Re: [PATCH] net: use sync wakeups for socket error reports

[Breno Leitao]

On Wed, Jul 08, 2026 at 06:32:02PM +0200, Eric Dumazet wrote:

> Perhaps this SYNC heuristic should be a per-socket choice so that
> applications can decide what is best for them.

Something like this?

    net: add SO_ERR_WAKE_SYNC for sync error-report wakeups
    
    sock_def_error_report() wakes EPOLLERR waiters with
    wake_up_interruptible_poll(), while sock_def_readable() and
    sock_def_write_space() already pass the sync hint. A socket with
    SO_TIMESTAMPING enabled delivers every TX and ACK timestamp through
    sk_error_queue and raises EPOLLERR, so the error path wakes a sleeping
    consumer very often.
    
    Without the sync hint the scheduler often places the woken consumer on a
    remote CPU, which costs a rescheduling IPI. Usama Arif measured 16,326
    such IPIs/min on a 176-core host running a production workload with
    SO_TIMESTAMPING enabled. [1]
    
    Switching the error path to a sync wakeup unconditionally is not the
    right fix, as there are different requirements for it to be async, see
    [2].
    
    Eric suggested that an options is to add SO_ERR_WAKE_SYNC so
    applications choose per socket, so a consumer draining a high-rate error
    queue can opt in to keep the wakeup local and drop the IPI, using socket
    flag SO_ERR_WAKE_SYNC.
    
    Link: https://lore.kernel.org/all/CANn89iLc1Bv_wmKvr_9mtGRM3gL7kgoy2Prr2SgtHY4C=ZgfBg@xxxxxxxxxxxxxx/ [1]
    Link: https://lore.kernel.org/netdev/20260526063650.952-1-xuewen.yan@xxxxxxxxxx/ [2]
    Suggested-by: Eric Dumazet <edumazet@xxxxxxxxxx>
    Signed-off-by: Breno Leitao <leitao@xxxxxxxxxx>

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index 5ef57f88df6b3..2a3c27aaf4e95 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -155,6 +155,8 @@
 #define SO_INQ			84
 #define SCM_INQ			SO_INQ
 
+#define SO_ERR_WAKE_SYNC	85
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 72fb1b006da93..00f31c74a63df 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -166,6 +166,8 @@
 #define SO_INQ			84
 #define SCM_INQ			SO_INQ
 
+#define SO_ERR_WAKE_SYNC	85
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index c16ec36dfee6b..db5b6cad17d49 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -147,6 +147,8 @@
 #define SO_INQ			0x4052
 #define SCM_INQ			SO_INQ
 
+#define SO_ERR_WAKE_SYNC	0x4053
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 71befa109e1cf..5e9ff3634265c 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -148,6 +148,8 @@
 #define SO_INQ                   0x005d
 #define SCM_INQ                  SO_INQ
 
+#define SO_ERR_WAKE_SYNC         0x005e
+
 #if !defined(__KERNEL__)
 
 
diff --git a/include/net/sock.h b/include/net/sock.h
index 51185222aac29..d8ee1dae8ecaf 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1022,6 +1022,7 @@ enum sock_flags {
 	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 */
+	SOCK_ERR_WAKE_SYNC, /* Sync wakeup on error report, %SO_ERR_WAKE_SYNC */
 };
 
 #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 53b5a8c002b1e..5527c9318b40e 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -150,6 +150,8 @@
 #define SO_INQ			84
 #define SCM_INQ			SO_INQ
 
+#define SO_ERR_WAKE_SYNC	85
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
diff --git a/net/core/sock.c b/net/core/sock.c
index 498a57f34f5b5..59caab6a7223a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1557,6 +1557,10 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 		sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool);
 		break;
 
+	case SO_ERR_WAKE_SYNC:
+		sock_valbool_flag(sk, SOCK_ERR_WAKE_SYNC, valbool);
+		break;
+
 	case SO_PASSCRED:
 		if (sk_may_scm_recv(sk))
 			sk->sk_scm_credentials = valbool;
@@ -2064,6 +2068,10 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE);
 		break;
 
+	case SO_ERR_WAKE_SYNC:
+		v.val = sock_flag(sk, SOCK_ERR_WAKE_SYNC);
+		break;
+
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	case SO_BUSY_POLL:
 		v.val = READ_ONCE(sk->sk_ll_usec);
@@ -3641,8 +3649,12 @@ static void sock_def_error_report(struct sock *sk)
 
 	rcu_read_lock();
 	wq = rcu_dereference(sk->sk_wq);
-	if (skwq_has_sleeper(wq))
-		wake_up_interruptible_poll(&wq->wait, EPOLLERR);
+	if (skwq_has_sleeper(wq)) {
+		if (sock_flag(sk, SOCK_ERR_WAKE_SYNC))
+			wake_up_interruptible_sync_poll(&wq->wait, EPOLLERR);
+		else
+			wake_up_interruptible_poll(&wq->wait, EPOLLERR);
+	}
 	sk_wake_async_rcu(sk, SOCK_WAKE_IO, POLL_ERR);
 	rcu_read_unlock();
 }