leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity
95dc8dd14e
linux/fs/xfs/xfs_attr_remote.c
Dave Chinner 7bc0dc271e xfs: rework remote attr CRCs 
Note: this changes the on-disk remote attribute format. I assert
that this is OK to do as CRCs are marked experimental and the first
kernel it is included in has not yet reached release yet. Further,
the userspace utilities are still evolving and so anyone using this
stuff right now is a developer or tester using volatile filesystems
for testing this feature. Hence changing the format right now to
save longer term pain is the right thing to do.

The fundamental change is to move from a header per extent in the
attribute to a header per filesytem block in the attribute. This
means there are more header blocks and the parsing of the attribute
data is slightly more complex, but it has the advantage that we
always know the size of the attribute on disk based on the length of
the data it contains.

This is where the header-per-extent method has problems. We don't
know the size of the attribute on disk without first knowing how
many extents are used to hold it. And we can't tell from a
mapping lookup, either, because remote attributes can be allocated
contiguously with other attribute blocks and so there is no obvious
way of determining the actual size of the atribute on disk short of
walking and mapping buffers.

The problem with this approach is that if we map a buffer
incorrectly (e.g. we make the last buffer for the attribute data too
long), we then get buffer cache lookup failure when we map it
correctly. i.e. we get a size mismatch on lookup. This is not
necessarily fatal, but it's a cache coherency problem that can lead
to returning the wrong data to userspace or writing the wrong data
to disk. And debug kernels will assert fail if this occurs.

I found lots of niggly little problems trying to fix this issue on a
4k block size filesystem, finally getting it to pass with lots of
fixes. The thing is, 1024 byte filesystems still failed, and it was
getting really complex handling all the corner cases that were
showing up. And there were clearly more that I hadn't found yet.

It is complex, fragile code, and if we don't fix it now, it will be
complex, fragile code forever more.

Hence the simple fix is to add a header to each filesystem block.
This gives us the same relationship between the attribute data
length and the number of blocks on disk as we have without CRCs -
it's a linear mapping and doesn't require us to guess anything. It
is simple to implement, too - the remote block count calculated at
lookup time can be used by the remote attribute set/get/remove code
without modification for both CRC and non-CRC filesystems. The world
becomes sane again.

Because the copy-in and copy-out now need to iterate over each
filesystem block, I moved them into helper functions so we separate
the block mapping and buffer manupulations from the attribute data
and CRC header manipulations. The code becomes much clearer as a
result, and it is a lot easier to understand and debug. It also
appears to be much more robust - once it worked on 4k block size
filesystems, it has worked without failure on 1k block size
filesystems, too.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Ben Myers <bpm@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

(cherry picked from commit ad1858d777)
2013-05-30 17:26:31 -05:00

632 lines
15 KiB
C
Raw Blame History

/*
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
* Copyright (c) 2013 Red Hat, 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 "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_error.h"
#include "xfs_da_btree.h"
#include "xfs_bmap_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_alloc.h"
#include "xfs_inode_item.h"
#include "xfs_bmap.h"
#include "xfs_attr.h"
#include "xfs_attr_leaf.h"
#include "xfs_attr_remote.h"
#include "xfs_trans_space.h"
#include "xfs_trace.h"
#include "xfs_cksum.h"
#include "xfs_buf_item.h"
#define ATTR_RMTVALUE_MAPSIZE 1 /* # of map entries at once */
/*
* Each contiguous block has a header, so it is not just a simple attribute
* length to FSB conversion.
*/
int
xfs_attr3_rmt_blocks(
struct xfs_mount *mp,
int attrlen)
{
if (xfs_sb_version_hascrc(&mp->m_sb)) {
int buflen = XFS_ATTR3_RMT_BUF_SPACE(mp, mp->m_sb.sb_blocksize);
return (attrlen + buflen - 1) / buflen;
}
return XFS_B_TO_FSB(mp, attrlen);
}
/*
* Checking of the remote attribute header is split into two parts. The verifier
* does CRC, location and bounds checking, the unpacking function checks the
* attribute parameters and owner.
*/
static bool
xfs_attr3_rmt_hdr_ok(
struct xfs_mount *mp,
void *ptr,
xfs_ino_t ino,
uint32_t offset,
uint32_t size,
xfs_daddr_t bno)
{
struct xfs_attr3_rmt_hdr *rmt = ptr;
if (bno != be64_to_cpu(rmt->rm_blkno))
return false;
if (offset != be32_to_cpu(rmt->rm_offset))
return false;
if (size != be32_to_cpu(rmt->rm_bytes))
return false;
if (ino != be64_to_cpu(rmt->rm_owner))
return false;
/* ok */
return true;
}
static bool
xfs_attr3_rmt_verify(
struct xfs_mount *mp,
void *ptr,
int fsbsize,
xfs_daddr_t bno)
{
struct xfs_attr3_rmt_hdr *rmt = ptr;
if (!xfs_sb_version_hascrc(&mp->m_sb))
return false;
if (rmt->rm_magic != cpu_to_be32(XFS_ATTR3_RMT_MAGIC))
return false;
if (!uuid_equal(&rmt->rm_uuid, &mp->m_sb.sb_uuid))
return false;
if (be64_to_cpu(rmt->rm_blkno) != bno)
return false;
if (be32_to_cpu(rmt->rm_bytes) > fsbsize - sizeof(*rmt))
return false;
if (be32_to_cpu(rmt->rm_offset) +
be32_to_cpu(rmt->rm_bytes) >= XATTR_SIZE_MAX)
return false;
if (rmt->rm_owner == 0)
return false;
return true;
}
static void
xfs_attr3_rmt_read_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
char *ptr;
int len;
bool corrupt = false;
xfs_daddr_t bno;
/* no verification of non-crc buffers */
if (!xfs_sb_version_hascrc(&mp->m_sb))
return;
ptr = bp->b_addr;
bno = bp->b_bn;
len = BBTOB(bp->b_length);
ASSERT(len >= XFS_LBSIZE(mp));
while (len > 0) {
if (!xfs_verify_cksum(ptr, XFS_LBSIZE(mp),
XFS_ATTR3_RMT_CRC_OFF)) {
corrupt = true;
break;
}
if (!xfs_attr3_rmt_verify(mp, ptr, XFS_LBSIZE(mp), bno)) {
corrupt = true;
break;
}
len -= XFS_LBSIZE(mp);
ptr += XFS_LBSIZE(mp);
bno += mp->m_bsize;
}
if (corrupt) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
xfs_buf_ioerror(bp, EFSCORRUPTED);
} else
ASSERT(len == 0);
}
static void
xfs_attr3_rmt_write_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
struct xfs_buf_log_item *bip = bp->b_fspriv;
char *ptr;
int len;
xfs_daddr_t bno;
/* no verification of non-crc buffers */
if (!xfs_sb_version_hascrc(&mp->m_sb))
return;
ptr = bp->b_addr;
bno = bp->b_bn;
len = BBTOB(bp->b_length);
ASSERT(len >= XFS_LBSIZE(mp));
while (len > 0) {
if (!xfs_attr3_rmt_verify(mp, ptr, XFS_LBSIZE(mp), bno)) {
XFS_CORRUPTION_ERROR(__func__,
XFS_ERRLEVEL_LOW, mp, bp->b_addr);
xfs_buf_ioerror(bp, EFSCORRUPTED);
return;
}
if (bip) {
struct xfs_attr3_rmt_hdr *rmt;
rmt = (struct xfs_attr3_rmt_hdr *)ptr;
rmt->rm_lsn = cpu_to_be64(bip->bli_item.li_lsn);
}
xfs_update_cksum(ptr, XFS_LBSIZE(mp), XFS_ATTR3_RMT_CRC_OFF);
len -= XFS_LBSIZE(mp);
ptr += XFS_LBSIZE(mp);
bno += mp->m_bsize;
}
ASSERT(len == 0);
}
const struct xfs_buf_ops xfs_attr3_rmt_buf_ops = {
.verify_read = xfs_attr3_rmt_read_verify,
.verify_write = xfs_attr3_rmt_write_verify,
};
STATIC int
xfs_attr3_rmt_hdr_set(
struct xfs_mount *mp,
void *ptr,
xfs_ino_t ino,
uint32_t offset,
uint32_t size,
xfs_daddr_t bno)
{
struct xfs_attr3_rmt_hdr *rmt = ptr;
if (!xfs_sb_version_hascrc(&mp->m_sb))
return 0;
rmt->rm_magic = cpu_to_be32(XFS_ATTR3_RMT_MAGIC);
rmt->rm_offset = cpu_to_be32(offset);
rmt->rm_bytes = cpu_to_be32(size);
uuid_copy(&rmt->rm_uuid, &mp->m_sb.sb_uuid);
rmt->rm_owner = cpu_to_be64(ino);
rmt->rm_blkno = cpu_to_be64(bno);
return sizeof(struct xfs_attr3_rmt_hdr);
}
/*
* Helper functions to copy attribute data in and out of the one disk extents
*/
STATIC int
xfs_attr_rmtval_copyout(
struct xfs_mount *mp,
struct xfs_buf *bp,
xfs_ino_t ino,
int *offset,
int *valuelen,
char **dst)
{
char *src = bp->b_addr;
xfs_daddr_t bno = bp->b_bn;
int len = BBTOB(bp->b_length);
ASSERT(len >= XFS_LBSIZE(mp));
while (len > 0 && *valuelen > 0) {
int hdr_size = 0;
int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, XFS_LBSIZE(mp));
byte_cnt = min_t(int, *valuelen, byte_cnt);
if (xfs_sb_version_hascrc(&mp->m_sb)) {
if (!xfs_attr3_rmt_hdr_ok(mp, src, ino, *offset,
byte_cnt, bno)) {
xfs_alert(mp,
"remote attribute header mismatch bno/off/len/owner (0x%llx/0x%x/Ox%x/0x%llx)",
bno, *offset, byte_cnt, ino);
return EFSCORRUPTED;
}
hdr_size = sizeof(struct xfs_attr3_rmt_hdr);
}
memcpy(*dst, src + hdr_size, byte_cnt);
/* roll buffer forwards */
len -= XFS_LBSIZE(mp);
src += XFS_LBSIZE(mp);
bno += mp->m_bsize;
/* roll attribute data forwards */
*valuelen -= byte_cnt;
*dst += byte_cnt;
*offset += byte_cnt;
}
return 0;
}
STATIC void
xfs_attr_rmtval_copyin(
struct xfs_mount *mp,
struct xfs_buf *bp,
xfs_ino_t ino,
int *offset,
int *valuelen,
char **src)
{
char *dst = bp->b_addr;
xfs_daddr_t bno = bp->b_bn;
int len = BBTOB(bp->b_length);
ASSERT(len >= XFS_LBSIZE(mp));
while (len > 0 && *valuelen > 0) {
int hdr_size;
int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, XFS_LBSIZE(mp));
byte_cnt = min(*valuelen, byte_cnt);
hdr_size = xfs_attr3_rmt_hdr_set(mp, dst, ino, *offset,
byte_cnt, bno);
memcpy(dst + hdr_size, *src, byte_cnt);
/*
* If this is the last block, zero the remainder of it.
* Check that we are actually the last block, too.
*/
if (byte_cnt + hdr_size < XFS_LBSIZE(mp)) {
ASSERT(*valuelen - byte_cnt == 0);
ASSERT(len == XFS_LBSIZE(mp));
memset(dst + hdr_size + byte_cnt, 0,
XFS_LBSIZE(mp) - hdr_size - byte_cnt);
}
/* roll buffer forwards */
len -= XFS_LBSIZE(mp);
dst += XFS_LBSIZE(mp);
bno += mp->m_bsize;
/* roll attribute data forwards */
*valuelen -= byte_cnt;
*src += byte_cnt;
*offset += byte_cnt;
}
}
/*
* Read the value associated with an attribute from the out-of-line buffer
* that we stored it in.
*/
int
xfs_attr_rmtval_get(
struct xfs_da_args *args)
{
struct xfs_bmbt_irec map[ATTR_RMTVALUE_MAPSIZE];
struct xfs_mount *mp = args->dp->i_mount;
struct xfs_buf *bp;
xfs_dablk_t lblkno = args->rmtblkno;
char *dst = args->value;
int valuelen = args->valuelen;
int nmap;
int error;
int blkcnt = args->rmtblkcnt;
int i;
int offset = 0;
trace_xfs_attr_rmtval_get(args);
ASSERT(!(args->flags & ATTR_KERNOVAL));
while (valuelen > 0) {
nmap = ATTR_RMTVALUE_MAPSIZE;
error = xfs_bmapi_read(args->dp, (xfs_fileoff_t)lblkno,
blkcnt, map, &nmap,
XFS_BMAPI_ATTRFORK);
if (error)
return error;
ASSERT(nmap >= 1);
for (i = 0; (i < nmap) && (valuelen > 0); i++) {
xfs_daddr_t dblkno;
int dblkcnt;
ASSERT((map[i].br_startblock != DELAYSTARTBLOCK) &&
(map[i].br_startblock != HOLESTARTBLOCK));
dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock);
dblkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
dblkno, dblkcnt, 0, &bp,
&xfs_attr3_rmt_buf_ops);
if (error)
return error;
error = xfs_attr_rmtval_copyout(mp, bp, args->dp->i_ino,
&offset, &valuelen,
&dst);
xfs_buf_relse(bp);
if (error)
return error;
/* roll attribute extent map forwards */
lblkno += map[i].br_blockcount;
blkcnt -= map[i].br_blockcount;
}
}
ASSERT(valuelen == 0);
return 0;
}
/*
* Write the value associated with an attribute into the out-of-line buffer
* that we have defined for it.
*/
int
xfs_attr_rmtval_set(
struct xfs_da_args *args)
{
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
struct xfs_bmbt_irec map;
xfs_dablk_t lblkno;
xfs_fileoff_t lfileoff = 0;
char *src = args->value;
int blkcnt;
int valuelen;
int nmap;
int error;
int offset = 0;
trace_xfs_attr_rmtval_set(args);
/*
* Find a "hole" in the attribute address space large enough for
* us to drop the new attribute's value into. Because CRC enable
* attributes have headers, we can't just do a straight byte to FSB
* conversion and have to take the header space into account.
*/
blkcnt = xfs_attr3_rmt_blocks(mp, args->valuelen);
error = xfs_bmap_first_unused(args->trans, args->dp, blkcnt, &lfileoff,
XFS_ATTR_FORK);
if (error)
return error;
args->rmtblkno = lblkno = (xfs_dablk_t)lfileoff;
args->rmtblkcnt = blkcnt;
/*
* Roll through the "value", allocating blocks on disk as required.
*/
while (blkcnt > 0) {
int committed;
/*
* Allocate a single extent, up to the size of the value.
*/
xfs_bmap_init(args->flist, args->firstblock);
nmap = 1;
error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
blkcnt,
XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA,
args->firstblock, args->total, &map, &nmap,
args->flist);
if (!error) {
error = xfs_bmap_finish(&args->trans, args->flist,
&committed);
}
if (error) {
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
return(error);
}
/*
* bmap_finish() may have committed the last trans and started
* a new one. We need the inode to be in all transactions.
*/
if (committed)
xfs_trans_ijoin(args->trans, dp, 0);
ASSERT(nmap == 1);
ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
(map.br_startblock != HOLESTARTBLOCK));
lblkno += map.br_blockcount;
blkcnt -= map.br_blockcount;
/*
* Start the next trans in the chain.
*/
error = xfs_trans_roll(&args->trans, dp);
if (error)
return (error);
}
/*
* Roll through the "value", copying the attribute value to the
* already-allocated blocks. Blocks are written synchronously
* so that we can know they are all on disk before we turn off
* the INCOMPLETE flag.
*/
lblkno = args->rmtblkno;
blkcnt = args->rmtblkcnt;
valuelen = args->valuelen;
while (valuelen > 0) {
struct xfs_buf *bp;
xfs_daddr_t dblkno;
int dblkcnt;
ASSERT(blkcnt > 0);
xfs_bmap_init(args->flist, args->firstblock);
nmap = 1;
error = xfs_bmapi_read(dp, (xfs_fileoff_t)lblkno,
blkcnt, &map, &nmap,
XFS_BMAPI_ATTRFORK);
if (error)
return(error);
ASSERT(nmap == 1);
ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
(map.br_startblock != HOLESTARTBLOCK));
dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
dblkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
bp = xfs_buf_get(mp->m_ddev_targp, dblkno, dblkcnt, 0);
if (!bp)
return ENOMEM;
bp->b_ops = &xfs_attr3_rmt_buf_ops;
xfs_attr_rmtval_copyin(mp, bp, args->dp->i_ino, &offset,
&valuelen, &src);
error = xfs_bwrite(bp); /* GROT: NOTE: synchronous write */
xfs_buf_relse(bp);
if (error)
return error;
/* roll attribute extent map forwards */
lblkno += map.br_blockcount;
blkcnt -= map.br_blockcount;
}
ASSERT(valuelen == 0);
return 0;
}
/*
* Remove the value associated with an attribute by deleting the
* out-of-line buffer that it is stored on.
*/
int
xfs_attr_rmtval_remove(
struct xfs_da_args *args)
{
struct xfs_mount *mp = args->dp->i_mount;
xfs_dablk_t lblkno;
int blkcnt;
int error;
int done;
trace_xfs_attr_rmtval_remove(args);
/*
* Roll through the "value", invalidating the attribute value's blocks.
* Note that args->rmtblkcnt is the minimum number of data blocks we'll
* see for a CRC enabled remote attribute. Each extent will have a
* header, and so we may have more blocks than we realise here. If we
* fail to map the blocks correctly, we'll have problems with the buffer
* lookups.
*/
lblkno = args->rmtblkno;
blkcnt = args->rmtblkcnt;
while (blkcnt > 0) {
struct xfs_bmbt_irec map;
struct xfs_buf *bp;
xfs_daddr_t dblkno;
int dblkcnt;
int nmap;
/*
* Try to remember where we decided to put the value.
*/
nmap = 1;
error = xfs_bmapi_read(args->dp, (xfs_fileoff_t)lblkno,
blkcnt, &map, &nmap, XFS_BMAPI_ATTRFORK);
if (error)
return(error);
ASSERT(nmap == 1);
ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
(map.br_startblock != HOLESTARTBLOCK));
dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
dblkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
/*
* If the "remote" value is in the cache, remove it.
*/
bp = xfs_incore(mp->m_ddev_targp, dblkno, dblkcnt, XBF_TRYLOCK);
if (bp) {
xfs_buf_stale(bp);
xfs_buf_relse(bp);
bp = NULL;
}
lblkno += map.br_blockcount;
blkcnt -= map.br_blockcount;
}
/*
* Keep de-allocating extents until the remote-value region is gone.
*/
lblkno = args->rmtblkno;
blkcnt = args->rmtblkcnt;
done = 0;
while (!done) {
int committed;
xfs_bmap_init(args->flist, args->firstblock);
error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA,
1, args->firstblock, args->flist,
&done);
if (!error) {
error = xfs_bmap_finish(&args->trans, args->flist,
&committed);
}
if (error) {
ASSERT(committed);
args->trans = NULL;
xfs_bmap_cancel(args->flist);
return error;
}
/*
* bmap_finish() may have committed the last trans and started
* a new one. We need the inode to be in all transactions.
*/
if (committed)
xfs_trans_ijoin(args->trans, args->dp, 0);
/*
* Close out trans and start the next one in the chain.
*/
error = xfs_trans_roll(&args->trans, args->dp);
if (error)
return (error);
}
return(0);
}
Reference in New Issue View Git Blame Copy Permalink