netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Tariq Toukan <ttoukan.linux@gmail.com>
To: Martin KaFai Lau <kafai@fb.com>, Tariq Toukan <tariqt@mellanox.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>,
	"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	Alexei Starovoitov <ast@fb.com>
Subject: Re: mlx4: Bug in XDP_TX + 16 rx-queues
Date: Tue, 20 Dec 2016 14:02:05 +0200	[thread overview]
Message-ID: <a586ecb7-e290-8c70-714b-2eea0b94c7fb@gmail.com> (raw)
In-Reply-To: <20161219233709.GA29858@kafai-mba.local>

Thanks Martin, nice catch!


On 20/12/2016 1:37 AM, Martin KaFai Lau wrote:
> Hi Tariq,
>
> On Sat, Dec 17, 2016 at 02:18:03AM -0800, Martin KaFai Lau wrote:
>> Hi All,
>>
>> I have been debugging with XDP_TX and 16 rx-queues.
>>
>> 1) When 16 rx-queues is used and an XDP prog is doing XDP_TX,
>> it seems that the packet cannot be XDP_TX out if the pkt
>> is received from some particular CPUs (/rx-queues).
>>
>> 2) If 8 rx-queues is used, it does not have problem.
>>
>> 3) The 16 rx-queues problem also went away after reverting these
>> two patches:
>> 15fca2c8eb41 net/mlx4_en: Add ethtool statistics for XDP cases
>> 67f8b1dcb9ee net/mlx4_en: Refactor the XDP forwarding rings scheme
>>
> After taking a closer look at 67f8b1dcb9ee ("net/mlx4_en: Refactor the XDP forwarding rings scheme")
> and armed with the fact that '>8 rx-queues does not work', I have
> made the attached change that fixed the issue.
>
> Making change in mlx4_en_fill_qp_context() could be an easier fix
> but I think this change will be easier for discussion purpose.
>
> I don't want to lie that I know anything about how this variable
> works in CX3.  If this change makes sense, I can cook up a diff.
> Otherwise, can you shed some light on what could be happening
> and hopefully can lead to a diff?
>
> Thanks
> --Martin
>
>
> diff --git i/drivers/net/ethernet/mellanox/mlx4/en_netdev.c w/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
> index bcd955339058..b3bfb987e493 100644
> --- i/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
> +++ w/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
> @@ -1638,10 +1638,10 @@ int mlx4_en_start_port(struct net_device *dev)
>
>   	/* Configure tx cq's and rings */
>   	for (t = 0 ; t < MLX4_EN_NUM_TX_TYPES; t++) {
> -		u8 num_tx_rings_p_up = t == TX ? priv->num_tx_rings_p_up : 1;
The bug lies in this line.
Number of rings per UP in case of TX_XDP should be 
priv->tx_ring_num[TX_XDP ], not 1.
Please try the following fix.
I can prepare and send it once the window opens again.

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c 
b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index bcd955339058..edbe200ac2fa 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1638,7 +1638,8 @@ int mlx4_en_start_port(struct net_device *dev)

         /* Configure tx cq's and rings */
         for (t = 0 ; t < MLX4_EN_NUM_TX_TYPES; t++) {
-               u8 num_tx_rings_p_up = t == TX ? priv->num_tx_rings_p_up 
: 1;
+               u8 num_tx_rings_p_up = t == TX ?
+                       priv->num_tx_rings_p_up : priv->tx_ring_num[t];

                 for (i = 0; i < priv->tx_ring_num[t]; i++) {
                         /* Configure cq */

> -
>   		for (i = 0; i < priv->tx_ring_num[t]; i++) {
>   			/* Configure cq */
> +			int user_prio;
> +
>   			cq = priv->tx_cq[t][i];
>   			err = mlx4_en_activate_cq(priv, cq, i);
>   			if (err) {
> @@ -1660,9 +1660,14 @@ int mlx4_en_start_port(struct net_device *dev)
>
>   			/* Configure ring */
>   			tx_ring = priv->tx_ring[t][i];
> +			if (t != TX_XDP)
> +				user_prio = i / priv->num_tx_rings_p_up;
> +			else
> +				user_prio = i & 0x07;
> +
>   			err = mlx4_en_activate_tx_ring(priv, tx_ring,
>   						       cq->mcq.cqn,
> -						       i / num_tx_rings_p_up);
> +						       user_prio);
>   			if (err) {
>   				en_err(priv, "Failed allocating Tx ring\n");
>   				mlx4_en_deactivate_cq(priv, cq);
Regards,
Tariq Toukan.

  reply	other threads:[~2016-12-20 12:02 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-12-17 10:18 mlx4: Bug in XDP_TX + 16 rx-queues Martin KaFai Lau
2016-12-18 10:31 ` Tariq Toukan
2016-12-18 18:14   ` Martin KaFai Lau
2016-12-19 23:37 ` Martin KaFai Lau
2016-12-20 12:02   ` Tariq Toukan [this message]
2016-12-20 14:22     ` David Miller
2016-12-21 16:37       ` Tariq Toukan
2016-12-20 18:31     ` Martin KaFai Lau
2016-12-21 16:47       ` Tariq Toukan

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=a586ecb7-e290-8c70-714b-2eea0b94c7fb@gmail.com \
    --to=ttoukan.linux@gmail.com \
    --cc=ast@fb.com \
    --cc=kafai@fb.com \
    --cc=netdev@vger.kernel.org \
    --cc=saeedm@mellanox.com \
    --cc=tariqt@mellanox.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).