udp: fix busy polling

Generic sk_busy_loop_end() only looks at sk->sk_receive_queue
for presence of packets.

Problem is that for UDP sockets after blamed commit, some packets
could be present in another queue: udp_sk(sk)->reader_queue

In some cases, a busy poller could spin until timeout expiration,
even if some packets are available in udp_sk(sk)->reader_queue.

v3: - make sk_busy_loop_end() nicer (Willem)

v2: - add a READ_ONCE(sk->sk_family) in sk_is_inet() to avoid KCSAN splats.
    - add a sk_is_inet() check in sk_is_udp() (Willem feedback)
    - add a sk_is_inet() check in sk_is_tcp().

Fixes: 2276f58ac589 ("udp: use a separate rx queue for packet reception")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 888a4b217829fd4d6baf52f784ce35e9ad6bd0ed..e65ec3fd27998a5b82fc2c4597c575125e653056 100644 (file)
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -505,12 +505,6 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock)
        return !!psock->saved_data_ready;
 }
 
-static inline bool sk_is_udp(const struct sock *sk)
-{
-       return sk->sk_type == SOCK_DGRAM &&
-              sk->sk_protocol == IPPROTO_UDP;
-}
-
 #if IS_ENABLED(CONFIG_NET_SOCK_MSG)
 
 #define BPF_F_STRPARSER        (1UL << 1)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index aa86453f6b9ba367f772570a7b783bb098be6236..d94c242eb3ed20b2c5b2e5ceea3953cf96341fb7 100644 (file)
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -307,11 +307,6 @@ static inline unsigned long inet_cmsg_flags(const struct inet_sock *inet)
 #define inet_assign_bit(nr, sk, val)           \
        assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val)
 
-static inline bool sk_is_inet(struct sock *sk)
-{
-       return sk->sk_family == AF_INET || sk->sk_family == AF_INET6;
-}
-
 /**
  * sk_to_full_sk - Access to a full socket
  * @sk: pointer to a socket

diff --git a/include/net/sock.h b/include/net/sock.h
index a7f815c7cfdfdf1296be2967fd100efdb10cdd63..54ca8dcbfb4335d657b5cea323aa7d8c4316d49e 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2765,9 +2765,25 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags)
                           &skb_shinfo(skb)->tskey);
 }
 
+static inline bool sk_is_inet(const struct sock *sk)
+{
+       int family = READ_ONCE(sk->sk_family);
+
+       return family == AF_INET || family == AF_INET6;
+}
+
 static inline bool sk_is_tcp(const struct sock *sk)
 {
-       return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP;
+       return sk_is_inet(sk) &&
+              sk->sk_type == SOCK_STREAM &&
+              sk->sk_protocol == IPPROTO_TCP;
+}
+
+static inline bool sk_is_udp(const struct sock *sk)
+{
+       return sk_is_inet(sk) &&
+              sk->sk_type == SOCK_DGRAM &&
+              sk->sk_protocol == IPPROTO_UDP;
 }
 
 static inline bool sk_is_stream_unix(const struct sock *sk)

diff --git a/net/core/sock.c b/net/core/sock.c
index 158dbdebce6a3693deb63e557e856d9cdd7500ae..0a7f46c37f0cfc169e11377107c8342c229da0de 100644 (file)
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -107,6 +107,7 @@
 #include <linux/interrupt.h>
 #include <linux/poll.h>
 #include <linux/tcp.h>
+#include <linux/udp.h>
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/user_namespace.h>
@@ -4144,8 +4145,14 @@ bool sk_busy_loop_end(void *p, unsigned long start_time)
 {
        struct sock *sk = p;
 
-       return !skb_queue_empty_lockless(&sk->sk_receive_queue) ||
-              sk_busy_loop_timeout(sk, start_time);
+       if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
+               return true;
+
+       if (sk_is_udp(sk) &&
+           !skb_queue_empty_lockless(&udp_sk(sk)->reader_queue))
+               return true;
+
+       return sk_busy_loop_timeout(sk, start_time);
 }
 EXPORT_SYMBOL(sk_busy_loop_end);
 #endif /* CONFIG_NET_RX_BUSY_POLL */