2018-06-06 10:42:14 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0
|
2013-08-12 18:49:39 +08:00
|
|
|
/*
|
|
|
|
|
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
|
|
|
|
|
* Copyright (c) 2013 Red Hat, Inc.
|
|
|
|
|
* All Rights Reserved.
|
|
|
|
|
*/
|
|
|
|
|
#include "xfs.h"
|
|
|
|
|
#include "xfs_fs.h"
|
2013-10-23 07:36:05 +08:00
|
|
|
#include "xfs_shared.h"
|
2013-10-23 07:50:10 +08:00
|
|
|
#include "xfs_format.h"
|
|
|
|
|
#include "xfs_log_format.h"
|
|
|
|
|
#include "xfs_trans_resv.h"
|
2013-08-12 18:49:39 +08:00
|
|
|
#include "xfs_bit.h"
|
|
|
|
|
#include "xfs_mount.h"
|
2013-10-15 06:17:51 +08:00
|
|
|
#include "xfs_da_format.h"
|
2013-08-12 18:49:39 +08:00
|
|
|
#include "xfs_da_btree.h"
|
2013-10-23 07:51:50 +08:00
|
|
|
#include "xfs_inode.h"
|
2013-08-12 18:49:39 +08:00
|
|
|
#include "xfs_attr_remote.h"
|
2013-10-23 07:50:10 +08:00
|
|
|
#include "xfs_trans.h"
|
2013-08-12 18:49:39 +08:00
|
|
|
#include "xfs_bmap.h"
|
|
|
|
|
#include "xfs_attr.h"
|
|
|
|
|
#include "xfs_attr_leaf.h"
|
|
|
|
|
#include "xfs_quota.h"
|
2013-10-29 19:11:51 +08:00
|
|
|
#include "xfs_dir2.h"
|
2019-11-03 00:40:53 +08:00
|
|
|
#include "xfs_error.h"
|
2013-08-12 18:49:39 +08:00
|
|
|
|
|
|
|
|
/*
|
xfs: fix memory corruption during remote attr value buffer invalidation
While running generic/103, I observed what looks like memory corruption
and (with slub debugging turned on) a slub redzone warning on i386 when
inactivating an inode with a 64k remote attr value.
On a v5 filesystem, maximally sized remote attr values require one block
more than 64k worth of space to hold both the remote attribute value
header (64 bytes). On a 4k block filesystem this results in a 68k
buffer; on a 64k block filesystem, this would be a 128k buffer. Note
that even though we'll never use more than 65,600 bytes of this buffer,
XFS_MAX_BLOCKSIZE is 64k.
This is a problem because the definition of struct xfs_buf_log_format
allows for XFS_MAX_BLOCKSIZE worth of dirty bitmap (64k). On i386 when we
invalidate a remote attribute, xfs_trans_binval zeroes all 68k worth of
the dirty map, writing right off the end of the log item and corrupting
memory. We've gotten away with this on x86_64 for years because the
compiler inserts a u32 padding on the end of struct xfs_buf_log_format.
Fortunately for us, remote attribute values are written to disk with
xfs_bwrite(), which is to say that they are not logged. Fix the problem
by removing all places where we could end up creating a buffer log item
for a remote attribute value and leave a note explaining why. Next,
replace the open-coded buffer invalidation with a call to the helper we
created in the previous patch that does better checking for bad metadata
before marking the buffer stale.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
2020-01-08 08:11:45 +08:00
|
|
|
* Invalidate any incore buffers associated with this remote attribute value
|
|
|
|
|
* extent. We never log remote attribute value buffers, which means that they
|
|
|
|
|
* won't be attached to a transaction and are therefore safe to mark stale.
|
|
|
|
|
* The actual bunmapi will be taken care of later.
|
2013-08-12 18:49:39 +08:00
|
|
|
*/
|
|
|
|
|
STATIC int
|
xfs: fix memory corruption during remote attr value buffer invalidation
While running generic/103, I observed what looks like memory corruption
and (with slub debugging turned on) a slub redzone warning on i386 when
inactivating an inode with a 64k remote attr value.
On a v5 filesystem, maximally sized remote attr values require one block
more than 64k worth of space to hold both the remote attribute value
header (64 bytes). On a 4k block filesystem this results in a 68k
buffer; on a 64k block filesystem, this would be a 128k buffer. Note
that even though we'll never use more than 65,600 bytes of this buffer,
XFS_MAX_BLOCKSIZE is 64k.
This is a problem because the definition of struct xfs_buf_log_format
allows for XFS_MAX_BLOCKSIZE worth of dirty bitmap (64k). On i386 when we
invalidate a remote attribute, xfs_trans_binval zeroes all 68k worth of
the dirty map, writing right off the end of the log item and corrupting
memory. We've gotten away with this on x86_64 for years because the
compiler inserts a u32 padding on the end of struct xfs_buf_log_format.
Fortunately for us, remote attribute values are written to disk with
xfs_bwrite(), which is to say that they are not logged. Fix the problem
by removing all places where we could end up creating a buffer log item
for a remote attribute value and leave a note explaining why. Next,
replace the open-coded buffer invalidation with a call to the helper we
created in the previous patch that does better checking for bad metadata
before marking the buffer stale.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
2020-01-08 08:11:45 +08:00
|
|
|
xfs_attr3_rmt_stale(
|
2013-08-12 18:49:39 +08:00
|
|
|
struct xfs_inode *dp,
|
|
|
|
|
xfs_dablk_t blkno,
|
|
|
|
|
int blkcnt)
|
|
|
|
|
{
|
|
|
|
|
struct xfs_bmbt_irec map;
|
|
|
|
|
int nmap;
|
|
|
|
|
int error;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Roll through the "value", invalidating the attribute value's
|
|
|
|
|
* blocks.
|
|
|
|
|
*/
|
2020-01-15 06:31:49 +08:00
|
|
|
while (blkcnt > 0) {
|
2013-08-12 18:49:39 +08:00
|
|
|
/*
|
|
|
|
|
* Try to remember where we decided to put the value.
|
|
|
|
|
*/
|
|
|
|
|
nmap = 1;
|
2020-01-15 06:31:49 +08:00
|
|
|
error = xfs_bmapi_read(dp, (xfs_fileoff_t)blkno, blkcnt,
|
2013-08-12 18:49:39 +08:00
|
|
|
&map, &nmap, XFS_BMAPI_ATTRFORK);
|
xfs: fix memory corruption during remote attr value buffer invalidation
While running generic/103, I observed what looks like memory corruption
and (with slub debugging turned on) a slub redzone warning on i386 when
inactivating an inode with a 64k remote attr value.
On a v5 filesystem, maximally sized remote attr values require one block
more than 64k worth of space to hold both the remote attribute value
header (64 bytes). On a 4k block filesystem this results in a 68k
buffer; on a 64k block filesystem, this would be a 128k buffer. Note
that even though we'll never use more than 65,600 bytes of this buffer,
XFS_MAX_BLOCKSIZE is 64k.
This is a problem because the definition of struct xfs_buf_log_format
allows for XFS_MAX_BLOCKSIZE worth of dirty bitmap (64k). On i386 when we
invalidate a remote attribute, xfs_trans_binval zeroes all 68k worth of
the dirty map, writing right off the end of the log item and corrupting
memory. We've gotten away with this on x86_64 for years because the
compiler inserts a u32 padding on the end of struct xfs_buf_log_format.
Fortunately for us, remote attribute values are written to disk with
xfs_bwrite(), which is to say that they are not logged. Fix the problem
by removing all places where we could end up creating a buffer log item
for a remote attribute value and leave a note explaining why. Next,
replace the open-coded buffer invalidation with a call to the helper we
created in the previous patch that does better checking for bad metadata
before marking the buffer stale.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
2020-01-08 08:11:45 +08:00
|
|
|
if (error)
|
2014-06-22 13:03:54 +08:00
|
|
|
return error;
|
xfs: fix memory corruption during remote attr value buffer invalidation
While running generic/103, I observed what looks like memory corruption
and (with slub debugging turned on) a slub redzone warning on i386 when
inactivating an inode with a 64k remote attr value.
On a v5 filesystem, maximally sized remote attr values require one block
more than 64k worth of space to hold both the remote attribute value
header (64 bytes). On a 4k block filesystem this results in a 68k
buffer; on a 64k block filesystem, this would be a 128k buffer. Note
that even though we'll never use more than 65,600 bytes of this buffer,
XFS_MAX_BLOCKSIZE is 64k.
This is a problem because the definition of struct xfs_buf_log_format
allows for XFS_MAX_BLOCKSIZE worth of dirty bitmap (64k). On i386 when we
invalidate a remote attribute, xfs_trans_binval zeroes all 68k worth of
the dirty map, writing right off the end of the log item and corrupting
memory. We've gotten away with this on x86_64 for years because the
compiler inserts a u32 padding on the end of struct xfs_buf_log_format.
Fortunately for us, remote attribute values are written to disk with
xfs_bwrite(), which is to say that they are not logged. Fix the problem
by removing all places where we could end up creating a buffer log item
for a remote attribute value and leave a note explaining why. Next,
replace the open-coded buffer invalidation with a call to the helper we
created in the previous patch that does better checking for bad metadata
before marking the buffer stale.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
2020-01-08 08:11:45 +08:00
|
|
|
if (XFS_IS_CORRUPT(dp->i_mount, nmap != 1))
|
|
|
|
|
return -EFSCORRUPTED;
|
2013-08-12 18:49:39 +08:00
|
|
|
|
|
|
|
|
/*
|
xfs: fix memory corruption during remote attr value buffer invalidation
While running generic/103, I observed what looks like memory corruption
and (with slub debugging turned on) a slub redzone warning on i386 when
inactivating an inode with a 64k remote attr value.
On a v5 filesystem, maximally sized remote attr values require one block
more than 64k worth of space to hold both the remote attribute value
header (64 bytes). On a 4k block filesystem this results in a 68k
buffer; on a 64k block filesystem, this would be a 128k buffer. Note
that even though we'll never use more than 65,600 bytes of this buffer,
XFS_MAX_BLOCKSIZE is 64k.
This is a problem because the definition of struct xfs_buf_log_format
allows for XFS_MAX_BLOCKSIZE worth of dirty bitmap (64k). On i386 when we
invalidate a remote attribute, xfs_trans_binval zeroes all 68k worth of
the dirty map, writing right off the end of the log item and corrupting
memory. We've gotten away with this on x86_64 for years because the
compiler inserts a u32 padding on the end of struct xfs_buf_log_format.
Fortunately for us, remote attribute values are written to disk with
xfs_bwrite(), which is to say that they are not logged. Fix the problem
by removing all places where we could end up creating a buffer log item
for a remote attribute value and leave a note explaining why. Next,
replace the open-coded buffer invalidation with a call to the helper we
created in the previous patch that does better checking for bad metadata
before marking the buffer stale.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
2020-01-08 08:11:45 +08:00
|
|
|
* Mark any incore buffers for the remote value as stale. We
|
|
|
|
|
* never log remote attr value buffers, so the buffer should be
|
|
|
|
|
* easy to kill.
|
2013-08-12 18:49:39 +08:00
|
|
|
*/
|
xfs: fix memory corruption during remote attr value buffer invalidation
While running generic/103, I observed what looks like memory corruption
and (with slub debugging turned on) a slub redzone warning on i386 when
inactivating an inode with a 64k remote attr value.
On a v5 filesystem, maximally sized remote attr values require one block
more than 64k worth of space to hold both the remote attribute value
header (64 bytes). On a 4k block filesystem this results in a 68k
buffer; on a 64k block filesystem, this would be a 128k buffer. Note
that even though we'll never use more than 65,600 bytes of this buffer,
XFS_MAX_BLOCKSIZE is 64k.
This is a problem because the definition of struct xfs_buf_log_format
allows for XFS_MAX_BLOCKSIZE worth of dirty bitmap (64k). On i386 when we
invalidate a remote attribute, xfs_trans_binval zeroes all 68k worth of
the dirty map, writing right off the end of the log item and corrupting
memory. We've gotten away with this on x86_64 for years because the
compiler inserts a u32 padding on the end of struct xfs_buf_log_format.
Fortunately for us, remote attribute values are written to disk with
xfs_bwrite(), which is to say that they are not logged. Fix the problem
by removing all places where we could end up creating a buffer log item
for a remote attribute value and leave a note explaining why. Next,
replace the open-coded buffer invalidation with a call to the helper we
created in the previous patch that does better checking for bad metadata
before marking the buffer stale.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
2020-01-08 08:11:45 +08:00
|
|
|
error = xfs_attr_rmtval_stale(dp, &map, 0);
|
|
|
|
|
if (error)
|
|
|
|
|
return error;
|
2013-08-12 18:49:39 +08:00
|
|
|
|
2020-01-15 06:31:49 +08:00
|
|
|
blkno += map.br_blockcount;
|
|
|
|
|
blkcnt -= map.br_blockcount;
|
2013-08-12 18:49:39 +08:00
|
|
|
}
|
|
|
|
|
|
2014-06-22 13:03:54 +08:00
|
|
|
return 0;
|
2013-08-12 18:49:39 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Invalidate all of the "remote" value regions pointed to by a particular
|
|
|
|
|
* leaf block.
|
|
|
|
|
* Note that we must release the lock on the buffer so that we are not
|
|
|
|
|
* caught holding something that the logging code wants to flush to disk.
|
|
|
|
|
*/
|
|
|
|
|
STATIC int
|
|
|
|
|
xfs_attr3_leaf_inactive(
|
2020-01-15 06:31:49 +08:00
|
|
|
struct xfs_trans **trans,
|
|
|
|
|
struct xfs_inode *dp,
|
|
|
|
|
struct xfs_buf *bp)
|
2013-08-12 18:49:39 +08:00
|
|
|
{
|
2020-01-15 06:31:49 +08:00
|
|
|
struct xfs_attr3_icleaf_hdr ichdr;
|
|
|
|
|
struct xfs_mount *mp = bp->b_mount;
|
|
|
|
|
struct xfs_attr_leafblock *leaf = bp->b_addr;
|
|
|
|
|
struct xfs_attr_leaf_entry *entry;
|
2013-08-12 18:49:39 +08:00
|
|
|
struct xfs_attr_leaf_name_remote *name_rmt;
|
2020-01-23 23:54:09 +08:00
|
|
|
int error = 0;
|
2020-01-15 06:31:49 +08:00
|
|
|
int i;
|
2013-08-12 18:49:39 +08:00
|
|
|
|
2015-04-13 09:26:02 +08:00
|
|
|
xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf);
|
2013-08-12 18:49:39 +08:00
|
|
|
|
|
|
|
|
/*
|
2020-01-15 06:31:49 +08:00
|
|
|
* Find the remote value extents for this leaf and invalidate their
|
|
|
|
|
* incore buffers.
|
2013-08-12 18:49:39 +08:00
|
|
|
*/
|
|
|
|
|
entry = xfs_attr3_leaf_entryp(leaf);
|
|
|
|
|
for (i = 0; i < ichdr.count; entry++, i++) {
|
2020-01-15 06:31:49 +08:00
|
|
|
int blkcnt;
|
2013-08-12 18:49:39 +08:00
|
|
|
|
2020-01-15 06:31:49 +08:00
|
|
|
if (!entry->nameidx || (entry->flags & XFS_ATTR_LOCAL))
|
|
|
|
|
continue;
|
2013-08-12 18:49:39 +08:00
|
|
|
|
2020-01-15 06:31:49 +08:00
|
|
|
name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
|
|
|
|
|
if (!name_rmt->valueblk)
|
|
|
|
|
continue;
|
2013-08-12 18:49:39 +08:00
|
|
|
|
2020-01-15 06:31:49 +08:00
|
|
|
blkcnt = xfs_attr3_rmt_blocks(dp->i_mount,
|
|
|
|
|
be32_to_cpu(name_rmt->valuelen));
|
|
|
|
|
error = xfs_attr3_rmt_stale(dp,
|
|
|
|
|
be32_to_cpu(name_rmt->valueblk), blkcnt);
|
|
|
|
|
if (error)
|
|
|
|
|
goto err;
|
2013-08-12 18:49:39 +08:00
|
|
|
}
|
|
|
|
|
|
2020-01-15 06:31:49 +08:00
|
|
|
xfs_trans_brelse(*trans, bp);
|
|
|
|
|
err:
|
2013-08-12 18:49:39 +08:00
|
|
|
return error;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Recurse (gasp!) through the attribute nodes until we find leaves.
|
|
|
|
|
* We're doing a depth-first traversal in order to invalidate everything.
|
|
|
|
|
*/
|
|
|
|
|
STATIC int
|
|
|
|
|
xfs_attr3_node_inactive(
|
2019-11-09 06:57:48 +08:00
|
|
|
struct xfs_trans **trans,
|
|
|
|
|
struct xfs_inode *dp,
|
|
|
|
|
struct xfs_buf *bp,
|
|
|
|
|
int level)
|
2013-08-12 18:49:39 +08:00
|
|
|
{
|
2019-11-21 01:46:05 +08:00
|
|
|
struct xfs_mount *mp = dp->i_mount;
|
2019-11-09 06:57:48 +08:00
|
|
|
struct xfs_da_blkinfo *info;
|
|
|
|
|
xfs_dablk_t child_fsb;
|
|
|
|
|
xfs_daddr_t parent_blkno, child_blkno;
|
|
|
|
|
struct xfs_buf *child_bp;
|
2013-08-12 18:49:39 +08:00
|
|
|
struct xfs_da3_icnode_hdr ichdr;
|
2019-11-09 06:57:48 +08:00
|
|
|
int error, i;
|
2013-08-12 18:49:39 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Since this code is recursive (gasp!) we must protect ourselves.
|
|
|
|
|
*/
|
|
|
|
|
if (level > XFS_DA_NODE_MAXDEPTH) {
|
2020-03-12 01:37:54 +08:00
|
|
|
xfs_buf_mark_corrupt(bp);
|
2020-03-12 01:37:53 +08:00
|
|
|
xfs_trans_brelse(*trans, bp); /* no locks for later trans */
|
2019-10-29 07:12:34 +08:00
|
|
|
return -EFSCORRUPTED;
|
2013-08-12 18:49:39 +08:00
|
|
|
}
|
|
|
|
|
|
2019-11-09 06:57:48 +08:00
|
|
|
xfs_da3_node_hdr_from_disk(dp->i_mount, &ichdr, bp->b_addr);
|
2013-08-12 18:49:39 +08:00
|
|
|
parent_blkno = bp->b_bn;
|
|
|
|
|
if (!ichdr.count) {
|
|
|
|
|
xfs_trans_brelse(*trans, bp);
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
2019-11-09 06:57:48 +08:00
|
|
|
child_fsb = be32_to_cpu(ichdr.btree[0].before);
|
2013-08-12 18:49:39 +08:00
|
|
|
xfs_trans_brelse(*trans, bp); /* no locks for later trans */
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* If this is the node level just above the leaves, simply loop
|
|
|
|
|
* over the leaves removing all of them. If this is higher up
|
|
|
|
|
* in the tree, recurse downward.
|
|
|
|
|
*/
|
|
|
|
|
for (i = 0; i < ichdr.count; i++) {
|
|
|
|
|
/*
|
|
|
|
|
* Read the subsidiary block to see what we have to work with.
|
|
|
|
|
* Don't do this in a transaction. This is a depth-first
|
|
|
|
|
* traversal of the tree so we may deal with many blocks
|
|
|
|
|
* before we come back to this one.
|
|
|
|
|
*/
|
2019-11-21 01:46:04 +08:00
|
|
|
error = xfs_da3_node_read(*trans, dp, child_fsb, &child_bp,
|
2017-10-18 05:16:28 +08:00
|
|
|
XFS_ATTR_FORK);
|
2013-08-12 18:49:39 +08:00
|
|
|
if (error)
|
2014-06-22 13:03:54 +08:00
|
|
|
return error;
|
2013-08-12 18:49:39 +08:00
|
|
|
|
2017-10-18 05:16:28 +08:00
|
|
|
/* save for re-read later */
|
|
|
|
|
child_blkno = XFS_BUF_ADDR(child_bp);
|
2013-08-12 18:49:39 +08:00
|
|
|
|
2017-10-18 05:16:28 +08:00
|
|
|
/*
|
|
|
|
|
* Invalidate the subtree, however we have to.
|
|
|
|
|
*/
|
|
|
|
|
info = child_bp->b_addr;
|
|
|
|
|
switch (info->magic) {
|
|
|
|
|
case cpu_to_be16(XFS_DA_NODE_MAGIC):
|
|
|
|
|
case cpu_to_be16(XFS_DA3_NODE_MAGIC):
|
|
|
|
|
error = xfs_attr3_node_inactive(trans, dp, child_bp,
|
|
|
|
|
level + 1);
|
|
|
|
|
break;
|
|
|
|
|
case cpu_to_be16(XFS_ATTR_LEAF_MAGIC):
|
|
|
|
|
case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
|
|
|
|
|
error = xfs_attr3_leaf_inactive(trans, dp, child_bp);
|
|
|
|
|
break;
|
|
|
|
|
default:
|
2020-03-12 01:37:54 +08:00
|
|
|
xfs_buf_mark_corrupt(child_bp);
|
2017-10-18 05:16:28 +08:00
|
|
|
xfs_trans_brelse(*trans, child_bp);
|
2019-11-03 00:40:53 +08:00
|
|
|
error = -EFSCORRUPTED;
|
2017-10-18 05:16:28 +08:00
|
|
|
break;
|
2013-08-12 18:49:39 +08:00
|
|
|
}
|
2017-10-18 05:16:28 +08:00
|
|
|
if (error)
|
|
|
|
|
return error;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Remove the subsidiary block from the cache and from the log.
|
|
|
|
|
*/
|
2020-01-24 09:01:18 +08:00
|
|
|
error = xfs_trans_get_buf(*trans, mp->m_ddev_targp,
|
2019-11-21 01:46:05 +08:00
|
|
|
child_blkno,
|
2020-01-24 09:01:18 +08:00
|
|
|
XFS_FSB_TO_BB(mp, mp->m_attr_geo->fsbcount), 0,
|
|
|
|
|
&child_bp);
|
|
|
|
|
if (error)
|
|
|
|
|
return error;
|
2019-11-21 01:46:05 +08:00
|
|
|
error = bp->b_error;
|
|
|
|
|
if (error) {
|
|
|
|
|
xfs_trans_brelse(*trans, child_bp);
|
2017-10-18 05:16:28 +08:00
|
|
|
return error;
|
2019-11-21 01:46:05 +08:00
|
|
|
}
|
2017-10-18 05:16:28 +08:00
|
|
|
xfs_trans_binval(*trans, child_bp);
|
2013-08-12 18:49:39 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* If we're not done, re-read the parent to get the next
|
|
|
|
|
* child block number.
|
|
|
|
|
*/
|
|
|
|
|
if (i + 1 < ichdr.count) {
|
2019-11-09 06:57:48 +08:00
|
|
|
struct xfs_da3_icnode_hdr phdr;
|
|
|
|
|
|
2019-11-21 01:46:04 +08:00
|
|
|
error = xfs_da3_node_read_mapped(*trans, dp,
|
|
|
|
|
parent_blkno, &bp, XFS_ATTR_FORK);
|
2013-08-12 18:49:39 +08:00
|
|
|
if (error)
|
|
|
|
|
return error;
|
2019-11-09 06:57:48 +08:00
|
|
|
xfs_da3_node_hdr_from_disk(dp->i_mount, &phdr,
|
|
|
|
|
bp->b_addr);
|
|
|
|
|
child_fsb = be32_to_cpu(phdr.btree[i + 1].before);
|
2013-08-12 18:49:39 +08:00
|
|
|
xfs_trans_brelse(*trans, bp);
|
|
|
|
|
}
|
|
|
|
|
/*
|
|
|
|
|
* Atomically commit the whole invalidate stuff.
|
|
|
|
|
*/
|
2017-08-29 01:21:03 +08:00
|
|
|
error = xfs_trans_roll_inode(trans, dp);
|
2013-08-12 18:49:39 +08:00
|
|
|
if (error)
|
|
|
|
|
return error;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Indiscriminately delete the entire attribute fork
|
|
|
|
|
*
|
|
|
|
|
* Recurse (gasp!) through the attribute nodes until we find leaves.
|
|
|
|
|
* We're doing a depth-first traversal in order to invalidate everything.
|
|
|
|
|
*/
|
2016-06-01 15:38:15 +08:00
|
|
|
static int
|
2013-08-12 18:49:39 +08:00
|
|
|
xfs_attr3_root_inactive(
|
|
|
|
|
struct xfs_trans **trans,
|
|
|
|
|
struct xfs_inode *dp)
|
|
|
|
|
{
|
2019-11-21 01:46:05 +08:00
|
|
|
struct xfs_mount *mp = dp->i_mount;
|
2013-08-12 18:49:39 +08:00
|
|
|
struct xfs_da_blkinfo *info;
|
|
|
|
|
struct xfs_buf *bp;
|
|
|
|
|
xfs_daddr_t blkno;
|
|
|
|
|
int error;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Read block 0 to see what we have to work with.
|
|
|
|
|
* We only get here if we have extents, since we remove
|
|
|
|
|
* the extents in reverse order the extent containing
|
|
|
|
|
* block 0 must still be there.
|
|
|
|
|
*/
|
2019-11-21 01:46:04 +08:00
|
|
|
error = xfs_da3_node_read(*trans, dp, 0, &bp, XFS_ATTR_FORK);
|
2013-08-12 18:49:39 +08:00
|
|
|
if (error)
|
|
|
|
|
return error;
|
|
|
|
|
blkno = bp->b_bn;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Invalidate the tree, even if the "tree" is only a single leaf block.
|
|
|
|
|
* This is a depth-first traversal!
|
|
|
|
|
*/
|
|
|
|
|
info = bp->b_addr;
|
|
|
|
|
switch (info->magic) {
|
|
|
|
|
case cpu_to_be16(XFS_DA_NODE_MAGIC):
|
|
|
|
|
case cpu_to_be16(XFS_DA3_NODE_MAGIC):
|
|
|
|
|
error = xfs_attr3_node_inactive(trans, dp, bp, 1);
|
|
|
|
|
break;
|
|
|
|
|
case cpu_to_be16(XFS_ATTR_LEAF_MAGIC):
|
|
|
|
|
case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
|
|
|
|
|
error = xfs_attr3_leaf_inactive(trans, dp, bp);
|
|
|
|
|
break;
|
|
|
|
|
default:
|
2019-10-29 07:12:34 +08:00
|
|
|
error = -EFSCORRUPTED;
|
2020-03-12 01:37:54 +08:00
|
|
|
xfs_buf_mark_corrupt(bp);
|
2013-08-12 18:49:39 +08:00
|
|
|
xfs_trans_brelse(*trans, bp);
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
if (error)
|
|
|
|
|
return error;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Invalidate the incore copy of the root block.
|
|
|
|
|
*/
|
2020-01-24 09:01:18 +08:00
|
|
|
error = xfs_trans_get_buf(*trans, mp->m_ddev_targp, blkno,
|
|
|
|
|
XFS_FSB_TO_BB(mp, mp->m_attr_geo->fsbcount), 0, &bp);
|
|
|
|
|
if (error)
|
|
|
|
|
return error;
|
2019-11-21 01:46:05 +08:00
|
|
|
error = bp->b_error;
|
|
|
|
|
if (error) {
|
|
|
|
|
xfs_trans_brelse(*trans, bp);
|
2013-08-12 18:49:39 +08:00
|
|
|
return error;
|
2019-11-21 01:46:05 +08:00
|
|
|
}
|
2013-08-12 18:49:39 +08:00
|
|
|
xfs_trans_binval(*trans, bp); /* remove from cache */
|
|
|
|
|
/*
|
|
|
|
|
* Commit the invalidate and start the next transaction.
|
|
|
|
|
*/
|
2017-08-29 01:21:03 +08:00
|
|
|
error = xfs_trans_roll_inode(trans, dp);
|
2013-08-12 18:49:39 +08:00
|
|
|
|
|
|
|
|
return error;
|
|
|
|
|
}
|
|
|
|
|
|
2015-05-29 05:40:08 +08:00
|
|
|
/*
|
|
|
|
|
* xfs_attr_inactive kills all traces of an attribute fork on an inode. It
|
|
|
|
|
* removes both the on-disk and in-memory inode fork. Note that this also has to
|
|
|
|
|
* handle the condition of inodes without attributes but with an attribute fork
|
|
|
|
|
* configured, so we can't use xfs_inode_hasattr() here.
|
|
|
|
|
*
|
|
|
|
|
* The in-memory attribute fork is removed even on error.
|
|
|
|
|
*/
|
2013-08-12 18:49:39 +08:00
|
|
|
int
|
2015-05-29 05:40:08 +08:00
|
|
|
xfs_attr_inactive(
|
|
|
|
|
struct xfs_inode *dp)
|
2013-08-12 18:49:39 +08:00
|
|
|
{
|
2015-05-29 05:40:08 +08:00
|
|
|
struct xfs_trans *trans;
|
|
|
|
|
struct xfs_mount *mp;
|
|
|
|
|
int lock_mode = XFS_ILOCK_SHARED;
|
|
|
|
|
int error = 0;
|
2013-08-12 18:49:39 +08:00
|
|
|
|
|
|
|
|
mp = dp->i_mount;
|
|
|
|
|
ASSERT(! XFS_NOT_DQATTACHED(mp, dp));
|
|
|
|
|
|
2015-05-29 05:40:08 +08:00
|
|
|
xfs_ilock(dp, lock_mode);
|
|
|
|
|
if (!XFS_IFORK_Q(dp))
|
|
|
|
|
goto out_destroy_fork;
|
|
|
|
|
xfs_iunlock(dp, lock_mode);
|
2013-08-12 18:49:39 +08:00
|
|
|
|
2015-05-29 05:40:08 +08:00
|
|
|
lock_mode = 0;
|
2016-04-06 07:19:55 +08:00
|
|
|
|
|
|
|
|
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_attrinval, 0, 0, 0, &trans);
|
2015-05-29 05:40:08 +08:00
|
|
|
if (error)
|
2016-04-06 07:19:55 +08:00
|
|
|
goto out_destroy_fork;
|
2015-05-29 05:40:08 +08:00
|
|
|
|
|
|
|
|
lock_mode = XFS_ILOCK_EXCL;
|
|
|
|
|
xfs_ilock(dp, lock_mode);
|
|
|
|
|
|
|
|
|
|
if (!XFS_IFORK_Q(dp))
|
|
|
|
|
goto out_cancel;
|
2013-08-12 18:49:39 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* No need to make quota reservations here. We expect to release some
|
|
|
|
|
* blocks, not allocate, in the common case.
|
|
|
|
|
*/
|
|
|
|
|
xfs_trans_ijoin(trans, dp, 0);
|
|
|
|
|
|
2015-06-23 06:47:20 +08:00
|
|
|
/*
|
|
|
|
|
* Invalidate and truncate the attribute fork extents. Make sure the
|
|
|
|
|
* fork actually has attributes as otherwise the invalidation has no
|
|
|
|
|
* blocks to read and returns an error. In this case, just do the fork
|
|
|
|
|
* removal below.
|
|
|
|
|
*/
|
|
|
|
|
if (xfs_inode_hasattr(dp) &&
|
2020-05-19 01:28:05 +08:00
|
|
|
dp->i_afp->if_format != XFS_DINODE_FMT_LOCAL) {
|
2015-05-29 05:40:08 +08:00
|
|
|
error = xfs_attr3_root_inactive(&trans, dp);
|
|
|
|
|
if (error)
|
|
|
|
|
goto out_cancel;
|
|
|
|
|
|
|
|
|
|
error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
|
|
|
|
|
if (error)
|
|
|
|
|
goto out_cancel;
|
2013-08-12 18:49:39 +08:00
|
|
|
}
|
|
|
|
|
|
2015-05-29 05:40:08 +08:00
|
|
|
/* Reset the attribute fork - this also destroys the in-core fork */
|
|
|
|
|
xfs_attr_fork_remove(dp, trans);
|
2013-08-12 18:49:39 +08:00
|
|
|
|
2015-06-04 11:48:08 +08:00
|
|
|
error = xfs_trans_commit(trans);
|
2015-05-29 05:40:08 +08:00
|
|
|
xfs_iunlock(dp, lock_mode);
|
2014-06-22 13:03:54 +08:00
|
|
|
return error;
|
2013-08-12 18:49:39 +08:00
|
|
|
|
2015-05-29 05:40:08 +08:00
|
|
|
out_cancel:
|
2015-06-04 11:47:56 +08:00
|
|
|
xfs_trans_cancel(trans);
|
2015-05-29 05:40:08 +08:00
|
|
|
out_destroy_fork:
|
|
|
|
|
/* kill the in-core attr fork before we drop the inode lock */
|
2020-05-19 01:29:27 +08:00
|
|
|
if (dp->i_afp) {
|
|
|
|
|
xfs_idestroy_fork(dp->i_afp);
|
|
|
|
|
kmem_cache_free(xfs_ifork_zone, dp->i_afp);
|
|
|
|
|
dp->i_afp = NULL;
|
|
|
|
|
}
|
2015-05-29 05:40:08 +08:00
|
|
|
if (lock_mode)
|
|
|
|
|
xfs_iunlock(dp, lock_mode);
|
2014-06-22 13:03:54 +08:00
|
|
|
return error;
|
2013-08-12 18:49:39 +08:00
|
|
|
}
|