mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-28 20:02:17 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
We've continued mainly to fix bugs in this round, as f2fs has been shipped in more devices. Especially, we've focused on stabilizing checkpoint=disable feature, and provided some interfaces for QA. Enhancement: - expose FS_NOCOW_FL for pin_file - run discard jobs at unmount time with timeout - tune discarding thread to avoid idling which consumes power - some checking codes to address vulnerabilities - give random value to i_generation - shutdown with more flags for QA Bug fix: - clean up stale objects when mount is failed along with checkpoint=disable - fix system being stuck due to wrong count by atomic writes - handle some corrupted disk cases - fix a deadlock in f2fs_read_inline_dir We've also added some minor build errors and clean-up patches. -----BEGIN PGP SIGNATURE----- iQIzBAABCAAdFiEE00UqedjCtOrGVvQiQBSofoJIUNIFAlyKk4YACgkQQBSofoJI UNIMVw//Rb3nmbQkMW/86DxtHDxuS8GEJmle0DiHeFMHgwy0ET0uZs9/AEfmuejC 95cXnF44QfVaFwkOXCK6aKXJXwN0+ZS0YvV/gPE8lgU6sdQhJBox5DC+rx+OwFq5 rZiF8qvE8iyM9Xt+RfMBGufzUb+LKBz0ozQFZpKJiNTBBf5vpeqMYASEEfxiEmZz GvvUNSBRw39OB5zTl5l2hnoNqkoFu6XHnf4f9+DnraVi8SuQzj6hdqsx0nYTHfLi Rax8kA4HUwoVgjhaLLXFbbhWIQ83bcZ0cj6wq7Lr7NbbIi7bKYP6sxtKjbe2Fuql m9Chm2LIvD1BfJnjdTk2krqY7Z4bX/4gmXukno/8X/cjWkpBV6HFWS73iTgrJjU2 d8kBFXwlIn+JlATSjsTtdfvKkTwxUhaGw1bBA96Am4c5tLQyOqyYWcfQA/tam/v4 dM9EQX5ZeRb6NXDeIxkXNfTSpDRnqlhJsTV5aK8qporyF1RkKVbyCpSt1P4q3KO5 UwsGZLFAVMzFaUVfyIS7dR5QVczQUTCH4g0yFNpBMvF8epOA4+jbYxQeGZfqFK3H mTC/Ba+VWWdYW2pZRNc9TnBsHg/xadMJq7EQb/ykGBe6JZJfB0wREj4LSr1lGK9a cU8JFGyqg1Rt/uRP0bb5IIec1YVton3Lq8ND9VZPNcV/mS5Gehg= =9BoH -----END PGP SIGNATURE----- Merge tag 'f2fs-for-5.1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs Pull f2fs updates from Jaegeuk Kim: "We've continued mainly to fix bugs in this round, as f2fs has been shipped in more devices. Especially, we've focused on stabilizing checkpoint=disable feature, and provided some interfaces for QA. Enhancements: - expose FS_NOCOW_FL for pin_file - run discard jobs at unmount time with timeout - tune discarding thread to avoid idling which consumes power - some checking codes to address vulnerabilities - give random value to i_generation - shutdown with more flags for QA Bug fixes: - clean up stale objects when mount is failed along with checkpoint=disable - fix system being stuck due to wrong count by atomic writes - handle some corrupted disk cases - fix a deadlock in f2fs_read_inline_dir We've also added some minor build error fixes and clean-up patches" * tag 'f2fs-for-5.1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (53 commits) f2fs: set pin_file under CAP_SYS_ADMIN f2fs: fix to avoid deadlock in f2fs_read_inline_dir() f2fs: fix to adapt small inline xattr space in __find_inline_xattr() f2fs: fix to do sanity check with inode.i_inline_xattr_size f2fs: give some messages for inline_xattr_size f2fs: don't trigger read IO for beyond EOF page f2fs: fix to add refcount once page is tagged PG_private f2fs: remove wrong comment in f2fs_invalidate_page() f2fs: fix to use kvfree instead of kzfree f2fs: print more parameters in trace_f2fs_map_blocks f2fs: trace f2fs_ioc_shutdown f2fs: fix to avoid deadlock of atomic file operations f2fs: fix to dirty inode for i_mode recovery f2fs: give random value to i_generation f2fs: no need to take page lock in readdir f2fs: fix to update iostat correctly in IPU path f2fs: fix encrypted page memory leak f2fs: make fault injection covering __submit_flush_wait() f2fs: fix to retry fill_super only if recovery failed f2fs: silence VM_WARN_ON_ONCE in mempool_alloc ...
947 lines
23 KiB
C
947 lines
23 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* fs/f2fs/dir.c
|
|
*
|
|
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
|
|
* http://www.samsung.com/
|
|
*/
|
|
#include <linux/fs.h>
|
|
#include <linux/f2fs_fs.h>
|
|
#include <linux/sched/signal.h>
|
|
#include "f2fs.h"
|
|
#include "node.h"
|
|
#include "acl.h"
|
|
#include "xattr.h"
|
|
#include <trace/events/f2fs.h>
|
|
|
|
static unsigned long dir_blocks(struct inode *inode)
|
|
{
|
|
return ((unsigned long long) (i_size_read(inode) + PAGE_SIZE - 1))
|
|
>> PAGE_SHIFT;
|
|
}
|
|
|
|
static unsigned int dir_buckets(unsigned int level, int dir_level)
|
|
{
|
|
if (level + dir_level < MAX_DIR_HASH_DEPTH / 2)
|
|
return 1 << (level + dir_level);
|
|
else
|
|
return MAX_DIR_BUCKETS;
|
|
}
|
|
|
|
static unsigned int bucket_blocks(unsigned int level)
|
|
{
|
|
if (level < MAX_DIR_HASH_DEPTH / 2)
|
|
return 2;
|
|
else
|
|
return 4;
|
|
}
|
|
|
|
static unsigned char f2fs_filetype_table[F2FS_FT_MAX] = {
|
|
[F2FS_FT_UNKNOWN] = DT_UNKNOWN,
|
|
[F2FS_FT_REG_FILE] = DT_REG,
|
|
[F2FS_FT_DIR] = DT_DIR,
|
|
[F2FS_FT_CHRDEV] = DT_CHR,
|
|
[F2FS_FT_BLKDEV] = DT_BLK,
|
|
[F2FS_FT_FIFO] = DT_FIFO,
|
|
[F2FS_FT_SOCK] = DT_SOCK,
|
|
[F2FS_FT_SYMLINK] = DT_LNK,
|
|
};
|
|
|
|
static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = {
|
|
[S_IFREG >> S_SHIFT] = F2FS_FT_REG_FILE,
|
|
[S_IFDIR >> S_SHIFT] = F2FS_FT_DIR,
|
|
[S_IFCHR >> S_SHIFT] = F2FS_FT_CHRDEV,
|
|
[S_IFBLK >> S_SHIFT] = F2FS_FT_BLKDEV,
|
|
[S_IFIFO >> S_SHIFT] = F2FS_FT_FIFO,
|
|
[S_IFSOCK >> S_SHIFT] = F2FS_FT_SOCK,
|
|
[S_IFLNK >> S_SHIFT] = F2FS_FT_SYMLINK,
|
|
};
|
|
|
|
static void set_de_type(struct f2fs_dir_entry *de, umode_t mode)
|
|
{
|
|
de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
|
|
}
|
|
|
|
unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de)
|
|
{
|
|
if (de->file_type < F2FS_FT_MAX)
|
|
return f2fs_filetype_table[de->file_type];
|
|
return DT_UNKNOWN;
|
|
}
|
|
|
|
static unsigned long dir_block_index(unsigned int level,
|
|
int dir_level, unsigned int idx)
|
|
{
|
|
unsigned long i;
|
|
unsigned long bidx = 0;
|
|
|
|
for (i = 0; i < level; i++)
|
|
bidx += dir_buckets(i, dir_level) * bucket_blocks(i);
|
|
bidx += idx * bucket_blocks(level);
|
|
return bidx;
|
|
}
|
|
|
|
static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
|
|
struct fscrypt_name *fname,
|
|
f2fs_hash_t namehash,
|
|
int *max_slots,
|
|
struct page **res_page)
|
|
{
|
|
struct f2fs_dentry_block *dentry_blk;
|
|
struct f2fs_dir_entry *de;
|
|
struct f2fs_dentry_ptr d;
|
|
|
|
dentry_blk = (struct f2fs_dentry_block *)page_address(dentry_page);
|
|
|
|
make_dentry_ptr_block(NULL, &d, dentry_blk);
|
|
de = f2fs_find_target_dentry(fname, namehash, max_slots, &d);
|
|
if (de)
|
|
*res_page = dentry_page;
|
|
|
|
return de;
|
|
}
|
|
|
|
struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname,
|
|
f2fs_hash_t namehash, int *max_slots,
|
|
struct f2fs_dentry_ptr *d)
|
|
{
|
|
struct f2fs_dir_entry *de;
|
|
unsigned long bit_pos = 0;
|
|
int max_len = 0;
|
|
|
|
if (max_slots)
|
|
*max_slots = 0;
|
|
while (bit_pos < d->max) {
|
|
if (!test_bit_le(bit_pos, d->bitmap)) {
|
|
bit_pos++;
|
|
max_len++;
|
|
continue;
|
|
}
|
|
|
|
de = &d->dentry[bit_pos];
|
|
|
|
if (unlikely(!de->name_len)) {
|
|
bit_pos++;
|
|
continue;
|
|
}
|
|
|
|
if (de->hash_code == namehash &&
|
|
fscrypt_match_name(fname, d->filename[bit_pos],
|
|
le16_to_cpu(de->name_len)))
|
|
goto found;
|
|
|
|
if (max_slots && max_len > *max_slots)
|
|
*max_slots = max_len;
|
|
max_len = 0;
|
|
|
|
bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
|
|
}
|
|
|
|
de = NULL;
|
|
found:
|
|
if (max_slots && max_len > *max_slots)
|
|
*max_slots = max_len;
|
|
return de;
|
|
}
|
|
|
|
static struct f2fs_dir_entry *find_in_level(struct inode *dir,
|
|
unsigned int level,
|
|
struct fscrypt_name *fname,
|
|
struct page **res_page)
|
|
{
|
|
struct qstr name = FSTR_TO_QSTR(&fname->disk_name);
|
|
int s = GET_DENTRY_SLOTS(name.len);
|
|
unsigned int nbucket, nblock;
|
|
unsigned int bidx, end_block;
|
|
struct page *dentry_page;
|
|
struct f2fs_dir_entry *de = NULL;
|
|
bool room = false;
|
|
int max_slots;
|
|
f2fs_hash_t namehash = f2fs_dentry_hash(&name, fname);
|
|
|
|
nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
|
|
nblock = bucket_blocks(level);
|
|
|
|
bidx = dir_block_index(level, F2FS_I(dir)->i_dir_level,
|
|
le32_to_cpu(namehash) % nbucket);
|
|
end_block = bidx + nblock;
|
|
|
|
for (; bidx < end_block; bidx++) {
|
|
/* no need to allocate new dentry pages to all the indices */
|
|
dentry_page = f2fs_find_data_page(dir, bidx);
|
|
if (IS_ERR(dentry_page)) {
|
|
if (PTR_ERR(dentry_page) == -ENOENT) {
|
|
room = true;
|
|
continue;
|
|
} else {
|
|
*res_page = dentry_page;
|
|
break;
|
|
}
|
|
}
|
|
|
|
de = find_in_block(dentry_page, fname, namehash, &max_slots,
|
|
res_page);
|
|
if (de)
|
|
break;
|
|
|
|
if (max_slots >= s)
|
|
room = true;
|
|
f2fs_put_page(dentry_page, 0);
|
|
}
|
|
|
|
if (!de && room && F2FS_I(dir)->chash != namehash) {
|
|
F2FS_I(dir)->chash = namehash;
|
|
F2FS_I(dir)->clevel = level;
|
|
}
|
|
|
|
return de;
|
|
}
|
|
|
|
struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
|
|
struct fscrypt_name *fname, struct page **res_page)
|
|
{
|
|
unsigned long npages = dir_blocks(dir);
|
|
struct f2fs_dir_entry *de = NULL;
|
|
unsigned int max_depth;
|
|
unsigned int level;
|
|
|
|
if (f2fs_has_inline_dentry(dir)) {
|
|
*res_page = NULL;
|
|
de = f2fs_find_in_inline_dir(dir, fname, res_page);
|
|
goto out;
|
|
}
|
|
|
|
if (npages == 0) {
|
|
*res_page = NULL;
|
|
goto out;
|
|
}
|
|
|
|
max_depth = F2FS_I(dir)->i_current_depth;
|
|
if (unlikely(max_depth > MAX_DIR_HASH_DEPTH)) {
|
|
f2fs_msg(F2FS_I_SB(dir)->sb, KERN_WARNING,
|
|
"Corrupted max_depth of %lu: %u",
|
|
dir->i_ino, max_depth);
|
|
max_depth = MAX_DIR_HASH_DEPTH;
|
|
f2fs_i_depth_write(dir, max_depth);
|
|
}
|
|
|
|
for (level = 0; level < max_depth; level++) {
|
|
*res_page = NULL;
|
|
de = find_in_level(dir, level, fname, res_page);
|
|
if (de || IS_ERR(*res_page))
|
|
break;
|
|
}
|
|
out:
|
|
/* This is to increase the speed of f2fs_create */
|
|
if (!de)
|
|
F2FS_I(dir)->task = current;
|
|
return de;
|
|
}
|
|
|
|
/*
|
|
* Find an entry in the specified directory with the wanted name.
|
|
* It returns the page where the entry was found (as a parameter - res_page),
|
|
* and the entry itself. Page is returned mapped and unlocked.
|
|
* Entry is guaranteed to be valid.
|
|
*/
|
|
struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
|
|
const struct qstr *child, struct page **res_page)
|
|
{
|
|
struct f2fs_dir_entry *de = NULL;
|
|
struct fscrypt_name fname;
|
|
int err;
|
|
|
|
err = fscrypt_setup_filename(dir, child, 1, &fname);
|
|
if (err) {
|
|
if (err == -ENOENT)
|
|
*res_page = NULL;
|
|
else
|
|
*res_page = ERR_PTR(err);
|
|
return NULL;
|
|
}
|
|
|
|
de = __f2fs_find_entry(dir, &fname, res_page);
|
|
|
|
fscrypt_free_filename(&fname);
|
|
return de;
|
|
}
|
|
|
|
struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p)
|
|
{
|
|
struct qstr dotdot = QSTR_INIT("..", 2);
|
|
|
|
return f2fs_find_entry(dir, &dotdot, p);
|
|
}
|
|
|
|
ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr,
|
|
struct page **page)
|
|
{
|
|
ino_t res = 0;
|
|
struct f2fs_dir_entry *de;
|
|
|
|
de = f2fs_find_entry(dir, qstr, page);
|
|
if (de) {
|
|
res = le32_to_cpu(de->ino);
|
|
f2fs_put_page(*page, 0);
|
|
}
|
|
|
|
return res;
|
|
}
|
|
|
|
void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
|
|
struct page *page, struct inode *inode)
|
|
{
|
|
enum page_type type = f2fs_has_inline_dentry(dir) ? NODE : DATA;
|
|
lock_page(page);
|
|
f2fs_wait_on_page_writeback(page, type, true, true);
|
|
de->ino = cpu_to_le32(inode->i_ino);
|
|
set_de_type(de, inode->i_mode);
|
|
set_page_dirty(page);
|
|
|
|
dir->i_mtime = dir->i_ctime = current_time(dir);
|
|
f2fs_mark_inode_dirty_sync(dir, false);
|
|
f2fs_put_page(page, 1);
|
|
}
|
|
|
|
static void init_dent_inode(const struct qstr *name, struct page *ipage)
|
|
{
|
|
struct f2fs_inode *ri;
|
|
|
|
f2fs_wait_on_page_writeback(ipage, NODE, true, true);
|
|
|
|
/* copy name info. to this inode page */
|
|
ri = F2FS_INODE(ipage);
|
|
ri->i_namelen = cpu_to_le32(name->len);
|
|
memcpy(ri->i_name, name->name, name->len);
|
|
set_page_dirty(ipage);
|
|
}
|
|
|
|
void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent,
|
|
struct f2fs_dentry_ptr *d)
|
|
{
|
|
struct qstr dot = QSTR_INIT(".", 1);
|
|
struct qstr dotdot = QSTR_INIT("..", 2);
|
|
|
|
/* update dirent of "." */
|
|
f2fs_update_dentry(inode->i_ino, inode->i_mode, d, &dot, 0, 0);
|
|
|
|
/* update dirent of ".." */
|
|
f2fs_update_dentry(parent->i_ino, parent->i_mode, d, &dotdot, 0, 1);
|
|
}
|
|
|
|
static int make_empty_dir(struct inode *inode,
|
|
struct inode *parent, struct page *page)
|
|
{
|
|
struct page *dentry_page;
|
|
struct f2fs_dentry_block *dentry_blk;
|
|
struct f2fs_dentry_ptr d;
|
|
|
|
if (f2fs_has_inline_dentry(inode))
|
|
return f2fs_make_empty_inline_dir(inode, parent, page);
|
|
|
|
dentry_page = f2fs_get_new_data_page(inode, page, 0, true);
|
|
if (IS_ERR(dentry_page))
|
|
return PTR_ERR(dentry_page);
|
|
|
|
dentry_blk = page_address(dentry_page);
|
|
|
|
make_dentry_ptr_block(NULL, &d, dentry_blk);
|
|
f2fs_do_make_empty_dir(inode, parent, &d);
|
|
|
|
set_page_dirty(dentry_page);
|
|
f2fs_put_page(dentry_page, 1);
|
|
return 0;
|
|
}
|
|
|
|
struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
|
|
const struct qstr *new_name, const struct qstr *orig_name,
|
|
struct page *dpage)
|
|
{
|
|
struct page *page;
|
|
int dummy_encrypt = DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(dir));
|
|
int err;
|
|
|
|
if (is_inode_flag_set(inode, FI_NEW_INODE)) {
|
|
page = f2fs_new_inode_page(inode);
|
|
if (IS_ERR(page))
|
|
return page;
|
|
|
|
if (S_ISDIR(inode->i_mode)) {
|
|
/* in order to handle error case */
|
|
get_page(page);
|
|
err = make_empty_dir(inode, dir, page);
|
|
if (err) {
|
|
lock_page(page);
|
|
goto put_error;
|
|
}
|
|
put_page(page);
|
|
}
|
|
|
|
err = f2fs_init_acl(inode, dir, page, dpage);
|
|
if (err)
|
|
goto put_error;
|
|
|
|
err = f2fs_init_security(inode, dir, orig_name, page);
|
|
if (err)
|
|
goto put_error;
|
|
|
|
if ((IS_ENCRYPTED(dir) || dummy_encrypt) &&
|
|
f2fs_may_encrypt(inode)) {
|
|
err = fscrypt_inherit_context(dir, inode, page, false);
|
|
if (err)
|
|
goto put_error;
|
|
}
|
|
} else {
|
|
page = f2fs_get_node_page(F2FS_I_SB(dir), inode->i_ino);
|
|
if (IS_ERR(page))
|
|
return page;
|
|
}
|
|
|
|
if (new_name) {
|
|
init_dent_inode(new_name, page);
|
|
if (IS_ENCRYPTED(dir))
|
|
file_set_enc_name(inode);
|
|
}
|
|
|
|
/*
|
|
* This file should be checkpointed during fsync.
|
|
* We lost i_pino from now on.
|
|
*/
|
|
if (is_inode_flag_set(inode, FI_INC_LINK)) {
|
|
if (!S_ISDIR(inode->i_mode))
|
|
file_lost_pino(inode);
|
|
/*
|
|
* If link the tmpfile to alias through linkat path,
|
|
* we should remove this inode from orphan list.
|
|
*/
|
|
if (inode->i_nlink == 0)
|
|
f2fs_remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino);
|
|
f2fs_i_links_write(inode, true);
|
|
}
|
|
return page;
|
|
|
|
put_error:
|
|
clear_nlink(inode);
|
|
f2fs_update_inode(inode, page);
|
|
f2fs_put_page(page, 1);
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode,
|
|
unsigned int current_depth)
|
|
{
|
|
if (inode && is_inode_flag_set(inode, FI_NEW_INODE)) {
|
|
if (S_ISDIR(inode->i_mode))
|
|
f2fs_i_links_write(dir, true);
|
|
clear_inode_flag(inode, FI_NEW_INODE);
|
|
}
|
|
dir->i_mtime = dir->i_ctime = current_time(dir);
|
|
f2fs_mark_inode_dirty_sync(dir, false);
|
|
|
|
if (F2FS_I(dir)->i_current_depth != current_depth)
|
|
f2fs_i_depth_write(dir, current_depth);
|
|
|
|
if (inode && is_inode_flag_set(inode, FI_INC_LINK))
|
|
clear_inode_flag(inode, FI_INC_LINK);
|
|
}
|
|
|
|
int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots)
|
|
{
|
|
int bit_start = 0;
|
|
int zero_start, zero_end;
|
|
next:
|
|
zero_start = find_next_zero_bit_le(bitmap, max_slots, bit_start);
|
|
if (zero_start >= max_slots)
|
|
return max_slots;
|
|
|
|
zero_end = find_next_bit_le(bitmap, max_slots, zero_start);
|
|
if (zero_end - zero_start >= slots)
|
|
return zero_start;
|
|
|
|
bit_start = zero_end + 1;
|
|
|
|
if (zero_end + 1 >= max_slots)
|
|
return max_slots;
|
|
goto next;
|
|
}
|
|
|
|
void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
|
|
const struct qstr *name, f2fs_hash_t name_hash,
|
|
unsigned int bit_pos)
|
|
{
|
|
struct f2fs_dir_entry *de;
|
|
int slots = GET_DENTRY_SLOTS(name->len);
|
|
int i;
|
|
|
|
de = &d->dentry[bit_pos];
|
|
de->hash_code = name_hash;
|
|
de->name_len = cpu_to_le16(name->len);
|
|
memcpy(d->filename[bit_pos], name->name, name->len);
|
|
de->ino = cpu_to_le32(ino);
|
|
set_de_type(de, mode);
|
|
for (i = 0; i < slots; i++) {
|
|
__set_bit_le(bit_pos + i, (void *)d->bitmap);
|
|
/* avoid wrong garbage data for readdir */
|
|
if (i)
|
|
(de + i)->name_len = 0;
|
|
}
|
|
}
|
|
|
|
int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
|
|
const struct qstr *orig_name,
|
|
struct inode *inode, nid_t ino, umode_t mode)
|
|
{
|
|
unsigned int bit_pos;
|
|
unsigned int level;
|
|
unsigned int current_depth;
|
|
unsigned long bidx, block;
|
|
f2fs_hash_t dentry_hash;
|
|
unsigned int nbucket, nblock;
|
|
struct page *dentry_page = NULL;
|
|
struct f2fs_dentry_block *dentry_blk = NULL;
|
|
struct f2fs_dentry_ptr d;
|
|
struct page *page = NULL;
|
|
int slots, err = 0;
|
|
|
|
level = 0;
|
|
slots = GET_DENTRY_SLOTS(new_name->len);
|
|
dentry_hash = f2fs_dentry_hash(new_name, NULL);
|
|
|
|
current_depth = F2FS_I(dir)->i_current_depth;
|
|
if (F2FS_I(dir)->chash == dentry_hash) {
|
|
level = F2FS_I(dir)->clevel;
|
|
F2FS_I(dir)->chash = 0;
|
|
}
|
|
|
|
start:
|
|
if (time_to_inject(F2FS_I_SB(dir), FAULT_DIR_DEPTH)) {
|
|
f2fs_show_injection_info(FAULT_DIR_DEPTH);
|
|
return -ENOSPC;
|
|
}
|
|
|
|
if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
|
|
return -ENOSPC;
|
|
|
|
/* Increase the depth, if required */
|
|
if (level == current_depth)
|
|
++current_depth;
|
|
|
|
nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
|
|
nblock = bucket_blocks(level);
|
|
|
|
bidx = dir_block_index(level, F2FS_I(dir)->i_dir_level,
|
|
(le32_to_cpu(dentry_hash) % nbucket));
|
|
|
|
for (block = bidx; block <= (bidx + nblock - 1); block++) {
|
|
dentry_page = f2fs_get_new_data_page(dir, NULL, block, true);
|
|
if (IS_ERR(dentry_page))
|
|
return PTR_ERR(dentry_page);
|
|
|
|
dentry_blk = page_address(dentry_page);
|
|
bit_pos = f2fs_room_for_filename(&dentry_blk->dentry_bitmap,
|
|
slots, NR_DENTRY_IN_BLOCK);
|
|
if (bit_pos < NR_DENTRY_IN_BLOCK)
|
|
goto add_dentry;
|
|
|
|
f2fs_put_page(dentry_page, 1);
|
|
}
|
|
|
|
/* Move to next level to find the empty slot for new dentry */
|
|
++level;
|
|
goto start;
|
|
add_dentry:
|
|
f2fs_wait_on_page_writeback(dentry_page, DATA, true, true);
|
|
|
|
if (inode) {
|
|
down_write(&F2FS_I(inode)->i_sem);
|
|
page = f2fs_init_inode_metadata(inode, dir, new_name,
|
|
orig_name, NULL);
|
|
if (IS_ERR(page)) {
|
|
err = PTR_ERR(page);
|
|
goto fail;
|
|
}
|
|
}
|
|
|
|
make_dentry_ptr_block(NULL, &d, dentry_blk);
|
|
f2fs_update_dentry(ino, mode, &d, new_name, dentry_hash, bit_pos);
|
|
|
|
set_page_dirty(dentry_page);
|
|
|
|
if (inode) {
|
|
f2fs_i_pino_write(inode, dir->i_ino);
|
|
f2fs_put_page(page, 1);
|
|
}
|
|
|
|
f2fs_update_parent_metadata(dir, inode, current_depth);
|
|
fail:
|
|
if (inode)
|
|
up_write(&F2FS_I(inode)->i_sem);
|
|
|
|
f2fs_put_page(dentry_page, 1);
|
|
|
|
return err;
|
|
}
|
|
|
|
int f2fs_add_dentry(struct inode *dir, struct fscrypt_name *fname,
|
|
struct inode *inode, nid_t ino, umode_t mode)
|
|
{
|
|
struct qstr new_name;
|
|
int err = -EAGAIN;
|
|
|
|
new_name.name = fname_name(fname);
|
|
new_name.len = fname_len(fname);
|
|
|
|
if (f2fs_has_inline_dentry(dir))
|
|
err = f2fs_add_inline_entry(dir, &new_name, fname->usr_fname,
|
|
inode, ino, mode);
|
|
if (err == -EAGAIN)
|
|
err = f2fs_add_regular_entry(dir, &new_name, fname->usr_fname,
|
|
inode, ino, mode);
|
|
|
|
f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
|
|
return err;
|
|
}
|
|
|
|
/*
|
|
* Caller should grab and release a rwsem by calling f2fs_lock_op() and
|
|
* f2fs_unlock_op().
|
|
*/
|
|
int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
|
|
struct inode *inode, nid_t ino, umode_t mode)
|
|
{
|
|
struct fscrypt_name fname;
|
|
struct page *page = NULL;
|
|
struct f2fs_dir_entry *de = NULL;
|
|
int err;
|
|
|
|
err = fscrypt_setup_filename(dir, name, 0, &fname);
|
|
if (err)
|
|
return err;
|
|
|
|
/*
|
|
* An immature stakable filesystem shows a race condition between lookup
|
|
* and create. If we have same task when doing lookup and create, it's
|
|
* definitely fine as expected by VFS normally. Otherwise, let's just
|
|
* verify on-disk dentry one more time, which guarantees filesystem
|
|
* consistency more.
|
|
*/
|
|
if (current != F2FS_I(dir)->task) {
|
|
de = __f2fs_find_entry(dir, &fname, &page);
|
|
F2FS_I(dir)->task = NULL;
|
|
}
|
|
if (de) {
|
|
f2fs_put_page(page, 0);
|
|
err = -EEXIST;
|
|
} else if (IS_ERR(page)) {
|
|
err = PTR_ERR(page);
|
|
} else {
|
|
err = f2fs_add_dentry(dir, &fname, inode, ino, mode);
|
|
}
|
|
fscrypt_free_filename(&fname);
|
|
return err;
|
|
}
|
|
|
|
int f2fs_do_tmpfile(struct inode *inode, struct inode *dir)
|
|
{
|
|
struct page *page;
|
|
int err = 0;
|
|
|
|
down_write(&F2FS_I(inode)->i_sem);
|
|
page = f2fs_init_inode_metadata(inode, dir, NULL, NULL, NULL);
|
|
if (IS_ERR(page)) {
|
|
err = PTR_ERR(page);
|
|
goto fail;
|
|
}
|
|
f2fs_put_page(page, 1);
|
|
|
|
clear_inode_flag(inode, FI_NEW_INODE);
|
|
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
|
|
fail:
|
|
up_write(&F2FS_I(inode)->i_sem);
|
|
return err;
|
|
}
|
|
|
|
void f2fs_drop_nlink(struct inode *dir, struct inode *inode)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
|
|
|
|
down_write(&F2FS_I(inode)->i_sem);
|
|
|
|
if (S_ISDIR(inode->i_mode))
|
|
f2fs_i_links_write(dir, false);
|
|
inode->i_ctime = current_time(inode);
|
|
|
|
f2fs_i_links_write(inode, false);
|
|
if (S_ISDIR(inode->i_mode)) {
|
|
f2fs_i_links_write(inode, false);
|
|
f2fs_i_size_write(inode, 0);
|
|
}
|
|
up_write(&F2FS_I(inode)->i_sem);
|
|
|
|
if (inode->i_nlink == 0)
|
|
f2fs_add_orphan_inode(inode);
|
|
else
|
|
f2fs_release_orphan_inode(sbi);
|
|
}
|
|
|
|
/*
|
|
* It only removes the dentry from the dentry page, corresponding name
|
|
* entry in name page does not need to be touched during deletion.
|
|
*/
|
|
void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
|
|
struct inode *dir, struct inode *inode)
|
|
{
|
|
struct f2fs_dentry_block *dentry_blk;
|
|
unsigned int bit_pos;
|
|
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
|
|
int i;
|
|
|
|
f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
|
|
|
|
if (F2FS_OPTION(F2FS_I_SB(dir)).fsync_mode == FSYNC_MODE_STRICT)
|
|
f2fs_add_ino_entry(F2FS_I_SB(dir), dir->i_ino, TRANS_DIR_INO);
|
|
|
|
if (f2fs_has_inline_dentry(dir))
|
|
return f2fs_delete_inline_entry(dentry, page, dir, inode);
|
|
|
|
lock_page(page);
|
|
f2fs_wait_on_page_writeback(page, DATA, true, true);
|
|
|
|
dentry_blk = page_address(page);
|
|
bit_pos = dentry - dentry_blk->dentry;
|
|
for (i = 0; i < slots; i++)
|
|
__clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
|
|
|
|
/* Let's check and deallocate this dentry page */
|
|
bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
|
|
NR_DENTRY_IN_BLOCK,
|
|
0);
|
|
set_page_dirty(page);
|
|
|
|
dir->i_ctime = dir->i_mtime = current_time(dir);
|
|
f2fs_mark_inode_dirty_sync(dir, false);
|
|
|
|
if (inode)
|
|
f2fs_drop_nlink(dir, inode);
|
|
|
|
if (bit_pos == NR_DENTRY_IN_BLOCK &&
|
|
!f2fs_truncate_hole(dir, page->index, page->index + 1)) {
|
|
f2fs_clear_page_cache_dirty_tag(page);
|
|
clear_page_dirty_for_io(page);
|
|
f2fs_clear_page_private(page);
|
|
ClearPageUptodate(page);
|
|
clear_cold_data(page);
|
|
inode_dec_dirty_pages(dir);
|
|
f2fs_remove_dirty_inode(dir);
|
|
}
|
|
f2fs_put_page(page, 1);
|
|
}
|
|
|
|
bool f2fs_empty_dir(struct inode *dir)
|
|
{
|
|
unsigned long bidx;
|
|
struct page *dentry_page;
|
|
unsigned int bit_pos;
|
|
struct f2fs_dentry_block *dentry_blk;
|
|
unsigned long nblock = dir_blocks(dir);
|
|
|
|
if (f2fs_has_inline_dentry(dir))
|
|
return f2fs_empty_inline_dir(dir);
|
|
|
|
for (bidx = 0; bidx < nblock; bidx++) {
|
|
dentry_page = f2fs_get_lock_data_page(dir, bidx, false);
|
|
if (IS_ERR(dentry_page)) {
|
|
if (PTR_ERR(dentry_page) == -ENOENT)
|
|
continue;
|
|
else
|
|
return false;
|
|
}
|
|
|
|
dentry_blk = page_address(dentry_page);
|
|
if (bidx == 0)
|
|
bit_pos = 2;
|
|
else
|
|
bit_pos = 0;
|
|
bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
|
|
NR_DENTRY_IN_BLOCK,
|
|
bit_pos);
|
|
|
|
f2fs_put_page(dentry_page, 1);
|
|
|
|
if (bit_pos < NR_DENTRY_IN_BLOCK)
|
|
return false;
|
|
}
|
|
return true;
|
|
}
|
|
|
|
int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
|
|
unsigned int start_pos, struct fscrypt_str *fstr)
|
|
{
|
|
unsigned char d_type = DT_UNKNOWN;
|
|
unsigned int bit_pos;
|
|
struct f2fs_dir_entry *de = NULL;
|
|
struct fscrypt_str de_name = FSTR_INIT(NULL, 0);
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(d->inode);
|
|
struct blk_plug plug;
|
|
bool readdir_ra = sbi->readdir_ra == 1;
|
|
int err = 0;
|
|
|
|
bit_pos = ((unsigned long)ctx->pos % d->max);
|
|
|
|
if (readdir_ra)
|
|
blk_start_plug(&plug);
|
|
|
|
while (bit_pos < d->max) {
|
|
bit_pos = find_next_bit_le(d->bitmap, d->max, bit_pos);
|
|
if (bit_pos >= d->max)
|
|
break;
|
|
|
|
de = &d->dentry[bit_pos];
|
|
if (de->name_len == 0) {
|
|
bit_pos++;
|
|
ctx->pos = start_pos + bit_pos;
|
|
printk_ratelimited(
|
|
"%s, invalid namelen(0), ino:%u, run fsck to fix.",
|
|
KERN_WARNING, le32_to_cpu(de->ino));
|
|
set_sbi_flag(sbi, SBI_NEED_FSCK);
|
|
continue;
|
|
}
|
|
|
|
d_type = f2fs_get_de_type(de);
|
|
|
|
de_name.name = d->filename[bit_pos];
|
|
de_name.len = le16_to_cpu(de->name_len);
|
|
|
|
/* check memory boundary before moving forward */
|
|
bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
|
|
if (unlikely(bit_pos > d->max ||
|
|
le16_to_cpu(de->name_len) > F2FS_NAME_LEN)) {
|
|
f2fs_msg(sbi->sb, KERN_WARNING,
|
|
"%s: corrupted namelen=%d, run fsck to fix.",
|
|
__func__, le16_to_cpu(de->name_len));
|
|
set_sbi_flag(sbi, SBI_NEED_FSCK);
|
|
err = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
if (IS_ENCRYPTED(d->inode)) {
|
|
int save_len = fstr->len;
|
|
|
|
err = fscrypt_fname_disk_to_usr(d->inode,
|
|
(u32)de->hash_code, 0,
|
|
&de_name, fstr);
|
|
if (err)
|
|
goto out;
|
|
|
|
de_name = *fstr;
|
|
fstr->len = save_len;
|
|
}
|
|
|
|
if (!dir_emit(ctx, de_name.name, de_name.len,
|
|
le32_to_cpu(de->ino), d_type)) {
|
|
err = 1;
|
|
goto out;
|
|
}
|
|
|
|
if (readdir_ra)
|
|
f2fs_ra_node_page(sbi, le32_to_cpu(de->ino));
|
|
|
|
ctx->pos = start_pos + bit_pos;
|
|
}
|
|
out:
|
|
if (readdir_ra)
|
|
blk_finish_plug(&plug);
|
|
return err;
|
|
}
|
|
|
|
static int f2fs_readdir(struct file *file, struct dir_context *ctx)
|
|
{
|
|
struct inode *inode = file_inode(file);
|
|
unsigned long npages = dir_blocks(inode);
|
|
struct f2fs_dentry_block *dentry_blk = NULL;
|
|
struct page *dentry_page = NULL;
|
|
struct file_ra_state *ra = &file->f_ra;
|
|
loff_t start_pos = ctx->pos;
|
|
unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK);
|
|
struct f2fs_dentry_ptr d;
|
|
struct fscrypt_str fstr = FSTR_INIT(NULL, 0);
|
|
int err = 0;
|
|
|
|
if (IS_ENCRYPTED(inode)) {
|
|
err = fscrypt_get_encryption_info(inode);
|
|
if (err && err != -ENOKEY)
|
|
goto out;
|
|
|
|
err = fscrypt_fname_alloc_buffer(inode, F2FS_NAME_LEN, &fstr);
|
|
if (err < 0)
|
|
goto out;
|
|
}
|
|
|
|
if (f2fs_has_inline_dentry(inode)) {
|
|
err = f2fs_read_inline_dir(file, ctx, &fstr);
|
|
goto out_free;
|
|
}
|
|
|
|
for (; n < npages; n++, ctx->pos = n * NR_DENTRY_IN_BLOCK) {
|
|
|
|
/* allow readdir() to be interrupted */
|
|
if (fatal_signal_pending(current)) {
|
|
err = -ERESTARTSYS;
|
|
goto out_free;
|
|
}
|
|
cond_resched();
|
|
|
|
/* readahead for multi pages of dir */
|
|
if (npages - n > 1 && !ra_has_index(ra, n))
|
|
page_cache_sync_readahead(inode->i_mapping, ra, file, n,
|
|
min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES));
|
|
|
|
dentry_page = f2fs_find_data_page(inode, n);
|
|
if (IS_ERR(dentry_page)) {
|
|
err = PTR_ERR(dentry_page);
|
|
if (err == -ENOENT) {
|
|
err = 0;
|
|
continue;
|
|
} else {
|
|
goto out_free;
|
|
}
|
|
}
|
|
|
|
dentry_blk = page_address(dentry_page);
|
|
|
|
make_dentry_ptr_block(inode, &d, dentry_blk);
|
|
|
|
err = f2fs_fill_dentries(ctx, &d,
|
|
n * NR_DENTRY_IN_BLOCK, &fstr);
|
|
if (err) {
|
|
f2fs_put_page(dentry_page, 0);
|
|
break;
|
|
}
|
|
|
|
f2fs_put_page(dentry_page, 0);
|
|
}
|
|
out_free:
|
|
fscrypt_fname_free_buffer(&fstr);
|
|
out:
|
|
trace_f2fs_readdir(inode, start_pos, ctx->pos, err);
|
|
return err < 0 ? err : 0;
|
|
}
|
|
|
|
static int f2fs_dir_open(struct inode *inode, struct file *filp)
|
|
{
|
|
if (IS_ENCRYPTED(inode))
|
|
return fscrypt_get_encryption_info(inode) ? -EACCES : 0;
|
|
return 0;
|
|
}
|
|
|
|
const struct file_operations f2fs_dir_operations = {
|
|
.llseek = generic_file_llseek,
|
|
.read = generic_read_dir,
|
|
.iterate_shared = f2fs_readdir,
|
|
.fsync = f2fs_sync_file,
|
|
.open = f2fs_dir_open,
|
|
.unlocked_ioctl = f2fs_ioctl,
|
|
#ifdef CONFIG_COMPAT
|
|
.compat_ioctl = f2fs_compat_ioctl,
|
|
#endif
|
|
};
|