Merge branch 'virtio_net-add-per-queue-interrupt-coalescing-support'

Gavin Li says:

====================
virtio_net: add per queue interrupt coalescing support

Currently, coalescing parameters are grouped for all transmit and receive
virtqueues. This patch series add support to set or get the parameters for
a specified virtqueue.

When the traffic between virtqueues is unbalanced, for example, one virtqueue
is busy and another virtqueue is idle, then it will be very useful to
control coalescing parameters at the virtqueue granularity.

Example command:
$ ethtool -Q eth5 queue_mask 0x1 --coalesce tx-packets 10
Would set max_packets=10 to VQ 1.
$ ethtool -Q eth5 queue_mask 0x1 --coalesce rx-packets 10
Would set max_packets=10 to VQ 0.
$ ethtool -Q eth5 queue_mask 0x1 --show-coalesce
 Queue: 0
 Adaptive RX: off  TX: off
 stats-block-usecs: 0
 sample-interval: 0
 pkt-rate-low: 0
 pkt-rate-high: 0

 rx-usecs: 222
 rx-frames: 0
 rx-usecs-irq: 0
 rx-frames-irq: 256

 tx-usecs: 222
 tx-frames: 0
 tx-usecs-irq: 0
 tx-frames-irq: 256

 rx-usecs-low: 0
 rx-frame-low: 0
 tx-usecs-low: 0
 tx-frame-low: 0

 rx-usecs-high: 0
 rx-frame-high: 0
 tx-usecs-high: 0
 tx-frame-high: 0
====================

Link: https://lore.kernel.org/r/20230731070656.96411-1-gavinl@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 177 insertions, 24 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 1270c8d23463..c615bbf24c0d 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -126,6 +126,11 @@ static const struct virtnet_stat_desc virtnet_rq_stats_desc[] = {
 #define VIRTNET_SQ_STATS_LEN	ARRAY_SIZE(virtnet_sq_stats_desc)
 #define VIRTNET_RQ_STATS_LEN	ARRAY_SIZE(virtnet_rq_stats_desc)
 
+struct virtnet_interrupt_coalesce {
+	u32 max_packets;
+	u32 max_usecs;
+};
+
 /* Internal representation of a send virtqueue */
 struct send_queue {
 	/* Virtqueue associated with this send _queue */
@@ -139,6 +144,8 @@ struct send_queue {
 
 	struct virtnet_sq_stats stats;
 
+	struct virtnet_interrupt_coalesce intr_coal;
+
 	struct napi_struct napi;
 
 	/* Record whether sq is in reset state. */
@@ -156,6 +163,8 @@ struct receive_queue {
 
 	struct virtnet_rq_stats stats;
 
+	struct virtnet_interrupt_coalesce intr_coal;
+
 	/* Chain pages by the private ptr. */
 	struct page *pages;
 
@@ -207,6 +216,7 @@ struct control_buf {
 	struct virtio_net_ctrl_rss rss;
 	struct virtio_net_ctrl_coal_tx coal_tx;
 	struct virtio_net_ctrl_coal_rx coal_rx;
+	struct virtio_net_ctrl_coal_vq coal_vq;
 };
 
 struct virtnet_info {
@@ -281,10 +291,8 @@ struct virtnet_info {
 	u32 speed;
 
 	/* Interrupt coalescing settings */
-	u32 tx_usecs;
-	u32 rx_usecs;
-	u32 tx_max_packets;
-	u32 rx_max_packets;
+	struct virtnet_interrupt_coalesce intr_coal_tx;
+	struct virtnet_interrupt_coalesce intr_coal_rx;
 
 	unsigned long guest_offloads;
 	unsigned long guest_offloads_capable;
@@ -3056,8 +3064,8 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
 		return -EINVAL;
 
 	/* Save parameters */
-	vi->tx_usecs = ec->tx_coalesce_usecs;
-	vi->tx_max_packets = ec->tx_max_coalesced_frames;
+	vi->intr_coal_tx.max_usecs = ec->tx_coalesce_usecs;
+	vi->intr_coal_tx.max_packets = ec->tx_max_coalesced_frames;
 
 	vi->ctrl->coal_rx.rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs);
 	vi->ctrl->coal_rx.rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames);
@@ -3069,8 +3077,57 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
 		return -EINVAL;
 
 	/* Save parameters */
-	vi->rx_usecs = ec->rx_coalesce_usecs;
-	vi->rx_max_packets = ec->rx_max_coalesced_frames;
+	vi->intr_coal_rx.max_usecs = ec->rx_coalesce_usecs;
+	vi->intr_coal_rx.max_packets = ec->rx_max_coalesced_frames;
+
+	return 0;
+}
+
+static int virtnet_send_ctrl_coal_vq_cmd(struct virtnet_info *vi,
+					 u16 vqn, u32 max_usecs, u32 max_packets)
+{
+	struct scatterlist sgs;
+
+	vi->ctrl->coal_vq.vqn = cpu_to_le16(vqn);
+	vi->ctrl->coal_vq.coal.max_usecs = cpu_to_le32(max_usecs);
+	vi->ctrl->coal_vq.coal.max_packets = cpu_to_le32(max_packets);
+	sg_init_one(&sgs, &vi->ctrl->coal_vq, sizeof(vi->ctrl->coal_vq));
+
+	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
+				  VIRTIO_NET_CTRL_NOTF_COAL_VQ_SET,
+				  &sgs))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int virtnet_send_notf_coal_vq_cmds(struct virtnet_info *vi,
+					  struct ethtool_coalesce *ec,
+					  u16 queue)
+{
+	int err;
+
+	if (ec->rx_coalesce_usecs || ec->rx_max_coalesced_frames) {
+		err = virtnet_send_ctrl_coal_vq_cmd(vi, rxq2vq(queue),
+						    ec->rx_coalesce_usecs,
+						    ec->rx_max_coalesced_frames);
+		if (err)
+			return err;
+		/* Save parameters */
+		vi->rq[queue].intr_coal.max_usecs = ec->rx_coalesce_usecs;
+		vi->rq[queue].intr_coal.max_packets = ec->rx_max_coalesced_frames;
+	}
+
+	if (ec->tx_coalesce_usecs || ec->tx_max_coalesced_frames) {
+		err = virtnet_send_ctrl_coal_vq_cmd(vi, txq2vq(queue),
+						    ec->tx_coalesce_usecs,
+						    ec->tx_max_coalesced_frames);
+		if (err)
+			return err;
+		/* Save parameters */
+		vi->sq[queue].intr_coal.max_usecs = ec->tx_coalesce_usecs;
+		vi->sq[queue].intr_coal.max_packets = ec->tx_max_coalesced_frames;
+	}
 
 	return 0;
 }
@@ -3090,22 +3147,42 @@ static int virtnet_coal_params_supported(struct ethtool_coalesce *ec)
 	return 0;
 }
 
+static int virtnet_should_update_vq_weight(int dev_flags, int weight,
+					   int vq_weight, bool *should_update)
+{
+	if (weight ^ vq_weight) {
+		if (dev_flags & IFF_UP)
+			return -EBUSY;
+		*should_update = true;
+	}
+
+	return 0;
+}
+
 static int virtnet_set_coalesce(struct net_device *dev,
 				struct ethtool_coalesce *ec,
 				struct kernel_ethtool_coalesce *kernel_coal,
 				struct netlink_ext_ack *extack)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
-	int ret, i, napi_weight;
+	int ret, queue_number, napi_weight;
 	bool update_napi = false;
 
 	/* Can't change NAPI weight if the link is up */
 	napi_weight = ec->tx_max_coalesced_frames ? NAPI_POLL_WEIGHT : 0;
-	if (napi_weight ^ vi->sq[0].napi.weight) {
-		if (dev->flags & IFF_UP)
-			return -EBUSY;
-		else
-			update_napi = true;
+	for (queue_number = 0; queue_number < vi->max_queue_pairs; queue_number++) {
+		ret = virtnet_should_update_vq_weight(dev->flags, napi_weight,
+						      vi->sq[queue_number].napi.weight,
+						      &update_napi);
+		if (ret)
+			return ret;
+
+		if (update_napi) {
+			/* All queues that belong to [queue_number, vi->max_queue_pairs] will be
+			 * updated for the sake of simplicity, which might not be necessary
+			 */
+			break;
+		}
 	}
 
 	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL))
@@ -3117,8 +3194,8 @@ static int virtnet_set_coalesce(struct net_device *dev,
 		return ret;
 
 	if (update_napi) {
-		for (i = 0; i < vi->max_queue_pairs; i++)
-			vi->sq[i].napi.weight = napi_weight;
+		for (; queue_number < vi->max_queue_pairs; queue_number++)
+			vi->sq[queue_number].napi.weight = napi_weight;
 	}
 
 	return ret;
@@ -3132,10 +3209,67 @@ static int virtnet_get_coalesce(struct net_device *dev,
 	struct virtnet_info *vi = netdev_priv(dev);
 
 	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) {
-		ec->rx_coalesce_usecs = vi->rx_usecs;
-		ec->tx_coalesce_usecs = vi->tx_usecs;
-		ec->tx_max_coalesced_frames = vi->tx_max_packets;
-		ec->rx_max_coalesced_frames = vi->rx_max_packets;
+		ec->rx_coalesce_usecs = vi->intr_coal_rx.max_usecs;
+		ec->tx_coalesce_usecs = vi->intr_coal_tx.max_usecs;
+		ec->tx_max_coalesced_frames = vi->intr_coal_tx.max_packets;
+		ec->rx_max_coalesced_frames = vi->intr_coal_rx.max_packets;
+	} else {
+		ec->rx_max_coalesced_frames = 1;
+
+		if (vi->sq[0].napi.weight)
+			ec->tx_max_coalesced_frames = 1;
+	}
+
+	return 0;
+}
+
+static int virtnet_set_per_queue_coalesce(struct net_device *dev,
+					  u32 queue,
+					  struct ethtool_coalesce *ec)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	int ret, napi_weight;
+	bool update_napi = false;
+
+	if (queue >= vi->max_queue_pairs)
+		return -EINVAL;
+
+	/* Can't change NAPI weight if the link is up */
+	napi_weight = ec->tx_max_coalesced_frames ? NAPI_POLL_WEIGHT : 0;
+	ret = virtnet_should_update_vq_weight(dev->flags, napi_weight,
+					      vi->sq[queue].napi.weight,
+					      &update_napi);
+	if (ret)
+		return ret;
+
+	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL))
+		ret = virtnet_send_notf_coal_vq_cmds(vi, ec, queue);
+	else
+		ret = virtnet_coal_params_supported(ec);
+
+	if (ret)
+		return ret;
+
+	if (update_napi)
+		vi->sq[queue].napi.weight = napi_weight;
+
+	return 0;
+}
+
+static int virtnet_get_per_queue_coalesce(struct net_device *dev,
+					  u32 queue,
+					  struct ethtool_coalesce *ec)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+
+	if (queue >= vi->max_queue_pairs)
+		return -EINVAL;
+
+	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) {
+		ec->rx_coalesce_usecs = vi->rq[queue].intr_coal.max_usecs;
+		ec->tx_coalesce_usecs = vi->sq[queue].intr_coal.max_usecs;
+		ec->tx_max_coalesced_frames = vi->sq[queue].intr_coal.max_packets;
+		ec->rx_max_coalesced_frames = vi->rq[queue].intr_coal.max_packets;
 	} else {
 		ec->rx_max_coalesced_frames = 1;
 
@@ -3276,6 +3410,8 @@ static const struct ethtool_ops virtnet_ethtool_ops = {
 	.set_link_ksettings = virtnet_set_link_ksettings,
 	.set_coalesce = virtnet_set_coalesce,
 	.get_coalesce = virtnet_get_coalesce,
+	.set_per_queue_coalesce = virtnet_set_per_queue_coalesce,
+	.get_per_queue_coalesce = virtnet_get_per_queue_coalesce,
 	.get_rxfh_key_size = virtnet_get_rxfh_key_size,
 	.get_rxfh_indir_size = virtnet_get_rxfh_indir_size,
 	.get_rxfh = virtnet_get_rxfh,
@@ -3952,6 +4088,8 @@ static bool virtnet_validate_features(struct virtio_device *vdev)
 	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_HASH_REPORT,
 			     "VIRTIO_NET_F_CTRL_VQ") ||
 	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_NOTF_COAL,
+			     "VIRTIO_NET_F_CTRL_VQ") ||
+	     VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_VQ_NOTF_COAL,
 			     "VIRTIO_NET_F_CTRL_VQ"))) {
 		return false;
 	}
@@ -4119,10 +4257,10 @@ static int virtnet_probe(struct virtio_device *vdev)
 	}
 
 	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) {
-		vi->rx_usecs = 0;
-		vi->tx_usecs = 0;
-		vi->tx_max_packets = 0;
-		vi->rx_max_packets = 0;
+		vi->intr_coal_rx.max_usecs = 0;
+		vi->intr_coal_tx.max_usecs = 0;
+		vi->intr_coal_tx.max_packets = 0;
+		vi->intr_coal_rx.max_packets = 0;
 	}
 
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_HASH_REPORT))
@@ -4376,6 +4514,7 @@ static struct virtio_device_id id_table[] = {
 	VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \
 	VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY, \
 	VIRTIO_NET_F_RSS, VIRTIO_NET_F_HASH_REPORT, VIRTIO_NET_F_NOTF_COAL, \
+	VIRTIO_NET_F_VQ_NOTF_COAL, \
 	VIRTIO_NET_F_GUEST_HDRLEN
 
 static unsigned int features[] = {
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 12c1c9699935..cc65ef0f3c3e 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -56,6 +56,7 @@
 #define VIRTIO_NET_F_MQ	22	/* Device supports Receive Flow
 					 * Steering */
 #define VIRTIO_NET_F_CTRL_MAC_ADDR 23	/* Set MAC address */
+#define VIRTIO_NET_F_VQ_NOTF_COAL 52	/* Device supports virtqueue notification coalescing */
 #define VIRTIO_NET_F_NOTF_COAL	53	/* Device supports notifications coalescing */
 #define VIRTIO_NET_F_GUEST_USO4	54	/* Guest can handle USOv4 in. */
 #define VIRTIO_NET_F_GUEST_USO6	55	/* Guest can handle USOv6 in. */
@@ -391,5 +392,18 @@ struct virtio_net_ctrl_coal_rx {
 };
 
 #define VIRTIO_NET_CTRL_NOTF_COAL_RX_SET		1
+#define VIRTIO_NET_CTRL_NOTF_COAL_VQ_SET		2
+#define VIRTIO_NET_CTRL_NOTF_COAL_VQ_GET		3
+
+struct virtio_net_ctrl_coal {
+	__le32 max_packets;
+	__le32 max_usecs;
+};
+
+struct  virtio_net_ctrl_coal_vq {
+	__le16 vqn;
+	__le16 reserved;
+	struct virtio_net_ctrl_coal coal;
+};
 
 #endif /* _UAPI_LINUX_VIRTIO_NET_H */