summaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/balloc.c11
-rw-r--r--fs/ext4/block_validity.c2
-rw-r--r--fs/ext4/dir.c12
-rw-r--r--fs/ext4/ext4.h179
-rw-r--r--fs/ext4/ext4_extents.h3
-rw-r--r--fs/ext4/ext4_jbd2.c2
-rw-r--r--fs/ext4/ext4_jbd2.h27
-rw-r--r--fs/ext4/extents.c288
-rw-r--r--fs/ext4/file.c6
-rw-r--r--fs/ext4/fsync.c93
-rw-r--r--fs/ext4/ialloc.c98
-rw-r--r--fs/ext4/inode.c507
-rw-r--r--fs/ext4/ioctl.c66
-rw-r--r--fs/ext4/mballoc.c152
-rw-r--r--fs/ext4/mballoc.h2
-rw-r--r--fs/ext4/migrate.c41
-rw-r--r--fs/ext4/move_extent.c303
-rw-r--r--fs/ext4/namei.c62
-rw-r--r--fs/ext4/resize.c5
-rw-r--r--fs/ext4/super.c135
-rw-r--r--fs/ext4/xattr.c35
21 files changed, 1299 insertions, 730 deletions
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 1d0418980f8d..e85b63c9fbcb 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -189,9 +189,6 @@ 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
@@ -761,7 +758,13 @@ static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb,
static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb,
ext4_group_t group)
{
- return ext4_bg_has_super(sb, group) ? EXT4_SB(sb)->s_gdb_count : 0;
+ if (!ext4_bg_has_super(sb, group))
+ return 0;
+
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG))
+ return le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg);
+ else
+ return EXT4_SB(sb)->s_gdb_count;
}
/**
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 50784ef07563..dc79b75d8f70 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -160,7 +160,7 @@ int ext4_setup_system_zone(struct super_block *sb)
if (ext4_bg_has_super(sb, i) &&
((i < 5) || ((i % flex_size) == 0)))
add_system_zone(sbi, ext4_group_first_block_no(sb, i),
- sbi->s_gdb_count + 1);
+ ext4_bg_num_gdb(sb, i) + 1);
gdp = ext4_get_group_desc(sb, i, NULL);
ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1);
if (ret)
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 9dc93168e262..aa6fb6b9d3ad 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -84,9 +84,11 @@ int ext4_check_dir_entry(const char *function, struct inode *dir,
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,
+ "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;
@@ -109,7 +111,7 @@ static int ext4_readdir(struct file *filp,
if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_COMPAT_DIR_INDEX) &&
- ((EXT4_I(inode)->i_flags & EXT4_INDEX_FL) ||
+ ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) ||
((inode->i_size >> sb->s_blocksize_bits) == 1))) {
err = ext4_dx_readdir(filp, dirent, filldir);
if (err != ERR_BAD_DX_DIR) {
@@ -120,7 +122,7 @@ static int ext4_readdir(struct file *filp,
* We don't set the inode dirty flag since it's not
* critical that it get flushed back to the disk.
*/
- EXT4_I(filp->f_path.dentry->d_inode)->i_flags &= ~EXT4_INDEX_FL;
+ ext4_clear_inode_flag(filp->f_path.dentry->d_inode, EXT4_INODE_INDEX);
}
stored = 0;
offset = filp->f_pos & (sb->s_blocksize - 1);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 8825515eeddd..0773352fd512 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -29,6 +29,9 @@
#include <linux/wait.h>
#include <linux/blockgroup_lock.h>
#include <linux/percpu_counter.h>
+#ifdef __KERNEL__
+#include <linux/compat.h>
+#endif
/*
* The fourth extended filesystem constants/structures
@@ -139,8 +142,8 @@ typedef struct ext4_io_end {
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 */
+ 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 +287,12 @@ 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 |\
@@ -314,15 +319,81 @@ static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
}
/*
- * Inode dynamic state flags
+ * Inode flags used for atomic set/get
*/
-#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*/
+enum {
+ EXT4_INODE_SECRM = 0, /* Secure deletion */
+ EXT4_INODE_UNRM = 1, /* Undelete */
+ EXT4_INODE_COMPR = 2, /* Compress file */
+ EXT4_INODE_SYNC = 3, /* Synchronous updates */
+ EXT4_INODE_IMMUTABLE = 4, /* Immutable file */
+ EXT4_INODE_APPEND = 5, /* writes to file may only append */
+ EXT4_INODE_NODUMP = 6, /* do not dump file */
+ EXT4_INODE_NOATIME = 7, /* do not update atime */
+/* Reserved for compression usage... */
+ EXT4_INODE_DIRTY = 8,
+ EXT4_INODE_COMPRBLK = 9, /* One or more compressed clusters */
+ EXT4_INODE_NOCOMPR = 10, /* Don't compress */
+ EXT4_INODE_ECOMPR = 11, /* Compression error */
+/* End compression flags --- maybe not all used */
+ EXT4_INODE_INDEX = 12, /* hash-indexed directory */
+ EXT4_INODE_IMAGIC = 13, /* AFS directory */
+ EXT4_INODE_JOURNAL_DATA = 14, /* file data should be journaled */
+ EXT4_INODE_NOTAIL = 15, /* file tail should not be merged */
+ EXT4_INODE_DIRSYNC = 16, /* dirsync behaviour (directories only) */
+ EXT4_INODE_TOPDIR = 17, /* Top of directory hierarchies*/
+ EXT4_INODE_HUGE_FILE = 18, /* Set to each huge file */
+ EXT4_INODE_EXTENTS = 19, /* Inode uses extents */
+ EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */
+ EXT4_INODE_EOFBLOCKS = 22, /* Blocks allocated beyond EOF */
+ EXT4_INODE_RESERVED = 31, /* reserved for ext4 lib */
+};
+
+#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG))
+#define CHECK_FLAG_VALUE(FLAG) if (!TEST_FLAG_VALUE(FLAG)) { \
+ printk(KERN_EMERG "EXT4 flag fail: " #FLAG ": %d %d\n", \
+ EXT4_##FLAG##_FL, EXT4_INODE_##FLAG); BUG_ON(1); }
+
+/*
+ * Since it's pretty easy to mix up bit numbers and hex values, and we
+ * can't do a compile-time test for ENUM values, we use a run-time
+ * test to make sure that EXT4_XXX_FL is consistent with respect to
+ * EXT4_INODE_XXX. If all is well the printk and BUG_ON will all drop
+ * out so it won't cost any extra space in the compiled kernel image.
+ * But it's important that these values are the same, since we are
+ * using EXT4_INODE_XXX to test for the flag values, but EXT4_XX_FL
+ * must be consistent with the values of FS_XXX_FL defined in
+ * include/linux/fs.h and the on-disk values found in ext2, ext3, and
+ * ext4 filesystems, and of course the values defined in e2fsprogs.
+ *
+ * It's not paranoia if the Murphy's Law really *is* out to get you. :-)
+ */
+static inline void ext4_check_flag_values(void)
+{
+ CHECK_FLAG_VALUE(SECRM);
+ CHECK_FLAG_VALUE(UNRM);
+ CHECK_FLAG_VALUE(COMPR);
+ CHECK_FLAG_VALUE(SYNC);
+ CHECK_FLAG_VALUE(IMMUTABLE);
+ CHECK_FLAG_VALUE(APPEND);
+ CHECK_FLAG_VALUE(NODUMP);
+ CHECK_FLAG_VALUE(NOATIME);
+ CHECK_FLAG_VALUE(DIRTY);
+ CHECK_FLAG_VALUE(COMPRBLK);
+ CHECK_FLAG_VALUE(NOCOMPR);
+ CHECK_FLAG_VALUE(ECOMPR);
+ CHECK_FLAG_VALUE(INDEX);
+ CHECK_FLAG_VALUE(IMAGIC);
+ CHECK_FLAG_VALUE(JOURNAL_DATA);
+ CHECK_FLAG_VALUE(NOTAIL);
+ CHECK_FLAG_VALUE(DIRSYNC);
+ CHECK_FLAG_VALUE(TOPDIR);
+ CHECK_FLAG_VALUE(HUGE_FILE);
+ CHECK_FLAG_VALUE(EXTENTS);
+ CHECK_FLAG_VALUE(EA_INODE);
+ CHECK_FLAG_VALUE(EOFBLOCKS);
+ CHECK_FLAG_VALUE(RESERVED);
+}
/* Used to pass group descriptor data when online resize is done */
struct ext4_new_group_input {
@@ -335,6 +406,18 @@ struct ext4_new_group_input {
__u16 unused;
};
+#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
+struct compat_ext4_new_group_input {
+ u32 group;
+ compat_u64 block_bitmap;
+ compat_u64 inode_bitmap;
+ compat_u64 inode_table;
+ u32 blocks_count;
+ u16 reserved_blocks;
+ u16 unused;
+};
+#endif
+
/* The struct ext4_new_group_input in kernel space, with free_blocks_count */
struct ext4_new_group_data {
__u32 group;
@@ -361,14 +444,11 @@ struct ext4_new_group_data {
so set the magic i_delalloc_reserve_flag after taking the
inode allocation semaphore for */
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004
- /* Call ext4_da_update_reserve_space() after successfully
- allocating the blocks */
-#define EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE 0x0008
/* 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 0x0010
-#define EXT4_GET_BLOCKS_CONVERT 0x0020
+#define EXT4_GET_BLOCKS_DIO 0x0008
+#define EXT4_GET_BLOCKS_CONVERT 0x0010
#define EXT4_GET_BLOCKS_DIO_CREATE_EXT (EXT4_GET_BLOCKS_DIO|\
EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
/* Convert extent to initialized after direct IO complete */
@@ -397,6 +477,7 @@ struct ext4_new_group_data {
#define EXT4_IOC_ALLOC_DA_BLKS _IO('f', 12)
#define EXT4_IOC_MOVE_EXT _IOWR('f', 15, struct move_extent)
+#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
* ioctl commands in 32 bit emulation
*/
@@ -407,11 +488,13 @@ struct ext4_new_group_data {
#define EXT4_IOC32_GETRSVSZ _IOR('f', 5, int)
#define EXT4_IOC32_SETRSVSZ _IOW('f', 6, int)
#define EXT4_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int)
+#define EXT4_IOC32_GROUP_ADD _IOW('f', 8, struct compat_ext4_new_group_input)
#ifdef CONFIG_JBD2_DEBUG
#define EXT4_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int)
#endif
#define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION
+#endif
/*
@@ -615,9 +698,8 @@ struct ext4_ext_cache {
*/
struct ext4_inode_info {
__le32 i_data[15]; /* unconverted */
- __u32 i_flags;
- ext4_fsblk_t i_file_acl;
__u32 i_dtime;
+ ext4_fsblk_t i_file_acl;
/*
* i_block_group is the number of the block group which contains
@@ -627,7 +709,8 @@ 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 */
+ unsigned long i_flags;
ext4_lblk_t i_dir_start_lookup;
#ifdef CONFIG_EXT4_FS_XATTR
@@ -693,16 +776,29 @@ struct ext4_inode_info {
unsigned int i_reserved_meta_blocks;
unsigned int i_allocated_meta_blocks;
unsigned short i_delalloc_reserved_flag;
+ sector_t i_da_metadata_calc_last_lblock;
+ int i_da_metadata_calc_len;
/* on-disk additional length */
__u16 i_extra_isize;
spinlock_t i_block_reservation_lock;
+#ifdef CONFIG_QUOTA
+ /* quota space reservation, managed internally by quota code */
+ qsize_t i_reserved_quota;
+#endif
/* completed async DIOs that might need unwritten extents handling */
struct list_head i_aio_dio_complete_list;
/* current io_end structure for async DIO write*/
ext4_io_end_t *cur_aio_dio;
+
+ /*
+ * Transactions that contain inode's metadata needed to complete
+ * fsync and fdatasync, respectively.
+ */
+ tid_t i_sync_tid;
+ tid_t i_datasync_tid;
};
/*
@@ -750,6 +846,7 @@ struct ext4_inode_info {
#define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */
#define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */
#define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */
+#define EXT4_MOUNT_DISCARD 0x40000000 /* Issue DISCARD requests */
#define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt
#define set_opt(o, opt) o |= EXT4_MOUNT_##opt
@@ -1033,6 +1130,37 @@ 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*/
+ EXT4_STATE_NEWENTRY, /* File just added to dir */
+};
+
+#define EXT4_INODE_BIT_FNS(name, field) \
+static inline int ext4_test_inode_##name(struct inode *inode, int bit) \
+{ \
+ return test_bit(bit, &EXT4_I(inode)->i_##field); \
+} \
+static inline void ext4_set_inode_##name(struct inode *inode, int bit) \
+{ \
+ set_bit(bit, &EXT4_I(inode)->i_##field); \
+} \
+static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \
+{ \
+ clear_bit(bit, &EXT4_I(inode)->i_##field); \
+}
+
+EXT4_INODE_BIT_FNS(flag, flags)
+EXT4_INODE_BIT_FNS(state, 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
@@ -1217,7 +1345,7 @@ struct ext4_dir_entry_2 {
#define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \
EXT4_FEATURE_COMPAT_DIR_INDEX) && \
- (EXT4_I(dir)->i_flags & EXT4_INDEX_FL))
+ ext4_test_inode_flag((dir), EXT4_INODE_INDEX))
#define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX)
#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1)
@@ -1424,8 +1552,10 @@ extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
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 qsize_t *ext4_get_reserved_space(struct inode *inode);
extern int flush_aio_dio_completed_IO(struct inode *inode);
+extern void ext4_da_update_reserve_space(struct inode *inode,
+ int used, int quota_claim);
/* ioctl.c */
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
@@ -1625,6 +1755,7 @@ struct ext4_group_info {
ext4_grpblk_t bb_first_free; /* first free block */
ext4_grpblk_t bb_free; /* total free blocks */
ext4_grpblk_t bb_fragments; /* nr of freespace fragments */
+ ext4_grpblk_t bb_largest_free_order;/* order of largest frag in BG */
struct list_head bb_prealloc_list;
#ifdef DOUBLE_CHECK
void *bb_bitmap;
@@ -1728,7 +1859,7 @@ 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);
@@ -1757,6 +1888,8 @@ 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_extents.h b/fs/ext4/ext4_extents.h
index 2ca686454e87..bdb6ce7e2eb4 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -225,7 +225,8 @@ static inline void ext4_ext_mark_initialized(struct ext4_extent *ext)
ext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ext));
}
-extern int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks);
+extern int ext4_ext_calc_metadata_amount(struct inode *inode,
+ sector_t lblocks);
extern ext4_fsblk_t ext_pblock(struct ext4_extent *ex);
extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *);
extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t);
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 6a9409920dee..496249aeec96 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -89,7 +89,7 @@ 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);
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index a2865980342f..386095d5b760 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -49,7 +49,7 @@
#define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \
EXT4_XATTR_TRANS_BLOCKS - 2 + \
- 2*EXT4_QUOTA_TRANS_BLOCKS(sb))
+ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
/*
* Define the number of metadata blocks we need to account to modify data.
@@ -57,7 +57,7 @@
* This include super block, inode block, quota blocks and xattr blocks
*/
#define EXT4_META_TRANS_BLOCKS(sb) (EXT4_XATTR_TRANS_BLOCKS + \
- 2*EXT4_QUOTA_TRANS_BLOCKS(sb))
+ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
/* Delete operations potentially hit one directory's namespace plus an
* entire inode, plus arbitrary amounts of bitmap/indirection data. Be
@@ -92,6 +92,7 @@
* but inode, sb and group updates are done only once */
#define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\
(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0)
+
#define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\
(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0)
#else
@@ -99,6 +100,9 @@
#define EXT4_QUOTA_INIT_BLOCKS(sb) 0
#define EXT4_QUOTA_DEL_BLOCKS(sb) 0
#endif
+#define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
int
ext4_mark_iloc_dirty(handle_t *handle,
@@ -254,6 +258,19 @@ static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode)
return 0;
}
+static inline void ext4_update_inode_fsync_trans(handle_t *handle,
+ struct inode *inode,
+ int datasync)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+
+ if (ext4_handle_valid(handle)) {
+ ei->i_sync_tid = handle->h_transaction->t_tid;
+ if (datasync)
+ ei->i_datasync_tid = handle->h_transaction->t_tid;
+ }
+}
+
/* super.c */
int ext4_force_commit(struct super_block *sb);
@@ -265,7 +282,7 @@ static inline int ext4_should_journal_data(struct inode *inode)
return 1;
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
return 1;
- if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
+ if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
return 1;
return 0;
}
@@ -276,7 +293,7 @@ static inline int ext4_should_order_data(struct inode *inode)
return 0;
if (!S_ISREG(inode->i_mode))
return 0;
- if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
+ if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
return 0;
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
return 1;
@@ -289,7 +306,7 @@ static inline int ext4_should_writeback_data(struct inode *inode)
return 0;
if (EXT4_JOURNAL(inode) == NULL)
return 1;
- if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
+ if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
return 0;
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
return 1;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 715264b4bae4..f37555909872 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -107,11 +107,8 @@ static int ext4_ext_truncate_extend_restart(handle_t *handle,
if (err <= 0)
return err;
err = ext4_truncate_restart_trans(handle, inode, needed);
- /*
- * We have dropped i_data_sem so someone might have cached again
- * an extent we are going to truncate.
- */
- ext4_ext_invalidate_cache(inode);
+ if (err == 0)
+ err = -EAGAIN;
return err;
}
@@ -296,29 +293,44 @@ static inline int ext4_ext_space_root_idx(struct inode *inode, int check)
* to allocate @blocks
* Worse case is one block per extent
*/
-int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks)
+int ext4_ext_calc_metadata_amount(struct inode *inode, sector_t lblock)
{
- int lcap, icap, rcap, leafs, idxs, num;
- int newextents = blocks;
-
- rcap = ext4_ext_space_root_idx(inode, 0);
- lcap = ext4_ext_space_block(inode, 0);
- icap = ext4_ext_space_block_idx(inode, 0);
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ int idxs, num = 0;
- /* number of new leaf blocks needed */
- num = leafs = (newextents + lcap - 1) / lcap;
+ idxs = ((inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
+ / sizeof(struct ext4_extent_idx));
/*
- * Worse case, we need separate index block(s)
- * to link all new leaf blocks
+ * If the new delayed allocation block is contiguous with the
+ * previous da block, it can share index blocks with the
+ * previous block, so we only need to allocate a new index
+ * block every idxs leaf blocks. At ldxs**2 blocks, we need
+ * an additional index block, and at ldxs**3 blocks, yet
+ * another index blocks.
*/
- idxs = (leafs + icap - 1) / icap;
- do {
- num += idxs;
- idxs = (idxs + icap - 1) / icap;
- } while (idxs > rcap);
+ if (ei->i_da_metadata_calc_len &&
+ ei->i_da_metadata_calc_last_lblock+1 == lblock) {
+ if ((ei->i_da_metadata_calc_len % idxs) == 0)
+ num++;
+ if ((ei->i_da_metadata_calc_len % (idxs*idxs)) == 0)
+ num++;
+ if ((ei->i_da_metadata_calc_len % (idxs*idxs*idxs)) == 0) {
+ num++;
+ ei->i_da_metadata_calc_len = 0;
+ } else
+ ei->i_da_metadata_calc_len++;
+ ei->i_da_metadata_calc_last_lblock++;
+ return num;
+ }
- return num;
+ /*
+ * In the worst case we need a new set of index blocks at
+ * every level of the inode's extent tree.
+ */
+ ei->i_da_metadata_calc_len = 1;
+ ei->i_da_metadata_calc_last_lblock = lblock;
+ return ext_depth(inode) + 1;
}
static int
@@ -1761,7 +1773,9 @@ int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
while (block < last && block != EXT_MAX_BLOCK) {
num = last - block;
/* find extent for this block */
+ down_read(&EXT4_I(inode)->i_data_sem);
path = ext4_ext_find_extent(inode, block, path);
+ up_read(&EXT4_I(inode)->i_data_sem);
if (IS_ERR(path)) {
err = PTR_ERR(path);
path = NULL;
@@ -1934,7 +1948,7 @@ 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);
@@ -2074,7 +2088,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
ext_debug("free last %u blocks starting %llu\n", num, start);
for (i = 0; i < num; i++) {
bh = sb_find_get_block(inode->i_sb, start + i);
- ext4_forget(handle, 0, inode, bh, start + i);
+ ext4_forget(handle, metadata, inode, bh, start + i);
}
ext4_free_blocks(handle, inode, start, num, metadata);
} else if (from == le32_to_cpu(ex->ee_block)
@@ -2167,7 +2181,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
correct_index = 1;
credits += (ext_depth(inode)) + 1;
}
- credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
+ credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb);
err = ext4_ext_truncate_extend_restart(handle, inode, credits);
if (err)
@@ -2246,7 +2260,7 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
int depth = ext_depth(inode);
struct ext4_ext_path *path;
handle_t *handle;
- int i = 0, err = 0;
+ int i, err;
ext_debug("truncate since %u\n", start);
@@ -2255,23 +2269,26 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
if (IS_ERR(handle))
return PTR_ERR(handle);
+again:
ext4_ext_invalidate_cache(inode);
/*
* We start scanning from right side, freeing all the blocks
* after i_size and walking into the tree depth-wise.
*/
+ depth = ext_depth(inode);
path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_NOFS);
if (path == NULL) {
ext4_journal_stop(handle);
return -ENOMEM;
}
+ path[0].p_depth = depth;
path[0].p_hdr = ext_inode_hdr(inode);
if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
err = -EIO;
goto out;
}
- path[0].p_depth = depth;
+ i = err = 0;
while (i >= 0 && err == 0) {
if (i == depth) {
@@ -2365,6 +2382,8 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start)
out:
ext4_ext_drop_refs(path);
kfree(path);
+ if (err == -EAGAIN)
+ goto again;
ext4_journal_stop(handle);
return err;
@@ -2429,7 +2448,7 @@ static void bi_complete(struct bio *bio, int error)
/* FIXME!! we need to try to merge to left or right after zero-out */
static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
{
- int ret = -EIO;
+ int ret;
struct bio *bio;
int blkbits, blocksize;
sector_t ee_pblock;
@@ -2453,6 +2472,9 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
len = ee_len;
bio = bio_alloc(GFP_NOIO, len);
+ if (!bio)
+ return -ENOMEM;
+
bio->bi_sector = ee_pblock;
bio->bi_bdev = inode->i_sb->s_bdev;
@@ -2480,17 +2502,15 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
submit_bio(WRITE, bio);
wait_for_completion(&event);
- if (test_bit(BIO_UPTODATE, &bio->bi_flags))
- ret = 0;
- else {
- ret = -EIO;
- break;
+ if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+ bio_put(bio);
+ return -EIO;
}
bio_put(bio);
ee_len -= done;
ee_pblock += done << (blkbits - 9);
}
- return ret;
+ return 0;
}
#define EXT4_EXT_ZERO_LEN 7
@@ -2515,11 +2535,21 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
struct ext4_extent *ex2 = NULL;
struct ext4_extent *ex3 = NULL;
struct ext4_extent_header *eh;
- ext4_lblk_t ee_block;
+ ext4_lblk_t ee_block, eof_block;
unsigned int allocated, ee_len, depth;
ext4_fsblk_t newblock;
int err = 0;
int ret = 0;
+ int may_zeroout;
+
+ ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical"
+ "block %llu, max_blocks %u\n", inode->i_ino,
+ (unsigned long long)iblock, max_blocks);
+
+ eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
+ inode->i_sb->s_blocksize_bits;
+ if (eof_block < iblock + max_blocks)
+ eof_block = iblock + max_blocks;
depth = ext_depth(inode);
eh = path[depth].p_hdr;
@@ -2528,16 +2558,23 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
ee_len = ext4_ext_get_actual_len(ex);
allocated = ee_len - (iblock - ee_block);
newblock = iblock - ee_block + ext_pblock(ex);
+
ex2 = ex;
orig_ex.ee_block = ex->ee_block;
orig_ex.ee_len = cpu_to_le16(ee_len);
ext4_ext_store_pblock(&orig_ex, ext_pblock(ex));
+ /*
+ * It is safe to convert extent to initialized via explicit
+ * zeroout only if extent is fully insde i_size or new_size.
+ */
+ may_zeroout = ee_block + ee_len <= eof_block;
+
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto out;
/* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */
- if (ee_len <= 2*EXT4_EXT_ZERO_LEN) {
+ if (ee_len <= 2*EXT4_EXT_ZERO_LEN && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -2568,7 +2605,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
if (allocated > max_blocks) {
unsigned int newdepth;
/* If extent has less than EXT4_EXT_ZERO_LEN zerout directly */
- if (allocated <= EXT4_EXT_ZERO_LEN) {
+ if (allocated <= EXT4_EXT_ZERO_LEN && may_zeroout) {
/*
* iblock == ee_block is handled by the zerouout
* at the beginning.
@@ -2644,7 +2681,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
ex3->ee_len = cpu_to_le16(allocated - max_blocks);
ext4_ext_mark_uninitialized(ex3);
err = ext4_ext_insert_extent(handle, inode, path, ex3, 0);
- if (err == -ENOSPC) {
+ if (err == -ENOSPC && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -2668,8 +2705,10 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
* update the extent length after successful insert of the
* split extent
*/
- orig_ex.ee_len = cpu_to_le16(ee_len -
- ext4_ext_get_actual_len(ex3));
+ ee_len -= ext4_ext_get_actual_len(ex3);
+ orig_ex.ee_len = cpu_to_le16(ee_len);
+ may_zeroout = ee_block + ee_len <= eof_block;
+
depth = newdepth;
ext4_ext_drop_refs(path);
path = ext4_ext_find_extent(inode, iblock, path);
@@ -2693,7 +2732,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
* otherwise give the extent a chance to merge to left
*/
if (le16_to_cpu(orig_ex.ee_len) <= EXT4_EXT_ZERO_LEN &&
- iblock != ee_block) {
+ iblock != ee_block && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -2762,7 +2801,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
goto out;
insert:
err = ext4_ext_insert_extent(handle, inode, path, &newex, 0);
- if (err == -ENOSPC) {
+ if (err == -ENOSPC && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -2822,14 +2861,21 @@ static int ext4_split_unwritten_extents(handle_t *handle,
struct ext4_extent *ex2 = NULL;
struct ext4_extent *ex3 = NULL;
struct ext4_extent_header *eh;
- ext4_lblk_t ee_block;
+ ext4_lblk_t ee_block, eof_block;
unsigned int allocated, ee_len, depth;
ext4_fsblk_t newblock;
int err = 0;
+ int may_zeroout;
+
+ ext_debug("ext4_split_unwritten_extents: inode %lu, logical"
+ "block %llu, max_blocks %u\n", inode->i_ino,
+ (unsigned long long)iblock, max_blocks);
+
+ eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
+ inode->i_sb->s_blocksize_bits;
+ if (eof_block < iblock + max_blocks)
+ eof_block = iblock + max_blocks;
- ext_debug("ext4_split_unwritten_extents: inode %lu,"
- "iblock %llu, max_blocks %u\n", inode->i_ino,
- (unsigned long long)iblock, max_blocks);
depth = ext_depth(inode);
eh = path[depth].p_hdr;
ex = path[depth].p_ext;
@@ -2837,12 +2883,19 @@ static int ext4_split_unwritten_extents(handle_t *handle,
ee_len = ext4_ext_get_actual_len(ex);
allocated = ee_len - (iblock - ee_block);
newblock = iblock - ee_block + ext_pblock(ex);
+
ex2 = ex;
orig_ex.ee_block = ex->ee_block;
orig_ex.ee_len = cpu_to_le16(ee_len);
ext4_ext_store_pblock(&orig_ex, ext_pblock(ex));
/*
+ * It is safe to convert extent to initialized via explicit
+ * zeroout only if extent is fully insde i_size or new_size.
+ */
+ may_zeroout = ee_block + ee_len <= eof_block;
+
+ /*
* If the uninitialized extent begins at the same logical
* block where the write begins, and the write completely
* covers the extent, then we don't need to split it.
@@ -2876,7 +2929,7 @@ static int ext4_split_unwritten_extents(handle_t *handle,
ex3->ee_len = cpu_to_le16(allocated - max_blocks);
ext4_ext_mark_uninitialized(ex3);
err = ext4_ext_insert_extent(handle, inode, path, ex3, flags);
- if (err == -ENOSPC) {
+ if (err == -ENOSPC && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -2900,8 +2953,10 @@ static int ext4_split_unwritten_extents(handle_t *handle,
* update the extent length after successful insert of the
* split extent
*/
- orig_ex.ee_len = cpu_to_le16(ee_len -
- ext4_ext_get_actual_len(ex3));
+ ee_len -= ext4_ext_get_actual_len(ex3);
+ orig_ex.ee_len = cpu_to_le16(ee_len);
+ may_zeroout = ee_block + ee_len <= eof_block;
+
depth = newdepth;
ext4_ext_drop_refs(path);
path = ext4_ext_find_extent(inode, iblock, path);
@@ -2947,7 +3002,7 @@ static int ext4_split_unwritten_extents(handle_t *handle,
goto out;
insert:
err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
- if (err == -ENOSPC) {
+ if (err == -ENOSPC && may_zeroout) {
err = ext4_ext_zeroout(inode, &orig_ex);
if (err)
goto fix_extent_len;
@@ -3027,6 +3082,14 @@ out:
return err;
}
+static void unmap_underlying_metadata_blocks(struct block_device *bdev,
+ sector_t block, int count)
+{
+ int i;
+ for (i = 0; i < count; i++)
+ unmap_underlying_metadata(bdev, block + i);
+}
+
static int
ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
ext4_lblk_t iblock, unsigned int max_blocks,
@@ -3057,13 +3120,15 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
if (io)
io->flag = DIO_AIO_UNWRITTEN;
else
- EXT4_I(inode)->i_state |= EXT4_STATE_DIO_UNWRITTEN;
+ ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
goto out;
}
/* async DIO end_io complete, convert the filled extent to written */
if (flags == EXT4_GET_BLOCKS_DIO_CONVERT_EXT) {
ret = ext4_convert_unwritten_extents_dio(handle, inode,
path);
+ if (ret >= 0)
+ ext4_update_inode_fsync_trans(handle, inode, 1);
goto out2;
}
/* buffered IO case */
@@ -3091,6 +3156,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
ret = ext4_ext_convert_to_initialized(handle, inode,
path, iblock,
max_blocks);
+ if (ret >= 0)
+ ext4_update_inode_fsync_trans(handle, inode, 1);
out:
if (ret <= 0) {
err = ret;
@@ -3098,6 +3165,30 @@ out:
} else
allocated = ret;
set_buffer_new(bh_result);
+ /*
+ * if we allocated more blocks than requested
+ * we need to make sure we unmap the extra block
+ * allocated. The actual needed block will get
+ * unmapped later when we find the buffer_head marked
+ * new.
+ */
+ if (allocated > max_blocks) {
+ unmap_underlying_metadata_blocks(inode->i_sb->s_bdev,
+ newblock + max_blocks,
+ allocated - max_blocks);
+ allocated = max_blocks;
+ }
+
+ /*
+ * If we have done fallocate with the offset that is already
+ * delayed allocated, we would have block reservation
+ * and quota reservation done in the delayed write path.
+ * But fallocate would have already updated quota and block
+ * count for this offset. So cancel these reservation
+ */
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+ ext4_da_update_reserve_space(inode, allocated, 0);
+
map_out:
set_buffer_mapped(bh_result);
out1:
@@ -3138,9 +3229,9 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
{
struct ext4_ext_path *path = NULL;
struct ext4_extent_header *eh;
- struct ext4_extent newex, *ex;
+ struct ext4_extent newex, *ex, *last_ex;
ext4_fsblk_t newblock;
- int err = 0, depth, ret, cache_type;
+ int i, 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;
@@ -3190,7 +3281,13 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
* this situation is possible, though, _during_ tree modification;
* this is why assert can't be put in ext4_ext_find_extent()
*/
- BUG_ON(path[depth].p_ext == NULL && depth != 0);
+ if (path[depth].p_ext == NULL && depth != 0) {
+ ext4_error(inode->i_sb, __func__, "bad extent address "
+ "inode: %lu, iblock: %lu, depth: %d",
+ inode->i_ino, (unsigned long) iblock, depth);
+ err = -EIO;
+ goto out2;
+ }
eh = path[depth].p_hdr;
ex = path[depth].p_ext;
@@ -3205,7 +3302,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
*/
ee_len = ext4_ext_get_actual_len(ex);
/* if found extent covers block, simply return it */
- if (iblock >= ee_block && iblock < ee_block + ee_len) {
+ if (in_range(iblock, ee_block, ee_len)) {
newblock = iblock - ee_block + ee_start;
/* number of remaining blocks in the extent */
allocated = ee_len - (iblock - ee_block);
@@ -3309,10 +3406,36 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
if (io)
io->flag = DIO_AIO_UNWRITTEN;
else
- EXT4_I(inode)->i_state |=
- EXT4_STATE_DIO_UNWRITTEN;;
+ ext4_set_inode_state(inode,
+ EXT4_STATE_DIO_UNWRITTEN);
}
}
+
+ if (unlikely(ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))) {
+ if (unlikely(!eh->eh_entries)) {
+ ext4_error(inode->i_sb, __func__,
+ "inode#%lu, eh->eh_entries = 0 and "
+ "EOFBLOCKS_FL set", inode->i_ino);
+ 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) &&
+ (iblock + 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 = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
if (err) {
/* free data blocks we just allocated */
@@ -3327,12 +3450,27 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
/* previous routine could use block we allocated */
newblock = ext_pblock(&newex);
allocated = ext4_ext_get_actual_len(&newex);
+ if (allocated > max_blocks)
+ allocated = max_blocks;
set_buffer_new(bh_result);
- /* Cache only when it is _not_ an uninitialized extent */
- if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0)
+ /*
+ * Update reserved blocks/metadata blocks after successful
+ * block allocation which had been deferred till now.
+ */
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+ ext4_da_update_reserve_space(inode, allocated, 1);
+
+ /*
+ * Cache the extent and update transaction to commit on fdatasync only
+ * when it is _not_ an uninitialized extent.
+ */
+ if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0) {
ext4_ext_put_in_cache(inode, iblock, allocated, newblock,
EXT4_EXT_CACHE_EXTENT);
+ ext4_update_inode_fsync_trans(handle, inode, 1);
+ } else
+ ext4_update_inode_fsync_trans(handle, inode, 0);
out:
if (allocated > max_blocks)
allocated = max_blocks;
@@ -3431,6 +3569,13 @@ static void ext4_falloc_update_inode(struct inode *inode,
i_size_write(inode, new_size);
if (new_size > EXT4_I(inode)->i_disksize)
ext4_update_i_disksize(inode, new_size);
+ } else {
+ /*
+ * Mark that we allocate beyond EOF so the subsequent truncate
+ * can proceed even if the new size is the same as i_size.
+ */
+ if (new_size > i_size_read(inode))
+ ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
}
}
@@ -3458,7 +3603,7 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
* currently supporting (pre)allocate mode for extent-based
* files _only_
*/
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return -EOPNOTSUPP;
/* preallocation to directories is currently not supported */
@@ -3477,6 +3622,11 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
*/
credits = ext4_chunk_trans_blocks(inode, max_blocks);
mutex_lock(&inode->i_mutex);
+ ret = inode_newsize_ok(inode, (len + offset));
+ if (ret) {
+ mutex_unlock(&inode->i_mutex);
+ return ret;
+ }
retry:
while (ret >= 0 && ret < max_blocks) {
block = block + ret;
@@ -3535,7 +3685,7 @@ retry:
* Returns 0 on success.
*/
int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
- loff_t len)
+ ssize_t len)
{
handle_t *handle;
ext4_lblk_t block;
@@ -3671,7 +3821,7 @@ static int ext4_xattr_fiemap(struct inode *inode,
int error = 0;
/* in-inode? */
- if (EXT4_I(inode)->i_state & EXT4_STATE_XATTR) {
+ if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
struct ext4_iloc iloc;
int offset; /* offset of xattr in inode */
@@ -3684,6 +3834,7 @@ static int ext4_xattr_fiemap(struct inode *inode,
physical += offset;
length = EXT4_SB(inode->i_sb)->s_inode_size - offset;
flags |= FIEMAP_EXTENT_DATA_INLINE;
+ brelse(iloc.bh);
} else { /* external block */
physical = EXT4_I(inode)->i_file_acl << blockbits;
length = inode->i_sb->s_blocksize;
@@ -3699,11 +3850,10 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len)
{
ext4_lblk_t start_blk;
- ext4_lblk_t len_blks;
int error = 0;
/* fallback to generic here if not in extents fmt */
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return generic_block_fiemap(inode, fieinfo, start, len,
ext4_get_block);
@@ -3713,17 +3863,21 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
error = ext4_xattr_fiemap(inode, fieinfo);
} else {
+ ext4_lblk_t len_blks;
+ __u64 last_blk;
+
start_blk = start >> inode->i_sb->s_blocksize_bits;
- len_blks = len >> inode->i_sb->s_blocksize_bits;
+ last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits;
+ if (last_blk >= EXT_MAX_BLOCK)
+ last_blk = EXT_MAX_BLOCK-1;
+ len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1;
/*
* Walk the extent tree gathering extent information.
* ext4_ext_fiemap_cb will push extents back to user.
*/
- down_read(&EXT4_I(inode)->i_data_sem);
error = ext4_ext_walk_space(inode, start_blk, len_blks,
ext4_ext_fiemap_cb, fieinfo);
- up_read(&EXT4_I(inode)->i_data_sem);
}
return error;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 9630583cef28..2a6054129bbc 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -35,9 +35,9 @@
*/
static int ext4_release_file(struct inode *inode, struct file *filp)
{
- if (EXT4_I(inode)->i_state & EXT4_STATE_DA_ALLOC_CLOSE) {
+ if (ext4_test_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE)) {
ext4_alloc_da_blocks(inode);
- EXT4_I(inode)->i_state &= ~EXT4_STATE_DA_ALLOC_CLOSE;
+ ext4_clear_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
}
/* if we are the last writer on the inode, drop the block reservation */
if ((filp->f_mode & FMODE_WRITE) &&
@@ -65,7 +65,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
* is smaller than s_maxbytes, which is for extent-mapped files.
*/
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) {
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
size_t length = iov_length(iov, nr_segs);
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 2b1531266ee2..c3660a60c300 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -35,6 +35,29 @@
#include <trace/events/ext4.h>
/*
+ * If we're not journaling and this is a just-created file, we have to
+ * sync our parent directory (if it was freshly created) since
+ * otherwise it will only be written by writeback, leaving a huge
+ * window during which a crash may lose the file. This may apply for
+ * the parent directory's parent as well, and so on recursively, if
+ * they are also freshly created.
+ */
+static void ext4_sync_parent(struct inode *inode)
+{
+ struct dentry *dentry = NULL;
+
+ while (inode && ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
+ ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
+ dentry = list_entry(inode->i_dentry.next,
+ struct dentry, d_alias);
+ if (!dentry || !dentry->d_parent || !dentry->d_parent->d_inode)
+ break;
+ inode = dentry->d_parent->d_inode;
+ sync_mapping_buffers(inode->i_mapping);
+ }
+}
+
+/*
* akpm: A new design for ext4_sync_file().
*
* This is only called from sys_fsync(), sys_fdatasync() and sys_msync().
@@ -51,25 +74,34 @@
int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
+ struct ext4_inode_info *ei = EXT4_I(inode);
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
- int err, ret = 0;
+ int ret;
+ tid_t commit_tid;
J_ASSERT(ext4_journal_current_handle() == NULL);
trace_ext4_sync_file(file, dentry, datasync);
+ if (inode->i_sb->s_flags & MS_RDONLY)
+ return 0;
+
ret = flush_aio_dio_completed_IO(inode);
if (ret < 0)
- goto out;
+ return ret;
+
+ if (!journal) {
+ ret = simple_fsync(file, dentry, datasync);
+ if (!ret && !list_empty(&inode->i_dentry))
+ ext4_sync_parent(inode);
+ return ret;
+ }
+
/*
- * data=writeback:
+ * data=writeback,ordered:
* The caller's filemap_fdatawrite()/wait will sync the data.
- * sync_inode() will sync the metadata
- *
- * data=ordered:
- * The caller's filemap_fdatawrite() will write the data and
- * sync_inode() will write the inode if it is dirty. Then the caller's
- * filemap_fdatawait() will wait on the pages.
+ * Metadata is in the journal, we wait for proper transaction to
+ * commit here.
*
* data=journal:
* filemap_fdatawrite won't do anything (the buffers are clean).
@@ -79,32 +111,25 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
* (they were dirtied by commit). But that's OK - the blocks are
* safe in-journal, which is all fsync() needs to ensure.
*/
- if (ext4_should_journal_data(inode)) {
- ret = ext4_force_commit(inode->i_sb);
- goto out;
- }
-
- if (!journal)
- ret = sync_mapping_buffers(inode->i_mapping);
+ if (ext4_should_journal_data(inode))
+ return ext4_force_commit(inode->i_sb);
- if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
- goto out;
-
- /*
- * The VFS has written the file data. If the inode is unaltered
- * then we need not start a commit.
- */
- if (inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC)) {
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_ALL,
- .nr_to_write = 0, /* sys_fsync did this */
- };
- err = sync_inode(inode, &wbc);
- if (ret == 0)
- ret = err;
- }
-out:
- if (journal && (journal->j_flags & JBD2_BARRIER))
+ commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
+ if (jbd2_log_start_commit(journal, commit_tid)) {
+ /*
+ * When the journal is on a different device than the
+ * fs data disk, we need to issue the barrier in
+ * writeback mode. (In ordered mode, the jbd2 layer
+ * will take care of issuing the barrier. In
+ * data=journal, all of the data blocks are written to
+ * the journal device.)
+ */
+ if (ext4_should_writeback_data(inode) &&
+ (journal->j_fs_dev != journal->j_dev) &&
+ (journal->j_flags & JBD2_BARRIER))
+ blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
+ ret = jbd2_log_wait_commit(journal, commit_tid);
+ } else if (journal->j_flags & JBD2_BARRIER)
blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
return ret;
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f3624ead4f6c..55a93f5bb003 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -244,57 +244,50 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
if (fatal)
goto error_return;
- /* Ok, now we can actually update the inode bitmaps.. */
- cleared = ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
- bit, bitmap_bh->b_data);
- if (!cleared)
- ext4_error(sb, "ext4_free_inode",
- "bit already cleared for inode %lu", ino);
- else {
- gdp = ext4_get_group_desc(sb, block_group, &bh2);
-
+ fatal = -ESRCH;
+ gdp = ext4_get_group_desc(sb, block_group, &bh2);
+ if (gdp) {
BUFFER_TRACE(bh2, "get_write_access");
fatal = ext4_journal_get_write_access(handle, bh2);
- if (fatal) goto error_return;
-
- if (gdp) {
- ext4_lock_group(sb, block_group);
- count = ext4_free_inodes_count(sb, gdp) + 1;
- ext4_free_inodes_set(sb, gdp, count);
- if (is_directory) {
- count = ext4_used_dirs_count(sb, gdp) - 1;
- ext4_used_dirs_set(sb, gdp, count);
- if (sbi->s_log_groups_per_flex) {
- ext4_group_t f;
-
- f = ext4_flex_group(sbi, block_group);
- atomic_dec(&sbi->s_flex_groups[f].free_inodes);
- }
+ }
+ ext4_lock_group(sb, block_group);
+ cleared = ext4_clear_bit(bit, bitmap_bh->b_data);
+ if (fatal || !cleared) {
+ ext4_unlock_group(sb, block_group);
+ goto out;
+ }
- }
- gdp->bg_checksum = ext4_group_desc_csum(sbi,
- block_group, gdp);
- ext4_unlock_group(sb, block_group);
- percpu_counter_inc(&sbi->s_freeinodes_counter);
- if (is_directory)
- percpu_counter_dec(&sbi->s_dirs_counter);
-
- if (sbi->s_log_groups_per_flex) {
- ext4_group_t f;
-
- f = ext4_flex_group(sbi, block_group);
- atomic_inc(&sbi->s_flex_groups[f].free_inodes);
- }
- }
- BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
- err = ext4_handle_dirty_metadata(handle, NULL, bh2);
- if (!fatal) fatal = err;
+ count = ext4_free_inodes_count(sb, gdp) + 1;
+ ext4_free_inodes_set(sb, gdp, count);
+ if (is_directory) {
+ count = ext4_used_dirs_count(sb, gdp) - 1;
+ ext4_used_dirs_set(sb, gdp, count);
+ percpu_counter_dec(&sbi->s_dirs_counter);
}
- BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata");
- err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
- if (!fatal)
- fatal = err;
- sb->s_dirt = 1;
+ gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp);
+ ext4_unlock_group(sb, block_group);
+
+ percpu_counter_inc(&sbi->s_freeinodes_counter);
+ if (sbi->s_log_groups_per_flex) {
+ ext4_group_t f = ext4_flex_group(sbi, block_group);
+
+ atomic_inc(&sbi->s_flex_groups[f].free_inodes);
+ if (is_directory)
+ atomic_dec(&sbi->s_flex_groups[f].used_dirs);
+ }
+ BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
+ fatal = ext4_handle_dirty_metadata(handle, NULL, bh2);
+out:
+ if (cleared) {
+ BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
+ if (!fatal)
+ fatal = err;
+ sb->s_dirt = 1;
+ } else
+ ext4_error(sb, "ext4_free_inode",
+ "bit already cleared for inode %lu", ino);
+
error_return:
brelse(bitmap_bh);
ext4_std_error(sb, fatal);
@@ -504,7 +497,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
if (S_ISDIR(mode) &&
((parent == sb->s_root->d_inode) ||
- (EXT4_I(parent)->i_flags & EXT4_TOPDIR_FL))) {
+ (ext4_test_inode_flag(parent, EXT4_INODE_TOPDIR)))) {
int best_ndir = inodes_per_group;
int ret = -1;
@@ -779,7 +772,7 @@ static int ext4_claim_inode(struct super_block *sb,
if (sbi->s_log_groups_per_flex) {
ext4_group_t f = ext4_flex_group(sbi, group);
- atomic_inc(&sbi->s_flex_groups[f].free_inodes);
+ atomic_inc(&sbi->s_flex_groups[f].used_dirs);
}
}
gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
@@ -904,7 +897,7 @@ repeat_in_this_group:
BUFFER_TRACE(inode_bitmap_bh,
"call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle,
- inode,
+ NULL,
inode_bitmap_bh);
if (err)
goto fail;
@@ -1029,7 +1022,8 @@ got:
inode->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
- ei->i_state = EXT4_STATE_NEW;
+ ei->i_state_flags = 0;
+ ext4_set_inode_state(inode, EXT4_STATE_NEW);
ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;
@@ -1050,7 +1044,7 @@ got:
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
/* set extent flag only for directory, file and normal symlink*/
if (S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) {
- EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
+ ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS);
ext4_ext_tree_init(handle, inode);
}
}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2c8caa51addb..1b23f9d2ef56 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -957,7 +957,7 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
int count = 0;
ext4_fsblk_t first_block = 0;
- J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL));
+ J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)));
J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
depth = ext4_block_to_path(inode, iblock, offsets,
&blocks_to_boundary);
@@ -1021,10 +1021,12 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
if (!err)
err = ext4_splice_branch(handle, inode, iblock,
partial, indirect_blks, count);
- else
+ if (err)
goto cleanup;
set_buffer_new(bh_result);
+
+ ext4_update_inode_fsync_trans(handle, inode, 1);
got_it:
map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
if (count > blocks_to_boundary)
@@ -1043,92 +1045,121 @@ out:
return err;
}
-qsize_t ext4_get_reserved_space(struct inode *inode)
+#ifdef CONFIG_QUOTA
+qsize_t *ext4_get_reserved_space(struct inode *inode)
{
- unsigned long long total;
-
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- total = EXT4_I(inode)->i_reserved_data_blocks +
- EXT4_I(inode)->i_reserved_meta_blocks;
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
-
- return total;
+ return &EXT4_I(inode)->i_reserved_quota;
}
+#endif
+
/*
* Calculate the number of metadata blocks need to reserve
- * to allocate @blocks for non extent file based file
+ * to allocate a new block at @lblocks for non extent file based file
*/
-static int ext4_indirect_calc_metadata_amount(struct inode *inode, int blocks)
+static int ext4_indirect_calc_metadata_amount(struct inode *inode,
+ sector_t lblock)
{
- int icap = EXT4_ADDR_PER_BLOCK(inode->i_sb);
- int ind_blks, dind_blks, tind_blks;
-
- /* number of new indirect blocks needed */
- ind_blks = (blocks + icap - 1) / icap;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ sector_t dind_mask = ~((sector_t)EXT4_ADDR_PER_BLOCK(inode->i_sb) - 1);
+ int blk_bits;
- dind_blks = (ind_blks + icap - 1) / icap;
+ if (lblock < EXT4_NDIR_BLOCKS)
+ return 0;
- tind_blks = 1;
+ lblock -= EXT4_NDIR_BLOCKS;
- return ind_blks + dind_blks + tind_blks;
+ if (ei->i_da_metadata_calc_len &&
+ (lblock & dind_mask) == ei->i_da_metadata_calc_last_lblock) {
+ ei->i_da_metadata_calc_len++;
+ return 0;
+ }
+ ei->i_da_metadata_calc_last_lblock = lblock & dind_mask;
+ ei->i_da_metadata_calc_len = 1;
+ blk_bits = order_base_2(lblock);
+ return (blk_bits / EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb)) + 1;
}
/*
* Calculate the number of metadata blocks need to reserve
- * to allocate given number of blocks
+ * to allocate a block located at @lblock
*/
-static int ext4_calc_metadata_amount(struct inode *inode, int blocks)
+static int ext4_calc_metadata_amount(struct inode *inode, sector_t lblock)
{
- if (!blocks)
- return 0;
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ return ext4_ext_calc_metadata_amount(inode, lblock);
- if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
- return ext4_ext_calc_metadata_amount(inode, blocks);
-
- return ext4_indirect_calc_metadata_amount(inode, blocks);
+ return ext4_indirect_calc_metadata_amount(inode, lblock);
}
-static void ext4_da_update_reserve_space(struct inode *inode, int used)
+/*
+ * Called with i_data_sem down, which is important since we can call
+ * ext4_discard_preallocations() from here.
+ */
+void ext4_da_update_reserve_space(struct inode *inode,
+ int used, int quota_claim)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- int total, mdb, mdb_free;
-
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- /* recalculate the number of metablocks still need to be reserved */
- total = EXT4_I(inode)->i_reserved_data_blocks - used;
- mdb = ext4_calc_metadata_amount(inode, total);
-
- /* figure out how many metablocks to release */
- BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
- mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
-
- if (mdb_free) {
- /* Account for allocated meta_blocks */
- mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
-
- /* update fs dirty blocks counter */
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ int mdb_free = 0, allocated_meta_blocks = 0;
+
+ spin_lock(&ei->i_block_reservation_lock);
+ if (unlikely(used > ei->i_reserved_data_blocks)) {
+ ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d "
+ "with only %d reserved data blocks\n",
+ __func__, inode->i_ino, used,
+ ei->i_reserved_data_blocks);
+ WARN_ON(1);
+ used = ei->i_reserved_data_blocks;
+ }
+
+ /* Update per-inode reservations */
+ ei->i_reserved_data_blocks -= used;
+ used += ei->i_allocated_meta_blocks;
+ ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
+ allocated_meta_blocks = ei->i_allocated_meta_blocks;
+ ei->i_allocated_meta_blocks = 0;
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter, used);
+
+ if (ei->i_reserved_data_blocks == 0) {
+ /*
+ * We can release all of the reserved metadata blocks
+ * only when we have written all of the delayed
+ * allocation blocks.
+ */
+ mdb_free = ei->i_reserved_meta_blocks;
+ ei->i_reserved_meta_blocks = 0;
+ ei->i_da_metadata_calc_len = 0;
percpu_counter_sub(&sbi->s_dirtyblocks_counter, mdb_free);
- EXT4_I(inode)->i_allocated_meta_blocks = 0;
- EXT4_I(inode)->i_reserved_meta_blocks = mdb;
}
-
- /* update per-inode reservations */
- BUG_ON(used > EXT4_I(inode)->i_reserved_data_blocks);
- EXT4_I(inode)->i_reserved_data_blocks -= used;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- /*
- * free those over-booking quota for metadata blocks
- */
- if (mdb_free)
- vfs_dq_release_reservation_block(inode, mdb_free);
+ /* Update quota subsystem */
+ if (quota_claim) {
+ vfs_dq_claim_block(inode, used);
+ if (mdb_free)
+ vfs_dq_release_reservation_block(inode, mdb_free);
+ } else {
+ /*
+ * We did fallocate with an offset that is already delayed
+ * allocated. So on delayed allocated writeback we should
+ * not update the quota for allocated blocks. But then
+ * converting an fallocate region to initialized region would
+ * have caused a metadata allocation. So claim quota for
+ * that
+ */
+ if (allocated_meta_blocks)
+ vfs_dq_claim_block(inode, allocated_meta_blocks);
+ vfs_dq_release_reservation_block(inode, mdb_free + used -
+ allocated_meta_blocks);
+ }
/*
* If we have done all the pending block allocations and if
* there aren't any writers on the inode, we can discard the
* inode's preallocations.
*/
- if (!total && (atomic_read(&inode->i_writecount) == 0))
+ if ((ei->i_reserved_data_blocks == 0) &&
+ (atomic_read(&inode->i_writecount) == 0))
ext4_discard_preallocations(inode);
}
@@ -1243,7 +1274,7 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
* file system block.
*/
down_read((&EXT4_I(inode)->i_data_sem));
- if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_get_blocks(handle, inode, block, max_blocks,
bh, 0);
} else {
@@ -1305,7 +1336,7 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
* We need to check for EXT4 here because migrate
* could have changed the inode type in between
*/
- if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_get_blocks(handle, inode, block, max_blocks,
bh, flags);
} else {
@@ -1318,20 +1349,22 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
* i_data's format changing. Force the migrate
* to fail by clearing migrate flags
*/
- EXT4_I(inode)->i_state &= ~EXT4_STATE_EXT_MIGRATE;
+ ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
}
- }
+ /*
+ * Update reserved blocks/metadata blocks after successful
+ * block allocation which had been deferred till now. We don't
+ * support fallocate for non extent files. So we can update
+ * reserve space here.
+ */
+ if ((retval > 0) &&
+ (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
+ ext4_da_update_reserve_space(inode, retval, 1);
+ }
if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
EXT4_I(inode)->i_delalloc_reserved_flag = 0;
- /*
- * Update reserved blocks/metadata blocks after successful
- * block allocation which had been deferred till now.
- */
- if ((retval > 0) && (flags & EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE))
- ext4_da_update_reserve_space(inode, retval);
-
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && buffer_mapped(bh)) {
int ret = check_block_validity(inode, "file system "
@@ -1534,6 +1567,16 @@ static int do_journal_get_write_access(handle_t *handle,
return ext4_journal_get_write_access(handle, bh);
}
+/*
+ * Truncate blocks that were not used by write. We have to truncate the
+ * pagecache as well so that corresponding buffers get properly unmapped.
+ */
+static void ext4_truncate_failed_write(struct inode *inode)
+{
+ truncate_inode_pages(inode->i_mapping, inode->i_size);
+ ext4_truncate(inode);
+}
+
static int ext4_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
@@ -1599,7 +1642,7 @@ retry:
ext4_journal_stop(handle);
if (pos + len > inode->i_size) {
- ext4_truncate(inode);
+ ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might
* still be on the orphan list; we need to
@@ -1709,7 +1752,7 @@ static int ext4_ordered_write_end(struct file *file,
ret = ret2;
if (pos + len > inode->i_size) {
- ext4_truncate(inode);
+ ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
@@ -1751,7 +1794,7 @@ static int ext4_writeback_write_end(struct file *file,
ret = ret2;
if (pos + len > inode->i_size) {
- ext4_truncate(inode);
+ ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
@@ -1793,7 +1836,7 @@ static int ext4_journalled_write_end(struct file *file,
new_i_size = pos + copied;
if (new_i_size > inode->i_size)
i_size_write(inode, pos+copied);
- EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
+ ext4_set_inode_state(inode, EXT4_STATE_JDATA);
if (new_i_size > EXT4_I(inode)->i_disksize) {
ext4_update_i_disksize(inode, new_i_size);
ret2 = ext4_mark_inode_dirty(handle, inode);
@@ -1814,7 +1857,7 @@ static int ext4_journalled_write_end(struct file *file,
if (!ret)
ret = ret2;
if (pos + len > inode->i_size) {
- ext4_truncate(inode);
+ ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
@@ -1827,11 +1870,15 @@ static int ext4_journalled_write_end(struct file *file,
return ret ? ret : copied;
}
-static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
+/*
+ * Reserve a single block located at lblock
+ */
+static int ext4_da_reserve_space(struct inode *inode, sector_t lblock)
{
int retries = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- unsigned long md_needed, mdblocks, total = 0;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ unsigned long md_needed, md_reserved;
/*
* recalculate the amount of metadata blocks to reserve
@@ -1839,86 +1886,78 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
* worse case is one extent per block
*/
repeat:
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- total = EXT4_I(inode)->i_reserved_data_blocks + nrblocks;
- mdblocks = ext4_calc_metadata_amount(inode, total);
- BUG_ON(mdblocks < EXT4_I(inode)->i_reserved_meta_blocks);
-
- md_needed = mdblocks - EXT4_I(inode)->i_reserved_meta_blocks;
- total = md_needed + nrblocks;
+ spin_lock(&ei->i_block_reservation_lock);
+ md_reserved = ei->i_reserved_meta_blocks;
+ md_needed = ext4_calc_metadata_amount(inode, lblock);
+ spin_unlock(&ei->i_block_reservation_lock);
/*
* Make quota reservation here to prevent quota overflow
* later. Real quota accounting is done at pages writeout
* time.
*/
- if (vfs_dq_reserve_block(inode, total)) {
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+ if (vfs_dq_reserve_block(inode, md_needed + 1))
return -EDQUOT;
- }
- if (ext4_claim_free_blocks(sbi, total)) {
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- vfs_dq_release_reservation_block(inode, total);
+ if (ext4_claim_free_blocks(sbi, md_needed + 1)) {
+ vfs_dq_release_reservation_block(inode, md_needed + 1);
if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
yield();
goto repeat;
}
return -ENOSPC;
}
- EXT4_I(inode)->i_reserved_data_blocks += nrblocks;
- EXT4_I(inode)->i_reserved_meta_blocks = mdblocks;
+ spin_lock(&ei->i_block_reservation_lock);
+ ei->i_reserved_data_blocks++;
+ ei->i_reserved_meta_blocks += md_needed;
+ spin_unlock(&ei->i_block_reservation_lock);
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
return 0; /* success */
}
static void ext4_da_release_space(struct inode *inode, int to_free)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- int total, mdb, mdb_free, release;
+ struct ext4_inode_info *ei = EXT4_I(inode);
if (!to_free)
return; /* Nothing to release, exit */
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- if (!EXT4_I(inode)->i_reserved_data_blocks) {
+ if (unlikely(to_free > ei->i_reserved_data_blocks)) {
/*
- * if there is no reserved blocks, but we try to free some
- * then the counter is messed up somewhere.
- * but since this function is called from invalidate
- * page, it's harmless to return without any action
+ * if there aren't enough reserved blocks, then the
+ * counter is messed up somewhere. Since this
+ * function is called from invalidate page, it's
+ * harmless to return without any action.
*/
- printk(KERN_INFO "ext4 delalloc try to release %d reserved "
- "blocks for inode %lu, but there is no reserved "
- "data blocks\n", to_free, inode->i_ino);
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- return;
+ ext4_msg(inode->i_sb, KERN_NOTICE, "ext4_da_release_space: "
+ "ino %lu, to_free %d with only %d reserved "
+ "data blocks\n", inode->i_ino, to_free,
+ ei->i_reserved_data_blocks);
+ WARN_ON(1);
+ to_free = ei->i_reserved_data_blocks;
}
+ ei->i_reserved_data_blocks -= to_free;
- /* recalculate the number of metablocks still need to be reserved */
- total = EXT4_I(inode)->i_reserved_data_blocks - to_free;
- mdb = ext4_calc_metadata_amount(inode, total);
-
- /* figure out how many metablocks to release */
- BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
- mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
-
- release = to_free + mdb_free;
-
- /* update fs dirty blocks counter for truncate case */
- percpu_counter_sub(&sbi->s_dirtyblocks_counter, release);
+ if (ei->i_reserved_data_blocks == 0) {
+ /*
+ * We can release all of the reserved metadata blocks
+ * only when we have written all of the delayed
+ * allocation blocks.
+ */
+ to_free += ei->i_reserved_meta_blocks;
+ ei->i_reserved_meta_blocks = 0;
+ ei->i_da_metadata_calc_len = 0;
+ }
- /* update per-inode reservations */
- BUG_ON(to_free > EXT4_I(inode)->i_reserved_data_blocks);
- EXT4_I(inode)->i_reserved_data_blocks -= to_free;
+ /* update fs dirty blocks counter */
+ percpu_counter_sub(&sbi->s_dirtyblocks_counter, to_free);
- BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
- EXT4_I(inode)->i_reserved_meta_blocks = mdb;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- vfs_dq_release_reservation_block(inode, release);
+ vfs_dq_release_reservation_block(inode, to_free);
}
static void ext4_da_page_release_reservation(struct page *page,
@@ -2223,10 +2262,10 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd)
* variables are updated after the blocks have been allocated.
*/
new.b_state = 0;
- get_blocks_flags = (EXT4_GET_BLOCKS_CREATE |
- EXT4_GET_BLOCKS_DELALLOC_RESERVE);
+ get_blocks_flags = EXT4_GET_BLOCKS_CREATE;
if (mpd->b_state & (1 << BH_Delay))
- get_blocks_flags |= EXT4_GET_BLOCKS_UPDATE_RESERVE_SPACE;
+ get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
+
blks = ext4_get_blocks(handle, mpd->inode, next, max_blocks,
&new, get_blocks_flags);
if (blks < 0) {
@@ -2255,7 +2294,7 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd)
ext4_msg(mpd->inode->i_sb, KERN_CRIT,
"delayed block allocation failed for inode %lu at "
"logical offset %llu with max blocks %zd with "
- "error %d\n", mpd->inode->i_ino,
+ "error %d", mpd->inode->i_ino,
(unsigned long long) next,
mpd->b_size >> mpd->inode->i_blkbits, err);
printk(KERN_CRIT "This should not happen!! "
@@ -2322,8 +2361,17 @@ static void mpage_add_bh_to_extent(struct mpage_da_data *mpd,
sector_t next;
int nrblocks = mpd->b_size >> mpd->inode->i_blkbits;
+ /*
+ * XXX Don't go larger than mballoc is willing to allocate
+ * This is a stopgap solution. We eventually need to fold
+ * mpage_da_submit_io() into this function and then call
+ * ext4_get_blocks() multiple times in a loop
+ */
+ if (nrblocks >= 8*1024*1024/mpd->inode->i_sb->s_blocksize)
+ goto flush_it;
+
/* check if thereserved journal credits might overflow */
- if (!(EXT4_I(mpd->inode)->i_flags & EXT4_EXTENTS_FL)) {
+ if (!(ext4_test_inode_flag(mpd->inode, EXT4_INODE_EXTENTS))) {
if (nrblocks >= EXT4_MAX_TRANS_DATA) {
/*
* With non-extent format we are limited by the journal
@@ -2524,7 +2572,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
* XXX: __block_prepare_write() unmaps passed block,
* is it OK?
*/
- ret = ext4_da_reserve_space(inode, 1);
+ ret = ext4_da_reserve_space(inode, iblock);
if (ret)
/* not enough space to reserve */
return ret;
@@ -2635,7 +2683,7 @@ static int __ext4_journalled_writepage(struct page *page,
ret = err;
walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one);
- EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
+ ext4_set_inode_state(inode, EXT4_STATE_JDATA);
out:
return ret;
}
@@ -2788,7 +2836,7 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode)
* number of contiguous block. So we will limit
* number of contiguous block to a sane value
*/
- if (!(inode->i_flags & EXT4_EXTENTS_FL) &&
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) &&
(max_blocks > EXT4_MAX_TRANS_DATA))
max_blocks = EXT4_MAX_TRANS_DATA;
@@ -2908,7 +2956,7 @@ retry:
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
- "%ld pages, ino %lu; err %d\n", __func__,
+ "%ld pages, ino %lu; err %d", __func__,
wbc->nr_to_write, inode->i_ino, ret);
goto out_writepages;
}
@@ -2983,7 +3031,7 @@ retry:
if (pages_skipped != wbc->pages_skipped)
ext4_msg(inode->i_sb, KERN_CRIT,
"This should not happen leaving %s "
- "with nr_to_write = %ld ret = %d\n",
+ "with nr_to_write = %ld ret = %d",
__func__, wbc->nr_to_write, ret);
/* Update index */
@@ -2999,8 +3047,7 @@ retry:
out_writepages:
if (!no_nrwrite_index_update)
wbc->no_nrwrite_index_update = 0;
- if (wbc->nr_to_write > nr_to_writebump)
- wbc->nr_to_write -= nr_to_writebump;
+ wbc->nr_to_write -= nr_to_writebump;
wbc->range_start = range_start;
trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
return ret;
@@ -3025,11 +3072,18 @@ static int ext4_nonda_switch(struct super_block *sb)
if (2 * free_blocks < 3 * dirty_blocks ||
free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
/*
- * free block count is less that 150% of dirty blocks
- * or free blocks is less that watermark
+ * free block count is less than 150% of dirty blocks
+ * or free blocks is less than watermark
*/
return 1;
}
+ /*
+ * Even if we don't switch but are nearing capacity,
+ * start pushing delalloc when 1/2 of free blocks are dirty.
+ */
+ if (free_blocks < 2 * dirty_blocks)
+ writeback_inodes_sb_if_idle(sb);
+
return 0;
}
@@ -3037,7 +3091,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
- int ret, retries = 0;
+ int ret, retries = 0, quota_retries = 0;
struct page *page;
pgoff_t index;
unsigned from, to;
@@ -3091,11 +3145,27 @@ retry:
* i_size_read because we hold i_mutex.
*/
if (pos + len > inode->i_size)
- ext4_truncate(inode);
+ ext4_truncate_failed_write(inode);
}
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
+
+ if ((ret == -EDQUOT) &&
+ EXT4_I(inode)->i_reserved_meta_blocks &&
+ (quota_retries++ < 3)) {
+ /*
+ * Since we often over-estimate the number of meta
+ * data blocks required, we may sometimes get a
+ * spurios out of quota error even though there would
+ * be enough space once we write the data blocks and
+ * find out how many meta data blocks were _really_
+ * required. So try forcing the inode write to see if
+ * that helps.
+ */
+ write_inode_now(inode, (quota_retries == 3));
+ goto retry;
+ }
out:
return ret;
}
@@ -3284,7 +3354,8 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
filemap_write_and_wait(mapping);
}
- if (EXT4_JOURNAL(inode) && EXT4_I(inode)->i_state & EXT4_STATE_JDATA) {
+ if (EXT4_JOURNAL(inode) &&
+ ext4_test_inode_state(inode, EXT4_STATE_JDATA)) {
/*
* This is a REALLY heavyweight approach, but the use of
* bmap on dirty files is expected to be extremely rare:
@@ -3303,7 +3374,7 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
* everything they get.
*/
- EXT4_I(inode)->i_state &= ~EXT4_STATE_JDATA;
+ ext4_clear_inode_state(inode, EXT4_STATE_JDATA);
journal = EXT4_JOURNAL(inode);
jbd2_journal_lock_updates(journal);
err = jbd2_journal_flush(journal);
@@ -3419,6 +3490,9 @@ retry:
* but cannot extend i_size. Bail out and pretend
* the write failed... */
ret = PTR_ERR(handle);
+ if (inode->i_nlink)
+ ext4_orphan_del(NULL, inode);
+
goto out;
}
if (inode->i_nlink)
@@ -3534,7 +3608,7 @@ static int ext4_end_aio_dio_nolock(ext4_io_end_t *io)
{
struct inode *inode = io->inode;
loff_t offset = io->offset;
- size_t size = io->size;
+ ssize_t size = io->size;
int ret = 0;
ext4_debug("end_aio_dio_onlock: io 0x%p from inode %lu,list->next 0x%p,"
@@ -3771,8 +3845,8 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) {
ext4_free_io_end(iocb->private);
iocb->private = NULL;
- } else if (ret > 0 && (EXT4_I(inode)->i_state &
- EXT4_STATE_DIO_UNWRITTEN)) {
+ } else if (ret > 0 && ext4_test_inode_state(inode,
+ EXT4_STATE_DIO_UNWRITTEN)) {
int err;
/*
* for non AIO case, since the IO is already
@@ -3782,7 +3856,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
offset, ret);
if (err < 0)
ret = err;
- EXT4_I(inode)->i_state &= ~EXT4_STATE_DIO_UNWRITTEN;
+ ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
}
return ret;
}
@@ -3798,7 +3872,7 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
- if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
return ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
@@ -4120,6 +4194,8 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
__le32 *last)
{
__le32 *p;
+ int is_metadata = S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode);
+
if (try_to_extend_transaction(handle, inode)) {
if (bh) {
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
@@ -4150,11 +4226,11 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
*p = 0;
tbh = sb_find_get_block(inode->i_sb, nr);
- ext4_forget(handle, 0, inode, tbh, nr);
+ ext4_forget(handle, is_metadata, inode, tbh, nr);
}
}
- ext4_free_blocks(handle, inode, block_to_free, count, 0);
+ ext4_free_blocks(handle, inode, block_to_free, count, is_metadata);
}
/**
@@ -4427,10 +4503,12 @@ void ext4_truncate(struct inode *inode)
if (!ext4_can_truncate(inode))
return;
+ ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
+
if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
- ei->i_state |= EXT4_STATE_DA_ALLOC_CLOSE;
+ ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
- if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
ext4_ext_truncate(inode);
return;
}
@@ -4714,7 +4792,7 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
{
/* We have all inode data except xattrs in memory here. */
return __ext4_get_inode_loc(inode, iloc,
- !(EXT4_I(inode)->i_state & EXT4_STATE_XATTR));
+ !ext4_test_inode_state(inode, EXT4_STATE_XATTR));
}
void ext4_set_inode_flags(struct inode *inode)
@@ -4737,20 +4815,26 @@ void ext4_set_inode_flags(struct inode *inode)
/* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
void ext4_get_inode_flags(struct ext4_inode_info *ei)
{
- unsigned int flags = ei->vfs_inode.i_flags;
-
- ei->i_flags &= ~(EXT4_SYNC_FL|EXT4_APPEND_FL|
- EXT4_IMMUTABLE_FL|EXT4_NOATIME_FL|EXT4_DIRSYNC_FL);
- if (flags & S_SYNC)
- ei->i_flags |= EXT4_SYNC_FL;
- if (flags & S_APPEND)
- ei->i_flags |= EXT4_APPEND_FL;
- if (flags & S_IMMUTABLE)
- ei->i_flags |= EXT4_IMMUTABLE_FL;
- if (flags & S_NOATIME)
- ei->i_flags |= EXT4_NOATIME_FL;
- if (flags & S_DIRSYNC)
- ei->i_flags |= EXT4_DIRSYNC_FL;
+ unsigned int vfs_fl;
+ unsigned long old_fl, new_fl;
+
+ do {
+ vfs_fl = ei->vfs_inode.i_flags;
+ old_fl = ei->i_flags;
+ new_fl = old_fl & ~(EXT4_SYNC_FL|EXT4_APPEND_FL|
+ EXT4_IMMUTABLE_FL|EXT4_NOATIME_FL|
+ EXT4_DIRSYNC_FL);
+ if (vfs_fl & S_SYNC)
+ new_fl |= EXT4_SYNC_FL;
+ if (vfs_fl & S_APPEND)
+ new_fl |= EXT4_APPEND_FL;
+ if (vfs_fl & S_IMMUTABLE)
+ new_fl |= EXT4_IMMUTABLE_FL;
+ if (vfs_fl & S_NOATIME)
+ new_fl |= EXT4_NOATIME_FL;
+ if (vfs_fl & S_DIRSYNC)
+ new_fl |= EXT4_DIRSYNC_FL;
+ } while (cmpxchg(&ei->i_flags, old_fl, new_fl) != old_fl);
}
static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode,
@@ -4781,8 +4865,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
struct ext4_iloc iloc;
struct ext4_inode *raw_inode;
struct ext4_inode_info *ei;
- struct buffer_head *bh;
struct inode *inode;
+ journal_t *journal = EXT4_SB(sb)->s_journal;
long ret;
int block;
@@ -4793,11 +4877,11 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
return inode;
ei = EXT4_I(inode);
+ iloc.bh = 0;
ret = __ext4_get_inode_loc(inode, &iloc, 0);
if (ret < 0)
goto bad_inode;
- bh = iloc.bh;
raw_inode = ext4_raw_inode(&iloc);
inode->i_mode = le16_to_cpu(raw_inode->i_mode);
inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
@@ -4808,7 +4892,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
}
inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
- ei->i_state = 0;
+ ei->i_state_flags = 0;
ei->i_dir_start_lookup = 0;
ei->i_dtime = le32_to_cpu(raw_inode->i_dtime);
/* We now have enough fields to check if the inode was active or not.
@@ -4820,7 +4904,6 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
if (inode->i_mode == 0 ||
!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) {
/* this inode is deleted */
- brelse(bh);
ret = -ESTALE;
goto bad_inode;
}
@@ -4837,6 +4920,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32;
inode->i_size = ext4_isize(raw_inode);
ei->i_disksize = inode->i_size;
+#ifdef CONFIG_QUOTA
+ ei->i_reserved_quota = 0;
+#endif
inode->i_generation = le32_to_cpu(raw_inode->i_generation);
ei->i_block_group = iloc.block_group;
ei->i_last_alloc_group = ~0;
@@ -4848,11 +4934,35 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
ei->i_data[block] = raw_inode->i_block[block];
INIT_LIST_HEAD(&ei->i_orphan);
+ /*
+ * Set transaction id's of transactions that have to be committed
+ * to finish f[data]sync. We set them to currently running transaction
+ * as we cannot be sure that the inode or some of its metadata isn't
+ * part of the transaction - the inode could have been reclaimed and
+ * now it is reread from disk.
+ */
+ if (journal) {
+ transaction_t *transaction;
+ tid_t tid;
+
+ spin_lock(&journal->j_state_lock);
+ if (journal->j_running_transaction)
+ transaction = journal->j_running_transaction;
+ else
+ transaction = journal->j_committing_transaction;
+ if (transaction)
+ tid = transaction->t_tid;
+ else
+ tid = journal->j_commit_sequence;
+ spin_unlock(&journal->j_state_lock);
+ ei->i_sync_tid = tid;
+ ei->i_datasync_tid = tid;
+ }
+
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
EXT4_INODE_SIZE(inode->i_sb)) {
- brelse(bh);
ret = -EIO;
goto bad_inode;
}
@@ -4865,7 +4975,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
EXT4_GOOD_OLD_INODE_SIZE +
ei->i_extra_isize;
if (*magic == cpu_to_le32(EXT4_XATTR_MAGIC))
- ei->i_state |= EXT4_STATE_XATTR;
+ ext4_set_inode_state(inode, EXT4_STATE_XATTR);
}
} else
ei->i_extra_isize = 0;
@@ -4884,10 +4994,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
ret = 0;
if (ei->i_file_acl &&
- ((ei->i_file_acl <
- (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) +
- EXT4_SB(sb)->s_gdb_count)) ||
- (ei->i_file_acl >= ext4_blocks_count(EXT4_SB(sb)->s_es)))) {
+ !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) {
ext4_error(sb, __func__,
"bad extended attribute block %llu in inode #%lu",
ei->i_file_acl, inode->i_ino);
@@ -4905,10 +5012,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
/* Validate block references which are part of inode */
ret = ext4_check_inode_blockref(inode);
}
- if (ret) {
- brelse(bh);
+ if (ret)
goto bad_inode;
- }
if (S_ISREG(inode->i_mode)) {
inode->i_op = &ext4_file_inode_operations;
@@ -4936,7 +5041,6 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
init_special_inode(inode, inode->i_mode,
new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
} else {
- brelse(bh);
ret = -EIO;
ext4_error(inode->i_sb, __func__,
"bogus i_mode (%o) for inode=%lu",
@@ -4949,6 +5053,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
return inode;
bad_inode:
+ brelse(iloc.bh);
iget_failed(inode);
return ERR_PTR(ret);
}
@@ -4968,7 +5073,7 @@ static int ext4_inode_blocks_set(handle_t *handle,
*/
raw_inode->i_blocks_lo = cpu_to_le32(i_blocks);
raw_inode->i_blocks_high = 0;
- ei->i_flags &= ~EXT4_HUGE_FILE_FL;
+ ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE);
return 0;
}
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE))
@@ -4981,9 +5086,9 @@ static int ext4_inode_blocks_set(handle_t *handle,
*/
raw_inode->i_blocks_lo = cpu_to_le32(i_blocks);
raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
- ei->i_flags &= ~EXT4_HUGE_FILE_FL;
+ ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE);
} else {
- ei->i_flags |= EXT4_HUGE_FILE_FL;
+ ext4_set_inode_flag(inode, EXT4_INODE_HUGE_FILE);
/* i_block is stored in file system block size */
i_blocks = i_blocks >> (inode->i_blkbits - 9);
raw_inode->i_blocks_lo = cpu_to_le32(i_blocks);
@@ -5010,7 +5115,7 @@ static int ext4_do_update_inode(handle_t *handle,
/* For fields not not tracking in the in-memory inode,
* initialise them to zero for new inodes. */
- if (ei->i_state & EXT4_STATE_NEW)
+ if (ext4_test_inode_state(inode, EXT4_STATE_NEW))
memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
ext4_get_inode_flags(ei);
@@ -5074,7 +5179,7 @@ static int ext4_do_update_inode(handle_t *handle,
EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
sb->s_dirt = 1;
ext4_handle_sync(handle);
- err = ext4_handle_dirty_metadata(handle, inode,
+ err = ext4_handle_dirty_metadata(handle, NULL,
EXT4_SB(sb)->s_sbh);
}
}
@@ -5103,11 +5208,12 @@ static int ext4_do_update_inode(handle_t *handle,
}
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
- rc = ext4_handle_dirty_metadata(handle, inode, bh);
+ rc = ext4_handle_dirty_metadata(handle, NULL, bh);
if (!err)
err = rc;
- ei->i_state &= ~EXT4_STATE_NEW;
+ ext4_clear_inode_state(inode, EXT4_STATE_NEW);
+ ext4_update_inode_fsync_trans(handle, inode, 0);
out_brelse:
brelse(bh);
ext4_std_error(inode->i_sb, err);
@@ -5170,7 +5276,7 @@ int ext4_write_inode(struct inode *inode, int wait)
} else {
struct ext4_iloc iloc;
- err = ext4_get_inode_loc(inode, &iloc);
+ err = __ext4_get_inode_loc(inode, &iloc, 0);
if (err)
return err;
if (wait)
@@ -5183,6 +5289,7 @@ int ext4_write_inode(struct inode *inode, int wait)
(unsigned long long)iloc.bh->b_blocknr);
err = -EIO;
}
+ brelse(iloc.bh);
}
return err;
}
@@ -5227,8 +5334,8 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
/* (user+group)*(old+new) structure, inode write (sb,
* inode block, ? - but truncate inode update has it) */
- handle = ext4_journal_start(inode, 2*(EXT4_QUOTA_INIT_BLOCKS(inode->i_sb)+
- EXT4_QUOTA_DEL_BLOCKS(inode->i_sb))+3);
+ handle = ext4_journal_start(inode, (EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)+
+ EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb))+3);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto err_out;
@@ -5249,7 +5356,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
}
if (attr->ia_valid & ATTR_SIZE) {
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) {
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
if (attr->ia_size > sbi->s_bitmap_maxbytes) {
@@ -5260,7 +5367,9 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
}
if (S_ISREG(inode->i_mode) &&
- attr->ia_valid & ATTR_SIZE && attr->ia_size < inode->i_size) {
+ attr->ia_valid & ATTR_SIZE &&
+ (attr->ia_size < inode->i_size ||
+ (ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)))) {
handle_t *handle;
handle = ext4_journal_start(inode, 3);
@@ -5291,6 +5400,9 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
goto err_out;
}
}
+ /* ext4_truncate will clear the flag */
+ if ((ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)))
+ ext4_truncate(inode);
}
rc = inode_setattr(inode, attr);
@@ -5365,7 +5477,7 @@ static int ext4_indirect_trans_blocks(struct inode *inode, int nrblocks,
static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
{
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return ext4_indirect_trans_blocks(inode, nrblocks, chunk);
return ext4_ext_index_trans_blocks(inode, nrblocks, chunk);
}
@@ -5529,8 +5641,8 @@ static int ext4_expand_extra_isize(struct inode *inode,
entry = IFIRST(header);
/* No extended attributes present */
- if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR) ||
- header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
+ if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
+ header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0,
new_extra_isize);
EXT4_I(inode)->i_extra_isize = new_extra_isize;
@@ -5574,7 +5686,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (ext4_handle_valid(handle) &&
EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
- !(EXT4_I(inode)->i_state & EXT4_STATE_NO_EXPAND)) {
+ !ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) {
/*
* We need extra buffer credits since we may write into EA block
* with this same handle. If journal_extend fails, then it will
@@ -5588,7 +5700,8 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
sbi->s_want_extra_isize,
iloc, handle);
if (ret) {
- EXT4_I(inode)->i_state |= EXT4_STATE_NO_EXPAND;
+ ext4_set_inode_state(inode,
+ EXT4_STATE_NO_EXPAND);
if (mnt_count !=
le16_to_cpu(sbi->s_es->s_mnt_count)) {
ext4_warning(inode->i_sb, __func__,
@@ -5655,7 +5768,7 @@ static int ext4_pin_inode(handle_t *handle, struct inode *inode)
err = jbd2_journal_get_write_access(handle, iloc.bh);
if (!err)
err = ext4_handle_dirty_metadata(handle,
- inode,
+ NULL,
iloc.bh);
brelse(iloc.bh);
}
@@ -5699,9 +5812,9 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
*/
if (val)
- EXT4_I(inode)->i_flags |= EXT4_JOURNAL_DATA_FL;
+ ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
else
- EXT4_I(inode)->i_flags &= ~EXT4_JOURNAL_DATA_FL;
+ ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
ext4_set_aops(inode);
jbd2_journal_unlock_updates(journal);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index c1cdf613e725..bf5ae883b1bd 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -92,6 +92,15 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
flags &= ~EXT4_EXTENTS_FL;
}
+ if (flags & EXT4_EOFBLOCKS_FL) {
+ /* we don't support adding EOFBLOCKS flag */
+ if (!(oldflags & EXT4_EOFBLOCKS_FL)) {
+ err = -EOPNOTSUPP;
+ goto flags_out;
+ }
+ } else if (oldflags & EXT4_EOFBLOCKS_FL)
+ ext4_truncate(inode);
+
handle = ext4_journal_start(inode, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
@@ -221,31 +230,39 @@ setversion_out:
struct file *donor_filp;
int err;
+ if (!(filp->f_mode & FMODE_READ) ||
+ !(filp->f_mode & FMODE_WRITE))
+ return -EBADF;
+
if (copy_from_user(&me,
(struct move_extent __user *)arg, sizeof(me)))
return -EFAULT;
+ me.moved_len = 0;
donor_filp = fget(me.donor_fd);
if (!donor_filp)
return -EBADF;
- if (!capable(CAP_DAC_OVERRIDE)) {
- if ((current->real_cred->fsuid != inode->i_uid) ||
- !(inode->i_mode & S_IRUSR) ||
- !(donor_filp->f_dentry->d_inode->i_mode &
- S_IRUSR)) {
- fput(donor_filp);
- return -EACCES;
- }
+ if (!(donor_filp->f_mode & FMODE_WRITE)) {
+ err = -EBADF;
+ goto mext_out;
}
+ err = mnt_want_write(filp->f_path.mnt);
+ if (err)
+ goto mext_out;
+
err = ext4_move_extents(filp, donor_filp, me.orig_start,
me.donor_start, me.len, &me.moved_len);
- fput(donor_filp);
-
- if (copy_to_user((struct move_extent *)arg, &me, sizeof(me)))
- return -EFAULT;
+ mnt_drop_write(filp->f_path.mnt);
+ if (me.moved_len > 0)
+ file_remove_suid(donor_filp);
+ if (copy_to_user((struct move_extent __user *)arg,
+ &me, sizeof(me)))
+ err = -EFAULT;
+mext_out:
+ fput(donor_filp);
return err;
}
@@ -356,7 +373,30 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case EXT4_IOC32_SETRSVSZ:
cmd = EXT4_IOC_SETRSVSZ;
break;
- case EXT4_IOC_GROUP_ADD:
+ case EXT4_IOC32_GROUP_ADD: {
+ struct compat_ext4_new_group_input __user *uinput;
+ struct ext4_new_group_input input;
+ mm_segment_t old_fs;
+ int err;
+
+ uinput = compat_ptr(arg);
+ err = get_user(input.group, &uinput->group);
+ err |= get_user(input.block_bitmap, &uinput->block_bitmap);
+ err |= get_user(input.inode_bitmap, &uinput->inode_bitmap);
+ err |= get_user(input.inode_table, &uinput->inode_table);
+ err |= get_user(input.blocks_count, &uinput->blocks_count);
+ err |= get_user(input.reserved_blocks,
+ &uinput->reserved_blocks);
+ if (err)
+ return -EFAULT;
+ old_fs = get_fs();
+ set_fs(KERNEL_DS);
+ err = ext4_ioctl(file, EXT4_IOC_GROUP_ADD,
+ (unsigned long) &input);
+ set_fs(old_fs);
+ return err;
+ }
+ case EXT4_IOC_MOVE_EXT:
break;
default:
return -ENOIOCTLCMD;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index bba12824defa..04e07e227278 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -658,6 +658,27 @@ static void ext4_mb_mark_free_simple(struct super_block *sb,
}
}
+/*
+ * Cache the order of the largest free extent we have available in this block
+ * group.
+ */
+static void
+mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp)
+{
+ int i;
+ int bits;
+
+ grp->bb_largest_free_order = -1; /* uninit */
+
+ bits = sb->s_blocksize_bits + 1;
+ for (i = bits; i >= 0; i--) {
+ if (grp->bb_counters[i] > 0) {
+ grp->bb_largest_free_order = i;
+ break;
+ }
+ }
+}
+
static noinline_for_stack
void ext4_mb_generate_buddy(struct super_block *sb,
void *buddy, void *bitmap, ext4_group_t group)
@@ -700,6 +721,7 @@ void ext4_mb_generate_buddy(struct super_block *sb,
*/
grp->bb_free = free;
}
+ mb_set_largest_free_order(sb, grp);
clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
@@ -725,6 +747,9 @@ void ext4_mb_generate_buddy(struct super_block *sb,
* contain blocks_per_page (PAGE_CACHE_SIZE / blocksize) blocks.
* So it can have information regarding groups_per_page which
* is blocks_per_page/2
+ *
+ * Locking note: This routine takes the block group lock of all groups
+ * for this page; do not hold this lock when calling this routine!
*/
static int ext4_mb_init_cache(struct page *page, char *incore)
@@ -910,6 +935,11 @@ out:
return err;
}
+/*
+ * Locking note: This routine calls ext4_mb_init_cache(), which takes the
+ * block group lock of all groups for this page; do not hold the BG lock when
+ * calling this routine!
+ */
static noinline_for_stack
int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
{
@@ -1004,6 +1034,11 @@ err:
return ret;
}
+/*
+ * Locking note: This routine calls ext4_mb_init_cache(), which takes the
+ * block group lock of all groups for this page; do not hold the BG lock when
+ * calling this routine!
+ */
static noinline_for_stack int
ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
struct ext4_buddy *e4b)
@@ -1150,7 +1185,7 @@ err:
return ret;
}
-static void ext4_mb_release_desc(struct ext4_buddy *e4b)
+static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
{
if (e4b->bd_bitmap_page)
page_cache_release(e4b->bd_bitmap_page);
@@ -1300,6 +1335,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
buddy = buddy2;
} while (1);
}
+ mb_set_largest_free_order(sb, e4b->bd_info);
mb_check_buddy(e4b);
}
@@ -1428,6 +1464,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
e4b->bd_info->bb_counters[ord]++;
e4b->bd_info->bb_counters[ord]++;
}
+ mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info);
mb_set_bits(EXT4_MB_BITMAP(e4b), ex->fe_start, len0);
mb_check_buddy(e4b);
@@ -1618,7 +1655,7 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac,
}
ext4_unlock_group(ac->ac_sb, group);
- ext4_mb_release_desc(e4b);
+ ext4_mb_unload_buddy(e4b);
return 0;
}
@@ -1674,7 +1711,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
ext4_mb_use_best_found(ac, e4b);
}
ext4_unlock_group(ac->ac_sb, group);
- ext4_mb_release_desc(e4b);
+ ext4_mb_unload_buddy(e4b);
return 0;
}
@@ -1823,16 +1860,22 @@ void ext4_mb_scan_aligned(struct ext4_allocation_context *ac,
}
}
+/* This is now called BEFORE we load the buddy bitmap. */
static int ext4_mb_good_group(struct ext4_allocation_context *ac,
ext4_group_t group, int cr)
{
unsigned free, fragments;
- unsigned i, bits;
int flex_size = ext4_flex_bg_size(EXT4_SB(ac->ac_sb));
struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group);
BUG_ON(cr < 0 || cr >= 4);
- BUG_ON(EXT4_MB_GRP_NEED_INIT(grp));
+
+ /* We only do this if the grp has never been initialized */
+ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
+ int ret = ext4_mb_init_group(ac->ac_sb, group);
+ if (ret)
+ return 0;
+ }
free = grp->bb_free;
fragments = grp->bb_fragments;
@@ -1845,17 +1888,16 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac,
case 0:
BUG_ON(ac->ac_2order == 0);
+ if (grp->bb_largest_free_order < ac->ac_2order)
+ return 0;
+
/* Avoid using the first bg of a flexgroup for data files */
if ((ac->ac_flags & EXT4_MB_HINT_DATA) &&
(flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) &&
((group % flex_size) == 0))
return 0;
- bits = ac->ac_sb->s_blocksize_bits + 1;
- for (i = ac->ac_2order; i <= bits; i++)
- if (grp->bb_counters[i] > 0)
- return 1;
- break;
+ return 1;
case 1:
if ((free / fragments) >= ac->ac_g_ex.fe_len)
return 1;
@@ -1966,7 +2008,7 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
sbi = EXT4_SB(sb);
ngroups = ext4_get_groups_count(sb);
/* non-extent files are limited to low blocks/groups */
- if (!(EXT4_I(ac->ac_inode)->i_flags & EXT4_EXTENTS_FL))
+ if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)))
ngroups = sbi->s_blockfile_groups;
BUG_ON(ac->ac_status == AC_STATUS_FOUND);
@@ -2026,15 +2068,11 @@ repeat:
group = ac->ac_g_ex.fe_group;
for (i = 0; i < ngroups; group++, i++) {
- struct ext4_group_info *grp;
- struct ext4_group_desc *desc;
-
if (group == ngroups)
group = 0;
- /* quick check to skip empty groups */
- grp = ext4_get_group_info(sb, group);
- if (grp->bb_free == 0)
+ /* This now checks without needing the buddy page */
+ if (!ext4_mb_good_group(ac, group, cr))
continue;
err = ext4_mb_load_buddy(sb, group, &e4b);
@@ -2042,15 +2080,18 @@ repeat:
goto out;
ext4_lock_group(sb, group);
+
+ /*
+ * We need to check again after locking the
+ * block group
+ */
if (!ext4_mb_good_group(ac, group, cr)) {
- /* someone did allocation from this group */
ext4_unlock_group(sb, group);
- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);
continue;
}
ac->ac_groups_scanned++;
- desc = ext4_get_group_desc(sb, group, NULL);
if (cr == 0)
ext4_mb_simple_scan_group(ac, &e4b);
else if (cr == 1 &&
@@ -2060,7 +2101,7 @@ repeat:
ext4_mb_complex_scan_group(ac, &e4b);
ext4_unlock_group(sb, group);
- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);
if (ac->ac_status != AC_STATUS_CONTINUE)
break;
@@ -2150,7 +2191,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
ext4_lock_group(sb, group);
memcpy(&sg, ext4_get_group_info(sb, group), i);
ext4_unlock_group(sb, group);
- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);
seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free,
sg.info.bb_fragments, sg.info.bb_first_free);
@@ -2257,6 +2298,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list);
init_rwsem(&meta_group_info[i]->alloc_sem);
meta_group_info[i]->bb_free_root.rb_node = NULL;
+ meta_group_info[i]->bb_largest_free_order = -1; /* uninit */
#ifdef DOUBLE_CHECK
{
@@ -2529,7 +2571,6 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
struct ext4_group_info *db;
int err, count = 0, count2 = 0;
struct ext4_free_data *entry;
- ext4_fsblk_t discard_block;
struct list_head *l, *ltmp;
list_for_each_safe(l, ltmp, &txn->t_private_list) {
@@ -2538,6 +2579,23 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
mb_debug(1, "gonna free %u blocks in group %u (0x%p):",
entry->count, entry->group, entry);
+ if (test_opt(sb, DISCARD)) {
+ int ret;
+ ext4_fsblk_t discard_block;
+
+ discard_block = entry->start_blk +
+ ext4_group_first_block_no(sb, entry->group);
+ trace_ext4_discard_blocks(sb,
+ (unsigned long long)discard_block,
+ entry->count);
+ ret = sb_issue_discard(sb, discard_block, entry->count);
+ if (ret == EOPNOTSUPP) {
+ ext4_warning(sb, __func__,
+ "discard not supported, disabling");
+ clear_opt(EXT4_SB(sb)->s_mount_opt, DISCARD);
+ }
+ }
+
err = ext4_mb_load_buddy(sb, entry->group, &e4b);
/* we expect to find existing buddy because it's pinned */
BUG_ON(err != 0);
@@ -2559,15 +2617,8 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
page_cache_release(e4b.bd_bitmap_page);
}
ext4_unlock_group(sb, entry->group);
- discard_block = (ext4_fsblk_t) entry->group * EXT4_BLOCKS_PER_GROUP(sb)
- + entry->start_blk
- + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
- trace_ext4_discard_blocks(sb, (unsigned long long)discard_block,
- entry->count);
- sb_issue_discard(sb, discard_block, entry->count);
-
kmem_cache_free(ext4_free_ext_cachep, entry);
- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);
}
mb_debug(1, "freed %u blocks in %u structures\n", count, count2);
@@ -2750,12 +2801,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED))
/* release all the reserved blocks if non delalloc */
percpu_counter_sub(&sbi->s_dirtyblocks_counter, reserv_blks);
- else {
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
- ac->ac_b_ex.fe_len);
- /* convert reserved quota blocks to real quota blocks */
- vfs_dq_claim_block(ac->ac_inode, ac->ac_b_ex.fe_len);
- }
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi,
@@ -3006,6 +3051,24 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac)
}
/*
+ * Called on failure; free up any blocks from the inode PA for this
+ * context. We don't need this for MB_GROUP_PA because we only change
+ * pa_free in ext4_mb_release_context(), but on failure, we've already
+ * zeroed out ac->ac_b_ex.fe_len, so group_pa->pa_free is not changed.
+ */
+static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac)
+{
+ struct ext4_prealloc_space *pa = ac->ac_pa;
+ int len;
+
+ if (pa && pa->pa_type == MB_INODE_PA) {
+ len = ac->ac_b_ex.fe_len;
+ pa->pa_free += len;
+ }
+
+}
+
+/*
* use blocks preallocated to inode
*/
static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac,
@@ -3113,7 +3176,7 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
continue;
/* non-extent files can't have physical blocks past 2^32 */
- if (!(EXT4_I(ac->ac_inode)->i_flags & EXT4_EXTENTS_FL) &&
+ if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) &&
pa->pa_pstart + pa->pa_len > EXT4_MAX_BLOCK_FILE_PHYS)
continue;
@@ -3692,7 +3755,7 @@ out:
ext4_unlock_group(sb, group);
if (ac)
kmem_cache_free(ext4_ac_cachep, ac);
- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);
put_bh(bitmap_bh);
return free;
}
@@ -3796,7 +3859,7 @@ repeat:
if (bitmap_bh == NULL) {
ext4_error(sb, __func__, "Error in reading block "
"bitmap for %u", group);
- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);
continue;
}
@@ -3805,7 +3868,7 @@ repeat:
ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa, ac);
ext4_unlock_group(sb, group);
- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);
put_bh(bitmap_bh);
list_del(&pa->u.pa_tmp_list);
@@ -3921,7 +3984,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
/* don't use group allocation for large files */
size = max(size, isize);
- if (size >= sbi->s_mb_stream_request) {
+ if (size > sbi->s_mb_stream_request) {
ac->ac_flags |= EXT4_MB_STREAM_ALLOC;
return;
}
@@ -4069,7 +4132,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb,
ext4_mb_release_group_pa(&e4b, pa, ac);
ext4_unlock_group(sb, group);
- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);
list_del(&pa->u.pa_tmp_list);
call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback);
}
@@ -4290,6 +4353,7 @@ repeat:
ac->ac_status = AC_STATUS_CONTINUE;
goto repeat;
} else if (*errp) {
+ ext4_discard_allocated_blocks(ac);
ac->ac_b_ex.fe_len = 0;
ar->len = 0;
ext4_mb_show_ac(ac);
@@ -4570,7 +4634,7 @@ do_more:
atomic_add(count, &sbi->s_flex_groups[flex_group].free_blocks);
}
- ext4_mb_release_desc(&e4b);
+ ext4_mb_unload_buddy(&e4b);
*freed += count;
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 0ca811061bc7..ceb9d41cd7cf 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -221,8 +221,6 @@ struct ext4_buddy {
#define EXT4_MB_BITMAP(e4b) ((e4b)->bd_bitmap)
#define EXT4_MB_BUDDY(e4b) ((e4b)->bd_buddy)
-#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
-
static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
struct ext4_free_extent *fex)
{
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index a93d5b80f3e2..7901f133f967 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -238,7 +238,7 @@ static int extend_credit_for_blkdel(handle_t *handle, struct inode *inode)
* So allocate a credit of 3. We may update
* quota (user and group).
*/
- needed = 3 + 2*EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
+ needed = 3 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb);
if (ext4_journal_extend(handle, needed) != 0)
retval = ext4_journal_restart(handle, needed);
@@ -357,12 +357,12 @@ static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
* happened after we started the migrate. We need to
* fail the migrate
*/
- if (!(EXT4_I(inode)->i_state & EXT4_STATE_EXT_MIGRATE)) {
+ if (!ext4_test_inode_state(inode, EXT4_STATE_EXT_MIGRATE)) {
retval = -EAGAIN;
up_write(&EXT4_I(inode)->i_data_sem);
goto err_out;
} else
- EXT4_I(inode)->i_state &= ~EXT4_STATE_EXT_MIGRATE;
+ ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
/*
* We have the extent map build with the tmp inode.
* Now copy the i_data across
@@ -465,7 +465,7 @@ int ext4_ext_migrate(struct inode *inode)
*/
if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_INCOMPAT_EXTENTS) ||
- (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return -EINVAL;
if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0)
@@ -477,7 +477,7 @@ int ext4_ext_migrate(struct inode *inode)
handle = ext4_journal_start(inode,
EXT4_DATA_TRANS_BLOCKS(inode->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
- 2 * EXT4_QUOTA_INIT_BLOCKS(inode->i_sb)
+ EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)
+ 1);
if (IS_ERR(handle)) {
retval = PTR_ERR(handle);
@@ -494,14 +494,10 @@ int ext4_ext_migrate(struct inode *inode)
}
i_size_write(tmp_inode, i_size_read(inode));
/*
- * We don't want the inode to be reclaimed
- * if we got interrupted in between. We have
- * this tmp inode carrying reference to the
- * data blocks of the original file. We set
- * the i_nlink to zero at the last stage after
- * switching the original file to extent format
+ * Set the i_nlink to zero so it will be deleted later
+ * when we drop inode reference.
*/
- tmp_inode->i_nlink = 1;
+ tmp_inode->i_nlink = 0;
ext4_ext_tree_init(handle, tmp_inode);
ext4_orphan_add(handle, tmp_inode);
@@ -524,10 +520,20 @@ int ext4_ext_migrate(struct inode *inode)
* allocation.
*/
down_read((&EXT4_I(inode)->i_data_sem));
- EXT4_I(inode)->i_state |= EXT4_STATE_EXT_MIGRATE;
+ ext4_set_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
up_read((&EXT4_I(inode)->i_data_sem));
handle = ext4_journal_start(inode, 1);
+ if (IS_ERR(handle)) {
+ /*
+ * It is impossible to update on-disk structures without
+ * a handle, so just rollback in-core changes and live other
+ * work to orphan_list_cleanup()
+ */
+ ext4_orphan_del(NULL, tmp_inode);
+ retval = PTR_ERR(handle);
+ goto out;
+ }
ei = EXT4_I(inode);
i_data = ei->i_data;
@@ -609,15 +615,8 @@ err_out:
/* Reset the extent details */
ext4_ext_tree_init(handle, tmp_inode);
-
- /*
- * Set the i_nlink to zero so that
- * generic_drop_inode really deletes the
- * inode
- */
- tmp_inode->i_nlink = 0;
-
ext4_journal_stop(handle);
+out:
unlock_new_inode(tmp_inode);
iput(tmp_inode);
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 25b6b1457360..a73ed781752d 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -77,12 +77,14 @@ static int
mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
struct ext4_extent **extent)
{
+ struct ext4_extent_header *eh;
int ppos, leaf_ppos = path->p_depth;
ppos = leaf_ppos;
if (EXT_LAST_EXTENT(path[ppos].p_hdr) > path[ppos].p_ext) {
/* leaf block */
*extent = ++path[ppos].p_ext;
+ path[ppos].p_block = ext_pblock(path[ppos].p_ext);
return 0;
}
@@ -119,9 +121,18 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
ext_block_hdr(path[cur_ppos+1].p_bh);
}
+ path[leaf_ppos].p_ext = *extent = NULL;
+
+ eh = path[leaf_ppos].p_hdr;
+ if (le16_to_cpu(eh->eh_entries) == 0)
+ /* empty leaf is found */
+ return -ENODATA;
+
/* leaf block */
path[leaf_ppos].p_ext = *extent =
EXT_FIRST_EXTENT(path[leaf_ppos].p_hdr);
+ path[leaf_ppos].p_block =
+ ext_pblock(path[leaf_ppos].p_ext);
return 0;
}
}
@@ -155,40 +166,15 @@ mext_check_null_inode(struct inode *inode1, struct inode *inode2,
}
/**
- * mext_double_down_read - Acquire two inodes' read semaphore
+ * double_down_write_data_sem - Acquire two inodes' write lock of i_data_sem
*
* @orig_inode: original inode structure
* @donor_inode: donor inode structure
- * Acquire read semaphore of the two inodes (orig and donor) by i_ino order.
+ * Acquire write lock of i_data_sem of the two inodes (orig and donor) by
+ * i_ino order.
*/
static void
-mext_double_down_read(struct inode *orig_inode, struct inode *donor_inode)
-{
- struct inode *first = orig_inode, *second = donor_inode;
-
- /*
- * Use the inode number to provide the stable locking order instead
- * of its address, because the C language doesn't guarantee you can
- * compare pointers that don't come from the same array.
- */
- if (donor_inode->i_ino < orig_inode->i_ino) {
- first = donor_inode;
- second = orig_inode;
- }
-
- down_read(&EXT4_I(first)->i_data_sem);
- down_read(&EXT4_I(second)->i_data_sem);
-}
-
-/**
- * mext_double_down_write - Acquire two inodes' write semaphore
- *
- * @orig_inode: original inode structure
- * @donor_inode: donor inode structure
- * Acquire write semaphore of the two inodes (orig and donor) by i_ino order.
- */
-static void
-mext_double_down_write(struct inode *orig_inode, struct inode *donor_inode)
+double_down_write_data_sem(struct inode *orig_inode, struct inode *donor_inode)
{
struct inode *first = orig_inode, *second = donor_inode;
@@ -203,32 +189,18 @@ mext_double_down_write(struct inode *orig_inode, struct inode *donor_inode)
}
down_write(&EXT4_I(first)->i_data_sem);
- down_write(&EXT4_I(second)->i_data_sem);
-}
-
-/**
- * mext_double_up_read - Release two inodes' read semaphore
- *
- * @orig_inode: original inode structure to be released its lock first
- * @donor_inode: donor inode structure to be released its lock second
- * Release read semaphore of two inodes (orig and donor).
- */
-static void
-mext_double_up_read(struct inode *orig_inode, struct inode *donor_inode)
-{
- up_read(&EXT4_I(orig_inode)->i_data_sem);
- up_read(&EXT4_I(donor_inode)->i_data_sem);
+ down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING);
}
/**
- * mext_double_up_write - Release two inodes' write semaphore
+ * double_up_write_data_sem - Release two inodes' write lock of i_data_sem
*
* @orig_inode: original inode structure to be released its lock first
* @donor_inode: donor inode structure to be released its lock second
- * Release write semaphore of two inodes (orig and donor).
+ * Release write lock of i_data_sem of two inodes (orig and donor).
*/
static void
-mext_double_up_write(struct inode *orig_inode, struct inode *donor_inode)
+double_up_write_data_sem(struct inode *orig_inode, struct inode *donor_inode)
{
up_write(&EXT4_I(orig_inode)->i_data_sem);
up_write(&EXT4_I(donor_inode)->i_data_sem);
@@ -280,6 +252,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
}
o_start->ee_len = start_ext->ee_len;
+ eblock = le32_to_cpu(start_ext->ee_block);
new_flag = 1;
} else if (start_ext->ee_len && new_ext->ee_len &&
@@ -290,6 +263,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
* orig |------------------------------|
*/
o_start->ee_len = start_ext->ee_len;
+ eblock = le32_to_cpu(start_ext->ee_block);
new_flag = 1;
} else if (!start_ext->ee_len && new_ext->ee_len &&
@@ -503,7 +477,6 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
struct ext4_extent *oext, *o_start, *o_end, *prev_ext;
struct ext4_extent new_ext, start_ext, end_ext;
ext4_lblk_t new_ext_end;
- ext4_fsblk_t new_phys_end;
int oext_alen, new_ext_alen, end_ext_alen;
int depth = ext_depth(orig_inode);
int ret;
@@ -517,7 +490,6 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
new_ext.ee_len = dext->ee_len;
new_ext_alen = ext4_ext_get_actual_len(&new_ext);
new_ext_end = le32_to_cpu(new_ext.ee_block) + new_ext_alen - 1;
- new_phys_end = ext_pblock(&new_ext) + new_ext_alen - 1;
/*
* Case: original extent is first
@@ -530,6 +502,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
le32_to_cpu(oext->ee_block) + oext_alen) {
start_ext.ee_len = cpu_to_le16(le32_to_cpu(new_ext.ee_block) -
le32_to_cpu(oext->ee_block));
+ start_ext.ee_block = oext->ee_block;
copy_extent_status(oext, &start_ext);
} else if (oext > EXT_FIRST_EXTENT(orig_path[depth].p_hdr)) {
prev_ext = oext - 1;
@@ -543,6 +516,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
start_ext.ee_len = cpu_to_le16(
ext4_ext_get_actual_len(prev_ext) +
new_ext_alen);
+ start_ext.ee_block = oext->ee_block;
copy_extent_status(prev_ext, &start_ext);
new_ext.ee_len = 0;
}
@@ -661,6 +635,7 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext,
* @donor_inode: donor inode
* @from: block offset of orig_inode
* @count: block count to be replaced
+ * @err: pointer to save return value
*
* Replace original inode extents and donor inode extents page by page.
* We implement this replacement in the following three steps:
@@ -671,33 +646,33 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext,
* 3. Change the block information of donor inode to point at the saved
* original inode blocks in the dummy extents.
*
- * Return 0 on success, or a negative error value on failure.
+ * Return replaced block count.
*/
static int
mext_replace_branches(handle_t *handle, struct inode *orig_inode,
struct inode *donor_inode, ext4_lblk_t from,
- ext4_lblk_t count)
+ ext4_lblk_t count, int *err)
{
struct ext4_ext_path *orig_path = NULL;
struct ext4_ext_path *donor_path = NULL;
struct ext4_extent *oext, *dext;
struct ext4_extent tmp_dext, tmp_oext;
ext4_lblk_t orig_off = from, donor_off = from;
- int err = 0;
int depth;
int replaced_count = 0;
int dext_alen;
- mext_double_down_write(orig_inode, donor_inode);
+ /* Protect extent trees against block allocations via delalloc */
+ double_down_write_data_sem(orig_inode, donor_inode);
/* Get the original extent for the block "orig_off" */
- err = get_ext_path(orig_inode, orig_off, &orig_path);
- if (err)
+ *err = get_ext_path(orig_inode, orig_off, &orig_path);
+ if (*err)
goto out;
/* Get the donor extent for the head */
- err = get_ext_path(donor_inode, donor_off, &donor_path);
- if (err)
+ *err = get_ext_path(donor_inode, donor_off, &donor_path);
+ if (*err)
goto out;
depth = ext_depth(orig_inode);
oext = orig_path[depth].p_ext;
@@ -707,9 +682,9 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode,
dext = donor_path[depth].p_ext;
tmp_dext = *dext;
- err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
+ *err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
donor_off, count);
- if (err)
+ if (*err)
goto out;
/* Loop for the donor extents */
@@ -718,7 +693,7 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode,
if (!dext) {
ext4_error(donor_inode->i_sb, __func__,
"The extent for donor must be found");
- err = -EIO;
+ *err = -EIO;
goto out;
} else if (donor_off != le32_to_cpu(tmp_dext.ee_block)) {
ext4_error(donor_inode->i_sb, __func__,
@@ -726,20 +701,20 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode,
"extent(%u) should be equal",
donor_off,
le32_to_cpu(tmp_dext.ee_block));
- err = -EIO;
+ *err = -EIO;
goto out;
}
/* Set donor extent to orig extent */
- err = mext_leaf_block(handle, orig_inode,
+ *err = mext_leaf_block(handle, orig_inode,
orig_path, &tmp_dext, &orig_off);
- if (err < 0)
+ if (*err)
goto out;
/* Set orig extent to donor extent */
- err = mext_leaf_block(handle, donor_inode,
+ *err = mext_leaf_block(handle, donor_inode,
donor_path, &tmp_oext, &donor_off);
- if (err < 0)
+ if (*err)
goto out;
dext_alen = ext4_ext_get_actual_len(&tmp_dext);
@@ -753,35 +728,25 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode,
if (orig_path)
ext4_ext_drop_refs(orig_path);
- err = get_ext_path(orig_inode, orig_off, &orig_path);
- if (err)
+ *err = get_ext_path(orig_inode, orig_off, &orig_path);
+ if (*err)
goto out;
depth = ext_depth(orig_inode);
oext = orig_path[depth].p_ext;
- if (le32_to_cpu(oext->ee_block) +
- ext4_ext_get_actual_len(oext) <= orig_off) {
- err = 0;
- goto out;
- }
tmp_oext = *oext;
if (donor_path)
ext4_ext_drop_refs(donor_path);
- err = get_ext_path(donor_inode, donor_off, &donor_path);
- if (err)
+ *err = get_ext_path(donor_inode, donor_off, &donor_path);
+ if (*err)
goto out;
depth = ext_depth(donor_inode);
dext = donor_path[depth].p_ext;
- if (le32_to_cpu(dext->ee_block) +
- ext4_ext_get_actual_len(dext) <= donor_off) {
- err = 0;
- goto out;
- }
tmp_dext = *dext;
- err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
+ *err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
donor_off, count - replaced_count);
- if (err)
+ if (*err)
goto out;
}
@@ -795,8 +760,12 @@ out:
kfree(donor_path);
}
- mext_double_up_write(orig_inode, donor_inode);
- return err;
+ ext4_ext_invalidate_cache(orig_inode);
+ ext4_ext_invalidate_cache(donor_inode);
+
+ double_up_write_data_sem(orig_inode, donor_inode);
+
+ return replaced_count;
}
/**
@@ -808,16 +777,17 @@ out:
* @data_offset_in_page: block index where data swapping starts
* @block_len_in_page: the number of blocks to be swapped
* @uninit: orig extent is uninitialized or not
+ * @err: pointer to save return value
*
* Save the data in original inode blocks and replace original inode extents
* with donor inode extents by calling mext_replace_branches().
- * Finally, write out the saved data in new original inode blocks. Return 0
- * on success, or a negative error value on failure.
+ * Finally, write out the saved data in new original inode blocks. Return
+ * replaced block count.
*/
static int
move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
pgoff_t orig_page_offset, int data_offset_in_page,
- int block_len_in_page, int uninit)
+ int block_len_in_page, int uninit, int *err)
{
struct inode *orig_inode = o_filp->f_dentry->d_inode;
struct address_space *mapping = orig_inode->i_mapping;
@@ -829,9 +799,11 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
long long offs = orig_page_offset << PAGE_CACHE_SHIFT;
unsigned long blocksize = orig_inode->i_sb->s_blocksize;
unsigned int w_flags = 0;
- unsigned int tmp_data_len, data_len;
+ unsigned int tmp_data_size, data_size, replaced_size;
void *fsdata;
- int ret, i, jblocks;
+ int i, jblocks;
+ int err2 = 0;
+ int replaced_count = 0;
int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
/*
@@ -841,8 +813,8 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
jblocks = ext4_writepage_trans_blocks(orig_inode) * 2;
handle = ext4_journal_start(orig_inode, jblocks);
if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- return ret;
+ *err = PTR_ERR(handle);
+ return 0;
}
if (segment_eq(get_fs(), KERNEL_DS))
@@ -858,39 +830,36 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
* Just swap data blocks between orig and donor.
*/
if (uninit) {
- ret = mext_replace_branches(handle, orig_inode,
- donor_inode, orig_blk_offset,
- block_len_in_page);
-
- /* Clear the inode cache not to refer to the old data */
- ext4_ext_invalidate_cache(orig_inode);
- ext4_ext_invalidate_cache(donor_inode);
+ replaced_count = mext_replace_branches(handle, orig_inode,
+ donor_inode, orig_blk_offset,
+ block_len_in_page, err);
goto out2;
}
offs = (long long)orig_blk_offset << orig_inode->i_blkbits;
- /* Calculate data_len */
+ /* Calculate data_size */
if ((orig_blk_offset + block_len_in_page - 1) ==
((orig_inode->i_size - 1) >> orig_inode->i_blkbits)) {
/* Replace the last block */
- tmp_data_len = orig_inode->i_size & (blocksize - 1);
+ tmp_data_size = orig_inode->i_size & (blocksize - 1);
/*
- * If data_len equal zero, it shows data_len is multiples of
+ * If data_size equal zero, it shows data_size is multiples of
* blocksize. So we set appropriate value.
*/
- if (tmp_data_len == 0)
- tmp_data_len = blocksize;
+ if (tmp_data_size == 0)
+ tmp_data_size = blocksize;
- data_len = tmp_data_len +
+ data_size = tmp_data_size +
((block_len_in_page - 1) << orig_inode->i_blkbits);
- } else {
- data_len = block_len_in_page << orig_inode->i_blkbits;
- }
+ } else
+ data_size = block_len_in_page << orig_inode->i_blkbits;
+
+ replaced_size = data_size;
- ret = a_ops->write_begin(o_filp, mapping, offs, data_len, w_flags,
+ *err = a_ops->write_begin(o_filp, mapping, offs, data_size, w_flags,
&page, &fsdata);
- if (unlikely(ret < 0))
+ if (unlikely(*err < 0))
goto out;
if (!PageUptodate(page)) {
@@ -911,14 +880,17 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
/* Release old bh and drop refs */
try_to_release_page(page, 0);
- ret = mext_replace_branches(handle, orig_inode, donor_inode,
- orig_blk_offset, block_len_in_page);
- if (ret < 0)
- goto out;
-
- /* Clear the inode cache not to refer to the old data */
- ext4_ext_invalidate_cache(orig_inode);
- ext4_ext_invalidate_cache(donor_inode);
+ replaced_count = mext_replace_branches(handle, orig_inode, donor_inode,
+ orig_blk_offset, block_len_in_page,
+ &err2);
+ if (err2) {
+ if (replaced_count) {
+ block_len_in_page = replaced_count;
+ replaced_size =
+ block_len_in_page << orig_inode->i_blkbits;
+ } else
+ goto out;
+ }
if (!page_has_buffers(page))
create_empty_buffers(page, 1 << orig_inode->i_blkbits, 0);
@@ -928,16 +900,16 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
bh = bh->b_this_page;
for (i = 0; i < block_len_in_page; i++) {
- ret = ext4_get_block(orig_inode,
+ *err = ext4_get_block(orig_inode,
(sector_t)(orig_blk_offset + i), bh, 0);
- if (ret < 0)
+ if (*err < 0)
goto out;
if (bh->b_this_page != NULL)
bh = bh->b_this_page;
}
- ret = a_ops->write_end(o_filp, mapping, offs, data_len, data_len,
+ *err = a_ops->write_end(o_filp, mapping, offs, data_size, replaced_size,
page, fsdata);
page = NULL;
@@ -951,18 +923,20 @@ out:
out2:
ext4_journal_stop(handle);
- return ret < 0 ? ret : 0;
+ if (err2)
+ *err = err2;
+
+ return replaced_count;
}
/**
- * mext_check_argumants - Check whether move extent can be done
+ * mext_check_arguments - Check whether move extent can be done
*
* @orig_inode: original inode
* @donor_inode: donor inode
* @orig_start: logical start offset in block for orig
* @donor_start: logical start offset in block for donor
* @len: the number of blocks to be moved
- * @moved_len: moved block length
*
* Check the arguments of ext4_move_extents() whether the files can be
* exchanged with each other.
@@ -970,21 +944,23 @@ out2:
*/
static int
mext_check_arguments(struct inode *orig_inode,
- struct inode *donor_inode, __u64 orig_start,
- __u64 donor_start, __u64 *len, __u64 moved_len)
+ struct inode *donor_inode, __u64 orig_start,
+ __u64 donor_start, __u64 *len)
{
ext4_lblk_t orig_blocks, donor_blocks;
unsigned int blkbits = orig_inode->i_blkbits;
unsigned int blocksize = 1 << blkbits;
- /* Regular file check */
- if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) {
- ext4_debug("ext4 move extent: The argument files should be "
- "regular file [ino:orig %lu, donor %lu]\n",
- orig_inode->i_ino, donor_inode->i_ino);
+ if (donor_inode->i_mode & (S_ISUID|S_ISGID)) {
+ ext4_debug("ext4 move extent: suid or sgid is set"
+ " to donor file [ino:orig %lu, donor %lu]\n",
+ orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
+ if (IS_IMMUTABLE(donor_inode) || IS_APPEND(donor_inode))
+ return -EPERM;
+
/* Ext4 move extent does not support swapfile */
if (IS_SWAPFILE(orig_inode) || IS_SWAPFILE(donor_inode)) {
ext4_debug("ext4 move extent: The argument files should "
@@ -1002,11 +978,11 @@ mext_check_arguments(struct inode *orig_inode,
}
/* Ext4 move extent supports only extent based file */
- if (!(EXT4_I(orig_inode)->i_flags & EXT4_EXTENTS_FL)) {
+ if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) {
ext4_debug("ext4 move extent: orig file is not extents "
"based file [ino:orig %lu]\n", orig_inode->i_ino);
return -EOPNOTSUPP;
- } else if (!(EXT4_I(donor_inode)->i_flags & EXT4_EXTENTS_FL)) {
+ } else if (!(ext4_test_inode_flag(donor_inode, EXT4_INODE_EXTENTS))) {
ext4_debug("ext4 move extent: donor file is not extents "
"based file [ino:donor %lu]\n", donor_inode->i_ino);
return -EOPNOTSUPP;
@@ -1025,13 +1001,6 @@ mext_check_arguments(struct inode *orig_inode,
return -EINVAL;
}
- if (moved_len) {
- ext4_debug("ext4 move extent: moved_len should be 0 "
- "[ino:orig %lu, donor %lu]\n", orig_inode->i_ino,
- donor_inode->i_ino);
- return -EINVAL;
- }
-
if ((orig_start > EXT_MAX_BLOCK) ||
(donor_start > EXT_MAX_BLOCK) ||
(*len > EXT_MAX_BLOCK) ||
@@ -1232,16 +1201,24 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
return -EINVAL;
}
- /* protect orig and donor against a truncate */
+ /* Regular file check */
+ if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) {
+ ext4_debug("ext4 move extent: The argument files should be "
+ "regular file [ino:orig %lu, donor %lu]\n",
+ orig_inode->i_ino, donor_inode->i_ino);
+ return -EINVAL;
+ }
+
+ /* Protect orig and donor inodes against a truncate */
ret1 = mext_inode_double_lock(orig_inode, donor_inode);
if (ret1 < 0)
return ret1;
- mext_double_down_read(orig_inode, donor_inode);
+ /* Protect extent tree against block allocations via delalloc */
+ double_down_write_data_sem(orig_inode, donor_inode);
/* Check the filesystem environment whether move_extent can be done */
ret1 = mext_check_arguments(orig_inode, donor_inode, orig_start,
- donor_start, &len, *moved_len);
- mext_double_up_read(orig_inode, donor_inode);
+ donor_start, &len);
if (ret1)
goto out;
@@ -1355,36 +1332,39 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
seq_start = le32_to_cpu(ext_cur->ee_block);
rest_blocks = seq_blocks;
- /* Discard preallocations of two inodes */
- down_write(&EXT4_I(orig_inode)->i_data_sem);
- ext4_discard_preallocations(orig_inode);
- up_write(&EXT4_I(orig_inode)->i_data_sem);
-
- down_write(&EXT4_I(donor_inode)->i_data_sem);
- ext4_discard_preallocations(donor_inode);
- up_write(&EXT4_I(donor_inode)->i_data_sem);
+ /*
+ * Up semaphore to avoid following problems:
+ * a. transaction deadlock among ext4_journal_start,
+ * ->write_begin via pagefault, and jbd2_journal_commit
+ * b. racing with ->readpage, ->write_begin, and ext4_get_block
+ * in move_extent_per_page
+ */
+ double_up_write_data_sem(orig_inode, donor_inode);
while (orig_page_offset <= seq_end_page) {
/* Swap original branches with new branches */
- ret1 = move_extent_per_page(o_filp, donor_inode,
+ block_len_in_page = move_extent_per_page(
+ o_filp, donor_inode,
orig_page_offset,
data_offset_in_page,
- block_len_in_page, uninit);
- if (ret1 < 0)
- goto out;
- orig_page_offset++;
+ block_len_in_page, uninit,
+ &ret1);
+
/* Count how many blocks we have exchanged */
*moved_len += block_len_in_page;
+ if (ret1 < 0)
+ break;
if (*moved_len > len) {
ext4_error(orig_inode->i_sb, __func__,
"We replaced blocks too much! "
"sum of replaced: %llu requested: %llu",
*moved_len, len);
ret1 = -EIO;
- goto out;
+ break;
}
+ orig_page_offset++;
data_offset_in_page = 0;
rest_blocks -= block_len_in_page;
if (rest_blocks > blocks_per_page)
@@ -1393,6 +1373,10 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
block_len_in_page = rest_blocks;
}
+ double_down_write_data_sem(orig_inode, donor_inode);
+ if (ret1 < 0)
+ break;
+
/* Decrease buffer counter */
if (holecheck_path)
ext4_ext_drop_refs(holecheck_path);
@@ -1414,6 +1398,11 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
}
out:
+ if (*moved_len) {
+ ext4_discard_preallocations(orig_inode);
+ ext4_discard_preallocations(donor_inode);
+ }
+
if (orig_path) {
ext4_ext_drop_refs(orig_path);
kfree(orig_path);
@@ -1422,7 +1411,7 @@ out:
ext4_ext_drop_refs(holecheck_path);
kfree(holecheck_path);
}
-
+ double_up_write_data_sem(orig_inode, donor_inode);
ret2 = mext_inode_double_unlock(orig_inode, donor_inode);
if (ret1)
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 6d2c1b897fc7..c3b6ad0fcc46 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -660,7 +660,7 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
dxtrace(printk(KERN_DEBUG "In htree_fill_tree, start hash: %x:%x\n",
start_hash, start_minor_hash));
dir = dir_file->f_path.dentry->d_inode;
- if (!(EXT4_I(dir)->i_flags & EXT4_INDEX_FL)) {
+ if (!(ext4_test_inode_flag(dir, EXT4_INODE_INDEX))) {
hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
if (hinfo.hash_version <= DX_HASH_TEA)
hinfo.hash_version +=
@@ -805,7 +805,7 @@ static void ext4_update_dx_flag(struct inode *inode)
{
if (!EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_COMPAT_DIR_INDEX))
- EXT4_I(inode)->i_flags &= ~EXT4_INDEX_FL;
+ ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
}
/*
@@ -1292,9 +1292,6 @@ errout:
* add_dirent_to_buf will attempt search the directory block for
* space. It will return -ENOSPC if no space is available, and -EIO
* and -EEXIST if directory entry already exists.
- *
- * NOTE! bh is NOT released in the case where ENOSPC is returned. In
- * all other cases bh is released.
*/
static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
struct inode *inode, struct ext4_dir_entry_2 *de,
@@ -1315,14 +1312,10 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
top = bh->b_data + blocksize - reclen;
while ((char *) de <= top) {
if (!ext4_check_dir_entry("ext4_add_entry", dir, de,
- bh, offset)) {
- brelse(bh);
+ bh, offset))
return -EIO;
- }
- if (ext4_match(namelen, name, de)) {
- brelse(bh);
+ if (ext4_match(namelen, name, de))
return -EEXIST;
- }
nlen = EXT4_DIR_REC_LEN(de->name_len);
rlen = ext4_rec_len_from_disk(de->rec_len, blocksize);
if ((de->inode? rlen - nlen: rlen) >= reclen)
@@ -1337,7 +1330,6 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
err = ext4_journal_get_write_access(handle, bh);
if (err) {
ext4_std_error(dir->i_sb, err);
- brelse(bh);
return err;
}
@@ -1377,7 +1369,6 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
err = ext4_handle_dirty_metadata(handle, dir, bh);
if (err)
ext4_std_error(dir->i_sb, err);
- brelse(bh);
return 0;
}
@@ -1433,7 +1424,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
brelse(bh);
return retval;
}
- EXT4_I(dir)->i_flags |= EXT4_INDEX_FL;
+ ext4_set_inode_flag(dir, EXT4_INODE_INDEX);
data1 = bh2->b_data;
memcpy (data1, de, len);
@@ -1471,7 +1462,9 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
if (!(de))
return retval;
- return add_dirent_to_buf(handle, dentry, inode, de, bh);
+ retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
+ brelse(bh);
+ return retval;
}
/*
@@ -1504,7 +1497,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
retval = ext4_dx_add_entry(handle, dentry, inode);
if (!retval || (retval != ERR_BAD_DX_DIR))
return retval;
- EXT4_I(dir)->i_flags &= ~EXT4_INDEX_FL;
+ ext4_clear_inode_flag(dir, EXT4_INODE_INDEX);
dx_fallback++;
ext4_mark_inode_dirty(handle, dir);
}
@@ -1514,8 +1507,10 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
if(!bh)
return retval;
retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
- if (retval != -ENOSPC)
+ if (retval != -ENOSPC) {
+ brelse(bh);
return retval;
+ }
if (blocks == 1 && !dx_fallback &&
EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX))
@@ -1528,7 +1523,11 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
de = (struct ext4_dir_entry_2 *) bh->b_data;
de->inode = 0;
de->rec_len = ext4_rec_len_to_disk(blocksize, blocksize);
- return add_dirent_to_buf(handle, dentry, inode, de, bh);
+ retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
+ brelse(bh);
+ if (retval == 0)
+ ext4_set_inode_state(inode, EXT4_STATE_NEWENTRY);
+ return retval;
}
/*
@@ -1561,10 +1560,8 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
goto journal_error;
err = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
- if (err != -ENOSPC) {
- bh = NULL;
+ if (err != -ENOSPC)
goto cleanup;
- }
/* Block full, should compress but for now just split */
dxtrace(printk(KERN_DEBUG "using %u of %u node entries\n",
@@ -1657,7 +1654,6 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
if (!de)
goto cleanup;
err = add_dirent_to_buf(handle, dentry, inode, de, bh);
- bh = NULL;
goto cleanup;
journal_error:
@@ -1775,7 +1771,7 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, int mode,
retry:
handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
- 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb));
+ EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -1809,7 +1805,7 @@ static int ext4_mknod(struct inode *dir, struct dentry *dentry,
retry:
handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
- 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb));
+ EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -1846,7 +1842,7 @@ static int ext4_mkdir(struct inode *dir, struct dentry *dentry, int mode)
retry:
handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
- 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb));
+ EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -2026,11 +2022,18 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto out_unlock;
+ /*
+ * Due to previous errors inode may be already a part of on-disk
+ * orphan list. If so skip on-disk list modification.
+ */
+ if (NEXT_ORPHAN(inode) && NEXT_ORPHAN(inode) <=
+ (le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)))
+ goto mem_insert;
/* Insert this inode at the head of the on-disk orphan list... */
NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan);
EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
- err = ext4_handle_dirty_metadata(handle, inode, EXT4_SB(sb)->s_sbh);
+ err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
if (!err)
err = rc;
@@ -2043,6 +2046,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
*
* This is safe: on error we're going to ignore the orphan list
* anyway on the next recovery. */
+mem_insert:
if (!err)
list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
@@ -2102,7 +2106,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
if (err)
goto out_brelse;
sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
- err = ext4_handle_dirty_metadata(handle, inode, sbi->s_sbh);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
} else {
struct ext4_iloc iloc2;
struct inode *i_prev =
@@ -2259,7 +2263,7 @@ static int ext4_symlink(struct inode *dir,
retry:
handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 5 +
- 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb));
+ EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -2290,7 +2294,7 @@ retry:
}
} else {
/* clear the extent format for fast symlink */
- EXT4_I(inode)->i_flags &= ~EXT4_EXTENTS_FL;
+ ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
inode->i_op = &ext4_fast_symlink_inode_operations;
memcpy((char *)&EXT4_I(inode)->i_data, symname, l);
inode->i_size = l-1;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 3cfc343c41b5..433ea27e2652 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -247,7 +247,7 @@ static int setup_new_group_blocks(struct super_block *sb,
goto exit_bh;
if (IS_ERR(gdb = bclean(handle, sb, block))) {
- err = PTR_ERR(bh);
+ err = PTR_ERR(gdb);
goto exit_bh;
}
ext4_handle_dirty_metadata(handle, NULL, gdb);
@@ -930,7 +930,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
percpu_counter_add(&sbi->s_freeinodes_counter,
EXT4_INODES_PER_GROUP(sb));
- if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG) &&
+ sbi->s_log_groups_per_flex) {
ext4_group_t flex_group;
flex_group = ext4_flex_group(sbi, input->group);
atomic_add(input->free_blocks_count,
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index d4ca92aab514..f27e045df7a6 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -227,6 +227,7 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
if (sb->s_flags & MS_RDONLY)
return ERR_PTR(-EROFS);
+ vfs_check_frozen(sb, SB_FREEZE_TRANS);
/* Special case here: if the journal has aborted behind our
* backs (eg. EIO in the commit thread), then we still need to
* take the FS itself readonly cleanly. */
@@ -603,10 +604,6 @@ static void ext4_put_super(struct super_block *sb)
if (sb->s_dirt)
ext4_commit_super(sb, 1);
- ext4_release_system_zone(sb);
- ext4_mb_release(sb);
- ext4_ext_release(sb);
- ext4_xattr_put_super(sb);
if (sbi->s_journal) {
err = jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
@@ -614,6 +611,12 @@ static void ext4_put_super(struct super_block *sb)
ext4_abort(sb, __func__,
"Couldn't clean up the journal");
}
+
+ ext4_release_system_zone(sb);
+ ext4_mb_release(sb);
+ ext4_ext_release(sb);
+ ext4_xattr_put_super(sb);
+
if (!(sb->s_flags & MS_RDONLY)) {
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
es->s_state = cpu_to_le16(sbi->s_mount_state);
@@ -700,10 +703,16 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
ei->i_reserved_data_blocks = 0;
ei->i_reserved_meta_blocks = 0;
ei->i_allocated_meta_blocks = 0;
+ ei->i_da_metadata_calc_len = 0;
ei->i_delalloc_reserved_flag = 0;
spin_lock_init(&(ei->i_block_reservation_lock));
+#ifdef CONFIG_QUOTA
+ ei->i_reserved_quota = 0;
+#endif
INIT_LIST_HEAD(&ei->i_aio_dio_complete_list);
ei->cur_aio_dio = NULL;
+ ei->i_sync_tid = 0;
+ ei->i_datasync_tid = 0;
return &ei->vfs_inode;
}
@@ -868,6 +877,8 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0");
if (test_opt(sb, JOURNAL_ASYNC_COMMIT))
seq_puts(seq, ",journal_async_commit");
+ else if (test_opt(sb, JOURNAL_CHECKSUM))
+ seq_puts(seq, ",journal_checksum");
if (test_opt(sb, NOBH))
seq_puts(seq, ",nobh");
if (test_opt(sb, I_VERSION))
@@ -899,6 +910,12 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
if (test_opt(sb, NO_AUTO_DA_ALLOC))
seq_puts(seq, ",noauto_da_alloc");
+ if (test_opt(sb, DISCARD))
+ seq_puts(seq, ",discard");
+
+ if (test_opt(sb, NOLOAD))
+ seq_puts(seq, ",norecovery");
+
ext4_show_quota_options(seq, sb);
return 0;
@@ -991,7 +1008,9 @@ static const struct dquot_operations ext4_quota_operations = {
.reserve_space = dquot_reserve_space,
.claim_space = dquot_claim_space,
.release_rsv = dquot_release_reserved_space,
+#ifdef CONFIG_QUOTA
.get_reserved_space = ext4_get_reserved_space,
+#endif
.alloc_inode = dquot_alloc_inode,
.free_space = dquot_free_space,
.free_inode = dquot_free_inode,
@@ -1079,7 +1098,8 @@ enum {
Opt_usrquota, Opt_grpquota, Opt_i_version,
Opt_stripe, Opt_delalloc, Opt_nodelalloc,
Opt_block_validity, Opt_noblock_validity,
- Opt_inode_readahead_blks, Opt_journal_ioprio
+ Opt_inode_readahead_blks, Opt_journal_ioprio,
+ Opt_discard, Opt_nodiscard,
};
static const match_table_t tokens = {
@@ -1104,6 +1124,7 @@ static const match_table_t tokens = {
{Opt_acl, "acl"},
{Opt_noacl, "noacl"},
{Opt_noload, "noload"},
+ {Opt_noload, "norecovery"},
{Opt_nobh, "nobh"},
{Opt_bh, "bh"},
{Opt_commit, "commit=%u"},
@@ -1144,6 +1165,8 @@ static const match_table_t tokens = {
{Opt_auto_da_alloc, "auto_da_alloc=%u"},
{Opt_auto_da_alloc, "auto_da_alloc"},
{Opt_noauto_da_alloc, "noauto_da_alloc"},
+ {Opt_discard, "discard"},
+ {Opt_nodiscard, "nodiscard"},
{Opt_err, NULL},
};
@@ -1195,6 +1218,11 @@ static int parse_options(char *options, struct super_block *sb,
if (!*p)
continue;
+ /*
+ * Initialize args struct so we know whether arg was
+ * found; some options take optional arguments.
+ */
+ args[0].to = args[0].from = 0;
token = match_token(p, tokens, args);
switch (token) {
case Opt_bsd_df:
@@ -1480,10 +1508,11 @@ set_qf_format:
clear_opt(sbi->s_mount_opt, BARRIER);
break;
case Opt_barrier:
- if (match_int(&args[0], &option)) {
- set_opt(sbi->s_mount_opt, BARRIER);
- break;
- }
+ if (args[0].from) {
+ if (match_int(&args[0], &option))
+ return 0;
+ } else
+ option = 1; /* No argument, default to 1 */
if (option)
set_opt(sbi->s_mount_opt, BARRIER);
else
@@ -1556,15 +1585,22 @@ set_qf_format:
set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC);
break;
case Opt_auto_da_alloc:
- if (match_int(&args[0], &option)) {
- clear_opt(sbi->s_mount_opt, NO_AUTO_DA_ALLOC);
- break;
- }
+ if (args[0].from) {
+ if (match_int(&args[0], &option))
+ return 0;
+ } else
+ option = 1; /* No argument, default to 1 */
if (option)
clear_opt(sbi->s_mount_opt, NO_AUTO_DA_ALLOC);
else
set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC);
break;
+ case Opt_discard:
+ set_opt(sbi->s_mount_opt, DISCARD);
+ break;
+ case Opt_nodiscard:
+ clear_opt(sbi->s_mount_opt, DISCARD);
+ break;
default:
ext4_msg(sb, KERN_ERR,
"Unrecognized mount option \"%s\" "
@@ -1673,14 +1709,14 @@ static int ext4_fill_flex_info(struct super_block *sb)
size_t size;
int i;
- if (!sbi->s_es->s_log_groups_per_flex) {
+ sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
+ groups_per_flex = 1 << sbi->s_log_groups_per_flex;
+
+ if (groups_per_flex < 2) {
sbi->s_log_groups_per_flex = 0;
return 1;
}
- sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
- groups_per_flex = 1 << sbi->s_log_groups_per_flex;
-
/* We allocate both existing and potentially added groups */
flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) <<
@@ -2668,24 +2704,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);
- err = percpu_counter_init(&sbi->s_freeblocks_counter,
- ext4_count_free_blocks(sb));
- if (!err) {
- err = percpu_counter_init(&sbi->s_freeinodes_counter,
- ext4_count_free_inodes(sb));
- }
- if (!err) {
- err = percpu_counter_init(&sbi->s_dirs_counter,
- ext4_count_dirs(sb));
- }
- if (!err) {
- err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
- }
- if (err) {
- ext4_msg(sb, KERN_ERR, "insufficient memory");
- goto failed_mount3;
- }
-
sbi->s_stripe = ext4_get_stripe_size(sbi);
sbi->s_max_writeback_mb_bump = 128;
@@ -2805,7 +2823,20 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
no_journal:
-
+ err = percpu_counter_init(&sbi->s_freeblocks_counter,
+ ext4_count_free_blocks(sb));
+ if (!err)
+ err = percpu_counter_init(&sbi->s_freeinodes_counter,
+ ext4_count_free_inodes(sb));
+ if (!err)
+ err = percpu_counter_init(&sbi->s_dirs_counter,
+ ext4_count_dirs(sb));
+ if (!err)
+ err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+ if (err) {
+ ext4_msg(sb, KERN_ERR, "insufficient memory");
+ goto failed_mount_wq;
+ }
if (test_opt(sb, NOBH)) {
if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) {
ext4_msg(sb, KERN_WARNING, "Ignoring nobh option - "
@@ -2880,7 +2911,7 @@ no_journal:
err = ext4_setup_system_zone(sb);
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize system "
- "zone (%d)\n", err);
+ "zone (%d)", err);
goto failed_mount4;
}
@@ -2938,6 +2969,10 @@ failed_mount_wq:
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
}
+ percpu_counter_destroy(&sbi->s_freeblocks_counter);
+ percpu_counter_destroy(&sbi->s_freeinodes_counter);
+ percpu_counter_destroy(&sbi->s_dirs_counter);
+ percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
failed_mount3:
if (sbi->s_flex_groups) {
if (is_vmalloc_addr(sbi->s_flex_groups))
@@ -2945,10 +2980,6 @@ failed_mount3:
else
kfree(sbi->s_flex_groups);
}
- percpu_counter_destroy(&sbi->s_freeblocks_counter);
- percpu_counter_destroy(&sbi->s_freeinodes_counter);
- percpu_counter_destroy(&sbi->s_dirs_counter);
- percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
@@ -3365,8 +3396,10 @@ int ext4_force_commit(struct super_block *sb)
return 0;
journal = EXT4_SB(sb)->s_journal;
- if (journal)
+ if (journal) {
+ vfs_check_frozen(sb, SB_FREEZE_TRANS);
ret = ext4_journal_force_commit(journal);
+ }
return ret;
}
@@ -3415,18 +3448,16 @@ static int ext4_freeze(struct super_block *sb)
* the journal.
*/
error = jbd2_journal_flush(journal);
- if (error < 0) {
- out:
- jbd2_journal_unlock_updates(journal);
- return error;
- }
+ if (error < 0)
+ goto out;
/* Journal blocked and flushed, clear needs_recovery flag. */
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
error = ext4_commit_super(sb, 1);
- if (error)
- goto out;
- return 0;
+out:
+ /* we rely on s_frozen to stop further updates */
+ jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+ return error;
}
/*
@@ -3443,7 +3474,6 @@ static int ext4_unfreeze(struct super_block *sb)
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
ext4_commit_super(sb, 1);
unlock_super(sb);
- jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
return 0;
}
@@ -3668,13 +3698,11 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter);
- ext4_free_blocks_count_set(es, buf->f_bfree);
buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
if (buf->f_bfree < ext4_r_blocks_count(es))
buf->f_bavail = 0;
buf->f_files = le32_to_cpu(es->s_inodes_count);
buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter);
- es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
buf->f_namelen = EXT4_NAME_LEN;
fsid = le64_to_cpup((void *)es->s_uuid) ^
le64_to_cpup((void *)es->s_uuid + sizeof(u64));
@@ -3978,6 +4006,7 @@ static int __init init_ext4_fs(void)
{
int err;
+ ext4_check_flag_values();
err = init_ext4_system_zone();
if (err)
return err;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index fed5b01d7a8d..4de7d0a75c42 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -267,7 +267,7 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
void *end;
int error;
- if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR))
+ if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
return -ENODATA;
error = ext4_get_inode_loc(inode, &iloc);
if (error)
@@ -393,7 +393,7 @@ ext4_xattr_ibody_list(struct inode *inode, char *buffer, size_t buffer_size)
void *end;
int error;
- if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR))
+ if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
return 0;
error = ext4_get_inode_loc(inode, &iloc);
if (error)
@@ -816,7 +816,7 @@ inserted:
EXT4_I(inode)->i_block_group);
/* non-extent files can't have physical blocks past 2^32 */
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
block = ext4_new_meta_blocks(handle, inode,
@@ -824,7 +824,7 @@ inserted:
if (error)
goto cleanup;
- if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS);
ea_idebug(inode, "creating block %d", block);
@@ -903,7 +903,7 @@ ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
is->s.base = is->s.first = IFIRST(header);
is->s.here = is->s.first;
is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
- if (EXT4_I(inode)->i_state & EXT4_STATE_XATTR) {
+ if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
error = ext4_xattr_check_names(IFIRST(header), is->s.end);
if (error)
return error;
@@ -935,10 +935,10 @@ ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
header = IHDR(inode, ext4_raw_inode(&is->iloc));
if (!IS_LAST_ENTRY(s->first)) {
header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
- EXT4_I(inode)->i_state |= EXT4_STATE_XATTR;
+ ext4_set_inode_state(inode, EXT4_STATE_XATTR);
} else {
header->h_magic = cpu_to_le32(0);
- EXT4_I(inode)->i_state &= ~EXT4_STATE_XATTR;
+ ext4_clear_inode_state(inode, EXT4_STATE_XATTR);
}
return 0;
}
@@ -981,17 +981,21 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
if (strlen(name) > 255)
return -ERANGE;
down_write(&EXT4_I(inode)->xattr_sem);
- no_expand = EXT4_I(inode)->i_state & EXT4_STATE_NO_EXPAND;
- EXT4_I(inode)->i_state |= EXT4_STATE_NO_EXPAND;
+ no_expand = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
+ ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
error = ext4_get_inode_loc(inode, &is.iloc);
if (error)
goto cleanup;
- if (EXT4_I(inode)->i_state & EXT4_STATE_NEW) {
+ error = ext4_journal_get_write_access(handle, is.iloc.bh);
+ if (error)
+ goto cleanup;
+
+ if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) {
struct ext4_inode *raw_inode = ext4_raw_inode(&is.iloc);
memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
- EXT4_I(inode)->i_state &= ~EXT4_STATE_NEW;
+ ext4_clear_inode_state(inode, EXT4_STATE_NEW);
}
error = ext4_xattr_ibody_find(inode, &i, &is);
@@ -1013,9 +1017,6 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
if (flags & XATTR_CREATE)
goto cleanup;
}
- error = ext4_journal_get_write_access(handle, is.iloc.bh);
- if (error)
- goto cleanup;
if (!value) {
if (!is.s.not_found)
error = ext4_xattr_ibody_set(handle, inode, &i, &is);
@@ -1046,7 +1047,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
ext4_xattr_update_super_block(handle, inode->i_sb);
inode->i_ctime = ext4_current_time(inode);
if (!value)
- EXT4_I(inode)->i_state &= ~EXT4_STATE_NO_EXPAND;
+ ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
/*
* The bh is consumed by ext4_mark_iloc_dirty, even with
@@ -1061,7 +1062,7 @@ cleanup:
brelse(is.iloc.bh);
brelse(bs.bh);
if (no_expand == 0)
- EXT4_I(inode)->i_state &= ~EXT4_STATE_NO_EXPAND;
+ ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
up_write(&EXT4_I(inode)->xattr_sem);
return error;
}
@@ -1326,6 +1327,8 @@ retry:
goto cleanup;
kfree(b_entry_name);
kfree(buffer);
+ b_entry_name = NULL;
+ buffer = NULL;
brelse(is->iloc.bh);
kfree(is);
kfree(bs);
generated by cgit v1.2.3 (git 2.0.4) at 2024-09-26 11:26:37 +0000