From 58590b06d79f7ce5ab64ff3b6d537180fa50dc84 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Oct 2010 21:23:12 -0400 Subject: ext4: fix EOFBLOCKS_FL handling It turns out we have several problems with how EOFBLOCKS_FL is handled. First of all, there was a fencepost error where we were not clearing the EOFBLOCKS_FL when fill in the last uninitialized block, but rather when we allocate the next block _after_ the uninitalized block. Secondly we were not testing to see if we needed to clear the EOFBLOCKS_FL when writing to the file O_DIRECT or when were converting an uninitialized block (which is the most common case). Google-Bug-Id: 2928259 Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 98 +++++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 69 insertions(+), 29 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 06328d3e571..82027841022 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3180,6 +3180,57 @@ static void unmap_underlying_metadata_blocks(struct block_device *bdev, unmap_underlying_metadata(bdev, block + i); } +/* + * Handle EOFBLOCKS_FL flag, clearing it if necessary + */ +static int check_eofblocks_fl(handle_t *handle, struct inode *inode, + struct ext4_map_blocks *map, + struct ext4_ext_path *path, + unsigned int len) +{ + int i, depth; + struct ext4_extent_header *eh; + struct ext4_extent *ex, *last_ex; + + if (!ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)) + return 0; + + depth = ext_depth(inode); + eh = path[depth].p_hdr; + ex = path[depth].p_ext; + + if (unlikely(!eh->eh_entries)) { + EXT4_ERROR_INODE(inode, "eh->eh_entries == 0 and " + "EOFBLOCKS_FL set"); + return -EIO; + } + last_ex = EXT_LAST_EXTENT(eh); + /* + * We should clear the EOFBLOCKS_FL flag if we are writing the + * last block in the last extent in the file. We test this by + * first checking to see if the caller to + * ext4_ext_get_blocks() was interested in the last block (or + * a block beyond the last block) in the current extent. If + * this turns out to be false, we can bail out from this + * function immediately. + */ + if (map->m_lblk + len < le32_to_cpu(last_ex->ee_block) + + ext4_ext_get_actual_len(last_ex)) + return 0; + /* + * If the caller does appear to be planning to write at or + * beyond the end of the current extent, we then test to see + * if the current extent is the last extent in the file, by + * checking to make sure it was reached via the rightmost node + * at each level of the tree. + */ + for (i = depth-1; i >= 0; i--) + if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr)) + return 0; + ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS); + return ext4_mark_inode_dirty(handle, inode); +} + static int ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, @@ -3217,8 +3268,12 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, if ((flags & EXT4_GET_BLOCKS_CONVERT)) { ret = ext4_convert_unwritten_extents_endio(handle, inode, path); - if (ret >= 0) + if (ret >= 0) { ext4_update_inode_fsync_trans(handle, inode, 1); + err = check_eofblocks_fl(handle, inode, map, path, + map->m_len); + } else + err = ret; goto out2; } /* buffered IO case */ @@ -3244,8 +3299,13 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, /* buffered write, writepage time, convert*/ ret = ext4_ext_convert_to_initialized(handle, inode, map, path); - if (ret >= 0) + if (ret >= 0) { ext4_update_inode_fsync_trans(handle, inode, 1); + err = check_eofblocks_fl(handle, inode, map, path, map->m_len); + if (err < 0) + goto out2; + } + out: if (ret <= 0) { err = ret; @@ -3292,6 +3352,7 @@ out2: } return err ? err : allocated; } + /* * Block allocation/map/preallocation routine for extents based files * @@ -3315,9 +3376,9 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, { struct ext4_ext_path *path = NULL; struct ext4_extent_header *eh; - struct ext4_extent newex, *ex, *last_ex; + struct ext4_extent newex, *ex; ext4_fsblk_t newblock; - int i, err = 0, depth, ret, cache_type; + int err = 0, depth, ret, cache_type; unsigned int allocated = 0; struct ext4_allocation_request ar; ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio; @@ -3497,31 +3558,10 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, map->m_flags |= EXT4_MAP_UNINIT; } - if (unlikely(ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))) { - if (unlikely(!eh->eh_entries)) { - EXT4_ERROR_INODE(inode, - "eh->eh_entries == 0 and " - "EOFBLOCKS_FL set"); - err = -EIO; - goto out2; - } - last_ex = EXT_LAST_EXTENT(eh); - /* - * If the current leaf block was reached by looking at - * the last index block all the way down the tree, and - * we are extending the inode beyond the last extent - * in the current leaf block, then clear the - * EOFBLOCKS_FL flag. - */ - for (i = depth-1; i >= 0; i--) { - if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr)) - break; - } - if ((i < 0) && - (map->m_lblk + ar.len > le32_to_cpu(last_ex->ee_block) + - ext4_ext_get_actual_len(last_ex))) - ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS); - } + err = check_eofblocks_fl(handle, inode, map, path, ar.len); + if (err) + goto out2; + err = ext4_ext_insert_extent(handle, inode, path, &newex, flags); if (err) { /* free data blocks we just allocated */ -- cgit v1.2.3-18-g5258 From 39e3ac2599a5f9aba499b5f8af809108e70a6163 Mon Sep 17 00:00:00 2001 From: Brian King Date: Wed, 27 Oct 2010 21:25:12 -0400 Subject: jbd2: Fix I/O hang in jbd2_journal_release_jbd_inode This fixes a hang seen in jbd2_journal_release_jbd_inode on a lot of Power 6 systems running with ext4. When we get in the hung state, all I/O to the disk in question gets blocked where we stay indefinitely. Looking at the task list, I can see we are stuck in jbd2_journal_release_jbd_inode waiting on a wake up. I added some debug code to detect this scenario and dump additional data if we were stuck in jbd2_journal_release_jbd_inode for longer than 30 minutes. When it hit, I was able to see that i_flags was 0, suggesting we missed the wake up. This patch changes i_flags to be an unsigned long, uses bit operators to access it, and adds barriers around the accesses. Prior to applying this patch, we were regularly hitting this hang on numerous systems in our test environment. After applying the patch, the hangs no longer occur. Signed-off-by: Brian King Signed-off-by: "Theodore Ts'o" --- fs/jbd2/commit.c | 12 ++++++++---- fs/jbd2/journal.c | 4 +++- include/linux/jbd2.h | 2 +- 3 files changed, 12 insertions(+), 6 deletions(-) diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 7c068c189d8..6494c81e3b0 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -26,7 +26,9 @@ #include #include #include +#include #include +#include /* * Default IO end handler for temporary BJ_IO buffer_heads. @@ -236,7 +238,7 @@ static int journal_submit_data_buffers(journal_t *journal, spin_lock(&journal->j_list_lock); list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) { mapping = jinode->i_vfs_inode->i_mapping; - jinode->i_flags |= JI_COMMIT_RUNNING; + set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags); spin_unlock(&journal->j_list_lock); /* * submit the inode data buffers. We use writepage @@ -251,7 +253,8 @@ static int journal_submit_data_buffers(journal_t *journal, spin_lock(&journal->j_list_lock); J_ASSERT(jinode->i_transaction == commit_transaction); commit_transaction->t_flushed_data_blocks = 1; - jinode->i_flags &= ~JI_COMMIT_RUNNING; + clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags); + smp_mb__after_clear_bit(); wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING); } spin_unlock(&journal->j_list_lock); @@ -272,7 +275,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal, /* For locking, see the comment in journal_submit_data_buffers() */ spin_lock(&journal->j_list_lock); list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) { - jinode->i_flags |= JI_COMMIT_RUNNING; + set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags); spin_unlock(&journal->j_list_lock); err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping); if (err) { @@ -288,7 +291,8 @@ static int journal_finish_inode_data_buffers(journal_t *journal, ret = err; } spin_lock(&journal->j_list_lock); - jinode->i_flags &= ~JI_COMMIT_RUNNING; + clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags); + smp_mb__after_clear_bit(); wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING); } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 0e8014ea6b9..75e1b5a0bc2 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -42,12 +42,14 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include #include #include +#include EXPORT_SYMBOL(jbd2_journal_extend); EXPORT_SYMBOL(jbd2_journal_stop); @@ -2206,7 +2208,7 @@ void jbd2_journal_release_jbd_inode(journal_t *journal, restart: spin_lock(&journal->j_list_lock); /* Is commit writing out inode - we have to wait */ - if (jinode->i_flags & JI_COMMIT_RUNNING) { + if (test_bit(__JI_COMMIT_RUNNING, &jinode->i_flags)) { wait_queue_head_t *wq; DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING); wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 0b52924a0cb..2ae86aa21fc 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -395,7 +395,7 @@ struct jbd2_inode { struct inode *i_vfs_inode; /* Flags of inode [j_list_lock] */ - unsigned int i_flags; + unsigned long i_flags; }; struct jbd2_revoke_table_s; -- cgit v1.2.3-18-g5258 From b853fd364810a241050778124842a8c415c72a69 Mon Sep 17 00:00:00 2001 From: Wen Congyang Date: Wed, 27 Oct 2010 21:27:12 -0400 Subject: ext4: avoid null dereference in trace_ext4_mballoc_discard ac->inode is set to null in function ext4_mb_release_group_pa(), and then trace_ext4_mballoc_discard(ac) is called, the kernel will panic. BUG: unable to handle kernel NULL pointer dereference at 000000a4 IP: [] ftrace_raw_event_ext4__mballoc+0x54/0xc0 [ext4] *pdpt = 0000000000abd001 *pde = 0000000000000000 Oops: 0000 [#1] SMP Pid: 550, comm: flush-8:16 Not tainted 2.6.36-rc1 #1 SE7320EP2/Altos G530 EIP: 0060:[] EFLAGS: 00010206 CPU: 1 EIP is at ftrace_raw_event_ext4__mballoc+0x54/0xc0 [ext4] EAX: f32ac840 EBX: f3f1cf88 ECX: f32ac840 EDX: 00000000 ESI: f32ac83c EDI: f880b9d8 EBP: 00000000 ESP: f4b77ae4 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 Process flush-8:16 (pid: 550, ti=f4b76000 task=f613e540 task.ti=f4b76000) Call Trace: [] ? ext4_mb_release_group_pa+0x121/0x150 [ext4] [] ? ext4_mb_discard_group_preallocations+0x336/0x400 [ext4] [] ? ext4_mb_new_blocks+0x3d1/0x4f0 [ext4] [] ? __make_request+0x10b/0x440 [] ? ext4_ext_map_blocks+0x1334/0x1980 [ext4] [] ? rb_reserve_next_event+0xaa/0x3b0 [] ? ext4_map_blocks+0xd6/0x1d0 [ext4] [] ? mpage_da_map_blocks+0xc7/0x8a0 [ext4] [] ? find_get_pages_tag+0x38/0x110 [] ? __pagevec_release+0x15/0x20 [] ? ext4_da_writepages+0x2b5/0x5d0 [ext4] [] ? __writepage+0x0/0x30 [] ? do_writepages+0x14/0x30 [] ? writeback_single_inode+0xa0/0x240 [] ? writeback_sb_inodes+0xc1/0x180 [] ? writeback_inodes_wb+0x88/0x140 [] ? wb_writeback+0x20b/0x320 [] ? lock_timer_base+0x27/0x50 [] ? wb_do_writeback+0x150/0x190 [] ? bdi_writeback_thread+0x88/0x1f0 [] ? complete+0x40/0x60 [] ? bdi_writeback_thread+0x0/0x1f0 [] ? kthread+0x74/0x80 [] ? kthread+0x0/0x80 [] ? kernel_thread_helper+0x6/0x10 Signed-off-by: Wen Congyang Acked-by: Steven Rostedt Signed-off-by: "Theodore Ts'o" --- include/trace/events/ext4.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 01e9e0076a9..6a1fcff95f7 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -796,8 +796,9 @@ DECLARE_EVENT_CLASS(ext4__mballoc, ), TP_fast_assign( - __entry->dev = ac->ac_inode->i_sb->s_dev; - __entry->ino = ac->ac_inode->i_ino; + __entry->dev = ac->ac_sb->s_dev; + __entry->ino = ac->ac_inode ? + ac->ac_inode->i_ino : 0; __entry->result_logical = ac->ac_b_ex.fe_logical; __entry->result_start = ac->ac_b_ex.fe_start; __entry->result_group = ac->ac_b_ex.fe_group; -- cgit v1.2.3-18-g5258 From fb1813f4a8a27bbd4735967e46931e61fc837a3e Mon Sep 17 00:00:00 2001 From: Curt Wohlgemuth Date: Wed, 27 Oct 2010 21:29:12 -0400 Subject: ext4: use dedicated slab caches for group_info structures ext4_group_info structures are currently allocated with kmalloc(). With a typical 4K block size, these are 136 bytes each -- meaning they'll each consume a 256-byte slab object. On a system with many ext4 large partitions, that's a lot of wasted kernel slab space. (E.g., a single 1TB partition will have about 8000 block groups, using about 2MB of slab, of which nearly 1MB is wasted.) This patch creates an array of slab pointers created as needed -- depending on the superblock block size -- and uses these slabs to allocate the group info objects. Google-Bug-Id: 2980809 Signed-off-by: Curt Wohlgemuth Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 1 + fs/ext4/mballoc.c | 98 +++++++++++++++++++++++++++++++++++++++++++------------ 2 files changed, 78 insertions(+), 21 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 889ec9d5e6a..b364b9df09b 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -205,6 +205,7 @@ typedef struct ext4_io_end { #define EXT4_MIN_BLOCK_SIZE 1024 #define EXT4_MAX_BLOCK_SIZE 65536 #define EXT4_MIN_BLOCK_LOG_SIZE 10 +#define EXT4_MAX_BLOCK_LOG_SIZE 16 #ifdef __KERNEL__ # define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize) #else diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 4b4ad4b7ce5..d4714d6cf7d 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -338,6 +338,14 @@ static struct kmem_cache *ext4_pspace_cachep; static struct kmem_cache *ext4_ac_cachep; static struct kmem_cache *ext4_free_ext_cachep; + +/* We create slab caches for groupinfo data structures based on the + * superblock block size. There will be one per mounted filesystem for + * each unique s_blocksize_bits */ +#define NR_GRPINFO_CACHES \ + (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE + 1) +static struct kmem_cache *ext4_groupinfo_caches[NR_GRPINFO_CACHES]; + static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group); static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, @@ -2233,15 +2241,24 @@ static const struct file_operations ext4_mb_seq_groups_fops = { .release = seq_release, }; +static struct kmem_cache *get_groupinfo_cache(int blocksize_bits) +{ + int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; + struct kmem_cache *cachep = ext4_groupinfo_caches[cache_index]; + + BUG_ON(!cachep); + return cachep; +} /* Create and initialize ext4_group_info data for the given group. */ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *desc) { - int i, len; + int i; int metalen = 0; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_info **meta_group_info; + struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); /* * First check if this group is the first of a reserved block. @@ -2261,22 +2278,16 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, meta_group_info; } - /* - * calculate needed size. if change bb_counters size, - * don't forget about ext4_mb_generate_buddy() - */ - len = offsetof(typeof(**meta_group_info), - bb_counters[sb->s_blocksize_bits + 2]); - meta_group_info = sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]; i = group & (EXT4_DESC_PER_BLOCK(sb) - 1); - meta_group_info[i] = kzalloc(len, GFP_KERNEL); + meta_group_info[i] = kmem_cache_alloc(cachep, GFP_KERNEL); if (meta_group_info[i] == NULL) { printk(KERN_ERR "EXT4-fs: can't allocate buddy mem\n"); goto exit_group_info; } + memset(meta_group_info[i], 0, kmem_cache_size(cachep)); set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(meta_group_info[i]->bb_state)); @@ -2331,6 +2342,7 @@ static int ext4_mb_init_backend(struct super_block *sb) int num_meta_group_infos_max; int array_size; struct ext4_group_desc *desc; + struct kmem_cache *cachep; /* This is the number of blocks used by GDT */ num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - @@ -2388,8 +2400,9 @@ static int ext4_mb_init_backend(struct super_block *sb) return 0; err_freebuddy: + cachep = get_groupinfo_cache(sb->s_blocksize_bits); while (i-- > 0) - kfree(ext4_get_group_info(sb, i)); + kmem_cache_free(cachep, ext4_get_group_info(sb, i)); i = num_meta_group_infos; while (i-- > 0) kfree(sbi->s_group_info[i]); @@ -2406,19 +2419,48 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) unsigned offset; unsigned max; int ret; + int cache_index; + struct kmem_cache *cachep; + char *namep = NULL; i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_offsets); sbi->s_mb_offsets = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_offsets == NULL) { - return -ENOMEM; + ret = -ENOMEM; + goto out; } i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_maxs); sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_maxs == NULL) { - kfree(sbi->s_mb_offsets); - return -ENOMEM; + ret = -ENOMEM; + goto out; + } + + cache_index = sb->s_blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; + cachep = ext4_groupinfo_caches[cache_index]; + if (!cachep) { + char name[32]; + int len = offsetof(struct ext4_group_info, + bb_counters[sb->s_blocksize_bits + 2]); + + sprintf(name, "ext4_groupinfo_%d", sb->s_blocksize_bits); + namep = kstrdup(name, GFP_KERNEL); + if (!namep) { + ret = -ENOMEM; + goto out; + } + + /* Need to free the kmem_cache_name() when we + * destroy the slab */ + cachep = kmem_cache_create(namep, len, 0, + SLAB_RECLAIM_ACCOUNT, NULL); + if (!cachep) { + ret = -ENOMEM; + goto out; + } + ext4_groupinfo_caches[cache_index] = cachep; } /* order 0 is regular bitmap */ @@ -2439,9 +2481,7 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) /* init file for buddy data */ ret = ext4_mb_init_backend(sb); if (ret != 0) { - kfree(sbi->s_mb_offsets); - kfree(sbi->s_mb_maxs); - return ret; + goto out; } spin_lock_init(&sbi->s_md_lock); @@ -2456,9 +2496,8 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group); if (sbi->s_locality_groups == NULL) { - kfree(sbi->s_mb_offsets); - kfree(sbi->s_mb_maxs); - return -ENOMEM; + ret = -ENOMEM; + goto out; } for_each_possible_cpu(i) { struct ext4_locality_group *lg; @@ -2475,7 +2514,13 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) if (sbi->s_journal) sbi->s_journal->j_commit_callback = release_blocks_on_commit; - return 0; +out: + if (ret) { + kfree(sbi->s_mb_offsets); + kfree(sbi->s_mb_maxs); + kfree(namep); + } + return ret; } /* need to called with the ext4 group lock held */ @@ -2503,6 +2548,7 @@ int ext4_mb_release(struct super_block *sb) int num_meta_group_infos; struct ext4_group_info *grinfo; struct ext4_sb_info *sbi = EXT4_SB(sb); + struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); if (sbi->s_group_info) { for (i = 0; i < ngroups; i++) { @@ -2513,7 +2559,7 @@ int ext4_mb_release(struct super_block *sb) ext4_lock_group(sb, i); ext4_mb_cleanup_pa(grinfo); ext4_unlock_group(sb, i); - kfree(grinfo); + kmem_cache_free(cachep, grinfo); } num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> @@ -2691,6 +2737,7 @@ int __init init_ext4_mballoc(void) void exit_ext4_mballoc(void) { + int i; /* * Wait for completion of call_rcu()'s on ext4_pspace_cachep * before destroying the slab cache. @@ -2699,6 +2746,15 @@ void exit_ext4_mballoc(void) kmem_cache_destroy(ext4_pspace_cachep); kmem_cache_destroy(ext4_ac_cachep); kmem_cache_destroy(ext4_free_ext_cachep); + + for (i = 0; i < NR_GRPINFO_CACHES; i++) { + struct kmem_cache *cachep = ext4_groupinfo_caches[i]; + if (cachep) { + char *name = (char *)kmem_cache_name(cachep); + kmem_cache_destroy(cachep); + kfree(name); + } + } ext4_remove_debugfs_entry(); } -- cgit v1.2.3-18-g5258 From 659c6009ca2e3a01acc9881bafe5f55ef09c965b Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Wed, 27 Oct 2010 21:30:03 -0400 Subject: ext4: stop looping in ext4_num_dirty_pages when max_pages reached Today we simply break out of the inner loop when we have accumulated max_pages; this keeps scanning forwad and doing pagevec_lookup_tag() in the while (!done) loop, this does potentially a lot of work with no net effect. When we have accumulated max_pages, just clean up and return. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 4b8debeb396..d88ba4a9eff 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1207,8 +1207,10 @@ static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx, break; idx++; num++; - if (num >= max_pages) + if (num >= max_pages) { + done = 1; break; + } } pagevec_release(&pvec); } -- cgit v1.2.3-18-g5258 From b443e7339aa08574d30b0819b344618459c76214 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Wed, 27 Oct 2010 21:30:03 -0400 Subject: ext4: don't bump up LONG_MAX nr_to_write by a factor of 8 I'm uneasy with lots of stuff going on in ext4_da_writepages(), but bumping nr_to_write from LLONG_MAX to -8 clearly isn't making anything better, so avoid the multiplier in that case. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d88ba4a9eff..50f3bba68a2 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3004,9 +3004,12 @@ static int ext4_da_writepages(struct address_space *mapping, * sbi->max_writeback_mb_bump whichever is smaller. */ max_pages = sbi->s_max_writeback_mb_bump << (20 - PAGE_CACHE_SHIFT); - if (!range_cyclic && range_whole) - desired_nr_to_write = wbc->nr_to_write * 8; - else + if (!range_cyclic && range_whole) { + if (wbc->nr_to_write == LONG_MAX) + desired_nr_to_write = wbc->nr_to_write; + else + desired_nr_to_write = wbc->nr_to_write * 8; + } else desired_nr_to_write = ext4_num_dirty_pages(inode, index, max_pages); if (desired_nr_to_write > max_pages) -- cgit v1.2.3-18-g5258 From 582987098207f1182ed5c7d01d5fedf7a5f56286 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Wed, 27 Oct 2010 21:30:03 -0400 Subject: ext4: check for negative error code from sb_issue_discard sb_issue_discard() is returning negative error code, so check for -EOPNOTSUPP. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- fs/ext4/mballoc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index d4714d6cf7d..53472e27b32 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2613,7 +2613,7 @@ static inline void ext4_issue_discard(struct super_block *sb, trace_ext4_discard_blocks(sb, (unsigned long long) discard_block, count); ret = sb_issue_discard(sb, discard_block, count); - if (ret == EOPNOTSUPP) { + if (ret == -EOPNOTSUPP) { ext4_warning(sb, "discard not supported, disabling"); clear_opt(EXT4_SB(sb)->s_mount_opt, DISCARD); } -- cgit v1.2.3-18-g5258 From 53fdcf992d616484d388a8ab9dad07dc8b8f1178 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Wed, 27 Oct 2010 21:30:04 -0400 Subject: ext4: don't hold spinlock while calling ext4_issue_discard() We can't hold the block group spinlock because we ext4_issue_discard() calls wait and hence can get rescheduled. Google-Bug-Id: 3017678 Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- fs/ext4/mballoc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 53472e27b32..ccdfec6acb7 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4696,12 +4696,12 @@ do_more: * with group lock held. generate_buddy look at * them with group lock_held */ + if (test_opt(sb, DISCARD)) + ext4_issue_discard(sb, block_group, bit, count); ext4_lock_group(sb, block_group); mb_clear_bits(bitmap_bh->b_data, bit, count); mb_free_blocks(inode, &e4b, bit, count); ext4_mb_return_to_preallocation(inode, &e4b, block, count); - if (test_opt(sb, DISCARD)) - ext4_issue_discard(sb, block_group, bit, count); } ret = ext4_free_blks_count(sb, gdp) + count; -- cgit v1.2.3-18-g5258 From a1c6c5698d53db4c47a25c3a8d11731a4d7b8370 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Wed, 27 Oct 2010 21:30:04 -0400 Subject: ext4: fix NULL pointer dereference in print_daily_error_info() Fix NULL pointer dereference in print_daily_error_info, when called on unmounted fs (EXT4_SB(sb) returns NULL), by removing error reporting timer in ext4_put_super. Google-Bug-Id: 3017663 Signed-off-by: Sergey Senozhatsky Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 26147746c27..751997d2cef 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -719,6 +719,7 @@ static void ext4_put_super(struct super_block *sb) ext4_abort(sb, "Couldn't clean up the journal"); } + del_timer(&sbi->s_err_report); ext4_release_system_zone(sb); ext4_mb_release(sb); ext4_ext_release(sb); -- cgit v1.2.3-18-g5258 From 5c2178e785244341d1e6f2bc3b62f20a337cc44f Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Oct 2010 21:30:04 -0400 Subject: jbd2: Add sanity check for attempts to start handle during umount An attempt to modify the file system during the call to jbd2_destroy_journal() can lead to a system lockup. So add some checking to make it much more obvious when this happens to and to determine where the offending code is located. Signed-off-by: "Theodore Ts'o" --- fs/jbd2/checkpoint.c | 10 ++++++++++ fs/jbd2/transaction.c | 1 + 2 files changed, 11 insertions(+) diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 5247e7ffdcb..524800dce20 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -299,6 +299,16 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh, transaction->t_chp_stats.cs_forced_to_close++; spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); + if (unlikely(journal->j_flags & JBD2_UNMOUNT)) + /* + * The journal thread is dead; so starting and + * waiting for a commit to finish will cause + * us to wait for a _very_ long time. + */ + printk(KERN_ERR "JBD2: %s: " + "Waiting for Godot: block %llu\n", + journal->j_devname, + (unsigned long long) bh->b_blocknr); jbd2_log_start_commit(journal, tid); jbd2_log_wait_commit(journal, tid); ret = 1; diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index f3479d6e0a8..6bf0a242613 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -156,6 +156,7 @@ alloc_transaction: */ repeat: read_lock(&journal->j_state_lock); + BUG_ON(journal->j_flags & JBD2_UNMOUNT); if (is_journal_aborted(journal) || (journal->j_errno != 0 && !(journal->j_flags & JBD2_ACK_ERR))) { read_unlock(&journal->j_state_lock); -- cgit v1.2.3-18-g5258 From e6fa0be699449d28a20e815bfe9ce26725ec4962 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Wed, 27 Oct 2010 21:30:04 -0400 Subject: Add helper function for blkdev_issue_zeroout (sb_issue_discard) This is done the same way as helper sb_issue_discard for blkdev_issue_discard. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- include/linux/blkdev.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2c54906f678..e5cb4d02968 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -941,6 +941,14 @@ static inline int sb_issue_discard(struct super_block *sb, return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_NOFS, BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); } +static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, + sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags) +{ + return blkdev_issue_zeroout(sb->s_bdev, + block << (sb->s_blocksize_bits - 9), + nr_blocks << (sb->s_blocksize_bits - 9), + gfp_mask, flags); +} extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); -- cgit v1.2.3-18-g5258 From bfff68738f1cb5c93dab1114634cea02aae9e7ba Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Wed, 27 Oct 2010 21:30:05 -0400 Subject: ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- Documentation/filesystems/ext4.txt | 14 ++ fs/ext4/ext4.h | 40 ++++ fs/ext4/ialloc.c | 120 ++++++++++ fs/ext4/super.c | 440 ++++++++++++++++++++++++++++++++++++- 4 files changed, 611 insertions(+), 3 deletions(-) diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index e1def1786e5..6ab9442d7ee 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -353,6 +353,20 @@ noauto_da_alloc replacing existing files via patterns such as system crashes before the delayed allocation blocks are forced to disk. +noinit_itable Do not initialize any uninitialized inode table + blocks in the background. This feature may be + used by installation CD's so that the install + process can complete as quickly as possible; the + inode table initialization process would then be + deferred until the next time the file system + is unmounted. + +init_itable=n The lazy itable init code will wait n times the + number of milliseconds it took to zero out the + previous block group's inode table. This + minimizes the impact on the systme performance + while file system's inode table is being initialized. + discard Controls whether ext4 should issue discard/TRIM nodiscard(*) commands to the underlying block device when blocks are freed. This is useful for SSD devices diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index b364b9df09b..0fe078d368d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -890,6 +890,7 @@ struct ext4_inode_info { #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */ #define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */ #define EXT4_MOUNT_DISCARD 0x40000000 /* Issue DISCARD requests */ +#define EXT4_MOUNT_INIT_INODE_TABLE 0x80000000 /* Initialize uninitialized itables */ #define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt #define set_opt(o, opt) o |= EXT4_MOUNT_##opt @@ -1173,6 +1174,11 @@ struct ext4_sb_info { /* timer for periodic error stats printing */ struct timer_list s_err_report; + + /* Lazy inode table initialization info */ + struct ext4_li_request *s_li_request; + /* Wait multiplier for lazy initialization thread */ + unsigned int s_li_wait_mult; }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) @@ -1536,6 +1542,38 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, extern struct proc_dir_entry *ext4_proc_root; +/* + * Timeout and state flag for lazy initialization inode thread. + */ +#define EXT4_DEF_LI_WAIT_MULT 10 +#define EXT4_DEF_LI_MAX_START_DELAY 5 +#define EXT4_LAZYINIT_QUIT 0x0001 +#define EXT4_LAZYINIT_RUNNING 0x0002 + +/* + * Lazy inode table initialization info + */ +struct ext4_lazy_init { + unsigned long li_state; + + wait_queue_head_t li_wait_daemon; + wait_queue_head_t li_wait_task; + struct timer_list li_timer; + struct task_struct *li_task; + + struct list_head li_request_list; + struct mutex li_list_mtx; +}; + +struct ext4_li_request { + struct super_block *lr_super; + struct ext4_sb_info *lr_sbi; + ext4_group_t lr_next_group; + struct list_head lr_request; + unsigned long lr_next_sched; + unsigned long lr_timeout; +}; + /* * Function prototypes */ @@ -1611,6 +1649,8 @@ extern unsigned ext4_init_inode_bitmap(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *desc); extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap); +extern int ext4_init_inode_table(struct super_block *sb, + ext4_group_t group, int barrier); /* mballoc.c */ extern long ext4_mb_stats; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 45853e0d1f2..e428f23215c 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -107,6 +107,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) desc = ext4_get_group_desc(sb, block_group, NULL); if (!desc) return NULL; + bitmap_blk = ext4_inode_bitmap(sb, desc); bh = sb_getblk(sb, bitmap_blk); if (unlikely(!bh)) { @@ -123,6 +124,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) unlock_buffer(bh); return bh; } + ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) { ext4_init_inode_bitmap(sb, bh, block_group, desc); @@ -133,6 +135,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) return bh; } ext4_unlock_group(sb, block_group); + if (buffer_uptodate(bh)) { /* * if not uninit if bh is uptodate, @@ -712,8 +715,17 @@ static int ext4_claim_inode(struct super_block *sb, { int free = 0, retval = 0, count; struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); + /* + * We have to be sure that new inode allocation does not race with + * inode table initialization, because otherwise we may end up + * allocating and writing new inode right before sb_issue_zeroout + * takes place and overwriting our new inode with zeroes. So we + * take alloc_sem to prevent it. + */ + down_read(&grp->alloc_sem); ext4_lock_group(sb, group); if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) { /* not a free inode */ @@ -724,6 +736,7 @@ static int ext4_claim_inode(struct super_block *sb, if ((group == 0 && ino < EXT4_FIRST_INO(sb)) || ino > EXT4_INODES_PER_GROUP(sb)) { ext4_unlock_group(sb, group); + up_read(&grp->alloc_sem); ext4_error(sb, "reserved inode or inode > inodes count - " "block_group = %u, inode=%lu", group, ino + group * EXT4_INODES_PER_GROUP(sb)); @@ -772,6 +785,7 @@ static int ext4_claim_inode(struct super_block *sb, gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); err_ret: ext4_unlock_group(sb, group); + up_read(&grp->alloc_sem); return retval; } @@ -1205,3 +1219,109 @@ unsigned long ext4_count_dirs(struct super_block * sb) } return count; } + +/* + * Zeroes not yet zeroed inode table - just write zeroes through the whole + * inode table. Must be called without any spinlock held. The only place + * where it is called from on active part of filesystem is ext4lazyinit + * thread, so we do not need any special locks, however we have to prevent + * inode allocation from the current group, so we take alloc_sem lock, to + * block ext4_claim_inode until we are finished. + */ +extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, + int barrier) +{ + struct ext4_group_info *grp = ext4_get_group_info(sb, group); + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_group_desc *gdp = NULL; + struct buffer_head *group_desc_bh; + handle_t *handle; + ext4_fsblk_t blk; + int num, ret = 0, used_blks = 0; + unsigned long flags = BLKDEV_IFL_WAIT; + + /* This should not happen, but just to be sure check this */ + if (sb->s_flags & MS_RDONLY) { + ret = 1; + goto out; + } + + gdp = ext4_get_group_desc(sb, group, &group_desc_bh); + if (!gdp) + goto out; + + /* + * We do not need to lock this, because we are the only one + * handling this flag. + */ + if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)) + goto out; + + handle = ext4_journal_start_sb(sb, 1); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } + + down_write(&grp->alloc_sem); + /* + * If inode bitmap was already initialized there may be some + * used inodes so we need to skip blocks with used inodes in + * inode table. + */ + if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) + used_blks = DIV_ROUND_UP((EXT4_INODES_PER_GROUP(sb) - + ext4_itable_unused_count(sb, gdp)), + sbi->s_inodes_per_block); + + blk = ext4_inode_table(sb, gdp) + used_blks; + num = sbi->s_itb_per_group - used_blks; + + BUFFER_TRACE(group_desc_bh, "get_write_access"); + ret = ext4_journal_get_write_access(handle, + group_desc_bh); + if (ret) + goto err_out; + + if (unlikely(num > EXT4_INODES_PER_GROUP(sb))) { + ext4_error(sb, "Something is wrong with group %u\n" + "Used itable blocks: %d" + "Itable blocks per group: %lu\n", + group, used_blks, sbi->s_itb_per_group); + ret = 1; + goto err_out; + } + + /* + * Skip zeroout if the inode table is full. But we set the ZEROED + * flag anyway, because obviously, when it is full it does not need + * further zeroing. + */ + if (unlikely(num == 0)) + goto skip_zeroout; + + ext4_debug("going to zero out inode table in group %d\n", + group); + if (barrier) + flags |= BLKDEV_IFL_BARRIER; + ret = sb_issue_zeroout(sb, blk, num, GFP_NOFS, flags); + if (ret < 0) + goto err_out; + +skip_zeroout: + ext4_lock_group(sb, group); + gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED); + gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); + ext4_unlock_group(sb, group); + + BUFFER_TRACE(group_desc_bh, + "call ext4_handle_dirty_metadata"); + ret = ext4_handle_dirty_metadata(handle, NULL, + group_desc_bh); + +err_out: + up_write(&grp->alloc_sem); + ext4_journal_stop(handle); +out: + return ret; +} diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 751997d2cef..5066537e5a3 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -41,6 +41,9 @@ #include #include +#include +#include + #include "ext4.h" #include "ext4_jbd2.h" #include "xattr.h" @@ -52,6 +55,8 @@ struct proc_dir_entry *ext4_proc_root; static struct kset *ext4_kset; +struct ext4_lazy_init *ext4_li_info; +struct mutex ext4_li_mtx; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); @@ -70,6 +75,8 @@ static void ext4_write_super(struct super_block *sb); static int ext4_freeze(struct super_block *sb); static int ext4_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, struct vfsmount *mnt); +static void ext4_destroy_lazyinit_thread(void); +static void ext4_unregister_li_request(struct super_block *sb); #if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23) static struct file_system_type ext3_fs_type = { @@ -720,6 +727,7 @@ static void ext4_put_super(struct super_block *sb) } del_timer(&sbi->s_err_report); + ext4_unregister_li_request(sb); ext4_release_system_zone(sb); ext4_mb_release(sb); ext4_ext_release(sb); @@ -1046,6 +1054,12 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) !(def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY)) seq_puts(seq, ",block_validity"); + if (!test_opt(sb, INIT_INODE_TABLE)) + seq_puts(seq, ",noinit_inode_table"); + else if (sbi->s_li_wait_mult) + seq_printf(seq, ",init_inode_table=%u", + (unsigned) sbi->s_li_wait_mult); + ext4_show_quota_options(seq, sb); return 0; @@ -1220,6 +1234,7 @@ enum { Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, + Opt_init_inode_table, Opt_noinit_inode_table, }; static const match_table_t tokens = { @@ -1290,6 +1305,9 @@ static const match_table_t tokens = { {Opt_dioread_lock, "dioread_lock"}, {Opt_discard, "discard"}, {Opt_nodiscard, "nodiscard"}, + {Opt_init_inode_table, "init_itable=%u"}, + {Opt_init_inode_table, "init_itable"}, + {Opt_noinit_inode_table, "noinit_itable"}, {Opt_err, NULL}, }; @@ -1760,6 +1778,20 @@ set_qf_format: case Opt_dioread_lock: clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK); break; + case Opt_init_inode_table: + set_opt(sbi->s_mount_opt, INIT_INODE_TABLE); + if (args[0].from) { + if (match_int(&args[0], &option)) + return 0; + } else + option = EXT4_DEF_LI_WAIT_MULT; + if (option < 0) + return 0; + sbi->s_li_wait_mult = option; + break; + case Opt_noinit_inode_table: + clear_opt(sbi->s_mount_opt, INIT_INODE_TABLE); + break; default: ext4_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" " @@ -1943,7 +1975,8 @@ int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group, } /* Called at mount-time, super-block is locked */ -static int ext4_check_descriptors(struct super_block *sb) +static int ext4_check_descriptors(struct super_block *sb, + ext4_group_t *first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); @@ -1952,7 +1985,7 @@ static int ext4_check_descriptors(struct super_block *sb) ext4_fsblk_t inode_bitmap; ext4_fsblk_t inode_table; int flexbg_flag = 0; - ext4_group_t i; + ext4_group_t i, grp = sbi->s_groups_count; if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) flexbg_flag = 1; @@ -1968,6 +2001,10 @@ static int ext4_check_descriptors(struct super_block *sb) last_block = first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1); + if ((grp == sbi->s_groups_count) && + !(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) + grp = i; + block_bitmap = ext4_block_bitmap(sb, gdp); if (block_bitmap < first_block || block_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " @@ -2005,6 +2042,8 @@ static int ext4_check_descriptors(struct super_block *sb) if (!flexbg_flag) first_block += EXT4_BLOCKS_PER_GROUP(sb); } + if (NULL != first_not_zeroed) + *first_not_zeroed = grp; ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb)); sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb)); @@ -2543,6 +2582,378 @@ static void print_daily_error_info(unsigned long arg) mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); /* Once a day */ } +static void ext4_lazyinode_timeout(unsigned long data) +{ + struct task_struct *p = (struct task_struct *)data; + wake_up_process(p); +} + +/* Find next suitable group and run ext4_init_inode_table */ +static int ext4_run_li_request(struct ext4_li_request *elr) +{ + struct ext4_group_desc *gdp = NULL; + ext4_group_t group, ngroups; + struct super_block *sb; + unsigned long timeout = 0; + int ret = 0; + + sb = elr->lr_super; + ngroups = EXT4_SB(sb)->s_groups_count; + + for (group = elr->lr_next_group; group < ngroups; group++) { + gdp = ext4_get_group_desc(sb, group, NULL); + if (!gdp) { + ret = 1; + break; + } + + if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) + break; + } + + if (group == ngroups) + ret = 1; + + if (!ret) { + timeout = jiffies; + ret = ext4_init_inode_table(sb, group, + elr->lr_timeout ? 0 : 1); + if (elr->lr_timeout == 0) { + timeout = jiffies - timeout; + if (elr->lr_sbi->s_li_wait_mult) + timeout *= elr->lr_sbi->s_li_wait_mult; + else + timeout *= 20; + elr->lr_timeout = timeout; + } + elr->lr_next_sched = jiffies + elr->lr_timeout; + elr->lr_next_group = group + 1; + } + + return ret; +} + +/* + * Remove lr_request from the list_request and free the + * request tructure. Should be called with li_list_mtx held + */ +static void ext4_remove_li_request(struct ext4_li_request *elr) +{ + struct ext4_sb_info *sbi; + + if (!elr) + return; + + sbi = elr->lr_sbi; + + list_del(&elr->lr_request); + sbi->s_li_request = NULL; + kfree(elr); +} + +static void ext4_unregister_li_request(struct super_block *sb) +{ + struct ext4_li_request *elr = EXT4_SB(sb)->s_li_request; + + if (!ext4_li_info) + return; + + mutex_lock(&ext4_li_info->li_list_mtx); + ext4_remove_li_request(elr); + mutex_unlock(&ext4_li_info->li_list_mtx); +} + +/* + * This is the function where ext4lazyinit thread lives. It walks + * through the request list searching for next scheduled filesystem. + * When such a fs is found, run the lazy initialization request + * (ext4_rn_li_request) and keep track of the time spend in this + * function. Based on that time we compute next schedule time of + * the request. When walking through the list is complete, compute + * next waking time and put itself into sleep. + */ +static int ext4_lazyinit_thread(void *arg) +{ + struct ext4_lazy_init *eli = (struct ext4_lazy_init *)arg; + struct list_head *pos, *n; + struct ext4_li_request *elr; + unsigned long next_wakeup; + DEFINE_WAIT(wait); + int ret; + + BUG_ON(NULL == eli); + + eli->li_timer.data = (unsigned long)current; + eli->li_timer.function = ext4_lazyinode_timeout; + + eli->li_task = current; + wake_up(&eli->li_wait_task); + +cont_thread: + while (true) { + next_wakeup = MAX_JIFFY_OFFSET; + + mutex_lock(&eli->li_list_mtx); + if (list_empty(&eli->li_request_list)) { + mutex_unlock(&eli->li_list_mtx); + goto exit_thread; + } + + list_for_each_safe(pos, n, &eli->li_request_list) { + 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_before(elr->lr_next_sched, next_wakeup)) + next_wakeup = elr->lr_next_sched; + } + mutex_unlock(&eli->li_list_mtx); + + if (freezing(current)) + refrigerator(); + + if (time_after_eq(jiffies, next_wakeup)) { + cond_resched(); + continue; + } + + eli->li_timer.expires = next_wakeup; + add_timer(&eli->li_timer); + prepare_to_wait(&eli->li_wait_daemon, &wait, + TASK_INTERRUPTIBLE); + if (time_before(jiffies, next_wakeup)) + schedule(); + finish_wait(&eli->li_wait_daemon, &wait); + } + +exit_thread: + /* + * It looks like the request list is empty, but we need + * to check it under the li_list_mtx lock, to prevent any + * additions into it, and of course we should lock ext4_li_mtx + * to atomically free the list and ext4_li_info, because at + * this point another ext4 filesystem could be registering + * new one. + */ + mutex_lock(&ext4_li_mtx); + mutex_lock(&eli->li_list_mtx); + if (!list_empty(&eli->li_request_list)) { + mutex_unlock(&eli->li_list_mtx); + mutex_unlock(&ext4_li_mtx); + goto cont_thread; + } + mutex_unlock(&eli->li_list_mtx); + del_timer_sync(&ext4_li_info->li_timer); + eli->li_task = NULL; + wake_up(&eli->li_wait_task); + + kfree(ext4_li_info); + ext4_li_info = NULL; + mutex_unlock(&ext4_li_mtx); + + return 0; +} + +static void ext4_clear_request_list(void) +{ + struct list_head *pos, *n; + 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); + ext4_remove_li_request(elr); + } + mutex_unlock(&ext4_li_info->li_list_mtx); +} + +static int ext4_run_lazyinit_thread(void) +{ + struct task_struct *t; + + t = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit"); + if (IS_ERR(t)) { + int err = PTR_ERR(t); + ext4_clear_request_list(); + del_timer_sync(&ext4_li_info->li_timer); + kfree(ext4_li_info); + ext4_li_info = NULL; + printk(KERN_CRIT "EXT4: error %d creating inode table " + "initialization thread\n", + err); + return err; + } + ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING; + + wait_event(ext4_li_info->li_wait_task, ext4_li_info->li_task != NULL); + return 0; +} + +/* + * Check whether it make sense to run itable init. thread or not. + * If there is at least one uninitialized inode table, return + * corresponding group number, else the loop goes through all + * groups and return total number of groups. + */ +static ext4_group_t ext4_has_uninit_itable(struct super_block *sb) +{ + ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count; + struct ext4_group_desc *gdp = NULL; + + for (group = 0; group < ngroups; group++) { + gdp = ext4_get_group_desc(sb, group, NULL); + if (!gdp) + continue; + + if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) + break; + } + + return group; +} + +static int ext4_li_info_new(void) +{ + struct ext4_lazy_init *eli = NULL; + + eli = kzalloc(sizeof(*eli), GFP_KERNEL); + if (!eli) + return -ENOMEM; + + eli->li_task = NULL; + INIT_LIST_HEAD(&eli->li_request_list); + mutex_init(&eli->li_list_mtx); + + init_waitqueue_head(&eli->li_wait_daemon); + init_waitqueue_head(&eli->li_wait_task); + init_timer(&eli->li_timer); + eli->li_state |= EXT4_LAZYINIT_QUIT; + + ext4_li_info = eli; + + return 0; +} + +static struct ext4_li_request *ext4_li_request_new(struct super_block *sb, + ext4_group_t start) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_li_request *elr; + unsigned long rnd; + + elr = kzalloc(sizeof(*elr), GFP_KERNEL); + if (!elr) + return NULL; + + elr->lr_super = sb; + elr->lr_sbi = sbi; + elr->lr_next_group = start; + + /* + * Randomize first schedule time of the request to + * spread the inode table initialization requests + * better. + */ + get_random_bytes(&rnd, sizeof(rnd)); + elr->lr_next_sched = jiffies + (unsigned long)rnd % + (EXT4_DEF_LI_MAX_START_DELAY * HZ); + + return elr; +} + +static int ext4_register_li_request(struct super_block *sb, + ext4_group_t first_not_zeroed) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_li_request *elr; + ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; + int ret = 0; + + if (sbi->s_li_request != NULL) + goto out; + + if (first_not_zeroed == ngroups || + (sb->s_flags & MS_RDONLY) || + !test_opt(sb, INIT_INODE_TABLE)) { + sbi->s_li_request = NULL; + goto out; + } + + if (first_not_zeroed == ngroups) { + sbi->s_li_request = NULL; + goto out; + } + + elr = ext4_li_request_new(sb, first_not_zeroed); + if (!elr) { + ret = -ENOMEM; + goto out; + } + + mutex_lock(&ext4_li_mtx); + + if (NULL == ext4_li_info) { + ret = ext4_li_info_new(); + if (ret) + goto out; + } + + mutex_lock(&ext4_li_info->li_list_mtx); + list_add(&elr->lr_request, &ext4_li_info->li_request_list); + mutex_unlock(&ext4_li_info->li_list_mtx); + + sbi->s_li_request = elr; + + if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) { + ret = ext4_run_lazyinit_thread(); + if (ret) + goto out; + } + + mutex_unlock(&ext4_li_mtx); + +out: + if (ret) { + mutex_unlock(&ext4_li_mtx); + kfree(elr); + } + return ret; +} + +/* + * We do not need to lock anything since this is called on + * module unload. + */ +static void ext4_destroy_lazyinit_thread(void) +{ + /* + * If thread exited earlier + * there's nothing to be done. + */ + if (!ext4_li_info) + return; + + ext4_clear_request_list(); + + while (ext4_li_info->li_task) { + wake_up(&ext4_li_info->li_wait_daemon); + wait_event(ext4_li_info->li_wait_task, + ext4_li_info->li_task == NULL); + } +} + static int ext4_fill_super(struct super_block *sb, void *data, int silent) __releases(kernel_lock) __acquires(kernel_lock) @@ -2568,6 +2979,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) __u64 blocks_count; int err; unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; + ext4_group_t first_not_zeroed; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) @@ -2630,6 +3042,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) /* Set defaults before we parse the mount options */ def_mount_opts = le32_to_cpu(es->s_default_mount_opts); + set_opt(sbi->s_mount_opt, INIT_INODE_TABLE); if (def_mount_opts & EXT4_DEFM_DEBUG) set_opt(sbi->s_mount_opt, DEBUG); if (def_mount_opts & EXT4_DEFM_BSDGROUPS) { @@ -2909,7 +3322,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount2; } } - if (!ext4_check_descriptors(sb)) { + if (!ext4_check_descriptors(sb, &first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); goto failed_mount2; } @@ -3130,6 +3543,10 @@ no_journal: goto failed_mount4; } + err = ext4_register_li_request(sb, first_not_zeroed); + if (err) + goto failed_mount4; + sbi->s_kobj.kset = ext4_kset; init_completion(&sbi->s_kobj_unregister); err = kobject_init_and_add(&sbi->s_kobj, &ext4_ktype, NULL, @@ -3847,6 +4264,19 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) enable_quota = 1; } } + + /* + * Reinitialize lazy itable initialization thread based on + * current settings + */ + if ((sb->s_flags & MS_RDONLY) || !test_opt(sb, INIT_INODE_TABLE)) + ext4_unregister_li_request(sb); + else { + ext4_group_t first_not_zeroed; + first_not_zeroed = ext4_has_uninit_itable(sb); + ext4_register_li_request(sb, first_not_zeroed); + } + ext4_setup_system_zone(sb); if (sbi->s_journal == NULL) ext4_commit_super(sb, 1); @@ -4317,6 +4747,9 @@ static int __init init_ext4_fs(void) err = register_filesystem(&ext4_fs_type); if (err) goto out; + + ext4_li_info = NULL; + mutex_init(&ext4_li_mtx); return 0; out: unregister_as_ext2(); @@ -4336,6 +4769,7 @@ out4: static void __exit exit_ext4_fs(void) { + ext4_destroy_lazyinit_thread(); unregister_as_ext2(); unregister_as_ext3(); unregister_filesystem(&ext4_fs_type); -- cgit v1.2.3-18-g5258 From 857ac889cce8a486d47874db4d2f9620e7e9e5de Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Wed, 27 Oct 2010 21:30:05 -0400 Subject: ext4: add interface to advertise ext4 features in sysfs User-space should have the opportunity to check what features doest ext4 support in each particular copy. This adds easy interface by creating new "features" directory in sys/fs/ext4/. In that directory files advertising feature names can be created. Add lazy_itable_init to the feature list. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 5 +++++ fs/ext4/ialloc.c | 19 ++++++++++--------- fs/ext4/super.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 65 insertions(+), 11 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 0fe078d368d..4c5fe37b237 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1574,6 +1574,11 @@ struct ext4_li_request { unsigned long lr_timeout; }; +struct ext4_features { + struct kobject f_kobj; + struct completion f_kobj_unregister; +}; + /* * Function prototypes */ diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index e428f23215c..87d228aae6b 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1274,6 +1274,16 @@ extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, ext4_itable_unused_count(sb, gdp)), sbi->s_inodes_per_block); + if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) { + ext4_error(sb, "Something is wrong with group %u\n" + "Used itable blocks: %d" + "itable unused count: %u\n", + group, used_blks, + ext4_itable_unused_count(sb, gdp)); + ret = 1; + goto out; + } + blk = ext4_inode_table(sb, gdp) + used_blks; num = sbi->s_itb_per_group - used_blks; @@ -1283,15 +1293,6 @@ extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, if (ret) goto err_out; - if (unlikely(num > EXT4_INODES_PER_GROUP(sb))) { - ext4_error(sb, "Something is wrong with group %u\n" - "Used itable blocks: %d" - "Itable blocks per group: %lu\n", - group, used_blks, sbi->s_itb_per_group); - ret = 1; - goto err_out; - } - /* * Skip zeroout if the inode table is full. But we set the ZEROED * flag anyway, because obviously, when it is full it does not need diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 5066537e5a3..c5b890140d0 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -57,6 +57,7 @@ struct proc_dir_entry *ext4_proc_root; static struct kset *ext4_kset; struct ext4_lazy_init *ext4_li_info; struct mutex ext4_li_mtx; +struct ext4_features *ext4_feat; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); @@ -709,6 +710,7 @@ static void ext4_put_super(struct super_block *sb) struct ext4_super_block *es = sbi->s_es; int i, err; + ext4_unregister_li_request(sb); dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); flush_workqueue(sbi->dio_unwritten_wq); @@ -727,7 +729,6 @@ static void ext4_put_super(struct super_block *sb) } del_timer(&sbi->s_err_report); - ext4_unregister_li_request(sb); ext4_release_system_zone(sb); ext4_mb_release(sb); ext4_ext_release(sb); @@ -2416,6 +2417,7 @@ static struct ext4_attr ext4_attr_##_name = { \ #define EXT4_ATTR(name, mode, show, store) \ static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store) +#define EXT4_INFO_ATTR(name) EXT4_ATTR(name, 0444, NULL, NULL) #define EXT4_RO_ATTR(name) EXT4_ATTR(name, 0444, name##_show, NULL) #define EXT4_RW_ATTR(name) EXT4_ATTR(name, 0644, name##_show, name##_store) #define EXT4_RW_ATTR_SBI_UI(name, elname) \ @@ -2452,6 +2454,14 @@ static struct attribute *ext4_attrs[] = { NULL, }; +/* Features this copy of ext4 supports */ +EXT4_INFO_ATTR(lazy_itable_init); + +static struct attribute *ext4_feat_attrs[] = { + ATTR_LIST(lazy_itable_init), + NULL, +}; + static ssize_t ext4_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { @@ -2480,7 +2490,6 @@ static void ext4_sb_release(struct kobject *kobj) complete(&sbi->s_kobj_unregister); } - static const struct sysfs_ops ext4_attr_ops = { .show = ext4_attr_show, .store = ext4_attr_store, @@ -2492,6 +2501,17 @@ static struct kobj_type ext4_ktype = { .release = ext4_sb_release, }; +static void ext4_feat_release(struct kobject *kobj) +{ + complete(&ext4_feat->f_kobj_unregister); +} + +static struct kobj_type ext4_feat_ktype = { + .default_attrs = ext4_feat_attrs, + .sysfs_ops = &ext4_attr_ops, + .release = ext4_feat_release, +}; + /* * Check whether this filesystem can be mounted based on * the features present and the RDONLY/RDWR mount requested. @@ -4720,6 +4740,30 @@ static struct file_system_type ext4_fs_type = { .fs_flags = FS_REQUIRES_DEV, }; +int __init ext4_init_feat_adverts(void) +{ + struct ext4_features *ef; + int ret = -ENOMEM; + + ef = kzalloc(sizeof(struct ext4_features), GFP_KERNEL); + if (!ef) + goto out; + + ef->f_kobj.kset = ext4_kset; + init_completion(&ef->f_kobj_unregister); + ret = kobject_init_and_add(&ef->f_kobj, &ext4_feat_ktype, NULL, + "features"); + if (ret) { + kfree(ef); + goto out; + } + + ext4_feat = ef; + ret = 0; +out: + return ret; +} + static int __init init_ext4_fs(void) { int err; @@ -4732,6 +4776,9 @@ static int __init init_ext4_fs(void) if (!ext4_kset) goto out4; ext4_proc_root = proc_mkdir("fs/ext4", NULL); + + err = ext4_init_feat_adverts(); + err = init_ext4_mballoc(); if (err) goto out3; @@ -4760,6 +4807,7 @@ out1: out2: exit_ext4_mballoc(); out3: + kfree(ext4_feat); remove_proc_entry("fs/ext4", NULL); kset_unregister(ext4_kset); out4: -- cgit v1.2.3-18-g5258 From a31437b85aa2cbc4ea80f9ee5d603fdd5430980c Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Wed, 27 Oct 2010 21:30:05 -0400 Subject: ext4: use sb_issue_zeroout in setup_new_group_blocks Use sb_issue_zeroout to zero out inode table and descriptor table blocks instead of old approach which involves journaling. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- fs/ext4/resize.c | 46 +++++++++++++--------------------------------- 1 file changed, 13 insertions(+), 33 deletions(-) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index ca5c8aa00a2..2f5e347de48 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -226,23 +226,13 @@ static int setup_new_group_blocks(struct super_block *sb, } /* Zero out all of the reserved backup group descriptor table blocks */ - for (i = 0, bit = gdblocks + 1, block = start + bit; - i < reserved_gdb; i++, block++, bit++) { - struct buffer_head *gdb; - - ext4_debug("clear reserved block %#04llx (+%d)\n", block, bit); - - if ((err = extend_or_restart_transaction(handle, 1, bh))) - goto exit_bh; + ext4_debug("clear inode table blocks %#04llx -> %#04llx\n", + block, sbi->s_itb_per_group); + err = sb_issue_zeroout(sb, gdblocks + start + 1, reserved_gdb, + GFP_NOFS, BLKDEV_IFL_WAIT); + if (err) + goto exit_bh; - if (IS_ERR(gdb = bclean(handle, sb, block))) { - err = PTR_ERR(gdb); - go