summaryrefslogtreecommitdiff
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/bdev.c113
-rw-r--r--block/blk-cgroup.c9
-rw-r--r--block/blk-cgroup.h2
-rw-r--r--block/blk-core.c3
-rw-r--r--block/blk-iocost.c14
-rw-r--r--block/blk-merge.c2
-rw-r--r--block/blk-mq.c9
-rw-r--r--block/blk-settings.c19
-rw-r--r--block/blk.h1
-rw-r--r--block/ioctl.c8
10 files changed, 120 insertions, 60 deletions
diff --git a/block/bdev.c b/block/bdev.c
index 7a5f611c3d2e..4dc94145eb53 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -583,9 +583,6 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder,
mutex_unlock(&bdev->bd_holder_lock);
bd_clear_claiming(whole, holder);
mutex_unlock(&bdev_lock);
-
- if (hops && hops->get_holder)
- hops->get_holder(holder);
}
/**
@@ -608,7 +605,6 @@ EXPORT_SYMBOL(bd_abort_claiming);
static void bd_end_claim(struct block_device *bdev, void *holder)
{
struct block_device *whole = bdev_whole(bdev);
- const struct blk_holder_ops *hops = bdev->bd_holder_ops;
bool unblock = false;
/*
@@ -631,9 +627,6 @@ static void bd_end_claim(struct block_device *bdev, void *holder)
whole->bd_holder = NULL;
mutex_unlock(&bdev_lock);
- if (hops && hops->put_holder)
- hops->put_holder(holder);
-
/*
* If this was the last claim, remove holder link and unblock evpoll if
* it was a write holder.
@@ -652,6 +645,14 @@ static void blkdev_flush_mapping(struct block_device *bdev)
bdev_write_inode(bdev);
}
+static void blkdev_put_whole(struct block_device *bdev)
+{
+ if (atomic_dec_and_test(&bdev->bd_openers))
+ blkdev_flush_mapping(bdev);
+ if (bdev->bd_disk->fops->release)
+ bdev->bd_disk->fops->release(bdev->bd_disk);
+}
+
static int blkdev_get_whole(struct block_device *bdev, blk_mode_t mode)
{
struct gendisk *disk = bdev->bd_disk;
@@ -670,20 +671,21 @@ static int blkdev_get_whole(struct block_device *bdev, blk_mode_t mode)
if (!atomic_read(&bdev->bd_openers))
set_init_blocksize(bdev);
- if (test_bit(GD_NEED_PART_SCAN, &disk->state))
- bdev_disk_changed(disk, false);
atomic_inc(&bdev->bd_openers);
+ if (test_bit(GD_NEED_PART_SCAN, &disk->state)) {
+ /*
+ * Only return scanning errors if we are called from contexts
+ * that explicitly want them, e.g. the BLKRRPART ioctl.
+ */
+ ret = bdev_disk_changed(disk, false);
+ if (ret && (mode & BLK_OPEN_STRICT_SCAN)) {
+ blkdev_put_whole(bdev);
+ return ret;
+ }
+ }
return 0;
}
-static void blkdev_put_whole(struct block_device *bdev)
-{
- if (atomic_dec_and_test(&bdev->bd_openers))
- blkdev_flush_mapping(bdev);
- if (bdev->bd_disk->fops->release)
- bdev->bd_disk->fops->release(bdev->bd_disk);
-}
-
static int blkdev_get_part(struct block_device *part, blk_mode_t mode)
{
struct gendisk *disk = part->bd_disk;
@@ -776,17 +778,17 @@ void blkdev_put_no_open(struct block_device *bdev)
static bool bdev_writes_blocked(struct block_device *bdev)
{
- return bdev->bd_writers == -1;
+ return bdev->bd_writers < 0;
}
static void bdev_block_writes(struct block_device *bdev)
{
- bdev->bd_writers = -1;
+ bdev->bd_writers--;
}
static void bdev_unblock_writes(struct block_device *bdev)
{
- bdev->bd_writers = 0;
+ bdev->bd_writers++;
}
static bool bdev_may_open(struct block_device *bdev, blk_mode_t mode)
@@ -813,6 +815,11 @@ static void bdev_claim_write_access(struct block_device *bdev, blk_mode_t mode)
bdev->bd_writers++;
}
+static inline bool bdev_unclaimed(const struct file *bdev_file)
+{
+ return bdev_file->private_data == BDEV_I(bdev_file->f_mapping->host);
+}
+
static void bdev_yield_write_access(struct file *bdev_file)
{
struct block_device *bdev;
@@ -820,14 +827,15 @@ static void bdev_yield_write_access(struct file *bdev_file)
if (bdev_allow_write_mounted)
return;
+ if (bdev_unclaimed(bdev_file))
+ return;
+
bdev = file_bdev(bdev_file);
- /* Yield exclusive or shared write access. */
- if (bdev_file->f_mode & FMODE_WRITE) {
- if (bdev_writes_blocked(bdev))
- bdev_unblock_writes(bdev);
- else
- bdev->bd_writers--;
- }
+
+ if (bdev_file->f_mode & FMODE_WRITE_RESTRICTED)
+ bdev_unblock_writes(bdev);
+ else if (bdev_file->f_mode & FMODE_WRITE)
+ bdev->bd_writers--;
}
/**
@@ -907,6 +915,8 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder,
bdev_file->f_mode |= FMODE_BUF_RASYNC | FMODE_CAN_ODIRECT;
if (bdev_nowait(bdev))
bdev_file->f_mode |= FMODE_NOWAIT;
+ if (mode & BLK_OPEN_RESTRICT_WRITES)
+ bdev_file->f_mode |= FMODE_WRITE_RESTRICTED;
bdev_file->f_mapping = bdev->bd_inode->i_mapping;
bdev_file->f_wb_err = filemap_sample_wb_err(bdev_file->f_mapping);
bdev_file->private_data = holder;
@@ -1012,6 +1022,20 @@ struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode,
}
EXPORT_SYMBOL(bdev_file_open_by_path);
+static inline void bd_yield_claim(struct file *bdev_file)
+{
+ struct block_device *bdev = file_bdev(bdev_file);
+ void *holder = bdev_file->private_data;
+
+ lockdep_assert_held(&bdev->bd_disk->open_mutex);
+
+ if (WARN_ON_ONCE(IS_ERR_OR_NULL(holder)))
+ return;
+
+ if (!bdev_unclaimed(bdev_file))
+ bd_end_claim(bdev, holder);
+}
+
void bdev_release(struct file *bdev_file)
{
struct block_device *bdev = file_bdev(bdev_file);
@@ -1036,7 +1060,7 @@ void bdev_release(struct file *bdev_file)
bdev_yield_write_access(bdev_file);
if (holder)
- bd_end_claim(bdev, holder);
+ bd_yield_claim(bdev_file);
/*
* Trigger event checking and tell drivers to flush MEDIA_CHANGE
@@ -1057,6 +1081,39 @@ put_no_open:
}
/**
+ * bdev_fput - yield claim to the block device and put the file
+ * @bdev_file: open block device
+ *
+ * Yield claim on the block device and put the file. Ensure that the
+ * block device can be reclaimed before the file is closed which is a
+ * deferred operation.
+ */
+void bdev_fput(struct file *bdev_file)
+{
+ if (WARN_ON_ONCE(bdev_file->f_op != &def_blk_fops))
+ return;
+
+ if (bdev_file->private_data) {
+ struct block_device *bdev = file_bdev(bdev_file);
+ struct gendisk *disk = bdev->bd_disk;
+
+ mutex_lock(&disk->open_mutex);
+ bdev_yield_write_access(bdev_file);
+ bd_yield_claim(bdev_file);
+ /*
+ * Tell release we already gave up our hold on the
+ * device and if write restrictions are available that
+ * we already gave up write access to the device.
+ */
+ bdev_file->private_data = BDEV_I(bdev_file->f_mapping->host);
+ mutex_unlock(&disk->open_mutex);
+ }
+
+ fput(bdev_file);
+}
+EXPORT_SYMBOL(bdev_fput);
+
+/**
* lookup_bdev() - Look up a struct block_device by name.
* @pathname: Name of the block device in the filesystem.
* @dev: Pointer to the block device's dev_t, if found.
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index bdbb557feb5a..059467086b13 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1409,6 +1409,12 @@ static int blkcg_css_online(struct cgroup_subsys_state *css)
return 0;
}
+void blkg_init_queue(struct request_queue *q)
+{
+ INIT_LIST_HEAD(&q->blkg_list);
+ mutex_init(&q->blkcg_mutex);
+}
+
int blkcg_init_disk(struct gendisk *disk)
{
struct request_queue *q = disk->queue;
@@ -1416,9 +1422,6 @@ int blkcg_init_disk(struct gendisk *disk)
bool preloaded;
int ret;
- INIT_LIST_HEAD(&q->blkg_list);
- mutex_init(&q->blkcg_mutex);
-
new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL);
if (!new_blkg)
return -ENOMEM;
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 78b74106bf10..90b3959d88cf 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -189,6 +189,7 @@ struct blkcg_policy {
extern struct blkcg blkcg_root;
extern bool blkcg_debug_stats;
+void blkg_init_queue(struct request_queue *q);
int blkcg_init_disk(struct gendisk *disk);
void blkcg_exit_disk(struct gendisk *disk);
@@ -482,6 +483,7 @@ struct blkcg {
};
static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
+static inline void blkg_init_queue(struct request_queue *q) { }
static inline int blkcg_init_disk(struct gendisk *disk) { return 0; }
static inline void blkcg_exit_disk(struct gendisk *disk) { }
static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; }
diff --git a/block/blk-core.c b/block/blk-core.c
index a16b5abdbbf5..b795ac177281 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -442,6 +442,8 @@ struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id)
init_waitqueue_head(&q->mq_freeze_wq);
mutex_init(&q->mq_freeze_lock);
+ blkg_init_queue(q);
+
/*
* Init percpu_ref in atomic mode so that it's faster to shutdown.
* See blk_register_queue() for details.
@@ -1195,6 +1197,7 @@ void __blk_flush_plug(struct blk_plug *plug, bool from_schedule)
if (unlikely(!rq_list_empty(plug->cached_rq)))
blk_mq_free_plug_rqs(plug);
+ plug->cur_ktime = 0;
current->flags &= ~PF_BLOCK_TS;
}
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 9a85bfbbc45a..690ca99dfaca 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1347,7 +1347,7 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now)
{
struct ioc *ioc = iocg->ioc;
struct blkcg_gq *blkg = iocg_to_blkg(iocg);
- u64 tdelta, delay, new_delay;
+ u64 tdelta, delay, new_delay, shift;
s64 vover, vover_pct;
u32 hwa;
@@ -1362,8 +1362,9 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now)
/* calculate the current delay in effect - 1/2 every second */
tdelta = now->now - iocg->delay_at;
- if (iocg->delay)
- delay = iocg->delay >> div64_u64(tdelta, USEC_PER_SEC);
+ shift = div64_u64(tdelta, USEC_PER_SEC);
+ if (iocg->delay && shift < BITS_PER_LONG)
+ delay = iocg->delay >> shift;
else
delay = 0;
@@ -1438,8 +1439,11 @@ static void iocg_pay_debt(struct ioc_gq *iocg, u64 abs_vpay,
lockdep_assert_held(&iocg->ioc->lock);
lockdep_assert_held(&iocg->waitq.lock);
- /* make sure that nobody messed with @iocg */
- WARN_ON_ONCE(list_empty(&iocg->active_list));
+ /*
+ * make sure that nobody messed with @iocg. Check iocg->pd.online
+ * to avoid warn when removing blkcg or disk.
+ */
+ WARN_ON_ONCE(list_empty(&iocg->active_list) && iocg->pd.online);
WARN_ON_ONCE(iocg->inuse > 1);
iocg->abs_vdebt -= min(abs_vpay, iocg->abs_vdebt);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 2a06fd33039d..4e3483a16b75 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -726,7 +726,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
* which can be mixed are set in each bio and mark @rq as mixed
* merged.
*/
-void blk_rq_set_mixed_merge(struct request *rq)
+static void blk_rq_set_mixed_merge(struct request *rq)
{
blk_opf_t ff = rq->cmd_flags & REQ_FAILFAST_MASK;
struct bio *bio;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 555ada922cf0..32afb87efbd0 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -770,16 +770,11 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
/*
* Partial zone append completions cannot be supported as the
* BIO fragments may end up not being written sequentially.
- * For such case, force the completed nbytes to be equal to
- * the BIO size so that bio_advance() sets the BIO remaining
- * size to 0 and we end up calling bio_endio() before returning.
*/
- if (bio->bi_iter.bi_size != nbytes) {
+ if (bio->bi_iter.bi_size != nbytes)
bio->bi_status = BLK_STS_IOERR;
- nbytes = bio->bi_iter.bi_size;
- } else {
+ else
bio->bi_iter.bi_sector = rq->__sector;
- }
}
bio_advance(bio, nbytes);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 3c7d8d638ab5..d2731843f2fc 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -146,8 +146,7 @@ static int blk_validate_limits(struct queue_limits *lim)
max_hw_sectors = min_not_zero(lim->max_hw_sectors,
lim->max_dev_sectors);
if (lim->max_user_sectors) {
- if (lim->max_user_sectors > max_hw_sectors ||
- lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE)
+ if (lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE)
return -EINVAL;
lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors);
} else {
@@ -183,17 +182,13 @@ static int blk_validate_limits(struct queue_limits *lim)
return -EINVAL;
/*
- * Devices that require a virtual boundary do not support scatter/gather
- * I/O natively, but instead require a descriptor list entry for each
- * page (which might not be identical to the Linux PAGE_SIZE). Because
- * of that they are not limited by our notion of "segment size".
+ * Stacking device may have both virtual boundary and max segment
+ * size limit, so allow this setting now, and long-term the two
+ * might need to move out of stacking limits since we have immutable
+ * bvec and lower layer bio splitting is supposed to handle the two
+ * correctly.
*/
- if (lim->virt_boundary_mask) {
- if (WARN_ON_ONCE(lim->max_segment_size &&
- lim->max_segment_size != UINT_MAX))
- return -EINVAL;
- lim->max_segment_size = UINT_MAX;
- } else {
+ if (!lim->virt_boundary_mask) {
/*
* The maximum segment size has an odd historic 64k default that
* drivers probably should override. Just like the I/O size we
diff --git a/block/blk.h b/block/blk.h
index 5cac4e29ae17..d9f584984bc4 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -339,7 +339,6 @@ int ll_back_merge_fn(struct request *req, struct bio *bio,
bool blk_attempt_req_merge(struct request_queue *q, struct request *rq,
struct request *next);
unsigned int blk_recalc_rq_segments(struct request *rq);
-void blk_rq_set_mixed_merge(struct request *rq);
bool blk_rq_merge_ok(struct request *rq, struct bio *bio);
enum elv_merge blk_try_merge(struct request *rq, struct bio *bio);
diff --git a/block/ioctl.c b/block/ioctl.c
index 0c76137adcaa..f505f9c341eb 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -96,7 +96,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
unsigned long arg)
{
uint64_t range[2];
- uint64_t start, len;
+ uint64_t start, len, end;
struct inode *inode = bdev->bd_inode;
int err;
@@ -117,7 +117,8 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
if (len & 511)
return -EINVAL;
- if (start + len > bdev_nr_bytes(bdev))
+ if (check_add_overflow(start, len, &end) ||
+ end > bdev_nr_bytes(bdev))
return -EINVAL;
filemap_invalidate_lock(inode->i_mapping);
@@ -562,7 +563,8 @@ static int blkdev_common_ioctl(struct block_device *bdev, blk_mode_t mode,
return -EACCES;
if (bdev_is_partition(bdev))
return -EINVAL;
- return disk_scan_partitions(bdev->bd_disk, mode);
+ return disk_scan_partitions(bdev->bd_disk,
+ mode | BLK_OPEN_STRICT_SCAN);
case BLKTRACESTART:
case BLKTRACESTOP:
case BLKTRACETEARDOWN:
generated by cgit v1.2.3-70-g09d2 (git 2.47.1) at 2025-02-05 19:58:41 +0000