net: avoid unconditionally touching sk_tsflags on RX

After commit 5d4cc87414c5 ("net: reorganize "struct sock" fields"),
the sk_tsflags field shares the same cacheline with sk_forward_alloc.

The UDP protocol does not acquire the sock lock in the RX path;
forward allocations are protected via the receive queue spinlock;
additionally udp_recvmsg() calls sock_recv_cmsgs() unconditionally
touching sk_tsflags on each packet reception.

Due to the above, under high packet rate traffic, when the BH and the
user-space process run on different CPUs, UDP packet reception
experiences a cache miss while accessing sk_tsflags.

The receive path doesn't strictly need to access the problematic field;
change sock_set_timestamping() to maintain the relevant information
in a newly allocated sk_flags bit, so that sock_recv_cmsgs() can
take decisions accessing the latter field only.

With this patch applied, on an AMD epic server with i40e NICs, I
measured a 10% performance improvement for small packets UDP flood
performance tests - possibly a larger delta could be observed with more
recent H/W.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/dbd18c8a1171549f8249ac5a8b30b1b5ec88a425.1739294057.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/net/sock.h b/include/net/sock.h
index 8036b3b79cd8be64550dcfd6ce213039460acb1f..60ebf3c7b229e257b164e0de1f56543ea69f38f3 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -954,6 +954,7 @@ enum sock_flags {
        SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */
        SOCK_RCVMARK, /* Receive SO_MARK  ancillary data with packet */
        SOCK_RCVPRIORITY, /* Receive SO_PRIORITY ancillary data with packet */
+       SOCK_TIMESTAMPING_ANY, /* Copy of sk_tsflags & TSFLAGS_ANY */
 };
 
 #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
@@ -2664,13 +2665,13 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
 {
 #define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL)                       | \
                           (1UL << SOCK_RCVTSTAMP)                      | \
-                          (1UL << SOCK_RCVMARK)                        |\
-                          (1UL << SOCK_RCVPRIORITY))
+                          (1UL << SOCK_RCVMARK)                        | \
+                          (1UL << SOCK_RCVPRIORITY)                    | \
+                          (1UL << SOCK_TIMESTAMPING_ANY))
 #define TSFLAGS_ANY      (SOF_TIMESTAMPING_SOFTWARE                    | \
                           SOF_TIMESTAMPING_RAW_HARDWARE)
 
-       if (sk->sk_flags & FLAGS_RECV_CMSGS ||
-           READ_ONCE(sk->sk_tsflags) & TSFLAGS_ANY)
+       if (READ_ONCE(sk->sk_flags) & FLAGS_RECV_CMSGS)
                __sock_recv_cmsgs(msg, sk, skb);
        else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
                sock_write_timestamp(sk, skb->tstamp);

diff --git a/net/core/sock.c b/net/core/sock.c
index eae2ae70a2e03df370d8ef7750a7bb13cc3b8d8f..a197f0a0b8788590f33ba0dda0528b03dc087497 100644 (file)
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -938,6 +938,7 @@ int sock_set_timestamping(struct sock *sk, int optname,
 
        WRITE_ONCE(sk->sk_tsflags, val);
        sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);
+       sock_valbool_flag(sk, SOCK_TIMESTAMPING_ANY, !!(val & TSFLAGS_ANY));
 
        if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
                sock_enable_timestamp(sk,