diff mbox series

[bpf,v4,3/4] net: implement ->sock_is_readable() for UDP and AF_UNIX

Message ID 20211008203306.37525-4-xiyou.wangcong@gmail.com (mailing list archive)
State Accepted
Delegated to: BPF
Headers show
Series sock_map: fix ->poll() and update selftests | expand

Checks

Context Check Description
netdev/cover_letter success Series has a cover letter
netdev/fixes_present fail Series targets non-next tree, but doesn't contain any Fixes tags
netdev/patch_count success Link
netdev/tree_selection success Clearly marked for bpf
netdev/subject_prefix success Link
netdev/cc_maintainers warning 16 maintainers not CCed: andrii@kernel.org christian.brauner@ubuntu.com Rao.Shoaib@oracle.com viro@zeniv.linux.org.uk edumazet@google.com kuniyu@amazon.co.jp songliubraving@fb.com yoshfuji@linux-ipv6.org yhs@fb.com davem@davemloft.net kafai@fb.com kuba@kernel.org jiang.wang@bytedance.com dsahern@kernel.org ast@kernel.org kpsingh@kernel.org
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/module_param success Was 0 now: 0
netdev/build_32bit success Errors and warnings before: 11 this patch: 11
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success No Fixes tag
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 46 lines checked
netdev/build_allmodconfig_warn success Errors and warnings before: 11 this patch: 11
netdev/header_inline success No static functions without inline keyword in header files
bpf/vmtest-bpf-PR success PR summary
bpf/vmtest-bpf success VM_Test

Commit Message

Cong Wang Oct. 8, 2021, 8:33 p.m. UTC 
From: Cong Wang <cong.wang@bytedance.com>

Yucong noticed we can't poll() sockets in sockmap even
when they are the destination sockets of redirections.
This is because we never poll any psock queues in ->poll(),
except for TCP. With ->sock_is_readable() now we can
overwrite >sock_is_readable(), invoke and implement it for
both UDP and AF_UNIX sockets.

Reported-by: Yucong Sun <sunyucong@gmail.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jakub Sitnicki <jakub@cloudflare.com>
Cc: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
---
 net/ipv4/udp.c      | 3 +++
 net/ipv4/udp_bpf.c  | 1 +
 net/unix/af_unix.c  | 4 ++++
 net/unix/unix_bpf.c | 2 ++
 4 files changed, 10 insertions(+)
diff mbox series

Patch

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8536b2a7210b..2fffcf2b54f3 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2867,6 +2867,9 @@  __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	    !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
 		mask &= ~(EPOLLIN | EPOLLRDNORM);
 
+	/* psock ingress_msg queue should not contain any bad checksum frames */
+	if (sk_is_readable(sk))
+		mask |= EPOLLIN | EPOLLRDNORM;
 	return mask;
 
 }
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 7a1d5f473878..bbe6569c9ad3 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -114,6 +114,7 @@  static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
 	*prot        = *base;
 	prot->close  = sock_map_close;
 	prot->recvmsg = udp_bpf_recvmsg;
+	prot->sock_is_readable = sk_msg_is_readable;
 }
 
 static void udp_bpf_check_v6_needs_rebuild(struct proto *ops)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 0878ab86597b..9e62d83ffd3e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -3052,6 +3052,8 @@  static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
 	/* readable? */
 	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
+	if (sk_is_readable(sk))
+		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* Connection-based need to check for termination and startup */
 	if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) &&
@@ -3091,6 +3093,8 @@  static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
 	/* readable? */
 	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
+	if (sk_is_readable(sk))
+		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* Connection-based need to check for termination and startup */
 	if (sk->sk_type == SOCK_SEQPACKET) {
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index b927e2baae50..452376c6f419 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -102,6 +102,7 @@  static void unix_dgram_bpf_rebuild_protos(struct proto *prot, const struct proto
 	*prot        = *base;
 	prot->close  = sock_map_close;
 	prot->recvmsg = unix_bpf_recvmsg;
+	prot->sock_is_readable = sk_msg_is_readable;
 }
 
 static void unix_stream_bpf_rebuild_protos(struct proto *prot,
@@ -110,6 +111,7 @@  static void unix_stream_bpf_rebuild_protos(struct proto *prot,
 	*prot        = *base;
 	prot->close  = sock_map_close;
 	prot->recvmsg = unix_bpf_recvmsg;
+	prot->sock_is_readable = sk_msg_is_readable;
 	prot->unhash  = sock_map_unhash;
 }