summaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/ext4.h4
-rw-r--r--fs/ext4/extents.c66
-rw-r--r--fs/ext4/file.c16
-rw-r--r--fs/ext4/inode.c35
-rw-r--r--fs/ext4/ioctl.c4
5 files changed, 83 insertions, 42 deletions
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 18373de980f2..7d962e7f388a 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3103,8 +3103,8 @@ extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
int ext4_fileattr_set(struct mnt_idmap *idmap,
- struct dentry *dentry, struct fileattr *fa);
-int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+ struct dentry *dentry, struct file_kattr *fa);
+int ext4_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
extern void ext4_reset_inode_seed(struct inode *inode);
int ext4_update_overhead(struct super_block *sb, bool force);
int ext4_force_shutdown(struct super_block *sb, u32 flags);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index b543a46fc809..b43aa82c1b39 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4501,6 +4501,8 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
struct ext4_map_blocks map;
unsigned int credits;
loff_t epos, old_size = i_size_read(inode);
+ unsigned int blkbits = inode->i_blkbits;
+ bool alloc_zero = false;
BUG_ON(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS));
map.m_lblk = offset;
@@ -4514,6 +4516,17 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
/*
+ * Do the actual write zero during a running journal transaction
+ * costs a lot. First allocate an unwritten extent and then
+ * convert it to written after zeroing it out.
+ */
+ if (flags & EXT4_GET_BLOCKS_ZERO) {
+ flags &= ~EXT4_GET_BLOCKS_ZERO;
+ flags |= EXT4_GET_BLOCKS_UNWRIT_EXT;
+ alloc_zero = true;
+ }
+
+ /*
* credits to insert 1 extent into extent tree
*/
credits = ext4_chunk_trans_blocks(inode, len);
@@ -4549,9 +4562,7 @@ retry:
* allow a full retry cycle for any remaining allocations
*/
retries = 0;
- map.m_lblk += ret;
- map.m_len = len = len - ret;
- epos = (loff_t)map.m_lblk << inode->i_blkbits;
+ epos = (loff_t)(map.m_lblk + ret) << blkbits;
inode_set_ctime_current(inode);
if (new_size) {
if (epos > new_size)
@@ -4571,6 +4582,21 @@ retry:
ret2 = ret3 ? ret3 : ret2;
if (unlikely(ret2))
break;
+
+ if (alloc_zero &&
+ (map.m_flags & (EXT4_MAP_MAPPED | EXT4_MAP_UNWRITTEN))) {
+ ret2 = ext4_issue_zeroout(inode, map.m_lblk, map.m_pblk,
+ map.m_len);
+ if (likely(!ret2))
+ ret2 = ext4_convert_unwritten_extents(NULL,
+ inode, (loff_t)map.m_lblk << blkbits,
+ (loff_t)map.m_len << blkbits);
+ if (ret2)
+ break;
+ }
+
+ map.m_lblk += ret;
+ map.m_len = len = len - ret;
}
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
@@ -4636,7 +4662,11 @@ static long ext4_zero_range(struct file *file, loff_t offset,
if (end_lblk > start_lblk) {
ext4_lblk_t zero_blks = end_lblk - start_lblk;
- flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | EXT4_EX_NOCACHE);
+ if (mode & FALLOC_FL_WRITE_ZEROES)
+ flags = EXT4_GET_BLOCKS_CREATE_ZERO | EXT4_EX_NOCACHE;
+ else
+ flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
+ EXT4_EX_NOCACHE);
ret = ext4_alloc_file_blocks(file, start_lblk, zero_blks,
new_size, flags);
if (ret)
@@ -4745,11 +4775,18 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
if (IS_ENCRYPTED(inode) &&
(mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)))
return -EOPNOTSUPP;
+ /*
+ * Don't allow writing zeroes if the underlying device does not
+ * enable the unmap write zeroes operation.
+ */
+ if ((mode & FALLOC_FL_WRITE_ZEROES) &&
+ !bdev_write_zeroes_unmap_sectors(inode->i_sb->s_bdev))
+ return -EOPNOTSUPP;
/* Return error if mode is not supported */
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
- FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |
- FALLOC_FL_INSERT_RANGE))
+ FALLOC_FL_ZERO_RANGE | FALLOC_FL_COLLAPSE_RANGE |
+ FALLOC_FL_INSERT_RANGE | FALLOC_FL_WRITE_ZEROES))
return -EOPNOTSUPP;
inode_lock(inode);
@@ -4780,16 +4817,23 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
if (ret)
goto out_invalidate_lock;
- if (mode & FALLOC_FL_PUNCH_HOLE)
+ switch (mode & FALLOC_FL_MODE_MASK) {
+ case FALLOC_FL_PUNCH_HOLE:
ret = ext4_punch_hole(file, offset, len);
- else if (mode & FALLOC_FL_COLLAPSE_RANGE)
+ break;
+ case FALLOC_FL_COLLAPSE_RANGE:
ret = ext4_collapse_range(file, offset, len);
- else if (mode & FALLOC_FL_INSERT_RANGE)
+ break;
+ case FALLOC_FL_INSERT_RANGE:
ret = ext4_insert_range(file, offset, len);
- else if (mode & FALLOC_FL_ZERO_RANGE)
+ break;
+ case FALLOC_FL_ZERO_RANGE:
+ case FALLOC_FL_WRITE_ZEROES:
ret = ext4_zero_range(file, offset, len, mode);
- else
+ break;
+ default:
ret = -EOPNOTSUPP;
+ }
out_invalidate_lock:
filemap_invalidate_unlock(mapping);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 21df81347147..48908ce0c3ea 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -804,9 +804,10 @@ static const struct vm_operations_struct ext4_file_vm_ops = {
.page_mkwrite = ext4_page_mkwrite,
};
-static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
+static int ext4_file_mmap_prepare(struct vm_area_desc *desc)
{
int ret;
+ struct file *file = desc->file;
struct inode *inode = file->f_mapping->host;
struct dax_device *dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
@@ -821,15 +822,15 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
* We don't support synchronous mappings for non-DAX files and
* for DAX files if underneath dax_device is not synchronous.
*/
- if (!daxdev_mapping_supported(vma, dax_dev))
+ if (!daxdev_mapping_supported(desc->vm_flags, file_inode(file), dax_dev))
return -EOPNOTSUPP;
file_accessed(file);
if (IS_DAX(file_inode(file))) {
- vma->vm_ops = &ext4_dax_vm_ops;
- vm_flags_set(vma, VM_HUGEPAGE);
+ desc->vm_ops = &ext4_dax_vm_ops;
+ desc->vm_flags |= VM_HUGEPAGE;
} else {
- vma->vm_ops = &ext4_file_vm_ops;
+ desc->vm_ops = &ext4_file_vm_ops;
}
return 0;
}
@@ -968,7 +969,7 @@ const struct file_operations ext4_file_operations = {
#ifdef CONFIG_COMPAT
.compat_ioctl = ext4_compat_ioctl,
#endif
- .mmap = ext4_file_mmap,
+ .mmap_prepare = ext4_file_mmap_prepare,
.open = ext4_file_open,
.release = ext4_release_file,
.fsync = ext4_sync_file,
@@ -977,7 +978,8 @@ const struct file_operations ext4_file_operations = {
.splice_write = iter_file_splice_write,
.fallocate = ext4_fallocate,
.fop_flags = FOP_MMAP_SYNC | FOP_BUFFER_RASYNC |
- FOP_DIO_PARALLEL_WRITE,
+ FOP_DIO_PARALLEL_WRITE |
+ FOP_DONTCACHE,
};
const struct inode_operations ext4_file_inode_operations = {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index be9a4cba35fd..5c7024051f1e 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1252,7 +1252,8 @@ int ext4_block_write_begin(handle_t *handle, struct folio *folio,
* and the ext4_write_end(). So doing the jbd2_journal_start at the start of
* ext4_write_begin() is the right place.
*/
-static int ext4_write_begin(struct file *file, struct address_space *mapping,
+static int ext4_write_begin(const struct kiocb *iocb,
+ struct address_space *mapping,
loff_t pos, unsigned len,
struct folio **foliop, void **fsdata)
{
@@ -1263,7 +1264,6 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
struct folio *folio;
pgoff_t index;
unsigned from, to;
- fgf_t fgp = FGP_WRITEBEGIN;
ret = ext4_emergency_state(inode->i_sb);
if (unlikely(ret))
@@ -1287,16 +1287,14 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
}
/*
- * __filemap_get_folio() can take a long time if the
+ * write_begin_get_folio() can take a long time if the
* system is thrashing due to memory pressure, or if the folio
* is being written back. So grab it first before we start
* the transaction handle. This also allows us to allocate
* the folio (if needed) without using GFP_NOFS.
*/
retry_grab:
- fgp |= fgf_set_order(len);
- folio = __filemap_get_folio(mapping, index, fgp,
- mapping_gfp_mask(mapping));
+ folio = write_begin_get_folio(iocb, mapping, index, len);
if (IS_ERR(folio))
return PTR_ERR(folio);
@@ -1400,12 +1398,12 @@ static int write_end_fn(handle_t *handle, struct inode *inode,
/*
* We need to pick up the new inode size which generic_commit_write gave us
- * `file' can be NULL - eg, when called from page_symlink().
+ * `iocb` can be NULL - eg, when called from page_symlink().
*
* ext4 never places buffers on inode->i_mapping->i_private_list. metadata
* buffers are managed internally.
*/
-static int ext4_write_end(struct file *file,
+static int ext4_write_end(const struct kiocb *iocb,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct folio *folio, void *fsdata)
@@ -1424,7 +1422,7 @@ static int ext4_write_end(struct file *file,
return ext4_write_inline_data_end(inode, pos, len, copied,
folio);
- copied = block_write_end(file, mapping, pos, len, copied, folio, fsdata);
+ copied = block_write_end(pos, len, copied, folio);
/*
* it's important to update i_size while still holding folio lock:
* page writeout could otherwise come in and zero beyond i_size.
@@ -1510,7 +1508,7 @@ static void ext4_journalled_zero_new_buffers(handle_t *handle,
} while (bh != head);
}
-static int ext4_journalled_write_end(struct file *file,
+static int ext4_journalled_write_end(const struct kiocb *iocb,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct folio *folio, void *fsdata)
@@ -3036,7 +3034,8 @@ static int ext4_nonda_switch(struct super_block *sb)
return 0;
}
-static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
+static int ext4_da_write_begin(const struct kiocb *iocb,
+ struct address_space *mapping,
loff_t pos, unsigned len,
struct folio **foliop, void **fsdata)
{
@@ -3044,7 +3043,6 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
struct folio *folio;
pgoff_t index;
struct inode *inode = mapping->host;
- fgf_t fgp = FGP_WRITEBEGIN;
ret = ext4_emergency_state(inode->i_sb);
if (unlikely(ret))
@@ -3054,7 +3052,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
if (ext4_nonda_switch(inode->i_sb) || ext4_verity_in_progress(inode)) {
*fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
- return ext4_write_begin(file, mapping, pos,
+ return ext4_write_begin(iocb, mapping, pos,
len, foliop, fsdata);
}
*fsdata = (void *)0;
@@ -3070,9 +3068,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
}
retry:
- fgp |= fgf_set_order(len);
- folio = __filemap_get_folio(mapping, index, fgp,
- mapping_gfp_mask(mapping));
+ folio = write_begin_get_folio(iocb, mapping, index, len);
if (IS_ERR(folio))
return PTR_ERR(folio);
@@ -3144,8 +3140,7 @@ static int ext4_da_do_write_end(struct address_space *mapping,
* block_write_end() will mark the inode as dirty with I_DIRTY_PAGES
* flag, which all that's needed to trigger page writeback.
*/
- copied = block_write_end(NULL, mapping, pos, len, copied,
- folio, NULL);
+ copied = block_write_end(pos, len, copied, folio);
new_i_size = pos + copied;
/*
@@ -3196,7 +3191,7 @@ static int ext4_da_do_write_end(struct address_space *mapping,
return copied;
}
-static int ext4_da_write_end(struct file *file,
+static int ext4_da_write_end(const struct kiocb *iocb,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct folio *folio, void *fsdata)
@@ -3205,7 +3200,7 @@ static int ext4_da_write_end(struct file *file,
int write_mode = (int)(unsigned long)fsdata;
if (write_mode == FALL_BACK_TO_NONDELALLOC)
- return ext4_write_end(file, mapping, pos,
+ return ext4_write_end(iocb, mapping, pos,
len, copied, folio, fsdata);
trace_ext4_da_write_end(inode, pos, len, copied);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 5668a17458ae..84e3c73952d7 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -980,7 +980,7 @@ group_add_out:
return err;
}
-int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+int ext4_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
{
struct inode *inode = d_inode(dentry);
struct ext4_inode_info *ei = EXT4_I(inode);
@@ -997,7 +997,7 @@ int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa)
}
int ext4_fileattr_set(struct mnt_idmap *idmap,
- struct dentry *dentry, struct fileattr *fa)
+ struct dentry *dentry, struct file_kattr *fa)
{
struct inode *inode = d_inode(dentry);
u32 flags = fa->flags;
generated by cgit (git 2.34.1) at 2025-07-29 08:43:49 +0000