From 1a3cbbc5a5e8a66934aa0947896a4aca6fd77298 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 7 Apr 2010 18:52:29 +0900 Subject: block: factor out bd_may_claim() Factor out bd_may_claim() from bd_claim(), add comments and apply a couple of cosmetic edits. This is to prepare for further updates to claim path. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- fs/block_dev.c | 65 ++++++++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 47 insertions(+), 18 deletions(-) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index 2a6d019..e59440c 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -661,41 +661,70 @@ void bd_forget(struct inode *inode) iput(bdev->bd_inode); } -int bd_claim(struct block_device *bdev, void *holder) +/** + * bd_may_claim - test whether a block device can be claimed + * @bdev: block device of interest + * @whole: whole block device containing @bdev, may equal @bdev + * @holder: holder trying to claim @bdev + * + * Test whther @bdev can be claimed by @holder. + * + * CONTEXT: + * spin_lock(&bdev_lock). + * + * RETURNS: + * %true if @bdev can be claimed, %false otherwise. + */ +static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, + void *holder) { - int res; - spin_lock(&bdev_lock); - - /* first decide result */ if (bdev->bd_holder == holder) - res = 0; /* already a holder */ + return true; /* already a holder */ else if (bdev->bd_holder != NULL) - res = -EBUSY; /* held by someone else */ + return false; /* held by someone else */ else if (bdev->bd_contains == bdev) - res = 0; /* is a whole device which isn't held */ + return true; /* is a whole device which isn't held */ - else if (bdev->bd_contains->bd_holder == bd_claim) - res = 0; /* is a partition of a device that is being partitioned */ - else if (bdev->bd_contains->bd_holder != NULL) - res = -EBUSY; /* is a partition of a held device */ + else if (whole->bd_holder == bd_claim) + return true; /* is a partition of a device that is being partitioned */ + else if (whole->bd_holder != NULL) + return false; /* is a partition of a held device */ else - res = 0; /* is a partition of an un-held device */ + return true; /* is a partition of an un-held device */ +} - /* now impose change */ - if (res==0) { +/** + * bd_claim - claim a block device + * @bdev: block device to claim + * @holder: holder trying to claim @bdev + * + * Try to claim @bdev. + * + * RETURNS: + * 0 if successful, -EBUSY if @bdev is already claimed. + */ +int bd_claim(struct block_device *bdev, void *holder) +{ + struct block_device *whole = bdev->bd_contains; + int res = -EBUSY; + + spin_lock(&bdev_lock); + + if (bd_may_claim(bdev, whole, holder)) { /* note that for a whole device bd_holders * will be incremented twice, and bd_holder will * be set to bd_claim before being set to holder */ - bdev->bd_contains->bd_holders ++; - bdev->bd_contains->bd_holder = bd_claim; + whole->bd_holders++; + whole->bd_holder = bd_claim; bdev->bd_holders++; bdev->bd_holder = holder; + res = 0; } + spin_unlock(&bdev_lock); return res; } - EXPORT_SYMBOL(bd_claim); void bd_release(struct block_device *bdev) -- cgit v1.1 From 6b4517a7913a09d3259bb1d21c9cb300f12294bd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 7 Apr 2010 18:53:59 +0900 Subject: block: implement bd_claiming and claiming block Currently, device claiming for exclusive open is done after low level open - disk->fops->open() - has completed successfully. This means that exclusive open attempts while a device is already exclusively open will fail only after disk->fops->open() is called. cdrom driver issues commands during open() which means that O_EXCL open attempt can unintentionally inject commands to in-progress command stream for burning thus disturbing burning process. In most cases, this doesn't cause problems because the first command to be issued is TUR which most devices can process in the middle of burning. However, depending on how a device replies to TUR during burning, cdrom driver may end up issuing further commands. This can't be resolved trivially by moving bd_claim() before doing actual open() because that means an open attempt which will end up failing could interfere other legit O_EXCL open attempts. ie. unconfirmed open attempts can fail others. This patch resolves the problem by introducing claiming block which is started by bd_start_claiming() and terminated either by bd_claim() or bd_abort_claiming(). bd_claim() from inside a claiming block is guaranteed to succeed and once a claiming block is started, other bd_start_claiming() or bd_claim() attempts block till the current claiming block is terminated. bd_claim() can still be used standalone although now it always synchronizes against claiming blocks, so the existing users will keep working without any change. blkdev_open() and open_bdev_exclusive() are converted to use claiming blocks so that exclusive open attempts from these functions don't interfere with the existing exclusive open. This problem was discovered while investigating bko#15403. https://bugzilla.kernel.org/show_bug.cgi?id=15403 The burning problem itself can be resolved by updating userspace probing tools to always open w/ O_EXCL. Signed-off-by: Tejun Heo Reported-by: Matthias-Christian Ott Cc: Kay Sievers Signed-off-by: Jens Axboe --- fs/block_dev.c | 198 ++++++++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 174 insertions(+), 24 deletions(-) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index e59440c..ea8385e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -694,11 +694,144 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, } /** + * bd_prepare_to_claim - prepare to claim a block device + * @bdev: block device of interest + * @whole: the whole device containing @bdev, may equal @bdev + * @holder: holder trying to claim @bdev + * + * Prepare to claim @bdev. This function fails if @bdev is already + * claimed by another holder and waits if another claiming is in + * progress. This function doesn't actually claim. On successful + * return, the caller has ownership of bd_claiming and bd_holder[s]. + * + * CONTEXT: + * spin_lock(&bdev_lock). Might release bdev_lock, sleep and regrab + * it multiple times. + * + * RETURNS: + * 0 if @bdev can be claimed, -EBUSY otherwise. + */ +static int bd_prepare_to_claim(struct block_device *bdev, + struct block_device *whole, void *holder) +{ +retry: + /* if someone else claimed, fail */ + if (!bd_may_claim(bdev, whole, holder)) + return -EBUSY; + + /* if someone else is claiming, wait for it to finish */ + if (whole->bd_claiming && whole->bd_claiming != holder) { + wait_queue_head_t *wq = bit_waitqueue(&whole->bd_claiming, 0); + DEFINE_WAIT(wait); + + prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); + spin_unlock(&bdev_lock); + schedule(); + finish_wait(wq, &wait); + spin_lock(&bdev_lock); + goto retry; + } + + /* yay, all mine */ + return 0; +} + +/** + * bd_start_claiming - start claiming a block device + * @bdev: block device of interest + * @holder: holder trying to claim @bdev + * + * @bdev is about to be opened exclusively. Check @bdev can be opened + * exclusively and mark that an exclusive open is in progress. Each + * successful call to this function must be matched with a call to + * either bd_claim() or bd_abort_claiming(). If this function + * succeeds, the matching bd_claim() is guaranteed to succeed. + * + * CONTEXT: + * Might sleep. + * + * RETURNS: + * Pointer to the block device containing @bdev on success, ERR_PTR() + * value on failure. + */ +static struct block_device *bd_start_claiming(struct block_device *bdev, + void *holder) +{ + struct gendisk *disk; + struct block_device *whole; + int partno, err; + + might_sleep(); + + /* + * @bdev might not have been initialized properly yet, look up + * and grab the outer block device the hard way. + */ + disk = get_gendisk(bdev->bd_dev, &partno); + if (!disk) + return ERR_PTR(-ENXIO); + + whole = bdget_disk(disk, 0); + put_disk(disk); + if (!whole) + return ERR_PTR(-ENOMEM); + + /* prepare to claim, if successful, mark claiming in progress */ + spin_lock(&bdev_lock); + + err = bd_prepare_to_claim(bdev, whole, holder); + if (err == 0) { + whole->bd_claiming = holder; + spin_unlock(&bdev_lock); + return whole; + } else { + spin_unlock(&bdev_lock); + bdput(whole); + return ERR_PTR(err); + } +} + +/* releases bdev_lock */ +static void __bd_abort_claiming(struct block_device *whole, void *holder) +{ + BUG_ON(whole->bd_claiming != holder); + whole->bd_claiming = NULL; + wake_up_bit(&whole->bd_claiming, 0); + + spin_unlock(&bdev_lock); + bdput(whole); +} + +/** + * bd_abort_claiming - abort claiming a block device + * @whole: whole block device returned by bd_start_claiming() + * @holder: holder trying to claim @bdev + * + * Abort a claiming block started by bd_start_claiming(). Note that + * @whole is not the block device to be claimed but the whole device + * returned by bd_start_claiming(). + * + * CONTEXT: + * Grabs and releases bdev_lock. + */ +static void bd_abort_claiming(struct block_device *whole, void *holder) +{ + spin_lock(&bdev_lock); + __bd_abort_claiming(whole, holder); /* releases bdev_lock */ +} + +/** * bd_claim - claim a block device * @bdev: block device to claim * @holder: holder trying to claim @bdev * - * Try to claim @bdev. + * Try to claim @bdev which must have been opened successfully. This + * function may be called with or without preceding + * blk_start_claiming(). In the former case, this function is always + * successful and terminates the claiming block. + * + * CONTEXT: + * Might sleep. * * RETURNS: * 0 if successful, -EBUSY if @bdev is already claimed. @@ -706,11 +839,14 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, int bd_claim(struct block_device *bdev, void *holder) { struct block_device *whole = bdev->bd_contains; - int res = -EBUSY; + int res; + + might_sleep(); spin_lock(&bdev_lock); - if (bd_may_claim(bdev, whole, holder)) { + res = bd_prepare_to_claim(bdev, whole, holder); + if (res == 0) { /* note that for a whole device bd_holders * will be incremented twice, and bd_holder will * be set to bd_claim before being set to holder @@ -719,10 +855,13 @@ int bd_claim(struct block_device *bdev, void *holder) whole->bd_holder = bd_claim; bdev->bd_holders++; bdev->bd_holder = holder; - res = 0; } - spin_unlock(&bdev_lock); + if (whole->bd_claiming) + __bd_abort_claiming(whole, holder); /* releases bdev_lock */ + else + spin_unlock(&bdev_lock); + return res; } EXPORT_SYMBOL(bd_claim); @@ -1338,6 +1477,7 @@ EXPORT_SYMBOL(blkdev_get); static int blkdev_open(struct inode * inode, struct file * filp) { + struct block_device *whole = NULL; struct block_device *bdev; int res; @@ -1360,22 +1500,25 @@ static int blkdev_open(struct inode * inode, struct file * filp) if (bdev == NULL) return -ENOMEM; + if (filp->f_mode & FMODE_EXCL) { + whole = bd_start_claiming(bdev, filp); + if (IS_ERR(whole)) { + bdput(bdev); + return PTR_ERR(whole); + } + } + filp->f_mapping = bdev->bd_inode->i_mapping; res = blkdev_get(bdev, filp->f_mode); - if (res) - return res; - if (filp->f_mode & FMODE_EXCL) { - res = bd_claim(bdev, filp); - if (res) - goto out_blkdev_put; + if (whole) { + if (res == 0) + BUG_ON(bd_claim(bdev, filp) != 0); + else + bd_abort_claiming(whole, filp); } - return 0; - - out_blkdev_put: - blkdev_put(bdev, filp->f_mode); return res; } @@ -1586,27 +1729,34 @@ EXPORT_SYMBOL(lookup_bdev); */ struct block_device *open_bdev_exclusive(const char *path, fmode_t mode, void *holder) { - struct block_device *bdev; - int error = 0; + struct block_device *bdev, *whole; + int error; bdev = lookup_bdev(path); if (IS_ERR(bdev)) return bdev; + whole = bd_start_claiming(bdev, holder); + if (IS_ERR(whole)) { + bdput(bdev); + return whole; + } + error = blkdev_get(bdev, mode); if (error) - return ERR_PTR(error); + goto out_abort_claiming; + error = -EACCES; if ((mode & FMODE_WRITE) && bdev_read_only(bdev)) - goto blkdev_put; - error = bd_claim(bdev, holder); - if (error) - goto blkdev_put; + goto out_blkdev_put; + BUG_ON(bd_claim(bdev, holder) != 0); return bdev; - -blkdev_put: + +out_blkdev_put: blkdev_put(bdev, mode); +out_abort_claiming: + bd_abort_claiming(whole, holder); return ERR_PTR(error); } -- cgit v1.1 From fbd9b09a177a481eda256447c881f014f29034fe Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Wed, 28 Apr 2010 17:55:06 +0400 Subject: blkdev: generalize flags for blkdev_issue_fn functions The patch just convert all blkdev_issue_xxx function to common set of flags. Wait/allocation semantics preserved. Signed-off-by: Dmitry Monakhov Signed-off-by: Jens Axboe --- fs/block_dev.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index ea8385e..dd76930 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -413,7 +413,8 @@ int blkdev_fsync(struct file *filp, struct dentry *dentry, int datasync) if (error) return error; - error = blkdev_issue_flush(bdev, NULL); + error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL, + (BLKDEV_IFL_WAIT)); if (error == -EOPNOTSUPP) error = 0; return error; -- cgit v1.1 From d3f2147307cce9eac56dd91d381709aa3f1615b3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 23 Mar 2010 11:11:05 -0400 Subject: Move grabbing s_umount to callers of grab_super() Signed-off-by: Al Viro --- fs/block_dev.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index 6dcee88..39cb659 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -245,6 +245,7 @@ struct super_block *freeze_bdev(struct block_device *bdev) sb = get_active_super(bdev); if (!sb) goto out; + down_write(&sb->s_umount); if (sb->s_flags & MS_RDONLY) { sb->s_frozen = SB_FREEZE_TRANS; up_write(&sb->s_umount); -- cgit v1.1 From 18e9e5104fcd9a973ffe3eed3816c87f2a1b6cd2 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 23 Mar 2010 10:34:56 -0400 Subject: Introduce freeze_super and thaw_super for the fsfreeze ioctl Currently the way we do freezing is by passing sb>s_bdev to freeze_bdev and then letting it do all the work. But freezing is more of an fs thing, and doesn't really have much to do with the bdev at all, all the work gets done with the super. In btrfs we do not populate s_bdev, since we can have multiple bdev's for one fs and setting s_bdev makes removing devices from a pool kind of tricky. This means that freezing a btrfs filesystem fails, which causes us to corrupt with things like tux-on-ice which use the fsfreeze mechanism. So instead of populating sb->s_bdev with a random bdev in our pool, I've broken the actual fs freezing stuff into freeze_super and thaw_super. These just take the super_block that we're freezing and does the appropriate work. It's basically just copy and pasted from freeze_bdev. I've then converted freeze_bdev over to use the new super helpers. I've tested this with ext4 and btrfs and verified everything continues to work the same as before. The only new gotcha is multiple calls to the fsfreeze ioctl will return EBUSY if the fs is already frozen. I thought this was a better solution than adding a freeze counter to the super_block, but if everybody hates this idea I'm open to suggestions. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Al Viro --- fs/block_dev.c | 74 +++++++++++++--------------------------------------------- 1 file changed, 16 insertions(+), 58 deletions(-) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index 39cb659..1aba036 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -245,38 +245,14 @@ struct super_block *freeze_bdev(struct block_device *bdev) sb = get_active_super(bdev); if (!sb) goto out; - down_write(&sb->s_umount); - if (sb->s_flags & MS_RDONLY) { - sb->s_frozen = SB_FREEZE_TRANS; - up_write(&sb->s_umount); + error = freeze_super(sb); + if (error) { + deactivate_super(sb); + bdev->bd_fsfreeze_count--; mutex_unlock(&bdev->bd_fsfreeze_mutex); - return sb; - } - - sb->s_frozen = SB_FREEZE_WRITE; - smp_wmb(); - - sync_filesystem(sb); - - sb->s_frozen = SB_FREEZE_TRANS; - smp_wmb(); - - sync_blockdev(sb->s_bdev); - - if (sb->s_op->freeze_fs) { - error = sb->s_op->freeze_fs(sb); - if (error) { - printk(KERN_ERR - "VFS:Filesystem freeze failed\n"); - sb->s_frozen = SB_UNFROZEN; - deactivate_locked_super(sb); - bdev->bd_fsfreeze_count--; - mutex_unlock(&bdev->bd_fsfreeze_mutex); - return ERR_PTR(error); - } + return ERR_PTR(error); } - up_write(&sb->s_umount); - + deactivate_super(sb); out: sync_blockdev(bdev); mutex_unlock(&bdev->bd_fsfreeze_mutex); @@ -297,40 +273,22 @@ int thaw_bdev(struct block_device *bdev, struct super_block *sb) mutex_lock(&bdev->bd_fsfreeze_mutex); if (!bdev->bd_fsfreeze_count) - goto out_unlock; + goto out; error = 0; if (--bdev->bd_fsfreeze_count > 0) - goto out_unlock; + goto out; if (!sb) - goto out_unlock; - - BUG_ON(sb->s_bdev != bdev); - down_write(&sb->s_umount); - if (sb->s_flags & MS_RDONLY) - goto out_unfrozen; - - if (sb->s_op->unfreeze_fs) { - error = sb->s_op->unfreeze_fs(sb); - if (error) { - printk(KERN_ERR - "VFS:Filesystem thaw failed\n"); - sb->s_frozen = SB_FREEZE_TRANS; - bdev->bd_fsfreeze_count++; - mutex_unlock(&bdev->bd_fsfreeze_mutex); - return error; - } - } - -out_unfrozen: - sb->s_frozen = SB_UNFROZEN; - smp_wmb(); - wake_up(&sb->s_wait_unfrozen); + goto out; - if (sb) - deactivate_locked_super(sb); -out_unlock: + error = thaw_super(sb); + if (error) { + bdev->bd_fsfreeze_count++; + mutex_unlock(&bdev->bd_fsfreeze_mutex); + return error; + } +out: mutex_unlock(&bdev->bd_fsfreeze_mutex); return 0; } -- cgit v1.1 From 7ea8085910ef3dd4f3cad6845aaa2b580d39b115 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 May 2010 17:53:25 +0200 Subject: drop unused dentry argument to ->fsync Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/block_dev.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index 26e5f50..d0b37e6 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -358,12 +358,7 @@ static loff_t block_llseek(struct file *file, loff_t offset, int origin) return retval; } -/* - * Filp is never NULL; the only case when ->fsync() is called with - * NULL first argument is nfsd_sync_dir() and that's not a directory. - */ - -int blkdev_fsync(struct file *filp, struct dentry *dentry, int datasync) +int blkdev_fsync(struct file *filp, int datasync) { struct inode *bd_inode = filp->f_mapping->host; struct block_device *bdev = I_BDEV(bd_inode); -- cgit v1.1 From 3322e79a3860fd0d50e3c1879b2e98ac582c0ff6 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Thu, 27 May 2010 22:42:19 +1000 Subject: fs: convert simple fs to new truncate Convert simple filesystems: ramfs, configfs, sysfs, block_dev to new truncate sequence. Cc: Christoph Hellwig Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- fs/block_dev.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index d0b37e6..7346c96 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -172,8 +172,9 @@ blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; - return blockdev_direct_IO_no_locking(rw, iocb, inode, I_BDEV(inode), - iov, offset, nr_segs, blkdev_get_blocks, NULL); + return blockdev_direct_IO_no_locking_newtrunc(rw, iocb, inode, + I_BDEV(inode), iov, offset, nr_segs, + blkdev_get_blocks, NULL); } int __sync_blockdev(struct block_device *bdev, int wait) @@ -309,8 +310,8 @@ static int blkdev_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata) { *pagep = NULL; - return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata, - blkdev_get_block); + return block_write_begin_newtrunc(file, mapping, pos, len, flags, + pagep, fsdata, blkdev_get_block); } static int blkdev_write_end(struct file *file, struct address_space *mapping, -- cgit v1.1 From cf3425707ed9ce0d5ebaba20bc3d22dd39e52f2f Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 26 May 2010 01:50:21 +1000 Subject: block: bd_start_claiming fix module refcount bd_start_claiming has an unbalanced module_put introduced in 6b4517a79. Signed-off-by: Nick Piggin Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- fs/block_dev.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index 7346c96..204a763 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -734,6 +734,7 @@ static struct block_device *bd_start_claiming(struct block_device *bdev, return ERR_PTR(-ENXIO); whole = bdget_disk(disk, 0); + module_put(disk->fops->owner); put_disk(disk); if (!whole) return ERR_PTR(-ENOMEM); -- cgit v1.1 From b0018361c3f934858592cbbb5e1a4f318c2a70ed Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 26 May 2010 01:51:19 +1000 Subject: block: bd_start_claiming cleanup I don't like the subtle multi-context code in bd_claim (ie. detects where it has been called based on bd_claiming). It seems clearer to just require a new function to finish a 2-part claim. Also improve commentary in bd_start_claiming as to how it should be used. Signed-off-by: Nick Piggin Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- fs/block_dev.c | 72 ++++++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 48 insertions(+), 24 deletions(-) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index 204a763..a1642ef 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -706,8 +706,13 @@ retry: * @bdev is about to be opened exclusively. Check @bdev can be opened * exclusively and mark that an exclusive open is in progress. Each * successful call to this function must be matched with a call to - * either bd_claim() or bd_abort_claiming(). If this function - * succeeds, the matching bd_claim() is guaranteed to succeed. + * either bd_finish_claiming() or bd_abort_claiming() (which do not + * fail). + * + * This function is used to gain exclusive access to the block device + * without actually causing other exclusive open attempts to fail. It + * should be used when the open sequence itself requires exclusive + * access but may subsequently fail. * * CONTEXT: * Might sleep. @@ -783,15 +788,47 @@ static void bd_abort_claiming(struct block_device *whole, void *holder) __bd_abort_claiming(whole, holder); /* releases bdev_lock */ } +/* increment holders when we have a legitimate claim. requires bdev_lock */ +static void __bd_claim(struct block_device *bdev, struct block_device *whole, + void *holder) +{ + /* note that for a whole device bd_holders + * will be incremented twice, and bd_holder will + * be set to bd_claim before being set to holder + */ + whole->bd_holders++; + whole->bd_holder = bd_claim; + bdev->bd_holders++; + bdev->bd_holder = holder; +} + +/** + * bd_finish_claiming - finish claiming a block device + * @bdev: block device of interest (passed to bd_start_claiming()) + * @whole: whole block device returned by bd_start_claiming() + * @holder: holder trying to claim @bdev + * + * Finish a claiming block started by bd_start_claiming(). + * + * CONTEXT: + * Grabs and releases bdev_lock. + */ +static void bd_finish_claiming(struct block_device *bdev, + struct block_device *whole, void *holder) +{ + spin_lock(&bdev_lock); + BUG_ON(whole->bd_claiming != holder); + BUG_ON(!bd_may_claim(bdev, whole, holder)); + __bd_claim(bdev, whole, holder); + __bd_abort_claiming(whole, holder); /* not actually an abort */ +} + /** * bd_claim - claim a block device * @bdev: block device to claim * @holder: holder trying to claim @bdev * - * Try to claim @bdev which must have been opened successfully. This - * function may be called with or without preceding - * blk_start_claiming(). In the former case, this function is always - * successful and terminates the claiming block. + * Try to claim @bdev which must have been opened successfully. * * CONTEXT: * Might sleep. @@ -807,23 +844,10 @@ int bd_claim(struct block_device *bdev, void *holder) might_sleep(); spin_lock(&bdev_lock); - res = bd_prepare_to_claim(bdev, whole, holder); - if (res == 0) { - /* note that for a whole device bd_holders - * will be incremented twice, and bd_holder will - * be set to bd_claim before being set to holder - */ - whole->bd_holders++; - whole->bd_holder = bd_claim; - bdev->bd_holders++; - bdev->bd_holder = holder; - } - - if (whole->bd_claiming) - __bd_abort_claiming(whole, holder); /* releases bdev_lock */ - else - spin_unlock(&bdev_lock); + if (res == 0) + __bd_claim(bdev, whole, holder); + spin_unlock(&bdev_lock); return res; } @@ -1477,7 +1501,7 @@ static int blkdev_open(struct inode * inode, struct file * filp) if (whole) { if (res == 0) - BUG_ON(bd_claim(bdev, filp) != 0); + bd_finish_claiming(bdev, whole, filp); else bd_abort_claiming(whole, filp); } @@ -1713,7 +1737,7 @@ struct block_device *open_bdev_exclusive(const char *path, fmode_t mode, void *h if ((mode & FMODE_WRITE) && bdev_read_only(bdev)) goto out_blkdev_put; - BUG_ON(bd_claim(bdev, holder) != 0); + bd_finish_claiming(bdev, whole, holder); return bdev; out_blkdev_put: -- cgit v1.1 From 3e6c05052c262ebe7fdd85e75e9d4f956cdd8d82 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 7 Jun 2010 20:17:38 +0200 Subject: block: remove duplicate BUG_ON() in bd_finish_claiming() We do the same BUG_ON() just a line later when calling into __bd_abort_claiming(). Reported-by: Tejun Heo Signed-off-by: Jens Axboe --- fs/block_dev.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs/block_dev.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index a1642ef..99d6af8 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -817,7 +817,6 @@ static void bd_finish_claiming(struct block_device *bdev, struct block_device *whole, void *holder) { spin_lock(&bdev_lock); - BUG_ON(whole->bd_claiming != holder); BUG_ON(!bd_may_claim(bdev, whole, holder)); __bd_claim(bdev, whole, holder); __bd_abort_claiming(whole, holder); /* not actually an abort */ -- cgit v1.1