From 343597d558e79fe704ba8846b5b2ed24056b89c2 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 27 Jul 2021 09:04:58 -0700 Subject: bpf, sockmap: Zap ingress queues after stopping strparser We don't want strparser to run and pass skbs into skmsg handlers when the psock is null. We just sk_drop them in this case. When removing a live socket from map it means extra drops that we do not need to incur. Move the zap below strparser close to avoid this condition. This way we stop the stream parser first stopping it from processing packets and then delete the psock. Fixes: a136678c0bdbb ("bpf: sk_msg, zap ingress queue on psock down") Signed-off-by: John Fastabend Signed-off-by: Andrii Nakryiko Acked-by: Jakub Sitnicki Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210727160500.1713554-2-john.fastabend@gmail.com --- net/core/skmsg.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 15d71288e741..28115ef742e8 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -773,8 +773,6 @@ static void sk_psock_destroy(struct work_struct *work) void sk_psock_drop(struct sock *sk, struct sk_psock *psock) { - sk_psock_stop(psock, false); - write_lock_bh(&sk->sk_callback_lock); sk_psock_restore_proto(sk, psock); rcu_assign_sk_user_data(sk, NULL); @@ -784,6 +782,8 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock) sk_psock_stop_verdict(sk, psock); write_unlock_bh(&sk->sk_callback_lock); + sk_psock_stop(psock, false); + INIT_RCU_WORK(&psock->rwork, sk_psock_destroy); queue_rcu_work(system_wq, &psock->rwork); } -- cgit v1.2.3 From 476d98018f32e68e7c5d4e8456940cf2b6d66f10 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 27 Jul 2021 09:04:59 -0700 Subject: bpf, sockmap: On cleanup we additionally need to remove cached skb Its possible if a socket is closed and the receive thread is under memory pressure it may have cached a skb. We need to ensure these skbs are free'd along with the normal ingress_skb queue. Before 799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()") tear down and backlog processing both had sock_lock for the common case of socket close or unhash. So it was not possible to have both running in parrallel so all we would need is the kfree in those kernels. But, latest kernels include the commit 799aa7f98d5e and this requires a bit more work. Without the ingress_lock guarding reading/writing the state->skb case its possible the tear down could run before the state update causing it to leak memory or worse when the backlog reads the state it could potentially run interleaved with the tear down and we might end up free'ing the state->skb from tear down side but already have the reference from backlog side. To resolve such races we wrap accesses in ingress_lock on both sides serializing tear down and backlog case. In both cases this only happens after an EAGAIN error case so having an extra lock in place is likely fine. The normal path will skip the locks. Note, we check state->skb before grabbing lock. This works because we can only enqueue with the mutex we hold already. Avoiding a race on adding state->skb after the check. And if tear down path is running that is also fine if the tear down path then removes state->skb we will simply set skb=NULL and the subsequent goto is skipped. This slight complication avoids locking in normal case. With this fix we no longer see this warning splat from tcp side on socket close when we hit the above case with redirect to ingress self. [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 [224913.936083] sock_close+0x14/0x20 Fixes: a136678c0bdbb ("bpf: sk_msg, zap ingress queue on psock down") Signed-off-by: John Fastabend Signed-off-by: Andrii Nakryiko Acked-by: Jakub Sitnicki Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210727160500.1713554-3-john.fastabend@gmail.com --- net/core/skmsg.c | 35 +++++++++++++++++++++++++++++------ 1 file changed, 29 insertions(+), 6 deletions(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 28115ef742e8..036cdb33a94a 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -590,23 +590,42 @@ static void sock_drop(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); } +static void sk_psock_skb_state(struct sk_psock *psock, + struct sk_psock_work_state *state, + struct sk_buff *skb, + int len, int off) +{ + spin_lock_bh(&psock->ingress_lock); + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { + state->skb = skb; + state->len = len; + state->off = off; + } else { + sock_drop(psock->sk, skb); + } + spin_unlock_bh(&psock->ingress_lock); +} + static void sk_psock_backlog(struct work_struct *work) { struct sk_psock *psock = container_of(work, struct sk_psock, work); struct sk_psock_work_state *state = &psock->work_state; - struct sk_buff *skb; + struct sk_buff *skb = NULL; bool ingress; u32 len, off; int ret; mutex_lock(&psock->work_mutex); - if (state->skb) { + if (unlikely(state->skb)) { + spin_lock_bh(&psock->ingress_lock); skb = state->skb; len = state->len; off = state->off; state->skb = NULL; - goto start; + spin_unlock_bh(&psock->ingress_lock); } + if (skb) + goto start; while ((skb = skb_dequeue(&psock->ingress_skb))) { len = skb->len; @@ -621,9 +640,8 @@ start: len, ingress); if (ret <= 0) { if (ret == -EAGAIN) { - state->skb = skb; - state->len = len; - state->off = off; + sk_psock_skb_state(psock, state, skb, + len, off); goto end; } /* Hard errors break pipe and stop xmit. */ @@ -722,6 +740,11 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock) skb_bpf_redirect_clear(skb); sock_drop(psock->sk, skb); } + kfree_skb(psock->work_state.skb); + /* We null the skb here to ensure that calls to sk_psock_backlog + * do not pick up the free'd skb. + */ + psock->work_state.skb = NULL; __sk_psock_purge_ingress_msg(psock); } -- cgit v1.2.3 From 9635720b7c88592214562cb72605bdab6708006c Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 27 Jul 2021 09:05:00 -0700 Subject: bpf, sockmap: Fix memleak on ingress msg enqueue If backlog handler is running during a tear down operation we may enqueue data on the ingress msg queue while tear down is trying to free it. sk_psock_backlog() sk_psock_handle_skb() skb_psock_skb_ingress() sk_psock_skb_ingress_enqueue() sk_psock_queue_msg(psock,msg) spin_lock(ingress_lock) sk_psock_zap_ingress() _sk_psock_purge_ingerss_msg() _sk_psock_purge_ingress_msg() -- free ingress_msg list -- spin_unlock(ingress_lock) spin_lock(ingress_lock) list_add_tail(msg,ingress_msg) <- entry on list with no one left to free it. spin_unlock(ingress_lock) To fix we only enqueue from backlog if the ENABLED bit is set. The tear down logic clears the bit with ingress_lock set so we wont enqueue the msg in the last step. Fixes: 799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()") Signed-off-by: John Fastabend Signed-off-by: Andrii Nakryiko Acked-by: Jakub Sitnicki Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210727160500.1713554-4-john.fastabend@gmail.com --- include/linux/skmsg.h | 54 +++++++++++++++++++++++++++++++++------------------ net/core/skmsg.c | 6 ------ 2 files changed, 35 insertions(+), 25 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; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 036cdb33a94a..2d6249b28928 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -584,12 +584,6 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, return sk_psock_skb_ingress(psock, skb); } -static void sock_drop(struct sock *sk, struct sk_buff *skb) -{ - sk_drops_add(sk, skb); - kfree_skb(skb); -} - static void sk_psock_skb_state(struct sk_psock *psock, struct sk_psock_work_state *state, struct sk_buff *skb, -- cgit v1.2.3