bpf_helpers.h |  2 ++
 2 files changed, 21 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a2fb333290dc..852dc17ab47a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2240,6 +2240,23 @@ union bpf_attr {
  *		pointer that was returned from bpf_sk_lookup_xxx\ ().
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags)
+ *	Description
+ *		For socket policies, insert *len* bytes into msg at offset
+ *		*start*.
+ *
+ *		If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
+ *		*msg* it may want to insert metadata or options into the msg.
+ *		This can later be read and used by any of the lower layer BPF
+ *		hooks.
+ *
+ *		This helper may fail if under memory pressure (a malloc
+ *		fails) in these cases BPF programs will get an appropriate
+ *		error and BPF programs will need to handle them.
+ *
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2331,7 +2348,8 @@ union bpf_attr {
 	FN(sk_release),			\
 	FN(map_push_elem),		\
 	FN(map_pop_elem),		\
-	FN(map_peek_elem),
+	FN(map_peek_elem),		\
+	FN(msg_push_data),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 6407a3df0f3b..686e57ce40f4 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -111,6 +111,8 @@ static int (*bpf_msg_cork_bytes)(void *ctx, int len) =
 	(void *) BPF_FUNC_msg_cork_bytes;
 static int (*bpf_msg_pull_data)(void *ctx, int start, int end, int flags) =
 	(void *) BPF_FUNC_msg_pull_data;
+static int (*bpf_msg_push_data)(void *ctx, int start, int end, int flags) =
+	(void *) BPF_FUNC_msg_push_data;
 static int (*bpf_bind)(void *ctx, void *addr, int addr_len) =
 	(void *) BPF_FUNC_bind;
 static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) =
-- 
cgit v1.2.3


From 84fbfe026acaa6d91e2f71f1635992bf472e2496 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Fri, 19 Oct 2018 19:56:51 -0700
Subject: bpf: test_sockmap add options to use msg_push_data

Add options to run msg_push_data, this patch creates two more flags
in test_sockmap that can be used to specify the offset and length
of bytes to be added. The new options are --txmsg_start_push to
specify where bytes should be inserted and --txmsg_end_push to
specify how many bytes. This is analagous to the options that are
used to pull data, --txmsg_start and --txmsg_end.

In addition to adding the options tests are added to the test
suit to run the tests similar to what was done for msg_pull_data.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_sockmap.c      | 58 ++++++++++++++-
 tools/testing/selftests/bpf/test_sockmap_kern.h | 97 +++++++++++++++++++------
 2 files changed, 129 insertions(+), 26 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index cbd1c0be8680..622ade0a0957 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -77,6 +77,8 @@ int txmsg_apply;
 int txmsg_cork;
 int txmsg_start;
 int txmsg_end;
+int txmsg_start_push;
+int txmsg_end_push;
 int txmsg_ingress;
 int txmsg_skb;
 int ktls;
@@ -100,6 +102,8 @@ static const struct option long_options[] = {
 	{"txmsg_cork",	required_argument,	NULL, 'k'},
 	{"txmsg_start", required_argument,	NULL, 's'},
 	{"txmsg_end",	required_argument,	NULL, 'e'},
+	{"txmsg_start_push", required_argument,	NULL, 'p'},
+	{"txmsg_end_push",   required_argument,	NULL, 'q'},
 	{"txmsg_ingress", no_argument,		&txmsg_ingress, 1 },
 	{"txmsg_skb", no_argument,		&txmsg_skb, 1 },
 	{"ktls", no_argument,			&ktls, 1 },
@@ -903,6 +907,30 @@ run:
 			}
 		}
 
+		if (txmsg_start_push) {
+			i = 2;
+			err = bpf_map_update_elem(map_fd[5],
+						  &i, &txmsg_start_push, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem (txmsg_start_push):  %d (%s)\n",
+					err, strerror(errno));
+				goto out;
+			}
+		}
+
+		if (txmsg_end_push) {
+			i = 3;
+			err = bpf_map_update_elem(map_fd[5],
+						  &i, &txmsg_end_push, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem %i@%i (txmsg_end_push):  %d (%s)\n",
+					txmsg_end_push, i, err, strerror(errno));
+				goto out;
+			}
+		}
+
 		if (txmsg_ingress) {
 			int in = BPF_F_INGRESS;
 
@@ -1235,6 +1263,8 @@ static int test_mixed(int cgrp)
 	txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0;
 	txmsg_apply = txmsg_cork = 0;
 	txmsg_start = txmsg_end = 0;
+	txmsg_start_push = txmsg_end_push = 0;
+
 	/* Test small and large iov_count values with pass/redir/apply/cork */
 	txmsg_pass = 1;
 	txmsg_redir = 0;
@@ -1351,6 +1381,8 @@ static int test_start_end(int cgrp)
 	/* Test basic start/end with lots of iov_count and iov_lengths */
 	txmsg_start = 1;
 	txmsg_end = 2;
+	txmsg_start_push = 1;
+	txmsg_end_push = 2;
 	err = test_txmsg(cgrp);
 	if (err)
 		goto out;
@@ -1364,6 +1396,8 @@ static int test_start_end(int cgrp)
 	for (i = 99; i <= 1600; i += 500) {
 		txmsg_start = 0;
 		txmsg_end = i;
+		txmsg_start_push = 0;
+		txmsg_end_push = i;
 		err = test_exec(cgrp, &opt);
 		if (err)
 			goto out;
@@ -1373,6 +1407,8 @@ static int test_start_end(int cgrp)
 	for (i = 199; i <= 1600; i += 500) {
 		txmsg_start = 100;
 		txmsg_end = i;
+		txmsg_start_push = 100;
+		txmsg_end_push = i;
 		err = test_exec(cgrp, &opt);
 		if (err)
 			goto out;
@@ -1381,6 +1417,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end with cork pulling last sg entry */
 	txmsg_start = 1500;
 	txmsg_end = 1600;
+	txmsg_start_push = 1500;
+	txmsg_end_push = 1600;
 	err = test_exec(cgrp, &opt);
 	if (err)
 		goto out;
@@ -1388,6 +1426,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end pull of single byte in last page */
 	txmsg_start = 1111;
 	txmsg_end = 1112;
+	txmsg_start_push = 1111;
+	txmsg_end_push = 1112;
 	err = test_exec(cgrp, &opt);
 	if (err)
 		goto out;
@@ -1395,6 +1435,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end with end < start */
 	txmsg_start = 1111;
 	txmsg_end = 0;
+	txmsg_start_push = 1111;
+	txmsg_end_push = 0;
 	err = test_exec(cgrp, &opt);
 	if (err)
 		goto out;
@@ -1402,6 +1444,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end with end > data */
 	txmsg_start = 0;
 	txmsg_end = 1601;
+	txmsg_start_push = 0;
+	txmsg_end_push = 1601;
 	err = test_exec(cgrp, &opt);
 	if (err)
 		goto out;
@@ -1409,6 +1453,8 @@ static int test_start_end(int cgrp)
 	/* Test start/end with start > data */
 	txmsg_start = 1601;
 	txmsg_end = 1600;
+	txmsg_start_push = 1601;
+	txmsg_end_push = 1600;
 	err = test_exec(cgrp, &opt);
 
 out:
@@ -1424,7 +1470,7 @@ char *map_names[] = {
 	"sock_map_redir",
 	"sock_apply_bytes",
 	"sock_cork_bytes",
-	"sock_pull_bytes",
+	"sock_bytes",
 	"sock_redir_flags",
 	"sock_skb_opts",
 };
@@ -1531,7 +1577,7 @@ static int __test_suite(int cg_fd, char *bpf_file)
 	}
 
 	/* Tests basic commands and APIs with range of iov values */
-	txmsg_start = txmsg_end = 0;
+	txmsg_start = txmsg_end = txmsg_start_push = txmsg_end_push = 0;
 	err = test_txmsg(cg_fd);
 	if (err)
 		goto out;
@@ -1580,7 +1626,7 @@ int main(int argc, char **argv)
 	if (argc < 2)
 		return test_suite(-1);
 
-	while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:",
+	while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:p:q:",
 				  long_options, &longindex)) != -1) {
 		switch (opt) {
 		case 's':
@@ -1589,6 +1635,12 @@ int main(int argc, char **argv)
 		case 'e':
 			txmsg_end = atoi(optarg);
 			break;
+		case 'p':
+			txmsg_start_push = atoi(optarg);
+			break;
+		case 'q':
+			txmsg_end_push = atoi(optarg);
+			break;
 		case 'a':
 			txmsg_apply = atoi(optarg);
 			break;
diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.h b/tools/testing/selftests/bpf/test_sockmap_kern.h
index 8e8e41780bb9..14b8bbac004f 100644
--- a/tools/testing/selftests/bpf/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/test_sockmap_kern.h
@@ -70,11 +70,11 @@ struct bpf_map_def SEC("maps") sock_cork_bytes = {
 	.max_entries = 1
 };
 
-struct bpf_map_def SEC("maps") sock_pull_bytes = {
+struct bpf_map_def SEC("maps") sock_bytes = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(int),
 	.value_size = sizeof(int),
-	.max_entries = 2
+	.max_entries = 4
 };
 
 struct bpf_map_def SEC("maps") sock_redir_flags = {
@@ -181,8 +181,8 @@ int bpf_sockmap(struct bpf_sock_ops *skops)
 SEC("sk_msg1")
 int bpf_prog4(struct sk_msg_md *msg)
 {
-	int *bytes, zero = 0, one = 1;
-	int *start, *end;
+	int *bytes, zero = 0, one = 1, two = 2, three = 3;
+	int *start, *end, *start_push, *end_push;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
 	if (bytes)
@@ -190,18 +190,24 @@ int bpf_prog4(struct sk_msg_md *msg)
 	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
 	if (bytes)
 		bpf_msg_cork_bytes(msg, *bytes);
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+	start = bpf_map_lookup_elem(&sock_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_bytes, &one);
 	if (start && end)
 		bpf_msg_pull_data(msg, *start, *end, 0);
+	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
+	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
+	if (start_push && end_push)
+		bpf_msg_push_data(msg, *start_push, *end_push, 0);
 	return SK_PASS;
 }
 
 SEC("sk_msg2")
 int bpf_prog5(struct sk_msg_md *msg)
 {
-	int err1 = -1, err2 = -1, zero = 0, one = 1;
-	int *bytes, *start, *end, len1, len2;
+	int zero = 0, one = 1, two = 2, three = 3;
+	int *start, *end, *start_push, *end_push;
+	int *bytes, len1, len2 = 0, len3;
+	int err1 = -1, err2 = -1;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
 	if (bytes)
@@ -210,8 +216,8 @@ int bpf_prog5(struct sk_msg_md *msg)
 	if (bytes)
 		err2 = bpf_msg_cork_bytes(msg, *bytes);
 	len1 = (__u64)msg->data_end - (__u64)msg->data;
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+	start = bpf_map_lookup_elem(&sock_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_bytes, &one);
 	if (start && end) {
 		int err;
 
@@ -225,6 +231,23 @@ int bpf_prog5(struct sk_msg_md *msg)
 		bpf_printk("sk_msg2: length update %i->%i\n",
 			   len1, len2);
 	}
+
+	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
+	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
+	if (start_push && end_push) {
+		int err;
+
+		bpf_printk("sk_msg2: push(%i:%i)\n",
+			   start_push ? *start_push : 0,
+			   end_push ? *end_push : 0);
+		err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
+		if (err)
+			bpf_printk("sk_msg2: push_data err %i\n", err);
+		len3 = (__u64)msg->data_end - (__u64)msg->data;
+		bpf_printk("sk_msg2: length push_update %i->%i\n",
+			   len2 ? len2 : len1, len3);
+	}
+
 	bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n",
 		   len1, err1, err2);
 	return SK_PASS;
@@ -233,8 +256,8 @@ int bpf_prog5(struct sk_msg_md *msg)
 SEC("sk_msg3")
 int bpf_prog6(struct sk_msg_md *msg)
 {
-	int *bytes, zero = 0, one = 1, key = 0;
-	int *start, *end, *f;
+	int *bytes, *start, *end, *start_push, *end_push, *f;
+	int zero = 0, one = 1, two = 2, three = 3, key = 0;
 	__u64 flags = 0;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
@@ -243,10 +266,17 @@ int bpf_prog6(struct sk_msg_md *msg)
 	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
 	if (bytes)
 		bpf_msg_cork_bytes(msg, *bytes);
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+
+	start = bpf_map_lookup_elem(&sock_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_bytes, &one);
 	if (start && end)
 		bpf_msg_pull_data(msg, *start, *end, 0);
+
+	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
+	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
+	if (start_push && end_push)
+		bpf_msg_push_data(msg, *start_push, *end_push, 0);
+
 	f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
 	if (f && *f) {
 		key = 2;
@@ -262,8 +292,9 @@ int bpf_prog6(struct sk_msg_md *msg)
 SEC("sk_msg4")
 int bpf_prog7(struct sk_msg_md *msg)
 {
-	int err1 = 0, err2 = 0, zero = 0, one = 1, key = 0;
-	int *f, *bytes, *start, *end, len1, len2;
+	int zero = 0, one = 1, two = 2, three = 3, len1, len2 = 0, len3;
+	int *bytes, *start, *end, *start_push, *end_push, *f;
+	int err1 = 0, err2 = 0, key = 0;
 	__u64 flags = 0;
 
 		int err;
@@ -274,10 +305,10 @@ int bpf_prog7(struct sk_msg_md *msg)
 	if (bytes)
 		err2 = bpf_msg_cork_bytes(msg, *bytes);
 	len1 = (__u64)msg->data_end - (__u64)msg->data;
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
-	if (start && end) {
 
+	start = bpf_map_lookup_elem(&sock_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_bytes, &one);
+	if (start && end) {
 		bpf_printk("sk_msg2: pull(%i:%i)\n",
 			   start ? *start : 0, end ? *end : 0);
 		err = bpf_msg_pull_data(msg, *start, *end, 0);
@@ -288,6 +319,22 @@ int bpf_prog7(struct sk_msg_md *msg)
 		bpf_printk("sk_msg2: length update %i->%i\n",
 			   len1, len2);
 	}
+
+	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
+	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
+	if (start_push && end_push) {
+		bpf_printk("sk_msg4: push(%i:%i)\n",
+			   start_push ? *start_push : 0,
+			   end_push ? *end_push : 0);
+		err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
+		if (err)
+			bpf_printk("sk_msg4: push_data err %i\n",
+				   err);
+		len3 = (__u64)msg->data_end - (__u64)msg->data;
+		bpf_printk("sk_msg4: length push_update %i->%i\n",
+			   len2 ? len2 : len1, len3);
+	}
+
 	f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
 	if (f && *f) {
 		key = 2;
@@ -342,8 +389,8 @@ int bpf_prog9(struct sk_msg_md *msg)
 SEC("sk_msg7")
 int bpf_prog10(struct sk_msg_md *msg)
 {
-	int *bytes, zero = 0, one = 1;
-	int *start, *end;
+	int *bytes, *start, *end, *start_push, *end_push;
+	int zero = 0, one = 1, two = 2, three = 3;
 
 	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
 	if (bytes)
@@ -351,10 +398,14 @@ int bpf_prog10(struct sk_msg_md *msg)
 	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
 	if (bytes)
 		bpf_msg_cork_bytes(msg, *bytes);
-	start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+	start = bpf_map_lookup_elem(&sock_bytes, &zero);
+	end = bpf_map_lookup_elem(&sock_bytes, &one);
 	if (start && end)
 		bpf_msg_pull_data(msg, *start, *end, 0);
+	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
+	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
+	if (start_push && end_push)
+		bpf_msg_push_data(msg, *start_push, *end_push, 0);
 
 	return SK_DROP;
 }
-- 
cgit v1.2.3


From 2a159c6f82381a458bc56e7e202b6bee57a2ccb7 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 21 Oct 2018 02:09:24 +0200
Subject: bpf, verifier: fix register type dump in xadd and st

Using reg_type_str[insn->dst_reg] is incorrect since insn->dst_reg
contains the register number but not the actual register type. Add
a small reg_state() helper and use it to get to the type. Also fix
up the test_verifier test cases that have an incorrect errstr.

Fixes: 9d2be44a7f33 ("bpf: Reuse canonical string formatter for ctx errs")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c                       | 19 +++++++++++++------
 tools/testing/selftests/bpf/test_verifier.c | 10 +++++-----
 2 files changed, 18 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7d6d9cf9ebd5..64e0981a4074 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1528,14 +1528,19 @@ static bool __is_pointer_value(bool allow_ptr_leaks,
 	return reg->type != SCALAR_VALUE;
 }
 
+static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno)
+{
+	return cur_regs(env) + regno;
+}
+
 static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
 {
-	return __is_pointer_value(env->allow_ptr_leaks, cur_regs(env) + regno);
+	return __is_pointer_value(env->allow_ptr_leaks, reg_state(env, regno));
 }
 
 static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
 {
-	const struct bpf_reg_state *reg = cur_regs(env) + regno;
+	const struct bpf_reg_state *reg = reg_state(env, regno);
 
 	return reg->type == PTR_TO_CTX ||
 	       reg->type == PTR_TO_SOCKET;
@@ -1543,7 +1548,7 @@ static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
 
 static bool is_pkt_reg(struct bpf_verifier_env *env, int regno)
 {
-	const struct bpf_reg_state *reg = cur_regs(env) + regno;
+	const struct bpf_reg_state *reg = reg_state(env, regno);
 
 	return type_is_pkt_pointer(reg->type);
 }
@@ -1958,7 +1963,8 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
 	if (is_ctx_reg(env, insn->dst_reg) ||
 	    is_pkt_reg(env, insn->dst_reg)) {
 		verbose(env, "BPF_XADD stores into R%d %s is not allowed\n",
-			insn->dst_reg, reg_type_str[insn->dst_reg]);
+			insn->dst_reg,
+			reg_type_str[reg_state(env, insn->dst_reg)->type]);
 		return -EACCES;
 	}
 
@@ -1983,7 +1989,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 				int access_size, bool zero_size_allowed,
 				struct bpf_call_arg_meta *meta)
 {
-	struct bpf_reg_state *reg = cur_regs(env) + regno;
+	struct bpf_reg_state *reg = reg_state(env, regno);
 	struct bpf_func_state *state = func(env, reg);
 	int off, i, slot, spi;
 
@@ -5264,7 +5270,8 @@ static int do_check(struct bpf_verifier_env *env)
 
 			if (is_ctx_reg(env, insn->dst_reg)) {
 				verbose(env, "BPF_ST stores into R%d %s is not allowed\n",
-					insn->dst_reg, reg_type_str[insn->dst_reg]);
+					insn->dst_reg,
+					reg_type_str[reg_state(env, insn->dst_reg)->type]);
 				return -EACCES;
 			}
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index f1ae8d09770f..769d68a48f30 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -3430,7 +3430,7 @@ static struct bpf_test tests[] = {
 			BPF_ST_MEM(BPF_DW, BPF_REG_1, offsetof(struct __sk_buff, mark), 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_ST stores into R1 inv is not allowed",
+		.errstr = "BPF_ST stores into R1 ctx is not allowed",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -3442,7 +3442,7 @@ static struct bpf_test tests[] = {
 				     BPF_REG_0, offsetof(struct __sk_buff, mark), 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "BPF_XADD stores into R1 inv is not allowed",
+		.errstr = "BPF_XADD stores into R1 ctx is not allowed",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
@@ -5670,7 +5670,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R2 leaks addr into mem",
 		.result_unpriv = REJECT,
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R1 inv is not allowed",
+		.errstr = "BPF_XADD stores into R1 ctx is not allowed",
 	},
 	{
 		"leak pointer into ctx 2",
@@ -5685,7 +5685,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R10 leaks addr into mem",
 		.result_unpriv = REJECT,
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R1 inv is not allowed",
+		.errstr = "BPF_XADD stores into R1 ctx is not allowed",
 	},
 	{
 		"leak pointer into ctx 3",
@@ -12634,7 +12634,7 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = REJECT,
-		.errstr = "BPF_XADD stores into R2 ctx",
+		.errstr = "BPF_XADD stores into R2 pkt is not allowed",
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
 	{
-- 
cgit v1.2.3


From 3dca21156b5f809510e8c3efe7f1046e27242e3d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 21 Oct 2018 02:09:28 +0200
Subject: bpf, libbpf: simplify and cleanup perf ring buffer walk

Simplify bpf_perf_event_read_simple() a bit and fix up some minor
things along the way: the return code in the header is not of type
int but enum bpf_perf_event_ret instead. Once callback indicated
to break the loop walking event data, it also needs to be consumed
in data_tail since it has been processed already.

Moreover, bpf_perf_event_print_t callback should avoid void * as
we actually get a pointer to struct perf_event_header and thus
applications can make use of container_of() to have type checks.
The walk also doesn't have to use modulo op since the ring size is
required to be power of two.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/map_perf_ring.c           | 10 +++--
 tools/lib/bpf/libbpf.c                      | 67 +++++++++++++----------------
 tools/lib/bpf/libbpf.h                      | 15 ++++---
 tools/testing/selftests/bpf/trace_helpers.c |  7 +--
 4 files changed, 47 insertions(+), 52 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c
index 6d41323be291..bdaf4062e26e 100644
--- a/tools/bpf/bpftool/map_perf_ring.c
+++ b/tools/bpf/bpftool/map_perf_ring.c
@@ -50,15 +50,17 @@ static void int_exit(int signo)
 	stop = true;
 }
 
-static enum bpf_perf_event_ret print_bpf_output(void *event, void *priv)
+static enum bpf_perf_event_ret
+print_bpf_output(struct perf_event_header *event, void *private_data)
 {
-	struct event_ring_info *ring = priv;
-	struct perf_event_sample *e = event;
+	struct perf_event_sample *e = container_of(event, struct perf_event_sample,
+						   header);
+	struct event_ring_info *ring = private_data;
 	struct {
 		struct perf_event_header header;
 		__u64 id;
 		__u64 lost;
-	} *lost = event;
+	} *lost = (typeof(lost))event;
 
 	if (json_output) {
 		jsonw_start_object(json_wtr);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 0c21355f04a7..b607be7236d3 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2415,56 +2415,47 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 }
 
 enum bpf_perf_event_ret
-bpf_perf_event_read_simple(void *mem, unsigned long size,
-			   unsigned long page_size, void **buf, size_t *buf_len,
-			   bpf_perf_event_print_t fn, void *priv)
+bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
+			   void **copy_mem, size_t *copy_size,
+			   bpf_perf_event_print_t fn, void *private_data)
 {
-	struct perf_event_mmap_page *header = mem;
+	struct perf_event_mmap_page *header = mmap_mem;
 	__u64 data_head = ring_buffer_read_head(header);
 	__u64 data_tail = header->data_tail;
-	int ret = LIBBPF_PERF_EVENT_ERROR;
-	void *base, *begin, *end;
-
-	if (data_head == data_tail)
-		return LIBBPF_PERF_EVENT_CONT;
-
-	base = ((char *)header) + page_size;
-
-	begin = base + data_tail % size;
-	end = base + data_head % size;
-
-	while (begin != end) {
-		struct perf_event_header *ehdr;
-
-		ehdr = begin;
-		if (begin + ehdr->size > base + size) {
-			long len = base + size - begin;
-
-			if (*buf_len < ehdr->size) {
-				free(*buf);
-				*buf = malloc(ehdr->size);
-				if (!*buf) {
+	void *base = ((__u8 *)header) + page_size;
+	int ret = LIBBPF_PERF_EVENT_CONT;
+	struct perf_event_header *ehdr;
+	size_t ehdr_size;
+
+	while (data_head != data_tail) {
+		ehdr = base + (data_tail & (mmap_size - 1));
+		ehdr_size = ehdr->size;
+
+		if (((void *)ehdr) + ehdr_size > base + mmap_size) {
+			void *copy_start = ehdr;
+			size_t len_first = base + mmap_size - copy_start;
+			size_t len_secnd = ehdr_size - len_first;
+
+			if (*copy_size < ehdr_size) {
+				free(*copy_mem);
+				*copy_mem = malloc(ehdr_size);
+				if (!*copy_mem) {
+					*copy_size = 0;
 					ret = LIBBPF_PERF_EVENT_ERROR;
 					break;
 				}
-				*buf_len = ehdr->size;
+				*copy_size = ehdr_size;
 			}
 
-			memcpy(*buf, begin, len);
-			memcpy(*buf + len, base, ehdr->size - len);
-			ehdr = (void *)*buf;
-			begin = base + ehdr->size - len;
-		} else if (begin + ehdr->size == base + size) {
-			begin = base;
-		} else {
-			begin += ehdr->size;
+			memcpy(*copy_mem, copy_start, len_first);
+			memcpy(*copy_mem + len_first, base, len_secnd);
+			ehdr = *copy_mem;
 		}
 
-		ret = fn(ehdr, priv);
+		ret = fn(ehdr, private_data);
+		data_tail += ehdr_size;
 		if (ret != LIBBPF_PERF_EVENT_CONT)
 			break;
-
-		data_tail += ehdr->size;
 	}
 
 	ring_buffer_write_tail(header, data_tail);
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 1354cc9f8cba..1f3468dad8b2 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -297,13 +297,14 @@ enum bpf_perf_event_ret {
 	LIBBPF_PERF_EVENT_CONT	= -2,
 };
 
-typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(void *event,
-							  void *priv);
-LIBBPF_API int bpf_perf_event_read_simple(void *mem, unsigned long size,
-					  unsigned long page_size,
-					  void **buf, size_t *buf_len,
-					  bpf_perf_event_print_t fn,
-					  void *priv);
+struct perf_event_header;
+typedef enum bpf_perf_event_ret
+	(*bpf_perf_event_print_t)(struct perf_event_header *hdr,
+				  void *private_data);
+LIBBPF_API enum bpf_perf_event_ret
+bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
+			   void **copy_mem, size_t *copy_size,
+			   bpf_perf_event_print_t fn, void *private_data);
 
 struct nlattr;
 typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index a3d1dace4a75..4cdb63bf0521 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -125,10 +125,11 @@ struct perf_event_sample {
 	char data[];
 };
 
-static enum bpf_perf_event_ret bpf_perf_event_print(void *event, void *priv)
+static enum bpf_perf_event_ret
+bpf_perf_event_print(struct perf_event_header *hdr, void *private_data)
 {
-	struct perf_event_sample *e = event;
-	perf_event_print_fn fn = priv;
+	struct perf_event_sample *e = (struct perf_event_sample *)hdr;
+	perf_event_print_fn fn = private_data;
 	int ret;
 
 	if (e->header.type == PERF_RECORD_SAMPLE) {
-- 
cgit v1.2.3


From c5fa5d602221362f8341ecd9e32d83194abf5bd9 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Sat, 20 Oct 2018 22:58:44 +0100
Subject: selftests/bpf: fix return value comparison for tests in
 test_libbpf.sh

The return value for each test in test_libbpf.sh is compared with

    if (( $? == 0 )) ; then ...

This works well with bash, but not with dash, that /bin/sh is aliased to
on some systems (such as Ubuntu).

Let's replace this comparison by something that works on both shells.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_libbpf.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_libbpf.sh b/tools/testing/selftests/bpf/test_libbpf.sh
index d97dc914cd49..156d89f1edcc 100755
--- a/tools/testing/selftests/bpf/test_libbpf.sh
+++ b/tools/testing/selftests/bpf/test_libbpf.sh
@@ -6,7 +6,7 @@ export TESTNAME=test_libbpf
 # Determine selftest success via shell exit code
 exit_handler()
 {
-	if (( $? == 0 )); then
+	if [ $? -eq 0 ]; then
 		echo "selftests: $TESTNAME [PASS]";
 	else
 		echo "$TESTNAME: failed at file $LAST_LOADED" 1>&2
-- 
cgit v1.2.3


From f8d5d0cc145cc21bfc56ef807dc28102aebbf228 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 7 Nov 2017 16:30:10 -0500
Subject: xarray: Add definition of struct xarray

This is a direct replacement for struct radix_tree_root.  Some of the
struct members have changed name; convert those, and use a #define so
that radix_tree users continue to work without change.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: Josef Bacik <jbacik@fb.com>
---
 include/linux/radix-tree.h               | 28 ++++--------
 include/linux/xarray.h                   | 70 +++++++++++++++++++++++++++++
 lib/Makefile                             |  2 +-
 lib/idr.c                                |  4 +-
 lib/radix-tree.c                         | 75 ++++++++++++++++----------------
 lib/xarray.c                             | 44 +++++++++++++++++++
 tools/testing/radix-tree/Makefile        |  5 ++-
 tools/testing/radix-tree/linux/bug.h     |  1 +
 tools/testing/radix-tree/linux/kconfig.h |  1 +
 tools/testing/radix-tree/multiorder.c    |  6 +--
 tools/testing/radix-tree/test.c          |  6 +--
 tools/testing/radix-tree/xarray.c        |  7 +++
 12 files changed, 181 insertions(+), 68 deletions(-)
 create mode 100644 lib/xarray.c
 create mode 100644 tools/testing/radix-tree/linux/kconfig.h
 create mode 100644 tools/testing/radix-tree/xarray.c

(limited to 'tools')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 60f3d8eb2cb7..0b080bd88ab7 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -30,6 +30,9 @@
 #include <linux/types.h>
 #include <linux/xarray.h>
 
+/* Keep unconverted code working */
+#define radix_tree_root		xarray
+
 /*
  * The bottom two bits of the slot determine how the remaining bits in the
  * slot are interpreted:
@@ -92,36 +95,21 @@ struct radix_tree_node {
 	unsigned long	tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
 };
 
-/* The IDR tag is stored in the low bits of the GFP flags */
+/* The IDR tag is stored in the low bits of xa_flags */
 #define ROOT_IS_IDR	((__force gfp_t)4)
-/* The top bits of gfp_mask are used to store the root tags */
+/* The top bits of xa_flags are used to store the root tags */
 #define ROOT_TAG_SHIFT	(__GFP_BITS_SHIFT)
 
-struct radix_tree_root {
-	spinlock_t		xa_lock;
-	gfp_t			gfp_mask;
-	struct radix_tree_node	__rcu *rnode;
-};
-
-#define RADIX_TREE_INIT(name, mask)	{				\
-	.xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock),			\
-	.gfp_mask = (mask),						\
-	.rnode = NULL,							\
-}
+#define RADIX_TREE_INIT(name, mask)	XARRAY_INIT(name, mask)
 
 #define RADIX_TREE(name, mask) \
 	struct radix_tree_root name = RADIX_TREE_INIT(name, mask)
 
-#define INIT_RADIX_TREE(root, mask)					\
-do {									\
-	spin_lock_init(&(root)->xa_lock);				\
-	(root)->gfp_mask = (mask);					\
-	(root)->rnode = NULL;						\
-} while (0)
+#define INIT_RADIX_TREE(root, mask) xa_init_flags(root, mask)
 
 static inline bool radix_tree_empty(const struct radix_tree_root *root)
 {
-	return root->rnode == NULL;
+	return root->xa_head == NULL;
 }
 
 /**
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 4d1cd7a083e8..9122cf8bf52a 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -10,6 +10,8 @@
  */
 
 #include <linux/bug.h>
+#include <linux/compiler.h>
+#include <linux/kconfig.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
 
@@ -153,6 +155,74 @@ static inline bool xa_is_internal(const void *entry)
 	return ((unsigned long)entry & 3) == 2;
 }
 
+/**
+ * struct xarray - The anchor of the XArray.
+ * @xa_lock: Lock that protects the contents of the XArray.
+ *
+ * To use the xarray, define it statically or embed it in your data structure.
+ * It is a very small data structure, so it does not usually make sense to
+ * allocate it separately and keep a pointer to it in your data structure.
+ *
+ * You may use the xa_lock to protect your own data structures as well.
+ */
+/*
+ * If all of the entries in the array are NULL, @xa_head is a NULL pointer.
+ * If the only non-NULL entry in the array is at index 0, @xa_head is that
+ * entry.  If any other entry in the array is non-NULL, @xa_head points
+ * to an @xa_node.
+ */
+struct xarray {
+	spinlock_t	xa_lock;
+/* private: The rest of the data structure is not to be used directly. */
+	gfp_t		xa_flags;
+	void __rcu *	xa_head;
+};
+
+#define XARRAY_INIT(name, flags) {				\
+	.xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock),		\
+	.xa_flags = flags,					\
+	.xa_head = NULL,					\
+}
+
+/**
+ * DEFINE_XARRAY_FLAGS() - Define an XArray with custom flags.
+ * @name: A string that names your XArray.
+ * @flags: XA_FLAG values.
+ *
+ * This is intended for file scope definitions of XArrays.  It declares
+ * and initialises an empty XArray with the chosen name and flags.  It is
+ * equivalent to calling xa_init_flags() on the array, but it does the
+ * initialisation at compiletime instead of runtime.
+ */
+#define DEFINE_XARRAY_FLAGS(name, flags)				\
+	struct xarray name = XARRAY_INIT(name, flags)
+
+/**
+ * DEFINE_XARRAY() - Define an XArray.
+ * @name: A string that names your XArray.
+ *
+ * This is intended for file scope definitions of XArrays.  It declares
+ * and initialises an empty XArray with the chosen name.  It is equivalent
+ * to calling xa_init() on the array, but it does the initialisation at
+ * compiletime instead of runtime.
+ */
+#define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0)
+
+void xa_init_flags(struct xarray *, gfp_t flags);
+
+/**
+ * xa_init() - Initialise an empty XArray.
+ * @xa: XArray.
+ *
+ * An empty XArray is full of NULL entries.
+ *
+ * Context: Any context.
+ */
+static inline void xa_init(struct xarray *xa)
+{
+	xa_init_flags(xa, 0);
+}
+
 #define xa_trylock(xa)		spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)		spin_lock(&(xa)->xa_lock)
 #define xa_unlock(xa)		spin_unlock(&(xa)->xa_lock)
diff --git a/lib/Makefile b/lib/Makefile
index ca3f7ebb900d..057385f1f145 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -18,7 +18,7 @@ KCOV_INSTRUMENT_debugobjects.o := n
 KCOV_INSTRUMENT_dynamic_debug.o := n
 
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
-	 rbtree.o radix-tree.o timerqueue.o\
+	 rbtree.o radix-tree.o timerqueue.o xarray.o \
 	 idr.o int_sqrt.o extable.o \
 	 sha1.o chacha20.o irq_regs.o argv_split.o \
 	 flex_proportions.o ratelimit.o show_mem.o \
diff --git a/lib/idr.c b/lib/idr.c
index 88419fbc5737..9a366b5be2c2 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -39,8 +39,8 @@ int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid,
 	unsigned int base = idr->idr_base;
 	unsigned int id = *nextid;
 
-	if (WARN_ON_ONCE(!(idr->idr_rt.gfp_mask & ROOT_IS_IDR)))
-		idr->idr_rt.gfp_mask |= IDR_RT_MARKER;
+	if (WARN_ON_ONCE(!(idr->idr_rt.xa_flags & ROOT_IS_IDR)))
+		idr->idr_rt.xa_flags |= IDR_RT_MARKER;
 
 	id = (id < base) ? 0 : id - base;
 	radix_tree_iter_init(&iter, id);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 59b28111eabc..299d4bdba109 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -124,7 +124,7 @@ static unsigned int radix_tree_descend(const struct radix_tree_node *parent,
 
 static inline gfp_t root_gfp_mask(const struct radix_tree_root *root)
 {
-	return root->gfp_mask & (__GFP_BITS_MASK & ~GFP_ZONEMASK);
+	return root->xa_flags & (__GFP_BITS_MASK & ~GFP_ZONEMASK);
 }
 
 static inline void tag_set(struct radix_tree_node *node, unsigned int tag,
@@ -147,32 +147,32 @@ static inline int tag_get(const struct radix_tree_node *node, unsigned int tag,
 
 static inline void root_tag_set(struct radix_tree_root *root, unsigned tag)
 {
-	root->gfp_mask |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT));
+	root->xa_flags |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT));
 }
 
 static inline void root_tag_clear(struct radix_tree_root *root, unsigned tag)
 {
-	root->gfp_mask &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT));
+	root->xa_flags &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT));
 }
 
 static inline void root_tag_clear_all(struct radix_tree_root *root)
 {
-	root->gfp_mask &= (1 << ROOT_TAG_SHIFT) - 1;
+	root->xa_flags &= (__force gfp_t)((1 << ROOT_TAG_SHIFT) - 1);
 }
 
 static inline int root_tag_get(const struct radix_tree_root *root, unsigned tag)
 {
-	return (__force int)root->gfp_mask & (1 << (tag + ROOT_TAG_SHIFT));
+	return (__force int)root->xa_flags & (1 << (tag + ROOT_TAG_SHIFT));
 }
 
 static inline unsigned root_tags_get(const struct radix_tree_root *root)
 {
-	return (__force unsigned)root->gfp_mask >> ROOT_TAG_SHIFT;
+	return (__force unsigned)root->xa_flags >> ROOT_TAG_SHIFT;
 }
 
 static inline bool is_idr(const struct radix_tree_root *root)
 {
-	return !!(root->gfp_mask & ROOT_IS_IDR);
+	return !!(root->xa_flags & ROOT_IS_IDR);
 }
 
 /*
@@ -291,12 +291,12 @@ static void dump_node(struct radix_tree_node *node, unsigned long index)
 /* For debug */
 static void radix_tree_dump(struct radix_tree_root *root)
 {
-	pr_debug("radix root: %p rnode %p tags %x\n",
-			root, root->rnode,
-			root->gfp_mask >> ROOT_TAG_SHIFT);
-	if (!radix_tree_is_internal_node(root->rnode))
+	pr_debug("radix root: %p xa_head %p tags %x\n",
+			root, root->xa_head,
+			root->xa_flags >> ROOT_TAG_SHIFT);
+	if (!radix_tree_is_internal_node(root->xa_head))
 		return;
-	dump_node(entry_to_node(root->rnode), 0);
+	dump_node(entry_to_node(root->xa_head), 0);
 }
 
 static void dump_ida_node(void *entry, unsigned long index)
@@ -340,9 +340,9 @@ static void dump_ida_node(void *entry, unsigned long index)
 static void ida_dump(struct ida *ida)
 {
 	struct radix_tree_root *root = &ida->ida_rt;
-	pr_debug("ida: %p node %p free %d\n", ida, root->rnode,
-				root->gfp_mask >> ROOT_TAG_SHIFT);
-	dump_ida_node(root->rnode, 0);
+	pr_debug("ida: %p node %p free %d\n", ida, root->xa_head,
+				root->xa_flags >> ROOT_TAG_SHIFT);
+	dump_ida_node(root->xa_head, 0);
 }
 #endif
 
@@ -576,7 +576,7 @@ int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order)
 static unsigned radix_tree_load_root(const struct radix_tree_root *root,
 		struct radix_tree_node **nodep, unsigned long *maxindex)
 {
-	struct radix_tree_node *node = rcu_dereference_raw(root->rnode);
+	struct radix_tree_node *node = rcu_dereference_raw(root->xa_head);
 
 	*nodep = node;
 
@@ -605,7 +605,7 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp,
 	while (index > shift_maxindex(maxshift))
 		maxshift += RADIX_TREE_MAP_SHIFT;
 
-	entry = rcu_dereference_raw(root->rnode);
+	entry = rcu_dereference_raw(root->xa_head);
 	if (!entry && (!is_idr(root) || root_tag_get(root, IDR_FREE)))
 		goto out;
 
@@ -633,7 +633,7 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp,
 		if (radix_tree_is_internal_node(entry)) {
 			entry_to_node(entry)->parent = node;
 		} else if (xa_is_value(entry)) {
-			/* Moving an exceptional root->rnode to a node */
+			/* Moving an exceptional root->xa_head to a node */
 			node->exceptional = 1;
 		}
 		/*
@@ -642,7 +642,7 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp,
 		 */
 		node->slots[0] = (void __rcu *)entry;
 		entry = node_to_entry(node);
-		rcu_assign_pointer(root->rnode, entry);
+		rcu_assign_pointer(root->xa_head, entry);
 		shift += RADIX_TREE_MAP_SHIFT;
 	} while (shift <= maxshift);
 out:
@@ -659,7 +659,7 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root,
 	bool shrunk = false;
 
 	for (;;) {
-		struct radix_tree_node *node = rcu_dereference_raw(root->rnode);
+		struct radix_tree_node *node = rcu_dereference_raw(root->xa_head);
 		struct radix_tree_node *child;
 
 		if (!radix_tree_is_internal_node(node))
@@ -695,9 +695,9 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root,
 		 * moving the node from one part of the tree to another: if it
 		 * was safe to dereference the old pointer to it
 		 * (node->slots[0]), it will be safe to dereference the new
-		 * one (root->rnode) as far as dependent read barriers go.
+		 * one (root->xa_head) as far as dependent read barriers go.
 		 */
-		root->rnode = (void __rcu *)child;
+		root->xa_head = (void __rcu *)child;
 		if (is_idr(root) && !tag_get(node, IDR_FREE, 0))
 			root_tag_clear(root, IDR_FREE);
 
@@ -745,9 +745,8 @@ static bool delete_node(struct radix_tree_root *root,
 
 		if (node->count) {
 			if (node_to_entry(node) ==
-					rcu_dereference_raw(root->rnode))
-				deleted |= radix_tree_shrink(root,
-								update_node);
+					rcu_dereference_raw(root->xa_head))
+				deleted |= radix_tree_shrink(root, update_node);
 			return deleted;
 		}
 
@@ -762,7 +761,7 @@ static bool delete_node(struct radix_tree_root *root,
 			 */
 			if (!is_idr(root))
 				root_tag_clear_all(root);
-			root->rnode = NULL;
+			root->xa_head = NULL;
 		}
 
 		WARN_ON_ONCE(!list_empty(&node->private_list));
@@ -787,7 +786,7 @@ static bool delete_node(struct radix_tree_root *root,
  *	at position @index in the radix tree @root.
  *
  *	Until there is more than one item in the tree, no nodes are
- *	allocated and @root->rnode is used as a direct slot instead of
+ *	allocated and @root->xa_head is used as a direct slot instead of
  *	pointing to a node, in which case *@nodep will be NULL.
  *
  *	Returns -ENOMEM, or 0 for success.
@@ -797,7 +796,7 @@ int __radix_tree_create(struct radix_tree_root *root, unsigned long index,
 			void __rcu ***slotp)
 {
 	struct radix_tree_node *node = NULL, *child;
-	void __rcu **slot = (void __rcu **)&root->rnode;
+	void __rcu **slot = (void __rcu **)&root->xa_head;
 	unsigned long maxindex;
 	unsigned int shift, offset = 0;
 	unsigned long max = index | ((1UL << order) - 1);
@@ -813,7 +812,7 @@ int __radix_tree_create(struct radix_tree_root *root, unsigned long index,
 		if (error < 0)
 			return error;
 		shift = error;
-		child = rcu_dereference_raw(root->rnode);
+		child = rcu_dereference_raw(root->xa_head);
 	}
 
 	while (shift > order) {
@@ -1004,7 +1003,7 @@ EXPORT_SYMBOL(__radix_tree_insert);
  *	tree @root.
  *
  *	Until there is more than one item in the tree, no nodes are
- *	allocated and @root->rnode is used as a direct slot instead of
+ *	allocated and @root->xa_head is used as a direct slot instead of
  *	pointing to a node, in which case *@nodep will be NULL.
  */
 void *__radix_tree_lookup(const struct radix_tree_root *root,
@@ -1017,7 +1016,7 @@ void *__radix_tree_lookup(const struct radix_tree_root *root,
 
  restart:
 	parent = NULL;
-	slot = (void __rcu **)&root->rnode;
+	slot = (void __rcu **)&root->xa_head;
 	radix_tree_load_root(root, &node, &maxindex);
 	if (index > maxindex)
 		return NULL;
@@ -1168,9 +1167,9 @@ void __radix_tree_replace(struct radix_tree_root *root,
 	/*
 	 * This function supports replacing exceptional entries and
 	 * deleting entries, but that needs accounting against the
-	 * node unless the slot is root->rnode.
+	 * node unless the slot is root->xa_head.
 	 */
-	WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->rnode) &&
+	WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) &&
 			(count || exceptional));
 	replace_slot(slot, item, node, count, exceptional);
 
@@ -1722,7 +1721,7 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root,
 		iter->tags = 1;
 		iter->node = NULL;
 		__set_iter_shift(iter, 0);
-		return (void __rcu **)&root->rnode;
+		return (void __rcu **)&root->xa_head;
 	}
 
 	do {
@@ -2109,7 +2108,7 @@ void __rcu **idr_get_free(struct radix_tree_root *root,
 			      unsigned long max)
 {
 	struct radix_tree_node *node = NULL, *child;
-	void __rcu **slot = (void __rcu **)&root->rnode;
+	void __rcu **slot = (void __rcu **)&root->xa_head;
 	unsigned long maxindex, start = iter->next_index;
 	unsigned int shift, offset = 0;
 
@@ -2125,7 +2124,7 @@ void __rcu **idr_get_free(struct radix_tree_root *root,
 		if (error < 0)
 			return ERR_PTR(error);
 		shift = error;
-		child = rcu_dereference_raw(root->rnode);
+		child = rcu_dereference_raw(root->xa_head);
 	}
 	if (start == 0 && shift == 0)
 		shift = RADIX_TREE_MAP_SHIFT;
@@ -2190,10 +2189,10 @@ void __rcu **idr_get_free(struct radix_tree_root *root,
  */
 void idr_destroy(struct idr *idr)
 {
-	struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.rnode);
+	struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.xa_head);
 	if (radix_tree_is_internal_node(node))
 		radix_tree_free_nodes(node);
-	idr->idr_rt.rnode = NULL;
+	idr->idr_rt.xa_head = NULL;
 	root_tag_set(&idr->idr_rt, IDR_FREE);
 }
 EXPORT_SYMBOL(idr_destroy);
diff --git a/lib/xarray.c b/lib/xarray.c
new file mode 100644
index 000000000000..862f4c64c754
--- /dev/null
+++ b/lib/xarray.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * XArray implementation
+ * Copyright (c) 2017 Microsoft Corporation
+ * Author: Matthew Wilcox <willy@infradead.org>
+ */
+
+#include <linux/export.h>
+#include <linux/xarray.h>
+
+/*
+ * Coding conventions in this file:
+ *
+ * @xa is used to refer to the entire xarray.
+ * @xas is the 'xarray operation state'.  It may be either a pointer to
+ * an xa_state, or an xa_state stored on the stack.  This is an unfortunate
+ * ambiguity.
+ * @index is the index of the entry being operated on
+ * @mark is an xa_mark_t; a small number indicating one of the mark bits.
+ * @node refers to an xa_node; usually the primary one being operated on by
+ * this function.
+ * @offset is the index into the slots array inside an xa_node.
+ * @parent refers to the @xa_node closer to the head than @node.
+ * @entry refers to something stored in a slot in the xarray
+ */
+
+/**
+ * xa_init_flags() - Initialise an empty XArray with flags.
+ * @xa: XArray.
+ * @flags: XA_FLAG values.
+ *
+ * If you need to initialise an XArray with special flags (eg you need
+ * to take the lock from interrupt context), use this function instead
+ * of xa_init().
+ *
+ * Context: Any context.
+ */
+void xa_init_flags(struct xarray *xa, gfp_t flags)
+{
+	spin_lock_init(&xa->xa_lock);
+	xa->xa_flags = flags;
+	xa->xa_head = NULL;
+}
+EXPORT_SYMBOL(xa_init_flags);
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index 12adcf9ffe86..c0cf1c79efd5 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -5,7 +5,7 @@ CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \
 LDFLAGS += -fsanitize=address -fsanitize=undefined
 LDLIBS+= -lpthread -lurcu
 TARGETS = main idr-test multiorder
-CORE_OFILES := radix-tree.o idr.o linux.o test.o find_bit.o
+CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o
 OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \
 	 tag_check.o multiorder.o idr-test.o iteration_check.o benchmark.o
 
@@ -35,6 +35,7 @@ vpath %.c ../../lib
 $(OFILES): Makefile *.h */*.h generated/map-shift.h \
 	../../include/linux/*.h \
 	../../include/asm/*.h \
+	../../../include/linux/xarray.h \
 	../../../include/linux/radix-tree.h \
 	../../../include/linux/idr.h
 
@@ -44,6 +45,8 @@ radix-tree.c: ../../../lib/radix-tree.c
 idr.c: ../../../lib/idr.c
 	sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@
 
+xarray.o: ../../../lib/xarray.c
+
 generated/map-shift.h:
 	@if ! grep -qws $(SHIFT) generated/map-shift.h; then		\
 		echo "#define XA_CHUNK_SHIFT $(SHIFT)" >		\
diff --git a/tools/testing/radix-tree/linux/bug.h b/tools/testing/radix-tree/linux/bug.h
index 23b8ed52f8c8..03dc8a57eb99 100644
--- a/tools/testing/radix-tree/linux/bug.h
+++ b/tools/testing/radix-tree/linux/bug.h
@@ -1 +1,2 @@
+#include <stdio.h>
 #include "asm/bug.h"
diff --git a/tools/testing/radix-tree/linux/kconfig.h b/tools/testing/radix-tree/linux/kconfig.h
new file mode 100644
index 000000000000..6c8675859913
--- /dev/null
+++ b/tools/testing/radix-tree/linux/kconfig.h
@@ -0,0 +1 @@
+#include "../../../../include/linux/kconfig.h"
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 2b4f4dba1882..080aea450430 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -192,13 +192,13 @@ static void multiorder_shrink(unsigned long index, int order)
 
 	assert(item_insert_order(&tree, 0, order) == 0);
 
-	node = tree.rnode;
+	node = tree.xa_head;
 
 	assert(item_insert(&tree, index) == 0);
-	assert(node != tree.rnode);
+	assert(node != tree.xa_head);
 
 	assert(item_delete(&tree, index) != 0);
-	assert(node == tree.rnode);
+	assert(node == tree.xa_head);
 
 	for (i = 0; i < max; i++) {
 		struct item *item = item_lookup(&tree, i);
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 62de66c314b7..70ddf964d51c 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -281,7 +281,7 @@ static int verify_node(struct radix_tree_node *slot, unsigned int tag,
 
 void verify_tag_consistency(struct radix_tree_root *root, unsigned int tag)
 {
-	struct radix_tree_node *node = root->rnode;
+	struct radix_tree_node *node = root->xa_head;
 	if (!radix_tree_is_internal_node(node))
 		return;
 	verify_node(node, tag, !!root_tag_get(root, tag));
@@ -311,13 +311,13 @@ void item_kill_tree(struct radix_tree_root *root)
 		}
 	}
 	assert(radix_tree_gang_lookup(root, (void **)items, 0, 32) == 0);
-	assert(root->rnode == NULL);
+	assert(root->xa_head == NULL);
 }
 
 void tree_verify_min_height(struct radix_tree_root *root, int maxindex)
 {
 	unsigned shift;
-	struct radix_tree_node *node = root->rnode;
+	struct radix_tree_node *node = root->xa_head;
 	if (!radix_tree_is_internal_node(node)) {
 		assert(maxindex == 0);
 		return;
diff --git a/tools/testing/radix-tree/xarray.c b/tools/testing/radix-tree/xarray.c
new file mode 100644
index 000000000000..9bbd667172a7
--- /dev/null
+++ b/tools/testing/radix-tree/xarray.c
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * xarray.c: Userspace shim for XArray test-suite
+ * Copyright (c) 2018 Matthew Wilcox <willy@infradead.org>
+ */
+
+#include "../../../lib/xarray.c"
-- 
cgit v1.2.3


From 01959dfe771c6893365482ec78dc1d9cbbbe6de8 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Thu, 9 Nov 2017 09:23:56 -0500
Subject: xarray: Define struct xa_node

This is a direct replacement for struct radix_tree_node.  A couple of
struct members have changed name, so convert those.  Use a #define so
that radix tree users continue to work without change.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: Josef Bacik <jbacik@fb.com>
---
 include/linux/radix-tree.h            | 29 +++------------------
 include/linux/xarray.h                | 27 ++++++++++++++++++++
 lib/radix-tree.c                      | 48 +++++++++++++++++------------------
 mm/workingset.c                       | 16 ++++++------
 tools/testing/radix-tree/multiorder.c | 30 +++++++++++-----------
 5 files changed, 77 insertions(+), 73 deletions(-)

(limited to 'tools')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 0b080bd88ab7..15388b7e38b9 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -32,6 +32,7 @@
 
 /* Keep unconverted code working */
 #define radix_tree_root		xarray
+#define radix_tree_node		xa_node
 
 /*
  * The bottom two bits of the slot determine how the remaining bits in the
@@ -60,41 +61,17 @@ static inline bool radix_tree_is_internal_node(void *ptr)
 
 /*** radix-tree API starts here ***/
 
-#define RADIX_TREE_MAX_TAGS 3
-
 #define RADIX_TREE_MAP_SHIFT	XA_CHUNK_SHIFT
 #define RADIX_TREE_MAP_SIZE	(1UL << RADIX_TREE_MAP_SHIFT)
 #define RADIX_TREE_MAP_MASK	(RADIX_TREE_MAP_SIZE-1)
 
-#define RADIX_TREE_TAG_LONGS	\
-	((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG)
+#define RADIX_TREE_MAX_TAGS	XA_MAX_MARKS
+#define RADIX_TREE_TAG_LONGS	XA_MARK_LONGS
 
 #define RADIX_TREE_INDEX_BITS  (8 /* CHAR_BIT */ * sizeof(unsigned long))
 #define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \
 					  RADIX_TREE_MAP_SHIFT))
 
-/*
- * @count is the count of every non-NULL element in the ->slots array
- * whether that is a value entry, a retry entry, a user pointer,
- * a sibling entry or a pointer to the next level of the tree.
- * @exceptional is the count of every element in ->slots which is
- * either a value entry or a sibling of a value entry.
- */
-struct radix_tree_node {
-	unsigned char	shift;		/* Bits remaining in each slot */
-	unsigned char	offset;		/* Slot offset in parent */
-	unsigned char	count;		/* Total entry count */
-	unsigned char	exceptional;	/* Exceptional entry count */
-	struct radix_tree_node *parent;		/* Used when ascending tree */
-	struct radix_tree_root *root;		/* The tree we belong to */
-	union {
-		struct list_head private_list;	/* For tree user */
-		struct rcu_head	rcu_head;	/* Used when freeing node */
-	};
-	void __rcu	*slots[RADIX_TREE_MAP_SIZE];
-	unsigned long	tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
-};
-
 /* The IDR tag is stored in the low bits of xa_flags */
 #define ROOT_IS_IDR	((__force gfp_t)4)
 /* The top bits of xa_flags are used to store the root tags */
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 9122cf8bf52a..52141dfc5a90 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -252,6 +252,33 @@ static inline void xa_init(struct xarray *xa)
 #endif
 #define XA_CHUNK_SIZE		(1UL << XA_CHUNK_SHIFT)
 #define XA_CHUNK_MASK		(XA_CHUNK_SIZE - 1)
+#define XA_MAX_MARKS		3
+#define XA_MARK_LONGS		DIV_ROUND_UP(XA_CHUNK_SIZE, BITS_PER_LONG)
+
+/*
+ * @count is the count of every non-NULL element in the ->slots array
+ * whether that is a value entry, a retry entry, a user pointer,
+ * a sibling entry or a pointer to the next level of the tree.
+ * @nr_values is the count of every element in ->slots which is
+ * either a value entry or a sibling of a value entry.
+ */
+struct xa_node {
+	unsigned char	shift;		/* Bits remaining in each slot */
+	unsigned char	offset;		/* Slot offset in parent */
+	unsigned char	count;		/* Total entry count */
+	unsigned char	nr_values;	/* Value entry count */
+	struct xa_node __rcu *parent;	/* NULL at top of tree */
+	struct xarray	*array;		/* The array we belong to */
+	union {
+		struct list_head private_list;	/* For tree user */
+		struct rcu_head	rcu_head;	/* Used when freeing node */
+	};
+	void __rcu	*slots[XA_CHUNK_SIZE];
+	union {
+		unsigned long	tags[XA_MAX_MARKS][XA_MARK_LONGS];
+		unsigned long	marks[XA_MAX_MARKS][XA_MARK_LONGS];
+	};
+};
 
 /* Private */
 static inline bool xa_is_node(const void *entry)
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 299d4bdba109..8a568cea1237 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -260,11 +260,11 @@ static void dump_node(struct radix_tree_node *node, unsigned long index)
 {
 	unsigned long i;
 
-	pr_debug("radix node: %p offset %d indices %lu-%lu parent %p tags %lx %lx %lx shift %d count %d exceptional %d\n",
+	pr_debug("radix node: %p offset %d indices %lu-%lu parent %p tags %lx %lx %lx shift %d count %d nr_values %d\n",
 		node, node->offset, index, index | node_maxindex(node),
 		node->parent,
 		node->tags[0][0], node->tags[1][0], node->tags[2][0],
-		node->shift, node->count, node->exceptional);
+		node->shift, node->count, node->nr_values);
 
 	for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
 		unsigned long first = index | (i << node->shift);
@@ -354,7 +354,7 @@ static struct radix_tree_node *
 radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent,
 			struct radix_tree_root *root,
 			unsigned int shift, unsigned int offset,
-			unsigned int count, unsigned int exceptional)
+			unsigned int count, unsigned int nr_values)
 {
 	struct radix_tree_node *ret = NULL;
 
@@ -401,9 +401,9 @@ out:
 		ret->shift = shift;
 		ret->offset = offset;
 		ret->count = count;
-		ret->exceptional = exceptional;
+		ret->nr_values = nr_values;
 		ret->parent = parent;
-		ret->root = root;
+		ret->array = root;
 	}
 	return ret;
 }
@@ -633,8 +633,8 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp,
 		if (radix_tree_is_internal_node(entry)) {
 			entry_to_node(entry)->parent = node;
 		} else if (xa_is_value(entry)) {
-			/* Moving an exceptional root->xa_head to a node */
-			node->exceptional = 1;
+			/* Moving a value entry root->xa_head to a node */
+			node->nr_values = 1;
 		}
 		/*
 		 * entry was already in the radix tree, so we do not need
@@ -928,12 +928,12 @@ static inline int insert_entries(struct radix_tree_node *node,
 		if (xa_is_node(old))
 			radix_tree_free_nodes(old);
 		if (xa_is_value(old))
-			node->exceptional--;
+			node->nr_values--;
 	}
 	if (node) {
 		node->count += n;
 		if (xa_is_value(item))
-			node->exceptional += n;
+			node->nr_values += n;
 	}
 	return n;
 }
@@ -947,7 +947,7 @@ static inline int insert_entries(struct radix_tree_node *node,
 	if (node) {
 		node->count++;
 		if (xa_is_value(item))
-			node->exceptional++;
+			node->nr_values++;
 	}
 	return 1;
 }
@@ -1083,7 +1083,7 @@ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index)
 EXPORT_SYMBOL(radix_tree_lookup);
 
 static inline void replace_sibling_entries(struct radix_tree_node *node,
-				void __rcu **slot, int count, int exceptional)
+				void __rcu **slot, int count, int values)
 {
 #ifdef CONFIG_RADIX_TREE_MULTIORDER
 	unsigned offset = get_slot_offset(node, slot);
@@ -1096,18 +1096,18 @@ static inline void replace_sibling_entries(struct radix_tree_node *node,
 			node->slots[offset] = NULL;
 			node->count--;
 		}
-		node->exceptional += exceptional;
+		node->nr_values += values;
 	}
 #endif
 }
 
 static void replace_slot(void __rcu **slot, void *item,
-		struct radix_tree_node *node, int count, int exceptional)
+		struct radix_tree_node *node, int count, int values)
 {
-	if (node && (count || exceptional)) {
+	if (node && (count || values)) {
 		node->count += count;
-		node->exceptional += exceptional;
-		replace_sibling_entries(node, slot, count, exceptional);
+		node->nr_values += values;
+		replace_sibling_entries(node, slot, count, values);
 	}
 
 	rcu_assign_pointer(*slot, item);
@@ -1161,17 +1161,17 @@ void __radix_tree_replace(struct radix_tree_root *root,
 			  radix_tree_update_node_t update_node)
 {
 	void *old = rcu_dereference_raw(*slot);
-	int exceptional = !!xa_is_value(item) - !!xa_is_value(old);
+	int values = !!xa_is_value(item) - !!xa_is_value(old);
 	int count = calculate_count(root, node, slot, item, old);
 
 	/*
-	 * This function supports replacing exceptional entries and
+	 * This function supports replacing value entries and
 	 * deleting entries, but that needs accounting against the
 	 * node unless the slot is root->xa_head.
 	 */
 	WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) &&
-			(count || exceptional));
-	replace_slot(slot, item, node, count, exceptional);
+			(count || values));
+	replace_slot(slot, item, node, count, values);
 
 	if (!node)
 		return;
@@ -1193,7 +1193,7 @@ void __radix_tree_replace(struct radix_tree_root *root,
  * across slot lookup and replacement.
  *
  * NOTE: This cannot be used to switch between non-entries (empty slots),
- * regular entries, and exceptional entries, as that requires accounting
+ * regular entries, and value entries, as that requires accounting
  * inside the radix tree node. When switching from one type of entry or
  * deleting, use __radix_tree_lookup() and __radix_tree_replace() or
  * radix_tree_iter_replace().
@@ -1301,7 +1301,7 @@ int radix_tree_split(struct radix_tree_root *root, unsigned long index,
 		rcu_assign_pointer(parent->slots[end], RADIX_TREE_RETRY);
 	}
 	rcu_assign_pointer(parent->slots[offset], RADIX_TREE_RETRY);
-	parent->exceptional -= (end - offset);
+	parent->nr_values -= (end - offset);
 
 	if (order == parent->shift)
 		return 0;
@@ -1961,7 +1961,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root,
 				struct radix_tree_node *node, void __rcu **slot)
 {
 	void *old = rcu_dereference_raw(*slot);
-	int exceptional = xa_is_value(old) ? -1 : 0;
+	int values = xa_is_value(old) ? -1 : 0;
 	unsigned offset = get_slot_offset(node, slot);
 	int tag;
 
@@ -1971,7 +1971,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root,
 		for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
 			node_tag_clear(root, node, tag, offset);
 
-	replace_slot(slot, NULL, node, -1, exceptional);
+	replace_slot(slot, NULL, node, -1, values);
 	return node && delete_node(root, node, NULL);
 }
 
diff --git a/mm/workingset.c b/mm/workingset.c
index bb109b3afac2..c201cbb8c00f 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -349,7 +349,7 @@ void workingset_update_node(struct radix_tree_node *node)
 	 * already where they should be. The list_empty() test is safe
 	 * as node->private_list is protected by the i_pages lock.
 	 */
-	if (node->count && node->count == node->exceptional) {
+	if (node->count && node->count == node->nr_values) {
 		if (list_empty(&node->private_list))
 			list_lru_add(&shadow_nodes, &node->private_list);
 	} else {
@@ -428,8 +428,8 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 	 * to reclaim, take the node off-LRU, and drop the lru_lock.
 	 */
 
-	node = container_of(item, struct radix_tree_node, private_list);
-	mapping = container_of(node->root, struct address_space, i_pages);
+	node = container_of(item, struct xa_node, private_list);
+	mapping = container_of(node->array, struct address_space, i_pages);
 
 	/* Coming from the list, invert the lock order */
 	if (!xa_trylock(&mapping->i_pages)) {
@@ -446,25 +446,25 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 	 * no pages, so we expect to be able to remove them all and
 	 * delete and free the empty node afterwards.
 	 */
-	if (WARN_ON_ONCE(!node->exceptional))
+	if (WARN_ON_ONCE(!node->nr_values))
 		goto out_invalid;
-	if (WARN_ON_ONCE(node->count != node->exceptional))
+	if (WARN_ON_ONCE(node->count != node->nr_values))
 		goto out_invalid;
 	for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
 		if (node->slots[i]) {
 			if (WARN_ON_ONCE(!xa_is_value(node->slots[i])))
 				goto out_invalid;
-			if (WARN_ON_ONCE(!node->exceptional))
+			if (WARN_ON_ONCE(!node->nr_values))
 				goto out_invalid;
 			if (WARN_ON_ONCE(!mapping->nrexceptional))
 				goto out_invalid;
 			node->slots[i] = NULL;
-			node->exceptional--;
+			node->nr_values--;
 			node->count--;
 			mapping->nrexceptional--;
 		}
 	}
-	if (WARN_ON_ONCE(node->exceptional))
+	if (WARN_ON_ONCE(node->nr_values))
 		goto out_invalid;
 	inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM);
 	__radix_tree_delete_node(&mapping->i_pages, node,
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 080aea450430..60786fa55302 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -393,7 +393,7 @@ static void multiorder_join2(unsigned order1, unsigned order2)
 	radix_tree_insert(&tree, 1 << order2, xa_mk_value(5));
 	item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL);
 	assert(item2 == xa_mk_value(5));
-	assert(node->exceptional == 1);
+	assert(node->nr_values == 1);
 
 	item2 = radix_tree_lookup(&tree, 0);
 	free(item2);
@@ -401,7 +401,7 @@ static void multiorder_join2(unsigned order1, unsigned order2)
 	radix_tree_join(&tree, 0, order1, item1);
 	item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL);
 	assert(item2 == item1);
-	assert(node->exceptional == 0);
+	assert(node->nr_values == 0);
 	item_kill_tree(&tree);
 }
 
@@ -409,7 +409,7 @@ static void multiorder_join2(unsigned order1, unsigned order2)
  * This test revealed an accounting bug for value entries at one point.
  * Nodes were being freed back into the pool with an elevated exception count
  * by radix_tree_join() and then radix_tree_split() was failing to zero the
- * count of exceptional entries.
+ * count of value entries.
  */
 static void multiorder_join3(unsigned int order)
 {
@@ -433,7 +433,7 @@ static void multiorder_join3(unsigned int order)
 	}
 
 	__radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(node->exceptional == node->count);
+	assert(node->nr_values == node->count);
 
 	item_kill_tree(&tree);
 }
@@ -520,7 +520,7 @@ static void __multiorder_split2(int old_order, int new_order)
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
 	assert(item == xa_mk_value(5));
-	assert(node->exceptional > 0);
+	assert(node->nr_values > 0);
 
 	radix_tree_split(&tree, 0, new_order);
 	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
@@ -530,7 +530,7 @@ static void __multiorder_split2(int old_order, int new_order)
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
 	assert(item != xa_mk_value(5));
-	assert(node->exceptional == 0);
+	assert(node->nr_values == 0);
 
 	item_kill_tree(&tree);
 }
@@ -547,7 +547,7 @@ static void __multiorder_split3(int old_order, int new_order)
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
 	assert(item == xa_mk_value(5));
-	assert(node->exceptional > 0);
+	assert(node->nr_values > 0);
 
 	radix_tree_split(&tree, 0, new_order);
 	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
@@ -556,7 +556,7 @@ static void __multiorder_split3(int old_order, int new_order)
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
 	assert(item == xa_mk_value(7));
-	assert(node->exceptional > 0);
+	assert(node->nr_values > 0);
 
 	item_kill_tree(&tree);
 
@@ -564,7 +564,7 @@ static void __multiorder_split3(int old_order, int new_order)
 
 	item = __radix_tree_lookup(&tree, 0, &node, NULL);
 	assert(item == xa_mk_value(5));
-	assert(node->exceptional > 0);
+	assert(node->nr_values > 0);
 
 	radix_tree_split(&tree, 0, new_order);
 	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
@@ -577,13 +577,13 @@ static void __multiorder_split3(int old_order, int new_order)
 
 	item = __radix_tree_lookup(&tree, 1 << new_order, &node, NULL);
 	assert(item == xa_mk_value(7));
-	assert(node->count == node->exceptional);
+	assert(node->count == node->nr_values);
 	do {
 		node = node->parent;
 		if (!node)
 			break;
 		assert(node->count == 1);
-		assert(node->exceptional == 0);
+		assert(node->nr_values == 0);
 	} while (1);
 
 	item_kill_tree(&tree);
@@ -611,15 +611,15 @@ static void multiorder_account(void)
 
 	__radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5));
 	__radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(node->count == node->exceptional * 2);
+	assert(node->count == node->nr_values * 2);
 	radix_tree_delete(&tree, 1 << 5);
-	assert(node->exceptional == 0);
+	assert(node->nr_values == 0);
 
 	__radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5));
 	__radix_tree_lookup(&tree, 1 << 5, &node, &slot);
-	assert(node->count == node->exceptional * 2);
+	assert(node->count == node->nr_values * 2);
 	__radix_tree_replace(&tree, node, slot, NULL, NULL);
-	assert(node->exceptional == 0);
+	assert(node->nr_values == 0);
 
 	item_kill_tree(&tree);
 }
-- 
cgit v1.2.3


From ad3d6c7263e368abdc151e1cc13dc78aa39cc7a7 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 7 Nov 2017 14:57:46 -0500
Subject: xarray: Add XArray load operation

The xa_load function brings with it a lot of infrastructure; xa_empty(),
xa_is_err(), and large chunks of the XArray advanced API that are used
to implement xa_load.

As the test-suite demonstrates, it is possible to use the XArray functions
on a radix tree.  The radix tree functions depend on the GFP flags being
stored in the root of the tree, so it's not possible to use the radix
tree functions on an XArray.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/xarray.h                    | 336 ++++++++++++++++++++++++++++++
 lib/Kconfig.debug                         |   3 +
 lib/Makefile                              |   1 +
 lib/radix-tree.c                          |  43 ----
 lib/test_xarray.c                         |  87 ++++++++
 lib/xarray.c                              | 195 +++++++++++++++++
 tools/include/linux/kernel.h              |   1 +
 tools/testing/radix-tree/.gitignore       |   1 +
 tools/testing/radix-tree/Makefile         |   6 +-
 tools/testing/radix-tree/linux/kernel.h   |   1 +
 tools/testing/radix-tree/linux/rcupdate.h |   2 +
 tools/testing/radix-tree/main.c           |   1 +
 tools/testing/radix-tree/test.h           |   1 +
 tools/testing/radix-tree/xarray.c         |  28 +++
 14 files changed, 661 insertions(+), 45 deletions(-)
 create mode 100644 lib/test_xarray.c

(limited to 'tools')

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 52141dfc5a90..a0df8217068c 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -12,6 +12,8 @@
 #include <linux/bug.h>
 #include <linux/compiler.h>
 #include <linux/kconfig.h>
+#include <linux/kernel.h>
+#include <linux/rcupdate.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
 
@@ -30,6 +32,10 @@
  *
  * 0-62: Sibling entries
  * 256: Retry entry
+ *
+ * Errors are also represented as internal entries, but use the negative
+ * space (-4094 to -2).  They're never stored in the slots array; only
+ * returned by the normal API.
  */
 
 #define BITS_PER_XA_VALUE	(BITS_PER_LONG - 1)
@@ -155,6 +161,42 @@ static inline bool xa_is_internal(const void *entry)
 	return ((unsigned long)entry & 3) == 2;
 }
 
+/**
+ * xa_is_err() - Report whether an XArray operation returned an error
+ * @entry: Result from calling an XArray function
+ *
+ * If an XArray operation cannot complete an operation, it will return
+ * a special value indicating an error.  This function tells you
+ * whether an error occurred; xa_err() tells you which error occurred.
+ *
+ * Context: Any context.
+ * Return: %true if the entry indicates an error.
+ */
+static inline bool xa_is_err(const void *entry)
+{
+	return unlikely(xa_is_internal(entry));
+}
+
+/**
+ * xa_err() - Turn an XArray result into an errno.
+ * @entry: Result from calling an XArray function.
+ *
+ * If an XArray operation cannot complete an operation, it will return
+ * a special pointer value which encodes an errno.  This function extracts
+ * the errno from the pointer value, or returns 0 if the pointer does not
+ * represent an errno.
+ *
+ * Context: Any context.
+ * Return: A negative errno or 0.
+ */
+static inline int xa_err(void *entry)
+{
+	/* xa_to_internal() would not do sign extension. */
+	if (xa_is_err(entry))
+		return (long)entry >> 2;
+	return 0;
+}
+
 /**
  * struct xarray - The anchor of the XArray.
  * @xa_lock: Lock that protects the contents of the XArray.
@@ -209,6 +251,7 @@ struct xarray {
 #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0)
 
 void xa_init_flags(struct xarray *, gfp_t flags);
+void *xa_load(struct xarray *, unsigned long index);
 
 /**
  * xa_init() - Initialise an empty XArray.
@@ -223,6 +266,18 @@ static inline void xa_init(struct xarray *xa)
 	xa_init_flags(xa, 0);
 }
 
+/**
+ * xa_empty() - Determine if an array has any present entries.
+ * @xa: XArray.
+ *
+ * Context: Any context.
+ * Return: %true if the array contains only NULL pointers.
+ */
+static inline bool xa_empty(const struct xarray *xa)
+{
+	return xa->xa_head == NULL;
+}
+
 #define xa_trylock(xa)		spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)		spin_lock(&(xa)->xa_lock)
 #define xa_unlock(xa)		spin_unlock(&(xa)->xa_lock)
@@ -280,6 +335,65 @@ struct xa_node {
 	};
 };
 
+void xa_dump(const struct xarray *);
+void xa_dump_node(const struct xa_node *);
+
+#ifdef XA_DEBUG
+#define XA_BUG_ON(xa, x) do {					\
+		if (x) {					\
+			xa_dump(xa);				\
+			BUG();					\
+		}						\
+	} while (0)
+#define XA_NODE_BUG_ON(node, x) do {				\
+		if (x) {					\
+			if (node) xa_dump_node(node);		\
+			BUG();					\
+		}						\
+	} while (0)
+#else
+#define XA_BUG_ON(xa, x)	do { } while (0)
+#define XA_NODE_BUG_ON(node, x)	do { } while (0)
+#endif
+
+/* Private */
+static inline void *xa_head(const struct xarray *xa)
+{
+	return rcu_dereference_check(xa->xa_head,
+						lockdep_is_held(&xa->xa_lock));
+}
+
+/* Private */
+static inline void *xa_head_locked(const struct xarray *xa)
+{
+	return rcu_dereference_protected(xa->xa_head,
+						lockdep_is_held(&xa->xa_lock));
+}
+
+/* Private */
+static inline void *xa_entry(const struct xarray *xa,
+				const struct xa_node *node, unsigned int offset)
+{
+	XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE);
+	return rcu_dereference_check(node->slots[offset],
+						lockdep_is_held(&xa->xa_lock));
+}
+
+/* Private */
+static inline void *xa_entry_locked(const struct xarray *xa,
+				const struct xa_node *node, unsigned int offset)
+{
+	XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE);
+	return rcu_dereference_protected(node->slots[offset],
+						lockdep_is_held(&xa->xa_lock));
+}
+
+/* Private */
+static inline struct xa_node *xa_to_node(const void *entry)
+{
+	return (struct xa_node *)((unsigned long)entry - 2);
+}
+
 /* Private */
 static inline bool xa_is_node(const void *entry)
 {
@@ -312,4 +426,226 @@ static inline bool xa_is_sibling(const void *entry)
 
 #define XA_RETRY_ENTRY		xa_mk_internal(256)
 
+/**
+ * xa_is_retry() - Is the entry a retry entry?
+ * @entry: Entry retrieved from the XArray
+ *
+ * Return: %true if the entry is a retry entry.
+ */
+static inline bool xa_is_retry(const void *entry)
+{
+	return unlikely(entry == XA_RETRY_ENTRY);
+}
+
+/**
+ * typedef xa_update_node_t - A callback function from the XArray.
+ * @node: The node which is being processed
+ *
+ * This function is called every time the XArray updates the count of
+ * present and value entries in a node.  It allows advanced users to
+ * maintain the private_list in the node.
+ *
+ * Context: The xa_lock is held and interrupts may be disabled.
+ *	    Implementations should not drop the xa_lock, nor re-enable
+ *	    interrupts.
+ */
+typedef void (*xa_update_node_t)(struct xa_node *node);
+
+/*
+ * The xa_state is opaque to its users.  It contains various different pieces
+ * of state involved in the current operation on the XArray.  It should be
+ * declared on the stack and passed between the various internal routines.
+ * The various elements in it should not be accessed directly, but only
+ * through the provided accessor functions.  The below documentation is for
+ * the benefit of those working on the code, not for users of the XArray.
+ *
+ * @xa_node usually points to the xa_node containing the slot we're operating
+ * on (and @xa_offset is the offset in the slots array).  If there is a
+ * single entry in the array at index 0, there are no allocated xa_nodes to
+ * point to, and so we store %NULL in @xa_node.  @xa_node is set to
+ * the value %XAS_RESTART if the xa_state is not walked to the correct
+ * position in the tree of nodes for this operation.  If an error occurs
+ * during an operation, it is set to an %XAS_ERROR value.  If we run off the
+ * end of the allocated nodes, it is set to %XAS_BOUNDS.
+ */
+struct xa_state {
+	struct xarray *xa;
+	unsigned long xa_index;
+	unsigned char xa_shift;
+	unsigned char xa_sibs;
+	unsigned char xa_offset;
+	unsigned char xa_pad;		/* Helps gcc generate better code */
+	struct xa_node *xa_node;
+	struct xa_node *xa_alloc;
+	xa_update_node_t xa_update;
+};
+
+/*
+ * We encode errnos in the xas->xa_node.  If an error has happened, we need to
+ * drop the lock to fix it, and once we've done so the xa_state is invalid.
+ */
+#define XA_ERROR(errno) ((struct xa_node *)(((unsigned long)errno << 2) | 2UL))
+#define XAS_BOUNDS	((struct xa_node *)1UL)
+#define XAS_RESTART	((struct xa_node *)3UL)
+
+#define __XA_STATE(array, index, shift, sibs)  {	\
+	.xa = array,					\
+	.xa_index = index,				\
+	.xa_shift = shift,				\
+	.xa_sibs = sibs,				\
+	.xa_offset = 0,					\
+	.xa_pad = 0,					\
+	.xa_node = XAS_RESTART,				\
+	.xa_alloc = NULL,				\
+	.xa_update = NULL				\
+}
+
+/**
+ * XA_STATE() - Declare an XArray operation state.
+ * @name: Name of this operation state (usually xas).
+ * @array: Array to operate on.
+ * @index: Initial index of interest.
+ *
+ * Declare and initialise an xa_state on the stack.
+ */
+#define XA_STATE(name, array, index)				\
+	struct xa_state name = __XA_STATE(array, index, 0, 0)
+
+/**
+ * XA_STATE_ORDER() - Declare an XArray operation state.
+ * @name: Name of this operation state (usually xas).
+ * @array: Array to operate on.
+ * @index: Initial index of interest.
+ * @order: Order of entry.
+ *
+ * Declare and initialise an xa_state on the stack.  This variant of
+ * XA_STATE() allows you to specify the 'order' of the element you
+ * want to operate on.`
+ */
+#define XA_STATE_ORDER(name, array, index, order)		\
+	struct xa_state name = __XA_STATE(array,		\
+			(index >> order) << order,		\
+			order - (order % XA_CHUNK_SHIFT),	\
+			(1U << (order % XA_CHUNK_SHIFT)) - 1)
+
+#define xas_marked(xas, mark)	xa_marked((xas)->xa, (mark))
+#define xas_trylock(xas)	xa_trylock((xas)->xa)
+#define xas_lock(xas)		xa_lock((xas)->xa)
+#define xas_unlock(xas)		xa_unlock((xas)->xa)
+#define xas_lock_bh(xas)	xa_lock_bh((xas)->xa)
+#define xas_unlock_bh(xas)	xa_unlock_bh((xas)->xa)
+#define xas_lock_irq(xas)	xa_lock_irq((xas)->xa)
+#define xas_unlock_irq(xas)	xa_unlock_irq((xas)->xa)
+#define xas_lock_irqsave(xas, flags) \
+				xa_lock_irqsave((xas)->xa, flags)
+#define xas_unlock_irqrestore(xas, flags) \
+				xa_unlock_irqrestore((xas)->xa, flags)
+
+/**
+ * xas_error() - Return an errno stored in the xa_state.
+ * @xas: XArray operation state.
+ *
+ * Return: 0 if no error has been noted.  A negative errno if one has.
+ */
+static inline int xas_error(const struct xa_state *xas)
+{
+	return xa_err(xas->xa_node);
+}
+
+/**
+ * xas_set_err() - Note an error in the xa_state.
+ * @xas: XArray operation state.
+ * @err: Negative error number.
+ *
+ * Only call this function with a negative @err; zero or positive errors
+ * will probably not behave the way you think they should.  If you want
+ * to clear the error from an xa_state, use xas_reset().
+ */
+static inline void xas_set_err(struct xa_state *xas, long err)
+{
+	xas->xa_node = XA_ERROR(err);
+}
+
+/**
+ * xas_invalid() - Is the xas in a retry or error state?
+ * @xas: XArray operation state.
+ *
+ * Return: %true if the xas cannot be used for operations.
+ */
+static inline bool xas_invalid(const struct xa_state *xas)
+{
+	return (unsigned long)xas->xa_node & 3;
+}
+
+/**
+ * xas_valid() - Is the xas a valid cursor into the array?
+ * @xas: XArray operation state.
+ *
+ * Return: %true if the xas can be used for operations.
+ */
+static inline bool xas_valid(const struct xa_state *xas)
+{
+	return !xas_invalid(xas);
+}
+
+/**
+ * xas_reset() - Reset an XArray operation state.
+ * @xas: XArray operation state.
+ *
+ * Resets the error or walk state of the @xas so future walks of the
+ * array will start from the root.  Use this if you have dropped the
+ * xarray lock and want to reuse the xa_state.
+ *
+ * Context: Any context.
+ */
+static inline void xas_reset(struct xa_state *xas)
+{
+	xas->xa_node = XAS_RESTART;
+}
+
+/**
+ * xas_retry() - Retry the operation if appropriate.
+ * @xas: XArray operation state.
+ * @entry: Entry from xarray.
+ *
+ * The advanced functions may sometimes return an internal entry, such as
+ * a retry entry or a zero entry.  This function sets up the @xas to restart
+ * the walk from the head of the array if needed.
+ *
+ * Context: Any context.
+ * Return: true if the operation needs to be retried.
+ */
+static inline bool xas_retry(struct xa_state *xas, const void *entry)
+{
+	if (!xa_is_retry(entry))
+		return false;
+	xas_reset(xas);
+	return true;
+}
+
+void *xas_load(struct xa_state *);
+
+/**
+ * xas_reload() - Refetch an entry from the xarray.
+ * @xas: XArray operation state.
+ *
+ * Use this function to check that a previously loaded entry still has
+ * the same value.  This is useful for the lockless pagecache lookup where
+ * we walk the array with only the RCU lock to protect us, lock the page,
+ * then check that the page hasn't moved since we looked it up.
+ *
+ * The caller guarantees that @xas is still valid.  If it may be in an
+ * error or restart state, call xas_load() instead.
+ *
+ * Return: The entry at this location in the xarray.
+ */
+static inline void *xas_reload(struct xa_state *xas)
+{
+	struct xa_node *node = xas->xa_node;
+
+	if (node)
+		return xa_entry(xas->xa, node, xas->xa_offset);
+	return xa_head(xas->xa);
+}
+
 #endif /* _LINUX_XARRAY_H */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 4966c4fbe7f7..091155e12422 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1813,6 +1813,9 @@ config TEST_BITFIELD
 config TEST_UUID
 	tristate "Test functions located in the uuid module at runtime"
 
+config TEST_XARRAY
+	tristate "Test the XArray code at runtime"
+
 config TEST_OVERFLOW
 	tristate "Test check_*_overflow() functions at runtime"
 
diff --git a/lib/Makefile b/lib/Makefile
index 057385f1f145..e6f809556af5 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -68,6 +68,7 @@ obj-$(CONFIG_TEST_PRINTF) += test_printf.o
 obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o
 obj-$(CONFIG_TEST_BITFIELD) += test_bitfield.o
 obj-$(CONFIG_TEST_UUID) += test_uuid.o
+obj-$(CONFIG_TEST_XARRAY) += test_xarray.o
 obj-$(CONFIG_TEST_PARMAN) += test_parman.o
 obj-$(CONFIG_TEST_KMOD) += test_kmod.o
 obj-$(CONFIG_TEST_DEBUG_VIRTUAL) += test_debug_virtual.o
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 8a568cea1237..b8e961428484 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -256,49 +256,6 @@ static unsigned long next_index(unsigned long index,
 }
 
 #ifndef __KERNEL__
-static void dump_node(struct radix_tree_node *node, unsigned long index)
-{
-	unsigned long i;
-
-	pr_debug("radix node: %p offset %d indices %lu-%lu parent %p tags %lx %lx %lx shift %d count %d nr_values %d\n",
-		node, node->offset, index, index | node_maxindex(node),
-		node->parent,
-		node->tags[0][0], node->tags[1][0], node->tags[2][0],
-		node->shift, node->count, node->nr_values);
-
-	for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
-		unsigned long first = index | (i << node->shift);
-		unsigned long last = first | ((1UL << node->shift) - 1);
-		void *entry = node->slots[i];
-		if (!entry)
-			continue;
-		if (entry == RADIX_TREE_RETRY) {
-			pr_debug("radix retry offset %ld indices %lu-%lu parent %p\n",
-					i, first, last, node);
-		} else if (!radix_tree_is_internal_node(entry)) {
-			pr_debug("radix entry %p offset %ld indices %lu-%lu parent %p\n",
-					entry, i, first, last, node);
-		} else if (xa_is_sibling(entry)) {
-			pr_debug("radix sblng %p offset %ld indices %lu-%lu parent %p val %p\n",
-					entry, i, first, last, node,
-					node->slots[xa_to_sibling(entry)]);
-		} else {
-			dump_node(entry_to_node(entry), first);
-		}
-	}
-}
-
-/* For debug */
-static void radix_tree_dump(struct radix_tree_root *root)
-{
-	pr_debug("radix root: %p xa_head %p tags %x\n",
-			root, root->xa_head,
-			root->xa_flags >> ROOT_TAG_SHIFT);
-	if (!radix_tree_is_internal_node(root->xa_head))
-		return;
-	dump_node(entry_to_node(root->xa_head), 0);
-}
-
 static void dump_ida_node(void *entry, unsigned long index)
 {
 	unsigned long i;
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
new file mode 100644
index 000000000000..a7248b87617f
--- /dev/null
+++ b/lib/test_xarray.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * test_xarray.c: Test the XArray API
+ * Copyright (c) 2017-2018 Microsoft Corporation
+ * Author: Matthew Wilcox <willy@infradead.org>
+ */
+
+#include <linux/xarray.h>
+#include <linux/module.h>
+
+static unsigned int tests_run;
+static unsigned int tests_passed;
+
+#ifndef XA_DEBUG
+# ifdef __KERNEL__
+void xa_dump(const struct xarray *xa) { }
+# endif
+#undef XA_BUG_ON
+#define XA_BUG_ON(xa, x) do {					\
+	tests_run++;						\
+	if (x) {						\
+		printk("BUG at %s:%d\n", __func__, __LINE__);	\
+		xa_dump(xa);					\
+		dump_stack();					\
+	} else {						\
+		tests_passed++;					\
+	}							\
+} while (0)
+#endif
+
+static void *xa_store_index(struct xarray *xa, unsigned long index, gfp_t gfp)
+{
+	radix_tree_insert(xa, index, xa_mk_value(index));
+	return NULL;
+}
+
+static void xa_erase_index(struct xarray *xa, unsigned long index)
+{
+	radix_tree_delete(xa, index);
+}
+
+static noinline void check_xa_load(struct xarray *xa)
+{
+	unsigned long i, j;
+
+	for (i = 0; i < 1024; i++) {
+		for (j = 0; j < 1024; j++) {
+			void *entry = xa_load(xa, j);
+			if (j < i)
+				XA_BUG_ON(xa, xa_to_value(entry) != j);
+			else
+				XA_BUG_ON(xa, entry);
+		}
+		XA_BUG_ON(xa, xa_store_index(xa, i, GFP_KERNEL) != NULL);
+	}
+
+	for (i = 0; i < 1024; i++) {
+		for (j = 0; j < 1024; j++) {
+			void *entry = xa_load(xa, j);
+			if (j >= i)
+				XA_BUG_ON(xa, xa_to_value(entry) != j);
+			else
+				XA_BUG_ON(xa, entry);
+		}
+		xa_erase_index(xa, i);
+	}
+	XA_BUG_ON(xa, !xa_empty(xa));
+}
+
+static RADIX_TREE(array, GFP_KERNEL);
+
+static int xarray_checks(void)
+{
+	check_xa_load(&array);
+
+	printk("XArray: %u of %u tests passed\n", tests_passed, tests_run);
+	return (tests_run == tests_passed) ? 0 : -EINVAL;
+}
+
+static void xarray_exit(void)
+{
+}
+
+module_init(xarray_checks);
+module_exit(xarray_exit);
+MODULE_AUTHOR("Matthew Wilcox <willy@infradead.org>");
+MODULE_LICENSE("GPL");
diff --git a/lib/xarray.c b/lib/xarray.c
index 862f4c64c754..19cfcbc69a68 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -24,6 +24,100 @@
  * @entry refers to something stored in a slot in the xarray
  */
 
+/* extracts the offset within this node from the index */
+static unsigned int get_offset(unsigned long index, struct xa_node *node)
+{
+	return (index >> node->shift) & XA_CHUNK_MASK;
+}
+
+/* move the index either forwards (find) or backwards (sibling slot) */
+static void xas_move_index(struct xa_state *xas, unsigned long offset)
+{
+	unsigned int shift = xas->xa_node->shift;
+	xas->xa_index &= ~XA_CHUNK_MASK << shift;
+	xas->xa_index += offset << shift;
+}
+
+static void *set_bounds(struct xa_state *xas)
+{
+	xas->xa_node = XAS_BOUNDS;
+	return NULL;
+}
+
+/*
+ * Starts a walk.  If the @xas is already valid, we assume that it's on
+ * the right path and just return where we've got to.  If we're in an
+ * error state, return NULL.  If the index is outside the current scope
+ * of the xarray, return NULL without changing @xas->xa_node.  Otherwise
+ * set @xas->xa_node to NULL and return the current head of the array.
+ */
+static void *xas_start(struct xa_state *xas)
+{
+	void *entry;
+
+	if (xas_valid(xas))
+		return xas_reload(xas);
+	if (xas_error(xas))
+		return NULL;
+
+	entry = xa_head(xas->xa);
+	if (!xa_is_node(entry)) {
+		if (xas->xa_index)
+			return set_bounds(xas);
+	} else {
+		if ((xas->xa_index >> xa_to_node(entry)->shift) > XA_CHUNK_MASK)
+			return set_bounds(xas);
+	}
+
+	xas->xa_node = NULL;
+	return entry;
+}
+
+static void *xas_descend(struct xa_state *xas, struct xa_node *node)
+{
+	unsigned int offset = get_offset(xas->xa_index, node);
+	void *entry = xa_entry(xas->xa, node, offset);
+
+	xas->xa_node = node;
+	if (xa_is_sibling(entry)) {
+		offset = xa_to_sibling(entry);
+		entry = xa_entry(xas->xa, node, offset);
+	}
+
+	xas->xa_offset = offset;
+	return entry;
+}
+
+/**
+ * xas_load() - Load an entry from the XArray (advanced).
+ * @xas: XArray operation state.
+ *
+ * Usually walks the @xas to the appropriate state to load the entry
+ * stored at xa_index.  However, it will do nothing and return %NULL if
+ * @xas is in an error state.  xas_load() will never expand the tree.
+ *
+ * If the xa_state is set up to operate on a multi-index entry, xas_load()
+ * may return %NULL or an internal entry, even if there are entries
+ * present within the range specified by @xas.
+ *
+ * Context: Any context.  The caller should hold the xa_lock or the RCU lock.
+ * Return: Usually an entry in the XArray, but see description for exceptions.
+ */
+void *xas_load(struct xa_state *xas)
+{
+	void *entry = xas_start(xas);
+
+	while (xa_is_node(entry)) {
+		struct xa_node *node = xa_to_node(entry);
+
+		if (xas->xa_shift > node->shift)
+			break;
+		entry = xas_descend(xas, node);
+	}
+	return entry;
+}
+EXPORT_SYMBOL_GPL(xas_load);
+
 /**
  * xa_init_flags() - Initialise an empty XArray with flags.
  * @xa: XArray.
@@ -42,3 +136,104 @@ void xa_init_flags(struct xarray *xa, gfp_t flags)
 	xa->xa_head = NULL;
 }
 EXPORT_SYMBOL(xa_init_flags);
+
+/**
+ * xa_load() - Load an entry from an XArray.
+ * @xa: XArray.
+ * @index: index into array.
+ *
+ * Context: Any context.  Takes and releases the RCU lock.
+ * Return: The entry at @index in @xa.
+ */
+void *xa_load(struct xarray *xa, unsigned long index)
+{
+	XA_STATE(xas, xa, index);
+	void *entry;
+
+	rcu_read_lock();
+	do {
+		entry = xas_load(&xas);
+	} while (xas_retry(&xas, entry));
+	rcu_read_unlock();
+
+	return entry;
+}
+EXPORT_SYMBOL(xa_load);
+
+#ifdef XA_DEBUG
+void xa_dump_node(const struct xa_node *node)
+{
+	unsigned i, j;
+
+	if (!node)
+		return;
+	if ((unsigned long)node & 3) {
+		pr_cont("node %px\n", node);
+		return;
+	}
+
+	pr_cont("node %px %s %d parent %px shift %d count %d values %d "
+		"array %px list %px %px marks",
+		node, node->parent ? "offset" : "max", node->offset,
+		node->parent, node->shift, node->count, node->nr_values,
+		node->array, node->private_list.prev, node->private_list.next);
+	for (i = 0; i < XA_MAX_MARKS; i++)
+		for (j = 0; j < XA_MARK_LONGS; j++)
+			pr_cont(" %lx", node->marks[i][j]);
+	pr_cont("\n");
+}
+
+void xa_dump_index(unsigned long index, unsigned int shift)
+{
+	if (!shift)
+		pr_info("%lu: ", index);
+	else if (shift >= BITS_PER_LONG)
+		pr_info("0-%lu: ", ~0UL);
+	else
+		pr_info("%lu-%lu: ", index, index | ((1UL << shift) - 1));
+}
+
+void xa_dump_entry(const void *entry, unsigned long index, unsigned long shift)
+{
+	if (!entry)
+		return;
+
+	xa_dump_index(index, shift);
+
+	if (xa_is_node(entry)) {
+		if (shift == 0) {
+			pr_cont("%px\n", entry);
+		} else {
+			unsigned long i;
+			struct xa_node *node = xa_to_node(entry);
+			xa_dump_node(node);
+			for (i = 0; i < XA_CHUNK_SIZE; i++)
+				xa_dump_entry(node->slots[i],
+				      index + (i << node->shift), node->shift);
+		}
+	} else if (xa_is_value(entry))
+		pr_cont("value %ld (0x%lx) [%px]\n", xa_to_value(entry),
+						xa_to_value(entry), entry);
+	else if (!xa_is_internal(entry))
+		pr_cont("%px\n", entry);
+	else if (xa_is_retry(entry))
+		pr_cont("retry (%ld)\n", xa_to_internal(entry));
+	else if (xa_is_sibling(entry))
+		pr_cont("sibling (slot %ld)\n", xa_to_sibling(entry));
+	else
+		pr_cont("UNKNOWN ENTRY (%px)\n", entry);
+}
+
+void xa_dump(const struct xarray *xa)
+{
+	void *entry = xa->xa_head;
+	unsigned int shift = 0;
+
+	pr_info("xarray: %px head %px flags %x marks %d %d %d\n", xa, entry,
+			xa->xa_flags, radix_tree_tagged(xa, 0),
+			radix_tree_tagged(xa, 1), radix_tree_tagged(xa, 2));
+	if (xa_is_node(entry))
+		shift = xa_to_node(entry)->shift + XA_CHUNK_SHIFT;
+	xa_dump_entry(entry, 0, shift);
+}
+#endif
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index 0ad884452c5c..6935ef94e77a 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -70,6 +70,7 @@
 #define BUG_ON(cond) assert(!(cond))
 #endif
 #endif
+#define BUG()	BUG_ON(1)
 
 #if __BYTE_ORDER == __BIG_ENDIAN
 #define cpu_to_le16 bswap_16
diff --git a/tools/testing/radix-tree/.gitignore b/tools/testing/radix-tree/.gitignore
index d4706c0ffceb..3834899b6693 100644
--- a/tools/testing/radix-tree/.gitignore
+++ b/tools/testing/radix-tree/.gitignore
@@ -4,3 +4,4 @@ idr-test
 main
 multiorder
 radix-tree.c
+xarray
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index c0cf1c79efd5..1379f1d78d0b 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -4,7 +4,7 @@ CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \
 	  -fsanitize=undefined
 LDFLAGS += -fsanitize=address -fsanitize=undefined
 LDLIBS+= -lpthread -lurcu
-TARGETS = main idr-test multiorder
+TARGETS = main idr-test multiorder xarray
 CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o
 OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \
 	 tag_check.o multiorder.o idr-test.o iteration_check.o benchmark.o
@@ -25,6 +25,8 @@ main:	$(OFILES)
 idr-test.o: ../../../lib/test_ida.c
 idr-test: idr-test.o $(CORE_OFILES)
 
+xarray: $(CORE_OFILES)
+
 multiorder: multiorder.o $(CORE_OFILES)
 
 clean:
@@ -45,7 +47,7 @@ radix-tree.c: ../../../lib/radix-tree.c
 idr.c: ../../../lib/idr.c
 	sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@
 
-xarray.o: ../../../lib/xarray.c
+xarray.o: ../../../lib/xarray.c ../../../lib/test_xarray.c
 
 generated/map-shift.h:
 	@if ! grep -qws $(SHIFT) generated/map-shift.h; then		\
diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h
index 426f32f28547..5d06ac75a14d 100644
--- a/tools/testing/radix-tree/linux/kernel.h
+++ b/tools/testing/radix-tree/linux/kernel.h
@@ -14,6 +14,7 @@
 #include "../../../include/linux/kconfig.h"
 
 #define printk printf
+#define pr_info printk
 #define pr_debug printk
 #define pr_cont printk
 
diff --git a/tools/testing/radix-tree/linux/rcupdate.h b/tools/testing/radix-tree/linux/rcupdate.h
index 73ed33658203..fd280b070fdb 100644
--- a/tools/testing/radix-tree/linux/rcupdate.h
+++ b/tools/testing/radix-tree/linux/rcupdate.h
@@ -6,5 +6,7 @@
 
 #define rcu_dereference_raw(p) rcu_dereference(p)
 #define rcu_dereference_protected(p, cond) rcu_dereference(p)
+#define rcu_dereference_check(p, cond) rcu_dereference(p)
+#define RCU_INIT_POINTER(p, v)	(p) = (v)
 
 #endif
diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c
index b741686e53d6..09deaf4f0959 100644
--- a/tools/testing/radix-tree/main.c
+++ b/tools/testing/radix-tree/main.c
@@ -365,6 +365,7 @@ int main(int argc, char **argv)
 	rcu_register_thread();
 	radix_tree_init();
 
+	xarray_tests();
 	regression1_test();
 	regression2_test();
 	regression3_test();
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index 92d901eacf49..e3dc7a16f09b 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -34,6 +34,7 @@ int tag_tagged_items(struct radix_tree_root *, pthread_mutex_t *,
 			unsigned iftag, unsigned thentag);
 unsigned long find_item(struct radix_tree_root *, void *item);
 
+void xarray_tests(void);
 void tag_check(void);
 void multiorder_checks(void);
 void iteration_test(unsigned order, unsigned duration);
diff --git a/tools/testing/radix-tree/xarray.c b/tools/testing/radix-tree/xarray.c
index 9bbd667172a7..e61e43efe463 100644
--- a/tools/testing/radix-tree/xarray.c
+++ b/tools/testing/radix-tree/xarray.c
@@ -4,4 +4,32 @@
  * Copyright (c) 2018 Matthew Wilcox <willy@infradead.org>
  */
 
+#define XA_DEBUG
+#include "test.h"
+
+#define module_init(x)
+#define module_exit(x)
+#define MODULE_AUTHOR(x)
+#define MODULE_LICENSE(x)
+#define dump_stack()	assert(0)
+
 #include "../../../lib/xarray.c"
+#undef XA_DEBUG
+#include "../../../lib/test_xarray.c"
+
+void xarray_tests(void)
+{
+	xarray_checks();
+	xarray_exit();
+}
+
+int __weak main(void)
+{
+	radix_tree_init();
+	xarray_tests();
+	radix_tree_cpu_dead(1);
+	rcu_barrier();
+	if (nr_allocated)
+		printf("nr_allocated = %d\n", nr_allocated);
+	return 0;
+}
-- 
cgit v1.2.3


From 9b89a0355144685a787b0dc5bcf7bdd6f2d02968 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Fri, 10 Nov 2017 09:34:31 -0500
Subject: xarray: Add XArray marks

XArray marks are like the radix tree tags, only slightly more strongly
typed.  They are renamed in order to distinguish them from tagged
pointers.  This commit adds the basic get/set/clear operations.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/xarray.h                        |  63 +++++++
 lib/test_xarray.c                             |  34 ++++
 lib/xarray.c                                  | 232 +++++++++++++++++++++++++-
 tools/include/asm-generic/bitops.h            |   1 +
 tools/include/asm-generic/bitops/atomic.h     |   9 -
 tools/include/asm-generic/bitops/non-atomic.h | 109 ++++++++++++
 tools/include/linux/spinlock.h                |  10 +-
 7 files changed, 445 insertions(+), 13 deletions(-)
 create mode 100644 tools/include/asm-generic/bitops/non-atomic.h

(limited to 'tools')

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index a0df8217068c..2de504ae9ba4 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -11,6 +11,7 @@
 
 #include <linux/bug.h>
 #include <linux/compiler.h>
+#include <linux/gfp.h>
 #include <linux/kconfig.h>
 #include <linux/kernel.h>
 #include <linux/rcupdate.h>
@@ -197,6 +198,20 @@ static inline int xa_err(void *entry)
 	return 0;
 }
 
+typedef unsigned __bitwise xa_mark_t;
+#define XA_MARK_0		((__force xa_mark_t)0U)
+#define XA_MARK_1		((__force xa_mark_t)1U)
+#define XA_MARK_2		((__force xa_mark_t)2U)
+#define XA_PRESENT		((__force xa_mark_t)8U)
+#define XA_MARK_MAX		XA_MARK_2
+
+/*
+ * Values for xa_flags.  The radix tree stores its GFP flags in the xa_flags,
+ * and we remain compatible with that.
+ */
+#define XA_FLAGS_MARK(mark)	((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \
+						(__force unsigned)(mark)))
+
 /**
  * struct xarray - The anchor of the XArray.
  * @xa_lock: Lock that protects the contents of the XArray.
@@ -252,6 +267,9 @@ struct xarray {
 
 void xa_init_flags(struct xarray *, gfp_t flags);
 void *xa_load(struct xarray *, unsigned long index);
+bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t);
+void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t);
+void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t);
 
 /**
  * xa_init() - Initialise an empty XArray.
@@ -278,6 +296,19 @@ static inline bool xa_empty(const struct xarray *xa)
 	return xa->xa_head == NULL;
 }
 
+/**
+ * xa_marked() - Inquire whether any entry in this array has a mark set
+ * @xa: Array
+ * @mark: Mark value
+ *
+ * Context: Any context.
+ * Return: %true if any entry has this mark set.
+ */
+static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark)
+{
+	return xa->xa_flags & XA_FLAGS_MARK(mark);
+}
+
 #define xa_trylock(xa)		spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)		spin_lock(&(xa)->xa_lock)
 #define xa_unlock(xa)		spin_unlock(&(xa)->xa_lock)
@@ -290,6 +321,12 @@ static inline bool xa_empty(const struct xarray *xa)
 #define xa_unlock_irqrestore(xa, flags) \
 				spin_unlock_irqrestore(&(xa)->xa_lock, flags)
 
+/*
+ * Versions of the normal API which require the caller to hold the xa_lock.
+ */
+void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t);
+void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t);
+
 /* Everything below here is the Advanced API.  Proceed with caution. */
 
 /*
@@ -388,6 +425,22 @@ static inline void *xa_entry_locked(const struct xarray *xa,
 						lockdep_is_held(&xa->xa_lock));
 }
 
+/* Private */
+static inline struct xa_node *xa_parent(const struct xarray *xa,
+					const struct xa_node *node)
+{
+	return rcu_dereference_check(node->parent,
+						lockdep_is_held(&xa->xa_lock));
+}
+
+/* Private */
+static inline struct xa_node *xa_parent_locked(const struct xarray *xa,
+					const struct xa_node *node)
+{
+	return rcu_dereference_protected(node->parent,
+						lockdep_is_held(&xa->xa_lock));
+}
+
 /* Private */
 static inline struct xa_node *xa_to_node(const void *entry)
 {
@@ -588,6 +641,12 @@ static inline bool xas_valid(const struct xa_state *xas)
 	return !xas_invalid(xas);
 }
 
+/* True if the pointer is something other than a node */
+static inline bool xas_not_node(struct xa_node *node)
+{
+	return ((unsigned long)node & 3) || !node;
+}
+
 /**
  * xas_reset() - Reset an XArray operation state.
  * @xas: XArray operation state.
@@ -625,6 +684,10 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry)
 
 void *xas_load(struct xa_state *);
 
+bool xas_get_mark(const struct xa_state *, xa_mark_t);
+void xas_set_mark(const struct xa_state *, xa_mark_t);
+void xas_clear_mark(const struct xa_state *, xa_mark_t);
+
 /**
  * xas_reload() - Refetch an entry from the xarray.
  * @xas: XArray operation state.
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index a7248b87617f..f8b0e9ba80a4 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -67,11 +67,45 @@ static noinline void check_xa_load(struct xarray *xa)
 	XA_BUG_ON(xa, !xa_empty(xa));
 }
 
+static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index)
+{
+	/* NULL elements have no marks set */
+	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
+	xa_set_mark(xa, index, XA_MARK_0);
+	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
+
+	/* Storing a pointer will not make a mark appear */
+	XA_BUG_ON(xa, xa_store_index(xa, index, GFP_KERNEL) != NULL);
+	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
+	xa_set_mark(xa, index, XA_MARK_0);
+	XA_BUG_ON(xa, !xa_get_mark(xa, index, XA_MARK_0));
+
+	/* Setting one mark will not set another mark */
+	XA_BUG_ON(xa, xa_get_mark(xa, index + 1, XA_MARK_0));
+	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_1));
+
+	/* Storing NULL clears marks, and they can't be set again */
+	xa_erase_index(xa, index);
+	XA_BUG_ON(xa, !xa_empty(xa));
+	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
+	xa_set_mark(xa, index, XA_MARK_0);
+	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
+}
+
+static noinline void check_xa_mark(struct xarray *xa)
+{
+	unsigned long index;
+
+	for (index = 0; index < 16384; index += 4)
+		check_xa_mark_1(xa, index);
+}
+
 static RADIX_TREE(array, GFP_KERNEL);
 
 static int xarray_checks(void)
 {
 	check_xa_load(&array);
+	check_xa_mark(&array);
 
 	printk("XArray: %u of %u tests passed\n", tests_passed, tests_run);
 	return (tests_run == tests_passed) ? 0 : -EINVAL;
diff --git a/lib/xarray.c b/lib/xarray.c
index 19cfcbc69a68..aa86c47e532f 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -5,6 +5,7 @@
  * Author: Matthew Wilcox <willy@infradead.org>
  */
 
+#include <linux/bitmap.h>
 #include <linux/export.h>
 #include <linux/xarray.h>
 
@@ -24,6 +25,48 @@
  * @entry refers to something stored in a slot in the xarray
  */
 
+static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark)
+{
+	if (!(xa->xa_flags & XA_FLAGS_MARK(mark)))
+		xa->xa_flags |= XA_FLAGS_MARK(mark);
+}
+
+static inline void xa_mark_clear(struct xarray *xa, xa_mark_t mark)
+{
+	if (xa->xa_flags & XA_FLAGS_MARK(mark))
+		xa->xa_flags &= ~(XA_FLAGS_MARK(mark));
+}
+
+static inline unsigned long *node_marks(struct xa_node *node, xa_mark_t mark)
+{
+	return node->marks[(__force unsigned)mark];
+}
+
+static inline bool node_get_mark(struct xa_node *node,
+		unsigned int offset, xa_mark_t mark)
+{
+	return test_bit(offset, node_marks(node, mark));
+}
+
+/* returns true if the bit was set */
+static inline bool node_set_mark(struct xa_node *node, unsigned int offset,
+				xa_mark_t mark)
+{
+	return __test_and_set_bit(offset, node_marks(node, mark));
+}
+
+/* returns true if the bit was set */
+static inline bool node_clear_mark(struct xa_node *node, unsigned int offset,
+				xa_mark_t mark)
+{
+	return __test_and_clear_bit(offset, node_marks(node, mark));
+}
+
+static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark)
+{
+	return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE);
+}
+
 /* extracts the offset within this node from the index */
 static unsigned int get_offset(unsigned long index, struct xa_node *node)
 {
@@ -118,6 +161,85 @@ void *xas_load(struct xa_state *xas)
 }
 EXPORT_SYMBOL_GPL(xas_load);
 
+/**
+ * xas_get_mark() - Returns the state of this mark.
+ * @xas: XArray operation state.
+ * @mark: Mark number.
+ *
+ * Return: true if the mark is set, false if the mark is clear or @xas
+ * is in an error state.
+ */
+bool xas_get_mark(const struct xa_state *xas, xa_mark_t mark)
+{
+	if (xas_invalid(xas))
+		return false;
+	if (!xas->xa_node)
+		return xa_marked(xas->xa, mark);
+	return node_get_mark(xas->xa_node, xas->xa_offset, mark);
+}
+EXPORT_SYMBOL_GPL(xas_get_mark);
+
+/**
+ * xas_set_mark() - Sets the mark on this entry and its parents.
+ * @xas: XArray operation state.
+ * @mark: Mark number.
+ *
+ * Sets the specified mark on this entry, and walks up the tree setting it
+ * on all the ancestor entries.  Does nothing if @xas has not been walked to
+ * an entry, or is in an error state.
+ */
+void xas_set_mark(const struct xa_state *xas, xa_mark_t mark)
+{
+	struct xa_node *node = xas->xa_node;
+	unsigned int offset = xas->xa_offset;
+
+	if (xas_invalid(xas))
+		return;
+
+	while (node) {
+		if (node_set_mark(node, offset, mark))
+			return;
+		offset = node->offset;
+		node = xa_parent_locked(xas->xa, node);
+	}
+
+	if (!xa_marked(xas->xa, mark))
+		xa_mark_set(xas->xa, mark);
+}
+EXPORT_SYMBOL_GPL(xas_set_mark);
+
+/**
+ * xas_clear_mark() - Clears the mark on this entry and its parents.
+ * @xas: XArray operation state.
+ * @mark: Mark number.
+ *
+ * Clears the specified mark on this entry, and walks back to the head
+ * attempting to clear it on all the ancestor entries.  Does nothing if
+ * @xas has not been walked to an entry, or is in an error state.
+ */
+void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark)
+{
+	struct xa_node *node = xas->xa_node;
+	unsigned int offset = xas->xa_offset;
+
+	if (xas_invalid(xas))
+		return;
+
+	while (node) {
+		if (!node_clear_mark(node, offset, mark))
+			return;
+		if (node_any_mark(node, mark))
+			return;
+
+		offset = node->offset;
+		node = xa_parent_locked(xas->xa, node);
+	}
+
+	if (xa_marked(xas->xa, mark))
+		xa_mark_clear(xas->xa, mark);
+}
+EXPORT_SYMBOL_GPL(xas_clear_mark);
+
 /**
  * xa_init_flags() - Initialise an empty XArray with flags.
  * @xa: XArray.
@@ -160,6 +282,112 @@ void *xa_load(struct xarray *xa, unsigned long index)
 }
 EXPORT_SYMBOL(xa_load);
 
+/**
+ * __xa_set_mark() - Set this mark on this entry while locked.
+ * @xa: XArray.
+ * @index: Index of entry.
+ * @mark: Mark number.
+ *
+ * Attempting to set a mark on a NULL entry does not succeed.
+ *
+ * Context: Any context.  Expects xa_lock to be held on entry.
+ */
+void __xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
+{
+	XA_STATE(xas, xa, index);
+	void *entry = xas_load(&xas);
+
+	if (entry)
+		xas_set_mark(&xas, mark);
+}
+EXPORT_SYMBOL_GPL(__xa_set_mark);
+
+/**
+ * __xa_clear_mark() - Clear this mark on this entry while locked.
+ * @xa: XArray.
+ * @index: Index of entry.
+ * @mark: Mark number.
+ *
+ * Context: Any context.  Expects xa_lock to be held on entry.
+ */
+void __xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
+{
+	XA_STATE(xas, xa, index);
+	void *entry = xas_load(&xas);
+
+	if (entry)
+		xas_clear_mark(&xas, mark);
+}
+EXPORT_SYMBOL_GPL(__xa_clear_mark);
+
+/**
+ * xa_get_mark() - Inquire whether this mark is set on this entry.
+ * @xa: XArray.
+ * @index: Index of entry.
+ * @mark: Mark number.
+ *
+ * This function uses the RCU read lock, so the result may be out of date
+ * by the time it returns.  If you need the result to be stable, use a lock.
+ *
+ * Context: Any context.  Takes and releases the RCU lock.
+ * Return: True if the entry at @index has this mark set, false if it doesn't.
+ */
+bool xa_get_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
+{
+	XA_STATE(xas, xa, index);
+	void *entry;
+
+	rcu_read_lock();
+	entry = xas_start(&xas);
+	while (xas_get_mark(&xas, mark)) {
+		if (!xa_is_node(entry))
+			goto found;
+		entry = xas_descend(&xas, xa_to_node(entry));
+	}
+	rcu_read_unlock();
+	return false;
+ found:
+	rcu_read_unlock();
+	return true;
+}
+EXPORT_SYMBOL(xa_get_mark);
+
+/**
+ * xa_set_mark() - Set this mark on this entry.
+ * @xa: XArray.
+ * @index: Index of entry.
+ * @mark: Mark number.
+ *
+ * Attempting to set a mark on a NULL entry does not succeed.
+ *
+ * Context: Process context.  Takes and releases the xa_lock.
+ */
+void xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
+{
+	xa_lock(xa);
+	__xa_set_mark(xa, index, mark);
+	xa_unlock(xa);
+}
+EXPORT_SYMBOL(xa_set_mark);
+
+/**
+ * xa_clear_mark() - Clear this mark on this entry.
+ * @xa: XArray.
+ * @index: Index of entry.
+ * @mark: Mark number.
+ *
+ * Clearing a mark always succeeds.
+ *
+ * Context: Process context.  Takes and releases the xa_lock.
+ */
+void xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark)
+{
+	xa_lock(xa);
+	__xa_clear_mark(xa, index, mark);
+	xa_unlock(xa);
+}
+EXPORT_SYMBOL(xa_clear_mark);
+
 #ifdef XA_DEBUG
 void xa_dump_node(const struct xa_node *node)
 {
@@ -230,8 +458,8 @@ void xa_dump(const struct xarray *xa)
 	unsigned int shift = 0;
 
 	pr_info("xarray: %px head %px flags %x marks %d %d %d\n", xa, entry,
-			xa->xa_flags, radix_tree_tagged(xa, 0),
-			radix_tree_tagged(xa, 1), radix_tree_tagged(xa, 2));
+			xa->xa_flags, xa_marked(xa, XA_MARK_0),
+			xa_marked(xa, XA_MARK_1), xa_marked(xa, XA_MARK_2));
 	if (xa_is_node(entry))
 		shift = xa_to_node(entry)->shift + XA_CHUNK_SHIFT;
 	xa_dump_entry(entry, 0, shift);
diff --git a/tools/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h
index 9bce3b56b5e7..5d2ab38965cc 100644
--- a/tools/include/asm-generic/bitops.h
+++ b/tools/include/asm-generic/bitops.h
@@ -27,5 +27,6 @@
 #include <asm-generic/bitops/hweight.h>
 
 #include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/non-atomic.h>
 
 #endif /* __TOOLS_ASM_GENERIC_BITOPS_H */
diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h
index 21c41ccd1266..2f6ea28764a7 100644
--- a/tools/include/asm-generic/bitops/atomic.h
+++ b/tools/include/asm-generic/bitops/atomic.h
@@ -15,13 +15,4 @@ static inline void clear_bit(int nr, unsigned long *addr)
 	addr[nr / __BITS_PER_LONG] &= ~(1UL << (nr % __BITS_PER_LONG));
 }
 
-static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
-{
-	return ((1UL << (nr % __BITS_PER_LONG)) &
-		(((unsigned long *)addr)[nr / __BITS_PER_LONG])) != 0;
-}
-
-#define __set_bit(nr, addr)	set_bit(nr, addr)
-#define __clear_bit(nr, addr)	clear_bit(nr, addr)
-
 #endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ */
diff --git a/tools/include/asm-generic/bitops/non-atomic.h b/tools/include/asm-generic/bitops/non-atomic.h
new file mode 100644
index 000000000000..7e10c4b50c5d
--- /dev/null
+++ b/tools/include/asm-generic/bitops/non-atomic.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
+#define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
+
+#include <asm/types.h>
+
+/**
+ * __set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p  |= mask;
+}
+
+static inline void __clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p &= ~mask;
+}
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __change_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p ^= mask;
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old | mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old & ~mask;
+	return (old & mask) != 0;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static inline int __test_and_change_bit(int nr,
+					    volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old ^ mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static inline int test_bit(int nr, const volatile unsigned long *addr)
+{
+	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+
+#endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h
index 1738c0391da4..622266b197d0 100644
--- a/tools/include/linux/spinlock.h
+++ b/tools/include/linux/spinlock.h
@@ -8,8 +8,14 @@
 #define spinlock_t		pthread_mutex_t
 #define DEFINE_SPINLOCK(x)	pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER
 #define __SPIN_LOCK_UNLOCKED(x)	(pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER
-#define spin_lock_init(x)      pthread_mutex_init(x, NULL)
-
+#define spin_lock_init(x)	pthread_mutex_init(x, NULL)
+
+#define spin_lock(x)			pthread_mutex_lock(x)
+#define spin_unlock(x)			pthread_mutex_unlock(x)
+#define spin_lock_bh(x)			pthread_mutex_lock(x)
+#define spin_unlock_bh(x)		pthread_mutex_unlock(x)
+#define spin_lock_irq(x)		pthread_mutex_lock(x)
+#define spin_unlock_irq(x)		pthread_mutex_unlock(x)
 #define spin_lock_irqsave(x, f)		(void)f, pthread_mutex_lock(x)
 #define spin_unlock_irqrestore(x, f)	(void)f, pthread_mutex_unlock(x)
 
-- 
cgit v1.2.3


From 58d6ea3085f2e53714810a513c61629f6d2be0a6 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Fri, 10 Nov 2017 15:15:08 -0500
Subject: xarray: Add XArray unconditional store operations

xa_store() differs from radix_tree_insert() in that it will overwrite an
existing element in the array rather than returning an error.  This is
the behaviour which most users want, and those that want more complex
behaviour generally want to use the xas family of routines anyway.

For memory allocation, xa_store() will first attempt to request memory
from the slab allocator; if memory is not immediately available, it will
drop the xa_lock and allocate memory, keeping a pointer in the xa_state.
It does not use the per-CPU cache, although those will continue to exist
until all radix tree users are converted to the xarray.

This patch also includes xa_erase() and __xa_erase() for a streamlined
way to store NULL.  Since there is no need to allocate memory in order
to store a NULL in the XArray, we do not need to trouble the user with
deciding what memory allocation flags to use.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/xarray.h                   | 147 ++++++-
 lib/radix-tree.c                         |   4 +-
 lib/test_xarray.c                        | 177 +++++++-
 lib/xarray.c                             | 693 +++++++++++++++++++++++++++++++
 tools/include/linux/bitmap.h             |   1 +
 tools/include/linux/spinlock.h           |   2 +
 tools/testing/radix-tree/Makefile        |   2 +-
 tools/testing/radix-tree/bitmap.c        |  23 +
 tools/testing/radix-tree/linux/kernel.h  |   4 +
 tools/testing/radix-tree/linux/lockdep.h |  11 +
 10 files changed, 1055 insertions(+), 9 deletions(-)
 create mode 100644 tools/testing/radix-tree/bitmap.c
 create mode 100644 tools/testing/radix-tree/linux/lockdep.h

(limited to 'tools')

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 2de504ae9ba4..15eab63286ed 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -205,10 +205,17 @@ typedef unsigned __bitwise xa_mark_t;
 #define XA_PRESENT		((__force xa_mark_t)8U)
 #define XA_MARK_MAX		XA_MARK_2
 
+enum xa_lock_type {
+	XA_LOCK_IRQ = 1,
+	XA_LOCK_BH = 2,
+};
+
 /*
  * Values for xa_flags.  The radix tree stores its GFP flags in the xa_flags,
  * and we remain compatible with that.
  */
+#define XA_FLAGS_LOCK_IRQ	((__force gfp_t)XA_LOCK_IRQ)
+#define XA_FLAGS_LOCK_BH	((__force gfp_t)XA_LOCK_BH)
 #define XA_FLAGS_MARK(mark)	((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \
 						(__force unsigned)(mark)))
 
@@ -267,6 +274,7 @@ struct xarray {
 
 void xa_init_flags(struct xarray *, gfp_t flags);
 void *xa_load(struct xarray *, unsigned long index);
+void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t);
 bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t);
 void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t);
 void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t);
@@ -309,6 +317,23 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark)
 	return xa->xa_flags & XA_FLAGS_MARK(mark);
 }
 
+/**
+ * xa_erase() - Erase this entry from the XArray.
+ * @xa: XArray.
+ * @index: Index of entry.
+ *
+ * This function is the equivalent of calling xa_store() with %NULL as
+ * the third argument.  The XArray does not need to allocate memory, so
+ * the user does not need to provide GFP flags.
+ *
+ * Context: Process context.  Takes and releases the xa_lock.
+ * Return: The entry which used to be at this index.
+ */
+static inline void *xa_erase(struct xarray *xa, unsigned long index)
+{
+	return xa_store(xa, index, NULL, 0);
+}
+
 #define xa_trylock(xa)		spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)		spin_lock(&(xa)->xa_lock)
 #define xa_unlock(xa)		spin_unlock(&(xa)->xa_lock)
@@ -322,11 +347,65 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark)
 				spin_unlock_irqrestore(&(xa)->xa_lock, flags)
 
 /*
- * Versions of the normal API which require the caller to hold the xa_lock.
- */
+ * Versions of the normal API which require the caller to hold the
+ * xa_lock.  If the GFP flags allow it, they will drop the lock to
+ * allocate memory, then reacquire it afterwards.  These functions
+ * may also re-enable interrupts if the XArray flags indicate the
+ * locking should be interrupt safe.
+ */
+void *__xa_erase(struct xarray *, unsigned long index);
+void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t);
 void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t);
 void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t);
 
+/**
+ * xa_erase_bh() - Erase this entry from the XArray.
+ * @xa: XArray.
+ * @index: Index of entry.
+ *
+ * This function is the equivalent of calling xa_store() with %NULL as
+ * the third argument.  The XArray does not need to allocate memory, so
+ * the user does not need to provide GFP flags.
+ *
+ * Context: Process context.  Takes and releases the xa_lock while
+ * disabling softirqs.
+ * Return: The entry which used to be at this index.
+ */
+static inline void *xa_erase_bh(struct xarray *xa, unsigned long index)
+{
+	void *entry;
+
+	xa_lock_bh(xa);
+	entry = __xa_erase(xa, index);
+	xa_unlock_bh(xa);
+
+	return entry;
+}
+
+/**
+ * xa_erase_irq() - Erase this entry from the XArray.
+ * @xa: XArray.
+ * @index: Index of entry.
+ *
+ * This function is the equivalent of calling xa_store() with %NULL as
+ * the third argument.  The XArray does not need to allocate memory, so
+ * the user does not need to provide GFP flags.
+ *
+ * Context: Process context.  Takes and releases the xa_lock while
+ * disabling interrupts.
+ * Return: The entry which used to be at this index.
+ */
+static inline void *xa_erase_irq(struct xarray *xa, unsigned long index)
+{
+	void *entry;
+
+	xa_lock_irq(xa);
+	entry = __xa_erase(xa, index);
+	xa_unlock_irq(xa);
+
+	return entry;
+}
+
 /* Everything below here is the Advanced API.  Proceed with caution. */
 
 /*
@@ -441,6 +520,12 @@ static inline struct xa_node *xa_parent_locked(const struct xarray *xa,
 						lockdep_is_held(&xa->xa_lock));
 }
 
+/* Private */
+static inline void *xa_mk_node(const struct xa_node *node)
+{
+	return (void *)((unsigned long)node | 2);
+}
+
 /* Private */
 static inline struct xa_node *xa_to_node(const void *entry)
 {
@@ -647,6 +732,12 @@ static inline bool xas_not_node(struct xa_node *node)
 	return ((unsigned long)node & 3) || !node;
 }
 
+/* True if the node represents head-of-tree, RESTART or BOUNDS */
+static inline bool xas_top(struct xa_node *node)
+{
+	return node <= XAS_RESTART;
+}
+
 /**
  * xas_reset() - Reset an XArray operation state.
  * @xas: XArray operation state.
@@ -683,10 +774,14 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry)
 }
 
 void *xas_load(struct xa_state *);
+void *xas_store(struct xa_state *, void *entry);
 
 bool xas_get_mark(const struct xa_state *, xa_mark_t);
 void xas_set_mark(const struct xa_state *, xa_mark_t);
 void xas_clear_mark(const struct xa_state *, xa_mark_t);
+void xas_init_marks(const struct xa_state *);
+
+bool xas_nomem(struct xa_state *, gfp_t);
 
 /**
  * xas_reload() - Refetch an entry from the xarray.
@@ -711,4 +806,52 @@ static inline void *xas_reload(struct xa_state *xas)
 	return xa_head(xas->xa);
 }
 
+/**
+ * xas_set() - Set up XArray operation state for a different index.
+ * @xas: XArray operation state.
+ * @index: New index into the XArray.
+ *
+ * Move the operation state to refer to a different index.  This will
+ * have the effect of starting a walk from the top; see xas_next()
+ * to move to an adjacent index.
+ */
+static inline void xas_set(struct xa_state *xas, unsigned long index)
+{
+	xas->xa_index = index;
+	xas->xa_node = XAS_RESTART;
+}
+
+/**
+ * xas_set_order() - Set up XArray operation state for a multislot entry.
+ * @xas: XArray operation state.
+ * @index: Target of the operation.
+ * @order: Entry occupies 2^@order indices.
+ */
+static inline void xas_set_order(struct xa_state *xas, unsigned long index,
+					unsigned int order)
+{
+#ifdef CONFIG_XARRAY_MULTI
+	xas->xa_index = order < BITS_PER_LONG ? (index >> order) << order : 0;
+	xas->xa_shift = order - (order % XA_CHUNK_SHIFT);
+	xas->xa_sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
+	xas->xa_node = XAS_RESTART;
+#else
+	BUG_ON(order > 0);
+	xas_set(xas, index);
+#endif
+}
+
+/**
+ * xas_set_update() - Set up XArray operation state for a callback.
+ * @xas: XArray operation state.
+ * @update: Function to call when updating a node.
+ *
+ * The XArray can notify a caller after it has updated an xa_node.
+ * This is advanced functionality and is only needed by the page cache.
+ */
+static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update)
+{
+	xas->xa_update = update;
+}
+
 #endif /* _LINUX_XARRAY_H */
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index b8e961428484..3479d93c32b9 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -47,7 +47,7 @@ static unsigned long height_to_maxnodes[RADIX_TREE_MAX_PATH + 1] __read_mostly;
 /*
  * Radix tree node cache.
  */
-static struct kmem_cache *radix_tree_node_cachep;
+struct kmem_cache *radix_tree_node_cachep;
 
 /*
  * The radix tree is variable-height, so an insert operation not only has
@@ -365,7 +365,7 @@ out:
 	return ret;
 }
 
-static void radix_tree_node_rcu_free(struct rcu_head *head)
+void radix_tree_node_rcu_free(struct rcu_head *head)
 {
 	struct radix_tree_node *node =
 			container_of(head, struct radix_tree_node, rcu_head);
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index f8b0e9ba80a4..b711030fbc32 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -30,13 +30,49 @@ void xa_dump(const struct xarray *xa) { }
 
 static void *xa_store_index(struct xarray *xa, unsigned long index, gfp_t gfp)
 {
-	radix_tree_insert(xa, index, xa_mk_value(index));
-	return NULL;
+	return xa_store(xa, index, xa_mk_value(index & LONG_MAX), gfp);
 }
 
 static void xa_erase_index(struct xarray *xa, unsigned long index)
 {
-	radix_tree_delete(xa, index);
+	XA_BUG_ON(xa, xa_erase(xa, index) != xa_mk_value(index & LONG_MAX));
+	XA_BUG_ON(xa, xa_load(xa, index) != NULL);
+}
+
+/*
+ * If anyone needs this, please move it to xarray.c.  We have no current
+ * users outside the test suite because all current multislot users want
+ * to use the advanced API.
+ */
+static void *xa_store_order(struct xarray *xa, unsigned long index,
+		unsigned order, void *entry, gfp_t gfp)
+{
+	XA_STATE_ORDER(xas, xa, index, order);
+	void *curr;
+
+	do {
+		xas_lock(&xas);
+		curr = xas_store(&xas, entry);
+		xas_unlock(&xas);
+	} while (xas_nomem(&xas, gfp));
+
+	return curr;
+}
+
+static noinline void check_xa_err(struct xarray *xa)
+{
+	XA_BUG_ON(xa, xa_err(xa_store_index(xa, 0, GFP_NOWAIT)) != 0);
+	XA_BUG_ON(xa, xa_err(xa_erase(xa, 0)) != 0);
+#ifndef __KERNEL__
+	/* The kernel does not fail GFP_NOWAIT allocations */
+	XA_BUG_ON(xa, xa_err(xa_store_index(xa, 1, GFP_NOWAIT)) != -ENOMEM);
+	XA_BUG_ON(xa, xa_err(xa_store_index(xa, 1, GFP_NOWAIT)) != -ENOMEM);
+#endif
+	XA_BUG_ON(xa, xa_err(xa_store_index(xa, 1, GFP_KERNEL)) != 0);
+	XA_BUG_ON(xa, xa_err(xa_store(xa, 1, xa_mk_value(0), GFP_KERNEL)) != 0);
+	XA_BUG_ON(xa, xa_err(xa_erase(xa, 1)) != 0);
+// kills the test-suite :-(
+//	XA_BUG_ON(xa, xa_err(xa_store(xa, 0, xa_mk_internal(0), 0)) != -EINVAL);
 }
 
 static noinline void check_xa_load(struct xarray *xa)
@@ -69,6 +105,9 @@ static noinline void check_xa_load(struct xarray *xa)
 
 static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index)
 {
+	unsigned int order;
+	unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 8 : 1;
+
 	/* NULL elements have no marks set */
 	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
 	xa_set_mark(xa, index, XA_MARK_0);
@@ -90,6 +129,37 @@ static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index)
 	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
 	xa_set_mark(xa, index, XA_MARK_0);
 	XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0));
+
+	/*
+	 * Storing a multi-index entry over entries with marks gives the
+	 * entire entry the union of the marks
+	 */
+	BUG_ON((index % 4) != 0);
+	for (order = 2; order < max_order; order++) {
+		unsigned long base = round_down(index, 1UL << order);
+		unsigned long next = base + (1UL << order);
+		unsigned long i;
+
+		XA_BUG_ON(xa, xa_store_index(xa, index + 1, GFP_KERNEL));
+		xa_set_mark(xa, index + 1, XA_MARK_0);
+		XA_BUG_ON(xa, xa_store_index(xa, index + 2, GFP_KERNEL));
+		xa_set_mark(xa, index + 2, XA_MARK_1);
+		XA_BUG_ON(xa, xa_store_index(xa, next, GFP_KERNEL));
+		xa_store_order(xa, index, order, xa_mk_value(index),
+				GFP_KERNEL);
+		for (i = base; i < next; i++) {
+			XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_0));
+			XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_1));
+			XA_BUG_ON(xa, xa_get_mark(xa, i, XA_MARK_2));
+		}
+		XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_0));
+		XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_1));
+		XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_2));
+		xa_erase_index(xa, index);
+		xa_erase_index(xa, next);
+		XA_BUG_ON(xa, !xa_empty(xa));
+	}
+	XA_BUG_ON(xa, !xa_empty(xa));
 }
 
 static noinline void check_xa_mark(struct xarray *xa)
@@ -100,12 +170,111 @@ static noinline void check_xa_mark(struct xarray *xa)
 		check_xa_mark_1(xa, index);
 }
 
-static RADIX_TREE(array, GFP_KERNEL);
+static noinline void check_xa_shrink(struct xarray *xa)
+{
+	XA_STATE(xas, xa, 1);
+	struct xa_node *node;
+
+	XA_BUG_ON(xa, !xa_empty(xa));
+	XA_BUG_ON(xa, xa_store_index(xa, 0, GFP_KERNEL) != NULL);
+	XA_BUG_ON(xa, xa_store_index(xa, 1, GFP_KERNEL) != NULL);
+
+	/*
+	 * Check that erasing the entry at 1 shrinks the tree and properly
+	 * marks the node as being deleted.
+	 */
+	xas_lock(&xas);
+	XA_BUG_ON(xa, xas_load(&xas) != xa_mk_value(1));
+	node = xas.xa_node;
+	XA_BUG_ON(xa, xa_entry_locked(xa, node, 0) != xa_mk_value(0));
+	XA_BUG_ON(xa, xas_store(&xas, NULL) != xa_mk_value(1));
+	XA_BUG_ON(xa, xa_load(xa, 1) != NULL);
+	XA_BUG_ON(xa, xas.xa_node != XAS_BOUNDS);
+	XA_BUG_ON(xa, xa_entry_locked(xa, node, 0) != XA_RETRY_ENTRY);
+	XA_BUG_ON(xa, xas_load(&xas) != NULL);
+	xas_unlock(&xas);
+	XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(0));
+	xa_erase_index(xa, 0);
+	XA_BUG_ON(xa, !xa_empty(xa));
+}
+
+static noinline void check_multi_store(struct xarray *xa)
+{
+#ifdef CONFIG_XARRAY_MULTI
+	unsigned long i, j, k;
+	unsigned int max_order = (sizeof(long) == 4) ? 30 : 60;
+
+	/* Loading from any position returns the same value */
+	xa_store_order(xa, 0, 1, xa_mk_value(0), GFP_KERNEL);
+	XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(0));
+	XA_BUG_ON(xa, xa_load(xa, 1) != xa_mk_value(0));
+	XA_BUG_ON(xa, xa_load(xa, 2) != NULL);
+	rcu_read_lock();
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->count != 2);
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->nr_values != 2);
+	rcu_read_unlock();
+
+	/* Storing adjacent to the value does not alter the value */
+	xa_store(xa, 3, xa, GFP_KERNEL);
+	XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(0));
+	XA_BUG_ON(xa, xa_load(xa, 1) != xa_mk_value(0));
+	XA_BUG_ON(xa, xa_load(xa, 2) != NULL);
+	rcu_read_lock();
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->count != 3);
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->nr_values != 2);
+	rcu_read_unlock();
+
+	/* Overwriting multiple indexes works */
+	xa_store_order(xa, 0, 2, xa_mk_value(1), GFP_KERNEL);
+	XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(1));
+	XA_BUG_ON(xa, xa_load(xa, 1) != xa_mk_value(1));
+	XA_BUG_ON(xa, xa_load(xa, 2) != xa_mk_value(1));
+	XA_BUG_ON(xa, xa_load(xa, 3) != xa_mk_value(1));
+	XA_BUG_ON(xa, xa_load(xa, 4) != NULL);
+	rcu_read_lock();
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->count != 4);
+	XA_BUG_ON(xa, xa_to_node(xa_head(xa))->nr_values != 4);
+	rcu_read_unlock();
+
+	/* We can erase multiple values with a single store */
+	xa_store_order(xa, 0, 63, NULL, GFP_KERNEL);
+	XA_BUG_ON(xa, !xa_empty(xa));
+
+	/* Even when the first slot is empty but the others aren't */
+	xa_store_index(xa, 1, GFP_KERNEL);
+	xa_store_index(xa, 2, GFP_KERNEL);
+	xa_store_order(xa, 0, 2, NULL, GFP_KERNEL);
+	XA_BUG_ON(xa, !xa_empty(xa));
+
+	for (i = 0; i < max_order; i++) {
+		for (j = 0; j < max_order; j++) {
+			xa_store_order(xa, 0, i, xa_mk_value(i), GFP_KERNEL);
+			xa_store_order(xa, 0, j, xa_mk_value(j), GFP_KERNEL);
+
+			for (k = 0; k < max_order; k++) {
+				void *entry = xa_load(xa, (1UL << k) - 1);
+				if ((i < k) && (j < k))
+					XA_BUG_ON(xa, entry != NULL);
+				else
+					XA_BUG_ON(xa, entry != xa_mk_value(j));
+			}
+
+			xa_erase(xa, 0);
+			XA_BUG_ON(xa, !xa_empty(xa));
+		}
+	}
+#endif
+}
+
+static DEFINE_XARRAY(array);
 
 static int xarray_checks(void)
 {
+	check_xa_err(&array);
 	check_xa_load(&array);
 	check_xa_mark(&array);
+	check_xa_shrink(&array);
+	check_multi_store(&array);
 
 	printk("XArray: %u of %u tests passed\n", tests_passed, tests_run);
 	return (tests_run == tests_passed) ? 0 : -EINVAL;
diff --git a/lib/xarray.c b/lib/xarray.c
index aa86c47e532f..4596a95ed9cd 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -7,6 +7,8 @@
 
 #include <linux/bitmap.h>
 #include <linux/export.h>
+#include <linux/list.h>
+#include <linux/slab.h>
 #include <linux/xarray.h>
 
 /*
@@ -25,6 +27,31 @@
  * @entry refers to something stored in a slot in the xarray
  */
 
+static inline unsigned int xa_lock_type(const struct xarray *xa)
+{
+	return (__force unsigned int)xa->xa_flags & 3;
+}
+
+static inline void xas_lock_type(struct xa_state *xas, unsigned int lock_type)
+{
+	if (lock_type == XA_LOCK_IRQ)
+		xas_lock_irq(xas);
+	else if (lock_type == XA_LOCK_BH)
+		xas_lock_bh(xas);
+	else
+		xas_lock(xas);
+}
+
+static inline void xas_unlock_type(struct xa_state *xas, unsigned int lock_type)
+{
+	if (lock_type == XA_LOCK_IRQ)
+		xas_unlock_irq(xas);
+	else if (lock_type == XA_LOCK_BH)
+		xas_unlock_bh(xas);
+	else
+		xas_unlock(xas);
+}
+
 static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark)
 {
 	if (!(xa->xa_flags & XA_FLAGS_MARK(mark)))
@@ -67,6 +94,34 @@ static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark)
 	return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE);
 }
 
+#define mark_inc(mark) do { \
+	mark = (__force xa_mark_t)((__force unsigned)(mark) + 1); \
+} while (0)
+
+/*
+ * xas_squash_marks() - Merge all marks to the first entry
+ * @xas: Array operation state.
+ *
+ * Set a mark on the first entry if any entry has it set.  Clear marks on
+ * all sibling entries.
+ */
+static void xas_squash_marks(const struct xa_state *xas)
+{
+	unsigned int mark = 0;
+	unsigned int limit = xas->xa_offset + xas->xa_sibs + 1;
+
+	if (!xas->xa_sibs)
+		return;
+
+	do {
+		unsigned long *marks = xas->xa_node->marks[mark];
+		if (find_next_bit(marks, limit, xas->xa_offset + 1) == limit)
+			continue;
+		__set_bit(xas->xa_offset, marks);
+		bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs);
+	} while (mark++ != (__force unsigned)XA_MARK_MAX);
+}
+
 /* extracts the offset within this node from the index */
 static unsigned int get_offset(unsigned long index, struct xa_node *node)
 {
@@ -161,6 +216,516 @@ void *xas_load(struct xa_state *xas)
 }
 EXPORT_SYMBOL_GPL(xas_load);
 
+/* Move the radix tree node cache here */
+extern struct kmem_cache *radix_tree_node_cachep;
+extern void radix_tree_node_rcu_free(struct rcu_head *head);
+
+#define XA_RCU_FREE	((struct xarray *)1)
+
+static void xa_node_free(struct xa_node *node)
+{
+	XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
+	node->array = XA_RCU_FREE;
+	call_rcu(&node->rcu_head, radix_tree_node_rcu_free);
+}
+
+/*
+ * xas_destroy() - Free any resources allocated during the XArray operation.
+ * @xas: XArray operation state.
+ *
+ * This function is now internal-only.
+ */
+static void xas_destroy(struct xa_state *xas)
+{
+	struct xa_node *node = xas->xa_alloc;
+
+	if (!node)
+		return;
+	XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
+	kmem_cache_free(radix_tree_node_cachep, node);
+	xas->xa_alloc = NULL;
+}
+
+/**
+ * xas_nomem() - Allocate memory if needed.
+ * @xas: XArray operation state.
+ * @gfp: Memory allocation flags.
+ *
+ * If we need to add new nodes to the XArray, we try to allocate memory
+ * with GFP_NOWAIT while holding the lock, which will usually succeed.
+ * If it fails, @xas is flagged as needing memory to continue.  The caller
+ * should drop the lock and call xas_nomem().  If xas_nomem() succeeds,
+ * the caller should retry the operation.
+ *
+ * Forward progress is guaranteed as one node is allocated here and
+ * stored in the xa_state where it will be found by xas_alloc().  More
+ * nodes will likely be found in the slab allocator, but we do not tie
+ * them up here.
+ *
+ * Return: true if memory was needed, and was successfully allocated.
+ */
+bool xas_nomem(struct xa_state *xas, gfp_t gfp)
+{
+	if (xas->xa_node != XA_ERROR(-ENOMEM)) {
+		xas_destroy(xas);
+		return false;
+	}
+	xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp);
+	if (!xas->xa_alloc)
+		return false;
+	XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list));
+	xas->xa_node = XAS_RESTART;
+	return true;
+}
+EXPORT_SYMBOL_GPL(xas_nomem);
+
+/*
+ * __xas_nomem() - Drop locks and allocate memory if needed.
+ * @xas: XArray operation state.
+ * @gfp: Memory allocation flags.
+ *
+ * Internal variant of xas_nomem().
+ *
+ * Return: true if memory was needed, and was successfully allocated.
+ */
+static bool __xas_nomem(struct xa_state *xas, gfp_t gfp)
+	__must_hold(xas->xa->xa_lock)
+{
+	unsigned int lock_type = xa_lock_type(xas->xa);
+
+	if (xas->xa_node != XA_ERROR(-ENOMEM)) {
+		xas_destroy(xas);
+		return false;
+	}
+	if (gfpflags_allow_blocking(gfp)) {
+		xas_unlock_type(xas, lock_type);
+		xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp);
+		xas_lock_type(xas, lock_type);
+	} else {
+		xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp);
+	}
+	if (!xas->xa_alloc)
+		return false;
+	XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list));
+	xas->xa_node = XAS_RESTART;
+	return true;
+}
+
+static void xas_update(struct xa_state *xas, struct xa_node *node)
+{
+	if (xas->xa_update)
+		xas->xa_update(node);
+	else
+		XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
+}
+
+static void *xas_alloc(struct xa_state *xas, unsigned int shift)
+{
+	struct xa_node *parent = xas->xa_node;
+	struct xa_node *node = xas->xa_alloc;
+
+	if (xas_invalid(xas))
+		return NULL;
+
+	if (node) {
+		xas->xa_alloc = NULL;
+	} else {
+		node = kmem_cache_alloc(radix_tree_node_cachep,
+					GFP_NOWAIT | __GFP_NOWARN);
+		if (!node) {
+			xas_set_err(xas, -ENOMEM);
+			return NULL;
+		}
+	}
+
+	if (parent) {
+		node->offset = xas->xa_offset;
+		parent->count++;
+		XA_NODE_BUG_ON(node, parent->count > XA_CHUNK_SIZE);
+		xas_update(xas, parent);
+	}
+	XA_NODE_BUG_ON(node, shift > BITS_PER_LONG);
+	XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
+	node->shift = shift;
+	node->count = 0;
+	node->nr_values = 0;
+	RCU_INIT_POINTER(node->parent, xas->xa_node);
+	node->array = xas->xa;
+
+	return node;
+}
+
+/*
+ * Use this to calculate the maximum index that will need to be created
+ * in order to add the entry described by @xas.  Because we cannot store a
+ * multiple-index entry at index 0, the calculation is a little more complex
+ * than you might expect.
+ */
+static unsigned long xas_max(struct xa_state *xas)
+{
+	unsigned long max = xas->xa_index;
+
+#ifdef CONFIG_XARRAY_MULTI
+	if (xas->xa_shift || xas->xa_sibs) {
+		unsigned long mask;
+		mask = (((xas->xa_sibs + 1UL) << xas->xa_shift) - 1);
+		max |= mask;
+		if (mask == max)
+			max++;
+	}
+#endif
+
+	return max;
+}
+
+/* The maximum index that can be contained in the array without expanding it */
+static unsigned long max_index(void *entry)
+{
+	if (!xa_is_node(entry))
+		return 0;
+	return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1;
+}
+
+static void xas_shrink(struct xa_state *xas)
+{
+	struct xarray *xa = xas->xa;
+	struct xa_node *node = xas->xa_node;
+
+	for (;;) {
+		void *entry;
+
+		XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE);
+		if (node->count != 1)
+			break;
+		entry = xa_entry_locked(xa, node, 0);
+		if (!entry)
+			break;
+		if (!xa_is_node(entry) && node->shift)
+			break;
+		xas->xa_node = XAS_BOUNDS;
+
+		RCU_INIT_POINTER(xa->xa_head, entry);
+
+		node->count = 0;
+		node->nr_values = 0;
+		if (!xa_is_node(entry))
+			RCU_INIT_POINTER(node->slots[0], XA_RETRY_ENTRY);
+		xas_update(xas, node);
+		xa_node_free(node);
+		if (!xa_is_node(entry))
+			break;
+		node = xa_to_node(entry);
+		node->parent = NULL;
+	}
+}
+
+/*
+ * xas_delete_node() - Attempt to delete an xa_node
+ * @xas: Array operation state.
+ *
+ * Attempts to delete the @xas->xa_node.  This will fail if xa->node has
+ * a non-zero reference count.
+ */
+static void xas_delete_node(struct xa_state *xas)
+{
+	struct xa_node *node = xas->xa_node;
+
+	for (;;) {
+		struct xa_node *parent;
+
+		XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE);
+		if (node->count)
+			break;
+
+		parent = xa_parent_locked(xas->xa, node);
+		xas->xa_node = parent;
+		xas->xa_offset = node->offset;
+		xa_node_free(node);
+
+		if (!parent) {
+			xas->xa->xa_head = NULL;
+			xas->xa_node = XAS_BOUNDS;
+			return;
+		}
+
+		parent->slots[xas->xa_offset] = NULL;
+		parent->count--;
+		XA_NODE_BUG_ON(parent, parent->count > XA_CHUNK_SIZE);
+		node = parent;
+		xas_update(xas, node);
+	}
+
+	if (!node->parent)
+		xas_shrink(xas);
+}
+
+/**
+ * xas_free_nodes() - Free this node and all nodes that it references
+ * @xas: Array operation state.
+ * @top: Node to free
+ *
+ * This node has been removed from the tree.  We must now free it and all
+ * of its subnodes.  There may be RCU walkers with references into the tree,
+ * so we must replace all entries with retry markers.
+ */
+static void xas_free_nodes(struct xa_state *xas, struct xa_node *top)
+{
+	unsigned int offset = 0;
+	struct xa_node *node = top;
+
+	for (;;) {
+		void *entry = xa_entry_locked(xas->xa, node, offset);
+
+		if (xa_is_node(entry)) {
+			node = xa_to_node(entry);
+			offset = 0;
+			continue;
+		}
+		if (entry)
+			RCU_INIT_POINTER(node->slots[offset], XA_RETRY_ENTRY);
+		offset++;
+		while (offset == XA_CHUNK_SIZE) {
+			struct xa_node *parent;
+
+			parent = xa_parent_locked(xas->xa, node);
+			offset = node->offset + 1;
+			node->count = 0;
+			node->nr_values = 0;
+			xas_update(xas, node);
+			xa_node_free(node);
+			if (node == top)
+				return;
+			node = parent;
+		}
+	}
+}
+
+/*
+ * xas_expand adds nodes to the head of the tree until it has reached
+ * sufficient height to be able to contain @xas->xa_index
+ */
+static int xas_expand(struct xa_state *xas, void *head)
+{
+	struct xarray *xa = xas->xa;
+	struct xa_node *node = NULL;
+	unsigned int shift = 0;
+	unsigned long max = xas_max(xas);
+
+	if (!head) {
+		if (max == 0)
+			return 0;
+		while ((max >> shift) >= XA_CHUNK_SIZE)
+			shift += XA_CHUNK_SHIFT;
+		return shift + XA_CHUNK_SHIFT;
+	} else if (xa_is_node(head)) {
+		node = xa_to_node(head);
+		shift = node->shift + XA_CHUNK_SHIFT;
+	}
+	xas->xa_node = NULL;
+
+	while (max > max_index(head)) {
+		xa_mark_t mark = 0;
+
+		XA_NODE_BUG_ON(node, shift > BITS_PER_LONG);
+		node = xas_alloc(xas, shift);
+		if (!node)
+			return -ENOMEM;
+
+		node->count = 1;
+		if (xa_is_value(head))
+			node->nr_values = 1;
+		RCU_INIT_POINTER(node->slots[0], head);
+
+		/* Propagate the aggregated mark info to the new child */
+		for (;;) {
+			if (xa_marked(xa, mark))
+				node_set_mark(node, 0, mark);
+			if (mark == XA_MARK_MAX)
+				break;
+			mark_inc(mark);
+		}
+
+		/*
+		 * Now that the new node is fully initialised, we can add
+		 * it to the tree
+		 */
+		if (xa_is_node(head)) {
+			xa_to_node(head)->offset = 0;
+			rcu_assign_pointer(xa_to_node(head)->parent, node);
+		}
+		head = xa_mk_node(node);
+		rcu_assign_pointer(xa->xa_head, head);
+		xas_update(xas, node);
+
+		shift += XA_CHUNK_SHIFT;
+	}
+
+	xas->xa_node = node;
+	return shift;
+}
+
+/*
+ * xas_create() - Create a slot to store an entry in.
+ * @xas: XArray operation state.
+ *
+ * Most users will not need to call this function directly, as it is called
+ * by xas_store().  It is useful for doing conditional store operations
+ * (see the xa_cmpxchg() implementation for an example).
+ *
+ * Return: If the slot already existed, returns the contents of this slot.
+ * If the slot was newly created, returns NULL.  If it failed to create the
+ * slot, returns NULL and indicates the error in @xas.
+ */
+static void *xas_create(struct xa_state *xas)
+{
+	struct xarray *xa = xas->xa;
+	void *entry;
+	void __rcu **slot;
+	struct xa_node *node = xas->xa_node;
+	int shift;
+	unsigned int order = xas->xa_shift;
+
+	if (xas_top(node)) {
+		entry = xa_head_locked(xa);
+		xas->xa_node = NULL;
+		shift = xas_expand(xas, entry);
+		if (shift < 0)
+			return NULL;
+		entry = xa_head_locked(xa);
+		slot = &xa->xa_head;
+	} else if (xas_error(xas)) {
+		return NULL;
+	} else if (node) {
+		unsigned int offset = xas->xa_offset;
+
+		shift = node->shift;
+		entry = xa_entry_locked(xa, node, offset);
+		slot = &node->slots[offset];
+	} else {
+		shift = 0;
+		entry = xa_head_locked(xa);
+		slot = &xa->xa_head;
+	}
+
+	while (shift > order) {
+		shift -= XA_CHUNK_SHIFT;
+		if (!entry) {
+			node = xas_alloc(xas, shift);
+			if (!node)
+				break;
+			rcu_assign_pointer(*slot, xa_mk_node(node));
+		} else if (xa_is_node(entry)) {
+			node = xa_to_node(entry);
+		} else {
+			break;
+		}
+		entry = xas_descend(xas, node);
+		slot = &node->slots[xas->xa_offset];
+	}
+
+	return entry;
+}
+
+static void update_node(struct xa_state *xas, struct xa_node *node,
+		int count, int values)
+{
+	if (!node || (!count && !values))
+		return;
+
+	node->count += count;
+	node->nr_values += values;
+	XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE);
+	XA_NODE_BUG_ON(node, node->nr_values > XA_CHUNK_SIZE);
+	xas_update(xas, node);
+	if (count < 0)
+		xas_delete_node(xas);
+}
+
+/**
+ * xas_store() - Store this entry in the XArray.
+ * @xas: XArray operation state.
+ * @entry: New entry.
+ *
+ * If @xas is operating on a multi-index entry, the entry returned by this
+ * function is essentially meaningless (it may be an internal entry or it
+ * may be %NULL, even if there are non-NULL entries at some of the indices
+ * covered by the range).  This is not a problem for any current users,
+ * and can be changed if needed.
+ *
+ * Return: The old entry at this index.
+ */
+void *xas_store(struct xa_state *xas, void *entry)
+{
+	struct xa_node *node;
+	void __rcu **slot = &xas->xa->xa_head;
+	unsigned int offset, max;
+	int count = 0;
+	int values = 0;
+	void *first, *next;
+	bool value = xa_is_value(entry);
+
+	if (entry)
+		first = xas_create(xas);
+	else
+		first = xas_load(xas);
+
+	if (xas_invalid(xas))
+		return first;
+	node = xas->xa_node;
+	if (node && (xas->xa_shift < node->shift))
+		xas->xa_sibs = 0;
+	if ((first == entry) && !xas->xa_sibs)
+		return first;
+
+	next = first;
+	offset = xas->xa_offset;
+	max = xas->xa_offset + xas->xa_sibs;
+	if (node) {
+		slot = &node->slots[offset];
+		if (xas->xa_sibs)
+			xas_squash_marks(xas);
+	}
+	if (!entry)
+		xas_init_marks(xas);
+
+	for (;;) {
+		/*
+		 * Must clear the marks before setting the entry to NULL,
+		 * otherwise xas_for_each_marked may find a NULL entry and
+		 * stop early.  rcu_assign_pointer contains a release barrier
+		 * so the mark clearing will appear to happen before the
+		 * entry is set to NULL.
+		 */
+		rcu_assign_pointer(*slot, entry);
+		if (xa_is_node(next))
+			xas_free_nodes(xas, xa_to_node(next));
+		if (!node)
+			break;
+		count += !next - !entry;
+		values += !xa_is_value(first) - !value;
+		if (entry) {
+			if (offset == max)
+				break;
+			if (!xa_is_sibling(entry))
+				entry = xa_mk_sibling(xas->xa_offset);
+		} else {
+			if (offset == XA_CHUNK_MASK)
+				break;
+		}
+		next = xa_entry_locked(xas->xa, node, ++offset);
+		if (!xa_is_sibling(next)) {
+			if (!entry && (offset > max))
+				break;
+			first = next;
+		}
+		slot++;
+	}
+
+	update_node(xas, node, count, values);
+	return first;
+}
+EXPORT_SYMBOL_GPL(xas_store);
+
 /**
  * xas_get_mark() - Returns the state of this mark.
  * @xas: XArray operation state.
@@ -240,6 +805,30 @@ void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark)
 }
 EXPORT_SYMBOL_GPL(xas_clear_mark);
 
+/**
+ * xas_init_marks() - Initialise all marks for the entry
+ * @xas: Array operations state.
+ *
+ * Initialise all marks for the entry specified by @xas.  If we're tracking
+ * free entries with a mark, we need to set it on all entries.  All other
+ * marks are cleared.
+ *
+ * This implementation is not as efficient as it could be; we may walk
+ * up the tree multiple times.
+ */
+void xas_init_marks(const struct xa_state *xas)
+{
+	xa_mark_t mark = 0;
+
+	for (;;) {
+		xas_clear_mark(xas, mark);
+		if (mark == XA_MARK_MAX)
+			break;
+		mark_inc(mark);
+	}
+}
+EXPORT_SYMBOL_GPL(xas_init_marks);
+
 /**
  * xa_init_flags() - Initialise an empty XArray with flags.
  * @xa: XArray.
@@ -253,9 +842,19 @@ EXPORT_SYMBOL_GPL(xas_clear_mark);
  */
 void xa_init_flags(struct xarray *xa, gfp_t flags)
 {
+	unsigned int lock_type;
+	static struct lock_class_key xa_lock_irq;
+	static struct lock_class_key xa_lock_bh;
+
 	spin_lock_init(&xa->xa_lock);
 	xa->xa_flags = flags;
 	xa->xa_head = NULL;
+
+	lock_type = xa_lock_type(xa);
+	if (lock_type == XA_LOCK_IRQ)
+		lockdep_set_class(&xa->xa_lock, &xa_lock_irq);
+	else if (lock_type == XA_LOCK_BH)
+		lockdep_set_class(&xa->xa_lock, &xa_lock_bh);
 }
 EXPORT_SYMBOL(xa_init_flags);
 
@@ -282,6 +881,100 @@ void *xa_load(struct xarray *xa, unsigned long index)
 }
 EXPORT_SYMBOL(xa_load);
 
+static void *xas_result(struct xa_state *xas, void *curr)
+{
+	XA_NODE_BUG_ON(xas->xa_node, xa_is_internal(curr));
+	if (xas_error(xas))
+		curr = xas->xa_node;
+	return curr;
+}
+
+/**
+ * __xa_erase() - Erase this entry from the XArray while locked.
+ * @xa: XArray.
+ * @index: Index into array.
+ *
+ * If the entry at this index is a multi-index entry then all indices will
+ * be erased, and the entry will no longer be a multi-index entry.
+ * This function expects the xa_lock to be held on entry.
+ *
+ * Context: Any context.  Expects xa_lock to be held on entry.  May
+ * release and reacquire xa_lock if @gfp flags permit.
+ * Return: The old entry at this index.
+ */
+void *__xa_erase(struct xarray *xa, unsigned long index)
+{
+	XA_STATE(xas, xa, index);
+	return xas_result(&xas, xas_store(&xas, NULL));
+}
+EXPORT_SYMBOL_GPL(__xa_erase);
+
+/**
+ * xa_store() - Store this entry in the XArray.
+ * @xa: XArray.
+ * @index: Index into array.
+ * @entry: New entry.
+ * @gfp: Memory allocation flags.
+ *
+ * After this function returns, loads from this index will return @entry.
+ * Storing into an existing multislot entry updates the entry of every index.
+ * The marks associated with @index are unaffected unless @entry is %NULL.
+ *
+ * Context: Process context.  Takes and releases the xa_lock.  May sleep
+ * if the @gfp flags permit.
+ * Return: The old entry at this index on success, xa_err(-EINVAL) if @entry
+ * cannot be stored in an XArray, or xa_err(-ENOMEM) if memory allocation
+ * failed.
+ */
+void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp)
+{
+	XA_STATE(xas, xa, index);
+	void *curr;
+
+	if (WARN_ON_ONCE(xa_is_internal(entry)))
+		return XA_ERROR(-EINVAL);
+
+	do {
+		xas_lock(&xas);
+		curr = xas_store(&xas, entry);
+		xas_unlock(&xas);
+	} while (xas_nomem(&xas, gfp));
+
+	return xas_result(&xas, curr);
+}
+EXPORT_SYMBOL(xa_store);
+
+/**
+ * __xa_store() - Store this entry in the XArray.
+ * @xa: XArray.
+ * @index: Index into array.
+ * @entry: New entry.
+ * @gfp: Memory allocation flags.
+ *
+ * You must already be holding the xa_lock when calling this function.
+ * It will drop the lock if needed to allocate memory, and then reacquire
+ * it afterwards.
+ *
+ * Context: Any context.  Expects xa_lock to be held on entry.  May
+ * release and reacquire xa_lock if @gfp flags permit.
+ * Return: The old entry at this index or xa_err() if an error happened.
+ */
+void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp)
+{
+	XA_STATE(xas, xa, index);
+	void *curr;
+
+	if (WARN_ON_ONCE(xa_is_internal(entry)))
+		return XA_ERROR(-EINVAL);
+
+	do {
+		curr = xas_store(&xas, entry);
+	} while (__xas_nomem(&xas, gfp));
+
+	return xas_result(&xas, curr);
+}
+EXPORT_SYMBOL(__xa_store);
+
 /**
  * __xa_set_mark() - Set this mark on this entry while locked.
  * @xa: XArray.
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index e63662db131b..05dca5c203f3 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -15,6 +15,7 @@ void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, int bits);
 int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, unsigned int bits);
+void bitmap_clear(unsigned long *map, unsigned int start, int len);
 
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
 
diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h
index 622266b197d0..c934572d935c 100644
--- a/tools/include/linux/spinlock.h
+++ b/tools/include/linux/spinlock.h
@@ -37,4 +37,6 @@ static inline bool arch_spin_is_locked(arch_spinlock_t *mutex)
 	return true;
 }
 
+#include <linux/lockdep.h>
+
 #endif
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index 1379f1d78d0b..acf1afa01c5b 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -5,7 +5,7 @@ CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \
 LDFLAGS += -fsanitize=address -fsanitize=undefined
 LDLIBS+= -lpthread -lurcu
 TARGETS = main idr-test multiorder xarray
-CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o
+CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o bitmap.o
 OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \
 	 tag_check.o multiorder.o idr-test.o iteration_check.o benchmark.o
 
diff --git a/tools/testing/radix-tree/bitmap.c b/tools/testing/radix-tree/bitmap.c
new file mode 100644
index 000000000000..66ec4a24a203
--- /dev/null
+++ b/tools/testing/radix-tree/bitmap.c
@@ -0,0 +1,23 @@
+/* lib/bitmap.c pulls in at least two other files. */
+
+#include <linux/bitmap.h>
+
+void bitmap_clear(unsigned long *map, unsigned int start, int len)
+{
+	unsigned long *p = map + BIT_WORD(start);
+	const unsigned int size = start + len;
+	int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
+	unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
+
+	while (len - bits_to_clear >= 0) {
+		*p &= ~mask_to_clear;
+		len -= bits_to_clear;
+		bits_to_clear = BITS_PER_LONG;
+		mask_to_clear = ~0UL;
+		p++;
+	}
+	if (len) {
+		mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
+		*p &= ~mask_to_clear;
+	}
+}
diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h
index 5d06ac75a14d..4568248222ae 100644
--- a/tools/testing/radix-tree/linux/kernel.h
+++ b/tools/testing/radix-tree/linux/kernel.h
@@ -18,4 +18,8 @@
 #define pr_debug printk
 #define pr_cont printk
 
+#define __acquires(x)
+#define __releases(x)
+#define __must_hold(x)
+
 #endif /* _KERNEL_H */
diff --git a/tools/testing/radix-tree/linux/lockdep.h b/tools/testing/radix-tree/linux/lockdep.h
new file mode 100644
index 000000000000..565fccdfe6e9
--- /dev/null
+++ b/tools/testing/radix-tree/linux/lockdep.h
@@ -0,0 +1,11 @@
+#ifndef _LINUX_LOCKDEP_H
+#define _LINUX_LOCKDEP_H
+struct lock_class_key {
+	unsigned int a;
+};
+
+static inline void lockdep_set_class(spinlock_t *lock,
+					struct lock_class_key *key)
+{
+}
+#endif /* _LINUX_LOCKDEP_H */
-- 
cgit v1.2.3


From f32f004cddf86d63a9c42994bbce9f4e2f07c9fa Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Wed, 4 Jul 2018 15:42:46 -0400
Subject: ida: Convert to XArray

Use the XA_TRACK_FREE ability to track which entries have a free bit,
similarly to how it uses the radix tree's IDR_FREE tag.  This eliminates
the per-cpu ida_bitmap preload, and fixes the memory consumption
regression I introduced when making the IDR able to store any pointer.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/idr.h                 |  18 +-
 lib/idr.c                           | 379 +++++++++++++++++++-----------------
 lib/radix-tree.c                    |  71 -------
 tools/testing/radix-tree/idr-test.c |   8 +-
 4 files changed, 213 insertions(+), 263 deletions(-)

(limited to 'tools')

diff --git a/include/linux/idr.h b/include/linux/idr.h
index 3ec8628ce17f..60daf34b625d 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -214,8 +214,7 @@ static inline void idr_preload_end(void)
 	     ++id, (entry) = idr_get_next((idr), &(id)))
 
 /*
- * IDA - IDR based id allocator, use when translation from id to
- * pointer isn't necessary.
+ * IDA - ID Allocator, use when translation from id to pointer isn't necessary.
  */
 #define IDA_CHUNK_SIZE		128	/* 128 bytes per chunk */
 #define IDA_BITMAP_LONGS	(IDA_CHUNK_SIZE / sizeof(long))
@@ -225,14 +224,14 @@ struct ida_bitmap {
 	unsigned long		bitmap[IDA_BITMAP_LONGS];
 };
 
-DECLARE_PER_CPU(struct ida_bitmap *, ida_bitmap);
-
 struct ida {
-	struct radix_tree_root	ida_rt;
+	struct xarray xa;
 };
 
+#define IDA_INIT_FLAGS	(XA_FLAGS_LOCK_IRQ | XA_FLAGS_ALLOC)
+
 #define IDA_INIT(name)	{						\
-	.ida_rt = RADIX_TREE_INIT(name, IDR_RT_MARKER | GFP_NOWAIT),	\
+	.xa = XARRAY_INIT(name, IDA_INIT_FLAGS)				\
 }
 #define DEFINE_IDA(name)	struct ida name = IDA_INIT(name)
 
@@ -292,7 +291,7 @@ static inline int ida_alloc_max(struct ida *ida, unsigned int max, gfp_t gfp)
 
 static inline void ida_init(struct ida *ida)
 {
-	INIT_RADIX_TREE(&ida->ida_rt, IDR_RT_MARKER | GFP_NOWAIT);
+	xa_init_flags(&ida->xa, IDA_INIT_FLAGS);
 }
 
 #define ida_simple_get(ida, start, end, gfp)	\
@@ -301,9 +300,6 @@ static inline void ida_init(struct ida *ida)
 
 static inline bool ida_is_empty(const struct ida *ida)
 {
-	return radix_tree_empty(&ida->ida_rt);
+	return xa_empty(&ida->xa);
 }
-
-/* in lib/radix-tree.c */
-int ida_pre_get(struct ida *ida, gfp_t gfp_mask);
 #endif /* __IDR_H__ */
diff --git a/lib/idr.c b/lib/idr.c
index 9a366b5be2c2..3c20ad9b0463 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -6,8 +6,6 @@
 #include <linux/spinlock.h>
 #include <linux/xarray.h>
 
-DEFINE_PER_CPU(struct ida_bitmap *, ida_bitmap);
-
 /**
  * idr_alloc_u32() - Allocate an ID.
  * @idr: IDR handle.
@@ -320,6 +318,9 @@ EXPORT_SYMBOL(idr_replace);
  * free the individual IDs in it.  You can use ida_is_empty() to find
  * out whether the IDA has any IDs currently allocated.
  *
+ * The IDA handles its own locking.  It is safe to call any of the IDA
+ * functions without synchronisation in your code.
+ *
  * IDs are currently limited to the range [0-INT_MAX].  If this is an awkward
  * limitation, it should be quite straightforward to raise the maximum.
  */
@@ -327,151 +328,197 @@ EXPORT_SYMBOL(idr_replace);
 /*
  * Developer's notes:
  *
- * The IDA uses the functionality provided by the IDR & radix tree to store
- * bitmaps in each entry.  The IDR_FREE tag means there is at least one bit
- * free, unlike the IDR where it means at least one entry is free.
+ * The IDA uses the functionality provided by the XArray to store bitmaps in
+ * each entry.  The XA_FREE_MARK is only cleared when all bits in the bitmap
+ * have been set.
  *
- * I considered telling the radix tree that each slot is an order-10 node
- * and storing the bit numbers in the radix tree, but the radix tree can't
- * allow a single multiorder entry at index 0, which would significantly
- * increase memory consumption for the IDA.  So instead we divide the index
- * by the number of bits in the leaf bitmap before doing a radix tree lookup.
+ * I considered telling the XArray that each slot is an order-10 node
+ * and indexing by bit number, but the XArray can't allow a single multi-index
+ * entry in the head, which would significantly increase memory consumption
+ * for the IDA.  So instead we divide the index by the number of bits in the
+ * leaf bitmap before doing a radix tree lookup.
  *
  * As an optimisation, if there are only a few low bits set in any given
  * leaf, instead of allocating a 128-byte bitmap, we store the bits
- * directly in the entry.
- *
- * We allow the radix tree 'exceptional' count to get out of date.  Nothing
- * in the IDA nor the radix tree code checks it.  If it becomes important
- * to maintain an accurate exceptional count, switch the rcu_assign_pointer()
- * calls to radix_tree_iter_replace() which will correct the exceptional
- * count.
- *
- * The IDA always requires a lock to alloc/free.  If we add a 'test_bit'
+ * as a value entry.  Value entries never have the XA_FREE_MARK cleared
+ * because we can always convert them into a bitmap entry.
+ *
+ * It would be possible to optimise further; once we've run out of a
+ * single 128-byte bitmap, we currently switch to a 576-byte node, put
+ * the 128-byte bitmap in the first entry and then start allocating extra
+ * 128-byte entries.  We could instead use the 512 bytes of the node's
+ * data as a bitmap before moving to that scheme.  I do not believe this
+ * is a worthwhile optimisation; Rasmus Villemoes surveyed the current
+ * users of the IDA and almost none of them use more than 1024 entries.
+ * Those that do use more than the 8192 IDs that the 512 bytes would
+ * provide.
+ *
+ * The IDA always uses a lock to alloc/free.  If we add a 'test_bit'
  * equivalent, it will still need locking.  Going to RCU lookup would require
  * using RCU to free bitmaps, and that's not trivial without embedding an
  * RCU head in the bitmap, which adds a 2-pointer overhead to each 128-byte
  * bitmap, which is excessive.
  */
 
-#define IDA_MAX (0x80000000U / IDA_BITMAP_BITS - 1)
-
-static int ida_get_new_above(struct ida *ida, int start)
+/**
+ * ida_alloc_range() - Allocate an unused ID.
+ * @ida: IDA handle.
+ * @min: Lowest ID to allocate.
+ * @max: Highest ID to allocate.
+ * @gfp: Memory allocation flags.
+ *
+ * Allocate an ID between @min and @max, inclusive.  The allocated ID will
+ * not exceed %INT_MAX, even if @max is larger.
+ *
+ * Context: Any context.
+ * Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
+ * or %-ENOSPC if there are no free IDs.
+ */
+int ida_alloc_range(struct ida *ida, unsigned int min, unsigned int max,
+			gfp_t gfp)
 {
-	struct radix_tree_root *root = &ida->ida_rt;
-	void __rcu **slot;
-	struct radix_tree_iter iter;
-	struct ida_bitmap *bitmap;
-	unsigned long index;
-	unsigned bit;
-	int new;
-
-	index = start / IDA_BITMAP_BITS;
-	bit = start % IDA_BITMAP_BITS;
-
-	slot = radix_tree_iter_init(&iter, index);
-	for (;;) {
-		if (slot)
-			slot = radix_tree_next_slot(slot, &iter,
-						RADIX_TREE_ITER_TAGGED);
-		if (!slot) {
-			slot = idr_get_free(root, &iter, GFP_NOWAIT, IDA_MAX);
-			if (IS_ERR(slot)) {
-				if (slot == ERR_PTR(-ENOMEM))
-					return -EAGAIN;
-				return PTR_ERR(slot);
+	XA_STATE(xas, &ida->xa, min / IDA_BITMAP_BITS);
+	unsigned bit = min % IDA_BITMAP_BITS;
+	unsigned long flags;
+	struct ida_bitmap *bitmap, *alloc = NULL;
+
+	if ((int)min < 0)
+		return -ENOSPC;
+
+	if ((int)max < 0)
+		max = INT_MAX;
+
+retry:
+	xas_lock_irqsave(&xas, flags);
+next:
+	bitmap = xas_find_marked(&xas, max / IDA_BITMAP_BITS, XA_FREE_MARK);
+	if (xas.xa_index > min / IDA_BITMAP_BITS)
+		bit = 0;
+	if (xas.xa_index * IDA_BITMAP_BITS + bit > max)
+		goto nospc;
+
+	if (xa_is_value(bitmap)) {
+		unsigned long tmp = xa_to_value(bitmap);
+
+		if (bit < BITS_PER_XA_VALUE) {
+			bit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE, bit);
+			if (xas.xa_index * IDA_BITMAP_BITS + bit > max)
+				goto nospc;
+			if (bit < BITS_PER_XA_VALUE) {
+				tmp |= 1UL << bit;
+				xas_store(&xas, xa_mk_value(tmp));
+				goto out;
 			}
 		}
-		if (iter.index > index)
-			bit = 0;
-		new = iter.index * IDA_BITMAP_BITS;
-		bitmap = rcu_dereference_raw(*slot);
-		if (xa_is_value(bitmap)) {
-			unsigned long tmp = xa_to_value(bitmap);
-			int vbit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE,
-							bit);
-			if (vbit < BITS_PER_XA_VALUE) {
-				tmp |= 1UL << vbit;
-				rcu_assign_pointer(*slot, xa_mk_value(tmp));
-				return new + vbit;
-			}
-			bitmap = this_cpu_xchg(ida_bitmap, NULL);
-			if (!bitmap)
-				return -EAGAIN;
-			bitmap->bitmap[0] = tmp;
-			rcu_assign_pointer(*slot, bitmap);
+		bitmap = alloc;
+		if (!bitmap)
+			bitmap = kzalloc(sizeof(*bitmap), GFP_NOWAIT);
+		if (!bitmap)
+			goto alloc;
+		bitmap->bitmap[0] = tmp;
+		xas_store(&xas, bitmap);
+		if (xas_error(&xas)) {
+			bitmap->bitmap[0] = 0;
+			goto out;
 		}
+	}
 
-		if (bitmap) {
-			bit = find_next_zero_bit(bitmap->bitmap,
-							IDA_BITMAP_BITS, bit);
-			new += bit;
-			if (new < 0)
-				return -ENOSPC;
-			if (bit == IDA_BITMAP_BITS)
-				continue;
+	if (bitmap) {
+		bit = find_next_zero_bit(bitmap->bitmap, IDA_BITMAP_BITS, bit);
+		if (xas.xa_index * IDA_BITMAP_BITS + bit > max)
+			goto nospc;
+		if (bit == IDA_BITMAP_BITS)
+			goto next;
 
-			__set_bit(bit, bitmap->bitmap);
-			if (bitmap_full(bitmap->bitmap, IDA_BITMAP_BITS))
-				radix_tree_iter_tag_clear(root, &iter,
-								IDR_FREE);
+		__set_bit(bit, bitmap->bitmap);
+		if (bitmap_full(bitmap->bitmap, IDA_BITMAP_BITS))
+			xas_clear_mark(&xas, XA_FREE_MARK);
+	} else {
+		if (bit < BITS_PER_XA_VALUE) {
+			bitmap = xa_mk_value(1UL << bit);
 		} else {
-			new += bit;
-			if (new < 0)
-				return -ENOSPC;
-			if (bit < BITS_PER_XA_VALUE) {
-				bitmap = xa_mk_value(1UL << bit);
-			} else {
-				bitmap = this_cpu_xchg(ida_bitmap, NULL);
-				if (!bitmap)
-					return -EAGAIN;
-				__set_bit(bit, bitmap->bitmap);
-			}
-			radix_tree_iter_replace(root, &iter, slot, bitmap);
+			bitmap = alloc;
+			if (!bitmap)
+				bitmap = kzalloc(sizeof(*bitmap), GFP_NOWAIT);
+			if (!bitmap)
+				goto alloc;
+			__set_bit(bit, bitmap->bitmap);
 		}
-
-		return new;
+		xas_store(&xas, bitmap);
+	}
+out:
+	xas_unlock_irqrestore(&xas, flags);
+	if (xas_nomem(&xas, gfp)) {
+		xas.xa_index = min / IDA_BITMAP_BITS;
+		bit = min % IDA_BITMAP_BITS;
+		goto retry;
 	}
+	if (bitmap != alloc)
+		kfree(alloc);
+	if (xas_error(&xas))
+		return xas_error(&xas);
+	return xas.xa_index * IDA_BITMAP_BITS + bit;
+alloc:
+	xas_unlock_irqrestore(&xas, flags);
+	alloc = kzalloc(sizeof(*bitmap), gfp);
+	if (!alloc)
+		return -ENOMEM;
+	xas_set(&xas, min / IDA_BITMAP_BITS);
+	bit = min % IDA_BITMAP_BITS;
+	goto retry;
+nospc:
+	xas_unlock_irqrestore(&xas, flags);
+	return -ENOSPC;
 }
+EXPORT_SYMBOL(ida_alloc_range);
 
-static void ida_remove(struct ida *ida, int id)
+/**
+ * ida_free() - Release an allocated ID.
+ * @ida: IDA handle.
+ * @id: Previously allocated ID.
+ *
+ * Context: Any context.
+ */
+void ida_free(struct ida *ida, unsigned int id)
 {
-	unsigned long index = id / IDA_BITMAP_BITS;
-	unsigned offset = id % IDA_BITMAP_BITS;
+	XA_STATE(xas, &ida->xa, id / IDA_BITMAP_BITS);
+	unsigned bit = id % IDA_BITMAP_BITS;
 	struct ida_bitmap *bitmap;
-	unsigned long *btmp;
-	struct radix_tree_iter iter;
-	void __rcu **slot;
+	unsigned long flags;
 
-	slot = radix_tree_iter_lookup(&ida->ida_rt, &iter, index);
-	if (!slot)
-		goto err;
+	BUG_ON((int)id < 0);
+
+	xas_lock_irqsave(&xas, flags);
+	bitmap = xas_load(&xas);
 
-	bitmap = rcu_dereference_raw(*slot);
 	if (xa_is_value(bitmap)) {
-		btmp = (unsigned long *)slot;
-		offset += 1; /* Intimate knowledge of the value encoding */
-		if (offset >= BITS_PER_LONG)
+		unsigned long v = xa_to_value(bitmap);
+		if (bit >= BITS_PER_XA_VALUE)
+			goto err;
+		if (!(v & (1UL << bit)))
 			goto err;
+		v &= ~(1UL << bit);
+		if (!v)
+			goto delete;
+		xas_store(&xas, xa_mk_value(v));
 	} else {
-		btmp = bitmap->bitmap;
-	}
-	if (!test_bit(offset, btmp))
-		goto err;
-
-	__clear_bit(offset, btmp);
-	radix_tree_iter_tag_set(&ida->ida_rt, &iter, IDR_FREE);
-	if (xa_is_value(bitmap)) {
-		if (xa_to_value(rcu_dereference_raw(*slot)) == 0)
-			radix_tree_iter_delete(&ida->ida_rt, &iter, slot);
-	} else if (bitmap_empty(btmp, IDA_BITMAP_BITS)) {
-		kfree(bitmap);
-		radix_tree_iter_delete(&ida->ida_rt, &iter, slot);
+		if (!test_bit(bit, bitmap->bitmap))
+			goto err;
+		__clear_bit(bit, bitmap->bitmap);
+		xas_set_mark(&xas, XA_FREE_MARK);
+		if (bitmap_empty(bitmap->bitmap, IDA_BITMAP_BITS)) {
+			kfree(bitmap);
+delete:
+			xas_store(&xas, NULL);
+		}
 	}
+	xas_unlock_irqrestore(&xas, flags);
 	return;
  err:
+	xas_unlock_irqrestore(&xas, flags);
 	WARN(1, "ida_free called for id=%d which is not allocated.\n", id);
 }
+EXPORT_SYMBOL(ida_free);
 
 /**
  * ida_destroy() - Free all IDs.
@@ -486,80 +533,60 @@ static void ida_remove(struct ida *ida, int id)
  */
 void ida_destroy(struct ida *ida)
 {
+	XA_STATE(xas, &ida->xa, 0);
+	struct ida_bitmap *bitmap;
 	unsigned long flags;
-	struct radix_tree_iter iter;
-	void __rcu **slot;
 
-	xa_lock_irqsave(&ida->ida_rt, flags);
-	radix_tree_for_each_slot(slot, &ida->ida_rt, &iter, 0) {
-		struct ida_bitmap *bitmap = rcu_dereference_raw(*slot);
+	xas_lock_irqsave(&xas, flags);
+	xas_for_each(&xas, bitmap, ULONG_MAX) {
 		if (!xa_is_value(bitmap))
 			kfree(bitmap);
-		radix_tree_iter_delete(&ida->ida_rt, &iter, slot);
+		xas_store(&xas, NULL);
 	}
-	xa_unlock_irqrestore(&ida->ida_rt, flags);
+	xas_unlock_irqrestore(&xas, flags);
 }
 EXPORT_SYMBOL(ida_destroy);
 
-/**
- * ida_alloc_range() - Allocate an unused ID.
- * @ida: IDA handle.
- * @min: Lowest ID to allocate.
- * @max: Highest ID to allocate.
- * @gfp: Memory allocation flags.
- *
- * Allocate an ID between @min and @max, inclusive.  The allocated ID will
- * not exceed %INT_MAX, even if @max is larger.
- *
- * Context: Any context.
- * Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
- * or %-ENOSPC if there are no free IDs.
- */
-int ida_alloc_range(struct ida *ida, unsigned int min, unsigned int max,
-			gfp_t gfp)
-{
-	int id = 0;
-	unsigned long flags;
-
-	if ((int)min < 0)
-		return -ENOSPC;
+#ifndef __KERNEL__
+extern void xa_dump_index(unsigned long index, unsigned int shift);
+#define IDA_CHUNK_SHIFT		ilog2(IDA_BITMAP_BITS)
 
-	if ((int)max < 0)
-		max = INT_MAX;
-
-again:
-	xa_lock_irqsave(&ida->ida_rt, flags);
-	id = ida_get_new_above(ida, min);
-	if (id > (int)max) {
-		ida_remove(ida, id);
-		id = -ENOSPC;
-	}
-	xa_unlock_irqrestore(&ida->ida_rt, flags);
+static void ida_dump_entry(void *entry, unsigned long index)
+{
+	unsigned long i;
+
+	if (!entry)
+		return;
+
+	if (xa_is_node(entry)) {
+		struct xa_node *node = xa_to_node(entry);
+		unsigned int shift = node->shift + IDA_CHUNK_SHIFT +
+			XA_CHUNK_SHIFT;
+
+		xa_dump_index(index * IDA_BITMAP_BITS, shift);
+		xa_dump_node(node);
+		for (i = 0; i < XA_CHUNK_SIZE; i++)
+			ida_dump_entry(node->slots[i],
+					index | (i << node->shift));
+	} else if (xa_is_value(entry)) {
+		xa_dump_index(index * IDA_BITMAP_BITS, ilog2(BITS_PER_LONG));
+		pr_cont("value: data %lx [%px]\n", xa_to_value(entry), entry);
+	} else {
+		struct ida_bitmap *bitmap = entry;
 
-	if (unlikely(id == -EAGAIN)) {
-		if (!ida_pre_get(ida, gfp))
-			return -ENOMEM;
-		goto again;
+		xa_dump_index(index * IDA_BITMAP_BITS, IDA_CHUNK_SHIFT);
+		pr_cont("bitmap: %p data", bitmap);
+		for (i = 0; i < IDA_BITMAP_LONGS; i++)
+			pr_cont(" %lx", bitmap->bitmap[i]);
+		pr_cont("\n");
 	}
-
-	return id;
 }
-EXPORT_SYMBOL(ida_alloc_range);
 
-/**
- * ida_free() - Release an allocated ID.
- * @ida: IDA handle.
- * @id: Previously allocated ID.
- *
- * Context: Any context.
- */
-void ida_free(struct ida *ida, unsigned int id)
+static void ida_dump(struct ida *ida)
 {
-	unsigned long flags;
-
-	BUG_ON((int)id < 0);
-	xa_lock_irqsave(&ida->ida_rt, flags);
-	ida_remove(ida, id);
-	xa_unlock_irqrestore(&ida->ida_rt, flags);
+	struct xarray *xa = &ida->xa;
+	pr_debug("ida: %p node %p free %d\n", ida, xa->xa_head,
+				xa->xa_flags >> ROOT_TAG_SHIFT);
+	ida_dump_entry(xa->xa_head, 0);
 }
-EXPORT_SYMBOL(ida_free);
+#endif
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 3479d93c32b9..68702061464f 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -255,54 +255,6 @@ static unsigned long next_index(unsigned long index,
 	return (index & ~node_maxindex(node)) + (offset << node->shift);
 }
 
-#ifndef __KERNEL__
-static void dump_ida_node(void *entry, unsigned long index)
-{
-	unsigned long i;
-
-	if (!entry)
-		return;
-
-	if (radix_tree_is_internal_node(entry)) {
-		struct radix_tree_node *node = entry_to_node(entry);
-
-		pr_debug("ida node: %p offset %d indices %lu-%lu parent %p free %lx shift %d count %d\n",
-			node, node->offset, index * IDA_BITMAP_BITS,
-			((index | node_maxindex(node)) + 1) *
-				IDA_BITMAP_BITS - 1,
-			node->parent, node->tags[0][0], node->shift,
-			node->count);
-		for (i = 0; i < RADIX_TREE_MAP_SIZE; i++)
-			dump_ida_node(node->slots[i],
-					index | (i << node->shift));
-	} else if (xa_is_value(entry)) {
-		pr_debug("ida excp: %p offset %d indices %lu-%lu data %lx\n",
-				entry, (int)(index & RADIX_TREE_MAP_MASK),
-				index * IDA_BITMAP_BITS,
-				index * IDA_BITMAP_BITS + BITS_PER_XA_VALUE,
-				xa_to_value(entry));
-	} else {
-		struct ida_bitmap *bitmap = entry;
-
-		pr_debug("ida btmp: %p offset %d indices %lu-%lu data", bitmap,
-				(int)(index & RADIX_TREE_MAP_MASK),
-				index * IDA_BITMAP_BITS,
-				(index + 1) * IDA_BITMAP_BITS - 1);
-		for (i = 0; i < IDA_BITMAP_LONGS; i++)
-			pr_cont(" %lx", bitmap->bitmap[i]);
-		pr_cont("\n");
-	}
-}
-
-static void ida_dump(struct ida *ida)
-{
-	struct radix_tree_root *root = &ida->ida_rt;
-	pr_debug("ida: %p node %p free %d\n", ida, root->xa_head,
-				root->xa_flags >> ROOT_TAG_SHIFT);
-	dump_ida_node(root->xa_head, 0);
-}
-#endif
-
 /*
  * This assumes that the caller has performed appropriate preallocation, and
  * that the caller has pinned this thread of control to the current CPU.
@@ -2039,27 +1991,6 @@ void idr_preload(gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(idr_preload);
 
-int ida_pre_get(struct ida *ida, gfp_t gfp)
-{
-	/*
-	 * The IDA API has no preload_end() equivalent.  Instead,
-	 * ida_get_new() can return -EAGAIN, prompting the caller
-	 * to return to the ida_pre_get() step.
-	 */
-	if (!__radix_tree_preload(gfp, IDA_PRELOAD_SIZE))
-		preempt_enable();
-
-	if (!this_cpu_read(ida_bitmap)) {
-		struct ida_bitmap *bitmap = kzalloc(sizeof(*bitmap), gfp);
-		if (!bitmap)
-			return 0;
-		if (this_cpu_cmpxchg(ida_bitmap, NULL, bitmap))
-			kfree(bitmap);
-	}
-
-	return 1;
-}
-
 void __rcu **idr_get_free(struct radix_tree_root *root,
 			      struct radix_tree_iter *iter, gfp_t gfp,
 			      unsigned long max)
@@ -2201,8 +2132,6 @@ static int radix_tree_cpu_dead(unsigned int cpu)
 		kmem_cache_free(radix_tree_node_cachep, node);
 		rtp->nr--;
 	}
-	kfree(per_cpu(ida_bitmap, cpu));
-	per_cpu(ida_bitmap, cpu) = NULL;
 	return 0;
 }
 
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index a5a4494922a6..1b63bdb7688f 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -402,16 +402,15 @@ void ida_check_nomem(void)
  */
 void ida_check_conv_user(void)
 {
-#if 0
 	DEFINE_IDA(ida);
 	unsigned long i;
 
-	radix_tree_cpu_dead(1);
 	for (i = 0; i < 1000000; i++) {
 		int id = ida_alloc(&ida, GFP_NOWAIT);
 		if (id == -ENOMEM) {
-			IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) !=
-					BITS_PER_XA_VALUE);
+			IDA_BUG_ON(&ida, ((i % IDA_BITMAP_BITS) !=
+					  BITS_PER_XA_VALUE) &&
+					 ((i % IDA_BITMAP_BITS) != 0));
 			id = ida_alloc(&ida, GFP_KERNEL);
 		} else {
 			IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) ==
@@ -420,7 +419,6 @@ void ida_check_conv_user(void)
 		IDA_BUG_ON(&ida, id != i);
 	}
 	ida_destroy(&ida);
-#endif
 }
 
 void ida_check_random(void)
-- 
cgit v1.2.3


From 3ece58a270cd1e5026282abe778bd50db7a11d08 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Wed, 16 May 2018 18:00:33 -0400
Subject: page cache: Convert find_get_pages_contig to XArray

There's no direct replacement for radix_tree_for_each_contig()
in the XArray API as it's an unusual thing to do.  Instead,
open-code a loop using xas_next().  This removes the only user of
radix_tree_for_each_contig() so delete the iterator from the API and
the test suite code for it.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 .clang-format                          |  1 -
 include/linux/radix-tree.h             | 17 -----------
 mm/filemap.c                           | 53 ++++++++++++++--------------------
 tools/testing/radix-tree/regression3.c | 23 ---------------
 4 files changed, 22 insertions(+), 72 deletions(-)

(limited to 'tools')

diff --git a/.clang-format b/.clang-format
index 1d5da22e0ba5..e6080f5834a3 100644
--- a/.clang-format
+++ b/.clang-format
@@ -323,7 +323,6 @@ ForEachMacros:
   - 'protocol_for_each_card'
   - 'protocol_for_each_dev'
   - 'queue_for_each_hw_ctx'
-  - 'radix_tree_for_each_contig'
   - 'radix_tree_for_each_slot'
   - 'radix_tree_for_each_tagged'
   - 'rbtree_postorder_for_each_entry_safe'
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index d55de428a589..023e888e1163 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -522,23 +522,6 @@ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot,
 	     slot || (slot = radix_tree_next_chunk(root, iter, 0)) ;	\
 	     slot = radix_tree_next_slot(slot, iter, 0))
 
-/**
- * radix_tree_for_each_contig - iterate over contiguous slots
- *
- * @slot:	the void** variable for pointer to slot
- * @root:	the struct radix_tree_root pointer
- * @iter:	the struct radix_tree_iter pointer
- * @start:	iteration starting index
- *
- * @slot points to radix tree slot, @iter->index contains its index.
- */
-#define radix_tree_for_each_contig(slot, root, iter, start)		\
-	for (slot = radix_tree_iter_init(iter, start) ;			\
-	     slot || (slot = radix_tree_next_chunk(root, iter,		\
-				RADIX_TREE_ITER_CONTIG)) ;		\
-	     slot = radix_tree_next_slot(slot, iter,			\
-				RADIX_TREE_ITER_CONTIG))
-
 /**
  * radix_tree_for_each_tagged - iterate over tagged slots
  *
diff --git a/mm/filemap.c b/mm/filemap.c
index b72c39fe61c2..089b67598100 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1721,57 +1721,43 @@ out:
 unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
 			       unsigned int nr_pages, struct page **pages)
 {
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, &mapping->i_pages, index);
+	struct page *page;
 	unsigned int ret = 0;
 
 	if (unlikely(!nr_pages))
 		return 0;
 
 	rcu_read_lock();
-	radix_tree_for_each_contig(slot, &mapping->i_pages, &iter, index) {
-		struct page *head, *page;
-repeat:
-		page = radix_tree_deref_slot(slot);
-		/* The hole, there no reason to continue */
-		if (unlikely(!page))
-			break;
-
-		if (radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
-			/*
-			 * A shadow entry of a recently evicted page,
-			 * or a swap entry from shmem/tmpfs.  Stop
-			 * looking for contiguous pages.
-			 */
+	for (page = xas_load(&xas); page; page = xas_next(&xas)) {
+		struct page *head;
+		if (xas_retry(&xas, page))
+			continue;
+		/*
+		 * If the entry has been swapped out, we can stop looking.
+		 * No current caller is looking for DAX entries.
+		 */
+		if (xa_is_value(page))
 			break;
-		}
 
 		head = compound_head(page);
 		if (!page_cache_get_speculative(head))
-			goto repeat;
+			goto retry;
 
 		/* The page was split under us? */
-		if (compound_head(page) != head) {
-			put_page(head);
-			goto repeat;
-		}
+		if (compound_head(page) != head)
+			goto put_page;
 
 		/* Has the page moved? */
-		if (unlikely(page != *slot)) {
-			put_page(head);
-			goto repeat;
-		}
+		if (unlikely(page != xas_reload(&xas)))
+			goto put_page;
 
 		/*
 		 * must check mapping and index after taking the ref.
 		 * otherwise we can get both false positives and false
 		 * negatives, which is just confusing to the caller.
 		 */
-		if (page->mapping == NULL || page_to_pgoff(page) != iter.index) {
+		if (!page->mapping || page_to_pgoff(page) != xas.xa_index) {
 			put_page(page);
 			break;
 		}
@@ -1779,6 +1765,11 @@ repeat:
 		pages[ret] = page;
 		if (++ret == nr_pages)
 			break;
+		continue;
+put_page:
+		put_page(head);
+retry:
+		xas_reset(&xas);
 	}
 	rcu_read_unlock();
 	return ret;
diff --git a/tools/testing/radix-tree/regression3.c b/tools/testing/radix-tree/regression3.c
index ace2543c3eda..9f9a3b280f56 100644
--- a/tools/testing/radix-tree/regression3.c
+++ b/tools/testing/radix-tree/regression3.c
@@ -69,21 +69,6 @@ void regression3_test(void)
 			continue;
 		}
 	}
-	radix_tree_delete(&root, 1);
-
-	first = true;
-	radix_tree_for_each_contig(slot, &root, &iter, 0) {
-		printv(2, "contig %ld %p\n", iter.index, *slot);
-		if (first) {
-			radix_tree_insert(&root, 1, ptr);
-			first = false;
-		}
-		if (radix_tree_deref_retry(*slot)) {
-			printv(2, "retry at %ld\n", iter.index);
-			slot = radix_tree_iter_retry(&iter);
-			continue;
-		}
-	}
 
 	radix_tree_for_each_slot(slot, &root, &iter, 0) {
 		printv(2, "slot %ld %p\n", iter.index, *slot);
@@ -93,14 +78,6 @@ void regression3_test(void)
 		}
 	}
 
-	radix_tree_for_each_contig(slot, &root, &iter, 0) {
-		printv(2, "contig %ld %p\n", iter.index, *slot);
-		if (!iter.index) {
-			printv(2, "next at %ld\n", iter.index);
-			slot = radix_tree_iter_resume(slot, &iter);
-		}
-	}
-
 	radix_tree_tag_set(&root, 0, 0);
 	radix_tree_tag_set(&root, 1, 0);
 	radix_tree_for_each_tagged(slot, &root, &iter, 0, 0) {
-- 
cgit v1.2.3


From a332125fc3223e1092f765db442b7afb9fd4ecde Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Thu, 17 May 2018 00:13:27 -0400
Subject: radix tree test suite: Convert regression1 to XArray

Now the page cache lookup is using the XArray, let's convert this
regression test from the radix tree API to the XArray so it's testing
roughly the same thing it was testing before.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/testing/radix-tree/regression1.c | 58 +++++++++++-----------------------
 1 file changed, 19 insertions(+), 39 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c
index 0aece092f40e..b4a4a7168986 100644
--- a/tools/testing/radix-tree/regression1.c
+++ b/tools/testing/radix-tree/regression1.c
@@ -53,12 +53,12 @@ struct page {
 	unsigned long index;
 };
 
-static struct page *page_alloc(void)
+static struct page *page_alloc(int index)
 {
 	struct page *p;
 	p = malloc(sizeof(struct page));
 	p->count = 1;
-	p->index = 1;
+	p->index = index;
 	pthread_mutex_init(&p->lock, NULL);
 
 	return p;
@@ -80,53 +80,33 @@ static void page_free(struct page *p)
 static unsigned find_get_pages(unsigned long start,
 			    unsigned int nr_pages, struct page **pages)
 {
-	unsigned int i;
-	unsigned int ret;
-	unsigned int nr_found;
+	XA_STATE(xas, &mt_tree, start);
+	struct page *page;
+	unsigned int ret = 0;
 
 	rcu_read_lock();
-restart:
-	nr_found = radix_tree_gang_lookup_slot(&mt_tree,
-				(void ***)pages, NULL, start, nr_pages);
-	ret = 0;
-	for (i = 0; i < nr_found; i++) {
-		struct page *page;
-repeat:
-		page = radix_tree_deref_slot((void **)pages[i]);
-		if (unlikely(!page))
+	xas_for_each(&xas, page, ULONG_MAX) {
+		if (xas_retry(&xas, page))
 			continue;
 
-		if (radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page)) {
-				/*
-				 * Transient condition which can only trigger
-				 * when entry at index 0 moves out of or back
-				 * to root: none yet gotten, safe to restart.
-				 */
-				assert((start | i) == 0);
-				goto restart;
-			}
-			/*
-			 * No exceptional entries are inserted in this test.
-			 */
-			assert(0);
-		}
-
 		pthread_mutex_lock(&page->lock);
-		if (!page->count) {
-			pthread_mutex_unlock(&page->lock);
-			goto repeat;
-		}
+		if (!page->count)
+			goto unlock;
+
 		/* don't actually update page refcount */
 		pthread_mutex_unlock(&page->lock);
 
 		/* Has the page moved? */
-		if (unlikely(page != *((void **)pages[i]))) {
-			goto repeat;
-		}
+		if (unlikely(page != xas_reload(&xas)))
+			goto put_page;
 
 		pages[ret] = page;
 		ret++;
+		continue;
+unlock:
+		pthread_mutex_unlock(&page->lock);
+put_page:
+		xas_reset(&xas);
 	}
 	rcu_read_unlock();
 	return ret;
@@ -145,12 +125,12 @@ static void *regression1_fn(void *arg)
 		for (j = 0; j < 1000000; j++) {
 			struct page *p;
 
-			p = page_alloc();
+			p = page_alloc(0);
 			pthread_mutex_lock(&mt_lock);
 			radix_tree_insert(&mt_tree, 0, p);
 			pthread_mutex_unlock(&mt_lock);
 
-			p = page_alloc();
+			p = page_alloc(1);
 			pthread_mutex_lock(&mt_lock);
 			radix_tree_insert(&mt_tree, 1, p);
 			pthread_mutex_unlock(&mt_lock);
-- 
cgit v1.2.3


From e21a29552fa3f44ea41c53488875015ae70fd7f8 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Wed, 22 Nov 2017 08:36:00 -0500
Subject: shmem: Convert find_swap_entry to XArray

This is a 1:1 conversion.  The major part of this patch is converting
the test framework from userspace to kernel space and mirroring the
algorithm now used in find_swap_entry().

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 lib/test_xarray.c               | 56 +++++++++++++++++++++++++++++++++++++
 mm/shmem.c                      | 27 +++++++-----------
 tools/testing/radix-tree/main.c | 61 -----------------------------------------
 tools/testing/radix-tree/test.c | 22 ---------------
 tools/testing/radix-tree/test.h |  1 -
 5 files changed, 66 insertions(+), 101 deletions(-)

(limited to 'tools')

diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index 128c6489082f..815daffdd8c9 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -631,6 +631,61 @@ static noinline void check_find(struct xarray *xa)
 	check_multi_find_2(xa);
 }
 
+/* See find_swap_entry() in mm/shmem.c */
+static noinline unsigned long xa_find_entry(struct xarray *xa, void *item)
+{
+	XA_STATE(xas, xa, 0);
+	unsigned int checked = 0;
+	void *entry;
+
+	rcu_read_lock();
+	xas_for_each(&xas, entry, ULONG_MAX) {
+		if (xas_retry(&xas, entry))
+			continue;
+		if (entry == item)
+			break;
+		checked++;
+		if ((checked % 4) != 0)
+			continue;
+		xas_pause(&xas);
+	}
+	rcu_read_unlock();
+
+	return entry ? xas.xa_index : -1;
+}
+
+static noinline void check_find_entry(struct xarray *xa)
+{
+#ifdef CONFIG_XARRAY_MULTI
+	unsigned int order;
+	unsigned long offset, index;
+
+	for (order = 0; order < 20; order++) {
+		for (offset = 0; offset < (1UL << (order + 3));
+		     offset += (1UL << order)) {
+			for (index = 0; index < (1UL << (order + 5));
+			     index += (1UL << order)) {
+				xa_store_order(xa, index, order,
+						xa_mk_value(index), GFP_KERNEL);
+				XA_BUG_ON(xa, xa_load(xa, index) !=
+						xa_mk_value(index));
+				XA_BUG_ON(xa, xa_find_entry(xa,
+						xa_mk_value(index)) != index);
+			}
+			XA_BUG_ON(xa, xa_find_entry(xa, xa) != -1);
+			xa_destroy(xa);
+		}
+	}
+#endif
+
+	XA_BUG_ON(xa, xa_find_entry(xa, xa) != -1);
+	xa_store_index(xa, ULONG_MAX, GFP_KERNEL);
+	XA_BUG_ON(xa, xa_find_entry(xa, xa) != -1);
+	XA_BUG_ON(xa, xa_find_entry(xa, xa_mk_value(LONG_MAX)) != -1);
+	xa_erase_index(xa, ULONG_MAX);
+	XA_BUG_ON(xa, !xa_empty(xa));
+}
+
 static noinline void check_move_small(struct xarray *xa, unsigned long idx)
 {
 	XA_STATE(xas, xa, 0);
@@ -972,6 +1027,7 @@ static int xarray_checks(void)
 	check_multi_store(&array);
 	check_xa_alloc();
 	check_find(&array);
+	check_find_entry(&array);
 	check_destroy(&array);
 	check_move(&array);
 	check_create_range(&array);
diff --git a/mm/shmem.c b/mm/shmem.c
index ce91569426f3..a305529d6b89 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1100,34 +1100,27 @@ static void shmem_evict_inode(struct inode *inode)
 	clear_inode(inode);
 }
 
-static unsigned long find_swap_entry(struct radix_tree_root *root, void *item)
+static unsigned long find_swap_entry(struct xarray *xa, void *item)
 {
-	struct radix_tree_iter iter;
-	void __rcu **slot;
-	unsigned long found = -1;
+	XA_STATE(xas, xa, 0);
 	unsigned int checked = 0;
+	void *entry;
 
 	rcu_read_lock();
-	radix_tree_for_each_slot(slot, root, &iter, 0) {
-		void *entry = radix_tree_deref_slot(slot);
-
-		if (radix_tree_deref_retry(entry)) {
-			slot = radix_tree_iter_retry(&iter);
+	xas_for_each(&xas, entry, ULONG_MAX) {
+		if (xas_retry(&xas, entry))
 			continue;
-		}
-		if (entry == item) {
-			found = iter.index;
+		if (entry == item)
 			break;
-		}
 		checked++;
-		if ((checked % 4096) != 0)
+		if ((checked % XA_CHECK_SCHED) != 0)
 			continue;
-		slot = radix_tree_iter_resume(slot, &iter);
+		xas_pause(&xas);
 		cond_resched_rcu();
 	}
-
 	rcu_read_unlock();
-	return found;
+
+	return entry ? xas.xa_index : -1;
 }
 
 /*
diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c
index 09deaf4f0959..79589ea570ab 100644
--- a/tools/testing/radix-tree/main.c
+++ b/tools/testing/radix-tree/main.c
@@ -236,63 +236,6 @@ void copy_tag_check(void)
 	item_kill_tree(&tree);
 }
 
-static void __locate_check(struct radix_tree_root *tree, unsigned long index,
-			unsigned order)
-{
-	struct item *item;
-	unsigned long index2;
-
-	item_insert_order(tree, index, order);
-	item = item_lookup(tree, index);
-	index2 = find_item(tree, item);
-	if (index != index2) {
-		printv(2, "index %ld order %d inserted; found %ld\n",
-			index, order, index2);
-		abort();
-	}
-}
-
-static void __order_0_locate_check(void)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	int i;
-
-	for (i = 0; i < 50; i++)
-		__locate_check(&tree, rand() % INT_MAX, 0);
-
-	item_kill_tree(&tree);
-}
-
-static void locate_check(void)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	unsigned order;
-	unsigned long offset, index;
-
-	__order_0_locate_check();
-
-	for (order = 0; order < 20; order++) {
-		for (offset = 0; offset < (1 << (order + 3));
-		     offset += (1UL << order)) {
-			for (index = 0; index < (1UL << (order + 5));
-			     index += (1UL << order)) {
-				__locate_check(&tree, index + offset, order);
-			}
-			if (find_item(&tree, &tree) != -1)
-				abort();
-
-			item_kill_tree(&tree);
-		}
-	}
-
-	if (find_item(&tree, &tree) != -1)
-		abort();
-	__locate_check(&tree, -1, 0);
-	if (find_item(&tree, &tree) != -1)
-		abort();
-	item_kill_tree(&tree);
-}
-
 static void single_thread_tests(bool long_run)
 {
 	int i;
@@ -303,10 +246,6 @@ static void single_thread_tests(bool long_run)
 	rcu_barrier();
 	printv(2, "after multiorder_check: %d allocated, preempt %d\n",
 		nr_allocated, preempt_count);
-	locate_check();
-	rcu_barrier();
-	printv(2, "after locate_check: %d allocated, preempt %d\n",
-		nr_allocated, preempt_count);
 	tag_check();
 	rcu_barrier();
 	printv(2, "after tag_check: %d allocated, preempt %d\n",
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 70ddf964d51c..470419bfd49d 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -209,28 +209,6 @@ int tag_tagged_items(struct radix_tree_root *root, pthread_mutex_t *lock,
 	return tagged;
 }
 
-/* Use the same pattern as find_swap_entry() in mm/shmem.c */
-unsigned long find_item(struct radix_tree_root *root, void *item)
-{
-	struct radix_tree_iter iter;
-	void **slot;
-	unsigned long found = -1;
-	unsigned long checked = 0;
-
-	radix_tree_for_each_slot(slot, root, &iter, 0) {
-		if (*slot == item) {
-			found = iter.index;
-			break;
-		}
-		checked++;
-		if ((checked % 4) != 0)
-			continue;
-		slot = radix_tree_iter_resume(slot, &iter);
-	}
-
-	return found;
-}
-
 static int verify_node(struct radix_tree_node *slot, unsigned int tag,
 			int tagged)
 {
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index e3dc7a16f09b..9532c18c6cb1 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -32,7 +32,6 @@ void item_kill_tree(struct radix_tree_root *root);
 int tag_tagged_items(struct radix_tree_root *, pthread_mutex_t *,
 			unsigned long start, unsigned long end, unsigned batch,
 			unsigned iftag, unsigned thentag);
-unsigned long find_item(struct radix_tree_root *, void *item);
 
 void xarray_tests(void);
 void tag_check(void);
-- 
cgit v1.2.3


From 1cf56f9d670b88b2e947a7ccdb8ba32e6477915d Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Mon, 9 Apr 2018 16:24:45 -0400
Subject: radix tree: Remove radix_tree_update_node_t

The only user of this functionality was the workingset code, and it's
now been converted to the XArray.  Remove __radix_tree_delete_node()
entirely as it was also only used by the workingset code.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/radix-tree.h            |  7 +-----
 lib/idr.c                             |  2 +-
 lib/radix-tree.c                      | 42 +++++++----------------------------
 tools/testing/radix-tree/multiorder.c |  2 +-
 4 files changed, 11 insertions(+), 42 deletions(-)

(limited to 'tools')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 8a4280bc350f..7513d0df984b 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -242,17 +242,12 @@ void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index,
 void *radix_tree_lookup(const struct radix_tree_root *, unsigned long);
 void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *,
 					unsigned long index);
-typedef void (*radix_tree_update_node_t)(struct radix_tree_node *);
 void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *,
-			  void __rcu **slot, void *entry,
-			  radix_tree_update_node_t update_node);
+			  void __rcu **slot, void *entry);
 void radix_tree_iter_replace(struct radix_tree_root *,
 		const struct radix_tree_iter *, void __rcu **slot, void *entry);
 void radix_tree_replace_slot(struct radix_tree_root *,
 			     void __rcu **slot, void *entry);
-void __radix_tree_delete_node(struct radix_tree_root *,
-			      struct radix_tree_node *,
-			      radix_tree_update_node_t update_node);
 void radix_tree_iter_delete(struct radix_tree_root *,
 			struct radix_tree_iter *iter, void __rcu **slot);
 void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
diff --git a/lib/idr.c b/lib/idr.c
index 3c20ad9b0463..cb1db9b8d3f6 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -297,7 +297,7 @@ void *idr_replace(struct idr *idr, void *ptr, unsigned long id)
 	if (!slot || radix_tree_tag_get(&idr->idr_rt, id, IDR_FREE))
 		return ERR_PTR(-ENOENT);
 
-	__radix_tree_replace(&idr->idr_rt, node, slot, ptr, NULL);
+	__radix_tree_replace(&idr->idr_rt, node, slot, ptr);
 
 	return entry;
 }
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 2f9c0e45eeb7..c4c252185734 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -562,8 +562,7 @@ out:
  *	radix_tree_shrink    -    shrink radix tree to minimum height
  *	@root		radix tree root
  */
-static inline bool radix_tree_shrink(struct radix_tree_root *root,
-				     radix_tree_update_node_t update_node)
+static inline bool radix_tree_shrink(struct radix_tree_root *root)
 {
 	bool shrunk = false;
 
@@ -631,8 +630,6 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root,
 		node->count = 0;
 		if (!radix_tree_is_internal_node(child)) {
 			node->slots[0] = (void __rcu *)RADIX_TREE_RETRY;
-			if (update_node)
-				update_node(node);
 		}
 
 		WARN_ON_ONCE(!list_empty(&node->private_list));
@@ -644,8 +641,7 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root,
 }
 
 static bool delete_node(struct radix_tree_root *root,
-			struct radix_tree_node *node,
-			radix_tree_update_node_t update_node)
+			struct radix_tree_node *node)
 {
 	bool deleted = false;
 
@@ -655,7 +651,7 @@ static bool delete_node(struct radix_tree_root *root,
 		if (node->count) {
 			if (node_to_entry(node) ==
 					rcu_dereference_raw(root->xa_head))
-				deleted |= radix_tree_shrink(root, update_node);
+				deleted |= radix_tree_shrink(root);
 			return deleted;
 		}
 
@@ -1059,15 +1055,13 @@ static int calculate_count(struct radix_tree_root *root,
  * @node:		pointer to tree node
  * @slot:		pointer to slot in @node
  * @item:		new item to store in the slot.
- * @update_node:	callback for changing leaf nodes
  *
  * For use with __radix_tree_lookup().  Caller must hold tree write locked
  * across slot lookup and replacement.
  */
 void __radix_tree_replace(struct radix_tree_root *root,
 			  struct radix_tree_node *node,
-			  void __rcu **slot, void *item,
-			  radix_tree_update_node_t update_node)
+			  void __rcu **slot, void *item)
 {
 	void *old = rcu_dereference_raw(*slot);
 	int values = !!xa_is_value(item) - !!xa_is_value(old);
@@ -1085,10 +1079,7 @@ void __radix_tree_replace(struct radix_tree_root *root,
 	if (!node)
 		return;
 
-	if (update_node)
-		update_node(node);
-
-	delete_node(root, node, update_node);
+	delete_node(root, node);
 }
 
 /**
@@ -1110,7 +1101,7 @@ void __radix_tree_replace(struct radix_tree_root *root,
 void radix_tree_replace_slot(struct radix_tree_root *root,
 			     void __rcu **slot, void *item)
 {
-	__radix_tree_replace(root, NULL, slot, item, NULL);
+	__radix_tree_replace(root, NULL, slot, item);
 }
 EXPORT_SYMBOL(radix_tree_replace_slot);
 
@@ -1127,7 +1118,7 @@ void radix_tree_iter_replace(struct radix_tree_root *root,
 				const struct radix_tree_iter *iter,
 				void __rcu **slot, void *item)
 {
-	__radix_tree_replace(root, iter->node, slot, item, NULL);
+	__radix_tree_replace(root, iter->node, slot, item);
 }
 
 #ifdef CONFIG_RADIX_TREE_MULTIORDER
@@ -1807,23 +1798,6 @@ radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *root,
 }
 EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot);
 
-/**
- *	__radix_tree_delete_node    -    try to free node after clearing a slot
- *	@root:		radix tree root
- *	@node:		node containing @index
- *	@update_node:	callback for changing leaf nodes
- *
- *	After clearing the slot at @index in @node from radix tree
- *	rooted at @root, call this function to attempt freeing the
- *	node and shrinking the tree.
- */
-void __radix_tree_delete_node(struct radix_tree_root *root,
-			      struct radix_tree_node *node,
-			      radix_tree_update_node_t update_node)
-{
-	delete_node(root, node, update_node);
-}
-
 static bool __radix_tree_delete(struct radix_tree_root *root,
 				struct radix_tree_node *node, void __rcu **slot)
 {
@@ -1839,7 +1813,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root,
 			node_tag_clear(root, node, tag, offset);
 
 	replace_slot(slot, NULL, node, -1, values);
-	return node && delete_node(root, node, NULL);
+	return node && delete_node(root, node);
 }
 
 /**
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 60786fa55302..0e0ff26c9bcb 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -618,7 +618,7 @@ static void multiorder_account(void)
 	__radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5));
 	__radix_tree_lookup(&tree, 1 << 5, &node, &slot);
 	assert(node->count == node->nr_values * 2);
-	__radix_tree_replace(&tree, node, slot, NULL, NULL);
+	__radix_tree_replace(&tree, node, slot, NULL);
 	assert(node->nr_values == 0);
 
 	item_kill_tree(&tree);
-- 
cgit v1.2.3


From 2956c6644bfd9aab9f6b21a12e1bd75876d9dd73 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Sat, 19 May 2018 16:47:47 -0400
Subject: radix tree: Remove split/join code

radix_tree_split and radix_tree_join were never used upstream.  Remove
them; if they're needed in future they will be replaced by XArray
equivalents.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/radix-tree.h            |   6 -
 lib/radix-tree.c                      | 171 +----------------------
 tools/testing/radix-tree/benchmark.c  |  91 -------------
 tools/testing/radix-tree/multiorder.c | 247 ----------------------------------
 4 files changed, 2 insertions(+), 513 deletions(-)

(limited to 'tools')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 7513d0df984b..44f9abdcb5ab 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -284,12 +284,6 @@ static inline void radix_tree_preload_end(void)
 	preempt_enable();
 }
 
-int radix_tree_split_preload(unsigned old_order, unsigned new_order, gfp_t);
-int radix_tree_split(struct radix_tree_root *, unsigned long index,
-			unsigned new_order);
-int radix_tree_join(struct radix_tree_root *, unsigned long index,
-			unsigned new_order, void *);
-
 void __rcu **idr_get_free(struct radix_tree_root *root,
 			      struct radix_tree_iter *iter, gfp_t gfp,
 			      unsigned long max);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index c4c252185734..c52e0bef5264 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -415,28 +415,6 @@ int radix_tree_maybe_preload(gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(radix_tree_maybe_preload);
 
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-/*
- * Preload with enough objects to ensure that we can split a single entry
- * of order @old_order into many entries of size @new_order
- */
-int radix_tree_split_preload(unsigned int old_order, unsigned int new_order,
-							gfp_t gfp_mask)
-{
-	unsigned top = 1 << (old_order % RADIX_TREE_MAP_SHIFT);
-	unsigned layers = (old_order / RADIX_TREE_MAP_SHIFT) -
-				(new_order / RADIX_TREE_MAP_SHIFT);
-	unsigned nr = 0;
-
-	WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask));
-	BUG_ON(new_order >= old_order);
-
-	while (layers--)
-		nr = nr * RADIX_TREE_MAP_SIZE + 1;
-	return __radix_tree_preload(gfp_mask, top * nr);
-}
-#endif
-
 /*
  * The same as function above, but preload number of nodes required to insert
  * (1 << order) continuous naturally-aligned elements.
@@ -1111,8 +1089,8 @@ EXPORT_SYMBOL(radix_tree_replace_slot);
  * @slot:	pointer to slot
  * @item:	new item to store in the slot.
  *
- * For use with radix_tree_split() and radix_tree_for_each_slot().
- * Caller must hold tree write locked across split and replacement.
+ * For use with radix_tree_for_each_slot().
+ * Caller must hold tree write locked.
  */
 void radix_tree_iter_replace(struct radix_tree_root *root,
 				const struct radix_tree_iter *iter,
@@ -1121,151 +1099,6 @@ void radix_tree_iter_replace(struct radix_tree_root *root,
 	__radix_tree_replace(root, iter->node, slot, item);
 }
 
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-/**
- * radix_tree_join - replace multiple entries with one multiorder entry
- * @root: radix tree root
- * @index: an index inside the new entry
- * @order: order of the new entry
- * @item: new entry
- *
- * Call this function to replace several entries with one larger entry.
- * The existing entries are presumed to not need freeing as a result of
- * this call.
- *
- * The replacement entry will have all the tags set on it that were set
- * on any of the entries it is replacing.
- */
-int radix_tree_join(struct radix_tree_root *root, unsigned long index,
-			unsigned order, void *item)
-{
-	struct radix_tree_node *node;
-	void __rcu **slot;
-	int error;
-
-	BUG_ON(radix_tree_is_internal_node(item));
-
-	error = __radix_tree_create(root, index, order, &node, &slot);
-	if (!error)
-		error = insert_entries(node, slot, item, order, true);
-	if (error > 0)
-		error = 0;
-
-	return error;
-}
-
-/**
- * radix_tree_split - Split an entry into smaller entries
- * @root: radix tree root
- * @index: An index within the large entry
- * @order: Order of new entries
- *
- * Call this function as the first step in replacing a multiorder entry
- * with several entries of lower order.  After this function returns,
- * loop over the relevant portion of the tree using radix_tree_for_each_slot()
- * and call radix_tree_iter_replace() to set up each new entry.
- *
- * The tags from this entry are replicated to all the new entries.
- *
- * The radix tree should be locked against modification during the entire
- * replacement operation.  Lock-free lookups will see RADIX_TREE_RETRY which
- * should prompt RCU walkers to restart the lookup from the root.
- */
-int radix_tree_split(struct radix_tree_root *root, unsigned long index,
-				unsigned order)
-{
-	struct radix_tree_node *parent, *node, *child;
-	void __rcu **slot;
-	unsigned int offset, end;
-	unsigned n, tag, tags = 0;
-	gfp_t gfp = root_gfp_mask(root);
-
-	if (!__radix_tree_lookup(root, index, &parent, &slot))
-		return -ENOENT;
-	if (!parent)
-		return -ENOENT;
-
-	offset = get_slot_offset(parent, slot);
-
-	for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
-		if (tag_get(parent, tag, offset))
-			tags |= 1 << tag;
-
-	for (end = offset + 1; end < RADIX_TREE_MAP_SIZE; end++) {
-		if (!xa_is_sibling(rcu_dereference_raw(parent->slots[end])))
-			break;
-		for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
-			if (tags & (1 << tag))
-				tag_set(parent, tag, end);
-		/* rcu_assign_pointer ensures tags are set before RETRY */
-		rcu_assign_pointer(parent->slots[end], RADIX_TREE_RETRY);
-	}
-	rcu_assign_pointer(parent->slots[offset], RADIX_TREE_RETRY);
-	parent->nr_values -= (end - offset);
-
-	if (order == parent->shift)
-		return 0;
-	if (order > parent->shift) {
-		while (offset < end)
-			offset += insert_entries(parent, &parent->slots[offset],
-					RADIX_TREE_RETRY, order, true);
-		return 0;
-	}
-
-	node = parent;
-
-	for (;;) {
-		if (node->shift > order) {
-			child = radix_tree_node_alloc(gfp, node, root,
-					node->shift - RADIX_TREE_MAP_SHIFT,
-					offset, 0, 0);
-			if (!child)
-				goto nomem;
-			if (node != parent) {
-				node->count++;
-				rcu_assign_pointer(node->slots[offset],
-							node_to_entry(child));
-				for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
-					if (tags & (1 << tag))
-						tag_set(node, tag, offset);
-			}
-
-			node = child;
-			offset = 0;
-			continue;
-		}
-
-		n = insert_entries(node, &node->slots[offset],
-					RADIX_TREE_RETRY, order, false);
-		BUG_ON(n > RADIX_TREE_MAP_SIZE);
-
-		for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
-			if (tags & (1 << tag))
-				tag_set(node, tag, offset);
-		offset += n;
-
-		while (offset == RADIX_TREE_MAP_SIZE) {
-			if (node == parent)
-				break;
-			offset = node->offset;
-			child = node;
-			node = node->parent;
-			rcu_assign_pointer(node->slots[offset],
-						node_to_entry(child));
-			offset++;
-		}
-		if ((node == parent) && (offset == end))
-			return 0;
-	}
-
- nomem:
-	/* Shouldn't happen; did user forget to preload? */
-	/* TODO: free all the allocated nodes */
-	WARN_ON(1);
-	return -ENOMEM;
-}
-#endif
-
 static void node_tag_set(struct radix_tree_root *root,
 				struct radix_tree_node *node,
 				unsigned int tag, unsigned int offset)
diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c
index 99c40f3ed133..35741b9c2a4a 100644
--- a/tools/testing/radix-tree/benchmark.c
+++ b/tools/testing/radix-tree/benchmark.c
@@ -146,90 +146,6 @@ static void benchmark_size(unsigned long size, unsigned long step, int order)
 	rcu_barrier();
 }
 
-static long long  __benchmark_split(unsigned long index,
-				    int old_order, int new_order)
-{
-	struct timespec start, finish;
-	long long nsec;
-	RADIX_TREE(tree, GFP_ATOMIC);
-
-	item_insert_order(&tree, index, old_order);
-
-	clock_gettime(CLOCK_MONOTONIC, &start);
-	radix_tree_split(&tree, index, new_order);
-	clock_gettime(CLOCK_MONOTONIC, &finish);
-	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
-	       (finish.tv_nsec - start.tv_nsec);
-
-	item_kill_tree(&tree);
-
-	return nsec;
-
-}
-
-static void benchmark_split(unsigned long size, unsigned long step)
-{
-	int i, j, idx;
-	long long nsec = 0;
-
-
-	for (idx = 0; idx < size; idx += step) {
-		for (i = 3; i < 11; i++) {
-			for (j = 0; j < i; j++) {
-				nsec += __benchmark_split(idx, i, j);
-			}
-		}
-	}
-
-	printv(2, "Size %8ld, step %8ld, split time %10lld ns\n",
-			size, step, nsec);
-
-}
-
-static long long  __benchmark_join(unsigned long index,
-			     unsigned order1, unsigned order2)
-{
-	unsigned long loc;
-	struct timespec start, finish;
-	long long nsec;
-	void *item, *item2 = item_create(index + 1, order1);
-	RADIX_TREE(tree, GFP_KERNEL);
-
-	item_insert_order(&tree, index, order2);
-	item = radix_tree_lookup(&tree, index);
-
-	clock_gettime(CLOCK_MONOTONIC, &start);
-	radix_tree_join(&tree, index + 1, order1, item2);
-	clock_gettime(CLOCK_MONOTONIC, &finish);
-	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
-		(finish.tv_nsec - start.tv_nsec);
-
-	loc = find_item(&tree, item);
-	if (loc == -1)
-		free(item);
-
-	item_kill_tree(&tree);
-
-	return nsec;
-}
-
-static void benchmark_join(unsigned long step)
-{
-	int i, j, idx;
-	long long nsec = 0;
-
-	for (idx = 0; idx < 1 << 10; idx += step) {
-		for (i = 1; i < 15; i++) {
-			for (j = 0; j < i; j++) {
-				nsec += __benchmark_join(idx, i, j);
-			}
-		}
-	}
-
-	printv(2, "Size %8d, step %8ld, join time %10lld ns\n",
-			1 << 10, step, nsec);
-}
-
 void benchmark(void)
 {
 	unsigned long size[] = {1 << 10, 1 << 20, 0};
@@ -247,11 +163,4 @@ void benchmark(void)
 	for (c = 0; size[c]; c++)
 		for (s = 0; step[s]; s++)
 			benchmark_size(size[c], step[s] << 9, 9);
-
-	for (c = 0; size[c]; c++)
-		for (s = 0; step[s]; s++)
-			benchmark_split(size[c], step[s]);
-
-	for (s = 0; step[s]; s++)
-		benchmark_join(step[s]);
 }
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 0e0ff26c9bcb..221e042d1b89 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -356,251 +356,6 @@ void multiorder_tagged_iteration(void)
 	item_kill_tree(&tree);
 }
 
-/*
- * Basic join checks: make sure we can't find an entry in the tree after
- * a larger entry has replaced it
- */
-static void multiorder_join1(unsigned long index,
-				unsigned order1, unsigned order2)
-{
-	unsigned long loc;
-	void *item, *item2 = item_create(index + 1, order1);
-	RADIX_TREE(tree, GFP_KERNEL);
-
-	item_insert_order(&tree, index, order2);
-	item = radix_tree_lookup(&tree, index);
-	radix_tree_join(&tree, index + 1, order1, item2);
-	loc = find_item(&tree, item);
-	if (loc == -1)
-		free(item);
-	item = radix_tree_lookup(&tree, index + 1);
-	assert(item == item2);
-	item_kill_tree(&tree);
-}
-
-/*
- * Check that the accounting of value entries is handled correctly
- * by joining a value entry to a normal pointer.
- */
-static void multiorder_join2(unsigned order1, unsigned order2)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	struct radix_tree_node *node;
-	void *item1 = item_create(0, order1);
-	void *item2;
-
-	item_insert_order(&tree, 0, order2);
-	radix_tree_insert(&tree, 1 << order2, xa_mk_value(5));
-	item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL);
-	assert(item2 == xa_mk_value(5));
-	assert(node->nr_values == 1);
-
-	item2 = radix_tree_lookup(&tree, 0);
-	free(item2);
-
-	radix_tree_join(&tree, 0, order1, item1);
-	item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL);
-	assert(item2 == item1);
-	assert(node->nr_values == 0);
-	item_kill_tree(&tree);
-}
-
-/*
- * This test revealed an accounting bug for value entries at one point.
- * Nodes were being freed back into the pool with an elevated exception count
- * by radix_tree_join() and then radix_tree_split() was failing to zero the
- * count of value entries.
- */
-static void multiorder_join3(unsigned int order)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	struct radix_tree_node *node;
-	void **slot;
-	struct radix_tree_iter iter;
-	unsigned long i;
-
-	for (i = 0; i < (1 << order); i++) {
-		radix_tree_insert(&tree, i, xa_mk_value(5));
-	}
-
-	radix_tree_join(&tree, 0, order, xa_mk_value(7));
-	rcu_barrier();
-
-	radix_tree_split(&tree, 0, 0);
-
-	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		radix_tree_iter_replace(&tree, &iter, slot, xa_mk_value(5));
-	}
-
-	__radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(node->nr_values == node->count);
-
-	item_kill_tree(&tree);
-}
-
-static void multiorder_join(void)
-{
-	int i, j, idx;
-
-	for (idx = 0; idx < 1024; idx = idx * 2 + 3) {
-		for (i = 1; i < 15; i++) {
-			for (j = 0; j < i; j++) {
-				multiorder_join1(idx, i, j);
-			}
-		}
-	}
-
-	for (i = 1; i < 15; i++) {
-		for (j = 0; j < i; j++) {
-			multiorder_join2(i, j);
-		}
-	}
-
-	for (i = 3; i < 10; i++) {
-		multiorder_join3(i);
-	}
-}
-
-static void check_mem(unsigned old_order, unsigned new_order, unsigned alloc)
-{
-	struct radix_tree_preload *rtp = &radix_tree_preloads;
-	if (rtp->nr != 0)
-		printv(2, "split(%u %u) remaining %u\n", old_order, new_order,
-							rtp->nr);
-	/*
-	 * Can't check for equality here as some nodes may have been
-	 * RCU-freed while we ran.  But we should never finish with more
-	 * nodes allocated since they should have all been preloaded.
-	 */
-	if (nr_allocated > alloc)
-		printv(2, "split(%u %u) allocated %u %u\n", old_order, new_order,
-							alloc, nr_allocated);
-}
-
-static void __multiorder_split(int old_order, int new_order)
-{
-	RADIX_TREE(tree, GFP_ATOMIC);
-	void **slot;
-	struct radix_tree_iter iter;
-	unsigned alloc;
-	struct item *item;
-
-	radix_tree_preload(GFP_KERNEL);
-	assert(item_insert_order(&tree, 0, old_order) == 0);
-	radix_tree_preload_end();
-
-	/* Wipe out the preloaded cache or it'll confuse check_mem() */
-	radix_tree_cpu_dead(0);
-
-	item = radix_tree_tag_set(&tree, 0, 2);
-
-	radix_tree_split_preload(old_order, new_order, GFP_KERNEL);
-	alloc = nr_allocated;
-	radix_tree_split(&tree, 0, new_order);
-	check_mem(old_order, new_order, alloc);
-	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		radix_tree_iter_replace(&tree, &iter, slot,
-					item_create(iter.index, new_order));
-	}
-	radix_tree_preload_end();
-
-	item_kill_tree(&tree);
-	free(item);
-}
-
-static void __multiorder_split2(int old_order, int new_order)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	void **slot;
-	struct radix_tree_iter iter;
-	struct radix_tree_node *node;
-	void *item;
-
-	__radix_tree_insert(&tree, 0, old_order, xa_mk_value(5));
-
-	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == xa_mk_value(5));
-	assert(node->nr_values > 0);
-
-	radix_tree_split(&tree, 0, new_order);
-	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		radix_tree_iter_replace(&tree, &iter, slot,
-					item_create(iter.index, new_order));
-	}
-
-	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item != xa_mk_value(5));
-	assert(node->nr_values == 0);
-
-	item_kill_tree(&tree);
-}
-
-static void __multiorder_split3(int old_order, int new_order)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	void **slot;
-	struct radix_tree_iter iter;
-	struct radix_tree_node *node;
-	void *item;
-
-	__radix_tree_insert(&tree, 0, old_order, xa_mk_value(5));
-
-	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == xa_mk_value(5));
-	assert(node->nr_values > 0);
-
-	radix_tree_split(&tree, 0, new_order);
-	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		radix_tree_iter_replace(&tree, &iter, slot, xa_mk_value(7));
-	}
-
-	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == xa_mk_value(7));
-	assert(node->nr_values > 0);
-
-	item_kill_tree(&tree);
-
-	__radix_tree_insert(&tree, 0, old_order, xa_mk_value(5));
-
-	item = __radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(item == xa_mk_value(5));
-	assert(node->nr_values > 0);
-
-	radix_tree_split(&tree, 0, new_order);
-	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		if (iter.index == (1 << new_order))
-			radix_tree_iter_replace(&tree, &iter, slot,
-						xa_mk_value(7));
-		else
-			radix_tree_iter_replace(&tree, &iter, slot, NULL);
-	}
-
-	item = __radix_tree_lookup(&tree, 1 << new_order, &node, NULL);
-	assert(item == xa_mk_value(7));
-	assert(node->count == node->nr_values);
-	do {
-		node = node->parent;
-		if (!node)
-			break;
-		assert(node->count == 1);
-		assert(node->nr_values == 0);
-	} while (1);
-
-	item_kill_tree(&tree);
-}
-
-static void multiorder_split(void)
-{
-	int i, j;
-
-	for (i = 3; i < 11; i++)
-		for (j = 0; j < i; j++) {
-			__multiorder_split(i, j);
-			__multiorder_split2(i, j);
-			__multiorder_split3(i, j);
-		}
-}
-
 static void multiorder_account(void)
 {
 	RADIX_TREE(tree, GFP_KERNEL);
@@ -702,8 +457,6 @@ void multiorder_checks(void)
 	multiorder_tag_tests();
 	multiorder_iteration();
 	multiorder_tagged_iteration();
-	multiorder_join();
-	multiorder_split();
 	multiorder_account();
 	multiorder_iteration_race();
 
-- 
cgit v1.2.3


From adb9d9c4ccb1ff0bf1d376e65f36aa5573c75c1a Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Mon, 9 Apr 2018 16:52:21 -0400
Subject: radix tree: Remove radix_tree_clear_tags

The page cache was the only user of this interface and it has now
been converted to the XArray.  Transform the test into a test of
xas_init_marks().

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/radix-tree.h           |  2 --
 lib/radix-tree.c                     | 13 ------------
 lib/test_xarray.c                    | 40 ++++++++++++++++++++++++++++++++++++
 tools/testing/radix-tree/tag_check.c | 29 --------------------------
 4 files changed, 40 insertions(+), 44 deletions(-)

(limited to 'tools')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 664d50c5c2ff..7b009af3bb1e 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -252,8 +252,6 @@ void radix_tree_iter_delete(struct radix_tree_root *,
 			struct radix_tree_iter *iter, void __rcu **slot);
 void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
 void *radix_tree_delete(struct radix_tree_root *, unsigned long);
-void radix_tree_clear_tags(struct radix_tree_root *, struct radix_tree_node *,
-			   void __rcu **slot);
 unsigned int radix_tree_gang_lookup(const struct radix_tree_root *,
 			void **results, unsigned long first_index,
 			unsigned int max_items);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index b57ddc3dbbbd..e92f2b6ae9c5 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1670,19 +1670,6 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
 }
 EXPORT_SYMBOL(radix_tree_delete);
 
-void radix_tree_clear_tags(struct radix_tree_root *root,
-			   struct radix_tree_node *node,
-			   void __rcu **slot)
-{
-	if (node) {
-		unsigned int tag, offset = get_slot_offset(node, slot);
-		for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
-			node_tag_clear(root, node, tag, offset);
-	} else {
-		root_tag_clear_all(root);
-	}
-}
-
 /**
  *	radix_tree_tagged - test whether any items in the tree are tagged
  *	@root:		radix tree root
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index 815daffdd8c9..ca86141641cb 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -213,12 +213,52 @@ static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index)
 	XA_BUG_ON(xa, !xa_empty(xa));
 }
 
+static noinline void check_xa_mark_2(struct xarray *xa)
+{
+	XA_STATE(xas, xa, 0);
+	unsigned long index;
+	unsigned int count = 0;
+	void *entry;
+
+	xa_store_index(xa, 0, GFP_KERNEL);
+	xa_set_mark(xa, 0, XA_MARK_0);
+	xas_lock(&xas);
+	xas_load(&xas);
+	xas_init_marks(&xas);
+	xas_unlock(&xas);
+	XA_BUG_ON(xa, !xa_get_mark(xa, 0, XA_MARK_0) == 0);
+
+	for (index = 3500; index < 4500; index++) {
+		xa_store_index(xa, index, GFP_KERNEL);
+		xa_set_mark(xa, index, XA_MARK_0);
+	}
+
+	xas_reset(&xas);
+	rcu_read_lock();
+	xas_for_each_marked(&xas, entry, ULONG_MAX, XA_MARK_0)
+		count++;
+	rcu_read_unlock();
+	XA_BUG_ON(xa, count != 1000);
+
+	xas_lock(&xas);
+	xas_for_each(&xas, entry, ULONG_MAX) {
+		xas_init_marks(&xas);
+		XA_BUG_ON(xa, !xa_get_mark(xa, xas.xa_index, XA_MARK_0));
+		XA_BUG_ON(xa, !xas_get_mark(&xas, XA_MARK_0));
+	}
+	xas_unlock(&xas);
+
+	xa_destroy(xa);
+}
+
 static noinline void check_xa_mark(struct xarray *xa)
 {
 	unsigned long index;
 
 	for (index = 0; index < 16384; index += 4)
 		check_xa_mark_1(xa, index);
+
+	check_xa_mark_2(xa);
 }
 
 static noinline void check_xa_shrink(struct xarray *xa)
diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c
index 543181e4847b..56a42f1c5ab0 100644
--- a/tools/testing/radix-tree/tag_check.c
+++ b/tools/testing/radix-tree/tag_check.c
@@ -331,34 +331,6 @@ static void single_check(void)
 	item_kill_tree(&tree);
 }
 
-void radix_tree_clear_tags_test(void)
-{
-	unsigned long index;
-	struct radix_tree_node *node;
-	struct radix_tree_iter iter;
-	void **slot;
-
-	RADIX_TREE(tree, GFP_KERNEL);
-
-	item_insert(&tree, 0);
-	item_tag_set(&tree, 0, 0);
-	__radix_tree_lookup(&tree, 0, &node, &slot);
-	radix_tree_clear_tags(&tree, node, slot);
-	assert(item_tag_get(&tree, 0, 0) == 0);
-
-	for (index = 0; index < 1000; index++) {
-		item_insert(&tree, index);
-		item_tag_set(&tree, index, 0);
-	}
-
-	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-		radix_tree_clear_tags(&tree, iter.node, slot);
-		assert(item_tag_get(&tree, iter.index, 0) == 0);
-	}
-
-	item_kill_tree(&tree);
-}
-
 void tag_check(void)
 {
 	single_check();
@@ -376,5 +348,4 @@ void tag_check(void)
 	thrash_tags();
 	rcu_barrier();
 	printv(2, "after thrash_tags: %d allocated\n", nr_allocated);
-	radix_tree_clear_tags_test();
 }
-- 
cgit v1.2.3


From 372266ba0267803564824b1c09f1bb7f3f3fc761 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Sat, 18 Aug 2018 07:09:22 -0400
Subject: radix tree test suite: Convert tag_tagged_items to XArray

The tag_tagged_items() function is supposed to test the page-writeback
tagging code.  Since that has been converted to the XArray, there's
not much point in testing the radix tree's tagging code.  This requires
using the pthread mutex embedded in the xarray instead of an external
lock, so remove the pthread mutexes which protect xarrays/radix trees.
Also remove radix_tree_iter_tag_set() as this was the last user.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/radix-tree.h                 |  2 --
 lib/radix-tree.c                           | 12 ----------
 tools/testing/radix-tree/iteration_check.c | 16 ++++++-------
 tools/testing/radix-tree/main.c            |  4 ++--
 tools/testing/radix-tree/multiorder.c      | 12 +++++-----
 tools/testing/radix-tree/regression1.c     | 17 +++++++-------
 tools/testing/radix-tree/regression2.c     |  8 +++----
 tools/testing/radix-tree/tag_check.c       |  4 ++--
 tools/testing/radix-tree/test.c            | 37 ++++++++++++------------------
 tools/testing/radix-tree/test.h            |  5 ++--
 10 files changed, 46 insertions(+), 71 deletions(-)

(limited to 'tools')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 7b009af3bb1e..9a1460488163 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -264,8 +264,6 @@ void *radix_tree_tag_clear(struct radix_tree_root *,
 			unsigned long index, unsigned int tag);
 int radix_tree_tag_get(const struct radix_tree_root *,
 			unsigned long index, unsigned int tag);
-void radix_tree_iter_tag_set(struct radix_tree_root *,
-		const struct radix_tree_iter *iter, unsigned int tag);
 void radix_tree_iter_tag_clear(struct radix_tree_root *,
 		const struct radix_tree_iter *iter, unsigned int tag);
 unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *,
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index e92f2b6ae9c5..f107dd2698e3 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1108,18 +1108,6 @@ void *radix_tree_tag_set(struct radix_tree_root *root,
 }
 EXPORT_SYMBOL(radix_tree_tag_set);
 
-/**
- * radix_tree_iter_tag_set - set a tag on the current iterator entry
- * @root:	radix tree root
- * @iter:	iterator state
- * @tag:	tag to set
- */
-void radix_tree_iter_tag_set(struct radix_tree_root *root,
-			const struct radix_tree_iter *iter, unsigned int tag)
-{
-	node_tag_set(root, iter->node, tag, iter_offset(iter));
-}
-
 static void node_tag_clear(struct radix_tree_root *root,
 				struct radix_tree_node *node,
 				unsigned int tag, unsigned int offset)
diff --git a/tools/testing/radix-tree/iteration_check.c b/tools/testing/radix-tree/iteration_check.c
index a92bab513701..d047327bb9ef 100644
--- a/tools/testing/radix-tree/iteration_check.c
+++ b/tools/testing/radix-tree/iteration_check.c
@@ -18,10 +18,9 @@
 
 #define NUM_THREADS	5
 #define MAX_IDX		100
-#define TAG		0
-#define NEW_TAG		1
+#define TAG		XA_MARK_0
+#define NEW_TAG		XA_MARK_1
 
-static pthread_mutex_t tree_lock = PTHREAD_MUTEX_INITIALIZER;
 static pthread_t threads[NUM_THREADS];
 static unsigned int seeds[3];
 static RADIX_TREE(tree, GFP_KERNEL);
@@ -38,7 +37,7 @@ static void *add_entries_fn(void *arg)
 		int order;
 
 		for (pgoff = 0; pgoff < MAX_IDX; pgoff++) {
-			pthread_mutex_lock(&tree_lock);
+			xa_lock(&tree);
 			for (order = max_order; order >= 0; order--) {
 				if (item_insert_order(&tree, pgoff, order)
 						== 0) {
@@ -46,7 +45,7 @@ static void *add_entries_fn(void *arg)
 					break;
 				}
 			}
-			pthread_mutex_unlock(&tree_lock);
+			xa_unlock(&tree);
 		}
 	}
 
@@ -150,9 +149,9 @@ static void *remove_entries_fn(void *arg)
 
 		pgoff = rand_r(&seeds[2]) % MAX_IDX;
 
-		pthread_mutex_lock(&tree_lock);
+		xa_lock(&tree);
 		item_delete(&tree, pgoff);
-		pthread_mutex_unlock(&tree_lock);
+		xa_unlock(&tree);
 	}
 
 	rcu_unregister_thread();
@@ -165,8 +164,7 @@ static void *tag_entries_fn(void *arg)
 	rcu_register_thread();
 
 	while (!test_complete) {
-		tag_tagged_items(&tree, &tree_lock, 0, MAX_IDX, 10, TAG,
-					NEW_TAG);
+		tag_tagged_items(&tree, 0, MAX_IDX, 10, TAG, NEW_TAG);
 	}
 	rcu_unregister_thread();
 	return NULL;
diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c
index 79589ea570ab..77a44c54998f 100644
--- a/tools/testing/radix-tree/main.c
+++ b/tools/testing/radix-tree/main.c
@@ -214,7 +214,7 @@ void copy_tag_check(void)
 	}
 
 //	printf("\ncopying tags...\n");
-	tagged = tag_tagged_items(&tree, NULL, start, end, ITEMS, 0, 1);
+	tagged = tag_tagged_items(&tree, start, end, ITEMS, XA_MARK_0, XA_MARK_1);
 
 //	printf("checking copied tags\n");
 	assert(tagged == count);
@@ -223,7 +223,7 @@ void copy_tag_check(void)
 	/* Copy tags in several rounds */
 //	printf("\ncopying tags...\n");
 	tmp = rand() % (count / 10 + 2);
-	tagged = tag_tagged_items(&tree, NULL, start, end, tmp, 0, 2);
+	tagged = tag_tagged_items(&tree, start, end, tmp, XA_MARK_0, XA_MARK_2);
 	assert(tagged == count);
 
 //	printf("%lu %lu %lu\n", tagged, tmp, count);
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 221e042d1b89..0436554a099a 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -59,7 +59,7 @@ static void __multiorder_tag_test(int index, int order)
 		assert(!radix_tree_tag_get(&tree, i, 1));
 	}
 
-	assert(tag_tagged_items(&tree, NULL, 0, ~0UL, 10, 0, 1) == 1);
+	assert(tag_tagged_items(&tree, 0, ~0UL, 10, XA_MARK_0, XA_MARK_1) == 1);
 	assert(radix_tree_tag_clear(&tree, index, 0));
 
 	for_each_index(i, base, order) {
@@ -87,7 +87,7 @@ static void __multiorder_tag_test2(unsigned order, unsigned long index2)
 	assert(radix_tree_tag_set(&tree, 0, 0));
 	assert(radix_tree_tag_set(&tree, index2, 0));
 
-	assert(tag_tagged_items(&tree, NULL, 0, ~0UL, 10, 0, 1) == 2);
+	assert(tag_tagged_items(&tree, 0, ~0UL, 10, XA_MARK_0, XA_MARK_1) == 2);
 
 	item_kill_tree(&tree);
 }
@@ -318,8 +318,8 @@ void multiorder_tagged_iteration(void)
 		}
 	}
 
-	assert(tag_tagged_items(&tree, NULL, 0, ~0UL, TAG_ENTRIES, 1, 2) ==
-				TAG_ENTRIES);
+	assert(tag_tagged_items(&tree, 0, ~0UL, TAG_ENTRIES, XA_MARK_1,
+				XA_MARK_2) == TAG_ENTRIES);
 
 	for (j = 0; j < 256; j++) {
 		int mask, k;
@@ -345,8 +345,8 @@ void multiorder_tagged_iteration(void)
 		}
 	}
 
-	assert(tag_tagged_items(&tree, NULL, 1, ~0UL, MT_NUM_ENTRIES * 2, 1, 0)
-			== TAG_ENTRIES);
+	assert(tag_tagged_items(&tree, 1, ~0UL, MT_NUM_ENTRIES * 2, XA_MARK_1,
+				XA_MARK_0) == TAG_ENTRIES);
 	i = 0;
 	radix_tree_for_each_tagged(slot, &tree, &iter, 0, 0) {
 		assert(iter.index == tag_index[i]);
diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c
index b4a4a7168986..a61c7bcbc72d 100644
--- a/tools/testing/radix-tree/regression1.c
+++ b/tools/testing/radix-tree/regression1.c
@@ -44,7 +44,6 @@
 #include "regression.h"
 
 static RADIX_TREE(mt_tree, GFP_KERNEL);
-static pthread_mutex_t mt_lock = PTHREAD_MUTEX_INITIALIZER;
 
 struct page {
 	pthread_mutex_t lock;
@@ -126,29 +125,29 @@ static void *regression1_fn(void *arg)
 			struct page *p;
 
 			p = page_alloc(0);
-			pthread_mutex_lock(&mt_lock);
+			xa_lock(&mt_tree);
 			radix_tree_insert(&mt_tree, 0, p);
-			pthread_mutex_unlock(&mt_lock);
+			xa_unlock(&mt_tree);
 
 			p = page_alloc(1);
-			pthread_mutex_lock(&mt_lock);
+			xa_lock(&mt_tree);
 			radix_tree_insert(&mt_tree, 1, p);
-			pthread_mutex_unlock(&mt_lock);
+			xa_unlock(&mt_tree);
 
-			pthread_mutex_lock(&mt_lock);
+			xa_lock(&mt_tree);
 			p = radix_tree_delete(&mt_tree, 1);
 			pthread_mutex_lock(&p->lock);
 			p->count--;
 			pthread_mutex_unlock(&p->lock);
-			pthread_mutex_unlock(&mt_lock);
+			xa_unlock(&mt_tree);
 			page_free(p);
 
-			pthread_mutex_lock(&mt_lock);
+			xa_lock(&mt_tree);
 			p = radix_tree_delete(&mt_tree, 0);
 			pthread_mutex_lock(&p->lock);
 			p->count--;
 			pthread_mutex_unlock(&p->lock);
-			pthread_mutex_unlock(&mt_lock);
+			xa_unlock(&mt_tree);
 			page_free(p);
 		}
 	} else {
diff --git a/tools/testing/radix-tree/regression2.c b/tools/testing/radix-tree/regression2.c
index 424b91c77831..f2c7e640a919 100644
--- a/tools/testing/radix-tree/regression2.c
+++ b/tools/testing/radix-tree/regression2.c
@@ -53,9 +53,9 @@
 #include "regression.h"
 #include "test.h"
 
-#define PAGECACHE_TAG_DIRTY     0
-#define PAGECACHE_TAG_WRITEBACK 1
-#define PAGECACHE_TAG_TOWRITE   2
+#define PAGECACHE_TAG_DIRTY     XA_MARK_0
+#define PAGECACHE_TAG_WRITEBACK XA_MARK_1
+#define PAGECACHE_TAG_TOWRITE   XA_MARK_2
 
 static RADIX_TREE(mt_tree, GFP_KERNEL);
 unsigned long page_count = 0;
@@ -92,7 +92,7 @@ void regression2_test(void)
 	/* 1. */
 	start = 0;
 	end = max_slots - 2;
-	tag_tagged_items(&mt_tree, NULL, start, end, 1,
+	tag_tagged_items(&mt_tree, start, end, 1,
 				PAGECACHE_TAG_DIRTY, PAGECACHE_TAG_TOWRITE);
 
 	/* 2. */
diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c
index 56a42f1c5ab0..f898957b1a19 100644
--- a/tools/testing/radix-tree/tag_check.c
+++ b/tools/testing/radix-tree/tag_check.c
@@ -24,7 +24,7 @@ __simple_checks(struct radix_tree_root *tree, unsigned long index, int tag)
 	item_tag_set(tree, index, tag);
 	ret = item_tag_get(tree, index, tag);
 	assert(ret != 0);
-	ret = tag_tagged_items(tree, NULL, first, ~0UL, 10, tag, !tag);
+	ret = tag_tagged_items(tree, first, ~0UL, 10, tag, !tag);
 	assert(ret == 1);
 	ret = item_tag_get(tree, index, !tag);
 	assert(ret != 0);
@@ -321,7 +321,7 @@ static void single_check(void)
 	assert(ret == 0);
 	verify_tag_consistency(&tree, 0);
 	verify_tag_consistency(&tree, 1);
-	ret = tag_tagged_items(&tree, NULL, first, 10, 10, 0, 1);
+	ret = tag_tagged_items(&tree, first, 10, 10, XA_MARK_0, XA_MARK_1);
 	assert(ret == 1);
 	ret = radix_tree_gang_lookup_tag(&tree, (void **)items, 0, BATCH, 1);
 	assert(ret == 1);
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 470419bfd49d..d70adcd03d35 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -176,35 +176,28 @@ void item_full_scan(struct radix_tree_root *root, unsigned long start,
 }
 
 /* Use the same pattern as tag_pages_for_writeback() in mm/page-writeback.c */
-int tag_tagged_items(struct radix_tree_root *root, pthread_mutex_t *lock,
-			unsigned long start, unsigned long end, unsigned batch,
-			unsigned iftag, unsigned thentag)
+int tag_tagged_items(struct xarray *xa, unsigned long start, unsigned long end,
+		unsigned batch, xa_mark_t iftag, xa_mark_t thentag)
 {
-	unsigned long tagged = 0;
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, xa, start);
+	unsigned int tagged = 0;
+	struct item *item;
 
 	if (batch == 0)
 		batch = 1;
 
-	if (lock)
-		pthread_mutex_lock(lock);
-	radix_tree_for_each_tagged(slot, root, &iter, start, iftag) {
-		if (iter.index > end)
-			break;
-		radix_tree_iter_tag_set(root, &iter, thentag);
-		tagged++;
-		if ((tagged % batch) != 0)
+	xas_lock_irq(&xas);
+	xas_for_each_marked(&xas, item, end, iftag) {
+		xas_set_mark(&xas, thentag);
+		if (++tagged % batch)
 			continue;
-		slot = radix_tree_iter_resume(slot, &iter);
-		if (lock) {
-			pthread_mutex_unlock(lock);
-			rcu_barrier();
-			pthread_mutex_lock(lock);
-		}
+
+		xas_pause(&xas);
+		xas_unlock_irq(&xas);
+		rcu_barrier();
+		xas_lock_irq(&xas);
 	}
-	if (lock)
-		pthread_mutex_unlock(lock);
+	xas_unlock_irq(&xas);
 
 	return tagged;
 }
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index 9532c18c6cb1..100e9a456f91 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -29,9 +29,8 @@ void item_full_scan(struct radix_tree_root *root, unsigned long start,
 			unsigned long nr, int chunk);
 void item_kill_tree(struct radix_tree_root *root);
 
-int tag_tagged_items(struct radix_tree_root *, pthread_mutex_t *,
-			unsigned long start, unsigned long end, unsigned batch,
-			unsigned iftag, unsigned thentag);
+int tag_tagged_items(struct xarray *, unsigned long start, unsigned long end,
+		unsigned batch, xa_mark_t iftag, xa_mark_t thentag);
 
 void xarray_tests(void);
 void tag_check(void);
-- 
cgit v1.2.3


From 47e0fab2b15155e33fdff777c791bebfd5855bbc Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Mon, 20 Aug 2018 15:48:46 -0400
Subject: radix tree test suite: Convert iteration test to XArray

With no code left in the kernel using the multiorder radix tree, convert
the iteration test from the radix tree to the XArray.  It's unlikely to
suffer the same bug as the radix tree, but this test will prevent that
bug from ever creeping into the XArray implementation.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/testing/radix-tree/iteration_check.c | 103 ++++++++++++++---------------
 tools/testing/radix-tree/test.c            |  17 +++--
 tools/testing/radix-tree/test.h            |   1 +
 3 files changed, 63 insertions(+), 58 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/radix-tree/iteration_check.c b/tools/testing/radix-tree/iteration_check.c
index d047327bb9ef..238db187aa15 100644
--- a/tools/testing/radix-tree/iteration_check.c
+++ b/tools/testing/radix-tree/iteration_check.c
@@ -1,5 +1,5 @@
 /*
- * iteration_check.c: test races having to do with radix tree iteration
+ * iteration_check.c: test races having to do with xarray iteration
  * Copyright (c) 2016 Intel Corporation
  * Author: Ross Zwisler <ross.zwisler@linux.intel.com>
  *
@@ -12,7 +12,6 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  */
-#include <linux/radix-tree.h>
 #include <pthread.h>
 #include "test.h"
 
@@ -23,29 +22,44 @@
 
 static pthread_t threads[NUM_THREADS];
 static unsigned int seeds[3];
-static RADIX_TREE(tree, GFP_KERNEL);
+static DEFINE_XARRAY(array);
 static bool test_complete;
 static int max_order;
 
-/* relentlessly fill the tree with tagged entries */
+void my_item_insert(struct xarray *xa, unsigned long index)
+{
+	XA_STATE(xas, xa, index);
+	struct item *item = item_create(index, 0);
+	int order;
+
+retry:
+	xas_lock(&xas);
+	for (order = max_order; order >= 0; order--) {
+		xas_set_order(&xas, index, order);
+		item->order = order;
+		if (xas_find_conflict(&xas))
+			continue;
+		xas_store(&xas, item);
+		xas_set_mark(&xas, TAG);
+		break;
+	}
+	xas_unlock(&xas);
+	if (xas_nomem(&xas, GFP_KERNEL))
+		goto retry;
+	if (order < 0)
+		free(item);
+}
+
+/* relentlessly fill the array with tagged entries */
 static void *add_entries_fn(void *arg)
 {
 	rcu_register_thread();
 
 	while (!test_complete) {
 		unsigned long pgoff;
-		int order;
 
 		for (pgoff = 0; pgoff < MAX_IDX; pgoff++) {
-			xa_lock(&tree);
-			for (order = max_order; order >= 0; order--) {
-				if (item_insert_order(&tree, pgoff, order)
-						== 0) {
-					item_tag_set(&tree, pgoff, TAG);
-					break;
-				}
-			}
-			xa_unlock(&tree);
+			my_item_insert(&array, pgoff);
 		}
 	}
 
@@ -55,33 +69,25 @@ static void *add_entries_fn(void *arg)
 }
 
 /*
- * Iterate over the tagged entries, doing a radix_tree_iter_retry() as we find
- * things that have been removed and randomly resetting our iteration to the
- * next chunk with radix_tree_iter_resume().  Both radix_tree_iter_retry() and
- * radix_tree_iter_resume() cause radix_tree_next_slot() to be called with a
- * NULL 'slot' variable.
+ * Iterate over tagged entries, retrying when we find ourselves in a deleted
+ * node and randomly pausing the iteration.
  */
 static void *tagged_iteration_fn(void *arg)
 {
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, &array, 0);
+	void *entry;
 
 	rcu_register_thread();
 
 	while (!test_complete) {
+		xas_set(&xas, 0);
 		rcu_read_lock();
-		radix_tree_for_each_tagged(slot, &tree, &iter, 0, TAG) {
-			void *entry = radix_tree_deref_slot(slot);
-			if (unlikely(!entry))
+		xas_for_each_marked(&xas, entry, ULONG_MAX, TAG) {
+			if (xas_retry(&xas, entry))
 				continue;
 
-			if (radix_tree_deref_retry(entry)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
-
 			if (rand_r(&seeds[0]) % 50 == 0) {
-				slot = radix_tree_iter_resume(slot, &iter);
+				xas_pause(&xas);
 				rcu_read_unlock();
 				rcu_barrier();
 				rcu_read_lock();
@@ -96,33 +102,25 @@ static void *tagged_iteration_fn(void *arg)
 }
 
 /*
- * Iterate over the entries, doing a radix_tree_iter_retry() as we find things
- * that have been removed and randomly resetting our iteration to the next
- * chunk with radix_tree_iter_resume().  Both radix_tree_iter_retry() and
- * radix_tree_iter_resume() cause radix_tree_next_slot() to be called with a
- * NULL 'slot' variable.
+ * Iterate over the entries, retrying when we find ourselves in a deleted
+ * node and randomly pausing the iteration.
  */
 static void *untagged_iteration_fn(void *arg)
 {
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, &array, 0);
+	void *entry;
 
 	rcu_register_thread();
 
 	while (!test_complete) {
+		xas_set(&xas, 0);
 		rcu_read_lock();
-		radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-			void *entry = radix_tree_deref_slot(slot);
-			if (unlikely(!entry))
+		xas_for_each(&xas, entry, ULONG_MAX) {
+			if (xas_retry(&xas, entry))
 				continue;
 
-			if (radix_tree_deref_retry(entry)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
-
 			if (rand_r(&seeds[1]) % 50 == 0) {
-				slot = radix_tree_iter_resume(slot, &iter);
+				xas_pause(&xas);
 				rcu_read_unlock();
 				rcu_barrier();
 				rcu_read_lock();
@@ -137,7 +135,7 @@ static void *untagged_iteration_fn(void *arg)
 }
 
 /*
- * Randomly remove entries to help induce radix_tree_iter_retry() calls in the
+ * Randomly remove entries to help induce retries in the
  * two iteration functions.
  */
 static void *remove_entries_fn(void *arg)
@@ -146,12 +144,13 @@ static void *remove_entries_fn(void *arg)
 
 	while (!test_complete) {
 		int pgoff;
+		struct item *item;
 
 		pgoff = rand_r(&seeds[2]) % MAX_IDX;
 
-		xa_lock(&tree);
-		item_delete(&tree, pgoff);
-		xa_unlock(&tree);
+		item = xa_erase(&array, pgoff);
+		if (item)
+			item_free(item, pgoff);
 	}
 
 	rcu_unregister_thread();
@@ -164,7 +163,7 @@ static void *tag_entries_fn(void *arg)
 	rcu_register_thread();
 
 	while (!test_complete) {
-		tag_tagged_items(&tree, 0, MAX_IDX, 10, TAG, NEW_TAG);
+		tag_tagged_items(&array, 0, MAX_IDX, 10, TAG, NEW_TAG);
 	}
 	rcu_unregister_thread();
 	return NULL;
@@ -215,5 +214,5 @@ void iteration_test(unsigned order, unsigned test_duration)
 		}
 	}
 
-	item_kill_tree(&tree);
+	item_kill_tree(&array);
 }
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index d70adcd03d35..32973dd51ec5 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -63,16 +63,21 @@ void item_sanity(struct item *item, unsigned long index)
 	assert((item->index | mask) == (index | mask));
 }
 
+void item_free(struct item *item, unsigned long index)
+{
+	item_sanity(item, index);
+	free(item);
+}
+
 int item_delete(struct radix_tree_root *root, unsigned long index)
 {
 	struct item *item = radix_tree_delete(root, index);
 
-	if (item) {
-		item_sanity(item, index);
-		free(item);
-		return 1;
-	}
-	return 0;
+	if (!item)
+		return 0;
+
+	item_free(item, index);
+	return 1;
 }
 
 static void item_free_rcu(struct rcu_head *head)
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index 100e9a456f91..a2f53c889a31 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -14,6 +14,7 @@ struct item *item_create(unsigned long index, unsigned int order);
 int __item_insert(struct radix_tree_root *root, struct item *item);
 int item_insert(struct radix_tree_root *root, unsigned long index);
 void item_sanity(struct item *item, unsigned long index);
+void item_free(struct item *item, unsigned long index);
 int item_insert_order(struct radix_tree_root *root, unsigned long index,
 			unsigned order);
 int item_delete(struct radix_tree_root *root, unsigned long index);
-- 
cgit v1.2.3


From d6427f8179b5dd65eb468c61fc8cc24657c336c9 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 28 Aug 2018 16:13:16 -0400
Subject: xarray: Move multiorder account test in-kernel

Move this test to the in-kernel test suite, and enhance it to test
several different orders.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 lib/test_xarray.c                     | 32 ++++++++++++++++++++++++++++++++
 tools/testing/radix-tree/multiorder.c | 24 ------------------------
 2 files changed, 32 insertions(+), 24 deletions(-)

(limited to 'tools')

diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index ca86141641cb..38cab4ccb24e 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -1019,6 +1019,37 @@ static noinline void check_workingset(struct xarray *xa, unsigned long index)
 	XA_BUG_ON(xa, !xa_empty(xa));
 }
 
+/*
+ * Check that the pointer / value / sibling entries are accounted the
+ * way we expect them to be.
+ */
+static noinline void check_account(struct xarray *xa)
+{
+#ifdef CONFIG_XARRAY_MULTI
+	unsigned int order;
+
+	for (order = 1; order < 12; order++) {
+		XA_STATE(xas, xa, 1 << order);
+
+		xa_store_order(xa, 0, order, xa, GFP_KERNEL);
+		xas_load(&xas);
+		XA_BUG_ON(xa, xas.xa_node->count == 0);
+		XA_BUG_ON(xa, xas.xa_node->count > (1 << order));
+		XA_BUG_ON(xa, xas.xa_node->nr_values != 0);
+
+		xa_store_order(xa, 1 << order, order, xa_mk_value(1 << order),
+				GFP_KERNEL);
+		XA_BUG_ON(xa, xas.xa_node->count != xas.xa_node->nr_values * 2);
+
+		xa_erase(xa, 1 << order);
+		XA_BUG_ON(xa, xas.xa_node->nr_values != 0);
+
+		xa_erase(xa, 0);
+		XA_BUG_ON(xa, !xa_empty(xa));
+	}
+#endif
+}
+
 static noinline void check_destroy(struct xarray *xa)
 {
 	unsigned long index;
@@ -1068,6 +1099,7 @@ static int xarray_checks(void)
 	check_xa_alloc();
 	check_find(&array);
 	check_find_entry(&array);
+	check_account(&array);
 	check_destroy(&array);
 	check_move(&array);
 	check_create_range(&array);
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 0436554a099a..dc27a3da210a 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -356,29 +356,6 @@ void multiorder_tagged_iteration(void)
 	item_kill_tree(&tree);
 }
 
-static void multiorder_account(void)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	struct radix_tree_node *node;
-	void **slot;
-
-	item_insert_order(&tree, 0, 5);
-
-	__radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5));
-	__radix_tree_lookup(&tree, 0, &node, NULL);
-	assert(node->count == node->nr_values * 2);
-	radix_tree_delete(&tree, 1 << 5);
-	assert(node->nr_values == 0);
-
-	__radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5));
-	__radix_tree_lookup(&tree, 1 << 5, &node, &slot);
-	assert(node->count == node->nr_values * 2);
-	__radix_tree_replace(&tree, node, slot, NULL);
-	assert(node->nr_values == 0);
-
-	item_kill_tree(&tree);
-}
-
 bool stop_iteration = false;
 
 static void *creator_func(void *ptr)
@@ -457,7 +434,6 @@ void multiorder_checks(void)
 	multiorder_tag_tests();
 	multiorder_iteration();
 	multiorder_tagged_iteration();
-	multiorder_account();
 	multiorder_iteration_race();
 
 	radix_tree_cpu_dead(0);
-- 
cgit v1.2.3


From 93eb07f72c8d86f8fe5e90907df1cc037f6ffbb7 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Sat, 8 Sep 2018 12:09:52 -0400
Subject: xarray: Move multiorder_shrink to kernel tests

Test this functionality inside the kernel as well as in userspace.
Also remove insert_bug() as there's no comparable thing to test
in the XArray code.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 lib/test_xarray.c                     |  37 ++++++++
 tools/testing/radix-tree/multiorder.c | 173 ----------------------------------
 2 files changed, 37 insertions(+), 173 deletions(-)

(limited to 'tools')

diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index 38cab4ccb24e..ff94b54a926d 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -199,9 +199,25 @@ static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index)
 		xa_store_order(xa, index, order, xa_mk_value(index),
 				GFP_KERNEL);
 		for (i = base; i < next; i++) {
+			XA_STATE(xas, xa, i);
+			unsigned int seen = 0;
+			void *entry;
+
 			XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_0));
 			XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_1));
 			XA_BUG_ON(xa, xa_get_mark(xa, i, XA_MARK_2));
+
+			/* We should see two elements in the array */
+			xas_for_each(&xas, entry, ULONG_MAX)
+				seen++;
+			XA_BUG_ON(xa, seen != 2);
+
+			/* One of which is marked */
+			xas_set(&xas, 0);
+			seen = 0;
+			xas_for_each_marked(&xas, entry, ULONG_MAX, XA_MARK_0)
+				seen++;
+			XA_BUG_ON(xa, seen != 1);
 		}
 		XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_0));
 		XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_1));
@@ -265,6 +281,8 @@ static noinline void check_xa_shrink(struct xarray *xa)
 {
 	XA_STATE(xas, xa, 1);
 	struct xa_node *node;
+	unsigned int order;
+	unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 15 : 1;
 
 	XA_BUG_ON(xa, !xa_empty(xa));
 	XA_BUG_ON(xa, xa_store_index(xa, 0, GFP_KERNEL) != NULL);
@@ -287,6 +305,25 @@ static noinline void check_xa_shrink(struct xarray *xa)
 	XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(0));
 	xa_erase_index(xa, 0);
 	XA_BUG_ON(xa, !xa_empty(xa));
+
+	for (order = 0; order < max_order; order++) {
+		unsigned long max = (1UL << order) - 1;
+		xa_store_order(xa, 0, order, xa_mk_value(0), GFP_KERNEL);
+		XA_BUG_ON(xa, xa_load(xa, max) != xa_mk_value(0));
+		XA_BUG_ON(xa, xa_load(xa, max + 1) != NULL);
+		rcu_read_lock();
+		node = xa_head(xa);
+		rcu_read_unlock();
+		XA_BUG_ON(xa, xa_store_index(xa, ULONG_MAX, GFP_KERNEL) !=
+				NULL);
+		rcu_read_lock();
+		XA_BUG_ON(xa, xa_head(xa) == node);
+		rcu_read_unlock();
+		XA_BUG_ON(xa, xa_load(xa, max + 1) != NULL);
+		xa_erase_index(xa, ULONG_MAX);
+		XA_BUG_ON(xa, xa->xa_head != node);
+		xa_erase_index(xa, 0);
+	}
 }
 
 static noinline void check_cmpxchg(struct xarray *xa)
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index dc27a3da210a..a60c03287e9c 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -20,127 +20,6 @@
 
 #include "test.h"
 
-#define for_each_index(i, base, order) \
-	for (i = base; i < base + (1 << order); i++)
-
-static void __multiorder_tag_test(int index, int order)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	int base, err, i;
-
-	/* our canonical entry */
-	base = index & ~((1 << order) - 1);
-
-	printv(2, "Multiorder tag test with index %d, canonical entry %d\n",
-			index, base);
-
-	err = item_insert_order(&tree, index, order);
-	assert(!err);
-
-	/*
-	 * Verify we get collisions for covered indices.  We try and fail to
-	 * insert a value entry so we don't leak memory via
-	 * item_insert_order().
-	 */
-	for_each_index(i, base, order) {
-		err = __radix_tree_insert(&tree, i, order, xa_mk_value(0xA0));
-		assert(err == -EEXIST);
-	}
-
-	for_each_index(i, base, order) {
-		assert(!radix_tree_tag_get(&tree, i, 0));
-		assert(!radix_tree_tag_get(&tree, i, 1));
-	}
-
-	assert(radix_tree_tag_set(&tree, index, 0));
-
-	for_each_index(i, base, order) {
-		assert(radix_tree_tag_get(&tree, i, 0));
-		assert(!radix_tree_tag_get(&tree, i, 1));
-	}
-
-	assert(tag_tagged_items(&tree, 0, ~0UL, 10, XA_MARK_0, XA_MARK_1) == 1);
-	assert(radix_tree_tag_clear(&tree, index, 0));
-
-	for_each_index(i, base, order) {
-		assert(!radix_tree_tag_get(&tree, i, 0));
-		assert(radix_tree_tag_get(&tree, i, 1));
-	}
-
-	assert(radix_tree_tag_clear(&tree, index, 1));
-
-	assert(!radix_tree_tagged(&tree, 0));
-	assert(!radix_tree_tagged(&tree, 1));
-
-	item_kill_tree(&tree);
-}
-
-static void __multiorder_tag_test2(unsigned order, unsigned long index2)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	unsigned long index = (1 << order);
-	index2 += index;
-
-	assert(item_insert_order(&tree, 0, order) == 0);
-	assert(item_insert(&tree, index2) == 0);
-
-	assert(radix_tree_tag_set(&tree, 0, 0));
-	assert(radix_tree_tag_set(&tree, index2, 0));
-
-	assert(tag_tagged_items(&tree, 0, ~0UL, 10, XA_MARK_0, XA_MARK_1) == 2);
-
-	item_kill_tree(&tree);
-}
-
-static void multiorder_tag_tests(void)
-{
-	int i, j;
-
-	/* test multi-order entry for indices 0-7 with no sibling pointers */
-	__multiorder_tag_test(0, 3);
-	__multiorder_tag_test(5, 3);
-
-	/* test multi-order entry for indices 8-15 with no sibling pointers */
-	__multiorder_tag_test(8, 3);
-	__multiorder_tag_test(15, 3);
-
-	/*
-	 * Our order 5 entry covers indices 0-31 in a tree with height=2.
-	 * This is broken up as follows:
-	 * 0-7:		canonical entry
-	 * 8-15:	sibling 1
-	 * 16-23:	sibling 2
-	 * 24-31:	sibling 3
-	 */
-	__multiorder_tag_test(0, 5);
-	__multiorder_tag_test(29, 5);
-
-	/* same test, but with indices 32-63 */
-	__multiorder_tag_test(32, 5);
-	__multiorder_tag_test(44, 5);
-
-	/*
-	 * Our order 8 entry covers indices 0-255 in a tree with height=3.
-	 * This is broken up as follows:
-	 * 0-63:	canonical entry
-	 * 64-127:	sibling 1
-	 * 128-191:	sibling 2
-	 * 192-255:	sibling 3
-	 */
-	__multiorder_tag_test(0, 8);
-	__multiorder_tag_test(190, 8);
-
-	/* same test, but with indices 256-511 */
-	__multiorder_tag_test(256, 8);
-	__multiorder_tag_test(300, 8);
-
-	__multiorder_tag_test(0x12345678UL, 8);
-
-	for (i = 1; i < 10; i++)
-		for (j = 0; j < (10 << i); j++)
-			__multiorder_tag_test2(i, j);
-}
-
 static void multiorder_check(unsigned long index, int order)
 {
 	unsigned long i;
@@ -181,53 +60,6 @@ static void multiorder_check(unsigned long index, int order)
 		item_check_absent(&tree, i);
 }
 
-static void multiorder_shrink(unsigned long index, int order)
-{
-	unsigned long i;
-	unsigned long max = 1 << order;
-	RADIX_TREE(tree, GFP_KERNEL);
-	struct radix_tree_node *node;
-
-	printv(2, "Multiorder shrink index %ld, order %d\n", index, order);
-
-	assert(item_insert_order(&tree, 0, order) == 0);
-
-	node = tree.xa_head;
-
-	assert(item_insert(&tree, index) == 0);
-	assert(node != tree.xa_head);
-
-	assert(item_delete(&tree, index) != 0);
-	assert(node == tree.xa_head);
-
-	for (i = 0; i < max; i++) {
-		struct item *item = item_lookup(&tree, i);
-		assert(item != 0);
-		assert(item->index == 0);
-	}
-	for (i = max; i < 2*max; i++)
-		item_check_absent(&tree, i);
-
-	if (!item_delete(&tree, 0)) {
-		printv(2, "failed to delete index %ld (order %d)\n", index, order);
-		abort();
-	}
-
-	for (i = 0; i < 2*max; i++)
-		item_check_absent(&tree, i);
-}
-
-static void multiorder_insert_bug(void)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-
-	item_insert(&tree, 0);
-	radix_tree_tag_set(&tree, 0, 0);
-	item_insert_order(&tree, 3 << 6, 6);
-
-	item_kill_tree(&tree);
-}
-
 void multiorder_iteration(void)
 {
 	RADIX_TREE(tree, GFP_KERNEL);
@@ -427,11 +259,6 @@ void multiorder_checks(void)
 		multiorder_check((1UL << i) + 1, i);
 	}
 
-	for (i = 0; i < 15; i++)
-		multiorder_shrink((1UL << (i + RADIX_TREE_MAP_SHIFT)), i);
-
-	multiorder_insert_bug();
-	multiorder_tag_tests();
 	multiorder_iteration();
 	multiorder_tagged_iteration();
 	multiorder_iteration_race();
-- 
cgit v1.2.3


From 4f06d6302da682157890f72c0573e12a73536814 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Sun, 9 Sep 2018 01:52:17 -0400
Subject: xarray: Move multiorder_check to in-kernel tests

This version is a little less thorough in order to be a little quicker,
but tests the important edge cases.  Also test adding a multiorder entry
at a non-canonical index, and erasing it.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 lib/test_xarray.c                     | 44 ++++++++++++++++++++++++++++++++
 tools/testing/radix-tree/multiorder.c | 48 -----------------------------------
 2 files changed, 44 insertions(+), 48 deletions(-)

(limited to 'tools')

diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index ff94b54a926d..0f06a93b4d0e 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -422,6 +422,43 @@ static noinline void check_xas_erase(struct xarray *xa)
 	}
 }
 
+#ifdef CONFIG_XARRAY_MULTI
+static noinline void check_multi_store_1(struct xarray *xa, unsigned long index,
+		unsigned int order)
+{
+	XA_STATE(xas, xa, index);
+	unsigned long min = index & ~((1UL << order) - 1);
+	unsigned long max = min + (1UL << order);
+
+	xa_store_order(xa, index, order, xa_mk_value(index), GFP_KERNEL);
+	XA_BUG_ON(xa, xa_load(xa, min) != xa_mk_value(index));
+	XA_BUG_ON(xa, xa_load(xa, max - 1) != xa_mk_value(index));
+	XA_BUG_ON(xa, xa_load(xa, max) != NULL);
+	XA_BUG_ON(xa, xa_load(xa, min - 1) != NULL);
+
+	XA_BUG_ON(xa, xas_store(&xas, xa_mk_value(min)) != xa_mk_value(index));
+	XA_BUG_ON(xa, xa_load(xa, min) != xa_mk_value(min));
+	XA_BUG_ON(xa, xa_load(xa, max - 1) != xa_mk_value(min));
+	XA_BUG_ON(xa, xa_load(xa, max) != NULL);
+	XA_BUG_ON(xa, xa_load(xa, min - 1) != NULL);
+
+	xa_erase_index(xa, min);
+	XA_BUG_ON(xa, !xa_empty(xa));
+}
+
+static noinline void check_multi_store_2(struct xarray *xa, unsigned long index,
+		unsigned int order)
+{
+	XA_STATE(xas, xa, index);
+	xa_store_order(xa, index, order, xa_mk_value(0), GFP_KERNEL);
+
+	XA_BUG_ON(xa, xas_store(&xas, xa_mk_value(1)) != xa_mk_value(0));
+	XA_BUG_ON(xa, xas.xa_index != index);
+	XA_BUG_ON(xa, xas_store(&xas, NULL) != xa_mk_value(1));
+	XA_BUG_ON(xa, !xa_empty(xa));
+}
+#endif
+
 static noinline void check_multi_store(struct xarray *xa)
 {
 #ifdef CONFIG_XARRAY_MULTI
@@ -487,6 +524,13 @@ static noinline void check_multi_store(struct xarray *xa)
 			XA_BUG_ON(xa, !xa_empty(xa));
 		}
 	}
+
+	for (i = 0; i < 20; i++) {
+		check_multi_store_1(xa, 200, i);
+		check_multi_store_1(xa, 0, i);
+		check_multi_store_1(xa, (1UL << i) + 1, i);
+	}
+	check_multi_store_2(xa, 4095, 9);
 #endif
 }
 
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index a60c03287e9c..6e8d66c2aa89 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -20,46 +20,6 @@
 
 #include "test.h"
 
-static void multiorder_check(unsigned long index, int order)
-{
-	unsigned long i;
-	unsigned long min = index & ~((1UL << order) - 1);
-	unsigned long max = min + (1UL << order);
-	void **slot;
-	struct item *item2 = item_create(min, order);
-	RADIX_TREE(tree, GFP_KERNEL);
-
-	printv(2, "Multiorder index %ld, order %d\n", index, order);
-
-	assert(item_insert_order(&tree, index, order) == 0);
-
-	for (i = min; i < max; i++) {
-		struct item *item = item_lookup(&tree, i);
-		assert(item != 0);
-		assert(item->index == index);
-	}
-	for (i = 0; i < min; i++)
-		item_check_absent(&tree, i);
-	for (i = max; i < 2*max; i++)
-		item_check_absent(&tree, i);
-	for (i = min; i < max; i++)
-		assert(radix_tree_insert(&tree, i, item2) == -EEXIST);
-
-	slot = radix_tree_lookup_slot(&tree, index);
-	free(*slot);
-	radix_tree_replace_slot(&tree, slot, item2);
-	for (i = min; i < max; i++) {
-		struct item *item = item_lookup(&tree, i);
-		assert(item != 0);
-		assert(item->index == min);
-	}
-
-	assert(item_delete(&tree, min) != 0);
-
-	for (i = 0; i < 2*max; i++)
-		item_check_absent(&tree, i);
-}
-
 void multiorder_iteration(void)
 {
 	RADIX_TREE(tree, GFP_KERNEL);
@@ -251,14 +211,6 @@ static void multiorder_iteration_race(void)
 
 void multiorder_checks(void)
 {
-	int i;
-
-	for (i = 0; i < 20; i++) {
-		multiorder_check(200, i);
-		multiorder_check(0, i);
-		multiorder_check((1UL << i) + 1, i);
-	}
-
 	multiorder_iteration();
 	multiorder_tagged_iteration();
 	multiorder_iteration_race();
-- 
cgit v1.2.3


From 9076b33d7dad8e316c90918845417e85347f682c Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Wed, 12 Sep 2018 12:52:45 -0400
Subject: radix tree test suite: Remove __item_insert

Inline it into its one caller

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/testing/radix-tree/test.c | 7 +------
 tools/testing/radix-tree/test.h | 1 -
 2 files changed, 1 insertion(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 32973dd51ec5..5991cfd34f2b 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -25,11 +25,6 @@ int item_tag_get(struct radix_tree_root *root, unsigned long index, int tag)
 	return radix_tree_tag_get(root, index, tag);
 }
 
-int __item_insert(struct radix_tree_root *root, struct item *item)
-{
-	return __radix_tree_insert(root, item->index, item->order, item);
-}
-
 struct item *item_create(unsigned long index, unsigned int order)
 {
 	struct item *ret = malloc(sizeof(*ret));
@@ -43,7 +38,7 @@ int item_insert_order(struct radix_tree_root *root, unsigned long index,
 			unsigned order)
 {
 	struct item *item = item_create(index, order);
-	int err = __item_insert(root, item);
+	int err = __radix_tree_insert(root, item->index, item->order, item);
 	if (err)
 		free(item);
 	return err;
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index a2f53c889a31..28961a08828e 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -11,7 +11,6 @@ struct item {
 };
 
 struct item *item_create(unsigned long index, unsigned int order);
-int __item_insert(struct radix_tree_root *root, struct item *item);
 int item_insert(struct radix_tree_root *root, unsigned long index);
 void item_sanity(struct item *item, unsigned long index);
 void item_free(struct item *item, unsigned long index);
-- 
cgit v1.2.3


From 879a9ae7b5bc046f195a725d62bbc96258e5d0c8 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Wed, 12 Sep 2018 23:12:47 -0400
Subject: radix tree test suite: Remove multiorder benchmarking

The multiorder radix tree code is being removed, so remove the
benchmarking of its performance.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/testing/radix-tree/benchmark.c | 50 +++++++++++++++---------------------
 1 file changed, 21 insertions(+), 29 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c
index 35741b9c2a4a..7e195ed8e92d 100644
--- a/tools/testing/radix-tree/benchmark.c
+++ b/tools/testing/radix-tree/benchmark.c
@@ -17,9 +17,6 @@
 #include <time.h>
 #include "test.h"
 
-#define for_each_index(i, base, order) \
-	        for (i = base; i < base + (1 << order); i++)
-
 #define NSEC_PER_SEC	1000000000L
 
 static long long benchmark_iter(struct radix_tree_root *root, bool tagged)
@@ -61,7 +58,7 @@ again:
 }
 
 static void benchmark_insert(struct radix_tree_root *root,
-			     unsigned long size, unsigned long step, int order)
+			     unsigned long size, unsigned long step)
 {
 	struct timespec start, finish;
 	unsigned long index;
@@ -70,19 +67,19 @@ static void benchmark_insert(struct radix_tree_root *root,
 	clock_gettime(CLOCK_MONOTONIC, &start);
 
 	for (index = 0 ; index < size ; index += step)
-		item_insert_order(root, index, order);
+		item_insert(root, index);
 
 	clock_gettime(CLOCK_MONOTONIC, &finish);
 
 	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
 	       (finish.tv_nsec - start.tv_nsec);
 
-	printv(2, "Size: %8ld, step: %8ld, order: %d, insertion: %15lld ns\n",
-		size, step, order, nsec);
+	printv(2, "Size: %8ld, step: %8ld, insertion: %15lld ns\n",
+		size, step, nsec);
 }
 
 static void benchmark_tagging(struct radix_tree_root *root,
-			     unsigned long size, unsigned long step, int order)
+			     unsigned long size, unsigned long step)
 {
 	struct timespec start, finish;
 	unsigned long index;
@@ -98,49 +95,48 @@ static void benchmark_tagging(struct radix_tree_root *root,
 	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
 	       (finish.tv_nsec - start.tv_nsec);
 
-	printv(2, "Size: %8ld, step: %8ld, order: %d, tagging: %17lld ns\n",
-		size, step, order, nsec);
+	printv(2, "Size: %8ld, step: %8ld, tagging: %17lld ns\n",
+		size, step, nsec);
 }
 
 static void benchmark_delete(struct radix_tree_root *root,
-			     unsigned long size, unsigned long step, int order)
+			     unsigned long size, unsigned long step)
 {
 	struct timespec start, finish;
-	unsigned long index, i;
+	unsigned long index;
 	long long nsec;
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
 
 	for (index = 0 ; index < size ; index += step)
-		for_each_index(i, index, order)
-			item_delete(root, i);
+		item_delete(root, index);
 
 	clock_gettime(CLOCK_MONOTONIC, &finish);
 
 	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
 	       (finish.tv_nsec - start.tv_nsec);
 
-	printv(2, "Size: %8ld, step: %8ld, order: %d, deletion: %16lld ns\n",
-		size, step, order, nsec);
+	printv(2, "Size: %8ld, step: %8ld, deletion: %16lld ns\n",
+		size, step, nsec);
 }
 
-static void benchmark_size(unsigned long size, unsigned long step, int order)
+static void benchmark_size(unsigned long size, unsigned long step)
 {
 	RADIX_TREE(tree, GFP_KERNEL);
 	long long normal, tagged;
 
-	benchmark_insert(&tree, size, step, order);
-	benchmark_tagging(&tree, size, step, order);
+	benchmark_insert(&tree, size, step);
+	benchmark_tagging(&tree, size, step);
 
 	tagged = benchmark_iter(&tree, true);
 	normal = benchmark_iter(&tree, false);
 
-	printv(2, "Size: %8ld, step: %8ld, order: %d, tagged iteration: %8lld ns\n",
-		size, step, order, tagged);
-	printv(2, "Size: %8ld, step: %8ld, order: %d, normal iteration: %8lld ns\n",
-		size, step, order, normal);
+	printv(2, "Size: %8ld, step: %8ld, tagged iteration: %8lld ns\n",
+		size, step, tagged);
+	printv(2, "Size: %8ld, step: %8ld, normal iteration: %8lld ns\n",
+		size, step, normal);
 
-	benchmark_delete(&tree, size, step, order);
+	benchmark_delete(&tree, size, step);
 
 	item_kill_tree(&tree);
 	rcu_barrier();
@@ -158,9 +154,5 @@ void benchmark(void)
 
 	for (c = 0; size[c]; c++)
 		for (s = 0; step[s]; s++)
-			benchmark_size(size[c], step[s], 0);
-
-	for (c = 0; size[c]; c++)
-		for (s = 0; step[s]; s++)
-			benchmark_size(size[c], step[s] << 9, 9);
+			benchmark_size(size[c], step[s]);
 }
-- 
cgit v1.2.3


From 4bb53bdda0d1e061035774ed4868bdeb4d889044 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Wed, 12 Sep 2018 23:29:32 -0400
Subject: radix tree tests: Move item_insert_order

The remaining tests are not suitable for moving in-kernel, so move
item_insert_order() into multiorder.c, make it static and make it use
the XArray.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/testing/radix-tree/multiorder.c | 19 +++++++++++++++++++
 tools/testing/radix-tree/test.c       | 12 +++---------
 tools/testing/radix-tree/test.h       |  2 --
 3 files changed, 22 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 6e8d66c2aa89..8c41dca272b1 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -20,6 +20,25 @@
 
 #include "test.h"
 
+static int item_insert_order(struct xarray *xa, unsigned long index,
+			unsigned order)
+{
+	XA_STATE_ORDER(xas, xa, index, order);
+	struct item *item = item_create(index, order);
+
+	do {
+		xas_lock(&xas);
+		xas_store(&xas, item);
+		xas_unlock(&xas);
+	} while (xas_nomem(&xas, GFP_KERNEL));
+
+	if (!xas_error(&xas))
+		return 0;
+
+	free(item);
+	return xas_error(&xas);
+}
+
 void multiorder_iteration(void)
 {
 	RADIX_TREE(tree, GFP_KERNEL);
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 5991cfd34f2b..5376b8c5d8d6 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -34,21 +34,15 @@ struct item *item_create(unsigned long index, unsigned int order)
 	return ret;
 }
 
-int item_insert_order(struct radix_tree_root *root, unsigned long index,
-			unsigned order)
+int item_insert(struct radix_tree_root *root, unsigned long index)
 {
-	struct item *item = item_create(index, order);
-	int err = __radix_tree_insert(root, item->index, item->order, item);
+	struct item *item = item_create(index, 0);
+	int err = radix_tree_insert(root, item->index, item);
 	if (err)
 		free(item);
 	return err;
 }
 
-int item_insert(struct radix_tree_root *root, unsigned long index)
-{
-	return item_insert_order(root, index, 0);
-}
-
 void item_sanity(struct item *item, unsigned long index)
 {
 	unsigned long mask;
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index 28961a08828e..e259c0839d5d 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -14,8 +14,6 @@ struct item *item_create(unsigned long index, unsigned int order);
 int item_insert(struct radix_tree_root *root, unsigned long index);
 void item_sanity(struct item *item, unsigned long index);
 void item_free(struct item *item, unsigned long index);
-int item_insert_order(struct radix_tree_root *root, unsigned long index,
-			unsigned order);
 int item_delete(struct radix_tree_root *root, unsigned long index);
 int item_delete_rcu(struct radix_tree_root *root, unsigned long index);
 struct item *item_lookup(struct radix_tree_root *root, unsigned long index);
-- 
cgit v1.2.3


From ccc89e30fac790e3a175dbfc863c67286fce96b0 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Thu, 13 Sep 2018 10:15:41 -0400
Subject: radix tree tests: Convert item_kill_tree to XArray

In preparation for the removal of the multiorder radix tree code,
convert item_kill_tree() to use the XArray so it can still be called
for XArrays containing multi-index entries.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/testing/radix-tree/test.c | 30 +++++++++---------------------
 1 file changed, 9 insertions(+), 21 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 5376b8c5d8d6..19045ce3bd23 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -252,31 +252,19 @@ void verify_tag_consistency(struct radix_tree_root *root, unsigned int tag)
 	verify_node(node, tag, !!root_tag_get(root, tag));
 }
 
-void item_kill_tree(struct radix_tree_root *root)
+void item_kill_tree(struct xarray *xa)
 {
-	struct radix_tree_iter iter;
-	void **slot;
-	struct item *items[32];
-	int nfound;
-
-	radix_tree_for_each_slot(slot, root, &iter, 0) {
-		if (xa_is_value(*slot))
-			radix_tree_delete(root, iter.index);
-	}
-
-	while ((nfound = radix_tree_gang_lookup(root, (void **)items, 0, 32))) {
-		int i;
-
-		for (i = 0; i < nfound; i++) {
-			void *ret;
+	XA_STATE(xas, xa, 0);
+	void *entry;
 
-			ret = radix_tree_delete(root, items[i]->index);
-			assert(ret == items[i]);
-			free(items[i]);
+	xas_for_each(&xas, entry, ULONG_MAX) {
+		if (!xa_is_value(entry)) {
+			item_free(entry, xas.xa_index);
 		}
+		xas_store(&xas, NULL);
 	}
-	assert(radix_tree_gang_lookup(root, (void **)items, 0, 32) == 0);
-	assert(root->xa_head == NULL);
+
+	assert(xa_empty(xa));
 }
 
 void tree_verify_min_height(struct radix_tree_root *root, int maxindex)
-- 
cgit v1.2.3


From b66b5a48b8a0e43dc114573da11c1a9c586a2d4f Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Sat, 22 Sep 2018 15:34:28 -0400
Subject: radix tree tests: Convert item_delete_rcu to XArray

In preparation for the removal of the multiorder radix tree code,
convert item_delete_rcu() to use the XArray so it can still be called
for XArrays containing multi-index entries.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/testing/radix-tree/test.c | 4 ++--
 tools/testing/radix-tree/test.h | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 19045ce3bd23..a15d0512e633 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -76,9 +76,9 @@ static void item_free_rcu(struct rcu_head *head)
 	free(item);
 }
 
-int item_delete_rcu(struct radix_tree_root *root, unsigned long index)
+int item_delete_rcu(struct xarray *xa, unsigned long index)
 {
-	struct item *item = radix_tree_delete(root, index);
+	struct item *item = xa_erase(xa, index);
 
 	if (item) {
 		item_sanity(item, index);
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index e259c0839d5d..1ee4b2c0ad10 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -15,7 +15,7 @@ int item_insert(struct radix_tree_root *root, unsigned long index);
 void item_sanity(struct item *item, unsigned long index);
 void item_free(struct item *item, unsigned long index);
 int item_delete(struct radix_tree_root *root, unsigned long index);
-int item_delete_rcu(struct radix_tree_root *root, unsigned long index);
+int item_delete_rcu(struct xarray *xa, unsigned long index);
 struct item *item_lookup(struct radix_tree_root *root, unsigned long index);
 
 void item_check_present(struct radix_tree_root *root, unsigned long index);
-- 
cgit v1.2.3


From 542980aa9318edcfb68aa7bf6eacf2814dc137dd Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Sat, 22 Sep 2018 16:12:41 -0400
Subject: radix tree test: Convert multiorder tests to XArray

This is the last remaining user of the multiorder functionality of the
radix tree.  Test the XArray instead.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 tools/testing/radix-tree/multiorder.c | 105 ++++++++++++++++------------------
 1 file changed, 49 insertions(+), 56 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 8c41dca272b1..ff27a74d9762 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -39,21 +39,20 @@ static int item_insert_order(struct xarray *xa, unsigned long index,
 	return xas_error(&xas);
 }
 
-void multiorder_iteration(void)
+void multiorder_iteration(struct xarray *xa)
 {
-	RADIX_TREE(tree, GFP_KERNEL);
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, xa, 0);
+	struct item *item;
 	int i, j, err;
 
-	printv(1, "Multiorder iteration test\n");
-
 #define NUM_ENTRIES 11
 	int index[NUM_ENTRIES] = {0, 2, 4, 8, 16, 32, 34, 36, 64, 72, 128};
 	int order[NUM_ENTRIES] = {1, 1, 2, 3,  4,  1,  0,  1,  3,  0, 7};
 
+	printv(1, "Multiorder iteration test\n");
+
 	for (i = 0; i < NUM_ENTRIES; i++) {
-		err = item_insert_order(&tree, index[i], order[i]);
+		err = item_insert_order(xa, index[i], order[i]);
 		assert(!err);
 	}
 
@@ -62,14 +61,14 @@ void multiorder_iteration(void)
 			if (j <= (index[i] | ((1 << order[i]) - 1)))
 				break;
 
-		radix_tree_for_each_slot(slot, &tree, &iter, j) {
-			int height = order[i] / RADIX_TREE_MAP_SHIFT;
-			int shift = height * RADIX_TREE_MAP_SHIFT;
+		xas_set(&xas, j);
+		xas_for_each(&xas, item, ULONG_MAX) {
+			int height = order[i] / XA_CHUNK_SHIFT;
+			int shift = height * XA_CHUNK_SHIFT;
 			unsigned long mask = (1UL << order[i]) - 1;
-			struct item *item = *slot;
 
-			assert((iter.index | mask) == (index[i] | mask));
-			assert(iter.shift == shift);
+			assert((xas.xa_index | mask) == (index[i] | mask));
+			assert(xas.xa_node->shift == shift);
 			assert(!radix_tree_is_internal_node(item));
 			assert((item->index | mask) == (index[i] | mask));
 			assert(item->order == order[i]);
@@ -77,18 +76,15 @@ void multiorder_iteration(void)
 		}
 	}
 
-	item_kill_tree(&tree);
+	item_kill_tree(xa);
 }
 
-void multiorder_tagged_iteration(void)
+void multiorder_tagged_iteration(struct xarray *xa)
 {
-	RADIX_TREE(tree, GFP_KERNEL);
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, xa, 0);
+	struct item *item;
 	int i, j;
 
-	printv(1, "Multiorder tagged iteration test\n");
-
 #define MT_NUM_ENTRIES 9
 	int index[MT_NUM_ENTRIES] = {0, 2, 4, 16, 32, 40, 64, 72, 128};
 	int order[MT_NUM_ENTRIES] = {1, 0, 2, 4,  3,  1,  3,  0,   7};
@@ -96,13 +92,15 @@ void multiorder_tagged_iteration(void)
 #define TAG_ENTRIES 7
 	int tag_index[TAG_ENTRIES] = {0, 4, 16, 40, 64, 72, 128};
 
+	printv(1, "Multiorder tagged iteration test\n");
+
 	for (i = 0; i < MT_NUM_ENTRIES; i++)
-		assert(!item_insert_order(&tree, index[i], order[i]));
+		assert(!item_insert_order(xa, index[i], order[i]));
 
-	assert(!radix_tree_tagged(&tree, 1));
+	assert(!xa_marked(xa, XA_MARK_1));
 
 	for (i = 0; i < TAG_ENTRIES; i++)
-		assert(radix_tree_tag_set(&tree, tag_index[i], 1));
+		xa_set_mark(xa, tag_index[i], XA_MARK_1);
 
 	for (j = 0; j < 256; j++) {
 		int k;
@@ -114,22 +112,22 @@ void multiorder_tagged_iteration(void)
 				break;
 		}
 
-		radix_tree_for_each_tagged(slot, &tree, &iter, j, 1) {
+		xas_set(&xas, j);
+		xas_for_each_marked(&xas, item, ULONG_MAX, XA_MARK_1) {
 			unsigned long mask;
-			struct item *item = *slot;
 			for (k = i; index[k] < tag_index[i]; k++)
 				;
 			mask = (1UL << order[k]) - 1;
 
-			assert((iter.index | mask) == (tag_index[i] | mask));
-			assert(!radix_tree_is_internal_node(item));
+			assert((xas.xa_index | mask) == (tag_index[i] | mask));
+			assert(!xa_is_internal(item));
 			assert((item->index | mask) == (tag_index[i] | mask));
 			assert(item->order == order[k]);
 			i++;
 		}
 	}
 
-	assert(tag_tagged_items(&tree, 0, ~0UL, TAG_ENTRIES, XA_MARK_1,
+	assert(tag_tagged_items(xa, 0, ULONG_MAX, TAG_ENTRIES, XA_MARK_1,
 				XA_MARK_2) == TAG_ENTRIES);
 
 	for (j = 0; j < 256; j++) {
@@ -142,29 +140,31 @@ void multiorder_tagged_iteration(void)
 				break;
 		}
 
-		radix_tree_for_each_tagged(slot, &tree, &iter, j, 2) {
-			struct item *item = *slot;
+		xas_set(&xas, j);
+		xas_for_each_marked(&xas, item, ULONG_MAX, XA_MARK_2) {
 			for (k = i; index[k] < tag_index[i]; k++)
 				;
 			mask = (1 << order[k]) - 1;
 
-			assert((iter.index | mask) == (tag_index[i] | mask));
-			assert(!radix_tree_is_internal_node(item));
+			assert((xas.xa_index | mask) == (tag_index[i] | mask));
+			assert(!xa_is_internal(item));
 			assert((item->index | mask) == (tag_index[i] | mask));
 			assert(item->order == order[k]);
 			i++;
 		}
 	}
 
-	assert(tag_tagged_items(&tree, 1, ~0UL, MT_NUM_ENTRIES * 2, XA_MARK_1,
+	assert(tag_tagged_items(xa, 1, ULONG_MAX, MT_NUM_ENTRIES * 2, XA_MARK_1,
 				XA_MARK_0) == TAG_ENTRIES);
 	i = 0;
-	radix_tree_for_each_tagged(slot, &tree, &iter, 0, 0) {
-		assert(iter.index == tag_index[i]);
+	xas_set(&xas, 0);
+	xas_for_each_marked(&xas, item, ULONG_MAX, XA_MARK_0) {
+		assert(xas.xa_index == tag_index[i]);
 		i++;
 	}
+	assert(i == TAG_ENTRIES);
 
-	item_kill_tree(&tree);
+	item_kill_tree(xa);
 }
 
 bool stop_iteration = false;
@@ -187,52 +187,45 @@ static void *creator_func(void *ptr)
 
 static void *iterator_func(void *ptr)
 {
-	struct radix_tree_root *tree = ptr;
-	struct radix_tree_iter iter;
+	XA_STATE(xas, ptr, 0);
 	struct item *item;
-	void **slot;
 
 	while (!stop_iteration) {
 		rcu_read_lock();
-		radix_tree_for_each_slot(slot, tree, &iter, 0) {
-			item = radix_tree_deref_slot(slot);
-
-			if (!item)
+		xas_for_each(&xas, item, ULONG_MAX) {
+			if (xas_retry(&xas, item))
 				continue;
-			if (radix_tree_deref_retry(item)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
 
-			item_sanity(item, iter.index);
+			item_sanity(item, xas.xa_index);
 		}
 		rcu_read_unlock();
 	}
 	return NULL;
 }
 
-static void multiorder_iteration_race(void)
+static void multiorder_iteration_race(struct xarray *xa)
 {
 	const int num_threads = sysconf(_SC_NPROCESSORS_ONLN);
 	pthread_t worker_thread[num_threads];
-	RADIX_TREE(tree, GFP_KERNEL);
 	int i;
 
-	pthread_create(&worker_thread[0], NULL, &creator_func, &tree);
+	pthread_create(&worker_thread[0], NULL, &creator_func, xa);
 	for (i = 1; i < num_threads; i++)
-		pthread_create(&worker_thread[i], NULL, &iterator_func, &tree);
+		pthread_create(&worker_thread[i], NULL, &iterator_func, xa);
 
 	for (i = 0; i < num_threads; i++)
 		pthread_join(worker_thread[i], NULL);
 
-	item_kill_tree(&tree);
+	item_kill_tree(xa);
 }
 
+static DEFINE_XARRAY(array);
+
 void multiorder_checks(void)
 {
-	multiorder_iteration();
-	multiorder_tagged_iteration();
-	multiorder_iteration_race();
+	multiorder_iteration(&array);
+	multiorder_tagged_iteration(&array);
+	multiorder_iteration_race(&array);
 
 	radix_tree_cpu_dead(0);
 }
-- 
cgit v1.2.3


From 3a08cd52c37c793ffc199f6fc2ecfc368e284b2d Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Sat, 22 Sep 2018 16:14:30 -0400
Subject: radix tree: Remove multiorder support

All users have now been converted to the XArray.  Removing the support
reduces code size and ensures new users will use the XArray instead.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/radix-tree.h                    |  40 +----
 lib/Kconfig                                   |   4 -
 lib/radix-tree.c                              | 215 ++------------------------
 mm/Kconfig                                    |   4 +-
 tools/testing/radix-tree/generated/autoconf.h |   1 -
 5 files changed, 19 insertions(+), 245 deletions(-)

(limited to 'tools')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 9a1460488163..06c4c7a6c09c 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -96,7 +96,6 @@ static inline bool radix_tree_empty(const struct radix_tree_root *root)
  * @next_index:	one beyond the last index for this chunk
  * @tags:	bit-mask for tag-iterating
  * @node:	node that contains current slot
- * @shift:	shift for the node that holds our slots
  *
  * This radix tree iterator works in terms of "chunks" of slots.  A chunk is a
  * subinterval of slots contained within one radix tree leaf node.  It is
@@ -110,20 +109,8 @@ struct radix_tree_iter {
 	unsigned long	next_index;
 	unsigned long	tags;
 	struct radix_tree_node *node;
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-	unsigned int	shift;
-#endif
 };
 
-static inline unsigned int iter_shift(const struct radix_tree_iter *iter)
-{
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-	return iter->shift;
-#else
-	return 0;
-#endif
-}
-
 /**
  * Radix-tree synchronization
  *
@@ -230,13 +217,8 @@ static inline int radix_tree_exception(void *arg)
 	return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK);
 }
 
-int __radix_tree_insert(struct radix_tree_root *, unsigned long index,
-			unsigned order, void *);
-static inline int radix_tree_insert(struct radix_tree_root *root,
-			unsigned long index, void *entry)
-{
-	return __radix_tree_insert(root, index, 0, entry);
-}
+int radix_tree_insert(struct radix_tree_root *, unsigned long index,
+			void *);
 void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index,
 			  struct radix_tree_node **nodep, void __rcu ***slotp);
 void *radix_tree_lookup(const struct radix_tree_root *, unsigned long);
@@ -384,7 +366,7 @@ void __rcu **radix_tree_iter_retry(struct radix_tree_iter *iter)
 static inline unsigned long
 __radix_tree_iter_add(struct radix_tree_iter *iter, unsigned long slots)
 {
-	return iter->index + (slots << iter_shift(iter));
+	return iter->index + slots;
 }
 
 /**
@@ -409,20 +391,8 @@ void __rcu **__must_check radix_tree_iter_resume(void __rcu **slot,
 static __always_inline long
 radix_tree_chunk_size(struct radix_tree_iter *iter)
 {
-	return (iter->next_index - iter->index) >> iter_shift(iter);
-}
-
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-void __rcu **__radix_tree_next_slot(void __rcu **slot,
-				struct radix_tree_iter *iter, unsigned flags);
-#else
-/* Can't happen without sibling entries, but the compiler can't tell that */
-static inline void __rcu **__radix_tree_next_slot(void __rcu **slot,
-				struct radix_tree_iter *iter, unsigned flags)
-{
-	return slot;
+	return iter->next_index - iter->index;
 }
-#endif
 
 /**
  * radix_tree_next_slot - find next slot in chunk
@@ -482,8 +452,6 @@ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot,
 	return NULL;
 
  found:
-	if (unlikely(radix_tree_is_internal_node(rcu_dereference_raw(*slot))))
-		return __radix_tree_next_slot(slot, iter, flags);
 	return slot;
 }
 
diff --git a/lib/Kconfig b/lib/Kconfig
index 40bfa6ccd294..a9965f4af4dd 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -405,10 +405,6 @@ config XARRAY_MULTI
 	  Support entries which occupy multiple consecutive indices in the
 	  XArray.
 
-config RADIX_TREE_MULTIORDER
-	bool
-	select XARRAY_MULTI
-
 config ASSOCIATIVE_ARRAY
 	bool
 	help
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index f107dd2698e3..1106bb6aa01e 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -110,11 +110,6 @@ static unsigned int radix_tree_descend(const struct radix_tree_node *parent,
 	unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK;
 	void __rcu **entry = rcu_dereference_raw(parent->slots[offset]);
 
-	if (xa_is_sibling(entry)) {
-		offset = xa_to_sibling(entry);
-		entry = rcu_dereference_raw(parent->slots[offset]);
-	}
-
 	*nodep = (void *)entry;
 	return offset;
 }
@@ -229,7 +224,7 @@ radix_tree_find_next_bit(struct radix_tree_node *node, unsigned int tag,
 
 static unsigned int iter_offset(const struct radix_tree_iter *iter)
 {
-	return (iter->index >> iter_shift(iter)) & RADIX_TREE_MAP_MASK;
+	return iter->index & RADIX_TREE_MAP_MASK;
 }
 
 /*
@@ -506,16 +501,13 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root)
 
 		/*
 		 * The candidate node has more than one child, or its child
-		 * is not at the leftmost slot, or the child is a multiorder
-		 * entry, we cannot shrink.
+		 * is not at the leftmost slot, we cannot shrink.
 		 */
 		if (node->count != 1)
 			break;
 		child = rcu_dereference_raw(node->slots[0]);
 		if (!child)
 			break;
-		if (!radix_tree_is_internal_node(child) && node->shift)
-			break;
 
 		/*
 		 * For an IDR, we must not shrink entry 0 into the root in
@@ -613,7 +605,6 @@ static bool delete_node(struct radix_tree_root *root,
  *	__radix_tree_create	-	create a slot in a radix tree
  *	@root:		radix tree root
  *	@index:		index key
- *	@order:		index occupies 2^order aligned slots
  *	@nodep:		returns node
  *	@slotp:		returns slot
  *
@@ -627,21 +618,19 @@ static bool delete_node(struct radix_tree_root *root,
  *	Returns -ENOMEM, or 0 for success.
  */
 static int __radix_tree_create(struct radix_tree_root *root,
-		unsigned long index, unsigned order,
-		struct radix_tree_node **nodep, void __rcu ***slotp)
+		unsigned long index, struct radix_tree_node **nodep,
+		void __rcu ***slotp)
 {
 	struct radix_tree_node *node = NULL, *child;
 	void __rcu **slot = (void __rcu **)&root->xa_head;
 	unsigned long maxindex;
 	unsigned int shift, offset = 0;
-	unsigned long max = index | ((1UL << order) - 1);
+	unsigned long max = index;
 	gfp_t gfp = root_gfp_mask(root);
 
 	shift = radix_tree_load_root(root, &child, &maxindex);
 
 	/* Make sure the tree is high enough.  */
-	if (order > 0 && max == ((1UL << order) - 1))
-		max++;
 	if (max > maxindex) {
 		int error = radix_tree_extend(root, gfp, max, shift);
 		if (error < 0)
@@ -650,7 +639,7 @@ static int __radix_tree_create(struct radix_tree_root *root,
 		child = rcu_dereference_raw(root->xa_head);
 	}
 
-	while (shift > order) {
+	while (shift > 0) {
 		shift -= RADIX_TREE_MAP_SHIFT;
 		if (child == NULL) {
 			/* Have to add a child node.  */
@@ -711,70 +700,8 @@ static void radix_tree_free_nodes(struct radix_tree_node *node)
 	}
 }
 
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-static inline int insert_entries(struct radix_tree_node *node,
-		void __rcu **slot, void *item, unsigned order, bool replace)
-{
-	void *sibling;
-	unsigned i, n, tag, offset, tags = 0;
-
-	if (node) {
-		if (order > node->shift)
-			n = 1 << (order - node->shift);
-		else
-			n = 1;
-		offset = get_slot_offset(node, slot);
-	} else {
-		n = 1;
-		offset = 0;
-	}
-
-	if (n > 1) {
-		offset = offset & ~(n - 1);
-		slot = &node->slots[offset];
-	}
-	sibling = xa_mk_sibling(offset);
-
-	for (i = 0; i < n; i++) {
-		if (slot[i]) {
-			if (replace) {
-				node->count--;
-				for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
-					if (tag_get(node, tag, offset + i))
-						tags |= 1 << tag;
-			} else
-				return -EEXIST;
-		}
-	}
-
-	for (i = 0; i < n; i++) {
-		struct radix_tree_node *old = rcu_dereference_raw(slot[i]);
-		if (i) {
-			rcu_assign_pointer(slot[i], sibling);
-			for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
-				if (tags & (1 << tag))
-					tag_clear(node, tag, offset + i);
-		} else {
-			rcu_assign_pointer(slot[i], item);
-			for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++)
-				if (tags & (1 << tag))
-					tag_set(node, tag, offset);
-		}
-		if (xa_is_node(old))
-			radix_tree_free_nodes(old);
-		if (xa_is_value(old))
-			node->nr_values--;
-	}
-	if (node) {
-		node->count += n;
-		if (xa_is_value(item))
-			node->nr_values += n;
-	}
-	return n;
-}
-#else
 static inline int insert_entries(struct radix_tree_node *node,
-		void __rcu **slot, void *item, unsigned order, bool replace)
+		void __rcu **slot, void *item, bool replace)
 {
 	if (*slot)
 		return -EEXIST;
@@ -786,19 +713,17 @@ static inline int insert_entries(struct radix_tree_node *node,
 	}
 	return 1;
 }
-#endif
 
 /**
  *	__radix_tree_insert    -    insert into a radix tree
  *	@root:		radix tree root
  *	@index:		index key
- *	@order:		key covers the 2^order indices around index
  *	@item:		item to insert
  *
  *	Insert an item into the radix tree at position @index.
  */
-int __radix_tree_insert(struct radix_tree_root *root, unsigned long index,
-			unsigned order, void *item)
+int radix_tree_insert(struct radix_tree_root *root, unsigned long index,
+			void *item)
 {
 	struct radix_tree_node *node;
 	void __rcu **slot;
@@ -806,11 +731,11 @@ int __radix_tree_insert(struct radix_tree_root *root, unsigned long index,
 
 	BUG_ON(radix_tree_is_internal_node(item));
 
-	error = __radix_tree_create(root, index, order, &node, &slot);
+	error = __radix_tree_create(root, index, &node, &slot);
 	if (error)
 		return error;
 
-	error = insert_entries(node, slot, item, order, false);
+	error = insert_entries(node, slot, item, false);
 	if (error < 0)
 		return error;
 
@@ -825,7 +750,7 @@ int __radix_tree_insert(struct radix_tree_root *root, unsigned long index,
 
 	return 0;
 }
-EXPORT_SYMBOL(__radix_tree_insert);
+EXPORT_SYMBOL(radix_tree_insert);
 
 /**
  *	__radix_tree_lookup	-	lookup an item in a radix tree
@@ -917,32 +842,12 @@ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index)
 }
 EXPORT_SYMBOL(radix_tree_lookup);
 
-static inline void replace_sibling_entries(struct radix_tree_node *node,
-				void __rcu **slot, int count, int values)
-{
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-	unsigned offset = get_slot_offset(node, slot);
-	void *ptr = xa_mk_sibling(offset);
-
-	while (++offset < RADIX_TREE_MAP_SIZE) {
-		if (rcu_dereference_raw(node->slots[offset]) != ptr)
-			break;
-		if (count < 0) {
-			node->slots[offset] = NULL;
-			node->count--;
-		}
-		node->nr_values += values;
-	}
-#endif
-}
-
 static void replace_slot(void __rcu **slot, void *item,
 		struct radix_tree_node *node, int count, int values)
 {
 	if (node && (count || values)) {
 		node->count += count;
 		node->nr_values += values;
-		replace_sibling_entries(node, slot, count, values);
 	}
 
 	rcu_assign_pointer(*slot, item);
@@ -1223,14 +1128,6 @@ int radix_tree_tag_get(const struct radix_tree_root *root,
 }
 EXPORT_SYMBOL(radix_tree_tag_get);
 
-static inline void __set_iter_shift(struct radix_tree_iter *iter,
-					unsigned int shift)
-{
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-	iter->shift = shift;
-#endif
-}
-
 /* Construct iter->tags bit-mask from node->tags[tag] array */
 static void set_iter_tags(struct radix_tree_iter *iter,
 				struct radix_tree_node *node, unsigned offset,
@@ -1257,92 +1154,11 @@ static void set_iter_tags(struct radix_tree_iter *iter,
 	}
 }
 
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-static void __rcu **skip_siblings(struct radix_tree_node **nodep,
-			void __rcu **slot, struct radix_tree_iter *iter)
-{
-	while (iter->index < iter->next_index) {
-		*nodep = rcu_dereference_raw(*slot);
-		if (*nodep && !xa_is_sibling(*nodep))
-			return slot;
-		slot++;
-		iter->index = __radix_tree_iter_add(iter, 1);
-		iter->tags >>= 1;
-	}
-
-	*nodep = NULL;
-	return NULL;
-}
-
-void __rcu **__radix_tree_next_slot(void __rcu **slot,
-				struct radix_tree_iter *iter, unsigned flags)
-{
-	unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK;
-	struct radix_tree_node *node;
-
-	slot = skip_siblings(&node, slot, iter);
-
-	while (radix_tree_is_internal_node(node)) {
-		unsigned offset;
-		unsigned long next_index;
-
-		if (node == RADIX_TREE_RETRY)
-			return slot;
-		node = entry_to_node(node);
-		iter->node = node;
-		iter->shift = node->shift;
-
-		if (flags & RADIX_TREE_ITER_TAGGED) {
-			offset = radix_tree_find_next_bit(node, tag, 0);
-			if (offset == RADIX_TREE_MAP_SIZE)
-				return NULL;
-			slot = &node->slots[offset];
-			iter->index = __radix_tree_iter_add(iter, offset);
-			set_iter_tags(iter, node, offset, tag);
-			node = rcu_dereference_raw(*slot);
-		} else {
-			offset = 0;
-			slot = &node->slots[0];
-			for (;;) {
-				node = rcu_dereference_raw(*slot);
-				if (node)
-					break;
-				slot++;
-				offset++;
-				if (offset == RADIX_TREE_MAP_SIZE)
-					return NULL;
-			}
-			iter->index = __radix_tree_iter_add(iter, offset);
-		}
-		if ((flags & RADIX_TREE_ITER_CONTIG) && (offset > 0))
-			goto none;
-		next_index = (iter->index | shift_maxindex(iter->shift)) + 1;
-		if (next_index < iter->next_index)
-			iter->next_index = next_index;
-	}
-
-	return slot;
- none:
-	iter->next_index = 0;
-	return NULL;
-}
-EXPORT_SYMBOL(__radix_tree_next_slot);
-#else
-static void __rcu **skip_siblings(struct radix_tree_node **nodep,
-			void __rcu **slot, struct radix_tree_iter *iter)
-{
-	return slot;
-}
-#endif
-
 void __rcu **radix_tree_iter_resume(void __rcu **slot,
 					struct radix_tree_iter *iter)
 {
-	struct radix_tree_node *node;
-
 	slot++;
 	iter->index = __radix_tree_iter_add(iter, 1);
-	skip_siblings(&node, slot, iter);
 	iter->next_index = iter->index;
 	iter->tags = 0;
 	return NULL;
@@ -1393,7 +1209,6 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root,
 		iter->next_index = maxindex + 1;
 		iter->tags = 1;
 		iter->node = NULL;
-		__set_iter_shift(iter, 0);
 		return (void __rcu **)&root->xa_head;
 	}
 
@@ -1414,8 +1229,6 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root,
 				while (++offset	< RADIX_TREE_MAP_SIZE) {
 					void *slot = rcu_dereference_raw(
 							node->slots[offset]);
-					if (xa_is_sibling(slot))
-						continue;
 					if (slot)
 						break;
 				}
@@ -1436,10 +1249,9 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root,
 	} while (node->shift && radix_tree_is_internal_node(child));
 
 	/* Update the iterator state */
-	iter->index = (index &~ node_maxindex(node)) | (offset << node->shift);
+	iter->index = (index &~ node_maxindex(node)) | offset;
 	iter->next_index = (index | node_maxindex(node)) + 1;
 	iter->node = node;
-	__set_iter_shift(iter, node->shift);
 
 	if (flags & RADIX_TREE_ITER_TAGGED)
 		set_iter_tags(iter, node, offset, tag);
@@ -1750,7 +1562,6 @@ void __rcu **idr_get_free(struct radix_tree_root *root,
 	else
 		iter->next_index = 1;
 	iter->node = node;
-	__set_iter_shift(iter, shift);
 	set_iter_tags(iter, node, offset, IDR_FREE);
 
 	return slot;
diff --git a/mm/Kconfig b/mm/Kconfig
index de64ea658716..02301a89089e 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -379,7 +379,7 @@ config TRANSPARENT_HUGEPAGE
 	bool "Transparent Hugepage Support"
 	depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select COMPACTION
-	select RADIX_TREE_MULTIORDER
+	select XARRAY_MULTI
 	help
 	  Transparent Hugepages allows the kernel to use huge pages and
 	  huge tlb transparently to the applications whenever possible.
@@ -671,7 +671,7 @@ config ZONE_DEVICE
 	depends on MEMORY_HOTREMOVE
 	depends on SPARSEMEM_VMEMMAP
 	depends on ARCH_HAS_ZONE_DEVICE
-	select RADIX_TREE_MULTIORDER
+	select XARRAY_MULTI
 
 	help
 	  Device memory hotplug support allows for establishing pmem,
diff --git a/tools/testing/radix-tree/generated/autoconf.h b/tools/testing/radix-tree/generated/autoconf.h
index ca8e03ad19ac..2218b3cc184e 100644
--- a/tools/testing/radix-tree/generated/autoconf.h
+++ b/tools/testing/radix-tree/generated/autoconf.h
@@ -1,2 +1 @@
-#define CONFIG_RADIX_TREE_MULTIORDER 1
 #define CONFIG_XARRAY_MULTI 1
-- 
cgit v1.2.3


From 882731e06c669a8626f2d4bfb351ca19264be029 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Sat, 20 Oct 2018 23:01:48 +0100
Subject: tools: bpftool: document restriction on '.' in names to pin in bpffs

Names used to pin eBPF programs and maps under the eBPF virtual file
system cannot contain a dot character, which is reserved for future
extensions of this file system.

Document this in bpftool man pages to avoid users getting confused if
pinning fails because of a dot.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Documentation/bpftool-map.rst  | 4 +++-
 tools/bpf/bpftool/Documentation/bpftool-prog.rst | 8 ++++++--
 2 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index 3497f2d80328..f55a2daed59b 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -86,7 +86,9 @@ DESCRIPTION
 	**bpftool map pin**     *MAP*  *FILE*
 		  Pin map *MAP* as *FILE*.
 
-		  Note: *FILE* must be located in *bpffs* mount.
+		  Note: *FILE* must be located in *bpffs* mount. It must not
+		  contain a dot character ('.'), which is reserved for future
+		  extensions of *bpffs*.
 
 	**bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*]
 		  Read events from a BPF_MAP_TYPE_PERF_EVENT_ARRAY map.
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 12c803003ab2..ac4e904b10fb 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -75,7 +75,9 @@ DESCRIPTION
 	**bpftool prog pin** *PROG* *FILE*
 		  Pin program *PROG* as *FILE*.
 
-		  Note: *FILE* must be located in *bpffs* mount.
+		  Note: *FILE* must be located in *bpffs* mount. It must not
+		  contain a dot character ('.'), which is reserved for future
+		  extensions of *bpffs*.
 
 	**bpftool prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
 		  Load bpf program from binary *OBJ* and pin as *FILE*.
@@ -91,7 +93,9 @@ DESCRIPTION
 		  If **dev** *NAME* is specified program will be loaded onto
 		  given networking device (offload).
 
-		  Note: *FILE* must be located in *bpffs* mount.
+		  Note: *FILE* must be located in *bpffs* mount. It must not
+		  contain a dot character ('.'), which is reserved for future
+		  extensions of *bpffs*.
 
         **bpftool prog attach** *PROG* *ATTACH_TYPE* *MAP*
                   Attach bpf program *PROG* (with type specified by *ATTACH_TYPE*)
-- 
cgit v1.2.3


From 06ee9da6a8b49e0e12b7a825dbe6ad243d5463e2 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Sat, 20 Oct 2018 23:01:49 +0100
Subject: tools: bpftool: print nb of cmds to stdout (not stderr) for batch
 mode

When batch mode is used and all commands succeeds, bpftool prints the
number of commands processed to stderr. There is no particular reason to
use stderr for this, we could as well use stdout. It would avoid getting
unnecessary output on stderr if the standard ouptut is redirected, for
example.

Reported-by: David Beckett <david.beckett@netronome.com>
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 828dde30e9ec..75a3296dc0bc 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -321,7 +321,8 @@ static int do_batch(int argc, char **argv)
 		p_err("reading batch file failed: %s", strerror(errno));
 		err = -1;
 	} else {
-		p_info("processed %d commands", lines);
+		if (!json_output)
+			printf("processed %d commands\n", lines);
 		err = 0;
 	}
 err_close:
-- 
cgit v1.2.3


From fe8ecccc10b3adc071de05ca7af728ca1a4ac9aa Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Sat, 20 Oct 2018 23:01:50 +0100
Subject: tools: bpftool: fix completion for "bpftool map update"

When trying to complete "bpftool map update" commands, the call to
printf would print an error message that would show on the command line
if no map is found to complete the command line.

Fix it by making sure we have map ids to complete the line with, before
we try to print something.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/bash-completion/bpftool | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index c56545e87b0d..3f78e6404589 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -143,7 +143,7 @@ _bpftool_map_update_map_type()
     local type
     type=$(bpftool -jp map show $keyword $ref | \
         command sed -n 's/.*"type": "\(.*\)",$/\1/p')
-    printf $type
+    [[ -n $type ]] && printf $type
 }
 
 _bpftool_map_update_get_id()
-- 
cgit v1.2.3


From b7e8452b860c299f342a012922bdd9ab8f2bb722 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Sat, 20 Oct 2018 09:04:41 -0300
Subject: perf evsel: Mark a evsel as disabled when asking the kernel do
 disable it

Because there may be more such events in the ring buffer that should be
discarded when an app decides to stop considering them.

At some point we'll do this with eBPF, this way we stop them at origin,
before they are placed in the ring buffer.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-uzufuxws4hufigx07ue1dpv6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evlist.c |  2 +-
 tools/perf/util/evsel.c  | 23 +++++++++++++++++------
 tools/perf/util/evsel.h  |  1 +
 3 files changed, 19 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index be440df29615..e88e6f9b1463 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -358,7 +358,7 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 	struct perf_evsel *pos;
 
 	evlist__for_each_entry(evlist, pos) {
-		if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+		if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->fd)
 			continue;
 		perf_evsel__disable(pos);
 	}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7e95ec1c19a8..6d187059a373 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1207,16 +1207,27 @@ int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter)
 
 int perf_evsel__enable(struct perf_evsel *evsel)
 {
-	return perf_evsel__run_ioctl(evsel,
-				     PERF_EVENT_IOC_ENABLE,
-				     0);
+	int err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0);
+
+	if (!err)
+		evsel->disabled = false;
+
+	return err;
 }
 
 int perf_evsel__disable(struct perf_evsel *evsel)
 {
-	return perf_evsel__run_ioctl(evsel,
-				     PERF_EVENT_IOC_DISABLE,
-				     0);
+	int err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0);
+	/*
+	 * We mark it disabled here so that tools that disable a event can
+	 * ignore events after they disable it. I.e. the ring buffer may have
+	 * already a few more events queued up before the kernel got the stop
+	 * request.
+	 */
+	if (!err)
+		evsel->disabled = true;
+
+	return err;
 }
 
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index ad5d615c6db6..4ef50f157b50 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -122,6 +122,7 @@ struct perf_evsel {
 	bool			snapshot;
 	bool 			supported;
 	bool 			needs_swap;
+	bool 			disabled;
 	bool			no_aux_samples;
 	bool			immediate;
 	bool			system_wide;
-- 
cgit v1.2.3


From 4291bf5cb93918232f88a3a70d8f70a72fbb6ab0 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Sat, 20 Oct 2018 09:18:50 -0300
Subject: perf trace: Drop addr_location refcounts

When we use machine__resolve() we grab a reference to
addr_location.thread (and in the future to other elements there) via
machine__findnew_thread(), so we must pair that with
addr_location__put(), else we'll never drop that thread when it exits
and no other remaining data structures have pointers to it. Fix it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ivg9hifzeuokb1f5jxc2wob4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 74638034861c..77b8748ad5ed 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1814,12 +1814,14 @@ static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evse
 	int max_stack = evsel->attr.sample_max_stack ?
 			evsel->attr.sample_max_stack :
 			trace->max_stack;
+	int err;
 
-	if (machine__resolve(trace->host, &al, sample) < 0 ||
-	    thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack))
+	if (machine__resolve(trace->host, &al, sample) < 0)
 		return -1;
 
-	return 0;
+	err = thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack);
+	addr_location__put(&al);
+	return err;
 }
 
 static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sample)
-- 
cgit v1.2.3


From a937c6658b8e77e1f65cde2be9970811752121bb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Sat, 20 Oct 2018 09:27:52 -0300
Subject: perf trace: Drop thread refcount in trace__event_handler()

We must pair:

   thread = machine__findnew_thread();

with thread__put(thread). Fix it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: c4191e55b874 ("perf trace: Show comm and tid for tracepoint events")
Link: https://lkml.kernel.org/n/tip-dkxsb8cwg87rmkrzrbns1o4z@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 77b8748ad5ed..589e0412652a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2152,8 +2152,8 @@ newline:
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
 		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
-	thread__put(thread);
 out:
+	thread__put(thread);
 	return 0;
 }
 
-- 
cgit v1.2.3


From cbb5df7e96070f1f728ff7885443646ebba703d4 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 22 Oct 2018 11:30:15 +0200
Subject: perf stat: Poll for monitored tasks being alive

Adding the check for tasks we monitor via -p/-t options, and finish stat
if there's no longer task to monitor.

Requested-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lkml.kernel.org/r/20181022093015.9106-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index b86aba1c8028..d1028d7755bb 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -409,6 +409,28 @@ static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
 	return leader;
 }
 
+static bool is_target_alive(struct target *_target,
+			    struct thread_map *threads)
+{
+	struct stat st;
+	int i;
+
+	if (!target__has_task(_target))
+		return true;
+
+	for (i = 0; i < threads->nr; i++) {
+		char path[PATH_MAX];
+
+		scnprintf(path, PATH_MAX, "%s/%d", procfs__mountpoint(),
+			  threads->map[i].pid);
+
+		if (!stat(path, &st))
+			return true;
+	}
+
+	return false;
+}
+
 static int __run_perf_stat(int argc, const char **argv, int run_idx)
 {
 	int interval = stat_config.interval;
@@ -579,6 +601,8 @@ try_again:
 		enable_counters();
 		while (!done) {
 			nanosleep(&ts, NULL);
+			if (!is_target_alive(&target, evsel_list->threads))
+				break;
 			if (timeout)
 				break;
 			if (interval) {
-- 
cgit v1.2.3


From c1c9b9695cc8868048f45c7e2559f65bc0be7382 Mon Sep 17 00:00:00 2001
From: Milian Wolff <milian.wolff@kdab.com>
Date: Sun, 21 Oct 2018 21:14:23 +0200
Subject: perf script: Allow extended console debug output

The script tool isn't using a browser, yet use_browser wasn't set
explicitly to zero. This in turn lead to confusing output such as:

  ```
  $ perf script -vvv ...
  ...
  overlapping maps in /home/milian/foobar (disable tui for more info)
  ...
  ```

Explicitly set use_browser to 0 now, which gives us the extended
debug information now in perf script as expected.

Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lkml.kernel.org/r/20181021191424.16183-1-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 4da5e32b9e03..bd468b90801b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3417,8 +3417,10 @@ int cmd_script(int argc, const char **argv)
 		exit(-1);
 	}
 
-	if (!script_name)
+	if (!script_name) {
 		setup_pager();
+		use_browser = 0;
+	}
 
 	session = perf_session__new(&data, false, &script.tool);
 	if (session == NULL)
-- 
cgit v1.2.3


From 7ee40678af935fb489b0c6cf0f75808175214cd7 Mon Sep 17 00:00:00 2001
From: Milian Wolff <milian.wolff@kdab.com>
Date: Sun, 21 Oct 2018 21:14:24 +0200
Subject: perf script: Flush output stream after events in verbose mode

When the perf script output is written to a terminal stream, the normal
output of `perf script` would get buffered, but its debug output would
be written directly. This made it quite hard to figure out where a given
debug output is coming from.

We can improve on this by flushing the output buffer after processing an
event. To see the value, compare the following output for a `perf script
-v` run:

Before this patch:
```
unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
unwind: find_proc_info dso /usr/lib/ld-2.28.so
unwind: reg 6, val 0
unwind: _start:ip = 0x7faf7dfdc000 (0x2000)
unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
unwind: find_proc_info dso /usr/lib/ld-2.28.so
unwind: reg 6, val 0
unwind: _start:ip = 0x7faf7dfdc000 (0x2000)
unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
unwind: find_proc_info dso /usr/lib/ld-2.28.so
unwind: reg 6, val 0
unwind: _start:ip = 0x7faf7dfdc000 (0x2000)
unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
... lots and lots of verbose debug output
cpp-inlining 24617 90229.122036534:          1 cycles:uppp:
            7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so)

cpp-inlining 24617 90229.122043974:          1 cycles:uppp:
            7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so)
...
```

After this patch:
```
...
unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
unwind: find_proc_info dso /usr/lib/ld-2.28.so
unwind: reg 6, val 0
unwind: _start:ip = 0x7faf7dfdc000 (0x2000)
cpp-inlining 24617 90229.122036534:          1 cycles:uppp:
            7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so)

unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
unwind: find_proc_info dso /usr/lib/ld-2.28.so
unwind: reg 6, val 0
unwind: _start:ip = 0x7faf7dfdc000 (0x2000)
cpp-inlining 24617 90229.122043974:          1 cycles:uppp:
            7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so)
...
```

This new output format makes it much easier to use perf script output
for debugging purposes, e.g. to investigate broken dwarf unwinding.

Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20181021191424.16183-2-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index bd468b90801b..ca09b7d2adb7 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1737,6 +1737,9 @@ static void process_event(struct perf_script *script,
 
 	if (PRINT_FIELD(METRIC))
 		perf_sample__fprint_metric(script, thread, evsel, sample, fp);
+
+	if (verbose)
+		fflush(fp);
 }
 
 static struct scripting_ops	*scripting_ops;
-- 
cgit v1.2.3


From a9c5e6c1e9bff42ca5f01ceb3092a27a010755fb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 22 Oct 2018 14:14:16 -0300
Subject: perf trace: Introduce per-event maximum number of events property

Call it 'nr', as in this context it should be expressive enough, i.e.:

  # perf trace -e sched:*waking/nr=8,call-graph=fp/
     0.000 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=001
                                       try_to_wake_up ([kernel.kallsyms])
                                       sched_clock ([kernel.kallsyms])
     3.933 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=001
                                       try_to_wake_up ([kernel.kallsyms])
                                       sched_clock ([kernel.kallsyms])
     3.970 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
                                       try_to_wake_up ([kernel.kallsyms])
                                       __libc_write (/usr/lib64/libpthread-2.26.so)
    20.069 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
                                       try_to_wake_up ([kernel.kallsyms])
                                       __libc_write (/usr/lib64/libpthread-2.26.so)
    37.170 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
                                       try_to_wake_up ([kernel.kallsyms])
                                       __libc_write (/usr/lib64/libpthread-2.26.so)
    53.267 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
                                       try_to_wake_up ([kernel.kallsyms])
                                       __libc_write (/usr/lib64/libpthread-2.26.so)
    70.365 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
                                       try_to_wake_up ([kernel.kallsyms])
                                       __libc_write (/usr/lib64/libpthread-2.26.so)
    75.781 Web Content/3649 sched:sched_waking:comm=JS Helper pid=3670 prio=120 target_cpu=000
                                       try_to_wake_up ([kernel.kallsyms])
                                       try_to_wake_up ([kernel.kallsyms])
                                       wake_up_q ([kernel.kallsyms])
                                       futex_wake ([kernel.kallsyms])
                                       do_futex ([kernel.kallsyms])
                                       __x64_sys_futex ([kernel.kallsyms])
                                       do_syscall_64 ([kernel.kallsyms])
                                       entry_SYSCALL_64_after_hwframe ([kernel.kallsyms])
                                       pthread_cond_signal@@GLIBC_2.3.2 (/usr/lib64/libpthread-2.26.so)
  #

  # perf trace -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
     0.000 :0/0 sched:sched_switch:swapper/0:0 [120] S ==> trace:3367 [120]
     0.046 :0/0 sched:sched_switch:swapper/1:0 [120] S ==> kworker/u16:58:2722 [120]
   570.670 irq/50-iwlwifi/680 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051ef00 len=66
                                       __dev_queue_xmit ([kernel.kallsyms])
  1106.141 jbd2/dm-0-8/476 block:block_plug:[jbd2/dm-0-8]
  1106.175 jbd2/dm-0-8/476 block:block_unplug:[jbd2/dm-0-8] 1
  1618.088 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
  1810.000 :0/0 net:net_dev_queue:dev=vnet0 skbaddr=0xffff93498051ef00 len=52
                                       __dev_queue_xmit ([kernel.kallsyms])
  3857.974 :0/0 net:net_dev_queue:dev=vnet0 skbaddr=0xffff93498051f900 len=52
                                       __dev_queue_xmit ([kernel.kallsyms])
  4790.277 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
  4790.448 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
  #

The global --max-events has precendence:

  # trace --max-events 3 -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
     0.000 :0/0 sched:sched_switch:swapper/0:0 [120] S ==> qemu-system-x86:2252 [120]
     0.029 qemu-system-x8/2252 sched:sched_switch:qemu-system-x86:2252 [120] D ==> swapper/0:0 [120]
    58.047 DNS Res~er #14/31661 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff9346966af100 len=84
                                       __dev_queue_xmit ([kernel.kallsyms])
                                       __libc_send (/usr/lib64/libpthread-2.26.so)
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-s4jswltvh660ughvg9nwngah@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-trace.txt | 20 ++++++++++++++++++++
 tools/perf/builtin-trace.c              | 19 +++++++++++++++++--
 tools/perf/util/evsel.h                 |  1 +
 3 files changed, 38 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 0d1a1cd4d328..e113450503d2 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -285,6 +285,26 @@ Trace the next min page page fault to take place on the first CPU:
                                        [0x18b26e6bc2bd] (/tmp/perf-17136.map)
   #
 
+Trace the next two sched:sched_switch events, four block:*_plug events, the
+next block:*_unplug and the next three net:*dev_queue events, this last one
+with a backtrace of at most 16 entries, system wide:
+
+  # perf trace -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
+     0.000 :0/0 sched:sched_switch:swapper/2:0 [120] S ==> rcu_sched:10 [120]
+     0.015 rcu_sched/10 sched:sched_switch:rcu_sched:10 [120] R ==> swapper/2:0 [120]
+   254.198 irq/50-iwlwifi/680 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051f600 len=66
+                                       __dev_queue_xmit ([kernel.kallsyms])
+   273.977 :0/0 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051f600 len=78
+                                       __dev_queue_xmit ([kernel.kallsyms])
+   274.007 :0/0 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051ff00 len=78
+                                       __dev_queue_xmit ([kernel.kallsyms])
+  2930.140 kworker/u16:58/2722 block:block_plug:[kworker/u16:58]
+  2930.162 kworker/u16:58/2722 block:block_unplug:[kworker/u16:58] 1
+  4466.094 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
+  8050.123 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
+  8050.271 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
+  #
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script[1]
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 589e0412652a..7081d7ea12e5 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2092,8 +2092,18 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 				union perf_event *event __maybe_unused,
 				struct perf_sample *sample)
 {
-	struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+	struct thread *thread;
 	int callchain_ret = 0;
+	/*
+	 * Check if we called perf_evsel__disable(evsel) due to, for instance,
+	 * this event's max_events having been hit and this is an entry coming
+	 * from the ring buffer that we should discard, since the max events
+	 * have already been considered/printed.
+	 */
+	if (evsel->disabled)
+		return 0;
+
+	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 
 	if (sample->callchain) {
 		callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
@@ -2142,6 +2152,11 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 					      sample->raw_data, sample->raw_size,
 					      trace->output);
 			++trace->nr_events_printed;
+
+			if (evsel->max_events != ULONG_MAX && ++evsel->nr_events_printed == evsel->max_events) {
+				perf_evsel__disable(evsel);
+				perf_evsel__close(evsel);
+			}
 		}
 	}
 
@@ -2726,7 +2741,7 @@ next_event:
 		int timeout = done ? 100 : -1;
 
 		if (!draining && perf_evlist__poll(evlist, timeout) > 0) {
-			if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP) == 0)
+			if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP | POLLNVAL) == 0)
 				draining = true;
 
 			goto again;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4ef50f157b50..3147ca76c6fc 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -102,6 +102,7 @@ struct perf_evsel {
 	int			idx;
 	u32			ids;
 	unsigned long		max_events;
+	unsigned long		nr_events_printed;
 	char			*name;
 	double			scale;
 	const char		*unit;
-- 
cgit v1.2.3


From 3e71c70c946b5d5e7b21397c621b14951e5c0fcf Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:35 +0300
Subject: perf scripts python: call-graph-from-sql.py: Use SPDX license
 identifier

Use SPDX license identifier in call-graph-from-sql.py.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index b494a67a1c67..ce1b91fcd6b8 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -1,15 +1,7 @@
 #!/usr/bin/python2
-# call-graph-from-sql.py: create call-graph from sql database
-# Copyright (c) 2014-2017, Intel Corporation.
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms and conditions of the GNU General Public License,
-# version 2, as published by the Free Software Foundation.
-#
-# This program is distributed in the hope it will be useful, but WITHOUT
-# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-# more details.
+# SPDX-License-Identifier: GPL-2.0
+# exported-sql-viewer.py: view data from sql database
+# Copyright (c) 2014-2018, Intel Corporation.
 
 # To use this script you will need to have exported data using either the
 # export-to-sqlite.py or the export-to-postgresql.py script.  Refer to those
-- 
cgit v1.2.3


From 88c2e3b4a97277399ceb80d630e9838330b2146a Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Sat, 20 Oct 2018 23:33:09 +0200
Subject: tc-tests: test denial of 'goto chain' on 'random' traffic in
 gact.json

add test to verify if act_gact forbids 'goto chain' control actions on
'random' traffic in gact.json.

Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/gact.json          | 24 ++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
index 68c91023cdb9..89189a03ce3d 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
@@ -536,5 +536,29 @@
         "matchPattern": "^[ \t]+index [0-9]+ ref",
         "matchCount": "0",
         "teardown": []
+    },
+    {
+        "id": "8e47",
+        "name": "Add gact action with random determ goto chain control action",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action pass random determ goto chain 1 2 index 90",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action pass random type determ goto chain 1 val 2.*index 90 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
     }
 ]
-- 
cgit v1.2.3


From 246e886d22e2a8ceceec1f4f66138f93eafddbaa Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Sat, 20 Oct 2018 23:33:10 +0200
Subject: tc-tests: test denial of 'goto chain' for exceed traffic in
 police.json

add test to verify if act_police forbids 'goto chain' control actions for
'exceed' traffic.

Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/police.json        | 24 ++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
index 30f9b54bd666..4086a50a670e 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
@@ -715,5 +715,29 @@
         "teardown": [
             "$TC actions flush action police"
         ]
+    },
+    {
+        "id": "b48b",
+        "name": "Add police action with exceed goto chain control action",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action police rate 1mbit burst 1k conform-exceed pass / goto chain 42",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action police",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 1Mbit burst 1Kb mtu 2Kb action pass/goto chain 42",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
     }
 ]
-- 
cgit v1.2.3


From 1d865c06f5715df94528f76d6bb7f6f98975e04e Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:36 +0300
Subject: perf scripts python: call-graph-from-sql.py: Provide better default
 column sizes

Set initial column sizes to improve initial display.

Committer testing:

Extended instructions on testing this, using the sqlite variant:

Make sure you have the SQLite glue for python+Qt installed, on fedora 27
I used:

  # dnf install python-pyside

Collect some PT samples, say 5-secs worth, system wide:

  # perf record -r 10 -e intel_pt//u -a sleep 5
  [ perf record: Woken up 49 times to write data ]
  [ perf record: Captured and wrote 96.131 MB perf.data ]

This results in this perf.data file:

  # ls -larth perf.data
  -rw-------. 1 root root 97M Oct 23 10:11 perf.data

With the following attributes:

  # perf evlist -v
  intel_pt//u: type: 8, size: 112, config: 0x300e601, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, exclude_kernel: 1, exclude_hv: 1, sample_id_all: 1
  dummy:u: type: 1, size: 112, config: 0x9, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|IDENTIFIER, read_format: ID, inherit: 1, exclude_kernel: 1, exclude_hv: 1, mmap: 1, comm: 1, task: 1, sample_id_all: 1, mmap2: 1, comm_exec: 1, context_switch: 1
  #

Then generate the "pt_example" tables using:

  # perf script -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py pt_example branches calls
  2018-10-23 10:56:59.177711 Creating database...
  2018-10-23 10:56:59.195842 Writing records...
   instruction trace error type 1 cpu 2 pid 1644 tid 1644 ip 0x263984516750 code 5: Failed to get instruction
   instruction trace error type 1 cpu 2 pid 1644 tid 1644 ip 0x7f26e116fd20 code 6: Trace doesn't match instruction
   instruction trace error type 1 cpu 2 pid 1644 tid 1644 ip 0x7f26e162c9ee code 6: Trace doesn't match instruction
   instruction trace error type 1 cpu 2 pid 1644 tid 1644 ip 0x7f26e9ce831a code 6: Trace doesn't match instruction
  <SNIP>
   instruction trace error type 1 cpu 0 pid 1644 tid 1644 ip 0x7f26e13d07b4 code 6: Trace doesn't match instruction
  Warning:
  132 instruction trace errors
  2018-10-23 11:25:25.015717 Adding indexes
  2018-10-23 11:25:28.788061 Done
  #

In my example, that perf.data file generated this db:

  # file pt_example
  pt_example: SQLite 3.x database, last written using SQLite version 3020001
  [root@seventh perf]# ls -lah pt_example
  -rw-r--r--. 1 root root 6.6G Oct 23 11:25 pt_example
  #

Then use this python script to use that db and provide a GUI:

  $ python tools/perf/scripts/python/call-graph-from-sql.py pt_example branches calls

I compared the column widths before this patch and after applying it,
the visual results match the patch intent.

The following patches will refer to this set of instructions in the "Committer
Testing" section.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index ce1b91fcd6b8..e1014f2628a7 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -280,6 +280,9 @@ class MainWindow(QMainWindow):
 		self.view = QTreeView()
 		self.view.setModel(self.model)
 
+		for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
+			self.view.setColumnWidth(c, w)
+
 		self.setCentralWidget(self.view)
 
 if __name__ == '__main__':
-- 
cgit v1.2.3


From 3c4ef451506897a15aff76ff141c995c6cd32f4d Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:37 +0300
Subject: perf scripts python: call-graph-from-sql.py: Set a minimum window
 size

Prevent weirdly small window size.

Committer testing:

Seems to work, but even before this patch, on my system, it always
started with:

xwininfo: Window id: 0x1e00002 "Call Graph: pt_example"
<SNIP>
  Width: 800
  Height: 600
<SNIP>

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-4-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index e1014f2628a7..68153fa1b4d1 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -274,6 +274,7 @@ class MainWindow(QMainWindow):
 		style = self.style()
 		icon = style.standardIcon(QStyle.SP_MessageBoxInformation)
 		self.setWindowIcon(icon);
+		self.setMinimumSize(200, 100)
 
 		self.model = TreeModel(db)
 
-- 
cgit v1.2.3


From 99a097c987c26c8c82293fcb92908d07009c925e Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:38 +0300
Subject: perf scripts python: call-graph-from-sql.py: Change icon

There are not many standard icons, but the computer icon looks slightly
better than the information icon.

Committer testing:

Noticed the change on the icon on the gnome menu right next to the
"Activities" menu, looks nicer indeed.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-5-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 68153fa1b4d1..2e33540f3de0 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -271,9 +271,7 @@ class MainWindow(QMainWindow):
 		self.setWindowTitle("Call Graph: " + dbname)
 		self.move(100, 100)
 		self.resize(800, 600)
-		style = self.style()
-		icon = style.standardIcon(QStyle.SP_MessageBoxInformation)
-		self.setWindowIcon(icon);
+		self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
 		self.setMinimumSize(200, 100)
 
 		self.model = TreeModel(db)
-- 
cgit v1.2.3


From 7e4fc93e2ade2b0c453a97e307203ffe3f930c98 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:39 +0300
Subject: perf scripts python: call-graph-from-sql.py: Make a "Main" function

Make a "Main" function so that the variables used do not pollute the global
namespace.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-6-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 2e33540f3de0..2b74b94eeccc 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -284,7 +284,9 @@ class MainWindow(QMainWindow):
 
 		self.setCentralWidget(self.view)
 
-if __name__ == '__main__':
+# Main
+
+def Main():
 	if (len(sys.argv) < 2):
 		print >> sys.stderr, "Usage is: call-graph-from-sql.py <database name>"
 		raise Exception("Too few arguments")
@@ -331,3 +333,6 @@ if __name__ == '__main__':
 	err = app.exec_()
 	db.close()
 	sys.exit(err)
+
+if __name__ == "__main__":
+	Main()
-- 
cgit v1.2.3


From b2556c46a69b4c0e6bbf690ac4ca2913cbe90e1e Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:40 +0300
Subject: perf scripts python: call-graph-from-sql.py: Separate the database
 details into a class

Separate the database details into a class that can provide different
connections using the same connection information.  That paves the way
for sub-processes that require their own connection.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-7-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 63 ++++++++++++++----------
 1 file changed, 38 insertions(+), 25 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 2b74b94eeccc..9d056deab2b1 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -284,6 +284,42 @@ class MainWindow(QMainWindow):
 
 		self.setCentralWidget(self.view)
 
+# Database reference
+
+class DBRef():
+
+	def __init__(self, is_sqlite3, dbname):
+		self.is_sqlite3 = is_sqlite3
+		self.dbname = dbname
+
+	def Open(self, connection_name):
+		dbname = self.dbname
+		if self.is_sqlite3:
+			db = QSqlDatabase.addDatabase("QSQLITE", connection_name)
+		else:
+			db = QSqlDatabase.addDatabase("QPSQL", connection_name)
+			opts = dbname.split()
+			for opt in opts:
+				if "=" in opt:
+					opt = opt.split("=")
+					if opt[0] == "hostname":
+						db.setHostName(opt[1])
+					elif opt[0] == "port":
+						db.setPort(int(opt[1]))
+					elif opt[0] == "username":
+						db.setUserName(opt[1])
+					elif opt[0] == "password":
+						db.setPassword(opt[1])
+					elif opt[0] == "dbname":
+						dbname = opt[1]
+				else:
+					dbname = opt
+
+		db.setDatabaseName(dbname)
+		if not db.open():
+			raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text())
+		return db, dbname
+
 # Main
 
 def Main():
@@ -302,31 +338,8 @@ def Main():
 	except:
 		pass
 
-	if is_sqlite3:
-		db = QSqlDatabase.addDatabase('QSQLITE')
-	else:
-		db = QSqlDatabase.addDatabase('QPSQL')
-		opts = dbname.split()
-		for opt in opts:
-			if '=' in opt:
-				opt = opt.split('=')
-				if opt[0] == 'hostname':
-					db.setHostName(opt[1])
-				elif opt[0] == 'port':
-					db.setPort(int(opt[1]))
-				elif opt[0] == 'username':
-					db.setUserName(opt[1])
-				elif opt[0] == 'password':
-					db.setPassword(opt[1])
-				elif opt[0] == 'dbname':
-					dbname = opt[1]
-			else:
-				dbname = opt
-
-	db.setDatabaseName(dbname)
-	if not db.open():
-		raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text())
-
+	dbref = DBRef(is_sqlite3, dbname)
+	db, dbname = dbref.Open("main")
 	app = QApplication(sys.argv)
 	window = MainWindow(db, dbname)
 	window.show()
-- 
cgit v1.2.3


From 5f9dfef1bb7fadfb2d001244ef23359982fedd06 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:41 +0300
Subject: perf scripts python: call-graph-from-sql.py: Add a class for global
 data

Keep global data in a single object that is easy to pass around as
needed, without polluting the global namespace.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-8-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 26 +++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 9d056deab2b1..0a4dc13d4818 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -264,17 +264,19 @@ class TreeModel(QAbstractItemModel):
 
 class MainWindow(QMainWindow):
 
-	def __init__(self, db, dbname, parent=None):
+	def __init__(self, glb, parent=None):
 		super(MainWindow, self).__init__(parent)
 
+		self.glb = glb
+
 		self.setObjectName("MainWindow")
-		self.setWindowTitle("Call Graph: " + dbname)
+		self.setWindowTitle("Call Graph: " + glb.dbname)
 		self.move(100, 100)
 		self.resize(800, 600)
 		self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
 		self.setMinimumSize(200, 100)
 
-		self.model = TreeModel(db)
+		self.model = TreeModel(glb.db)
 
 		self.view = QTreeView()
 		self.view.setModel(self.model)
@@ -284,6 +286,17 @@ class MainWindow(QMainWindow):
 
 		self.setCentralWidget(self.view)
 
+# Global data
+
+class Glb():
+
+	def __init__(self, dbref, db, dbname):
+		self.dbref = dbref
+		self.db = db
+		self.dbname = dbname
+		self.app = None
+		self.mainwindow = None
+
 # Database reference
 
 class DBRef():
@@ -340,9 +353,12 @@ def Main():
 
 	dbref = DBRef(is_sqlite3, dbname)
 	db, dbname = dbref.Open("main")
+	glb = Glb(dbref, db, dbname)
 	app = QApplication(sys.argv)
-	window = MainWindow(db, dbname)
-	window.show()
+	glb.app = app
+	mainwindow = MainWindow(glb)
+	glb.mainwindow = mainwindow
+	mainwindow.show()
 	err = app.exec_()
 	db.close()
 	sys.exit(err)
-- 
cgit v1.2.3


From e99ef8141a6d97abaf47647cfd0034769144d080 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:42 +0300
Subject: perf scripts python: call-graph-from-sql.py: Remove use of
 setObjectName()

The object name is never used, so don't bother setting it.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-9-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 1 -
 1 file changed, 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 0a4dc13d4818..65c18e351bc4 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -269,7 +269,6 @@ class MainWindow(QMainWindow):
 
 		self.glb = glb
 
-		self.setObjectName("MainWindow")
 		self.setWindowTitle("Call Graph: " + glb.dbname)
 		self.move(100, 100)
 		self.resize(800, 600)
-- 
cgit v1.2.3


From 70d831e85c1bdd87d193e85666bf3aa39aab7f21 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:43 +0300
Subject: perf scripts python: call-graph-from-sql.py: Factor out
 CallGraphModel from TreeModel

Factor out CallGraphModel from TreeModel, which paves the way to reuse
TreeModel in future reports.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-10-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 90 ++++++++++++++++--------
 1 file changed, 61 insertions(+), 29 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 65c18e351bc4..ada486048ad8 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -201,42 +201,47 @@ class TreeItem():
 			self.selectCalls()
 		return self.child_count
 
-	def columnCount(self):
-		return 7
-
-	def columnHeader(self, column):
-		headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
-		return headers[column]
+	def hasChildren(self):
+		if not self.query_done:
+			return True
+		return self.child_count > 0
 
 	def getData(self, column):
 		return self.data[column]
 
+# Tree data model
+
 class TreeModel(QAbstractItemModel):
 
-	def __init__(self, db, parent=None):
+	def __init__(self, root, parent=None):
 		super(TreeModel, self).__init__(parent)
-		self.db = db
-		self.root = TreeItem(db, 0, None)
+		self.root = root
+		self.last_row_read = 0
 
-	def columnCount(self, parent):
-		return self.root.columnCount()
-
-	def rowCount(self, parent):
+	def Item(self, parent):
 		if parent.isValid():
-			parent_item = parent.internalPointer()
+			return parent.internalPointer()
 		else:
-			parent_item = self.root
-		return parent_item.childCount()
+			return self.root
+
+	def rowCount(self, parent):
+		result = self.Item(parent).childCount()
+		if result < 0:
+			result = 0
+			self.dataChanged.emit(parent, parent)
+		return result
+
+	def hasChildren(self, parent):
+		return self.Item(parent).hasChildren()
 
 	def headerData(self, section, orientation, role):
 		if role == Qt.TextAlignmentRole:
-			if section > 1:
-				return Qt.AlignRight
+			return self.columnAlignment(section)
 		if role != Qt.DisplayRole:
 			return None
 		if orientation != Qt.Horizontal:
 			return None
-		return self.root.columnHeader(section)
+		return self.columnHeader(section)
 
 	def parent(self, child):
 		child_item = child.internalPointer()
@@ -246,21 +251,48 @@ class TreeModel(QAbstractItemModel):
 		return self.createIndex(parent_item.getRow(), 0, parent_item)
 
 	def index(self, row, column, parent):
-		if parent.isValid():
-			parent_item = parent.internalPointer()
-		else:
-			parent_item = self.root
-		child_item = parent_item.getChildItem(row)
+		child_item = self.Item(parent).getChildItem(row)
 		return self.createIndex(row, column, child_item)
 
+	def DisplayData(self, item, index):
+		return item.getData(index.column())
+
+	def columnAlignment(self, column):
+		return Qt.AlignLeft
+
+	def columnFont(self, column):
+		return None
+
 	def data(self, index, role):
 		if role == Qt.TextAlignmentRole:
-			if index.column() > 1:
-				return Qt.AlignRight
+			return self.columnAlignment(index.column())
+		if role == Qt.FontRole:
+			return self.columnFont(index.column())
 		if role != Qt.DisplayRole:
 			return None
-		index_item = index.internalPointer()
-		return index_item.getData(index.column())
+		item = index.internalPointer()
+		return self.DisplayData(item, index)
+
+# Context-sensitive call graph data model
+
+class CallGraphModel(TreeModel):
+
+	def __init__(self, glb, parent=None):
+		super(CallGraphModel, self).__init__(TreeItem(glb.db, 0, None), parent)
+		self.glb = glb
+
+	def columnCount(self, parent=None):
+		return 7
+
+	def columnHeader(self, column):
+		headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
+		return headers[column]
+
+	def columnAlignment(self, column):
+		alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
+		return alignment[column]
+
+# Main window
 
 class MainWindow(QMainWindow):
 
@@ -275,7 +307,7 @@ class MainWindow(QMainWindow):
 		self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
 		self.setMinimumSize(200, 100)
 
-		self.model = TreeModel(glb.db)
+		self.model = CallGraphModel(glb)
 
 		self.view = QTreeView()
 		self.view.setModel(self.model)
-- 
cgit v1.2.3


From 4be9ace7e1cdcb44c1fba1fb41ec2b92dda06732 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:44 +0300
Subject: perf scripts python: call-graph-from-sql.py: Add data helper
 functions

Add helper functions for a few common cases.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-11-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 54 +++++++++++++-----------
 1 file changed, 29 insertions(+), 25 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index ada486048ad8..7f2eabe7dacd 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -52,6 +52,28 @@ from PySide.QtGui import *
 from PySide.QtSql import *
 from decimal import *
 
+# Data formatting helpers
+
+def dsoname(name):
+	if name == "[kernel.kallsyms]":
+		return "[kernel]"
+	return name
+
+# Percent to one decimal place
+
+def PercentToOneDP(n, d):
+	if not d:
+		return "0.0"
+	x = (n * Decimal(100)) / d
+	return str(x.quantize(Decimal(".1"), rounding=ROUND_HALF_UP))
+
+# Helper for queries that must not fail
+
+def QueryExec(query, stmt):
+	ret = query.exec_(stmt)
+	if not ret:
+		raise Exception("Query failed: " + query.lastError().text())
+
 class TreeItem():
 
 	def __init__(self, db, row, parent_item):
@@ -73,9 +95,7 @@ class TreeItem():
 	def setUpRoot(self):
 		self.query_done = True
 		query = QSqlQuery(self.db)
-		ret = query.exec_('SELECT id, comm FROM comms')
-		if not ret:
-			raise Exception("Query failed: " + query.lastError().text())
+		QueryExec(query, 'SELECT id, comm FROM comms')
 		while query.next():
 			if not query.value(0):
 				continue
@@ -91,9 +111,7 @@ class TreeItem():
 		self.child_items = []
 		self.child_count = 0
 		query = QSqlQuery(self.db)
-		ret = query.exec_('SELECT thread_id, ( SELECT pid FROM threads WHERE id = thread_id ), ( SELECT tid FROM threads WHERE id = thread_id ) FROM comm_threads WHERE comm_id = ' + str(comm_id))
-		if not ret:
-			raise Exception("Query failed: " + query.lastError().text())
+		QueryExec(query, 'SELECT thread_id, ( SELECT pid FROM threads WHERE id = thread_id ), ( SELECT tid FROM threads WHERE id = thread_id ) FROM comm_threads WHERE comm_id = ' + str(comm_id))
 		while query.next():
 			child_item = TreeItem(self.db, self.child_count, self)
 			self.child_items.append(child_item)
@@ -114,18 +132,6 @@ class TreeItem():
 	def getRow(self):
 		return self.row
 
-	def timePercent(self, b):
-		if not self.time:
-			return "0.0"
-		x = (b * Decimal(100)) / self.time
-		return str(x.quantize(Decimal('.1'), rounding=ROUND_HALF_UP))
-
-	def branchPercent(self, b):
-		if not self.branch_count:
-			return "0.0"
-		x = (b * Decimal(100)) / self.branch_count
-		return str(x.quantize(Decimal('.1'), rounding=ROUND_HALF_UP))
-
 	def addChild(self, call_path_id, name, dso, count, time, branch_count):
 		child_item = TreeItem(self.db, self.child_count, self)
 		child_item.comm_id = self.comm_id
@@ -134,14 +140,12 @@ class TreeItem():
 		child_item.branch_count = branch_count
 		child_item.time = time
 		child_item.data[0] = name
-		if dso == "[kernel.kallsyms]":
-			dso = "[kernel]"
-		child_item.data[1] = dso
+		child_item.data[1] = dsoname(dso)
 		child_item.data[2] = str(count)
 		child_item.data[3] = str(time)
-		child_item.data[4] = self.timePercent(time)
+		child_item.data[4] = PercentToOneDP(time, self.time)
 		child_item.data[5] = str(branch_count)
-		child_item.data[6] = self.branchPercent(branch_count)
+		child_item.data[6] = PercentToOneDP(branch_count, self.branch_count)
 		self.child_items.append(child_item)
 		self.child_count += 1
 
@@ -189,12 +193,12 @@ class TreeItem():
 			self.branch_count = total_branch_count
 			if self.branch_count:
 				for child_item in self.child_items:
-					child_item.data[6] = self.branchPercent(child_item.branch_count)
+					child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
 		if total_time > self.time:
 			self.time = total_time
 			if self.time:
 				for child_item in self.child_items:
-					child_item.data[4] = self.timePercent(child_item.time)
+					child_item.data[4] = PercentToOneDP(child_item.time, self.time)
 
 	def childCount(self):
 		if not self.query_done:
-- 
cgit v1.2.3


From 341e73cbd3019d350d1271803b45d84af88f2408 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:45 +0300
Subject: perf scripts python: call-graph-from-sql.py: Refactor TreeItem class

class TreeItem represents items at all levels of the call-graph tree.
However, not all the levels represent the same data i.e. the top-level is
comms, the next level is threads, and subsequent levels are functions.
Consequently it is simpler to have separate classes for different levels
with commonality in a base class. Refactor TreeItem class accordingly.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-12-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 273 +++++++++++------------
 1 file changed, 133 insertions(+), 140 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 7f2eabe7dacd..ee1085169a3e 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -74,145 +74,6 @@ def QueryExec(query, stmt):
 	if not ret:
 		raise Exception("Query failed: " + query.lastError().text())
 
-class TreeItem():
-
-	def __init__(self, db, row, parent_item):
-		self.db = db
-		self.row = row
-		self.parent_item = parent_item
-		self.query_done = False;
-		self.child_count = 0
-		self.child_items = []
-		self.data = ["", "", "", "", "", "", ""]
-		self.comm_id = 0
-		self.thread_id = 0
-		self.call_path_id = 1
-		self.branch_count = 0
-		self.time = 0
-		if not parent_item:
-			self.setUpRoot()
-
-	def setUpRoot(self):
-		self.query_done = True
-		query = QSqlQuery(self.db)
-		QueryExec(query, 'SELECT id, comm FROM comms')
-		while query.next():
-			if not query.value(0):
-				continue
-			child_item = TreeItem(self.db, self.child_count, self)
-			self.child_items.append(child_item)
-			self.child_count += 1
-			child_item.setUpLevel1(query.value(0), query.value(1))
-
-	def setUpLevel1(self, comm_id, comm):
-		self.query_done = True;
-		self.comm_id = comm_id
-		self.data[0] = comm
-		self.child_items = []
-		self.child_count = 0
-		query = QSqlQuery(self.db)
-		QueryExec(query, 'SELECT thread_id, ( SELECT pid FROM threads WHERE id = thread_id ), ( SELECT tid FROM threads WHERE id = thread_id ) FROM comm_threads WHERE comm_id = ' + str(comm_id))
-		while query.next():
-			child_item = TreeItem(self.db, self.child_count, self)
-			self.child_items.append(child_item)
-			self.child_count += 1
-			child_item.setUpLevel2(comm_id, query.value(0), query.value(1), query.value(2))
-
-	def setUpLevel2(self, comm_id, thread_id, pid, tid):
-		self.comm_id = comm_id
-		self.thread_id = thread_id
-		self.data[0] = str(pid) + ":" + str(tid)
-
-	def getChildItem(self, row):
-		return self.child_items[row]
-
-	def getParentItem(self):
-		return self.parent_item
-
-	def getRow(self):
-		return self.row
-
-	def addChild(self, call_path_id, name, dso, count, time, branch_count):
-		child_item = TreeItem(self.db, self.child_count, self)
-		child_item.comm_id = self.comm_id
-		child_item.thread_id = self.thread_id
-		child_item.call_path_id = call_path_id
-		child_item.branch_count = branch_count
-		child_item.time = time
-		child_item.data[0] = name
-		child_item.data[1] = dsoname(dso)
-		child_item.data[2] = str(count)
-		child_item.data[3] = str(time)
-		child_item.data[4] = PercentToOneDP(time, self.time)
-		child_item.data[5] = str(branch_count)
-		child_item.data[6] = PercentToOneDP(branch_count, self.branch_count)
-		self.child_items.append(child_item)
-		self.child_count += 1
-
-	def selectCalls(self):
-		self.query_done = True;
-		query = QSqlQuery(self.db)
-		ret = query.exec_('SELECT id, call_path_id, branch_count, call_time, return_time, '
-				  '( SELECT name FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ), '
-				  '( SELECT short_name FROM dsos WHERE id = ( SELECT dso_id FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ) ), '
-				  '( SELECT ip FROM call_paths where id = call_path_id ) '
-				  'FROM calls WHERE parent_call_path_id = ' + str(self.call_path_id) + ' AND comm_id = ' + str(self.comm_id) + ' AND thread_id = ' + str(self.thread_id) +
-				  ' ORDER BY call_path_id')
-		if not ret:
-			raise Exception("Query failed: " + query.lastError().text())
-		last_call_path_id = 0
-		name = ""
-		dso = ""
-		count = 0
-		branch_count = 0
-		total_branch_count = 0
-		time = 0
-		total_time = 0
-		while query.next():
-			if query.value(1) == last_call_path_id:
-				count += 1
-				branch_count += query.value(2)
-				time += query.value(4) - query.value(3)
-			else:
-				if count:
-					self.addChild(last_call_path_id, name, dso, count, time, branch_count)
-				last_call_path_id = query.value(1)
-				name = query.value(5)
-				dso = query.value(6)
-				count = 1
-				total_branch_count += branch_count
-				total_time += time
-				branch_count = query.value(2)
-				time = query.value(4) - query.value(3)
-		if count:
-			self.addChild(last_call_path_id, name, dso, count, time, branch_count)
-		total_branch_count += branch_count
-		total_time += time
-		# Top level does not have time or branch count, so fix that here
-		if total_branch_count > self.branch_count:
-			self.branch_count = total_branch_count
-			if self.branch_count:
-				for child_item in self.child_items:
-					child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
-		if total_time > self.time:
-			self.time = total_time
-			if self.time:
-				for child_item in self.child_items:
-					child_item.data[4] = PercentToOneDP(child_item.time, self.time)
-
-	def childCount(self):
-		if not self.query_done:
-			self.selectCalls()
-		return self.child_count
-
-	def hasChildren(self):
-		if not self.query_done:
-			return True
-		return self.child_count > 0
-
-	def getData(self, column):
-		return self.data[column]
-
 # Tree data model
 
 class TreeModel(QAbstractItemModel):
@@ -277,12 +138,144 @@ class TreeModel(QAbstractItemModel):
 		item = index.internalPointer()
 		return self.DisplayData(item, index)
 
+# Context-sensitive call graph data model item base
+
+class CallGraphLevelItemBase(object):
+
+	def __init__(self, glb, row, parent_item):
+		self.glb = glb
+		self.row = row
+		self.parent_item = parent_item
+		self.query_done = False;
+		self.child_count = 0
+		self.child_items = []
+
+	def getChildItem(self, row):
+		return self.child_items[row]
+
+	def getParentItem(self):
+		return self.parent_item
+
+	def getRow(self):
+		return self.row
+
+	def childCount(self):
+		if not self.query_done:
+			self.Select()
+			if not self.child_count:
+				return -1
+		return self.child_count
+
+	def hasChildren(self):
+		if not self.query_done:
+			return True
+		return self.child_count > 0
+
+	def getData(self, column):
+		return self.data[column]
+
+# Context-sensitive call graph data model level 2+ item base
+
+class CallGraphLevelTwoPlusItemBase(CallGraphLevelItemBase):
+
+	def __init__(self, glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item):
+		super(CallGraphLevelTwoPlusItemBase, self).__init__(glb, row, parent_item)
+		self.comm_id = comm_id
+		self.thread_id = thread_id
+		self.call_path_id = call_path_id
+		self.branch_count = branch_count
+		self.time = time
+
+	def Select(self):
+		self.query_done = True;
+		query = QSqlQuery(self.glb.db)
+		QueryExec(query, "SELECT call_path_id, name, short_name, COUNT(calls.id), SUM(return_time - call_time), SUM(branch_count)"
+					" FROM calls"
+					" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
+					" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
+					" INNER JOIN dsos ON symbols.dso_id = dsos.id"
+					" WHERE parent_call_path_id = " + str(self.call_path_id) +
+					" AND comm_id = " + str(self.comm_id) +
+					" AND thread_id = " + str(self.thread_id) +
+					" GROUP BY call_path_id, name, short_name"
+					" ORDER BY call_path_id")
+		while query.next():
+			child_item = CallGraphLevelThreeItem(self.glb, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), int(query.value(5)), self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+
+# Context-sensitive call graph data model level three item
+
+class CallGraphLevelThreeItem(CallGraphLevelTwoPlusItemBase):
+
+	def __init__(self, glb, row, comm_id, thread_id, call_path_id, name, dso, count, time, branch_count, parent_item):
+		super(CallGraphLevelThreeItem, self).__init__(glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item)
+		dso = dsoname(dso)
+		self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ]
+		self.dbid = call_path_id
+
+# Context-sensitive call graph data model level two item
+
+class CallGraphLevelTwoItem(CallGraphLevelTwoPlusItemBase):
+
+	def __init__(self, glb, row, comm_id, thread_id, pid, tid, parent_item):
+		super(CallGraphLevelTwoItem, self).__init__(glb, row, comm_id, thread_id, 1, 0, 0, parent_item)
+		self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""]
+		self.dbid = thread_id
+
+	def Select(self):
+		super(CallGraphLevelTwoItem, self).Select()
+		for child_item in self.child_items:
+			self.time += child_item.time
+			self.branch_count += child_item.branch_count
+		for child_item in self.child_items:
+			child_item.data[4] = PercentToOneDP(child_item.time, self.time)
+			child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
+
+# Context-sensitive call graph data model level one item
+
+class CallGraphLevelOneItem(CallGraphLevelItemBase):
+
+	def __init__(self, glb, row, comm_id, comm, parent_item):
+		super(CallGraphLevelOneItem, self).__init__(glb, row, parent_item)
+		self.data = [comm, "", "", "", "", "", ""]
+		self.dbid = comm_id
+
+	def Select(self):
+		self.query_done = True;
+		query = QSqlQuery(self.glb.db)
+		QueryExec(query, "SELECT thread_id, pid, tid"
+					" FROM comm_threads"
+					" INNER JOIN threads ON thread_id = threads.id"
+					" WHERE comm_id = " + str(self.dbid))
+		while query.next():
+			child_item = CallGraphLevelTwoItem(self.glb, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+
+# Context-sensitive call graph data model root item
+
+class CallGraphRootItem(CallGraphLevelItemBase):
+
+	def __init__(self, glb):
+		super(CallGraphRootItem, self).__init__(glb, 0, None)
+		self.dbid = 0
+		self.query_done = True;
+		query = QSqlQuery(glb.db)
+		QueryExec(query, "SELECT id, comm FROM comms")
+		while query.next():
+			if not query.value(0):
+				continue
+			child_item = CallGraphLevelOneItem(glb, self.child_count, query.value(0), query.value(1), self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+
 # Context-sensitive call graph data model
 
 class CallGraphModel(TreeModel):
 
 	def __init__(self, glb, parent=None):
-		super(CallGraphModel, self).__init__(TreeItem(glb.db, 0, None), parent)
+		super(CallGraphModel, self).__init__(CallGraphRootItem(glb), parent)
 		self.glb = glb
 
 	def columnCount(self, parent=None):
-- 
cgit v1.2.3


From 031c2a004ba75a4f8f2a6d0a7ca6f2fe5912de22 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:46 +0300
Subject: perf scripts python: call-graph-from-sql.py: Rename to
 exported-sql-viewer.py

Additional reports will be added to the script so rename to reflect the
more general purpose.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-13-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/intel-pt.txt             |   2 +-
 tools/perf/scripts/python/call-graph-from-sql.py  | 395 ----------------------
 tools/perf/scripts/python/export-to-postgresql.py |   2 +-
 tools/perf/scripts/python/export-to-sqlite.py     |   2 +-
 tools/perf/scripts/python/exported-sql-viewer.py  | 395 ++++++++++++++++++++++
 5 files changed, 398 insertions(+), 398 deletions(-)
 delete mode 100644 tools/perf/scripts/python/call-graph-from-sql.py
 create mode 100755 tools/perf/scripts/python/exported-sql-viewer.py

(limited to 'tools')

diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index 76971d2e4164..115eaacc455f 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -106,7 +106,7 @@ in transaction, respectively.
 While it is possible to create scripts to analyze the data, an alternative
 approach is available to export the data to a sqlite or postgresql database.
 Refer to script export-to-sqlite.py or export-to-postgresql.py for more details,
-and to script call-graph-from-sql.py for an example of using the database.
+and to script exported-sql-viewer.py for an example of using the database.
 
 There is also script intel-pt-events.py which provides an example of how to
 unpack the raw data for power events and PTWRITE.
diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
deleted file mode 100644
index ee1085169a3e..000000000000
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ /dev/null
@@ -1,395 +0,0 @@
-#!/usr/bin/python2
-# SPDX-License-Identifier: GPL-2.0
-# exported-sql-viewer.py: view data from sql database
-# Copyright (c) 2014-2018, Intel Corporation.
-
-# To use this script you will need to have exported data using either the
-# export-to-sqlite.py or the export-to-postgresql.py script.  Refer to those
-# scripts for details.
-#
-# Following on from the example in the export scripts, a
-# call-graph can be displayed for the pt_example database like this:
-#
-#	python tools/perf/scripts/python/call-graph-from-sql.py pt_example
-#
-# Note that for PostgreSQL, this script supports connecting to remote databases
-# by setting hostname, port, username, password, and dbname e.g.
-#
-#	python tools/perf/scripts/python/call-graph-from-sql.py "hostname=myhost username=myuser password=mypassword dbname=pt_example"
-#
-# The result is a GUI window with a tree representing a context-sensitive
-# call-graph.  Expanding a couple of levels of the tree and adjusting column
-# widths to suit will display something like:
-#
-#                                         Call Graph: pt_example
-# Call Path                          Object      Count   Time(ns)  Time(%)  Branch Count   Branch Count(%)
-# v- ls
-#     v- 2638:2638
-#         v- _start                  ld-2.19.so    1     10074071   100.0         211135            100.0
-#           |- unknown               unknown       1        13198     0.1              1              0.0
-#           >- _dl_start             ld-2.19.so    1      1400980    13.9          19637              9.3
-#           >- _d_linit_internal     ld-2.19.so    1       448152     4.4          11094              5.3
-#           v-__libc_start_main@plt  ls            1      8211741    81.5         180397             85.4
-#              >- _dl_fixup          ld-2.19.so    1         7607     0.1            108              0.1
-#              >- __cxa_atexit       libc-2.19.so  1        11737     0.1             10              0.0
-#              >- __libc_csu_init    ls            1        10354     0.1             10              0.0
-#              |- _setjmp            libc-2.19.so  1            0     0.0              4              0.0
-#              v- main               ls            1      8182043    99.6         180254             99.9
-#
-# Points to note:
-#	The top level is a command name (comm)
-#	The next level is a thread (pid:tid)
-#	Subsequent levels are functions
-#	'Count' is the number of calls
-#	'Time' is the elapsed time until the function returns
-#	Percentages are relative to the level above
-#	'Branch Count' is the total number of branches for that function and all
-#       functions that it calls
-
-import sys
-from PySide.QtCore import *
-from PySide.QtGui import *
-from PySide.QtSql import *
-from decimal import *
-
-# Data formatting helpers
-
-def dsoname(name):
-	if name == "[kernel.kallsyms]":
-		return "[kernel]"
-	return name
-
-# Percent to one decimal place
-
-def PercentToOneDP(n, d):
-	if not d:
-		return "0.0"
-	x = (n * Decimal(100)) / d
-	return str(x.quantize(Decimal(".1"), rounding=ROUND_HALF_UP))
-
-# Helper for queries that must not fail
-
-def QueryExec(query, stmt):
-	ret = query.exec_(stmt)
-	if not ret:
-		raise Exception("Query failed: " + query.lastError().text())
-
-# Tree data model
-
-class TreeModel(QAbstractItemModel):
-
-	def __init__(self, root, parent=None):
-		super(TreeModel, self).__init__(parent)
-		self.root = root
-		self.last_row_read = 0
-
-	def Item(self, parent):
-		if parent.isValid():
-			return parent.internalPointer()
-		else:
-			return self.root
-
-	def rowCount(self, parent):
-		result = self.Item(parent).childCount()
-		if result < 0:
-			result = 0
-			self.dataChanged.emit(parent, parent)
-		return result
-
-	def hasChildren(self, parent):
-		return self.Item(parent).hasChildren()
-
-	def headerData(self, section, orientation, role):
-		if role == Qt.TextAlignmentRole:
-			return self.columnAlignment(section)
-		if role != Qt.DisplayRole:
-			return None
-		if orientation != Qt.Horizontal:
-			return None
-		return self.columnHeader(section)
-
-	def parent(self, child):
-		child_item = child.internalPointer()
-		if child_item is self.root:
-			return QModelIndex()
-		parent_item = child_item.getParentItem()
-		return self.createIndex(parent_item.getRow(), 0, parent_item)
-
-	def index(self, row, column, parent):
-		child_item = self.Item(parent).getChildItem(row)
-		return self.createIndex(row, column, child_item)
-
-	def DisplayData(self, item, index):
-		return item.getData(index.column())
-
-	def columnAlignment(self, column):
-		return Qt.AlignLeft
-
-	def columnFont(self, column):
-		return None
-
-	def data(self, index, role):
-		if role == Qt.TextAlignmentRole:
-			return self.columnAlignment(index.column())
-		if role == Qt.FontRole:
-			return self.columnFont(index.column())
-		if role != Qt.DisplayRole:
-			return None
-		item = index.internalPointer()
-		return self.DisplayData(item, index)
-
-# Context-sensitive call graph data model item base
-
-class CallGraphLevelItemBase(object):
-
-	def __init__(self, glb, row, parent_item):
-		self.glb = glb
-		self.row = row
-		self.parent_item = parent_item
-		self.query_done = False;
-		self.child_count = 0
-		self.child_items = []
-
-	def getChildItem(self, row):
-		return self.child_items[row]
-
-	def getParentItem(self):
-		return self.parent_item
-
-	def getRow(self):
-		return self.row
-
-	def childCount(self):
-		if not self.query_done:
-			self.Select()
-			if not self.child_count:
-				return -1
-		return self.child_count
-
-	def hasChildren(self):
-		if not self.query_done:
-			return True
-		return self.child_count > 0
-
-	def getData(self, column):
-		return self.data[column]
-
-# Context-sensitive call graph data model level 2+ item base
-
-class CallGraphLevelTwoPlusItemBase(CallGraphLevelItemBase):
-
-	def __init__(self, glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item):
-		super(CallGraphLevelTwoPlusItemBase, self).__init__(glb, row, parent_item)
-		self.comm_id = comm_id
-		self.thread_id = thread_id
-		self.call_path_id = call_path_id
-		self.branch_count = branch_count
-		self.time = time
-
-	def Select(self):
-		self.query_done = True;
-		query = QSqlQuery(self.glb.db)
-		QueryExec(query, "SELECT call_path_id, name, short_name, COUNT(calls.id), SUM(return_time - call_time), SUM(branch_count)"
-					" FROM calls"
-					" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
-					" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
-					" INNER JOIN dsos ON symbols.dso_id = dsos.id"
-					" WHERE parent_call_path_id = " + str(self.call_path_id) +
-					" AND comm_id = " + str(self.comm_id) +
-					" AND thread_id = " + str(self.thread_id) +
-					" GROUP BY call_path_id, name, short_name"
-					" ORDER BY call_path_id")
-		while query.next():
-			child_item = CallGraphLevelThreeItem(self.glb, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), int(query.value(5)), self)
-			self.child_items.append(child_item)
-			self.child_count += 1
-
-# Context-sensitive call graph data model level three item
-
-class CallGraphLevelThreeItem(CallGraphLevelTwoPlusItemBase):
-
-	def __init__(self, glb, row, comm_id, thread_id, call_path_id, name, dso, count, time, branch_count, parent_item):
-		super(CallGraphLevelThreeItem, self).__init__(glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item)
-		dso = dsoname(dso)
-		self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ]
-		self.dbid = call_path_id
-
-# Context-sensitive call graph data model level two item
-
-class CallGraphLevelTwoItem(CallGraphLevelTwoPlusItemBase):
-
-	def __init__(self, glb, row, comm_id, thread_id, pid, tid, parent_item):
-		super(CallGraphLevelTwoItem, self).__init__(glb, row, comm_id, thread_id, 1, 0, 0, parent_item)
-		self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""]
-		self.dbid = thread_id
-
-	def Select(self):
-		super(CallGraphLevelTwoItem, self).Select()
-		for child_item in self.child_items:
-			self.time += child_item.time
-			self.branch_count += child_item.branch_count
-		for child_item in self.child_items:
-			child_item.data[4] = PercentToOneDP(child_item.time, self.time)
-			child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
-
-# Context-sensitive call graph data model level one item
-
-class CallGraphLevelOneItem(CallGraphLevelItemBase):
-
-	def __init__(self, glb, row, comm_id, comm, parent_item):
-		super(CallGraphLevelOneItem, self).__init__(glb, row, parent_item)
-		self.data = [comm, "", "", "", "", "", ""]
-		self.dbid = comm_id
-
-	def Select(self):
-		self.query_done = True;
-		query = QSqlQuery(self.glb.db)
-		QueryExec(query, "SELECT thread_id, pid, tid"
-					" FROM comm_threads"
-					" INNER JOIN threads ON thread_id = threads.id"
-					" WHERE comm_id = " + str(self.dbid))
-		while query.next():
-			child_item = CallGraphLevelTwoItem(self.glb, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self)
-			self.child_items.append(child_item)
-			self.child_count += 1
-
-# Context-sensitive call graph data model root item
-
-class CallGraphRootItem(CallGraphLevelItemBase):
-
-	def __init__(self, glb):
-		super(CallGraphRootItem, self).__init__(glb, 0, None)
-		self.dbid = 0
-		self.query_done = True;
-		query = QSqlQuery(glb.db)
-		QueryExec(query, "SELECT id, comm FROM comms")
-		while query.next():
-			if not query.value(0):
-				continue
-			child_item = CallGraphLevelOneItem(glb, self.child_count, query.value(0), query.value(1), self)
-			self.child_items.append(child_item)
-			self.child_count += 1
-
-# Context-sensitive call graph data model
-
-class CallGraphModel(TreeModel):
-
-	def __init__(self, glb, parent=None):
-		super(CallGraphModel, self).__init__(CallGraphRootItem(glb), parent)
-		self.glb = glb
-
-	def columnCount(self, parent=None):
-		return 7
-
-	def columnHeader(self, column):
-		headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
-		return headers[column]
-
-	def columnAlignment(self, column):
-		alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
-		return alignment[column]
-
-# Main window
-
-class MainWindow(QMainWindow):
-
-	def __init__(self, glb, parent=None):
-		super(MainWindow, self).__init__(parent)
-
-		self.glb = glb
-
-		self.setWindowTitle("Call Graph: " + glb.dbname)
-		self.move(100, 100)
-		self.resize(800, 600)
-		self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
-		self.setMinimumSize(200, 100)
-
-		self.model = CallGraphModel(glb)
-
-		self.view = QTreeView()
-		self.view.setModel(self.model)
-
-		for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
-			self.view.setColumnWidth(c, w)
-
-		self.setCentralWidget(self.view)
-
-# Global data
-
-class Glb():
-
-	def __init__(self, dbref, db, dbname):
-		self.dbref = dbref
-		self.db = db
-		self.dbname = dbname
-		self.app = None
-		self.mainwindow = None
-
-# Database reference
-
-class DBRef():
-
-	def __init__(self, is_sqlite3, dbname):
-		self.is_sqlite3 = is_sqlite3
-		self.dbname = dbname
-
-	def Open(self, connection_name):
-		dbname = self.dbname
-		if self.is_sqlite3:
-			db = QSqlDatabase.addDatabase("QSQLITE", connection_name)
-		else:
-			db = QSqlDatabase.addDatabase("QPSQL", connection_name)
-			opts = dbname.split()
-			for opt in opts:
-				if "=" in opt:
-					opt = opt.split("=")
-					if opt[0] == "hostname":
-						db.setHostName(opt[1])
-					elif opt[0] == "port":
-						db.setPort(int(opt[1]))
-					elif opt[0] == "username":
-						db.setUserName(opt[1])
-					elif opt[0] == "password":
-						db.setPassword(opt[1])
-					elif opt[0] == "dbname":
-						dbname = opt[1]
-				else:
-					dbname = opt
-
-		db.setDatabaseName(dbname)
-		if not db.open():
-			raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text())
-		return db, dbname
-
-# Main
-
-def Main():
-	if (len(sys.argv) < 2):
-		print >> sys.stderr, "Usage is: call-graph-from-sql.py <database name>"
-		raise Exception("Too few arguments")
-
-	dbname = sys.argv[1]
-
-	is_sqlite3 = False
-	try:
-		f = open(dbname)
-		if f.read(15) == "SQLite format 3":
-			is_sqlite3 = True
-		f.close()
-	except:
-		pass
-
-	dbref = DBRef(is_sqlite3, dbname)
-	db, dbname = dbref.Open("main")
-	glb = Glb(dbref, db, dbname)
-	app = QApplication(sys.argv)
-	glb.app = app
-	mainwindow = MainWindow(glb)
-	glb.mainwindow = mainwindow
-	mainwindow.show()
-	err = app.exec_()
-	db.close()
-	sys.exit(err)
-
-if __name__ == "__main__":
-	Main()
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index e46f51b17513..0564dd7377f2 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -59,7 +59,7 @@ import datetime
 #	pt_example=# \q
 #
 # An example of using the database is provided by the script
-# call-graph-from-sql.py.  Refer to that script for details.
+# exported-sql-viewer.py.  Refer to that script for details.
 #
 # Tables:
 #
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
index e4bb82c8aba9..245caf2643ed 100644
--- a/tools/perf/scripts/python/export-to-sqlite.py
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -40,7 +40,7 @@ import datetime
 #	sqlite> .quit
 #
 # An example of using the database is provided by the script
-# call-graph-from-sql.py.  Refer to that script for details.
+# exported-sql-viewer.py.  Refer to that script for details.
 #
 # The database structure is practically the same as created by the script
 # export-to-postgresql.py. Refer to that script for details.  A notable
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
new file mode 100755
index 000000000000..03e7a1de7f31
--- /dev/null
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -0,0 +1,395 @@
+#!/usr/bin/python2
+# SPDX-License-Identifier: GPL-2.0
+# exported-sql-viewer.py: view data from sql database
+# Copyright (c) 2014-2018, Intel Corporation.
+
+# To use this script you will need to have exported data using either the
+# export-to-sqlite.py or the export-to-postgresql.py script.  Refer to those
+# scripts for details.
+#
+# Following on from the example in the export scripts, a
+# call-graph can be displayed for the pt_example database like this:
+#
+#	python tools/perf/scripts/python/exported-sql-viewer.py pt_example
+#
+# Note that for PostgreSQL, this script supports connecting to remote databases
+# by setting hostname, port, username, password, and dbname e.g.
+#
+#	python tools/perf/scripts/python/exported-sql-viewer.py "hostname=myhost username=myuser password=mypassword dbname=pt_example"
+#
+# The result is a GUI window with a tree representing a context-sensitive
+# call-graph.  Expanding a couple of levels of the tree and adjusting column
+# widths to suit will display something like:
+#
+#                                         Call Graph: pt_example
+# Call Path                          Object      Count   Time(ns)  Time(%)  Branch Count   Branch Count(%)
+# v- ls
+#     v- 2638:2638
+#         v- _start                  ld-2.19.so    1     10074071   100.0         211135            100.0
+#           |- unknown               unknown       1        13198     0.1              1              0.0
+#           >- _dl_start             ld-2.19.so    1      1400980    13.9          19637              9.3
+#           >- _d_linit_internal     ld-2.19.so    1       448152     4.4          11094              5.3
+#           v-__libc_start_main@plt  ls            1      8211741    81.5         180397             85.4
+#              >- _dl_fixup          ld-2.19.so    1         7607     0.1            108              0.1
+#              >- __cxa_atexit       libc-2.19.so  1        11737     0.1             10              0.0
+#              >- __libc_csu_init    ls            1        10354     0.1             10              0.0
+#              |- _setjmp            libc-2.19.so  1            0     0.0              4              0.0
+#              v- main               ls            1      8182043    99.6         180254             99.9
+#
+# Points to note:
+#	The top level is a command name (comm)
+#	The next level is a thread (pid:tid)
+#	Subsequent levels are functions
+#	'Count' is the number of calls
+#	'Time' is the elapsed time until the function returns
+#	Percentages are relative to the level above
+#	'Branch Count' is the total number of branches for that function and all
+#       functions that it calls
+
+import sys
+from PySide.QtCore import *
+from PySide.QtGui import *
+from PySide.QtSql import *
+from decimal import *
+
+# Data formatting helpers
+
+def dsoname(name):
+	if name == "[kernel.kallsyms]":
+		return "[kernel]"
+	return name
+
+# Percent to one decimal place
+
+def PercentToOneDP(n, d):
+	if not d:
+		return "0.0"
+	x = (n * Decimal(100)) / d
+	return str(x.quantize(Decimal(".1"), rounding=ROUND_HALF_UP))
+
+# Helper for queries that must not fail
+
+def QueryExec(query, stmt):
+	ret = query.exec_(stmt)
+	if not ret:
+		raise Exception("Query failed: " + query.lastError().text())
+
+# Tree data model
+
+class TreeModel(QAbstractItemModel):
+
+	def __init__(self, root, parent=None):
+		super(TreeModel, self).__init__(parent)
+		self.root = root
+		self.last_row_read = 0
+
+	def Item(self, parent):
+		if parent.isValid():
+			return parent.internalPointer()
+		else:
+			return self.root
+
+	def rowCount(self, parent):
+		result = self.Item(parent).childCount()
+		if result < 0:
+			result = 0
+			self.dataChanged.emit(parent, parent)
+		return result
+
+	def hasChildren(self, parent):
+		return self.Item(parent).hasChildren()
+
+	def headerData(self, section, orientation, role):
+		if role == Qt.TextAlignmentRole:
+			return self.columnAlignment(section)
+		if role != Qt.DisplayRole:
+			return None
+		if orientation != Qt.Horizontal:
+			return None
+		return self.columnHeader(section)
+
+	def parent(self, child):
+		child_item = child.internalPointer()
+		if child_item is self.root:
+			return QModelIndex()
+		parent_item = child_item.getParentItem()
+		return self.createIndex(parent_item.getRow(), 0, parent_item)
+
+	def index(self, row, column, parent):
+		child_item = self.Item(parent).getChildItem(row)
+		return self.createIndex(row, column, child_item)
+
+	def DisplayData(self, item, index):
+		return item.getData(index.column())
+
+	def columnAlignment(self, column):
+		return Qt.AlignLeft
+
+	def columnFont(self, column):
+		return None
+
+	def data(self, index, role):
+		if role == Qt.TextAlignmentRole:
+			return self.columnAlignment(index.column())
+		if role == Qt.FontRole:
+			return self.columnFont(index.column())
+		if role != Qt.DisplayRole:
+			return None
+		item = index.internalPointer()
+		return self.DisplayData(item, index)
+
+# Context-sensitive call graph data model item base
+
+class CallGraphLevelItemBase(object):
+
+	def __init__(self, glb, row, parent_item):
+		self.glb = glb
+		self.row = row
+		self.parent_item = parent_item
+		self.query_done = False;
+		self.child_count = 0
+		self.child_items = []
+
+	def getChildItem(self, row):
+		return self.child_items[row]
+
+	def getParentItem(self):
+		return self.parent_item
+
+	def getRow(self):
+		return self.row
+
+	def childCount(self):
+		if not self.query_done:
+			self.Select()
+			if not self.child_count:
+				return -1
+		return self.child_count
+
+	def hasChildren(self):
+		if not self.query_done:
+			return True
+		return self.child_count > 0
+
+	def getData(self, column):
+		return self.data[column]
+
+# Context-sensitive call graph data model level 2+ item base
+
+class CallGraphLevelTwoPlusItemBase(CallGraphLevelItemBase):
+
+	def __init__(self, glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item):
+		super(CallGraphLevelTwoPlusItemBase, self).__init__(glb, row, parent_item)
+		self.comm_id = comm_id
+		self.thread_id = thread_id
+		self.call_path_id = call_path_id
+		self.branch_count = branch_count
+		self.time = time
+
+	def Select(self):
+		self.query_done = True;
+		query = QSqlQuery(self.glb.db)
+		QueryExec(query, "SELECT call_path_id, name, short_name, COUNT(calls.id), SUM(return_time - call_time), SUM(branch_count)"
+					" FROM calls"
+					" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
+					" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
+					" INNER JOIN dsos ON symbols.dso_id = dsos.id"
+					" WHERE parent_call_path_id = " + str(self.call_path_id) +
+					" AND comm_id = " + str(self.comm_id) +
+					" AND thread_id = " + str(self.thread_id) +
+					" GROUP BY call_path_id, name, short_name"
+					" ORDER BY call_path_id")
+		while query.next():
+			child_item = CallGraphLevelThreeItem(self.glb, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), int(query.value(5)), self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+
+# Context-sensitive call graph data model level three item
+
+class CallGraphLevelThreeItem(CallGraphLevelTwoPlusItemBase):
+
+	def __init__(self, glb, row, comm_id, thread_id, call_path_id, name, dso, count, time, branch_count, parent_item):
+		super(CallGraphLevelThreeItem, self).__init__(glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item)
+		dso = dsoname(dso)
+		self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ]
+		self.dbid = call_path_id
+
+# Context-sensitive call graph data model level two item
+
+class CallGraphLevelTwoItem(CallGraphLevelTwoPlusItemBase):
+
+	def __init__(self, glb, row, comm_id, thread_id, pid, tid, parent_item):
+		super(CallGraphLevelTwoItem, self).__init__(glb, row, comm_id, thread_id, 1, 0, 0, parent_item)
+		self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""]
+		self.dbid = thread_id
+
+	def Select(self):
+		super(CallGraphLevelTwoItem, self).Select()
+		for child_item in self.child_items:
+			self.time += child_item.time
+			self.branch_count += child_item.branch_count
+		for child_item in self.child_items:
+			child_item.data[4] = PercentToOneDP(child_item.time, self.time)
+			child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
+
+# Context-sensitive call graph data model level one item
+
+class CallGraphLevelOneItem(CallGraphLevelItemBase):
+
+	def __init__(self, glb, row, comm_id, comm, parent_item):
+		super(CallGraphLevelOneItem, self).__init__(glb, row, parent_item)
+		self.data = [comm, "", "", "", "", "", ""]
+		self.dbid = comm_id
+
+	def Select(self):
+		self.query_done = True;
+		query = QSqlQuery(self.glb.db)
+		QueryExec(query, "SELECT thread_id, pid, tid"
+					" FROM comm_threads"
+					" INNER JOIN threads ON thread_id = threads.id"
+					" WHERE comm_id = " + str(self.dbid))
+		while query.next():
+			child_item = CallGraphLevelTwoItem(self.glb, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+
+# Context-sensitive call graph data model root item
+
+class CallGraphRootItem(CallGraphLevelItemBase):
+
+	def __init__(self, glb):
+		super(CallGraphRootItem, self).__init__(glb, 0, None)
+		self.dbid = 0
+		self.query_done = True;
+		query = QSqlQuery(glb.db)
+		QueryExec(query, "SELECT id, comm FROM comms")
+		while query.next():
+			if not query.value(0):
+				continue
+			child_item = CallGraphLevelOneItem(glb, self.child_count, query.value(0), query.value(1), self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+
+# Context-sensitive call graph data model
+
+class CallGraphModel(TreeModel):
+
+	def __init__(self, glb, parent=None):
+		super(CallGraphModel, self).__init__(CallGraphRootItem(glb), parent)
+		self.glb = glb
+
+	def columnCount(self, parent=None):
+		return 7
+
+	def columnHeader(self, column):
+		headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
+		return headers[column]
+
+	def columnAlignment(self, column):
+		alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
+		return alignment[column]
+
+# Main window
+
+class MainWindow(QMainWindow):
+
+	def __init__(self, glb, parent=None):
+		super(MainWindow, self).__init__(parent)
+
+		self.glb = glb
+
+		self.setWindowTitle("Call Graph: " + glb.dbname)
+		self.move(100, 100)
+		self.resize(800, 600)
+		self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
+		self.setMinimumSize(200, 100)
+
+		self.model = CallGraphModel(glb)
+
+		self.view = QTreeView()
+		self.view.setModel(self.model)
+
+		for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
+			self.view.setColumnWidth(c, w)
+
+		self.setCentralWidget(self.view)
+
+# Global data
+
+class Glb():
+
+	def __init__(self, dbref, db, dbname):
+		self.dbref = dbref
+		self.db = db
+		self.dbname = dbname
+		self.app = None
+		self.mainwindow = None
+
+# Database reference
+
+class DBRef():
+
+	def __init__(self, is_sqlite3, dbname):
+		self.is_sqlite3 = is_sqlite3
+		self.dbname = dbname
+
+	def Open(self, connection_name):
+		dbname = self.dbname
+		if self.is_sqlite3:
+			db = QSqlDatabase.addDatabase("QSQLITE", connection_name)
+		else:
+			db = QSqlDatabase.addDatabase("QPSQL", connection_name)
+			opts = dbname.split()
+			for opt in opts:
+				if "=" in opt:
+					opt = opt.split("=")
+					if opt[0] == "hostname":
+						db.setHostName(opt[1])
+					elif opt[0] == "port":
+						db.setPort(int(opt[1]))
+					elif opt[0] == "username":
+						db.setUserName(opt[1])
+					elif opt[0] == "password":
+						db.setPassword(opt[1])
+					elif opt[0] == "dbname":
+						dbname = opt[1]
+				else:
+					dbname = opt
+
+		db.setDatabaseName(dbname)
+		if not db.open():
+			raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text())
+		return db, dbname
+
+# Main
+
+def Main():
+	if (len(sys.argv) < 2):
+		print >> sys.stderr, "Usage is: exported-sql-viewer.py <database name>"
+		raise Exception("Too few arguments")
+
+	dbname = sys.argv[1]
+
+	is_sqlite3 = False
+	try:
+		f = open(dbname)
+		if f.read(15) == "SQLite format 3":
+			is_sqlite3 = True
+		f.close()
+	except:
+		pass
+
+	dbref = DBRef(is_sqlite3, dbname)
+	db, dbname = dbref.Open("main")
+	glb = Glb(dbref, db, dbname)
+	app = QApplication(sys.argv)
+	glb.app = app
+	mainwindow = MainWindow(glb)
+	glb.mainwindow = mainwindow
+	mainwindow.show()
+	err = app.exec_()
+	db.close()
+	sys.exit(err)
+
+if __name__ == "__main__":
+	Main()
-- 
cgit v1.2.3


From 1beb5c7b07040b70975a2ae0e90b87d412fabf06 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:47 +0300
Subject: perf scripts python: exported-sql-viewer.py: Add support for multiple
 sub-windows

Use Qt MDI (multiple document interface) to support multiple sub-windows.
Put the data model in a cache so that each sub-window can share the same
data. This allows mutiple views of the call-graph at the same time and
paves the way to add more reports.

Committer testing:

Starts with a "File  Reports  Windows" main menu, from the "Reports" I
can get what was available up to now, the "Context-Sensitivi Call Graph"
option.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-14-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 182 +++++++++++++++++++++--
 1 file changed, 173 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 03e7a1de7f31..c2f44351821e 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -47,6 +47,8 @@
 #       functions that it calls
 
 import sys
+import weakref
+import threading
 from PySide.QtCore import *
 from PySide.QtGui import *
 from PySide.QtSql import *
@@ -138,6 +140,23 @@ class TreeModel(QAbstractItemModel):
 		item = index.internalPointer()
 		return self.DisplayData(item, index)
 
+# Model cache
+
+model_cache = weakref.WeakValueDictionary()
+model_cache_lock = threading.Lock()
+
+def LookupCreateModel(model_name, create_fn):
+	model_cache_lock.acquire()
+	try:
+		model = model_cache[model_name]
+	except:
+		model = None
+	if model is None:
+		model = create_fn()
+		model_cache[model_name] = model
+	model_cache_lock.release()
+	return model
+
 # Context-sensitive call graph data model item base
 
 class CallGraphLevelItemBase(object):
@@ -289,6 +308,144 @@ class CallGraphModel(TreeModel):
 		alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
 		return alignment[column]
 
+# Context-sensitive call graph window
+
+class CallGraphWindow(QMdiSubWindow):
+
+	def __init__(self, glb, parent=None):
+		super(CallGraphWindow, self).__init__(parent)
+
+		self.model = LookupCreateModel("Context-Sensitive Call Graph", lambda x=glb: CallGraphModel(x))
+
+		self.view = QTreeView()
+		self.view.setModel(self.model)
+
+		for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
+			self.view.setColumnWidth(c, w)
+
+		self.setWidget(self.view)
+
+		AddSubWindow(glb.mainwindow.mdi_area, self, "Context-Sensitive Call Graph")
+
+# Action Definition
+
+def CreateAction(label, tip, callback, parent=None, shortcut=None):
+	action = QAction(label, parent)
+	if shortcut != None:
+		action.setShortcuts(shortcut)
+	action.setStatusTip(tip)
+	action.triggered.connect(callback)
+	return action
+
+# Typical application actions
+
+def CreateExitAction(app, parent=None):
+	return CreateAction("&Quit", "Exit the application", app.closeAllWindows, parent, QKeySequence.Quit)
+
+# Typical MDI actions
+
+def CreateCloseActiveWindowAction(mdi_area):
+	return CreateAction("Cl&ose", "Close the active window", mdi_area.closeActiveSubWindow, mdi_area)
+
+def CreateCloseAllWindowsAction(mdi_area):
+	return CreateAction("Close &All", "Close all the windows", mdi_area.closeAllSubWindows, mdi_area)
+
+def CreateTileWindowsAction(mdi_area):
+	return CreateAction("&Tile", "Tile the windows", mdi_area.tileSubWindows, mdi_area)
+
+def CreateCascadeWindowsAction(mdi_area):
+	return CreateAction("&Cascade", "Cascade the windows", mdi_area.cascadeSubWindows, mdi_area)
+
+def CreateNextWindowAction(mdi_area):
+	return CreateAction("Ne&xt", "Move the focus to the next window", mdi_area.activateNextSubWindow, mdi_area, QKeySequence.NextChild)
+
+def CreatePreviousWindowAction(mdi_area):
+	return CreateAction("Pre&vious", "Move the focus to the previous window", mdi_area.activatePreviousSubWindow, mdi_area, QKeySequence.PreviousChild)
+
+# Typical MDI window menu
+
+class WindowMenu():
+
+	def __init__(self, mdi_area, menu):
+		self.mdi_area = mdi_area
+		self.window_menu = menu.addMenu("&Windows")
+		self.close_active_window = CreateCloseActiveWindowAction(mdi_area)
+		self.close_all_windows = CreateCloseAllWindowsAction(mdi_area)
+		self.tile_windows = CreateTileWindowsAction(mdi_area)
+		self.cascade_windows = CreateCascadeWindowsAction(mdi_area)
+		self.next_window = CreateNextWindowAction(mdi_area)
+		self.previous_window = CreatePreviousWindowAction(mdi_area)
+		self.window_menu.aboutToShow.connect(self.Update)
+
+	def Update(self):
+		self.window_menu.clear()
+		sub_window_count = len(self.mdi_area.subWindowList())
+		have_sub_windows = sub_window_count != 0
+		self.close_active_window.setEnabled(have_sub_windows)
+		self.close_all_windows.setEnabled(have_sub_windows)
+		self.tile_windows.setEnabled(have_sub_windows)
+		self.cascade_windows.setEnabled(have_sub_windows)
+		self.next_window.setEnabled(have_sub_windows)
+		self.previous_window.setEnabled(have_sub_windows)
+		self.window_menu.addAction(self.close_active_window)
+		self.window_menu.addAction(self.close_all_windows)
+		self.window_menu.addSeparator()
+		self.window_menu.addAction(self.tile_windows)
+		self.window_menu.addAction(self.cascade_windows)
+		self.window_menu.addSeparator()
+		self.window_menu.addAction(self.next_window)
+		self.window_menu.addAction(self.previous_window)
+		if sub_window_count == 0:
+			return
+		self.window_menu.addSeparator()
+		nr = 1
+		for sub_window in self.mdi_area.subWindowList():
+			label = str(nr) + " " + sub_window.name
+			if nr < 10:
+				label = "&" + label
+			action = self.window_menu.addAction(label)
+			action.setCheckable(True)
+			action.setChecked(sub_window == self.mdi_area.activeSubWindow())
+			action.triggered.connect(lambda x=nr: self.setActiveSubWindow(x))
+			self.window_menu.addAction(action)
+			nr += 1
+
+	def setActiveSubWindow(self, nr):
+		self.mdi_area.setActiveSubWindow(self.mdi_area.subWindowList()[nr - 1])
+
+# Unique name for sub-windows
+
+def NumberedWindowName(name, nr):
+	if nr > 1:
+		name += " <" + str(nr) + ">"
+	return name
+
+def UniqueSubWindowName(mdi_area, name):
+	nr = 1
+	while True:
+		unique_name = NumberedWindowName(name, nr)
+		ok = True
+		for sub_window in mdi_area.subWindowList():
+			if sub_window.name == unique_name:
+				ok = False
+				break
+		if ok:
+			return unique_name
+		nr += 1
+
+# Add a sub-window
+
+def AddSubWindow(mdi_area, sub_window, name):
+	unique_name = UniqueSubWindowName(mdi_area, name)
+	sub_window.setMinimumSize(200, 100)
+	sub_window.resize(800, 600)
+	sub_window.setWindowTitle(unique_name)
+	sub_window.setAttribute(Qt.WA_DeleteOnClose)
+	sub_window.setWindowIcon(sub_window.style().standardIcon(QStyle.SP_FileIcon))
+	sub_window.name = unique_name
+	mdi_area.addSubWindow(sub_window)
+	sub_window.show()
+
 # Main window
 
 class MainWindow(QMainWindow):
@@ -298,21 +455,28 @@ class MainWindow(QMainWindow):
 
 		self.glb = glb
 
-		self.setWindowTitle("Call Graph: " + glb.dbname)
-		self.move(100, 100)
-		self.resize(800, 600)
+		self.setWindowTitle("Exported SQL Viewer: " + glb.dbname)
 		self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
 		self.setMinimumSize(200, 100)
 
-		self.model = CallGraphModel(glb)
+		self.mdi_area = QMdiArea()
+		self.mdi_area.setHorizontalScrollBarPolicy(Qt.ScrollBarAsNeeded)
+		self.mdi_area.setVerticalScrollBarPolicy(Qt.ScrollBarAsNeeded)
 
-		self.view = QTreeView()
-		self.view.setModel(self.model)
+		self.setCentralWidget(self.mdi_area)
 
-		for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
-			self.view.setColumnWidth(c, w)
+		menu = self.menuBar()
+
+		file_menu = menu.addMenu("&File")
+		file_menu.addAction(CreateExitAction(glb.app, self))
+
+		reports_menu = menu.addMenu("&Reports")
+		reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self))
+
+		self.window_menu = WindowMenu(self.mdi_area, menu)
 
-		self.setCentralWidget(self.view)
+	def NewCallGraph(self):
+		CallGraphWindow(self.glb, self)
 
 # Global data
 
-- 
cgit v1.2.3


From ebd70c7dc2f5f57315e19d959ddc9cb05e9d48e1 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:48 +0300
Subject: perf scripts python: exported-sql-viewer.py: Add ability to find
 symbols in the call-graph

Add a Find bar that appears at the bottom of the call-graph window.

Committer testing:

Using:

  python tools/perf/scripts/python/exported-sql-viewer.py pt_example branches calls

Using the database built in the first "Committer Testing" section in
this patch series I was able to:

  "Reports"
      "Context-Sensitive Call Graphs"
           Control+F or select "Edit" in the top menu then "Find"
                __poll<ENTER>

and find the first place where the "__poll" function appears, then
press the down arrow in the lower right corner and go to the next, etc.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-15-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 306 ++++++++++++++++++++++-
 1 file changed, 305 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index c2f44351821e..0386a600ffc7 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -49,6 +49,7 @@
 import sys
 import weakref
 import threading
+import string
 from PySide.QtCore import *
 from PySide.QtGui import *
 from PySide.QtSql import *
@@ -76,6 +77,27 @@ def QueryExec(query, stmt):
 	if not ret:
 		raise Exception("Query failed: " + query.lastError().text())
 
+# Background thread
+
+class Thread(QThread):
+
+	done = Signal(object)
+
+	def __init__(self, task, param=None, parent=None):
+		super(Thread, self).__init__(parent)
+		self.task = task
+		self.param = param
+
+	def run(self):
+		while True:
+			if self.param is None:
+				done, result = self.task()
+			else:
+				done, result = self.task(self.param)
+			self.done.emit(result)
+			if done:
+				break
+
 # Tree data model
 
 class TreeModel(QAbstractItemModel):
@@ -157,6 +179,125 @@ def LookupCreateModel(model_name, create_fn):
 	model_cache_lock.release()
 	return model
 
+# Find bar
+
+class FindBar():
+
+	def __init__(self, parent, finder, is_reg_expr=False):
+		self.finder = finder
+		self.context = []
+		self.last_value = None
+		self.last_pattern = None
+
+		label = QLabel("Find:")
+		label.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.textbox = QComboBox()
+		self.textbox.setEditable(True)
+		self.textbox.currentIndexChanged.connect(self.ValueChanged)
+
+		self.progress = QProgressBar()
+		self.progress.setRange(0, 0)
+		self.progress.hide()
+
+		if is_reg_expr:
+			self.pattern = QCheckBox("Regular Expression")
+		else:
+			self.pattern = QCheckBox("Pattern")
+		self.pattern.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.next_button = QToolButton()
+		self.next_button.setIcon(parent.style().standardIcon(QStyle.SP_ArrowDown))
+		self.next_button.released.connect(lambda: self.NextPrev(1))
+
+		self.prev_button = QToolButton()
+		self.prev_button.setIcon(parent.style().standardIcon(QStyle.SP_ArrowUp))
+		self.prev_button.released.connect(lambda: self.NextPrev(-1))
+
+		self.close_button = QToolButton()
+		self.close_button.setIcon(parent.style().standardIcon(QStyle.SP_DockWidgetCloseButton))
+		self.close_button.released.connect(self.Deactivate)
+
+		self.hbox = QHBoxLayout()
+		self.hbox.setContentsMargins(0, 0, 0, 0)
+
+		self.hbox.addWidget(label)
+		self.hbox.addWidget(self.textbox)
+		self.hbox.addWidget(self.progress)
+		self.hbox.addWidget(self.pattern)
+		self.hbox.addWidget(self.next_button)
+		self.hbox.addWidget(self.prev_button)
+		self.hbox.addWidget(self.close_button)
+
+		self.bar = QWidget()
+		self.bar.setLayout(self.hbox);
+		self.bar.hide()
+
+	def Widget(self):
+		return self.bar
+
+	def Activate(self):
+		self.bar.show()
+		self.textbox.setFocus()
+
+	def Deactivate(self):
+		self.bar.hide()
+
+	def Busy(self):
+		self.textbox.setEnabled(False)
+		self.pattern.hide()
+		self.next_button.hide()
+		self.prev_button.hide()
+		self.progress.show()
+
+	def Idle(self):
+		self.textbox.setEnabled(True)
+		self.progress.hide()
+		self.pattern.show()
+		self.next_button.show()
+		self.prev_button.show()
+
+	def Find(self, direction):
+		value = self.textbox.currentText()
+		pattern = self.pattern.isChecked()
+		self.last_value = value
+		self.last_pattern = pattern
+		self.finder.Find(value, direction, pattern, self.context)
+
+	def ValueChanged(self):
+		value = self.textbox.currentText()
+		pattern = self.pattern.isChecked()
+		index = self.textbox.currentIndex()
+		data = self.textbox.itemData(index)
+		# Store the pattern in the combo box to keep it with the text value
+		if data == None:
+			self.textbox.setItemData(index, pattern)
+		else:
+			self.pattern.setChecked(data)
+		self.Find(0)
+
+	def NextPrev(self, direction):
+		value = self.textbox.currentText()
+		pattern = self.pattern.isChecked()
+		if value != self.last_value:
+			index = self.textbox.findText(value)
+			# Allow for a button press before the value has been added to the combo box
+			if index < 0:
+				index = self.textbox.count()
+				self.textbox.addItem(value, pattern)
+				self.textbox.setCurrentIndex(index)
+				return
+			else:
+				self.textbox.setItemData(index, pattern)
+		elif pattern != self.last_pattern:
+			# Keep the pattern recorded in the combo box up to date
+			index = self.textbox.currentIndex()
+			self.textbox.setItemData(index, pattern)
+		self.Find(direction)
+
+	def NotFound(self):
+		QMessageBox.information(self.bar, "Find", "'" + self.textbox.currentText() + "' not found")
+
 # Context-sensitive call graph data model item base
 
 class CallGraphLevelItemBase(object):
@@ -308,6 +449,123 @@ class CallGraphModel(TreeModel):
 		alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
 		return alignment[column]
 
+	def FindSelect(self, value, pattern, query):
+		if pattern:
+			# postgresql and sqlite pattern patching differences:
+			#   postgresql LIKE is case sensitive but sqlite LIKE is not
+			#   postgresql LIKE allows % and _ to be escaped with \ but sqlite LIKE does not
+			#   postgresql supports ILIKE which is case insensitive
+			#   sqlite supports GLOB (text only) which uses * and ? and is case sensitive
+			if not self.glb.dbref.is_sqlite3:
+				# Escape % and _
+				s = value.replace("%", "\%")
+				s = s.replace("_", "\_")
+				# Translate * and ? into SQL LIKE pattern characters % and _
+				trans = string.maketrans("*?", "%_")
+				match = " LIKE '" + str(s).translate(trans) + "'"
+			else:
+				match = " GLOB '" + str(value) + "'"
+		else:
+			match = " = '" + str(value) + "'"
+		QueryExec(query, "SELECT call_path_id, comm_id, thread_id"
+						" FROM calls"
+						" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
+						" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
+						" WHERE symbols.name" + match +
+						" GROUP BY comm_id, thread_id, call_path_id"
+						" ORDER BY comm_id, thread_id, call_path_id")
+
+	def FindPath(self, query):
+		# Turn the query result into a list of ids that the tree view can walk
+		# to open the tree at the right place.
+		ids = []
+		parent_id = query.value(0)
+		while parent_id:
+			ids.insert(0, parent_id)
+			q2 = QSqlQuery(self.glb.db)
+			QueryExec(q2, "SELECT parent_id"
+					" FROM call_paths"
+					" WHERE id = " + str(parent_id))
+			if not q2.next():
+				break
+			parent_id = q2.value(0)
+		# The call path root is not used
+		if ids[0] == 1:
+			del ids[0]
+		ids.insert(0, query.value(2))
+		ids.insert(0, query.value(1))
+		return ids
+
+	def Found(self, query, found):
+		if found:
+			return self.FindPath(query)
+		return []
+
+	def FindValue(self, value, pattern, query, last_value, last_pattern):
+		if last_value == value and pattern == last_pattern:
+			found = query.first()
+		else:
+			self.FindSelect(value, pattern, query)
+			found = query.next()
+		return self.Found(query, found)
+
+	def FindNext(self, query):
+		found = query.next()
+		if not found:
+			found = query.first()
+		return self.Found(query, found)
+
+	def FindPrev(self, query):
+		found = query.previous()
+		if not found:
+			found = query.last()
+		return self.Found(query, found)
+
+	def FindThread(self, c):
+		if c.direction == 0 or c.value != c.last_value or c.pattern != c.last_pattern:
+			ids = self.FindValue(c.value, c.pattern, c.query, c.last_value, c.last_pattern)
+		elif c.direction > 0:
+			ids = self.FindNext(c.query)
+		else:
+			ids = self.FindPrev(c.query)
+		return (True, ids)
+
+	def Find(self, value, direction, pattern, context, callback):
+		class Context():
+			def __init__(self, *x):
+				self.value, self.direction, self.pattern, self.query, self.last_value, self.last_pattern = x
+			def Update(self, *x):
+				self.value, self.direction, self.pattern, self.last_value, self.last_pattern = x + (self.value, self.pattern)
+		if len(context):
+			context[0].Update(value, direction, pattern)
+		else:
+			context.append(Context(value, direction, pattern, QSqlQuery(self.glb.db), None, None))
+		# Use a thread so the UI is not blocked during the SELECT
+		thread = Thread(self.FindThread, context[0])
+		thread.done.connect(lambda ids, t=thread, c=callback: self.FindDone(t, c, ids), Qt.QueuedConnection)
+		thread.start()
+
+	def FindDone(self, thread, callback, ids):
+		callback(ids)
+
+# Vertical widget layout
+
+class VBox():
+
+	def __init__(self, w1, w2, w3=None):
+		self.vbox = QWidget()
+		self.vbox.setLayout(QVBoxLayout());
+
+		self.vbox.layout().setContentsMargins(0, 0, 0, 0)
+
+		self.vbox.layout().addWidget(w1)
+		self.vbox.layout().addWidget(w2)
+		if w3:
+			self.vbox.layout().addWidget(w3)
+
+	def Widget(self):
+		return self.vbox
+
 # Context-sensitive call graph window
 
 class CallGraphWindow(QMdiSubWindow):
@@ -323,10 +581,45 @@ class CallGraphWindow(QMdiSubWindow):
 		for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
 			self.view.setColumnWidth(c, w)
 
-		self.setWidget(self.view)
+		self.find_bar = FindBar(self, self)
+
+		self.vbox = VBox(self.view, self.find_bar.Widget())
+
+		self.setWidget(self.vbox.Widget())
 
 		AddSubWindow(glb.mainwindow.mdi_area, self, "Context-Sensitive Call Graph")
 
+	def DisplayFound(self, ids):
+		if not len(ids):
+			return False
+		parent = QModelIndex()
+		for dbid in ids:
+			found = False
+			n = self.model.rowCount(parent)
+			for row in xrange(n):
+				child = self.model.index(row, 0, parent)
+				if child.internalPointer().dbid == dbid:
+					found = True
+					self.view.setCurrentIndex(child)
+					parent = child
+					break
+			if not found:
+				break
+		return found
+
+	def Find(self, value, direction, pattern, context):
+		self.view.setFocus()
+		self.find_bar.Busy()
+		self.model.Find(value, direction, pattern, context, self.FindDone)
+
+	def FindDone(self, ids):
+		found = True
+		if not self.DisplayFound(ids):
+			found = False
+		self.find_bar.Idle()
+		if not found:
+			self.find_bar.NotFound()
+
 # Action Definition
 
 def CreateAction(label, tip, callback, parent=None, shortcut=None):
@@ -470,11 +763,22 @@ class MainWindow(QMainWindow):
 		file_menu = menu.addMenu("&File")
 		file_menu.addAction(CreateExitAction(glb.app, self))
 
+		edit_menu = menu.addMenu("&Edit")
+		edit_menu.addAction(CreateAction("&Find...", "Find items", self.Find, self, QKeySequence.Find))
+
 		reports_menu = menu.addMenu("&Reports")
 		reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self))
 
 		self.window_menu = WindowMenu(self.mdi_area, menu)
 
+	def Find(self):
+		win = self.mdi_area.activeSubWindow()
+		if win:
+			try:
+				win.find_bar.Activate()
+			except:
+				pass
+
 	def NewCallGraph(self):
 		CallGraphWindow(self.glb, self)
 
-- 
cgit v1.2.3


From 82f68e2898e634b8b0efc7ddd57e037ef75ea114 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:49 +0300
Subject: perf scripts python: exported-sql-viewer.py: Add ability to shrink /
 enlarge font

Shrinking the font allows more information to display.

Committer testing:

Works, tested with the convenient Control+Shift+'+' and Control+'-' as
well with the more cumbersome top menu "Edit" + "Enlarge/Shrink font"
options.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-16-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 0386a600ffc7..310ba7147583 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -706,6 +706,20 @@ class WindowMenu():
 	def setActiveSubWindow(self, nr):
 		self.mdi_area.setActiveSubWindow(self.mdi_area.subWindowList()[nr - 1])
 
+# Font resize
+
+def ResizeFont(widget, diff):
+	font = widget.font()
+	sz = font.pointSize()
+	font.setPointSize(sz + diff)
+	widget.setFont(font)
+
+def ShrinkFont(widget):
+	ResizeFont(widget, -1)
+
+def EnlargeFont(widget):
+	ResizeFont(widget, 1)
+
 # Unique name for sub-windows
 
 def NumberedWindowName(name, nr):
@@ -765,6 +779,8 @@ class MainWindow(QMainWindow):
 
 		edit_menu = menu.addMenu("&Edit")
 		edit_menu.addAction(CreateAction("&Find...", "Find items", self.Find, self, QKeySequence.Find))
+		edit_menu.addAction(CreateAction("&Shrink Font", "Make text smaller", self.ShrinkFont, self, [QKeySequence("Ctrl+-")]))
+		edit_menu.addAction(CreateAction("&Enlarge Font", "Make text bigger", self.EnlargeFont, self, [QKeySequence("Ctrl++")]))
 
 		reports_menu = menu.addMenu("&Reports")
 		reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self))
@@ -779,6 +795,14 @@ class MainWindow(QMainWindow):
 			except:
 				pass
 
+	def ShrinkFont(self):
+		win = self.mdi_area.activeSubWindow()
+		ShrinkFont(win.view)
+
+	def EnlargeFont(self):
+		win = self.mdi_area.activeSubWindow()
+		EnlargeFont(win.view)
+
 	def NewCallGraph(self):
 		CallGraphWindow(self.glb, self)
 
-- 
cgit v1.2.3


From 8392b74b575c38fa5d50d1fe07fa9a4bcea93862 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:50 +0300
Subject: perf scripts python: exported-sql-viewer.py: Add ability to display
 all the database tables

Displaying all the database tables can help make the database easier to
understand.

Committer testing:

Opened all the tables, even the sqlite master table, which I selected
everything and used control+C, lets see if it works...

  CREATE VIEW threads_view AS SELECT id,machine_id,(SELECT host_or_guest FROM machines_view WHERE id = machine_id) AS host_or_guest,process_id,pid,tid FROM threads

Humm, nope, just one of the cells got copied, even with everything selected :-)

Anyway, works as advertised, useful for perusing the data.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-17-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 694 +++++++++++++++++++++++
 1 file changed, 694 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 310ba7147583..ef822d850109 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -50,10 +50,15 @@ import sys
 import weakref
 import threading
 import string
+import cPickle
+import re
+import os
 from PySide.QtCore import *
 from PySide.QtGui import *
 from PySide.QtSql import *
 from decimal import *
+from ctypes import *
+from multiprocessing import Process, Array, Value, Event
 
 # Data formatting helpers
 
@@ -146,6 +151,68 @@ class TreeModel(QAbstractItemModel):
 	def DisplayData(self, item, index):
 		return item.getData(index.column())
 
+	def FetchIfNeeded(self, row):
+		if row > self.last_row_read:
+			self.last_row_read = row
+			if row + 10 >= self.root.child_count:
+				self.fetcher.Fetch(glb_chunk_sz)
+
+	def columnAlignment(self, column):
+		return Qt.AlignLeft
+
+	def columnFont(self, column):
+		return None
+
+	def data(self, index, role):
+		if role == Qt.TextAlignmentRole:
+			return self.columnAlignment(index.column())
+		if role == Qt.FontRole:
+			return self.columnFont(index.column())
+		if role != Qt.DisplayRole:
+			return None
+		item = index.internalPointer()
+		return self.DisplayData(item, index)
+
+# Table data model
+
+class TableModel(QAbstractTableModel):
+
+	def __init__(self, parent=None):
+		super(TableModel, self).__init__(parent)
+		self.child_count = 0
+		self.child_items = []
+		self.last_row_read = 0
+
+	def Item(self, parent):
+		if parent.isValid():
+			return parent.internalPointer()
+		else:
+			return self
+
+	def rowCount(self, parent):
+		return self.child_count
+
+	def headerData(self, section, orientation, role):
+		if role == Qt.TextAlignmentRole:
+			return self.columnAlignment(section)
+		if role != Qt.DisplayRole:
+			return None
+		if orientation != Qt.Horizontal:
+			return None
+		return self.columnHeader(section)
+
+	def index(self, row, column, parent):
+		return self.createIndex(row, column, self.child_items[row])
+
+	def DisplayData(self, item, index):
+		return item.getData(index.column())
+
+	def FetchIfNeeded(self, row):
+		if row > self.last_row_read:
+			self.last_row_read = row
+			if row + 10 >= self.child_count:
+				self.fetcher.Fetch(glb_chunk_sz)
+
 	def columnAlignment(self, column):
 		return Qt.AlignLeft
 
@@ -620,6 +687,601 @@ class CallGraphWindow(QMdiSubWindow):
 		if not found:
 			self.find_bar.NotFound()
 
+# Child data item  finder
+
+class ChildDataItemFinder():
+
+	def __init__(self, root):
+		self.root = root
+		self.value, self.direction, self.pattern, self.last_value, self.last_pattern = (None,) * 5
+		self.rows = []
+		self.pos = 0
+
+	def FindSelect(self):
+		self.rows = []
+		if self.pattern:
+			pattern = re.compile(self.value)
+			for child in self.root.child_items:
+				for column_data in child.data:
+					if re.search(pattern, str(column_data)) is not None:
+						self.rows.append(child.row)
+						break
+		else:
+			for child in self.root.child_items:
+				for column_data in child.data:
+					if self.value in str(column_data):
+						self.rows.append(child.row)
+						break
+
+	def FindValue(self):
+		self.pos = 0
+		if self.last_value != self.value or self.pattern != self.last_pattern:
+			self.FindSelect()
+		if not len(self.rows):
+			return -1
+		return self.rows[self.pos]
+
+	def FindThread(self):
+		if self.direction == 0 or self.value != self.last_value or self.pattern != self.last_pattern:
+			row = self.FindValue()
+		elif len(self.rows):
+			if self.direction > 0:
+				self.pos += 1
+				if self.pos >= len(self.rows):
+					self.pos = 0
+			else:
+				self.pos -= 1
+				if self.pos < 0:
+					self.pos = len(self.rows) - 1
+			row = self.rows[self.pos]
+		else:
+			row = -1
+		return (True, row)
+
+	def Find(self, value, direction, pattern, context, callback):
+		self.value, self.direction, self.pattern, self.last_value, self.last_pattern = (value, direction,pattern, self.value, self.pattern)
+		# Use a thread so the UI is not blocked
+		thread = Thread(self.FindThread)
+		thread.done.connect(lambda row, t=thread, c=callback: self.FindDone(t, c, row), Qt.QueuedConnection)
+		thread.start()
+
+	def FindDone(self, thread, callback, row):
+		callback(row)
+
+# Number of database records to fetch in one go
+
+glb_chunk_sz = 10000
+
+# size of pickled integer big enough for record size
+
+glb_nsz = 8
+
+# Background process for SQL data fetcher
+
+class SQLFetcherProcess():
+
+	def __init__(self, dbref, sql, buffer, head, tail, fetch_count, fetching_done, process_target, wait_event, fetched_event, prep):
+		# Need a unique connection name
+		conn_name = "SQLFetcher" + str(os.getpid())
+		self.db, dbname = dbref.Open(conn_name)
+		self.sql = sql
+		self.buffer = buffer
+		self.head = head
+		self.tail = tail
+		self.fetch_count = fetch_count
+		self.fetching_done = fetching_done
+		self.process_target = process_target
+		self.wait_event = wait_event
+		self.fetched_event = fetched_event
+		self.prep = prep
+		self.query = QSqlQuery(self.db)
+		self.query_limit = 0 if "$$last_id$$" in sql else 2
+		self.last_id = -1
+		self.fetched = 0
+		self.more = True
+		self.local_head = self.head.value
+		self.local_tail = self.tail.value
+
+	def Select(self):
+		if self.query_limit:
+			if self.query_limit == 1:
+				return
+			self.query_limit -= 1
+		stmt = self.sql.replace("$$last_id$$", str(self.last_id))
+		QueryExec(self.query, stmt)
+
+	def Next(self):
+		if not self.query.next():
+			self.Select()
+			if not self.query.next():
+				return None
+		self.last_id = self.query.value(0)
+		return self.prep(self.query)
+
+	def WaitForTarget(self):
+		while True:
+			self.wait_event.clear()
+			target = self.process_target.value
+			if target > self.fetched or target < 0:
+				break
+			self.wait_event.wait()
+		return target
+
+	def HasSpace(self, sz):
+		if self.local_tail <= self.local_head:
+			space = len(self.buffer) - self.local_head
+			if space > sz:
+				return True
+			if space >= glb_nsz:
+				# Use 0 (or space < glb_nsz) to mean there is no more at the top of the buffer
+				nd = cPickle.dumps(0, cPickle.HIGHEST_PROTOCOL)
+				self.buffer[self.local_head : self.local_head + len(nd)] = nd
+			self.local_head = 0
+		if self.local_tail - self.local_head > sz:
+			return True
+		return False
+
+	def WaitForSpace(self, sz):
+		if self.HasSpace(sz):
+			return
+		while True:
+			self.wait_event.clear()
+			self.local_tail = self.tail.value
+			if self.HasSpace(sz):
+				return
+			self.wait_event.wait()
+
+	def AddToBuffer(self, obj):
+		d = cPickle.dumps(obj, cPickle.HIGHEST_PROTOCOL)
+		n = len(d)
+		nd = cPickle.dumps(n, cPickle.HIGHEST_PROTOCOL)
+		sz = n + glb_nsz
+		self.WaitForSpace(sz)
+		pos = self.local_head
+		self.buffer[pos : pos + len(nd)] = nd
+		self.buffer[pos + glb_nsz : pos + sz] = d
+		self.local_head += sz
+
+	def FetchBatch(self, batch_size):
+		fetched = 0
+		while batch_size > fetched:
+			obj = self.Next()
+			if obj is None:
+				self.more = False
+				break
+			self.AddToBuffer(obj)
+			fetched += 1
+		if fetched:
+			self.fetched += fetched
+			with self.fetch_count.get_lock():
+				self.fetch_count.value += fetched
+			self.head.value = self.local_head
+			self.fetched_event.set()
+
+	def Run(self):
+		while self.more:
+			target = self.WaitForTarget()
+			if target < 0:
+				break
+			batch_size = min(glb_chunk_sz, target - self.fetched)
+			self.FetchBatch(batch_size)
+		self.fetching_done.value = True
+		self.fetched_event.set()
+
+def SQLFetcherFn(*x):
+	process = SQLFetcherProcess(*x)
+	process.Run()
+
+# SQL data fetcher
+
+class SQLFetcher(QObject):
+
+	done = Signal(object)
+
+	def __init__(self, glb, sql, prep, process_data, parent=None):
+		super(SQLFetcher, self).__init__(parent)
+		self.process_data = process_data
+		self.more = True
+		self.target = 0
+		self.last_target = 0
+		self.fetched = 0
+		self.buffer_size = 16 * 1024 * 1024
+		self.buffer = Array(c_char, self.buffer_size, lock=False)
+		self.head = Value(c_longlong)
+		self.tail = Value(c_longlong)
+		self.local_tail = 0
+		self.fetch_count = Value(c_longlong)
+		self.fetching_done = Value(c_bool)
+		self.last_count = 0
+		self.process_target = Value(c_longlong)
+		self.wait_event = Event()
+		self.fetched_event = Event()
+		glb.AddInstanceToShutdownOnExit(self)
+		self.process = Process(target=SQLFetcherFn, args=(glb.dbref, sql, self.buffer, self.head, self.tail, self.fetch_count, self.fetching_done, self.process_target, self.wait_event, self.fetched_event, prep))
+		self.process.start()
+		self.thread = Thread(self.Thread)
+		self.thread.done.connect(self.ProcessData, Qt.QueuedConnection)
+		self.thread.start()
+
+	def Shutdown(self):
+		# Tell the thread and process to exit
+		self.process_target.value = -1
+		self.wait_event.set()
+		self.more = False
+		self.fetching_done.value = True
+		self.fetched_event.set()
+
+	def Thread(self):
+		if not self.more:
+			return True, 0
+		while True:
+			self.fetched_event.clear()
+			fetch_count = self.fetch_count.value
+			if fetch_count != self.last_count:
+				break
+			if self.fetching_done.value:
+				self.more = False
+				return True, 0
+			self.fetched_event.wait()
+		count = fetch_count - self.last_count
+		self.last_count = fetch_count
+		self.fetched += count
+		return False, count
+
+	def Fetch(self, nr):
+		if not self.more:
+			# -1 inidcates there are no more
+			return -1
+		result = self.fetched
+		extra = result + nr - self.target
+		if extra > 0:
+			self.target += extra
+			# process_target < 0 indicates shutting down
+			if self.process_target.value >= 0:
+				self.process_target.value = self.target
+			self.wait_event.set()
+		return result
+
+	def RemoveFromBuffer(self):
+		pos = self.local_tail
+		if len(self.buffer) - pos < glb_nsz:
+			pos = 0
+		n = cPickle.loads(self.buffer[pos : pos + glb_nsz])
+		if n == 0:
+			pos = 0
+			n = cPickle.loads(self.buffer[0 : glb_nsz])
+		pos += glb_nsz
+		obj = cPickle.loads(self.buffer[pos : pos + n])
+		self.local_tail = pos + n
+		return obj
+
+	def ProcessData(self, count):
+		for i in xrange(count):
+			obj = self.RemoveFromBuffer()
+			self.process_data(obj)
+		self.tail.value = self.local_tail
+		self.wait_event.set()
+		self.done.emit(count)
+
+# Fetch more records bar
+
+class FetchMoreRecordsBar():
+
+	def __init__(self, model, parent):
+		self.model = model
+
+		self.label = QLabel("Number of records (x " + "{:,}".format(glb_chunk_sz) + ") to fetch:")
+		self.label.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.fetch_count = QSpinBox()
+		self.fetch_count.setRange(1, 1000000)
+		self.fetch_count.setValue(10)
+		self.fetch_count.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.fetch = QPushButton("Go!")
+		self.fetch.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+		self.fetch.released.connect(self.FetchMoreRecords)
+
+		self.progress = QProgressBar()
+		self.progress.setRange(0, 100)
+		self.progress.hide()
+
+		self.done_label = QLabel("All records fetched")
+		self.done_label.hide()
+
+		self.spacer = QLabel("")
+
+		self.close_button = QToolButton()
+		self.close_button.setIcon(parent.style().standardIcon(QStyle.SP_DockWidgetCloseButton))
+		self.close_button.released.connect(self.Deactivate)
+
+		self.hbox = QHBoxLayout()
+		self.hbox.setContentsMargins(0, 0, 0, 0)
+
+		self.hbox.addWidget(self.label)
+		self.hbox.addWidget(self.fetch_count)
+		self.hbox.addWidget(self.fetch)
+		self.hbox.addWidget(self.spacer)
+		self.hbox.addWidget(self.progress)
+		self.hbox.addWidget(self.done_label)
+		self.hbox.addWidget(self.close_button)
+
+		self.bar = QWidget()
+		self.bar.setLayout(self.hbox);
+		self.bar.show()
+
+		self.in_progress = False
+		self.model.progress.connect(self.Progress)
+
+		self.done = False
+
+		if not model.HasMoreRecords():
+			self.Done()
+
+	def Widget(self):
+		return self.bar
+
+	def Activate(self):
+		self.bar.show()
+		self.fetch.setFocus()
+
+	def Deactivate(self):
+		self.bar.hide()
+
+	def Enable(self, enable):
+		self.fetch.setEnabled(enable)
+		self.fetch_count.setEnabled(enable)
+
+	def Busy(self):
+		self.Enable(False)
+		self.fetch.hide()
+		self.spacer.hide()
+		self.progress.show()
+
+	def Idle(self):
+		self.in_progress = False
+		self.Enable(True)
+		self.progress.hide()
+		self.fetch.show()
+		self.spacer.show()
+
+	def Target(self):
+		return self.fetch_count.value() * glb_chunk_sz
+
+	def Done(self):
+		self.done = True
+		self.Idle()
+		self.label.hide()
+		self.fetch_count.hide()
+		self.fetch.hide()
+		self.spacer.hide()
+		self.done_label.show()
+
+	def Progress(self, count):
+		if self.in_progress:
+			if count:
+				percent = ((count - self.start) * 100) / self.Target()
+				if percent >= 100:
+					self.Idle()
+				else:
+					self.progress.setValue(percent)
+		if not count:
+			# Count value of zero means no more records
+			self.Done()
+
+	def FetchMoreRecords(self):
+		if self.done:
+			return
+		self.progress.setValue(0)
+		self.Busy()
+		self.in_progress = True
+		self.start = self.model.FetchMoreRecords(self.Target())
+
+# SQL data preparation
+
+def SQLTableDataPrep(query, count):
+	data = []
+	for i in xrange(count):
+		data.append(query.value(i))
+	return data
+
+# SQL table data model item
+
+class SQLTableItem():
+
+	def __init__(self, row, data):
+		self.row = row
+		self.data = data
+
+	def getData(self, column):
+		return self.data[column]
+
+# SQL table data model
+
+class SQLTableModel(TableModel):
+
+	progress = Signal(object)
+
+	def __init__(self, glb, sql, column_count, parent=None):
+		super(SQLTableModel, self).__init__(parent)
+		self.glb = glb
+		self.more = True
+		self.populated = 0
+		self.fetcher = SQLFetcher(glb, sql, lambda x, y=column_count: SQLTableDataPrep(x, y), self.AddSample)
+		self.fetcher.done.connect(self.Update)
+		self.fetcher.Fetch(glb_chunk_sz)
+
+	def DisplayData(self, item, index):
+		self.FetchIfNeeded(item.row)
+		return item.getData(index.column())
+
+	def AddSample(self, data):
+		child = SQLTableItem(self.populated, data)
+		self.child_items.append(child)
+		self.populated += 1
+
+	def Update(self, fetched):
+		if not fetched:
+			self.more = False
+			self.progress.emit(0)
+		child_count = self.child_count
+		count = self.populated - child_count
+		if count > 0:
+			parent = QModelIndex()
+			self.beginInsertRows(parent, child_count, child_count + count - 1)
+			self.insertRows(child_count, count, parent)
+			self.child_count += count
+			self.endInsertRows()
+			self.progress.emit(self.child_count)
+
+	def FetchMoreRecords(self, count):
+		current = self.child_count
+		if self.more:
+			self.fetcher.Fetch(count)
+		else:
+			self.progress.emit(0)
+		return current
+
+	def HasMoreRecords(self):
+		return self.more
+
+# SQL automatic table data model
+
+class SQLAutoTableModel(SQLTableModel):
+
+	def __init__(self, glb, table_name, parent=None):
+		sql = "SELECT * FROM " + table_name + " WHERE id > $$last_id$$ ORDER BY id LIMIT " + str(glb_chunk_sz)
+		if table_name == "comm_threads_view":
+			# For now, comm_threads_view has no id column
+			sql = "SELECT * FROM " + table_name + " WHERE comm_id > $$last_id$$ ORDER BY comm_id LIMIT " + str(glb_chunk_sz)
+		self.column_headers = []
+		query = QSqlQuery(glb.db)
+		if glb.dbref.is_sqlite3:
+			QueryExec(query, "PRAGMA table_info(" + table_name + ")")
+			while query.next():
+				self.column_headers.append(query.value(1))
+			if table_name == "sqlite_master":
+				sql = "SELECT * FROM " + table_name
+		else:
+			if table_name[:19] == "information_schema.":
+				sql = "SELECT * FROM " + table_name
+				select_table_name = table_name[19:]
+				schema = "information_schema"
+			else:
+				select_table_name = table_name
+				schema = "public"
+			QueryExec(query, "SELECT column_name FROM information_schema.columns WHERE table_schema = '" + schema + "' and table_name = '" + select_table_name + "'")
+			while query.next():
+				self.column_headers.append(query.value(0))
+		super(SQLAutoTableModel, self).__init__(glb, sql, len(self.column_headers), parent)
+
+	def columnCount(self, parent=None):
+		return len(self.column_headers)
+
+	def columnHeader(self, column):
+		return self.column_headers[column]
+
+# Base class for custom ResizeColumnsToContents
+
+class ResizeColumnsToContentsBase(QObject):
+
+	def __init__(self, parent=None):
+		super(ResizeColumnsToContentsBase, self).__init__(parent)
+
+	def ResizeColumnToContents(self, column, n):
+		# Using the view's resizeColumnToContents() here is extrememly slow
+		# so implement a crude alternative
+		font = self.view.font()
+		metrics = QFontMetrics(font)
+		max = 0
+		for row in xrange(n):
+			val = self.data_model.child_items[row].data[column]
+			len = metrics.width(str(val) + "MM")
+			max = len if len > max else max
+		val = self.data_model.columnHeader(column)
+		len = metrics.width(str(val) + "MM")
+		max = len if len > max else max
+		self.view.setColumnWidth(column, max)
+
+	def ResizeColumnsToContents(self):
+		n = min(self.data_model.child_count, 100)
+		if n < 1:
+			# No data yet, so connect a signal to notify when there is
+			self.data_model.rowsInserted.connect(self.UpdateColumnWidths)
+			return
+		columns = self.data_model.columnCount()
+		for i in xrange(columns):
+			self.ResizeColumnToContents(i, n)
+
+	def UpdateColumnWidths(self, *x):
+		# This only needs to be done once, so disconnect the signal now
+		self.data_model.rowsInserted.disconnect(self.UpdateColumnWidths)
+		self.ResizeColumnsToContents()
+
+# Table window
+
+class TableWindow(QMdiSubWindow, ResizeColumnsToContentsBase):
+
+	def __init__(self, glb, table_name, parent=None):
+		super(TableWindow, self).__init__(parent)
+
+		self.data_model = LookupCreateModel(table_name + " Table", lambda: SQLAutoTableModel(glb, table_name))
+
+		self.model = QSortFilterProxyModel()
+		self.model.setSourceModel(self.data_model)
+
+		self.view = QTableView()
+		self.view.setModel(self.model)
+		self.view.setEditTriggers(QAbstractItemView.NoEditTriggers)
+		self.view.verticalHeader().setVisible(False)
+		self.view.sortByColumn(-1, Qt.AscendingOrder)
+		self.view.setSortingEnabled(True)
+
+		self.ResizeColumnsToContents()
+
+		self.find_bar = FindBar(self, self, True)
+
+		self.finder = ChildDataItemFinder(self.data_model)
+
+		self.fetch_bar = FetchMoreRecordsBar(self.data_model, self)
+
+		self.vbox = VBox(self.view, self.find_bar.Widget(), self.fetch_bar.Widget())
+
+		self.setWidget(self.vbox.Widget())
+
+		AddSubWindow(glb.mainwindow.mdi_area, self, table_name + " Table")
+
+	def Find(self, value, direction, pattern, context):
+		self.view.setFocus()
+		self.find_bar.Busy()
+		self.finder.Find(value, direction, pattern, context, self.FindDone)
+
+	def FindDone(self, row):
+		self.find_bar.Idle()
+		if row >= 0:
+			self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex()))
+		else:
+			self.find_bar.NotFound()
+
+# Table list
+
+def GetTableList(glb):
+	tables = []
+	query = QSqlQuery(glb.db)
+	if glb.dbref.is_sqlite3:
+		QueryExec(query, "SELECT name FROM sqlite_master WHERE type IN ( 'table' , 'view' ) ORDER BY name")
+	else:
+		QueryExec(query, "SELECT table_name FROM information_schema.tables WHERE table_schema = 'public' AND table_type IN ( 'BASE TABLE' , 'VIEW' ) ORDER BY table_name")
+	while query.next():
+		tables.append(query.value(0))
+	if glb.dbref.is_sqlite3:
+		tables.append("sqlite_master")
+	else:
+		tables.append("information_schema.tables")
+		tables.append("information_schema.views")
+		tables.append("information_schema.columns")
+	return tables
+
 # Action Definition
 
 def CreateAction(label, tip, callback, parent=None, shortcut=None):
@@ -779,12 +1441,15 @@ class MainWindow(QMainWindow):
 
 		edit_menu = menu.addMenu("&Edit")
 		edit_menu.addAction(CreateAction("&Find...", "Find items", self.Find, self, QKeySequence.Find))
+		edit_menu.addAction(CreateAction("Fetch &more records...", "Fetch more records", self.FetchMoreRecords, self, [QKeySequence(Qt.Key_F8)]))
 		edit_menu.addAction(CreateAction("&Shrink Font", "Make text smaller", self.ShrinkFont, self, [QKeySequence("Ctrl+-")]))
 		edit_menu.addAction(CreateAction("&Enlarge Font", "Make text bigger", self.EnlargeFont, self, [QKeySequence("Ctrl++")]))
 
 		reports_menu = menu.addMenu("&Reports")
 		reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self))
 
+		self.TableMenu(GetTableList(glb), menu)
+
 		self.window_menu = WindowMenu(self.mdi_area, menu)
 
 	def Find(self):
@@ -795,6 +1460,14 @@ class MainWindow(QMainWindow):
 			except:
 				pass
 
+	def FetchMoreRecords(self):
+		win = self.mdi_area.activeSubWindow()
+		if win:
+			try:
+				win.fetch_bar.Activate()
+			except:
+				pass
+
 	def ShrinkFont(self):
 		win = self.mdi_area.activeSubWindow()
 		ShrinkFont(win.view)
@@ -803,9 +1476,17 @@ class MainWindow(QMainWindow):
 		win = self.mdi_area.activeSubWindow()
 		EnlargeFont(win.view)
 
+	def TableMenu(self, tables, menu):
+		table_menu = menu.addMenu("&Tables")
+		for table in tables:
+			table_menu.addAction(CreateAction(table, "Create a new window containing a table view", lambda t=table: self.NewTableView(t), self))
+
 	def NewCallGraph(self):
 		CallGraphWindow(self.glb, self)
 
+	def NewTableView(self, table_name):
+		TableWindow(self.glb, table_name, self)
+
 # Global data
 
 class Glb():
@@ -816,6 +1497,18 @@ class Glb():
 		self.dbname = dbname
 		self.app = None
 		self.mainwindow = None
+		self.instances_to_shutdown_on_exit = weakref.WeakSet()
+
+	def AddInstanceToShutdownOnExit(self, instance):
+		self.instances_to_shutdown_on_exit.add(instance)
+
+	# Shutdown any background processes or threads
+	def ShutdownInstances(self):
+		for x in self.instances_to_shutdown_on_exit:
+			try:
+				x.Shutdown()
+			except:
+				pass
 
 # Database reference
 
@@ -880,6 +1573,7 @@ def Main():
 	glb.mainwindow = mainwindow
 	mainwindow.show()
 	err = app.exec_()
+	glb.ShutdownInstances()
 	db.close()
 	sys.exit(err)
 
-- 
cgit v1.2.3


From 76099f98aea4606f7c96b8d2366b46840529d08f Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 23 Oct 2018 10:59:49 +0300
Subject: perf scripts python: exported-sql-viewer.py: Add All branches report

Add a report to display branches in a similar fashion to perf script. The
main purpose of this report is to display disassembly, however, presently,
the only supported disassembler is Intel XED, and additionally the object
code must be present in perf build ID cache.

To use Intel XED, libxed.so must be present. To build and install
libxed.so:
	git clone https://github.com/intelxed/mbuild.git mbuild
	git clone https://github.com/intelxed/xed
	cd xed
	./mfile.py --share
	sudo ./mfile.py --prefix=/usr/local install
	sudo ldconfig

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181023075949.18920-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 547 +++++++++++++++++++++++
 1 file changed, 547 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index ef822d850109..24cb0bd56afa 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -46,6 +46,48 @@
 #	'Branch Count' is the total number of branches for that function and all
 #       functions that it calls
 
+# There is also a "All branches" report, which displays branches and
+# possibly disassembly.  However, presently, the only supported disassembler is
+# Intel XED, and additionally the object code must be present in perf build ID
+# cache. To use Intel XED, libxed.so must be present. To build and install
+# libxed.so:
+#            git clone https://github.com/intelxed/mbuild.git mbuild
+#            git clone https://github.com/intelxed/xed
+#            cd xed
+#            ./mfile.py --share
+#            sudo ./mfile.py --prefix=/usr/local install
+#            sudo ldconfig
+#
+# Example report:
+#
+# Time           CPU  Command  PID    TID    Branch Type            In Tx  Branch
+# 8107675239590  2    ls       22011  22011  return from interrupt  No     ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea260 _start (ld-2.19.so)
+#                                                                              7fab593ea260 48 89 e7                                        mov %rsp, %rdi
+# 8107675239899  2    ls       22011  22011  hardware interrupt     No         7fab593ea260 _start (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel])
+# 8107675241900  2    ls       22011  22011  return from interrupt  No     ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea260 _start (ld-2.19.so)
+#                                                                              7fab593ea260 48 89 e7                                        mov %rsp, %rdi
+#                                                                              7fab593ea263 e8 c8 06 00 00                                  callq  0x7fab593ea930
+# 8107675241900  2    ls       22011  22011  call                   No         7fab593ea263 _start+0x3 (ld-2.19.so) -> 7fab593ea930 _dl_start (ld-2.19.so)
+#                                                                              7fab593ea930 55                                              pushq  %rbp
+#                                                                              7fab593ea931 48 89 e5                                        mov %rsp, %rbp
+#                                                                              7fab593ea934 41 57                                           pushq  %r15
+#                                                                              7fab593ea936 41 56                                           pushq  %r14
+#                                                                              7fab593ea938 41 55                                           pushq  %r13
+#                                                                              7fab593ea93a 41 54                                           pushq  %r12
+#                                                                              7fab593ea93c 53                                              pushq  %rbx
+#                                                                              7fab593ea93d 48 89 fb                                        mov %rdi, %rbx
+#                                                                              7fab593ea940 48 83 ec 68                                     sub $0x68, %rsp
+#                                                                              7fab593ea944 0f 31                                           rdtsc
+#                                                                              7fab593ea946 48 c1 e2 20                                     shl $0x20, %rdx
+#                                                                              7fab593ea94a 89 c0                                           mov %eax, %eax
+#                                                                              7fab593ea94c 48 09 c2                                        or %rax, %rdx
+#                                                                              7fab593ea94f 48 8b 05 1a 15 22 00                            movq  0x22151a(%rip), %rax
+# 8107675242232  2    ls       22011  22011  hardware interrupt     No         7fab593ea94f _dl_start+0x1f (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel])
+# 8107675242900  2    ls       22011  22011  return from interrupt  No     ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea94f _dl_start+0x1f (ld-2.19.so)
+#                                                                              7fab593ea94f 48 8b 05 1a 15 22 00                            movq  0x22151a(%rip), %rax
+#                                                                              7fab593ea956 48 89 15 3b 13 22 00                            movq  %rdx, 0x22133b(%rip)
+# 8107675243232  2    ls       22011  22011  hardware interrupt     No         7fab593ea956 _dl_start+0x26 (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel])
+
 import sys
 import weakref
 import threading
@@ -62,6 +104,16 @@ from multiprocessing import Process, Array, Value, Event
 
 # Data formatting helpers
 
+def tohex(ip):
+	if ip < 0:
+		ip += 1 << 64
+	return "%x" % ip
+
+def offstr(offset):
+	if offset:
+		return "+0x%x" % offset
+	return ""
+
 def dsoname(name):
 	if name == "[kernel.kallsyms]":
 		return "[kernel]"
@@ -1077,6 +1129,351 @@ class FetchMoreRecordsBar():
 		self.in_progress = True
 		self.start = self.model.FetchMoreRecords(self.Target())
 
+# Brance data model level two item
+
+class BranchLevelTwoItem():
+
+	def __init__(self, row, text, parent_item):
+		self.row = row
+		self.parent_item = parent_item
+		self.data = [""] * 8
+		self.data[7] = text
+		self.level = 2
+
+	def getParentItem(self):
+		return self.parent_item
+
+	def getRow(self):
+		return self.row
+
+	def childCount(self):
+		return 0
+
+	def hasChildren(self):
+		return False
+
+	def getData(self, column):
+		return self.data[column]
+
+# Brance data model level one item
+
+class BranchLevelOneItem():
+
+	def __init__(self, glb, row, data, parent_item):
+		self.glb = glb
+		self.row = row
+		self.parent_item = parent_item
+		self.child_count = 0
+		self.child_items = []
+		self.data = data[1:]
+		self.dbid = data[0]
+		self.level = 1
+		self.query_done = False
+
+	def getChildItem(self, row):
+		return self.child_items[row]
+
+	def getParentItem(self):
+		return self.parent_item
+
+	def getRow(self):
+		return self.row
+
+	def Select(self):
+		self.query_done = True
+
+		if not self.glb.have_disassembler:
+			return
+
+		query = QSqlQuery(self.glb.db)
+
+		QueryExec(query, "SELECT cpu, to_dso_id, to_symbol_id, to_sym_offset, short_name, long_name, build_id, sym_start, to_ip"
+				  " FROM samples"
+				  " INNER JOIN dsos ON samples.to_dso_id = dsos.id"
+				  " INNER JOIN symbols ON samples.to_symbol_id = symbols.id"
+				  " WHERE samples.id = " + str(self.dbid))
+		if not query.next():
+			return
+		cpu = query.value(0)
+		dso = query.value(1)
+		sym = query.value(2)
+		if dso == 0 or sym == 0:
+			return
+		off = query.value(3)
+		short_name = query.value(4)
+		long_name = query.value(5)
+		build_id = query.value(6)
+		sym_start = query.value(7)
+		ip = query.value(8)
+
+		QueryExec(query, "SELECT samples.dso_id, symbol_id, sym_offset, sym_start"
+				  " FROM samples"
+				  " INNER JOIN symbols ON samples.symbol_id = symbols.id"
+				  " WHERE samples.id > " + str(self.dbid) + " AND cpu = " + str(cpu) +
+				  " ORDER BY samples.id"
+				  " LIMIT 1")
+		if not query.next():
+			return
+		if query.value(0) != dso:
+			# Cannot disassemble from one dso to another
+			return
+		bsym = query.value(1)
+		boff = query.value(2)
+		bsym_start = query.value(3)
+		if bsym == 0:
+			return
+		tot = bsym_start + boff + 1 - sym_start - off
+		if tot <= 0 or tot > 16384:
+			return
+
+		inst = self.glb.disassembler.Instruction()
+		f = self.glb.FileFromNamesAndBuildId(short_name, long_name, build_id)
+		if not f:
+			return
+		mode = 0 if Is64Bit(f) else 1
+		self.glb.disassembler.SetMode(inst, mode)
+
+		buf_sz = tot + 16
+		buf = create_string_buffer(tot + 16)
+		f.seek(sym_start + off)
+		buf.value = f.read(buf_sz)
+		buf_ptr = addressof(buf)
+		i = 0
+		while tot > 0:
+			cnt, text = self.glb.disassembler.DisassembleOne(inst, buf_ptr, buf_sz, ip)
+			if cnt:
+				byte_str = tohex(ip).rjust(16)
+				for k in xrange(cnt):
+					byte_str += " %02x" % ord(buf[i])
+					i += 1
+				while k < 15:
+					byte_str += "   "
+					k += 1
+				self.child_items.append(BranchLevelTwoItem(0, byte_str + " " + text, self))
+				self.child_count += 1
+			else:
+				return
+			buf_ptr += cnt
+			tot -= cnt
+			buf_sz -= cnt
+			ip += cnt
+
+	def childCount(self):
+		if not self.query_done:
+			self.Select()
+			if not self.child_count:
+				return -1
+		return self.child_count
+
+	def hasChildren(self):
+		if not self.query_done:
+			return True
+		return self.child_count > 0
+
+	def getData(self, column):
+		return self.data[column]
+
+# Brance data model root item
+
+class BranchRootItem():
+
+	def __init__(self):
+		self.child_count = 0
+		self.child_items = []
+		self.level = 0
+
+	def getChildItem(self, row):
+		return self.child_items[row]
+
+	def getParentItem(self):
+		return None
+
+	def getRow(self):
+		return 0
+
+	def childCount(self):
+		return self.child_count
+
+	def hasChildren(self):
+		return self.child_count > 0
+
+	def getData(self, column):
+		return ""
+
+# Branch data preparation
+
+def BranchDataPrep(query):
+	data = []
+	for i in xrange(0, 8):
+		data.append(query.value(i))
+	data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) +
+			" (" + dsoname(query.value(11)) + ")" + " -> " +
+			tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) +
+			" (" + dsoname(query.value(15)) + ")")
+	return data
+
+# Branch data model
+
+class BranchModel(TreeModel):
+
+	progress = Signal(object)
+
+	def __init__(self, glb, event_id, where_clause, parent=None):
+		super(BranchModel, self).__init__(BranchRootItem(), parent)
+		self.glb = glb
+		self.event_id = event_id
+		self.more = True
+		self.populated = 0
+		sql = ("SELECT samples.id, time, cpu, comm, pid, tid, branch_types.name,"
+			" CASE WHEN in_tx = '0' THEN 'No' ELSE 'Yes' END,"
+			" ip, symbols.name, sym_offset, dsos.short_name,"
+			" to_ip, to_symbols.name, to_sym_offset, to_dsos.short_name"
+			" FROM samples"
+			" INNER JOIN comms ON comm_id = comms.id"
+			" INNER JOIN threads ON thread_id = threads.id"
+			" INNER JOIN branch_types ON branch_type = branch_types.id"
+			" INNER JOIN symbols ON symbol_id = symbols.id"
+			" INNER JOIN symbols to_symbols ON to_symbol_id = to_symbols.id"
+			" INNER JOIN dsos ON samples.dso_id = dsos.id"
+			" INNER JOIN dsos AS to_dsos ON samples.to_dso_id = to_dsos.id"
+			" WHERE samples.id > $$last_id$$" + where_clause +
+			" AND evsel_id = " + str(self.event_id) +
+			" ORDER BY samples.id"
+			" LIMIT " + str(glb_chunk_sz))
+		self.fetcher = SQLFetcher(glb, sql, BranchDataPrep, self.AddSample)
+		self.fetcher.done.connect(self.Update)
+		self.fetcher.Fetch(glb_chunk_sz)
+
+	def columnCount(self, parent=None):
+		return 8
+
+	def columnHeader(self, column):
+		return ("Time", "CPU", "Command", "PID", "TID", "Branch Type", "In Tx", "Branch")[column]
+
+	def columnFont(self, column):
+		if column != 7:
+			return None
+		return QFont("Monospace")
+
+	def DisplayData(self, item, index):
+		if item.level == 1:
+			self.FetchIfNeeded(item.row)
+		return item.getData(index.column())
+
+	def AddSample(self, data):
+		child = BranchLevelOneItem(self.glb, self.populated, data, self.root)
+		self.root.child_items.append(child)
+		self.populated += 1
+
+	def Update(self, fetched):
+		if not fetched:
+			self.more = False
+			self.progress.emit(0)
+		child_count = self.root.child_count
+		count = self.populated - child_count
+		if count > 0:
+			parent = QModelIndex()
+			self.beginInsertRows(parent, child_count, child_count + count - 1)
+			self.insertRows(child_count, count, parent)
+			self.root.child_count += count
+			self.endInsertRows()
+			self.progress.emit(self.root.child_count)
+
+	def FetchMoreRecords(self, count):
+		current = self.root.child_count
+		if self.more:
+			self.fetcher.Fetch(count)
+		else:
+			self.progress.emit(0)
+		return current
+
+	def HasMoreRecords(self):
+		return self.more
+
+# Branch window
+
+class BranchWindow(QMdiSubWindow):
+
+	def __init__(self, glb, event_id, name, where_clause, parent=None):
+		super(BranchWindow, self).__init__(parent)
+
+		model_name = "Branch Events " + str(event_id)
+		if len(where_clause):
+			model_name = where_clause + " " + model_name
+
+		self.model = LookupCreateModel(model_name, lambda: BranchModel(glb, event_id, where_clause))
+
+		self.view = QTreeView()
+		self.view.setUniformRowHeights(True)
+		self.view.setModel(self.model)
+
+		self.ResizeColumnsToContents()
+
+		self.find_bar = FindBar(self, self, True)
+
+		self.finder = ChildDataItemFinder(self.model.root)
+
+		self.fetch_bar = FetchMoreRecordsBar(self.model, self)
+
+		self.vbox = VBox(self.view, self.find_bar.Widget(), self.fetch_bar.Widget())
+
+		self.setWidget(self.vbox.Widget())
+
+		AddSubWindow(glb.mainwindow.mdi_area, self, name + " Branch Events")
+
+	def ResizeColumnToContents(self, column, n):
+		# Using the view's resizeColumnToContents() here is extrememly slow
+		# so implement a crude alternative
+		mm = "MM" if column else "MMMM"
+		font = self.view.font()
+		metrics = QFontMetrics(font)
+		max = 0
+		for row in xrange(n):
+			val = self.model.root.child_items[row].data[column]
+			len = metrics.width(str(val) + mm)
+			max = len if len > max else max
+		val = self.model.columnHeader(column)
+		len = metrics.width(str(val) + mm)
+		max = len if len > max else max
+		self.view.setColumnWidth(column, max)
+
+	def ResizeColumnsToContents(self):
+		n = min(self.model.root.child_count, 100)
+		if n < 1:
+			# No data yet, so connect a signal to notify when there is
+			self.model.rowsInserted.connect(self.UpdateColumnWidths)
+			return
+		columns = self.model.columnCount()
+		for i in xrange(columns):
+			self.ResizeColumnToContents(i, n)
+
+	def UpdateColumnWidths(self, *x):
+		# This only needs to be done once, so disconnect the signal now
+		self.model.rowsInserted.disconnect(self.UpdateColumnWidths)
+		self.ResizeColumnsToContents()
+
+	def Find(self, value, direction, pattern, context):
+		self.view.setFocus()
+		self.find_bar.Busy()
+		self.finder.Find(value, direction, pattern, context, self.FindDone)
+
+	def FindDone(self, row):
+		self.find_bar.Idle()
+		if row >= 0:
+			self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex()))
+		else:
+			self.find_bar.NotFound()
+
+# Event list
+
+def GetEventList(db):
+	events = []
+	query = QSqlQuery(db)
+	QueryExec(query, "SELECT name FROM selected_events WHERE id > 0 ORDER BY id")
+	while query.next():
+		events.append(query.value(0))
+	return events
+
 # SQL data preparation
 
 def SQLTableDataPrep(query, count):
@@ -1448,6 +1845,8 @@ class MainWindow(QMainWindow):
 		reports_menu = menu.addMenu("&Reports")
 		reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self))
 
+		self.EventMenu(GetEventList(glb.db), reports_menu)
+
 		self.TableMenu(GetTableList(glb), menu)
 
 		self.window_menu = WindowMenu(self.mdi_area, menu)
@@ -1476,6 +1875,20 @@ class MainWindow(QMainWindow):
 		win = self.mdi_area.activeSubWindow()
 		EnlargeFont(win.view)
 
+	def EventMenu(self, events, reports_menu):
+		branches_events = 0
+		for event in events:
+			event = event.split(":")[0]
+			if event == "branches":
+				branches_events += 1
+		dbid = 0
+		for event in events:
+			dbid += 1
+			event = event.split(":")[0]
+			if event == "branches":
+				label = "All branches" if branches_events == 1 else "All branches " + "(id=" + dbid + ")"
+				reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewBranchView(x), self))
+
 	def TableMenu(self, tables, menu):
 		table_menu = menu.addMenu("&Tables")
 		for table in tables:
@@ -1484,9 +1897,112 @@ class MainWindow(QMainWindow):
 	def NewCallGraph(self):
 		CallGraphWindow(self.glb, self)
 
+	def NewBranchView(self, event_id):
+		BranchWindow(self.glb, event_id, "", "", self)
+
 	def NewTableView(self, table_name):
 		TableWindow(self.glb, table_name, self)
 
+# XED Disassembler
+
+class xed_state_t(Structure):
+
+	_fields_ = [
+		("mode", c_int),
+		("width", c_int)
+	]
+
+class XEDInstruction():
+
+	def __init__(self, libxed):
+		# Current xed_decoded_inst_t structure is 192 bytes. Use 512 to allow for future expansion
+		xedd_t = c_byte * 512
+		self.xedd = xedd_t()
+		self.xedp = addressof(self.xedd)
+		libxed.xed_decoded_inst_zero(self.xedp)
+		self.state = xed_state_t()
+		self.statep = addressof(self.state)
+		# Buffer for disassembled instruction text
+		self.buffer = create_string_buffer(256)
+		self.bufferp = addressof(self.buffer)
+
+class LibXED():
+
+	def __init__(self):
+		self.libxed = CDLL("libxed.so")
+
+		self.xed_tables_init = self.libxed.xed_tables_init
+		self.xed_tables_init.restype = None
+		self.xed_tables_init.argtypes = []
+
+		self.xed_decoded_inst_zero = self.libxed.xed_decoded_inst_zero
+		self.xed_decoded_inst_zero.restype = None
+		self.xed_decoded_inst_zero.argtypes = [ c_void_p ]
+
+		self.xed_operand_values_set_mode = self.libxed.xed_operand_values_set_mode
+		self.xed_operand_values_set_mode.restype = None
+		self.xed_operand_values_set_mode.argtypes = [ c_void_p, c_void_p ]
+
+		self.xed_decoded_inst_zero_keep_mode = self.libxed.xed_decoded_inst_zero_keep_mode
+		self.xed_decoded_inst_zero_keep_mode.restype = None
+		self.xed_decoded_inst_zero_keep_mode.argtypes = [ c_void_p ]
+
+		self.xed_decode = self.libxed.xed_decode
+		self.xed_decode.restype = c_int
+		self.xed_decode.argtypes = [ c_void_p, c_void_p, c_uint ]
+
+		self.xed_format_context = self.libxed.xed_format_context
+		self.xed_format_context.restype = c_uint
+		self.xed_format_context.argtypes = [ c_int, c_void_p, c_void_p, c_int, c_ulonglong, c_void_p, c_void_p ]
+
+		self.xed_tables_init()
+
+	def Instruction(self):
+		return XEDInstruction(self)
+
+	def SetMode(self, inst, mode):
+		if mode:
+			inst.state.mode = 4 # 32-bit
+			inst.state.width = 4 # 4 bytes
+		else:
+			inst.state.mode = 1 # 64-bit
+			inst.state.width = 8 # 8 bytes
+		self.xed_operand_values_set_mode(inst.xedp, inst.statep)
+
+	def DisassembleOne(self, inst, bytes_ptr, bytes_cnt, ip):
+		self.xed_decoded_inst_zero_keep_mode(inst.xedp)
+		err = self.xed_decode(inst.xedp, bytes_ptr, bytes_cnt)
+		if err:
+			return 0, ""
+		# Use AT&T mode (2), alternative is Intel (3)
+		ok = self.xed_format_context(2, inst.xedp, inst.bufferp, sizeof(inst.buffer), ip, 0, 0)
+		if not ok:
+			return 0, ""
+		# Return instruction length and the disassembled instruction text
+		# For now, assume the length is in byte 166
+		return inst.xedd[166], inst.buffer.value
+
+def TryOpen(file_name):
+	try:
+		return open(file_name, "rb")
+	except:
+		return None
+
+def Is64Bit(f):
+	result = sizeof(c_void_p)
+	# ELF support only
+	pos = f.tell()
+	f.seek(0)
+	header = f.read(7)
+	f.seek(pos)
+	magic = header[0:4]
+	eclass = ord(header[4])
+	encoding = ord(header[5])
+	version = ord(header[6])
+	if magic == chr(127) + "ELF" and eclass > 0 and eclass < 3 and encoding > 0 and encoding < 3 and version == 1:
+		result = True if eclass == 2 else False
+	return result
+
 # Global data
 
 class Glb():
@@ -1495,9 +2011,40 @@ class Glb():
 		self.dbref = dbref
 		self.db = db
 		self.dbname = dbname
+		self.home_dir = os.path.expanduser("~")
+		self.buildid_dir = os.getenv("PERF_BUILDID_DIR")
+		if self.buildid_dir:
+			self.buildid_dir += "/.build-id/"
+		else:
+			self.buildid_dir = self.home_dir + "/.debug/.build-id/"
 		self.app = None
 		self.mainwindow = None
 		self.instances_to_shutdown_on_exit = weakref.WeakSet()
+		try:
+			self.disassembler = LibXED()
+			self.have_disassembler = True
+		except:
+			self.have_disassembler = False
+
+	def FileFromBuildId(self, build_id):
+		file_name = self.buildid_dir + build_id[0:2] + "/" + build_id[2:] + "/elf"
+		return TryOpen(file_name)
+
+	def FileFromNamesAndBuildId(self, short_name, long_name, build_id):
+		# Assume current machine i.e. no support for virtualization
+		if short_name[0:7] == "[kernel" and os.path.basename(long_name) == "kcore":
+			file_name = os.getenv("PERF_KCORE")
+			f = TryOpen(file_name) if file_name else None
+			if f:
+				return f
+			# For now, no special handling if long_name is /proc/kcore
+			f = TryOpen(long_name)
+			if f:
+				return f
+		f = self.FileFromBuildId(build_id)
+		if f:
+			return f
+		return None
 
 	def AddInstanceToShutdownOnExit(self, instance):
 		self.instances_to_shutdown_on_exit.add(instance)
-- 
cgit v1.2.3


From b585ebdb5912cf1438d4822f79aaebe36a2d123a Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Thu, 20 Sep 2018 11:05:36 -0700
Subject: perf script: Add --insn-trace for instruction decoding

Add a --insn-trace short hand option for decoding and disassembling
instruction streams for intel_pt. This automatically pipes the output
into the xed disassembler to generate disassembled instructions.  This
just makes this use model much nicer to use.

Before

  % perf record -e intel_pt// ...
  % perf script --itrace=i0ns --ns -F +insn,-event,-period | xed -F insn: -A -64
   swapper 0 [000] 17276.429606186: ffffffff81010486 pt_config ([kernel.kallsyms])    nopl  %eax, (%rax,%rax,1)
   swapper 0 [000] 17276.429606186: ffffffff8101048b pt_config ([kernel.kallsyms])    add $0x10, %rsp
   swapper 0 [000] 17276.429606186: ffffffff8101048f pt_config ([kernel.kallsyms])    popq  %rbx
   swapper 0 [000] 17276.429606186: ffffffff81010490 pt_config ([kernel.kallsyms])    popq  %rbp
   swapper 0 [000] 17276.429606186: ffffffff81010491 pt_config ([kernel.kallsyms])    popq  %r12
   swapper 0 [000] 17276.429606186: ffffffff81010493 pt_config ([kernel.kallsyms])    popq  %r13
   swapper 0 [000] 17276.429606186: ffffffff81010495 pt_config ([kernel.kallsyms])    popq  %r14
   swapper 0 [000] 17276.429606186: ffffffff81010497 pt_config ([kernel.kallsyms])    popq  %r15
   swapper 0 [000] 17276.429606186: ffffffff81010499 pt_config ([kernel.kallsyms])    retq
   swapper 0 [000] 17276.429606186: ffffffff8101063e pt_event_add ([kernel.kallsyms])         cmpl  $0x1, 0x1b0(%rbx)
   swapper 0 [000] 17276.429606186: ffffffff81010645 pt_event_add ([kernel.kallsyms])         mov $0xffffffea, %eax
   swapper 0 [000] 17276.429606186: ffffffff8101064a pt_event_add ([kernel.kallsyms])         mov $0x0, %edx
   swapper 0 [000] 17276.429606186: ffffffff8101064f pt_event_add ([kernel.kallsyms])         popq  %rbx
   swapper 0 [000] 17276.429606186: ffffffff81010650 pt_event_add ([kernel.kallsyms])         cmovnz %edx, %eax
   swapper 0 [000] 17276.429606186: ffffffff81010653 pt_event_add ([kernel.kallsyms])         jmp 0xffffffff81010635
   swapper 0 [000] 17276.429606186: ffffffff81010635 pt_event_add ([kernel.kallsyms])         retq
   swapper 0 [000] 17276.429606186: ffffffff8115e687 event_sched_in.isra.107 ([kernel.kallsyms])       test %eax, %eax

Now:

  % perf record -e intel_pt// ...
  % perf script --insn-trace --xed
  ... same output ...

XED needs to be installed with:

  $ git clone https://github.com/intelxed/mbuild.git mbuild
  $ git clone https://github.com/intelxed/xed
  $ cd xed
  $ ./mfile.py
  $ ./mfile.py examples
  $ sudo ./mfile.py --prefix=/usr/local install
  $ sudo cp obj/examples/xed /usr/local/bin
  $ xed | head -3
  ERROR: required argument(s) were missing
  Copyright (C) 2017, Intel Corporation. All rights reserved.
  XED version: [v10.0-328-g7d62c8c49b7b]
  $

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20180920180540.14039-2-andi@firstfloor.org
[ Fixed up whitespace damage, added the 'mfile.py examples + cp obj/examples/xed ... ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/build-xed.txt   | 19 +++++++++++++++++++
 tools/perf/Documentation/perf-script.txt |  7 +++++++
 tools/perf/builtin-script.c              | 23 +++++++++++++++++++++++
 3 files changed, 49 insertions(+)
 create mode 100644 tools/perf/Documentation/build-xed.txt

(limited to 'tools')

diff --git a/tools/perf/Documentation/build-xed.txt b/tools/perf/Documentation/build-xed.txt
new file mode 100644
index 000000000000..6222c1e7231f
--- /dev/null
+++ b/tools/perf/Documentation/build-xed.txt
@@ -0,0 +1,19 @@
+
+For --xed the xed tool is needed. Here is how to install it:
+
+  $ git clone https://github.com/intelxed/mbuild.git mbuild
+  $ git clone https://github.com/intelxed/xed
+  $ cd xed
+  $ ./mfile.py --share
+  $ ./mfile.py examples
+  $ sudo ./mfile.py --prefix=/usr/local install
+  $ sudo ldconfig
+  $ sudo cp obj/examples/xed /usr/local/bin
+
+Basic xed testing:
+
+  $ xed | head -3
+  ERROR: required argument(s) were missing
+  Copyright (C) 2017, Intel Corporation. All rights reserved.
+  XED version: [v10.0-328-g7d62c8c49b7b]
+  $
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index afdafe2110a1..00c655ab4968 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -383,6 +383,13 @@ include::itrace.txt[]
 	will be printed. Each entry has function name and file/line. Enabled by
 	default, disable with --no-inline.
 
+--insn-trace::
+	Show instruction stream for intel_pt traces. Combine with --xed to
+	show disassembly.
+
+--xed::
+	Run xed disassembler on output. Requires installing the xed disassembler.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ca09b7d2adb7..411ea175bcaf 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -44,6 +44,7 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <unistd.h>
+#include <subcmd/pager.h>
 
 #include "sane_ctype.h"
 
@@ -3103,6 +3104,24 @@ static int perf_script__process_auxtrace_info(struct perf_session *session,
 #define perf_script__process_auxtrace_info 0
 #endif
 
+static int parse_insn_trace(const struct option *opt __maybe_unused,
+			    const char *str __maybe_unused,
+			    int unset __maybe_unused)
+{
+	parse_output_fields(NULL, "+insn,-event,-period", 0);
+	itrace_parse_synth_opts(opt, "i0ns", 0);
+	nanosecs = true;
+	return 0;
+}
+
+static int parse_xed(const struct option *opt __maybe_unused,
+		     const char *str __maybe_unused,
+		     int unset __maybe_unused)
+{
+	force_pager("xed -F insn: -A -64 | less");
+	return 0;
+}
+
 int cmd_script(int argc, const char **argv)
 {
 	bool show_full_info = false;
@@ -3187,6 +3206,10 @@ int cmd_script(int argc, const char **argv)
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
 		   "only consider these symbols"),
+	OPT_CALLBACK_OPTARG(0, "insn-trace", &itrace_synth_opts, NULL, NULL,
+			"Decode instructions from itrace", parse_insn_trace),
+	OPT_CALLBACK_OPTARG(0, "xed", NULL, NULL, NULL,
+			"Run xed disassembler on output", parse_xed),
 	OPT_STRING(0, "stop-bt", &symbol_conf.bt_stop_list_str, "symbol[,symbol...]",
 		   "Stop display of callgraph at these symbols"),
 	OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
-- 
cgit v1.2.3


From 4eb068157121939f4bc16256a37bcd88f5554123 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Thu, 20 Sep 2018 11:05:37 -0700
Subject: perf script: Make itrace script default to all calls

By default 'perf script' for itrace outputs sampled instructions or
branches. In my experience this is confusing to users because it's hard
to correlate with real program behavior. The sampling makes sense for
tools like 'perf report' that actually sample to reduce the run time,
but run time is normally not a problem for 'perf script'.  It's better
to give an accurate representation of the program flow.

Default 'perf script' to output all calls for itrace. That's a much saner
default. The old behavior can be still requested with 'perf script'
--itrace=ibxwpe100000

v2: Fix ETM build failure
v3: Really fix ETM build failure (Kim Phillips)

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Leo Yan <leo.yan@linaro.org>
Link: http://lkml.kernel.org/r/20180920180540.14039-3-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/itrace.txt |  7 ++++---
 tools/perf/builtin-script.c         |  5 ++++-
 tools/perf/util/auxtrace.c          | 17 ++++++++++++-----
 tools/perf/util/auxtrace.h          |  5 ++++-
 tools/perf/util/cs-etm.c            |  3 ++-
 tools/perf/util/intel-bts.c         |  3 ++-
 tools/perf/util/intel-pt.c          |  3 ++-
 7 files changed, 30 insertions(+), 13 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index a3abe04c779d..c2182cbabde3 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -11,10 +11,11 @@
 		l	synthesize last branch entries (use with i or x)
 		s       skip initial number of events
 
-	The default is all events i.e. the same as --itrace=ibxwpe
+	The default is all events i.e. the same as --itrace=ibxwpe,
+	except for perf script where it is --itrace=ce
 
-	In addition, the period (default 100000) for instructions events
-	can be specified in units of:
+	In addition, the period (default 100000, except for perf script where it is 1)
+	for instructions events can be specified in units of:
 
 		i	instructions
 		t	ticks
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 411ea175bcaf..6099c722a679 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3131,7 +3131,10 @@ int cmd_script(int argc, const char **argv)
 	char *rec_script_path = NULL;
 	char *rep_script_path = NULL;
 	struct perf_session *session;
-	struct itrace_synth_opts itrace_synth_opts = { .set = false, };
+	struct itrace_synth_opts itrace_synth_opts = {
+		.set = false,
+		.default_no_sample = true,
+	};
 	char *script_path = NULL;
 	const char **__argv;
 	int i, j, err = 0;
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c4617bcfd521..72d5ba2479bf 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -962,16 +962,23 @@ s64 perf_event__process_auxtrace(struct perf_session *session,
 #define PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ	64
 #define PERF_ITRACE_MAX_LAST_BRANCH_SZ		1024
 
-void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
+				    bool no_sample)
 {
-	synth_opts->instructions = true;
 	synth_opts->branches = true;
 	synth_opts->transactions = true;
 	synth_opts->ptwrites = true;
 	synth_opts->pwr_events = true;
 	synth_opts->errors = true;
-	synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
-	synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+	if (no_sample) {
+		synth_opts->period_type = PERF_ITRACE_PERIOD_INSTRUCTIONS;
+		synth_opts->period = 1;
+		synth_opts->calls = true;
+	} else {
+		synth_opts->instructions = true;
+		synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+		synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+	}
 	synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
 	synth_opts->last_branch_sz = PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ;
 	synth_opts->initial_skip = 0;
@@ -999,7 +1006,7 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 	}
 
 	if (!str) {
-		itrace_synth_opts__set_default(synth_opts);
+		itrace_synth_opts__set_default(synth_opts, false);
 		return 0;
 	}
 
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index d88f6e9eb461..8e50f96d4b23 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -58,6 +58,7 @@ enum itrace_period_type {
 /**
  * struct itrace_synth_opts - AUX area tracing synthesis options.
  * @set: indicates whether or not options have been set
+ * @default_no_sample: Default to no sampling.
  * @inject: indicates the event (not just the sample) must be fully synthesized
  *          because 'perf inject' will write it out
  * @instructions: whether to synthesize 'instructions' events
@@ -82,6 +83,7 @@ enum itrace_period_type {
  */
 struct itrace_synth_opts {
 	bool			set;
+	bool			default_no_sample;
 	bool			inject;
 	bool			instructions;
 	bool			branches;
@@ -528,7 +530,8 @@ int perf_event__process_auxtrace_error(struct perf_session *session,
 				       union perf_event *event);
 int itrace_parse_synth_opts(const struct option *opt, const char *str,
 			    int unset);
-void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
+				    bool no_sample);
 
 size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp);
 void perf_session__auxtrace_error_inc(struct perf_session *session,
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 2ae640257fdb..3b37d66dc533 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1432,7 +1432,8 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
 		etm->synth_opts = *session->itrace_synth_opts;
 	} else {
-		itrace_synth_opts__set_default(&etm->synth_opts);
+		itrace_synth_opts__set_default(&etm->synth_opts,
+				session->itrace_synth_opts->default_no_sample);
 		etm->synth_opts.callchain = false;
 	}
 
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 7f0c83b6332b..3b3a3d55dca1 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -910,7 +910,8 @@ int intel_bts_process_auxtrace_info(union perf_event *event,
 	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
 		bts->synth_opts = *session->itrace_synth_opts;
 	} else {
-		itrace_synth_opts__set_default(&bts->synth_opts);
+		itrace_synth_opts__set_default(&bts->synth_opts,
+				session->itrace_synth_opts->default_no_sample);
 		if (session->itrace_synth_opts)
 			bts->synth_opts.thread_stack =
 				session->itrace_synth_opts->thread_stack;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 48c1d415c6b0..ffa385a029b3 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2559,7 +2559,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
 		pt->synth_opts = *session->itrace_synth_opts;
 	} else {
-		itrace_synth_opts__set_default(&pt->synth_opts);
+		itrace_synth_opts__set_default(&pt->synth_opts,
+				session->itrace_synth_opts->default_no_sample);
 		if (use_browser != -1) {
 			pt->synth_opts.branches = false;
 			pt->synth_opts.callchain = true;
-- 
cgit v1.2.3


From d1b1552e15d41297abcaf3812378e3391d44fa6b Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Thu, 20 Sep 2018 11:05:38 -0700
Subject: tools script: Add --call-trace and --call-ret-trace

Add short cut options to print PT call trace and call-ret-trace, for
calls and call and returns. Roughly corresponds to ftrace function
tracer and function graph tracer.

Just makes these common use cases nicer to use.

% perf record -a -e intel_pt// sleep 1
% perf script --call-trace
	    perf   900 [000] 194167.205652203: ([kernel.kallsyms])          perf_pmu_enable
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])          __x86_indirect_thunk_rax
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])          event_filter_match
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])          group_sched_in
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])              __x86_indirect_thunk_rax
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])              event_sched_in.isra.107
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  perf_event_set_state.part.71
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                      perf_event_update_time
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  perf_pmu_disable
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  perf_log_itrace_start
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  __x86_indirect_thunk_rax
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                      perf_event_update_userpage

% perf script --call-ret-trace
	    perf   900 [000] 194167.205652203:   tr strt     ([unknown])        pt_config
            perf   900 [000] 194167.205652203:   return      ([kernel.kallsyms])            pt_config
            perf   900 [000] 194167.205652203:   return      ([kernel.kallsyms])            pt_event_add
            perf   900 [000] 194167.205652203:   call        ([kernel.kallsyms])            perf_pmu_enable
            perf   900 [000] 194167.205652203:   return      ([kernel.kallsyms])            perf_pmu_nop_void
            perf   900 [000] 194167.205652203:   return      ([kernel.kallsyms])            event_sched_in.isra.107
            perf   900 [000] 194167.205652203:   call        ([kernel.kallsyms])            __x86_indirect_thunk_rax
            perf   900 [000] 194167.205652203:   return      ([kernel.kallsyms])            perf_pmu_nop_int
            perf   900 [000] 194167.205652203:   return      ([kernel.kallsyms])            group_sched_in
            perf   900 [000] 194167.205652203:   call        ([kernel.kallsyms])            event_filter_match
            perf   900 [000] 194167.205652203:   return      ([kernel.kallsyms])            event_filter_match
            perf   900 [000] 194167.205652203:   call        ([kernel.kallsyms])            group_sched_in
            perf   900 [000] 194167.205652203:   call        ([kernel.kallsyms])                __x86_indirect_thunk_rax
            perf   900 [000] 194167.205652203:   return      ([kernel.kallsyms])                perf_pmu_nop_txn
            perf   900 [000] 194167.205652203:   call        ([kernel.kallsyms])                event_sched_in.isra.107
            perf   900 [000] 194167.205652203:   call        ([kernel.kallsyms])                    perf_event_set_state.part.71

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Kim Phillips <kim.phillips@arm.com>
Link: http://lkml.kernel.org/r/20180920180540.14039-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-script.txt |  7 +++++++
 tools/perf/builtin-script.c              | 24 ++++++++++++++++++++++++
 2 files changed, 31 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 00c655ab4968..805baabd238e 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -390,6 +390,13 @@ include::itrace.txt[]
 --xed::
 	Run xed disassembler on output. Requires installing the xed disassembler.
 
+--call-trace::
+	Show call stream for intel_pt traces. The CPUs are interleaved, but
+	can be filtered with -C.
+
+--call-ret-trace::
+	Show call and return stream for intel_pt traces.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 6099c722a679..566e1450898a 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3122,6 +3122,26 @@ static int parse_xed(const struct option *opt __maybe_unused,
 	return 0;
 }
 
+static int parse_call_trace(const struct option *opt __maybe_unused,
+			    const char *str __maybe_unused,
+			    int unset __maybe_unused)
+{
+	parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent", 0);
+	itrace_parse_synth_opts(opt, "cewp", 0);
+	nanosecs = true;
+	return 0;
+}
+
+static int parse_callret_trace(const struct option *opt __maybe_unused,
+			    const char *str __maybe_unused,
+			    int unset __maybe_unused)
+{
+	parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent,+flags", 0);
+	itrace_parse_synth_opts(opt, "crewp", 0);
+	nanosecs = true;
+	return 0;
+}
+
 int cmd_script(int argc, const char **argv)
 {
 	bool show_full_info = false;
@@ -3213,6 +3233,10 @@ int cmd_script(int argc, const char **argv)
 			"Decode instructions from itrace", parse_insn_trace),
 	OPT_CALLBACK_OPTARG(0, "xed", NULL, NULL, NULL,
 			"Run xed disassembler on output", parse_xed),
+	OPT_CALLBACK_OPTARG(0, "call-trace", &itrace_synth_opts, NULL, NULL,
+			"Decode calls from from itrace", parse_call_trace),
+	OPT_CALLBACK_OPTARG(0, "call-ret-trace", &itrace_synth_opts, NULL, NULL,
+			"Decode calls and returns from itrace", parse_callret_trace),
 	OPT_STRING(0, "stop-bt", &symbol_conf.bt_stop_list_str, "symbol[,symbol...]",
 		   "Stop display of callgraph at these symbols"),
 	OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
-- 
cgit v1.2.3


From 99f753f048b3f02f31a56951781672021af6cd0d Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Thu, 20 Sep 2018 11:05:39 -0700
Subject: perf script: Implement --graph-function

Add a ftrace style --graph-function argument to 'perf script' that
allows to print itrace function calls only below a given function. This
makes it easier to find the code of interest in a large trace.

% perf record -e intel_pt//k -a sleep 1
% perf script --graph-function group_sched_in --call-trace
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])          group_sched_in
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])              __x86_indirect_thunk_rax
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])              event_sched_in.isra.107
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  perf_event_set_state.part.71
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                      perf_event_update_time
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  perf_pmu_disable
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  perf_log_itrace_start
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  __x86_indirect_thunk_rax
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                      perf_event_update_userpage
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                          calc_timer_values
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                              sched_clock_cpu
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                          __x86_indirect_thunk_rax
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                          arch_perf_update_userpage
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                              __fentry__
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                              using_native_sched_clock
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                              sched_clock_stable
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  perf_pmu_enable
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])              __x86_indirect_thunk_rax
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])          group_sched_in
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])              __x86_indirect_thunk_rax
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])              event_sched_in.isra.107
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                  perf_event_set_state.part.71
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                      perf_event_update_time
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                  perf_pmu_disable
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                  perf_log_itrace_start
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                  __x86_indirect_thunk_rax
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                      perf_event_update_userpage
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                          calc_timer_values
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                              sched_clock_cpu
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                          __x86_indirect_thunk_rax
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                          arch_perf_update_userpage
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                              __fentry__
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                              using_native_sched_clock
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                              sched_clock_stable

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Kim Phillips <kim.phillips@arm.com>
Link: http://lkml.kernel.org/r/20180920180540.14039-5-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-script.txt |  4 ++
 tools/perf/builtin-script.c              | 96 ++++++++++++++++++++++++++------
 tools/perf/util/symbol.h                 |  3 +-
 tools/perf/util/thread.h                 |  2 +
 4 files changed, 86 insertions(+), 19 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 805baabd238e..a2b37ce48094 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -397,6 +397,10 @@ include::itrace.txt[]
 --call-ret-trace::
 	Show call and return stream for intel_pt traces.
 
+--graph-function::
+	For itrace only show specified functions and their callees for
+	itrace. Multiple functions can be separated by comma.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 566e1450898a..9d2249ea75e3 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1105,6 +1105,35 @@ out:
 	return printed;
 }
 
+static const char *resolve_branch_sym(struct perf_sample *sample,
+				      struct perf_evsel *evsel,
+				      struct thread *thread,
+				      struct addr_location *al,
+				      u64 *ip)
+{
+	struct addr_location addr_al;
+	struct perf_event_attr *attr = &evsel->attr;
+	const char *name = NULL;
+
+	if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) {
+		if (sample_addr_correlates_sym(attr)) {
+			thread__resolve(thread, &addr_al, sample);
+			if (addr_al.sym)
+				name = addr_al.sym->name;
+			else
+				*ip = sample->addr;
+		} else {
+			*ip = sample->addr;
+		}
+	} else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) {
+		if (al->sym)
+			name = al->sym->name;
+		else
+			*ip = sample->ip;
+	}
+	return name;
+}
+
 static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 					   struct perf_evsel *evsel,
 					   struct thread *thread,
@@ -1112,7 +1141,6 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	size_t depth = thread_stack__depth(thread);
-	struct addr_location addr_al;
 	const char *name = NULL;
 	static int spacing;
 	int len = 0;
@@ -1126,22 +1154,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 	if (thread->ts && sample->flags & PERF_IP_FLAG_RETURN)
 		depth += 1;
 
-	if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) {
-		if (sample_addr_correlates_sym(attr)) {
-			thread__resolve(thread, &addr_al, sample);
-			if (addr_al.sym)
-				name = addr_al.sym->name;
-			else
-				ip = sample->addr;
-		} else {
-			ip = sample->addr;
-		}
-	} else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) {
-		if (al->sym)
-			name = al->sym->name;
-		else
-			ip = sample->ip;
-	}
+	name = resolve_branch_sym(sample, evsel, thread, al, &ip);
 
 	if (PRINT_FIELD(DSO) && !(PRINT_FIELD(IP) || PRINT_FIELD(ADDR))) {
 		dlen += fprintf(fp, "(");
@@ -1647,6 +1660,47 @@ static void perf_sample__fprint_metric(struct perf_script *script,
 	}
 }
 
+static bool show_event(struct perf_sample *sample,
+		       struct perf_evsel *evsel,
+		       struct thread *thread,
+		       struct addr_location *al)
+{
+	int depth = thread_stack__depth(thread);
+
+	if (!symbol_conf.graph_function)
+		return true;
+
+	if (thread->filter) {
+		if (depth <= thread->filter_entry_depth) {
+			thread->filter = false;
+			return false;
+		}
+		return true;
+	} else {
+		const char *s = symbol_conf.graph_function;
+		u64 ip;
+		const char *name = resolve_branch_sym(sample, evsel, thread, al,
+				&ip);
+		unsigned nlen;
+
+		if (!name)
+			return false;
+		nlen = strlen(name);
+		while (*s) {
+			unsigned len = strcspn(s, ",");
+			if (nlen == len && !strncmp(name, s, len)) {
+				thread->filter = true;
+				thread->filter_entry_depth = depth;
+				return true;
+			}
+			s += len;
+			if (*s == ',')
+				s++;
+		}
+		return false;
+	}
+}
+
 static void process_event(struct perf_script *script,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
 			  struct addr_location *al,
@@ -1661,6 +1715,9 @@ static void process_event(struct perf_script *script,
 	if (output[type].fields == 0)
 		return;
 
+	if (!show_event(sample, evsel, thread, al))
+		return;
+
 	++es->samples;
 
 	perf_sample__fprintf_start(sample, thread, evsel,
@@ -3237,6 +3294,8 @@ int cmd_script(int argc, const char **argv)
 			"Decode calls from from itrace", parse_call_trace),
 	OPT_CALLBACK_OPTARG(0, "call-ret-trace", &itrace_synth_opts, NULL, NULL,
 			"Decode calls and returns from itrace", parse_callret_trace),
+	OPT_STRING(0, "graph-function", &symbol_conf.graph_function, "symbol[,symbol...]",
+			"Only print symbols and callees with --call-trace/--call-ret-trace"),
 	OPT_STRING(0, "stop-bt", &symbol_conf.bt_stop_list_str, "symbol[,symbol...]",
 		   "Stop display of callgraph at these symbols"),
 	OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
@@ -3494,7 +3553,8 @@ int cmd_script(int argc, const char **argv)
 	script.session = session;
 	script__setup_sample_type(&script);
 
-	if (output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT)
+	if ((output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT) ||
+	    symbol_conf.graph_function)
 		itrace_synth_opts.thread_stack = true;
 
 	session->itrace_synth_opts = &itrace_synth_opts;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index f25fae4b5743..d726a8a7bb1b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -123,7 +123,8 @@ struct symbol_conf {
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
-			*field_sep;
+			*field_sep,
+			*graph_function;
 	const char	*default_guest_vmlinux_name,
 			*default_guest_kallsyms,
 			*default_guest_modules;
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 07606aa6998d..36c09a9904e6 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -42,6 +42,8 @@ struct thread {
 	void				*addr_space;
 	struct unwind_libunwind_ops	*unwind_libunwind_ops;
 #endif
+	bool			filter;
+	int			filter_entry_depth;
 };
 
 struct machine;
-- 
cgit v1.2.3


From fe57120e18a1f9124ca758c89cc54f91333d1847 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Mon, 24 Sep 2018 10:07:32 -0700
Subject: perf script: Support total cycles count

For 'perf script' brstackinsn also print a running cycles count.  This
makes it easier to calculate cycle deltas for code sections measured
with LBRs.

% perf record -b -a sleep 1
% perf script -F +brstackinsn
...
        00007f73ecc41083        insn: 74 06                     # PRED 9 cycles [17] 1.11 IPC
        00007f73ecc4108b        insn: a8 10
        00007f73ecc4108d        insn: 74 71                     # PRED 1 cycles [18] 1.00 IPC
        00007f73ecc41100        insn: 48 8b 46 10
        00007f73ecc41104        insn: 4c 8b 38
        00007f73ecc41107        insn: 4d 85 ff
        00007f73ecc4110a        insn: 0f 84 b0 00 00 00
        00007f73ecc41110        insn: 83 43 58 01
        00007f73ecc41114        insn: 48 89 df
        00007f73ecc41117        insn: e8 94 73 04 00            # PRED 6 cycles [24] 1.00 IPC

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Link: http://lkml.kernel.org/r/20180924170732.GA28040@tassilo.jf.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9d2249ea75e3..b5bc85bd0bbe 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -913,7 +913,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end,
 
 static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 			    struct perf_insn *x, u8 *inbuf, int len,
-			    int insn, FILE *fp)
+			    int insn, FILE *fp, int *total_cycles)
 {
 	int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t#%s%s%s%s", ip,
 			      dump_insn(x, ip, inbuf, len, NULL),
@@ -922,7 +922,8 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 			      en->flags.in_tx ? " INTX" : "",
 			      en->flags.abort ? " ABORT" : "");
 	if (en->flags.cycles) {
-		printed += fprintf(fp, " %d cycles", en->flags.cycles);
+		*total_cycles += en->flags.cycles;
+		printed += fprintf(fp, " %d cycles [%d]", en->flags.cycles, *total_cycles);
 		if (insn)
 			printed += fprintf(fp, " %.2f IPC", (float)insn / en->flags.cycles);
 	}
@@ -979,6 +980,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 	u8 buffer[MAXBB];
 	unsigned off;
 	struct symbol *lastsym = NULL;
+	int total_cycles = 0;
 
 	if (!(br && br->nr))
 		return 0;
@@ -999,7 +1001,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 		printed += ip__fprintf_sym(br->entries[nr - 1].from, thread,
 					   x.cpumode, x.cpu, &lastsym, attr, fp);
 		printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
-					    &x, buffer, len, 0, fp);
+					    &x, buffer, len, 0, fp, &total_cycles);
 	}
 
 	/* Print all blocks */
@@ -1027,7 +1029,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 
 			printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
 			if (ip == end) {
-				printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp);
+				printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp,
+							    &total_cycles);
 				break;
 			} else {
 				printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip,
-- 
cgit v1.2.3


From 9d954f9519707bc0af29ead8b1dedc660306da1b Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:12:55 +0900
Subject: selftests/ftrace: Add --stop-fail hidden option for debug

Add --stop-fail option for debugging the ftracetest.

With this option, ftracetest stops right after a testcase
fails instead of finish running all testcases.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/ftracetest | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index f9a9d424c980..c9c7fa8dc440 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -69,6 +69,10 @@ parse_opts() { # opts
       DEBUG=1
       shift 1
     ;;
+    --stop-fail)
+      STOP_FAILURE=1
+      shift 1
+    ;;
     --fail-unsupported)
       UNSUPPORTED_RESULT=1
       shift 1
@@ -117,6 +121,7 @@ KEEP_LOG=0
 DEBUG=0
 VERBOSE=0
 UNSUPPORTED_RESULT=0
+STOP_FAILURE=0
 # Parse command-line options
 parse_opts $*
 
@@ -304,6 +309,10 @@ run_test() { # testfile
 # Main loop
 for t in $TEST_CASES; do
   run_test $t
+  if [ $STOP_FAILURE -ne 0 -a $TOTAL_RESULT -ne 0 ]; then
+    echo "A failure detected. Stop test."
+    exit 1
+  fi
 done
 
 # Test on instance loop
@@ -315,6 +324,10 @@ for t in $TEST_CASES; do
   run_test $t
   rmdir $TRACING_DIR
   TRACING_DIR=$SAVED_TRACING_DIR
+  if [ $STOP_FAILURE -ne 0 -a $TOTAL_RESULT -ne 0 ]; then
+    echo "A failure detected. Stop test."
+    exit 1
+  fi
 done
 
 prlog ""
-- 
cgit v1.2.3


From 5d1c6580d616dfc864ffdec587e645e50a21c072 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:13:23 +0900
Subject: selftests/ftrace: Add --console hidden option

Add --console hidden option for debug test cases.

This option allows to put "sh" or something else
when the test case hits a bug.

For example, if you find a testcase which doesn't
pass, you can insert sh for interactive debug as below

  -----
  #!/bin/sh
  # description: sample test case

  good-command
  suspicious-wrong-command
  sh # <- add this for interactive debug
  -----

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/ftracetest | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index c9c7fa8dc440..8debd37038e4 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -60,11 +60,21 @@ parse_opts() { # opts
       shift 1
     ;;
     --verbose|-v|-vv|-vvv)
+      if [ $VERBOSE -eq -1 ]; then
+	usage "--console can not use with --verbose"
+      fi
       VERBOSE=$((VERBOSE + 1))
       [ $1 = '-vv' ] && VERBOSE=$((VERBOSE + 1))
       [ $1 = '-vvv' ] && VERBOSE=$((VERBOSE + 2))
       shift 1
     ;;
+    --console)
+      if [ $VERBOSE -ne 0 ]; then
+	usage "--console can not use with --verbose"
+      fi
+      VERBOSE=-1
+      shift 1
+    ;;
     --debug|-d)
       DEBUG=1
       shift 1
@@ -283,7 +293,9 @@ run_test() { # testfile
   testcase $1
   echo "execute$INSTANCE: "$1 > $testlog
   SIG_RESULT=0
-  if [ -z "$LOG_FILE" ]; then
+  if [ $VERBOSE -eq -1 ]; then
+    __run_test $1
+  elif [ -z "$LOG_FILE" ]; then
     __run_test $1 2>&1
   elif [ $VERBOSE -ge 3 ]; then
     __run_test $1 | tee -a $testlog 2>&1
-- 
cgit v1.2.3


From 7d0abba4293e555a5b1a6ea060cddd05f4ee357f Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:13:51 +0900
Subject: selftests/ftrace: Add case number prefix to logfile

Add a case number prefix to each logfile. This makes
it easier to find which logfile is corresponding
to which failure.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/ftracetest | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index 8debd37038e4..3ca596255eff 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -284,13 +284,13 @@ __run_test() { # testfile
 # Run one test case
 run_test() { # testfile
   local testname=`basename $1`
+  testcase $1
   if [ ! -z "$LOG_FILE" ] ; then
-    local testlog=`mktemp $LOG_DIR/${testname}-log.XXXXXX`
+    local testlog=`mktemp $LOG_DIR/${CASENO}-${testname}-log.XXXXXX`
   else
     local testlog=/proc/self/fd/1
   fi
   export TMPDIR=`mktemp -d /tmp/ftracetest-dir.XXXXXX`
-  testcase $1
   echo "execute$INSTANCE: "$1 > $testlog
   SIG_RESULT=0
   if [ $VERBOSE -eq -1 ]; then
-- 
cgit v1.2.3


From 7590472e78c8fbe1383aba30450655fd6415fa7b Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:14:19 +0900
Subject: selftests/ftrace: More initialize features in initialize_ftrace

Clear pid filter, synthetic_events, snapshots,
ftrace filter, and trace log in initialize_ftrace(),
since those are used in test cases.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/test.d/functions | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions
index e4645d5e3126..b2bfa4dd43f7 100644
--- a/tools/testing/selftests/ftrace/test.d/functions
+++ b/tools/testing/selftests/ftrace/test.d/functions
@@ -89,12 +89,17 @@ initialize_ftrace() { # Reset ftrace to initial-state
     reset_tracer
     reset_trigger
     reset_events_filter
+    reset_ftrace_filter
     disable_events
     echo > set_event_pid	# event tracer is always on
+    echo > set_ftrace_pid
     [ -f set_ftrace_filter ] && echo | tee set_ftrace_*
     [ -f set_graph_function ] && echo | tee set_graph_*
     [ -f stack_trace_filter ] && echo > stack_trace_filter
     [ -f kprobe_events ] && echo > kprobe_events
     [ -f uprobe_events ] && echo > uprobe_events
+    [ -f synthetic_events ] && echo > synthetic_events
+    [ -f snapshot ] && echo 0 > snapshot
+    clear_trace
     enable_tracing
 }
-- 
cgit v1.2.3


From 3a96a9d0a4e985e80280357393d86ff4401eeff7 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:14:48 +0900
Subject: selftests/ftrace: Add SPDX License Identifier to template

Add SPDX License Identifier line to template file so
that someone who makes new testcase from the template
does not forgot it.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/test.d/template | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/template b/tools/testing/selftests/ftrace/test.d/template
index 5c39ceb18a0d..799da7e0b3c9 100644
--- a/tools/testing/selftests/ftrace/test.d/template
+++ b/tools/testing/selftests/ftrace/test.d/template
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL2.0
 # description: %HERE DESCRIBE WHAT THIS DOES%
 # you have to add ".tc" extention for your testcase file
 # Note that all tests are run with "errexit" option.
-- 
cgit v1.2.3


From 9768cc46d39a029f7da47beea449d023b377103d Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:15:16 +0900
Subject: selftests/ftrace: Cleanup ftrace after running test

Cleanup ftrace by initialize_ftrace() after running
all test cases. This means we also don't need cleanup
ftrace on each test case, except for some special
options.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/ftracetest | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index 3ca596255eff..5c71d58febb2 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -341,6 +341,7 @@ for t in $TEST_CASES; do
     exit 1
   fi
 done
+(cd $TRACING_DIR; initialize_ftrace) # for cleanup
 
 prlog ""
 prlog "# of passed: " `echo $PASSED_CASES | wc -w`
-- 
cgit v1.2.3


From e527c47081c7e2795ffc3201809de9545cc25830 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:15:44 +0900
Subject: selftests/ftrace: Remove unneeded per-test init/cleanup ftrace

Since ftracetest framework calls initialize_ftrace() right before
each test and after all tests, we don't need to init/cleanup
ftrace for each test case.
Just remove such unneeded init/cleanup code because it can
increase logfile size.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../selftests/ftrace/test.d/event/event-enable.tc        |  6 ------
 tools/testing/selftests/ftrace/test.d/event/event-pid.tc |  3 +--
 .../selftests/ftrace/test.d/event/subsystem-enable.tc    |  6 ------
 .../selftests/ftrace/test.d/event/toplevel-enable.tc     |  6 ------
 .../ftrace/test.d/ftrace/fgraph-filter-stack.tc          |  4 ----
 .../selftests/ftrace/test.d/ftrace/fgraph-filter.tc      |  9 ---------
 .../selftests/ftrace/test.d/ftrace/func-filter-pid.tc    |  6 ------
 .../ftrace/test.d/ftrace/func_event_triggers.tc          |  3 ---
 .../selftests/ftrace/test.d/ftrace/func_profiler.tc      |  4 ----
 .../ftrace/test.d/ftrace/func_set_ftrace_file.tc         | 13 -------------
 .../ftrace/test.d/ftrace/func_traceonoff_triggers.tc     | 11 -----------
 .../selftests/ftrace/test.d/kprobe/add_and_remove.tc     |  3 ---
 .../testing/selftests/ftrace/test.d/kprobe/busy_check.tc |  3 ---
 .../selftests/ftrace/test.d/kprobe/kprobe_args.tc        |  2 --
 .../selftests/ftrace/test.d/kprobe/kprobe_args_string.tc |  5 -----
 .../selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc |  5 -----
 .../selftests/ftrace/test.d/kprobe/kprobe_args_type.tc   |  4 ----
 .../selftests/ftrace/test.d/kprobe/kprobe_eventname.tc   |  5 -----
 .../selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc      |  9 ---------
 .../selftests/ftrace/test.d/kprobe/kprobe_module.tc      |  5 -----
 .../selftests/ftrace/test.d/kprobe/kretprobe_args.tc     |  2 --
 .../ftrace/test.d/kprobe/kretprobe_maxactive.tc          |  4 ----
 .../selftests/ftrace/test.d/kprobe/multiple_kprobes.tc   |  5 -----
 .../testing/selftests/ftrace/test.d/kprobe/probepoint.tc |  4 ----
 .../inter-event/trigger-extended-error-support.tc        | 12 ------------
 .../inter-event/trigger-field-variable-support.tc        | 13 -------------
 .../inter-event/trigger-inter-event-combined-hist.tc     | 13 -------------
 .../trigger/inter-event/trigger-multi-actions-accept.tc  | 14 --------------
 .../trigger/inter-event/trigger-onmatch-action-hist.tc   | 13 -------------
 .../inter-event/trigger-onmatch-onmax-action-hist.tc     | 13 -------------
 .../trigger/inter-event/trigger-onmax-action-hist.tc     | 13 -------------
 .../inter-event/trigger-synthetic-event-createremove.tc  | 12 ------------
 .../ftrace/test.d/trigger/trigger-eventonoff.tc          | 12 ------------
 .../selftests/ftrace/test.d/trigger/trigger-filter.tc    | 14 --------------
 .../selftests/ftrace/test.d/trigger/trigger-hist-mod.tc  | 12 ------------
 .../selftests/ftrace/test.d/trigger/trigger-hist.tc      | 12 ------------
 .../selftests/ftrace/test.d/trigger/trigger-multihist.tc | 16 ----------------
 .../selftests/ftrace/test.d/trigger/trigger-snapshot.tc  | 12 ------------
 .../ftrace/test.d/trigger/trigger-stacktrace.tc          | 12 ------------
 .../ftrace/test.d/trigger/trigger-trace-marker-hist.tc   | 11 -----------
 .../test.d/trigger/trigger-trace-marker-snapshot.tc      | 12 ------------
 .../trigger/trigger-trace-marker-synthetic-kernel.tc     | 12 ------------
 .../test.d/trigger/trigger-trace-marker-synthetic.tc     | 12 ------------
 .../ftrace/test.d/trigger/trigger-traceonoff.tc          | 12 ------------
 44 files changed, 1 insertion(+), 378 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
index 9daf034186f5..386dbddbdc11 100644
--- a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
@@ -9,7 +9,6 @@ do_reset() {
 }
 
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -23,9 +22,6 @@ if [ ! -f set_event -o ! -d events/sched ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 echo 'sched:sched_switch' > set_event
 
 yield
@@ -57,6 +53,4 @@ if [ $count -ne 0 ]; then
     fail "sched_switch events should not be recorded"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
index 132478b305c2..6dbf67544fde 100644
--- a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
@@ -30,8 +30,7 @@ if [ ! -f set_event_pid ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
+echo 0 > options/event-fork
 
 echo 1 > events/sched/sched_switch/enable
 
diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
index 6a37a8642ee6..10eb17f161b7 100644
--- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
@@ -9,7 +9,6 @@ do_reset() {
 }
 
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -23,9 +22,6 @@ if [ ! -f set_event -o ! -d events/sched ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 echo 'sched:*' > set_event
 
 yield
@@ -57,6 +53,4 @@ if [ $count -ne 0 ]; then
     fail "any of scheduler events should not be recorded"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
index 4e9b6e2c0219..8d55a233c1a4 100644
--- a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
@@ -8,7 +8,6 @@ do_reset() {
 }
 
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -22,9 +21,6 @@ if [ ! -f available_events -o ! -f set_event -o ! -d events ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 echo '*:*' > set_event
 
 yield
@@ -60,6 +56,4 @@ if [ $count -ne 0 ]; then
     fail "any of events should not be recorded"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
index 1aec99d108eb..aefab0c66d54 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
@@ -16,13 +16,9 @@ if [ ! -f set_ftrace_filter ]; then
 fi
 
 do_reset() {
-    reset_tracer
     if [ -e /proc/sys/kernel/stack_tracer_enabled ]; then
 	    echo 0 > /proc/sys/kernel/stack_tracer_enabled
     fi
-    enable_tracing
-    clear_trace
-    echo > set_ftrace_filter
 }
 
 fail() { # msg
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
index 9f8d27ca39cf..c8a5209f2119 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
@@ -9,14 +9,7 @@ if ! grep -q function_graph available_tracers; then
     exit_unsupported
 fi
 
-do_reset() {
-    reset_tracer
-    enable_tracing
-    clear_trace
-}
-
 fail() { # msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -48,6 +41,4 @@ if [ $count -eq 0 ]; then
     fail "No schedule traces found?"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
index 524ce24b3c22..970903cb7834 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
@@ -35,12 +35,6 @@ if [ $do_function_fork -eq 1 ]; then
 fi
 
 do_reset() {
-    reset_tracer
-    clear_trace
-    enable_tracing
-    echo > set_ftrace_filter
-    echo > set_ftrace_pid
-
     if [ $do_function_fork -eq 0 ]; then
 	return
     fi
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
index 6fed4cf2db81..ca2ffd7957f9 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
@@ -25,15 +25,12 @@ do_reset() {
 }
 
 fail() { # mesg
-    do_reset
     echo $1
     exit_fail
 }
 
 SLEEP_TIME=".1"
 
-do_reset
-
 echo "Testing function probes with events:"
 
 EVENT="sched:sched_switch"
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
index b2d5a8febfe8..dfbae637c60c 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
@@ -29,8 +29,6 @@ if [ ! -f function_profile_enabled ]; then
 fi
 
 fail() { # mesg
-    reset_tracer
-    echo > set_ftrace_filter
     echo $1
     exit_fail
 }
@@ -76,6 +74,4 @@ if ! grep -v -e '^#' -e 'schedule' trace > /dev/null; then
 	fail "no other functions besides schedule was found"
 fi
 
-reset_tracer
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
index 68e7a48f5828..51f6e6146bd9 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
@@ -15,22 +15,11 @@ if [ ! -f set_ftrace_filter ]; then
     exit_unsupported
 fi
 
-do_reset() {
-    reset_tracer
-    reset_ftrace_filter
-    disable_events
-    clear_trace
-    enable_tracing
-}
-
 fail() { # mesg
-    do_reset
     echo $1
     exit_fail
 }
 
-do_reset
-
 FILTER=set_ftrace_filter
 FUNC1="schedule"
 FUNC2="do_softirq"
@@ -165,6 +154,4 @@ test_actual
 rm $TMPDIR/expected
 rm $TMPDIR/actual
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
index f6d9ac73268a..0c04282d33dd 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
@@ -16,24 +16,13 @@ if [ ! -f set_ftrace_filter ]; then
     exit_unsupported
 fi
 
-do_reset() {
-    reset_ftrace_filter
-    reset_tracer
-    disable_events
-    clear_trace
-    enable_tracing
-}
-
 fail() { # mesg
-    do_reset
     echo $1
     exit_fail
 }
 
 SLEEP_TIME=".1"
 
-do_reset
-
 echo "Testing function probes with enabling disabling tracing:"
 
 cnt_trace() {
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
index 4604d2103c89..bb1eb5a7c64e 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
@@ -4,10 +4,7 @@
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
-echo 0 > events/enable
-echo > kprobe_events
 echo p:myevent _do_fork > kprobe_events
 grep myevent kprobe_events
 test -d events/kprobes/myevent
 echo > kprobe_events
-clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
index bbc443a9190c..442c1a8c5edf 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
@@ -4,12 +4,9 @@
 
 [ -f kprobe_events ] || exit_unsupported
 
-echo 0 > events/enable
-echo > kprobe_events
 echo p:myevent _do_fork > kprobe_events
 test -d events/kprobes/myevent
 echo 1 > events/kprobes/myevent/enable
 echo > kprobe_events && exit_fail # this must fail
 echo 0 > events/kprobes/myevent/enable
 echo > kprobe_events # this must succeed
-clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
index 8b43c6804fc3..9578535ccd67 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
@@ -4,8 +4,6 @@
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
-echo 0 > events/enable
-echo > kprobe_events
 echo 'p:testprobe _do_fork $stack $stack0 +0($stack)' > kprobe_events
 grep testprobe kprobe_events
 test -d events/kprobes/testprobe
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
index 1ad70cdaf442..46e7744f8358 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
@@ -4,9 +4,6 @@
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
-echo 0 > events/enable
-echo > kprobe_events
-
 case `uname -m` in
 x86_64)
   ARG1=%di
@@ -44,5 +41,3 @@ echo 1 > events/kprobes/testprobe/enable
 echo "p:test _do_fork" >> kprobe_events
 grep -qe "testprobe.* arg1=\"test\" arg2=\"test\"" trace
 
-echo 0 > events/enable
-echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
index d026ff4e562f..d783a8ce0692 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
@@ -6,9 +6,6 @@
 
 grep "x8/16/32/64" README > /dev/null || exit_unsupported # version issue
 
-echo 0 > events/enable
-echo > kprobe_events
-
 PROBEFUNC="vfs_read"
 GOODREG=
 BADREG=
@@ -100,5 +97,3 @@ test_badarg "${GOODREG}::${GOODTYPE}" "${GOODREG}:${BADTYPE}" \
 
 test_goodarg "\$comm:string" "+0(\$stack):string"
 test_badarg "\$comm:x64" "\$stack:string" "${GOODREG}:string"
-
-echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
index 2a1755bfc290..37443dd23d15 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
@@ -6,10 +6,6 @@
 
 grep "x8/16/32/64" README > /dev/null || exit_unsupported # version issue
 
-echo 0 > events/enable
-echo > kprobe_events
-enable_tracing
-
 echo 'p:testprobe _do_fork $stack0:s32 $stack0:u32 $stack0:x32 $stack0:b8@4/32' > kprobe_events
 grep testprobe kprobe_events
 test -d events/kprobes/testprobe
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc
index 2724a1068cb1..3fb70e01b1fe 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc
@@ -4,9 +4,6 @@
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
-disable_events
-echo > kprobe_events
-
 :;: "Add an event on function without name" ;:
 
 FUNC=`grep " [tT] .*vfs_read$" /proc/kallsyms | tail -n 1 | cut -f 3 -d " "`
@@ -33,5 +30,3 @@ echo "p $FUNC" > kprobe_events
 EVENT=`grep $FUNC kprobe_events | cut -f 1 -d " " | cut -f 2 -d:`
 [ "x" != "x$EVENT" ] || exit_failure
 test -d events/$EVENT || exit_failure
-
-echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
index cc4cac0e60f2..492426e95e09 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
@@ -8,8 +8,6 @@ grep function available_tracers || exit_unsupported # this is configurable
 # prepare
 echo nop > current_tracer
 echo _do_fork > set_ftrace_filter
-echo 0 > events/enable
-echo > kprobe_events
 echo 'p:testprobe _do_fork' > kprobe_events
 
 # kprobe on / ftrace off
@@ -47,10 +45,3 @@ echo > trace
 ( echo "forked")
 grep testprobe trace
 ! grep '_do_fork <-' trace
-
-# cleanup
-echo nop > current_tracer
-echo > set_ftrace_filter
-echo 0 > events/kprobes/testprobe/enable
-echo > kprobe_events
-echo > trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc
index 1e9f75f7a30f..ec6c5fffef1e 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc
@@ -4,9 +4,6 @@
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
-disable_events
-echo > kprobe_events
-
 :;: "Add an event on a module function without specifying event name" ;:
 
 MOD=`lsmod | head -n 2 | tail -n 1 | cut -f1 -d" "`
@@ -25,5 +22,3 @@ test -d events/kprobes/event1 || exit_failure
 
 echo "p:kprobes1/event1 $MOD:$FUNC" > kprobe_events
 test -d events/kprobes1/event1 || exit_failure
-
-echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
index 321954683aaa..4c6b21e30b02 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
@@ -4,8 +4,6 @@
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
-echo 0 > events/enable
-echo > kprobe_events
 echo 'r:testprobe2 _do_fork $retval' > kprobe_events
 grep testprobe2 kprobe_events
 test -d events/kprobes/testprobe2
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc
index 7c0290684c43..8e05b178519a 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc
@@ -5,8 +5,6 @@
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 grep -q 'r\[maxactive\]' README || exit_unsupported # this is older version
 
-echo > kprobe_events
-
 # Test if we successfully reject unknown messages
 if echo 'a:myprobeaccept inet_csk_accept' > kprobe_events; then false; else true; fi
 
@@ -37,5 +35,3 @@ echo > kprobe_events
 echo 'r10 inet_csk_accept' > kprobe_events
 grep inet_csk_accept kprobe_events
 echo > kprobe_events
-
-clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
index ce361b9d62cf..5862eee91e1d 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc
@@ -12,11 +12,6 @@ case `uname -m` in
   *) OFFS=0;;
 esac
 
-if [ -d events/kprobes ]; then
-  echo 0 > events/kprobes/enable
-  echo > kprobe_events
-fi
-
 N=0
 echo "Setup up kprobes on first available 256 text symbols"
 grep -i " t " /proc/kallsyms | cut -f3 -d" " | grep -v .*\\..* | \
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc b/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc
index 519d2763f5d2..a902aa0aaabc 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc
@@ -30,8 +30,6 @@ if [ `printf "%x" -1 | wc -c` != 9 ]; then
   UINT_TEST=yes
 fi
 
-echo 0 > events/enable
-echo > kprobe_events
 echo "p:testprobe ${TARGET_FUNC}" > kprobe_events
 echo "p:testprobe ${TARGET}" > kprobe_events
 echo "p:testprobe ${TARGET_FUNC}${NEXT}" > kprobe_events
@@ -39,5 +37,3 @@ echo "p:testprobe ${TARGET_FUNC}${NEXT}" > kprobe_events
 if [ "${UINT_TEST}" = yes ]; then
 ! echo "p:testprobe ${TARGET_FUNC}${OVERFLOW}" > kprobe_events
 fi
-echo > kprobe_events
-clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc
index 2aabab363cfb..401104344593 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc
@@ -2,14 +2,7 @@
 # description: event trigger - test extended error support
 
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -24,9 +17,6 @@ if [ ! -f synthetic_events ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 echo "Test extended error support"
 echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger
 ! echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_wakeup/trigger 2> /dev/null
@@ -34,6 +24,4 @@ if ! grep -q "ERROR:" events/sched/sched_wakeup/hist; then
     fail "Failed to generate extended error in histogram"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
index 7fd5b4a8f060..575af23df04e 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
@@ -1,14 +1,7 @@
 #!/bin/sh
 # description: event trigger - test field variable support
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -23,10 +16,6 @@ if [ ! -f synthetic_events ]; then
     exit_unsupported
 fi
 
-clear_synthetic_events
-reset_tracer
-do_reset
-
 echo "Test field variable support"
 
 echo 'wakeup_latency u64 lat; pid_t pid; int prio; char comm[16]' > synthetic_events
@@ -49,6 +38,4 @@ if grep -q "synthetic_prio=prio" events/sched/sched_waking/hist; then
     fail "Failed to remove histogram with field variable"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
index c93dbe38b5df..92aef26e2631 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
@@ -1,14 +1,7 @@
 #!/bin/sh
 # description: event trigger - test inter-event combined histogram trigger
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -23,10 +16,6 @@ if [ ! -f synthetic_events ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-clear_synthetic_events
-
 echo "Test create synthetic event"
 
 echo 'waking_latency  u64 lat pid_t pid' > synthetic_events
@@ -53,6 +42,4 @@ if ! grep -q "pid:" events/synthetic/waking+wakeup_latency/hist; then
     fail "Failed to create combined histogram"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc
index c193dce611a2..4ddc546771b5 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc
@@ -1,15 +1,7 @@
 #!/bin/sh
 # description: event trigger - test multiple actions on hist trigger
 
-
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -24,10 +16,6 @@ if [ ! -f synthetic_events ]; then
     exit_unsupported
 fi
 
-clear_synthetic_events
-reset_tracer
-do_reset
-
 echo "Test multiple actions on hist trigger"
 echo 'wakeup_latency u64 lat; pid_t pid' >> synthetic_events
 TRIGGER1=events/sched/sched_wakeup/trigger
@@ -39,6 +27,4 @@ echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_
 echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_switch.$wakeup_lat,prev_pid) if next_comm=="cyclictest"' >> $TRIGGER2
 echo 'hist:keys=next_pid if next_comm=="cyclictest"' >> $TRIGGER2
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
index e84e7d048566..1ef5dd4521f0 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
@@ -1,14 +1,7 @@
 #!/bin/sh
 # description: event trigger - test inter-event histogram trigger onmatch action
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -23,10 +16,6 @@ if [ ! -f synthetic_events ]; then
     exit_unsupported
 fi
 
-clear_synthetic_events
-reset_tracer
-do_reset
-
 echo "Test create synthetic event"
 
 echo 'wakeup_latency  u64 lat pid_t pid char comm[16]' > synthetic_events
@@ -45,6 +34,4 @@ if ! grep -q "ping" events/synthetic/wakeup_latency/hist; then
     fail "Failed to create onmatch action inter-event histogram"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
index 7907d8aacde3..7234683ee5e5 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
@@ -1,14 +1,7 @@
 #!/bin/sh
 # description: event trigger - test inter-event histogram trigger onmatch-onmax action
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -23,10 +16,6 @@ if [ ! -f synthetic_events ]; then
     exit_unsupported
 fi
 
-clear_synthetic_events
-reset_tracer
-do_reset
-
 echo "Test create synthetic event"
 
 echo 'wakeup_latency  u64 lat pid_t pid char comm[16]' > synthetic_events
@@ -45,6 +34,4 @@ if [ ! grep -q "ping" events/synthetic/wakeup_latency/hist -o ! grep -q "max:" e
     fail "Failed to create onmatch-onmax action inter-event histogram"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
index 38b7ed6242b2..55b9630a1d70 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
@@ -1,14 +1,7 @@
 #!/bin/sh
 # description: event trigger - test inter-event histogram trigger onmax action
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -23,10 +16,6 @@ if [ ! -f synthetic_events ]; then
     exit_unsupported
 fi
 
-clear_synthetic_events
-reset_tracer
-do_reset
-
 echo "Test create synthetic event"
 
 echo 'wakeup_latency  u64 lat pid_t pid char comm[16]' > synthetic_events
@@ -43,6 +32,4 @@ if ! grep -q "max:" events/sched/sched_switch/hist; then
     fail "Failed to create onmax action inter-event histogram"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc
index cef11377dcbd..8d647fb572dd 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc
@@ -1,13 +1,7 @@
 #!/bin/sh
 # description: event trigger - test synthetic event create remove
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
 
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -22,10 +16,6 @@ if [ ! -f synthetic_events ]; then
     exit_unsupported
 fi
 
-clear_synthetic_events
-reset_tracer
-do_reset
-
 echo "Test create synthetic event"
 
 echo 'wakeup_latency  u64 lat pid_t pid char comm[16]' > synthetic_events
@@ -49,6 +39,4 @@ if [ -d events/synthetic/wakeup_latency ]; then
     fail "Failed to delete wakeup_latency synthetic event"
 fi
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc
index 28cc355a3a7b..eddb51e1fbf7 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc
@@ -3,14 +3,7 @@
 # description: event trigger - test event enable/disable trigger
 # flags: instance
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -25,9 +18,6 @@ if [ ! -f events/sched/sched_process_fork/trigger ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 FEATURE=`grep enable_event events/sched/sched_process_fork/trigger`
 if [ -z "$FEATURE" ]; then
     echo "event enable/disable trigger is not supported"
@@ -61,6 +51,4 @@ echo 'enable_event:sched:sched_switch' > events/sched/sched_process_fork/trigger
 ! echo 'enable_event:sched:sched_switch' > events/sched/sched_process_fork/trigger
 ! echo 'disable_event:sched:sched_switch' > events/sched/sched_process_fork/trigger
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc
index a48e23eb8a8b..2dcc2296ebdd 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc
@@ -3,14 +3,7 @@
 # description: event trigger - test trigger filter
 # flags: instance
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -25,9 +18,6 @@ if [ ! -f events/sched/sched_process_fork/trigger ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 echo "Test trigger filter"
 echo 1 > tracing_on
 echo 'traceoff if child_pid == 0' > events/sched/sched_process_fork/trigger
@@ -54,8 +44,4 @@ echo '!traceoff' > events/sched/sched_process_fork/trigger
 echo 'traceoff if parent_pid >= 0 || child_pid >= 0' > events/sched/sched_process_fork/trigger
 echo '!traceoff' > events/sched/sched_process_fork/trigger
 
-
-
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
index 8da80efc44d8..fab4431639d3 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc
@@ -3,14 +3,7 @@
 # description: event trigger - test histogram modifiers
 # flags: instance
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -30,9 +23,6 @@ if [ ! -f events/sched/sched_process_fork/hist ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 echo "Test histogram with execname modifier"
 
 echo 'hist:keys=common_pid.execname' > events/sched/sched_process_fork/trigger
@@ -71,6 +61,4 @@ for i in `seq 1 10` ; do ( echo "forked" > /dev/null); done
 grep 'bytes_req: ~ 2^[0-9]*' events/kmem/kmalloc/hist > /dev/null || \
     fail "log2 modifier on kmem/kmalloc did not work"
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
index 449fe9ff91a2..177e8d4c4744 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc
@@ -3,14 +3,7 @@
 # description: event trigger - test histogram trigger
 # flags: instance
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -30,9 +23,6 @@ if [ ! -f events/sched/sched_process_fork/hist ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 echo "Test histogram basic tigger"
 
 echo 'hist:keys=parent_pid:vals=child_pid' > events/sched/sched_process_fork/trigger
@@ -79,6 +69,4 @@ check_inc `grep -o "child_pid:[[:space:]]*[[:digit:]]*" \
     events/sched/sched_process_fork/hist | cut -d: -f2 ` ||
     fail "sort param on sched_process_fork did not work"
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
index c5ef8b9d02b3..18fdaab9f570 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc
@@ -3,14 +3,7 @@
 # description: event trigger - test multiple histogram triggers
 # flags: instance
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -30,11 +23,6 @@ if [ ! -f events/sched/sched_process_fork/hist ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
-reset_trigger
-
 echo "Test histogram multiple tiggers"
 
 echo 'hist:keys=parent_pid:vals=child_pid' > events/sched/sched_process_fork/trigger
@@ -67,8 +55,4 @@ grep test_hist events/sched/sched_process_exit/hist > /dev/null || \
 diffs=`diff events/sched/sched_process_exit/hist events/sched/sched_process_fork/hist | wc -l`
 test $diffs -eq 0 || fail "Same name histograms are not same"
 
-reset_trigger
-
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc
index ed38f0050d77..7717c0a09686 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc
@@ -2,14 +2,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # description: event trigger - test snapshot-trigger
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -29,9 +22,6 @@ if [ ! -f snapshot ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 FEATURE=`grep snapshot events/sched/sched_process_fork/trigger`
 if [ -z "$FEATURE" ]; then
     echo "snapshot trigger is not supported"
@@ -57,6 +47,4 @@ echo "Test snapshot semantic errors"
 echo "snapshot" > events/sched/sched_process_fork/trigger
 ! echo "snapshot" > events/sched/sched_process_fork/trigger
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc
index 3121d795a868..398c05c4d2a7 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-stacktrace.tc
@@ -2,14 +2,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # description: event trigger - test stacktrace-trigger
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -24,9 +17,6 @@ if [ ! -f events/sched/sched_process_fork/trigger ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 FEATURE=`grep stacktrace events/sched/sched_process_fork/trigger`
 if [ -z "$FEATURE" ]; then
     echo "stacktrace trigger is not supported"
@@ -49,6 +39,4 @@ echo "Test stacktrace semantic errors"
 echo "stacktrace" > events/sched/sched_process_fork/trigger
 ! echo "stacktrace" > events/sched/sched_process_fork/trigger
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-hist.tc
index 2acbfe2c0c0c..ab6bedb25736 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-hist.tc
@@ -3,14 +3,7 @@
 # description: trace_marker trigger - test histogram trigger
 # flags: instance
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -35,8 +28,6 @@ if [ ! -f events/ftrace/print/hist ]; then
     exit_unsupported
 fi
 
-do_reset
-
 echo "Test histogram trace_marker tigger"
 
 echo 'hist:keys=common_pid' > events/ftrace/print/trigger
@@ -44,6 +35,4 @@ for i in `seq 1 10` ; do echo "hello" > trace_marker; done
 grep 'hitcount: *10$' events/ftrace/print/hist > /dev/null || \
     fail "hist trigger did not trigger correct times on trace_marker"
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc
index 6748e8cb42d0..79ce7d51350b 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc
@@ -3,15 +3,7 @@
 # description: trace_marker trigger - test snapshot trigger
 # flags: instance
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    echo 0 > snapshot
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -54,8 +46,6 @@ test_trace() {
     done
 }
 
-do_reset
-
 echo "Test snapshot trace_marker tigger"
 
 echo 'snapshot' > events/ftrace/print/trigger
@@ -69,6 +59,4 @@ for i in `seq 1 10` ; do echo "hello >$i<" > trace_marker; done
 test_trace trace 1
 test_trace snapshot 2
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic-kernel.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic-kernel.tc
index 0a69c5d1cda8..18b4d1c2807e 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic-kernel.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic-kernel.tc
@@ -3,15 +3,7 @@
 # description: trace_marker trigger - test histogram with synthetic event against kernel event
 # flags:
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    echo > synthetic_events
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -46,8 +38,6 @@ if [ ! -f events/ftrace/print/hist ]; then
     exit_unsupported
 fi
 
-do_reset
-
 echo "Test histogram kernel event to trace_marker latency histogram trigger"
 
 echo 'latency u64 lat' > synthetic_events
@@ -63,6 +53,4 @@ grep 'hitcount: *1$' events/ftrace/print/hist > /dev/null || \
 grep 'hitcount: *1$' events/synthetic/latency/hist > /dev/null || \
     fail "hist trigger did not trigger "
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic.tc
index 3666dd6ab02a..dd262d6d0db6 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic.tc
@@ -3,15 +3,7 @@
 # description: trace_marker trigger - test histogram with synthetic event
 # flags:
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    echo > synthetic_events
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -41,8 +33,6 @@ if [ ! -f events/ftrace/print/hist ]; then
     exit_unsupported
 fi
 
-do_reset
-
 echo "Test histogram trace_marker to trace_marker latency histogram trigger"
 
 echo 'latency u64 lat' > synthetic_events
@@ -61,6 +51,4 @@ fi
 grep 'hitcount: *1$' events/synthetic/latency/hist > /dev/null || \
     fail "hist trigger did not trigger "
 
-do_reset
-
 exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc
index c59d9eb546da..d5d2dcbc9cab 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-traceonoff.tc
@@ -2,14 +2,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # description: event trigger - test traceon/off trigger
 
-do_reset() {
-    reset_trigger
-    echo > set_event
-    clear_trace
-}
-
 fail() { #msg
-    do_reset
     echo $1
     exit_fail
 }
@@ -24,9 +17,6 @@ if [ ! -f events/sched/sched_process_fork/trigger ]; then
     exit_unsupported
 fi
 
-reset_tracer
-do_reset
-
 echo "Test traceoff trigger"
 echo 1 > tracing_on
 echo 'traceoff' > events/sched/sched_process_fork/trigger
@@ -54,6 +44,4 @@ echo 'traceon' > events/sched/sched_process_fork/trigger
 ! echo 'traceon' > events/sched/sched_process_fork/trigger
 ! echo 'traceoff' > events/sched/sched_process_fork/trigger
 
-do_reset
-
 exit 0
-- 
cgit v1.2.3


From 2452c96e617a0ff6fb2692e55217a3fa57a7322c Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:16:13 +0900
Subject: selftests/ftrace: Fix to test kprobe $comm arg only if available

Test $comm in kprobe-event argument syntax testcase
only if it is supported on the kernel because
$comm has been introduced 4.8 kernel.
So on older stable kernel, it should be skipped.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
index d783a8ce0692..6f0f19953193 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
@@ -75,8 +75,11 @@ test_badarg "\$stackp" "\$stack0+10" "\$stack1-10"
 echo "r ${PROBEFUNC} \$retval" > kprobe_events
 ! echo "p ${PROBEFUNC} \$retval" > kprobe_events
 
+# $comm was introduced in 4.8, older kernels reject it.
+if grep -A1 "fetcharg:" README | grep -q '\$comm' ; then
 : "Comm access"
 test_goodarg "\$comm"
+fi
 
 : "Indirect memory access"
 test_goodarg "+0(${GOODREG})" "-0(${GOODREG})" "+10(\$stack)" \
-- 
cgit v1.2.3


From 72ce3daf92ba4f5bae6e91095d40e67b367c6b2f Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:16:41 +0900
Subject: selftests/ftrace: Fix checkbashisms errors

Fix a test case to make checkbashisms clean.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc  | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc
index 79ce7d51350b..df246e505af7 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc
@@ -39,10 +39,10 @@ test_trace() {
 	fi
 	echo "testing $line for >$x<"
 	match=`echo $line | sed -e "s/>$x<//"`
-	if [ "$line" == "$match" ]; then
+	if [ "$line" = "$match" ]; then
 	    fail "$line does not have >$x< in it"
 	fi
-	let x=$x+2
+	x=$((x+2))
     done
 }
 
-- 
cgit v1.2.3


From cec3adf5f57160d829a033bcb578c3dd0a90c693 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:17:10 +0900
Subject: selftests/ftrace: Use loopback address instead of localhost

Use raw loopback address instead of localhost, because
"localhost" can depend on nsswitch and in some case
we can not resolve the localhost.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/test.d/event/event-enable.tc         | 4 ----
 tools/testing/selftests/ftrace/test.d/event/event-pid.tc            | 4 ----
 tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc     | 4 ----
 tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc      | 4 ----
 tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc     | 4 ----
 tools/testing/selftests/ftrace/test.d/functions                     | 6 ++++++
 .../test.d/trigger/inter-event/trigger-field-variable-support.tc    | 2 +-
 .../test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc | 2 +-
 .../test.d/trigger/inter-event/trigger-onmatch-action-hist.tc       | 3 ++-
 .../test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc | 3 ++-
 .../ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc  | 3 ++-
 11 files changed, 14 insertions(+), 25 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
index 386dbddbdc11..dfb0d5122f7b 100644
--- a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc
@@ -13,10 +13,6 @@ fail() { #msg
     exit_fail
 }
 
-yield() {
-    ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1
-}
-
 if [ ! -f set_event -o ! -d events/sched ]; then
     echo "event tracing is not supported"
     exit_unsupported
diff --git a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
index 6dbf67544fde..e28897738500 100644
--- a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
@@ -16,10 +16,6 @@ fail() { #msg
     exit_fail
 }
 
-yield() {
-    ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1
-}
-
 if [ ! -f set_event -o ! -d events/sched ]; then
     echo "event tracing is not supported"
     exit_unsupported
diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
index 10eb17f161b7..83a8c571e93a 100644
--- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
@@ -13,10 +13,6 @@ fail() { #msg
     exit_fail
 }
 
-yield() {
-    ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1
-}
-
 if [ ! -f set_event -o ! -d events/sched ]; then
     echo "event tracing is not supported"
     exit_unsupported
diff --git a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
index 8d55a233c1a4..84d7bda08d2a 100644
--- a/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/toplevel-enable.tc
@@ -12,10 +12,6 @@ fail() { #msg
     exit_fail
 }
 
-yield() {
-    ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1
-}
-
 if [ ! -f available_events -o ! -f set_event -o ! -d events ]; then
     echo "event tracing is not supported"
     exit_unsupported
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
index 970903cb7834..64cfcc75e3c1 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
@@ -48,10 +48,6 @@ fail() { # msg
     exit_fail
 }
 
-yield() {
-    ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1
-}
-
 do_test() {
     disable_tracing
 
diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions
index b2bfa4dd43f7..7b96e80e6b8a 100644
--- a/tools/testing/selftests/ftrace/test.d/functions
+++ b/tools/testing/selftests/ftrace/test.d/functions
@@ -103,3 +103,9 @@ initialize_ftrace() { # Reset ftrace to initial-state
     clear_trace
     enable_tracing
 }
+
+LOCALHOST=127.0.0.1
+
+yield() {
+    ping $LOCALHOST -c 1 || sleep .001 || usleep 1 || sleep 1
+}
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
index 575af23df04e..f59b2a9a1f22 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
@@ -23,7 +23,7 @@ echo 'hist:keys=comm:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/
 echo 'hist:keys=next_comm:wakeup_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_waking).wakeup_latency($wakeup_lat,next_pid,sched.sched_waking.prio,next_comm) if next_comm=="ping"' > events/sched/sched_switch/trigger
 echo 'hist:keys=pid,prio,comm:vals=lat:sort=pid,prio' > events/synthetic/wakeup_latency/trigger
 
-ping localhost -c 3
+ping $LOCALHOST -c 3
 if ! grep -q "ping" events/synthetic/wakeup_latency/hist; then
     fail "Failed to create inter-event histogram"
 fi
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
index 92aef26e2631..524d9ce361e2 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
@@ -37,7 +37,7 @@ echo 'waking+wakeup_latency u64 lat; pid_t pid' >> synthetic_events
 echo 'hist:keys=pid,lat:sort=pid,lat:ww_lat=$waking_lat+$wakeup_lat:onmatch(synthetic.wakeup_latency).waking+wakeup_latency($ww_lat,pid)' >> events/synthetic/wakeup_latency/trigger
 echo 'hist:keys=pid,lat:sort=pid,lat' >> events/synthetic/waking+wakeup_latency/trigger
 
-ping localhost -c 3
+ping $LOCALHOST -c 3
 if ! grep -q "pid:" events/synthetic/waking+wakeup_latency/hist; then
     fail "Failed to create combined histogram"
 fi
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
index 1ef5dd4521f0..39fb65b0cd9f 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
@@ -29,7 +29,8 @@ echo "Test histogram variables,simple expression support and onmatch action"
 echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger
 echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_wakeup).wakeup_latency($wakeup_lat,next_pid,next_comm) if next_comm=="ping"' > events/sched/sched_switch/trigger
 echo 'hist:keys=comm,pid,lat:wakeup_lat=lat:sort=lat' > events/synthetic/wakeup_latency/trigger
-ping localhost -c 5
+
+ping $LOCALHOST -c 5
 if ! grep -q "ping" events/synthetic/wakeup_latency/hist; then
     fail "Failed to create onmatch action inter-event histogram"
 fi
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
index 7234683ee5e5..81ab3939c96a 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
@@ -29,7 +29,8 @@ echo "Test histogram variables,simple expression support and onmatch-onmax actio
 echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger
 echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_wakeup).wakeup_latency($wakeup_lat,next_pid,next_comm):onmax($wakeup_lat).save(next_comm,prev_pid,prev_prio,prev_comm) if next_comm=="ping"' >> events/sched/sched_switch/trigger
 echo 'hist:keys=comm,pid,lat:wakeup_lat=lat:sort=lat' > events/synthetic/wakeup_latency/trigger
-ping localhost -c 5
+
+ping $LOCALHOST -c 5
 if [ ! grep -q "ping" events/synthetic/wakeup_latency/hist -o ! grep -q "max:" events/sched/sched_switch/hist]; then
     fail "Failed to create onmatch-onmax action inter-event histogram"
 fi
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
index 55b9630a1d70..1180ab5f0845 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
@@ -27,7 +27,8 @@ echo "Test onmax action"
 
 echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_waking/trigger
 echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:onmax($wakeup_lat).save(next_comm,prev_pid,prev_prio,prev_comm) if next_comm=="ping"' >> events/sched/sched_switch/trigger
-ping localhost -c 3
+
+ping $LOCALHOST -c 3
 if ! grep -q "max:" events/sched/sched_switch/hist; then
     fail "Failed to create onmax action inter-event histogram"
 fi
-- 
cgit v1.2.3


From af2a0750f374935c07b8beab78d6032b1ca2218d Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:17:38 +0900
Subject: selftests/ftrace: Improve kprobe on module testcase to load/unload
 module

Improve kprobe events on module testcase to check module
load/unload with disabled/enabled events. This also change
the target module to trace_printk.ko, so it depends on
CONFIG_SAMPLE_TRACE_PRINTK=m.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/config              |  4 +++
 .../ftrace/test.d/kprobe/kprobe_module.tc          | 35 ++++++++++++++++++++--
 2 files changed, 36 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/config b/tools/testing/selftests/ftrace/config
index 07db5ab09cc7..32cf61b6bb54 100644
--- a/tools/testing/selftests/ftrace/config
+++ b/tools/testing/selftests/ftrace/config
@@ -7,3 +7,7 @@ CONFIG_HIST_TRIGGERS=y
 CONFIG_PREEMPT_TRACER=y
 CONFIG_IRQSOFF_TRACER=y
 CONFIG_PREEMPTIRQ_DELAY_TEST=m
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SAMPLES=y
+CONFIG_SAMPLE_TRACE_PRINTK=m
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc
index ec6c5fffef1e..d861bd776c5e 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc
@@ -4,11 +4,18 @@
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
+rmmod trace-printk ||:
+if ! modprobe trace-printk ; then
+  echo "No trace-printk sample module - please make CONFIG_SAMPLE_TRACE_PRINTK=
+m"
+  exit_unresolved;
+fi
+
+MOD=trace_printk
+FUNC=trace_printk_irq_work
+
 :;: "Add an event on a module function without specifying event name" ;:
 
-MOD=`lsmod | head -n 2 | tail -n 1 | cut -f1 -d" "`
-FUNC=`grep -m 1 ".* t .*\\[$MOD\\]" /proc/kallsyms | xargs | cut -f3 -d" "`
-[ "x" != "x$MOD" -a "y" != "y$FUNC" ] || exit_unresolved
 echo "p $MOD:$FUNC" > kprobe_events
 PROBE_NAME=`echo $MOD:$FUNC | tr ".:" "_"`
 test -d events/kprobes/p_${PROBE_NAME}_0 || exit_failure
@@ -22,3 +29,25 @@ test -d events/kprobes/event1 || exit_failure
 
 echo "p:kprobes1/event1 $MOD:$FUNC" > kprobe_events
 test -d events/kprobes1/event1 || exit_failure
+
+:;: "Remove target module, but event still be there" ;:
+if ! rmmod trace-printk ; then
+  echo "Failed to unload module - please enable CONFIG_MODULE_UNLOAD"
+  exit_unresolved;
+fi
+test -d events/kprobes1/event1
+
+:;: "Check posibility to defining events on unloaded module";:
+echo "p:event2 $MOD:$FUNC" >> kprobe_events
+
+:;: "Target is gone, but we can prepare for next time";:
+echo 1 > events/kprobes1/event1/enable
+
+:;: "Load module again, which means the event1 should be recorded";:
+modprobe trace-printk
+grep "event1:" trace
+
+:;: "Remove the module again and check the event is not locked"
+rmmod trace-printk
+echo 0 > events/kprobes1/event1/enable
+echo "-:kprobes1/event1" >> kprobe_events
-- 
cgit v1.2.3


From e42e5c46b07d09b6b985ceea954eae165103c7ed Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:18:06 +0900
Subject: selftests/ftrace: Improve kprobe testcase to check log data

Improve kprobe testcase to check the log data correctness
and ensure the event definition is corrctly including
argument definition.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
index 9578535ccd67..bcdecf80a8f1 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
@@ -5,10 +5,14 @@
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
 echo 'p:testprobe _do_fork $stack $stack0 +0($stack)' > kprobe_events
-grep testprobe kprobe_events
+grep testprobe kprobe_events | grep -q 'arg1=\$stack arg2=\$stack0 arg3=+0(\$stack)'
 test -d events/kprobes/testprobe
+
 echo 1 > events/kprobes/testprobe/enable
 ( echo "forked")
+grep testprobe trace | grep '_do_fork' | \
+  grep -q 'arg1=0x[[:xdigit:]]* arg2=0x[[:xdigit:]]* arg3=0x[[:xdigit:]]*$'
+
 echo 0 > events/kprobes/testprobe/enable
 echo "-:testprobe" >> kprobe_events
 clear_trace
-- 
cgit v1.2.3


From 1e51263ef4e637199b725df6811f0d2bea70156c Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:18:35 +0900
Subject: selftests/ftrace: Improve kretprobe testcase to check log data

Improve kretprobe testcase to check the log data correctness
and ensure the event definition is corrctly including
argument definition.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
index 4c6b21e30b02..ac9ab4a12e53 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
@@ -4,11 +4,16 @@
 
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 
+# Add new kretprobe event
 echo 'r:testprobe2 _do_fork $retval' > kprobe_events
-grep testprobe2 kprobe_events
+grep testprobe2 kprobe_events | grep -q 'arg1=\$retval'
 test -d events/kprobes/testprobe2
+
 echo 1 > events/kprobes/testprobe2/enable
 ( echo "forked")
+
+cat trace | grep testprobe2 | grep -q '<- _do_fork'
+
 echo 0 > events/kprobes/testprobe2/enable
 echo '-:testprobe2' >> kprobe_events
 clear_trace
-- 
cgit v1.2.3


From 00b2f2bc3aacb658c44dcb76e004423b6a6380eb Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:19:03 +0900
Subject: selftests/ftrace: Test kprobe-event argument with various bitsize

Improve the kprobe-event with argument types testcase
to test it with various bitsize.
kprobe-event argument can be recorded in given types with
various bitsize (8, 16, 32, 64), thus the type testcase
should test the different bitsize too.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../ftrace/test.d/kprobe/kprobe_args_type.tc       | 48 ++++++++++++++--------
 1 file changed, 32 insertions(+), 16 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
index 37443dd23d15..1bcb67dcae26 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
@@ -6,29 +6,45 @@
 
 grep "x8/16/32/64" README > /dev/null || exit_unsupported # version issue
 
-echo 'p:testprobe _do_fork $stack0:s32 $stack0:u32 $stack0:x32 $stack0:b8@4/32' > kprobe_events
-grep testprobe kprobe_events
-test -d events/kprobes/testprobe
-
-echo 1 > events/kprobes/testprobe/enable
-( echo "forked")
-echo 0 > events/kprobes/testprobe/enable
-ARGS=`tail -n 1 trace | sed -e 's/.* arg1=\(.*\) arg2=\(.*\) arg3=\(.*\) arg4=\(.*\)/\1 \2 \3 \4/'`
+gen_event() { # Bitsize
+  echo "p:testprobe _do_fork \$stack0:s$1 \$stack0:u$1 \$stack0:x$1 \$stack0:b4@4/$1"
+}
 
-check_types() {
-  X1=`printf "%x" $1 | tail -c 8`
+check_types() { # s-type u-type x-type bf-type width
+  test $# -eq 5
+  CW=$5
+  CW=$((CW / 4))
+  X1=`printf "%x" $1 | tail -c ${CW}`
   X2=`printf "%x" $2`
   X3=`printf "%x" $3`
   test $X1 = $X2
   test $X2 = $X3
   test 0x$X3 = $3
 
-  B4=`printf "%02x" $4`
-  B3=`echo -n $X3 | tail -c 3 | head -c 2`
+  B4=`printf "%1x" $4`
+  B3=`printf "%03x" 0x$X3 | tail -c 2 | head -c 1`
   test $B3 = $B4
 }
-check_types $ARGS
 
-echo "-:testprobe" >> kprobe_events
-clear_trace
-test -d events/kprobes/testprobe && exit_fail || exit_pass
+for width in 64 32 16 8; do
+  : "Add new event with basic types"
+  gen_event $width > kprobe_events
+  grep testprobe kprobe_events
+  test -d events/kprobes/testprobe
+
+  : "Trace the event"
+  echo 1 > events/kprobes/testprobe/enable
+  ( echo "forked")
+  echo 0 > events/kprobes/testprobe/enable
+
+  : "Confirm the arguments is recorded in given types correctly"
+  ARGS=`grep "testprobe" trace | sed -e 's/.* arg1=\(.*\) arg2=\(.*\) arg3=\(.*\) arg4=\(.*\)/\1 \2 \3 \4/'`
+  check_types $ARGS $width
+
+  : "Clear event for next loop"
+  echo "-:testprobe" >> kprobe_events
+  clear_trace
+
+done
+
+exit_pass
-- 
cgit v1.2.3


From ddbc31e63aef5e7d12f28f3ac4742420bd5b274c Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:19:31 +0900
Subject: selftests/ftrace: Check set_event_pid result

Ensure the set_event_pid shows set pid list.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/test.d/event/event-pid.tc | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
index e28897738500..f9cb214220b1 100644
--- a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc
@@ -42,6 +42,7 @@ do_reset
 read mypid rest < /proc/self/stat
 
 echo $mypid > set_event_pid
+grep -q $mypid set_event_pid
 echo 'sched:sched_switch' > set_event
 
 yield
-- 
cgit v1.2.3


From b0898e84851c96248c376897c96f3fde3ff7e3b5 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:19:59 +0900
Subject: selftests/ftrace: Add kprobe event with $comm argument testcase

Add kprobe-event with $comm argument testcase to
ftracetest. This not only checks syntax but
also checks log file.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc  | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc
new file mode 100644
index 000000000000..15c1f70fcaf9
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc
@@ -0,0 +1,17 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Kprobe event with comm arguments
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+grep -A1 "fetcharg:" README | grep -q "\$comm" || exit_unsupported # this is too old
+
+echo 'p:testprobe _do_fork comm=$comm ' > kprobe_events
+grep testprobe kprobe_events | grep -q 'comm=$comm'
+test -d events/kprobes/testprobe
+
+echo 1 > events/kprobes/testprobe/enable
+( echo "forked")
+grep testprobe trace | grep -q 'comm=".*"'
+
+exit 0
-- 
cgit v1.2.3


From 32f6e5da83c7f06db7e4efbdacdbc59c16fd6ecb Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:20:28 +0900
Subject: selftests/ftrace: Add kprobe profile testcase

Add a testcase for testing kprobe_profile interface
which provides per-kprobe event hit/misshit counts.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/test.d/kprobe/profile.tc | 15 +++++++++++++++
 1 file changed, 15 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/kprobe/profile.tc

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc b/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc
new file mode 100644
index 000000000000..0384b525cdee
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc
@@ -0,0 +1,15 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Kprobe dynamic event - adding and removing
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+! grep -q 'myevent' kprobe_profile
+echo p:myevent _do_fork > kprobe_events
+grep -q 'myevent[[:space:]]*0[[:space:]]*0$' kprobe_profile
+echo 1 > events/kprobes/myevent/enable
+( echo "forked" )
+grep -q 'myevent[[:space:]]*[[:digit:]]*[[:space:]]*0$' kprobe_profile
+echo 0 > events/kprobes/myevent/enable
+echo > kprobe_events
+! grep -q 'myevent' kprobe_profile
-- 
cgit v1.2.3


From 873b4af2103fbd1bb7895be202a58878254d89bc Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:20:56 +0900
Subject: selftests/ftrace: Add kprobe-event with symbol argument test

Add a testcase for kprobe-event with @symbol argument.
Since @symbol needs to refer the kernel data symbol
(linux_proc_banner), it requires CONFIG_KALLSYMS_ALL.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/config              |  1 +
 .../ftrace/test.d/kprobe/kprobe_args_symbol.tc     | 39 ++++++++++++++++++++++
 2 files changed, 40 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/config b/tools/testing/selftests/ftrace/config
index 32cf61b6bb54..b7ac74fcb0fa 100644
--- a/tools/testing/selftests/ftrace/config
+++ b/tools/testing/selftests/ftrace/config
@@ -11,3 +11,4 @@ CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_SAMPLES=y
 CONFIG_SAMPLE_TRACE_PRINTK=m
+CONFIG_KALLSYMS_ALL=y
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc
new file mode 100644
index 000000000000..2b6dd33f9076
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc
@@ -0,0 +1,39 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Kprobe event symbol argument
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+SYMBOL="linux_proc_banner"
+
+if [ ! -f /proc/kallsyms ]; then
+  echo "Can not check the target symbol - please enable CONFIG_KALLSYMS"
+  exit_unresolved
+elif ! grep "$SYMBOL\$" /proc/kallsyms; then
+  echo "Linux banner is not exported - please enable CONFIG_KALLSYMS_ALL"
+  exit_unresolved
+fi
+
+: "Test get basic types symbol argument"
+echo "p:testprobe_u _do_fork arg1=@linux_proc_banner:u64 arg2=@linux_proc_banner:u32 arg3=@linux_proc_banner:u16 arg4=@linux_proc_banner:u8" > kprobe_events
+echo "p:testprobe_s _do_fork arg1=@linux_proc_banner:s64 arg2=@linux_proc_banner:s32 arg3=@linux_proc_banner:s16 arg4=@linux_proc_banner:s8" >> kprobe_events
+if grep -q "x8/16/32/64" README; then
+  echo "p:testprobe_x _do_fork arg1=@linux_proc_banner:x64 arg2=@linux_proc_banner:x32 arg3=@linux_proc_banner:x16 arg4=@linux_proc_banner:x8" >> kprobe_events
+fi
+echo "p:testprobe_bf _do_fork arg1=@linux_proc_banner:b8@4/32" >> kprobe_events
+echo 1 > events/kprobes/enable
+(echo "forked")
+echo 0 > events/kprobes/enable
+grep "testprobe_[usx]:.* arg1=.* arg2=.* arg3=.* arg4=.*" trace
+grep "testprobe_bf:.* arg1=.*" trace
+
+: "Test get string symbol argument"
+echo "p:testprobe_str _do_fork arg1=@linux_proc_banner:string" > kprobe_events
+echo 1 > events/kprobes/enable
+(echo "forked")
+echo 0 > events/kprobes/enable
+RESULT=`grep "testprobe_str" trace | sed -e 's/.* arg1=\(.*\)/\1/'`
+
+RESULT=`echo $RESULT | sed -e 's/.* \((.*)\) \((.*)\) .*/\1 \2/'`
+ORIG=`cat /proc/version | sed -e 's/.* \((.*)\) \((.*)\) .*/\1 \2/'`
+test "$RESULT" = "$ORIG"
-- 
cgit v1.2.3


From 4d23e9b4fd2e44f10d22b9d2ba1dfb3fff8cd9d5 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:21:25 +0900
Subject: selftests/ftrace: Add trace_printk sample module test

Add trace_printk sample module test. This requires to
enable trace_printk.ko module for test.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../selftests/ftrace/test.d/event/trace_printk.tc  | 27 ++++++++++++++++++++++
 1 file changed, 27 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/event/trace_printk.tc

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/event/trace_printk.tc b/tools/testing/selftests/ftrace/test.d/event/trace_printk.tc
new file mode 100644
index 000000000000..b02550b42be9
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/event/trace_printk.tc
@@ -0,0 +1,27 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Test trace_printk from module
+
+rmmod trace-printk ||:
+if ! modprobe trace-printk ; then
+  echo "No trace-printk sample module - please make CONFIG_SAMPLE_TRACE_PRINTK=m"
+  exit_unresolved;
+fi
+
+echo "Waiting for irq work"
+sleep 1
+
+grep -q ": This .* trace_bputs" trace
+grep -q ": This .* trace_puts" trace
+grep -q ": This .* trace_bprintk" trace
+grep -q ": This .* trace_printk" trace
+
+grep -q ": (irq) .* trace_bputs" trace
+grep -q ": (irq) .* trace_puts" trace
+grep -q ": (irq) .* trace_bprintk" trace
+grep -q ": (irq) .* trace_printk" trace
+
+grep -q "This is a %s that will use trace_bprintk" printk_formats
+grep -q "(irq) This is a static string that will use trace_bputs" printk_formats
+
+rmmod trace-printk ||:
-- 
cgit v1.2.3


From c21ceceae94dc22f5b42c8174efa4597a0c990de Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:21:53 +0900
Subject: selftests/ftrace: Add ringbuffer size changing testcase

Add a testcase for changing ringbuffer size. This tests
not only ringbuffer size but also tests the imbalance
per-cpu buffer size change too.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../ftrace/test.d/00basic/ringbuffer_size.tc       | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_size.tc

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_size.tc b/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_size.tc
new file mode 100644
index 000000000000..ab70f0077c35
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_size.tc
@@ -0,0 +1,22 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Change the ringbuffer size
+# flags: instance
+
+rb_size_test() {
+ORIG=`cat buffer_size_kb`
+
+expr $ORIG / 2 > buffer_size_kb
+
+expr $ORIG \* 2 > buffer_size_kb
+
+echo $ORIG > buffer_size_kb
+}
+
+rb_size_test
+
+: "If per-cpu buffer is supported, imbalance it"
+if [ -d per_cpu/cpu0 ]; then
+  cd per_cpu/cpu0
+  rb_size_test
+fi
-- 
cgit v1.2.3


From 5b56a07b9c461bb4db26797c82d6ac3be0f83a94 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:22:21 +0900
Subject: selftests/ftrace: Add function profiling stat testcase

Add a testcase for function profiling per-cpu statistics
interface. There is already func_profile.tc, but that is
mainly focusing on the combination of function-profiler
and function tracer. This testcase ensures trace_stat
per-cpu function statistics is correctly updated.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../ftrace/test.d/ftrace/func_profile_stat.tc      | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/ftrace/func_profile_stat.tc

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_profile_stat.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_profile_stat.tc
new file mode 100644
index 000000000000..0d501058aa75
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_profile_stat.tc
@@ -0,0 +1,22 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: ftrace - function profiling
+
+[ ! -f function_profile_enabled ] && exit_unsupported
+
+: "Enable function profile"
+echo 1 > function_profile_enabled
+
+: "Profile must be updated"
+cp trace_stat/function0 $TMPDIR/
+( echo "forked"; sleep 1 )
+: "diff returns 0 if there is no difference"
+! diff trace_stat/function0 $TMPDIR/function0
+
+echo 0 > function_profile_enabled
+
+: "Profile must NOT be updated"
+cp trace_stat/function0 $TMPDIR/
+( echo "forked"; sleep 1 )
+: "diff returns 0 if there is no difference"
+diff trace_stat/function0 $TMPDIR/function0
-- 
cgit v1.2.3


From 47c509d30db4cef11a406f87279633cd21380163 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:22:49 +0900
Subject: selftests/ftrace: Add max stack tracer testcase

Add a testcase for max stack tracer, which checks basic
max stack usage tracing and its filter feature.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../ftrace/test.d/ftrace/func_stack_tracer.tc      | 39 ++++++++++++++++++++++
 1 file changed, 39 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc
new file mode 100644
index 000000000000..b414f0e3c646
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc
@@ -0,0 +1,39 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: ftrace - Max stack tracer
+# Test the basic function of max-stack usage tracing
+
+if [ ! -f stack_trace ]; then
+  echo "Max stack tracer is not supported - please make CONFIG_STACK_TRACER=y"
+  exit_unsupported
+fi
+
+echo > stack_trace_filter
+echo 0 > stack_max_size
+echo 1 > /proc/sys/kernel/stack_tracer_enabled
+
+: "Fork and wait for the first entry become !lock"
+timeout=10
+while [ $timeout -ne 0 ]; do
+  ( echo "forked" )
+  FL=`grep " 0)" stack_trace`
+  echo $FL | grep -q "lock" || break;
+  timeout=$((timeout - 1))
+done
+echo 0 > /proc/sys/kernel/stack_tracer_enabled
+
+echo '*lock*' > stack_trace_filter
+test `cat stack_trace_filter | wc -l` -eq `grep lock stack_trace_filter | wc -l`
+
+echo 0 > stack_max_size
+echo 1 > /proc/sys/kernel/stack_tracer_enabled
+
+: "Fork and always the first entry including lock"
+timeout=10
+while [ $timeout -ne 0 ]; do
+  ( echo "forked" )
+  FL=`grep " 0)" stack_trace`
+  echo $FL | grep -q "lock"
+  timeout=$((timeout - 1))
+done
+echo 0 > /proc/sys/kernel/stack_tracer_enabled
-- 
cgit v1.2.3


From 7bc026d6c0328f49469a56168b50ff7a498a5810 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:23:18 +0900
Subject: selftests/ftrace: Add function filter on module testcase

Add a testcase for function filter on module.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../ftrace/test.d/ftrace/func_mod_trace.tc         | 24 ++++++++++++++++++++++
 1 file changed, 24 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc
new file mode 100644
index 000000000000..9330c873f9fe
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc
@@ -0,0 +1,24 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: ftrace - function trace on module
+
+[ ! -f set_ftrace_filter ] && exit_unsupported
+
+: "mod: allows to filter a non exist function"
+echo 'non_exist_func:mod:non_exist_module' > set_ftrace_filter
+grep -q "non_exist_func" set_ftrace_filter
+
+: "mod: on exist module"
+echo '*:mod:trace_printk' > set_ftrace_filter
+if ! modprobe trace-printk ; then
+  echo "No trace-printk sample module - please make CONFIG_SAMPLE_TRACE_PRINTK=
+m"
+  exit_unresolved;
+fi
+
+: "Wildcard should be resolved after loading module"
+grep -q "trace_printk_irq_work" set_ftrace_filter
+
+: "After removing the filter becomes empty"
+rmmod trace_printk
+test `cat set_ftrace_filter | wc -l` -eq 0
-- 
cgit v1.2.3


From 174fd823397a2f19905a20bbcf47907e30e58444 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:23:46 +0900
Subject: selftests/ftrace: Add trace_pipe testcase

Add a simple testcase for trace_pipe which can consume
ringbuffer.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../selftests/ftrace/test.d/00basic/trace_pipe.tc        | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/00basic/trace_pipe.tc

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/00basic/trace_pipe.tc b/tools/testing/selftests/ftrace/test.d/00basic/trace_pipe.tc
new file mode 100644
index 000000000000..5058fbcfd90f
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/trace_pipe.tc
@@ -0,0 +1,16 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: trace_pipe and trace_marker
+# flags: instance
+
+[ ! -f trace_marker ] && exit_unsupported
+
+echo "test input 1" > trace_marker
+
+: "trace interface never consume the ring buffer"
+grep -q "test input 1" trace
+grep -q "test input 1" trace
+
+: "trace interface never consume the ring buffer"
+head -n 1 trace_pipe | grep -q "test input 1"
+! grep -q "test input 1" trace
-- 
cgit v1.2.3


From 91ae08a265142d9378f7d972e00de29d5c91a2de Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:24:14 +0900
Subject: selftests/ftrace: Add stacktrace ftrace filter command testcase

Add a test case for stacktrace filter command for ftrace.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc | 12 ++++++++++++
 1 file changed, 12 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
new file mode 100644
index 000000000000..bf72e783d014
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
@@ -0,0 +1,12 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL2.0
+# description: ftrace - stacktrace filter command
+# flags: instance
+
+echo _do_fork:stacktrace >> set_ftrace_filter
+
+grep -q "_do_fork:stacktrace:unlimited" set_ftrace_filter
+
+(echo "forked"; sleep 1)
+
+grep -q "<stack trace>" trace
-- 
cgit v1.2.3


From c1edd060b41383bb6fa76008aacf4b0b3b1c46e7 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:24:42 +0900
Subject: selftests/ftrace: Add wakeup tracer testcase

Add a testcase for wakeup tracer.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/config              |  1 +
 .../selftests/ftrace/test.d/tracer/wakeup.tc       | 25 ++++++++++++++++++++++
 2 files changed, 26 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/tracer/wakeup.tc

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/config b/tools/testing/selftests/ftrace/config
index b7ac74fcb0fa..c2c8de4fafff 100644
--- a/tools/testing/selftests/ftrace/config
+++ b/tools/testing/selftests/ftrace/config
@@ -4,6 +4,7 @@ CONFIG_FUNCTION_PROFILER=y
 CONFIG_TRACER_SNAPSHOT=y
 CONFIG_STACK_TRACER=y
 CONFIG_HIST_TRIGGERS=y
+CONFIG_SCHED_TRACER=y
 CONFIG_PREEMPT_TRACER=y
 CONFIG_IRQSOFF_TRACER=y
 CONFIG_PREEMPTIRQ_DELAY_TEST=m
diff --git a/tools/testing/selftests/ftrace/test.d/tracer/wakeup.tc b/tools/testing/selftests/ftrace/test.d/tracer/wakeup.tc
new file mode 100644
index 000000000000..e3005fa785f0
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/tracer/wakeup.tc
@@ -0,0 +1,25 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL2.0
+# description: Test wakeup tracer
+
+if ! which chrt ; then
+  echo "chrt is not found. This test requires nice command."
+  exit_unresolved
+fi
+
+if ! grep -wq "wakeup" available_tracers ; then
+  echo "wakeup tracer is not supported"
+  exit_unsupported
+fi
+
+echo wakeup > current_tracer
+echo 1 > tracing_on
+echo 0 > tracing_max_latency
+
+: "Wakeup higher priority task"
+chrt -f 5 sleep 1
+
+echo 0 > tracing_on
+grep '+ \[[[:digit:]]*\]' trace
+grep '==> \[[[:digit:]]*\]' trace
+
-- 
cgit v1.2.3


From c575dea2c1a50306d382615fad06767564734e0b Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:25:11 +0900
Subject: selftests/ftrace: Add wakeup_rt tracer testcase

Add a testcase for wakeup_rt tracer. This requires chrt
command to test.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../selftests/ftrace/test.d/tracer/wakeup_rt.tc    | 25 ++++++++++++++++++++++
 1 file changed, 25 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/tracer/wakeup_rt.tc

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/tracer/wakeup_rt.tc b/tools/testing/selftests/ftrace/test.d/tracer/wakeup_rt.tc
new file mode 100644
index 000000000000..f99b5178e00a
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/tracer/wakeup_rt.tc
@@ -0,0 +1,25 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL2.0
+# description: Test wakeup RT tracer
+
+if ! which chrt ; then
+  echo "chrt is not found. This test requires chrt command."
+  exit_unresolved
+fi
+
+if ! grep -wq "wakeup_rt" available_tracers ; then
+  echo "wakeup_rt tracer is not supported"
+  exit_unsupported
+fi
+
+echo wakeup_rt > current_tracer
+echo 1 > tracing_on
+echo 0 > tracing_max_latency
+
+: "Wakeup a realtime task"
+chrt -f 5 sleep 1
+
+echo 0 > tracing_on
+grep "+ \[[[:digit:]]*\]" trace
+grep "==> \[[[:digit:]]*\]" trace
+
-- 
cgit v1.2.3


From 8ffade754bdf8350f63792c6125346d77f975b41 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 30 Aug 2018 23:25:39 +0900
Subject: selftests/ftrace: Add ftrace cpumask testcase

Add a testcase for tracing_cpumask with function tracer.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 .../selftests/ftrace/test.d/ftrace/func_cpumask.tc | 42 ++++++++++++++++++++++
 1 file changed, 42 insertions(+)
 create mode 100644 tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc
new file mode 100644
index 000000000000..0e6810743576
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_cpumask.tc
@@ -0,0 +1,42 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL2.0
+# description: ftrace - function trace with cpumask
+
+if ! which nproc ; then
+  nproc() {
+    ls -d /sys/devices/system/cpu/cpu[0-9]* | wc -l
+  }
+fi
+
+NP=`nproc`
+
+if [ $NP -eq 1 ] ;then
+  echo "We can not test cpumask on UP environment"
+  exit_unresolved
+fi
+
+ORIG_CPUMASK=`cat tracing_cpumask`
+
+do_reset() {
+  echo $ORIG_CPUMASK > tracing_cpumask
+}
+
+echo 0 > tracing_on
+echo > trace
+: "Bitmask only record on CPU1"
+echo 2 > tracing_cpumask
+MASK=0x`cat tracing_cpumask`
+test `printf "%d" $MASK` -eq 2 || do_reset
+
+echo function > current_tracer
+echo 1 > tracing_on
+(echo "forked")
+echo 0 > tracing_on
+
+: "Check CPU1 events are recorded"
+grep -q -e "\[001\]" trace || do_reset
+
+: "There should be No other cpu events"
+! grep -qv -e "\[001\]" -e "^#" trace || do_reset
+
+do_reset
-- 
cgit v1.2.3


From 9a244229a4b850b11952a0df79607c69b18fd8df Mon Sep 17 00:00:00 2001
From: "Shuah Khan (Samsung OSG)" <shuah@kernel.org>
Date: Wed, 26 Sep 2018 13:07:11 -0600
Subject: selftests: watchdog: fix message when /dev/watchdog open fails

When /dev/watchdog open fails, watchdog exits with "watchdog not enabled"
message. This is incorrect when open fails due to insufficient privilege.

Fix message to clearly state the reason when open fails with EACCESS when
a non-root user runs it.

Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/watchdog/watchdog-test.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c
index 6e290874b70e..e029e2017280 100644
--- a/tools/testing/selftests/watchdog/watchdog-test.c
+++ b/tools/testing/selftests/watchdog/watchdog-test.c
@@ -89,7 +89,13 @@ int main(int argc, char *argv[])
 	fd = open("/dev/watchdog", O_WRONLY);
 
 	if (fd == -1) {
-		printf("Watchdog device not enabled.\n");
+		if (errno == ENOENT)
+			printf("Watchdog device not enabled.\n");
+		else if (errno == EACCES)
+			printf("Run watchdog as root.\n");
+		else
+			printf("Watchdog device open failed %s\n",
+				strerror(errno));
 		exit(-1);
 	}
 
-- 
cgit v1.2.3


From 04d5e4bd37516ad60854eb74592c7dbddd75d277 Mon Sep 17 00:00:00 2001
From: Jerry Hoemann <jerry.hoemann@hpe.com>
Date: Wed, 26 Sep 2018 15:23:08 -0600
Subject: selftests: watchdog: Fix error message.

Printf's say errno but print the string version of error.
Make consistent.

Signed-off-by: Jerry Hoemann <jerry.hoemann@hpe.com>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/watchdog/watchdog-test.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c
index e029e2017280..f1c6e025cbe5 100644
--- a/tools/testing/selftests/watchdog/watchdog-test.c
+++ b/tools/testing/selftests/watchdog/watchdog-test.c
@@ -109,7 +109,7 @@ int main(int argc, char *argv[])
 				printf("Last boot is caused by: %s.\n", (flags != 0) ?
 					"Watchdog" : "Power-On-Reset");
 			else
-				printf("WDIOC_GETBOOTSTATUS errno '%s'\n", strerror(errno));
+				printf("WDIOC_GETBOOTSTATUS error '%s'\n", strerror(errno));
 			break;
 		case 'd':
 			flags = WDIOS_DISABLECARD;
@@ -117,7 +117,7 @@ int main(int argc, char *argv[])
 			if (!ret)
 				printf("Watchdog card disabled.\n");
 			else
-				printf("WDIOS_DISABLECARD errno '%s'\n", strerror(errno));
+				printf("WDIOS_DISABLECARD error '%s'\n", strerror(errno));
 			break;
 		case 'e':
 			flags = WDIOS_ENABLECARD;
@@ -125,7 +125,7 @@ int main(int argc, char *argv[])
 			if (!ret)
 				printf("Watchdog card enabled.\n");
 			else
-				printf("WDIOS_ENABLECARD errno '%s'\n", strerror(errno));
+				printf("WDIOS_ENABLECARD error '%s'\n", strerror(errno));
 			break;
 		case 'p':
 			ping_rate = strtoul(optarg, NULL, 0);
@@ -139,7 +139,7 @@ int main(int argc, char *argv[])
 			if (!ret)
 				printf("Watchdog timeout set to %u seconds.\n", flags);
 			else
-				printf("WDIOC_SETTIMEOUT errno '%s'\n", strerror(errno));
+				printf("WDIOC_SETTIMEOUT error '%s'\n", strerror(errno));
 			break;
 		default:
 			usage(argv[0]);
-- 
cgit v1.2.3


From 7514c39cf1d9433203c9b7c6674dbfa429db804b Mon Sep 17 00:00:00 2001
From: Jerry Hoemann <jerry.hoemann@hpe.com>
Date: Wed, 26 Sep 2018 15:23:09 -0600
Subject: selftests: watchdog: Add gettimeout and get|set pretimeout

Add command line arguments to call ioctl WDIOC_GETTIMEOUT,
WDIOC_GETPRETIMEOUT and WDIOC_SETPRETIMEOUT.

Signed-off-by: Jerry Hoemann <jerry.hoemann@hpe.com>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/watchdog/watchdog-test.c | 33 +++++++++++++++++++++++-
 1 file changed, 32 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c
index f1c6e025cbe5..e0f1600dc1b3 100644
--- a/tools/testing/selftests/watchdog/watchdog-test.c
+++ b/tools/testing/selftests/watchdog/watchdog-test.c
@@ -19,7 +19,7 @@
 
 int fd;
 const char v = 'V';
-static const char sopts[] = "bdehp:t:";
+static const char sopts[] = "bdehp:t:Tn:N";
 static const struct option lopts[] = {
 	{"bootstatus",          no_argument, NULL, 'b'},
 	{"disable",             no_argument, NULL, 'd'},
@@ -27,6 +27,9 @@ static const struct option lopts[] = {
 	{"help",                no_argument, NULL, 'h'},
 	{"pingrate",      required_argument, NULL, 'p'},
 	{"timeout",       required_argument, NULL, 't'},
+	{"gettimeout",          no_argument, NULL, 'T'},
+	{"pretimeout",    required_argument, NULL, 'n'},
+	{"getpretimeout",       no_argument, NULL, 'N'},
 	{NULL,                  no_argument, NULL, 0x0}
 };
 
@@ -71,9 +74,13 @@ static void usage(char *progname)
 	printf(" -h, --help          Print the help message\n");
 	printf(" -p, --pingrate=P    Set ping rate to P seconds (default %d)\n", DEFAULT_PING_RATE);
 	printf(" -t, --timeout=T     Set timeout to T seconds\n");
+	printf(" -T, --gettimeout    Get the timeout\n");
+	printf(" -n, --pretimeout=T  Set the pretimeout to T seconds\n");
+	printf(" -N, --getpretimeout Get the pretimeout\n");
 	printf("\n");
 	printf("Parameters are parsed left-to-right in real-time.\n");
 	printf("Example: %s -d -t 10 -p 5 -e\n", progname);
+	printf("Example: %s -t 12 -T -n 7 -N\n", progname);
 }
 
 int main(int argc, char *argv[])
@@ -141,6 +148,30 @@ int main(int argc, char *argv[])
 			else
 				printf("WDIOC_SETTIMEOUT error '%s'\n", strerror(errno));
 			break;
+		case 'T':
+			oneshot = 1;
+			ret = ioctl(fd, WDIOC_GETTIMEOUT, &flags);
+			if (!ret)
+				printf("WDIOC_GETTIMEOUT returns %u seconds.\n", flags);
+			else
+				printf("WDIOC_GETTIMEOUT error '%s'\n", strerror(errno));
+			break;
+		case 'n':
+			flags = strtoul(optarg, NULL, 0);
+			ret = ioctl(fd, WDIOC_SETPRETIMEOUT, &flags);
+			if (!ret)
+				printf("Watchdog pretimeout set to %u seconds.\n", flags);
+			else
+				printf("WDIOC_SETPRETIMEOUT error '%s'\n", strerror(errno));
+			break;
+		case 'N':
+			oneshot = 1;
+			ret = ioctl(fd, WDIOC_GETPRETIMEOUT, &flags);
+			if (!ret)
+				printf("WDIOC_GETPRETIMEOUT returns %u seconds.\n", flags);
+			else
+				printf("WDIOC_GETPRETIMEOUT error '%s'\n", strerror(errno));
+			break;
 		default:
 			usage(argv[0]);
 			goto end;
-- 
cgit v1.2.3


From d89d08ffd2c5a9043c8df7333d9bee6c09904a8f Mon Sep 17 00:00:00 2001
From: "Shuah Khan (Samsung OSG)" <shuah@kernel.org>
Date: Wed, 26 Sep 2018 16:37:43 -0600
Subject: selftests: watchdog: Fix ioctl SET* error paths to take oneshot exit
 path

When ioctls for WDIOC_SETOPTIONS (WDIOS_DISABLECARD or WDIOS_ENABLECARD),
WDIOC_SETTIMEOUT, and WDIOC_SETPRETIMEOUT fail, the error path continues
to handler watchdog timer until user terminates it. When ioctl returns
error, it might not be safe to let the watchdog tick. The error could be
due an unsupported ioctl command or some other error.

Fix it to handle error paths as oneshot to stop the watchdog ticks and
exit right away.

Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/watchdog/watchdog-test.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c
index e0f1600dc1b3..c6bd9a68306b 100644
--- a/tools/testing/selftests/watchdog/watchdog-test.c
+++ b/tools/testing/selftests/watchdog/watchdog-test.c
@@ -123,16 +123,20 @@ int main(int argc, char *argv[])
 			ret = ioctl(fd, WDIOC_SETOPTIONS, &flags);
 			if (!ret)
 				printf("Watchdog card disabled.\n");
-			else
+			else {
 				printf("WDIOS_DISABLECARD error '%s'\n", strerror(errno));
+				oneshot = 1;
+			}
 			break;
 		case 'e':
 			flags = WDIOS_ENABLECARD;
 			ret = ioctl(fd, WDIOC_SETOPTIONS, &flags);
 			if (!ret)
 				printf("Watchdog card enabled.\n");
-			else
+			else {
 				printf("WDIOS_ENABLECARD error '%s'\n", strerror(errno));
+				oneshot = 1;
+			}
 			break;
 		case 'p':
 			ping_rate = strtoul(optarg, NULL, 0);
@@ -145,8 +149,10 @@ int main(int argc, char *argv[])
 			ret = ioctl(fd, WDIOC_SETTIMEOUT, &flags);
 			if (!ret)
 				printf("Watchdog timeout set to %u seconds.\n", flags);
-			else
+			else {
 				printf("WDIOC_SETTIMEOUT error '%s'\n", strerror(errno));
+				oneshot = 1;
+			}
 			break;
 		case 'T':
 			oneshot = 1;
@@ -161,8 +167,10 @@ int main(int argc, char *argv[])
 			ret = ioctl(fd, WDIOC_SETPRETIMEOUT, &flags);
 			if (!ret)
 				printf("Watchdog pretimeout set to %u seconds.\n", flags);
-			else
+			else {
 				printf("WDIOC_SETPRETIMEOUT error '%s'\n", strerror(errno));
+				oneshot = 1;
+			}
 			break;
 		case 'N':
 			oneshot = 1;
-- 
cgit v1.2.3


From a4f222e000b3f75bd1ab763dcc289d004ff6596e Mon Sep 17 00:00:00 2001
From: Fathi Boudra <fathi.boudra@linaro.org>
Date: Fri, 7 Sep 2018 09:34:54 -0500
Subject: selftests: gpio: restructure Makefile
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch cleans up the Makefile by restructuring a couple of
things, namely:
1) change explicit paths in targets for variables
2) substitute a variable (BINARIES) for another, part of the
   selftests build system (TEST_PROGS_EXTENDED)
3) proper cleaning up of the EXTRA objects

The resulting Makefile is much more readable and manageable.

Signed-off-by: Fathi Boudra <fathi.boudra@linaro.org>
Signed-off-by: Daniel Díaz <daniel.diaz@linaro.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/gpio/Makefile | 32 +++++++++++++++-----------------
 1 file changed, 15 insertions(+), 17 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index 4665cdbf1a8d..a4a01ec8b2a5 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -1,28 +1,26 @@
 # SPDX-License-Identifier: GPL-2.0
 
+CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/
+LDLIBS += -lmount -I/usr/include/libmount
+
 TEST_PROGS := gpio-mockup.sh
-TEST_FILES := gpio-mockup-sysfs.sh $(BINARIES)
-BINARIES := gpio-mockup-chardev
-EXTRA_PROGS := ../gpiogpio-event-mon ../gpiogpio-hammer ../gpiolsgpio
-EXTRA_DIRS := ../gpioinclude/
-EXTRA_OBJS := ../gpiogpio-event-mon-in.o ../gpiogpio-event-mon.o
-EXTRA_OBJS += ../gpiogpio-hammer-in.o ../gpiogpio-utils.o ../gpiolsgpio-in.o
-EXTRA_OBJS += ../gpiolsgpio.o
+TEST_FILES := gpio-mockup-sysfs.sh
+TEST_PROGS_EXTENDED := gpio-mockup-chardev
+
+GPIODIR := ../../../gpio
+GPIOOBJ := gpio-utils.o
 
 include ../lib.mk
 
-all: $(BINARIES)
+all: $(TEST_PROGS_EXTENDED)
 
 override define CLEAN
-	$(RM) $(BINARIES) $(EXTRA_PROGS) $(EXTRA_OBJS)
-	$(RM) -r $(EXTRA_DIRS)
+	$(RM) $(TEST_PROGS_EXTENDED)
+	$(MAKE) -C $(GPIODIR) clean
 endef
 
-CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/
-LDLIBS += -lmount -I/usr/include/libmount
-
-$(BINARIES):| khdr
-$(BINARIES): ../../../gpio/gpio-utils.o
+$(TEST_PROGS_EXTENDED):| khdr
+$(TEST_PROGS_EXTENDED): $(GPIODIR)/$(GPIOOBJ)
 
-../../../gpio/gpio-utils.o:
-	make ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE) -C ../../../gpio
+$(GPIODIR)/$(GPIOOBJ):
+	$(MAKE) -C $(GPIODIR)
-- 
cgit v1.2.3


From 8c7f6316fccf38ca45d33ed658cc4813837b6294 Mon Sep 17 00:00:00 2001
From: Daniel Díaz <daniel.diaz@linaro.org>
Date: Fri, 7 Sep 2018 09:34:55 -0500
Subject: selftests: gpio: Fix OUTPUT directory in Makefile
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When simply running `make' from the selftests top dir, this
error shows up:

  cc -O2 -g -std=gnu99 -Wall -I../../../../usr/include/ -I/usr/include/libmount -I/usr/include/blkid -I/usr/include/uuid    gpio-mockup-chardev.c ../../../gpio/gpio-utils.o  -lmount -o gpio-mockup-chardev
  cc: error: ../../../gpio/gpio-utils.o: No such file or directory
  <builtin>: recipe for target 'gpio-mockup-chardev' failed
  make[1]: *** [gpio-mockup-chardev] Error 1

because the output directory is set to "selftests/gpio" and
all binaries built from ../../../gpio/ end up there. In fact,
they appear as, exempli gratia:
* gpiogpio-event-mon
* gpiogpio-hammer
* gpioinclude/
* gpiolsgpio
which is wrong, as it's missing a directory separator
somewhere.

This patch sets straight the output directory when building
../../../gpio/ so that binaries don't cross paths.

Signed-off-by: Daniel Díaz <daniel.diaz@linaro.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/gpio/Makefile | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index a4a01ec8b2a5..46648427d537 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -7,7 +7,7 @@ TEST_PROGS := gpio-mockup.sh
 TEST_FILES := gpio-mockup-sysfs.sh
 TEST_PROGS_EXTENDED := gpio-mockup-chardev
 
-GPIODIR := ../../../gpio
+GPIODIR := $(realpath ../../../gpio)
 GPIOOBJ := gpio-utils.o
 
 include ../lib.mk
@@ -16,11 +16,11 @@ all: $(TEST_PROGS_EXTENDED)
 
 override define CLEAN
 	$(RM) $(TEST_PROGS_EXTENDED)
-	$(MAKE) -C $(GPIODIR) clean
+	$(MAKE) -C $(GPIODIR) OUTPUT=$(GPIODIR)/ clean
 endef
 
 $(TEST_PROGS_EXTENDED):| khdr
 $(TEST_PROGS_EXTENDED): $(GPIODIR)/$(GPIOOBJ)
 
 $(GPIODIR)/$(GPIOOBJ):
-	$(MAKE) -C $(GPIODIR)
+	$(MAKE) OUTPUT=$(GPIODIR)/ -C $(GPIODIR)
-- 
cgit v1.2.3


From 717da97e94a9ba590632624992a9f79d53d3579b Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sat, 13 Oct 2018 16:41:05 +0100
Subject: kvm: selftests: fix spelling mistake "Insufficent" -> "Insufficient"

Trivial fix to spelling mistake in TEST_ASSERT message text

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/kvm/lib/kvm_util.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 6fd8c089cafc..a56ef6b187bb 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -123,7 +123,7 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 
 	/* Allocate memory. */
 	vm = calloc(1, sizeof(*vm));
-	TEST_ASSERT(vm != NULL, "Insufficent Memory");
+	TEST_ASSERT(vm != NULL, "Insufficient Memory");
 
 	vm->mode = mode;
 	vm_open(vm, perm);
-- 
cgit v1.2.3


From 8f381ac4d3210025891c5397e744fd4c771481d7 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Fri, 12 Oct 2018 22:21:06 -0400
Subject: selftests/ftrace: Add color to the PASS / FAIL results

Now that ftracetest has over 80 tests, it is difficult to simply scroll
up the console window to find the failed tests when it reports just two
tests have failed. In order to make this stand out better, have the
color of the word "PASS" be green, "FAIL" and "XFAIL" be red, and all
other results be blue. This helps tremendously in quickly spotting the
failed tests by just scrolling up the console window.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/ftracetest | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index 5c71d58febb2..4946b2edfcff 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -153,7 +153,7 @@ else
 fi
 
 prlog() { # messages
-  [ -z "$LOG_FILE" ] && echo "$@" || echo "$@" | tee -a $LOG_FILE
+  [ -z "$LOG_FILE" ] && echo -e "$@" || echo -e "$@" | tee -a $LOG_FILE
 }
 catlog() { #file
   [ -z "$LOG_FILE" ] && cat $1 || cat $1 | tee -a $LOG_FILE
@@ -195,37 +195,37 @@ test_on_instance() { # testfile
 eval_result() { # sigval
   case $1 in
     $PASS)
-      prlog "	[PASS]"
+      prlog "	[\e[32mPASS\e[30m]"
       PASSED_CASES="$PASSED_CASES $CASENO"
       return 0
     ;;
     $FAIL)
-      prlog "	[FAIL]"
+      prlog "	[\e[31mFAIL\e[30m]"
       FAILED_CASES="$FAILED_CASES $CASENO"
       return 1 # this is a bug.
     ;;
     $UNRESOLVED)
-      prlog "	[UNRESOLVED]"
+      prlog "	[\e[34mUNRESOLVED\e[30m]"
       UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO"
       return 1 # this is a kind of bug.. something happened.
     ;;
     $UNTESTED)
-      prlog "	[UNTESTED]"
+      prlog "	[\e[34mUNTESTED\e[30m]"
       UNTESTED_CASES="$UNTESTED_CASES $CASENO"
       return 0
     ;;
     $UNSUPPORTED)
-      prlog "	[UNSUPPORTED]"
+      prlog "	[\e[34mUNSUPPORTED\e[30m]"
       UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO"
       return $UNSUPPORTED_RESULT # depends on use case
     ;;
     $XFAIL)
-      prlog "	[XFAIL]"
+      prlog "	[\e[31mXFAIL\e[30m]"
       XFAILED_CASES="$XFAILED_CASES $CASENO"
       return 0
     ;;
     *)
-      prlog "	[UNDEFINED]"
+      prlog "	[\e[34mUNDEFINED\e[30m]"
       UNDEFINED_CASES="$UNDEFINED_CASES $CASENO"
       return 1 # this must be a test bug
     ;;
-- 
cgit v1.2.3


From fb363e2d20351e1d16629df19e7bce1a31b3227a Mon Sep 17 00:00:00 2001
From: Andrea Parri <andrea.parri@amarulasolutions.com>
Date: Tue, 16 Oct 2018 16:13:46 +0200
Subject: selftests: kvm: Fix -Wformat warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fixes the following warnings:

dirty_log_test.c: In function ‘help’:
dirty_log_test.c:216:9: warning: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 2 has type ‘int’ [-Wformat=]
  printf(" -i: specify iteration counts (default: %"PRIu64")\n",
         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from include/test_util.h:18:0,
                 from dirty_log_test.c:16:
/usr/include/inttypes.h:105:34: note: format string is defined here
 # define PRIu64  __PRI64_PREFIX "u"
dirty_log_test.c:218:9: warning: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 2 has type ‘int’ [-Wformat=]
  printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from include/test_util.h:18:0,
                 from dirty_log_test.c:16:
/usr/include/inttypes.h:105:34: note: format string is defined here
 # define PRIu64  __PRI64_PREFIX "u"

Signed-off-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/kvm/dirty_log_test.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 0c2cdc105f96..a9c4b5e21d7e 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -31,9 +31,9 @@
 /* How many pages to dirty for each guest loop */
 #define  TEST_PAGES_PER_LOOP            1024
 /* How many host loops to run (one KVM_GET_DIRTY_LOG for each loop) */
-#define  TEST_HOST_LOOP_N               32
+#define  TEST_HOST_LOOP_N               32UL
 /* Interval for each host loop (ms) */
-#define  TEST_HOST_LOOP_INTERVAL        10
+#define  TEST_HOST_LOOP_INTERVAL        10UL
 
 /*
  * Guest variables.  We use these variables to share data between host
-- 
cgit v1.2.3


From 0387662d1b6c5ad2950d8e94d5e380af3f15c05c Mon Sep 17 00:00:00 2001
From: Peng Hao <peng.hao2@zte.com.cn>
Date: Fri, 12 Oct 2018 03:53:50 +0800
Subject: selftests: fix warning: "_GNU_SOURCE" redefined

Makefile contains -D_GNU_SOURCE. remove define "_GNU_SOURCE"
in c files.

Signed-off-by: Peng Hao <peng.hao2@zte.com.cn>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/proc/fd-001-lookup.c  | 2 +-
 tools/testing/selftests/proc/fd-003-kthread.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/proc/fd-001-lookup.c b/tools/testing/selftests/proc/fd-001-lookup.c
index a2010dfb2110..60d7948e7124 100644
--- a/tools/testing/selftests/proc/fd-001-lookup.c
+++ b/tools/testing/selftests/proc/fd-001-lookup.c
@@ -14,7 +14,7 @@
  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  */
 // Test /proc/*/fd lookup.
-#define _GNU_SOURCE
+
 #undef NDEBUG
 #include <assert.h>
 #include <dirent.h>
diff --git a/tools/testing/selftests/proc/fd-003-kthread.c b/tools/testing/selftests/proc/fd-003-kthread.c
index 1d659d55368c..dc591f97b63d 100644
--- a/tools/testing/selftests/proc/fd-003-kthread.c
+++ b/tools/testing/selftests/proc/fd-003-kthread.c
@@ -14,7 +14,7 @@
  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  */
 // Test that /proc/$KERNEL_THREAD/fd/ is empty.
-#define _GNU_SOURCE
+
 #undef NDEBUG
 #include <sys/syscall.h>
 #include <assert.h>
-- 
cgit v1.2.3


From 8096fbcf55c0da535bdca9adab982ec0c5affb67 Mon Sep 17 00:00:00 2001
From: Daniel Díaz <daniel.diaz@linaro.org>
Date: Tue, 16 Oct 2018 12:02:20 -0500
Subject: selftests/ftrace: Use colored output when available
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If test is being directly executed (with stdout opened on the
terminal) and the terminal capabilities indicate enough
colors, then use the existing scheme of green, red, and blue
to show when tests pass, fail or end in a different way.

When running the tests redirecting the stdout, for instance,
to a file, then colors are not shown, thus producing a more
readable output.

Signed-off-by: Daniel Díaz <daniel.diaz@linaro.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/ftracetest | 29 ++++++++++++++++++++++-------
 1 file changed, 22 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index 4946b2edfcff..d987bbec675f 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -152,6 +152,21 @@ else
   date > $LOG_FILE
 fi
 
+# Define text colors
+# Check available colors on the terminal, if any
+ncolors=`tput colors 2>/dev/null`
+color_reset=
+color_red=
+color_green=
+color_blue=
+# If stdout exists and number of colors is eight or more, use them
+if [ -t 1 -a "$ncolors" -a "$ncolors" -ge 8 ]; then
+  color_reset="\e[0m"
+  color_red="\e[31m"
+  color_green="\e[32m"
+  color_blue="\e[34m"
+fi
+
 prlog() { # messages
   [ -z "$LOG_FILE" ] && echo -e "$@" || echo -e "$@" | tee -a $LOG_FILE
 }
@@ -195,37 +210,37 @@ test_on_instance() { # testfile
 eval_result() { # sigval
   case $1 in
     $PASS)
-      prlog "	[\e[32mPASS\e[30m]"
+      prlog "	[${color_green}PASS${color_reset}]"
       PASSED_CASES="$PASSED_CASES $CASENO"
       return 0
     ;;
     $FAIL)
-      prlog "	[\e[31mFAIL\e[30m]"
+      prlog "	[${color_red}FAIL${color_reset}]"
       FAILED_CASES="$FAILED_CASES $CASENO"
       return 1 # this is a bug.
     ;;
     $UNRESOLVED)
-      prlog "	[\e[34mUNRESOLVED\e[30m]"
+      prlog "	[${color_blue}UNRESOLVED${color_reset}]"
       UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO"
       return 1 # this is a kind of bug.. something happened.
     ;;
     $UNTESTED)
-      prlog "	[\e[34mUNTESTED\e[30m]"
+      prlog "	[${color_blue}UNTESTED${color_reset}]"
       UNTESTED_CASES="$UNTESTED_CASES $CASENO"
       return 0
     ;;
     $UNSUPPORTED)
-      prlog "	[\e[34mUNSUPPORTED\e[30m]"
+      prlog "	[${color_blue}UNSUPPORTED${color_reset}]"
       UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO"
       return $UNSUPPORTED_RESULT # depends on use case
     ;;
     $XFAIL)
-      prlog "	[\e[31mXFAIL\e[30m]"
+      prlog "	[${color_red}XFAIL${color_reset}]"
       XFAILED_CASES="$XFAILED_CASES $CASENO"
       return 0
     ;;
     *)
-      prlog "	[\e[34mUNDEFINED\e[30m]"
+      prlog "	[${color_blue}UNDEFINED${color_reset}]"
       UNDEFINED_CASES="$UNDEFINED_CASES $CASENO"
       return 1 # this must be a test bug
     ;;
-- 
cgit v1.2.3


From f73581f8d9a367459f36e6a4ef0065997ab14c75 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 17 Oct 2018 12:33:23 +0900
Subject: selftests/ftrace: Strip escape sequences for log file

Strip escape sequences from the stream to the ftracetest
summary log file. Note that all test-case results are
dumped raw in each file.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
---
 tools/testing/selftests/ftrace/ftracetest | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index d987bbec675f..75244db70331 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -167,11 +167,18 @@ if [ -t 1 -a "$ncolors" -a "$ncolors" -ge 8 ]; then
   color_blue="\e[34m"
 fi
 
+strip_esc() {
+  # busybox sed implementation doesn't accept "\x1B", so use [:cntrl:] instead.
+  sed -E "s/[[:cntrl:]]\[([0-9]{1,2}(;[0-9]{1,2})?)?[m|K]//g"
+}
+
 prlog() { # messages
-  [ -z "$LOG_FILE" ] && echo -e "$@" || echo -e "$@" | tee -a $LOG_FILE
+  echo -e "$@"
+  [ "$LOG_FILE" ] && echo -e "$@" | strip_esc >> $LOG_FILE
 }
 catlog() { #file
-  [ -z "$LOG_FILE" ] && cat $1 || cat $1 | tee -a $LOG_FILE
+  cat $1
+  [ "$LOG_FILE" ] && cat $1 | strip_esc >> $LOG_FILE
 }
 prlog "=== Ftrace unit tests ==="
 
-- 
cgit v1.2.3


From 4ed591c8ab44e711e56b8e021ffaf4f407c045f5 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 24 Oct 2018 13:58:39 -0700
Subject: net/ipv6: Allow onlink routes to have a device mismatch if it is the
 default route

The intent of ip6_route_check_nh_onlink is to make sure the gateway
given for an onlink route is not actually on a connected route for
a different interface (e.g., 2001:db8:1::/64 is on dev eth1 and then
an onlink route has a via 2001:db8:1::1 dev eth2). If the gateway
lookup hits the default route then it most likely will be a different
interface than the onlink route which is ok.

Update ip6_route_check_nh_onlink to disregard the device mismatch
if the gateway lookup hits the default route. Turns out the existing
onlink tests are passing because there is no default route or it is
an unreachable default, so update the onlink tests to have a default
route other than unreachable.

Fixes: fc1e64e1092f6 ("net/ipv6: Add support for onlink flag")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c                                |  2 ++
 tools/testing/selftests/net/fib-onlink-tests.sh | 14 +++++++-------
 2 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e3226284e480..2a7423c39456 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2745,6 +2745,8 @@ static int ip6_route_check_nh_onlink(struct net *net,
 	grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0);
 	if (grt) {
 		if (!grt->dst.error &&
+		    /* ignore match if it is the default route */
+		    grt->from && !ipv6_addr_any(&grt->from->fib6_dst.addr) &&
 		    (grt->rt6i_flags & flags || dev != grt->dst.dev)) {
 			NL_SET_ERR_MSG(extack,
 				       "Nexthop has invalid gateway or device mismatch");
diff --git a/tools/testing/selftests/net/fib-onlink-tests.sh b/tools/testing/selftests/net/fib-onlink-tests.sh
index 3991ad1a368d..864f865eee55 100755
--- a/tools/testing/selftests/net/fib-onlink-tests.sh
+++ b/tools/testing/selftests/net/fib-onlink-tests.sh
@@ -167,8 +167,8 @@ setup()
 	# add vrf table
 	ip li add ${VRF} type vrf table ${VRF_TABLE}
 	ip li set ${VRF} up
-	ip ro add table ${VRF_TABLE} unreachable default
-	ip -6 ro add table ${VRF_TABLE} unreachable default
+	ip ro add table ${VRF_TABLE} unreachable default metric 8192
+	ip -6 ro add table ${VRF_TABLE} unreachable default metric 8192
 
 	# create test interfaces
 	ip li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]}
@@ -185,20 +185,20 @@ setup()
 	for n in 1 3 5 7; do
 		ip li set ${NETIFS[p${n}]} up
 		ip addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]}
-		ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]}
+		ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad
 	done
 
 	# move peer interfaces to namespace and add addresses
 	for n in 2 4 6 8; do
 		ip li set ${NETIFS[p${n}]} netns ${PEER_NS} up
 		ip -netns ${PEER_NS} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]}
-		ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]}
+		ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad
 	done
 
-	set +e
+	ip -6 ro add default via ${V6ADDRS[p3]/::[0-9]/::64}
+	ip -6 ro add table ${VRF_TABLE} default via ${V6ADDRS[p7]/::[0-9]/::64}
 
-	# let DAD complete - assume default of 1 probe
-	sleep 1
+	set +e
 }
 
 cleanup()
-- 
cgit v1.2.3


From a3f49d97c22022666fb94101454520a7adacaf08 Mon Sep 17 00:00:00 2001
From: Naresh Kamboju <naresh.kamboju@linaro.org>
Date: Thu, 25 Oct 2018 20:17:28 +0530
Subject: selftests/bpf: add config fragments BPF_STREAM_PARSER and XDP_SOCKETS

BPF sockmap and hashmap are dependent on CONFIG_BPF_STREAM_PARSER and
xskmap is dependent on CONFIG_XDP_SOCKETS

Signed-off-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/config | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index dd49df5e2df4..7f90d3645af8 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -20,3 +20,5 @@ CONFIG_VXLAN=y
 CONFIG_GENEVE=y
 CONFIG_NET_CLS_FLOWER=m
 CONFIG_LWTUNNEL=y
+CONFIG_BPF_STREAM_PARSER=y
+CONFIG_XDP_SOCKETS=y
-- 
cgit v1.2.3


From 36641ad61db5ce9befd5eb0071abb36eaff16cfc Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 24 Oct 2018 22:05:43 +0200
Subject: bpf: fix test suite to enable all unpriv program types

Given BPF_PROG_TYPE_CGROUP_SKB program types are also valid in an
unprivileged setting, lets not omit these tests and potentially
have issues fall through the cracks. Make this more obvious by
adding a small test_as_unpriv() helper.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 769d68a48f30..8e1a79d2792c 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -4891,6 +4891,8 @@ static struct bpf_test tests[] = {
 			BPF_EXIT_INSN(),
 		},
 		.result = ACCEPT,
+		.result_unpriv = REJECT,
+		.errstr_unpriv = "R3 pointer comparison prohibited",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 	},
 	{
@@ -5146,6 +5148,7 @@ static struct bpf_test tests[] = {
 		.fixup_cgroup_storage = { 1 },
 		.result = REJECT,
 		.errstr = "get_local_storage() doesn't support non-zero flags",
+		.errstr_unpriv = "R2 leaks addr into helper function",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 	},
 	{
@@ -5261,6 +5264,7 @@ static struct bpf_test tests[] = {
 		.fixup_percpu_cgroup_storage = { 1 },
 		.result = REJECT,
 		.errstr = "get_local_storage() doesn't support non-zero flags",
+		.errstr_unpriv = "R2 leaks addr into helper function",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 	},
 	{
@@ -14050,6 +14054,13 @@ static void get_unpriv_disabled()
 	fclose(fd);
 }
 
+static bool test_as_unpriv(struct bpf_test *test)
+{
+	return !test->prog_type ||
+	       test->prog_type == BPF_PROG_TYPE_SOCKET_FILTER ||
+	       test->prog_type == BPF_PROG_TYPE_CGROUP_SKB;
+}
+
 static int do_test(bool unpriv, unsigned int from, unsigned int to)
 {
 	int i, passes = 0, errors = 0, skips = 0;
@@ -14060,10 +14071,10 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to)
 		/* Program types that are not supported by non-root we
 		 * skip right away.
 		 */
-		if (!test->prog_type && unpriv_disabled) {
+		if (test_as_unpriv(test) && unpriv_disabled) {
 			printf("#%d/u %s SKIP\n", i, test->descr);
 			skips++;
-		} else if (!test->prog_type) {
+		} else if (test_as_unpriv(test)) {
 			if (!unpriv)
 				set_admin(false);
 			printf("#%d/u %s ", i, test->descr);
-- 
cgit v1.2.3


From ab21c1b5f799395232b838e98981cfed6d647905 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 24 Oct 2018 22:05:44 +0200
Subject: bpf: disallow direct packet access for unpriv in cg_skb

Commit b39b5f411dcf ("bpf: add cg_skb_is_valid_access for
BPF_PROG_TYPE_CGROUP_SKB") added support for returning pkt pointers
for direct packet access. Given this program type is allowed for both
unprivileged and privileged users, we shouldn't allow unprivileged
ones to use it, e.g. besides others one reason would be to avoid any
potential speculation on the packet test itself, thus guard this for
root only.

Fixes: b39b5f411dcf ("bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/core/filter.c                           | 6 ++++++
 tools/testing/selftests/bpf/test_verifier.c | 2 +-
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/net/core/filter.c b/net/core/filter.c
index 35c6933c2622..3fdddfa9a0fd 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5496,7 +5496,13 @@ static bool cg_skb_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range(struct __sk_buff, flow_keys):
 		return false;
+	case bpf_ctx_range(struct __sk_buff, data):
+	case bpf_ctx_range(struct __sk_buff, data_end):
+		if (!capable(CAP_SYS_ADMIN))
+			return false;
+		break;
 	}
+
 	if (type == BPF_WRITE) {
 		switch (off) {
 		case bpf_ctx_range(struct __sk_buff, mark):
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 8e1a79d2792c..36f3d3009d1a 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -4892,7 +4892,7 @@ static struct bpf_test tests[] = {
 		},
 		.result = ACCEPT,
 		.result_unpriv = REJECT,
-		.errstr_unpriv = "R3 pointer comparison prohibited",
+		.errstr_unpriv = "invalid bpf_context access off=76 size=4",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 	},
 	{
-- 
cgit v1.2.3


From 48dc0ef19044bfb69193302fbe3a834e3331b7ae Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Mon, 22 Oct 2018 18:16:26 -0300
Subject: selftests/powerpc: Fix ptrace tm failure

Test ptrace-tm-spd-gpr fails on current kernel (4.19) due to a segmentation
fault that happens on the child process prior to setting cptr[2] = 1. This
causes the parent process to wait forever at 'while (!pptr[2])' and the test to
be killed by the test harness framework by timeout, thus, failing.

The segmentation fault happens because of a inline assembly being
generated as:

	0x10000355c <tm_spd_gpr+492>    lfs    f0, 0(0)

This is reading memory position 0x0 and causing the segmentation fault.

This code is being generated by ASM_LOAD_FPR_SINGLE_PRECISION(flt_4), where
flt_4 is passed to the inline assembly block as:

	[flt_4] "r" (&d)

Since the inline assembly 'r' constraint means any GPR, gpr0 is being
chosen, thus causing this issue when issuing a Load Floating-Point Single
instruction.

This patch simply changes the constraint to 'b', which specify that this
register will be used as base, and r0 is not allowed to be used, avoiding
this issue.

Other than that, removing flt_2 register from the input operands, since it
is not used by the inline assembly code at all.

Cc: stable@vger.kernel.org
Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Segher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c
index 327fa943c7f3..dbdffa2e2c82 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c
@@ -67,8 +67,8 @@ trans:
 		"3: ;"
 		: [res] "=r" (result), [texasr] "=r" (texasr)
 		: [gpr_1]"i"(GPR_1), [gpr_2]"i"(GPR_2), [gpr_4]"i"(GPR_4),
-		[sprn_texasr] "i" (SPRN_TEXASR), [flt_1] "r" (&a),
-		[flt_2] "r" (&b), [flt_4] "r" (&d)
+		[sprn_texasr] "i" (SPRN_TEXASR), [flt_1] "b" (&a),
+		[flt_4] "b" (&d)
 		: "memory", "r5", "r6", "r7",
 		"r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15",
 		"r16", "r17", "r18", "r19", "r20", "r21", "r22", "r23",
-- 
cgit v1.2.3


From 58cfbac25b1fd2b76f94566aed28a3662b0ff8c6 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Fri, 26 Oct 2018 04:24:15 +1100
Subject: Revert "selftests/powerpc: Fix out-of-tree build errors"

This reverts commit d8a2fe29d3c97038c8efcc328d5e7940c5310565.

That commit, by me, fixed the out of tree build errors by causing some
of the tests not to build at all.
---
 tools/testing/selftests/powerpc/cache_shape/Makefile   | 2 ++
 tools/testing/selftests/powerpc/ptrace/Makefile        | 2 ++
 tools/testing/selftests/powerpc/signal/Makefile        | 2 ++
 tools/testing/selftests/powerpc/switch_endian/Makefile | 1 -
 4 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/cache_shape/Makefile b/tools/testing/selftests/powerpc/cache_shape/Makefile
index 62e947ca9921..ede4d3dae750 100644
--- a/tools/testing/selftests/powerpc/cache_shape/Makefile
+++ b/tools/testing/selftests/powerpc/cache_shape/Makefile
@@ -1,6 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := cache_shape
 
+all: $(TEST_PROGS)
+
 $(TEST_PROGS): ../harness.c ../utils.c
 
 top_srcdir = ../../../../..
diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile
index 6ac71b629276..9b35ca8e8f13 100644
--- a/tools/testing/selftests/powerpc/ptrace/Makefile
+++ b/tools/testing/selftests/powerpc/ptrace/Makefile
@@ -7,6 +7,8 @@ TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \
 top_srcdir = ../../../../..
 include ../../lib.mk
 
+all: $(TEST_PROGS)
+
 CFLAGS += -m64 -I../../../../../usr/include -I../tm -mhtm -fno-pie
 
 ptrace-pkey core-pkey: child.h
diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile
index d34a7c7710db..1fca25c6ace0 100644
--- a/tools/testing/selftests/powerpc/signal/Makefile
+++ b/tools/testing/selftests/powerpc/signal/Makefile
@@ -1,6 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 TEST_PROGS := signal signal_tm
 
+all: $(TEST_PROGS)
+
 $(TEST_PROGS): ../harness.c ../utils.c signal.S
 
 CFLAGS += -maltivec
diff --git a/tools/testing/selftests/powerpc/switch_endian/Makefile b/tools/testing/selftests/powerpc/switch_endian/Makefile
index bdc081afedb0..fcd2dcb8972b 100644
--- a/tools/testing/selftests/powerpc/switch_endian/Makefile
+++ b/tools/testing/selftests/powerpc/switch_endian/Makefile
@@ -8,7 +8,6 @@ EXTRA_CLEAN = $(OUTPUT)/*.o $(OUTPUT)/check-reversed.S
 top_srcdir = ../../../../..
 include ../../lib.mk
 
-$(OUTPUT)/switch_endian_test: ASFLAGS += -I $(OUTPUT)
 $(OUTPUT)/switch_endian_test: $(OUTPUT)/check-reversed.S
 
 $(OUTPUT)/check-reversed.o: $(OUTPUT)/check.o
-- 
cgit v1.2.3


From b1d29ba82cf2bc784f4c963ddd6a2cf29e229b33 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Fri, 26 Oct 2018 15:06:08 -0700
Subject: delayacct: track delays from thrashing cache pages

Delay accounting already measures the time a task spends in direct reclaim
and waiting for swapin, but in low memory situations tasks spend can spend
a significant amount of their time waiting on thrashing page cache.  This
isn't tracked right now.

To know the full impact of memory contention on an individual task,
measure the delay when waiting for a recently evicted active cache page to
read back into memory.

Also update tools/accounting/getdelays.c:

     [hannes@computer accounting]$ sudo ./getdelays -d -p 1
     print delayacct stats ON
     PID     1

     CPU             count     real total  virtual total    delay total  delay average
                     50318      745000000      847346785      400533713          0.008ms
     IO              count    delay total  delay average
                       435      122601218              0ms
     SWAP            count    delay total  delay average
                         0              0              0ms
     RECLAIM         count    delay total  delay average
                         0              0              0ms
     THRASHING       count    delay total  delay average
                        19       12621439              0ms

Link: http://lkml.kernel.org/r/20180828172258.3185-4-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Daniel Drake <drake@endlessm.com>
Tested-by: Suren Baghdasaryan <surenb@google.com>
Cc: Christopher Lameter <cl@linux.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Weiner <jweiner@fb.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Enderborg <peter.enderborg@sony.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vinayak Menon <vinmenon@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/delayacct.h      | 23 +++++++++++++++++++++++
 include/uapi/linux/taskstats.h |  6 +++++-
 kernel/delayacct.c             | 15 +++++++++++++++
 mm/filemap.c                   | 11 +++++++++++
 tools/accounting/getdelays.c   |  8 +++++++-
 5 files changed, 61 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 31c865d1842e..577d1b25fccd 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -57,7 +57,12 @@ struct task_delay_info {
 
 	u64 freepages_start;
 	u64 freepages_delay;	/* wait for memory reclaim */
+
+	u64 thrashing_start;
+	u64 thrashing_delay;	/* wait for thrashing page */
+
 	u32 freepages_count;	/* total count of memory reclaim */
+	u32 thrashing_count;	/* total count of thrash waits */
 };
 #endif
 
@@ -76,6 +81,8 @@ extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *);
 extern __u64 __delayacct_blkio_ticks(struct task_struct *);
 extern void __delayacct_freepages_start(void);
 extern void __delayacct_freepages_end(void);
+extern void __delayacct_thrashing_start(void);
+extern void __delayacct_thrashing_end(void);
 
 static inline int delayacct_is_task_waiting_on_io(struct task_struct *p)
 {
@@ -156,6 +163,18 @@ static inline void delayacct_freepages_end(void)
 		__delayacct_freepages_end();
 }
 
+static inline void delayacct_thrashing_start(void)
+{
+	if (current->delays)
+		__delayacct_thrashing_start();
+}
+
+static inline void delayacct_thrashing_end(void)
+{
+	if (current->delays)
+		__delayacct_thrashing_end();
+}
+
 #else
 static inline void delayacct_set_flag(int flag)
 {}
@@ -182,6 +201,10 @@ static inline void delayacct_freepages_start(void)
 {}
 static inline void delayacct_freepages_end(void)
 {}
+static inline void delayacct_thrashing_start(void)
+{}
+static inline void delayacct_thrashing_end(void)
+{}
 
 #endif /* CONFIG_TASK_DELAY_ACCT */
 
diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h
index b7aa7bb2349f..5e8ca16a9079 100644
--- a/include/uapi/linux/taskstats.h
+++ b/include/uapi/linux/taskstats.h
@@ -34,7 +34,7 @@
  */
 
 
-#define TASKSTATS_VERSION	8
+#define TASKSTATS_VERSION	9
 #define TS_COMM_LEN		32	/* should be >= TASK_COMM_LEN
 					 * in linux/sched.h */
 
@@ -164,6 +164,10 @@ struct taskstats {
 	/* Delay waiting for memory reclaim */
 	__u64	freepages_count;
 	__u64	freepages_delay_total;
+
+	/* Delay waiting for thrashing page */
+	__u64	thrashing_count;
+	__u64	thrashing_delay_total;
 };
 
 
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index ca8ac2824f0b..2a12b988c717 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -135,9 +135,12 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 	d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp;
 	tmp = d->freepages_delay_total + tsk->delays->freepages_delay;
 	d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp;
+	tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay;
+	d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp;
 	d->blkio_count += tsk->delays->blkio_count;
 	d->swapin_count += tsk->delays->swapin_count;
 	d->freepages_count += tsk->delays->freepages_count;
+	d->thrashing_count += tsk->delays->thrashing_count;
 	raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
 
 	return 0;
@@ -169,3 +172,15 @@ void __delayacct_freepages_end(void)
 		&current->delays->freepages_count);
 }
 
+void __delayacct_thrashing_start(void)
+{
+	current->delays->thrashing_start = ktime_get_ns();
+}
+
+void __delayacct_thrashing_end(void)
+{
+	delayacct_end(&current->delays->lock,
+		      &current->delays->thrashing_start,
+		      &current->delays->thrashing_delay,
+		      &current->delays->thrashing_count);
+}
diff --git a/mm/filemap.c b/mm/filemap.c
index 7997adce5a29..01a841f17bf4 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -36,6 +36,7 @@
 #include <linux/cleancache.h>
 #include <linux/shmem_fs.h>
 #include <linux/rmap.h>
+#include <linux/delayacct.h>
 #include "internal.h"
 
 #define CREATE_TRACE_POINTS
@@ -1073,8 +1074,15 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 {
 	struct wait_page_queue wait_page;
 	wait_queue_entry_t *wait = &wait_page.wait;
+	bool thrashing = false;
 	int ret = 0;
 
+	if (bit_nr == PG_locked && !PageSwapBacked(page) &&
+	    !PageUptodate(page) && PageWorkingset(page)) {
+		delayacct_thrashing_start();
+		thrashing = true;
+	}
+
 	init_wait(wait);
 	wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0;
 	wait->func = wake_page_function;
@@ -1113,6 +1121,9 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 
 	finish_wait(q, wait);
 
+	if (thrashing)
+		delayacct_thrashing_end();
+
 	/*
 	 * A signal could leave PageWaiters set. Clearing it here if
 	 * !waitqueue_active would be possible (by open-coding finish_wait),
diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c
index 9f420d98b5fb..8cb504d30384 100644
--- a/tools/accounting/getdelays.c
+++ b/tools/accounting/getdelays.c
@@ -203,6 +203,8 @@ static void print_delayacct(struct taskstats *t)
 	       "SWAP  %15s%15s%15s\n"
 	       "      %15llu%15llu%15llums\n"
 	       "RECLAIM  %12s%15s%15s\n"
+	       "      %15llu%15llu%15llums\n"
+	       "THRASHING%12s%15s%15s\n"
 	       "      %15llu%15llu%15llums\n",
 	       "count", "real total", "virtual total",
 	       "delay total", "delay average",
@@ -222,7 +224,11 @@ static void print_delayacct(struct taskstats *t)
 	       "count", "delay total", "delay average",
 	       (unsigned long long)t->freepages_count,
 	       (unsigned long long)t->freepages_delay_total,
-	       average_ms(t->freepages_delay_total, t->freepages_count));
+	       average_ms(t->freepages_delay_total, t->freepages_count),
+	       "count", "delay total", "delay average",
+	       (unsigned long long)t->thrashing_count,
+	       (unsigned long long)t->thrashing_delay_total,
+	       average_ms(t->thrashing_delay_total, t->thrashing_count));
 }
 
 static void task_context_switch_counts(struct taskstats *t)
-- 
cgit v1.2.3


From 439de0d7443789c688428429874b8e27f693c00e Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Fri, 26 Oct 2018 15:09:09 -0700
Subject: userfaultfd: selftest: cleanup help messages

Firstly, the help in the comment region is obsolete, now we support
three parameters.  Since at it, change it and move it into the help
message of the program.

Also, the help messages dumped here and there is obsolete too.  Use a
single usage() helper.

Link: http://lkml.kernel.org/r/20180930074259.18229-2-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Zi Yan <zi.yan@cs.rutgers.edu>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Shaohua Li <shli@fb.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/userfaultfd.c | 46 +++++++++++++++++++-------------
 1 file changed, 28 insertions(+), 18 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 7b8171e3128a..5ff3a4f9173e 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -34,18 +34,6 @@
  * per-CPU threads 1 by triggering userfaults inside
  * pthread_mutex_lock will also verify the atomicity of the memory
  * transfer (UFFDIO_COPY).
- *
- * The program takes two parameters: the amounts of physical memory in
- * megabytes (MiB) of the area and the number of bounces to execute.
- *
- * # 100MiB 99999 bounces
- * ./userfaultfd 100 99999
- *
- * # 1GiB 99 bounces
- * ./userfaultfd 1000 99
- *
- * # 10MiB-~6GiB 999 bounces, continue forever unless an error triggers
- * while ./userfaultfd $[RANDOM % 6000 + 10] 999; do true; done
  */
 
 #define _GNU_SOURCE
@@ -115,6 +103,30 @@ pthread_attr_t attr;
 				 ~(unsigned long)(sizeof(unsigned long long) \
 						  -  1)))
 
+const char *examples =
+    "# Run anonymous memory test on 100MiB region with 99999 bounces:\n"
+    "./userfaultfd anon 100 99999\n\n"
+    "# Run share memory test on 1GiB region with 99 bounces:\n"
+    "./userfaultfd shmem 1000 99\n\n"
+    "# Run hugetlb memory test on 256MiB region with 50 bounces (using /dev/hugepages/hugefile):\n"
+    "./userfaultfd hugetlb 256 50 /dev/hugepages/hugefile\n\n"
+    "# Run the same hugetlb test but using shmem:\n"
+    "./userfaultfd hugetlb_shared 256 50 /dev/hugepages/hugefile\n\n"
+    "# 10MiB-~6GiB 999 bounces anonymous test, "
+    "continue forever unless an error triggers\n"
+    "while ./userfaultfd anon $[RANDOM % 6000 + 10] 999; do true; done\n\n";
+
+static void usage(void)
+{
+	fprintf(stderr, "\nUsage: ./userfaultfd <test type> <MiB> <bounces> "
+		"[hugetlbfs_file]\n\n");
+	fprintf(stderr, "Supported <test type>: anon, hugetlb, "
+		"hugetlb_shared, shmem\n\n");
+	fprintf(stderr, "Examples:\n\n");
+	fprintf(stderr, examples);
+	exit(1);
+}
+
 static int anon_release_pages(char *rel_area)
 {
 	int ret = 0;
@@ -1272,8 +1284,7 @@ static void sigalrm(int sig)
 int main(int argc, char **argv)
 {
 	if (argc < 4)
-		fprintf(stderr, "Usage: <test type> <MiB> <bounces> [hugetlbfs_file]\n"),
-				exit(1);
+		usage();
 
 	if (signal(SIGALRM, sigalrm) == SIG_ERR)
 		fprintf(stderr, "failed to arm SIGALRM"), exit(1);
@@ -1286,20 +1297,19 @@ int main(int argc, char **argv)
 		nr_cpus;
 	if (!nr_pages_per_cpu) {
 		fprintf(stderr, "invalid MiB\n");
-		fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
+		usage();
 	}
 
 	bounces = atoi(argv[3]);
 	if (bounces <= 0) {
 		fprintf(stderr, "invalid bounces\n");
-		fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
+		usage();
 	}
 	nr_pages = nr_pages_per_cpu * nr_cpus;
 
 	if (test_type == TEST_HUGETLB) {
 		if (argc < 5)
-			fprintf(stderr, "Usage: hugetlb <MiB> <bounces> <hugetlbfs_file>\n"),
-				exit(1);
+			usage();
 		huge_fd = open(argv[4], O_CREAT | O_RDWR, 0755);
 		if (huge_fd < 0) {
 			fprintf(stderr, "Open of %s failed", argv[3]);
-- 
cgit v1.2.3


From 04d877319e2aa3895cc7998adb32de0967d3927b Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Fri, 26 Oct 2018 15:09:13 -0700
Subject: userfaultfd: selftest: generalize read and poll

We do very similar things in read and poll modes, but we're copying the
codes around.  Share the codes properly on reading the message and
handling the page fault to make the code cleaner.  Meanwhile this solves
previous mismatch of behaviors between the two modes on that the old code:

- did not check EAGAIN case in read() mode
- ignored BOUNCE_VERIFY check in read() mode

Link: http://lkml.kernel.org/r/20180930074259.18229-3-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Zi Yan <zi.yan@cs.rutgers.edu>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Shaohua Li <shli@fb.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/userfaultfd.c | 77 ++++++++++++++++++--------------
 1 file changed, 43 insertions(+), 34 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 5ff3a4f9173e..7a8c6937cc67 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -451,6 +451,43 @@ static int copy_page(int ufd, unsigned long offset)
 	return __copy_page(ufd, offset, false);
 }
 
+static int uffd_read_msg(int ufd, struct uffd_msg *msg)
+{
+	int ret = read(uffd, msg, sizeof(*msg));
+
+	if (ret != sizeof(*msg)) {
+		if (ret < 0) {
+			if (errno == EAGAIN)
+				return 1;
+			else
+				perror("blocking read error"), exit(1);
+		} else {
+			fprintf(stderr, "short read\n"), exit(1);
+		}
+	}
+
+	return 0;
+}
+
+/* Return 1 if page fault handled by us; otherwise 0 */
+static int uffd_handle_page_fault(struct uffd_msg *msg)
+{
+	unsigned long offset;
+
+	if (msg->event != UFFD_EVENT_PAGEFAULT)
+		fprintf(stderr, "unexpected msg event %u\n",
+			msg->event), exit(1);
+
+	if (bounces & BOUNCE_VERIFY &&
+	    msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
+		fprintf(stderr, "unexpected write fault\n"), exit(1);
+
+	offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst;
+	offset &= ~(page_size-1);
+
+	return copy_page(uffd, offset);
+}
+
 static void *uffd_poll_thread(void *arg)
 {
 	unsigned long cpu = (unsigned long) arg;
@@ -458,7 +495,6 @@ static void *uffd_poll_thread(void *arg)
 	struct uffd_msg msg;
 	struct uffdio_register uffd_reg;
 	int ret;
-	unsigned long offset;
 	char tmp_chr;
 	unsigned long userfaults = 0;
 
@@ -482,25 +518,15 @@ static void *uffd_poll_thread(void *arg)
 		if (!(pollfd[0].revents & POLLIN))
 			fprintf(stderr, "pollfd[0].revents %d\n",
 				pollfd[0].revents), exit(1);
-		ret = read(uffd, &msg, sizeof(msg));
-		if (ret < 0) {
-			if (errno == EAGAIN)
-				continue;
-			perror("nonblocking read error"), exit(1);
-		}
+		if (uffd_read_msg(uffd, &msg))
+			continue;
 		switch (msg.event) {
 		default:
 			fprintf(stderr, "unexpected msg event %u\n",
 				msg.event), exit(1);
 			break;
 		case UFFD_EVENT_PAGEFAULT:
-			if (msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
-				fprintf(stderr, "unexpected write fault\n"), exit(1);
-			offset = (char *)(unsigned long)msg.arg.pagefault.address -
-				area_dst;
-			offset &= ~(page_size-1);
-			if (copy_page(uffd, offset))
-				userfaults++;
+			userfaults += uffd_handle_page_fault(&msg);
 			break;
 		case UFFD_EVENT_FORK:
 			close(uffd);
@@ -528,8 +554,6 @@ static void *uffd_read_thread(void *arg)
 {
 	unsigned long *this_cpu_userfaults;
 	struct uffd_msg msg;
-	unsigned long offset;
-	int ret;
 
 	this_cpu_userfaults = (unsigned long *) arg;
 	*this_cpu_userfaults = 0;
@@ -538,24 +562,9 @@ static void *uffd_read_thread(void *arg)
 	/* from here cancellation is ok */
 
 	for (;;) {
-		ret = read(uffd, &msg, sizeof(msg));
-		if (ret != sizeof(msg)) {
-			if (ret < 0)
-				perror("blocking read error"), exit(1);
-			else
-				fprintf(stderr, "short read\n"), exit(1);
-		}
-		if (msg.event != UFFD_EVENT_PAGEFAULT)
-			fprintf(stderr, "unexpected msg event %u\n",
-				msg.event), exit(1);
-		if (bounces & BOUNCE_VERIFY &&
-		    msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
-			fprintf(stderr, "unexpected write fault\n"), exit(1);
-		offset = (char *)(unsigned long)msg.arg.pagefault.address -
-			 area_dst;
-		offset &= ~(page_size-1);
-		if (copy_page(uffd, offset))
-			(*this_cpu_userfaults)++;
+		if (uffd_read_msg(uffd, &msg))
+			continue;
+		(*this_cpu_userfaults) += uffd_handle_page_fault(&msg);
 	}
 	return (void *)NULL;
 }
-- 
cgit v1.2.3


From 7eaa8c969efa77127de9a05856eef9e5d22cf487 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Fri, 26 Oct 2018 15:09:17 -0700
Subject: userfaultfd: selftest: recycle lock threads first

Now we recycle the uffd servicing threads earlier than the lock threads.
It might happen that when the lock thread is still blocked at a pthread
mutex lock while the servicing thread has already quitted for the cpu so
the lock thread will be blocked forever and hang the test program.  To fix
the possible race, recycle the lock threads first.

This never happens with current missing-only tests, but when I start to
run the write-protection tests (the feature is not yet posted upstream) it
happens every time of the run possibly because in that new test we'll need
to service two page faults for each lock operation.

Link: http://lkml.kernel.org/r/20180930074259.18229-4-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Zi Yan <zi.yan@cs.rutgers.edu>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Shaohua Li <shli@fb.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/userfaultfd.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 7a8c6937cc67..5d1db824f73a 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -626,6 +626,12 @@ static int stress(unsigned long *userfaults)
 	if (uffd_test_ops->release_pages(area_src))
 		return 1;
 
+
+	finished = 1;
+	for (cpu = 0; cpu < nr_cpus; cpu++)
+		if (pthread_join(locking_threads[cpu], NULL))
+			return 1;
+
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		char c;
 		if (bounces & BOUNCE_POLL) {
@@ -643,11 +649,6 @@ static int stress(unsigned long *userfaults)
 		}
 	}
 
-	finished = 1;
-	for (cpu = 0; cpu < nr_cpus; cpu++)
-		if (pthread_join(locking_threads[cpu], NULL))
-			return 1;
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From 26db3d09d9e1963c9db77cb275bd2d36e56ef57a Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 26 Oct 2018 15:09:52 -0700
Subject: mm/gup_benchmark.c: time put_page()

We'd like to measure time to unpin user pages, so this adds a second
benchmark timer on put_page, separate from get_page.

Adding the field breaks this ioctl ABI, but should be okay since this an
in-tree kernel selftest.

[akpm@linux-foundation.org: add expansion to struct gup_benchmark for future use]
Link: http://lkml.kernel.org/r/20181010195605.10689-1-keith.busch@intel.com
Signed-off-by: Keith Busch <keith.busch@intel.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/gup_benchmark.c                         | 9 +++++++--
 tools/testing/selftests/vm/gup_benchmark.c | 6 ++++--
 2 files changed, 11 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
index 7405c9d89d65..e6aff102373b 100644
--- a/mm/gup_benchmark.c
+++ b/mm/gup_benchmark.c
@@ -8,11 +8,13 @@
 #define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_benchmark)
 
 struct gup_benchmark {
-	__u64 delta_usec;
+	__u64 get_delta_usec;
+	__u64 put_delta_usec;
 	__u64 addr;
 	__u64 size;
 	__u32 nr_pages_per_call;
 	__u32 flags;
+	__u64 expansion[10];	/* For future use */
 };
 
 static int __gup_benchmark_ioctl(unsigned int cmd,
@@ -48,14 +50,17 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 	}
 	end_time = ktime_get();
 
-	gup->delta_usec = ktime_us_delta(end_time, start_time);
+	gup->get_delta_usec = ktime_us_delta(end_time, start_time);
 	gup->size = addr - gup->addr;
 
+	start_time = ktime_get();
 	for (i = 0; i < nr_pages; i++) {
 		if (!pages[i])
 			break;
 		put_page(pages[i]);
 	}
+	end_time = ktime_get();
+	gup->put_delta_usec = ktime_us_delta(end_time, start_time);
 
 	kvfree(pages);
 	return 0;
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index 36df55132036..bdcb97acd0ac 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -17,7 +17,8 @@
 #define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_benchmark)
 
 struct gup_benchmark {
-	__u64 delta_usec;
+	__u64 get_delta_usec;
+	__u64 put_delta_usec;
 	__u64 addr;
 	__u64 size;
 	__u32 nr_pages_per_call;
@@ -81,7 +82,8 @@ int main(int argc, char **argv)
 		if (ioctl(fd, GUP_FAST_BENCHMARK, &gup))
 			perror("ioctl"), exit(1);
 
-		printf("Time: %lld us", gup.delta_usec);
+		printf("Time: get:%lld put:%lld us", gup.get_delta_usec,
+			gup.put_delta_usec);
 		if (gup.size != size)
 			printf(", truncated (size: %lld)", gup.size);
 		printf("\n");
-- 
cgit v1.2.3


From 714a3a1ebafe6e23af55a5c694c308f4044a7e00 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 26 Oct 2018 15:09:56 -0700
Subject: mm/gup_benchmark.c: add additional pinning methods

Provide new gup benchmark ioctl commands to run different user page
pinning methods, get_user_pages_longterm() and get_user_pages(), in
addition to the existing get_user_pages_fast().

Link: http://lkml.kernel.org/r/20181010195605.10689-2-keith.busch@intel.com
Signed-off-by: Keith Busch <keith.busch@intel.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/gup_benchmark.c                         | 28 ++++++++++++++++++++++++++--
 tools/testing/selftests/vm/gup_benchmark.c | 13 +++++++++++--
 2 files changed, 37 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
index e6aff102373b..debf11388a60 100644
--- a/mm/gup_benchmark.c
+++ b/mm/gup_benchmark.c
@@ -6,6 +6,8 @@
 #include <linux/debugfs.h>
 
 #define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_benchmark)
+#define GUP_LONGTERM_BENCHMARK	_IOWR('g', 2, struct gup_benchmark)
+#define GUP_BENCHMARK		_IOWR('g', 3, struct gup_benchmark)
 
 struct gup_benchmark {
 	__u64 get_delta_usec;
@@ -43,7 +45,23 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 			nr = (next - addr) / PAGE_SIZE;
 		}
 
-		nr = get_user_pages_fast(addr, nr, gup->flags & 1, pages + i);
+		switch (cmd) {
+		case GUP_FAST_BENCHMARK:
+			nr = get_user_pages_fast(addr, nr, gup->flags & 1,
+						 pages + i);
+			break;
+		case GUP_LONGTERM_BENCHMARK:
+			nr = get_user_pages_longterm(addr, nr, gup->flags & 1,
+						     pages + i, NULL);
+			break;
+		case GUP_BENCHMARK:
+			nr = get_user_pages(addr, nr, gup->flags & 1, pages + i,
+					    NULL);
+			break;
+		default:
+			return -1;
+		}
+
 		if (nr <= 0)
 			break;
 		i += nr;
@@ -72,8 +90,14 @@ static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd,
 	struct gup_benchmark gup;
 	int ret;
 
-	if (cmd != GUP_FAST_BENCHMARK)
+	switch (cmd) {
+	case GUP_FAST_BENCHMARK:
+	case GUP_LONGTERM_BENCHMARK:
+	case GUP_BENCHMARK:
+		break;
+	default:
 		return -EINVAL;
+	}
 
 	if (copy_from_user(&gup, (void __user *)arg, sizeof(gup)))
 		return -EFAULT;
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index bdcb97acd0ac..c2f785ded9b9 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -15,6 +15,8 @@
 #define PAGE_SIZE sysconf(_SC_PAGESIZE)
 
 #define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_benchmark)
+#define GUP_LONGTERM_BENCHMARK	_IOWR('g', 2, struct gup_benchmark)
+#define GUP_BENCHMARK		_IOWR('g', 3, struct gup_benchmark)
 
 struct gup_benchmark {
 	__u64 get_delta_usec;
@@ -30,9 +32,10 @@ int main(int argc, char **argv)
 	struct gup_benchmark gup;
 	unsigned long size = 128 * MB;
 	int i, fd, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
+	int cmd = GUP_FAST_BENCHMARK;
 	char *p;
 
-	while ((opt = getopt(argc, argv, "m:r:n:tT")) != -1) {
+	while ((opt = getopt(argc, argv, "m:r:n:tTLU")) != -1) {
 		switch (opt) {
 		case 'm':
 			size = atoi(optarg) * MB;
@@ -49,6 +52,12 @@ int main(int argc, char **argv)
 		case 'T':
 			thp = 0;
 			break;
+		case 'L':
+			cmd = GUP_LONGTERM_BENCHMARK;
+			break;
+		case 'U':
+			cmd = GUP_BENCHMARK;
+			break;
 		case 'w':
 			write = 1;
 		default:
@@ -79,7 +88,7 @@ int main(int argc, char **argv)
 
 	for (i = 0; i < repeats; i++) {
 		gup.size = size;
-		if (ioctl(fd, GUP_FAST_BENCHMARK, &gup))
+		if (ioctl(fd, cmd, &gup))
 			perror("ioctl"), exit(1);
 
 		printf("Time: get:%lld put:%lld us", gup.get_delta_usec,
-- 
cgit v1.2.3


From 319e0bec1aecb36c5ac6d23812af487ff2c8f47f Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 26 Oct 2018 15:09:59 -0700
Subject: tools/testing/selftests/vm/gup_benchmark.c: fix 'write' flag usage

If the '-w' parameter was provided, the benchmark would exit due to a
mssing 'break'.

Link: http://lkml.kernel.org/r/20181010195605.10689-3-keith.busch@intel.com
Signed-off-by: Keith Busch <keith.busch@intel.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/gup_benchmark.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index c2f785ded9b9..b2082df8beb4 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -60,6 +60,7 @@ int main(int argc, char **argv)
 			break;
 		case 'w':
 			write = 1;
+			break;
 		default:
 			return -1;
 		}
-- 
cgit v1.2.3


From aeb85ed4f41a8c0f5c4606d69f5da75e2348d984 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 26 Oct 2018 15:10:02 -0700
Subject: tools/testing/selftests/vm/gup_benchmark.c: allow user specified file

Allow a user to specify a file to map by adding a new option, '-f',
providing a means to test various file backings.

If not specified, the benchmark will use a private mapping of /dev/zero,
which produces an anonymous mapping as before.

[akpm@linux-foundation.org: avoid using comma operator]
Link: http://lkml.kernel.org/r/20181010195605.10689-4-keith.busch@intel.com
Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/gup_benchmark.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index b2082df8beb4..43a2d60e0e93 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -31,11 +31,12 @@ int main(int argc, char **argv)
 {
 	struct gup_benchmark gup;
 	unsigned long size = 128 * MB;
-	int i, fd, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
+	int i, fd, filed, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
 	int cmd = GUP_FAST_BENCHMARK;
+	char *file = "/dev/zero";
 	char *p;
 
-	while ((opt = getopt(argc, argv, "m:r:n:tTLU")) != -1) {
+	while ((opt = getopt(argc, argv, "m:r:n:f:tTLU")) != -1) {
 		switch (opt) {
 		case 'm':
 			size = atoi(optarg) * MB;
@@ -61,11 +62,20 @@ int main(int argc, char **argv)
 		case 'w':
 			write = 1;
 			break;
+		case 'f':
+			file = optarg;
+			break;
 		default:
 			return -1;
 		}
 	}
 
+	filed = open(file, O_RDWR|O_CREAT);
+	if (filed < 0) {
+		perror("open");
+		exit(filed);
+	}
+
 	gup.nr_pages_per_call = nr_pages;
 	gup.flags = write;
 
@@ -73,8 +83,7 @@ int main(int argc, char **argv)
 	if (fd == -1)
 		perror("open"), exit(1);
 
-	p = mmap(NULL, size, PROT_READ | PROT_WRITE,
-			MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	p = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE, filed, 0);
 	if (p == MAP_FAILED)
 		perror("mmap"), exit(1);
 	gup.addr = (unsigned long)p;
-- 
cgit v1.2.3


From 0dd8666afb99c71d124e0c2abf1ad7d934a242a0 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 26 Oct 2018 15:10:08 -0700
Subject: tools/testing/selftests/vm/gup_benchmark.c: add MAP_SHARED option

Add a new benchmark option, -S, to request MAP_SHARED.  This can be used
to compare with MAP_PRIVATE, or for files that require this option, like
dax.

Link: http://lkml.kernel.org/r/20181010195605.10689-5-keith.busch@intel.com
Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/gup_benchmark.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index 43a2d60e0e93..5c8e4cb1441a 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -32,11 +32,11 @@ int main(int argc, char **argv)
 	struct gup_benchmark gup;
 	unsigned long size = 128 * MB;
 	int i, fd, filed, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
-	int cmd = GUP_FAST_BENCHMARK;
+	int cmd = GUP_FAST_BENCHMARK, flags = MAP_PRIVATE;
 	char *file = "/dev/zero";
 	char *p;
 
-	while ((opt = getopt(argc, argv, "m:r:n:f:tTLU")) != -1) {
+	while ((opt = getopt(argc, argv, "m:r:n:f:tTLUS")) != -1) {
 		switch (opt) {
 		case 'm':
 			size = atoi(optarg) * MB;
@@ -65,6 +65,10 @@ int main(int argc, char **argv)
 		case 'f':
 			file = optarg;
 			break;
+		case 'S':
+			flags &= ~MAP_PRIVATE;
+			flags |= MAP_SHARED;
+			break;
 		default:
 			return -1;
 		}
@@ -83,7 +87,7 @@ int main(int argc, char **argv)
 	if (fd == -1)
 		perror("open"), exit(1);
 
-	p = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE, filed, 0);
+	p = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, filed, 0);
 	if (p == MAP_FAILED)
 		perror("mmap"), exit(1);
 	gup.addr = (unsigned long)p;
-- 
cgit v1.2.3


From 3821b76c3cdb5f2c5ef1b082de79829e8ff50a7d Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 26 Oct 2018 15:10:12 -0700
Subject: tools/testing/selftests/vm/gup_benchmark.c: add MAP_HUGETLB option

Add a new option '-H' to the gup benchmark to help understand how hugetlb
mapping pages compare with the default.

Link: http://lkml.kernel.org/r/20181010195605.10689-6-keith.busch@intel.com
Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/gup_benchmark.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index 5c8e4cb1441a..880b96fc80d4 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -36,7 +36,7 @@ int main(int argc, char **argv)
 	char *file = "/dev/zero";
 	char *p;
 
-	while ((opt = getopt(argc, argv, "m:r:n:f:tTLUS")) != -1) {
+	while ((opt = getopt(argc, argv, "m:r:n:f:tTLUSH")) != -1) {
 		switch (opt) {
 		case 'm':
 			size = atoi(optarg) * MB;
@@ -69,6 +69,9 @@ int main(int argc, char **argv)
 			flags &= ~MAP_PRIVATE;
 			flags |= MAP_SHARED;
 			break;
+		case 'H':
+			flags |= MAP_HUGETLB;
+			break;
 		default:
 			return -1;
 		}
-- 
cgit v1.2.3


From 91cbacc34512e37c9bb89125ca4b224ca6459245 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Fri, 26 Oct 2018 15:10:48 -0700
Subject: tools/testing/selftests/vm/map_fixed_noreplace.c: add test for
 MAP_FIXED_NOREPLACE

Add a test for MAP_FIXED_NOREPLACE, based on some code originally by Jann
Horn.  This would have caught the overlap bug reported by Daniel Micay.

I originally suggested to Michal that we create MAP_FIXED_NOREPLACE, but
instead of writing a selftest I spent my time bike-shedding whether it
should be called MAP_FIXED_SAFE/NOCLOBBER/WEAK/NEW ..  mea culpa.

Link: http://lkml.kernel.org/r/20181013133929.28653-1-mpe@ellerman.id.au
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Khalid Aziz <khalid.aziz@oracle.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Jann Horn <jannh@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Cc: Joel Stanley <joel@jms.id.au>
Cc: Jason Evans <jasone@google.com>
Cc: David Goldblatt <davidtgoldblatt@gmail.com>
Cc: Daniel Micay <danielmicay@gmail.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/.gitignore            |   1 +
 tools/testing/selftests/vm/Makefile              |   1 +
 tools/testing/selftests/vm/map_fixed_noreplace.c | 206 +++++++++++++++++++++++
 3 files changed, 208 insertions(+)
 create mode 100644 tools/testing/selftests/vm/map_fixed_noreplace.c

(limited to 'tools')

diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index af5ff83f6d7f..31b3c98b6d34 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -13,3 +13,4 @@ mlock-random-test
 virtual_address_range
 gup_benchmark
 va_128TBswitch
+map_fixed_noreplace
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index e94b7b14bcb2..6e67e726e5a5 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -12,6 +12,7 @@ TEST_GEN_FILES += gup_benchmark
 TEST_GEN_FILES += hugepage-mmap
 TEST_GEN_FILES += hugepage-shm
 TEST_GEN_FILES += map_hugetlb
+TEST_GEN_FILES += map_fixed_noreplace
 TEST_GEN_FILES += map_populate
 TEST_GEN_FILES += mlock-random-test
 TEST_GEN_FILES += mlock2-tests
diff --git a/tools/testing/selftests/vm/map_fixed_noreplace.c b/tools/testing/selftests/vm/map_fixed_noreplace.c
new file mode 100644
index 000000000000..d91bde511268
--- /dev/null
+++ b/tools/testing/selftests/vm/map_fixed_noreplace.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Test that MAP_FIXED_NOREPLACE works.
+ *
+ * Copyright 2018, Jann Horn <jannh@google.com>
+ * Copyright 2018, Michael Ellerman, IBM Corporation.
+ */
+
+#include <sys/mman.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#ifndef MAP_FIXED_NOREPLACE
+#define MAP_FIXED_NOREPLACE 0x100000
+#endif
+
+#define BASE_ADDRESS	(256ul * 1024 * 1024)
+
+
+static void dump_maps(void)
+{
+	char cmd[32];
+
+	snprintf(cmd, sizeof(cmd), "cat /proc/%d/maps", getpid());
+	system(cmd);
+}
+
+int main(void)
+{
+	unsigned long flags, addr, size, page_size;
+	char *p;
+
+	page_size = sysconf(_SC_PAGE_SIZE);
+
+	flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED_NOREPLACE;
+
+	// Check we can map all the areas we need below
+	errno = 0;
+	addr = BASE_ADDRESS;
+	size = 5 * page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p == MAP_FAILED) {
+		dump_maps();
+		printf("Error: couldn't map the space we need for the test\n");
+		return 1;
+	}
+
+	errno = 0;
+	if (munmap((void *)addr, 5 * page_size) != 0) {
+		dump_maps();
+		printf("Error: munmap failed!?\n");
+		return 1;
+	}
+	printf("unmap() successful\n");
+
+	errno = 0;
+	addr = BASE_ADDRESS + page_size;
+	size = 3 * page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p == MAP_FAILED) {
+		dump_maps();
+		printf("Error: first mmap() failed unexpectedly\n");
+		return 1;
+	}
+
+	/*
+	 * Exact same mapping again:
+	 *   base |  free  | new
+	 *     +1 | mapped | new
+	 *     +2 | mapped | new
+	 *     +3 | mapped | new
+	 *     +4 |  free  | new
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS;
+	size = 5 * page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p != MAP_FAILED) {
+		dump_maps();
+		printf("Error:1: mmap() succeeded when it shouldn't have\n");
+		return 1;
+	}
+
+	/*
+	 * Second mapping contained within first:
+	 *
+	 *   base |  free  |
+	 *     +1 | mapped |
+	 *     +2 | mapped | new
+	 *     +3 | mapped |
+	 *     +4 |  free  |
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS + (2 * page_size);
+	size = page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p != MAP_FAILED) {
+		dump_maps();
+		printf("Error:2: mmap() succeeded when it shouldn't have\n");
+		return 1;
+	}
+
+	/*
+	 * Overlap end of existing mapping:
+	 *   base |  free  |
+	 *     +1 | mapped |
+	 *     +2 | mapped |
+	 *     +3 | mapped | new
+	 *     +4 |  free  | new
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS + (3 * page_size);
+	size = 2 * page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p != MAP_FAILED) {
+		dump_maps();
+		printf("Error:3: mmap() succeeded when it shouldn't have\n");
+		return 1;
+	}
+
+	/*
+	 * Overlap start of existing mapping:
+	 *   base |  free  | new
+	 *     +1 | mapped | new
+	 *     +2 | mapped |
+	 *     +3 | mapped |
+	 *     +4 |  free  |
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS;
+	size = 2 * page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p != MAP_FAILED) {
+		dump_maps();
+		printf("Error:4: mmap() succeeded when it shouldn't have\n");
+		return 1;
+	}
+
+	/*
+	 * Adjacent to start of existing mapping:
+	 *   base |  free  | new
+	 *     +1 | mapped |
+	 *     +2 | mapped |
+	 *     +3 | mapped |
+	 *     +4 |  free  |
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS;
+	size = page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p == MAP_FAILED) {
+		dump_maps();
+		printf("Error:5: mmap() failed when it shouldn't have\n");
+		return 1;
+	}
+
+	/*
+	 * Adjacent to end of existing mapping:
+	 *   base |  free  |
+	 *     +1 | mapped |
+	 *     +2 | mapped |
+	 *     +3 | mapped |
+	 *     +4 |  free  |  new
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS + (4 * page_size);
+	size = page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p == MAP_FAILED) {
+		dump_maps();
+		printf("Error:6: mmap() failed when it shouldn't have\n");
+		return 1;
+	}
+
+	addr = BASE_ADDRESS;
+	size = 5 * page_size;
+	if (munmap((void *)addr, size) != 0) {
+		dump_maps();
+		printf("Error: munmap failed!?\n");
+		return 1;
+	}
+	printf("unmap() successful\n");
+
+	printf("OK\n");
+	return 0;
+}
-- 
cgit v1.2.3


From 0d0352d8b3d6d7ca9a710b40e194cbbaeb841c88 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Mon, 22 Oct 2018 00:08:48 +0900
Subject: selftests/ftrace: Fix synthetic event test to delete event correctly

Fix the synthetic event test case to remove event correctly.
If redirecting command to synthetic_event file without append
mode, it cleans up all existing events and execute (parse) the
command. This means "delete event" always fails to find the
target event.

Since previous synthetic event has a bug which doesn't return
-ENOENT even if it fails to find the deleting event, this test
passed. But fixing that bug, this test fails because this test
itself has a bug.

This fixes that bug by trying to delete event right after
adding an event, and use append mode redirection ('>>') instead
of normal redirection ('>').

Link: http://lkml.kernel.org/r/154013452832.25576.2305459545429386517.stgit@devbox

Acked-by: Shuah Khan <shuah@kernel.org>
Acked-by: Tom Zanussi <zanussi@linux.intel.com>
Tested-by: Tom Zanussi <zanussi@linux.intel.com>
Cc: Tom Zanussi <zanussi@kernel.org>
Cc: Tom Zanussi <tom.zanussi@linux.intel.com>
Cc: Rajvi Jingar <rajvi.jingar@intel.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: stable@vger.kernel.org
Fixes: f06eec4d0f2c ('selftests: ftrace: Add inter-event hist triggers testcases')
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 .../inter-event/trigger-synthetic-event-createremove.tc      | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc
index cef11377dcbd..c604438df13b 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc
@@ -35,18 +35,18 @@ fi
 
 reset_trigger
 
-echo "Test create synthetic event with an error"
-echo 'wakeup_latency  u64 lat pid_t pid char' > synthetic_events > /dev/null
+echo "Test remove synthetic event"
+echo '!wakeup_latency  u64 lat pid_t pid char comm[16]' >> synthetic_events
 if [ -d events/synthetic/wakeup_latency ]; then
-    fail "Created wakeup_latency synthetic event with an invalid format"
+    fail "Failed to delete wakeup_latency synthetic event"
 fi
 
 reset_trigger
 
-echo "Test remove synthetic event"
-echo '!wakeup_latency  u64 lat pid_t pid char comm[16]' > synthetic_events
+echo "Test create synthetic event with an error"
+echo 'wakeup_latency  u64 lat pid_t pid char' > synthetic_events > /dev/null
 if [ -d events/synthetic/wakeup_latency ]; then
-    fail "Failed to delete wakeup_latency synthetic event"
+    fail "Created wakeup_latency synthetic event with an invalid format"
 fi
 
 do_reset
-- 
cgit v1.2.3


From a95ecac5cb2fc8a8ee606991384d33ee121df00c Mon Sep 17 00:00:00 2001
From: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Date: Tue, 23 Oct 2018 13:34:56 +0530
Subject: selftests/powerpc: Relax L1d miss targets for rfi_flush test

When running the rfi_flush test, if the system is loaded, we see two
issues:
1. The L1d misses when rfi_flush is disabled increase significantly due
to other workloads interfering with the cache.
2. The L1d misses when rfi_flush is enabled sometimes goes slightly
below the expected number of misses.

To address these, let's relax the expected number of L1d misses:
1. When rfi_flush is disabled, we allow upto half the expected number of
the misses for when rfi_flush is enabled.
2. When rfi_flush is enabled, we allow ~1% lower number of cache misses.

Reported-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Tested-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/security/rfi_flush.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/security/rfi_flush.c b/tools/testing/selftests/powerpc/security/rfi_flush.c
index 564ed45bbf73..0a7d0afb26b8 100644
--- a/tools/testing/selftests/powerpc/security/rfi_flush.c
+++ b/tools/testing/selftests/powerpc/security/rfi_flush.c
@@ -49,6 +49,7 @@ int rfi_flush_test(void)
 	struct perf_event_read v;
 	__u64 l1d_misses_total = 0;
 	unsigned long iterations = 100000, zero_size = 24 * 1024;
+	unsigned long l1d_misses_expected;
 	int rfi_flush_org, rfi_flush;
 
 	SKIP_IF(geteuid() != 0);
@@ -71,6 +72,12 @@ int rfi_flush_test(void)
 
 	iter = repetitions;
 
+	/*
+	 * We expect to see l1d miss for each cacheline access when rfi_flush
+	 * is set. Allow a small variation on this.
+	 */
+	l1d_misses_expected = iterations * (zero_size / CACHELINE_SIZE - 2);
+
 again:
 	FAIL_IF(perf_event_reset(fd));
 
@@ -78,10 +85,9 @@ again:
 
 	FAIL_IF(read(fd, &v, sizeof(v)) != sizeof(v));
 
-	/* Expect at least zero_size/CACHELINE_SIZE misses per iteration */
-	if (v.l1d_misses >= (iterations * zero_size / CACHELINE_SIZE) && rfi_flush)
+	if (rfi_flush && v.l1d_misses >= l1d_misses_expected)
 		passes++;
-	else if (v.l1d_misses < iterations && !rfi_flush)
+	else if (!rfi_flush && v.l1d_misses < (l1d_misses_expected / 2))
 		passes++;
 
 	l1d_misses_total += v.l1d_misses;
@@ -92,13 +98,15 @@ again:
 	if (passes < repetitions) {
 		printf("FAIL (L1D misses with rfi_flush=%d: %llu %c %lu) [%d/%d failures]\n",
 		       rfi_flush, l1d_misses_total, rfi_flush ? '<' : '>',
-		       rfi_flush ? (repetitions * iterations * zero_size / CACHELINE_SIZE) : iterations,
+		       rfi_flush ? repetitions * l1d_misses_expected :
+		       repetitions * l1d_misses_expected / 2,
 		       repetitions - passes, repetitions);
 		rc = 1;
 	} else
 		printf("PASS (L1D misses with rfi_flush=%d: %llu %c %lu) [%d/%d pass]\n",
 		       rfi_flush, l1d_misses_total, rfi_flush ? '>' : '<',
-		       rfi_flush ? (repetitions * iterations * zero_size / CACHELINE_SIZE) : iterations,
+		       rfi_flush ? repetitions * l1d_misses_expected :
+		       repetitions * l1d_misses_expected / 2,
 		       passes, repetitions);
 
 	if (rfi_flush == rfi_flush_org) {
-- 
cgit v1.2.3


From f443f38c5789ece6ebe59ae21c27bf861e61c4e2 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 24 Oct 2018 14:31:12 -0300
Subject: tools include uapi: Grab a copy of linux/fs.h

We'll use it to create tables for the 'flags' argument to the 'mount'
and 'umount' syscalls.

Add it to check_headers.sh so that when a new protocol gets added we get
a notification during the build process.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-yacf9jvkwfwg2g95r2us3xb3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/fs.h | 393 ++++++++++++++++++++++++++++++++++++++++++
 tools/perf/check-headers.sh   |   1 +
 2 files changed, 394 insertions(+)
 create mode 100644 tools/include/uapi/linux/fs.h

(limited to 'tools')

diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
new file mode 100644
index 000000000000..73e01918f996
--- /dev/null
+++ b/tools/include/uapi/linux/fs.h
@@ -0,0 +1,393 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_FS_H
+#define _UAPI_LINUX_FS_H
+
+/*
+ * This file has definitions for some important file table structures
+ * and constants and structures used by various generic file system
+ * ioctl's.  Please do not make any changes in this file before
+ * sending patches for review to linux-fsdevel@vger.kernel.org and
+ * linux-api@vger.kernel.org.
+ */
+
+#include <linux/limits.h>
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/*
+ * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
+ * the file limit at runtime and only root can increase the per-process
+ * nr_file rlimit, so it's safe to set up a ridiculously high absolute
+ * upper limit on files-per-process.
+ *
+ * Some programs (notably those using select()) may have to be 
+ * recompiled to take full advantage of the new limits..  
+ */
+
+/* Fixed constants first: */
+#undef NR_OPEN
+#define INR_OPEN_CUR 1024	/* Initial setting for nfile rlimits */
+#define INR_OPEN_MAX 4096	/* Hard limit for nfile rlimits */
+
+#define BLOCK_SIZE_BITS 10
+#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
+
+#define SEEK_SET	0	/* seek relative to beginning of file */
+#define SEEK_CUR	1	/* seek relative to current file position */
+#define SEEK_END	2	/* seek relative to end of file */
+#define SEEK_DATA	3	/* seek to the next data */
+#define SEEK_HOLE	4	/* seek to the next hole */
+#define SEEK_MAX	SEEK_HOLE
+
+#define RENAME_NOREPLACE	(1 << 0)	/* Don't overwrite target */
+#define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
+#define RENAME_WHITEOUT		(1 << 2)	/* Whiteout source */
+
+struct file_clone_range {
+	__s64 src_fd;
+	__u64 src_offset;
+	__u64 src_length;
+	__u64 dest_offset;
+};
+
+struct fstrim_range {
+	__u64 start;
+	__u64 len;
+	__u64 minlen;
+};
+
+/* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
+#define FILE_DEDUPE_RANGE_SAME		0
+#define FILE_DEDUPE_RANGE_DIFFERS	1
+
+/* from struct btrfs_ioctl_file_extent_same_info */
+struct file_dedupe_range_info {
+	__s64 dest_fd;		/* in - destination file */
+	__u64 dest_offset;	/* in - start of extent in destination */
+	__u64 bytes_deduped;	/* out - total # of bytes we were able
+				 * to dedupe from this file. */
+	/* status of this dedupe operation:
+	 * < 0 for error
+	 * == FILE_DEDUPE_RANGE_SAME if dedupe succeeds
+	 * == FILE_DEDUPE_RANGE_DIFFERS if data differs
+	 */
+	__s32 status;		/* out - see above description */
+	__u32 reserved;		/* must be zero */
+};
+
+/* from struct btrfs_ioctl_file_extent_same_args */
+struct file_dedupe_range {
+	__u64 src_offset;	/* in - start of extent in source */
+	__u64 src_length;	/* in - length of extent */
+	__u16 dest_count;	/* in - total elements in info array */
+	__u16 reserved1;	/* must be zero */
+	__u32 reserved2;	/* must be zero */
+	struct file_dedupe_range_info info[0];
+};
+
+/* And dynamically-tunable limits and defaults: */
+struct files_stat_struct {
+	unsigned long nr_files;		/* read only */
+	unsigned long nr_free_files;	/* read only */
+	unsigned long max_files;		/* tunable */
+};
+
+struct inodes_stat_t {
+	long nr_inodes;
+	long nr_unused;
+	long dummy[5];		/* padding for sysctl ABI compatibility */
+};
+
+
+#define NR_FILE  8192	/* this can well be larger on a larger system */
+
+
+/*
+ * These are the fs-independent mount-flags: up to 32 flags are supported
+ */
+#define MS_RDONLY	 1	/* Mount read-only */
+#define MS_NOSUID	 2	/* Ignore suid and sgid bits */
+#define MS_NODEV	 4	/* Disallow access to device special files */
+#define MS_NOEXEC	 8	/* Disallow program execution */
+#define MS_SYNCHRONOUS	16	/* Writes are synced at once */
+#define MS_REMOUNT	32	/* Alter flags of a mounted FS */
+#define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
+#define MS_DIRSYNC	128	/* Directory modifications are synchronous */
+#define MS_NOATIME	1024	/* Do not update access times. */
+#define MS_NODIRATIME	2048	/* Do not update directory access times */
+#define MS_BIND		4096
+#define MS_MOVE		8192
+#define MS_REC		16384
+#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
+				   MS_VERBOSE is deprecated. */
+#define MS_SILENT	32768
+#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
+#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
+#define MS_PRIVATE	(1<<18)	/* change to private */
+#define MS_SLAVE	(1<<19)	/* change to slave */
+#define MS_SHARED	(1<<20)	/* change to shared */
+#define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
+#define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
+#define MS_I_VERSION	(1<<23) /* Update inode I_version field */
+#define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
+#define MS_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
+
+/* These sb flags are internal to the kernel */
+#define MS_SUBMOUNT     (1<<26)
+#define MS_NOREMOTELOCK	(1<<27)
+#define MS_NOSEC	(1<<28)
+#define MS_BORN		(1<<29)
+#define MS_ACTIVE	(1<<30)
+#define MS_NOUSER	(1<<31)
+
+/*
+ * Superblock flags that can be altered by MS_REMOUNT
+ */
+#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\
+			 MS_LAZYTIME)
+
+/*
+ * Old magic mount flag and mask
+ */
+#define MS_MGC_VAL 0xC0ED0000
+#define MS_MGC_MSK 0xffff0000
+
+/*
+ * Structure for FS_IOC_FSGETXATTR[A] and FS_IOC_FSSETXATTR.
+ */
+struct fsxattr {
+	__u32		fsx_xflags;	/* xflags field value (get/set) */
+	__u32		fsx_extsize;	/* extsize field value (get/set)*/
+	__u32		fsx_nextents;	/* nextents field value (get)	*/
+	__u32		fsx_projid;	/* project identifier (get/set) */
+	__u32		fsx_cowextsize;	/* CoW extsize field value (get/set)*/
+	unsigned char	fsx_pad[8];
+};
+
+/*
+ * Flags for the fsx_xflags field
+ */
+#define FS_XFLAG_REALTIME	0x00000001	/* data in realtime volume */
+#define FS_XFLAG_PREALLOC	0x00000002	/* preallocated file extents */
+#define FS_XFLAG_IMMUTABLE	0x00000008	/* file cannot be modified */
+#define FS_XFLAG_APPEND		0x00000010	/* all writes append */
+#define FS_XFLAG_SYNC		0x00000020	/* all writes synchronous */
+#define FS_XFLAG_NOATIME	0x00000040	/* do not update access time */
+#define FS_XFLAG_NODUMP		0x00000080	/* do not include in backups */
+#define FS_XFLAG_RTINHERIT	0x00000100	/* create with rt bit set */
+#define FS_XFLAG_PROJINHERIT	0x00000200	/* create with parents projid */
+#define FS_XFLAG_NOSYMLINKS	0x00000400	/* disallow symlink creation */
+#define FS_XFLAG_EXTSIZE	0x00000800	/* extent size allocator hint */
+#define FS_XFLAG_EXTSZINHERIT	0x00001000	/* inherit inode extent size */
+#define FS_XFLAG_NODEFRAG	0x00002000	/* do not defragment */
+#define FS_XFLAG_FILESTREAM	0x00004000	/* use filestream allocator */
+#define FS_XFLAG_DAX		0x00008000	/* use DAX for IO */
+#define FS_XFLAG_COWEXTSIZE	0x00010000	/* CoW extent size allocator hint */
+#define FS_XFLAG_HASATTR	0x80000000	/* no DIFLAG for this	*/
+
+/* the read-only stuff doesn't really belong here, but any other place is
+   probably as bad and I don't want to create yet another include file. */
+
+#define BLKROSET   _IO(0x12,93)	/* set device read-only (0 = read-write) */
+#define BLKROGET   _IO(0x12,94)	/* get read-only status (0 = read_write) */
+#define BLKRRPART  _IO(0x12,95)	/* re-read partition table */
+#define BLKGETSIZE _IO(0x12,96)	/* return device size /512 (long *arg) */
+#define BLKFLSBUF  _IO(0x12,97)	/* flush buffer cache */
+#define BLKRASET   _IO(0x12,98)	/* set read ahead for block device */
+#define BLKRAGET   _IO(0x12,99)	/* get current read ahead setting */
+#define BLKFRASET  _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */
+#define BLKFRAGET  _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */
+#define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */
+#define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */
+#define BLKSSZGET  _IO(0x12,104)/* get block device sector size */
+#if 0
+#define BLKPG      _IO(0x12,105)/* See blkpg.h */
+
+/* Some people are morons.  Do not use sizeof! */
+
+#define BLKELVGET  _IOR(0x12,106,size_t)/* elevator get */
+#define BLKELVSET  _IOW(0x12,107,size_t)/* elevator set */
+/* This was here just to show that the number is taken -
+   probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */
+#endif
+/* A jump here: 108-111 have been used for various private purposes. */
+#define BLKBSZGET  _IOR(0x12,112,size_t)
+#define BLKBSZSET  _IOW(0x12,113,size_t)
+#define BLKGETSIZE64 _IOR(0x12,114,size_t)	/* return device size in bytes (u64 *arg) */
+#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup)
+#define BLKTRACESTART _IO(0x12,116)
+#define BLKTRACESTOP _IO(0x12,117)
+#define BLKTRACETEARDOWN _IO(0x12,118)
+#define BLKDISCARD _IO(0x12,119)
+#define BLKIOMIN _IO(0x12,120)
+#define BLKIOOPT _IO(0x12,121)
+#define BLKALIGNOFF _IO(0x12,122)
+#define BLKPBSZGET _IO(0x12,123)
+#define BLKDISCARDZEROES _IO(0x12,124)
+#define BLKSECDISCARD _IO(0x12,125)
+#define BLKROTATIONAL _IO(0x12,126)
+#define BLKZEROOUT _IO(0x12,127)
+/*
+ * A jump here: 130-131 are reserved for zoned block devices
+ * (see uapi/linux/blkzoned.h)
+ */
+
+#define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
+#define FIBMAP	   _IO(0x00,1)	/* bmap access */
+#define FIGETBSZ   _IO(0x00,2)	/* get the block size used for bmap */
+#define FIFREEZE	_IOWR('X', 119, int)	/* Freeze */
+#define FITHAW		_IOWR('X', 120, int)	/* Thaw */
+#define FITRIM		_IOWR('X', 121, struct fstrim_range)	/* Trim */
+#define FICLONE		_IOW(0x94, 9, int)
+#define FICLONERANGE	_IOW(0x94, 13, struct file_clone_range)
+#define FIDEDUPERANGE	_IOWR(0x94, 54, struct file_dedupe_range)
+
+#define FSLABEL_MAX 256	/* Max chars for the interface; each fs may differ */
+
+#define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
+#define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
+#define	FS_IOC_GETVERSION		_IOR('v', 1, long)
+#define	FS_IOC_SETVERSION		_IOW('v', 2, long)
+#define FS_IOC_FIEMAP			_IOWR('f', 11, struct fiemap)
+#define FS_IOC32_GETFLAGS		_IOR('f', 1, int)
+#define FS_IOC32_SETFLAGS		_IOW('f', 2, int)
+#define FS_IOC32_GETVERSION		_IOR('v', 1, int)
+#define FS_IOC32_SETVERSION		_IOW('v', 2, int)
+#define FS_IOC_FSGETXATTR		_IOR('X', 31, struct fsxattr)
+#define FS_IOC_FSSETXATTR		_IOW('X', 32, struct fsxattr)
+#define FS_IOC_GETFSLABEL		_IOR(0x94, 49, char[FSLABEL_MAX])
+#define FS_IOC_SETFSLABEL		_IOW(0x94, 50, char[FSLABEL_MAX])
+
+/*
+ * File system encryption support
+ */
+/* Policy provided via an ioctl on the topmost directory */
+#define FS_KEY_DESCRIPTOR_SIZE	8
+
+#define FS_POLICY_FLAGS_PAD_4		0x00
+#define FS_POLICY_FLAGS_PAD_8		0x01
+#define FS_POLICY_FLAGS_PAD_16		0x02
+#define FS_POLICY_FLAGS_PAD_32		0x03
+#define FS_POLICY_FLAGS_PAD_MASK	0x03
+#define FS_POLICY_FLAGS_VALID		0x03
+
+/* Encryption algorithms */
+#define FS_ENCRYPTION_MODE_INVALID		0
+#define FS_ENCRYPTION_MODE_AES_256_XTS		1
+#define FS_ENCRYPTION_MODE_AES_256_GCM		2
+#define FS_ENCRYPTION_MODE_AES_256_CBC		3
+#define FS_ENCRYPTION_MODE_AES_256_CTS		4
+#define FS_ENCRYPTION_MODE_AES_128_CBC		5
+#define FS_ENCRYPTION_MODE_AES_128_CTS		6
+#define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7
+#define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8
+
+struct fscrypt_policy {
+	__u8 version;
+	__u8 contents_encryption_mode;
+	__u8 filenames_encryption_mode;
+	__u8 flags;
+	__u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
+};
+
+#define FS_IOC_SET_ENCRYPTION_POLICY	_IOR('f', 19, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_PWSALT	_IOW('f', 20, __u8[16])
+#define FS_IOC_GET_ENCRYPTION_POLICY	_IOW('f', 21, struct fscrypt_policy)
+
+/* Parameters for passing an encryption key into the kernel keyring */
+#define FS_KEY_DESC_PREFIX		"fscrypt:"
+#define FS_KEY_DESC_PREFIX_SIZE		8
+
+/* Structure that userspace passes to the kernel keyring */
+#define FS_MAX_KEY_SIZE			64
+
+struct fscrypt_key {
+	__u32 mode;
+	__u8 raw[FS_MAX_KEY_SIZE];
+	__u32 size;
+};
+
+/*
+ * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
+ *
+ * Note: for historical reasons, these flags were originally used and
+ * defined for use by ext2/ext3, and then other file systems started
+ * using these flags so they wouldn't need to write their own version
+ * of chattr/lsattr (which was shipped as part of e2fsprogs).  You
+ * should think twice before trying to use these flags in new
+ * contexts, or trying to assign these flags, since they are used both
+ * as the UAPI and the on-disk encoding for ext2/3/4.  Also, we are
+ * almost out of 32-bit flags.  :-)
+ *
+ * We have recently hoisted FS_IOC_FSGETXATTR / FS_IOC_FSSETXATTR from
+ * XFS to the generic FS level interface.  This uses a structure that
+ * has padding and hence has more room to grow, so it may be more
+ * appropriate for many new use cases.
+ *
+ * Please do not change these flags or interfaces before checking with
+ * linux-fsdevel@vger.kernel.org and linux-api@vger.kernel.org.
+ */
+#define	FS_SECRM_FL			0x00000001 /* Secure deletion */
+#define	FS_UNRM_FL			0x00000002 /* Undelete */
+#define	FS_COMPR_FL			0x00000004 /* Compress file */
+#define FS_SYNC_FL			0x00000008 /* Synchronous updates */
+#define FS_IMMUTABLE_FL			0x00000010 /* Immutable file */
+#define FS_APPEND_FL			0x00000020 /* writes to file may only append */
+#define FS_NODUMP_FL			0x00000040 /* do not dump file */
+#define FS_NOATIME_FL			0x00000080 /* do not update atime */
+/* Reserved for compression usage... */
+#define FS_DIRTY_FL			0x00000100
+#define FS_COMPRBLK_FL			0x00000200 /* One or more compressed clusters */
+#define FS_NOCOMP_FL			0x00000400 /* Don't compress */
+/* End compression flags --- maybe not all used */
+#define FS_ENCRYPT_FL			0x00000800 /* Encrypted file */
+#define FS_BTREE_FL			0x00001000 /* btree format dir */
+#define FS_INDEX_FL			0x00001000 /* hash-indexed directory */
+#define FS_IMAGIC_FL			0x00002000 /* AFS directory */
+#define FS_JOURNAL_DATA_FL		0x00004000 /* Reserved for ext3 */
+#define FS_NOTAIL_FL			0x00008000 /* file tail should not be merged */
+#define FS_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
+#define FS_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
+#define FS_HUGE_FILE_FL			0x00040000 /* Reserved for ext4 */
+#define FS_EXTENT_FL			0x00080000 /* Extents */
+#define FS_EA_INODE_FL			0x00200000 /* Inode used for large EA */
+#define FS_EOFBLOCKS_FL			0x00400000 /* Reserved for ext4 */
+#define FS_NOCOW_FL			0x00800000 /* Do not cow file */
+#define FS_INLINE_DATA_FL		0x10000000 /* Reserved for ext4 */
+#define FS_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
+#define FS_RESERVED_FL			0x80000000 /* reserved for ext2 lib */
+
+#define FS_FL_USER_VISIBLE		0x0003DFFF /* User visible flags */
+#define FS_FL_USER_MODIFIABLE		0x000380FF /* User modifiable flags */
+
+
+#define SYNC_FILE_RANGE_WAIT_BEFORE	1
+#define SYNC_FILE_RANGE_WRITE		2
+#define SYNC_FILE_RANGE_WAIT_AFTER	4
+
+/*
+ * Flags for preadv2/pwritev2:
+ */
+
+typedef int __bitwise __kernel_rwf_t;
+
+/* high priority request, poll if possible */
+#define RWF_HIPRI	((__force __kernel_rwf_t)0x00000001)
+
+/* per-IO O_DSYNC */
+#define RWF_DSYNC	((__force __kernel_rwf_t)0x00000002)
+
+/* per-IO O_SYNC */
+#define RWF_SYNC	((__force __kernel_rwf_t)0x00000004)
+
+/* per-IO, return -EAGAIN if operation would block */
+#define RWF_NOWAIT	((__force __kernel_rwf_t)0x00000008)
+
+/* per-IO O_APPEND */
+#define RWF_APPEND	((__force __kernel_rwf_t)0x00000010)
+
+/* mask of flags supported by the kernel */
+#define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
+			 RWF_APPEND)
+
+#endif /* _UAPI_LINUX_FS_H */
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index c72cc73a6b09..9531f7bd7d9b 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -5,6 +5,7 @@ HEADERS='
 include/uapi/drm/drm.h
 include/uapi/drm/i915_drm.h
 include/uapi/linux/fcntl.h
+include/uapi/linux/fs.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
 include/uapi/linux/in.h
-- 
cgit v1.2.3


From ceaf8e5b49ce18e9e58d292130e92150d01a34e6 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 24 Oct 2018 14:54:55 -0300
Subject: perf beauty: Add a generator for MS_ mount/umount's flag constants

It'll use tools/include copy of linux/fs.h to generate a table to be
used by tools, initially by the 'mount' and 'umount' beautifiers in
'perf trace', but that could also be used to translate from a string
constant to the integer value to be used in a eBPF or tracefs tracepoint
filter.

When used without any args it produces:

  $ tools/perf/trace/beauty/mount_flags.sh
  static const char *mount_flags[] = {
	[1 ? (ilog2(1) + 1) : 0] = "RDONLY",
	[2 ? (ilog2(2) + 1) : 0] = "NOSUID",
	[4 ? (ilog2(4) + 1) : 0] = "NODEV",
	[8 ? (ilog2(8) + 1) : 0] = "NOEXEC",
	[16 ? (ilog2(16) + 1) : 0] = "SYNCHRONOUS",
	[32 ? (ilog2(32) + 1) : 0] = "REMOUNT",
	[64 ? (ilog2(64) + 1) : 0] = "MANDLOCK",
	[128 ? (ilog2(128) + 1) : 0] = "DIRSYNC",
	[1024 ? (ilog2(1024) + 1) : 0] = "NOATIME",
	[2048 ? (ilog2(2048) + 1) : 0] = "NODIRATIME",
	[4096 ? (ilog2(4096) + 1) : 0] = "BIND",
	[8192 ? (ilog2(8192) + 1) : 0] = "MOVE",
	[16384 ? (ilog2(16384) + 1) : 0] = "REC",
	[32768 ? (ilog2(32768) + 1) : 0] = "SILENT",
	[16 + 1] = "POSIXACL",
	[17 + 1] = "UNBINDABLE",
	[18 + 1] = "PRIVATE",
	[19 + 1] = "SLAVE",
	[20 + 1] = "SHARED",
	[21 + 1] = "RELATIME",
	[22 + 1] = "KERNMOUNT",
	[23 + 1] = "I_VERSION",
	[24 + 1] = "STRICTATIME",
	[25 + 1] = "LAZYTIME",
	[26 + 1] = "SUBMOUNT",
	[27 + 1] = "NOREMOTELOCK",
	[28 + 1] = "NOSEC",
	[29 + 1] = "BORN",
	[30 + 1] = "ACTIVE",
	[31 + 1] = "NOUSER",
  };
  $

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mgutbbkmip9gfnmd28ikg7xt@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/mount_flags.sh | 15 +++++++++++++++
 1 file changed, 15 insertions(+)
 create mode 100755 tools/perf/trace/beauty/mount_flags.sh

(limited to 'tools')

diff --git a/tools/perf/trace/beauty/mount_flags.sh b/tools/perf/trace/beauty/mount_flags.sh
new file mode 100755
index 000000000000..45547573a1db
--- /dev/null
+++ b/tools/perf/trace/beauty/mount_flags.sh
@@ -0,0 +1,15 @@
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+
+printf "static const char *mount_flags[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
+egrep $regex ${header_dir}/fs.h | egrep -v '(MSK|VERBOSE|MGC_VAL)\>' | \
+	sed -r "s/$regex/\2 \2 \1/g" | sort -n | \
+	xargs printf "\t[%s ? (ilog2(%s) + 1) : 0] = \"%s\",\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+\(1<<([[:digit:]]+)\)[[:space:]]*.*'
+egrep $regex ${header_dir}/fs.h | \
+	sed -r "s/$regex/\2 \1/g" | \
+	xargs printf "\t[%s + 1] = \"%s\",\n"
+printf "};\n"
-- 
cgit v1.2.3


From 794f594e0c3be6199e0b3e2324280e8785806fb6 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 24 Oct 2018 15:54:23 -0300
Subject: perf beauty: Switch from GPL v2.0 to LGPL v2.1

The intention is to have this as a library, since it is not perf
specific at all.

I did the switch for the files where I'm the only contributor, with the
exception of a few lines changed by Jiri Olsa.

Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-a04q6chdyjknm1hr305ulx8h@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/clone.c                     | 3 +--
 tools/perf/trace/beauty/drm_ioctl.sh                | 1 +
 tools/perf/trace/beauty/eventfd.c                   | 2 +-
 tools/perf/trace/beauty/fcntl.c                     | 3 +--
 tools/perf/trace/beauty/flock.c                     | 2 +-
 tools/perf/trace/beauty/futex_op.c                  | 2 +-
 tools/perf/trace/beauty/futex_val3.c                | 2 +-
 tools/perf/trace/beauty/ioctl.c                     | 3 +--
 tools/perf/trace/beauty/kcmp.c                      | 3 +--
 tools/perf/trace/beauty/kcmp_type.sh                | 1 +
 tools/perf/trace/beauty/kvm_ioctl.sh                | 1 +
 tools/perf/trace/beauty/madvise_behavior.sh         | 1 +
 tools/perf/trace/beauty/mmap.c                      | 2 +-
 tools/perf/trace/beauty/mode_t.c                    | 2 +-
 tools/perf/trace/beauty/msg_flags.c                 | 2 +-
 tools/perf/trace/beauty/open_flags.c                | 2 +-
 tools/perf/trace/beauty/perf_event_open.c           | 2 +-
 tools/perf/trace/beauty/perf_ioctl.sh               | 1 +
 tools/perf/trace/beauty/pid.c                       | 3 ++-
 tools/perf/trace/beauty/pkey_alloc.c                | 3 +--
 tools/perf/trace/beauty/pkey_alloc_access_rights.sh | 1 +
 tools/perf/trace/beauty/prctl.c                     | 3 +--
 tools/perf/trace/beauty/prctl_option.sh             | 1 +
 tools/perf/trace/beauty/sched_policy.c              | 2 +-
 tools/perf/trace/beauty/seccomp.c                   | 2 +-
 tools/perf/trace/beauty/signum.c                    | 2 +-
 tools/perf/trace/beauty/sndrv_ctl_ioctl.sh          | 1 +
 tools/perf/trace/beauty/sndrv_pcm_ioctl.sh          | 1 +
 tools/perf/trace/beauty/sockaddr.c                  | 2 +-
 tools/perf/trace/beauty/socket.c                    | 2 +-
 tools/perf/trace/beauty/socket_ipproto.sh           | 1 +
 tools/perf/trace/beauty/socket_type.c               | 2 +-
 tools/perf/trace/beauty/statx.c                     | 3 +--
 tools/perf/trace/beauty/vhost_virtio_ioctl.sh       | 1 +
 tools/perf/trace/beauty/waitid_options.c            | 2 +-
 35 files changed, 36 insertions(+), 31 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c
index d64d049ab991..010406500c30 100644
--- a/tools/perf/trace/beauty/clone.c
+++ b/tools/perf/trace/beauty/clone.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/cone.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh
index 9d3816815e60..9aa94fd523a9 100755
--- a/tools/perf/trace/beauty/drm_ioctl.sh
+++ b/tools/perf/trace/beauty/drm_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/
 
diff --git a/tools/perf/trace/beauty/eventfd.c b/tools/perf/trace/beauty/eventfd.c
index 5d6a477a6400..db5b9b492113 100644
--- a/tools/perf/trace/beauty/eventfd.c
+++ b/tools/perf/trace/beauty/eventfd.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #ifndef EFD_SEMAPHORE
 #define EFD_SEMAPHORE		1
 #endif
diff --git a/tools/perf/trace/beauty/fcntl.c b/tools/perf/trace/beauty/fcntl.c
index 9e8900c13cb1..e6de31674e24 100644
--- a/tools/perf/trace/beauty/fcntl.c
+++ b/tools/perf/trace/beauty/fcntl.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/fcntl.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/flock.c b/tools/perf/trace/beauty/flock.c
index c4ff6ad30b06..cf02ae5f0ba6 100644
--- a/tools/perf/trace/beauty/flock.c
+++ b/tools/perf/trace/beauty/flock.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 
 #include "trace/beauty/beauty.h"
 #include <linux/kernel.h>
diff --git a/tools/perf/trace/beauty/futex_op.c b/tools/perf/trace/beauty/futex_op.c
index 61850fbc85ff..1136bde56406 100644
--- a/tools/perf/trace/beauty/futex_op.c
+++ b/tools/perf/trace/beauty/futex_op.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <linux/futex.h>
 
 #ifndef FUTEX_WAIT_BITSET
diff --git a/tools/perf/trace/beauty/futex_val3.c b/tools/perf/trace/beauty/futex_val3.c
index 26f6b3253511..138b7d588a70 100644
--- a/tools/perf/trace/beauty/futex_val3.c
+++ b/tools/perf/trace/beauty/futex_val3.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <linux/futex.h>
 
 #ifndef FUTEX_BITSET_MATCH_ANY
diff --git a/tools/perf/trace/beauty/ioctl.c b/tools/perf/trace/beauty/ioctl.c
index 1be3b4cf0827..5d2a7fd8d407 100644
--- a/tools/perf/trace/beauty/ioctl.c
+++ b/tools/perf/trace/beauty/ioctl.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/ioctl.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/kcmp.c b/tools/perf/trace/beauty/kcmp.c
index f62040eb9d5c..b276a274f203 100644
--- a/tools/perf/trace/beauty/kcmp.c
+++ b/tools/perf/trace/beauty/kcmp.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/kcmp.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh
index a3c304caa336..df8b17486d57 100755
--- a/tools/perf/trace/beauty/kcmp_type.sh
+++ b/tools/perf/trace/beauty/kcmp_type.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh
index c4699fd46bb6..4ce54f5bf756 100755
--- a/tools/perf/trace/beauty/kvm_ioctl.sh
+++ b/tools/perf/trace/beauty/kvm_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh
index 431639eb4d29..4527d290cdfc 100755
--- a/tools/perf/trace/beauty/madvise_behavior.sh
+++ b/tools/perf/trace/beauty/madvise_behavior.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 9f68077b241b..0605593552c6 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <uapi/linux/mman.h>
 
 static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
diff --git a/tools/perf/trace/beauty/mode_t.c b/tools/perf/trace/beauty/mode_t.c
index d929ad7dd97b..6879d36d3004 100644
--- a/tools/perf/trace/beauty/mode_t.c
+++ b/tools/perf/trace/beauty/mode_t.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
diff --git a/tools/perf/trace/beauty/msg_flags.c b/tools/perf/trace/beauty/msg_flags.c
index c064d6aae659..1b9d6306d274 100644
--- a/tools/perf/trace/beauty/msg_flags.c
+++ b/tools/perf/trace/beauty/msg_flags.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/socket.h>
 
diff --git a/tools/perf/trace/beauty/open_flags.c b/tools/perf/trace/beauty/open_flags.c
index 6aec6178a99d..cc673fec9184 100644
--- a/tools/perf/trace/beauty/open_flags.c
+++ b/tools/perf/trace/beauty/open_flags.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
diff --git a/tools/perf/trace/beauty/perf_event_open.c b/tools/perf/trace/beauty/perf_event_open.c
index 2bafd7c995ff..981185c1974b 100644
--- a/tools/perf/trace/beauty/perf_event_open.c
+++ b/tools/perf/trace/beauty/perf_event_open.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #ifndef PERF_FLAG_FD_NO_GROUP
 # define PERF_FLAG_FD_NO_GROUP		(1UL << 0)
 #endif
diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh
index 6492c74df928..9aabd9743ef6 100755
--- a/tools/perf/trace/beauty/perf_ioctl.sh
+++ b/tools/perf/trace/beauty/perf_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/pid.c b/tools/perf/trace/beauty/pid.c
index 0313df342830..1a6acc46807b 100644
--- a/tools/perf/trace/beauty/pid.c
+++ b/tools/perf/trace/beauty/pid.c
@@ -1,4 +1,5 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
+
 size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_arg *arg)
 {
 	int pid = arg->val;
diff --git a/tools/perf/trace/beauty/pkey_alloc.c b/tools/perf/trace/beauty/pkey_alloc.c
index 2ba784a3734a..d3e5188a9bef 100644
--- a/tools/perf/trace/beauty/pkey_alloc.c
+++ b/tools/perf/trace/beauty/pkey_alloc.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/pkey_alloc.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
index e0a51aeb20b2..f8f1b560cf8a 100755
--- a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
+++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
diff --git a/tools/perf/trace/beauty/prctl.c b/tools/perf/trace/beauty/prctl.c
index 246130dad6c4..be7a5d395975 100644
--- a/tools/perf/trace/beauty/prctl.c
+++ b/tools/perf/trace/beauty/prctl.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/prctl.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
index f24722146ebe..d32f8f1124af 100755
--- a/tools/perf/trace/beauty/prctl_option.sh
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/sched_policy.c b/tools/perf/trace/beauty/sched_policy.c
index ba5096ae76b6..48f2b5c9aa3e 100644
--- a/tools/perf/trace/beauty/sched_policy.c
+++ b/tools/perf/trace/beauty/sched_policy.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sched.h>
 
 /*
diff --git a/tools/perf/trace/beauty/seccomp.c b/tools/perf/trace/beauty/seccomp.c
index b7097fd5fed9..e36156b19c70 100644
--- a/tools/perf/trace/beauty/seccomp.c
+++ b/tools/perf/trace/beauty/seccomp.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #ifndef SECCOMP_SET_MODE_STRICT
 #define SECCOMP_SET_MODE_STRICT 0
 #endif
diff --git a/tools/perf/trace/beauty/signum.c b/tools/perf/trace/beauty/signum.c
index bde18a53f090..587fec545b8a 100644
--- a/tools/perf/trace/beauty/signum.c
+++ b/tools/perf/trace/beauty/signum.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <signal.h>
 
 static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg)
diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
index eb511bb5fbd3..e0803b957593 100755
--- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
index 6818392968b2..7a464a7bf913 100755
--- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
diff --git a/tools/perf/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c
index 71a79f72d9d9..9410ad230f10 100644
--- a/tools/perf/trace/beauty/sockaddr.c
+++ b/tools/perf/trace/beauty/sockaddr.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 // Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c
index 65227269384b..d971a2596417 100644
--- a/tools/perf/trace/beauty/socket.c
+++ b/tools/perf/trace/beauty/socket.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/socket.c
  *
diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh
index a3cc24633bec..de0f2f29017f 100755
--- a/tools/perf/trace/beauty/socket_ipproto.sh
+++ b/tools/perf/trace/beauty/socket_ipproto.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/socket_type.c b/tools/perf/trace/beauty/socket_type.c
index bca26aef4a77..a63a9a332aa0 100644
--- a/tools/perf/trace/beauty/socket_type.c
+++ b/tools/perf/trace/beauty/socket_type.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/socket.h>
 
diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c
index 5643b692af4c..630f2760dd66 100644
--- a/tools/perf/trace/beauty/statx.c
+++ b/tools/perf/trace/beauty/statx.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/statx.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
index 0f6a5197d0be..439773daaf77 100755
--- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
+++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/waitid_options.c b/tools/perf/trace/beauty/waitid_options.c
index 8465281a093d..42ff58ad613b 100644
--- a/tools/perf/trace/beauty/waitid_options.c
+++ b/tools/perf/trace/beauty/waitid_options.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/wait.h>
 
-- 
cgit v1.2.3


From 579e5ff629b17744f62473f314768de8b6f1e66c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 25 Oct 2018 14:21:31 -0300
Subject: perf beauty: Introduce strarray__scnprintf_flags()

Generalizing pkey_alloc__scnprintf_access_rights(), so that we can use
it with other flags-like arguments, such as mount's mountflags argument.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-o3ymi3104m8moaz9865g09w9@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/beauty.h     |  1 +
 tools/perf/trace/beauty/pkey_alloc.c | 27 ++++++++++++++++-----------
 2 files changed, 17 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 2570152d3909..a1806c4f3ccd 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -24,6 +24,7 @@ struct strarray {
 }
 
 size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const char *intfmt, int val);
+size_t strarray__scnprintf_flags(struct strarray *sa, char *bf, size_t size, unsigned long flags);
 
 struct trace;
 struct thread;
diff --git a/tools/perf/trace/beauty/pkey_alloc.c b/tools/perf/trace/beauty/pkey_alloc.c
index d3e5188a9bef..1b8ed4cac815 100644
--- a/tools/perf/trace/beauty/pkey_alloc.c
+++ b/tools/perf/trace/beauty/pkey_alloc.c
@@ -9,31 +9,28 @@
 #include <linux/kernel.h>
 #include <linux/log2.h>
 
-static size_t pkey_alloc__scnprintf_access_rights(int access_rights, char *bf, size_t size)
+size_t strarray__scnprintf_flags(struct strarray *sa, char *bf, size_t size, unsigned long flags)
 {
 	int i, printed = 0;
 
-#include "trace/beauty/generated/pkey_alloc_access_rights_array.c"
-	static DEFINE_STRARRAY(pkey_alloc_access_rights);
-
-	if (access_rights == 0) {
-		const char *s = strarray__pkey_alloc_access_rights.entries[0];
+	if (flags == 0) {
+		const char *s = sa->entries[0];
 		if (s)
 			return scnprintf(bf, size, "%s", s);
 		return scnprintf(bf, size, "%d", 0);
 	}
 
-	for (i = 1; i < strarray__pkey_alloc_access_rights.nr_entries; ++i) {
-		int bit = 1 << (i - 1);
+	for (i = 1; i < sa->nr_entries; ++i) {
+		unsigned long bit = 1UL << (i - 1);
 
-		if (!(access_rights & bit))
+		if (!(flags & bit))
 			continue;
 
 		if (printed != 0)
 			printed += scnprintf(bf + printed, size - printed, "|");
 
-		if (strarray__pkey_alloc_access_rights.entries[i] != NULL)
-			printed += scnprintf(bf + printed, size - printed, "%s", strarray__pkey_alloc_access_rights.entries[i]);
+		if (sa->entries[i] != NULL)
+			printed += scnprintf(bf + printed, size - printed, "%s", sa->entries[i]);
 		else
 			printed += scnprintf(bf + printed, size - printed, "0x%#", bit);
 	}
@@ -41,6 +38,14 @@ static size_t pkey_alloc__scnprintf_access_rights(int access_rights, char *bf, s
 	return printed;
 }
 
+static size_t pkey_alloc__scnprintf_access_rights(int access_rights, char *bf, size_t size)
+{
+#include "trace/beauty/generated/pkey_alloc_access_rights_array.c"
+	static DEFINE_STRARRAY(pkey_alloc_access_rights);
+
+	return strarray__scnprintf_flags(&strarray__pkey_alloc_access_rights, bf, size, access_rights);
+}
+
 size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg)
 {
 	unsigned long cmd = arg->val;
-- 
cgit v1.2.3


From 496fd346b71ffa0ff35623e9ec79df0bad47bd66 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 25 Oct 2018 16:09:47 -0300
Subject: perf trace beauty: Allow syscalls to mask an argument before
 considering it

Take mount's 'flags' arg, to cope with this semantic, as defined in do_mount in fs/namespace.c:

  /*
   * Pre-0.97 versions of mount() didn't have a flags word.  When the
   * flags word was introduced its top half was required to have the
   * magic value 0xC0ED, and this remained so until 2.4.0-test9.
   * Therefore, if this magic number is present, it carries no
   * information and must be discarded.
   */

We need to mask this arg, and then see if it is zero, when we simply
don't print the arg name and value.

The next patch will use this for mount's 'flag' arg.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-btue14k5jemayuykfrwsnh85@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 7081d7ea12e5..14fb63e17de5 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -614,6 +614,7 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
 
 struct syscall_arg_fmt {
 	size_t	   (*scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
+	unsigned long (*mask_val)(struct syscall_arg *arg, unsigned long val);
 	void	   *parm;
 	const char *name;
 	bool	   show_zero;
@@ -1487,6 +1488,19 @@ static size_t syscall__scnprintf_name(struct syscall *sc, char *bf, size_t size,
 	return scnprintf(bf, size, "arg%d: ", arg->idx);
 }
 
+/*
+ * Check if the value is in fact zero, i.e. mask whatever needs masking, such
+ * as mount 'flags' argument that needs ignoring some magic flag, see comment
+ * in tools/perf/trace/beauty/mount_flags.c
+ */
+static unsigned long syscall__mask_val(struct syscall *sc, struct syscall_arg *arg, unsigned long val)
+{
+	if (sc->arg_fmt && sc->arg_fmt[arg->idx].mask_val)
+		return sc->arg_fmt[arg->idx].mask_val(arg, val);
+
+	return val;
+}
+
 static size_t syscall__scnprintf_val(struct syscall *sc, char *bf, size_t size,
 				     struct syscall_arg *arg, unsigned long val)
 {
@@ -1535,6 +1549,11 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
 				continue;
 
 			val = syscall_arg__val(&arg, arg.idx);
+			/*
+			 * Some syscall args need some mask, most don't and
+			 * return val untouched.
+			 */
+			val = syscall__mask_val(sc, &arg, val);
 
 			/*
  			 * Suppress this argument if its value is zero and
-- 
cgit v1.2.3


From 73d141adcea66de656d0c8336811f2b0bbd9700c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 25 Oct 2018 15:18:06 -0300
Subject: perf trace beauty: Beautify mount/umount's 'flags' argument

  # trace -e mount mount -o ro -t debugfs nodev /mnt
     0.000 ( 1.040 ms): mount/27235 mount(dev_name: 0x5601cc8c64e0, dir_name: 0x5601cc8c6500, type: 0x5601cc8c6480, flags: RDONLY) = 0
  # trace -e mount mount -o remount,relatime -t debugfs nodev /mnt
     0.000 ( 2.946 ms): mount/27262 mount(dev_name: 0x55f4a73d64e0, dir_name: 0x55f4a73d6500, type: 0x55f4a73d6480, flags: REMOUNT|RELATIME) = 0
  # trace -e mount mount -o remount,strictatime -t debugfs nodev /mnt
     0.000 ( 2.934 ms): mount/27265 mount(dev_name: 0x5617f71d94e0, dir_name: 0x5617f71d9500, type: 0x5617f71d9480, flags: REMOUNT|STRICTATIME) = 0
  # trace -e mount mount -o remount,suid,silent -t debugfs nodev /mnt
     0.000 ( 0.049 ms): mount/27273 mount(dev_name: 0x55ad65df24e0, dir_name: 0x55ad65df2500, type: 0x55ad65df2480, flags: REMOUNT|SILENT) = 0
  # trace -e mount mount -o remount,rw,sync,lazytime -t debugfs nodev /mnt
     0.000 ( 2.684 ms): mount/27281 mount(dev_name: 0x561216055530, dir_name: 0x561216055550, type: 0x561216055510, flags: SYNCHRONOUS|REMOUNT|LAZYTIME) = 0
  # trace -e mount mount -o remount,dirsync -t debugfs nodev /mnt
     0.000 ( 3.512 ms): mount/27314 mount(dev_name: 0x55c4e7188480, dir_name: 0x55c4e7188530, type: 0x55c4e71884a0, flags: REMOUNT|DIRSYNC, data: 0x55c4e71884e0) = 0
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-i5ncao73c0bd02qprgrq6wb9@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.perf              |  8 +++++++
 tools/perf/builtin-trace.c            |  3 +++
 tools/perf/trace/beauty/Build         |  1 +
 tools/perf/trace/beauty/beauty.h      |  6 +++++
 tools/perf/trace/beauty/mount_flags.c | 43 +++++++++++++++++++++++++++++++++++
 5 files changed, 61 insertions(+)
 create mode 100644 tools/perf/trace/beauty/mount_flags.c

(limited to 'tools')

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 2f3bf025e305..a31c5c29d53a 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -460,6 +460,12 @@ madvise_behavior_tbl := $(srctree)/tools/perf/trace/beauty/madvise_behavior.sh
 $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_tbl)
 	$(Q)$(SHELL) '$(madvise_behavior_tbl)' $(madvise_hdr_dir) > $@
 
+mount_flags_array := $(beauty_outdir)/mount_flags_array.c
+mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
+
+$(mount_flags_array): $(linux_uapi_dir)/fs.h $(mount_flags_tbl)
+	$(Q)$(SHELL) '$(mount_flags_tbl)' $(linux_uapi_dir) > $@
+
 prctl_option_array := $(beauty_outdir)/prctl_option_array.c
 prctl_hdr_dir := $(srctree)/tools/include/uapi/linux/
 prctl_option_tbl := $(srctree)/tools/perf/trace/beauty/prctl_option.sh
@@ -577,6 +583,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(socket_ipproto_array) \
 	$(vhost_virtio_ioctl_array) \
 	$(madvise_behavior_array) \
+	$(mount_flags_array) \
 	$(perf_ioctl_array) \
 	$(prctl_option_array) \
 	$(arch_errno_name_array)
@@ -863,6 +870,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
 		$(OUTPUT)pmu-events/pmu-events.c \
 		$(OUTPUT)$(madvise_behavior_array) \
+		$(OUTPUT)$(mount_flags_array) \
 		$(OUTPUT)$(drm_ioctl_array) \
 		$(OUTPUT)$(pkey_alloc_access_rights_array) \
 		$(OUTPUT)$(sndrv_ctl_ioctl_array) \
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 14fb63e17de5..76c14c0129fc 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -726,6 +726,9 @@ static struct syscall_fmt {
 	  .arg = { [0] = { .scnprintf = SCA_HEX,	/* addr */ },
 		   [2] = { .scnprintf = SCA_MMAP_PROT,	/* prot */ },
 		   [3] = { .scnprintf = SCA_MMAP_FLAGS,	/* flags */ }, }, },
+	{ .name	    = "mount",
+	  .arg = { [3] = { .scnprintf = SCA_MOUNT_FLAGS, /* flags */
+			   .mask_val  = SCAMV_MOUNT_FLAGS, /* flags */ }, }, },
 	{ .name	    = "mprotect",
 	  .arg = { [0] = { .scnprintf = SCA_HEX,	/* start */ },
 		   [2] = { .scnprintf = SCA_MMAP_PROT,	/* prot */ }, }, },
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index c3b0afd67760..304313073242 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -5,6 +5,7 @@ ifeq ($(SRCARCH),$(filter $(SRCARCH),x86))
 libperf-y += ioctl.o
 endif
 libperf-y += kcmp.o
+libperf-y += mount_flags.o
 libperf-y += pkey_alloc.o
 libperf-y += prctl.o
 libperf-y += sockaddr.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index a1806c4f3ccd..039c29039b2c 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -123,6 +123,12 @@ size_t syscall_arg__scnprintf_kcmp_type(char *bf, size_t size, struct syscall_ar
 size_t syscall_arg__scnprintf_kcmp_idx(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_KCMP_IDX syscall_arg__scnprintf_kcmp_idx
 
+unsigned long syscall_arg__mask_val_mount_flags(struct syscall_arg *arg, unsigned long flags);
+#define SCAMV_MOUNT_FLAGS syscall_arg__mask_val_mount_flags
+
+size_t syscall_arg__scnprintf_mount_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_MOUNT_FLAGS syscall_arg__scnprintf_mount_flags
+
 size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PKEY_ALLOC_ACCESS_RIGHTS syscall_arg__scnprintf_pkey_alloc_access_rights
 
diff --git a/tools/perf/trace/beauty/mount_flags.c b/tools/perf/trace/beauty/mount_flags.c
new file mode 100644
index 000000000000..712935c6620a
--- /dev/null
+++ b/tools/perf/trace/beauty/mount_flags.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * trace/beauty/mount_flags.c
+ *
+ *  Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/log2.h>
+#include <sys/mount.h>
+
+static size_t mount__scnprintf_flags(unsigned long flags, char *bf, size_t size)
+{
+#include "trace/beauty/generated/mount_flags_array.c"
+	static DEFINE_STRARRAY(mount_flags);
+
+	return strarray__scnprintf_flags(&strarray__mount_flags, bf, size, flags);
+}
+
+unsigned long syscall_arg__mask_val_mount_flags(struct syscall_arg *arg __maybe_unused, unsigned long flags)
+{
+	// do_mount in fs/namespace.c:
+	/*
+	 * Pre-0.97 versions of mount() didn't have a flags word.  When the
+	 * flags word was introduced its top half was required to have the
+	 * magic value 0xC0ED, and this remained so until 2.4.0-test9.
+	 * Therefore, if this magic number is present, it carries no
+	 * information and must be discarded.
+	 */
+	if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
+		flags &= ~MS_MGC_MSK;
+
+	return flags;
+}
+
+size_t syscall_arg__scnprintf_mount_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+	unsigned long flags = arg->val;
+
+	return mount__scnprintf_flags(flags, bf, size);
+}
-- 
cgit v1.2.3


From f932184e282f574cfd34afee917a10b782fd3e76 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 25 Oct 2018 17:24:45 -0300
Subject: perf trace: Consider syscall aliases too

When trying to trace the 'umount' syscall on x86_64 I noticed that it
was failing:

  # trace -e umount umount /mnt
  event syntax error: 'umount'
                       \___ parser error
  Run 'perf list' for a list of valid events

   Usage: perf trace [<options>] [<command>]
      or: perf trace [<options>] -- <command> [<options>]
      or: perf trace record [<options>] [<command>]
      or: perf trace record [<options>] -- <command> [<options>]

      -e, --event <event>   event/syscall selector. use 'perf list' to list available events
  #

This is because in the x86-64 we have it just as 'umount2':

  $ grep umount arch/x86/entry/syscalls/syscall_64.tbl
  166	common	umount2			__x64_sys_umount
  $

So if the syscall name fails, try fallbacking to looking at the aliases
we have in the syscall_fmts table to then re-lookup, now:

  # trace -e umount umount -f /mnt
  umount: /mnt: not mounted.
     1.759 ( 0.004 ms): umount/18365 umount2(name: 0x55fbfcbc4480, flags: 1) = -1 EINVAL Invalid argument
  #

Time to beautify the flags arg :-)

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ukweodgzbmjd25lfkgryeft1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 76c14c0129fc..db8711061ca3 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -862,6 +862,18 @@ static struct syscall_fmt *syscall_fmt__find(const char *name)
 	return bsearch(name, syscall_fmts, nmemb, sizeof(struct syscall_fmt), syscall_fmt__cmp);
 }
 
+static struct syscall_fmt *syscall_fmt__find_by_alias(const char *alias)
+{
+	int i, nmemb = ARRAY_SIZE(syscall_fmts);
+
+	for (i = 0; i < nmemb; ++i) {
+		if (syscall_fmts[i].alias && strcmp(syscall_fmts[i].alias, alias) == 0)
+			return &syscall_fmts[i];
+	}
+
+	return NULL;
+}
+
 /*
  * is_exit: is this "exit" or "exit_group"?
  * is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter.
@@ -3195,6 +3207,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 	int len = strlen(str) + 1, err = -1, list, idx;
 	char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
 	char group_name[PATH_MAX];
+	struct syscall_fmt *fmt;
 
 	if (strace_groups_dir == NULL)
 		return -1;
@@ -3212,12 +3225,19 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 		if (syscalltbl__id(trace->sctbl, s) >= 0 ||
 		    syscalltbl__strglobmatch_first(trace->sctbl, s, &idx) >= 0) {
 			list = 1;
+			goto do_concat;
+		}
+
+		fmt = syscall_fmt__find_by_alias(s);
+		if (fmt != NULL) {
+			list = 1;
+			s = fmt->name;
 		} else {
 			path__join(group_name, sizeof(group_name), strace_groups_dir, s);
 			if (access(group_name, R_OK) == 0)
 				list = 1;
 		}
-
+do_concat:
 		if (lists[list]) {
 			sprintf(lists[list] + strlen(lists[list]), ",%s", s);
 		} else {
-- 
cgit v1.2.3


From 476c92cacf383c83584ba02d06c88cf18f062afb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 26 Oct 2018 13:23:25 -0300
Subject: perf trace: Beautify the umount's 'name' argument

By using the SCA_FILENAME beautifier, that works when either the
probe:vfs_getname probe is in place or with the eBPF program
tools/perf/examples/bpf/augmented_syscalls.c:

  # perf probe -l
  probe:vfs_getname (on getname_flags:73@acme/git/linux/fs/namei.c with pathname)
  # perf trace -e umount
  9630.332 ( 9.521 ms): umount/8082 umount2(name: /mnt) = 0
  #

The augmented syscalls one will be done in the next patch.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-hegbzlpd2nrn584l5jxn7sy2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index db8711061ca3..d286f73ef2e5 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -838,7 +838,8 @@ static struct syscall_fmt {
 	  .arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
 	{ .name	    = "tkill",
 	  .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
-	{ .name     = "umount2", .alias = "umount", },
+	{ .name     = "umount2", .alias = "umount",
+	  .arg = { [0] = { .scnprintf = SCA_FILENAME, /* name */ }, }, },
 	{ .name	    = "uname", .alias = "newuname", },
 	{ .name	    = "unlinkat",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
-- 
cgit v1.2.3


From 23c07a23cbed389d0b9c7a06486574621df8d1a4 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 26 Oct 2018 13:51:45 -0300
Subject: perf trace: Beautify mount's first pathname arg

The pathname beautifiers so far support just one augmented pathname per
syscall, so do it just for mount's first arg, later this will get fixed.

With:

  # perf probe -l
  probe:vfs_getname    (on getname_flags:73@acme/git/linux/fs/namei.c with pathname)
  #

Later this will get added to augmented_syscalls.c (eBPF):

In one xterm:

  # perf trace -e mount,umount
  2687.331 ( 3.544 ms): mount/8892 mount(dev_name: /mnt, dir_name: 0x561f9ac184a0, type: 0x561f9ac1b170, flags: BIND) = 0
  3912.126 ( 8.807 ms): umount/8895 umount2(name: /mnt) = 0
  ^C#

In the other:

  $ sudo mount --bind /proc /mnt
  $ sudo umount /mnt

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-qsvhrm2es635cl4zicqjeth2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index d286f73ef2e5..dc8a6c4986ce 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -727,7 +727,8 @@ static struct syscall_fmt {
 		   [2] = { .scnprintf = SCA_MMAP_PROT,	/* prot */ },
 		   [3] = { .scnprintf = SCA_MMAP_FLAGS,	/* flags */ }, }, },
 	{ .name	    = "mount",
-	  .arg = { [3] = { .scnprintf = SCA_MOUNT_FLAGS, /* flags */
+	  .arg = { [0] = { .scnprintf = SCA_FILENAME, /* dev_name */ },
+		   [3] = { .scnprintf = SCA_MOUNT_FLAGS, /* flags */
 			   .mask_val  = SCAMV_MOUNT_FLAGS, /* flags */ }, }, },
 	{ .name	    = "mprotect",
 	  .arg = { [0] = { .scnprintf = SCA_HEX,	/* start */ },
-- 
cgit v1.2.3


From 4e303fbe2d95806c875f5ebfcb3d980e20b4bd83 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 26 Oct 2018 15:55:23 -0300
Subject: perf top: Allow disabling the overwrite mode

In ebebbf082357 ("perf top: Switch default mode to overwrite mode") we
forgot to leave a way to disable that new default, add a --overwrite
option that can be disabled using --no-overwrite, since the code already
in such a way that we can readily disable this mode.

This is useful when investigating bugs with this mode like the recent
report from David Miller where lots of unknown symbols appear due to
disabling the events while processing them which disables all record
types, not just PERF_RECORD_SAMPLE, which makes it impossible to resolve
maps when we lose PERF_RECORD_MMAP records.

This can be easily seen while building a kernel, when there are lots of
short lived processes.

Reported-by: David Miller <davem@davemloft.net>
Acked-by: Kan Liang <kan.liang@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: ebebbf082357 ("perf top: Switch default mode to overwrite mode")
Link: https://lkml.kernel.org/n/tip-oqgsz2bq4kgrnnajrafcdhie@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-top.txt | 5 +++++
 tools/perf/builtin-top.c              | 2 ++
 2 files changed, 7 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 114fda12aa49..d4be6061fe1c 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -242,6 +242,11 @@ Default is to monitor all CPUS.
 --hierarchy::
 	Enable hierarchy output.
 
+--overwrite::
+	This is the default, but for investigating problems with it or any other strange
+	behaviour like lots of unknown samples, we may want to disable this mode by using
+	--no-overwrite.
+
 --force::
 	Don't do ownership validation.
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index d21d8751e749..214fad747b04 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1372,6 +1372,8 @@ int cmd_top(int argc, const char **argv)
 		    "Show raw trace event output (do not use print fmt or plugins)"),
 	OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
 		    "Show entries in a hierarchy"),
+	OPT_BOOLEAN(0, "overwrite", &top.record_opts.overwrite,
+		    "Use a backward ring buffer, default: yes"),
 	OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"),
 	OPT_UINTEGER(0, "num-thread-synthesize", &top.nr_threads_synthesize,
 			"number of thread to run event synthesize"),
-- 
cgit v1.2.3


From b31d30d9be32d41bef3e6076a965565d3a3d8005 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 29 Oct 2018 14:56:48 -0700
Subject: tools/bpf: add unlimited rlimit for flow_dissector_load

On our test machine, bpf selftest test_flow_dissector.sh failed
with the following error:
  # ./test_flow_dissector.sh
  bpffs not mounted. Mounting...
  libbpf: failed to create map (name: 'jmp_table'): Operation not permitted
  libbpf: failed to load object 'bpf_flow.o'
  ./flow_dissector_load: bpf_prog_load bpf_flow.o
  selftests: test_flow_dissector [FAILED]

Let us increase the rlimit to remove the above map
creation failure.

Signed-off-by: Yonghong Song <yhs@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/flow_dissector_load.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/flow_dissector_load.c b/tools/testing/selftests/bpf/flow_dissector_load.c
index d3273b5b3173..ae8180b11d5f 100644
--- a/tools/testing/selftests/bpf/flow_dissector_load.c
+++ b/tools/testing/selftests/bpf/flow_dissector_load.c
@@ -11,6 +11,8 @@
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
 
+#include "bpf_rlimit.h"
+
 const char *cfg_pin_path = "/sys/fs/bpf/flow_dissector";
 const char *cfg_map_name = "jmp_table";
 bool cfg_attach = true;
-- 
cgit v1.2.3


From a0aebae07f211c05d64be886e56d352eea86350b Mon Sep 17 00:00:00 2001
From: Joel Stanley <joel@jms.id.au>
Date: Mon, 22 Oct 2018 22:39:26 +1030
Subject: selftests: powerpc: Fix warning for security subdir

typing 'make' inside tools/testing/selftests/powerpc gave a build
warning:

BUILD_TARGET=tools/testing/selftests/powerpc/security; mkdir -p $BUILD_TARGET; make OUTPUT=$BUILD_TARGET -k -C security all
make[1]: Entering directory 'tools/testing/selftests/powerpc/security'
../../lib.mk:20: ../../../../scripts/subarch.include: No such file or directory
make[1]: *** No rule to make target '../../../../scripts/subarch.include'.
make[1]: Failed to remake makefile '../../../../scripts/subarch.include'.

The build is one level deeper than lib.mk thinks it is. Set top_srcdir
to set things straight.

Note that the test program is still built.

Signed-off-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/security/Makefile | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/security/Makefile b/tools/testing/selftests/powerpc/security/Makefile
index 44690f1bb26a..85861c46b445 100644
--- a/tools/testing/selftests/powerpc/security/Makefile
+++ b/tools/testing/selftests/powerpc/security/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0+
 
 TEST_GEN_PROGS := rfi_flush
+top_srcdir = ../../../../..
 
 CFLAGS += -I../../../../../usr/include
 
-- 
cgit v1.2.3


From c39b79082a38a4f8c801790edecbbb4d62ed2992 Mon Sep 17 00:00:00 2001
From: Joel Stanley <joel@jms.id.au>
Date: Mon, 29 Oct 2018 22:23:49 +1100
Subject: selftests/powerpc/ptrace: Fix out-of-tree build

We should use TEST_GEN_PROGS, not TEST_PROGS. That tells the selftests
makefile (lib.mk) that those tests are generated (built), and so it
adds the $(OUTPUT) prefix for us, making the out-of-tree build work
correctly.

It also means we don't need our own clean rule, lib.mk does it.

We also have to update the ptrace-pkey and core-pkey rules to use
$(OUTPUT).

Signed-off-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/ptrace/Makefile | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile
index 9b35ca8e8f13..8d3f006c98cc 100644
--- a/tools/testing/selftests/powerpc/ptrace/Makefile
+++ b/tools/testing/selftests/powerpc/ptrace/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \
+TEST_GEN_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \
               ptrace-tar ptrace-tm-tar ptrace-tm-spd-tar ptrace-vsx ptrace-tm-vsx \
               ptrace-tm-spd-vsx ptrace-tm-spr ptrace-hwbreak ptrace-pkey core-pkey \
               perf-hwbreak ptrace-syscall
@@ -7,14 +7,9 @@ TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \
 top_srcdir = ../../../../..
 include ../../lib.mk
 
-all: $(TEST_PROGS)
-
 CFLAGS += -m64 -I../../../../../usr/include -I../tm -mhtm -fno-pie
 
-ptrace-pkey core-pkey: child.h
-ptrace-pkey core-pkey: LDLIBS += -pthread
-
-$(TEST_PROGS): ../harness.c ../utils.c ../lib/reg.S ptrace.h
+$(OUTPUT)/ptrace-pkey $(OUTPUT)/core-pkey: child.h
+$(OUTPUT)/ptrace-pkey $(OUTPUT)/core-pkey: LDLIBS += -pthread
 
-clean:
-	rm -f $(TEST_PROGS) *.o
+$(TEST_GEN_PROGS): ../harness.c ../utils.c ../lib/reg.S ptrace.h
-- 
cgit v1.2.3


From 27825349d7b238533a47e3d98b8bb0efd886b752 Mon Sep 17 00:00:00 2001
From: Joel Stanley <joel@jms.id.au>
Date: Mon, 29 Oct 2018 22:23:50 +1100
Subject: selftests/powerpc/signal: Fix out-of-tree build

We should use TEST_GEN_PROGS, not TEST_PROGS. That tells the selftests
makefile (lib.mk) that those tests are generated (built), and so it
adds the $(OUTPUT) prefix for us, making the out-of-tree build work
correctly.

It also means we don't need our own clean rule, lib.mk does it.

We also have to update the signal_tm rule to use $(OUTPUT).

Signed-off-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/signal/Makefile | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile
index 1fca25c6ace0..209a958dca12 100644
--- a/tools/testing/selftests/powerpc/signal/Makefile
+++ b/tools/testing/selftests/powerpc/signal/Makefile
@@ -1,15 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
-TEST_PROGS := signal signal_tm
-
-all: $(TEST_PROGS)
-
-$(TEST_PROGS): ../harness.c ../utils.c signal.S
+TEST_GEN_PROGS := signal signal_tm
 
 CFLAGS += -maltivec
-signal_tm: CFLAGS += -mhtm
+$(OUTPUT)/signal_tm: CFLAGS += -mhtm
 
 top_srcdir = ../../../../..
 include ../../lib.mk
 
-clean:
-	rm -f $(TEST_PROGS) *.o
+$(TEST_GEN_PROGS): ../harness.c ../utils.c signal.S
-- 
cgit v1.2.3


From 98415da03ae6559dc62899fd31e55e194779c45b Mon Sep 17 00:00:00 2001
From: Joel Stanley <joel@jms.id.au>
Date: Mon, 29 Oct 2018 22:23:51 +1100
Subject: selftests/powerpc/pmu: Link ebb tests with -no-pie

When running the ebb tests after building on a ppc64le Ubuntu machine:

 $ pmu/ebb/reg_access_test: error while loading shared libraries:
 R_PPC64_ADDR16_HI reloc at 0x000000013a965130 for symbol `' out of
 range

This is because the Ubuntu toolchain builds has PIE enabled by default.
Change it to be always off instead.

Signed-off-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/pmu/ebb/Makefile | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
index bd5dfa509272..23f4caf48ffc 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
@@ -5,6 +5,9 @@ noarg:
 # The EBB handler is 64-bit code and everything links against it
 CFLAGS += -m64
 
+# Toolchains may build PIE by default which breaks the assembly
+LDFLAGS += -no-pie
+
 TEST_GEN_PROGS := reg_access_test event_attributes_test cycles_test	\
 	 cycles_with_freeze_test pmc56_overflow_test		\
 	 ebb_vs_cpu_event_test cpu_event_vs_ebb_test		\
-- 
cgit v1.2.3


From 266bac361d5677e61a6815bd29abeb3bdced2b07 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Mon, 29 Oct 2018 22:23:52 +1100
Subject: selftests/powerpc/switch_endian: Fix out-of-tree build

For the out-of-tree build to work we need to tell switch_endian_test
to look for check-reversed.S in $(OUTPUT).

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/switch_endian/Makefile | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/switch_endian/Makefile b/tools/testing/selftests/powerpc/switch_endian/Makefile
index fcd2dcb8972b..bdc081afedb0 100644
--- a/tools/testing/selftests/powerpc/switch_endian/Makefile
+++ b/tools/testing/selftests/powerpc/switch_endian/Makefile
@@ -8,6 +8,7 @@ EXTRA_CLEAN = $(OUTPUT)/*.o $(OUTPUT)/check-reversed.S
 top_srcdir = ../../../../..
 include ../../lib.mk
 
+$(OUTPUT)/switch_endian_test: ASFLAGS += -I $(OUTPUT)
 $(OUTPUT)/switch_endian_test: $(OUTPUT)/check-reversed.S
 
 $(OUTPUT)/check-reversed.o: $(OUTPUT)/check.o
-- 
cgit v1.2.3


From 69f8117f17b332a68cd8f4bf8c2d0d3d5b84efc5 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Mon, 29 Oct 2018 22:23:53 +1100
Subject: selftests/powerpc/cache_shape: Fix out-of-tree build

Use TEST_GEN_PROGS and don't redefine all, this makes the out-of-tree
build work. We need to move the extra dependencies below the include
of lib.mk, because it adds the $(OUTPUT) prefix if it's defined.

We can also drop the clean rule, lib.mk does it for us.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/cache_shape/Makefile | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/cache_shape/Makefile b/tools/testing/selftests/powerpc/cache_shape/Makefile
index ede4d3dae750..689f6c8ebcd8 100644
--- a/tools/testing/selftests/powerpc/cache_shape/Makefile
+++ b/tools/testing/selftests/powerpc/cache_shape/Makefile
@@ -1,12 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
-TEST_PROGS := cache_shape
-
-all: $(TEST_PROGS)
-
-$(TEST_PROGS): ../harness.c ../utils.c
+TEST_GEN_PROGS := cache_shape
 
 top_srcdir = ../../../../..
 include ../../lib.mk
 
-clean:
-	rm -f $(TEST_PROGS) *.o
+$(TEST_GEN_PROGS): ../harness.c ../utils.c
-- 
cgit v1.2.3


From 218d61110f69632974034b6e27686ce482a1c455 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 29 Oct 2018 09:47:00 -0300
Subject: perf top: Do not use overwrite mode by default

Enabling --overwrite mode allows us to to use just the most recent
records, which helps in high core count machines such as Knights
Landing/Mill, but right now is being disabled by default as the pausing
used in this technique is leading to loss of metadata events such as
PERF_RECORD_MMAP which makes 'perf top' unable to resolve samples,
leading to lots of unknown samples appearing on the UI.

Enabling this may be useful if you are in such machines and profiling a
workload that doesn't creates short lived threads and/or doesn't uses
many executable mmap operations.

Work is being planed to solve this situation, till then, this will
remain disabled by default.

Reported-by: David Miller <davem@davemloft.net>
Acked-by: Kan Liang <kan.liang@intel.com>
Link: https://lkml.kernel.org/r/4f84468f-37d9-cf1b-12c1-514ef74b6a48@linux.intel.com
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: ebebbf082357 ("perf top: Switch default mode to overwrite mode")
Link: https://lkml.kernel.org/n/tip-ehvf77vi1si9409r7p4wx788@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-top.txt | 11 ++++++++---
 tools/perf/builtin-top.c              | 11 +++++++++--
 2 files changed, 17 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index d4be6061fe1c..808b664343c9 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -243,9 +243,14 @@ Default is to monitor all CPUS.
 	Enable hierarchy output.
 
 --overwrite::
-	This is the default, but for investigating problems with it or any other strange
-	behaviour like lots of unknown samples, we may want to disable this mode by using
-	--no-overwrite.
+	Enable this to use just the most recent records, which helps in high core count
+	machines such as Knights Landing/Mill, but right now is disabled by default as
+	the pausing used in this technique is leading to loss of metadata events such
+	as PERF_RECORD_MMAP which makes 'perf top' unable to resolve samples, leading
+	to lots of unknown samples appearing on the UI. Enable this if you are in such
+	machines and profiling a workload that doesn't creates short lived threads and/or
+	doesn't uses many executable mmap operations. Work is being planed to solve
+	this situation, till then, this will remain disabled by default.
 
 --force::
 	Don't do ownership validation.
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 214fad747b04..8e29e0cc8626 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1257,7 +1257,14 @@ int cmd_top(int argc, const char **argv)
 				.uses_mmap   = true,
 			},
 			.proc_map_timeout    = 500,
-			.overwrite	= 1,
+			/*
+			 * FIXME: This will lose PERF_RECORD_MMAP and other metadata
+			 * when we pause, fix that and reenable. Probably using a
+			 * separate evlist with a dummy event, i.e. a non-overwrite
+			 * ring buffer just for metadata events, while PERF_RECORD_SAMPLE
+			 * stays in overwrite mode. -acme
+			 * */
+			.overwrite	= 0,
 		},
 		.max_stack	     = sysctl__max_stack(),
 		.annotation_opts     = annotation__default_options,
@@ -1373,7 +1380,7 @@ int cmd_top(int argc, const char **argv)
 	OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
 		    "Show entries in a hierarchy"),
 	OPT_BOOLEAN(0, "overwrite", &top.record_opts.overwrite,
-		    "Use a backward ring buffer, default: yes"),
+		    "Use a backward ring buffer, default: no"),
 	OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"),
 	OPT_UINTEGER(0, "num-thread-synthesize", &top.nr_threads_synthesize,
 			"number of thread to run event synthesize"),
-- 
cgit v1.2.3


From 1fe627da30331024f453faef04d500079b901107 Mon Sep 17 00:00:00 2001
From: Milian Wolff <milian.wolff@kdab.com>
Date: Mon, 29 Oct 2018 15:16:44 +0100
Subject: perf unwind: Take pgoff into account when reporting elf to libdwfl

libdwfl parses an ELF file itself and creates mappings for the
individual sections. perf on the other hand sees raw mmap events which
represent individual sections. When we encounter an address pointing
into a mapping with pgoff != 0, we must take that into account and
report the file at the non-offset base address.

This fixes unwinding with libdwfl in some cases. E.g. for a file like:

```

using namespace std;

mutex g_mutex;

double worker()
{
    lock_guard<mutex> guard(g_mutex);
    uniform_real_distribution<double> uniform(-1E5, 1E5);
    default_random_engine engine;
    double s = 0;
    for (int i = 0; i < 1000; ++i) {
        s += norm(complex<double>(uniform(engine), uniform(engine)));
    }
    cout << s << endl;
    return s;
}

int main()
{
    vector<std::future<double>> results;
    for (int i = 0; i < 10000; ++i) {
        results.push_back(async(launch::async, worker));
    }
    return 0;
}
```

Compile it with `g++ -g -O2 -lpthread cpp-locking.cpp  -o cpp-locking`,
then record it with `perf record --call-graph dwarf -e
sched:sched_switch`.

When you analyze it with `perf script` and libunwind, you should see:

```
cpp-locking 20038 [005] 54830.236589: sched:sched_switch: prev_comm=cpp-locking prev_pid=20038 prev_prio=120 prev_state=T ==> next_comm=swapper/5 next_pid=0 next_prio=120
        ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1670208 schedule+0x28 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb16737cc rwsem_down_read_failed+0xec (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1665e04 call_rwsem_down_read_failed+0x14 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1672a03 down_read+0x13 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb106bd85 __do_page_fault+0x445 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb18015f5 page_fault+0x45 (/lib/modules/4.14.78-1-lts/build/vmlinux)
            7f38e4252591 new_heap+0x101 (/usr/lib/libc-2.28.so)
            7f38e4252d0b arena_get2.part.4+0x2fb (/usr/lib/libc-2.28.so)
            7f38e4255b1c tcache_init.part.6+0xec (/usr/lib/libc-2.28.so)
            7f38e42569e5 __GI___libc_malloc+0x115 (inlined)
            7f38e4241790 __GI__IO_file_doallocate+0x90 (inlined)
            7f38e424fbbf __GI__IO_doallocbuf+0x4f (inlined)
            7f38e424ee47 __GI__IO_file_overflow+0x197 (inlined)
            7f38e424df36 _IO_new_file_xsputn+0x116 (inlined)
            7f38e4242bfb __GI__IO_fwrite+0xdb (inlined)
            7f38e463fa6d std::basic_streambuf<char, std::char_traits<char> >::sputn(char const*, long)+0x1cd (inlined)
            7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> >::_M_put(char const*, long)+0x1cd (inlined)
            7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> > std::__write<char>(std::ostreambuf_iterator<char, std::char_traits<char> >, char const*, int)+0x1cd (inlined)
            7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> > std::num_put<char, std::ostreambuf_iterator<char, std::char_traits<char> > >::_M_insert_float<double>(std::ostreambuf_iterator<c>
            7f38e464bd70 std::num_put<char, std::ostreambuf_iterator<char, std::char_traits<char> > >::put(std::ostreambuf_iterator<char, std::char_traits<char> >, std::ios_base&, char, double) const+0x90 (inl>
            7f38e464bd70 std::ostream& std::ostream::_M_insert<double>(double)+0x90 (/usr/lib/libstdc++.so.6.0.25)
            563b9cb502f7 std::ostream::operator<<(double)+0xb7 (inlined)
            563b9cb502f7 worker()+0xb7 (/ssd/milian/projects/kdab/rnd/hotspot/build/tests/test-clients/cpp-locking/cpp-locking)
            563b9cb506fb double std::__invoke_impl<double, double (*)()>(std::__invoke_other, double (*&&)())+0x2b (inlined)
            563b9cb506fb std::__invoke_result<double (*)()>::type std::__invoke<double (*)()>(double (*&&)())+0x2b (inlined)
            563b9cb506fb decltype (__invoke((_S_declval<0ul>)())) std::thread::_Invoker<std::tuple<double (*)()> >::_M_invoke<0ul>(std::_Index_tuple<0ul>)+0x2b (inlined)
            563b9cb506fb std::thread::_Invoker<std::tuple<double (*)()> >::operator()()+0x2b (inlined)
            563b9cb506fb std::__future_base::_Task_setter<std::unique_ptr<std::__future_base::_Result<double>, std::__future_base::_Result_base::_Deleter>, std::thread::_Invoker<std::tuple<double (*)()> >, dou>
            563b9cb506fb std::_Function_handler<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> (), std::__future_base::_Task_setter<std::unique_ptr<std::__future_>
            563b9cb507e8 std::function<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> ()>::operator()() const+0x28 (inlined)
            563b9cb507e8 std::__future_base::_State_baseV2::_M_do_set(std::function<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> ()>*, bool*)+0x28 (/ssd/milian/>
            7f38e46d24fe __pthread_once_slow+0xbe (/usr/lib/libpthread-2.28.so)
            563b9cb51149 __gthread_once+0xe9 (inlined)
            563b9cb51149 void std::call_once<void (std::__future_base::_State_baseV2::*)(std::function<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> ()>*, bool*)>
            563b9cb51149 std::__future_base::_State_baseV2::_M_set_result(std::function<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> ()>, bool)+0xe9 (inlined)
            563b9cb51149 std::__future_base::_Async_state_impl<std::thread::_Invoker<std::tuple<double (*)()> >, double>::_Async_state_impl(std::thread::_Invoker<std::tuple<double (*)()> >&&)::{lambda()#1}::op>
            563b9cb51149 void std::__invoke_impl<void, std::__future_base::_Async_state_impl<std::thread::_Invoker<std::tuple<double (*)()> >, double>::_Async_state_impl(std::thread::_Invoker<std::tuple<double>
            563b9cb51149 std::__invoke_result<std::__future_base::_Async_state_impl<std::thread::_Invoker<std::tuple<double (*)()> >, double>::_Async_state_impl(std::thread::_Invoker<std::tuple<double (*)()> >>
            563b9cb51149 decltype (__invoke((_S_declval<0ul>)())) std::thread::_Invoker<std::tuple<std::__future_base::_Async_state_impl<std::thread::_Invoker<std::tuple<double (*)()> >, double>::_Async_state_>
            563b9cb51149 std::thread::_Invoker<std::tuple<std::__future_base::_Async_state_impl<std::thread::_Invoker<std::tuple<double (*)()> >, double>::_Async_state_impl(std::thread::_Invoker<std::tuple<dou>
            563b9cb51149 std::thread::_State_impl<std::thread::_Invoker<std::tuple<std::__future_base::_Async_state_impl<std::thread::_Invoker<std::tuple<double (*)()> >, double>::_Async_state_impl(std::thread>
            7f38e45f0062 execute_native_thread_routine+0x12 (/usr/lib/libstdc++.so.6.0.25)
            7f38e46caa9c start_thread+0xfc (/usr/lib/libpthread-2.28.so)
            7f38e42ccb22 __GI___clone+0x42 (inlined)
```

Before this patch, using libdwfl, you would see:

```
cpp-locking 20038 [005] 54830.236589: sched:sched_switch: prev_comm=cpp-locking prev_pid=20038 prev_prio=120 prev_state=T ==> next_comm=swapper/5 next_pid=0 next_prio=120
        ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1670208 schedule+0x28 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb16737cc rwsem_down_read_failed+0xec (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1665e04 call_rwsem_down_read_failed+0x14 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1672a03 down_read+0x13 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb106bd85 __do_page_fault+0x445 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb18015f5 page_fault+0x45 (/lib/modules/4.14.78-1-lts/build/vmlinux)
            7f38e4252591 new_heap+0x101 (/usr/lib/libc-2.28.so)
        a041161e77950c5c [unknown] ([unknown])
```

With this patch applied, we get a bit further in unwinding:

```
cpp-locking 20038 [005] 54830.236589: sched:sched_switch: prev_comm=cpp-locking prev_pid=20038 prev_prio=120 prev_state=T ==> next_comm=swapper/5 next_pid=0 next_prio=120
        ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1670208 schedule+0x28 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb16737cc rwsem_down_read_failed+0xec (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1665e04 call_rwsem_down_read_failed+0x14 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1672a03 down_read+0x13 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb106bd85 __do_page_fault+0x445 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb18015f5 page_fault+0x45 (/lib/modules/4.14.78-1-lts/build/vmlinux)
            7f38e4252591 new_heap+0x101 (/usr/lib/libc-2.28.so)
            7f38e4252d0b arena_get2.part.4+0x2fb (/usr/lib/libc-2.28.so)
            7f38e4255b1c tcache_init.part.6+0xec (/usr/lib/libc-2.28.so)
            7f38e42569e5 __GI___libc_malloc+0x115 (inlined)
            7f38e4241790 __GI__IO_file_doallocate+0x90 (inlined)
            7f38e424fbbf __GI__IO_doallocbuf+0x4f (inlined)
            7f38e424ee47 __GI__IO_file_overflow+0x197 (inlined)
            7f38e424df36 _IO_new_file_xsputn+0x116 (inlined)
            7f38e4242bfb __GI__IO_fwrite+0xdb (inlined)
            7f38e463fa6d std::basic_streambuf<char, std::char_traits<char> >::sputn(char const*, long)+0x1cd (inlined)
            7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> >::_M_put(char const*, long)+0x1cd (inlined)
            7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> > std::__write<char>(std::ostreambuf_iterator<char, std::char_traits<char> >, char const*, int)+0x1cd (inlined)
            7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> > std::num_put<char, std::ostreambuf_iterator<char, std::char_traits<char> > >::_M_insert_float<double>(std::ostreambuf_iterator<c>
            7f38e464bd70 std::num_put<char, std::ostreambuf_iterator<char, std::char_traits<char> > >::put(std::ostreambuf_iterator<char, std::char_traits<char> >, std::ios_base&, char, double) const+0x90 (inl>
            7f38e464bd70 std::ostream& std::ostream::_M_insert<double>(double)+0x90 (/usr/lib/libstdc++.so.6.0.25)
            563b9cb502f7 std::ostream::operator<<(double)+0xb7 (inlined)
            563b9cb502f7 worker()+0xb7 (/ssd/milian/projects/kdab/rnd/hotspot/build/tests/test-clients/cpp-locking/cpp-locking)
        6eab825c1ee3e4ff [unknown] ([unknown])
```

Note that the backtrace is still stopping too early, when compared to
the nice results obtained via libunwind. It's unclear so far what the
reason for that is.

Committer note:

Further comment by Milian on the thread started on the Link: tag below:

 ---
The remaining issue is due to a bug in elfutils:

https://sourceware.org/ml/elfutils-devel/2018-q4/msg00089.html

With both patches applied, libunwind and elfutils produce the same output for
the above scenario.
 ---

Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20181029141644.3907-1-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/unwind-libdw.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 6f318b15950e..5eff9bfc5758 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -45,13 +45,13 @@ static int __report_module(struct addr_location *al, u64 ip,
 		Dwarf_Addr s;
 
 		dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
-		if (s != al->map->start)
+		if (s != al->map->start - al->map->pgoff)
 			mod = 0;
 	}
 
 	if (!mod)
 		mod = dwfl_report_elf(ui->dwfl, dso->short_name,
-				      (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start,
+				      (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start - al->map->pgoff,
 				      false);
 
 	return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1;
-- 
cgit v1.2.3


From d6c9c05fe1eb4b213b183d8a1e79416256dc833a Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Tue, 30 Oct 2018 15:18:28 +0800
Subject: perf cs-etm: Correct CPU mode for samples

Since commit edeb0c90df35 ("perf tools: Stop fallbacking to kallsyms for
vdso symbols lookup"), the kernel address cannot be properly parsed to
kernel symbol with command 'perf script -k vmlinux'.  The reason is
CoreSight samples is always to set CPU mode as PERF_RECORD_MISC_USER,
thus it fails to find corresponding map/dso in below flows:

  process_sample_event()
    `-> machine__resolve()
	  `-> thread__find_map(thread, sample->cpumode, sample->ip, al);

In this flow it needs to pass argument 'sample->cpumode' to tell what's
the CPU mode, before it always passed PERF_RECORD_MISC_USER but without
any failure until the commit edeb0c90df35 ("perf tools: Stop fallbacking
to kallsyms for vdso symbols lookup") has been merged.  The reason is
even with the wrong CPU mode the function thread__find_map() firstly
fails to find map but it will rollback to find kernel map for vdso
symbols lookup.  In the latest code it has removed the fallback code,
thus if CPU mode is PERF_RECORD_MISC_USER then it cannot find map
anymore with kernel address.

This patch is to correct samples CPU mode setting, it creates a new
helper function cs_etm__cpu_mode() to tell what's the CPU mode based on
the address with the info from machine structure; this patch has a bit
extension to check not only kernel and user mode, but also check for
host/guest and hypervisor mode.  Finally this patch uses the function in
instruction and branch samples and also apply in cs_etm__mem_access()
for a minor polishing.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Miller <davem@davemloft.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: stable@kernel.org # v4.19
Link: http://lkml.kernel.org/r/1540883908-17018-1-git-send-email-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cs-etm.c | 39 ++++++++++++++++++++++++++++++---------
 1 file changed, 30 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 3b37d66dc533..73430b73570d 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -244,6 +244,27 @@ static void cs_etm__free(struct perf_session *session)
 	zfree(&aux);
 }
 
+static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address)
+{
+	struct machine *machine;
+
+	machine = etmq->etm->machine;
+
+	if (address >= etmq->etm->kernel_start) {
+		if (machine__is_host(machine))
+			return PERF_RECORD_MISC_KERNEL;
+		else
+			return PERF_RECORD_MISC_GUEST_KERNEL;
+	} else {
+		if (machine__is_host(machine))
+			return PERF_RECORD_MISC_USER;
+		else if (perf_guest)
+			return PERF_RECORD_MISC_GUEST_USER;
+		else
+			return PERF_RECORD_MISC_HYPERVISOR;
+	}
+}
+
 static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
 			      size_t size, u8 *buffer)
 {
@@ -258,10 +279,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
 		return -1;
 
 	machine = etmq->etm->machine;
-	if (address >= etmq->etm->kernel_start)
-		cpumode = PERF_RECORD_MISC_KERNEL;
-	else
-		cpumode = PERF_RECORD_MISC_USER;
+	cpumode = cs_etm__cpu_mode(etmq, address);
 
 	thread = etmq->thread;
 	if (!thread) {
@@ -653,7 +671,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 	struct perf_sample sample = {.ip = 0,};
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
-	event->sample.header.misc = PERF_RECORD_MISC_USER;
+	event->sample.header.misc = cs_etm__cpu_mode(etmq, addr);
 	event->sample.header.size = sizeof(struct perf_event_header);
 
 	sample.ip = addr;
@@ -665,7 +683,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 	sample.cpu = etmq->packet->cpu;
 	sample.flags = 0;
 	sample.insn_len = 1;
-	sample.cpumode = event->header.misc;
+	sample.cpumode = event->sample.header.misc;
 
 	if (etm->synth_opts.last_branch) {
 		cs_etm__copy_last_branch_rb(etmq);
@@ -706,12 +724,15 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 		u64			nr;
 		struct branch_entry	entries;
 	} dummy_bs;
+	u64 ip;
+
+	ip = cs_etm__last_executed_instr(etmq->prev_packet);
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
-	event->sample.header.misc = PERF_RECORD_MISC_USER;
+	event->sample.header.misc = cs_etm__cpu_mode(etmq, ip);
 	event->sample.header.size = sizeof(struct perf_event_header);
 
-	sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
+	sample.ip = ip;
 	sample.pid = etmq->pid;
 	sample.tid = etmq->tid;
 	sample.addr = cs_etm__first_executed_instr(etmq->packet);
@@ -720,7 +741,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 	sample.period = 1;
 	sample.cpu = etmq->packet->cpu;
 	sample.flags = 0;
-	sample.cpumode = PERF_RECORD_MISC_USER;
+	sample.cpumode = event->sample.header.misc;
 
 	/*
 	 * perf report cannot handle events without a branch stack
-- 
cgit v1.2.3


From e9024d519d892b38176cafd46f68a7cdddd77412 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 30 Oct 2018 12:12:26 -0300
Subject: perf callchain: Honour the ordering of PERF_CONTEXT_{USER,KERNEL,etc}

When processing using 'perf report -g caller', which is the default, we
ended up reverting the callchain entries received from the kernel, but
simply reverting throws away the information that tells that from a
point onwards the addresses are for userspace, kernel, guest kernel,
guest user, hypervisor.

The idea is that if we are walking backwards, for each cluster of
non-cpumode entries we have to first scan backwards for the next one and
use that for the cluster.

This seems silly and more expensive than it needs to be but it is enough
for a initial fix.

The code here is really complicated because it is intimately intertwined
with the lbr and branch handling, as well as this callchain order,
further fixes will be needed to properly take into account the cpumode
in those cases.

Another problem with ORDER_CALLER is that the NULL "0" IP that is at the
end of most callchains shows up at the top of the histogram because
every callchain contains it and with ORDER_CALLER it is the first entry.

Signed-off-by: David S. Miller <davem@davemloft.net>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Souvik Banerjee <souvik1997@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: stable@vger.kernel.org # 4.19
Link: https://lkml.kernel.org/n/tip-2wt3ayp6j2y2f2xowixa8y6y@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/machine.c | 35 ++++++++++++++++++++++++++++++++++-
 1 file changed, 34 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 111ae858cbcb..8ee8ab39d8ac 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2140,6 +2140,27 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 	return 0;
 }
 
+static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread,
+			     struct callchain_cursor *cursor,
+			     struct symbol **parent,
+			     struct addr_location *root_al,
+			     u8 *cpumode, int ent)
+{
+	int err = 0;
+
+	while (--ent >= 0) {
+		u64 ip = chain->ips[ent];
+
+		if (ip >= PERF_CONTEXT_MAX) {
+			err = add_callchain_ip(thread, cursor, parent,
+					       root_al, cpumode, ip,
+					       false, NULL, NULL, 0);
+			break;
+		}
+	}
+	return err;
+}
+
 static int thread__resolve_callchain_sample(struct thread *thread,
 					    struct callchain_cursor *cursor,
 					    struct perf_evsel *evsel,
@@ -2246,6 +2267,12 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	}
 
 check_calls:
+	if (callchain_param.order != ORDER_CALLEE) {
+		err = find_prev_cpumode(chain, thread, cursor, parent, root_al,
+					&cpumode, chain->nr - first_call);
+		if (err)
+			return (err < 0) ? err : 0;
+	}
 	for (i = first_call, nr_entries = 0;
 	     i < chain_nr && nr_entries < max_stack; i++) {
 		u64 ip;
@@ -2260,9 +2287,15 @@ check_calls:
 			continue;
 #endif
 		ip = chain->ips[j];
-
 		if (ip < PERF_CONTEXT_MAX)
                        ++nr_entries;
+		else if (callchain_param.order != ORDER_CALLEE) {
+			err = find_prev_cpumode(chain, thread, cursor, parent,
+						root_al, &cpumode, j);
+			if (err)
+				return (err < 0) ? err : 0;
+			continue;
+		}
 
 		err = add_callchain_ip(thread, cursor, parent,
 				       root_al, &cpumode, ip,
-- 
cgit v1.2.3


From 733ac4f9935c4b257aff2ec476e6c20665daf6c2 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 12:27:37 -0300
Subject: tools include uapi: Update linux/fs.h copy

To silence this perf build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/fs.h' differs from latest version at 'include/uapi/linux/fs.h'
  diff -u tools/include/uapi/linux/fs.h include/uapi/linux/fs.h

Due to just two comments added by:

  Fixes: 578bdaabd015 ("crypto: speck - remove Speck")

So nothing that entails changes in tools/, that so far uses fs.h to
generate the mount and umount syscalls 'flags' argument integer->string
tables with:

  $ tools/perf/trace/beauty/mount_flags.sh
  static const char *mount_flags[] = {
	[4096 ? (ilog2(4096) + 1) : 0] = "BIND",
<SNIP>
	[30 + 1] = "ACTIVE",
	[31 + 1] = "NOUSER",
  };
  $
  # trace -e mount,umount mount --bind /proc /mnt
     1.228 ( 2.581 ms): mount/1068 mount(dev_name: /mnt, dir_name: 0x55f011c354a0, type: 0x55f011c38170, flags: BIND) = 0
  # trace -e mount,umount umount /proc /mnt
  umount: /proc: target is busy.
     1.587 ( 0.010 ms): umount/1070 umount2(name: /proc) = -1 EBUSY Device or resource busy
     1.799 (12.660 ms): umount/1070 umount2(name: /mnt) = 0
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Link: https://lkml.kernel.org/n/tip-c00bqzclscgah26z2g5zxm73@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/fs.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index 73e01918f996..a441ea1bfe6d 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -279,8 +279,8 @@ struct fsxattr {
 #define FS_ENCRYPTION_MODE_AES_256_CTS		4
 #define FS_ENCRYPTION_MODE_AES_128_CBC		5
 #define FS_ENCRYPTION_MODE_AES_128_CTS		6
-#define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7
-#define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8
+#define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7 /* Removed, do not use. */
+#define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8 /* Removed, do not use. */
 
 struct fscrypt_policy {
 	__u8 version;
-- 
cgit v1.2.3


From 8dd4c0f68c0db4c0f01af60a99a7ed34fd3dee2b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 13:10:50 -0300
Subject: tools arch uapi: Update asm-generic/unistd.h and arm64 unistd.h
 copies

To get the changes in:

  82b355d161c9 ("y2038: Remove newstat family from default syscall set")

Which will make the syscall table used by 'perf trace' for arm64 to be
updated from the changes in that patch.

This silences these perf build warnings:

  Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/unistd.h' differs from latest version at 'arch/arm64/include/uapi/asm/unistd.h'
  diff -u tools/arch/arm64/include/uapi/asm/unistd.h arch/arm64/include/uapi/asm/unistd.h
  Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/unistd.h' differs from latest version at 'include/uapi/asm-generic/unistd.h'
  diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h

Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-3euy7c4yy5mvnp5bm16t9vqg@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/arm64/include/uapi/asm/unistd.h | 1 +
 tools/include/uapi/asm-generic/unistd.h    | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
index 5072cbd15c82..dae1584cf017 100644
--- a/tools/arch/arm64/include/uapi/asm/unistd.h
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -16,5 +16,6 @@
  */
 
 #define __ARCH_WANT_RENAMEAT
+#define __ARCH_WANT_NEW_STAT
 
 #include <asm-generic/unistd.h>
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index df4bedb9b01c..538546edbfbd 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -242,10 +242,12 @@ __SYSCALL(__NR_tee, sys_tee)
 /* fs/stat.c */
 #define __NR_readlinkat 78
 __SYSCALL(__NR_readlinkat, sys_readlinkat)
+#if defined(__ARCH_WANT_NEW_STAT) || defined(__ARCH_WANT_STAT64)
 #define __NR3264_fstatat 79
 __SC_3264(__NR3264_fstatat, sys_fstatat64, sys_newfstatat)
 #define __NR3264_fstat 80
 __SC_3264(__NR3264_fstat, sys_fstat64, sys_newfstat)
+#endif
 
 /* fs/sync.c */
 #define __NR_sync 81
-- 
cgit v1.2.3


From 89eb1f3b7f2a9156ce6f78713d7924c1bb2fab9f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 14:20:07 -0300
Subject: tools include uapi: Update asound.h copy

To silence this perf build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/sound/asound.h' differs from latest version at 'include/uapi/sound/asound.h'
  diff -u tools/include/uapi/sound/asound.h include/uapi/sound/asound.h

Due to this cset:

  a98401518def ("ALSA: timer: fix wrong comment to refer to 'SNDRV_TIMER_PSFLG_*'")

Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Cc: Takashi Iwai <tiwai@suse.de>
Link: https://lkml.kernel.org/n/tip-76gsvs0w2g0x723ivqa2xua3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/sound/asound.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index ed0a120d4f08..404d4b9ffe76 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -752,7 +752,7 @@ struct snd_timer_info {
 #define SNDRV_TIMER_PSFLG_EARLY_EVENT	(1<<2)	/* write early event to the poll queue */
 
 struct snd_timer_params {
-	unsigned int flags;		/* flags - SNDRV_MIXER_PSFLG_* */
+	unsigned int flags;		/* flags - SNDRV_TIMER_PSFLG_* */
 	unsigned int ticks;		/* requested resolution in ticks */
 	unsigned int queue_size;	/* total size of queue (32-1024) */
 	unsigned int reserved0;		/* reserved, was: failure locations */
-- 
cgit v1.2.3


From 80ee5668b8a755039ca6180c6272a6e8efee5aad Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 15:26:47 -0300
Subject: perf beauty: Add a generator for MAP_ mmap's flag constants

It'll use tools/{arch}/*,include copies of mman.h to generate a table to
be used by tools, initially by the 'mmap' beautifiers in 'perf trace',
but that could also be used to translate from a string constant to the
integer value to be used in a eBPF or tracefs tracepoint filter.

Tested for all archs using:

$ for arch in `ls tools/arch/` ; \
	do echo $arch ; tools/perf/trace/beauty/mmap_flags.sh $arch ; \
   done | less

Example for alpha, an oddball, doesn't include any header, defines all
its stuff:

  $ tools/perf/trace/beauty/mmap_flags.sh alpha
  static const char *mmap_flags[] = {
	[ilog2(0x10) + 1] = "ANONYMOUS",
	[ilog2(0x02000) + 1] = "DENYWRITE",
	[ilog2(0x04000) + 1] = "EXECUTABLE",
	[ilog2(0x100) + 1] = "FIXED",
	[ilog2(0x01000) + 1] = "GROWSDOWN",
	[ilog2(0x100000) + 1] = "HUGETLB",
	[ilog2(0x08000) + 1] = "LOCKED",
	[ilog2(0x40000) + 1] = "NONBLOCK",
	[ilog2(0x10000) + 1] = "NORESERVE",
	[ilog2(0x20000) + 1] = "POPULATE",
	[ilog2(0x02) + 1] = "PRIVATE",
	[ilog2(0x01) + 1] = "SHARED",
	[ilog2(0x80000) + 1] = "STACK",
  };
  $

Common case, my workstation, defines one entry (MAP_32BIT), then
includes mman.h, which gets it to include mman-common.h too:

  $ tools/perf/trace/beauty/mmap_flags.sh
  static const char *mmap_flags[] = {
	[ilog2(0x40) + 1] = "32BIT",
	[ilog2(0x01) + 1] = "SHARED",
	[ilog2(0x02) + 1] = "PRIVATE",
	[ilog2(0x10) + 1] = "FIXED",
	[ilog2(0x20) + 1] = "ANONYMOUS",
	[ilog2(0x100000) + 1] = "FIXED_NOREPLACE",
	[ilog2(0x0100) + 1] = "GROWSDOWN",
	[ilog2(0x0800) + 1] = "DENYWRITE",
	[ilog2(0x1000) + 1] = "EXECUTABLE",
	[ilog2(0x2000) + 1] = "LOCKED",
	[ilog2(0x4000) + 1] = "NORESERVE",
	[ilog2(0x8000) + 1] = "POPULATE",
	[ilog2(0x10000) + 1] = "NONBLOCK",
	[ilog2(0x20000) + 1] = "STACK",
	[ilog2(0x40000) + 1] = "HUGETLB",
	[ilog2(0x80000) + 1] = "SYNC",
  };
  $ uname -m
  x86_64
  $

Sparc, that defines a bunch then includes just mman-common.h:

  $ tools/perf/trace/beauty/mmap_flags.sh sparc
  static const char *mmap_flags[] = {
	[ilog2(0x0800) + 1] = "DENYWRITE",
	[ilog2(0x1000) + 1] = "EXECUTABLE",
	[ilog2(0x0200) + 1] = "GROWSDOWN",
	[ilog2(0x40000) + 1] = "HUGETLB",
	[ilog2(0x100) + 1] = "LOCKED",
	[ilog2(0x10000) + 1] = "NONBLOCK",
	[ilog2(0x40) + 1] = "NORESERVE",
	[ilog2(0x8000) + 1] = "POPULATE",
	[ilog2(0x20000) + 1] = "STACK",
	[ilog2(0x01) + 1] = "SHARED",
	[ilog2(0x02) + 1] = "PRIVATE",
	[ilog2(0x10) + 1] = "FIXED",
	[ilog2(0x20) + 1] = "ANONYMOUS",
	[ilog2(0x100000) + 1] = "FIXED_NOREPLACE",
  };
  [acme@jouet perf]$

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-xydeh491z8fkgglcmqnl5thj@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/mmap_flags.sh | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)
 create mode 100755 tools/perf/trace/beauty/mmap_flags.sh

(limited to 'tools')

diff --git a/tools/perf/trace/beauty/mmap_flags.sh b/tools/perf/trace/beauty/mmap_flags.sh
new file mode 100755
index 000000000000..22c3fdca8975
--- /dev/null
+++ b/tools/perf/trace/beauty/mmap_flags.sh
@@ -0,0 +1,32 @@
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+if [ $# -ne 2 ] ; then
+	[ $# -eq 1 ] && hostarch=$1 || hostarch=`uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/`
+	header_dir=tools/include/uapi/asm-generic
+	arch_header_dir=tools/arch/${hostarch}/include/uapi/asm
+else
+	header_dir=$1
+	arch_header_dir=$2
+fi
+
+arch_mman=${arch_header_dir}/mman.h
+
+# those in egrep -vw are flags, we want just the bits
+
+printf "static const char *mmap_flags[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MAP_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
+egrep -q $regex ${arch_mman} && \
+(egrep $regex ${arch_mman} | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman} &&
+(egrep $regex ${header_dir}/mman-common.h | \
+	egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.h>.*' ${arch_mman} &&
+(egrep $regex ${header_dir}/mman.h | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+printf "};\n"
-- 
cgit v1.2.3


From fbd7458db75790e37903c75be68513a4c087737c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 16:11:59 -0300
Subject: perf beauty: Wire up the mmap flags table generator to the Makefile

Now when we run 'make -C tools/perf O=/tmp/build/perf' we end up with:

  $ cat /tmp/build/perf/trace/beauty/generated/mmap_flags_array.c
  static const char *mmap_flags[] = {
	[ilog2(0x40) + 1] = "32BIT",
	[ilog2(0x01) + 1] = "SHARED",
	[ilog2(0x02) + 1] = "PRIVATE",
	[ilog2(0x10) + 1] = "FIXED",
	[ilog2(0x20) + 1] = "ANONYMOUS",
	[ilog2(0x100000) + 1] = "FIXED_NOREPLACE",
	[ilog2(0x0100) + 1] = "GROWSDOWN",
	[ilog2(0x0800) + 1] = "DENYWRITE",
	[ilog2(0x1000) + 1] = "EXECUTABLE",
	[ilog2(0x2000) + 1] = "LOCKED",
	[ilog2(0x4000) + 1] = "NORESERVE",
	[ilog2(0x8000) + 1] = "POPULATE",
	[ilog2(0x10000) + 1] = "NONBLOCK",
	[ilog2(0x20000) + 1] = "STACK",
	[ilog2(0x40000) + 1] = "HUGETLB",
	[ilog2(0x80000) + 1] = "SYNC",
  };
  $

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-t3fn7u3tjsupio6e6vkufx9m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.perf | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index a31c5c29d53a..3ccb4f0bf088 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -1,4 +1,5 @@
 include ../scripts/Makefile.include
+include ../scripts/Makefile.arch
 
 # The default target of this Makefile is...
 all:
@@ -385,6 +386,8 @@ export INSTALL SHELL_PATH
 SHELL = $(SHELL_PATH)
 
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
+asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
+arch_asm_uapi_dir := $(srctree)/tools/arch/$(ARCH)/include/uapi/asm/
 
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
@@ -460,6 +463,12 @@ madvise_behavior_tbl := $(srctree)/tools/perf/trace/beauty/madvise_behavior.sh
 $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_tbl)
 	$(Q)$(SHELL) '$(madvise_behavior_tbl)' $(madvise_hdr_dir) > $@
 
+mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c
+mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh
+
+$(mmap_flags_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(arch_asm_uapi_dir)/mman.h $(mmap_flags_tbl)
+	$(Q)$(SHELL) '$(mmap_flags_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
+
 mount_flags_array := $(beauty_outdir)/mount_flags_array.c
 mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
 
@@ -583,6 +592,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(socket_ipproto_array) \
 	$(vhost_virtio_ioctl_array) \
 	$(madvise_behavior_array) \
+	$(mmap_flags_array) \
 	$(mount_flags_array) \
 	$(perf_ioctl_array) \
 	$(prctl_option_array) \
@@ -870,6 +880,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
 		$(OUTPUT)pmu-events/pmu-events.c \
 		$(OUTPUT)$(madvise_behavior_array) \
+		$(OUTPUT)$(mmap_flags_array) \
 		$(OUTPUT)$(mount_flags_array) \
 		$(OUTPUT)$(drm_ioctl_array) \
 		$(OUTPUT)$(pkey_alloc_access_rights_array) \
-- 
cgit v1.2.3


From 2f967f1dbbc1f746ad0deda8352bcf563d59e1c7 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 16:30:38 -0300
Subject: perf trace beauty: Use the mmap flags table generated from headers

Instead of requiring us to go on and edit sources to add new flag.

  # perf trace -e *mmap sleep 0.1
     0.025 ( 0.005 ms): sleep/29876 mmap(len: 163746, prot: READ, flags: PRIVATE, fd: 3) = 0x7faa68ad1000
     0.059 ( 0.004 ms): sleep/29876 mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS) = 0x7faa68acf000
     0.069 ( 0.006 ms): sleep/29876 mmap(len: 3889792, prot: EXEC|READ, flags: PRIVATE|DENYWRITE, fd: 3) = 0x7faa6851f000
     0.086 ( 0.009 ms): sleep/29876 mmap(addr: 0x7faa688cb000, len: 24576, prot: READ|WRITE, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 1753088) = 0x7faa688cb000
     0.101 ( 0.005 ms): sleep/29876 mmap(addr: 0x7faa688d1000, len: 14976, prot: READ|WRITE, flags: PRIVATE|FIXED|ANONYMOUS) = 0x7faa688d1000
     0.348 ( 0.005 ms): sleep/29876 mmap(len: 111950656, prot: READ, flags: PRIVATE, fd: 3) = 0x7faa61a5b000
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ggmoy6vxoygh5yim890ht0kf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/mmap.c | 48 ++++++++++--------------------------------
 1 file changed, 11 insertions(+), 37 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 0605593552c6..c534bd96ef5c 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: LGPL-2.1
 #include <uapi/linux/mman.h>
+#include <linux/log2.h>
 
 static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 					       struct syscall_arg *arg)
@@ -30,50 +31,23 @@ static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 
 #define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot
 
+static size_t mmap__scnprintf_flags(unsigned long flags, char *bf, size_t size)
+{
+#include "trace/beauty/generated/mmap_flags_array.c"
+       static DEFINE_STRARRAY(mmap_flags);
+
+       return strarray__scnprintf_flags(&strarray__mmap_flags, bf, size, flags);
+}
+
 static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 						struct syscall_arg *arg)
 {
-	int printed = 0, flags = arg->val;
+	unsigned long flags = arg->val;
 
 	if (flags & MAP_ANONYMOUS)
 		arg->mask |= (1 << 4) | (1 << 5); /* Mask 4th ('fd') and 5th ('offset') args, ignored */
 
-#define	P_MMAP_FLAG(n) \
-	if (flags & MAP_##n) { \
-		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
-		flags &= ~MAP_##n; \
-	}
-
-	P_MMAP_FLAG(SHARED);
-	P_MMAP_FLAG(PRIVATE);
-#ifdef MAP_32BIT
-	P_MMAP_FLAG(32BIT);
-#endif
-	P_MMAP_FLAG(ANONYMOUS);
-	P_MMAP_FLAG(DENYWRITE);
-	P_MMAP_FLAG(EXECUTABLE);
-	P_MMAP_FLAG(FILE);
-	P_MMAP_FLAG(FIXED);
-#ifdef MAP_FIXED_NOREPLACE
-	P_MMAP_FLAG(FIXED_NOREPLACE);
-#endif
-	P_MMAP_FLAG(GROWSDOWN);
-	P_MMAP_FLAG(HUGETLB);
-	P_MMAP_FLAG(LOCKED);
-	P_MMAP_FLAG(NONBLOCK);
-	P_MMAP_FLAG(NORESERVE);
-	P_MMAP_FLAG(POPULATE);
-	P_MMAP_FLAG(STACK);
-	P_MMAP_FLAG(UNINITIALIZED);
-#ifdef MAP_SYNC
-	P_MMAP_FLAG(SYNC);
-#endif
-#undef P_MMAP_FLAG
-
-	if (flags)
-		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
-
-	return printed;
+	return mmap__scnprintf_flags(flags, bf, size);
 }
 
 #define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
-- 
cgit v1.2.3


From 685626dc26bd9cead850d06520708acbd16bcfda Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 16:50:08 -0300
Subject: tools include uapi: Update linux/mmap.h copy

To pick up the changes from:

  20916d4636a9 ("mm/hugetlb: add mmap() encodings for 32MB and 512MB page sizes")

That do not entail changes in in tools, this just shows that we have to
consider bits [26:31] of flags to beautify that in tools like 'perf
trace'

This silences this perf build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/mman.h' differs from latest version at 'include/uapi/linux/mman.h'
  diff -u tools/include/uapi/linux/mman.h include/uapi/linux/mman.h

Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-3rvc39lon93kgt5pl31d8g4x@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/mman.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index bfd5938fede6..d0f515d53299 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -28,7 +28,9 @@
 #define MAP_HUGE_2MB	HUGETLB_FLAG_ENCODE_2MB
 #define MAP_HUGE_8MB	HUGETLB_FLAG_ENCODE_8MB
 #define MAP_HUGE_16MB	HUGETLB_FLAG_ENCODE_16MB
+#define MAP_HUGE_32MB	HUGETLB_FLAG_ENCODE_32MB
 #define MAP_HUGE_256MB	HUGETLB_FLAG_ENCODE_256MB
+#define MAP_HUGE_512MB	HUGETLB_FLAG_ENCODE_512MB
 #define MAP_HUGE_1GB	HUGETLB_FLAG_ENCODE_1GB
 #define MAP_HUGE_2GB	HUGETLB_FLAG_ENCODE_2GB
 #define MAP_HUGE_16GB	HUGETLB_FLAG_ENCODE_16GB
-- 
cgit v1.2.3


From 827758129a0f84fbd0b2dda15e14a77a7604803d Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 17:01:46 -0300
Subject: tools headers: Sync the various kvm.h header copies

For powerpc, s390, x86 and the main uapi linux/kvm.h header, none of
them entail changes in tooling.

Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-avn7iy8f4tcm2y40sbsdk31m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/powerpc/include/uapi/asm/kvm.h |  1 +
 tools/arch/s390/include/uapi/asm/kvm.h    |  2 ++
 tools/arch/x86/include/uapi/asm/kvm.h     |  6 ++----
 tools/include/uapi/linux/kvm.h            | 21 +++++++++++++++++++--
 4 files changed, 24 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 1b32b56a03d3..8c876c166ef2 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -634,6 +634,7 @@ struct kvm_ppc_cpu_char {
 
 #define KVM_REG_PPC_DEC_EXPIRY	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
 #define KVM_REG_PPC_ONLINE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
+#define KVM_REG_PPC_PTCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc0)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 9a50f02b9894..16511d97e8dc 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -160,6 +160,8 @@ struct kvm_s390_vm_cpu_subfunc {
 #define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW	1
 #define KVM_S390_VM_CRYPTO_DISABLE_AES_KW	2
 #define KVM_S390_VM_CRYPTO_DISABLE_DEA_KW	3
+#define KVM_S390_VM_CRYPTO_ENABLE_APIE		4
+#define KVM_S390_VM_CRYPTO_DISABLE_APIE		5
 
 /* kvm attributes for migration mode */
 #define KVM_S390_VM_MIGRATION_STOP	0
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 8a6eff9c27f3..dabfcf7c3941 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -300,10 +300,7 @@ struct kvm_vcpu_events {
 		__u8 injected;
 		__u8 nr;
 		__u8 has_error_code;
-		union {
-			__u8 pad;
-			__u8 pending;
-		};
+		__u8 pending;
 		__u32 error_code;
 	} exception;
 	struct {
@@ -387,6 +384,7 @@ struct kvm_sync_regs {
 
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
+#define KVM_STATE_NESTED_EVMCS		0x00000004
 
 #define KVM_STATE_NESTED_SMM_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_SMM_VMXON	0x00000002
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 2875ce85b322..2b7a652c9fa4 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -420,13 +420,19 @@ struct kvm_run {
 struct kvm_coalesced_mmio_zone {
 	__u64 addr;
 	__u32 size;
-	__u32 pad;
+	union {
+		__u32 pad;
+		__u32 pio;
+	};
 };
 
 struct kvm_coalesced_mmio {
 	__u64 phys_addr;
 	__u32 len;
-	__u32 pad;
+	union {
+		__u32 pad;
+		__u32 pio;
+	};
 	__u8  data[8];
 };
 
@@ -751,6 +757,15 @@ struct kvm_ppc_resize_hpt {
 
 #define KVM_S390_SIE_PAGE_OFFSET 1
 
+/*
+ * On arm64, machine type can be used to request the physical
+ * address size for the VM. Bits[7-0] are reserved for the guest
+ * PA size shift (i.e, log2(PA_Size)). For backward compatibility,
+ * value 0 implies the default IPA size, 40bits.
+ */
+#define KVM_VM_TYPE_ARM_IPA_SIZE_MASK	0xffULL
+#define KVM_VM_TYPE_ARM_IPA_SIZE(x)		\
+	((x) & KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
 /*
  * ioctls for /dev/kvm fds:
  */
@@ -958,6 +973,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_HYPERV_SEND_IPI 161
 #define KVM_CAP_COALESCED_PIO 162
 #define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163
+#define KVM_CAP_EXCEPTION_PAYLOAD 164
+#define KVM_CAP_ARM_VM_IPA_SIZE 165
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3


From d45a57fff0a657045a77b395ae713ffae0cb4e46 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 17:04:47 -0300
Subject: tools headers uapi: Update linux/netlink.h header copy

Picking the changes from:

  89d35528d17d ("netlink: Add new socket option to enable strict checking on dumps")

To silence this build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/netlink.h' differs from latest version at 'include/uapi/linux/netlink.h'

Cc: Alexei Starovoitov <ast@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric Leblond <eric@regit.org>
Link: https://lkml.kernel.org/n/tip-1xymkfjpmhxfzrs46t8z8mjw@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/netlink.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/netlink.h b/tools/include/uapi/linux/netlink.h
index 776bc92e9118..486ed1f0c0bc 100644
--- a/tools/include/uapi/linux/netlink.h
+++ b/tools/include/uapi/linux/netlink.h
@@ -155,6 +155,7 @@ enum nlmsgerr_attrs {
 #define NETLINK_LIST_MEMBERSHIPS	9
 #define NETLINK_CAP_ACK			10
 #define NETLINK_EXT_ACK			11
+#define NETLINK_DUMP_STRICT_CHK		12
 
 struct nl_pktinfo {
 	__u32	group;
-- 
cgit v1.2.3


From 76b0b801782b34b3028dcef3de36cb634e3908a8 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 17:06:57 -0300
Subject: tools headers uapi: Update linux/if_link.h header copy

To pick the changes from:

  9163a0fc1f0c ("net: bridge: add support for per-port vlan stats")

And silence this build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/if_link.h' differs from latest version at 'include/uapi/linux/if_link.h'

Cc: Alexei Starovoitov <ast@kernel.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric Leblond <eric@regit.org>
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Link: https://lkml.kernel.org/n/tip-7p53ghippywz7fqkwo3nkzet@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/if_link.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 58faab897201..1debfa42cba1 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -287,6 +287,7 @@ enum {
 	IFLA_BR_MCAST_STATS_ENABLED,
 	IFLA_BR_MCAST_IGMP_VERSION,
 	IFLA_BR_MCAST_MLD_VERSION,
+	IFLA_BR_VLAN_STATS_PER_PORT,
 	__IFLA_BR_MAX,
 };
 
-- 
cgit v1.2.3


From ff27a06af6ffd3f49b9e193eb68f487ad76651e1 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Tue, 30 Oct 2018 22:30:03 -0700
Subject: perf top: Start display thread earlier

If events are coming in at a rate such that the event processing thread
can barely keep up, our initial run of the event ring will almost never
terminate and this delays the starting of the display thread.

The screen basically stays black until the event thread can get out of
it's endless loop.

Therefore, start the display thread before we start processing the ring
buffer.

This also make sure that we always have the user requested real time
setting engaged when processing the ring.

Signed-off-by: David S. Miller <davem@davemloft.net>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/20181030.223003.2242527041807905962.davem@davemloft.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-top.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 8e29e0cc8626..b2838de13de0 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1134,11 +1134,6 @@ static int __cmd_top(struct perf_top *top)
         if (!target__none(&opts->target))
                 perf_evlist__enable(top->evlist);
 
-	/* Wait for a minimal set of events before starting the snapshot */
-	perf_evlist__poll(top->evlist, 100);
-
-	perf_top__mmap_read(top);
-
 	ret = -1;
 	if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
 							    display_thread), top)) {
@@ -1156,6 +1151,11 @@ static int __cmd_top(struct perf_top *top)
 		}
 	}
 
+	/* Wait for a minimal set of events before starting the snapshot */
+	perf_evlist__poll(top->evlist, 100);
+
+	perf_top__mmap_read(top);
+
 	while (!done) {
 		u64 hits = top->samples;
 
-- 
cgit v1.2.3


From 4f8f382e635707ddaddf8269a116e4f8cc8835c0 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Tue, 30 Oct 2018 22:24:04 -0700
Subject: perf tools: Don't clone maps from parent when synthesizing forks

When synthesizing FORK events, we are trying to create thread objects
for the already running tasks on the machine.

Normally, for a kernel FORK event, we want to clone the parent's maps
because that is what the kernel just did.

But when synthesizing, this should not be done.  If we do, we end up
with overlapping maps as we process the sythesized MMAP2 events that
get delivered shortly thereafter.

Use the FORK event misc flags in an internal way to signal this
situation, so we can elide the map clone when appropriate.

Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joe Mario <jmario@redhat.com>
Link: http://lkml.kernel.org/r/20181030.222404.2085088822877051075.davem@davemloft.net
[ Added comment about flag use in machine__process_fork_event(),
  use ternary op in thread__clone_map_groups() as suggested by Jiri ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 include/uapi/linux/perf_event.h       |  2 ++
 tools/include/uapi/linux/perf_event.h |  2 ++
 tools/perf/util/event.c               |  1 +
 tools/perf/util/machine.c             | 19 ++++++++++++++++++-
 tools/perf/util/thread.c              | 13 +++++--------
 tools/perf/util/thread.h              |  2 +-
 6 files changed, 29 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index f35eb72739c0..9de8780ac8d9 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -646,10 +646,12 @@ struct perf_event_mmap_page {
  *
  *   PERF_RECORD_MISC_MMAP_DATA  - PERF_RECORD_MMAP* events
  *   PERF_RECORD_MISC_COMM_EXEC  - PERF_RECORD_COMM event
+ *   PERF_RECORD_MISC_FORK_EXEC  - PERF_RECORD_FORK event (perf internal)
  *   PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events
  */
 #define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
+#define PERF_RECORD_MISC_FORK_EXEC		(1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
 /*
  * These PERF_RECORD_MISC_* flags below are safely reused
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index f35eb72739c0..9de8780ac8d9 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -646,10 +646,12 @@ struct perf_event_mmap_page {
  *
  *   PERF_RECORD_MISC_MMAP_DATA  - PERF_RECORD_MMAP* events
  *   PERF_RECORD_MISC_COMM_EXEC  - PERF_RECORD_COMM event
+ *   PERF_RECORD_MISC_FORK_EXEC  - PERF_RECORD_FORK event (perf internal)
  *   PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events
  */
 #define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
+#define PERF_RECORD_MISC_FORK_EXEC		(1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
 /*
  * These PERF_RECORD_MISC_* flags below are safely reused
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index bc646185f8d9..e9c108a6b1c3 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -308,6 +308,7 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
 	event->fork.pid  = tgid;
 	event->fork.tid  = pid;
 	event->fork.header.type = PERF_RECORD_FORK;
+	event->fork.header.misc = PERF_RECORD_MISC_FORK_EXEC;
 
 	event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 8ee8ab39d8ac..8f36ce813bc5 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1708,6 +1708,7 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 	struct thread *parent = machine__findnew_thread(machine,
 							event->fork.ppid,
 							event->fork.ptid);
+	bool do_maps_clone = true;
 	int err = 0;
 
 	if (dump_trace)
@@ -1736,9 +1737,25 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 
 	thread = machine__findnew_thread(machine, event->fork.pid,
 					 event->fork.tid);
+	/*
+	 * When synthesizing FORK events, we are trying to create thread
+	 * objects for the already running tasks on the machine.
+	 *
+	 * Normally, for a kernel FORK event, we want to clone the parent's
+	 * maps because that is what the kernel just did.
+	 *
+	 * But when synthesizing, this should not be done.  If we do, we end up
+	 * with overlapping maps as we process the sythesized MMAP2 events that
+	 * get delivered shortly thereafter.
+	 *
+	 * Use the FORK event misc flags in an internal way to signal this
+	 * situation, so we can elide the map clone when appropriate.
+	 */
+	if (event->fork.header.misc & PERF_RECORD_MISC_FORK_EXEC)
+		do_maps_clone = false;
 
 	if (thread == NULL || parent == NULL ||
-	    thread__fork(thread, parent, sample->time) < 0) {
+	    thread__fork(thread, parent, sample->time, do_maps_clone) < 0) {
 		dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
 		err = -1;
 	}
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 2048d393ece6..3d9ed7d0e281 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -330,7 +330,8 @@ static int thread__prepare_access(struct thread *thread)
 }
 
 static int thread__clone_map_groups(struct thread *thread,
-				    struct thread *parent)
+				    struct thread *parent,
+				    bool do_maps_clone)
 {
 	/* This is new thread, we share map groups for process. */
 	if (thread->pid_ == parent->pid_)
@@ -341,15 +342,11 @@ static int thread__clone_map_groups(struct thread *thread,
 			 thread->pid_, thread->tid, parent->pid_, parent->tid);
 		return 0;
 	}
-
 	/* But this one is new process, copy maps. */
-	if (map_groups__clone(thread, parent->mg) < 0)
-		return -ENOMEM;
-
-	return 0;
+	return do_maps_clone ? map_groups__clone(thread, parent->mg) : 0;
 }
 
-int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone)
 {
 	if (parent->comm_set) {
 		const char *comm = thread__comm_str(parent);
@@ -362,7 +359,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 	}
 
 	thread->ppid = parent->tid;
-	return thread__clone_map_groups(thread, parent);
+	return thread__clone_map_groups(thread, parent, do_maps_clone);
 }
 
 void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 36c09a9904e6..30e2b4c165fe 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -89,7 +89,7 @@ struct comm *thread__comm(const struct thread *thread);
 struct comm *thread__exec_comm(const struct thread *thread);
 const char *thread__comm_str(const struct thread *thread);
 int thread__insert_map(struct thread *thread, struct map *map);
-int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
 struct thread *thread__main_thread(struct machine *machine, struct thread *thread);
-- 
cgit v1.2.3


From 242483068b4b9ad02f1653819b6e683577681e0e Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 31 Oct 2018 11:10:42 +0200
Subject: perf intel-pt: Insert callchain context into synthesized callchains

In the absence of a fallback, callchains must encode also the callchain
context. Do that now there is no fallback.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: stable@vger.kernel.org # 4.19
Link: http://lkml.kernel.org/r/100ea2ec-ed14-b56d-d810-e0a6d2f4b069@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt.c     |  6 ++++--
 tools/perf/util/thread-stack.c | 44 +++++++++++++++++++++++++++++++++---------
 tools/perf/util/thread-stack.h |  2 +-
 3 files changed, 40 insertions(+), 12 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index ffa385a029b3..60732213d16a 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -759,7 +759,8 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 	if (pt->synth_opts.callchain) {
 		size_t sz = sizeof(struct ip_callchain);
 
-		sz += pt->synth_opts.callchain_sz * sizeof(u64);
+		/* Add 1 to callchain_sz for callchain context */
+		sz += (pt->synth_opts.callchain_sz + 1) * sizeof(u64);
 		ptq->chain = zalloc(sz);
 		if (!ptq->chain)
 			goto out_free;
@@ -1160,7 +1161,8 @@ static void intel_pt_prep_sample(struct intel_pt *pt,
 
 	if (pt->synth_opts.callchain) {
 		thread_stack__sample(ptq->thread, ptq->chain,
-				     pt->synth_opts.callchain_sz, sample->ip);
+				     pt->synth_opts.callchain_sz + 1,
+				     sample->ip, pt->kernel_start);
 		sample->callchain = ptq->chain;
 	}
 
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index c091635bf7dc..61a4286a74dc 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -310,20 +310,46 @@ void thread_stack__free(struct thread *thread)
 	}
 }
 
+static inline u64 callchain_context(u64 ip, u64 kernel_start)
+{
+	return ip < kernel_start ? PERF_CONTEXT_USER : PERF_CONTEXT_KERNEL;
+}
+
 void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
-			  size_t sz, u64 ip)
+			  size_t sz, u64 ip, u64 kernel_start)
 {
-	size_t i;
+	u64 context = callchain_context(ip, kernel_start);
+	u64 last_context;
+	size_t i, j;
 
-	if (!thread || !thread->ts)
-		chain->nr = 1;
-	else
-		chain->nr = min(sz, thread->ts->cnt + 1);
+	if (sz < 2) {
+		chain->nr = 0;
+		return;
+	}
 
-	chain->ips[0] = ip;
+	chain->ips[0] = context;
+	chain->ips[1] = ip;
+
+	if (!thread || !thread->ts) {
+		chain->nr = 2;
+		return;
+	}
+
+	last_context = context;
+
+	for (i = 2, j = 1; i < sz && j <= thread->ts->cnt; i++, j++) {
+		ip = thread->ts->stack[thread->ts->cnt - j].ret_addr;
+		context = callchain_context(ip, kernel_start);
+		if (context != last_context) {
+			if (i >= sz - 1)
+				break;
+			chain->ips[i++] = context;
+			last_context = context;
+		}
+		chain->ips[i] = ip;
+	}
 
-	for (i = 1; i < chain->nr; i++)
-		chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
+	chain->nr = i;
 }
 
 struct call_return_processor *
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index b7e41c4ebfdd..f97c00a8c251 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -84,7 +84,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 			u64 to_ip, u16 insn_len, u64 trace_nr);
 void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
 void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
-			  size_t sz, u64 ip);
+			  size_t sz, u64 ip, u64 kernel_start);
 int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
 size_t thread_stack__depth(struct thread *thread);
-- 
cgit v1.2.3


From 5d4f0edaa3ac4f1844ed7c64cd2bae6f1912bac5 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 31 Oct 2018 11:10:43 +0200
Subject: perf intel-pt/bts: Calculate cpumode for synthesized samples

In the absence of a fallback, samples must provide a correct cpumode for
the 'ip'. Do that now there is no fallback.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: stable@vger.kernel.org # 4.19
Link: http://lkml.kernel.org/r/20181031091043.23465-6-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-bts.c | 17 ++++++++++++-----
 tools/perf/util/intel-pt.c  | 22 +++++++++++++---------
 2 files changed, 25 insertions(+), 14 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 3b3a3d55dca1..7b27d77306c2 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -269,6 +269,13 @@ static int intel_bts_do_fix_overlap(struct auxtrace_queue *queue,
 	return 0;
 }
 
+static inline u8 intel_bts_cpumode(struct intel_bts *bts, uint64_t ip)
+{
+	return machine__kernel_ip(bts->machine, ip) ?
+	       PERF_RECORD_MISC_KERNEL :
+	       PERF_RECORD_MISC_USER;
+}
+
 static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 					 struct branch *branch)
 {
@@ -281,12 +288,8 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	    bts->num_events++ <= bts->synth_opts.initial_skip)
 		return 0;
 
-	event.sample.header.type = PERF_RECORD_SAMPLE;
-	event.sample.header.misc = PERF_RECORD_MISC_USER;
-	event.sample.header.size = sizeof(struct perf_event_header);
-
-	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = le64_to_cpu(branch->from);
+	sample.cpumode = intel_bts_cpumode(bts, sample.ip);
 	sample.pid = btsq->pid;
 	sample.tid = btsq->tid;
 	sample.addr = le64_to_cpu(branch->to);
@@ -298,6 +301,10 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	sample.insn_len = btsq->intel_pt_insn.length;
 	memcpy(sample.insn, btsq->intel_pt_insn.buf, INTEL_PT_INSN_BUF_SZ);
 
+	event.sample.header.type = PERF_RECORD_SAMPLE;
+	event.sample.header.misc = sample.cpumode;
+	event.sample.header.size = sizeof(struct perf_event_header);
+
 	if (bts->synth_opts.inject) {
 		event.sample.header.size = bts->branches_event_size;
 		ret = perf_event__synthesize_sample(&event,
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 60732213d16a..86cc9a64e982 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -407,6 +407,13 @@ intel_pt_cache_lookup(struct dso *dso, struct machine *machine, u64 offset)
 	return auxtrace_cache__lookup(dso->auxtrace_cache, offset);
 }
 
+static inline u8 intel_pt_cpumode(struct intel_pt *pt, uint64_t ip)
+{
+	return ip >= pt->kernel_start ?
+	       PERF_RECORD_MISC_KERNEL :
+	       PERF_RECORD_MISC_USER;
+}
+
 static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 				   uint64_t *insn_cnt_ptr, uint64_t *ip,
 				   uint64_t to_ip, uint64_t max_insn_cnt,
@@ -429,10 +436,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 	if (to_ip && *ip == to_ip)
 		goto out_no_cache;
 
-	if (*ip >= ptq->pt->kernel_start)
-		cpumode = PERF_RECORD_MISC_KERNEL;
-	else
-		cpumode = PERF_RECORD_MISC_USER;
+	cpumode = intel_pt_cpumode(ptq->pt, *ip);
 
 	thread = ptq->thread;
 	if (!thread) {
@@ -1059,15 +1063,11 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
 				   union perf_event *event,
 				   struct perf_sample *sample)
 {
-	event->sample.header.type = PERF_RECORD_SAMPLE;
-	event->sample.header.misc = PERF_RECORD_MISC_USER;
-	event->sample.header.size = sizeof(struct perf_event_header);
-
 	if (!pt->timeless_decoding)
 		sample->time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
-	sample->cpumode = PERF_RECORD_MISC_USER;
 	sample->ip = ptq->state->from_ip;
+	sample->cpumode = intel_pt_cpumode(pt, sample->ip);
 	sample->pid = ptq->pid;
 	sample->tid = ptq->tid;
 	sample->addr = ptq->state->to_ip;
@@ -1076,6 +1076,10 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
 	sample->flags = ptq->flags;
 	sample->insn_len = ptq->insn_len;
 	memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
+
+	event->sample.header.type = PERF_RECORD_SAMPLE;
+	event->sample.header.misc = sample->cpumode;
+	event->sample.header.size = sizeof(struct perf_event_header);
 }
 
 static int intel_pt_inject_event(union perf_event *event,
-- 
cgit v1.2.3


From 8f3f09358c81248109463b3cae254b7db4ea9af0 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 31 Oct 2018 09:56:45 +0000
Subject: selftests: mlxsw: qos_mc_aware: Tweak for min shaper

Since the minimum shaper is now being enabled for MC TCs, it's
unreasonable to expect no UC traffic loss. Minimal min shaper value is
200Mbps, which is 20% of the 1Gbps that this test configures on egress.
To cover for glitches, tolerate up to 25% UC degradation under MC
overload.

Fixes: b5638d46c90a ("selftests: mlxsw: Add a test for UC behavior under MC flood")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
index 0150bb2741eb..a8fc36d670e1 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
@@ -311,7 +311,7 @@ test_mc_aware()
 			ret = 100 * ($ucth1 - $ucth2) / $ucth1
 			if (ret > 0) { ret } else { 0 }
 		    ")
-	check_err $(bc <<< "$deg > 10")
+	check_err $(bc <<< "$deg > 25")
 
 	local interval=$((d1 - d0))
 	local mc_ir=$(rate $u0 $u1 $interval)
-- 
cgit v1.2.3


From a5ee171d087ee632a5f190bb3ce1c0f98e06ec0a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 31 Oct 2018 09:56:46 +0000
Subject: selftests: mlxsw: qos_mc_aware: Add a test for UC awareness

In a previous patch, mlxsw was updated to configure a minimum bandwidth
allowance on MC TCs. Test that this indeed fixes the problem of UC
traffic overload pushing out all MC traffic.

Fixes: b5638d46c90a ("selftests: mlxsw: Add a test for UC behavior under MC flood")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/qos_mc_aware.sh    | 93 ++++++++++++++++------
 1 file changed, 70 insertions(+), 23 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
index a8fc36d670e1..117f6f35d72f 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
@@ -25,24 +25,24 @@
 # Thus we set MTU to 10K on all involved interfaces. Then both unicast and
 # multicast traffic uses 8K frames.
 #
-# +-----------------------+                +----------------------------------+
-# | H1                    |                |                               H2 |
-# |                       |                |  unicast --> + $h2.111           |
-# |                       |                |  traffic     | 192.0.2.129/28    |
-# |          multicast    |                |              | e-qos-map 0:1     |
-# |          traffic      |                |              |                   |
-# | $h1 + <-----          |                |              + $h2               |
-# +-----|-----------------+                +--------------|-------------------+
-#       |                                                 |
-# +-----|-------------------------------------------------|-------------------+
-# |     + $swp1                                           + $swp2             |
-# |     | >1Gbps                                          | >1Gbps            |
-# | +---|----------------+                     +----------|----------------+  |
-# | |   + $swp1.1        |                     |          + $swp2.111      |  |
+# +---------------------------+            +----------------------------------+
+# | H1                        |            |                               H2 |
+# |                           |            |  unicast --> + $h2.111           |
+# |                 multicast |            |  traffic     | 192.0.2.129/28    |
+# |                 traffic   |            |              | e-qos-map 0:1     |
+# |           $h1 + <-----    |            |              |                   |
+# | 192.0.2.65/28 |           |            |              + $h2               |
+# +---------------|-----------+            +--------------|-------------------+
+#                 |                                       |
+# +---------------|---------------------------------------|-------------------+
+# |         $swp1 +                                       + $swp2             |
+# |        >1Gbps |                                       | >1Gbps            |
+# | +-------------|------+                     +----------|----------------+  |
+# | |     $swp1.1 +      |                     |          + $swp2.111      |  |
 # | |                BR1 |             SW      | BR111                     |  |
-# | |   + $swp3.1        |                     |          + $swp3.111      |  |
-# | +---|----------------+                     +----------|----------------+  |
-# |     \_________________________________________________/                   |
+# | |     $swp3.1 +      |                     |          + $swp3.111      |  |
+# | +-------------|------+                     +----------|----------------+  |
+# |               \_______________________________________/                   |
 # |                                    |                                      |
 # |                                    + $swp3                                |
 # |                                    | 1Gbps bottleneck                     |
@@ -51,6 +51,7 @@
 #                                      |
 #                                   +--|-----------------+
 #                                   |  + $h3          H3 |
+#                                   |  | 192.0.2.66/28   |
 #                                   |  |                 |
 #                                   |  + $h3.111         |
 #                                   |    192.0.2.130/28  |
@@ -59,6 +60,7 @@
 ALL_TESTS="
 	ping_ipv4
 	test_mc_aware
+	test_uc_aware
 "
 
 lib_dir=$(dirname $0)/../../../net/forwarding
@@ -68,14 +70,14 @@ source $lib_dir/lib.sh
 
 h1_create()
 {
-	simple_if_init $h1
+	simple_if_init $h1 192.0.2.65/28
 	mtu_set $h1 10000
 }
 
 h1_destroy()
 {
 	mtu_restore $h1
-	simple_if_fini $h1
+	simple_if_fini $h1 192.0.2.65/28
 }
 
 h2_create()
@@ -97,7 +99,7 @@ h2_destroy()
 
 h3_create()
 {
-	simple_if_init $h3
+	simple_if_init $h3 192.0.2.66/28
 	mtu_set $h3 10000
 
 	vlan_create $h3 111 v$h3 192.0.2.130/28
@@ -108,7 +110,7 @@ h3_destroy()
 	vlan_destroy $h3 111
 
 	mtu_restore $h3
-	simple_if_fini $h3
+	simple_if_fini $h3 192.0.2.66/28
 }
 
 switch_create()
@@ -251,7 +253,7 @@ measure_uc_rate()
 	# average ingress rate to somewhat mitigate this.
 	local min_ingress=2147483648
 
-	mausezahn $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \
+	$MZ $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \
 		-a own -b $h3mac -t udp -q &
 	sleep 1
 
@@ -291,7 +293,7 @@ test_mc_aware()
 	check_err $? "Could not get high enough UC-only ingress rate"
 	local ucth1=${uc_rate[1]}
 
-	mausezahn $h1 -p 8000 -c 0 -a own -b bc -t udp -q &
+	$MZ $h1 -p 8000 -c 0 -a own -b bc -t udp -q &
 
 	local d0=$(date +%s)
 	local t0=$(ethtool_stats_get $h3 rx_octets_prio_0)
@@ -335,6 +337,51 @@ test_mc_aware()
 	echo "    egress UC throughput  $(humanize ${uc_rate_2[1]})"
 	echo "    ingress MC throughput $(humanize $mc_ir)"
 	echo "    egress MC throughput  $(humanize $mc_er)"
+	echo
+}
+
+test_uc_aware()
+{
+	RET=0
+
+	$MZ $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \
+		-a own -b $h3mac -t udp -q &
+
+	local d0=$(date +%s)
+	local t0=$(ethtool_stats_get $h3 rx_octets_prio_1)
+	local u0=$(ethtool_stats_get $swp2 rx_octets_prio_1)
+	sleep 1
+
+	local attempts=50
+	local passes=0
+	local i
+
+	for ((i = 0; i < attempts; ++i)); do
+		if $ARPING -c 1 -I $h1 -b 192.0.2.66 -q -w 0.1; then
+			((passes++))
+		fi
+
+		sleep 0.1
+	done
+
+	local d1=$(date +%s)
+	local t1=$(ethtool_stats_get $h3 rx_octets_prio_1)
+	local u1=$(ethtool_stats_get $swp2 rx_octets_prio_1)
+
+	local interval=$((d1 - d0))
+	local uc_ir=$(rate $u0 $u1 $interval)
+	local uc_er=$(rate $t0 $t1 $interval)
+
+	((attempts == passes))
+	check_err $?
+
+	# Suppress noise from killing mausezahn.
+	{ kill %% && wait; } 2>/dev/null
+
+	log_test "MC performace under UC overload"
+	echo "    ingress UC throughput $(humanize ${uc_ir})"
+	echo "    egress UC throughput  $(humanize ${uc_er})"
+	echo "    sent $attempts BC ARPs, got $passes responses"
 }
 
 trap cleanup EXIT
-- 
cgit v1.2.3


From deee2cae27d1914850195e3fb219cc611e953560 Mon Sep 17 00:00:00 2001
From: Li Zhijian <lizhijian@cn.fujitsu.com>
Date: Tue, 30 Oct 2018 11:15:55 +0800
Subject: kselftests/bpf: use ping6 as the default ipv6 ping binary if it
 exists

ping binary on some distros doesn't support "ping -6" anymore.

Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_skb_cgroup_id.sh | 3 ++-
 tools/testing/selftests/bpf/test_sock_addr.sh     | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id.sh b/tools/testing/selftests/bpf/test_skb_cgroup_id.sh
index 42544a969abc..a9bc6f82abc1 100755
--- a/tools/testing/selftests/bpf/test_skb_cgroup_id.sh
+++ b/tools/testing/selftests/bpf/test_skb_cgroup_id.sh
@@ -10,7 +10,7 @@ wait_for_ip()
 	echo -n "Wait for testing link-local IP to become available "
 	for _i in $(seq ${MAX_PING_TRIES}); do
 		echo -n "."
-		if ping -6 -q -c 1 -W 1 ff02::1%${TEST_IF} >/dev/null 2>&1; then
+		if $PING6 -c 1 -W 1 ff02::1%${TEST_IF} >/dev/null 2>&1; then
 			echo " OK"
 			return
 		fi
@@ -58,5 +58,6 @@ BPF_PROG_OBJ="${DIR}/test_skb_cgroup_id_kern.o"
 BPF_PROG_SECTION="cgroup_id_logger"
 BPF_PROG_ID=0
 PROG="${DIR}/test_skb_cgroup_id_user"
+type ping6 >/dev/null 2>&1 && PING6="ping6" || PING6="ping -6"
 
 main
diff --git a/tools/testing/selftests/bpf/test_sock_addr.sh b/tools/testing/selftests/bpf/test_sock_addr.sh
index 9832a875a828..3b9fdb8094aa 100755
--- a/tools/testing/selftests/bpf/test_sock_addr.sh
+++ b/tools/testing/selftests/bpf/test_sock_addr.sh
@@ -4,7 +4,8 @@ set -eu
 
 ping_once()
 {
-	ping -${1} -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1
+	type ping${1} >/dev/null 2>&1 && PING="ping${1}" || PING="ping -${1}"
+	$PING -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1
 }
 
 wait_for_ip()
-- 
cgit v1.2.3


From 3615353218744bb60f55170c620ce4dce1a008c7 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 31 Oct 2018 12:57:18 -0700
Subject: libbpf: Fix compile error in libbpf_attach_type_by_name

Arnaldo Carvalho de Melo reported build error in libbpf when clang
version 3.8.1-24 (tags/RELEASE_381/final) is used:

libbpf.c:2201:36: error: comparison of constant -22 with expression of
type 'const enum bpf_attach_type' is always false
[-Werror,-Wtautological-constant-out-of-range-compare]
                if (section_names[i].attach_type == -EINVAL)
                    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ^  ~~~~~~~
1 error generated.

Fix the error by keeping "is_attachable" property of a program in a
separate struct field instead of trying to use attach_type itself.

Fixes: 956b620fcf0b ("libbpf: Introduce libbpf_attach_type_by_name")
Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index b607be7236d3..d6e62e90e8d4 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2084,19 +2084,19 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 	prog->expected_attach_type = type;
 }
 
-#define BPF_PROG_SEC_IMPL(string, ptype, eatype, atype) \
-	{ string, sizeof(string) - 1, ptype, eatype, atype }
+#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, atype) \
+	{ string, sizeof(string) - 1, ptype, eatype, is_attachable, atype }
 
 /* Programs that can NOT be attached. */
-#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, -EINVAL)
+#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0)
 
 /* Programs that can be attached. */
 #define BPF_APROG_SEC(string, ptype, atype) \
-	BPF_PROG_SEC_IMPL(string, ptype, 0, atype)
+	BPF_PROG_SEC_IMPL(string, ptype, 0, 1, atype)
 
 /* Programs that must specify expected attach type at load time. */
 #define BPF_EAPROG_SEC(string, ptype, eatype) \
-	BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype)
+	BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, eatype)
 
 /* Programs that can be attached but attach type can't be identified by section
  * name. Kept for backward compatibility.
@@ -2108,6 +2108,7 @@ static const struct {
 	size_t len;
 	enum bpf_prog_type prog_type;
 	enum bpf_attach_type expected_attach_type;
+	int is_attachable;
 	enum bpf_attach_type attach_type;
 } section_names[] = {
 	BPF_PROG_SEC("socket",			BPF_PROG_TYPE_SOCKET_FILTER),
@@ -2198,7 +2199,7 @@ int libbpf_attach_type_by_name(const char *name,
 	for (i = 0; i < ARRAY_SIZE(section_names); i++) {
 		if (strncmp(name, section_names[i].sec, section_names[i].len))
 			continue;
-		if (section_names[i].attach_type == -EINVAL)
+		if (!section_names[i].is_attachable)
 			return -EINVAL;
 		*attach_type = section_names[i].attach_type;
 		return 0;
-- 
cgit v1.2.3


From 1936f094e164cc13ebf17aba1d6b34e033e64188 Mon Sep 17 00:00:00 2001
From: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
Date: Wed, 31 Oct 2018 22:48:13 +0530
Subject: selftests/powerpc: Fix compilation issue due to asm label

We are using 'dscr_insn' as a label in inline asm to identify if a
SIGILL was generated by the mtspr instruction at that point. However,
with inline assembly, the compiler is still free to duplicate the asm
statement for optimization purposes, which results in the label being
defined twice with the error:
	/tmp/ccerQCql.s:874: Error: symbol `dscr_insn' is already defined

With different compiler versions, we may also see:
	/tmp/ccJzLDlN.o:(.toc+0x0): undefined reference to `dscr_insn'

Remove the use of the label in the inline assembly. Instead, just look
for the offending instruction in the signal handler.

Fixes: d2bf793237b3 ("selftests/powerpc: Add test to verify rfi flush across a system call")
Reported-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Tested-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/utils.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c
index 43c342845be0..ed62f4153d3e 100644
--- a/tools/testing/selftests/powerpc/utils.c
+++ b/tools/testing/selftests/powerpc/utils.c
@@ -25,7 +25,6 @@
 #include "utils.h"
 
 static char auxv[4096];
-extern unsigned int dscr_insn[];
 
 int read_auxv(char *buf, ssize_t buf_size)
 {
@@ -247,7 +246,8 @@ static void sigill_handler(int signr, siginfo_t *info, void *unused)
 	ucontext_t *ctx = (ucontext_t *)unused;
 	unsigned long *pc = &UCONTEXT_NIA(ctx);
 
-	if (*pc == (unsigned long)&dscr_insn) {
+	/* mtspr 3,RS to check for move to DSCR below */
+	if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) {
 		if (!warned++)
 			printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n");
 		*pc += 4;
@@ -271,5 +271,5 @@ void set_dscr(unsigned long val)
 		init = 1;
 	}
 
-	asm volatile("dscr_insn: mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR));
+	asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR));
 }
-- 
cgit v1.2.3


From 2683f4128c8730699296827d3209d2de80fa1d6c Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 1 Nov 2018 00:05:54 +0100
Subject: bpf: add various test cases to test_verifier

Add some more map related test cases to test_verifier kselftest
to improve test coverage. Summary: 1012 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 250 ++++++++++++++++++++++++++++
 1 file changed, 250 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 36f3d3009d1a..4c7445d4b3e6 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -6454,6 +6454,256 @@ static struct bpf_test tests[] = {
 		.errstr = "R1 min value is negative",
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
+	{
+		"map access: known scalar += value_ptr",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_MOV64_IMM(BPF_REG_1, 4),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"map access: value_ptr += known scalar",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_MOV64_IMM(BPF_REG_1, 4),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"map access: unknown scalar += value_ptr",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"map access: value_ptr += unknown scalar",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"map access: value_ptr += value_ptr",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_0),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = REJECT,
+		.errstr = "R0 pointer += pointer prohibited",
+	},
+	{
+		"map access: known scalar -= value_ptr",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_MOV64_IMM(BPF_REG_1, 4),
+			BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = REJECT,
+		.errstr = "R1 tried to subtract pointer from scalar",
+	},
+	{
+		"map access: value_ptr -= known scalar",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_MOV64_IMM(BPF_REG_1, 4),
+			BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = REJECT,
+		.errstr = "R0 min value is outside of the array range",
+	},
+	{
+		"map access: value_ptr -= known scalar, 2",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+			BPF_MOV64_IMM(BPF_REG_1, 6),
+			BPF_MOV64_IMM(BPF_REG_2, 4),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_2),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"map access: unknown scalar -= value_ptr",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
+			BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = REJECT,
+		.errstr = "R1 tried to subtract pointer from scalar",
+	},
+	{
+		"map access: value_ptr -= unknown scalar",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
+			BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = REJECT,
+		.errstr = "R0 min value is negative",
+	},
+	{
+		"map access: value_ptr -= unknown scalar, 2",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
+			BPF_ALU64_IMM(BPF_OR, BPF_REG_1, 0x7),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+			BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = ACCEPT,
+		.retval = 1,
+	},
+	{
+		"map access: value_ptr -= value_ptr",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+			BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_0),
+			BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map_array_48b = { 3 },
+		.result = REJECT,
+		.errstr = "R0 invalid mem access 'inv'",
+		.errstr_unpriv = "R0 pointer -= pointer prohibited",
+	},
 	{
 		"map lookup helper access to map",
 		.insns = {
-- 
cgit v1.2.3


From 832c6f2c29ec519b766923937f4f93fb1008b47d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 1 Nov 2018 00:05:55 +0100
Subject: bpf: test make sure to run unpriv test cases in test_verifier

Right now unprivileged tests are never executed as a BPF test run,
only loaded. Allow for running them as well so that we can check
the outcome and probe for regressions.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_verifier.c | 71 ++++++++++++++++-------------
 1 file changed, 40 insertions(+), 31 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 4c7445d4b3e6..6f61df62f690 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -76,7 +76,7 @@ struct bpf_test {
 	int fixup_percpu_cgroup_storage[MAX_FIXUPS];
 	const char *errstr;
 	const char *errstr_unpriv;
-	uint32_t retval;
+	uint32_t retval, retval_unpriv;
 	enum {
 		UNDEF,
 		ACCEPT,
@@ -3084,6 +3084,8 @@ static struct bpf_test tests[] = {
 		.fixup_prog1 = { 2 },
 		.result = ACCEPT,
 		.retval = 42,
+		/* Verifier rewrite for unpriv skips tail call here. */
+		.retval_unpriv = 2,
 	},
 	{
 		"stack pointer arithmetic",
@@ -14149,6 +14151,33 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type,
 	}
 }
 
+static int set_admin(bool admin)
+{
+	cap_t caps;
+	const cap_value_t cap_val = CAP_SYS_ADMIN;
+	int ret = -1;
+
+	caps = cap_get_proc();
+	if (!caps) {
+		perror("cap_get_proc");
+		return -1;
+	}
+	if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_val,
+				admin ? CAP_SET : CAP_CLEAR)) {
+		perror("cap_set_flag");
+		goto out;
+	}
+	if (cap_set_proc(caps)) {
+		perror("cap_set_proc");
+		goto out;
+	}
+	ret = 0;
+out:
+	if (cap_free(caps))
+		perror("cap_free");
+	return ret;
+}
+
 static void do_test_single(struct bpf_test *test, bool unpriv,
 			   int *passes, int *errors)
 {
@@ -14157,6 +14186,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	struct bpf_insn *prog = test->insns;
 	int map_fds[MAX_NR_MAPS];
 	const char *expected_err;
+	uint32_t expected_val;
 	uint32_t retval;
 	int i, err;
 
@@ -14176,6 +14206,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		       test->result_unpriv : test->result;
 	expected_err = unpriv && test->errstr_unpriv ?
 		       test->errstr_unpriv : test->errstr;
+	expected_val = unpriv && test->retval_unpriv ?
+		       test->retval_unpriv : test->retval;
 
 	reject_from_alignment = fd_prog < 0 &&
 				(test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) &&
@@ -14209,16 +14241,20 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		__u8 tmp[TEST_DATA_LEN << 2];
 		__u32 size_tmp = sizeof(tmp);
 
+		if (unpriv)
+			set_admin(true);
 		err = bpf_prog_test_run(fd_prog, 1, test->data,
 					sizeof(test->data), tmp, &size_tmp,
 					&retval, NULL);
+		if (unpriv)
+			set_admin(false);
 		if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
 			printf("Unexpected bpf_prog_test_run error\n");
 			goto fail_log;
 		}
-		if (!err && retval != test->retval &&
-		    test->retval != POINTER_VALUE) {
-			printf("FAIL retval %d != %d\n", retval, test->retval);
+		if (!err && retval != expected_val &&
+		    expected_val != POINTER_VALUE) {
+			printf("FAIL retval %d != %d\n", retval, expected_val);
 			goto fail_log;
 		}
 	}
@@ -14261,33 +14297,6 @@ static bool is_admin(void)
 	return (sysadmin == CAP_SET);
 }
 
-static int set_admin(bool admin)
-{
-	cap_t caps;
-	const cap_value_t cap_val = CAP_SYS_ADMIN;
-	int ret = -1;
-
-	caps = cap_get_proc();
-	if (!caps) {
-		perror("cap_get_proc");
-		return -1;
-	}
-	if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_val,
-				admin ? CAP_SET : CAP_CLEAR)) {
-		perror("cap_set_flag");
-		goto out;
-	}
-	if (cap_set_proc(caps)) {
-		perror("cap_set_proc");
-		goto out;
-	}
-	ret = 0;
-out:
-	if (cap_free(caps))
-		perror("cap_free");
-	return ret;
-}
-
 static void get_unpriv_disabled()
 {
 	char buf[2];
-- 
cgit v1.2.3


From bcb6fb5da77c2a228adf07cc9cb1a0c2aa2001c6 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Wed, 31 Oct 2018 21:57:30 -0500
Subject: objtool: Support GCC 9 cold subfunction naming scheme

Starting with GCC 8, a lot of unlikely code was moved out of line to
"cold" subfunctions in .text.unlikely.

For example, the unlikely bits of:

  irq_do_set_affinity()

are moved out to the following subfunction:

  irq_do_set_affinity.cold.49()

Starting with GCC 9, the numbered suffix has been removed.  So in the
above example, the cold subfunction is instead:

  irq_do_set_affinity.cold()

Tweak the objtool subfunction detection logic so that it detects both
GCC 8 and GCC 9 naming schemes.

Reported-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/015e9544b1f188d36a7f02fa31e9e95629aa5f50.1541040800.git.jpoimboe@redhat.com
---
 tools/objtool/elf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 7ec85d567598..f8cef271dfc7 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -301,7 +301,7 @@ static int read_symbols(struct elf *elf)
 			if (sym->type != STT_FUNC)
 				continue;
 			sym->pfunc = sym->cfunc = sym;
-			coldstr = strstr(sym->name, ".cold.");
+			coldstr = strstr(sym->name, ".cold");
 			if (!coldstr)
 				continue;
 
-- 
cgit v1.2.3


From 51f5fd2e4615dcdc25cd7f9d19b7b27eb9ecdac7 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Wed, 31 Oct 2018 17:44:08 +0000
Subject: tools headers barrier: Fix arm64 tools build failure wrt
 smp_load_{acquire,release}

Cheers for reporting this. I managed to reproduce the build failure with
gcc version 6.3.0 20170516 (Debian 6.3.0-18+deb9u1).

The code in question is the arm64 versions of smp_load_acquire() and
smp_store_release(). Unlike other architectures, these are not built
around READ_ONCE() and WRITE_ONCE() since we have instructions we can
use instead of fences. Bringing our macros up-to-date with those (i.e.
tweaking the union initialisation and using the special "uXX_alias_t"
types) appears to fix the issue for me.

Committer notes:

Testing it in the systems previously failing:

  # time dm android-ndk:r12b-arm \
         android-ndk:r15c-arm \
         debian:experimental-x-arm64 \
         ubuntu:14.04.4-x-linaro-arm64 \
         ubuntu:16.04-x-arm \
         ubuntu:16.04-x-arm64 \
         ubuntu:18.04-x-arm \
         ubuntu:18.04-x-arm64
    1 android-ndk:r12b-arm          : Ok   arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease)
    2 android-ndk:r15c-arm          : Ok   arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease)
    3 debian:experimental-x-arm64   : Ok   aarch64-linux-gnu-gcc (Debian 8.2.0-7) 8.2.0
    4 ubuntu:14.04.4-x-linaro-arm64 : Ok   aarch64-linux-gnu-gcc (Linaro GCC 5.5-2017.10) 5.5.0
    5 ubuntu:16.04-x-arm            : Ok   arm-linux-gnueabihf-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609
    6 ubuntu:16.04-x-arm64          : Ok   aarch64-linux-gnu-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609
    7 ubuntu:18.04-x-arm            : Ok   arm-linux-gnueabihf-gcc (Ubuntu/Linaro 7.3.0-27ubuntu1~18.04) 7.3.0
    8 ubuntu:18.04-x-arm64          : Ok   aarch64-linux-gnu-gcc (Ubuntu/Linaro 7.3.0-27ubuntu1~18.04) 7.3.0

Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20181031174408.GA27871@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/arm64/include/asm/barrier.h | 133 +++++++++++++++++----------------
 1 file changed, 67 insertions(+), 66 deletions(-)

(limited to 'tools')

diff --git a/tools/arch/arm64/include/asm/barrier.h b/tools/arch/arm64/include/asm/barrier.h
index 12835ea0e417..378c051fa177 100644
--- a/tools/arch/arm64/include/asm/barrier.h
+++ b/tools/arch/arm64/include/asm/barrier.h
@@ -14,74 +14,75 @@
 #define wmb()		asm volatile("dmb ishst" ::: "memory")
 #define rmb()		asm volatile("dmb ishld" ::: "memory")
 
-#define smp_store_release(p, v)					\
-do {								\
-	union { typeof(*p) __val; char __c[1]; } __u =		\
-		{ .__val = (__force typeof(*p)) (v) }; 		\
-								\
-	switch (sizeof(*p)) {					\
-	case 1:							\
-		asm volatile ("stlrb %w1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u8 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	case 2:							\
-		asm volatile ("stlrh %w1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u16 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	case 4:							\
-		asm volatile ("stlr %w1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u32 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	case 8:							\
-		asm volatile ("stlr %1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u64 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	default:						\
-		/* Only to shut up gcc ... */			\
-		mb();						\
-		break;						\
-	}							\
+#define smp_store_release(p, v)						\
+do {									\
+	union { typeof(*p) __val; char __c[1]; } __u =			\
+		{ .__val = (v) }; 					\
+									\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile ("stlrb %w1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u8_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile ("stlrh %w1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u16_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile ("stlr %w1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u32_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	case 8:								\
+		asm volatile ("stlr %1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u64_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	default:							\
+		/* Only to shut up gcc ... */				\
+		mb();							\
+		break;							\
+	}								\
 } while (0)
 
-#define smp_load_acquire(p)					\
-({								\
-	union { typeof(*p) __val; char __c[1]; } __u;		\
-								\
-	switch (sizeof(*p)) {					\
-	case 1:							\
-		asm volatile ("ldarb %w0, %1"			\
-			: "=r" (*(__u8 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	case 2:							\
-		asm volatile ("ldarh %w0, %1"			\
-			: "=r" (*(__u16 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	case 4:							\
-		asm volatile ("ldar %w0, %1"			\
-			: "=r" (*(__u32 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	case 8:							\
-		asm volatile ("ldar %0, %1"			\
-			: "=r" (*(__u64 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	default:						\
-		/* Only to shut up gcc ... */			\
-		mb();						\
-		break;						\
-	}							\
-	__u.__val;						\
+#define smp_load_acquire(p)						\
+({									\
+	union { typeof(*p) __val; char __c[1]; } __u =			\
+		{ .__c = { 0 } };					\
+									\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile ("ldarb %w0, %1"				\
+			: "=r" (*(__u8_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile ("ldarh %w0, %1"				\
+			: "=r" (*(__u16_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile ("ldar %w0, %1"				\
+			: "=r" (*(__u32_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	case 8:								\
+		asm volatile ("ldar %0, %1"				\
+			: "=r" (*(__u64_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	default:							\
+		/* Only to shut up gcc ... */				\
+		mb();							\
+		break;							\
+	}								\
+	__u.__val;							\
 })
 
 #endif /* _TOOLS_LINUX_ASM_AARCH64_BARRIER_H */
-- 
cgit v1.2.3


From febf8a3712e4209b7e650b37b3b240a2b387794d Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 1 Nov 2018 10:34:34 -0300
Subject: perf examples bpf: Start augmenting raw_syscalls:sys_{start,exit}

The previous approach of attaching to each syscall showed how it is
possible to augment tracepoints and use that augmentation, pointer
payloads, in the existing beautifiers in 'perf trace', but for a more
general solution we now will try to augment the main
raw_syscalls:sys_{enter,exit} syscalls, and then pass instructions in
maps so that it knows which syscalls and which pointer contents, and how
many bytes for each of the arguments should be copied.

Start with just the bare minimum to collect what is provided by those
two tracepoints via the __augmented_syscalls__ map + bpf-output perf
event, which results in perf trace showing them without connecting
enter+exit:

  # perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c sleep 1
     0.000 sleep/11563 raw_syscalls:sys_exit:NR 59 = 0
     0.019 (         ): sleep/11563 brk() ...
     0.021 sleep/11563 raw_syscalls:sys_exit:NR 12 = 94682642325504
     0.033 (         ): sleep/11563 access(filename:, mode: R) ...
     0.037 sleep/11563 raw_syscalls:sys_exit:NR 21 = -2
     0.041 (         ): sleep/11563 openat(dfd: CWD, filename: , flags: CLOEXEC) ...
     0.044 sleep/11563 raw_syscalls:sys_exit:NR 257 = 3
     0.045 (         ): sleep/11563 fstat(fd: 3, statbuf: 0x7ffdbf7119b0) ...
     0.046 sleep/11563 raw_syscalls:sys_exit:NR 5 = 0
     0.047 (         ): sleep/11563 mmap(len: 103334, prot: READ, flags: PRIVATE, fd: 3) ...
     0.049 sleep/11563 raw_syscalls:sys_exit:NR 9 = 140196285493248
     0.050 (         ): sleep/11563 close(fd: 3) ...
     0.051 sleep/11563 raw_syscalls:sys_exit:NR 3 = 0
     0.059 (         ): sleep/11563 openat(dfd: CWD, filename: , flags: CLOEXEC) ...
     0.062 sleep/11563 raw_syscalls:sys_exit:NR 257 = 3
     0.063 (         ): sleep/11563 read(fd: 3, buf: 0x7ffdbf711b78, count: 832) ...
     0.065 sleep/11563 raw_syscalls:sys_exit:NR 0 = 832
     0.066 (         ): sleep/11563 fstat(fd: 3, statbuf: 0x7ffdbf711a10) ...
     0.067 sleep/11563 raw_syscalls:sys_exit:NR 5 = 0
     0.068 (         ): sleep/11563 mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS) ...
     0.070 sleep/11563 raw_syscalls:sys_exit:NR 9 = 140196285485056
     0.073 (         ): sleep/11563 mmap(len: 3889792, prot: EXEC|READ, flags: PRIVATE|DENYWRITE, fd: 3) ...
     0.076 sleep/11563 raw_syscalls:sys_exit:NR 9 = 140196279463936
     0.077 (         ): sleep/11563 mprotect(start: 0x7f81fd8a8000, len: 2093056) ...
     0.083 sleep/11563 raw_syscalls:sys_exit:NR 10 = 0
     0.084 (         ): sleep/11563 mmap(addr: 0x7f81fdaa7000, len: 24576, prot: READ|WRITE, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 1753088) ...
     0.088 sleep/11563 raw_syscalls:sys_exit:NR 9 = 140196283314176
     0.091 (         ): sleep/11563 mmap(addr: 0x7f81fdaad000, len: 14976, prot: READ|WRITE, flags: PRIVATE|FIXED|ANONYMOUS) ...
     0.093 sleep/11563 raw_syscalls:sys_exit:NR 9 = 140196283338752
     0.097 (         ): sleep/11563 close(fd: 3) ...
     0.098 sleep/11563 raw_syscalls:sys_exit:NR 3 = 0
     0.107 (         ): sleep/11563 arch_prctl(option: 4098, arg2: 140196285490432) ...
     0.108 sleep/11563 raw_syscalls:sys_exit:NR 158 = 0
     0.143 (         ): sleep/11563 mprotect(start: 0x7f81fdaa7000, len: 16384, prot: READ) ...
     0.146 sleep/11563 raw_syscalls:sys_exit:NR 10 = 0
     0.157 (         ): sleep/11563 mprotect(start: 0x561d037e7000, len: 4096, prot: READ) ...
     0.160 sleep/11563 raw_syscalls:sys_exit:NR 10 = 0
     0.163 (         ): sleep/11563 mprotect(start: 0x7f81fdcd5000, len: 4096, prot: READ) ...
     0.165 sleep/11563 raw_syscalls:sys_exit:NR 10 = 0
     0.166 (         ): sleep/11563 munmap(addr: 0x7f81fdcbb000, len: 103334) ...
     0.174 sleep/11563 raw_syscalls:sys_exit:NR 11 = 0
     0.216 (         ): sleep/11563 brk() ...
     0.217 sleep/11563 raw_syscalls:sys_exit:NR 12 = 94682642325504
     0.217 (         ): sleep/11563 brk(brk: 0x561d05453000) ...
     0.219 sleep/11563 raw_syscalls:sys_exit:NR 12 = 94682642460672
     0.220 (         ): sleep/11563 brk() ...
     0.221 sleep/11563 raw_syscalls:sys_exit:NR 12 = 94682642460672
     0.224 (         ): sleep/11563 open(filename: , flags: CLOEXEC) ...
     0.228 sleep/11563 raw_syscalls:sys_exit:NR 2 = 3
     0.229 (         ): sleep/11563 fstat(fd: 3, statbuf: 0x7f81fdaacaa0) ...
     0.230 sleep/11563 raw_syscalls:sys_exit:NR 5 = 0
     0.231 (         ): sleep/11563 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) ...
     0.234 sleep/11563 raw_syscalls:sys_exit:NR 9 = 140196166418432
     0.237 (         ): sleep/11563 close(fd: 3) ...
     0.238 sleep/11563 raw_syscalls:sys_exit:NR 3 = 0
     0.262 (         ): sleep/11563 nanosleep(rqtp: 0x7ffdbf7126f0) ...
  1000.399 sleep/11563 raw_syscalls:sys_exit:NR 35 = 0
  1000.440 (         ): sleep/11563 close(fd: 1) ...
  1000.447 sleep/11563 raw_syscalls:sys_exit:NR 3 = 0
  1000.454 (         ): sleep/11563 close(fd: 2) ...
  1000.468 (         ): sleep/11563 exit_group(                                                           )
  #

In the next csets we'll connect those events to the existing enter/exit
raw_syscalls handlers in 'perf trace', just like we did with the
syscalls:sys_{enter,exit}_* tracepoints.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-5nl8l4hx1tl9pqdx65nkp6pw@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/examples/bpf/augmented_raw_syscalls.c | 59 ++++++++++++++++++++++++
 1 file changed, 59 insertions(+)
 create mode 100644 tools/perf/examples/bpf/augmented_raw_syscalls.c

(limited to 'tools')

diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
new file mode 100644
index 000000000000..cde91c34b101
--- /dev/null
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Augment the raw_syscalls tracepoints with the contents of the pointer arguments.
+ *
+ * Test it with:
+ *
+ * perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c cat /etc/passwd > /dev/null
+ *
+ * This exactly matches what is marshalled into the raw_syscall:sys_enter
+ * payload expected by the 'perf trace' beautifiers.
+ *
+ * For now it just uses the existing tracepoint augmentation code in 'perf
+ * trace', in the next csets we'll hook up these with the sys_enter/sys_exit
+ * code that will combine entry/exit in a strace like way.
+ */
+
+#include <stdio.h>
+#include <linux/socket.h>
+
+/* bpf-output associated map */
+struct bpf_map SEC("maps") __augmented_syscalls__ = {
+	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(u32),
+	.max_entries = __NR_CPUS__,
+};
+
+struct syscall_enter_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	unsigned long	   args[6];
+};
+
+struct syscall_exit_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   ret;
+};
+
+SEC("raw_syscalls:sys_enter")
+int sys_enter(struct syscall_enter_args *args)
+{
+	struct {
+		struct syscall_enter_args args;
+	} augmented_args;
+	unsigned int len = sizeof(augmented_args);
+
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len);
+	return 0;
+}
+
+SEC("raw_syscalls:sys_exit")
+int sys_exit(struct syscall_exit_args *args)
+{
+	return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */
+}
+
+license(GPL);
-- 
cgit v1.2.3


From 3c5e3dabf3722a883227623a4adf61976c2224ff Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 1 Nov 2018 13:50:35 -0300
Subject: perf trace: When augmenting raw_syscalls plug raw_syscalls:sys_exit
 too

With just this commit we get to support all syscalls via hooking
raw_syscalls:sys_{enter,exit} to the trace__sys_{enter,exit} routines
to combine, strace-like, those tracepoints.

  # trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c sleep 1
         ? (         ): sleep/31680  ... [continued]: execve()) = 0
     0.043 ( 0.004 ms): sleep/31680 brk() = 0x55652a851000
     0.070 ( 0.009 ms): sleep/31680 access(filename:, mode: R) = -1 ENOENT No such file or directory
     0.087 ( 0.006 ms): sleep/31680 openat(dfd: CWD, filename: , flags: CLOEXEC) = 3
     0.096 ( 0.003 ms): sleep/31680 fstat(fd: 3, statbuf: 0x7ffc5269e190) = 0
     0.101 ( 0.005 ms): sleep/31680 mmap(len: 103334, prot: READ, flags: PRIVATE, fd: 3) = 0x7f709c239000
     0.109 ( 0.002 ms): sleep/31680 close(fd: 3) = 0
     0.126 ( 0.006 ms): sleep/31680 openat(dfd: CWD, filename: , flags: CLOEXEC) = 3
     0.135 ( 0.003 ms): sleep/31680 read(fd: 3, buf: 0x7ffc5269e358, count: 832) = 832
     0.141 ( 0.002 ms): sleep/31680 fstat(fd: 3, statbuf: 0x7ffc5269e1f0) = 0
     0.146 ( 0.005 ms): sleep/31680 mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS) = 0x7f709c237000
     0.159 ( 0.007 ms): sleep/31680 mmap(len: 3889792, prot: EXEC|READ, flags: PRIVATE|DENYWRITE, fd: 3) = 0x7f709bc79000
     0.168 ( 0.009 ms): sleep/31680 mprotect(start: 0x7f709be26000, len: 2093056) = 0
     0.179 ( 0.010 ms): sleep/31680 mmap(addr: 0x7f709c025000, len: 24576, prot: READ|WRITE, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 1753088) = 0x7f709c025000
     0.196 ( 0.005 ms): sleep/31680 mmap(addr: 0x7f709c02b000, len: 14976, prot: READ|WRITE, flags: PRIVATE|FIXED|ANONYMOUS) = 0x7f709c02b000
     0.210 ( 0.002 ms): sleep/31680 close(fd: 3) = 0
     0.230 ( 0.002 ms): sleep/31680 arch_prctl(option: 4098, arg2: 140121632638208) = 0
     0.306 ( 0.009 ms): sleep/31680 mprotect(start: 0x7f709c025000, len: 16384, prot: READ) = 0
     0.338 ( 0.005 ms): sleep/31680 mprotect(start: 0x556529607000, len: 4096, prot: READ) = 0
     0.348 ( 0.005 ms): sleep/31680 mprotect(start: 0x7f709c253000, len: 4096, prot: READ) = 0
     0.356 ( 0.019 ms): sleep/31680 munmap(addr: 0x7f709c239000, len: 103334) = 0
     0.463 ( 0.002 ms): sleep/31680 brk() = 0x55652a851000
     0.468 ( 0.004 ms): sleep/31680 brk(brk: 0x55652a872000) = 0x55652a872000
     0.474 ( 0.002 ms): sleep/31680 brk() = 0x55652a872000
     0.484 ( 0.008 ms): sleep/31680 open(filename: , flags: CLOEXEC) = 3
     0.497 ( 0.002 ms): sleep/31680 fstat(fd: 3, statbuf: 0x7f709c02aaa0) = 0
     0.501 ( 0.006 ms): sleep/31680 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7f70950aa000
     0.514 ( 0.002 ms): sleep/31680 close(fd: 3) = 0
     0.554 (1000.140 ms): sleep/31680 nanosleep(rqtp: 0x7ffc5269eed0) = 0
  1000.734 ( 0.007 ms): sleep/31680 close(fd: 1) = 0
  1000.748 ( 0.004 ms): sleep/31680 close(fd: 2) = 0
  1000.769 (         ): sleep/31680 exit_group()
  #

Now to allow selecting which syscalls should be traced, using a map.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-votqqmqhag8e1i9mgyzfez3o@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index dc8a6c4986ce..f582ca575883 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3501,7 +3501,8 @@ int cmd_trace(int argc, const char **argv)
 		evsel->handler = trace__sys_enter;
 
 		evlist__for_each_entry(trace.evlist, evsel) {
-			if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) {
+			if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_") ||
+			    strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0) {
 				perf_evsel__init_augmented_syscall_tp(evsel);
 				perf_evsel__init_augmented_syscall_tp_ret(evsel);
 				evsel->handler = trace__sys_exit;
-- 
cgit v1.2.3


From cd26ea6d50a207ee37e0364ecc2d196d6c9671e8 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Sat, 3 Nov 2018 08:19:56 -0300
Subject: perf trace: Fix setting of augmented payload when using eBPF +
 raw_syscalls

For now with BPF raw_augmented we hook into raw_syscalls:sys_enter and
there we get all 6 syscall args plus the tracepoint common fields
(sizeof(long)) and the syscall_nr (another long). So we check if that is
the case and if so don't look after the sc->args_size, but always after
the full raw_syscalls:sys_enter payload, which is fixed.

We'll revisit this later to pass s->args_size to the BPF augmenter (now
tools/perf/examples/bpf/augmented_raw_syscalls.c, so that it copies only
what we need for each syscall, like what happens when we use
syscalls:sys_enter_NAME, so that we reduce the kernel/userspace traffic
to just what is needed for each syscall.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-nlslrg8apxdsobt4pwl3n7ur@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 37 ++++++++++++++++++++++++++++++-------
 1 file changed, 30 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index f582ca575883..835619476370 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -108,6 +108,7 @@ struct trace {
 	} stats;
 	unsigned int		max_stack;
 	unsigned int		min_stack;
+	bool			raw_augmented_syscalls;
 	bool			not_ev_qualifier;
 	bool			live;
 	bool			full_time;
@@ -1724,13 +1725,28 @@ static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel,
 	return printed;
 }
 
-static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size)
+static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size, bool raw_augmented)
 {
 	void *augmented_args = NULL;
+	/*
+	 * For now with BPF raw_augmented we hook into raw_syscalls:sys_enter
+	 * and there we get all 6 syscall args plus the tracepoint common
+	 * fields (sizeof(long)) and the syscall_nr (another long). So we check
+	 * if that is the case and if so don't look after the sc->args_size,
+	 * but always after the full raw_syscalls:sys_enter payload, which is
+	 * fixed.
+	 *
+	 * We'll revisit this later to pass s->args_size to the BPF augmenter
+	 * (now tools/perf/examples/bpf/augmented_raw_syscalls.c, so that it
+	 * copies only what we need for each syscall, like what happens when we
+	 * use syscalls:sys_enter_NAME, so that we reduce the kernel/userspace
+	 * traffic to just what is needed for each syscall.
+	 */
+	int args_size = raw_augmented ? (8 * (int)sizeof(long)) : sc->args_size;
 
-	*augmented_args_size = sample->raw_size - sc->args_size;
+	*augmented_args_size = sample->raw_size - args_size;
 	if (*augmented_args_size > 0)
-		augmented_args = sample->raw_data + sc->args_size;
+		augmented_args = sample->raw_data + args_size;
 
 	return augmented_args;
 }
@@ -1780,7 +1796,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	 * here and avoid using augmented syscalls when the evsel is the raw_syscalls one.
 	 */
 	if (evsel != trace->syscalls.events.sys_enter)
-		augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
+		augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls);
 	ttrace->entry_time = sample->time;
 	msg = ttrace->entry_str;
 	printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name);
@@ -1833,7 +1849,7 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
 		goto out_put;
 
 	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
-	augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
+	augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls);
 	syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
 	fprintf(trace->output, "%s", msg);
 	err = 0;
@@ -3501,8 +3517,15 @@ int cmd_trace(int argc, const char **argv)
 		evsel->handler = trace__sys_enter;
 
 		evlist__for_each_entry(trace.evlist, evsel) {
-			if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_") ||
-			    strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0) {
+			bool raw_syscalls_sys_exit = strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0;
+
+			if (raw_syscalls_sys_exit) {
+				trace.raw_augmented_syscalls = true;
+				goto init_augmented_syscall_tp;
+			}
+
+			if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) {
+init_augmented_syscall_tp:
 				perf_evsel__init_augmented_syscall_tp(evsel);
 				perf_evsel__init_augmented_syscall_tp_ret(evsel);
 				evsel->handler = trace__sys_exit;
-- 
cgit v1.2.3


From 79ef68c7e1f665578e005b454480b6eca60edabe Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 5 Nov 2018 12:23:40 -0300
Subject: perf augmented_syscalls: Start collecting pathnames in the BPF
 program

This is the start of having the raw_syscalls:sys_enter BPF handler
collecting pointer arguments, namely pathnames, and with two syscalls
that have that pointer in different arguments, "open" as it as its first
argument, "openat" as the second.

With this in place the existing beautifiers in 'perf trace' works, those
args are shown instead of just the pointer that comes with the syscalls
tracepoints.

This also serves to show and document pitfalls in the process of using
just that place in the kernel (raw_syscalls:sys_enter) plus tables
provided by userspace to collect syscall pointer arguments.

One is the need to use a barrier, as suggested by Edward, to avoid clang
optimizations that make the kernel BPF verifier to refuse loading our
pointer contents collector.

The end result should be a generic eBPF program that works in all
architectures, with the differences amongst archs resolved by the
userspace component, 'perf trace', that should get all its tables
created automatically from the kernel components where they are defined,
via string table constructors for things not expressed in BTF/DWARF
(enums, structs, etc), and otherwise using those observability files
(BTF).

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: Edward Cree <ecree@solarflare.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Yonghong Song <yhs@fb.com>
Link: https://lkml.kernel.org/n/tip-37dz54pmotgpnwg9tb6zuk9j@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/examples/bpf/augmented_raw_syscalls.c | 72 ++++++++++++++++++++++++
 1 file changed, 72 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index cde91c34b101..90a19336310b 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -37,15 +37,87 @@ struct syscall_exit_args {
 	long		   ret;
 };
 
+struct augmented_filename {
+	unsigned int	size;
+	int		reserved;
+	char		value[256];
+};
+
+#define SYS_OPEN 2
+#define SYS_OPENAT 257
+
 SEC("raw_syscalls:sys_enter")
 int sys_enter(struct syscall_enter_args *args)
 {
 	struct {
 		struct syscall_enter_args args;
+		struct augmented_filename filename;
 	} augmented_args;
 	unsigned int len = sizeof(augmented_args);
+	const void *filename_arg = NULL;
 
 	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
+	/*
+	 * Yonghong and Edward Cree sayz:
+	 *
+	 * https://www.spinics.net/lists/netdev/msg531645.html
+	 *
+	 * >>   R0=inv(id=0) R1=inv2 R6=ctx(id=0,off=0,imm=0) R7=inv64 R10=fp0,call_-1
+	 * >> 10: (bf) r1 = r6
+	 * >> 11: (07) r1 += 16
+	 * >> 12: (05) goto pc+2
+	 * >> 15: (79) r3 = *(u64 *)(r1 +0)
+	 * >> dereference of modified ctx ptr R1 off=16 disallowed
+	 * > Aha, we at least got a different error message this time.
+	 * > And indeed llvm has done that optimisation, rather than the more obvious
+	 * > 11: r3 = *(u64 *)(r1 +16)
+	 * > because it wants to have lots of reads share a single insn.  You may be able
+	 * > to defeat that optimisation by adding compiler barriers, idk.  Maybe someone
+	 * > with llvm knowledge can figure out how to stop it (ideally, llvm would know
+	 * > when it's generating for bpf backend and not do that).  -O0?  ¯\_(ツ)_/¯
+	 *
+	 * The optimization mostly likes below:
+	 *
+	 *	br1:
+	 * 	...
+	 *	r1 += 16
+	 *	goto merge
+	 *	br2:
+	 *	...
+	 *	r1 += 20
+	 *	goto merge
+	 *	merge:
+	 *	*(u64 *)(r1 + 0)
+	 *
+	 * The compiler tries to merge common loads. There is no easy way to
+	 * stop this compiler optimization without turning off a lot of other
+	 * optimizations. The easiest way is to add barriers:
+	 *
+	 * 	 __asm__ __volatile__("": : :"memory")
+	 *
+	 * 	 after the ctx memory access to prevent their down stream merging.
+	 */
+	switch (augmented_args.args.syscall_nr) {
+	case SYS_OPEN:	 filename_arg = (const void *)args->args[0];
+			__asm__ __volatile__("": : :"memory");
+			 break;
+	case SYS_OPENAT: filename_arg = (const void *)args->args[1];
+			 break;
+	}
+
+	if (filename_arg != NULL) {
+		augmented_args.filename.reserved = 0;
+		augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
+							      sizeof(augmented_args.filename.value),
+							      filename_arg);
+		if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) {
+			len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size;
+			len &= sizeof(augmented_args.filename.value) - 1;
+		}
+	} else {
+		len = sizeof(augmented_args.args);
+	}
+
 	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len);
 	return 0;
 }
-- 
cgit v1.2.3


From c3537fc251503af18085b8f84126d13743663970 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Mon, 1 Oct 2018 12:59:26 -0700
Subject: perf evlist: Move perf_evsel__reset_weak_group into evlist

- Move the function from builtin-stat to evlist for reuse
- Rename to evlist to match purpose better
- Pass the evlist as first argument.
- No functional changes

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20181001195927.14211-1-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 28 +---------------------------
 tools/perf/util/evlist.c  | 27 +++++++++++++++++++++++++++
 tools/perf/util/evlist.h  |  3 +++
 3 files changed, 31 insertions(+), 27 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index d1028d7755bb..a635abfa77b6 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -383,32 +383,6 @@ static bool perf_evsel__should_store_id(struct perf_evsel *counter)
 	return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID;
 }
 
-static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
-{
-	struct perf_evsel *c2, *leader;
-	bool is_open = true;
-
-	leader = evsel->leader;
-	pr_debug("Weak group for %s/%d failed\n",
-			leader->name, leader->nr_members);
-
-	/*
-	 * for_each_group_member doesn't work here because it doesn't
-	 * include the first entry.
-	 */
-	evlist__for_each_entry(evsel_list, c2) {
-		if (c2 == evsel)
-			is_open = false;
-		if (c2->leader == leader) {
-			if (is_open)
-				perf_evsel__close(c2);
-			c2->leader = c2;
-			c2->nr_members = 0;
-		}
-	}
-	return leader;
-}
-
 static bool is_target_alive(struct target *_target,
 			    struct thread_map *threads)
 {
@@ -477,7 +451,7 @@ try_again:
 			if ((errno == EINVAL || errno == EBADF) &&
 			    counter->leader != counter &&
 			    counter->weak_group) {
-				counter = perf_evsel__reset_weak_group(counter);
+				counter = perf_evlist__reset_weak_group(evsel_list, counter);
 				goto try_again;
 			}
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e88e6f9b1463..668d2a9ef0f4 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1810,3 +1810,30 @@ void perf_evlist__force_leader(struct perf_evlist *evlist)
 		leader->forced_leader = true;
 	}
 }
+
+struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evsel_list,
+						 struct perf_evsel *evsel)
+{
+	struct perf_evsel *c2, *leader;
+	bool is_open = true;
+
+	leader = evsel->leader;
+	pr_debug("Weak group for %s/%d failed\n",
+			leader->name, leader->nr_members);
+
+	/*
+	 * for_each_group_member doesn't work here because it doesn't
+	 * include the first entry.
+	 */
+	evlist__for_each_entry(evsel_list, c2) {
+		if (c2 == evsel)
+			is_open = false;
+		if (c2->leader == leader) {
+			if (is_open)
+				perf_evsel__close(c2);
+			c2->leader = c2;
+			c2->nr_members = 0;
+		}
+	}
+	return leader;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index dc66436add98..9919eed6d15b 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -312,4 +312,7 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist);
 
 void perf_evlist__force_leader(struct perf_evlist *evlist);
 
+struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evlist,
+						 struct perf_evsel *evsel);
+
 #endif /* __PERF_EVLIST_H */
-- 
cgit v1.2.3


From cf99ad1424c54fc84b84d3a3deb57a48c340c30a Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Mon, 1 Oct 2018 12:59:27 -0700
Subject: perf record: Support weak groups

Implement a weak group fallback for 'perf record', similar to the
existing 'perf stat' support.  This allows to use groups that might be
longer than the available counters without failing.

Before:

  $ perf record  -e '{cycles,cache-misses,cache-references,cpu_clk_unhalted.thread,cycles,cycles,cycles}' -a sleep 1
  Error:
  The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (cycles).
  /bin/dmesg | grep -i perf may provide additional information.

After:

  $ ./perf record  -e '{cycles,cache-misses,cache-references,cpu_clk_unhalted.thread,cycles,cycles,cycles}:W' -a sleep 1
  WARNING: No sample_id_all support, falling back to unordered processing
  [ perf record: Woken up 3 times to write data ]
  [ perf record: Captured and wrote 8.136 MB perf.data (134069 samples) ]

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20181001195927.14211-2-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-list.txt | 1 -
 tools/perf/builtin-record.c            | 7 ++++++-
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 236b9b97dfdb..667c14e56031 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -55,7 +55,6 @@ counted. The following modifiers exist:
  S - read sample value (PERF_SAMPLE_READ)
  D - pin the event to the PMU
  W - group is weak and will fallback to non-group if not schedulable,
-     only supported in 'perf stat' for now.
 
 The 'p' modifier can be used for specifying how precise the instruction
 address should be. The 'p' modifier can be specified multiple times:
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 10cf889c6d75..488779bc4c8d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -391,7 +391,12 @@ try_again:
 					ui__warning("%s\n", msg);
 				goto try_again;
 			}
-
+			if ((errno == EINVAL || errno == EBADF) &&
+			    pos->leader != pos &&
+			    pos->weak_group) {
+			        pos = perf_evlist__reset_weak_group(evlist, pos);
+				goto try_again;
+			}
 			rc = -errno;
 			perf_evsel__open_strerror(pos, &opts->target,
 						  errno, msg, sizeof(msg));
-- 
cgit v1.2.3


From ea1fa48c055f833eb25f0c33188feecb7002ada5 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 23 Oct 2018 17:16:16 +0200
Subject: perf stat: Handle different PMU names with common prefix

On s390 the CPU Measurement Facility for counters now supports
2 PMUs named cpum_cf (CPU Measurement Facility for counters) and
cpum_cf_diag (CPU Measurement Facility for diagnostic counters)
for one and the same CPU.

Running command

 [root@s35lp76 perf]# ./perf stat -e tx_c_tend \
	 -- ~/mytests/cf-tx-events 1

 Measuring transactions
 TX_C_TABORT_NO_SPECIAL: 0 expected:0
 TX_C_TABORT_SPECIAL: 0 expected:0
 TX_C_TEND: 1 expected:1
 TX_NC_TABORT: 11 expected:11
 TX_NC_TEND: 1 expected:1

 Performance counter stats for '/root/mytests/cf-tx-events 1':

  2      tx_c_tend

      0.002120091 seconds time elapsed

      0.000121000 seconds user
      0.002127000 seconds sys

 [root@s35lp76 perf]#

displays output which is unexpected (and wrong):

  2      tx_c_tend

The test program definitely triggers only one transaction, as shown
in line 'TX_C_TEND: 1 expected:1'.

This is caused by the following call sequence:

pmu_lookup() scans and installs a PMU.
+--> pmu_aliases() parses all aliases in directory
		.../<pmu-name>/events/* which are file names.
     +--> pmu_aliases_parse() Read each file in directory and create
                      an new alias entry. This is done with
          +--> perf_pmu__new_alias() and
	       +--> __perf_pmu__new_alias() which also check for
	                   identical alias names.

After pmu_aliases() returns, a complete list of event names
for this pmu has been created. Now function

pmu_add_cpu_aliases()   is called to add the events listed in the json
|                       files to the alias list of the cpu.
+--> perf_pmu__find_map()  Returns a pointer to the json events.

Now function pmu_add_cpu_aliases() scans through all events listed
in the JSON files for this CPU.
Each json event pmu name is compared with the current PMU being
built up and if they mismatch, the json event is added to the
current PMUs alias list.
To avoid duplicate entries the following comparison is done:

	if (!is_arm_pmu_core(name)) {
	     pname = pe->pmu ? pe->pmu : "cpu";
	     if (strncmp(pname, name, strlen(pname)))
		     continue;
     }

The culprit is the strncmp() function.

Using current s390 PMU naming, the first PMU is 'cpum_cf'
and a long list of events is added, among them 'tx_c_tend'

When the second PMU named 'cpum_cf_diag' is added, only one event
named 'CF_DIAG' is added by the pmu_aliases()  function.

Now function pmu_add_cpu_aliases() is invoked for PMU 'cpum_cf_diag'.
Since the CPUID string is the same for both PMUs, json file events
for PMU named 'cpum_cf' are added to the PMU 'cpm_cf_diag'

This happens because the strncmp() actually compares:

     strncmp("cpum_cf", "cpum_cf_diag", 6);

The first parameter is the pmu name taken from the event in
the json file. The second parameter is the pmu name of the PMU
currently being built.
They are different, but the length of the compare only tests the
common prefix and this returns 0(true) when it should return false.

Now all events for PMU cpum_cf are added to the alias list for pmu
cpum_cf_diag.

Later on in function parse_events_add_pmu() the event 'tx_c_end' is
searched in all available PMUs and found twice, adding it two
times to the evsel_list global variable which is the root
of all events. This results in a counter value of 2 instead
of 1.

Output with this patch:

 [root@s35lp76 perf]# ./perf stat -e tx_c_tend \
			-- ~/mytests/cf-tx-events 1
 Measuring transactions
 TX_C_TABORT_NO_SPECIAL: 0 expected:0
 TX_C_TABORT_SPECIAL: 0 expected:0
 TX_C_TEND: 1 expected:1
 TX_NC_TABORT: 11 expected:11
 TX_NC_TEND: 1 expected:1

 Performance counter stats for '/root/mytests/cf-tx-events 1':

                  1      tx_c_tend

      0.001815365 seconds time elapsed

      0.000123000 seconds user
      0.001756000 seconds sys

 [root@s35lp76 perf]#

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Reviewed-by: Sebastien Boisvert <sboisvert@gydle.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: stable@vger.kernel.org
Fixes: 292c34c10249 ("perf pmu: Fix core PMU alias list for X86 platform")
Link: http://lkml.kernel.org/r/20181023151616.78193-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/pmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 7799788f662f..7e49baad304d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -773,7 +773,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 
 		if (!is_arm_pmu_core(name)) {
 			pname = pe->pmu ? pe->pmu : "cpu";
-			if (strncmp(pname, name, strlen(pname)))
+			if (strcmp(pname, name))
 				continue;
 		}
 
-- 
cgit v1.2.3


From 590ac60d8aa929bd21e35cd95a7d8720d00eb4f3 Mon Sep 17 00:00:00 2001
From: Jin Yao <yao.jin@linux.intel.com>
Date: Wed, 31 Oct 2018 19:06:35 +0800
Subject: perf top: Display the LBR stats in callchain entry

'perf report' has supported the displaying of LBR stats (such as cycles,
predicted%) in callchain entry.

For example:

  $ perf report --branch-history --stdio

  --1.01%--intel_idle mwait.h:29
            intel_idle cpufeature.h:164 (cycles:5)
            intel_idle cpufeature.h:164 (predicted:76.4%)
            intel_idle mwait.h:102 (cycles:41)
            intel_idle current.h:15

While 'perf top' doesn't support that.

For example:

  $ perf top -a -b --call-graph branch

  -   13.86%     0.23%  [kernel]		[k] __x86_indirect_thunk_rax
     - 13.65% __x86_indirect_thunk_rax
        + 1.69% do_syscall_64
        + 1.68% do_select
        + 1.41% ktime_get
        + 0.70% __schedule
        + 0.62% do_sys_poll
          0.58% __x86_indirect_thunk_rax

Actually it's very easy to enable this feature in 'perf top'.

With this patch, the result is:

  $ perf top -a -b --call-graph branch

  $ -   13.58%     0.00%  [kernel]		[k] __x86_indirect_thunk_rax
     $ - 13.57% __x86_indirect_thunk_rax (predicted:93.9%)
        $ + 1.78% do_select (cycles:2)
        $ + 1.68% perf_pmu_disable.part.99 (cycles:1)
        $ + 1.45% ___sys_recvmsg (cycles:25)
        $ + 0.81% unix_stream_sendmsg (cycles:18)
        $ + 0.80% ktime_get (cycles:400)
          $ 0.58% pick_next_task_fair (cycles:47)
        $ + 0.56% i915_request_retire (cycles:2)
        $ + 0.52% do_sys_poll (cycles:4)

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1540983995-20462-1-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-top.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index b2838de13de0..aa0c73e57924 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1429,6 +1429,9 @@ int cmd_top(int argc, const char **argv)
 		}
 	}
 
+	if (opts->branch_stack && callchain_param.enabled)
+		symbol_conf.show_branchflag_count = true;
+
 	sort__mode = SORT_MODE__TOP;
 	/* display thread wants entries to be collapsed in a different tree */
 	perf_hpp_list.need_collapse = 1;
-- 
cgit v1.2.3


From 5ed4419d47f8ba6bbccd8e3203276b3c39a792b7 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Sun, 4 Nov 2018 17:12:35 +0200
Subject: perf scripts python: exported-sql-viewer.py: Fall back to
 /usr/local/lib/libxed.so

Fall back to /usr/local/lib/libxed.so to cater for distributions that do
not have /usr/local/lib in the library path by default.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181104151238.15947-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 24cb0bd56afa..20cc8e7879b9 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -1929,7 +1929,12 @@ class XEDInstruction():
 class LibXED():
 
 	def __init__(self):
-		self.libxed = CDLL("libxed.so")
+		try:
+			self.libxed = CDLL("libxed.so")
+		except:
+			self.libxed = None
+		if not self.libxed:
+			self.libxed = CDLL("/usr/local/lib/libxed.so")
 
 		self.xed_tables_init = self.libxed.xed_tables_init
 		self.xed_tables_init.restype = None
-- 
cgit v1.2.3


From 210cf1f96185f0c6383df8b6030e3d2945e1b41a Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Sun, 4 Nov 2018 17:12:36 +0200
Subject: perf scripts python: exported-sql-viewer.py: Add Selected branches
 report

Fetching data from the database can be slow. Add a report that provides
the ability to select a subset of branches.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181104151238.15947-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 327 +++++++++++++++++++++++
 1 file changed, 327 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 20cc8e7879b9..a9d2b3170141 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -119,6 +119,14 @@ def dsoname(name):
 		return "[kernel]"
 	return name
 
+def findnth(s, sub, n, offs=0):
+	pos = s.find(sub)
+	if pos < 0:
+		return pos
+	if n <= 1:
+		return offs + pos
+	return findnth(s[pos + 1:], sub, n - 1, offs + pos + 1)
+
 # Percent to one decimal place
 
 def PercentToOneDP(n, d):
@@ -1464,6 +1472,317 @@ class BranchWindow(QMdiSubWindow):
 		else:
 			self.find_bar.NotFound()
 
+# Dialog data item converted and validated using a SQL table
+
+class SQLTableDialogDataItem():
+
+	def __init__(self, glb, label, placeholder_text, table_name, match_column, column_name1, column_name2, parent):
+		self.glb = glb
+		self.label = label
+		self.placeholder_text = placeholder_text
+		self.table_name = table_name
+		self.match_column = match_column
+		self.column_name1 = column_name1
+		self.column_name2 = column_name2
+		self.parent = parent
+
+		self.value = ""
+
+		self.widget = QLineEdit()
+		self.widget.editingFinished.connect(self.Validate)
+		self.widget.textChanged.connect(self.Invalidate)
+		self.red = False
+		self.error = ""
+		self.validated = True
+
+		self.last_id = 0
+		self.first_time = 0
+		self.last_time = 2 ** 64
+		if self.table_name == "<timeranges>":
+			query = QSqlQuery(self.glb.db)
+			QueryExec(query, "SELECT id, time FROM samples ORDER BY id DESC LIMIT 1")
+			if query.next():
+				self.last_id = int(query.value(0))
+				self.last_time = int(query.value(1))
+			QueryExec(query, "SELECT time FROM samples WHERE time != 0 ORDER BY id LIMIT 1")
+			if query.next():
+				self.first_time = int(query.value(0))
+			if placeholder_text:
+				placeholder_text += ", between " + str(self.first_time) + " and " + str(self.last_time)
+
+		if placeholder_text:
+			self.widget.setPlaceholderText(placeholder_text)
+
+	def ValueToIds(self, value):
+		ids = []
+		query = QSqlQuery(self.glb.db)
+		stmt = "SELECT id FROM " + self.table_name + " WHERE " + self.match_column + " = '" + value + "'"
+		ret = query.exec_(stmt)
+		if ret:
+			while query.next():
+				ids.append(str(query.value(0)))
+		return ids
+
+	def IdBetween(self, query, lower_id, higher_id, order):
+		QueryExec(query, "SELECT id FROM samples WHERE id > " + str(lower_id) + " AND id < " + str(higher_id) + " ORDER BY id " + order + " LIMIT 1")
+		if query.next():
+			return True, int(query.value(0))
+		else:
+			return False, 0
+
+	def BinarySearchTime(self, lower_id, higher_id, target_time, get_floor):
+		query = QSqlQuery(self.glb.db)
+		while True:
+			next_id = int((lower_id + higher_id) / 2)
+			QueryExec(query, "SELECT time FROM samples WHERE id = " + str(next_id))
+			if not query.next():
+				ok, dbid = self.IdBetween(query, lower_id, next_id, "DESC")
+				if not ok:
+					ok, dbid = self.IdBetween(query, next_id, higher_id, "")
+					if not ok:
+						return str(higher_id)
+				next_id = dbid
+				QueryExec(query, "SELECT time FROM samples WHERE id = " + str(next_id))
+			next_time = int(query.value(0))
+			if get_floor:
+				if target_time > next_time:
+					lower_id = next_id
+				else:
+					higher_id = next_id
+				if higher_id <= lower_id + 1:
+					return str(higher_id)
+			else:
+				if target_time >= next_time:
+					lower_id = next_id
+				else:
+					higher_id = next_id
+				if higher_id <= lower_id + 1:
+					return str(lower_id)
+
+	def ConvertRelativeTime(self, val):
+		print "val ", val
+		mult = 1
+		suffix = val[-2:]
+		if suffix == "ms":
+			mult = 1000000
+		elif suffix == "us":
+			mult = 1000
+		elif suffix == "ns":
+			mult = 1
+		else:
+			return val
+		val = val[:-2].strip()
+		if not self.IsNumber(val):
+			return val
+		val = int(val) * mult
+		if val >= 0:
+			val += self.first_time
+		else:
+			val += self.last_time
+		return str(val)
+
+	def ConvertTimeRange(self, vrange):
+		print "vrange ", vrange
+		if vrange[0] == "":
+			vrange[0] = str(self.first_time)
+		if vrange[1] == "":
+			vrange[1] = str(self.last_time)
+		vrange[0] = self.ConvertRelativeTime(vrange[0])
+		vrange[1] = self.ConvertRelativeTime(vrange[1])
+		print "vrange2 ", vrange
+		if not self.IsNumber(vrange[0]) or not self.IsNumber(vrange[1]):
+			return False
+		print "ok1"
+		beg_range = max(int(vrange[0]), self.first_time)
+		end_range = min(int(vrange[1]), self.last_time)
+		if beg_range > self.last_time or end_range < self.first_time:
+			return False
+		print "ok2"
+		vrange[0] = self.BinarySearchTime(0, self.last_id, beg_range, True)
+		vrange[1] = self.BinarySearchTime(1, self.last_id + 1, end_range, False)
+		print "vrange3 ", vrange
+		return True
+
+	def AddTimeRange(self, value, ranges):
+		print "value ", value
+		n = value.count("-")
+		if n == 1:
+			pass
+		elif n == 2:
+			if value.split("-")[1].strip() == "":
+				n = 1
+		elif n == 3:
+			n = 2
+		else:
+			return False
+		pos = findnth(value, "-", n)
+		vrange = [value[:pos].strip() ,value[pos+1:].strip()]
+		if self.ConvertTimeRange(vrange):
+			ranges.append(vrange)
+			return True
+		return False
+
+	def InvalidValue(self, value):
+		self.value = ""
+		palette = QPalette()
+		palette.setColor(QPalette.Text,Qt.red)
+		self.widget.setPalette(palette)
+		self.red = True
+		self.error = self.label + " invalid value '" + value + "'"
+		self.parent.ShowMessage(self.error)
+
+	def IsNumber(self, value):
+		try:
+			x = int(value)
+		except:
+			x = 0
+		return str(x) == value
+
+	def Invalidate(self):
+		self.validated = False
+
+	def Validate(self):
+		input_string = self.widget.text()
+		self.validated = True
+		if self.red:
+			palette = QPalette()
+			self.widget.setPalette(palette)
+			self.red = False
+		if not len(input_string.strip()):
+			self.error = ""
+			self.value = ""
+			return
+		if self.table_name == "<timeranges>":
+			ranges = []
+			for value in [x.strip() for x in input_string.split(",")]:
+				if not self.AddTimeRange(value, ranges):
+					return self.InvalidValue(value)
+			ranges = [("(" + self.column_name1 + " >= " + r[0] + " AND " + self.column_name1 + " <= " + r[1] + ")") for r in ranges]
+			self.value = " OR ".join(ranges)
+		elif self.table_name == "<ranges>":
+			singles = []
+			ranges = []
+			for value in [x.strip() for x in input_string.split(",")]:
+				if "-" in value:
+					vrange = value.split("-")
+					if len(vrange) != 2 or not self.IsNumber(vrange[0]) or not self.IsNumber(vrange[1]):
+						return self.InvalidValue(value)
+					ranges.append(vrange)
+				else:
+					if not self.IsNumber(value):
+						return self.InvalidValue(value)
+					singles.append(value)
+			ranges = [("(" + self.column_name1 + " >= " + r[0] + " AND " + self.column_name1 + " <= " + r[1] + ")") for r in ranges]
+			if len(singles):
+				ranges.append(self.column_name1 + " IN (" + ",".join(singles) + ")")
+			self.value = " OR ".join(ranges)
+		elif self.table_name:
+			all_ids = []
+			for value in [x.strip() for x in input_string.split(",")]:
+				ids = self.ValueToIds(value)
+				if len(ids):
+					all_ids.extend(ids)
+				else:
+					return self.InvalidValue(value)
+			self.value = self.column_name1 + " IN (" + ",".join(all_ids) + ")"
+			if self.column_name2:
+				self.value = "( " + self.value + " OR " + self.column_name2 + " IN (" + ",".join(all_ids) + ") )"
+		else:
+			self.value = input_string.strip()
+		self.error = ""
+		self.parent.ClearMessage()
+
+	def IsValid(self):
+		if not self.validated:
+			self.Validate()
+		if len(self.error):
+			self.parent.ShowMessage(self.error)
+			return False
+		return True
+
+# Selected branch report creation dialog
+
+class SelectedBranchDialog(QDialog):
+
+	def __init__(self, glb, parent=None):
+		super(SelectedBranchDialog, self).__init__(parent)
+
+		self.glb = glb
+
+		self.name = ""
+		self.where_clause = ""
+
+		self.setWindowTitle("Selected Branches")
+		self.setMinimumWidth(600)
+
+		items = (
+			("Report name:", "Enter a name to appear in the window title bar", "", "", "", ""),
+			("Time ranges:", "Enter time ranges", "<timeranges>", "", "samples.id", ""),
+			("CPUs:", "Enter CPUs or ranges e.g. 0,5-6", "<ranges>", "", "cpu", ""),
+			("Commands:", "Only branches with these commands will be included", "comms", "comm", "comm_id", ""),
+			("PIDs:", "Only branches with these process IDs will be included", "threads", "pid", "thread_id", ""),
+			("TIDs:", "Only branches with these thread IDs will be included", "threads", "tid", "thread_id", ""),
+			("DSOs:", "Only branches with these DSOs will be included", "dsos", "short_name", "samples.dso_id", "to_dso_id"),
+			("Symbols:", "Only branches with these symbols will be included", "symbols", "name", "symbol_id", "to_symbol_id"),
+			("Raw SQL clause: ", "Enter a raw SQL WHERE clause", "", "", "", ""),
+			)
+		self.data_items = [SQLTableDialogDataItem(glb, *x, parent=self) for x in items]
+
+		self.grid = QGridLayout()
+
+		for row in xrange(len(self.data_items)):
+			self.grid.addWidget(QLabel(self.data_items[row].label), row, 0)
+			self.grid.addWidget(self.data_items[row].widget, row, 1)
+
+		self.status = QLabel()
+
+		self.ok_button = QPushButton("Ok", self)
+		self.ok_button.setDefault(True)
+		self.ok_button.released.connect(self.Ok)
+		self.ok_button.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.cancel_button = QPushButton("Cancel", self)
+		self.cancel_button.released.connect(self.reject)
+		self.cancel_button.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.hbox = QHBoxLayout()
+		#self.hbox.addStretch()
+		self.hbox.addWidget(self.status)
+		self.hbox.addWidget(self.ok_button)
+		self.hbox.addWidget(self.cancel_button)
+
+		self.vbox = QVBoxLayout()
+		self.vbox.addLayout(self.grid)
+		self.vbox.addLayout(self.hbox)
+
+		self.setLayout(self.vbox);
+
+	def Ok(self):
+		self.name = self.data_items[0].value
+		if not self.name:
+			self.ShowMessage("Report name is required")
+			return
+		for d in self.data_items:
+			if not d.IsValid():
+				return
+		for d in self.data_items[1:]:
+			if len(d.value):
+				if len(self.where_clause):
+					self.where_clause += " AND "
+				self.where_clause += d.value
+		if len(self.where_clause):
+			self.where_clause = " AND ( " + self.where_clause + " ) "
+		else:
+			self.ShowMessage("No selection")
+			return
+		self.accept()
+
+	def ShowMessage(self, msg):
+		self.status.setText("<font color=#FF0000>" + msg)
+
+	def ClearMessage(self):
+		self.status.setText("")
+
 # Event list
 
 def GetEventList(db):
@@ -1888,6 +2207,8 @@ class MainWindow(QMainWindow):
 			if event == "branches":
 				label = "All branches" if branches_events == 1 else "All branches " + "(id=" + dbid + ")"
 				reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewBranchView(x), self))
+				label = "Selected branches" if branches_events == 1 else "Selected branches " + "(id=" + dbid + ")"
+				reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewSelectedBranchView(x), self))
 
 	def TableMenu(self, tables, menu):
 		table_menu = menu.addMenu("&Tables")
@@ -1900,6 +2221,12 @@ class MainWindow(QMainWindow):
 	def NewBranchView(self, event_id):
 		BranchWindow(self.glb, event_id, "", "", self)
 
+	def NewSelectedBranchView(self, event_id):
+		dialog = SelectedBranchDialog(self.glb, self)
+		ret = dialog.exec_()
+		if ret:
+			BranchWindow(self.glb, event_id, dialog.name, dialog.where_clause, self)
+
 	def NewTableView(self, table_name):
 		TableWindow(self.glb, table_name, self)
 
-- 
cgit v1.2.3


From 65b24292e8f34df22a16bf7c47823325ac247572 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Sun, 4 Nov 2018 17:12:37 +0200
Subject: perf scripts python: exported-sql-viewer.py: Add help window

Add a window to display help. It is also possible to display the help
only, by using the option "--help-only" instead of a database name.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181104151238.15947-4-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 155 ++++++++++++++++++++++-
 1 file changed, 154 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index a9d2b3170141..c2fcf6c5237a 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -2084,6 +2084,147 @@ class WindowMenu():
 	def setActiveSubWindow(self, nr):
 		self.mdi_area.setActiveSubWindow(self.mdi_area.subWindowList()[nr - 1])
 
+# Help text
+
+glb_help_text = """
+<h1>Contents</h1>
+<style>
+p.c1 {
+    text-indent: 40px;
+}
+p.c2 {
+    text-indent: 80px;
+}
+}
+</style>
+<p class=c1><a href=#reports>1. Reports</a></p>
+<p class=c2><a href=#callgraph>1.1 Context-Sensitive Call Graph</a></p>
+<p class=c2><a href=#allbranches>1.2 All branches</a></p>
+<p class=c2><a href=#selectedbranches>1.3 Selected branches</a></p>
+<p class=c1><a href=#tables>2. Tables</a></p>
+<h1 id=reports>1. Reports</h1>
+<h2 id=callgraph>1.1 Context-Sensitive Call Graph</h2>
+The result is a GUI window with a tree representing a context-sensitive
+call-graph. Expanding a couple of levels of the tree and adjusting column
+widths to suit will display something like:
+<pre>
+                                         Call Graph: pt_example
+Call Path                          Object      Count   Time(ns)  Time(%)  Branch Count   Branch Count(%)
+v- ls
+    v- 2638:2638
+        v- _start                  ld-2.19.so    1     10074071   100.0         211135            100.0
+          |- unknown               unknown       1        13198     0.1              1              0.0
+          >- _dl_start             ld-2.19.so    1      1400980    13.9          19637              9.3
+          >- _d_linit_internal     ld-2.19.so    1       448152     4.4          11094              5.3
+          v-__libc_start_main@plt  ls            1      8211741    81.5         180397             85.4
+             >- _dl_fixup          ld-2.19.so    1         7607     0.1            108              0.1
+             >- __cxa_atexit       libc-2.19.so  1        11737     0.1             10              0.0
+             >- __libc_csu_init    ls            1        10354     0.1             10              0.0
+             |- _setjmp            libc-2.19.so  1            0     0.0              4              0.0
+             v- main               ls            1      8182043    99.6         180254             99.9
+</pre>
+<h3>Points to note:</h3>
+<ul>
+<li>The top level is a command name (comm)</li>
+<li>The next level is a thread (pid:tid)</li>
+<li>Subsequent levels are functions</li>
+<li>'Count' is the number of calls</li>
+<li>'Time' is the elapsed time until the function returns</li>
+<li>Percentages are relative to the level above</li>
+<li>'Branch Count' is the total number of branches for that function and all functions that it calls
+</ul>
+<h3>Find</h3>
+Ctrl-F displays a Find bar which finds function names by either an exact match or a pattern match.
+The pattern matching symbols are ? for any character and * for zero or more characters.
+<h2 id=allbranches>1.2 All branches</h2>
+The All branches report displays all branches in chronological order.
+Not all data is fetched immediately. More records can be fetched using the Fetch bar provided.
+<h3>Disassembly</h3>
+Open a branch to display disassembly. This only works if:
+<ol>
+<li>The disassembler is available. Currently, only Intel XED is supported - see <a href=#xed>Intel XED Setup</a></li>
+<li>The object code is available. Currently, only the perf build ID cache is searched for object code.
+The default directory ~/.debug can be overridden by setting environment variable PERF_BUILDID_DIR.
+One exception is kcore where the DSO long name is used (refer dsos_view on the Tables menu),
+or alternatively, set environment variable PERF_KCORE to the kcore file name.</li>
+</ol>
+<h4 id=xed>Intel XED Setup</h4>
+To use Intel XED, libxed.so must be present.  To build and install libxed.so:
+<pre>
+git clone https://github.com/intelxed/mbuild.git mbuild
+git clone https://github.com/intelxed/xed
+cd xed
+./mfile.py --share
+sudo ./mfile.py --prefix=/usr/local install
+sudo ldconfig
+</pre>
+<h3>Find</h3>
+Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match.
+Refer to Python documentation for the regular expression syntax.
+All columns are searched, but only currently fetched rows are searched.
+<h2 id=selectedbranches>1.3 Selected branches</h2>
+This is the same as the <a href=#allbranches>All branches</a> report but with the data reduced
+by various selection criteria. A dialog box displays available criteria which are AND'ed together.
+<h3>1.3.1 Time ranges</h3>
+The time ranges hint text shows the total time range. Relative time ranges can also be entered in
+ms, us or ns. Also, negative values are relative to the end of trace.  Examples:
+<pre>
+	81073085947329-81073085958238	From 81073085947329 to 81073085958238
+	100us-200us		From 100us to 200us
+	10ms-			From 10ms to the end
+	-100ns			The first 100ns
+	-10ms-			The last 10ms
+</pre>
+N.B. Due to the granularity of timestamps, there could be no branches in any given time range.
+<h1 id=tables>2. Tables</h1>
+The Tables menu shows all tables and views in the database. Most tables have an associated view
+which displays the information in a more friendly way. Not all data for large tables is fetched
+immediately. More records can be fetched using the Fetch bar provided. Columns can be sorted,
+but that can be slow for large tables.
+<p>There are also tables of database meta-information.
+For SQLite3 databases, the sqlite_master table is included.
+For PostgreSQL databases, information_schema.tables/views/columns are included.
+<h3>Find</h3>
+Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match.
+Refer to Python documentation for the regular expression syntax.
+All columns are searched, but only currently fetched rows are searched.
+"""
+
+# Help window
+
+class HelpWindow(QMdiSubWindow):
+
+	def __init__(self, glb, parent=None):
+		super(HelpWindow, self).__init__(parent)
+
+		self.text = QTextBrowser()
+		self.text.setHtml(glb_help_text)
+		self.text.setReadOnly(True)
+		self.text.setOpenExternalLinks(True)
+
+		self.setWidget(self.text)
+
+		AddSubWindow(glb.mainwindow.mdi_area, self, "Exported SQL Viewer Help")
+
+# Main window that only displays the help text
+
+class HelpOnlyWindow(QMainWindow):
+
+	def __init__(self, parent=None):
+		super(HelpOnlyWindow, self).__init__(parent)
+
+		self.setMinimumSize(200, 100)
+		self.resize(800, 600)
+		self.setWindowTitle("Exported SQL Viewer Help")
+		self.setWindowIcon(self.style().standardIcon(QStyle.SP_MessageBoxInformation))
+
+		self.text = QTextBrowser()
+		self.text.setHtml(glb_help_text)
+		self.text.setReadOnly(True)
+		self.text.setOpenExternalLinks(True)
+
+		self.setCentralWidget(self.text)
+
 # Font resize
 
 def ResizeFont(widget, diff):
@@ -2170,6 +2311,9 @@ class MainWindow(QMainWindow):
 
 		self.window_menu = WindowMenu(self.mdi_area, menu)
 
+		help_menu = menu.addMenu("&Help")
+		help_menu.addAction(CreateAction("&Exported SQL Viewer Help", "Helpful information", self.Help, self, QKeySequence.HelpContents))
+
 	def Find(self):
 		win = self.mdi_area.activeSubWindow()
 		if win:
@@ -2230,6 +2374,9 @@ class MainWindow(QMainWindow):
 	def NewTableView(self, table_name):
 		TableWindow(self.glb, table_name, self)
 
+	def Help(self):
+		HelpWindow(self.glb, self)
+
 # XED Disassembler
 
 class xed_state_t(Structure):
@@ -2429,10 +2576,16 @@ class DBRef():
 
 def Main():
 	if (len(sys.argv) < 2):
-		print >> sys.stderr, "Usage is: exported-sql-viewer.py <database name>"
+		print >> sys.stderr, "Usage is: exported-sql-viewer.py {<database name> | --help-only}"
 		raise Exception("Too few arguments")
 
 	dbname = sys.argv[1]
+	if dbname == "--help-only":
+		app = QApplication(sys.argv)
+		mainwindow = HelpOnlyWindow()
+		mainwindow.show()
+		err = app.exec_()
+		sys.exit(err)
 
 	is_sqlite3 = False
 	try:
-- 
cgit v1.2.3


From 35fa1cee21e34f43db928d022610707d5a234faf Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Sun, 4 Nov 2018 17:12:38 +0200
Subject: perf scripts python: exported-sql-viewer.py: Fix table find when
 table re-ordered

Table rows can be re-ordered by selecting a column to sort by. After
re-ordering, the "find" operation was highlighting the wrong row, fix
it.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181104151238.15947-5-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index c2fcf6c5237a..f278ce5ebab7 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -1975,7 +1975,7 @@ class TableWindow(QMdiSubWindow, ResizeColumnsToContentsBase):
 	def FindDone(self, row):
 		self.find_bar.Idle()
 		if row >= 0:
-			self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex()))
+			self.view.setCurrentIndex(self.model.mapFromSource(self.data_model.index(row, 0, QModelIndex())))
 		else:
 			self.find_bar.NotFound()
 
@@ -2188,6 +2188,8 @@ For PostgreSQL databases, information_schema.tables/views/columns are included.
 Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match.
 Refer to Python documentation for the regular expression syntax.
 All columns are searched, but only currently fetched rows are searched.
+<p>N.B. Results are found in id order, so if the table is re-ordered, find-next and find-previous
+will go to the next/previous result in id order, instead of display order.
 """
 
 # Help window
-- 
cgit v1.2.3


From 93f8be2799515e01647c5a9b0d17a90a00ebcf82 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 5 Nov 2018 09:35:04 +0200
Subject: perf intel-pt: Add more event information to debug log

More event information is useful for debugging, especially MMAP events.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Link: http://lkml.kernel.org/r/20181105073505.8129-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt-decoder/intel-pt-log.c |  5 +++++
 tools/perf/util/intel-pt-decoder/intel-pt-log.h |  1 +
 tools/perf/util/intel-pt.c                      | 16 +++++++++++++---
 3 files changed, 19 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.c b/tools/perf/util/intel-pt-decoder/intel-pt-log.c
index e02bc7b166a0..5e64da270f97 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-log.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.c
@@ -31,6 +31,11 @@ static FILE *f;
 static char log_name[MAX_LOG_NAME];
 bool intel_pt_enable_logging;
 
+void *intel_pt_log_fp(void)
+{
+	return f;
+}
+
 void intel_pt_log_enable(void)
 {
 	intel_pt_enable_logging = true;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h
index 45b64f93f358..cc084937f701 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-log.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h
@@ -22,6 +22,7 @@
 
 struct intel_pt_pkt;
 
+void *intel_pt_log_fp(void);
 void intel_pt_log_enable(void);
 void intel_pt_log_disable(void);
 void intel_pt_log_set_name(const char *name);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 86cc9a64e982..149ff361ca78 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -206,6 +206,16 @@ static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf,
 	intel_pt_dump(pt, buf, len);
 }
 
+static void intel_pt_log_event(union perf_event *event)
+{
+	FILE *f = intel_pt_log_fp();
+
+	if (!intel_pt_enable_logging || !f)
+		return;
+
+	perf_event__fprintf(event, f);
+}
+
 static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a,
 				   struct auxtrace_buffer *b)
 {
@@ -2010,9 +2020,9 @@ static int intel_pt_process_event(struct perf_session *session,
 		 event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)
 		err = intel_pt_context_switch(pt, event, sample);
 
-	intel_pt_log("event %s (%u): cpu %d time %"PRIu64" tsc %#"PRIx64"\n",
-		     perf_event__name(event->header.type), event->header.type,
-		     sample->cpu, sample->time, timestamp);
+	intel_pt_log("event %u: cpu %d time %"PRIu64" tsc %#"PRIx64" ",
+		     event->header.type, sample->cpu, sample->time, timestamp);
+	intel_pt_log_event(event);
 
 	return err;
 }
-- 
cgit v1.2.3


From f6c23e3b55cb93f32a724f41af8d38888bc2ab6b Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 5 Nov 2018 09:35:05 +0200
Subject: perf intel-pt: Add MTC and CYC timestamps to debug log

One cause of decoding errors is un-synchronized side-band data.
Timestamps are needed to debug such cases. TSC packet timestamps are
logged. Log also MTC and CYC timestamps.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Link: http://lkml.kernel.org/r/20181105073505.8129-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools')

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 58f6a9ceb590..4503f3ca45ab 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1474,6 +1474,8 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder)
 		decoder->have_calc_cyc_to_tsc = false;
 		intel_pt_calc_cyc_to_tsc(decoder, true);
 	}
+
+	intel_pt_log_to("Setting timestamp", decoder->timestamp);
 }
 
 static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder)
@@ -1514,6 +1516,8 @@ static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder)
 		decoder->timestamp = timestamp;
 
 	decoder->timestamp_insn_cnt = 0;
+
+	intel_pt_log_to("Setting timestamp", decoder->timestamp);
 }
 
 /* Walk PSB+ packets when already in sync. */
-- 
cgit v1.2.3


From e2c39f36c354a06c6e9d32d4fdf8660b41803d82 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 5 Nov 2018 15:46:51 -0300
Subject: perf beauty: Use SRCARCH, ARCH=x86_64 must map to "x86" to find the
 headers

Guenter reported that using ARCH=x86_64 to build perf has regressed:

  $ make -C tools/perf O=/tmp/build/perf ARCH=x86_64
  make: Entering directory '/home/acme/git/perf/tools/perf'
    BUILD:   Doing 'make -j4' parallel build
    HOSTCC   /tmp/build/perf/fixdep.o
    HOSTLD   /tmp/build/perf/fixdep-in.o
    LINK     /tmp/build/perf/fixdep

  Auto-detecting system features:
  ...                         dwarf: [ on  ]
  <SNIP>
  ...                           bpf: [ on  ]

    GEN      /tmp/build/perf/common-cmds.h
  make[2]: *** No rule to make target '/home/acme/git/perf/tools/arch/x86_64/include/uapi/asm//mman.h', needed by '/tmp/build/perf/trace/beauty/generated/mmap_flags_array.c'.  Stop.
  make[2]: *** Waiting for unfinished jobs....
    PERF_VERSION = 4.19.gf6c23e3
  make[1]: *** [Makefile.perf:207: sub-make] Error 2
  make: *** [Makefile:70: all] Error 2
  make: Leaving directory '/home/acme/git/perf/tools/perf'
  $

This is because we must use $(SRCARCH) where we were using $(ARCH), so
that, just like the top level Makefile, we get this done:

  # Additional ARCH settings for x86
  ifeq ($(ARCH),i386)
          SRCARCH := x86
  endif
  ifeq ($(ARCH),x86_64)
          SRCARCH := x86
  endif

Which is done in tools/scripts/Makefile.arch, so switch to use
$(SRCARCH).

Reported-by: Guenter Roeck <linux@roeck-us.net>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Clark Williams <williams@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: fbd7458db757 ("perf beauty: Wire up the mmap flags table generator to the Makefile")
Link: https://lkml.kernel.org/r/20181105184612.GD7077@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.perf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 3ccb4f0bf088..d95655489f7e 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -387,7 +387,7 @@ SHELL = $(SHELL_PATH)
 
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
 asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
-arch_asm_uapi_dir := $(srctree)/tools/arch/$(ARCH)/include/uapi/asm/
+arch_asm_uapi_dir := $(srctree)/tools/arch/$(SRCARCH)/include/uapi/asm/
 
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
-- 
cgit v1.2.3


From 6ac2226229d931153331a93d90655a3de05b9290 Mon Sep 17 00:00:00 2001
From: Gustavo Romero <gromero@linux.vnet.ibm.com>
Date: Thu, 1 Nov 2018 20:13:21 -0400
Subject: perf tools: Fix undefined symbol scnprintf in libperf-jvmti.so

Currently jvmti agent can not be used because function scnprintf is not
present in the agent libperf-jvmti.so. As a result the JVM when using
such agent to record JITed code profiling information will fail on
looking up scnprintf:

  java: symbol lookup error: lib/libperf-jvmti.so: undefined symbol: scnprintf

This commit fixes that by reverting to the use of snprintf, that can be
looked up, instead of scnprintf, adding a proper check for the returned
value in order to print a better error message when the jitdump file
pathname is too long. Checking the returned value also helps to comply
with some recent gcc versions, like gcc8, which will fail due to
truncated writing checks related to the -Werror=format-truncation= flag.

Signed-off-by: Gustavo Romero <gromero@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
LPU-Reference: 1541117601-18937-2-git-send-email-gromero@linux.vnet.ibm.com
Link: https://lkml.kernel.org/n/tip-mvpxxxy7wnzaj74cq75muw3f@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/jvmti/jvmti_agent.c | 49 ++++++++++++++++++++++++++++++++----------
 1 file changed, 38 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
index ac1bcdc17dae..f7eb63cbbc65 100644
--- a/tools/perf/jvmti/jvmti_agent.c
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -125,7 +125,7 @@ perf_get_timestamp(void)
 }
 
 static int
-debug_cache_init(void)
+create_jit_cache_dir(void)
 {
 	char str[32];
 	char *base, *p;
@@ -144,8 +144,13 @@ debug_cache_init(void)
 
 	strftime(str, sizeof(str), JIT_LANG"-jit-%Y%m%d", &tm);
 
-	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/", base);
-
+	ret = snprintf(jit_path, PATH_MAX, "%s/.debug/", base);
+	if (ret >= PATH_MAX) {
+		warnx("jvmti: cannot generate jit cache dir because %s/.debug/"
+			" is too long, please check the cwd, JITDUMPDIR, and"
+			" HOME variables", base);
+		return -1;
+	}
 	ret = mkdir(jit_path, 0755);
 	if (ret == -1) {
 		if (errno != EEXIST) {
@@ -154,20 +159,32 @@ debug_cache_init(void)
 		}
 	}
 
-	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit", base);
+	ret = snprintf(jit_path, PATH_MAX, "%s/.debug/jit", base);
+	if (ret >= PATH_MAX) {
+		warnx("jvmti: cannot generate jit cache dir because"
+			" %s/.debug/jit is too long, please check the cwd,"
+			" JITDUMPDIR, and HOME variables", base);
+		return -1;
+	}
 	ret = mkdir(jit_path, 0755);
 	if (ret == -1) {
 		if (errno != EEXIST) {
-			warn("cannot create jit cache dir %s", jit_path);
+			warn("jvmti: cannot create jit cache dir %s", jit_path);
 			return -1;
 		}
 	}
 
-	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit/%s.XXXXXXXX", base, str);
-
+	ret = snprintf(jit_path, PATH_MAX, "%s/.debug/jit/%s.XXXXXXXX", base, str);
+	if (ret >= PATH_MAX) {
+		warnx("jvmti: cannot generate jit cache dir because"
+			" %s/.debug/jit/%s.XXXXXXXX is too long, please check"
+			" the cwd, JITDUMPDIR, and HOME variables",
+			base, str);
+		return -1;
+	}
 	p = mkdtemp(jit_path);
 	if (p != jit_path) {
-		warn("cannot create jit cache dir %s", jit_path);
+		warn("jvmti: cannot create jit cache dir %s", jit_path);
 		return -1;
 	}
 
@@ -228,7 +245,7 @@ void *jvmti_open(void)
 {
 	char dump_path[PATH_MAX];
 	struct jitheader header;
-	int fd;
+	int fd, ret;
 	FILE *fp;
 
 	init_arch_timestamp();
@@ -245,12 +262,22 @@ void *jvmti_open(void)
 
 	memset(&header, 0, sizeof(header));
 
-	debug_cache_init();
+	/*
+	 * jitdump file dir
+	 */
+	if (create_jit_cache_dir() < 0)
+		return NULL;
 
 	/*
 	 * jitdump file name
 	 */
-	scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+	ret = snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+	if (ret >= PATH_MAX) {
+		warnx("jvmti: cannot generate jitdump file full path because"
+			" %s/jit-%i.dump is too long, please check the cwd,"
+			" JITDUMPDIR, and HOME variables", jit_path, getpid());
+		return NULL;
+	}
 
 	fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666);
 	if (fd == -1)
-- 
cgit v1.2.3


From af31b04b67f4fd7f639fd465a507c154c46fc9fb Mon Sep 17 00:00:00 2001
From: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>
Date: Tue, 30 Oct 2018 21:50:25 -0400
Subject: tools/testing/nvdimm: Fix the array size for dimm devices.

KASAN reports following global out of bounds access while
nfit_test is being loaded. The out of bound access happens
the following reference to dimm_fail_cmd_flags[dimm]. 'dimm' is
over than the index value, NUM_DCR (==5).

  static int override_return_code(int dimm, unsigned int func, int rc)
  {
          if ((1 << func) & dimm_fail_cmd_flags[dimm]) {

dimm_fail_cmd_flags[] definition:
  static unsigned long dimm_fail_cmd_flags[NUM_DCR];

'dimm' is the return value of get_dimm(), and get_dimm() returns
the index of handle[] array. The handle[] has 7 index. Let's use
ARRAY_SIZE(handle) as the array size.

KASAN report:

==================================================================
BUG: KASAN: global-out-of-bounds in nfit_test_ctl+0x47bb/0x55b0 [nfit_test]
Read of size 8 at addr ffffffffc10cbbe8 by task kworker/u41:0/8
...
Call Trace:
 dump_stack+0xea/0x1b0
 ? dump_stack_print_info.cold.0+0x1b/0x1b
 ? kmsg_dump_rewind_nolock+0xd9/0xd9
 print_address_description+0x65/0x22e
 ? nfit_test_ctl+0x47bb/0x55b0 [nfit_test]
 kasan_report.cold.6+0x92/0x1a6
 nfit_test_ctl+0x47bb/0x55b0 [nfit_test]
...
The buggy address belongs to the variable:
 dimm_fail_cmd_flags+0x28/0xffffffffffffa440 [nfit_test]
==================================================================

Fixes: 39611e83a28c ("tools/testing/nvdimm: Make DSM failure code injection...")
Signed-off-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 tools/testing/nvdimm/test/nfit.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 9527d47a1070..01ec04bf91b5 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -140,8 +140,8 @@ static u32 handle[] = {
 	[6] = NFIT_DIMM_HANDLE(1, 0, 0, 0, 1),
 };
 
-static unsigned long dimm_fail_cmd_flags[NUM_DCR];
-static int dimm_fail_cmd_code[NUM_DCR];
+static unsigned long dimm_fail_cmd_flags[ARRAY_SIZE(handle)];
+static int dimm_fail_cmd_code[ARRAY_SIZE(handle)];
 
 static const struct nd_intel_smart smart_def = {
 	.flags = ND_INTEL_SMART_HEALTH_VALID
@@ -205,7 +205,7 @@ struct nfit_test {
 		unsigned long deadline;
 		spinlock_t lock;
 	} ars_state;
-	struct device *dimm_dev[NUM_DCR];
+	struct device *dimm_dev[ARRAY_SIZE(handle)];
 	struct nd_intel_smart *smart;
 	struct nd_intel_smart_threshold *smart_threshold;
 	struct badrange badrange;
@@ -2680,7 +2680,7 @@ static int nfit_test_probe(struct platform_device *pdev)
 		u32 nfit_handle = __to_nfit_memdev(nfit_mem)->device_handle;
 		int i;
 
-		for (i = 0; i < NUM_DCR; i++)
+		for (i = 0; i < ARRAY_SIZE(handle); i++)
 			if (nfit_handle == handle[i])
 				dev_set_drvdata(nfit_test->dimm_dev[i],
 						nfit_mem);
-- 
cgit v1.2.3


From 8e88c29b351ed4e09dd63f825f1c8260b0cb0ab3 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sun, 23 Sep 2018 17:04:20 +0200
Subject: perf tools: Do not zero sample_id_all for group members

Andi reported following malfunction:

  # perf record -e '{ref-cycles,cycles}:S' -a sleep 1
  # perf script
  non matching sample_id_all

That's because we disable sample_id_all bit for non-sampling group
members. We can't do that, because it needs to be the same over the
whole event list. This patch keeps it untouched again.

Reported-by: Andi Kleen <andi@firstfloor.org>
Tested-by: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180923150420.27327-1-jolsa@kernel.org
Fixes: e9add8bac6c6 ("perf evsel: Disable write_backward for leader sampling group events")
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/attr/test-record-group-sampling | 1 -
 tools/perf/util/evsel.c                          | 1 -
 2 files changed, 2 deletions(-)

(limited to 'tools')

diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling
index 8a33ca4f9e1f..f0729c454f16 100644
--- a/tools/perf/tests/attr/test-record-group-sampling
+++ b/tools/perf/tests/attr/test-record-group-sampling
@@ -37,4 +37,3 @@ sample_freq=0
 sample_period=0
 freq=0
 write_backward=0
-sample_id_all=0
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 6d187059a373..d37bb1566cd9 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -956,7 +956,6 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		attr->sample_freq    = 0;
 		attr->sample_period  = 0;
 		attr->write_backward = 0;
-		attr->sample_id_all  = 0;
 	}
 
 	if (opts->no_samples)
-- 
cgit v1.2.3


From 2c7645b0f7d1014f2636393de7906c6bfd25939f Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Mon, 12 Nov 2018 13:46:06 +1100
Subject: selftests/powerpc: Fix wild_bctr test to work on ppc64

The selftest I recently added to test branching to an out-of-bounds
NIP doesn't work on 64-bit big endian. It does fail but not in the
right way. That is it SEGVs trying to load from the opd at BAD_NIP,
but it never gets as far as branching to BAD_NIP.

To fix it we need to create an opd which is reachable but which holds
the bad address.

Fixes: b7683fc66eba ("selftests/powerpc: Add a test of wild bctr")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/mm/wild_bctr.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/mm/wild_bctr.c b/tools/testing/selftests/powerpc/mm/wild_bctr.c
index 1b0e9e9a2ddc..90469a9e49d4 100644
--- a/tools/testing/selftests/powerpc/mm/wild_bctr.c
+++ b/tools/testing/selftests/powerpc/mm/wild_bctr.c
@@ -105,6 +105,20 @@ static void dump_regs(void)
 	}
 }
 
+#ifdef _CALL_AIXDESC
+struct opd {
+	unsigned long ip;
+	unsigned long toc;
+	unsigned long env;
+};
+static struct opd bad_opd = {
+	.ip = BAD_NIP,
+};
+#define BAD_FUNC (&bad_opd)
+#else
+#define BAD_FUNC BAD_NIP
+#endif
+
 int test_wild_bctr(void)
 {
 	int (*func_ptr)(void);
@@ -133,7 +147,7 @@ int test_wild_bctr(void)
 
 		poison_regs();
 
-		func_ptr = (int (*)(void))BAD_NIP;
+		func_ptr = (int (*)(void))BAD_FUNC;
 		func_ptr();
 
 		FAIL_IF(1); /* we didn't segv? */
-- 
cgit v1.2.3


From b2fed34a628df6118b5d4e13f49a33e15f704fa9 Mon Sep 17 00:00:00 2001
From: Gustavo Romero <gromero@linux.vnet.ibm.com>
Date: Wed, 14 Nov 2018 21:33:30 -0500
Subject: selftests/powerpc: Adjust wild_bctr to build with old binutils

Currently the selftest wild_bctr can fail to build when an old gcc is
used, notably on gcc using a binutils version <= 2.27, because the
assembler does not support the integer suffix UL.

This patch adjusts the wild_bctr test so the REG_POISON value is still
treated as an unsigned long for the shifts on compilation but the UL
suffix is absent on the stringification, so the inline asm code
generated has no UL suffixes.

Signed-off-by: Gustavo Romero <gromero@linux.vnet.ibm.com>
[mpe: Wrap long line]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/mm/wild_bctr.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/powerpc/mm/wild_bctr.c b/tools/testing/selftests/powerpc/mm/wild_bctr.c
index 90469a9e49d4..f2fa101c5a6a 100644
--- a/tools/testing/selftests/powerpc/mm/wild_bctr.c
+++ b/tools/testing/selftests/powerpc/mm/wild_bctr.c
@@ -47,8 +47,9 @@ static int ok(void)
 	return 0;
 }
 
-#define REG_POISON	0x5a5aUL
-#define POISONED_REG(n)	((REG_POISON << 48) | ((n) << 32) | (REG_POISON << 16) | (n))
+#define REG_POISON	0x5a5a
+#define POISONED_REG(n)	((((unsigned long)REG_POISON) << 48) | ((n) << 32) | \
+			 (((unsigned long)REG_POISON) << 16) | (n))
 
 static inline void poison_regs(void)
 {
-- 
cgit v1.2.3