Skip to contentSkip to conversation

vdpa/mlx5: fix completion queue polling

PATCH Applied Matan Azrad 2 participants 3 messages Sep 10, 2020 – Sep 18, 2020

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 vdpa/mlx5: fix completion queue polling

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")
---
 drivers/vdpa/mlx5/mlx5_vdpa_event.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)
drivers/vdpa/mlx5/mlx5_vdpa_event.c +3 -4
index 5a2d4fb..2672935 100644
@@ -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) ==
Signature · 1 line
1.8.3.1
Reviewed-by on v1 1/1
#1 lore raw
Quoted 11 lines · Matan Azrad

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.

Quoted 9 lines
Fixes c5f714e50b0e ("vdpa/mlx5: optimize completion queue poll")
---
 drivers/vdpa/mlx5/mlx5_vdpa_event.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

Thanks,
Maxime

#2 lore raw
In reply to Matan Azrad
Quoted 11 lines · Matan Azrad

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.

Quoted 8 lines
Fixes c5f714e50b0e ("vdpa/mlx5: optimize completion queue poll")
---
 drivers/vdpa/mlx5/mlx5_vdpa_event.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

Applied to dpdk-next-virtio/master.

Thanks,
Maxime