diff mbox

[dpdk-dev] net/mlx5: fix queue wrap-around of multi-packet send

Message ID 20170118005155.20192-1-yskoh@mellanox.com (mailing list archive)
State Accepted, archived
Delegated to: Ferruh Yigit
Headers

Checks

Context Check Description
ci/checkpatch success coding style OK
ci/Intel compilation success Compilation OK

Commit Message

Yongseok Koh Jan. 18, 2017, 12:51 a.m. UTC 
  When the WQ is wrapped around, it wrongly checks the condition when
resetting the pointer. It should be compared against the end of the queue,
not the beginning of the queue. And this isn't even needed when the length
of the copying data crosses the boundary.

Fixes: e5291c280c08 ("net/mlx5: use work queue buffer as a raw buffer")

CC: stable@dpdk.org
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
---
 drivers/net/mlx5/mlx5_rxtx.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

Comments

Adrien Mazarguil Jan. 20, 2017, 4:56 p.m. UTC | #1 
On Tue, Jan 17, 2017 at 04:51:55PM -0800, Yongseok Koh wrote:
> When the WQ is wrapped around, it wrongly checks the condition when
> resetting the pointer. It should be compared against the end of the queue,
> not the beginning of the queue. And this isn't even needed when the length
> of the copying data crosses the boundary.
> 
> Fixes: e5291c280c08 ("net/mlx5: use work queue buffer as a raw buffer")
> 
> CC: stable@dpdk.org
> Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
> ---
>  drivers/net/mlx5/mlx5_rxtx.c | 10 ++++++----
>  1 file changed, 6 insertions(+), 4 deletions(-)

Thanks for addressing this issue.

Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Ferruh Yigit Jan. 20, 2017, 6:43 p.m. UTC | #2 
On 1/20/2017 4:56 PM, Adrien Mazarguil wrote:
> On Tue, Jan 17, 2017 at 04:51:55PM -0800, Yongseok Koh wrote:
>> When the WQ is wrapped around, it wrongly checks the condition when
>> resetting the pointer. It should be compared against the end of the queue,
>> not the beginning of the queue. And this isn't even needed when the length
>> of the copying data crosses the boundary.
>>
>> Fixes: e5291c280c08 ("net/mlx5: use work queue buffer as a raw buffer")
>>
>> CC: stable@dpdk.org
>> Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
>> ---
>>  drivers/net/mlx5/mlx5_rxtx.c | 10 ++++++----
>>  1 file changed, 6 insertions(+), 4 deletions(-)
> 
> Thanks for addressing this issue.
> 
> Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>

Fixes: fdcb0f53053b ("net/mlx5: use work queue buffer as a raw buffer")
Applied to dpdk-next-net/master, thanks.
diff mbox

Patch

diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx5_rxtx.c
index 2ae949295..f54db5b85 100644
--- a/drivers/net/mlx5/mlx5_rxtx.c
+++ b/drivers/net/mlx5/mlx5_rxtx.c
@@ -1037,11 +1037,13 @@  mlx5_tx_burst_mpw_inline(void *dpdk_txq, struct rte_mbuf **pkts,
 				rte_memcpy((void *)(uintptr_t)mpw.data.raw,
 					   (void *)addr,
 					   length);
-				mpw.data.raw += length;
+
+				if (length == max)
+					mpw.data.raw =
+						(volatile void *)txq->wqes;
+				else
+					mpw.data.raw += length;
 			}
-			if ((uintptr_t)mpw.data.raw ==
-			    (uintptr_t)tx_mlx5_wqe(txq, 1 << txq->wqe_n))
-				mpw.data.raw = (volatile void *)txq->wqes;
 			++mpw.pkts_n;
 			++j;
 			if (mpw.pkts_n == MLX5_MPW_DSEG_MAX) {