summaryrefslogtreecommitdiff
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/bio-integrity.c11
-rw-r--r--block/bio.c229
-rw-r--r--block/blk-cgroup.c6
-rw-r--r--block/blk-core.c36
-rw-r--r--block/blk-flush.c15
-rw-r--r--block/blk-lib.c77
-rw-r--r--block/blk-map.c4
-rw-r--r--block/blk-merge.c171
-rw-r--r--block/blk-mq-sysfs.c25
-rw-r--r--block/blk-mq-tag.c4
-rw-r--r--block/blk-mq-tag.h12
-rw-r--r--block/blk-mq.c26
-rw-r--r--block/blk-settings.c48
-rw-r--r--block/blk-sysfs.c43
-rw-r--r--block/blk.h6
-rw-r--r--block/bounce.c27
-rw-r--r--block/genhd.c9
-rw-r--r--block/partition-generic.c12
18 files changed, 442 insertions, 319 deletions
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 719b7152aed1..4aecca79374a 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -355,13 +355,12 @@ static void bio_integrity_verify_fn(struct work_struct *work)
container_of(work, struct bio_integrity_payload, bip_work);
struct bio *bio = bip->bip_bio;
struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
- int error;
- error = bio_integrity_process(bio, bi->verify_fn);
+ bio->bi_error = bio_integrity_process(bio, bi->verify_fn);
/* Restore original bio completion handler */
bio->bi_end_io = bip->bip_end_io;
- bio_endio(bio, error);
+ bio_endio(bio);
}
/**
@@ -376,7 +375,7 @@ static void bio_integrity_verify_fn(struct work_struct *work)
* in process context. This function postpones completion
* accordingly.
*/
-void bio_integrity_endio(struct bio *bio, int error)
+void bio_integrity_endio(struct bio *bio)
{
struct bio_integrity_payload *bip = bio_integrity(bio);
@@ -386,9 +385,9 @@ void bio_integrity_endio(struct bio *bio, int error)
* integrity metadata. Restore original bio end_io handler
* and run it.
*/
- if (error) {
+ if (bio->bi_error) {
bio->bi_end_io = bip->bip_end_io;
- bio_endio(bio, error);
+ bio_endio(bio);
return;
}
diff --git a/block/bio.c b/block/bio.c
index 2a00d349cd68..515b5434fe2d 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -269,7 +269,6 @@ static void bio_free(struct bio *bio)
void bio_init(struct bio *bio)
{
memset(bio, 0, sizeof(*bio));
- bio->bi_flags = 1 << BIO_UPTODATE;
atomic_set(&bio->__bi_remaining, 1);
atomic_set(&bio->__bi_cnt, 1);
}
@@ -292,14 +291,17 @@ void bio_reset(struct bio *bio)
__bio_free(bio);
memset(bio, 0, BIO_RESET_BYTES);
- bio->bi_flags = flags | (1 << BIO_UPTODATE);
+ bio->bi_flags = flags;
atomic_set(&bio->__bi_remaining, 1);
}
EXPORT_SYMBOL(bio_reset);
-static void bio_chain_endio(struct bio *bio, int error)
+static void bio_chain_endio(struct bio *bio)
{
- bio_endio(bio->bi_private, error);
+ struct bio *parent = bio->bi_private;
+
+ parent->bi_error = bio->bi_error;
+ bio_endio(parent);
bio_put(bio);
}
@@ -309,7 +311,7 @@ static void bio_chain_endio(struct bio *bio, int error)
*/
static inline void bio_inc_remaining(struct bio *bio)
{
- bio->bi_flags |= (1 << BIO_CHAIN);
+ bio_set_flag(bio, BIO_CHAIN);
smp_mb__before_atomic();
atomic_inc(&bio->__bi_remaining);
}
@@ -493,7 +495,7 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
if (unlikely(!bvl))
goto err_free;
- bio->bi_flags |= 1 << BIO_OWNS_VEC;
+ bio_set_flag(bio, BIO_OWNS_VEC);
} else if (nr_iovecs) {
bvl = bio->bi_inline_vecs;
}
@@ -578,7 +580,7 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
* so we don't set nor calculate new physical/hw segment counts here
*/
bio->bi_bdev = bio_src->bi_bdev;
- bio->bi_flags |= 1 << BIO_CLONED;
+ bio_set_flag(bio, BIO_CLONED);
bio->bi_rw = bio_src->bi_rw;
bio->bi_iter = bio_src->bi_iter;
bio->bi_io_vec = bio_src->bi_io_vec;
@@ -692,31 +694,22 @@ integrity_clone:
EXPORT_SYMBOL(bio_clone_bioset);
/**
- * bio_get_nr_vecs - return approx number of vecs
- * @bdev: I/O target
+ * bio_add_pc_page - attempt to add page to bio
+ * @q: the target queue
+ * @bio: destination bio
+ * @page: page to add
+ * @len: vec entry length
+ * @offset: vec entry offset
+ *
+ * Attempt to add a page to the bio_vec maplist. This can fail for a
+ * number of reasons, such as the bio being full or target block device
+ * limitations. The target block device must allow bio's up to PAGE_SIZE,
+ * so it is always possible to add a single page to an empty bio.
*
- * Return the approximate number of pages we can send to this target.
- * There's no guarantee that you will be able to fit this number of pages
- * into a bio, it does not account for dynamic restrictions that vary
- * on offset.
+ * This should only be used by REQ_PC bios.
*/
-int bio_get_nr_vecs(struct block_device *bdev)
-{
- struct request_queue *q = bdev_get_queue(bdev);
- int nr_pages;
-
- nr_pages = min_t(unsigned,
- queue_max_segments(q),
- queue_max_sectors(q) / (PAGE_SIZE >> 9) + 1);
-
- return min_t(unsigned, nr_pages, BIO_MAX_PAGES);
-
-}
-EXPORT_SYMBOL(bio_get_nr_vecs);
-
-static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
- *page, unsigned int len, unsigned int offset,
- unsigned int max_sectors)
+int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page
+ *page, unsigned int len, unsigned int offset)
{
int retried_segments = 0;
struct bio_vec *bvec;
@@ -727,7 +720,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
if (unlikely(bio_flagged(bio, BIO_CLONED)))
return 0;
- if (((bio->bi_iter.bi_size + len) >> 9) > max_sectors)
+ if (((bio->bi_iter.bi_size + len) >> 9) > queue_max_hw_sectors(q))
return 0;
/*
@@ -740,28 +733,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
if (page == prev->bv_page &&
offset == prev->bv_offset + prev->bv_len) {
- unsigned int prev_bv_len = prev->bv_len;
prev->bv_len += len;
-
- if (q->merge_bvec_fn) {
- struct bvec_merge_data bvm = {
- /* prev_bvec is already charged in
- bi_size, discharge it in order to
- simulate merging updated prev_bvec
- as new bvec. */
- .bi_bdev = bio->bi_bdev,
- .bi_sector = bio->bi_iter.bi_sector,
- .bi_size = bio->bi_iter.bi_size -
- prev_bv_len,
- .bi_rw = bio->bi_rw,
- };
-
- if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len) {
- prev->bv_len -= len;
- return 0;
- }
- }
-
bio->bi_iter.bi_size += len;
goto done;
}
@@ -770,8 +742,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
* If the queue doesn't support SG gaps and adding this
* offset would create a gap, disallow it.
*/
- if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS) &&
- bvec_gap_to_prev(prev, offset))
+ if (bvec_gap_to_prev(q, prev, offset))
return 0;
}
@@ -804,30 +775,9 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
blk_recount_segments(q, bio);
}
- /*
- * if queue has other restrictions (eg varying max sector size
- * depending on offset), it can specify a merge_bvec_fn in the
- * queue to get further control
- */
- if (q->merge_bvec_fn) {
- struct bvec_merge_data bvm = {
- .bi_bdev = bio->bi_bdev,
- .bi_sector = bio->bi_iter.bi_sector,
- .bi_size = bio->bi_iter.bi_size - len,
- .bi_rw = bio->bi_rw,
- };
-
- /*
- * merge_bvec_fn() returns number of bytes it can accept
- * at this offset
- */
- if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len)
- goto failed;
- }
-
/* If we may be able to merge these biovecs, force a recount */
if (bio->bi_vcnt > 1 && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
- bio->bi_flags &= ~(1 << BIO_SEG_VALID);
+ bio_clear_flag(bio, BIO_SEG_VALID);
done:
return len;
@@ -841,28 +791,6 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
blk_recount_segments(q, bio);
return 0;
}
-
-/**
- * bio_add_pc_page - attempt to add page to bio
- * @q: the target queue
- * @bio: destination bio
- * @page: page to add
- * @len: vec entry length
- * @offset: vec entry offset
- *
- * Attempt to add a page to the bio_vec maplist. This can fail for a
- * number of reasons, such as the bio being full or target block device
- * limitations. The target block device must allow bio's up to PAGE_SIZE,
- * so it is always possible to add a single page to an empty bio.
- *
- * This should only be used by REQ_PC bios.
- */
-int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page,
- unsigned int len, unsigned int offset)
-{
- return __bio_add_page(q, bio, page, len, offset,
- queue_max_hw_sectors(q));
-}
EXPORT_SYMBOL(bio_add_pc_page);
/**
@@ -872,22 +800,47 @@ EXPORT_SYMBOL(bio_add_pc_page);
* @len: vec entry length
* @offset: vec entry offset
*
- * Attempt to add a page to the bio_vec maplist. This can fail for a
- * number of reasons, such as the bio being full or target block device
- * limitations. The target block device must allow bio's up to PAGE_SIZE,
- * so it is always possible to add a single page to an empty bio.
+ * Attempt to add a page to the bio_vec maplist. This will only fail
+ * if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio.
*/
-int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
- unsigned int offset)
+int bio_add_page(struct bio *bio, struct page *page,
+ unsigned int len, unsigned int offset)
{
- struct request_queue *q = bdev_get_queue(bio->bi_bdev);
- unsigned int max_sectors;
+ struct bio_vec *bv;
+
+ /*
+ * cloned bio must not modify vec list
+ */
+ if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
+ return 0;
+
+ /*
+ * For filesystems with a blocksize smaller than the pagesize
+ * we will often be called with the same page as last time and
+ * a consecutive offset. Optimize this special case.
+ */
+ if (bio->bi_vcnt > 0) {
+ bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
+
+ if (page == bv->bv_page &&
+ offset == bv->bv_offset + bv->bv_len) {
+ bv->bv_len += len;
+ goto done;
+ }
+ }
+
+ if (bio->bi_vcnt >= bio->bi_max_vecs)
+ return 0;
- max_sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
- if ((max_sectors < (len >> 9)) && !bio->bi_iter.bi_size)
- max_sectors = len >> 9;
+ bv = &bio->bi_io_vec[bio->bi_vcnt];
+ bv->bv_page = page;
+ bv->bv_len = len;
+ bv->bv_offset = offset;
- return __bio_add_page(q, bio, page, len, offset, max_sectors);
+ bio->bi_vcnt++;
+done:
+ bio->bi_iter.bi_size += len;
+ return len;
}
EXPORT_SYMBOL(bio_add_page);
@@ -896,11 +849,11 @@ struct submit_bio_ret {
int error;
};
-static void submit_bio_wait_endio(struct bio *bio, int error)
+static void submit_bio_wait_endio(struct bio *bio)
{
struct submit_bio_ret *ret = bio->bi_private;
- ret->error = error;
+ ret->error = bio->bi_error;
complete(&ret->event);
}
@@ -1388,7 +1341,7 @@ struct bio *bio_map_user_iov(struct request_queue *q,
if (iter->type & WRITE)
bio->bi_rw |= REQ_WRITE;
- bio->bi_flags |= (1 << BIO_USER_MAPPED);
+ bio_set_flag(bio, BIO_USER_MAPPED);
/*
* subtle -- if __bio_map_user() ended up bouncing a bio,
@@ -1445,7 +1398,7 @@ void bio_unmap_user(struct bio *bio)
}
EXPORT_SYMBOL(bio_unmap_user);
-static void bio_map_kern_endio(struct bio *bio, int err)
+static void bio_map_kern_endio(struct bio *bio)
{
bio_put(bio);
}
@@ -1501,13 +1454,13 @@ struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
}
EXPORT_SYMBOL(bio_map_kern);
-static void bio_copy_kern_endio(struct bio *bio, int err)
+static void bio_copy_kern_endio(struct bio *bio)
{
bio_free_pages(bio);
bio_put(bio);
}
-static void bio_copy_kern_endio_read(struct bio *bio, int err)
+static void bio_copy_kern_endio_read(struct bio *bio)
{
char *p = bio->bi_private;
struct bio_vec *bvec;
@@ -1518,7 +1471,7 @@ static void bio_copy_kern_endio_read(struct bio *bio, int err)
p += bvec->bv_len;
}
- bio_copy_kern_endio(bio, err);
+ bio_copy_kern_endio(bio);
}
/**
@@ -1768,7 +1721,7 @@ static inline bool bio_remaining_done(struct bio *bio)
BUG_ON(atomic_read(&bio->__bi_remaining) <= 0);
if (atomic_dec_and_test(&bio->__bi_remaining)) {
- clear_bit(BIO_CHAIN, &bio->bi_flags);
+ bio_clear_flag(bio, BIO_CHAIN);
return true;
}
@@ -1778,25 +1731,15 @@ static inline bool bio_remaining_done(struct bio *bio)
/**
* bio_endio - end I/O on a bio
* @bio: bio
- * @error: error, if any
*
* Description:
- * bio_endio() will end I/O on the whole bio. bio_endio() is the
- * preferred way to end I/O on a bio, it takes care of clearing
- * BIO_UPTODATE on error. @error is 0 on success, and and one of the
- * established -Exxxx (-EIO, for instance) error values in case
- * something went wrong. No one should call bi_end_io() directly on a
- * bio unless they own it and thus know that it has an end_io
- * function.
+ * bio_endio() will end I/O on the whole bio. bio_endio() is the preferred
+ * way to end I/O on a bio. No one should call bi_end_io() directly on a
+ * bio unless they own it and thus know that it has an end_io function.
**/
-void bio_endio(struct bio *bio, int error)
+void bio_endio(struct bio *bio)
{
while (bio) {
- if (error)
- clear_bit(BIO_UPTODATE, &bio->bi_flags);
- else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
- error = -EIO;
-
if (unlikely(!bio_remaining_done(bio)))
break;
@@ -1810,11 +1753,12 @@ void bio_endio(struct bio *bio, int error)
*/
if (bio->bi_end_io == bio_chain_endio) {
struct bio *parent = bio->bi_private;
+ parent->bi_error = bio->bi_error;
bio_put(bio);
bio = parent;
} else {
if (bio->bi_end_io)
- bio->bi_end_io(bio, error);
+ bio->bi_end_io(bio);
bio = NULL;
}
}
@@ -1831,8 +1775,9 @@ EXPORT_SYMBOL(bio_endio);
* Allocates and returns a new bio which represents @sectors from the start of
* @bio, and updates @bio to represent the remaining sectors.
*
- * The newly allocated bio will point to @bio's bi_io_vec; it is the caller's
- * responsibility to ensure that @bio is not freed before the split.
+ * Unless this is a discard request the newly allocated bio will point
+ * to @bio's bi_io_vec; it is the caller's responsibility to ensure that
+ * @bio is not freed before the split.
*/
struct bio *bio_split(struct bio *bio, int sectors,
gfp_t gfp, struct bio_set *bs)
@@ -1842,7 +1787,15 @@ struct bio *bio_split(struct bio *bio, int sectors,
BUG_ON(sectors <= 0);
BUG_ON(sectors >= bio_sectors(bio));
- split = bio_clone_fast(bio, gfp, bs);
+ /*
+ * Discards need a mutable bio_vec to accommodate the payload
+ * required by the DSM TRIM and UNMAP commands.
+ */
+ if (bio->bi_rw & REQ_DISCARD)
+ split = bio_clone_bioset(bio, gfp, bs);
+ else
+ split = bio_clone_fast(bio, gfp, bs);
+
if (!split)
return NULL;
@@ -1873,7 +1826,7 @@ void bio_trim(struct bio *bio, int offset, int size)
if (offset == 0 && size == bio->bi_iter.bi_size)
return;
- clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+ bio_clear_flag(bio, BIO_SEG_VALID);
bio_advance(bio, offset << 9);
@@ -2009,6 +1962,7 @@ int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css)
bio->bi_css = blkcg_css;
return 0;
}
+EXPORT_SYMBOL_GPL(bio_associate_blkcg);
/**
* bio_associate_current - associate a bio with %current
@@ -2039,6 +1993,7 @@ int bio_associate_current(struct bio *bio)
bio->bi_css = task_get_css(current, blkio_cgrp_id);
return 0;
}
+EXPORT_SYMBOL_GPL(bio_associate_current);
/**
* bio_disassociate_task - undo bio_associate_current()
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 9da02c021ebe..d6283b3f5db5 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -718,8 +718,12 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
return -EINVAL;
disk = get_gendisk(MKDEV(major, minor), &part);
- if (!disk || part)
+ if (!disk)
return -EINVAL;
+ if (part) {
+ put_disk(disk);
+ return -EINVAL;
+ }
rcu_read_lock();
spin_lock_irq(disk->queue->queue_lock);
diff --git a/block/blk-core.c b/block/blk-core.c
index 627ed0c593fb..60912e983f16 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -143,18 +143,16 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
unsigned int nbytes, int error)
{
if (error)
- clear_bit(BIO_UPTODATE, &bio->bi_flags);
- else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
- error = -EIO;
+ bio->bi_error = error;
if (unlikely(rq->cmd_flags & REQ_QUIET))
- set_bit(BIO_QUIET, &bio->bi_flags);
+ bio_set_flag(bio, BIO_QUIET);
bio_advance(bio, nbytes);
/* don't actually finish bio if it's part of flush sequence */
if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
- bio_endio(bio, error);
+ bio_endio(bio);
}
void blk_dump_rq_flags(struct request *rq, char *msg)
@@ -645,6 +643,10 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
if (q->id < 0)
goto fail_q;
+ q->bio_split = bioset_create(BIO_POOL_SIZE, 0);
+ if (!q->bio_split)
+ goto fail_id;
+
q->backing_dev_info.ra_pages =
(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
q->backing_dev_info.capabilities = BDI_CAP_CGROUP_WRITEBACK;
@@ -653,7 +655,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
err = bdi_init(&q->backing_dev_info);
if (err)
- goto fail_id;
+ goto fail_split;
setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
laptop_mode_timer_fn, (unsigned long) q);
@@ -695,6 +697,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
fail_bdi:
bdi_destroy(&q->backing_dev_info);
+fail_split:
+ bioset_free(q->bio_split);
fail_id:
ida_simple_remove(&blk_queue_ida, q->id);
fail_q:
@@ -1612,6 +1616,8 @@ static void blk_queue_bio(struct request_queue *q, struct bio *bio)
struct request *req;
unsigned int request_count = 0;
+ blk_queue_split(q, &bio, q->bio_split);
+
/*
* low level driver can indicate that it wants pages above a
* certain limit bounced to low memory (ie for highmem, or even
@@ -1620,7 +1626,8 @@ static void blk_queue_bio(struct request_queue *q, struct bio *bio)
blk_queue_bounce(q, &bio);
if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
- bio_endio(bio, -EIO);
+ bio->bi_error = -EIO;
+ bio_endio(bio);
return;
}
@@ -1673,7 +1680,8 @@ get_rq:
*/
req = get_request(q, rw_flags, bio, GFP_NOIO);
if (IS_ERR(req)) {
- bio_endio(bio, PTR_ERR(req)); /* @q is dead */
+ bio->bi_error = PTR_ERR(req);
+ bio_endio(bio);
goto out_unlock;
}
@@ -1832,15 +1840,6 @@ generic_make_request_checks(struct bio *bio)
goto end_io;
}
- 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),
- queue_max_hw_sectors(q));
- goto end_io;
- }
-
part = bio->bi_bdev->bd_part;
if (should_fail_request(part, bio->bi_iter.bi_size) ||
should_fail_request(&part_to_disk(part)->part0,
@@ -1896,7 +1895,8 @@ generic_make_request_checks(struct bio *bio)
return true;
end_io:
- bio_endio(bio, err);
+ bio->bi_error = err;
+ bio_endio(bio);
return false;
}
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 20badd7b9d1b..9c423e53324a 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -73,6 +73,7 @@
#include "blk.h"
#include "blk-mq.h"
+#include "blk-mq-tag.h"
/* FLUSH/FUA sequences */
enum {
@@ -226,7 +227,12 @@ static void flush_end_io(struct request *flush_rq, int error)
struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx);
if (q->mq_ops) {
+ struct blk_mq_hw_ctx *hctx;
+
+ /* release the tag's ownership to the req cloned from */
spin_lock_irqsave(&fq->mq_flush_lock, flags);
+ hctx = q->mq_ops->map_queue(q, flush_rq->mq_ctx->cpu);
+ blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq);
flush_rq->tag = -1;
}
@@ -308,11 +314,18 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
/*
* Borrow tag from the first request since they can't
- * be in flight at the same time.
+ * be in flight at the same time. And acquire the tag's
+ * ownership for flush req.
*/
if (q->mq_ops) {
+ struct blk_mq_hw_ctx *hctx;
+
flush_rq->mq_ctx = first_rq->mq_ctx;
flush_rq->tag = first_rq->tag;
+ fq->orig_rq = first_rq;
+
+ hctx = q->mq_ops->map_queue(q, first_rq->mq_ctx->cpu);
+ blk_mq_tag_set_rq(hctx, first_rq->tag, flush_rq);
}
flush_rq->cmd_type = REQ_TYPE_FS;
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 7688ee3f5d72..bd40292e5009 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -11,21 +11,28 @@
struct bio_batch {
atomic_t done;
- unsigned long flags;
+ int error;
struct completion *wait;
};
-static void bio_batch_end_io(struct bio *bio, int err)
+static void bio_batch_end_io(struct bio *bio)
{
struct bio_batch *bb = bio->bi_private;
- if (err && (err != -EOPNOTSUPP))
- clear_bit(BIO_UPTODATE, &bb->flags);
+ if (bio->bi_error && bio->bi_error != -EOPNOTSUPP)
+ bb->error = bio->bi_error;
if (atomic_dec_and_test(&bb->done))
complete(bb->wait);
bio_put(bio);
}
+/*
+ * Ensure that max discard sectors doesn't overflow bi_size and hopefully
+ * it is of the proper granularity as long as the granularity is a power
+ * of two.
+ */
+#define MAX_BIO_SECTORS ((1U << 31) >> 9)
+
/**
* blkdev_issue_discard - queue a discard
* @bdev: blockdev to issue discard for
@@ -43,8 +50,6 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
DECLARE_COMPLETION_ONSTACK(wait);
struct request_queue *q = bdev_get_queue(bdev);
int type = REQ_WRITE | REQ_DISCARD;
- unsigned int max_discard_sectors, granularity;
- int alignment;
struct bio_batch bb;
struct bio *bio;
int ret = 0;
@@ -56,21 +61,6 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
- /* Zero-sector (unknown) and one-sector granularities are the same. */
- granularity = max(q->limits.discard_granularity >> 9, 1U);
- alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
-
- /*
- * Ensure that max_discard_sectors is of the proper
- * granularity, so that requests stay aligned after a split.
- */
- max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
- max_discard_sectors -= max_discard_sectors % granularity;
- if (unlikely(!max_discard_sectors)) {
- /* Avoid infinite loop below. Being cautious never hurts. */
- return -EOPNOTSUPP;
- }
-
if (flags & BLKDEV_DISCARD_SECURE) {
if (!blk_queue_secdiscard(q))
return -EOPNOTSUPP;
@@ -78,13 +68,13 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
}
atomic_set(&bb.done, 1);
- bb.flags = 1 << BIO_UPTODATE;
+ bb.error = 0;
bb.wait = &wait;
blk_start_plug(&plug);
while (nr_sects) {
unsigned int req_sects;
- sector_t end_sect, tmp;
+ sector_t end_sect;
bio = bio_alloc(gfp_mask, 1);
if (!bio) {
@@ -92,21 +82,8 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
break;
}
- req_sects = min_t(sector_t, nr_sects, max_discard_sectors);
-
- /*
- * If splitting a request, and the next starting sector would be
- * misaligned, stop the discard at the previous aligned sector.
- */
+ req_sects = min_t(sector_t, nr_sects, MAX_BIO_SECTORS);
end_sect = sector + req_sects;
- tmp = end_sect;
- if (req_sects < nr_sects &&
- sector_div(tmp, granularity) != alignment) {
- end_sect = end_sect - alignment;
- sector_div(end_sect, granularity);
- end_sect = end_sect * granularity + alignment;
- req_sects = end_sect - sector;
- }
bio->bi_iter.bi_sector = sector;
bio->bi_end_io = bio_batch_end_io;
@@ -134,9 +111,8 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
if (!atomic_dec_and_test(&bb.done))
wait_for_completion_io(&wait);
- if (!test_bit(BIO_UPTODATE, &bb.flags))
- ret = -EIO;
-
+ if (bb.error)
+ return bb.error;
return ret;
}
EXPORT_SYMBOL(blkdev_issue_discard);
@@ -166,13 +142,11 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
if (!q)
return -ENXIO;
- max_write_same_sectors = q->limits.max_write_same_sectors;
-
- if (max_write_same_sectors == 0)
- return -EOPNOTSUPP;
+ /* Ensure that max_write_same_sectors doesn't overflow bi_size */
+ max_write_same_sectors = UINT_MAX >> 9;
atomic_set(&bb.done, 1);
- bb.flags = 1 << BIO_UPTODATE;
+ bb.error = 0;
bb.wait = &wait;
while (nr_sects) {
@@ -208,9 +182,8 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
if (!atomic_dec_and_test(&bb.done))
wait_for_completion_io(&wait);
- if (!test_bit(BIO_UPTODATE, &bb.flags))
- ret = -ENOTSUPP;
-
+ if (bb.error)
+ return bb.error;
return ret;
}
EXPORT_SYMBOL(blkdev_issue_write_same);
@@ -236,7 +209,7 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
DECLARE_COMPLETION_ONSTACK(wait);
atomic_set(&bb.done, 1);
- bb.flags = 1 << BIO_UPTODATE;
+ bb.error = 0;
bb.wait = &wait;
ret = 0;
@@ -270,10 +243,8 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
if (!atomic_dec_and_test(&bb.done))
wait_for_completion_io(&wait);
- if (!test_bit(BIO_UPTODATE, &bb.flags))
- /* One of bios in the batch was completed with error.*/
- ret = -EIO;
-
+ if (bb.error)
+ return bb.error;
return ret;
}
diff --git a/block/blk-map.c b/block/blk-map.c
index da310a105429..233841644c9d 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -94,7 +94,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
return PTR_ERR(bio);
if (map_data && map_data->null_mapped)
- bio->bi_flags |= (1 << BIO_NULL_MAPPED);
+ bio_set_flag(bio, BIO_NULL_MAPPED);
if (bio->bi_iter.bi_size != iter->count) {
/*
@@ -103,7 +103,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
* normal IO completion path
*/
bio_get(bio);
- bio_endio(bio, 0);
+ bio_endio(bio);
__blk_rq_unmap_user(bio);
return -EINVAL;
}
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 30a0d9f89017..d088cffb8105 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -9,12 +9,146 @@
#include "blk.h"
+static struct bio *blk_bio_discard_split(struct request_queue *q,
+ struct bio *bio,
+ struct bio_set *bs)
+{
+ unsigned int max_discard_sectors, granularity;
+ int alignment;
+ sector_t tmp;
+ unsigned split_sectors;
+
+ /* Zero-sector (unknown) and one-sector granularities are the same. */
+ granularity = max(q->limits.discard_granularity >> 9, 1U);
+
+ max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
+ max_discard_sectors -= max_discard_sectors % granularity;
+
+ if (unlikely(!max_discard_sectors)) {
+ /* XXX: warn */
+ return NULL;
+ }
+
+ if (bio_sectors(bio) <= max_discard_sectors)
+ return NULL;
+
+ split_sectors = max_discard_sectors;
+
+ /*
+ * If the next starting sector would be misaligned, stop the discard at
+ * the previous aligned sector.
+ */
+ alignment = (q->limits.discard_alignment >> 9) % granularity;
+
+ tmp = bio->bi_iter.bi_sector + split_sectors - alignment;
+ tmp = sector_div(tmp, granularity);
+
+ if (split_sectors > tmp)
+ split_sectors -= tmp;
+
+ return bio_split(bio, split_sectors, GFP_NOIO, bs);
+}
+
+static struct bio *blk_bio_write_same_split(struct request_queue *q,
+ struct bio *bio,
+ struct bio_set *bs)
+{
+ if (!q->limits.max_write_same_sectors)
+ return NULL;
+
+ if (bio_sectors(bio) <= q->limits.max_write_same_sectors)
+ return NULL;
+
+ return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs);
+}
+
+static struct bio *blk_bio_segment_split(struct request_queue *q,
+ struct bio *bio,
+ struct bio_set *bs)
+{
+ struct bio *split;
+ struct bio_vec bv, bvprv;
+ struct bvec_iter iter;
+ unsigned seg_size = 0, nsegs = 0, sectors = 0;
+ int prev = 0;
+
+ bio_for_each_segment(bv, bio, iter) {
+ sectors += bv.bv_len >> 9;
+
+ if (sectors > queue_max_sectors(q))
+ goto split;
+
+ /*
+ * If the queue doesn't support SG gaps and adding this
+ * offset would create a gap, disallow it.
+ */
+ if (prev && bvec_gap_to_prev(q, &bvprv, bv.bv_offset))
+ goto split;
+
+ if (prev && blk_queue_cluster(q)) {
+ if (seg_size + bv.bv_len > queue_max_segment_size(q))
+ goto new_segment;
+ if (!BIOVEC_PHYS_MERGEABLE(&bvprv, &bv))
+ goto new_segment;
+ if (!BIOVEC_SEG_BOUNDARY(q, &bvprv, &bv))
+ goto new_segment;
+
+ seg_size += bv.bv_len;
+ bvprv = bv;
+ prev = 1;
+ continue;
+ }
+new_segment:
+ if (nsegs == queue_max_segments(q))
+ goto split;
+
+ nsegs++;
+ bvprv = bv;
+ prev = 1;
+ seg_size = bv.bv_len;
+ }
+
+ return NULL;
+split:
+ split = bio_clone_bioset(bio, GFP_NOIO, bs);
+
+ split->bi_iter.bi_size -= iter.bi_size;
+ bio->bi_iter = iter;
+
+ if (bio_integrity(bio)) {
+ bio_integrity_advance(bio, split->bi_iter.bi_size);
+ bio_integrity_trim(split, 0, bio_sectors(split));
+ }
+
+ return split;
+}
+
+void blk_queue_split(struct request_queue *q, struct bio **bio,
+ struct bio_set *bs)
+{
+ struct bio *split;
+
+ if ((*bio)->bi_rw & REQ_DISCARD)
+ split = blk_bio_discard_split(q, *bio, bs);
+ else if ((*bio)->bi_rw & REQ_WRITE_SAME)
+ split = blk_bio_write_same_split(q, *bio, bs);
+ else
+ split = blk_bio_segment_split(q, *bio, q->bio_split);
+
+ if (split) {
+ bio_chain(split, *bio);
+ generic_make_request(*bio);
+ *bio = split;
+ }
+}
+EXPORT_SYMBOL(blk_queue_split);
+
static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
struct bio *bio,
bool no_sg_merge)
{
struct bio_vec bv, bvprv = { NULL };
- int cluster, high, highprv = 1;
+ int cluster, prev = 0;
unsigned int seg_size, nr_phys_segs;
struct bio *fbio, *bbio;
struct bvec_iter iter;
@@ -36,7 +170,6 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
cluster = blk_queue_cluster(q);
seg_size = 0;
nr_phys_segs = 0;
- high = 0;
for_each_bio(bio) {
bio_for_each_segment(bv, bio, iter) {
/*
@@ -46,13 +179,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
if (no_sg_merge)
goto new_segment;
- /*
- * 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 (prev && cluster) {
if (seg_size + bv.bv_len
> queue_max_segment_size(q))
goto new_segment;
@@ -72,8 +199,8 @@ new_segment:
nr_phys_segs++;
bvprv = bv;
+ prev = 1;
seg_size = bv.bv_len;
- highprv = high;
}
bbio = bio;
}
@@ -116,7 +243,7 @@ void blk_recount_segments(struct request_queue *q, struct bio *bio)
bio->bi_next = nxt;
}
- bio->bi_flags |= (1 << BIO_SEG_VALID);
+ bio_set_flag(bio, BIO_SEG_VALID);
}
EXPORT_SYMBOL(blk_recount_segments);
@@ -266,7 +393,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
if (rq->cmd_flags & REQ_WRITE)
memset(q->dma_drain_buffer, 0, q->dma_drain_size);
- sg->page_link &= ~0x02;
+ sg_unmark_end(sg);
sg = sg_next(sg);
sg_set_page(sg, virt_to_page(q->dma_drain_buffer),
q->dma_drain_size,
@@ -356,12 +483,12 @@ static bool req_no_special_merge(struct request *req)
return !q->mq_ops && req->special;
}
-static int req_gap_to_prev(struct request *req, struct request *next)
+static int req_gap_to_prev(struct request *req, struct bio *next)
{
struct bio *prev = req->biotail;
- return bvec_gap_to_prev(&prev->bi_io_vec[prev->bi_vcnt - 1],
- next->bio->bi_io_vec[0].bv_offset);
+ return bvec_gap_to_prev(req->q, &prev->bi_io_vec[prev->bi_vcnt - 1],
+ next->bi_io_vec[0].bv_offset);
}
static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
@@ -378,8 +505,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
if (req_no_special_merge(req) || req_no_special_merge(next))
return 0;
- if (test_bit(QUEUE_FLAG_SG_GAPS, &q->queue_flags) &&
- req_gap_to_prev(req, next))
+ if (req_gap_to_prev(req, next->bio))
return 0;
/*
@@ -564,8 +690,6 @@ int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
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;
@@ -590,13 +714,8 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
return false;
/* Only check gaps if the bio carries data */
- if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS) && bio_has_data(bio)) {
- struct bio_vec *bprev;
-
- bprev = &rq->biotail->bi_io_vec[rq->biotail->bi_vcnt - 1];
- if (bvec_gap_to_prev(bprev, bio->bi_io_vec[0].bv_offset))
- return false;
- }
+ if (bio_has_data(bio) && req_gap_to_prev(rq, bio))
+ return false;
return true;
}
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index b79685e06b70..279c5d674edf 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -141,15 +141,26 @@ static ssize_t blk_mq_sysfs_completed_show(struct blk_mq_ctx *ctx, char *page)
static ssize_t sysfs_list_show(char *page, struct list_head *list, char *msg)
{
- char *start_page = page;
struct request *rq;
+ int len = snprintf(page, PAGE_SIZE - 1, "%s:\n", msg);
+
+ list_for_each_entry(rq, list, queuelist) {
+ const int rq_len = 2 * sizeof(rq) + 2;
+
+ /* if the output will be truncated */
+ if (PAGE_SIZE - 1 < len + rq_len) {
+ /* backspacing if it can't hold '\t...\n' */
+ if (PAGE_SIZE - 1 < len + 5)
+ len -= rq_len;
+ len += snprintf(page + len, PAGE_SIZE - 1 - len,
+ "\t...\n");
+ break;
+ }
+ len += snprintf(page + len, PAGE_SIZE - 1 - len,
+ "\t%p\n", rq);
+ }
- page += sprintf(page, "%s:\n", msg);
-
- list_for_each_entry(rq, list, queuelist)
- page += sprintf(page, "\t%p\n", rq);
-
- return page - start_page;
+ return len;
}
static ssize_t blk_mq_sysfs_rq_list_show(struct blk_mq_ctx *ctx, char *page)
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 9b6e28830b82..9115c6d59948 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -429,7 +429,7 @@ static void bt_for_each(struct blk_mq_hw_ctx *hctx,
for (bit = find_first_bit(&bm->word, bm->depth);
bit < bm->depth;
bit = find_next_bit(&bm->word, bm->depth, bit + 1)) {
- rq = blk_mq_tag_to_rq(hctx->tags, off + bit);
+ rq = hctx->tags->rqs[off + bit];
if (rq->q == hctx->queue)
fn(hctx, rq, data, reserved);
}
@@ -453,7 +453,7 @@ static void bt_tags_for_each(struct blk_mq_tags *tags,
for (bit = find_first_bit(&bm->word, bm->depth);
bit < bm->depth;
bit = find_next_bit(&bm->word, bm->depth, bit + 1)) {
- rq = blk_mq_tag_to_rq(tags, off + bit);
+ rq = tags->rqs[off + bit];
fn(rq, data, reserved);
}
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 75893a34237d..9eb2cf4f01cb 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -89,4 +89,16 @@ static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
__blk_mq_tag_idle(hctx);
}
+/*
+ * This helper should only be used for flush request to share tag
+ * with the request cloned from, and both the two requests can't be
+ * in flight at the same time. The caller has to make sure the tag
+ * can't be freed.
+ */
+static inline void blk_mq_tag_set_rq(struct blk_mq_hw_ctx *hctx,
+ unsigned int tag, struct request *rq)
+{
+ hctx->tags->rqs[tag] = rq;
+}
+
#endif
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 7d842db59699..f2d67b4047a0 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -559,23 +559,9 @@ void blk_mq_abort_requeue_list(struct request_queue *q)
}
EXPORT_SYMBOL(blk_mq_abort_requeue_list);
-static inline bool is_flush_request(struct request *rq,
- struct blk_flush_queue *fq, unsigned int tag)
-{
- return ((rq->cmd_flags & REQ_FLUSH_SEQ) &&
- fq->flush_rq->tag == tag);
-}
-
struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
{
- struct request *rq = tags->rqs[tag];
- /* mq_ctx of flush rq is always cloned from the corresponding req */
- struct blk_flush_queue *fq = blk_get_flush_queue(rq->q, rq->mq_ctx);
-
- if (!is_flush_request(rq, fq, tag))
- return rq;
-
- return fq->flush_rq;
+ return tags->rqs[tag];
}
EXPORT_SYMBOL(blk_mq_tag_to_rq);
@@ -1199,7 +1185,7 @@ static struct request *blk_mq_map_request(struct request_queue *q,
struct blk_mq_alloc_data alloc_data;
if (unlikely(blk_mq_queue_enter(q, GFP_KERNEL))) {
- bio_endio(bio, -EIO);
+ bio_io_error(bio);
return NULL;
}
@@ -1283,10 +1269,12 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
blk_queue_bounce(q, &bio);
if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
- bio_endio(bio, -EIO);
+ bio_io_error(bio);
return;
}
+ blk_queue_split(q, &bio, q->bio_split);
+
if (!is_flush_fua && !blk_queue_nomerges(q) &&
blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
return;
@@ -1368,10 +1356,12 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
blk_queue_bounce(q, &bio);
if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
- bio_endio(bio, -EIO);
+ bio_io_error(bio);
return;
}
+ blk_queue_split(q, &bio, q->bio_split);
+
if (!is_flush_fua && !blk_queue_nomerges(q) &&
blk_attempt_plug_merge(q, bio, &request_count, NULL))
return;
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 12600bfffca9..7d8f129a1516 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -53,28 +53,6 @@ void blk_queue_unprep_rq(struct request_queue *q, unprep_rq_fn *ufn)
}
EXPORT_SYMBOL(blk_queue_unprep_rq);
-/**
- * blk_queue_merge_bvec - set a merge_bvec function for queue
- * @q: queue
- * @mbfn: merge_bvec_fn
- *
- * Usually queues have static limitations on the max sectors or segments that
- * we can put in a request. Stacking drivers may have some settings that
- * are dynamic, and thus we have to query the queue whether it is ok to
- * add a new bio_vec to a bio at a given offset or not. If the block device
- * has such limitations, it needs to register a merge_bvec_fn to control
- * the size of bio's sent to it. Note that a block device *must* allow a
- * single page to be added to an empty bio. The block device driver may want
- * to use the bio_split() function to deal with these bio's. By default
- * no merge_bvec_fn is defined for a queue, and only the fixed limits are
- * honored.
- */
-void blk_queue_merge_bvec(struct request_queue *q, merge_bvec_fn *mbfn)
-{
- q->merge_bvec_fn = mbfn;
-}
-EXPORT_SYMBOL(blk_queue_merge_bvec);
-
void blk_queue_softirq_done(struct request_queue *q, softirq_done_fn *fn)
{
q->softirq_done_fn = fn;
@@ -111,11 +89,13 @@ void blk_set_default_limits(struct queue_limits *lim)
lim->max_segments = BLK_MAX_SEGMENTS;
lim->max_integrity_segments = 0;
lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
+ lim->virt_boundary_mask = 0;
lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
lim->chunk_sectors = 0;
lim->max_write_same_sectors = 0;
lim->max_discard_sectors = 0;
+ lim->max_hw_discard_sectors = 0;
lim->discard_granularity = 0;
lim->discard_alignment = 0;
lim->discard_misaligned = 0;
@@ -241,8 +221,8 @@ EXPORT_SYMBOL(blk_queue_bounce_limit);
* Description:
* Enables a low level driver to set a hard upper limit,
* max_hw_sectors, on the size of requests. max_hw_sectors is set by
- * the device driver based upon the combined capabilities of I/O
- * controller and storage device.
+ * the device driver based upon the capabilities of the I/O
+ * controller.
*
* max_sectors is a soft limit imposed by the block layer for
* filesystem type requests. This value can be overridden on a
@@ -257,7 +237,9 @@ void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_
__func__, max_hw_sectors);
}
- limits->max_sectors = limits->max_hw_sectors = max_hw_sectors;
+ limits->max_hw_sectors = max_hw_sectors;
+ limits->max_sectors = min_t(unsigned int, max_hw_sectors,
+ BLK_DEF_MAX_SECTORS);
}
EXPORT_SYMBOL(blk_limits_max_hw_sectors);
@@ -303,6 +285,7 @@ EXPORT_SYMBOL(blk_queue_chunk_sectors);
void blk_queue_max_discard_sectors(struct request_queue *q,
unsigned int max_discard_sectors)
{
+ q->limits.max_hw_discard_sectors = max_discard_sectors;
q->limits.max_discard_sectors = max_discard_sectors;
}
EXPORT_SYMBOL(blk_queue_max_discard_sectors);
@@ -550,6 +533,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
b->seg_boundary_mask);
+ t->virt_boundary_mask = min_not_zero(t->virt_boundary_mask,
+ b->virt_boundary_mask);
t->max_segments = min_not_zero(t->max_segments, b->max_segments);
t->max_integrity_segments = min_not_zero(t->max_integrity_segments,
@@ -641,6 +626,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
t->max_discard_sectors = min_not_zero(t->max_discard_sectors,
b->max_discard_sectors);
+ t->max_hw_discard_sectors = min_not_zero(t->max_hw_discard_sectors,
+ b->max_hw_discard_sectors);
t->discard_granularity = max(t->discard_granularity,
b->discard_granularity);
t->discard_alignment = lcm_not_zero(t->discard_alignment, alignment) %
@@ -788,6 +775,17 @@ void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask)
EXPORT_SYMBOL(blk_queue_segment_boundary);
/**
+ * blk_queue_virt_boundary - set boundary rules for bio merging
+ * @q: the request queue for the device
+ * @mask: the memory boundary mask
+ **/
+void blk_queue_virt_boundary(struct request_queue *q, unsigned long mask)
+{
+ q->limits.virt_boundary_mask = mask;
+}
+EXPORT_SYMBOL(blk_queue_virt_boundary);
+
+/**
* blk_queue_dma_alignment - set dma length and memory alignment
* @q: the request queue for the device
* @mask: alignment mask
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 6264b382d4d1..3e44a9da2a13 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -145,12 +145,43 @@ static ssize_t queue_discard_granularity_show(struct request_queue *q, char *pag
return queue_var_show(q->limits.discard_granularity, page);
}
+static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page)
+{
+ unsigned long long val;
+
+ val = q->limits.max_hw_discard_sectors << 9;
+ return sprintf(page, "%llu\n", val);
+}
+
static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
{
return sprintf(page, "%llu\n",
(unsigned long long)q->limits.max_discard_sectors << 9);
}
+static ssize_t queue_discard_max_store(struct request_queue *q,
+ const char *page, size_t count)
+{
+ unsigned long max_discard;
+ ssize_t ret = queue_var_store(&max_discard, page, count);
+
+ if (ret < 0)
+ return ret;
+
+ if (max_discard & (q->limits.discard_granularity - 1))
+ return -EINVAL;
+
+ max_discard >>= 9;
+ if (max_discard > UINT_MAX)
+ return -EINVAL;
+
+ if (max_discard > q->limits.max_hw_discard_sectors)
+ max_discard = q->limits.max_hw_discard_sectors;
+
+ q->limits.max_discard_sectors = max_discard;
+ return ret;
+}
+
static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page)
{
return queue_var_show(queue_discard_zeroes_data(q), page);
@@ -360,9 +391,15 @@ static struct queue_sysfs_entry queue_discard_granularity_entry = {
.show = queue_discard_granularity_show,
};
+static struct queue_sysfs_entry queue_discard_max_hw_entry = {
+ .attr = {.name = "discard_max_hw_bytes", .mode = S_IRUGO },
+ .show = queue_discard_max_hw_show,
+};
+
static struct queue_sysfs_entry queue_discard_max_entry = {
- .attr = {.name = "discard_max_bytes", .mode = S_IRUGO },
+ .attr = {.name = "discard_max_bytes", .mode = S_IRUGO | S_IWUSR },
.show = queue_discard_max_show,
+ .store = queue_discard_max_store,
};
static struct queue_sysfs_entry queue_discard_zeroes_data_entry = {
@@ -421,6 +458,7 @@ static struct attribute *default_attrs[] = {
&queue_io_opt_entry.attr,
&queue_discard_granularity_entry.attr,
&queue_discard_max_entry.attr,
+ &queue_discard_max_hw_entry.attr,
&queue_discard_zeroes_data_entry.attr,
&queue_write_same_max_entry.attr,
&queue_nonrot_entry.attr,
@@ -523,6 +561,9 @@ static void blk_release_queue(struct kobject *kobj)
blk_trace_shutdown(q);
+ if (q->bio_split)
+ bioset_free(q->bio_split);
+
ida_simple_remove(&blk_queue_ida, q->id);
call_rcu(&q->rcu_head, blk_free_queue_rcu);
}
diff --git a/block/blk.h b/block/blk.h
index 026d9594142b..838188b35a83 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -22,6 +22,12 @@ struct blk_flush_queue {
struct list_head flush_queue[2];
struct list_head flush_data_in_flight;
struct request *flush_rq;
+
+ /*
+ * flush_rq shares tag with this rq, both can't be active
+ * at the same time
+ */
+ struct request *orig_rq;
spinlock_t mq_flush_lock;
};
diff --git a/block/bounce.c b/block/bounce.c
index 31cad13a0c9d..0611aea1cfe9 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -123,7 +123,7 @@ static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
}
}
-static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
+static void bounce_end_io(struct bio *bio, mempool_t *pool)
{
struct bio *bio_orig = bio->bi_private;
struct bio_vec *bvec, *org_vec;
@@ -141,39 +141,40 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
mempool_free(bvec->bv_page, pool);
}
- bio_endio(bio_orig, err);
+ bio_orig->bi_error = bio->bi_error;
+ bio_endio(bio_orig);
bio_put(bio);
}
-static void bounce_end_io_write(struct bio *bio, int err)
+static void bounce_end_io_write(struct bio *bio)
{
- bounce_end_io(bio, page_pool, err);
+ bounce_end_io(bio, page_pool);
}
-static void bounce_end_io_write_isa(struct bio *bio, int err)
+static void bounce_end_io_write_isa(struct bio *bio)
{
- bounce_end_io(bio, isa_page_pool, err);
+ bounce_end_io(bio, isa_page_pool);
}
-static void __bounce_end_io_read(struct bio *bio, mempool_t *pool, int err)
+static void __bounce_end_io_read(struct bio *bio, mempool_t *pool)
{
struct bio *bio_orig = bio->bi_private;
- if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+ if (!bio->bi_error)
copy_to_high_bio_irq(bio_orig, bio);
- bounce_end_io(bio, pool, err);
+ bounce_end_io(bio, pool);
}
-static void bounce_end_io_read(struct bio *bio, int err)
+static void bounce_end_io_read(struct bio *bio)
{
- __bounce_end_io_read(bio, page_pool, err);
+ __bounce_end_io_read(bio, page_pool);
}
-static void bounce_end_io_read_isa(struct bio *bio, int err)
+static void bounce_end_io_read_isa(struct bio *bio)
{
- __bounce_end_io_read(bio, isa_page_pool, err);
+ __bounce_end_io_read(bio, isa_page_pool);
}
static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
diff --git a/block/genhd.c b/block/genhd.c
index 59a1395eedac..0c706f33a599 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1110,8 +1110,7 @@ static void disk_release(struct device *dev)
disk_release_events(disk);
kfree(disk->random);
disk_replace_part_tbl(disk, NULL);
- free_part_stats(&disk->part0);
- free_part_info(&disk->part0);
+ hd_free_part(&disk->part0);
if (disk->queue)
blk_put_queue(disk->queue);
kfree(disk);
@@ -1285,7 +1284,11 @@ struct gendisk *alloc_disk_node(int minors, int node_id)
* converted to make use of bd_mutex and sequence counters.
*/
seqcount_init(&disk->part0.nr_sects_seq);
- hd_ref_init(&disk->part0);
+ if (hd_ref_init(&disk->part0)) {
+ hd_free_part(&disk->part0);
+ kfree(disk);
+ return NULL;
+ }
disk->minors = minors;
rand_initialize_disk(disk);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 0d9e5f97f0a8..e7711133284e 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -212,8 +212,7 @@ static void part_release(struct device *dev)
{
struct hd_struct *p = dev_to_part(dev);
blk_free_devt(dev->devt);
- free_part_stats(p);
- free_part_info(p);
+ hd_free_part(p);
kfree(p);
}
@@ -233,8 +232,9 @@ static void delete_partition_rcu_cb(struct rcu_head *head)
put_device(part_to_dev(part));
}
-void __delete_partition(struct hd_struct *part)
+void __delete_partition(struct percpu_ref *ref)
{
+ struct hd_struct *part = container_of(ref, struct hd_struct, ref);
call_rcu(&part->rcu_head, delete_partition_rcu_cb);
}
@@ -255,7 +255,7 @@ void delete_partition(struct gendisk *disk, int partno)
kobject_put(part->holder_dir);
device_del(part_to_dev(part));
- hd_struct_put(part);
+ hd_struct_kill(part);
}
static ssize_t whole_disk_show(struct device *dev,
@@ -356,8 +356,8 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
if (!dev_get_uevent_suppress(ddev))
kobject_uevent(&pdev->kobj, KOBJ_ADD);
- hd_ref_init(p);
- return p;
+ if (!hd_ref_init(p))
+ return p;
out_free_info:
free_part_info(p);