| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1403775708-22244-3-git-send-email-ming.lei@canonical.com>
Date: Thu, 26 Jun 2014 17:41:48 +0800
From: Ming Lei <ming.lei@...onical.com>
To: Jens Axboe <axboe@...nel.dk>, linux-kernel@...r.kernel.org
Cc: Rusty Russell <rusty@...tcorp.com.au>, linux-api@...r.kernel.org,
virtualization@...ts.linux-foundation.org,
"Michael S. Tsirkin" <mst@...hat.com>,
Stefan Hajnoczi <stefanha@...hat.com>,
Paolo Bonzini <pbonzini@...hat.com>,
Ming Lei <ming.lei@...onical.com>
Subject: [PATCH v3 2/2] block: virtio-blk: support multi virt queues per virtio-blk device
Firstly this patch supports more than one virtual queues for virtio-blk
device.
Secondly this patch maps the virtual queue to blk-mq's hardware queue.
With this approach, both scalability and performance can be improved.
Signed-off-by: Ming Lei <ming.lei@...onical.com>
---
drivers/block/virtio_blk.c | 104 +++++++++++++++++++++++++++++++++++---------
1 file changed, 84 insertions(+), 20 deletions(-)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index f63d358..0a58140 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -15,17 +15,22 @@
#include <linux/numa.h>
#define PART_BITS 4
+#define VQ_NAME_LEN 16
static int major;
static DEFINE_IDA(vd_index_ida);
static struct workqueue_struct *virtblk_wq;
+struct virtio_blk_vq {
+ struct virtqueue *vq;
+ spinlock_t lock;
+ char name[VQ_NAME_LEN];
+} ____cacheline_aligned_in_smp;
+
struct virtio_blk
{
struct virtio_device *vdev;
- struct virtqueue *vq;
- spinlock_t vq_lock;
/* The disk structure for the kernel. */
struct gendisk *disk;
@@ -47,6 +52,10 @@ struct virtio_blk
/* Ida index - used to track minor number allocations. */
int index;
+
+ /* num of vqs */
+ int num_vqs;
+ struct virtio_blk_vq *vqs;
};
struct virtblk_req
@@ -133,14 +142,15 @@ static void virtblk_done(struct virtqueue *vq)
{
struct virtio_blk *vblk = vq->vdev->priv;
bool req_done = false;
+ int qid = vq->index;
struct virtblk_req *vbr;
unsigned long flags;
unsigned int len;
- spin_lock_irqsave(&vblk->vq_lock, flags);
+ spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
do {
virtqueue_disable_cb(vq);
- while ((vbr = virtqueue_get_buf(vblk->vq, &len)) != NULL) {
+ while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) {
blk_mq_complete_request(vbr->req);
req_done = true;
}
@@ -151,7 +161,7 @@ static void virtblk_done(struct virtqueue *vq)
/* In case queue is stopped waiting for more buffers. */
if (req_done)
blk_mq_start_stopped_hw_queues(vblk->disk->queue, true);
- spin_unlock_irqrestore(&vblk->vq_lock, flags);
+ spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
}
static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
@@ -160,6 +170,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
unsigned long flags;
unsigned int num;
+ int qid = hctx->queue_num;
const bool last = (req->cmd_flags & REQ_END) != 0;
int err;
bool notify = false;
@@ -202,12 +213,12 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
}
- spin_lock_irqsave(&vblk->vq_lock, flags);
- err = __virtblk_add_req(vblk->vq, vbr, vbr->sg, num);
+ spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
+ err = __virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num);
if (err) {
- virtqueue_kick(vblk->vq);
+ virtqueue_kick(vblk->vqs[qid].vq);
blk_mq_stop_hw_queue(hctx);
- spin_unlock_irqrestore(&vblk->vq_lock, flags);
+ spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
/* Out of mem doesn't actually happen, since we fall back
* to direct descriptors */
if (err == -ENOMEM || err == -ENOSPC)
@@ -215,12 +226,12 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
return BLK_MQ_RQ_QUEUE_ERROR;
}
- if (last && virtqueue_kick_prepare(vblk->vq))
+ if (last && virtqueue_kick_prepare(vblk->vqs[qid].vq))
notify = true;
- spin_unlock_irqrestore(&vblk->vq_lock, flags);
+ spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
if (notify)
- virtqueue_notify(vblk->vq);
+ virtqueue_notify(vblk->vqs[qid].vq);
return BLK_MQ_RQ_QUEUE_OK;
}
@@ -377,12 +388,64 @@ static void virtblk_config_changed(struct virtio_device *vdev)
static int init_vq(struct virtio_blk *vblk)
{
int err = 0;
+ int i;
+ vq_callback_t **callbacks;
+ const char **names;
+ struct virtqueue **vqs;
+ unsigned short num_vqs;
+ struct virtio_device *vdev = vblk->vdev;
+
+ err = virtio_cread_feature(vdev, VIRTIO_BLK_F_MQ,
+ struct virtio_blk_config, num_queues,
+ &num_vqs);
+ if (err)
+ num_vqs = 1;
+
+ vblk->vqs = kmalloc(sizeof(*vblk->vqs) * num_vqs, GFP_KERNEL);
+ if (!vblk->vqs) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ names = kmalloc(sizeof(*names) * num_vqs, GFP_KERNEL);
+ if (!names)
+ goto err_names;
+
+ callbacks = kmalloc(sizeof(*callbacks) * num_vqs, GFP_KERNEL);
+ if (!callbacks)
+ goto err_callbacks;
+
+ vqs = kmalloc(sizeof(*vqs) * num_vqs, GFP_KERNEL);
+ if (!vqs)
+ goto err_vqs;
- /* We expect one virtqueue, for output. */
- vblk->vq = virtio_find_single_vq(vblk->vdev, virtblk_done, "requests");
- if (IS_ERR(vblk->vq))
- err = PTR_ERR(vblk->vq);
+ for (i = 0; i < num_vqs; i++) {
+ callbacks[i] = virtblk_done;
+ snprintf(vblk->vqs[i].name, VQ_NAME_LEN, "req.%d", i);
+ names[i] = vblk->vqs[i].name;
+ }
+
+ /* Discover virtqueues and write information to configuration. */
+ err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names);
+ if (err)
+ goto err_find_vqs;
+ for (i = 0; i < num_vqs; i++) {
+ spin_lock_init(&vblk->vqs[i].lock);
+ vblk->vqs[i].vq = vqs[i];
+ }
+ vblk->num_vqs = num_vqs;
+
+ err_find_vqs:
+ kfree(vqs);
+ err_vqs:
+ kfree(callbacks);
+ err_callbacks:
+ kfree(names);
+ err_names:
+ if (err)
+ kfree(vblk->vqs);
+ out:
return err;
}
@@ -551,7 +614,6 @@ static int virtblk_probe(struct virtio_device *vdev)
err = init_vq(vblk);
if (err)
goto out_free_vblk;
- spin_lock_init(&vblk->vq_lock);
/* FIXME: How many partitions? How long is a piece of string? */
vblk->disk = alloc_disk(1 << PART_BITS);
@@ -562,7 +624,7 @@ static int virtblk_probe(struct virtio_device *vdev)
/* Default queue sizing is to fill the ring. */
if (!virtblk_queue_depth) {
- virtblk_queue_depth = vblk->vq->num_free;
+ virtblk_queue_depth = vblk->vqs[0].vq->num_free;
/* ... but without indirect descs, we use 2 descs per req */
if (!virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC))
virtblk_queue_depth /= 2;
@@ -570,7 +632,6 @@ static int virtblk_probe(struct virtio_device *vdev)
memset(&vblk->tag_set, 0, sizeof(vblk->tag_set));
vblk->tag_set.ops = &virtio_mq_ops;
- vblk->tag_set.nr_hw_queues = 1;
vblk->tag_set.queue_depth = virtblk_queue_depth;
vblk->tag_set.numa_node = NUMA_NO_NODE;
vblk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
@@ -578,6 +639,7 @@ static int virtblk_probe(struct virtio_device *vdev)
sizeof(struct virtblk_req) +
sizeof(struct scatterlist) * sg_elems;
vblk->tag_set.driver_data = vblk;
+ vblk->tag_set.nr_hw_queues = vblk->num_vqs;
err = blk_mq_alloc_tag_set(&vblk->tag_set);
if (err)
@@ -727,6 +789,7 @@ static void virtblk_remove(struct virtio_device *vdev)
refc = atomic_read(&disk_to_dev(vblk->disk)->kobj.kref.refcount);
put_disk(vblk->disk);
vdev->config->del_vqs(vdev);
+ kfree(vblk->vqs);
kfree(vblk);
/* Only free device id if we don't have any users */
@@ -777,7 +840,8 @@ static const struct virtio_device_id id_table[] = {
static unsigned int features[] = {
VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI,
- VIRTIO_BLK_F_WCE, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE
+ VIRTIO_BLK_F_WCE, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
+ VIRTIO_BLK_F_MQ,
};
static struct virtio_driver virtio_blk = {
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists