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()
...
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index e85c04b..a3f28f3 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -70,23 +70,25 @@
}
/**
- * bio_integrity_alloc_bioset - Allocate integrity payload and attach it to bio
+ * bio_integrity_alloc - Allocate integrity payload and attach it to bio
* @bio: bio to attach integrity metadata to
* @gfp_mask: Memory allocation mask
* @nr_vecs: Number of integrity metadata scatter-gather elements
- * @bs: bio_set to allocate from
*
* Description: This function prepares a bio for attaching integrity
* metadata. nr_vecs specifies the maximum number of pages containing
* integrity metadata that can be attached.
*/
-struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *bio,
- gfp_t gfp_mask,
- unsigned int nr_vecs,
- struct bio_set *bs)
+struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
+ gfp_t gfp_mask,
+ unsigned int nr_vecs)
{
struct bio_integrity_payload *bip;
unsigned int idx = vecs_to_idx(nr_vecs);
+ struct bio_set *bs = bio->bi_pool;
+
+ if (!bs)
+ bs = fs_bio_set;
BUG_ON(bio == NULL);
bip = NULL;
@@ -114,37 +116,22 @@
return bip;
}
-EXPORT_SYMBOL(bio_integrity_alloc_bioset);
-
-/**
- * bio_integrity_alloc - Allocate integrity payload and attach it to bio
- * @bio: bio to attach integrity metadata to
- * @gfp_mask: Memory allocation mask
- * @nr_vecs: Number of integrity metadata scatter-gather elements
- *
- * Description: This function prepares a bio for attaching integrity
- * metadata. nr_vecs specifies the maximum number of pages containing
- * integrity metadata that can be attached.
- */
-struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
- gfp_t gfp_mask,
- unsigned int nr_vecs)
-{
- return bio_integrity_alloc_bioset(bio, gfp_mask, nr_vecs, fs_bio_set);
-}
EXPORT_SYMBOL(bio_integrity_alloc);
/**
* bio_integrity_free - Free bio integrity payload
* @bio: bio containing bip to be freed
- * @bs: bio_set this bio was allocated from
*
* Description: Used to free the integrity portion of a bio. Usually
* called from bio_free().
*/
-void bio_integrity_free(struct bio *bio, struct bio_set *bs)
+void bio_integrity_free(struct bio *bio)
{
struct bio_integrity_payload *bip = bio->bi_integrity;
+ struct bio_set *bs = bio->bi_pool;
+
+ if (!bs)
+ bs = fs_bio_set;
BUG_ON(bip == NULL);
@@ -730,19 +717,18 @@
* @bio: New bio
* @bio_src: Original bio
* @gfp_mask: Memory allocation mask
- * @bs: bio_set to allocate bip from
*
* Description: Called to allocate a bip when cloning a bio
*/
int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
- gfp_t gfp_mask, struct bio_set *bs)
+ gfp_t gfp_mask)
{
struct bio_integrity_payload *bip_src = bio_src->bi_integrity;
struct bio_integrity_payload *bip;
BUG_ON(bip_src == NULL);
- bip = bio_integrity_alloc_bioset(bio, gfp_mask, bip_src->bip_vcnt, bs);
+ bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt);
if (bip == NULL)
return -EIO;
diff --git a/fs/bio.c b/fs/bio.c
index 71072ab..9298c65 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -55,6 +55,7 @@
* IO code that does not need private memory pools.
*/
struct bio_set *fs_bio_set;
+EXPORT_SYMBOL(fs_bio_set);
/*
* Our slab pool management
@@ -233,26 +234,37 @@
return bvl;
}
-void bio_free(struct bio *bio, struct bio_set *bs)
+static void __bio_free(struct bio *bio)
{
- void *p;
-
- if (bio_has_allocated_vec(bio))
- bvec_free_bs(bs, bio->bi_io_vec, BIO_POOL_IDX(bio));
+ bio_disassociate_task(bio);
if (bio_integrity(bio))
- bio_integrity_free(bio, bs);
+ bio_integrity_free(bio);
+}
- /*
- * If we have front padding, adjust the bio pointer before freeing
- */
- p = bio;
- if (bs->front_pad)
+static void bio_free(struct bio *bio)
+{
+ struct bio_set *bs = bio->bi_pool;
+ void *p;
+
+ __bio_free(bio);
+
+ if (bs) {
+ if (bio_has_allocated_vec(bio))
+ bvec_free_bs(bs, bio->bi_io_vec, BIO_POOL_IDX(bio));
+
+ /*
+ * If we have front padding, adjust the bio pointer before freeing
+ */
+ p = bio;
p -= bs->front_pad;
- mempool_free(p, bs->bio_pool);
+ mempool_free(p, bs->bio_pool);
+ } else {
+ /* Bio was allocated by bio_kmalloc() */
+ kfree(bio);
+ }
}
-EXPORT_SYMBOL(bio_free);
void bio_init(struct bio *bio)
{
@@ -263,48 +275,85 @@
EXPORT_SYMBOL(bio_init);
/**
+ * bio_reset - reinitialize a bio
+ * @bio: bio to reset
+ *
+ * Description:
+ * After calling bio_reset(), @bio will be in the same state as a freshly
+ * allocated bio returned bio bio_alloc_bioset() - the only fields that are
+ * preserved are the ones that are initialized by bio_alloc_bioset(). See
+ * comment in struct bio.
+ */
+void bio_reset(struct bio *bio)
+{
+ unsigned long flags = bio->bi_flags & (~0UL << BIO_RESET_BITS);
+
+ __bio_free(bio);
+
+ memset(bio, 0, BIO_RESET_BYTES);
+ bio->bi_flags = flags|(1 << BIO_UPTODATE);
+}
+EXPORT_SYMBOL(bio_reset);
+
+/**
* bio_alloc_bioset - allocate a bio for I/O
* @gfp_mask: the GFP_ mask given to the slab allocator
* @nr_iovecs: number of iovecs to pre-allocate
* @bs: the bio_set to allocate from.
*
* Description:
- * bio_alloc_bioset will try its own mempool to satisfy the allocation.
- * If %__GFP_WAIT is set then we will block on the internal pool waiting
- * for a &struct bio to become free.
+ * If @bs is NULL, uses kmalloc() to allocate the bio; else the allocation is
+ * backed by the @bs's mempool.
*
- * Note that the caller must set ->bi_destructor on successful return
- * of a bio, to do the appropriate freeing of the bio once the reference
- * count drops to zero.
- **/
+ * When @bs is not NULL, if %__GFP_WAIT is set then bio_alloc will always be
+ * able to allocate a bio. This is due to the mempool guarantees. To make this
+ * work, callers must never allocate more than 1 bio at a time from this pool.
+ * Callers that need to allocate more than 1 bio must always submit the
+ * previously allocated bio for IO before attempting to allocate a new one.
+ * Failure to do so can cause deadlocks under memory pressure.
+ *
+ * RETURNS:
+ * Pointer to new bio on success, NULL on failure.
+ */
struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
{
+ unsigned front_pad;
+ unsigned inline_vecs;
unsigned long idx = BIO_POOL_NONE;
struct bio_vec *bvl = NULL;
struct bio *bio;
void *p;
- p = mempool_alloc(bs->bio_pool, gfp_mask);
+ if (!bs) {
+ if (nr_iovecs > UIO_MAXIOV)
+ return NULL;
+
+ p = kmalloc(sizeof(struct bio) +
+ nr_iovecs * sizeof(struct bio_vec),
+ gfp_mask);
+ front_pad = 0;
+ inline_vecs = nr_iovecs;
+ } else {
+ p = mempool_alloc(bs->bio_pool, gfp_mask);
+ front_pad = bs->front_pad;
+ inline_vecs = BIO_INLINE_VECS;
+ }
+
if (unlikely(!p))
return NULL;
- bio = p + bs->front_pad;
+ bio = p + front_pad;
bio_init(bio);
- if (unlikely(!nr_iovecs))
- goto out_set;
-
- if (nr_iovecs <= BIO_INLINE_VECS) {
- bvl = bio->bi_inline_vecs;
- nr_iovecs = BIO_INLINE_VECS;
- } else {
+ if (nr_iovecs > inline_vecs) {
bvl = bvec_alloc_bs(gfp_mask, nr_iovecs, &idx, bs);
if (unlikely(!bvl))
goto err_free;
-
- nr_iovecs = bvec_nr_vecs(idx);
+ } else if (nr_iovecs) {
+ bvl = bio->bi_inline_vecs;
}
-out_set:
+
+ bio->bi_pool = bs;
bio->bi_flags |= idx << BIO_POOL_OFFSET;
bio->bi_max_vecs = nr_iovecs;
bio->bi_io_vec = bvl;
@@ -316,80 +365,6 @@
}
EXPORT_SYMBOL(bio_alloc_bioset);
-static void bio_fs_destructor(struct bio *bio)
-{
- bio_free(bio, fs_bio_set);
-}
-
-/**
- * bio_alloc - allocate a new bio, memory pool backed
- * @gfp_mask: allocation mask to use
- * @nr_iovecs: number of iovecs
- *
- * bio_alloc will allocate a bio and associated bio_vec array that can hold
- * at least @nr_iovecs entries. Allocations will be done from the
- * fs_bio_set. Also see @bio_alloc_bioset and @bio_kmalloc.
- *
- * If %__GFP_WAIT is set, then bio_alloc will always be able to allocate
- * a bio. This is due to the mempool guarantees. To make this work, callers
- * must never allocate more than 1 bio at a time from this pool. Callers
- * that need to allocate more than 1 bio must always submit the previously
- * allocated bio for IO before attempting to allocate a new one. Failure to
- * do so can cause livelocks under memory pressure.
- *
- * RETURNS:
- * Pointer to new bio on success, NULL on failure.
- */
-struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
-{
- struct bio *bio = bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set);
-
- if (bio)
- bio->bi_destructor = bio_fs_destructor;
-
- return bio;
-}
-EXPORT_SYMBOL(bio_alloc);
-
-static void bio_kmalloc_destructor(struct bio *bio)
-{
- if (bio_integrity(bio))
- bio_integrity_free(bio, fs_bio_set);
- kfree(bio);
-}
-
-/**
- * bio_kmalloc - allocate a bio for I/O using kmalloc()
- * @gfp_mask: the GFP_ mask given to the slab allocator
- * @nr_iovecs: number of iovecs to pre-allocate
- *
- * Description:
- * Allocate a new bio with @nr_iovecs bvecs. If @gfp_mask contains
- * %__GFP_WAIT, the allocation is guaranteed to succeed.
- *
- **/
-struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
-{
- struct bio *bio;
-
- if (nr_iovecs > UIO_MAXIOV)
- return NULL;
-
- bio = kmalloc(sizeof(struct bio) + nr_iovecs * sizeof(struct bio_vec),
- gfp_mask);
- if (unlikely(!bio))
- return NULL;
-
- bio_init(bio);
- bio->bi_flags |= BIO_POOL_NONE << BIO_POOL_OFFSET;
- bio->bi_max_vecs = nr_iovecs;
- bio->bi_io_vec = bio->bi_inline_vecs;
- bio->bi_destructor = bio_kmalloc_destructor;
-
- return bio;
-}
-EXPORT_SYMBOL(bio_kmalloc);
-
void zero_fill_bio(struct bio *bio)
{
unsigned long flags;
@@ -420,11 +395,8 @@
/*
* last put frees it
*/
- if (atomic_dec_and_test(&bio->bi_cnt)) {
- bio_disassociate_task(bio);
- bio->bi_next = NULL;
- bio->bi_destructor(bio);
- }
+ if (atomic_dec_and_test(&bio->bi_cnt))
+ bio_free(bio);
}
EXPORT_SYMBOL(bio_put);
@@ -466,26 +438,28 @@
EXPORT_SYMBOL(__bio_clone);
/**
- * bio_clone - clone a bio
+ * bio_clone_bioset - clone a bio
* @bio: bio to clone
* @gfp_mask: allocation priority
+ * @bs: bio_set to allocate from
*
* Like __bio_clone, only also allocates the returned bio
*/
-struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
+struct bio *bio_clone_bioset(struct bio *bio, gfp_t gfp_mask,
+ struct bio_set *bs)
{
- struct bio *b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, fs_bio_set);
+ struct bio *b;
+ b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, bs);
if (!b)
return NULL;
- b->bi_destructor = bio_fs_destructor;
__bio_clone(b, bio);
if (bio_integrity(bio)) {
int ret;
- ret = bio_integrity_clone(b, bio, gfp_mask, fs_bio_set);
+ ret = bio_integrity_clone(b, bio, gfp_mask);
if (ret < 0) {
bio_put(b);
@@ -495,7 +469,7 @@
return b;
}
-EXPORT_SYMBOL(bio_clone);
+EXPORT_SYMBOL(bio_clone_bioset);
/**
* bio_get_nr_vecs - return approx number of vecs
@@ -1501,7 +1475,7 @@
trace_block_split(bdev_get_queue(bi->bi_bdev), bi,
bi->bi_sector + first_sectors);
- BUG_ON(bi->bi_vcnt != 1);
+ BUG_ON(bi->bi_vcnt != 1 && bi->bi_vcnt != 0);
BUG_ON(bi->bi_idx != 0);
atomic_set(&bp->cnt, 3);
bp->error = 0;
@@ -1511,17 +1485,22 @@
bp->bio2.bi_size -= first_sectors << 9;
bp->bio1.bi_size = first_sectors << 9;
- bp->bv1 = bi->bi_io_vec[0];
- bp->bv2 = bi->bi_io_vec[0];
- bp->bv2.bv_offset += first_sectors << 9;
- bp->bv2.bv_len -= first_sectors << 9;
- bp->bv1.bv_len = first_sectors << 9;
+ if (bi->bi_vcnt != 0) {
+ bp->bv1 = bi->bi_io_vec[0];
+ bp->bv2 = bi->bi_io_vec[0];
- bp->bio1.bi_io_vec = &bp->bv1;
- bp->bio2.bi_io_vec = &bp->bv2;
+ if (bio_is_rw(bi)) {
+ bp->bv2.bv_offset += first_sectors << 9;
+ bp->bv2.bv_len -= first_sectors << 9;
+ bp->bv1.bv_len = first_sectors << 9;
+ }
- bp->bio1.bi_max_vecs = 1;
- bp->bio2.bi_max_vecs = 1;
+ bp->bio1.bi_io_vec = &bp->bv1;
+ bp->bio2.bi_io_vec = &bp->bv2;
+
+ bp->bio1.bi_max_vecs = 1;
+ bp->bio2.bi_max_vecs = 1;
+ }
bp->bio1.bi_end_io = bio_pair_end_1;
bp->bio2.bi_end_io = bio_pair_end_2;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 38e721b..b3c1d3d 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -116,6 +116,8 @@
int set_blocksize(struct block_device *bdev, int size)
{
+ struct address_space *mapping;
+
/* Size must be a power of two, and between 512 and PAGE_SIZE */
if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size))
return -EINVAL;
@@ -124,6 +126,19 @@
if (size < bdev_logical_block_size(bdev))
return -EINVAL;
+ /* Prevent starting I/O or mapping the device */
+ percpu_down_write(&bdev->bd_block_size_semaphore);
+
+ /* Check that the block device is not memory mapped */
+ mapping = bdev->bd_inode->i_mapping;
+ mutex_lock(&mapping->i_mmap_mutex);
+ if (mapping_mapped(mapping)) {
+ mutex_unlock(&mapping->i_mmap_mutex);
+ percpu_up_write(&bdev->bd_block_size_semaphore);
+ return -EBUSY;
+ }
+ mutex_unlock(&mapping->i_mmap_mutex);
+
/* Don't change the size if it is same as current */
if (bdev->bd_block_size != size) {
sync_blockdev(bdev);
@@ -131,6 +146,9 @@
bdev->bd_inode->i_blkbits = blksize_bits(size);
kill_bdev(bdev);
}
+
+ percpu_up_write(&bdev->bd_block_size_semaphore);
+
return 0;
}
@@ -441,6 +459,12 @@
struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL);
if (!ei)
return NULL;
+
+ if (unlikely(percpu_init_rwsem(&ei->bdev.bd_block_size_semaphore))) {
+ kmem_cache_free(bdev_cachep, ei);
+ return NULL;
+ }
+
return &ei->vfs_inode;
}
@@ -449,6 +473,8 @@
struct inode *inode = container_of(head, struct inode, i_rcu);
struct bdev_inode *bdi = BDEV_I(inode);
+ percpu_free_rwsem(&bdi->bdev.bd_block_size_semaphore);
+
kmem_cache_free(bdev_cachep, bdi);
}
@@ -1567,6 +1593,22 @@
return blkdev_ioctl(bdev, mode, cmd, arg);
}
+ssize_t blkdev_aio_read(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
+{
+ ssize_t ret;
+ struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
+
+ percpu_down_read(&bdev->bd_block_size_semaphore);
+
+ ret = generic_file_aio_read(iocb, iov, nr_segs, pos);
+
+ percpu_up_read(&bdev->bd_block_size_semaphore);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(blkdev_aio_read);
+
/*
* Write data to the block device. Only intended for the block device itself
* and the raw driver which basically is a fake block device.
@@ -1578,12 +1620,16 @@
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
+ struct block_device *bdev = I_BDEV(file->f_mapping->host);
struct blk_plug plug;
ssize_t ret;
BUG_ON(iocb->ki_pos != pos);
blk_start_plug(&plug);
+
+ percpu_down_read(&bdev->bd_block_size_semaphore);
+
ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
if (ret > 0 || ret == -EIOCBQUEUED) {
ssize_t err;
@@ -1592,11 +1638,29 @@
if (err < 0 && ret > 0)
ret = err;
}
+
+ percpu_up_read(&bdev->bd_block_size_semaphore);
+
blk_finish_plug(&plug);
+
return ret;
}
EXPORT_SYMBOL_GPL(blkdev_aio_write);
+static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ int ret;
+ struct block_device *bdev = I_BDEV(file->f_mapping->host);
+
+ percpu_down_read(&bdev->bd_block_size_semaphore);
+
+ ret = generic_file_mmap(file, vma);
+
+ percpu_up_read(&bdev->bd_block_size_semaphore);
+
+ return ret;
+}
+
/*
* Try to release a page associated with block device when the system
* is under memory pressure.
@@ -1627,9 +1691,9 @@
.llseek = block_llseek,
.read = do_sync_read,
.write = do_sync_write,
- .aio_read = generic_file_aio_read,
+ .aio_read = blkdev_aio_read,
.aio_write = blkdev_aio_write,
- .mmap = generic_file_mmap,
+ .mmap = blkdev_mmap,
.fsync = blkdev_fsync,
.unlocked_ioctl = block_ioctl,
#ifdef CONFIG_COMPAT
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index 1585db1..f936cb5 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -814,8 +814,8 @@
struct bio *bio;
if (per_dev != master_dev) {
- bio = bio_kmalloc(GFP_KERNEL,
- master_dev->bio->bi_max_vecs);
+ bio = bio_clone_kmalloc(master_dev->bio,
+ GFP_KERNEL);
if (unlikely(!bio)) {
ORE_DBGMSG(
"Failed to allocate BIO size=%u\n",
@@ -824,7 +824,6 @@
goto out;
}
- __bio_clone(bio, master_dev->bio);
bio->bi_bdev = NULL;
bio->bi_next = NULL;
per_dev->offset = master_dev->offset;