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
6b2dbba: "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()
  ...

Documentation/ABI/testing/sysfs-block

@@ -206,3 +206,17 @@ Description:
 		when a discarded area is read the discard_zeroes_data
 		parameter will be set to one. Otherwise it will be 0 and
 		the result of reading a discarded area is undefined.
+
+What:		/sys/block/<disk>/queue/write_same_max_bytes
+Date:		January 2012
+Contact:	Martin K. Petersen <[email protected]>
+Description:
+		Some devices support a write same operation in which a
+		single data block can be written to a range of several
+		contiguous blocks on storage. This can be used to wipe
+		areas on disk or to initialize drives in a RAID
+		configuration. write_same_max_bytes indicates how many
+		bytes can be written in a single write same command. If
+		write_same_max_bytes is 0, write same is not supported
+		by the device.
+

Documentation/block/biodoc.txt

@@ -465,7 +465,6 @@ struct bio {
        bio_end_io_t	*bi_end_io;  /* bi_end_io (bio) */
        atomic_t		bi_cnt;	     /* pin count: free when it hits zero */
        void             *bi_private;
-       bio_destructor_t *bi_destructor; /* bi_destructor (bio) */
 };
 
 With this multipage bio design:
@@ -647,10 +646,6 @@ for a non-clone bio. There are the 6 pools setup for different size biovecs,
 so bio_alloc(gfp_mask, nr_iovecs) will allocate a vec_list of the
 given size from these slabs.
 
-The bi_destructor() routine takes into account the possibility of the bio
-having originated from a different source (see later discussions on
-n/w to block transfers and kvec_cb)
-
 The bio_get() routine may be used to hold an extra reference on a bio prior
 to i/o submission, if the bio fields are likely to be accessed after the
 i/o is issued (since the bio may otherwise get freed in case i/o completion

Documentation/percpu-rw-semaphore.txt

@@ -0,0 +1,27 @@
+Percpu rw semaphores
+--------------------
+
+Percpu rw semaphores is a new read-write semaphore design that is
+optimized for locking for reading.
+
+The problem with traditional read-write semaphores is that when multiple
+cores take the lock for reading, the cache line containing the semaphore
+is bouncing between L1 caches of the cores, causing performance
+degradation.
+
+Locking for reading is very fast, it uses RCU and it avoids any atomic
+instruction in the lock and unlock path. On the other hand, locking for
+writing is very expensive, it calls synchronize_rcu() that can take
+hundreds of milliseconds.
+
+The lock is declared with "struct percpu_rw_semaphore" type.
+The lock is initialized percpu_init_rwsem, it returns 0 on success and
+-ENOMEM on allocation failure.
+The lock must be freed with percpu_free_rwsem to avoid memory leak.
+
+The lock is locked for read with percpu_down_read, percpu_up_read and
+for write with percpu_down_write, percpu_up_write.
+
+The idea of using RCU for optimized rw-lock was introduced by
+Eric Dumazet <[email protected]>.
+The code was written by Mikulas Patocka <[email protected]>

block/blk-core.c

@@ -606,8 +606,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	/*
 	 * A queue starts its life with bypass turned on to avoid
 	 * unnecessary bypass on/off overhead and nasty surprises during
-	 * init.  The initial bypass will be finished at the end of
-	 * blk_init_allocated_queue().
+	 * init.  The initial bypass will be finished when the queue is
+	 * registered by blk_register_queue().
 	 */
 	q->bypass_depth = 1;
 	__set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags);
@@ -694,7 +694,7 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	q->request_fn		= rfn;
 	q->prep_rq_fn		= NULL;
 	q->unprep_rq_fn		= NULL;
-	q->queue_flags		= QUEUE_FLAG_DEFAULT;
+	q->queue_flags		|= QUEUE_FLAG_DEFAULT;
 
 	/* Override internal queue lock with supplied lock pointer */
 	if (lock)
@@ -710,11 +710,6 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	/* init elevator */
 	if (elevator_init(q, NULL))
 		return NULL;
-
-	blk_queue_congestion_threshold(q);
-
-	/* all done, end the initial bypass */
-	blk_queue_bypass_end(q);
 	return q;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
@@ -1657,8 +1652,8 @@ generic_make_request_checks(struct bio *bio)
 		goto end_io;
 	}
 
-	if (unlikely(!(bio->bi_rw & REQ_DISCARD) &&
-		     nr_sectors > queue_max_hw_sectors(q))) {
+	if (likely(bio_is_rw(bio) &&
+		   nr_sectors > queue_max_hw_sectors(q))) {
 		printk(KERN_ERR "bio too big device %s (%u > %u)\n",
 		       bdevname(bio->bi_bdev, b),
 		       bio_sectors(bio),
@@ -1699,8 +1694,12 @@ generic_make_request_checks(struct bio *bio)
 
 	if ((bio->bi_rw & REQ_DISCARD) &&
 	    (!blk_queue_discard(q) ||
-	     ((bio->bi_rw & REQ_SECURE) &&
-	      !blk_queue_secdiscard(q)))) {
+	     ((bio->bi_rw & REQ_SECURE) && !blk_queue_secdiscard(q)))) {
+		err = -EOPNOTSUPP;
+		goto end_io;
+	}
+
+	if (bio->bi_rw & REQ_WRITE_SAME && !bdev_write_same(bio->bi_bdev)) {
 		err = -EOPNOTSUPP;
 		goto end_io;
 	}
@@ -1810,15 +1809,20 @@ EXPORT_SYMBOL(generic_make_request);
  */
 void submit_bio(int rw, struct bio *bio)
 {
-	int count = bio_sectors(bio);
-
 	bio->bi_rw |= rw;
 
 	/*
 	 * If it's a regular read/write or a barrier with data attached,
 	 * go through the normal accounting stuff before submission.
 	 */
-	if (bio_has_data(bio) && !(rw & REQ_DISCARD)) {
+	if (bio_has_data(bio)) {
+		unsigned int count;
+
+		if (unlikely(rw & REQ_WRITE_SAME))
+			count = bdev_logical_block_size(bio->bi_bdev) >> 9;
+		else
+			count = bio_sectors(bio);
+
 		if (rw & WRITE) {
 			count_vm_events(PGPGOUT, count);
 		} else {
@@ -1864,11 +1868,10 @@ EXPORT_SYMBOL(submit_bio);
  */
 int blk_rq_check_limits(struct request_queue *q, struct request *rq)
 {
-	if (rq->cmd_flags & REQ_DISCARD)
+	if (!rq_mergeable(rq))
 		return 0;
 
-	if (blk_rq_sectors(rq) > queue_max_sectors(q) ||
-	    blk_rq_bytes(rq) > queue_max_hw_sectors(q) << 9) {
+	if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, rq->cmd_flags)) {
 		printk(KERN_ERR "%s: over max size limit.\n", __func__);
 		return -EIO;
 	}
@@ -2340,7 +2343,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	req->buffer = bio_data(req->bio);
 
 	/* update sector only for requests with clear definition of sector */
-	if (req->cmd_type == REQ_TYPE_FS || (req->cmd_flags & REQ_DISCARD))
+	if (req->cmd_type == REQ_TYPE_FS)
 		req->__sector += total_bytes >> 9;
 
 	/* mixed attributes always follow the first bio */
@@ -2781,16 +2784,10 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 	blk_rq_init(NULL, rq);
 
 	__rq_for_each_bio(bio_src, rq_src) {
-		bio = bio_alloc_bioset(gfp_mask, bio_src->bi_max_vecs, bs);
+		bio = bio_clone_bioset(bio_src, gfp_mask, bs);
 		if (!bio)
 			goto free_and_out;
 
-		__bio_clone(bio, bio_src);
-
-		if (bio_integrity(bio_src) &&
-		    bio_integrity_clone(bio, bio_src, gfp_mask, bs))
-			goto free_and_out;
-
 		if (bio_ctr && bio_ctr(bio, bio_src, data))
 			goto free_and_out;
 
@@ -2807,7 +2804,7 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 
 free_and_out:
 	if (bio)
-		bio_free(bio, bs);
+		bio_put(bio);
 	blk_rq_unprep_clone(rq);
 
 	return -ENOMEM;

block/blk-lib.c

@@ -129,6 +129,80 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL(blkdev_issue_discard);
 
+/**
+ * blkdev_issue_write_same - queue a write same operation
+ * @bdev:	target blockdev
+ * @sector:	start sector
+ * @nr_sects:	number of sectors to write
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @page:	page containing data to write
+ *
+ * Description:
+ *    Issue a write same request for the sectors in question.
+ */
+int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
+			    sector_t nr_sects, gfp_t gfp_mask,
+			    struct page *page)
+{
+	DECLARE_COMPLETION_ONSTACK(wait);
+	struct request_queue *q = bdev_get_queue(bdev);
+	unsigned int max_write_same_sectors;
+	struct bio_batch bb;
+	struct bio *bio;
+	int ret = 0;
+
+	if (!q)
+		return -ENXIO;
+
+	max_write_same_sectors = q->limits.max_write_same_sectors;
+
+	if (max_write_same_sectors == 0)
+		return -EOPNOTSUPP;
+
+	atomic_set(&bb.done, 1);
+	bb.flags = 1 << BIO_UPTODATE;
+	bb.wait = &wait;
+
+	while (nr_sects) {
+		bio = bio_alloc(gfp_mask, 1);
+		if (!bio) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		bio->bi_sector = sector;
+		bio->bi_end_io = bio_batch_end_io;
+		bio->bi_bdev = bdev;
+		bio->bi_private = &bb;
+		bio->bi_vcnt = 1;
+		bio->bi_io_vec->bv_page = page;
+		bio->bi_io_vec->bv_offset = 0;
+		bio->bi_io_vec->bv_len = bdev_logical_block_size(bdev);
+
+		if (nr_sects > max_write_same_sectors) {
+			bio->bi_size = max_write_same_sectors << 9;
+			nr_sects -= max_write_same_sectors;
+			sector += max_write_same_sectors;
+		} else {
+			bio->bi_size = nr_sects << 9;
+			nr_sects = 0;
+		}
+
+		atomic_inc(&bb.done);
+		submit_bio(REQ_WRITE | REQ_WRITE_SAME, bio);
+	}
+
+	/* Wait for bios in-flight */
+	if (!atomic_dec_and_test(&bb.done))
+		wait_for_completion(&wait);
+
+	if (!test_bit(BIO_UPTODATE, &bb.flags))
+		ret = -ENOTSUPP;
+
+	return ret;
+}
+EXPORT_SYMBOL(blkdev_issue_write_same);
+
 /**
  * blkdev_issue_zeroout - generate number of zero filed write bios
  * @bdev:	blockdev to issue
@@ -140,7 +214,7 @@ EXPORT_SYMBOL(blkdev_issue_discard);
  *  Generate and issue number of bios with zerofiled pages.
  */
 
-int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
+int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 			sector_t nr_sects, gfp_t gfp_mask)
 {
 	int ret;
@@ -190,4 +264,32 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 
 	return ret;
 }
+
+/**
+ * blkdev_issue_zeroout - zero-fill a block range
+ * @bdev:	blockdev to write
+ * @sector:	start sector
+ * @nr_sects:	number of sectors to write
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ *
+ * Description:
+ *  Generate and issue number of bios with zerofiled pages.
+ */
+
+int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
+			 sector_t nr_sects, gfp_t gfp_mask)
+{
+	if (bdev_write_same(bdev)) {
+		unsigned char bdn[BDEVNAME_SIZE];
+
+		if (!blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
+					     ZERO_PAGE(0)))
+			return 0;
+
+		bdevname(bdev, bdn);
+		pr_err("%s: WRITE SAME failed. Manually zeroing.\n", bdn);
+	}
+
+	return __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask);
+}
 EXPORT_SYMBOL(blkdev_issue_zeroout);