Re: [PATCH][net-next] net/smc: avoid atomic_set and smp_wmb in the tx path when possible

[Wen Gu <guwen@linux.alibaba.com>]

On 2023/11/16 10:20, Li RongQing wrote:
> there is rare possibility that conn->tx_pushing is not 1, since
   There
> tx_pushing is just checked with 1, so move the setting tx_pushing
> to 1 after atomic_dec_and_test() return false, to avoid atomic_set
> and smp_wmb in tx path
                         .
> 

Some nits:

1. It is normally using [PATCH net-next] rather than [PATCH][net-next]
    in subject. And new version should better be marked. such as:

    # git format-patch --subject-prefix="PATCH net-next" -v 3

    And CC all relevant people listed by:

    # ./scripts/get_maintainer.pl <your patch>

2. Few improvements in the commit body.


Thanks,
Wen Gu

> Signed-off-by: Li RongQing <lirongqing@baidu.com>
> ---
>   net/smc/smc_tx.c | 7 ++++---
>   1 file changed, 4 insertions(+), 3 deletions(-)
> 
> diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
> index 3b0ff3b..72dbdee 100644
> --- a/net/smc/smc_tx.c
> +++ b/net/smc/smc_tx.c
> @@ -667,8 +667,6 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
>   		return 0;
>   
>   again:
> -	atomic_set(&conn->tx_pushing, 1);
> -	smp_wmb(); /* Make sure tx_pushing is 1 before real send */
>   	rc = __smc_tx_sndbuf_nonempty(conn);
>   
>   	/* We need to check whether someone else have added some data into
> @@ -677,8 +675,11 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
>   	 * If so, we need to push again to prevent those data hang in the send
>   	 * queue.
>   	 */
> -	if (unlikely(!atomic_dec_and_test(&conn->tx_pushing)))
> +	if (unlikely(!atomic_dec_and_test(&conn->tx_pushing))) {
> +		atomic_set(&conn->tx_pushing, 1);
> +		smp_wmb(); /* Make sure tx_pushing is 1 before real send */
>   		goto again;
> +	}
>   
>   	return rc;
>   }