patches for DPDK stable branches
 help / color / mirror / Atom feed
From: fengchengwen <fengchengwen@huawei.com>
To: Ashok Kaladi <ashok.k.kaladi@intel.com>, <jerinj@marvell.com>,
	<thomas@monjalon.net>
Cc: <dev@dpdk.org>, <s.v.naga.harish.k@intel.com>,
	<erik.g.carrillo@intel.com>, <abhinandan.gujjar@intel.com>,
	<stable@dpdk.org>
Subject: Re: [PATCH 2/2] ethdev: fix race condition in fast-path ops setup
Date: Mon, 20 Feb 2023 15:01:34 +0800	[thread overview]
Message-ID: <970123b7-23ca-616e-bf5a-a04578db65dc@huawei.com> (raw)
In-Reply-To: <20230220060839.1267349-2-ashok.k.kaladi@intel.com>

Sorry resend, because forget one line.

On 2023/2/20 14:08, Ashok Kaladi wrote:
> If ethdev enqueue or dequeue function is called during
> eth_dev_fp_ops_setup(), it may get pre-empted after setting
> the function pointers, but before setting the pointer to port data.
> In this case the newly registered enqueue/dequeue function will use
> dummy port data and end up in seg fault.
> 
> This patch moves the updation of each data pointers before updating
> corresponding function pointers.
> 
> Fixes: c87d435a4d79 ("ethdev: copy fast-path API into separate structure")
> Cc: stable@dpdk.org
> 
> Signed-off-by: Ashok Kaladi <ashok.k.kaladi@intel.com>
> 
> diff --git a/lib/ethdev/ethdev_private.c b/lib/ethdev/ethdev_private.c
> index 48090c879a..a0232c669f 100644
> --- a/lib/ethdev/ethdev_private.c
> +++ b/lib/ethdev/ethdev_private.c
> @@ -270,17 +270,17 @@ void
>  eth_dev_fp_ops_setup(struct rte_eth_fp_ops *fpo,
>  		const struct rte_eth_dev *dev)
>  {
> +	fpo->rxq.data = dev->data->rx_queues;
>  	fpo->rx_pkt_burst = dev->rx_pkt_burst;
> +	fpo->txq.data = dev->data->tx_queues;
>  	fpo->tx_pkt_burst = dev->tx_pkt_burst;
>  	fpo->tx_pkt_prepare = dev->tx_pkt_prepare;
>  	fpo->rx_queue_count = dev->rx_queue_count;
>  	fpo->rx_descriptor_status = dev->rx_descriptor_status;
>  	fpo->tx_descriptor_status = dev->tx_descriptor_status;
>  
> -	fpo->rxq.data = dev->data->rx_queues;
>  	fpo->rxq.clbk = (void **)(uintptr_t)dev->post_rx_burst_cbs;
>  
> -	fpo->txq.data = dev->data->tx_queues;
>  	fpo->txq.clbk = (void **)(uintptr_t)dev->pre_tx_burst_cbs;

Hi Ashok,

The modification is OK for the x86 platform (which has strong memory order, and will keep write-after-write order in here, and read-after-read in rte_eth_rx/tx_burst),
but for other weak memory order (like ARM platform) will fail.

For the weak memory order, suggest add write-mb in here, and read-mb in rte_eth_rx/tx_burst.
But the read-mb in rte_eth_rx/tx_burst will affect performance, especially the variable will changes only once when start.

So I suggest use write-mb + delay in here:
   fpo->rxq.data = dev->data->rx_queues;
   fpo->txq.data = dev->data->tx_queues;
   wmb();
   mdelay(5); // delay e.g. 5ms
   fpo->rx_pkt_burst = dev->rx_pkt_burst;
   fpo->tx_pkt_burst = dev->tx_pkt_burst;

And also cc ARMv8 maintainer.

>  }
>  
> 

  parent reply	other threads:[~2023-02-20  7:01 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-20  6:08 [PATCH 1/2] eventdev: fix race condition in fast-path set function Ashok Kaladi
2023-02-20  6:08 ` [PATCH 2/2] ethdev: fix race condition in fast-path ops setup Ashok Kaladi
2023-02-20  6:57   ` fengchengwen
2023-02-21  7:24     ` Ruifeng Wang
2023-02-21 17:00       ` Stephen Hemminger
2023-02-22  1:07         ` fengchengwen
2023-02-22  9:41           ` Ruifeng Wang
2023-02-22 10:41           ` Konstantin Ananyev
2023-02-22 22:48             ` Honnappa Nagarahalli
2023-02-23  1:15               ` Stephen Hemminger
2023-02-23  4:47                 ` Honnappa Nagarahalli
2023-02-23  4:40             ` Honnappa Nagarahalli
2023-02-23  8:23               ` fengchengwen
2023-02-23 13:31                 ` Konstantin Ananyev
2023-02-25  1:32                   ` fengchengwen
2023-02-28 23:57                   ` Honnappa Nagarahalli
2023-02-20  7:01   ` fengchengwen [this message]
2023-02-20  9:44   ` Konstantin Ananyev
2023-03-03 16:49   ` Ferruh Yigit
  -- strict thread matches above, loose matches on Subject: below --
2023-02-20  6:06 [PATCH 1/2] eventdev: fix race condition in fast-path set function Ashok Kaladi
2023-02-20  6:06 ` [PATCH 2/2] ethdev: fix race condition in fast-path ops setup Ashok Kaladi

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=970123b7-23ca-616e-bf5a-a04578db65dc@huawei.com \
    --to=fengchengwen@huawei.com \
    --cc=abhinandan.gujjar@intel.com \
    --cc=ashok.k.kaladi@intel.com \
    --cc=dev@dpdk.org \
    --cc=erik.g.carrillo@intel.com \
    --cc=jerinj@marvell.com \
    --cc=s.v.naga.harish.k@intel.com \
    --cc=stable@dpdk.org \
    --cc=thomas@monjalon.net \
    /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).