This is a note to let you know that I've just added the patch titled
bpf, sockmap: Fix sk->sk_forward_alloc warn_on in sk_stream_kill_queues
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
bpf-sockmap-fix-sk-sk_forward_alloc-warn_on-in-sk_st.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 62e6bcf550edf137dbf06b1977338bcc9bf1524c
Author: Wang Yufen <wangyufen@xxxxxxxxxx>
Date: Tue May 24 15:53:11 2022 +0800
bpf, sockmap: Fix sk->sk_forward_alloc warn_on in sk_stream_kill_queues
[ Upstream commit d8616ee2affcff37c5d315310da557a694a3303d ]
During TCP sockmap redirect pressure test, the following warning is triggered:
WARNING: CPU: 3 PID: 2145 at net/core/stream.c:205 sk_stream_kill_queues+0xbc/0xd0
CPU: 3 PID: 2145 Comm: iperf Kdump: loaded Tainted: G W 5.10.0+ #9
Call Trace:
inet_csk_destroy_sock+0x55/0x110
inet_csk_listen_stop+0xbb/0x380
tcp_close+0x41b/0x480
inet_release+0x42/0x80
__sock_release+0x3d/0xa0
sock_close+0x11/0x20
__fput+0x9d/0x240
task_work_run+0x62/0x90
exit_to_user_mode_prepare+0x110/0x120
syscall_exit_to_user_mode+0x27/0x190
entry_SYSCALL_64_after_hwframe+0x44/0xa9
The reason we observed is that:
When the listener is closing, a connection may have completed the three-way
handshake but not accepted, and the client has sent some packets. The child
sks in accept queue release by inet_child_forget()->inet_csk_destroy_sock(),
but psocks of child sks have not released.
To fix, add sock_map_destroy to release psocks.
Signed-off-by: Wang Yufen <wangyufen@xxxxxxxxxx>
Signed-off-by: Daniel Borkmann <daniel@xxxxxxxxxxxxx>
Signed-off-by: Andrii Nakryiko <andrii@xxxxxxxxxx>
Acked-by: Jakub Sitnicki <jakub@xxxxxxxxxxxxxx>
Acked-by: John Fastabend <john.fastabend@xxxxxxxxx>
Link: https://lore.kernel.org/bpf/20220524075311.649153-1-wangyufen@xxxxxxxxxx
Stable-dep-of: 8bbabb3fddcd ("bpf, sock_map: Move cancel_work_sync() out of sock lock")
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 818cd594e922..84efd8dd139d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2022,6 +2022,7 @@ int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog);
int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags);
void sock_map_unhash(struct sock *sk);
+void sock_map_destroy(struct sock *sk);
void sock_map_close(struct sock *sk, long timeout);
#else
static inline int bpf_prog_offload_init(struct bpf_prog *prog,
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 0c742cdf413c..ee7c67d8442d 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -96,6 +96,7 @@ struct sk_psock {
spinlock_t link_lock;
refcount_t refcnt;
void (*saved_unhash)(struct sock *sk);
+ void (*saved_destroy)(struct sock *sk);
void (*saved_close)(struct sock *sk, long timeout);
void (*saved_write_space)(struct sock *sk);
void (*saved_data_ready)(struct sock *sk);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 736d8b035a67..680f51f8974a 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -720,6 +720,7 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
psock->eval = __SK_NONE;
psock->sk_proto = prot;
psock->saved_unhash = prot->unhash;
+ psock->saved_destroy = prot->destroy;
psock->saved_close = prot->close;
psock->saved_write_space = sk->sk_write_space;
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 795b3acfb9fd..43563d651ed0 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -1524,6 +1524,29 @@ void sock_map_unhash(struct sock *sk)
}
EXPORT_SYMBOL_GPL(sock_map_unhash);
+void sock_map_destroy(struct sock *sk)
+{
+ void (*saved_destroy)(struct sock *sk);
+ struct sk_psock *psock;
+
+ rcu_read_lock();
+ psock = sk_psock_get(sk);
+ if (unlikely(!psock)) {
+ rcu_read_unlock();
+ if (sk->sk_prot->destroy)
+ sk->sk_prot->destroy(sk);
+ return;
+ }
+
+ saved_destroy = psock->saved_destroy;
+ sock_map_remove_links(sk, psock);
+ rcu_read_unlock();
+ sk_psock_stop(psock, true);
+ sk_psock_put(sk, psock);
+ saved_destroy(sk);
+}
+EXPORT_SYMBOL_GPL(sock_map_destroy);
+
void sock_map_close(struct sock *sk, long timeout)
{
void (*saved_close)(struct sock *sk, long timeout);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 72892ebe9607..5194c6870273 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -543,6 +543,7 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
struct proto *base)
{
prot[TCP_BPF_BASE] = *base;
+ prot[TCP_BPF_BASE].destroy = sock_map_destroy;
prot[TCP_BPF_BASE].close = sock_map_close;
prot[TCP_BPF_BASE].recvmsg = tcp_bpf_recvmsg;
prot[TCP_BPF_BASE].sock_is_readable = sk_msg_is_readable;
