From 8a2f8460e816f4786939a0cefbda35af6bd1a1c5 Mon Sep 17 00:00:00 2001 From: Zheng Liu Date: Sun, 19 Aug 2012 18:07:40 -0400 Subject: ext4: remove duplicated declarations in inode.c In patch cb20d5188366f04d96d2e07b1240cc92170ade40, ext4_set_bh_endio and ext4_end_io_buffer_write are declared at the beginning of inode.c, and again later on in the middle of the file. Remove the second set of duplicated function declarations. Signed-off-by: Zheng Liu Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 6324f74e0342..b4effbda7a96 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1954,9 +1954,6 @@ out: return ret; } -static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode); -static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate); - /* * Note that we don't need to start a transaction unless we're journaling data * because we should have holes filled from ext4_page_mkwrite(). We even don't -- cgit v1.2.1 From 90b0a97323f42ead278bbccbdf0e123db2add400 Mon Sep 17 00:00:00 2001 From: Carlos Maiolino Date: Mon, 17 Sep 2012 23:39:12 -0400 Subject: ext4: fix possible non-initialized variable in htree_dirblock_to_tree() htree_dirblock_to_tree() declares a non-initialized 'err' variable, which is passed as a reference to another functions expecting them to set this variable with their error codes. It's passed to ext4_bread(), which then passes it to ext4_getblk(). If ext4_map_blocks() returns 0 due to a lookup failure, leaving the ext4_getblk() buffer_head uninitialized, it will make ext4_getblk() return to ext4_bread() without initialize the 'err' variable, and ext4_bread() will return to htree_dirblock_to_tree() with this variable still uninitialized. htree_dirblock_to_tree() will pass this variable with garbage back to ext4_htree_fill_tree(), which expects a number of directory entries added to the rb-tree. which, in case, might return a fake non-zero value due the garbage left in the 'err' variable, leading the kernel to an Oops in ext4_dx_readdir(), once this is expecting a filled rb-tree node, when in turn it will have a NULL-ed one, causing an invalid page request when trying to get a fname struct from this NULL-ed rb-tree node in this line: fname = rb_entry(info->curr_node, struct fname, rb_hash); The patch itself initializes the err variable in htree_dirblock_to_tree() to avoid usage mistakes by the called functions, and also fix ext4_getblk() to return a initialized 'err' variable when ext4_map_blocks() fails a lookup. Signed-off-by: Carlos Maiolino Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b4effbda7a96..ca76b5ed6c9e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -732,11 +732,13 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, err = ext4_map_blocks(handle, inode, &map, create ? EXT4_GET_BLOCKS_CREATE : 0); + /* ensure we send some value back into *errp */ + *errp = 0; + if (err < 0) *errp = err; if (err <= 0) return NULL; - *errp = 0; bh = sb_getblk(inode->i_sb, map.m_pblk); if (!bh) { -- cgit v1.2.1 From 00d4e7362ed01987183e9528295de3213031309c Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 19 Sep 2012 22:42:36 -0400 Subject: ext4: fix potential deadlock in ext4_nonda_switch() In ext4_nonda_switch(), if the file system is getting full we used to call writeback_inodes_sb_if_idle(). The problem is that we can be holding i_mutex already, and this causes a potential deadlock when writeback_inodes_sb_if_idle() when it tries to take s_umount. (See lockdep output below). As it turns out we don't need need to hold s_umount; the fact that we are in the middle of the write(2) system call will keep the superblock pinned. Unfortunately writeback_inodes_sb() checks to make sure s_umount is taken, and the VFS uses a different mechanism for making sure the file system doesn't get unmounted out from under us. The simplest way of dealing with this is to just simply grab s_umount using a trylock, and skip kicking the writeback flusher thread in the very unlikely case that we can't take a read lock on s_umount without blocking. Also, we now check the cirteria for kicking the writeback thread before we decide to whether to fall back to non-delayed writeback, so if there are any outstanding delayed allocation writes, we try to get them resolved as soon as possible. [ INFO: possible circular locking dependency detected ] 3.6.0-rc1-00042-gce894ca #367 Not tainted ------------------------------------------------------- dd/8298 is trying to acquire lock: (&type->s_umount_key#18){++++..}, at: [] writeback_inodes_sb_if_idle+0x28/0x46 but task is already holding lock: (&sb->s_type->i_mutex_key#8){+.+...}, at: [] generic_file_aio_write+0x5f/0xd3 which lock already depends on the new lock. 2 locks held by dd/8298: #0: (sb_writers#2){.+.+.+}, at: [] generic_file_aio_write+0x56/0xd3 #1: (&sb->s_type->i_mutex_key#8){+.+...}, at: [] generic_file_aio_write+0x5f/0xd3 stack backtrace: Pid: 8298, comm: dd Not tainted 3.6.0-rc1-00042-gce894ca #367 Call Trace: [] ? console_unlock+0x345/0x372 [] print_circular_bug+0x190/0x19d [] __lock_acquire+0x86d/0xb6c [] ? mark_held_locks+0x5c/0x7b [] lock_acquire+0x66/0xb9 [] ? writeback_inodes_sb_if_idle+0x28/0x46 [] down_read+0x28/0x58 [] ? writeback_inodes_sb_if_idle+0x28/0x46 [] writeback_inodes_sb_if_idle+0x28/0x46 [] ext4_nonda_switch+0xe1/0xf4 [] ext4_da_write_begin+0x27/0x193 [] generic_file_buffered_write+0xc8/0x1bb [] __generic_file_aio_write+0x1dd/0x205 [] generic_file_aio_write+0x78/0xd3 [] ext4_file_write+0x480/0x4a6 [] ? __lock_acquire+0x41e/0xb6c [] ? sched_clock_cpu+0x11a/0x13e [] ? trace_hardirqs_off+0xb/0xd [] ? local_clock+0x37/0x4e [] do_sync_write+0x67/0x9d [] ? wait_on_retry_sync_kiocb+0x44/0x44 [] vfs_write+0x7b/0xe6 [] sys_write+0x3b/0x64 [] syscall_call+0x7/0xb Signed-off-by: "Theodore Ts'o" Cc: stable@vger.kernel.org --- fs/ext4/inode.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ca76b5ed6c9e..0a31197590d7 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2462,6 +2462,16 @@ static int ext4_nonda_switch(struct super_block *sb) free_blocks = EXT4_C2B(sbi, percpu_counter_read_positive(&sbi->s_freeclusters_counter)); dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter); + /* + * Start pushing delalloc when 1/2 of free blocks are dirty. + */ + if (dirty_blocks && (free_blocks < 2 * dirty_blocks) && + !writeback_in_progress(sb->s_bdi) && + down_read_trylock(&sb->s_umount)) { + writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE); + up_read(&sb->s_umount); + } + if (2 * free_blocks < 3 * dirty_blocks || free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) { /* @@ -2470,13 +2480,6 @@ static int ext4_nonda_switch(struct super_block *sb) */ return 1; } - /* - * Even if we don't switch but are nearing capacity, - * start pushing delalloc when 1/2 of free blocks are dirty. - */ - if (free_blocks < 2 * dirty_blocks) - writeback_inodes_sb_if_idle(sb, WB_REASON_FS_FREE_SPACE); - return 0; } -- cgit v1.2.1 From b71fc079b5d8f42b2a52743c8d2f1d35d655b1c5 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 26 Sep 2012 21:52:20 -0400 Subject: ext4: fix fdatasync() for files with only i_size changes Code tracking when transaction needs to be committed on fdatasync(2) forgets to handle a situation when only inode's i_size is changed. Thus in such situations fdatasync(2) doesn't force transaction with new i_size to disk and that can result in wrong i_size after a crash. Fix the issue by updating inode's i_datasync_tid whenever its size is updated. CC: # >= 2.6.32 Reported-by: Kristian Nielsen Signed-off-by: Jan Kara --- fs/ext4/inode.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0a31197590d7..4df5e95801b4 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4054,6 +4054,7 @@ static int ext4_do_update_inode(handle_t *handle, struct ext4_inode_info *ei = EXT4_I(inode); struct buffer_head *bh = iloc->bh; int err = 0, rc, block; + int need_datasync = 0; uid_t i_uid; gid_t i_gid; @@ -4104,7 +4105,10 @@ static int ext4_do_update_inode(handle_t *handle, raw_inode->i_file_acl_high = cpu_to_le16(ei->i_file_acl >> 32); raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl); - ext4_isize_set(raw_inode, ei->i_disksize); + if (ei->i_disksize != ext4_isize(raw_inode)) { + ext4_isize_set(raw_inode, ei->i_disksize); + need_datasync = 1; + } if (ei->i_disksize > 0x7fffffffULL) { struct super_block *sb = inode->i_sb; if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, @@ -4157,7 +4161,7 @@ static int ext4_do_update_inode(handle_t *handle, err = rc; ext4_clear_inode_state(inode, EXT4_STATE_NEW); - ext4_update_inode_fsync_trans(handle, inode, 0); + ext4_update_inode_fsync_trans(handle, inode, need_datasync); out_brelse: brelse(bh); ext4_std_error(inode->i_sb, err); -- cgit v1.2.1 From f45ee3a1ea438af96e4fd2c0b16d195e67ef235f Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Fri, 28 Sep 2012 23:21:09 -0400 Subject: ext4: ext4_inode_info diet Generic inode has unused i_private pointer which may be used as cur_aio_dio storage. TODO: If cur_aio_dio will be passed as an argument to get_block_t this allow to have concurent AIO_DIO requests. Reviewed-by: Zheng Liu Reviewed-by: Jan Kara Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 4df5e95801b4..a99588673566 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3056,7 +3056,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, * hook to the iocb. */ iocb->private = NULL; - EXT4_I(inode)->cur_aio_dio = NULL; + ext4_inode_aio_set(inode, NULL); if (!is_sync_kiocb(iocb)) { ext4_io_end_t *io_end = ext4_init_io_end(inode, GFP_NOFS); @@ -3073,7 +3073,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, * is a unwritten extents needs to be converted * when IO is completed. */ - EXT4_I(inode)->cur_aio_dio = iocb->private; + ext4_inode_aio_set(inode, io_end); } if (overwrite) @@ -3093,7 +3093,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, NULL, DIO_LOCKING); if (iocb->private) - EXT4_I(inode)->cur_aio_dio = NULL; + ext4_inode_aio_set(inode, NULL); /* * The io_end structure takes a reference to the inode, * that structure needs to be destroyed and the -- cgit v1.2.1 From 28a535f9a0df060569dcc786e5bc2e1de43d7dc7 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Sat, 29 Sep 2012 00:14:55 -0400 Subject: ext4: completed_io locking cleanup Current unwritten extent conversion state-machine is very fuzzy. - For unknown reason it performs conversion under i_mutex. What for? My diagnosis: We already protect extent tree with i_data_sem, truncate and punch_hole should wait for DIO, so the only data we have to protect is end_io->flags modification, but only flush_completed_IO and end_io_work modified this flags and we can serialize them via i_completed_io_lock. Currently all these games with mutex_trylock result in the following deadlock truncate: kworker: ext4_setattr ext4_end_io_work mutex_lock(i_mutex) inode_dio_wait(inode) ->BLOCK DEADLOCK<- mutex_trylock() inode_dio_done() #TEST_CASE1_BEGIN MNT=/mnt_scrach unlink $MNT/file fallocate -l $((1024*1024*1024)) $MNT/file aio-stress -I 100000 -O -s 100m -n -t 1 -c 10 -o 2 -o 3 $MNT/file sleep 2 truncate -s 0 $MNT/file #TEST_CASE1_END Or use 286's xfstests https://github.com/dmonakhov/xfstests/blob/devel/286 This patch makes state machine simple and clean: (1) xxx_end_io schedule final extent conversion simply by calling ext4_add_complete_io(), which append it to ei->i_completed_io_list NOTE1: because of (2A) work should be queued only if ->i_completed_io_list was empty, otherwise the work is scheduled already. (2) ext4_flush_completed_IO is responsible for handling all pending end_io from ei->i_completed_io_list Flushing sequence consists of following stages: A) LOCKED: Atomically drain completed_io_list to local_list B) Perform extents conversion C) LOCKED: move converted io's to to_free list for final deletion This logic depends on context which we was called from. D) Final end_io context destruction NOTE1: i_mutex is no longer required because end_io->flags modification is protected by ei->ext4_complete_io_lock Full list of changes: - Move all completion end_io related routines to page-io.c in order to improve logic locality - Move open coded logic from various xx_end_xx routines to ext4_add_complete_io() - remove EXT4_IO_END_FSYNC - Improve SMP scalability by removing useless i_mutex which does not protect io->flags anymore. - Reduce lock contention on i_completed_io_lock by optimizing list walk. - Rename ext4_end_io_nolock to end4_end_io and make it static - Check flush completion status to ext4_ext_punch_hole(). Because it is not good idea to punch blocks from corrupted inode. Changes since V3 (in request to Jan's comments): Fall back to active flush_completed_IO() approach in order to prevent performance issues with nolocked DIO reads. Changes since V2: Fix use-after-free caused by race truncate vs end_io_work Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 25 ++----------------------- 1 file changed, 2 insertions(+), 23 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index a99588673566..09d0488e9a15 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2881,9 +2881,6 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, { struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode; ext4_io_end_t *io_end = iocb->private; - struct workqueue_struct *wq; - unsigned long flags; - struct ext4_inode_info *ei; /* if not async direct IO or dio with 0 bytes write, just return */ if (!io_end || !size) @@ -2912,24 +2909,14 @@ out: io_end->iocb = iocb; io_end->result = ret; } - wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq; - - /* Add the io_end to per-inode completed aio dio list*/ - ei = EXT4_I(io_end->inode); - spin_lock_irqsave(&ei->i_completed_io_lock, flags); - list_add_tail(&io_end->list, &ei->i_completed_io_list); - spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); - /* queue the work to convert unwritten extents to written */ - queue_work(wq, &io_end->work); + ext4_add_complete_io(io_end); } static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate) { ext4_io_end_t *io_end = bh->b_private; - struct workqueue_struct *wq; struct inode *inode; - unsigned long flags; if (!test_clear_buffer_uninit(bh) || !io_end) goto out; @@ -2948,15 +2935,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate) */ inode = io_end->inode; ext4_set_io_unwritten_flag(inode, io_end); - - /* Add the io_end to per-inode completed io list*/ - spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags); - list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list); - spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags); - - wq = EXT4_SB(inode->i_sb)->dio_unwritten_wq; - /* queue the work to convert unwritten extents to written */ - queue_work(wq, &io_end->work); + ext4_add_complete_io(io_end); out: bh->b_private = NULL; bh->b_end_io = NULL; -- cgit v1.2.1 From 17335dcc471199717839b2fa3492ca36f70f1168 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Sat, 29 Sep 2012 00:41:21 -0400 Subject: ext4: serialize dio nonlocked reads with defrag workers Inode's block defrag and ext4_change_inode_journal_flag() may affect nonlocked DIO reads result, so proper synchronization required. - Add missed inode_dio_wait() calls where appropriate - Check inode state under extra i_dio_count reference. Reviewed-by: Jan Kara Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 09d0488e9a15..bdd399bc2abf 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4720,6 +4720,10 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) return err; } + /* Wait for all existing dio workers */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + jbd2_journal_lock_updates(journal); /* @@ -4739,6 +4743,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) ext4_set_aops(inode); jbd2_journal_unlock_updates(journal); + ext4_inode_resume_unlocked_dio(inode); /* Finally we can mark the inode as dirty. */ -- cgit v1.2.1 From 1c9114f9c0f10f58dd7e568a7152025af47b27e5 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Sat, 29 Sep 2012 00:55:23 -0400 Subject: ext4: serialize unlocked dio reads with truncate Current serialization will works only for DIO which holds i_mutex, but nonlocked DIO following race is possible: dio_nolock_read_task truncate_task ->ext4_setattr() ->inode_dio_wait() ->ext4_ext_direct_IO ->ext4_ind_direct_IO ->__blockdev_direct_IO ->ext4_get_block ->truncate_setsize() ->ext4_truncate() #alloc truncated blocks #to other inode ->submit_io() #INFORMATION LEAK In order to serialize with unlocked DIO reads we have to rearrange wait sequence 1) update i_size first 2) if i_size about to be reduced wait for outstanding DIO requests 3) and only after that truncate inode blocks Reviewed-by: Jan Kara Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index bdd399bc2abf..0bfc63331467 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4283,7 +4283,6 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) } if (attr->ia_valid & ATTR_SIZE) { - inode_dio_wait(inode); if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); @@ -4332,8 +4331,12 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) } if (attr->ia_valid & ATTR_SIZE) { - if (attr->ia_size != i_size_read(inode)) + if (attr->ia_size != i_size_read(inode)) { truncate_setsize(inode, attr->ia_size); + /* Inode size will be reduced, wait for dio in flight */ + if (orphan) + inode_dio_wait(inode); + } ext4_truncate(inode); } -- cgit v1.2.1 From 1b65007e9870e0021397b548e8cd6bbc584f9152 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Sat, 29 Sep 2012 00:56:15 -0400 Subject: ext4: endless truncate due to nonlocked dio readers If we have enough aggressive DIO readers, truncate and other dio waiters will wait forever inside inode_dio_wait(). It is reasonable to disable nonlock DIO read optimization during truncate. Reviewed-by: Jan Kara Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0bfc63331467..05ab70dd5c64 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4333,9 +4333,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid & ATTR_SIZE) { if (attr->ia_size != i_size_read(inode)) { truncate_setsize(inode, attr->ia_size); - /* Inode size will be reduced, wait for dio in flight */ - if (orphan) + /* Inode size will be reduced, wait for dio in flight. + * Temporarily disable dioread_nolock to prevent + * livelock. */ + if (orphan) { + ext4_inode_block_unlocked_dio(inode); inode_dio_wait(inode); + ext4_inode_resume_unlocked_dio(inode); + } } ext4_truncate(inode); } -- cgit v1.2.1 From 1f555cfa29e8f787d675e8390f88ce517a37271a Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Sat, 29 Sep 2012 00:58:26 -0400 Subject: ext4: serialize truncate with owerwrite DIO workers Jan Kara have spotted interesting issue: There are potential data corruption issue with direct IO overwrites racing with truncate: Like: dio write truncate_task ->ext4_ext_direct_IO ->overwrite == 1 ->down_read(&EXT4_I(inode)->i_data_sem); ->mutex_unlock(&inode->i_mutex); ->ext4_setattr() ->inode_dio_wait() ->truncate_setsize() ->ext4_truncate() ->down_write(&EXT4_I(inode)->i_data_sem); ->__blockdev_direct_IO ->ext4_get_block ->submit_io() ->up_read(&EXT4_I(inode)->i_data_sem); # truncate data blocks, allocate them to # other inode - bad stuff happens because # dio is still in flight. In order to serialize with truncate dio worker should grab extra i_dio_count reference before drop i_mutex. Reviewed-by: Jan Kara Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 05ab70dd5c64..09308ad0f314 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3010,6 +3010,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, overwrite = *((int *)iocb->private); if (overwrite) { + atomic_inc(&inode->i_dio_count); down_read(&EXT4_I(inode)->i_data_sem); mutex_unlock(&inode->i_mutex); } @@ -3107,6 +3108,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, retake_lock: /* take i_mutex locking again if we do a ovewrite dio */ if (overwrite) { + inode_dio_done(inode); up_read(&EXT4_I(inode)->i_data_sem); mutex_lock(&inode->i_mutex); } -- cgit v1.2.1 From 041bbb6d369811e948ae01f3d00414264076be35 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 30 Sep 2012 23:04:56 -0400 Subject: ext4: fix mtime update in nodelalloc mode Commits 5e8830dc85d0 and 41c4d25f78c0 introduced a regression into v3.6-rc1 for ext4 in nodealloc mode, such that mtime updates would not take place for files modified via mmap if the page was already in the page cache. This would also affect ext3 file systems mounted using the ext4 file system driver. The problem was that ext4_page_mkwrite() had a shortcut which would avoid calling __block_page_mkwrite() under some circumstances, and the above two commit transferred the responsibility of calling file_update_time() to __block_page_mkwrite --- which woudln't get called in some circumstances. Since __block_page_mkwrite() only has three callers, block_page_mkwrite(), ext4_page_mkwrite, and nilfs_page_mkwrite(), the best way to solve this is to move the responsibility for calling file_update_time() to its caller. This problem was found via xfstests #215 with a file system mounted with -o nodelalloc. Signed-off-by: "Theodore Ts'o" Reviewed-by: Jan Kara Cc: KONISHI Ryusuke Cc: stable@vger.kernel.org --- fs/ext4/inode.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 09308ad0f314..f18e786e87b0 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4788,6 +4788,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) int retries = 0; sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); /* Delalloc case is easy... */ if (test_opt(inode->i_sb, DELALLOC) && !ext4_should_journal_data(inode) && -- cgit v1.2.1