linux/fs/f2fs/xattr.c

855 lines
21 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* 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.
*/
#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"
#include "segment.h"
static void *xattr_alloc(struct f2fs_sb_info *sbi, int size, bool *is_inline)
{
if (likely(size == sbi->inline_xattr_slab_size)) {
*is_inline = true;
return f2fs_kmem_cache_alloc(sbi->inline_xattr_slab,
GFP_F2FS_ZERO, false, sbi);
}
*is_inline = false;
return f2fs_kzalloc(sbi, size, GFP_NOFS);
}
static void xattr_free(struct f2fs_sb_info *sbi, void *xattr_addr,
bool is_inline)
{
if (is_inline)
kmem_cache_free(sbi->inline_xattr_slab, xattr_addr);
else
kfree(xattr_addr);
}
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:
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 mnt_idmap *idmap,
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:
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)
{
f2fs: avoid NULL pointer dereference in f2fs_xattr_advise_get We will encounter oops by executing below command. getfattr -n system.advise /mnt/f2fs/file Killed message log: BUG: unable to handle kernel NULL pointer dereference at (null) IP: [<f8b54d69>] f2fs_xattr_advise_get+0x29/0x40 [f2fs] *pdpt = 00000000319b7001 *pde = 0000000000000000 Oops: 0002 [#1] SMP Modules linked in: f2fs(O) snd_intel8x0 snd_ac97_codec ac97_bus snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq joydev snd_seq_device snd_timer bnep snd rfcomm microcode bluetooth soundcore i2c_piix4 mac_hid serio_raw parport_pc ppdev lp parport binfmt_misc hid_generic psmouse usbhid hid e1000 [last unloaded: f2fs] CPU: 3 PID: 3134 Comm: getfattr Tainted: G O 4.0.0-rc1 #6 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 task: f3a71b60 ti: f19a6000 task.ti: f19a6000 EIP: 0060:[<f8b54d69>] EFLAGS: 00010246 CPU: 3 EIP is at f2fs_xattr_advise_get+0x29/0x40 [f2fs] EAX: 00000000 EBX: f19a7e71 ECX: 00000000 EDX: f8b5b467 ESI: 00000000 EDI: f2008570 EBP: f19a7e14 ESP: f19a7e08 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 CR0: 80050033 CR2: 00000000 CR3: 319b8000 CR4: 000007f0 Stack: f8b5a634 c0cbb580 00000000 f19a7e34 c1193850 00000000 00000007 f19a7e71 f19a7e64 c0cbb580 c1193810 f19a7e50 c1193c00 00000000 00000000 00000000 c0cbb580 00000000 f19a7f70 c1194097 00000000 00000000 00000000 74737973 Call Trace: [<c1193850>] generic_getxattr+0x40/0x50 [<c1193810>] ? xattr_resolve_name+0x80/0x80 [<c1193c00>] vfs_getxattr+0x70/0xa0 [<c1194097>] getxattr+0x87/0x190 [<c11801d7>] ? path_lookupat+0x57/0x5f0 [<c11819d2>] ? putname+0x32/0x50 [<c116653a>] ? kmem_cache_alloc+0x2a/0x130 [<c11819d2>] ? putname+0x32/0x50 [<c11819d2>] ? putname+0x32/0x50 [<c11819d2>] ? putname+0x32/0x50 [<c11827f9>] ? user_path_at_empty+0x49/0x70 [<c118283f>] ? user_path_at+0x1f/0x30 [<c11941e7>] path_getxattr+0x47/0x80 [<c11948e7>] SyS_getxattr+0x27/0x30 [<c163f748>] sysenter_do_call+0x12/0x12 Code: 66 90 55 89 e5 57 56 53 66 66 66 66 90 8b 78 20 89 d3 ba 67 b4 b5 f8 89 d8 89 ce e8 42 7c 7b c8 85 c0 75 16 0f b6 87 44 01 00 00 <88> 06 b8 01 00 00 00 5b 5e 5f 5d c3 8d 76 00 b8 ea ff ff ff eb EIP: [<f8b54d69>] f2fs_xattr_advise_get+0x29/0x40 [f2fs] SS:ESP 0068:f19a7e08 CR2: 0000000000000000 ---[ end trace 860260654f1f416a ]--- The reason is that in getfattr there are two steps which is indicated by strace info: 1) try to lookup and get size of specified xattr. 2) get value of the extented attribute. strace info: getxattr("/mnt/f2fs/file", "system.advise", 0x0, 0) = 1 getxattr("/mnt/f2fs/file", "system.advise", "\x00", 256) = 1 For the first step, getfattr may pass a NULL pointer in @value and zero in @size as parameters for ->getxattr, but we access this @value pointer directly without checking whether the pointer is valid or not in f2fs_xattr_advise_get, so the oops occurs. This patch fixes this issue by verifying @value pointer before using. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-03-23 02:36:15 +00:00
if (buffer)
*((char *)buffer) = F2FS_I(inode)->i_advise;
return sizeof(char);
}
static int f2fs_xattr_advise_set(const struct xattr_handler *handler,
struct mnt_idmap *idmap,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
{
unsigned char old_advise = F2FS_I(inode)->i_advise;
unsigned char new_advise;
if (!inode_owner_or_capable(&nop_mnt_idmap, inode))
return -EPERM;
if (value == NULL)
return -EINVAL;
new_advise = *(char *)value;
if (new_advise & ~FADVISE_MODIFIABLE_BITS)
return -EINVAL;
new_advise = new_advise & FADVISE_MODIFIABLE_BITS;
new_advise |= old_advise & ~FADVISE_MODIFIABLE_BITS;
F2FS_I(inode)->i_advise = new_advise;
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 * const f2fs_xattr_handler_map[] = {
[F2FS_XATTR_INDEX_USER] = &f2fs_xattr_user_handler,
#ifdef CONFIG_F2FS_FS_POSIX_ACL
[F2FS_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access,
[F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default,
#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 * const f2fs_xattr_handlers[] = {
&f2fs_xattr_user_handler,
&f2fs_xattr_trusted_handler,
#ifdef CONFIG_F2FS_FS_SECURITY
&f2fs_xattr_security_handler,
#endif
&f2fs_xattr_advise_handler,
NULL,
};
static inline const char *f2fs_xattr_prefix(int index,
struct dentry *dentry)
{
const struct xattr_handler *handler = NULL;
if (index > 0 && index < ARRAY_SIZE(f2fs_xattr_handler_map))
handler = f2fs_xattr_handler_map[index];
if (!xattr_handler_can_list(handler, dentry))
return NULL;
return xattr_prefix(handler);
}
f2fs: fix to avoid accessing xattr across the boundary When we traverse xattr entries via __find_xattr(), if the raw filesystem content is faked or any hardware failure occurs, out-of-bound error can be detected by KASAN. Fix the issue by introducing boundary check. [ 38.402878] c7 1827 BUG: KASAN: slab-out-of-bounds in f2fs_getxattr+0x518/0x68c [ 38.402891] c7 1827 Read of size 4 at addr ffffffc0b6fb35dc by task [ 38.402935] c7 1827 Call trace: [ 38.402952] c7 1827 [<ffffff900809003c>] dump_backtrace+0x0/0x6bc [ 38.402966] c7 1827 [<ffffff9008090030>] show_stack+0x20/0x2c [ 38.402981] c7 1827 [<ffffff900871ab10>] dump_stack+0xfc/0x140 [ 38.402995] c7 1827 [<ffffff9008325c40>] print_address_description+0x80/0x2d8 [ 38.403009] c7 1827 [<ffffff900832629c>] kasan_report_error+0x198/0x1fc [ 38.403022] c7 1827 [<ffffff9008326104>] kasan_report_error+0x0/0x1fc [ 38.403037] c7 1827 [<ffffff9008325000>] __asan_load4+0x1b0/0x1b8 [ 38.403051] c7 1827 [<ffffff90085fcc44>] f2fs_getxattr+0x518/0x68c [ 38.403066] c7 1827 [<ffffff90085fc508>] f2fs_xattr_generic_get+0xb0/0xd0 [ 38.403080] c7 1827 [<ffffff9008395708>] __vfs_getxattr+0x1f4/0x1fc [ 38.403096] c7 1827 [<ffffff9008621bd0>] inode_doinit_with_dentry+0x360/0x938 [ 38.403109] c7 1827 [<ffffff900862d6cc>] selinux_d_instantiate+0x2c/0x38 [ 38.403123] c7 1827 [<ffffff900861b018>] security_d_instantiate+0x68/0x98 [ 38.403136] c7 1827 [<ffffff9008377db8>] d_splice_alias+0x58/0x348 [ 38.403149] c7 1827 [<ffffff900858d16c>] f2fs_lookup+0x608/0x774 [ 38.403163] c7 1827 [<ffffff900835eacc>] lookup_slow+0x1e0/0x2cc [ 38.403177] c7 1827 [<ffffff9008367fe0>] walk_component+0x160/0x520 [ 38.403190] c7 1827 [<ffffff9008369ef4>] path_lookupat+0x110/0x2b4 [ 38.403203] c7 1827 [<ffffff900835dd38>] filename_lookup+0x1d8/0x3a8 [ 38.403216] c7 1827 [<ffffff900835eeb0>] user_path_at_empty+0x54/0x68 [ 38.403229] c7 1827 [<ffffff9008395f44>] SyS_getxattr+0xb4/0x18c [ 38.403241] c7 1827 [<ffffff9008084200>] el0_svc_naked+0x34/0x38 Signed-off-by: Randall Huang <huangrandall@google.com> [Jaegeuk Kim: Fix wrong ending boundary] Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-11 08:26:46 +00:00
static struct f2fs_xattr_entry *__find_xattr(void *base_addr,
void *last_base_addr, void **last_addr,
int index, size_t len, const char *name)
{
struct f2fs_xattr_entry *entry;
list_for_each_xattr(entry, base_addr) {
f2fs: fix to avoid accessing xattr across the boundary When we traverse xattr entries via __find_xattr(), if the raw filesystem content is faked or any hardware failure occurs, out-of-bound error can be detected by KASAN. Fix the issue by introducing boundary check. [ 38.402878] c7 1827 BUG: KASAN: slab-out-of-bounds in f2fs_getxattr+0x518/0x68c [ 38.402891] c7 1827 Read of size 4 at addr ffffffc0b6fb35dc by task [ 38.402935] c7 1827 Call trace: [ 38.402952] c7 1827 [<ffffff900809003c>] dump_backtrace+0x0/0x6bc [ 38.402966] c7 1827 [<ffffff9008090030>] show_stack+0x20/0x2c [ 38.402981] c7 1827 [<ffffff900871ab10>] dump_stack+0xfc/0x140 [ 38.402995] c7 1827 [<ffffff9008325c40>] print_address_description+0x80/0x2d8 [ 38.403009] c7 1827 [<ffffff900832629c>] kasan_report_error+0x198/0x1fc [ 38.403022] c7 1827 [<ffffff9008326104>] kasan_report_error+0x0/0x1fc [ 38.403037] c7 1827 [<ffffff9008325000>] __asan_load4+0x1b0/0x1b8 [ 38.403051] c7 1827 [<ffffff90085fcc44>] f2fs_getxattr+0x518/0x68c [ 38.403066] c7 1827 [<ffffff90085fc508>] f2fs_xattr_generic_get+0xb0/0xd0 [ 38.403080] c7 1827 [<ffffff9008395708>] __vfs_getxattr+0x1f4/0x1fc [ 38.403096] c7 1827 [<ffffff9008621bd0>] inode_doinit_with_dentry+0x360/0x938 [ 38.403109] c7 1827 [<ffffff900862d6cc>] selinux_d_instantiate+0x2c/0x38 [ 38.403123] c7 1827 [<ffffff900861b018>] security_d_instantiate+0x68/0x98 [ 38.403136] c7 1827 [<ffffff9008377db8>] d_splice_alias+0x58/0x348 [ 38.403149] c7 1827 [<ffffff900858d16c>] f2fs_lookup+0x608/0x774 [ 38.403163] c7 1827 [<ffffff900835eacc>] lookup_slow+0x1e0/0x2cc [ 38.403177] c7 1827 [<ffffff9008367fe0>] walk_component+0x160/0x520 [ 38.403190] c7 1827 [<ffffff9008369ef4>] path_lookupat+0x110/0x2b4 [ 38.403203] c7 1827 [<ffffff900835dd38>] filename_lookup+0x1d8/0x3a8 [ 38.403216] c7 1827 [<ffffff900835eeb0>] user_path_at_empty+0x54/0x68 [ 38.403229] c7 1827 [<ffffff9008395f44>] SyS_getxattr+0xb4/0x18c [ 38.403241] c7 1827 [<ffffff9008084200>] el0_svc_naked+0x34/0x38 Signed-off-by: Randall Huang <huangrandall@google.com> [Jaegeuk Kim: Fix wrong ending boundary] Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-11 08:26:46 +00:00
if ((void *)(entry) + sizeof(__u32) > last_base_addr ||
(void *)XATTR_NEXT_ENTRY(entry) > last_base_addr) {
if (last_addr)
*last_addr = entry;
f2fs: fix to avoid accessing xattr across the boundary When we traverse xattr entries via __find_xattr(), if the raw filesystem content is faked or any hardware failure occurs, out-of-bound error can be detected by KASAN. Fix the issue by introducing boundary check. [ 38.402878] c7 1827 BUG: KASAN: slab-out-of-bounds in f2fs_getxattr+0x518/0x68c [ 38.402891] c7 1827 Read of size 4 at addr ffffffc0b6fb35dc by task [ 38.402935] c7 1827 Call trace: [ 38.402952] c7 1827 [<ffffff900809003c>] dump_backtrace+0x0/0x6bc [ 38.402966] c7 1827 [<ffffff9008090030>] show_stack+0x20/0x2c [ 38.402981] c7 1827 [<ffffff900871ab10>] dump_stack+0xfc/0x140 [ 38.402995] c7 1827 [<ffffff9008325c40>] print_address_description+0x80/0x2d8 [ 38.403009] c7 1827 [<ffffff900832629c>] kasan_report_error+0x198/0x1fc [ 38.403022] c7 1827 [<ffffff9008326104>] kasan_report_error+0x0/0x1fc [ 38.403037] c7 1827 [<ffffff9008325000>] __asan_load4+0x1b0/0x1b8 [ 38.403051] c7 1827 [<ffffff90085fcc44>] f2fs_getxattr+0x518/0x68c [ 38.403066] c7 1827 [<ffffff90085fc508>] f2fs_xattr_generic_get+0xb0/0xd0 [ 38.403080] c7 1827 [<ffffff9008395708>] __vfs_getxattr+0x1f4/0x1fc [ 38.403096] c7 1827 [<ffffff9008621bd0>] inode_doinit_with_dentry+0x360/0x938 [ 38.403109] c7 1827 [<ffffff900862d6cc>] selinux_d_instantiate+0x2c/0x38 [ 38.403123] c7 1827 [<ffffff900861b018>] security_d_instantiate+0x68/0x98 [ 38.403136] c7 1827 [<ffffff9008377db8>] d_splice_alias+0x58/0x348 [ 38.403149] c7 1827 [<ffffff900858d16c>] f2fs_lookup+0x608/0x774 [ 38.403163] c7 1827 [<ffffff900835eacc>] lookup_slow+0x1e0/0x2cc [ 38.403177] c7 1827 [<ffffff9008367fe0>] walk_component+0x160/0x520 [ 38.403190] c7 1827 [<ffffff9008369ef4>] path_lookupat+0x110/0x2b4 [ 38.403203] c7 1827 [<ffffff900835dd38>] filename_lookup+0x1d8/0x3a8 [ 38.403216] c7 1827 [<ffffff900835eeb0>] user_path_at_empty+0x54/0x68 [ 38.403229] c7 1827 [<ffffff9008395f44>] SyS_getxattr+0xb4/0x18c [ 38.403241] c7 1827 [<ffffff9008084200>] el0_svc_naked+0x34/0x38 Signed-off-by: Randall Huang <huangrandall@google.com> [Jaegeuk Kim: Fix wrong ending boundary] Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-11 08:26:46 +00:00
return NULL;
}
f2fs: fix to avoid accessing xattr across the boundary When we traverse xattr entries via __find_xattr(), if the raw filesystem content is faked or any hardware failure occurs, out-of-bound error can be detected by KASAN. Fix the issue by introducing boundary check. [ 38.402878] c7 1827 BUG: KASAN: slab-out-of-bounds in f2fs_getxattr+0x518/0x68c [ 38.402891] c7 1827 Read of size 4 at addr ffffffc0b6fb35dc by task [ 38.402935] c7 1827 Call trace: [ 38.402952] c7 1827 [<ffffff900809003c>] dump_backtrace+0x0/0x6bc [ 38.402966] c7 1827 [<ffffff9008090030>] show_stack+0x20/0x2c [ 38.402981] c7 1827 [<ffffff900871ab10>] dump_stack+0xfc/0x140 [ 38.402995] c7 1827 [<ffffff9008325c40>] print_address_description+0x80/0x2d8 [ 38.403009] c7 1827 [<ffffff900832629c>] kasan_report_error+0x198/0x1fc [ 38.403022] c7 1827 [<ffffff9008326104>] kasan_report_error+0x0/0x1fc [ 38.403037] c7 1827 [<ffffff9008325000>] __asan_load4+0x1b0/0x1b8 [ 38.403051] c7 1827 [<ffffff90085fcc44>] f2fs_getxattr+0x518/0x68c [ 38.403066] c7 1827 [<ffffff90085fc508>] f2fs_xattr_generic_get+0xb0/0xd0 [ 38.403080] c7 1827 [<ffffff9008395708>] __vfs_getxattr+0x1f4/0x1fc [ 38.403096] c7 1827 [<ffffff9008621bd0>] inode_doinit_with_dentry+0x360/0x938 [ 38.403109] c7 1827 [<ffffff900862d6cc>] selinux_d_instantiate+0x2c/0x38 [ 38.403123] c7 1827 [<ffffff900861b018>] security_d_instantiate+0x68/0x98 [ 38.403136] c7 1827 [<ffffff9008377db8>] d_splice_alias+0x58/0x348 [ 38.403149] c7 1827 [<ffffff900858d16c>] f2fs_lookup+0x608/0x774 [ 38.403163] c7 1827 [<ffffff900835eacc>] lookup_slow+0x1e0/0x2cc [ 38.403177] c7 1827 [<ffffff9008367fe0>] walk_component+0x160/0x520 [ 38.403190] c7 1827 [<ffffff9008369ef4>] path_lookupat+0x110/0x2b4 [ 38.403203] c7 1827 [<ffffff900835dd38>] filename_lookup+0x1d8/0x3a8 [ 38.403216] c7 1827 [<ffffff900835eeb0>] user_path_at_empty+0x54/0x68 [ 38.403229] c7 1827 [<ffffff9008395f44>] SyS_getxattr+0xb4/0x18c [ 38.403241] c7 1827 [<ffffff9008084200>] el0_svc_naked+0x34/0x38 Signed-off-by: Randall Huang <huangrandall@google.com> [Jaegeuk Kim: Fix wrong ending boundary] Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-11 08:26:46 +00:00
if (entry->e_name_index != index)
continue;
if (entry->e_name_len != len)
continue;
if (!memcmp(entry->e_name, name, len))
break;
}
return entry;
}
f2fs: support flexible inline xattr size Now, in product, more and more features based on file encryption were introduced, their demand of xattr space is increasing, however, inline xattr has fixed-size of 200 bytes, once inline xattr space is full, new increased xattr data would occupy additional xattr block which may bring us more space usage and performance regression during persisting. In order to resolve above issue, it's better to expand inline xattr size flexibly according to user's requirement. So this patch introduces new filesystem feature 'flexible inline xattr', and new mount option 'inline_xattr_size=%u', once mkfs enables the feature, we can use the option to make f2fs supporting flexible inline xattr size. To support this feature, we add extra attribute i_inline_xattr_size in inode layout, indicating that how many space inline xattr borrows from block address mapping space in inode layout, by this, we can easily locate and store flexible-sized inline xattr data in inode. Inode disk layout: +----------------------+ | .i_mode | | ... | | .i_ext | +----------------------+ | .i_extra_isize | | .i_inline_xattr_size |-----------+ | ... | | +----------------------+ | | .i_addr | | | - block address or | | | - inline data | | +----------------------+<---+ v | inline xattr | +---inline xattr range +----------------------+<---+ | .i_nid | +----------------------+ | node_footer | | (nid, ino, offset) | +----------------------+ Note that, we have to cnosider backward compatibility which reserved inline_data space, 200 bytes, all the time, reported by Sheng Yong. Previous inline data or directory always reserved 200 bytes in inode layout, even if inline_xattr is disabled. In order to keep inline_dentry's structure for backward compatibility, we get the space back only from inline_data. Signed-off-by: Chao Yu <yuchao0@huawei.com> Reported-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-09-06 13:59:50 +00:00
static struct f2fs_xattr_entry *__find_inline_xattr(struct inode *inode,
void *base_addr, void **last_addr, int index,
size_t len, const char *name)
{
struct f2fs_xattr_entry *entry;
f2fs: support flexible inline xattr size Now, in product, more and more features based on file encryption were introduced, their demand of xattr space is increasing, however, inline xattr has fixed-size of 200 bytes, once inline xattr space is full, new increased xattr data would occupy additional xattr block which may bring us more space usage and performance regression during persisting. In order to resolve above issue, it's better to expand inline xattr size flexibly according to user's requirement. So this patch introduces new filesystem feature 'flexible inline xattr', and new mount option 'inline_xattr_size=%u', once mkfs enables the feature, we can use the option to make f2fs supporting flexible inline xattr size. To support this feature, we add extra attribute i_inline_xattr_size in inode layout, indicating that how many space inline xattr borrows from block address mapping space in inode layout, by this, we can easily locate and store flexible-sized inline xattr data in inode. Inode disk layout: +----------------------+ | .i_mode | | ... | | .i_ext | +----------------------+ | .i_extra_isize | | .i_inline_xattr_size |-----------+ | ... | | +----------------------+ | | .i_addr | | | - block address or | | | - inline data | | +----------------------+<---+ v | inline xattr | +---inline xattr range +----------------------+<---+ | .i_nid | +----------------------+ | node_footer | | (nid, ino, offset) | +----------------------+ Note that, we have to cnosider backward compatibility which reserved inline_data space, 200 bytes, all the time, reported by Sheng Yong. Previous inline data or directory always reserved 200 bytes in inode layout, even if inline_xattr is disabled. In order to keep inline_dentry's structure for backward compatibility, we get the space back only from inline_data. Signed-off-by: Chao Yu <yuchao0@huawei.com> Reported-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-09-06 13:59:50 +00:00
unsigned int inline_size = inline_xattr_size(inode);
void *max_addr = base_addr + inline_size;
entry = __find_xattr(base_addr, max_addr, last_addr, index, len, name);
if (!entry)
return NULL;
/* inline xattr header or entry across max inline xattr size */
if (IS_XATTR_LAST_ENTRY(entry) &&
(void *)entry + sizeof(__u32) > max_addr) {
*last_addr = entry;
return NULL;
}
return entry;
}
static int read_inline_xattr(struct inode *inode, struct page *ipage,
void *txattr_addr)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
unsigned int inline_size = inline_xattr_size(inode);
struct page *page = NULL;
void *inline_addr;
if (ipage) {
f2fs: support flexible inline xattr size Now, in product, more and more features based on file encryption were introduced, their demand of xattr space is increasing, however, inline xattr has fixed-size of 200 bytes, once inline xattr space is full, new increased xattr data would occupy additional xattr block which may bring us more space usage and performance regression during persisting. In order to resolve above issue, it's better to expand inline xattr size flexibly according to user's requirement. So this patch introduces new filesystem feature 'flexible inline xattr', and new mount option 'inline_xattr_size=%u', once mkfs enables the feature, we can use the option to make f2fs supporting flexible inline xattr size. To support this feature, we add extra attribute i_inline_xattr_size in inode layout, indicating that how many space inline xattr borrows from block address mapping space in inode layout, by this, we can easily locate and store flexible-sized inline xattr data in inode. Inode disk layout: +----------------------+ | .i_mode | | ... | | .i_ext | +----------------------+ | .i_extra_isize | | .i_inline_xattr_size |-----------+ | ... | | +----------------------+ | | .i_addr | | | - block address or | | | - inline data | | +----------------------+<---+ v | inline xattr | +---inline xattr range +----------------------+<---+ | .i_nid | +----------------------+ | node_footer | | (nid, ino, offset) | +----------------------+ Note that, we have to cnosider backward compatibility which reserved inline_data space, 200 bytes, all the time, reported by Sheng Yong. Previous inline data or directory always reserved 200 bytes in inode layout, even if inline_xattr is disabled. In order to keep inline_dentry's structure for backward compatibility, we get the space back only from inline_data. Signed-off-by: Chao Yu <yuchao0@huawei.com> Reported-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-09-06 13:59:50 +00:00
inline_addr = inline_xattr_addr(inode, ipage);
} else {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
page = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(page))
return PTR_ERR(page);
f2fs: support flexible inline xattr size Now, in product, more and more features based on file encryption were introduced, their demand of xattr space is increasing, however, inline xattr has fixed-size of 200 bytes, once inline xattr space is full, new increased xattr data would occupy additional xattr block which may bring us more space usage and performance regression during persisting. In order to resolve above issue, it's better to expand inline xattr size flexibly according to user's requirement. So this patch introduces new filesystem feature 'flexible inline xattr', and new mount option 'inline_xattr_size=%u', once mkfs enables the feature, we can use the option to make f2fs supporting flexible inline xattr size. To support this feature, we add extra attribute i_inline_xattr_size in inode layout, indicating that how many space inline xattr borrows from block address mapping space in inode layout, by this, we can easily locate and store flexible-sized inline xattr data in inode. Inode disk layout: +----------------------+ | .i_mode | | ... | | .i_ext | +----------------------+ | .i_extra_isize | | .i_inline_xattr_size |-----------+ | ... | | +----------------------+ | | .i_addr | | | - block address or | | | - inline data | | +----------------------+<---+ v | inline xattr | +---inline xattr range +----------------------+<---+ | .i_nid | +----------------------+ | node_footer | | (nid, ino, offset) | +----------------------+ Note that, we have to cnosider backward compatibility which reserved inline_data space, 200 bytes, all the time, reported by Sheng Yong. Previous inline data or directory always reserved 200 bytes in inode layout, even if inline_xattr is disabled. In order to keep inline_dentry's structure for backward compatibility, we get the space back only from inline_data. Signed-off-by: Chao Yu <yuchao0@huawei.com> Reported-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-09-06 13:59:50 +00:00
inline_addr = inline_xattr_addr(inode, page);
}
memcpy(txattr_addr, inline_addr, inline_size);
f2fs_put_page(page, 1);
return 0;
}
static int read_xattr_block(struct inode *inode, void *txattr_addr)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t xnid = F2FS_I(inode)->i_xattr_nid;
unsigned int inline_size = inline_xattr_size(inode);
struct page *xpage;
void *xattr_addr;
/* The inode already has an extended attribute block. */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
xpage = f2fs_get_node_page(sbi, xnid);
if (IS_ERR(xpage))
return PTR_ERR(xpage);
xattr_addr = page_address(xpage);
memcpy(txattr_addr + inline_size, xattr_addr, VALID_XATTR_BLOCK_SIZE);
f2fs_put_page(xpage, 1);
return 0;
}
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, int *base_size,
bool *is_inline)
{
f2fs: fix to avoid accessing xattr across the boundary When we traverse xattr entries via __find_xattr(), if the raw filesystem content is faked or any hardware failure occurs, out-of-bound error can be detected by KASAN. Fix the issue by introducing boundary check. [ 38.402878] c7 1827 BUG: KASAN: slab-out-of-bounds in f2fs_getxattr+0x518/0x68c [ 38.402891] c7 1827 Read of size 4 at addr ffffffc0b6fb35dc by task [ 38.402935] c7 1827 Call trace: [ 38.402952] c7 1827 [<ffffff900809003c>] dump_backtrace+0x0/0x6bc [ 38.402966] c7 1827 [<ffffff9008090030>] show_stack+0x20/0x2c [ 38.402981] c7 1827 [<ffffff900871ab10>] dump_stack+0xfc/0x140 [ 38.402995] c7 1827 [<ffffff9008325c40>] print_address_description+0x80/0x2d8 [ 38.403009] c7 1827 [<ffffff900832629c>] kasan_report_error+0x198/0x1fc [ 38.403022] c7 1827 [<ffffff9008326104>] kasan_report_error+0x0/0x1fc [ 38.403037] c7 1827 [<ffffff9008325000>] __asan_load4+0x1b0/0x1b8 [ 38.403051] c7 1827 [<ffffff90085fcc44>] f2fs_getxattr+0x518/0x68c [ 38.403066] c7 1827 [<ffffff90085fc508>] f2fs_xattr_generic_get+0xb0/0xd0 [ 38.403080] c7 1827 [<ffffff9008395708>] __vfs_getxattr+0x1f4/0x1fc [ 38.403096] c7 1827 [<ffffff9008621bd0>] inode_doinit_with_dentry+0x360/0x938 [ 38.403109] c7 1827 [<ffffff900862d6cc>] selinux_d_instantiate+0x2c/0x38 [ 38.403123] c7 1827 [<ffffff900861b018>] security_d_instantiate+0x68/0x98 [ 38.403136] c7 1827 [<ffffff9008377db8>] d_splice_alias+0x58/0x348 [ 38.403149] c7 1827 [<ffffff900858d16c>] f2fs_lookup+0x608/0x774 [ 38.403163] c7 1827 [<ffffff900835eacc>] lookup_slow+0x1e0/0x2cc [ 38.403177] c7 1827 [<ffffff9008367fe0>] walk_component+0x160/0x520 [ 38.403190] c7 1827 [<ffffff9008369ef4>] path_lookupat+0x110/0x2b4 [ 38.403203] c7 1827 [<ffffff900835dd38>] filename_lookup+0x1d8/0x3a8 [ 38.403216] c7 1827 [<ffffff900835eeb0>] user_path_at_empty+0x54/0x68 [ 38.403229] c7 1827 [<ffffff9008395f44>] SyS_getxattr+0xb4/0x18c [ 38.403241] c7 1827 [<ffffff9008084200>] el0_svc_naked+0x34/0x38 Signed-off-by: Randall Huang <huangrandall@google.com> [Jaegeuk Kim: Fix wrong ending boundary] Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-11 08:26:46 +00:00
void *cur_addr, *txattr_addr, *last_txattr_addr;
void *last_addr = NULL;
nid_t xnid = F2FS_I(inode)->i_xattr_nid;
unsigned int inline_size = inline_xattr_size(inode);
int err;
f2fs: fix to avoid accessing xattr across the boundary When we traverse xattr entries via __find_xattr(), if the raw filesystem content is faked or any hardware failure occurs, out-of-bound error can be detected by KASAN. Fix the issue by introducing boundary check. [ 38.402878] c7 1827 BUG: KASAN: slab-out-of-bounds in f2fs_getxattr+0x518/0x68c [ 38.402891] c7 1827 Read of size 4 at addr ffffffc0b6fb35dc by task [ 38.402935] c7 1827 Call trace: [ 38.402952] c7 1827 [<ffffff900809003c>] dump_backtrace+0x0/0x6bc [ 38.402966] c7 1827 [<ffffff9008090030>] show_stack+0x20/0x2c [ 38.402981] c7 1827 [<ffffff900871ab10>] dump_stack+0xfc/0x140 [ 38.402995] c7 1827 [<ffffff9008325c40>] print_address_description+0x80/0x2d8 [ 38.403009] c7 1827 [<ffffff900832629c>] kasan_report_error+0x198/0x1fc [ 38.403022] c7 1827 [<ffffff9008326104>] kasan_report_error+0x0/0x1fc [ 38.403037] c7 1827 [<ffffff9008325000>] __asan_load4+0x1b0/0x1b8 [ 38.403051] c7 1827 [<ffffff90085fcc44>] f2fs_getxattr+0x518/0x68c [ 38.403066] c7 1827 [<ffffff90085fc508>] f2fs_xattr_generic_get+0xb0/0xd0 [ 38.403080] c7 1827 [<ffffff9008395708>] __vfs_getxattr+0x1f4/0x1fc [ 38.403096] c7 1827 [<ffffff9008621bd0>] inode_doinit_with_dentry+0x360/0x938 [ 38.403109] c7 1827 [<ffffff900862d6cc>] selinux_d_instantiate+0x2c/0x38 [ 38.403123] c7 1827 [<ffffff900861b018>] security_d_instantiate+0x68/0x98 [ 38.403136] c7 1827 [<ffffff9008377db8>] d_splice_alias+0x58/0x348 [ 38.403149] c7 1827 [<ffffff900858d16c>] f2fs_lookup+0x608/0x774 [ 38.403163] c7 1827 [<ffffff900835eacc>] lookup_slow+0x1e0/0x2cc [ 38.403177] c7 1827 [<ffffff9008367fe0>] walk_component+0x160/0x520 [ 38.403190] c7 1827 [<ffffff9008369ef4>] path_lookupat+0x110/0x2b4 [ 38.403203] c7 1827 [<ffffff900835dd38>] filename_lookup+0x1d8/0x3a8 [ 38.403216] c7 1827 [<ffffff900835eeb0>] user_path_at_empty+0x54/0x68 [ 38.403229] c7 1827 [<ffffff9008395f44>] SyS_getxattr+0xb4/0x18c [ 38.403241] c7 1827 [<ffffff9008084200>] el0_svc_naked+0x34/0x38 Signed-off-by: Randall Huang <huangrandall@google.com> [Jaegeuk Kim: Fix wrong ending boundary] Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-11 08:26:46 +00:00
if (!xnid && !inline_size)
return -ENODATA;
*base_size = XATTR_SIZE(inode) + XATTR_PADDING_SIZE;
txattr_addr = xattr_alloc(F2FS_I_SB(inode), *base_size, is_inline);
if (!txattr_addr)
return -ENOMEM;
last_txattr_addr = (void *)txattr_addr + XATTR_SIZE(inode);
f2fs: fix to avoid accessing xattr across the boundary When we traverse xattr entries via __find_xattr(), if the raw filesystem content is faked or any hardware failure occurs, out-of-bound error can be detected by KASAN. Fix the issue by introducing boundary check. [ 38.402878] c7 1827 BUG: KASAN: slab-out-of-bounds in f2fs_getxattr+0x518/0x68c [ 38.402891] c7 1827 Read of size 4 at addr ffffffc0b6fb35dc by task [ 38.402935] c7 1827 Call trace: [ 38.402952] c7 1827 [<ffffff900809003c>] dump_backtrace+0x0/0x6bc [ 38.402966] c7 1827 [<ffffff9008090030>] show_stack+0x20/0x2c [ 38.402981] c7 1827 [<ffffff900871ab10>] dump_stack+0xfc/0x140 [ 38.402995] c7 1827 [<ffffff9008325c40>] print_address_description+0x80/0x2d8 [ 38.403009] c7 1827 [<ffffff900832629c>] kasan_report_error+0x198/0x1fc [ 38.403022] c7 1827 [<ffffff9008326104>] kasan_report_error+0x0/0x1fc [ 38.403037] c7 1827 [<ffffff9008325000>] __asan_load4+0x1b0/0x1b8 [ 38.403051] c7 1827 [<ffffff90085fcc44>] f2fs_getxattr+0x518/0x68c [ 38.403066] c7 1827 [<ffffff90085fc508>] f2fs_xattr_generic_get+0xb0/0xd0 [ 38.403080] c7 1827 [<ffffff9008395708>] __vfs_getxattr+0x1f4/0x1fc [ 38.403096] c7 1827 [<ffffff9008621bd0>] inode_doinit_with_dentry+0x360/0x938 [ 38.403109] c7 1827 [<ffffff900862d6cc>] selinux_d_instantiate+0x2c/0x38 [ 38.403123] c7 1827 [<ffffff900861b018>] security_d_instantiate+0x68/0x98 [ 38.403136] c7 1827 [<ffffff9008377db8>] d_splice_alias+0x58/0x348 [ 38.403149] c7 1827 [<ffffff900858d16c>] f2fs_lookup+0x608/0x774 [ 38.403163] c7 1827 [<ffffff900835eacc>] lookup_slow+0x1e0/0x2cc [ 38.403177] c7 1827 [<ffffff9008367fe0>] walk_component+0x160/0x520 [ 38.403190] c7 1827 [<ffffff9008369ef4>] path_lookupat+0x110/0x2b4 [ 38.403203] c7 1827 [<ffffff900835dd38>] filename_lookup+0x1d8/0x3a8 [ 38.403216] c7 1827 [<ffffff900835eeb0>] user_path_at_empty+0x54/0x68 [ 38.403229] c7 1827 [<ffffff9008395f44>] SyS_getxattr+0xb4/0x18c [ 38.403241] c7 1827 [<ffffff9008084200>] el0_svc_naked+0x34/0x38 Signed-off-by: Randall Huang <huangrandall@google.com> [Jaegeuk Kim: Fix wrong ending boundary] Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-11 08:26:46 +00:00
/* read from inline xattr */
if (inline_size) {
err = read_inline_xattr(inode, ipage, txattr_addr);
if (err)
goto out;
f2fs: support flexible inline xattr size Now, in product, more and more features based on file encryption were introduced, their demand of xattr space is increasing, however, inline xattr has fixed-size of 200 bytes, once inline xattr space is full, new increased xattr data would occupy additional xattr block which may bring us more space usage and performance regression during persisting. In order to resolve above issue, it's better to expand inline xattr size flexibly according to user's requirement. So this patch introduces new filesystem feature 'flexible inline xattr', and new mount option 'inline_xattr_size=%u', once mkfs enables the feature, we can use the option to make f2fs supporting flexible inline xattr size. To support this feature, we add extra attribute i_inline_xattr_size in inode layout, indicating that how many space inline xattr borrows from block address mapping space in inode layout, by this, we can easily locate and store flexible-sized inline xattr data in inode. Inode disk layout: +----------------------+ | .i_mode | | ... | | .i_ext | +----------------------+ | .i_extra_isize | | .i_inline_xattr_size |-----------+ | ... | | +----------------------+ | | .i_addr | | | - block address or | | | - inline data | | +----------------------+<---+ v | inline xattr | +---inline xattr range +----------------------+<---+ | .i_nid | +----------------------+ | node_footer | | (nid, ino, offset) | +----------------------+ Note that, we have to cnosider backward compatibility which reserved inline_data space, 200 bytes, all the time, reported by Sheng Yong. Previous inline data or directory always reserved 200 bytes in inode layout, even if inline_xattr is disabled. In order to keep inline_dentry's structure for backward compatibility, we get the space back only from inline_data. Signed-off-by: Chao Yu <yuchao0@huawei.com> Reported-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-09-06 13:59:50 +00:00
*xe = __find_inline_xattr(inode, txattr_addr, &last_addr,
index, len, name);
if (*xe) {
*base_size = inline_size;
goto check;
}
}
/* read from xattr node block */
if (xnid) {
err = read_xattr_block(inode, txattr_addr);
if (err)
goto out;
}
if (last_addr)
cur_addr = XATTR_HDR(last_addr) - 1;
else
cur_addr = txattr_addr;
*xe = __find_xattr(cur_addr, last_txattr_addr, NULL, index, len, name);
f2fs: fix to avoid accessing xattr across the boundary When we traverse xattr entries via __find_xattr(), if the raw filesystem content is faked or any hardware failure occurs, out-of-bound error can be detected by KASAN. Fix the issue by introducing boundary check. [ 38.402878] c7 1827 BUG: KASAN: slab-out-of-bounds in f2fs_getxattr+0x518/0x68c [ 38.402891] c7 1827 Read of size 4 at addr ffffffc0b6fb35dc by task [ 38.402935] c7 1827 Call trace: [ 38.402952] c7 1827 [<ffffff900809003c>] dump_backtrace+0x0/0x6bc [ 38.402966] c7 1827 [<ffffff9008090030>] show_stack+0x20/0x2c [ 38.402981] c7 1827 [<ffffff900871ab10>] dump_stack+0xfc/0x140 [ 38.402995] c7 1827 [<ffffff9008325c40>] print_address_description+0x80/0x2d8 [ 38.403009] c7 1827 [<ffffff900832629c>] kasan_report_error+0x198/0x1fc [ 38.403022] c7 1827 [<ffffff9008326104>] kasan_report_error+0x0/0x1fc [ 38.403037] c7 1827 [<ffffff9008325000>] __asan_load4+0x1b0/0x1b8 [ 38.403051] c7 1827 [<ffffff90085fcc44>] f2fs_getxattr+0x518/0x68c [ 38.403066] c7 1827 [<ffffff90085fc508>] f2fs_xattr_generic_get+0xb0/0xd0 [ 38.403080] c7 1827 [<ffffff9008395708>] __vfs_getxattr+0x1f4/0x1fc [ 38.403096] c7 1827 [<ffffff9008621bd0>] inode_doinit_with_dentry+0x360/0x938 [ 38.403109] c7 1827 [<ffffff900862d6cc>] selinux_d_instantiate+0x2c/0x38 [ 38.403123] c7 1827 [<ffffff900861b018>] security_d_instantiate+0x68/0x98 [ 38.403136] c7 1827 [<ffffff9008377db8>] d_splice_alias+0x58/0x348 [ 38.403149] c7 1827 [<ffffff900858d16c>] f2fs_lookup+0x608/0x774 [ 38.403163] c7 1827 [<ffffff900835eacc>] lookup_slow+0x1e0/0x2cc [ 38.403177] c7 1827 [<ffffff9008367fe0>] walk_component+0x160/0x520 [ 38.403190] c7 1827 [<ffffff9008369ef4>] path_lookupat+0x110/0x2b4 [ 38.403203] c7 1827 [<ffffff900835dd38>] filename_lookup+0x1d8/0x3a8 [ 38.403216] c7 1827 [<ffffff900835eeb0>] user_path_at_empty+0x54/0x68 [ 38.403229] c7 1827 [<ffffff9008395f44>] SyS_getxattr+0xb4/0x18c [ 38.403241] c7 1827 [<ffffff9008084200>] el0_svc_naked+0x34/0x38 Signed-off-by: Randall Huang <huangrandall@google.com> [Jaegeuk Kim: Fix wrong ending boundary] Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-11 08:26:46 +00:00
if (!*xe) {
f2fs_err(F2FS_I_SB(inode), "lookup inode (%lu) has corrupted xattr",
inode->i_ino);
set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
err = -ENODATA;
f2fs_handle_error(F2FS_I_SB(inode),
ERROR_CORRUPTED_XATTR);
f2fs: fix to avoid accessing xattr across the boundary When we traverse xattr entries via __find_xattr(), if the raw filesystem content is faked or any hardware failure occurs, out-of-bound error can be detected by KASAN. Fix the issue by introducing boundary check. [ 38.402878] c7 1827 BUG: KASAN: slab-out-of-bounds in f2fs_getxattr+0x518/0x68c [ 38.402891] c7 1827 Read of size 4 at addr ffffffc0b6fb35dc by task [ 38.402935] c7 1827 Call trace: [ 38.402952] c7 1827 [<ffffff900809003c>] dump_backtrace+0x0/0x6bc [ 38.402966] c7 1827 [<ffffff9008090030>] show_stack+0x20/0x2c [ 38.402981] c7 1827 [<ffffff900871ab10>] dump_stack+0xfc/0x140 [ 38.402995] c7 1827 [<ffffff9008325c40>] print_address_description+0x80/0x2d8 [ 38.403009] c7 1827 [<ffffff900832629c>] kasan_report_error+0x198/0x1fc [ 38.403022] c7 1827 [<ffffff9008326104>] kasan_report_error+0x0/0x1fc [ 38.403037] c7 1827 [<ffffff9008325000>] __asan_load4+0x1b0/0x1b8 [ 38.403051] c7 1827 [<ffffff90085fcc44>] f2fs_getxattr+0x518/0x68c [ 38.403066] c7 1827 [<ffffff90085fc508>] f2fs_xattr_generic_get+0xb0/0xd0 [ 38.403080] c7 1827 [<ffffff9008395708>] __vfs_getxattr+0x1f4/0x1fc [ 38.403096] c7 1827 [<ffffff9008621bd0>] inode_doinit_with_dentry+0x360/0x938 [ 38.403109] c7 1827 [<ffffff900862d6cc>] selinux_d_instantiate+0x2c/0x38 [ 38.403123] c7 1827 [<ffffff900861b018>] security_d_instantiate+0x68/0x98 [ 38.403136] c7 1827 [<ffffff9008377db8>] d_splice_alias+0x58/0x348 [ 38.403149] c7 1827 [<ffffff900858d16c>] f2fs_lookup+0x608/0x774 [ 38.403163] c7 1827 [<ffffff900835eacc>] lookup_slow+0x1e0/0x2cc [ 38.403177] c7 1827 [<ffffff9008367fe0>] walk_component+0x160/0x520 [ 38.403190] c7 1827 [<ffffff9008369ef4>] path_lookupat+0x110/0x2b4 [ 38.403203] c7 1827 [<ffffff900835dd38>] filename_lookup+0x1d8/0x3a8 [ 38.403216] c7 1827 [<ffffff900835eeb0>] user_path_at_empty+0x54/0x68 [ 38.403229] c7 1827 [<ffffff9008395f44>] SyS_getxattr+0xb4/0x18c [ 38.403241] c7 1827 [<ffffff9008084200>] el0_svc_naked+0x34/0x38 Signed-off-by: Randall Huang <huangrandall@google.com> [Jaegeuk Kim: Fix wrong ending boundary] Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-11 08:26:46 +00:00
goto out;
}
check:
if (IS_XATTR_LAST_ENTRY(*xe)) {
err = -ENODATA;
goto out;
}
*base_addr = txattr_addr;
return 0;
out:
xattr_free(F2FS_I_SB(inode), txattr_addr, *is_inline);
return err;
}
static int read_all_xattrs(struct inode *inode, struct page *ipage,
void **base_addr)
{
struct f2fs_xattr_header *header;
nid_t xnid = F2FS_I(inode)->i_xattr_nid;
unsigned int size = VALID_XATTR_BLOCK_SIZE;
unsigned int inline_size = inline_xattr_size(inode);
void *txattr_addr;
int err;
txattr_addr = f2fs_kzalloc(F2FS_I_SB(inode),
inline_size + size + XATTR_PADDING_SIZE, GFP_NOFS);
if (!txattr_addr)
return -ENOMEM;
/* read from inline xattr */
if (inline_size) {
err = read_inline_xattr(inode, ipage, txattr_addr);
if (err)
goto fail;
}
/* read from xattr node block */
if (xnid) {
err = read_xattr_block(inode, txattr_addr);
if (err)
goto fail;
}
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:
kfree(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 = inline_xattr_size(inode);
struct page *in_page = NULL;
void *xattr_addr;
void *inline_addr = NULL;
struct page *xpage;
nid_t new_nid = 0;
int err = 0;
if (hsize > inline_size && !F2FS_I(inode)->i_xattr_nid)
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
if (!f2fs_alloc_nid(sbi, &new_nid))
return -ENOSPC;
/* write to inline xattr */
if (inline_size) {
if (ipage) {
f2fs: support flexible inline xattr size Now, in product, more and more features based on file encryption were introduced, their demand of xattr space is increasing, however, inline xattr has fixed-size of 200 bytes, once inline xattr space is full, new increased xattr data would occupy additional xattr block which may bring us more space usage and performance regression during persisting. In order to resolve above issue, it's better to expand inline xattr size flexibly according to user's requirement. So this patch introduces new filesystem feature 'flexible inline xattr', and new mount option 'inline_xattr_size=%u', once mkfs enables the feature, we can use the option to make f2fs supporting flexible inline xattr size. To support this feature, we add extra attribute i_inline_xattr_size in inode layout, indicating that how many space inline xattr borrows from block address mapping space in inode layout, by this, we can easily locate and store flexible-sized inline xattr data in inode. Inode disk layout: +----------------------+ | .i_mode | | ... | | .i_ext | +----------------------+ | .i_extra_isize | | .i_inline_xattr_size |-----------+ | ... | | +----------------------+ | | .i_addr | | | - block address or | | | - inline data | | +----------------------+<---+ v | inline xattr | +---inline xattr range +----------------------+<---+ | .i_nid | +----------------------+ | node_footer | | (nid, ino, offset) | +----------------------+ Note that, we have to cnosider backward compatibility which reserved inline_data space, 200 bytes, all the time, reported by Sheng Yong. Previous inline data or directory always reserved 200 bytes in inode layout, even if inline_xattr is disabled. In order to keep inline_dentry's structure for backward compatibility, we get the space back only from inline_data. Signed-off-by: Chao Yu <yuchao0@huawei.com> Reported-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-09-06 13:59:50 +00:00
inline_addr = inline_xattr_addr(inode, ipage);
} else {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
in_page = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(in_page)) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
f2fs_alloc_nid_failed(sbi, new_nid);
return PTR_ERR(in_page);
}
inline_addr = inline_xattr_addr(inode, in_page);
}
f2fs_wait_on_page_writeback(ipage ? ipage : in_page,
NODE, true, true);
/* no need to use xattr node block */
if (hsize <= inline_size) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_truncate_xattr_node(inode);
f2fs_alloc_nid_failed(sbi, new_nid);
if (err) {
f2fs_put_page(in_page, 1);
return err;
}
memcpy(inline_addr, txattr_addr, inline_size);
set_page_dirty(ipage ? ipage : in_page);
goto in_page_out;
}
}
/* write to xattr node block */
if (F2FS_I(inode)->i_xattr_nid) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
xpage = f2fs_get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
if (IS_ERR(xpage)) {
err = PTR_ERR(xpage);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
f2fs_alloc_nid_failed(sbi, new_nid);
goto in_page_out;
}
f2fs_bug_on(sbi, new_nid);
f2fs_wait_on_page_writeback(xpage, NODE, true, true);
} else {
struct dnode_of_data dn;
set_new_dnode(&dn, inode, NULL, NULL, new_nid);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
xpage = f2fs_new_node_page(&dn, XATTR_NODE_OFFSET);
if (IS_ERR(xpage)) {
err = PTR_ERR(xpage);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
f2fs_alloc_nid_failed(sbi, new_nid);
goto in_page_out;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
f2fs_alloc_nid_done(sbi, new_nid);
}
xattr_addr = page_address(xpage);
if (inline_size)
memcpy(inline_addr, txattr_addr, inline_size);
memcpy(xattr_addr, txattr_addr + inline_size, VALID_XATTR_BLOCK_SIZE);
if (inline_size)
set_page_dirty(ipage ? ipage : in_page);
set_page_dirty(xpage);
f2fs_put_page(xpage, 1);
in_page_out:
f2fs_put_page(in_page, 1);
return err;
}
int f2fs_getxattr(struct inode *inode, int index, const char *name,
f2fs: avoid deadlock on init_inode_metadata Previously, init_inode_metadata does not hold any parent directory's inode page. So, f2fs_init_acl can grab its parent inode page without any problem. But, when we use inline_dentry, that page is grabbed during f2fs_add_link, so that we can fall into deadlock condition like below. INFO: task mknod:11006 blocked for more than 120 seconds. Tainted: G OE 3.17.0-rc1+ #13 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. mknod D ffff88003fc94580 0 11006 11004 0x00000000 ffff880007717b10 0000000000000002 ffff88003c323220 ffff880007717fd8 0000000000014580 0000000000014580 ffff88003daecb30 ffff88003c323220 ffff88003fc94e80 ffff88003ffbb4e8 ffff880007717ba0 0000000000000002 Call Trace: [<ffffffff8173dc40>] ? bit_wait+0x50/0x50 [<ffffffff8173d4cd>] io_schedule+0x9d/0x130 [<ffffffff8173dc6c>] bit_wait_io+0x2c/0x50 [<ffffffff8173da3b>] __wait_on_bit_lock+0x4b/0xb0 [<ffffffff811640a7>] __lock_page+0x67/0x70 [<ffffffff810acf50>] ? autoremove_wake_function+0x40/0x40 [<ffffffff811652cc>] pagecache_get_page+0x14c/0x1e0 [<ffffffffa029afa9>] get_node_page+0x59/0x130 [f2fs] [<ffffffffa02a63ad>] read_all_xattrs+0x24d/0x430 [f2fs] [<ffffffffa02a6ca2>] f2fs_getxattr+0x52/0xe0 [f2fs] [<ffffffffa02a7481>] f2fs_get_acl+0x41/0x2d0 [f2fs] [<ffffffff8122d847>] get_acl+0x47/0x70 [<ffffffff8122db5a>] posix_acl_create+0x5a/0x150 [<ffffffffa02a7759>] f2fs_init_acl+0x29/0xcb [f2fs] [<ffffffffa0286a8d>] init_inode_metadata+0x5d/0x340 [f2fs] [<ffffffffa029253a>] f2fs_add_inline_entry+0x12a/0x2e0 [f2fs] [<ffffffffa0286ea5>] __f2fs_add_link+0x45/0x4a0 [f2fs] [<ffffffffa028b5b6>] ? f2fs_new_inode+0x146/0x220 [f2fs] [<ffffffffa028b816>] f2fs_mknod+0x86/0xf0 [f2fs] [<ffffffff811e3ec1>] vfs_mknod+0xe1/0x160 [<ffffffff811e4b26>] SyS_mknod+0x1f6/0x200 [<ffffffff81741d7f>] tracesys+0xe1/0xe6 Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-10-14 02:42:53 +00:00
void *buffer, size_t buffer_size, struct page *ipage)
{
struct f2fs_xattr_entry *entry = NULL;
int error;
unsigned int size, len;
void *base_addr = NULL;
int base_size;
bool is_inline;
if (name == NULL)
return -EINVAL;
len = strlen(name);
if (len > F2FS_NAME_LEN)
return -ERANGE;
if (!ipage)
f2fs_down_read(&F2FS_I(inode)->i_xattr_sem);
error = lookup_all_xattrs(inode, ipage, index, len, name,
&entry, &base_addr, &base_size, &is_inline);
if (!ipage)
f2fs_up_read(&F2FS_I(inode)->i_xattr_sem);
if (error)
return error;
size = le16_to_cpu(entry->e_value_size);
if (buffer && size > buffer_size) {
error = -ERANGE;
goto out;
}
if (buffer) {
char *pval = entry->e_name + entry->e_name_len;
if (base_size - (pval - (char *)base_addr) < size) {
error = -ERANGE;
goto out;
}
memcpy(buffer, pval, size);
}
error = size;
out:
xattr_free(F2FS_I_SB(inode), base_addr, is_inline);
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, *last_base_addr;
int error;
size_t rest = buffer_size;
f2fs_down_read(&F2FS_I(inode)->i_xattr_sem);
error = read_all_xattrs(inode, NULL, &base_addr);
f2fs_up_read(&F2FS_I(inode)->i_xattr_sem);
if (error)
return error;
last_base_addr = (void *)base_addr + XATTR_SIZE(inode);
list_for_each_xattr(entry, base_addr) {
const char *prefix;
size_t prefix_len;
size_t size;
prefix = f2fs_xattr_prefix(entry->e_name_index, dentry);
if ((void *)(entry) + sizeof(__u32) > last_base_addr ||
(void *)XATTR_NEXT_ENTRY(entry) > last_base_addr) {
f2fs_err(F2FS_I_SB(inode), "list inode (%lu) has corrupted xattr",
inode->i_ino);
set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
f2fs_handle_error(F2FS_I_SB(inode),
ERROR_CORRUPTED_XATTR);
break;
}
if (!prefix)
continue;
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:
kfree(base_addr);
return error;
}
static bool f2fs_xattr_value_same(struct f2fs_xattr_entry *entry,
const void *value, size_t size)
{
void *pval = entry->e_name + entry->e_name_len;
return (le16_to_cpu(entry->e_value_size) == size) &&
!memcmp(pval, value, size);
}
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_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_xattr_entry *here, *last;
f2fs: fix to avoid accessing xattr across the boundary When we traverse xattr entries via __find_xattr(), if the raw filesystem content is faked or any hardware failure occurs, out-of-bound error can be detected by KASAN. Fix the issue by introducing boundary check. [ 38.402878] c7 1827 BUG: KASAN: slab-out-of-bounds in f2fs_getxattr+0x518/0x68c [ 38.402891] c7 1827 Read of size 4 at addr ffffffc0b6fb35dc by task [ 38.402935] c7 1827 Call trace: [ 38.402952] c7 1827 [<ffffff900809003c>] dump_backtrace+0x0/0x6bc [ 38.402966] c7 1827 [<ffffff9008090030>] show_stack+0x20/0x2c [ 38.402981] c7 1827 [<ffffff900871ab10>] dump_stack+0xfc/0x140 [ 38.402995] c7 1827 [<ffffff9008325c40>] print_address_description+0x80/0x2d8 [ 38.403009] c7 1827 [<ffffff900832629c>] kasan_report_error+0x198/0x1fc [ 38.403022] c7 1827 [<ffffff9008326104>] kasan_report_error+0x0/0x1fc [ 38.403037] c7 1827 [<ffffff9008325000>] __asan_load4+0x1b0/0x1b8 [ 38.403051] c7 1827 [<ffffff90085fcc44>] f2fs_getxattr+0x518/0x68c [ 38.403066] c7 1827 [<ffffff90085fc508>] f2fs_xattr_generic_get+0xb0/0xd0 [ 38.403080] c7 1827 [<ffffff9008395708>] __vfs_getxattr+0x1f4/0x1fc [ 38.403096] c7 1827 [<ffffff9008621bd0>] inode_doinit_with_dentry+0x360/0x938 [ 38.403109] c7 1827 [<ffffff900862d6cc>] selinux_d_instantiate+0x2c/0x38 [ 38.403123] c7 1827 [<ffffff900861b018>] security_d_instantiate+0x68/0x98 [ 38.403136] c7 1827 [<ffffff9008377db8>] d_splice_alias+0x58/0x348 [ 38.403149] c7 1827 [<ffffff900858d16c>] f2fs_lookup+0x608/0x774 [ 38.403163] c7 1827 [<ffffff900835eacc>] lookup_slow+0x1e0/0x2cc [ 38.403177] c7 1827 [<ffffff9008367fe0>] walk_component+0x160/0x520 [ 38.403190] c7 1827 [<ffffff9008369ef4>] path_lookupat+0x110/0x2b4 [ 38.403203] c7 1827 [<ffffff900835dd38>] filename_lookup+0x1d8/0x3a8 [ 38.403216] c7 1827 [<ffffff900835eeb0>] user_path_at_empty+0x54/0x68 [ 38.403229] c7 1827 [<ffffff9008395f44>] SyS_getxattr+0xb4/0x18c [ 38.403241] c7 1827 [<ffffff9008084200>] el0_svc_naked+0x34/0x38 Signed-off-by: Randall Huang <huangrandall@google.com> [Jaegeuk Kim: Fix wrong ending boundary] Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-11 08:26:46 +00:00
void *base_addr, *last_base_addr;
int found, newsize;
size_t len;
__u32 new_hsize;
int error;
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;
retry:
error = read_all_xattrs(inode, ipage, &base_addr);
if (error)
return error;
last_base_addr = (void *)base_addr + XATTR_SIZE(inode);
f2fs: fix to avoid accessing xattr across the boundary When we traverse xattr entries via __find_xattr(), if the raw filesystem content is faked or any hardware failure occurs, out-of-bound error can be detected by KASAN. Fix the issue by introducing boundary check. [ 38.402878] c7 1827 BUG: KASAN: slab-out-of-bounds in f2fs_getxattr+0x518/0x68c [ 38.402891] c7 1827 Read of size 4 at addr ffffffc0b6fb35dc by task [ 38.402935] c7 1827 Call trace: [ 38.402952] c7 1827 [<ffffff900809003c>] dump_backtrace+0x0/0x6bc [ 38.402966] c7 1827 [<ffffff9008090030>] show_stack+0x20/0x2c [ 38.402981] c7 1827 [<ffffff900871ab10>] dump_stack+0xfc/0x140 [ 38.402995] c7 1827 [<ffffff9008325c40>] print_address_description+0x80/0x2d8 [ 38.403009] c7 1827 [<ffffff900832629c>] kasan_report_error+0x198/0x1fc [ 38.403022] c7 1827 [<ffffff9008326104>] kasan_report_error+0x0/0x1fc [ 38.403037] c7 1827 [<ffffff9008325000>] __asan_load4+0x1b0/0x1b8 [ 38.403051] c7 1827 [<ffffff90085fcc44>] f2fs_getxattr+0x518/0x68c [ 38.403066] c7 1827 [<ffffff90085fc508>] f2fs_xattr_generic_get+0xb0/0xd0 [ 38.403080] c7 1827 [<ffffff9008395708>] __vfs_getxattr+0x1f4/0x1fc [ 38.403096] c7 1827 [<ffffff9008621bd0>] inode_doinit_with_dentry+0x360/0x938 [ 38.403109] c7 1827 [<ffffff900862d6cc>] selinux_d_instantiate+0x2c/0x38 [ 38.403123] c7 1827 [<ffffff900861b018>] security_d_instantiate+0x68/0x98 [ 38.403136] c7 1827 [<ffffff9008377db8>] d_splice_alias+0x58/0x348 [ 38.403149] c7 1827 [<ffffff900858d16c>] f2fs_lookup+0x608/0x774 [ 38.403163] c7 1827 [<ffffff900835eacc>] lookup_slow+0x1e0/0x2cc [ 38.403177] c7 1827 [<ffffff9008367fe0>] walk_component+0x160/0x520 [ 38.403190] c7 1827 [<ffffff9008369ef4>] path_lookupat+0x110/0x2b4 [ 38.403203] c7 1827 [<ffffff900835dd38>] filename_lookup+0x1d8/0x3a8 [ 38.403216] c7 1827 [<ffffff900835eeb0>] user_path_at_empty+0x54/0x68 [ 38.403229] c7 1827 [<ffffff9008395f44>] SyS_getxattr+0xb4/0x18c [ 38.403241] c7 1827 [<ffffff9008084200>] el0_svc_naked+0x34/0x38 Signed-off-by: Randall Huang <huangrandall@google.com> [Jaegeuk Kim: Fix wrong ending boundary] Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-11 08:26:46 +00:00
/* find entry with wanted name. */
here = __find_xattr(base_addr, last_base_addr, NULL, index, len, name);
f2fs: fix to avoid accessing xattr across the boundary When we traverse xattr entries via __find_xattr(), if the raw filesystem content is faked or any hardware failure occurs, out-of-bound error can be detected by KASAN. Fix the issue by introducing boundary check. [ 38.402878] c7 1827 BUG: KASAN: slab-out-of-bounds in f2fs_getxattr+0x518/0x68c [ 38.402891] c7 1827 Read of size 4 at addr ffffffc0b6fb35dc by task [ 38.402935] c7 1827 Call trace: [ 38.402952] c7 1827 [<ffffff900809003c>] dump_backtrace+0x0/0x6bc [ 38.402966] c7 1827 [<ffffff9008090030>] show_stack+0x20/0x2c [ 38.402981] c7 1827 [<ffffff900871ab10>] dump_stack+0xfc/0x140 [ 38.402995] c7 1827 [<ffffff9008325c40>] print_address_description+0x80/0x2d8 [ 38.403009] c7 1827 [<ffffff900832629c>] kasan_report_error+0x198/0x1fc [ 38.403022] c7 1827 [<ffffff9008326104>] kasan_report_error+0x0/0x1fc [ 38.403037] c7 1827 [<ffffff9008325000>] __asan_load4+0x1b0/0x1b8 [ 38.403051] c7 1827 [<ffffff90085fcc44>] f2fs_getxattr+0x518/0x68c [ 38.403066] c7 1827 [<ffffff90085fc508>] f2fs_xattr_generic_get+0xb0/0xd0 [ 38.403080] c7 1827 [<ffffff9008395708>] __vfs_getxattr+0x1f4/0x1fc [ 38.403096] c7 1827 [<ffffff9008621bd0>] inode_doinit_with_dentry+0x360/0x938 [ 38.403109] c7 1827 [<ffffff900862d6cc>] selinux_d_instantiate+0x2c/0x38 [ 38.403123] c7 1827 [<ffffff900861b018>] security_d_instantiate+0x68/0x98 [ 38.403136] c7 1827 [<ffffff9008377db8>] d_splice_alias+0x58/0x348 [ 38.403149] c7 1827 [<ffffff900858d16c>] f2fs_lookup+0x608/0x774 [ 38.403163] c7 1827 [<ffffff900835eacc>] lookup_slow+0x1e0/0x2cc [ 38.403177] c7 1827 [<ffffff9008367fe0>] walk_component+0x160/0x520 [ 38.403190] c7 1827 [<ffffff9008369ef4>] path_lookupat+0x110/0x2b4 [ 38.403203] c7 1827 [<ffffff900835dd38>] filename_lookup+0x1d8/0x3a8 [ 38.403216] c7 1827 [<ffffff900835eeb0>] user_path_at_empty+0x54/0x68 [ 38.403229] c7 1827 [<ffffff9008395f44>] SyS_getxattr+0xb4/0x18c [ 38.403241] c7 1827 [<ffffff9008084200>] el0_svc_naked+0x34/0x38 Signed-off-by: Randall Huang <huangrandall@google.com> [Jaegeuk Kim: Fix wrong ending boundary] Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-11 08:26:46 +00:00
if (!here) {
if (!F2FS_I(inode)->i_xattr_nid) {
error = f2fs_recover_xattr_data(inode, NULL);
f2fs_notice(F2FS_I_SB(inode),
"recover xattr in inode (%lu), error(%d)",
inode->i_ino, error);
if (!error) {
kfree(base_addr);
goto retry;
}
}
f2fs_err(F2FS_I_SB(inode), "set inode (%lu) has corrupted xattr",
inode->i_ino);
set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
error = -EFSCORRUPTED;
f2fs_handle_error(F2FS_I_SB(inode),
ERROR_CORRUPTED_XATTR);
f2fs: fix to avoid accessing xattr across the boundary When we traverse xattr entries via __find_xattr(), if the raw filesystem content is faked or any hardware failure occurs, out-of-bound error can be detected by KASAN. Fix the issue by introducing boundary check. [ 38.402878] c7 1827 BUG: KASAN: slab-out-of-bounds in f2fs_getxattr+0x518/0x68c [ 38.402891] c7 1827 Read of size 4 at addr ffffffc0b6fb35dc by task [ 38.402935] c7 1827 Call trace: [ 38.402952] c7 1827 [<ffffff900809003c>] dump_backtrace+0x0/0x6bc [ 38.402966] c7 1827 [<ffffff9008090030>] show_stack+0x20/0x2c [ 38.402981] c7 1827 [<ffffff900871ab10>] dump_stack+0xfc/0x140 [ 38.402995] c7 1827 [<ffffff9008325c40>] print_address_description+0x80/0x2d8 [ 38.403009] c7 1827 [<ffffff900832629c>] kasan_report_error+0x198/0x1fc [ 38.403022] c7 1827 [<ffffff9008326104>] kasan_report_error+0x0/0x1fc [ 38.403037] c7 1827 [<ffffff9008325000>] __asan_load4+0x1b0/0x1b8 [ 38.403051] c7 1827 [<ffffff90085fcc44>] f2fs_getxattr+0x518/0x68c [ 38.403066] c7 1827 [<ffffff90085fc508>] f2fs_xattr_generic_get+0xb0/0xd0 [ 38.403080] c7 1827 [<ffffff9008395708>] __vfs_getxattr+0x1f4/0x1fc [ 38.403096] c7 1827 [<ffffff9008621bd0>] inode_doinit_with_dentry+0x360/0x938 [ 38.403109] c7 1827 [<ffffff900862d6cc>] selinux_d_instantiate+0x2c/0x38 [ 38.403123] c7 1827 [<ffffff900861b018>] security_d_instantiate+0x68/0x98 [ 38.403136] c7 1827 [<ffffff9008377db8>] d_splice_alias+0x58/0x348 [ 38.403149] c7 1827 [<ffffff900858d16c>] f2fs_lookup+0x608/0x774 [ 38.403163] c7 1827 [<ffffff900835eacc>] lookup_slow+0x1e0/0x2cc [ 38.403177] c7 1827 [<ffffff9008367fe0>] walk_component+0x160/0x520 [ 38.403190] c7 1827 [<ffffff9008369ef4>] path_lookupat+0x110/0x2b4 [ 38.403203] c7 1827 [<ffffff900835dd38>] filename_lookup+0x1d8/0x3a8 [ 38.403216] c7 1827 [<ffffff900835eeb0>] user_path_at_empty+0x54/0x68 [ 38.403229] c7 1827 [<ffffff9008395f44>] SyS_getxattr+0xb4/0x18c [ 38.403241] c7 1827 [<ffffff9008084200>] el0_svc_naked+0x34/0x38 Signed-off-by: Randall Huang <huangrandall@google.com> [Jaegeuk Kim: Fix wrong ending boundary] Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-11 08:26:46 +00:00
goto exit;
}
found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1;
if (found) {
if ((flags & XATTR_CREATE)) {
error = -EEXIST;
goto exit;
}
if (value && f2fs_xattr_value_same(here, value, size))
goto same;
} else if ((flags & XATTR_REPLACE)) {
error = -ENODATA;
goto exit;
}
last = here;
f2fs: fix to do sanity check on last xattr entry in __f2fs_setxattr() As Wenqing Liu reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=215235 - Overview page fault in f2fs_setxattr() when mount and operate on corrupted image - Reproduce tested on kernel 5.16-rc3, 5.15.X under root 1. unzip tmp7.zip 2. ./single.sh f2fs 7 Sometimes need to run the script several times - Kernel dump loop0: detected capacity change from 0 to 131072 F2FS-fs (loop0): Found nat_bits in checkpoint F2FS-fs (loop0): Mounted with checkpoint version = 7548c2ee BUG: unable to handle page fault for address: ffffe47bc7123f48 RIP: 0010:kfree+0x66/0x320 Call Trace: __f2fs_setxattr+0x2aa/0xc00 [f2fs] f2fs_setxattr+0xfa/0x480 [f2fs] __f2fs_set_acl+0x19b/0x330 [f2fs] __vfs_removexattr+0x52/0x70 __vfs_removexattr_locked+0xb1/0x140 vfs_removexattr+0x56/0x100 removexattr+0x57/0x80 path_removexattr+0xa3/0xc0 __x64_sys_removexattr+0x17/0x20 do_syscall_64+0x37/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xae The root cause is in __f2fs_setxattr(), we missed to do sanity check on last xattr entry, result in out-of-bound memory access during updating inconsistent xattr data of target inode. After the fix, it can detect such xattr inconsistency as below: F2FS-fs (loop11): inode (7) has invalid last xattr entry, entry_size: 60676 F2FS-fs (loop11): inode (8) has corrupted xattr F2FS-fs (loop11): inode (8) has corrupted xattr F2FS-fs (loop11): inode (8) has invalid last xattr entry, entry_size: 47736 Cc: stable@vger.kernel.org Reported-by: Wenqing Liu <wenqingliu0120@gmail.com> Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-12-12 09:16:30 +00:00
while (!IS_XATTR_LAST_ENTRY(last)) {
if ((void *)(last) + sizeof(__u32) > last_base_addr ||
(void *)XATTR_NEXT_ENTRY(last) > last_base_addr) {
f2fs_err(F2FS_I_SB(inode), "inode (%lu) has invalid last xattr entry, entry_size: %zu",
inode->i_ino, ENTRY_SIZE(last));
set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
error = -EFSCORRUPTED;
f2fs_handle_error(F2FS_I_SB(inode),
ERROR_CORRUPTED_XATTR);
f2fs: fix to do sanity check on last xattr entry in __f2fs_setxattr() As Wenqing Liu reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=215235 - Overview page fault in f2fs_setxattr() when mount and operate on corrupted image - Reproduce tested on kernel 5.16-rc3, 5.15.X under root 1. unzip tmp7.zip 2. ./single.sh f2fs 7 Sometimes need to run the script several times - Kernel dump loop0: detected capacity change from 0 to 131072 F2FS-fs (loop0): Found nat_bits in checkpoint F2FS-fs (loop0): Mounted with checkpoint version = 7548c2ee BUG: unable to handle page fault for address: ffffe47bc7123f48 RIP: 0010:kfree+0x66/0x320 Call Trace: __f2fs_setxattr+0x2aa/0xc00 [f2fs] f2fs_setxattr+0xfa/0x480 [f2fs] __f2fs_set_acl+0x19b/0x330 [f2fs] __vfs_removexattr+0x52/0x70 __vfs_removexattr_locked+0xb1/0x140 vfs_removexattr+0x56/0x100 removexattr+0x57/0x80 path_removexattr+0xa3/0xc0 __x64_sys_removexattr+0x17/0x20 do_syscall_64+0x37/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xae The root cause is in __f2fs_setxattr(), we missed to do sanity check on last xattr entry, result in out-of-bound memory access during updating inconsistent xattr data of target inode. After the fix, it can detect such xattr inconsistency as below: F2FS-fs (loop11): inode (7) has invalid last xattr entry, entry_size: 60676 F2FS-fs (loop11): inode (8) has corrupted xattr F2FS-fs (loop11): inode (8) has corrupted xattr F2FS-fs (loop11): inode (8) has invalid last xattr entry, entry_size: 47736 Cc: stable@vger.kernel.org Reported-by: Wenqing Liu <wenqingliu0120@gmail.com> Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-12-12 09:16:30 +00:00
goto exit;
}
last = XATTR_NEXT_ENTRY(last);
f2fs: fix to do sanity check on last xattr entry in __f2fs_setxattr() As Wenqing Liu reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=215235 - Overview page fault in f2fs_setxattr() when mount and operate on corrupted image - Reproduce tested on kernel 5.16-rc3, 5.15.X under root 1. unzip tmp7.zip 2. ./single.sh f2fs 7 Sometimes need to run the script several times - Kernel dump loop0: detected capacity change from 0 to 131072 F2FS-fs (loop0): Found nat_bits in checkpoint F2FS-fs (loop0): Mounted with checkpoint version = 7548c2ee BUG: unable to handle page fault for address: ffffe47bc7123f48 RIP: 0010:kfree+0x66/0x320 Call Trace: __f2fs_setxattr+0x2aa/0xc00 [f2fs] f2fs_setxattr+0xfa/0x480 [f2fs] __f2fs_set_acl+0x19b/0x330 [f2fs] __vfs_removexattr+0x52/0x70 __vfs_removexattr_locked+0xb1/0x140 vfs_removexattr+0x56/0x100 removexattr+0x57/0x80 path_removexattr+0xa3/0xc0 __x64_sys_removexattr+0x17/0x20 do_syscall_64+0x37/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xae The root cause is in __f2fs_setxattr(), we missed to do sanity check on last xattr entry, result in out-of-bound memory access during updating inconsistent xattr data of target inode. After the fix, it can detect such xattr inconsistency as below: F2FS-fs (loop11): inode (7) has invalid last xattr entry, entry_size: 60676 F2FS-fs (loop11): inode (8) has corrupted xattr F2FS-fs (loop11): inode (8) has corrupted xattr F2FS-fs (loop11): inode (8) has invalid last xattr entry, entry_size: 47736 Cc: stable@vger.kernel.org Reported-by: Wenqing Liu <wenqingliu0120@gmail.com> Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2021-12-12 09:16:30 +00:00
}
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;
/*
* Explicitly add the null terminator. The unused xattr space
* is supposed to always be zeroed, which would make this
* unnecessary, but don't depend on that.
*/
*(u32 *)((u8 *)last + newsize) = 0;
}
error = write_all_xattrs(inode, new_hsize, base_addr, ipage);
if (error)
goto exit;
if (index == F2FS_XATTR_INDEX_ENCRYPTION &&
!strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT))
f2fs_set_encrypted_inode(inode);
if (!S_ISDIR(inode->i_mode))
goto same;
/*
* In restrict mode, fsync() always try to trigger checkpoint for all
* metadata consistency, in other mode, it triggers checkpoint when
* parent's xattr metadata was updated.
*/
if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT)
set_sbi_flag(sbi, SBI_NEED_CP);
else
f2fs_add_ino_entry(sbi, inode->i_ino, XATTR_DIR_INO);
same:
if (is_inode_flag_set(inode, FI_ACL_MODE)) {
inode->i_mode = F2FS_I(inode)->i_acl_mode;
clear_inode_flag(inode, FI_ACL_MODE);
}
f2fs update for 6.6-rc1 In this cycle, we don't have a highlighted feature enhancement, but mostly have fixed issues mainly in two parts: 1) zoned block device, 2) compression support. For zoned block device, we've tried to improve the power-off recovery flow as much as possible. For compression, we found some corner cases caused by wrong compression policy and logics. Other than them, there were some reverts and stat corrections. Bug fix: - use finish zone command when closing a zone - check zone type before sending async reset zone command - fix to assign compress_level for lz4 correctly - fix error path of f2fs_submit_page_read() - don't {,de}compress non-full cluster - send small discard commands during checkpoint back - flush inode if atomic file is aborted - correct to account gc/cp stats And, there are minor bug fixes, avoiding false lockdep warning, and clean-ups. -----BEGIN PGP SIGNATURE----- iQIzBAABCgAdFiEE00UqedjCtOrGVvQiQBSofoJIUNIFAmTyemoACgkQQBSofoJI UNLLKQ//bupYGPOqAgKbd/s7FhtULMiiRmFVy7W2eoMIc/oeeXOGrzDAF/1NifLC WLV4uBNVTS4PS8D1vRzxZNEZt9aqPS0vQ8hxW/3nTI9Z425NX3nz7gLSxxmwIkIe xj++V6tvKPcCH0BfKvfFCtcxj09PsflgdEuT8w/sIkH6p4o+VEMFs1Lc9PQsjUmh epznK7JGBwpAxmHqI74n1eAw2CI6W+oKx23YDTNMBD6hmXTU0fkTeBURrOlSsUHZ nhafPecsrCEI+OpAj03G/7e/zt+iTUKdmHx9O5ir/P00vF/c+SU2vSwB97FiHqBi B4UmocTM0MAsU80PQcmE6aU3zgQFI0Yun5yZ24VeWjKTu76ssZSmT2HA/4RL+LLf AeAW4FSyfh76pls8X5IWfilxGLWq6kTzSZA0MF7dH2q7qlj5apL5wKpm/XH6POqn qELY/Y9+P1QuCcNL8BiYrgA5xBqVJ7Uw/6/6U3Y77PElc+Pwl3vI8UZ7uCOBrsXL e0TLXy23AJA6AS2DyLLziy669nXAZRb95B8TWMfEeVZIMFvCeeqYc74N8jOFa0T8 q6uQFZs+0cETLZA8MSZdlNhzvhJmbW6wgSIz++CEdikWSLBZMKWxBVjCPkkCY9uc DMh8zruSVbYPZWBTcxkMFEBJKKrU43++e7pb8ZoqTj4Pq1317b0= =Qa8+ -----END PGP SIGNATURE----- Merge tag 'f2fs-for-6-6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs Pull f2fs updates from Jaegeuk Kim: "In this cycle, we don't have a highlighted feature enhancement, but mostly have fixed issues mainly in two parts: 1) zoned block device, and 2) compression support. For zoned block device, we've tried to improve the power-off recovery flow as much as possible. For compression, we found some corner cases caused by wrong compression policy and logics. Other than them, there were some reverts and stat corrections. Bug fixes: - use finish zone command when closing a zone - check zone type before sending async reset zone command - fix to assign compress_level for lz4 correctly - fix error path of f2fs_submit_page_read() - don't {,de}compress non-full cluster - send small discard commands during checkpoint back - flush inode if atomic file is aborted - correct to account gc/cp stats And, there are minor bug fixes, avoiding false lockdep warning, and clean-ups" * tag 'f2fs-for-6-6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (25 commits) f2fs: use finish zone command when closing a zone f2fs: compress: fix to assign compress_level for lz4 correctly f2fs: fix error path of f2fs_submit_page_read() f2fs: clean up error handling in sanity_check_{compress_,}inode() f2fs: avoid false alarm of circular locking Revert "f2fs: do not issue small discard commands during checkpoint" f2fs: doc: fix description of max_small_discards f2fs: should update REQ_TIME for direct write f2fs: fix to account cp stats correctly f2fs: fix to account gc stats correctly f2fs: remove unneeded check condition in __f2fs_setxattr() f2fs: fix to update i_ctime in __f2fs_setxattr() Revert "f2fs: fix to do sanity check on extent cache correctly" f2fs: increase usage of folio_next_index() helper f2fs: Only lfs mode is allowed with zoned block device feature f2fs: check zone type before sending async reset zone command f2fs: compress: don't {,de}compress non-full cluster f2fs: allow f2fs_ioc_{,de}compress_file to be interrupted f2fs: don't reopen the main block device in f2fs_scan_devices f2fs: fix to avoid mmap vs set_compress_option case ...
2023-09-02 22:37:59 +00:00
inode_set_ctime_current(inode);
f2fs_mark_inode_dirty_sync(inode, true);
exit:
kfree(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;
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
if (!f2fs_is_checkpoint_ready(sbi))
return -ENOSPC;
err = f2fs_dquot_initialize(inode);
if (err)
return err;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
/* this case is only from f2fs_init_inode_metadata */
if (ipage)
return __f2fs_setxattr(inode, index, name, value,
size, ipage, flags);
f2fs_balance_fs(sbi, true);
f2fs: use rw_sem instead of fs_lock(locks mutex) The fs_locks is used to block other ops(ex, recovery) when doing checkpoint. And each other operate routine(besides checkpoint) needs to acquire a fs_lock, there is a terrible problem here, if these are too many concurrency threads acquiring fs_lock, so that they will block each other and may lead to some performance problem, but this is not the phenomenon we want to see. Though there are some optimization patches introduced to enhance the usage of fs_lock, but the thorough solution is using a *rw_sem* to replace the fs_lock. Checkpoint routine takes write_sem, and other ops take read_sem, so that we can block other ops(ex, recovery) when doing checkpoint, and other ops will not disturb each other, this can avoid the problem described above completely. Because of the weakness of rw_sem, the above change may introduce a potential problem that the checkpoint thread might get starved if other threads are intensively locking the read semaphore for I/O.(Pointed out by Xu Jin) In order to avoid this, a wait_list is introduced, the appending read semaphore ops will be dropped into the wait_list if checkpoint thread is waiting for write semaphore, and will be waked up when checkpoint thread gives up write semaphore. Thanks to Kim's previous review and test, and will be very glad to see other guys' performance tests about this patch. V2: -fix the potential starvation problem. -use more suitable func name suggested by Xu Jin. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> [Jaegeuk Kim: adjust minor coding standard] Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-09-27 10:08:30 +00:00
f2fs_lock_op(sbi);
f2fs_down_write(&F2FS_I(inode)->i_xattr_sem);
err = __f2fs_setxattr(inode, index, name, value, size, ipage, flags);
f2fs_up_write(&F2FS_I(inode)->i_xattr_sem);
f2fs: use rw_sem instead of fs_lock(locks mutex) The fs_locks is used to block other ops(ex, recovery) when doing checkpoint. And each other operate routine(besides checkpoint) needs to acquire a fs_lock, there is a terrible problem here, if these are too many concurrency threads acquiring fs_lock, so that they will block each other and may lead to some performance problem, but this is not the phenomenon we want to see. Though there are some optimization patches introduced to enhance the usage of fs_lock, but the thorough solution is using a *rw_sem* to replace the fs_lock. Checkpoint routine takes write_sem, and other ops take read_sem, so that we can block other ops(ex, recovery) when doing checkpoint, and other ops will not disturb each other, this can avoid the problem described above completely. Because of the weakness of rw_sem, the above change may introduce a potential problem that the checkpoint thread might get starved if other threads are intensively locking the read semaphore for I/O.(Pointed out by Xu Jin) In order to avoid this, a wait_list is introduced, the appending read semaphore ops will be dropped into the wait_list if checkpoint thread is waiting for write semaphore, and will be waked up when checkpoint thread gives up write semaphore. Thanks to Kim's previous review and test, and will be very glad to see other guys' performance tests about this patch. V2: -fix the potential starvation problem. -use more suitable func name suggested by Xu Jin. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> [Jaegeuk Kim: adjust minor coding standard] Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-09-27 10:08:30 +00:00
f2fs_unlock_op(sbi);
f2fs_update_time(sbi, REQ_TIME);
return err;
}
int f2fs_init_xattr_caches(struct f2fs_sb_info *sbi)
{
dev_t dev = sbi->sb->s_bdev->bd_dev;
char slab_name[32];
sprintf(slab_name, "f2fs_xattr_entry-%u:%u", MAJOR(dev), MINOR(dev));
sbi->inline_xattr_slab_size = F2FS_OPTION(sbi).inline_xattr_size *
sizeof(__le32) + XATTR_PADDING_SIZE;
sbi->inline_xattr_slab = f2fs_kmem_cache_create(slab_name,
sbi->inline_xattr_slab_size);
if (!sbi->inline_xattr_slab)
return -ENOMEM;
return 0;
}
void f2fs_destroy_xattr_caches(struct f2fs_sb_info *sbi)
{
kmem_cache_destroy(sbi->inline_xattr_slab);
}