vdpa/mlx5: fix completion queue polling
diff mbox series

Message ID 1599722434-432403-1-git-send-email-matan@nvidia.com
State Accepted
Delegated to: Maxime Coquelin
Headers show
Series
  • vdpa/mlx5: fix completion queue polling
Related show

Checks

Context Check Description
ci/iol-testing success Testing PASS
ci/iol-intel-Performance success Performance Testing PASS
ci/iol-intel-Functional success Functional Testing PASS
ci/iol-broadcom-Performance success Performance Testing PASS
ci/iol-broadcom-Functional success Functional Testing PASS
ci/travis-robot success Travis build: passed
ci/Intel-compilation success Compilation OK
ci/checkpatch success coding style OK

Commit Message

Matan Azrad Sept. 10, 2020, 7:20 a.m. UTC
The CQ polling is done in order to notify the guest about new traffic
bursts and to release FW resources for the next bursts management.

When HW is faster than SW, it may be that all the FW resources are busy
in SW due to late polling.
In this case, due to wrong WQE counter masking, the fullness
calculation of the completions number is 0 while the queue is full.

Change the WQE counter masking to 16-bit wideness instead of the CQ
size mask as defined by the CQE format.

Fixes: c5f714e50b0e ("vdpa/mlx5: optimize completion queue poll")
Cc: stable@dpdk.org

Signed-off-by: Matan Azrad <matan@nvidia.com>
Acked-by: Xueming Li <xuemingl@nvidia.com>
---
 drivers/vdpa/mlx5/mlx5_vdpa_event.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

Comments

Maxime Coquelin Sept. 18, 2020, 10:33 a.m. UTC | #1
On 9/10/20 9:20 AM, Matan Azrad wrote:
> The CQ polling is done in order to notify the guest about new traffic
> bursts and to release FW resources for the next bursts management.
> 
> When HW is faster than SW, it may be that all the FW resources are busy
> in SW due to late polling.
> In this case, due to wrong WQE counter masking, the fullness
> calculation of the completions number is 0 while the queue is full.
> 
> Change the WQE counter masking to 16-bit wideness instead of the CQ
> size mask as defined by the CQE format.
> 
> Fixes: c5f714e50b0e ("vdpa/mlx5: optimize completion queue poll")
> Cc: stable@dpdk.org
> 
> Signed-off-by: Matan Azrad <matan@nvidia.com>
> Acked-by: Xueming Li <xuemingl@nvidia.com>
> ---
>  drivers/vdpa/mlx5/mlx5_vdpa_event.c | 7 +++----
>  1 file changed, 3 insertions(+), 4 deletions(-)
> 


Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>

Thanks,
Maxime
Maxime Coquelin Sept. 18, 2020, 12:29 p.m. UTC | #2
On 9/10/20 9:20 AM, Matan Azrad wrote:
> The CQ polling is done in order to notify the guest about new traffic
> bursts and to release FW resources for the next bursts management.
> 
> When HW is faster than SW, it may be that all the FW resources are busy
> in SW due to late polling.
> In this case, due to wrong WQE counter masking, the fullness
> calculation of the completions number is 0 while the queue is full.
> 
> Change the WQE counter masking to 16-bit wideness instead of the CQ
> size mask as defined by the CQE format.
> 
> Fixes: c5f714e50b0e ("vdpa/mlx5: optimize completion queue poll")
> Cc: stable@dpdk.org
> 
> Signed-off-by: Matan Azrad <matan@nvidia.com>
> Acked-by: Xueming Li <xuemingl@nvidia.com>
> ---
>  drivers/vdpa/mlx5/mlx5_vdpa_event.c | 7 +++----
>  1 file changed, 3 insertions(+), 4 deletions(-)

Applied to dpdk-next-virtio/master.

Thanks,
Maxime

Patch
diff mbox series

diff --git a/drivers/vdpa/mlx5/mlx5_vdpa_event.c b/drivers/vdpa/mlx5/mlx5_vdpa_event.c
index 5a2d4fb..2672935 100644
--- a/drivers/vdpa/mlx5/mlx5_vdpa_event.c
+++ b/drivers/vdpa/mlx5/mlx5_vdpa_event.c
@@ -172,7 +172,7 @@ 
 	cq->callfd = callfd;
 	/* Init CQ to ones to be in HW owner in the start. */
 	cq->cqes[0].op_own = MLX5_CQE_OWNER_MASK;
-	cq->cqes[0].wqe_counter = rte_cpu_to_be_16(cq_size - 1);
+	cq->cqes[0].wqe_counter = rte_cpu_to_be_16(UINT16_MAX);
 	/* First arming. */
 	mlx5_vdpa_cq_arm(priv, cq);
 	return 0;
@@ -187,7 +187,6 @@ 
 	struct mlx5_vdpa_event_qp *eqp =
 				container_of(cq, struct mlx5_vdpa_event_qp, cq);
 	const unsigned int cq_size = 1 << cq->log_desc_n;
-	const unsigned int cq_mask = cq_size - 1;
 	union {
 		struct {
 			uint16_t wqe_counter;
@@ -196,13 +195,13 @@ 
 		};
 		uint32_t word;
 	} last_word;
-	uint16_t next_wqe_counter = cq->cq_ci & cq_mask;
+	uint16_t next_wqe_counter = cq->cq_ci;
 	uint16_t cur_wqe_counter;
 	uint16_t comp;
 
 	last_word.word = rte_read32(&cq->cqes[0].wqe_counter);
 	cur_wqe_counter = rte_be_to_cpu_16(last_word.wqe_counter);
-	comp = (cur_wqe_counter + 1u - next_wqe_counter) & cq_mask;
+	comp = cur_wqe_counter + (uint16_t)1 - next_wqe_counter;
 	if (comp) {
 		cq->cq_ci += comp;
 		MLX5_ASSERT(!!(cq->cq_ci & cq_size) ==