From f4245bd4ebf903541ba758ad06c118626d8c6f18 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Tue, 2 Nov 2010 14:07:17 -0400 Subject: ext4: fix lazyinit hang after removing request When the request has been removed from the list and no other request has been issued, we will end up with next wakeup scheduled to MAX_JIFFY_OFFSET which is bad. So check for that. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 40131b777af..8d1d9423ce9 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2740,7 +2740,8 @@ cont_thread: if (freezing(current)) refrigerator(); - if (time_after_eq(jiffies, next_wakeup)) { + if ((time_after_eq(jiffies, next_wakeup)) || + (MAX_JIFFY_OFFSET == next_wakeup)) { cond_resched(); continue; } -- cgit v1.2.3-70-g09d2 From b2c78cd09b6ef78c8f20190f0b3e6df1d3651b70 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 2 Nov 2010 14:19:30 -0400 Subject: ext4: "ret" may be used uninitialized in ext4_lazyinit_thread() Newer GCC's reported the following build warning: fs/ext4/super.c: In function 'ext4_lazyinit_thread': fs/ext4/super.c:2702: warning: 'ret' may be used uninitialized in this function Fix it by removing the need for the ret variable in the first place. Signed-off-by: "Lukas Czerner" Reported-by: "Stefan Richter" Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8d1d9423ce9..4d7ef31eacb 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2699,7 +2699,6 @@ static int ext4_lazyinit_thread(void *arg) struct ext4_li_request *elr; unsigned long next_wakeup; DEFINE_WAIT(wait); - int ret; BUG_ON(NULL == eli); @@ -2723,13 +2722,12 @@ cont_thread: elr = list_entry(pos, struct ext4_li_request, lr_request); - if (time_after_eq(jiffies, elr->lr_next_sched)) - ret = ext4_run_li_request(elr); - - if (ret) { - ret = 0; - ext4_remove_li_request(elr); - continue; + if (time_after_eq(jiffies, elr->lr_next_sched)) { + if (ext4_run_li_request(elr) != 0) { + /* error, remove the lazy_init job */ + ext4_remove_li_request(elr); + continue; + } } if (time_before(elr->lr_next_sched, next_wakeup)) -- cgit v1.2.3-70-g09d2 From ce7e010aef63dc6b37a2354f7c9f5f4aedb37978 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 3 Nov 2010 12:03:21 -0400 Subject: ext4: initialize the percpu counters before replaying the journal We now initialize the percpu counters before replaying the journal, but after the journal, we recalculate the global counters, to deal with the possibility of the per-blockgroup counts getting updated by the journal replay. Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 65 ++++++++++++++++++++++++++++++++++----------------------- 1 file changed, 39 insertions(+), 26 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 4d7ef31eacb..04352e9729d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3347,6 +3347,24 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) get_random_bytes(&sbi->s_next_generation, sizeof(u32)); spin_lock_init(&sbi->s_next_gen_lock); + err = percpu_counter_init(&sbi->s_freeblocks_counter, + ext4_count_free_blocks(sb)); + if (!err) { + err = percpu_counter_init(&sbi->s_freeinodes_counter, + ext4_count_free_inodes(sb)); + } + if (!err) { + err = percpu_counter_init(&sbi->s_dirs_counter, + ext4_count_dirs(sb)); + } + if (!err) { + err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0); + } + if (err) { + ext4_msg(sb, KERN_ERR, "insufficient memory"); + goto failed_mount3; + } + sbi->s_stripe = ext4_get_stripe_size(sbi); sbi->s_max_writeback_mb_bump = 128; @@ -3445,22 +3463,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } set_task_ioprio(sbi->s_journal->j_task, journal_ioprio); -no_journal: - err = percpu_counter_init(&sbi->s_freeblocks_counter, - ext4_count_free_blocks(sb)); - if (!err) - err = percpu_counter_init(&sbi->s_freeinodes_counter, - ext4_count_free_inodes(sb)); - if (!err) - err = percpu_counter_init(&sbi->s_dirs_counter, - ext4_count_dirs(sb)); - if (!err) - err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0); - if (err) { - ext4_msg(sb, KERN_ERR, "insufficient memory"); - goto failed_mount_wq; - } + /* + * The journal may have updated the bg summary counts, so we + * need to update the global counters. + */ + percpu_counter_set(&sbi->s_freeblocks_counter, + ext4_count_free_blocks(sb)); + percpu_counter_set(&sbi->s_freeinodes_counter, + ext4_count_free_inodes(sb)); + percpu_counter_set(&sbi->s_dirs_counter, + ext4_count_dirs(sb)); + percpu_counter_set(&sbi->s_dirtyblocks_counter, 0); +no_journal: EXT4_SB(sb)->dio_unwritten_wq = create_workqueue("ext4-dio-unwritten"); if (!EXT4_SB(sb)->dio_unwritten_wq) { printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n"); @@ -3610,10 +3625,6 @@ failed_mount_wq: jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; } - percpu_counter_destroy(&sbi->s_freeblocks_counter); - percpu_counter_destroy(&sbi->s_freeinodes_counter); - percpu_counter_destroy(&sbi->s_dirs_counter); - percpu_counter_destroy(&sbi->s_dirtyblocks_counter); failed_mount3: if (sbi->s_flex_groups) { if (is_vmalloc_addr(sbi->s_flex_groups)) @@ -3621,6 +3632,10 @@ failed_mount3: else kfree(sbi->s_flex_groups); } + percpu_counter_destroy(&sbi->s_freeblocks_counter); + percpu_counter_destroy(&sbi->s_freeinodes_counter); + percpu_counter_destroy(&sbi->s_dirs_counter); + percpu_counter_destroy(&sbi->s_dirtyblocks_counter); failed_mount2: for (i = 0; i < db_count; i++) brelse(sbi->s_group_desc[i]); @@ -3948,13 +3963,11 @@ static int ext4_commit_super(struct super_block *sb, int sync) else es->s_kbytes_written = cpu_to_le64(EXT4_SB(sb)->s_kbytes_written); - if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeblocks_counter)) - ext4_free_blocks_count_set(es, percpu_counter_sum_positive( - &EXT4_SB(sb)->s_freeblocks_counter)); - if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeinodes_counter)) - es->s_free_inodes_count = - cpu_to_le32(percpu_counter_sum_positive( - &EXT4_SB(sb)->s_freeinodes_counter)); + ext4_free_blocks_count_set(es, percpu_counter_sum_positive( + &EXT4_SB(sb)->s_freeblocks_counter)); + es->s_free_inodes_count = + cpu_to_le32(percpu_counter_sum_positive( + &EXT4_SB(sb)->s_freeinodes_counter)); sb->s_dirt = 0; BUFFER_TRACE(sbh, "marking dirty"); mark_buffer_dirty(sbh); -- cgit v1.2.3-70-g09d2 From f7ad6d2e9201a6e1c9ee6530a291452eb695feb8 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 8 Nov 2010 13:43:33 -0500 Subject: ext4: handle writeback of inodes which are being freed The following BUG can occur when an inode which is getting freed when it still has dirty pages outstanding, and it gets deleted (in this because it was the target of a rename). In ordered mode, we need to make sure the data pages are written just in case we crash before the rename (or unlink) is committed. If the inode is being freed then when we try to igrab the inode, we end up tripping the BUG_ON at fs/ext4/page-io.c:146. To solve this problem, we need to keep track of the number of io callbacks which are pending, and avoid destroying the inode until they have all been completed. That way we don't have to bump the inode count to keep the inode from being destroyed; an approach which doesn't work because the count could have already been dropped down to zero before the inode writeback has started (at which point we're not allowed to bump the count back up to 1, since it's already started getting freed). Thanks to Dave Chinner for suggesting this approach, which is also used by XFS. kernel BUG at /scratch_space/linux-2.6/fs/ext4/page-io.c:146! Call Trace: [] ext4_bio_write_page+0x172/0x307 [] mpage_da_submit_io+0x2f9/0x37b [] mpage_da_map_and_submit+0x2cc/0x2e2 [] mpage_add_bh_to_extent+0xc6/0xd5 [] write_cache_pages_da+0x2a4/0x3ac [] ext4_da_writepages+0x2d6/0x44d [] do_writepages+0x1c/0x25 [] __filemap_fdatawrite_range+0x4b/0x4d [] filemap_fdatawrite_range+0xe/0x10 [] jbd2_journal_begin_ordered_truncate+0x7b/0xa2 [] ext4_evict_inode+0x57/0x24c [] evict+0x22/0x92 [] iput+0x212/0x249 [] dentry_iput+0xa1/0xb9 [] d_kill+0x3d/0x5d [] dput+0x13a/0x147 [] sys_renameat+0x1b5/0x258 [] ? _atomic_dec_and_lock+0x2d/0x4c [] ? cp_new_stat+0xde/0xea [] ? sys_newlstat+0x2d/0x38 [] sys_rename+0x16/0x18 [] system_call_fastpath+0x16/0x1b Reported-by: Nick Bowler Signed-off-by: "Theodore Ts'o" Tested-by: Nick Bowler --- fs/ext4/ext4.h | 2 ++ fs/ext4/page-io.c | 59 ++++++++++++++++++++++++++++++++----------------------- fs/ext4/super.c | 2 ++ 3 files changed, 38 insertions(+), 25 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 8b5dd6369f8..670d1343f91 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -858,6 +858,7 @@ struct ext4_inode_info { spinlock_t i_completed_io_lock; /* current io_end structure for async DIO write*/ ext4_io_end_t *cur_aio_dio; + atomic_t i_ioend_count; /* Number of outstanding io_end structs */ /* * Transactions that contain inode's metadata needed to complete @@ -2060,6 +2061,7 @@ extern int ext4_move_extents(struct file *o_filp, struct file *d_filp, /* page-io.c */ extern int __init ext4_init_pageio(void); extern void ext4_exit_pageio(void); +extern void ext4_ioend_wait(struct inode *); extern void ext4_free_io_end(ext4_io_end_t *io); extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags); extern int ext4_end_io_nolock(ext4_io_end_t *io); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 46a7d6a9d97..a24c8cca737 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -32,8 +32,14 @@ static struct kmem_cache *io_page_cachep, *io_end_cachep; +#define WQ_HASH_SZ 37 +#define to_ioend_wq(v) (&ioend_wq[((unsigned long)v) % WQ_HASH_SZ]) +static wait_queue_head_t ioend_wq[WQ_HASH_SZ]; + int __init ext4_init_pageio(void) { + int i; + io_page_cachep = KMEM_CACHE(ext4_io_page, SLAB_RECLAIM_ACCOUNT); if (io_page_cachep == NULL) return -ENOMEM; @@ -42,6 +48,8 @@ int __init ext4_init_pageio(void) kmem_cache_destroy(io_page_cachep); return -ENOMEM; } + for (i = 0; i < WQ_HASH_SZ; i++) + init_waitqueue_head(&ioend_wq[i]); return 0; } @@ -52,9 +60,17 @@ void ext4_exit_pageio(void) kmem_cache_destroy(io_page_cachep); } +void ext4_ioend_wait(struct inode *inode) +{ + wait_queue_head_t *wq = to_ioend_wq(inode); + + wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_ioend_count) == 0)); +} + void ext4_free_io_end(ext4_io_end_t *io) { int i; + wait_queue_head_t *wq; BUG_ON(!io); if (io->page) @@ -69,7 +85,10 @@ void ext4_free_io_end(ext4_io_end_t *io) } } io->num_io_pages = 0; - iput(io->inode); + wq = to_ioend_wq(io->inode); + if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count) && + waitqueue_active(wq)) + wake_up_all(wq); kmem_cache_free(io_end_cachep, io); } @@ -142,8 +161,8 @@ ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags) io = kmem_cache_alloc(io_end_cachep, flags); if (io) { memset(io, 0, sizeof(*io)); - io->inode = igrab(inode); - BUG_ON(!io->inode); + atomic_inc(&EXT4_I(inode)->i_ioend_count); + io->inode = inode; INIT_WORK(&io->work, ext4_end_io_work); INIT_LIST_HEAD(&io->list); } @@ -171,35 +190,15 @@ static void ext4_end_bio(struct bio *bio, int error) struct workqueue_struct *wq; struct inode *inode; unsigned long flags; - ext4_fsblk_t err_block; int i; BUG_ON(!io_end); - inode = io_end->inode; bio->bi_private = NULL; bio->bi_end_io = NULL; if (test_bit(BIO_UPTODATE, &bio->bi_flags)) error = 0; - err_block = bio->bi_sector >> (inode->i_blkbits - 9); bio_put(bio); - if (!(inode->i_sb->s_flags & MS_ACTIVE)) { - pr_err("sb umounted, discard end_io request for inode %lu\n", - io_end->inode->i_ino); - ext4_free_io_end(io_end); - return; - } - - if (error) { - io_end->flag |= EXT4_IO_END_ERROR; - ext4_warning(inode->i_sb, "I/O error writing to inode %lu " - "(offset %llu size %ld starting block %llu)", - inode->i_ino, - (unsigned long long) io_end->offset, - (long) io_end->size, - (unsigned long long) err_block); - } - for (i = 0; i < io_end->num_io_pages; i++) { struct page *page = io_end->pages[i]->p_page; struct buffer_head *bh, *head; @@ -254,8 +253,19 @@ static void ext4_end_bio(struct bio *bio, int error) if (!partial_write) SetPageUptodate(page); } - io_end->num_io_pages = 0; + inode = io_end->inode; + + if (error) { + io_end->flag |= EXT4_IO_END_ERROR; + ext4_warning(inode->i_sb, "I/O error writing to inode %lu " + "(offset %llu size %ld starting block %llu)", + inode->i_ino, + (unsigned long long) io_end->offset, + (long) io_end->size, + (unsigned long long) + bio->bi_sector >> (inode->i_blkbits - 9)); + } /* Add the io_end to per-inode completed io list*/ spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags); @@ -305,7 +315,6 @@ static int io_submit_init(struct ext4_io_submit *io, bio->bi_private = io->io_end = io_end; bio->bi_end_io = ext4_end_bio; - io_end->inode = inode; io_end->offset = (page->index << PAGE_CACHE_SHIFT) + bh_offset(bh); io->io_bio = bio; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 04352e9729d..45653af8895 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -828,12 +828,14 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->cur_aio_dio = NULL; ei->i_sync_tid = 0; ei->i_datasync_tid = 0; + atomic_set(&ei->i_ioend_count, 0); return &ei->vfs_inode; } static void ext4_destroy_inode(struct inode *inode) { + ext4_ioend_wait(inode); if (!list_empty(&(EXT4_I(inode)->i_orphan))) { ext4_msg(inode->i_sb, KERN_ERR, "Inode %lu (%p): orphan list check failed!", -- cgit v1.2.3-70-g09d2 From 87009d86dc045d228e21242467a67a5f99347553 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Mon, 8 Nov 2010 13:47:33 -0500 Subject: ext4: do not try to grab the s_umount semaphore in ext4_quota_off It's not needed to sync the filesystem, and it fixes a lock_dep complaint. Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" Reviewed-by: Jan Kara --- fs/ext4/super.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 45653af8895..ee91e29ddf9 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4570,12 +4570,10 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, static int ext4_quota_off(struct super_block *sb, int type) { - /* Force all delayed allocation blocks to be allocated */ - if (test_opt(sb, DELALLOC)) { - down_read(&sb->s_umount); + /* Force all delayed allocation blocks to be allocated. + * Caller already holds s_umount sem */ + if (test_opt(sb, DELALLOC)) sync_filesystem(sb); - up_read(&sb->s_umount); - } return dquot_quota_off(sb, type); } -- cgit v1.2.3-70-g09d2 From 7ff9c073dd4d7200399076554f7ab9b876f196f6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 8 Nov 2010 13:51:33 -0500 Subject: ext4: Add new ext4 inode tracepoints Add ext4_evict_inode, ext4_drop_inode, ext4_mark_inode_dirty, and ext4_begin_ordered_truncate() Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 3 ++ fs/ext4/super.c | 10 +++++ include/trace/events/ext4.h | 97 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 110 insertions(+) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 19161647046..846e1e9db43 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -53,6 +53,7 @@ static inline int ext4_begin_ordered_truncate(struct inode *inode, loff_t new_size) { + trace_ext4_begin_ordered_truncate(inode, new_size); return jbd2_journal_begin_ordered_truncate( EXT4_SB(inode->i_sb)->s_journal, &EXT4_I(inode)->jinode, @@ -178,6 +179,7 @@ void ext4_evict_inode(struct inode *inode) handle_t *handle; int err; + trace_ext4_evict_inode(inode); if (inode->i_nlink) { truncate_inode_pages(&inode->i_data, 0); goto no_delete; @@ -5649,6 +5651,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) int err, ret; might_sleep(); + trace_ext4_mark_inode_dirty(inode, _RET_IP_); err = ext4_reserve_inode_write(handle, inode, &iloc); if (ext4_handle_valid(handle) && EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize && diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ee91e29ddf9..61182fe6254 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -833,6 +833,14 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } +static int ext4_drop_inode(struct inode *inode) +{ + int drop = generic_drop_inode(inode); + + trace_ext4_drop_inode(inode, drop); + return drop; +} + static void ext4_destroy_inode(struct inode *inode) { ext4_ioend_wait(inode); @@ -1175,6 +1183,7 @@ static const struct super_operations ext4_sops = { .destroy_inode = ext4_destroy_inode, .write_inode = ext4_write_inode, .dirty_inode = ext4_dirty_inode, + .drop_inode = ext4_drop_inode, .evict_inode = ext4_evict_inode, .put_super = ext4_put_super, .sync_fs = ext4_sync_fs, @@ -1196,6 +1205,7 @@ static const struct super_operations ext4_nojournal_sops = { .destroy_inode = ext4_destroy_inode, .write_inode = ext4_write_inode, .dirty_inode = ext4_dirty_inode, + .drop_inode = ext4_drop_inode, .evict_inode = ext4_evict_inode, .write_super = ext4_write_super, .put_super = ext4_put_super, diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 289010d3270..e5e345fb2a5 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -98,6 +98,103 @@ TRACE_EVENT(ext4_allocate_inode, (unsigned long) __entry->dir, __entry->mode) ); +TRACE_EVENT(ext4_evict_inode, + TP_PROTO(struct inode *inode), + + TP_ARGS(inode), + + TP_STRUCT__entry( + __field( int, dev_major ) + __field( int, dev_minor ) + __field( ino_t, ino ) + __field( int, nlink ) + ), + + TP_fast_assign( + __entry->dev_major = MAJOR(inode->i_sb->s_dev); + __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->ino = inode->i_ino; + __entry->nlink = inode->i_nlink; + ), + + TP_printk("dev %d,%d ino %lu nlink %d", + __entry->dev_major, __entry->dev_minor, + (unsigned long) __entry->ino, __entry->nlink) +); + +TRACE_EVENT(ext4_drop_inode, + TP_PROTO(struct inode *inode, int drop), + + TP_ARGS(inode, drop), + + TP_STRUCT__entry( + __field( int, dev_major ) + __field( int, dev_minor ) + __field( ino_t, ino ) + __field( int, drop ) + ), + + TP_fast_assign( + __entry->dev_major = MAJOR(inode->i_sb->s_dev); + __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->ino = inode->i_ino; + __entry->drop = drop; + ), + + TP_printk("dev %d,%d ino %lu drop %d", + __entry->dev_major, __entry->dev_minor, + (unsigned long) __entry->ino, __entry->drop) +); + +TRACE_EVENT(ext4_mark_inode_dirty, + TP_PROTO(struct inode *inode, unsigned long IP), + + TP_ARGS(inode, IP), + + TP_STRUCT__entry( + __field( int, dev_major ) + __field( int, dev_minor ) + __field( ino_t, ino ) + __field(unsigned long, ip ) + ), + + TP_fast_assign( + __entry->dev_major = MAJOR(inode->i_sb->s_dev); + __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->ino = inode->i_ino; + __entry->ip = IP; + ), + + TP_printk("dev %d,%d ino %lu caller %pF", + __entry->dev_major, __entry->dev_minor, + (unsigned long) __entry->ino, (void *)__entry->ip) +); + +TRACE_EVENT(ext4_begin_ordered_truncate, + TP_PROTO(struct inode *inode, loff_t new_size), + + TP_ARGS(inode, new_size), + + TP_STRUCT__entry( + __field( int, dev_major ) + __field( int, dev_minor ) + __field( ino_t, ino ) + __field( loff_t, new_size ) + ), + + TP_fast_assign( + __entry->dev_major = MAJOR(inode->i_sb->s_dev); + __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->ino = inode->i_ino; + __entry->new_size = new_size; + ), + + TP_printk("dev %d,%d ino %lu new_size %lld", + __entry->dev_major, __entry->dev_minor, + (unsigned long) __entry->ino, + (long long) __entry->new_size) +); + DECLARE_EVENT_CLASS(ext4__write_begin, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, -- cgit v1.2.3-70-g09d2 From f4c8cc652d9f70680dd91be60a7a455040d0a282 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 17 Nov 2010 21:46:25 -0500 Subject: ext4: missing unlock in ext4_clear_request_list() If the the li_request_list was empty then it returned with the lock held. Instead of adding a "goto unlock" I just removed that special case and let it go past the empty list_for_each_safe(). Signed-off-by: Dan Carpenter Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 61182fe6254..ef09d1443d1 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2799,9 +2799,6 @@ static void ext4_clear_request_list(void) struct ext4_li_request *elr; mutex_lock(&ext4_li_info->li_list_mtx); - if (list_empty(&ext4_li_info->li_request_list)) - return; - list_for_each_safe(pos, n, &ext4_li_info->li_request_list) { elr = list_entry(pos, struct ext4_li_request, lr_request); -- cgit v1.2.3-70-g09d2 From 5a9ae68a349aa076bc8557ee2fcf865574459282 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Fri, 19 Nov 2010 09:56:44 -0500 Subject: ext4: ext4_fill_super shouldn't return 0 on corruption At the start of ext4_fill_super, ret is set to -EINVAL, and any failure path out of that function returns ret. However, the generic_check_addressable clause sets ret = 0 (if it passes), which means that a subsequent failure (e.g. a group checksum error) returns 0 even though the mount should fail. This causes vfs_kern_mount in turn to think that the mount succeeded, leading to an oops. A simple fix is to avoid using ret for the generic_check_addressable check, which was last changed in commit 30ca22c70e3ef0a96ff84de69cd7e8561b416cb2. Signed-off-by: Darrick J. Wong Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ef09d1443d1..14ada8c50c4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3265,13 +3265,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * Test whether we have more sectors than will fit in sector_t, * and whether the max offset is addressable by the page cache. */ - ret = generic_check_addressable(sb->s_blocksize_bits, + err = generic_check_addressable(sb->s_blocksize_bits, ext4_blocks_count(es)); - if (ret) { + if (err) { ext4_msg(sb, KERN_ERR, "filesystem" " too large to mount safely on this system"); if (sizeof(sector_t) < 8) ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled"); + ret = err; goto failed_mount; } -- cgit v1.2.3-70-g09d2 From 93bb41f4f8b89ac8b4d0a734bc59634cb0a29a89 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Fri, 19 Nov 2010 21:18:35 -0500 Subject: fs: Do not dispatch FITRIM through separate super_operation There was concern that FITRIM ioctl is not common enough to be included in core vfs ioctl, as Christoph Hellwig pointed out there's no real point in dispatching this out to a separate vector instead of just through ->ioctl. So this commit removes ioctl_fstrim() from vfs ioctl and trim_fs from super_operation structure. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 1 - fs/ioctl.c | 39 --------------------------------------- include/linux/fs.h | 1 - 3 files changed, 41 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 14ada8c50c4..e32195d6aac 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1197,7 +1197,6 @@ static const struct super_operations ext4_sops = { .quota_write = ext4_quota_write, #endif .bdev_try_to_free_page = bdev_try_to_free_page, - .trim_fs = ext4_trim_fs }; static const struct super_operations ext4_nojournal_sops = { diff --git a/fs/ioctl.c b/fs/ioctl.c index e92fdbb3bc3..f855ea4fc88 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -530,41 +530,6 @@ static int ioctl_fsthaw(struct file *filp) return thaw_super(sb); } -static int ioctl_fstrim(struct file *filp, void __user *argp) -{ - struct super_block *sb = filp->f_path.dentry->d_inode->i_sb; - struct fstrim_range range; - int ret = 0; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - /* If filesystem doesn't support trim feature, return. */ - if (sb->s_op->trim_fs == NULL) - return -EOPNOTSUPP; - - /* If a blockdevice-backed filesystem isn't specified, return EINVAL. */ - if (sb->s_bdev == NULL) - return -EINVAL; - - if (argp == NULL) { - range.start = 0; - range.len = ULLONG_MAX; - range.minlen = 0; - } else if (copy_from_user(&range, argp, sizeof(range))) - return -EFAULT; - - ret = sb->s_op->trim_fs(sb, &range); - if (ret < 0) - return ret; - - if ((argp != NULL) && - (copy_to_user(argp, &range, sizeof(range)))) - return -EFAULT; - - return 0; -} - /* * When you add any new common ioctls to the switches above and below * please update compat_sys_ioctl() too. @@ -615,10 +580,6 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, error = ioctl_fsthaw(filp); break; - case FITRIM: - error = ioctl_fstrim(filp, argp); - break; - case FS_IOC_FIEMAP: return ioctl_fiemap(filp, arg); diff --git a/include/linux/fs.h b/include/linux/fs.h index 334d68a1710..eedc00b7b1e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1612,7 +1612,6 @@ struct super_operations { ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); #endif int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); - int (*trim_fs) (struct super_block *, struct fstrim_range *); }; /* -- cgit v1.2.3-70-g09d2 From 1449032be17abb69116dbc393f67ceb8bd034f92 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 14 Dec 2010 15:27:50 -0500 Subject: ext4: Turn off multiple page-io submission by default Jon Nelson has found a test case which causes postgresql to fail with the error: psql:t.sql:4: ERROR: invalid page header in block 38269 of relation base/16384/16581 Under memory pressure, it looks like part of a file can end up getting replaced by zero's. Until we can figure out the cause, we'll roll back the change and use block_write_full_page() instead of ext4_bio_write_page(). The new, more efficient writing function can be used via the mount option mblk_io_submit, so we can test and fix the new page I/O code. To reproduce the problem, install postgres 8.4 or 9.0, and pin enough memory such that the system just at the end of triggering writeback before running the following sql script: begin; create temporary table foo as select x as a, ARRAY[x] as b FROM generate_series(1, 10000000 ) AS x; create index foo_a_idx on foo (a); create index foo_b_idx on foo USING GIN (b); rollback; If the temporary table is created on a hard drive partition which is encrypted using dm_crypt, then under memory pressure, approximately 30-40% of the time, pgsql will issue the above failure. This patch should fix this problem, and the problem will come back if the file system is mounted with the mblk_io_submit mount option. Reported-by: Jon Nelson Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 1 + fs/ext4/inode.c | 5 ++++- fs/ext4/super.c | 14 ++++++++++++-- 3 files changed, 17 insertions(+), 3 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 6a5edea2d70..94ce3d7a1c4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -910,6 +910,7 @@ struct ext4_inode_info { #define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */ #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */ #define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */ +#define EXT4_MOUNT_MBLK_IO_SUBMIT 0x4000000 /* multi-block io submits */ #define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */ #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */ #define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index bdbe6990220..e659597b690 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2125,9 +2125,12 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, */ if (unlikely(journal_data && PageChecked(page))) err = __ext4_journalled_writepage(page, len); - else + else if (test_opt(inode->i_sb, MBLK_IO_SUBMIT)) err = ext4_bio_write_page(&io_submit, page, len, mpd->wbc); + else + err = block_write_full_page(page, + noalloc_get_block_write, mpd->wbc); if (!err) mpd->pages_written++; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index e32195d6aac..fb15c9c0be7 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1026,6 +1026,8 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) !(def_mount_opts & EXT4_DEFM_NODELALLOC)) seq_puts(seq, ",nodelalloc"); + if (test_opt(sb, MBLK_IO_SUBMIT)) + seq_puts(seq, ",mblk_io_submit"); if (sbi->s_stripe) seq_printf(seq, ",stripe=%lu", sbi->s_stripe); /* @@ -1239,8 +1241,8 @@ enum { Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota, Opt_noquota, Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err, Opt_resize, Opt_usrquota, Opt_grpquota, Opt_i_version, - Opt_stripe, Opt_delalloc, Opt_nodelalloc, - Opt_block_validity, Opt_noblock_validity, + Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit, + Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity, Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, @@ -1304,6 +1306,8 @@ static const match_table_t tokens = { {Opt_resize, "resize"}, {Opt_delalloc, "delalloc"}, {Opt_nodelalloc, "nodelalloc"}, + {Opt_mblk_io_submit, "mblk_io_submit"}, + {Opt_nomblk_io_submit, "nomblk_io_submit"}, {Opt_block_validity, "block_validity"}, {Opt_noblock_validity, "noblock_validity"}, {Opt_inode_readahead_blks, "inode_readahead_blks=%u"}, @@ -1725,6 +1729,12 @@ set_qf_format: case Opt_nodelalloc: clear_opt(sbi->s_mount_opt, DELALLOC); break; + case Opt_mblk_io_submit: + set_opt(sbi->s_mount_opt, MBLK_IO_SUBMIT); + break; + case Opt_nomblk_io_submit: + clear_opt(sbi->s_mount_opt, MBLK_IO_SUBMIT); + break; case Opt_stripe: if (match_int(&args[0], &option)) return 0; -- cgit v1.2.3-70-g09d2