#include <linux/interrupt.h>
#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
#include <linux/hdreg.h>
#include <linux/cdrom.h>
#include <linux/module.h>
struct split_bio {
struct bio *bio;
atomic_t pending;
- int err;
};
static DEFINE_MUTEX(blkfront_mutex);
unsigned int feature_persistent:1;
unsigned int max_indirect_segments;
int is_ready;
+ struct blk_mq_tag_set tag_set;
};
static unsigned int nr_minors;
((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
static int blkfront_setup_indirect(struct blkfront_info *info);
+static int blkfront_gather_backend_features(struct blkfront_info *info);
static int get_id_from_freelist(struct blkfront_info *info)
{
struct blkfront_info *info)
{
struct grant *gnt_list_entry;
- unsigned long buffer_mfn;
+ unsigned long buffer_gfn;
BUG_ON(list_empty(&info->grants));
gnt_list_entry = list_first_entry(&info->grants, struct grant,
BUG_ON(!pfn);
gnt_list_entry->pfn = pfn;
}
- buffer_mfn = pfn_to_mfn(gnt_list_entry->pfn);
+ buffer_gfn = pfn_to_gfn(gnt_list_entry->pfn);
gnttab_grant_foreign_access_ref(gnt_list_entry->gref,
info->xbdev->otherend_id,
- buffer_mfn, 0);
+ buffer_gfn, 0);
return gnt_list_entry;
}
!(info->feature_flush & REQ_FUA)));
}
-/*
- * do_blkif_request
- * read a block; request is in a request queue
- */
-static void do_blkif_request(struct request_queue *rq)
+static int blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
+ const struct blk_mq_queue_data *qd)
{
- struct blkfront_info *info = NULL;
- struct request *req;
- int queued;
-
- pr_debug("Entered do_blkif_request\n");
+ struct blkfront_info *info = qd->rq->rq_disk->private_data;
- queued = 0;
-
- while ((req = blk_peek_request(rq)) != NULL) {
- info = req->rq_disk->private_data;
-
- if (RING_FULL(&info->ring))
- goto wait;
+ blk_mq_start_request(qd->rq);
+ spin_lock_irq(&info->io_lock);
+ if (RING_FULL(&info->ring))
+ goto out_busy;
- blk_start_request(req);
+ if (blkif_request_flush_invalid(qd->rq, info))
+ goto out_err;
- if (blkif_request_flush_invalid(req, info)) {
- __blk_end_request_all(req, -EOPNOTSUPP);
- continue;
- }
+ if (blkif_queue_request(qd->rq))
+ goto out_busy;
- pr_debug("do_blk_req %p: cmd %p, sec %lx, "
- "(%u/%u) [%s]\n",
- req, req->cmd, (unsigned long)blk_rq_pos(req),
- blk_rq_cur_sectors(req), blk_rq_sectors(req),
- rq_data_dir(req) ? "write" : "read");
-
- if (blkif_queue_request(req)) {
- blk_requeue_request(rq, req);
-wait:
- /* Avoid pointless unplugs. */
- blk_stop_queue(rq);
- break;
- }
+ flush_requests(info);
+ spin_unlock_irq(&info->io_lock);
+ return BLK_MQ_RQ_QUEUE_OK;
- queued++;
- }
+out_err:
+ spin_unlock_irq(&info->io_lock);
+ return BLK_MQ_RQ_QUEUE_ERROR;
- if (queued != 0)
- flush_requests(info);
+out_busy:
+ spin_unlock_irq(&info->io_lock);
+ blk_mq_stop_hw_queue(hctx);
+ return BLK_MQ_RQ_QUEUE_BUSY;
}
+static struct blk_mq_ops blkfront_mq_ops = {
+ .queue_rq = blkif_queue_rq,
+ .map_queue = blk_mq_map_queue,
+};
+
static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
unsigned int physical_sector_size,
unsigned int segments)
struct request_queue *rq;
struct blkfront_info *info = gd->private_data;
- rq = blk_init_queue(do_blkif_request, &info->io_lock);
- if (rq == NULL)
+ memset(&info->tag_set, 0, sizeof(info->tag_set));
+ info->tag_set.ops = &blkfront_mq_ops;
+ info->tag_set.nr_hw_queues = 1;
+ info->tag_set.queue_depth = BLK_RING_SIZE(info);
+ info->tag_set.numa_node = NUMA_NO_NODE;
+ info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
+ info->tag_set.cmd_size = 0;
+ info->tag_set.driver_data = info;
+
+ if (blk_mq_alloc_tag_set(&info->tag_set))
+ return -1;
+ rq = blk_mq_init_queue(&info->tag_set);
+ if (IS_ERR(rq)) {
+ blk_mq_free_tag_set(&info->tag_set);
return -1;
+ }
queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
static void xlvbd_release_gendisk(struct blkfront_info *info)
{
unsigned int minor, nr_minors;
- unsigned long flags;
if (info->rq == NULL)
return;
- spin_lock_irqsave(&info->io_lock, flags);
-
/* No more blkif_request(). */
- blk_stop_queue(info->rq);
+ blk_mq_stop_hw_queues(info->rq);
/* No more gnttab callback work. */
gnttab_cancel_free_callback(&info->callback);
- spin_unlock_irqrestore(&info->io_lock, flags);
/* Flush gnttab callback work. Must be done with no locks held. */
flush_work(&info->work);
xlbd_release_minors(minor, nr_minors);
blk_cleanup_queue(info->rq);
+ blk_mq_free_tag_set(&info->tag_set);
info->rq = NULL;
put_disk(info->gd);
info->gd = NULL;
}
+/* Must be called with io_lock holded */
static void kick_pending_request_queues(struct blkfront_info *info)
{
- if (!RING_FULL(&info->ring)) {
- /* Re-enable calldowns. */
- blk_start_queue(info->rq);
- /* Kick things off immediately. */
- do_blkif_request(info->rq);
- }
+ if (!RING_FULL(&info->ring))
+ blk_mq_start_stopped_hw_queues(info->rq, true);
}
static void blkif_restart_queue(struct work_struct *work)
BLKIF_STATE_SUSPENDED : BLKIF_STATE_DISCONNECTED;
/* No more blkif_request(). */
if (info->rq)
- blk_stop_queue(info->rq);
+ blk_mq_stop_hw_queues(info->rq);
/* Remove all persistent grants */
if (!list_empty(&info->grants)) {
* Add the used indirect page back to the list of
* available pages for indirect grefs.
*/
- indirect_page = pfn_to_page(s->indirect_grants[i]->pfn);
- list_add(&indirect_page->lru, &info->indirect_pages);
+ if (!info->feature_persistent) {
+ indirect_page = pfn_to_page(s->indirect_grants[i]->pfn);
+ list_add(&indirect_page->lru, &info->indirect_pages);
+ }
s->indirect_grants[i]->gref = GRANT_INVALID_REF;
list_add_tail(&s->indirect_grants[i]->node, &info->grants);
}
queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
queue_flag_clear(QUEUE_FLAG_SECDISCARD, rq);
}
- __blk_end_request_all(req, error);
+ blk_mq_complete_request(req, error);
break;
case BLKIF_OP_FLUSH_DISKCACHE:
case BLKIF_OP_WRITE_BARRIER:
dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
"request: %x\n", bret->status);
- __blk_end_request_all(req, error);
+ blk_mq_complete_request(req, error);
break;
default:
BUG();
return 0;
}
-static void split_bio_end(struct bio *bio, int error)
+static void split_bio_end(struct bio *bio)
{
struct split_bio *split_bio = bio->bi_private;
- if (error)
- split_bio->err = error;
-
if (atomic_dec_and_test(&split_bio->pending)) {
split_bio->bio->bi_phys_segments = 0;
- bio_endio(split_bio->bio, split_bio->err);
+ split_bio->bio->bi_error = bio->bi_error;
+ bio_endio(split_bio->bio);
kfree(split_bio);
}
bio_put(bio);
info->shadow_free = info->ring.req_prod_pvt;
info->shadow[BLK_RING_SIZE(info)-1].req.u.rw.id = 0x0fffffff;
- rc = blkfront_setup_indirect(info);
+ rc = blkfront_gather_backend_features(info);
if (rc) {
kfree(copy);
return rc;
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.
- */
- 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;
- }
- 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_end_request_all(req, 0);
- }
- spin_unlock_irq(&info->io_lock);
-
xenbus_switch_state(info->xbdev, XenbusStateConnected);
spin_lock_irq(&info->io_lock);
/* Requeue pending requests (flush or discard) */
list_del_init(&req->queuelist);
BUG_ON(req->nr_phys_segments > segs);
- blk_requeue_request(info->rq, req);
+ blk_mq_requeue_request(req);
}
spin_unlock_irq(&info->io_lock);
+ blk_mq_kick_requeue_list(info->rq);
while ((bio = bio_list_pop(&bio_list)) != NULL) {
/* Traverse the list of pending bios and re-queue them */
static int blkfront_setup_indirect(struct blkfront_info *info)
{
- unsigned int indirect_segments, segs;
+ unsigned int segs;
int err, i;
- err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
- "feature-max-indirect-segments", "%u", &indirect_segments,
- NULL);
- if (err) {
- info->max_indirect_segments = 0;
+ if (info->max_indirect_segments == 0)
segs = BLKIF_MAX_SEGMENTS_PER_REQUEST;
- } else {
- info->max_indirect_segments = min(indirect_segments,
- xen_blkif_max_segments);
+ else
segs = info->max_indirect_segments;
- }
err = fill_grant_buffer(info, (segs + INDIRECT_GREFS(segs)) * BLK_RING_SIZE(info));
if (err)
return -ENOMEM;
}
+/*
+ * Gather all backend feature-*
+ */
+static int blkfront_gather_backend_features(struct blkfront_info *info)
+{
+ int err;
+ int barrier, flush, discard, persistent;
+ unsigned int indirect_segments;
+
+ info->feature_flush = 0;
+
+ err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "feature-barrier", "%d", &barrier,
+ NULL);
+
+ /*
+ * If there's no "feature-barrier" defined, then it means
+ * we're dealing with a very old backend which writes
+ * synchronously; nothing to do.
+ *
+ * If there are barriers, then we use flush.
+ */
+ if (!err && barrier)
+ info->feature_flush = REQ_FLUSH | REQ_FUA;
+ /*
+ * And if there is "feature-flush-cache" use that above
+ * barriers.
+ */
+ err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "feature-flush-cache", "%d", &flush,
+ NULL);
+
+ if (!err && flush)
+ info->feature_flush = REQ_FLUSH;
+
+ err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "feature-discard", "%d", &discard,
+ NULL);
+
+ if (!err && discard)
+ blkfront_setup_discard(info);
+
+ err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "feature-persistent", "%u", &persistent,
+ NULL);
+ if (err)
+ info->feature_persistent = 0;
+ else
+ info->feature_persistent = persistent;
+
+ err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "feature-max-indirect-segments", "%u", &indirect_segments,
+ NULL);
+ if (err)
+ info->max_indirect_segments = 0;
+ else
+ info->max_indirect_segments = min(indirect_segments,
+ xen_blkif_max_segments);
+
+ return blkfront_setup_indirect(info);
+}
+
/*
* Invoked when the backend is finally 'ready' (and has told produced
* the details about the physical device - #sectors, size, etc).
unsigned int physical_sector_size;
unsigned int binfo;
int err;
- int barrier, flush, discard, persistent;
switch (info->connected) {
case BLKIF_STATE_CONNECTED:
if (err != 1)
physical_sector_size = sector_size;
- info->feature_flush = 0;
-
- err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
- "feature-barrier", "%d", &barrier,
- NULL);
-
- /*
- * If there's no "feature-barrier" defined, then it means
- * we're dealing with a very old backend which writes
- * synchronously; nothing to do.
- *
- * If there are barriers, then we use flush.
- */
- if (!err && barrier)
- info->feature_flush = REQ_FLUSH | REQ_FUA;
- /*
- * And if there is "feature-flush-cache" use that above
- * barriers.
- */
- err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
- "feature-flush-cache", "%d", &flush,
- NULL);
-
- if (!err && flush)
- info->feature_flush = REQ_FLUSH;
-
- err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
- "feature-discard", "%d", &discard,
- NULL);
-
- if (!err && discard)
- blkfront_setup_discard(info);
-
- err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
- "feature-persistent", "%u", &persistent,
- NULL);
- if (err)
- info->feature_persistent = 0;
- else
- info->feature_persistent = persistent;
-
- err = blkfront_setup_indirect(info);
+ err = blkfront_gather_backend_features(info);
if (err) {
xenbus_dev_fatal(info->xbdev, err, "setup_indirect at %s",
info->xbdev->otherend);
break;
/* Missed the backend's Closing state -- fallthrough */
case XenbusStateClosing:
- blkfront_closing(info);
+ if (info)
+ blkfront_closing(info);
break;
}
}