netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH net v2] rds: introduce acquire/release ordering in acquire/release_in_xmit()
@ 2024-03-15  9:28 Yewon Choi
  2024-03-15 13:32 ` Michal Kubiak
  2024-03-19 11:30 ` patchwork-bot+netdevbpf
  0 siblings, 2 replies; 3+ messages in thread
From: Yewon Choi @ 2024-03-15  9:28 UTC (permalink / raw)
  To: Allison Henderson, David S. Miller, Eric Dumazet, Jakub Kicinski,
	Paolo Abeni, netdev, linux-rdma, rds-devel, linux-kernel
  Cc: Dae R. Jeong

acquire/release_in_xmit() work as bit lock in rds_send_xmit(), so they
are expected to ensure acquire/release memory ordering semantics.
However, test_and_set_bit/clear_bit() don't imply such semantics, on
top of this, following smp_mb__after_atomic() does not guarantee release
ordering (memory barrier actually should be placed before clear_bit()).

Instead, we use clear_bit_unlock/test_and_set_bit_lock() here.

Fixes: 0f4b1c7e89e6 ("rds: fix rds_send_xmit() serialization")
Fixes: 1f9ecd7eacfd ("RDS: Pass rds_conn_path to rds_send_xmit()")
Signed-off-by: Yewon Choi <woni9911@gmail.com>
---
Changes in v1 -> v2:
- Added missing Fixes tags

 net/rds/send.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/rds/send.c b/net/rds/send.c
index 5e57a1581dc6..8f38009721b7 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -103,13 +103,12 @@ EXPORT_SYMBOL_GPL(rds_send_path_reset);
 
 static int acquire_in_xmit(struct rds_conn_path *cp)
 {
-	return test_and_set_bit(RDS_IN_XMIT, &cp->cp_flags) == 0;
+	return test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags) == 0;
 }
 
 static void release_in_xmit(struct rds_conn_path *cp)
 {
-	clear_bit(RDS_IN_XMIT, &cp->cp_flags);
-	smp_mb__after_atomic();
+	clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags);
 	/*
 	 * We don't use wait_on_bit()/wake_up_bit() because our waking is in a
 	 * hot path and finding waiters is very rare.  We don't want to walk
-- 
2.43.0


^ permalink raw reply related	[flat|nested] 3+ messages in thread

* Re: [PATCH net v2] rds: introduce acquire/release ordering in acquire/release_in_xmit()
  2024-03-15  9:28 [PATCH net v2] rds: introduce acquire/release ordering in acquire/release_in_xmit() Yewon Choi
@ 2024-03-15 13:32 ` Michal Kubiak
  2024-03-19 11:30 ` patchwork-bot+netdevbpf
  1 sibling, 0 replies; 3+ messages in thread
From: Michal Kubiak @ 2024-03-15 13:32 UTC (permalink / raw)
  To: Yewon Choi
  Cc: Allison Henderson, David S. Miller, Eric Dumazet, Jakub Kicinski,
	Paolo Abeni, netdev, linux-rdma, rds-devel, linux-kernel,
	Dae R. Jeong

On Fri, Mar 15, 2024 at 06:28:38PM +0900, Yewon Choi wrote:
> acquire/release_in_xmit() work as bit lock in rds_send_xmit(), so they
> are expected to ensure acquire/release memory ordering semantics.
> However, test_and_set_bit/clear_bit() don't imply such semantics, on
> top of this, following smp_mb__after_atomic() does not guarantee release
> ordering (memory barrier actually should be placed before clear_bit()).
> 
> Instead, we use clear_bit_unlock/test_and_set_bit_lock() here.
> 
> Fixes: 0f4b1c7e89e6 ("rds: fix rds_send_xmit() serialization")
> Fixes: 1f9ecd7eacfd ("RDS: Pass rds_conn_path to rds_send_xmit()")
> Signed-off-by: Yewon Choi <woni9911@gmail.com>
> ---
> Changes in v1 -> v2:
> - Added missing Fixes tags
> 
>  net/rds/send.c | 5 ++---
>  1 file changed, 2 insertions(+), 3 deletions(-)
> 
> diff --git a/net/rds/send.c b/net/rds/send.c
> index 5e57a1581dc6..8f38009721b7 100644
> --- a/net/rds/send.c
> +++ b/net/rds/send.c
> @@ -103,13 +103,12 @@ EXPORT_SYMBOL_GPL(rds_send_path_reset);
>  
>  static int acquire_in_xmit(struct rds_conn_path *cp)
>  {
> -	return test_and_set_bit(RDS_IN_XMIT, &cp->cp_flags) == 0;
> +	return test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags) == 0;
>  }
>  
>  static void release_in_xmit(struct rds_conn_path *cp)
>  {
> -	clear_bit(RDS_IN_XMIT, &cp->cp_flags);
> -	smp_mb__after_atomic();
> +	clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags);
>  	/*
>  	 * We don't use wait_on_bit()/wake_up_bit() because our waking is in a
>  	 * hot path and finding waiters is very rare.  We don't want to walk
> -- 
> 2.43.0
> 

LGTM

Thanks,
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>


^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [PATCH net v2] rds: introduce acquire/release ordering in acquire/release_in_xmit()
  2024-03-15  9:28 [PATCH net v2] rds: introduce acquire/release ordering in acquire/release_in_xmit() Yewon Choi
  2024-03-15 13:32 ` Michal Kubiak
@ 2024-03-19 11:30 ` patchwork-bot+netdevbpf
  1 sibling, 0 replies; 3+ messages in thread
From: patchwork-bot+netdevbpf @ 2024-03-19 11:30 UTC (permalink / raw)
  To: Yewon Choi
  Cc: allison.henderson, davem, edumazet, kuba, pabeni, netdev,
	linux-rdma, rds-devel, linux-kernel, threeearcat

Hello:

This patch was applied to netdev/net.git (main)
by Paolo Abeni <pabeni@redhat.com>:

On Fri, 15 Mar 2024 18:28:38 +0900 you wrote:
> acquire/release_in_xmit() work as bit lock in rds_send_xmit(), so they
> are expected to ensure acquire/release memory ordering semantics.
> However, test_and_set_bit/clear_bit() don't imply such semantics, on
> top of this, following smp_mb__after_atomic() does not guarantee release
> ordering (memory barrier actually should be placed before clear_bit()).
> 
> Instead, we use clear_bit_unlock/test_and_set_bit_lock() here.
> 
> [...]

Here is the summary with links:
  - [net,v2] rds: introduce acquire/release ordering in acquire/release_in_xmit()
    https://git.kernel.org/netdev/net/c/1422f28826d2

You are awesome, thank you!
-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html



^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2024-03-19 11:30 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2024-03-15  9:28 [PATCH net v2] rds: introduce acquire/release ordering in acquire/release_in_xmit() Yewon Choi
2024-03-15 13:32 ` Michal Kubiak
2024-03-19 11:30 ` patchwork-bot+netdevbpf

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).