[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1333469916.18626.284.camel@edumazet-glaptop>
Date: Tue, 03 Apr 2012 18:18:36 +0200
From: Eric Dumazet <eric.dumazet@...il.com>
To: Chris Metcalf <cmetcalf@...era.com>
Cc: Stephen Hemminger <shemminger@...tta.com>, netdev@...r.kernel.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH] marvell sky2 driver: fix so it works without unaligned
accesses
On Tue, 2012-04-03 at 11:13 -0400, Chris Metcalf wrote:
> The driver uses a receive_new() routine that ends up requiring unaligned
> accesses in IP header processing. If the architecture doesn't support
> efficient unaligned accesses, just copy all ingress packets to the bounce
> buffers instead.
>
> This allows the driver to be used on the Tilera TILEmpower-Gx, since
> the tile architecture doesn't currently handle kernel unaligned accesses,
> just userspace.
>
> Signed-off-by: Chris Metcalf <cmetcalf@...era.com>
> ---
> drivers/net/ethernet/marvell/sky2.c | 10 +++++++---
> 1 files changed, 7 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
> index 879b0a4..7a15482 100644
> --- a/drivers/net/ethernet/marvell/sky2.c
> +++ b/drivers/net/ethernet/marvell/sky2.c
> @@ -2490,6 +2490,7 @@ static struct sk_buff *receive_copy(struct sky2_port *sky2,
> return skb;
> }
>
> +#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
> /* Adjust length of skb with fragments to match received data */
> static void skb_put_frags(struct sk_buff *skb, unsigned int hdr_space,
> unsigned int length)
> @@ -2555,6 +2556,7 @@ nomap:
> nobuf:
> return NULL;
> }
> +#endif /* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */
>
> /*
> * Receive one packet.
> @@ -2598,10 +2600,12 @@ static struct sk_buff *sky2_receive(struct net_device *dev,
> goto error;
>
> okay:
> - if (length < copybreak)
> - skb = receive_copy(sky2, re, length);
> - else
> +#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
> + if (length >= copybreak)
> skb = receive_new(sky2, re, length);
> + else
> +#endif
> + skb = receive_copy(sky2, re, length);
>
> dev->stats.rx_dropped += (skb == NULL);
>
The (expensive ?) copy should be done only if (sky2->hw->flags &
SKY2_HW_RAM_BUFFER)
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index b806d9b..3da3cdc 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -2599,7 +2599,11 @@ static struct sk_buff *sky2_receive(struct net_device *dev,
goto error;
okay:
- if (length < copybreak)
+ if ((length < copybreak)
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+ || (sky2->hw->flags & SKY2_HW_RAM_BUFFER)
+#endif
+ )
skb = receive_copy(sky2, re, length);
else
skb = receive_new(sky2, re, length);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists