There is a separate receive path for small packets (under 256 bytes).
Instead of allocating a new dma-capable skb to be used for the next packet,
this path allocates a skb and copies the data into it (reusing the existing
sbk for the next packet). There are two bytes of junk data at the beginning
of every packet. I believe these are inserted in order to allow aligned DMA
and IP headers. We skip over them using skb_reserve. Before copying over
the data, we must use a barrier to ensure we see the whole packet. The
current code only synchronizes len bytes, starting from the beginning of
the packet, including the junk bytes. However, this leaves off the final
two bytes in the packet. Synchronize the whole packet.
To reproduce this problem, ping a HME with a payload size between 17 and
214
$ ping -s 17 <hme_address>
which will complain rather loudly about the data mismatch. Small packets
(below 60 bytes on the wire) do not have this issue. I suspect this is
related to the padding added to increase the minimum packet size.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Sean Anderson <[email protected]>
Reviewed-by: Andrew Lunn <[email protected]>
---
Changes in v2:
- Add Fixes tag
drivers/net/ethernet/sun/sunhme.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index 1921054b7f7d..e660902cfdf7 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -2020,9 +2020,9 @@ static void happy_meal_rx(struct happy_meal *hp, struct net_device *dev)
skb_reserve(copy_skb, 2);
skb_put(copy_skb, len);
- dma_sync_single_for_cpu(hp->dma_dev, dma_addr, len, DMA_FROM_DEVICE);
+ dma_sync_single_for_cpu(hp->dma_dev, dma_addr, len + 2, DMA_FROM_DEVICE);
skb_copy_from_linear_data(skb, copy_skb->data, len);
- dma_sync_single_for_device(hp->dma_dev, dma_addr, len, DMA_FROM_DEVICE);
+ dma_sync_single_for_device(hp->dma_dev, dma_addr, len + 2, DMA_FROM_DEVICE);
/* Reuse original ring buffer. */
hme_write_rxd(hp, this,
(RXFLAG_OWN|((RX_BUF_ALLOC_SIZE-RX_OFFSET)<<16)),
--
2.37.1
Hello:
This patch was applied to netdev/net.git (master)
by Jakub Kicinski <[email protected]>:
On Tue, 20 Sep 2022 19:50:18 -0400 you wrote:
> There is a separate receive path for small packets (under 256 bytes).
> Instead of allocating a new dma-capable skb to be used for the next packet,
> this path allocates a skb and copies the data into it (reusing the existing
> sbk for the next packet). There are two bytes of junk data at the beginning
> of every packet. I believe these are inserted in order to allow aligned DMA
> and IP headers. We skip over them using skb_reserve. Before copying over
> the data, we must use a barrier to ensure we see the whole packet. The
> current code only synchronizes len bytes, starting from the beginning of
> the packet, including the junk bytes. However, this leaves off the final
> two bytes in the packet. Synchronize the whole packet.
>
> [...]
Here is the summary with links:
- [net,v2] net: sunhme: Fix packet reception for len < RX_COPY_THRESHOLD
https://git.kernel.org/netdev/net/c/878e2405710a
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html