[PATCH RFC 3/4] xen, blkfront: introduce support for multiple hw queues

From: Arianna Avanzini
Date: Fri Aug 22 2014 - 07:19:37 EST

This commit introduces in xen-blkfront actual support for multiple
hardware queues. The number of available hardware queues is gathered
from the backend via XenStore; in case the expected XenStore key
is not available, the frontend defaults to a single I/O ring.

Signed-off-by: Arianna Avanzini <avanzini.arianna@xxxxxxxxx>
---
drivers/block/xen-blkfront.c | 793 +++++++++++++++++++++++++------------------
1 file changed, 463 insertions(+), 330 deletions(-)

diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index a047346..e27aaa1 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -99,10 +99,27 @@ static unsigned int xen_blkif_max_segments = 32;
module_param_named(max, xen_blkif_max_segments, int, S_IRUGO);
MODULE_PARM_DESC(max, "Maximum amount of segments in indirect requests (default is 32)");

-static unsigned int hardware_queues = 1;
-
#define BLK_RING_SIZE __CONST_RING_SIZE(blkif, PAGE_SIZE)

+struct blkfront_ring_info
+{
+ spinlock_t io_lock;
+ int ring_ref;
+ struct blkif_front_ring ring;
+ unsigned int evtchn, irq;
+ struct blk_shadow shadow[BLK_RING_SIZE];
+ unsigned long shadow_free;
+
+ struct work_struct work;
+ struct gnttab_free_callback callback;
+ struct list_head grants;
+ struct list_head indirect_pages;
+ unsigned int persistent_gnts_c;
+
+ struct blkfront_info *info;
+ unsigned int hctx_index;
+};
+
/*
* We have one of these per vbd, whether ide, scsi or 'other'. They
* hang in private_data off the gendisk structure. We may end up
@@ -110,24 +127,15 @@ static unsigned int hardware_queues = 1;
*/
struct blkfront_info
{
- spinlock_t io_lock;
struct mutex mutex;
struct xenbus_device *xbdev;
struct gendisk *gd;
int vdevice;
blkif_vdev_t handle;
enum blkif_state connected;
- int ring_ref;
- struct blkif_front_ring ring;
- unsigned int evtchn, irq;
+ unsigned int nr_rings;
+ struct blkfront_ring_info *rinfo;
struct request_queue *rq;
- struct work_struct work;
- struct gnttab_free_callback callback;
- struct blk_shadow shadow[BLK_RING_SIZE];
- struct list_head grants;
- struct list_head indirect_pages;
- unsigned int persistent_gnts_c;
- unsigned long shadow_free;
unsigned int feature_flush;
unsigned int flush_op;
unsigned int feature_discard:1;
@@ -135,6 +143,7 @@ struct blkfront_info
unsigned int discard_granularity;
unsigned int discard_alignment;
unsigned int feature_persistent:1;
+ unsigned int hardware_queues;
unsigned int max_indirect_segments;
int is_ready;
/* Block layer tags. */
@@ -171,32 +180,35 @@ static DEFINE_SPINLOCK(minor_lock);
#define INDIRECT_GREFS(_segs) \
((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)

-static int blkfront_setup_indirect(struct blkfront_info *info);
+static int blkfront_gather_indirect(struct blkfront_info *info);
+static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo,
+ unsigned int segs);

-static int get_id_from_freelist(struct blkfront_info *info)
+static int get_id_from_freelist(struct blkfront_ring_info *rinfo)
{
- unsigned long free = info->shadow_free;
+ unsigned long free = rinfo->shadow_free;
BUG_ON(free >= BLK_RING_SIZE);
- info->shadow_free = info->shadow[free].req.u.rw.id;
- info->shadow[free].req.u.rw.id = 0x0fffffee; /* debug */
+ rinfo->shadow_free = rinfo->shadow[free].req.u.rw.id;
+ rinfo->shadow[free].req.u.rw.id = 0x0fffffee; /* debug */
return free;
}

-static int add_id_to_freelist(struct blkfront_info *info,
+static int add_id_to_freelist(struct blkfront_ring_info *rinfo,
unsigned long id)
{
- if (info->shadow[id].req.u.rw.id != id)
+ if (rinfo->shadow[id].req.u.rw.id != id)
return -EINVAL;
- if (info->shadow[id].request == NULL)
+ if (rinfo->shadow[id].request == NULL)
return -EINVAL;
- info->shadow[id].req.u.rw.id = info->shadow_free;
- info->shadow[id].request = NULL;
- info->shadow_free = id;
+ rinfo->shadow[id].req.u.rw.id = rinfo->shadow_free;
+ rinfo->shadow[id].request = NULL;
+ rinfo->shadow_free = id;
return 0;
}

-static int fill_grant_buffer(struct blkfront_info *info, int num)
+static int fill_grant_buffer(struct blkfront_ring_info *rinfo, int num)
{
+ struct blkfront_info *info = rinfo->info;
struct page *granted_page;
struct grant *gnt_list_entry, *n;
int i = 0;
@@ -216,7 +228,7 @@ static int fill_grant_buffer(struct blkfront_info *info, int num)
}

gnt_list_entry->gref = GRANT_INVALID_REF;
- list_add(&gnt_list_entry->node, &info->grants);
+ list_add(&gnt_list_entry->node, &rinfo->grants);
i++;
}

@@ -224,7 +236,7 @@ static int fill_grant_buffer(struct blkfront_info *info, int num)

out_of_memory:
list_for_each_entry_safe(gnt_list_entry, n,
- &info->grants, node) {
+ &rinfo->grants, node) {
list_del(&gnt_list_entry->node);
if (info->feature_persistent)
__free_page(pfn_to_page(gnt_list_entry->pfn));
@@ -237,31 +249,31 @@ out_of_memory:

static struct grant *get_grant(grant_ref_t *gref_head,
unsigned long pfn,
- struct blkfront_info *info)
+ struct blkfront_ring_info *rinfo)
{
struct grant *gnt_list_entry;
unsigned long buffer_mfn;

- BUG_ON(list_empty(&info->grants));
- gnt_list_entry = list_first_entry(&info->grants, struct grant,
+ BUG_ON(list_empty(&rinfo->grants));
+ gnt_list_entry = list_first_entry(&rinfo->grants, struct grant,
node);
list_del(&gnt_list_entry->node);

if (gnt_list_entry->gref != GRANT_INVALID_REF) {
- info->persistent_gnts_c--;
+ rinfo->persistent_gnts_c--;
return gnt_list_entry;
}

/* Assign a gref to this page */
gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
BUG_ON(gnt_list_entry->gref == -ENOSPC);
- if (!info->feature_persistent) {
+ if (!rinfo->info->feature_persistent) {
BUG_ON(!pfn);
gnt_list_entry->pfn = pfn;
}
buffer_mfn = pfn_to_mfn(gnt_list_entry->pfn);
gnttab_grant_foreign_access_ref(gnt_list_entry->gref,
- info->xbdev->otherend_id,
+ rinfo->info->xbdev->otherend_id,
buffer_mfn, 0);
return gnt_list_entry;
}
@@ -332,8 +344,8 @@ static void xlbd_release_minors(unsigned int minor, unsigned int nr)

static void blkif_restart_queue_callback(void *arg)
{
- struct blkfront_info *info = (struct blkfront_info *)arg;
- schedule_work(&info->work);
+ struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)arg;
+ schedule_work(&rinfo->work);
}

static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg)
@@ -392,9 +404,11 @@ static int blkif_ioctl(struct block_device *bdev, fmode_t mode,
* @req: a request struct
* @ring_idx: index of the ring the request is to be inserted in
*/
-static int blkif_queue_request(struct request *req)
+static int blkif_queue_request(struct request *req, unsigned int ring_idx)
{
struct blkfront_info *info = req->rq_disk->private_data;
+ struct blkfront_ring_info *rinfo = &info->rinfo[ring_idx];
+ struct blkif_front_ring *ring = &info->rinfo[ring_idx].ring;
struct blkif_request *ring_req;
unsigned long id;
unsigned int fsect, lsect;
@@ -424,15 +438,15 @@ static int blkif_queue_request(struct request *req)
max_grefs += INDIRECT_GREFS(req->nr_phys_segments);

/* Check if we have enough grants to allocate a requests */
- if (info->persistent_gnts_c < max_grefs) {
+ if (rinfo->persistent_gnts_c < max_grefs) {
new_persistent_gnts = 1;
if (gnttab_alloc_grant_references(
- max_grefs - info->persistent_gnts_c,
+ max_grefs - rinfo->persistent_gnts_c,
&gref_head) < 0) {
gnttab_request_free_callback(
- &info->callback,
+ &rinfo->callback,
blkif_restart_queue_callback,
- info,
+ rinfo,
max_grefs);
return 1;
}
@@ -440,9 +454,9 @@ static int blkif_queue_request(struct request *req)
new_persistent_gnts = 0;

/* Fill out a communications ring structure. */
- ring_req = RING_GET_REQUEST(&info->ring, info->ring.req_prod_pvt);
- id = get_id_from_freelist(info);
- info->shadow[id].request = req;
+ ring_req = RING_GET_REQUEST(ring, ring->req_prod_pvt);
+ id = get_id_from_freelist(rinfo);
+ rinfo->shadow[id].request = req;

if (unlikely(req->cmd_flags & (REQ_DISCARD | REQ_SECURE))) {
ring_req->operation = BLKIF_OP_DISCARD;
@@ -458,7 +472,7 @@ static int blkif_queue_request(struct request *req)
req->nr_phys_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST);
BUG_ON(info->max_indirect_segments &&
req->nr_phys_segments > info->max_indirect_segments);
- nseg = blk_rq_map_sg(req->q, req, info->shadow[id].sg);
+ nseg = blk_rq_map_sg(req->q, req, rinfo->shadow[id].sg);
ring_req->u.rw.id = id;
if (nseg > BLKIF_MAX_SEGMENTS_PER_REQUEST) {
/*
@@ -489,7 +503,7 @@ static int blkif_queue_request(struct request *req)
}
ring_req->u.rw.nr_segments = nseg;
}
- for_each_sg(info->shadow[id].sg, sg, nseg, i) {
+ for_each_sg(rinfo->shadow[id].sg, sg, nseg, i) {
fsect = sg->offset >> 9;
lsect = fsect + (sg->length >> 9) - 1;

@@ -505,22 +519,22 @@ static int blkif_queue_request(struct request *req)
struct page *indirect_page;

/* Fetch a pre-allocated page to use for indirect grefs */
- BUG_ON(list_empty(&info->indirect_pages));
- indirect_page = list_first_entry(&info->indirect_pages,
+ BUG_ON(list_empty(&rinfo->indirect_pages));
+ indirect_page = list_first_entry(&rinfo->indirect_pages,
struct page, lru);
list_del(&indirect_page->lru);
pfn = page_to_pfn(indirect_page);
}
- gnt_list_entry = get_grant(&gref_head, pfn, info);
- info->shadow[id].indirect_grants[n] = gnt_list_entry;
+ gnt_list_entry = get_grant(&gref_head, pfn, rinfo);
+ rinfo->shadow[id].indirect_grants[n] = gnt_list_entry;
segments = kmap_atomic(pfn_to_page(gnt_list_entry->pfn));
ring_req->u.indirect.indirect_grefs[n] = gnt_list_entry->gref;
}

- gnt_list_entry = get_grant(&gref_head, page_to_pfn(sg_page(sg)), info);
+ gnt_list_entry = get_grant(&gref_head, page_to_pfn(sg_page(sg)), rinfo);
ref = gnt_list_entry->gref;

- info->shadow[id].grants_used[i] = gnt_list_entry;
+ rinfo->shadow[id].grants_used[i] = gnt_list_entry;

if (rq_data_dir(req) && info->feature_persistent) {
char *bvec_data;
@@ -566,10 +580,10 @@ static int blkif_queue_request(struct request *req)
kunmap_atomic(segments);
}

- info->ring.req_prod_pvt++;
+ ring->req_prod_pvt++;

/* Keep a private copy so we can reissue requests when recovering. */
- info->shadow[id].req = *ring_req;
+ rinfo->shadow[id].req = *ring_req;

if (new_persistent_gnts)
gnttab_free_grant_references(gref_head);
@@ -578,14 +592,16 @@ static int blkif_queue_request(struct request *req)
}


-static inline void flush_requests(struct blkfront_info *info)
+static inline void flush_requests(struct blkfront_info *info,
+ unsigned int ring_idx)
{
+ struct blkfront_ring_info *rinfo = &info->rinfo[ring_idx];
int notify;

- RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&info->ring, notify);
+ RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&rinfo->ring, notify);

if (notify)
- notify_remote_via_irq(info->irq);
+ notify_remote_via_irq(rinfo->irq);
}

static inline bool blkif_request_flush_mismatch(struct request *req,
@@ -612,8 +628,9 @@ static void do_blkif_request(struct request_queue *rq)

while ((req = blk_peek_request(rq)) != NULL) {
info = req->rq_disk->private_data;
+ BUG_ON(info->nr_rings != 1);

- if (RING_FULL(&info->ring))
+ if (RING_FULL(&info->rinfo[0].ring))
goto wait;

blk_start_request(req);
@@ -629,7 +646,7 @@ static void do_blkif_request(struct request_queue *rq)
blk_rq_cur_sectors(req), blk_rq_sectors(req),
rq_data_dir(req) ? "write" : "read");

- if (blkif_queue_request(req)) {
+ if (blkif_queue_request(req, 0)) {
blk_requeue_request(rq, req);
wait:
/* Avoid pointless unplugs. */
@@ -641,23 +658,25 @@ wait:
}

if (queued != 0)
- flush_requests(info);
+ flush_requests(info, 0);
}

static int blkfront_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
{
- struct blkfront_info *info = req->rq_disk->private_data;
+ struct blkfront_ring_info *rinfo =
+ (struct blkfront_ring_info *)hctx->driver_data;
+ struct blkfront_info *info = rinfo->info;

pr_debug("Entered blkfront_queue_rq\n");

- spin_lock_irq(&info->io_lock);
- if (RING_FULL(&info->ring))
+ spin_lock_irq(&rinfo->io_lock);
+ if (RING_FULL(&rinfo->ring))
goto wait;

if (blkif_request_flush_mismatch(req, info)) {
req->errors = -EIO;
blk_mq_complete_request(req);
- spin_unlock_irq(&info->io_lock);
+ spin_unlock_irq(&rinfo->io_lock);
return BLK_MQ_RQ_QUEUE_ERROR;
}

@@ -666,22 +685,27 @@ static int blkfront_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
blk_rq_cur_sectors(req), blk_rq_sectors(req),
rq_data_dir(req) ? "write" : "read");

- if (blkif_queue_request(req)) {
+ if (blkif_queue_request(req, rinfo->hctx_index)) {
wait:
/* Avoid pointless unplugs. */
blk_mq_stop_hw_queue(hctx);
- spin_unlock_irq(&info->io_lock);
+ spin_unlock_irq(&rinfo->io_lock);
return BLK_MQ_RQ_QUEUE_BUSY;
}

- flush_requests(info);
- spin_unlock_irq(&info->io_lock);
+ flush_requests(info, rinfo->hctx_index);
+ spin_unlock_irq(&rinfo->io_lock);
return BLK_MQ_RQ_QUEUE_OK;
}

static int blkfront_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
unsigned int index)
{
+ struct blkfront_info *info = (struct blkfront_info *)data;
+
+ hctx->driver_data = &info->rinfo[index];
+ info->rinfo[index].hctx_index = index;
+
return 0;
}

@@ -704,10 +728,10 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
struct request_queue *rq;
struct blkfront_info *info = gd->private_data;

- if (hardware_queues) {
+ if (info->hardware_queues) {
memset(&info->tag_set, 0, sizeof(info->tag_set));
info->tag_set.ops = &blkfront_mq_ops;
- info->tag_set.nr_hw_queues = hardware_queues;
+ info->tag_set.nr_hw_queues = info->hardware_queues;
info->tag_set.queue_depth = BLK_RING_SIZE;
info->tag_set.numa_node = NUMA_NO_NODE;
info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
@@ -722,7 +746,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
return -1;
}
} else {
- rq = blk_init_queue(do_blkif_request, &info->io_lock);
+ rq = blk_init_queue(do_blkif_request, &info->rinfo[0].io_lock);
if (rq == NULL)
return -1;
}
@@ -945,28 +969,40 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
return err;
}

+void blk_mq_free_queue(struct request_queue *q);
+
static void xlvbd_release_gendisk(struct blkfront_info *info)
{
unsigned int minor, nr_minors;
- unsigned long flags;
+ unsigned long *flags;
+ int i;

if (info->rq == NULL)
return;

- spin_lock_irqsave(&info->io_lock, flags);
+ flags = kzalloc(sizeof(unsigned long) * info->nr_rings,
+ GFP_KERNEL);
+ if (!flags)
+ return;

- /* No more blkif_request(). */
- if (hardware_queues)
+ /* No more blkif_request() and no more gnttab callback work. */
+ if (info->hardware_queues) {
blk_mq_stop_hw_queues(info->rq);
- else
+ for (i = 0 ; i < info->nr_rings ; i++) {
+ spin_lock_irqsave(&info->rinfo[i].io_lock, flags[i]);
+ gnttab_cancel_free_callback(&info->rinfo[i].callback);
+ spin_unlock_irqrestore(&info->rinfo[i].io_lock, flags[i]);
+ }
+ } else {
+ spin_lock_irqsave(&info->rinfo[0].io_lock, flags[0]);
blk_stop_queue(info->rq);
-
- /* No more gnttab callback work. */
- gnttab_cancel_free_callback(&info->callback);
- spin_unlock_irqrestore(&info->io_lock, flags);
+ gnttab_cancel_free_callback(&info->rinfo[0].callback);
+ spin_unlock_irqrestore(&info->rinfo[0].io_lock, flags[0]);
+ }

/* Flush gnttab callback work. Must be done with no locks held. */
- flush_work(&info->work);
+ for (i = 0 ; i < info->nr_rings ; i++)
+ flush_work(&info->rinfo[i].work);

del_gendisk(info->gd);

@@ -982,12 +1018,13 @@ static void xlvbd_release_gendisk(struct blkfront_info *info)
info->gd = NULL;
}

-static void kick_pending_request_queues(struct blkfront_info *info)
+static void kick_pending_request_queues(struct blkfront_ring_info *rinfo)
{
- if (!RING_FULL(&info->ring)) {
- if (hardware_queues) {
+ if (!RING_FULL(&rinfo->ring)) {
+ struct blkfront_info *info = rinfo->info;
+ if (info->hardware_queues)
blk_mq_start_stopped_hw_queues(info->rq, 0);
- } else {
+ else {
/* Re-enable calldowns. */
blk_start_queue(info->rq);
/* Kick things off immediately. */
@@ -998,83 +1035,42 @@ static void kick_pending_request_queues(struct blkfront_info *info)

static void blkif_restart_queue(struct work_struct *work)
{
- struct blkfront_info *info = container_of(work, struct blkfront_info, work);
+ struct blkfront_ring_info *rinfo = container_of(work,
+ struct blkfront_ring_info, work);
+ struct blkfront_info *info = rinfo->info;

- spin_lock_irq(&info->io_lock);
+ spin_lock_irq(&rinfo->io_lock);
if (info->connected == BLKIF_STATE_CONNECTED)
- kick_pending_request_queues(info);
- spin_unlock_irq(&info->io_lock);
+ kick_pending_request_queues(rinfo);
+ spin_unlock_irq(&rinfo->io_lock);
}

-static void blkif_free(struct blkfront_info *info, int suspend)
+static void blkif_free_ring(struct blkfront_ring_info *rinfo,
+ int persistent)
{
struct grant *persistent_gnt;
- struct grant *n;
int i, j, segs;

- /* Prevent new requests being issued until we fix things up. */
- spin_lock_irq(&info->io_lock);
- info->connected = suspend ?
- BLKIF_STATE_SUSPENDED : BLKIF_STATE_DISCONNECTED;
- /* No more blkif_request(). */
- if (info->rq) {
- if (hardware_queues)
- blk_mq_stop_hw_queues(info->rq);
- else
- blk_stop_queue(info->rq);
- }
-
- /* Remove all persistent grants */
- if (!list_empty(&info->grants)) {
- list_for_each_entry_safe(persistent_gnt, n,
- &info->grants, node) {
- list_del(&persistent_gnt->node);
- if (persistent_gnt->gref != GRANT_INVALID_REF) {
- gnttab_end_foreign_access(persistent_gnt->gref,
- 0, 0UL);
- info->persistent_gnts_c--;
- }
- if (info->feature_persistent)
- __free_page(pfn_to_page(persistent_gnt->pfn));
- kfree(persistent_gnt);
- }
- }
- BUG_ON(info->persistent_gnts_c != 0);
-
- /*
- * Remove indirect pages, this only happens when using indirect
- * descriptors but not persistent grants
- */
- if (!list_empty(&info->indirect_pages)) {
- struct page *indirect_page, *n;
-
- BUG_ON(info->feature_persistent);
- list_for_each_entry_safe(indirect_page, n, &info->indirect_pages, lru) {
- list_del(&indirect_page->lru);
- __free_page(indirect_page);
- }
- }
-
for (i = 0; i < BLK_RING_SIZE; i++) {
/*
* Clear persistent grants present in requests already
* on the shared ring
*/
- if (!info->shadow[i].request)
+ if (!rinfo->shadow[i].request)
goto free_shadow;

- segs = info->shadow[i].req.operation == BLKIF_OP_INDIRECT ?
- info->shadow[i].req.u.indirect.nr_segments :
- info->shadow[i].req.u.rw.nr_segments;
+ segs = rinfo->shadow[i].req.operation == BLKIF_OP_INDIRECT ?
+ rinfo->shadow[i].req.u.indirect.nr_segments :
+ rinfo->shadow[i].req.u.rw.nr_segments;
for (j = 0; j < segs; j++) {
- persistent_gnt = info->shadow[i].grants_used[j];
+ persistent_gnt = rinfo->shadow[i].grants_used[j];
gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
- if (info->feature_persistent)
+ if (persistent)
__free_page(pfn_to_page(persistent_gnt->pfn));
kfree(persistent_gnt);
}

- if (info->shadow[i].req.operation != BLKIF_OP_INDIRECT)
+ if (rinfo->shadow[i].req.operation != BLKIF_OP_INDIRECT)
/*
* If this is not an indirect operation don't try to
* free indirect segments
@@ -1082,44 +1078,105 @@ static void blkif_free(struct blkfront_info *info, int suspend)
goto free_shadow;

for (j = 0; j < INDIRECT_GREFS(segs); j++) {
- persistent_gnt = info->shadow[i].indirect_grants[j];
+ persistent_gnt = rinfo->shadow[i].indirect_grants[j];
gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
__free_page(pfn_to_page(persistent_gnt->pfn));
kfree(persistent_gnt);
}

free_shadow:
- kfree(info->shadow[i].grants_used);
- info->shadow[i].grants_used = NULL;
- kfree(info->shadow[i].indirect_grants);
- info->shadow[i].indirect_grants = NULL;
- kfree(info->shadow[i].sg);
- info->shadow[i].sg = NULL;
+ kfree(rinfo->shadow[i].grants_used);
+ rinfo->shadow[i].grants_used = NULL;
+ kfree(rinfo->shadow[i].indirect_grants);
+ rinfo->shadow[i].indirect_grants = NULL;
+ kfree(rinfo->shadow[i].sg);
+ rinfo->shadow[i].sg = NULL;
}

- /* No more gnttab callback work. */
- gnttab_cancel_free_callback(&info->callback);
- spin_unlock_irq(&info->io_lock);
+ /* Free resources associated with old device channel. */
+ if (rinfo->ring_ref != GRANT_INVALID_REF) {
+ gnttab_end_foreign_access(rinfo->ring_ref, 0,
+ (unsigned long)rinfo->ring.sring);
+ rinfo->ring_ref = GRANT_INVALID_REF;
+ rinfo->ring.sring = NULL;
+ }
+ if (rinfo->irq)
+ unbind_from_irqhandler(rinfo->irq, rinfo);
+ rinfo->evtchn = rinfo->irq = 0;

- /* Flush gnttab callback work. Must be done with no locks held. */
- flush_work(&info->work);
+}

- /* Free resources associated with old device channel. */
- if (info->ring_ref != GRANT_INVALID_REF) {
- gnttab_end_foreign_access(info->ring_ref, 0,
- (unsigned long)info->ring.sring);
- info->ring_ref = GRANT_INVALID_REF;
- info->ring.sring = NULL;
+static void blkif_free(struct blkfront_info *info, int suspend)
+{
+ struct grant *persistent_gnt;
+ struct grant *n;
+ int i;
+
+ info->connected = suspend ?
+ BLKIF_STATE_SUSPENDED : BLKIF_STATE_DISCONNECTED;
+
+ /* Prevent new requests being issued until we fix things up. */
+ /* No more blkif_request() and no more gnttab callback work. */
+ if (!info->hardware_queues && info->rq) {
+ spin_lock_irq(&info->rinfo[0].io_lock);
+ blk_stop_queue(info->rq);
+ gnttab_cancel_free_callback(&info->rinfo[0].callback);
+ spin_unlock_irq(&info->rinfo[0].io_lock);
+ } else {
+ blk_mq_stop_hw_queues(info->rq);
+
+ for (i = 0 ; i < info->nr_rings ; i++) {
+ struct blkfront_ring_info *rinfo = &info->rinfo[i];
+
+ spin_lock_irq(&info->rinfo[i].io_lock);
+ /* Remove all persistent grants */
+ if (!list_empty(&rinfo->grants)) {
+ list_for_each_entry_safe(persistent_gnt, n,
+ &rinfo->grants, node) {
+ list_del(&persistent_gnt->node);
+ if (persistent_gnt->gref != GRANT_INVALID_REF) {
+ gnttab_end_foreign_access(persistent_gnt->gref,
+ 0, 0UL);
+ rinfo->persistent_gnts_c--;
+ }
+ if (info->feature_persistent)
+ __free_page(pfn_to_page(persistent_gnt->pfn));
+ kfree(persistent_gnt);
+ }
+ }
+ BUG_ON(rinfo->persistent_gnts_c != 0);
+
+ /*
+ * Remove indirect pages, this only happens when using indirect
+ * descriptors but not persistent grants
+ */
+ if (!list_empty(&rinfo->indirect_pages)) {
+ struct page *indirect_page, *n;
+
+ BUG_ON(info->feature_persistent);
+ list_for_each_entry_safe(indirect_page, n, &rinfo->indirect_pages, lru) {
+ list_del(&indirect_page->lru);
+ __free_page(indirect_page);
+ }
+ }
+
+ blkif_free_ring(&info->rinfo[i], info->feature_persistent);
+ }
+
+ gnttab_cancel_free_callback(&info->rinfo[i].callback);
+ spin_unlock_irq(&info->rinfo[i].io_lock);
}
- if (info->irq)
- unbind_from_irqhandler(info->irq, info);
- info->evtchn = info->irq = 0;

+ /* Flush gnttab callback work. Must be done with no locks held. */
+ for (i = 0 ; i < info->nr_rings ; i++)
+ flush_work(&info->rinfo[i].work);
}

-static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
+static void blkif_completion(struct blk_shadow *s,
+ struct blkfront_ring_info *rinfo,
struct blkif_response *bret)
{
+ struct blkfront_info *info = rinfo->info;
int i = 0;
struct scatterlist *sg;
char *bvec_data;
@@ -1160,8 +1217,8 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
if (!info->feature_persistent)
pr_alert_ratelimited("backed has not unmapped grant: %u\n",
s->grants_used[i]->gref);
- list_add(&s->grants_used[i]->node, &info->grants);
- info->persistent_gnts_c++;
+ list_add(&s->grants_used[i]->node, &rinfo->grants);
+ rinfo->persistent_gnts_c++;
} else {
/*
* If the grant is not mapped by the backend we end the
@@ -1171,7 +1228,7 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
*/
gnttab_end_foreign_access(s->grants_used[i]->gref, 0, 0UL);
s->grants_used[i]->gref = GRANT_INVALID_REF;
- list_add_tail(&s->grants_used[i]->node, &info->grants);
+ list_add_tail(&s->grants_used[i]->node, &rinfo->grants);
}
}
if (s->req.operation == BLKIF_OP_INDIRECT) {
@@ -1180,8 +1237,8 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
if (!info->feature_persistent)
pr_alert_ratelimited("backed has not unmapped grant: %u\n",
s->indirect_grants[i]->gref);
- list_add(&s->indirect_grants[i]->node, &info->grants);
- info->persistent_gnts_c++;
+ list_add(&s->indirect_grants[i]->node, &rinfo->grants);
+ rinfo->persistent_gnts_c++;
} else {
struct page *indirect_page;

@@ -1191,9 +1248,9 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
* available pages for indirect grefs.
*/
indirect_page = pfn_to_page(s->indirect_grants[i]->pfn);
- list_add(&indirect_page->lru, &info->indirect_pages);
+ list_add(&indirect_page->lru, &rinfo->indirect_pages);
s->indirect_grants[i]->gref = GRANT_INVALID_REF;
- list_add_tail(&s->indirect_grants[i]->node, &info->grants);
+ list_add_tail(&s->indirect_grants[i]->node, &rinfo->grants);
}
}
}
@@ -1205,24 +1262,25 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
struct blkif_response *bret;
RING_IDX i, rp;
unsigned long flags;
- struct blkfront_info *info = (struct blkfront_info *)dev_id;
+ struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)dev_id;
+ struct blkfront_info *info = rinfo->info;
int error;

- spin_lock_irqsave(&info->io_lock, flags);
+ spin_lock_irqsave(&rinfo->io_lock, flags);

if (unlikely(info->connected != BLKIF_STATE_CONNECTED)) {
- spin_unlock_irqrestore(&info->io_lock, flags);
+ spin_unlock_irqrestore(&rinfo->io_lock, flags);
return IRQ_HANDLED;
}

again:
- rp = info->ring.sring->rsp_prod;
+ rp = rinfo->ring.sring->rsp_prod;
rmb(); /* Ensure we see queued responses up to 'rp'. */

- for (i = info->ring.rsp_cons; i != rp; i++) {
+ for (i = rinfo->ring.rsp_cons; i != rp; i++) {
unsigned long id;

- bret = RING_GET_RESPONSE(&info->ring, i);
+ bret = RING_GET_RESPONSE(&rinfo->ring, i);
id = bret->id;
/*
* The backend has messed up and given us an id that we would
@@ -1236,12 +1294,12 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
* the id is busted. */
continue;
}
- req = info->shadow[id].request;
+ req = rinfo->shadow[id].request;

if (bret->operation != BLKIF_OP_DISCARD)
- blkif_completion(&info->shadow[id], info, bret);
+ blkif_completion(&rinfo->shadow[id], rinfo, bret);

- if (add_id_to_freelist(info, id)) {
+ if (add_id_to_freelist(rinfo, id)) {
WARN(1, "%s: response to %s (id %ld) couldn't be recycled!\n",
info->gd->disk_name, op_name(bret->operation), id);
continue;
@@ -1260,7 +1318,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
queue_flag_clear(QUEUE_FLAG_SECDISCARD, rq);
}
- if (hardware_queues)
+ if (info->hardware_queues)
blk_mq_complete_request(req);
else
__blk_end_request_all(req, error);
@@ -1273,7 +1331,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
error = req->errors = -EOPNOTSUPP;
}
if (unlikely(bret->status == BLKIF_RSP_ERROR &&
- info->shadow[id].req.u.rw.nr_segments == 0)) {
+ rinfo->shadow[id].req.u.rw.nr_segments == 0)) {
printk(KERN_WARNING "blkfront: %s: empty %s op failed\n",
info->gd->disk_name, op_name(bret->operation));
error = req->errors = -EOPNOTSUPP;
@@ -1292,7 +1350,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
"request: %x\n", bret->status);

- if (hardware_queues)
+ if (info->hardware_queues)
blk_mq_complete_request(req);
else
__blk_end_request_all(req, error);
@@ -1302,31 +1360,31 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
}
}

- info->ring.rsp_cons = i;
+ rinfo->ring.rsp_cons = i;

- if (i != info->ring.req_prod_pvt) {
+ if (i != rinfo->ring.req_prod_pvt) {
int more_to_do;
- RING_FINAL_CHECK_FOR_RESPONSES(&info->ring, more_to_do);
+ RING_FINAL_CHECK_FOR_RESPONSES(&rinfo->ring, more_to_do);
if (more_to_do)
goto again;
} else
- info->ring.sring->rsp_event = i + 1;
+ rinfo->ring.sring->rsp_event = i + 1;

- kick_pending_request_queues(info);
+ kick_pending_request_queues(rinfo);

- spin_unlock_irqrestore(&info->io_lock, flags);
+ spin_unlock_irqrestore(&rinfo->io_lock, flags);

return IRQ_HANDLED;
}


static int setup_blkring(struct xenbus_device *dev,
- struct blkfront_info *info)
+ struct blkfront_ring_info *rinfo)
{
struct blkif_sring *sring;
int err;

- info->ring_ref = GRANT_INVALID_REF;
+ rinfo->ring_ref = GRANT_INVALID_REF;

sring = (struct blkif_sring *)__get_free_page(GFP_NOIO | __GFP_HIGH);
if (!sring) {
@@ -1334,32 +1392,32 @@ static int setup_blkring(struct xenbus_device *dev,
return -ENOMEM;
}
SHARED_RING_INIT(sring);
- FRONT_RING_INIT(&info->ring, sring, PAGE_SIZE);
+ FRONT_RING_INIT(&rinfo->ring, sring, PAGE_SIZE);

- err = xenbus_grant_ring(dev, virt_to_mfn(info->ring.sring));
+ err = xenbus_grant_ring(dev, virt_to_mfn(rinfo->ring.sring));
if (err < 0) {
free_page((unsigned long)sring);
- info->ring.sring = NULL;
+ rinfo->ring.sring = NULL;
goto fail;
}
- info->ring_ref = err;
+ rinfo->ring_ref = err;

- err = xenbus_alloc_evtchn(dev, &info->evtchn);
+ err = xenbus_alloc_evtchn(dev, &rinfo->evtchn);
if (err)
goto fail;

- err = bind_evtchn_to_irqhandler(info->evtchn, blkif_interrupt, 0,
- "blkif", info);
+ err = bind_evtchn_to_irqhandler(rinfo->evtchn, blkif_interrupt, 0,
+ "blkif", rinfo);
if (err <= 0) {
xenbus_dev_fatal(dev, err,
"bind_evtchn_to_irqhandler failed");
goto fail;
}
- info->irq = err;
+ rinfo->irq = err;

return 0;
fail:
- blkif_free(info, 0);
+ blkif_free(rinfo->info, 0);
return err;
}

@@ -1369,13 +1427,16 @@ static int talk_to_blkback(struct xenbus_device *dev,
struct blkfront_info *info)
{
const char *message = NULL;
+ char ring_ref_s[64] = "", evtchn_s[64] = "";
struct xenbus_transaction xbt;
- int err;
+ int i, err;

- /* Create shared ring, alloc event channel. */
- err = setup_blkring(dev, info);
- if (err)
- goto out;
+ for (i = 0 ; i < info->nr_rings ; i++) {
+ /* Create shared ring, alloc event channel. */
+ err = setup_blkring(dev, &info->rinfo[i]);
+ if (err)
+ goto out;
+ }

again:
err = xenbus_transaction_start(&xbt);
@@ -1384,18 +1445,30 @@ again:
goto destroy_blkring;
}

- err = xenbus_printf(xbt, dev->nodename,
- "ring-ref", "%u", info->ring_ref);
- if (err) {
- message = "writing ring-ref";
- goto abort_transaction;
- }
- err = xenbus_printf(xbt, dev->nodename,
- "event-channel", "%u", info->evtchn);
- if (err) {
- message = "writing event-channel";
- goto abort_transaction;
+ for (i = 0 ; i < info->nr_rings ; i++) {
+ if (!info->hardware_queues) {
+ BUG_ON(i > 0);
+ /* Support old XenStore keys */
+ snprintf(ring_ref_s, 64, "ring-ref");
+ snprintf(evtchn_s, 64, "event-channel");
+ } else {
+ snprintf(ring_ref_s, 64, "ring-ref-%d", i);
+ snprintf(evtchn_s, 64, "event-channel-%d", i);
+ }
+ err = xenbus_printf(xbt, dev->nodename,
+ ring_ref_s, "%u", info->rinfo[i].ring_ref);
+ if (err) {
+ message = "writing ring-ref";
+ goto abort_transaction;
+ }
+ err = xenbus_printf(xbt, dev->nodename,
+ evtchn_s, "%u", info->rinfo[i].evtchn);
+ if (err) {
+ message = "writing event-channel";
+ goto abort_transaction;
+ }
}
+
err = xenbus_printf(xbt, dev->nodename, "protocol", "%s",
XEN_IO_PROTO_ABI_NATIVE);
if (err) {
@@ -1439,8 +1512,9 @@ again:
static int blkfront_probe(struct xenbus_device *dev,
const struct xenbus_device_id *id)
{
- int err, vdevice, i;
+ int err, vdevice, i, r;
struct blkfront_info *info;
+ unsigned int nr_queues;

/* FIXME: Use dynamic device id if this is not set. */
err = xenbus_scanf(XBT_NIL, dev->nodename,
@@ -1491,23 +1565,47 @@ static int blkfront_probe(struct xenbus_device *dev,
}

mutex_init(&info->mutex);
- spin_lock_init(&info->io_lock);
info->xbdev = dev;
info->vdevice = vdevice;
- INIT_LIST_HEAD(&info->grants);
- INIT_LIST_HEAD(&info->indirect_pages);
- info->persistent_gnts_c = 0;
info->connected = BLKIF_STATE_DISCONNECTED;
- INIT_WORK(&info->work, blkif_restart_queue);
-
- for (i = 0; i < BLK_RING_SIZE; i++)
- info->shadow[i].req.u.rw.id = i+1;
- info->shadow[BLK_RING_SIZE-1].req.u.rw.id = 0x0fffffff;

/* Front end dir is a number, which is used as the id. */
info->handle = simple_strtoul(strrchr(dev->nodename, '/')+1, NULL, 0);
dev_set_drvdata(&dev->dev, info);

+ /* Gather the number of hardware queues as soon as possible */
+ err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "nr_supported_hw_queues", "%u", &nr_queues,
+ NULL);
+ if (err)
+ info->hardware_queues = 0;
+ else
+ info->hardware_queues = nr_queues;
+ /*
+ * The backend has told us the number of hw queues he wants.
+ * Allocate the correct number of rings.
+ */
+ info->nr_rings = info->hardware_queues ? : 1;
+ pr_info("blkfront: %d hardware queues, %d rings\n",
+ info->hardware_queues, info->nr_rings);
+
+ info->rinfo = kzalloc(info->nr_rings *
+ sizeof(struct blkfront_ring_info),
+ GFP_KERNEL);
+ for (r = 0 ; r < info->nr_rings ; r++) {
+ struct blkfront_ring_info *rinfo = &info->rinfo[r];
+
+ rinfo->info = info;
+ rinfo->persistent_gnts_c = 0;
+ INIT_LIST_HEAD(&rinfo->grants);
+ INIT_LIST_HEAD(&rinfo->indirect_pages);
+ INIT_WORK(&rinfo->work, blkif_restart_queue);
+ spin_lock_init(&rinfo->io_lock);
+ for (i = 0; i < BLK_RING_SIZE; i++)
+ rinfo->shadow[i].req.u.rw.id = i+1;
+ rinfo->shadow[BLK_RING_SIZE-1].req.u.rw.id = 0x0fffffff;
+ }
+
err = talk_to_blkback(dev, info);
if (err) {
kfree(info);
@@ -1533,107 +1631,126 @@ static void split_bio_end(struct bio *bio, int error)
bio_put(bio);
}

-static int blkif_recover(struct blkfront_info *info)
+static int blkif_setup_shadow(struct blkfront_ring_info *rinfo,
+ struct blk_shadow **copy)
{
int i;
+
+ /* Stage 1: Make a safe copy of the shadow state. */
+ *copy = kmemdup(rinfo->shadow, sizeof(rinfo->shadow),
+ GFP_NOIO | __GFP_REPEAT | __GFP_HIGH);
+ if (!*copy)
+ return -ENOMEM;
+
+ /* Stage 2: Set up free list. */
+ memset(&rinfo->shadow, 0, sizeof(rinfo->shadow));
+ for (i = 0; i < BLK_RING_SIZE; i++)
+ rinfo->shadow[i].req.u.rw.id = i+1;
+ rinfo->shadow_free = rinfo->ring.req_prod_pvt;
+ rinfo->shadow[BLK_RING_SIZE-1].req.u.rw.id = 0x0fffffff;
+
+ return 0;
+}
+
+static int blkif_recover(struct blkfront_info *info)
+{
+ int i, r;
struct request *req, *n;
struct blk_shadow *copy;
- int rc;
+ int rc = 0;
struct bio *bio, *cloned_bio;
- struct bio_list bio_list, merge_bio;
+ struct bio_list uninitialized_var(bio_list), merge_bio;
unsigned int segs, offset;
int pending, size;
struct split_bio *split_bio;
struct list_head requests;

- /* Stage 1: Make a safe copy of the shadow state. */
- copy = kmemdup(info->shadow, sizeof(info->shadow),
- GFP_NOIO | __GFP_REPEAT | __GFP_HIGH);
- if (!copy)
- return -ENOMEM;
+ segs = blkfront_gather_indirect(info);

- /* Stage 2: Set up free list. */
- memset(&info->shadow, 0, sizeof(info->shadow));
- for (i = 0; i < BLK_RING_SIZE; i++)
- info->shadow[i].req.u.rw.id = i+1;
- info->shadow_free = info->ring.req_prod_pvt;
- info->shadow[BLK_RING_SIZE-1].req.u.rw.id = 0x0fffffff;
+ for (r = 0 ; r < info->nr_rings ; i++) {
+ rc |= blkif_setup_shadow(&info->rinfo[i], &copy);

- rc = blkfront_setup_indirect(info);
- if (rc) {
- kfree(copy);
- return rc;
- }
+ rc |= blkfront_setup_indirect(&info->rinfo[i], segs);
+ if (rc) {
+ kfree(copy);
+ return rc;
+ }

- segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
- blk_queue_max_segments(info->rq, segs);
- bio_list_init(&bio_list);
- INIT_LIST_HEAD(&requests);
- for (i = 0; i < BLK_RING_SIZE; i++) {
- /* Not in use? */
- if (!copy[i].request)
- continue;
+ segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
+ blk_queue_max_segments(info->rq, segs);
+ bio_list_init(&bio_list);
+ INIT_LIST_HEAD(&requests);
+ for (i = 0; i < BLK_RING_SIZE; i++) {
+ /* Not in use? */
+ if (!copy[i].request)
+ continue;

- /*
- * Get the bios in the request so we can re-queue them.
- */
- if (copy[i].request->cmd_flags &
- (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
/*
- * Flush operations don't contain bios, so
- * we need to requeue the whole request
+ * Get the bios in the request so we can re-queue them.
*/
- list_add(&copy[i].request->queuelist, &requests);
- continue;
+ if (copy[i].request->cmd_flags &
+ (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
+ /*
+ * Flush operations don't contain bios, so
+ * we need to requeue the whole request
+ */
+ list_add(&copy[i].request->queuelist, &requests);
+ continue;
+ }
+ merge_bio.head = copy[i].request->bio;
+ merge_bio.tail = copy[i].request->biotail;
+ bio_list_merge(&bio_list, &merge_bio);
+ copy[i].request->bio = NULL;
+ blk_put_request(copy[i].request);
}
- merge_bio.head = copy[i].request->bio;
- merge_bio.tail = copy[i].request->biotail;
- bio_list_merge(&bio_list, &merge_bio);
- copy[i].request->bio = NULL;
- blk_put_request(copy[i].request);
- }

- kfree(copy);
+ kfree(copy);
+ }

/*
- * Empty the queue, this is important because we might have
- * requests in the queue with more segments than what we
- * can handle now.
+ * If we are using the request interface, empty the queue,
+ * this is important because we might have requests in the
+ * queue with more segments than what we can handle now.
*/
- spin_lock_irq(&info->io_lock);
- while ((req = blk_fetch_request(info->rq)) != NULL) {
- if (req->cmd_flags &
- (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
- list_add(&req->queuelist, &requests);
- continue;
+ if (!info->hardware_queues) {
+ spin_lock_irq(&info->rinfo[0].io_lock);
+ while ((req = blk_fetch_request(info->rq)) != NULL) {
+ if (req->cmd_flags &
+ (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
+ list_add(&req->queuelist, &requests);
+ continue;
+ }
+ merge_bio.head = req->bio;
+ merge_bio.tail = req->biotail;
+ bio_list_merge(&bio_list, &merge_bio);
+ req->bio = NULL;
+ if (req->cmd_flags & (REQ_FLUSH | REQ_FUA))
+ pr_alert("diskcache flush request found!\n");
+ __blk_put_request(info->rq, req);
}
- merge_bio.head = req->bio;
- merge_bio.tail = req->biotail;
- bio_list_merge(&bio_list, &merge_bio);
- req->bio = NULL;
- if (req->cmd_flags & (REQ_FLUSH | REQ_FUA))
- pr_alert("diskcache flush request found!\n");
- __blk_put_request(info->rq, req);
+ spin_unlock_irq(&info->rinfo[0].io_lock);
}
- spin_unlock_irq(&info->io_lock);

xenbus_switch_state(info->xbdev, XenbusStateConnected);

- spin_lock_irq(&info->io_lock);
-
/* Now safe for us to use the shared ring */
info->connected = BLKIF_STATE_CONNECTED;

- /* Kick any other new requests queued since we resumed */
- kick_pending_request_queues(info);
+ for (i = 0 ; i < info->nr_rings ; i++) {
+ spin_lock_irq(&info->rinfo[i].io_lock);
+
+ /* Kick any other new requests queued since we resumed */
+ kick_pending_request_queues(&info->rinfo[i]);
+
+ list_for_each_entry_safe(req, n, &requests, queuelist) {
+ /* Requeue pending requests (flush or discard) */
+ list_del_init(&req->queuelist);
+ BUG_ON(req->nr_phys_segments > segs);
+ blk_requeue_request(info->rq, req);
+ }

- list_for_each_entry_safe(req, n, &requests, queuelist) {
- /* Requeue pending requests (flush or discard) */
- list_del_init(&req->queuelist);
- BUG_ON(req->nr_phys_segments > segs);
- blk_requeue_request(info->rq, req);
+ spin_unlock_irq(&info->rinfo[i].io_lock);
}
- spin_unlock_irq(&info->io_lock);

while ((bio = bio_list_pop(&bio_list)) != NULL) {
/* Traverse the list of pending bios and re-queue them */
@@ -1758,14 +1875,15 @@ static void blkfront_setup_discard(struct blkfront_info *info)
info->feature_secdiscard = !!discard_secure;
}

-static int blkfront_setup_indirect(struct blkfront_info *info)
+
+static int blkfront_gather_indirect(struct blkfront_info *info)
{
unsigned int indirect_segments, segs;
- int err, i;
+ int err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "feature-max-indirect-segments", "%u",
+ &indirect_segments,
+ NULL);

- err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
- "feature-max-indirect-segments", "%u", &indirect_segments,
- NULL);
if (err) {
info->max_indirect_segments = 0;
segs = BLKIF_MAX_SEGMENTS_PER_REQUEST;
@@ -1775,7 +1893,16 @@ static int blkfront_setup_indirect(struct blkfront_info *info)
segs = info->max_indirect_segments;
}

- err = fill_grant_buffer(info, (segs + INDIRECT_GREFS(segs)) * BLK_RING_SIZE);
+ return segs;
+}
+
+static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo,
+ unsigned int segs)
+{
+ struct blkfront_info *info = rinfo->info;
+ int err, i;
+
+ err = fill_grant_buffer(rinfo, (segs + INDIRECT_GREFS(segs)) * BLK_RING_SIZE);
if (err)
goto out_of_memory;

@@ -1787,31 +1914,31 @@ static int blkfront_setup_indirect(struct blkfront_info *info)
*/
int num = INDIRECT_GREFS(segs) * BLK_RING_SIZE;

- BUG_ON(!list_empty(&info->indirect_pages));
+ BUG_ON(!list_empty(&rinfo->indirect_pages));
for (i = 0; i < num; i++) {
struct page *indirect_page = alloc_page(GFP_NOIO);
if (!indirect_page)
goto out_of_memory;
- list_add(&indirect_page->lru, &info->indirect_pages);
+ list_add(&indirect_page->lru, &rinfo->indirect_pages);
}
}

for (i = 0; i < BLK_RING_SIZE; i++) {
- info->shadow[i].grants_used = kzalloc(
- sizeof(info->shadow[i].grants_used[0]) * segs,
+ rinfo->shadow[i].grants_used = kzalloc(
+ sizeof(rinfo->shadow[i].grants_used[0]) * segs,
GFP_NOIO);
- info->shadow[i].sg = kzalloc(sizeof(info->shadow[i].sg[0]) * segs, GFP_NOIO);
+ rinfo->shadow[i].sg = kzalloc(sizeof(rinfo->shadow[i].sg[0]) * segs, GFP_NOIO);
if (info->max_indirect_segments)
- info->shadow[i].indirect_grants = kzalloc(
- sizeof(info->shadow[i].indirect_grants[0]) *
+ rinfo->shadow[i].indirect_grants = kzalloc(
+ sizeof(rinfo->shadow[i].indirect_grants[0]) *
INDIRECT_GREFS(segs),
GFP_NOIO);
- if ((info->shadow[i].grants_used == NULL) ||
- (info->shadow[i].sg == NULL) ||
+ if ((rinfo->shadow[i].grants_used == NULL) ||
+ (rinfo->shadow[i].sg == NULL) ||
(info->max_indirect_segments &&
- (info->shadow[i].indirect_grants == NULL)))
+ (rinfo->shadow[i].indirect_grants == NULL)))
goto out_of_memory;
- sg_init_table(info->shadow[i].sg, segs);
+ sg_init_table(rinfo->shadow[i].sg, segs);
}


@@ -1819,16 +1946,16 @@ static int blkfront_setup_indirect(struct blkfront_info *info)

out_of_memory:
for (i = 0; i < BLK_RING_SIZE; i++) {
- kfree(info->shadow[i].grants_used);
- info->shadow[i].grants_used = NULL;
- kfree(info->shadow[i].sg);
- info->shadow[i].sg = NULL;
- kfree(info->shadow[i].indirect_grants);
- info->shadow[i].indirect_grants = NULL;
- }
- if (!list_empty(&info->indirect_pages)) {
+ kfree(rinfo->shadow[i].grants_used);
+ rinfo->shadow[i].grants_used = NULL;
+ kfree(rinfo->shadow[i].sg);
+ rinfo->shadow[i].sg = NULL;
+ kfree(rinfo->shadow[i].indirect_grants);
+ rinfo->shadow[i].indirect_grants = NULL;
+ }
+ if (!list_empty(&rinfo->indirect_pages)) {
struct page *indirect_page, *n;
- list_for_each_entry_safe(indirect_page, n, &info->indirect_pages, lru) {
+ list_for_each_entry_safe(indirect_page, n, &rinfo->indirect_pages, lru) {
list_del(&indirect_page->lru);
__free_page(indirect_page);
}
@@ -1846,7 +1973,8 @@ static void blkfront_connect(struct blkfront_info *info)
unsigned long sector_size;
unsigned int physical_sector_size;
unsigned int binfo;
- int err;
+ unsigned int segs;
+ int i, err;
int barrier, flush, discard, persistent;

switch (info->connected) {
@@ -1950,11 +2078,14 @@ static void blkfront_connect(struct blkfront_info *info)
else
info->feature_persistent = persistent;

- err = blkfront_setup_indirect(info);
- if (err) {
- xenbus_dev_fatal(info->xbdev, err, "setup_indirect at %s",
- info->xbdev->otherend);
- return;
+ segs = blkfront_gather_indirect(info);
+ for (i = 0 ; i < info->nr_rings ; i++) {
+ err = blkfront_setup_indirect(&info->rinfo[i], segs);
+ if (err) {
+ xenbus_dev_fatal(info->xbdev, err, "setup_indirect at %s",
+ info->xbdev->otherend);
+ return;
+ }
}

err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size,
@@ -1967,11 +2098,13 @@ static void blkfront_connect(struct blkfront_info *info)

xenbus_switch_state(info->xbdev, XenbusStateConnected);

- /* Kick pending requests. */
- spin_lock_irq(&info->io_lock);
info->connected = BLKIF_STATE_CONNECTED;
- kick_pending_request_queues(info);
- spin_unlock_irq(&info->io_lock);
+ /* Kick pending requests. */
+ for (i = 0 ; i < info->nr_rings ; i++) {
+ spin_lock_irq(&info->rinfo[i].io_lock);
+ kick_pending_request_queues(&info->rinfo[i]);
+ spin_unlock_irq(&info->rinfo[i].io_lock);
+ }

add_disk(info->gd);

--
2.0.4

--
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/