summaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/Kconfig1
-rw-r--r--fs/ext4/acl.c2
-rw-r--r--fs/ext4/ext4.h92
-rw-r--r--fs/ext4/ext4_jbd2.c3
-rw-r--r--fs/ext4/extents.c12
-rw-r--r--fs/ext4/file.c11
-rw-r--r--fs/ext4/ialloc.c2
-rw-r--r--fs/ext4/inline.c4
-rw-r--r--fs/ext4/inode-test.c6
-rw-r--r--fs/ext4/inode.c24
-rw-r--r--fs/ext4/ioctl.c9
-rw-r--r--fs/ext4/mballoc.c172
-rw-r--r--fs/ext4/move_extent.c19
-rw-r--r--fs/ext4/namei.c26
-rw-r--r--fs/ext4/super.c73
-rw-r--r--fs/ext4/xattr.c20
16 files changed, 292 insertions, 184 deletions
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index 86699c8cab28..e20d59221fc0 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -28,6 +28,7 @@ config EXT3_FS_SECURITY
config EXT4_FS
tristate "The Extended 4 (ext4) filesystem"
+ select BUFFER_HEAD
select JBD2
select CRC16
select CRYPTO
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 27fcbddfb148..3bffe862f954 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -259,7 +259,7 @@ retry:
error = __ext4_set_acl(handle, inode, type, acl, 0 /* xattr_flags */);
if (!error && update_mode) {
inode->i_mode = mode;
- inode->i_ctime = current_time(inode);
+ inode_set_ctime_current(inode);
error = ext4_mark_inode_dirty(handle, inode);
}
out_stop:
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0a2d55faa095..481491e892df 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -868,64 +868,70 @@ struct ext4_inode {
* affected filesystem before 2242.
*/
-static inline __le32 ext4_encode_extra_time(struct timespec64 *time)
+static inline __le32 ext4_encode_extra_time(struct timespec64 ts)
{
- u32 extra =((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK;
- return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS));
+ u32 extra = ((ts.tv_sec - (s32)ts.tv_sec) >> 32) & EXT4_EPOCH_MASK;
+ return cpu_to_le32(extra | (ts.tv_nsec << EXT4_EPOCH_BITS));
}
-static inline void ext4_decode_extra_time(struct timespec64 *time,
- __le32 extra)
+static inline struct timespec64 ext4_decode_extra_time(__le32 base,
+ __le32 extra)
{
+ struct timespec64 ts = { .tv_sec = (signed)le32_to_cpu(base) };
+
if (unlikely(extra & cpu_to_le32(EXT4_EPOCH_MASK)))
- time->tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32;
- time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
+ ts.tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32;
+ ts.tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
+ return ts;
}
-#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \
+#define EXT4_INODE_SET_XTIME_VAL(xtime, inode, raw_inode, ts) \
do { \
- if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) {\
- (raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec); \
- (raw_inode)->xtime ## _extra = \
- ext4_encode_extra_time(&(inode)->xtime); \
- } \
- else \
- (raw_inode)->xtime = cpu_to_le32(clamp_t(int32_t, (inode)->xtime.tv_sec, S32_MIN, S32_MAX)); \
+ if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) { \
+ (raw_inode)->xtime = cpu_to_le32((ts).tv_sec); \
+ (raw_inode)->xtime ## _extra = ext4_encode_extra_time(ts); \
+ } else \
+ (raw_inode)->xtime = cpu_to_le32(clamp_t(int32_t, (ts).tv_sec, S32_MIN, S32_MAX)); \
} while (0)
-#define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode) \
-do { \
- if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \
- (raw_inode)->xtime = cpu_to_le32((einode)->xtime.tv_sec); \
- if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra)) \
- (raw_inode)->xtime ## _extra = \
- ext4_encode_extra_time(&(einode)->xtime); \
-} while (0)
+#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \
+ EXT4_INODE_SET_XTIME_VAL(xtime, inode, raw_inode, (inode)->xtime)
+
+#define EXT4_INODE_SET_CTIME(inode, raw_inode) \
+ EXT4_INODE_SET_XTIME_VAL(i_ctime, inode, raw_inode, inode_get_ctime(inode))
+
+#define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode) \
+ if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \
+ EXT4_INODE_SET_XTIME_VAL(xtime, &((einode)->vfs_inode), \
+ raw_inode, (einode)->xtime)
+
+#define EXT4_INODE_GET_XTIME_VAL(xtime, inode, raw_inode) \
+ (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra) ? \
+ ext4_decode_extra_time((raw_inode)->xtime, \
+ (raw_inode)->xtime ## _extra) : \
+ (struct timespec64) { \
+ .tv_sec = (signed)le32_to_cpu((raw_inode)->xtime) \
+ })
#define EXT4_INODE_GET_XTIME(xtime, inode, raw_inode) \
do { \
- (inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime); \
- if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) { \
- ext4_decode_extra_time(&(inode)->xtime, \
- raw_inode->xtime ## _extra); \
- } \
- else \
- (inode)->xtime.tv_nsec = 0; \
+ (inode)->xtime = EXT4_INODE_GET_XTIME_VAL(xtime, inode, raw_inode); \
} while (0)
+#define EXT4_INODE_GET_CTIME(inode, raw_inode) \
+do { \
+ inode_set_ctime_to_ts(inode, \
+ EXT4_INODE_GET_XTIME_VAL(i_ctime, inode, raw_inode)); \
+} while (0)
-#define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode) \
-do { \
- if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \
- (einode)->xtime.tv_sec = \
- (signed)le32_to_cpu((raw_inode)->xtime); \
- else \
- (einode)->xtime.tv_sec = 0; \
- if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra)) \
- ext4_decode_extra_time(&(einode)->xtime, \
- raw_inode->xtime ## _extra); \
- else \
- (einode)->xtime.tv_nsec = 0; \
+#define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode) \
+do { \
+ if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \
+ (einode)->xtime = \
+ EXT4_INODE_GET_XTIME_VAL(xtime, &(einode->vfs_inode), \
+ raw_inode); \
+ else \
+ (einode)->xtime = (struct timespec64){0, 0}; \
} while (0)
#define i_disk_version osd1.linux1.l_i_version
@@ -3774,8 +3780,6 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh)
set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
}
-#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
-
/* For ioend & aio unwritten conversion wait queues */
#define EXT4_WQ_HASH_SZ 37
#define ext4_ioend_wq(v) (&ext4__ioend_wq[((unsigned long)(v)) %\
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 77f318ec8abb..b38d59581411 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -234,8 +234,7 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line,
might_sleep();
- if (bh->b_bdev->bd_super)
- ext4_check_bdev_write_error(bh->b_bdev->bd_super);
+ ext4_check_bdev_write_error(sb);
if (ext4_handle_valid(handle)) {
err = jbd2_journal_get_write_access(handle, bh);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index e4115d338f10..202c76996b62 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4476,12 +4476,12 @@ retry:
map.m_lblk += ret;
map.m_len = len = len - ret;
epos = (loff_t)map.m_lblk << inode->i_blkbits;
- inode->i_ctime = current_time(inode);
+ inode_set_ctime_current(inode);
if (new_size) {
if (epos > new_size)
epos = new_size;
if (ext4_update_inode_size(inode, epos) & 0x1)
- inode->i_mtime = inode->i_ctime;
+ inode->i_mtime = inode_get_ctime(inode);
}
ret2 = ext4_mark_inode_dirty(handle, inode);
ext4_update_inode_fsync_trans(handle, inode, 1);
@@ -4617,7 +4617,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
/* Now release the pages and zero block aligned part of pages */
truncate_pagecache_range(inode, start, end - 1);
- inode->i_mtime = inode->i_ctime = current_time(inode);
+ inode->i_mtime = inode_set_ctime_current(inode);
ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
flags);
@@ -4642,7 +4642,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
goto out_mutex;
}
- inode->i_mtime = inode->i_ctime = current_time(inode);
+ inode->i_mtime = inode_set_ctime_current(inode);
if (new_size)
ext4_update_inode_size(inode, new_size);
ret = ext4_mark_inode_dirty(handle, inode);
@@ -5378,7 +5378,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)
up_write(&EXT4_I(inode)->i_data_sem);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
- inode->i_mtime = inode->i_ctime = current_time(inode);
+ inode->i_mtime = inode_set_ctime_current(inode);
ret = ext4_mark_inode_dirty(handle, inode);
ext4_update_inode_fsync_trans(handle, inode, 1);
@@ -5488,7 +5488,7 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len)
/* Expand file to avoid data loss if there is error while shifting */
inode->i_size += len;
EXT4_I(inode)->i_disksize += len;
- inode->i_mtime = inode->i_ctime = current_time(inode);
+ inode->i_mtime = inode_set_ctime_current(inode);
ret = ext4_mark_inode_dirty(handle, inode);
if (ret)
goto out_stop;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index c457c8517f0f..2dc3f8301225 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -723,8 +723,7 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
}
#ifdef CONFIG_FS_DAX
-static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
- enum page_entry_size pe_size)
+static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf, unsigned int order)
{
int error = 0;
vm_fault_t result;
@@ -740,7 +739,7 @@ static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf,
* read-only.
*
* We check for VM_SHARED rather than vmf->cow_page since the latter is
- * unset for pe_size != PE_SIZE_PTE (i.e. only in do_cow_fault); for
+ * unset for order != 0 (i.e. only in do_cow_fault); for
* other sizes, dax_iomap_fault will handle splitting / fallback so that
* we eventually come back with a COW page.
*/
@@ -764,7 +763,7 @@ retry:
} else {
filemap_invalidate_lock_shared(mapping);
}
- result = dax_iomap_fault(vmf, pe_size, &pfn, &error, &ext4_iomap_ops);
+ result = dax_iomap_fault(vmf, order, &pfn, &error, &ext4_iomap_ops);
if (write) {
ext4_journal_stop(handle);
@@ -773,7 +772,7 @@ retry:
goto retry;
/* Handling synchronous page fault? */
if (result & VM_FAULT_NEEDDSYNC)
- result = dax_finish_sync_fault(vmf, pe_size, pfn);
+ result = dax_finish_sync_fault(vmf, order, pfn);
filemap_invalidate_unlock_shared(mapping);
sb_end_pagefault(sb);
} else {
@@ -785,7 +784,7 @@ retry:
static vm_fault_t ext4_dax_fault(struct vm_fault *vmf)
{
- return ext4_dax_huge_fault(vmf, PE_SIZE_PTE);
+ return ext4_dax_huge_fault(vmf, 0);
}
static const struct vm_operations_struct ext4_dax_vm_ops = {
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 754f961cd9fd..48abef5f23e7 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1250,7 +1250,7 @@ got:
inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb);
/* This is the optimal IO size (for stat), not the fs block size */
inode->i_blocks = 0;
- inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
+ inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode);
ei->i_crtime = inode->i_mtime;
memset(ei->i_data, 0, sizeof(ei->i_data));
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index a4b7e4bc32d4..003861037374 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -1037,7 +1037,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle,
* happen is that the times are slightly out of date
* and/or different from the directory change time.
*/
- dir->i_mtime = dir->i_ctime = current_time(dir);
+ dir->i_mtime = inode_set_ctime_current(dir);
ext4_update_dx_flag(dir);
inode_inc_iversion(dir);
return 1;
@@ -1991,7 +1991,7 @@ out:
ext4_orphan_del(handle, inode);
if (err == 0) {
- inode->i_mtime = inode->i_ctime = current_time(inode);
+ inode->i_mtime = inode_set_ctime_current(inode);
err = ext4_mark_inode_dirty(handle, inode);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
diff --git a/fs/ext4/inode-test.c b/fs/ext4/inode-test.c
index 7935ea6cf92c..f0c0fd507fbc 100644
--- a/fs/ext4/inode-test.c
+++ b/fs/ext4/inode-test.c
@@ -245,9 +245,9 @@ static void inode_test_xtimestamp_decoding(struct kunit *test)
struct timestamp_expectation *test_param =
(struct timestamp_expectation *)(test->param_value);
- timestamp.tv_sec = get_32bit_time(test_param);
- ext4_decode_extra_time(&timestamp,
- cpu_to_le32(test_param->extra_bits));
+ timestamp = ext4_decode_extra_time(
+ cpu_to_le32(get_32bit_time(test_param)),
+ cpu_to_le32(test_param->extra_bits));
KUNIT_EXPECT_EQ_MSG(test,
test_param->expected.tv_sec,
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 43775a6ca505..89737d5a1614 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1569,7 +1569,7 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd,
if (folio->index < mpd->first_page)
continue;
- if (folio->index + folio_nr_pages(folio) - 1 > end)
+ if (folio_next_index(folio) - 1 > end)
continue;
BUG_ON(!folio_test_locked(folio));
BUG_ON(folio_test_writeback(folio));
@@ -2455,7 +2455,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
if (mpd->map.m_len == 0)
mpd->first_page = folio->index;
- mpd->next_page = folio->index + folio_nr_pages(folio);
+ mpd->next_page = folio_next_index(folio);
/*
* Writeout when we cannot modify metadata is simple.
* Just submit the page. For data=journal mode we
@@ -3986,7 +3986,7 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
if (IS_SYNC(inode))
ext4_handle_sync(handle);
- inode->i_mtime = inode->i_ctime = current_time(inode);
+ inode->i_mtime = inode_set_ctime_current(inode);
ret2 = ext4_mark_inode_dirty(handle, inode);
if (unlikely(ret2))
ret = ret2;
@@ -4146,7 +4146,7 @@ out_stop:
if (inode->i_nlink)
ext4_orphan_del(handle, inode);
- inode->i_mtime = inode->i_ctime = current_time(inode);
+ inode->i_mtime = inode_set_ctime_current(inode);
err2 = ext4_mark_inode_dirty(handle, inode);
if (unlikely(err2 && !err))
err = err2;
@@ -4249,7 +4249,7 @@ static int ext4_fill_raw_inode(struct inode *inode, struct ext4_inode *raw_inode
}
raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
- EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode);
+ EXT4_INODE_SET_CTIME(inode, raw_inode);
EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode);
EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode);
@@ -4858,7 +4858,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
}
}
- EXT4_INODE_GET_XTIME(i_ctime, inode, raw_inode);
+ EXT4_INODE_GET_CTIME(inode, raw_inode);
EXT4_INODE_GET_XTIME(i_mtime, inode, raw_inode);
EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode);
EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode);
@@ -4981,7 +4981,7 @@ static void __ext4_update_other_inode_time(struct super_block *sb,
spin_unlock(&inode->i_lock);
spin_lock(&ei->i_raw_lock);
- EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode);
+ EXT4_INODE_SET_CTIME(inode, raw_inode);
EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode);
EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
ext4_inode_csum_set(inode, raw_inode, ei);
@@ -5376,10 +5376,8 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
* Update c/mtime on truncate up, ext4_truncate() will
* update c/mtime in shrink case below
*/
- if (!shrink) {
- inode->i_mtime = current_time(inode);
- inode->i_ctime = inode->i_mtime;
- }
+ if (!shrink)
+ inode->i_mtime = inode_set_ctime_current(inode);
if (shrink)
ext4_fc_track_range(handle, inode,
@@ -5537,7 +5535,7 @@ int ext4_getattr(struct mnt_idmap *idmap, const struct path *path,
STATX_ATTR_NODUMP |
STATX_ATTR_VERITY);
- generic_fillattr(idmap, inode, stat);
+ generic_fillattr(idmap, request_mask, inode, stat);
return 0;
}
@@ -6140,7 +6138,7 @@ retry_alloc:
if (err == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry_alloc;
out_ret:
- ret = block_page_mkwrite_return(err);
+ ret = vmf_fs_error(err);
out:
filemap_invalidate_unlock_shared(mapping);
sb_end_pagefault(inode->i_sb);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 331859511f80..b0349f451863 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -449,7 +449,8 @@ static long swap_inode_boot_loader(struct super_block *sb,
diff = size - size_bl;
swap_inode_data(inode, inode_bl);
- inode->i_ctime = inode_bl->i_ctime = current_time(inode);
+ inode_set_ctime_current(inode);
+ inode_set_ctime_current(inode_bl);
inode_inc_iversion(inode);
inode->i_generation = get_random_u32();
@@ -663,7 +664,7 @@ static int ext4_ioctl_setflags(struct inode *inode,
ext4_set_inode_flags(inode, false);
- inode->i_ctime = current_time(inode);
+ inode_set_ctime_current(inode);
inode_inc_iversion(inode);
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
@@ -774,7 +775,7 @@ static int ext4_ioctl_setproject(struct inode *inode, __u32 projid)
}
EXT4_I(inode)->i_projid = kprojid;
- inode->i_ctime = current_time(inode);
+ inode_set_ctime_current(inode);
inode_inc_iversion(inode);
out_dirty:
rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
@@ -1266,7 +1267,7 @@ static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
}
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err == 0) {
- inode->i_ctime = current_time(inode);
+ inode_set_ctime_current(inode);
inode_inc_iversion(inode);
inode->i_generation = generation;
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index a2475b8c9fb5..21b903fe546e 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1006,14 +1006,11 @@ static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context
* fls() instead since we need to know the actual length while modifying
* goal length.
*/
- order = fls(ac->ac_g_ex.fe_len);
+ order = fls(ac->ac_g_ex.fe_len) - 1;
min_order = order - sbi->s_mb_best_avail_max_trim_order;
if (min_order < 0)
min_order = 0;
- if (1 << min_order < ac->ac_o_ex.fe_len)
- min_order = fls(ac->ac_o_ex.fe_len) + 1;
-
if (sbi->s_stripe > 0) {
/*
* We are assuming that stripe size is always a multiple of
@@ -1021,9 +1018,16 @@ static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context
*/
num_stripe_clusters = EXT4_NUM_B2C(sbi, sbi->s_stripe);
if (1 << min_order < num_stripe_clusters)
- min_order = fls(num_stripe_clusters);
+ /*
+ * We consider 1 order less because later we round
+ * up the goal len to num_stripe_clusters
+ */
+ min_order = fls(num_stripe_clusters) - 1;
}
+ if (1 << min_order < ac->ac_o_ex.fe_len)
+ min_order = fls(ac->ac_o_ex.fe_len);
+
for (i = order; i >= min_order; i--) {
int frag_order;
/*
@@ -4761,8 +4765,8 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
int order, i;
struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
struct ext4_locality_group *lg;
- struct ext4_prealloc_space *tmp_pa, *cpa = NULL;
- ext4_lblk_t tmp_pa_start, tmp_pa_end;
+ struct ext4_prealloc_space *tmp_pa = NULL, *cpa = NULL;
+ loff_t tmp_pa_end;
struct rb_node *iter;
ext4_fsblk_t goal_block;
@@ -4770,47 +4774,151 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
if (!(ac->ac_flags & EXT4_MB_HINT_DATA))
return false;
- /* first, try per-file preallocation */
+ /*
+ * first, try per-file preallocation by searching the inode pa rbtree.
+ *
+ * Here, we can't do a direct traversal of the tree because
+ * ext4_mb_discard_group_preallocation() can paralelly mark the pa
+ * deleted and that can cause direct traversal to skip some entries.
+ */
read_lock(&ei->i_prealloc_lock);
+
+ if (RB_EMPTY_ROOT(&ei->i_prealloc_node)) {
+ goto try_group_pa;
+ }
+
+ /*
+ * Step 1: Find a pa with logical start immediately adjacent to the
+ * original logical start. This could be on the left or right.
+ *
+ * (tmp_pa->pa_lstart never changes so we can skip locking for it).
+ */
for (iter = ei->i_prealloc_node.rb_node; iter;
iter = ext4_mb_pa_rb_next_iter(ac->ac_o_ex.fe_logical,
- tmp_pa_start, iter)) {
+ tmp_pa->pa_lstart, iter)) {
tmp_pa = rb_entry(iter, struct ext4_prealloc_space,
pa_node.inode_node);
+ }
- /* all fields in this condition don't change,
- * so we can skip locking for them */
- tmp_pa_start = tmp_pa->pa_lstart;
- tmp_pa_end = tmp_pa->pa_lstart + EXT4_C2B(sbi, tmp_pa->pa_len);
-
- /* original request start doesn't lie in this PA */
- if (ac->ac_o_ex.fe_logical < tmp_pa_start ||
- ac->ac_o_ex.fe_logical >= tmp_pa_end)
- continue;
+ /*
+ * Step 2: The adjacent pa might be to the right of logical start, find
+ * the left adjacent pa. After this step we'd have a valid tmp_pa whose
+ * logical start is towards the left of original request's logical start
+ */
+ if (tmp_pa->pa_lstart > ac->ac_o_ex.fe_logical) {
+ struct rb_node *tmp;
+ tmp = rb_prev(&tmp_pa->pa_node.inode_node);
- /* non-extent files can't have physical blocks past 2^32 */
- if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) &&
- (tmp_pa->pa_pstart + EXT4_C2B(sbi, tmp_pa->pa_len) >
- EXT4_MAX_BLOCK_FILE_PHYS)) {
+ if (tmp) {
+ tmp_pa = rb_entry(tmp, struct ext4_prealloc_space,
+ pa_node.inode_node);
+ } else {
/*
- * Since PAs don't overlap, we won't find any
- * other PA to satisfy this.
+ * If there is no adjacent pa to the left then finding
+ * an overlapping pa is not possible hence stop searching
+ * inode pa tree
*/
- break;
+ goto try_group_pa;
}
+ }
+
+ BUG_ON(!(tmp_pa && tmp_pa->pa_lstart <= ac->ac_o_ex.fe_logical));
- /* found preallocated blocks, use them */
+ /*
+ * Step 3: If the left adjacent pa is deleted, keep moving left to find
+ * the first non deleted adjacent pa. After this step we should have a
+ * valid tmp_pa which is guaranteed to be non deleted.
+ */
+ for (iter = &tmp_pa->pa_node.inode_node;; iter = rb_prev(iter)) {
+ if (!iter) {
+ /*
+ * no non deleted left adjacent pa, so stop searching
+ * inode pa tree
+ */
+ goto try_group_pa;
+ }
+ tmp_pa = rb_entry(iter, struct ext4_prealloc_space,
+ pa_node.inode_node);
spin_lock(&tmp_pa->pa_lock);
- if (tmp_pa->pa_deleted == 0 && tmp_pa->pa_free &&
- likely(ext4_mb_pa_goal_check(ac, tmp_pa))) {
- atomic_inc(&tmp_pa->pa_count);
- ext4_mb_use_inode_pa(ac, tmp_pa);
+ if (tmp_pa->pa_deleted == 0) {
+ /*
+ * We will keep holding the pa_lock from
+ * this point on because we don't want group discard
+ * to delete this pa underneath us. Since group
+ * discard is anyways an ENOSPC operation it
+ * should be okay for it to wait a few more cycles.
+ */
+ break;
+ } else {
spin_unlock(&tmp_pa->pa_lock);
- read_unlock(&ei->i_prealloc_lock);
- return true;
}
+ }
+
+ BUG_ON(!(tmp_pa && tmp_pa->pa_lstart <= ac->ac_o_ex.fe_logical));
+ BUG_ON(tmp_pa->pa_deleted == 1);
+
+ /*
+ * Step 4: We now have the non deleted left adjacent pa. Only this
+ * pa can possibly satisfy the request hence check if it overlaps
+ * original logical start and stop searching if it doesn't.
+ */
+ tmp_pa_end = (loff_t)tmp_pa->pa_lstart + EXT4_C2B(sbi, tmp_pa->pa_len);
+
+ if (ac->ac_o_ex.fe_logical >= tmp_pa_end) {
spin_unlock(&tmp_pa->pa_lock);
+ goto try_group_pa;
+ }
+
+ /* non-extent files can't have physical blocks past 2^32 */
+ if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) &&
+ (tmp_pa->pa_pstart + EXT4_C2B(sbi, tmp_pa->pa_len) >
+ EXT4_MAX_BLOCK_FILE_PHYS)) {
+ /*
+ * Since PAs don't overlap, we won't find any other PA to
+ * satisfy this.
+ */
+ spin_unlock(&tmp_pa->pa_lock);
+ goto try_group_pa;
+ }
+
+ if (tmp_pa->pa_free && likely(ext4_mb_pa_goal_check(ac, tmp_pa))) {
+ atomic_inc(&tmp_pa->pa_count);
+ ext4_mb_use_inode_pa(ac, tmp_pa);
+ spin_unlock(&tmp_pa->pa_lock);
+ read_unlock(&ei->i_prealloc_lock);
+ return true;
+ } else {
+ /*
+ * We found a valid overlapping pa but couldn't use it because
+ * it had no free blocks. This should ideally never happen
+ * because:
+ *
+ * 1. When a new inode pa is added to rbtree it must have
+ * pa_free > 0 since otherwise we won't actually need
+ * preallocation.
+ *
+ * 2. An inode pa that is in the rbtree can only have it's
+ * pa_free become zero when another thread calls:
+ * ext4_mb_new_blocks
+ * ext4_mb_use_preallocated
+ * ext4_mb_use_inode_pa
+ *
+ * 3. Further, after the above calls make pa_free == 0, we will
+ * immediately remove it from the rbtree in:
+ * ext4_mb_new_blocks
+ * ext4_mb_release_context
+ * ext4_mb_put_pa
+ *
+ * 4. Since the pa_free becoming 0 and pa_free getting removed
+ * from tree both happen in ext4_mb_new_blocks, which is always
+ * called with i_data_sem held for data allocations, we can be
+ * sure that another process will never see a pa in rbtree with
+ * pa_free == 0.
+ */
+ WARN_ON_ONCE(tmp_pa->pa_free == 0);
}
+ spin_unlock(&tmp_pa->pa_lock);
+try_group_pa:
read_unlock(&ei->i_prealloc_lock);
/* can we use group allocation? */
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index b5af2fc03b2f..18a9e7c47975 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -340,10 +340,8 @@ again:
ext4_double_up_write_data_sem(orig_inode, donor_inode);
goto data_copy;
}
- if ((folio_has_private(folio[0]) &&
- !filemap_release_folio(folio[0], 0)) ||
- (folio_has_private(folio[1]) &&
- !filemap_release_folio(folio[1], 0))) {
+ if (!filemap_release_folio(folio[0], 0) ||
+ !filemap_release_folio(folio[1], 0)) {
*err = -EBUSY;
goto drop_data_sem;
}
@@ -362,10 +360,8 @@ data_copy:
/* At this point all buffers in range are uptodate, old mapping layout
* is no longer required, try to drop it now. */
- if ((folio_has_private(folio[0]) &&
- !filemap_release_folio(folio[0], 0)) ||
- (folio_has_private(folio[1]) &&
- !filemap_release_folio(folio[1], 0))) {
+ if (!filemap_release_folio(folio[0], 0) ||
+ !filemap_release_folio(folio[1], 0)) {
*err = -EBUSY;
goto unlock_folios;
}
@@ -392,14 +388,11 @@ data_copy:
for (i = 0; i < block_len_in_page; i++) {
*err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0);
if (*err < 0)
- break;
+ goto repair_branches;
bh = bh->b_this_page;
}
- if (!*err)
- *err = block_commit_write(&folio[0]->page, from, from + replaced_size);
- if (unlikely(*err < 0))
- goto repair_branches;
+ block_commit_write(&folio[0]->page, from, from + replaced_size);
/* Even in case of data=writeback it is reasonable to pin
* inode to transaction, to prevent unexpected data loss */
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 0caf6c730ce3..933ad03f4f58 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2203,7 +2203,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
* happen is that the times are slightly out of date
* and/or different from the directory change time.
*/
- dir->i_mtime = dir->i_ctime = current_time(dir);
+ dir->i_mtime = inode_set_ctime_current(dir);
ext4_update_dx_flag(dir);
inode_inc_iversion(dir);
err2 = ext4_mark_inode_dirty(handle, dir);
@@ -3197,7 +3197,8 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
* recovery. */
inode->i_size = 0;
ext4_orphan_add(handle, inode);
- inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode);
+ dir->i_mtime = inode_set_ctime_current(dir);
+ inode_set_ctime_current(inode);
retval = ext4_mark_inode_dirty(handle, inode);
if (retval)
goto end_rmdir;
@@ -3271,7 +3272,7 @@ int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
retval = ext4_delete_entry(handle, dir, de, bh);
if (retval)
goto out_handle;
- dir->i_ctime = dir->i_mtime = current_time(dir);
+ dir->i_mtime = inode_set_ctime_current(dir);
ext4_update_dx_flag(dir);
retval = ext4_mark_inode_dirty(handle, dir);
if (retval)
@@ -3286,7 +3287,7 @@ int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
drop_nlink(inode);
if (!inode->i_nlink)
ext4_orphan_add(handle, inode);
- inode->i_ctime = current_time(inode);
+ inode_set_ctime_current(inode);
retval = ext4_mark_inode_dirty(handle, inode);
if (dentry && !retval)
ext4_fc_track_unlink(handle, dentry);
@@ -3463,7 +3464,7 @@ retry:
if (IS_DIRSYNC(dir))
ext4_handle_sync(handle);
- inode->i_ctime = current_time(inode);
+ inode_set_ctime_current(inode);
ext4_inc_count(inode);
ihold(inode);
@@ -3641,8 +3642,7 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent,
if (ext4_has_feature_filetype(ent->dir->i_sb))
ent->de->file_type = file_type;
inode_inc_iversion(ent->dir);
- ent->dir->i_ctime = ent->dir->i_mtime =
- current_time(ent->dir);
+ ent->dir->i_mtime = inode_set_ctime_current(ent->dir);
retval = ext4_mark_inode_dirty(handle, ent->dir);
BUFFER_TRACE(ent->bh, "call ext4_handle_dirty_metadata");
if (!ent->inlined) {
@@ -3941,7 +3941,7 @@ static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir,
* Like most other Unix systems, set the ctime for inodes on a
* rename.
*/
- old.inode->i_ctime = current_time(old.inode);
+ inode_set_ctime_current(old.inode);
retval = ext4_mark_inode_dirty(handle, old.inode);
if (unlikely(retval))
goto end_rename;
@@ -3955,9 +3955,9 @@ static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir,
if (new.inode) {
ext4_dec_count(new.inode);
- new.inode->i_ctime = current_time(new.inode);
+ inode_set_ctime_current(new.inode);
}
- old.dir->i_ctime = old.dir->i_mtime = current_time(old.dir);
+ old.dir->i_mtime = inode_set_ctime_current(old.dir);
ext4_update_dx_flag(old.dir);
if (old.dir_bh) {
retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
@@ -4053,7 +4053,6 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
};
u8 new_file_type;
int retval;
- struct timespec64 ctime;
if ((ext4_test_inode_flag(new_dir, EXT4_INODE_PROJINHERIT) &&
!projid_eq(EXT4_I(new_dir)->i_projid,
@@ -4147,9 +4146,8 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
* Like most other Unix systems, set the ctime for inodes on a
* rename.
*/
- ctime = current_time(old.inode);
- old.inode->i_ctime = ctime;
- new.inode->i_ctime = ctime;
+ inode_set_ctime_current(old.inode);
+ inode_set_ctime_current(new.inode);
retval = ext4_mark_inode_dirty(handle, old.inode);
if (unlikely(retval))
goto end_rename;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c94ebf704616..73547d2334fd 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -93,6 +93,7 @@ static int ext4_get_tree(struct fs_context *fc);
static int ext4_reconfigure(struct fs_context *fc);
static void ext4_fc_free(struct fs_context *fc);
static int ext4_init_fs_context(struct fs_context *fc);
+static void ext4_kill_sb(struct super_block *sb);
static const struct fs_parameter_spec ext4_param_specs[];
/*
@@ -135,12 +136,12 @@ static struct file_system_type ext2_fs_type = {
.name = "ext2",
.init_fs_context = ext4_init_fs_context,
.parameters = ext4_param_specs,
- .kill_sb = kill_block_super,
+ .kill_sb = ext4_kill_sb,
.fs_flags = FS_REQUIRES_DEV,
};
MODULE_ALIAS_FS("ext2");
MODULE_ALIAS("ext2");
-#define IS_EXT2_SB(sb) ((sb)->s_bdev->bd_holder == &ext2_fs_type)
+#define IS_EXT2_SB(sb) ((sb)->s_type == &ext2_fs_type)
#else
#define IS_EXT2_SB(sb) (0)
#endif
@@ -151,12 +152,12 @@ static struct file_system_type ext3_fs_type = {
.name = "ext3",
.init_fs_context = ext4_init_fs_context,
.parameters = ext4_param_specs,
- .kill_sb = kill_block_super,
+ .kill_sb = ext4_kill_sb,
.fs_flags = FS_REQUIRES_DEV,
};
MODULE_ALIAS_FS("ext3");
MODULE_ALIAS("ext3");
-#define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type)
+#define IS_EXT3_SB(sb) ((sb)->s_type == &ext3_fs_type)
static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
@@ -1096,15 +1097,6 @@ void ext4_update_dynamic_rev(struct super_block *sb)
*/
}
-static void ext4_bdev_mark_dead(struct block_device *bdev)
-{
- ext4_force_shutdown(bdev->bd_holder, EXT4_GOING_FLAGS_NOLOGFLUSH);
-}
-
-static const struct blk_holder_ops ext4_holder_ops = {
- .mark_dead = ext4_bdev_mark_dead,
-};
-
/*
* Open the external journal device
*/
@@ -1113,7 +1105,7 @@ static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb)
struct block_device *bdev;
bdev = blkdev_get_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE, sb,
- &ext4_holder_ops);
+ &fs_holder_ops);
if (IS_ERR(bdev))
goto fail;
return bdev;
@@ -1125,25 +1117,6 @@ fail:
return NULL;
}
-/*
- * Release the journal device
- */
-static void ext4_blkdev_remove(struct ext4_sb_info *sbi)
-{
- struct block_device *bdev;
- bdev = sbi->s_journal_bdev;
- if (bdev) {
- /*
- * Invalidate the journal device's buffers. We don't want them
- * floating about in memory - the physical journal device may
- * hotswapped, and it breaks the `ro-after' testing code.
- */
- invalidate_bdev(bdev);
- blkdev_put(bdev, sbi->s_sb);
- sbi->s_journal_bdev = NULL;
- }
-}
-
static inline struct inode *orphan_list_entry(struct list_head *l)
{
return &list_entry(l, struct ext4_inode_info, i_orphan)->vfs_inode;
@@ -1339,8 +1312,13 @@ static void ext4_put_super(struct super_block *sb)
sync_blockdev(sb->s_bdev);
invalidate_bdev(sb->s_bdev);
if (sbi->s_journal_bdev) {
+ /*
+ * Invalidate the journal device's buffers. We don't want them
+ * floating about in memory - the physical journal device may
+ * hotswapped, and it breaks the `ro-after' testing code.
+ */
sync_blockdev(sbi->s_journal_bdev);
- ext4_blkdev_remove(sbi);
+ invalidate_bdev(sbi->s_journal_bdev);
}
ext4_xattr_destroy_cache(sbi->s_ea_inode_cache);
@@ -5572,7 +5550,6 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
spin_lock_init(&sbi->s_bdev_wb_lock);
errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err,
&sbi->s_bdev_wb_err);
- sb->s_bdev->bd_super = sb;
EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
ext4_orphan_cleanup(sb, es);
EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
@@ -5664,9 +5641,11 @@ failed_mount:
kfree(get_qf_name(sb, sbi, i));
#endif
fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
- /* ext4_blkdev_remove() calls kill_bdev(), release bh before it. */
brelse(sbi->s_sbh);
- ext4_blkdev_remove(sbi);
+ if (sbi->s_journal_bdev) {
+ invalidate_bdev(sbi->s_journal_bdev);
+ blkdev_put(sbi->s_journal_bdev, sb);
+ }
out_fail:
invalidate_bdev(sb->s_bdev);
sb->s_fs_info = NULL;
@@ -5854,7 +5833,10 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
if (WARN_ON_ONCE(!ext4_has_feature_journal(sb)))
return NULL;
+ /* see get_tree_bdev why this is needed and safe */
+ up_write(&sb->s_umount);
bdev = ext4_blkdev_get(j_dev, sb);
+ down_write(&sb->s_umount);
if (bdev == NULL)
return NULL;
@@ -7103,7 +7085,7 @@ static int ext4_quota_off(struct super_block *sb, int type)
}
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);
+ inode->i_mtime = inode_set_ctime_current(inode);
err = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
out_unlock:
@@ -7273,13 +7255,24 @@ static inline int ext3_feature_set_ok(struct super_block *sb)
return 1;
}
+static void ext4_kill_sb(struct super_block *sb)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct block_device *journal_bdev = sbi ? sbi->s_journal_bdev : NULL;
+
+ kill_block_super(sb);
+
+ if (journal_bdev)
+ blkdev_put(journal_bdev, sb);
+}
+
static struct file_system_type ext4_fs_type = {
.owner = THIS_MODULE,
.name = "ext4",
.init_fs_context = ext4_init_fs_context,
.parameters = ext4_param_specs,
- .kill_sb = kill_block_super,
- .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
+ .kill_sb = ext4_kill_sb,
+ .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME,
};
MODULE_ALIAS_FS("ext4");
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 321e3a888c20..281e1bfbbe3e 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -356,13 +356,13 @@ ext4_xattr_inode_hash(struct ext4_sb_info *sbi, const void *buffer, size_t size)
static u64 ext4_xattr_inode_get_ref(struct inode *ea_inode)
{
- return ((u64)ea_inode->i_ctime.tv_sec << 32) |
+ return ((u64) inode_get_ctime(ea_inode).tv_sec << 32) |
(u32) inode_peek_iversion_raw(ea_inode);
}
static void ext4_xattr_inode_set_ref(struct inode *ea_inode, u64 ref_count)
{
- ea_inode->i_ctime.tv_sec = (u32)(ref_count >> 32);
+ inode_set_ctime(ea_inode, (u32)(ref_count >> 32), 0);
inode_set_iversion_raw(ea_inode, ref_count & 0xffffffff);
}
@@ -1782,6 +1782,20 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
memmove(here, (void *)here + size,
(void *)last - (void *)here + sizeof(__u32));
memset(last, 0, size);
+
+ /*
+ * Update i_inline_off - moved ibody region might contain
+ * system.data attribute. Handling a failure here won't
+ * cause other complications for setting an xattr.
+ */
+ if (!is_block && ext4_has_inline_data(inode)) {
+ ret = ext4_find_inline_data_nolock(inode);
+ if (ret) {
+ ext4_warning_inode(inode,
+ "unable to update i_inline_off");
+ goto out;
+ }
+ }
} else if (s->not_found) {
/* Insert new name. */
size_t size = EXT4_XATTR_LEN(name_len);
@@ -2459,7 +2473,7 @@ retry_inode:
}
if (!error) {
ext4_xattr_update_super_block(handle, inode->i_sb);
- inode->i_ctime = current_time(inode);
+ inode_set_ctime_current(inode);
inode_inc_iversion(inode);
if (!value)
no_expand = 0;
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-29 16:02:33 +0300