aboutsummaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2010-03-05 10:47:00 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2010-03-05 10:47:00 -0800
commit1f63b9c15b17d5af360c180f5c71537e954d5d3b (patch)
tree4da17d6f2035ae093680fa2caa3e1c84b44bb237 /fs/ext4
parentb24bc1e61cec2174faf5dfa632da16b6ca17144f (diff)
parent64e290ec69be39f1887fa0b403c1e417b6b038e7 (diff)
Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (36 commits) ext4: fix up rb_root initializations to use RB_ROOT ext4: Code cleanup for EXT4_IOC_MOVE_EXT ioctl ext4: Fix the NULL reference in double_down_write_data_sem() ext4: Fix insertion point of extent in mext_insert_across_blocks() ext4: consolidate in_range() definitions ext4: cleanup to use ext4_grp_offs_to_block() ext4: cleanup to use ext4_group_first_block_no() ext4: Release page references acquired in ext4_da_block_invalidatepages ext4: Fix ext4_quota_write cross block boundary behaviour ext4: Convert BUG_ON checks to use ext4_error() instead ext4: Use direct_IO_no_locking in ext4 dio read ext4: use ext4_get_block_write in buffer write ext4: mechanical rename some of the direct I/O get_block's identifiers ext4: make "offset" consistent in ext4_check_dir_entry() ext4: Handle non empty on-disk orphan link ext4: explicitly remove inode from orphan list after failed direct io ext4: fix error handling in migrate ext4: deprecate obsoleted mount options ext4: Fix fencepost error in chosing choosing group vs file preallocation. jbd2: clean up an assertion in jbd2_journal_commit_transaction() ...
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/balloc.c35
-rw-r--r--fs/ext4/block_validity.c4
-rw-r--r--fs/ext4/dir.c14
-rw-r--r--fs/ext4/ext4.h106
-rw-r--r--fs/ext4/ext4_jbd2.c4
-rw-r--r--fs/ext4/ext4_jbd2.h24
-rw-r--r--fs/ext4/extents.c260
-rw-r--r--fs/ext4/file.c4
-rw-r--r--fs/ext4/fsync.c2
-rw-r--r--fs/ext4/ialloc.c32
-rw-r--r--fs/ext4/inode.c459
-rw-r--r--fs/ext4/ioctl.c12
-rw-r--r--fs/ext4/mballoc.c73
-rw-r--r--fs/ext4/mballoc.h9
-rw-r--r--fs/ext4/migrate.c35
-rw-r--r--fs/ext4/move_extent.c36
-rw-r--r--fs/ext4/namei.c63
-rw-r--r--fs/ext4/resize.c102
-rw-r--r--fs/ext4/super.c342
-rw-r--r--fs/ext4/xattr.c56
20 files changed, 1043 insertions, 629 deletions
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 22bc7435d91..d2f37a5516c 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -97,8 +97,8 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
/* If checksum is bad mark all blocks used to prevent allocation
* essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
- ext4_error(sb, __func__,
- "Checksum bad for group %u", block_group);
+ ext4_error(sb, "Checksum bad for group %u",
+ block_group);
ext4_free_blks_set(sb, gdp, 0);
ext4_free_inodes_set(sb, gdp, 0);
ext4_itable_unused_set(sb, gdp, 0);
@@ -130,8 +130,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
* to make sure we calculate the right free blocks
*/
group_blocks = ext4_blocks_count(sbi->s_es) -
- le32_to_cpu(sbi->s_es->s_first_data_block) -
- (EXT4_BLOCKS_PER_GROUP(sb) * (ngroups - 1));
+ ext4_group_first_block_no(sb, ngroups - 1);
} else {
group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
}
@@ -189,9 +188,6 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
* when a file system is mounted (see ext4_fill_super).
*/
-
-#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
-
/**
* ext4_get_group_desc() -- load group descriptor from disk
* @sb: super block
@@ -210,10 +206,8 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (block_group >= ngroups) {
- ext4_error(sb, "ext4_get_group_desc",
- "block_group >= groups_count - "
- "block_group = %u, groups_count = %u",
- block_group, ngroups);
+ ext4_error(sb, "block_group >= groups_count - block_group = %u,"
+ " groups_count = %u", block_group, ngroups);
return NULL;
}
@@ -221,8 +215,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
if (!sbi->s_group_desc[group_desc]) {
- ext4_error(sb, "ext4_get_group_desc",
- "Group descriptor not loaded - "
+ ext4_error(sb, "Group descriptor not loaded - "
"block_group = %u, group_desc = %u, desc = %u",
block_group, group_desc, offset);
return NULL;
@@ -282,9 +275,7 @@ static int ext4_valid_block_bitmap(struct super_block *sb,
return 1;
err_out:
- ext4_error(sb, __func__,
- "Invalid block bitmap - "
- "block_group = %d, block = %llu",
+ ext4_error(sb, "Invalid block bitmap - block_group = %d, block = %llu",
block_group, bitmap_blk);
return 0;
}
@@ -311,8 +302,7 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
bitmap_blk = ext4_block_bitmap(sb, desc);
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
- ext4_error(sb, __func__,
- "Cannot read block bitmap - "
+ ext4_error(sb, "Cannot read block bitmap - "
"block_group = %u, block_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
@@ -354,8 +344,7 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
set_bitmap_uptodate(bh);
if (bh_submit_read(bh) < 0) {
put_bh(bh);
- ext4_error(sb, __func__,
- "Cannot read block bitmap - "
+ ext4_error(sb, "Cannot read block bitmap - "
"block_group = %u, block_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
@@ -419,8 +408,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
in_range(block + count - 1, ext4_inode_table(sb, desc),
sbi->s_itb_per_group)) {
- ext4_error(sb, __func__,
- "Adding blocks in system zones - "
+ ext4_error(sb, "Adding blocks in system zones - "
"Block = %llu, count = %lu",
block, count);
goto error_return;
@@ -453,8 +441,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
BUFFER_TRACE(bitmap_bh, "clear bit");
if (!ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
bit + i, bitmap_bh->b_data)) {
- ext4_error(sb, __func__,
- "bit already cleared for block %llu",
+ ext4_error(sb, "bit already cleared for block %llu",
(ext4_fsblk_t)(block + i));
BUFFER_TRACE(bitmap_bh, "bit already cleared");
} else {
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index a60ab9aad57..983f0e12749 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -205,14 +205,14 @@ void ext4_release_system_zone(struct super_block *sb)
entry = rb_entry(n, struct ext4_system_zone, node);
kmem_cache_free(ext4_system_zone_cachep, entry);
if (!parent)
- EXT4_SB(sb)->system_blks.rb_node = NULL;
+ EXT4_SB(sb)->system_blks = RB_ROOT;
else if (parent->rb_left == n)
parent->rb_left = NULL;
else if (parent->rb_right == n)
parent->rb_right = NULL;
n = parent;
}
- EXT4_SB(sb)->system_blks.rb_node = NULL;
+ EXT4_SB(sb)->system_blks = RB_ROOT;
}
/*
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 9dc93168e26..86cb6d86a04 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -83,10 +83,12 @@ int ext4_check_dir_entry(const char *function, struct inode *dir,
error_msg = "inode out of bounds";
if (error_msg != NULL)
- ext4_error(dir->i_sb, function,
- "bad entry in directory #%lu: %s - "
- "offset=%u, inode=%u, rec_len=%d, name_len=%d",
- dir->i_ino, error_msg, offset,
+ __ext4_error(dir->i_sb, function,
+ "bad entry in directory #%lu: %s - block=%llu"
+ "offset=%u(%u), inode=%u, rec_len=%d, name_len=%d",
+ dir->i_ino, error_msg,
+ (unsigned long long) bh->b_blocknr,
+ (unsigned) (offset%bh->b_size), offset,
le32_to_cpu(de->inode),
rlen, de->name_len);
return error_msg == NULL ? 1 : 0;
@@ -150,7 +152,7 @@ static int ext4_readdir(struct file *filp,
*/
if (!bh) {
if (!dir_has_error) {
- ext4_error(sb, __func__, "directory #%lu "
+ ext4_error(sb, "directory #%lu "
"contains a hole at offset %Lu",
inode->i_ino,
(unsigned long long) filp->f_pos);
@@ -303,7 +305,7 @@ static void free_rb_tree_fname(struct rb_root *root)
kfree(old);
}
if (!parent)
- root->rb_node = NULL;
+ *root = RB_ROOT;
else if (parent->rb_left == n)
parent->rb_left = NULL;
else if (parent->rb_right == n)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 4cedc91ec59..6e5787a29b9 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -53,6 +53,12 @@
#define ext4_debug(f, a...) do {} while (0)
#endif
+#define EXT4_ERROR_INODE(inode, fmt, a...) \
+ ext4_error_inode(__func__, (inode), (fmt), ## a);
+
+#define EXT4_ERROR_FILE(file, fmt, a...) \
+ ext4_error_file(__func__, (file), (fmt), ## a);
+
/* data type for block offset of block group */
typedef int ext4_grpblk_t;
@@ -133,14 +139,14 @@ struct mpage_da_data {
int pages_written;
int retval;
};
-#define DIO_AIO_UNWRITTEN 0x1
+#define EXT4_IO_UNWRITTEN 0x1
typedef struct ext4_io_end {
struct list_head list; /* per-file finished AIO list */
struct inode *inode; /* file being written to */
unsigned int flag; /* unwritten or not */
- int error; /* I/O error code */
- ext4_lblk_t offset; /* offset in the file */
- size_t size; /* size of the extent */
+ struct page *page; /* page struct for buffer write */
+ loff_t offset; /* offset in the file */
+ ssize_t size; /* size of the extent */
struct work_struct work; /* data work queue */
} ext4_io_end_t;
@@ -284,10 +290,12 @@ struct flex_groups {
#define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
#define EXT4_HUGE_FILE_FL 0x00040000 /* Set to each huge file */
#define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */
+#define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */
+#define EXT4_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */
#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */
-#define EXT4_FL_USER_VISIBLE 0x000BDFFF /* User visible flags */
-#define EXT4_FL_USER_MODIFIABLE 0x000B80FF /* User modifiable flags */
+#define EXT4_FL_USER_VISIBLE 0x004BDFFF /* User visible flags */
+#define EXT4_FL_USER_MODIFIABLE 0x004B80FF /* User modifiable flags */
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
@@ -313,17 +321,6 @@ static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
return flags & EXT4_OTHER_FLMASK;
}
-/*
- * Inode dynamic state flags
- */
-#define EXT4_STATE_JDATA 0x00000001 /* journaled data exists */
-#define EXT4_STATE_NEW 0x00000002 /* inode is newly created */
-#define EXT4_STATE_XATTR 0x00000004 /* has in-inode xattrs */
-#define EXT4_STATE_NO_EXPAND 0x00000008 /* No space for expansion */
-#define EXT4_STATE_DA_ALLOC_CLOSE 0x00000010 /* Alloc DA blks on close */
-#define EXT4_STATE_EXT_MIGRATE 0x00000020 /* Inode is migrating */
-#define EXT4_STATE_DIO_UNWRITTEN 0x00000040 /* need convert on dio done*/
-
/* Used to pass group descriptor data when online resize is done */
struct ext4_new_group_input {
__u32 group; /* Group number for this data */
@@ -364,19 +361,20 @@ struct ext4_new_group_data {
/* caller is from the direct IO path, request to creation of an
unitialized extents if not allocated, split the uninitialized
extent if blocks has been preallocated already*/
-#define EXT4_GET_BLOCKS_DIO 0x0008
+#define EXT4_GET_BLOCKS_PRE_IO 0x0008
#define EXT4_GET_BLOCKS_CONVERT 0x0010
-#define EXT4_GET_BLOCKS_DIO_CREATE_EXT (EXT4_GET_BLOCKS_DIO|\
+#define EXT4_GET_BLOCKS_IO_CREATE_EXT (EXT4_GET_BLOCKS_PRE_IO|\
+ EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
+ /* Convert extent to initialized after IO complete */
+#define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\
EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
- /* Convert extent to initialized after direct IO complete */
-#define EXT4_GET_BLOCKS_DIO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\
- EXT4_GET_BLOCKS_DIO_CREATE_EXT)
/*
* Flags used by ext4_free_blocks
*/
#define EXT4_FREE_BLOCKS_METADATA 0x0001
#define EXT4_FREE_BLOCKS_FORGET 0x0002
+#define EXT4_FREE_BLOCKS_VALIDATED 0x0004
/*
* ioctl commands
@@ -630,7 +628,7 @@ struct ext4_inode_info {
* near to their parent directory's inode.
*/
ext4_group_t i_block_group;
- __u32 i_state; /* Dynamic state flags for ext4 */
+ unsigned long i_state_flags; /* Dynamic state flags */
ext4_lblk_t i_dir_start_lookup;
#ifdef CONFIG_EXT4_FS_XATTR
@@ -708,8 +706,9 @@ struct ext4_inode_info {
qsize_t i_reserved_quota;
#endif
- /* completed async DIOs that might need unwritten extents handling */
- struct list_head i_aio_dio_complete_list;
+ /* completed IOs that might need unwritten extents handling */
+ struct list_head i_completed_io_list;
+ spinlock_t i_completed_io_lock;
/* current io_end structure for async DIO write*/
ext4_io_end_t *cur_aio_dio;
@@ -760,6 +759,7 @@ struct ext4_inode_info {
#define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */
#define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */
#define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */
+#define EXT4_MOUNT_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */
#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 */
@@ -1050,6 +1050,34 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
(ino >= EXT4_FIRST_INO(sb) &&
ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
}
+
+/*
+ * Inode dynamic state flags
+ */
+enum {
+ EXT4_STATE_JDATA, /* journaled data exists */
+ EXT4_STATE_NEW, /* inode is newly created */
+ EXT4_STATE_XATTR, /* has in-inode xattrs */
+ EXT4_STATE_NO_EXPAND, /* No space for expansion */
+ EXT4_STATE_DA_ALLOC_CLOSE, /* Alloc DA blks on close */
+ EXT4_STATE_EXT_MIGRATE, /* Inode is migrating */
+ EXT4_STATE_DIO_UNWRITTEN, /* need convert on dio done*/
+};
+
+static inline int ext4_test_inode_state(struct inode *inode, int bit)
+{
+ return test_bit(bit, &EXT4_I(inode)->i_state_flags);
+}
+
+static inline void ext4_set_inode_state(struct inode *inode, int bit)
+{
+ set_bit(bit, &EXT4_I(inode)->i_state_flags);
+}
+
+static inline void ext4_clear_inode_state(struct inode *inode, int bit)
+{
+ clear_bit(bit, &EXT4_I(inode)->i_state_flags);
+}
#else
/* Assume that user mode programs are passing in an ext4fs superblock, not
* a kernel struct super_block. This will allow us to call the feature-test
@@ -1126,6 +1154,8 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
#define EXT4_FEATURE_INCOMPAT_64BIT 0x0080
#define EXT4_FEATURE_INCOMPAT_MMP 0x0100
#define EXT4_FEATURE_INCOMPAT_FLEX_BG 0x0200
+#define EXT4_FEATURE_INCOMPAT_EA_INODE 0x0400 /* EA in inode */
+#define EXT4_FEATURE_INCOMPAT_DIRDATA 0x1000 /* data in dirent */
#define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR
#define EXT4_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \
@@ -1439,7 +1469,7 @@ extern int ext4_block_truncate_page(handle_t *handle,
struct address_space *mapping, loff_t from);
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 int flush_aio_dio_completed_IO(struct inode *inode);
+extern int flush_completed_IO(struct inode *inode);
extern void ext4_da_update_reserve_space(struct inode *inode,
int used, int quota_claim);
/* ioctl.c */
@@ -1465,13 +1495,20 @@ extern int ext4_group_extend(struct super_block *sb,
ext4_fsblk_t n_blocks_count);
/* super.c */
-extern void ext4_error(struct super_block *, const char *, const char *, ...)
+extern void __ext4_error(struct super_block *, const char *, const char *, ...)
+ __attribute__ ((format (printf, 3, 4)));
+#define ext4_error(sb, message...) __ext4_error(sb, __func__, ## message)
+extern void ext4_error_inode(const char *, struct inode *, const char *, ...)
+ __attribute__ ((format (printf, 3, 4)));
+extern void ext4_error_file(const char *, struct file *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
extern void __ext4_std_error(struct super_block *, const char *, int);
extern void ext4_abort(struct super_block *, const char *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
-extern void ext4_warning(struct super_block *, const char *, const char *, ...)
+extern void __ext4_warning(struct super_block *, const char *,
+ const char *, ...)
__attribute__ ((format (printf, 3, 4)));
+#define ext4_warning(sb, message...) __ext4_warning(sb, __func__, ## message)
extern void ext4_msg(struct super_block *, const char *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
extern void ext4_grp_locked_error(struct super_block *, ext4_group_t,
@@ -1744,7 +1781,7 @@ extern void ext4_ext_release(struct super_block *);
extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
loff_t len);
extern int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
- loff_t len);
+ ssize_t len);
extern int ext4_get_blocks(handle_t *handle, struct inode *inode,
sector_t block, unsigned int max_blocks,
struct buffer_head *bh, int flags);
@@ -1756,6 +1793,15 @@ extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
__u64 len, __u64 *moved_len);
+/* BH_Uninit flag: blocks are allocated but uninitialized on disk */
+enum ext4_state_bits {
+ BH_Uninit /* blocks are allocated but uninitialized on disk */
+ = BH_JBDPrivateStart,
+};
+
+BUFFER_FNS(Uninit, uninit)
+TAS_BUFFER_FNS(Uninit, uninit)
+
/*
* Add new method to test wether block and inode bitmaps are properly
* initialized. With uninit_bg reading the block from disk is not enough
@@ -1773,6 +1819,8 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh)
set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
}
+#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
+
#endif /* __KERNEL__ */
#endif /* _EXT4_H */
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index b57e5c711b6..53d2764d71c 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -125,14 +125,14 @@ int __ext4_handle_dirty_metadata(const char *where, handle_t *handle,
ext4_journal_abort_handle(where, __func__, bh,
handle, err);
} else {
- if (inode && bh)
+ if (inode)
mark_buffer_dirty_inode(bh, inode);
else
mark_buffer_dirty(bh);
if (inode && inode_needs_sync(inode)) {
sync_dirty_buffer(bh);
if (buffer_req(bh) && !buffer_uptodate(bh)) {
- ext4_error(inode->i_sb, __func__,
+ ext4_error(inode->i_sb,
"IO error syncing inode, "
"inode=%lu, block=%llu",
inode->i_ino,
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 05eca817d70..b79ad512646 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -304,4 +304,28 @@ static inline int ext4_should_writeback_data(struct inode *inode)
return 0;
}
+/*
+ * This function controls whether or not we should try to go down the
+ * dioread_nolock code paths, which makes it safe to avoid taking
+ * i_mutex for direct I/O reads. This only works for extent-based
+ * files, and it doesn't work for nobh or if data journaling is
+ * enabled, since the dioread_nolock code uses b_private to pass
+ * information back to the I/O completion handler, and this conflicts
+ * with the jbd's use of b_private.
+ */
+static inline int ext4_should_dioread_nolock(struct inode *inode)
+{
+ if (!test_opt(inode->i_sb, DIOREAD_NOLOCK))
+ return 0;
+ if (test_opt(inode->i_sb, NOBH))
+ return 0;
+ if (!S_ISREG(inode->i_mode))
+ return 0;
+ if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ return 0;
+ if (ext4_should_journal_data(inode))
+ return 0;
+ return 1;
+}
+
#endif /* _EXT4_JBD2_H */
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 765a4826b11..94c8ee81f5e 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -195,8 +195,7 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
if (S_ISREG(inode->i_mode))
block_group++;
}
- bg_start = (block_group * EXT4_BLOCKS_PER_GROUP(inode->i_sb)) +
- le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_first_data_block);
+ bg_start = ext4_group_first_block_no(inode->i_sb, block_group);
last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
/*
@@ -440,7 +439,7 @@ static int __ext4_ext_check(const char *function, struct inode *inode,
return 0;
corrupted:
- ext4_error(inode->i_sb, function,
+ __ext4_error(inode->i_sb, function,
"bad header/extent in inode #%lu: %s - magic %x, "
"entries %u, max %u(%u), depth %u(%u)",
inode->i_ino, error_msg, le16_to_cpu(eh->eh_magic),
@@ -703,7 +702,12 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
}
eh = ext_block_hdr(bh);
ppos++;
- BUG_ON(ppos > depth);
+ if (unlikely(ppos > depth)) {
+ put_bh(bh);
+ EXT4_ERROR_INODE(inode,
+ "ppos %d > depth %d", ppos, depth);
+ goto err;
+ }
path[ppos].p_bh = bh;
path[ppos].p_hdr = eh;
i--;
@@ -749,7 +753,12 @@ int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
if (err)
return err;
- BUG_ON(logical == le32_to_cpu(curp->p_idx->ei_block));
+ if (unlikely(logical == le32_to_cpu(curp->p_idx->ei_block))) {
+ EXT4_ERROR_INODE(inode,
+ "logical %d == ei_block %d!",
+ logical, le32_to_cpu(curp->p_idx->ei_block));
+ return -EIO;
+ }
len = EXT_MAX_INDEX(curp->p_hdr) - curp->p_idx;
if (logical > le32_to_cpu(curp->p_idx->ei_block)) {
/* insert after */
@@ -779,9 +788,17 @@ int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
ext4_idx_store_pblock(ix, ptr);
le16_add_cpu(&curp->p_hdr->eh_entries, 1);
- BUG_ON(le16_to_cpu(curp->p_hdr->eh_entries)
- > le16_to_cpu(curp->p_hdr->eh_max));
- BUG_ON(ix > EXT_LAST_INDEX(curp->p_hdr));
+ if (unlikely(le16_to_cpu(curp->p_hdr->eh_entries)
+ > le16_to_cpu(curp->p_hdr->eh_max))) {
+ EXT4_ERROR_INODE(inode,
+ "logical %d == ei_block %d!",
+ logical, le32_to_cpu(curp->p_idx->ei_block));
+ return -EIO;
+ }
+ if (unlikely(ix > EXT_LAST_INDEX(curp->p_hdr))) {
+ EXT4_ERROR_INODE(inode, "ix > EXT_LAST_INDEX!");
+ return -EIO;
+ }
err = ext4_ext_dirty(handle, inode, curp);
ext4_std_error(inode->i_sb, err);
@@ -819,7 +836,10 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
/* if current leaf will be split, then we should use
* border from split point */
- BUG_ON(path[depth].p_ext > EXT_MAX_EXTENT(path[depth].p_hdr));
+ if (unlikely(path[depth].p_ext > EXT_MAX_EXTENT(path[depth].p_hdr))) {
+ EXT4_ERROR_INODE(inode, "p_ext > EXT_MAX_EXTENT!");
+ return -EIO;
+ }
if (path[depth].p_ext != EXT_MAX_EXTENT(path[depth].p_hdr)) {
border = path[depth].p_ext[1].ee_block;
ext_debug("leaf will be split."
@@ -860,7 +880,11 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
/* initialize new leaf */
newblock = ablocks[--a];
- BUG_ON(newblock == 0);
+ if (unlikely(newblock == 0)) {
+ EXT4_ERROR_INODE(inode, "newblock == 0!");
+ err = -EIO;
+ goto cleanup;
+ }
bh = sb_getblk(inode->i_sb, newblock);
if (!bh) {
err = -EIO;
@@ -880,7 +904,14 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
ex = EXT_FIRST_EXTENT(neh);
/* move remainder of path[depth] to the new leaf */
- BUG_ON(path[depth].p_hdr->eh_entries != path[depth].p_hdr->eh_max);
+ if (unlikely(path[depth].p_hdr->eh_entries !=
+ path[depth].p_hdr->eh_max)) {
+ EXT4_ERROR_INODE(inode, "eh_entries %d != eh_max %d!",
+ path[depth].p_hdr->eh_entries,
+ path[depth].p_hdr->eh_max);
+ err = -EIO;
+ goto cleanup;
+ }
/* start copy from next extent */
/* TODO: we could do it by single memmove */
m = 0;
@@ -927,7 +958,11 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
/* create intermediate indexes */
k = depth - at - 1;
- BUG_ON(k < 0);
+ if (unlikely(k < 0)) {
+ EXT4_ERROR_INODE(inode, "k %d < 0!", k);
+ err = -EIO;
+ goto cleanup;
+ }
if (k)
ext_debug("create %d intermediate indices\n", k);
/* insert new index into current index block */
@@ -964,8 +999,14 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
ext_debug("cur 0x%p, last 0x%p\n", path[i].p_idx,
EXT_MAX_INDEX(path[i].p_hdr));
- BUG_ON(EXT_MAX_INDEX(path[i].p_hdr) !=
- EXT_LAST_INDEX(path[i].p_hdr));
+ if (unlikely(EXT_MAX_INDEX(path[i].p_hdr) !=
+ EXT_LAST_INDEX(path[i].p_hdr))) {
+ EXT4_ERROR_INODE(inode,
+ "EXT_MAX_INDEX != EXT_LAST_INDEX ee_block %d!",
+ le32_to_cpu(path[i].p_ext->ee_block));
+ err = -EIO;
+ goto cleanup;
+ }
while (path[i].p_idx <= EXT_MAX_INDEX(path[i].p_hdr)) {
ext_debug("%d: move %d:%llu in new index %llu\n", i,
le32_to_cpu(path[i].p_idx->ei_block),
@@ -1203,7 +1244,10 @@ ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path,
struct ext4_extent *ex;
int depth, ee_len;
- BUG_ON(path == NULL);
+ if (unlikely(path == NULL)) {
+ EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical);
+ return -EIO;
+ }
depth = path->p_depth;
*phys = 0;
@@ -1217,15 +1261,33 @@ ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path,
ex = path[depth].p_ext;
ee_len = ext4_ext_get_actual_len(ex);
if (*logical < le32_to_cpu(ex->ee_block)) {
- BUG_ON(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex);
+ if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) {
+ EXT4_ERROR_INODE(inode,
+ "EXT_FIRST_EXTENT != ex *logical %d ee_block %d!",
+ *logical, le32_to_cpu(ex->ee_block));
+ return -EIO;
+ }
while (--depth >= 0) {
ix = path[depth].p_idx;
- BUG_ON(ix != EXT_FIRST_INDEX(path[depth].p_hdr));
+ if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) {
+ EXT4_ERROR_INODE(inode,
+ "ix (%d) != EXT_FIRST_INDEX (%d) (depth %d)!",
+ ix != NULL ? ix->ei_block : 0,
+ EXT_FIRST_INDEX(path[depth].p_hdr) != NULL ?
+ EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block : 0,
+ depth);
+ return -EIO;
+ }
}
return 0;
}
- BUG_ON(*logical < (le32_to_cpu(ex->ee_block) + ee_len));
+ if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) {
+ EXT4_ERROR_INODE(inode,
+ "logical %d < ee_block %d + ee_len %d!",
+ *logical, le32_to_cpu(ex->ee_block), ee_len);
+ return -EIO;
+ }
*logical = le32_to_cpu(ex->ee_block) + ee_len - 1;
*phys = ext_pblock(ex) + ee_len - 1;
@@ -1251,7 +1313,10 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
int depth; /* Note, NOT eh_depth; depth from top of tree */
int ee_len;
- BUG_ON(path == NULL);
+ if (unlikely(path == NULL)) {
+ EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical);
+ return -EIO;
+ }
depth = path->p_depth;
*phys = 0;
@@ -1265,17 +1330,32 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
ex = path[depth].p_ext;
ee_len = ext4_ext_get_actual_len(ex);
if (*logical < le32_to_cpu(ex->ee_block)) {
- BUG_ON(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex);
+ if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) {
+ EXT4_ERROR_INODE(inode,
+ "first_extent(path[%d].p_hdr) != ex",
+ depth);
+ return -EIO;
+ }
while (--depth >= 0) {
ix = path[depth].p_idx;
- BUG_ON(ix != EXT_FIRST_INDEX(path[depth].p_hdr));
+ if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) {
+ EXT4_ERROR_INODE(inode,
+ "ix != EXT_FIRST_INDEX *logical %d!",
+ *logical);
+ return -EIO;
+ }
}
*logical = le32_to_cpu(ex->ee_block);
*phys = ext_pblock(ex);
return 0;
}
- BUG_ON(*logical < (le32_to_cpu(ex->ee_block) + ee_len));
+ if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) {
+ EXT4_ERROR_INODE(inode,
+ "logical %d < ee_block %d + ee_len %d!",
+ *logical, le32_to_cpu(ex->ee_block), ee_len);
+ return -EIO;
+ }
if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) {
/* next allocated block in this leaf */
@@ -1414,8 +1494,12 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
eh = path[depth].p_hdr;
ex = path[depth].p_ext;
- BUG_ON(ex == NULL);
- BUG_ON(eh == NULL);
+
+ if (unlikely(ex == NULL || eh == NULL)) {
+ EXT4_ERROR_INODE(inode,
+ "ex %p == NULL or eh %p == NULL", ex, eh);
+ return -EIO;
+ }
if (depth == 0) {
/* there is no tree at all */
@@ -1538,8 +1622,9 @@ int ext4_ext_try_to_merge(struct inode *inode,
merge_done = 1;
WARN_ON(eh->eh_entries == 0);
if (!eh->eh_entries)
- ext4_error(inode->i_sb, "ext4_ext_try_to_merge",
- "inode#%lu, eh->eh_entries = 0!", inode->i_ino);
+ ext4_error(inode->i_sb,
+ "inode#%lu, eh->eh_entries = 0!",
+ inode->i_ino);
}
return merge_done;
@@ -1612,13 +1697,19 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
ext4_lblk_t next;
unsigned uninitialized = 0;
- BUG_ON(ext4_ext_get_actual_len(newext) == 0);
+ if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
+ EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
+ return -EIO;
+ }
depth = ext_depth(inode);
ex = path[depth].p_ext;
- BUG_ON(path[depth].p_hdr == NULL);
+ if (unlikely(path[depth].p_hdr == NULL)) {
+ EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
+ return -EIO;
+ }
/* try to insert block into found extent and return */
- if (ex && (flag != EXT4_GET_BLOCKS_DIO_CREATE_EXT)
+ if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)
&& ext4_can_extents_be_merged(inode, ex, newext)) {
ext_debug("append [%d]%d block to %d:[%d]%d (from %llu)\n",
ext4_ext_is_uninitialized(newext),
@@ -1739,7 +1830,7 @@ has_space:
merge:
/* try to merge extents to the right */
- if (flag != EXT4_GET_BLOCKS_DIO_CREATE_EXT)
+ if (!(flag & EXT4_GET_BLOCKS_PRE_IO))
ext4_ext_try_to_merge(inode, path, nearex);
/* try to merge extents to the left */
@@ -1787,7 +1878,11 @@ int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
}
depth = ext_depth(inode);
- BUG_ON(path[depth].p_hdr == NULL);
+ if (unlikely(path[depth].p_hdr == NULL)) {
+ EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
+ err = -EIO;
+ break;
+ }
ex = path[depth].p_ext;
next = ext4_ext_next_allocated_block(path);
@@ -1838,7 +1933,11 @@ int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
cbex.ec_type = EXT4_EXT_CACHE_EXTENT;
}
- BUG_ON(cbex.ec_len == 0);
+ if (unlikely(cbex.ec_len == 0)) {
+ EXT4_ERROR_INODE(inode, "cbex.ec_len == 0");
+ err = -EIO;
+ break;
+ }
err = func(inode, path, &cbex, ex, cbdata);
ext4_ext_drop_refs(path);
@@ -1952,7 +2051,7 @@ ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
BUG_ON(cex->ec_type != EXT4_EXT_CACHE_GAP &&
cex->ec_type != EXT4_EXT_CACHE_EXTENT);
- if (block >= cex->ec_block && block < cex->ec_block + cex->ec_len) {
+ if (in_range(block, cex->ec_block, cex->ec_len)) {
ex->ee_block = cpu_to_le32(cex->ec_block);
ext4_ext_store_pblock(ex, cex->ec_start);
ex->ee_len = cpu_to_le16(cex->ec_len);
@@ -1981,7 +2080,10 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
/* free index block */
path--;
leaf = idx_pblock(path->p_idx);
- BUG_ON(path->p_hdr->eh_entries == 0);
+ if (unlikely(path->p_hdr->eh_entries == 0)) {
+ EXT4_ERROR_INODE(inode, "path->p_hdr->eh_entries == 0");
+ return -EIO;
+ }
err = ext4_ext_get_access(handle, inode, path);
if (err)
return err;
@@ -2119,8 +2221,10 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
if (!path[depth].p_hdr)
path[depth].p_hdr = ext_block_hdr(path[depth].p_bh);
eh = path[depth].p_hdr;
- BUG_ON(eh == NULL);
-
+ if (unlikely(path[depth].p_hdr == NULL)) {
+ EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
+ return -EIO;
+ }
/* find where to start removing */
ex = EXT_LAST_EXTENT(eh);
@