diff options
| author | Andrii Nakryiko <andrii@kernel.org> | 2021-07-27 14:54:45 -0700 |
|---|---|---|
| committer | Andrii Nakryiko <andrii@kernel.org> | 2021-07-27 14:55:35 -0700 |
| commit | f1fdee33f5b458017995c487684e04c859815080 (patch) | |
| tree | adead7fa8fe7b2e7668ce45327fc1a5e9ff9505e /include/linux | |
| parent | d6371c76e20d7d3f61b05fd67b596af4d14a8886 (diff) | |
| parent | 9635720b7c88592214562cb72605bdab6708006c (diff) | |
Merge branch 'sockmap fixes picked up by stress tests'
John Fastabend says:
====================
Running stress tests with recent patch to remove an extra lock in sockmap
resulted in a couple new issues popping up. It seems only one of them
is actually related to the patch:
799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()")
The other two issues had existed long before, but I guess the timing
with the serialization we had before was too tight to get any of
our tests or deployments to hit it.
With attached series stress testing sockmap+TCP with workloads that
create lots of short-lived connections no more splats like below were
seen on upstream bpf branch.
[224913.935822] WARNING: CPU: 3 PID: 32100 at net/core/stream.c:208 sk_stream_kill_queues+0x212/0x220
[224913.935841] Modules linked in: fuse overlay bpf_preload x86_pkg_temp_thermal intel_uncore wmi_bmof squashfs sch_fq_codel efivarfs ip_tables x_tables uas xhci_pci ixgbe mdio xfrm_algo xhci_hcd wmi
[224913.935897] CPU: 3 PID: 32100 Comm: fgs-bench Tainted: G I 5.14.0-rc1alu+ #181
[224913.935908] Hardware name: Dell Inc. Precision 5820 Tower/002KVM, BIOS 1.9.2 01/24/2019
[224913.935914] RIP: 0010:sk_stream_kill_queues+0x212/0x220
[224913.935923] Code: 8b 83 20 02 00 00 85 c0 75 20 5b 5d 41 5c 41 5d 41 5e 41 5f c3 48 89 df e8 2b 11 fe ff eb c3 0f 0b e9 7c ff ff ff 0f 0b eb ce <0f> 0b 5b 5d 41 5c 41 5d 41 5e 41 5f c3 90 0f 1f 44 00 00 41 57 41
[224913.935932] RSP: 0018:ffff88816271fd38 EFLAGS: 00010206
[224913.935941] RAX: 0000000000000ae8 RBX: ffff88815acd5240 RCX: dffffc0000000000
[224913.935948] RDX: 0000000000000003 RSI: 0000000000000ae8 RDI: ffff88815acd5460
[224913.935954] RBP: ffff88815acd5460 R08: ffffffff955c0ae8 R09: fffffbfff2e6f543
[224913.935961] R10: ffffffff9737aa17 R11: fffffbfff2e6f542 R12: ffff88815acd5390
[224913.935967] R13: ffff88815acd5480 R14: ffffffff98d0c080 R15: ffffffff96267500
[224913.935974] FS: 00007f86e6bd1700(0000) GS:ffff888451cc0000(0000) knlGS:0000000000000000
[224913.935981] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[224913.935988] CR2: 000000c0008eb000 CR3: 00000001020e0005 CR4: 00000000003706e0
[224913.935994] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[224913.936000] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[224913.936007] Call Trace:
[224913.936016] inet_csk_destroy_sock+0xba/0x1f0
[224913.936033] __tcp_close+0x620/0x790
[224913.936047] tcp_close+0x20/0x80
[224913.936056] inet_release+0x8f/0xf0
[224913.936070] __sock_release+0x72/0x120
v3: make sock_drop inline in skmsg.h
v2: init skb to null and fix a space/tab issue. Added Jakub's acks.
====================
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Diffstat (limited to 'include/linux')
| -rw-r--r-- | include/linux/skmsg.h | 54 |
1 files changed, 35 insertions, 19 deletions
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 96f319099744..14ab0c0bc924 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -285,11 +285,45 @@ static inline struct sk_psock *sk_psock(const struct sock *sk) return rcu_dereference_sk_user_data(sk); } +static inline void sk_psock_set_state(struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + set_bit(bit, &psock->state); +} + +static inline void sk_psock_clear_state(struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + clear_bit(bit, &psock->state); +} + +static inline bool sk_psock_test_state(const struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + return test_bit(bit, &psock->state); +} + +static inline void sock_drop(struct sock *sk, struct sk_buff *skb) +{ + sk_drops_add(sk, skb); + kfree_skb(skb); +} + +static inline void drop_sk_msg(struct sk_psock *psock, struct sk_msg *msg) +{ + if (msg->skb) + sock_drop(psock->sk, msg->skb); + kfree(msg); +} + static inline void sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { spin_lock_bh(&psock->ingress_lock); - list_add_tail(&msg->list, &psock->ingress_msg); + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + list_add_tail(&msg->list, &psock->ingress_msg); + else + drop_sk_msg(psock, msg); spin_unlock_bh(&psock->ingress_lock); } @@ -406,24 +440,6 @@ static inline void sk_psock_restore_proto(struct sock *sk, psock->psock_update_sk_prot(sk, psock, true); } -static inline void sk_psock_set_state(struct sk_psock *psock, - enum sk_psock_state_bits bit) -{ - set_bit(bit, &psock->state); -} - -static inline void sk_psock_clear_state(struct sk_psock *psock, - enum sk_psock_state_bits bit) -{ - clear_bit(bit, &psock->state); -} - -static inline bool sk_psock_test_state(const struct sk_psock *psock, - enum sk_psock_state_bits bit) -{ - return test_bit(bit, &psock->state); -} - static inline struct sk_psock *sk_psock_get(struct sock *sk) { struct sk_psock *psock; |
