Merge tag 'v6.0' into rdma.git for-next

Trvial merge conflicts against rdma.git for-rc resolved matching
linux-next:
            drivers/infiniband/hw/hns/hns_roce_hw_v2.c
            drivers/infiniband/hw/hns/hns_roce_main.c

https://lore.kernel.org/r/20220929124005.105149-1-broonie@kernel.org

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

10 files changed, 137 insertions, 23 deletions

diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index f94929ebb54b..7ea150cdc137 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -17,21 +17,23 @@ static int process_event_mask(struct perf_tool *tool __maybe_unused,
 			 struct machine *machine __maybe_unused)
 {
 	struct perf_record_cpu_map *map_event = &event->cpu_map;
-	struct perf_record_record_cpu_map *mask;
 	struct perf_record_cpu_map_data *data;
 	struct perf_cpu_map *map;
 	int i;
+	unsigned int long_size;
 
 	data = &map_event->data;
 
 	TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__MASK);
 
-	mask = (struct perf_record_record_cpu_map *)data->data;
+	long_size = data->mask32_data.long_size;
 
-	TEST_ASSERT_VAL("wrong nr",   mask->nr == 1);
+	TEST_ASSERT_VAL("wrong long_size", long_size == 4 || long_size == 8);
+
+	TEST_ASSERT_VAL("wrong nr",   data->mask32_data.nr == 1);
 
 	for (i = 0; i < 20; i++) {
-		TEST_ASSERT_VAL("wrong cpu", test_bit(i, mask->mask));
+		TEST_ASSERT_VAL("wrong cpu", perf_record_cpu_map_data__test_bit(i, data));
 	}
 
 	map = cpu_map__new_data(data);
@@ -51,7 +53,6 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 			 struct machine *machine __maybe_unused)
 {
 	struct perf_record_cpu_map *map_event = &event->cpu_map;
-	struct cpu_map_entries *cpus;
 	struct perf_record_cpu_map_data *data;
 	struct perf_cpu_map *map;
 
@@ -59,11 +60,9 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 
 	TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__CPUS);
 
-	cpus = (struct cpu_map_entries *)data->data;
-
-	TEST_ASSERT_VAL("wrong nr",   cpus->nr == 2);
-	TEST_ASSERT_VAL("wrong cpu",  cpus->cpu[0] == 1);
-	TEST_ASSERT_VAL("wrong cpu",  cpus->cpu[1] == 256);
+	TEST_ASSERT_VAL("wrong nr",   data->cpus_data.nr == 2);
+	TEST_ASSERT_VAL("wrong cpu",  data->cpus_data.cpu[0] == 1);
+	TEST_ASSERT_VAL("wrong cpu",  data->cpus_data.cpu[1] == 256);
 
 	map = cpu_map__new_data(data);
 	TEST_ASSERT_VAL("wrong nr",  perf_cpu_map__nr(map) == 2);
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index dfb6173b2a82..9e9a2b67de19 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -114,8 +114,7 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
 
 	for (i = 0; i < nsyscalls; ++i)
 		for (j = 0; j < expected_nr_events[i]; ++j) {
-			int foo = syscalls[i]();
-			++foo;
+			syscalls[i]();
 		}
 
 	md = &evlist->mmap[0];
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 6a001fcfed68..4952abe716f3 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -332,7 +332,7 @@ out_delete_evlist:
 out:
 	if (err == -EACCES)
 		return TEST_SKIP;
-	if (err < 0)
+	if (err < 0 || errs != 0)
 		return TEST_FAIL;
 	return TEST_OK;
 }
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 07f2411b0ad4..20930dd48ee0 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -86,10 +86,15 @@ static bool samples_same(const struct perf_sample *s1,
 			COMP(read.time_running);
 		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
 		if (read_format & PERF_FORMAT_GROUP) {
-			for (i = 0; i < s1->read.group.nr; i++)
-				MCOMP(read.group.values[i]);
+			for (i = 0; i < s1->read.group.nr; i++) {
+				/* FIXME: check values without LOST */
+				if (read_format & PERF_FORMAT_LOST)
+					MCOMP(read.group.values[i]);
+			}
 		} else {
 			COMP(read.one.id);
+			if (read_format & PERF_FORMAT_LOST)
+				COMP(read.one.lost);
 		}
 	}
 
@@ -263,7 +268,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 			.data	= (void *)aux_data,
 		},
 	};
-	struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
+	struct sample_read_value values[] = {{1, 5, 0}, {9, 3, 0}, {2, 7, 0}, {6, 4, 1},};
 	struct perf_sample sample_out, sample_out_endian;
 	size_t i, sz, bufsz;
 	int err, ret = -1;
@@ -286,6 +291,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 	} else {
 		sample.read.one.value = 0x08789faeb786aa87ULL;
 		sample.read.one.id    = 99;
+		sample.read.one.lost  = 1;
 	}
 
 	sz = perf_event__sample_event_size(&sample, sample_type, read_format);
@@ -370,7 +376,7 @@ out_free:
  */
 static int test__sample_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
-	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
+	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15, 20, 21, 22, 28, 29, 30, 31};
 	u64 sample_type;
 	u64 sample_regs;
 	size_t i;
diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index 00c7285ce1ac..301f95427159 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -61,7 +61,7 @@ test_register_capture() {
     echo "Register capture test [Skipped missing registers]"
     return
   fi
-  if ! perf record -o - --intr-regs=di,r8,dx,cx -e cpu/br_inst_retired.near_call/p \
+  if ! perf record -o - --intr-regs=di,r8,dx,cx -e br_inst_retired.near_call:p \
     -c 1000 --per-thread true 2> /dev/null \
     | perf script -F ip,sym,iregs -i - 2> /dev/null \
     | egrep -q "DI:"
diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh
index 9313ef2739e0..26a51b48aee4 100755
--- a/tools/perf/tests/shell/stat.sh
+++ b/tools/perf/tests/shell/stat.sh
@@ -28,6 +28,24 @@ test_stat_record_report() {
   echo "stat record and report test [Success]"
 }
 
+test_stat_repeat_weak_groups() {
+  echo "stat repeat weak groups test"
+  if ! perf stat -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' \
+     true 2>&1 | grep -q 'seconds time elapsed'
+  then
+    echo "stat repeat weak groups test [Skipped event parsing failed]"
+    return
+  fi
+  if ! perf stat -r2 -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}:W' \
+    true > /dev/null 2>&1
+  then
+    echo "stat repeat weak groups test [Failed]"
+    err=1
+    return
+  fi
+  echo "stat repeat weak groups test [Success]"
+}
+
 test_topdown_groups() {
   # Topdown events must be grouped with the slots event first. Test that
   # parse-events reorders this.
@@ -75,6 +93,7 @@ test_topdown_weak_groups() {
 
 test_default_stat
 test_stat_record_report
+test_stat_repeat_weak_groups
 test_topdown_groups
 test_topdown_weak_groups
 exit $err
diff --git a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
new file mode 100755
index 000000000000..d724855d097c
--- /dev/null
+++ b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
@@ -0,0 +1,83 @@
+#!/bin/sh
+# perf stat --bpf-counters --for-each-cgroup test
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+test_cgroups=
+if [ "$1" = "-v" ]; then
+	verbose="1"
+fi
+
+# skip if --bpf-counters --for-each-cgroup is not supported
+check_bpf_counter()
+{
+	if ! perf stat -a --bpf-counters --for-each-cgroup / true > /dev/null 2>&1; then
+		if [ "${verbose}" = "1" ]; then
+			echo "Skipping: --bpf-counters --for-each-cgroup not supported"
+			perf --no-pager stat -a --bpf-counters --for-each-cgroup / true || true
+		fi
+		exit 2
+	fi
+}
+
+# find two cgroups to measure
+find_cgroups()
+{
+	# try usual systemd slices first
+	if [ -d /sys/fs/cgroup/system.slice -a -d /sys/fs/cgroup/user.slice ]; then
+		test_cgroups="system.slice,user.slice"
+		return
+	fi
+
+	# try root and self cgroups
+	local self_cgrp=$(grep perf_event /proc/self/cgroup | cut -d: -f3)
+	if [ -z ${self_cgrp} ]; then
+		# cgroup v2 doesn't specify perf_event
+		self_cgrp=$(grep ^0: /proc/self/cgroup | cut -d: -f3)
+	fi
+
+	if [ -z ${self_cgrp} ]; then
+		test_cgroups="/"
+	else
+		test_cgroups="/,${self_cgrp}"
+	fi
+}
+
+# As cgroup events are cpu-wide, we cannot simply compare the result.
+# Just check if it runs without failure and has non-zero results.
+check_system_wide_counted()
+{
+	local output
+
+	output=$(perf stat -a --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, sleep 1  2>&1)
+	if echo ${output} | grep -q -F "<not "; then
+		echo "Some system-wide events are not counted"
+		if [ "${verbose}" = "1" ]; then
+			echo ${output}
+		fi
+		exit 1
+	fi
+}
+
+check_cpu_list_counted()
+{
+	local output
+
+	output=$(perf stat -C 1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1  2>&1)
+	if echo ${output} | grep -q -F "<not "; then
+		echo "Some CPU events are not counted"
+		if [ "${verbose}" = "1" ]; then
+			echo ${output}
+		fi
+		exit 1
+	fi
+}
+
+check_bpf_counter
+find_cgroups
+
+check_system_wide_counted
+check_cpu_list_counted
+
+exit 0
diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh
index c644f94a6500..ec801cffae6b 100755
--- a/tools/perf/tests/shell/test_brstack.sh
+++ b/tools/perf/tests/shell/test_brstack.sh
@@ -12,7 +12,8 @@ if ! [ -x "$(command -v cc)" ]; then
 fi
 
 # skip the test if the hardware doesn't support branch stack sampling
-perf record -b -o- -B true > /dev/null 2>&1 || exit 2
+# and if the architecture doesn't support filter types: any,save_type,u
+perf record -b -o- -B --branch-filter any,save_type,u true > /dev/null 2>&1 || exit 2
 
 TMPDIR=$(mktemp -d /tmp/__perf_test.program.XXXXX)
 
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 4fd8d703ff19..8ab035b55875 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -43,10 +43,11 @@ static bool is_ignored_symbol(const char *name, char type)
 	/* Symbol names that begin with the following are ignored.*/
 	static const char * const ignored_prefixes[] = {
 		"$",			/* local symbols for ARM, MIPS, etc. */
-		".LASANPC",		/* s390 kasan local symbols */
+		".L",			/* local labels, .LBB,.Ltmpxxx,.L__unnamed_xx,.LASANPC, etc. */
 		"__crc_",		/* modversions */
 		"__efistub_",		/* arm64 EFI stub namespace */
-		"__kvm_nvhe_",		/* arm64 non-VHE KVM namespace */
+		"__kvm_nvhe_$",		/* arm64 local symbols in non-VHE KVM namespace */
+		"__kvm_nvhe_.L",	/* arm64 local symbols in non-VHE KVM namespace */
 		"__AArch64ADRPThunk_",	/* arm64 lld */
 		"__ARMV5PILongThunk_",	/* arm lld */
 		"__ARMV7PILongThunk_",
diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c
index 9d4c45184e71..56455da30341 100644
--- a/tools/perf/tests/wp.c
+++ b/tools/perf/tests/wp.c
@@ -2,7 +2,9 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <errno.h>
 #include <sys/ioctl.h>
+#include <linux/compiler.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/kernel.h>
 #include "tests.h"
@@ -137,8 +139,7 @@ static int test__wp_rw(struct test_suite *test __maybe_unused,
 #endif
 }
 
-static int test__wp_modify(struct test_suite *test __maybe_unused,
-			   int subtest __maybe_unused)
+static int test__wp_modify(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 #if defined(__s390x__)
 	return TEST_SKIP;
@@ -160,6 +161,11 @@ static int test__wp_modify(struct test_suite *test __maybe_unused,
 	new_attr.disabled = 1;
 	ret = ioctl(fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &new_attr);
 	if (ret < 0) {
+		if (errno == ENOTTY) {
+			test->test_cases[subtest].skip_reason = "missing kernel support";
+			ret = TEST_SKIP;
+		}
+
 		pr_debug("ioctl(PERF_EVENT_IOC_MODIFY_ATTRIBUTES) failed\n");
 		close(fd);
 		return ret;