Re: [PATCH 2/2] net/sock: Propagate WF_SYNC only when requested

Shrikanth Hegde <[email protected]> Tue, 21 Jul 2026 10:20:03 +0530
Newsgroups	org.kernel.vger.linux-sctp,org.kernel.vger.linux-kernel,org.kernel.vger.netdev
Message-ID	<[email protected]>
Hi Srikar,

On 7/14/26 7:09 AM, Srikar Dronamraju wrote:
> Use SOCK_SYNC_WAKEUP to select between synchronous and asynchronous wakeup
> wakeup APIs. This avoids propagating WF_SYNC when no blocking waiter is
> expected. All wakeup locations in networking code that currently issue
> synchronous poll-style wakeups unconditionally are updated.
> 

You can also add the performance data in the cover-letter to this patch.

> Signed-off-by: Srikar Dronamraju <[email protected]>
> ---
>   net/core/sock.c    | 31 ++++++++++++++++++++++++-------
>   net/sctp/socket.c  | 10 ++++++++--
>   net/smc/af_smc.c   |  4 ++--
>   net/smc/smc_rx.c   | 10 ++++++++--
>   net/tipc/socket.c  | 22 +++++++++++++++++-----
>   net/unix/af_unix.c | 26 ++++++++++++++++++--------
>   6 files changed, 77 insertions(+), 26 deletions(-)
> 
> diff --git a/net/core/sock.c b/net/core/sock.c
> index 8a59bfaa8096..a214e883b14b 100644
> --- a/net/core/sock.c
> +++ b/net/core/sock.c
> @@ -3652,9 +3652,15 @@ void sock_def_readable(struct sock *sk)
>   
>   	rcu_read_lock();
>   	wq = rcu_dereference(sk->sk_wq);
> -	if (skwq_has_sleeper(wq))
> -		wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI |
> +	if (skwq_has_sleeper(wq)) {
> +		if (sock_flag(sk, SOCK_SYNC_WAKEUP)) {
> +			wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI |
> +						EPOLLRDNORM | EPOLLRDBAND);
> +		} else {
> +			wake_up_interruptible_poll(&wq->wait, EPOLLIN | EPOLLPRI |
>   						EPOLLRDNORM | EPOLLRDBAND);
> +		}
> +	}
>   	sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN);
>   	rcu_read_unlock();
>   }
> @@ -3670,9 +3676,15 @@ static void sock_def_write_space(struct sock *sk)
>   	 */
>   	if (sock_writeable(sk)) {
>   		wq = rcu_dereference(sk->sk_wq);
> -		if (skwq_has_sleeper(wq))
> -			wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
> +		if (skwq_has_sleeper(wq)) {
> +			if (sock_flag(sk, SOCK_SYNC_WAKEUP)) {
> +				wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
> +						EPOLLWRNORM | EPOLLWRBAND);
> +			} else {
> +				wake_up_interruptible_poll(&wq->wait, EPOLLOUT |
>   						EPOLLWRNORM | EPOLLWRBAND);
> +			}
> +		}
>   
>   		/* Should agree with poll, otherwise some programs break */
>   		sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT);
> @@ -3695,10 +3707,15 @@ static void sock_def_write_space_wfree(struct sock *sk, int wmem_alloc)
>   
>   		/* rely on refcount_sub from sock_wfree() */
>   		smp_mb__after_atomic();
> -		if (wq && waitqueue_active(&wq->wait))
> -			wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
> +		if (wq && waitqueue_active(&wq->wait)) {
> +			if (sock_flag(sk, SOCK_SYNC_WAKEUP)) {
> +				wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
>   						EPOLLWRNORM | EPOLLWRBAND);
> -
> +			} else {
> +				wake_up_interruptible_poll(&wq->wait, EPOLLOUT |
> +						EPOLLWRNORM | EPOLLWRBAND);
> +			}
> +		}
>   		/* Should agree with poll, otherwise some programs break */
>   		sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT);
>   	}
> diff --git a/net/sctp/socket.c b/net/sctp/socket.c
> index c7b9e325ec1c..9cb3432f065a 100644
> --- a/net/sctp/socket.c
> +++ b/net/sctp/socket.c
> @@ -9348,9 +9348,15 @@ void sctp_data_ready(struct sock *sk)
>   
>   	rcu_read_lock();
>   	wq = rcu_dereference(sk->sk_wq);
> -	if (skwq_has_sleeper(wq))
> -		wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN |
> +	if (skwq_has_sleeper(wq)) {
> +		if (sock_flag(sk, SOCK_SYNC_WAKEUP)) {
> +			wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN |
> +					EPOLLRDNORM | EPOLLRDBAND);
> +		} else {
> +			wake_up_interruptible_poll(&wq->wait, EPOLLIN |
>   						EPOLLRDNORM | EPOLLRDBAND);
> +		}
> +	}
>   	sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN);
>   	rcu_read_unlock();
>   }
> diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
> index b5db69073e20..1a6ea2e30769 100644
> --- a/net/smc/af_smc.c
> +++ b/net/smc/af_smc.c
> @@ -819,10 +819,10 @@ static void smc_fback_wakeup_waitqueue(struct smc_sock *smc, void *key)
>   		wake_up_interruptible_all(&wq->wait);
>   	} else {
>   		flags = key_to_poll(key);
> -		if (flags & (EPOLLIN | EPOLLOUT))
> +		if (flags & (EPOLLIN | EPOLLOUT) && sock_flag(&smc->sk, SOCK_SYNC_WAKEUP))
>   			/* sk_data_ready or sk_write_space */
>   			wake_up_interruptible_sync_poll(&wq->wait, flags);
> -		else if (flags & EPOLLERR)
> +		else
>   			/* sk_error_report */
>   			wake_up_interruptible_poll(&wq->wait, flags);
>   	}
> diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
> index c1d9b923938d..4e288a2364d2 100644
> --- a/net/smc/smc_rx.c
> +++ b/net/smc/smc_rx.c
> @@ -39,9 +39,15 @@ static void smc_rx_wake_up(struct sock *sk)
>   	/* called already in smc_listen_work() */
>   	rcu_read_lock();
>   	wq = rcu_dereference(sk->sk_wq);
> -	if (skwq_has_sleeper(wq))
> -		wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI |
> +	if (skwq_has_sleeper(wq)) {
> +		if (sock_flag(sk, SOCK_SYNC_WAKEUP)) {
> +			wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI |
>   						EPOLLRDNORM | EPOLLRDBAND);
> +		} else {
> +			wake_up_interruptible_poll(&wq->wait, EPOLLIN | EPOLLPRI |
> +						EPOLLRDNORM | EPOLLRDBAND);
> +		}
> +	}
>   	sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN);
>   	if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
>   	    (sk->sk_state == SMC_CLOSED))
> diff --git a/net/tipc/socket.c b/net/tipc/socket.c
> index e564341e0216..9fa83a89882c 100644
> --- a/net/tipc/socket.c
> +++ b/net/tipc/socket.c
> @@ -2116,9 +2116,15 @@ static void tipc_write_space(struct sock *sk)
>   
>   	rcu_read_lock();
>   	wq = rcu_dereference(sk->sk_wq);
> -	if (skwq_has_sleeper(wq))
> -		wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
> +	if (skwq_has_sleeper(wq)) {
> +		if (sock_flag(sk, SOCK_SYNC_WAKEUP)) {
> +			wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
>   						EPOLLWRNORM | EPOLLWRBAND);
> +		} else {
> +			wake_up_interruptible_poll(&wq->wait, EPOLLOUT |
> +						EPOLLWRNORM | EPOLLWRBAND);
> +		}
> +	}
>   	rcu_read_unlock();
>   }
>   
> @@ -2134,9 +2140,15 @@ static void tipc_data_ready(struct sock *sk)
>   
>   	rcu_read_lock();
>   	wq = rcu_dereference(sk->sk_wq);
> -	if (skwq_has_sleeper(wq))
> -		wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN |
> -						EPOLLRDNORM | EPOLLRDBAND);
> +	if (skwq_has_sleeper(wq)) {
> +		if (sock_flag(sk, SOCK_SYNC_WAKEUP)) {
> +			wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN |
> +							EPOLLRDNORM | EPOLLRDBAND);
> +		} else {
> +			wake_up_interruptible_poll(&wq->wait, EPOLLIN |
> +							EPOLLRDNORM | EPOLLRDBAND);
> +		}
> +	}
>   	rcu_read_unlock();
>   }
>   
> diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
> index f7a9d55eee8a..15ebcc2d9d58 100644
> --- a/net/unix/af_unix.c
> +++ b/net/unix/af_unix.c
> @@ -601,9 +601,15 @@ static void unix_write_space(struct sock *sk)
>   	rcu_read_lock();
>   	if (unix_writable(sk, READ_ONCE(sk->sk_state))) {
>   		wq = rcu_dereference(sk->sk_wq);
> -		if (skwq_has_sleeper(wq))
> -			wake_up_interruptible_sync_poll(&wq->wait,
> -				EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND);
> +		if (skwq_has_sleeper(wq)) {
> +			if (sock_flag(sk, SOCK_SYNC_WAKEUP)) {
> +				wake_up_interruptible_sync_poll(&wq->wait,
> +					EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND);
> +			} else {
> +				wake_up_interruptible_poll(&wq->wait,
> +					EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND);
> +			}
> +		}
>   		sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT);
>   	}
>   	rcu_read_unlock();
> @@ -2603,11 +2609,15 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
>   		goto out;
>   	}
>   
> -	if (wq_has_sleeper(&u->peer_wait))
> -		wake_up_interruptible_sync_poll(&u->peer_wait,
> -						EPOLLOUT | EPOLLWRNORM |
> -						EPOLLWRBAND);
> -
> +	if (wq_has_sleeper(&u->peer_wait)) {
> +		if (sock_flag(sk, SOCK_SYNC_WAKEUP)) {
> +			wake_up_interruptible_sync_poll(&u->peer_wait,
> +						EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND);
> +		} else {
> +			wake_up_interruptible_poll(&u->peer_wait,
> +						EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND);
> +		}
> +	}
>   	if (msg->msg_name) {
>   		unix_copy_addr(msg, skb->sk);
>   


Would it make sense to write a macro or a wrapper function do the
same instead of sprinkling the same at all the places?

similar comment for patch 1.

IMHO, it would make it easier to read.