From 22843291efc986ce7722610073fcf85a39b4cb13 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 10 Nov 2020 16:49:29 -0800 Subject: vfs: remove lockdep bogosity in __sb_start_write __sb_start_write has some weird looking lockdep code that claims to exist to handle nested freeze locking requests from xfs. The code as written seems broken -- if we think we hold a read lock on any of the higher freeze levels (e.g. we hold SB_FREEZE_WRITE and are trying to lock SB_FREEZE_PAGEFAULT), it converts a blocking lock attempt into a trylock. However, it's not correct to downgrade a blocking lock attempt to a trylock unless the downgrading code or the callers are prepared to deal with that situation. Neither __sb_start_write nor its callers handle this at all. For example: sb_start_pagefault ignores the return value completely, with the result that if xfs_filemap_fault loses a race with a different thread trying to fsfreeze, it will proceed without pagefault freeze protection (thereby breaking locking rules) and then unlocks the pagefault freeze lock that it doesn't own on its way out (thereby corrupting the lock state), which leads to a system hang shortly afterwards. Normally, this won't happen because our ownership of a read lock on a higher freeze protection level blocks fsfreeze from grabbing a write lock on that higher level. *However*, if lockdep is offline, lock_is_held_type unconditionally returns 1, which means that percpu_rwsem_is_held returns 1, which means that __sb_start_write unconditionally converts blocking freeze lock attempts into trylocks, even when we *don't* hold anything that would block a fsfreeze. Apparently this all held together until 5.10-rc1, when bugs in lockdep caused lockdep to shut itself off early in an fstests run, and once fstests gets to the "race writes with freezer" tests, kaboom. This might explain the long trail of vanishingly infrequent livelocks in fstests after lockdep goes offline that I've never been able to diagnose. We could fix it by spinning on the trylock if wait==true, but AFAICT the locking works fine if lockdep is not built at all (and I didn't see any complaints running fstests overnight), so remove this snippet entirely. NOTE: Commit f4b554af9931 in 2015 created the current weird logic (which used to exist in a different form in commit 5accdf82ba25c from 2012) in __sb_start_write. XFS solved this whole problem in the late 2.6 era by creating a variant of transactions (XFS_TRANS_NO_WRITECOUNT) that don't grab intwrite freeze protection, thus making lockdep's solution unnecessary. The commit claims that Dave Chinner explained that the trylock hack + comment could be removed, but nobody ever did. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Jan Kara --- fs/super.c | 33 ++++----------------------------- 1 file changed, 4 insertions(+), 29 deletions(-) (limited to 'fs/super.c') diff --git a/fs/super.c b/fs/super.c index a51c2083cd6b..e1fd667454d4 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1647,36 +1647,11 @@ EXPORT_SYMBOL(__sb_end_write); */ int __sb_start_write(struct super_block *sb, int level, bool wait) { - bool force_trylock = false; - int ret = 1; + if (!wait) + return percpu_down_read_trylock(sb->s_writers.rw_sem + level-1); -#ifdef CONFIG_LOCKDEP - /* - * We want lockdep to tell us about possible deadlocks with freezing - * but it's it bit tricky to properly instrument it. Getting a freeze - * protection works as getting a read lock but there are subtle - * problems. XFS for example gets freeze protection on internal level - * twice in some cases, which is OK only because we already hold a - * freeze protection also on higher level. Due to these cases we have - * to use wait == F (trylock mode) which must not fail. - */ - if (wait) { - int i; - - for (i = 0; i < level - 1; i++) - if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) { - force_trylock = true; - break; - } - } -#endif - if (wait && !force_trylock) - percpu_down_read(sb->s_writers.rw_sem + level-1); - else - ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1); - - WARN_ON(force_trylock && !ret); - return ret; + percpu_down_read(sb->s_writers.rw_sem + level-1); + return 1; } EXPORT_SYMBOL(__sb_start_write); -- cgit v1.2.3-70-g09d2 From 8a3c84b649b033024d2349f96234b26cbd6083a6 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 10 Nov 2020 16:50:21 -0800 Subject: vfs: separate __sb_start_write into blocking and non-blocking helpers Break this function into two helpers so that it's obvious that the trylock versions return a value that must be checked, and the blocking versions don't require that. While we're at it, clean up the return type mismatch. Signed-off-by: Darrick J. Wong Reviewed-by: Jan Kara Reviewed-by: Christoph Hellwig --- fs/aio.c | 2 +- fs/io_uring.c | 3 +-- fs/super.c | 18 ++++++++++++------ include/linux/fs.h | 21 +++++++++++---------- 4 files changed, 25 insertions(+), 19 deletions(-) (limited to 'fs/super.c') diff --git a/fs/aio.c b/fs/aio.c index c45c20d87538..6a21d8919409 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1572,7 +1572,7 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb, * we return to userspace. */ if (S_ISREG(file_inode(file)->i_mode)) { - __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true); + sb_start_write(file_inode(file)->i_sb); __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE); } req->ki_flags |= IOCB_WRITE; diff --git a/fs/io_uring.c b/fs/io_uring.c index b42dfa0243bf..4cbaddfe3d80 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3532,8 +3532,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, * we return to userspace. */ if (req->flags & REQ_F_ISREG) { - __sb_start_write(file_inode(req->file)->i_sb, - SB_FREEZE_WRITE, true); + sb_start_write(file_inode(req->file)->i_sb); __sb_writers_release(file_inode(req->file)->i_sb, SB_FREEZE_WRITE); } diff --git a/fs/super.c b/fs/super.c index e1fd667454d4..59aa59279133 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1645,16 +1645,22 @@ EXPORT_SYMBOL(__sb_end_write); * This is an internal function, please use sb_start_{write,pagefault,intwrite} * instead. */ -int __sb_start_write(struct super_block *sb, int level, bool wait) +void __sb_start_write(struct super_block *sb, int level) { - if (!wait) - return percpu_down_read_trylock(sb->s_writers.rw_sem + level-1); - - percpu_down_read(sb->s_writers.rw_sem + level-1); - return 1; + percpu_down_read(sb->s_writers.rw_sem + level - 1); } EXPORT_SYMBOL(__sb_start_write); +/* + * This is an internal function, please use sb_start_{write,pagefault,intwrite} + * instead. + */ +bool __sb_start_write_trylock(struct super_block *sb, int level) +{ + return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); +} +EXPORT_SYMBOL_GPL(__sb_start_write_trylock); + /** * sb_wait_write - wait until all writers to given file system finish * @sb: the super for which we wait diff --git a/include/linux/fs.h b/include/linux/fs.h index 0bd126418bb6..305989afd49c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1581,7 +1581,8 @@ extern struct timespec64 current_time(struct inode *inode); */ void __sb_end_write(struct super_block *sb, int level); -int __sb_start_write(struct super_block *sb, int level, bool wait); +void __sb_start_write(struct super_block *sb, int level); +bool __sb_start_write_trylock(struct super_block *sb, int level); #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) @@ -1645,12 +1646,12 @@ static inline void sb_end_intwrite(struct super_block *sb) */ static inline void sb_start_write(struct super_block *sb) { - __sb_start_write(sb, SB_FREEZE_WRITE, true); + __sb_start_write(sb, SB_FREEZE_WRITE); } -static inline int sb_start_write_trylock(struct super_block *sb) +static inline bool sb_start_write_trylock(struct super_block *sb) { - return __sb_start_write(sb, SB_FREEZE_WRITE, false); + return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); } /** @@ -1674,7 +1675,7 @@ static inline int sb_start_write_trylock(struct super_block *sb) */ static inline void sb_start_pagefault(struct super_block *sb) { - __sb_start_write(sb, SB_FREEZE_PAGEFAULT, true); + __sb_start_write(sb, SB_FREEZE_PAGEFAULT); } /* @@ -1692,12 +1693,12 @@ static inline void sb_start_pagefault(struct super_block *sb) */ static inline void sb_start_intwrite(struct super_block *sb) { - __sb_start_write(sb, SB_FREEZE_FS, true); + __sb_start_write(sb, SB_FREEZE_FS); } -static inline int sb_start_intwrite_trylock(struct super_block *sb) +static inline bool sb_start_intwrite_trylock(struct super_block *sb) { - return __sb_start_write(sb, SB_FREEZE_FS, false); + return __sb_start_write_trylock(sb, SB_FREEZE_FS); } @@ -2756,14 +2757,14 @@ static inline void file_start_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; - __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true); + sb_start_write(file_inode(file)->i_sb); } static inline bool file_start_write_trylock(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; - return __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, false); + return sb_start_write_trylock(file_inode(file)->i_sb); } static inline void file_end_write(struct file *file) -- cgit v1.2.3-70-g09d2 From 9b8523423b23ee3dfd88e32f5b7207be56a4e782 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 10 Nov 2020 16:50:21 -0800 Subject: vfs: move __sb_{start,end}_write* to fs.h Now that we've straightened out the callers, move these three functions to fs.h since they're fairly trivial. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Jan Kara --- fs/super.c | 30 ------------------------------ include/linux/fs.h | 21 ++++++++++++++++++--- 2 files changed, 18 insertions(+), 33 deletions(-) (limited to 'fs/super.c') diff --git a/fs/super.c b/fs/super.c index 59aa59279133..98bb0629ee10 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1631,36 +1631,6 @@ int super_setup_bdi(struct super_block *sb) } EXPORT_SYMBOL(super_setup_bdi); -/* - * This is an internal function, please use sb_end_{write,pagefault,intwrite} - * instead. - */ -void __sb_end_write(struct super_block *sb, int level) -{ - percpu_up_read(sb->s_writers.rw_sem + level-1); -} -EXPORT_SYMBOL(__sb_end_write); - -/* - * This is an internal function, please use sb_start_{write,pagefault,intwrite} - * instead. - */ -void __sb_start_write(struct super_block *sb, int level) -{ - percpu_down_read(sb->s_writers.rw_sem + level - 1); -} -EXPORT_SYMBOL(__sb_start_write); - -/* - * This is an internal function, please use sb_start_{write,pagefault,intwrite} - * instead. - */ -bool __sb_start_write_trylock(struct super_block *sb, int level) -{ - return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); -} -EXPORT_SYMBOL_GPL(__sb_start_write_trylock); - /** * sb_wait_write - wait until all writers to given file system finish * @sb: the super for which we wait diff --git a/include/linux/fs.h b/include/linux/fs.h index 305989afd49c..6dabd019cab0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1580,9 +1580,24 @@ extern struct timespec64 current_time(struct inode *inode); * Snapshotting support. */ -void __sb_end_write(struct super_block *sb, int level); -void __sb_start_write(struct super_block *sb, int level); -bool __sb_start_write_trylock(struct super_block *sb, int level); +/* + * These are internal functions, please use sb_start_{write,pagefault,intwrite} + * instead. + */ +static inline void __sb_end_write(struct super_block *sb, int level) +{ + percpu_up_read(sb->s_writers.rw_sem + level-1); +} + +static inline void __sb_start_write(struct super_block *sb, int level) +{ + percpu_down_read(sb->s_writers.rw_sem + level - 1); +} + +static inline bool __sb_start_write_trylock(struct super_block *sb, int level) +{ + return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); +} #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) -- cgit v1.2.3-70-g09d2