OpenCloudOS-Kernel/fs/xfs/xfs_attr_list.c

540 lines
13 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
* Copyright (c) 2013 Red Hat, Inc.
* All Rights Reserved.
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_da_format.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_bmap.h"
xfs: Set up infrastructure for log attribute replay Currently attributes are modified directly across one or more transactions. But they are not logged or replayed in the event of an error. The goal of log attr replay is to enable logging and replaying of attribute operations using the existing delayed operations infrastructure. This will later enable the attributes to become part of larger multi part operations that also must first be recorded to the log. This is mostly of interest in the scheme of parent pointers which would need to maintain an attribute containing parent inode information any time an inode is moved, created, or removed. Parent pointers would then be of interest to any feature that would need to quickly derive an inode path from the mount point. Online scrub, nfs lookups and fs grow or shrink operations are all features that could take advantage of this. This patch adds two new log item types for setting or removing attributes as deferred operations. The xfs_attri_log_item will log an intent to set or remove an attribute. The corresponding xfs_attrd_log_item holds a reference to the xfs_attri_log_item and is freed once the transaction is done. Both log items use a generic xfs_attr_log_format structure that contains the attribute name, value, flags, inode, and an op_flag that indicates if the operations is a set or remove. [dchinner: added extra little bits needed for intent whiteouts] Signed-off-by: Allison Henderson <allison.henderson@oracle.com> Reviewed-by: Chandan Babu R <chandanrlinux@gmail.com> Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Dave Chinner <david@fromorbit.com>
2022-05-04 10:41:02 +08:00
#include "xfs_da_btree.h"
#include "xfs_attr.h"
#include "xfs_attr_sf.h"
#include "xfs_attr_leaf.h"
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_dir2.h"
STATIC int
xfs_attr_shortform_compare(const void *a, const void *b)
{
xfs_attr_sf_sort_t *sa, *sb;
sa = (xfs_attr_sf_sort_t *)a;
sb = (xfs_attr_sf_sort_t *)b;
if (sa->hash < sb->hash) {
return -1;
} else if (sa->hash > sb->hash) {
return 1;
} else {
return sa->entno - sb->entno;
}
}
#define XFS_ISRESET_CURSOR(cursor) \
(!((cursor)->initted) && !((cursor)->hashval) && \
!((cursor)->blkno) && !((cursor)->offset))
/*
* Copy out entries of shortform attribute lists for attr_list().
* Shortform attribute lists are not stored in hashval sorted order.
* If the output buffer is not large enough to hold them all, then
* we have to calculate each entries' hashvalue and sort them before
* we can begin returning them to the user.
*/
static int
xfs_attr_shortform_list(
struct xfs_attr_list_context *context)
{
struct xfs_attrlist_cursor_kern *cursor = &context->cursor;
struct xfs_inode *dp = context->dp;
struct xfs_attr_sf_sort *sbuf, *sbp;
struct xfs_attr_shortform *sf;
struct xfs_attr_sf_entry *sfe;
int sbsize, nsbuf, count, i;
int error = 0;
xfs: make inode attribute forks a permanent part of struct xfs_inode Syzkaller reported a UAF bug a while back: ================================================================== BUG: KASAN: use-after-free in xfs_ilock_attr_map_shared+0xe3/0xf6 fs/xfs/xfs_inode.c:127 Read of size 4 at addr ffff88802cec919c by task syz-executor262/2958 CPU: 2 PID: 2958 Comm: syz-executor262 Not tainted 5.15.0-0.30.3-20220406_1406 #3 Hardware name: Red Hat KVM, BIOS 1.13.0-2.module+el8.3.0+7860+a7792d29 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x82/0xa9 lib/dump_stack.c:106 print_address_description.constprop.9+0x21/0x2d5 mm/kasan/report.c:256 __kasan_report mm/kasan/report.c:442 [inline] kasan_report.cold.14+0x7f/0x11b mm/kasan/report.c:459 xfs_ilock_attr_map_shared+0xe3/0xf6 fs/xfs/xfs_inode.c:127 xfs_attr_get+0x378/0x4c2 fs/xfs/libxfs/xfs_attr.c:159 xfs_xattr_get+0xe3/0x150 fs/xfs/xfs_xattr.c:36 __vfs_getxattr+0xdf/0x13d fs/xattr.c:399 cap_inode_need_killpriv+0x41/0x5d security/commoncap.c:300 security_inode_need_killpriv+0x4c/0x97 security/security.c:1408 dentry_needs_remove_privs.part.28+0x21/0x63 fs/inode.c:1912 dentry_needs_remove_privs+0x80/0x9e fs/inode.c:1908 do_truncate+0xc3/0x1e0 fs/open.c:56 handle_truncate fs/namei.c:3084 [inline] do_open fs/namei.c:3432 [inline] path_openat+0x30ab/0x396d fs/namei.c:3561 do_filp_open+0x1c4/0x290 fs/namei.c:3588 do_sys_openat2+0x60d/0x98c fs/open.c:1212 do_sys_open+0xcf/0x13c fs/open.c:1228 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x7e arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0x0 RIP: 0033:0x7f7ef4bb753d Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 1b 79 2c 00 f7 d8 64 89 01 48 RSP: 002b:00007f7ef52c2ed8 EFLAGS: 00000246 ORIG_RAX: 0000000000000055 RAX: ffffffffffffffda RBX: 0000000000404148 RCX: 00007f7ef4bb753d RDX: 00007f7ef4bb753d RSI: 0000000000000000 RDI: 0000000020004fc0 RBP: 0000000000404140 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0030656c69662f2e R13: 00007ffd794db37f R14: 00007ffd794db470 R15: 00007f7ef52c2fc0 </TASK> Allocated by task 2953: kasan_save_stack+0x19/0x38 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:46 [inline] set_alloc_info mm/kasan/common.c:434 [inline] __kasan_slab_alloc+0x68/0x7c mm/kasan/common.c:467 kasan_slab_alloc include/linux/kasan.h:254 [inline] slab_post_alloc_hook mm/slab.h:519 [inline] slab_alloc_node mm/slub.c:3213 [inline] slab_alloc mm/slub.c:3221 [inline] kmem_cache_alloc+0x11b/0x3eb mm/slub.c:3226 kmem_cache_zalloc include/linux/slab.h:711 [inline] xfs_ifork_alloc+0x25/0xa2 fs/xfs/libxfs/xfs_inode_fork.c:287 xfs_bmap_add_attrfork+0x3f2/0x9b1 fs/xfs/libxfs/xfs_bmap.c:1098 xfs_attr_set+0xe38/0x12a7 fs/xfs/libxfs/xfs_attr.c:746 xfs_xattr_set+0xeb/0x1a9 fs/xfs/xfs_xattr.c:59 __vfs_setxattr+0x11b/0x177 fs/xattr.c:180 __vfs_setxattr_noperm+0x128/0x5e0 fs/xattr.c:214 __vfs_setxattr_locked+0x1d4/0x258 fs/xattr.c:275 vfs_setxattr+0x154/0x33d fs/xattr.c:301 setxattr+0x216/0x29f fs/xattr.c:575 __do_sys_fsetxattr fs/xattr.c:632 [inline] __se_sys_fsetxattr fs/xattr.c:621 [inline] __x64_sys_fsetxattr+0x243/0x2fe fs/xattr.c:621 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x7e arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0x0 Freed by task 2949: kasan_save_stack+0x19/0x38 mm/kasan/common.c:38 kasan_set_track+0x1c/0x21 mm/kasan/common.c:46 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:360 ____kasan_slab_free mm/kasan/common.c:366 [inline] ____kasan_slab_free mm/kasan/common.c:328 [inline] __kasan_slab_free+0xe2/0x10e mm/kasan/common.c:374 kasan_slab_free include/linux/kasan.h:230 [inline] slab_free_hook mm/slub.c:1700 [inline] slab_free_freelist_hook mm/slub.c:1726 [inline] slab_free mm/slub.c:3492 [inline] kmem_cache_free+0xdc/0x3ce mm/slub.c:3508 xfs_attr_fork_remove+0x8d/0x132 fs/xfs/libxfs/xfs_attr_leaf.c:773 xfs_attr_sf_removename+0x5dd/0x6cb fs/xfs/libxfs/xfs_attr_leaf.c:822 xfs_attr_remove_iter+0x68c/0x805 fs/xfs/libxfs/xfs_attr.c:1413 xfs_attr_remove_args+0xb1/0x10d fs/xfs/libxfs/xfs_attr.c:684 xfs_attr_set+0xf1e/0x12a7 fs/xfs/libxfs/xfs_attr.c:802 xfs_xattr_set+0xeb/0x1a9 fs/xfs/xfs_xattr.c:59 __vfs_removexattr+0x106/0x16a fs/xattr.c:468 cap_inode_killpriv+0x24/0x47 security/commoncap.c:324 security_inode_killpriv+0x54/0xa1 security/security.c:1414 setattr_prepare+0x1a6/0x897 fs/attr.c:146 xfs_vn_change_ok+0x111/0x15e fs/xfs/xfs_iops.c:682 xfs_vn_setattr_size+0x5f/0x15a fs/xfs/xfs_iops.c:1065 xfs_vn_setattr+0x125/0x2ad fs/xfs/xfs_iops.c:1093 notify_change+0xae5/0x10a1 fs/attr.c:410 do_truncate+0x134/0x1e0 fs/open.c:64 handle_truncate fs/namei.c:3084 [inline] do_open fs/namei.c:3432 [inline] path_openat+0x30ab/0x396d fs/namei.c:3561 do_filp_open+0x1c4/0x290 fs/namei.c:3588 do_sys_openat2+0x60d/0x98c fs/open.c:1212 do_sys_open+0xcf/0x13c fs/open.c:1228 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x7e arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0x0 The buggy address belongs to the object at ffff88802cec9188 which belongs to the cache xfs_ifork of size 40 The buggy address is located 20 bytes inside of 40-byte region [ffff88802cec9188, ffff88802cec91b0) The buggy address belongs to the page: page:00000000c3af36a1 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x2cec9 flags: 0xfffffc0000200(slab|node=0|zone=1|lastcpupid=0x1fffff) raw: 000fffffc0000200 ffffea00009d2580 0000000600000006 ffff88801a9ffc80 raw: 0000000000000000 0000000080490049 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88802cec9080: fb fb fb fc fc fa fb fb fb fb fc fc fb fb fb fb ffff88802cec9100: fb fc fc fb fb fb fb fb fc fc fb fb fb fb fb fc >ffff88802cec9180: fc fa fb fb fb fb fc fc fa fb fb fb fb fc fc fb ^ ffff88802cec9200: fb fb fb fb fc fc fb fb fb fb fb fc fc fb fb fb ffff88802cec9280: fb fb fc fc fa fb fb fb fb fc fc fa fb fb fb fb ================================================================== The root cause of this bug is the unlocked access to xfs_inode.i_afp from the getxattr code paths while trying to determine which ILOCK mode to use to stabilize the xattr data. Unfortunately, the VFS does not acquire i_rwsem when vfs_getxattr (or listxattr) call into the filesystem, which means that getxattr can race with a removexattr that's tearing down the attr fork and crash: xfs_attr_set: xfs_attr_get: xfs_attr_fork_remove: xfs_ilock_attr_map_shared: xfs_idestroy_fork(ip->i_afp); kmem_cache_free(xfs_ifork_cache, ip->i_afp); if (ip->i_afp && ip->i_afp = NULL; xfs_need_iread_extents(ip->i_afp)) <KABOOM> ip->i_forkoff = 0; Regrettably, the VFS is much more lax about i_rwsem and getxattr than is immediately obvious -- not only does it not guarantee that we hold i_rwsem, it actually doesn't guarantee that we *don't* hold it either. The getxattr system call won't acquire the lock before calling XFS, but the file capabilities code calls getxattr with and without i_rwsem held to determine if the "security.capabilities" xattr is set on the file. Fixing the VFS locking requires a treewide investigation into every code path that could touch an xattr and what i_rwsem state it expects or sets up. That could take years or even prove impossible; fortunately, we can fix this UAF problem inside XFS. An earlier version of this patch used smp_wmb in xfs_attr_fork_remove to ensure that i_forkoff is always zeroed before i_afp is set to null and changed the read paths to use smp_rmb before accessing i_forkoff and i_afp, which avoided these UAF problems. However, the patch author was too busy dealing with other problems in the meantime, and by the time he came back to this issue, the situation had changed a bit. On a modern system with selinux, each inode will always have at least one xattr for the selinux label, so it doesn't make much sense to keep incurring the extra pointer dereference. Furthermore, Allison's upcoming parent pointer patchset will also cause nearly every inode in the filesystem to have extended attributes. Therefore, make the inode attribute fork structure part of struct xfs_inode, at a cost of 40 more bytes. This patch adds a clunky if_present field where necessary to maintain the existing logic of xattr fork null pointer testing in the existing codebase. The next patch switches the logic over to XFS_IFORK_Q and it all goes away. Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2022-07-10 01:56:06 +08:00
sf = (struct xfs_attr_shortform *)dp->i_af.if_u1.if_data;
ASSERT(sf != NULL);
if (!sf->hdr.count)
return 0;
trace_xfs_attr_list_sf(context);
/*
* If the buffer is large enough and the cursor is at the start,
* do not bother with sorting since we will return everything in
* one buffer and another call using the cursor won't need to be
* made.
* Note the generous fudge factor of 16 overhead bytes per entry.
* If bufsize is zero then put_listent must be a search function
* and can just scan through what we have.
*/
if (context->bufsize == 0 ||
(XFS_ISRESET_CURSOR(cursor) &&
xfs: make inode attribute forks a permanent part of struct xfs_inode Syzkaller reported a UAF bug a while back: ================================================================== BUG: KASAN: use-after-free in xfs_ilock_attr_map_shared+0xe3/0xf6 fs/xfs/xfs_inode.c:127 Read of size 4 at addr ffff88802cec919c by task syz-executor262/2958 CPU: 2 PID: 2958 Comm: syz-executor262 Not tainted 5.15.0-0.30.3-20220406_1406 #3 Hardware name: Red Hat KVM, BIOS 1.13.0-2.module+el8.3.0+7860+a7792d29 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x82/0xa9 lib/dump_stack.c:106 print_address_description.constprop.9+0x21/0x2d5 mm/kasan/report.c:256 __kasan_report mm/kasan/report.c:442 [inline] kasan_report.cold.14+0x7f/0x11b mm/kasan/report.c:459 xfs_ilock_attr_map_shared+0xe3/0xf6 fs/xfs/xfs_inode.c:127 xfs_attr_get+0x378/0x4c2 fs/xfs/libxfs/xfs_attr.c:159 xfs_xattr_get+0xe3/0x150 fs/xfs/xfs_xattr.c:36 __vfs_getxattr+0xdf/0x13d fs/xattr.c:399 cap_inode_need_killpriv+0x41/0x5d security/commoncap.c:300 security_inode_need_killpriv+0x4c/0x97 security/security.c:1408 dentry_needs_remove_privs.part.28+0x21/0x63 fs/inode.c:1912 dentry_needs_remove_privs+0x80/0x9e fs/inode.c:1908 do_truncate+0xc3/0x1e0 fs/open.c:56 handle_truncate fs/namei.c:3084 [inline] do_open fs/namei.c:3432 [inline] path_openat+0x30ab/0x396d fs/namei.c:3561 do_filp_open+0x1c4/0x290 fs/namei.c:3588 do_sys_openat2+0x60d/0x98c fs/open.c:1212 do_sys_open+0xcf/0x13c fs/open.c:1228 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x7e arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0x0 RIP: 0033:0x7f7ef4bb753d Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 1b 79 2c 00 f7 d8 64 89 01 48 RSP: 002b:00007f7ef52c2ed8 EFLAGS: 00000246 ORIG_RAX: 0000000000000055 RAX: ffffffffffffffda RBX: 0000000000404148 RCX: 00007f7ef4bb753d RDX: 00007f7ef4bb753d RSI: 0000000000000000 RDI: 0000000020004fc0 RBP: 0000000000404140 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0030656c69662f2e R13: 00007ffd794db37f R14: 00007ffd794db470 R15: 00007f7ef52c2fc0 </TASK> Allocated by task 2953: kasan_save_stack+0x19/0x38 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:46 [inline] set_alloc_info mm/kasan/common.c:434 [inline] __kasan_slab_alloc+0x68/0x7c mm/kasan/common.c:467 kasan_slab_alloc include/linux/kasan.h:254 [inline] slab_post_alloc_hook mm/slab.h:519 [inline] slab_alloc_node mm/slub.c:3213 [inline] slab_alloc mm/slub.c:3221 [inline] kmem_cache_alloc+0x11b/0x3eb mm/slub.c:3226 kmem_cache_zalloc include/linux/slab.h:711 [inline] xfs_ifork_alloc+0x25/0xa2 fs/xfs/libxfs/xfs_inode_fork.c:287 xfs_bmap_add_attrfork+0x3f2/0x9b1 fs/xfs/libxfs/xfs_bmap.c:1098 xfs_attr_set+0xe38/0x12a7 fs/xfs/libxfs/xfs_attr.c:746 xfs_xattr_set+0xeb/0x1a9 fs/xfs/xfs_xattr.c:59 __vfs_setxattr+0x11b/0x177 fs/xattr.c:180 __vfs_setxattr_noperm+0x128/0x5e0 fs/xattr.c:214 __vfs_setxattr_locked+0x1d4/0x258 fs/xattr.c:275 vfs_setxattr+0x154/0x33d fs/xattr.c:301 setxattr+0x216/0x29f fs/xattr.c:575 __do_sys_fsetxattr fs/xattr.c:632 [inline] __se_sys_fsetxattr fs/xattr.c:621 [inline] __x64_sys_fsetxattr+0x243/0x2fe fs/xattr.c:621 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x7e arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0x0 Freed by task 2949: kasan_save_stack+0x19/0x38 mm/kasan/common.c:38 kasan_set_track+0x1c/0x21 mm/kasan/common.c:46 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:360 ____kasan_slab_free mm/kasan/common.c:366 [inline] ____kasan_slab_free mm/kasan/common.c:328 [inline] __kasan_slab_free+0xe2/0x10e mm/kasan/common.c:374 kasan_slab_free include/linux/kasan.h:230 [inline] slab_free_hook mm/slub.c:1700 [inline] slab_free_freelist_hook mm/slub.c:1726 [inline] slab_free mm/slub.c:3492 [inline] kmem_cache_free+0xdc/0x3ce mm/slub.c:3508 xfs_attr_fork_remove+0x8d/0x132 fs/xfs/libxfs/xfs_attr_leaf.c:773 xfs_attr_sf_removename+0x5dd/0x6cb fs/xfs/libxfs/xfs_attr_leaf.c:822 xfs_attr_remove_iter+0x68c/0x805 fs/xfs/libxfs/xfs_attr.c:1413 xfs_attr_remove_args+0xb1/0x10d fs/xfs/libxfs/xfs_attr.c:684 xfs_attr_set+0xf1e/0x12a7 fs/xfs/libxfs/xfs_attr.c:802 xfs_xattr_set+0xeb/0x1a9 fs/xfs/xfs_xattr.c:59 __vfs_removexattr+0x106/0x16a fs/xattr.c:468 cap_inode_killpriv+0x24/0x47 security/commoncap.c:324 security_inode_killpriv+0x54/0xa1 security/security.c:1414 setattr_prepare+0x1a6/0x897 fs/attr.c:146 xfs_vn_change_ok+0x111/0x15e fs/xfs/xfs_iops.c:682 xfs_vn_setattr_size+0x5f/0x15a fs/xfs/xfs_iops.c:1065 xfs_vn_setattr+0x125/0x2ad fs/xfs/xfs_iops.c:1093 notify_change+0xae5/0x10a1 fs/attr.c:410 do_truncate+0x134/0x1e0 fs/open.c:64 handle_truncate fs/namei.c:3084 [inline] do_open fs/namei.c:3432 [inline] path_openat+0x30ab/0x396d fs/namei.c:3561 do_filp_open+0x1c4/0x290 fs/namei.c:3588 do_sys_openat2+0x60d/0x98c fs/open.c:1212 do_sys_open+0xcf/0x13c fs/open.c:1228 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x7e arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0x0 The buggy address belongs to the object at ffff88802cec9188 which belongs to the cache xfs_ifork of size 40 The buggy address is located 20 bytes inside of 40-byte region [ffff88802cec9188, ffff88802cec91b0) The buggy address belongs to the page: page:00000000c3af36a1 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x2cec9 flags: 0xfffffc0000200(slab|node=0|zone=1|lastcpupid=0x1fffff) raw: 000fffffc0000200 ffffea00009d2580 0000000600000006 ffff88801a9ffc80 raw: 0000000000000000 0000000080490049 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88802cec9080: fb fb fb fc fc fa fb fb fb fb fc fc fb fb fb fb ffff88802cec9100: fb fc fc fb fb fb fb fb fc fc fb fb fb fb fb fc >ffff88802cec9180: fc fa fb fb fb fb fc fc fa fb fb fb fb fc fc fb ^ ffff88802cec9200: fb fb fb fb fc fc fb fb fb fb fb fc fc fb fb fb ffff88802cec9280: fb fb fc fc fa fb fb fb fb fc fc fa fb fb fb fb ================================================================== The root cause of this bug is the unlocked access to xfs_inode.i_afp from the getxattr code paths while trying to determine which ILOCK mode to use to stabilize the xattr data. Unfortunately, the VFS does not acquire i_rwsem when vfs_getxattr (or listxattr) call into the filesystem, which means that getxattr can race with a removexattr that's tearing down the attr fork and crash: xfs_attr_set: xfs_attr_get: xfs_attr_fork_remove: xfs_ilock_attr_map_shared: xfs_idestroy_fork(ip->i_afp); kmem_cache_free(xfs_ifork_cache, ip->i_afp); if (ip->i_afp && ip->i_afp = NULL; xfs_need_iread_extents(ip->i_afp)) <KABOOM> ip->i_forkoff = 0; Regrettably, the VFS is much more lax about i_rwsem and getxattr than is immediately obvious -- not only does it not guarantee that we hold i_rwsem, it actually doesn't guarantee that we *don't* hold it either. The getxattr system call won't acquire the lock before calling XFS, but the file capabilities code calls getxattr with and without i_rwsem held to determine if the "security.capabilities" xattr is set on the file. Fixing the VFS locking requires a treewide investigation into every code path that could touch an xattr and what i_rwsem state it expects or sets up. That could take years or even prove impossible; fortunately, we can fix this UAF problem inside XFS. An earlier version of this patch used smp_wmb in xfs_attr_fork_remove to ensure that i_forkoff is always zeroed before i_afp is set to null and changed the read paths to use smp_rmb before accessing i_forkoff and i_afp, which avoided these UAF problems. However, the patch author was too busy dealing with other problems in the meantime, and by the time he came back to this issue, the situation had changed a bit. On a modern system with selinux, each inode will always have at least one xattr for the selinux label, so it doesn't make much sense to keep incurring the extra pointer dereference. Furthermore, Allison's upcoming parent pointer patchset will also cause nearly every inode in the filesystem to have extended attributes. Therefore, make the inode attribute fork structure part of struct xfs_inode, at a cost of 40 more bytes. This patch adds a clunky if_present field where necessary to maintain the existing logic of xattr fork null pointer testing in the existing codebase. The next patch switches the logic over to XFS_IFORK_Q and it all goes away. Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2022-07-10 01:56:06 +08:00
(dp->i_af.if_bytes + sf->hdr.count * 16) < context->bufsize)) {
for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
if (XFS_IS_CORRUPT(context->dp->i_mount,
!xfs_attr_namecheck(sfe->nameval,
sfe->namelen)))
return -EFSCORRUPTED;
context->put_listent(context,
sfe->flags,
sfe->nameval,
(int)sfe->namelen,
(int)sfe->valuelen);
/*
* Either search callback finished early or
* didn't fit it all in the buffer after all.
*/
if (context->seen_enough)
break;
sfe = xfs_attr_sf_nextentry(sfe);
}
trace_xfs_attr_list_sf_all(context);
return 0;
}
/* do no more for a search callback */
if (context->bufsize == 0)
return 0;
/*
* It didn't all fit, so we have to sort everything on hashval.
*/
sbsize = sf->hdr.count * sizeof(*sbuf);
sbp = sbuf = kmem_alloc(sbsize, KM_NOFS);
/*
* Scan the attribute list for the rest of the entries, storing
* the relevant info from only those that match into a buffer.
*/
nsbuf = 0;
for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
if (unlikely(
((char *)sfe < (char *)sf) ||
xfs: make inode attribute forks a permanent part of struct xfs_inode Syzkaller reported a UAF bug a while back: ================================================================== BUG: KASAN: use-after-free in xfs_ilock_attr_map_shared+0xe3/0xf6 fs/xfs/xfs_inode.c:127 Read of size 4 at addr ffff88802cec919c by task syz-executor262/2958 CPU: 2 PID: 2958 Comm: syz-executor262 Not tainted 5.15.0-0.30.3-20220406_1406 #3 Hardware name: Red Hat KVM, BIOS 1.13.0-2.module+el8.3.0+7860+a7792d29 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x82/0xa9 lib/dump_stack.c:106 print_address_description.constprop.9+0x21/0x2d5 mm/kasan/report.c:256 __kasan_report mm/kasan/report.c:442 [inline] kasan_report.cold.14+0x7f/0x11b mm/kasan/report.c:459 xfs_ilock_attr_map_shared+0xe3/0xf6 fs/xfs/xfs_inode.c:127 xfs_attr_get+0x378/0x4c2 fs/xfs/libxfs/xfs_attr.c:159 xfs_xattr_get+0xe3/0x150 fs/xfs/xfs_xattr.c:36 __vfs_getxattr+0xdf/0x13d fs/xattr.c:399 cap_inode_need_killpriv+0x41/0x5d security/commoncap.c:300 security_inode_need_killpriv+0x4c/0x97 security/security.c:1408 dentry_needs_remove_privs.part.28+0x21/0x63 fs/inode.c:1912 dentry_needs_remove_privs+0x80/0x9e fs/inode.c:1908 do_truncate+0xc3/0x1e0 fs/open.c:56 handle_truncate fs/namei.c:3084 [inline] do_open fs/namei.c:3432 [inline] path_openat+0x30ab/0x396d fs/namei.c:3561 do_filp_open+0x1c4/0x290 fs/namei.c:3588 do_sys_openat2+0x60d/0x98c fs/open.c:1212 do_sys_open+0xcf/0x13c fs/open.c:1228 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x7e arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0x0 RIP: 0033:0x7f7ef4bb753d Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 1b 79 2c 00 f7 d8 64 89 01 48 RSP: 002b:00007f7ef52c2ed8 EFLAGS: 00000246 ORIG_RAX: 0000000000000055 RAX: ffffffffffffffda RBX: 0000000000404148 RCX: 00007f7ef4bb753d RDX: 00007f7ef4bb753d RSI: 0000000000000000 RDI: 0000000020004fc0 RBP: 0000000000404140 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0030656c69662f2e R13: 00007ffd794db37f R14: 00007ffd794db470 R15: 00007f7ef52c2fc0 </TASK> Allocated by task 2953: kasan_save_stack+0x19/0x38 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:46 [inline] set_alloc_info mm/kasan/common.c:434 [inline] __kasan_slab_alloc+0x68/0x7c mm/kasan/common.c:467 kasan_slab_alloc include/linux/kasan.h:254 [inline] slab_post_alloc_hook mm/slab.h:519 [inline] slab_alloc_node mm/slub.c:3213 [inline] slab_alloc mm/slub.c:3221 [inline] kmem_cache_alloc+0x11b/0x3eb mm/slub.c:3226 kmem_cache_zalloc include/linux/slab.h:711 [inline] xfs_ifork_alloc+0x25/0xa2 fs/xfs/libxfs/xfs_inode_fork.c:287 xfs_bmap_add_attrfork+0x3f2/0x9b1 fs/xfs/libxfs/xfs_bmap.c:1098 xfs_attr_set+0xe38/0x12a7 fs/xfs/libxfs/xfs_attr.c:746 xfs_xattr_set+0xeb/0x1a9 fs/xfs/xfs_xattr.c:59 __vfs_setxattr+0x11b/0x177 fs/xattr.c:180 __vfs_setxattr_noperm+0x128/0x5e0 fs/xattr.c:214 __vfs_setxattr_locked+0x1d4/0x258 fs/xattr.c:275 vfs_setxattr+0x154/0x33d fs/xattr.c:301 setxattr+0x216/0x29f fs/xattr.c:575 __do_sys_fsetxattr fs/xattr.c:632 [inline] __se_sys_fsetxattr fs/xattr.c:621 [inline] __x64_sys_fsetxattr+0x243/0x2fe fs/xattr.c:621 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x7e arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0x0 Freed by task 2949: kasan_save_stack+0x19/0x38 mm/kasan/common.c:38 kasan_set_track+0x1c/0x21 mm/kasan/common.c:46 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:360 ____kasan_slab_free mm/kasan/common.c:366 [inline] ____kasan_slab_free mm/kasan/common.c:328 [inline] __kasan_slab_free+0xe2/0x10e mm/kasan/common.c:374 kasan_slab_free include/linux/kasan.h:230 [inline] slab_free_hook mm/slub.c:1700 [inline] slab_free_freelist_hook mm/slub.c:1726 [inline] slab_free mm/slub.c:3492 [inline] kmem_cache_free+0xdc/0x3ce mm/slub.c:3508 xfs_attr_fork_remove+0x8d/0x132 fs/xfs/libxfs/xfs_attr_leaf.c:773 xfs_attr_sf_removename+0x5dd/0x6cb fs/xfs/libxfs/xfs_attr_leaf.c:822 xfs_attr_remove_iter+0x68c/0x805 fs/xfs/libxfs/xfs_attr.c:1413 xfs_attr_remove_args+0xb1/0x10d fs/xfs/libxfs/xfs_attr.c:684 xfs_attr_set+0xf1e/0x12a7 fs/xfs/libxfs/xfs_attr.c:802 xfs_xattr_set+0xeb/0x1a9 fs/xfs/xfs_xattr.c:59 __vfs_removexattr+0x106/0x16a fs/xattr.c:468 cap_inode_killpriv+0x24/0x47 security/commoncap.c:324 security_inode_killpriv+0x54/0xa1 security/security.c:1414 setattr_prepare+0x1a6/0x897 fs/attr.c:146 xfs_vn_change_ok+0x111/0x15e fs/xfs/xfs_iops.c:682 xfs_vn_setattr_size+0x5f/0x15a fs/xfs/xfs_iops.c:1065 xfs_vn_setattr+0x125/0x2ad fs/xfs/xfs_iops.c:1093 notify_change+0xae5/0x10a1 fs/attr.c:410 do_truncate+0x134/0x1e0 fs/open.c:64 handle_truncate fs/namei.c:3084 [inline] do_open fs/namei.c:3432 [inline] path_openat+0x30ab/0x396d fs/namei.c:3561 do_filp_open+0x1c4/0x290 fs/namei.c:3588 do_sys_openat2+0x60d/0x98c fs/open.c:1212 do_sys_open+0xcf/0x13c fs/open.c:1228 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x7e arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0x0 The buggy address belongs to the object at ffff88802cec9188 which belongs to the cache xfs_ifork of size 40 The buggy address is located 20 bytes inside of 40-byte region [ffff88802cec9188, ffff88802cec91b0) The buggy address belongs to the page: page:00000000c3af36a1 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x2cec9 flags: 0xfffffc0000200(slab|node=0|zone=1|lastcpupid=0x1fffff) raw: 000fffffc0000200 ffffea00009d2580 0000000600000006 ffff88801a9ffc80 raw: 0000000000000000 0000000080490049 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88802cec9080: fb fb fb fc fc fa fb fb fb fb fc fc fb fb fb fb ffff88802cec9100: fb fc fc fb fb fb fb fb fc fc fb fb fb fb fb fc >ffff88802cec9180: fc fa fb fb fb fb fc fc fa fb fb fb fb fc fc fb ^ ffff88802cec9200: fb fb fb fb fc fc fb fb fb fb fb fc fc fb fb fb ffff88802cec9280: fb fb fc fc fa fb fb fb fb fc fc fa fb fb fb fb ================================================================== The root cause of this bug is the unlocked access to xfs_inode.i_afp from the getxattr code paths while trying to determine which ILOCK mode to use to stabilize the xattr data. Unfortunately, the VFS does not acquire i_rwsem when vfs_getxattr (or listxattr) call into the filesystem, which means that getxattr can race with a removexattr that's tearing down the attr fork and crash: xfs_attr_set: xfs_attr_get: xfs_attr_fork_remove: xfs_ilock_attr_map_shared: xfs_idestroy_fork(ip->i_afp); kmem_cache_free(xfs_ifork_cache, ip->i_afp); if (ip->i_afp && ip->i_afp = NULL; xfs_need_iread_extents(ip->i_afp)) <KABOOM> ip->i_forkoff = 0; Regrettably, the VFS is much more lax about i_rwsem and getxattr than is immediately obvious -- not only does it not guarantee that we hold i_rwsem, it actually doesn't guarantee that we *don't* hold it either. The getxattr system call won't acquire the lock before calling XFS, but the file capabilities code calls getxattr with and without i_rwsem held to determine if the "security.capabilities" xattr is set on the file. Fixing the VFS locking requires a treewide investigation into every code path that could touch an xattr and what i_rwsem state it expects or sets up. That could take years or even prove impossible; fortunately, we can fix this UAF problem inside XFS. An earlier version of this patch used smp_wmb in xfs_attr_fork_remove to ensure that i_forkoff is always zeroed before i_afp is set to null and changed the read paths to use smp_rmb before accessing i_forkoff and i_afp, which avoided these UAF problems. However, the patch author was too busy dealing with other problems in the meantime, and by the time he came back to this issue, the situation had changed a bit. On a modern system with selinux, each inode will always have at least one xattr for the selinux label, so it doesn't make much sense to keep incurring the extra pointer dereference. Furthermore, Allison's upcoming parent pointer patchset will also cause nearly every inode in the filesystem to have extended attributes. Therefore, make the inode attribute fork structure part of struct xfs_inode, at a cost of 40 more bytes. This patch adds a clunky if_present field where necessary to maintain the existing logic of xattr fork null pointer testing in the existing codebase. The next patch switches the logic over to XFS_IFORK_Q and it all goes away. Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2022-07-10 01:56:06 +08:00
((char *)sfe >= ((char *)sf + dp->i_af.if_bytes)))) {
XFS_CORRUPTION_ERROR("xfs_attr_shortform_list",
XFS_ERRLEVEL_LOW,
context->dp->i_mount, sfe,
sizeof(*sfe));
kmem_free(sbuf);
return -EFSCORRUPTED;
}
sbp->entno = i;
sbp->hash = xfs_da_hashname(sfe->nameval, sfe->namelen);
sbp->name = sfe->nameval;
sbp->namelen = sfe->namelen;
/* These are bytes, and both on-disk, don't endian-flip */
sbp->valuelen = sfe->valuelen;
sbp->flags = sfe->flags;
sfe = xfs_attr_sf_nextentry(sfe);
sbp++;
nsbuf++;
}
/*
* Sort the entries on hash then entno.
*/
xfs_sort(sbuf, nsbuf, sizeof(*sbuf), xfs_attr_shortform_compare);
/*
* Re-find our place IN THE SORTED LIST.
*/
count = 0;
cursor->initted = 1;
cursor->blkno = 0;
for (sbp = sbuf, i = 0; i < nsbuf; i++, sbp++) {
if (sbp->hash == cursor->hashval) {
if (cursor->offset == count) {
break;
}
count++;
} else if (sbp->hash > cursor->hashval) {
break;
}
}
if (i == nsbuf)
goto out;
/*
* Loop putting entries into the user buffer.
*/
for ( ; i < nsbuf; i++, sbp++) {
if (cursor->hashval != sbp->hash) {
cursor->hashval = sbp->hash;
cursor->offset = 0;
}
if (XFS_IS_CORRUPT(context->dp->i_mount,
!xfs_attr_namecheck(sbp->name,
sbp->namelen))) {
error = -EFSCORRUPTED;
goto out;
}
context->put_listent(context,
sbp->flags,
sbp->name,
sbp->namelen,
sbp->valuelen);
if (context->seen_enough)
break;
cursor->offset++;
}
out:
kmem_free(sbuf);
return error;
}
/*
* We didn't find the block & hash mentioned in the cursor state, so
* walk down the attr btree looking for the hash.
*/
STATIC int
xfs_attr_node_list_lookup(
struct xfs_attr_list_context *context,
struct xfs_attrlist_cursor_kern *cursor,
struct xfs_buf **pbp)
{
struct xfs_da3_icnode_hdr nodehdr;
struct xfs_da_intnode *node;
struct xfs_da_node_entry *btree;
struct xfs_inode *dp = context->dp;
struct xfs_mount *mp = dp->i_mount;
struct xfs_trans *tp = context->tp;
struct xfs_buf *bp;
int i;
int error = 0;
unsigned int expected_level = 0;
uint16_t magic;
ASSERT(*pbp == NULL);
cursor->blkno = 0;
for (;;) {
error = xfs_da3_node_read(tp, dp, cursor->blkno, &bp,
XFS_ATTR_FORK);
if (error)
return error;
node = bp->b_addr;
magic = be16_to_cpu(node->hdr.info.magic);
if (magic == XFS_ATTR_LEAF_MAGIC ||
magic == XFS_ATTR3_LEAF_MAGIC)
break;
if (magic != XFS_DA_NODE_MAGIC &&
magic != XFS_DA3_NODE_MAGIC) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
node, sizeof(*node));
goto out_corruptbuf;
}
xfs_da3_node_hdr_from_disk(mp, &nodehdr, node);
/* Tree taller than we can handle; bail out! */
if (nodehdr.level >= XFS_DA_NODE_MAXDEPTH)
goto out_corruptbuf;
/* Check the level from the root node. */
if (cursor->blkno == 0)
expected_level = nodehdr.level - 1;
else if (expected_level != nodehdr.level)
goto out_corruptbuf;
else
expected_level--;
btree = nodehdr.btree;
for (i = 0; i < nodehdr.count; btree++, i++) {
if (cursor->hashval <= be32_to_cpu(btree->hashval)) {
cursor->blkno = be32_to_cpu(btree->before);
trace_xfs_attr_list_node_descend(context,
btree);
break;
}
}
xfs_trans_brelse(tp, bp);
if (i == nodehdr.count)
return 0;
/* We can't point back to the root. */
if (XFS_IS_CORRUPT(mp, cursor->blkno == 0))
return -EFSCORRUPTED;
}
if (expected_level != 0)
goto out_corruptbuf;
*pbp = bp;
return 0;
out_corruptbuf:
xfs_buf_mark_corrupt(bp);
xfs_trans_brelse(tp, bp);
return -EFSCORRUPTED;
}
STATIC int
xfs_attr_node_list(
struct xfs_attr_list_context *context)
{
struct xfs_attrlist_cursor_kern *cursor = &context->cursor;
struct xfs_attr3_icleaf_hdr leafhdr;
struct xfs_attr_leafblock *leaf;
struct xfs_da_intnode *node;
struct xfs_buf *bp;
struct xfs_inode *dp = context->dp;
struct xfs_mount *mp = dp->i_mount;
int error = 0;
trace_xfs_attr_node_list(context);
cursor->initted = 1;
/*
* Do all sorts of validation on the passed-in cursor structure.
* If anything is amiss, ignore the cursor and look up the hashval
* starting from the btree root.
*/
bp = NULL;
if (cursor->blkno > 0) {
error = xfs_da3_node_read(context->tp, dp, cursor->blkno, &bp,
XFS_ATTR_FORK);
if ((error != 0) && (error != -EFSCORRUPTED))
return error;
if (bp) {
struct xfs_attr_leaf_entry *entries;
node = bp->b_addr;
switch (be16_to_cpu(node->hdr.info.magic)) {
case XFS_DA_NODE_MAGIC:
case XFS_DA3_NODE_MAGIC:
trace_xfs_attr_list_wrong_blk(context);
xfs_trans_brelse(context->tp, bp);
bp = NULL;
break;
case XFS_ATTR_LEAF_MAGIC:
case XFS_ATTR3_LEAF_MAGIC:
leaf = bp->b_addr;
xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo,
&leafhdr, leaf);
entries = xfs_attr3_leaf_entryp(leaf);
if (cursor->hashval > be32_to_cpu(
entries[leafhdr.count - 1].hashval)) {
trace_xfs_attr_list_wrong_blk(context);
xfs_trans_brelse(context->tp, bp);
bp = NULL;
} else if (cursor->hashval <= be32_to_cpu(
entries[0].hashval)) {
trace_xfs_attr_list_wrong_blk(context);
xfs_trans_brelse(context->tp, bp);
bp = NULL;
}
break;
default:
trace_xfs_attr_list_wrong_blk(context);
xfs_trans_brelse(context->tp, bp);
bp = NULL;
}
}
}
/*
* We did not find what we expected given the cursor's contents,
* so we start from the top and work down based on the hash value.
* Note that start of node block is same as start of leaf block.
*/
if (bp == NULL) {
error = xfs_attr_node_list_lookup(context, cursor, &bp);
if (error || !bp)
return error;
}
ASSERT(bp != NULL);
/*
* Roll upward through the blocks, processing each leaf block in
* order. As long as there is space in the result buffer, keep
* adding the information.
*/
for (;;) {
leaf = bp->b_addr;
error = xfs_attr3_leaf_list_int(bp, context);
if (error)
break;
xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf);
if (context->seen_enough || leafhdr.forw == 0)
break;
cursor->blkno = leafhdr.forw;
xfs_trans_brelse(context->tp, bp);
error = xfs_attr3_leaf_read(context->tp, dp, cursor->blkno,
&bp);
if (error)
return error;
}
xfs_trans_brelse(context->tp, bp);
return error;
}
/*
* Copy out attribute list entries for attr_list(), for leaf attribute lists.
*/
int
xfs_attr3_leaf_list_int(
struct xfs_buf *bp,
struct xfs_attr_list_context *context)
{
struct xfs_attrlist_cursor_kern *cursor = &context->cursor;
struct xfs_attr_leafblock *leaf;
struct xfs_attr3_icleaf_hdr ichdr;
struct xfs_attr_leaf_entry *entries;
struct xfs_attr_leaf_entry *entry;
int i;
struct xfs_mount *mp = context->dp->i_mount;
trace_xfs_attr_list_leaf(context);
leaf = bp->b_addr;
xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf);
entries = xfs_attr3_leaf_entryp(leaf);
cursor->initted = 1;
/*
* Re-find our place in the leaf block if this is a new syscall.
*/
if (context->resynch) {
entry = &entries[0];
for (i = 0; i < ichdr.count; entry++, i++) {
if (be32_to_cpu(entry->hashval) == cursor->hashval) {
if (cursor->offset == context->dupcnt) {
context->dupcnt = 0;
break;
}
context->dupcnt++;
} else if (be32_to_cpu(entry->hashval) >
cursor->hashval) {
context->dupcnt = 0;
break;
}
}
if (i == ichdr.count) {
trace_xfs_attr_list_notfound(context);
return 0;
}
} else {
entry = &entries[0];
i = 0;
}
context->resynch = 0;
/*
* We have found our place, start copying out the new attributes.
*/
for (; i < ichdr.count; entry++, i++) {
char *name;
int namelen, valuelen;
if (be32_to_cpu(entry->hashval) != cursor->hashval) {
cursor->hashval = be32_to_cpu(entry->hashval);
cursor->offset = 0;
}
if ((entry->flags & XFS_ATTR_INCOMPLETE) &&
!context->allow_incomplete)
continue;
if (entry->flags & XFS_ATTR_LOCAL) {
xfs_attr_leaf_name_local_t *name_loc;
name_loc = xfs_attr3_leaf_name_local(leaf, i);
name = name_loc->nameval;
namelen = name_loc->namelen;
valuelen = be16_to_cpu(name_loc->valuelen);
} else {
xfs_attr_leaf_name_remote_t *name_rmt;
name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
name = name_rmt->name;
namelen = name_rmt->namelen;
valuelen = be32_to_cpu(name_rmt->valuelen);
}
if (XFS_IS_CORRUPT(context->dp->i_mount,
!xfs_attr_namecheck(name, namelen)))
return -EFSCORRUPTED;
context->put_listent(context, entry->flags,
name, namelen, valuelen);
if (context->seen_enough)
break;
cursor->offset++;
}
trace_xfs_attr_list_leaf_end(context);
return 0;
}
/*
* Copy out attribute entries for attr_list(), for leaf attribute lists.
*/
STATIC int
xfs_attr_leaf_list(
struct xfs_attr_list_context *context)
{
struct xfs_buf *bp;
int error;
trace_xfs_attr_leaf_list(context);
context->cursor.blkno = 0;
error = xfs_attr3_leaf_read(context->tp, context->dp, 0, &bp);
if (error)
return error;
error = xfs_attr3_leaf_list_int(bp, context);
xfs_trans_brelse(context->tp, bp);
return error;
}
int
xfs_attr_list_ilocked(
struct xfs_attr_list_context *context)
{
struct xfs_inode *dp = context->dp;
ASSERT(xfs_isilocked(dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
/*
* Decide on what work routines to call based on the inode size.
*/
if (!xfs_inode_hasattr(dp))
return 0;
xfs: make inode attribute forks a permanent part of struct xfs_inode Syzkaller reported a UAF bug a while back: ================================================================== BUG: KASAN: use-after-free in xfs_ilock_attr_map_shared+0xe3/0xf6 fs/xfs/xfs_inode.c:127 Read of size 4 at addr ffff88802cec919c by task syz-executor262/2958 CPU: 2 PID: 2958 Comm: syz-executor262 Not tainted 5.15.0-0.30.3-20220406_1406 #3 Hardware name: Red Hat KVM, BIOS 1.13.0-2.module+el8.3.0+7860+a7792d29 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x82/0xa9 lib/dump_stack.c:106 print_address_description.constprop.9+0x21/0x2d5 mm/kasan/report.c:256 __kasan_report mm/kasan/report.c:442 [inline] kasan_report.cold.14+0x7f/0x11b mm/kasan/report.c:459 xfs_ilock_attr_map_shared+0xe3/0xf6 fs/xfs/xfs_inode.c:127 xfs_attr_get+0x378/0x4c2 fs/xfs/libxfs/xfs_attr.c:159 xfs_xattr_get+0xe3/0x150 fs/xfs/xfs_xattr.c:36 __vfs_getxattr+0xdf/0x13d fs/xattr.c:399 cap_inode_need_killpriv+0x41/0x5d security/commoncap.c:300 security_inode_need_killpriv+0x4c/0x97 security/security.c:1408 dentry_needs_remove_privs.part.28+0x21/0x63 fs/inode.c:1912 dentry_needs_remove_privs+0x80/0x9e fs/inode.c:1908 do_truncate+0xc3/0x1e0 fs/open.c:56 handle_truncate fs/namei.c:3084 [inline] do_open fs/namei.c:3432 [inline] path_openat+0x30ab/0x396d fs/namei.c:3561 do_filp_open+0x1c4/0x290 fs/namei.c:3588 do_sys_openat2+0x60d/0x98c fs/open.c:1212 do_sys_open+0xcf/0x13c fs/open.c:1228 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x7e arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0x0 RIP: 0033:0x7f7ef4bb753d Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 1b 79 2c 00 f7 d8 64 89 01 48 RSP: 002b:00007f7ef52c2ed8 EFLAGS: 00000246 ORIG_RAX: 0000000000000055 RAX: ffffffffffffffda RBX: 0000000000404148 RCX: 00007f7ef4bb753d RDX: 00007f7ef4bb753d RSI: 0000000000000000 RDI: 0000000020004fc0 RBP: 0000000000404140 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0030656c69662f2e R13: 00007ffd794db37f R14: 00007ffd794db470 R15: 00007f7ef52c2fc0 </TASK> Allocated by task 2953: kasan_save_stack+0x19/0x38 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:46 [inline] set_alloc_info mm/kasan/common.c:434 [inline] __kasan_slab_alloc+0x68/0x7c mm/kasan/common.c:467 kasan_slab_alloc include/linux/kasan.h:254 [inline] slab_post_alloc_hook mm/slab.h:519 [inline] slab_alloc_node mm/slub.c:3213 [inline] slab_alloc mm/slub.c:3221 [inline] kmem_cache_alloc+0x11b/0x3eb mm/slub.c:3226 kmem_cache_zalloc include/linux/slab.h:711 [inline] xfs_ifork_alloc+0x25/0xa2 fs/xfs/libxfs/xfs_inode_fork.c:287 xfs_bmap_add_attrfork+0x3f2/0x9b1 fs/xfs/libxfs/xfs_bmap.c:1098 xfs_attr_set+0xe38/0x12a7 fs/xfs/libxfs/xfs_attr.c:746 xfs_xattr_set+0xeb/0x1a9 fs/xfs/xfs_xattr.c:59 __vfs_setxattr+0x11b/0x177 fs/xattr.c:180 __vfs_setxattr_noperm+0x128/0x5e0 fs/xattr.c:214 __vfs_setxattr_locked+0x1d4/0x258 fs/xattr.c:275 vfs_setxattr+0x154/0x33d fs/xattr.c:301 setxattr+0x216/0x29f fs/xattr.c:575 __do_sys_fsetxattr fs/xattr.c:632 [inline] __se_sys_fsetxattr fs/xattr.c:621 [inline] __x64_sys_fsetxattr+0x243/0x2fe fs/xattr.c:621 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x7e arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0x0 Freed by task 2949: kasan_save_stack+0x19/0x38 mm/kasan/common.c:38 kasan_set_track+0x1c/0x21 mm/kasan/common.c:46 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:360 ____kasan_slab_free mm/kasan/common.c:366 [inline] ____kasan_slab_free mm/kasan/common.c:328 [inline] __kasan_slab_free+0xe2/0x10e mm/kasan/common.c:374 kasan_slab_free include/linux/kasan.h:230 [inline] slab_free_hook mm/slub.c:1700 [inline] slab_free_freelist_hook mm/slub.c:1726 [inline] slab_free mm/slub.c:3492 [inline] kmem_cache_free+0xdc/0x3ce mm/slub.c:3508 xfs_attr_fork_remove+0x8d/0x132 fs/xfs/libxfs/xfs_attr_leaf.c:773 xfs_attr_sf_removename+0x5dd/0x6cb fs/xfs/libxfs/xfs_attr_leaf.c:822 xfs_attr_remove_iter+0x68c/0x805 fs/xfs/libxfs/xfs_attr.c:1413 xfs_attr_remove_args+0xb1/0x10d fs/xfs/libxfs/xfs_attr.c:684 xfs_attr_set+0xf1e/0x12a7 fs/xfs/libxfs/xfs_attr.c:802 xfs_xattr_set+0xeb/0x1a9 fs/xfs/xfs_xattr.c:59 __vfs_removexattr+0x106/0x16a fs/xattr.c:468 cap_inode_killpriv+0x24/0x47 security/commoncap.c:324 security_inode_killpriv+0x54/0xa1 security/security.c:1414 setattr_prepare+0x1a6/0x897 fs/attr.c:146 xfs_vn_change_ok+0x111/0x15e fs/xfs/xfs_iops.c:682 xfs_vn_setattr_size+0x5f/0x15a fs/xfs/xfs_iops.c:1065 xfs_vn_setattr+0x125/0x2ad fs/xfs/xfs_iops.c:1093 notify_change+0xae5/0x10a1 fs/attr.c:410 do_truncate+0x134/0x1e0 fs/open.c:64 handle_truncate fs/namei.c:3084 [inline] do_open fs/namei.c:3432 [inline] path_openat+0x30ab/0x396d fs/namei.c:3561 do_filp_open+0x1c4/0x290 fs/namei.c:3588 do_sys_openat2+0x60d/0x98c fs/open.c:1212 do_sys_open+0xcf/0x13c fs/open.c:1228 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x7e arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0x0 The buggy address belongs to the object at ffff88802cec9188 which belongs to the cache xfs_ifork of size 40 The buggy address is located 20 bytes inside of 40-byte region [ffff88802cec9188, ffff88802cec91b0) The buggy address belongs to the page: page:00000000c3af36a1 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x2cec9 flags: 0xfffffc0000200(slab|node=0|zone=1|lastcpupid=0x1fffff) raw: 000fffffc0000200 ffffea00009d2580 0000000600000006 ffff88801a9ffc80 raw: 0000000000000000 0000000080490049 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88802cec9080: fb fb fb fc fc fa fb fb fb fb fc fc fb fb fb fb ffff88802cec9100: fb fc fc fb fb fb fb fb fc fc fb fb fb fb fb fc >ffff88802cec9180: fc fa fb fb fb fb fc fc fa fb fb fb fb fc fc fb ^ ffff88802cec9200: fb fb fb fb fc fc fb fb fb fb fb fc fc fb fb fb ffff88802cec9280: fb fb fc fc fa fb fb fb fb fc fc fa fb fb fb fb ================================================================== The root cause of this bug is the unlocked access to xfs_inode.i_afp from the getxattr code paths while trying to determine which ILOCK mode to use to stabilize the xattr data. Unfortunately, the VFS does not acquire i_rwsem when vfs_getxattr (or listxattr) call into the filesystem, which means that getxattr can race with a removexattr that's tearing down the attr fork and crash: xfs_attr_set: xfs_attr_get: xfs_attr_fork_remove: xfs_ilock_attr_map_shared: xfs_idestroy_fork(ip->i_afp); kmem_cache_free(xfs_ifork_cache, ip->i_afp); if (ip->i_afp && ip->i_afp = NULL; xfs_need_iread_extents(ip->i_afp)) <KABOOM> ip->i_forkoff = 0; Regrettably, the VFS is much more lax about i_rwsem and getxattr than is immediately obvious -- not only does it not guarantee that we hold i_rwsem, it actually doesn't guarantee that we *don't* hold it either. The getxattr system call won't acquire the lock before calling XFS, but the file capabilities code calls getxattr with and without i_rwsem held to determine if the "security.capabilities" xattr is set on the file. Fixing the VFS locking requires a treewide investigation into every code path that could touch an xattr and what i_rwsem state it expects or sets up. That could take years or even prove impossible; fortunately, we can fix this UAF problem inside XFS. An earlier version of this patch used smp_wmb in xfs_attr_fork_remove to ensure that i_forkoff is always zeroed before i_afp is set to null and changed the read paths to use smp_rmb before accessing i_forkoff and i_afp, which avoided these UAF problems. However, the patch author was too busy dealing with other problems in the meantime, and by the time he came back to this issue, the situation had changed a bit. On a modern system with selinux, each inode will always have at least one xattr for the selinux label, so it doesn't make much sense to keep incurring the extra pointer dereference. Furthermore, Allison's upcoming parent pointer patchset will also cause nearly every inode in the filesystem to have extended attributes. Therefore, make the inode attribute fork structure part of struct xfs_inode, at a cost of 40 more bytes. This patch adds a clunky if_present field where necessary to maintain the existing logic of xattr fork null pointer testing in the existing codebase. The next patch switches the logic over to XFS_IFORK_Q and it all goes away. Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2022-07-10 01:56:06 +08:00
if (dp->i_af.if_format == XFS_DINODE_FMT_LOCAL)
return xfs_attr_shortform_list(context);
if (xfs_attr_is_leaf(dp))
return xfs_attr_leaf_list(context);
return xfs_attr_node_list(context);
}
int
xfs_attr_list(
struct xfs_attr_list_context *context)
{
struct xfs_inode *dp = context->dp;
uint lock_mode;
int error;
XFS_STATS_INC(dp->i_mount, xs_attr_list);
if (xfs_is_shutdown(dp->i_mount))
return -EIO;
lock_mode = xfs_ilock_attr_map_shared(dp);
error = xfs_attr_list_ilocked(context);
xfs_iunlock(dp, lock_mode);
return error;
}