linux/fs/f2fs/xattr.c
Chao Yu ba38c27eb9 f2fs: enhance lookup xattr
Previously, in getxattr we will load all entries both in inline xattr and
xattr node block, and then do the lookup in all entries, but our lookup
flow shows low efficiency, since if we can lookup and hit in inline xattr
of inode page cache first, we don't need to load and lookup xattr node
block, which can obviously save cpu time and IO latency.

Signed-off-by: Chao Yu <yuchao0@huawei.com>
[Jaegeuk Kim: initialize NULL to avoid warning]
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-02-22 20:24:51 -08:00

690 lines
16 KiB
C

/*
* fs/f2fs/xattr.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*
* Portions of this code from linux/fs/ext2/xattr.c
*
* Copyright (C) 2001-2003 Andreas Gruenbacher <agruen@suse.de>
*
* Fix by Harrison Xing <harrison@mountainviewdata.com>.
* Extended attributes for symlinks and special files added per
* suggestion of Luka Renko <luka.renko@hermes.si>.
* xattr consolidation Copyright (c) 2004 James Morris <jmorris@redhat.com>,
* Red Hat Inc.
*
* 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/rwsem.h>
#include <linux/f2fs_fs.h>
#include <linux/security.h>
#include <linux/posix_acl_xattr.h>
#include "f2fs.h"
#include "xattr.h"
static int f2fs_xattr_generic_get(const struct xattr_handler *handler,
struct dentry *unused, struct inode *inode,
const char *name, void *buffer, size_t size)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
switch (handler->flags) {
case F2FS_XATTR_INDEX_USER:
if (!test_opt(sbi, XATTR_USER))
return -EOPNOTSUPP;
break;
case F2FS_XATTR_INDEX_TRUSTED:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
break;
case F2FS_XATTR_INDEX_SECURITY:
break;
default:
return -EINVAL;
}
return f2fs_getxattr(inode, handler->flags, name,
buffer, size, NULL);
}
static int f2fs_xattr_generic_set(const struct xattr_handler *handler,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
switch (handler->flags) {
case F2FS_XATTR_INDEX_USER:
if (!test_opt(sbi, XATTR_USER))
return -EOPNOTSUPP;
break;
case F2FS_XATTR_INDEX_TRUSTED:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
break;
case F2FS_XATTR_INDEX_SECURITY:
break;
default:
return -EINVAL;
}
return f2fs_setxattr(inode, handler->flags, name,
value, size, NULL, flags);
}
static bool f2fs_xattr_user_list(struct dentry *dentry)
{
struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
return test_opt(sbi, XATTR_USER);
}
static bool f2fs_xattr_trusted_list(struct dentry *dentry)
{
return capable(CAP_SYS_ADMIN);
}
static int f2fs_xattr_advise_get(const struct xattr_handler *handler,
struct dentry *unused, struct inode *inode,
const char *name, void *buffer, size_t size)
{
if (buffer)
*((char *)buffer) = F2FS_I(inode)->i_advise;
return sizeof(char);
}
static int f2fs_xattr_advise_set(const struct xattr_handler *handler,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
{
if (!inode_owner_or_capable(inode))
return -EPERM;
if (value == NULL)
return -EINVAL;
F2FS_I(inode)->i_advise |= *(char *)value;
f2fs_mark_inode_dirty_sync(inode, true);
return 0;
}
#ifdef CONFIG_F2FS_FS_SECURITY
static int f2fs_initxattrs(struct inode *inode, const struct xattr *xattr_array,
void *page)
{
const struct xattr *xattr;
int err = 0;
for (xattr = xattr_array; xattr->name != NULL; xattr++) {
err = f2fs_setxattr(inode, F2FS_XATTR_INDEX_SECURITY,
xattr->name, xattr->value,
xattr->value_len, (struct page *)page, 0);
if (err < 0)
break;
}
return err;
}
int f2fs_init_security(struct inode *inode, struct inode *dir,
const struct qstr *qstr, struct page *ipage)
{
return security_inode_init_security(inode, dir, qstr,
&f2fs_initxattrs, ipage);
}
#endif
const struct xattr_handler f2fs_xattr_user_handler = {
.prefix = XATTR_USER_PREFIX,
.flags = F2FS_XATTR_INDEX_USER,
.list = f2fs_xattr_user_list,
.get = f2fs_xattr_generic_get,
.set = f2fs_xattr_generic_set,
};
const struct xattr_handler f2fs_xattr_trusted_handler = {
.prefix = XATTR_TRUSTED_PREFIX,
.flags = F2FS_XATTR_INDEX_TRUSTED,
.list = f2fs_xattr_trusted_list,
.get = f2fs_xattr_generic_get,
.set = f2fs_xattr_generic_set,
};
const struct xattr_handler f2fs_xattr_advise_handler = {
.name = F2FS_SYSTEM_ADVISE_NAME,
.flags = F2FS_XATTR_INDEX_ADVISE,
.get = f2fs_xattr_advise_get,
.set = f2fs_xattr_advise_set,
};
const struct xattr_handler f2fs_xattr_security_handler = {
.prefix = XATTR_SECURITY_PREFIX,
.flags = F2FS_XATTR_INDEX_SECURITY,
.get = f2fs_xattr_generic_get,
.set = f2fs_xattr_generic_set,
};
static const struct xattr_handler *f2fs_xattr_handler_map[] = {
[F2FS_XATTR_INDEX_USER] = &f2fs_xattr_user_handler,
#ifdef CONFIG_F2FS_FS_POSIX_ACL
[F2FS_XATTR_INDEX_POSIX_ACL_ACCESS] = &posix_acl_access_xattr_handler,
[F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT] = &posix_acl_default_xattr_handler,
#endif
[F2FS_XATTR_INDEX_TRUSTED] = &f2fs_xattr_trusted_handler,
#ifdef CONFIG_F2FS_FS_SECURITY
[F2FS_XATTR_INDEX_SECURITY] = &f2fs_xattr_security_handler,
#endif
[F2FS_XATTR_INDEX_ADVISE] = &f2fs_xattr_advise_handler,
};
const struct xattr_handler *f2fs_xattr_handlers[] = {
&f2fs_xattr_user_handler,
#ifdef CONFIG_F2FS_FS_POSIX_ACL
&posix_acl_access_xattr_handler,
&posix_acl_default_xattr_handler,
#endif
&f2fs_xattr_trusted_handler,
#ifdef CONFIG_F2FS_FS_SECURITY
&f2fs_xattr_security_handler,
#endif
&f2fs_xattr_advise_handler,
NULL,
};
static inline const struct xattr_handler *f2fs_xattr_handler(int index)
{
const struct xattr_handler *handler = NULL;
if (index > 0 && index < ARRAY_SIZE(f2fs_xattr_handler_map))
handler = f2fs_xattr_handler_map[index];
return handler;
}
static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int index,
size_t len, const char *name)
{
struct f2fs_xattr_entry *entry;
list_for_each_xattr(entry, base_addr) {
if (entry->e_name_index != index)
continue;
if (entry->e_name_len != len)
continue;
if (!memcmp(entry->e_name, name, len))
break;
}
return entry;
}
static struct f2fs_xattr_entry *__find_inline_xattr(void *base_addr,
void **last_addr, int index,
size_t len, const char *name)
{
struct f2fs_xattr_entry *entry;
unsigned int inline_size = F2FS_INLINE_XATTR_ADDRS << 2;
list_for_each_xattr(entry, base_addr) {
if ((void *)entry + sizeof(__u32) > base_addr + inline_size ||
(void *)XATTR_NEXT_ENTRY(entry) + sizeof(__u32) >
base_addr + inline_size) {
*last_addr = entry;
return NULL;
}
if (entry->e_name_index != index)
continue;
if (entry->e_name_len != len)
continue;
if (!memcmp(entry->e_name, name, len))
break;
}
return entry;
}
static int lookup_all_xattrs(struct inode *inode, struct page *ipage,
unsigned int index, unsigned int len,
const char *name, struct f2fs_xattr_entry **xe,
void **base_addr)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
void *cur_addr, *txattr_addr, *last_addr = NULL;
nid_t xnid = F2FS_I(inode)->i_xattr_nid;
unsigned int size = xnid ? VALID_XATTR_BLOCK_SIZE : 0;
unsigned int inline_size = 0;
int err = 0;
inline_size = inline_xattr_size(inode);
if (!size && !inline_size)
return -ENODATA;
txattr_addr = kzalloc(inline_size + size + sizeof(__u32),
GFP_F2FS_ZERO);
if (!txattr_addr)
return -ENOMEM;
/* read from inline xattr */
if (inline_size) {
struct page *page = NULL;
void *inline_addr;
if (ipage) {
inline_addr = inline_xattr_addr(ipage);
} else {
page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto out;
}
inline_addr = inline_xattr_addr(page);
}
memcpy(txattr_addr, inline_addr, inline_size);
f2fs_put_page(page, 1);
*xe = __find_inline_xattr(txattr_addr, &last_addr,
index, len, name);
if (*xe)
goto check;
}
/* read from xattr node block */
if (xnid) {
struct page *xpage;
void *xattr_addr;
/* The inode already has an extended attribute block. */
xpage = get_node_page(sbi, xnid);
if (IS_ERR(xpage)) {
err = PTR_ERR(xpage);
goto out;
}
xattr_addr = page_address(xpage);
memcpy(txattr_addr + inline_size, xattr_addr, size);
f2fs_put_page(xpage, 1);
}
if (last_addr)
cur_addr = XATTR_HDR(last_addr) - 1;
else
cur_addr = txattr_addr;
*xe = __find_xattr(cur_addr, index, len, name);
check:
if (IS_XATTR_LAST_ENTRY(*xe)) {
err = -ENODATA;
goto out;
}
*base_addr = txattr_addr;
return 0;
out:
kzfree(txattr_addr);
return err;
}
static int read_all_xattrs(struct inode *inode, struct page *ipage,
void **base_addr)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_xattr_header *header;
size_t size = PAGE_SIZE, inline_size = 0;
void *txattr_addr;
int err;
inline_size = inline_xattr_size(inode);
txattr_addr = kzalloc(inline_size + size, GFP_F2FS_ZERO);
if (!txattr_addr)
return -ENOMEM;
/* read from inline xattr */
if (inline_size) {
struct page *page = NULL;
void *inline_addr;
if (ipage) {
inline_addr = inline_xattr_addr(ipage);
} else {
page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
}
inline_addr = inline_xattr_addr(page);
}
memcpy(txattr_addr, inline_addr, inline_size);
f2fs_put_page(page, 1);
}
/* read from xattr node block */
if (F2FS_I(inode)->i_xattr_nid) {
struct page *xpage;
void *xattr_addr;
/* The inode already has an extended attribute block. */
xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
if (IS_ERR(xpage)) {
err = PTR_ERR(xpage);
goto fail;
}
xattr_addr = page_address(xpage);
memcpy(txattr_addr + inline_size, xattr_addr, PAGE_SIZE);
f2fs_put_page(xpage, 1);
}
header = XATTR_HDR(txattr_addr);
/* never been allocated xattrs */
if (le32_to_cpu(header->h_magic) != F2FS_XATTR_MAGIC) {
header->h_magic = cpu_to_le32(F2FS_XATTR_MAGIC);
header->h_refcount = cpu_to_le32(1);
}
*base_addr = txattr_addr;
return 0;
fail:
kzfree(txattr_addr);
return err;
}
static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
void *txattr_addr, struct page *ipage)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
size_t inline_size = 0;
void *xattr_addr;
struct page *xpage;
nid_t new_nid = 0;
int err;
inline_size = inline_xattr_size(inode);
if (hsize > inline_size && !F2FS_I(inode)->i_xattr_nid)
if (!alloc_nid(sbi, &new_nid))
return -ENOSPC;
/* write to inline xattr */
if (inline_size) {
struct page *page = NULL;
void *inline_addr;
if (ipage) {
inline_addr = inline_xattr_addr(ipage);
f2fs_wait_on_page_writeback(ipage, NODE, true);
set_page_dirty(ipage);
} else {
page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
alloc_nid_failed(sbi, new_nid);
return PTR_ERR(page);
}
inline_addr = inline_xattr_addr(page);
f2fs_wait_on_page_writeback(page, NODE, true);
}
memcpy(inline_addr, txattr_addr, inline_size);
f2fs_put_page(page, 1);
/* no need to use xattr node block */
if (hsize <= inline_size) {
err = truncate_xattr_node(inode, ipage);
alloc_nid_failed(sbi, new_nid);
return err;
}
}
/* write to xattr node block */
if (F2FS_I(inode)->i_xattr_nid) {
xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
if (IS_ERR(xpage)) {
alloc_nid_failed(sbi, new_nid);
return PTR_ERR(xpage);
}
f2fs_bug_on(sbi, new_nid);
f2fs_wait_on_page_writeback(xpage, NODE, true);
} else {
struct dnode_of_data dn;
set_new_dnode(&dn, inode, NULL, NULL, new_nid);
xpage = new_node_page(&dn, XATTR_NODE_OFFSET, ipage);
if (IS_ERR(xpage)) {
alloc_nid_failed(sbi, new_nid);
return PTR_ERR(xpage);
}
alloc_nid_done(sbi, new_nid);
}
xattr_addr = page_address(xpage);
memcpy(xattr_addr, txattr_addr + inline_size, MAX_XATTR_BLOCK_SIZE);
set_page_dirty(xpage);
f2fs_put_page(xpage, 1);
/* need to checkpoint during fsync */
F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));
return 0;
}
int f2fs_getxattr(struct inode *inode, int index, const char *name,
void *buffer, size_t buffer_size, struct page *ipage)
{
struct f2fs_xattr_entry *entry = NULL;
int error = 0;
unsigned int size, len;
char *pval;
void *base_addr = NULL;
if (name == NULL)
return -EINVAL;
len = strlen(name);
if (len > F2FS_NAME_LEN)
return -ERANGE;
error = lookup_all_xattrs(inode, ipage, index, len, name,
&entry, &base_addr);
if (error)
return error;
size = le16_to_cpu(entry->e_value_size);
if (buffer && size > buffer_size) {
error = -ERANGE;
goto out;
}
pval = entry->e_name + entry->e_name_len;
if (buffer) {
char *pval = entry->e_name + entry->e_name_len;
memcpy(buffer, pval, size);
}
error = size;
out:
kzfree(base_addr);
return error;
}
ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
{
struct inode *inode = d_inode(dentry);
struct f2fs_xattr_entry *entry;
void *base_addr;
int error = 0;
size_t rest = buffer_size;
error = read_all_xattrs(inode, NULL, &base_addr);
if (error)
return error;
list_for_each_xattr(entry, base_addr) {
const struct xattr_handler *handler =
f2fs_xattr_handler(entry->e_name_index);
const char *prefix;
size_t prefix_len;
size_t size;
if (!handler || (handler->list && !handler->list(dentry)))
continue;
prefix = handler->prefix ?: handler->name;
prefix_len = strlen(prefix);
size = prefix_len + entry->e_name_len + 1;
if (buffer) {
if (size > rest) {
error = -ERANGE;
goto cleanup;
}
memcpy(buffer, prefix, prefix_len);
buffer += prefix_len;
memcpy(buffer, entry->e_name, entry->e_name_len);
buffer += entry->e_name_len;
*buffer++ = 0;
}
rest -= size;
}
error = buffer_size - rest;
cleanup:
kzfree(base_addr);
return error;
}
static int __f2fs_setxattr(struct inode *inode, int index,
const char *name, const void *value, size_t size,
struct page *ipage, int flags)
{
struct f2fs_xattr_entry *here, *last;
void *base_addr;
int found, newsize;
size_t len;
__u32 new_hsize;
int error = 0;
if (name == NULL)
return -EINVAL;
if (value == NULL)
size = 0;
len = strlen(name);
if (len > F2FS_NAME_LEN)
return -ERANGE;
if (size > MAX_VALUE_LEN(inode))
return -E2BIG;
error = read_all_xattrs(inode, ipage, &base_addr);
if (error)
return error;
/* find entry with wanted name. */
here = __find_xattr(base_addr, index, len, name);
found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1;
if ((flags & XATTR_REPLACE) && !found) {
error = -ENODATA;
goto exit;
} else if ((flags & XATTR_CREATE) && found) {
error = -EEXIST;
goto exit;
}
last = here;
while (!IS_XATTR_LAST_ENTRY(last))
last = XATTR_NEXT_ENTRY(last);
newsize = XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + len + size);
/* 1. Check space */
if (value) {
int free;
/*
* If value is NULL, it is remove operation.
* In case of update operation, we calculate free.
*/
free = MIN_OFFSET(inode) - ((char *)last - (char *)base_addr);
if (found)
free = free + ENTRY_SIZE(here);
if (unlikely(free < newsize)) {
error = -E2BIG;
goto exit;
}
}
/* 2. Remove old entry */
if (found) {
/*
* If entry is found, remove old entry.
* If not found, remove operation is not needed.
*/
struct f2fs_xattr_entry *next = XATTR_NEXT_ENTRY(here);
int oldsize = ENTRY_SIZE(here);
memmove(here, next, (char *)last - (char *)next);
last = (struct f2fs_xattr_entry *)((char *)last - oldsize);
memset(last, 0, oldsize);
}
new_hsize = (char *)last - (char *)base_addr;
/* 3. Write new entry */
if (value) {
char *pval;
/*
* Before we come here, old entry is removed.
* We just write new entry.
*/
last->e_name_index = index;
last->e_name_len = len;
memcpy(last->e_name, name, len);
pval = last->e_name + len;
memcpy(pval, value, size);
last->e_value_size = cpu_to_le16(size);
new_hsize += newsize;
}
error = write_all_xattrs(inode, new_hsize, base_addr, ipage);
if (error)
goto exit;
if (is_inode_flag_set(inode, FI_ACL_MODE)) {
inode->i_mode = F2FS_I(inode)->i_acl_mode;
inode->i_ctime = current_time(inode);
clear_inode_flag(inode, FI_ACL_MODE);
}
if (index == F2FS_XATTR_INDEX_ENCRYPTION &&
!strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT))
f2fs_set_encrypted_inode(inode);
f2fs_mark_inode_dirty_sync(inode, true);
if (!error && S_ISDIR(inode->i_mode))
set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_CP);
exit:
kzfree(base_addr);
return error;
}
int f2fs_setxattr(struct inode *inode, int index, const char *name,
const void *value, size_t size,
struct page *ipage, int flags)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int err;
/* this case is only from init_inode_metadata */
if (ipage)
return __f2fs_setxattr(inode, index, name, value,
size, ipage, flags);
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
/* protect xattr_ver */
down_write(&F2FS_I(inode)->i_sem);
err = __f2fs_setxattr(inode, index, name, value, size, ipage, flags);
up_write(&F2FS_I(inode)->i_sem);
f2fs_unlock_op(sbi);
f2fs_update_time(sbi, REQ_TIME);
return err;
}