From ff9893dc8aa622a4f122293a6861566a284edea5 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 27 Jun 2011 16:36:31 -0400 Subject: ext4: split ext4_ind_truncate from ext4_truncate We are about to move all indirect inode functions to a new file. Before we do that, let's split ext4_ind_truncate() out of ext4_truncate() leaving only generic code in the latter, so we will be able to move ext4_ind_truncate() to the new file. Signed-off-by: Amir Goldstein Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 1921392cd708..8532dd43d320 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1834,6 +1834,8 @@ extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); extern void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim); +extern void ext4_ind_truncate(struct inode *inode); + /* ioctl.c */ extern long ext4_ioctl(struct file *, unsigned int, unsigned long); extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long); -- cgit v1.2.1 From 1f7d1e77419050831a905353683807fa69a26625 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 27 Jun 2011 19:16:02 -0400 Subject: ext4: move __ext4_check_blockref to block_validity.c In preparation for moving the indirect functions to a separate file, move __ext4_check_blockref() to block_validity.c and rename it to ext4_check_blockref() which is exported as globally visible function. Also, rename the cpp macro ext4_check_inode_blockref() to ext4_ind_check_inode(), to make it clear that it is only valid for use with non-extent mapped inodes. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 8532dd43d320..82ba7eb7c4a5 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2124,6 +2124,19 @@ static inline void ext4_mark_super_dirty(struct super_block *sb) sb->s_dirt =1; } +/* + * Block validity checking + */ +#define ext4_check_indirect_blockref(inode, bh) \ + ext4_check_blockref(__func__, __LINE__, inode, \ + (__le32 *)(bh)->b_data, \ + EXT4_ADDR_PER_BLOCK((inode)->i_sb)) + +#define ext4_ind_check_inode(inode) \ + ext4_check_blockref(__func__, __LINE__, inode, \ + EXT4_I(inode)->i_data, \ + EXT4_NDIR_BLOCKS) + /* * Inodes and files operations */ @@ -2153,6 +2166,8 @@ extern void ext4_exit_system_zone(void); extern int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, unsigned int count); +extern int ext4_check_blockref(const char *, unsigned int, + struct inode *, __le32 *, unsigned int); /* extents.c */ extern int ext4_ext_tree_init(handle_t *handle, struct inode *); -- cgit v1.2.1 From dae1e52cb1267bf8f52e5e47a80fab566d7e8aa4 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 27 Jun 2011 19:40:50 -0400 Subject: ext4: move ext4_ind_* functions from inode.c to indirect.c This patch moves functions from inode.c to indirect.c. The moved functions are ext4_ind_* functions and their helpers. Functions called from inode.c are declared extern. Signed-off-by: Amir Goldstein Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 82ba7eb7c4a5..ddaf5043fb38 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1834,6 +1834,15 @@ extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); extern void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim); + +/* indirect.c */ +extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, + struct ext4_map_blocks *map, int flags); +extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, + const struct iovec *iov, loff_t offset, + unsigned long nr_segs); +extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock); +extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk); extern void ext4_ind_truncate(struct inode *inode); /* ioctl.c */ -- cgit v1.2.1 From f86186b44b4164600cce03d0d93ad48ec21fa429 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Tue, 28 Jun 2011 10:01:31 -0400 Subject: ext4: refactor duplicated block placement code I found that ext4_ext_find_goal() and ext4_find_near() share the same code for returning a coloured start block based on i_block_group. We can refactor this into a common function so that they don't diverge in the future. Thanks to adilger for suggesting the new function name. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index ddaf5043fb38..49d2cea47382 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1743,6 +1743,7 @@ extern unsigned ext4_init_block_bitmap(struct super_block *sb, struct ext4_group_desc *desc); #define ext4_free_blocks_after_init(sb, group, desc) \ ext4_init_block_bitmap(sb, NULL, group, desc) +ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); /* dir.c */ extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *, -- cgit v1.2.1 From 7132de744ba76930d13033061018ddd7e3e8cd91 Mon Sep 17 00:00:00 2001 From: Maxim Patlasov Date: Sun, 10 Jul 2011 19:37:48 -0400 Subject: ext4: fix i_blocks/quota accounting when extent insertion fails The current implementation of ext4_free_blocks() always calls dquot_free_block This looks quite sensible in the most cases: blocks to be freed are associated with inode and were accounted in quota and i_blocks some time ago. However, there is a case when blocks to free were not accounted by the time calling ext4_free_blocks() yet: 1. delalloc is on, write_begin pre-allocated some space in quota 2. write-back happens, ext4 allocates some blocks in ext4_ext_map_blocks() 3. then ext4_ext_map_blocks() gets an error (e.g. ENOSPC) from ext4_ext_insert_extent() and calls ext4_free_blocks(). In this scenario, ext4_free_blocks() calls dquot_free_block() who, in turn, decrements i_blocks for blocks which were not accounted yet (due to delalloc) After clean umount, e2fsck reports something like: > Inode 21, i_blocks is 5080, should be 5128. Fix? because i_blocks was erroneously decremented as explained above. The patch fixes the problem by passing the new flag EXT4_FREE_BLOCKS_NO_QUOT_UPDATE to ext4_free_blocks(), to request that the dquot_free_block() call be skipped. Signed-off-by: Maxim Patlasov Signed-off-by: "Theodore Ts'o" Cc: stable@kernel.org --- fs/ext4/ext4.h | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 49d2cea47382..d13f3b509886 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -526,6 +526,7 @@ struct ext4_new_group_data { #define EXT4_FREE_BLOCKS_METADATA 0x0001 #define EXT4_FREE_BLOCKS_FORGET 0x0002 #define EXT4_FREE_BLOCKS_VALIDATED 0x0004 +#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008 /* * ioctl commands -- cgit v1.2.1 From 3d56b8d2c74cc3f375ce332b3ac3519e009d79ee Mon Sep 17 00:00:00 2001 From: Tao Ma Date: Mon, 11 Jul 2011 00:03:38 -0400 Subject: ext4: Speed up FITRIM by recording flags in ext4_group_info In ext4, when FITRIM is called every time, we iterate all the groups and do trim one by one. It is a bit time wasting if the group has been trimmed and there is no change since the last trim. So this patch adds a new flag in ext4_group_info->bb_state to indicate that the group has been trimmed, and it will be cleared if some blocks is freed(in release_blocks_on_commit). Another trim_minlen is added in ext4_sb_info to record the last minlen we use to trim the volume, so that if the caller provide a small one, we will go on the trim regardless of the bb_state. A simple test with my intel x25m ssd: df -h shows: /dev/sdb1 40G 21G 17G 56% /mnt/ext4 Block size: 4096 run the FITRIM with the following parameter: range.start = 0; range.len = UINT64_MAX; range.minlen = 1048576; without the patch: [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m5.505s user 0m0.000s sys 0m1.224s [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m5.359s user 0m0.000s sys 0m1.178s [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m5.228s user 0m0.000s sys 0m1.151s with the patch: [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m5.625s user 0m0.000s sys 0m1.269s [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m0.002s user 0m0.000s sys 0m0.001s [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m0.002s user 0m0.000s sys 0m0.001s A big improvement for the 2nd and 3rd run. Even after I delete some big image files, it is still much faster than iterating the whole disk. [root@boyu-tm test]# time ./ftrim /mnt/ext4/a real 0m1.217s user 0m0.000s sys 0m0.196s Cc: Lukas Czerner Reviewed-by: Andreas Dilger Signed-off-by: Tao Ma Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index d13f3b509886..62cee2b6fe79 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1215,6 +1215,9 @@ struct ext4_sb_info { /* Kernel thread for multiple mount protection */ struct task_struct *s_mmp_tsk; + + /* record the last minlen when FITRIM is called. */ + atomic_t s_last_trim_minblks; }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) @@ -2080,11 +2083,19 @@ struct ext4_group_info { * 5 free 8-block regions. */ }; -#define EXT4_GROUP_INFO_NEED_INIT_BIT 0 +#define EXT4_GROUP_INFO_NEED_INIT_BIT 0 +#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT 1 #define EXT4_MB_GRP_NEED_INIT(grp) \ (test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state))) +#define EXT4_MB_GRP_WAS_TRIMMED(grp) \ + (test_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) +#define EXT4_MB_GRP_SET_TRIMMED(grp) \ + (set_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) +#define EXT4_MB_GRP_CLEAR_TRIMMED(grp) \ + (clear_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) + #define EXT4_MAX_CONTENTION 8 #define EXT4_CONTENTION_THRESHOLD 2 -- cgit v1.2.1 From 8f82f840ec6ab873f520364d443ff6fa1b3f8e22 Mon Sep 17 00:00:00 2001 From: Yongqiang Yang Date: Tue, 26 Jul 2011 21:35:44 -0400 Subject: ext4: prevent parallel resizers by atomic bit ops Before this patch, parallel resizers are allowed and protected by a mutex lock, actually, there is no need to support parallel resizer, so this patch prevents parallel resizers by atmoic bit ops, like lock_page() and unlock_page() do. To do this, the patch removed the mutex lock s_resize_lock from struct ext4_sb_info and added a unsigned long field named s_resize_flags which inidicates if there is a resizer. Signed-off-by: Yongqiang Yang Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 62cee2b6fe79..bb0f7760c7c8 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1127,7 +1127,8 @@ struct ext4_sb_info { struct journal_s *s_journal; struct list_head s_orphan; struct mutex s_orphan_lock; - struct mutex s_resize_lock; + unsigned long s_resize_flags; /* Flags indicating if there + is a resizer */ unsigned long s_commit_interval; u32 s_max_batch_time; u32 s_min_batch_time; @@ -2269,6 +2270,10 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh) extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ]; +#define EXT4_RESIZING 0 +extern int ext4_resize_begin(struct super_block *sb); +extern void ext4_resize_end(struct super_block *sb); + #endif /* __KERNEL__ */ #endif /* _EXT4_H */ -- cgit v1.2.1 From 0529155e8a4bcb77dfc9ceaea19c6501487e452b Mon Sep 17 00:00:00 2001 From: Yongqiang Yang Date: Tue, 26 Jul 2011 21:43:56 -0400 Subject: ext4: rename ext4_add_groupblocks() to ext4_group_add_blocks() Signed-off-by: Yongqiang Yang Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index bb0f7760c7c8..bbe81db76c71 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1799,7 +1799,7 @@ extern void ext4_free_blocks(handle_t *handle, struct inode *inode, unsigned long count, int flags); extern int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t i, struct ext4_group_desc *desc); -extern void ext4_add_groupblocks(handle_t *handle, struct super_block *sb, +extern void ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count); extern int ext4_trim_fs(struct super_block *, struct fstrim_range *); -- cgit v1.2.1 From cc7365dfe48cb2191f1572bf69e30d3e58716313 Mon Sep 17 00:00:00 2001 From: Yongqiang Yang Date: Tue, 26 Jul 2011 21:46:07 -0400 Subject: ext4: let ext4_group_add_blocks() return an error code This patch lets ext4_group_add_blocks() return an error code if it fails, so that upper functions can handle error correctly. Signed-off-by: Yongqiang Yang Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index bbe81db76c71..da7ab48948f2 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1799,7 +1799,7 @@ extern void ext4_free_blocks(handle_t *handle, struct inode *inode, unsigned long count, int flags); extern int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t i, struct ext4_group_desc *desc); -extern void ext4_group_add_blocks(handle_t *handle, struct super_block *sb, +extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count); extern int ext4_trim_fs(struct super_block *, struct fstrim_range *); -- cgit v1.2.1 From c3e94d1df9bdd9e2c4ba7e8f534f7925f1756f97 Mon Sep 17 00:00:00 2001 From: Yongqiang Yang Date: Tue, 26 Jul 2011 22:05:53 -0400 Subject: ext4: let setup_new_group_blocks() set multiple bits at a time Rename mb_set_bits() to ext4_set_bits() and make it a global function so that setup_new_group_blocks() can use it. Signed-off-by: Yongqiang Yang Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index da7ab48948f2..ba2009b49a55 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -940,6 +940,8 @@ struct ext4_inode_info { #define ext4_find_next_zero_bit find_next_zero_bit_le #define ext4_find_next_bit find_next_bit_le +extern void ext4_set_bits(void *bm, int cur, int len); + /* * Maximal mount counts between two filesystem checks */ -- cgit v1.2.1 From 9933fc0ac1ac14b795819cd63d05ea92112f690a Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 1 Aug 2011 08:45:02 -0400 Subject: ext4: introduce ext4_kvmalloc(), ext4_kzalloc(), and ext4_kvfree() Introduce new helper functions which try kmalloc, and then fall back to vmalloc if necessary, and use them for allocating and deallocating s_flex_groups. Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs/ext4/ext4.h') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index ba2009b49a55..db9feadf53a0 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1874,6 +1874,9 @@ extern int ext4_group_extend(struct super_block *sb, ext4_fsblk_t n_blocks_count); /* super.c */ +extern void *ext4_kvmalloc(size_t size, gfp_t flags); +extern void *ext4_kvzalloc(size_t size, gfp_t flags); +extern void ext4_kvfree(void *ptr); extern void __ext4_error(struct super_block *, const char *, unsigned int, const char *, ...) __attribute__ ((format (printf, 4, 5))); -- cgit v1.2.1