summaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/balloc.c66
-rw-r--r--fs/ext4/dir.c3
-rw-r--r--fs/ext4/ext4.h35
-rw-r--r--fs/ext4/ext4_jbd2.c7
-rw-r--r--fs/ext4/ext4_jbd2.h4
-rw-r--r--fs/ext4/extents.c14
-rw-r--r--fs/ext4/extents_status.c8
-rw-r--r--fs/ext4/file.c3
-rw-r--r--fs/ext4/inline.c15
-rw-r--r--fs/ext4/inode.c65
-rw-r--r--fs/ext4/mballoc.c22
-rw-r--r--fs/ext4/migrate.c2
-rw-r--r--fs/ext4/mmp.c4
-rw-r--r--fs/ext4/move_extent.c1
-rw-r--r--fs/ext4/namei.c131
-rw-r--r--fs/ext4/page-io.c32
-rw-r--r--fs/ext4/resize.c15
-rw-r--r--fs/ext4/super.c18
-rw-r--r--fs/ext4/xattr.c9
19 files changed, 263 insertions, 191 deletions
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 5c56785007e..0762d143e25 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);
@@ -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 d638c57e996..ef1bed66c14 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 eb37d76bf91..7cc5a0e2368 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -875,6 +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.
@@ -1158,7 +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) */
};
@@ -1504,6 +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
@@ -1952,10 +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,
@@ -1984,16 +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 */
@@ -2136,8 +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);
@@ -2196,8 +2187,6 @@ 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);
@@ -2569,19 +2558,11 @@ 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);
@@ -2769,13 +2750,11 @@ 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.
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index c3fb607413e..0074e0d23d6 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 81cfefa9dc0..17c00ff202f 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 e305a31641f..4da228a0e6d 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -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 */
@@ -4018,7 +4019,7 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
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)
@@ -4036,7 +4037,7 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
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) {
@@ -4475,7 +4476,7 @@ got_allocated_blocks:
* 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;
}
@@ -4740,6 +4741,13 @@ static long ext4_zero_range(struct file *file, loff_t offset,
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.
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 98c90f5834e..3f5c188953a 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;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 708aad76819..8695f70af1e 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);
@@ -237,6 +237,7 @@ 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 82edf5b9335..645205d8ada 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 b2cee73c143..8a064734e6e 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);
@@ -555,7 +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);
@@ -627,7 +630,7 @@ found:
* 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
@@ -922,6 +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);
@@ -1540,7 +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;
}
@@ -1577,7 +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
@@ -1769,6 +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);
@@ -1846,6 +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);
@@ -1876,6 +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))
@@ -1892,7 +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);
@@ -1911,7 +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++;
@@ -3439,7 +3446,7 @@ 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);
@@ -4303,12 +4310,15 @@ 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);
@@ -4346,8 +4356,10 @@ 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)))
@@ -4359,24 +4371,11 @@ 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)) {
@@ -4408,12 +4407,24 @@ 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);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index c8238a26818..59e31622cc6 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -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)
/*
@@ -1176,15 +1176,16 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
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);
@@ -1209,9 +1210,10 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
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);
@@ -2617,7 +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;
@@ -2642,8 +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;
@@ -2876,6 +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;
@@ -2888,6 +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;
@@ -3145,7 +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 */
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index 2ae73a80c19..ec092437d3e 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 04434ad3e8e..32bce844c2e 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 1b809fe51da..2484c7ec6a7 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -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;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 1cb84f78909..3520ab8a663 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 c18d95b5054..b24a2541a9b 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -401,7 +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;
@@ -414,10 +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
@@ -428,19 +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 f3b84cd9de5..bb0e80f03e2 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 c4895c195e0..b9b9aabfb4d 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));
}
@@ -5370,6 +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 4eec399ec80..e7387337060 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);
@@ -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;
@@ -774,6 +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;
@@ -859,6 +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)
@@ -896,7 +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 v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-01 05:44:44 +0000