From 90615370309b5bb32962b50a822730dda467e7f5 Mon Sep 17 00:00:00 2001 From: Erez Shitrit Date: Thu, 2 Apr 2015 13:39:05 +0300 Subject: [PATCH] IB/mlx4: Fix WQE LSO segment calculation commit ca9b590caa17bcbbea119594992666e96cde9c2f upstream. The current code decreases from the mss size (which is the gso_size from the kernel skb) the size of the packet headers. It shouldn't do that because the mss that comes from the stack (e.g IPoIB) includes only the tcp payload without the headers. The result is indication to the HW that each packet that the HW sends is smaller than what it could be, and too many packets will be sent for big messages. An easy way to demonstrate one more aspect of the problem is by configuring the ipoib mtu to be less than 2*hlen (2*56) and then run app sending big TCP messages. This will tell the HW to send packets with giant (negative value which under unsigned arithmetics becomes a huge positive one) length and the QP moves to SQE state. Fixes: b832be1e4007 ('IB/mlx4: Add IPoIB LSO support') Reported-by: Matthew Finlay Signed-off-by: Erez Shitrit Signed-off-by: Or Gerlitz Signed-off-by: Doug Ledford Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/hw/mlx4/qp.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 4f10af2905b..262a18437ce 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -2174,8 +2174,7 @@ static int build_lso_seg(struct mlx4_wqe_lso_seg *wqe, struct ib_send_wr *wr, memcpy(wqe->header, wr->wr.ud.header, wr->wr.ud.hlen); - *lso_hdr_sz = cpu_to_be32((wr->wr.ud.mss - wr->wr.ud.hlen) << 16 | - wr->wr.ud.hlen); + *lso_hdr_sz = cpu_to_be32(wr->wr.ud.mss << 16 | wr->wr.ud.hlen); *lso_seg_len = halign; return 0; }