summaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/Makefile2
-rw-r--r--fs/ext4/acl.c11
-rw-r--r--fs/ext4/acl.h2
-rw-r--r--fs/ext4/balloc.c8
-rw-r--r--fs/ext4/block_validity.c7
-rw-r--r--fs/ext4/dir.c58
-rw-r--r--fs/ext4/ext4.h208
-rw-r--r--fs/ext4/ext4_extents.h73
-rw-r--r--fs/ext4/ext4_jbd2.h2
-rw-r--r--fs/ext4/extents.c455
-rw-r--r--fs/ext4/file.c68
-rw-r--r--fs/ext4/fsync.c90
-rw-r--r--fs/ext4/ialloc.c137
-rw-r--r--fs/ext4/inode.c683
-rw-r--r--fs/ext4/ioctl.c24
-rw-r--r--fs/ext4/mballoc.c598
-rw-r--r--fs/ext4/migrate.c4
-rw-r--r--fs/ext4/move_extent.c22
-rw-r--r--fs/ext4/namei.c134
-rw-r--r--fs/ext4/page-io.c428
-rw-r--r--fs/ext4/resize.c119
-rw-r--r--fs/ext4/super.c971
-rw-r--r--fs/ext4/xattr.c32
-rw-r--r--fs/ext4/xattr.h10
24 files changed, 2775 insertions, 1371 deletions
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index 8867b2a1e5f..c947e36eda6 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -4,7 +4,7 @@
obj-$(CONFIG_EXT4_FS) += ext4.o
-ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \
+ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \
ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 5e2ed4504ea..e0270d1f8d8 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -238,10 +238,17 @@ ext4_set_acl(handle_t *handle, struct inode *inode, int type,
}
int
-ext4_check_acl(struct inode *inode, int mask)
+ext4_check_acl(struct inode *inode, int mask, unsigned int flags)
{
- struct posix_acl *acl = ext4_get_acl(inode, ACL_TYPE_ACCESS);
+ struct posix_acl *acl;
+
+ if (flags & IPERM_FLAG_RCU) {
+ if (!negative_cached_acl(inode, ACL_TYPE_ACCESS))
+ return -ECHILD;
+ return -EAGAIN;
+ }
+ acl = ext4_get_acl(inode, ACL_TYPE_ACCESS);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (acl) {
diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h
index 9d843d5deac..dec821168fd 100644
--- a/fs/ext4/acl.h
+++ b/fs/ext4/acl.h
@@ -54,7 +54,7 @@ static inline int ext4_acl_count(size_t size)
#ifdef CONFIG_EXT4_FS_POSIX_ACL
/* acl.c */
-extern int ext4_check_acl(struct inode *, int);
+extern int ext4_check_acl(struct inode *, int, unsigned int);
extern int ext4_acl_chmod(struct inode *);
extern int ext4_init_acl(handle_t *, struct inode *, struct inode *);
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index bd30799a43e..adf96b82278 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -171,7 +171,8 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
* less than the blocksize * 8 ( which is the size
* of bitmap ), set rest of the block bitmap to 1
*/
- mark_bitmap_end(group_blocks, sb->s_blocksize * 8, bh->b_data);
+ ext4_mark_bitmap_end(group_blocks, sb->s_blocksize * 8,
+ bh->b_data);
}
return free_blocks - ext4_group_used_meta_blocks(sb, block_group, gdp);
}
@@ -489,7 +490,7 @@ error_return:
* Check if filesystem has nblocks free & available for allocation.
* On success return 1, return 0 on failure.
*/
-int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks)
+static int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks)
{
s64 free_blocks, dirty_blocks, root_blocks;
struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
@@ -591,7 +592,8 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
* Account for the allocated meta blocks. We will never
* fail EDQUOT for metdata, but we do account for it.
*/
- if (!(*errp) && EXT4_I(inode)->i_delalloc_reserved_flag) {
+ if (!(*errp) &&
+ ext4_test_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED)) {
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
EXT4_I(inode)->i_allocated_meta_blocks += ar.len;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 3db5084db9b..fac90f3fba8 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -29,16 +29,15 @@ struct ext4_system_zone {
static struct kmem_cache *ext4_system_zone_cachep;
-int __init init_ext4_system_zone(void)
+int __init ext4_init_system_zone(void)
{
- ext4_system_zone_cachep = KMEM_CACHE(ext4_system_zone,
- SLAB_RECLAIM_ACCOUNT);
+ ext4_system_zone_cachep = KMEM_CACHE(ext4_system_zone, 0);
if (ext4_system_zone_cachep == NULL)
return -ENOMEM;
return 0;
}
-void exit_ext4_system_zone(void)
+void ext4_exit_system_zone(void)
{
kmem_cache_destroy(ext4_system_zone_cachep);
}
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 374510f72ba..164c56092e5 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -39,7 +39,7 @@ static int ext4_release_dir(struct inode *inode,
struct file *filp);
const struct file_operations ext4_dir_operations = {
- .llseek = generic_file_llseek,
+ .llseek = ext4_llseek,
.read = generic_read_dir,
.readdir = ext4_readdir, /* we take BKL. needed?*/
.unlocked_ioctl = ext4_ioctl,
@@ -60,9 +60,13 @@ static unsigned char get_dtype(struct super_block *sb, int filetype)
return (ext4_filetype_table[filetype]);
}
-
+/*
+ * Return 0 if the directory entry is OK, and 1 if there is a problem
+ *
+ * Note: this is the opposite of what ext2 and ext3 historically returned...
+ */
int __ext4_check_dir_entry(const char *function, unsigned int line,
- struct inode *dir,
+ struct inode *dir, struct file *filp,
struct ext4_dir_entry_2 *de,
struct buffer_head *bh,
unsigned int offset)
@@ -71,26 +75,37 @@ int __ext4_check_dir_entry(const char *function, unsigned int line,
const int rlen = ext4_rec_len_from_disk(de->rec_len,
dir->i_sb->s_blocksize);
- if (rlen < EXT4_DIR_REC_LEN(1))
+ if (unlikely(rlen < EXT4_DIR_REC_LEN(1)))
error_msg = "rec_len is smaller than minimal";
- else if (rlen % 4 != 0)
+ else if (unlikely(rlen % 4 != 0))
error_msg = "rec_len % 4 != 0";
- else if (rlen < EXT4_DIR_REC_LEN(de->name_len))
+ else if (unlikely(rlen < EXT4_DIR_REC_LEN(de->name_len)))
error_msg = "rec_len is too small for name_len";
- else if (((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize)
+ else if (unlikely(((char *) de - bh->b_data) + rlen >
+ dir->i_sb->s_blocksize))
error_msg = "directory entry across blocks";
- else if (le32_to_cpu(de->inode) >
- le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count))
+ else if (unlikely(le32_to_cpu(de->inode) >
+ le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count)))
error_msg = "inode out of bounds";
+ else
+ return 0;
- if (error_msg != NULL)
- ext4_error_inode(dir, function, line, bh->b_blocknr,
- "bad entry in directory: %s - "
- "offset=%u(%u), inode=%u, rec_len=%d, name_len=%d",
- error_msg, (unsigned) (offset%bh->b_size), offset,
- le32_to_cpu(de->inode),
- rlen, de->name_len);
- return error_msg == NULL ? 1 : 0;
+ if (filp)
+ ext4_error_file(filp, function, line, bh ? bh->b_blocknr : 0,
+ "bad entry in directory: %s - offset=%u(%u), "
+ "inode=%u, rec_len=%d, name_len=%d",
+ error_msg, (unsigned) (offset%bh->b_size),
+ offset, le32_to_cpu(de->inode),
+ rlen, de->name_len);
+ else
+ ext4_error_inode(dir, function, line, bh ? bh->b_blocknr : 0,
+ "bad entry in directory: %s - offset=%u(%u), "
+ "inode=%u, rec_len=%d, name_len=%d",
+ error_msg, (unsigned) (offset%bh->b_size),
+ offset, le32_to_cpu(de->inode),
+ rlen, de->name_len);
+
+ return 1;
}
static int ext4_readdir(struct file *filp,
@@ -152,8 +167,9 @@ static int ext4_readdir(struct file *filp,
*/
if (!bh) {
if (!dir_has_error) {
- EXT4_ERROR_INODE(inode, "directory "
- "contains a hole at offset %Lu",
+ EXT4_ERROR_FILE(filp, 0,
+ "directory contains a "
+ "hole at offset %llu",
(unsigned long long) filp->f_pos);
dir_has_error = 1;
}
@@ -194,8 +210,8 @@ revalidate:
while (!error && filp->f_pos < inode->i_size
&& offset < sb->s_blocksize) {
de = (struct ext4_dir_entry_2 *) (bh->b_data + offset);
- if (!ext4_check_dir_entry(inode, de,
- bh, offset)) {
+ if (ext4_check_dir_entry(inode, filp, de,
+ bh, offset)) {
/*
* On error, skip the f_pos to the next block
*/
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 889ec9d5e6a..0c8d97b56f3 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -62,8 +62,8 @@
#define EXT4_ERROR_INODE_BLOCK(inode, block, fmt, a...) \
ext4_error_inode((inode), __func__, __LINE__, (block), (fmt), ## a)
-#define EXT4_ERROR_FILE(file, fmt, a...) \
- ext4_error_file(__func__, __LINE__, (file), (fmt), ## a)
+#define EXT4_ERROR_FILE(file, block, fmt, a...) \
+ ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a)
/* data type for block offset of block group */
typedef int ext4_grpblk_t;
@@ -168,7 +168,20 @@ struct mpage_da_data {
int pages_written;
int retval;
};
-#define EXT4_IO_UNWRITTEN 0x1
+
+/*
+ * Flags for ext4_io_end->flags
+ */
+#define EXT4_IO_END_UNWRITTEN 0x0001
+#define EXT4_IO_END_ERROR 0x0002
+
+struct ext4_io_page {
+ struct page *p_page;
+ atomic_t p_count;
+};
+
+#define MAX_IO_PAGES 128
+
typedef struct ext4_io_end {
struct list_head list; /* per-file finished IO list */
struct inode *inode; /* file being written to */
@@ -179,8 +192,18 @@ typedef struct ext4_io_end {
struct work_struct work; /* data work queue */
struct kiocb *iocb; /* iocb struct for AIO */
int result; /* error value for AIO */
+ int num_io_pages;
+ struct ext4_io_page *pages[MAX_IO_PAGES];
} ext4_io_end_t;
+struct ext4_io_submit {
+ int io_op;
+ struct bio *io_bio;
+ ext4_io_end_t *io_end;
+ struct ext4_io_page *io_page;
+ sector_t io_next_block;
+};
+
/*
* Special inodes numbers
*/
@@ -205,6 +228,7 @@ typedef struct ext4_io_end {
#define EXT4_MIN_BLOCK_SIZE 1024
#define EXT4_MAX_BLOCK_SIZE 65536
#define EXT4_MIN_BLOCK_LOG_SIZE 10
+#define EXT4_MAX_BLOCK_LOG_SIZE 16
#ifdef __KERNEL__
# define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize)
#else
@@ -537,23 +561,7 @@ struct ext4_new_group_data {
#define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION
#endif
-
-/*
- * Mount options
- */
-struct ext4_mount_options {
- unsigned long s_mount_opt;
- uid_t s_resuid;
- gid_t s_resgid;
- unsigned long s_commit_interval;
- u32 s_min_batch_time, s_max_batch_time;
-#ifdef CONFIG_QUOTA
- int s_jquota_fmt;
- char *s_qf_names[MAXQUOTAS];
-#endif
-};
-
-/* Max physical block we can addres w/o extents */
+/* Max physical block we can address w/o extents */
#define EXT4_MAX_BLOCK_FILE_PHYS 0xFFFFFFFF
/*
@@ -685,6 +693,8 @@ do { \
if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) \
ext4_decode_extra_time(&(inode)->xtime, \
raw_inode->xtime ## _extra); \
+ else \
+ (inode)->xtime.tv_nsec = 0; \
} while (0)
#define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode) \
@@ -695,6 +705,8 @@ do { \
if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra)) \
ext4_decode_extra_time(&(einode)->xtime, \
raw_inode->xtime ## _extra); \
+ else \
+ (einode)->xtime.tv_nsec = 0; \
} while (0)
#define i_disk_version osd1.linux1.l_i_version
@@ -726,12 +738,13 @@ do { \
/*
* storage for cached extent
+ * If ec_len == 0, then the cache is invalid.
+ * If ec_start == 0, then the cache represents a gap (null mapping)
*/
struct ext4_ext_cache {
ext4_fsblk_t ec_start;
ext4_lblk_t ec_block;
__u32 ec_len; /* must be 32bit to return holes */
- __u32 ec_type;
};
/*
@@ -750,10 +763,12 @@ struct ext4_inode_info {
* near to their parent directory's inode.
*/
ext4_group_t i_block_group;
+ ext4_lblk_t i_dir_start_lookup;
+#if (BITS_PER_LONG < 64)
unsigned long i_state_flags; /* Dynamic state flags */
+#endif
unsigned long i_flags;
- ext4_lblk_t i_dir_start_lookup;
#ifdef CONFIG_EXT4_FS_XATTR
/*
* Extended attributes can be read independently of the main file
@@ -796,7 +811,7 @@ struct ext4_inode_info {
*/
struct rw_semaphore i_data_sem;
struct inode vfs_inode;
- struct jbd2_inode jinode;
+ struct jbd2_inode *jinode;
struct ext4_ext_cache i_cached_extent;
/*
@@ -816,14 +831,12 @@ struct ext4_inode_info {
unsigned int i_reserved_data_blocks;
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;
+ ext4_lblk_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;
@@ -832,9 +845,12 @@ struct ext4_inode_info {
/* completed IOs that might need unwritten extents handling */
struct list_head i_completed_io_list;
spinlock_t i_completed_io_lock;
+ atomic_t i_ioend_count; /* Number of outstanding io_end structs */
/* current io_end structure for async DIO write*/
ext4_io_end_t *cur_aio_dio;
+ spinlock_t i_block_reservation_lock;
+
/*
* Transactions that contain inode's metadata needed to complete
* fsync and fdatasync, respectively.
@@ -885,16 +901,27 @@ struct ext4_inode_info {
#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_MBLK_IO_SUBMIT 0x4000000 /* multi-block io submits */
#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 EXT4_MOUNT_INIT_INODE_TABLE 0x80000000 /* Initialize uninitialized itables */
-#define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt
-#define set_opt(o, opt) o |= EXT4_MOUNT_##opt
+#define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \
+ ~EXT4_MOUNT_##opt
+#define set_opt(sb, opt) EXT4_SB(sb)->s_mount_opt |= \
+ EXT4_MOUNT_##opt
#define test_opt(sb, opt) (EXT4_SB(sb)->s_mount_opt & \
EXT4_MOUNT_##opt)
+#define clear_opt2(sb, opt) EXT4_SB(sb)->s_mount_opt2 &= \
+ ~EXT4_MOUNT2_##opt
+#define set_opt2(sb, opt) EXT4_SB(sb)->s_mount_opt2 |= \
+ EXT4_MOUNT2_##opt
+#define test_opt2(sb, opt) (EXT4_SB(sb)->s_mount_opt2 & \
+ EXT4_MOUNT2_##opt)
+
#define ext4_set_bit ext2_set_bit
#define ext4_set_bit_atomic ext2_set_bit_atomic
#define ext4_clear_bit ext2_clear_bit
@@ -1060,6 +1087,7 @@ struct ext4_sb_info {
struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */
struct buffer_head **s_group_desc;
unsigned int s_mount_opt;
+ unsigned int s_mount_opt2;
unsigned int s_mount_flags;
ext4_fsblk_t s_sb_block;
uid_t s_resuid;
@@ -1087,7 +1115,6 @@ struct ext4_sb_info {
struct completion s_kobj_unregister;
/* Journaling */
- struct inode *s_journal_inode;
struct journal_s *s_journal;
struct list_head s_orphan;
struct mutex s_orphan_lock;
@@ -1120,10 +1147,7 @@ struct ext4_sb_info {
/* for buddy allocator */
struct ext4_group_info ***s_group_info;
struct inode *s_buddy_cache;
- long s_blocks_reserved;
- spinlock_t s_reserve_lock;
spinlock_t s_md_lock;
- tid_t s_last_transaction;
unsigned short *s_mb_offsets;
unsigned int *s_mb_maxs;
@@ -1141,7 +1165,6 @@ struct ext4_sb_info {
unsigned long s_mb_last_start;
/* stats for buddy allocator */
- spinlock_t s_mb_pa_lock;
atomic_t s_bal_reqs; /* number of reqs with len > 1 */
atomic_t s_bal_success; /* we found long enough chunks */
atomic_t s_bal_allocated; /* in blocks */
@@ -1172,6 +1195,11 @@ struct ext4_sb_info {
/* timer for periodic error stats printing */
struct timer_list s_err_report;
+
+ /* Lazy inode table initialization info */
+ struct ext4_li_request *s_li_request;
+ /* Wait multiplier for lazy initialization thread */
+ unsigned int s_li_wait_mult;
};
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1210,24 +1238,39 @@ enum {
EXT4_STATE_EXT_MIGRATE, /* Inode is migrating */
EXT4_STATE_DIO_UNWRITTEN, /* need convert on dio done*/
EXT4_STATE_NEWENTRY, /* File just added to dir */
+ EXT4_STATE_DELALLOC_RESERVED, /* blks already reserved for delalloc */
};
-#define EXT4_INODE_BIT_FNS(name, field) \
+#define EXT4_INODE_BIT_FNS(name, field, offset) \
static inline int ext4_test_inode_##name(struct inode *inode, int bit) \
{ \
- return test_bit(bit, &EXT4_I(inode)->i_##field); \
+ return test_bit(bit + (offset), &EXT4_I(inode)->i_##field); \
} \
static inline void ext4_set_inode_##name(struct inode *inode, int bit) \
{ \
- set_bit(bit, &EXT4_I(inode)->i_##field); \
+ set_bit(bit + (offset), &EXT4_I(inode)->i_##field); \
} \
static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \
{ \
- clear_bit(bit, &EXT4_I(inode)->i_##field); \
+ clear_bit(bit + (offset), &EXT4_I(inode)->i_##field); \
}
-EXT4_INODE_BIT_FNS(flag, flags)
-EXT4_INODE_BIT_FNS(state, state_flags)
+EXT4_INODE_BIT_FNS(flag, flags, 0)
+#if (BITS_PER_LONG < 64)
+EXT4_INODE_BIT_FNS(state, state_flags, 0)
+
+static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
+{
+ (ei)->i_state_flags = 0;
+}
+#else
+EXT4_INODE_BIT_FNS(state, flags, 32)
+
+static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
+{
+ /* We depend on the fact that callers will set i_flags */
+}
+#endif
#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
@@ -1533,7 +1576,42 @@ ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp);
-extern struct proc_dir_entry *ext4_proc_root;
+/*
+ * Timeout and state flag for lazy initialization inode thread.
+ */
+#define EXT4_DEF_LI_WAIT_MULT 10
+#define EXT4_DEF_LI_MAX_START_DELAY 5
+#define EXT4_LAZYINIT_QUIT 0x0001
+#define EXT4_LAZYINIT_RUNNING 0x0002
+
+/*
+ * Lazy inode table initialization info
+ */
+struct ext4_lazy_init {
+ unsigned long li_state;
+
+ wait_queue_head_t li_wait_daemon;
+ wait_queue_head_t li_wait_task;
+ struct timer_list li_timer;
+ struct task_struct *li_task;
+
+ struct list_head li_request_list;
+ struct mutex li_list_mtx;
+};
+
+struct ext4_li_request {
+ struct super_block *lr_super;
+ struct ext4_sb_info *lr_sbi;
+ ext4_group_t lr_next_group;
+ struct list_head lr_request;
+ unsigned long lr_next_sched;
+ unsigned long lr_timeout;
+};
+
+struct ext4_features {
+ struct kobject f_kobj;
+ struct completion f_kobj_unregister;
+};
/*
* Function prototypes
@@ -1561,7 +1639,6 @@ extern unsigned long ext4_bg_num_gdb(struct super_block *sb,
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_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 *);
@@ -1581,10 +1658,12 @@ extern unsigned ext4_init_block_bitmap(struct super_block *sb,
/* dir.c */
extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
+ struct file *,
struct ext4_dir_entry_2 *,
struct buffer_head *, unsigned int);
-#define ext4_check_dir_entry(dir, de, bh, offset) \
- __ext4_check_dir_entry(__func__, __LINE__, (dir), (de), (bh), (offset))
+#define ext4_check_dir_entry(dir, filp, de, bh, offset) \
+ unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \
+ (de), (bh), (offset)))
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
__u32 minor_hash,
struct ext4_dir_entry_2 *dirent);
@@ -1592,6 +1671,7 @@ extern void ext4_htree_free_dir_info(struct dir_private_info *p);
/* fsync.c */
extern int ext4_sync_file(struct file *, int);
+extern int ext4_flush_completed_IO(struct inode *);
/* hash.c */
extern int ext4fs_dirhash(const char *name, int len, struct
@@ -1605,11 +1685,9 @@ extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
extern unsigned long ext4_count_free_inodes(struct super_block *);
extern unsigned long ext4_count_dirs(struct super_block *);
extern void ext4_check_inodes_bitmap(struct super_block *);
-extern unsigned ext4_init_inode_bitmap(struct super_block *sb,
- struct buffer_head *bh,
- ext4_group_t group,
- struct ext4_group_desc *desc);
-extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
+extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
+extern int ext4_init_inode_table(struct super_block *sb,
+ ext4_group_t group, int barrier);
/* mballoc.c */
extern long ext4_mb_stats;
@@ -1620,16 +1698,15 @@ extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
struct ext4_allocation_request *, int *);
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 int __init ext4_init_mballoc(void);
+extern void ext4_exit_mballoc(void);
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);
+extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
+
/* inode.c */
struct buffer_head *ext4_getblk(handle_t *, struct inode *,
ext4_lblk_t, int, int *);
@@ -1657,13 +1734,11 @@ extern void ext4_get_inode_flags(struct ext4_inode_info *);
extern int ext4_alloc_da_blocks(struct inode *inode);
extern void ext4_set_aops(struct inode *inode);
extern int ext4_writepage_trans_blocks(struct inode *);
-extern int ext4_meta_trans_blocks(struct inode *, int nrblocks, int idxblocks);
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_completed_IO(struct inode *inode);
extern void ext4_da_update_reserve_space(struct inode *inode,
int used, int quota_claim);
/* ioctl.c */
@@ -1696,8 +1771,8 @@ extern void ext4_error_inode(struct inode *, const char *, unsigned int,
ext4_fsblk_t, const char *, ...)
__attribute__ ((format (printf, 5, 6)));
extern void ext4_error_file(struct file *, const char *, unsigned int,
- const char *, ...)
- __attribute__ ((format (printf, 4, 5)));
+ ext4_fsblk_t, const char *, ...)
+ __attribute__ ((format (printf, 5, 6)));
extern void __ext4_std_error(struct super_block *, const char *,
unsigned int, int);
extern void __ext4_abort(struct super_block *, const char *, unsigned int,
@@ -1960,6 +2035,7 @@ extern const struct file_operations ext4_dir_operations;
/* file.c */
extern const struct inode_operations ext4_file_inode_operations;
extern const struct file_operations ext4_file_operations;
+extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
/* namei.c */
extern const struct inode_operations ext4_dir_inode_operations;
@@ -1973,8 +2049,8 @@ extern const struct inode_operations ext4_fast_symlink_inode_operations;
/* block_validity */
extern void ext4_release_system_zone(struct super_block *sb);
extern int ext4_setup_system_zone(struct super_block *sb);
-extern int __init init_ext4_system_zone(void);
-extern void exit_ext4_system_zone(void);
+extern int __init ext4_init_system_zone(void);
+extern void ext4_exit_system_zone(void);
extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
ext4_fsblk_t start_blk,
unsigned int count);
@@ -1989,7 +2065,7 @@ extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
extern void ext4_ext_truncate(struct inode *);
extern void ext4_ext_init(struct super_block *);
extern void ext4_ext_release(struct super_block *);
-extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
+extern long ext4_fallocate(struct file *file, int mode, loff_t offset,
loff_t len);
extern int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
ssize_t len);
@@ -2002,6 +2078,18 @@ extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
__u64 start_orig, __u64 start_donor,
__u64 len, __u64 *moved_len);
+/* page-io.c */
+extern int __init ext4_init_pageio(void);
+extern void ext4_exit_pageio(void);
+extern void ext4_ioend_wait(struct inode *);
+extern void ext4_free_io_end(ext4_io_end_t *io);
+extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
+extern int ext4_end_io_nolock(ext4_io_end_t *io);
+extern void ext4_io_submit(struct ext4_io_submit *io);
+extern int ext4_bio_write_page(struct ext4_io_submit *io,
+ struct page *page,
+ int len,
+ struct writeback_control *wbc);
/* BH_Uninit flag: blocks are allocated but uninitialized on disk */
enum ext4_state_bits {
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index bdb6ce7e2eb..2e29abb30f7 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -119,10 +119,6 @@ struct ext4_ext_path {
* structure for external API
*/
-#define EXT4_EXT_CACHE_NO 0
-#define EXT4_EXT_CACHE_GAP 1
-#define EXT4_EXT_CACHE_EXTENT 2
-
/*
* to be called by ext4_ext_walk_space()
* negative retcode - error
@@ -197,7 +193,7 @@ static inline unsigned short ext_depth(struct inode *inode)
static inline void
ext4_ext_invalidate_cache(struct inode *inode)
{
- EXT4_I(inode)->i_cached_extent.ec_type = EXT4_EXT_CACHE_NO;
+ EXT4_I(inode)->i_cached_extent.ec_len = 0;
}
static inline void ext4_ext_mark_uninitialized(struct ext4_extent *ext)
@@ -225,11 +221,60 @@ static inline void ext4_ext_mark_initialized(struct ext4_extent *ext)
ext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ext));
}
+/*
+ * ext4_ext_pblock:
+ * combine low and high parts of physical block number into ext4_fsblk_t
+ */
+static inline ext4_fsblk_t ext4_ext_pblock(struct ext4_extent *ex)
+{
+ ext4_fsblk_t block;
+
+ block = le32_to_cpu(ex->ee_start_lo);
+ block |= ((ext4_fsblk_t) le16_to_cpu(ex->ee_start_hi) << 31) << 1;
+ return block;
+}
+
+/*
+ * ext4_idx_pblock:
+ * combine low and high parts of a leaf physical block number into ext4_fsblk_t
+ */
+static inline ext4_fsblk_t ext4_idx_pblock(struct ext4_extent_idx *ix)
+{
+ ext4_fsblk_t block;
+
+ block = le32_to_cpu(ix->ei_leaf_lo);
+ block |= ((ext4_fsblk_t) le16_to_cpu(ix->ei_leaf_hi) << 31) << 1;
+ return block;
+}
+
+/*
+ * ext4_ext_store_pblock:
+ * stores a large physical block number into an extent struct,
+ * breaking it into parts
+ */
+static inline void ext4_ext_store_pblock(struct ext4_extent *ex,
+ ext4_fsblk_t pb)
+{
+ ex->ee_start_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff));
+ ex->ee_start_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) &
+ 0xffff);
+}
+
+/*
+ * ext4_idx_store_pblock:
+ * stores a large physical block number into an index struct,
+ * breaking it into parts
+ */
+static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix,
+ ext4_fsblk_t pb)
+{
+ ix->ei_leaf_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff));
+ ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) &
+ 0xffff);
+}
+
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);
+ ext4_lblk_t lblocks);
extern int ext4_extent_tree_init(handle_t *, struct inode *);
extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
int num,
@@ -237,19 +282,9 @@ extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
extern int ext4_can_extents_be_merged(struct inode *inode,
struct ext4_extent *ex1,
struct ext4_extent *ex2);
-extern int ext4_ext_try_to_merge(struct inode *inode,
- struct ext4_ext_path *path,
- struct ext4_extent *);
-extern unsigned int ext4_ext_check_overlap(struct inode *, struct ext4_extent *, struct ext4_ext_path *);
extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *, int);
-extern int ext4_ext_walk_space(struct inode *, ext4_lblk_t, ext4_lblk_t,
- ext_prepare_callback, void *);
extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
struct ext4_ext_path *);
-extern int ext4_ext_search_left(struct inode *, struct ext4_ext_path *,
- ext4_lblk_t *, ext4_fsblk_t *);
-extern int ext4_ext_search_right(struct inode *, struct ext4_ext_path *,
- ext4_lblk_t *, ext4_fsblk_t *);
extern void ext4_ext_drop_refs(struct ext4_ext_path *);
extern int ext4_ext_check_inode(struct inode *inode);
#endif /* _EXT4_EXTENTS */
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index b0bd792c58c..d8b992e658c 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -253,7 +253,7 @@ static inline int ext4_journal_force_commit(journal_t *journal)
static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode)
{
if (ext4_handle_valid(handle))
- return jbd2_journal_file_inode(handle, &EXT4_I(inode)->jinode);
+ return jbd2_journal_file_inode(handle, EXT4_I(inode)->jinode);
return 0;
}
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 06328d3e571..63a75810b7c 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -44,55 +44,6 @@
#include "ext4_jbd2.h"
#include "ext4_extents.h"
-
-/*
- * ext_pblock:
- * combine low and high parts of physical block number into ext4_fsblk_t
- */
-ext4_fsblk_t ext_pblock(struct ext4_extent *ex)
-{
- ext4_fsblk_t block;
-
- block = le32_to_cpu(ex->ee_start_lo);
- block |= ((ext4_fsblk_t) le16_to_cpu(ex->ee_start_hi) << 31) << 1;
- return block;
-}
-
-/*
- * idx_pblock:
- * combine low and high parts of a leaf physical block number into ext4_fsblk_t
- */
-ext4_fsblk_t idx_pblock(struct ext4_extent_idx *ix)
-{
- ext4_fsblk_t block;
-
- block = le32_to_cpu(ix->ei_leaf_lo);
- block |= ((ext4_fsblk_t) le16_to_cpu(ix->ei_leaf_hi) << 31) << 1;
- return block;
-}
-
-/*
- * ext4_ext_store_pblock:
- * stores a large physical block number into an extent struct,
- * breaking it into parts
- */
-void ext4_ext_store_pblock(struct ext4_extent *ex, ext4_fsblk_t pb)
-{
- ex->ee_start_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff));
- ex->ee_start_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff);
-}
-
-/*
- * ext4_idx_store_pblock:
- * stores a large physical block number into an index struct,
- * breaking it into parts
- */
-static void ext4_idx_store_pblock(struct ext4_extent_idx *ix, ext4_fsblk_t pb)
-{
- ix->ei_leaf_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff));
- ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff);
-}
-
static int ext4_ext_truncate_extend_restart(handle_t *handle,
struct inode *inode,
int needed)
@@ -166,10 +117,33 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
struct ext4_extent *ex;
depth = path->p_depth;
- /* try to predict block placement */
+ /*
+ * Try to predict block placement assuming that we are
+ * filling in a file which will eventually be
+ * non-sparse --- i.e., in the case of libbfd writing
+ * an ELF object sections out-of-order but in a way
+ * the eventually results in a contiguous object or
+ * executable file, or some database extending a table
+ * space file. However, this is actually somewhat
+ * non-ideal if we are writing a sparse file such as
+ * qemu or KVM writing a raw image file that is going
+ * to stay fairly sparse, since it will end up
+ * fragmenting the file system's free space. Maybe we
+ * should have some hueristics or some way to allow
+ * userspace to pass a hint to file system,
+ * especiially if the latter case turns out to be
+ * common.
+ */
ex = path[depth].p_ext;
- if (ex)
- return ext_pblock(ex)+(block-le32_to_cpu(ex->ee_block));
+ if (ex) {
+ ext4_fsblk_t ext_pblk = ext4_ext_pblock(ex);
+ ext4_lblk_t ext_block = le32_to_cpu(ex->ee_block);
+
+ if (block > ext_block)
+ return ext_pblk + (block - ext_block);
+ else
+ return ext_pblk - (ext_block - block);
+ }
/* it looks like index is empty;
* try to find starting block from index itself */
@@ -292,7 +266,7 @@ 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, sector_t lblock)
+int ext4_ext_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
{
struct ext4_inode_info *ei = EXT4_I(inode);
int idxs, num = 0;
@@ -354,7 +328,7 @@ ext4_ext_max_entries(struct inode *inode, int depth)
static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
{
- ext4_fsblk_t block = ext_pblock(ext);
+ ext4_fsblk_t block = ext4_ext_pblock(ext);
int len = ext4_ext_get_actual_len(ext);
return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
@@ -363,7 +337,7 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
static int ext4_valid_extent_idx(struct inode *inode,
struct ext4_extent_idx *ext_idx)
{
- ext4_fsblk_t block = idx_pblock(ext_idx);
+ ext4_fsblk_t block = ext4_idx_pblock(ext_idx);
return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1);
}
@@ -463,13 +437,13 @@ static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
for (k = 0; k <= l; k++, path++) {
if (path->p_idx) {
ext_debug(" %d->%llu", le32_to_cpu(path->p_idx->ei_block),
- idx_pblock(path->p_idx));
+ ext4_idx_pblock(path->p_idx));
} else if (path->p_ext) {
ext_debug(" %d:[%d]%d:%llu ",
le32_to_cpu(path->p_ext->ee_block),
ext4_ext_is_uninitialized(path->p_ext),
ext4_ext_get_actual_len(path->p_ext),
- ext_pblock(path->p_ext));
+ ext4_ext_pblock(path->p_ext));
} else
ext_debug(" []");
}
@@ -494,7 +468,7 @@ static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path)
for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) {
ext_debug("%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block),
ext4_ext_is_uninitialized(ex),
- ext4_ext_get_actual_len(ex), ext_pblock(ex));
+ ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex));
}
ext_debug("\n");
}
@@ -545,7 +519,7 @@ ext4_ext_binsearch_idx(struct inode *inode,
path->p_idx = l - 1;
ext_debug(" -> %d->%lld ", le32_to_cpu(path->p_idx->ei_block),
- idx_pblock(path->p_idx));
+ ext4_idx_pblock(path->p_idx));
#ifdef CHECK_BINSEARCH
{
@@ -614,7 +588,7 @@ ext4_ext_binsearch(struct inode *inode,
path->p_ext = l - 1;
ext_debug(" -> %d:%llu:[%d]%d ",
le32_to_cpu(path->p_ext->ee_block),
- ext_pblock(path->p_ext),
+ ext4_ext_pblock(path->p_ext),
ext4_ext_is_uninitialized(path->p_ext),
ext4_ext_get_actual_len(path->p_ext));
@@ -682,7 +656,7 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max));
ext4_ext_binsearch_idx(inode, path + ppos, block);
- path[ppos].p_block = idx_pblock(path[ppos].p_idx);
+ path[ppos].p_block = ext4_idx_pblock(path[ppos].p_idx);
path[ppos].p_depth = i;
path[ppos].p_ext = NULL;
@@ -721,7 +695,7 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
ext4_ext_binsearch(inode, path + ppos, block);
/* if not an empty leaf */
if (path[ppos].p_ext)
- path[ppos].p_block = ext_pblock(path[ppos].p_ext);
+ path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext);
ext4_ext_show_path(inode, path);
@@ -739,9 +713,9 @@ err:
* insert new index [@logical;@ptr] into the block at @curp;
* check where to insert: before @curp or after @curp
*/
-int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
- struct ext4_ext_path *curp,
- int logical, ext4_fsblk_t ptr)
+static int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *curp,
+ int logical, ext4_fsblk_t ptr)
{
struct ext4_extent_idx *ix;
int len, err;
@@ -917,7 +891,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
EXT_MAX_EXTENT(path[depth].p_hdr)) {
ext_debug("move %d:%llu:[%d]%d in new leaf %llu\n",
le32_to_cpu(path[depth].p_ext->ee_block),
- ext_pblock(path[depth].p_ext),
+ ext4_ext_pblock(path[depth].p_ext),
ext4_ext_is_uninitialized(path[depth].p_ext),
ext4_ext_get_actual_len(path[depth].p_ext),
newblock);
@@ -1007,7 +981,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
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),
- idx_pblock(path[i].p_idx),
+ ext4_idx_pblock(path[i].p_idx),
newblock);
/*memmove(++fidx, path[i].p_idx++,
sizeof(struct ext4_extent_idx));
@@ -1146,7 +1120,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
ext_debug("new root: num %d(%d), lblock %d, ptr %llu\n",
le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max),
le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block),
- idx_pblock(EXT_FIRST_INDEX(neh)));
+ ext4_idx_pblock(EXT_FIRST_INDEX(neh)));
neh->eh_depth = cpu_to_le16(path->p_depth + 1);
err = ext4_ext_dirty(handle, inode, curp);
@@ -1232,9 +1206,9 @@ out:
* returns 0 at @phys
* return value contains 0 (success) or error code
*/
-int
-ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path,
- ext4_lblk_t *logical, ext4_fsblk_t *phys)
+static int ext4_ext_search_left(struct inode *inode,
+ struct ext4_ext_path *path,
+ ext4_lblk_t *logical, ext4_fsblk_t *phys)
{
struct ext4_extent_idx *ix;
struct ext4_extent *ex;
@@ -1286,7 +1260,7 @@ ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path,
}
*logical = le32_to_cpu(ex->ee_block) + ee_len - 1;
- *phys = ext_pblock(ex) + ee_len - 1;
+ *phys = ext4_ext_pblock(ex) + ee_len - 1;
return 0;
}
@@ -1297,9 +1271,9 @@ ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path,
* returns 0 at @phys
* return value contains 0 (success) or error code
*/
-int
-ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
- ext4_lblk_t *logical, ext4_fsblk_t *phys)
+static int ext4_ext_search_right(struct inode *inode,
+ struct ext4_ext_path *path,
+ ext4_lblk_t *logical, ext4_fsblk_t *phys)
{
struct buffer_head *bh = NULL;
struct ext4_extent_header *eh;
@@ -1342,7 +1316,7 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
}
}
*logical = le32_to_cpu(ex->ee_block);
- *phys = ext_pblock(ex);
+ *phys = ext4_ext_pblock(ex);
return 0;
}
@@ -1357,7 +1331,7 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
/* next allocated block in this leaf */
ex++;
*logical = le32_to_cpu(ex->ee_block);
- *phys = ext_pblock(ex);
+ *phys = ext4_ext_pblock(ex);
return 0;
}
@@ -1376,7 +1350,7 @@ got_index:
* follow it and find the closest allocated
* block to the right */
ix++;
- block = idx_pblock(ix);
+ block = ext4_idx_pblock(ix);
while (++depth < path->p_depth) {
bh = sb_bread(inode->i_sb, block);
if (bh == NULL)
@@ -1388,7 +1362,7 @@ got_index:
return -EIO;
}
ix = EXT_FIRST_INDEX(eh);
- block = idx_pblock(ix);
+ block = ext4_idx_pblock(ix);
put_bh(bh);
}
@@ -1402,7 +1376,7 @@ got_index:
}
ex = EXT_FIRST_EXTENT(eh);
*logical = le32_to_cpu(ex->ee_block);
- *phys = ext_pblock(ex);
+ *phys = ext4_ext_pblock(ex);
put_bh(bh);
return 0;
}
@@ -1573,7 +1547,7 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
return 0;
#endif
- if (ext_pblock(ex1) + ext1_ee_len == ext_pblock(ex2))
+ if (ext4_ext_pblock(ex1) + ext1_ee_len == ext4_ext_pblock(ex2))
return 1;
return 0;
}
@@ -1585,9 +1559,9 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
* Returns 0 if the extents (ex and ex+1) were _not_ merged and returns
* 1 if they got merged.
*/
-int ext4_ext_try_to_merge(struct inode *inode,
- struct ext4_ext_path *path,
- struct ext4_extent *ex)
+static int ext4_ext_try_to_merge(struct inode *inode,
+ struct ext4_ext_path *path,
+ struct ext4_extent *ex)
{
struct ext4_extent_header *eh;
unsigned int depth, len;
@@ -1632,9 +1606,9 @@ int ext4_ext_try_to_merge(struct inode *inode,
* such that there will be no overlap, and then returns 1.
* If there is no overlap found, it returns 0.
*/
-unsigned int ext4_ext_check_overlap(struct inode *inode,
- struct ext4_extent *newext,
- struct ext4_ext_path *path)
+static unsigned int ext4_ext_check_overlap(struct inode *inode,
+ struct ext4_extent *newext,
+ struct ext4_ext_path *path)
{
ext4_lblk_t b1, b2;
unsigned int depth, len1;
@@ -1706,11 +1680,12 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
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),
- ext4_ext_get_actual_len(newext),
- le32_to_cpu(ex->ee_block),
- ext4_ext_is_uninitialized(ex),
- ext4_ext_get_actual_len(ex), ext_pblock(ex));
+ ext4_ext_is_uninitialized(newext),
+ ext4_ext_get_actual_len(newext),
+ le32_to_cpu(ex->ee_block),
+ ext4_ext_is_uninitialized(ex),
+ ext4_ext_get_actual_len(ex),
+ ext4_ext_pblock(ex));
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
return err;
@@ -1780,7 +1755,7 @@ has_space:
/* there is no extent in this leaf, create first one */
ext_debug("first extent in the leaf: %d:%llu:[%d]%d\n",
le32_to_cpu(newext->ee_block),
- ext_pblock(newext),
+ ext4_ext_pblock(newext),
ext4_ext_is_uninitialized(newext),
ext4_ext_get_actual_len(newext));
path[depth].p_ext = EXT_FIRST_EXTENT(eh);
@@ -1794,7 +1769,7 @@ has_space:
ext_debug("insert %d:%llu:[%d]%d after: nearest 0x%p, "
"move %d from 0x%p to 0x%p\n",
le32_to_cpu(newext->ee_block),
- ext_pblock(newext),
+ ext4_ext_pblock(newext),
ext4_ext_is_uninitialized(newext),
ext4_ext_get_actual_len(newext),
nearex, len, nearex + 1, nearex + 2);
@@ -1808,7 +1783,7 @@ has_space:
ext_debug("insert %d:%llu:[%d]%d before: nearest 0x%p, "
"move %d from 0x%p to 0x%p\n",
le32_to_cpu(newext->ee_block),
- ext_pblock(newext),
+ ext4_ext_pblock(newext),
ext4_ext_is_uninitialized(newext),
ext4_ext_get_actual_len(newext),
nearex, len, nearex + 1, nearex + 2);
@@ -1819,7 +1794,7 @@ has_space:
le16_add_cpu(&eh->eh_entries, 1);
nearex = path[depth].p_ext;
nearex->ee_block = newext->ee_block;
- ext4_ext_store_pblock(nearex, ext_pblock(newext));
+ ext4_ext_store_pblock(nearex, ext4_ext_pblock(newext));
nearex->ee_len = newext->ee_len;
merge:
@@ -1845,9 +1820,9 @@ cleanup:
return err;
}
-int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
- ext4_lblk_t num, ext_prepare_callback func,
- void *cbdata)
+static int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
+ ext4_lblk_t num, ext_prepare_callback func,
+ void *cbdata)
{
struct ext4_ext_path *path = NULL;
struct ext4_ext_cache cbex;
@@ -1919,12 +1894,10 @@ int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
cbex.ec_block = start;
cbex.ec_len = end - start;
cbex.ec_start = 0;
- cbex.ec_type = EXT4_EXT_CACHE_GAP;
} else {
cbex.ec_block = le32_to_cpu(ex->ee_block);
cbex.ec_len = ext4_ext_get_actual_len(ex);
- cbex.ec_start = ext_pblock(ex);
- cbex.ec_type = EXT4_EXT_CACHE_EXTENT;
+ cbex.ec_start = ext4_ext_pblock(ex);
}
if (unlikely(cbex.ec_len == 0)) {
@@ -1964,13 +1937,12 @@ int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
static void
ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block,
- __u32 len, ext4_fsblk_t start, int type)
+ __u32 len, ext4_fsblk_t start)
{
struct ext4_ext_cache *cex;
BUG_ON(len == 0);
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
cex = &EXT4_I(inode)->i_cached_extent;
- cex->ec_type = type;
cex->ec_block = block;
cex->ec_len = len;
cex->ec_start = start;
@@ -2023,15 +1995,18 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
}
ext_debug(" -> %u:%lu\n", lblock, len);
- ext4_ext_put_in_cache(inode, lblock, len, 0, EXT4_EXT_CACHE_GAP);
+ ext4_ext_put_in_cache(inode, lblock, len, 0);
}
+/*
+ * Return 0 if cache is invalid; 1 if the cache is valid
+ */
static int
ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
struct ext4_extent *ex)
{
struct ext4_ext_cache *cex;
- int ret = EXT4_EXT_CACHE_NO;
+ int ret = 0;
/*
* We borrow i_block_reservation_lock to protect i_cached_extent
@@ -2040,11 +2015,9 @@ ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
cex = &EXT4_I(inode)->i_cached_extent;
/* has cache valid data? */
- if (cex->ec_type == EXT4_EXT_CACHE_NO)
+ if (cex->ec_len == 0)
goto errout;
- BUG_ON(cex->ec_type != EXT4_EXT_CACHE_GAP &&
- cex->ec_type != EXT4_EXT_CACHE_EXTENT);
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);
@@ -2052,7 +2025,7 @@ ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
ext_debug("%u cached by %u:%u:%llu\n",
block,
cex->ec_block, cex->ec_len, cex->ec_start);
- ret = cex->ec_type;
+ ret = 1;
}
errout:
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
@@ -2073,7 +2046,7 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
/* free index block */
path--;
- leaf = idx_pblock(path->p_idx);
+ leaf = ext4_idx_pblock(path->p_idx);
if (unlikely(path->p_hdr->eh_entries == 0)) {
EXT4_ERROR_INODE(inode, "path->p_hdr->eh_entries == 0");
return -EIO;
@@ -2181,7 +2154,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t start;
num = le32_to_cpu(ex->ee_block) + ee_len - from;
- start = ext_pblock(ex) + ee_len - num;
+ start = ext4_ext_pblock(ex) + ee_len - num;
ext_debug("free last %u blocks starting %llu\n", num, start);
ext4_free_blocks(handle, inode, 0, start, num, flags);
} else if (from == le32_to_cpu(ex->ee_block)
@@ -2310,7 +2283,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
goto out;
ext_debug("new extent: %u:%u:%llu\n", block, num,
- ext_pblock(ex));
+ ext4_ext_pblock(ex));
ex--;
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
@@ -2421,9 +2394,9 @@ again:
struct buffer_head *bh;
/* go to the next level */
ext_debug("move to level %d (block %llu)\n",
- i + 1, idx_pblock(path[i].p_idx));
+ i + 1, ext4_idx_pblock(path[i].p_idx));
memset(path + i + 1, 0, sizeof(*path));
- bh = sb_bread(sb, idx_pblock(path[i].p_idx));
+ bh = sb_bread(sb, ext4_idx_pblock(path[i].p_idx));
if (!bh) {
/* should we reset i_size? */
err = -EIO;
@@ -2535,77 +2508,21 @@ void ext4_ext_release(struct super_block *sb)
#endif
}
-static void bi_complete(struct bio *bio, int error)
-{
- complete((struct completion *)bio->bi_private);
-}
-
/* FIXME!! we need to try to merge to left or right after zero-out */
static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
{
+ ext4_fsblk_t ee_pblock;
+ unsigned int ee_len;
int ret;
- struct bio *bio;
- int blkbits, blocksize;
- sector_t ee_pblock;
- struct completion event;
- unsigned int ee_len, len, done, offset;
-
- blkbits = inode->i_blkbits;
- blocksize = inode->i_sb->s_blocksize;
ee_len = ext4_ext_get_actual_len(ex);
- ee_pblock = ext_pblock(ex);
-
- /* convert ee_pblock to 512 byte sectors */
- ee_pblock = ee_pblock << (blkbits - 9);
-
- while (ee_len > 0) {
-
- if (ee_len > BIO_MAX_PAGES)
- len = BIO_MAX_PAGES;
- else
- len = ee_len;
-
- bio = bio_alloc(GFP_NOIO, len);
- if (!bio)
- return -ENOMEM;
-
- bio->bi_sector = ee_pblock;
- bio->bi_bdev = inode->i_sb->s_bdev;
-
- done = 0;
- offset = 0;
- while (done < len) {
- ret = bio_add_page(bio, ZERO_PAGE(0),
- blocksize, offset);
- if (ret != blocksize) {
- /*
- * We can't add any more pages because of
- * hardware limitations. Start a new bio.
- */
- break;
- }
- done++;
- offset += blocksize;
- if (offset >= PAGE_CACHE_SIZE)
- offset = 0;
- }
+ ee_pblock = ext4_ext_pblock(ex);
- init_completion(&event);
- bio->bi_private = &event;
- bio->bi_end_io = bi_complete;
- submit_bio(WRITE, bio);
- wait_for_completion(&event);
+ ret = sb_issue_zeroout(inode->i_sb, ee_pblock, ee_len, GFP_NOFS);
+ if (ret > 0)
+ ret = 0;
- if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) {
- bio_put(bio);
- return -EIO;
- }
- bio_put(bio);
- ee_len -= done;
- ee_pblock += done << (blkbits - 9);
- }
- return 0;
+ return ret;
}
#define EXT4_EXT_ZERO_LEN 7
@@ -2651,12 +2568,12 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
allocated = ee_len - (map->m_lblk - ee_block);
- newblock = map->m_lblk - ee_block + ext_pblock(ex);
+ newblock = map->m_lblk - ee_block + ext4_ext_pblock(ex);
ex2 = ex;
orig_ex.ee_block = ex->ee_block;
orig_ex.ee_len = cpu_to_le16(ee_len);
- ext4_ext_store_pblock(&orig_ex, ext_pblock(ex));
+ ext4_ext_store_pblock(&orig_ex, ext4_ext_pblock(ex));
/*
* It is safe to convert extent to initialized via explicit
@@ -2675,7 +2592,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
/* update the extent length and mark as initialized */
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
- ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* zeroed the full extent */
return allocated;
@@ -2710,7 +2627,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
ex->ee_block = orig_ex.ee_block;
ex->ee_len = cpu_to_le16(ee_len - allocated);
ext4_ext_mark_uninitialized(ex);
- ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
ex3 = &newex;
@@ -2725,7 +2642,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
goto fix_extent_len;
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
- ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_store_pblock(ex,
+ ext4_ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* blocks available from map->m_lblk */
return allocated;
@@ -2782,7 +2700,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
/* update the extent length and mark as initialized */
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
- ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* zeroed the full extent */
/* blocks available from map->m_lblk */
@@ -2833,7 +2751,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
/* update the extent length and mark as initialized */
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
- ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* zero out the first half */
/* blocks available from map->m_lblk */
@@ -2902,7 +2820,7 @@ insert:
/* update the extent length and mark as initialized */
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
- ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* zero out the first half */
return allocated;
@@ -2915,7 +2833,7 @@ out:
fix_extent_len:
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
- ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_mark_uninitialized(ex);
ext4_ext_dirty(handle, inode, path + depth);
return err;
@@ -2927,14 +2845,14 @@ fix_extent_len:
* to an uninitialized extent.
*
* Writing to an uninitized extent may result in splitting the uninitialized
- * extent into multiple /intialized unintialized extents (up to three)
+ * extent into multiple /initialized uninitialized extents (up to three)
* There are three possibilities:
* a> There is no split required: Entire extent should be uninitialized
* b> Splits in two extents: Write is happening at either end of the extent
* c> Splits in three extents: Somone is writing in middle of the extent
*
* One of more index blocks maybe needed if the extent tree grow after
- * the unintialized extent split. To prevent ENOSPC occur at the IO
+ * the uninitialized extent split. To prevent ENOSPC occur at the IO
* complete, we need to split the uninitialized extent before DIO submit
* the IO. The uninitialized extent called at this time will be split
* into three uninitialized extent(at most). After IO complete, the part
@@ -2973,12 +2891,12 @@ static int ext4_split_unwritten_extents(handle_t *handle,
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
allocated = ee_len - (map->m_lblk - ee_block);
- newblock = map->m_lblk - ee_block + ext_pblock(ex);
+ newblock = map->m_lblk - ee_block + ext4_ext_pblock(ex);
ex2 = ex;
orig_ex.ee_block = ex->ee_block;
orig_ex.ee_len = cpu_to_le16(ee_len);
- ext4_ext_store_pblock(&orig_ex, ext_pblock(ex));
+ ext4_ext_store_pblock(&orig_ex, ext4_ext_pblock(ex));
/*
* It is safe to convert extent to initialized via explicit
@@ -3027,7 +2945,7 @@ static int ext4_split_unwritten_extents(handle_t *handle,
/* update the extent length and mark as initialized */
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
- ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* zeroed the full extent */
/* blocks available from map->m_lblk */
@@ -3099,7 +3017,7 @@ insert:
/* update the extent length and mark as initialized */
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
- ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_dirty(handle, inode, path + depth);
/* zero out the first half */
return allocated;
@@ -3112,7 +3030,7 @@ out:
fix_extent_len:
ex->ee_block = orig_ex.ee_block;
ex->ee_len = orig_ex.ee_len;
- ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
+ ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex));
ext4_ext_mark_uninitialized(ex);
ext4_ext_dirty(handle, inode, path + depth);
return err;
@@ -3180,6 +3098,57 @@ static void unmap_underlying_metadata_blocks(struct block_device *bdev,
unmap_underlying_metadata(bdev, block + i);
}
+/*
+ * Handle EOFBLOCKS_FL flag, clearing it if necessary
+ */
+static int check_eofblocks_fl(handle_t *handle, struct inode *inode,
+ ext4_lblk_t lblk,
+ struct ext4_ext_path *path,
+ unsigned int len)
+{
+ int i, depth;
+ struct ext4_extent_header *eh;
+ struct ext4_extent *ex, *last_ex;
+
+ if (!ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))
+ return 0;
+
+ depth = ext_depth(inode);
+ eh = path[depth].p_hdr;
+ ex = path[depth].p_ext;
+
+ if (unlikely(!eh->eh_entries)) {
+ EXT4_ERROR_INODE(inode, "eh->eh_entries == 0 and "
+ "EOFBLOCKS_FL set");
+ return -EIO;
+ }
+ last_ex = EXT_LAST_EXTENT(eh);
+ /*
+ * We should clear the EOFBLOCKS_FL flag if we are writing the
+ * last block in the last extent in the file. We test this by
+ * first checking to see if the caller to
+ * ext4_ext_get_blocks() was interested in the last block (or
+ * a block beyond the last block) in the current extent. If
+ * this turns out to be false, we can bail out from this
+ * function immediately.
+ */
+ if (lblk + len < le32_to_cpu(last_ex->ee_block) +
+ ext4_ext_get_actual_len(last_ex))
+ return 0;
+ /*
+ * If the caller does appear to be planning to write at or
+ * beyond the end of the current extent, we then test to see
+ * if the current extent is the last extent in the file, by
+ * checking to make sure it was reached via the rightmost node
+ * at each level of the tree.
+ */
+ for (i = depth-1; i >= 0; i--)
+ if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr))
+ return 0;
+ ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
+ return ext4_mark_inode_dirty(handle, inode);
+}
+
static int
ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map,
@@ -3206,7 +3175,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
* completed
*/
if (io)
- io->flag = EXT4_IO_UNWRITTEN;
+ io->flag = EXT4_IO_END_UNWRITTEN;
else
ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
if (ext4_should_dioread_nolock(inode))
@@ -3217,8 +3186,12 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
if ((flags & EXT4_GET_BLOCKS_CONVERT)) {
ret = ext4_convert_unwritten_extents_endio(handle, inode,
path);
- if (ret >= 0)
+ if (ret >= 0) {
ext4_update_inode_fsync_trans(handle, inode, 1);
+ err = check_eofblocks_fl(handle, inode, map->m_lblk,
+ path, map->m_len);
+ } else
+ err = ret;
goto out2;
}
/* buffered IO case */
@@ -3244,8 +3217,14 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
/* buffered write, writepage time, convert*/
ret = ext4_ext_convert_to_initialized(handle, inode, map, path);
- if (ret >= 0)
+ if (ret >= 0) {
ext4_update_inode_fsync_trans(handle, inode, 1);
+ err = check_eofblocks_fl(handle, inode, map->m_lblk, path,
+ map->m_len);
+ if (err < 0)
+ goto out2;
+ }
+
out:
if (ret <= 0) {
err = ret;
@@ -3292,6 +3271,7 @@ out2:
}
return err ? err : allocated;
}
+
/*
* Block allocation/map/preallocation routine for extents based files
*
@@ -3315,9 +3295,9 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
{
struct ext4_ext_path *path = NULL;
struct ext4_extent_header *eh;
- struct ext4_extent newex, *ex, *last_ex;
+ struct ext4_extent newex, *ex;
ext4_fsblk_t newblock;
- int i, err = 0, depth, ret, cache_type;
+ int err = 0, depth, ret;
unsigned int allocated = 0;
struct ext4_allocation_request ar;
ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
@@ -3326,9 +3306,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
map->m_lblk, map->m_len, inode->i_ino);
/* check in cache */
- cache_type = ext4_ext_in_cache(inode, map->m_lblk, &newex);
- if (cache_type) {
- if (cache_type == EXT4_EXT_CACHE_GAP) {
+ if (ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
+ if (!newex.ee_start_lo && !newex.ee_start_hi) {
if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
/*
* block isn't allocated yet and
@@ -3337,17 +3316,15 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
goto out2;
}
/* we should allocate requested block */
- } else if (cache_type == EXT4_EXT_CACHE_EXTENT) {
+ } else {
/* block is already allocated */
newblock = map->m_lblk
- le32_to_cpu(newex.ee_block)
- + ext_pblock(&newex);
+ + ext4_ext_pblock(&newex);
/* number of remaining blocks in the extent */
allocated = ext4_ext_get_actual_len(&newex) -
(map->m_lblk - le32_to_cpu(newex.ee_block));
goto out;
- } else {
- BUG();
}
}
@@ -3379,7 +3356,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
ex = path[depth].p_ext;
if (ex) {
ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block);
- ext4_fsblk_t ee_start = ext_pblock(ex);
+ ext4_fsblk_t ee_start = ext4_ext_pblock(ex);
unsigned short ee_len;
/*
@@ -3398,8 +3375,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
/* Do not put uninitialized extent in the cache */
if (!ext4_ext_is_uninitialized(ex)) {
ext4_ext_put_in_cache(inode, ee_block,
- ee_len, ee_start,
- EXT4_EXT_CACHE_EXTENT);
+ ee_len, ee_start);
goto out;
}
ret = ext4_ext_handle_uninitialized_extents(handle,
@@ -3488,7 +3464,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
*/
if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
if (io)
- io->flag = EXT4_IO_UNWRITTEN;
+ io->flag = EXT4_IO_END_UNWRITTEN;
else
ext4_set_inode_state(inode,
EXT4_STATE_DIO_UNWRITTEN);
@@ -3497,44 +3473,23 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
map->m_flags |= EXT4_MAP_UNINIT;
}
- if (unlikely(ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))) {
- if (unlikely(!eh->eh_entries)) {
- EXT4_ERROR_INODE(inode,
- "eh->eh_entries == 0 and "
- "EOFBLOCKS_FL set");
- err = -EIO;
- goto out2;
- }
- last_ex = EXT_LAST_EXTENT(eh);
- /*
- * If the current leaf block was reached by looking at
- * the last index block all the way down the tree, and
- * we are extending the inode beyond the last extent
- * in the current leaf block, then clear the
- * EOFBLOCKS_FL flag.
- */
- for (i = depth-1; i >= 0; i--) {
- if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr))
- break;
- }
- if ((i < 0) &&
- (map->m_lblk + ar.len > le32_to_cpu(last_ex->ee_block) +
- ext4_ext_get_actual_len(last_ex)))
- ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
- }
+ err = check_eofblocks_fl(handle, inode, map->m_lblk, path, ar.len);
+ if (err)
+ goto out2;
+
err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
if (err) {
/* free data blocks we just allocated */
/* 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, 0, ext_pblock(&newex),
+ ext4_free_blocks(handle, inode, 0, ext4_ext_pblock(&newex),
ext4_ext_get_actual_len(&newex), 0);
goto out2;
}
/* previous routine could use block we allocated */
- newblock = ext_pblock(&newex);
+ newblock = ext4_ext_pblock(&newex);
allocated = ext4_ext_get_actual_len(&newex);
if (allocated > map->m_len)
allocated = map->m_len;
@@ -3552,8 +3507,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
* when it is _not_ an uninitialized extent.
*/
if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0) {
- ext4_ext_put_in_cache(inode, map->m_lblk, allocated, newblock,
- EXT4_EXT_CACHE_EXTENT);
+ ext4_ext_put_in_cache(inode, map->m_lblk, allocated, newblock);
ext4_update_inode_fsync_trans(handle, inode, 1);
} else
ext4_update_inode_fsync_trans(handle, inode, 0);
@@ -3581,6 +3535,12 @@ void ext4_ext_truncate(struct inode *inode)
int err = 0;
/*
+ * finish any pending end_io work so we won't run the risk of
+ * converting any truncated blocks to initialized later
+ */
+ ext4_flush_completed_IO(inode);
+
+ /*
* probably first extent we're gonna free will be last in block
*/
err = ext4_writepage_trans_blocks(inode);
@@ -3667,14 +3627,15 @@ static void ext4_falloc_update_inode(struct inode *inode,
}
/*
- * preallocate space for a file. This implements ext4's fallocate inode
+ * preallocate space for a file. This implements ext4's fallocate file
* operation, which gets called from sys_fallocate system call.
* For block-mapped files, posix_fallocate should fall back to the method
* of writing zeroes to the required new blocks (the same behavior which is
* expected for file systems which do not support fallocate() system call).
*/
-long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
+long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
+ struct inode *inode = file->f_path.dentry->d_inode;
handle_t *handle;
loff_t new_size;
unsigned int max_blocks;
@@ -3684,6 +3645,10 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
struct ext4_map_blocks map;
unsigned int credits, blkbits = inode->i_blkbits;
+ /* We only support the FALLOC_FL_KEEP_SIZE mode */
+ if (mode & ~FALLOC_FL_KEEP_SIZE)
+ return -EOPNOTSUPP;
+
/*
* currently supporting (pre)allocate mode for extent-based
* files _only_
@@ -3691,10 +3656,6 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return -EOPNOTSUPP;
- /* preallocation to directories is currently not supported */
- if (S_ISDIR(inode->i_mode))
- return -ENODEV;
-
map.m_lblk = offset >> blkbits;
/*
* We can't just convert len to max_blocks because
@@ -3729,7 +3690,7 @@ retry:
printk(KERN_ERR "%s: ext4_ext_map_blocks "
"returned error inode#%lu, block=%u, "
"max_blocks=%u", __func__,
- inode->i_ino, block, max_blocks);
+ inode->i_ino, map.m_lblk, max_blocks);
#endif
ext4_mark_inode_dirty(handle, inode);
ret2 = ext4_journal_stop(handle);
@@ -3829,7 +3790,7 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
logical = (__u64)newex->ec_block << blksize_bits;
- if (newex->ec_type == EXT4_EXT_CACHE_GAP) {
+ if (newex->ec_start == 0) {
pgoff_t offset;
struct page *page;
struct buffer_head *bh = NULL;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index ee92b66d455..2e8322c8aa8 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -104,6 +104,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
{
struct super_block *sb = inode->i_sb;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ struct ext4_inode_info *ei = EXT4_I(inode);
struct vfsmount *mnt = filp->f_path.mnt;
struct path path;
char buf[64], *cp;
@@ -127,11 +128,74 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
ext4_mark_super_dirty(sb);
}
}
+ /*
+ * Set up the jbd2_inode if we are opening the inode for
+ * writing and the journal is present
+ */
+ if (sbi->s_journal && !ei->jinode && (filp->f_mode & FMODE_WRITE)) {
+ struct jbd2_inode *jinode = jbd2_alloc_inode(GFP_KERNEL);
+
+ spin_lock(&inode->i_lock);
+ if (!ei->jinode) {
+ if (!jinode) {
+ spin_unlock(&inode->i_lock);
+ return -ENOMEM;
+ }
+ ei->jinode = jinode;
+ jbd2_journal_init_jbd_inode(ei->jinode, inode);
+ jinode = NULL;
+ }
+ spin_unlock(&inode->i_lock);
+ if (unlikely(jinode != NULL))
+ jbd2_free_inode(jinode);
+ }
return dquot_file_open(inode, filp);
}
+/*
+ * ext4_llseek() copied from generic_file_llseek() to handle both
+ * block-mapped and extent-mapped maxbytes values. This should
+ * otherwise be identical with generic_file_llseek().
+ */
+loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
+{
+ struct inode *inode = file->f_mapping->host;
+ loff_t maxbytes;
+
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+ maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes;
+ else
+ maxbytes = inode->i_sb->s_maxbytes;
+ mutex_lock(&inode->i_mutex);
+ switch (origin) {
+ case SEEK_END:
+ offset += inode->i_size;
+ break;
+ case SEEK_CUR:
+ if (offset == 0) {
+ mutex_unlock(&inode->i_mutex);
+ return file->f_pos;
+ }
+ offset += file->f_pos;
+ break;
+ }
+
+ if (offset < 0 || offset > maxbytes) {
+ mutex_unlock(&inode->i_mutex);
+ return -EINVAL;
+ }
+
+ if (offset != file->f_pos) {
+ file->f_pos = offset;
+ file->f_version = 0;
+ }
+ mutex_unlock(&inode->i_mutex);
+
+ return offset;
+}
+
const struct file_operations ext4_file_operations = {
- .llseek = generic_file_llseek,
+ .llseek = ext4_llseek,
.read = do_sync_read,
.write = do_sync_write,
.aio_read = generic_file_aio_read,
@@ -146,6 +210,7 @@ const struct file_operations ext4_file_operations = {
.fsync = ext4_sync_file,
.splice_read = generic_file_splice_read,
.splice_write = generic_file_splice_write,
+ .fallocate = ext4_fallocate,
};
const struct inode_operations ext4_file_inode_operations = {
@@ -159,7 +224,6 @@ const struct inode_operations ext4_file_inode_operations = {
.removexattr = generic_removexattr,
#endif
.check_acl = ext4_check_acl,
- .fallocate = ext4_fallocate,
.fiemap = ext4_fiemap,
};
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 592adf2e546..7829b287822 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -34,6 +34,89 @@
#include <trace/events/ext4.h>
+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_completed_io_list)){
+ ext4_debug("inode %lu completed_io list is empty\n", inode->i_ino);
+ return;
+ }
+
+ 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);
+ after = cur->next;
+ io1 = container_of(after, ext4_io_end_t, list);
+
+ 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
+}
+
+/*
+ * This function is called from ext4_sync_file().
+ *
+ * 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 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.
+ */
+extern int ext4_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(&ei->i_completed_io_list))
+ return ret;
+
+ 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_io_nolock() to convert completed
+ * IO to written.
+ *
+ * When ext4_sync_file() is called, run_queue() may already
+ * about to flush the work corresponding to this io structure.
+ * It will be upset if it founds the io structure related
+ * to the work-to-be schedule is freed.
+ *
+ * Thus we need to keep the io structure still valid here after
+ * convertion finished. The io structure has a flag to
+ * avoid double converting from both fsync and background work
+ * queue work.
+ */
+ 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;
+}
+
/*
* If we're not journaling and this is a just-created file, we have to
* sync our parent directory (if it was freshly created) since
@@ -86,7 +169,7 @@ int ext4_sync_file(struct file *file, int datasync)
if (inode->i_sb->s_flags & MS_RDONLY)
return 0;
- ret = flush_completed_IO(inode);
+ ret = ext4_flush_completed_IO(inode);
if (ret < 0)
return ret;
@@ -128,10 +211,9 @@ int ext4_sync_file(struct file *file, int datasync)
(journal->j_fs_dev != journal->j_dev) &&
(journal->j_flags & JBD2_BARRIER))
blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL,
- NULL, BLKDEV_IFL_WAIT);
+ NULL);
ret = jbd2_log_wait_commit(journal, commit_tid);
} else if (journal->j_flags & JBD2_BARRIER)
- blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL,
- BLKDEV_IFL_WAIT);
+ blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
return ret;
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 45853e0d1f2..eb9097aec6f 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -50,7 +50,7 @@
* need to use it within a single byte (to ensure we get endianness right).
* We can use memset for the rest of the bitmap as there are no other users.
*/
-void mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
+void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
{
int i;
@@ -65,9 +65,10 @@ void mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
}
/* Initializes an uninitialized inode bitmap */
-unsigned ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh,
- ext4_group_t block_group,
- struct ext4_group_desc *gdp)
+static unsigned ext4_init_inode_bitmap(struct super_block *sb,
+ struct buffer_head *bh,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -85,7 +86,7 @@ unsigned ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh,
}
memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8);
- mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
+ ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
bh->b_data);
return EXT4_INODES_PER_GROUP(sb);
@@ -107,6 +108,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
desc = ext4_get_group_desc(sb, block_group, NULL);
if (!desc)
return NULL;
+
bitmap_blk = ext4_inode_bitmap(sb, desc);
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
@@ -123,6 +125,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
unlock_buffer(bh);
return bh;
}
+
ext4_lock_group(sb, block_group);
if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
ext4_init_inode_bitmap(sb, bh, block_group, desc);
@@ -133,6 +136,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
return bh;
}
ext4_unlock_group(sb, block_group);
+
if (buffer_uptodate(bh)) {
/*
* if not uninit if bh is uptodate,
@@ -411,8 +415,8 @@ struct orlov_stats {
* for a particular block group or flex_bg. If flex_size is 1, then g
* is a block group number; otherwise it is flex_bg number.
*/
-void get_orlov_stats(struct super_block *sb, ext4_group_t g,
- int flex_size, struct orlov_stats *stats)
+static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
+ int flex_size, struct orlov_stats *stats)
{
struct ext4_group_desc *desc;
struct flex_groups *flex_group = EXT4_SB(sb)->s_flex_groups;
@@ -712,8 +716,17 @@ static int ext4_claim_inode(struct super_block *sb,
{
int free = 0, retval = 0, count;
struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_group_info *grp = ext4_get_group_info(sb, group);
struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
+ /*
+ * We have to be sure that new inode allocation does not race with
+ * inode table initialization, because otherwise we may end up
+ * allocating and writing new inode right before sb_issue_zeroout
+ * takes place and overwriting our new inode with zeroes. So we
+ * take alloc_sem to prevent it.
+ */
+ down_read(&grp->alloc_sem);
ext4_lock_group(sb, group);
if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) {
/* not a free inode */
@@ -724,6 +737,7 @@ static int ext4_claim_inode(struct super_block *sb,
if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
ino > EXT4_INODES_PER_GROUP(sb)) {
ext4_unlock_group(sb, group);
+ up_read(&grp->alloc_sem);
ext4_error(sb, "reserved inode or inode > inodes count - "
"block_group = %u, inode=%lu", group,
ino + group * EXT4_INODES_PER_GROUP(sb));
@@ -772,6 +786,7 @@ static int ext4_claim_inode(struct super_block *sb,
gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
err_ret:
ext4_unlock_group(sb, group);
+ up_read(&grp->alloc_sem);
return retval;
}
@@ -1012,7 +1027,7 @@ got:
inode->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
- ei->i_state_flags = 0;
+ ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */
ext4_set_inode_state(inode, EXT4_STATE_NEW);
ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;
@@ -1205,3 +1220,109 @@ unsigned long ext4_count_dirs(struct super_block * sb)
}
return count;
}
+
+/*
+ * Zeroes not yet zeroed inode table - just write zeroes through the whole
+ * inode table. Must be called without any spinlock held. The only place
+ * where it is called from on active part of filesystem is ext4lazyinit
+ * thread, so we do not need any special locks, however we have to prevent
+ * inode allocation from the current group, so we take alloc_sem lock, to
+ * block ext4_claim_inode until we are finished.
+ */
+extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
+ int barrier)
+{
+ struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_group_desc *gdp = NULL;
+ struct buffer_head *group_desc_bh;
+ handle_t *handle;
+ ext4_fsblk_t blk;
+ int num, ret = 0, used_blks = 0;
+
+ /* This should not happen, but just to be sure check this */
+ if (sb->s_flags & MS_RDONLY) {
+ ret = 1;
+ goto out;
+ }
+
+ gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
+ if (!gdp)
+ goto out;
+
+ /*
+ * We do not need to lock this, because we are the only one
+ * handling this flag.
+ */
+ if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))
+ goto out;
+
+ handle = ext4_journal_start_sb(sb, 1);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+
+ down_write(&grp->alloc_sem);
+ /*
+ * If inode bitmap was already initialized there may be some
+ * used inodes so we need to skip blocks with used inodes in
+ * inode table.
+ */
+ if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)))
+ used_blks = DIV_ROUND_UP((EXT4_INODES_PER_GROUP(sb) -
+ ext4_itable_unused_count(sb, gdp)),
+ sbi->s_inodes_per_block);
+
+ if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) {
+ ext4_error(sb, "Something is wrong with group %u\n"
+ "Used itable blocks: %d"
+ "itable unused count: %u\n",
+ group, used_blks,
+ ext4_itable_unused_count(sb, gdp));
+ ret = 1;
+ goto out;
+ }
+
+ blk = ext4_inode_table(sb, gdp) + used_blks;
+ num = sbi->s_itb_per_group - used_blks;
+
+ BUFFER_TRACE(group_desc_bh, "get_write_access");
+ ret = ext4_journal_get_write_access(handle,
+ group_desc_bh);
+ if (ret)
+ goto err_out;
+
+ /*
+ * Skip zeroout if the inode table is full. But we set the ZEROED
+ * flag anyway, because obviously, when it is full it does not need
+ * further zeroing.
+ */
+ if (unlikely(num == 0))
+ goto skip_zeroout;
+
+ ext4_debug("going to zero out inode table in group %d\n",
+ group);
+ ret = sb_issue_zeroout(sb, blk, num, GFP_NOFS);
+ if (ret < 0)
+ goto err_out;
+ if (barrier)
+ blkdev_issue_flush(sb->s_bdev, GFP_NOFS, NULL);
+
+skip_zeroout:
+ ext4_lock_group(sb, group);
+ gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED);
+ gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
+ ext4_unlock_group(sb, group);
+
+ BUFFER_TRACE(group_desc_bh,
+ "call ext4_handle_dirty_metadata");
+ ret = ext4_handle_dirty_metadata(handle, NULL,
+ group_desc_bh);
+
+err_out:
+ up_write(&grp->alloc_sem);
+ ext4_journal_stop(handle);
+out:
+ return ret;
+}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 4b8debeb396..9f7f9e49914 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -39,7 +39,9 @@
#include <linux/bio.h>
#include <linux/workqueue.h>
#include <linux/kernel.h>
+#include <linux/printk.h>
#include <linux/slab.h>
+#include <linux/ratelimit.h>
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -53,13 +55,27 @@
static inline int ext4_begin_ordered_truncate(struct inode *inode,
loff_t new_size)
{
- return jbd2_journal_begin_ordered_truncate(
- EXT4_SB(inode->i_sb)->s_journal,
- &EXT4_I(inode)->jinode,
- new_size);
+ trace_ext4_begin_ordered_truncate(inode, new_size);
+ /*
+ * If jinode is zero, then we never opened the file for
+ * writing, so there's no need to call
+ * jbd2_journal_begin_ordered_truncate() since there's no
+ * outstanding writes we need to flush.
+ */
+ if (!EXT4_I(inode)->jinode)
+ return 0;
+ return jbd2_journal_begin_ordered_truncate(EXT4_JOURNAL(inode),
+ EXT4_I(inode)->jinode,
+ new_size);
}
static void ext4_invalidatepage(struct page *page, unsigned long offset);
+static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create);
+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);
+static int __ext4_journalled_writepage(struct page *page, unsigned int len);
+static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh);
/*
* Test whether an inode is a fast symlink.
@@ -172,6 +188,7 @@ void ext4_evict_inode(struct inode *inode)
handle_t *handle;
int err;
+ trace_ext4_evict_inode(inode);
if (inode->i_nlink) {
truncate_inode_pages(&inode->i_data, 0);
goto no_delete;
@@ -544,7 +561,7 @@ static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
}
/**
- * ext4_blks_to_allocate: Look up the block map and count the number
+ * ext4_blks_to_allocate - Look up the block map and count the number
* of direct blocks need to be allocated for the given branch.
*
* @branch: chain of indirect blocks
@@ -583,13 +600,19 @@ static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
/**
* ext4_alloc_blocks: multiple allocate blocks needed for a branch
+ * @handle: handle for this transaction
+ * @inode: inode which needs allocated blocks
+ * @iblock: the logical block to start allocated at
+ * @goal: preferred physical block of allocation
* @indirect_blks: the number of blocks need to allocate for indirect
* blocks
- *
+ * @blks: number of desired blocks
* @new_blocks: on return it will store the new block numbers for
* the indirect blocks(if needed) and the first direct block,
- * @blks: on return it will store the total number of allocated
- * direct blocks
+ * @err: on return it will store the error code
+ *
+ * This function will return the number of blocks allocated as
+ * requested by the passed-in parameters.
*/
static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
ext4_lblk_t iblock, ext4_fsblk_t goal,
@@ -703,9 +726,11 @@ failed_out:
/**
* ext4_alloc_branch - allocate and set up a chain of blocks.
+ * @handle: handle for this transaction
* @inode: owner
* @indirect_blks: number of allocated indirect blocks
* @blks: number of allocated direct blocks
+ * @goal: preferred place for allocation
* @offsets: offsets (in the blocks) to store the pointers to next.
* @branch: place to store the chain in.
*
@@ -755,6 +780,11 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
* parent to disk.
*/
bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
+ if (unlikely(!bh)) {
+ err = -EIO;
+ goto failed;
+ }
+
branch[n].bh = bh;
lock_buffer(bh);
BUFFER_TRACE(bh, "call get_create_access");
@@ -813,6 +843,7 @@ failed:
/**
* ext4_splice_branch - splice the allocated branch onto inode.
+ * @handle: handle for this transaction
* @inode: owner
* @block: (logical) number of block we are adding
* @chain: chain of indirect blocks (with a missing link - see
@@ -1068,7 +1099,7 @@ static int ext4_indirect_calc_metadata_amount(struct inode *inode,
* Calculate the number of metadata blocks need to reserve
* to allocate a block located at @lblock
*/
-static int ext4_calc_metadata_amount(struct inode *inode, sector_t lblock)
+static int ext4_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
{
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
return ext4_ext_calc_metadata_amount(inode, lblock);
@@ -1207,8 +1238,10 @@ static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
break;
idx++;
num++;
- if (num >= max_pages)
+ if (num >= max_pages) {
+ done = 1;
break;
+ }
}
pagevec_release(&pvec);
}
@@ -1305,7 +1338,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
* avoid double accounting
*/
if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
- EXT4_I(inode)->i_delalloc_reserved_flag = 1;
+ ext4_set_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
/*
* We need to check for EXT4 here because migrate
* could have changed the inode type in between
@@ -1335,7 +1368,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
ext4_da_update_reserve_space(inode, retval, 1);
}
if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
- EXT4_I(inode)->i_delalloc_reserved_flag = 0;
+ ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
@@ -1538,10 +1571,10 @@ static int do_journal_get_write_access(handle_t *handle,
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
/*
- * __block_prepare_write() could have dirtied some buffers. Clean
+ * __block_write_begin() could have dirtied some buffers. Clean
* the dirty bit as jbd2_journal_get_write_access() could complain
* otherwise about fs integrity issues. Setting of the dirty bit
- * by __block_prepare_write() isn't a real problem here as we clear
+ * by __block_write_begin() isn't a real problem here as we clear
* the bit before releasing a page lock and thus writeback cannot
* ever write the buffer.
*/
@@ -1863,7 +1896,7 @@ static int ext4_journalled_write_end(struct file *file,
/*
* Reserve a single block located at lblock
*/
-static int ext4_da_reserve_space(struct inode *inode, sector_t lblock)
+static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
{
int retries = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -1995,16 +2028,23 @@ static void ext4_da_page_release_reservation(struct page *page,
*
* As pages are already locked by write_cache_pages(), we can't use it
*/
-static int mpage_da_submit_io(struct mpage_da_data *mpd)
+static int mpage_da_submit_io(struct mpage_da_data *mpd,
+ struct ext4_map_blocks *map)
{
- long pages_skipped;
struct pagevec pvec;
unsigned long index, end;
int ret = 0, err, nr_pages, i;
struct inode *inode = mpd->inode;
struct address_space *mapping = inode->i_mapping;
+ loff_t size = i_size_read(inode);
+ unsigned int len, block_start;
+ struct buffer_head *bh, *page_bufs = NULL;
+ int journal_data = ext4_should_journal_data(inode);
+ sector_t pblock = 0, cur_logical = 0;
+ struct ext4_io_submit io_submit;
BUG_ON(mpd->next_page <= mpd->first_page);
+ memset(&io_submit, 0, sizeof(io_submit));
/*
* We need to start from the first_page to the next_page - 1
* to make sure we also write the mapped dirty buffer_heads.
@@ -2020,122 +2060,111 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd)
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
+ int commit_write = 0, redirty_page = 0;
struct page *page = pvec.pages[i];
index = page->index;
if (index > end)
break;
+
+ if (index == size >> PAGE_CACHE_SHIFT)
+ len = size & ~PAGE_CACHE_MASK;
+ else
+ len = PAGE_CACHE_SIZE;
+ if (map) {
+ cur_logical = index << (PAGE_CACHE_SHIFT -
+ inode->i_blkbits);
+ pblock = map->m_pblk + (cur_logical -
+ map->m_lblk);
+ }
index++;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
- pages_skipped = mpd->wbc->pages_skipped;
- err = mapping->a_ops->writepage(page, mpd->wbc);
- if (!err && (pages_skipped == mpd->wbc->pages_skipped))
- /*
- * have successfully written the page
- * without skipping the same
- */
- mpd->pages_written++;
/*
- * In error case, we have to continue because
- * remaining pages are still locked
- * XXX: unlock and re-dirty them?
+ * If the page does not have buffers (for
+ * whatever reason), try to create them using
+ * __block_write_begin. If this fails,
+ * redirty the page and move on.
*/
- if (ret == 0)
- ret = err;
- }
- pagevec_release(&pvec);
- }
- return ret;
-}
-
-/*
- * mpage_put_bnr_to_bhs - walk blocks and assign them actual numbers
- *
- * the function goes through all passed space and put actual disk
- * block numbers into buffer heads, dropping BH_Delay and BH_Unwritten
- */
-static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd,
- struct ext4_map_blocks *map)
-{
- struct inode *inode = mpd->inode;
- struct address_space *mapping = inode->i_mapping;
- int blocks = map->m_len;
- sector_t pblock = map->m_pblk, cur_logical;
- struct buffer_head *head, *bh;
- pgoff_t index, end;
- struct pagevec pvec;
- int nr_pages, i;
-
- index = map->m_lblk >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
- end = (map->m_lblk + blocks - 1) >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
- cur_logical = index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
-
- pagevec_init(&pvec, 0);
-
- while (index <= end) {
- /* XXX: optimize tail */
- nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
- if (nr_pages == 0)
- break;
- for (i = 0; i < nr_pages; i++) {
- struct page *page = pvec.pages[i];
-
- index = page->index;
- if (index > end)
- break;
- index++;
-
- BUG_ON(!PageLocked(page));
- BUG_ON(PageWriteback(page));
- BUG_ON(!page_has_buffers(page));
-
- bh = page_buffers(page);
- head = bh;
-
- /* skip blocks out of the range */
- do {
- if (cur_logical >= map->m_lblk)
- break;
- cur_logical++;
- } while ((bh = bh->b_this_page) != head);
+ if (!page_has_buffers(page)) {
+ if (__block_write_begin(page, 0, len,
+ noalloc_get_block_write)) {
+ redirty_page:
+ redirty_page_for_writepage(mpd->wbc,
+ page);
+ unlock_page(page);
+ continue;
+ }
+ commit_write = 1;
+ }
+ bh = page_bufs = page_buffers(page);
+ block_start = 0;
do {
- if (cur_logical >= map->m_lblk + blocks)
- break;
-
- if (buffer_delay(bh) || buffer_unwritten(bh)) {
-
- BUG_ON(bh->b_bdev != inode->i_sb->s_bdev);
-
+ if (!bh)
+ goto redirty_page;
+ if (map && (cur_logical >= map->m_lblk) &&
+ (cur_logical <= (map->m_lblk +
+ (map->m_len - 1)))) {
if (buffer_delay(bh)) {
clear_buffer_delay(bh);
bh->b_blocknr = pblock;
- } else {
- /*
- * unwritten already should have
- * blocknr assigned. Verify that
- */
- clear_buffer_unwritten(bh);
- BUG_ON(bh->b_blocknr != pblock);
}
+ if (buffer_unwritten(bh) ||
+ buffer_mapped(bh))
+ BUG_ON(bh->b_blocknr != pblock);
+ if (map->m_flags & EXT4_MAP_UNINIT)
+ set_buffer_uninit(bh);
+ clear_buffer_unwritten(bh);
+ }
- } else if (buffer_mapped(bh))
- BUG_ON(bh->b_blocknr != pblock);
-
- if (map->m_flags & EXT4_MAP_UNINIT)
- set_buffer_uninit(bh);
+ /* redirty page if block allocation undone */
+ if (buffer_delay(bh) || buffer_unwritten(bh))
+ redirty_page = 1;
+ bh = bh->b_this_page;
+ block_start += bh->b_size;
cur_logical++;
pblock++;
- } while ((bh = bh->b_this_page) != head);
+ } while (bh != page_bufs);
+
+ if (redirty_page)
+ goto redirty_page;
+
+ if (commit_write)
+ /* mark the buffer_heads as dirty & uptodate */
+ block_commit_write(page, 0, len);
+
+ /*
+ * Delalloc doesn't support data journalling,
+ * but eventually maybe we'll lift this
+ * restriction.
+ */
+ if (unlikely(journal_data && PageChecked(page)))
+ err = __ext4_journalled_writepage(page, len);
+ else if (test_opt(inode->i_sb, MBLK_IO_SUBMIT))
+ err = ext4_bio_write_page(&io_submit, page,
+ len, mpd->wbc);
+ else
+ err = block_write_full_page(page,
+ noalloc_get_block_write, mpd->wbc);
+
+ if (!err)
+ mpd->pages_written++;
+ /*
+ * In error case, we have to continue because
+ * remaining pages are still locked
+ */
+ if (ret == 0)
+ ret = err;
}
pagevec_release(&pvec);
}
+ ext4_io_submit(&io_submit);
+ return ret;
}
-
static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd,
sector_t logical, long blk_cnt)
{
@@ -2187,35 +2216,32 @@ static void ext4_print_free_blocks(struct inode *inode)
}
/*
- * mpage_da_map_blocks - go through given space
+ * mpage_da_map_and_submit - go through given space, map them
+ * if necessary, and then submit them for I/O
*
* @mpd - bh describing space
*
* The function skips space we know is already mapped to disk blocks.
*
*/
-static int mpage_da_map_blocks(struct mpage_da_data *mpd)
+static void mpage_da_map_and_submit(struct mpage_da_data *mpd)
{
int err, blks, get_blocks_flags;
- struct ext4_map_blocks map;
+ struct ext4_map_blocks map, *mapp = NULL;
sector_t next = mpd->b_blocknr;
unsigned max_blocks = mpd->b_size >> mpd->inode->i_blkbits;
loff_t disksize = EXT4_I(mpd->inode)->i_disksize;
handle_t *handle = NULL;
/*
- * We consider only non-mapped and non-allocated blocks
+ * If the blocks are mapped already, or we couldn't accumulate
+ * any blocks, then proceed immediately to the submission stage.
*/
- if ((mpd->b_state & (1 << BH_Mapped)) &&
- !(mpd->b_state & (1 << BH_Delay)) &&
- !(mpd->b_state & (1 << BH_Unwritten)))
- return 0;
-
- /*
- * If we didn't accumulate anything to write simply return
- */
- if (!mpd->b_size)
- return 0;
+ if ((mpd->b_size == 0) ||
+ ((mpd->b_state & (1 << BH_Mapped)) &&
+ !(mpd->b_state & (1 << BH_Delay)) &&
+ !(mpd->b_state & (1 << BH_Unwritten))))
+ goto submit_io;
handle = ext4_journal_current_handle();
BUG_ON(!handle);
@@ -2231,7 +2257,7 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd)
* affects functions in many different parts of the allocation
* call path. This flag exists primarily because we don't
* want to change *many* call functions, so ext4_map_blocks()
- * will set the magic i_delalloc_reserved_flag once the
+ * will set the EXT4_STATE_DELALLOC_RESERVED flag once the
* inode's allocation semaphore is taken.
*
* If the blocks in questions were delalloc blocks, set
@@ -2252,17 +2278,18 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd)
err = blks;
/*
- * If get block returns with error we simply
- * return. Later writepage will redirty the page and
- * writepages will find the dirty page again
+ * If get block returns EAGAIN or ENOSPC and there
+ * appears to be free blocks we will call
+ * ext4_writepage() for all of the pages which will
+ * just redirty the pages.
*/
if (err == -EAGAIN)
- return 0;
+ goto submit_io;
if (err == -ENOSPC &&
ext4_count_free_blocks(sb)) {
mpd->retval = err;
- return 0;
+ goto submit_io;
}
/*
@@ -2287,10 +2314,11 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd)
/* invalidate all the pages */
ext4_da_block_invalidatepages(mpd, next,
mpd->b_size >> mpd->inode->i_blkbits);
- return err;
+ return;
}
BUG_ON(blks == 0);
+ mapp = &map;
if (map.m_flags & EXT4_MAP_NEW) {
struct block_device *bdev = mpd->inode->i_sb->s_bdev;
int i;
@@ -2299,18 +2327,11 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd)
unmap_underlying_metadata(bdev, map.m_pblk + i);
}
- /*
- * If blocks are delayed marked, we need to
- * put actual blocknr and drop delayed bit
- */
- if ((mpd->b_state & (1 << BH_Delay)) ||
- (mpd->b_state & (1 << BH_Unwritten)))
- mpage_put_bnr_to_bhs(mpd, &map);
-
if (ext4_should_order_data(mpd->inode)) {
err = ext4_jbd2_file_inode(handle, mpd->inode);
if (err)
- return err;
+ /* This only happens if the journal is aborted */
+ return;
}
/*
@@ -2321,10 +2342,16 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd)
disksize = i_size_read(mpd->inode);
if (disksize > EXT4_I(mpd->inode)->i_disksize) {
ext4_update_i_disksize(mpd->inode, disksize);
- return ext4_mark_inode_dirty(handle, mpd->inode);
+ err = ext4_mark_inode_dirty(handle, mpd->inode);
+ if (err)
+ ext4_error(mpd->inode->i_sb,
+ "Failed to mark inode %lu dirty",
+ mpd->inode->i_ino);
}
- return 0;
+submit_io:
+ mpage_da_submit_io(mpd, mapp);
+ mpd->io_done = 1;
}
#define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | \
@@ -2401,9 +2428,7 @@ flush_it:
* We couldn't merge the block to our extent, so we
* need to flush current extent and start new one
*/
- if (mpage_da_map_blocks(mpd) == 0)
- mpage_da_submit_io(mpd);
- mpd->io_done = 1;
+ mpage_da_map_and_submit(mpd);
return;
}
@@ -2422,9 +2447,9 @@ static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh)
* The function finds extents of pages and scan them for all blocks.
*/
static int __mpage_da_writepage(struct page *page,
- struct writeback_control *wbc, void *data)
+ struct writeback_control *wbc,
+ struct mpage_da_data *mpd)
{
- struct mpage_da_data *mpd = data;
struct inode *inode = mpd->inode;
struct buffer_head *bh, *head;
sector_t logical;
@@ -2435,15 +2460,13 @@ static int __mpage_da_writepage(struct page *page,
if (mpd->next_page != page->index) {
/*
* Nope, we can't. So, we map non-allocated blocks
- * and start IO on them using writepage()
+ * and start IO on them
*/
if (mpd->next_page != mpd->first_page) {
- if (mpage_da_map_blocks(mpd) == 0)
- mpage_da_submit_io(mpd);
+ mpage_da_map_and_submit(mpd);
/*
* skip rest of the page in the page_vec
*/
- mpd->io_done = 1;
redirty_page_for_writepage(wbc, page);
unlock_page(page);
return MPAGE_DA_EXTENT_TAIL;
@@ -2550,8 +2573,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
if (buffer_delay(bh))
return 0; /* Not sure this could or should happen */
/*
- * XXX: __block_prepare_write() unmaps passed block,
- * is it OK?
+ * XXX: __block_write_begin() unmaps passed block, is it OK?
*/
ret = ext4_da_reserve_space(inode, iblock);
if (ret)
@@ -2583,7 +2605,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
/*
* This function is used as a standard get_block_t calback function
* when there is no desire to allocate any blocks. It is used as a
- * callback function for block_prepare_write() and block_write_full_page().
+ * callback function for block_write_begin() and block_write_full_page().
* These functions should only try to map a single block at a time.
*
* Since this function doesn't do block allocations even if the caller
@@ -2623,6 +2645,7 @@ static int __ext4_journalled_writepage(struct page *page,
int ret = 0;
int err;
+ ClearPageChecked(page);
page_bufs = page_buffers(page);
BUG_ON(!page_bufs);
walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one);
@@ -2700,7 +2723,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
static int ext4_writepage(struct page *page,
struct writeback_control *wbc)
{
- int ret = 0;
+ int ret = 0, commit_write = 0;
loff_t size;
unsigned int len;
struct buffer_head *page_bufs = NULL;
@@ -2713,71 +2736,44 @@ static int ext4_writepage(struct page *page,
else
len = PAGE_CACHE_SIZE;
- if (page_has_buffers(page)) {
- page_bufs = page_buffers(page);
- if (walk_page_buffers(NULL, page_bufs, 0, len, NULL,
- ext4_bh_delay_or_unwritten)) {
- /*
- * We don't want to do block allocation
- * So redirty the page and return
- * We may reach here when we do a journal commit
- * via journal_submit_inode_data_buffers.
- * If we don't have mapping block we just ignore
- * them. We can also reach here via shrink_page_list
- */
+ /*
+ * If the page does not have buffers (for whatever reason),
+ * try to create them using __block_write_begin. If this
+ * fails, redirty the page and move on.
+ */
+ if (!page_has_buffers(page)) {
+ if (__block_write_begin(page, 0, len,
+ noalloc_get_block_write)) {
+ redirty_page:
redirty_page_for_writepage(wbc, page);
unlock_page(page);
return 0;
}
- } else {
+ commit_write = 1;
+ }
+ page_bufs = page_buffers(page);
+ if (walk_page_buffers(NULL, page_bufs, 0, len, NULL,
+ ext4_bh_delay_or_unwritten)) {
/*
- * The test for page_has_buffers() is subtle:
- * We know the page is dirty but it lost buffers. That means
- * that at some moment in time after write_begin()/write_end()
- * has been called all buffers have been clean and thus they
- * must have been written at least once. So they are all
- * mapped and we can happily proceed with mapping them
- * and writing the page.
- *
- * Try to initialize the buffer_heads and check whether
- * all are mapped and non delay. We don't want to
- * do block allocation here.
+ * We don't want to do block allocation, so redirty
+ * the page and return. We may reach here when we do
+ * a journal commit via journal_submit_inode_data_buffers.
+ * We can also reach here via shrink_page_list
*/
- ret = block_prepare_write(page, 0, len,
- noalloc_get_block_write);
- if (!ret) {
- page_bufs = page_buffers(page);
- /* check whether all are mapped and non delay */
- if (walk_page_buffers(NULL, page_bufs, 0, len, NULL,
- ext4_bh_delay_or_unwritten)) {
- redirty_page_for_writepage(wbc, page);
- unlock_page(page);
- return 0;
- }
- } else {
- /*
- * We can't do block allocation here
- * so just redity the page and unlock
- * and return
- */
- redirty_page_for_writepage(wbc, page);
- unlock_page(page);
- return 0;
- }
+ goto redirty_page;
+ }
+ if (commit_write)
/* now mark the buffer_heads as dirty and uptodate */
block_commit_write(page, 0, len);
- }
- if (PageChecked(page) && ext4_should_journal_data(inode)) {
+ if (PageChecked(page) && ext4_should_journal_data(inode))
/*
* It's mmapped pagecache. Add buffers and journal it. There
* doesn't seem much point in redirtying the page here.
*/
- ClearPageChecked(page);
return __ext4_journalled_writepage(page, len);
- }
- if (page_bufs && buffer_uninit(page_bufs)) {
+ if (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);
@@ -2824,25 +2820,32 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode)
*/
static int write_cache_pages_da(struct address_space *mapping,
struct writeback_control *wbc,
- struct mpage_da_data *mpd)
+ struct mpage_da_data *mpd,
+ pgoff_t *done_index)
{
int ret = 0;
int done = 0;
struct pagevec pvec;
- int nr_pages;
+ unsigned nr_pages;
pgoff_t index;
pgoff_t end; /* Inclusive */
long nr_to_write = wbc->nr_to_write;
+ int tag;
pagevec_init(&pvec, 0);
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ tag = PAGECACHE_TAG_TOWRITE;
+ else
+ tag = PAGECACHE_TAG_DIRTY;
+
+ *done_index = index;
while (!done && (index <= end)) {
int i;
- nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
- PAGECACHE_TAG_DIRTY,
+ nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
break;
@@ -2862,6 +2865,8 @@ static int write_cache_pages_da(struct address_space *mapping,
break;
}
+ *done_index = page->index + 1;
+
lock_page(page);
/*
@@ -2947,6 +2952,8 @@ static int ext4_da_writepages(struct address_space *mapping,
long desired_nr_to_write, nr_to_writebump = 0;
loff_t range_start = wbc->range_start;
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
+ pgoff_t done_index = 0;
+ pgoff_t end;
trace_ext4_da_writepages(inode, wbc);
@@ -2982,8 +2989,11 @@ static int ext4_da_writepages(struct address_space *mapping,
wbc->range_start = index << PAGE_CACHE_SHIFT;
wbc->range_end = LLONG_MAX;
wbc->range_cyclic = 0;
- } else
+ end = -1;
+ } else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
+ end = wbc->range_end >> PAGE_CACHE_SHIFT;
+ }
/*
* This works around two forms of stupidity. The first is in
@@ -3002,9 +3012,12 @@ static int ext4_da_writepages(struct address_space *mapping,
* sbi->max_writeback_mb_bump whichever is smaller.
*/
max_pages = sbi->s_max_writeback_mb_bump << (20 - PAGE_CACHE_SHIFT);
- if (!range_cyclic && range_whole)
- desired_nr_to_write = wbc->nr_to_write * 8;
- else
+ if (!range_cyclic && range_whole) {
+ if (wbc->nr_to_write == LONG_MAX)
+ desired_nr_to_write = wbc->nr_to_write;
+ else
+ desired_nr_to_write = wbc->nr_to_write * 8;
+ } else
desired_nr_to_write = ext4_num_dirty_pages(inode, index,
max_pages);
if (desired_nr_to_write > max_pages)
@@ -3021,6 +3034,9 @@ static int ext4_da_writepages(struct address_space *mapping,
pages_skipped = wbc->pages_skipped;
retry:
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ tag_pages_for_writeback(mapping, index, end);
+
while (!ret && wbc->nr_to_write > 0) {
/*
@@ -3059,16 +3075,14 @@ retry:
mpd.io_done = 0;
mpd.pages_written = 0;
mpd.retval = 0;
- ret = write_cache_pages_da(mapping, wbc, &mpd);
+ ret = write_cache_pages_da(mapping, wbc, &mpd, &done_index);
/*
* 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.
*/
if (!mpd.io_done && mpd.next_page != mpd.first_page) {
- if (mpage_da_map_blocks(&mpd) == 0)
- mpage_da_submit_io(&mpd);
- mpd.io_done = 1;
+ mpage_da_map_and_submit(&mpd);
ret = MPAGE_DA_EXTENT_TAIL;
}
trace_ext4_da_write_pages(inode, &mpd);
@@ -3115,14 +3129,13 @@ retry:
__func__, wbc->nr_to_write, ret);
/* Update index */
- index += pages_written;
wbc->range_cyclic = range_cyclic;
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
/*
* set the writeback_index so that range_cyclic
* mode will write it back later
*/
- mapping->writeback_index = index;
+ mapping->writeback_index = done_index;
out_writepages:
wbc->nr_to_write -= nr_to_writebump;
@@ -3367,7 +3380,7 @@ int ext4_alloc_da_blocks(struct inode *inode)
* doing I/O at all.
*
* We could call write_cache_pages(), and then redirty all of
- * the pages by calling redirty_page_for_writeback() but that
+ * the pages by calling redirty_page_for_writepage() but that
* would be ugly in the extreme. So instead we would need to
* replicate parts of the code in the above functions,
* simplifying them becuase we wouldn't actually intend to
@@ -3457,15 +3470,6 @@ 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;
@@ -3642,173 +3646,6 @@ static int ext4_get_block_write(struct inode *inode, sector_t iblock,
EXT4_GET_BLOCKS_IO_CREATE_EXT);
}
-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_completed_io_list)){
- ext4_debug("inode %lu completed_io list is empty\n", inode->i_ino);
- return;
- }
-
- 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);
- after = cur->next;
- io1 = container_of(after, ext4_io_end_t, list);
-
- 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_io_nolock(ext4_io_end_t *io)
-{
- struct inode *inode = io->inode;
- loff_t offset = io->offset;
- ssize_t size = io->size;
- int ret = 0;
-
- 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 != EXT4_IO_UNWRITTEN)
- return ret;
-
- 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"
- " io is still on inode %lu aio dio list\n",
- __func__, ret, inode->i_ino);
- return ret;
- }
-
- if (io->iocb)
- aio_complete(io->iocb, io->result, 0);
- /* clear the DIO AIO unwritten flag */
- io->flag = 0;
- return ret;
-}
-
-/*
- * work on completed aio dio IO, to convert unwritten extents to extents
- */
-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;
- struct ext4_inode_info *ei = EXT4_I(inode);
- unsigned long flags;
- int ret;
-
- mutex_lock(&inode->i_mutex);
- 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 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 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_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(&ei->i_completed_io_list))
- return ret;
-
- 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_io_nolock() to convert completed
- * IO to written.
- *
- * When ext4_sync_file() is called, run_queue() may already
- * about to flush the work corresponding to this io structure.
- * It will be upset if it founds the io structure related
- * to the work-to-be schedule is freed.
- *
- * Thus we need to keep the io structure still valid here after
- * convertion finished. The io structure has a flag to
- * avoid double converting from both fsync and background work
- * queue work.
- */
- 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, gfp_t flags)
-{
- ext4_io_end_t *io = NULL;
-
- io = kmalloc(sizeof(*io), flags);
-
- if (io) {
- igrab(inode);
- io->inode = inode;
- io->flag = 0;
- io->offset = 0;
- io->size = 0;
- io->page = NULL;
- io->iocb = NULL;
- io->result = 0;
- INIT_WORK(&io->work, ext4_end_io_work);
- INIT_LIST_HEAD(&io->list);
- }
-
- return io;
-}
-
static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
ssize_t size, void *private, int ret,
bool is_async)
@@ -3828,7 +3665,7 @@ 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 != EXT4_IO_UNWRITTEN){
+ if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
ext4_free_io_end(io_end);
iocb->private = NULL;
out:
@@ -3845,14 +3682,14 @@ out:
}
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*/
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);
+
+ /* queue the work to convert unwritten extents to written */
+ queue_work(wq, &io_end->work);
iocb->private = NULL;
}
@@ -3873,7 +3710,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
goto out;
}
- io_end->flag = EXT4_IO_UNWRITTEN;
+ io_end->flag = EXT4_IO_END_UNWRITTEN;
inode = io_end->inode;
/* Add the io_end to per-inode completed io list*/
@@ -3901,8 +3738,7 @@ static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode)
retry:
io_end = ext4_init_io_end(inode, GFP_ATOMIC);
if (!io_end) {
- if (printk_ratelimit())
- printk(KERN_WARNING "%s: allocation fail\n", __func__);
+ pr_warn_ratelimited("%s: allocation fail\n", __func__);
schedule();
goto retry;
}
@@ -3926,9 +3762,9 @@ retry:
* preallocated extents, and those write extend the file, no need to
* fall back to buffered IO.
*
- * For holes, we fallocate those blocks, mark them as unintialized
+ * For holes, we fallocate those blocks, mark them as uninitialized
* If those blocks were preallocated, we mark sure they are splited, but
- * still keep the range to write as unintialized.
+ * still keep the range to write as uninitialized.
*
* The unwrritten extents will be converted to written when DIO is completed.
* For async direct IO, since the IO may still pending when return, we
@@ -4226,7 +4062,7 @@ int ext4_block_truncate_page(handle_t *handle,
if (ext4_should_journal_data(inode)) {
err = ext4_handle_dirty_metadata(handle, inode, bh);
} else {
- if (ext4_should_order_data(inode))
+ if (ext4_should_order_data(inode) && EXT4_I(inode)->jinode)
err = ext4_jbd2_file_inode(handle, inode);
mark_buffer_dirty(bh);
}
@@ -4350,6 +4186,7 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode,
{
__le32 *p;
int flags = EXT4_FREE_BLOCKS_FORGET | EXT4_FREE_BLOCKS_VALIDATED;
+ int err;
if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
flags |= EXT4_FREE_BLOCKS_METADATA;
@@ -4365,11 +4202,23 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode,
if (try_to_extend_transaction(handle, inode)) {
if (bh) {
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
- ext4_handle_dirty_metadata(handle, inode, bh);
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
+ if (unlikely(err)) {
+ ext4_std_error(inode->i_sb, err);
+ return 1;
+ }
+ }
+ err = ext4_mark_inode_dirty(handle, inode);
+ if (unlikely(err)) {
+ ext4_std_error(inode->i_sb, err);
+ return 1;
+ }
+ err = ext4_truncate_restart_trans(handle, inode,
+ blocks_for_truncate(inode));
+ if (unlikely(err)) {
+ ext4_std_error(inode->i_sb, err);
+ return 1;
}
- ext4_mark_inode_dirty(handle, inode);
- ext4_truncate_restart_trans(handle, inode,
- blocks_for_truncate(inode));
if (bh) {
BUFFER_TRACE(bh, "retaking write access");
ext4_journal_get_write_access(handle, bh);
@@ -4530,6 +4379,7 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
(__le32 *) bh->b_data,
(__le32 *) bh->b_data + addr_per_block,
depth);
+ brelse(bh);
/*
* Everything below this this pointer has been
@@ -5040,7 +4890,7 @@ 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_flags = 0;
+ ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */
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.
@@ -5299,7 +5149,7 @@ static int ext4_do_update_inode(handle_t *handle,
if (ext4_inode_blocks_set(handle, raw_inode, ei))
goto out_brelse;
raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
- raw_inode->i_flags = cpu_to_le32(ei->i_flags);
+ raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF);
if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
cpu_to_le32(EXT4_OS_HURD))
raw_inode->i_file_acl_high =
@@ -5464,6 +5314,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = dentry->d_inode;
int error, rc = 0;
+ int orphan = 0;
const unsigned int ia_valid = attr->ia_valid;
error = inode_change_ok(inode, attr);
@@ -5519,8 +5370,10 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
error = PTR_ERR(handle);
goto err_out;
}
-
- error = ext4_orphan_add(handle, inode);
+ if (ext4_handle_valid(handle)) {
+ error = ext4_orphan_add(handle, inode);
+ orphan = 1;
+ }
EXT4_I(inode)->i_disksize = attr->ia_size;
rc = ext4_mark_inode_dirty(handle, inode);
if (!error)
@@ -5538,6 +5391,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
goto err_out;
}
ext4_orphan_del(handle, inode);
+ orphan = 0;
ext4_journal_stop(handle);
goto err_out;
}
@@ -5560,7 +5414,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
* If the call to ext4_truncate failed to get a transaction handle at
* all, we need to clean up the in-core orphan list manually.
*/
- if (inode->i_nlink)
+ if (orphan && inode->i_nlink)
ext4_orphan_del(NULL, inode);
if (!rc && (ia_valid & ATTR_MODE))
@@ -5592,9 +5446,7 @@ int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
* will return the blocks that include the delayed allocation
* blocks for this file.
*/
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
delalloc_blocks = EXT4_I(inode)->i_reserved_data_blocks;
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
stat->blocks += (delalloc_blocks << inode->i_sb->s_blocksize_bits)>>9;
return 0;
@@ -5643,7 +5495,7 @@ static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
*
* Also account for superblock, inode, quota and xattr blocks
*/
-int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk)
+static int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk)
{
ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb);
int gdpblocks;
@@ -5831,6 +5683,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
int err, ret;
might_sleep();
+ trace_ext4_mark_inode_dirty(inode, _RET_IP_);
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (ext4_handle_valid(handle) &&
EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index bf5ae883b1b..eb3bc2fe647 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -331,6 +331,30 @@ mext_out:
return err;
}
+ case FITRIM:
+ {
+ struct super_block *sb = inode->i_sb;
+ struct fstrim_range range;
+ int ret = 0;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (copy_from_user(&range, (struct fstrim_range *)arg,
+ sizeof(range)))
+ return -EFAULT;
+
+ ret = ext4_trim_fs(sb, &range);
+ if (ret < 0)
+ return ret;
+
+ if (copy_to_user((struct fstrim_range *)arg, &range,
+ sizeof(range)))
+ return -EFAULT;
+
+ return 0;
+ }
+
default:
return -ENOTTY;
}
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 4b4ad4b7ce5..851f49b2f9d 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -338,6 +338,14 @@
static struct kmem_cache *ext4_pspace_cachep;
static struct kmem_cache *ext4_ac_cachep;
static struct kmem_cache *ext4_free_ext_cachep;
+
+/* We create slab caches for groupinfo data structures based on the
+ * superblock block size. There will be one per mounted filesystem for
+ * each unique s_blocksize_bits */
+#define NR_GRPINFO_CACHES \
+ (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE + 1)
+static struct kmem_cache *ext4_groupinfo_caches[NR_GRPINFO_CACHES];
+
static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
ext4_group_t group);
static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
@@ -939,6 +947,85 @@ out:
}
/*
+ * lock the group_info alloc_sem of all the groups
+ * belonging to the same buddy cache page. This
+ * make sure other parallel operation on the buddy
+ * cache doesn't happen whild holding the buddy cache
+ * lock
+ */
+static int ext4_mb_get_buddy_cache_lock(struct super_block *sb,
+ ext4_group_t group)
+{
+ int i;
+ int block, pnum;
+ int blocks_per_page;
+ int groups_per_page;
+ ext4_group_t ngroups = ext4_get_groups_count(sb);
+ ext4_group_t first_group;
+ struct ext4_group_info *grp;
+
+ blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
+ /*
+ * the buddy cache inode stores the block bitmap
+ * and buddy information in consecutive blocks.
+ * So for each group we need two blocks.
+ */
+ block = group * 2;
+ pnum = block / blocks_per_page;
+ first_group = pnum * blocks_per_page / 2;
+
+ groups_per_page = blocks_per_page >> 1;
+ if (groups_per_page == 0)
+ groups_per_page = 1;
+ /* read all groups the page covers into the cache */
+ for (i = 0; i < groups_per_page; i++) {
+
+ if ((first_group + i) >= ngroups)
+ break;
+ grp = ext4_get_group_info(sb, first_group + i);
+ /* take all groups write allocation
+ * semaphore. This make sure there is
+ * no block allocation going on in any
+ * of that groups
+ */
+ down_write_nested(&grp->alloc_sem, i);
+ }
+ return i;
+}
+
+static void ext4_mb_put_buddy_cache_lock(struct super_block *sb,
+ ext4_group_t group, int locked_group)
+{
+ int i;
+ int block, pnum;
+ int blocks_per_page;
+ ext4_group_t first_group;
+ struct ext4_group_info *grp;
+
+ blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
+ /*
+ * the buddy cache inode stores the block bitmap
+ * and buddy information in consecutive blocks.
+ * So for each group we need two blocks.
+ */
+ block = group * 2;
+ pnum = block / blocks_per_page;
+ first_group = pnum * blocks_per_page / 2;
+ /* release locks on all the groups */
+ for (i = 0; i < locked_group; i++) {
+
+ grp = ext4_get_group_info(sb, first_group + i);
+ /* take all groups write allocation
+ * semaphore. This make sure there is
+ * no block allocation going on in any
+ * of that groups
+ */
+ up_write(&grp->alloc_sem);
+ }
+
+}
+
+/*
* Locking note: This routine calls ext4_mb_init_cache(), which takes the
* block group lock of all groups for this page; do not hold the BG lock when
* calling this routine!
@@ -1915,84 +2002,6 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac,
return 0;
}
-/*
- * lock the group_info alloc_sem of all the groups
- * belonging to the same buddy cache page. This
- * make sure other parallel operation on the buddy
- * cache doesn't happen whild holding the buddy cache
- * lock
- */
-int ext4_mb_get_buddy_cache_lock(struct super_block *sb, ext4_group_t group)
-{
- int i;
- int block, pnum;
- int blocks_per_page;
- int groups_per_page;
- ext4_group_t ngroups = ext4_get_groups_count(sb);
- ext4_group_t first_group;
- struct ext4_group_info *grp;
-
- blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
- /*
- * the buddy cache inode stores the block bitmap
- * and buddy information in consecutive blocks.
- * So for each group we need two blocks.
- */
- block = group * 2;
- pnum = block / blocks_per_page;
- first_group = pnum * blocks_per_page / 2;
-
- groups_per_page = blocks_per_page >> 1;
- if (groups_per_page == 0)
- groups_per_page = 1;
- /* read all groups the page covers into the cache */
- for (i = 0; i < groups_per_page; i++) {
-
- if ((first_group + i) >= ngroups)
- break;
- grp = ext4_get_group_info(sb, first_group + i);
- /* take all groups write allocation
- * semaphore. This make sure there is
- * no block allocation going on in any
- * of that groups
- */
- down_write_nested(&grp->alloc_sem, i);
- }
- return i;
-}
-
-void ext4_mb_put_buddy_cache_lock(struct super_block *sb,
- ext4_group_t group, int locked_group)
-{
- int i;
- int block, pnum;
- int blocks_per_page;
- ext4_group_t first_group;
- struct ext4_group_info *grp;
-
- blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
- /*
- * the buddy cache inode stores the block bitmap
- * and buddy information in consecutive blocks.
- * So for each group we need two blocks.
- */
- block = group * 2;
- pnum = block / blocks_per_page;
- first_group = pnum * blocks_per_page / 2;
- /* release locks on all the groups */
- for (i = 0; i < locked_group; i++) {
-
- grp = ext4_get_group_info(sb, first_group + i);
- /* take all groups write allocation
- * semaphore. This make sure there is
- * no block allocation going on in any
- * of that groups
- */
- up_write(&grp->alloc_sem);
- }
-
-}
-
static noinline_for_stack int
ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
{
@@ -2233,15 +2242,24 @@ static const struct file_operations ext4_mb_seq_groups_fops = {
.release = seq_release,
};
+static struct kmem_cache *get_groupinfo_cache(int blocksize_bits)
+{
+ int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE;
+ struct kmem_cache *cachep = ext4_groupinfo_caches[cache_index];
+
+ BUG_ON(!cachep);
+ return cachep;
+}
/* Create and initialize ext4_group_info data for the given group. */
int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
struct ext4_group_desc *desc)
{
- int i, len;
+ int i;
int metalen = 0;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_group_info **meta_group_info;
+ struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits);
/*
* First check if this group is the first of a reserved block.
@@ -2261,22 +2279,16 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
meta_group_info;
}
- /*
- * calculate needed size. if change bb_counters size,
- * don't forget about ext4_mb_generate_buddy()
- */
- len = offsetof(typeof(**meta_group_info),
- bb_counters[sb->s_blocksize_bits + 2]);
-
meta_group_info =
sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)];
i = group & (EXT4_DESC_PER_BLOCK(sb) - 1);
- meta_group_info[i] = kzalloc(len, GFP_KERNEL);
+ meta_group_info[i] = kmem_cache_alloc(cachep, GFP_KERNEL);
if (meta_group_info[i] == NULL) {
printk(KERN_ERR "EXT4-fs: can't allocate buddy mem\n");
goto exit_group_info;
}
+ memset(meta_group_info[i], 0, kmem_cache_size(cachep));
set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT,
&(meta_group_info[i]->bb_state));
@@ -2331,6 +2343,7 @@ static int ext4_mb_init_backend(struct super_block *sb)
int num_meta_group_infos_max;
int array_size;
struct ext4_group_desc *desc;
+ struct kmem_cache *cachep;
/* This is the number of blocks used by GDT */
num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) -
@@ -2373,6 +2386,7 @@ static int ext4_mb_init_backend(struct super_block *sb)
printk(KERN_ERR "EXT4-fs: can't get new inode\n");
goto err_freesgi;
}
+ sbi->s_buddy_cache->i_ino = get_next_ino();
EXT4_I(sbi->s_buddy_cache)->i_disksize = 0;
for (i = 0; i < ngroups; i++) {
desc = ext4_get_group_desc(sb, i, NULL);
@@ -2388,8 +2402,9 @@ static int ext4_mb_init_backend(struct super_block *sb)
return 0;
err_freebuddy:
+ cachep = get_groupinfo_cache(sb->s_blocksize_bits);
while (i-- > 0)
- kfree(ext4_get_group_info(sb, i));
+ kmem_cache_free(cachep, ext4_get_group_info(sb, i));
i = num_meta_group_infos;
while (i-- > 0)
kfree(sbi->s_group_info[i]);
@@ -2406,19 +2421,48 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
unsigned offset;
unsigned max;
int ret;
+ int cache_index;
+ struct kmem_cache *cachep;
+ char *namep = NULL;
i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_offsets);
sbi->s_mb_offsets = kmalloc(i, GFP_KERNEL);
if (sbi->s_mb_offsets == NULL) {
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out;
}
i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_maxs);
sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL);
if (sbi->s_mb_maxs == NULL) {
- kfree(sbi->s_mb_offsets);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ cache_index = sb->s_blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE;
+ cachep = ext4_groupinfo_caches[cache_index];
+ if (!cachep) {
+ char name[32];
+ int len = offsetof(struct ext4_group_info,
+ bb_counters[sb->s_blocksize_bits + 2]);
+
+ sprintf(name, "ext4_groupinfo_%d", sb->s_blocksize_bits);
+ namep = kstrdup(name, GFP_KERNEL);
+ if (!namep) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ /* Need to free the kmem_cache_name() when we
+ * destroy the slab */
+ cachep = kmem_cache_create(namep, len, 0,
+ SLAB_RECLAIM_ACCOUNT, NULL);
+ if (!cachep) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ ext4_groupinfo_caches[cache_index] = cachep;
}
/* order 0 is regular bitmap */
@@ -2439,9 +2483,7 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
/* init file for buddy data */
ret = ext4_mb_init_backend(sb);
if (ret != 0) {
- kfree(sbi->s_mb_offsets);
- kfree(sbi->s_mb_maxs);
- return ret;
+ goto out;
}
spin_lock_init(&sbi->s_md_lock);
@@ -2456,9 +2498,8 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
if (sbi->s_locality_groups == NULL) {
- kfree(sbi->s_mb_offsets);
- kfree(sbi->s_mb_maxs);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out;
}
for_each_possible_cpu(i) {
struct ext4_locality_group *lg;
@@ -2475,7 +2516,13 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
if (sbi->s_journal)
sbi->s_journal->j_commit_callback = release_blocks_on_commit;
- return 0;
+out:
+ if (ret) {
+ kfree(sbi->s_mb_offsets);
+ kfree(sbi->s_mb_maxs);
+ kfree(namep);
+ }
+ return ret;
}
/* need to called with the ext4 group lock held */
@@ -2503,6 +2550,7 @@ int ext4_mb_release(struct super_block *sb)
int num_meta_group_infos;
struct ext4_group_info *grinfo;
struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits);
if (sbi->s_group_info) {
for (i = 0; i < ngroups; i++) {
@@ -2513,7 +2561,7 @@ int ext4_mb_release(struct super_block *sb)
ext4_lock_group(sb, i);
ext4_mb_cleanup_pa(grinfo);
ext4_unlock_group(sb, i);
- kfree(grinfo);
+ kmem_cache_free(cachep, grinfo);
}
num_meta_group_infos = (ngroups +
EXT4_DESC_PER_BLOCK(sb) - 1) >>
@@ -2557,20 +2605,15 @@ int ext4_mb_release(struct super_block *sb)
return 0;
}
-static inline void ext4_issue_discard(struct super_block *sb,
+static inline int ext4_issue_discard(struct super_block *sb,
ext4_group_t block_group, ext4_grpblk_t block, int count)
{
- int ret;
ext4_fsblk_t discard_block;
discard_block = block + ext4_group_first_block_no(sb, block_group);
trace_ext4_discard_blocks(sb,
(unsigned long long) discard_block, count);
- ret = sb_issue_discard(sb, discard_block, count);
- if (ret == EOPNOTSUPP) {
- ext4_warning(sb, "discard not supported, disabling");
- clear_opt(EXT4_SB(sb)->s_mount_opt, DISCARD);
- }
+ return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0);
}
/*
@@ -2582,7 +2625,7 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
struct super_block *sb = journal->j_private;
struct ext4_buddy e4b;
struct ext4_group_info *db;
- int err, count = 0, count2 = 0;
+ int err, ret, count = 0, count2 = 0;
struct ext4_free_data *entry;
struct list_head *l, *ltmp;
@@ -2592,9 +2635,15 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
mb_debug(1, "gonna free %u blocks in group %u (0x%p):",
entry->count, entry->group, entry);
- if (test_opt(sb, DISCARD))
- ext4_issue_discard(sb, entry->group,
+ if (test_opt(sb, DISCARD)) {
+ ret = ext4_issue_discard(sb, entry->group,
entry->start_blk, entry->count);
+ if (unlikely(ret == -EOPNOTSUPP)) {
+ ext4_warning(sb, "discard not supported, "
+ "disabling");
+ clear_opt(sb, DISCARD);
+ }
+ }
err = ext4_mb_load_buddy(sb, entry->group, &e4b);
/* we expect to find existing buddy because it's pinned */
@@ -2658,28 +2707,22 @@ static void ext4_remove_debugfs_entry(void)
#endif
-int __init init_ext4_mballoc(void)
+int __init ext4_init_mballoc(void)
{
- ext4_pspace_cachep =
- kmem_cache_create("ext4_prealloc_space",
- sizeof(struct ext4_prealloc_space),
- 0, SLAB_RECLAIM_ACCOUNT, NULL);
+ ext4_pspace_cachep = KMEM_CACHE(ext4_prealloc_space,
+ SLAB_RECLAIM_ACCOUNT);
if (ext4_pspace_cachep == NULL)
return -ENOMEM;
- ext4_ac_cachep =
- kmem_cache_create("ext4_alloc_context",
- sizeof(struct ext4_allocation_context),
- 0, SLAB_RECLAIM_ACCOUNT, NULL);
+ ext4_ac_cachep = KMEM_CACHE(ext4_allocation_context,
+ SLAB_RECLAIM_ACCOUNT);
if (ext4_ac_cachep == NULL) {
kmem_cache_destroy(ext4_pspace_cachep);
return -ENOMEM;
}
- ext4_free_ext_cachep =
- kmem_cache_create("ext4_free_block_extents",
- sizeof(struct ext4_free_data),
- 0, SLAB_RECLAIM_ACCOUNT, NULL);
+ ext4_free_ext_cachep = KMEM_CACHE(ext4_free_data,
+ SLAB_RECLAIM_ACCOUNT);
if (ext4_free_ext_cachep == NULL) {
kmem_cache_destroy(ext4_pspace_cachep);
kmem_cache_destroy(ext4_ac_cachep);
@@ -2689,8 +2732,9 @@ int __init init_ext4_mballoc(void)
return 0;
}
-void exit_ext4_mballoc(void)
+void ext4_exit_mballoc(void)
{
+ int i;
/*
* Wait for completion of call_rcu()'s on ext4_pspace_cachep
* before destroying the slab cache.
@@ -2699,6 +2743,15 @@ void exit_ext4_mballoc(void)
kmem_cache_destroy(ext4_pspace_cachep);
kmem_cache_destroy(ext4_ac_cachep);
kmem_cache_destroy(ext4_free_ext_cachep);
+
+ for (i = 0; i < NR_GRPINFO_CACHES; i++) {
+ struct kmem_cache *cachep = ext4_groupinfo_caches[i];
+ if (cachep) {
+ char *name = (char *)kmem_cache_name(cachep);
+ kmem_cache_destroy(cachep);
+ kfree(name);
+ }
+ }
ext4_remove_debugfs_entry();
}
@@ -3535,8 +3588,7 @@ static int ext4_mb_new_preallocation(struct ext4_allocation_context *ac)
*/
static noinline_for_stack int
ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
- struct ext4_prealloc_space *pa,
- struct ext4_allocation_context *ac)
+ struct ext4_prealloc_space *pa)
{
struct super_block *sb = e4b->bd_sb;
struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -3554,11 +3606,6 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
end = bit + pa->pa_len;
- if (ac) {
- ac->ac_sb = sb;
- ac->ac_inode = pa->pa_inode;
- }
-
while (bit < end) {
bit = mb_find_next_zero_bit(bitmap_bh->b_data, end, bit);
if (bit >= end)
@@ -3569,16 +3616,9 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
(unsigned) next - bit, (unsigned) group);
free += next - bit;
- if (ac) {
- ac->ac_b_ex.fe_group = group;
- ac->ac_b_ex.fe_start = bit;
- ac->ac_b_ex.fe_len = next - bit;
- ac->ac_b_ex.fe_logical = 0;
- trace_ext4_mballoc_discard(ac);
- }
-
- trace_ext4_mb_release_inode_pa(sb, ac, pa, grp_blk_start + bit,
- next - bit);
+ trace_ext4_mballoc_discard(sb, NULL, group, bit, next - bit);
+ trace_ext4_mb_release_inode_pa(sb, pa->pa_inode, pa,
+ grp_blk_start + bit, next - bit);
mb_free_blocks(pa->pa_inode, e4b, bit, next - bit);
bit = next + 1;
}
@@ -3601,29 +3641,19 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
static noinline_for_stack int
ext4_mb_release_group_pa(struct ext4_buddy *e4b,
- struct ext4_prealloc_space *pa,
- struct ext4_allocation_context *ac)
+ struct ext4_prealloc_space *pa)
{
struct super_block *sb = e4b->bd_sb;
ext4_group_t group;
ext4_grpblk_t bit;
- trace_ext4_mb_release_group_pa(sb, ac, pa);
+ trace_ext4_mb_release_group_pa(sb, pa);
BUG_ON(pa->pa_deleted == 0);
ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len);
atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded);
-
- if (ac) {
- ac->ac_sb = sb;
- ac->ac_inode = NULL;
- ac->ac_b_ex.fe_group = group;
- ac->ac_b_ex.fe_start = bit;
- ac->ac_b_ex.fe_len = pa->pa_len;
- ac->ac_b_ex.fe_logical = 0;
- trace_ext4_mballoc_discard(ac);
- }
+ trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len);
return 0;
}
@@ -3644,7 +3674,6 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
struct ext4_group_info *grp = ext4_get_group_info(sb, group);
struct buffer_head *bitmap_bh = NULL;
struct ext4_prealloc_space *pa, *tmp;
- struct ext4_allocation_context *ac;
struct list_head list;
struct ext4_buddy e4b;
int err;
@@ -3673,9 +3702,6 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
needed = EXT4_BLOCKS_PER_GROUP(sb) + 1;
INIT_LIST_HEAD(&list);
- ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
- if (ac)
- ac->ac_sb = sb;
repeat:
ext4_lock_group(sb, group);
list_for_each_entry_safe(pa, tmp,
@@ -3730,9 +3756,9 @@ repeat:
spin_unlock(pa->pa_obj_lock);
if (pa->pa_type == MB_GROUP_PA)
- ext4_mb_release_group_pa(&e4b, pa, ac);
+ ext4_mb_release_group_pa(&e4b, pa);
else
- ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa, ac);
+ ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa);
list_del(&pa->u.pa_tmp_list);
call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback);
@@ -3740,8 +3766,6 @@ repeat:
out:
ext4_unlock_group(sb, group);
- if (ac)
- kmem_cache_free(ext4_ac_cachep, ac);
ext4_mb_unload_buddy(&e4b);
put_bh(bitmap_bh);
return free;
@@ -3762,7 +3786,6 @@ void ext4_discard_preallocations(struct inode *inode)
struct super_block *sb = inode->i_sb;
struct buffer_head *bitmap_bh = NULL;
struct ext4_prealloc_space *pa, *tmp;
- struct ext4_allocation_context *ac;
ext4_group_t group = 0;
struct list_head list;
struct ext4_buddy e4b;
@@ -3778,11 +3801,6 @@ void ext4_discard_preallocations(struct inode *inode)
INIT_LIST_HEAD(&list);
- ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
- if (ac) {
- ac->ac_sb = sb;
- ac->ac_inode = inode;
- }
repeat:
/* first, collect all pa's in the inode */
spin_lock(&ei->i_prealloc_lock);
@@ -3852,7 +3870,7 @@ repeat:
ext4_lock_group(sb, group);
list_del(&pa->pa_group_list);
- ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa, ac);
+ ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa);
ext4_unlock_group(sb, group);
ext4_mb_unload_buddy(&e4b);
@@ -3861,23 +3879,8 @@ repeat:
list_del(&pa->u.pa_tmp_list);
call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback);
}
- if (ac)
- kmem_cache_free(ext4_ac_cachep, ac);
}
-/*
- * finds all preallocated spaces and return blocks being freed to them
- * if preallocated space becomes full (no block is used from the space)
- * then the function frees space in buddy
- * XXX: at the moment, truncate (which is the only way to free blocks)
- * discards all preallocations
- */
-static void ext4_mb_return_to_preallocation(struct inode *inode,
- struct ext4_buddy *e4b,
- sector_t block, int count)
-{
- BUG_ON(!list_empty(&EXT4_I(inode)->i_prealloc_list));
-}
#ifdef CONFIG_EXT4_DEBUG
static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
{
@@ -4060,14 +4063,10 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb,
struct ext4_buddy e4b;
struct list_head discard_list;
struct ext4_prealloc_space *pa, *tmp;
- struct ext4_allocation_context *ac;
mb_debug(1, "discard locality group preallocation\n");
INIT_LIST_HEAD(&discard_list);
- ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
- if (ac)
- ac->ac_sb = sb;
spin_lock(&lg->lg_prealloc_lock);
list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[order],
@@ -4119,15 +4118,13 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb,
}
ext4_lock_group(sb, group);
list_del(&pa->pa_group_list);
- ext4_mb_release_group_pa(&e4b, pa, ac);
+ ext4_mb_release_group_pa(&e4b, pa);
ext4_unlock_group(sb, group);
ext4_mb_unload_buddy(&e4b);
list_del(&pa->u.pa_tmp_list);
call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback);
}
- if (ac)
- kmem_cache_free(ext4_ac_cachep, ac);
}
/*
@@ -4273,7 +4270,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
* EDQUOT check, as blocks and quotas have been already
* reserved when data being copied into pagecache.
*/
- if (EXT4_I(ar->inode)->i_delalloc_reserved_flag)
+ if (ext4_test_inode_state(ar->inode, EXT4_STATE_DELALLOC_RESERVED))
ar->flags |= EXT4_MB_DELALLOC_RESERVED;
else {
/* Without delayed allocation we need to verify
@@ -4370,7 +4367,8 @@ out:
if (inquota && ar->len < inquota)
dquot_free_block(ar->inode, inquota - ar->len);
if (!ar->len) {
- if (!EXT4_I(ar->inode)->i_delalloc_reserved_flag)
+ if (!ext4_test_inode_state(ar->inode,
+ EXT4_STATE_DELALLOC_RESERVED))
/* release all the reserved blocks if non delalloc */
percpu_counter_sub(&sbi->s_dirtyblocks_counter,
reserv_blks);
@@ -4491,7 +4489,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
{
struct buffer_head *bitmap_bh = NULL;
struct super_block *sb = inode->i_sb;
- struct ext4_allocation_context *ac = NULL;
struct ext4_group_desc *gdp;
unsigned long freed = 0;
unsigned int overflow;
@@ -4531,6 +4528,8 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
if (!bh)
tbh = sb_find_get_block(inode->i_sb,
block + i);
+ if (unlikely(!tbh))
+ continue;
ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA,
inode, tbh, block + i);
}
@@ -4546,12 +4545,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
if (!ext4_should_writeback_data(inode))
flags |= EXT4_FREE_BLOCKS_METADATA;
- ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
- if (ac) {
- ac->ac_inode = inode;
- ac->ac_sb = sb;
- }
-
do_more:
overflow = 0;
ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
@@ -4609,12 +4602,7 @@ do_more:
BUG_ON(!mb_test_bit(bit + i, bitmap_bh->b_data));
}
#endif
- if (ac) {
- ac->ac_b_ex.fe_group = block_group;
- ac->ac_b_ex.fe_start = bit;
- ac->ac_b_ex.fe_len = count;
- trace_ext4_mballoc_free(ac);
- }
+ trace_ext4_mballoc_free(sb, inode, block_group, bit, count);
err = ext4_mb_load_buddy(sb, block_group, &e4b);
if (err)
@@ -4626,7 +4614,11 @@ do_more:
* blocks being freed are metadata. these blocks shouldn't
* be used until this transaction is committed
*/
- new_entry = kmem_cache_alloc(ext4_free_ext_cachep, GFP_NOFS);
+ new_entry = kmem_cache_alloc(ext4_free_ext_cachep, GFP_NOFS);
+ if (!new_entry) {
+ err = -ENOMEM;
+ goto error_return;
+ }
new_entry->start_blk = bit;
new_entry->group = block_group;
new_entry->count = count;
@@ -4643,9 +4635,6 @@ do_more:
ext4_lock_group(sb, block_group);
mb_clear_bits(bitmap_bh->b_data, bit, count);
mb_free_blocks(inode, &e4b, bit, count);
- ext4_mb_return_to_preallocation(inode, &e4b, block, count);
- if (test_opt(sb, DISCARD))
- ext4_issue_discard(sb, block_group, bit, count);
}
ret = ext4_free_blks_count(sb, gdp) + count;
@@ -4685,7 +4674,194 @@ error_return:
dquot_free_block(inode, freed);
brelse(bitmap_bh);
ext4_std_error(sb, err);
- if (ac)
- kmem_cache_free(ext4_ac_cachep, ac);
return;
}
+
+/**
+ * ext4_trim_extent -- function to TRIM one single free extent in the group
+ * @sb: super block for the file system
+ * @start: starting block of the free extent in the alloc. group
+ * @count: number of blocks to TRIM
+ * @group: alloc. group we are working with
+ * @e4b: ext4 buddy for the group
+ *
+ * Trim "count" blocks starting at "start" in the "group". To assure that no
+ * one will allocate those blocks, mark it as used in buddy bitmap. This must
+ * be called with under the group lock.
+ */
+static int ext4_trim_extent(struct super_block *sb, int start, int count,
+ ext4_group_t group, struct ext4_buddy *e4b)
+{
+ struct ext4_free_extent ex;
+ int ret = 0;
+
+ assert_spin_locked(ext4_group_lock_ptr(sb, group));
+
+ ex.fe_start = start;
+ ex.fe_group = group;
+ ex.fe_len = count;
+
+ /*
+ * Mark blocks used, so no one can reuse them while
+ * being trimmed.
+ */
+ mb_mark_used(e4b, &ex);
+ ext4_unlock_group(sb, group);
+
+ ret = ext4_issue_discard(sb, group, start, count);
+
+ ext4_lock_group(sb, group);
+ mb_free_blocks(NULL, e4b, start, ex.fe_len);
+ return ret;
+}
+
+/**
+ * ext4_trim_all_free -- function to trim all free space in alloc. group
+ * @sb: super block for file system
+ * @e4b: ext4 buddy
+ * @start: first group block to examine
+ * @max: last group block to examine
+ * @minblocks: minimum extent block count
+ *
+ * ext4_trim_all_free walks through group's buddy bitmap searching for free
+ * extents. When the free block is found, ext4_trim_extent is called to TRIM
+ * the extent.
+ *
+ *
+ * ext4_trim_all_free walks through group's block bitmap searching for free
+ * extents. When the free extent is found, mark it as used in group buddy
+ * bitmap. Then issue a TRIM command on this extent and free the extent in
+ * the group buddy bitmap. This is done until whole group is scanned.
+ */
+ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b,
+ ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks)
+{
+ void *bitmap;
+ ext4_grpblk_t next, count = 0;
+ ext4_group_t group;
+ int ret = 0;
+
+ BUG_ON(e4b == NULL);
+
+ bitmap = e4b->bd_bitmap;
+ group = e4b->bd_group;
+ start = (e4b->bd_info->bb_first_free > start) ?
+ e4b->bd_info->bb_first_free : start;
+ ext4_lock_group(sb, group);
+
+ while (start < max) {
+ start = mb_find_next_zero_bit(bitmap, max, start);
+ if (start >= max)
+ break;
+ next = mb_find_next_bit(bitmap, max, start);
+
+ if ((next - start) >= minblocks) {
+ ret = ext4_trim_extent(sb, start,
+ next - start, group, e4b);
+ if (ret < 0)
+ break;
+ count += next - start;
+ }
+ start = next + 1;
+
+ if (fatal_signal_pending(current)) {
+ count = -ERESTARTSYS;
+ break;
+ }
+
+ if (need_resched()) {
+ ext4_unlock_group(sb, group);
+ cond_resched();
+ ext4_lock_group(sb, group);
+ }
+
+ if ((e4b->bd_info->bb_free - count) < minblocks)
+ break;
+ }
+ ext4_unlock_group(sb, group);
+
+ ext4_debug("trimmed %d blocks in the group %d\n",
+ count, group);
+
+ if (ret < 0)
+ count = ret;
+
+ return count;
+}
+
+/**
+ * ext4_trim_fs() -- trim ioctl handle function
+ * @sb: superblock for filesystem
+ * @range: fstrim_range structure
+ *
+ * start: First Byte to trim
+ * len: number of Bytes to trim from start
+ * minlen: minimum extent length in Bytes
+ * ext4_trim_fs goes through all allocation groups containing Bytes from
+ * start to start+len. For each such a group ext4_trim_all_free function
+ * is invoked to trim all free space.
+ */
+int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
+{
+ struct ext4_buddy e4b;
+ ext4_group_t first_group, last_group;
+ ext4_group_t group, ngroups = ext4_get_groups_count(sb);
+ ext4_grpblk_t cnt = 0, first_block, last_block;
+ uint64_t start, len, minlen, trimmed;
+ ext4_fsblk_t first_data_blk =
+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
+ int ret = 0;
+
+ start = range->start >> sb->s_blocksize_bits;
+ len = range->len >> sb->s_blocksize_bits;
+ minlen = range->minlen >> sb->s_blocksize_bits;
+ trimmed = 0;
+
+ if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
+ return -EINVAL;
+ if (start < first_data_blk) {
+ len -= first_data_blk - start;
+ start = first_data_blk;
+ }
+
+ /* Determine first and last group to examine based on start and len */
+ ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) start,
+ &first_group, &first_block);
+ ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) (start + len),
+ &last_group, &last_block);
+ last_group = (last_group > ngroups - 1) ? ngroups - 1 : last_group;
+ last_block = EXT4_BLOCKS_PER_GROUP(sb);
+
+ if (first_group > last_group)
+ return -EINVAL;
+
+ for (group = first_group; group <= last_group; group++) {
+ ret = ext4_mb_load_buddy(sb, group, &e4b);
+ if (ret) {
+ ext4_error(sb, "Error in loading buddy "
+ "information for %u", group);
+ break;
+ }
+
+ if (len >= EXT4_BLOCKS_PER_GROUP(sb))
+ len -= (EXT4_BLOCKS_PER_GROUP(sb) - first_block);
+ else
+ last_block = first_block + len;
+
+ if (e4b.bd_info->bb_free >= minlen) {
+ cnt = ext4_trim_all_free(sb, &e4b, first_block,
+ last_block, minlen);
+ if (cnt < 0) {
+ ret = cnt;
+ ext4_mb_unload_buddy(&e4b);
+ break;
+ }
+ }
+ ext4_mb_unload_buddy(&e4b);
+ trimmed += cnt;
+ first_block = 0;
+ }
+ range->len = trimmed * sb->s_blocksize;
+
+ return ret;
+}
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index 1765c2c50a9..b0a126f23c2 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -412,7 +412,7 @@ static int free_ext_idx(handle_t *handle, struct inode *inode,
struct buffer_head *bh;
struct ext4_extent_header *eh;
- block = idx_pblock(ix);
+ block = ext4_idx_pblock(ix);
bh = sb_bread(inode->i_sb, block);
if (!bh)
return -EIO;
@@ -496,7 +496,7 @@ int ext4_ext_migrate(struct inode *inode)
goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) *
EXT4_INODES_PER_GROUP(inode->i_sb)) + 1;
tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode,
- S_IFREG, 0, goal);
+ S_IFREG, NULL, goal);
if (IS_ERR(tmp_inode)) {
retval = -ENOMEM;
ext4_journal_stop(handle);
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 5f1ed9fc913..b9f3e7862f1 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -85,7 +85,7 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
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);
+ path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext);
return 0;
}
@@ -96,7 +96,7 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
/* index block */
path[ppos].p_idx++;
- path[ppos].p_block = idx_pblock(path[ppos].p_idx);
+ path[ppos].p_block = ext4_idx_pblock(path[ppos].p_idx);
if (path[ppos+1].p_bh)
brelse(path[ppos+1].p_bh);
path[ppos+1].p_bh =
@@ -111,7 +111,7 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
path[cur_ppos].p_idx =
EXT_FIRST_INDEX(path[cur_ppos].p_hdr);
path[cur_ppos].p_block =
- idx_pblock(path[cur_ppos].p_idx);
+ ext4_idx_pblock(path[cur_ppos].p_idx);
if (path[cur_ppos+1].p_bh)
brelse(path[cur_ppos+1].p_bh);
path[cur_ppos+1].p_bh = sb_bread(inode->i_sb,
@@ -133,7 +133,7 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
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);
+ ext4_ext_pblock(path[leaf_ppos].p_ext);
return 0;
}
}
@@ -249,7 +249,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
*/
o_end->ee_block = end_ext->ee_block;
o_end->ee_len = end_ext->ee_len;
- ext4_ext_store_pblock(o_end, ext_pblock(end_ext));
+ ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext));
}
o_start->ee_len = start_ext->ee_len;
@@ -276,7 +276,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
*/
o_end->ee_block = end_ext->ee_block;
o_end->ee_len = end_ext->ee_len;
- ext4_ext_store_pblock(o_end, ext_pblock(end_ext));
+ ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext));
/*
* Set 0 to the extent block if new_ext was
@@ -361,7 +361,7 @@ mext_insert_inside_block(struct ext4_extent *o_start,
/* Insert new entry */
if (new_ext->ee_len) {
o_start[i] = *new_ext;
- ext4_ext_store_pblock(&o_start[i++], ext_pblock(new_ext));
+ ext4_ext_store_pblock(&o_start[i++], ext4_ext_pblock(new_ext));
}
/* Insert end entry */
@@ -488,7 +488,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
start_ext.ee_len = end_ext.ee_len = 0;
new_ext.ee_block = cpu_to_le32(*from);
- ext4_ext_store_pblock(&new_ext, ext_pblock(dext));
+ ext4_ext_store_pblock(&new_ext, ext4_ext_pblock(dext));
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;
@@ -553,7 +553,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
copy_extent_status(oext, &end_ext);
end_ext_alen = ext4_ext_get_actual_len(&end_ext);
ext4_ext_store_pblock(&end_ext,
- (ext_pblock(o_end) + oext_alen - end_ext_alen));
+ (ext4_ext_pblock(o_end) + oext_alen - end_ext_alen));
end_ext.ee_block =
cpu_to_le32(le32_to_cpu(o_end->ee_block) +
oext_alen - end_ext_alen);
@@ -604,7 +604,7 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext,
/* When tmp_dext is too large, pick up the target range. */
diff = donor_off - le32_to_cpu(tmp_dext->ee_block);
- ext4_ext_store_pblock(tmp_dext, ext_pblock(tmp_dext) + diff);
+ ext4_ext_store_pblock(tmp_dext, ext4_ext_pblock(tmp_dext) + diff);
tmp_dext->ee_block =
cpu_to_le32(le32_to_cpu(tmp_dext->ee_block) + diff);
tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_dext->ee_len) - diff);
@@ -613,7 +613,7 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext,
tmp_dext->ee_len = cpu_to_le16(max_count);
orig_diff = orig_off - le32_to_cpu(tmp_oext->ee_block);
- ext4_ext_store_pblock(tmp_oext, ext_pblock(tmp_oext) + orig_diff);
+ ext4_ext_store_pblock(tmp_oext, ext4_ext_pblock(tmp_oext) + orig_diff);
/* Adjust extent length if donor extent is larger than orig */
if (ext4_ext_get_actual_len(tmp_dext) >
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 314c0d3b3fa..5485390d32c 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -581,9 +581,9 @@ static int htree_dirblock_to_tree(struct file *dir_file,
dir->i_sb->s_blocksize -
EXT4_DIR_REC_LEN(0));
for (; de < top; de = ext4_next_entry(de, dir->i_sb->s_blocksize)) {
- if (!ext4_check_dir_entry(dir, de, bh,
- (block<<EXT4_BLOCK_SIZE_BITS(dir->i_sb))
- +((char *)de - bh->b_data))) {
+ if (ext4_check_dir_entry(dir, NULL, de, bh,
+ (block<<EXT4_BLOCK_SIZE_BITS(dir->i_sb))
+ + ((char *)de - bh->b_data))) {
/* On error, skip the f_pos to the next block. */
dir_file->f_pos = (dir_file->f_pos |
(dir->i_sb->s_blocksize - 1)) + 1;
@@ -820,7 +820,7 @@ static inline int search_dirblock(struct buffer_head *bh,
if ((char *) de + namelen <= dlimit &&
ext4_match (namelen, name, de)) {
/* found a match - just to be sure, do a full check */
- if (!ext4_check_dir_entry(dir, de, bh, offset))
+ if (ext4_check_dir_entry(dir, NULL, de, bh, offset))
return -1;
*res_dir = de;
return 1;
@@ -856,6 +856,7 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
struct buffer_head *bh_use[NAMEI_RA_SIZE];
struct buffer_head *bh, *ret = NULL;
ext4_lblk_t start, block, b;
+ const u8 *name = d_name->name;
int ra_max = 0; /* Number of bh's in the readahead
buffer, bh_use[] */
int ra_ptr = 0; /* Current index into readahead
@@ -870,6 +871,16 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
namelen = d_name->len;
if (namelen > EXT4_NAME_LEN)
return NULL;
+ if ((namelen <= 2) && (name[0] == '.') &&
+ (name[1] == '.' || name[1] == '\0')) {
+ /*
+ * "." or ".." will only be in the first block
+ * NFS may look up ".."; "." should be handled by the VFS
+ */
+ block = start = 0;
+ nblocks = 1;
+ goto restart;
+ }
if (is_dx(dir)) {
bh = ext4_dx_find_entry(dir, d_name, res_dir, &err);
/*
@@ -960,55 +971,35 @@ cleanup_and_exit:
static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct qstr *d_name,
struct ext4_dir_entry_2 **res_dir, int *err)
{
- struct super_block * sb;
+ struct super_block * sb = dir->i_sb;
struct dx_hash_info hinfo;
- u32 hash;
struct dx_frame frames[2], *frame;
- struct ext4_dir_entry_2 *de, *top;
struct buffer_head *bh;
ext4_lblk_t block;
int retval;
- int namelen = d_name->len;
- const u8 *name = d_name->name;
- sb = dir->i_sb;
- /* NFS may look up ".." - look at dx_root directory block */
- if (namelen > 2 || name[0] != '.'||(name[1] != '.' && name[1] != '\0')){
- if (!(frame = dx_probe(d_name, dir, &hinfo, frames, err)))
- return NULL;
- } else {
- frame = frames;
- frame->bh = NULL; /* for dx_release() */
- frame->at = (struct dx_entry *)frames; /* hack for zero entry*/
- dx_set_block(frame->at, 0); /* dx_root block is 0 */
- }
- hash = hinfo.hash;
+ if (!(frame = dx_probe(d_name, dir, &hinfo, frames, err)))
+ return NULL;
do {
block = dx_get_block(frame->at);
- if (!(bh = ext4_bread (NULL,dir, block, 0, err)))
+ if (!(bh = ext4_bread(NULL, dir, block, 0, err)))
goto errout;
- de = (struct ext4_dir_entry_2 *) bh->b_data;
- top = (struct ext4_dir_entry_2 *) ((char *) de + sb->s_blocksize -
- EXT4_DIR_REC_LEN(0));
- for (; de < top; de = ext4_next_entry(de, sb->s_blocksize)) {
- int off = (block << EXT4_BLOCK_SIZE_BITS(sb))
- + ((char *) de - bh->b_data);
-
- if (!ext4_check_dir_entry(dir, de, bh, off)) {
- brelse(bh);
- *err = ERR_BAD_DX_DIR;
- goto errout;
- }
- if (ext4_match(namelen, name, de)) {
- *res_dir = de;
- dx_release(frames);
- return bh;
- }
+ retval = search_dirblock(bh, dir, d_name,
+ block << EXT4_BLOCK_SIZE_BITS(sb),
+ res_dir);
+ if (retval == 1) { /* Success! */
+ dx_release(frames);
+ return bh;
}
brelse(bh);
+ if (retval == -1) {
+ *err = ERR_BAD_DX_DIR;
+ goto errout;
+ }
+
/* Check to see if we should continue to search */
- retval = ext4_htree_next_block(dir, hash, frame,
+ retval = ext4_htree_next_block(dir, hinfo.hash, frame,
frames, NULL);
if (retval < 0) {
ext4_warning(sb,
@@ -1045,7 +1036,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, stru
return ERR_PTR(-EIO);
}
inode = ext4_iget(dir->i_sb, ino);
- if (unlikely(IS_ERR(inode))) {
+ if (IS_ERR(inode)) {
if (PTR_ERR(inode) == -ESTALE) {
EXT4_ERROR_INODE(dir,
"deleted inode referenced: %u",
@@ -1278,7 +1269,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
de = (struct ext4_dir_entry_2 *)bh->b_data;
top = bh->b_data + blocksize - reclen;
while ((char *) de <= top) {
- if (!ext4_check_dir_entry(dir, de, bh, offset))
+ if (ext4_check_dir_entry(dir, NULL, de, bh, offset))
return -EIO;
if (ext4_match(namelen, name, de))
return -EEXIST;
@@ -1611,7 +1602,11 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
if (err)
goto journal_error;
}
- ext4_handle_dirty_metadata(handle, inode, frames[0].bh);
+ err = ext4_handle_dirty_metadata(handle, inode, frames[0].bh);
+ if (err) {
+ ext4_std_error(inode->i_sb, err);
+ goto cleanup;
+ }
}
de = do_split(handle, dir, &bh, frame, &hinfo, &err);
if (!de)
@@ -1639,17 +1634,21 @@ static int ext4_delete_entry(handle_t *handle,
{
struct ext4_dir_entry_2 *de, *pde;
unsigned int blocksize = dir->i_sb->s_blocksize;
- int i;
+ int i, err;
i = 0;
pde = NULL;
de = (struct ext4_dir_entry_2 *) bh->b_data;
while (i < bh->b_size) {
- if (!ext4_check_dir_entry(dir, de, bh, i))
+ if (ext4_check_dir_entry(dir, NULL, de, bh, i))
return -EIO;
if (de == de_del) {
BUFFER_TRACE(bh, "get_write_access");
- ext4_journal_get_write_access(handle, bh);
+ err = ext4_journal_get_write_access(handle, bh);
+ if (unlikely(err)) {
+ ext4_std_error(dir->i_sb, err);
+ return err;
+ }
if (pde)
pde->rec_len = ext4_rec_len_to_disk(
ext4_rec_len_from_disk(pde->rec_len,
@@ -1661,7 +1660,11 @@ static int ext4_delete_entry(handle_t *handle,
de->inode = 0;
dir->i_version++;
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
- ext4_handle_dirty_metadata(handle, dir, bh);
+ err = ext4_handle_dirty_metadata(handle, dir, bh);
+ if (unlikely(err)) {
+ ext4_std_error(dir->i_sb, err);
+ return err;
+ }
return 0;
}
i += ext4_rec_len_from_disk(de->rec_len, blocksize);
@@ -1798,7 +1801,7 @@ static int ext4_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
handle_t *handle;
struct inode *inode;
- struct buffer_head *dir_block;
+ struct buffer_head *dir_block = NULL;
struct ext4_dir_entry_2 *de;
unsigned int blocksize = dir->i_sb->s_blocksize;
int err, retries = 0;
@@ -1831,7 +1834,9 @@ retry:
if (!dir_block)
goto out_clear_inode;
BUFFER_TRACE(dir_block, "get_write_access");
- ext4_journal_get_write_access(handle, dir_block);
+ err = ext4_journal_get_write_access(handle, dir_block);
+ if (err)
+ goto out_clear_inode;
de = (struct ext4_dir_entry_2 *) dir_block->b_data;
de->inode = cpu_to_le32(inode->i_ino);
de->name_len = 1;
@@ -1848,10 +1853,12 @@ retry:
ext4_set_de_type(dir->i_sb, de, S_IFDIR);
inode->i_nlink = 2;
BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
- ext4_handle_dirty_metadata(handle, dir, dir_block);
- brelse(dir_block);
- ext4_mark_inode_dirty(handle, inode);
- err = ext4_add_entry(handle, dentry, inode);
+ err = ext4_handle_dirty_metadata(handle, dir, dir_block);
+ if (err)
+ goto out_clear_inode;
+ err = ext4_mark_inode_dirty(handle, inode);
+ if (!err)
+ err = ext4_add_entry(handle, dentry, inode);
if (err) {
out_clear_inode:
clear_nlink(inode);
@@ -1862,10 +1869,13 @@ out_clear_inode:
}
ext4_inc_count(handle, dir);
ext4_update_dx_flag(dir);
- ext4_mark_inode_dirty(handle, dir);
+ err = ext4_mark_inode_dirty(handle, dir);
+ if (err)
+ goto out_clear_inode;
d_instantiate(dentry, inode);
unlock_new_inode(inode);
out_stop:
+ brelse(dir_block);
ext4_journal_stop(handle);
if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
goto retry;
@@ -1928,7 +1938,7 @@ static int empty_dir(struct inode *inode)
}
de = (struct ext4_dir_entry_2 *) bh->b_data;
}
- if (!ext4_check_dir_entry(inode, de, bh, offset)) {
+ if (ext4_check_dir_entry(inode, NULL, de, bh, offset)) {
de = (struct ext4_dir_entry_2 *)(bh->b_data +
sb->s_blocksize);
offset = (offset | (sb->s_blocksize - 1)) + 1;
@@ -2312,7 +2322,7 @@ retry:
inode->i_ctime = ext4_current_time(inode);
ext4_inc_count(handle, inode);
- atomic_inc(&inode->i_count);
+ ihold(inode);
err = ext4_add_entry(handle, dentry, inode);
if (!err) {
@@ -2416,7 +2426,11 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
ext4_current_time(new_dir);
ext4_mark_inode_dirty(handle, new_dir);
BUFFER_TRACE(new_bh, "call ext4_handle_dirty_metadata");
- ext4_handle_dirty_metadata(handle, new_dir, new_bh);
+ retval = ext4_handle_dirty_metadata(handle, new_dir, new_bh);
+ if (unlikely(retval)) {
+ ext4_std_error(new_dir->i_sb, retval);
+ goto end_rename;
+ }
brelse(new_bh);
new_bh = NULL;
}
@@ -2468,7 +2482,11 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) =
cpu_to_le32(new_dir->i_ino);
BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
- ext4_handle_dirty_metadata(handle, old_dir, dir_bh);
+ retval = ext4_handle_dirty_metadata(handle, old_dir, dir_bh);
+ if (retval) {
+ ext4_std_error(old_dir->i_sb, retval);
+ goto end_rename;
+ }
ext4_dec_count(handle, old_dir);
if (new_inode) {
/* checked empty_dir above, can't have another parent,
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
new file mode 100644
index 00000000000..7270dcfca92
--- /dev/null
+++ b/fs/ext4/page-io.c
@@ -0,0 +1,428 @@
+/*
+ * linux/fs/ext4/page-io.c
+ *
+ * This contains the new page_io functions for ext4
+ *
+ * Written by Theodore Ts'o, 2010.
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/jbd2.h>
+#include <linux/highuid.h>
+#include <linux/pagemap.h>
+#include <linux/quotaops.h>
+#include <linux/string.h>
+#include <linux/buffer_head.h>
+#include <linux/writeback.h>
+#include <linux/pagevec.h>
+#include <linux/mpage.h>
+#include <linux/namei.h>
+#include <linux/uio.h>
+#include <linux/bio.h>
+#include <linux/workqueue.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include "ext4_jbd2.h"
+#include "xattr.h"
+#include "acl.h"
+#include "ext4_extents.h"
+
+static struct kmem_cache *io_page_cachep, *io_end_cachep;
+
+#define WQ_HASH_SZ 37
+#define to_ioend_wq(v) (&ioend_wq[((unsigned long)v) % WQ_HASH_SZ])
+static wait_queue_head_t ioend_wq[WQ_HASH_SZ];
+
+int __init ext4_init_pageio(void)
+{
+ int i;
+
+ io_page_cachep = KMEM_CACHE(ext4_io_page, SLAB_RECLAIM_ACCOUNT);
+ if (io_page_cachep == NULL)
+ return -ENOMEM;
+ io_end_cachep = KMEM_CACHE(ext4_io_end, SLAB_RECLAIM_ACCOUNT);
+ if (io_end_cachep == NULL) {
+ kmem_cache_destroy(io_page_cachep);
+ return -ENOMEM;
+ }
+ for (i = 0; i < WQ_HASH_SZ; i++)
+ init_waitqueue_head(&ioend_wq[i]);
+
+ return 0;
+}
+
+void ext4_exit_pageio(void)
+{
+ kmem_cache_destroy(io_end_cachep);
+ kmem_cache_destroy(io_page_cachep);
+}
+
+void ext4_ioend_wait(struct inode *inode)
+{
+ wait_queue_head_t *wq = to_ioend_wq(inode);
+
+ wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_ioend_count) == 0));
+}
+
+static void put_io_page(struct ext4_io_page *io_page)
+{
+ if (atomic_dec_and_test(&io_page->p_count)) {
+ end_page_writeback(io_page->p_page);
+ put_page(io_page->p_page);
+ kmem_cache_free(io_page_cachep, io_page);
+ }
+}
+
+void ext4_free_io_end(ext4_io_end_t *io)
+{
+ int i;
+ wait_queue_head_t *wq;
+
+ BUG_ON(!io);
+ if (io->page)
+ put_page(io->page);
+ for (i = 0; i < io->num_io_pages; i++)
+ put_io_page(io->pages[i]);
+ io->num_io_pages = 0;
+ wq = to_ioend_wq(io->inode);
+ if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count) &&
+ waitqueue_active(wq))
+ wake_up_all(wq);
+ kmem_cache_free(io_end_cachep, io);
+}
+
+/*
+ * check a range of space and convert unwritten extents to written.
+ */
+int ext4_end_io_nolock(ext4_io_end_t *io)
+{
+ struct inode *inode = io->inode;
+ loff_t offset = io->offset;
+ ssize_t size = io->size;
+ int ret = 0;
+
+ 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 & EXT4_IO_END_UNWRITTEN))
+ return ret;
+
+ 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 "
+ "io is still on inode %lu aio dio list\n",
+ __func__, ret, inode->i_ino);
+ return ret;
+ }
+
+ if (io->iocb)
+ aio_complete(io->iocb, io->result, 0);
+ /* clear the DIO AIO unwritten flag */
+ io->flag &= ~EXT4_IO_END_UNWRITTEN;
+ return ret;
+}
+
+/*
+ * work on completed aio dio IO, to convert unwritten extents to extents
+ */
+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;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ unsigned long flags;
+ int ret;
+
+ mutex_lock(&inode->i_mutex);
+ 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);
+}
+
+ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
+{
+ ext4_io_end_t *io = kmem_cache_zalloc(io_end_cachep, flags);
+ if (io) {
+ atomic_inc(&EXT4_I(inode)->i_ioend_count);
+ io->inode = inode;
+ INIT_WORK(&io->work, ext4_end_io_work);
+ INIT_LIST_HEAD(&io->list);
+ }
+ return io;
+}
+
+/*
+ * Print an buffer I/O error compatible with the fs/buffer.c. This
+ * provides compatibility with dmesg scrapers that look for a specific
+ * buffer I/O error message. We really need a unified error reporting
+ * structure to userspace ala Digital Unix's uerf system, but it's
+ * probably not going to happen in my lifetime, due to LKML politics...
+ */
+static void buffer_io_error(struct buffer_head *bh)
+{
+ char b[BDEVNAME_SIZE];
+ printk(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n",
+ bdevname(bh->b_bdev, b),
+ (unsigned long long)bh->b_blocknr);
+}
+
+static void ext4_end_bio(struct bio *bio, int error)
+{
+ ext4_io_end_t *io_end = bio->bi_private;
+ struct workqueue_struct *wq;
+ struct inode *inode;
+ unsigned long flags;
+ int i;
+
+ BUG_ON(!io_end);
+ bio->bi_private = NULL;
+ bio->bi_end_io = NULL;
+ if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+ error = 0;
+ bio_put(bio);
+
+ for (i = 0; i < io_end->num_io_pages; i++) {
+ struct page *page = io_end->pages[i]->p_page;
+ struct buffer_head *bh, *head;
+ int partial_write = 0;
+
+ head = page_buffers(page);
+ if (error)
+ SetPageError(page);
+ BUG_ON(!head);
+ if (head->b_size == PAGE_CACHE_SIZE)
+ clear_buffer_dirty(head);
+ else {
+ loff_t offset;
+ loff_t io_end_offset = io_end->offset + io_end->size;
+
+ offset = (sector_t) page->index << PAGE_CACHE_SHIFT;
+ bh = head;
+ do {
+ if ((offset >= io_end->offset) &&
+ (offset+bh->b_size <= io_end_offset)) {
+ if (error)
+ buffer_io_error(bh);
+
+ clear_buffer_dirty(bh);
+ }
+ if (buffer_delay(bh))
+ partial_write = 1;
+ else if (!buffer_mapped(bh))
+ clear_buffer_dirty(bh);
+ else if (buffer_dirty(bh))
+ partial_write = 1;
+ offset += bh->b_size;
+ bh = bh->b_this_page;
+ } while (bh != head);
+ }
+
+ /*
+ * If this is a partial write which happened to make
+ * all buffers uptodate then we can optimize away a
+ * bogus readpage() for the next read(). Here we
+ * 'discover' whether the page went uptodate as a
+ * result of this (potentially partial) write.
+ */
+ if (!partial_write)
+ SetPageUptodate(page);
+
+ put_io_page(io_end->pages[i]);
+ }
+ io_end->num_io_pages = 0;
+ inode = io_end->inode;
+
+ if (error) {
+ io_end->flag |= EXT4_IO_END_ERROR;
+ ext4_warning(inode->i_sb, "I/O error writing to inode %lu "
+ "(offset %llu size %ld starting block %llu)",
+ inode->i_ino,
+ (unsigned long long) io_end->offset,
+ (long) io_end->size,
+ (unsigned long long)
+ bio->bi_sector >> (inode->i_blkbits - 9));
+ }
+
+ /* 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);
+}
+
+void ext4_io_submit(struct ext4_io_submit *io)
+{
+ struct bio *bio = io->io_bio;
+
+ if (bio) {
+ bio_get(io->io_bio);
+ submit_bio(io->io_op, io->io_bio);
+ BUG_ON(bio_flagged(io->io_bio, BIO_EOPNOTSUPP));
+ bio_put(io->io_bio);
+ }
+ io->io_bio = 0;
+ io->io_op = 0;
+ io->io_end = 0;
+}
+
+static int io_submit_init(struct ext4_io_submit *io,
+ struct inode *inode,
+ struct writeback_control *wbc,
+ struct buffer_head *bh)
+{
+ ext4_io_end_t *io_end;
+ struct page *page = bh->b_page;
+ int nvecs = bio_get_nr_vecs(bh->b_bdev);
+ struct bio *bio;
+
+ io_end = ext4_init_io_end(inode, GFP_NOFS);
+ if (!io_end)
+ return -ENOMEM;
+ do {
+ bio = bio_alloc(GFP_NOIO, nvecs);
+ nvecs >>= 1;
+ } while (bio == NULL);
+
+ bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+ bio->bi_bdev = bh->b_bdev;
+ bio->bi_private = io->io_end = io_end;
+ bio->bi_end_io = ext4_end_bio;
+
+ io_end->offset = (page->index << PAGE_CACHE_SHIFT) + bh_offset(bh);
+
+ io->io_bio = bio;
+ io->io_op = (wbc->sync_mode == WB_SYNC_ALL ?
+ WRITE_SYNC_PLUG : WRITE);
+ io->io_next_block = bh->b_blocknr;
+ return 0;
+}
+
+static int io_submit_add_bh(struct ext4_io_submit *io,
+ struct ext4_io_page *io_page,
+ struct inode *inode,
+ struct writeback_control *wbc,
+ struct buffer_head *bh)
+{
+ ext4_io_end_t *io_end;
+ int ret;
+
+ if (buffer_new(bh)) {
+ clear_buffer_new(bh);
+ unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
+ }
+
+ if (!buffer_mapped(bh) || buffer_delay(bh)) {
+ if (!buffer_mapped(bh))
+ clear_buffer_dirty(bh);
+ if (io->io_bio)
+ ext4_io_submit(io);
+ return 0;
+ }
+
+ if (io->io_bio && bh->b_blocknr != io->io_next_block) {
+submit_and_retry:
+ ext4_io_submit(io);
+ }
+ if (io->io_bio == NULL) {
+ ret = io_submit_init(io, inode, wbc, bh);
+ if (ret)
+ return ret;
+ }
+ io_end = io->io_end;
+ if ((io_end->num_io_pages >= MAX_IO_PAGES) &&
+ (io_end->pages[io_end->num_io_pages-1] != io_page))
+ goto submit_and_retry;
+ if (buffer_uninit(bh))
+ io->io_end->flag |= EXT4_IO_END_UNWRITTEN;
+ io->io_end->size += bh->b_size;
+ io->io_next_block++;
+ ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
+ if (ret != bh->b_size)
+ goto submit_and_retry;
+ if ((io_end->num_io_pages == 0) ||
+ (io_end->pages[io_end->num_io_pages-1] != io_page)) {
+ io_end->pages[io_end->num_io_pages++] = io_page;
+ atomic_inc(&io_page->p_count);
+ }
+ return 0;
+}
+
+int ext4_bio_write_page(struct ext4_io_submit *io,
+ struct page *page,
+ int len,
+ struct writeback_control *wbc)
+{
+ struct inode *inode = page->mapping->host;
+ unsigned block_start, block_end, blocksize;
+ struct ext4_io_page *io_page;
+ struct buffer_head *bh, *head;
+ int ret = 0;
+
+ blocksize = 1 << inode->i_blkbits;
+
+ BUG_ON(PageWriteback(page));
+ set_page_writeback(page);
+ ClearPageError(page);
+
+ io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
+ if (!io_page) {
+ set_page_dirty(page);
+ unlock_page(page);
+ return -ENOMEM;
+ }
+ io_page->p_page = page;
+ atomic_set(&io_page->p_count, 1);
+ get_page(page);
+
+ for (bh = head = page_buffers(page), block_start = 0;
+ bh != head || !block_start;
+ block_start = block_end, bh = bh->b_this_page) {
+ block_end = block_start + blocksize;
+ if (block_start >= len) {
+ clear_buffer_dirty(bh);
+ set_buffer_uptodate(bh);
+ continue;
+ }
+ ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
+ if (ret) {
+ /*
+ * We only get here on ENOMEM. Not much else
+ * we can do but mark the page as dirty, and
+ * better luck next time.
+ */
+ set_page_dirty(page);
+ break;
+ }
+ }
+ unlock_page(page);
+ /*
+ * If the page was truncated before we could do the writeback,
+ * or we had a memory allocation error while trying to write
+ * the first buffer head, we won't have submitted any pages for
+ * I/O. In that case we need to make sure we've cleared the
+ * PageWriteback bit from the page to prevent the system from
+ * wedging later on.
+ */
+ put_io_page(io_page);
+ return ret;
+}
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index ca5c8aa00a2..3ecc6e45d2f 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -220,29 +220,25 @@ static int setup_new_group_blocks(struct super_block *sb,
memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, gdb->b_size);
set_buffer_uptodate(gdb);
unlock_buffer(gdb);
- ext4_handle_dirty_metadata(handle, NULL, gdb);
+ err = ext4_handle_dirty_metadata(handle, NULL, gdb);
+ if (unlikely(err)) {
+ brelse(gdb);
+ goto exit_bh;
+ }
ext4_set_bit(bit, bh->b_data);
brelse(gdb);
}
/* Zero out all of the reserved backup group descriptor table blocks */
- for (i = 0, bit = gdblocks + 1, block = start + bit;
- i < reserved_gdb; i++, block++, bit++) {
- struct buffer_head *gdb;
-
- ext4_debug("clear reserved block %#04llx (+%d)\n", block, bit);
-
- if ((err = extend_or_restart_transaction(handle, 1, bh)))
- goto exit_bh;
-
- if (IS_ERR(gdb = bclean(handle, sb, block))) {
- err = PTR_ERR(gdb);
- goto exit_bh;
- }
- ext4_handle_dirty_metadata(handle, NULL, gdb);
+ ext4_debug("clear inode table blocks %#04llx -> %#04llx\n",
+ block, sbi->s_itb_per_group);
+ err = sb_issue_zeroout(sb, gdblocks + start + 1, reserved_gdb,
+ GFP_NOFS);
+ if (err)
+ goto exit_bh;
+ for (i = 0, bit = gdblocks + 1; i < reserved_gdb; i++, bit++)
ext4_set_bit(bit, bh->b_data);
- brelse(gdb);
- }
+
ext4_debug("mark block bitmap %#04llx (+%llu)\n", input->block_bitmap,
input->block_bitmap - start);
ext4_set_bit(input->block_bitmap - start, bh->b_data);
@@ -251,29 +247,26 @@ static int setup_new_group_blocks(struct super_block *sb,
ext4_set_bit(input->inode_bitmap - start, bh->b_data);
/* Zero out all of the inode table blocks */
- for (i = 0, block = input->inode_table, bit = block - start;
- i < sbi->s_itb_per_group; i++, bit++, block++) {
- struct buffer_head *it;
-
- ext4_debug("clear inode block %#04llx (+%d)\n", block, bit);
-
- if ((err = extend_or_restart_transaction(handle, 1, bh)))
- goto exit_bh;
-
- if (IS_ERR(it = bclean(handle, sb, block))) {
- err = PTR_ERR(it);
- goto exit_bh;
- }
- ext4_handle_dirty_metadata(handle, NULL, it);
- brelse(it);
+ block = input->inode_table;
+ ext4_debug("clear inode table blocks %#04llx -> %#04llx\n",
+ block, sbi->s_itb_per_group);
+ err = sb_issue_zeroout(sb, block, sbi->s_itb_per_group, GFP_NOFS);
+ if (err)
+ goto exit_bh;
+ for (i = 0, bit = input->inode_table - start;
+ i < sbi->s_itb_per_group; i++, bit++)
ext4_set_bit(bit, bh->b_data);
- }
if ((err = extend_or_restart_transaction(handle, 2, bh)))
goto exit_bh;
- mark_bitmap_end(input->blocks_count, sb->s_blocksize * 8, bh->b_data);
- ext4_handle_dirty_metadata(handle, NULL, bh);
+ ext4_mark_bitmap_end(input->blocks_count, sb->s_blocksize * 8,
+ bh->b_data);
+ err = ext4_handle_dirty_metadata(handle, NULL, bh);
+ if (unlikely(err)) {
+ ext4_std_error(sb, err);
+ goto exit_bh;
+ }
brelse(bh);
/* Mark unused entries in inode bitmap used */
ext4_debug("clear inode bitmap %#04llx (+%llu)\n",
@@ -283,9 +276,11 @@ static int setup_new_group_blocks(struct super_block *sb,
goto exit_journal;
}
- mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
- bh->b_data);
- ext4_handle_dirty_metadata(handle, NULL, bh);
+ ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
+ bh->b_data);
+ err = ext4_handle_dirty_metadata(handle, NULL, bh);
+ if (unlikely(err))
+ ext4_std_error(sb, err);
exit_bh:
brelse(bh);
@@ -437,17 +432,21 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
goto exit_dind;
}
- if ((err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh)))
+ err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
+ if (unlikely(err))
goto exit_dind;
- if ((err = ext4_journal_get_write_access(handle, *primary)))
+ err = ext4_journal_get_write_access(handle, *primary);
+ if (unlikely(err))
goto exit_sbh;
- if ((err = ext4_journal_get_write_access(handle, dind)))
- goto exit_primary;
+ err = ext4_journal_get_write_access(handle, dind);
+ if (unlikely(err))
+ ext4_std_error(sb, err);
/* ext4_reserve_inode_write() gets a reference on the iloc */
- if ((err = ext4_reserve_inode_write(handle, inode, &iloc)))
+ err = ext4_reserve_inode_write(handle, inode, &iloc);
+ if (unlikely(err))
goto exit_dindj;
n_group_desc = kmalloc((gdb_num + 1) * sizeof(struct buffer_head *),
@@ -469,12 +468,20 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
* reserved inode, and will become GDT blocks (primary and backup).
*/
data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)] = 0;
- ext4_handle_dirty_metadata(handle, NULL, dind);
- brelse(dind);
+ err = ext4_handle_dirty_metadata(handle, NULL, dind);
+ if (unlikely(err)) {
+ ext4_std_error(sb, err);
+ goto exit_inode;
+ }
inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9;
ext4_mark_iloc_dirty(handle, inode, &iloc);
memset((*primary)->b_data, 0, sb->s_blocksize);
- ext4_handle_dirty_metadata(handle, NULL, *primary);
+ err = ext4_handle_dirty_metadata(handle, NULL, *primary);
+ if (unlikely(err)) {
+ ext4_std_error(sb, err);
+ goto exit_inode;
+ }
+ brelse(dind);
o_group_desc = EXT4_SB(sb)->s_group_desc;
memcpy(n_group_desc, o_group_desc,
@@ -485,19 +492,19 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
kfree(o_group_desc);
le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
- ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
+ err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
+ if (err)
+ ext4_std_error(sb, err);
- return 0;
+ return err;
exit_inode:
/* ext4_journal_release_buffer(handle, iloc.bh); */
brelse(iloc.bh);
exit_dindj:
/* ext4_journal_release_buffer(handle, dind); */
-exit_primary:
- /* ext4_journal_release_buffer(handle, *primary); */
exit_sbh:
- /* ext4_journal_release_buffer(handle, *primary); */
+ /* ext4_journal_release_buffer(handle, EXT4_SB(sb)->s_sbh); */
exit_dind:
brelse(dind);
exit_bh:
@@ -680,7 +687,9 @@ static void update_backups(struct super_block *sb,
memset(bh->b_data + size, 0, rest);
set_buffer_uptodate(bh);
unlock_buffer(bh);
- ext4_handle_dirty_metadata(handle, NULL, bh);
+ err = ext4_handle_dirty_metadata(handle, NULL, bh);
+ if (unlikely(err))
+ ext4_std_error(sb, err);
brelse(bh);
}
if ((err2 = ext4_journal_stop(handle)) && !err)
@@ -898,7 +907,11 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
/* Update the global fs size fields */
sbi->s_groups_count++;
- ext4_handle_dirty_metadata(handle, NULL, primary);
+ err = ext4_handle_dirty_metadata(handle, NULL, primary);
+ if (unlikely(err)) {
+ ext4_std_error(sb, err);
+ goto exit_journal;
+ }
/* Update the reserved block counts only once the new group is
* active. */
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 26147746c27..48ce561fafa 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -26,7 +26,6 @@
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/parser.h>
-#include <linux/smp_lock.h>
#include <linux/buffer_head.h>
#include <linux/exportfs.h>
#include <linux/vfs.h>
@@ -41,6 +40,9 @@
#include <linux/crc16.h>
#include <asm/uaccess.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+
#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -50,8 +52,11 @@
#define CREATE_TRACE_POINTS
#include <trace/events/ext4.h>
-struct proc_dir_entry *ext4_proc_root;
+static struct proc_dir_entry *ext4_proc_root;
static struct kset *ext4_kset;
+struct ext4_lazy_init *ext4_li_info;
+struct mutex ext4_li_mtx;
+struct ext4_features *ext4_feat;
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
@@ -68,14 +73,16 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
static int ext4_unfreeze(struct super_block *sb);
static void ext4_write_super(struct super_block *sb);
static int ext4_freeze(struct super_block *sb);
-static int ext4_get_sb(struct file_system_type *fs_type, int flags,
- const char *dev_name, void *data, struct vfsmount *mnt);
+static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *data);
+static void ext4_destroy_lazyinit_thread(void);
+static void ext4_unregister_li_request(struct super_block *sb);
#if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
static struct file_system_type ext3_fs_type = {
.owner = THIS_MODULE,
.name = "ext3",
- .get_sb = ext4_get_sb,
+ .mount = ext4_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
@@ -381,13 +388,14 @@ static void ext4_handle_error(struct super_block *sb)
void __ext4_error(struct super_block *sb, const char *function,
unsigned int line, const char *fmt, ...)
{
+ struct va_format vaf;
va_list args;
va_start(args, fmt);
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: ",
- sb->s_id, function, line, current->comm);
- vprintk(fmt, args);
- printk("\n");
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: %pV\n",
+ sb->s_id, function, line, current->comm, &vaf);
va_end(args);
ext4_handle_error(sb);
@@ -398,28 +406,31 @@ void ext4_error_inode(struct inode *inode, const char *function,
const char *fmt, ...)
{
va_list args;
+ struct va_format vaf;
struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
es->s_last_error_block = cpu_to_le64(block);
save_error_info(inode->i_sb, function, line);
va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: ",
inode->i_sb->s_id, function, line, inode->i_ino);
if (block)
- printk("block %llu: ", block);
- printk("comm %s: ", current->comm);
- vprintk(fmt, args);
- printk("\n");
+ printk(KERN_CONT "block %llu: ", block);
+ printk(KERN_CONT "comm %s: %pV\n", current->comm, &vaf);
va_end(args);
ext4_handle_error(inode->i_sb);
}
void ext4_error_file(struct file *file, const char *function,
- unsigned int line, const char *fmt, ...)
+ unsigned int line, ext4_fsblk_t block,
+ const char *fmt, ...)
{
va_list args;
+ struct va_format vaf;
struct ext4_super_block *es;
struct inode *inode = file->f_dentry->d_inode;
char pathname[80], *path;
@@ -427,17 +438,18 @@ void ext4_error_file(struct file *file, const char *function,
es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
save_error_info(inode->i_sb, function, line);
- va_start(args, fmt);
path = d_path(&(file->f_path), pathname, sizeof(pathname));
- if (!path)
+ if (IS_ERR(path))
path = "(unknown)";
printk(KERN_CRIT
- "EXT4-fs error (device %s): %s:%d: inode #%lu "
- "(comm %s path %s): ",
- inode->i_sb->s_id, function, line, inode->i_ino,
- current->comm, path);
- vprintk(fmt, args);
- printk("\n");
+ "EXT4-fs error (device %s): %s:%d: inode #%lu: ",
+ inode->i_sb->s_id, function, line, inode->i_ino);
+ if (block)
+ printk(KERN_CONT "block %llu: ", block);
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk(KERN_CONT "comm %s: path %s: %pV\n", current->comm, path, &vaf);
va_end(args);
ext4_handle_error(inode->i_sb);
@@ -536,28 +548,29 @@ void __ext4_abort(struct super_block *sb, const char *function,
panic("EXT4-fs panic from previous error\n");
}
-void ext4_msg (struct super_block * sb, const char *prefix,
- const char *fmt, ...)
+void ext4_msg(struct super_block *sb, const char *prefix, const char *fmt, ...)
{
+ struct va_format vaf;
va_list args;
va_start(args, fmt);
- printk("%sEXT4-fs (%s): ", prefix, sb->s_id);
- vprintk(fmt, args);
- printk("\n");
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk("%sEXT4-fs (%s): %pV\n", prefix, sb->s_id, &vaf);
va_end(args);
}
void __ext4_warning(struct super_block *sb, const char *function,
unsigned int line, const char *fmt, ...)
{
+ struct va_format vaf;
va_list args;
va_start(args, fmt);
- printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: ",
- sb->s_id, function, line);
- vprintk(fmt, args);
- printk("\n");
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: %pV\n",
+ sb->s_id, function, line, &vaf);
va_end(args);
}
@@ -568,21 +581,25 @@ void __ext4_grp_locked_error(const char *function, unsigned int line,
__releases(bitlock)
__acquires(bitlock)
{
+ struct va_format vaf;
va_list args;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
es->s_last_error_ino = cpu_to_le32(ino);
es->s_last_error_block = cpu_to_le64(block);
__save_error_info(sb, function, line);
+
va_start(args, fmt);
+
+ vaf.fmt = fmt;
+ vaf.va = &args;
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u",
sb->s_id, function, line, grp);
if (ino)
- printk("inode %lu: ", ino);
+ printk(KERN_CONT "inode %lu: ", ino);
if (block)
- printk("block %llu:", (unsigned long long) block);
- vprintk(fmt, args);
- printk("\n");
+ printk(KERN_CONT "block %llu:", (unsigned long long) block);
+ printk(KERN_CONT "%pV\n", &vaf);
va_end(args);
if (test_opt(sb, ERRORS_CONT)) {
@@ -640,7 +657,7 @@ static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb)
struct block_device *bdev;
char b[BDEVNAME_SIZE];
- bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
+ bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb);
if (IS_ERR(bdev))
goto fail;
return bdev;
@@ -656,8 +673,7 @@ fail:
*/
static int ext4_blkdev_put(struct block_device *bdev)
{
- bd_release(bdev);
- return blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
+ return blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
}
static int ext4_blkdev_remove(struct ext4_sb_info *sbi)
@@ -702,13 +718,13 @@ static void ext4_put_super(struct super_block *sb)
struct ext4_super_block *es = sbi->s_es;
int i, err;
+ ext4_unregister_li_request(sb);
dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
flush_workqueue(sbi->dio_unwritten_wq);
destroy_workqueue(sbi->dio_unwritten_wq);
lock_super(sb);
- lock_kernel();
if (sb->s_dirt)
ext4_commit_super(sb, 1);
@@ -719,6 +735,7 @@ static void ext4_put_super(struct super_block *sb)
ext4_abort(sb, "Couldn't clean up the journal");
}
+ del_timer(&sbi->s_err_report);
ext4_release_system_zone(sb);
ext4_mb_release(sb);
ext4_ext_release(sb);
@@ -775,7 +792,6 @@ static void ext4_put_super(struct super_block *sb)
* Now that we are completely done shutting down the
* superblock, we need to actually destroy the kobject.
*/
- unlock_kernel();
unlock_super(sb);
kobject_put(&sbi->s_kobj);
wait_for_completion(&sbi->s_kobj_unregister);
@@ -801,32 +817,43 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
- /*
- * Note: We can be called before EXT4_SB(sb)->s_journal is set,
- * therefore it can be null here. Don't check it, just initialize
- * jinode.
- */
- jbd2_journal_init_jbd_inode(&ei->jinode, &ei->vfs_inode);
ei->i_reserved_data_blocks = 0;
ei->i_reserved_meta_blocks = 0;
ei->i_allocated_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
- ei->i_delalloc_reserved_flag = 0;
spin_lock_init(&(ei->i_block_reservation_lock));
#ifdef CONFIG_QUOTA
ei->i_reserved_quota = 0;
#endif
+ ei->jinode = NULL;
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;
+ atomic_set(&ei->i_ioend_count, 0);
return &ei->vfs_inode;
}
+static int ext4_drop_inode(struct inode *inode)
+{
+ int drop = generic_drop_inode(inode);
+
+ trace_ext4_drop_inode(inode, drop);
+ return drop;
+}
+
+static void ext4_i_callback(struct rcu_head *head)
+{
+ struct inode *inode = container_of(head, struct inode, i_rcu);
+ INIT_LIST_HEAD(&inode->i_dentry);
+ kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
+}
+
static void ext4_destroy_inode(struct inode *inode)
{
+ ext4_ioend_wait(inode);
if (!list_empty(&(EXT4_I(inode)->i_orphan))) {
ext4_msg(inode->i_sb, KERN_ERR,
"Inode %lu (%p): orphan list check failed!",
@@ -836,7 +863,7 @@ static void ext4_destroy_inode(struct inode *inode)
true);
dump_stack();
}
- kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
+ call_rcu(&inode->i_rcu, ext4_i_callback);
}
static void init_once(void *foo)
@@ -874,9 +901,12 @@ void ext4_clear_inode(struct inode *inode)
end_writeback(inode);
dquot_drop(inode);
ext4_discard_preallocations(inode);
- if (EXT4_JOURNAL(inode))
- jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
- &EXT4_I(inode)->jinode);
+ if (EXT4_I(inode)->jinode) {
+ jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode),
+ EXT4_I(inode)->jinode);
+ jbd2_free_inode(EXT4_I(inode)->jinode);
+ EXT4_I(inode)->jinode = NULL;
+ }
}
static inline void ext4_show_quota_options(struct seq_file *seq,
@@ -1009,6 +1039,8 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
!(def_mount_opts & EXT4_DEFM_NODELALLOC))
seq_puts(seq, ",nodelalloc");
+ if (test_opt(sb, MBLK_IO_SUBMIT))
+ seq_puts(seq, ",mblk_io_submit");
if (sbi->s_stripe)
seq_printf(seq, ",stripe=%lu", sbi->s_stripe);
/*
@@ -1045,6 +1077,12 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
!(def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY))
seq_puts(seq, ",block_validity");
+ if (!test_opt(sb, INIT_INODE_TABLE))
+ seq_puts(seq, ",noinit_inode_table");
+ else if (sbi->s_li_wait_mult)
+ seq_printf(seq, ",init_inode_table=%u",
+ (unsigned) sbi->s_li_wait_mult);
+
ext4_show_quota_options(seq, sb);
return 0;
@@ -1123,7 +1161,7 @@ static int ext4_release_dquot(struct dquot *dquot);
static int ext4_mark_dquot_dirty(struct dquot *dquot);
static int ext4_write_info(struct super_block *sb, int type);
static int ext4_quota_on(struct super_block *sb, int type, int format_id,
- char *path);
+ struct path *path);
static int ext4_quota_off(struct super_block *sb, int type);
static int ext4_quota_on_mount(struct super_block *sb, int type);
static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
@@ -1160,6 +1198,7 @@ static const struct super_operations ext4_sops = {
.destroy_inode = ext4_destroy_inode,
.write_inode = ext4_write_inode,
.dirty_inode = ext4_dirty_inode,
+ .drop_inode = ext4_drop_inode,
.evict_inode = ext4_evict_inode,
.put_super = ext4_put_super,
.sync_fs = ext4_sync_fs,
@@ -1180,6 +1219,7 @@ static const struct super_operations ext4_nojournal_sops = {
.destroy_inode = ext4_destroy_inode,
.write_inode = ext4_write_inode,
.dirty_inode = ext4_dirty_inode,
+ .drop_inode = ext4_drop_inode,
.evict_inode = ext4_evict_inode,
.write_super = ext4_write_super,
.put_super = ext4_put_super,
@@ -1214,11 +1254,12 @@ enum {
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_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
+ Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
Opt_inode_readahead_blks, Opt_journal_ioprio,
Opt_dioread_nolock, Opt_dioread_lock,
Opt_discard, Opt_nodiscard,
+ Opt_init_inode_table, Opt_noinit_inode_table,
};
static const match_table_t tokens = {
@@ -1278,6 +1319,8 @@ static const match_table_t tokens = {
{Opt_resize, "resize"},
{Opt_delalloc, "delalloc"},
{Opt_nodelalloc, "nodelalloc"},
+ {Opt_mblk_io_submit, "mblk_io_submit"},
+ {Opt_nomblk_io_submit, "nomblk_io_submit"},
{Opt_block_validity, "block_validity"},
{Opt_noblock_validity, "noblock_validity"},
{Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
@@ -1289,6 +1332,9 @@ static const match_table_t tokens = {
{Opt_dioread_lock, "dioread_lock"},
{Opt_discard, "discard"},
{Opt_nodiscard, "nodiscard"},
+ {Opt_init_inode_table, "init_itable=%u"},
+ {Opt_init_inode_table, "init_itable"},
+ {Opt_noinit_inode_table, "noinit_itable"},
{Opt_err, NULL},
};
@@ -1353,7 +1399,7 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args)
sbi->s_qf_names[qtype] = NULL;
return 0;
}
- set_opt(sbi->s_mount_opt, QUOTA);
+ set_opt(sb, QUOTA);
return 1;
}
@@ -1408,21 +1454,21 @@ static int parse_options(char *options, struct super_block *sb,
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);
+ clear_opt(sb, 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);
+ set_opt(sb, MINIX_DF);
break;
case Opt_grpid:
ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
- set_opt(sbi->s_mount_opt, GRPID);
+ set_opt(sb, GRPID);
break;
case Opt_nogrpid:
ext4_msg(sb, KERN_WARNING, deprecated_msg, p, "2.6.38");
- clear_opt(sbi->s_mount_opt, GRPID);
+ clear_opt(sb, GRPID);
break;
case Opt_resuid:
@@ -1440,38 +1486,38 @@ static int parse_options(char *options, struct super_block *sb,
/* *sb_block = match_int(&args[0]); */
break;
case Opt_err_panic:
- clear_opt(sbi->s_mount_opt, ERRORS_CONT);
- clear_opt(sbi->s_mount_opt, ERRORS_RO);
- set_opt(sbi->s_mount_opt, ERRORS_PANIC);
+ clear_opt(sb, ERRORS_CONT);
+ clear_opt(sb, ERRORS_RO);
+ set_opt(sb, ERRORS_PANIC);
break;
case Opt_err_ro:
- clear_opt(sbi->s_mount_opt, ERRORS_CONT);
- clear_opt(sbi->s_mount_opt, ERRORS_PANIC);
- set_opt(sbi->s_mount_opt, ERRORS_RO);
+ clear_opt(sb, ERRORS_CONT);
+ clear_opt(sb, ERRORS_PANIC);
+ set_opt(sb, ERRORS_RO);
break;
case Opt_err_cont:
- clear_opt(sbi->s_mount_opt, ERRORS_RO);
- clear_opt(sbi->s_mount_opt, ERRORS_PANIC);
- set_opt(sbi->s_mount_opt, ERRORS_CONT);
+ clear_opt(sb, ERRORS_RO);
+ clear_opt(sb, ERRORS_PANIC);
+ set_opt(sb, ERRORS_CONT);
break;
case Opt_nouid32:
- set_opt(sbi->s_mount_opt, NO_UID32);
+ set_opt(sb, NO_UID32);
break;
case Opt_debug:
- set_opt(sbi->s_mount_opt, DEBUG);
+ set_opt(sb, DEBUG);
break;
case Opt_oldalloc:
- set_opt(sbi->s_mount_opt, OLDALLOC);
+ set_opt(sb, OLDALLOC);
break;
case Opt_orlov:
- clear_opt(sbi->s_mount_opt, OLDALLOC);
+ clear_opt(sb, OLDALLOC);
break;
#ifdef CONFIG_EXT4_FS_XATTR
case Opt_user_xattr:
- set_opt(sbi->s_mount_opt, XATTR_USER);
+ set_opt(sb, XATTR_USER);
break;
case Opt_nouser_xattr:
- clear_opt(sbi->s_mount_opt, XATTR_USER);
+ clear_opt(sb, XATTR_USER);
break;
#else
case Opt_user_xattr:
@@ -1481,10 +1527,10 @@ static int parse_options(char *options, struct super_block *sb,
#endif
#ifdef CONFIG_EXT4_FS_POSIX_ACL
case Opt_acl:
- set_opt(sbi->s_mount_opt, POSIX_ACL);
+ set_opt(sb, POSIX_ACL);
break;
case Opt_noacl:
- clear_opt(sbi->s_mount_opt, POSIX_ACL);
+ clear_opt(sb, POSIX_ACL);
break;
#else
case Opt_acl:
@@ -1503,7 +1549,7 @@ static int parse_options(char *options, struct super_block *sb,
"Cannot specify journal on remount");
return 0;
}
- set_opt(sbi->s_mount_opt, UPDATE_JOURNAL);
+ set_opt(sb, UPDATE_JOURNAL);
break;
case Opt_journal_dev:
if (is_remount) {
@@ -1516,14 +1562,14 @@ static int parse_options(char *options, struct super_block *sb,
*journal_devnum = option;
break;
case Opt_journal_checksum:
- set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM);
+ set_opt(sb, JOURNAL_CHECKSUM);
break;
case Opt_journal_async_commit:
- set_opt(sbi->s_mount_opt, JOURNAL_ASYNC_COMMIT);
- set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM);
+ set_opt(sb, JOURNAL_ASYNC_COMMIT);
+ set_opt(sb, JOURNAL_CHECKSUM);
break;
case Opt_noload:
- set_opt(sbi->s_mount_opt, NOLOAD);
+ set_opt(sb, NOLOAD);
break;
case Opt_commit:
if (match_int(&args[0], &option))
@@ -1566,15 +1612,15 @@ static int parse_options(char *options, struct super_block *sb,
return 0;
}
} else {
- clear_opt(sbi->s_mount_opt, DATA_FLAGS);
+ clear_opt(sb, DATA_FLAGS);
sbi->s_mount_opt |= data_opt;
}
break;
case Opt_data_err_abort:
- set_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
+ set_opt(sb, DATA_ERR_ABORT);
break;
case Opt_data_err_ignore:
- clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
+ clear_opt(sb, DATA_ERR_ABORT);
break;
#ifdef CONFIG_QUOTA
case Opt_usrjquota:
@@ -1614,12 +1660,12 @@ set_qf_format:
break;
case Opt_quota:
case Opt_usrquota:
- set_opt(sbi->s_mount_opt, QUOTA);
- set_opt(sbi->s_mount_opt, USRQUOTA);
+ set_opt(sb, QUOTA);
+ set_opt(sb, USRQUOTA);
break;
case Opt_grpquota:
- set_opt(sbi->s_mount_opt, QUOTA);
- set_opt(sbi->s_mount_opt, GRPQUOTA);
+ set_opt(sb, QUOTA);
+ set_opt(sb, GRPQUOTA);
break;
case Opt_noquota:
if (sb_any_quota_loaded(sb)) {
@@ -1627,9 +1673,9 @@ set_qf_format:
"options when quota turned on");
return 0;
}
- clear_opt(sbi->s_mount_opt, QUOTA);
- clear_opt(sbi->s_mount_opt, USRQUOTA);
- clear_opt(sbi->s_mount_opt, GRPQUOTA);
+ clear_opt(sb, QUOTA);
+ clear_opt(sb, USRQUOTA);
+ clear_opt(sb, GRPQUOTA);
break;
#else
case Opt_quota:
@@ -1655,7 +1701,7 @@ set_qf_format:
sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
break;
case Opt_nobarrier:
- clear_opt(sbi->s_mount_opt, BARRIER);
+ clear_opt(sb, BARRIER);
break;
case Opt_barrier:
if (args[0].from) {
@@ -1664,9 +1710,9 @@ set_qf_format:
} else
option = 1; /* No argument, default to 1 */
if (option)
- set_opt(sbi->s_mount_opt, BARRIER);
+ set_opt(sb, BARRIER);
else
- clear_opt(sbi->s_mount_opt, BARRIER);
+ clear_opt(sb, BARRIER);
break;
case Opt_ignore:
break;
@@ -1690,11 +1736,17 @@ set_qf_format:
"Ignoring deprecated bh option");
break;
case Opt_i_version:
- set_opt(sbi->s_mount_opt, I_VERSION);
+ set_opt(sb, I_VERSION);
sb->s_flags |= MS_I_VERSION;
break;
case Opt_nodelalloc:
- clear_opt(sbi->s_mount_opt, DELALLOC);
+ clear_opt(sb, DELALLOC);
+ break;
+ case Opt_mblk_io_submit:
+ set_opt(sb, MBLK_IO_SUBMIT);
+ break;
+ case Opt_nomblk_io_submit:
+ clear_opt(sb, MBLK_IO_SUBMIT);
break;
case Opt_stripe:
if (match_int(&args[0], &option))
@@ -1704,13 +1756,13 @@ set_qf_format:
sbi->s_stripe = option;
break;
case Opt_delalloc:
- set_opt(sbi->s_mount_opt, DELALLOC);
+ set_opt(sb, DELALLOC);
break;
case Opt_block_validity:
- set_opt(sbi->s_mount_opt, BLOCK_VALIDITY);
+ set_opt(sb, BLOCK_VALIDITY);
break;
case Opt_noblock_validity:
- clear_opt(sbi->s_mount_opt, BLOCK_VALIDITY);
+ clear_opt(sb, BLOCK_VALIDITY);
break;
case Opt_inode_readahead_blks:
if (match_int(&args[0], &option))
@@ -1734,7 +1786,7 @@ set_qf_format:
option);
break;
case Opt_noauto_da_alloc:
- set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC);
+ set_opt(sb, NO_AUTO_DA_ALLOC);
break;
case Opt_auto_da_alloc:
if (args[0].from) {
@@ -1743,21 +1795,35 @@ set_qf_format:
} else
option = 1; /* No argument, default to 1 */
if (option)
- clear_opt(sbi->s_mount_opt, NO_AUTO_DA_ALLOC);
+ clear_opt(sb, NO_AUTO_DA_ALLOC);
else
- set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC);
+ set_opt(sb,NO_AUTO_DA_ALLOC);
break;
case Opt_discard:
- set_opt(sbi->s_mount_opt, DISCARD);
+ set_opt(sb, DISCARD);
break;
case Opt_nodiscard:
- clear_opt(sbi->s_mount_opt, DISCARD);
+ clear_opt(sb, DISCARD);
break;
case Opt_dioread_nolock:
- set_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ set_opt(sb, DIOREAD_NOLOCK);
break;
case Opt_dioread_lock:
- clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK);
+ clear_opt(sb, DIOREAD_NOLOCK);
+ break;
+ case Opt_init_inode_table:
+ set_opt(sb, INIT_INODE_TABLE);
+ if (args[0].from) {
+ if (match_int(&args[0], &option))
+ return 0;
+ } else
+ option = EXT4_DEF_LI_WAIT_MULT;
+ if (option < 0)
+ return 0;
+ sbi->s_li_wait_mult = option;
+ break;
+ case Opt_noinit_inode_table:
+ clear_opt(sb, INIT_INODE_TABLE);
break;
default:
ext4_msg(sb, KERN_ERR,
@@ -1769,10 +1835,10 @@ set_qf_format:
#ifdef CONFIG_QUOTA
if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
- clear_opt(sbi->s_mount_opt, USRQUOTA);
+ clear_opt(sb, USRQUOTA);
if (test_opt(sb, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA])
- clear_opt(sbi->s_mount_opt, GRPQUOTA);
+ clear_opt(sb, GRPQUOTA);
if (test_opt(sb, GRPQUOTA) || test_opt(sb, USRQUOTA)) {
ext4_msg(sb, KERN_ERR, "old and new quota "
@@ -1842,12 +1908,12 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
ext4_commit_super(sb, 1);
if (test_opt(sb, DEBUG))
printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
- "bpg=%lu, ipg=%lu, mo=%04x]\n",
+ "bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n",
sb->s_blocksize,
sbi->s_groups_count,
EXT4_BLOCKS_PER_GROUP(sb),
EXT4_INODES_PER_GROUP(sb),
- sbi->s_mount_opt);
+ sbi->s_mount_opt, sbi->s_mount_opt2);
return res;
}
@@ -1877,14 +1943,13 @@ static int ext4_fill_flex_info(struct super_block *sb)
size = flex_group_count * sizeof(struct flex_groups);
sbi->s_flex_groups = kzalloc(size, GFP_KERNEL);
if (sbi->s_flex_groups == NULL) {
- sbi->s_flex_groups = vmalloc(size);
- if (sbi->s_flex_groups)
- memset(sbi->s_flex_groups, 0, size);
- }
- if (sbi->s_flex_groups == NULL) {
- ext4_msg(sb, KERN_ERR, "not enough memory for "
- "%u flex groups", flex_group_count);
- goto failed;
+ sbi->s_flex_groups = vzalloc(size);
+ if (sbi->s_flex_groups == NULL) {
+ ext4_msg(sb, KERN_ERR,
+ "not enough memory for %u flex groups",
+ flex_group_count);
+ goto failed;
+ }
}
for (i = 0; i < sbi->s_groups_count; i++) {
@@ -1942,7 +2007,8 @@ int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group,
}
/* Called at mount-time, super-block is locked */
-static int ext4_check_descriptors(struct super_block *sb)
+static int ext4_check_descriptors(struct super_block *sb,
+ ext4_group_t *first_not_zeroed)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
@@ -1951,7 +2017,7 @@ static int ext4_check_descriptors(struct super_block *sb)
ext4_fsblk_t inode_bitmap;
ext4_fsblk_t inode_table;
int flexbg_flag = 0;
- ext4_group_t i;
+ ext4_group_t i, grp = sbi->s_groups_count;
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
flexbg_flag = 1;
@@ -1967,6 +2033,10 @@ static int ext4_check_descriptors(struct super_block *sb)
last_block = first_block +
(EXT4_BLOCKS_PER_GROUP(sb) - 1);
+ if ((grp == sbi->s_groups_count) &&
+ !(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+ grp = i;
+
block_bitmap = ext4_block_bitmap(sb, gdp);
if (block_bitmap < first_block || block_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
@@ -2004,6 +2074,8 @@ static int ext4_check_descriptors(struct super_block *sb)
if (!flexbg_flag)
first_block += EXT4_BLOCKS_PER_GROUP(sb);
}
+ if (NULL != first_not_zeroed)
+ *first_not_zeroed = grp;
ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb));
sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb));
@@ -2376,6 +2448,7 @@ static struct ext4_attr ext4_attr_##_name = { \
#define EXT4_ATTR(name, mode, show, store) \
static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
+#define EXT4_INFO_ATTR(name) EXT4_ATTR(name, 0444, NULL, NULL)
#define EXT4_RO_ATTR(name) EXT4_ATTR(name, 0444, name##_show, NULL)
#define EXT4_RW_ATTR(name) EXT4_ATTR(name, 0644, name##_show, name##_store)
#define EXT4_RW_ATTR_SBI_UI(name, elname) \
@@ -2412,6 +2485,16 @@ static struct attribute *ext4_attrs[] = {
NULL,
};
+/* Features this copy of ext4 supports */
+EXT4_INFO_ATTR(lazy_itable_init);
+EXT4_INFO_ATTR(batched_discard);
+
+static struct attribute *ext4_feat_attrs[] = {
+ ATTR_LIST(lazy_itable_init),
+ ATTR_LIST(batched_discard),
+ NULL,
+};
+
static ssize_t ext4_attr_show(struct kobject *kobj,
struct attribute *attr, char *buf)
{
@@ -2440,7 +2523,6 @@ static void ext4_sb_release(struct kobject *kobj)
complete(&sbi->s_kobj_unregister);
}
-
static const struct sysfs_ops ext4_attr_ops = {
.show = ext4_attr_show,
.store = ext4_attr_store,
@@ -2452,6 +2534,17 @@ static struct kobj_type ext4_ktype = {
.release = ext4_sb_release,
};
+static void ext4_feat_release(struct kobject *kobj)
+{
+ complete(&ext4_feat->f_kobj_unregister);
+}
+
+static struct kobj_type ext4_feat_ktype = {
+ .default_attrs = ext4_feat_attrs,
+ .sysfs_ops = &ext4_attr_ops,
+ .release = ext4_feat_release,
+};
+
/*
* Check whether this filesystem can be mounted based on
* the features present and the RDONLY/RDWR mount requested.
@@ -2542,6 +2635,368 @@ static void print_daily_error_info(unsigned long arg)
mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); /* Once a day */
}
+static void ext4_lazyinode_timeout(unsigned long data)
+{
+ struct task_struct *p = (struct task_struct *)data;
+ wake_up_process(p);
+}
+
+/* Find next suitable group and run ext4_init_inode_table */
+static int ext4_run_li_request(struct ext4_li_request *elr)
+{
+ struct ext4_group_desc *gdp = NULL;
+ ext4_group_t group, ngroups;
+ struct super_block *sb;
+ unsigned long timeout = 0;
+ int ret = 0;
+
+ sb = elr->lr_super;
+ ngroups = EXT4_SB(sb)->s_groups_count;
+
+ for (group = elr->lr_next_group; group < ngroups; group++) {
+ gdp = ext4_get_group_desc(sb, group, NULL);
+ if (!gdp) {
+ ret = 1;
+ break;
+ }
+
+ if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+ break;
+ }
+
+ if (group == ngroups)
+ ret = 1;
+
+ if (!ret) {
+ timeout = jiffies;
+ ret = ext4_init_inode_table(sb, group,
+ elr->lr_timeout ? 0 : 1);
+ if (elr->lr_timeout == 0) {
+ timeout = jiffies - timeout;
+ if (elr->lr_sbi->s_li_wait_mult)
+ timeout *= elr->lr_sbi->s_li_wait_mult;
+ else
+ timeout *= 20;
+ elr->lr_timeout = timeout;
+ }
+ elr->lr_next_sched = jiffies + elr->lr_timeout;
+ elr->lr_next_group = group + 1;
+ }
+
+ return ret;
+}
+
+/*
+ * Remove lr_request from the list_request and free the
+ * request tructure. Should be called with li_list_mtx held
+ */
+static void ext4_remove_li_request(struct ext4_li_request *elr)
+{
+ struct ext4_sb_info *sbi;
+
+ if (!elr)
+ return;
+
+ sbi = elr->lr_sbi;
+
+ list_del(&elr->lr_request);
+ sbi->s_li_request = NULL;
+ kfree(elr);
+}
+
+static void ext4_unregister_li_request(struct super_block *sb)
+{
+ struct ext4_li_request *elr = EXT4_SB(sb)->s_li_request;
+
+ if (!ext4_li_info)
+ return;
+
+ mutex_lock(&ext4_li_info->li_list_mtx);
+ ext4_remove_li_request(elr);
+ mutex_unlock(&ext4_li_info->li_list_mtx);
+}
+
+/*
+ * This is the function where ext4lazyinit thread lives. It walks
+ * through the request list searching for next scheduled filesystem.
+ * When such a fs is found, run the lazy initialization request
+ * (ext4_rn_li_request) and keep track of the time spend in this
+ * function. Based on that time we compute next schedule time of
+ * the request. When walking through the list is complete, compute
+ * next waking time and put itself into sleep.
+ */
+static int ext4_lazyinit_thread(void *arg)
+{
+ struct ext4_lazy_init *eli = (struct ext4_lazy_init *)arg;
+ struct list_head *pos, *n;
+ struct ext4_li_request *elr;
+ unsigned long next_wakeup;
+ DEFINE_WAIT(wait);
+
+ BUG_ON(NULL == eli);
+
+ eli->li_timer.data = (unsigned long)current;
+ eli->li_timer.function = ext4_lazyinode_timeout;
+
+ eli->li_task = current;
+ wake_up(&eli->li_wait_task);
+
+cont_thread:
+ while (true) {
+ next_wakeup = MAX_JIFFY_OFFSET;
+
+ mutex_lock(&eli->li_list_mtx);
+ if (list_empty(&eli->li_request_list)) {
+ mutex_unlock(&eli->li_list_mtx);
+ goto exit_thread;
+ }
+
+ list_for_each_safe(pos, n, &eli->li_request_list) {
+ elr = list_entry(pos, struct ext4_li_request,
+ lr_request);
+
+ if (time_after_eq(jiffies, elr->lr_next_sched)) {
+ if (ext4_run_li_request(elr) != 0) {
+ /* error, remove the lazy_init job */
+ ext4_remove_li_request(elr);
+ continue;
+ }
+ }
+
+ if (time_before(elr->lr_next_sched, next_wakeup))
+ next_wakeup = elr->lr_next_sched;
+ }
+ mutex_unlock(&eli->li_list_mtx);
+
+ if (freezing(current))
+ refrigerator();
+
+ if ((time_after_eq(jiffies, next_wakeup)) ||
+ (MAX_JIFFY_OFFSET == next_wakeup)) {
+ cond_resched();
+ continue;
+ }
+
+ eli->li_timer.expires = next_wakeup;
+ add_timer(&eli->li_timer);
+ prepare_to_wait(&eli->li_wait_daemon, &wait,
+ TASK_INTERRUPTIBLE);
+ if (time_before(jiffies, next_wakeup))
+ schedule();
+ finish_wait(&eli->li_wait_daemon, &wait);
+ }
+
+exit_thread:
+ /*
+ * It looks like the request list is empty, but we need
+ * to check it under the li_list_mtx lock, to prevent any
+ * additions into it, and of course we should lock ext4_li_mtx
+ * to atomically free the list and ext4_li_info, because at
+ * this point another ext4 filesystem could be registering
+ * new one.
+ */
+ mutex_lock(&ext4_li_mtx);
+ mutex_lock(&eli->li_list_mtx);
+ if (!list_empty(&eli->li_request_list)) {
+ mutex_unlock(&eli->li_list_mtx);
+ mutex_unlock(&ext4_li_mtx);
+ goto cont_thread;
+ }
+ mutex_unlock(&eli->li_list_mtx);
+ del_timer_sync(&ext4_li_info->li_timer);
+ eli->li_task = NULL;
+ wake_up(&eli->li_wait_task);
+
+ kfree(ext4_li_info);
+ ext4_li_info = NULL;
+ mutex_unlock(&ext4_li_mtx);
+
+ return 0;
+}
+
+static void ext4_clear_request_list(void)
+{
+ struct list_head *pos, *n;
+ struct ext4_li_request *elr;
+
+ mutex_lock(&ext4_li_info->li_list_mtx);
+ list_for_each_safe(pos, n, &ext4_li_info->li_request_list) {
+ elr = list_entry(pos, struct ext4_li_request,
+ lr_request);
+ ext4_remove_li_request(elr);
+ }
+ mutex_unlock(&ext4_li_info->li_list_mtx);
+}
+
+static int ext4_run_lazyinit_thread(void)
+{
+ struct task_struct *t;
+
+ t = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit");
+ if (IS_ERR(t)) {
+ int err = PTR_ERR(t);
+ ext4_clear_request_list();
+ del_timer_sync(&ext4_li_info->li_timer);
+ kfree(ext4_li_info);
+ ext4_li_info = NULL;
+ printk(KERN_CRIT "EXT4: error %d creating inode table "
+ "initialization thread\n",
+ err);
+ return err;
+ }
+ ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING;
+
+ wait_event(ext4_li_info->li_wait_task, ext4_li_info->li_task != NULL);
+ return 0;
+}
+
+/*
+ * Check whether it make sense to run itable init. thread or not.
+ * If there is at least one uninitialized inode table, return
+ * corresponding group number, else the loop goes through all
+ * groups and return total number of groups.
+ */
+static ext4_group_t ext4_has_uninit_itable(struct super_block *sb)
+{
+ ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count;
+ struct ext4_group_desc *gdp = NULL;
+
+ for (group = 0; group < ngroups; group++) {
+ gdp = ext4_get_group_desc(sb, group, NULL);
+ if (!gdp)
+ continue;
+
+ if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
+ break;
+ }
+
+ return group;
+}
+
+static int ext4_li_info_new(void)
+{
+ struct ext4_lazy_init *eli = NULL;
+
+ eli = kzalloc(sizeof(*eli), GFP_KERNEL);
+ if (!eli)
+ return -ENOMEM;
+
+ eli->li_task = NULL;
+ INIT_LIST_HEAD(&eli->li_request_list);
+ mutex_init(&eli->li_list_mtx);
+
+ init_waitqueue_head(&eli->li_wait_daemon);
+ init_waitqueue_head(&eli->li_wait_task);
+ init_timer(&eli->li_timer);
+ eli->li_state |= EXT4_LAZYINIT_QUIT;
+
+ ext4_li_info = eli;
+
+ return 0;
+}
+
+static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
+ ext4_group_t start)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_li_request *elr;
+ unsigned long rnd;
+
+ elr = kzalloc(sizeof(*elr), GFP_KERNEL);
+ if (!elr)
+ return NULL;
+
+ elr->lr_super = sb;
+ elr->lr_sbi = sbi;
+ elr->lr_next_group = start;
+
+ /*
+ * Randomize first schedule time of the request to
+ * spread the inode table initialization requests
+ * better.
+ */
+ get_random_bytes(&rnd, sizeof(rnd));
+ elr->lr_next_sched = jiffies + (unsigned long)rnd %
+ (EXT4_DEF_LI_MAX_START_DELAY * HZ);
+
+ return elr;
+}
+
+static int ext4_register_li_request(struct super_block *sb,
+ ext4_group_t first_not_zeroed)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_li_request *elr;
+ ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+ int ret = 0;
+
+ if (sbi->s_li_request != NULL)
+ return 0;
+
+ if (first_not_zeroed == ngroups ||
+ (sb->s_flags & MS_RDONLY) ||
+ !test_opt(sb, INIT_INODE_TABLE)) {
+ sbi->s_li_request = NULL;
+ return 0;
+ }
+
+ if (first_not_zeroed == ngroups) {
+ sbi->s_li_request = NULL;
+ return 0;
+ }
+
+ elr = ext4_li_request_new(sb, first_not_zeroed);
+ if (!elr)
+ return -ENOMEM;
+
+ mutex_lock(&ext4_li_mtx);
+
+ if (NULL == ext4_li_info) {
+ ret = ext4_li_info_new();
+ if (ret)
+ goto out;
+ }
+
+ mutex_lock(&ext4_li_info->li_list_mtx);
+ list_add(&elr->lr_request, &ext4_li_info->li_request_list);
+ mutex_unlock(&ext4_li_info->li_list_mtx);
+
+ sbi->s_li_request = elr;
+
+ if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) {
+ ret = ext4_run_lazyinit_thread();
+ if (ret)
+ goto out;
+ }
+out:
+ mutex_unlock(&ext4_li_mtx);
+ if (ret)
+ kfree(elr);
+ return ret;
+}
+
+/*
+ * We do not need to lock anything since this is called on
+ * module unload.
+ */
+static void ext4_destroy_lazyinit_thread(void)
+{
+ /*
+ * If thread exited earlier
+ * there's nothing to be done.
+ */
+ if (!ext4_li_info)
+ return;
+
+ ext4_clear_request_list();
+
+ while (ext4_li_info->li_task) {
+ wake_up(&ext4_li_info->li_wait_daemon);
+ wait_event(ext4_li_info->li_wait_task,
+ ext4_li_info->li_task == NULL);
+ }
+}
+
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
__releases(kernel_lock)
__acquires(kernel_lock)
@@ -2567,6 +3022,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
__u64 blocks_count;
int err;
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
+ ext4_group_t first_not_zeroed;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
@@ -2588,8 +3044,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_sectors_written_start =
part_stat_read(sb->s_bdev->bd_part, sectors[1]);
- unlock_kernel();
-
/* Cleanup superblock name */
for (cp = sb->s_id; (cp = strchr(cp, '/'));)
*cp = '!';
@@ -2629,40 +3083,41 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
/* Set defaults before we parse the mount options */
def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
+ set_opt(sb, INIT_INODE_TABLE);
if (def_mount_opts & EXT4_DEFM_DEBUG)
- set_opt(sbi->s_mount_opt, DEBUG);
+ set_opt(sb, DEBUG);
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);
+ set_opt(sb, GRPID);
}
if (def_mount_opts & EXT4_DEFM_UID16)
- set_opt(sbi->s_mount_opt, NO_UID32);
+ set_opt(sb, NO_UID32);
#ifdef CONFIG_EXT4_FS_XATTR
if (def_mount_opts & EXT4_DEFM_XATTR_USER)
- set_opt(sbi->s_mount_opt, XATTR_USER);
+ set_opt(sb, XATTR_USER);
#endif
#ifdef CONFIG_EXT4_FS_POSIX_ACL
if (def_mount_opts & EXT4_DEFM_ACL)
- set_opt(sbi->s_mount_opt, POSIX_ACL);
+ set_opt(sb, POSIX_ACL);
#endif
if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
- set_opt(sbi->s_mount_opt, JOURNAL_DATA);
+ set_opt(sb, JOURNAL_DATA);
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
- set_opt(sbi->s_mount_opt, ORDERED_DATA);
+ set_opt(sb, ORDERED_DATA);
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_WBACK)
- set_opt(sbi->s_mount_opt, WRITEBACK_DATA);
+ set_opt(sb, WRITEBACK_DATA);
if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_PANIC)
- set_opt(sbi->s_mount_opt, ERRORS_PANIC);
+ set_opt(sb, ERRORS_PANIC);
else if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_CONTINUE)
- set_opt(sbi->s_mount_opt, ERRORS_CONT);
+ set_opt(sb, ERRORS_CONT);
else
- set_opt(sbi->s_mount_opt, ERRORS_RO);
+ set_opt(sb, ERRORS_RO);
if (def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY)
- set_opt(sbi->s_mount_opt, BLOCK_VALIDITY);
+ set_opt(sb, BLOCK_VALIDITY);
if (def_mount_opts & EXT4_DEFM_DISCARD)
- set_opt(sbi->s_mount_opt, DISCARD);
+ set_opt(sb, DISCARD);
sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
@@ -2671,7 +3126,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME;
if ((def_mount_opts & EXT4_DEFM_NOBARRIER) == 0)
- set_opt(sbi->s_mount_opt, BARRIER);
+ set_opt(sb, BARRIER);
/*
* enable delayed allocation by default
@@ -2679,7 +3134,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
*/
if (!IS_EXT3_SB(sb) &&
((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0))
- set_opt(sbi->s_mount_opt, DELALLOC);
+ set_opt(sb, DELALLOC);
if (!parse_options((char *) sbi->s_es->s_mount_opts, sb,
&journal_devnum, &journal_ioprio, NULL, 0)) {
@@ -2831,15 +3286,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
* Test whether we have more sectors than will fit in sector_t,
* and whether the max offset is addressable by the page cache.
*/
- if ((ext4_blocks_count(es) >
- (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) ||
- (ext4_blocks_count(es) >
- (pgoff_t)(~0ULL) >> (PAGE_CACHE_SHIFT - sb->s_blocksize_bits))) {
+ err = generic_check_addressable(sb->s_blocksize_bits,
+ ext4_blocks_count(es));
+ if (err) {
ext4_msg(sb, KERN_ERR, "filesystem"
" too large to mount safely on this system");
if (sizeof(sector_t) < 8)
ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled");
- ret = -EFBIG;
+ ret = err;
goto failed_mount;
}
@@ -2908,7 +3362,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount2;
}
}
- if (!ext4_check_descriptors(sb)) {
+ if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
goto failed_mount2;
}
@@ -2924,6 +3378,24 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);
+ err = percpu_counter_init(&sbi->s_freeblocks_counter,
+ ext4_count_free_blocks(sb));
+ if (!err) {
+ err = percpu_counter_init(&sbi->s_freeinodes_counter,
+ ext4_count_free_inodes(sb));
+ }
+ if (!err) {
+ err = percpu_counter_init(&sbi->s_dirs_counter,
+ ext4_count_dirs(sb));
+ }
+ if (!err) {
+ err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+ }
+ if (err) {
+ ext4_msg(sb, KERN_ERR, "insufficient memory");
+ goto failed_mount3;
+ }
+
sbi->s_stripe = ext4_get_stripe_size(sbi);
sbi->s_max_writeback_mb_bump = 128;
@@ -2965,8 +3437,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
"suppressed and not mounted read-only");
goto failed_mount_wq;
} else {
- clear_opt(sbi->s_mount_opt, DATA_FLAGS);
- set_opt(sbi->s_mount_opt, WRITEBACK_DATA);
+ clear_opt(sb, DATA_FLAGS);
+ set_opt(sb, WRITEBACK_DATA);
sbi->s_journal = NULL;
needs_recovery = 0;
goto no_journal;
@@ -3004,9 +3476,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
*/
if (jbd2_journal_check_available_features
(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE))
- set_opt(sbi->s_mount_opt, ORDERED_DATA);
+ set_opt(sb, ORDERED_DATA);
else
- set_opt(sbi->s_mount_opt, JOURNAL_DATA);
+ set_opt(sb, JOURNAL_DATA);
break;
case EXT4_MOUNT_ORDERED_DATA:
@@ -3022,22 +3494,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
-no_journal:
- err = percpu_counter_init(&sbi->s_freeblocks_counter,
- ext4_count_free_blocks(sb));
- if (!err)
- err = percpu_counter_init(&sbi->s_freeinodes_counter,
- ext4_count_free_inodes(sb));
- if (!err)
- err = percpu_counter_init(&sbi->s_dirs_counter,
- ext4_count_dirs(sb));
- if (!err)
- err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
- if (err) {
- ext4_msg(sb, KERN_ERR, "insufficient memory");
- goto failed_mount_wq;
- }
+ /*
+ * The journal may have updated the bg summary counts, so we
+ * need to update the global counters.
+ */
+ percpu_counter_set(&sbi->s_freeblocks_counter,
+ ext4_count_free_blocks(sb));
+ percpu_counter_set(&sbi->s_freeinodes_counter,
+ ext4_count_free_inodes(sb));
+ percpu_counter_set(&sbi->s_dirs_counter,
+ ext4_count_dirs(sb));
+ percpu_counter_set(&sbi->s_dirtyblocks_counter, 0);
+no_journal:
EXT4_SB(sb)->dio_unwritten_wq = create_workqueue("ext4-dio-unwritten");
if (!EXT4_SB(sb)->dio_unwritten_wq) {
printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n");
@@ -3099,18 +3568,18 @@ no_journal:
(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) {
ext4_msg(sb, KERN_WARNING, "Ignoring delalloc option - "
"requested data journaling mode");
- clear_opt(sbi->s_mount_opt, DELALLOC);
+ clear_opt(sb, 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);
+ clear_opt(sb, 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);
+ clear_opt(sb, DIOREAD_NOLOCK);
}
}
@@ -3129,6 +3598,10 @@ no_journal:
goto failed_mount4;
}
+ err = ext4_register_li_request(sb, first_not_zeroed);
+ if (err)
+ goto failed_mount4;
+
sbi->s_kobj.kset = ext4_kset;
init_completion(&sbi->s_kobj_unregister);
err = kobject_init_and_add(&sbi->s_kobj, &ext4_ktype, NULL,
@@ -3166,7 +3639,6 @@ no_journal:
if (es->s_error_count)
mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
- lock_kernel();
kfree(orig_data);
return 0;
@@ -3184,10 +3656,6 @@ failed_mount_wq:
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
}
- percpu_counter_destroy(&sbi->s_freeblocks_counter);
- percpu_counter_destroy(&sbi->s_freeinodes_counter);
- percpu_counter_destroy(&sbi->s_dirs_counter);
- percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
failed_mount3:
if (sbi->s_flex_groups) {
if (is_vmalloc_addr(sbi->s_flex_groups))
@@ -3195,6 +3663,10 @@ failed_mount3:
else
kfree(sbi->s_flex_groups);
}
+ percpu_counter_destroy(&sbi->s_freeblocks_counter);
+ percpu_counter_destroy(&sbi->s_freeinodes_counter);
+ percpu_counter_destroy(&sbi->s_dirs_counter);
+ percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
@@ -3213,7 +3685,6 @@ out_fail:
sb->s_fs_info = NULL;
kfree(sbi->s_blockgroup_lock);
kfree(sbi);
- lock_kernel();
out_free_orig:
kfree(orig_data);
return ret;
@@ -3306,13 +3777,6 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
if (bdev == NULL)
return NULL;
- if (bd_claim(bdev, sb)) {
- ext4_msg(sb, KERN_ERR,
- "failed to claim external journal device");
- blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
- return NULL;
- }
-
blocksize = sb->s_blocksize;
hblock = bdev_logical_block_size(bdev);
if (blocksize < hblock) {
@@ -3470,7 +3934,7 @@ static int ext4_load_journal(struct super_block *sb,
EXT4_SB(sb)->s_journal = journal;
ext4_clear_journal_err(sb, es);
- if (journal_devnum &&
+ if (!really_read_only && journal_devnum &&
journal_devnum != le32_to_cpu(es->s_journal_dev)) {
es->s_journal_dev = cpu_to_le32(journal_devnum);
@@ -3524,9 +3988,10 @@ static int ext4_commit_super(struct super_block *sb, int sync)
es->s_kbytes_written =
cpu_to_le64(EXT4_SB(sb)->s_kbytes_written);
ext4_free_blocks_count_set(es, percpu_counter_sum_positive(
- &EXT4_SB(sb)->s_freeblocks_counter));
- es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive(
- &EXT4_SB(sb)->s_freeinodes_counter));
+ &EXT4_SB(sb)->s_freeblocks_counter));
+ es->s_free_inodes_count =
+ cpu_to_le32(percpu_counter_sum_positive(
+ &EXT4_SB(sb)->s_freeinodes_counter));
sb->s_dirt = 0;
BUFFER_TRACE(sbh, "marking dirty");
mark_buffer_dirty(sbh);
@@ -3706,6 +4171,22 @@ static int ext4_unfreeze(struct super_block *sb)
return 0;
}
+/*
+ * Structure to save mount options for ext4_remount's benefit
+ */
+struct ext4_mount_options {
+ unsigned long s_mount_opt;
+ unsigned long s_mount_opt2;
+ uid_t s_resuid;
+ gid_t s_resgid;
+ unsigned long s_commit_interval;
+ u32 s_min_batch_time, s_max_batch_time;
+#ifdef CONFIG_QUOTA
+ int s_jquota_fmt;
+ char *s_qf_names[MAXQUOTAS];
+#endif
+};
+
static int ext4_remount(struct super_block *sb, int *flags, char *data)
{
struct ext4_super_block *es;
@@ -3722,12 +4203,11 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
#endif
char *orig_data = kstrdup(data, GFP_KERNEL);
- lock_kernel();
-
/* Store the original options */
lock_super(sb);
old_sb_flags = sb->s_flags;
old_opts.s_mount_opt = sbi->s_mount_opt;
+ old_opts.s_mount_opt2 = sbi->s_mount_opt2;
old_opts.s_resuid = sbi->s_resuid;
old_opts.s_resgid = sbi->s_resgid;
old_opts.s_commit_interval = sbi->s_commit_interval;
@@ -3846,6 +4326,19 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
enable_quota = 1;
}
}
+
+ /*
+ * Reinitialize lazy itable initialization thread based on
+ * current settings
+ */
+ if ((sb->s_flags & MS_RDONLY) || !test_opt(sb, INIT_INODE_TABLE))
+ ext4_unregister_li_request(sb);
+ else {
+ ext4_group_t first_not_zeroed;
+ first_not_zeroed = ext4_has_uninit_itable(sb);
+ ext4_register_li_request(sb, first_not_zeroed);
+ }
+
ext4_setup_system_zone(sb);
if (sbi->s_journal == NULL)
ext4_commit_super(sb, 1);
@@ -3858,7 +4351,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
kfree(old_opts.s_qf_names[i]);
#endif
unlock_super(sb);
- unlock_kernel();
if (enable_quota)
dquot_resume(sb, -1);
@@ -3869,6 +4361,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
restore_opts:
sb->s_flags = old_sb_flags;
sbi->s_mount_opt = old_opts.s_mount_opt;
+ sbi->s_mount_opt2 = old_opts.s_mount_opt2;
sbi->s_resuid = old_opts.s_resuid;
sbi->s_resgid = old_opts.s_resgid;
sbi->s_commit_interval = old_opts.s_commit_interval;
@@ -3884,7 +4377,6 @@ restore_opts:
}
#endif
unlock_super(sb);
- unlock_kernel();
kfree(orig_data);
return err;
}
@@ -4066,27 +4558,20 @@ static int ext4_quota_on_mount(struct super_block *sb, int type)
* Standard function to be called on quota_on
*/
static int ext4_quota_on(struct super_block *sb, int type, int format_id,
- char *name)
+ struct path *path)
{
int err;
- struct path path;
if (!test_opt(sb, QUOTA))
return -EINVAL;
- err = kern_path(name, LOOKUP_FOLLOW, &path);
- if (err)
- return err;
-
/* Quotafile not on the same filesystem? */
- if (path.mnt->mnt_sb != sb) {
- path_put(&path);
+ if (path->mnt->mnt_sb != sb)
return -EXDEV;
- }
/* Journaling quota? */
if (EXT4_SB(sb)->s_qf_names[type]) {
/* Quotafile not in fs root? */
- if (path.dentry->d_parent != sb->s_root)
+ if (path->dentry->d_parent != sb->s_root)
ext4_msg(sb, KERN_WARNING,
"Quota file not on filesystem root. "
"Journaled quota will not work");
@@ -4097,7 +4582,7 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
* all updates to the file when we bypass pagecache...
*/
if (EXT4_SB(sb)->s_journal &&
- ext4_should_journal_data(path.dentry->d_inode)) {
+ ext4_should_journal_data(path->dentry->d_inode)) {
/*
* We don't need to lock updates but journal_flush() could
* otherwise be livelocked...
@@ -4105,25 +4590,19 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
- if (err) {
- path_put(&path);
+ if (err)
return err;
- }
}
- err = dquot_quota_on_path(sb, type, format_id, &path);
- path_put(&path);
- return err;
+ return dquot_quota_on(sb, type, format_id, path);
}
static int ext4_quota_off(struct super_block *sb, int type)
{
- /* Force all delayed allocation blocks to be allocated */
- if (test_opt(sb, DELALLOC)) {
- down_read(&sb->s_umount);
+ /* Force all delayed allocation blocks to be allocated.
+ * Caller already holds s_umount sem */
+ if (test_opt(sb, DELALLOC))
sync_filesystem(sb);
- up_read(&sb->s_umount);
- }
return dquot_quota_off(sb, type);
}
@@ -4229,17 +4708,17 @@ out:
#endif
-static int ext4_get_sb(struct file_system_type *fs_type, int flags,
- const char *dev_name, void *data, struct vfsmount *mnt)
+static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *data)
{
- return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt);
+ return mount_bdev(fs_type, flags, dev_name, data, ext4_fill_super);
}
#if !defined(CONFIG_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,
+ .mount = ext4_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
@@ -4284,28 +4763,58 @@ static inline void unregister_as_ext3(void) { }
static struct file_system_type ext4_fs_type = {
.owner = THIS_MODULE,
.name = "ext4",
- .get_sb = ext4_get_sb,
+ .mount = ext4_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
-static int __init init_ext4_fs(void)
+int __init ext4_init_feat_adverts(void)
+{
+ struct ext4_features *ef;
+ int ret = -ENOMEM;
+
+ ef = kzalloc(sizeof(struct ext4_features), GFP_KERNEL);
+ if (!ef)
+ goto out;
+
+ ef->f_kobj.kset = ext4_kset;
+ init_completion(&ef->f_kobj_unregister);
+ ret = kobject_init_and_add(&ef->f_kobj, &ext4_feat_ktype, NULL,
+ "features");
+ if (ret) {
+ kfree(ef);
+ goto out;
+ }
+
+ ext4_feat = ef;
+ ret = 0;
+out:
+ return ret;
+}
+
+static int __init ext4_init_fs(void)
{
int err;
ext4_check_flag_values();
- err = init_ext4_system_zone();
+ err = ext4_init_pageio();
if (err)
return err;
+ err = ext4_init_system_zone();
+ if (err)
+ goto out5;
ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
if (!ext4_kset)
goto out4;
ext4_proc_root = proc_mkdir("fs/ext4", NULL);
- err = init_ext4_mballoc();
+
+ err = ext4_init_feat_adverts();
+
+ err = ext4_init_mballoc();
if (err)
goto out3;
- err = init_ext4_xattr();
+ err = ext4_init_xattr();
if (err)
goto out2;
err = init_inodecache();
@@ -4316,38 +4825,46 @@ static int __init init_ext4_fs(void)
err = register_filesystem(&ext4_fs_type);
if (err)
goto out;
+
+ ext4_li_info = NULL;
+ mutex_init(&ext4_li_mtx);
return 0;
out:
unregister_as_ext2();
unregister_as_ext3();
destroy_inodecache();
out1:
- exit_ext4_xattr();
+ ext4_exit_xattr();
out2:
- exit_ext4_mballoc();
+ ext4_exit_mballoc();
out3:
+ kfree(ext4_feat);
remove_proc_entry("fs/ext4", NULL);
kset_unregister(ext4_kset);
out4:
- exit_ext4_system_zone();
+ ext4_exit_system_zone();
+out5:
+ ext4_exit_pageio();
return err;
}
-static void __exit exit_ext4_fs(void)
+static void __exit ext4_exit_fs(void)
{
+ ext4_destroy_lazyinit_thread();
unregister_as_ext2();
unregister_as_ext3();
unregister_filesystem(&ext4_fs_type);
destroy_inodecache();
- exit_ext4_xattr();
- exit_ext4_mballoc();
+ ext4_exit_xattr();
+ ext4_exit_mballoc();
remove_proc_entry("fs/ext4", NULL);
kset_unregister(ext4_kset);
- exit_ext4_system_zone();
+ ext4_exit_system_zone();
+ ext4_exit_pageio();
}
MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
MODULE_DESCRIPTION("Fourth Extended Filesystem");
MODULE_LICENSE("GPL");
-module_init(init_ext4_fs)
-module_exit(exit_ext4_fs)
+module_init(ext4_init_fs)
+module_exit(ext4_exit_fs)
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 3a8cd8dff1a..fc32176eee3 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -427,23 +427,23 @@ cleanup:
static int
ext4_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
- int i_error, b_error;
+ int ret, ret2;
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 {
- if (buffer) {
- buffer += i_error;
- buffer_size -= i_error;
- }
- b_error = ext4_xattr_block_list(dentry, buffer, buffer_size);
- if (b_error < 0)
- i_error = 0;
+ ret = ret2 = ext4_xattr_ibody_list(dentry, buffer, buffer_size);
+ if (ret < 0)
+ goto errout;
+ if (buffer) {
+ buffer += ret;
+ buffer_size -= ret;
}
+ ret = ext4_xattr_block_list(dentry, buffer, buffer_size);
+ if (ret < 0)
+ goto errout;
+ ret += ret2;
+errout:
up_read(&EXT4_I(dentry->d_inode)->xattr_sem);
- return i_error + b_error;
+ return ret;
}
/*
@@ -947,7 +947,7 @@ ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
/*
* ext4_xattr_set_handle()
*
- * Create, replace or remove an extended attribute for this inode. Buffer
+ * Create, replace or remove an extended attribute for this inode. Value
* is NULL to remove an existing extended attribute, and non-NULL to
* either replace an existing extended attribute, or create a new extended
* attribute. The flags XATTR_REPLACE and XATTR_CREATE
@@ -1588,7 +1588,7 @@ static void ext4_xattr_rehash(struct ext4_xattr_header *header,
#undef BLOCK_HASH_SHIFT
int __init
-init_ext4_xattr(void)
+ext4_init_xattr(void)
{
ext4_xattr_cache = mb_cache_create("ext4_xattr", 6);
if (!ext4_xattr_cache)
@@ -1597,7 +1597,7 @@ init_ext4_xattr(void)
}
void
-exit_ext4_xattr(void)
+ext4_exit_xattr(void)
{
if (ext4_xattr_cache)
mb_cache_destroy(ext4_xattr_cache);
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index 518e96e4390..1ef16520b95 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -83,8 +83,8 @@ extern void ext4_xattr_put_super(struct super_block *);
extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
struct ext4_inode *raw_inode, handle_t *handle);
-extern int init_ext4_xattr(void);
-extern void exit_ext4_xattr(void);
+extern int __init ext4_init_xattr(void);
+extern void ext4_exit_xattr(void);
extern const struct xattr_handler *ext4_xattr_handlers[];
@@ -121,14 +121,14 @@ ext4_xattr_put_super(struct super_block *sb)
{
}
-static inline int
-init_ext4_xattr(void)
+static __init inline int
+ext4_init_xattr(void)
{
return 0;
}
static inline void
-exit_ext4_xattr(void)
+ext4_exit_xattr(void)
{
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-26 08:56:06 +0000