[net-next,v7] ipv6: Fix soft lockups in fib6_select_path under high next hop churn

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 6383263bfd04..c134ba202c4c 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1183,8 +1183,8 @@  static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 		while (sibling) {
 			if (sibling->fib6_metric == rt->fib6_metric &&
 			    rt6_qualify_for_ecmp(sibling)) {
-				list_add_tail(&rt->fib6_siblings,
-					      &sibling->fib6_siblings);
+				list_add_tail_rcu(&rt->fib6_siblings,
+						  &sibling->fib6_siblings);
 				break;
 			}
 			sibling = rcu_dereference_protected(sibling->fib6_next,
@@ -1245,7 +1245,7 @@  static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 							 fib6_siblings)
 					sibling->fib6_nsiblings--;
 				rt->fib6_nsiblings = 0;
-				list_del_init(&rt->fib6_siblings);
+				list_del_rcu(&rt->fib6_siblings);
 				rt6_multipath_rebalance(next_sibling);
 				return err;
 			}
@@ -1963,7 +1963,7 @@  static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 					 &rt->fib6_siblings, fib6_siblings)
 			sibling->fib6_nsiblings--;
 		rt->fib6_nsiblings = 0;
-		list_del_init(&rt->fib6_siblings);
+		list_del_rcu(&rt->fib6_siblings);
 		rt6_multipath_rebalance(next_sibling);
 	}
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d7ce5cf2017a..e23e653de158 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -413,8 +413,8 @@  void fib6_select_path(const struct net *net, struct fib6_result *res,
 		      struct flowi6 *fl6, int oif, bool have_oif_match,
 		      const struct sk_buff *skb, int strict)
 {
-	struct fib6_info *sibling, *next_sibling;
 	struct fib6_info *match = res->f6i;
+	struct fib6_info *sibling;
 
 	if (!match->nh && (!match->fib6_nsiblings || have_oif_match))
 		goto out;
@@ -440,8 +440,8 @@  void fib6_select_path(const struct net *net, struct fib6_result *res,
 	if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound))
 		goto out;
 
-	list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings,
-				 fib6_siblings) {
+	list_for_each_entry_rcu(sibling, &match->fib6_siblings,
+				fib6_siblings) {
 		const struct fib6_nh *nh = sibling->fib6_nh;
 		int nh_upper_bound;
 
@@ -5195,14 +5195,18 @@  static void ip6_route_mpath_notify(struct fib6_info *rt,
 	 * nexthop. Since sibling routes are always added at the end of
 	 * the list, find the first sibling of the last route appended
 	 */
+	rcu_read_lock();
+
 	if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) {
-		rt = list_first_entry(&rt_last->fib6_siblings,
-				      struct fib6_info,
-				      fib6_siblings);
+		rt = list_first_or_null_rcu(&rt_last->fib6_siblings,
+					    struct fib6_info,
+					    fib6_siblings);
 	}
 
 	if (rt)
 		inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
+
+	rcu_read_unlock();
 }
 
 static bool ip6_route_mpath_should_notify(const struct fib6_info *rt)
@@ -5547,17 +5551,21 @@  static size_t rt6_nlmsg_size(struct fib6_info *f6i)
 		nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size,
 					 &nexthop_len);
 	} else {
-		struct fib6_info *sibling, *next_sibling;
 		struct fib6_nh *nh = f6i->fib6_nh;
+		struct fib6_info *sibling;
 
 		nexthop_len = 0;
 		if (f6i->fib6_nsiblings) {
 			rt6_nh_nlmsg_size(nh, &nexthop_len);
 
-			list_for_each_entry_safe(sibling, next_sibling,
-						 &f6i->fib6_siblings, fib6_siblings) {
+			rcu_read_lock();
+
+			list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
+						fib6_siblings) {
 				rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len);
 			}
+
+			rcu_read_unlock();
 		}
 		nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
 	}
@@ -5721,7 +5729,7 @@  static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 		    lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
 			goto nla_put_failure;
 	} else if (rt->fib6_nsiblings) {
-		struct fib6_info *sibling, *next_sibling;
+		struct fib6_info *sibling;
 		struct nlattr *mp;
 
 		mp = nla_nest_start_noflag(skb, RTA_MULTIPATH);
@@ -5733,14 +5741,21 @@  static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 				    0) < 0)
 			goto nla_put_failure;
 
-		list_for_each_entry_safe(sibling, next_sibling,
-					 &rt->fib6_siblings, fib6_siblings) {
+		rcu_read_lock();
+
+		list_for_each_entry_rcu(sibling, &rt->fib6_siblings,
+					fib6_siblings) {
 			if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common,
 					    sibling->fib6_nh->fib_nh_weight,
-					    AF_INET6, 0) < 0)
+					    AF_INET6, 0) < 0) {
+				rcu_read_unlock();
+
 				goto nla_put_failure;
+			}
 		}
 
+		rcu_read_unlock();
+
 		nla_nest_end(skb, mp);
 	} else if (rt->nh) {
 		if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id))
@@ -6177,7 +6192,7 @@  void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 	err = -ENOBUFS;
 	seq = info->nlh ? info->nlh->nlmsg_seq : 0;
 
-	skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any());
+	skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC);
 	if (!skb)
 		goto errout;
 
@@ -6190,7 +6205,7 @@  void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 		goto errout;
 	}
 	rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE,
-		    info->nlh, gfp_any());
+		    info->nlh, GFP_ATOMIC);
 	return;
 errout:
 	rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 26a4883a65c9..8c4db5199a42 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -96,6 +96,7 @@  TEST_PROGS += fdb_flush.sh
 TEST_PROGS += fq_band_pktlimit.sh
 TEST_PROGS += vlan_hw_filter.sh
 TEST_PROGS += bpf_offload.py
+TEST_PROGS += ipv6_route_update_soft_lockup.sh
 
 # YNL files, must be before "include ..lib.mk"
 YNL_GEN_FILES := ncdevmem
diff --git a/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh
new file mode 100755
index 000000000000..a6b2b1f9c641
--- /dev/null
+++ b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh
@@ -0,0 +1,262 @@ 
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Testing for potential kernel soft lockup during IPv6 routing table
+# refresh under heavy outgoing IPv6 traffic. If a kernel soft lockup
+# occurs, a kernel panic will be triggered to prevent associated issues.
+#
+#
+#                            Test Environment Layout
+#
+# ┌----------------┐                                         ┌----------------┐
+# |     SOURCE_NS  |                                         |     SINK_NS    |
+# |    NAMESPACE   |                                         |    NAMESPACE   |
+# |(iperf3 clients)|                                         |(iperf3 servers)|
+# |                |                                         |                |
+# |                |                                         |                |
+# |    ┌-----------|                             nexthops    |---------┐      |
+# |    |veth_source|<--------------------------------------->|veth_sink|<┐    |
+# |    └-----------|2001:0DB8:1::0:1/96  2001:0DB8:1::1:1/96 |---------┘ |    |
+# |                |         ^           2001:0DB8:1::1:2/96 |           |    |
+# |                |         .                   .           |       fwd |    |
+# |  ┌---------┐   |         .                   .           |           |    |
+# |  |   IPv6  |   |         .                   .           |           V    |
+# |  | routing |   |         .           2001:0DB8:1::1:80/96|        ┌-----┐ |
+# |  |  table  |   |         .                               |        | lo  | |
+# |  | nexthop |   |         .                               └--------┴-----┴-┘
+# |  | update  |   |         ............................> 2001:0DB8:2::1:1/128
+# |  └-------- ┘   |
+# └----------------┘
+#
+# The test script sets up two network namespaces, source_ns and sink_ns,
+# connected via a veth link. Within source_ns, it continuously updates the
+# IPv6 routing table by flushing and inserting IPV6_NEXTHOP_ADDR_COUNT nexthop
+# IPs destined for SINK_LOOPBACK_IP_ADDR in sink_ns. This refresh occurs at a
+# rate of 1/ROUTING_TABLE_REFRESH_PERIOD per second for TEST_DURATION seconds.
+#
+# Simultaneously, multiple iperf3 clients within source_ns generate heavy
+# outgoing IPv6 traffic. Each client is assigned a unique port number starting
+# at 5000 and incrementing sequentially. Each client targets a unique iperf3
+# server running in sink_ns, connected to the SINK_LOOPBACK_IFACE interface
+# using the same port number.
+#
+# The number of iperf3 servers and clients is set to half of the total
+# available cores on each machine.
+#
+# NOTE: We have tested this script on machines with various CPU specifications,
+# ranging from lower to higher performance as listed below. The test script
+# effectively triggered a kernel soft lockup on machines running an unpatched
+# kernel in under a minute:
+#
+# - 1x Intel Xeon E-2278G 8-Core Processor @ 3.40GHz
+# - 1x Intel Xeon E-2378G Processor 8-Core @ 2.80GHz
+# - 1x AMD EPYC 7401P 24-Core Processor @ 2.00GHz
+# - 1x AMD EPYC 7402P 24-Core Processor @ 2.80GHz
+# - 2x Intel Xeon Gold 5120 14-Core Processor @ 2.20GHz
+# - 1x Ampere Altra Q80-30 80-Core Processor @ 3.00GHz
+# - 2x Intel Xeon Gold 5120 14-Core Processor @ 2.20GHz
+# - 2x Intel Xeon Silver 4214 24-Core Processor @ 2.20GHz
+# - 1x AMD EPYC 7502P 32-Core @ 2.50GHz
+# - 1x Intel Xeon Gold 6314U 32-Core Processor @ 2.30GHz
+# - 2x Intel Xeon Gold 6338 32-Core Processor @ 2.00GHz
+#
+# On less performant machines, you may need to increase the TEST_DURATION
+# parameter to enhance the likelihood of encountering a race condition leading
+# to a kernel soft lockup and avoid a false negative result.
+#
+# NOTE: The test may not produce the expected result in virtualized
+# environments (e.g., qemu) due to differences in timing and CPU handling,
+# which can affect the conditions needed to trigger a soft lockup.
+
+source lib.sh
+source net_helper.sh
+
+TEST_DURATION=300
+ROUTING_TABLE_REFRESH_PERIOD=0.01
+
+IPERF3_BITRATE="300m"
+
+
+IPV6_NEXTHOP_ADDR_COUNT="128"
+IPV6_NEXTHOP_ADDR_MASK="96"
+IPV6_NEXTHOP_PREFIX="2001:0DB8:1"
+
+
+SOURCE_TEST_IFACE="veth_source"
+SOURCE_TEST_IP_ADDR="2001:0DB8:1::0:1/96"
+
+SINK_TEST_IFACE="veth_sink"
+# ${SINK_TEST_IFACE} is populated with the following range of IPv6 addresses:
+# 2001:0DB8:1::1:1  to 2001:0DB8:1::1:${IPV6_NEXTHOP_ADDR_COUNT}
+SINK_LOOPBACK_IFACE="lo"
+SINK_LOOPBACK_IP_MASK="128"
+SINK_LOOPBACK_IP_ADDR="2001:0DB8:2::1:1"
+
+nexthop_ip_list=""
+termination_signal=""
+kernel_softlokup_panic_prev_val=""
+
+terminate_ns_processes_by_pattern() {
+	local ns=$1
+	local pattern=$2
+
+	for pid in $(ip netns pids ${ns}); do
+		[ -e /proc/$pid/cmdline ] && grep -qe "${pattern}" /proc/$pid/cmdline && kill -9 $pid
+	done
+}
+
+cleanup() {
+	echo "info: cleaning up namespaces and terminating all processes within them..."
+
+
+	# Terminate iperf3 instances running in the source_ns. To avoid race
+	# conditions, first iterate over the PIDs and terminate those
+	# associated with the bash shells running the
+	# `while true; do iperf3 -c ...; done` loops. In a second iteration,
+	# terminate the individual `iperf3 -c ...` instances.
+	terminate_ns_processes_by_pattern ${source_ns} while
+	terminate_ns_processes_by_pattern ${source_ns} iperf3
+
+	# Repeat the same process for sink_ns
+	terminate_ns_processes_by_pattern ${sink_ns} while
+	terminate_ns_processes_by_pattern ${sink_ns} iperf3
+
+	# Check if any iperf3 instances are still running. This could happen
+	# if a core has entered an infinite loop and the timeout for detecting
+	# the soft lockup has not expired, but either the test interval has
+	# already elapsed or the test was terminated manually (e.g., with ^C)
+	for pid in $(ip netns pids ${source_ns}); do
+		if [ -e /proc/$pid/cmdline ] && grep -qe 'iperf3' /proc/$pid/cmdline; then
+			echo "FAIL: unable to terminate some iperf3 instances. Soft lockup is underway. A kernel panic is on the way!"
+			exit ${ksft_fail}
+		fi
+	done
+
+	if [ "$termination_signal" == "SIGINT" ]; then
+		echo "SKIP: Termination due to ^C (SIGINT)"
+	elif [ "$termination_signal" == "SIGALRM" ]; then
+		echo "PASS: No kernel soft lockup occurred during this ${TEST_DURATION} second test"
+	fi
+
+	cleanup_ns ${source_ns} ${sink_ns}
+
+	sysctl -qw kernel.softlockup_panic=${kernel_softlokup_panic_prev_val}
+}
+
+setup_prepare() {
+	setup_ns source_ns sink_ns
+
+	ip -n ${source_ns} link add name ${SOURCE_TEST_IFACE} type veth peer name ${SINK_TEST_IFACE} netns ${sink_ns}
+
+	# Setting up the Source namespace
+	ip -n ${source_ns} addr add ${SOURCE_TEST_IP_ADDR} dev ${SOURCE_TEST_IFACE}
+	ip -n ${source_ns} link set dev ${SOURCE_TEST_IFACE} qlen 10000
+	ip -n ${source_ns} link set dev ${SOURCE_TEST_IFACE} up
+	ip netns exec ${source_ns} sysctl -qw net.ipv6.fib_multipath_hash_policy=1
+
+	# Setting up the Sink namespace
+	ip -n ${sink_ns} addr add ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK} dev ${SINK_LOOPBACK_IFACE}
+	ip -n ${sink_ns} link set dev ${SINK_LOOPBACK_IFACE} up
+	ip netns exec ${sink_ns} sysctl -qw net.ipv6.conf.${SINK_LOOPBACK_IFACE}.forwarding=1
+
+	ip -n ${sink_ns} link set ${SINK_TEST_IFACE} up
+	ip netns exec ${sink_ns} sysctl -qw net.ipv6.conf.${SINK_TEST_IFACE}.forwarding=1
+
+
+	# Populate nexthop IPv6 addresses on the test interface in the sink_ns
+	echo "info: populating ${IPV6_NEXTHOP_ADDR_COUNT} IPv6 addresses on the ${SINK_TEST_IFACE} interface ..."
+	for IP in $(seq 1 ${IPV6_NEXTHOP_ADDR_COUNT}); do
+		ip -n ${sink_ns} addr add ${IPV6_NEXTHOP_PREFIX}::$(printf "1:%x" "${IP}")/${IPV6_NEXTHOP_ADDR_MASK} dev ${SINK_TEST_IFACE};
+	done
+
+	# Preparing list of nexthops
+	for IP in $(seq 1 ${IPV6_NEXTHOP_ADDR_COUNT}); do
+		nexthop_ip_list=$nexthop_ip_list" nexthop via ${IPV6_NEXTHOP_PREFIX}::$(printf "1:%x" $IP) dev ${SOURCE_TEST_IFACE} weight 1"
+	done
+}
+
+
+test_soft_lockup_during_routing_table_refresh() {
+	# Start num_of_iperf_servers iperf3 servers in the sink_ns namespace,
+	# each listening on ports starting at 5001 and incrementing
+	# sequentially. Since iperf3 instances may terminate unexpectedly, a
+	# while loop is used to automatically restart them in such cases.
+	echo "info: starting ${num_of_iperf_servers} iperf3 servers in the sink_ns namespace ..."
+	for i in $(seq 1 ${num_of_iperf_servers}); do
+		cmd="iperf3 --bind ${SINK_LOOPBACK_IP_ADDR} -s -p $(printf '5%03d' ${i}) --rcv-timeout 200 &>/dev/null"
+		ip netns exec ${sink_ns} bash -c "while true; do ${cmd}; done &" &>/dev/null
+	done
+
+	# Wait for the iperf3 servers to be ready
+	for i in $(seq ${num_of_iperf_servers}); do
+		port=$(printf '5%03d' ${i});
+		wait_local_port_listen ${sink_ns} ${port} tcp
+	done
+
+	# Continuously refresh the routing table in the background within
+	# the source_ns namespace
+	ip netns exec ${source_ns} bash -c "
+		while \$(ip netns list | grep -q ${source_ns}); do
+			ip -6 route add ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK} ${nexthop_ip_list};
+			sleep ${ROUTING_TABLE_REFRESH_PERIOD};
+			ip -6 route delete ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK};
+		done &"
+
+	# Start num_of_iperf_servers iperf3 clients in the source_ns namespace,
+	# each sending TCP traffic on sequential ports starting at 5001.
+	# Since iperf3 instances may terminate unexpectedly (e.g., if the route
+	# to the server is deleted in the background during a route refresh), a
+	# while loop is used to automatically restart them in such cases.
+	echo "info: starting ${num_of_iperf_servers} iperf3 clients in the source_ns namespace ..."
+	for i in $(seq 1 ${num_of_iperf_servers}); do
+		cmd="iperf3 -c ${SINK_LOOPBACK_IP_ADDR} -p $(printf '5%03d' ${i}) --length 64 --bitrate ${IPERF3_BITRATE} -t 0 --connect-timeout 150 &>/dev/null"
+		ip netns exec ${source_ns} bash -c "while true; do ${cmd}; done &" &>/dev/null
+	done
+
+	echo "info: IPv6 routing table is being updated at the rate of $(echo "1/${ROUTING_TABLE_REFRESH_PERIOD}" | bc)/s for ${TEST_DURATION} seconds ..."
+	echo "info: A kernel soft lockup, if detected, results in a kernel panic!"
+
+	wait
+}
+
+# Make sure 'iperf3' is installed, skip the test otherwise
+if [ ! -x "$(command -v "iperf3")" ]; then
+	echo "SKIP: 'iperf3' is not installed. Skipping the test."
+	exit ${ksft_skip}
+fi
+
+# Determine the number of cores on the machine
+num_of_iperf_servers=$(( $(nproc)/2 ))
+
+# Check if we are running on a multi-core machine, skip the test otherwise
+if [ "${num_of_iperf_servers}" -eq 0 ]; then
+	echo "SKIP: This test is not valid on a single core machine!"
+	exit ${ksft_skip}
+fi
+
+# Since the kernel soft lockup we're testing causes at least one core to enter
+# an infinite loop, destabilizing the host and likely affecting subsequent
+# tests, we trigger a kernel panic instead of reporting a failure and
+# continuing
+kernel_softlokup_panic_prev_val=$(sysctl -n kernel.softlockup_panic)
+sysctl -qw kernel.softlockup_panic=1
+
+handle_sigint() {
+	termination_signal="SIGINT"
+	cleanup
+	exit ${ksft_skip}
+}
+
+handle_sigalrm() {
+	termination_signal="SIGALRM"
+	cleanup
+	exit ${ksft_pass}
+}
+
+trap handle_sigint SIGINT
+trap handle_sigalrm SIGALRM
+
+(sleep ${TEST_DURATION} && kill -s SIGALRM $$)&
+
+setup_prepare
+test_soft_lockup_during_routing_table_refresh