1 files changed, 335 insertions, 149 deletions

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 5a244f05360..54535831f1e 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -9,70 +9,59 @@
 
 #include "blk.h"
 
-void blk_recalc_rq_sectors(struct request *rq, int nsect)
-{
-	if (blk_fs_request(rq) || blk_discard_rq(rq)) {
-		rq->hard_sector += nsect;
-		rq->hard_nr_sectors -= nsect;
-
-		/*
-		 * Move the I/O submission pointers ahead if required.
-		 */
-		if ((rq->nr_sectors >= rq->hard_nr_sectors) &&
-		    (rq->sector <= rq->hard_sector)) {
-			rq->sector = rq->hard_sector;
-			rq->nr_sectors = rq->hard_nr_sectors;
-			rq->hard_cur_sectors = bio_cur_sectors(rq->bio);
-			rq->current_nr_sectors = rq->hard_cur_sectors;
-			rq->buffer = bio_data(rq->bio);
-		}
-
-		/*
-		 * if total number of sectors is less than the first segment
-		 * size, something has gone terribly wrong
-		 */
-		if (rq->nr_sectors < rq->current_nr_sectors) {
-			printk(KERN_ERR "blk: request botched\n");
-			rq->nr_sectors = rq->current_nr_sectors;
-		}
-	}
-}
-
 static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 					     struct bio *bio)
 {
-	unsigned int phys_size;
-	struct bio_vec *bv, *bvprv = NULL;
-	int cluster, i, high, highprv = 1;
+	struct bio_vec bv, bvprv = { NULL };
+	int cluster, high, highprv = 1, no_sg_merge;
 	unsigned int seg_size, nr_phys_segs;
 	struct bio *fbio, *bbio;
+	struct bvec_iter iter;
 
 	if (!bio)
 		return 0;
 
+	/*
+	 * This should probably be returning 0, but blk_add_request_payload()
+	 * (Christoph!!!!)
+	 */
+	if (bio->bi_rw & REQ_DISCARD)
+		return 1;
+
+	if (bio->bi_rw & REQ_WRITE_SAME)
+		return 1;
+
 	fbio = bio;
-	cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
+	cluster = blk_queue_cluster(q);
 	seg_size = 0;
-	phys_size = nr_phys_segs = 0;
+	nr_phys_segs = 0;
+	no_sg_merge = test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags);
+	high = 0;
 	for_each_bio(bio) {
-		bio_for_each_segment(bv, bio, i) {
+		bio_for_each_segment(bv, bio, iter) {
 			/*
-			 * the trick here is making sure that a high page is
-			 * never considered part of another segment, since that
-			 * might change with the bounce page.
+			 * If SG merging is disabled, each bio vector is
+			 * a segment
 			 */
-			high = page_to_pfn(bv->bv_page) > q->bounce_pfn;
-			if (high || highprv)
+			if (no_sg_merge)
 				goto new_segment;
-			if (cluster) {
-				if (seg_size + bv->bv_len > q->max_segment_size)
+
+			/*
+			 * the trick here is making sure that a high page is
+			 * never considered part of another segment, since
+			 * that might change with the bounce page.
+			 */
+			high = page_to_pfn(bv.bv_page) > queue_bounce_pfn(q);
+			if (!high && !highprv && cluster) {
+				if (seg_size + bv.bv_len
+				    > queue_max_segment_size(q))
 					goto new_segment;
-				if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv))
+				if (!BIOVEC_PHYS_MERGEABLE(&bvprv, &bv))
 					goto new_segment;
-				if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bv))
+				if (!BIOVEC_SEG_BOUNDARY(q, &bvprv, &bv))
 					goto new_segment;
 
-				seg_size += bv->bv_len;
+				seg_size += bv.bv_len;
 				bvprv = bv;
 				continue;
 			}
@@ -83,7 +72,7 @@ new_segment:
 
 			nr_phys_segs++;
 			bvprv = bv;
-			seg_size = bv->bv_len;
+			seg_size = bv.bv_len;
 			highprv = high;
 		}
 		bbio = bio;
@@ -104,11 +93,16 @@ void blk_recalc_rq_segments(struct request *rq)
 
 void blk_recount_segments(struct request_queue *q, struct bio *bio)
 {
-	struct bio *nxt = bio->bi_next;
+	if (test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags))
+		bio->bi_phys_segments = bio->bi_vcnt;
+	else {
+		struct bio *nxt = bio->bi_next;
+
+		bio->bi_next = NULL;
+		bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio);
+		bio->bi_next = nxt;
+	}
 
-	bio->bi_next = NULL;
-	bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio);
-	bio->bi_next = nxt;
 	bio->bi_flags |= (1 << BIO_SEG_VALID);
 }
 EXPORT_SYMBOL(blk_recount_segments);
@@ -116,98 +110,147 @@ EXPORT_SYMBOL(blk_recount_segments);
 static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 				   struct bio *nxt)
 {
-	if (!test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
+	struct bio_vec end_bv = { NULL }, nxt_bv;
+	struct bvec_iter iter;
+
+	if (!blk_queue_cluster(q))
 		return 0;
 
 	if (bio->bi_seg_back_size + nxt->bi_seg_front_size >
-	    q->max_segment_size)
+	    queue_max_segment_size(q))
 		return 0;
 
 	if (!bio_has_data(bio))
 		return 1;
 
-	if (!BIOVEC_PHYS_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)))
+	bio_for_each_segment(end_bv, bio, iter)
+		if (end_bv.bv_len == iter.bi_size)
+			break;
+
+	nxt_bv = bio_iovec(nxt);
+
+	if (!BIOVEC_PHYS_MERGEABLE(&end_bv, &nxt_bv))
 		return 0;
 
 	/*
 	 * bio and nxt are contiguous in memory; check if the queue allows
 	 * these two to be merged into one
 	 */
-	if (BIO_SEG_BOUNDARY(q, bio, nxt))
+	if (BIOVEC_SEG_BOUNDARY(q, &end_bv, &nxt_bv))
 		return 1;
 
 	return 0;
 }
 
-/*
- * map a request to scatterlist, return number of sg entries setup. Caller
- * must make sure sg can hold rq->nr_phys_segments entries
- */
-int blk_rq_map_sg(struct request_queue *q, struct request *rq,
-		  struct scatterlist *sglist)
+static inline void
+__blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec,
+		     struct scatterlist *sglist, struct bio_vec *bvprv,
+		     struct scatterlist **sg, int *nsegs, int *cluster)
+{
+
+	int nbytes = bvec->bv_len;
+
+	if (*sg && *cluster) {
+		if ((*sg)->length + nbytes > queue_max_segment_size(q))
+			goto new_segment;
+
+		if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
+			goto new_segment;
+		if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bvec))
+			goto new_segment;
+
+		(*sg)->length += nbytes;
+	} else {
+new_segment:
+		if (!*sg)
+			*sg = sglist;
+		else {
+			/*
+			 * If the driver previously mapped a shorter
+			 * list, we could see a termination bit
+			 * prematurely unless it fully inits the sg
+			 * table on each mapping. We KNOW that there
+			 * must be more entries here or the driver
+			 * would be buggy, so force clear the
+			 * termination bit to avoid doing a full
+			 * sg_init_table() in drivers for each command.
+			 */
+			sg_unmark_end(*sg);
+			*sg = sg_next(*sg);
+		}
+
+		sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset);
+		(*nsegs)++;
+	}
+	*bvprv = *bvec;
+}
+
+static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
+			     struct scatterlist *sglist,
+			     struct scatterlist **sg)
 {
-	struct bio_vec *bvec, *bvprv;
-	struct req_iterator iter;
-	struct scatterlist *sg;
+	struct bio_vec bvec, bvprv = { NULL };
+	struct bvec_iter iter;
 	int nsegs, cluster;
 
 	nsegs = 0;
-	cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
+	cluster = blk_queue_cluster(q);
 
-	/*
-	 * for each bio in rq
-	 */
-	bvprv = NULL;
-	sg = NULL;
-	rq_for_each_segment(bvec, rq, iter) {
-		int nbytes = bvec->bv_len;
+	if (bio->bi_rw & REQ_DISCARD) {
+		/*
+		 * This is a hack - drivers should be neither modifying the
+		 * biovec, nor relying on bi_vcnt - but because of
+		 * blk_add_request_payload(), a discard bio may or may not have
+		 * a payload we need to set up here (thank you Christoph) and
+		 * bi_vcnt is really the only way of telling if we need to.
+		 */
 
-		if (bvprv && cluster) {
-			if (sg->length + nbytes > q->max_segment_size)
-				goto new_segment;
+		if (bio->bi_vcnt)
+			goto single_segment;
 
-			if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
-				goto new_segment;
-			if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bvec))
-				goto new_segment;
+		return 0;
+	}
 
-			sg->length += nbytes;
-		} else {
-new_segment:
-			if (!sg)
-				sg = sglist;
-			else {
-				/*
-				 * If the driver previously mapped a shorter
-				 * list, we could see a termination bit
-				 * prematurely unless it fully inits the sg
-				 * table on each mapping. We KNOW that there
-				 * must be more entries here or the driver
-				 * would be buggy, so force clear the
-				 * termination bit to avoid doing a full
-				 * sg_init_table() in drivers for each command.
-				 */
-				sg->page_link &= ~0x02;
-				sg = sg_next(sg);
-			}
+	if (bio->bi_rw & REQ_WRITE_SAME) {
+single_segment:
+		*sg = sglist;
+		bvec = bio_iovec(bio);
+		sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset);
+		return 1;
+	}
 
-			sg_set_page(sg, bvec->bv_page, nbytes, bvec->bv_offset);
-			nsegs++;
-		}
-		bvprv = bvec;
-	} /* segments in rq */
+	for_each_bio(bio)
+		bio_for_each_segment(bvec, bio, iter)
+			__blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg,
+					     &nsegs, &cluster);
+
+	return nsegs;
+}
+
+/*
+ * map a request to scatterlist, return number of sg entries setup. Caller
+ * must make sure sg can hold rq->nr_phys_segments entries
+ */
+int blk_rq_map_sg(struct request_queue *q, struct request *rq,
+		  struct scatterlist *sglist)
+{
+	struct scatterlist *sg = NULL;
+	int nsegs = 0;
 
+	if (rq->bio)
+		nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg);
 
 	if (unlikely(rq->cmd_flags & REQ_COPY_USER) &&
-	    (rq->data_len & q->dma_pad_mask)) {
-		unsigned int pad_len = (q->dma_pad_mask & ~rq->data_len) + 1;
+	    (blk_rq_bytes(rq) & q->dma_pad_mask)) {
+		unsigned int pad_len =
+			(q->dma_pad_mask & ~blk_rq_bytes(rq)) + 1;
 
 		sg->length += pad_len;
 		rq->extra_len += pad_len;
 	}
 
 	if (q->dma_drain_size && q->dma_drain_needed(rq)) {
-		if (rq->cmd_flags & REQ_RW)
+		if (rq->cmd_flags & REQ_WRITE)
 			memset(q->dma_drain_buffer, 0, q->dma_drain_size);
 
 		sg->page_link &= ~0x02;
@@ -227,19 +270,46 @@ new_segment:
 }
 EXPORT_SYMBOL(blk_rq_map_sg);
 
+/**
+ * blk_bio_map_sg - map a bio to a scatterlist
+ * @q: request_queue in question
+ * @bio: bio being mapped
+ * @sglist: scatterlist being mapped
+ *
+ * Note:
+ *    Caller must make sure sg can hold bio->bi_phys_segments entries
+ *
+ * Will return the number of sg entries setup
+ */
+int blk_bio_map_sg(struct request_queue *q, struct bio *bio,
+		   struct scatterlist *sglist)
+{
+	struct scatterlist *sg = NULL;
+	int nsegs;
+	struct bio *next = bio->bi_next;
+	bio->bi_next = NULL;
+
+	nsegs = __blk_bios_map_sg(q, bio, sglist, &sg);
+	bio->bi_next = next;
+	if (sg)
+		sg_mark_end(sg);
+
+	BUG_ON(bio->bi_phys_segments && nsegs > bio->bi_phys_segments);
+	return nsegs;
+}
+EXPORT_SYMBOL(blk_bio_map_sg);
+
 static inline int ll_new_hw_segment(struct request_queue *q,
 				    struct request *req,
 				    struct bio *bio)
 {
 	int nr_phys_segs = bio_phys_segments(q, bio);
 
-	if (req->nr_phys_segments + nr_phys_segs > q->max_hw_segments
-	    || req->nr_phys_segments + nr_phys_segs > q->max_phys_segments) {
-		req->cmd_flags |= REQ_NOMERGE;
-		if (req == q->last_merge)
-			q->last_merge = NULL;
-		return 0;
-	}
+	if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(q))
+		goto no_merge;
+
+	if (bio_integrity(bio) && blk_integrity_merge_bio(q, req, bio))
+		goto no_merge;
 
 	/*
 	 * This will form the start of a new hw segment.  Bump both
@@ -247,19 +317,19 @@ static inline int ll_new_hw_segment(struct request_queue *q,
 	 */
 	req->nr_phys_segments += nr_phys_segs;
 	return 1;
+
+no_merge:
+	req->cmd_flags |= REQ_NOMERGE;
+	if (req == q->last_merge)
+		q->last_merge = NULL;
+	return 0;
 }
 
 int ll_back_merge_fn(struct request_queue *q, struct request *req,
 		     struct bio *bio)
 {
-	unsigned short max_sectors;
-
-	if (unlikely(blk_pc_request(req)))
-		max_sectors = q->max_hw_sectors;
-	else
-		max_sectors = q->max_sectors;
-
-	if (req->nr_sectors + bio_sectors(bio) > max_sectors) {
+	if (blk_rq_sectors(req) + bio_sectors(bio) >
+	    blk_rq_get_max_sectors(req)) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -276,15 +346,8 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req,
 int ll_front_merge_fn(struct request_queue *q, struct request *req,
 		      struct bio *bio)
 {
-	unsigned short max_sectors;
-
-	if (unlikely(blk_pc_request(req)))
-		max_sectors = q->max_hw_sectors;
-	else
-		max_sectors = q->max_sectors;
-
-
-	if (req->nr_sectors + bio_sectors(bio) > max_sectors) {
+	if (blk_rq_sectors(req) + bio_sectors(bio) >
+	    blk_rq_get_max_sectors(req)) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -298,6 +361,17 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 	return ll_new_hw_segment(q, req, bio);
 }
 
+/*
+ * blk-mq uses req->special to carry normal driver per-request payload, it
+ * does not indicate a prepared command that we cannot merge with.
+ */
+static bool req_no_special_merge(struct request *req)
+{
+	struct request_queue *q = req->q;
+
+	return !q->mq_ops && req->special;
+}
+
 static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 				struct request *next)
 {
@@ -309,13 +383,14 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	 * First check if the either of the requests are re-queued
 	 * requests.  Can't merge them if they are.
 	 */
-	if (req->special || next->special)
+	if (req_no_special_merge(req) || req_no_special_merge(next))
 		return 0;
 
 	/*
 	 * Will it become too large?
 	 */
-	if ((req->nr_sectors + next->nr_sectors) > q->max_sectors)
+	if ((blk_rq_sectors(req) + blk_rq_sectors(next)) >
+	    blk_rq_get_max_sectors(req))
 		return 0;
 
 	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
@@ -327,10 +402,10 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 		total_phys_segments--;
 	}
 
-	if (total_phys_segments > q->max_phys_segments)
+	if (total_phys_segments > queue_max_segments(q))
 		return 0;
 
-	if (total_phys_segments > q->max_hw_segments)
+	if (blk_integrity_rq(req) && blk_integrity_merge_rq(q, req, next))
 		return 0;
 
 	/* Merge is OK... */
@@ -338,6 +413,53 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	return 1;
 }
 
+/**
+ * blk_rq_set_mixed_merge - mark a request as mixed merge
+ * @rq: request to mark as mixed merge
+ *
+ * Description:
+ *     @rq is about to be mixed merged.  Make sure the attributes
+ *     which can be mixed are set in each bio and mark @rq as mixed
+ *     merged.
+ */
+void blk_rq_set_mixed_merge(struct request *rq)
+{
+	unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
+	struct bio *bio;
+
+	if (rq->cmd_flags & REQ_MIXED_MERGE)
+		return;
+
+	/*
+	 * @rq will no longer represent mixable attributes for all the
+	 * contained bios.  It will just track those of the first one.
+	 * Distributes the attributs to each bio.
+	 */
+	for (bio = rq->bio; bio; bio = bio->bi_next) {
+		WARN_ON_ONCE((bio->bi_rw & REQ_FAILFAST_MASK) &&
+			     (bio->bi_rw & REQ_FAILFAST_MASK) != ff);
+		bio->bi_rw |= ff;
+	}
+	rq->cmd_flags |= REQ_MIXED_MERGE;
+}
+
+static void blk_account_io_merge(struct request *req)
+{
+	if (blk_do_io_stat(req)) {
+		struct hd_struct *part;
+		int cpu;
+
+		cpu = part_stat_lock();
+		part = req->part;
+
+		part_round_stats(cpu, part);
+		part_dec_in_flight(part, rq_data_dir(req));
+
+		hd_struct_put(part);
+		part_stat_unlock();
+	}
+}
+
 /*
  * Has to be called with the request spinlock acquired
  */
@@ -347,18 +469,22 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	if (!rq_mergeable(req) || !rq_mergeable(next))
 		return 0;
 
+	if (!blk_check_merge_flags(req->cmd_flags, next->cmd_flags))
+		return 0;
+
 	/*
 	 * not contiguous
 	 */
-	if (req->sector + req->nr_sectors != next->sector)
+	if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next))
 		return 0;
 
 	if (rq_data_dir(req) != rq_data_dir(next)
 	    || req->rq_disk != next->rq_disk
-	    || next->special)
+	    || req_no_special_merge(next))
 		return 0;
 
-	if (blk_integrity_rq(req) != blk_integrity_rq(next))
+	if (req->cmd_flags & REQ_WRITE_SAME &&
+	    !blk_write_same_mergeable(req->bio, next->bio))
 		return 0;
 
 	/*
@@ -371,6 +497,19 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 		return 0;
 
 	/*
+	 * If failfast settings disagree or any of the two is already
+	 * a mixed merge, mark both as mixed before proceeding.  This
+	 * makes sure that all involved bios have mixable attributes
+	 * set properly.
+	 */
+	if ((req->cmd_flags | next->cmd_flags) & REQ_MIXED_MERGE ||
+	    (req->cmd_flags & REQ_FAILFAST_MASK) !=
+	    (next->cmd_flags & REQ_FAILFAST_MASK)) {
+		blk_rq_set_mixed_merge(req);
+		blk_rq_set_mixed_merge(next);
+	}
+
+	/*
 	 * At this point we have either done a back merge
 	 * or front merge. We need the smaller start_time of
 	 * the merged requests to be the current request
@@ -382,27 +521,21 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	req->biotail->bi_next = next->bio;
 	req->biotail = next->biotail;
 
-	req->nr_sectors = req->hard_nr_sectors += next->hard_nr_sectors;
+	req->__data_len += blk_rq_bytes(next);
 
 	elv_merge_requests(q, req, next);
 
-	if (req->rq_disk) {
-		struct hd_struct *part;
-		int cpu;
-
-		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, req->sector);
-
-		part_round_stats(cpu, part);
-		part_dec_in_flight(part);
-
-		part_stat_unlock();
-	}
+	/*
+	 * 'next' is going away, so update stats accordingly
+	 */
+	blk_account_io_merge(next);
 
 	req->ioprio = ioprio_best(req->ioprio, next->ioprio);
 	if (blk_rq_cpu_valid(next))
 		req->cpu = next->cpu;
 
+	/* owner-ship of bio passed from next to req */
+	next->bio = NULL;
 	__blk_put_request(q, next);
 	return 1;
 }
@@ -426,3 +559,56 @@ int attempt_front_merge(struct request_queue *q, struct request *rq)
 
 	return 0;
 }
+
+int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
+			  struct request *next)
+{
+	return attempt_merge(q, rq, next);
+}
+
+bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
+{
+	struct request_queue *q = rq->q;
+
+	if (!rq_mergeable(rq) || !bio_mergeable(bio))
+		return false;
+
+	if (!blk_check_merge_flags(rq->cmd_flags, bio->bi_rw))
+		return false;
+
+	/* different data direction or already started, don't merge */
+	if (bio_data_dir(bio) != rq_data_dir(rq))
+		return false;
+
+	/* must be same device and not a special request */
+	if (rq->rq_disk != bio->bi_bdev->bd_disk || req_no_special_merge(rq))
+		return false;
+
+	/* only merge integrity protected bio into ditto rq */
+	if (bio_integrity(bio) != blk_integrity_rq(rq))
+		return false;
+
+	/* must be using the same buffer */
+	if (rq->cmd_flags & REQ_WRITE_SAME &&
+	    !blk_write_same_mergeable(rq->bio, bio))
+		return false;
+
+	if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS)) {
+		struct bio_vec *bprev;
+
+		bprev = &rq->biotail->bi_io_vec[bio->bi_vcnt - 1];
+		if (bvec_gap_to_prev(bprev, bio->bi_io_vec[0].bv_offset))
+			return false;
+	}
+
+	return true;
+}
+
+int blk_try_merge(struct request *rq, struct bio *bio)
+{
+	if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
+		return ELEVATOR_BACK_MERGE;
+	else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector)
+		return ELEVATOR_FRONT_MERGE;
+	return ELEVATOR_NO_MERGE;
+}