[dpdk-stable] patch 'net/bnx2x: fix to sync fastpath Rx queue access' has been queued to stable release 19.11.1

[luca.boccassi at gmail.com]

Hi,

FYI, your patch has been queued to stable release 19.11.1

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 02/13/20. 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.

Thanks.

Luca Boccassi

---
>From 5fb6087d0e72af502978ae25ee537550fe250af5 Mon Sep 17 00:00:00 2001
From: Rasesh Mody <rmody at marvell.com>
Date: Sun, 26 Jan 2020 14:54:19 -0800
Subject: [PATCH] net/bnx2x: fix to sync fastpath Rx queue access

[ upstream commit 141c86f55f734c4f8b9ad3129b6e58807b5c4577 ]

PMD handles fast path completions in the Rx handler and control path
completions in the interrupt handler. They both are processing
completions from the same fastpath completion queue. There is a
potential for race condition when these two paths are processing
the completions from the same queue and trying to updating Rx Producer.

Add a fastpath Rx lock between these two paths to close this race.

Fixes: 540a211084a7 ("bnx2x: driver core")

Signed-off-by: Rasesh Mody <rmody at marvell.com>
---
 drivers/net/bnx2x/bnx2x.c      | 12 ++++++++++++
 drivers/net/bnx2x/bnx2x.h      |  3 +++
 drivers/net/bnx2x/bnx2x_rxtx.c |  8 +++++++-
 3 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bnx2x/bnx2x.c b/drivers/net/bnx2x/bnx2x.c
index 50e289b286..0b4030e2b9 100644
--- a/drivers/net/bnx2x/bnx2x.c
+++ b/drivers/net/bnx2x/bnx2x.c
@@ -1167,6 +1167,10 @@ static int bnx2x_has_rx_work(struct bnx2x_fastpath *fp)
 	if (unlikely((rx_cq_cons_sb & MAX_RCQ_ENTRIES(rxq)) ==
 		     MAX_RCQ_ENTRIES(rxq)))
 		rx_cq_cons_sb++;
+
+	PMD_RX_LOG(DEBUG, "hw CQ cons = %d, sw CQ cons = %d",
+		   rx_cq_cons_sb, rxq->rx_cq_head);
+
 	return rxq->rx_cq_head != rx_cq_cons_sb;
 }
 
@@ -1249,9 +1253,12 @@ static uint8_t bnx2x_rxeof(struct bnx2x_softc *sc, struct bnx2x_fastpath *fp)
 	uint16_t bd_cons, bd_prod, bd_prod_fw, comp_ring_cons;
 	uint16_t hw_cq_cons, sw_cq_cons, sw_cq_prod;
 
+	rte_spinlock_lock(&(fp)->rx_mtx);
+
 	rxq = sc->rx_queues[fp->index];
 	if (!rxq) {
 		PMD_RX_LOG(ERR, "RX queue %d is NULL", fp->index);
+		rte_spinlock_unlock(&(fp)->rx_mtx);
 		return 0;
 	}
 
@@ -1321,9 +1328,14 @@ next_cqe:
 	rxq->rx_cq_head = sw_cq_cons;
 	rxq->rx_cq_tail = sw_cq_prod;
 
+	PMD_RX_LOG(DEBUG, "BD prod = %d, sw CQ prod = %d",
+		   bd_prod_fw, sw_cq_prod);
+
 	/* Update producers */
 	bnx2x_update_rx_prod(sc, fp, bd_prod_fw, sw_cq_prod);
 
+	rte_spinlock_unlock(&(fp)->rx_mtx);
+
 	return sw_cq_cons != hw_cq_cons;
 }
 
diff --git a/drivers/net/bnx2x/bnx2x.h b/drivers/net/bnx2x/bnx2x.h
index 3383c76759..1dbc98197d 100644
--- a/drivers/net/bnx2x/bnx2x.h
+++ b/drivers/net/bnx2x/bnx2x.h
@@ -360,6 +360,9 @@ struct bnx2x_fastpath {
 	/* pointer back to parent structure */
 	struct bnx2x_softc *sc;
 
+	/* Used to synchronize fastpath Rx access */
+	rte_spinlock_t rx_mtx;
+
 	/* status block */
 	struct bnx2x_dma                 sb_dma;
 	union bnx2x_host_hc_status_block status_block;
diff --git a/drivers/net/bnx2x/bnx2x_rxtx.c b/drivers/net/bnx2x/bnx2x_rxtx.c
index ae97dfee36..0d77035844 100644
--- a/drivers/net/bnx2x/bnx2x_rxtx.c
+++ b/drivers/net/bnx2x/bnx2x_rxtx.c
@@ -346,6 +346,8 @@ bnx2x_recv_pkts(void *p_rxq, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 	uint16_t len, pad;
 	struct rte_mbuf *rx_mb = NULL;
 
+	rte_spinlock_lock(&(fp)->rx_mtx);
+
 	hw_cq_cons = le16toh(*fp->rx_cq_cons_sb);
 	if ((hw_cq_cons & USABLE_RCQ_ENTRIES_PER_PAGE) ==
 			USABLE_RCQ_ENTRIES_PER_PAGE) {
@@ -357,8 +359,10 @@ bnx2x_recv_pkts(void *p_rxq, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 	sw_cq_cons = rxq->rx_cq_head;
 	sw_cq_prod = rxq->rx_cq_tail;
 
-	if (sw_cq_cons == hw_cq_cons)
+	if (sw_cq_cons == hw_cq_cons) {
+		rte_spinlock_unlock(&(fp)->rx_mtx);
 		return 0;
+	}
 
 	while (nb_rx < nb_pkts && sw_cq_cons != hw_cq_cons) {
 
@@ -439,6 +443,8 @@ next_rx:
 
 	bnx2x_upd_rx_prod_fast(sc, fp, bd_prod, sw_cq_prod);
 
+	rte_spinlock_unlock(&(fp)->rx_mtx);
+
 	return nb_rx;
 }
 
-- 
2.20.1

---
  Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- -	2020-02-11 11:17:44.121928415 +0000
+++ 0158-net-bnx2x-fix-to-sync-fastpath-Rx-queue-access.patch	2020-02-11 11:17:38.760008079 +0000
@@ -1,8 +1,10 @@
-From 141c86f55f734c4f8b9ad3129b6e58807b5c4577 Mon Sep 17 00:00:00 2001
+From 5fb6087d0e72af502978ae25ee537550fe250af5 Mon Sep 17 00:00:00 2001
 From: Rasesh Mody <rmody at marvell.com>
 Date: Sun, 26 Jan 2020 14:54:19 -0800
 Subject: [PATCH] net/bnx2x: fix to sync fastpath Rx queue access
 
+[ upstream commit 141c86f55f734c4f8b9ad3129b6e58807b5c4577 ]
+
 PMD handles fast path completions in the Rx handler and control path
 completions in the interrupt handler. They both are processing
 completions from the same fastpath completion queue. There is a
@@ -12,7 +14,6 @@
 Add a fastpath Rx lock between these two paths to close this race.
 
 Fixes: 540a211084a7 ("bnx2x: driver core")
-Cc: stable at dpdk.org
 
 Signed-off-by: Rasesh Mody <rmody at marvell.com>
 ---