summaryrefslogtreecommitdiff
path: root/fs/f2fs/file.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/f2fs/file.c')
-rw-r--r--fs/f2fs/file.c480
1 files changed, 342 insertions, 138 deletions
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 5808d5c709a7..531379f513fa 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -21,6 +21,7 @@
#include <linux/mount.h>
#include <linux/pagevec.h>
#include <linux/random.h>
+#include <linux/uio.h>
#include <linux/uuid.h>
#include <linux/file.h>
@@ -33,6 +34,19 @@
#include "trace.h"
#include <trace/events/f2fs.h>
+static int f2fs_filemap_fault(struct vm_area_struct *vma,
+ struct vm_fault *vmf)
+{
+ struct inode *inode = file_inode(vma->vm_file);
+ int err;
+
+ down_read(&F2FS_I(inode)->i_mmap_sem);
+ err = filemap_fault(vma, vmf);
+ up_read(&F2FS_I(inode)->i_mmap_sem);
+
+ return err;
+}
+
static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
struct vm_fault *vmf)
{
@@ -60,13 +74,14 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
f2fs_balance_fs(sbi, dn.node_changed);
file_update_time(vma->vm_file);
+ down_read(&F2FS_I(inode)->i_mmap_sem);
lock_page(page);
if (unlikely(page->mapping != inode->i_mapping ||
page_offset(page) > i_size_read(inode) ||
!PageUptodate(page))) {
unlock_page(page);
err = -EFAULT;
- goto out;
+ goto out_sem;
}
/*
@@ -86,15 +101,19 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
if (!PageUptodate(page))
SetPageUptodate(page);
+ f2fs_update_iostat(sbi, APP_MAPPED_IO, F2FS_BLKSIZE);
+
trace_f2fs_vm_page_mkwrite(page, DATA);
mapped:
/* fill the page */
f2fs_wait_on_page_writeback(page, DATA, false);
/* wait for GCed encrypted page writeback */
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
- f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr);
+ if (f2fs_encrypted_file(inode))
+ f2fs_wait_on_block_writeback(sbi, dn.data_blkaddr);
+out_sem:
+ up_read(&F2FS_I(inode)->i_mmap_sem);
out:
sb_end_pagefault(inode->i_sb);
f2fs_update_time(sbi, REQ_TIME);
@@ -102,7 +121,7 @@ out:
}
static const struct vm_operations_struct f2fs_file_vm_ops = {
- .fault = filemap_fault,
+ .fault = f2fs_filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = f2fs_vm_page_mkwrite,
};
@@ -117,11 +136,6 @@ static int get_parent_ino(struct inode *inode, nid_t *pino)
if (!dentry)
return 0;
- if (update_dent_inode(inode, inode, &dentry->d_name)) {
- dput(dentry);
- return 0;
- }
-
*pino = parent_ino(dentry);
dput(dentry);
return 1;
@@ -142,8 +156,6 @@ static inline bool need_do_checkpoint(struct inode *inode)
need_cp = true;
else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
need_cp = true;
- else if (F2FS_I(inode)->xattr_ver == cur_cp_version(F2FS_CKPT(sbi)))
- need_cp = true;
else if (test_opt(sbi, FASTBOOT))
need_cp = true;
else if (sbi->active_logs == 2)
@@ -169,7 +181,6 @@ static void try_to_fix_pino(struct inode *inode)
nid_t pino;
down_write(&fi->i_sem);
- fi->xattr_ver = 0;
if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
get_parent_ino(inode, &pino)) {
f2fs_i_pino_write(inode, pino);
@@ -268,9 +279,19 @@ sync_nodes:
goto sync_nodes;
}
- ret = wait_on_node_pages_writeback(sbi, ino);
- if (ret)
- goto out;
+ /*
+ * If it's atomic_write, it's just fine to keep write ordering. So
+ * here we don't need to wait for node write completion, since we use
+ * node chain which serializes node blocks. If one of node writes are
+ * reordered, we can see simply broken chain, resulting in stopping
+ * roll-forward recovery. It means we'll recover all or none node blocks
+ * given fsync mark.
+ */
+ if (!atomic) {
+ ret = wait_on_node_pages_writeback(sbi, ino);
+ if (ret)
+ goto out;
+ }
/* once recovery info is written, don't need to tack this */
remove_ino_entry(sbi, ino, APPEND_INO);
@@ -278,7 +299,8 @@ sync_nodes:
flush_out:
remove_ino_entry(sbi, ino, UPDATE_INO);
clear_inode_flag(inode, FI_UPDATE_WRITE);
- ret = f2fs_issue_flush(sbi);
+ if (!atomic)
+ ret = f2fs_issue_flush(sbi);
f2fs_update_time(sbi, REQ_TIME);
out:
trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
@@ -375,7 +397,8 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
dn.ofs_in_node++, pgofs++,
data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
block_t blkaddr;
- blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+ blkaddr = datablock_addr(dn.inode,
+ dn.node_page, dn.ofs_in_node);
if (__found_offset(blkaddr, dirty, pgofs, whence)) {
f2fs_put_dnode(&dn);
@@ -423,14 +446,6 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
struct inode *inode = file_inode(file);
int err;
- if (f2fs_encrypted_inode(inode)) {
- err = fscrypt_get_encryption_info(inode);
- if (err)
- return 0;
- if (!f2fs_encrypted_inode(inode))
- return -ENOKEY;
- }
-
/* we don't need to use inline_data strictly */
err = f2fs_convert_inline_inode(inode);
if (err)
@@ -443,11 +458,10 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
static int f2fs_file_open(struct inode *inode, struct file *filp)
{
- int ret = generic_file_open(inode, filp);
struct dentry *dir;
- if (!ret && f2fs_encrypted_inode(inode)) {
- ret = fscrypt_get_encryption_info(inode);
+ if (f2fs_encrypted_inode(inode)) {
+ int ret = fscrypt_get_encryption_info(inode);
if (ret)
return -EACCES;
if (!fscrypt_has_encryption_key(inode))
@@ -460,7 +474,7 @@ static int f2fs_file_open(struct inode *inode, struct file *filp)
return -EPERM;
}
dput(dir);
- return ret;
+ return dquot_file_open(inode, filp);
}
int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
@@ -469,9 +483,13 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
struct f2fs_node *raw_node;
int nr_free = 0, ofs = dn->ofs_in_node, len = count;
__le32 *addr;
+ int base = 0;
+
+ if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode))
+ base = get_extra_isize(dn->inode);
raw_node = F2FS_NODE(dn->node_page);
- addr = blkaddr_in_node(raw_node) + ofs;
+ addr = blkaddr_in_node(raw_node) + base + ofs;
for (; count > 0; count--, addr++, dn->ofs_in_node++) {
block_t blkaddr = le32_to_cpu(*addr);
@@ -531,12 +549,14 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
page = get_lock_data_page(inode, index, true);
if (IS_ERR(page))
- return 0;
+ return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page);
truncate_out:
f2fs_wait_on_page_writeback(page, DATA, true);
zero_user(page, offset, PAGE_SIZE - offset);
- if (!cache_only || !f2fs_encrypted_inode(inode) ||
- !S_ISREG(inode->i_mode))
+
+ /* An encrypted inode should have a key and truncate the last page. */
+ f2fs_bug_on(F2FS_I_SB(inode), cache_only && f2fs_encrypted_inode(inode));
+ if (!cache_only)
set_page_dirty(page);
f2fs_put_page(page, 1);
return 0;
@@ -569,8 +589,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
}
if (f2fs_has_inline_data(inode)) {
- if (truncate_inline_inode(ipage, from))
- set_page_dirty(ipage);
+ truncate_inline_inode(inode, ipage, from);
f2fs_put_page(ipage, 1);
truncate_page = true;
goto out;
@@ -619,6 +638,12 @@ int f2fs_truncate(struct inode *inode)
trace_f2fs_truncate(inode);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(F2FS_I_SB(inode), FAULT_TRUNCATE)) {
+ f2fs_show_injection_info(FAULT_TRUNCATE);
+ return -EIO;
+ }
+#endif
/* we should check inline_data size */
if (!f2fs_may_inline_data(inode)) {
err = f2fs_convert_inline_inode(inode);
@@ -640,7 +665,6 @@ int f2fs_getattr(struct vfsmount *mnt,
{
struct inode *inode = d_inode(dentry);
generic_fillattr(inode, stat);
- stat->blocks <<= 3;
return 0;
}
@@ -684,14 +708,34 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
if (err)
return err;
+ if (is_quota_modification(inode, attr)) {
+ err = dquot_initialize(inode);
+ if (err)
+ return err;
+ }
+ if ((attr->ia_valid & ATTR_UID &&
+ !uid_eq(attr->ia_uid, inode->i_uid)) ||
+ (attr->ia_valid & ATTR_GID &&
+ !gid_eq(attr->ia_gid, inode->i_gid))) {
+ err = dquot_transfer(inode, attr);
+ if (err)
+ return err;
+ }
+
if (attr->ia_valid & ATTR_SIZE) {
- if (f2fs_encrypted_inode(inode) &&
- fscrypt_get_encryption_info(inode))
- return -EACCES;
+ if (f2fs_encrypted_inode(inode)) {
+ err = fscrypt_get_encryption_info(inode);
+ if (err)
+ return err;
+ if (!fscrypt_has_encryption_key(inode))
+ return -ENOKEY;
+ }
if (attr->ia_size <= i_size_read(inode)) {
+ down_write(&F2FS_I(inode)->i_mmap_sem);
truncate_setsize(inode, attr->ia_size);
err = f2fs_truncate(inode);
+ up_write(&F2FS_I(inode)->i_mmap_sem);
if (err)
return err;
} else {
@@ -699,7 +743,9 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
* do not trim all blocks after i_size if target size is
* larger than i_size.
*/
+ down_write(&F2FS_I(inode)->i_mmap_sem);
truncate_setsize(inode, attr->ia_size);
+ up_write(&F2FS_I(inode)->i_mmap_sem);
/* should convert inline inode here */
if (!f2fs_may_inline_data(inode)) {
@@ -845,12 +891,14 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
blk_start = (loff_t)pg_start << PAGE_SHIFT;
blk_end = (loff_t)pg_end << PAGE_SHIFT;
+ down_write(&F2FS_I(inode)->i_mmap_sem);
truncate_inode_pages_range(mapping, blk_start,
blk_end - 1);
f2fs_lock_op(sbi);
ret = truncate_hole(inode, pg_start, pg_end);
f2fs_unlock_op(sbi);
+ up_write(&F2FS_I(inode)->i_mmap_sem);
}
}
@@ -881,7 +929,8 @@ next_dnode:
done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, inode) -
dn.ofs_in_node, len);
for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) {
- *blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+ *blkaddr = datablock_addr(dn.inode,
+ dn.node_page, dn.ofs_in_node);
if (!is_checkpointed_data(sbi, *blkaddr)) {
if (test_opt(sbi, LFS)) {
@@ -957,15 +1006,15 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
ADDRS_PER_PAGE(dn.node_page, dst_inode) -
dn.ofs_in_node, len - i);
do {
- dn.data_blkaddr = datablock_addr(dn.node_page,
- dn.ofs_in_node);
+ dn.data_blkaddr = datablock_addr(dn.inode,
+ dn.node_page, dn.ofs_in_node);
truncate_data_blocks_range(&dn, 1);
if (do_replace[i]) {
f2fs_i_blocks_write(src_inode,
- 1, false);
+ 1, false, false);
f2fs_i_blocks_write(dst_inode,
- 1, true);
+ 1, true, false);
f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
blkaddr[i], ni.version, true, false);
@@ -1017,11 +1066,11 @@ static int __exchange_data_block(struct inode *src_inode,
while (len) {
olen = min((pgoff_t)4 * ADDRS_PER_BLOCK, len);
- src_blkaddr = f2fs_kvzalloc(sizeof(block_t) * olen, GFP_KERNEL);
+ src_blkaddr = kvzalloc(sizeof(block_t) * olen, GFP_KERNEL);
if (!src_blkaddr)
return -ENOMEM;
- do_replace = f2fs_kvzalloc(sizeof(int) * olen, GFP_KERNEL);
+ do_replace = kvzalloc(sizeof(int) * olen, GFP_KERNEL);
if (!do_replace) {
kvfree(src_blkaddr);
return -ENOMEM;
@@ -1089,16 +1138,17 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
pg_start = offset >> PAGE_SHIFT;
pg_end = (offset + len) >> PAGE_SHIFT;
+ down_write(&F2FS_I(inode)->i_mmap_sem);
/* write out all dirty pages from offset */
ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
if (ret)
- return ret;
+ goto out;
truncate_pagecache(inode, offset);
ret = f2fs_do_collapse(inode, pg_start, pg_end);
if (ret)
- return ret;
+ goto out;
/* write out all moved pages, if possible */
filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
@@ -1111,6 +1161,8 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
if (!ret)
f2fs_i_size_write(inode, new_size);
+out:
+ up_write(&F2FS_I(inode)->i_mmap_sem);
return ret;
}
@@ -1124,7 +1176,8 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
int ret;
for (; index < end; index++, dn->ofs_in_node++) {
- if (datablock_addr(dn->node_page, dn->ofs_in_node) == NULL_ADDR)
+ if (datablock_addr(dn->inode, dn->node_page,
+ dn->ofs_in_node) == NULL_ADDR)
count++;
}
@@ -1135,8 +1188,8 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
dn->ofs_in_node = ofs_in_node;
for (index = start; index < end; index++, dn->ofs_in_node++) {
- dn->data_blkaddr =
- datablock_addr(dn->node_page, dn->ofs_in_node);
+ dn->data_blkaddr = datablock_addr(dn->inode,
+ dn->node_page, dn->ofs_in_node);
/*
* reserve_new_blocks will not guarantee entire block
* allocation.
@@ -1175,9 +1228,10 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
if (ret)
return ret;
+ down_write(&F2FS_I(inode)->i_mmap_sem);
ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1);
if (ret)
- return ret;
+ goto out_sem;
truncate_pagecache_range(inode, offset, offset + len - 1);
@@ -1191,17 +1245,15 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
ret = fill_zero(inode, pg_start, off_start,
off_end - off_start);
if (ret)
- return ret;
+ goto out_sem;
- if (offset + len > new_size)
- new_size = offset + len;
new_size = max_t(loff_t, new_size, offset + len);
} else {
if (off_start) {
ret = fill_zero(inode, pg_start++, off_start,
PAGE_SIZE - off_start);
if (ret)
- return ret;
+ goto out_sem;
new_size = max_t(loff_t, new_size,
(loff_t)pg_start << PAGE_SHIFT);
@@ -1250,6 +1302,8 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
out:
if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size)
f2fs_i_size_write(inode, new_size);
+out_sem:
+ up_write(&F2FS_I(inode)->i_mmap_sem);
return ret;
}
@@ -1262,8 +1316,9 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
int ret = 0;
new_size = i_size_read(inode) + len;
- if (new_size > inode->i_sb->s_maxbytes)
- return -EFBIG;
+ ret = inode_newsize_ok(inode, new_size);
+ if (ret)
+ return ret;
if (offset >= i_size_read(inode))
return -EINVAL;
@@ -1278,14 +1333,15 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
f2fs_balance_fs(sbi, true);
+ down_write(&F2FS_I(inode)->i_mmap_sem);
ret = truncate_blocks(inode, i_size_read(inode), true);
if (ret)
- return ret;
+ goto out;
/* write out all dirty pages from offset */
ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
if (ret)
- return ret;
+ goto out;
truncate_pagecache(inode, offset);
@@ -1314,6 +1370,8 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
if (!ret)
f2fs_i_size_write(inode, new_size);
+out:
+ up_write(&F2FS_I(inode)->i_mmap_sem);
return ret;
}
@@ -1433,6 +1491,7 @@ static int f2fs_release_file(struct inode *inode, struct file *filp)
drop_inmem_pages(inode);
if (f2fs_is_volatile_file(inode)) {
clear_inode_flag(inode, FI_VOLATILE_FILE);
+ stat_dec_volatile_write(inode);
set_inode_flag(inode, FI_DROP_CACHE);
filemap_fdatawrite(inode->i_mapping);
clear_inode_flag(inode, FI_DROP_CACHE);
@@ -1440,17 +1499,20 @@ static int f2fs_release_file(struct inode *inode, struct file *filp)
return 0;
}
-#define F2FS_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL))
-#define F2FS_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL)
-
-static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
+static int f2fs_file_flush(struct file *file, fl_owner_t id)
{
- if (S_ISDIR(mode))
- return flags;
- else if (S_ISREG(mode))
- return flags & F2FS_REG_FLMASK;
- else
- return flags & F2FS_OTHER_FLMASK;
+ struct inode *inode = file_inode(file);
+
+ /*
+ * If the process doing a transaction is crashed, we should do
+ * roll-back. Otherwise, other reader/write can see corrupted database
+ * until all the writers close its file. Since this should be done
+ * before dropping file lock, it needs to do in ->flush.
+ */
+ if (f2fs_is_atomic_file(inode) &&
+ F2FS_I(inode)->inmem_task == current)
+ drop_inmem_pages(inode);
+ return 0;
}
static int f2fs_ioc_getflags(struct file *filp, unsigned long arg)
@@ -1479,28 +1541,34 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
if (ret)
return ret;
- flags = f2fs_mask_flags(inode->i_mode, flags);
-
inode_lock(inode);
+ /* Is it quota file? Do not allow user to mess with it */
+ if (IS_NOQUOTA(inode)) {
+ ret = -EPERM;
+ goto unlock_out;
+ }
+
+ flags = f2fs_mask_flags(inode->i_mode, flags);
+
oldflags = fi->i_flags;
if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
if (!capable(CAP_LINUX_IMMUTABLE)) {
- inode_unlock(inode);
ret = -EPERM;
- goto out;
+ goto unlock_out;
}
}
flags = flags & FS_FL_USER_MODIFIABLE;
flags |= oldflags & ~FS_FL_USER_MODIFIABLE;
fi->i_flags = flags;
- inode_unlock(inode);
inode->i_ctime = current_time(inode);
f2fs_set_inode_flags(inode);
-out:
+ f2fs_mark_inode_dirty_sync(inode, false);
+unlock_out:
+ inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
}
@@ -1520,6 +1588,9 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
if (!inode_owner_or_capable(inode))
return -EACCES;
+ if (!S_ISREG(inode->i_mode))
+ return -EINVAL;
+
ret = mnt_want_write_file(filp);
if (ret)
return ret;
@@ -1534,17 +1605,26 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
goto out;
set_inode_flag(inode, FI_ATOMIC_FILE);
+ set_inode_flag(inode, FI_HOT_DATA);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
if (!get_dirty_pages(inode))
- goto out;
+ goto inc_stat;
f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING,
"Unexpected flush for atomic writes: ino=%lu, npages=%u",
inode->i_ino, get_dirty_pages(inode));
ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
- if (ret)
+ if (ret) {
clear_inode_flag(inode, FI_ATOMIC_FILE);
+ clear_inode_flag(inode, FI_HOT_DATA);
+ goto out;
+ }
+
+inc_stat:
+ F2FS_I(inode)->inmem_task = current;
+ stat_inc_atomic_write(inode);
+ stat_update_max_atomic_write(inode);
out:
inode_unlock(inode);
mnt_drop_write_file(filp);
@@ -1569,15 +1649,19 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
goto err_out;
if (f2fs_is_atomic_file(inode)) {
- clear_inode_flag(inode, FI_ATOMIC_FILE);
ret = commit_inmem_pages(inode);
- if (ret) {
- set_inode_flag(inode, FI_ATOMIC_FILE);
+ if (ret)
goto err_out;
+
+ ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
+ if (!ret) {
+ clear_inode_flag(inode, FI_ATOMIC_FILE);
+ clear_inode_flag(inode, FI_HOT_DATA);
+ stat_dec_atomic_write(inode);
}
+ } else {
+ ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false);
}
-
- ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
err_out:
inode_unlock(inode);
mnt_drop_write_file(filp);
@@ -1592,6 +1676,9 @@ static int f2fs_ioc_start_volatile_write(struct file *filp)
if (!inode_owner_or_capable(inode))
return -EACCES;
+ if (!S_ISREG(inode->i_mode))
+ return -EINVAL;
+
ret = mnt_want_write_file(filp);
if (ret)
return ret;
@@ -1605,6 +1692,9 @@ static int f2fs_ioc_start_volatile_write(struct file *filp)
if (ret)
goto out;
+ stat_inc_volatile_write(inode);
+ stat_update_max_volatile_write(inode);
+
set_inode_flag(inode, FI_VOLATILE_FILE);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
out:
@@ -1660,6 +1750,7 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp)
drop_inmem_pages(inode);
if (f2fs_is_volatile_file(inode)) {
clear_inode_flag(inode, FI_VOLATILE_FILE);
+ stat_dec_volatile_write(inode);
ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
}
@@ -1705,7 +1796,7 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
f2fs_stop_checkpoint(sbi, false);
break;
case F2FS_GOING_DOWN_METAFLUSH:
- sync_meta_pages(sbi, META, LONG_MAX);
+ sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO);
f2fs_stop_checkpoint(sbi, false);
break;
default:
@@ -1766,31 +1857,16 @@ static bool uuid_is_nonzero(__u8 u[16])
static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
{
- struct fscrypt_policy policy;
struct inode *inode = file_inode(filp);
- if (copy_from_user(&policy, (struct fscrypt_policy __user *)arg,
- sizeof(policy)))
- return -EFAULT;
-
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
- return fscrypt_process_policy(filp, &policy);
+ return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
}
static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
{
- struct fscrypt_policy policy;
- struct inode *inode = file_inode(filp);
- int err;
-
- err = fscrypt_get_policy(inode, &policy);
- if (err)
- return err;
-
- if (copy_to_user((struct fscrypt_policy __user *)arg, &policy, sizeof(policy)))
- return -EFAULT;
- return 0;
+ return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
}
static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg)
@@ -1856,7 +1932,51 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
mutex_lock(&sbi->gc_mutex);
}
- ret = f2fs_gc(sbi, sync, true);
+ ret = f2fs_gc(sbi, sync, true, NULL_SEGNO);
+out:
+ mnt_drop_write_file(filp);
+ return ret;
+}
+
+static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_gc_range range;
+ u64 end;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (copy_from_user(&range, (struct f2fs_gc_range __user *)arg,
+ sizeof(range)))
+ return -EFAULT;
+
+ if (f2fs_readonly(sbi->sb))
+ return -EROFS;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ end = range.start + range.len;
+ if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi))
+ return -EINVAL;
+do_more:
+ if (!range.sync) {
+ if (!mutex_trylock(&sbi->gc_mutex)) {
+ ret = -EBUSY;
+ goto out;
+ }
+ } else {
+ mutex_lock(&sbi->gc_mutex);
+ }
+
+ ret = f2fs_gc(sbi, range.sync, true, GET_SEGNO(sbi, range.start));
+ range.start += sbi->blocks_per_seg;
+ if (range.start <= end)
+ goto do_more;
out:
mnt_drop_write_file(filp);
return ret;
@@ -1890,17 +2010,16 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
{
struct inode *inode = file_inode(filp);
struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
- struct extent_info ei;
+ struct extent_info ei = {0,0,0};
pgoff_t pg_start, pg_end;
unsigned int blk_per_seg = sbi->blocks_per_seg;
unsigned int total = 0, sec_num;
- unsigned int pages_per_sec = sbi->segs_per_sec * blk_per_seg;
block_t blk_end = 0;
bool fragmented = false;
int err;
/* if in-place-update policy is enabled, don't waste time here */
- if (need_inplace_update(inode))
+ if (need_inplace_update_policy(inode, NULL))
return -EINVAL;
pg_start = range->start >> PAGE_SHIFT;
@@ -1934,7 +2053,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
*/
while (map.m_lblk < pg_end) {
map.m_len = pg_end - map.m_lblk;
- err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ);
+ err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT);
if (err)
goto out;
@@ -1958,7 +2077,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
map.m_lblk = pg_start;
map.m_len = pg_end - pg_start;
- sec_num = (map.m_len + pages_per_sec - 1) / pages_per_sec;
+ sec_num = (map.m_len + BLKS_PER_SEC(sbi) - 1) / BLKS_PER_SEC(sbi);
/*
* make sure there are enough free section for LFS allocation, this can
@@ -1976,7 +2095,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
do_map:
map.m_len = pg_end - map.m_lblk;
- err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ);
+ err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT);
if (err)
goto clear_out;
@@ -2035,42 +2154,40 @@ static int f2fs_ioc_defragment(struct file *filp, unsigned long arg)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (!S_ISREG(inode->i_mode))
+ if (!S_ISREG(inode->i_mode) || f2fs_is_atomic_file(inode))
return -EINVAL;
- err = mnt_want_write_file(filp);
- if (err)
- return err;
-
- if (f2fs_readonly(sbi->sb)) {
- err = -EROFS;
- goto out;
- }
+ if (f2fs_readonly(sbi->sb))
+ return -EROFS;
if (copy_from_user(&range, (struct f2fs_defragment __user *)arg,
- sizeof(range))) {
- err = -EFAULT;
- goto out;
- }
+ sizeof(range)))
+ return -EFAULT;
/* verify alignment of offset & size */
- if (range.start & (F2FS_BLKSIZE - 1) ||
- range.len & (F2FS_BLKSIZE - 1)) {
- err = -EINVAL;
- goto out;
- }
+ if (range.start & (F2FS_BLKSIZE - 1) || range.len & (F2FS_BLKSIZE - 1))
+ return -EINVAL;
+
+ if (unlikely((range.start + range.len) >> PAGE_SHIFT >
+ sbi->max_file_blocks))
+ return -EINVAL;
+
+ err = mnt_want_write_file(filp);
+ if (err)
+ return err;
err = f2fs_defragment_range(sbi, filp, &range);
+ mnt_drop_write_file(filp);
+
f2fs_update_time(sbi, REQ_TIME);
if (err < 0)
- goto out;
+ return err;
if (copy_to_user((struct f2fs_defragment __user *)arg, &range,
sizeof(range)))
- err = -EFAULT;
-out:
- mnt_drop_write_file(filp);
- return err;
+ return -EFAULT;
+
+ return 0;
}
static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
@@ -2204,6 +2321,8 @@ static int f2fs_ioc_move_range(struct file *filp, unsigned long arg)
range.pos_out, range.len);
mnt_drop_write_file(filp);
+ if (err)
+ goto err_out;
if (copy_to_user((struct f2fs_move_range __user *)arg,
&range, sizeof(range)))
@@ -2213,6 +2332,79 @@ err_out:
return err;
}
+static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct sit_info *sm = SIT_I(sbi);
+ unsigned int start_segno = 0, end_segno = 0;
+ unsigned int dev_start_segno = 0, dev_end_segno = 0;
+ struct f2fs_flush_device range;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (f2fs_readonly(sbi->sb))
+ return -EROFS;
+
+ if (copy_from_user(&range, (struct f2fs_flush_device __user *)arg,
+ sizeof(range)))
+ return -EFAULT;
+
+ if (sbi->s_ndevs <= 1 || sbi->s_ndevs - 1 <= range.dev_num ||
+ sbi->segs_per_sec != 1) {
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "Can't flush %u in %d for segs_per_sec %u != 1\n",
+ range.dev_num, sbi->s_ndevs,
+ sbi->segs_per_sec);
+ return -EINVAL;
+ }
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ if (range.dev_num != 0)
+ dev_start_segno = GET_SEGNO(sbi, FDEV(range.dev_num).start_blk);
+ dev_end_segno = GET_SEGNO(sbi, FDEV(range.dev_num).end_blk);
+
+ start_segno = sm->last_victim[FLUSH_DEVICE];
+ if (start_segno < dev_start_segno || start_segno >= dev_end_segno)
+ start_segno = dev_start_segno;
+ end_segno = min(start_segno + range.segments, dev_end_segno);
+
+ while (start_segno < end_segno) {
+ if (!mutex_trylock(&sbi->gc_mutex)) {
+ ret = -EBUSY;
+ goto out;
+ }
+ sm->last_victim[GC_CB] = end_segno + 1;
+ sm->last_victim[GC_GREEDY] = end_segno + 1;
+ sm->last_victim[ALLOC_NEXT] = end_segno + 1;
+ ret = f2fs_gc(sbi, true, true, start_segno);
+ if (ret == -EAGAIN)
+ ret = 0;
+ else if (ret < 0)
+ break;
+ start_segno++;
+ }
+out:
+ mnt_drop_write_file(filp);
+ return ret;
+}
+
+static int f2fs_ioc_get_features(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ u32 sb_feature = le32_to_cpu(F2FS_I_SB(inode)->raw_super->feature);
+
+ /* Must validate to set it with SQLite behavior in Android. */
+ sb_feature |= F2FS_FEATURE_ATOMIC_WRITE;
+
+ return put_user(sb_feature, (u32 __user *)arg);
+}
+
long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
switch (cmd) {
@@ -2244,12 +2436,18 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return f2fs_ioc_get_encryption_pwsalt(filp, arg);
case F2FS_IOC_GARBAGE_COLLECT:
return f2fs_ioc_gc(filp, arg);
+ case F2FS_IOC_GARBAGE_COLLECT_RANGE:
+ return f2fs_ioc_gc_range(filp, arg);
case F2FS_IOC_WRITE_CHECKPOINT:
return f2fs_ioc_write_checkpoint(filp, arg);
case F2FS_IOC_DEFRAGMENT:
return f2fs_ioc_defragment(filp, arg);
case F2FS_IOC_MOVE_RANGE:
return f2fs_ioc_move_range(filp, arg);
+ case F2FS_IOC_FLUSH_DEVICE:
+ return f2fs_ioc_flush_device(filp, arg);
+ case F2FS_IOC_GET_FEATURES:
+ return f2fs_ioc_get_features(filp, arg);
default:
return -ENOTTY;
}
@@ -2262,16 +2460,15 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
struct blk_plug plug;
ssize_t ret;
- if (f2fs_encrypted_inode(inode) &&
- !fscrypt_has_encryption_key(inode) &&
- fscrypt_get_encryption_info(inode))
- return -EACCES;
-
inode_lock(inode);
ret = generic_write_checks(iocb, from);
if (ret > 0) {
- int err = f2fs_preallocate_blocks(iocb, from);
+ int err;
+ if (iov_iter_fault_in_readable(from, iov_iter_count(from)))
+ set_inode_flag(inode, FI_NO_PREALLOC);
+
+ err = f2fs_preallocate_blocks(iocb, from);
if (err) {
inode_unlock(inode);
return err;
@@ -2279,6 +2476,10 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
blk_start_plug(&plug);
ret = __generic_file_write_iter(iocb, from);
blk_finish_plug(&plug);
+ clear_inode_flag(inode, FI_NO_PREALLOC);
+
+ if (ret > 0)
+ f2fs_update_iostat(F2FS_I_SB(inode), APP_WRITE_IO, ret);
}
inode_unlock(inode);
@@ -2315,10 +2516,12 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case F2FS_IOC_GET_ENCRYPTION_PWSALT:
case F2FS_IOC_GET_ENCRYPTION_POLICY:
case F2FS_IOC_GARBAGE_COLLECT:
+ case F2FS_IOC_GARBAGE_COLLECT_RANGE:
case F2FS_IOC_WRITE_CHECKPOINT:
case F2FS_IOC_DEFRAGMENT:
- break;
case F2FS_IOC_MOVE_RANGE:
+ case F2FS_IOC_FLUSH_DEVICE:
+ case F2FS_IOC_GET_FEATURES:
break;
default:
return -ENOIOCTLCMD;
@@ -2334,6 +2537,7 @@ const struct file_operations f2fs_file_operations = {
.open = f2fs_file_open,
.release = f2fs_release_file,
.mmap = f2fs_file_mmap,
+ .flush = f2fs_file_flush,
.fsync = f2fs_sync_file,
.fallocate = f2fs_fallocate,
.unlocked_ioctl = f2fs_ioctl,
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-22 23:56:19 +0000