From 58a63729c957621f1990c3494c702711188ca347 Mon Sep 17 00:00:00 2001 From: Long Li Date: Fri, 9 Aug 2024 08:58:58 -0700 Subject: net: mana: Fix doorbell out of order violation and avoid unnecessary doorbell rings After napi_complete_done() is called when NAPI is polling in the current process context, another NAPI may be scheduled and start running in softirq on another CPU and may ring the doorbell before the current CPU does. When combined with unnecessary rings when there is no need to arm the CQ, it triggers error paths in the hardware. This patch fixes this by calling napi_complete_done() after doorbell rings. It limits the number of unnecessary rings when there is no need to arm. MANA hardware specifies that there must be one doorbell ring every 8 CQ wraparounds. This driver guarantees one doorbell ring as soon as the number of consumed CQEs exceeds 4 CQ wraparounds. In practical workloads, the 4 CQ wraparounds proves to be big enough that it rarely exceeds this limit before all the napi weight is consumed. To implement this, add a per-CQ counter cq->work_done_since_doorbell, and make sure the CQ is armed as soon as passing 4 wraparounds of the CQ. Cc: stable@vger.kernel.org Fixes: e1b5683ff62e ("net: mana: Move NAPI from EQ to CQ") Reviewed-by: Haiyang Zhang Signed-off-by: Long Li Link: https://patch.msgid.link/1723219138-29887-1-git-send-email-longli@linuxonhyperv.com Signed-off-by: Paolo Abeni --- include/net/mana/mana.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 6439fd8b437b..7caa334f4888 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -275,6 +275,7 @@ struct mana_cq { /* NAPI data */ struct napi_struct napi; int work_done; + int work_done_since_doorbell; int budget; }; -- cgit v1.2.3 From 69139d2919dd4aa9a553c8245e7c63e82613e3fc Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sun, 11 Aug 2024 19:21:53 -0700 Subject: vsock: fix recursive ->recvmsg calls After a vsock socket has been added to a BPF sockmap, its prot->recvmsg has been replaced with vsock_bpf_recvmsg(). Thus the following recursiion could happen: vsock_bpf_recvmsg() -> __vsock_recvmsg() -> vsock_connectible_recvmsg() -> prot->recvmsg() -> vsock_bpf_recvmsg() again We need to fix it by calling the original ->recvmsg() without any BPF sockmap logic in __vsock_recvmsg(). Fixes: 634f1a7110b4 ("vsock: support sockmap") Reported-by: syzbot+bdb4bd87b5e22058e2a4@syzkaller.appspotmail.com Tested-by: syzbot+bdb4bd87b5e22058e2a4@syzkaller.appspotmail.com Cc: Bobby Eshleman Cc: Michael S. Tsirkin Cc: Stefano Garzarella Signed-off-by: Cong Wang Acked-by: Michael S. Tsirkin Link: https://patch.msgid.link/20240812022153.86512-1-xiyou.wangcong@gmail.com Signed-off-by: Paolo Abeni --- include/net/af_vsock.h | 4 ++++ net/vmw_vsock/af_vsock.c | 50 +++++++++++++++++++++++++++-------------------- net/vmw_vsock/vsock_bpf.c | 4 ++-- 3 files changed, 35 insertions(+), 23 deletions(-) (limited to 'include/net') diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 535701efc1e5..24d970f7a4fa 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -230,8 +230,12 @@ struct vsock_tap { int vsock_add_tap(struct vsock_tap *vt); int vsock_remove_tap(struct vsock_tap *vt); void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque); +int __vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags); int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); +int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags); int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 4b040285aa78..0ff9b2dd86ba 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1270,25 +1270,28 @@ out: return err; } +int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) +{ + struct sock *sk = sock->sk; + struct vsock_sock *vsk = vsock_sk(sk); + + return vsk->transport->dgram_dequeue(vsk, msg, len, flags); +} + int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { #ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; const struct proto *prot; -#endif - struct vsock_sock *vsk; - struct sock *sk; - sk = sock->sk; - vsk = vsock_sk(sk); - -#ifdef CONFIG_BPF_SYSCALL prot = READ_ONCE(sk->sk_prot); if (prot != &vsock_proto) return prot->recvmsg(sk, msg, len, flags, NULL); #endif - return vsk->transport->dgram_dequeue(vsk, msg, len, flags); + return __vsock_dgram_recvmsg(sock, msg, len, flags); } EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg); @@ -2174,15 +2177,12 @@ out: } int -vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +__vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; -#ifdef CONFIG_BPF_SYSCALL - const struct proto *prot; -#endif int err; sk = sock->sk; @@ -2233,14 +2233,6 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, goto out; } -#ifdef CONFIG_BPF_SYSCALL - prot = READ_ONCE(sk->sk_prot); - if (prot != &vsock_proto) { - release_sock(sk); - return prot->recvmsg(sk, msg, len, flags, NULL); - } -#endif - if (sk->sk_type == SOCK_STREAM) err = __vsock_stream_recvmsg(sk, msg, len, flags); else @@ -2250,6 +2242,22 @@ out: release_sock(sk); return err; } + +int +vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) +{ +#ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; + const struct proto *prot; + + prot = READ_ONCE(sk->sk_prot); + if (prot != &vsock_proto) + return prot->recvmsg(sk, msg, len, flags, NULL); +#endif + + return __vsock_connectible_recvmsg(sock, msg, len, flags); +} EXPORT_SYMBOL_GPL(vsock_connectible_recvmsg); static int vsock_set_rcvlowat(struct sock *sk, int val) diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index a3c97546ab84..c42c5cc18f32 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -64,9 +64,9 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int int err; if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) - err = vsock_connectible_recvmsg(sock, msg, len, flags); + err = __vsock_connectible_recvmsg(sock, msg, len, flags); else if (sk->sk_type == SOCK_DGRAM) - err = vsock_dgram_recvmsg(sock, msg, len, flags); + err = __vsock_dgram_recvmsg(sock, msg, len, flags); else err = -EPROTOTYPE; -- cgit v1.2.3