Merge branch 'main' of https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git

# Conflicts:
#	MAINTAINERS
#	tools/testing/selftests/net/lib.sh

6 files changed, 380 insertions, 23 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.c b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
index 6eb9096d084c..477aedbb01ba 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_xsk.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
@@ -1164,8 +1164,8 @@ static int __send_pkts(struct ifobject *ifobject, struct xsk_socket_info *xsk,
 		       bool test_timeout)
 {
 	u32 i, idx = 0, valid_pkts = 0, valid_frags = 0, buffer_len;
+	struct xsk_umem_info *umem = ifobject->xsk_arr[0].umem_real;
 	struct pkt_stream *pkt_stream = xsk->pkt_stream;
-	struct xsk_umem_info *umem = xsk->umem;
 	bool use_poll = ifobject->use_poll;
 	struct pollfd fds = { };
 	int ret;
@@ -1514,7 +1514,7 @@ static int thread_common_ops_tx(struct test_spec *test, struct ifobject *ifobjec
 	umem_tx->base_addr = 0;
 	umem_tx->next_buffer = 0;
 
-	ret = xsk_configure(test, ifobject, umem_tx, true);
+	ret = xsk_configure(test, ifobject, umem_rx, true);
 	if (ret)
 		return ret;
 	ifobject->xsk = &ifobject->xsk_arr[0];
diff --git a/tools/testing/selftests/drivers/net/hw/toeplitz.py b/tools/testing/selftests/drivers/net/hw/toeplitz.py
index cd7e080e6f84..571732198b93 100755
--- a/tools/testing/selftests/drivers/net/hw/toeplitz.py
+++ b/tools/testing/selftests/drivers/net/hw/toeplitz.py
@@ -21,6 +21,8 @@ from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx, KsftFailEx
 ETH_RSS_HASH_TOP = 1
 # Must match RPS_MAX_CPUS in toeplitz.c
 RPS_MAX_CPUS = 16
+# Cap Rx queues so IRQ pinning leaves free CPUs in the RPS_MAX_CPUS range
+QUEUE_CAP = 8
 
 
 def _check_rps_and_rfs_not_configured(cfg):
@@ -48,6 +50,25 @@ def _get_cpu_for_irq(irq):
         return int(data)
 
 
+def _cap_queue_count(cfg):
+    ehdr = {"header": {"dev-index": cfg.ifindex}}
+    chans = cfg.ethnl.channels_get(ehdr)
+
+    config = {}
+    restore = {}
+    for key in ("combined-count", "rx-count"):
+        cur = chans.get(key, 0)
+        if cur > QUEUE_CAP:
+            config[key] = QUEUE_CAP
+            restore[key] = cur
+
+    if not config:
+        return
+
+    cfg.ethnl.channels_set(ehdr | config)
+    defer(cfg.ethnl.channels_set, ehdr | restore)
+
+
 def _get_irq_cpus(cfg):
     """
     Read the list of IRQs for the device Rx queues.
@@ -177,6 +198,7 @@ def test(cfg, proto_flag, ipver, grp):
     ]
 
     if grp:
+        _cap_queue_count(cfg)
         _check_rps_and_rfs_not_configured(cfg)
     if grp == "rss":
         irq_cpus = ",".join([str(x) for x in _get_irq_cpus(cfg)])
diff --git a/tools/testing/selftests/net/getsockopt_iter.c b/tools/testing/selftests/net/getsockopt_iter.c
index 209569354d0e..fe5a5268bc34 100644
--- a/tools/testing/selftests/net/getsockopt_iter.c
+++ b/tools/testing/selftests/net/getsockopt_iter.c
@@ -11,6 +11,8 @@
  *   that always reports the required buffer length back via optlen,
  *   even when the user buffer is too small to receive any group bits.
  * - vsock:   SO_VM_SOCKETS_BUFFER_SIZE covers the u64 path.
+ * - raw:     ICMP_FILTER covers a fixed-size struct payload that clamps
+ *            the length down on a short buffer instead of failing.
  *
  * Author: Breno Leitao <leitao@debian.org>
  */
@@ -24,12 +26,20 @@
 #include <linux/rtnetlink.h>
 #include <linux/time_types.h>
 #include <linux/vm_sockets.h>
+#include <linux/icmp.h>
+#include <netinet/in.h>
 #include <sys/socket.h>
 #include "kselftest_harness.h"
 
 #ifndef AF_VSOCK
 #define AF_VSOCK 40
 #endif
+#ifndef SOL_RAW
+#define SOL_RAW 255
+#endif
+#ifndef ICMP_FILTER
+#define ICMP_FILTER 1
+#endif
 
 /* ---------- netlink ---------- */
 
@@ -297,4 +307,91 @@ TEST_F(vsock, connect_timeout_old_exact)
 	ASSERT_EQ(sizeof(tv), optlen);
 }
 
+/* ---------- raw (ipv4) ---------- */
+
+FIXTURE(raw)
+{
+	int fd;
+};
+
+FIXTURE_SETUP(raw)
+{
+	struct icmp_filter filt = { .data = 0xdeadbeef };
+
+	self->fd = socket(AF_INET, SOCK_RAW, IPPROTO_ICMP);
+	if (self->fd < 0)
+		SKIP(return, "SOCK_RAW/ICMP socket: %s", strerror(errno));
+
+	if (setsockopt(self->fd, SOL_RAW, ICMP_FILTER, &filt, sizeof(filt)) < 0)
+		SKIP(return, "set ICMP_FILTER: %s", strerror(errno));
+}
+
+FIXTURE_TEARDOWN(raw)
+{
+	if (self->fd >= 0)
+		close(self->fd);
+}
+
+TEST_F(raw, icmpfilter_exact)
+{
+	struct icmp_filter filt = {};
+	socklen_t optlen = sizeof(filt);
+
+	ASSERT_EQ(0, getsockopt(self->fd, SOL_RAW, ICMP_FILTER,
+				&filt, &optlen));
+	ASSERT_EQ(sizeof(filt), optlen);
+	ASSERT_EQ(0xdeadbeef, filt.data);
+}
+
+TEST_F(raw, icmpfilter_oversize_clamped)
+{
+	char buf[16] = {};
+	socklen_t optlen = sizeof(buf);
+
+	ASSERT_EQ(0, getsockopt(self->fd, SOL_RAW, ICMP_FILTER,
+				buf, &optlen));
+	ASSERT_EQ(sizeof(struct icmp_filter), optlen);
+}
+
+/* Unlike the int/u64 options above, ICMP_FILTER clamps the length down
+ * to the user buffer instead of returning EINVAL: a short buffer
+ * succeeds and reports the truncated length back via optlen.
+ */
+TEST_F(raw, icmpfilter_undersize_clamped)
+{
+	char buf[2] = {};
+	socklen_t optlen = sizeof(buf);
+
+	ASSERT_EQ(0, getsockopt(self->fd, SOL_RAW, ICMP_FILTER,
+				buf, &optlen));
+	ASSERT_EQ(sizeof(buf), optlen);
+}
+
+TEST_F(raw, icmpfilter_wrong_proto)
+{
+	struct icmp_filter filt;
+	socklen_t optlen = sizeof(filt);
+	int fd;
+
+	fd = socket(AF_INET, SOCK_RAW, IPPROTO_UDP);
+	if (fd < 0)
+		SKIP(return, "SOCK_RAW/UDP socket: %s", strerror(errno));
+
+	ASSERT_EQ(-1, getsockopt(fd, SOL_RAW, ICMP_FILTER, &filt, &optlen));
+	ASSERT_EQ(EOPNOTSUPP, errno);
+	close(fd);
+}
+
+TEST_F(raw, bad_optname)
+{
+	socklen_t optlen;
+	int val;
+
+	optlen = sizeof(val);
+
+	ASSERT_EQ(-1, getsockopt(self->fd, SOL_RAW, 0x7fff, &val, &optlen));
+	ASSERT_EQ(ENOPROTOOPT, errno);
+	ASSERT_EQ(sizeof(val), optlen);
+}
+
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index d46d2cec89e4..f13672c985bf 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -72,13 +72,9 @@ ksft_exit_status_merge()
 
 timestamp_ms()
 {
-	local now
-	local seconds
-	local nanoseconds
-
-	now=$(date -u +%s:%N) || return
-	seconds=${now%:*}
-	nanoseconds=${now#*:}
+	local now=$(date -u +%s:%N)
+	local seconds=${now%:*}
+	local nanoseconds=${now#*:}
 
 	if [[ $nanoseconds =~ ^[0-9]+$ ]]; then
 		nanoseconds=${nanoseconds:0:9}
@@ -93,10 +89,9 @@ loopy_wait()
 {
 	local sleep_cmd=$1; shift
 	local timeout_ms=$1; shift
-	local start_time
 	local current_time
 
-	start_time=$(timestamp_ms) || return
+	local start_time=$(timestamp_ms)
 	while true
 	do
 		local out
@@ -105,7 +100,7 @@ loopy_wait()
 			return 0
 		fi
 
-		current_time=$(timestamp_ms) || return
+		local current_time=$(timestamp_ms)
 		if ((current_time - start_time > timeout_ms)); then
 			echo -n "$out"
 			return 1
diff --git a/tools/testing/selftests/net/rtnetlink.py b/tools/testing/selftests/net/rtnetlink.py
index 3622413d793d..0c67c7c00d84 100755
--- a/tools/testing/selftests/net/rtnetlink.py
+++ b/tools/testing/selftests/net/rtnetlink.py
@@ -2,27 +2,106 @@
 # SPDX-License-Identifier: GPL-2.0
 
 import socket
+import struct
 import time
-from lib.py import bkg, ip, ksft_exit, ksft_run, ksft_ge, ksft_true, KsftSkipEx
+from lib.py import bkg, ip, ksft_exit, ksft_run, ksft_eq, ksft_ge, ksft_true, KsftSkipEx
 from lib.py import CmdExitFailure, NetNS, NetNSEnter, RtnlAddrFamily
 
 IPV4_ALL_HOSTS_MULTICAST = b'\xe0\x00\x00\x01'
+IPV4_TEST_MULTICAST = b'\xef\x01\x01\x01'
+IPV6_TEST_MULTICAST = bytes.fromhex('ff020000000000000000000000000123')
+
+
+def _users_for(rtnl: RtnlAddrFamily, family: int, grp: bytes, ifindex: int):
+    """Return mc-users for grp on ifindex, or 0 if absent."""
+
+    addrs = rtnl.getmulticast({"ifa-family": family}, dump=True)
+    matches = [addr for addr in addrs
+               if addr['multicast'] == grp and addr['ifa-index'] == ifindex]
+    if not matches:
+        return 0
+    if 'mc-users' not in matches[0]:
+        return None
+
+    return matches[0]['mc-users']
+
 
 def dump_mcaddr_check() -> None:
     """
-    Verify that at least one interface has the IPv4 all-hosts multicast address.
-    At least the loopback interface should have this address.
+    Verify IPv4 multicast addresses and their user counts in RTM_GETMULTICAST.
+    """
+
+    with NetNS() as ns:
+        with NetNSEnter(str(ns)):
+            ip("link set lo up")
+            rtnl = RtnlAddrFamily()
+            lo_idx = socket.if_nametoindex('lo')
+            addresses = rtnl.getmulticast({"ifa-family": socket.AF_INET}, dump=True)
+
+            all_host_multicasts = [
+                addr for addr in addresses
+                if addr['multicast'] == IPV4_ALL_HOSTS_MULTICAST
+            ]
+
+            ksft_ge(len(all_host_multicasts), 1,
+                    "No interface found with the IPv4 all-hosts multicast address")
+
+            mreq = IPV4_TEST_MULTICAST + socket.inet_aton('127.0.0.1')
+            before = _users_for(rtnl, socket.AF_INET, IPV4_TEST_MULTICAST, lo_idx)
+            if before is None:
+                raise KsftSkipEx("kernel does not expose IFA_MC_USERS")
+
+            s1 = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
+            s2 = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
+            try:
+                s1.setsockopt(socket.IPPROTO_IP, socket.IP_ADD_MEMBERSHIP, mreq)
+                s2.setsockopt(socket.IPPROTO_IP, socket.IP_ADD_MEMBERSHIP, mreq)
+
+                after_join = _users_for(rtnl, socket.AF_INET,
+                                        IPV4_TEST_MULTICAST, lo_idx)
+                if after_join is None:
+                    raise KsftSkipEx("kernel does not expose IFA_MC_USERS")
+                ksft_eq(after_join - before, 2,
+                        f"users delta != 2 after two joins "
+                        f"(before={before}, after={after_join})")
+            finally:
+                s1.close()
+                s2.close()
+
+
+def dump_mcaddr6_check() -> None:
+    """
+    Verify IPv6 multicast addresses and their user counts in RTM_GETMULTICAST.
     """
 
-    rtnl = RtnlAddrFamily()
-    addresses = rtnl.getmulticast({"ifa-family": socket.AF_INET}, dump=True)
+    with NetNS() as ns:
+        with NetNSEnter(str(ns)):
+            ip("link set lo up")
+            rtnl = RtnlAddrFamily()
+            lo_idx = socket.if_nametoindex('lo')
+            before = _users_for(rtnl, socket.AF_INET6,
+                                IPV6_TEST_MULTICAST, lo_idx)
+            if before is None:
+                raise KsftSkipEx("kernel does not expose IFA_MC_USERS for IPv6")
+
+            mreq = IPV6_TEST_MULTICAST + struct.pack('=I', lo_idx)
+            s1 = socket.socket(socket.AF_INET6, socket.SOCK_DGRAM)
+            s2 = socket.socket(socket.AF_INET6, socket.SOCK_DGRAM)
+            try:
+                s1.setsockopt(socket.IPPROTO_IPV6, socket.IPV6_JOIN_GROUP, mreq)
+                s2.setsockopt(socket.IPPROTO_IPV6, socket.IPV6_JOIN_GROUP, mreq)
 
-    all_host_multicasts = [
-        addr for addr in addresses if addr['multicast'] == IPV4_ALL_HOSTS_MULTICAST
-    ]
+                after_join = _users_for(rtnl, socket.AF_INET6,
+                                        IPV6_TEST_MULTICAST, lo_idx)
+                if after_join is None:
+                    raise KsftSkipEx("kernel does not expose IFA_MC_USERS for IPv6")
+                ksft_eq(after_join - before, 2,
+                        f"IPv6 users delta != 2 after two joins "
+                        f"(before={before}, after={after_join})")
+            finally:
+                s1.close()
+                s2.close()
 
-    ksft_ge(len(all_host_multicasts), 1,
-            "No interface found with the IPv4 all-hosts multicast address")
 
 def ipv4_devconf_notify() -> None:
     """
@@ -56,7 +135,7 @@ def ipv4_devconf_notify() -> None:
               f"No 'forwarding on' notificiation found for interface {ifname}")
 
 def main() -> None:
-    ksft_run([dump_mcaddr_check, ipv4_devconf_notify])
+    ksft_run([dump_mcaddr_check, dump_mcaddr6_check, ipv4_devconf_notify])
     ksft_exit()
 
 if __name__ == "__main__":
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index a1f97a4b606e..0cf12c50fb74 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -1540,5 +1540,169 @@
             "$TC qdisc del dev $DUMMY root",
             "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
         ]
+    },
+    {
+        "id": "fb6c",
+        "name": "Force multiq to dequeue from its child's gso_skb with qfq leaf",
+        "category": [
+            "qdisc",
+            "tbf",
+            "multiq",
+            "qfq"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "echo \"1 1 4\" > /sys/bus/netdevsim/new_device",
+            "$IP link set dev $ETH up || true",
+            "$IP l set addr 01:02:03:04:05:06 dev $ETH || true",
+            "$IP n add dev $ETH 10.10.11.1 lladdr 01:02:03:04:05:06 dev $ETH || true",
+            "$IP addr add 10.10.11.10/24 dev $ETH || true",
+            "$TC qdisc add dev $ETH root handle 1: tbf rate 88bit burst 1661b peakrate 2257333 minburst 1024 limit 7b",
+            "$TC qdisc add dev $ETH parent 1: handle 2: multiq",
+            "$TC qdisc add dev $ETH parent 2:1 handle 3: qfq",
+            "$TC class add dev $ETH classid 3:1 parent 3: qfq maxpkt 512 weight 1",
+            "$TC filter add dev $ETH parent 2: protocol all prio 1 matchall action skbedit queue_mapping 0",
+            "$TC filter add dev $ETH parent 3: protocol all prio 1 matchall classid 3:1 action ok"
+        ],
+        "cmdUnderTest": "ping -c 1 10.10.11.1 -W0.01 -I$ETH || true",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s -j qdisc ls dev $ETH parent 1:",
+        "matchJSON": [
+            {
+                "kind": "multiq",
+                "handle": "2:",
+                "bytes": 98,
+                "packets": 1,
+                "backlog": 0,
+                "qlen": 0
+            }
+        ],
+        "teardown": [
+            "$TC qdisc del dev $ETH handle 1: root",
+            "echo \"1\" > /sys/bus/netdevsim/del_device"
+        ]
+    },
+    {
+        "id": "1922",
+        "name": "Force multiq to dequeue from its child's gso_skb with dualpi2 leaf",
+        "category": [
+            "qdisc",
+            "tbf",
+            "multiq",
+            "dualpi2"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "echo \"1 1 4\" > /sys/bus/netdevsim/new_device",
+            "$IP link set dev $ETH up || true",
+            "$IP l set addr 01:02:03:04:05:06 dev $ETH || true",
+            "$IP n add dev $ETH 10.10.11.1 lladdr 01:02:03:04:05:06 dev $ETH || true",
+            "$IP addr add 10.10.11.10/24 dev $ETH || true",
+            "$TC qdisc add dev $ETH root handle 1: tbf rate 88bit burst 1661b peakrate 2257333 minburst 1024 limit 7b",
+            "$TC qdisc add dev $ETH parent 1: handle 2: multiq",
+            "$TC qdisc add dev $ETH parent 2:1 handle 3: dualpi2",
+            "$TC filter add dev $ETH parent 2: protocol ip prio 1 u32 match ip dst 10.10.11.1 action skbedit queue_mapping 0",
+            "$TC filter add dev $ETH parent 3: protocol ip prio 1 u32 match ip dst 10.10.11.1 classid 3:1 action ok"
+        ],
+        "cmdUnderTest": "ping -c 1 10.10.11.1 -W0.01 -I$ETH || true",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j -s qdisc ls dev $ETH handle 3:",
+        "matchJSON": [
+            {
+                "kind": "dualpi2",
+                "handle": "3:",
+                "bytes": 98,
+                "packets": 1,
+                "backlog": 0,
+                "qlen": 0
+            }
+        ],
+        "teardown": [
+            "$TC qdisc del dev $ETH handle 1: root",
+            "echo \"1\" > /sys/bus/netdevsim/del_device"
+        ]
+    },
+    {
+        "id": "476f",
+        "name": "Force taprio to dequeue from its child's gso_skb with qfq leaf",
+        "category": [
+            "qdisc",
+            "tbf",
+            "multiq",
+            "qfq"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "echo \"1 1 4\" > /sys/bus/netdevsim/new_device",
+            "$IP link set dev $ETH up || true",
+            "$IP l set addr 01:02:03:04:05:06 dev $ETH || true",
+            "$IP n add dev $ETH 10.10.11.1 lladdr 01:02:03:04:05:06 dev $ETH || true",
+            "$TC qdisc add dev $ETH root handle 1: taprio num_tc 2 map 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 queues 1@0 1@1 base-time 9000000000000000000 sched-entry S 03 200000 flags 0x0 clockid CLOCK_TAI",
+            "$TC qdisc add dev $ETH parent 1:1 handle 3: qfq",
+            "$TC class add dev $ETH classid 3:1 parent 3: qfq maxpkt 512 weight 1",
+            "$TC filter add dev $ETH parent 3: protocol all prio 1 matchall classid 3:1 action ok"
+        ],
+        "cmdUnderTest": "ping -c 1 10.10.11.1 -W0.01 -I$ETH || true",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s -j qdisc ls dev $ETH",
+        "matchJSON": [
+            {
+                "kind": "taprio",
+                "handle": "1:",
+                "bytes": 98,
+                "packets": 1,
+                "backlog": 0,
+                "qlen": 0
+            }
+        ],
+        "teardown": [
+            "$TC qdisc del dev $ETH handle 1: root",
+            "echo \"1\" > /sys/bus/netdevsim/del_device"
+        ]
+    },
+    {
+        "id": "0235",
+        "name": "Force taprio to dequeue from its child's gso_skb with dualpi2 leaf",
+        "category": [
+            "qdisc",
+            "tbf",
+            "taprio",
+            "dualpi2"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "echo \"1 1 4\" > /sys/bus/netdevsim/new_device",
+            "$IP link set dev $ETH up || true",
+            "$IP l set addr 01:02:03:04:05:06 dev $ETH || true",
+            "$IP n add dev $ETH 10.10.11.1 lladdr 01:02:03:04:05:06 dev $ETH || true",
+            "$TC qdisc add dev $ETH root handle 1: taprio num_tc 2 map 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 queues 1@0 1@1 base-time 9000000000000000000 sched-entry S 03 200000 flags 0x0 clockid CLOCK_TAI",
+            "$TC qdisc replace dev $ETH parent 1:1 handle 3: dualpi2",
+            "$TC filter add dev $ETH parent 3: protocol ip prio 1 u32 match ip dst 10.10.11.1 classid 3:1 action ok"
+        ],
+        "cmdUnderTest": "ping -c 1 10.10.11.1 -W0.01 -I$ETH || true",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j -s qdisc ls dev $ETH handle 3:",
+        "matchJSON": [
+            {
+                "kind": "dualpi2",
+                "handle": "3:",
+                "bytes": 98,
+                "packets": 1,
+                "backlog": 0,
+                "qlen": 0
+            }
+        ],
+        "teardown": [
+            "$TC qdisc del dev $ETH handle 1: root",
+            "echo \"1\" > /sys/bus/netdevsim/del_device"
+        ]
     }
 ]