+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
* All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "libxfs_priv.h"
#include "xfs_fs.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
+#include "xfs_defer.h"
#include "xfs_inode.h"
+#include "xfs_errortag.h"
#include "xfs_cksum.h"
#include "xfs_trans.h"
#include "xfs_ialloc.h"
+#include "xfs_dir2.h"
/*
* Check that none of the inode's in the buffer have a next
bool readahead)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
+ xfs_agnumber_t agno;
int i;
int ni;
/*
* Validate the magic number and version of every inode in the buffer
*/
+ agno = xfs_daddr_to_agno(mp, XFS_BUF_ADDR(bp));
ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
for (i = 0; i < ni; i++) {
int di_ok;
xfs_dinode_t *dip;
+ xfs_agino_t unlinked_ino;
dip = xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog));
+ unlinked_ino = be32_to_cpu(dip->di_next_unlinked);
di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
- xfs_dinode_good_version(mp, dip->di_version);
+ xfs_dinode_good_version(mp, dip->di_version) &&
+ (unlinked_ino == NULLAGINO ||
+ xfs_verify_agino(mp, agno, unlinked_ino));
if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
- XFS_ERRTAG_ITOBP_INOTOBP,
- XFS_RANDOM_ITOBP_INOTOBP))) {
+ XFS_ERRTAG_ITOBP_INOTOBP))) {
if (readahead) {
bp->b_flags &= ~XBF_DONE;
xfs_buf_ioerror(bp, -EIO);
return;
}
- xfs_buf_ioerror(bp, -EFSCORRUPTED);
- xfs_verifier_error(bp);
#ifdef DEBUG
xfs_alert(mp,
"bad inode magic/vsn daddr %lld #%d (magic=%x)",
(unsigned long long)bp->b_bn, i,
be16_to_cpu(dip->di_magic));
#endif
+ xfs_buf_verifier_error(bp, -EFSCORRUPTED,
+ __func__, dip, sizeof(*dip),
+ NULL);
+ return;
}
}
- xfs_inobp_check(mp, bp);
}
ASSERT(buf_flags & XBF_TRYLOCK);
return error;
}
-
- if (error == -EFSCORRUPTED &&
- (iget_flags & XFS_IGET_UNTRUSTED))
- return -EINVAL;
-
xfs_warn(mp, "%s: xfs_trans_read_buf() returned error %d.",
__func__, error);
return error;
struct xfs_icdinode *to = &ip->i_d;
struct inode *inode = VFS_I(ip);
- to->di_mode = be16_to_cpu(from->di_mode);
- to->di_version = from ->di_version;
/*
* Convert v1 inodes immediately to v2 inode format as this is the
* minimum inode version format we support in the rest of the code.
*/
+ to->di_version = from->di_version;
if (to->di_version == 1) {
set_nlink(inode, be16_to_cpu(from->di_onlink));
to->di_projid_lo = 0;
inode->i_mtime.tv_nsec = (int)be32_to_cpu(from->di_mtime.t_nsec);
inode->i_ctime.tv_sec = (int)be32_to_cpu(from->di_ctime.t_sec);
inode->i_ctime.tv_nsec = (int)be32_to_cpu(from->di_ctime.t_nsec);
+ inode->i_generation = be32_to_cpu(from->di_gen);
+ inode->i_mode = be16_to_cpu(from->di_mode);
to->di_size = be64_to_cpu(from->di_size);
to->di_nblocks = be64_to_cpu(from->di_nblocks);
to->di_dmevmask = be32_to_cpu(from->di_dmevmask);
to->di_dmstate = be16_to_cpu(from->di_dmstate);
to->di_flags = be16_to_cpu(from->di_flags);
- to->di_gen = be32_to_cpu(from->di_gen);
if (to->di_version == 3) {
- to->di_changecount = be64_to_cpu(from->di_changecount);
+ inode_set_iversion_queried(inode,
+ be64_to_cpu(from->di_changecount));
to->di_crtime.t_sec = be32_to_cpu(from->di_crtime.t_sec);
to->di_crtime.t_nsec = be32_to_cpu(from->di_crtime.t_nsec);
to->di_flags2 = be64_to_cpu(from->di_flags2);
+ to->di_cowextsize = be32_to_cpu(from->di_cowextsize);
}
}
to->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
to->di_onlink = 0;
- to->di_mode = cpu_to_be16(from->di_mode);
to->di_version = from->di_version;
to->di_format = from->di_format;
to->di_uid = cpu_to_be32(from->di_uid);
to->di_ctime.t_sec = cpu_to_be32(inode->i_ctime.tv_sec);
to->di_ctime.t_nsec = cpu_to_be32(inode->i_ctime.tv_nsec);
to->di_nlink = cpu_to_be32(inode->i_nlink);
+ to->di_gen = cpu_to_be32(inode->i_generation);
+ to->di_mode = cpu_to_be16(inode->i_mode);
to->di_size = cpu_to_be64(from->di_size);
to->di_nblocks = cpu_to_be64(from->di_nblocks);
to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
to->di_dmstate = cpu_to_be16(from->di_dmstate);
to->di_flags = cpu_to_be16(from->di_flags);
- to->di_gen = cpu_to_be32(from->di_gen);
if (from->di_version == 3) {
- to->di_changecount = cpu_to_be64(from->di_changecount);
+ to->di_changecount = cpu_to_be64(inode_peek_iversion(inode));
to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec);
to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec);
to->di_flags2 = cpu_to_be64(from->di_flags2);
-
+ to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
to->di_ino = cpu_to_be64(ip->i_ino);
to->di_lsn = cpu_to_be64(lsn);
memset(to->di_pad2, 0, sizeof(to->di_pad2));
to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec);
to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec);
to->di_flags2 = cpu_to_be64(from->di_flags2);
+ to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
to->di_ino = cpu_to_be64(from->di_ino);
to->di_lsn = cpu_to_be64(from->di_lsn);
memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
}
}
-bool
+static xfs_failaddr_t
+xfs_dinode_verify_fork(
+ struct xfs_dinode *dip,
+ struct xfs_mount *mp,
+ int whichfork)
+{
+ uint32_t di_nextents = XFS_DFORK_NEXTENTS(dip, whichfork);
+
+ switch (XFS_DFORK_FORMAT(dip, whichfork)) {
+ case XFS_DINODE_FMT_LOCAL:
+ /*
+ * no local regular files yet
+ */
+ if (whichfork == XFS_DATA_FORK) {
+ if (S_ISREG(be16_to_cpu(dip->di_mode)))
+ return __this_address;
+ if (be64_to_cpu(dip->di_size) >
+ XFS_DFORK_SIZE(dip, mp, whichfork))
+ return __this_address;
+ }
+ if (di_nextents)
+ return __this_address;
+ break;
+ case XFS_DINODE_FMT_EXTENTS:
+ if (di_nextents > XFS_DFORK_MAXEXT(dip, mp, whichfork))
+ return __this_address;
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ if (whichfork == XFS_ATTR_FORK) {
+ if (di_nextents > MAXAEXTNUM)
+ return __this_address;
+ } else if (di_nextents > MAXEXTNUM) {
+ return __this_address;
+ }
+ break;
+ default:
+ return __this_address;
+ }
+ return NULL;
+}
+
+xfs_failaddr_t
xfs_dinode_verify(
struct xfs_mount *mp,
xfs_ino_t ino,
struct xfs_dinode *dip)
{
+ xfs_failaddr_t fa;
+ uint16_t mode;
+ uint16_t flags;
+ uint64_t flags2;
+ uint64_t di_size;
+
if (dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC))
- return false;
+ return __this_address;
+
+ /* Verify v3 integrity information first */
+ if (dip->di_version >= 3) {
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return __this_address;
+ if (!xfs_verify_cksum((char *)dip, mp->m_sb.sb_inodesize,
+ XFS_DINODE_CRC_OFF))
+ return __this_address;
+ if (be64_to_cpu(dip->di_ino) != ino)
+ return __this_address;
+ if (!uuid_equal(&dip->di_uuid, &mp->m_sb.sb_meta_uuid))
+ return __this_address;
+ }
+
+ /* don't allow invalid i_size */
+ di_size = be64_to_cpu(dip->di_size);
+ if (di_size & (1ULL << 63))
+ return __this_address;
+
+ mode = be16_to_cpu(dip->di_mode);
+ if (mode && xfs_mode_to_ftype(mode) == XFS_DIR3_FT_UNKNOWN)
+ return __this_address;
+
+ /* No zero-length symlinks/dirs. */
+ if ((S_ISLNK(mode) || S_ISDIR(mode)) && di_size == 0)
+ return __this_address;
+
+ /* Fork checks carried over from xfs_iformat_fork */
+ if (mode &&
+ be32_to_cpu(dip->di_nextents) + be16_to_cpu(dip->di_anextents) >
+ be64_to_cpu(dip->di_nblocks))
+ return __this_address;
+
+ if (mode && XFS_DFORK_BOFF(dip) > mp->m_sb.sb_inodesize)
+ return __this_address;
+
+ flags = be16_to_cpu(dip->di_flags);
+
+ if (mode && (flags & XFS_DIFLAG_REALTIME) && !mp->m_rtdev_targp)
+ return __this_address;
+
+ /* Do we have appropriate data fork formats for the mode? */
+ switch (mode & S_IFMT) {
+ case S_IFIFO:
+ case S_IFCHR:
+ case S_IFBLK:
+ case S_IFSOCK:
+ if (dip->di_format != XFS_DINODE_FMT_DEV)
+ return __this_address;
+ break;
+ case S_IFREG:
+ case S_IFLNK:
+ case S_IFDIR:
+ fa = xfs_dinode_verify_fork(dip, mp, XFS_DATA_FORK);
+ if (fa)
+ return fa;
+ break;
+ case 0:
+ /* Uninitialized inode ok. */
+ break;
+ default:
+ return __this_address;
+ }
+
+ if (XFS_DFORK_Q(dip)) {
+ fa = xfs_dinode_verify_fork(dip, mp, XFS_ATTR_FORK);
+ if (fa)
+ return fa;
+ } else {
+ /*
+ * If there is no fork offset, this may be a freshly-made inode
+ * in a new disk cluster, in which case di_aformat is zeroed.
+ * Otherwise, such an inode must be in EXTENTS format; this goes
+ * for freed inodes as well.
+ */
+ switch (dip->di_aformat) {
+ case 0:
+ case XFS_DINODE_FMT_EXTENTS:
+ break;
+ default:
+ return __this_address;
+ }
+ if (dip->di_anextents)
+ return __this_address;
+ }
+
+ /* extent size hint validation */
+ fa = xfs_inode_validate_extsize(mp, be32_to_cpu(dip->di_extsize),
+ mode, flags);
+ if (fa)
+ return fa;
/* only version 3 or greater inodes are extensively verified here */
if (dip->di_version < 3)
- return true;
-
- if (!xfs_sb_version_hascrc(&mp->m_sb))
- return false;
- if (!xfs_verify_cksum((char *)dip, mp->m_sb.sb_inodesize,
- XFS_DINODE_CRC_OFF))
- return false;
- if (be64_to_cpu(dip->di_ino) != ino)
- return false;
- if (!uuid_equal(&dip->di_uuid, &mp->m_sb.sb_meta_uuid))
- return false;
- return true;
+ return NULL;
+
+ flags2 = be64_to_cpu(dip->di_flags2);
+
+ /* don't allow reflink/cowextsize if we don't have reflink */
+ if ((flags2 & (XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE)) &&
+ !xfs_sb_version_hasreflink(&mp->m_sb))
+ return __this_address;
+
+ /* only regular files get reflink */
+ if ((flags2 & XFS_DIFLAG2_REFLINK) && (mode & S_IFMT) != S_IFREG)
+ return __this_address;
+
+ /* don't let reflink and realtime mix */
+ if ((flags2 & XFS_DIFLAG2_REFLINK) && (flags & XFS_DIFLAG_REALTIME))
+ return __this_address;
+
+ /* don't let reflink and dax mix */
+ if ((flags2 & XFS_DIFLAG2_REFLINK) && (flags2 & XFS_DIFLAG2_DAX))
+ return __this_address;
+
+ /* COW extent size hint validation */
+ fa = xfs_inode_validate_cowextsize(mp, be32_to_cpu(dip->di_cowextsize),
+ mode, flags, flags2);
+ if (fa)
+ return fa;
+
+ return NULL;
}
void
struct xfs_mount *mp,
struct xfs_dinode *dip)
{
- __uint32_t crc;
+ uint32_t crc;
if (dip->di_version < 3)
return;
ASSERT(xfs_sb_version_hascrc(&mp->m_sb));
- crc = xfs_start_cksum((char *)dip, mp->m_sb.sb_inodesize,
+ crc = xfs_start_cksum_update((char *)dip, mp->m_sb.sb_inodesize,
XFS_DINODE_CRC_OFF);
dip->di_crc = xfs_end_cksum(crc);
}
{
xfs_buf_t *bp;
xfs_dinode_t *dip;
+ xfs_failaddr_t fa;
int error;
/*
!(mp->m_flags & XFS_MOUNT_IKEEP)) {
/* initialise the on-disk inode core */
memset(&ip->i_d, 0, sizeof(ip->i_d));
- ip->i_d.di_gen = prandom_u32();
- if (xfs_sb_version_hascrc(&mp->m_sb))
- ip->i_d.di_version = 3;
- else
- ip->i_d.di_version = 2;
+ VFS_I(ip)->i_generation = prandom_u32();
+ ip->i_d.di_version = 3;
return 0;
}
return error;
/* even unallocated inodes are verified */
- if (!xfs_dinode_verify(mp, ip->i_ino, dip)) {
- xfs_alert(mp, "%s: validation failed for inode %lld failed",
- __func__, ip->i_ino);
-
- XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, dip);
+ fa = xfs_dinode_verify(mp, ip->i_ino, dip);
+ if (fa) {
+ xfs_inode_verifier_error(ip, -EFSCORRUPTED, "dinode", dip,
+ sizeof(*dip), fa);
error = -EFSCORRUPTED;
goto out_brelse;
}
* that xfs_ialloc won't overwrite or relies on being correct.
*/
ip->i_d.di_version = dip->di_version;
- ip->i_d.di_gen = be32_to_cpu(dip->di_gen);
+ VFS_I(ip)->i_generation = be32_to_cpu(dip->di_gen);
ip->i_d.di_flushiter = be16_to_cpu(dip->di_flushiter);
/*
* the inode is already free and not try to mess
* with the uninitialized part of it.
*/
- ip->i_d.di_mode = 0;
+ VFS_I(ip)->i_mode = 0;
}
ASSERT(ip->i_d.di_version >= 2);
-
ip->i_delayed_blks = 0;
/*
xfs_trans_brelse(tp, bp);
return error;
}
+
+/*
+ * Validate di_extsize hint.
+ *
+ * The rules are documented at xfs_ioctl_setattr_check_extsize().
+ * These functions must be kept in sync with each other.
+ */
+xfs_failaddr_t
+xfs_inode_validate_extsize(
+ struct xfs_mount *mp,
+ uint32_t extsize,
+ uint16_t mode,
+ uint16_t flags)
+{
+ bool rt_flag;
+ bool hint_flag;
+ bool inherit_flag;
+ uint32_t extsize_bytes;
+ uint32_t blocksize_bytes;
+
+ rt_flag = (flags & XFS_DIFLAG_REALTIME);
+ hint_flag = (flags & XFS_DIFLAG_EXTSIZE);
+ inherit_flag = (flags & XFS_DIFLAG_EXTSZINHERIT);
+ extsize_bytes = XFS_FSB_TO_B(mp, extsize);
+
+ if (rt_flag)
+ blocksize_bytes = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog;
+ else
+ blocksize_bytes = mp->m_sb.sb_blocksize;
+
+ if ((hint_flag || inherit_flag) && !(S_ISDIR(mode) || S_ISREG(mode)))
+ return __this_address;
+
+ if (hint_flag && !S_ISREG(mode))
+ return __this_address;
+
+ if (inherit_flag && !S_ISDIR(mode))
+ return __this_address;
+
+ if ((hint_flag || inherit_flag) && extsize == 0)
+ return __this_address;
+
+ /* free inodes get flags set to zero but extsize remains */
+ if (mode && !(hint_flag || inherit_flag) && extsize != 0)
+ return __this_address;
+
+ if (extsize_bytes % blocksize_bytes)
+ return __this_address;
+
+ if (extsize > MAXEXTLEN)
+ return __this_address;
+
+ if (!rt_flag && extsize > mp->m_sb.sb_agblocks / 2)
+ return __this_address;
+
+ return NULL;
+}
+
+/*
+ * Validate di_cowextsize hint.
+ *
+ * The rules are documented at xfs_ioctl_setattr_check_cowextsize().
+ * These functions must be kept in sync with each other.
+ */
+xfs_failaddr_t
+xfs_inode_validate_cowextsize(
+ struct xfs_mount *mp,
+ uint32_t cowextsize,
+ uint16_t mode,
+ uint16_t flags,
+ uint64_t flags2)
+{
+ bool rt_flag;
+ bool hint_flag;
+ uint32_t cowextsize_bytes;
+
+ rt_flag = (flags & XFS_DIFLAG_REALTIME);
+ hint_flag = (flags2 & XFS_DIFLAG2_COWEXTSIZE);
+ cowextsize_bytes = XFS_FSB_TO_B(mp, cowextsize);
+
+ if (hint_flag && !xfs_sb_version_hasreflink(&mp->m_sb))
+ return __this_address;
+
+ if (hint_flag && !(S_ISDIR(mode) || S_ISREG(mode)))
+ return __this_address;
+
+ if (hint_flag && cowextsize == 0)
+ return __this_address;
+
+ /* free inodes get flags set to zero but cowextsize remains */
+ if (mode && !hint_flag && cowextsize != 0)
+ return __this_address;
+
+ if (hint_flag && rt_flag)
+ return __this_address;
+
+ if (cowextsize_bytes % mp->m_sb.sb_blocksize)
+ return __this_address;
+
+ if (cowextsize > MAXEXTLEN)
+ return __this_address;
+
+ if (cowextsize > mp->m_sb.sb_agblocks / 2)
+ return __this_address;
+
+ return NULL;
+}