DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Ananyev, Konstantin" <konstantin.ananyev@intel.com>
To: "dev@dpdk.org" <dev@dpdk.org>, Hanoh Haim <hhaim@cisco.com>
Subject: Re: [dpdk-dev] [PATCH] mbuf: cleanup rte_pktmbuf_lastseg(), fix atomic usage
Date: Wed, 15 Nov 2017 11:08:17 +0000	[thread overview]
Message-ID: <2601191342CEEE43887BDE71AB9772585FABD3F5@irsmsx105.ger.corp.intel.com> (raw)



Hi Hanon,

> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Hanoh Haim
> Sent: Wednesday, November 15, 2017 8:36 AM
> To: dev@dpdk.org
> Cc: Hanoh Haim <hhaim@cisco.com>
> Subject: [dpdk-dev] [PATCH] mbuf: cleanup rte_pktmbuf_lastseg(), fix atomic usage
> 
> Signed-off-by: Hanoh Haim <hhaim@cisco.com>
> ---
>  lib/librte_mbuf/rte_mbuf.h | 27 +++++++++++++--------------
>  1 file changed, 13 insertions(+), 14 deletions(-)
> 
> diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
> index 7e326bb..ab110f8 100644
> --- a/lib/librte_mbuf/rte_mbuf.h
> +++ b/lib/librte_mbuf/rte_mbuf.h
> @@ -1159,6 +1159,15 @@ static inline void rte_pktmbuf_reset(struct rte_mbuf *m)
> 	__rte_mbuf_sanity_check(m, 1);
>  }
> 
> +
> +static __rte_always_inline void rte_pktmbuf_reset_before_free(struct rte_mbuf *m)
> +{
> +	if (m->next != NULL) {
> +		m->next = NULL;
> +		m->nb_segs = 1;
> +	}
> +}
> +
>  /**
>   * Allocate a new mbuf from a mempool.
>   *
> @@ -1323,8 +1332,7 @@ static inline void rte_pktmbuf_detach(struct rte_mbuf *m)
> 	m->ol_flags = 0;
> 
> 	if (rte_mbuf_refcnt_update(md, -1) == 0) {
> -		md->next = NULL;
> -		md->nb_segs = 1;
> +		rte_pktmbuf_reset_before_free(md);
> 		rte_mbuf_refcnt_set(md, 1);
> 		rte_mbuf_raw_free(md);
> 	}
> @@ -1354,25 +1362,16 @@ rte_pktmbuf_prefree_seg(struct rte_mbuf *m)
> 		if (RTE_MBUF_INDIRECT(m))
> 			rte_pktmbuf_detach(m);
> 
> -		if (m->next != NULL) {
> -			m->next = NULL;
> -			m->nb_segs = 1;
> -		}
> -
> +		rte_pktmbuf_reset_before_free(m);
> 		return m;
> 
> -       } else if (rte_atomic16_add_return(&m->refcnt_atomic, -1) == 0) {
> -
> +	} else if (rte_mbuf_refcnt_update(m, -1) == 0) {

That would cause extra read; cmp (and possible slowdown) for atomic refcnt.
If that really need to be fixed - probably we need to introduce a new function
that would do update without trying to read refctn first - rte_mbuf_refcnt_update_blind() or so.
Konstantin


> 
> 		if (RTE_MBUF_INDIRECT(m))
> 			rte_pktmbuf_detach(m);
> 
> -		if (m->next != NULL) {
> -			m->next = NULL;
> -			m->nb_segs = 1;
> -		}
> +		rte_pktmbuf_reset_before_free(m);
> 		rte_mbuf_refcnt_set(m, 1);
> -
> 		return m;
> 	}
> 	return NULL;
> --
> 2.9.3

             reply	other threads:[~2017-11-15 11:08 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-11-15 11:08 Ananyev, Konstantin [this message]
  -- strict thread matches above, loose matches on Subject: below --
2017-11-15  8:35 Hanoh Haim
2017-11-15  8:50 ` Ananyev, Konstantin
2017-11-15  8:30 Hanoh Haim
2017-11-15  8:41 ` Olivier MATZ
2017-11-15  8:25 Hanoh Haim
2017-11-15  8:16 Hanoh Haim

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=2601191342CEEE43887BDE71AB9772585FABD3F5@irsmsx105.ger.corp.intel.com \
    --to=konstantin.ananyev@intel.com \
    --cc=dev@dpdk.org \
    --cc=hhaim@cisco.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).