1 files changed, 147 insertions, 66 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 8bdd0121212..6f8dba161bf 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -38,10 +38,12 @@
 
 #include "blk.h"
 #include "blk-cgroup.h"
+#include "blk-mq.h"
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_split);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug);
 
 DEFINE_IDA(blk_queue_ida);
@@ -130,7 +132,7 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 	bio_advance(bio, nbytes);
 
 	/* don't actually finish bio if it's part of flush sequence */
-	if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
+	if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
 		bio_endio(bio, error);
 }
 
@@ -145,8 +147,8 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 	printk(KERN_INFO "  sector %llu, nr/cnr %u/%u\n",
 	       (unsigned long long)blk_rq_pos(rq),
 	       blk_rq_sectors(rq), blk_rq_cur_sectors(rq));
-	printk(KERN_INFO "  bio %p, biotail %p, buffer %p, len %u\n",
-	       rq->bio, rq->biotail, rq->buffer, blk_rq_bytes(rq));
+	printk(KERN_INFO "  bio %p, biotail %p, len %u\n",
+	       rq->bio, rq->biotail, blk_rq_bytes(rq));
 
 	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
 		printk(KERN_INFO "  cdb: ");
@@ -245,7 +247,18 @@ EXPORT_SYMBOL(blk_stop_queue);
 void blk_sync_queue(struct request_queue *q)
 {
 	del_timer_sync(&q->timeout);
-	cancel_delayed_work_sync(&q->delay_work);
+
+	if (q->mq_ops) {
+		struct blk_mq_hw_ctx *hctx;
+		int i;
+
+		queue_for_each_hw_ctx(q, hctx, i) {
+			cancel_delayed_work_sync(&hctx->run_work);
+			cancel_delayed_work_sync(&hctx->delay_work);
+		}
+	} else {
+		cancel_delayed_work_sync(&q->delay_work);
+	}
 }
 EXPORT_SYMBOL(blk_sync_queue);
 
@@ -497,8 +510,13 @@ void blk_cleanup_queue(struct request_queue *q)
 	 * Drain all requests queued before DYING marking. Set DEAD flag to
 	 * prevent that q->request_fn() gets invoked after draining finished.
 	 */
-	spin_lock_irq(lock);
-	__blk_drain_queue(q, true);
+	if (q->mq_ops) {
+		blk_mq_drain_queue(q);
+		spin_lock_irq(lock);
+	} else {
+		spin_lock_irq(lock);
+		__blk_drain_queue(q, true);
+	}
 	queue_flag_set(QUEUE_FLAG_DEAD, q);
 	spin_unlock_irq(lock);
 
@@ -559,12 +577,9 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	if (!q)
 		return NULL;
 
-	if (percpu_counter_init(&q->mq_usage_counter, 0))
-		goto fail_q;
-
 	q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask);
 	if (q->id < 0)
-		goto fail_c;
+		goto fail_q;
 
 	q->backing_dev_info.ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
@@ -622,8 +637,6 @@ fail_bdi:
 	bdi_destroy(&q->backing_dev_info);
 fail_id:
 	ida_simple_remove(&blk_queue_ida, q->id);
-fail_c:
-	percpu_counter_destroy(&q->mq_usage_counter);
 fail_q:
 	kmem_cache_free(blk_requestq_cachep, q);
 	return NULL;
@@ -693,9 +706,13 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	if (!q)
 		return NULL;
 
-	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
+	q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
+	if (!q->flush_rq)
 		return NULL;
 
+	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
+		goto fail;
+
 	q->request_fn		= rfn;
 	q->prep_rq_fn		= NULL;
 	q->unprep_rq_fn		= NULL;
@@ -718,12 +735,16 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	/* init elevator */
 	if (elevator_init(q, NULL)) {
 		mutex_unlock(&q->sysfs_lock);
-		return NULL;
+		goto fail;
 	}
 
 	mutex_unlock(&q->sysfs_lock);
 
 	return q;
+
+fail:
+	kfree(q->flush_rq);
+	return NULL;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
 
@@ -823,6 +844,47 @@ static void freed_request(struct request_list *rl, unsigned int flags)
 		__freed_request(rl, sync ^ 1);
 }
 
+int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
+{
+	struct request_list *rl;
+
+	spin_lock_irq(q->queue_lock);
+	q->nr_requests = nr;
+	blk_queue_congestion_threshold(q);
+
+	/* congestion isn't cgroup aware and follows root blkcg for now */
+	rl = &q->root_rl;
+
+	if (rl->count[BLK_RW_SYNC] >= queue_congestion_on_threshold(q))
+		blk_set_queue_congested(q, BLK_RW_SYNC);
+	else if (rl->count[BLK_RW_SYNC] < queue_congestion_off_threshold(q))
+		blk_clear_queue_congested(q, BLK_RW_SYNC);
+
+	if (rl->count[BLK_RW_ASYNC] >= queue_congestion_on_threshold(q))
+		blk_set_queue_congested(q, BLK_RW_ASYNC);
+	else if (rl->count[BLK_RW_ASYNC] < queue_congestion_off_threshold(q))
+		blk_clear_queue_congested(q, BLK_RW_ASYNC);
+
+	blk_queue_for_each_rl(rl, q) {
+		if (rl->count[BLK_RW_SYNC] >= q->nr_requests) {
+			blk_set_rl_full(rl, BLK_RW_SYNC);
+		} else {
+			blk_clear_rl_full(rl, BLK_RW_SYNC);
+			wake_up(&rl->wait[BLK_RW_SYNC]);
+		}
+
+		if (rl->count[BLK_RW_ASYNC] >= q->nr_requests) {
+			blk_set_rl_full(rl, BLK_RW_ASYNC);
+		} else {
+			blk_clear_rl_full(rl, BLK_RW_ASYNC);
+			wake_up(&rl->wait[BLK_RW_ASYNC]);
+		}
+	}
+
+	spin_unlock_irq(q->queue_lock);
+	return 0;
+}
+
 /*
  * Determine if elevator data should be initialized when allocating the
  * request associated with @bio.
@@ -1157,6 +1219,8 @@ struct request *blk_make_request(struct request_queue *q, struct bio *bio,
 	if (unlikely(!rq))
 		return ERR_PTR(-ENOMEM);
 
+	blk_rq_set_block_pc(rq);
+
 	for_each_bio(bio) {
 		struct bio *bounce_bio = bio;
 		int ret;
@@ -1174,6 +1238,22 @@ struct request *blk_make_request(struct request_queue *q, struct bio *bio,
 EXPORT_SYMBOL(blk_make_request);
 
 /**
+ * blk_rq_set_block_pc - initialize a requeest to type BLOCK_PC
+ * @rq:		request to be initialized
+ *
+ */
+void blk_rq_set_block_pc(struct request *rq)
+{
+	rq->cmd_type = REQ_TYPE_BLOCK_PC;
+	rq->__data_len = 0;
+	rq->__sector = (sector_t) -1;
+	rq->bio = rq->biotail = NULL;
+	memset(rq->__cmd, 0, sizeof(rq->__cmd));
+	rq->cmd = rq->__cmd;
+}
+EXPORT_SYMBOL(blk_rq_set_block_pc);
+
+/**
  * blk_requeue_request - put a request back on queue
  * @q:		request queue where request should be inserted
  * @rq:		request to be inserted
@@ -1208,12 +1288,15 @@ static void add_acct_request(struct request_queue *q, struct request *rq,
 static void part_round_stats_single(int cpu, struct hd_struct *part,
 				    unsigned long now)
 {
+	int inflight;
+
 	if (now == part->stamp)
 		return;
 
-	if (part_in_flight(part)) {
+	inflight = part_in_flight(part);
+	if (inflight) {
 		__part_stat_add(cpu, part, time_in_queue,
-				part_in_flight(part) * (now - part->stamp));
+				inflight * (now - part->stamp));
 		__part_stat_add(cpu, part, io_ticks, (now - part->stamp));
 	}
 	part->stamp = now;
@@ -1263,6 +1346,11 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	if (unlikely(!q))
 		return;
 
+	if (q->mq_ops) {
+		blk_mq_free_request(req);
+		return;
+	}
+
 	blk_pm_put_request(req);
 
 	elv_completed_request(q, req);
@@ -1279,7 +1367,7 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 		struct request_list *rl = blk_rq_rl(req);
 
 		BUG_ON(!list_empty(&req->queuelist));
-		BUG_ON(!hlist_unhashed(&req->hash));
+		BUG_ON(ELV_ON_HASH(req));
 
 		blk_free_request(rl, req);
 		freed_request(rl, flags);
@@ -1326,13 +1414,12 @@ void blk_add_request_payload(struct request *rq, struct page *page,
 	bio->bi_io_vec->bv_offset = 0;
 	bio->bi_io_vec->bv_len = len;
 
-	bio->bi_size = len;
+	bio->bi_iter.bi_size = len;
 	bio->bi_vcnt = 1;
 	bio->bi_phys_segments = 1;
 
 	rq->__data_len = rq->resid_len = len;
 	rq->nr_phys_segments = 1;
-	rq->buffer = bio_data(bio);
 }
 EXPORT_SYMBOL_GPL(blk_add_request_payload);
 
@@ -1351,7 +1438,7 @@ bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 
 	req->biotail->bi_next = bio;
 	req->biotail = bio;
-	req->__data_len += bio->bi_size;
+	req->__data_len += bio->bi_iter.bi_size;
 	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
 
 	blk_account_io_start(req, false);
@@ -1374,14 +1461,8 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
 	bio->bi_next = req->bio;
 	req->bio = bio;
 
-	/*
-	 * may not be valid. if the low level driver said
-	 * it didn't need a bounce buffer then it better
-	 * not touch req->buffer either...
-	 */
-	req->buffer = bio_data(bio);
-	req->__sector = bio->bi_sector;
-	req->__data_len += bio->bi_size;
+	req->__sector = bio->bi_iter.bi_sector;
+	req->__data_len += bio->bi_iter.bi_size;
 	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
 
 	blk_account_io_start(req, false);
@@ -1404,6 +1485,8 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
  * added on the elevator at this point.  In addition, we don't have
  * reliable access to the elevator outside queue lock.  Only check basic
  * merging parameters without querying the elevator.
+ *
+ * Caller must ensure !blk_queue_nomerges(q) beforehand.
  */
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 			    unsigned int *request_count)
@@ -1413,9 +1496,6 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 	bool ret = false;
 	struct list_head *plug_list;
 
-	if (blk_queue_nomerges(q))
-		goto out;
-
 	plug = current->plug;
 	if (!plug)
 		goto out;
@@ -1459,7 +1539,7 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 		req->cmd_flags |= REQ_FAILFAST_MASK;
 
 	req->errors = 0;
-	req->__sector = bio->bi_sector;
+	req->__sector = bio->bi_iter.bi_sector;
 	req->ioprio = bio_prio(bio);
 	blk_rq_bio_prep(req->q, req, bio);
 }
@@ -1494,7 +1574,8 @@ void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	 * Check if we can merge with the plugged list before grabbing
 	 * any locks.
 	 */
-	if (blk_attempt_plug_merge(q, bio, &request_count))
+	if (!blk_queue_nomerges(q) &&
+	    blk_attempt_plug_merge(q, bio, &request_count))
 		return;
 
 	spin_lock_irq(q->queue_lock);
@@ -1583,12 +1664,12 @@ static inline void blk_partition_remap(struct bio *bio)
 	if (bio_sectors(bio) && bdev != bdev->bd_contains) {
 		struct hd_struct *p = bdev->bd_part;
 
-		bio->bi_sector += p->start_sect;
+		bio->bi_iter.bi_sector += p->start_sect;
 		bio->bi_bdev = bdev->bd_contains;
 
 		trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), bio,
 				      bdev->bd_dev,
-				      bio->bi_sector - p->start_sect);
+				      bio->bi_iter.bi_sector - p->start_sect);
 	}
 }
 
@@ -1626,7 +1707,7 @@ static int __init fail_make_request_debugfs(void)
 	struct dentry *dir = fault_create_debugfs_attr("fail_make_request",
 						NULL, &fail_make_request);
 
-	return IS_ERR(dir) ? PTR_ERR(dir) : 0;
+	return PTR_ERR_OR_ZERO(dir);
 }
 
 late_initcall(fail_make_request_debugfs);
@@ -1654,7 +1735,7 @@ static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors)
 	/* Test device or partition size, when known. */
 	maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
 	if (maxsector) {
-		sector_t sector = bio->bi_sector;
+		sector_t sector = bio->bi_iter.bi_sector;
 
 		if (maxsector < nr_sectors || maxsector - nr_sectors < sector) {
 			/*
@@ -1690,7 +1771,7 @@ generic_make_request_checks(struct bio *bio)
 		       "generic_make_request: Trying to access "
 			"nonexistent block-device %s (%Lu)\n",
 			bdevname(bio->bi_bdev, b),
-			(long long) bio->bi_sector);
+			(long long) bio->bi_iter.bi_sector);
 		goto end_io;
 	}
 
@@ -1704,9 +1785,9 @@ generic_make_request_checks(struct bio *bio)
 	}
 
 	part = bio->bi_bdev->bd_part;
-	if (should_fail_request(part, bio->bi_size) ||
+	if (should_fail_request(part, bio->bi_iter.bi_size) ||
 	    should_fail_request(&part_to_disk(part)->part0,
-				bio->bi_size))
+				bio->bi_iter.bi_size))
 		goto end_io;
 
 	/*
@@ -1865,7 +1946,7 @@ void submit_bio(int rw, struct bio *bio)
 		if (rw & WRITE) {
 			count_vm_events(PGPGOUT, count);
 		} else {
-			task_io_account_read(bio->bi_size);
+			task_io_account_read(bio->bi_iter.bi_size);
 			count_vm_events(PGPGIN, count);
 		}
 
@@ -1874,7 +1955,7 @@ void submit_bio(int rw, struct bio *bio)
 			printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n",
 			current->comm, task_pid_nr(current),
 				(rw & WRITE) ? "WRITE" : "READ",
-				(unsigned long long)bio->bi_sector,
+				(unsigned long long)bio->bi_iter.bi_sector,
 				bdevname(bio->bi_bdev, b),
 				count);
 		}
@@ -1900,7 +1981,7 @@ EXPORT_SYMBOL(submit_bio);
  *    in some cases below, so export this function.
  *    Request stacking drivers like request-based dm may change the queue
  *    limits while requests are in the queue (e.g. dm's table swapping).
- *    Such request stacking drivers should check those requests agaist
+ *    Such request stacking drivers should check those requests against
  *    the new queue limits again when they dispatch those requests,
  *    although such checkings are also done against the old queue limits
  *    when submitting requests.
@@ -2007,7 +2088,7 @@ unsigned int blk_rq_err_bytes(const struct request *rq)
 	for (bio = rq->bio; bio; bio = bio->bi_next) {
 		if ((bio->bi_rw & ff) != ff)
 			break;
-		bytes += bio->bi_size;
+		bytes += bio->bi_iter.bi_size;
 	}
 
 	/* this could lead to infinite loop */
@@ -2325,7 +2406,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	if (!req->bio)
 		return false;
 
-	trace_block_rq_complete(req->q, req);
+	trace_block_rq_complete(req->q, req, nr_bytes);
 
 	/*
 	 * For fs requests, rq is just carrier of independent bio's
@@ -2378,9 +2459,9 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	total_bytes = 0;
 	while (req->bio) {
 		struct bio *bio = req->bio;
-		unsigned bio_bytes = min(bio->bi_size, nr_bytes);
+		unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
 
-		if (bio_bytes == bio->bi_size)
+		if (bio_bytes == bio->bi_iter.bi_size)
 			req->bio = bio->bi_next;
 
 		req_bio_endio(req, bio, bio_bytes, error);
@@ -2406,7 +2487,6 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	}
 
 	req->__data_len -= total_bytes;
-	req->buffer = bio_data(req->bio);
 
 	/* update sector only for requests with clear definition of sector */
 	if (req->cmd_type == REQ_TYPE_FS)
@@ -2475,7 +2555,7 @@ EXPORT_SYMBOL_GPL(blk_unprep_request);
 /*
  * queue lock must be held
  */
-static void blk_finish_request(struct request *req, int error)
+void blk_finish_request(struct request *req, int error)
 {
 	if (blk_rq_tagged(req))
 		blk_queue_end_tag(req->q, req);
@@ -2501,6 +2581,7 @@ static void blk_finish_request(struct request *req, int error)
 		__blk_put_request(req->q, req);
 	}
 }
+EXPORT_SYMBOL(blk_finish_request);
 
 /**
  * blk_end_bidi_request - Complete a bidi request
@@ -2724,11 +2805,10 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 	/* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */
 	rq->cmd_flags |= bio->bi_rw & REQ_WRITE;
 
-	if (bio_has_data(bio)) {
+	if (bio_has_data(bio))
 		rq->nr_phys_segments = bio_phys_segments(q, bio);
-		rq->buffer = bio_data(bio);
-	}
-	rq->__data_len = bio->bi_size;
+
+	rq->__data_len = bio->bi_iter.bi_size;
 	rq->bio = rq->biotail = bio;
 
 	if (bio->bi_bdev)
@@ -2746,10 +2826,10 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 void rq_flush_dcache_pages(struct request *rq)
 {
 	struct req_iterator iter;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 
 	rq_for_each_segment(bvec, rq, iter)
-		flush_dcache_page(bvec->bv_page);
+		flush_dcache_page(bvec.bv_page);
 }
 EXPORT_SYMBOL_GPL(rq_flush_dcache_pages);
 #endif
@@ -2803,7 +2883,7 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
 
 /*
  * Copy attributes of the original request to the clone request.
- * The actual data parts (e.g. ->cmd, ->buffer, ->sense) are not copied.
+ * The actual data parts (e.g. ->cmd, ->sense) are not copied.
  */
 static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 {
@@ -2829,7 +2909,7 @@ static void __blk_rq_prep_clone(struct request *dst, struct request *src)
  *
  * Description:
  *     Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq.
- *     The actual data parts of @rq_src (e.g. ->cmd, ->buffer, ->sense)
+ *     The actual data parts of @rq_src (e.g. ->cmd, ->sense)
  *     are not copied, and copying such parts is the caller's responsibility.
  *     Also, pages which the original bios are pointing to are not copied
  *     and the cloned bios just point same pages.
@@ -2876,20 +2956,25 @@ free_and_out:
 }
 EXPORT_SYMBOL_GPL(blk_rq_prep_clone);
 
-int kblockd_schedule_work(struct request_queue *q, struct work_struct *work)
+int kblockd_schedule_work(struct work_struct *work)
 {
 	return queue_work(kblockd_workqueue, work);
 }
 EXPORT_SYMBOL(kblockd_schedule_work);
 
-int kblockd_schedule_delayed_work(struct request_queue *q,
-			struct delayed_work *dwork, unsigned long delay)
+int kblockd_schedule_delayed_work(struct delayed_work *dwork,
+				  unsigned long delay)
 {
 	return queue_delayed_work(kblockd_workqueue, dwork, delay);
 }
 EXPORT_SYMBOL(kblockd_schedule_delayed_work);
 
-#define PLUG_MAGIC	0x91827364
+int kblockd_schedule_delayed_work_on(int cpu, struct delayed_work *dwork,
+				     unsigned long delay)
+{
+	return queue_delayed_work_on(cpu, kblockd_workqueue, dwork, delay);
+}
+EXPORT_SYMBOL(kblockd_schedule_delayed_work_on);
 
 /**
  * blk_start_plug - initialize blk_plug and track it inside the task_struct
@@ -2909,7 +2994,6 @@ void blk_start_plug(struct blk_plug *plug)
 {
 	struct task_struct *tsk = current;
 
-	plug->magic = PLUG_MAGIC;
 	INIT_LIST_HEAD(&plug->list);
 	INIT_LIST_HEAD(&plug->mq_list);
 	INIT_LIST_HEAD(&plug->cb_list);
@@ -3006,8 +3090,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	LIST_HEAD(list);
 	unsigned int depth;
 
-	BUG_ON(plug->magic != PLUG_MAGIC);
-
 	flush_plug_callbacks(plug, from_schedule);
 
 	if (!list_empty(&plug->mq_list))
@@ -3230,8 +3312,7 @@ int __init blk_dev_init(void)
 
 	/* used for unplugging and affects IO latency/throughput - HIGHPRI */
 	kblockd_workqueue = alloc_workqueue("kblockd",
-					    WQ_MEM_RECLAIM | WQ_HIGHPRI |
-					    WQ_POWER_EFFICIENT, 0);
+					    WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
 	if (!kblockd_workqueue)
 		panic("Failed to create kblockd\n");