patch 'net/qede: fix Rx bulk' has been queued to stable release 21.11.1

[Kevin Traynor <ktraynor@redhat.com>]

Hi,

FYI, your patch has been queued to stable release 21.11.1

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 03/21/22. 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/kevintraynor/dpdk-stable

This queued commit can be viewed at:
https://github.com/kevintraynor/dpdk-stable/commit/bc19f2b75de23a6d8a971d29a55246c5dca56225

Thanks.

Kevin

---
From bc19f2b75de23a6d8a971d29a55246c5dca56225 Mon Sep 17 00:00:00 2001
From: Devendra Singh Rawat <dsinghrawat@marvell.com>
Date: Fri, 4 Mar 2022 17:38:32 +0530
Subject: [PATCH] net/qede: fix Rx bulk

[ upstream commit f65c7fbceca91b54200ca3dc5d27f2292e5d829f ]

qede_alloc_rx_bulk_mbufs() was trimming the number of requested
mbufs count to QEDE_MAX_BULK_ALLOC_COUNT.
The Rx callback was ignorant of this trimming and it was always
resetting the number of empty RX BD ring slots to 0.
This resulted in Rx BD ring getting into an inconsistent
state and ultimately the application fails to receive any traffic.

The fix trims the number of requested mbufs count before
making call to qede_alloc_rx_bulk_mbufs().
After qede_alloc_rx_bulk_mbufs() returns successfully, the
number of empty Rx BD ring slots are decremented by the
correct count.

Fixes: 8f2312474529 ("net/qede: fix performance bottleneck in Rx path")

Signed-off-by: Devendra Singh Rawat <dsinghrawat@marvell.com>
Signed-off-by: Rasesh Mody <rmody@marvell.com>
---
 drivers/net/qede/qede_rxtx.c | 68 ++++++++++++++++--------------------
 1 file changed, 31 insertions(+), 37 deletions(-)

diff --git a/drivers/net/qede/qede_rxtx.c b/drivers/net/qede/qede_rxtx.c
index 0b3b4c7ef6..bf3c26fd33 100644
--- a/drivers/net/qede/qede_rxtx.c
+++ b/drivers/net/qede/qede_rxtx.c
@@ -39,4 +39,5 @@ static inline int qede_alloc_rx_buffer(struct qede_rx_queue *rxq)
 static inline int qede_alloc_rx_bulk_mbufs(struct qede_rx_queue *rxq, int count)
 {
+	void *obj_p[QEDE_MAX_BULK_ALLOC_COUNT] __rte_cache_aligned;
 	struct rte_mbuf *mbuf = NULL;
 	struct eth_rx_bd *rx_bd;
@@ -44,24 +45,13 @@ static inline int qede_alloc_rx_bulk_mbufs(struct qede_rx_queue *rxq, int count)
 	int i, ret = 0;
 	uint16_t idx;
-	uint16_t mask = NUM_RX_BDS(rxq);
-
-	if (count > QEDE_MAX_BULK_ALLOC_COUNT)
-		count = QEDE_MAX_BULK_ALLOC_COUNT;
 
 	idx = rxq->sw_rx_prod & NUM_RX_BDS(rxq);
 
-	if (count > mask - idx + 1)
-		count = mask - idx + 1;
-
-	ret = rte_mempool_get_bulk(rxq->mb_pool, (void **)&rxq->sw_rx_ring[idx],
-				   count);
-
+	ret = rte_mempool_get_bulk(rxq->mb_pool, obj_p, count);
 	if (unlikely(ret)) {
 		PMD_RX_LOG(ERR, rxq,
 			   "Failed to allocate %d rx buffers "
 			    "sw_rx_prod %u sw_rx_cons %u mp entries %u free %u",
-			    count,
-			    rxq->sw_rx_prod & NUM_RX_BDS(rxq),
-			    rxq->sw_rx_cons & NUM_RX_BDS(rxq),
+			    count, idx, rxq->sw_rx_cons & NUM_RX_BDS(rxq),
 			    rte_mempool_avail_count(rxq->mb_pool),
 			    rte_mempool_in_use_count(rxq->mb_pool));
@@ -70,7 +60,10 @@ static inline int qede_alloc_rx_bulk_mbufs(struct qede_rx_queue *rxq, int count)
 
 	for (i = 0; i < count; i++) {
-		rte_prefetch0(rxq->sw_rx_ring[(idx + 1) & NUM_RX_BDS(rxq)]);
-		mbuf = rxq->sw_rx_ring[idx & NUM_RX_BDS(rxq)];
+		mbuf = obj_p[i];
+		if (likely(i < count - 1))
+			rte_prefetch0(obj_p[i + 1]);
 
+		idx = rxq->sw_rx_prod & NUM_RX_BDS(rxq);
+		rxq->sw_rx_ring[idx] = mbuf;
 		mapping = rte_mbuf_data_iova_default(mbuf);
 		rx_bd = (struct eth_rx_bd *)
@@ -78,7 +71,6 @@ static inline int qede_alloc_rx_bulk_mbufs(struct qede_rx_queue *rxq, int count)
 		rx_bd->addr.hi = rte_cpu_to_le_32(U64_HI(mapping));
 		rx_bd->addr.lo = rte_cpu_to_le_32(U64_LO(mapping));
-		idx++;
+		rxq->sw_rx_prod++;
 	}
-	rxq->sw_rx_prod = idx;
 
 	return 0;
@@ -1547,23 +1539,24 @@ qede_recv_pkts_regular(void *p_rxq, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 #endif
 	uint8_t offset, flags, bd_num;
-
+	uint16_t count = 0;
 
 	/* Allocate buffers that we used in previous loop */
 	if (rxq->rx_alloc_count) {
-		if (unlikely(qede_alloc_rx_bulk_mbufs(rxq,
-			     rxq->rx_alloc_count))) {
+		count = rxq->rx_alloc_count > QEDE_MAX_BULK_ALLOC_COUNT ?
+			QEDE_MAX_BULK_ALLOC_COUNT : rxq->rx_alloc_count;
+
+		if (unlikely(qede_alloc_rx_bulk_mbufs(rxq, count))) {
 			struct rte_eth_dev *dev;
 
 			PMD_RX_LOG(ERR, rxq,
-				   "New buffer allocation failed,"
-				   "dropping incoming packetn");
+				   "New buffers allocation failed,"
+				   "dropping incoming packets\n");
 			dev = &rte_eth_devices[rxq->port_id];
-			dev->data->rx_mbuf_alloc_failed +=
-							rxq->rx_alloc_count;
-			rxq->rx_alloc_errors += rxq->rx_alloc_count;
+			dev->data->rx_mbuf_alloc_failed += count;
+			rxq->rx_alloc_errors += count;
 			return 0;
 		}
 		qede_update_rx_prod(qdev, rxq);
-		rxq->rx_alloc_count = 0;
+		rxq->rx_alloc_count -= count;
 	}
 
@@ -1734,5 +1727,5 @@ next_cqe:
 
 	/* Request number of buffers to be allocated in next loop */
-	rxq->rx_alloc_count = rx_alloc_count;
+	rxq->rx_alloc_count += rx_alloc_count;
 
 	rxq->rcv_pkts += rx_pkt;
@@ -1774,23 +1767,24 @@ qede_recv_pkts(void *p_rxq, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 	uint32_t rss_hash;
 	int rx_alloc_count = 0;
-
+	uint16_t count = 0;
 
 	/* Allocate buffers that we used in previous loop */
 	if (rxq->rx_alloc_count) {
-		if (unlikely(qede_alloc_rx_bulk_mbufs(rxq,
-			     rxq->rx_alloc_count))) {
+		count = rxq->rx_alloc_count > QEDE_MAX_BULK_ALLOC_COUNT ?
+			QEDE_MAX_BULK_ALLOC_COUNT : rxq->rx_alloc_count;
+
+		if (unlikely(qede_alloc_rx_bulk_mbufs(rxq, count))) {
 			struct rte_eth_dev *dev;
 
 			PMD_RX_LOG(ERR, rxq,
-				   "New buffer allocation failed,"
-				   "dropping incoming packetn");
+				   "New buffers allocation failed,"
+				   "dropping incoming packets\n");
 			dev = &rte_eth_devices[rxq->port_id];
-			dev->data->rx_mbuf_alloc_failed +=
-							rxq->rx_alloc_count;
-			rxq->rx_alloc_errors += rxq->rx_alloc_count;
+			dev->data->rx_mbuf_alloc_failed += count;
+			rxq->rx_alloc_errors += count;
 			return 0;
 		}
 		qede_update_rx_prod(qdev, rxq);
-		rxq->rx_alloc_count = 0;
+		rxq->rx_alloc_count -= count;
 	}
 
@@ -2031,5 +2025,5 @@ next_cqe:
 
 	/* Request number of buffers to be allocated in next loop */
-	rxq->rx_alloc_count = rx_alloc_count;
+	rxq->rx_alloc_count += rx_alloc_count;
 
 	rxq->rcv_pkts += rx_pkt;
-- 
2.34.1

---
  Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- -	2022-03-16 15:14:12.330649311 +0000
+++ 0007-net-qede-fix-Rx-bulk.patch	2022-03-16 15:14:12.104847591 +0000
@@ -1 +1 @@
-From f65c7fbceca91b54200ca3dc5d27f2292e5d829f Mon Sep 17 00:00:00 2001
+From bc19f2b75de23a6d8a971d29a55246c5dca56225 Mon Sep 17 00:00:00 2001
@@ -5,0 +6,2 @@
+[ upstream commit f65c7fbceca91b54200ca3dc5d27f2292e5d829f ]
+
@@ -20 +21,0 @@
-Cc: stable@dpdk.org
@@ -29 +30 @@
-index 0c52568180..02fa1fcaa1 100644
+index 0b3b4c7ef6..bf3c26fd33 100644
@@ -87 +88 @@
-@@ -1545,23 +1537,24 @@ qede_recv_pkts_regular(void *p_rxq, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
+@@ -1547,23 +1539,24 @@ qede_recv_pkts_regular(void *p_rxq, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
@@ -121 +122 @@
-@@ -1732,5 +1725,5 @@ next_cqe:
+@@ -1734,5 +1727,5 @@ next_cqe:
@@ -128 +129 @@
-@@ -1772,23 +1765,24 @@ qede_recv_pkts(void *p_rxq, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
+@@ -1774,23 +1767,24 @@ qede_recv_pkts(void *p_rxq, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
@@ -162 +163 @@
-@@ -2029,5 +2023,5 @@ next_cqe:
+@@ -2031,5 +2025,5 @@ next_cqe: