[PATCH net-next v4 0/4] virtio-net: support dynamic coalescing moderation

[PATCH net-next v4 0/4] virtio-net: support dynamic coalescing moderation

[Heng Qi]

Now, virtio-net already supports per-queue moderation parameter
setting. Based on this, we use the linux dimlib to support
dynamic coalescing moderation for virtio-net.

Due to some scheduling issues, we only support and test the rx dim.

Some test results:

I. Sockperf UDP
=================================================
1. Env
rxq_0 with affinity to cpu_0.

2. Cmd
client: taskset -c 0 sockperf tp -p 8989 -i $IP -t 10 -m 16B
server: taskset -c 0 sockperf sr -p 8989

3. Result
dim off: 1143277.00 rxpps, throughput 17.844 MBps, cpu is 100%.
dim on:  1124161.00 rxpps, throughput 17.610 MBps, cpu is 83.5%.
=================================================

II. Redis
=================================================
1. Env
There are 8 rxqs, and rxq_i with affinity to cpu_i.

2. Result
When all cpus are 100%, ops/sec of memtier_benchmark client is
dim off:  978437.23
dim on:  1143638.28
=================================================

III. Nginx
=================================================
1. Env
There are 8 rxqs and rxq_i with affinity to cpu_i.

2. Result
When all cpus are 100%, requests/sec of wrk client is
dim off:  877931.67
dim on:  1019160.31
=================================================

IV. Latency of sockperf udp
=================================================
1. Rx cmd
taskset -c 0 sockperf sr -p 8989

2. Tx cmd
taskset -c 0 sockperf pp -i ${ip} -p 8989 -t 10

After running this cmd 5 times and averaging the results,

3. Result
dim off: 17.7735 usec
dim on:  18.0110 usec
=================================================

Changelog:
v3->v4:
- Patch(5/5): drop.

v2->v3:
- Patch(4/5): some minor modifications.

v1->v2:
- Patch(2/5): a minor fix.
- Patch(4/5):
   - improve the judgment of dim switch conditions.
   - Cancel the work when vq reset. 
- Patch(5/5): drop the tx dim implementation.

Heng Qi (4):
  virtio-net: returns whether napi is complete
  virtio-net: separate rx/tx coalescing moderation cmds
  virtio-net: extract virtqueue coalescig cmd for reuse
  virtio-net: support rx netdim

 drivers/net/virtio_net.c | 312 ++++++++++++++++++++++++++++++++-------
 1 file changed, 255 insertions(+), 57 deletions(-)

-- 
2.19.1.6.gb485710b

[PATCH net-next v4 1/4] virtio-net: returns whether napi is complete

[Heng Qi]

rx netdim needs to count the traffic during a complete napi process,
and start updating and comparing samples to make decisions after
the napi ends. Let virtqueue_napi_complete() return true if napi is done,
otherwise vice versa.

Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/net/virtio_net.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d16f592c2061..0ad2894e6a5e 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -431,7 +431,7 @@ static void virtqueue_napi_schedule(struct napi_struct *napi,
 	}
 }
 
-static void virtqueue_napi_complete(struct napi_struct *napi,
+static bool virtqueue_napi_complete(struct napi_struct *napi,
 				    struct virtqueue *vq, int processed)
 {
 	int opaque;
@@ -440,9 +440,13 @@ static void virtqueue_napi_complete(struct napi_struct *napi,
 	if (napi_complete_done(napi, processed)) {
 		if (unlikely(virtqueue_poll(vq, opaque)))
 			virtqueue_napi_schedule(napi, vq);
+		else
+			return true;
 	} else {
 		virtqueue_disable_cb(vq);
 	}
+
+	return false;
 }
 
 static void skb_xmit_done(struct virtqueue *vq)
-- 
2.19.1.6.gb485710b

[PATCH net-next v4 2/4] virtio-net: separate rx/tx coalescing moderation cmds

[Heng Qi]

This patch separates the rx and tx global coalescing moderation
commands to support netdim switches in subsequent patches.

Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/net/virtio_net.c | 31 ++++++++++++++++++++++++++++---
 1 file changed, 28 insertions(+), 3 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 0ad2894e6a5e..0285301caf78 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3266,10 +3266,10 @@ static int virtnet_get_link_ksettings(struct net_device *dev,
 	return 0;
 }
 
-static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
-				       struct ethtool_coalesce *ec)
+static int virtnet_send_tx_notf_coal_cmds(struct virtnet_info *vi,
+					  struct ethtool_coalesce *ec)
 {
-	struct scatterlist sgs_tx, sgs_rx;
+	struct scatterlist sgs_tx;
 	int i;
 
 	vi->ctrl->coal_tx.tx_usecs = cpu_to_le32(ec->tx_coalesce_usecs);
@@ -3289,6 +3289,15 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
 		vi->sq[i].intr_coal.max_packets = ec->tx_max_coalesced_frames;
 	}
 
+	return 0;
+}
+
+static int virtnet_send_rx_notf_coal_cmds(struct virtnet_info *vi,
+					  struct ethtool_coalesce *ec)
+{
+	struct scatterlist sgs_rx;
+	int i;
+
 	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);
 	sg_init_one(&sgs_rx, &vi->ctrl->coal_rx, sizeof(vi->ctrl->coal_rx));
@@ -3309,6 +3318,22 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
 	return 0;
 }
 
+static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
+				       struct ethtool_coalesce *ec)
+{
+	int err;
+
+	err = virtnet_send_tx_notf_coal_cmds(vi, ec);
+	if (err)
+		return err;
+
+	err = virtnet_send_rx_notf_coal_cmds(vi, ec);
+	if (err)
+		return err;
+
+	return 0;
+}
+
 static int virtnet_send_ctrl_coal_vq_cmd(struct virtnet_info *vi,
 					 u16 vqn, u32 max_usecs, u32 max_packets)
 {
-- 
2.19.1.6.gb485710b

[PATCH net-next v4 3/4] virtio-net: extract virtqueue coalescig cmd for reuse

[Heng Qi]

Extract commands to set virtqueue coalescing parameters for reuse
by ethtool -Q, vq resize and netdim.

Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/net/virtio_net.c | 106 +++++++++++++++++++++++----------------
 1 file changed, 64 insertions(+), 42 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 0285301caf78..69fe09e99b3c 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2849,6 +2849,58 @@ static void virtnet_cpu_notif_remove(struct virtnet_info *vi)
 					    &vi->node_dead);
 }
 
+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_rx_ctrl_coal_vq_cmd(struct virtnet_info *vi,
+					    u16 queue, u32 max_usecs,
+					    u32 max_packets)
+{
+	int err;
+
+	err = virtnet_send_ctrl_coal_vq_cmd(vi, rxq2vq(queue),
+					    max_usecs, max_packets);
+	if (err)
+		return err;
+
+	vi->rq[queue].intr_coal.max_usecs = max_usecs;
+	vi->rq[queue].intr_coal.max_packets = max_packets;
+
+	return 0;
+}
+
+static int virtnet_send_tx_ctrl_coal_vq_cmd(struct virtnet_info *vi,
+					    u16 queue, u32 max_usecs,
+					    u32 max_packets)
+{
+	int err;
+
+	err = virtnet_send_ctrl_coal_vq_cmd(vi, txq2vq(queue),
+					    max_usecs, max_packets);
+	if (err)
+		return err;
+
+	vi->sq[queue].intr_coal.max_usecs = max_usecs;
+	vi->sq[queue].intr_coal.max_packets = max_packets;
+
+	return 0;
+}
+
 static void virtnet_get_ringparam(struct net_device *dev,
 				  struct ethtool_ringparam *ring,
 				  struct kernel_ethtool_ringparam *kernel_ring,
@@ -2906,14 +2958,11 @@ static int virtnet_set_ringparam(struct net_device *dev,
 			 * through the VIRTIO_NET_CTRL_NOTF_COAL_TX_SET command, or, if the driver
 			 * did not set any TX coalescing parameters, to 0.
 			 */
-			err = virtnet_send_ctrl_coal_vq_cmd(vi, txq2vq(i),
-							    vi->intr_coal_tx.max_usecs,
-							    vi->intr_coal_tx.max_packets);
+			err = virtnet_send_tx_ctrl_coal_vq_cmd(vi, i,
+							       vi->intr_coal_tx.max_usecs,
+							       vi->intr_coal_tx.max_packets);
 			if (err)
 				return err;
-
-			vi->sq[i].intr_coal.max_usecs = vi->intr_coal_tx.max_usecs;
-			vi->sq[i].intr_coal.max_packets = vi->intr_coal_tx.max_packets;
 		}
 
 		if (ring->rx_pending != rx_pending) {
@@ -2922,14 +2971,11 @@ static int virtnet_set_ringparam(struct net_device *dev,
 				return err;
 
 			/* The reason is same as the transmit virtqueue reset */
-			err = virtnet_send_ctrl_coal_vq_cmd(vi, rxq2vq(i),
-							    vi->intr_coal_rx.max_usecs,
-							    vi->intr_coal_rx.max_packets);
+			err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, i,
+							       vi->intr_coal_rx.max_usecs,
+							       vi->intr_coal_rx.max_packets);
 			if (err)
 				return err;
-
-			vi->rq[i].intr_coal.max_usecs = vi->intr_coal_rx.max_usecs;
-			vi->rq[i].intr_coal.max_packets = vi->intr_coal_rx.max_packets;
 		}
 	}
 
@@ -3334,48 +3380,24 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
 	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;
 
-	err = virtnet_send_ctrl_coal_vq_cmd(vi, rxq2vq(queue),
-					    ec->rx_coalesce_usecs,
-					    ec->rx_max_coalesced_frames);
+	err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, queue,
+					       ec->rx_coalesce_usecs,
+					       ec->rx_max_coalesced_frames);
 	if (err)
 		return err;
 
-	vi->rq[queue].intr_coal.max_usecs = ec->rx_coalesce_usecs;
-	vi->rq[queue].intr_coal.max_packets = ec->rx_max_coalesced_frames;
-
-	err = virtnet_send_ctrl_coal_vq_cmd(vi, txq2vq(queue),
-					    ec->tx_coalesce_usecs,
-					    ec->tx_max_coalesced_frames);
+	err = virtnet_send_tx_ctrl_coal_vq_cmd(vi, queue,
+					       ec->tx_coalesce_usecs,
+					       ec->tx_max_coalesced_frames);
 	if (err)
 		return err;
 
-	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;
 }
 
-- 
2.19.1.6.gb485710b

[PATCH net-next v4 4/4] virtio-net: support rx netdim

[Heng Qi]

By comparing the traffic information in the complete napi processes,
let the virtio-net driver automatically adjust the coalescing
moderation parameters of each receive queue.

Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
---
v2->v3:
- Some minor modifications.

v1->v2:
- Improved the judgment of dim switch conditions.
- Cancel the work when vq reset.

 drivers/net/virtio_net.c | 191 ++++++++++++++++++++++++++++++++++-----
 1 file changed, 169 insertions(+), 22 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 69fe09e99b3c..bc32d5aae005 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -19,6 +19,7 @@
 #include <linux/average.h>
 #include <linux/filter.h>
 #include <linux/kernel.h>
+#include <linux/dim.h>
 #include <net/route.h>
 #include <net/xdp.h>
 #include <net/net_failover.h>
@@ -172,6 +173,17 @@ struct receive_queue {
 
 	struct virtnet_rq_stats stats;
 
+	/* The number of rx notifications */
+	u16 calls;
+
+	/* Is dynamic interrupt moderation enabled? */
+	bool dim_enabled;
+
+	/* Dynamic Interrupt Moderation */
+	struct dim dim;
+
+	u32 packets_in_napi;
+
 	struct virtnet_interrupt_coalesce intr_coal;
 
 	/* Chain pages by the private ptr. */
@@ -305,6 +317,9 @@ struct virtnet_info {
 	u8 duplex;
 	u32 speed;
 
+	/* Is rx dynamic interrupt moderation enabled? */
+	bool rx_dim_enabled;
+
 	/* Interrupt coalescing settings */
 	struct virtnet_interrupt_coalesce intr_coal_tx;
 	struct virtnet_interrupt_coalesce intr_coal_rx;
@@ -2001,6 +2016,7 @@ static void skb_recv_done(struct virtqueue *rvq)
 	struct virtnet_info *vi = rvq->vdev->priv;
 	struct receive_queue *rq = &vi->rq[vq2rxq(rvq)];
 
+	rq->calls++;
 	virtqueue_napi_schedule(&rq->napi, rvq);
 }
 
@@ -2141,6 +2157,26 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
 	}
 }
 
+static void virtnet_rx_dim_work(struct work_struct *work);
+
+static void virtnet_rx_dim_update(struct virtnet_info *vi, struct receive_queue *rq)
+{
+	struct dim_sample cur_sample = {};
+
+	if (!rq->packets_in_napi)
+		return;
+
+	u64_stats_update_begin(&rq->stats.syncp);
+	dim_update_sample(rq->calls,
+			  u64_stats_read(&rq->stats.packets),
+			  u64_stats_read(&rq->stats.bytes),
+			  &cur_sample);
+	u64_stats_update_end(&rq->stats.syncp);
+
+	net_dim(&rq->dim, cur_sample);
+	rq->packets_in_napi = 0;
+}
+
 static int virtnet_poll(struct napi_struct *napi, int budget)
 {
 	struct receive_queue *rq =
@@ -2149,17 +2185,22 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 	struct send_queue *sq;
 	unsigned int received;
 	unsigned int xdp_xmit = 0;
+	bool napi_complete;
 
 	virtnet_poll_cleantx(rq);
 
 	received = virtnet_receive(rq, budget, &xdp_xmit);
+	rq->packets_in_napi += received;
 
 	if (xdp_xmit & VIRTIO_XDP_REDIR)
 		xdp_do_flush();
 
 	/* Out of packets? */
-	if (received < budget)
-		virtqueue_napi_complete(napi, rq->vq, received);
+	if (received < budget) {
+		napi_complete = virtqueue_napi_complete(napi, rq->vq, received);
+		if (napi_complete && rq->dim_enabled)
+			virtnet_rx_dim_update(vi, rq);
+	}
 
 	if (xdp_xmit & VIRTIO_XDP_TX) {
 		sq = virtnet_xdp_get_sq(vi);
@@ -2179,6 +2220,7 @@ static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index)
 	virtnet_napi_tx_disable(&vi->sq[qp_index].napi);
 	napi_disable(&vi->rq[qp_index].napi);
 	xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
+	cancel_work_sync(&vi->rq[qp_index].dim.work);
 }
 
 static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
@@ -2196,6 +2238,9 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
 	if (err < 0)
 		goto err_xdp_reg_mem_model;
 
+	INIT_WORK(&vi->rq[qp_index].dim.work, virtnet_rx_dim_work);
+	vi->rq[qp_index].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+
 	virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi);
 	virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi);
 
@@ -2393,8 +2438,10 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
 
 	qindex = rq - vi->rq;
 
-	if (running)
+	if (running) {
 		napi_disable(&rq->napi);
+		cancel_work_sync(&rq->dim.work);
+	}
 
 	err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_free_unused_buf);
 	if (err)
@@ -2403,8 +2450,10 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
 	if (!try_fill_recv(vi, rq, GFP_KERNEL))
 		schedule_delayed_work(&vi->refill, 0);
 
-	if (running)
+	if (running) {
+		INIT_WORK(&rq->dim.work, virtnet_rx_dim_work);
 		virtnet_napi_enable(rq->vq, &rq->napi);
+	}
 	return err;
 }
 
@@ -3341,24 +3390,55 @@ static int virtnet_send_tx_notf_coal_cmds(struct virtnet_info *vi,
 static int virtnet_send_rx_notf_coal_cmds(struct virtnet_info *vi,
 					  struct ethtool_coalesce *ec)
 {
+	bool rx_ctrl_dim_on = !!ec->use_adaptive_rx_coalesce;
+	bool update = false, switch_dim;
 	struct scatterlist sgs_rx;
 	int i;
 
-	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);
-	sg_init_one(&sgs_rx, &vi->ctrl->coal_rx, sizeof(vi->ctrl->coal_rx));
-
-	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
-				  VIRTIO_NET_CTRL_NOTF_COAL_RX_SET,
-				  &sgs_rx))
-		return -EINVAL;
+	switch_dim = rx_ctrl_dim_on != vi->rx_dim_enabled;
+	if (switch_dim) {
+		if (rx_ctrl_dim_on) {
+			if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) {
+				vi->rx_dim_enabled = true;
+				for (i = 0; i < vi->max_queue_pairs; i++)
+					vi->rq[i].dim_enabled = true;
+			} else {
+				return -EOPNOTSUPP;
+			}
+		} else {
+			vi->rx_dim_enabled = false;
+			for (i = 0; i < vi->max_queue_pairs; i++)
+				vi->rq[i].dim_enabled = false;
+		}
+	} else {
+		if (ec->rx_coalesce_usecs != vi->intr_coal_rx.max_usecs ||
+		    ec->rx_max_coalesced_frames != vi->intr_coal_rx.max_packets)
+			update = true;
 
-	/* Save parameters */
-	vi->intr_coal_rx.max_usecs = ec->rx_coalesce_usecs;
-	vi->intr_coal_rx.max_packets = ec->rx_max_coalesced_frames;
-	for (i = 0; i < vi->max_queue_pairs; i++) {
-		vi->rq[i].intr_coal.max_usecs = ec->rx_coalesce_usecs;
-		vi->rq[i].intr_coal.max_packets = ec->rx_max_coalesced_frames;
+		if (vi->rx_dim_enabled) {
+			if (update)
+				return -EINVAL;
+		} else {
+			/* Since the per-queue coalescing params can be set,
+			 * we need apply the global new params even if they
+			 * are not updated.
+			 */
+			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);
+			sg_init_one(&sgs_rx, &vi->ctrl->coal_rx, sizeof(vi->ctrl->coal_rx));
+
+			if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
+						  VIRTIO_NET_CTRL_NOTF_COAL_RX_SET,
+						  &sgs_rx))
+				return -EINVAL;
+
+			vi->intr_coal_rx.max_usecs = ec->rx_coalesce_usecs;
+			vi->intr_coal_rx.max_packets = ec->rx_max_coalesced_frames;
+			for (i = 0; i < vi->max_queue_pairs; i++) {
+				vi->rq[i].intr_coal.max_usecs = ec->rx_coalesce_usecs;
+				vi->rq[i].intr_coal.max_packets = ec->rx_max_coalesced_frames;
+			}
+		}
 	}
 
 	return 0;
@@ -3380,15 +3460,54 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi,
 	return 0;
 }
 
+static int virtnet_send_rx_notf_coal_vq_cmds(struct virtnet_info *vi,
+					     struct ethtool_coalesce *ec,
+					     u16 queue)
+{
+	bool rx_ctrl_dim_on = !!ec->use_adaptive_rx_coalesce;
+	bool cur_rx_dim = vi->rq[queue].dim_enabled;
+	bool update = false, switch_dim;
+	u32 max_usecs, max_packets;
+	int err;
+
+	switch_dim = rx_ctrl_dim_on != cur_rx_dim;
+	if (switch_dim) {
+		if (rx_ctrl_dim_on)
+			vi->rq[queue].dim_enabled = true;
+		else
+			vi->rq[queue].dim_enabled = false;
+	} else {
+		max_usecs = vi->rq[queue].intr_coal.max_usecs;
+		max_packets = vi->rq[queue].intr_coal.max_packets;
+		if (ec->rx_coalesce_usecs != max_usecs ||
+		    ec->rx_max_coalesced_frames != max_packets)
+			update = true;
+
+		if (cur_rx_dim) {
+			if (update)
+				return -EINVAL;
+		} else {
+			if (!update)
+				return 0;
+
+			err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, queue,
+							       ec->rx_coalesce_usecs,
+							       ec->rx_max_coalesced_frames);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
 static int virtnet_send_notf_coal_vq_cmds(struct virtnet_info *vi,
 					  struct ethtool_coalesce *ec,
 					  u16 queue)
 {
 	int err;
 
-	err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, queue,
-					       ec->rx_coalesce_usecs,
-					       ec->rx_max_coalesced_frames);
+	err = virtnet_send_rx_notf_coal_vq_cmds(vi, ec, queue);
 	if (err)
 		return err;
 
@@ -3401,6 +3520,32 @@ static int virtnet_send_notf_coal_vq_cmds(struct virtnet_info *vi,
 	return 0;
 }
 
+static void virtnet_rx_dim_work(struct work_struct *work)
+{
+	struct dim *dim = container_of(work, struct dim, work);
+	struct receive_queue *rq = container_of(dim,
+			struct receive_queue, dim);
+	struct virtnet_info *vi = rq->vq->vdev->priv;
+	struct net_device *dev = vi->dev;
+	struct dim_cq_moder update_moder;
+	int qnum = rq - vi->rq, err;
+
+	update_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
+	if (update_moder.usec != vi->rq[qnum].intr_coal.max_usecs ||
+	    update_moder.pkts != vi->rq[qnum].intr_coal.max_packets) {
+		rtnl_lock();
+		err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, qnum,
+						       update_moder.usec,
+						       update_moder.pkts);
+		if (err)
+			pr_debug("%s: Failed to send dim parameters on rxq%d\n",
+				 dev->name, (int)(rq - vi->rq));
+		rtnl_unlock();
+	}
+
+	dim->state = DIM_START_MEASURE;
+}
+
 static int virtnet_coal_params_supported(struct ethtool_coalesce *ec)
 {
 	/* usecs coalescing is supported only if VIRTIO_NET_F_NOTF_COAL
@@ -3482,6 +3627,7 @@ static int virtnet_get_coalesce(struct net_device *dev,
 		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;
+		ec->use_adaptive_rx_coalesce = vi->rx_dim_enabled;
 	} else {
 		ec->rx_max_coalesced_frames = 1;
 
@@ -3539,6 +3685,7 @@ static int virtnet_get_per_queue_coalesce(struct net_device *dev,
 		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;
+		ec->use_adaptive_rx_coalesce = vi->rq[queue].dim_enabled;
 	} else {
 		ec->rx_max_coalesced_frames = 1;
 
@@ -3664,7 +3811,7 @@ static int virtnet_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info)
 
 static const struct ethtool_ops virtnet_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES |
-		ETHTOOL_COALESCE_USECS,
+		ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE_RX,
 	.get_drvinfo = virtnet_get_drvinfo,
 	.get_link = ethtool_op_get_link,
 	.get_ringparam = virtnet_get_ringparam,
-- 
2.19.1.6.gb485710b

Re: [PATCH net-next v4 4/4] virtio-net: support rx netdim

[Jason Wang]

On Mon, Nov 20, 2023 at 8:38 PM Heng Qi <hengqi@linux.alibaba.com> wrote:
>
> By comparing the traffic information in the complete napi processes,
> let the virtio-net driver automatically adjust the coalescing
> moderation parameters of each receive queue.
>
> Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
> ---
> v2->v3:
> - Some minor modifications.
>
> v1->v2:
> - Improved the judgment of dim switch conditions.
> - Cancel the work when vq reset.
>
>  drivers/net/virtio_net.c | 191 ++++++++++++++++++++++++++++++++++-----
>  1 file changed, 169 insertions(+), 22 deletions(-)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 69fe09e99b3c..bc32d5aae005 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -19,6 +19,7 @@
>  #include <linux/average.h>
>  #include <linux/filter.h>
>  #include <linux/kernel.h>
> +#include <linux/dim.h>
>  #include <net/route.h>
>  #include <net/xdp.h>
>  #include <net/net_failover.h>
> @@ -172,6 +173,17 @@ struct receive_queue {
>
>         struct virtnet_rq_stats stats;
>
> +       /* The number of rx notifications */
> +       u16 calls;
> +
> +       /* Is dynamic interrupt moderation enabled? */
> +       bool dim_enabled;
> +
> +       /* Dynamic Interrupt Moderation */
> +       struct dim dim;
> +
> +       u32 packets_in_napi;
> +
>         struct virtnet_interrupt_coalesce intr_coal;
>
>         /* Chain pages by the private ptr. */
> @@ -305,6 +317,9 @@ struct virtnet_info {
>         u8 duplex;
>         u32 speed;
>
> +       /* Is rx dynamic interrupt moderation enabled? */
> +       bool rx_dim_enabled;
> +
>         /* Interrupt coalescing settings */
>         struct virtnet_interrupt_coalesce intr_coal_tx;
>         struct virtnet_interrupt_coalesce intr_coal_rx;
> @@ -2001,6 +2016,7 @@ static void skb_recv_done(struct virtqueue *rvq)
>         struct virtnet_info *vi = rvq->vdev->priv;
>         struct receive_queue *rq = &vi->rq[vq2rxq(rvq)];
>
> +       rq->calls++;
>         virtqueue_napi_schedule(&rq->napi, rvq);
>  }
>
> @@ -2141,6 +2157,26 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
>         }
>  }
>
> +static void virtnet_rx_dim_work(struct work_struct *work);
> +
> +static void virtnet_rx_dim_update(struct virtnet_info *vi, struct receive_queue *rq)
> +{
> +       struct dim_sample cur_sample = {};
> +
> +       if (!rq->packets_in_napi)
> +               return;
> +
> +       u64_stats_update_begin(&rq->stats.syncp);
> +       dim_update_sample(rq->calls,
> +                         u64_stats_read(&rq->stats.packets),
> +                         u64_stats_read(&rq->stats.bytes),
> +                         &cur_sample);
> +       u64_stats_update_end(&rq->stats.syncp);
> +
> +       net_dim(&rq->dim, cur_sample);
> +       rq->packets_in_napi = 0;
> +}
> +
>  static int virtnet_poll(struct napi_struct *napi, int budget)
>  {
>         struct receive_queue *rq =
> @@ -2149,17 +2185,22 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
>         struct send_queue *sq;
>         unsigned int received;
>         unsigned int xdp_xmit = 0;
> +       bool napi_complete;
>
>         virtnet_poll_cleantx(rq);
>
>         received = virtnet_receive(rq, budget, &xdp_xmit);
> +       rq->packets_in_napi += received;
>
>         if (xdp_xmit & VIRTIO_XDP_REDIR)
>                 xdp_do_flush();
>
>         /* Out of packets? */
> -       if (received < budget)
> -               virtqueue_napi_complete(napi, rq->vq, received);
> +       if (received < budget) {
> +               napi_complete = virtqueue_napi_complete(napi, rq->vq, received);
> +               if (napi_complete && rq->dim_enabled)
> +                       virtnet_rx_dim_update(vi, rq);
> +       }
>
>         if (xdp_xmit & VIRTIO_XDP_TX) {
>                 sq = virtnet_xdp_get_sq(vi);
> @@ -2179,6 +2220,7 @@ static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index)
>         virtnet_napi_tx_disable(&vi->sq[qp_index].napi);
>         napi_disable(&vi->rq[qp_index].napi);
>         xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
> +       cancel_work_sync(&vi->rq[qp_index].dim.work);
>  }
>
>  static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
> @@ -2196,6 +2238,9 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
>         if (err < 0)
>                 goto err_xdp_reg_mem_model;
>
> +       INIT_WORK(&vi->rq[qp_index].dim.work, virtnet_rx_dim_work);
> +       vi->rq[qp_index].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;

So in V2, you explained it can be done here but I want to know why it
must be done here.

For example, the refill_work is initialized in alloc_queues().

> +
>         virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi);
>         virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi);
>
> @@ -2393,8 +2438,10 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
>
>         qindex = rq - vi->rq;
>
> -       if (running)
> +       if (running) {
>                 napi_disable(&rq->napi);
> +               cancel_work_sync(&rq->dim.work);
> +       }
>
>         err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_free_unused_buf);
>         if (err)
> @@ -2403,8 +2450,10 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
>         if (!try_fill_recv(vi, rq, GFP_KERNEL))
>                 schedule_delayed_work(&vi->refill, 0);
>
> -       if (running)
> +       if (running) {
> +               INIT_WORK(&rq->dim.work, virtnet_rx_dim_work);
>                 virtnet_napi_enable(rq->vq, &rq->napi);
> +       }
>         return err;
>  }
>
> @@ -3341,24 +3390,55 @@ static int virtnet_send_tx_notf_coal_cmds(struct virtnet_info *vi,
>  static int virtnet_send_rx_notf_coal_cmds(struct virtnet_info *vi,
>                                           struct ethtool_coalesce *ec)
>  {
> +       bool rx_ctrl_dim_on = !!ec->use_adaptive_rx_coalesce;
> +       bool update = false, switch_dim;
>         struct scatterlist sgs_rx;
>         int i;
>
> -       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);
> -       sg_init_one(&sgs_rx, &vi->ctrl->coal_rx, sizeof(vi->ctrl->coal_rx));
> -
> -       if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
> -                                 VIRTIO_NET_CTRL_NOTF_COAL_RX_SET,
> -                                 &sgs_rx))
> -               return -EINVAL;
> +       switch_dim = rx_ctrl_dim_on != vi->rx_dim_enabled;
> +       if (switch_dim) {
> +               if (rx_ctrl_dim_on) {
> +                       if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) {

So basically, I'm asking why we need to duplicate the check here?

E.g caller has done the check for us:

        if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL))
                ret = virtnet_send_notf_coal_cmds(vi, ec);
        else
                ret = virtnet_coal_params_supported(ec);

?

Please also check other nested if/else, usually, too many levels of
nesting is a hint that the logic needs to be optimized.

Thanks

Re: [PATCH net-next v4 4/4] virtio-net: support rx netdim

[Jason Wang]

On Wed, Nov 22, 2023 at 1:52 PM Jason Wang <jasowang@redhat.com> wrote:
>
> On Mon, Nov 20, 2023 at 8:38 PM Heng Qi <hengqi@linux.alibaba.com> wrote:
> >
> > By comparing the traffic information in the complete napi processes,
> > let the virtio-net driver automatically adjust the coalescing
> > moderation parameters of each receive queue.
> >
> > Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
> > ---
> > v2->v3:
> > - Some minor modifications.
> >
> > v1->v2:
> > - Improved the judgment of dim switch conditions.
> > - Cancel the work when vq reset.
> >
> >  drivers/net/virtio_net.c | 191 ++++++++++++++++++++++++++++++++++-----
> >  1 file changed, 169 insertions(+), 22 deletions(-)
> >
> > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > index 69fe09e99b3c..bc32d5aae005 100644
> > --- a/drivers/net/virtio_net.c
> > +++ b/drivers/net/virtio_net.c
> > @@ -19,6 +19,7 @@
> >  #include <linux/average.h>
> >  #include <linux/filter.h>
> >  #include <linux/kernel.h>
> > +#include <linux/dim.h>
> >  #include <net/route.h>
> >  #include <net/xdp.h>
> >  #include <net/net_failover.h>
> > @@ -172,6 +173,17 @@ struct receive_queue {
> >
> >         struct virtnet_rq_stats stats;
> >
> > +       /* The number of rx notifications */
> > +       u16 calls;
> > +
> > +       /* Is dynamic interrupt moderation enabled? */
> > +       bool dim_enabled;
> > +
> > +       /* Dynamic Interrupt Moderation */
> > +       struct dim dim;
> > +
> > +       u32 packets_in_napi;
> > +
> >         struct virtnet_interrupt_coalesce intr_coal;
> >
> >         /* Chain pages by the private ptr. */
> > @@ -305,6 +317,9 @@ struct virtnet_info {
> >         u8 duplex;
> >         u32 speed;
> >
> > +       /* Is rx dynamic interrupt moderation enabled? */
> > +       bool rx_dim_enabled;
> > +
> >         /* Interrupt coalescing settings */
> >         struct virtnet_interrupt_coalesce intr_coal_tx;
> >         struct virtnet_interrupt_coalesce intr_coal_rx;
> > @@ -2001,6 +2016,7 @@ static void skb_recv_done(struct virtqueue *rvq)
> >         struct virtnet_info *vi = rvq->vdev->priv;
> >         struct receive_queue *rq = &vi->rq[vq2rxq(rvq)];
> >
> > +       rq->calls++;
> >         virtqueue_napi_schedule(&rq->napi, rvq);
> >  }
> >
> > @@ -2141,6 +2157,26 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
> >         }
> >  }
> >
> > +static void virtnet_rx_dim_work(struct work_struct *work);
> > +
> > +static void virtnet_rx_dim_update(struct virtnet_info *vi, struct receive_queue *rq)
> > +{
> > +       struct dim_sample cur_sample = {};
> > +
> > +       if (!rq->packets_in_napi)
> > +               return;
> > +
> > +       u64_stats_update_begin(&rq->stats.syncp);
> > +       dim_update_sample(rq->calls,
> > +                         u64_stats_read(&rq->stats.packets),
> > +                         u64_stats_read(&rq->stats.bytes),
> > +                         &cur_sample);
> > +       u64_stats_update_end(&rq->stats.syncp);
> > +
> > +       net_dim(&rq->dim, cur_sample);
> > +       rq->packets_in_napi = 0;
> > +}
> > +
> >  static int virtnet_poll(struct napi_struct *napi, int budget)
> >  {
> >         struct receive_queue *rq =
> > @@ -2149,17 +2185,22 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
> >         struct send_queue *sq;
> >         unsigned int received;
> >         unsigned int xdp_xmit = 0;
> > +       bool napi_complete;
> >
> >         virtnet_poll_cleantx(rq);
> >
> >         received = virtnet_receive(rq, budget, &xdp_xmit);
> > +       rq->packets_in_napi += received;
> >
> >         if (xdp_xmit & VIRTIO_XDP_REDIR)
> >                 xdp_do_flush();
> >
> >         /* Out of packets? */
> > -       if (received < budget)
> > -               virtqueue_napi_complete(napi, rq->vq, received);
> > +       if (received < budget) {
> > +               napi_complete = virtqueue_napi_complete(napi, rq->vq, received);
> > +               if (napi_complete && rq->dim_enabled)
> > +                       virtnet_rx_dim_update(vi, rq);
> > +       }
> >
> >         if (xdp_xmit & VIRTIO_XDP_TX) {
> >                 sq = virtnet_xdp_get_sq(vi);
> > @@ -2179,6 +2220,7 @@ static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index)
> >         virtnet_napi_tx_disable(&vi->sq[qp_index].napi);
> >         napi_disable(&vi->rq[qp_index].napi);
> >         xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
> > +       cancel_work_sync(&vi->rq[qp_index].dim.work);
> >  }
> >
> >  static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
> > @@ -2196,6 +2238,9 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
> >         if (err < 0)
> >                 goto err_xdp_reg_mem_model;
> >
> > +       INIT_WORK(&vi->rq[qp_index].dim.work, virtnet_rx_dim_work);
> > +       vi->rq[qp_index].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
>
> So in V2, you explained it can be done here but I want to know why it
> must be done here.
>
> For example, the refill_work is initialized in alloc_queues().
>
> > +
> >         virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi);
> >         virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi);
> >
> > @@ -2393,8 +2438,10 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
> >
> >         qindex = rq - vi->rq;
> >
> > -       if (running)
> > +       if (running) {
> >                 napi_disable(&rq->napi);
> > +               cancel_work_sync(&rq->dim.work);
> > +       }
> >
> >         err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_free_unused_buf);
> >         if (err)
> > @@ -2403,8 +2450,10 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
> >         if (!try_fill_recv(vi, rq, GFP_KERNEL))
> >                 schedule_delayed_work(&vi->refill, 0);
> >
> > -       if (running)
> > +       if (running) {
> > +               INIT_WORK(&rq->dim.work, virtnet_rx_dim_work);
> >                 virtnet_napi_enable(rq->vq, &rq->napi);
> > +       }
> >         return err;
> >  }
> >
> > @@ -3341,24 +3390,55 @@ static int virtnet_send_tx_notf_coal_cmds(struct virtnet_info *vi,
> >  static int virtnet_send_rx_notf_coal_cmds(struct virtnet_info *vi,
> >                                           struct ethtool_coalesce *ec)
> >  {
> > +       bool rx_ctrl_dim_on = !!ec->use_adaptive_rx_coalesce;
> > +       bool update = false, switch_dim;
> >         struct scatterlist sgs_rx;
> >         int i;
> >
> > -       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);
> > -       sg_init_one(&sgs_rx, &vi->ctrl->coal_rx, sizeof(vi->ctrl->coal_rx));
> > -
> > -       if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
> > -                                 VIRTIO_NET_CTRL_NOTF_COAL_RX_SET,
> > -                                 &sgs_rx))
> > -               return -EINVAL;
> > +       switch_dim = rx_ctrl_dim_on != vi->rx_dim_enabled;
> > +       if (switch_dim) {
> > +               if (rx_ctrl_dim_on) {
> > +                       if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) {
>
> So basically, I'm asking why we need to duplicate the check here?
>
> E.g caller has done the check for us:
>
>         if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL))
>                 ret = virtnet_send_notf_coal_cmds(vi, ec);
>         else
>                 ret = virtnet_coal_params_supported(ec);

Speak too fast, they have different features :(

But the point still, the logic needs some optimizations to reduce the
levels of nesting if/else.

Thanks

>
> ?
>
> Please also check other nested if/else, usually, too many levels of
> nesting is a hint that the logic needs to be optimized.
>
> Thanks

Re: [PATCH net-next v4 4/4] virtio-net: support rx netdim

[Yinjun Zhang]

On Mon, 20 Nov 2023 20:37:34 +0800, Heng Qi wrote:
<...>
> @@ -2179,6 +2220,7 @@ static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index)
>  	virtnet_napi_tx_disable(&vi->sq[qp_index].napi);
>  	napi_disable(&vi->rq[qp_index].napi);
>  	xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
> +	cancel_work_sync(&vi->rq[qp_index].dim.work);

I'm not sure, but please check if here may cause deadlock:
 rtnl_lock held ->
 .ndo_stop ->
 virtnet_disable_queue_pair() ->
 cancel_work_sync() ->
 virtnet_rx_dim_work() ->
 rtnl_lock()

>  }
>  
>  static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)

<...>

Re: [PATCH net-next v4 4/4] virtio-net: support rx netdim

[Heng Qi]

在 2023/11/22 下午1:52, Jason Wang 写道:
> On Mon, Nov 20, 2023 at 8:38 PM Heng Qi <hengqi@linux.alibaba.com> wrote:
>> By comparing the traffic information in the complete napi processes,
>> let the virtio-net driver automatically adjust the coalescing
>> moderation parameters of each receive queue.
>>
>> Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
>> ---
>> v2->v3:
>> - Some minor modifications.
>>
>> v1->v2:
>> - Improved the judgment of dim switch conditions.
>> - Cancel the work when vq reset.
>>
>>   drivers/net/virtio_net.c | 191 ++++++++++++++++++++++++++++++++++-----
>>   1 file changed, 169 insertions(+), 22 deletions(-)
>>
>> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
>> index 69fe09e99b3c..bc32d5aae005 100644
>> --- a/drivers/net/virtio_net.c
>> +++ b/drivers/net/virtio_net.c
>> @@ -19,6 +19,7 @@
>>   #include <linux/average.h>
>>   #include <linux/filter.h>
>>   #include <linux/kernel.h>
>> +#include <linux/dim.h>
>>   #include <net/route.h>
>>   #include <net/xdp.h>
>>   #include <net/net_failover.h>
>> @@ -172,6 +173,17 @@ struct receive_queue {
>>
>>          struct virtnet_rq_stats stats;
>>
>> +       /* The number of rx notifications */
>> +       u16 calls;
>> +
>> +       /* Is dynamic interrupt moderation enabled? */
>> +       bool dim_enabled;
>> +
>> +       /* Dynamic Interrupt Moderation */
>> +       struct dim dim;
>> +
>> +       u32 packets_in_napi;
>> +
>>          struct virtnet_interrupt_coalesce intr_coal;
>>
>>          /* Chain pages by the private ptr. */
>> @@ -305,6 +317,9 @@ struct virtnet_info {
>>          u8 duplex;
>>          u32 speed;
>>
>> +       /* Is rx dynamic interrupt moderation enabled? */
>> +       bool rx_dim_enabled;
>> +
>>          /* Interrupt coalescing settings */
>>          struct virtnet_interrupt_coalesce intr_coal_tx;
>>          struct virtnet_interrupt_coalesce intr_coal_rx;
>> @@ -2001,6 +2016,7 @@ static void skb_recv_done(struct virtqueue *rvq)
>>          struct virtnet_info *vi = rvq->vdev->priv;
>>          struct receive_queue *rq = &vi->rq[vq2rxq(rvq)];
>>
>> +       rq->calls++;
>>          virtqueue_napi_schedule(&rq->napi, rvq);
>>   }
>>
>> @@ -2141,6 +2157,26 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
>>          }
>>   }
>>
>> +static void virtnet_rx_dim_work(struct work_struct *work);
>> +
>> +static void virtnet_rx_dim_update(struct virtnet_info *vi, struct receive_queue *rq)
>> +{
>> +       struct dim_sample cur_sample = {};
>> +
>> +       if (!rq->packets_in_napi)
>> +               return;
>> +
>> +       u64_stats_update_begin(&rq->stats.syncp);
>> +       dim_update_sample(rq->calls,
>> +                         u64_stats_read(&rq->stats.packets),
>> +                         u64_stats_read(&rq->stats.bytes),
>> +                         &cur_sample);
>> +       u64_stats_update_end(&rq->stats.syncp);
>> +
>> +       net_dim(&rq->dim, cur_sample);
>> +       rq->packets_in_napi = 0;
>> +}
>> +
>>   static int virtnet_poll(struct napi_struct *napi, int budget)
>>   {
>>          struct receive_queue *rq =
>> @@ -2149,17 +2185,22 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
>>          struct send_queue *sq;
>>          unsigned int received;
>>          unsigned int xdp_xmit = 0;
>> +       bool napi_complete;
>>
>>          virtnet_poll_cleantx(rq);
>>
>>          received = virtnet_receive(rq, budget, &xdp_xmit);
>> +       rq->packets_in_napi += received;
>>
>>          if (xdp_xmit & VIRTIO_XDP_REDIR)
>>                  xdp_do_flush();
>>
>>          /* Out of packets? */
>> -       if (received < budget)
>> -               virtqueue_napi_complete(napi, rq->vq, received);
>> +       if (received < budget) {
>> +               napi_complete = virtqueue_napi_complete(napi, rq->vq, received);
>> +               if (napi_complete && rq->dim_enabled)
>> +                       virtnet_rx_dim_update(vi, rq);
>> +       }
>>
>>          if (xdp_xmit & VIRTIO_XDP_TX) {
>>                  sq = virtnet_xdp_get_sq(vi);
>> @@ -2179,6 +2220,7 @@ static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index)
>>          virtnet_napi_tx_disable(&vi->sq[qp_index].napi);
>>          napi_disable(&vi->rq[qp_index].napi);
>>          xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
>> +       cancel_work_sync(&vi->rq[qp_index].dim.work);
>>   }
>>
>>   static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
>> @@ -2196,6 +2238,9 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
>>          if (err < 0)
>>                  goto err_xdp_reg_mem_model;
>>
>> +       INIT_WORK(&vi->rq[qp_index].dim.work, virtnet_rx_dim_work);
>> +       vi->rq[qp_index].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
> So in V2, you explained it can be done here but I want to know why it
> must be done here.

It is not must be done here. We can place it in probe and make sure that 
INIT_WORK() is
done before napi is enabled for the first time.

So then I'll don't call INIT_WORK() every time after "napi_disable -> 
napi_enable" happens,
and use the following process:
Call INIT_WORK() in the driver probe and do cancel_work() after each 
related napi_disable.

This will be clearer.

Additionally, Yinjun Zhang found that cancel_work_sync() will cause a 
deadlock
when ndo_stop and virtnet_rx_dim_work occurs at the same time, so 
cancel_work() will be used.

>
> For example, the refill_work is initialized in alloc_queues().
>
>> +
>>          virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi);
>>          virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi);
>>
>> @@ -2393,8 +2438,10 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
>>
>>          qindex = rq - vi->rq;
>>
>> -       if (running)
>> +       if (running) {
>>                  napi_disable(&rq->napi);
>> +               cancel_work_sync(&rq->dim.work);
>> +       }
>>
>>          err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_free_unused_buf);
>>          if (err)
>> @@ -2403,8 +2450,10 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
>>          if (!try_fill_recv(vi, rq, GFP_KERNEL))
>>                  schedule_delayed_work(&vi->refill, 0);
>>
>> -       if (running)
>> +       if (running) {
>> +               INIT_WORK(&rq->dim.work, virtnet_rx_dim_work);
>>                  virtnet_napi_enable(rq->vq, &rq->napi);
>> +       }
>>          return err;
>>   }
>>
>> @@ -3341,24 +3390,55 @@ static int virtnet_send_tx_notf_coal_cmds(struct virtnet_info *vi,
>>   static int virtnet_send_rx_notf_coal_cmds(struct virtnet_info *vi,
>>                                            struct ethtool_coalesce *ec)
>>   {
>> +       bool rx_ctrl_dim_on = !!ec->use_adaptive_rx_coalesce;
>> +       bool update = false, switch_dim;
>>          struct scatterlist sgs_rx;
>>          int i;
>>
>> -       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);
>> -       sg_init_one(&sgs_rx, &vi->ctrl->coal_rx, sizeof(vi->ctrl->coal_rx));
>> -
>> -       if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL,
>> -                                 VIRTIO_NET_CTRL_NOTF_COAL_RX_SET,
>> -                                 &sgs_rx))
>> -               return -EINVAL;
>> +       switch_dim = rx_ctrl_dim_on != vi->rx_dim_enabled;
>> +       if (switch_dim) {
>> +               if (rx_ctrl_dim_on) {
>> +                       if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) {
> So basically, I'm asking why we need to duplicate the check here?

Here is VIRTIO_NET_F_*VQ*_NOTF_COAL.

>
> E.g caller has done the check for us:
>
>          if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL))
>                  ret = virtnet_send_notf_coal_cmds(vi, ec);
>          else
>                  ret = virtnet_coal_params_supported(ec);
>
> ?
>
> Please also check other nested if/else, usually, too many levels of
> nesting is a hint that the logic needs to be optimized.

I will optimize this.

Thanks!

>
> Thanks

Re: [PATCH net-next v4 4/4] virtio-net: support rx netdim

[Heng Qi]

在 2023/11/22 下午5:29, Yinjun Zhang 写道:
> On Mon, 20 Nov 2023 20:37:34 +0800, Heng Qi wrote:
> <...>
>> @@ -2179,6 +2220,7 @@ static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index)
>>   	virtnet_napi_tx_disable(&vi->sq[qp_index].napi);
>>   	napi_disable(&vi->rq[qp_index].napi);
>>   	xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
>> +	cancel_work_sync(&vi->rq[qp_index].dim.work);
> I'm not sure, but please check if here may cause deadlock:
>   rtnl_lock held ->
>   .ndo_stop ->
>   virtnet_disable_queue_pair() ->
>   cancel_work_sync() ->
>   virtnet_rx_dim_work() ->
>   rtnl_lock()

Good catch!

I tried using cancel_work() which solves the problem. Additionally I 
tested the
scenario of ctrl cmd/.remove/.ndo_stop()/dim_work when there is a lot of 
concurrency,
and this can work very well.

Thanks!

>
>>   }
>>   
>>   static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
> <...>