6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Vadim Fedorenko vadfed@meta.com
[ Upstream commit 488b6d91b07112eaaaa4454332c1480894d4e06e ]
When SOF_TIMESTAMPING_OPT_ID is used to ambiguate timestamped datagrams, the sk_tskey can become unpredictable in case of any error happened during sendmsg(). Move increment later in the code and make decrement of sk_tskey in error path. This solution is still racy in case of multiple threads doing snedmsg() over the very same socket in parallel, but still makes error path much more predictable.
Fixes: 09c2d251b707 ("net-timestamp: add key to disambiguate concurrent datagrams") Reported-by: Andy Lutomirski luto@amacapital.net Signed-off-by: Vadim Fedorenko vadfed@meta.com Reviewed-by: Willem de Bruijn willemb@google.com Link: https://lore.kernel.org/r/20240213110428.1681540-1-vadfed@meta.com Signed-off-by: Paolo Abeni pabeni@redhat.com Stable-dep-of: 3301ab7d5aeb ("net/ipv6: release expired exception dst cached in socket") Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/ip_output.c | 13 ++++++++----- net/ipv6/ip6_output.c | 13 ++++++++----- 2 files changed, 16 insertions(+), 10 deletions(-)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a6d460aaee794..c82107bbd9810 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -980,8 +980,8 @@ static int __ip_append_data(struct sock *sk, unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; struct rtable *rt = (struct rtable *)cork->dst; + bool paged, hold_tskey, extra_uref = false; unsigned int wmem_alloc_delta = 0; - bool paged, extra_uref = false; u32 tskey = 0;
skb = skb_peek_tail(queue); @@ -990,10 +990,6 @@ static int __ip_append_data(struct sock *sk, mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; paged = !!cork->gso_size;
- if (cork->tx_flags & SKBTX_ANY_TSTAMP && - READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) - tskey = atomic_inc_return(&sk->sk_tskey) - 1; - hh_len = LL_RESERVED_SPACE(rt->dst.dev);
fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); @@ -1051,6 +1047,11 @@ static int __ip_append_data(struct sock *sk,
cork->length += length;
+ hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP && + READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID; + if (hold_tskey) + tskey = atomic_inc_return(&sk->sk_tskey) - 1; + /* So, what's going on in the loop below? * * We use calculated fragment length to generate chained skb, @@ -1255,6 +1256,8 @@ static int __ip_append_data(struct sock *sk, cork->length -= length; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); + if (hold_tskey) + atomic_dec(&sk->sk_tskey); return err; }
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index f2227e662d1cf..4082470803615 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1499,11 +1499,11 @@ static int __ip6_append_data(struct sock *sk, bool zc = false; u32 tskey = 0; struct rt6_info *rt = (struct rt6_info *)cork->dst; + bool paged, hold_tskey, extra_uref = false; struct ipv6_txoptions *opt = v6_cork->opt; int csummode = CHECKSUM_NONE; unsigned int maxnonfragsize, headersize; unsigned int wmem_alloc_delta = 0; - bool paged, extra_uref = false;
skb = skb_peek_tail(queue); if (!skb) { @@ -1515,10 +1515,6 @@ static int __ip6_append_data(struct sock *sk, mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize; orig_mtu = mtu;
- if (cork->tx_flags & SKBTX_ANY_TSTAMP && - READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) - tskey = atomic_inc_return(&sk->sk_tskey) - 1; - hh_len = LL_RESERVED_SPACE(rt->dst.dev);
fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + @@ -1606,6 +1602,11 @@ static int __ip6_append_data(struct sock *sk, } }
+ hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP && + READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID; + if (hold_tskey) + tskey = atomic_inc_return(&sk->sk_tskey) - 1; + /* * Let's try using as much space as possible. * Use MTU if total length of the message fits into the MTU. @@ -1844,6 +1845,8 @@ static int __ip6_append_data(struct sock *sk, cork->length -= length; IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); + if (hold_tskey) + atomic_dec(&sk->sk_tskey); return err; }