inet6_rt_notify() can be called under RCU protection only. This means the route could be changed concurrently and rt6_fill_node() could return -EMSGSIZE. Re-size the skb when this happens and retry, removing one WARN_ON() that syzbot was able to trigger: WARNING: CPU: 3 PID: 6291 at net/ipv6/route.c:6342 inet6_rt_notify+0x475/0x4b0 net/ipv6/route.c:6342 Modules linked in: CPU: 3 UID: 0 PID: 6291 Comm: syz.0.77 Not tainted 6.16.0-rc7-syzkaller #0 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014 RIP: 0010:inet6_rt_notify+0x475/0x4b0 net/ipv6/route.c:6342 Code: fc ff ff e8 6d 52 ea f7 e9 47 fc ff ff 48 8b 7c 24 08 4c 89 04 24 e8 5a 52 ea f7 4c 8b 04 24 e9 94 fd ff ff e8 9c fe 84 f7 90 <0f> 0b 90 e9 bd fd ff ff e8 6e 52 ea f7 e9 bb fb ff ff 48 89 df e8 RSP: 0018:ffffc900035cf1d8 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffffc900035cf540 RCX: ffffffff8a36e790 RDX: ffff88802f7e8000 RSI: ffffffff8a36e9d4 RDI: 0000000000000005 RBP: ffff88803c230f00 R08: 0000000000000005 R09: 00000000ffffffa6 R10: 00000000ffffffa6 R11: 0000000000000001 R12: 00000000ffffffa6 R13: 0000000000000900 R14: ffff888032ea4100 R15: 0000000000000000 FS: 00007fac7b89a6c0(0000) GS:ffff8880d6a20000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fac7b899f98 CR3: 0000000034b3f000 CR4: 0000000000352ef0 Call Trace: ip6_route_mpath_notify+0xde/0x280 net/ipv6/route.c:5356 ip6_route_multipath_add+0x1181/0x1bd0 net/ipv6/route.c:5536 inet6_rtm_newroute+0xe4/0x1a0 net/ipv6/route.c:5647 rtnetlink_rcv_msg+0x95e/0xe90 net/core/rtnetlink.c:6944 netlink_rcv_skb+0x155/0x420 net/netlink/af_netlink.c:2552 netlink_unicast_kernel net/netlink/af_netlink.c:1320 [inline] netlink_unicast+0x58d/0x850 net/netlink/af_netlink.c:1346 netlink_sendmsg+0x8d1/0xdd0 net/netlink/af_netlink.c:1896 sock_sendmsg_nosec net/socket.c:712 [inline] __sock_sendmsg net/socket.c:727 [inline] ____sys_sendmsg+0xa95/0xc70 net/socket.c:2566 ___sys_sendmsg+0x134/0x1d0 net/socket.c:2620 Fixes: 169fd62799e8 ("ipv6: Get rid of RTNL for SIOCADDRT and RTM_NEWROUTE.") Signed-off-by: Eric Dumazet Reported-by: syzbot --- net/ipv6/route.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 79c8f1acf8a35e465ab1a21aca50a554ca6f513b..9f92129efa05087d435575aa84c81b30430db249 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6321,8 +6321,9 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int nlm_flags) { - struct sk_buff *skb; struct net *net = info->nl_net; + struct sk_buff *skb; + size_t sz; u32 seq; int err; @@ -6330,17 +6331,21 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, seq = info->nlh ? info->nlh->nlmsg_seq : 0; rcu_read_lock(); - - skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC); + sz = rt6_nlmsg_size(rt); +retry: + skb = nlmsg_new(sz, GFP_ATOMIC); if (!skb) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, event, info->portid, seq, nlm_flags); if (err < 0) { - /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ - WARN_ON(err == -EMSGSIZE); kfree_skb(skb); + /* -EMSGSIZE implies needed space grew under us. */ + if (err == -EMSGSIZE) { + sz = max(rt6_nlmsg_size(rt), sz << 1); + goto retry; + } goto errout; } -- 2.50.1.470.g6ba607880d-goog While testing prior patch, I was able to trigger an infinite loop in rt6_nlmsg_size() in the following place: list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, fib6_siblings) { rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len); } This is because fib6_del_route() and fib6_add_rt2node() uses list_del_rcu(), which can confuse rcu readers, because they might no longer see the head of the list. Restart the loop if f6i->fib6_nsiblings is zero. Fixes: d9ccb18f83ea ("ipv6: Fix soft lockups in fib6_select_path under high next hop churn") Signed-off-by: Eric Dumazet --- net/ipv6/ip6_fib.c | 4 ++-- net/ipv6/route.c | 34 ++++++++++++++++++---------------- 2 files changed, 20 insertions(+), 18 deletions(-) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 93578b2ec35fb55ca1f56c3e558661989568639e..af7db69d9eac97033fde46c5ee57e0cfb53a36db 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1265,7 +1265,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, &rt->fib6_siblings, fib6_siblings) sibling->fib6_nsiblings--; - rt->fib6_nsiblings = 0; + WRITE_ONCE(rt->fib6_nsiblings, 0); list_del_rcu(&rt->fib6_siblings); rcu_read_lock(); rt6_multipath_rebalance(next_sibling); @@ -2015,7 +2015,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) sibling->fib6_nsiblings--; - rt->fib6_nsiblings = 0; + WRITE_ONCE(rt->fib6_nsiblings, 0); list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 9f92129efa05087d435575aa84c81b30430db249..6d4e147ae46bc245ccd195e5fb0e254f34ec65a4 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5670,32 +5670,34 @@ static int rt6_nh_nlmsg_size(struct fib6_nh *nh, void *arg) static size_t rt6_nlmsg_size(struct fib6_info *f6i) { + struct fib6_info *sibling; + struct fib6_nh *nh; int nexthop_len; if (f6i->nh) { nexthop_len = nla_total_size(4); /* RTA_NH_ID */ nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size, &nexthop_len); - } else { - 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); - - rcu_read_lock(); + goto common; + } - list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, - fib6_siblings) { - rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len); - } + rcu_read_lock(); +retry: + nh = f6i->fib6_nh; + nexthop_len = 0; + if (READ_ONCE(f6i->fib6_nsiblings)) { + rt6_nh_nlmsg_size(nh, &nexthop_len); - rcu_read_unlock(); + list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, + fib6_siblings) { + rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len); + if (!READ_ONCE(f6i->fib6_nsiblings)) + goto retry; } - nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); } - + rcu_read_unlock(); + nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); +common: return NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(16) /* RTA_SRC */ + nla_total_size(16) /* RTA_DST */ -- 2.50.1.470.g6ba607880d-goog fib6_info_uses_dev() seems to rely on RCU without an explicit protection. Like the prior fix in rt6_nlmsg_size(), we need to make sure fib6_del_route() or fib6_add_rt2node() have not removed the anchor from the list, or we risk an infinite loop. Fixes: d9ccb18f83ea ("ipv6: Fix soft lockups in fib6_select_path under high next hop churn") Signed-off-by: Eric Dumazet --- net/ipv6/route.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6d4e147ae46bc245ccd195e5fb0e254f34ec65a4..04f2b860ca6156776e0cedd18d96877effd287a4 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5958,16 +5958,21 @@ static bool fib6_info_uses_dev(const struct fib6_info *f6i, if (f6i->fib6_nh->fib_nh_dev == dev) return true; - if (f6i->fib6_nsiblings) { - struct fib6_info *sibling, *next_sibling; + if (READ_ONCE(f6i->fib6_nsiblings)) { + const struct fib6_info *sibling; - list_for_each_entry_safe(sibling, next_sibling, - &f6i->fib6_siblings, fib6_siblings) { - if (sibling->fib6_nh->fib_nh_dev == dev) + rcu_read_lock(); + list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, + fib6_siblings) { + if (sibling->fib6_nh->fib_nh_dev == dev) { + rcu_read_unlock(); return true; + } + if (!READ_ONCE(f6i->fib6_nsiblings)) + break; } + rcu_read_unlock(); } - return false; } -- 2.50.1.470.g6ba607880d-goog rt->fib6_nsiblings can be read locklessly, add corresponding READ_ONCE() and WRITE_ONCE() annotations. Fixes: 66f5d6ce53e6 ("ipv6: replace rwlock with rcu and spinlock in fib6_table") Signed-off-by: Eric Dumazet --- net/ipv6/ip6_fib.c | 20 +++++++++++++------- net/ipv6/route.c | 5 +++-- 2 files changed, 16 insertions(+), 9 deletions(-) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index af7db69d9eac97033fde46c5ee57e0cfb53a36db..4d68bd853dbae92a48a15eeee091bfdde3b5c77d 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -445,15 +445,17 @@ struct fib6_dump_arg { static int fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg) { enum fib_event_type fib_event = FIB_EVENT_ENTRY_REPLACE; + unsigned int nsiblings; int err; if (!rt || rt == arg->net->ipv6.fib6_null_entry) return 0; - if (rt->fib6_nsiblings) + nsiblings = READ_ONCE(rt->fib6_nsiblings); + if (nsiblings) err = call_fib6_multipath_entry_notifier(arg->nb, fib_event, rt, - rt->fib6_nsiblings, + nsiblings, arg->extack); else err = call_fib6_entry_notifier(arg->nb, fib_event, rt, @@ -1138,7 +1140,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, if (rt6_duplicate_nexthop(iter, rt)) { if (rt->fib6_nsiblings) - rt->fib6_nsiblings = 0; + WRITE_ONCE(rt->fib6_nsiblings, 0); if (!(iter->fib6_flags & RTF_EXPIRES)) return -EEXIST; if (!(rt->fib6_flags & RTF_EXPIRES)) { @@ -1167,7 +1169,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, */ if (rt_can_ecmp && rt6_qualify_for_ecmp(iter)) - rt->fib6_nsiblings++; + WRITE_ONCE(rt->fib6_nsiblings, + rt->fib6_nsiblings + 1); } if (iter->fib6_metric > rt->fib6_metric) @@ -1217,7 +1220,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, fib6_nsiblings = 0; list_for_each_entry_safe(sibling, temp_sibling, &rt->fib6_siblings, fib6_siblings) { - sibling->fib6_nsiblings++; + WRITE_ONCE(sibling->fib6_nsiblings, + sibling->fib6_nsiblings + 1); BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings); fib6_nsiblings++; } @@ -1264,7 +1268,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) - sibling->fib6_nsiblings--; + WRITE_ONCE(sibling->fib6_nsiblings, + sibling->fib6_nsiblings - 1); WRITE_ONCE(rt->fib6_nsiblings, 0); list_del_rcu(&rt->fib6_siblings); rcu_read_lock(); @@ -2014,7 +2019,8 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, notify_del = true; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) - sibling->fib6_nsiblings--; + WRITE_ONCE(sibling->fib6_nsiblings, + sibling->fib6_nsiblings - 1); WRITE_ONCE(rt->fib6_nsiblings, 0); list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 04f2b860ca6156776e0cedd18d96877effd287a4..aaedc08607c01c409276032b3ac213bb1876c726 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5346,7 +5346,8 @@ static void ip6_route_mpath_notify(struct fib6_info *rt, */ rcu_read_lock(); - if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) { + if ((nlflags & NLM_F_APPEND) && rt_last && + READ_ONCE(rt_last->fib6_nsiblings)) { rt = list_first_or_null_rcu(&rt_last->fib6_siblings, struct fib6_info, fib6_siblings); @@ -5856,7 +5857,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, if (dst->lwtstate && lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; - } else if (rt->fib6_nsiblings) { + } else if (READ_ONCE(rt->fib6_nsiblings)) { struct fib6_info *sibling; struct nlattr *mp; -- 2.50.1.470.g6ba607880d-goog