DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Zhang, Qi Z" <qi.z.zhang@intel.com>
To: "Ye, Xiaolong" <xiaolong.ye@intel.com>
Cc: "Xing, Beilei" <beilei.xing@intel.com>,
	"dev@dpdk.org" <dev@dpdk.org>,
	"stable@dpdk.org" <stable@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH] net/ice: remove bulk alloc compile option
Date: Fri, 6 Mar 2020 23:29:30 +0000	[thread overview]
Message-ID: <039ED4275CED7440929022BC67E70611547DB595@SHSMSX103.ccr.corp.intel.com> (raw)
In-Reply-To: <20200306084626.GB18727@intel.com>



> -----Original Message-----
> From: Ye, Xiaolong <xiaolong.ye@intel.com>
> Sent: Friday, March 6, 2020 4:46 PM
> To: Zhang, Qi Z <qi.z.zhang@intel.com>
> Cc: Xing, Beilei <beilei.xing@intel.com>; dev@dpdk.org; stable@dpdk.org
> Subject: Re: [PATCH] net/ice: remove bulk alloc compile option
> 
> Hi, Qi
> 
> Thanks for the cleanup.
> 
> On 03/04, Qi Zhang wrote:
> >Remove CONFIG_RTE_LIBRTE_ICE_RX_ALLOW_BULK_ALLOC with below
> >consideration:
> >
> >1. a default Rx path can always be selected by setting a proper
> >   rx_free_thresh value at runtime, see
> >   ice_check_rx_burst_bulk_alloc_preconditions.
> >
> >2. its not a big deal to always reserve more space for desc ring.
> >   "ring_size = (uint16_t)(rxq->nb_rx_desc + ICE_RX_MAX_BURST);"
> >
> >3. Fixes a potential invalid memory access in ice_reset_rx_queue.
> >   if CONFIG_RTE_LIBRTE_ICE_RX_ALLOW_BULK_ALLOC is turned on while
> >   ice_check_rx_burst_bulk_alloc_preconditions return fail.
> >   below code will have problem.
> >
> >   for (i = 0; i < ICE_RX_MAX_BURST; ++i)
> >   	rxq->sw_ring[rxq->nb_rx_desc + i].mbuf = &rxq->fake_mbuf;
> >
> >Fixes: 50370662b727 ("net/ice: support device and queue ops")
> >Cc: stable@dpdk.org
> >
> >Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
> >---
> > config/common_base         |  1 -
> > doc/guides/nics/ice.rst    |  4 ---
> > drivers/net/ice/ice_rxtx.c | 64
> >++++++++++------------------------------------
> > 3 files changed, 13 insertions(+), 56 deletions(-)
> >
> >diff --git a/config/common_base b/config/common_base index
> >7ca2f28b1..c31175f9d 100644
> >--- a/config/common_base
> >+++ b/config/common_base
> >@@ -337,7 +337,6 @@ CONFIG_RTE_LIBRTE_ICE_PMD=y
> >CONFIG_RTE_LIBRTE_ICE_DEBUG_RX=n
> CONFIG_RTE_LIBRTE_ICE_DEBUG_TX=n
> >CONFIG_RTE_LIBRTE_ICE_DEBUG_TX_FREE=n
> >-CONFIG_RTE_LIBRTE_ICE_RX_ALLOW_BULK_ALLOC=y
> > CONFIG_RTE_LIBRTE_ICE_16BYTE_RX_DESC=n
> >
> > # Compile burst-oriented IAVF PMD driver diff --git
> >a/doc/guides/nics/ice.rst b/doc/guides/nics/ice.rst index
> >cde3fd620..8af32dabf 100644
> >--- a/doc/guides/nics/ice.rst
> >+++ b/doc/guides/nics/ice.rst
> >@@ -54,10 +54,6 @@ Please note that enabling debugging options may
> affect system performance.
> >
> >   Toggle display of generic debugging messages.
> >
> >-- ``CONFIG_RTE_LIBRTE_ICE_RX_ALLOW_BULK_ALLOC`` (default ``y``)
> >-
> >-  Toggle bulk allocation for RX.
> >-
> > - ``CONFIG_RTE_LIBRTE_ICE_16BYTE_RX_DESC`` (default ``n``)
> >
> >   Toggle to use a 16-byte RX descriptor, by default the RX descriptor is 32
> byte.
> >diff --git a/drivers/net/ice/ice_rxtx.c b/drivers/net/ice/ice_rxtx.c
> >index 60c411bfa..c7e5fc484 100644
> >--- a/drivers/net/ice/ice_rxtx.c
> >+++ b/drivers/net/ice/ice_rxtx.c
> >@@ -236,17 +236,15 @@ _ice_rx_queue_release_mbufs(struct
> ice_rx_queue *rxq)
> > 			rxq->sw_ring[i].mbuf = NULL;
> > 		}
> > 	}
> >-#ifdef RTE_LIBRTE_ICE_RX_ALLOW_BULK_ALLOC
> >-		if (rxq->rx_nb_avail == 0)
> >-			return;
> >-		for (i = 0; i < rxq->rx_nb_avail; i++) {
> >-			struct rte_mbuf *mbuf;
> >-
> >-			mbuf = rxq->rx_stage[rxq->rx_next_avail + i];
> >-			rte_pktmbuf_free_seg(mbuf);
> >-		}
> >-		rxq->rx_nb_avail = 0;
> >-#endif /* RTE_LIBRTE_ICE_RX_ALLOW_BULK_ALLOC */
> >+	if (rxq->rx_nb_avail == 0)
> >+		return;
> >+	for (i = 0; i < rxq->rx_nb_avail; i++) {
> >+		struct rte_mbuf *mbuf;
> >+
> >+		mbuf = rxq->rx_stage[rxq->rx_next_avail + i];
> >+		rte_pktmbuf_free_seg(mbuf);
> >+	}
> 
> How about just
> 
> 	for (i = 0; i < rxq->rx_nb_avail; i++)
> 		rte_pktmbuf_free_seg(rxq->rx_stage[rxq->rx_next_avail + i]);

I just remove the compile option and keep the code unchanged, but no objection for your suggestion. 

> 
> [snip]
> 
> For the rest,
> 
> Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
> 
> And can this cleanup be applied to i40e as well? I think it's good to have less
> configurations generally.

I40e should be similar with a little bit complexity, I will take chance to cleanup later.

Thanks
Qi

> 
> Thanks,
> Xiaolong

  reply	other threads:[~2020-03-06 23:29 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-04 11:40 Qi Zhang
2020-03-06  8:46 ` Ye Xiaolong
2020-03-06 23:29   ` Zhang, Qi Z [this message]
2020-03-08  4:13   ` Ye Xiaolong
  -- strict thread matches above, loose matches on Subject: below --
2020-03-04 11:39 Qi Zhang

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=039ED4275CED7440929022BC67E70611547DB595@SHSMSX103.ccr.corp.intel.com \
    --to=qi.z.zhang@intel.com \
    --cc=beilei.xing@intel.com \
    --cc=dev@dpdk.org \
    --cc=stable@dpdk.org \
    --cc=xiaolong.ye@intel.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).