DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Mattias Rönnblom" <mattias.ronnblom@ericsson.com>
To: "Morten Brørup" <mb@smartsharesystems.com>,
	"jerinj@marvell.com" <jerinj@marvell.com>
Cc: Jerin Jacob <jerinjacobk@gmail.com>,
	"hofors@lysator.liu.se" <hofors@lysator.liu.se>,
	"dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [PATCH] eventdev: avoid non-burst shortcut for variable-size bursts
Date: Thu, 11 May 2023 08:29:59 +0000	[thread overview]
Message-ID: <d2be2b57-333c-588a-097a-a3d8d77aed5a@ericsson.com> (raw)
In-Reply-To: <98CBD80474FA8B44BF855DF32C47DC35D878FE@smartserver.smartshare.dk>

On 2023-05-11 09:09, Morten Brørup wrote:
>> From: Mattias Rönnblom [mailto:mattias.ronnblom@ericsson.com]
>> Sent: Thursday, 11 May 2023 08.43
>>
>> Use non-burst event enqueue and dequeue calls from burst enqueue and
>> dequeue only when the burst size is compile-time constant (and equal
>> to one).
>>
>> Signed-off-by: Mattias Rönnblom <mattias.ronnblom@ericsson.com>
>> ---
>>   lib/eventdev/rte_eventdev.h | 4 ++--
>>   1 file changed, 2 insertions(+), 2 deletions(-)
>>
>> diff --git a/lib/eventdev/rte_eventdev.h b/lib/eventdev/rte_eventdev.h
>> index a90e23ac8b..8af15816db 100644
>> --- a/lib/eventdev/rte_eventdev.h
>> +++ b/lib/eventdev/rte_eventdev.h
>> @@ -1944,7 +1944,7 @@ __rte_event_enqueue_burst(uint8_t dev_id, uint8_t
>> port_id,
>>   	 * Allow zero cost non burst mode routine invocation if application
>>   	 * requests nb_events as const one
>>   	 */
>> -	if (nb_events == 1)
>> +	if (__builtin_constant_p(nb_events) && nb_events == 1)
> 
> In my experience using __builtin_constant_p(), you need __extension__(__builtin_constant_p(nb_events)) to avoid warnings about using this non-standard feature.
> 

Yes, since it's a public header. Thanks.

>>   		return (fp_ops->enqueue)(port, ev);
>>   	else
>>   		return fn(port, ev, nb_events);
>> @@ -2200,7 +2200,7 @@ rte_event_dequeue_burst(uint8_t dev_id, uint8_t port_id,
>> struct rte_event ev[],
>>   	 * Allow zero cost non burst mode routine invocation if application
>>   	 * requests nb_events as const one
>>   	 */
>> -	if (nb_events == 1)
>> +	if (__builtin_constant_p(nb_events) && nb_events == 1)
>>   		return (fp_ops->dequeue)(port, ev, timeout_ticks);
>>   	else
>>   		return (fp_ops->dequeue_burst)(port, ev, nb_events,
>> --
>> 2.34.1
> 
> With __extension__() added,
> 
> Acked-by: Morten Brørup <mb@smartsharesystems.com>
> 


  parent reply	other threads:[~2023-05-11  8:30 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-05-11  6:43 Mattias Rönnblom
2023-05-11  7:09 ` Morten Brørup
2023-05-11  8:16   ` [PATCH v2] " Mattias Rönnblom
2023-05-11  8:24     ` [PATCH v3] " Mattias Rönnblom
2023-05-11  9:01       ` Morten Brørup
2023-05-12 11:59       ` Jerin Jacob
2023-05-12 13:15         ` Mattias Rönnblom
2023-05-12 13:56           ` Morten Brørup
2023-05-12 14:52             ` Mattias Rönnblom
2023-05-15 12:33             ` Jerin Jacob
2023-05-15 12:38           ` Jerin Jacob
2023-05-15 20:52             ` Mattias Rönnblom
2023-05-16 13:08               ` Jerin Jacob
2023-05-17  7:16                 ` Mattias Rönnblom
2023-05-17 12:28                   ` Jerin Jacob
2023-05-11  8:24     ` [PATCH v2] " Morten Brørup
2023-05-11  8:29   ` Mattias Rönnblom [this message]
2023-05-11  9:06     ` [PATCH] " Morten Brørup

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=d2be2b57-333c-588a-097a-a3d8d77aed5a@ericsson.com \
    --to=mattias.ronnblom@ericsson.com \
    --cc=dev@dpdk.org \
    --cc=hofors@lysator.liu.se \
    --cc=jerinj@marvell.com \
    --cc=jerinjacobk@gmail.com \
    --cc=mb@smartsharesystems.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).