patch 'net/netvsc: fix using Tx queue higher than Rx queues' has been queued to stable release 22.11.7

[luca.boccassi@gmail.com]

Hi,

FYI, your patch has been queued to stable release 22.11.7

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 11/14/24. 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/bluca/dpdk-stable

This queued commit can be viewed at:
https://github.com/bluca/dpdk-stable/commit/44c959d8c30e5383fcadfcb4be5a0475ca6fb828

Thanks.

Luca Boccassi

---
From 44c959d8c30e5383fcadfcb4be5a0475ca6fb828 Mon Sep 17 00:00:00 2001
From: Alan Elder <alan.elder@microsoft.com>
Date: Thu, 17 Oct 2024 12:20:29 -0700
Subject: [PATCH] net/netvsc: fix using Tx queue higher than Rx queues

[ upstream commit e90020535c03cf9e60448ba623cac3301f111dae ]

The previous code allowed the number of Tx queues to be set higher than
the number of Rx queues.  If a packet was sent on a Tx queue with index
>= number Rx queues there was a segfault due to accessing beyond the end
of the dev->data->rx_queues[] array.

This commit fixes the issue by creating an Rx queue for every Tx queue
meaning that an event buffer is allocated to handle receiving Tx
completion messages.

mbuf pool and Rx ring are not allocated for these additional Rx queues
and RSS configuration ensures that no packets are received on them.

Fixes: 4e9c73e96e83 ("net/netvsc: add Hyper-V network device")

Signed-off-by: Alan Elder <alan.elder@microsoft.com>
Signed-off-by: Long Li <longli@microsoft.com>
---
 drivers/net/netvsc/hn_ethdev.c |  9 +++++
 drivers/net/netvsc/hn_rxtx.c   | 69 +++++++++++++++++++++++++++++-----
 2 files changed, 69 insertions(+), 9 deletions(-)

diff --git a/drivers/net/netvsc/hn_ethdev.c b/drivers/net/netvsc/hn_ethdev.c
index d0bbc0a4c0..73db9d38d9 100644
--- a/drivers/net/netvsc/hn_ethdev.c
+++ b/drivers/net/netvsc/hn_ethdev.c
@@ -313,6 +313,15 @@ static int hn_rss_reta_update(struct rte_eth_dev *dev,
 
 		if (reta_conf[idx].mask & mask)
 			hv->rss_ind[i] = reta_conf[idx].reta[shift];
+
+		/*
+		 * Ensure we don't allow config that directs traffic to an Rx
+		 * queue that we aren't going to poll
+		 */
+		if (hv->rss_ind[i] >=  dev->data->nb_rx_queues) {
+			PMD_DRV_LOG(ERR, "RSS distributing traffic to invalid Rx queue");
+			return -EINVAL;
+		}
 	}
 
 	err = hn_rndis_conf_rss(hv, NDIS_RSS_FLAG_DISABLE);
diff --git a/drivers/net/netvsc/hn_rxtx.c b/drivers/net/netvsc/hn_rxtx.c
index 6496979f28..fc9df9f3b4 100644
--- a/drivers/net/netvsc/hn_rxtx.c
+++ b/drivers/net/netvsc/hn_rxtx.c
@@ -234,6 +234,17 @@ static void hn_reset_txagg(struct hn_tx_queue *txq)
 	txq->agg_prevpkt = NULL;
 }
 
+static void
+hn_rx_queue_free_common(struct hn_rx_queue *rxq)
+{
+	if (!rxq)
+		return;
+
+	rte_free(rxq->rxbuf_info);
+	rte_free(rxq->event_buf);
+	rte_free(rxq);
+}
+
 int
 hn_dev_tx_queue_setup(struct rte_eth_dev *dev,
 		      uint16_t queue_idx, uint16_t nb_desc,
@@ -243,6 +254,7 @@ hn_dev_tx_queue_setup(struct rte_eth_dev *dev,
 {
 	struct hn_data *hv = dev->data->dev_private;
 	struct hn_tx_queue *txq;
+	struct hn_rx_queue *rxq = NULL;
 	char name[RTE_MEMPOOL_NAMESIZE];
 	uint32_t tx_free_thresh;
 	int err = -ENOMEM;
@@ -301,6 +313,27 @@ hn_dev_tx_queue_setup(struct rte_eth_dev *dev,
 		goto error;
 	}
 
+	/*
+	 * If there are more Tx queues than Rx queues, allocate rx_queues
+	 * with event buffer so that Tx completion messages can still be
+	 * received
+	 */
+	if (queue_idx >= dev->data->nb_rx_queues) {
+		rxq = hn_rx_queue_alloc(hv, queue_idx, socket_id);
+
+		if (!rxq) {
+			err = -ENOMEM;
+			goto error;
+		}
+
+		/*
+		 * Don't allocate mbuf pool or rx ring.  RSS is always configured
+		 * to ensure packets aren't received by this Rx queue.
+		 */
+		rxq->mb_pool = NULL;
+		rxq->rx_ring = NULL;
+	}
+
 	txq->agg_szmax  = RTE_MIN(hv->chim_szmax, hv->rndis_agg_size);
 	txq->agg_pktmax = hv->rndis_agg_pkts;
 	txq->agg_align  = hv->rndis_agg_align;
@@ -311,12 +344,15 @@ hn_dev_tx_queue_setup(struct rte_eth_dev *dev,
 				     socket_id, tx_conf);
 	if (err == 0) {
 		dev->data->tx_queues[queue_idx] = txq;
+		if (rxq != NULL)
+			dev->data->rx_queues[queue_idx] = rxq;
 		return 0;
 	}
 
 error:
 	rte_mempool_free(txq->txdesc_pool);
 	rte_memzone_free(txq->tx_rndis_mz);
+	hn_rx_queue_free_common(rxq);
 	rte_free(txq);
 	return err;
 }
@@ -363,6 +399,12 @@ hn_dev_tx_queue_release(struct rte_eth_dev *dev, uint16_t qid)
 
 	if (!txq)
 		return;
+	/*
+	 * Free any Rx queues allocated for a Tx queue without a corresponding
+	 * Rx queue
+	 */
+	if (qid >= dev->data->nb_rx_queues)
+		hn_rx_queue_free_common(dev->data->rx_queues[qid]);
 
 	rte_mempool_free(txq->txdesc_pool);
 
@@ -552,10 +594,12 @@ static void hn_rxpkt(struct hn_rx_queue *rxq, struct hn_rx_bufinfo *rxb,
 		     const struct hn_rxinfo *info)
 {
 	struct hn_data *hv = rxq->hv;
-	struct rte_mbuf *m;
+	struct rte_mbuf *m = NULL;
 	bool use_extbuf = false;
 
-	m = rte_pktmbuf_alloc(rxq->mb_pool);
+	if (likely(rxq->mb_pool != NULL))
+		m = rte_pktmbuf_alloc(rxq->mb_pool);
+
 	if (unlikely(!m)) {
 		struct rte_eth_dev *dev =
 			&rte_eth_devices[rxq->port_id];
@@ -942,7 +986,15 @@ hn_dev_rx_queue_setup(struct rte_eth_dev *dev,
 	if (queue_idx == 0) {
 		rxq = hv->primary;
 	} else {
-		rxq = hn_rx_queue_alloc(hv, queue_idx, socket_id);
+		/*
+		 * If the number of Tx queues was previously greater than the
+		 * number of Rx queues, we may already have allocated an rxq.
+		 */
+		if (!dev->data->rx_queues[queue_idx])
+			rxq = hn_rx_queue_alloc(hv, queue_idx, socket_id);
+		else
+			rxq = dev->data->rx_queues[queue_idx];
+
 		if (!rxq)
 			return -ENOMEM;
 	}
@@ -975,9 +1027,10 @@ hn_dev_rx_queue_setup(struct rte_eth_dev *dev,
 
 fail:
 	rte_ring_free(rxq->rx_ring);
-	rte_free(rxq->rxbuf_info);
-	rte_free(rxq->event_buf);
-	rte_free(rxq);
+	/* Only free rxq if it was created in this function. */
+	if (!dev->data->rx_queues[queue_idx])
+		hn_rx_queue_free_common(rxq);
+
 	return error;
 }
 
@@ -998,9 +1051,7 @@ hn_rx_queue_free(struct hn_rx_queue *rxq, bool keep_primary)
 	if (keep_primary && rxq == rxq->hv->primary)
 		return;
 
-	rte_free(rxq->rxbuf_info);
-	rte_free(rxq->event_buf);
-	rte_free(rxq);
+	hn_rx_queue_free_common(rxq);
 }
 
 void
-- 
2.45.2

---
  Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- -	2024-11-12 22:06:58.765987433 +0000
+++ 0002-net-netvsc-fix-using-Tx-queue-higher-than-Rx-queues.patch	2024-11-12 22:06:58.627306574 +0000
@@ -1 +1 @@
-From e90020535c03cf9e60448ba623cac3301f111dae Mon Sep 17 00:00:00 2001
+From 44c959d8c30e5383fcadfcb4be5a0475ca6fb828 Mon Sep 17 00:00:00 2001
@@ -5,0 +6,2 @@
+[ upstream commit e90020535c03cf9e60448ba623cac3301f111dae ]
+
@@ -19 +20,0 @@
-Cc: stable@dpdk.org
@@ -29 +30 @@
-index f8cb05a118..1736cb5d07 100644
+index d0bbc0a4c0..73db9d38d9 100644
@@ -49 +50 @@
-index 870f62e5fa..52aedb001f 100644
+index 6496979f28..fc9df9f3b4 100644
@@ -52 +53 @@
-@@ -222,6 +222,17 @@ static void hn_reset_txagg(struct hn_tx_queue *txq)
+@@ -234,6 +234,17 @@ static void hn_reset_txagg(struct hn_tx_queue *txq)
@@ -70 +71 @@
-@@ -231,6 +242,7 @@ hn_dev_tx_queue_setup(struct rte_eth_dev *dev,
+@@ -243,6 +254,7 @@ hn_dev_tx_queue_setup(struct rte_eth_dev *dev,
@@ -78 +79 @@
-@@ -289,6 +301,27 @@ hn_dev_tx_queue_setup(struct rte_eth_dev *dev,
+@@ -301,6 +313,27 @@ hn_dev_tx_queue_setup(struct rte_eth_dev *dev,
@@ -106 +107 @@
-@@ -299,12 +332,15 @@ hn_dev_tx_queue_setup(struct rte_eth_dev *dev,
+@@ -311,12 +344,15 @@ hn_dev_tx_queue_setup(struct rte_eth_dev *dev,
@@ -122 +123 @@
-@@ -351,6 +387,12 @@ hn_dev_tx_queue_release(struct rte_eth_dev *dev, uint16_t qid)
+@@ -363,6 +399,12 @@ hn_dev_tx_queue_release(struct rte_eth_dev *dev, uint16_t qid)
@@ -135 +136 @@
-@@ -540,10 +582,12 @@ static void hn_rxpkt(struct hn_rx_queue *rxq, struct hn_rx_bufinfo *rxb,
+@@ -552,10 +594,12 @@ static void hn_rxpkt(struct hn_rx_queue *rxq, struct hn_rx_bufinfo *rxb,
@@ -150 +151 @@
-@@ -930,7 +974,15 @@ hn_dev_rx_queue_setup(struct rte_eth_dev *dev,
+@@ -942,7 +986,15 @@ hn_dev_rx_queue_setup(struct rte_eth_dev *dev,
@@ -167 +168 @@
-@@ -963,9 +1015,10 @@ hn_dev_rx_queue_setup(struct rte_eth_dev *dev,
+@@ -975,9 +1027,10 @@ hn_dev_rx_queue_setup(struct rte_eth_dev *dev,
@@ -181 +182 @@
-@@ -986,9 +1039,7 @@ hn_rx_queue_free(struct hn_rx_queue *rxq, bool keep_primary)
+@@ -998,9 +1051,7 @@ hn_rx_queue_free(struct hn_rx_queue *rxq, bool keep_primary)