mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-22 08:49:45 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
Pull f2fs updates from Jaegeuk Kim: "This series adds two ioctls to control cached data and fragmented files. Most of the rest fixes missing error cases and bugs that we have not covered so far. Summary: Enhancements: - support an ioctl to execute online file defragmentation - support an ioctl to flush cached data - speed up shrinking of extent_cache entries - handle broken superblock - refector dirty inode management infra - revisit f2fs_map_blocks to handle more cases - reduce global lock coverage - add detecting user's idle time Major bug fixes: - fix data race condition on cached nat entries - fix error cases of volatile and atomic writes" * tag 'for-f2fs-4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (87 commits) f2fs: should unset atomic flag after successful commit f2fs: fix wrong memory condition check f2fs: monitor the number of background checkpoint f2fs: detect idle time depending on user behavior f2fs: introduce time and interval facility f2fs: skip releasing nodes in chindless extent tree f2fs: use atomic type for node count in extent tree f2fs: recognize encrypted data in f2fs_fiemap f2fs: clean up f2fs_balance_fs f2fs: remove redundant calls f2fs: avoid unnecessary f2fs_balance_fs calls f2fs: check the page status filled from disk f2fs: introduce __get_node_page to reuse common code f2fs: check node id earily when readaheading node page f2fs: read isize while holding i_mutex in fiemap Revert "f2fs: check the node block address of newly allocated nid" f2fs: cover more area with nat_tree_lock f2fs: introduce max_file_blocks in sbi f2fs crypto: check CONFIG_F2FS_FS_XATTR for encrypted symlink f2fs: introduce zombie list for fast shrinking extent trees ...
434 lines
12 KiB
C
434 lines
12 KiB
C
/*
|
|
* fs/f2fs/inode.c
|
|
*
|
|
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
|
|
* http://www.samsung.com/
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*/
|
|
#include <linux/fs.h>
|
|
#include <linux/f2fs_fs.h>
|
|
#include <linux/buffer_head.h>
|
|
#include <linux/writeback.h>
|
|
|
|
#include "f2fs.h"
|
|
#include "node.h"
|
|
|
|
#include <trace/events/f2fs.h>
|
|
|
|
void f2fs_set_inode_flags(struct inode *inode)
|
|
{
|
|
unsigned int flags = F2FS_I(inode)->i_flags;
|
|
unsigned int new_fl = 0;
|
|
|
|
if (flags & FS_SYNC_FL)
|
|
new_fl |= S_SYNC;
|
|
if (flags & FS_APPEND_FL)
|
|
new_fl |= S_APPEND;
|
|
if (flags & FS_IMMUTABLE_FL)
|
|
new_fl |= S_IMMUTABLE;
|
|
if (flags & FS_NOATIME_FL)
|
|
new_fl |= S_NOATIME;
|
|
if (flags & FS_DIRSYNC_FL)
|
|
new_fl |= S_DIRSYNC;
|
|
inode_set_flags(inode, new_fl,
|
|
S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
|
|
}
|
|
|
|
static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
|
|
{
|
|
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
|
|
S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
|
|
if (ri->i_addr[0])
|
|
inode->i_rdev =
|
|
old_decode_dev(le32_to_cpu(ri->i_addr[0]));
|
|
else
|
|
inode->i_rdev =
|
|
new_decode_dev(le32_to_cpu(ri->i_addr[1]));
|
|
}
|
|
}
|
|
|
|
static bool __written_first_block(struct f2fs_inode *ri)
|
|
{
|
|
block_t addr = le32_to_cpu(ri->i_addr[0]);
|
|
|
|
if (addr != NEW_ADDR && addr != NULL_ADDR)
|
|
return true;
|
|
return false;
|
|
}
|
|
|
|
static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
|
|
{
|
|
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
|
|
if (old_valid_dev(inode->i_rdev)) {
|
|
ri->i_addr[0] =
|
|
cpu_to_le32(old_encode_dev(inode->i_rdev));
|
|
ri->i_addr[1] = 0;
|
|
} else {
|
|
ri->i_addr[0] = 0;
|
|
ri->i_addr[1] =
|
|
cpu_to_le32(new_encode_dev(inode->i_rdev));
|
|
ri->i_addr[2] = 0;
|
|
}
|
|
}
|
|
}
|
|
|
|
static void __recover_inline_status(struct inode *inode, struct page *ipage)
|
|
{
|
|
void *inline_data = inline_data_addr(ipage);
|
|
__le32 *start = inline_data;
|
|
__le32 *end = start + MAX_INLINE_DATA / sizeof(__le32);
|
|
|
|
while (start < end) {
|
|
if (*start++) {
|
|
f2fs_wait_on_page_writeback(ipage, NODE);
|
|
|
|
set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
|
|
set_raw_inline(F2FS_I(inode), F2FS_INODE(ipage));
|
|
set_page_dirty(ipage);
|
|
return;
|
|
}
|
|
}
|
|
return;
|
|
}
|
|
|
|
static int do_read_inode(struct inode *inode)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
|
|
struct f2fs_inode_info *fi = F2FS_I(inode);
|
|
struct page *node_page;
|
|
struct f2fs_inode *ri;
|
|
|
|
/* Check if ino is within scope */
|
|
if (check_nid_range(sbi, inode->i_ino)) {
|
|
f2fs_msg(inode->i_sb, KERN_ERR, "bad inode number: %lu",
|
|
(unsigned long) inode->i_ino);
|
|
WARN_ON(1);
|
|
return -EINVAL;
|
|
}
|
|
|
|
node_page = get_node_page(sbi, inode->i_ino);
|
|
if (IS_ERR(node_page))
|
|
return PTR_ERR(node_page);
|
|
|
|
ri = F2FS_INODE(node_page);
|
|
|
|
inode->i_mode = le16_to_cpu(ri->i_mode);
|
|
i_uid_write(inode, le32_to_cpu(ri->i_uid));
|
|
i_gid_write(inode, le32_to_cpu(ri->i_gid));
|
|
set_nlink(inode, le32_to_cpu(ri->i_links));
|
|
inode->i_size = le64_to_cpu(ri->i_size);
|
|
inode->i_blocks = le64_to_cpu(ri->i_blocks);
|
|
|
|
inode->i_atime.tv_sec = le64_to_cpu(ri->i_atime);
|
|
inode->i_ctime.tv_sec = le64_to_cpu(ri->i_ctime);
|
|
inode->i_mtime.tv_sec = le64_to_cpu(ri->i_mtime);
|
|
inode->i_atime.tv_nsec = le32_to_cpu(ri->i_atime_nsec);
|
|
inode->i_ctime.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
|
|
inode->i_mtime.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
|
|
inode->i_generation = le32_to_cpu(ri->i_generation);
|
|
|
|
fi->i_current_depth = le32_to_cpu(ri->i_current_depth);
|
|
fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid);
|
|
fi->i_flags = le32_to_cpu(ri->i_flags);
|
|
fi->flags = 0;
|
|
fi->i_advise = ri->i_advise;
|
|
fi->i_pino = le32_to_cpu(ri->i_pino);
|
|
fi->i_dir_level = ri->i_dir_level;
|
|
|
|
if (f2fs_init_extent_tree(inode, &ri->i_ext))
|
|
set_page_dirty(node_page);
|
|
|
|
get_inline_info(fi, ri);
|
|
|
|
/* check data exist */
|
|
if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
|
|
__recover_inline_status(inode, node_page);
|
|
|
|
/* get rdev by using inline_info */
|
|
__get_inode_rdev(inode, ri);
|
|
|
|
if (__written_first_block(ri))
|
|
set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
|
|
|
|
f2fs_put_page(node_page, 1);
|
|
|
|
stat_inc_inline_xattr(inode);
|
|
stat_inc_inline_inode(inode);
|
|
stat_inc_inline_dir(inode);
|
|
|
|
return 0;
|
|
}
|
|
|
|
struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_SB(sb);
|
|
struct inode *inode;
|
|
int ret = 0;
|
|
|
|
inode = iget_locked(sb, ino);
|
|
if (!inode)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
if (!(inode->i_state & I_NEW)) {
|
|
trace_f2fs_iget(inode);
|
|
return inode;
|
|
}
|
|
if (ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi))
|
|
goto make_now;
|
|
|
|
ret = do_read_inode(inode);
|
|
if (ret)
|
|
goto bad_inode;
|
|
make_now:
|
|
if (ino == F2FS_NODE_INO(sbi)) {
|
|
inode->i_mapping->a_ops = &f2fs_node_aops;
|
|
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
|
|
} else if (ino == F2FS_META_INO(sbi)) {
|
|
inode->i_mapping->a_ops = &f2fs_meta_aops;
|
|
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
|
|
} else if (S_ISREG(inode->i_mode)) {
|
|
inode->i_op = &f2fs_file_inode_operations;
|
|
inode->i_fop = &f2fs_file_operations;
|
|
inode->i_mapping->a_ops = &f2fs_dblock_aops;
|
|
} else if (S_ISDIR(inode->i_mode)) {
|
|
inode->i_op = &f2fs_dir_inode_operations;
|
|
inode->i_fop = &f2fs_dir_operations;
|
|
inode->i_mapping->a_ops = &f2fs_dblock_aops;
|
|
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO);
|
|
} else if (S_ISLNK(inode->i_mode)) {
|
|
if (f2fs_encrypted_inode(inode))
|
|
inode->i_op = &f2fs_encrypted_symlink_inode_operations;
|
|
else
|
|
inode->i_op = &f2fs_symlink_inode_operations;
|
|
inode_nohighmem(inode);
|
|
inode->i_mapping->a_ops = &f2fs_dblock_aops;
|
|
} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
|
|
S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
|
|
inode->i_op = &f2fs_special_inode_operations;
|
|
init_special_inode(inode, inode->i_mode, inode->i_rdev);
|
|
} else {
|
|
ret = -EIO;
|
|
goto bad_inode;
|
|
}
|
|
unlock_new_inode(inode);
|
|
trace_f2fs_iget(inode);
|
|
return inode;
|
|
|
|
bad_inode:
|
|
iget_failed(inode);
|
|
trace_f2fs_iget_exit(inode, ret);
|
|
return ERR_PTR(ret);
|
|
}
|
|
|
|
int update_inode(struct inode *inode, struct page *node_page)
|
|
{
|
|
struct f2fs_inode *ri;
|
|
|
|
f2fs_wait_on_page_writeback(node_page, NODE);
|
|
|
|
ri = F2FS_INODE(node_page);
|
|
|
|
ri->i_mode = cpu_to_le16(inode->i_mode);
|
|
ri->i_advise = F2FS_I(inode)->i_advise;
|
|
ri->i_uid = cpu_to_le32(i_uid_read(inode));
|
|
ri->i_gid = cpu_to_le32(i_gid_read(inode));
|
|
ri->i_links = cpu_to_le32(inode->i_nlink);
|
|
ri->i_size = cpu_to_le64(i_size_read(inode));
|
|
ri->i_blocks = cpu_to_le64(inode->i_blocks);
|
|
|
|
if (F2FS_I(inode)->extent_tree)
|
|
set_raw_extent(&F2FS_I(inode)->extent_tree->largest,
|
|
&ri->i_ext);
|
|
else
|
|
memset(&ri->i_ext, 0, sizeof(ri->i_ext));
|
|
set_raw_inline(F2FS_I(inode), ri);
|
|
|
|
ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
|
|
ri->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
|
|
ri->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec);
|
|
ri->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec);
|
|
ri->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
|
|
ri->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
|
|
ri->i_current_depth = cpu_to_le32(F2FS_I(inode)->i_current_depth);
|
|
ri->i_xattr_nid = cpu_to_le32(F2FS_I(inode)->i_xattr_nid);
|
|
ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags);
|
|
ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino);
|
|
ri->i_generation = cpu_to_le32(inode->i_generation);
|
|
ri->i_dir_level = F2FS_I(inode)->i_dir_level;
|
|
|
|
__set_inode_rdev(inode, ri);
|
|
set_cold_node(inode, node_page);
|
|
clear_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
|
|
|
|
return set_page_dirty(node_page);
|
|
}
|
|
|
|
int update_inode_page(struct inode *inode)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
|
|
struct page *node_page;
|
|
int ret = 0;
|
|
retry:
|
|
node_page = get_node_page(sbi, inode->i_ino);
|
|
if (IS_ERR(node_page)) {
|
|
int err = PTR_ERR(node_page);
|
|
if (err == -ENOMEM) {
|
|
cond_resched();
|
|
goto retry;
|
|
} else if (err != -ENOENT) {
|
|
f2fs_stop_checkpoint(sbi);
|
|
}
|
|
return 0;
|
|
}
|
|
ret = update_inode(inode, node_page);
|
|
f2fs_put_page(node_page, 1);
|
|
return ret;
|
|
}
|
|
|
|
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
|
|
|
|
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
|
|
inode->i_ino == F2FS_META_INO(sbi))
|
|
return 0;
|
|
|
|
if (!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_INODE))
|
|
return 0;
|
|
|
|
/*
|
|
* We need to balance fs here to prevent from producing dirty node pages
|
|
* during the urgent cleaning time when runing out of free sections.
|
|
*/
|
|
if (update_inode_page(inode))
|
|
f2fs_balance_fs(sbi, true);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Called at the last iput() if i_nlink is zero
|
|
*/
|
|
void f2fs_evict_inode(struct inode *inode)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
|
|
struct f2fs_inode_info *fi = F2FS_I(inode);
|
|
nid_t xnid = fi->i_xattr_nid;
|
|
int err = 0;
|
|
|
|
/* some remained atomic pages should discarded */
|
|
if (f2fs_is_atomic_file(inode))
|
|
commit_inmem_pages(inode, true);
|
|
|
|
trace_f2fs_evict_inode(inode);
|
|
truncate_inode_pages_final(&inode->i_data);
|
|
|
|
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
|
|
inode->i_ino == F2FS_META_INO(sbi))
|
|
goto out_clear;
|
|
|
|
f2fs_bug_on(sbi, get_dirty_pages(inode));
|
|
remove_dirty_inode(inode);
|
|
|
|
f2fs_destroy_extent_tree(inode);
|
|
|
|
if (inode->i_nlink || is_bad_inode(inode))
|
|
goto no_delete;
|
|
|
|
sb_start_intwrite(inode->i_sb);
|
|
set_inode_flag(fi, FI_NO_ALLOC);
|
|
i_size_write(inode, 0);
|
|
|
|
if (F2FS_HAS_BLOCKS(inode))
|
|
err = f2fs_truncate(inode, true);
|
|
|
|
if (!err) {
|
|
f2fs_lock_op(sbi);
|
|
err = remove_inode_page(inode);
|
|
f2fs_unlock_op(sbi);
|
|
}
|
|
|
|
sb_end_intwrite(inode->i_sb);
|
|
no_delete:
|
|
stat_dec_inline_xattr(inode);
|
|
stat_dec_inline_dir(inode);
|
|
stat_dec_inline_inode(inode);
|
|
|
|
invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino);
|
|
if (xnid)
|
|
invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
|
|
if (is_inode_flag_set(fi, FI_APPEND_WRITE))
|
|
add_ino_entry(sbi, inode->i_ino, APPEND_INO);
|
|
if (is_inode_flag_set(fi, FI_UPDATE_WRITE))
|
|
add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
|
|
if (is_inode_flag_set(fi, FI_FREE_NID)) {
|
|
if (err && err != -ENOENT)
|
|
alloc_nid_done(sbi, inode->i_ino);
|
|
else
|
|
alloc_nid_failed(sbi, inode->i_ino);
|
|
clear_inode_flag(fi, FI_FREE_NID);
|
|
}
|
|
|
|
if (err && err != -ENOENT) {
|
|
if (!exist_written_data(sbi, inode->i_ino, ORPHAN_INO)) {
|
|
/*
|
|
* get here because we failed to release resource
|
|
* of inode previously, reminder our user to run fsck
|
|
* for fixing.
|
|
*/
|
|
set_sbi_flag(sbi, SBI_NEED_FSCK);
|
|
f2fs_msg(sbi->sb, KERN_WARNING,
|
|
"inode (ino:%lu) resource leak, run fsck "
|
|
"to fix this issue!", inode->i_ino);
|
|
}
|
|
}
|
|
out_clear:
|
|
#ifdef CONFIG_F2FS_FS_ENCRYPTION
|
|
if (fi->i_crypt_info)
|
|
f2fs_free_encryption_info(inode, fi->i_crypt_info);
|
|
#endif
|
|
clear_inode(inode);
|
|
}
|
|
|
|
/* caller should call f2fs_lock_op() */
|
|
void handle_failed_inode(struct inode *inode)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
|
|
int err = 0;
|
|
|
|
clear_nlink(inode);
|
|
make_bad_inode(inode);
|
|
unlock_new_inode(inode);
|
|
|
|
i_size_write(inode, 0);
|
|
if (F2FS_HAS_BLOCKS(inode))
|
|
err = f2fs_truncate(inode, false);
|
|
|
|
if (!err)
|
|
err = remove_inode_page(inode);
|
|
|
|
/*
|
|
* if we skip truncate_node in remove_inode_page bacause we failed
|
|
* before, it's better to find another way to release resource of
|
|
* this inode (e.g. valid block count, node block or nid). Here we
|
|
* choose to add this inode to orphan list, so that we can call iput
|
|
* for releasing in orphan recovery flow.
|
|
*
|
|
* Note: we should add inode to orphan list before f2fs_unlock_op()
|
|
* so we can prevent losing this orphan when encoutering checkpoint
|
|
* and following suddenly power-off.
|
|
*/
|
|
if (err && err != -ENOENT) {
|
|
err = acquire_orphan_inode(sbi);
|
|
if (!err)
|
|
add_orphan_inode(sbi, inode->i_ino);
|
|
}
|
|
|
|
set_inode_flag(F2FS_I(inode), FI_FREE_NID);
|
|
f2fs_unlock_op(sbi);
|
|
|
|
/* iput will drop the inode object */
|
|
iput(inode);
|
|
}
|