Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR (net-7.0-rc2).

Conflicts:

tools/testing/selftests/drivers/net/hw/rss_ctx.py
  19c3a2a81d2b ("selftests: drv-net: rss: Generate unique ports for RSS context tests")
  ce5a0f4612db ("selftests: drv-net: rss_ctx: test RSS contexts persist after ifdown/up")

include/net/inet_connection_sock.h
  858d2a4f67ff6 ("tcp: fix potential race in tcp_v6_syn_recv_sock()")
  fcd3d039fab69 ("tcp: make tcp_v{4,6}_send_check() static")
https://lore.kernel.org/aZ8PSFLzBrEU3I89@sirena.org.uk

drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
  69050f8d6d075 ("treewide: Replace kmalloc with kmalloc_obj for non-scalar types")
  bf4afc53b77ae ("Convert 'alloc_obj' family to use the new default GFP_KERNEL argument")
  8a96b9144f18a ("net/mlx5e: Alloc xsk channel param out of mlx5e_open_xsk()")

Adjacent changes:

net/netfilter/ipvs/ip_vs_ctl.c
  c59bd9e62e06 ("ipvs: use more counters to avoid service lookups")
  bf4afc53b77a ("Convert 'alloc_obj' family to use the new default GFP_KERNEL argument")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 214 insertions, 22 deletions

diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index cbeb3a38fdfe..97246eab863a 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -4,13 +4,16 @@
 import datetime
 import random
 import re
+import time
+from lib.py import ksft_disruptive
 from lib.py import ksft_run, ksft_pr, ksft_exit
 from lib.py import ksft_eq, ksft_ne, ksft_ge, ksft_in, ksft_lt, ksft_true, ksft_raises
 from lib.py import NetDrvEpEnv
 from lib.py import EthtoolFamily, NetdevFamily
 from lib.py import KsftSkipEx, KsftFailEx
 from lib.py import rand_port, rand_ports
-from lib.py import ethtool, ip, defer, GenerateTraffic, CmdExitFailure
+from lib.py import cmd, ethtool, ip, defer, CmdExitFailure, wait_file
+from lib.py import GenerateTraffic
 
 
 def _rss_key_str(key):
@@ -808,6 +811,98 @@ def test_rss_default_context_rule(cfg):
                           'noise' : (0, 1) })
 
 
+@ksft_disruptive
+def test_rss_context_persist_ifupdown(cfg, pre_down=False):
+    """
+    Test that RSS contexts and their associated ntuple filters persist across
+    an interface down/up cycle.
+
+    """
+
+    require_ntuple(cfg)
+
+    qcnt = len(_get_rx_cnts(cfg))
+    if qcnt < 6:
+        try:
+            ethtool(f"-L {cfg.ifname} combined 6")
+            defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+        except Exception as exc:
+            raise KsftSkipEx("Not enough queues for the test") from exc
+
+    ethtool(f"-X {cfg.ifname} equal 2")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    ifup = defer(ip, f"link set dev {cfg.ifname} up")
+    if pre_down:
+        ip(f"link set dev {cfg.ifname} down")
+
+    try:
+        ctx1_id = ethtool_create(cfg, "-X", "context new start 2 equal 2")
+        defer(ethtool, f"-X {cfg.ifname} context {ctx1_id} delete")
+    except CmdExitFailure as exc:
+        raise KsftSkipEx("Create context not supported with interface down") from exc
+
+    ctx2_id = ethtool_create(cfg, "-X", "context new start 4 equal 2")
+    defer(ethtool, f"-X {cfg.ifname} context {ctx2_id} delete")
+
+    port_ctx2 = rand_port()
+    flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port_ctx2} context {ctx2_id}"
+    ntuple_id = ethtool_create(cfg, "-N", flow)
+    defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}")
+
+    if not pre_down:
+        ip(f"link set dev {cfg.ifname} down")
+    ifup.exec()
+
+    wait_file(f"/sys/class/net/{cfg.ifname}/carrier",
+        lambda x: x.strip() == "1", deadline=20)
+
+    remote_addr = cfg.remote_addr_v[cfg.addr_ipver]
+    for _ in range(10):
+        if cmd(f"ping -c 1 -W 1 {remote_addr}", fail=False).ret == 0:
+            break
+        time.sleep(1)
+    else:
+        raise KsftSkipEx("Cannot reach remote host after interface up")
+
+    ctxs = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}}, dump=True)
+
+    data1 = [c for c in ctxs if c.get('context') == ctx1_id]
+    ksft_eq(len(data1), 1, f"Context {ctx1_id} should persist after ifup")
+
+    data2 = [c for c in ctxs if c.get('context') == ctx2_id]
+    ksft_eq(len(data2), 1, f"Context {ctx2_id} should persist after ifup")
+
+    _ntuple_rule_check(cfg, ntuple_id, ctx2_id)
+
+    cnts = _get_rx_cnts(cfg)
+    GenerateTraffic(cfg).wait_pkts_and_stop(20000)
+    cnts = _get_rx_cnts(cfg, prev=cnts)
+
+    main_traffic = sum(cnts[0:2])
+    ksft_ge(main_traffic, 18000, f"Main context traffic distribution: {cnts}")
+    ksft_lt(sum(cnts[2:6]), 500, f"Other context queues should be mostly empty: {cnts}")
+
+    _send_traffic_check(cfg, port_ctx2, f"context {ctx2_id}",
+                        {'target': (4, 5),
+                         'noise': (0, 1),
+                         'empty': (2, 3)})
+
+
+def test_rss_context_persist_create_and_ifdown(cfg):
+    """
+    Create RSS contexts then cycle the interface down and up.
+    """
+    test_rss_context_persist_ifupdown(cfg, pre_down=False)
+
+
+def test_rss_context_persist_ifdown_and_create(cfg):
+    """
+    Bring interface down first, then create RSS contexts and bring up.
+    """
+    test_rss_context_persist_ifupdown(cfg, pre_down=True)
+
+
 def main() -> None:
     with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
         cfg.context_cnt = None
@@ -822,7 +917,9 @@ def main() -> None:
                   test_rss_context_out_of_order, test_rss_context4_create_with_cfg,
                   test_flow_add_context_missing,
                   test_delete_rss_context_busy, test_rss_ntuple_addition,
-                  test_rss_default_context_rule],
+                  test_rss_default_context_rule,
+                  test_rss_context_persist_create_and_ifdown,
+                  test_rss_context_persist_ifdown_and_create],
                  args=(cfg, ))
     ksft_exit()
 
diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile
index 1340b3df9c31..45a3e7ad3dcb 100644
--- a/tools/testing/selftests/drivers/net/team/Makefile
+++ b/tools/testing/selftests/drivers/net/team/Makefile
@@ -5,6 +5,7 @@ TEST_PROGS := \
 	dev_addr_lists.sh \
 	options.sh \
 	propagation.sh \
+	refleak.sh \
 # end of TEST_PROGS
 
 TEST_INCLUDES := \
diff --git a/tools/testing/selftests/drivers/net/team/refleak.sh b/tools/testing/selftests/drivers/net/team/refleak.sh
new file mode 100755
index 000000000000..ef08213ab964
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/team/refleak.sh
@@ -0,0 +1,17 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# shellcheck disable=SC2154
+
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/lib.sh
+
+trap cleanup_all_ns EXIT
+
+# Test that there is no reference count leak and that dummy1 can be deleted.
+# https://lore.kernel.org/netdev/4d69abe1-ca8d-4f0b-bcf8-13899b211e57@I-love.SAKURA.ne.jp/
+setup_ns ns1 ns2
+ip -n "$ns1" link add name team1 type team
+ip -n "$ns1" link add name dummy1 mtu 1499 type dummy
+ip -n "$ns1" link set dev dummy1 master team1
+ip -n "$ns1" link set dev dummy1 netns "$ns2"
+ip -n "$ns2" link del dev dummy1
diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_zero_wnd_fin.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_zero_wnd_fin.pkt
new file mode 100644
index 000000000000..e245359a1a91
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_zero_wnd_fin.pkt
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Some TCP stacks send FINs even though the window is closed. We break
+// a possible FIN/ACK loop by accepting the FIN.
+
+--mss=1000
+
+`./defaults.sh`
+
+// Establish a connection.
+   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 0>
+   +0 < . 1:1(0) ack 1 win 257
+
+   +0 accept(3, ..., ...) = 4
+
+   +0 < P. 1:60001(60000) ack 1 win 257
+    * > .  1:1(0) ack 60001 win 0
+
+   +0 < F. 60001:60001(0) ack 1 win 257
+   +0 > . 1:1(0) ack 60002 win 0
diff --git a/tools/testing/selftests/sched_ext/rt_stall.c b/tools/testing/selftests/sched_ext/rt_stall.c
index 015200f80f6e..ab772e336f86 100644
--- a/tools/testing/selftests/sched_ext/rt_stall.c
+++ b/tools/testing/selftests/sched_ext/rt_stall.c
@@ -23,6 +23,30 @@
 #define CORE_ID		0	/* CPU to pin tasks to */
 #define RUN_TIME        5	/* How long to run the test in seconds */
 
+/* Signal the parent that setup is complete by writing to a pipe */
+static void signal_ready(int fd)
+{
+	char c = 1;
+
+	if (write(fd, &c, 1) != 1) {
+		perror("write to ready pipe");
+		exit(EXIT_FAILURE);
+	}
+	close(fd);
+}
+
+/* Wait for a child to signal readiness via a pipe */
+static void wait_ready(int fd)
+{
+	char c;
+
+	if (read(fd, &c, 1) != 1) {
+		perror("read from ready pipe");
+		exit(EXIT_FAILURE);
+	}
+	close(fd);
+}
+
 /* Simple busy-wait function for test tasks */
 static void process_func(void)
 {
@@ -122,14 +146,24 @@ static bool sched_stress_test(bool is_ext)
 
 	float ext_runtime, rt_runtime, actual_ratio;
 	int ext_pid, rt_pid;
+	int ext_ready[2], rt_ready[2];
 
 	ksft_print_header();
 	ksft_set_plan(1);
 
+	if (pipe(ext_ready) || pipe(rt_ready)) {
+		perror("pipe");
+		ksft_exit_fail();
+	}
+
 	/* Create and set up a EXT task */
 	ext_pid = fork();
 	if (ext_pid == 0) {
+		close(ext_ready[0]);
+		close(rt_ready[0]);
+		close(rt_ready[1]);
 		set_affinity(CORE_ID);
+		signal_ready(ext_ready[1]);
 		process_func();
 		exit(0);
 	} else if (ext_pid < 0) {
@@ -140,8 +174,12 @@ static bool sched_stress_test(bool is_ext)
 	/* Create an RT task */
 	rt_pid = fork();
 	if (rt_pid == 0) {
+		close(ext_ready[0]);
+		close(ext_ready[1]);
+		close(rt_ready[0]);
 		set_affinity(CORE_ID);
 		set_sched(SCHED_FIFO, 50);
+		signal_ready(rt_ready[1]);
 		process_func();
 		exit(0);
 	} else if (rt_pid < 0) {
@@ -149,6 +187,17 @@ static bool sched_stress_test(bool is_ext)
 		ksft_exit_fail();
 	}
 
+	/*
+	 * Wait for both children to complete their setup (affinity and
+	 * scheduling policy) before starting the measurement window.
+	 * This prevents flaky failures caused by the RT child's setup
+	 * time eating into the measurement period.
+	 */
+	close(ext_ready[1]);
+	close(rt_ready[1]);
+	wait_ready(ext_ready[0]);
+	wait_ready(rt_ready[0]);
+
 	/* Let the processes run for the specified time */
 	sleep(RUN_TIME);
 
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index dc8dbe74a6d0..86e338886b33 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -210,16 +210,21 @@ check_result() {
 }
 
 add_namespaces() {
-	local orig_mode
-	orig_mode=$(cat /proc/sys/net/vsock/child_ns_mode)
-
-	for mode in "${NS_MODES[@]}"; do
-		echo "${mode}" > /proc/sys/net/vsock/child_ns_mode
-		ip netns add "${mode}0" 2>/dev/null
-		ip netns add "${mode}1" 2>/dev/null
-	done
-
-	echo "${orig_mode}" > /proc/sys/net/vsock/child_ns_mode
+	ip netns add "global-parent" 2>/dev/null
+	echo "global" | ip netns exec "global-parent" \
+		tee /proc/sys/net/vsock/child_ns_mode &>/dev/null
+	ip netns add "local-parent" 2>/dev/null
+	echo "local" | ip netns exec "local-parent" \
+		tee /proc/sys/net/vsock/child_ns_mode &>/dev/null
+
+	nsenter --net=/var/run/netns/global-parent \
+		ip netns add "global0" 2>/dev/null
+	nsenter --net=/var/run/netns/global-parent \
+		ip netns add "global1" 2>/dev/null
+	nsenter --net=/var/run/netns/local-parent \
+		ip netns add "local0" 2>/dev/null
+	nsenter --net=/var/run/netns/local-parent \
+		ip netns add "local1" 2>/dev/null
 }
 
 init_namespaces() {
@@ -237,6 +242,8 @@ del_namespaces() {
 		log_host "removed ns ${mode}0"
 		log_host "removed ns ${mode}1"
 	done
+	ip netns del "global-parent" &>/dev/null
+	ip netns del "local-parent" &>/dev/null
 }
 
 vm_ssh() {
@@ -287,7 +294,7 @@ check_args() {
 }
 
 check_deps() {
-	for dep in vng ${QEMU} busybox pkill ssh ss socat; do
+	for dep in vng ${QEMU} busybox pkill ssh ss socat nsenter; do
 		if [[ ! -x $(command -v "${dep}") ]]; then
 			echo -e "skip:    dependency ${dep} not found!\n"
 			exit "${KSFT_SKIP}"
@@ -1231,12 +1238,8 @@ test_ns_local_same_cid_ok() {
 }
 
 test_ns_host_vsock_child_ns_mode_ok() {
-	local orig_mode
-	local rc
-
-	orig_mode=$(cat /proc/sys/net/vsock/child_ns_mode)
+	local rc="${KSFT_PASS}"
 
-	rc="${KSFT_PASS}"
 	for mode in "${NS_MODES[@]}"; do
 		local ns="${mode}0"
 
@@ -1246,15 +1249,13 @@ test_ns_host_vsock_child_ns_mode_ok() {
 			continue
 		fi
 
-		if ! echo "${mode}" > /proc/sys/net/vsock/child_ns_mode; then
-			log_host "child_ns_mode should be writable to ${mode}"
+		if ! echo "${mode}" | ip netns exec "${ns}" \
+			tee /proc/sys/net/vsock/child_ns_mode &>/dev/null; then
 			rc="${KSFT_FAIL}"
 			continue
 		fi
 	done
 
-	echo "${orig_mode}" > /proc/sys/net/vsock/child_ns_mode
-
 	return "${rc}"
 }