1 files changed, 169 insertions, 124 deletions

diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 7294bd115e3..407a99e46f6 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -88,10 +88,11 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	char b[BDEVNAME_SIZE];
 	char b2[BDEVNAME_SIZE];
 	struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
+	bool discard_supported = false;
 
 	if (!conf)
 		return -ENOMEM;
-	list_for_each_entry(rdev1, &mddev->disks, same_set) {
+	rdev_for_each(rdev1, mddev) {
 		pr_debug("md/raid0:%s: looking at %s\n",
 			 mdname(mddev),
 			 bdevname(rdev1->bdev, b));
@@ -102,7 +103,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 		sector_div(sectors, mddev->chunk_sectors);
 		rdev1->sectors = sectors * mddev->chunk_sectors;
 
-		list_for_each_entry(rdev2, &mddev->disks, same_set) {
+		rdev_for_each(rdev2, mddev) {
 			pr_debug("md/raid0:%s:   comparing %s(%llu)"
 				 " with %s(%llu)\n",
 				 mdname(mddev),
@@ -157,7 +158,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	smallest = NULL;
 	dev = conf->devlist;
 	err = -EINVAL;
-	list_for_each_entry(rdev1, &mddev->disks, same_set) {
+	rdev_for_each(rdev1, mddev) {
 		int j = rdev1->raid_disk;
 
 		if (mddev->level == 10) {
@@ -174,7 +175,13 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 			rdev1->new_raid_disk = j;
 		}
 
-		if (j < 0 || j >= mddev->raid_disks) {
+		if (j < 0) {
+			printk(KERN_ERR
+			       "md/raid0:%s: remove inactive devices before converting to RAID0\n",
+			       mdname(mddev));
+			goto abort;
+		}
+		if (j >= mddev->raid_disks) {
 			printk(KERN_ERR "md/raid0:%s: bad disk number %d - "
 			       "aborting!\n", mdname(mddev), j);
 			goto abort;
@@ -188,19 +195,16 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 
 		disk_stack_limits(mddev->gendisk, rdev1->bdev,
 				  rdev1->data_offset << 9);
-		/* as we don't honour merge_bvec_fn, we must never risk
-		 * violating it, so limit ->max_segments to 1, lying within
-		 * a single page.
-		 */
-
-		if (rdev1->bdev->bd_disk->queue->merge_bvec_fn) {
-			blk_queue_max_segments(mddev->queue, 1);
-			blk_queue_segment_boundary(mddev->queue,
-						   PAGE_CACHE_SIZE - 1);
-		}
+
+		if (rdev1->bdev->bd_disk->queue->merge_bvec_fn)
+			conf->has_merge_bvec = 1;
+
 		if (!smallest || (rdev1->sectors < smallest->sectors))
 			smallest = rdev1;
 		cnt++;
+
+		if (blk_queue_discard(bdev_get_queue(rdev1->bdev)))
+			discard_supported = true;
 	}
 	if (cnt != mddev->raid_disks) {
 		printk(KERN_ERR "md/raid0:%s: too few disks (%d of %d) - "
@@ -278,6 +282,11 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	blk_queue_io_opt(mddev->queue,
 			 (mddev->chunk_sectors << 9) * mddev->raid_disks);
 
+	if (!discard_supported)
+		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+	else
+		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+
 	pr_debug("md/raid0:%s: done.\n", mdname(mddev));
 	*private_conf = conf;
 
@@ -286,12 +295,68 @@ abort:
 	kfree(conf->strip_zone);
 	kfree(conf->devlist);
 	kfree(conf);
-	*private_conf = NULL;
+	*private_conf = ERR_PTR(err);
 	return err;
 }
 
+/* Find the zone which holds a particular offset
+ * Update *sectorp to be an offset in that zone
+ */
+static struct strip_zone *find_zone(struct r0conf *conf,
+				    sector_t *sectorp)
+{
+	int i;
+	struct strip_zone *z = conf->strip_zone;
+	sector_t sector = *sectorp;
+
+	for (i = 0; i < conf->nr_strip_zones; i++)
+		if (sector < z[i].zone_end) {
+			if (i)
+				*sectorp = sector - z[i-1].zone_end;
+			return z + i;
+		}
+	BUG();
+}
+
+/*
+ * remaps the bio to the target device. we separate two flows.
+ * power 2 flow and a general flow for the sake of perfromance
+*/
+static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone,
+				sector_t sector, sector_t *sector_offset)
+{
+	unsigned int sect_in_chunk;
+	sector_t chunk;
+	struct r0conf *conf = mddev->private;
+	int raid_disks = conf->strip_zone[0].nb_dev;
+	unsigned int chunk_sects = mddev->chunk_sectors;
+
+	if (is_power_of_2(chunk_sects)) {
+		int chunksect_bits = ffz(~chunk_sects);
+		/* find the sector offset inside the chunk */
+		sect_in_chunk  = sector & (chunk_sects - 1);
+		sector >>= chunksect_bits;
+		/* chunk in zone */
+		chunk = *sector_offset;
+		/* quotient is the chunk in real device*/
+		sector_div(chunk, zone->nb_dev << chunksect_bits);
+	} else{
+		sect_in_chunk = sector_div(sector, chunk_sects);
+		chunk = *sector_offset;
+		sector_div(chunk, chunk_sects * zone->nb_dev);
+	}
+	/*
+	*  position the bio over the real device
+	*  real sector = chunk in device + starting of zone
+	*	+ the position in the chunk
+	*/
+	*sector_offset = (chunk * chunk_sects) + sect_in_chunk;
+	return conf->devlist[(zone - conf->strip_zone)*raid_disks
+			     + sector_div(sector, zone->nb_dev)];
+}
+
 /**
- *	raid0_mergeable_bvec -- tell bio layer if a two requests can be merged
+ *	raid0_mergeable_bvec -- tell bio layer if two requests can be merged
  *	@q: request queue
  *	@bvm: properties of new bio
  *	@biovec: the request that could be merged to it.
@@ -303,10 +368,15 @@ static int raid0_mergeable_bvec(struct request_queue *q,
 				struct bio_vec *biovec)
 {
 	struct mddev *mddev = q->queuedata;
+	struct r0conf *conf = mddev->private;
 	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
+	sector_t sector_offset = sector;
 	int max;
 	unsigned int chunk_sectors = mddev->chunk_sectors;
 	unsigned int bio_sectors = bvm->bi_size >> 9;
+	struct strip_zone *zone;
+	struct md_rdev *rdev;
+	struct request_queue *subq;
 
 	if (is_power_of_2(chunk_sectors))
 		max =  (chunk_sectors - ((sector & (chunk_sectors-1))
@@ -314,10 +384,27 @@ static int raid0_mergeable_bvec(struct request_queue *q,
 	else
 		max =  (chunk_sectors - (sector_div(sector, chunk_sectors)
 						+ bio_sectors)) << 9;
-	if (max < 0) max = 0; /* bio_add cannot handle a negative return */
+	if (max < 0)
+		max = 0; /* bio_add cannot handle a negative return */
 	if (max <= biovec->bv_len && bio_sectors == 0)
 		return biovec->bv_len;
-	else 
+	if (max < biovec->bv_len)
+		/* too small already, no need to check further */
+		return max;
+	if (!conf->has_merge_bvec)
+		return max;
+
+	/* May need to check subordinate device */
+	sector = sector_offset;
+	zone = find_zone(mddev->private, &sector_offset);
+	rdev = map_sector(mddev, zone, sector, &sector_offset);
+	subq = bdev_get_queue(rdev->bdev);
+	if (subq->merge_bvec_fn) {
+		bvm->bi_bdev = rdev->bdev;
+		bvm->bi_sector = sector_offset + zone->dev_start +
+			rdev->data_offset;
+		return min(max, subq->merge_bvec_fn(subq, bvm, biovec));
+	} else
 		return max;
 }
 
@@ -329,12 +416,15 @@ static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks
 	WARN_ONCE(sectors || raid_disks,
 		  "%s does not support generic reshape\n", __func__);
 
-	list_for_each_entry(rdev, &mddev->disks, same_set)
-		array_sectors += rdev->sectors;
+	rdev_for_each(rdev, mddev)
+		array_sectors += (rdev->sectors &
+				  ~(sector_t)(mddev->chunk_sectors-1));
 
 	return array_sectors;
 }
 
+static int raid0_stop(struct mddev *mddev);
+
 static int raid0_run(struct mddev *mddev)
 {
 	struct r0conf *conf;
@@ -348,6 +438,8 @@ static int raid0_run(struct mddev *mddev)
 	if (md_check_no_bitmap(mddev))
 		return -EINVAL;
 	blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
+	blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
+	blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors);
 
 	/* if private is not null, we are here after takeover */
 	if (mddev->private == NULL) {
@@ -382,7 +474,12 @@ static int raid0_run(struct mddev *mddev)
 
 	blk_queue_merge_bvec(mddev->queue, raid0_mergeable_bvec);
 	dump_zones(mddev);
-	return md_integrity_register(mddev);
+
+	ret = md_integrity_register(mddev);
+	if (ret)
+		raid0_stop(mddev);
+
+	return ret;
 }
 
 static int raid0_stop(struct mddev *mddev)
@@ -397,62 +494,6 @@ static int raid0_stop(struct mddev *mddev)
 	return 0;
 }
 
-/* Find the zone which holds a particular offset
- * Update *sectorp to be an offset in that zone
- */
-static struct strip_zone *find_zone(struct r0conf *conf,
-				    sector_t *sectorp)
-{
-	int i;
-	struct strip_zone *z = conf->strip_zone;
-	sector_t sector = *sectorp;
-
-	for (i = 0; i < conf->nr_strip_zones; i++)
-		if (sector < z[i].zone_end) {
-			if (i)
-				*sectorp = sector - z[i-1].zone_end;
-			return z + i;
-		}
-	BUG();
-}
-
-/*
- * remaps the bio to the target device. we separate two flows.
- * power 2 flow and a general flow for the sake of perfromance
-*/
-static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone,
-				sector_t sector, sector_t *sector_offset)
-{
-	unsigned int sect_in_chunk;
-	sector_t chunk;
-	struct r0conf *conf = mddev->private;
-	int raid_disks = conf->strip_zone[0].nb_dev;
-	unsigned int chunk_sects = mddev->chunk_sectors;
-
-	if (is_power_of_2(chunk_sects)) {
-		int chunksect_bits = ffz(~chunk_sects);
-		/* find the sector offset inside the chunk */
-		sect_in_chunk  = sector & (chunk_sects - 1);
-		sector >>= chunksect_bits;
-		/* chunk in zone */
-		chunk = *sector_offset;
-		/* quotient is the chunk in real device*/
-		sector_div(chunk, zone->nb_dev << chunksect_bits);
-	} else{
-		sect_in_chunk = sector_div(sector, chunk_sects);
-		chunk = *sector_offset;
-		sector_div(chunk, chunk_sects * zone->nb_dev);
-	}
-	/*
-	*  position the bio over the real device
-	*  real sector = chunk in device + starting of zone
-	*	+ the position in the chunk
-	*/
-	*sector_offset = (chunk * chunk_sects) + sect_in_chunk;
-	return conf->devlist[(zone - conf->strip_zone)*raid_disks
-			     + sector_div(sector, zone->nb_dev)];
-}
-
 /*
  * Is io distribute over 1 or more chunks ?
 */
@@ -460,69 +501,56 @@ static inline int is_io_in_chunk_boundary(struct mddev *mddev,
 			unsigned int chunk_sects, struct bio *bio)
 {
 	if (likely(is_power_of_2(chunk_sects))) {
-		return chunk_sects >= ((bio->bi_sector & (chunk_sects-1))
-					+ (bio->bi_size >> 9));
+		return chunk_sects >=
+			((bio->bi_iter.bi_sector & (chunk_sects-1))
+					+ bio_sectors(bio));
 	} else{
-		sector_t sector = bio->bi_sector;
+		sector_t sector = bio->bi_iter.bi_sector;
 		return chunk_sects >= (sector_div(sector, chunk_sects)
-						+ (bio->bi_size >> 9));
+						+ bio_sectors(bio));
 	}
 }
 
 static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 {
-	unsigned int chunk_sects;
-	sector_t sector_offset;
 	struct strip_zone *zone;
 	struct md_rdev *tmp_dev;
+	struct bio *split;
 
 	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
 		md_flush_request(mddev, bio);
 		return;
 	}
 
-	chunk_sects = mddev->chunk_sectors;
-	if (unlikely(!is_io_in_chunk_boundary(mddev, chunk_sects, bio))) {
-		sector_t sector = bio->bi_sector;
-		struct bio_pair *bp;
-		/* Sanity check -- queue functions should prevent this happening */
-		if (bio->bi_vcnt != 1 ||
-		    bio->bi_idx != 0)
-			goto bad_map;
-		/* This is a one page bio that upper layers
-		 * refuse to split for us, so we need to split it.
-		 */
-		if (likely(is_power_of_2(chunk_sects)))
-			bp = bio_split(bio, chunk_sects - (sector &
-							   (chunk_sects-1)));
-		else
-			bp = bio_split(bio, chunk_sects -
-				       sector_div(sector, chunk_sects));
-		raid0_make_request(mddev, &bp->bio1);
-		raid0_make_request(mddev, &bp->bio2);
-		bio_pair_release(bp);
-		return;
-	}
+	do {
+		sector_t sector = bio->bi_iter.bi_sector;
+		unsigned chunk_sects = mddev->chunk_sectors;
 
-	sector_offset = bio->bi_sector;
-	zone =  find_zone(mddev->private, &sector_offset);
-	tmp_dev = map_sector(mddev, zone, bio->bi_sector,
-			     &sector_offset);
-	bio->bi_bdev = tmp_dev->bdev;
-	bio->bi_sector = sector_offset + zone->dev_start +
-		tmp_dev->data_offset;
-
-	generic_make_request(bio);
-	return;
+		unsigned sectors = chunk_sects -
+			(likely(is_power_of_2(chunk_sects))
+			 ? (sector & (chunk_sects-1))
+			 : sector_div(sector, chunk_sects));
 
-bad_map:
-	printk("md/raid0:%s: make_request bug: can't convert block across chunks"
-	       " or bigger than %dk %llu %d\n",
-	       mdname(mddev), chunk_sects / 2,
-	       (unsigned long long)bio->bi_sector, bio->bi_size >> 10);
+		if (sectors < bio_sectors(bio)) {
+			split = bio_split(bio, sectors, GFP_NOIO, fs_bio_set);
+			bio_chain(split, bio);
+		} else {
+			split = bio;
+		}
 
-	bio_io_error(bio);
-	return;
+		zone = find_zone(mddev->private, &sector);
+		tmp_dev = map_sector(mddev, zone, sector, &sector);
+		split->bi_bdev = tmp_dev->bdev;
+		split->bi_iter.bi_sector = sector + zone->dev_start +
+			tmp_dev->data_offset;
+
+		if (unlikely((split->bi_rw & REQ_DISCARD) &&
+			 !blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
+			/* Just ignore it */
+			bio_endio(split, 0);
+		} else
+			generic_make_request(split);
+	} while (split != bio);
 }
 
 static void raid0_status(struct seq_file *seq, struct mddev *mddev)
@@ -543,13 +571,14 @@ static void *raid0_takeover_raid45(struct mddev *mddev)
 		return ERR_PTR(-EINVAL);
 	}
 
-	list_for_each_entry(rdev, &mddev->disks, same_set) {
+	rdev_for_each(rdev, mddev) {
 		/* check slot number for a disk */
 		if (rdev->raid_disk == mddev->raid_disks-1) {
 			printk(KERN_ERR "md/raid0:%s: raid5 must have missing parity disk!\n",
 			       mdname(mddev));
 			return ERR_PTR(-EINVAL);
 		}
+		rdev->sectors = mddev->dev_sectors;
 	}
 
 	/* Set new parameters */
@@ -609,6 +638,7 @@ static void *raid0_takeover_raid10(struct mddev *mddev)
 static void *raid0_takeover_raid1(struct mddev *mddev)
 {
 	struct r0conf *priv_conf;
+	int chunksect;
 
 	/* Check layout:
 	 *  - (N - 1) mirror drives must be already faulty
@@ -619,10 +649,25 @@ static void *raid0_takeover_raid1(struct mddev *mddev)
 		return ERR_PTR(-EINVAL);
 	}
 
+	/*
+	 * a raid1 doesn't have the notion of chunk size, so
+	 * figure out the largest suitable size we can use.
+	 */
+	chunksect = 64 * 2; /* 64K by default */
+
+	/* The array must be an exact multiple of chunksize */
+	while (chunksect && (mddev->array_sectors & (chunksect - 1)))
+		chunksect >>= 1;
+
+	if ((chunksect << 9) < PAGE_SIZE)
+		/* array size does not allow a suitable chunk size */
+		return ERR_PTR(-EINVAL);
+
 	/* Set new parameters */
 	mddev->new_level = 0;
 	mddev->new_layout = 0;
-	mddev->new_chunk_sectors = 128; /* by default set chunk size to 64k */
+	mddev->new_chunk_sectors = chunksect;
+	mddev->chunk_sectors = chunksect;
 	mddev->delta_disks = 1 - mddev->raid_disks;
 	mddev->raid_disks = 1;
 	/* make sure it will be not marked as dirty */