Merge branch 'virtio_net-make-rss-interact-properly-with-queue-number'

Philo Lu says:

====================
virtio_net: Make RSS interact properly with queue number

With this patch set, RSS updates with queue_pairs changing:
- When virtnet_probe, init default rss and commit
- When queue_pairs changes _without_ user rss configuration, update rss
  with the new queue number
- When queue_pairs changes _with_ user rss configuration, keep rss as user
  configured

Patch 1 and 2 fix possible out of bound errors for indir_table and key.
Patch 3 and 4 add RSS update in probe() and set_queues().
====================

Link: https://patch.msgid.link/20241104085706.13872-1-lulie@linux.alibaba.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

drivers/net/virtio_net.c

@@ -368,15 +368,16 @@ struct receive_queue {
  * because table sizes may be differ according to the device configuration.
  */
 #define VIRTIO_NET_RSS_MAX_KEY_SIZE     40
-#define VIRTIO_NET_RSS_MAX_TABLE_LEN    128
 struct virtio_net_ctrl_rss {
 	u32 hash_types;
 	u16 indirection_table_mask;
 	u16 unclassified_queue;
-	u16 indirection_table[VIRTIO_NET_RSS_MAX_TABLE_LEN];
+	u16 hash_cfg_reserved; /* for HASH_CONFIG (see virtio_net_hash_config for details) */
 	u16 max_tx_vq;
 	u8 hash_key_length;
 	u8 key[VIRTIO_NET_RSS_MAX_KEY_SIZE];
+
+	u16 *indirection_table;
 };
 
 /* Control VQ buffers: protected by the rtnl lock */
@@ -512,6 +513,25 @@ static struct sk_buff *virtnet_skb_append_frag(struct sk_buff *head_skb,
 					       struct page *page, void *buf,
 					       int len, int truesize);
 
+static int rss_indirection_table_alloc(struct virtio_net_ctrl_rss *rss, u16 indir_table_size)
+{
+	if (!indir_table_size) {
+		rss->indirection_table = NULL;
+		return 0;
+	}
+
+	rss->indirection_table = kmalloc_array(indir_table_size, sizeof(u16), GFP_KERNEL);
+	if (!rss->indirection_table)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void rss_indirection_table_free(struct virtio_net_ctrl_rss *rss)
+{
+	kfree(rss->indirection_table);
+}
+
 static bool is_xdp_frame(void *ptr)
 {
 	return (unsigned long)ptr & VIRTIO_XDP_FLAG;
@@ -3374,15 +3394,59 @@ static void virtnet_ack_link_announce(struct virtnet_info *vi)
 		dev_warn(&vi->dev->dev, "Failed to ack link announce.\n");
 }
 
+static bool virtnet_commit_rss_command(struct virtnet_info *vi);
+
+static void virtnet_rss_update_by_qpairs(struct virtnet_info *vi, u16 queue_pairs)
+{
+	u32 indir_val = 0;
+	int i = 0;
+
+	for (; i < vi->rss_indir_table_size; ++i) {
+		indir_val = ethtool_rxfh_indir_default(i, queue_pairs);
+		vi->rss.indirection_table[i] = indir_val;
+	}
+	vi->rss.max_tx_vq = queue_pairs;
+}
+
 static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 {
 	struct virtio_net_ctrl_mq *mq __free(kfree) = NULL;
-	struct scatterlist sg;
+	struct virtio_net_ctrl_rss old_rss;
 	struct net_device *dev = vi->dev;
+	struct scatterlist sg;
 
 	if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
 		return 0;
 
+	/* Firstly check if we need update rss. Do updating if both (1) rss enabled and
+	 * (2) no user configuration.
+	 *
+	 * During rss command processing, device updates queue_pairs using rss.max_tx_vq. That is,
+	 * the device updates queue_pairs together with rss, so we can skip the sperate queue_pairs
+	 * update (VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET below) and return directly.
+	 */
+	if (vi->has_rss && !netif_is_rxfh_configured(dev)) {
+		memcpy(&old_rss, &vi->rss, sizeof(old_rss));
+		if (rss_indirection_table_alloc(&vi->rss, vi->rss_indir_table_size)) {
+			vi->rss.indirection_table = old_rss.indirection_table;
+			return -ENOMEM;
+		}
+
+		virtnet_rss_update_by_qpairs(vi, queue_pairs);
+
+		if (!virtnet_commit_rss_command(vi)) {
+			/* restore ctrl_rss if commit_rss_command failed */
+			rss_indirection_table_free(&vi->rss);
+			memcpy(&vi->rss, &old_rss, sizeof(old_rss));
+
+			dev_warn(&dev->dev, "Fail to set num of queue pairs to %d, because committing RSS failed\n",
+				 queue_pairs);
+			return -EINVAL;
+		}
+		rss_indirection_table_free(&old_rss);
+		goto succ;
+	}
+
 	mq = kzalloc(sizeof(*mq), GFP_KERNEL);
 	if (!mq)
 		return -ENOMEM;
@@ -3395,12 +3459,12 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 		dev_warn(&dev->dev, "Fail to set num of queue pairs to %d\n",
 			 queue_pairs);
 		return -EINVAL;
-	} else {
-		vi->curr_queue_pairs = queue_pairs;
-		/* virtnet_open() will refill when device is going to up. */
-		if (dev->flags & IFF_UP)
-			schedule_delayed_work(&vi->refill, 0);
 	}
+succ:
+	vi->curr_queue_pairs = queue_pairs;
+	/* virtnet_open() will refill when device is going to up. */
+	if (dev->flags & IFF_UP)
+		schedule_delayed_work(&vi->refill, 0);
 
 	return 0;
 }
@@ -3828,11 +3892,15 @@ static bool virtnet_commit_rss_command(struct virtnet_info *vi)
 	/* prepare sgs */
 	sg_init_table(sgs, 4);
 
-	sg_buf_size = offsetof(struct virtio_net_ctrl_rss, indirection_table);
+	sg_buf_size = offsetof(struct virtio_net_ctrl_rss, hash_cfg_reserved);
 	sg_set_buf(&sgs[0], &vi->rss, sg_buf_size);
 
-	sg_buf_size = sizeof(uint16_t) * (vi->rss.indirection_table_mask + 1);
+	if (vi->has_rss) {
-	sg_set_buf(&sgs[1], vi->rss.indirection_table, sg_buf_size);
+		sg_buf_size = sizeof(uint16_t) * vi->rss_indir_table_size;
+		sg_set_buf(&sgs[1], vi->rss.indirection_table, sg_buf_size);
+	} else {
+		sg_set_buf(&sgs[1], &vi->rss.hash_cfg_reserved, sizeof(uint16_t));
+	}
 
 	sg_buf_size = offsetof(struct virtio_net_ctrl_rss, key)
 			- offsetof(struct virtio_net_ctrl_rss, max_tx_vq);
@@ -3856,21 +3924,14 @@ err:
 
 static void virtnet_init_default_rss(struct virtnet_info *vi)
 {
-	u32 indir_val = 0;
-	int i = 0;
-
 	vi->rss.hash_types = vi->rss_hash_types_supported;
 	vi->rss_hash_types_saved = vi->rss_hash_types_supported;
 	vi->rss.indirection_table_mask = vi->rss_indir_table_size
 						? vi->rss_indir_table_size - 1 : 0;
 	vi->rss.unclassified_queue = 0;
 
-	for (; i < vi->rss_indir_table_size; ++i) {
+	virtnet_rss_update_by_qpairs(vi, vi->curr_queue_pairs);
-		indir_val = ethtool_rxfh_indir_default(i, vi->curr_queue_pairs);
-		vi->rss.indirection_table[i] = indir_val;
-	}
 
-	vi->rss.max_tx_vq = vi->has_rss ? vi->curr_queue_pairs : 0;
 	vi->rss.hash_key_length = vi->rss_key_size;
 
 	netdev_rss_key_fill(vi->rss.key, vi->rss_key_size);
@@ -6420,10 +6481,19 @@ static int virtnet_probe(struct virtio_device *vdev)
 			virtio_cread16(vdev, offsetof(struct virtio_net_config,
 				rss_max_indirection_table_length));
 	}
+	err = rss_indirection_table_alloc(&vi->rss, vi->rss_indir_table_size);
+	if (err)
+		goto free;
 
 	if (vi->has_rss || vi->has_rss_hash_report) {
 		vi->rss_key_size =
 			virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size));
+		if (vi->rss_key_size > VIRTIO_NET_RSS_MAX_KEY_SIZE) {
+			dev_err(&vdev->dev, "rss_max_key_size=%u exceeds the limit %u.\n",
+				vi->rss_key_size, VIRTIO_NET_RSS_MAX_KEY_SIZE);
+			err = -EINVAL;
+			goto free;
+		}
 
 		vi->rss_hash_types_supported =
 		    virtio_cread32(vdev, offsetof(struct virtio_net_config, supported_hash_types));
@@ -6551,6 +6621,15 @@ static int virtnet_probe(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
+	if (vi->has_rss || vi->has_rss_hash_report) {
+		if (!virtnet_commit_rss_command(vi)) {
+			dev_warn(&vdev->dev, "RSS disabled because committing failed.\n");
+			dev->hw_features &= ~NETIF_F_RXHASH;
+			vi->has_rss_hash_report = false;
+			vi->has_rss = false;
+		}
+	}
+
 	virtnet_set_queues(vi, vi->curr_queue_pairs);
 
 	/* a random MAC address has been assigned, notify the device.
@@ -6674,6 +6753,8 @@ static void virtnet_remove(struct virtio_device *vdev)
 
 	remove_vq_common(vi);
 
+	rss_indirection_table_free(&vi->rss);
+
 	free_netdev(vi->dev);
 }