[PATCH 07/10] xen/blkback: pseudo support for multi hardware queues

From: Bob Liu
Date: Sun Feb 15 2015 - 03:21:07 EST

Next message: Bob Liu: "[PATCH 08/10] xen/blkfront: negotiate hardware queue number with backend"
Previous message: Bob Liu: "[PATCH 10/10] xen/blkfront: use work queue to fast blkif interrupt return"
In reply to: Bob Liu: "[PATCH 10/10] xen/blkfront: use work queue to fast blkif interrupt return"
Next in thread: Bob Liu: "[PATCH 08/10] xen/blkfront: negotiate hardware queue number with backend"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Prepare patch for multi hardware queues, the ring number was mandatory set to 1.

Signed-off-by: Arianna Avanzini <avanzini.arianna@xxxxxxxxx>
Signed-off-by: Bob Liu <bob.liu@xxxxxxxxxx>
---
drivers/block/xen-blkback/common.h | 3 +-
drivers/block/xen-blkback/xenbus.c | 368 +++++++++++++++++++++++--------------
2 files changed, 233 insertions(+), 138 deletions(-)

diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index 71863d4..4565deb 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -333,7 +333,8 @@ struct xen_blkif {
unsigned long long st_rd_sect;
unsigned long long st_wr_sect;
/* Rings for this device */
- struct xen_blkif_ring ring;
+ struct xen_blkif_ring *rings;
+ unsigned int nr_rings;
};

struct seg_buf {
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 4b7bde6..93e5f38 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -78,11 +78,14 @@ static int blkback_name(struct xen_blkif *blkif, char *buf)

static void xen_update_blkif_status(struct xen_blkif *blkif)
{
- int err;
+ int err, i;
char name[TASK_COMM_LEN];
+ char per_ring_name[TASK_COMM_LEN + 4];
+ struct xen_blkif_ring *ring;

- /* Not ready to connect? */
- if (!blkif->ring.irq || !blkif->vbd.bdev)
+ /* Not ready to connect? Check irq of first ring as the others
+ * should all be the same.*/
+ if (!blkif->rings || !blkif->rings[0].irq || !blkif->vbd.bdev)
return;

/* Already connected? */
@@ -107,21 +110,108 @@ static void xen_update_blkif_status(struct xen_blkif *blkif)
}
invalidate_inode_pages2(blkif->vbd.bdev->bd_inode->i_mapping);

- blkif->ring.xenblkd = kthread_run(xen_blkif_schedule, &blkif->ring, "%s", name);
- if (IS_ERR(blkif->ring.xenblkd)) {
- err = PTR_ERR(blkif->ring.xenblkd);
- blkif->ring.xenblkd = NULL;
- xenbus_dev_error(blkif->be->dev, err, "start xenblkd");
- return;
+ if (blkif->nr_rings == 1) {
+ blkif->rings[0].xenblkd = kthread_run(xen_blkif_schedule, &blkif->rings[0], "%s", name);
+ if (IS_ERR(blkif->rings[0].xenblkd)) {
+ err = PTR_ERR(blkif->rings[0].xenblkd);
+ blkif->rings[0].xenblkd = NULL;
+ xenbus_dev_error(blkif->be->dev, err, "start xenblkd");
+ return;
+ }
+ } else {
+ for (i = 0 ; i < blkif->nr_rings ; i++) {
+ snprintf(per_ring_name, TASK_COMM_LEN + 1, "%s-%d", name, i);
+ ring = &blkif->rings[i];
+ ring->xenblkd = kthread_run(xen_blkif_schedule, ring, "%s", per_ring_name);
+ if (IS_ERR(ring->xenblkd)) {
+ err = PTR_ERR(ring->xenblkd);
+ ring->xenblkd = NULL;
+ xenbus_dev_error(blkif->be->dev, err,
+ "start %s xenblkd", per_ring_name);
+ return;
+ }
+ }
}
}

+static int xen_blkif_alloc_rings(struct xen_blkif *blkif)
+{
+ struct xen_blkif_ring *ring;
+ struct pending_req *req, *n;
+ int i, j, r;
+
+ blkif->rings = kzalloc(blkif->nr_rings * sizeof(struct xen_blkif_ring), GFP_KERNEL);
+ if (!blkif->rings)
+ return -ENOMEM;
+
+ for (r = 0; r < blkif->nr_rings; r++) {
+ ring = &blkif->rings[r];
+ spin_lock_init(&ring->blk_ring_lock);
+ init_waitqueue_head(&ring->wq);
+ ring->st_print = jiffies;
+ ring->persistent_gnts.rb_node = NULL;
+ spin_lock_init(&ring->free_pages_lock);
+ INIT_LIST_HEAD(&ring->free_pages);
+ INIT_LIST_HEAD(&ring->persistent_purge_list);
+ ring->free_pages_num = 0;
+ atomic_set(&ring->persistent_gnt_in_use, 0);
+ atomic_set(&ring->inflight, 0);
+ INIT_WORK(&ring->persistent_purge_work, xen_blkbk_unmap_purged_grants);
+ INIT_LIST_HEAD(&ring->pending_free);
+
+ for (i = 0; i < XEN_BLKIF_REQS; i++) {
+ req = kzalloc(sizeof(*req), GFP_KERNEL);
+ if (!req)
+ goto fail;
+ list_add_tail(&req->free_list,
+ &ring->pending_free);
+ for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) {
+ req->segments[j] = kzalloc(sizeof(*req->segments[0]),
+ GFP_KERNEL);
+ if (!req->segments[j])
+ goto fail;
+ }
+ for (j = 0; j < MAX_INDIRECT_PAGES; j++) {
+ req->indirect_pages[j] = kzalloc(sizeof(*req->indirect_pages[0]),
+ GFP_KERNEL);
+ if (!req->indirect_pages[j])
+ goto fail;
+ }
+ }
+ spin_lock_init(&ring->pending_free_lock);
+ init_waitqueue_head(&ring->pending_free_wq);
+ init_waitqueue_head(&ring->shutdown_wq);
+ ring->blkif = blkif;
+ xen_blkif_get(blkif);
+ }
+ return 0;
+
+fail:
+ while (--r >= 0) {
+ ring = &blkif->rings[r];
+ list_for_each_entry_safe(req, n, &ring->pending_free, free_list) {
+ list_del(&req->free_list);
+ for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) {
+ if (!req->segments[j])
+ break;
+ kfree(req->segments[j]);
+ }
+ for (j = 0; j < MAX_INDIRECT_PAGES; j++) {
+ if (!req->indirect_pages[j])
+ break;
+ kfree(req->indirect_pages[j]);
+ }
+ kfree(req);
+ }
+ xen_blkif_put(blkif);
+ }
+ kfree(blkif->rings);
+ return -ENOMEM;
+}
+
static struct xen_blkif *xen_blkif_alloc(domid_t domid)
{
struct xen_blkif *blkif;
- struct pending_req *req, *n;
- int i, j;
- struct xen_blkif_ring *ring;

BUILD_BUG_ON(MAX_INDIRECT_PAGES > BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST);

@@ -130,68 +220,18 @@ static struct xen_blkif *xen_blkif_alloc(domid_t domid)
return ERR_PTR(-ENOMEM);

blkif->domid = domid;
- ring = &blkif->ring;
- spin_lock_init(&ring->blk_ring_lock);
atomic_set(&blkif->refcnt, 1);
- init_waitqueue_head(&ring->wq);
init_completion(&blkif->drain_complete);
atomic_set(&blkif->drain, 0);
- ring->st_print = jiffies;
- ring->persistent_gnts.rb_node = NULL;
- spin_lock_init(&ring->free_pages_lock);
- INIT_LIST_HEAD(&ring->free_pages);
- INIT_LIST_HEAD(&ring->persistent_purge_list);
- ring->free_pages_num = 0;
- atomic_set(&ring->persistent_gnt_in_use, 0);
- atomic_set(&ring->inflight, 0);
- INIT_WORK(&ring->persistent_purge_work, xen_blkbk_unmap_purged_grants);
-
- INIT_LIST_HEAD(&ring->pending_free);
INIT_WORK(&blkif->free_work, xen_blkif_deferred_free);

- for (i = 0; i < XEN_BLKIF_REQS; i++) {
- req = kzalloc(sizeof(*req), GFP_KERNEL);
- if (!req)
- goto fail;
- list_add_tail(&req->free_list, &ring->pending_free);
- for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) {
- req->segments[j] = kzalloc(sizeof(*req->segments[0]),
- GFP_KERNEL);
- if (!req->segments[j])
- goto fail;
- }
- for (j = 0; j < MAX_INDIRECT_PAGES; j++) {
- req->indirect_pages[j] = kzalloc(sizeof(*req->indirect_pages[0]),
- GFP_KERNEL);
- if (!req->indirect_pages[j])
- goto fail;
- }
+ blkif->nr_rings = 1;
+ if (xen_blkif_alloc_rings(blkif)) {
+ kmem_cache_free(xen_blkif_cachep, blkif);
+ return ERR_PTR(-ENOMEM);
}
- spin_lock_init(&ring->pending_free_lock);
- init_waitqueue_head(&ring->pending_free_wq);
- init_waitqueue_head(&ring->shutdown_wq);

return blkif;
-
-fail:
- list_for_each_entry_safe(req, n, &ring->pending_free, free_list) {
- list_del(&req->free_list);
- for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) {
- if (!req->segments[j])
- break;
- kfree(req->segments[j]);
- }
- for (j = 0; j < MAX_INDIRECT_PAGES; j++) {
- if (!req->indirect_pages[j])
- break;
- kfree(req->indirect_pages[j]);
- }
- kfree(req);
- }
-
- kmem_cache_free(xen_blkif_cachep, blkif);
-
- return ERR_PTR(-ENOMEM);
}

static int xen_blkif_map(struct xen_blkif_ring *ring, unsigned long shared_page,
@@ -249,69 +289,76 @@ static int xen_blkif_map(struct xen_blkif_ring *ring, unsigned long shared_page,

static int xen_blkif_disconnect(struct xen_blkif *blkif)
{
- struct xen_blkif_ring *ring = &blkif->ring;
+ struct xen_blkif_ring *ring;
+ int i;
+
+ for (i = 0; i < blkif->nr_rings; i++) {
+ ring = &blkif->rings[i];
+ if (ring->xenblkd) {
+ kthread_stop(ring->xenblkd);
+ wake_up(&ring->shutdown_wq);
+ ring->xenblkd = NULL;
+ }

- if (ring->xenblkd) {
- kthread_stop(ring->xenblkd);
- wake_up(&ring->shutdown_wq);
- ring->xenblkd = NULL;
- }
+ /* The above kthread_stop() guarantees that at this point we
+ * don't have any discard_io or other_io requests. So, checking
+ * for inflight IO is enough.
+ */
+ if (atomic_read(&ring->inflight) > 0)
+ return -EBUSY;

- /* The above kthread_stop() guarantees that at this point we
- * don't have any discard_io or other_io requests. So, checking
- * for inflight IO is enough.
- */
- if (atomic_read(&ring->inflight) > 0)
- return -EBUSY;
+ if (ring->irq) {
+ unbind_from_irqhandler(ring->irq, ring);
+ ring->irq = 0;
+ }

- if (ring->irq) {
- unbind_from_irqhandler(ring->irq, ring);
- ring->irq = 0;
- }
+ if (ring->blk_rings.common.sring) {
+ xenbus_unmap_ring_vfree(blkif->be->dev, ring->blk_ring);
+ ring->blk_rings.common.sring = NULL;
+ }

- if (ring->blk_rings.common.sring) {
- xenbus_unmap_ring_vfree(blkif->be->dev, ring->blk_ring);
- ring->blk_rings.common.sring = NULL;
+ /* Remove all persistent grants and the cache of ballooned pages. */
+ xen_blkbk_free_caches(ring);
}

- /* Remove all persistent grants and the cache of ballooned pages. */
- xen_blkbk_free_caches(ring);
-
return 0;
}

static void xen_blkif_free(struct xen_blkif *blkif)
{
struct pending_req *req, *n;
- int i = 0, j;
- struct xen_blkif_ring *ring = &blkif->ring;
+ int i = 0, j, r;
+ struct xen_blkif_ring *ring;

xen_blkif_disconnect(blkif);
xen_vbd_free(&blkif->vbd);

- /* Make sure everything is drained before shutting down */
- BUG_ON(ring->persistent_gnt_c != 0);
- BUG_ON(atomic_read(&ring->persistent_gnt_in_use) != 0);
- BUG_ON(ring->free_pages_num != 0);
- BUG_ON(!list_empty(&ring->persistent_purge_list));
- BUG_ON(!list_empty(&ring->free_pages));
- BUG_ON(!RB_EMPTY_ROOT(&ring->persistent_gnts));
+ for (r = 0; r < blkif->nr_rings; r++) {
+ ring = &blkif->rings[r];
+ /* Make sure everything is drained before shutting down */
+ BUG_ON(ring->persistent_gnt_c != 0);
+ BUG_ON(atomic_read(&ring->persistent_gnt_in_use) != 0);
+ BUG_ON(ring->free_pages_num != 0);
+ BUG_ON(!list_empty(&ring->persistent_purge_list));
+ BUG_ON(!list_empty(&ring->free_pages));
+ BUG_ON(!RB_EMPTY_ROOT(&ring->persistent_gnts));

- /* Check that there is no request in use */
- list_for_each_entry_safe(req, n, &ring->pending_free, free_list) {
- list_del(&req->free_list);
+ /* Check that there is no request in use */
+ list_for_each_entry_safe(req, n, &ring->pending_free, free_list) {
+ list_del(&req->free_list);

- for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++)
- kfree(req->segments[j]);
+ for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++)
+ kfree(req->segments[j]);

- for (j = 0; j < MAX_INDIRECT_PAGES; j++)
- kfree(req->indirect_pages[j]);
+ for (j = 0; j < MAX_INDIRECT_PAGES; j++)
+ kfree(req->indirect_pages[j]);

- kfree(req);
- i++;
- }
+ kfree(req);
+ i++;
+ }

- WARN_ON(i != XEN_BLKIF_REQS);
+ WARN_ON(i != XEN_BLKIF_REQS);
+ }

kmem_cache_free(xen_blkif_cachep, blkif);
}
@@ -339,15 +386,19 @@ int __init xen_blkif_interface_init(void)
struct xenbus_device *dev = to_xenbus_device(_dev); \
struct backend_info *be = dev_get_drvdata(&dev->dev); \
struct xen_blkif *blkif = be->blkif; \
- struct xen_blkif_ring *ring = &blkif->ring; \
+ struct xen_blkif_ring *ring; \
+ int i; \
\
- blkif->st_oo_req = ring->st_oo_req; \
- blkif->st_rd_req = ring->st_rd_req; \
- blkif->st_wr_req = ring->st_wr_req; \
- blkif->st_f_req = ring->st_f_req; \
- blkif->st_ds_req = ring->st_ds_req; \
- blkif->st_rd_sect = ring->st_rd_sect; \
- blkif->st_wr_sect = ring->st_wr_sect; \
+ for (i = 0; i < blkif->nr_rings; i++) { \
+ ring = &blkif->rings[i]; \
+ blkif->st_oo_req += ring->st_oo_req; \
+ blkif->st_rd_req += ring->st_rd_req; \
+ blkif->st_wr_req += ring->st_wr_req; \
+ blkif->st_f_req += ring->st_f_req; \
+ blkif->st_ds_req += ring->st_ds_req; \
+ blkif->st_rd_sect += ring->st_rd_sect; \
+ blkif->st_wr_sect += ring->st_wr_sect; \
+ } \
\
return sprintf(buf, format, ##args); \
} \
@@ -471,6 +522,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
static int xen_blkbk_remove(struct xenbus_device *dev)
{
struct backend_info *be = dev_get_drvdata(&dev->dev);
+ int i;

DPRINTK("");

@@ -487,7 +539,8 @@ static int xen_blkbk_remove(struct xenbus_device *dev)

if (be->blkif) {
xen_blkif_disconnect(be->blkif);
- xen_blkif_put(be->blkif);
+ for (i = 0; i < be->blkif->nr_rings; i++)
+ xen_blkif_put(be->blkif);
}

kfree(be->mode);
@@ -870,19 +923,13 @@ static int connect_ring(struct backend_info *be)
unsigned int evtchn;
unsigned int pers_grants;
char protocol[64] = "";
- int err;
+ int err, i;
+ char *xspath;
+ size_t xspathsize;
+ const size_t xenstore_path_ext_size = 11; /* sufficient for "/queue-NNN" */

DPRINTK("%s", dev->otherend);

- err = xenbus_gather(XBT_NIL, dev->otherend, "ring-ref", "%lu",
- &ring_ref, "event-channel", "%u", &evtchn, NULL);
- if (err) {
- xenbus_dev_fatal(dev, err,
- "reading %s/ring-ref and event-channel",
- dev->otherend);
- return err;
- }
-
be->blkif->blk_protocol = BLKIF_PROTOCOL_NATIVE;
err = xenbus_gather(XBT_NIL, dev->otherend, "protocol",
"%63s", protocol, NULL);
@@ -907,19 +954,66 @@ static int connect_ring(struct backend_info *be)
be->blkif->vbd.feature_gnt_persistent = pers_grants;
be->blkif->vbd.overflow_max_grants = 0;

- pr_info(DRV_PFX "ring-ref %ld, event-channel %d, protocol %d (%s) %s\n",
- ring_ref, evtchn, be->blkif->blk_protocol, protocol,
- pers_grants ? "persistent grants" : "");
+ if (be->blkif->nr_rings == 1) {
+ err = xenbus_gather(XBT_NIL, dev->otherend, "ring-ref", "%lu",
+ &ring_ref, "event-channel", "%u", &evtchn, NULL);
+ if (err) {
+ xenbus_dev_fatal(dev, err,
+ "reading %s/ring-ref and event-channel",
+ dev->otherend);
+ goto out;
+ }

- /* Map the shared frame, irq etc. */
- err = xen_blkif_map(&be->blkif->ring, ring_ref, evtchn);
- if (err) {
- xenbus_dev_fatal(dev, err, "mapping ring-ref %lu port %u",
- ring_ref, evtchn);
- return err;
- }
+ pr_info(DRV_PFX "ring-ref %ld, event-channel %d, protocol %d (%s) %s\n",
+ ring_ref, evtchn, be->blkif->blk_protocol, protocol,
+ pers_grants ? "persistent grants" : "");

+ /* Map the shared frame, irq etc. */
+ err = xen_blkif_map(&be->blkif->rings[0], ring_ref, evtchn);
+ if (err) {
+ xenbus_dev_fatal(dev, err, "mapping ring-ref %lu port %u",
+ ring_ref, evtchn);
+ goto out;
+ }
+ } else {
+ xspathsize = strlen(dev->otherend) + xenstore_path_ext_size;
+ xspath = kzalloc(xspathsize, GFP_KERNEL);
+ if (!xspath) {
+ xenbus_dev_fatal(dev, -ENOMEM, "reading ring references");
+ err = -ENOMEM;
+ goto out;
+ }
+
+ for (i = 0; i < be->blkif->nr_rings; i++) {
+ memset(xspath, 0, xspathsize);
+ snprintf(xspath, xspathsize, "%s/queue-%u", dev->otherend, i);
+ err = xenbus_gather(XBT_NIL, xspath, "ring-ref", "%lu",
+ &ring_ref, "event-channel", "%u", &evtchn, NULL);
+ if (err) {
+ xenbus_dev_fatal(dev, err,
+ "reading %s %d/ring-ref and event-channel",
+ xspath, i);
+ kfree(xspath);
+ goto out;
+ }
+
+ pr_info(DRV_PFX "ring-ref %ld, event-channel %d, protocol %d (%s) %s\n",
+ ring_ref, evtchn, be->blkif->blk_protocol, protocol,
+ pers_grants ? "persistent grants" : "");
+ /* Map the shared frame, irq etc. */
+ err = xen_blkif_map(&be->blkif->rings[i], ring_ref, evtchn);
+ if (err) {
+ xenbus_dev_fatal(dev, err, "mapping ring-ref %lu port %u",
+ ring_ref, evtchn);
+ kfree(xspath);
+ goto out;
+ }
+ }
+ kfree(xspath);
+ }
return 0;
+out:
+ return err;
}

static const struct xenbus_device_id xen_blkbk_ids[] = {
--
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: Bob Liu: "[PATCH 08/10] xen/blkfront: negotiate hardware queue number with backend"
Previous message: Bob Liu: "[PATCH 10/10] xen/blkfront: use work queue to fast blkif interrupt return"
In reply to: Bob Liu: "[PATCH 10/10] xen/blkfront: use work queue to fast blkif interrupt return"
Next in thread: Bob Liu: "[PATCH 08/10] xen/blkfront: negotiate hardware queue number with backend"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]