davidlt/kernel-ark
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

A lot of bug fixes and cleanups for ext4, including:

Browse Source 
* Fix performance problems found in dioread_nolock now that it is the
   default, caused by transaction leaks.
 * Clean up fiemap handling in ext4
 * Clean up and refactor multiple block allocator (mballoc) code
 * Fix a problem with mballoc with a smaller file systems running out
   of blocks because they couldn't properly use blocks that had been
   reserved by inode preallocation.
 * Fixed a race in ext4_sync_parent() versus rename()
 * Simplify the error handling in the extent manipulation code
 * Make sure all metadata I/O errors are felected to ext4_ext_dirty()'s and
   ext4_make_inode_dirty()'s callers.
 * Avoid passing an error pointer to brelse in ext4_xattr_set()
 * Fix race which could result to freeing an inode on the dirty last
   in data=journal mode.
 * Fix refcount handling if ext4_iget() fails
 * Fix a crash in generic/019 caused by a corrupted extent node
 -----BEGIN PGP SIGNATURE-----
 
 iQEyBAABCAAdFiEEK2m5VNv+CHkogTfJ8vlZVpUNgaMFAl7Ze8kACgkQ8vlZVpUN
 gaNChAf4xn0ytFSrweI/S2Sp05G/2L/ocZ2TZZk2ZdGeN1E+ABdSIv/zIF9zuFgZ
 /pY/C+fyEZWt4E3FlNO8gJzoEedkzMCMnUhSIfI+wZbcclyTOSNMJtnrnJKAEtVH
 HOvGZJmg357jy407RCGhZpJ773nwU2xhBTr5OFxvSf9mt/vzebxIOnw5D7HPlC1V
 Fgm6Du8q+tRrPsyjv1Yu4pUEVXMJ7qUcvt326AXVM3kCZO1Aa5GrURX0w3J4mzW1
 tc1tKmtbLcVVYTo9CwHXhk/edbxrhAydSP2iACand3tK6IJuI6j9x+bBJnxXitnr
 vsxsfTYMG18+2SxrJ9LwmagqmrRq
 =HMTs
 -----END PGP SIGNATURE-----

Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "A lot of bug fixes and cleanups for ext4, including:

   - Fix performance problems found in dioread_nolock now that it is the
     default, caused by transaction leaks.

   - Clean up fiemap handling in ext4

   - Clean up and refactor multiple block allocator (mballoc) code

   - Fix a problem with mballoc with a smaller file systems running out
     of blocks because they couldn't properly use blocks that had been
     reserved by inode preallocation.

   - Fixed a race in ext4_sync_parent() versus rename()

   - Simplify the error handling in the extent manipulation code

   - Make sure all metadata I/O errors are felected to
     ext4_ext_dirty()'s and ext4_make_inode_dirty()'s callers.

   - Avoid passing an error pointer to brelse in ext4_xattr_set()

   - Fix race which could result to freeing an inode on the dirty last
     in data=journal mode.

   - Fix refcount handling if ext4_iget() fails

   - Fix a crash in generic/019 caused by a corrupted extent node"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (58 commits)
  ext4: avoid unnecessary transaction starts during writeback
  ext4: don't block for O_DIRECT if IOCB_NOWAIT is set
  ext4: remove the access_ok() check in ext4_ioctl_get_es_cache
  fs: remove the access_ok() check in ioctl_fiemap
  fs: handle FIEMAP_FLAG_SYNC in fiemap_prep
  fs: move fiemap range validation into the file systems instances
  iomap: fix the iomap_fiemap prototype
  fs: move the fiemap definitions out of fs.h
  fs: mark __generic_block_fiemap static
  ext4: remove the call to fiemap_check_flags in ext4_fiemap
  ext4: split _ext4_fiemap
  ext4: fix fiemap size checks for bitmap files
  ext4: fix EXT4_MAX_LOGICAL_BLOCK macro
  add comment for ext4_dir_entry_2 file_type member
  jbd2: avoid leaking transaction credits when unreserving handle
  ext4: drop ext4_journal_free_reserved()
  ext4: mballoc: use lock for checking free blocks while retrying
  ext4: mballoc: refactor ext4_mb_good_group()
  ext4: mballoc: introduce pcpu seqcnt for freeing PA to improve ENOSPC handling
  ext4: mballoc: refactor ext4_mb_discard_preallocations()
  ...
This commit is contained in:
Linus Torvalds 2020-06-05 16:19:28 -07:00
commit 0b166a57e6
47 changed files with 906 additions and 664 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
Documentation/filesystems/fiemap.rst
View File

@ -206,16 +206,18 @@ EINTR once fatal signal received.
Flag checking should be done at the beginning of the ->fiemap callback via the
fiemap_check_flags() helper::
fiemap_prep() helper::
int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 *len, u32 supported_flags);
The struct fieinfo should be passed in as received from ioctl_fiemap(). The
set of fiemap flags which the fs understands should be passed via fs_flags. If
fiemap_check_flags finds invalid user flags, it will place the bad values in
fiemap_prep finds invalid user flags, it will place the bad values in
fieinfo->fi_flags and return -EBADR. If the file system gets -EBADR, from
fiemap_check_flags(), it should immediately exit, returning that error back to
ioctl_fiemap().
fiemap_prep(), it should immediately exit, returning that error back to
ioctl_fiemap(). Additionally the range is validate against the supported
maximum file size.
For each extent in the request range, the file system should call

1
fs/bad_inode.c
View File

@ -15,6 +15,7 @@
#include <linux/time.h>
#include <linux/namei.h>
#include <linux/poll.h>
#include <linux/fiemap.h>
static int bad_file_open(struct inode *inode, struct file *filp)
{

1
fs/btrfs/extent_io.h
View File

@ -5,6 +5,7 @@
#include <linux/rbtree.h>
#include <linux/refcount.h>
#include <linux/fiemap.h>
#include "ulist.h"
/*

4
fs/btrfs/inode.c
View File

@ -7828,14 +7828,12 @@ const struct iomap_dio_ops btrfs_dops = {
.submit_io = btrfs_submit_direct,
};
#define BTRFS_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC)
static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len)
{
int ret;
ret = fiemap_check_flags(fieinfo, BTRFS_FIEMAP_FLAGS);
ret = fiemap_prep(inode, fieinfo, start, &len, 0);
if (ret)
return ret;

1
fs/cifs/inode.c
View File

@ -25,6 +25,7 @@
#include <linux/freezer.h>
#include <linux/sched/signal.h>
#include <linux/wait_bit.h>
#include <linux/fiemap.h>
#include <asm/div64.h>
#include "cifsfs.h"

6
fs/cifs/smb2ops.c
View File

@ -12,6 +12,7 @@
#include <linux/uuid.h>
#include <linux/sort.h>
#include <crypto/aead.h>
#include <linux/fiemap.h>
#include "cifsfs.h"
#include "cifsglob.h"
#include "smb2pdu.h"
@ -3407,8 +3408,9 @@ static int smb3_fiemap(struct cifs_tcon *tcon,
int i, num, rc, flags, last_blob;
u64 next;
if (fiemap_check_flags(fei, FIEMAP_FLAG_SYNC))
return -EBADR;
rc = fiemap_prep(d_inode(cfile->dentry), fei, start, &len, 0);
if (rc)
return rc;
xid = get_xid();
again:

1
fs/ext2/inode.c
View File

@ -36,6 +36,7 @@
#include <linux/iomap.h>
#include <linux/namei.h>
#include <linux/uio.h>
#include <linux/fiemap.h>
#include "ext2.h"
#include "acl.h"
#include "xattr.h"

3
fs/ext4/Kconfig
View File

@ -99,8 +99,7 @@ config EXT4_DEBUG
Enables run-time debugging support for the ext4 filesystem.
If you select Y here, then you will be able to turn on debugging
with a command such as:
echo 1 > /sys/module/ext4/parameters/mballoc_debug
using dynamic debug control for mb_debug() / ext_debug() msgs.
config EXT4_KUNIT_TESTS
tristate "KUnit tests for ext4"

5
fs/ext4/acl.c
View File

@ -215,9 +215,8 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type,
value, size, xattr_flags);
kfree(value);
if (!error) {
if (!error)
set_cached_acl(inode, type, acl);
}
return error;
}
@ -256,7 +255,7 @@ retry:
if (!error && update_mode) {
inode->i_mode = mode;
inode->i_ctime = current_time(inode);
ext4_mark_inode_dirty(handle, inode);
error = ext4_mark_inode_dirty(handle, inode);
}
out_stop:
ext4_journal_stop(handle);

5
fs/ext4/balloc.c
View File

@ -903,10 +903,11 @@ ext4_fsblk_t ext4_inode_to_goal_block(struct inode *inode)
return bg_start;
if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
colour = (current->pid % 16) *
colour = (task_pid_nr(current) % 16) *
(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
else
colour = (current->pid % 16) * ((last_block - bg_start) / 16);
colour = (task_pid_nr(current) % 16) *
((last_block - bg_start) / 16);
return bg_start + colour;
}

42
fs/ext4/ext4.h
View File

@ -36,6 +36,7 @@
#include <crypto/hash.h>
#include <linux/falloc.h>
#include <linux/percpu-rwsem.h>
#include <linux/fiemap.h>
#ifdef __KERNEL__
#include <linux/compat.h>
#endif
@ -80,14 +81,22 @@
#define ext4_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
/*
* Turn on EXT_DEBUG to get lots of info about extents operations.
*/
/*
* Turn on EXT_DEBUG to enable ext4_ext_show_path/leaf/move in extents.c
*/
#define EXT_DEBUG__
#ifdef EXT_DEBUG
#define ext_debug(fmt, ...) printk(fmt, ##__VA_ARGS__)
/*
* Dynamic printk for controlled extents debugging.
*/
#ifdef CONFIG_EXT4_DEBUG
#define ext_debug(ino, fmt, ...) \
pr_debug("[%s/%d] EXT4-fs (%s): ino %lu: (%s, %d): %s:" fmt, \
current->comm, task_pid_nr(current), \
ino->i_sb->s_id, ino->i_ino, __FILE__, __LINE__, \
__func__, ##__VA_ARGS__)
#else
#define ext_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#define ext_debug(ino, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
/* data type for block offset of block group */
@ -142,6 +151,8 @@ enum SHIFT_DIRECTION {
#define EXT4_MB_USE_ROOT_BLOCKS 0x1000
/* Use blocks from reserved pool */
#define EXT4_MB_USE_RESERVED 0x2000
/* Do strict check for free blocks while retrying block allocation */
#define EXT4_MB_STRICT_CHECK 0x4000
struct ext4_allocation_request {
/* target inode for block we're allocating */
@ -171,10 +182,10 @@ struct ext4_allocation_request {
* well as to store the information returned by ext4_map_blocks(). It
* takes less room on the stack than a struct buffer_head.
*/
#define EXT4_MAP_NEW (1 << BH_New)
#define EXT4_MAP_MAPPED (1 << BH_Mapped)
#define EXT4_MAP_UNWRITTEN (1 << BH_Unwritten)
#define EXT4_MAP_BOUNDARY (1 << BH_Boundary)
#define EXT4_MAP_NEW BIT(BH_New)
#define EXT4_MAP_MAPPED BIT(BH_Mapped)
#define EXT4_MAP_UNWRITTEN BIT(BH_Unwritten)
#define EXT4_MAP_BOUNDARY BIT(BH_Boundary)
#define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY)
@ -417,7 +428,7 @@ struct flex_groups {
/* 0x00400000 was formerly EXT4_EOFBLOCKS_FL */
#define EXT4_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */
#define EXT4_PROJINHERIT_FL 0x20000000 /* Create with parents projid */
#define EXT4_CASEFOLD_FL 0x40000000 /* Casefolded file */
#define EXT4_CASEFOLD_FL 0x40000000 /* Casefolded directory */
#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */
#define EXT4_FL_USER_VISIBLE 0x705BDFFF /* User visible flags */
@ -490,6 +501,7 @@ enum {
/* 22 was formerly EXT4_INODE_EOFBLOCKS */
EXT4_INODE_INLINE_DATA = 28, /* Data in inode. */
EXT4_INODE_PROJINHERIT = 29, /* Create with parents projid */
EXT4_INODE_CASEFOLD = 30, /* Casefolded directory */
EXT4_INODE_RESERVED = 31, /* reserved for ext4 lib */
};
@ -535,6 +547,7 @@ static inline void ext4_check_flag_values(void)
CHECK_FLAG_VALUE(EA_INODE);
CHECK_FLAG_VALUE(INLINE_DATA);
CHECK_FLAG_VALUE(PROJINHERIT);
CHECK_FLAG_VALUE(CASEFOLD);
CHECK_FLAG_VALUE(RESERVED);
}
@ -609,8 +622,6 @@ enum {
#define EXT4_GET_BLOCKS_METADATA_NOFAIL 0x0020
/* Don't normalize allocation size (used for fallocate) */
#define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040
/* Request will not result in inode size update (user for fallocate) */
#define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080
/* Convert written extents to unwritten */
#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN 0x0100
/* Write zeros to newly created written extents */
@ -632,6 +643,7 @@ enum {
*/
#define EXT4_EX_NOCACHE 0x40000000
#define EXT4_EX_FORCE_CACHE 0x20000000
#define EXT4_EX_NOFAIL 0x10000000
/*
* Flags used by ext4_free_blocks
@ -2051,7 +2063,7 @@ struct ext4_dir_entry_2 {
__le32 inode; /* Inode number */
__le16 rec_len; /* Directory entry length */
__u8 name_len; /* Name length */
__u8 file_type;
__u8 file_type; /* See file type macros EXT4_FT_* below */
char name[EXT4_NAME_LEN]; /* File name */
};
@ -3354,7 +3366,7 @@ struct ext4_extent;
*/
#define EXT_MAX_BLOCKS 0xffffffff
extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
extern void ext4_ext_tree_init(handle_t *handle, struct inode *inode);
extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);

9
fs/ext4/ext4_extents.h
View File

@ -170,10 +170,13 @@ struct partial_cluster {
(EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
#define EXT_LAST_INDEX(__hdr__) \
(EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
#define EXT_MAX_EXTENT(__hdr__) \
(EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)
#define EXT_MAX_EXTENT(__hdr__) \
((le16_to_cpu((__hdr__)->eh_max)) ? \
((EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) \
: 0)
#define EXT_MAX_INDEX(__hdr__) \
(EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)
((le16_to_cpu((__hdr__)->eh_max)) ? \
((EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) : 0)
static inline struct ext4_extent_header *ext_inode_hdr(struct inode *inode)
{

11
fs/ext4/ext4_jbd2.h
View File

@ -222,7 +222,10 @@ ext4_mark_iloc_dirty(handle_t *handle,
int ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
struct ext4_iloc *iloc);
int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode);
#define ext4_mark_inode_dirty(__h, __i) \
__ext4_mark_inode_dirty((__h), (__i), __func__, __LINE__)
int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode,
const char *func, unsigned int line);
int ext4_expand_extra_isize(struct inode *inode,
unsigned int new_extra_isize,
@ -335,12 +338,6 @@ static inline handle_t *__ext4_journal_start(struct inode *inode,
handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
int type);
static inline void ext4_journal_free_reserved(handle_t *handle)
{
if (ext4_handle_valid(handle))
jbd2_journal_free_reserved(handle);
}
static inline handle_t *ext4_journal_current_handle(void)
{
return journal_current_handle();

444
fs/ext4/extents.c
View File

File diff suppressed because it is too large Load Diff

2
fs/ext4/extents_status.c
View File

@ -1054,7 +1054,7 @@ static void count_rsvd(struct inode *inode, ext4_lblk_t lblk, long len,
end = (end > ext4_es_end(es)) ? ext4_es_end(es) : end;
/* record the first block of the first delonly extent seen */
if (rc->first_do_lblk_found == false) {
if (!rc->first_do_lblk_found) {
rc->first_do_lblk = i;
rc->first_do_lblk_found = true;
}

17
fs/ext4/file.c
View File

@ -287,6 +287,7 @@ static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset,
bool truncate = false;
u8 blkbits = inode->i_blkbits;
ext4_lblk_t written_blk, end_blk;
int ret;
/*
* Note that EXT4_I(inode)->i_disksize can get extended up to
@ -327,8 +328,14 @@ static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset,
goto truncate;
}
if (ext4_update_inode_size(inode, offset + written))
ext4_mark_inode_dirty(handle, inode);
if (ext4_update_inode_size(inode, offset + written)) {
ret = ext4_mark_inode_dirty(handle, inode);
if (unlikely(ret)) {
written = ret;
ext4_journal_stop(handle);
goto truncate;
}
}
/*
* We may need to truncate allocated but not written blocks beyond EOF.
@ -495,6 +502,12 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (ret <= 0)
return ret;
/* if we're going to block and IOCB_NOWAIT is set, return -EAGAIN */
if ((iocb->ki_flags & IOCB_NOWAIT) && (unaligned_io || extend)) {
ret = -EAGAIN;
goto out;
}
offset = iocb->ki_pos;
count = ret;

28
fs/ext4/fsync.c
View File

@ -44,30 +44,28 @@
*/
static int ext4_sync_parent(struct inode *inode)
{
struct dentry *dentry = NULL;
struct inode *next;
struct dentry *dentry, *next;
int ret = 0;
if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY))
return 0;
inode = igrab(inode);
dentry = d_find_any_alias(inode);
if (!dentry)
return 0;
while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
dentry = d_find_any_alias(inode);
if (!dentry)
break;
next = igrab(d_inode(dentry->d_parent));
next = dget_parent(dentry);
dput(dentry);
if (!next)
break;
iput(inode);
inode = next;
dentry = next;
inode = dentry->d_inode;
/*
* The directory inode may have gone through rmdir by now. But
* the inode itself and its blocks are still allocated (we hold
* a reference to the inode so it didn't go through
* ext4_evict_inode()) and so we are safe to flush metadata
* blocks and the inode.
* a reference to the inode via its dentry), so it didn't go
* through ext4_evict_inode()) and so we are safe to flush
* metadata blocks and the inode.
*/
ret = sync_mapping_buffers(inode->i_mapping);
if (ret)
@ -76,7 +74,7 @@ static int ext4_sync_parent(struct inode *inode)
if (ret)
break;
}
iput(inode);
dput(dentry);
return ret;
}

1
fs/ext4/ialloc.c
View File

@ -1246,6 +1246,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
ext4_error_err(sb, -err,
"couldn't read orphan inode %lu (err %d)",
ino, err);
brelse(bitmap_bh);
return inode;
}

4
fs/ext4/indirect.c
View File

@ -467,7 +467,9 @@ static int ext4_splice_branch(handle_t *handle,
/*
* OK, we spliced it into the inode itself on a direct block.
*/
ext4_mark_inode_dirty(handle, ar->inode);
err = ext4_mark_inode_dirty(handle, ar->inode);
if (unlikely(err))
goto err_out;
jbd_debug(5, "splicing direct\n");
}
return err;

6
fs/ext4/inline.c
View File

@ -1260,7 +1260,7 @@ out:
int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
struct inode *dir, struct inode *inode)
{
int ret, inline_size, no_expand;
int ret, ret2, inline_size, no_expand;
void *inline_start;
struct ext4_iloc iloc;
@ -1314,7 +1314,9 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
out:
ext4_write_unlock_xattr(dir, &no_expand);
ext4_mark_inode_dirty(handle, dir);
ret2 = ext4_mark_inode_dirty(handle, dir);
if (unlikely(ret2 && !ret))
ret = ret2;
brelse(iloc.bh);
return ret;
}

108
fs/ext4/inode.c
View File

@ -220,6 +220,16 @@ void ext4_evict_inode(struct inode *inode)
ext4_begin_ordered_truncate(inode, 0);
truncate_inode_pages_final(&inode->i_data);
/*
* For inodes with journalled data, transaction commit could have
* dirtied the inode. Flush worker is ignoring it because of I_FREEING
* flag but we still need to remove the inode from the writeback lists.
*/
if (!list_empty_careful(&inode->i_io_list)) {
WARN_ON_ONCE(!ext4_should_journal_data(inode));
inode_io_list_del(inode);
}
/*
* Protect us against freezing - iput() caller didn't have to have any
* protection against it
@ -432,11 +442,9 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
*/
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);
retval = ext4_ext_map_blocks(handle, inode, map, 0);
} else {
retval = ext4_ind_map_blocks(handle, inode, map, flags &
EXT4_GET_BLOCKS_KEEP_SIZE);
retval = ext4_ind_map_blocks(handle, inode, map, 0);
}
up_read((&EXT4_I(inode)->i_data_sem));
@ -493,9 +501,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
#endif
map->m_flags = 0;
ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u,"
"logical block %lu\n", inode->i_ino, flags, map->m_len,
(unsigned long) map->m_lblk);
ext_debug(inode, "flag 0x%x, max_blocks %u, logical block %lu\n",
flags, map->m_len, (unsigned long) map->m_lblk);
/*
* ext4_map_blocks returns an int, and m_len is an unsigned int
@ -541,11 +548,9 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
*/
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);
retval = ext4_ext_map_blocks(handle, inode, map, 0);
} else {
retval = ext4_ind_map_blocks(handle, inode, map, flags &
EXT4_GET_BLOCKS_KEEP_SIZE);
retval = ext4_ind_map_blocks(handle, inode, map, 0);
}
if (retval > 0) {
unsigned int status;
@ -726,6 +731,9 @@ out_sem:
return ret;
}
}
if (retval < 0)
ext_debug(inode, "failed with err %d\n", retval);
return retval;
}
@ -1296,7 +1304,7 @@ static int ext4_write_end(struct file *file,
* filesystems.
*/
if (i_size_changed || inline_data)
ext4_mark_inode_dirty(handle, inode);
ret = ext4_mark_inode_dirty(handle, inode);
if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode))
/* if we have allocated more blocks and copied
@ -1526,6 +1534,7 @@ struct mpage_da_data {
struct ext4_map_blocks map;
struct ext4_io_submit io_submit; /* IO submission data */
unsigned int do_map:1;
unsigned int scanned_until_end:1;
};
static void mpage_release_unused_pages(struct mpage_da_data *mpd,
@ -1541,6 +1550,7 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd,
if (mpd->first_page >= mpd->next_page)
return;
mpd->scanned_until_end = 0;
index = mpd->first_page;
end = mpd->next_page - 1;
if (invalidate) {
@ -1681,8 +1691,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
invalid_block = ~0;
map->m_flags = 0;
ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u,"
"logical block %lu\n", inode->i_ino, map->m_len,
ext_debug(inode, "max_blocks %u, logical block %lu\n", map->m_len,
(unsigned long) map->m_lblk);
/* Lookup extent status tree firstly */
@ -2078,7 +2087,7 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
return err;
}
#define BH_FLAGS ((1 << BH_Unwritten) | (1 << BH_Delay))
#define BH_FLAGS (BIT(BH_Unwritten) | BIT(BH_Delay))
/*
* mballoc gives us at most this number of blocks...
@ -2188,7 +2197,11 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
if (err < 0)
return err;
}
return lblk < blocks;
if (lblk >= blocks) {
mpd->scanned_until_end = 1;
return 0;
}
return 1;
}
/*
@ -2311,7 +2324,7 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
* mapping, or maybe the page was submitted for IO.
* So we return to call further extent mapping.
*/
if (err < 0 || map_bh == true)
if (err < 0 || map_bh)
goto out;
/* Page fully mapped - let IO run! */
err = mpage_submit_page(mpd, page);
@ -2358,7 +2371,7 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
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))
if (map->m_flags & BIT(BH_Delay))
get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
err = ext4_map_blocks(handle, inode, map, get_blocks_flags);
@ -2546,7 +2559,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
tag);
if (nr_pages == 0)
goto out;
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
@ -2601,6 +2614,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
pagevec_release(&pvec);
cond_resched();
}
mpd->scanned_until_end = 1;
return 0;
out:
pagevec_release(&pvec);
@ -2619,7 +2633,6 @@ static int ext4_writepages(struct address_space *mapping,
struct inode *inode = mapping->host;
int needed_blocks, rsv_blocks = 0, ret = 0;
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
bool done;
struct blk_plug plug;
bool give_up_on_write = false;
@ -2705,7 +2718,6 @@ static int ext4_writepages(struct address_space *mapping,
retry:
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, mpd.first_page, mpd.last_page);
done = false;
blk_start_plug(&plug);
/*
@ -2715,6 +2727,7 @@ retry:
* started.
*/
mpd.do_map = 0;
mpd.scanned_until_end = 0;
mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
if (!mpd.io_submit.io_end) {
ret = -ENOMEM;
@ -2730,7 +2743,7 @@ retry:
if (ret < 0)
goto unplug;
while (!done && mpd.first_page <= mpd.last_page) {
while (!mpd.scanned_until_end && wbc->nr_to_write > 0) {
/* For each extent of pages we use new io_end */
mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
if (!mpd.io_submit.io_end) {
@ -2765,20 +2778,9 @@ retry:
trace_ext4_da_write_pages(inode, mpd.first_page, mpd.wbc);
ret = mpage_prepare_extent_to_map(&mpd);
if (!ret) {
if (mpd.map.m_len)
ret = mpage_map_and_submit_extent(handle, &mpd,
if (!ret && mpd.map.m_len)
ret = mpage_map_and_submit_extent(handle, &mpd,
&give_up_on_write);
else {
/*
* We scanned the whole range (or exhausted
* nr_to_write), submitted what was mapped and
* didn't find anything needing mapping. We are
* done.
*/
done = true;
}
}
/*
* Caution: If the handle is synchronous,
* ext4_journal_stop() can wait for transaction commit
@ -3077,7 +3079,7 @@ static int ext4_da_write_end(struct file *file,
* new_i_size is less that inode->i_size
* bu greater than i_disksize.(hint delalloc)
*/
ext4_mark_inode_dirty(handle, inode);
ret = ext4_mark_inode_dirty(handle, inode);
}
}
@ -3094,7 +3096,7 @@ static int ext4_da_write_end(struct file *file,
if (ret2 < 0)
ret = ret2;
ret2 = ext4_journal_stop(handle);
if (!ret)
if (unlikely(ret2 && !ret))
ret = ret2;
return ret ? ret : copied;
@ -3883,6 +3885,8 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
loff_t len)
{
handle_t *handle;
int ret;
loff_t size = i_size_read(inode);
WARN_ON(!inode_is_locked(inode));
@ -3896,10 +3900,10 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
if (IS_ERR(handle))
return PTR_ERR(handle);
ext4_update_i_disksize(inode, size);
ext4_mark_inode_dirty(handle, inode);
ret = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
return 0;
return ret;
}
static void ext4_wait_dax_page(struct ext4_inode_info *ei)
@ -3951,7 +3955,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
loff_t first_block_offset, last_block_offset;
handle_t *handle;
unsigned int credits;
int ret = 0;
int ret = 0, ret2 = 0;
trace_ext4_punch_hole(inode, offset, length, 0);
@ -4074,7 +4078,9 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
ext4_handle_sync(handle);
inode->i_mtime = inode->i_ctime = current_time(inode);
ext4_mark_inode_dirty(handle, inode);
ret2 = ext4_mark_inode_dirty(handle, inode);
if (unlikely(ret2))
ret = ret2;
if (ret >= 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
out_stop:
@ -4143,7 +4149,7 @@ int ext4_truncate(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int credits;
int err = 0;
int err = 0, err2;
handle_t *handle;
struct address_space *mapping = inode->i_mapping;
@ -4231,7 +4237,9 @@ out_stop:
ext4_orphan_del(handle, inode);
inode->i_mtime = inode->i_ctime = current_time(inode);
ext4_mark_inode_dirty(handle, inode);
err2 = ext4_mark_inode_dirty(handle, inode);
if (unlikely(err2 && !err))
err = err2;
ext4_journal_stop(handle);
trace_ext4_truncate_exit(inode);
@ -5289,6 +5297,8 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
inode->i_gid = attr->ia_gid;
error = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
if (unlikely(error))
return error;
}
if (attr->ia_valid & ATTR_SIZE) {
@ -5774,7 +5784,8 @@ out_unlock:
* Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync)
* we start and wait on commits.
*/
int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode,
const char *func, unsigned int line)
{
struct ext4_iloc iloc;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@ -5784,13 +5795,18 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
trace_ext4_mark_inode_dirty(inode, _RET_IP_);
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
return err;
goto out;
if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize)
ext4_try_to_expand_extra_isize(inode, sbi->s_want_extra_isize,
iloc, handle);
return ext4_mark_iloc_dirty(handle, inode, &iloc);
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
out:
if (unlikely(err))
ext4_error_inode_err(inode, func, line, 0, err,
"mark_inode_dirty error");
return err;
}
/*

8
fs/ext4/ioctl.c
View File

@ -754,14 +754,6 @@ static int ext4_ioctl_get_es_cache(struct file *filp, unsigned long arg)
fieinfo.fi_extents_max = fiemap.fm_extent_count;
fieinfo.fi_extents_start = ufiemap->fm_extents;
if (fiemap.fm_extent_count != 0 &&
!access_ok(fieinfo.fi_extents_start,
fieinfo.fi_extents_max * sizeof(struct fiemap_extent)))
return -EFAULT;
if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC)
filemap_write_and_wait(inode->i_mapping);
error = ext4_get_es_cache(inode, &fieinfo, fiemap.fm_start,
fiemap.fm_length);
fiemap.fm_flags = fieinfo.fi_flags;

512
fs/ext4/mballoc.c
View File

File diff suppressed because it is too large Load Diff

16
fs/ext4/mballoc.h
View File

@ -24,19 +24,15 @@
#include "ext4.h"
/*
* mb_debug() dynamic printk msgs could be used to debug mballoc code.
*/
#ifdef CONFIG_EXT4_DEBUG
extern ushort ext4_mballoc_debug;
#define mb_debug(n, fmt, ...) \
do { \
if ((n) <= ext4_mballoc_debug) { \
printk(KERN_DEBUG "(%s, %d): %s: " fmt, \
__FILE__, __LINE__, __func__, ##__VA_ARGS__); \
} \
} while (0)
#define mb_debug(sb, fmt, ...) \
pr_debug("[%s/%d] EXT4-fs (%s): (%s, %d): %s: " fmt, \
current->comm, task_pid_nr(current), sb->s_id, \
__FILE__, __LINE__, __func__, ##__VA_ARGS__)
#else
#define mb_debug(n, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#define mb_debug(sb, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
#define EXT4_MB_HISTORY_ALLOC 1 /* allocation */

12
fs/ext4/migrate.c
View File

@ -287,7 +287,7 @@ static int free_ind_block(handle_t *handle, struct inode *inode, __le32 *i_data)
static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
struct inode *tmp_inode)
{
int retval;
int retval, retval2 = 0;
__le32 i_data[3];
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_inode_info *tmp_ei = EXT4_I(tmp_inode);
@ -342,7 +342,9 @@ static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
* i_blocks when freeing the indirect meta-data blocks
*/
retval = free_ind_block(handle, inode, i_data);
ext4_mark_inode_dirty(handle, inode);
retval2 = ext4_mark_inode_dirty(handle, inode);
if (unlikely(retval2 && !retval))
retval = retval2;
err_out:
return retval;
@ -601,7 +603,7 @@ int ext4_ind_migrate(struct inode *inode)
ext4_lblk_t start, end;
ext4_fsblk_t blk;
handle_t *handle;
int ret;
int ret, ret2 = 0;
if (!ext4_has_feature_extents(inode->i_sb) ||
(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
@ -655,7 +657,9 @@ int ext4_ind_migrate(struct inode *inode)
memset(ei->i_data, 0, sizeof(ei->i_data));
for (i = start; i <= end; i++)
ei->i_data[i] = cpu_to_le32(blk++);
ext4_mark_inode_dirty(handle, inode);
ret2 = ext4_mark_inode_dirty(handle, inode);
if (unlikely(ret2 && !ret))
ret = ret2;
errout:
ext4_journal_stop(handle);
up_write(&EXT4_I(inode)->i_data_sem);

76
fs/ext4/namei.c
View File

@ -1993,7 +1993,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
{
unsigned int blocksize = dir->i_sb->s_blocksize;
int csum_size = 0;
int err;
int err, err2;
if (ext4_has_metadata_csum(inode->i_sb))
csum_size = sizeof(struct ext4_dir_entry_tail);
@ -2028,12 +2028,12 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
dir->i_mtime = dir->i_ctime = current_time(dir);
ext4_update_dx_flag(dir);
inode_inc_iversion(dir);
ext4_mark_inode_dirty(handle, dir);
err2 = ext4_mark_inode_dirty(handle, dir);
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_dirblock(handle, dir, bh);
if (err)
ext4_std_error(dir->i_sb, err);
return 0;
return err ? err : err2;
}
/*
@ -2223,7 +2223,9 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
}
ext4_clear_inode_flag(dir, EXT4_INODE_INDEX);
dx_fallback++;
ext4_mark_inode_dirty(handle, dir);
retval = ext4_mark_inode_dirty(handle, dir);
if (unlikely(retval))
goto out;
}
blocks = dir->i_size >> sb->s_blocksize_bits;
for (block = 0; block < blocks; block++) {
@ -2576,12 +2578,12 @@ static int ext4_add_nondir(handle_t *handle,
struct inode *inode = *inodep;
int err = ext4_add_entry(handle, dentry, inode);
if (!err) {
ext4_mark_inode_dirty(handle, inode);
err = ext4_mark_inode_dirty(handle, inode);
if (IS_DIRSYNC(dir))
ext4_handle_sync(handle);
d_instantiate_new(dentry, inode);
*inodep = NULL;
return 0;
return err;
}
drop_nlink(inode);
ext4_orphan_add(handle, inode);
@ -2775,7 +2777,7 @@ static int ext4_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
handle_t *handle;
struct inode *inode;
int err, credits, retries = 0;
int err, err2 = 0, credits, retries = 0;
if (EXT4_DIR_LINK_MAX(dir))
return -EMLINK;
@ -2808,7 +2810,9 @@ out_clear_inode:
clear_nlink(inode);
ext4_orphan_add(handle, inode);
unlock_new_inode(inode);
ext4_mark_inode_dirty(handle, inode);
err2 = ext4_mark_inode_dirty(handle, inode);
if (unlikely(err2))
err = err2;
ext4_journal_stop(handle);
iput(inode);
goto out_retry;
@ -3148,10 +3152,12 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
inode->i_size = 0;
ext4_orphan_add(handle, inode);
inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode);
ext4_mark_inode_dirty(handle, inode);
retval = ext4_mark_inode_dirty(handle, inode);
if (retval)
goto end_rmdir;
ext4_dec_count(handle, dir);
ext4_update_dx_flag(dir);
ext4_mark_inode_dirty(handle, dir);
retval = ext4_mark_inode_dirty(handle, dir);
#ifdef CONFIG_UNICODE
/* VFS negative dentries are incompatible with Encoding and
@ -3221,7 +3227,9 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
goto end_unlink;
dir->i_ctime = dir->i_mtime = current_time(dir);
ext4_update_dx_flag(dir);
ext4_mark_inode_dirty(handle, dir);
retval = ext4_mark_inode_dirty(handle, dir);
if (retval)
goto end_unlink;
if (inode->i_nlink == 0)
ext4_warning_inode(inode, "Deleting file '%.*s' with no links",
dentry->d_name.len, dentry->d_name.name);
@ -3230,7 +3238,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
if (!inode->i_nlink)
ext4_orphan_add(handle, inode);
inode->i_ctime = current_time(inode);
ext4_mark_inode_dirty(handle, inode);
retval = ext4_mark_inode_dirty(handle, inode);
#ifdef CONFIG_UNICODE
/* VFS negative dentries are incompatible with Encoding and
@ -3419,7 +3427,7 @@ retry:
err = ext4_add_entry(handle, dentry, inode);
if (!err) {
ext4_mark_inode_dirty(handle, inode);
err = ext4_mark_inode_dirty(handle, inode);
/* this can happen only for tmpfile being
* linked the first time
*/
@ -3531,7 +3539,7 @@ static int ext4_rename_dir_finish(handle_t *handle, struct ext4_renament *ent,
static int ext4_setent(handle_t *handle, struct ext4_renament *ent,
unsigned ino, unsigned file_type)
{
int retval;
int retval, retval2;
BUFFER_TRACE(ent->bh, "get write access");
retval = ext4_journal_get_write_access(handle, ent->bh);
@ -3543,19 +3551,19 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent,
inode_inc_iversion(ent->dir);
ent->dir->i_ctime = ent->dir->i_mtime =
current_time(ent->dir);
ext4_mark_inode_dirty(handle, ent->dir);
retval = ext4_mark_inode_dirty(handle, ent->dir);
BUFFER_TRACE(ent->bh, "call ext4_handle_dirty_metadata");
if (!ent->inlined) {
retval = ext4_handle_dirty_dirblock(handle, ent->dir, ent->bh);
if (unlikely(retval)) {
ext4_std_error(ent->dir->i_sb, retval);
return retval;
retval2 = ext4_handle_dirty_dirblock(handle, ent->dir, ent->bh);
if (unlikely(retval2)) {
ext4_std_error(ent->dir->i_sb, retval2);
return retval2;
}
}
brelse(ent->bh);
ent->bh = NULL;
return 0;
return retval;
}
static int ext4_find_delete_entry(handle_t *handle, struct inode *dir,
@ -3790,7 +3798,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
EXT4_FT_CHRDEV);
if (retval)
goto end_rename;
ext4_mark_inode_dirty(handle, whiteout);
retval = ext4_mark_inode_dirty(handle, whiteout);
if (unlikely(retval))
goto end_rename;
}
if (!new.bh) {
retval = ext4_add_entry(handle, new.dentry, old.inode);
@ -3811,7 +3821,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
* rename.
*/
old.inode->i_ctime = current_time(old.inode);
ext4_mark_inode_dirty(handle, old.inode);
retval = ext4_mark_inode_dirty(handle, old.inode);
if (unlikely(retval))
goto end_rename;
if (!whiteout) {
/*
@ -3840,12 +3852,18 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
} else {
ext4_inc_count(handle, new.dir);
ext4_update_dx_flag(new.dir);
ext4_mark_inode_dirty(handle, new.dir);
retval = ext4_mark_inode_dirty(handle, new.dir);
if (unlikely(retval))
goto end_rename;
}
}
ext4_mark_inode_dirty(handle, old.dir);
retval = ext4_mark_inode_dirty(handle, old.dir);
if (unlikely(retval))
goto end_rename;
if (new.inode) {
ext4_mark_inode_dirty(handle, new.inode);
retval = ext4_mark_inode_dirty(handle, new.inode);
if (unlikely(retval))
goto end_rename;
if (!new.inode->i_nlink)
ext4_orphan_add(handle, new.inode);
}
@ -3979,8 +3997,12 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
ctime = current_time(old.inode);
old.inode->i_ctime = ctime;
new.inode->i_ctime = ctime;
ext4_mark_inode_dirty(handle, old.inode);
ext4_mark_inode_dirty(handle, new.inode);
retval = ext4_mark_inode_dirty(handle, old.inode);
if (unlikely(retval))
goto end_rename;
retval = ext4_mark_inode_dirty(handle, new.inode);
if (unlikely(retval))
goto end_rename;
if (old.dir_bh) {
retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);

27
fs/ext4/super.c
View File

@ -3718,7 +3718,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
int blocksize, clustersize;
unsigned int db_count;
unsigned int i;
int needs_recovery, has_huge_files, has_bigalloc;
int needs_recovery, has_huge_files;
__u64 blocks_count;
int err = 0;
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
@ -4010,17 +4010,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, and O_DIRECT support!\n");
/* can't mount with both data=journal and dioread_nolock. */
clear_opt(sb, DIOREAD_NOLOCK);
if (test_opt2(sb, EXPLICIT_DELALLOC)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"both data=journal and delalloc");
goto failed_mount;
}
if (test_opt(sb, DIOREAD_NOLOCK)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"both data=journal and dioread_nolock");
goto failed_mount;
}
if (test_opt(sb, DAX)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"both data=journal and dax");
@ -4237,8 +4233,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
/* Handle clustersize */
clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size);
has_bigalloc = ext4_has_feature_bigalloc(sb);
if (has_bigalloc) {
if (ext4_has_feature_bigalloc(sb)) {
if (clustersize < blocksize) {
ext4_msg(sb, KERN_ERR,
"cluster size (%d) smaller than "
@ -5925,7 +5920,7 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
EXT4_I(inode)->i_flags |= EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL;
inode_set_flags(inode, S_NOATIME | S_IMMUTABLE,
S_NOATIME | S_IMMUTABLE);
ext4_mark_inode_dirty(handle, inode);
err = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
unlock_inode:
inode_unlock(inode);
@ -6027,12 +6022,14 @@ static int ext4_quota_off(struct super_block *sb, int type)
* this is not a hard failure and quotas are already disabled.
*/
handle = ext4_journal_start(inode, EXT4_HT_QUOTA, 1);
if (IS_ERR(handle))
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto out_unlock;
}
EXT4_I(inode)->i_flags &= ~(EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL);
inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE);
inode->i_mtime = inode->i_ctime = current_time(inode);
ext4_mark_inode_dirty(handle, inode);
err = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
out_unlock:
inode_unlock(inode);
@ -6090,7 +6087,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
{
struct inode *inode = sb_dqopt(sb)->files[type];
ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
int err, offset = off & (sb->s_blocksize - 1);
int err = 0, err2 = 0, offset = off & (sb->s_blocksize - 1);
int retries = 0;
struct buffer_head *bh;
handle_t *handle = journal_current_handle();
@ -6138,9 +6135,11 @@ out:
if (inode->i_size < off + len) {
i_size_write(inode, off + len);
EXT4_I(inode)->i_disksize = inode->i_size;
ext4_mark_inode_dirty(handle, inode);
err2 = ext4_mark_inode_dirty(handle, inode);
if (unlikely(err2 && !err))
err = err2;
}
return len;
return err ? err : len;
}
#endif

13
fs/ext4/xattr.c
View File

@ -1327,7 +1327,7 @@ static int ext4_xattr_inode_write(handle_t *handle, struct inode *ea_inode,
int blocksize = ea_inode->i_sb->s_blocksize;
int max_blocks = (bufsize + blocksize - 1) >> ea_inode->i_blkbits;
int csize, wsize = 0;
int ret = 0;
int ret = 0, ret2 = 0;
int retries = 0;
retry:
@ -1385,7 +1385,9 @@ retry:
ext4_update_i_disksize(ea_inode, wsize);
inode_unlock(ea_inode);
ext4_mark_inode_dirty(handle, ea_inode);
ret2 = ext4_mark_inode_dirty(handle, ea_inode);
if (unlikely(ret2 && !ret))
ret = ret2;
out:
brelse(bh);
@ -1800,8 +1802,11 @@ ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i,
if (EXT4_I(inode)->i_file_acl) {
/* The inode already has an extended attribute block. */
bs->bh = ext4_sb_bread(sb, EXT4_I(inode)->i_file_acl, REQ_PRIO);
if (IS_ERR(bs->bh))
return PTR_ERR(bs->bh);
if (IS_ERR(bs->bh)) {
error = PTR_ERR(bs->bh);
bs->bh = NULL;
return error;
}
ea_bdebug(bs->bh, "b_count=%d, refcount=%d",
atomic_read(&(bs->bh->b_count)),
le32_to_cpu(BHDR(bs->bh)->h_refcount));

3
fs/f2fs/data.c
View File

@ -19,6 +19,7 @@
#include <linux/uio.h>
#include <linux/cleancache.h>
#include <linux/sched/signal.h>
#include <linux/fiemap.h>
#include "f2fs.h"
#include "node.h"
@ -1824,7 +1825,7 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
return ret;
}
ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR);
ret = fiemap_prep(inode, fieinfo, start, &len, FIEMAP_FLAG_XATTR);
if (ret)
return ret;

1
fs/f2fs/inline.c
View File

@ -8,6 +8,7 @@
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/fiemap.h>
#include "f2fs.h"
#include "node.h"

1
fs/fs-writeback.c
View File

@ -1125,6 +1125,7 @@ void inode_io_list_del(struct inode *inode)
inode_io_list_del_locked(inode, wb);
spin_unlock(&wb->list_lock);
}
EXPORT_SYMBOL(inode_io_list_del);
/*
* mark an inode as under writeback on the sb

1
fs/gfs2/inode.c
View File

@ -17,6 +17,7 @@
#include <linux/crc32.h>
#include <linux/iomap.h>
#include <linux/security.h>
#include <linux/fiemap.h>
#include <linux/uaccess.h>
#include "gfs2.h"

1
fs/hpfs/file.c
View File

@ -9,6 +9,7 @@
#include "hpfs_fn.h"
#include <linux/mpage.h>
#include <linux/fiemap.h>
#define BLOCKS(size) (((size) + 511) >> 9)

2
fs/internal.h
View File

@ -142,8 +142,6 @@ extern int dentry_needs_remove_privs(struct dentry *dentry);
/*
* fs-writeback.c
*/
extern void inode_io_list_del(struct inode *inode);
extern long get_nr_dirty_inodes(void);
extern int invalidate_inodes(struct super_block *, bool);

82
fs/ioctl.c
View File

@ -18,6 +18,7 @@
#include <linux/buffer_head.h>
#include <linux/falloc.h>
#include <linux/sched/signal.h>
#include <linux/fiemap.h>
#include "internal.h"
@ -148,61 +149,55 @@ int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical,
EXPORT_SYMBOL(fiemap_fill_next_extent);
/**
* fiemap_check_flags - check validity of requested flags for fiemap
* fiemap_prep - check validity of requested flags for fiemap
* @inode: Inode to operate on
* @fieinfo: Fiemap context passed into ->fiemap
* @fs_flags: Set of fiemap flags that the file system understands
* @start: Start of the mapped range
* @len: Length of the mapped range, can be truncated by this function.
* @supported_flags: Set of fiemap flags that the file system understands
*
* Called from file system ->fiemap callback. This will compute the
* intersection of valid fiemap flags and those that the fs supports. That
* value is then compared against the user supplied flags. In case of bad user
* flags, the invalid values will be written into the fieinfo structure, and
* -EBADR is returned, which tells ioctl_fiemap() to return those values to
* userspace. For this reason, a return code of -EBADR should be preserved.
* This function must be called from each ->fiemap instance to validate the
* fiemap request against the file system parameters.
*
* Returns 0 on success, -EBADR on bad flags.
* Returns 0 on success, or a negative error on failure.
*/
int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags)
int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 *len, u32 supported_flags)
{
u64 maxbytes = inode->i_sb->s_maxbytes;
u32 incompat_flags;
int ret = 0;
incompat_flags = fieinfo->fi_flags & ~(FIEMAP_FLAGS_COMPAT & fs_flags);
if (incompat_flags) {
fieinfo->fi_flags = incompat_flags;
return -EBADR;
}
return 0;
}
EXPORT_SYMBOL(fiemap_check_flags);
static int fiemap_check_ranges(struct super_block *sb,
u64 start, u64 len, u64 *new_len)
{
u64 maxbytes = (u64) sb->s_maxbytes;
*new_len = len;
if (len == 0)
if (*len == 0)
return -EINVAL;
if (start > maxbytes)
return -EFBIG;
/*
* Shrink request scope to what the fs can actually handle.
*/
if (len > maxbytes || (maxbytes - len) < start)
*new_len = maxbytes - start;
if (*len > maxbytes || (maxbytes - *len) < start)
*len = maxbytes - start;
return 0;
supported_flags |= FIEMAP_FLAG_SYNC;
supported_flags &= FIEMAP_FLAGS_COMPAT;
incompat_flags = fieinfo->fi_flags & ~supported_flags;
if (incompat_flags) {
fieinfo->fi_flags = incompat_flags;
return -EBADR;
}
if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC)
ret = filemap_write_and_wait(inode->i_mapping);
return ret;
}
EXPORT_SYMBOL(fiemap_prep);
static int ioctl_fiemap(struct file *filp, struct fiemap __user *ufiemap)
{
struct fiemap fiemap;
struct fiemap_extent_info fieinfo = { 0, };
struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
u64 len;
int error;
if (!inode->i_op->fiemap)
@ -214,24 +209,13 @@ static int ioctl_fiemap(struct file *filp, struct fiemap __user *ufiemap)
if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS)
return -EINVAL;
error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length,
&len);
if (error)
return error;
fieinfo.fi_flags = fiemap.fm_flags;
fieinfo.fi_extents_max = fiemap.fm_extent_count;
fieinfo.fi_extents_start = ufiemap->fm_extents;
if (fiemap.fm_extent_count != 0 &&
!access_ok(fieinfo.fi_extents_start,
fieinfo.fi_extents_max * sizeof(struct fiemap_extent)))
return -EFAULT;
error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start,
fiemap.fm_length);
if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC)
filemap_write_and_wait(inode->i_mapping);
error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, len);
fiemap.fm_flags = fieinfo.fi_flags;
fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped;
if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap)))
@ -307,8 +291,7 @@ static inline loff_t blk_to_logical(struct inode *inode, sector_t blk)
* If you use this function directly, you need to do your own locking. Use
* generic_block_fiemap if you want the locking done for you.
*/
int __generic_block_fiemap(struct inode *inode,
static int __generic_block_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo, loff_t start,
loff_t len, get_block_t *get_block)
{
@ -320,7 +303,7 @@ int __generic_block_fiemap(struct inode *inode,
bool past_eof = false, whole_file = false;
int ret = 0;
ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
ret = fiemap_prep(inode, fieinfo, start, &len, FIEMAP_FLAG_SYNC);
if (ret)
return ret;
@ -453,7 +436,6 @@ int __generic_block_fiemap(struct inode *inode,
return ret;
}
EXPORT_SYMBOL(__generic_block_fiemap);
/**
* generic_block_fiemap - FIEMAP for block based inodes

11
fs/iomap/fiemap.c
View File

@ -6,6 +6,7 @@
#include <linux/compiler.h>
#include <linux/fs.h>
#include <linux/iomap.h>
#include <linux/fiemap.h>
struct fiemap_ctx {
struct fiemap_extent_info *fi;
@ -65,7 +66,7 @@ iomap_fiemap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
}
int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
loff_t start, loff_t len, const struct iomap_ops *ops)
u64 start, u64 len, const struct iomap_ops *ops)
{
struct fiemap_ctx ctx;
loff_t ret;
@ -74,16 +75,10 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
ctx.fi = fi;
ctx.prev.type = IOMAP_HOLE;
ret = fiemap_check_flags(fi, FIEMAP_FLAG_SYNC);
ret = fiemap_prep(inode, fi, start, &len, 0);
if (ret)
return ret;
if (fi->fi_flags & FIEMAP_FLAG_SYNC) {
ret = filemap_write_and_wait(inode->i_mapping);
if (ret)
return ret;
}
while (len > 0) {
ret = iomap_apply(inode, start, len, IOMAP_REPORT, ops, &ctx,
iomap_fiemap_actor);

14
fs/jbd2/transaction.c
View File

@ -541,17 +541,24 @@ handle_t *jbd2_journal_start(journal_t *journal, int nblocks)
}
EXPORT_SYMBOL(jbd2_journal_start);
static void __jbd2_journal_unreserve_handle(handle_t *handle)
static void __jbd2_journal_unreserve_handle(handle_t *handle, transaction_t *t)
{
journal_t *journal = handle->h_journal;
WARN_ON(!handle->h_reserved);
sub_reserved_credits(journal, handle->h_total_credits);
if (t)
atomic_sub(handle->h_total_credits, &t->t_outstanding_credits);
}
void jbd2_journal_free_reserved(handle_t *handle)
{
__jbd2_journal_unreserve_handle(handle);
journal_t *journal = handle->h_journal;
/* Get j_state_lock to pin running transaction if it exists */
read_lock(&journal->j_state_lock);
__jbd2_journal_unreserve_handle(handle, journal->j_running_transaction);
read_unlock(&journal->j_state_lock);
jbd2_free_handle(handle);
}
EXPORT_SYMBOL(jbd2_journal_free_reserved);
@ -722,7 +729,8 @@ static void stop_this_handle(handle_t *handle)
atomic_sub(handle->h_total_credits,
&transaction->t_outstanding_credits);
if (handle->h_rsv_handle)
__jbd2_journal_unreserve_handle(handle->h_rsv_handle);
__jbd2_journal_unreserve_handle(handle->h_rsv_handle,
transaction);
if (atomic_dec_and_test(&transaction->t_updates))
wake_up(&journal->j_wait_updates);

3
fs/nilfs2/inode.c
View File

@ -14,6 +14,7 @@
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/uio.h>
#include <linux/fiemap.h>
#include "nilfs.h"
#include "btnode.h"
#include "segment.h"
@ -996,7 +997,7 @@ int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
unsigned int blkbits = inode->i_blkbits;
int ret, n;
ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
ret = fiemap_prep(inode, fieinfo, start, &len, 0);
if (ret)
return ret;

4
fs/ocfs2/extent_map.c
View File

@ -733,8 +733,6 @@ static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
return 0;
}
#define OCFS2_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC)
int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 map_start, u64 map_len)
{
@ -746,7 +744,7 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
struct buffer_head *di_bh = NULL;
struct ocfs2_extent_rec rec;
ret = fiemap_check_flags(fieinfo, OCFS2_FIEMAP_FLAGS);
ret = fiemap_prep(inode, fieinfo, map_start, &map_len, 0);
if (ret)
return ret;

5
fs/overlayfs/inode.c
View File

@ -10,6 +10,7 @@
#include <linux/xattr.h>
#include <linux/posix_acl.h>
#include <linux/ratelimit.h>
#include <linux/fiemap.h>
#include "overlayfs.h"
@ -479,10 +480,6 @@ static int ovl_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
return -EOPNOTSUPP;
old_cred = ovl_override_creds(inode->i_sb);
if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC)
filemap_write_and_wait(realinode->i_mapping);
err = realinode->i_op->fiemap(realinode, fieinfo, start, len);
revert_creds(old_cred);

1
fs/xfs/xfs_iops.c
View File

@ -25,6 +25,7 @@
#include <linux/posix_acl.h>
#include <linux/security.h>
#include <linux/iversion.h>
#include <linux/fiemap.h>
/*
* Directories have different lock order w.r.t. mmap_sem compared to regular

25
include/linux/fiemap.h Normal file
View File

@ -0,0 +1,25 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_FIEMAP_H
#define _LINUX_FIEMAP_H 1
#include <uapi/linux/fiemap.h>
#include <linux/fs.h>
struct fiemap_extent_info {
unsigned int fi_flags; /* Flags as passed from user */
unsigned int fi_extents_mapped; /* Number of mapped extents */
unsigned int fi_extents_max; /* Size of fiemap_extent array */
struct fiemap_extent __user *fi_extents_start; /* Start of
fiemap_extent array */
};
int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 *len, u32 supported_flags);
int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
u64 phys, u64 len, u32 flags);
int generic_block_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo, u64 start, u64 len,
get_block_t *get_block);
#endif /* _LINUX_FIEMAP_H 1 */

23
include/linux/fs.h
View File

@ -24,7 +24,6 @@
#include <linux/capability.h>
#include <linux/semaphore.h>
#include <linux/fcntl.h>
#include <linux/fiemap.h>
#include <linux/rculist_bl.h>
#include <linux/atomic.h>
#include <linux/shrinker.h>
@ -48,6 +47,7 @@ struct backing_dev_info;
struct bdi_writeback;
struct bio;
struct export_operations;
struct fiemap_extent_info;
struct hd_geometry;
struct iovec;
struct kiocb;
@ -1755,19 +1755,6 @@ extern long compat_ptr_ioctl(struct file *file, unsigned int cmd,
extern void inode_init_owner(struct inode *inode, const struct inode *dir,
umode_t mode);
extern bool may_open_dev(const struct path *path);
/*
* VFS FS_IOC_FIEMAP helper definitions.
*/
struct fiemap_extent_info {
unsigned int fi_flags; /* Flags as passed from user */
unsigned int fi_extents_mapped; /* Number of mapped extents */
unsigned int fi_extents_max; /* Size of fiemap_extent array */
struct fiemap_extent __user *fi_extents_start; /* Start of
fiemap_extent array */
};
int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
u64 phys, u64 len, u32 flags);
int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
/*
* This is the "filldir" function type, used by readdir() to let
@ -3323,14 +3310,6 @@ static inline int vfs_fstat(int fd, struct kstat *stat)
extern const char *vfs_get_link(struct dentry *, struct delayed_call *);
extern int vfs_readlink(struct dentry *, char __user *, int);
extern int __generic_block_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo,
loff_t start, loff_t len,
get_block_t *get_block);
extern int generic_block_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo, u64 start,
u64 len, get_block_t *get_block);
extern struct file_system_type *get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
extern struct file_system_type *get_fs_type(const char *name);

2
include/linux/iomap.h
View File

@ -177,7 +177,7 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf,
const struct iomap_ops *ops);
int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
loff_t start, loff_t len, const struct iomap_ops *ops);
u64 start, u64 len, const struct iomap_ops *ops);
loff_t iomap_seek_hole(struct inode *inode, loff_t offset,
const struct iomap_ops *ops);
loff_t iomap_seek_data(struct inode *inode, loff_t offset,

1
include/linux/writeback.h
View File

@ -197,6 +197,7 @@ void wakeup_flusher_threads(enum wb_reason reason);
void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi,
enum wb_reason reason);
void inode_wait_for_writeback(struct inode *inode);
void inode_io_list_del(struct inode *inode);
/* writeback.h requires fs.h; it, too, is not included from here. */
static inline void wait_on_inode(struct inode *inode)

9
include/trace/events/ext4.h
View File

@ -35,7 +35,8 @@ struct partial_cluster;
{ EXT4_MB_DELALLOC_RESERVED, "DELALLOC_RESV" }, \
{ EXT4_MB_STREAM_ALLOC, "STREAM_ALLOC" }, \
{ EXT4_MB_USE_ROOT_BLOCKS, "USE_ROOT_BLKS" }, \
{ EXT4_MB_USE_RESERVED, "USE_RESV" })
{ EXT4_MB_USE_RESERVED, "USE_RESV" }, \
{ EXT4_MB_STRICT_CHECK, "STRICT_CHECK" })
#define show_map_flags(flags) __print_flags(flags, "|", \
{ EXT4_GET_BLOCKS_CREATE, "CREATE" }, \
@ -45,8 +46,10 @@ struct partial_cluster;
{ EXT4_GET_BLOCKS_CONVERT, "CONVERT" }, \
{ EXT4_GET_BLOCKS_METADATA_NOFAIL, "METADATA_NOFAIL" }, \
{ EXT4_GET_BLOCKS_NO_NORMALIZE, "NO_NORMALIZE" }, \
{ EXT4_GET_BLOCKS_KEEP_SIZE, "KEEP_SIZE" }, \
{ EXT4_GET_BLOCKS_ZERO, "ZERO" })
{ EXT4_GET_BLOCKS_CONVERT_UNWRITTEN, "CONVERT_UNWRITTEN" }, \
{ EXT4_GET_BLOCKS_ZERO, "ZERO" }, \
{ EXT4_GET_BLOCKS_IO_SUBMIT, "IO_SUBMIT" }, \
{ EXT4_EX_NOCACHE, "EX_NOCACHE" })
/*
* __print_flags() requires that all enum values be wrapped in the

6
include/uapi/linux/fiemap.h
View File

@ -9,8 +9,8 @@
* Andreas Dilger <adilger@sun.com>
*/
#ifndef _LINUX_FIEMAP_H
#define _LINUX_FIEMAP_H
#ifndef _UAPI_LINUX_FIEMAP_H
#define _UAPI_LINUX_FIEMAP_H
#include <linux/types.h>
@ -67,4 +67,4 @@ struct fiemap {
#define FIEMAP_EXTENT_SHARED 0x00002000 /* Space shared with other
* files. */
#endif /* _LINUX_FIEMAP_H */
#endif /* _UAPI_LINUX_FIEMAP_H */