Virtualization - Aug 2012 - [PATCH v3 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 <levinsasha928 at gmail.com>
---
 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..7c63065 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..3a644f1 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..da2e44c 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..949c89e 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 = 16;
+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..ca5ae7a 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..4063e03 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..418f933 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 <levinsasha928 at gmail.com>
---
 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        | 34 ++++++++++++++++++++++++++++++----
 include/linux/virtio.h              |  1 +
 net/9p/trans_virtio.c               |  5 +++++
 8 files changed, 56 insertions(+), 4 deletions(-)

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 7c63065..e4c6c42 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 3a644f1..ed22db8 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 da2e44c..8f30732 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 949c89e..a00e19d 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 = 16;
 module_param(indirect_thresh, uint, S_IRUGO);
 
+static unsigned int indirect_alloc_thresh = 16;
+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 ca5ae7a..039c4a6 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 4063e03..dde867b 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 +391,14 @@ 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) {
+		u32 descs = vq->vring.desc[i].len / sizeof(struct vring_desc);
+		if (descs > 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 +667,25 @@ 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);
+
+			if (vq->indirect_cache == NULL)
+				vq->indirect_alloc_thresh = 0;
+		}
+	}
 
 	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
 
@@ -685,6 +709,8 @@ 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 418f933..058b6dd 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 Thu, Aug 30, 2012 at 01:21:57PM +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 <levinsasha928 at gmail.com>
Some minor comments here and for the next patch.
And I think I see a bug. Otherwise looks good to me.

Let's add MODULE_PARM_DESC clearly explaining
that this is a debugging option and users should
not touch it.

We can also add this text:
Min. number of free space in the ring to trigger direct
descriptor use. Set to 1 to always use direct
descriptors.


Also maybe direct_thresh is a better name.
> ---
>  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..7c63065 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..3a644f1 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..da2e44c 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..949c89e 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 = 16;
> +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..ca5ae7a 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..4063e03 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.
> +	 */
Fix comments to mention threshold.
> +	if ((out + in) > 1 && vq->num_free &&
> +		(vq->num_free < vq->indirect_thresh)) {
Please do not add () around conditions like this.

>  		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;
> +
cleaner
	else
	`	vq->indirect_thresh = 0;

So when indirect_thresh is 0 (default) this
disables indirect completely. Likely not what you wanted.
Maybe the right thing to do is something like
	if (!indirect_thresh)
		vq->indirect_thresh = vq->vring.num + 1
?
>  	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..418f933 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