From 5cee5815d1564bbbd505fea86f4550f1efdb5cd0 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 27 Apr 2009 16:43:51 +0200 Subject: vfs: Make sys_sync() use fsync_super() (version 4) It is unnecessarily fragile to have two places (fsync_super() and do_sync()) doing data integrity sync of the filesystem. Alter __fsync_super() to accommodate needs of both callers and use it. So after this patch __fsync_super() is the only place where we gather all the calls needed to properly send all data on a filesystem to disk. Nice bonus is that we get a complete livelock avoidance and write_supers() is now only used for periodic writeback of superblocks. sync_blockdevs() introduced a couple of patches ago is gone now. [build fixes folded] Signed-off-by: Jan Kara Signed-off-by: Al Viro --- fs/fs-writeback.c | 49 ------------------------------------------------- 1 file changed, 49 deletions(-) (limited to 'fs/fs-writeback.c') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 91013ff7dd53..e0fb2e789598 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -678,55 +678,6 @@ void sync_inodes_sb(struct super_block *sb, int wait) sync_sb_inodes(sb, &wbc); } -/** - * sync_inodes - writes all inodes to disk - * @wait: wait for completion - * - * sync_inodes() goes through each super block's dirty inode list, writes the - * inodes out, waits on the writeout and puts the inodes back on the normal - * list. - * - * This is for sys_sync(). fsync_dev() uses the same algorithm. The subtle - * part of the sync functions is that the blockdev "superblock" is processed - * last. This is because the write_inode() function of a typical fs will - * perform no I/O, but will mark buffers in the blockdev mapping as dirty. - * What we want to do is to perform all that dirtying first, and then write - * back all those inode blocks via the blockdev mapping in one sweep. So the - * additional (somewhat redundant) sync_blockdev() calls here are to make - * sure that really happens. Because if we call sync_inodes_sb(wait=1) with - * outstanding dirty inodes, the writeback goes block-at-a-time within the - * filesystem's write_inode(). This is extremely slow. - */ -static void __sync_inodes(int wait) -{ - struct super_block *sb; - - spin_lock(&sb_lock); -restart: - list_for_each_entry(sb, &super_blocks, s_list) { - sb->s_count++; - spin_unlock(&sb_lock); - down_read(&sb->s_umount); - if (sb->s_root) { - sync_inodes_sb(sb, wait); - sync_blockdev(sb->s_bdev); - } - up_read(&sb->s_umount); - spin_lock(&sb_lock); - if (__put_super_and_need_restart(sb)) - goto restart; - } - spin_unlock(&sb_lock); -} - -void sync_inodes(int wait) -{ - __sync_inodes(0); - - if (wait) - __sync_inodes(1); -} - /** * write_inode_now - write an inode to disk * @inode: inode to write to disk -- cgit v1.2.3 From 545b9fd3d737afc0bb5203b1e79194a471605acd Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Tue, 2 Jun 2009 12:07:47 +0200 Subject: fs: remove incorrect I_NEW warnings Some filesystems can call in to sync an inode that is still in the I_NEW state (eg. ext family, when mounted with -osync). This is OK because the filesystem has sole access to the new inode, so it can modify i_state without races (because no other thread should be modifying it, by definition of I_NEW). Ie. a false positive, so remove the warnings. The races are described here 7ef0d7377cb287e08f3ae94cebc919448e1f5dff, which is also where the warnings were introduced. Reported-by: Stephen Hemminger Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- fs/fs-writeback.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'fs/fs-writeback.c') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e0fb2e789598..efcedb6d9cbc 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -289,7 +289,6 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc) int ret; BUG_ON(inode->i_state & I_SYNC); - WARN_ON(inode->i_state & I_NEW); /* Set I_SYNC, reset I_DIRTY */ dirty = inode->i_state & I_DIRTY; @@ -314,7 +313,6 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc) } spin_lock(&inode_lock); - WARN_ON(inode->i_state & I_NEW); inode->i_state &= ~I_SYNC; if (!(inode->i_state & I_FREEING)) { if (!(inode->i_state & I_DIRTY) && -- cgit v1.2.3 From 4195f73d1329e49727bcceb028e58cb38376c2b0 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Thu, 28 May 2009 09:01:15 +0200 Subject: fs: block_dump missing dentry locking I think the block_dump output in __mark_inode_dirty is missing dentry locking. Surely the i_dentry list can change any time, so we may not even *get* a dentry there. If we do get one by chance, then it would appear to be able to go away or get renamed at any time... Signed-off-by: Al Viro --- fs/fs-writeback.c | 41 ++++++++++++++++++++++++----------------- 1 file changed, 24 insertions(+), 17 deletions(-) (limited to 'fs/fs-writeback.c') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index efcedb6d9cbc..40308e98c6a4 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -64,6 +64,28 @@ static void writeback_release(struct backing_dev_info *bdi) clear_bit(BDI_pdflush, &bdi->state); } +static noinline void block_dump___mark_inode_dirty(struct inode *inode) +{ + if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) { + struct dentry *dentry; + const char *name = "?"; + + dentry = d_find_alias(inode); + if (dentry) { + spin_lock(&dentry->d_lock); + name = (const char *) dentry->d_name.name; + } + printk(KERN_DEBUG + "%s(%d): dirtied inode %lu (%s) on %s\n", + current->comm, task_pid_nr(current), inode->i_ino, + name, inode->i_sb->s_id); + if (dentry) { + spin_unlock(&dentry->d_lock); + dput(dentry); + } + } +} + /** * __mark_inode_dirty - internal function * @inode: inode to mark @@ -114,23 +136,8 @@ void __mark_inode_dirty(struct inode *inode, int flags) if ((inode->i_state & flags) == flags) return; - if (unlikely(block_dump)) { - struct dentry *dentry = NULL; - const char *name = "?"; - - if (!list_empty(&inode->i_dentry)) { - dentry = list_entry(inode->i_dentry.next, - struct dentry, d_alias); - if (dentry && dentry->d_name.name) - name = (const char *) dentry->d_name.name; - } - - if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) - printk(KERN_DEBUG - "%s(%d): dirtied inode %lu (%s) on %s\n", - current->comm, task_pid_nr(current), inode->i_ino, - name, inode->i_sb->s_id); - } + if (unlikely(block_dump)) + block_dump___mark_inode_dirty(inode); spin_lock(&inode_lock); if ((inode->i_state & flags) != flags) { -- cgit v1.2.3 From 84a892456046921a40646114deed65e2df93a1bc Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Tue, 16 Jun 2009 15:33:17 -0700 Subject: writeback: skip new or to-be-freed inodes 1) I_FREEING tests should be coupled with I_CLEAR The two I_FREEING tests are racy because clear_inode() can set i_state to I_CLEAR between the clear of I_SYNC and the test of I_FREEING. 2) skip I_WILL_FREE inodes in generic_sync_sb_inodes() to avoid possible races with generic_forget_inode() generic_forget_inode() sets I_WILL_FREE call writeback on its own, so generic_sync_sb_inodes() shall not try to step in and create possible races: generic_forget_inode inode->i_state |= I_WILL_FREE; spin_unlock(&inode_lock); generic_sync_sb_inodes() spin_lock(&inode_lock); __iget(inode); __writeback_single_inode // see non zero i_count may WARN here ==> WARN_ON(inode->i_state & I_WILL_FREE); spin_unlock(&inode_lock); may call generic_forget_inode again ==> iput(inode); The above race and warning didn't turn up because writeback_inodes() holds the s_umount lock, so generic_forget_inode() finds MS_ACTIVE and returns early. But we are not sure the UBIFS calls and future callers will guarantee that. So skip I_WILL_FREE inodes for the sake of safety. Cc: Eric Sandeen Acked-by: Jeff Layton Cc: Masayoshi MIZUMA Signed-off-by: Wu Fengguang Cc: Artem Bityutskiy Cc: Christoph Hellwig Acked-by: Jan Kara Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fs-writeback.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs/fs-writeback.c') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 40308e98c6a4..caf049146ca2 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -321,7 +321,7 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc) spin_lock(&inode_lock); inode->i_state &= ~I_SYNC; - if (!(inode->i_state & I_FREEING)) { + if (!(inode->i_state & (I_FREEING | I_CLEAR))) { if (!(inode->i_state & I_DIRTY) && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { /* @@ -492,7 +492,7 @@ void generic_sync_sb_inodes(struct super_block *sb, break; } - if (inode->i_state & I_NEW) { + if (inode->i_state & (I_NEW | I_WILL_FREE)) { requeue_io(inode); continue; } @@ -523,7 +523,7 @@ void generic_sync_sb_inodes(struct super_block *sb, if (current_is_pdflush() && !writeback_acquire(bdi)) break; - BUG_ON(inode->i_state & I_FREEING); + BUG_ON(inode->i_state & (I_FREEING | I_CLEAR)); __iget(inode); pages_skipped = wbc->pages_skipped; __writeback_single_inode(inode, wbc); -- cgit v1.2.3 From 01c031945f2755c7afaaf456088543312f2b72ea Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Jun 2009 13:35:40 +0200 Subject: cleanup __writeback_single_inode There is no reason to for the split between __writeback_single_inode and __sync_single_inode, the former just does a couple of checks before tail-calling the latter. So merge the two, and while we're at it split out the I_SYNC waiting case for data integrity writers, as it's logically separate function. Finally rename __writeback_single_inode to writeback_single_inode. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/fs-writeback.c | 100 +++++++++++++++++++++++++++--------------------------- 1 file changed, 50 insertions(+), 50 deletions(-) (limited to 'fs/fs-writeback.c') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index caf049146ca2..c54226be5294 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -278,7 +278,26 @@ int sb_has_dirty_inodes(struct super_block *sb) EXPORT_SYMBOL(sb_has_dirty_inodes); /* - * Write a single inode's dirty pages and inode data out to disk. + * Wait for writeback on an inode to complete. + */ +static void inode_wait_for_writeback(struct inode *inode) +{ + DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC); + wait_queue_head_t *wqh; + + wqh = bit_waitqueue(&inode->i_state, __I_SYNC); + do { + spin_unlock(&inode_lock); + __wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE); + spin_lock(&inode_lock); + } while (inode->i_state & I_SYNC); +} + +/* + * Write out an inode's dirty pages. Called under inode_lock. Either the + * caller has ref on the inode (either via __iget or via syscall against an fd) + * or the inode has I_WILL_FREE set (via generic_forget_inode) + * * If `wait' is set, wait on the writeout. * * The whole writeout design is quite complex and fragile. We want to avoid @@ -288,13 +307,38 @@ EXPORT_SYMBOL(sb_has_dirty_inodes); * Called under inode_lock. */ static int -__sync_single_inode(struct inode *inode, struct writeback_control *wbc) +writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { - unsigned dirty; struct address_space *mapping = inode->i_mapping; int wait = wbc->sync_mode == WB_SYNC_ALL; + unsigned dirty; int ret; + if (!atomic_read(&inode->i_count)) + WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); + else + WARN_ON(inode->i_state & I_WILL_FREE); + + if (inode->i_state & I_SYNC) { + /* + * If this inode is locked for writeback and we are not doing + * writeback-for-data-integrity, move it to s_more_io so that + * writeback can proceed with the other inodes on s_io. + * + * We'll have another go at writing back this inode when we + * completed a full scan of s_io. + */ + if (!wait) { + requeue_io(inode); + return 0; + } + + /* + * It's a data-integrity sync. We must wait. + */ + inode_wait_for_writeback(inode); + } + BUG_ON(inode->i_state & I_SYNC); /* Set I_SYNC, reset I_DIRTY */ @@ -389,50 +433,6 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc) return ret; } -/* - * Write out an inode's dirty pages. Called under inode_lock. Either the - * caller has ref on the inode (either via __iget or via syscall against an fd) - * or the inode has I_WILL_FREE set (via generic_forget_inode) - */ -static int -__writeback_single_inode(struct inode *inode, struct writeback_control *wbc) -{ - wait_queue_head_t *wqh; - - if (!atomic_read(&inode->i_count)) - WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); - else - WARN_ON(inode->i_state & I_WILL_FREE); - - if ((wbc->sync_mode != WB_SYNC_ALL) && (inode->i_state & I_SYNC)) { - /* - * We're skipping this inode because it's locked, and we're not - * doing writeback-for-data-integrity. Move it to s_more_io so - * that writeback can proceed with the other inodes on s_io. - * We'll have another go at writing back this inode when we - * completed a full scan of s_io. - */ - requeue_io(inode); - return 0; - } - - /* - * It's a data-integrity sync. We must wait. - */ - if (inode->i_state & I_SYNC) { - DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC); - - wqh = bit_waitqueue(&inode->i_state, __I_SYNC); - do { - spin_unlock(&inode_lock); - __wait_on_bit(wqh, &wq, inode_wait, - TASK_UNINTERRUPTIBLE); - spin_lock(&inode_lock); - } while (inode->i_state & I_SYNC); - } - return __sync_single_inode(inode, wbc); -} - /* * Write out a superblock's list of dirty inodes. A wait will be performed * upon no inodes, all inodes or the final one, depending upon sync_mode. @@ -526,7 +526,7 @@ void generic_sync_sb_inodes(struct super_block *sb, BUG_ON(inode->i_state & (I_FREEING | I_CLEAR)); __iget(inode); pages_skipped = wbc->pages_skipped; - __writeback_single_inode(inode, wbc); + writeback_single_inode(inode, wbc); if (current_is_pdflush()) writeback_release(bdi); if (wbc->pages_skipped != pages_skipped) { @@ -708,7 +708,7 @@ int write_inode_now(struct inode *inode, int sync) might_sleep(); spin_lock(&inode_lock); - ret = __writeback_single_inode(inode, &wbc); + ret = writeback_single_inode(inode, &wbc); spin_unlock(&inode_lock); if (sync) inode_sync_wait(inode); @@ -732,7 +732,7 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc) int ret; spin_lock(&inode_lock); - ret = __writeback_single_inode(inode, wbc); + ret = writeback_single_inode(inode, wbc); spin_unlock(&inode_lock); return ret; } -- cgit v1.2.3