[PATCH v2 1/2] virtio-ring: Use threshold for switching to indirect descriptors

Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will use indirect
descriptors even if we have plenty of space in the ring. This means that
we take a performance hit at all times due to the overhead of creating
indirect descriptors.

Instead, use it only after we're below a configurable offset.

Signed-off-by: Sasha Levin <redacted>
---
 drivers/block/virtio_blk.c          |  4 ++++
 drivers/char/hw_random/virtio-rng.c |  4 ++++
 drivers/char/virtio_console.c       |  4 ++++
 drivers/net/virtio_net.c            |  4 ++++
 drivers/virtio/virtio_balloon.c     |  4 ++++
 drivers/virtio/virtio_ring.c        | 21 +++++++++++++++------
 include/linux/virtio.h              |  1 +
 net/9p/trans_virtio.c               |  4 ++++
 8 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 2edfb5c..13b8ae9 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c

@@ -22,6 +22,9 @@ static DEFINE_IDA(vd_index_ida);
 
 struct workqueue_struct *virtblk_wq;
 
+static unsigned int indirect_thresh;
+module_param(indirect_thresh, uint, S_IRUGO);
+
 struct virtio_blk
 {
 	struct virtio_device *vdev;

@@ -735,6 +738,7 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 
 	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
 	vblk->config_enable = true;
+	vdev->indirect_thresh = indirect_thresh;
 
 	err = init_vq(vblk);
 	if (err)

diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c
index 5708299..02d8421 100644
--- a/drivers/char/hw_random/virtio-rng.c
+++ b/drivers/char/hw_random/virtio-rng.c

@@ -25,6 +25,9 @@
 #include <linux/virtio_rng.h>
 #include <linux/module.h>
 
+static unsigned int indirect_thresh;
+module_param(indirect_thresh, uint, S_IRUGO);
+
 static struct virtqueue *vq;
 static unsigned int data_avail;
 static DECLARE_COMPLETION(have_data);

@@ -93,6 +96,7 @@ static int probe_common(struct virtio_device *vdev)
 	int err;
 
 	/* We expect a single virtqueue. */
+	vdev->indirect_thresh = indirect_thresh;
 	vq = virtio_find_single_vq(vdev, random_recv_done, "input");
 	if (IS_ERR(vq))
 		return PTR_ERR(vq);

diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index e88f843..fc14e7f 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c

@@ -39,6 +39,9 @@
 #include <linux/module.h>
 #include "../tty/hvc/hvc_console.h"
 
+static unsigned int indirect_thresh;
+module_param(indirect_thresh, uint, S_IRUGO);
+
 /*
  * This is a global struct for storing common data for all the devices
  * this driver handles.

@@ -1887,6 +1890,7 @@ static int __devinit virtcons_probe(struct virtio_device *vdev)
 				       max_nr_ports),
 			      &portdev->config.max_nr_ports) == 0)
 		multiport = true;
+	vdev->indirect_thresh = indirect_thresh;
 
 	err = init_vqs(portdev);
 	if (err < 0) {

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index cbf8b06..64a8321 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c

@@ -34,6 +34,9 @@ static bool csum = true, gso = true;
 module_param(csum, bool, 0444);
 module_param(gso, bool, 0444);
 
+static unsigned int indirect_thresh;
+module_param(indirect_thresh, uint, S_IRUGO);
+
 /* FIXME: MTU in config. */
 #define MAX_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN)
 #define GOOD_COPY_LEN	128

@@ -1128,6 +1131,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
 		vi->mergeable_rx_bufs = true;
+	vdev->indirect_thresh = indirect_thresh;
 
 	err = init_vqs(vi);
 	if (err)

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 0908e60..fce7347 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c

@@ -35,6 +35,9 @@
  */
 #define VIRTIO_BALLOON_PAGES_PER_PAGE (PAGE_SIZE >> VIRTIO_BALLOON_PFN_SHIFT)
 
+static unsigned int indirect_thresh;
+module_param(indirect_thresh, uint, S_IRUGO);
+
 struct virtio_balloon
 {
 	struct virtio_device *vdev;

@@ -356,6 +359,7 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	init_waitqueue_head(&vb->acked);
 	vb->vdev = vdev;
 	vb->need_stats_update = 0;
+	vdev->indirect_thresh = indirect_thresh;
 
 	err = init_vqs(vb);
 	if (err)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 5aa43c3..99a64a7 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c

@@ -87,8 +87,11 @@ struct vring_virtqueue
 	/* Other side has made a mess, don't try any more. */
 	bool broken;
 
-	/* Host supports indirect buffers */
-	bool indirect;
+	/*
+	 * Min. number of free space in the ring to trigger direct
+	 * descriptor use
+	 */
+	unsigned int indirect_thresh;
 
 	/* Host publishes avail event idx */
 	bool event;

@@ -216,9 +219,12 @@ int virtqueue_add_buf(struct virtqueue *_vq,
 	}
 #endif
 
-	/* If the host supports indirect descriptor tables, and we have multiple
-	 * buffers, then go indirect. FIXME: tune this threshold */
-	if (vq->indirect && (out + in) > 1 && vq->num_free) {
+	/*
+	 * If the host supports indirect descriptor tables, and we have multiple
+	 * buffers, then go indirect.
+	 */
+	if ((out + in) > 1 && vq->num_free &&
+		(vq->num_free < vq->indirect_thresh)) {
 		head = vring_add_indirect(vq, sg, out, in, gfp);
 		if (likely(head >= 0))
 			goto add_head;

@@ -647,13 +653,16 @@ struct virtqueue *vring_new_virtqueue(unsigned int num,
 	vq->broken = false;
 	vq->last_used_idx = 0;
 	vq->num_added = 0;
+	vq->indirect_thresh = 0;
 	list_add_tail(&vq->vq.list, &vdev->vqs);
 #ifdef DEBUG
 	vq->in_use = false;
 	vq->last_add_time_valid = false;
 #endif
 
-	vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC);
+	if (virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC))
+		vq->indirect_thresh = vdev->indirect_thresh;
+
 	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
 
 	/* No callback?  Tell other side not to bother us. */

diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index a1ba8bb..48bc457 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h

@@ -69,6 +69,7 @@ struct virtio_device {
 	/* Note that this is a Linux set_bit-style bitmap. */
 	unsigned long features[1];
 	void *priv;
+	unsigned int indirect_thresh;
 };
 
 #define dev_to_virtio(dev) container_of(dev, struct virtio_device, dev)

diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 35b8911..fc93962 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c

@@ -52,6 +52,9 @@
 
 #define VIRTQUEUE_NUM	128
 
+static unsigned int indirect_thresh;
+module_param(indirect_thresh, uint, S_IRUGO);
+
 /* a single mutex to manage channel initialization and attachment */
 static DEFINE_MUTEX(virtio_9p_lock);
 static DECLARE_WAIT_QUEUE_HEAD(vp_wq);

@@ -501,6 +504,7 @@ static int p9_virtio_probe(struct virtio_device *vdev)
 	chan->vdev = vdev;
 
 	/* We expect one virtqueue, for requests. */
+	vdev->indirect_thresh = indirect_thresh;
 	chan->vq = virtio_find_single_vq(vdev, req_done, "requests");
 	if (IS_ERR(chan->vq)) {
 		err = PTR_ERR(chan->vq);

-- 
1.7.12

Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will
use indirect descriptors and allocate them using a simple
kmalloc().

This patch adds a cache which will allow indirect buffers under
a configurable size to be allocated from that cache instead.

Signed-off-by: Sasha Levin <redacted>
---

Changes in v2:

 - Free correctly indirect buffers.

 drivers/block/virtio_blk.c          |  4 ++++
 drivers/char/hw_random/virtio-rng.c |  4 ++++
 drivers/char/virtio_console.c       |  4 ++++
 drivers/net/virtio_net.c            |  4 ++++
 drivers/virtio/virtio_balloon.c     |  4 ++++
 drivers/virtio/virtio_ring.c        | 28 ++++++++++++++++++++++++----
 include/linux/virtio.h              |  1 +
 net/9p/trans_virtio.c               |  5 +++++
 8 files changed, 50 insertions(+), 4 deletions(-)

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 13b8ae9..7f670af 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c

@@ -25,6 +25,9 @@ struct workqueue_struct *virtblk_wq;
 static unsigned int indirect_thresh;
 module_param(indirect_thresh, uint, S_IRUGO);
 
+static unsigned int indirect_alloc_thresh;
+module_param(indirect_alloc_thresh, uint, S_IRUGO);
+
 struct virtio_blk
 {
 	struct virtio_device *vdev;

@@ -739,6 +742,7 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
 	vblk->config_enable = true;
 	vdev->indirect_thresh = indirect_thresh;
+	vdev->indirect_alloc_thresh = indirect_alloc_thresh;
 
 	err = init_vq(vblk);
 	if (err)

diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c
index 02d8421..8475ece 100644
--- a/drivers/char/hw_random/virtio-rng.c
+++ b/drivers/char/hw_random/virtio-rng.c

@@ -28,6 +28,9 @@
 static unsigned int indirect_thresh;
 module_param(indirect_thresh, uint, S_IRUGO);
 
+static unsigned int indirect_alloc_thresh;
+module_param(indirect_alloc_thresh, uint, S_IRUGO);
+
 static struct virtqueue *vq;
 static unsigned int data_avail;
 static DECLARE_COMPLETION(have_data);

@@ -97,6 +100,7 @@ static int probe_common(struct virtio_device *vdev)
 
 	/* We expect a single virtqueue. */
 	vdev->indirect_thresh = indirect_thresh;
+	vdev->indirect_alloc_thresh = indirect_alloc_thresh;
 	vq = virtio_find_single_vq(vdev, random_recv_done, "input");
 	if (IS_ERR(vq))
 		return PTR_ERR(vq);

diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index fc14e7f..c6f24a7 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c

@@ -42,6 +42,9 @@
 static unsigned int indirect_thresh;
 module_param(indirect_thresh, uint, S_IRUGO);
 
+static unsigned int indirect_alloc_thresh;
+module_param(indirect_alloc_thresh, uint, S_IRUGO);
+
 /*
  * This is a global struct for storing common data for all the devices
  * this driver handles.

@@ -1891,6 +1894,7 @@ static int __devinit virtcons_probe(struct virtio_device *vdev)
 			      &portdev->config.max_nr_ports) == 0)
 		multiport = true;
 	vdev->indirect_thresh = indirect_thresh;
+	vdev->indirect_alloc_thresh = indirect_alloc_thresh;
 
 	err = init_vqs(portdev);
 	if (err < 0) {

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 64a8321..c091efd 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c

@@ -37,6 +37,9 @@ module_param(gso, bool, 0444);
 static unsigned int indirect_thresh;
 module_param(indirect_thresh, uint, S_IRUGO);
 
+static unsigned int indirect_alloc_thresh;
+module_param(indirect_alloc_thresh, uint, S_IRUGO);
+
 /* FIXME: MTU in config. */
 #define MAX_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN)
 #define GOOD_COPY_LEN	128

@@ -1132,6 +1135,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
 		vi->mergeable_rx_bufs = true;
 	vdev->indirect_thresh = indirect_thresh;
+	vdev->indirect_alloc_thresh = indirect_alloc_thresh;
 
 	err = init_vqs(vi);
 	if (err)

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index fce7347..ccf87db 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c

@@ -38,6 +38,9 @@
 static unsigned int indirect_thresh;
 module_param(indirect_thresh, uint, S_IRUGO);
 
+static unsigned int indirect_alloc_thresh;
+module_param(indirect_alloc_thresh, uint, S_IRUGO);
+
 struct virtio_balloon
 {
 	struct virtio_device *vdev;

@@ -360,6 +363,7 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	vb->vdev = vdev;
 	vb->need_stats_update = 0;
 	vdev->indirect_thresh = indirect_thresh;
+	vdev->indirect_alloc_thresh = indirect_alloc_thresh;
 
 	err = init_vqs(vb);
 	if (err)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 99a64a7..e8b9c54 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c

@@ -93,6 +93,10 @@ struct vring_virtqueue
 	 */
 	unsigned int indirect_thresh;
 
+	/* Buffers below this size will be allocated from cache */
+	unsigned int indirect_alloc_thresh;
+	struct kmem_cache *indirect_cache;
+
 	/* Host publishes avail event idx */
 	bool event;
 

@@ -135,7 +139,10 @@ static int vring_add_indirect(struct vring_virtqueue *vq,
 	unsigned head;
 	int i;
 
-	desc = kmalloc((out + in) * sizeof(struct vring_desc), gfp);
+	if ((out + in) <= vq->indirect_alloc_thresh)
+		desc = kmem_cache_alloc(vq->indirect_cache, gfp);
+	else
+		desc = kmalloc((out + in) * sizeof(struct vring_desc), gfp);
 	if (!desc)
 		return -ENOMEM;
 

@@ -384,8 +391,13 @@ static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
 	i = head;
 
 	/* Free the indirect table */
-	if (vq->vring.desc[i].flags & VRING_DESC_F_INDIRECT)
-		kfree(phys_to_virt(vq->vring.desc[i].addr));
+	if (vq->vring.desc[i].flags & VRING_DESC_F_INDIRECT) {
+		if (vq->vring.desc[i].len > vq->indirect_alloc_thresh)
+			kfree(phys_to_virt(vq->vring.desc[i].addr));
+		else
+			kmem_cache_free(vq->indirect_cache,
+					phys_to_virt(vq->vring.desc[i].addr));
+	}
 
 	while (vq->vring.desc[i].flags & VRING_DESC_F_NEXT) {
 		i = vq->vring.desc[i].next;

@@ -654,14 +666,20 @@ struct virtqueue *vring_new_virtqueue(unsigned int num,
 	vq->last_used_idx = 0;
 	vq->num_added = 0;
 	vq->indirect_thresh = 0;
+	vq->indirect_alloc_thresh = 0;
+	vq->indirect_cache = NULL;
 	list_add_tail(&vq->vq.list, &vdev->vqs);
 #ifdef DEBUG
 	vq->in_use = false;
 	vq->last_add_time_valid = false;
 #endif
 
-	if (virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC))
+	if (virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC)) {
 		vq->indirect_thresh = vdev->indirect_thresh;
+		vq->indirect_alloc_thresh = vdev->indirect_alloc_thresh;
+		if (vq->indirect_alloc_thresh)
+			vq->indirect_cache = KMEM_CACHE(vring_desc[vq->indirect_alloc_thresh], 0);
+	}
 
 	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
 

@@ -685,6 +703,8 @@ EXPORT_SYMBOL_GPL(vring_new_virtqueue);
 void vring_del_virtqueue(struct virtqueue *vq)
 {
 	list_del(&vq->list);
+	if (to_vvq(vq)->indirect_cache)
+		kmem_cache_destroy(to_vvq(vq)->indirect_cache);
 	kfree(to_vvq(vq));
 }
 EXPORT_SYMBOL_GPL(vring_del_virtqueue);

diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 48bc457..3261c02 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h

@@ -70,6 +70,7 @@ struct virtio_device {
 	unsigned long features[1];
 	void *priv;
 	unsigned int indirect_thresh;
+	unsigned int indirect_alloc_thresh;
 };
 
 #define dev_to_virtio(dev) container_of(dev, struct virtio_device, dev)

diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index fc93962..3044c86 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c

@@ -55,6 +55,9 @@
 static unsigned int indirect_thresh;
 module_param(indirect_thresh, uint, S_IRUGO);
 
+static unsigned int indirect_alloc_thresh;
+module_param(indirect_alloc_thresh, uint, S_IRUGO);
+
 /* a single mutex to manage channel initialization and attachment */
 static DEFINE_MUTEX(virtio_9p_lock);
 static DECLARE_WAIT_QUEUE_HEAD(vp_wq);

@@ -505,6 +508,8 @@ static int p9_virtio_probe(struct virtio_device *vdev)
 
 	/* We expect one virtqueue, for requests. */
 	vdev->indirect_thresh = indirect_thresh;
+	vdev->indirect_alloc_thresh = indirect_alloc_thresh;
+
 	chan->vq = virtio_find_single_vq(vdev, req_done, "requests");
 	if (IS_ERR(chan->vq)) {
 		err = PTR_ERR(chan->vq);

-- 
1.7.12

On Tue, Aug 28, 2012 at 03:04:02PM +0200, Sasha Levin wrote:

Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will use indirect
descriptors even if we have plenty of space in the ring. This means that
we take a performance hit at all times due to the overhead of creating
indirect descriptors.

Instead, use it only after we're below a configurable offset.

Signed-off-by: Sasha Levin <redacted>

I imagine this helps performance? Any numbers?

On Tue, Aug 28, 2012 at 03:04:03PM +0200, Sasha Levin wrote:

Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will
use indirect descriptors and allocate them using a simple
kmalloc().

This patch adds a cache which will allow indirect buffers under
a configurable size to be allocated from that cache instead.

Signed-off-by: Sasha Levin <redacted>

I imagine this helps performance? Any numbers?

On 08/28/2012 03:20 PM, Michael S. Tsirkin wrote:

On Tue, Aug 28, 2012 at 03:04:03PM +0200, Sasha Levin wrote:

quoted

Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will
use indirect descriptors and allocate them using a simple
kmalloc().

This patch adds a cache which will allow indirect buffers under
a configurable size to be allocated from that cache instead.

Signed-off-by: Sasha Levin <redacted>

I imagine this helps performance? Any numbers?

I ran benchmarks on the original RFC, I've re-tested it now and got similar
numbers to the original ones (virtio-net using vhost-net, thresh=16):

Before:
	Recv   Send    Send
	Socket Socket  Message  Elapsed
	Size   Size    Size     Time     Throughput
	bytes  bytes   bytes    secs.    10^6bits/sec

	 87380  16384  16384    10.00    4512.12

After:
	Recv   Send    Send
	Socket Socket  Message  Elapsed
	Size   Size    Size     Time     Throughput
	bytes  bytes   bytes    secs.    10^6bits/sec

	 87380  16384  16384    10.00    5399.18


Thanks,
Sasha

On Tue, Aug 28, 2012 at 03:35:00PM +0200, Sasha Levin wrote:

On 08/28/2012 03:20 PM, Michael S. Tsirkin wrote:

quoted

On Tue, Aug 28, 2012 at 03:04:03PM +0200, Sasha Levin wrote:

quoted

Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will
use indirect descriptors and allocate them using a simple
kmalloc().

This patch adds a cache which will allow indirect buffers under
a configurable size to be allocated from that cache instead.

Signed-off-by: Sasha Levin <redacted>

I imagine this helps performance? Any numbers?

I ran benchmarks on the original RFC, I've re-tested it now and got similar
numbers to the original ones (virtio-net using vhost-net, thresh=16):

Before:
	Recv   Send    Send
	Socket Socket  Message  Elapsed
	Size   Size    Size     Time     Throughput
	bytes  bytes   bytes    secs.    10^6bits/sec

	 87380  16384  16384    10.00    4512.12

After:
	Recv   Send    Send
	Socket Socket  Message  Elapsed
	Size   Size    Size     Time     Throughput
	bytes  bytes   bytes    secs.    10^6bits/sec

	 87380  16384  16384    10.00    5399.18


Thanks,
Sasha

This is with both patches 1 + 2?
Sorry could you please also test what happens if you apply
- just patch 1
- just patch 2

Thanks!

On 08/29/2012 01:07 PM, Michael S. Tsirkin wrote:

On Tue, Aug 28, 2012 at 03:35:00PM +0200, Sasha Levin wrote:

quoted

On 08/28/2012 03:20 PM, Michael S. Tsirkin wrote:

quoted

On Tue, Aug 28, 2012 at 03:04:03PM +0200, Sasha Levin wrote:

quoted

Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will
use indirect descriptors and allocate them using a simple
kmalloc().

This patch adds a cache which will allow indirect buffers under
a configurable size to be allocated from that cache instead.

Signed-off-by: Sasha Levin <redacted>

I imagine this helps performance? Any numbers?

I ran benchmarks on the original RFC, I've re-tested it now and got similar
numbers to the original ones (virtio-net using vhost-net, thresh=16):

Before:
	Recv   Send    Send
	Socket Socket  Message  Elapsed
	Size   Size    Size     Time     Throughput
	bytes  bytes   bytes    secs.    10^6bits/sec

	 87380  16384  16384    10.00    4512.12

After:
	Recv   Send    Send
	Socket Socket  Message  Elapsed
	Size   Size    Size     Time     Throughput
	bytes  bytes   bytes    secs.    10^6bits/sec

	 87380  16384  16384    10.00    5399.18


Thanks,
Sasha

This is with both patches 1 + 2?
Sorry could you please also test what happens if you apply
- just patch 1
- just patch 2

Thanks!

Sure thing!

I've also re-ran it on a IBM server type host instead of my laptop. Here are the
results:

Vanilla kernel:

MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.33.1
() port 0 AF_INET
enable_enobufs failed: getprotobyname
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    10.00    7922.72

Patch 1, with threshold=16:

MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.33.1
() port 0 AF_INET
enable_enobufs failed: getprotobyname
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    10.00    8415.07

Patch 2:

MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.33.1
() port 0 AF_INET
enable_enobufs failed: getprotobyname
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    10.00    8931.05


Note that these are simple tests with netperf listening on one end and a simple
'netperf -H [host]' within the guest. If there are other tests which may be
interesting please let me know.


Thanks,
Sasha

On Wed, Aug 29, 2012 at 05:03:03PM +0200, Sasha Levin wrote:

On 08/29/2012 01:07 PM, Michael S. Tsirkin wrote:

quoted

On Tue, Aug 28, 2012 at 03:35:00PM +0200, Sasha Levin wrote:

quoted

On 08/28/2012 03:20 PM, Michael S. Tsirkin wrote:

quoted

On Tue, Aug 28, 2012 at 03:04:03PM +0200, Sasha Levin wrote:

quoted

Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will
use indirect descriptors and allocate them using a simple
kmalloc().

This patch adds a cache which will allow indirect buffers under
a configurable size to be allocated from that cache instead.

Signed-off-by: Sasha Levin <redacted>

I imagine this helps performance? Any numbers?

I ran benchmarks on the original RFC, I've re-tested it now and got similar
numbers to the original ones (virtio-net using vhost-net, thresh=16):

Before:
	Recv   Send    Send
	Socket Socket  Message  Elapsed
	Size   Size    Size     Time     Throughput
	bytes  bytes   bytes    secs.    10^6bits/sec

	 87380  16384  16384    10.00    4512.12

After:
	Recv   Send    Send
	Socket Socket  Message  Elapsed
	Size   Size    Size     Time     Throughput
	bytes  bytes   bytes    secs.    10^6bits/sec

	 87380  16384  16384    10.00    5399.18


Thanks,
Sasha

This is with both patches 1 + 2?
Sorry could you please also test what happens if you apply
- just patch 1
- just patch 2

Thanks!

Sure thing!

I've also re-ran it on a IBM server type host instead of my laptop. Here are the
results:

Vanilla kernel:

MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.33.1
() port 0 AF_INET
enable_enobufs failed: getprotobyname
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    10.00    7922.72

Patch 1, with threshold=16:

OK so let us set it to 16 for virtio-net by default then?

MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.33.1
() port 0 AF_INET
enable_enobufs failed: getprotobyname
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    10.00    8415.07

Patch 2:

MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.33.1
() port 0 AF_INET
enable_enobufs failed: getprotobyname
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    10.00    8931.05


Note that these are simple tests with netperf listening on one end and a simple
'netperf -H [host]' within the guest. If there are other tests which may be
interesting please let me know.


Thanks,
Sasha

Checking that host CPU utilization did not jump would be nice.
E.g. measure BW/host CPU.

-- 
MST

On Tue, Aug 28, 2012 at 03:04:03PM +0200, Sasha Levin wrote:

Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will
use indirect descriptors and allocate them using a simple
kmalloc().

This patch adds a cache which will allow indirect buffers under
a configurable size to be allocated from that cache instead.

Signed-off-by: Sasha Levin <redacted>

The API is ugly - how does driver know what to set?
Is this a typical request size? Then let's call it that.

Also this is really per VQ, right?

What is a good default for net? I guess max sg?

So this means that drivers need to know how large each
descriptor is to avoid trying to allocate 32Mbyte chunks :)

This looks wrong. indirect_alloc_thresh is in entries but len is in
bytes, isn't it?

I am not a purist but this line looks way too long.
Also - no need to check cache creation succeeded?
On failure - disable caching?

Also - let's check that values are sane before passing them on?
They come from user after all.

Also - should not threshold be per VQ? E.g. for -net we do not
need the cache for RX unless in legacy big packet mode.

On Wed, Aug 29, 2012 at 05:03:03PM +0200, Sasha Levin wrote:

On 08/29/2012 01:07 PM, Michael S. Tsirkin wrote:

quoted

On Tue, Aug 28, 2012 at 03:35:00PM +0200, Sasha Levin wrote:

quoted

On 08/28/2012 03:20 PM, Michael S. Tsirkin wrote:

quoted

On Tue, Aug 28, 2012 at 03:04:03PM +0200, Sasha Levin wrote:

quoted

Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will
use indirect descriptors and allocate them using a simple
kmalloc().

This patch adds a cache which will allow indirect buffers under
a configurable size to be allocated from that cache instead.

Signed-off-by: Sasha Levin <redacted>

I imagine this helps performance? Any numbers?

I ran benchmarks on the original RFC, I've re-tested it now and got similar
numbers to the original ones (virtio-net using vhost-net, thresh=16):

Before:
	Recv   Send    Send
	Socket Socket  Message  Elapsed
	Size   Size    Size     Time     Throughput
	bytes  bytes   bytes    secs.    10^6bits/sec

	 87380  16384  16384    10.00    4512.12

After:
	Recv   Send    Send
	Socket Socket  Message  Elapsed
	Size   Size    Size     Time     Throughput
	bytes  bytes   bytes    secs.    10^6bits/sec

	 87380  16384  16384    10.00    5399.18


Thanks,
Sasha

This is with both patches 1 + 2?
Sorry could you please also test what happens if you apply
- just patch 1
- just patch 2

Thanks!

Sure thing!

I've also re-ran it on a IBM server type host instead of my laptop. Here are the
results:

Vanilla kernel:

MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.33.1
() port 0 AF_INET
enable_enobufs failed: getprotobyname
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    10.00    7922.72

Patch 1, with threshold=16:

MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.33.1
() port 0 AF_INET
enable_enobufs failed: getprotobyname
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    10.00    8415.07

Patch 2:

MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.33.1
() port 0 AF_INET
enable_enobufs failed: getprotobyname
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    10.00    8931.05


Note that these are simple tests with netperf listening on one end and a simple
'netperf -H [host]' within the guest. If there are other tests which may be
interesting please let me know.


Thanks,
Sasha

And which parameter did you use for patch 2?

On 08/29/2012 05:38 PM, Michael S. Tsirkin wrote:

On Wed, Aug 29, 2012 at 05:03:03PM +0200, Sasha Levin wrote:

quoted

On 08/29/2012 01:07 PM, Michael S. Tsirkin wrote:

quoted

On Tue, Aug 28, 2012 at 03:35:00PM +0200, Sasha Levin wrote:

quoted

On 08/28/2012 03:20 PM, Michael S. Tsirkin wrote:

quoted

On Tue, Aug 28, 2012 at 03:04:03PM +0200, Sasha Levin wrote:

quoted

Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will
use indirect descriptors and allocate them using a simple
kmalloc().

This patch adds a cache which will allow indirect buffers under
a configurable size to be allocated from that cache instead.

Signed-off-by: Sasha Levin <redacted>

I imagine this helps performance? Any numbers?

I ran benchmarks on the original RFC, I've re-tested it now and got similar
numbers to the original ones (virtio-net using vhost-net, thresh=16):

Before:
	Recv   Send    Send
	Socket Socket  Message  Elapsed
	Size   Size    Size     Time     Throughput
	bytes  bytes   bytes    secs.    10^6bits/sec

	 87380  16384  16384    10.00    4512.12

After:
	Recv   Send    Send
	Socket Socket  Message  Elapsed
	Size   Size    Size     Time     Throughput
	bytes  bytes   bytes    secs.    10^6bits/sec

	 87380  16384  16384    10.00    5399.18


Thanks,
Sasha

This is with both patches 1 + 2?
Sorry could you please also test what happens if you apply
- just patch 1
- just patch 2

Thanks!

Sure thing!

I've also re-ran it on a IBM server type host instead of my laptop. Here are the
results:

Vanilla kernel:

MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.33.1
() port 0 AF_INET
enable_enobufs failed: getprotobyname
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    10.00    7922.72

Patch 1, with threshold=16:

MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.33.1
() port 0 AF_INET
enable_enobufs failed: getprotobyname
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    10.00    8415.07

Patch 2:

MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.33.1
() port 0 AF_INET
enable_enobufs failed: getprotobyname
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    10.00    8931.05


Note that these are simple tests with netperf listening on one end and a simple
'netperf -H [host]' within the guest. If there are other tests which may be
interesting please let me know.


Thanks,
Sasha

And which parameter did you use for patch 2?

Same as in the first one, 16, the only difference in patch 2 is that we use a
kmemcache, so there's no point in changing the threshold vs patch 1.


Thanks,
Sasha

On 08/29/2012 05:38 PM, Michael S. Tsirkin wrote:

On Tue, Aug 28, 2012 at 03:04:03PM +0200, Sasha Levin wrote:

quoted

Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will
use indirect descriptors and allocate them using a simple
kmalloc().

This patch adds a cache which will allow indirect buffers under
a configurable size to be allocated from that cache instead.

Signed-off-by: Sasha Levin <redacted>

The API is ugly - how does driver know what to set?
Is this a typical request size? Then let's call it that.

We've discussed it during the RFC phase, the idea is that we don't know what
would be a good number to use as threshold - which is why I'd like to keep it
disabled as default until it gets more serious tests.

The driver doesn't know what to set, the plan was to make it a dynamic
algorithms which would change it based on current load. Since I can't really do
testing which will provide the correct values for that, the decision was to do
it this way as the first stage and modify it later.

Also this is really per VQ, right?

Right, we keep it per-device at this stage to keep it simple.

What is a good default for net? I guess max sg?

I think that it depends on the workload. I'd say we should keep the default to 0
(disabled) unless we can have a good way to adjust it to the load.

quoted

---

Changes in v2:

 - Free correctly indirect buffers.

 drivers/block/virtio_blk.c          |  4 ++++
 drivers/char/hw_random/virtio-rng.c |  4 ++++
 drivers/char/virtio_console.c       |  4 ++++
 drivers/net/virtio_net.c            |  4 ++++
 drivers/virtio/virtio_balloon.c     |  4 ++++
 drivers/virtio/virtio_ring.c        | 28 ++++++++++++++++++++++++----
 include/linux/virtio.h              |  1 +
 net/9p/trans_virtio.c               |  5 +++++
 8 files changed, 50 insertions(+), 4 deletions(-)

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 13b8ae9..7f670af 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c

@@ -25,6 +25,9 @@ struct workqueue_struct *virtblk_wq;
 static unsigned int indirect_thresh;
 module_param(indirect_thresh, uint, S_IRUGO);
 
+static unsigned int indirect_alloc_thresh;
+module_param(indirect_alloc_thresh, uint, S_IRUGO);
+
 struct virtio_blk
 {
 	struct virtio_device *vdev;

@@ -739,6 +742,7 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
 	vblk->config_enable = true;
 	vdev->indirect_thresh = indirect_thresh;
+	vdev->indirect_alloc_thresh = indirect_alloc_thresh;
 
 	err = init_vq(vblk);
 	if (err)

diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c
index 02d8421..8475ece 100644
--- a/drivers/char/hw_random/virtio-rng.c
+++ b/drivers/char/hw_random/virtio-rng.c

@@ -28,6 +28,9 @@
 static unsigned int indirect_thresh;
 module_param(indirect_thresh, uint, S_IRUGO);
 
+static unsigned int indirect_alloc_thresh;
+module_param(indirect_alloc_thresh, uint, S_IRUGO);
+
 static struct virtqueue *vq;
 static unsigned int data_avail;
 static DECLARE_COMPLETION(have_data);

@@ -97,6 +100,7 @@ static int probe_common(struct virtio_device *vdev)
 
 	/* We expect a single virtqueue. */
 	vdev->indirect_thresh = indirect_thresh;
+	vdev->indirect_alloc_thresh = indirect_alloc_thresh;
 	vq = virtio_find_single_vq(vdev, random_recv_done, "input");
 	if (IS_ERR(vq))
 		return PTR_ERR(vq);

diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index fc14e7f..c6f24a7 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c

@@ -42,6 +42,9 @@
 static unsigned int indirect_thresh;
 module_param(indirect_thresh, uint, S_IRUGO);
 
+static unsigned int indirect_alloc_thresh;
+module_param(indirect_alloc_thresh, uint, S_IRUGO);
+
 /*
  * This is a global struct for storing common data for all the devices
  * this driver handles.

@@ -1891,6 +1894,7 @@ static int __devinit virtcons_probe(struct virtio_device *vdev)
 			      &portdev->config.max_nr_ports) == 0)
 		multiport = true;
 	vdev->indirect_thresh = indirect_thresh;
+	vdev->indirect_alloc_thresh = indirect_alloc_thresh;
 
 	err = init_vqs(portdev);
 	if (err < 0) {

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 64a8321..c091efd 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c

@@ -37,6 +37,9 @@ module_param(gso, bool, 0444);
 static unsigned int indirect_thresh;
 module_param(indirect_thresh, uint, S_IRUGO);
 
+static unsigned int indirect_alloc_thresh;
+module_param(indirect_alloc_thresh, uint, S_IRUGO);
+
 /* FIXME: MTU in config. */
 #define MAX_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN)
 #define GOOD_COPY_LEN	128

@@ -1132,6 +1135,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
 		vi->mergeable_rx_bufs = true;
 	vdev->indirect_thresh = indirect_thresh;
+	vdev->indirect_alloc_thresh = indirect_alloc_thresh;
 
 	err = init_vqs(vi);
 	if (err)

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index fce7347..ccf87db 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c

@@ -38,6 +38,9 @@
 static unsigned int indirect_thresh;
 module_param(indirect_thresh, uint, S_IRUGO);
 
+static unsigned int indirect_alloc_thresh;
+module_param(indirect_alloc_thresh, uint, S_IRUGO);
+
 struct virtio_balloon
 {
 	struct virtio_device *vdev;

@@ -360,6 +363,7 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	vb->vdev = vdev;
 	vb->need_stats_update = 0;
 	vdev->indirect_thresh = indirect_thresh;
+	vdev->indirect_alloc_thresh = indirect_alloc_thresh;
 
 	err = init_vqs(vb);
 	if (err)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 99a64a7..e8b9c54 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c

@@ -93,6 +93,10 @@ struct vring_virtqueue
 	 */
 	unsigned int indirect_thresh;
 
+	/* Buffers below this size will be allocated from cache */
+	unsigned int indirect_alloc_thresh;
+	struct kmem_cache *indirect_cache;
+
 	/* Host publishes avail event idx */
 	bool event;
 

@@ -135,7 +139,10 @@ static int vring_add_indirect(struct vring_virtqueue *vq,
 	unsigned head;
 	int i;
 
-	desc = kmalloc((out + in) * sizeof(struct vring_desc), gfp);
+	if ((out + in) <= vq->indirect_alloc_thresh)
+		desc = kmem_cache_alloc(vq->indirect_cache, gfp);
+	else
+		desc = kmalloc((out + in) * sizeof(struct vring_desc), gfp);
 	if (!desc)
 		return -ENOMEM;

So this means that drivers need to know how large each
descriptor is to avoid trying to allocate 32Mbyte chunks :)

Right, this interface isn't perfect and would hopefully be removed in favour of
a dynamic algorithm in the driver.

quoted

@@ -384,8 +391,13 @@ static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
 	i = head;
 
 	/* Free the indirect table */
-	if (vq->vring.desc[i].flags & VRING_DESC_F_INDIRECT)
-		kfree(phys_to_virt(vq->vring.desc[i].addr));
+	if (vq->vring.desc[i].flags & VRING_DESC_F_INDIRECT) {
+		if (vq->vring.desc[i].len > vq->indirect_alloc_thresh)

This looks wrong. indirect_alloc_thresh is in entries but len is in
bytes, isn't it?

Uh, yes. It's supposed to be '.len/sizeof(struct vring_desc)'.

quoted

+			kfree(phys_to_virt(vq->vring.desc[i].addr));
+		else
+			kmem_cache_free(vq->indirect_cache,
+					phys_to_virt(vq->vring.desc[i].addr));
+	}
 
 	while (vq->vring.desc[i].flags & VRING_DESC_F_NEXT) {
 		i = vq->vring.desc[i].next;

@@ -654,14 +666,20 @@ struct virtqueue *vring_new_virtqueue(unsigned int num,
 	vq->last_used_idx = 0;
 	vq->num_added = 0;
 	vq->indirect_thresh = 0;
+	vq->indirect_alloc_thresh = 0;
+	vq->indirect_cache = NULL;
 	list_add_tail(&vq->vq.list, &vdev->vqs);
 #ifdef DEBUG
 	vq->in_use = false;
 	vq->last_add_time_valid = false;
 #endif
 
-	if (virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC))
+	if (virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC)) {
 		vq->indirect_thresh = vdev->indirect_thresh;
+		vq->indirect_alloc_thresh = vdev->indirect_alloc_thresh;
+		if (vq->indirect_alloc_thresh)
+			vq->indirect_cache = KMEM_CACHE(vring_desc[vq->indirect_alloc_thresh],

0);

I am not a purist but this line looks way too long.
Also - no need to check cache creation succeeded?
On failure - disable caching?

Also - let's check that values are sane before passing them on?
They come from user after all.

will fix these two.

Also - should not threshold be per VQ? E.g. for -net we do not
need the cache for RX unless in legacy big packet mode.

We've discussed it two months ago over IRC (at least thats what I have in my
notes) - the plan was to keep it simple per-device until something more advanced
to deal with the threshold shows up.


Thanks,
Sasha

quoted

+	}
 
 	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
 

@@ -685,6 +703,8 @@ EXPORT_SYMBOL_GPL(vring_new_virtqueue);
 void vring_del_virtqueue(struct virtqueue *vq)
 {
 	list_del(&vq->list);
+	if (to_vvq(vq)->indirect_cache)
+		kmem_cache_destroy(to_vvq(vq)->indirect_cache);
 	kfree(to_vvq(vq));
 }
 EXPORT_SYMBOL_GPL(vring_del_virtqueue);

diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 48bc457..3261c02 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h

@@ -70,6 +70,7 @@ struct virtio_device {
 	unsigned long features[1];
 	void *priv;
 	unsigned int indirect_thresh;
+	unsigned int indirect_alloc_thresh;
 };
 
 #define dev_to_virtio(dev) container_of(dev, struct virtio_device, dev)

diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index fc93962..3044c86 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c

@@ -55,6 +55,9 @@
 static unsigned int indirect_thresh;
 module_param(indirect_thresh, uint, S_IRUGO);
 
+static unsigned int indirect_alloc_thresh;
+module_param(indirect_alloc_thresh, uint, S_IRUGO);
+
 /* a single mutex to manage channel initialization and attachment */
 static DEFINE_MUTEX(virtio_9p_lock);
 static DECLARE_WAIT_QUEUE_HEAD(vp_wq);

@@ -505,6 +508,8 @@ static int p9_virtio_probe(struct virtio_device *vdev)
 
 	/* We expect one virtqueue, for requests. */
 	vdev->indirect_thresh = indirect_thresh;
+	vdev->indirect_alloc_thresh = indirect_alloc_thresh;
+
 	chan->vq = virtio_find_single_vq(vdev, req_done, "requests");
 	if (IS_ERR(chan->vq)) {
 		err = PTR_ERR(chan->vq);

-- 
1.7.12