net: group sk_backlog and sk_receive_queue

UDP receivers suffer from sk_rmem_alloc updates,
currently sharing a cache line with fields that
need to be read-mostly (sock_read_rx group):

1) RFS enabled hosts read sk_napi_id
from __udpv6_queue_rcv_skb().

2) sk->sk_rcvbuf is read from __udp_enqueue_schedule_skb()

/* --- cacheline 3 boundary (192 bytes) --- */
struct {
    atomic_t           rmem_alloc;           /*  0xc0   0x4 */   // Oops
    int                len;                  /*  0xc4   0x4 */
    struct sk_buff *   head;                 /*  0xc8   0x8 */
    struct sk_buff *   tail;                 /*  0xd0   0x8 */
} sk_backlog;                                /*  0xc0  0x18 */
__u8                       __cacheline_group_end__sock_write_rx[0]; /*  0xd8     0 */
__u8                       __cacheline_group_begin__sock_read_rx[0]; /*  0xd8     0 */
struct dst_entry *         sk_rx_dst;        /*  0xd8   0x8 */
int                        sk_rx_dst_ifindex;/*  0xe0   0x4 */
u32                        sk_rx_dst_cookie; /*  0xe4   0x4 */
unsigned int               sk_ll_usec;       /*  0xe8   0x4 */
unsigned int               sk_napi_id;       /*  0xec   0x4 */
u16                        sk_busy_poll_budget;/*  0xf0   0x2 */
u8                         sk_prefer_busy_poll;/*  0xf2   0x1 */
u8                         sk_userlocks;     /*  0xf3   0x1 */
int                        sk_rcvbuf;        /*  0xf4   0x4 */
struct sk_filter *         sk_filter;        /*  0xf8   0x8 */

Move sk_error (which is less often dirtied) there.

Alternative would be to cache align sock_read_rx but
this has more implications/risks.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250916160951.541279-8-edumazet@google.com
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

diff --git a/include/net/sock.h b/include/net/sock.h
index 0fd465935334160eeda7c1ea608f5d6161f02cb1..867dc44140d4c1b56ecfab1220c81133fe0394a0 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -394,7 +394,6 @@ struct sock {
 
        atomic_t                sk_drops;
        __s32                   sk_peek_off;
-       struct sk_buff_head     sk_error_queue;
        struct sk_buff_head     sk_receive_queue;
        /*
         * The backlog queue is special, it is always used with
@@ -412,6 +411,7 @@ struct sock {
        } sk_backlog;
 #define sk_rmem_alloc sk_backlog.rmem_alloc
 
+       struct sk_buff_head     sk_error_queue;
        __cacheline_group_end(sock_write_rx);
 
        __cacheline_group_begin(sock_read_rx);