Merge branch 'for-3.7/core' of git://git.kernel.dk/linux-block

Pull block IO update from Jens Axboe:
 "Core block IO bits for 3.7.  Not a huge round this time, it contains:

   - First series from Kent cleaning up and generalizing bio allocation
     and freeing.

   - WRITE_SAME support from Martin.

   - Mikulas patches to prevent O_DIRECT crashes when someone changes
     the block size of a device.

   - Make bio_split() work on data-less bio's (like trim/discards).

   - A few other minor fixups."

Fixed up silent semantic mis-merge as per Mikulas Patocka and Andrew
Morton.  It is due to the VM no longer using a prio-tree (see commit
6b2dbba8b6ac: "mm: replace vma prio_tree with an interval tree").

So make set_blocksize() use mapping_mapped() instead of open-coding the
internal VM knowledge that has changed.

* 'for-3.7/core' of git://git.kernel.dk/linux-block: (26 commits)
  block: makes bio_split support bio without data
  scatterlist: refactor the sg_nents
  scatterlist: add sg_nents
  fs: fix include/percpu-rwsem.h export error
  percpu-rw-semaphore: fix documentation typos
  fs/block_dev.c:1644:5: sparse: symbol 'blkdev_mmap' was not declared
  blockdev: turn a rw semaphore into a percpu rw semaphore
  Fix a crash when block device is read and block size is changed at the same time
  block: fix request_queue->flags initialization
  block: lift the initial queue bypass mode on blk_register_queue() instead of blk_init_allocated_queue()
  block: ioctl to zero block ranges
  block: Make blkdev_issue_zeroout use WRITE SAME
  block: Implement support for WRITE SAME
  block: Consolidate command flag and queue limit checks for merges
  block: Clean up special command handling logic
  block/blk-tag.c: Remove useless kfree
  block: remove the duplicated setting for congestion_threshold
  block: reject invalid queue attribute values
  block: Add bio_clone_bioset(), bio_clone_kmalloc()
  block: Consolidate bio_alloc_bioset(), bio_kmalloc()
  ...

5 files changed, 27 insertions, 119 deletions

diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 664743d6a6cd..bbf459bca61d 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -798,14 +798,6 @@ static int crypt_convert(struct crypt_config *cc,
 	return 0;
 }
 
-static void dm_crypt_bio_destructor(struct bio *bio)
-{
-	struct dm_crypt_io *io = bio->bi_private;
-	struct crypt_config *cc = io->cc;
-
-	bio_free(bio, cc->bs);
-}
-
 /*
  * Generate a new unfragmented bio with the given size
  * This should never violate the device limitations
@@ -974,7 +966,6 @@ static void clone_init(struct dm_crypt_io *io, struct bio *clone)
 	clone->bi_end_io  = crypt_endio;
 	clone->bi_bdev    = cc->dev->bdev;
 	clone->bi_rw      = io->base_bio->bi_rw;
-	clone->bi_destructor = dm_crypt_bio_destructor;
 }
 
 static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
@@ -988,19 +979,14 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
 	 * copy the required bvecs because we need the original
 	 * one in order to decrypt the whole bio data *afterwards*.
 	 */
-	clone = bio_alloc_bioset(gfp, bio_segments(base_bio), cc->bs);
+	clone = bio_clone_bioset(base_bio, gfp, cc->bs);
 	if (!clone)
 		return 1;
 
 	crypt_inc_pending(io);
 
 	clone_init(io, clone);
-	clone->bi_idx = 0;
-	clone->bi_vcnt = bio_segments(base_bio);
-	clone->bi_size = base_bio->bi_size;
 	clone->bi_sector = cc->start + io->sector;
-	memcpy(clone->bi_io_vec, bio_iovec(base_bio),
-	       sizeof(struct bio_vec) * clone->bi_vcnt);
 
 	generic_make_request(clone);
 	return 0;
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index ea5dd289fe2a..1c46f97d6664 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -249,16 +249,6 @@ static void vm_dp_init(struct dpages *dp, void *data)
 	dp->context_ptr = data;
 }
 
-static void dm_bio_destructor(struct bio *bio)
-{
-	unsigned region;
-	struct io *io;
-
-	retrieve_io_and_region_from_bio(bio, &io, &region);
-
-	bio_free(bio, io->client->bios);
-}
-
 /*
  * Functions for getting the pages from kernel memory.
  */
@@ -317,7 +307,6 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 		bio->bi_sector = where->sector + (where->count - remaining);
 		bio->bi_bdev = where->bdev;
 		bio->bi_end_io = endio;
-		bio->bi_destructor = dm_bio_destructor;
 		store_io_and_region_in_bio(bio, io, region);
 
 		if (rw & REQ_DISCARD) {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 67ffa391edcf..66ceaff6455c 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -86,12 +86,17 @@ struct dm_rq_target_io {
 };
 
 /*
- * For request-based dm.
- * One of these is allocated per bio.
+ * For request-based dm - the bio clones we allocate are embedded in these
+ * structs.
+ *
+ * We allocate these with bio_alloc_bioset, using the front_pad parameter when
+ * the bioset is created - this means the bio has to come at the end of the
+ * struct.
  */
 struct dm_rq_clone_bio_info {
 	struct bio *orig;
 	struct dm_rq_target_io *tio;
+	struct bio clone;
 };
 
 union map_info *dm_get_mapinfo(struct bio *bio)
@@ -211,6 +216,11 @@ struct dm_md_mempools {
 static struct kmem_cache *_io_cache;
 static struct kmem_cache *_tio_cache;
 static struct kmem_cache *_rq_tio_cache;
+
+/*
+ * Unused now, and needs to be deleted. But since io_pool is overloaded and it's
+ * still used for _io_cache, I'm leaving this for a later cleanup
+ */
 static struct kmem_cache *_rq_bio_info_cache;
 
 static int __init local_init(void)
@@ -467,16 +477,6 @@ static void free_rq_tio(struct dm_rq_target_io *tio)
 	mempool_free(tio, tio->md->tio_pool);
 }
 
-static struct dm_rq_clone_bio_info *alloc_bio_info(struct mapped_device *md)
-{
-	return mempool_alloc(md->io_pool, GFP_ATOMIC);
-}
-
-static void free_bio_info(struct dm_rq_clone_bio_info *info)
-{
-	mempool_free(info, info->tio->md->io_pool);
-}
-
 static int md_in_flight(struct mapped_device *md)
 {
 	return atomic_read(&md->pending[READ]) +
@@ -681,11 +681,6 @@ static void clone_endio(struct bio *bio, int error)
 		}
 	}
 
-	/*
-	 * Store md for cleanup instead of tio which is about to get freed.
-	 */
-	bio->bi_private = md->bs;
-
 	free_tio(md, tio);
 	bio_put(bio);
 	dec_pending(io, error);
@@ -1036,11 +1031,6 @@ static void __map_bio(struct dm_target *ti, struct bio *clone,
 		/* error the io and bail out, or requeue it if needed */
 		md = tio->io->md;
 		dec_pending(tio->io, r);
-		/*
-		 * Store bio_set for cleanup.
-		 */
-		clone->bi_end_io = NULL;
-		clone->bi_private = md->bs;
 		bio_put(clone);
 		free_tio(md, tio);
 	} else if (r) {
@@ -1059,13 +1049,6 @@ struct clone_info {
 	unsigned short idx;
 };
 
-static void dm_bio_destructor(struct bio *bio)
-{
-	struct bio_set *bs = bio->bi_private;
-
-	bio_free(bio, bs);
-}
-
 /*
  * Creates a little bio that just does part of a bvec.
  */
@@ -1077,7 +1060,6 @@ static struct bio *split_bvec(struct bio *bio, sector_t sector,
 	struct bio_vec *bv = bio->bi_io_vec + idx;
 
 	clone = bio_alloc_bioset(GFP_NOIO, 1, bs);
-	clone->bi_destructor = dm_bio_destructor;
 	*clone->bi_io_vec = *bv;
 
 	clone->bi_sector = sector;
@@ -1090,7 +1072,7 @@ static struct bio *split_bvec(struct bio *bio, sector_t sector,
 	clone->bi_flags |= 1 << BIO_CLONED;
 
 	if (bio_integrity(bio)) {
-		bio_integrity_clone(clone, bio, GFP_NOIO, bs);
+		bio_integrity_clone(clone, bio, GFP_NOIO);
 		bio_integrity_trim(clone,
 				   bio_sector_offset(bio, idx, offset), len);
 	}
@@ -1109,7 +1091,6 @@ static struct bio *clone_bio(struct bio *bio, sector_t sector,
 
 	clone = bio_alloc_bioset(GFP_NOIO, bio->bi_max_vecs, bs);
 	__bio_clone(clone, bio);
-	clone->bi_destructor = dm_bio_destructor;
 	clone->bi_sector = sector;
 	clone->bi_idx = idx;
 	clone->bi_vcnt = idx + bv_count;
@@ -1117,7 +1098,7 @@ static struct bio *clone_bio(struct bio *bio, sector_t sector,
 	clone->bi_flags &= ~(1 << BIO_SEG_VALID);
 
 	if (bio_integrity(bio)) {
-		bio_integrity_clone(clone, bio, GFP_NOIO, bs);
+		bio_integrity_clone(clone, bio, GFP_NOIO);
 
 		if (idx != bio->bi_idx || clone->bi_size < bio->bi_size)
 			bio_integrity_trim(clone,
@@ -1152,9 +1133,8 @@ static void __issue_target_request(struct clone_info *ci, struct dm_target *ti,
 	 * ci->bio->bi_max_vecs is BIO_INLINE_VECS anyway, for both flush
 	 * and discard, so no need for concern about wasted bvec allocations.
 	 */
-	clone = bio_alloc_bioset(GFP_NOIO, ci->bio->bi_max_vecs, ci->md->bs);
-	__bio_clone(clone, ci->bio);
-	clone->bi_destructor = dm_bio_destructor;
+	clone = bio_clone_bioset(ci->bio, GFP_NOIO, ci->md->bs);
+
 	if (len) {
 		clone->bi_sector = ci->sector;
 		clone->bi_size = to_bytes(len);
@@ -1484,30 +1464,17 @@ void dm_dispatch_request(struct request *rq)
 }
 EXPORT_SYMBOL_GPL(dm_dispatch_request);
 
-static void dm_rq_bio_destructor(struct bio *bio)
-{
-	struct dm_rq_clone_bio_info *info = bio->bi_private;
-	struct mapped_device *md = info->tio->md;
-
-	free_bio_info(info);
-	bio_free(bio, md->bs);
-}
-
 static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
 				 void *data)
 {
 	struct dm_rq_target_io *tio = data;
-	struct mapped_device *md = tio->md;
-	struct dm_rq_clone_bio_info *info = alloc_bio_info(md);
-
-	if (!info)
-		return -ENOMEM;
+	struct dm_rq_clone_bio_info *info =
+		container_of(bio, struct dm_rq_clone_bio_info, clone);
 
 	info->orig = bio_orig;
 	info->tio = tio;
 	bio->bi_end_io = end_clone_bio;
 	bio->bi_private = info;
-	bio->bi_destructor = dm_rq_bio_destructor;
 
 	return 0;
 }
@@ -2771,7 +2738,10 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity)
 	if (!pools->tio_pool)
 		goto free_io_pool_and_out;
 
-	pools->bs = bioset_create(pool_size, 0);
+	pools->bs = (type == DM_TYPE_BIO_BASED) ?
+		bioset_create(pool_size, 0) :
+		bioset_create(pool_size,
+			      offsetof(struct dm_rq_clone_bio_info, clone));
 	if (!pools->bs)
 		goto free_tio_pool_and_out;
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 308e87b417e0..95c88012a3b9 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -155,32 +155,17 @@ static int start_readonly;
  * like bio_clone, but with a local bio set
  */
 
-static void mddev_bio_destructor(struct bio *bio)
-{
-	struct mddev *mddev, **mddevp;
-
-	mddevp = (void*)bio;
-	mddev = mddevp[-1];
-
-	bio_free(bio, mddev->bio_set);
-}
-
 struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
 			    struct mddev *mddev)
 {
 	struct bio *b;
-	struct mddev **mddevp;
 
 	if (!mddev || !mddev->bio_set)
 		return bio_alloc(gfp_mask, nr_iovecs);
 
-	b = bio_alloc_bioset(gfp_mask, nr_iovecs,
-			     mddev->bio_set);
+	b = bio_alloc_bioset(gfp_mask, nr_iovecs, mddev->bio_set);
 	if (!b)
 		return NULL;
-	mddevp = (void*)b;
-	mddevp[-1] = mddev;
-	b->bi_destructor = mddev_bio_destructor;
 	return b;
 }
 EXPORT_SYMBOL_GPL(bio_alloc_mddev);
@@ -188,32 +173,10 @@ EXPORT_SYMBOL_GPL(bio_alloc_mddev);
 struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask,
 			    struct mddev *mddev)
 {
-	struct bio *b;
-	struct mddev **mddevp;
-
 	if (!mddev || !mddev->bio_set)
 		return bio_clone(bio, gfp_mask);
 
-	b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs,
-			     mddev->bio_set);
-	if (!b)
-		return NULL;
-	mddevp = (void*)b;
-	mddevp[-1] = mddev;
-	b->bi_destructor = mddev_bio_destructor;
-	__bio_clone(b, bio);
-	if (bio_integrity(bio)) {
-		int ret;
-
-		ret = bio_integrity_clone(b, bio, gfp_mask, mddev->bio_set);
-
-		if (ret < 0) {
-			bio_put(b);
-			return NULL;
-		}
-	}
-
-	return b;
+	return bio_clone_bioset(bio, gfp_mask, mddev->bio_set);
 }
 EXPORT_SYMBOL_GPL(bio_clone_mddev);
 
@@ -5006,8 +4969,7 @@ int md_run(struct mddev *mddev)
 	}
 
 	if (mddev->bio_set == NULL)
-		mddev->bio_set = bioset_create(BIO_POOL_SIZE,
-					       sizeof(struct mddev *));
+		mddev->bio_set = bioset_create(BIO_POOL_SIZE, 0);
 
 	spin_lock(&pers_lock);
 	pers = find_pers(mddev->level, mddev->clevel);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index de63a1fc3737..a9e4fa95dfaa 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -422,6 +422,7 @@ 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);
 
 	/* if private is not null, we are here after takeover */
 	if (mddev->private == NULL) {