linux_dsm_epyc7002/fs/f2fs/xattr.h

166 lines
4.9 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/xattr.h
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*
* Portions of this code from linux/fs/ext2/xattr.h
*
* On-disk format of extended attributes for the ext2 filesystem.
*
* (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org>
*/
#ifndef __F2FS_XATTR_H__
#define __F2FS_XATTR_H__
#include <linux/init.h>
#include <linux/xattr.h>
/* Magic value in attribute blocks */
#define F2FS_XATTR_MAGIC 0xF2F52011
/* Maximum number of references to one attribute block */
#define F2FS_XATTR_REFCOUNT_MAX 1024
/* Name indexes */
#define F2FS_SYSTEM_ADVISE_NAME "system.advise"
#define F2FS_XATTR_INDEX_USER 1
#define F2FS_XATTR_INDEX_POSIX_ACL_ACCESS 2
#define F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT 3
#define F2FS_XATTR_INDEX_TRUSTED 4
#define F2FS_XATTR_INDEX_LUSTRE 5
#define F2FS_XATTR_INDEX_SECURITY 6
#define F2FS_XATTR_INDEX_ADVISE 7
/* Should be same as EXT4_XATTR_INDEX_ENCRYPTION */
#define F2FS_XATTR_INDEX_ENCRYPTION 9
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 23:26:24 +07:00
#define F2FS_XATTR_INDEX_VERITY 11
#define F2FS_XATTR_NAME_ENCRYPTION_CONTEXT "c"
f2fs: add fs-verity support Add fs-verity support to f2fs. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. The f2fs support for fs-verity consists of: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->readpages() to verify data as it's read from verity files and to support reading verity metadata pages. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). Like ext4, f2fs stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by f2fs with only some relatively small changes to f2fs. Extended attributes cannot be used because (a) f2fs limits the total size of an inode's xattr entries to 4096 bytes, which wouldn't be enough for even a single Merkle tree block, and (b) f2fs encryption doesn't encrypt xattrs, yet the verity metadata *must* be encrypted when the file is because it contains hashes of the plaintext data. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-22 23:26:24 +07:00
#define F2FS_XATTR_NAME_VERITY "v"
struct f2fs_xattr_header {
__le32 h_magic; /* magic number for identification */
__le32 h_refcount; /* reference count */
__u32 h_reserved[4]; /* zero right now */
};
struct f2fs_xattr_entry {
__u8 e_name_index;
__u8 e_name_len;
__le16 e_value_size; /* size of attribute value */
char e_name[0]; /* attribute name */
};
#define XATTR_HDR(ptr) ((struct f2fs_xattr_header *)(ptr))
#define XATTR_ENTRY(ptr) ((struct f2fs_xattr_entry *)(ptr))
#define XATTR_FIRST_ENTRY(ptr) (XATTR_ENTRY(XATTR_HDR(ptr) + 1))
#define XATTR_ROUND (3)
#define XATTR_ALIGN(size) (((size) + XATTR_ROUND) & ~XATTR_ROUND)
#define ENTRY_SIZE(entry) (XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + \
(entry)->e_name_len + le16_to_cpu((entry)->e_value_size)))
#define XATTR_NEXT_ENTRY(entry) ((struct f2fs_xattr_entry *)((char *)(entry) +\
ENTRY_SIZE(entry)))
#define IS_XATTR_LAST_ENTRY(entry) (*(__u32 *)(entry) == 0)
#define list_for_each_xattr(entry, addr) \
for (entry = XATTR_FIRST_ENTRY(addr);\
!IS_XATTR_LAST_ENTRY(entry);\
entry = XATTR_NEXT_ENTRY(entry))
#define VALID_XATTR_BLOCK_SIZE (PAGE_SIZE - sizeof(struct node_footer))
#define XATTR_PADDING_SIZE (sizeof(__u32))
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 15:26:46 +07:00
#define XATTR_SIZE(x,i) (((x) ? VALID_XATTR_BLOCK_SIZE : 0) + \
(inline_xattr_size(i)))
#define MIN_OFFSET(i) XATTR_ALIGN(inline_xattr_size(i) + \
VALID_XATTR_BLOCK_SIZE)
#define MAX_VALUE_LEN(i) (MIN_OFFSET(i) - \
sizeof(struct f2fs_xattr_header) - \
sizeof(struct f2fs_xattr_entry))
f2fs: fix to do sanity check with inode.i_inline_xattr_size As Paul Bandha reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202709 When I run the poc on the mounted f2fs img I get a buffer overflow in read_inline_xattr due to there being no sanity check on the value of i_inline_xattr_size. I created the img by just modifying the value of i_inline_xattr_size in the inode: i_name [test1.txt] i_ext: fofs:0 blkaddr:0 len:0 i_extra_isize [0x 18 : 24] i_inline_xattr_size [0x ffff : 65535] i_addr[ofs] [0x 0 : 0] mkdir /mnt/f2fs mount ./f2fs1.img /mnt/f2fs gcc poc.c -o poc ./poc int main() { int y = syscall(SYS_listxattr, "/mnt/f2fs/test1.txt", NULL, 0); printf("ret %d", y); printf("errno: %d\n", errno); } BUG: KASAN: slab-out-of-bounds in read_inline_xattr+0x18f/0x260 Read of size 262140 at addr ffff88011035efd8 by task f2fs1poc/3263 CPU: 0 PID: 3263 Comm: f2fs1poc Not tainted 4.18.0-custom #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.1-0-g0551a4be2c-prebuilt.qemu-project.org 04/01/2014 Call Trace: dump_stack+0x71/0xab print_address_description+0x83/0x250 kasan_report+0x213/0x350 memcpy+0x1f/0x50 read_inline_xattr+0x18f/0x260 read_all_xattrs+0xba/0x190 f2fs_listxattr+0x9d/0x3f0 listxattr+0xb2/0xd0 path_listxattr+0x93/0xe0 do_syscall_64+0x9d/0x220 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Let's add sanity check for inode.i_inline_xattr_size during f2fs_iget() to avoid this issue. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-03-04 16:19:04 +07:00
#define MAX_INLINE_XATTR_SIZE \
(DEF_ADDRS_PER_INODE - \
F2FS_TOTAL_EXTRA_ATTR_SIZE / sizeof(__le32) - \
DEF_INLINE_RESERVED_SIZE - \
MIN_INLINE_DENTRY_SIZE / sizeof(__le32))
/*
* On-disk structure of f2fs_xattr
* We use inline xattrs space + 1 block for xattr.
*
* +--------------------+
* | f2fs_xattr_header |
* | |
* +--------------------+
* | f2fs_xattr_entry |
* | .e_name_index = 1 |
* | .e_name_len = 3 |
* | .e_value_size = 14 |
* | .e_name = "foo" |
* | "value_of_xattr" |<- value_offs = e_name + e_name_len
* +--------------------+
* | f2fs_xattr_entry |
* | .e_name_index = 4 |
* | .e_name = "bar" |
* +--------------------+
* | |
* | Free |
* | |
* +--------------------+<- MIN_OFFSET
* | node_footer |
* | (nid, ino, offset) |
* +--------------------+
*
**/
#ifdef CONFIG_F2FS_FS_XATTR
extern const struct xattr_handler f2fs_xattr_user_handler;
extern const struct xattr_handler f2fs_xattr_trusted_handler;
extern const struct xattr_handler f2fs_xattr_advise_handler;
extern const struct xattr_handler f2fs_xattr_security_handler;
extern const struct xattr_handler *f2fs_xattr_handlers[];
extern int f2fs_setxattr(struct inode *, int, const char *,
const void *, size_t, struct page *, int);
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 09:42:53 +07:00
extern int f2fs_getxattr(struct inode *, int, const char *, void *,
size_t, struct page *);
extern ssize_t f2fs_listxattr(struct dentry *, char *, size_t);
#else
#define f2fs_xattr_handlers NULL
static inline int f2fs_setxattr(struct inode *inode, int index,
const char *name, const void *value, size_t size,
struct page *page, int flags)
{
return -EOPNOTSUPP;
}
static inline int f2fs_getxattr(struct inode *inode, int index,
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 09:42:53 +07:00
const char *name, void *buffer,
size_t buffer_size, struct page *dpage)
{
return -EOPNOTSUPP;
}
static inline ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer,
size_t buffer_size)
{
return -EOPNOTSUPP;
}
#endif
#ifdef CONFIG_F2FS_FS_SECURITY
extern int f2fs_init_security(struct inode *, struct inode *,
const struct qstr *, struct page *);
#else
static inline int f2fs_init_security(struct inode *inode, struct inode *dir,
const struct qstr *qstr, struct page *ipage)
{
return 0;
}
#endif
#endif /* __F2FS_XATTR_H__ */