vdpa/mlx5: fix completion queue polling
Subsystems (2)
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.
--- drivers/vdpa/mlx5/mlx5_vdpa_event.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)
drivers/vdpa/mlx5/mlx5_vdpa_event.c +3 -4
@@ -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
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")Signed-off-by Matan Azrad <[email protected]>Acked-by Xueming Li <[email protected]>--- drivers/vdpa/mlx5/mlx5_vdpa_event.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)
Thanks,
Maxime
Maxime Coquelin
AppliedQuoted 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")Signed-off-by Matan Azrad <[email protected]>Acked-by Xueming Li <[email protected]>--- drivers/vdpa/mlx5/mlx5_vdpa_event.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)
Applied to dpdk-next-virtio/master.
Thanks,
Maxime