1 files changed, 87 insertions, 118 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 1bf83a0df0f6..5d1fc8e17dd1 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -120,6 +120,42 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 }
 EXPORT_SYMBOL(blk_rq_init);
 
+#define REQ_OP_NAME(name) [REQ_OP_##name] = #name
+static const char *const blk_op_name[] = {
+	REQ_OP_NAME(READ),
+	REQ_OP_NAME(WRITE),
+	REQ_OP_NAME(FLUSH),
+	REQ_OP_NAME(DISCARD),
+	REQ_OP_NAME(SECURE_ERASE),
+	REQ_OP_NAME(ZONE_RESET),
+	REQ_OP_NAME(WRITE_SAME),
+	REQ_OP_NAME(WRITE_ZEROES),
+	REQ_OP_NAME(SCSI_IN),
+	REQ_OP_NAME(SCSI_OUT),
+	REQ_OP_NAME(DRV_IN),
+	REQ_OP_NAME(DRV_OUT),
+};
+#undef REQ_OP_NAME
+
+/**
+ * blk_op_str - Return string XXX in the REQ_OP_XXX.
+ * @op: REQ_OP_XXX.
+ *
+ * Description: Centralize block layer function to convert REQ_OP_XXX into
+ * string format. Useful in the debugging and tracing bio or request. For
+ * invalid REQ_OP_XXX it returns string "UNKNOWN".
+ */
+inline const char *blk_op_str(unsigned int op)
+{
+	const char *op_str = "UNKNOWN";
+
+	if (op < ARRAY_SIZE(blk_op_name) && blk_op_name[op])
+		op_str = blk_op_name[op];
+
+	return op_str;
+}
+EXPORT_SYMBOL_GPL(blk_op_str);
+
 static const struct {
 	int		errno;
 	const char	*name;
@@ -167,18 +203,23 @@ int blk_status_to_errno(blk_status_t status)
 }
 EXPORT_SYMBOL_GPL(blk_status_to_errno);
 
-static void print_req_error(struct request *req, blk_status_t status)
+static void print_req_error(struct request *req, blk_status_t status,
+		const char *caller)
 {
 	int idx = (__force int)status;
 
 	if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors)))
 		return;
 
-	printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu flags %x\n",
-				__func__, blk_errors[idx].name,
-				req->rq_disk ?  req->rq_disk->disk_name : "?",
-				(unsigned long long)blk_rq_pos(req),
-				req->cmd_flags);
+	printk_ratelimited(KERN_ERR
+		"%s: %s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x "
+		"phys_seg %u prio class %u\n",
+		caller, blk_errors[idx].name,
+		req->rq_disk ? req->rq_disk->disk_name : "?",
+		blk_rq_pos(req), req_op(req), blk_op_str(req_op(req)),
+		req->cmd_flags & ~REQ_OP_MASK,
+		req->nr_phys_segments,
+		IOPRIO_PRIO_CLASS(req->ioprio));
 }
 
 static void req_bio_endio(struct request *rq, struct bio *bio,
@@ -282,35 +323,6 @@ void blk_set_queue_dying(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_set_queue_dying);
 
-/* Unconfigure the I/O scheduler and dissociate from the cgroup controller. */
-void blk_exit_queue(struct request_queue *q)
-{
-	/*
-	 * Since the I/O scheduler exit code may access cgroup information,
-	 * perform I/O scheduler exit before disassociating from the block
-	 * cgroup controller.
-	 */
-	if (q->elevator) {
-		ioc_clear_queue(q);
-		elevator_exit(q, q->elevator);
-		q->elevator = NULL;
-	}
-
-	/*
-	 * Remove all references to @q from the block cgroup controller before
-	 * restoring @q->queue_lock to avoid that restoring this pointer causes
-	 * e.g. blkcg_print_blkgs() to crash.
-	 */
-	blkcg_exit_queue(q);
-
-	/*
-	 * Since the cgroup code may dereference the @q->backing_dev_info
-	 * pointer, only decrease its reference count after having removed the
-	 * association with the block cgroup controller.
-	 */
-	bdi_put(q->backing_dev_info);
-}
-
 /**
  * blk_cleanup_queue - shutdown a request queue
  * @q: request queue to shutdown
@@ -346,17 +358,22 @@ void blk_cleanup_queue(struct request_queue *q)
 	del_timer_sync(&q->backing_dev_info->laptop_mode_wb_timer);
 	blk_sync_queue(q);
 
-	/*
-	 * I/O scheduler exit is only safe after the sysfs scheduler attribute
-	 * has been removed.
-	 */
-	WARN_ON_ONCE(q->kobj.state_in_sysfs);
-
-	blk_exit_queue(q);
-
 	if (queue_is_mq(q))
 		blk_mq_exit_queue(q);
 
+	/*
+	 * In theory, request pool of sched_tags belongs to request queue.
+	 * However, the current implementation requires tag_set for freeing
+	 * requests, so free the pool now.
+	 *
+	 * Queue has become frozen, there can't be any in-queue requests, so
+	 * it is safe to free requests now.
+	 */
+	mutex_lock(&q->sysfs_lock);
+	if (q->elevator)
+		blk_mq_sched_free_requests(q);
+	mutex_unlock(&q->sysfs_lock);
+
 	percpu_ref_exit(&q->q_usage_counter);
 
 	/* @q is and will stay empty, shutdown and put */
@@ -574,15 +591,15 @@ void blk_put_request(struct request *req)
 }
 EXPORT_SYMBOL(blk_put_request);
 
-bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
-			    struct bio *bio)
+bool bio_attempt_back_merge(struct request *req, struct bio *bio,
+		unsigned int nr_segs)
 {
 	const int ff = bio->bi_opf & REQ_FAILFAST_MASK;
 
-	if (!ll_back_merge_fn(q, req, bio))
+	if (!ll_back_merge_fn(req, bio, nr_segs))
 		return false;
 
-	trace_block_bio_backmerge(q, req, bio);
+	trace_block_bio_backmerge(req->q, req, bio);
 
 	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
 		blk_rq_set_mixed_merge(req);
@@ -595,15 +612,15 @@ bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 	return true;
 }
 
-bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
-			     struct bio *bio)
+bool bio_attempt_front_merge(struct request *req, struct bio *bio,
+		unsigned int nr_segs)
 {
 	const int ff = bio->bi_opf & REQ_FAILFAST_MASK;
 
-	if (!ll_front_merge_fn(q, req, bio))
+	if (!ll_front_merge_fn(req, bio, nr_segs))
 		return false;
 
-	trace_block_bio_frontmerge(q, req, bio);
+	trace_block_bio_frontmerge(req->q, req, bio);
 
 	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
 		blk_rq_set_mixed_merge(req);
@@ -645,6 +662,7 @@ no_merge:
  * blk_attempt_plug_merge - try to merge with %current's plugged list
  * @q: request_queue new bio is being queued at
  * @bio: new bio being queued
+ * @nr_segs: number of segments in @bio
  * @same_queue_rq: pointer to &struct request that gets filled in when
  * another request associated with @q is found on the plug list
  * (optional, may be %NULL)
@@ -663,7 +681,7 @@ no_merge:
  * Caller must ensure !blk_queue_nomerges(q) beforehand.
  */
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
-			    struct request **same_queue_rq)
+		unsigned int nr_segs, struct request **same_queue_rq)
 {
 	struct blk_plug *plug;
 	struct request *rq;
@@ -692,10 +710,10 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 
 		switch (blk_try_merge(rq, bio)) {
 		case ELEVATOR_BACK_MERGE:
-			merged = bio_attempt_back_merge(q, rq, bio);
+			merged = bio_attempt_back_merge(rq, bio, nr_segs);
 			break;
 		case ELEVATOR_FRONT_MERGE:
-			merged = bio_attempt_front_merge(q, rq, bio);
+			merged = bio_attempt_front_merge(rq, bio, nr_segs);
 			break;
 		case ELEVATOR_DISCARD_MERGE:
 			merged = bio_attempt_discard_merge(q, rq, bio);
@@ -711,18 +729,6 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 	return false;
 }
 
-void blk_init_request_from_bio(struct request *req, struct bio *bio)
-{
-	if (bio->bi_opf & REQ_RAHEAD)
-		req->cmd_flags |= REQ_FAILFAST_MASK;
-
-	req->__sector = bio->bi_iter.bi_sector;
-	req->ioprio = bio_prio(bio);
-	req->write_hint = bio->bi_write_hint;
-	blk_rq_bio_prep(req->q, req, bio);
-}
-EXPORT_SYMBOL_GPL(blk_init_request_from_bio);
-
 static void handle_bad_sector(struct bio *bio, sector_t maxsector)
 {
 	char b[BDEVNAME_SIZE];
@@ -994,22 +1000,8 @@ blk_qc_t generic_make_request(struct bio *bio)
 	 * yet.
 	 */
 	struct bio_list bio_list_on_stack[2];
-	blk_mq_req_flags_t flags = 0;
-	struct request_queue *q = bio->bi_disk->queue;
 	blk_qc_t ret = BLK_QC_T_NONE;
 
-	if (bio->bi_opf & REQ_NOWAIT)
-		flags = BLK_MQ_REQ_NOWAIT;
-	if (bio_flagged(bio, BIO_QUEUE_ENTERED))
-		blk_queue_enter_live(q);
-	else if (blk_queue_enter(q, flags) < 0) {
-		if (!blk_queue_dying(q) && (bio->bi_opf & REQ_NOWAIT))
-			bio_wouldblock_error(bio);
-		else
-			bio_io_error(bio);
-		return ret;
-	}
-
 	if (!generic_make_request_checks(bio))
 		goto out;
 
@@ -1046,22 +1038,11 @@ blk_qc_t generic_make_request(struct bio *bio)
 	bio_list_init(&bio_list_on_stack[0]);
 	current->bio_list = bio_list_on_stack;
 	do {
-		bool enter_succeeded = true;
-
-		if (unlikely(q != bio->bi_disk->queue)) {
-			if (q)
-				blk_queue_exit(q);
-			q = bio->bi_disk->queue;
-			flags = 0;
-			if (bio->bi_opf & REQ_NOWAIT)
-				flags = BLK_MQ_REQ_NOWAIT;
-			if (blk_queue_enter(q, flags) < 0) {
-				enter_succeeded = false;
-				q = NULL;
-			}
-		}
+		struct request_queue *q = bio->bi_disk->queue;
+		blk_mq_req_flags_t flags = bio->bi_opf & REQ_NOWAIT ?
+			BLK_MQ_REQ_NOWAIT : 0;
 
-		if (enter_succeeded) {
+		if (likely(blk_queue_enter(q, flags) == 0)) {
 			struct bio_list lower, same;
 
 			/* Create a fresh bio_list for all subordinate requests */
@@ -1069,6 +1050,8 @@ blk_qc_t generic_make_request(struct bio *bio)
 			bio_list_init(&bio_list_on_stack[0]);
 			ret = q->make_request_fn(q, bio);
 
+			blk_queue_exit(q);
+
 			/* sort new bios into those for a lower level
 			 * and those for the same level
 			 */
@@ -1095,8 +1078,6 @@ blk_qc_t generic_make_request(struct bio *bio)
 	current->bio_list = NULL; /* deactivate */
 
 out:
-	if (q)
-		blk_queue_exit(q);
 	return ret;
 }
 EXPORT_SYMBOL(generic_make_request);
@@ -1200,7 +1181,9 @@ static int blk_cloned_rq_check_limits(struct request_queue *q,
 				      struct request *rq)
 {
 	if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, req_op(rq))) {
-		printk(KERN_ERR "%s: over max size limit.\n", __func__);
+		printk(KERN_ERR "%s: over max size limit. (%u > %u)\n",
+			__func__, blk_rq_sectors(rq),
+			blk_queue_get_max_sectors(q, req_op(rq)));
 		return -EIO;
 	}
 
@@ -1210,9 +1193,10 @@ static int blk_cloned_rq_check_limits(struct request_queue *q,
 	 * Recalculate it to check the request correctly on this queue's
 	 * limitation.
 	 */
-	blk_recalc_rq_segments(rq);
+	rq->nr_phys_segments = blk_recalc_rq_segments(rq);
 	if (rq->nr_phys_segments > queue_max_segments(q)) {
-		printk(KERN_ERR "%s: over max segments limit.\n", __func__);
+		printk(KERN_ERR "%s: over max segments limit. (%hu > %hu)\n",
+			__func__, rq->nr_phys_segments, queue_max_segments(q));
 		return -EIO;
 	}
 
@@ -1394,7 +1378,7 @@ EXPORT_SYMBOL_GPL(blk_steal_bios);
  *
  *     This special helper function is only for request stacking drivers
  *     (e.g. request-based dm) so that they can handle partial completion.
- *     Actual device drivers should use blk_end_request instead.
+ *     Actual device drivers should use blk_mq_end_request instead.
  *
  *     Passing the result of blk_rq_bytes() as @nr_bytes guarantees
  *     %false return from this function.
@@ -1419,7 +1403,7 @@ bool blk_update_request(struct request *req, blk_status_t error,
 
 	if (unlikely(error && !blk_rq_is_passthrough(req) &&
 		     !(req->rq_flags & RQF_QUIET)))
-		print_req_error(req, error);
+		print_req_error(req, error, __func__);
 
 	blk_account_io_completion(req, nr_bytes);
 
@@ -1478,28 +1462,13 @@ bool blk_update_request(struct request *req, blk_status_t error,
 		}
 
 		/* recalculate the number of segments */
-		blk_recalc_rq_segments(req);
+		req->nr_phys_segments = blk_recalc_rq_segments(req);
 	}
 
 	return true;
 }
 EXPORT_SYMBOL_GPL(blk_update_request);
 
-void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
-		     struct bio *bio)
-{
-	if (bio_has_data(bio))
-		rq->nr_phys_segments = bio_phys_segments(q, bio);
-	else if (bio_op(bio) == REQ_OP_DISCARD)
-		rq->nr_phys_segments = 1;
-
-	rq->__data_len = bio->bi_iter.bi_size;
-	rq->bio = rq->biotail = bio;
-
-	if (bio->bi_disk)
-		rq->rq_disk = bio->bi_disk;
-}
-
 #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
 /**
  * rq_flush_dcache_pages - Helper function to flush all pages in a request