net/mlx5e: Remove the outer loop when allocating legacy RQ WQEs

Legacy RQ WQEs are allocated in a loop in small batches (8 WQEs). As
partial batches are allowed, there is no point to have a loop in a loop,
so the outer loop is removed, and the batch size is increased up to the
total number of WQEs to allocate, still not smaller than 8.

Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Maxim Mikityanskiy 2022-09-30 09:28:54 -07:00 committed by Jakub Kicinski
parent 3f5fe0b2e6
commit 0b48223237
2 changed files with 17 additions and 22 deletions

View File

@ -424,7 +424,7 @@ static void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
mlx5e_free_rx_wqe(rq, wi, false); mlx5e_free_rx_wqe(rq, wi, false);
} }
static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk) static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk)
{ {
struct mlx5_wq_cyc *wq = &rq->wqe.wq; struct mlx5_wq_cyc *wq = &rq->wqe.wq;
int i; int i;
@ -805,38 +805,33 @@ static void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
{ {
struct mlx5_wq_cyc *wq = &rq->wqe.wq; struct mlx5_wq_cyc *wq = &rq->wqe.wq;
int wqe_bulk, count;
bool busy = false; bool busy = false;
u8 wqe_bulk; u16 head;
if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
return false; return false;
wqe_bulk = rq->wqe.info.wqe_bulk; if (mlx5_wq_cyc_missing(wq) < rq->wqe.info.wqe_bulk)
if (mlx5_wq_cyc_missing(wq) < wqe_bulk)
return false; return false;
if (rq->page_pool) if (rq->page_pool)
page_pool_nid_changed(rq->page_pool, numa_mem_id()); page_pool_nid_changed(rq->page_pool, numa_mem_id());
do { wqe_bulk = mlx5_wq_cyc_missing(wq);
u16 head = mlx5_wq_cyc_get_head(wq); head = mlx5_wq_cyc_get_head(wq);
int count;
u8 bulk;
/* Don't allow any newly allocated WQEs to share the same page /* Don't allow any newly allocated WQEs to share the same page with old
* with old WQEs that aren't completed yet. Stop earlier. * WQEs that aren't completed yet. Stop earlier.
*/ */
bulk = wqe_bulk - ((head + wqe_bulk) & rq->wqe.info.wqe_index_mask); wqe_bulk -= (head + wqe_bulk) & rq->wqe.info.wqe_index_mask;
count = mlx5e_alloc_rx_wqes(rq, head, bulk); count = mlx5e_alloc_rx_wqes(rq, head, wqe_bulk);
mlx5_wq_cyc_push_n(wq, count); mlx5_wq_cyc_push_n(wq, count);
if (unlikely(count != bulk)) { if (unlikely(count != wqe_bulk)) {
rq->stats->buff_alloc_err++; rq->stats->buff_alloc_err++;
busy = true; busy = true;
break; }
}
} while (mlx5_wq_cyc_missing(wq) >= wqe_bulk);
/* ensure wqes are visible to device before updating doorbell record */ /* ensure wqes are visible to device before updating doorbell record */
dma_wmb(); dma_wmb();

View File

@ -123,7 +123,7 @@ static inline void mlx5_wq_cyc_push(struct mlx5_wq_cyc *wq)
wq->cur_sz++; wq->cur_sz++;
} }
static inline void mlx5_wq_cyc_push_n(struct mlx5_wq_cyc *wq, u8 n) static inline void mlx5_wq_cyc_push_n(struct mlx5_wq_cyc *wq, u16 n)
{ {
wq->wqe_ctr += n; wq->wqe_ctr += n;
wq->cur_sz += n; wq->cur_sz += n;