summaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/Kconfig11
-rw-r--r--fs/ext4/acl.c74
-rw-r--r--fs/ext4/balloc.c81
-rw-r--r--fs/ext4/block_validity.c8
-rw-r--r--fs/ext4/dir.c14
-rw-r--r--fs/ext4/ext4.h148
-rw-r--r--fs/ext4/ext4_extents.h3
-rw-r--r--fs/ext4/ext4_jbd2.c86
-rw-r--r--fs/ext4/ext4_jbd2.h68
-rw-r--r--fs/ext4/extents.c394
-rw-r--r--fs/ext4/file.c13
-rw-r--r--fs/ext4/fsync.c68
-rw-r--r--fs/ext4/ialloc.c48
-rw-r--r--fs/ext4/inode.c964
-rw-r--r--fs/ext4/ioctl.c41
-rw-r--r--fs/ext4/mballoc.c178
-rw-r--r--fs/ext4/mballoc.h10
-rw-r--r--fs/ext4/migrate.c62
-rw-r--r--fs/ext4/move_extent.c312
-rw-r--r--fs/ext4/namei.c124
-rw-r--r--fs/ext4/resize.c104
-rw-r--r--fs/ext4/super.c528
-rw-r--r--fs/ext4/xattr.c112
-rw-r--r--fs/ext4/xattr_security.c20
-rw-r--r--fs/ext4/xattr_trusted.c20
-rw-r--r--fs/ext4/xattr_user.c25
26 files changed, 2092 insertions, 1424 deletions
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index 9f2d45d75b1..9ed1bb1f319 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -26,6 +26,17 @@ config EXT4_FS
If unsure, say N.
+config EXT4_USE_FOR_EXT23
+ bool "Use ext4 for ext2/ext3 file systems"
+ depends on EXT4_FS
+ depends on EXT3_FS=n || EXT2_FS=n
+ default y
+ help
+ Allow the ext4 file system driver code to be used for ext2 or
+ ext3 file system mounts. This allows users to reduce their
+ compiled kernel size by using one file system driver for
+ ext2, ext3, and ext4 file systems.
+
config EXT4_FS_XATTR
bool "Ext4 extended attributes"
depends on EXT4_FS
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 0df88b2a69b..8a2a29d35a6 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -364,12 +364,12 @@ out:
* Extended attribute handlers
*/
static size_t
-ext4_xattr_list_acl_access(struct inode *inode, char *list, size_t list_len,
- const char *name, size_t name_len)
+ext4_xattr_list_acl_access(struct dentry *dentry, char *list, size_t list_len,
+ const char *name, size_t name_len, int type)
{
const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS);
- if (!test_opt(inode->i_sb, POSIX_ACL))
+ if (!test_opt(dentry->d_sb, POSIX_ACL))
return 0;
if (list && size <= list_len)
memcpy(list, POSIX_ACL_XATTR_ACCESS, size);
@@ -377,12 +377,12 @@ ext4_xattr_list_acl_access(struct inode *inode, char *list, size_t list_len,
}
static size_t
-ext4_xattr_list_acl_default(struct inode *inode, char *list, size_t list_len,
- const char *name, size_t name_len)
+ext4_xattr_list_acl_default(struct dentry *dentry, char *list, size_t list_len,
+ const char *name, size_t name_len, int type)
{
const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT);
- if (!test_opt(inode->i_sb, POSIX_ACL))
+ if (!test_opt(dentry->d_sb, POSIX_ACL))
return 0;
if (list && size <= list_len)
memcpy(list, POSIX_ACL_XATTR_DEFAULT, size);
@@ -390,15 +390,18 @@ ext4_xattr_list_acl_default(struct inode *inode, char *list, size_t list_len,
}
static int
-ext4_xattr_get_acl(struct inode *inode, int type, void *buffer, size_t size)
+ext4_xattr_get_acl(struct dentry *dentry, const char *name, void *buffer,
+ size_t size, int type)
{
struct posix_acl *acl;
int error;
- if (!test_opt(inode->i_sb, POSIX_ACL))
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
+ if (!test_opt(dentry->d_sb, POSIX_ACL))
return -EOPNOTSUPP;
- acl = ext4_get_acl(inode, type);
+ acl = ext4_get_acl(dentry->d_inode, type);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (acl == NULL)
@@ -410,31 +413,16 @@ ext4_xattr_get_acl(struct inode *inode, int type, void *buffer, size_t size)
}
static int
-ext4_xattr_get_acl_access(struct inode *inode, const char *name,
- void *buffer, size_t size)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext4_xattr_get_acl(inode, ACL_TYPE_ACCESS, buffer, size);
-}
-
-static int
-ext4_xattr_get_acl_default(struct inode *inode, const char *name,
- void *buffer, size_t size)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext4_xattr_get_acl(inode, ACL_TYPE_DEFAULT, buffer, size);
-}
-
-static int
-ext4_xattr_set_acl(struct inode *inode, int type, const void *value,
- size_t size)
+ext4_xattr_set_acl(struct dentry *dentry, const char *name, const void *value,
+ size_t size, int flags, int type)
{
+ struct inode *inode = dentry->d_inode;
handle_t *handle;
struct posix_acl *acl;
int error, retries = 0;
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
if (!test_opt(inode->i_sb, POSIX_ACL))
return -EOPNOTSUPP;
if (!is_owner_or_cap(inode))
@@ -466,34 +454,18 @@ release_and_out:
return error;
}
-static int
-ext4_xattr_set_acl_access(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext4_xattr_set_acl(inode, ACL_TYPE_ACCESS, value, size);
-}
-
-static int
-ext4_xattr_set_acl_default(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext4_xattr_set_acl(inode, ACL_TYPE_DEFAULT, value, size);
-}
-
struct xattr_handler ext4_xattr_acl_access_handler = {
.prefix = POSIX_ACL_XATTR_ACCESS,
+ .flags = ACL_TYPE_ACCESS,
.list = ext4_xattr_list_acl_access,
- .get = ext4_xattr_get_acl_access,
- .set = ext4_xattr_set_acl_access,
+ .get = ext4_xattr_get_acl,
+ .set = ext4_xattr_set_acl,
};
struct xattr_handler ext4_xattr_acl_default_handler = {
.prefix = POSIX_ACL_XATTR_DEFAULT,
+ .flags = ACL_TYPE_DEFAULT,
.list = ext4_xattr_list_acl_default,
- .get = ext4_xattr_get_acl_default,
- .set = ext4_xattr_set_acl_default,
+ .get = ext4_xattr_get_acl,
+ .set = ext4_xattr_set_acl,
};
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 1d0418980f8..d2f37a5516c 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -97,8 +97,8 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
/* If checksum is bad mark all blocks used to prevent allocation
* essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
- ext4_error(sb, __func__,
- "Checksum bad for group %u", block_group);
+ ext4_error(sb, "Checksum bad for group %u",
+ block_group);
ext4_free_blks_set(sb, gdp, 0);
ext4_free_inodes_set(sb, gdp, 0);
ext4_itable_unused_set(sb, gdp, 0);
@@ -130,8 +130,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
* to make sure we calculate the right free blocks
*/
group_blocks = ext4_blocks_count(sbi->s_es) -
- le32_to_cpu(sbi->s_es->s_first_data_block) -
- (EXT4_BLOCKS_PER_GROUP(sb) * (ngroups - 1));
+ ext4_group_first_block_no(sb, ngroups - 1);
} else {
group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
}
@@ -189,9 +188,6 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
* when a file system is mounted (see ext4_fill_super).
*/
-
-#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
-
/**
* ext4_get_group_desc() -- load group descriptor from disk
* @sb: super block
@@ -210,10 +206,8 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (block_group >= ngroups) {
- ext4_error(sb, "ext4_get_group_desc",
- "block_group >= groups_count - "
- "block_group = %u, groups_count = %u",
- block_group, ngroups);
+ ext4_error(sb, "block_group >= groups_count - block_group = %u,"
+ " groups_count = %u", block_group, ngroups);
return NULL;
}
@@ -221,8 +215,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
if (!sbi->s_group_desc[group_desc]) {
- ext4_error(sb, "ext4_get_group_desc",
- "Group descriptor not loaded - "
+ ext4_error(sb, "Group descriptor not loaded - "
"block_group = %u, group_desc = %u, desc = %u",
block_group, group_desc, offset);
return NULL;
@@ -282,9 +275,7 @@ static int ext4_valid_block_bitmap(struct super_block *sb,
return 1;
err_out:
- ext4_error(sb, __func__,
- "Invalid block bitmap - "
- "block_group = %d, block = %llu",
+ ext4_error(sb, "Invalid block bitmap - block_group = %d, block = %llu",
block_group, bitmap_blk);
return 0;
}
@@ -311,8 +302,7 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
bitmap_blk = ext4_block_bitmap(sb, desc);
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
- ext4_error(sb, __func__,
- "Cannot read block bitmap - "
+ ext4_error(sb, "Cannot read block bitmap - "
"block_group = %u, block_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
@@ -354,8 +344,7 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
set_bitmap_uptodate(bh);
if (bh_submit_read(bh) < 0) {
put_bh(bh);
- ext4_error(sb, __func__,
- "Cannot read block bitmap - "
+ ext4_error(sb, "Cannot read block bitmap - "
"block_group = %u, block_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
@@ -419,8 +408,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
in_range(block + count - 1, ext4_inode_table(sb, desc),
sbi->s_itb_per_group)) {
- ext4_error(sb, __func__,
- "Adding blocks in system zones - "
+ ext4_error(sb, "Adding blocks in system zones - "
"Block = %llu, count = %lu",
block, count);
goto error_return;
@@ -453,8 +441,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
BUFFER_TRACE(bitmap_bh, "clear bit");
if (!ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
bit + i, bitmap_bh->b_data)) {
- ext4_error(sb, __func__,
- "bit already cleared for block %llu",
+ ext4_error(sb, "bit already cleared for block %llu",
(ext4_fsblk_t)(block + i));
BUFFER_TRACE(bitmap_bh, "bit already cleared");
} else {
@@ -499,44 +486,6 @@ error_return:
}
/**
- * ext4_free_blocks() -- Free given blocks and update quota
- * @handle: handle for this transaction
- * @inode: inode
- * @block: start physical block to free
- * @count: number of blocks to count
- * @metadata: Are these metadata blocks
- */
-void ext4_free_blocks(handle_t *handle, struct inode *inode,
- ext4_fsblk_t block, unsigned long count,
- int metadata)
-{
- struct super_block *sb;
- unsigned long dquot_freed_blocks;
-
- /* this isn't the right place to decide whether block is metadata
- * inode.c/extents.c knows better, but for safety ... */
- if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
- metadata = 1;
-
- /* We need to make sure we don't reuse
- * block released untill the transaction commit.
- * writeback mode have weak data consistency so
- * don't force data as metadata when freeing block
- * for writeback mode.
- */
- if (metadata == 0 && !ext4_should_writeback_data(inode))
- metadata = 1;
-
- sb = inode->i_sb;
-
- ext4_mb_free_blocks(handle, inode, block, count,
- metadata, &dquot_freed_blocks);
- if (dquot_freed_blocks)
- vfs_dq_free_block(inode, dquot_freed_blocks);
- return;
-}
-
-/**
* ext4_has_free_blocks()
* @sbi: in-core super block structure.
* @nblocks: number of needed blocks
@@ -761,7 +710,13 @@ 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 50784ef0756..983f0e12749 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -16,7 +16,6 @@
#include <linux/module.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
-#include <linux/version.h>
#include <linux/blkdev.h>
#include <linux/mutex.h>
#include "ext4.h"
@@ -160,7 +159,7 @@ 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)
@@ -206,14 +205,14 @@ void ext4_release_system_zone(struct super_block *sb)
entry = rb_entry(n, struct ext4_system_zone, node);
kmem_cache_free(ext4_system_zone_cachep, entry);
if (!parent)
- EXT4_SB(sb)->system_blks.rb_node = NULL;
+ EXT4_SB(sb)->system_blks = RB_ROOT;
else if (parent->rb_left == n)
parent->rb_left = NULL;
else if (parent->rb_right == n)
parent->rb_right = NULL;
n = parent;
}
- EXT4_SB(sb)->system_blks.rb_node = NULL;
+ EXT4_SB(sb)->system_blks = RB_ROOT;
}
/*
@@ -228,6 +227,7 @@ int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
struct rb_node *n = sbi->system_blks.rb_node;
if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
+ (start_blk + count < start_blk) ||
(start_blk + count > ext4_blocks_count(sbi->s_es)))
return 0;
while (n) {
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 9dc93168e26..86cb6d86a04 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -83,10 +83,12 @@ int ext4_check_dir_entry(const char *function, struct inode *dir,
error_msg = "inode out of bounds";
if (error_msg != NULL)
- ext4_error(dir->i_sb, function,
- "bad entry in directory #%lu: %s - "
- "offset=%u, inode=%u, rec_len=%d, name_len=%d",
- dir->i_ino, error_msg, offset,
+ __ext4_error(dir->i_sb, function,
+ "bad entry in directory #%lu: %s - block=%llu"
+ "offset=%u(%u), inode=%u, rec_len=%d, name_len=%d",
+ dir->i_ino, error_msg,
+ (unsigned long long) bh->b_blocknr,
+ (unsigned) (offset%bh->b_size), offset,
le32_to_cpu(de->inode),
rlen, de->name_len);
return error_msg == NULL ? 1 : 0;
@@ -150,7 +152,7 @@ static int ext4_readdir(struct file *filp,
*/
if (!bh) {
if (!dir_has_error) {
- ext4_error(sb, __func__, "directory #%lu "
+ ext4_error(sb, "directory #%lu "
"contains a hole at offset %Lu",
inode->i_ino,
(unsigned long long) filp->f_pos);
@@ -303,7 +305,7 @@ static void free_rb_tree_fname(struct rb_root *root)
kfree(old);
}
if (!parent)
- root->rb_node = NULL;
+ *root = RB_ROOT;
else if (parent->rb_left == n)
parent->rb_left = NULL;
else if (parent->rb_right == n)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 8825515eedd..bf938cf7c5f 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -53,6 +53,12 @@
#define ext4_debug(f, a...) do {} while (0)
#endif
+#define EXT4_ERROR_INODE(inode, fmt, a...) \
+ ext4_error_inode(__func__, (inode), (fmt), ## a);
+
+#define EXT4_ERROR_FILE(file, fmt, a...) \
+ ext4_error_file(__func__, (file), (fmt), ## a);
+
/* data type for block offset of block group */
typedef int ext4_grpblk_t;
@@ -133,14 +139,14 @@ struct mpage_da_data {
int pages_written;
int retval;
};
-#define DIO_AIO_UNWRITTEN 0x1
+#define EXT4_IO_UNWRITTEN 0x1
typedef struct ext4_io_end {
struct list_head list; /* per-file finished AIO list */
struct inode *inode; /* file being written to */
unsigned int flag; /* unwritten or not */
- int error; /* I/O error code */
- ext4_lblk_t offset; /* offset in the file */
- size_t size; /* size of the extent */
+ struct page *page; /* page struct for buffer write */
+ loff_t offset; /* offset in the file */
+ ssize_t size; /* size of the extent */
struct work_struct work; /* data work queue */
} ext4_io_end_t;
@@ -284,10 +290,12 @@ struct flex_groups {
#define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
#define EXT4_HUGE_FILE_FL 0x00040000 /* Set to each huge file */
#define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */
+#define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */
+#define EXT4_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */
#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */
-#define EXT4_FL_USER_VISIBLE 0x000BDFFF /* User visible flags */
-#define EXT4_FL_USER_MODIFIABLE 0x000B80FF /* User modifiable flags */
+#define EXT4_FL_USER_VISIBLE 0x004BDFFF /* User visible flags */
+#define EXT4_FL_USER_MODIFIABLE 0x004B80FF /* User modifiable flags */
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
@@ -313,17 +321,6 @@ static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
return flags & EXT4_OTHER_FLMASK;
}
-/*
- * Inode dynamic state flags
- */
-#define EXT4_STATE_JDATA 0x00000001 /* journaled data exists */
-#define EXT4_STATE_NEW 0x00000002 /* inode is newly created */
-#define EXT4_STATE_XATTR 0x00000004 /* has in-inode xattrs */
-#define EXT4_STATE_NO_EXPAND 0x00000008 /* No space for expansion */
-#define EXT4_STATE_DA_ALLOC_CLOSE 0x00000010 /* Alloc DA blks on close */
-#define EXT4_STATE_EXT_MIGRATE 0x00000020 /* Inode is migrating */
-#define EXT4_STATE_DIO_UNWRITTEN 0x00000040 /* need convert on dio done*/
-
/* Used to pass group descriptor data when online resize is done */
struct ext4_new_group_input {
__u32 group; /* Group number for this data */
@@ -361,19 +358,23 @@ 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_CREATE_EXT (EXT4_GET_BLOCKS_DIO|\
+#define EXT4_GET_BLOCKS_PRE_IO 0x0008
+#define EXT4_GET_BLOCKS_CONVERT 0x0010
+#define EXT4_GET_BLOCKS_IO_CREATE_EXT (EXT4_GET_BLOCKS_PRE_IO|\
+ EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
+ /* Convert extent to initialized after IO complete */
+#define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\
EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
- /* Convert extent to initialized after direct IO complete */
-#define EXT4_GET_BLOCKS_DIO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\
- EXT4_GET_BLOCKS_DIO_CREATE_EXT)
+
+/*
+ * Flags used by ext4_free_blocks
+ */
+#define EXT4_FREE_BLOCKS_METADATA 0x0001
+#define EXT4_FREE_BLOCKS_FORGET 0x0002
+#define EXT4_FREE_BLOCKS_VALIDATED 0x0004
/*
* ioctl commands
@@ -627,7 +628,7 @@ struct ext4_inode_info {
* near to their parent directory's inode.
*/
ext4_group_t i_block_group;
- __u32 i_state; /* Dynamic state flags for ext4 */
+ unsigned long i_state_flags; /* Dynamic state flags */
ext4_lblk_t i_dir_start_lookup;
#ifdef CONFIG_EXT4_FS_XATTR
@@ -693,16 +694,30 @@ 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;
+ /* completed IOs that might need unwritten extents handling */
+ struct list_head i_completed_io_list;
+ spinlock_t i_completed_io_lock;
/* current io_end structure for async DIO write*/
ext4_io_end_t *cur_aio_dio;
+
+ /*
+ * Transactions that contain inode's metadata needed to complete
+ * fsync and fdatasync, respectively.
+ */
+ tid_t i_sync_tid;
+ tid_t i_datasync_tid;
};
/*
@@ -744,12 +759,14 @@ struct ext4_inode_info {
#define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */
#define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */
#define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */
+#define EXT4_MOUNT_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */
#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
#define EXT4_MOUNT_I_VERSION 0x2000000 /* i_version support */
#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
@@ -997,7 +1014,7 @@ struct ext4_sb_info {
atomic_t s_lock_busy;
/* locality groups */
- struct ext4_locality_group *s_locality_groups;
+ struct ext4_locality_group __percpu *s_locality_groups;
/* for write statistics */
unsigned long s_sectors_written_start;
@@ -1033,6 +1050,34 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
(ino >= EXT4_FIRST_INO(sb) &&
ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
}
+
+/*
+ * Inode dynamic state flags
+ */
+enum {
+ EXT4_STATE_JDATA, /* journaled data exists */
+ EXT4_STATE_NEW, /* inode is newly created */
+ EXT4_STATE_XATTR, /* has in-inode xattrs */
+ EXT4_STATE_NO_EXPAND, /* No space for expansion */
+ EXT4_STATE_DA_ALLOC_CLOSE, /* Alloc DA blks on close */
+ EXT4_STATE_EXT_MIGRATE, /* Inode is migrating */
+ EXT4_STATE_DIO_UNWRITTEN, /* need convert on dio done*/
+};
+
+static inline int ext4_test_inode_state(struct inode *inode, int bit)
+{
+ return test_bit(bit, &EXT4_I(inode)->i_state_flags);
+}
+
+static inline void ext4_set_inode_state(struct inode *inode, int bit)
+{
+ set_bit(bit, &EXT4_I(inode)->i_state_flags);
+}
+
+static inline void ext4_clear_inode_state(struct inode *inode, int bit)
+{
+ clear_bit(bit, &EXT4_I(inode)->i_state_flags);
+}
#else
/* Assume that user mode programs are passing in an ext4fs superblock, not
* a kernel struct super_block. This will allow us to call the feature-test
@@ -1109,6 +1154,8 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
#define EXT4_FEATURE_INCOMPAT_64BIT 0x0080
#define EXT4_FEATURE_INCOMPAT_MMP 0x0100
#define EXT4_FEATURE_INCOMPAT_FLEX_BG 0x0200
+#define EXT4_FEATURE_INCOMPAT_EA_INODE 0x0400 /* EA in inode */
+#define EXT4_FEATURE_INCOMPAT_DIRDATA 0x1000 /* data in dirent */
#define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR
#define EXT4_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \
@@ -1324,8 +1371,6 @@ extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t goal, unsigned long *count, int *errp);
extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
extern int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
-extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
- ext4_fsblk_t block, unsigned long count, int metadata);
extern void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
ext4_fsblk_t block, unsigned long count);
extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
@@ -1384,16 +1429,15 @@ extern int ext4_mb_reserve_blocks(struct super_block *, int);
extern void ext4_discard_preallocations(struct inode *);
extern int __init init_ext4_mballoc(void);
extern void exit_ext4_mballoc(void);
-extern void ext4_mb_free_blocks(handle_t *, struct inode *,
- ext4_fsblk_t, unsigned long, int, unsigned long *);
+extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
+ struct buffer_head *bh, ext4_fsblk_t block,
+ unsigned long count, int flags);
extern int ext4_mb_add_groupinfo(struct super_block *sb,
ext4_group_t i, struct ext4_group_desc *desc);
extern int ext4_mb_get_buddy_cache_lock(struct super_block *, ext4_group_t);
extern void ext4_mb_put_buddy_cache_lock(struct super_block *,
ext4_group_t, int);
/* inode.c */
-int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
- struct buffer_head *bh, ext4_fsblk_t blocknr);
struct buffer_head *ext4_getblk(handle_t *, struct inode *,
ext4_lblk_t, int, int *);
struct buffer_head *ext4_bread(handle_t *, struct inode *,
@@ -1402,7 +1446,7 @@ int ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
extern struct inode *ext4_iget(struct super_block *, unsigned long);
-extern int ext4_write_inode(struct inode *, int);
+extern int ext4_write_inode(struct inode *, struct writeback_control *);
extern int ext4_setattr(struct dentry *, struct iattr *);
extern int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat);
@@ -1424,8 +1468,10 @@ 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 int flush_aio_dio_completed_IO(struct inode *inode);
+extern qsize_t *ext4_get_reserved_space(struct inode *inode);
+extern int flush_completed_IO(struct inode *inode);
+extern void ext4_da_update_reserve_space(struct inode *inode,
+ int used, int quota_claim);
/* ioctl.c */
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
@@ -1449,13 +1495,20 @@ extern int ext4_group_extend(struct super_block *sb,
ext4_fsblk_t n_blocks_count);
/* super.c */
-extern void ext4_error(struct super_block *, const char *, const char *, ...)
+extern void __ext4_error(struct super_block *, const char *, const char *, ...)
+ __attribute__ ((format (printf, 3, 4)));
+#define ext4_error(sb, message...) __ext4_error(sb, __func__, ## message)
+extern void ext4_error_inode(const char *, struct inode *, const char *, ...)
+ __attribute__ ((format (printf, 3, 4)));
+extern void ext4_error_file(const char *, struct file *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
extern void __ext4_std_error(struct super_block *, const char *, int);
extern void ext4_abort(struct super_block *, const char *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
-extern void ext4_warning(struct super_block *, const char *, const char *, ...)
+extern void __ext4_warning(struct super_block *, const char *,
+ const char *, ...)
__attribute__ ((format (printf, 3, 4)));
+#define ext4_warning(sb, message...) __ext4_warning(sb, __func__, ## message)
extern void ext4_msg(struct super_block *, const char *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
extern void ext4_grp_locked_error(struct super_block *, ext4_group_t,
@@ -1728,7 +1781,7 @@ extern void ext4_ext_release(struct super_block *);
extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
loff_t len);
extern int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
- loff_t len);
+ ssize_t len);
extern int ext4_get_blocks(handle_t *handle, struct inode *inode,
sector_t block, unsigned int max_blocks,
struct buffer_head *bh, int flags);
@@ -1740,6 +1793,15 @@ extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
__u64 len, __u64 *moved_len);
+/* BH_Uninit flag: blocks are allocated but uninitialized on disk */
+enum ext4_state_bits {
+ BH_Uninit /* blocks are allocated but uninitialized on disk */
+ = BH_JBDPrivateStart,
+};
+
+BUFFER_FNS(Uninit, uninit)
+TAS_BUFFER_FNS(Uninit, uninit)
+
/*
* Add new method to test wether block and inode bitmaps are properly
* initialized. With uninit_bg reading the block from disk is not enough
@@ -1757,6 +1819,8 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh)
set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
}
+#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
+
#endif /* __KERNEL__ */
#endif /* _EXT4_H */
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 2ca686454e8..bdb6ce7e2eb 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 6a9409920de..53d2764d71c 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -4,6 +4,8 @@
#include "ext4_jbd2.h"
+#include <trace/events/ext4.h>
+
int __ext4_journal_get_undo_access(const char *where, handle_t *handle,
struct buffer_head *bh)
{
@@ -32,35 +34,69 @@ int __ext4_journal_get_write_access(const char *where, handle_t *handle,
return err;
}
-int __ext4_journal_forget(const char *where, handle_t *handle,
- struct buffer_head *bh)
+/*
+ * The ext4 forget function must perform a revoke if we are freeing data
+ * which has been journaled. Metadata (eg. indirect blocks) must be
+ * revoked in all cases.
+ *
+ * "bh" may be NULL: a metadata block may have been freed from memory
+ * but there may still be a record of it in the journal, and that record
+ * still needs to be revoked.
+ *
+ * If the handle isn't valid we're not journaling, but we still need to
+ * call into ext4_journal_revoke() to put the buffer head.
+ */
+int __ext4_forget(const char *where, handle_t *handle, int is_metadata,
+ struct inode *inode, struct buffer_head *bh,
+ ext4_fsblk_t blocknr)
{
- int err = 0;
+ int err;
- if (ext4_handle_valid(handle)) {
- err = jbd2_journal_forget(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, __func__, bh,
- handle, err);
- }
- else
+ might_sleep();
+
+ trace_ext4_forget(inode, is_metadata, blocknr);
+ BUFFER_TRACE(bh, "enter");
+
+ jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
+ "data mode %x\n",
+ bh, is_metadata, inode->i_mode,
+ test_opt(inode->i_sb, DATA_FLAGS));
+
+ /* In the no journal case, we can just do a bforget and return */
+ if (!ext4_handle_valid(handle)) {
bforget(bh);
- return err;
-}
+ return 0;
+ }
-int __ext4_journal_revoke(const char *where, handle_t *handle,
- ext4_fsblk_t blocknr, struct buffer_head *bh)
-{
- int err = 0;
+ /* Never use the revoke function if we are doing full data
+ * journaling: there is no need to, and a V1 superblock won't
+ * support it. Otherwise, only skip the revoke on un-journaled
+ * data blocks. */
- if (ext4_handle_valid(handle)) {
- err = jbd2_journal_revoke(handle, blocknr, bh);
- if (err)
- ext4_journal_abort_handle(where, __func__, bh,
- handle, err);
+ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
+ (!is_metadata && !ext4_should_journal_data(inode))) {
+ if (bh) {
+ BUFFER_TRACE(bh, "call jbd2_journal_forget");
+ err = jbd2_journal_forget(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __func__, bh,
+ handle, err);
+ return err;
+ }
+ return 0;
}
- else
- bforget(bh);
+
+ /*
+ * data!=journal && (is_metadata || should_journal_data(inode))
+ */
+ BUFFER_TRACE(bh, "call jbd2_journal_revoke");
+ err = jbd2_journal_revoke(handle, blocknr, bh);
+ if (err) {
+ ext4_journal_abort_handle(where, __func__, bh, handle, err);
+ ext4_abort(inode->i_sb, __func__,
+ "error %d when attempting revoke", err);
+ }
+ BUFFER_TRACE(bh, "exit");
return err;
}
@@ -89,14 +125,14 @@ int __ext4_handle_dirty_metadata(const char *where, handle_t *handle,
ext4_journal_abort_handle(where, __func__, bh,
handle, err);
} else {
- if (inode && bh)
+ if (inode)
mark_buffer_dirty_inode(bh, inode);
else
mark_buffer_dirty(bh);
if (inode && inode_needs_sync(inode)) {
sync_dirty_buffer(bh);
if (buffer_req(bh) && !buffer_uptodate(bh)) {
- ext4_error(inode->i_sb, __func__,
+ ext4_error(inode->i_sb,
"IO error syncing inode, "
"inode=%lu, block=%llu",
inode->i_ino,
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index a2865980342..b79ad512646 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,
@@ -116,12 +120,8 @@ int ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode);
/*
- * Wrapper functions with which ext4 calls into JBD. The intent here is
- * to allow these to be turned into appropriate stubs so ext4 can control
- * ext2 filesystems, so ext2+ext4 systems only nee one fs. This work hasn't
- * been done yet.
+ * Wrapper functions with which ext4 calls into JBD.
*/
-
void ext4_journal_abort_handle(const char *caller, const char *err_fn,
struct buffer_head *bh, handle_t *handle, int err);
@@ -131,13 +131,9 @@ int __ext4_journal_get_undo_access(const char *where, handle_t *handle,
int __ext4_journal_get_write_access(const char *where, handle_t *handle,
struct buffer_head *bh);
-/* When called with an invalid handle, this will still do a put on the BH */
-int __ext4_journal_forget(const char *where, handle_t *handle,
- struct buffer_head *bh);
-
-/* When called with an invalid handle, this will still do a put on the BH */
-int __ext4_journal_revoke(const char *where, handle_t *handle,
- ext4_fsblk_t blocknr, struct buffer_head *bh);
+int __ext4_forget(const char *where, handle_t *handle, int is_metadata,
+ struct inode *inode, struct buffer_head *bh,
+ ext4_fsblk_t blocknr);
int __ext4_journal_get_create_access(const char *where,
handle_t *handle, struct buffer_head *bh);
@@ -149,12 +145,11 @@ int __ext4_handle_dirty_metadata(const char *where, handle_t *handle,
__ext4_journal_get_undo_access(__func__, (handle), (bh))
#define ext4_journal_get_write_access(handle, bh) \
__ext4_journal_get_write_access(__func__, (handle), (bh))
-#define ext4_journal_revoke(handle, blocknr, bh) \
- __ext4_journal_revoke(__func__, (handle), (blocknr), (bh))
+#define ext4_forget(handle, is_metadata, inode, bh, block_nr) \
+ __ext4_forget(__func__, (handle), (is_metadata), (inode), (bh),\
+ (block_nr))
#define ext4_journal_get_create_access(handle, bh) \
__ext4_journal_get_create_access(__func__, (handle), (bh))
-#define ext4_journal_forget(handle, bh) \
- __ext4_journal_forget(__func__, (handle), (bh))
#define ext4_handle_dirty_metadata(handle, inode, bh) \
__ext4_handle_dirty_metadata(__func__, (handle), (inode), (bh))
@@ -254,6 +249,19 @@ 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);
@@ -296,4 +304,28 @@ static inline int ext4_should_writeback_data(struct inode *inode)
return 0;
}
+/*
+ * This function controls whether or not we should try to go down the
+ * dioread_nolock code paths, which makes it safe to avoid taking
+ * i_mutex for direct I/O reads. This only works for extent-based
+ * files, and it doesn't work for nobh or if data journaling is
+ * enabled, since the dioread_nolock code uses b_private to pass
+ * information back to the I/O completion handler, and this conflicts
+ * with the jbd's use of b_private.
+ */
+static inline int ext4_should_dioread_nolock(struct inode *inode)
+{
+ if (!test_opt(inode->i_sb, DIOREAD_NOLOCK))
+ return 0;
+ if (test_opt(inode->i_sb, NOBH))
+ return 0;
+ if (!S_ISREG(inode->i_mode))
+ return 0;
+ if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+ return 0;
+ if (ext4_should_journal_data(inode))
+ return 0;
+ return 1;
+}
+
#endif /* _EXT4_JBD2_H */
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 715264b4bae..94c8ee81f5e 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -195,8 +195,7 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
if (S_ISREG(inode->i_mode))
block_group++;
}
- bg_start = (block_group * EXT4_BLOCKS_PER_GROUP(inode->i_sb)) +
- le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_first_data_block);
+ bg_start = ext4_group_first_block_no(inode->i_sb, block_group);
last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
/*
@@ -296,29 +295,44 @@ 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
@@ -425,7 +439,7 @@ static int __ext4_ext_check(const char *function, struct inode *inode,
return 0;
corrupted:
- ext4_error(inode->i_sb, function,
+ __ext4_error(inode->i_sb, function,
"bad header/extent in inode #%lu: %s - magic %x, "
"entries %u, max %u(%u), depth %u(%u)",
inode->i_ino, error_msg, le16_to_cpu(eh->eh_magic),
@@ -688,7 +702,12 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
}
eh = ext_block_hdr(bh);
ppos++;
- BUG_ON(ppos > depth);
+ if (unlikely(ppos > depth)) {
+ put_bh(bh);
+ EXT4_ERROR_INODE(inode,
+ "ppos %d > depth %d", ppos, depth);
+ goto err;
+ }
path[ppos].p_bh = bh;
path[ppos].p_hdr = eh;
i--;
@@ -734,7 +753,12 @@ int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
if (err)
return err;
- BUG_ON(logical == le32_to_cpu(curp->p_idx->ei_block));
+ if (unlikely(logical == le32_to_cpu(curp->p_idx->ei_block))) {
+ EXT4_ERROR_INODE(inode,
+ "logical %d == ei_block %d!",
+ logical, le32_to_cpu(curp->p_idx->ei_block));
+ return -EIO;
+ }
len = EXT_MAX_INDEX(curp->p_hdr) - curp->p_idx;
if (logical > le32_to_cpu(curp->p_idx->ei_block)) {
/* insert after */
@@ -764,9 +788,17 @@ int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
ext4_idx_store_pblock(ix, ptr);
le16_add_cpu(&curp->p_hdr->eh_entries, 1);
- BUG_ON(le16_to_cpu(curp->p_hdr->eh_entries)
- > le16_to_cpu(curp->p_hdr->eh_max));
- BUG_ON(ix > EXT_LAST_INDEX(curp->p_hdr));
+ if (unlikely(le16_to_cpu(curp->p_hdr->eh_entries)
+ > le16_to_cpu(curp->p_hdr->eh_max))) {
+ EXT4_ERROR_INODE(inode,
+ "logical %d == ei_block %d!",
+ logical, le32_to_cpu(curp->p_idx->ei_block));
+ return -EIO;
+ }
+ if (unlikely(ix > EXT_LAST_INDEX(curp->p_hdr))) {
+ EXT4_ERROR_INODE(inode, "ix > EXT_LAST_INDEX!");
+ return -EIO;
+ }
err = ext4_ext_dirty(handle, inode, curp);
ext4_std_error(inode->i_sb, err);
@@ -804,7 +836,10 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
/* if current leaf will be split, then we should use
* border from split point */
- BUG_ON(path[depth].p_ext > EXT_MAX_EXTENT(path[depth].p_hdr));
+ if (unlikely(path[depth].p_ext > EXT_MAX_EXTENT(path[depth].p_hdr))) {
+ EXT4_ERROR_INODE(inode, "p_ext > EXT_MAX_EXTENT!");
+ return -EIO;
+ }
if (path[depth].p_ext != EXT_MAX_EXTENT(path[depth].p_hdr)) {
border = path[depth].p_ext[1].ee_block;
ext_debug("leaf will be split."
@@ -845,7 +880,11 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
/* initialize new leaf */
newblock = ablocks[--a];
- BUG_ON(newblock == 0);
+ if (unlikely(newblock == 0)) {
+ EXT4_ERROR_INODE(inode, "newblock == 0!");
+ err = -EIO;
+ goto cleanup;
+ }
bh = sb_getblk(inode->i_sb, newblock);
if (!bh) {
err = -EIO;
@@ -865,7 +904,14 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
ex = EXT_FIRST_EXTENT(neh);
/* move remainder of path[depth] to the new leaf */
- BUG_ON(path[depth].p_hdr->eh_entries != path[depth].p_hdr->eh_max);
+ if (unlikely(path[depth].p_hdr->eh_entries !=
+ path[depth].p_hdr->eh_max)) {
+ EXT4_ERROR_INODE(inode, "eh_entries %d != eh_max %d!",
+ path[depth].p_hdr->eh_entries,
+ path[depth].p_hdr->eh_max);
+ err = -EIO;
+ goto cleanup;
+ }
/* start copy from next extent */
/* TODO: we could do it by single memmove */
m = 0;
@@ -912,7 +958,11 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
/* create intermediate indexes */
k = depth - at - 1;
- BUG_ON(k < 0);
+ if (unlikely(k < 0)) {
+ EXT4_ERROR_INODE(inode, "k %d < 0!", k);
+ err = -EIO;
+ goto cleanup;
+ }
if (k)
ext_debug("create %d intermediate indices\n", k);
/* insert new index into current index block */
@@ -949,8 +999,14 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
ext_debug("cur 0x%p, last 0x%p\n", path[i].p_idx,
EXT_MAX_INDEX(path[i].p_hdr));
- BUG_ON(EXT_MAX_INDEX(path[i].p_hdr) !=
- EXT_LAST_INDEX(path[i].p_hdr));
+ if (unlikely(EXT_MAX_INDEX(path[i].p_hdr) !=
+ EXT_LAST_INDEX(path[i].p_hdr))) {
+ EXT4_ERROR_INODE(inode,
+ "EXT_MAX_INDEX != EXT_LAST_INDEX ee_block %d!",
+ le32_to_cpu(path[i].p_ext->ee_block));
+ err = -EIO;
+ goto cleanup;
+ }
while (path[i].p_idx <= EXT_MAX_INDEX(path[i].p_hdr)) {
ext_debug("%d: move %d:%llu in new index %llu\n", i,
le32_to_cpu(path[i].p_idx->ei_block),
@@ -1007,7 +1063,8 @@ cleanup:
for (i = 0; i < depth; i++) {
if (!ablocks[i])
continue;
- ext4_free_blocks(handle, inode, ablocks[i], 1, 1);
+ ext4_free_blocks(handle, inode, 0, ablocks[i], 1,
+ EXT4_FREE_BLOCKS_METADATA);
}
}
kfree(ablocks);
@@ -1187,7 +1244,10 @@ ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path,
struct ext4_extent *ex;
int depth, ee_len;
- BUG_ON(path == NULL);
+ if (unlikely(path == NULL)) {
+ EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical);
+ return -EIO;
+ }
depth = path->p_depth;
*phys = 0;
@@ -1201,15 +1261,33 @@ ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path,
ex = path[depth].p_ext;
ee_len = ext4_ext_get_actual_len(ex);
if (*logical < le32_to_cpu(ex->ee_block)) {
- BUG_ON(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex);
+ if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) {
+ EXT4_ERROR_INODE(inode,
+ "EXT_FIRST_EXTENT != ex *logical %d ee_block %d!",
+ *logical, le32_to_cpu(ex->ee_block));
+ return -EIO;
+ }
while (--depth >= 0) {
ix = path[depth].p_idx;
- BUG_ON(ix != EXT_FIRST_INDEX(path[depth].p_hdr));
+ if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) {
+ EXT4_ERROR_INODE(inode,
+ "ix (%d) != EXT_FIRST_INDEX (%d) (depth %d)!",
+ ix != NULL ? ix->ei_block : 0,
+ EXT_FIRST_INDEX(path[depth].p_hdr) != NULL ?
+ EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block : 0,
+ depth);
+ return -EIO;
+ }
}
return 0;
}
- BUG_ON(*logical < (le32_to_cpu(ex->ee_block) + ee_len));
+ if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) {
+ EXT4_ERROR_INODE(inode,
+ "logical %d < ee_block %d + ee_len %d!",
+ *logical, le32_to_cpu(ex->ee_block), ee_len);
+ return -EIO;
+ }
*logical = le32_to_cpu(ex->ee_block) + ee_len - 1;
*phys = ext_pblock(ex) + ee_len - 1;
@@ -1235,7 +1313,10 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
int depth; /* Note, NOT eh_depth; depth from top of tree */
int ee_len;
- BUG_ON(path == NULL);
+ if (unlikely(path == NULL)) {
+ EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical);
+ return -EIO;
+ }
depth = path->p_depth;
*phys = 0;
@@ -1249,17 +1330,32 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
ex = path[depth].p_ext;
ee_len = ext4_ext_get_actual_len(ex);
if (*logical < le32_to_cpu(ex->ee_block)) {
- BUG_ON(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex);
+ if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) {
+ EXT4_ERROR_INODE(inode,
+ "first_extent(path[%d].p_hdr) != ex",
+ depth);
+ return -EIO;
+ }
while (--depth >= 0) {
ix = path[depth].p_idx;
- BUG_ON(ix != EXT_FIRST_INDEX(path[depth].p_hdr));
+ if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) {
+ EXT4_ERROR_INODE(inode,
+ "ix != EXT_FIRST_INDEX *logical %d!",
+ *logical);
+ return -EIO;
+ }
}
*logical = le32_to_cpu(ex->ee_block);
*phys = ext_pblock(ex);
return 0;
}
- BUG_ON(*logical < (le32_to_cpu(ex->ee_block) + ee_len));
+ if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) {
+ EXT4_ERROR_INODE(inode,
+ "logical %d < ee_block %d + ee_len %d!",
+ *logical, le32_to_cpu(ex->ee_block), ee_len);
+ return -EIO;
+ }
if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) {
/* next allocated block in this leaf */
@@ -1398,8 +1494,12 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
eh = path[depth].p_hdr;
ex = path[depth].p_ext;
- BUG_ON(ex == NULL);
- BUG_ON(eh == NULL);
+
+ if (unlikely(ex == NULL || eh == NULL)) {
+ EXT4_ERROR_INODE(inode,
+ "ex %p == NULL or eh %p == NULL", ex, eh);
+ return -EIO;
+ }
if (depth == 0) {
/* there is no tree at all */
@@ -1522,8 +1622,9 @@ int ext4_ext_try_to_merge(struct inode *inode,
merge_done = 1;
WARN_ON(eh->eh_entries == 0);
if (!eh->eh_entries)
- ext4_error(inode->i_sb, "ext4_ext_try_to_merge",
- "inode#%lu, eh->eh_entries = 0!", inode->i_ino);
+ ext4_error(inode->i_sb,
+ "inode#%lu, eh->eh_entries = 0!",
+ inode->i_ino);
}
return merge_done;
@@ -1596,13 +1697,19 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
ext4_lblk_t next;
unsigned uninitialized = 0;
- BUG_ON(ext4_ext_get_actual_len(newext) == 0);
+ if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
+ EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
+ return -EIO;
+ }
depth = ext_depth(inode);
ex = path[depth].p_ext;
- BUG_ON(path[depth].p_hdr == NULL);
+ if (unlikely(path[depth].p_hdr == NULL)) {
+ EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
+ return -EIO;
+ }
/* try to insert block into found extent and return */
- if (ex && (flag != EXT4_GET_BLOCKS_DIO_CREATE_EXT)
+ if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)
&& ext4_can_extents_be_merged(inode, ex, newext)) {
ext_debug("append [%d]%d block to %d:[%d]%d (from %llu)\n",
ext4_ext_is_uninitialized(newext),
@@ -1723,7 +1830,7 @@ has_space:
merge:
/* try to merge extents to the right */
- if (flag != EXT4_GET_BLOCKS_DIO_CREATE_EXT)
+ if (!(flag & EXT4_GET_BLOCKS_PRE_IO))
ext4_ext_try_to_merge(inode, path, nearex);
/* try to merge extents to the left */
@@ -1761,7 +1868,9 @@ 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;
@@ -1769,7 +1878,11 @@ int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
}
depth = ext_depth(inode);
- BUG_ON(path[depth].p_hdr == NULL);
+ if (unlikely(path[depth].p_hdr == NULL)) {
+ EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
+ err = -EIO;
+ break;
+ }
ex = path[depth].p_ext;
next = ext4_ext_next_allocated_block(path);
@@ -1820,7 +1933,11 @@ int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
cbex.ec_type = EXT4_EXT_CACHE_EXTENT;
}
- BUG_ON(cbex.ec_len == 0);
+ if (unlikely(cbex.ec_len == 0)) {
+ EXT4_ERROR_INODE(inode, "cbex.ec_len == 0");
+ err = -EIO;
+ break;
+ }
err = func(inode, path, &cbex, ex, cbdata);
ext4_ext_drop_refs(path);
@@ -1934,7 +2051,7 @@ ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
BUG_ON(cex->ec_type != EXT4_EXT_CACHE_GAP &&
cex->ec_type != EXT4_EXT_CACHE_EXTENT);
- if (block >= cex->ec_block && block < cex->ec_block + cex->ec_len) {
+ if (in_range(block, cex->ec_block, cex->ec_len)) {
ex->ee_block = cpu_to_le32(cex->ec_block);
ext4_ext_store_pblock(ex, cex->ec_start);
ex->ee_len = cpu_to_le16(cex->ec_len);
@@ -1957,14 +2074,16 @@ errout:
static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path)
{
- struct buffer_head *bh;
int err;
ext4_fsblk_t leaf;
/* free index block */
path--;
leaf = idx_pblock(path->p_idx);
- BUG_ON(path->p_hdr->eh_entries == 0);
+ if (unlikely(path->p_hdr->eh_entries == 0)) {
+ EXT4_ERROR_INODE(inode, "path->p_hdr->eh_entries == 0");
+ return -EIO;
+ }
err = ext4_ext_get_access(handle, inode, path);
if (err)
return err;
@@ -1973,9 +2092,8 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
if (err)
return err;
ext_debug("index is empty, remove it, free block %llu\n", leaf);
- bh = sb_find_get_block(inode->i_sb, leaf);
- ext4_forget(handle, 1, inode, bh, leaf);
- ext4_free_blocks(handle, inode, leaf, 1, 1);
+ ext4_free_blocks(handle, inode, 0, leaf, 1,
+ EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
return err;
}
@@ -2042,12 +2160,11 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
struct ext4_extent *ex,
ext4_lblk_t from, ext4_lblk_t to)
{
- struct buffer_head *bh;
unsigned short ee_len = ext4_ext_get_actual_len(ex);
- int i, metadata = 0;
+ int flags = EXT4_FREE_BLOCKS_FORGET;
if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
- metadata = 1;
+ flags |= EXT4_FREE_BLOCKS_METADATA;
#ifdef EXTENTS_STATS
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -2072,11 +2189,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
num = le32_to_cpu(ex->ee_block) + ee_len - from;
start = ext_pblock(ex) + ee_len - num;
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_free_blocks(handle, inode, start, num, metadata);
+ ext4_free_blocks(handle, inode, 0, start, num, flags);
} else if (from == le32_to_cpu(ex->ee_block)
&& to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
printk(KERN_INFO "strange request: removal %u-%u from %u:%u\n",
@@ -2108,8 +2221,10 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
if (!path[depth].p_hdr)
path[depth].p_hdr = ext_block_hdr(path[depth].p_bh);
eh = path[depth].p_hdr;
- BUG_ON(eh == NULL);
-
+ if (unlikely(path[depth].p_hdr == NULL)) {
+ EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth);
+ return -EIO;
+ }
/* find where to start removing */
ex = EXT_LAST_EXTENT(eh);
@@ -2167,7 +2282,7 @@ 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)
@@ -2972,7 +3087,7 @@ fix_extent_len:
ext4_ext_dirty(handle, inode, path + depth);
return err;
}
-static int ext4_convert_unwritten_extents_dio(handle_t *handle,
+static int ext4_convert_unwritten_extents_endio(handle_t *handle,
struct inode *inode,
struct ext4_ext_path *path)
{
@@ -3027,6 +3142,14 @@ 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,
@@ -3044,8 +3167,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
flags, allocated);
ext4_ext_show_leaf(inode, path);
- /* DIO get_block() before submit the IO, split the extent */
- if (flags == EXT4_GET_BLOCKS_DIO_CREATE_EXT) {
+ /* get_block() before submit the IO, split the extent */
+ if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
ret = ext4_split_unwritten_extents(handle,
inode, path, iblock,
max_blocks, flags);
@@ -3055,15 +3178,19 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
* completed
*/
if (io)
- io->flag = DIO_AIO_UNWRITTEN;
+ io->flag = EXT4_IO_UNWRITTEN;
else
- EXT4_I(inode)->i_state |= EXT4_STATE_DIO_UNWRITTEN;
+ ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
+ if (ext4_should_dioread_nolock(inode))
+ set_buffer_uninit(bh_result);
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,
+ /* IO end_io complete, convert the filled extent to written */
+ if ((flags & EXT4_GET_BLOCKS_CONVERT)) {
+ ret = ext4_convert_unwritten_extents_endio(handle, inode,
path);
+ if (ret >= 0)
+ ext4_update_inode_fsync_trans(handle, inode, 1);
goto out2;
}
/* buffered IO case */
@@ -3091,6 +3218,8 @@ 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 +3227,30 @@ 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:
@@ -3138,7 +3291,7 @@ 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;
unsigned int allocated = 0;
@@ -3190,7 +3343,13 @@ 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 (unlikely(path[depth].p_ext == NULL && depth != 0)) {
+ EXT4_ERROR_INODE(inode, "bad extent address "
+ "iblock: %d, depth: %d pblock %lld",
+ iblock, depth, path[depth].p_block);
+ err = -EIO;
+ goto out2;
+ }
eh = path[depth].p_hdr;
ex = path[depth].p_ext;
@@ -3205,7 +3364,7 @@ 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);
@@ -3297,21 +3456,35 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){
ext4_ext_mark_uninitialized(&newex);
/*
- * io_end structure was created for every async
- * direct IO write to the middle of the file.
- * To avoid unecessary convertion for every aio dio rewrite
- * to the mid of file, here we flag the IO that is really
- * need the convertion.
+ * io_end structure was created for every IO write to an
+ * uninitialized extent. To avoid unecessary conversion,
+ * here we flag the IO that really needs the conversion.
* For non asycn direct IO case, flag the inode state
* that we need to perform convertion when IO is done.
*/
- if (flags == EXT4_GET_BLOCKS_DIO_CREATE_EXT) {
+ if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
if (io)
- io->flag = DIO_AIO_UNWRITTEN;
+ io->flag = EXT4_IO_UNWRITTEN;
else
- EXT4_I(inode)->i_state |=
- EXT4_STATE_DIO_UNWRITTEN;;
+ ext4_set_inode_state(inode,
+ EXT4_STATE_DIO_UNWRITTEN);
}
+ if (ext4_should_dioread_nolock(inode))
+ set_buffer_uninit(bh_result);
+ }
+
+ if (unlikely(EXT4_I(inode)->i_flags & EXT4_EOFBLOCKS_FL)) {
+ if (unlikely(!eh->eh_entries)) {
+ EXT4_ERROR_INODE(inode,
+ "eh->eh_entries == 0 ee_block %d",
+ ex->ee_block);
+ err = -EIO;
+ goto out2;
+ }
+ last_ex = EXT_LAST_EXTENT(eh);
+ if (iblock + ar.len > le32_to_cpu(last_ex->ee_block)
+ + ext4_ext_get_actual_len(last_ex))
+ EXT4_I(inode)->i_flags &= ~EXT4_EOFBLOCKS_FL;
}
err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
if (err) {
@@ -3319,20 +3492,35 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
/* not a good idea to call discard here directly,
* but otherwise we'd need to call it every free() */
ext4_discard_preallocations(inode);
- ext4_free_blocks(handle, inode, ext_pblock(&newex),
- ext4_ext_get_actual_len(&newex), 0);
+ ext4_free_blocks(handle, inode, 0, ext_pblock(&newex),
+ ext4_ext_get_actual_len(&newex), 0);
goto out2;
}
/* 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 +3619,13 @@ 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_I(inode)->i_flags |= EXT4_EOFBLOCKS_FL;
}
}
@@ -3535,7 +3730,7 @@ 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;
@@ -3567,7 +3762,7 @@ int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
map_bh.b_state = 0;
ret = ext4_get_blocks(handle, inode, block,
max_blocks, &map_bh,
- EXT4_GET_BLOCKS_DIO_CONVERT_EXT);
+ EXT4_GET_BLOCKS_IO_CONVERT_EXT);
if (ret <= 0) {
WARN_ON(ret <= 0);
printk(KERN_ERR "%s: ext4_ext_get_blocks "
@@ -3671,7 +3866,7 @@ 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 */
@@ -3699,7 +3894,6 @@ 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 */
@@ -3713,17 +3907,21 @@ 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 9630583cef2..d0776e410f3 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -23,6 +23,7 @@
#include <linux/jbd2.h>
#include <linux/mount.h>
#include <linux/path.h>
+#include <linux/quotaops.h>
#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -35,9 +36,9 @@
*/
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) &&
@@ -116,18 +117,16 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
* devices or filesystem images.
*/
memset(buf, 0, sizeof(buf));
- path.mnt = mnt->mnt_parent;
- path.dentry = mnt->mnt_mountpoint;
- path_get(&path);
+ path.mnt = mnt;
+ path.dentry = mnt->mnt_root;
cp = d_path(&path, buf, sizeof(buf));
- path_put(&path);
if (!IS_ERR(cp)) {
memcpy(sbi->s_es->s_last_mounted, cp,
sizeof(sbi->s_es->s_last_mounted));
sb->s_dirt = 1;
}
}
- return generic_file_open(inode, filp);
+ return dquot_file_open(inode, filp);
}
const struct file_operations ext4_file_operations = {
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 2b1531266ee..0d0c3239c1c 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -51,25 +51,30 @@
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);
- ret = flush_aio_dio_completed_IO(inode);
+ if (inode->i_sb->s_flags & MS_RDONLY)
+ return 0;
+
+ ret = flush_completed_IO(inode);
if (ret < 0)
- goto out;
+ return ret;
+
+ if (!journal)
+ return simple_fsync(file, dentry, datasync);
+
/*
- * 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 +84,25 @@ 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 (ext4_should_journal_data(inode))
+ return ext4_force_commit(inode->i_sb);
- if (!journal)
- ret = sync_mapping_buffers(inode->i_mapping);
-
- 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);
+ 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 f3624ead4f6..361c0b9962a 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -76,8 +76,7 @@ unsigned ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh,
/* If checksum is bad mark all blocks and inodes use to prevent
* allocation, essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
- ext4_error(sb, __func__, "Checksum bad for group %u",
- block_group);
+ ext4_error(sb, "Checksum bad for group %u", block_group);
ext4_free_blks_set(sb, gdp, 0);
ext4_free_inodes_set(sb, gdp, 0);
ext4_itable_unused_set(sb, gdp, 0);
@@ -111,8 +110,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
bitmap_blk = ext4_inode_bitmap(sb, desc);
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
- ext4_error(sb, __func__,
- "Cannot read inode bitmap - "
+ ext4_error(sb, "Cannot read inode bitmap - "
"block_group = %u, inode_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
@@ -153,8 +151,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
set_bitmap_uptodate(bh);
if (bh_submit_read(bh) < 0) {
put_bh(bh);
- ext4_error(sb, __func__,
- "Cannot read inode bitmap - "
+ ext4_error(sb, "Cannot read inode bitmap - "
"block_group = %u, inode_bitmap = %llu",
block_group, bitmap_blk);
return NULL;
@@ -217,10 +214,10 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
* Note: we must free any quota before locking the superblock,
* as writing the quota to disk may need the lock as well.
*/
- vfs_dq_init(inode);
+ dquot_initialize(inode);
ext4_xattr_delete_inode(handle, inode);
- vfs_dq_free_inode(inode);
- vfs_dq_drop(inode);
+ dquot_free_inode(inode);
+ dquot_drop(inode);
is_directory = S_ISDIR(inode->i_mode);
@@ -229,8 +226,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
es = EXT4_SB(sb)->s_es;
if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
- ext4_error(sb, "ext4_free_inode",
- "reserved or nonexistent inode %lu", ino);
+ ext4_error(sb, "reserved or nonexistent inode %lu", ino);
goto error_return;
}
block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
@@ -248,8 +244,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
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);
+ ext4_error(sb, "bit already cleared for inode %lu", ino);
else {
gdp = ext4_get_group_desc(sb, block_group, &bh2);
@@ -736,8 +731,7 @@ static int ext4_claim_inode(struct super_block *sb,
if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
ino > EXT4_INODES_PER_GROUP(sb)) {
ext4_unlock_group(sb, group);
- ext4_error(sb, __func__,
- "reserved inode or inode > inodes count - "
+ ext4_error(sb, "reserved inode or inode > inodes count - "
"block_group = %u, inode=%lu", group,
ino + group * EXT4_INODES_PER_GROUP(sb));
return 1;
@@ -904,7 +898,7 @@ 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;
@@ -1029,15 +1023,16 @@ 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;
ret = inode;
- if (vfs_dq_alloc_inode(inode)) {
- err = -EDQUOT;
+ dquot_initialize(inode);
+ err = dquot_alloc_inode(inode);
+ if (err)
goto fail_drop;
- }
err = ext4_init_acl(handle, inode, dir);
if (err)
@@ -1074,10 +1069,10 @@ really_out:
return ret;
fail_free_drop:
- vfs_dq_free_inode(inode);
+ dquot_free_inode(inode);
fail_drop:
- vfs_dq_drop(inode);
+ dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
inode->i_nlink = 0;
unlock_new_inode(inode);
@@ -1098,8 +1093,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
/* Error cases - e2fsck has already cleaned up for us */
if (ino > max_ino) {
- ext4_warning(sb, __func__,
- "bad orphan ino %lu! e2fsck was run?", ino);
+ ext4_warning(sb, "bad orphan ino %lu! e2fsck was run?", ino);
goto error;
}
@@ -1107,8 +1101,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
if (!bitmap_bh) {
- ext4_warning(sb, __func__,
- "inode bitmap error for orphan %lu", ino);
+ ext4_warning(sb, "inode bitmap error for orphan %lu", ino);
goto error;
}
@@ -1140,8 +1133,7 @@ iget_failed:
err = PTR_ERR(inode);
inode = NULL;
bad_orphan:
- ext4_warning(sb, __func__,
- "bad orphan inode %lu! e2fsck was run?", ino);
+ ext4_warning(sb, "bad orphan inode %lu! e2fsck was run?", ino);
printk(KERN_NOTICE "ext4_test_bit(bit=%d, block=%llu) = %d\n",
bit, (unsigned long long)bitmap_bh->b_blocknr,
ext4_test_bit(bit, bitmap_bh->b_data));
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2c8caa51add..986120f3006 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -38,6 +38,7 @@
#include <linux/uio.h>
#include <linux/bio.h>
#include <linux/workqueue.h>
+#include <linux/kernel.h>
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -71,58 +72,6 @@ static int ext4_inode_is_fast_symlink(struct inode *inode)
}
/*
- * The ext4 forget function must perform a revoke if we are freeing data
- * which has been journaled. Metadata (eg. indirect blocks) must be
- * revoked in all cases.
- *
- * "bh" may be NULL: a metadata block may have been freed from memory
- * but there may still be a record of it in the journal, and that record
- * still needs to be revoked.
- *
- * If the handle isn't valid we're not journaling, but we still need to
- * call into ext4_journal_revoke() to put the buffer head.
- */
-int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
- struct buffer_head *bh, ext4_fsblk_t blocknr)
-{
- int err;
-
- might_sleep();
-
- BUFFER_TRACE(bh, "enter");
-
- jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
- "data mode %x\n",
- bh, is_metadata, inode->i_mode,
- test_opt(inode->i_sb, DATA_FLAGS));
-
- /* Never use the revoke function if we are doing full data
- * journaling: there is no need to, and a V1 superblock won't
- * support it. Otherwise, only skip the revoke on un-journaled
- * data blocks. */
-
- if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
- (!is_metadata && !ext4_should_journal_data(inode))) {
- if (bh) {
- BUFFER_TRACE(bh, "call jbd2_journal_forget");
- return ext4_journal_forget(handle, bh);
- }
- return 0;
- }
-
- /*
- * data!=journal && (is_metadata || should_journal_data(inode))
- */
- BUFFER_TRACE(bh, "call ext4_journal_revoke");
- err = ext4_journal_revoke(handle, blocknr, bh);
- if (err)
- ext4_abort(inode->i_sb, __func__,
- "error %d when attempting revoke", err);
- BUFFER_TRACE(bh, "exit");
- return err;
-}
-
-/*
* Work out how many blocks we need to proceed with the next chunk of a
* truncate transaction.
*/
@@ -222,6 +171,9 @@ void ext4_delete_inode(struct inode *inode)
handle_t *handle;
int err;
+ if (!is_bad_inode(inode))
+ dquot_initialize(inode);
+
if (ext4_should_order_data(inode))
ext4_begin_ordered_truncate(inode, 0);
truncate_inode_pages(&inode->i_data, 0);
@@ -246,7 +198,7 @@ void ext4_delete_inode(struct inode *inode)
inode->i_size = 0;
err = ext4_mark_inode_dirty(handle, inode);
if (err) {
- ext4_warning(inode->i_sb, __func__,
+ ext4_warning(inode->i_sb,
"couldn't mark inode dirty (err %d)", err);
goto stop_handle;
}
@@ -264,7 +216,7 @@ void ext4_delete_inode(struct inode *inode)
if (err > 0)
err = ext4_journal_restart(handle, 3);
if (err != 0) {
- ext4_warning(inode->i_sb, __func__,
+ ext4_warning(inode->i_sb,
"couldn't extend journal (err %d)", err);
stop_handle:
ext4_journal_stop(handle);
@@ -375,8 +327,7 @@ static int ext4_block_to_path(struct inode *inode,
offsets[n++] = i_block & (ptrs - 1);
final = ptrs;
} else {
- ext4_warning(inode->i_sb, "ext4_block_to_path",
- "block %lu > max in inode %lu",
+ ext4_warning(inode->i_sb, "block %lu > max in inode %lu",
i_block + direct_blocks +
indirect_blocks + double_blocks, inode->i_ino);
}
@@ -396,7 +347,7 @@ static int __ext4_check_blockref(const char *function, struct inode *inode,
if (blk &&
unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
blk, 1))) {
- ext4_error(inode->i_sb, function,
+ __ext4_error(inode->i_sb, function,
"invalid block reference %u "
"in inode #%lu", blk, inode->i_ino);
return -EIO;
@@ -659,7 +610,14 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
if (*err)
goto failed_out;
- BUG_ON(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS);
+ if (unlikely(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS)) {
+ EXT4_ERROR_INODE(inode,
+ "current_block %llu + count %lu > %d!",
+ current_block, count,
+ EXT4_MAX_BLOCK_FILE_PHYS);
+ *err = -EIO;
+ goto failed_out;
+ }
target -= count;
/* allocate blocks for indirect blocks */
@@ -695,7 +653,14 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
ar.flags = EXT4_MB_HINT_DATA;
current_block = ext4_mb_new_blocks(handle, &ar, err);
- BUG_ON(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS);
+ if (unlikely(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS)) {
+ EXT4_ERROR_INODE(inode,
+ "current_block %llu + ar.len %d > %d!",
+ current_block, ar.len,
+ EXT4_MAX_BLOCK_FILE_PHYS);
+ *err = -EIO;
+ goto failed_out;
+ }
if (*err && (target == blks)) {
/*
@@ -721,7 +686,7 @@ allocated:
return ret;
failed_out:
for (i = 0; i < index; i++)
- ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
+ ext4_free_blocks(handle, inode, 0, new_blocks[i], 1, 0);
return ret;
}
@@ -817,14 +782,20 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
return err;
failed:
/* Allocation failed, free what we already allocated */
+ ext4_free_blocks(handle, inode, 0, new_blocks[0], 1, 0);
for (i = 1; i <= n ; i++) {
- BUFFER_TRACE(branch[i].bh, "call jbd2_journal_forget");
- ext4_journal_forget(handle, branch[i].bh);
+ /*
+ * branch[i].bh is newly allocated, so there is no
+ * need to revoke the block, which is why we don't
+ * need to set EXT4_FREE_BLOCKS_METADATA.
+ */
+ ext4_free_blocks(handle, inode, 0, new_blocks[i], 1,
+ EXT4_FREE_BLOCKS_FORGET);
}
- for (i = 0; i < indirect_blks; i++)
- ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
+ for (i = n+1; i < indirect_blks; i++)
+ ext4_free_blocks(handle, inode, 0, new_blocks[i], 1, 0);
- ext4_free_blocks(handle, inode, new_blocks[i], num, 0);
+ ext4_free_blocks(handle, inode, 0, new_blocks[i], num, 0);
return err;
}
@@ -903,12 +874,16 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,
err_out:
for (i = 1; i <= num; i++) {
- BUFFER_TRACE(where[i].bh, "call jbd2_journal_forget");
- ext4_journal_forget(handle, where[i].bh);
- ext4_free_blocks(handle, inode,
- le32_to_cpu(where[i-1].key), 1, 0);
+ /*
+ * branch[i].bh is newly allocated, so there is no
+ * need to revoke the block, which is why we don't
+ * need to set EXT4_FREE_BLOCKS_METADATA.
+ */
+ ext4_free_blocks(handle, inode, where[i].bh, 0, 1,
+ EXT4_FREE_BLOCKS_FORGET);
}
- ext4_free_blocks(handle, inode, le32_to_cpu(where[num].key), blks, 0);
+ ext4_free_blocks(handle, inode, 0, le32_to_cpu(where[num].key),
+ blks, 0);
return err;
}
@@ -1021,10 +996,12 @@ 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 +1020,121 @@ 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);
+ int dind_mask = 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 = roundup_pow_of_two(lblock + 1);
+ 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_I(inode)->i_flags & EXT4_EXTENTS_FL)
- return ext4_ext_calc_metadata_amount(inode, blocks);
+ return ext4_ext_calc_metadata_amount(inode, lblock);
- 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);
+ trace_ext4_da_update_reserve_space(inode, used);
+ 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) {
+ dquot_claim_block(inode, used);
+ if (mdb_free)
+ dquot_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)
+ dquot_claim_block(inode, allocated_meta_blocks);
+ dquot_release_reservation_block(inode, mdb_free + used);
+ }
/*
* 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);
}
@@ -1136,7 +1142,7 @@ static int check_block_validity(struct inode *inode, const char *msg,
sector_t logical, sector_t phys, int len)
{
if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), phys, len)) {
- ext4_error(inode->i_sb, msg,
+ __ext4_error(inode->i_sb, msg,
"inode #%lu logical block %llu mapped to %llu "
"(size %d)", inode->i_ino,
(unsigned long long) logical,
@@ -1318,20 +1324,22 @@ 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 +1542,18 @@ 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_get_block_write(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create);
static int ext4_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
@@ -1575,8 +1595,12 @@ retry:
}
*pagep = page;
- ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
- ext4_get_block);
+ if (ext4_should_dioread_nolock(inode))
+ ret = block_write_begin(file, mapping, pos, len, flags, pagep,
+ fsdata, ext4_get_block_write);
+ else
+ ret = block_write_begin(file, mapping, pos, len, flags, pagep,
+ fsdata, ext4_get_block);
if (!ret && ext4_should_journal_data(inode)) {
ret = walk_page_buffers(handle, page_buffers(page),
@@ -1599,7 +1623,7 @@ 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 +1733,7 @@ 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 +1775,7 @@ 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 +1817,7 @@ 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 +1838,7 @@ 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 +1851,16 @@ 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;
+ int ret;
/*
* recalculate the amount of metadata blocks to reserve
@@ -1839,86 +1868,80 @@ 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);
+ trace_ext4_da_reserve_space(inode, md_needed);
+ 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);
- return -EDQUOT;
- }
+ ret = dquot_reserve_block(inode, md_needed + 1);
+ if (ret)
+ return ret;
- 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)) {
+ dquot_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);
+ dquot_release_reservation_block(inode, to_free);
}
static void ext4_da_page_release_reservation(struct page *page,
@@ -2095,6 +2118,8 @@ static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical,
} else if (buffer_mapped(bh))
BUG_ON(bh->b_blocknr != pblock);
+ if (buffer_uninit(exbh))
+ set_buffer_uninit(bh);
cur_logical++;
pblock++;
} while ((bh = bh->b_this_page) != head);
@@ -2137,17 +2162,16 @@ static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd,
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
- index = page->index;
- if (index > end)
+ if (page->index > end)
break;
- index++;
-
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
block_invalidatepage(page, 0);
ClearPageUptodate(page);
unlock_page(page);
}
+ index = pvec.pages[nr_pages - 1]->index + 1;
+ pagevec_release(&pvec);
}
return;
}
@@ -2223,10 +2247,12 @@ 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 (ext4_should_dioread_nolock(mpd->inode))
+ get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
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) {
@@ -2524,7 +2550,7 @@ 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;
@@ -2600,7 +2626,6 @@ static int bput_one(handle_t *handle, struct buffer_head *bh)
}
static int __ext4_journalled_writepage(struct page *page,
- struct writeback_control *wbc,
unsigned int len)
{
struct address_space *mapping = page->mapping;
@@ -2635,11 +2660,14 @@ 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;
}
+static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode);
+static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
+
/*
* Note that we don't need to start a transaction unless we're journaling data
* because we should have holes filled from ext4_page_mkwrite(). We even don't
@@ -2687,7 +2715,7 @@ static int ext4_writepage(struct page *page,
int ret = 0;
loff_t size;
unsigned int len;
- struct buffer_head *page_bufs;
+ struct buffer_head *page_bufs = NULL;
struct inode *inode = page->mapping->host;
trace_ext4_writepage(inode, page);
@@ -2758,12 +2786,16 @@ static int ext4_writepage(struct page *page,
* doesn't seem much point in redirtying the page here.
*/
ClearPageChecked(page);
- return __ext4_journalled_writepage(page, wbc, len);
+ return __ext4_journalled_writepage(page, len);
}
if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
ret = nobh_writepage(page, noalloc_get_block_write, wbc);
- else
+ else if (page_bufs && buffer_uninit(page_bufs)) {
+ ext4_set_bh_endio(page_bufs, inode);
+ ret = block_write_full_page_endio(page, noalloc_get_block_write,
+ wbc, ext4_end_io_buffer_write);
+ } else
ret = block_write_full_page(page, noalloc_get_block_write,
wbc);
@@ -2788,7 +2820,7 @@ 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_I(inode)->i_flags & EXT4_EXTENTS_FL) &&
(max_blocks > EXT4_MAX_TRANS_DATA))
max_blocks = EXT4_MAX_TRANS_DATA;
@@ -2933,7 +2965,7 @@ retry:
ret = write_cache_pages(mapping, wbc, __mpage_da_writepage,
&mpd);
/*
- * If we have a contigous extent of pages and we
+ * If we have a contiguous extent of pages and we
* haven't done the I/O yet, map the blocks and submit
* them for I/O.
*/
@@ -2999,8 +3031,7 @@ 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 +3056,18 @@ 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 +3075,7 @@ 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 +3129,27 @@ 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 +3338,8 @@ 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 +3358,7 @@ 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);
@@ -3328,11 +3383,45 @@ ext4_readpages(struct file *file, struct address_space *mapping,
return mpage_readpages(mapping, pages, nr_pages, ext4_get_block);
}
+static void ext4_free_io_end(ext4_io_end_t *io)
+{
+ BUG_ON(!io);
+ if (io->page)
+ put_page(io->page);
+ iput(io->inode);
+ kfree(io);
+}
+
+static void ext4_invalidatepage_free_endio(struct page *page, unsigned long offset)
+{
+ struct buffer_head *head, *bh;
+ unsigned int curr_off = 0;
+
+ if (!page_has_buffers(page))
+ return;
+ head = bh = page_buffers(page);
+ do {
+ if (offset <= curr_off && test_clear_buffer_uninit(bh)
+ && bh->b_private) {
+ ext4_free_io_end(bh->b_private);
+ bh->b_private = NULL;
+ bh->b_end_io = NULL;
+ }
+ curr_off = curr_off + bh->b_size;
+ bh = bh->b_this_page;
+ } while (bh != head);
+}
+
static void ext4_invalidatepage(struct page *page, unsigned long offset)
{
journal_t *journal = EXT4_JOURNAL(page->mapping->host);
/*
+ * free any io_end structure allocated for buffers to be discarded
+ */
+ if (ext4_should_dioread_nolock(page->mapping->host))
+ ext4_invalidatepage_free_endio(page, offset);
+ /*
* If it's a full truncate we just forget about the pending dirtying
*/
if (offset == 0)
@@ -3403,7 +3492,14 @@ static ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
}
retry:
- ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
+ if (rw == READ && ext4_should_dioread_nolock(inode))
+ ret = blockdev_direct_IO_no_locking(rw, iocb, inode,
+ inode->i_sb->s_bdev, iov,
+ offset, nr_segs,
+ ext4_get_block, NULL);
+ else
+ ret = blockdev_direct_IO(rw, iocb, inode,
+ inode->i_sb->s_bdev, iov,
offset, nr_segs,
ext4_get_block, NULL);
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -3419,6 +3515,9 @@ 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)
@@ -3446,75 +3545,63 @@ out:
return ret;
}
-static int ext4_get_block_dio_write(struct inode *inode, sector_t iblock,
+static int ext4_get_block_write(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
- handle_t *handle = NULL;
+ handle_t *handle = ext4_journal_current_handle();
int ret = 0;
unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
int dio_credits;
+ int started = 0;
- ext4_debug("ext4_get_block_dio_write: inode %lu, create flag %d\n",
+ ext4_debug("ext4_get_block_write: inode %lu, create flag %d\n",
inode->i_ino, create);
/*
- * DIO VFS code passes create = 0 flag for write to
- * the middle of file. It does this to avoid block
- * allocation for holes, to prevent expose stale data
- * out when there is parallel buffered read (which does
- * not hold the i_mutex lock) while direct IO write has
- * not completed. DIO request on holes finally falls back
- * to buffered IO for this reason.
- *
- * For ext4 extent based file, since we support fallocate,
- * new allocated extent as uninitialized, for holes, we
- * could fallocate blocks for holes, thus parallel
- * buffered IO read will zero out the page when read on
- * a hole while parallel DIO write to the hole has not completed.
- *
- * when we come here, we know it's a direct IO write to
- * to the middle of file (<i_size)
- * so it's safe to override the create flag from VFS.
+ * ext4_get_block in prepare for a DIO write or buffer write.
+ * We allocate an uinitialized extent if blocks haven't been allocated.
+ * The extent will be converted to initialized after IO complete.
*/
- create = EXT4_GET_BLOCKS_DIO_CREATE_EXT;
+ create = EXT4_GET_BLOCKS_IO_CREATE_EXT;
- if (max_blocks > DIO_MAX_BLOCKS)
- max_blocks = DIO_MAX_BLOCKS;
- dio_credits = ext4_chunk_trans_blocks(inode, max_blocks);
- handle = ext4_journal_start(inode, dio_credits);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
+ if (!handle) {
+ if (max_blocks > DIO_MAX_BLOCKS)
+ max_blocks = DIO_MAX_BLOCKS;
+ dio_credits = ext4_chunk_trans_blocks(inode, max_blocks);
+ handle = ext4_journal_start(inode, dio_credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+ started = 1;
}
+
ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result,
create);
if (ret > 0) {
bh_result->b_size = (ret << inode->i_blkbits);
ret = 0;
}
- ext4_journal_stop(handle);
+ if (started)
+ ext4_journal_stop(handle);
out:
return ret;
}
-static void ext4_free_io_end(ext4_io_end_t *io)
-{
- BUG_ON(!io);
- iput(io->inode);
- kfree(io);
-}
-static void dump_aio_dio_list(struct inode * inode)
+static void dump_completed_IO(struct inode * inode)
{
#ifdef EXT4_DEBUG
struct list_head *cur, *before, *after;
ext4_io_end_t *io, *io0, *io1;
+ unsigned long flags;
- if (list_empty(&EXT4_I(inode)->i_aio_dio_complete_list)){
- ext4_debug("inode %lu aio dio list is empty\n", inode->i_ino);
+ if (list_empty(&EXT4_I(inode)->i_completed_io_list)){
+ ext4_debug("inode %lu completed_io list is empty\n", inode->i_ino);
return;
}
- ext4_debug("Dump inode %lu aio_dio_completed_IO list \n", inode->i_ino);
- list_for_each_entry(io, &EXT4_I(inode)->i_aio_dio_complete_list, list){
+ ext4_debug("Dump inode %lu completed_io list \n", inode->i_ino);
+ spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
+ list_for_each_entry(io, &EXT4_I(inode)->i_completed_io_list, list){
cur = &io->list;
before = cur->prev;
io0 = container_of(before, ext4_io_end_t, list);
@@ -3524,32 +3611,31 @@ static void dump_aio_dio_list(struct inode * inode)
ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n",
io, inode->i_ino, io0, io1);
}
+ spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags);
#endif
}
/*
* check a range of space and convert unwritten extents to written.
*/
-static int ext4_end_aio_dio_nolock(ext4_io_end_t *io)
+static int ext4_end_io_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,"
+ ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
"list->prev 0x%p\n",
io, inode->i_ino, io->list.next, io->list.prev);
if (list_empty(&io->list))
return ret;
- if (io->flag != DIO_AIO_UNWRITTEN)
+ if (io->flag != EXT4_IO_UNWRITTEN)
return ret;
- if (offset + size <= i_size_read(inode))
- ret = ext4_convert_unwritten_extents(inode, offset, size);
-
+ ret = ext4_convert_unwritten_extents(inode, offset, size);
if (ret < 0) {
printk(KERN_EMERG "%s: failed to convert unwritten"
"extents to written extents, error is %d"
@@ -3562,50 +3648,64 @@ static int ext4_end_aio_dio_nolock(ext4_io_end_t *io)
io->flag = 0;
return ret;
}
+
/*
* work on completed aio dio IO, to convert unwritten extents to extents
*/
-static void ext4_end_aio_dio_work(struct work_struct *work)
+static void ext4_end_io_work(struct work_struct *work)
{
- ext4_io_end_t *io = container_of(work, ext4_io_end_t, work);
- struct inode *inode = io->inode;
- int ret = 0;
+ ext4_io_end_t *io = container_of(work, ext4_io_end_t, work);
+ struct inode *inode = io->inode;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ unsigned long flags;
+ int ret;
mutex_lock(&inode->i_mutex);
- ret = ext4_end_aio_dio_nolock(io);
- if (ret >= 0) {
- if (!list_empty(&io->list))
- list_del_init(&io->list);
- ext4_free_io_end(io);
+ ret = ext4_end_io_nolock(io);
+ if (ret < 0) {
+ mutex_unlock(&inode->i_mutex);
+ return;
}
+
+ spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+ if (!list_empty(&io->list))
+ list_del_init(&io->list);
+ spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
mutex_unlock(&inode->i_mutex);
+ ext4_free_io_end(io);
}
+
/*
* This function is called from ext4_sync_file().
*
- * When AIO DIO IO is completed, the work to convert unwritten
- * extents to written is queued on workqueue but may not get immediately
+ * When IO is completed, the work to convert unwritten extents to
+ * written is queued on workqueue but may not get immediately
* scheduled. When fsync is called, we need to ensure the
* conversion is complete before fsync returns.
- * The inode keeps track of a list of completed AIO from DIO path
- * that might needs to do the conversion. This function walks through
- * the list and convert the related unwritten extents to written.
+ * The inode keeps track of a list of pending/completed IO that
+ * might needs to do the conversion. This function walks through
+ * the list and convert the related unwritten extents for completed IO
+ * to written.
+ * The function return the number of pending IOs on success.
*/
-int flush_aio_dio_completed_IO(struct inode *inode)
+int flush_completed_IO(struct inode *inode)
{
ext4_io_end_t *io;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ unsigned long flags;
int ret = 0;
int ret2 = 0;
- if (list_empty(&EXT4_I(inode)->i_aio_dio_complete_list))
+ if (list_empty(&ei->i_completed_io_list))
return ret;
- dump_aio_dio_list(inode);
- while (!list_empty(&EXT4_I(inode)->i_aio_dio_complete_list)){
- io = list_entry(EXT4_I(inode)->i_aio_dio_complete_list.next,
+ dump_completed_IO(inode);
+ spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+ while (!list_empty(&ei->i_completed_io_list)){
+ io = list_entry(ei->i_completed_io_list.next,
ext4_io_end_t, list);
/*
- * Calling ext4_end_aio_dio_nolock() to convert completed
+ * Calling ext4_end_io_nolock() to convert completed
* IO to written.
*
* When ext4_sync_file() is called, run_queue() may already
@@ -3618,20 +3718,23 @@ int flush_aio_dio_completed_IO(struct inode *inode)
* avoid double converting from both fsync and background work
* queue work.
*/
- ret = ext4_end_aio_dio_nolock(io);
+ spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+ ret = ext4_end_io_nolock(io);
+ spin_lock_irqsave(&ei->i_completed_io_lock, flags);
if (ret < 0)
ret2 = ret;
else
list_del_init(&io->list);
}
+ spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
return (ret2 < 0) ? ret2 : 0;
}
-static ext4_io_end_t *ext4_init_io_end (struct inode *inode)
+static ext4_io_end_t *ext4_init_io_end (struct inode *inode, gfp_t flags)
{
ext4_io_end_t *io = NULL;
- io = kmalloc(sizeof(*io), GFP_NOFS);
+ io = kmalloc(sizeof(*io), flags);
if (io) {
igrab(inode);
@@ -3639,8 +3742,8 @@ static ext4_io_end_t *ext4_init_io_end (struct inode *inode)
io->flag = 0;
io->offset = 0;
io->size = 0;
- io->error = 0;
- INIT_WORK(&io->work, ext4_end_aio_dio_work);
+ io->page = NULL;
+ INIT_WORK(&io->work, ext4_end_io_work);
INIT_LIST_HEAD(&io->list);
}
@@ -3652,6 +3755,8 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
{
ext4_io_end_t *io_end = iocb->private;
struct workqueue_struct *wq;
+ unsigned long flags;
+ struct ext4_inode_info *ei;
/* if not async direct IO or dio with 0 bytes write, just return */
if (!io_end || !size)
@@ -3663,7 +3768,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
size);
/* if not aio dio with unwritten extents, just free io and return */
- if (io_end->flag != DIO_AIO_UNWRITTEN){
+ if (io_end->flag != EXT4_IO_UNWRITTEN){
ext4_free_io_end(io_end);
iocb->private = NULL;
return;
@@ -3671,16 +3776,85 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
io_end->offset = offset;
io_end->size = size;
+ io_end->flag = EXT4_IO_UNWRITTEN;
wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq;
/* queue the work to convert unwritten extents to written */
queue_work(wq, &io_end->work);
/* Add the io_end to per-inode completed aio dio list*/
- list_add_tail(&io_end->list,
- &EXT4_I(io_end->inode)->i_aio_dio_complete_list);
+ ei = EXT4_I(io_end->inode);
+ spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+ list_add_tail(&io_end->list, &ei->i_completed_io_list);
+ spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
iocb->private = NULL;
}
+
+static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
+{
+ ext4_io_end_t *io_end = bh->b_private;
+ struct workqueue_struct *wq;
+ struct inode *inode;
+ unsigned long flags;
+
+ if (!test_clear_buffer_uninit(bh) || !io_end)
+ goto out;
+
+ if (!(io_end->inode->i_sb->s_flags & MS_ACTIVE)) {
+ printk("sb umounted, discard end_io request for inode %lu\n",
+ io_end->inode->i_ino);
+ ext4_free_io_end(io_end);
+ goto out;
+ }
+
+ io_end->flag = EXT4_IO_UNWRITTEN;
+ inode = io_end->inode;
+
+ /* Add the io_end to per-inode completed io list*/
+ spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
+ list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list);
+ spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags);
+
+ wq = EXT4_SB(inode->i_sb)->dio_unwritten_wq;
+ /* queue the work to convert unwritten extents to written */
+ queue_work(wq, &io_end->work);
+out:
+ bh->b_private = NULL;
+ bh->b_end_io = NULL;
+ clear_buffer_uninit(bh);
+ end_buffer_async_write(bh, uptodate);
+}
+
+static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode)
+{
+ ext4_io_end_t *io_end;
+ struct page *page = bh->b_page;
+ loff_t offset = (sector_t)page->index << PAGE_CACHE_SHIFT;
+ size_t size = bh->b_size;
+
+retry:
+ io_end = ext4_init_io_end(inode, GFP_ATOMIC);
+ if (!io_end) {
+ if (printk_ratelimit())
+ printk(KERN_WARNING "%s: allocation fail\n", __func__);
+ schedule();
+ goto retry;
+ }
+ io_end->offset = offset;
+ io_end->size = size;
+ /*
+ * We need to hold a reference to the page to make sure it
+ * doesn't get evicted before ext4_end_io_work() has a chance
+ * to convert the extent from written to unwritten.
+ */
+ io_end->page = page;
+ get_page(io_end->page);
+
+ bh->b_private = io_end;
+ bh->b_end_io = ext4_end_io_buffer_write;
+ return 0;
+}
+
/*
* For ext4 extent files, ext4 will do direct-io write to holes,
* preallocated extents, and those write extend the file, no need to
@@ -3734,7 +3908,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
iocb->private = NULL;
EXT4_I(inode)->cur_aio_dio = NULL;
if (!is_sync_kiocb(iocb)) {
- iocb->private = ext4_init_io_end(inode);
+ iocb->private = ext4_init_io_end(inode, GFP_NOFS);
if (!iocb->private)
return -ENOMEM;
/*
@@ -3750,7 +3924,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
ret = blockdev_direct_IO(rw, iocb, inode,
inode->i_sb->s_bdev, iov,
offset, nr_segs,
- ext4_get_block_dio_write,
+ ext4_get_block_write,
ext4_end_io_dio);
if (iocb->private)
EXT4_I(inode)->cur_aio_dio = NULL;
@@ -3771,8 +3945,8 @@ 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 +3956,7 @@ 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;
}
@@ -4064,7 +4238,7 @@ static Indirect *ext4_find_shared(struct inode *inode, int depth,
int k, err;
*top = 0;
- /* Make k index the deepest non-null offest + 1 */
+ /* Make k index the deepest non-null offset + 1 */
for (k = depth; k > 1 && !offsets[k-1]; k--)
;
partial = ext4_get_branch(inode, k, offsets, chain, &err);
@@ -4113,13 +4287,27 @@ no_top:
* We release `count' blocks on disk, but (last - first) may be greater
* than `count' because there can be holes in there.
*/
-static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
- struct buffer_head *bh,
- ext4_fsblk_t block_to_free,
- unsigned long count, __le32 *first,
- __le32 *last)
+static int ext4_clear_blocks(handle_t *handle, struct inode *inode,
+ struct buffer_head *bh,
+ ext4_fsblk_t block_to_free,
+ unsigned long count, __le32 *first,
+ __le32 *last)
{
__le32 *p;
+ int flags = EXT4_FREE_BLOCKS_FORGET | EXT4_FREE_BLOCKS_VALIDATED;
+
+ if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ flags |= EXT4_FREE_BLOCKS_METADATA;
+
+ if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free,
+ count)) {
+ ext4_error(inode->i_sb, "inode #%lu: "
+ "attempt to clear blocks %llu len %lu, invalid",
+ inode->i_ino, (unsigned long long) block_to_free,
+ count);
+ return 1;
+ }
+
if (try_to_extend_transaction(handle, inode)) {
if (bh) {
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
@@ -4134,27 +4322,11 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
}
}
- /*
- * Any buffers which are on the journal will be in memory. We
- * find them on the hash table so jbd2_journal_revoke() will
- * run jbd2_journal_forget() on them. We've already detached
- * each block from the file, so bforget() in
- * jbd2_journal_forget() should be safe.
- *
- * AKPM: turn on bforget in jbd2_journal_forget()!!!
- */
- for (p = first; p < last; p++) {
- u32 nr = le32_to_cpu(*p);
- if (nr) {
- struct buffer_head *tbh;
-
- *p = 0;
- tbh = sb_find_get_block(inode->i_sb, nr);
- ext4_forget(handle, 0, inode, tbh, nr);
- }
- }
+ for (p = first; p < last; p++)
+ *p = 0;
- ext4_free_blocks(handle, inode, block_to_free, count, 0);
+ ext4_free_blocks(handle, inode, 0, block_to_free, count, flags);
+ return 0;
}
/**
@@ -4210,9 +4382,10 @@ static void ext4_free_data(handle_t *handle, struct inode *inode,
} else if (nr == block_to_free + count) {
count++;
} else {
- ext4_clear_blocks(handle, inode, this_bh,
- block_to_free,
- count, block_to_free_p, p);
+ if (ext4_clear_blocks(handle, inode, this_bh,
+ block_to_free, count,
+ block_to_free_p, p))
+ break;
block_to_free = nr;
block_to_free_p = p;
count = 1;
@@ -4236,7 +4409,7 @@ static void ext4_free_data(handle_t *handle, struct inode *inode,
if ((EXT4_JOURNAL(inode) == NULL) || bh2jh(this_bh))
ext4_handle_dirty_metadata(handle, inode, this_bh);
else
- ext4_error(inode->i_sb, __func__,
+ ext4_error(inode->i_sb,
"circular indirect block detected, "
"inode=%lu, block=%llu",
inode->i_ino,
@@ -4276,6 +4449,16 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
if (!nr)
continue; /* A hole */
+ if (!ext4_data_block_valid(EXT4_SB(inode->i_sb),
+ nr, 1)) {
+ ext4_error(inode->i_sb,
+ "indirect mapped block in inode "
+ "#%lu invalid (level %d, blk #%lu)",
+ inode->i_ino, depth,
+ (unsigned long) nr);
+ break;
+ }
+
/* Go read the buffer for the next level down */
bh = sb_bread(inode->i_sb, nr);
@@ -4284,7 +4467,7 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
* (should be rare).
*/
if (!bh) {
- ext4_error(inode->i_sb, "ext4_free_branches",
+ ext4_error(inode->i_sb,
"Read failure, inode=%lu, block=%llu",
inode->i_ino, nr);
continue;
@@ -4342,7 +4525,8 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
blocks_for_truncate(inode));
}
- ext4_free_blocks(handle, inode, nr, 1, 1);
+ ext4_free_blocks(handle, inode, 0, nr, 1,
+ EXT4_FREE_BLOCKS_METADATA);
if (parent_bh) {
/*
@@ -4427,8 +4611,10 @@ void ext4_truncate(struct inode *inode)
if (!ext4_can_truncate(inode))
return;
+ EXT4_I(inode)->i_flags &= ~EXT4_EOFBLOCKS_FL;
+
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) {
ext4_ext_truncate(inode);
@@ -4598,9 +4784,8 @@ static int __ext4_get_inode_loc(struct inode *inode,
bh = sb_getblk(sb, block);
if (!bh) {
- ext4_error(sb, "ext4_get_inode_loc", "unable to read "
- "inode block - inode=%lu, block=%llu",
- inode->i_ino, block);
+ ext4_error(sb, "unable to read inode block - "
+ "inode=%lu, block=%llu", inode->i_ino, block);
return -EIO;
}
if (!buffer_uptodate(bh)) {
@@ -4698,9 +4883,8 @@ make_io:
submit_bh(READ_META, bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
- ext4_error(sb, __func__,
- "unable to read inode block - inode=%lu, "
- "block=%llu", inode->i_ino, block);
+ ext4_error(sb, "unable to read inode block - inode=%lu,"
+ " block=%llu", inode->i_ino, block);
brelse(bh);
return -EIO;
}
@@ -4714,7 +4898,7 @@ 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)
@@ -4781,8 +4965,8 @@ 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 +4977,11 @@ 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 +4992,7 @@ 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 +5004,6 @@ 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 +5020,9 @@ 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 +5034,35 @@ 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 +5075,7 @@ 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;
@@ -4884,12 +5094,8 @@ 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_error(sb, __func__,
- "bad extended attribute block %llu in inode #%lu",
+ !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) {
+ ext4_error(sb, "bad extended attribute block %llu inode #%lu",
ei->i_file_acl, inode->i_ino);
ret = -EIO;
goto bad_inode;
@@ -4905,10 +5111,8 @@ 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;
@@ -4936,10 +5140,8 @@ 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",
+ ext4_error(inode->i_sb, "bogus i_mode (%o) for inode=%lu",
inode->i_mode, inode->i_ino);
goto bad_inode;
}
@@ -4949,6 +5151,7 @@ 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);
}
@@ -5010,7 +5213,7 @@ 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 +5277,7 @@ 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 +5306,12 @@ 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);
@@ -5149,7 +5353,7 @@ out_brelse:
* `stuff()' is running, and the new i_size will be lost. Plus the inode
* will no longer be on the superblock's dirty inode list.
*/
-int ext4_write_inode(struct inode *inode, int wait)
+int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
{
int err;
@@ -5163,7 +5367,7 @@ int ext4_write_inode(struct inode *inode, int wait)
return -EIO;
}
- if (!wait)
+ if (wbc->sync_mode != WB_SYNC_ALL)
return 0;
err = ext4_force_commit(inode->i_sb);
@@ -5173,13 +5377,11 @@ int ext4_write_inode(struct inode *inode, int wait)
err = ext4_get_inode_loc(inode, &iloc);
if (err)
return err;
- if (wait)
+ if (wbc->sync_mode == WB_SYNC_ALL)
sync_dirty_buffer(iloc.bh);
if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
- ext4_error(inode->i_sb, __func__,
- "IO error syncing inode, "
- "inode=%lu, block=%llu",
- inode->i_ino,
+ ext4_error(inode->i_sb, "IO error syncing inode, "
+ "inode=%lu, block=%llu", inode->i_ino,
(unsigned long long)iloc.bh->b_blocknr);
err = -EIO;
}
@@ -5221,19 +5423,21 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
if (error)
return error;
+ if (ia_valid & ATTR_SIZE)
+ dquot_initialize(inode);
if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
(ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) {
handle_t *handle;
/* (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;
}
- error = vfs_dq_transfer(inode, attr) ? -EDQUOT : 0;
+ error = dquot_transfer(inode, attr);
if (error) {
ext4_journal_stop(handle);
return error;
@@ -5260,7 +5464,9 @@ 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_I(inode)->i_flags & EXT4_EOFBLOCKS_FL))) {
handle_t *handle;
handle = ext4_journal_start(inode, 3);
@@ -5291,6 +5497,9 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
goto err_out;
}
}
+ /* ext4_truncate will clear the flag */
+ if ((EXT4_I(inode)->i_flags & EXT4_EOFBLOCKS_FL))
+ ext4_truncate(inode);
}
rc = inode_setattr(inode, attr);
@@ -5376,7 +5585,7 @@ static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
* worse case, the indexs blocks spread over different block groups
*
* If datablocks are discontiguous, they are possible to spread over
- * different block groups too. If they are contiugous, with flexbg,
+ * different block groups too. If they are contiuguous, with flexbg,
* they could still across block group boundary.
*
* Also account for superblock, inode, quota and xattr blocks
@@ -5452,7 +5661,7 @@ int ext4_writepage_trans_blocks(struct inode *inode)
* Calculate the journal credits for a chunk of data modification.
*
* This is called from DIO, fallocate or whoever calling
- * ext4_get_blocks() to map/allocate a chunk of contigous disk blocks.
+ * ext4_get_blocks() to map/allocate a chunk of contiguous disk blocks.
*
* journal buffers for data blocks are not included here, as DIO
* and fallocate do no need to journal data buffers.
@@ -5529,8 +5738,8 @@ 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 +5783,7 @@ 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
@@ -5588,10 +5797,11 @@ 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__,
+ ext4_warning(inode->i_sb,
"Unable to expand inode %lu. Delete"
" some EAs or run e2fsck.",
inode->i_ino);
@@ -5613,7 +5823,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
* i_size has been changed by generic_commit_write() and we thus need
* to include the updated inode in the current transaction.
*
- * Also, vfs_dq_alloc_block() will always dirty the inode when blocks
+ * Also, dquot_alloc_block() will always dirty the inode when blocks
* are allocated to the file.
*
* If the inode is marked synchronous, we don't honour that here - doing
@@ -5655,7 +5865,7 @@ 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);
}
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index c1cdf613e72..016d0249294 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;
}
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index bba12824def..54df209d2ee 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -69,7 +69,7 @@
*
* pa_lstart -> the logical start block for this prealloc space
* pa_pstart -> the physical start block for this prealloc space
- * pa_len -> lenght for this prealloc space
+ * pa_len -> length for this prealloc space
* pa_free -> free space available in this prealloc space
*
* The inode preallocation space is used looking at the _logical_ start
@@ -142,7 +142,7 @@
* 2 blocks and the order of allocation is >= sbi->s_mb_order2_reqs. The
* value of s_mb_order2_reqs can be tuned via
* /sys/fs/ext4/<partition>/mb_order2_req. If the request len is equal to
- * stripe size (sbi->s_stripe), we try to search for contigous block in
+ * stripe size (sbi->s_stripe), we try to search for contiguous block in
* stripe size. This should result in better allocation on RAID setups. If
* not, we search in the specific group using bitmap for best extents. The
* tunable min_to_scan and max_to_scan control the behaviour here.
@@ -441,10 +441,9 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b,
for (i = 0; i < count; i++) {
if (!mb_test_bit(first + i, e4b->bd_info->bb_bitmap)) {
ext4_fsblk_t blocknr;
- blocknr = e4b->bd_group * EXT4_BLOCKS_PER_GROUP(sb);
+
+ blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
blocknr += first + i;
- blocknr +=
- le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
ext4_grp_locked_error(sb, e4b->bd_group,
__func__, "double-free of inode"
" %lu's block %llu(bit %u in group %u)",
@@ -1255,10 +1254,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
if (!mb_test_bit(block, EXT4_MB_BITMAP(e4b))) {
ext4_fsblk_t blocknr;
- blocknr = e4b->bd_group * EXT4_BLOCKS_PER_GROUP(sb);
+
+ blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
blocknr += block;
- blocknr +=
- le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
ext4_grp_locked_error(sb, e4b->bd_group,
__func__, "double-free of inode"
" %lu's block %llu(bit %u in group %u)",
@@ -1631,7 +1629,6 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
int max;
int err;
struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
- struct ext4_super_block *es = sbi->s_es;
struct ext4_free_extent ex;
if (!(ac->ac_flags & EXT4_MB_HINT_TRY_GOAL))
@@ -1648,8 +1645,8 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
if (max >= ac->ac_g_ex.fe_len && ac->ac_g_ex.fe_len == sbi->s_stripe) {
ext4_fsblk_t start;
- start = (e4b->bd_group * EXT4_BLOCKS_PER_GROUP(ac->ac_sb)) +
- ex.fe_start + le32_to_cpu(es->s_first_data_block);
+ start = ext4_group_first_block_no(ac->ac_sb, e4b->bd_group) +
+ ex.fe_start;
/* use do_div to get remainder (would be 64-bit modulo) */
if (do_div(start, sbi->s_stripe) == 0) {
ac->ac_found++;
@@ -1803,8 +1800,8 @@ void ext4_mb_scan_aligned(struct ext4_allocation_context *ac,
BUG_ON(sbi->s_stripe == 0);
/* find first stripe-aligned block in group */
- first_group_block = e4b->bd_group * EXT4_BLOCKS_PER_GROUP(sb)
- + le32_to_cpu(sbi->s_es->s_first_data_block);
+ first_group_block = ext4_group_first_block_no(sb, e4b->bd_group);
+
a = first_group_block + sbi->s_stripe - 1;
do_div(a, sbi->s_stripe);
i = (a * sbi->s_stripe) - first_group_block;
@@ -2256,7 +2253,7 @@ 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_free_root = RB_ROOT;
#ifdef DOUBLE_CHECK
{
@@ -2529,7 +2526,6 @@ 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) {
@@ -2559,13 +2555,16 @@ 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);
-
+ if (test_opt(sb, DISCARD)) {
+ 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);
+ sb_issue_discard(sb, discard_block, entry->count);
+ }
kmem_cache_free(ext4_free_ext_cachep, entry);
ext4_mb_release_desc(&e4b);
}
@@ -2698,14 +2697,11 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
if (err)
goto out_err;
- block = ac->ac_b_ex.fe_group * EXT4_BLOCKS_PER_GROUP(sb)
- + ac->ac_b_ex.fe_start
- + le32_to_cpu(es->s_first_data_block);
+ block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
len = ac->ac_b_ex.fe_len;
if (!ext4_data_block_valid(sbi, block, len)) {
- ext4_error(sb, __func__,
- "Allocating blocks %llu-%llu which overlap "
+ ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
"fs metadata\n", block, block+len);
/* File system mounted not to panic on error
* Fix the bitmap and repeat the block allocation
@@ -2750,12 +2746,6 @@ 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 +2996,24 @@ 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,
@@ -3144,9 +3152,7 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
/* The max size of hash table is PREALLOC_TB_SIZE */
order = PREALLOC_TB_SIZE - 1;
- goal_block = ac->ac_g_ex.fe_group * EXT4_BLOCKS_PER_GROUP(ac->ac_sb) +
- ac->ac_g_ex.fe_start +
- le32_to_cpu(EXT4_SB(ac->ac_sb)->s_es->s_first_data_block);
+ goal_block = ext4_grp_offs_to_block(ac->ac_sb, &ac->ac_g_ex);
/*
* search for the prealloc space that is having
* minimal distance from the goal block.
@@ -3509,8 +3515,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
if (bit >= end)
break;
next = mb_find_next_bit(bitmap_bh->b_data, end, bit);
- start = group * EXT4_BLOCKS_PER_GROUP(sb) + bit +
- le32_to_cpu(sbi->s_es->s_first_data_block);
+ start = ext4_group_first_block_no(sb, group) + bit;
mb_debug(1, " free preallocated %u/%u in group %u\n",
(unsigned) start, (unsigned) next - bit,
(unsigned) group);
@@ -3606,15 +3611,13 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
bitmap_bh = ext4_read_block_bitmap(sb, group);
if (bitmap_bh == NULL) {
- ext4_error(sb, __func__, "Error in reading block "
- "bitmap for %u", group);
+ ext4_error(sb, "Error reading block bitmap for %u", group);
return 0;
}
err = ext4_mb_load_buddy(sb, group, &e4b);
if (err) {
- ext4_error(sb, __func__, "Error in loading buddy "
- "information for %u", group);
+ ext4_error(sb, "Error loading buddy information for %u", group);
put_bh(bitmap_bh);
return 0;
}
@@ -3787,15 +3790,15 @@ repeat:
err = ext4_mb_load_buddy(sb, group, &e4b);
if (err) {
- ext4_error(sb, __func__, "Error in loading buddy "
- "information for %u", group);
+ ext4_error(sb, "Error loading buddy information for %u",
+ group);
continue;
}
bitmap_bh = ext4_read_block_bitmap(sb, group);
if (bitmap_bh == NULL) {
- ext4_error(sb, __func__, "Error in reading block "
- "bitmap for %u", group);
+ ext4_error(sb, "Error reading block bitmap for %u",
+ group);
ext4_mb_release_desc(&e4b);
continue;
}
@@ -3921,7 +3924,7 @@ 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;
}
@@ -3932,7 +3935,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
* per cpu locality group is to reduce the contention between block
* request from multiple CPUs.
*/
- ac->ac_lg = per_cpu_ptr(sbi->s_locality_groups, raw_smp_processor_id());
+ ac->ac_lg = __this_cpu_ptr(sbi->s_locality_groups);
/* we're going to use group allocation */
ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC;
@@ -4060,8 +4063,8 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb,
ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, NULL);
if (ext4_mb_load_buddy(sb, group, &e4b)) {
- ext4_error(sb, __func__, "Error in loading buddy "
- "information for %u", group);
+ ext4_error(sb, "Error loading buddy information for %u",
+ group);
continue;
}
ext4_lock_group(sb, group);
@@ -4237,7 +4240,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
return 0;
}
reserv_blks = ar->len;
- while (ar->len && vfs_dq_alloc_block(ar->inode, ar->len)) {
+ while (ar->len && dquot_alloc_block(ar->inode, ar->len)) {
ar->flags |= EXT4_MB_HINT_NOPREALLOC;
ar->len--;
}
@@ -4290,6 +4293,7 @@ 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);
@@ -4313,7 +4317,7 @@ out2:
kmem_cache_free(ext4_ac_cachep, ac);
out1:
if (inquota && ar->len < inquota)
- vfs_dq_free_block(ar->inode, inquota - ar->len);
+ dquot_free_block(ar->inode, inquota - ar->len);
out3:
if (!ar->len) {
if (!EXT4_I(ar->inode)->i_delalloc_reserved_flag)
@@ -4422,18 +4426,24 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
return 0;
}
-/*
- * Main entry point into mballoc to free blocks
+/**
+ * ext4_free_blocks() -- Free given blocks and update quota
+ * @handle: handle for this transaction
+ * @inode: inode
+ * @block: start physical block to free
+ * @count: number of blocks to count
+ * @metadata: Are these metadata blocks
*/
-void ext4_mb_free_blocks(handle_t *handle, struct inode *inode,
- ext4_fsblk_t block, unsigned long count,
- int metadata, unsigned long *freed)
+void ext4_free_blocks(handle_t *handle, struct inode *inode,
+ struct buffer_head *bh, ext4_fsblk_t block,
+ unsigned long count, int flags)
{
struct buffer_head *bitmap_bh = NULL;
struct super_block *sb = inode->i_sb;
struct ext4_allocation_context *ac = NULL;
struct ext4_group_desc *gdp;
struct ext4_super_block *es;
+ unsigned long freed = 0;
unsigned int overflow;
ext4_grpblk_t bit;
struct buffer_head *gd_bh;
@@ -4443,21 +4453,49 @@ void ext4_mb_free_blocks(handle_t *handle, struct inode *inode,
int err = 0;
int ret;
- *freed = 0;
+ if (bh) {
+ if (block)
+ BUG_ON(block != bh->b_blocknr);
+ else
+ block = bh->b_blocknr;
+ }
sbi = EXT4_SB(sb);
es = EXT4_SB(sb)->s_es;
- if (block < le32_to_cpu(es->s_first_data_block) ||
- block + count < block ||
- block + count > ext4_blocks_count(es)) {
- ext4_error(sb, __func__,
- "Freeing blocks not in datazone - "
- "block = %llu, count = %lu", block, count);
+ if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
+ !ext4_data_block_valid(sbi, block, count)) {
+ ext4_error(sb, "Freeing blocks not in datazone - "
+ "block = %llu, count = %lu", block, count);
goto error_return;
}
ext4_debug("freeing block %llu\n", block);
- trace_ext4_free_blocks(inode, block, count, metadata);
+ trace_ext4_free_blocks(inode, block, count, flags);
+
+ if (flags & EXT4_FREE_BLOCKS_FORGET) {
+ struct buffer_head *tbh = bh;
+ int i;
+
+ BUG_ON(bh && (count > 1));
+
+ for (i = 0; i < count; i++) {
+ if (!bh)
+ tbh = sb_find_get_block(inode->i_sb,
+ block + i);
+ ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA,
+ inode, tbh, block + i);
+ }
+ }
+
+ /*
+ * We need to make sure we don't reuse the freed block until
+ * after the transaction is committed, which we can do by
+ * treating the block as metadata, below. We make an
+ * exception if the inode is to be written in writeback mode
+ * since writeback mode has weak data consistency guarantees.
+ */
+ if (!ext4_should_writeback_data(inode))
+ flags |= EXT4_FREE_BLOCKS_METADATA;
ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
if (ac) {
@@ -4495,8 +4533,7 @@ do_more:
in_range(block + count - 1, ext4_inode_table(sb, gdp),
EXT4_SB(sb)->s_itb_per_group)) {
- ext4_error(sb, __func__,
- "Freeing blocks in system zone - "
+ ext4_error(sb, "Freeing blocks in system zone - "
"Block = %llu, count = %lu", block, count);
/* err = 0. ext4_std_error should be a no op */
goto error_return;
@@ -4533,7 +4570,8 @@ do_more:
err = ext4_mb_load_buddy(sb, block_group, &e4b);
if (err)
goto error_return;
- if (metadata && ext4_handle_valid(handle)) {
+
+ if ((flags & EXT4_FREE_BLOCKS_METADATA) && ext4_handle_valid(handle)) {
struct ext4_free_data *new_entry;
/*
* blocks being freed are metadata. these blocks shouldn't
@@ -4572,7 +4610,7 @@ do_more:
ext4_mb_release_desc(&e4b);
- *freed += count;
+ freed += count;
/* We dirtied the bitmap block */
BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
@@ -4592,6 +4630,8 @@ do_more:
}
sb->s_dirt = 1;
error_return:
+ if (freed)
+ dquot_free_block(inode, freed);
brelse(bitmap_bh);
ext4_std_error(sb, err);
if (ac)
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 0ca811061bc..b619322c76f 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -17,7 +17,6 @@
#include <linux/proc_fs.h>
#include <linux/pagemap.h>
#include <linux/seq_file.h>
-#include <linux/version.h>
#include <linux/blkdev.h>
#include <linux/mutex.h>
#include "ext4_jbd2.h"
@@ -221,16 +220,9 @@ 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)
{
- ext4_fsblk_t block;
-
- block = (ext4_fsblk_t) fex->fe_group * EXT4_BLOCKS_PER_GROUP(sb)
- + fex->fe_start
- + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
- return block;
+ return ext4_group_first_block_no(sb, fex->fe_group) + fex->fe_start;
}
#endif
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index a93d5b80f3e..8b87bd0eac9 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);
@@ -262,13 +262,17 @@ static int free_dind_blocks(handle_t *handle,
for (i = 0; i < max_entries; i++) {
if (tmp_idata[i]) {
extend_credit_for_blkdel(handle, inode);
- ext4_free_blocks(handle, inode,
- le32_to_cpu(tmp_idata[i]), 1, 1);
+ ext4_free_blocks(handle, inode, 0,
+ le32_to_cpu(tmp_idata[i]), 1,
+ EXT4_FREE_BLOCKS_METADATA |
+ EXT4_FREE_BLOCKS_FORGET);
}
}
put_bh(bh);
extend_credit_for_blkdel(handle, inode);
- ext4_free_blocks(handle, inode, le32_to_cpu(i_data), 1, 1);
+ ext4_free_blocks(handle, inode, 0, le32_to_cpu(i_data), 1,
+ EXT4_FREE_BLOCKS_METADATA |
+ EXT4_FREE_BLOCKS_FORGET);
return 0;
}
@@ -297,7 +301,9 @@ static int free_tind_blocks(handle_t *handle,
}
put_bh(bh);
extend_credit_for_blkdel(handle, inode);
- ext4_free_blocks(handle, inode, le32_to_cpu(i_data), 1, 1);
+ ext4_free_blocks(handle, inode, 0, le32_to_cpu(i_data), 1,
+ EXT4_FREE_BLOCKS_METADATA |
+ EXT4_FREE_BLOCKS_FORGET);
return 0;
}
@@ -308,8 +314,10 @@ static int free_ind_block(handle_t *handle, struct inode *inode, __le32 *i_data)
/* ei->i_data[EXT4_IND_BLOCK] */
if (i_data[0]) {
extend_credit_for_blkdel(handle, inode);
- ext4_free_blocks(handle, inode,
- le32_to_cpu(i_data[0]), 1, 1);
+ ext4_free_blocks(handle, inode, 0,
+ le32_to_cpu(i_data[0]), 1,
+ EXT4_FREE_BLOCKS_METADATA |
+ EXT4_FREE_BLOCKS_FORGET);
}
/* ei->i_data[EXT4_DIND_BLOCK] */
@@ -357,12 +365,12 @@ 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
@@ -419,7 +427,8 @@ static int free_ext_idx(handle_t *handle, struct inode *inode,
}
put_bh(bh);
extend_credit_for_blkdel(handle, inode);
- ext4_free_blocks(handle, inode, block, 1, 1);
+ ext4_free_blocks(handle, inode, 0, block, 1,
+ EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
return retval;
}
@@ -477,7 +486,7 @@ 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 +503,10 @@ 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 +529,20 @@ 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 +624,8 @@ 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 25b6b145736..aa5fe28d180 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;
}
}
@@ -141,12 +152,12 @@ mext_check_null_inode(struct inode *inode1, struct inode *inode2,
int ret = 0;
if (inode1 == NULL) {
- ext4_error(inode2->i_sb, function,
+ __ext4_error(inode2->i_sb, function,
"Both inodes should not be NULL: "
"inode1 NULL inode2 %lu", inode2->i_ino);
ret = -EIO;
} else if (inode2 == NULL) {
- ext4_error(inode1->i_sb, function,
+ __ext4_error(inode1->i_sb, function,
"Both inodes should not be NULL: "
"inode1 %lu inode2 NULL", inode1->i_ino);
ret = -EIO;
@@ -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;
}
@@ -554,7 +528,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
* new_ext |-------|
*/
if (le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end) {
- ext4_error(orig_inode->i_sb, __func__,
+ ext4_error(orig_inode->i_sb,
"new_ext_end(%u) should be less than or equal to "
"oext->ee_block(%u) + oext_alen(%d) - 1",
new_ext_end, le32_to_cpu(oext->ee_block),
@@ -596,7 +570,7 @@ out:
* @tmp_oext: the extent that will belong to the donor inode
* @orig_off: block offset of original inode
* @donor_off: block offset of donor inode
- * @max_count: the maximun length of extents
+ * @max_count: the maximum length of extents
*
* Return 0 on success, or a negative error value on failure.
*/
@@ -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;
@@ -707,39 +682,39 @@ 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 */
while (1) {
/* The extent for donor must be found. */
if (!dext) {
- ext4_error(donor_inode->i_sb, __func__,
+ ext4_error(donor_inode->i_sb,
"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__,
+ ext4_error(donor_inode->i_sb,
"Donor offset(%u) and the first block of donor "
"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.
@@ -970,18 +944,17 @@ 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;
}
@@ -1025,13 +998,6 @@ 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) ||
@@ -1088,7 +1054,7 @@ mext_check_arguments(struct inode *orig_inode,
}
if (!*len) {
- ext4_debug("ext4 move extent: len shoudld not be 0 "
+ ext4_debug("ext4 move extent: len should not be 0 "
"[ino:orig %lu, donor %lu]\n", orig_inode->i_ino,
donor_inode->i_ino);
return -EINVAL;
@@ -1232,16 +1198,24 @@ 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 +1329,39 @@ 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__,
+ ext4_error(orig_inode->i_sb,
"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 +1370,10 @@ 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 +1395,11 @@ 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 +1408,7 @@ 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 6d2c1b897fc..0c070fabd10 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -383,8 +383,7 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
if (root->info.hash_version != DX_HASH_TEA &&
root->info.hash_version != DX_HASH_HALF_MD4 &&
root->info.hash_version != DX_HASH_LEGACY) {
- ext4_warning(dir->i_sb, __func__,
- "Unrecognised inode hash code %d",
+ ext4_warning(dir->i_sb, "Unrecognised inode hash code %d",
root->info.hash_version);
brelse(bh);
*err = ERR_BAD_DX_DIR;
@@ -399,8 +398,7 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
hash = hinfo->hash;
if (root->info.unused_flags & 1) {
- ext4_warning(dir->i_sb, __func__,
- "Unimplemented inode hash flags: %#06x",
+ ext4_warning(dir->i_sb, "Unimplemented inode hash flags: %#06x",
root->info.unused_flags);
brelse(bh);
*err = ERR_BAD_DX_DIR;
@@ -408,8 +406,7 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
}
if ((indirect = root->info.indirect_levels) > 1) {
- ext4_warning(dir->i_sb, __func__,
- "Unimplemented inode hash depth: %#06x",
+ ext4_warning(dir->i_sb, "Unimplemented inode hash depth: %#06x",
root->info.indirect_levels);
brelse(bh);
*err = ERR_BAD_DX_DIR;
@@ -421,8 +418,7 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
if (dx_get_limit(entries) != dx_root_limit(dir,
root->info.info_length)) {
- ext4_warning(dir->i_sb, __func__,
- "dx entry: limit != root limit");
+ ext4_warning(dir->i_sb, "dx entry: limit != root limit");
brelse(bh);
*err = ERR_BAD_DX_DIR;
goto fail;
@@ -433,7 +429,7 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
{
count = dx_get_count(entries);
if (!count || count > dx_get_limit(entries)) {
- ext4_warning(dir->i_sb, __func__,
+ ext4_warning(dir->i_sb,
"dx entry: no count or count > limit");
brelse(bh);
*err = ERR_BAD_DX_DIR;
@@ -478,7 +474,7 @@ dx_probe(const struct qstr *d_name, struct inode *dir,
goto fail2;
at = entries = ((struct dx_node *) bh->b_data)->entries;
if (dx_get_limit(entries) != dx_node_limit (dir)) {
- ext4_warning(dir->i_sb, __func__,
+ ext4_warning(dir->i_sb,
"dx entry: limit != node limit");
brelse(bh);
*err = ERR_BAD_DX_DIR;
@@ -494,7 +490,7 @@ fail2:
}
fail:
if (*err == ERR_BAD_DX_DIR)
- ext4_warning(dir->i_sb, __func__,
+ ext4_warning(dir->i_sb,
"Corrupt dir inode %ld, running e2fsck is "
"recommended.", dir->i_ino);
return NULL;
@@ -947,9 +943,8 @@ restart:
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
/* read error, skip block & hope for the best */
- ext4_error(sb, __func__, "reading directory #%lu "
- "offset %lu", dir->i_ino,
- (unsigned long)block);
+ ext4_error(sb, "reading directory #%lu offset %lu",
+ dir->i_ino, (unsigned long)block);
brelse(bh);
goto next;
}
@@ -1041,7 +1036,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct q
retval = ext4_htree_next_block(dir, hash, frame,
frames, NULL);
if (retval < 0) {
- ext4_warning(sb, __func__,
+ ext4_warning(sb,
"error reading index page in directory #%lu",
dir->i_ino);
*err = retval;
@@ -1071,14 +1066,13 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, stru
__u32 ino = le32_to_cpu(de->inode);
brelse(bh);
if (!ext4_valid_inum(dir->i_sb, ino)) {
- ext4_error(dir->i_sb, "ext4_lookup",
- "bad inode number: %u", ino);
+ ext4_error(dir->i_sb, "bad inode number: %u", ino);
return ERR_PTR(-EIO);
}
inode = ext4_iget(dir->i_sb, ino);
if (unlikely(IS_ERR(inode))) {
if (PTR_ERR(inode) == -ESTALE) {
- ext4_error(dir->i_sb, __func__,
+ ext4_error(dir->i_sb,
"deleted inode referenced: %u",
ino);
return ERR_PTR(-EIO);
@@ -1110,7 +1104,7 @@ struct dentry *ext4_get_parent(struct dentry *child)
brelse(bh);
if (!ext4_valid_inum(child->d_inode->i_sb, ino)) {
- ext4_error(child->d_inode->i_sb, "ext4_get_parent",
+ ext4_error(child->d_inode->i_sb,
"bad inode number: %u", ino);
return ERR_PTR(-EIO);
}
@@ -1292,9 +1286,6 @@ 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 +1306,10 @@ 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 +1324,6 @@ 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 +1363,6 @@ 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;
}
@@ -1419,7 +1404,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
de = (struct ext4_dir_entry_2 *)((char *)fde +
ext4_rec_len_from_disk(fde->rec_len, blocksize));
if ((char *) de >= (((char *) root) + blocksize)) {
- ext4_error(dir->i_sb, __func__,
+ ext4_error(dir->i_sb,
"invalid rec_len for '..' in inode %lu",
dir->i_ino);
brelse(bh);
@@ -1471,7 +1456,9 @@ 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;
}
/*
@@ -1514,8 +1501,10 @@ 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 +1517,9 @@ 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);
+ return retval;
}
/*
@@ -1561,10 +1552,8 @@ 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",
@@ -1580,8 +1569,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
if (levels && (dx_get_count(frames->entries) ==
dx_get_limit(frames->entries))) {
- ext4_warning(sb, __func__,
- "Directory index full!");
+ ext4_warning(sb, "Directory index full!");
err = -ENOSPC;
goto cleanup;
}
@@ -1657,7 +1645,6 @@ 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:
@@ -1772,10 +1759,12 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, int mode,
struct inode *inode;
int err, retries = 0;
+ dquot_initialize(dir);
+
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);
@@ -1806,10 +1795,12 @@ static int ext4_mknod(struct inode *dir, struct dentry *dentry,
if (!new_valid_dev(rdev))
return -EINVAL;
+ dquot_initialize(dir);
+
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);
@@ -1843,10 +1834,12 @@ static int ext4_mkdir(struct inode *dir, struct dentry *dentry, int mode)
if (EXT4_DIR_LINK_MAX(dir))
return -EMLINK;
+ dquot_initialize(dir);
+
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);
@@ -1922,11 +1915,11 @@ static int empty_dir(struct inode *inode)
if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2) ||
!(bh = ext4_bread(NULL, inode, 0, 0, &err))) {
if (err)
- ext4_error(inode->i_sb, __func__,
+ ext4_error(inode->i_sb,
"error %d reading directory #%lu offset 0",
err, inode->i_ino);
else
- ext4_warning(inode->i_sb, __func__,
+ ext4_warning(inode->i_sb,
"bad directory (dir #%lu) - no data block",
inode->i_ino);
return 1;
@@ -1937,7 +1930,7 @@ static int empty_dir(struct inode *inode)
!le32_to_cpu(de1->inode) ||
strcmp(".", de->name) ||
strcmp("..", de1->name)) {
- ext4_warning(inode->i_sb, "empty_dir",
+ ext4_warning(inode->i_sb,
"bad directory (dir #%lu) - no `.' or `..'",
inode->i_ino);
brelse(bh);
@@ -1955,7 +1948,7 @@ static int empty_dir(struct inode *inode)
offset >> EXT4_BLOCK_SIZE_BITS(sb), 0, &err);
if (!bh) {
if (err)
- ext4_error(sb, __func__,
+ ext4_error(sb,
"error %d reading directory"
" #%lu offset %u",
err, inode->i_ino, offset);
@@ -2026,11 +2019,18 @@ 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 +2043,7 @@ 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 +2103,7 @@ 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 =
@@ -2142,7 +2143,9 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
/* Initialize quotas before so that eventual writes go in
* separate transaction */
- vfs_dq_init(dentry->d_inode);
+ dquot_initialize(dir);
+ dquot_initialize(dentry->d_inode);
+
handle = ext4_journal_start(dir, EXT4_DELETE_TRANS_BLOCKS(dir->i_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -2169,7 +2172,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
if (retval)
goto end_rmdir;
if (!EXT4_DIR_LINK_EMPTY(inode))
- ext4_warning(inode->i_sb, "ext4_rmdir",
+ ext4_warning(inode->i_sb,
"empty directory has too many links (%d)",
inode->i_nlink);
inode->i_version++;
@@ -2201,7 +2204,9 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
/* Initialize quotas before so that eventual writes go
* in separate transaction */
- vfs_dq_init(dentry->d_inode);
+ dquot_initialize(dir);
+ dquot_initialize(dentry->d_inode);
+
handle = ext4_journal_start(dir, EXT4_DELETE_TRANS_BLOCKS(dir->i_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -2221,7 +2226,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
goto end_unlink;
if (!inode->i_nlink) {
- ext4_warning(inode->i_sb, "ext4_unlink",
+ ext4_warning(inode->i_sb,
"Deleting nonexistent file (%lu), %d",
inode->i_ino, inode->i_nlink);
inode->i_nlink = 1;
@@ -2256,10 +2261,12 @@ static int ext4_symlink(struct inode *dir,
if (l > dir->i_sb->s_blocksize)
return -ENAMETOOLONG;
+ dquot_initialize(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);
@@ -2314,6 +2321,8 @@ static int ext4_link(struct dentry *old_dentry,
if (inode->i_nlink >= EXT4_LINK_MAX)
return -EMLINK;
+ dquot_initialize(dir);
+
/*
* Return -ENOENT if we've raced with unlink and i_nlink is 0. Doing
* otherwise has the potential to corrupt the orphan inode list.
@@ -2364,12 +2373,15 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
struct ext4_dir_entry_2 *old_de, *new_de;
int retval, force_da_alloc = 0;
+ dquot_initialize(old_dir);
+ dquot_initialize(new_dir);
+
old_bh = new_bh = dir_bh = NULL;
/* Initialize quotas before so that eventual writes go
* in separate transaction */
if (new_dentry->d_inode)
- vfs_dq_init(new_dentry->d_inode);
+ dquot_initialize(new_dentry->d_inode);
handle = ext4_journal_start(old_dir, 2 *
EXT4_DATA_TRANS_BLOCKS(old_dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2);
@@ -2468,7 +2480,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
}
}
if (retval) {
- ext4_warning(old_dir->i_sb, "ext4_rename",
+ ext4_warning(old_dir->i_sb,
"Deleting old file (%lu), %d, error=%d",
old_dir->i_ino, old_dir->i_nlink, retval);
}
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 3cfc343c41b..5692c48754a 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -48,65 +48,54 @@ static int verify_group_input(struct super_block *sb,
ext4_get_group_no_and_offset(sb, start, NULL, &offset);
if (group != sbi->s_groups_count)
- ext4_warning(sb, __func__,
- "Cannot add at group %u (only %u groups)",
+ ext4_warning(sb, "Cannot add at group %u (only %u groups)",
input->group, sbi->s_groups_count);
else if (offset != 0)
- ext4_warning(sb, __func__, "Last group not full");
+ ext4_warning(sb, "Last group not full");
else if (input->reserved_blocks > input->blocks_count / 5)
- ext4_warning(sb, __func__, "Reserved blocks too high (%u)",
+ ext4_warning(sb, "Reserved blocks too high (%u)",
input->reserved_blocks);
else if (free_blocks_count < 0)
- ext4_warning(sb, __func__, "Bad blocks count %u",
+ ext4_warning(sb, "Bad blocks count %u",
input->blocks_count);
else if (!(bh = sb_bread(sb, end - 1)))
- ext4_warning(sb, __func__,
- "Cannot read last block (%llu)",
+ ext4_warning(sb, "Cannot read last block (%llu)",
end - 1);
else if (outside(input->block_bitmap, start, end))
- ext4_warning(sb, __func__,
- "Block bitmap not in group (block %llu)",
+ ext4_warning(sb, "Block bitmap not in group (block %llu)",
(unsigned long long)input->block_bitmap);
else if (outside(input->inode_bitmap, start, end))
- ext4_warning(sb, __func__,
- "Inode bitmap not in group (block %llu)",
+ ext4_warning(sb, "Inode bitmap not in group (block %llu)",
(unsigned long long)input->inode_bitmap);
else if (outside(input->inode_table, start, end) ||
outside(itend - 1, start, end))
- ext4_warning(sb, __func__,
- "Inode table not in group (blocks %llu-%llu)",
+ ext4_warning(sb, "Inode table not in group (blocks %llu-%llu)",
(unsigned long long)input->inode_table, itend - 1);
else if (input->inode_bitmap == input->block_bitmap)
- ext4_warning(sb, __func__,
- "Block bitmap same as inode bitmap (%llu)",
+ ext4_warning(sb, "Block bitmap same as inode bitmap (%llu)",
(unsigned long long)input->block_bitmap);
else if (inside(input->block_bitmap, input->inode_table, itend))
- ext4_warning(sb, __func__,
- "Block bitmap (%llu) in inode table (%llu-%llu)",
+ ext4_warning(sb, "Block bitmap (%llu) in inode table "
+ "(%llu-%llu)",
(unsigned long long)input->block_bitmap,
(unsigned long long)input->inode_table, itend - 1);
else if (inside(input->inode_bitmap, input->inode_table, itend))
- ext4_warning(sb, __func__,
- "Inode bitmap (%llu) in inode table (%llu-%llu)",
+ ext4_warning(sb, "Inode bitmap (%llu) in inode table "
+ "(%llu-%llu)",
(unsigned long long)input->inode_bitmap,
(unsigned long long)input->inode_table, itend - 1);
else if (inside(input->block_bitmap, start, metaend))
- ext4_warning(sb, __func__,
- "Block bitmap (%llu) in GDT table"
- " (%llu-%llu)",
+ ext4_warning(sb, "Block bitmap (%llu) in GDT table (%llu-%llu)",
(unsigned long long)input->block_bitmap,
start, metaend - 1);
else if (inside(input->inode_bitmap, start, metaend))
- ext4_warning(sb, __func__,
- "Inode bitmap (%llu) in GDT table"
- " (%llu-%llu)",
+ ext4_warning(sb, "Inode bitmap (%llu) in GDT table (%llu-%llu)",
(unsigned long long)input->inode_bitmap,
start, metaend - 1);
else if (inside(input->inode_table, start, metaend) ||
inside(itend - 1, start, metaend))
- ext4_warning(sb, __func__,
- "Inode table (%llu-%llu) overlaps"
- "GDT table (%llu-%llu)",
+ ext4_warning(sb, "Inode table (%llu-%llu) overlaps GDT table "
+ "(%llu-%llu)",
(unsigned long long)input->inode_table,
itend - 1, start, metaend - 1);
else
@@ -247,7 +236,7 @@ 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);
@@ -364,8 +353,7 @@ static int verify_reserved_gdb(struct super_block *sb,
while ((grp = ext4_list_backups(sb, &three, &five, &seven)) < end) {
if (le32_to_cpu(*p++) !=
grp * EXT4_BLOCKS_PER_GROUP(sb) + blk){
- ext4_warning(sb, __func__,
- "reserved GDT %llu"
+ ext4_warning(sb, "reserved GDT %llu"
" missing grp %d (%llu)",
blk, grp,
grp *
@@ -420,8 +408,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
*/
if (EXT4_SB(sb)->s_sbh->b_blocknr !=
le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) {
- ext4_warning(sb, __func__,
- "won't resize using backup superblock at %llu",
+ ext4_warning(sb, "won't resize using backup superblock at %llu",
(unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr);
return -EPERM;
}
@@ -444,8 +431,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
data = (__le32 *)dind->b_data;
if (le32_to_cpu(data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)]) != gdblock) {
- ext4_warning(sb, __func__,
- "new group %u GDT block %llu not reserved",
+ ext4_warning(sb, "new group %u GDT block %llu not reserved",
input->group, gdblock);
err = -EINVAL;
goto exit_dind;
@@ -468,7 +454,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
GFP_NOFS);
if (!n_group_desc) {
err = -ENOMEM;
- ext4_warning(sb, __func__,
+ ext4_warning(sb,
"not enough memory for %lu groups", gdb_num + 1);
goto exit_inode;
}
@@ -567,8 +553,7 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
/* Get each reserved primary GDT block and verify it holds backups */
for (res = 0; res < reserved_gdb; res++, blk++) {
if (le32_to_cpu(*data) != blk) {
- ext4_warning(sb, __func__,
- "reserved block %llu"
+ ext4_warning(sb, "reserved block %llu"
" not at offset %ld",
blk,
(long)(data - (__le32 *)dind->b_data));
@@ -713,8 +698,7 @@ static void update_backups(struct super_block *sb,
*/
exit_err:
if (err) {
- ext4_warning(sb, __func__,
- "can't update backup for group %u (err %d), "
+ ext4_warning(sb, "can't update backup for group %u (err %d), "
"forcing fsck on next reboot", group, err);
sbi->s_mount_state &= ~EXT4_VALID_FS;
sbi->s_es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
@@ -753,20 +737,19 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
if (gdb_off == 0 && !EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
- ext4_warning(sb, __func__,
- "Can't resize non-sparse filesystem further");
+ ext4_warning(sb, "Can't resize non-sparse filesystem further");
return -EPERM;
}
if (ext4_blocks_count(es) + input->blocks_count <
ext4_blocks_count(es)) {
- ext4_warning(sb, __func__, "blocks_count overflow");
+ ext4_warning(sb, "blocks_count overflow");
return -EINVAL;
}
if (le32_to_cpu(es->s_inodes_count) + EXT4_INODES_PER_GROUP(sb) <
le32_to_cpu(es->s_inodes_count)) {
- ext4_warning(sb, __func__, "inodes_count overflow");
+ ext4_warning(sb, "inodes_count overflow");
return -EINVAL;
}
@@ -774,14 +757,13 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
if (!EXT4_HAS_COMPAT_FEATURE(sb,
EXT4_FEATURE_COMPAT_RESIZE_INODE)
|| !le16_to_cpu(es->s_reserved_gdt_blocks)) {
- ext4_warning(sb, __func__,
+ ext4_warning(sb,
"No reserved GDT blocks, can't resize");
return -EPERM;
}
inode = ext4_iget(sb, EXT4_RESIZE_INO);
if (IS_ERR(inode)) {
- ext4_warning(sb, __func__,
- "Error opening resize inode");
+ ext4_warning(sb, "Error opening resize inode");
return PTR_ERR(inode);
}
}
@@ -810,8 +792,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
mutex_lock(&sbi->s_resize_lock);
if (input->group != sbi->s_groups_count) {
- ext4_warning(sb, __func__,
- "multiple resizers run on filesystem!");
+ ext4_warning(sb, "multiple resizers run on filesystem!");
err = -EBUSY;
goto exit_journal;
}
@@ -997,13 +978,12 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
" too large to resize to %llu blocks safely\n",
sb->s_id, n_blocks_count);
if (sizeof(sector_t) < 8)
- ext4_warning(sb, __func__, "CONFIG_LBDAF not enabled");
+ ext4_warning(sb, "CONFIG_LBDAF not enabled");
return -EINVAL;
}
if (n_blocks_count < o_blocks_count) {
- ext4_warning(sb, __func__,
- "can't shrink FS - resize aborted");
+ ext4_warning(sb, "can't shrink FS - resize aborted");
return -EBUSY;
}
@@ -1011,15 +991,14 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
ext4_get_group_no_and_offset(sb, o_blocks_count, &group, &last);
if (last == 0) {
- ext4_warning(sb, __func__,
- "need to use ext2online to resize further");
+ ext4_warning(sb, "need to use ext2online to resize further");
return -EPERM;
}
add = EXT4_BLOCKS_PER_GROUP(sb) - last;
if (o_blocks_count + add < o_blocks_count) {
- ext4_warning(sb, __func__, "blocks_count overflow");
+ ext4_warning(sb, "blocks_count overflow");
return -EINVAL;
}
@@ -1027,16 +1006,13 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
add = n_blocks_count - o_blocks_count;
if (o_blocks_count + add < n_blocks_count)
- ext4_warning(sb, __func__,
- "will only finish group (%llu"
- " blocks, %u new)",
+ ext4_warning(sb, "will only finish group (%llu blocks, %u new)",
o_blocks_count + add, add);
/* See if the device is actually as big as what was requested */
bh = sb_bread(sb, o_blocks_count + add - 1);
if (!bh) {
- ext4_warning(sb, __func__,
- "can't read last block, resize aborted");
+ ext4_warning(sb, "can't read last block, resize aborted");
return -ENOSPC;
}
brelse(bh);
@@ -1047,14 +1023,13 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
handle = ext4_journal_start_sb(sb, 3);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
- ext4_warning(sb, __func__, "error %d on journal start", err);
+ ext4_warning(sb, "error %d on journal start", err);
goto exit_put;
}
mutex_lock(&EXT4_SB(sb)->s_resize_lock);
if (o_blocks_count != ext4_blocks_count(es)) {
- ext4_warning(sb, __func__,
- "multiple resizers run on filesystem!");
+ ext4_warning(sb, "multiple resizers run on filesystem!");
mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
ext4_journal_stop(handle);
err = -EBUSY;
@@ -1063,8 +1038,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
if ((err = ext4_journal_get_write_access(handle,
EXT4_SB(sb)->s_sbh))) {
- ext4_warning(sb, __func__,
- "error %d on journal write access", err);
+ ext4_warning(sb, "error %d on journal write access", err);
mutex_unlock(&EXT4_SB(sb)->s_resize_lock);
ext4_journal_stop(handle);
goto exit_put;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index d4ca92aab51..ba191dae873 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -302,7 +302,7 @@ void ext4_journal_abort_handle(const char *caller, const char *err_fn,
* write out the superblock safely.
*
* We'll just use the jbd2_journal_abort() error code to record an error in
- * the journal instead. On recovery, the journal will compain about
+ * the journal instead. On recovery, the journal will complain about
* that error until we've noted it down and cleared it.
*/
@@ -333,7 +333,7 @@ static void ext4_handle_error(struct super_block *sb)
sb->s_id);
}
-void ext4_error(struct super_block *sb, const char *function,
+void __ext4_error(struct super_block *sb, const char *function,
const char *fmt, ...)
{
va_list args;
@@ -347,6 +347,42 @@ void ext4_error(struct super_block *sb, const char *function,
ext4_handle_error(sb);
}
+void ext4_error_inode(const char *function, struct inode *inode,
+ const char *fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s: inode #%lu: (comm %s) ",
+ inode->i_sb->s_id, function, inode->i_ino, current->comm);
+ vprintk(fmt, args);
+ printk("\n");
+ va_end(args);
+
+ ext4_handle_error(inode->i_sb);
+}
+
+void ext4_error_file(const char *function, struct file *file,
+ const char *fmt, ...)
+{
+ va_list args;
+ struct inode *inode = file->f_dentry->d_inode;
+ char pathname[80], *path;
+
+ va_start(args, fmt);
+ path = d_path(&(file->f_path), pathname, sizeof(pathname));
+ if (!path)
+ path = "(unknown)";
+ printk(KERN_CRIT
+ "EXT4-fs error (device %s): %s: inode #%lu (comm %s path %s): ",
+ inode->i_sb->s_id, function, inode->i_ino, current->comm, path);
+ vprintk(fmt, args);
+ printk("\n");
+ va_end(args);
+
+ ext4_handle_error(inode->i_sb);
+}
+
static const char *ext4_decode_error(struct super_block *sb, int errno,
char nbuf[16])
{
@@ -450,7 +486,7 @@ void ext4_msg (struct super_block * sb, const char *prefix,
va_end(args);
}
-void ext4_warning(struct super_block *sb, const char *function,
+void __ext4_warning(struct super_block *sb, const char *function,
const char *fmt, ...)
{
va_list args;
@@ -507,7 +543,7 @@ void ext4_update_dynamic_rev(struct super_block *sb)
if (le32_to_cpu(es->s_rev_level) > EXT4_GOOD_OLD_REV)
return;
- ext4_warning(sb, __func__,
+ ext4_warning(sb,
"updating to rev %d because of new feature flag, "
"running e2fsck is recommended",
EXT4_DYNAMIC_REV);
@@ -603,10 +639,6 @@ 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 +646,12 @@ 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 +738,17 @@ 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));
- INIT_LIST_HEAD(&ei->i_aio_dio_complete_list);
+#ifdef CONFIG_QUOTA
+ ei->i_reserved_quota = 0;
+#endif
+ INIT_LIST_HEAD(&ei->i_completed_io_list);
+ spin_lock_init(&ei->i_completed_io_lock);
ei->cur_aio_dio = NULL;
+ ei->i_sync_tid = 0;
+ ei->i_datasync_tid = 0;
return &ei->vfs_inode;
}
@@ -753,6 +798,7 @@ static void destroy_inodecache(void)
static void ext4_clear_inode(struct inode *inode)
{
+ dquot_drop(inode);
ext4_discard_preallocations(inode);
if (EXT4_JOURNAL(inode))
jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
@@ -765,9 +811,22 @@ static inline void ext4_show_quota_options(struct seq_file *seq,
#if defined(CONFIG_QUOTA)
struct ext4_sb_info *sbi = EXT4_SB(sb);
- if (sbi->s_jquota_fmt)
- seq_printf(seq, ",jqfmt=%s",
- (sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold" : "vfsv0");
+ if (sbi->s_jquota_fmt) {
+ char *fmtname = "";
+
+ switch (sbi->s_jquota_fmt) {
+ case QFMT_VFS_OLD:
+ fmtname = "vfsold";
+ break;
+ case QFMT_VFS_V0:
+ fmtname = "vfsv0";
+ break;
+ case QFMT_VFS_V1:
+ fmtname = "vfsv1";
+ break;
+ }
+ seq_printf(seq, ",jqfmt=%s", fmtname);
+ }
if (sbi->s_qf_names[USRQUOTA])
seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]);
@@ -775,10 +834,10 @@ static inline void ext4_show_quota_options(struct seq_file *seq,
if (sbi->s_qf_names[GRPQUOTA])
seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]);
- if (sbi->s_mount_opt & EXT4_MOUNT_USRQUOTA)
+ if (test_opt(sb, USRQUOTA))
seq_puts(seq, ",usrquota");
- if (sbi->s_mount_opt & EXT4_MOUNT_GRPQUOTA)
+ if (test_opt(sb, GRPQUOTA))
seq_puts(seq, ",grpquota");
#endif
}
@@ -899,6 +958,15 @@ 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");
+
+ if (test_opt(sb, DIOREAD_NOLOCK))
+ seq_puts(seq, ",dioread_nolock");
+
ext4_show_quota_options(seq, sb);
return 0;
@@ -985,17 +1053,9 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
const char *data, size_t len, loff_t off);
static const struct dquot_operations ext4_quota_operations = {
- .initialize = dquot_initialize,
- .drop = dquot_drop,
- .alloc_space = dquot_alloc_space,
- .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,
- .alloc_inode = dquot_alloc_inode,
- .free_space = dquot_free_space,
- .free_inode = dquot_free_inode,
- .transfer = dquot_transfer,
+#endif
.write_dquot = ext4_write_dquot,
.acquire_dquot = ext4_acquire_dquot,
.release_dquot = ext4_release_dquot,
@@ -1074,12 +1134,14 @@ enum {
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
Opt_data_err_abort, Opt_data_err_ignore,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
- Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
- Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err, Opt_resize,
- Opt_usrquota, Opt_grpquota, Opt_i_version,
+ Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
+ Opt_noquota, Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err,
+ Opt_resize, Opt_usrquota, Opt_grpquota, Opt_i_version,
Opt_stripe, Opt_delalloc, Opt_nodelalloc,
Opt_block_validity, Opt_noblock_validity,
- Opt_inode_readahead_blks, Opt_journal_ioprio
+ Opt_inode_readahead_blks, Opt_journal_ioprio,
+ Opt_dioread_nolock, Opt_dioread_lock,
+ Opt_discard, Opt_nodiscard,
};
static const match_table_t tokens = {
@@ -1104,6 +1166,7 @@ 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"},
@@ -1125,6 +1188,7 @@ static const match_table_t tokens = {
{Opt_grpjquota, "grpjquota=%s"},
{Opt_jqfmt_vfsold, "jqfmt=vfsold"},
{Opt_jqfmt_vfsv0, "jqfmt=vfsv0"},
+ {Opt_jqfmt_vfsv1, "jqfmt=vfsv1"},
{Opt_grpquota, "grpquota"},
{Opt_noquota, "noquota"},
{Opt_quota, "quota"},
@@ -1144,6 +1208,10 @@ 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_dioread_nolock, "dioread_nolock"},
+ {Opt_dioread_lock, "dioread_lock"},
+ {Opt_discard, "discard"},
+ {Opt_nodiscard, "nodiscard"},
{Opt_err, NULL},
};
@@ -1171,6 +1239,66 @@ static ext4_fsblk_t get_sb_block(void **data)
}
#define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
+static char deprecated_msg[] = "Mount option \"%s\" will be removed by %s\n"
+ "Contact linux-ext4@vger.kernel.org if you think we should keep it.\n";
+
+#ifdef CONFIG_QUOTA
+static int set_qf_name(struct super_block *sb, int qtype, substring_t *args)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ char *qname;
+
+ if (sb_any_quota_loaded(sb) &&
+ !sbi->s_qf_names[qtype]) {
+ ext4_msg(sb, KERN_ERR,
+ "Cannot change journaled "
+ "quota options when quota turned on");
+ return 0;
+ }
+ qname = match_strdup(args);
+ if (!qname) {
+ ext4_msg(sb, KERN_ERR,
+ "Not enough memory for storing quotafile name");
+ return 0;
+ }
+ if (sbi->s_qf_names[qtype] &&
+ strcmp(sbi->s_qf_names[qtype], qname)) {
+ ext4_msg(sb, KERN_ERR,
+ "%s quota file already specified", QTYPE2NAME(qtype));
+ kfree(qname);
+ return 0;
+ }
+ sbi->s_qf_names[qtype] = qname;
+ if (strchr(sbi->s_qf_names[qtype], '/')) {
+ ext4_msg(sb, KERN_ERR,
+ "quotafile must be on filesystem root");
+ kfree(sbi->s_qf_names[qtype]);
+ sbi->s_qf_names[qtype] = NULL;
+ return 0;
+ }
+ set_opt(sbi->s_mount_opt, QUOTA);
+ return 1;
+}
+
+static int clear_qf_name(struct super_block *sb, int qtype)
+{
+
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ if (sb_any_quota_loaded(sb) &&
+ sbi->s_qf_names[qtype]) {
+ ext4_msg(sb, KERN_ERR, "Cannot change journaled quota options"
+ " when quota turned on");
+ return 0;
+ }
+ /*
+ * The space will be released later when all options are confirmed
+ * to be correct
+ */
+ sbi->s_qf_names[qtype] = NULL;
+ return 1;
+}
+#endif
static int parse_options(char *options, struct super_block *sb,
unsigned long *journal_devnum,
@@ -1183,8 +1311,7 @@ static int parse_options(char *options, struct super_block *sb,
int data_opt = 0;
int option;
#ifdef CONFIG_QUOTA
- int qtype, qfmt;
- char *qname;
+ int qfmt;
#endif
if (!options)
@@ -1195,19 +1322,31 @@ 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:
+ ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
clear_opt(sbi->s_mount_opt, MINIX_DF);
break;
case Opt_minix_df:
+ ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
set_opt(sbi->s_mount_opt, MINIX_DF);
+
break;
case Opt_grpid:
+ ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
set_opt(sbi->s_mount_opt, GRPID);
+
break;
case Opt_nogrpid:
+ ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
clear_opt(sbi->s_mount_opt, GRPID);
+
break;
case Opt_resuid:
if (match_int(&args[0], &option))
@@ -1344,14 +1483,13 @@ static int parse_options(char *options, struct super_block *sb,
data_opt = EXT4_MOUNT_WRITEBACK_DATA;
datacheck:
if (is_remount) {
- if ((sbi->s_mount_opt & EXT4_MOUNT_DATA_FLAGS)
- != data_opt) {
+ if (test_opt(sb, DATA_FLAGS) != data_opt) {
ext4_msg(sb, KERN_ERR,
"Cannot change data mode on remount");
return 0;
}
} else {
- sbi->s_mount_opt &= ~EXT4_MOUNT_DATA_FLAGS;
+ clear_opt(sbi->s_mount_opt, DATA_FLAGS);
sbi->s_mount_opt |= data_opt;
}
break;
@@ -1363,68 +1501,30 @@ static int parse_options(char *options, struct super_block *sb,
break;
#ifdef CONFIG_QUOTA
case Opt_usrjquota:
- qtype = USRQUOTA;
- goto set_qf_name;
- case Opt_grpjquota:
- qtype = GRPQUOTA;
-set_qf_name:
- if (sb_any_quota_loaded(sb) &&
- !sbi->s_qf_names[qtype]) {
- ext4_msg(sb, KERN_ERR,
- "Cannot change journaled "
- "quota options when quota turned on");
+ if (!set_qf_name(sb, USRQUOTA, &args[0]))
return 0;
- }
- qname = match_strdup(&args[0]);
- if (!qname) {
- ext4_msg(sb, KERN_ERR,
- "Not enough memory for "
- "storing quotafile name");
- return 0;
- }
- if (sbi->s_qf_names[qtype] &&
- strcmp(sbi->s_qf_names[qtype], qname)) {
- ext4_msg(sb, KERN_ERR,
- "%s quota file already "
- "specified", QTYPE2NAME(qtype));
- kfree(qname);
- return 0;
- }
- sbi->s_qf_names[qtype] = qname;
- if (strchr(sbi->s_qf_names[qtype], '/')) {
- ext4_msg(sb, KERN_ERR,
- "quotafile must be on "
- "filesystem root");
- kfree(sbi->s_qf_names[qtype]);
- sbi->s_qf_names[qtype] = NULL;
+ break;
+ case Opt_grpjquota:
+ if (!set_qf_name(sb, GRPQUOTA, &args[0]))
return 0;
- }
- set_opt(sbi->s_mount_opt, QUOTA);
break;
case Opt_offusrjquota:
- qtype = USRQUOTA;
- goto clear_qf_name;
+ if (!clear_qf_name(sb, USRQUOTA))
+ return 0;
+ break;
case Opt_offgrpjquota:
- qtype = GRPQUOTA;
-clear_qf_name:
- if (sb_any_quota_loaded(sb) &&
- sbi->s_qf_names[qtype]) {
- ext4_msg(sb, KERN_ERR, "Cannot change "
- "journaled quota options when "
- "quota turned on");
+ if (!clear_qf_name(sb, GRPQUOTA))
return 0;
- }
- /*
- * The space will be released later when all options
- * are confirmed to be correct
- */
- sbi->s_qf_names[qtype] = NULL;
break;
+
case Opt_jqfmt_vfsold:
qfmt = QFMT_VFS_OLD;
goto set_qf_format;
case Opt_jqfmt_vfsv0:
qfmt = QFMT_VFS_V0;
+ goto set_qf_format;
+ case Opt_jqfmt_vfsv1:
+ qfmt = QFMT_VFS_V1;
set_qf_format:
if (sb_any_quota_loaded(sb) &&
sbi->s_jquota_fmt != qfmt) {
@@ -1467,6 +1567,7 @@ set_qf_format:
case Opt_offgrpjquota:
case Opt_jqfmt_vfsold:
case Opt_jqfmt_vfsv0:
+ case Opt_jqfmt_vfsv1:
ext4_msg(sb, KERN_ERR,
"journaled quota options not supported");
break;
@@ -1480,10 +1581,11 @@ 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 +1658,28 @@ 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;
+ case Opt_dioread_nolock:
+ set_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ break;
+ case Opt_dioread_lock:
+ clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ break;
default:
ext4_msg(sb, KERN_ERR,
"Unrecognized mount option \"%s\" "
@@ -1574,18 +1689,13 @@ set_qf_format:
}
#ifdef CONFIG_QUOTA
if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
- if ((sbi->s_mount_opt & EXT4_MOUNT_USRQUOTA) &&
- sbi->s_qf_names[USRQUOTA])
+ if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
clear_opt(sbi->s_mount_opt, USRQUOTA);
- if ((sbi->s_mount_opt & EXT4_MOUNT_GRPQUOTA) &&
- sbi->s_qf_names[GRPQUOTA])
+ if (test_opt(sb, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA])
clear_opt(sbi->s_mount_opt, GRPQUOTA);
- if ((sbi->s_qf_names[USRQUOTA] &&
- (sbi->s_mount_opt & EXT4_MOUNT_GRPQUOTA)) ||
- (sbi->s_qf_names[GRPQUOTA] &&
- (sbi->s_mount_opt & EXT4_MOUNT_USRQUOTA))) {
+ if (test_opt(sb, GRPQUOTA) || test_opt(sb, USRQUOTA)) {
ext4_msg(sb, KERN_ERR, "old and new quota "
"format mixing");
return 0;
@@ -1673,14 +1783,14 @@ 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) <<
@@ -1895,7 +2005,7 @@ static void ext4_orphan_cleanup(struct super_block *sb,
}
list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
- vfs_dq_init(inode);
+ dquot_initialize(inode);
if (inode->i_nlink) {
ext4_msg(sb, KERN_DEBUG,
"%s: truncating inode %lu to %lld bytes",
@@ -2099,11 +2209,8 @@ static int parse_strtoul(const char *buf,
{
char *endp;
- while (*buf && isspace(*buf))
- buf++;
- *value = simple_strtoul(buf, &endp, 0);
- while (*endp && isspace(*endp))
- endp++;
+ *value = simple_strtoul(skip_spaces(buf), &endp, 0);
+ endp = skip_spaces(endp);
if (*endp || *value > max)
return -EINVAL;
@@ -2134,9 +2241,9 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_attr *a,
struct super_block *sb = sbi->s_buddy_cache->i_sb;
return snprintf(buf, PAGE_SIZE, "%llu\n",
- sbi->s_kbytes_written +
+ (unsigned long long)(sbi->s_kbytes_written +
((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
- EXT4_SB(sb)->s_sectors_written_start) >> 1));
+ EXT4_SB(sb)->s_sectors_written_start) >> 1)));
}
static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
@@ -2251,7 +2358,7 @@ static void ext4_sb_release(struct kobject *kobj)
}
-static struct sysfs_ops ext4_attr_ops = {
+static const struct sysfs_ops ext4_attr_ops = {
.show = ext4_attr_show,
.store = ext4_attr_store,
};
@@ -2391,8 +2498,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
if (def_mount_opts & EXT4_DEFM_DEBUG)
set_opt(sbi->s_mount_opt, DEBUG);
- if (def_mount_opts & EXT4_DEFM_BSDGROUPS)
+ if (def_mount_opts & EXT4_DEFM_BSDGROUPS) {
+ ext4_msg(sb, KERN_WARNING, deprecated_msg, "bsdgroups",
+ "2.6.38");
set_opt(sbi->s_mount_opt, GRPID);
+ }
if (def_mount_opts & EXT4_DEFM_UID16)
set_opt(sbi->s_mount_opt, NO_UID32);
#ifdef CONFIG_EXT4_FS_XATTR
@@ -2404,11 +2514,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
set_opt(sbi->s_mount_opt, POSIX_ACL);
#endif
if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
- sbi->s_mount_opt |= EXT4_MOUNT_JOURNAL_DATA;
+ set_opt(sbi->s_mount_opt, JOURNAL_DATA);
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
- sbi->s_mount_opt |= EXT4_MOUNT_ORDERED_DATA;
+ set_opt(sbi->s_mount_opt, ORDERED_DATA);
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_WBACK)
- sbi->s_mount_opt |= EXT4_MOUNT_WRITEBACK_DATA;
+ set_opt(sbi->s_mount_opt, WRITEBACK_DATA);
if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_PANIC)
set_opt(sbi->s_mount_opt, ERRORS_PANIC);
@@ -2436,7 +2546,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount;
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
- ((sbi->s_mount_opt & EXT4_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
+ (test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV &&
(EXT4_HAS_COMPAT_FEATURE(sb, ~0U) ||
@@ -2721,31 +2831,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
if (ext4_load_journal(sb, es, journal_devnum))
goto failed_mount3;
- if (!(sb->s_flags & MS_RDONLY) &&
- EXT4_SB(sb)->s_journal->j_failed_commit) {
- ext4_msg(sb, KERN_CRIT, "error: "
- "ext4_fill_super: Journal transaction "
- "%u is corrupt",
- EXT4_SB(sb)->s_journal->j_failed_commit);
- if (test_opt(sb, ERRORS_RO)) {
- ext4_msg(sb, KERN_CRIT,
- "Mounting filesystem read-only");
- sb->s_flags |= MS_RDONLY;
- EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
- es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
- }
- if (test_opt(sb, ERRORS_PANIC)) {
- EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
- es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
- ext4_commit_super(sb, 1);
- goto failed_mount4;
- }
- }
} else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
ext4_msg(sb, KERN_ERR, "required journal recovery "
"suppressed and not mounted read-only");
- goto failed_mount4;
+ goto failed_mount_wq;
} else {
clear_opt(sbi->s_mount_opt, DATA_FLAGS);
set_opt(sbi->s_mount_opt, WRITEBACK_DATA);
@@ -2758,7 +2848,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
!jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_64BIT)) {
ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature");
- goto failed_mount4;
+ goto failed_mount_wq;
}
if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
@@ -2797,7 +2887,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) {
ext4_msg(sb, KERN_ERR, "Journal does not support "
"requested data journaling mode");
- goto failed_mount4;
+ goto failed_mount_wq;
}
default:
break;
@@ -2805,13 +2895,17 @@ 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:
-
if (test_opt(sb, NOBH)) {
if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) {
ext4_msg(sb, KERN_WARNING, "Ignoring nobh option - "
"its supported only with writeback mode");
clear_opt(sbi->s_mount_opt, NOBH);
}
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ ext4_msg(sb, KERN_WARNING, "dioread_nolock option is "
+ "not supported with nobh mode");
+ goto failed_mount_wq;
+ }
}
EXT4_SB(sb)->dio_unwritten_wq = create_workqueue("ext4-dio-unwritten");
if (!EXT4_SB(sb)->dio_unwritten_wq) {
@@ -2876,6 +2970,18 @@ no_journal:
"requested data journaling mode");
clear_opt(sbi->s_mount_opt, DELALLOC);
}
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+ ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
+ "option - requested data journaling mode");
+ clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ }
+ if (sb->s_blocksize < PAGE_SIZE) {
+ ext4_msg(sb, KERN_WARNING, "Ignoring dioread_nolock "
+ "option - block size is too small");
+ clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ }
+ }
err = ext4_setup_system_zone(sb);
if (err) {
@@ -3339,10 +3445,9 @@ static void ext4_clear_journal_err(struct super_block *sb,
char nbuf[16];
errstr = ext4_decode_error(sb, j_errno, nbuf);
- ext4_warning(sb, __func__, "Filesystem error recorded "
+ ext4_warning(sb, "Filesystem error recorded "
"from previous mount: %s", errstr);
- ext4_warning(sb, __func__, "Marking fs in need of "
- "filesystem check.");
+ ext4_warning(sb, "Marking fs in need of filesystem check.");
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
@@ -3493,7 +3598,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
ext4_abort(sb, __func__, "Abort forced by user");
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
- ((sbi->s_mount_opt & EXT4_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
+ (test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
es = sbi->s_es;
@@ -3668,13 +3773,11 @@ 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));
@@ -3689,7 +3792,7 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
* Process 1 Process 2
* ext4_create() quota_sync()
* jbd2_journal_start() write_dquot()
- * vfs_dq_init() down(dqio_mutex)
+ * dquot_initialize() down(dqio_mutex)
* down(dqio_mutex) jbd2_journal_start()
*
*/
@@ -3898,9 +4001,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
int err = 0;
int offset = off & (sb->s_blocksize - 1);
- int tocopy;
int journal_quota = EXT4_SB(sb)->s_qf_names[type] != NULL;
- size_t towrite = len;
struct buffer_head *bh;
handle_t *handle = journal_current_handle();
@@ -3910,52 +4011,53 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
(unsigned long long)off, (unsigned long long)len);
return -EIO;
}
+ /*
+ * Since we account only one data block in transaction credits,
+ * then it is impossible to cross a block boundary.
+ */
+ if (sb->s_blocksize - offset < len) {
+ ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)"
+ " cancelled because not block aligned",
+ (unsigned long long)off, (unsigned long long)len);
+ return -EIO;
+ }
+
mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
- while (towrite > 0) {
- tocopy = sb->s_blocksize - offset < towrite ?
- sb->s_blocksize - offset : towrite;
- bh = ext4_bread(handle, inode, blk, 1, &err);
- if (!bh)
+ bh = ext4_bread(handle, inode, blk, 1, &err);
+ if (!bh)
+ goto out;
+ if (journal_quota) {
+ err = ext4_journal_get_write_access(handle, bh);
+ if (err) {
+ brelse(bh);
goto out;
- if (journal_quota) {
- err = ext4_journal_get_write_access(handle, bh);
- if (err) {
- brelse(bh);
- goto out;
- }
}
- lock_buffer(bh);
- memcpy(bh->b_data+offset, data, tocopy);
- flush_dcache_page(bh->b_page);
- unlock_buffer(bh);
- if (journal_quota)
- err = ext4_handle_dirty_metadata(handle, NULL, bh);
- else {
- /* Always do at least ordered writes for quotas */
- err = ext4_jbd2_file_inode(handle, inode);
- mark_buffer_dirty(bh);
- }
- brelse(bh);
- if (err)
- goto out;
- offset = 0;
- towrite -= tocopy;
- data += tocopy;
- blk++;
}
+ lock_buffer(bh);
+ memcpy(bh->b_data+offset, data, len);
+ flush_dcache_page(bh->b_page);
+ unlock_buffer(bh);
+ if (journal_quota)
+ err = ext4_handle_dirty_metadata(handle, NULL, bh);
+ else {
+ /* Always do at least ordered writes for quotas */
+ err = ext4_jbd2_file_inode(handle, inode);
+ mark_buffer_dirty(bh);
+ }
+ brelse(bh);
out:
- if (len == towrite) {
+ if (err) {
mutex_unlock(&inode->i_mutex);
return err;
}
- if (inode->i_size < off+len-towrite) {
- i_size_write(inode, off+len-towrite);
+ if (inode->i_size < off + len) {
+ i_size_write(inode, off + len);
EXT4_I(inode)->i_disksize = inode->i_size;
}
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
ext4_mark_inode_dirty(handle, inode);
mutex_unlock(&inode->i_mutex);
- return len - towrite;
+ return len;
}
#endif
@@ -3966,6 +4068,60 @@ static int ext4_get_sb(struct file_system_type *fs_type, int flags,
return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt);
}
+#if !defined(CONTIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
+static struct file_system_type ext2_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "ext2",
+ .get_sb = ext4_get_sb,
+ .kill_sb = kill_block_super,
+ .fs_flags = FS_REQUIRES_DEV,
+};
+
+static inline void register_as_ext2(void)
+{
+ int err = register_filesystem(&ext2_fs_type);
+ if (err)
+ printk(KERN_WARNING
+ "EXT4-fs: Unable to register as ext2 (%d)\n", err);
+}
+
+static inline void unregister_as_ext2(void)
+{
+ unregister_filesystem(&ext2_fs_type);
+}
+MODULE_ALIAS("ext2");
+#else
+static inline void register_as_ext2(void) { }
+static inline void unregister_as_ext2(void) { }
+#endif
+
+#if !defined(CONTIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
+static struct file_system_type ext3_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "ext3",
+ .get_sb = ext4_get_sb,
+ .kill_sb = kill_block_super,
+ .fs_flags = FS_REQUIRES_DEV,
+};
+
+static inline void register_as_ext3(void)
+{
+ int err = register_filesystem(&ext3_fs_type);
+ if (err)
+ printk(KERN_WARNING
+ "EXT4-fs: Unable to register as ext3 (%d)\n", err);
+}
+
+static inline void unregister_as_ext3(void)
+{
+ unregister_filesystem(&ext3_fs_type);
+}
+MODULE_ALIAS("ext3");
+#else
+static inline void register_as_ext3(void) { }
+static inline void unregister_as_ext3(void) { }
+#endif
+
static struct file_system_type ext4_fs_type = {
.owner = THIS_MODULE,
.name = "ext4",
@@ -3995,11 +4151,15 @@ static int __init init_ext4_fs(void)
err = init_inodecache();
if (err)
goto out1;
+ register_as_ext2();
+ register_as_ext3();
err = register_filesystem(&ext4_fs_type);
if (err)
goto out;
return 0;
out:
+ unregister_as_ext2();
+ unregister_as_ext3();
destroy_inodecache();
out1:
exit_ext4_xattr();
@@ -4015,6 +4175,8 @@ out4:
static void __exit exit_ext4_fs(void)
{
+ unregister_as_ext2();
+ unregister_as_ext3();
unregister_filesystem(&ext4_fs_type);
destroy_inodecache();
exit_ext4_xattr();
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index fed5b01d7a8..b4c5aa8489d 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -92,7 +92,7 @@ static struct buffer_head *ext4_xattr_cache_find(struct inode *,
struct mb_cache_entry **);
static void ext4_xattr_rehash(struct ext4_xattr_header *,
struct ext4_xattr_entry *);
-static int ext4_xattr_list(struct inode *inode, char *buffer,
+static int ext4_xattr_list(struct dentry *dentry, char *buffer,
size_t buffer_size);
static struct mb_cache *ext4_xattr_cache;
@@ -140,7 +140,7 @@ ext4_xattr_handler(int name_index)
ssize_t
ext4_listxattr(struct dentry *dentry, char *buffer, size_t size)
{
- return ext4_xattr_list(dentry->d_inode, buffer, size);
+ return ext4_xattr_list(dentry, buffer, size);
}
static int
@@ -227,7 +227,8 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
ea_bdebug(bh, "b_count=%d, refcount=%d",
atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
if (ext4_xattr_check_block(bh)) {
-bad_block: ext4_error(inode->i_sb, __func__,
+bad_block:
+ ext4_error(inode->i_sb,
"inode %lu: bad block %llu", inode->i_ino,
EXT4_I(inode)->i_file_acl);
error = -EIO;
@@ -267,7 +268,7 @@ 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)
@@ -325,7 +326,7 @@ ext4_xattr_get(struct inode *inode, int name_index, const char *name,
}
static int
-ext4_xattr_list_entries(struct inode *inode, struct ext4_xattr_entry *entry,
+ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry,
char *buffer, size_t buffer_size)
{
size_t rest = buffer_size;
@@ -335,9 +336,10 @@ ext4_xattr_list_entries(struct inode *inode, struct ext4_xattr_entry *entry,
ext4_xattr_handler(entry->e_name_index);
if (handler) {
- size_t size = handler->list(inode, buffer, rest,
+ size_t size = handler->list(dentry, buffer, rest,
entry->e_name,
- entry->e_name_len);
+ entry->e_name_len,
+ handler->flags);
if (buffer) {
if (size > rest)
return -ERANGE;
@@ -350,8 +352,9 @@ ext4_xattr_list_entries(struct inode *inode, struct ext4_xattr_entry *entry,
}
static int
-ext4_xattr_block_list(struct inode *inode, char *buffer, size_t buffer_size)
+ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
+ struct inode *inode = dentry->d_inode;
struct buffer_head *bh = NULL;
int error;
@@ -369,14 +372,14 @@ ext4_xattr_block_list(struct inode *inode, char *buffer, size_t buffer_size)
ea_bdebug(bh, "b_count=%d, refcount=%d",
atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
if (ext4_xattr_check_block(bh)) {
- ext4_error(inode->i_sb, __func__,
+ ext4_error(inode->i_sb,
"inode %lu: bad block %llu", inode->i_ino,
EXT4_I(inode)->i_file_acl);
error = -EIO;
goto cleanup;
}
ext4_xattr_cache_insert(bh);
- error = ext4_xattr_list_entries(inode, BFIRST(bh), buffer, buffer_size);
+ error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size);
cleanup:
brelse(bh);
@@ -385,15 +388,16 @@ cleanup:
}
static int
-ext4_xattr_ibody_list(struct inode *inode, char *buffer, size_t buffer_size)
+ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
+ struct inode *inode = dentry->d_inode;
struct ext4_xattr_ibody_header *header;
struct ext4_inode *raw_inode;
struct ext4_iloc iloc;
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)
@@ -404,7 +408,7 @@ ext4_xattr_ibody_list(struct inode *inode, char *buffer, size_t buffer_size)
error = ext4_xattr_check_names(IFIRST(header), end);
if (error)
goto cleanup;
- error = ext4_xattr_list_entries(inode, IFIRST(header),
+ error = ext4_xattr_list_entries(dentry, IFIRST(header),
buffer, buffer_size);
cleanup:
@@ -423,12 +427,12 @@ cleanup:
* used / required on success.
*/
static int
-ext4_xattr_list(struct inode *inode, char *buffer, size_t buffer_size)
+ext4_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
int i_error, b_error;
- down_read(&EXT4_I(inode)->xattr_sem);
- i_error = ext4_xattr_ibody_list(inode, buffer, buffer_size);
+ down_read(&EXT4_I(dentry->d_inode)->xattr_sem);
+ i_error = ext4_xattr_ibody_list(dentry, buffer, buffer_size);
if (i_error < 0) {
b_error = 0;
} else {
@@ -436,11 +440,11 @@ ext4_xattr_list(struct inode *inode, char *buffer, size_t buffer_size)
buffer += i_error;
buffer_size -= i_error;
}
- b_error = ext4_xattr_block_list(inode, buffer, buffer_size);
+ b_error = ext4_xattr_block_list(dentry, buffer, buffer_size);
if (b_error < 0)
i_error = 0;
}
- up_read(&EXT4_I(inode)->xattr_sem);
+ up_read(&EXT4_I(dentry->d_inode)->xattr_sem);
return i_error + b_error;
}
@@ -482,15 +486,16 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
ea_bdebug(bh, "refcount now=0; freeing");
if (ce)
mb_cache_entry_free(ce);
- ext4_free_blocks(handle, inode, bh->b_blocknr, 1, 1);
get_bh(bh);
- ext4_forget(handle, 1, inode, bh, bh->b_blocknr);
+ ext4_free_blocks(handle, inode, bh, 0, 1,
+ EXT4_FREE_BLOCKS_METADATA |
+ EXT4_FREE_BLOCKS_FORGET);
} else {
le32_add_cpu(&BHDR(bh)->h_refcount, -1);
error = ext4_handle_dirty_metadata(handle, inode, bh);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
- vfs_dq_free_block(inode, 1);
+ dquot_free_block(inode, 1);
ea_bdebug(bh, "refcount now=%d; releasing",
le32_to_cpu(BHDR(bh)->h_refcount));
if (ce)
@@ -661,9 +666,8 @@ ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i,
atomic_read(&(bs->bh->b_count)),
le32_to_cpu(BHDR(bs->bh)->h_refcount));
if (ext4_xattr_check_block(bs->bh)) {
- ext4_error(sb, __func__,
- "inode %lu: bad block %llu", inode->i_ino,
- EXT4_I(inode)->i_file_acl);
+ ext4_error(sb, "inode %lu: bad block %llu",
+ inode->i_ino, EXT4_I(inode)->i_file_acl);
error = -EIO;
goto cleanup;
}
@@ -783,8 +787,8 @@ inserted:
else {
/* The old block is released after updating
the inode. */
- error = -EDQUOT;
- if (vfs_dq_alloc_block(inode, 1))
+ error = dquot_alloc_block(inode, 1);
+ if (error)
goto cleanup;
error = ext4_journal_get_write_access(handle,
new_bh);
@@ -832,7 +836,8 @@ inserted:
new_bh = sb_getblk(sb, block);
if (!new_bh) {
getblk_failed:
- ext4_free_blocks(handle, inode, block, 1, 1);
+ ext4_free_blocks(handle, inode, 0, block, 1,
+ EXT4_FREE_BLOCKS_METADATA);
error = -EIO;
goto cleanup;
}
@@ -871,13 +876,12 @@ cleanup:
return error;
cleanup_dquot:
- vfs_dq_free_block(inode, 1);
+ dquot_free_block(inode, 1);
goto cleanup;
bad_block:
- ext4_error(inode->i_sb, __func__,
- "inode %lu: bad block %llu", inode->i_ino,
- EXT4_I(inode)->i_file_acl);
+ ext4_error(inode->i_sb, "inode %lu: bad block %llu",
+ inode->i_ino, EXT4_I(inode)->i_file_acl);
goto cleanup;
#undef header
@@ -903,7 +907,7 @@ 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 +939,10 @@ 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 +985,21 @@ 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 +1021,6 @@ 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 +1051,7 @@ 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 +1066,7 @@ 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;
}
@@ -1189,9 +1194,8 @@ retry:
if (!bh)
goto cleanup;
if (ext4_xattr_check_block(bh)) {
- ext4_error(inode->i_sb, __func__,
- "inode %lu: bad block %llu", inode->i_ino,
- EXT4_I(inode)->i_file_acl);
+ ext4_error(inode->i_sb, "inode %lu: bad block %llu",
+ inode->i_ino, EXT4_I(inode)->i_file_acl);
error = -EIO;
goto cleanup;
}
@@ -1296,6 +1300,8 @@ retry:
/* Remove the chosen entry from the inode */
error = ext4_xattr_ibody_set(handle, inode, &i, is);
+ if (error)
+ goto cleanup;
entry = IFIRST(header);
if (entry_size + EXT4_XATTR_SIZE(size) >= new_extra_isize)
@@ -1326,6 +1332,8 @@ retry:
goto cleanup;
kfree(b_entry_name);
kfree(buffer);
+ b_entry_name = NULL;
+ buffer = NULL;
brelse(is->iloc.bh);
kfree(is);
kfree(bs);
@@ -1364,16 +1372,14 @@ ext4_xattr_delete_inode(handle_t *handle, struct inode *inode)
goto cleanup;
bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
if (!bh) {
- ext4_error(inode->i_sb, __func__,
- "inode %lu: block %llu read error", inode->i_ino,
- EXT4_I(inode)->i_file_acl);
+ ext4_error(inode->i_sb, "inode %lu: block %llu read error",
+ inode->i_ino, EXT4_I(inode)->i_file_acl);
goto cleanup;
}
if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
BHDR(bh)->h_blocks != cpu_to_le32(1)) {
- ext4_error(inode->i_sb, __func__,
- "inode %lu: bad block %llu", inode->i_ino,
- EXT4_I(inode)->i_file_acl);
+ ext4_error(inode->i_sb, "inode %lu: bad block %llu",
+ inode->i_ino, EXT4_I(inode)->i_file_acl);
goto cleanup;
}
ext4_xattr_release_block(handle, inode, bh);
@@ -1498,7 +1504,7 @@ again:
}
bh = sb_bread(inode->i_sb, ce->e_block);
if (!bh) {
- ext4_error(inode->i_sb, __func__,
+ ext4_error(inode->i_sb,
"inode %lu: block %lu read error",
inode->i_ino, (unsigned long) ce->e_block);
} else if (le32_to_cpu(BHDR(bh)->h_refcount) >=
diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c
index ca5f89fc6ca..983c253999a 100644
--- a/fs/ext4/xattr_security.c
+++ b/fs/ext4/xattr_security.c
@@ -12,8 +12,8 @@
#include "xattr.h"
static size_t
-ext4_xattr_security_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext4_xattr_security_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const size_t prefix_len = sizeof(XATTR_SECURITY_PREFIX)-1;
const size_t total_len = prefix_len + name_len + 1;
@@ -28,23 +28,23 @@ ext4_xattr_security_list(struct inode *inode, char *list, size_t list_size,
}
static int
-ext4_xattr_security_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+ext4_xattr_security_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext4_xattr_get(inode, EXT4_XATTR_INDEX_SECURITY, name,
- buffer, size);
+ return ext4_xattr_get(dentry->d_inode, EXT4_XATTR_INDEX_SECURITY,
+ name, buffer, size);
}
static int
-ext4_xattr_security_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+ext4_xattr_security_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext4_xattr_set(inode, EXT4_XATTR_INDEX_SECURITY, name,
- value, size, flags);
+ return ext4_xattr_set(dentry->d_inode, EXT4_XATTR_INDEX_SECURITY,
+ name, value, size, flags);
}
int
diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c
index ac1a52cf2a3..15b50edc658 100644
--- a/fs/ext4/xattr_trusted.c
+++ b/fs/ext4/xattr_trusted.c
@@ -14,8 +14,8 @@
#include "xattr.h"
static size_t
-ext4_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext4_xattr_trusted_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;
@@ -32,23 +32,23 @@ ext4_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
}
static int
-ext4_xattr_trusted_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+ext4_xattr_trusted_get(struct dentry *dentry, const char *name, void *buffer,
+ size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext4_xattr_get(inode, EXT4_XATTR_INDEX_TRUSTED, name,
- buffer, size);
+ return ext4_xattr_get(dentry->d_inode, EXT4_XATTR_INDEX_TRUSTED,
+ name, buffer, size);
}
static int
-ext4_xattr_trusted_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+ext4_xattr_trusted_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext4_xattr_set(inode, EXT4_XATTR_INDEX_TRUSTED, name,
- value, size, flags);
+ return ext4_xattr_set(dentry->d_inode, EXT4_XATTR_INDEX_TRUSTED,
+ name, value, size, flags);
}
struct xattr_handler ext4_xattr_trusted_handler = {
diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c
index d91aa61b42a..c4ce05746ce 100644
--- a/fs/ext4/xattr_user.c
+++ b/fs/ext4/xattr_user.c
@@ -13,13 +13,13 @@
#include "xattr.h"
static size_t
-ext4_xattr_user_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext4_xattr_user_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const size_t prefix_len = XATTR_USER_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;
- if (!test_opt(inode->i_sb, XATTR_USER))
+ if (!test_opt(dentry->d_sb, XATTR_USER))
return 0;
if (list && total_len <= list_size) {
@@ -31,26 +31,27 @@ ext4_xattr_user_list(struct inode *inode, char *list, size_t list_size,
}
static int
-ext4_xattr_user_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+ext4_xattr_user_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- if (!test_opt(inode->i_sb, XATTR_USER))
+ if (!test_opt(dentry->d_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext4_xattr_get(inode, EXT4_XATTR_INDEX_USER, name, buffer, size);
+ return ext4_xattr_get(dentry->d_inode, EXT4_XATTR_INDEX_USER,
+ name, buffer, size);
}
static int
-ext4_xattr_user_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+ext4_xattr_user_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- if (!test_opt(inode->i_sb, XATTR_USER))
+ if (!test_opt(dentry->d_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext4_xattr_set(inode, EXT4_XATTR_INDEX_USER, name,
- value, size, flags);
+ return ext4_xattr_set(dentry->d_inode, EXT4_XATTR_INDEX_USER,
+ name, value, size, flags);
}
struct xattr_handler ext4_xattr_user_handler = {
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-22 04:32:25 +0000