diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-04-05 19:47:26 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-04-05 19:47:26 +0300 |
commit | fae02687777ad80c1299c684f7f814c542103fa6 (patch) | |
tree | af687c7bc5962f758f72807626039a44f6fa8ef5 /block | |
parent | 8cb4a9a82b21623dbb4b3051dd30d98356cf95bc (diff) | |
parent | caeb4b0a11b3393e43f7fa8e0a5a18462acc66bd (diff) | |
download | linux-fae02687777ad80c1299c684f7f814c542103fa6.tar.xz |
Merge tag 'vfs-6.9-rc3.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs
Pull vfs fixes from Christian Brauner:
"This contains a few small fixes. This comes with some delay because I
wanted to wait on people running their reproducers and the Easter
Holidays meant that those replies came in a little later than usual:
- Fix handling of preventing writes to mounted block devices.
Since last kernel we allow to prevent writing to mounted block
devices provided CONFIG_BLK_DEV_WRITE_MOUNTED isn't set and the
block device is opened with restricted writes. When we switched to
opening block devices as files we altered the mechanism by which we
recognize when a block device has been opened with write
restrictions.
The detection logic assumed that only read-write mounted
filesystems would apply write restrictions to their block devices
from other openers. That of course is not true since it also makes
sense to apply write restrictions for filesystems that are
read-only.
Fix the detection logic using an FMODE_* bit. We still have a few
left since we freed up a couple a while ago. I also picked up a
patch to free up four additional FMODE_* bits scheduled for the
next merge window.
- Fix counting the number of writers to a block device. This just
changes the logic to be consistent.
- Fix a bug in aio causing a NULL pointer derefernce after we
implemented batched processing in aio.
- Finally, add the changes we discussed that allows to yield block
devices early even though file closing itself is deferred.
This also allows us to remove two holder operations to get and
release the holder to align lifetime of file and holder of the
block device"
* tag 'vfs-6.9-rc3.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
aio: Fix null ptr deref in aio_complete() wakeup
fs,block: yield devices early
block: count BLK_OPEN_RESTRICT_WRITES openers
block: handle BLK_OPEN_RESTRICT_WRITES correctly
Diffstat (limited to 'block')
-rw-r--r-- | block/bdev.c | 84 |
1 files changed, 66 insertions, 18 deletions
diff --git a/block/bdev.c b/block/bdev.c index 7a5f611c3d2e..b8e32d933a63 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. @@ -776,17 +769,17 @@ 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 +806,11 @@ 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 +818,15 @@ 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 +906,8 @@ 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 +1013,20 @@ 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 +1051,7 @@ 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 +1072,39 @@ 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. |