summaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/balloc.c68
-rw-r--r--fs/ext4/dir.c3
-rw-r--r--fs/ext4/ext4.h76
-rw-r--r--fs/ext4/ext4_extents.h22
-rw-r--r--fs/ext4/ext4_jbd2.c7
-rw-r--r--fs/ext4/ext4_jbd2.h4
-rw-r--r--fs/ext4/extents.c345
-rw-r--r--fs/ext4/extents_status.c12
-rw-r--r--fs/ext4/file.c155
-rw-r--r--fs/ext4/inline.c15
-rw-r--r--fs/ext4/inode.c143
-rw-r--r--fs/ext4/mballoc.c40
-rw-r--r--fs/ext4/migrate.c2
-rw-r--r--fs/ext4/mmp.c4
-rw-r--r--fs/ext4/move_extent.c39
-rw-r--r--fs/ext4/namei.c131
-rw-r--r--fs/ext4/page-io.c37
-rw-r--r--fs/ext4/resize.c15
-rw-r--r--fs/ext4/super.c71
-rw-r--r--fs/ext4/xattr.c32
20 files changed, 673 insertions, 548 deletions
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 6ea7b1436bbc..0762d143e252 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -83,9 +83,9 @@ static inline int ext4_block_in_group(struct super_block *sb,
/* Return the number of clusters used for file system metadata; this
* represents the overhead needed by the file system.
*/
-unsigned ext4_num_overhead_clusters(struct super_block *sb,
- ext4_group_t block_group,
- struct ext4_group_desc *gdp)
+static unsigned ext4_num_overhead_clusters(struct super_block *sb,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp)
{
unsigned num_clusters;
int block_cluster = -1, inode_cluster = -1, itbl_cluster = -1, i, c;
@@ -176,9 +176,10 @@ static unsigned int num_clusters_in_group(struct super_block *sb,
}
/* Initializes an uninitialized block bitmap */
-void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
- ext4_group_t block_group,
- struct ext4_group_desc *gdp)
+static void ext4_init_block_bitmap(struct super_block *sb,
+ struct buffer_head *bh,
+ ext4_group_t block_group,
+ struct ext4_group_desc *gdp)
{
unsigned int bit, bit_max;
struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -307,6 +308,7 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
ext4_group_t block_group,
struct buffer_head *bh)
{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_grpblk_t offset;
ext4_grpblk_t next_zero_bit;
ext4_fsblk_t blk;
@@ -326,14 +328,14 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
/* check whether block bitmap block number is set */
blk = ext4_block_bitmap(sb, desc);
offset = blk - group_first_block;
- if (!ext4_test_bit(offset, bh->b_data))
+ if (!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
/* bad block bitmap */
return blk;
/* check whether the inode bitmap block number is set */
blk = ext4_inode_bitmap(sb, desc);
offset = blk - group_first_block;
- if (!ext4_test_bit(offset, bh->b_data))
+ if (!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
/* bad block bitmap */
return blk;
@@ -341,18 +343,19 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
blk = ext4_inode_table(sb, desc);
offset = blk - group_first_block;
next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
- offset + EXT4_SB(sb)->s_itb_per_group,
- offset);
- if (next_zero_bit < offset + EXT4_SB(sb)->s_itb_per_group)
+ EXT4_B2C(sbi, offset + EXT4_SB(sb)->s_itb_per_group),
+ EXT4_B2C(sbi, offset));
+ if (next_zero_bit <
+ EXT4_B2C(sbi, offset + EXT4_SB(sb)->s_itb_per_group))
/* bad bitmap for inode tables */
return blk;
return 0;
}
-void ext4_validate_block_bitmap(struct super_block *sb,
- struct ext4_group_desc *desc,
- ext4_group_t block_group,
- struct buffer_head *bh)
+static void ext4_validate_block_bitmap(struct super_block *sb,
+ struct ext4_group_desc *desc,
+ ext4_group_t block_group,
+ struct buffer_head *bh)
{
ext4_fsblk_t blk;
struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
@@ -667,7 +670,7 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb)
continue;
x = ext4_count_free(bitmap_bh->b_data,
- EXT4_BLOCKS_PER_GROUP(sb) / 8);
+ EXT4_CLUSTERS_PER_GROUP(sb) / 8);
printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n",
i, ext4_free_group_clusters(sb, gdp), x);
bitmap_count += x;
@@ -708,16 +711,6 @@ static inline int test_root(ext4_group_t a, int b)
}
}
-static int ext4_group_sparse(ext4_group_t group)
-{
- if (group <= 1)
- return 1;
- if (!(group & 1))
- return 0;
- return (test_root(group, 7) || test_root(group, 5) ||
- test_root(group, 3));
-}
-
/**
* ext4_bg_has_super - number of blocks used by the superblock in group
* @sb: superblock for filesystem
@@ -728,11 +721,26 @@ static int ext4_group_sparse(ext4_group_t group)
*/
int ext4_bg_has_super(struct super_block *sb, ext4_group_t group)
{
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
- !ext4_group_sparse(group))
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+ if (group == 0)
+ return 1;
+ if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_SPARSE_SUPER2)) {
+ if (group == le32_to_cpu(es->s_backup_bgs[0]) ||
+ group == le32_to_cpu(es->s_backup_bgs[1]))
+ return 1;
return 0;
- return 1;
+ }
+ if ((group <= 1) || !EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER))
+ return 1;
+ if (!(group & 1))
+ return 0;
+ if (test_root(group, 3) || (test_root(group, 5)) ||
+ test_root(group, 7))
+ return 1;
+
+ return 0;
}
static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb,
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index d638c57e996e..ef1bed66c14f 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -105,7 +105,7 @@ int __ext4_check_dir_entry(const char *function, unsigned int line,
static int ext4_readdir(struct file *file, struct dir_context *ctx)
{
unsigned int offset;
- int i, stored;
+ int i;
struct ext4_dir_entry_2 *de;
int err;
struct inode *inode = file_inode(file);
@@ -133,7 +133,6 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
return ret;
}
- stored = 0;
offset = ctx->pos & (sb->s_blocksize - 1);
while (ctx->pos < inode->i_size) {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index f1c65dc7cc0a..1479e2ae00d2 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -158,7 +158,6 @@ struct ext4_allocation_request {
#define EXT4_MAP_MAPPED (1 << BH_Mapped)
#define EXT4_MAP_UNWRITTEN (1 << BH_Unwritten)
#define EXT4_MAP_BOUNDARY (1 << BH_Boundary)
-#define EXT4_MAP_UNINIT (1 << BH_Uninit)
/* Sometimes (in the bigalloc case, from ext4_da_get_block_prep) the caller of
* ext4_map_blocks wants to know whether or not the underlying cluster has
* already been accounted for. EXT4_MAP_FROM_CLUSTER conveys to the caller that
@@ -169,7 +168,7 @@ struct ext4_allocation_request {
#define EXT4_MAP_FROM_CLUSTER (1 << BH_AllocFromCluster)
#define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
- EXT4_MAP_UNINIT | EXT4_MAP_FROM_CLUSTER)
+ EXT4_MAP_FROM_CLUSTER)
struct ext4_map_blocks {
ext4_fsblk_t m_pblk;
@@ -184,7 +183,7 @@ struct ext4_map_blocks {
#define EXT4_IO_END_UNWRITTEN 0x0001
/*
- * For converting uninitialized extents on a work queue. 'handle' is used for
+ * For converting unwritten extents on a work queue. 'handle' is used for
* buffered writeback.
*/
typedef struct ext4_io_end {
@@ -537,26 +536,26 @@ enum {
/*
* Flags used by ext4_map_blocks()
*/
- /* Allocate any needed blocks and/or convert an unitialized
+ /* Allocate any needed blocks and/or convert an unwritten
extent to be an initialized ext4 */
#define EXT4_GET_BLOCKS_CREATE 0x0001
- /* Request the creation of an unitialized extent */
-#define EXT4_GET_BLOCKS_UNINIT_EXT 0x0002
-#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT (EXT4_GET_BLOCKS_UNINIT_EXT|\
+ /* Request the creation of an unwritten extent */
+#define EXT4_GET_BLOCKS_UNWRIT_EXT 0x0002
+#define EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT (EXT4_GET_BLOCKS_UNWRIT_EXT|\
EXT4_GET_BLOCKS_CREATE)
/* Caller is from the delayed allocation writeout path
* finally doing the actual allocation of delayed blocks */
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004
/* caller is from the direct IO path, request to creation of an
- unitialized extents if not allocated, split the uninitialized
+ unwritten extents if not allocated, split the unwritten
extent if blocks has been preallocated already*/
#define EXT4_GET_BLOCKS_PRE_IO 0x0008
#define EXT4_GET_BLOCKS_CONVERT 0x0010
#define EXT4_GET_BLOCKS_IO_CREATE_EXT (EXT4_GET_BLOCKS_PRE_IO|\
- EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
+ EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
/* Convert extent to initialized after IO complete */
#define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\
- EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
+ EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
/* Eventual metadata allocation (due to growing extent tree)
* should not fail, so try to use reserved blocks for that.*/
#define EXT4_GET_BLOCKS_METADATA_NOFAIL 0x0020
@@ -876,6 +875,8 @@ struct ext4_inode_info {
struct inode vfs_inode;
struct jbd2_inode *jinode;
+ spinlock_t i_raw_lock; /* protects updates to the raw inode */
+
/*
* File creation time. Its function is same as that of
* struct timespec i_{a,c,m}time in the generic inode.
@@ -1159,7 +1160,8 @@ struct ext4_super_block {
__le32 s_usr_quota_inum; /* inode for tracking user quota */
__le32 s_grp_quota_inum; /* inode for tracking group quota */
__le32 s_overhead_clusters; /* overhead blocks/clusters in fs */
- __le32 s_reserved[108]; /* Padding to the end of the block */
+ __le32 s_backup_bgs[2]; /* groups with sparse_super2 SBs */
+ __le32 s_reserved[106]; /* Padding to the end of the block */
__le32 s_checksum; /* crc32c(superblock) */
};
@@ -1505,6 +1507,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
#define EXT4_FEATURE_COMPAT_EXT_ATTR 0x0008
#define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010
#define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020
+#define EXT4_FEATURE_COMPAT_SPARSE_SUPER2 0x0200
#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001
#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002
@@ -1953,10 +1956,6 @@ extern void ext4_get_group_no_and_offset(struct super_block *sb,
extern ext4_group_t ext4_get_group_number(struct super_block *sb,
ext4_fsblk_t block);
-extern void ext4_validate_block_bitmap(struct super_block *sb,
- struct ext4_group_desc *desc,
- ext4_group_t block_group,
- struct buffer_head *bh);
extern unsigned int ext4_block_group(struct super_block *sb,
ext4_fsblk_t blocknr);
extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb,
@@ -1985,16 +1984,9 @@ extern int ext4_wait_block_bitmap(struct super_block *sb,
struct buffer_head *bh);
extern struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
ext4_group_t block_group);
-extern void ext4_init_block_bitmap(struct super_block *sb,
- struct buffer_head *bh,
- ext4_group_t group,
- struct ext4_group_desc *desc);
extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
ext4_group_t block_group,
struct ext4_group_desc *gdp);
-extern unsigned ext4_num_overhead_clusters(struct super_block *sb,
- ext4_group_t block_group,
- struct ext4_group_desc *gdp);
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
/* dir.c */
@@ -2137,8 +2129,6 @@ 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_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_zero_partial_blocks(handle_t *handle, struct inode *inode,
loff_t lstart, loff_t lend);
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
@@ -2198,8 +2188,6 @@ extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count);
/* super.c */
extern int ext4_calculate_overhead(struct super_block *sb);
-extern int ext4_superblock_csum_verify(struct super_block *sb,
- struct ext4_super_block *es);
extern void ext4_superblock_csum_set(struct super_block *sb);
extern void *ext4_kvmalloc(size_t size, gfp_t flags);
extern void *ext4_kvzalloc(size_t size, gfp_t flags);
@@ -2466,23 +2454,6 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
up_write(&EXT4_I(inode)->i_data_sem);
}
-/*
- * Update i_disksize after writeback has been started. Races with truncate
- * are avoided by checking i_size under i_data_sem.
- */
-static inline void ext4_wb_update_i_disksize(struct inode *inode, loff_t newsize)
-{
- loff_t i_size;
-
- down_write(&EXT4_I(inode)->i_data_sem);
- i_size = i_size_read(inode);
- if (newsize > i_size)
- newsize = i_size;
- if (newsize > EXT4_I(inode)->i_disksize)
- EXT4_I(inode)->i_disksize = newsize;
- up_write(&EXT4_I(inode)->i_data_sem);
-}
-
struct ext4_group_info {
unsigned long bb_state;
struct rb_root bb_free_root;
@@ -2588,19 +2559,11 @@ extern const struct file_operations ext4_dir_operations;
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);
-extern void ext4_unwritten_wait(struct inode *inode);
/* inline.c */
extern int ext4_has_inline_data(struct inode *inode);
-extern int ext4_get_inline_size(struct inode *inode);
extern int ext4_get_max_inline_size(struct inode *inode);
extern int ext4_find_inline_data_nolock(struct inode *inode);
-extern void ext4_write_inline_data(struct inode *inode,
- struct ext4_iloc *iloc,
- void *buffer, loff_t pos,
- unsigned int len);
-extern int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
- unsigned int len);
extern int ext4_init_inline_data(handle_t *handle, struct inode *inode,
unsigned int len);
extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);
@@ -2788,23 +2751,20 @@ 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);
+ struct writeback_control *wbc,
+ bool keep_towrite);
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
-extern void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp);
-extern int ext4_mmp_csum_verify(struct super_block *sb,
- struct mmp_struct *mmp);
/*
* Note that these flags will never ever appear in a buffer_head's state flag.
* See EXT4_MAP_... to see where this is used.
*/
enum ext4_state_bits {
- BH_Uninit /* blocks are allocated but uninitialized on disk */
- = BH_JBDPrivateStart,
- BH_AllocFromCluster, /* allocated blocks were part of already
+ BH_AllocFromCluster /* allocated blocks were part of already
* allocated cluster. */
+ = BH_JBDPrivateStart
};
/*
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 5074fe23f19e..a867f5ca9991 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -137,21 +137,21 @@ struct ext4_ext_path {
* EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an
* initialized extent. This is 2^15 and not (2^16 - 1), since we use the
* MSB of ee_len field in the extent datastructure to signify if this
- * particular extent is an initialized extent or an uninitialized (i.e.
+ * particular extent is an initialized extent or an unwritten (i.e.
* preallocated).
- * EXT_UNINIT_MAX_LEN is the maximum number of blocks we can have in an
- * uninitialized extent.
+ * EXT_UNWRITTEN_MAX_LEN is the maximum number of blocks we can have in an
+ * unwritten extent.
* If ee_len is <= 0x8000, it is an initialized extent. Otherwise, it is an
- * uninitialized one. In other words, if MSB of ee_len is set, it is an
- * uninitialized extent with only one special scenario when ee_len = 0x8000.
- * In this case we can not have an uninitialized extent of zero length and
+ * unwritten one. In other words, if MSB of ee_len is set, it is an
+ * unwritten extent with only one special scenario when ee_len = 0x8000.
+ * In this case we can not have an unwritten extent of zero length and
* thus we make it as a special case of initialized extent with 0x8000 length.
* This way we get better extent-to-group alignment for initialized extents.
* Hence, the maximum number of blocks we can have in an *initialized*
- * extent is 2^15 (32768) and in an *uninitialized* extent is 2^15-1 (32767).
+ * extent is 2^15 (32768) and in an *unwritten* extent is 2^15-1 (32767).
*/
#define EXT_INIT_MAX_LEN (1UL << 15)
-#define EXT_UNINIT_MAX_LEN (EXT_INIT_MAX_LEN - 1)
+#define EXT_UNWRITTEN_MAX_LEN (EXT_INIT_MAX_LEN - 1)
#define EXT_FIRST_EXTENT(__hdr__) \
@@ -187,14 +187,14 @@ static inline unsigned short ext_depth(struct inode *inode)
return le16_to_cpu(ext_inode_hdr(inode)->eh_depth);
}
-static inline void ext4_ext_mark_uninitialized(struct ext4_extent *ext)
+static inline void ext4_ext_mark_unwritten(struct ext4_extent *ext)
{
- /* We can not have an uninitialized extent of zero length! */
+ /* We can not have an unwritten extent of zero length! */
BUG_ON((le16_to_cpu(ext->ee_len) & ~EXT_INIT_MAX_LEN) == 0);
ext->ee_len |= cpu_to_le16(EXT_INIT_MAX_LEN);
}
-static inline int ext4_ext_is_uninitialized(struct ext4_extent *ext)
+static inline int ext4_ext_is_unwritten(struct ext4_extent *ext)
{
/* Extent with ee_len of 0x8000 is treated as an initialized extent */
return (le16_to_cpu(ext->ee_len) > EXT_INIT_MAX_LEN);
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index c3fb607413ed..0074e0d23d6e 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -122,9 +122,10 @@ handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
return handle;
}
-void ext4_journal_abort_handle(const char *caller, unsigned int line,
- const char *err_fn, struct buffer_head *bh,
- handle_t *handle, int err)
+static void ext4_journal_abort_handle(const char *caller, unsigned int line,
+ const char *err_fn,
+ struct buffer_head *bh,
+ handle_t *handle, int err)
{
char nbuf[16];
const char *errstr = ext4_decode_error(NULL, err, nbuf);
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 81cfefa9dc0c..17c00ff202f2 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -231,10 +231,6 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode);
/*
* Wrapper functions with which ext4 calls into JBD.
*/
-void ext4_journal_abort_handle(const char *caller, unsigned int line,
- const char *err_fn,
- struct buffer_head *bh, handle_t *handle, int err);
-
int __ext4_journal_get_write_access(const char *where, unsigned int line,
handle_t *handle, struct buffer_head *bh);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 82df3ce9874a..4da228a0e6d0 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -50,8 +50,8 @@
*/
#define EXT4_EXT_MAY_ZEROOUT 0x1 /* safe to zeroout if split fails \
due to ENOSPC */
-#define EXT4_EXT_MARK_UNINIT1 0x2 /* mark first half uninitialized */
-#define EXT4_EXT_MARK_UNINIT2 0x4 /* mark second half uninitialized */
+#define EXT4_EXT_MARK_UNWRIT1 0x2 /* mark first half unwritten */
+#define EXT4_EXT_MARK_UNWRIT2 0x4 /* mark second half unwritten */
#define EXT4_EXT_DATA_VALID1 0x8 /* first half contains valid data */
#define EXT4_EXT_DATA_VALID2 0x10 /* second half contains valid data */
@@ -143,6 +143,7 @@ static int ext4_ext_get_access(handle_t *handle, struct inode *inode,
{
if (path->p_bh) {
/* path points to block */
+ BUFFER_TRACE(path->p_bh, "get_write_access");
return ext4_journal_get_write_access(handle, path->p_bh);
}
/* path points to leaf/index in inode body */
@@ -524,7 +525,7 @@ __read_extent_tree_block(const char *function, unsigned int line,
lblk - prev, ~0,
EXTENT_STATUS_HOLE);
- if (ext4_ext_is_uninitialized(ex))
+ if (ext4_ext_is_unwritten(ex))
status = EXTENT_STATUS_UNWRITTEN;
ext4_es_cache_extent(inode, lblk, len,
ext4_ext_pblock(ex), status);
@@ -620,7 +621,7 @@ static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
} 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_is_unwritten(path->p_ext),
ext4_ext_get_actual_len(path->p_ext),
ext4_ext_pblock(path->p_ext));
} else
@@ -646,7 +647,7 @@ 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_is_unwritten(ex),
ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex));
}
ext_debug("\n");
@@ -677,7 +678,7 @@ static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path,
ext_debug("move %d:%llu:[%d]%d in new leaf %llu\n",
le32_to_cpu(ex->ee_block),
ext4_ext_pblock(ex),
- ext4_ext_is_uninitialized(ex),
+ ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex),
newblock);
ex++;
@@ -802,7 +803,7 @@ ext4_ext_binsearch(struct inode *inode,
ext_debug(" -> %d:%llu:[%d]%d ",
le32_to_cpu(path->p_ext->ee_block),
ext4_ext_pblock(path->p_ext),
- ext4_ext_is_uninitialized(path->p_ext),
+ ext4_ext_is_unwritten(path->p_ext),
ext4_ext_get_actual_len(path->p_ext));
#ifdef CHECK_BINSEARCH
@@ -1686,11 +1687,11 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
/*
* Make sure that both extents are initialized. We don't merge
- * uninitialized extents so that we can be sure that end_io code has
+ * unwritten extents so that we can be sure that end_io code has
* the extent that was written properly split out and conversion to
* initialized is trivial.
*/
- if (ext4_ext_is_uninitialized(ex1) != ext4_ext_is_uninitialized(ex2))
+ if (ext4_ext_is_unwritten(ex1) != ext4_ext_is_unwritten(ex2))
return 0;
ext1_ee_len = ext4_ext_get_actual_len(ex1);
@@ -1707,10 +1708,10 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
*/
if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
return 0;
- if (ext4_ext_is_uninitialized(ex1) &&
+ if (ext4_ext_is_unwritten(ex1) &&
(ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN) ||
atomic_read(&EXT4_I(inode)->i_unwritten) ||
- (ext1_ee_len + ext2_ee_len > EXT_UNINIT_MAX_LEN)))
+ (ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN)))
return 0;
#ifdef AGGRESSIVE_TEST
if (ext1_ee_len >= 4)
@@ -1735,7 +1736,7 @@ static int ext4_ext_try_to_merge_right(struct inode *inode,
{
struct ext4_extent_header *eh;
unsigned int depth, len;
- int merge_done = 0, uninit;
+ int merge_done = 0, unwritten;
depth = ext_depth(inode);
BUG_ON(path[depth].p_hdr == NULL);
@@ -1745,11 +1746,11 @@ static int ext4_ext_try_to_merge_right(struct inode *inode,
if (!ext4_can_extents_be_merged(inode, ex, ex + 1))
break;
/* merge with next extent! */
- uninit = ext4_ext_is_uninitialized(ex);
+ unwritten = ext4_ext_is_unwritten(ex);
ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ ext4_ext_get_actual_len(ex + 1));
- if (uninit)
- ext4_ext_mark_uninitialized(ex);
+ if (unwritten)
+ ext4_ext_mark_unwritten(ex);
if (ex + 1 < EXT_LAST_EXTENT(eh)) {
len = (EXT_LAST_EXTENT(eh) - ex - 1)
@@ -1903,7 +1904,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
struct ext4_ext_path *npath = NULL;
int depth, len, err;
ext4_lblk_t next;
- int mb_flags = 0, uninit;
+ int mb_flags = 0, unwritten;
if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
@@ -1943,21 +1944,21 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
if (ext4_can_extents_be_merged(inode, ex, newext)) {
ext_debug("append [%d]%d block to %u:[%d]%d"
"(from %llu)\n",
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
le32_to_cpu(ex->ee_block),
- ext4_ext_is_uninitialized(ex),
+ ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex),
ext4_ext_pblock(ex));
err = ext4_ext_get_access(handle, inode,
path + depth);
if (err)
return err;
- uninit = ext4_ext_is_uninitialized(ex);
+ unwritten = ext4_ext_is_unwritten(ex);
ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ ext4_ext_get_actual_len(newext));
- if (uninit)
- ext4_ext_mark_uninitialized(ex);
+ if (unwritten)
+ ext4_ext_mark_unwritten(ex);
eh = path[depth].p_hdr;
nearex = ex;
goto merge;
@@ -1969,10 +1970,10 @@ prepend:
ext_debug("prepend %u[%d]%d block to %u:[%d]%d"
"(from %llu)\n",
le32_to_cpu(newext->ee_block),
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
le32_to_cpu(ex->ee_block),
- ext4_ext_is_uninitialized(ex),
+ ext4_ext_is_unwritten(ex),
ext4_ext_get_actual_len(ex),
ext4_ext_pblock(ex));
err = ext4_ext_get_access(handle, inode,
@@ -1980,13 +1981,13 @@ prepend:
if (err)
return err;
- uninit = ext4_ext_is_uninitialized(ex);
+ unwritten = ext4_ext_is_unwritten(ex);
ex->ee_block = newext->ee_block;
ext4_ext_store_pblock(ex, ext4_ext_pblock(newext));
ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
+ ext4_ext_get_actual_len(newext));
- if (uninit)
- ext4_ext_mark_uninitialized(ex);
+ if (unwritten)
+ ext4_ext_mark_unwritten(ex);
eh = path[depth].p_hdr;
nearex = ex;
goto merge;
@@ -2046,7 +2047,7 @@ has_space:
ext_debug("first extent in the leaf: %u:%llu:[%d]%d\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext));
nearex = EXT_FIRST_EXTENT(eh);
} else {
@@ -2057,7 +2058,7 @@ has_space:
"nearest %p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
nearex);
nearex++;
@@ -2068,7 +2069,7 @@ has_space:
"nearest %p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
nearex);
}
@@ -2078,7 +2079,7 @@ has_space:
"move %d extents from 0x%p to 0x%p\n",
le32_to_cpu(newext->ee_block),
ext4_ext_pblock(newext),
- ext4_ext_is_uninitialized(newext),
+ ext4_ext_is_unwritten(newext),
ext4_ext_get_actual_len(newext),
len, nearex, nearex + 1);
memmove(nearex + 1, nearex,
@@ -2200,7 +2201,7 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
es.es_lblk = le32_to_cpu(ex->ee_block);
es.es_len = ext4_ext_get_actual_len(ex);
es.es_pblk = ext4_ext_pblock(ex);
- if (ext4_ext_is_uninitialized(ex))
+ if (ext4_ext_is_unwritten(ex))
flags |= FIEMAP_EXTENT_UNWRITTEN;
}
@@ -2576,7 +2577,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
unsigned num;
ext4_lblk_t ex_ee_block;
unsigned short ex_ee_len;
- unsigned uninitialized = 0;
+ unsigned unwritten = 0;
struct ext4_extent *ex;
ext4_fsblk_t pblk;
@@ -2623,13 +2624,13 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
while (ex >= EXT_FIRST_EXTENT(eh) &&
ex_ee_block + ex_ee_len > start) {
- if (ext4_ext_is_uninitialized(ex))
- uninitialized = 1;
+ if (ext4_ext_is_unwritten(ex))
+ unwritten = 1;
else
- uninitialized = 0;
+ unwritten = 0;
ext_debug("remove ext %u:[%d]%d\n", ex_ee_block,
- uninitialized, ex_ee_len);
+ unwritten, ex_ee_len);
path[depth].p_ext = ex;
a = ex_ee_block > start ? ex_ee_block : start;
@@ -2701,11 +2702,11 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
ex->ee_len = cpu_to_le16(num);
/*
- * Do not mark uninitialized if all the blocks in the
+ * Do not mark unwritten if all the blocks in the
* extent have been removed.
*/
- if (uninitialized && num)
- ext4_ext_mark_uninitialized(ex);
+ if (unwritten && num)
+ ext4_ext_mark_unwritten(ex);
/*
* If the extent was completely released,
* we need to remove it from the leaf
@@ -2854,9 +2855,9 @@ again:
end < ee_block + ext4_ext_get_actual_len(ex) - 1) {
int split_flag = 0;
- if (ext4_ext_is_uninitialized(ex))
- split_flag = EXT4_EXT_MARK_UNINIT1 |
- EXT4_EXT_MARK_UNINIT2;
+ if (ext4_ext_is_unwritten(ex))
+ split_flag = EXT4_EXT_MARK_UNWRIT1 |
+ EXT4_EXT_MARK_UNWRIT2;
/*
* Split the extent in two so that 'end' is the last
@@ -3113,7 +3114,7 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
* @path: the path to the extent
* @split: the logical block where the extent is splitted.
* @split_flags: indicates if the extent could be zeroout if split fails, and
- * the states(init or uninit) of new extents.
+ * the states(init or unwritten) of new extents.
* @flags: flags used to insert new extent to extent tree.
*
*
@@ -3155,10 +3156,10 @@ static int ext4_split_extent_at(handle_t *handle,
newblock = split - ee_block + ext4_ext_pblock(ex);
BUG_ON(split < ee_block || split >= (ee_block + ee_len));
- BUG_ON(!ext4_ext_is_uninitialized(ex) &&
+ BUG_ON(!ext4_ext_is_unwritten(ex) &&
split_flag & (EXT4_EXT_MAY_ZEROOUT |
- EXT4_EXT_MARK_UNINIT1 |
- EXT4_EXT_MARK_UNINIT2));
+ EXT4_EXT_MARK_UNWRIT1 |
+ EXT4_EXT_MARK_UNWRIT2));
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
@@ -3170,8 +3171,8 @@ static int ext4_split_extent_at(handle_t *handle,
* then we just change the state of the extent, and splitting
* is not needed.
*/
- if (split_flag & EXT4_EXT_MARK_UNINIT2)
- ext4_ext_mark_uninitialized(ex);
+ if (split_flag & EXT4_EXT_MARK_UNWRIT2)
+ ext4_ext_mark_unwritten(ex);
else
ext4_ext_mark_initialized(ex);
@@ -3185,8 +3186,8 @@ static int ext4_split_extent_at(handle_t *handle,
/* case a */
memcpy(&orig_ex, ex, sizeof(orig_ex));
ex->ee_len = cpu_to_le16(split - ee_block);
- if (split_flag & EXT4_EXT_MARK_UNINIT1)
- ext4_ext_mark_uninitialized(ex);
+ if (split_flag & EXT4_EXT_MARK_UNWRIT1)
+ ext4_ext_mark_unwritten(ex);
/*
* path may lead to new leaf, not to original leaf any more
@@ -3200,8 +3201,8 @@ static int ext4_split_extent_at(handle_t *handle,
ex2->ee_block = cpu_to_le32(split);
ex2->ee_len = cpu_to_le16(ee_len - (split - ee_block));
ext4_ext_store_pblock(ex2, newblock);
- if (split_flag & EXT4_EXT_MARK_UNINIT2)
- ext4_ext_mark_uninitialized(ex2);
+ if (split_flag & EXT4_EXT_MARK_UNWRIT2)
+ ext4_ext_mark_unwritten(ex2);
err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
@@ -3278,7 +3279,7 @@ static int ext4_split_extent(handle_t *handle,
struct ext4_extent *ex;
unsigned int ee_len, depth;
int err = 0;
- int uninitialized;
+ int unwritten;
int split_flag1, flags1;
int allocated = map->m_len;
@@ -3286,14 +3287,14 @@ static int ext4_split_extent(handle_t *handle,
ex = path[depth].p_ext;
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
- uninitialized = ext4_ext_is_uninitialized(ex);
+ unwritten = ext4_ext_is_unwritten(ex);
if (map->m_lblk + map->m_len < ee_block + ee_len) {
split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT;
flags1 = flags | EXT4_GET_BLOCKS_PRE_IO;
- if (uninitialized)
- split_flag1 |= EXT4_EXT_MARK_UNINIT1 |
- EXT4_EXT_MARK_UNINIT2;
+ if (unwritten)
+ split_flag1 |= EXT4_EXT_MARK_UNWRIT1 |
+ EXT4_EXT_MARK_UNWRIT2;
if (split_flag & EXT4_EXT_DATA_VALID2)
split_flag1 |= EXT4_EXT_DATA_VALID1;
err = ext4_split_extent_at(handle, inode, path,
@@ -3313,15 +3314,20 @@ static int ext4_split_extent(handle_t *handle,
return PTR_ERR(path);
depth = ext_depth(inode);
ex = path[depth].p_ext;
- uninitialized = ext4_ext_is_uninitialized(ex);
+ if (!ex) {
+ EXT4_ERROR_INODE(inode, "unexpected hole at %lu",
+ (unsigned long) map->m_lblk);
+ return -EIO;
+ }
+ unwritten = ext4_ext_is_unwritten(ex);
split_flag1 = 0;
if (map->m_lblk >= ee_block) {
split_flag1 = split_flag & EXT4_EXT_DATA_VALID2;
- if (uninitialized) {
- split_flag1 |= EXT4_EXT_MARK_UNINIT1;
+ if (unwritten) {
+ split_flag1 |= EXT4_EXT_MARK_UNWRIT1;
split_flag1 |= split_flag & (EXT4_EXT_MAY_ZEROOUT |
- EXT4_EXT_MARK_UNINIT2);
+ EXT4_EXT_MARK_UNWRIT2);
}
err = ext4_split_extent_at(handle, inode, path,
map->m_lblk, split_flag1, flags);
@@ -3336,16 +3342,16 @@ out:
/*
* This function is called by ext4_ext_map_blocks() if someone tries to write
- * to an uninitialized extent. It may result in splitting the uninitialized
+ * to an unwritten extent. It may result in splitting the unwritten
* extent into multiple extents (up to three - one initialized and two
- * uninitialized).
+ * unwritten).
* There are three possibilities:
* a> There is no split required: Entire extent should be initialized
* 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
*
* Pre-conditions:
- * - The extent pointed to by 'path' is uninitialized.
+ * - The extent pointed to by 'path' is unwritten.
* - The extent pointed to by 'path' contains a superset
* of the logical span [map->m_lblk, map->m_lblk + map->m_len).
*
@@ -3391,12 +3397,12 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
/* Pre-conditions */
- BUG_ON(!ext4_ext_is_uninitialized(ex));
+ BUG_ON(!ext4_ext_is_unwritten(ex));
BUG_ON(!in_range(map->m_lblk, ee_block, ee_len));
/*
* Attempt to transfer newly initialized blocks from the currently
- * uninitialized extent to its neighbor. This is much cheaper
+ * unwritten extent to its neighbor. This is much cheaper
* than an insertion followed by a merge as those involve costly
* memmove() calls. Transferring to the left is the common case in
* steady state for workloads doing fallocate(FALLOC_FL_KEEP_SIZE)
@@ -3432,7 +3438,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
* - C4: abut_ex can receive the additional blocks without
* overflowing the (initialized) length limit.
*/
- if ((!ext4_ext_is_uninitialized(abut_ex)) && /*C1*/
+ if ((!ext4_ext_is_unwritten(abut_ex)) && /*C1*/
((prev_lblk + prev_len) == ee_block) && /*C2*/
((prev_pblk + prev_len) == ee_pblk) && /*C3*/
(prev_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/
@@ -3447,7 +3453,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
ex->ee_block = cpu_to_le32(ee_block + map_len);
ext4_ext_store_pblock(ex, ee_pblk + map_len);
ex->ee_len = cpu_to_le16(ee_len - map_len);
- ext4_ext_mark_uninitialized(ex); /* Restore the flag */
+ ext4_ext_mark_unwritten(ex); /* Restore the flag */
/* Extend abut_ex by 'map_len' blocks */
abut_ex->ee_len = cpu_to_le16(prev_len + map_len);
@@ -3478,7 +3484,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
* - C4: abut_ex can receive the additional blocks without
* overflowing the (initialized) length limit.
*/
- if ((!ext4_ext_is_uninitialized(abut_ex)) && /*C1*/
+ if ((!ext4_ext_is_unwritten(abut_ex)) && /*C1*/
((map->m_lblk + map_len) == next_lblk) && /*C2*/
((ee_pblk + ee_len) == next_pblk) && /*C3*/
(next_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/
@@ -3493,7 +3499,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
abut_ex->ee_block = cpu_to_le32(next_lblk - map_len);
ext4_ext_store_pblock(abut_ex, next_pblk - map_len);
ex->ee_len = cpu_to_le16(ee_len - map_len);
- ext4_ext_mark_uninitialized(ex); /* Restore the flag */
+ ext4_ext_mark_unwritten(ex); /* Restore the flag */
/* Extend abut_ex by 'map_len' blocks */
abut_ex->ee_len = cpu_to_le16(next_len + map_len);
@@ -3598,26 +3604,26 @@ out:
/*
* This function is called by ext4_ext_map_blocks() from
* ext4_get_blocks_dio_write() when DIO to write
- * to an uninitialized extent.
+ * to an unwritten extent.
*
- * Writing to an uninitialized extent may result in splitting the uninitialized
- * extent into multiple initialized/uninitialized extents (up to three)
+ * Writing to an unwritten extent may result in splitting the unwritten
+ * extent into multiple initialized/unwritten extents (up to three)
* There are three possibilities:
- * a> There is no split required: Entire extent should be uninitialized
+ * a> There is no split required: Entire extent should be unwritten
* 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
*
* This works the same way in the case of initialized -> unwritten conversion.
*
* One of more index blocks maybe needed if the extent tree grow after
- * 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
+ * the unwritten extent split. To prevent ENOSPC occur at the IO
+ * complete, we need to split the unwritten extent before DIO submit
+ * the IO. The unwritten extent called at this time will be split
+ * into three unwritten extent(at most). After IO complete, the part
* being filled will be convert to initialized by the end_io callback function
* via ext4_convert_unwritten_extents().
*
- * Returns the size of uninitialized extent to be written on success.
+ * Returns the size of unwritten extent to be written on success.
*/
static int ext4_split_convert_extents(handle_t *handle,
struct inode *inode,
@@ -3655,7 +3661,7 @@ static int ext4_split_convert_extents(handle_t *handle,
} else if (flags & EXT4_GET_BLOCKS_CONVERT) {
split_flag |= ee_block + ee_len <= eof_block ?
EXT4_EXT_MAY_ZEROOUT : 0;
- split_flag |= (EXT4_EXT_MARK_UNINIT2 | EXT4_EXT_DATA_VALID2);
+ split_flag |= (EXT4_EXT_MARK_UNWRIT2 | EXT4_EXT_DATA_VALID2);
}
flags |= EXT4_GET_BLOCKS_PRE_IO;
return ext4_split_extent(handle, inode, path, map, split_flag, flags);
@@ -3694,13 +3700,19 @@ static int ext4_convert_initialized_extents(handle_t *handle,
}
depth = ext_depth(inode);
ex = path[depth].p_ext;
+ if (!ex) {
+ EXT4_ERROR_INODE(inode, "unexpected hole at %lu",
+ (unsigned long) map->m_lblk);
+ err = -EIO;
+ goto out;
+ }
}
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
goto out;
- /* first mark the extent as uninitialized */
- ext4_ext_mark_uninitialized(ex);
+ /* first mark the extent as unwritten */
+ ext4_ext_mark_unwritten(ex);
/* note: ext4_ext_correct_indexes() isn't needed here because
* borders are not changed
@@ -3960,10 +3972,10 @@ ext4_ext_convert_initialized_extent(handle_t *handle, struct inode *inode,
/*
* Make sure that the extent is no bigger than we support with
- * uninitialized extent
+ * unwritten extent
*/
- if (map->m_len > EXT_UNINIT_MAX_LEN)
- map->m_len = EXT_UNINIT_MAX_LEN / 2;
+ if (map->m_len > EXT_UNWRITTEN_MAX_LEN)
+ map->m_len = EXT_UNWRITTEN_MAX_LEN / 2;
ret = ext4_convert_initialized_extents(handle, inode, map,
path);
@@ -3982,7 +3994,7 @@ ext4_ext_convert_initialized_extent(handle_t *handle, struct inode *inode,
}
static int
-ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
+ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map,
struct ext4_ext_path *path, int flags,
unsigned int allocated, ext4_fsblk_t newblock)
@@ -3991,23 +4003,23 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
int err = 0;
ext4_io_end_t *io = ext4_inode_aio(inode);
- ext_debug("ext4_ext_handle_uninitialized_extents: inode %lu, logical "
+ ext_debug("ext4_ext_handle_unwritten_extents: inode %lu, logical "
"block %llu, max_blocks %u, flags %x, allocated %u\n",
inode->i_ino, (unsigned long long)map->m_lblk, map->m_len,
flags, allocated);
ext4_ext_show_leaf(inode, path);
/*
- * When writing into uninitialized space, we should not fail to
+ * When writing into unwritten space, we should not fail to
* allocate metadata blocks for the new extent block if needed.
*/
flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL;
- trace_ext4_ext_handle_uninitialized_extents(inode, map, flags,
+ trace_ext4_ext_handle_unwritten_extents(inode, map, flags,
allocated, newblock);
/* get_block() before submit the IO, split the extent */
- if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
+ if (flags & EXT4_GET_BLOCKS_PRE_IO) {
ret = ext4_split_convert_extents(handle, inode, map,
path, flags | EXT4_GET_BLOCKS_CONVERT);
if (ret <= 0)
@@ -4022,12 +4034,10 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
else
ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
map->m_flags |= EXT4_MAP_UNWRITTEN;
- if (ext4_should_dioread_nolock(inode))
- map->m_flags |= EXT4_MAP_UNINIT;
goto out;
}
/* IO end_io complete, convert the filled extent to written */
- if ((flags & EXT4_GET_BLOCKS_CONVERT)) {
+ if (flags & EXT4_GET_BLOCKS_CONVERT) {
ret = ext4_convert_unwritten_extents_endio(handle, inode, map,
path);
if (ret >= 0) {
@@ -4048,7 +4058,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
* repeat fallocate creation request
* we already have an unwritten extent
*/
- if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) {
+ if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) {
map->m_flags |= EXT4_MAP_UNWRITTEN;
goto map_out;
}
@@ -4299,7 +4309,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
/*
- * Uninitialized extents are treated as holes, except that
+ * unwritten extents are treated as holes, except that
* we split out initialized portions during a write.
*/
ee_len = ext4_ext_get_actual_len(ex);
@@ -4318,16 +4328,16 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
* If the extent is initialized check whether the
* caller wants to convert it to unwritten.
*/
- if ((!ext4_ext_is_uninitialized(ex)) &&
+ if ((!ext4_ext_is_unwritten(ex)) &&
(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) {
allocated = ext4_ext_convert_initialized_extent(
handle, inode, map, path, flags,
allocated, newblock);
goto out2;
- } else if (!ext4_ext_is_uninitialized(ex))
+ } else if (!ext4_ext_is_unwritten(ex))
goto out;
- ret = ext4_ext_handle_uninitialized_extents(
+ ret = ext4_ext_handle_unwritten_extents(
handle, inode, map, path, flags,
allocated, newblock);
if (ret < 0)
@@ -4399,15 +4409,15 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
/*
* See if request is beyond maximum number of blocks we can have in
* a single extent. For an initialized extent this limit is
- * EXT_INIT_MAX_LEN and for an uninitialized extent this limit is
- * EXT_UNINIT_MAX_LEN.
+ * EXT_INIT_MAX_LEN and for an unwritten extent this limit is
+ * EXT_UNWRITTEN_MAX_LEN.
*/
if (map->m_len > EXT_INIT_MAX_LEN &&
- !(flags & EXT4_GET_BLOCKS_UNINIT_EXT))
+ !(flags & EXT4_GET_BLOCKS_UNWRIT_EXT))
map->m_len = EXT_INIT_MAX_LEN;
- else if (map->m_len > EXT_UNINIT_MAX_LEN &&
- (flags & EXT4_GET_BLOCKS_UNINIT_EXT))
- map->m_len = EXT_UNINIT_MAX_LEN;
+ else if (map->m_len > EXT_UNWRITTEN_MAX_LEN &&
+ (flags & EXT4_GET_BLOCKS_UNWRIT_EXT))
+ map->m_len = EXT_UNWRITTEN_MAX_LEN;
/* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */
newex.ee_len = cpu_to_le16(map->m_len);
@@ -4455,21 +4465,19 @@ got_allocated_blocks:
/* try to insert new extent into found leaf and return */
ext4_ext_store_pblock(&newex, newblock + offset);
newex.ee_len = cpu_to_le16(ar.len);
- /* Mark uninitialized */
- if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){
- ext4_ext_mark_uninitialized(&newex);
+ /* Mark unwritten */
+ if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT){
+ ext4_ext_mark_unwritten(&newex);
map->m_flags |= EXT4_MAP_UNWRITTEN;
/*
* io_end structure was created for every IO write to an
- * uninitialized extent. To avoid unnecessary conversion,
+ * unwritten extent. To avoid unnecessary conversion,
* here we flag the IO that really needs the conversion.
* For non asycn direct IO case, flag the inode state
* that we need to perform conversion when IO is done.
*/
- if ((flags & EXT4_GET_BLOCKS_PRE_IO))
+ if (flags & EXT4_GET_BLOCKS_PRE_IO)
set_unwritten = 1;
- if (ext4_should_dioread_nolock(inode))
- map->m_flags |= EXT4_MAP_UNINIT;
}
err = 0;
@@ -4596,9 +4604,9 @@ got_allocated_blocks:
/*
* Cache the extent and update transaction to commit on fdatasync only
- * when it is _not_ an uninitialized extent.
+ * when it is _not_ an unwritten extent.
*/
- if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0)
+ if ((flags & EXT4_GET_BLOCKS_UNWRIT_EXT) == 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
else
ext4_update_inode_fsync_trans(handle, inode, 0);
@@ -4672,7 +4680,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
* that it doesn't get unnecessarily split into multiple
* extents.
*/
- if (len <= EXT_UNINIT_MAX_LEN)
+ if (len <= EXT_UNWRITTEN_MAX_LEN)
flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
/*
@@ -4730,6 +4738,16 @@ static long ext4_zero_range(struct file *file, loff_t offset,
trace_ext4_zero_range(inode, offset, len, mode);
+ if (!S_ISREG(inode->i_mode))
+ return -EINVAL;
+
+ /* Call ext4_force_commit to flush all data in case of data=journal. */
+ if (ext4_should_journal_data(inode)) {
+ ret = ext4_force_commit(inode->i_sb);
+ if (ret)
+ return ret;
+ }
+
/*
* Write out all dirty pages to avoid race conditions
* Then release them.
@@ -4761,7 +4779,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
else
max_blocks -= lblk;
- flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT |
+ flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT |
EXT4_GET_BLOCKS_CONVERT_UNWRITTEN;
if (mode & FALLOC_FL_KEEP_SIZE)
flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
@@ -4878,9 +4896,6 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
if (mode & FALLOC_FL_PUNCH_HOLE)
return ext4_punch_hole(inode, offset, len);
- if (mode & FALLOC_FL_COLLAPSE_RANGE)
- return ext4_collapse_range(inode, offset, len);
-
ret = ext4_convert_inline_data(inode);
if (ret)
return ret;
@@ -4892,6 +4907,9 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return -EOPNOTSUPP;
+ if (mode & FALLOC_FL_COLLAPSE_RANGE)
+ return ext4_collapse_range(inode, offset, len);
+
if (mode & FALLOC_FL_ZERO_RANGE)
return ext4_zero_range(file, offset, len, mode);
@@ -4904,7 +4922,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
- lblk;
- flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT;
+ flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT;
if (mode & FALLOC_FL_KEEP_SIZE)
flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
@@ -5229,18 +5247,19 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift,
if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr))
update = 1;
- *start = ex_last->ee_block +
+ *start = le32_to_cpu(ex_last->ee_block) +
ext4_ext_get_actual_len(ex_last);
while (ex_start <= ex_last) {
- ex_start->ee_block -= shift;
- if (ex_start >
- EXT_FIRST_EXTENT(path[depth].p_hdr)) {
- if (ext4_ext_try_to_merge_right(inode,
- path, ex_start - 1))
- ex_last--;
- }
- ex_start++;
+ le32_add_cpu(&ex_start->ee_block, -shift);
+ /* Try to merge to the left. */
+ if ((ex_start >
+ EXT_FIRST_EXTENT(path[depth].p_hdr)) &&
+ ext4_ext_try_to_merge_right(inode,
+ path, ex_start - 1))
+ ex_last--;
+ else
+ ex_start++;
}
err = ext4_ext_dirty(handle, inode, path + depth);
if (err)
@@ -5255,7 +5274,7 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift,
if (err)
goto out;
- path[depth].p_idx->ei_block -= shift;
+ le32_add_cpu(&path[depth].p_idx->ei_block, -shift);
err = ext4_ext_dirty(handle, inode, path + depth);
if (err)
goto out;
@@ -5300,7 +5319,8 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
return ret;
}
- stop_block = extent->ee_block + ext4_ext_get_actual_len(extent);
+ stop_block = le32_to_cpu(extent->ee_block) +
+ ext4_ext_get_actual_len(extent);
ext4_ext_drop_refs(path);
kfree(path);
@@ -5313,10 +5333,18 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
* enough to accomodate the shift.
*/
path = ext4_ext_find_extent(inode, start - 1, NULL, 0);
+ if (IS_ERR(path))
+ return PTR_ERR(path);
depth = path->p_depth;
extent = path[depth].p_ext;
- ex_start = extent->ee_block;
- ex_end = extent->ee_block + ext4_ext_get_actual_len(extent);
+ if (extent) {
+ ex_start = le32_to_cpu(extent->ee_block);
+ ex_end = le32_to_cpu(extent->ee_block) +
+ ext4_ext_get_actual_len(extent);
+ } else {
+ ex_start = 0;
+ ex_end = 0;
+ }
ext4_ext_drop_refs(path);
kfree(path);
@@ -5331,7 +5359,13 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
return PTR_ERR(path);
depth = path->p_depth;
extent = path[depth].p_ext;
- current_block = extent->ee_block;
+ if (!extent) {
+ EXT4_ERROR_INODE(inode, "unexpected hole at %lu",
+ (unsigned long) start);
+ return -EIO;
+ }
+
+ current_block = le32_to_cpu(extent->ee_block);
if (start > current_block) {
/* Hole, move to the next extent */
ret = mext_next_extent(inode, path, &extent);
@@ -5365,17 +5399,18 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
ext4_lblk_t punch_start, punch_stop;
handle_t *handle;
unsigned int credits;
- loff_t new_size;
+ loff_t new_size, ioffset;
int ret;
- BUG_ON(offset + len > i_size_read(inode));
-
/* Collapse range works only on fs block size aligned offsets. */
if (offset & (EXT4_BLOCK_SIZE(sb) - 1) ||
len & (EXT4_BLOCK_SIZE(sb) - 1))
return -EINVAL;
if (!S_ISREG(inode->i_mode))
+ return -EINVAL;
+
+ if (EXT4_SB(inode->i_sb)->s_cluster_ratio > 1)
return -EOPNOTSUPP;
trace_ext4_collapse_range(inode, offset, len);
@@ -5383,22 +5418,34 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
punch_start = offset >> EXT4_BLOCK_SIZE_BITS(sb);
punch_stop = (offset + len) >> EXT4_BLOCK_SIZE_BITS(sb);
+ /* Call ext4_force_commit to flush all data in case of data=journal. */
+ if (ext4_should_journal_data(inode)) {
+ ret = ext4_force_commit(inode->i_sb);
+ if (ret)
+ return ret;
+ }
+
+ /*
+ * Need to round down offset to be aligned with page size boundary
+ * for page size > block size.
+ */
+ ioffset = round_down(offset, PAGE_SIZE);
+
/* Write out all dirty pages */
- ret = filemap_write_and_wait_range(inode->i_mapping, offset, -1);
+ ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
+ LLONG_MAX);
if (ret)
return ret;
/* Take mutex lock */
mutex_lock(&inode->i_mutex);
- /* It's not possible punch hole on append only file */
- if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
- ret = -EPERM;
- goto out_mutex;
- }
-
- if (IS_SWAPFILE(inode)) {
- ret = -ETXTBSY;
+ /*
+ * There is no need to overlap collapse range with EOF, in which case
+ * it is effectively a truncate operation
+ */
+ if (offset + len >= i_size_read(inode)) {
+ ret = -EINVAL;
goto out_mutex;
}
@@ -5408,7 +5455,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
goto out_mutex;
}
- truncate_pagecache_range(inode, offset, -1);
+ truncate_pagecache(inode, ioffset);
/* Wait for existing dio to complete */
ext4_inode_block_unlocked_dio(inode);
@@ -5425,7 +5472,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
ext4_discard_preallocations(inode);
ret = ext4_es_remove_extent(inode, punch_start,
- EXT_MAX_BLOCKS - punch_start - 1);
+ EXT_MAX_BLOCKS - punch_start);
if (ret) {
up_write(&EXT4_I(inode)->i_data_sem);
goto out_stop;
@@ -5436,6 +5483,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
up_write(&EXT4_I(inode)->i_data_sem);
goto out_stop;
}
+ ext4_discard_preallocations(inode);
ret = ext4_ext_shift_extents(inode, handle, punch_stop,
punch_stop - punch_start);
@@ -5445,10 +5493,9 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
}
new_size = i_size_read(inode) - len;
- truncate_setsize(inode, new_size);
+ i_size_write(inode, new_size);
EXT4_I(inode)->i_disksize = new_size;
- ext4_discard_preallocations(inode);
up_write(&EXT4_I(inode)->i_data_sem);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 0a014a7194b2..3f5c188953a4 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -344,8 +344,14 @@ static int ext4_es_can_be_merged(struct extent_status *es1,
if (ext4_es_status(es1) != ext4_es_status(es2))
return 0;
- if (((__u64) es1->es_len) + es2->es_len > 0xFFFFFFFFULL)
+ if (((__u64) es1->es_len) + es2->es_len > EXT_MAX_BLOCKS) {
+ pr_warn("ES assertion failed when merging extents. "
+ "The sum of lengths of es1 (%d) and es2 (%d) "
+ "is bigger than allowed file size (%d)\n",
+ es1->es_len, es2->es_len, EXT_MAX_BLOCKS);
+ WARN_ON(1);
return 0;
+ }
if (((__u64) es1->es_lblk) + es1->es_len != es2->es_lblk)
return 0;
@@ -433,7 +439,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode,
ee_start = ext4_ext_pblock(ex);
ee_len = ext4_ext_get_actual_len(ex);
- ee_status = ext4_ext_is_uninitialized(ex) ? 1 : 0;
+ ee_status = ext4_ext_is_unwritten(ex) ? 1 : 0;
es_status = ext4_es_is_unwritten(es) ? 1 : 0;
/*
@@ -810,7 +816,7 @@ retry:
newes.es_lblk = end + 1;
newes.es_len = len2;
- block = 0x7FDEADBEEF;
+ block = 0x7FDEADBEEFULL;
if (ext4_es_is_written(&orig_es) ||
ext4_es_is_unwritten(&orig_es))
block = ext4_es_pblock(&orig_es) +
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index ca7502d89fde..4e8bc284ec0e 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -57,7 +57,7 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
return 0;
}
-void ext4_unwritten_wait(struct inode *inode)
+static void ext4_unwritten_wait(struct inode *inode)
{
wait_queue_head_t *wq = ext4_ioend_wq(inode);
@@ -82,7 +82,7 @@ ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
size_t count = iov_length(iov, nr_segs);
loff_t final_size = pos + count;
- if (pos >= inode->i_size)
+ if (pos >= i_size_read(inode))
return 0;
if ((pos & blockmask) || (final_size & blockmask))
@@ -92,58 +92,91 @@ ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
}
static ssize_t
-ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
+ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
+ struct inode *inode = file_inode(iocb->ki_filp);
+ struct mutex *aio_mutex = NULL;
struct blk_plug plug;
- int unaligned_aio = 0;
- ssize_t ret;
+ int o_direct = file->f_flags & O_DIRECT;
int overwrite = 0;
size_t length = iov_length(iov, nr_segs);
+ ssize_t ret;
- if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
- !is_sync_kiocb(iocb))
- unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
+ BUG_ON(iocb->ki_pos != pos);
- /* Unaligned direct AIO must be serialized; see comment above */
- if (unaligned_aio) {
- mutex_lock(ext4_aio_mutex(inode));
+ /*
+ * Unaligned direct AIO must be serialized; see comment above
+ * In the case of O_APPEND, assume that we must always serialize
+ */
+ if (o_direct &&
+ ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
+ !is_sync_kiocb(iocb) &&
+ (file->f_flags & O_APPEND ||
+ ext4_unaligned_aio(inode, iov, nr_segs, pos))) {
+ aio_mutex = ext4_aio_mutex(inode);
+ mutex_lock(aio_mutex);
ext4_unwritten_wait(inode);
}
- BUG_ON(iocb->ki_pos != pos);
-
mutex_lock(&inode->i_mutex);
- blk_start_plug(&plug);
+ if (file->f_flags & O_APPEND)
+ iocb->ki_pos = pos = i_size_read(inode);
+
+ /*
+ * If we have encountered a bitmap-format file, the size limit
+ * is smaller than s_maxbytes, which is for extent-mapped files.
+ */
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- iocb->private = &overwrite;
+ if ((pos > sbi->s_bitmap_maxbytes) ||
+ (pos == sbi->s_bitmap_maxbytes && length > 0)) {
+ mutex_unlock(&inode->i_mutex);
+ ret = -EFBIG;
+ goto errout;
+ }
- /* check whether we do a DIO overwrite or not */
- if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
- !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
- struct ext4_map_blocks map;
- unsigned int blkbits = inode->i_blkbits;
- int err, len;
+ if (pos + length > sbi->s_bitmap_maxbytes) {
+ nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
+ sbi->s_bitmap_maxbytes - pos);
+ }
+ }
- map.m_lblk = pos >> blkbits;
- map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
- - map.m_lblk;
- len = map.m_len;
+ if (o_direct) {
+ blk_start_plug(&plug);
- err = ext4_map_blocks(NULL, inode, &map, 0);
- /*
- * 'err==len' means that all of blocks has been preallocated no
- * matter they are initialized or not. For excluding
- * uninitialized extents, we need to check m_flags. There are
- * two conditions that indicate for initialized extents.
- * 1) If we hit extent cache, EXT4_MAP_MAPPED flag is returned;
- * 2) If we do a real lookup, non-flags are returned.
- * So we should check these two conditions.
- */
- if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
- overwrite = 1;
+ iocb->private = &overwrite;
+
+ /* check whether we do a DIO overwrite or not */
+ if (ext4_should_dioread_nolock(inode) && !aio_mutex &&
+ !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
+ struct ext4_map_blocks map;
+ unsigned int blkbits = inode->i_blkbits;
+ int err, len;
+
+ map.m_lblk = pos >> blkbits;
+ map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
+ - map.m_lblk;
+ len = map.m_len;
+
+ err = ext4_map_blocks(NULL, inode, &map, 0);
+ /*
+ * 'err==len' means that all of blocks has
+ * been preallocated no matter they are
+ * initialized or not. For excluding
+ * unwritten extents, we need to check
+ * m_flags. There are two conditions that
+ * indicate for initialized extents. 1) If we
+ * hit extent cache, EXT4_MAP_MAPPED flag is
+ * returned; 2) If we do a real lookup,
+ * non-flags are returned. So we should check
+ * these two conditions.
+ */
+ if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
+ overwrite = 1;
+ }
}
ret = __generic_file_aio_write(iocb, iov, nr_segs);
@@ -156,45 +189,12 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
if (err < 0)
ret = err;
}
- blk_finish_plug(&plug);
-
- if (unaligned_aio)
- mutex_unlock(ext4_aio_mutex(inode));
-
- return ret;
-}
-
-static ssize_t
-ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
-{
- struct inode *inode = file_inode(iocb->ki_filp);
- ssize_t ret;
-
- /*
- * If we have encountered a bitmap-format file, the size limit
- * is smaller than s_maxbytes, which is for extent-mapped files.
- */
-
- if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- size_t length = iov_length(iov, nr_segs);
-
- if ((pos > sbi->s_bitmap_maxbytes ||
- (pos == sbi->s_bitmap_maxbytes && length > 0)))
- return -EFBIG;
-
- if (pos + length > sbi->s_bitmap_maxbytes) {
- nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
- sbi->s_bitmap_maxbytes - pos);
- }
- }
-
- if (unlikely(iocb->ki_filp->f_flags & O_DIRECT))
- ret = ext4_file_dio_write(iocb, iov, nr_segs, pos);
- else
- ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
+ if (o_direct)
+ blk_finish_plug(&plug);
+errout:
+ if (aio_mutex)
+ mutex_unlock(aio_mutex);
return ret;
}
@@ -244,6 +244,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
+ BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err) {
ext4_journal_stop(handle);
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 82edf5b93352..645205d8ada6 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -22,7 +22,7 @@
#define EXT4_INLINE_DOTDOT_OFFSET 2
#define EXT4_INLINE_DOTDOT_SIZE 4
-int ext4_get_inline_size(struct inode *inode)
+static int ext4_get_inline_size(struct inode *inode)
{
if (EXT4_I(inode)->i_inline_off)
return EXT4_I(inode)->i_inline_size;
@@ -211,8 +211,8 @@ out:
* value since it is already handled by ext4_xattr_ibody_inline_set.
* That saves us one memcpy.
*/
-void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
- void *buffer, loff_t pos, unsigned int len)
+static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
+ void *buffer, loff_t pos, unsigned int len)
{
struct ext4_xattr_entry *entry;
struct ext4_xattr_ibody_header *header;
@@ -264,6 +264,7 @@ static int ext4_create_inline_data(handle_t *handle,
if (error)
return error;
+ BUFFER_TRACE(is.iloc.bh, "get_write_access");
error = ext4_journal_get_write_access(handle, is.iloc.bh);
if (error)
goto out;
@@ -347,6 +348,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode,
if (error == -ENODATA)
goto out;
+ BUFFER_TRACE(is.iloc.bh, "get_write_access");
error = ext4_journal_get_write_access(handle, is.iloc.bh);
if (error)
goto out;
@@ -373,8 +375,8 @@ out:
return error;
}
-int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
- unsigned int len)
+static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
+ unsigned int len)
{
int ret, size;
struct ext4_inode_info *ei = EXT4_I(inode);
@@ -424,6 +426,7 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle,
if (error)
goto out;
+ BUFFER_TRACE(is.iloc.bh, "get_write_access");
error = ext4_journal_get_write_access(handle, is.iloc.bh);
if (error)
goto out;
@@ -1007,6 +1010,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle,
if (err)
return err;
+ BUFFER_TRACE(iloc->bh, "get_write_access");
err = ext4_journal_get_write_access(handle, iloc->bh);
if (err)
return err;
@@ -1669,6 +1673,7 @@ int ext4_delete_inline_entry(handle_t *handle,
EXT4_MIN_INLINE_DATA_SIZE;
}
+ BUFFER_TRACE(bh, "get_write_access");
err = ext4_journal_get_write_access(handle, bh);
if (err)
goto out;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5b0d2c7d5408..7fcd68ee9155 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -148,6 +148,9 @@ static int ext4_inode_is_fast_symlink(struct inode *inode)
int ea_blocks = EXT4_I(inode)->i_file_acl ?
EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0;
+ if (ext4_has_inline_data(inode))
+ return 0;
+
return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
}
@@ -443,7 +446,7 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
* could be converted.
*/
if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, flags &
EXT4_GET_BLOCKS_KEEP_SIZE);
@@ -489,8 +492,8 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
* Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping
* based files
*
- * On success, it returns the number of blocks being mapped or allocate.
- * if create==0 and the blocks are pre-allocated and uninitialized block,
+ * On success, it returns the number of blocks being mapped or allocated.
+ * if create==0 and the blocks are pre-allocated and unwritten block,
* the result buffer head is unmapped. If the create ==1, it will make sure
* the buffer head is mapped.
*
@@ -522,6 +525,10 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
if (unlikely(map->m_len > INT_MAX))
map->m_len = INT_MAX;
+ /* We can handle the block number less than EXT_MAX_BLOCKS */
+ if (unlikely(map->m_lblk >= EXT_MAX_BLOCKS))
+ return -EIO;
+
/* Lookup extent status tree firstly */
if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
ext4_es_lru_add(inode);
@@ -551,7 +558,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
* file system block.
*/
if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, flags &
EXT4_GET_BLOCKS_KEEP_SIZE);
@@ -618,12 +625,12 @@ found:
map->m_flags &= ~EXT4_MAP_FLAGS;
/*
- * New blocks allocate and/or writing to uninitialized extent
+ * New blocks allocate and/or writing to unwritten extent
* will possibly result in updating i_data, so we take
* the write lock of i_data_sem, and call get_blocks()
* with create == 1 flag.
*/
- down_write((&EXT4_I(inode)->i_data_sem));
+ down_write(&EXT4_I(inode)->i_data_sem);
/*
* if the caller is from delayed allocation writeout path
@@ -918,6 +925,7 @@ int do_journal_get_write_access(handle_t *handle,
*/
if (dirty)
clear_buffer_dirty(bh);
+ BUFFER_TRACE(bh, "get write access");
ret = ext4_journal_get_write_access(handle, bh);
if (!ret && dirty)
ret = ext4_handle_dirty_metadata(handle, NULL, bh);
@@ -1536,7 +1544,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
ext4_es_lru_add(inode);
if (ext4_es_is_hole(&es)) {
retval = 0;
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
goto add_delayed;
}
@@ -1573,7 +1581,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
* Try to see if we can get the block without requesting a new
* file system block.
*/
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_has_inline_data(inode)) {
/*
* We will soon create blocks for this page, and let
@@ -1765,6 +1773,7 @@ static int __ext4_journalled_writepage(struct page *page,
BUG_ON(!ext4_handle_valid(handle));
if (inline_data) {
+ BUFFER_TRACE(inode_bh, "get write access");
ret = ext4_journal_get_write_access(handle, inode_bh);
err = ext4_handle_dirty_metadata(handle, inode, inode_bh);
@@ -1842,6 +1851,7 @@ static int ext4_writepage(struct page *page,
struct buffer_head *page_bufs = NULL;
struct inode *inode = page->mapping->host;
struct ext4_io_submit io_submit;
+ bool keep_towrite = false;
trace_ext4_writepage(page);
size = i_size_read(inode);
@@ -1872,6 +1882,7 @@ static int ext4_writepage(struct page *page,
unlock_page(page);
return 0;
}
+ keep_towrite = true;
}
if (PageChecked(page) && ext4_should_journal_data(inode))
@@ -1888,7 +1899,7 @@ static int ext4_writepage(struct page *page,
unlock_page(page);
return -ENOMEM;
}
- ret = ext4_bio_write_page(&io_submit, page, len, wbc);
+ ret = ext4_bio_write_page(&io_submit, page, len, wbc, keep_towrite);
ext4_io_submit(&io_submit);
/* Drop io_end reference we got from init */
ext4_put_io_end_defer(io_submit.io_end);
@@ -1907,7 +1918,7 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
else
len = PAGE_CACHE_SIZE;
clear_page_dirty_for_io(page);
- err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc);
+ err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false);
if (!err)
mpd->wbc->nr_to_write--;
mpd->first_page++;
@@ -2028,7 +2039,7 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
* Scan buffers corresponding to changed extent (we expect corresponding pages
* to be already locked) and update buffer state according to new extent state.
* We map delalloc buffers to their physical location, clear unwritten bits,
- * and mark buffers as uninit when we perform writes to uninitialized extents
+ * and mark buffers as uninit when we perform writes to unwritten extents
* and do extent conversion after IO is finished. If the last page is not fully
* mapped, we update @map to the next extent in the last page that needs
* mapping. Otherwise we submit the page for IO.
@@ -2122,12 +2133,12 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
struct inode *inode = mpd->inode;
struct ext4_map_blocks *map = &mpd->map;
int get_blocks_flags;
- int err;
+ int err, dioread_nolock;
trace_ext4_da_write_pages_extent(inode, map);
/*
* Call ext4_map_blocks() to allocate any delayed allocation blocks, or
- * to convert an uninitialized extent to be initialized (in the case
+ * to convert an unwritten extent to be initialized (in the case
* where we have written into one or more preallocated blocks). It is
* possible that we're going to need more metadata blocks than
* previously reserved. However we must not fail because we're in
@@ -2144,7 +2155,8 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
*/
get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
EXT4_GET_BLOCKS_METADATA_NOFAIL;
- if (ext4_should_dioread_nolock(inode))
+ dioread_nolock = ext4_should_dioread_nolock(inode);
+ if (dioread_nolock)
get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
if (map->m_flags & (1 << BH_Delay))
get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
@@ -2152,7 +2164,7 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
err = ext4_map_blocks(handle, inode, map, get_blocks_flags);
if (err < 0)
return err;
- if (map->m_flags & EXT4_MAP_UNINIT) {
+ if (dioread_nolock && (map->m_flags & EXT4_MAP_UNWRITTEN)) {
if (!mpd->io_submit.io_end->handle &&
ext4_handle_valid(handle)) {
mpd->io_submit.io_end->handle = handle->h_rsv_handle;
@@ -2243,13 +2255,23 @@ static int mpage_map_and_submit_extent(handle_t *handle,
return err;
} while (map->m_len);
- /* Update on-disk size after IO is submitted */
+ /*
+ * Update on-disk size after IO is submitted. Races with
+ * truncate are avoided by checking i_size under i_data_sem.
+ */
disksize = ((loff_t)mpd->first_page) << PAGE_CACHE_SHIFT;
if (disksize > EXT4_I(inode)->i_disksize) {
int err2;
-
- ext4_wb_update_i_disksize(inode, disksize);
+ loff_t i_size;
+
+ down_write(&EXT4_I(inode)->i_data_sem);
+ i_size = i_size_read(inode);
+ if (disksize > i_size)
+ disksize = i_size;
+ if (disksize > EXT4_I(inode)->i_disksize)
+ EXT4_I(inode)->i_disksize = disksize;
err2 = ext4_mark_inode_dirty(handle, inode);
+ up_write(&EXT4_I(inode)->i_data_sem);
if (err2)
ext4_error(inode->i_sb,
"Failed to mark inode %lu dirty",
@@ -3056,9 +3078,9 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
* 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 uninitialized
+ * For holes, we fallocate those blocks, mark them as unwritten
* If those blocks were preallocated, we mark sure they are split, but
- * still keep the range to write as uninitialized.
+ * still keep the range to write as unwritten.
*
* The unwritten extents will be converted to written when DIO is completed.
* For async direct IO, since the IO may still pending when return, we
@@ -3110,12 +3132,12 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
* We could direct write to holes and fallocate.
*
* Allocated blocks to fill the hole are marked as
- * uninitialized to prevent parallel buffered read to expose
+ * unwritten to prevent parallel buffered read to expose
* the stale data before DIO complete the data IO.
*
* As to previously fallocated extents, ext4 get_block will
* just simply mark the buffer mapped but still keep the
- * extents uninitialized.
+ * extents unwritten.
*
* For non AIO case, we will convert those unwritten extents
* to written after return back from blockdev_direct_IO.
@@ -3426,7 +3448,7 @@ unlock:
* This required during truncate. We need to physically zero the tail end
* of that block so it doesn't yield old data if the file is later grown.
*/
-int ext4_block_truncate_page(handle_t *handle,
+static int ext4_block_truncate_page(handle_t *handle,
struct address_space *mapping, loff_t from)
{
unsigned offset = from & (PAGE_CACHE_SIZE-1);
@@ -3527,15 +3549,6 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
}
mutex_lock(&inode->i_mutex);
- /* It's not possible punch hole on append only file */
- if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
- ret = -EPERM;
- goto out_mutex;
- }
- if (IS_SWAPFILE(inode)) {
- ret = -ETXTBSY;
- goto out_mutex;
- }
/* No need to punch hole beyond i_size */
if (offset >= inode->i_size)
@@ -3616,7 +3629,6 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
ret = ext4_free_hole_blocks(handle, inode, first_block,
stop_block);
- ext4_discard_preallocations(inode);
up_write(&EXT4_I(inode)->i_data_sem);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
@@ -4300,12 +4312,15 @@ static int ext4_do_update_inode(handle_t *handle,
struct ext4_inode *raw_inode = ext4_raw_inode(iloc);
struct ext4_inode_info *ei = EXT4_I(inode);
struct buffer_head *bh = iloc->bh;
+ struct super_block *sb = inode->i_sb;
int err = 0, rc, block;
- int need_datasync = 0;
+ int need_datasync = 0, set_large_file = 0;
uid_t i_uid;
gid_t i_gid;
- /* For fields not not tracking in the in-memory inode,
+ spin_lock(&ei->i_raw_lock);
+
+ /* For fields not tracked in the in-memory inode,
* initialise them to zero for new inodes. */
if (ext4_test_inode_state(inode, EXT4_STATE_NEW))
memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
@@ -4343,8 +4358,10 @@ static int ext4_do_update_inode(handle_t *handle,
EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode);
- if (ext4_inode_blocks_set(handle, raw_inode, ei))
+ if (ext4_inode_blocks_set(handle, raw_inode, ei)) {
+ spin_unlock(&ei->i_raw_lock);
goto out_brelse;
+ }
raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF);
if (likely(!test_opt2(inode->i_sb, HURD_COMPAT)))
@@ -4356,24 +4373,11 @@ static int ext4_do_update_inode(handle_t *handle,
need_datasync = 1;
}
if (ei->i_disksize > 0x7fffffffULL) {
- struct super_block *sb = inode->i_sb;
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_LARGE_FILE) ||
EXT4_SB(sb)->s_es->s_rev_level ==
- cpu_to_le32(EXT4_GOOD_OLD_REV)) {
- /* If this is the first large file
- * created, add a flag to the superblock.
- */
- err = ext4_journal_get_write_access(handle,
- EXT4_SB(sb)->s_sbh);
- if (err)
- goto out_brelse;
- ext4_update_dynamic_rev(sb);
- EXT4_SET_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
- ext4_handle_sync(handle);
- err = ext4_handle_dirty_super(handle, sb);
- }
+ cpu_to_le32(EXT4_GOOD_OLD_REV))
+ set_large_file = 1;
}
raw_inode->i_generation = cpu_to_le32(inode->i_generation);
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
@@ -4405,12 +4409,24 @@ static int ext4_do_update_inode(handle_t *handle,
ext4_inode_csum_set(inode, raw_inode, ei);
+ spin_unlock(&ei->i_raw_lock);
+
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
rc = ext4_handle_dirty_metadata(handle, NULL, bh);
if (!err)
err = rc;
ext4_clear_inode_state(inode, EXT4_STATE_NEW);
-
+ if (set_large_file) {
+ BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access");
+ err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
+ if (err)
+ goto out_brelse;
+ ext4_update_dynamic_rev(sb);
+ EXT4_SET_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
+ ext4_handle_sync(handle);
+ err = ext4_handle_dirty_super(handle, sb);
+ }
ext4_update_inode_fsync_trans(handle, inode, need_datasync);
out_brelse:
brelse(bh);
@@ -4423,21 +4439,20 @@ out_brelse:
*
* We are called from a few places:
*
- * - Within generic_file_write() for O_SYNC files.
+ * - Within generic_file_aio_write() -> generic_write_sync() for O_SYNC files.
* Here, there will be no transaction running. We wait for any running
* transaction to commit.
*
- * - Within sys_sync(), kupdate and such.
- * We wait on commit, if tol to.
+ * - Within flush work (sys_sync(), kupdate and such).
+ * We wait on commit, if told to.
*
- * - Within prune_icache() (PF_MEMALLOC == true)
- * Here we simply return. We can't afford to block kswapd on the
- * journal commit.
+ * - Within iput_final() -> write_inode_now()
+ * We wait on commit, if told to.
*
* In all cases it is actually safe for us to return without doing anything,
* because the inode has been copied into a raw inode buffer in
- * ext4_mark_inode_dirty(). This is a correctness thing for O_SYNC and for
- * knfsd.
+ * ext4_mark_inode_dirty(). This is a correctness thing for WB_SYNC_ALL
+ * writeback.
*
* Note that we are absolutely dependent upon all inode dirtiers doing the
* right thing: they *must* call mark_inode_dirty() after dirtying info in
@@ -4449,15 +4464,15 @@ out_brelse:
* stuff();
* inode->i_size = expr;
*
- * is in error because a kswapd-driven write_inode() could occur while
- * `stuff()' is running, and the new i_size will be lost. Plus the inode
- * will no longer be on the superblock's dirty inode list.
+ * is in error because write_inode() could occur while `stuff()' is running,
+ * and the new i_size will be lost. Plus the inode will no longer be on the
+ * superblock's dirty inode list.
*/
int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
{
int err;
- if (current->flags & PF_MEMALLOC)
+ if (WARN_ON_ONCE(current->flags & PF_MEMALLOC))
return 0;
if (EXT4_SB(inode->i_sb)->s_journal) {
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index a888cac76e9c..59e31622cc6e 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -989,7 +989,7 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
poff = block % blocks_per_page;
page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
if (!page)
- return -EIO;
+ return -ENOMEM;
BUG_ON(page->mapping != inode->i_mapping);
e4b->bd_bitmap_page = page;
e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize);
@@ -1003,7 +1003,7 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
pnum = block / blocks_per_page;
page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
if (!page)
- return -EIO;
+ return -ENOMEM;
BUG_ON(page->mapping != inode->i_mapping);
e4b->bd_buddy_page = page;
return 0;
@@ -1044,6 +1044,8 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
* allocating. If we are looking at the buddy cache we would
* have taken a reference using ext4_mb_load_buddy and that
* would have pinned buddy page to page cache.
+ * The call to ext4_mb_get_buddy_page_lock will mark the
+ * page accessed.
*/
ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b);
if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) {
@@ -1062,7 +1064,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
ret = -EIO;
goto err;
}
- mark_page_accessed(page);
if (e4b.bd_buddy_page == NULL) {
/*
@@ -1082,7 +1083,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
ret = -EIO;
goto err;
}
- mark_page_accessed(page);
err:
ext4_mb_put_buddy_page_lock(&e4b);
return ret;
@@ -1141,7 +1141,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
/* we could use find_or_create_page(), but it locks page
* what we'd like to avoid in fast path ... */
- page = find_get_page(inode->i_mapping, pnum);
+ page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED);
if (page == NULL || !PageUptodate(page)) {
if (page)
/*
@@ -1168,19 +1168,24 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
unlock_page(page);
}
}
- if (page == NULL || !PageUptodate(page)) {
+ if (page == NULL) {
+ ret = -ENOMEM;
+ goto err;
+ }
+ if (!PageUptodate(page)) {
ret = -EIO;
goto err;
}
+
+ /* Pages marked accessed already */
e4b->bd_bitmap_page = page;
e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize);
- mark_page_accessed(page);
block++;
pnum = block / blocks_per_page;
poff = block % blocks_per_page;
- page = find_get_page(inode->i_mapping, pnum);
+ page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED);
if (page == NULL || !PageUptodate(page)) {
if (page)
page_cache_release(page);
@@ -1197,13 +1202,18 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
unlock_page(page);
}
}
- if (page == NULL || !PageUptodate(page)) {
+ if (page == NULL) {
+ ret = -ENOMEM;
+ goto err;
+ }
+ if (!PageUptodate(page)) {
ret = -EIO;
goto err;
}
+
+ /* Pages marked accessed already */
e4b->bd_buddy_page = page;
e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize);
- mark_page_accessed(page);
BUG_ON(e4b->bd_bitmap_page == NULL);
BUG_ON(e4b->bd_buddy_page == NULL);
@@ -2609,7 +2619,7 @@ int ext4_mb_init(struct super_block *sb)
sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
if (sbi->s_locality_groups == NULL) {
ret = -ENOMEM;
- goto out_free_groupinfo_slab;
+ goto out;
}
for_each_possible_cpu(i) {
struct ext4_locality_group *lg;
@@ -2634,8 +2644,6 @@ int ext4_mb_init(struct super_block *sb)
out_free_locality_groups:
free_percpu(sbi->s_locality_groups);
sbi->s_locality_groups = NULL;
-out_free_groupinfo_slab:
- ext4_groupinfo_destroy_slabs();
out:
kfree(sbi->s_mb_offsets);
sbi->s_mb_offsets = NULL;
@@ -2868,6 +2876,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
if (!bitmap_bh)
goto out_err;
+ BUFFER_TRACE(bitmap_bh, "getting write access");
err = ext4_journal_get_write_access(handle, bitmap_bh);
if (err)
goto out_err;
@@ -2880,6 +2889,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group,
ext4_free_group_clusters(sb, gdp));
+ BUFFER_TRACE(gdp_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, gdp_bh);
if (err)
goto out_err;
@@ -3137,7 +3147,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
}
BUG_ON(start + size <= ac->ac_o_ex.fe_logical &&
start > ac->ac_o_ex.fe_logical);
- BUG_ON(size <= 0 || size > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb));
+ BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
/* now prepare goal request */
@@ -5008,6 +5018,8 @@ error_return:
*/
static int ext4_trim_extent(struct super_block *sb, int start, int count,
ext4_group_t group, struct ext4_buddy *e4b)
+__releases(bitlock)
+__acquires(bitlock)
{
struct ext4_free_extent ex;
int ret = 0;
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index 2ae73a80c19b..ec092437d3e0 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -505,7 +505,7 @@ int ext4_ext_migrate(struct inode *inode)
* with i_data_sem held to prevent racing with block
* allocation.
*/
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
ext4_set_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
up_read((&EXT4_I(inode)->i_data_sem));
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 04434ad3e8e0..32bce844c2e1 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -18,7 +18,7 @@ static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp)
return cpu_to_le32(csum);
}
-int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
+static int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
{
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
@@ -27,7 +27,7 @@ int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
return mmp->mmp_checksum == ext4_mmp_csum(sb, mmp);
}
-void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp)
+static void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp)
{
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 58ee7dc87669..2484c7ec6a72 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -57,8 +57,8 @@ get_ext_path(struct inode *inode, ext4_lblk_t lblock,
static void
copy_extent_status(struct ext4_extent *src, struct ext4_extent *dest)
{
- if (ext4_ext_is_uninitialized(src))
- ext4_ext_mark_uninitialized(dest);
+ if (ext4_ext_is_unwritten(src))
+ ext4_ext_mark_unwritten(dest);
else
dest->ee_len = cpu_to_le16(ext4_ext_get_actual_len(dest));
}
@@ -391,6 +391,7 @@ mext_insert_extents(handle_t *handle, struct inode *orig_inode,
if (depth) {
/* Register to journal */
+ BUFFER_TRACE(orig_path->p_bh, "get_write_access");
ret = ext4_journal_get_write_access(handle, orig_path->p_bh);
if (ret)
return ret;
@@ -593,14 +594,14 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext,
* @inode: inode in question
* @from: block offset of inode
* @count: block count to be checked
- * @uninit: extents expected to be uninitialized
+ * @unwritten: extents expected to be unwritten
* @err: pointer to save error value
*
* Return 1 if all extents in range has expected type, and zero otherwise.
*/
static int
mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count,
- int uninit, int *err)
+ int unwritten, int *err)
{
struct ext4_ext_path *path = NULL;
struct ext4_extent *ext;
@@ -611,7 +612,7 @@ mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count,
if (*err)
goto out;
ext = path[ext_depth(inode)].p_ext;
- if (uninit != ext4_ext_is_uninitialized(ext))
+ if (unwritten != ext4_ext_is_unwritten(ext))
goto out;
from += ext4_ext_get_actual_len(ext);
ext4_ext_drop_refs(path);
@@ -894,7 +895,7 @@ out:
* @orig_page_offset: page index on original file
* @data_offset_in_page: block index where data swapping starts
* @block_len_in_page: the number of blocks to be swapped
- * @uninit: orig extent is uninitialized or not
+ * @unwritten: orig extent is unwritten or not
* @err: pointer to save return value
*
* Save the data in original inode blocks and replace original inode extents
@@ -905,7 +906,7 @@ out:
static int
move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
pgoff_t orig_page_offset, int data_offset_in_page,
- int block_len_in_page, int uninit, int *err)
+ int block_len_in_page, int unwritten, int *err)
{
struct inode *orig_inode = file_inode(o_filp);
struct page *pagep[2] = {NULL, NULL};
@@ -962,27 +963,27 @@ again:
if (unlikely(*err < 0))
goto stop_journal;
/*
- * If orig extent was uninitialized it can become initialized
+ * If orig extent was unwritten it can become initialized
* at any time after i_data_sem was dropped, in order to
* serialize with delalloc we have recheck extent while we
* hold page's lock, if it is still the case data copy is not
* necessary, just swap data blocks between orig and donor.
*/
- if (uninit) {
+ if (unwritten) {
ext4_double_down_write_data_sem(orig_inode, donor_inode);
/* If any of extents in range became initialized we have to
* fallback to data copying */
- uninit = mext_check_coverage(orig_inode, orig_blk_offset,
- block_len_in_page, 1, err);
+ unwritten = mext_check_coverage(orig_inode, orig_blk_offset,
+ block_len_in_page, 1, err);
if (*err)
goto drop_data_sem;
- uninit &= mext_check_coverage(donor_inode, orig_blk_offset,
- block_len_in_page, 1, err);
+ unwritten &= mext_check_coverage(donor_inode, orig_blk_offset,
+ block_len_in_page, 1, err);
if (*err)
goto drop_data_sem;
- if (!uninit) {
+ if (!unwritten) {
ext4_double_up_write_data_sem(orig_inode, donor_inode);
goto data_copy;
}
@@ -1259,7 +1260,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
int data_offset_in_page;
int block_len_in_page;
- int uninit;
+ int unwritten;
if (orig_inode->i_sb != donor_inode->i_sb) {
ext4_debug("ext4 move extent: The argument files "
@@ -1391,8 +1392,8 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
!last_extent)
continue;
- /* Is original extent is uninitialized */
- uninit = ext4_ext_is_uninitialized(ext_prev);
+ /* Is original extent is unwritten */
+ unwritten = ext4_ext_is_unwritten(ext_prev);
data_offset_in_page = seq_start % blocks_per_page;
@@ -1432,8 +1433,8 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
o_filp, donor_inode,
orig_page_offset,
data_offset_in_page,
- block_len_in_page, uninit,
- &ret);
+ block_len_in_page,
+ unwritten, &ret);
/* Count how many blocks we have exchanged */
*moved_len += block_len_in_page;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 1cb84f78909e..3520ab8a6639 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -67,6 +67,7 @@ static struct buffer_head *ext4_append(handle_t *handle,
return ERR_PTR(err);
inode->i_size += inode->i_sb->s_blocksize;
EXT4_I(inode)->i_disksize = inode->i_size;
+ BUFFER_TRACE(bh, "get_write_access");
err = ext4_journal_get_write_access(handle, bh);
if (err) {
brelse(bh);
@@ -1778,6 +1779,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
blocksize = dir->i_sb->s_blocksize;
dxtrace(printk(KERN_DEBUG "Creating index: inode %lu\n", dir->i_ino));
+ BUFFER_TRACE(bh, "get_write_access");
retval = ext4_journal_get_write_access(handle, bh);
if (retval) {
ext4_std_error(dir->i_sb, retval);
@@ -2510,8 +2512,7 @@ static int empty_dir(struct inode *inode)
ext4_rec_len_from_disk(de1->rec_len, sb->s_blocksize);
de = ext4_next_entry(de1, sb->s_blocksize);
while (offset < inode->i_size) {
- if (!bh ||
- (void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
+ if ((void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
unsigned int lblock;
err = 0;
brelse(bh);
@@ -2539,26 +2540,37 @@ static int empty_dir(struct inode *inode)
return 1;
}
-/* ext4_orphan_add() links an unlinked or truncated inode into a list of
+/*
+ * ext4_orphan_add() links an unlinked or truncated inode into a list of
* such inodes, starting at the superblock, in case we crash before the
* file is closed/deleted, or in case the inode truncate spans multiple
* transactions and the last transaction is not recovered after a crash.
*
* At filesystem recovery time, we walk this list deleting unlinked
* inodes and truncating linked inodes in ext4_orphan_cleanup().
+ *
+ * Orphan list manipulation functions must be called under i_mutex unless
+ * we are just creating the inode or deleting it.
*/
int ext4_orphan_add(handle_t *handle, struct inode *inode)
{
struct super_block *sb = inode->i_sb;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_iloc iloc;
int err = 0, rc;
+ bool dirty = false;
- if (!EXT4_SB(sb)->s_journal)
+ if (!sbi->s_journal)
return 0;
- mutex_lock(&EXT4_SB(sb)->s_orphan_lock);
+ WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) &&
+ !mutex_is_locked(&inode->i_mutex));
+ /*
+ * Exit early if inode already is on orphan list. This is a big speedup
+ * since we don't have to contend on the global s_orphan_lock.
+ */
if (!list_empty(&EXT4_I(inode)->i_orphan))
- goto out_unlock;
+ return 0;
/*
* Orphan handling is only valid for files with data blocks
@@ -2569,48 +2581,51 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
- BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
- err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
+ BUFFER_TRACE(sbi->s_sbh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
- goto out_unlock;
+ goto out;
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
- goto out_unlock;
+ goto out;
+
+ mutex_lock(&sbi->s_orphan_lock);
/*
* Due to previous errors inode may be already a part of on-disk
* orphan list. If so skip on-disk list modification.
*/
- if (NEXT_ORPHAN(inode) && NEXT_ORPHAN(inode) <=
- (le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)))
- goto mem_insert;
-
- /* Insert this inode at the head of the on-disk orphan list... */
- NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan);
- EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
- err = ext4_handle_dirty_super(handle, sb);
- rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
- if (!err)
- err = rc;
-
- /* Only add to the head of the in-memory list if all the
- * previous operations succeeded. If the orphan_add is going to
- * fail (possibly taking the journal offline), we can't risk
- * leaving the inode on the orphan list: stray orphan-list
- * entries can cause panics at unmount time.
- *
- * This is safe: on error we're going to ignore the orphan list
- * anyway on the next recovery. */
-mem_insert:
- if (!err)
- list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
-
+ if (!NEXT_ORPHAN(inode) || NEXT_ORPHAN(inode) >
+ (le32_to_cpu(sbi->s_es->s_inodes_count))) {
+ /* Insert this inode at the head of the on-disk orphan list */
+ NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan);
+ sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
+ dirty = true;
+ }
+ list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan);
+ mutex_unlock(&sbi->s_orphan_lock);
+
+ if (dirty) {
+ err = ext4_handle_dirty_super(handle, sb);
+ rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
+ if (!err)
+ err = rc;
+ if (err) {
+ /*
+ * We have to remove inode from in-memory list if
+ * addition to on disk orphan list failed. Stray orphan
+ * list entries can cause panics at unmount time.
+ */
+ mutex_lock(&sbi->s_orphan_lock);
+ list_del(&EXT4_I(inode)->i_orphan);
+ mutex_unlock(&sbi->s_orphan_lock);
+ }
+ }
jbd_debug(4, "superblock will point to %lu\n", inode->i_ino);
jbd_debug(4, "orphan inode %lu will point to %d\n",
inode->i_ino, NEXT_ORPHAN(inode));
-out_unlock:
- mutex_unlock(&EXT4_SB(sb)->s_orphan_lock);
- ext4_std_error(inode->i_sb, err);
+out:
+ ext4_std_error(sb, err);
return err;
}
@@ -2622,45 +2637,51 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
{
struct list_head *prev;
struct ext4_inode_info *ei = EXT4_I(inode);
- struct ext4_sb_info *sbi;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
__u32 ino_next;
struct ext4_iloc iloc;
int err = 0;
- if ((!EXT4_SB(inode->i_sb)->s_journal) &&
- !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS))
+ if (!sbi->s_journal && !(sbi->s_mount_state & EXT4_ORPHAN_FS))
return 0;
- mutex_lock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
+ WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) &&
+ !mutex_is_locked(&inode->i_mutex));
+ /* Do this quick check before taking global s_orphan_lock. */
if (list_empty(&ei->i_orphan))
- goto out;
+ return 0;
- ino_next = NEXT_ORPHAN(inode);
- prev = ei->i_orphan.prev;
- sbi = EXT4_SB(inode->i_sb);
+ if (handle) {
+ /* Grab inode buffer early before taking global s_orphan_lock */
+ err = ext4_reserve_inode_write(handle, inode, &iloc);
+ }
+ mutex_lock(&sbi->s_orphan_lock);
jbd_debug(4, "remove inode %lu from orphan list\n", inode->i_ino);
+ prev = ei->i_orphan.prev;
list_del_init(&ei->i_orphan);
/* If we're on an error path, we may not have a valid
* transaction handle with which to update the orphan list on
* disk, but we still need to remove the inode from the linked
* list in memory. */
- if (!handle)
- goto out;
-
- err = ext4_reserve_inode_write(handle, inode, &iloc);
- if (err)
+ if (!handle || err) {
+ mutex_unlock(&sbi->s_orphan_lock);
goto out_err;
+ }
+ ino_next = NEXT_ORPHAN(inode);
if (prev == &sbi->s_orphan) {
jbd_debug(4, "superblock will point to %u\n", ino_next);
BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
- if (err)
+ if (err) {
+ mutex_unlock(&sbi->s_orphan_lock);
goto out_brelse;
+ }
sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
+ mutex_unlock(&sbi->s_orphan_lock);
err = ext4_handle_dirty_super(handle, inode->i_sb);
} else {
struct ext4_iloc iloc2;
@@ -2670,20 +2691,20 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
jbd_debug(4, "orphan inode %lu will point to %u\n",
i_prev->i_ino, ino_next);
err = ext4_reserve_inode_write(handle, i_prev, &iloc2);
- if (err)
+ if (err) {
+ mutex_unlock(&sbi->s_orphan_lock);
goto out_brelse;
+ }
NEXT_ORPHAN(i_prev) = ino_next;
err = ext4_mark_iloc_dirty(handle, i_prev, &iloc2);
+ mutex_unlock(&sbi->s_orphan_lock);
}
if (err)
goto out_brelse;
NEXT_ORPHAN(inode) = 0;
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
-
out_err:
ext4_std_error(inode->i_sb, err);
-out:
- mutex_unlock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
return err;
out_brelse:
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index ab95508e3d40..b24a2541a9ba 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -308,13 +308,14 @@ static void ext4_end_bio(struct bio *bio, int error)
if (error) {
struct inode *inode = io_end->inode;
- ext4_warning(inode->i_sb, "I/O error writing to inode %lu "
+ ext4_warning(inode->i_sb, "I/O error %d writing to inode %lu "
"(offset %llu size %ld starting block %llu)",
- inode->i_ino,
+ error, inode->i_ino,
(unsigned long long) io_end->offset,
(long) io_end->size,
(unsigned long long)
bi_sector >> (inode->i_blkbits - 9));
+ mapping_set_error(inode->i_mapping, error);
}
if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
@@ -400,7 +401,8 @@ submit_and_retry:
int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
- struct writeback_control *wbc)
+ struct writeback_control *wbc,
+ bool keep_towrite)
{
struct inode *inode = page->mapping->host;
unsigned block_start, blocksize;
@@ -413,10 +415,24 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
- set_page_writeback(page);
+ if (keep_towrite)
+ set_page_writeback_keepwrite(page);
+ else
+ set_page_writeback(page);
ClearPageError(page);
/*
+ * Comments copied from block_write_full_page:
+ *
+ * The page straddles i_size. It must be zeroed out on each and every
+ * writepage invocation because it may be mmapped. "A file is mapped
+ * in multiples of the page size. For a file that is not a multiple of
+ * the page size, the remaining memory is zeroed when mapped, and
+ * writes to that region are not written out to the file."
+ */
+ if (len < PAGE_CACHE_SIZE)
+ zero_user_segment(page, len, PAGE_CACHE_SIZE);
+ /*
* In the first loop we prepare and mark buffers to submit. We have to
* mark all buffers in the page before submitting so that
* end_page_writeback() cannot be called from ext4_bio_end_io() when IO
@@ -427,19 +443,6 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
do {
block_start = bh_offset(bh);
if (block_start >= len) {
- /*
- * Comments copied from block_write_full_page_endio:
- *
- * The page straddles i_size. It must be zeroed out on
- * each and every writepage invocation because it may
- * be mmapped. "A file is mapped in multiples of the
- * page size. For a file that is not a multiple of
- * the page size, the remaining memory is zeroed when
- * mapped, and writes to that region are not written
- * out to the file."
- */
- zero_user_segment(page, block_start,
- block_start + blocksize);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index f3b84cd9de56..bb0e80f03e2e 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -42,7 +42,7 @@ int ext4_resize_begin(struct super_block *sb)
void ext4_resize_end(struct super_block *sb)
{
clear_bit_unlock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}
static ext4_group_t ext4_meta_bg_first_group(struct super_block *sb,
@@ -348,6 +348,7 @@ static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
bh = sb_getblk(sb, blk);
if (unlikely(!bh))
return ERR_PTR(-ENOMEM);
+ BUFFER_TRACE(bh, "get_write_access");
if ((err = ext4_journal_get_write_access(handle, bh))) {
brelse(bh);
bh = ERR_PTR(err);
@@ -426,6 +427,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle,
if (unlikely(!bh))
return -ENOMEM;
+ BUFFER_TRACE(bh, "get_write_access");
err = ext4_journal_get_write_access(handle, bh);
if (err)
return err;
@@ -518,6 +520,7 @@ static int setup_new_flex_group_blocks(struct super_block *sb,
goto out;
}
+ BUFFER_TRACE(gdb, "get_write_access");
err = ext4_journal_get_write_access(handle, gdb);
if (err) {
brelse(gdb);
@@ -790,14 +793,17 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
goto exit_dind;
}
+ BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
if (unlikely(err))
goto exit_dind;
+ BUFFER_TRACE(gdb_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, gdb_bh);
if (unlikely(err))
goto exit_dind;
+ BUFFER_TRACE(dind, "get_write_access");
err = ext4_journal_get_write_access(handle, dind);
if (unlikely(err))
ext4_std_error(sb, err);
@@ -902,6 +908,7 @@ static int add_new_gdb_meta_bg(struct super_block *sb,
EXT4_SB(sb)->s_group_desc = n_group_desc;
EXT4_SB(sb)->s_gdb_count++;
ext4_kvfree(o_group_desc);
+ BUFFER_TRACE(gdb_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, gdb_bh);
if (unlikely(err))
brelse(gdb_bh);
@@ -977,6 +984,7 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
}
for (i = 0; i < reserved_gdb; i++) {
+ BUFFER_TRACE(primary[i], "get_write_access");
if ((err = ext4_journal_get_write_access(handle, primary[i])))
goto exit_bh;
}
@@ -1084,6 +1092,7 @@ static void update_backups(struct super_block *sb, int blk_off, char *data,
ext4_debug("update metadata backup %llu(+%llu)\n",
backup_block, backup_block -
ext4_group_first_block_no(sb, group));
+ BUFFER_TRACE(bh, "get_write_access");
if ((err = ext4_journal_get_write_access(handle, bh)))
break;
lock_buffer(bh);
@@ -1163,6 +1172,7 @@ static int ext4_add_new_descs(handle_t *handle, struct super_block *sb,
*/
if (gdb_off) {
gdb_bh = sbi->s_group_desc[gdb_num];
+ BUFFER_TRACE(gdb_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, gdb_bh);
if (!err && reserved_gdb && ext4_bg_num_gdb(sb, group))
@@ -1433,6 +1443,7 @@ static int ext4_flex_group_add(struct super_block *sb,
goto exit;
}
+ BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto exit_journal;
@@ -1645,6 +1656,7 @@ static int ext4_group_extend_no_check(struct super_block *sb,
return err;
}
+ BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
if (err) {
ext4_warning(sb, "error %d on journal write access", err);
@@ -1804,6 +1816,7 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode)
if (IS_ERR(handle))
return PTR_ERR(handle);
+ BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto errout;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index f3c667091618..b9b9aabfb4d2 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -138,8 +138,8 @@ static __le32 ext4_superblock_csum(struct super_block *sb,
return cpu_to_le32(csum);
}
-int ext4_superblock_csum_verify(struct super_block *sb,
- struct ext4_super_block *es)
+static int ext4_superblock_csum_verify(struct super_block *sb,
+ struct ext4_super_block *es)
{
if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
@@ -879,6 +879,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
return NULL;
ei->vfs_inode.i_version = 1;
+ spin_lock_init(&ei->i_raw_lock);
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
ext4_es_init_tree(&ei->i_es_tree);
@@ -1903,7 +1904,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
if (!(sbi->s_mount_state & EXT4_VALID_FS))
ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, "
"running e2fsck is recommended");
- else if ((sbi->s_mount_state & EXT4_ERROR_FS))
+ else if (sbi->s_mount_state & EXT4_ERROR_FS)
ext4_msg(sb, KERN_WARNING,
"warning: mounting fs with errors, "
"running e2fsck is recommended");
@@ -2404,6 +2405,16 @@ static ext4_fsblk_t descriptor_loc(struct super_block *sb,
if (ext4_bg_has_super(sb, bg))
has_super = 1;
+ /*
+ * If we have a meta_bg fs with 1k blocks, group 0's GDT is at
+ * block 2, not 1. If s_first_data_block == 0 (bigalloc is enabled
+ * on modern mke2fs or blksize > 1k on older mke2fs) then we must
+ * compensate.
+ */
+ if (sb->s_blocksize == 1024 && nr == 0 &&
+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) == 0)
+ has_super++;
+
return (has_super + ext4_group_first_block_no(sb, bg));
}
@@ -3337,7 +3348,7 @@ static ext4_fsblk_t ext4_calculate_resv_clusters(struct super_block *sb)
* By default we reserve 2% or 4096 clusters, whichever is smaller.
* This should cover the situations where we can not afford to run
* out of space like for example punch hole, or converting
- * uninitialized extents in delalloc path. In most cases such
+ * unwritten extents in delalloc path. In most cases such
* allocation would require 1, or 2 blocks, higher numbers are
* very rare.
*/
@@ -3869,19 +3880,38 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount2;
}
}
+
+ /*
+ * set up enough so that it can read an inode,
+ * and create new inode for buddy allocator
+ */
+ sbi->s_gdb_count = db_count;
+ if (!test_opt(sb, NOLOAD) &&
+ EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
+ sb->s_op = &ext4_sops;
+ else
+ sb->s_op = &ext4_nojournal_sops;
+
+ ext4_ext_init(sb);
+ err = ext4_mb_init(sb);
+ if (err) {
+ ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
+ err);
+ goto failed_mount2;
+ }
+
if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
- goto failed_mount2;
+ goto failed_mount2a;
}
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
if (!ext4_fill_flex_info(sb)) {
ext4_msg(sb, KERN_ERR,
"unable to initialize "
"flex_bg meta info!");
- goto failed_mount2;
+ goto failed_mount2a;
}
- sbi->s_gdb_count = db_count;
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);
@@ -3916,14 +3946,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_stripe = ext4_get_stripe_size(sbi);
sbi->s_extent_max_zeroout_kb = 32;
- /*
- * set up enough so that it can read an inode
- */
- if (!test_opt(sb, NOLOAD) &&
- EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
- sb->s_op = &ext4_sops;
- else
- sb->s_op = &ext4_nojournal_sops;
sb->s_export_op = &ext4_export_ops;
sb->s_xattr = ext4_xattr_handlers;
#ifdef CONFIG_QUOTA
@@ -4113,21 +4135,13 @@ no_journal:
if (err) {
ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for "
"reserved pool", ext4_calculate_resv_clusters(sb));
- goto failed_mount4a;
+ goto failed_mount5;
}
err = ext4_setup_system_zone(sb);
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize system "
"zone (%d)", err);
- goto failed_mount4a;
- }
-
- ext4_ext_init(sb);
- err = ext4_mb_init(sb);
- if (err) {
- ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
- err);
goto failed_mount5;
}
@@ -4204,11 +4218,8 @@ failed_mount8:
failed_mount7:
ext4_unregister_li_request(sb);
failed_mount6:
- ext4_mb_release(sb);
-failed_mount5:
- ext4_ext_release(sb);
ext4_release_system_zone(sb);
-failed_mount4a:
+failed_mount5:
dput(sb->s_root);
sb->s_root = NULL;
failed_mount4:
@@ -4232,11 +4243,14 @@ failed_mount3:
percpu_counter_destroy(&sbi->s_extent_cache_cnt);
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
+failed_mount2a:
+ ext4_mb_release(sb);
failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
ext4_kvfree(sbi->s_group_desc);
failed_mount:
+ ext4_ext_release(sb);
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
if (sbi->s_proc) {
@@ -5367,6 +5381,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
bh = ext4_bread(handle, inode, blk, 1, &err);
if (!bh)
goto out;
+ BUFFER_TRACE(bh, "get write access");
err = ext4_journal_get_write_access(handle, bh);
if (err) {
brelse(bh);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 1f5cf5880718..e7387337060c 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -369,6 +369,9 @@ ext4_xattr_get(struct inode *inode, int name_index, const char *name,
{
int error;
+ if (strlen(name) > 255)
+ return -ERANGE;
+
down_read(&EXT4_I(inode)->xattr_sem);
error = ext4_xattr_ibody_get(inode, name_index, name, buffer,
buffer_size);
@@ -513,6 +516,7 @@ static void ext4_xattr_update_super_block(handle_t *handle,
if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR))
return;
+ BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR);
ext4_handle_dirty_super(handle, sb);
@@ -520,8 +524,8 @@ static void ext4_xattr_update_super_block(handle_t *handle,
}
/*
- * Release the xattr block BH: If the reference count is > 1, decrement
- * it; otherwise free the block.
+ * Release the xattr block BH: If the reference count is > 1, decrement it;
+ * otherwise free the block.
*/
static void
ext4_xattr_release_block(handle_t *handle, struct inode *inode,
@@ -532,6 +536,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
ce = mb_cache_entry_get(ext4_mb_cache, bh->b_bdev, bh->b_blocknr);
+ BUFFER_TRACE(bh, "get_write_access");
error = ext4_journal_get_write_access(handle, bh);
if (error)
goto out;
@@ -542,16 +547,31 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
if (ce)
mb_cache_entry_free(ce);
get_bh(bh);
+ unlock_buffer(bh);
ext4_free_blocks(handle, inode, bh, 0, 1,
EXT4_FREE_BLOCKS_METADATA |
EXT4_FREE_BLOCKS_FORGET);
- unlock_buffer(bh);
} else {
le32_add_cpu(&BHDR(bh)->h_refcount, -1);
if (ce)
mb_cache_entry_release(ce);
+ /*
+ * Beware of this ugliness: Releasing of xattr block references
+ * from different inodes can race and so we have to protect
+ * from a race where someone else frees the block (and releases
+ * its journal_head) before we are done dirtying the buffer. In
+ * nojournal mode this race is harmless and we actually cannot
+ * call ext4_handle_dirty_xattr_block() with locked buffer as
+ * that function can call sync_dirty_buffer() so for that case
+ * we handle the dirtying after unlocking the buffer.
+ */
+ if (ext4_handle_valid(handle))
+ error = ext4_handle_dirty_xattr_block(handle, inode,
+ bh);
unlock_buffer(bh);
- error = ext4_handle_dirty_xattr_block(handle, inode, bh);
+ if (!ext4_handle_valid(handle))
+ error = ext4_handle_dirty_xattr_block(handle, inode,
+ bh);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1));
@@ -759,6 +779,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
if (s->base) {
ce = mb_cache_entry_get(ext4_mb_cache, bs->bh->b_bdev,
bs->bh->b_blocknr);
+ BUFFER_TRACE(bs->bh, "get_write_access");
error = ext4_journal_get_write_access(handle, bs->bh);
if (error)
goto cleanup;
@@ -844,6 +865,7 @@ inserted:
EXT4_C2B(EXT4_SB(sb), 1));
if (error)
goto cleanup;
+ BUFFER_TRACE(new_bh, "get_write_access");
error = ext4_journal_get_write_access(handle,
new_bh);
if (error)
@@ -881,7 +903,7 @@ inserted:
* take i_data_sem because we will test
* i_delalloc_reserved_flag in ext4_mb_new_blocks
*/
- down_read((&EXT4_I(inode)->i_data_sem));
+ down_read(&EXT4_I(inode)->i_data_sem);
block = ext4_new_meta_blocks(handle, inode, goal, 0,
NULL, &error);
up_read((&EXT4_I(inode)->i_data_sem));
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-29 21:16:09 +0100