From c8585c6fcaf2011de54c3592e80a634a2b9e1a7f Mon Sep 17 00:00:00 2001 From: Daeho Jeong Date: Mon, 25 Apr 2016 23:22:35 -0400 Subject: [PATCH] ext4: fix races between changing inode journal mode and ext4_writepages In ext4, there is a race condition between changing inode journal mode and ext4_writepages(). While ext4_writepages() is executed on a non-journalled mode inode, the inode's journal mode could be enabled by ioctl() and then, some pages dirtied after switching the journal mode will be still exposed to ext4_writepages() in non-journaled mode. To resolve this problem, we use fs-wide per-cpu rw semaphore by Jan Kara's suggestion because we don't want to waste ext4_inode_info's space for this extra rare case. Signed-off-by: Daeho Jeong Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara --- fs/ext4/ext4.h | 4 ++++ fs/ext4/inode.c | 15 ++++++++++++--- fs/ext4/super.c | 4 ++++ kernel/locking/percpu-rwsem.c | 1 + 4 files changed, 21 insertions(+), 3 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index cb00b1119ec9..ba5aecc07fbc 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -33,6 +33,7 @@ #include #include #include +#include #ifdef __KERNEL__ #include #endif @@ -1508,6 +1509,9 @@ struct ext4_sb_info { struct ratelimit_state s_err_ratelimit_state; struct ratelimit_state s_warning_ratelimit_state; struct ratelimit_state s_msg_ratelimit_state; + + /* Barrier between changing inodes' journal flags and writepages ops. */ + struct percpu_rw_semaphore s_journal_flag_rwsem; }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 779ef4c11bc1..4d8ebbe00456 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2612,11 +2612,14 @@ static int ext4_writepages(struct address_space *mapping, struct blk_plug plug; bool give_up_on_write = false; + percpu_down_read(&sbi->s_journal_flag_rwsem); trace_ext4_writepages(inode, wbc); - if (dax_mapping(mapping)) - return dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, - wbc); + if (dax_mapping(mapping)) { + ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, + wbc); + goto out_writepages; + } /* * No pages to write? This is mainly a kludge to avoid starting @@ -2786,6 +2789,7 @@ retry: out_writepages: trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); + percpu_up_read(&sbi->s_journal_flag_rwsem); return ret; } @@ -5436,6 +5440,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) journal_t *journal; handle_t *handle; int err; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); /* * We have to be very careful here: changing a data block's @@ -5475,6 +5480,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) } } + percpu_down_write(&sbi->s_journal_flag_rwsem); jbd2_journal_lock_updates(journal); /* @@ -5491,6 +5497,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) err = jbd2_journal_flush(journal); if (err < 0) { jbd2_journal_unlock_updates(journal); + percpu_up_write(&sbi->s_journal_flag_rwsem); ext4_inode_resume_unlocked_dio(inode); return err; } @@ -5499,6 +5506,8 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) ext4_set_aops(inode); jbd2_journal_unlock_updates(journal); + percpu_up_write(&sbi->s_journal_flag_rwsem); + if (val) up_write(&EXT4_I(inode)->i_mmap_sem); ext4_inode_resume_unlocked_dio(inode); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 304c712dbe12..20c5d52253b4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -859,6 +859,7 @@ static void ext4_put_super(struct super_block *sb) percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); + percpu_free_rwsem(&sbi->s_journal_flag_rwsem); brelse(sbi->s_sbh); #ifdef CONFIG_QUOTA for (i = 0; i < EXT4_MAXQUOTAS; i++) @@ -3930,6 +3931,9 @@ no_journal: if (!err) err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0, GFP_KERNEL); + if (!err) + err = percpu_init_rwsem(&sbi->s_journal_flag_rwsem); + if (err) { ext4_msg(sb, KERN_ERR, "insufficient memory"); goto failed_mount6; diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index f231e0bb311c..bec0b647f9cc 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -37,6 +37,7 @@ void percpu_free_rwsem(struct percpu_rw_semaphore *brw) free_percpu(brw->fast_read_ctr); brw->fast_read_ctr = NULL; /* catch use after free bugs */ } +EXPORT_SYMBOL_GPL(percpu_free_rwsem); /* * This is the fast-path for down_read/up_read. If it succeeds we rely