mirror of
https://github.com/tbsdtv/linux_media.git
synced 2025-07-23 20:51:03 +02:00
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>
789 lines
20 KiB
C
789 lines
20 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Copyright (c) 2000-2006 Silicon Graphics, 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_inode.h"
|
|
#include "xfs_trans.h"
|
|
#include "xfs_inode_item.h"
|
|
#include "xfs_btree.h"
|
|
#include "xfs_bmap_btree.h"
|
|
#include "xfs_bmap.h"
|
|
#include "xfs_error.h"
|
|
#include "xfs_trace.h"
|
|
#include "xfs_da_format.h"
|
|
#include "xfs_da_btree.h"
|
|
#include "xfs_dir2_priv.h"
|
|
#include "xfs_attr_leaf.h"
|
|
#include "xfs_types.h"
|
|
#include "xfs_errortag.h"
|
|
|
|
struct kmem_cache *xfs_ifork_cache;
|
|
|
|
void
|
|
xfs_init_local_fork(
|
|
struct xfs_inode *ip,
|
|
int whichfork,
|
|
const void *data,
|
|
int64_t size)
|
|
{
|
|
struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
|
|
int mem_size = size;
|
|
bool zero_terminate;
|
|
|
|
/*
|
|
* If we are using the local fork to store a symlink body we need to
|
|
* zero-terminate it so that we can pass it back to the VFS directly.
|
|
* Overallocate the in-memory fork by one for that and add a zero
|
|
* to terminate it below.
|
|
*/
|
|
zero_terminate = S_ISLNK(VFS_I(ip)->i_mode);
|
|
if (zero_terminate)
|
|
mem_size++;
|
|
|
|
if (size) {
|
|
ifp->if_u1.if_data = kmem_alloc(mem_size, KM_NOFS);
|
|
memcpy(ifp->if_u1.if_data, data, size);
|
|
if (zero_terminate)
|
|
ifp->if_u1.if_data[size] = '\0';
|
|
} else {
|
|
ifp->if_u1.if_data = NULL;
|
|
}
|
|
|
|
ifp->if_bytes = size;
|
|
}
|
|
|
|
/*
|
|
* The file is in-lined in the on-disk inode.
|
|
*/
|
|
STATIC int
|
|
xfs_iformat_local(
|
|
struct xfs_inode *ip,
|
|
struct xfs_dinode *dip,
|
|
int whichfork,
|
|
int size)
|
|
{
|
|
/*
|
|
* If the size is unreasonable, then something
|
|
* is wrong and we just bail out rather than crash in
|
|
* kmem_alloc() or memcpy() below.
|
|
*/
|
|
if (unlikely(size > XFS_DFORK_SIZE(dip, ip->i_mount, whichfork))) {
|
|
xfs_warn(ip->i_mount,
|
|
"corrupt inode %Lu (bad size %d for local fork, size = %zd).",
|
|
(unsigned long long) ip->i_ino, size,
|
|
XFS_DFORK_SIZE(dip, ip->i_mount, whichfork));
|
|
xfs_inode_verifier_error(ip, -EFSCORRUPTED,
|
|
"xfs_iformat_local", dip, sizeof(*dip),
|
|
__this_address);
|
|
return -EFSCORRUPTED;
|
|
}
|
|
|
|
xfs_init_local_fork(ip, whichfork, XFS_DFORK_PTR(dip, whichfork), size);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* The file consists of a set of extents all of which fit into the on-disk
|
|
* inode.
|
|
*/
|
|
STATIC int
|
|
xfs_iformat_extents(
|
|
struct xfs_inode *ip,
|
|
struct xfs_dinode *dip,
|
|
int whichfork)
|
|
{
|
|
struct xfs_mount *mp = ip->i_mount;
|
|
struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
|
|
int state = xfs_bmap_fork_to_state(whichfork);
|
|
xfs_extnum_t nex = xfs_dfork_nextents(dip, whichfork);
|
|
int size = nex * sizeof(xfs_bmbt_rec_t);
|
|
struct xfs_iext_cursor icur;
|
|
struct xfs_bmbt_rec *dp;
|
|
struct xfs_bmbt_irec new;
|
|
int i;
|
|
|
|
/*
|
|
* If the number of extents is unreasonable, then something is wrong and
|
|
* we just bail out rather than crash in kmem_alloc() or memcpy() below.
|
|
*/
|
|
if (unlikely(size < 0 || size > XFS_DFORK_SIZE(dip, mp, whichfork))) {
|
|
xfs_warn(ip->i_mount, "corrupt inode %llu ((a)extents = %llu).",
|
|
ip->i_ino, nex);
|
|
xfs_inode_verifier_error(ip, -EFSCORRUPTED,
|
|
"xfs_iformat_extents(1)", dip, sizeof(*dip),
|
|
__this_address);
|
|
return -EFSCORRUPTED;
|
|
}
|
|
|
|
ifp->if_bytes = 0;
|
|
ifp->if_u1.if_root = NULL;
|
|
ifp->if_height = 0;
|
|
if (size) {
|
|
dp = (xfs_bmbt_rec_t *) XFS_DFORK_PTR(dip, whichfork);
|
|
|
|
xfs_iext_first(ifp, &icur);
|
|
for (i = 0; i < nex; i++, dp++) {
|
|
xfs_failaddr_t fa;
|
|
|
|
xfs_bmbt_disk_get_all(dp, &new);
|
|
fa = xfs_bmap_validate_extent(ip, whichfork, &new);
|
|
if (fa) {
|
|
xfs_inode_verifier_error(ip, -EFSCORRUPTED,
|
|
"xfs_iformat_extents(2)",
|
|
dp, sizeof(*dp), fa);
|
|
return -EFSCORRUPTED;
|
|
}
|
|
|
|
xfs_iext_insert(ip, &icur, &new, state);
|
|
trace_xfs_read_extent(ip, &icur, state, _THIS_IP_);
|
|
xfs_iext_next(ifp, &icur);
|
|
}
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* The file has too many extents to fit into
|
|
* the inode, so they are in B-tree format.
|
|
* Allocate a buffer for the root of the B-tree
|
|
* and copy the root into it. The i_extents
|
|
* field will remain NULL until all of the
|
|
* extents are read in (when they are needed).
|
|
*/
|
|
STATIC int
|
|
xfs_iformat_btree(
|
|
struct xfs_inode *ip,
|
|
struct xfs_dinode *dip,
|
|
int whichfork)
|
|
{
|
|
struct xfs_mount *mp = ip->i_mount;
|
|
xfs_bmdr_block_t *dfp;
|
|
struct xfs_ifork *ifp;
|
|
/* REFERENCED */
|
|
int nrecs;
|
|
int size;
|
|
int level;
|
|
|
|
ifp = xfs_ifork_ptr(ip, whichfork);
|
|
dfp = (xfs_bmdr_block_t *)XFS_DFORK_PTR(dip, whichfork);
|
|
size = XFS_BMAP_BROOT_SPACE(mp, dfp);
|
|
nrecs = be16_to_cpu(dfp->bb_numrecs);
|
|
level = be16_to_cpu(dfp->bb_level);
|
|
|
|
/*
|
|
* blow out if -- fork has less extents than can fit in
|
|
* fork (fork shouldn't be a btree format), root btree
|
|
* block has more records than can fit into the fork,
|
|
* or the number of extents is greater than the number of
|
|
* blocks.
|
|
*/
|
|
if (unlikely(ifp->if_nextents <= XFS_IFORK_MAXEXT(ip, whichfork) ||
|
|
nrecs == 0 ||
|
|
XFS_BMDR_SPACE_CALC(nrecs) >
|
|
XFS_DFORK_SIZE(dip, mp, whichfork) ||
|
|
ifp->if_nextents > ip->i_nblocks) ||
|
|
level == 0 || level > XFS_BM_MAXLEVELS(mp, whichfork)) {
|
|
xfs_warn(mp, "corrupt inode %Lu (btree).",
|
|
(unsigned long long) ip->i_ino);
|
|
xfs_inode_verifier_error(ip, -EFSCORRUPTED,
|
|
"xfs_iformat_btree", dfp, size,
|
|
__this_address);
|
|
return -EFSCORRUPTED;
|
|
}
|
|
|
|
ifp->if_broot_bytes = size;
|
|
ifp->if_broot = kmem_alloc(size, KM_NOFS);
|
|
ASSERT(ifp->if_broot != NULL);
|
|
/*
|
|
* Copy and convert from the on-disk structure
|
|
* to the in-memory structure.
|
|
*/
|
|
xfs_bmdr_to_bmbt(ip, dfp, XFS_DFORK_SIZE(dip, ip->i_mount, whichfork),
|
|
ifp->if_broot, size);
|
|
|
|
ifp->if_bytes = 0;
|
|
ifp->if_u1.if_root = NULL;
|
|
ifp->if_height = 0;
|
|
return 0;
|
|
}
|
|
|
|
int
|
|
xfs_iformat_data_fork(
|
|
struct xfs_inode *ip,
|
|
struct xfs_dinode *dip)
|
|
{
|
|
struct inode *inode = VFS_I(ip);
|
|
int error;
|
|
|
|
/*
|
|
* Initialize the extent count early, as the per-format routines may
|
|
* depend on it.
|
|
*/
|
|
ip->i_df.if_format = dip->di_format;
|
|
ip->i_df.if_nextents = xfs_dfork_data_extents(dip);
|
|
|
|
switch (inode->i_mode & S_IFMT) {
|
|
case S_IFIFO:
|
|
case S_IFCHR:
|
|
case S_IFBLK:
|
|
case S_IFSOCK:
|
|
ip->i_disk_size = 0;
|
|
inode->i_rdev = xfs_to_linux_dev_t(xfs_dinode_get_rdev(dip));
|
|
return 0;
|
|
case S_IFREG:
|
|
case S_IFLNK:
|
|
case S_IFDIR:
|
|
switch (ip->i_df.if_format) {
|
|
case XFS_DINODE_FMT_LOCAL:
|
|
error = xfs_iformat_local(ip, dip, XFS_DATA_FORK,
|
|
be64_to_cpu(dip->di_size));
|
|
if (!error)
|
|
error = xfs_ifork_verify_local_data(ip);
|
|
return error;
|
|
case XFS_DINODE_FMT_EXTENTS:
|
|
return xfs_iformat_extents(ip, dip, XFS_DATA_FORK);
|
|
case XFS_DINODE_FMT_BTREE:
|
|
return xfs_iformat_btree(ip, dip, XFS_DATA_FORK);
|
|
default:
|
|
xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__,
|
|
dip, sizeof(*dip), __this_address);
|
|
return -EFSCORRUPTED;
|
|
}
|
|
break;
|
|
default:
|
|
xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip,
|
|
sizeof(*dip), __this_address);
|
|
return -EFSCORRUPTED;
|
|
}
|
|
}
|
|
|
|
static uint16_t
|
|
xfs_dfork_attr_shortform_size(
|
|
struct xfs_dinode *dip)
|
|
{
|
|
struct xfs_attr_shortform *atp =
|
|
(struct xfs_attr_shortform *)XFS_DFORK_APTR(dip);
|
|
|
|
return be16_to_cpu(atp->hdr.totsize);
|
|
}
|
|
|
|
void
|
|
xfs_ifork_init_attr(
|
|
struct xfs_inode *ip,
|
|
enum xfs_dinode_fmt format,
|
|
xfs_extnum_t nextents)
|
|
{
|
|
ASSERT(!ip->i_af.if_present);
|
|
|
|
ip->i_af.if_present = 1;
|
|
ip->i_af.if_format = format;
|
|
ip->i_af.if_nextents = nextents;
|
|
}
|
|
|
|
void
|
|
xfs_ifork_zap_attr(
|
|
struct xfs_inode *ip)
|
|
{
|
|
ASSERT(ip->i_af.if_present);
|
|
ASSERT(ip->i_af.if_broot == NULL);
|
|
ASSERT(ip->i_af.if_u1.if_data == NULL);
|
|
ASSERT(ip->i_af.if_height == 0);
|
|
|
|
memset(&ip->i_af, 0, sizeof(struct xfs_ifork));
|
|
ip->i_af.if_format = XFS_DINODE_FMT_EXTENTS;
|
|
}
|
|
|
|
int
|
|
xfs_iformat_attr_fork(
|
|
struct xfs_inode *ip,
|
|
struct xfs_dinode *dip)
|
|
{
|
|
xfs_extnum_t naextents = xfs_dfork_attr_extents(dip);
|
|
int error = 0;
|
|
|
|
/*
|
|
* Initialize the extent count early, as the per-format routines may
|
|
* depend on it.
|
|
*/
|
|
xfs_ifork_init_attr(ip, dip->di_aformat, naextents);
|
|
|
|
switch (ip->i_af.if_format) {
|
|
case XFS_DINODE_FMT_LOCAL:
|
|
error = xfs_iformat_local(ip, dip, XFS_ATTR_FORK,
|
|
xfs_dfork_attr_shortform_size(dip));
|
|
if (!error)
|
|
error = xfs_ifork_verify_local_attr(ip);
|
|
break;
|
|
case XFS_DINODE_FMT_EXTENTS:
|
|
error = xfs_iformat_extents(ip, dip, XFS_ATTR_FORK);
|
|
break;
|
|
case XFS_DINODE_FMT_BTREE:
|
|
error = xfs_iformat_btree(ip, dip, XFS_ATTR_FORK);
|
|
break;
|
|
default:
|
|
xfs_inode_verifier_error(ip, error, __func__, dip,
|
|
sizeof(*dip), __this_address);
|
|
error = -EFSCORRUPTED;
|
|
break;
|
|
}
|
|
|
|
if (error)
|
|
xfs_ifork_zap_attr(ip);
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* Reallocate the space for if_broot based on the number of records
|
|
* being added or deleted as indicated in rec_diff. Move the records
|
|
* and pointers in if_broot to fit the new size. When shrinking this
|
|
* will eliminate holes between the records and pointers created by
|
|
* the caller. When growing this will create holes to be filled in
|
|
* by the caller.
|
|
*
|
|
* The caller must not request to add more records than would fit in
|
|
* the on-disk inode root. If the if_broot is currently NULL, then
|
|
* if we are adding records, one will be allocated. The caller must also
|
|
* not request that the number of records go below zero, although
|
|
* it can go to zero.
|
|
*
|
|
* ip -- the inode whose if_broot area is changing
|
|
* ext_diff -- the change in the number of records, positive or negative,
|
|
* requested for the if_broot array.
|
|
*/
|
|
void
|
|
xfs_iroot_realloc(
|
|
xfs_inode_t *ip,
|
|
int rec_diff,
|
|
int whichfork)
|
|
{
|
|
struct xfs_mount *mp = ip->i_mount;
|
|
int cur_max;
|
|
struct xfs_ifork *ifp;
|
|
struct xfs_btree_block *new_broot;
|
|
int new_max;
|
|
size_t new_size;
|
|
char *np;
|
|
char *op;
|
|
|
|
/*
|
|
* Handle the degenerate case quietly.
|
|
*/
|
|
if (rec_diff == 0) {
|
|
return;
|
|
}
|
|
|
|
ifp = xfs_ifork_ptr(ip, whichfork);
|
|
if (rec_diff > 0) {
|
|
/*
|
|
* If there wasn't any memory allocated before, just
|
|
* allocate it now and get out.
|
|
*/
|
|
if (ifp->if_broot_bytes == 0) {
|
|
new_size = XFS_BMAP_BROOT_SPACE_CALC(mp, rec_diff);
|
|
ifp->if_broot = kmem_alloc(new_size, KM_NOFS);
|
|
ifp->if_broot_bytes = (int)new_size;
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* If there is already an existing if_broot, then we need
|
|
* to realloc() it and shift the pointers to their new
|
|
* location. The records don't change location because
|
|
* they are kept butted up against the btree block header.
|
|
*/
|
|
cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, 0);
|
|
new_max = cur_max + rec_diff;
|
|
new_size = XFS_BMAP_BROOT_SPACE_CALC(mp, new_max);
|
|
ifp->if_broot = krealloc(ifp->if_broot, new_size,
|
|
GFP_NOFS | __GFP_NOFAIL);
|
|
op = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1,
|
|
ifp->if_broot_bytes);
|
|
np = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1,
|
|
(int)new_size);
|
|
ifp->if_broot_bytes = (int)new_size;
|
|
ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <=
|
|
XFS_IFORK_SIZE(ip, whichfork));
|
|
memmove(np, op, cur_max * (uint)sizeof(xfs_fsblock_t));
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* rec_diff is less than 0. In this case, we are shrinking the
|
|
* if_broot buffer. It must already exist. If we go to zero
|
|
* records, just get rid of the root and clear the status bit.
|
|
*/
|
|
ASSERT((ifp->if_broot != NULL) && (ifp->if_broot_bytes > 0));
|
|
cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, 0);
|
|
new_max = cur_max + rec_diff;
|
|
ASSERT(new_max >= 0);
|
|
if (new_max > 0)
|
|
new_size = XFS_BMAP_BROOT_SPACE_CALC(mp, new_max);
|
|
else
|
|
new_size = 0;
|
|
if (new_size > 0) {
|
|
new_broot = kmem_alloc(new_size, KM_NOFS);
|
|
/*
|
|
* First copy over the btree block header.
|
|
*/
|
|
memcpy(new_broot, ifp->if_broot,
|
|
XFS_BMBT_BLOCK_LEN(ip->i_mount));
|
|
} else {
|
|
new_broot = NULL;
|
|
}
|
|
|
|
/*
|
|
* Only copy the records and pointers if there are any.
|
|
*/
|
|
if (new_max > 0) {
|
|
/*
|
|
* First copy the records.
|
|
*/
|
|
op = (char *)XFS_BMBT_REC_ADDR(mp, ifp->if_broot, 1);
|
|
np = (char *)XFS_BMBT_REC_ADDR(mp, new_broot, 1);
|
|
memcpy(np, op, new_max * (uint)sizeof(xfs_bmbt_rec_t));
|
|
|
|
/*
|
|
* Then copy the pointers.
|
|
*/
|
|
op = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1,
|
|
ifp->if_broot_bytes);
|
|
np = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, new_broot, 1,
|
|
(int)new_size);
|
|
memcpy(np, op, new_max * (uint)sizeof(xfs_fsblock_t));
|
|
}
|
|
kmem_free(ifp->if_broot);
|
|
ifp->if_broot = new_broot;
|
|
ifp->if_broot_bytes = (int)new_size;
|
|
if (ifp->if_broot)
|
|
ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <=
|
|
XFS_IFORK_SIZE(ip, whichfork));
|
|
return;
|
|
}
|
|
|
|
|
|
/*
|
|
* This is called when the amount of space needed for if_data
|
|
* is increased or decreased. The change in size is indicated by
|
|
* the number of bytes that need to be added or deleted in the
|
|
* byte_diff parameter.
|
|
*
|
|
* If the amount of space needed has decreased below the size of the
|
|
* inline buffer, then switch to using the inline buffer. Otherwise,
|
|
* use kmem_realloc() or kmem_alloc() to adjust the size of the buffer
|
|
* to what is needed.
|
|
*
|
|
* ip -- the inode whose if_data area is changing
|
|
* byte_diff -- the change in the number of bytes, positive or negative,
|
|
* requested for the if_data array.
|
|
*/
|
|
void
|
|
xfs_idata_realloc(
|
|
struct xfs_inode *ip,
|
|
int64_t byte_diff,
|
|
int whichfork)
|
|
{
|
|
struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
|
|
int64_t new_size = ifp->if_bytes + byte_diff;
|
|
|
|
ASSERT(new_size >= 0);
|
|
ASSERT(new_size <= XFS_IFORK_SIZE(ip, whichfork));
|
|
|
|
if (byte_diff == 0)
|
|
return;
|
|
|
|
if (new_size == 0) {
|
|
kmem_free(ifp->if_u1.if_data);
|
|
ifp->if_u1.if_data = NULL;
|
|
ifp->if_bytes = 0;
|
|
return;
|
|
}
|
|
|
|
ifp->if_u1.if_data = krealloc(ifp->if_u1.if_data, new_size,
|
|
GFP_NOFS | __GFP_NOFAIL);
|
|
ifp->if_bytes = new_size;
|
|
}
|
|
|
|
void
|
|
xfs_idestroy_fork(
|
|
struct xfs_ifork *ifp)
|
|
{
|
|
if (ifp->if_broot != NULL) {
|
|
kmem_free(ifp->if_broot);
|
|
ifp->if_broot = NULL;
|
|
}
|
|
|
|
switch (ifp->if_format) {
|
|
case XFS_DINODE_FMT_LOCAL:
|
|
kmem_free(ifp->if_u1.if_data);
|
|
ifp->if_u1.if_data = NULL;
|
|
break;
|
|
case XFS_DINODE_FMT_EXTENTS:
|
|
case XFS_DINODE_FMT_BTREE:
|
|
if (ifp->if_height)
|
|
xfs_iext_destroy(ifp);
|
|
break;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Convert in-core extents to on-disk form
|
|
*
|
|
* In the case of the data fork, the in-core and on-disk fork sizes can be
|
|
* different due to delayed allocation extents. We only copy on-disk extents
|
|
* here, so callers must always use the physical fork size to determine the
|
|
* size of the buffer passed to this routine. We will return the size actually
|
|
* used.
|
|
*/
|
|
int
|
|
xfs_iextents_copy(
|
|
struct xfs_inode *ip,
|
|
struct xfs_bmbt_rec *dp,
|
|
int whichfork)
|
|
{
|
|
int state = xfs_bmap_fork_to_state(whichfork);
|
|
struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
|
|
struct xfs_iext_cursor icur;
|
|
struct xfs_bmbt_irec rec;
|
|
int64_t copied = 0;
|
|
|
|
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED));
|
|
ASSERT(ifp->if_bytes > 0);
|
|
|
|
for_each_xfs_iext(ifp, &icur, &rec) {
|
|
if (isnullstartblock(rec.br_startblock))
|
|
continue;
|
|
ASSERT(xfs_bmap_validate_extent(ip, whichfork, &rec) == NULL);
|
|
xfs_bmbt_disk_set_all(dp, &rec);
|
|
trace_xfs_write_extent(ip, &icur, state, _RET_IP_);
|
|
copied += sizeof(struct xfs_bmbt_rec);
|
|
dp++;
|
|
}
|
|
|
|
ASSERT(copied > 0);
|
|
ASSERT(copied <= ifp->if_bytes);
|
|
return copied;
|
|
}
|
|
|
|
/*
|
|
* Each of the following cases stores data into the same region
|
|
* of the on-disk inode, so only one of them can be valid at
|
|
* any given time. While it is possible to have conflicting formats
|
|
* and log flags, e.g. having XFS_ILOG_?DATA set when the fork is
|
|
* in EXTENTS format, this can only happen when the fork has
|
|
* changed formats after being modified but before being flushed.
|
|
* In these cases, the format always takes precedence, because the
|
|
* format indicates the current state of the fork.
|
|
*/
|
|
void
|
|
xfs_iflush_fork(
|
|
struct xfs_inode *ip,
|
|
struct xfs_dinode *dip,
|
|
struct xfs_inode_log_item *iip,
|
|
int whichfork)
|
|
{
|
|
char *cp;
|
|
struct xfs_ifork *ifp;
|
|
xfs_mount_t *mp;
|
|
static const short brootflag[2] =
|
|
{ XFS_ILOG_DBROOT, XFS_ILOG_ABROOT };
|
|
static const short dataflag[2] =
|
|
{ XFS_ILOG_DDATA, XFS_ILOG_ADATA };
|
|
static const short extflag[2] =
|
|
{ XFS_ILOG_DEXT, XFS_ILOG_AEXT };
|
|
|
|
if (!iip)
|
|
return;
|
|
ifp = xfs_ifork_ptr(ip, whichfork);
|
|
/*
|
|
* This can happen if we gave up in iformat in an error path,
|
|
* for the attribute fork.
|
|
*/
|
|
if (!ifp) {
|
|
ASSERT(whichfork == XFS_ATTR_FORK);
|
|
return;
|
|
}
|
|
cp = XFS_DFORK_PTR(dip, whichfork);
|
|
mp = ip->i_mount;
|
|
switch (ifp->if_format) {
|
|
case XFS_DINODE_FMT_LOCAL:
|
|
if ((iip->ili_fields & dataflag[whichfork]) &&
|
|
(ifp->if_bytes > 0)) {
|
|
ASSERT(ifp->if_u1.if_data != NULL);
|
|
ASSERT(ifp->if_bytes <= XFS_IFORK_SIZE(ip, whichfork));
|
|
memcpy(cp, ifp->if_u1.if_data, ifp->if_bytes);
|
|
}
|
|
break;
|
|
|
|
case XFS_DINODE_FMT_EXTENTS:
|
|
if ((iip->ili_fields & extflag[whichfork]) &&
|
|
(ifp->if_bytes > 0)) {
|
|
ASSERT(ifp->if_nextents > 0);
|
|
(void)xfs_iextents_copy(ip, (xfs_bmbt_rec_t *)cp,
|
|
whichfork);
|
|
}
|
|
break;
|
|
|
|
case XFS_DINODE_FMT_BTREE:
|
|
if ((iip->ili_fields & brootflag[whichfork]) &&
|
|
(ifp->if_broot_bytes > 0)) {
|
|
ASSERT(ifp->if_broot != NULL);
|
|
ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <=
|
|
XFS_IFORK_SIZE(ip, whichfork));
|
|
xfs_bmbt_to_bmdr(mp, ifp->if_broot, ifp->if_broot_bytes,
|
|
(xfs_bmdr_block_t *)cp,
|
|
XFS_DFORK_SIZE(dip, mp, whichfork));
|
|
}
|
|
break;
|
|
|
|
case XFS_DINODE_FMT_DEV:
|
|
if (iip->ili_fields & XFS_ILOG_DEV) {
|
|
ASSERT(whichfork == XFS_DATA_FORK);
|
|
xfs_dinode_put_rdev(dip,
|
|
linux_to_xfs_dev_t(VFS_I(ip)->i_rdev));
|
|
}
|
|
break;
|
|
|
|
default:
|
|
ASSERT(0);
|
|
break;
|
|
}
|
|
}
|
|
|
|
/* Convert bmap state flags to an inode fork. */
|
|
struct xfs_ifork *
|
|
xfs_iext_state_to_fork(
|
|
struct xfs_inode *ip,
|
|
int state)
|
|
{
|
|
if (state & BMAP_COWFORK)
|
|
return ip->i_cowfp;
|
|
else if (state & BMAP_ATTRFORK)
|
|
return &ip->i_af;
|
|
return &ip->i_df;
|
|
}
|
|
|
|
/*
|
|
* Initialize an inode's copy-on-write fork.
|
|
*/
|
|
void
|
|
xfs_ifork_init_cow(
|
|
struct xfs_inode *ip)
|
|
{
|
|
if (ip->i_cowfp)
|
|
return;
|
|
|
|
ip->i_cowfp = kmem_cache_zalloc(xfs_ifork_cache,
|
|
GFP_NOFS | __GFP_NOFAIL);
|
|
ip->i_cowfp->if_present = 1;
|
|
ip->i_cowfp->if_format = XFS_DINODE_FMT_EXTENTS;
|
|
}
|
|
|
|
/* Verify the inline contents of the data fork of an inode. */
|
|
int
|
|
xfs_ifork_verify_local_data(
|
|
struct xfs_inode *ip)
|
|
{
|
|
xfs_failaddr_t fa = NULL;
|
|
|
|
switch (VFS_I(ip)->i_mode & S_IFMT) {
|
|
case S_IFDIR:
|
|
fa = xfs_dir2_sf_verify(ip);
|
|
break;
|
|
case S_IFLNK:
|
|
fa = xfs_symlink_shortform_verify(ip);
|
|
break;
|
|
default:
|
|
break;
|
|
}
|
|
|
|
if (fa) {
|
|
xfs_inode_verifier_error(ip, -EFSCORRUPTED, "data fork",
|
|
ip->i_df.if_u1.if_data, ip->i_df.if_bytes, fa);
|
|
return -EFSCORRUPTED;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
/* Verify the inline contents of the attr fork of an inode. */
|
|
int
|
|
xfs_ifork_verify_local_attr(
|
|
struct xfs_inode *ip)
|
|
{
|
|
struct xfs_ifork *ifp = &ip->i_af;
|
|
xfs_failaddr_t fa;
|
|
|
|
if (!ifp->if_present)
|
|
fa = __this_address;
|
|
else
|
|
fa = xfs_attr_shortform_verify(ip);
|
|
|
|
if (fa) {
|
|
xfs_inode_verifier_error(ip, -EFSCORRUPTED, "attr fork",
|
|
ifp ? ifp->if_u1.if_data : NULL,
|
|
ifp ? ifp->if_bytes : 0, fa);
|
|
return -EFSCORRUPTED;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
int
|
|
xfs_iext_count_may_overflow(
|
|
struct xfs_inode *ip,
|
|
int whichfork,
|
|
int nr_to_add)
|
|
{
|
|
struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
|
|
uint64_t max_exts;
|
|
uint64_t nr_exts;
|
|
|
|
if (whichfork == XFS_COW_FORK)
|
|
return 0;
|
|
|
|
max_exts = xfs_iext_max_nextents(xfs_inode_has_large_extent_counts(ip),
|
|
whichfork);
|
|
|
|
if (XFS_TEST_ERROR(false, ip->i_mount, XFS_ERRTAG_REDUCE_MAX_IEXTENTS))
|
|
max_exts = 10;
|
|
|
|
nr_exts = ifp->if_nextents + nr_to_add;
|
|
if (nr_exts < ifp->if_nextents || nr_exts > max_exts)
|
|
return -EFBIG;
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Upgrade this inode's extent counter fields to be able to handle a potential
|
|
* increase in the extent count by nr_to_add. Normally this is the same
|
|
* quantity that caused xfs_iext_count_may_overflow() to return -EFBIG.
|
|
*/
|
|
int
|
|
xfs_iext_count_upgrade(
|
|
struct xfs_trans *tp,
|
|
struct xfs_inode *ip,
|
|
uint nr_to_add)
|
|
{
|
|
ASSERT(nr_to_add <= XFS_MAX_EXTCNT_UPGRADE_NR);
|
|
|
|
if (!xfs_has_large_extent_counts(ip->i_mount) ||
|
|
xfs_inode_has_large_extent_counts(ip) ||
|
|
XFS_TEST_ERROR(false, ip->i_mount, XFS_ERRTAG_REDUCE_MAX_IEXTENTS))
|
|
return -EFBIG;
|
|
|
|
ip->i_diflags2 |= XFS_DIFLAG2_NREXT64;
|
|
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
|
|
|
|
return 0;
|
|
}
|