[v3,4/4] net/mlx5: engage free on completion queue
Checks
Commit Message
The free on completion queue keeps the indices of elts array,
all mbuf stored below this index should be freed on arrival
of normal send completion. In debug version it also contains
an index of completed transmitting descriptor (WQE) to check
queues synchronization.
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
---
drivers/net/mlx5/mlx5_rxtx.c | 33 +++++++++++++++++----------------
drivers/net/mlx5/mlx5_rxtx.h | 4 +---
drivers/net/mlx5/mlx5_txq.c | 2 --
3 files changed, 18 insertions(+), 21 deletions(-)
@@ -2043,8 +2043,7 @@ enum mlx5_txcmp_code {
uint16_t tail;
txq->wqe_pi = rte_be_to_cpu_16(last_cqe->wqe_counter);
- tail = ((volatile struct mlx5_wqe_cseg *)
- (txq->wqes + (txq->wqe_pi & txq->wqe_m)))->misc;
+ tail = txq->fcqs[(txq->cq_ci - 1) & txq->cqe_m];
if (likely(tail != txq->elts_tail)) {
mlx5_tx_free_elts(txq, tail, olx);
assert(tail == txq->elts_tail);
@@ -2095,6 +2094,7 @@ enum mlx5_txcmp_code {
* here, before we might perform SQ reset.
*/
rte_wmb();
+ txq->cq_ci = ci;
ret = mlx5_tx_error_cqe_handle
(txq, (volatile struct mlx5_err_cqe *)cqe);
if (unlikely(ret < 0)) {
@@ -2108,17 +2108,18 @@ enum mlx5_txcmp_code {
/*
* We are going to fetch all entries with
* MLX5_CQE_SYNDROME_WR_FLUSH_ERR status.
+ * The send queue is supposed to be empty.
*/
++ci;
+ txq->cq_pi = ci;
+ last_cqe = NULL;
continue;
}
/* Normal transmit completion. */
+ assert(ci != txq->cq_pi);
+ assert((txq->fcqs[ci & txq->cqe_m] >> 16) == cqe->wqe_counter);
++ci;
last_cqe = cqe;
-#ifndef NDEBUG
- if (txq->cq_pi)
- --txq->cq_pi;
-#endif
/*
* We have to restrict the amount of processed CQEs
* in one tx_burst routine call. The CQ may be large
@@ -2127,7 +2128,7 @@ enum mlx5_txcmp_code {
* multiple iterations may introduce significant
* latency.
*/
- if (--count == 0)
+ if (likely(--count == 0))
break;
} while (true);
if (likely(ci != txq->cq_ci)) {
@@ -2177,15 +2178,15 @@ enum mlx5_txcmp_code {
/* Request unconditional completion on last WQE. */
last->cseg.flags = RTE_BE32(MLX5_COMP_ALWAYS <<
MLX5_COMP_MODE_OFFSET);
- /* Save elts_head in unused "immediate" field of WQE. */
- last->cseg.misc = head;
- /*
- * A CQE slot must always be available. Count the
- * issued CEQ "always" request instead of production
- * index due to here can be CQE with errors and
- * difference with ci may become inconsistent.
- */
- assert(txq->cqe_s > ++txq->cq_pi);
+ /* Save elts_head in dedicated free on completion queue. */
+#ifdef NDEBUG
+ txq->fcqs[txq->cq_pi++ & txq->cqe_m] = head;
+#else
+ txq->fcqs[txq->cq_pi++ & txq->cqe_m] = head |
+ (last->cseg.opcode >> 8) << 16;
+#endif
+ /* A CQE slot must always be available. */
+ assert((txq->cq_pi - txq->cq_ci) <= txq->cqe_s);
}
}
@@ -273,9 +273,7 @@ struct mlx5_txq_data {
uint16_t wqe_thres; /* WQE threshold to request completion in CQ. */
/* WQ related fields. */
uint16_t cq_ci; /* Consumer index for completion queue. */
-#ifndef NDEBUG
- uint16_t cq_pi; /* Counter of issued CQE "always" requests. */
-#endif
+ uint16_t cq_pi; /* Production index for completion queue. */
uint16_t cqe_s; /* Number of CQ elements. */
uint16_t cqe_m; /* Mask for CQ indices. */
/* CQ related fields. */
@@ -717,9 +717,7 @@ struct mlx5_txq_obj *
txq_data->cq_db = cq_info.dbrec;
txq_data->cqes = (volatile struct mlx5_cqe *)cq_info.buf;
txq_data->cq_ci = 0;
-#ifndef NDEBUG
txq_data->cq_pi = 0;
-#endif
txq_data->wqe_ci = 0;
txq_data->wqe_pi = 0;
txq_data->wqe_comp = 0;