[dpdk-stable] patch 'net/bnxt: fix scalar Tx completion handling' has been queued to stable release 19.11.10

[christian.ehrhardt@canonical.com]

Hi,

FYI, your patch has been queued to stable release 19.11.10

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 08/12/21. So please
shout if anyone has objections.

Also note that after the patch there's a diff of the upstream commit vs the
patch applied to the branch. This will indicate if there was any rebasing
needed to apply to the stable branch. If there were code changes for rebasing
(ie: not only metadata diffs), please double check that the rebase was
correctly done.

Queued patches are on a temporary branch at:
https://github.com/cpaelzer/dpdk-stable-queue

This queued commit can be viewed at:
https://github.com/cpaelzer/dpdk-stable-queue/commit/b2af7f5effd596659e41375c1087c0b2ac6836bc

Thanks.

Christian Ehrhardt <christian.ehrhardt@canonical.com>

---
From b2af7f5effd596659e41375c1087c0b2ac6836bc Mon Sep 17 00:00:00 2001
From: Lance Richardson <lance.richardson@broadcom.com>
Date: Wed, 16 Jun 2021 13:55:22 -0400
Subject: [PATCH] net/bnxt: fix scalar Tx completion handling

[ upstream commit 2b5a36f4df0c00407117ed6f8f9444dd943b4f4c ]

Preserve the raw (unmasked) transmit completion ring
consumer index.

Remove cache prefetches that have no measurable performance
benefit.

Fixes: c7de4195cc4c ("net/bnxt: modify ring index logic")

Signed-off-by: Lance Richardson <lance.richardson@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
---
 drivers/net/bnxt/bnxt_txr.c | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/drivers/net/bnxt/bnxt_txr.c b/drivers/net/bnxt/bnxt_txr.c
index a3543e7cea..892f8c1a4c 100644
--- a/drivers/net/bnxt/bnxt_txr.c
+++ b/drivers/net/bnxt/bnxt_txr.c
@@ -398,30 +398,26 @@ static void bnxt_tx_cmp(struct bnxt_tx_queue *txq, int nr_pkts)
 
 static int bnxt_handle_tx_cp(struct bnxt_tx_queue *txq)
 {
+	uint32_t nb_tx_pkts = 0, cons, ring_mask, opaque;
 	struct bnxt_cp_ring_info *cpr = txq->cp_ring;
 	uint32_t raw_cons = cpr->cp_raw_cons;
-	uint32_t cons;
-	uint32_t nb_tx_pkts = 0;
+	struct bnxt_ring *cp_ring_struct;
 	struct tx_cmpl *txcmp;
-	struct cmpl_base *cp_desc_ring = cpr->cp_desc_ring;
-	struct bnxt_ring *cp_ring_struct = cpr->cp_ring_struct;
-	uint32_t ring_mask = cp_ring_struct->ring_mask;
-	uint32_t opaque = 0;
 
 	if (bnxt_tx_bds_in_hw(txq) < txq->tx_free_thresh)
 		return 0;
 
+	cp_ring_struct = cpr->cp_ring_struct;
+	ring_mask = cp_ring_struct->ring_mask;
+
 	do {
 		cons = RING_CMPL(ring_mask, raw_cons);
 		txcmp = (struct tx_cmpl *)&cpr->cp_desc_ring[cons];
-		rte_prefetch_non_temporal(&cp_desc_ring[(cons + 2) &
-							ring_mask]);
 
-		if (!CMPL_VALID(txcmp, cpr->valid))
+		if (!CMP_VALID(txcmp, raw_cons, cp_ring_struct))
 			break;
-		opaque = rte_cpu_to_le_32(txcmp->opaque);
-		NEXT_CMPL(cpr, cons, cpr->valid, 1);
-		rte_prefetch0(&cp_desc_ring[cons]);
+
+		opaque = rte_le_to_cpu_32(txcmp->opaque);
 
 		if (CMP_TYPE(txcmp) == TX_CMPL_TYPE_TX_L2)
 			nb_tx_pkts += opaque;
@@ -429,9 +425,11 @@ static int bnxt_handle_tx_cp(struct bnxt_tx_queue *txq)
 			RTE_LOG_DP(ERR, PMD,
 					"Unhandled CMP type %02x\n",
 					CMP_TYPE(txcmp));
-		raw_cons = cons;
+		raw_cons = NEXT_RAW_CMP(raw_cons);
 	} while (nb_tx_pkts < ring_mask);
 
+	cpr->valid = !!(raw_cons & cp_ring_struct->ring_size);
+
 	if (nb_tx_pkts) {
 		bnxt_tx_cmp(txq, nb_tx_pkts);
 		cpr->cp_raw_cons = raw_cons;
-- 
2.32.0

---
  Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- -	2021-08-10 15:11:14.960344021 +0200
+++ 0050-net-bnxt-fix-scalar-Tx-completion-handling.patch	2021-08-10 15:11:13.026638158 +0200
@@ -1 +1 @@
-From 2b5a36f4df0c00407117ed6f8f9444dd943b4f4c Mon Sep 17 00:00:00 2001
+From b2af7f5effd596659e41375c1087c0b2ac6836bc Mon Sep 17 00:00:00 2001
@@ -5,0 +6,2 @@
+[ upstream commit 2b5a36f4df0c00407117ed6f8f9444dd943b4f4c ]
+
@@ -13 +14,0 @@
-Cc: stable@dpdk.org
@@ -22 +23 @@
-index 27459960de..54eaab34a0 100644
+index a3543e7cea..892f8c1a4c 100644
@@ -25 +26 @@
-@@ -444,30 +444,26 @@ static void bnxt_tx_cmp(struct bnxt_tx_queue *txq, int nr_pkts)
+@@ -398,30 +398,26 @@ static void bnxt_tx_cmp(struct bnxt_tx_queue *txq, int nr_pkts)
@@ -64 +65 @@
-@@ -475,9 +471,11 @@ static int bnxt_handle_tx_cp(struct bnxt_tx_queue *txq)
+@@ -429,9 +425,11 @@ static int bnxt_handle_tx_cp(struct bnxt_tx_queue *txq)
@@ -75,2 +76,2 @@
- 		if (txq->offloads & DEV_TX_OFFLOAD_MBUF_FAST_FREE)
- 			bnxt_tx_cmp_fast(txq, nb_tx_pkts);
+ 		bnxt_tx_cmp(txq, nb_tx_pkts);
+ 		cpr->cp_raw_cons = raw_cons;