Netdev List
 help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: Amir Vadai <amirv@mellanox.com>
Cc: netdev@vger.kernel.org, Or Gerlitz <ogerlitz@mellanox.com>,
	Eugenia Emantayev <eugenia@mellanox.com>,
	Eric Dumazet <edumazet@google.com>
Subject: Re: [PATCH net] net/mlx4_en: Fix pages never dma unmapped on rx
Date: Sun, 06 Oct 2013 07:22:52 -0700	[thread overview]
Message-ID: <1381069372.3564.68.camel@edumazet-glaptop.roam.corp.google.com> (raw)
In-Reply-To: <1381064240-12902-1-git-send-email-amirv@mellanox.com>

On Sun, 2013-10-06 at 14:57 +0200, Amir Vadai wrote:
> This patch fixes a bug introduced by commit 51151a16 (mlx4: allow
> order-0 memory allocations in RX path).
> 
> dma_unmap_page never reached because condition to detect last fragment
> in page is wrong. offset+frag_stride can't be greater than size, need to
> make sure no additional frag will fit in page => compare offset +
> frag_stride + next_frag_size instead.
> next_frag_size could be next frag in the same skb, or the first frag in
> the next.
> 
> CC: Eric Dumazet <edumazet@google.com>
> Signed-off-by: Amir Vadai <amirv@mellanox.com>
> ---
>  drivers/net/ethernet/mellanox/mlx4/en_rx.c | 5 ++++-
>  1 file changed, 4 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
> index dec455c..44d8865 100644
> --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
> +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
> @@ -131,8 +131,11 @@ static void mlx4_en_free_frag(struct mlx4_en_priv *priv,
>  			      int i)
>  {
>  	const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i];
> +	u16 next_frag_end = frags[i].offset + frag_info->frag_stride;
>  

Hmm, could you make this an u32 ?

frags[i].offset and frags[i].size are u32

Maybe some folks want to use PAGE_SIZE=65536 or whatever high order
allocs


> -	if (frags[i].offset + frag_info->frag_stride > frags[i].size)
> +	next_frag_end += frags[(i + 1) % priv->num_frags].size;
> +
> +	if (next_frag_end > frags[i].size)
>  		dma_unmap_page(priv->ddev, frags[i].dma, frags[i].size,
>  					 PCI_DMA_FROMDEVICE);
>  

Not sure I understand how this can work. How was this tested ?

frags[i + 1].size is the size of the page containing next fragment,
so now test should _always_ trigger.

(We could rename @size to @page_size to avoid confusion)

I think you meant to add the size of the next fragment ?

What about following instead (I also removed the divide operation)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index dec455c..22444de 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -131,10 +131,17 @@ static void mlx4_en_free_frag(struct mlx4_en_priv *priv,
 			      int i)
 {
 	const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i];
+	u32 next_frag_end = frags[i].offset + frag_info->frag_stride;
 
-	if (frags[i].offset + frag_info->frag_stride > frags[i].size)
+	frag_info++;
+	if (i + 1 == priv->num_frags)
+		frag_info = &priv->frag_info[0];
+
+	next_frag_end += frag_info->frag_stride;
+
+	if (next_frag_end > frags[i].size)
 		dma_unmap_page(priv->ddev, frags[i].dma, frags[i].size,
-					 PCI_DMA_FROMDEVICE);
+			       PCI_DMA_FROMDEVICE);
 
 	if (frags[i].page)
 		put_page(frags[i].page);

  reply	other threads:[~2013-10-06 14:22 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-10-06 12:57 [PATCH net] net/mlx4_en: Fix pages never dma unmapped on rx Amir Vadai
2013-10-06 14:22 ` Eric Dumazet [this message]
2013-10-06 15:05   ` Amir Vadai

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=1381069372.3564.68.camel@edumazet-glaptop.roam.corp.google.com \
    --to=eric.dumazet@gmail.com \
    --cc=amirv@mellanox.com \
    --cc=edumazet@google.com \
    --cc=eugenia@mellanox.com \
    --cc=netdev@vger.kernel.org \
    --cc=ogerlitz@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