via-velocity: Correct 64-byte alignment for rx buffers
authorSimon Kagstrom <simon.kagstrom@netinsight.net>
Wed, 25 Nov 2009 22:09:53 +0000 (22:09 +0000)
committerDavid S. Miller <davem@davemloft.net>
Thu, 26 Nov 2009 23:51:06 +0000 (15:51 -0800)
(From the VIA driver). The current code does not guarantee 64-byte
alignment since it simply does

        int add = skb->data & 63;

        skb->data += add;

(via skb_reserve). So for example, if the skb->data address would be
0x10, this would result in 32-byte alignment (0x10 + 0x10).

Correct by adding

        64 - (skb->data & 63)

instead.

Signed-off-by: Simon Kagstrom <simon.kagstrom@netinsight.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
drivers/net/via-velocity.c

index 1e6b395c555f401614807a3e473e557f9930f195..04d3836bfa5d2ceaa9f44b68228c6eeaa92f5308 100644 (file)
@@ -1470,7 +1470,8 @@ static int velocity_alloc_rx_buf(struct velocity_info *vptr, int idx)
         *      Do the gymnastics to get the buffer head for data at
         *      64byte alignment.
         */
-       skb_reserve(rd_info->skb, (unsigned long) rd_info->skb->data & 63);
+       skb_reserve(rd_info->skb,
+                       64 - ((unsigned long) rd_info->skb->data & 63));
        rd_info->skb_dma = pci_map_single(vptr->pdev, rd_info->skb->data,
                                        vptr->rx.buf_sz, PCI_DMA_FROMDEVICE);