Re: [PATCH] ixgbe: fix truesize calculation when merging active tail into lro skb

On 02/13/2012 01:43 PM, Jeff Kirsher wrote:

On Mon, 2012-02-13 at 15:12 +0100, Eric Dumazet wrote:

quoted

Le lundi 13 février 2012 à 14:52 +0100, Christian Brunner a écrit :

quoted

I'm seeing some page allocation failures with the ixgbe driver under heavy
load. While looking after it, I came accoss the truesize handling. I suspect,
that there is a small misstake in ixgbe_merge_active_tail(). (But I'm not
really sure).

Truesize allocation of the skb may be larger than skb->len, because
ixgbe is allocating PAGE_SIZE/2 for received fragments. Hence we 
should use the truesize of the tail when merging.

Signed-off-by: Christian Brunner <redacted>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a42b0b2..c4d25af 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -1222,7 +1222,7 @@ static inline struct sk_buff *ixgbe_merge_active_tail(struct sk_buff *tail)
 
 	head->len += tail->len;
 	head->data_len += tail->len;
-	head->truesize += tail->len;
+	head->truesize += tail->truesize;
 
 	IXGBE_CB(tail)->head = NULL;
 

You forgot CC Intel guys, but they usually catch netdev traffic :)

Acked-by: Eric Dumazet <redacted>

Cc: Jeff Kirsher <redacted>
Cc: Jesse Brandeburg <redacted>

Thanks Eric for bringing this to my attention.

Thanks Christian for the patch, I have added it to my queue.

The code itself is correct, but the comment isn't.  This code path is
applied only to the case where we are not using pages.  The default Rx
buffer size is actually about 3K when RSC is in use, which means
truesize is about 4.25K per buffer.

Thanks,

Alex