/*
* Mark bytes first through last inclusive as dirty in the buf
* item's bitmap.
*/
void
xfs_buf_item_log(
xfs_buf_log_item_t *bip,
uint first,
uint last)
{
int i;
uint start;
uint end;
struct xfs_buf *bp = bip->bli_buf;
/*
* walk each buffer segment and mark them dirty appropriately.
*/
start = 0;
for (i = 0; i < bip->bli_format_count; i++) {
if (start > last)
break;
end = start + BBTOB(bp->b_maps[i].bm_len);
if (first > end) {
start += BBTOB(bp->b_maps[i].bm_len);
continue;
}
if (first < start)
first = start;
if (end > last)
end = last;
xfs_buf_item_log_segment(first, end,
&bip->bli_formats[i].blf_data_map[0]);
start += bp->b_maps[i].bm_len;
}
}
/*
* initialize a buffer full of dquots and log the whole thing
*/
STATIC void
xfs_qm_init_dquot_blk(
xfs_trans_t *tp,
xfs_mount_t *mp,
xfs_dqid_t id,
uint type,
xfs_buf_t *bp)
{
xfs_dqblk_t *d;
int curid, i;
ASSERT(tp);
ASSERT(XFS_BUF_ISBUSY(bp));
ASSERT(XFS_BUF_VALUSEMA(bp) <= 0);
d = (xfs_dqblk_t *)XFS_BUF_PTR(bp);
/*
* ID of the first dquot in the block - id's are zero based.
*/
curid = id - (id % XFS_QM_DQPERBLK(mp));
ASSERT(curid >= 0);
memset(d, 0, BBTOB(XFS_QI_DQCHUNKLEN(mp)));
for (i = 0; i < XFS_QM_DQPERBLK(mp); i++, d++, curid++)
xfs_qm_dqinit_core(curid, type, d);
xfs_trans_dquot_buf(tp, bp,
(type & XFS_DQ_USER ? XFS_BLI_UDQUOT_BUF :
((type & XFS_DQ_PROJ) ? XFS_BLI_PDQUOT_BUF :
XFS_BLI_GDQUOT_BUF)));
xfs_trans_log_buf(tp, bp, 0, BBTOB(XFS_QI_DQCHUNKLEN(mp)) - 1);
}
/* Convert an xfs_fsmap to an fsmap. */
void
xfs_fsmap_from_internal(
struct fsmap *dest,
struct xfs_fsmap *src)
{
dest->fmr_device = src->fmr_device;
dest->fmr_flags = src->fmr_flags;
dest->fmr_physical = BBTOB(src->fmr_physical);
dest->fmr_owner = src->fmr_owner;
dest->fmr_offset = BBTOB(src->fmr_offset);
dest->fmr_length = BBTOB(src->fmr_length);
dest->fmr_reserved[0] = 0;
dest->fmr_reserved[1] = 0;
dest->fmr_reserved[2] = 0;
}
void
xfs_symlink_local_to_remote(
struct xfs_trans *tp,
struct xfs_buf *bp,
struct xfs_inode *ip,
struct xfs_ifork *ifp)
{
struct xfs_mount *mp = ip->i_mount;
char *buf;
xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF);
if (!xfs_sb_version_hascrc(&mp->m_sb)) {
bp->b_ops = NULL;
memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes);
xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1);
return;
}
/*
* As this symlink fits in an inode literal area, it must also fit in
* the smallest buffer the filesystem supports.
*/
ASSERT(BBTOB(bp->b_length) >=
ifp->if_bytes + sizeof(struct xfs_dsymlink_hdr));
bp->b_ops = &xfs_symlink_buf_ops;
buf = bp->b_addr;
buf += xfs_symlink_hdr_set(mp, ip->i_ino, 0, ifp->if_bytes, bp);
memcpy(buf, ifp->if_u1.if_data, ifp->if_bytes);
xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsymlink_hdr) +
ifp->if_bytes - 1);
}
/*
* This function is called to verify that our callers have logged
* all the bytes that they changed.
*
* It does this by comparing the original copy of the buffer stored in
* the buf log item's bli_orig array to the current copy of the buffer
* and ensuring that all bytes which mismatch are set in the bli_logged
* array of the buf log item.
*/
STATIC void
xfs_buf_item_log_check(
xfs_buf_log_item_t *bip)
{
char *orig;
char *buffer;
int x;
xfs_buf_t *bp;
ASSERT(bip->bli_orig != NULL);
ASSERT(bip->bli_logged != NULL);
bp = bip->bli_buf;
ASSERT(bp->b_length > 0);
ASSERT(bp->b_addr != NULL);
orig = bip->bli_orig;
buffer = bp->b_addr;
for (x = 0; x < BBTOB(bp->b_length); x++) {
if (orig[x] != buffer[x] && !btst(bip->bli_logged, x)) {
xfs_emerg(bp->b_mount,
"%s: bip %x buffer %x orig %x index %d",
__func__, bip, bp, orig, x);
ASSERT(0);
}
}
}
/* Initialize a new AG btree root block with zero entries. */
int
xrep_init_btblock(
struct xfs_scrub *sc,
xfs_fsblock_t fsb,
struct xfs_buf **bpp,
xfs_btnum_t btnum,
const struct xfs_buf_ops *ops)
{
struct xfs_trans *tp = sc->tp;
struct xfs_mount *mp = sc->mp;
struct xfs_buf *bp;
trace_xrep_init_btblock(mp, XFS_FSB_TO_AGNO(mp, fsb),
XFS_FSB_TO_AGBNO(mp, fsb), btnum);
ASSERT(XFS_FSB_TO_AGNO(mp, fsb) == sc->sa.agno);
bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, fsb),
XFS_FSB_TO_BB(mp, 1), 0);
xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
xfs_btree_init_block(mp, bp, btnum, 0, 0, sc->sa.agno, 0);
xfs_trans_buf_set_type(tp, bp, XFS_BLFT_BTREE_BUF);
xfs_trans_log_buf(tp, bp, 0, bp->b_length);
bp->b_ops = ops;
*bpp = bp;
return 0;
}
/*
* Warnings specifically for verifier errors. Differentiate CRC vs. invalid
* values, and omit the stack trace unless the error level is tuned high.
*/
void
xfs_verifier_error(
struct xfs_buf *bp)
{
xfs_alert(NULL, "Metadata %s detected at %s block 0x%llx/0x%x",
bp->b_error == -EFSBADCRC ? "CRC error" : "corruption",
bp->b_ops->name, bp->b_bn, BBTOB(bp->b_length));
}
/*
* Allocate a new buf log item to go with the given buffer.
* Set the buffer's b_fsprivate field to point to the new
* buf log item. If there are other item's attached to the
* buffer (see xfs_buf_attach_iodone() below), then put the
* buf log item at the front.
*/
void
xfs_buf_item_init(
xfs_buf_t *bp,
xfs_mount_t *mp)
{
xfs_log_item_t *lip = bp->b_fspriv;
xfs_buf_log_item_t *bip;
int chunks;
int map_size;
int error;
int i;
/*
* Check to see if there is already a buf log item for
* this buffer. If there is, it is guaranteed to be
* the first. If we do already have one, there is
* nothing to do here so return.
*/
ASSERT(bp->b_target->bt_mount == mp);
if (lip != NULL && lip->li_type == XFS_LI_BUF)
return;
bip = kmem_zone_zalloc(xfs_buf_item_zone, KM_SLEEP);
xfs_log_item_init(mp, &bip->bli_item, XFS_LI_BUF, &xfs_buf_item_ops);
bip->bli_buf = bp;
xfs_buf_hold(bp);
/*
* chunks is the number of XFS_BLF_CHUNK size pieces the buffer
* can be divided into. Make sure not to truncate any pieces.
* map_size is the size of the bitmap needed to describe the
* chunks of the buffer.
*
* Discontiguous buffer support follows the layout of the underlying
* buffer. This makes the implementation as simple as possible.
*/
error = xfs_buf_item_get_format(bip, bp->b_map_count);
ASSERT(error == 0);
for (i = 0; i < bip->bli_format_count; i++) {
chunks = DIV_ROUND_UP(BBTOB(bp->b_maps[i].bm_len),
XFS_BLF_CHUNK);
map_size = DIV_ROUND_UP(chunks, NBWORD);
bip->bli_formats[i].blf_type = XFS_LI_BUF;
bip->bli_formats[i].blf_blkno = bp->b_maps[i].bm_bn;
bip->bli_formats[i].blf_len = bp->b_maps[i].bm_len;
bip->bli_formats[i].blf_map_size = map_size;
}
/*
* Put the buf item into the list of items attached to the
* buffer at the front.
*/
if (bp->b_fspriv)
bip->bli_item.li_bio_list = bp->b_fspriv;
bp->b_fspriv = bip;
}
xfs_buf_t *
xfs_buf_get_flags(xfs_buftarg_t *target, xfs_daddr_t blkno, size_t len, int flags)
{
struct buf *bp = NULL;
KASSERT((target != NULL), ("got NULL buftarg_t"));
bp = getblk(target->specvp, blkno, BBTOB(len), 0, 0, 0);
if (bp != NULL)
xfs_buf_set_target(bp, target);
return (bp);
}
/*
* initialize a buffer full of dquots and log the whole thing
*/
STATIC void
xfs_qm_init_dquot_blk(
xfs_trans_t *tp,
xfs_mount_t *mp,
xfs_dqid_t id,
uint type,
xfs_buf_t *bp)
{
struct xfs_quotainfo *q = mp->m_quotainfo;
xfs_dqblk_t *d;
int curid, i;
ASSERT(tp);
ASSERT(xfs_buf_islocked(bp));
d = bp->b_addr;
/*
* ID of the first dquot in the block - id's are zero based.
*/
curid = id - (id % q->qi_dqperchunk);
ASSERT(curid >= 0);
memset(d, 0, BBTOB(q->qi_dqchunklen));
for (i = 0; i < q->qi_dqperchunk; i++, d++, curid++) {
d->dd_diskdq.d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
d->dd_diskdq.d_version = XFS_DQUOT_VERSION;
d->dd_diskdq.d_id = cpu_to_be32(curid);
d->dd_diskdq.d_flags = type;
if (xfs_sb_version_hascrc(&mp->m_sb)) {
uuid_copy(&d->dd_uuid, &mp->m_sb.sb_uuid);
xfs_update_cksum((char *)d, sizeof(struct xfs_dqblk),
XFS_DQUOT_CRC_OFF);
}
}
xfs_trans_dquot_buf(tp, bp,
(type & XFS_DQ_USER ? XFS_BLF_UDQUOT_BUF :
((type & XFS_DQ_PROJ) ? XFS_BLF_PDQUOT_BUF :
XFS_BLF_GDQUOT_BUF)));
xfs_trans_log_buf(tp, bp, 0, BBTOB(q->qi_dqchunklen) - 1);
}
xfs_buf_t *
xfs_buf_read_flags(xfs_buftarg_t *target, xfs_daddr_t blkno, size_t len, int flags)
{
struct buf *bp;
KASSERT((target != NULL), ("got NULL buftarg_t"));
if (bread(target->specvp, blkno, BBTOB(len), NOCRED, &bp)) {
printf("bread failed specvp %p blkno %qd BBTOB(len) %ld\n",
target->specvp, blkno, (long)BBTOB(len));
bp = NULL;
}
/* not really sure what B_MANAGED really does for us
* maybe we should drop this and just stick with a locked buf
*/
if (flags & B_MANAGED)
bp->b_flags |= B_MANAGED;
xfs_buf_set_target(bp, target);
return (bp);
}
int
xfs_calc_dquots_per_chunk(
struct xfs_mount *mp,
unsigned int nbblks) /* basic block units */
{
unsigned int ndquots;
ASSERT(nbblks > 0);
ndquots = BBTOB(nbblks);
do_div(ndquots, sizeof(xfs_dqblk_t));
return ndquots;
}
/*
* Call fiemap helper to fill in user data.
* Returns positive errors to xfs_getbmap.
*/
STATIC int
xfs_fiemap_format(
void **arg,
struct getbmapx *bmv,
int *full)
{
int error;
struct fiemap_extent_info *fieinfo = *arg;
u32 fiemap_flags = 0;
u64 logical, physical, length;
/* Do nothing for a hole */
if (bmv->bmv_block == -1LL)
return 0;
logical = BBTOB(bmv->bmv_offset);
physical = BBTOB(bmv->bmv_block);
length = BBTOB(bmv->bmv_length);
if (bmv->bmv_oflags & BMV_OF_PREALLOC)
fiemap_flags |= FIEMAP_EXTENT_UNWRITTEN;
else if (bmv->bmv_oflags & BMV_OF_DELALLOC) {
fiemap_flags |= (FIEMAP_EXTENT_DELALLOC |
FIEMAP_EXTENT_UNKNOWN);
physical = 0; /* no block yet */
}
if (bmv->bmv_oflags & BMV_OF_LAST)
fiemap_flags |= FIEMAP_EXTENT_LAST;
error = fiemap_fill_next_extent(fieinfo, logical, physical,
length, fiemap_flags);
if (error > 0) {
error = 0;
*full = 1; /* user array now full */
}
return -error;
}
void
xfs_buf_readahead(
xfs_buftarg_t *target,
xfs_daddr_t ioff,
size_t isize,
xfs_buf_flags_t flags)
{
daddr_t rablkno;
int rabsize;
rablkno = ioff;
rabsize = BBTOB(isize);
breada(target->specvp, &rablkno, &rabsize, 1, NOCRED);
}
static void
xfs_dir3_block_read_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
if ((xfs_sb_version_hascrc(&mp->m_sb) &&
!xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
XFS_DIR3_DATA_CRC_OFF)) ||
!xfs_dir3_block_verify(bp)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
xfs_buf_ioerror(bp, EFSCORRUPTED);
}
}
STATIC void
xfs_attr_rmtval_copyin(
struct xfs_mount *mp,
struct xfs_buf *bp,
xfs_ino_t ino,
int *offset,
int *valuelen,
__uint8_t **src)
{
char *dst = bp->b_addr;
xfs_daddr_t bno = bp->b_bn;
int len = BBTOB(bp->b_length);
int blksize = mp->m_attr_geo->blksize;
ASSERT(len >= blksize);
while (len > 0 && *valuelen > 0) {
int hdr_size;
int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, blksize);
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 < blksize) {
ASSERT(*valuelen - byte_cnt == 0);
ASSERT(len == blksize);
memset(dst + hdr_size + byte_cnt, 0,
blksize - hdr_size - byte_cnt);
}
/* roll buffer forwards */
len -= blksize;
dst += blksize;
bno += BTOBB(blksize);
/* roll attribute data forwards */
*valuelen -= byte_cnt;
*src += byte_cnt;
*offset += byte_cnt;
}
}
static void
xfs_attr3_rmt_write_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
xfs_failaddr_t fa;
int blksize = mp->m_attr_geo->blksize;
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 >= blksize);
while (len > 0) {
struct xfs_attr3_rmt_hdr *rmt = (struct xfs_attr3_rmt_hdr *)ptr;
fa = xfs_attr3_rmt_verify(mp, ptr, blksize, bno);
if (fa) {
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
return;
}
/*
* Ensure we aren't writing bogus LSNs to disk. See
* xfs_attr3_rmt_hdr_set() for the explanation.
*/
if (rmt->rm_lsn != cpu_to_be64(NULLCOMMITLSN)) {
xfs_verifier_error(bp, -EFSCORRUPTED, __this_address);
return;
}
xfs_update_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF);
len -= blksize;
ptr += blksize;
bno += BTOBB(blksize);
}
if (len != 0)
xfs_verifier_error(bp, -EFSCORRUPTED, __this_address);
}
/*
* 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,
__uint8_t **dst)
{
char *src = bp->b_addr;
xfs_daddr_t bno = bp->b_bn;
int len = BBTOB(bp->b_length);
int blksize = mp->m_attr_geo->blksize;
ASSERT(len >= blksize);
while (len > 0 && *valuelen > 0) {
int hdr_size = 0;
int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, blksize);
byte_cnt = min(*valuelen, byte_cnt);
if (xfs_sb_version_hascrc(&mp->m_sb)) {
if (!xfs_attr3_rmt_hdr_ok(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 -= blksize;
src += blksize;
bno += BTOBB(blksize);
/* roll attribute data forwards */
*valuelen -= byte_cnt;
*dst += byte_cnt;
*offset += byte_cnt;
}
return 0;
}
/* XXX: (dgc) Propagate errors, only exit if fail-on-error flag set */
int
libxfs_device_zero(struct xfs_buftarg *btp, xfs_daddr_t start, uint len)
{
xfs_off_t start_offset, end_offset, offset;
ssize_t zsize, bytes;
char *z;
int fd;
zsize = min(BDSTRAT_SIZE, BBTOB(len));
if ((z = memalign(libxfs_device_alignment(), zsize)) == NULL) {
fprintf(stderr,
_("%s: %s can't memalign %d bytes: %s\n"),
progname, __FUNCTION__, (int)zsize, strerror(errno));
exit(1);
}
memset(z, 0, zsize);
fd = libxfs_device_to_fd(btp->dev);
start_offset = LIBXFS_BBTOOFF64(start);
if ((lseek64(fd, start_offset, SEEK_SET)) < 0) {
fprintf(stderr, _("%s: %s seek to offset %llu failed: %s\n"),
progname, __FUNCTION__,
(unsigned long long)start_offset, strerror(errno));
exit(1);
}
end_offset = LIBXFS_BBTOOFF64(start + len) - start_offset;
for (offset = 0; offset < end_offset; ) {
bytes = min((ssize_t)(end_offset - offset), zsize);
if ((bytes = write(fd, z, bytes)) < 0) {
fprintf(stderr, _("%s: %s write failed: %s\n"),
progname, __FUNCTION__, strerror(errno));
exit(1);
} else if (bytes == 0) {
fprintf(stderr, _("%s: %s not progressing?\n"),
progname, __FUNCTION__);
exit(1);
}
offset += bytes;
}
free(z);
return 0;
}
static int
__xfs_attr3_rmt_read_verify(
struct xfs_buf *bp,
bool check_crc,
xfs_failaddr_t *failaddr)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
char *ptr;
int len;
xfs_daddr_t bno;
int blksize = mp->m_attr_geo->blksize;
/* no verification of non-crc buffers */
if (!xfs_sb_version_hascrc(&mp->m_sb))
return 0;
ptr = bp->b_addr;
bno = bp->b_bn;
len = BBTOB(bp->b_length);
ASSERT(len >= blksize);
while (len > 0) {
if (check_crc &&
!xfs_verify_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF)) {
*failaddr = __this_address;
return -EFSBADCRC;
}
*failaddr = xfs_attr3_rmt_verify(mp, ptr, blksize, bno);
if (*failaddr)
return -EFSCORRUPTED;
len -= blksize;
ptr += blksize;
bno += BTOBB(blksize);
}
if (len != 0) {
*failaddr = __this_address;
return -EFSCORRUPTED;
}
return 0;
}
static struct xfs_buf *
xfs_get_aghdr_buf(
struct xfs_mount *mp,
xfs_daddr_t blkno,
size_t numblks,
int flags,
const struct xfs_buf_ops *ops)
{
struct xfs_buf *bp;
bp = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, flags);
if (!bp)
return NULL;
xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
bp->b_bn = blkno;
bp->b_maps[0].bm_bn = blkno;
bp->b_ops = ops;
return bp;
}
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);
}
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;
int blksize = mp->m_attr_geo->blksize;
/* 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 >= blksize);
while (len > 0) {
if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) {
xfs_buf_ioerror(bp, -EFSCORRUPTED);
xfs_verifier_error(bp);
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, blksize, XFS_ATTR3_RMT_CRC_OFF);
len -= blksize;
ptr += blksize;
bno += BTOBB(blksize);
}
ASSERT(len == 0);
}
static void
xfs_dir3_block_write_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
struct xfs_buf_log_item *bip = bp->b_fspriv;
struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr;
if (!xfs_dir3_block_verify(bp)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr);
xfs_buf_ioerror(bp, EFSCORRUPTED);
return;
}
if (!xfs_sb_version_hascrc(&mp->m_sb))
return;
if (bip)
hdr3->lsn = cpu_to_be64(bip->bli_item.li_lsn);
xfs_update_cksum(bp->b_addr, BBTOB(bp->b_length), XFS_DIR3_DATA_CRC_OFF);
}
static void
xfs_attr3_rmt_read_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
char *ptr;
int len;
xfs_daddr_t bno;
int blksize = mp->m_attr_geo->blksize;
/* 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 >= blksize);
while (len > 0) {
if (!xfs_verify_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF)) {
xfs_buf_ioerror(bp, -EFSBADCRC);
break;
}
if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) {
xfs_buf_ioerror(bp, -EFSCORRUPTED);
break;
}
len -= blksize;
ptr += blksize;
bno += BTOBB(blksize);
}
if (bp->b_error)
xfs_verifier_error(bp);
else
ASSERT(len == 0);
}
/*
* Check that the holemask and freemask of a hypothetical inode cluster match
* what's actually on disk. If sparse inodes are enabled, the cluster does
* not actually have to map to inodes if the corresponding holemask bit is set.
*
* @cluster_base is the first inode in the cluster within the @irec.
*/
STATIC int
xchk_iallocbt_check_cluster(
struct xchk_btree *bs,
struct xfs_inobt_rec_incore *irec,
unsigned int cluster_base)
{
struct xfs_imap imap;
struct xfs_mount *mp = bs->cur->bc_mp;
struct xfs_dinode *dip;
struct xfs_buf *cluster_bp;
unsigned int nr_inodes;
xfs_agnumber_t agno = bs->cur->bc_private.a.agno;
xfs_agblock_t agbno;
unsigned int cluster_index;
uint16_t cluster_mask = 0;
uint16_t ir_holemask;
int error = 0;
nr_inodes = min_t(unsigned int, XFS_INODES_PER_CHUNK,
mp->m_inodes_per_cluster);
/* Map this inode cluster */
agbno = XFS_AGINO_TO_AGBNO(mp, irec->ir_startino + cluster_base);
/* Compute a bitmask for this cluster that can be used for holemask. */
for (cluster_index = 0;
cluster_index < nr_inodes;
cluster_index += XFS_INODES_PER_HOLEMASK_BIT)
cluster_mask |= XFS_INOBT_MASK((cluster_base + cluster_index) /
XFS_INODES_PER_HOLEMASK_BIT);
/*
* Map the first inode of this cluster to a buffer and offset.
* Be careful about inobt records that don't align with the start of
* the inode buffer when block sizes are large enough to hold multiple
* inode chunks. When this happens, cluster_base will be zero but
* ir_startino can be large enough to make im_boffset nonzero.
*/
ir_holemask = (irec->ir_holemask & cluster_mask);
imap.im_blkno = XFS_AGB_TO_DADDR(mp, agno, agbno);
imap.im_len = XFS_FSB_TO_BB(mp, mp->m_blocks_per_cluster);
imap.im_boffset = XFS_INO_TO_OFFSET(mp, irec->ir_startino);
if (imap.im_boffset != 0 && cluster_base != 0) {
ASSERT(imap.im_boffset == 0 || cluster_base == 0);
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
return 0;
}
trace_xchk_iallocbt_check_cluster(mp, agno, irec->ir_startino,
imap.im_blkno, imap.im_len, cluster_base, nr_inodes,
cluster_mask, ir_holemask,
XFS_INO_TO_OFFSET(mp, irec->ir_startino +
cluster_base));
/* The whole cluster must be a hole or not a hole. */
if (ir_holemask != cluster_mask && ir_holemask != 0) {
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
return 0;
}
/* If any part of this is a hole, skip it. */
if (ir_holemask) {
xchk_xref_is_not_owned_by(bs->sc, agbno,
mp->m_blocks_per_cluster,
&XFS_RMAP_OINFO_INODES);
return 0;
}
xchk_xref_is_owned_by(bs->sc, agbno, mp->m_blocks_per_cluster,
&XFS_RMAP_OINFO_INODES);
/* Grab the inode cluster buffer. */
error = xfs_imap_to_bp(mp, bs->cur->bc_tp, &imap, &dip, &cluster_bp,
0, 0);
if (!xchk_btree_xref_process_error(bs->sc, bs->cur, 0, &error))
return error;
/* Check free status of each inode within this cluster. */
for (cluster_index = 0; cluster_index < nr_inodes; cluster_index++) {
struct xfs_dinode *dip;
if (imap.im_boffset >= BBTOB(cluster_bp->b_length)) {
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
break;
}
dip = xfs_buf_offset(cluster_bp, imap.im_boffset);
error = xchk_iallocbt_check_cluster_ifree(bs, irec,
cluster_base + cluster_index, dip);
if (error)
break;
imap.im_boffset += mp->m_sb.sb_inodesize;
}
xfs_trans_brelse(bs->cur->bc_tp, cluster_bp);
return error;
}
/*
* Allocate a new buf log item to go with the given buffer.
* Set the buffer's b_fsprivate field to point to the new
* buf log item. If there are other item's attached to the
* buffer (see xfs_buf_attach_iodone() below), then put the
* buf log item at the front.
*/
void
xfs_buf_item_init(
xfs_buf_t *bp,
xfs_mount_t *mp)
{
xfs_log_item_t *lip = bp->b_fspriv;
xfs_buf_log_item_t *bip;
int chunks;
int map_size;
int error;
int i;
/*
* Check to see if there is already a buf log item for
* this buffer. If there is, it is guaranteed to be
* the first. If we do already have one, there is
* nothing to do here so return.
*/
ASSERT(bp->b_target->bt_mount == mp);
if (lip != NULL && lip->li_type == XFS_LI_BUF)
return;
bip = kmem_zone_zalloc(xfs_buf_item_zone, KM_SLEEP);
xfs_log_item_init(mp, &bip->bli_item, XFS_LI_BUF, &xfs_buf_item_ops);
bip->bli_buf = bp;
xfs_buf_hold(bp);
/*
* chunks is the number of XFS_BLF_CHUNK size pieces the buffer
* can be divided into. Make sure not to truncate any pieces.
* map_size is the size of the bitmap needed to describe the
* chunks of the buffer.
*
* Discontiguous buffer support follows the layout of the underlying
* buffer. This makes the implementation as simple as possible.
*/
error = xfs_buf_item_get_format(bip, bp->b_map_count);
ASSERT(error == 0);
for (i = 0; i < bip->bli_format_count; i++) {
chunks = DIV_ROUND_UP(BBTOB(bp->b_maps[i].bm_len),
XFS_BLF_CHUNK);
map_size = DIV_ROUND_UP(chunks, NBWORD);
bip->bli_formats[i].blf_type = XFS_LI_BUF;
bip->bli_formats[i].blf_blkno = bp->b_maps[i].bm_bn;
bip->bli_formats[i].blf_len = bp->b_maps[i].bm_len;
bip->bli_formats[i].blf_map_size = map_size;
}
#ifdef XFS_TRANS_DEBUG
/*
* Allocate the arrays for tracking what needs to be logged
* and what our callers request to be logged. bli_orig
* holds a copy of the original, clean buffer for comparison
* against, and bli_logged keeps a 1 bit flag per byte in
* the buffer to indicate which bytes the callers have asked
* to have logged.
*/
bip->bli_orig = kmem_alloc(BBTOB(bp->b_length), KM_SLEEP);
memcpy(bip->bli_orig, bp->b_addr, BBTOB(bp->b_length));
bip->bli_logged = kmem_zalloc(BBTOB(bp->b_length) / NBBY, KM_SLEEP);
#endif
/*
* Put the buf item into the list of items attached to the
* buffer at the front.
*/
if (bp->b_fspriv)
bip->bli_item.li_bio_list = bp->b_fspriv;
bp->b_fspriv = bip;
}
static void
zero_log(xfs_mount_t *mp)
{
int error;
xlog_t log;
xfs_daddr_t head_blk, tail_blk;
dev_t logdev = (mp->m_sb.sb_logstart == 0) ? x.logdev : x.ddev;
memset(&log, 0, sizeof(log));
if (!x.logdev)
x.logdev = x.ddev;
x.logBBsize = XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
x.logBBstart = XFS_FSB_TO_DADDR(mp, mp->m_sb.sb_logstart);
log.l_dev = logdev;
log.l_logsize = BBTOB(x.logBBsize);
log.l_logBBsize = x.logBBsize;
log.l_logBBstart = x.logBBstart;
log.l_mp = mp;
if (xfs_sb_version_hassector(&mp->m_sb)) {
log.l_sectbb_log = mp->m_sb.sb_logsectlog - BBSHIFT;
ASSERT(log.l_sectbb_log <= mp->m_sectbb_log);
/* for larger sector sizes, must have v2 or external log */
ASSERT(log.l_sectbb_log == 0 ||
log.l_logBBstart == 0 ||
xfs_sb_version_haslogv2(&mp->m_sb));
ASSERT(mp->m_sb.sb_logsectlog >= BBSHIFT);
}
log.l_sectbb_mask = (1 << log.l_sectbb_log) - 1;
if ((error = xlog_find_tail(&log, &head_blk, &tail_blk))) {
do_warn(_("zero_log: cannot find log head/tail "
"(xlog_find_tail=%d), zeroing it anyway\n"),
error);
} else {
if (verbose) {
do_warn(_("zero_log: head block %lld tail block %lld\n"),
head_blk, tail_blk);
}
if (head_blk != tail_blk) {
if (zap_log) {
do_warn(_(
"ALERT: The filesystem has valuable metadata changes in a log which is being\n"
"destroyed because the -L option was used.\n"));
} else {
do_warn(_(
"ERROR: The filesystem has valuable metadata changes in a log which needs to\n"
"be replayed. Mount the filesystem to replay the log, and unmount it before\n"
"re-running xfs_repair. If you are unable to mount the filesystem, then use\n"
"the -L option to destroy the log and attempt a repair.\n"
"Note that destroying the log may cause corruption -- please attempt a mount\n"
"of the filesystem before doing this.\n"));
exit(2);
}
}
}
libxfs_log_clear(logdev,
XFS_FSB_TO_DADDR(mp, mp->m_sb.sb_logstart),
(xfs_extlen_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks),
&mp->m_sb.sb_uuid,
xfs_sb_version_haslogv2(&mp->m_sb) ? 2 : 1,
mp->m_sb.sb_logsunit, XLOG_FMT);
}
/*
* This initializes all the quota information that's kept in the
* mount structure
*/
STATIC int
xfs_qm_init_quotainfo(
xfs_mount_t *mp)
{
xfs_quotainfo_t *qinf;
int error;
xfs_dquot_t *dqp;
ASSERT(XFS_IS_QUOTA_RUNNING(mp));
qinf = mp->m_quotainfo = kmem_zalloc(sizeof(xfs_quotainfo_t), KM_SLEEP);
/*
* See if quotainodes are setup, and if not, allocate them,
* and change the superblock accordingly.
*/
if ((error = xfs_qm_init_quotainos(mp))) {
kmem_free(qinf);
mp->m_quotainfo = NULL;
return error;
}
INIT_RADIX_TREE(&qinf->qi_uquota_tree, GFP_NOFS);
INIT_RADIX_TREE(&qinf->qi_gquota_tree, GFP_NOFS);
mutex_init(&qinf->qi_tree_lock);
INIT_LIST_HEAD(&qinf->qi_lru_list);
qinf->qi_lru_count = 0;
mutex_init(&qinf->qi_lru_lock);
/* mutex used to serialize quotaoffs */
mutex_init(&qinf->qi_quotaofflock);
/* Precalc some constants */
qinf->qi_dqchunklen = XFS_FSB_TO_BB(mp, XFS_DQUOT_CLUSTER_SIZE_FSB);
ASSERT(qinf->qi_dqchunklen);
qinf->qi_dqperchunk = BBTOB(qinf->qi_dqchunklen);
do_div(qinf->qi_dqperchunk, sizeof(xfs_dqblk_t));
mp->m_qflags |= (mp->m_sb.sb_qflags & XFS_ALL_QUOTA_CHKD);
/*
* We try to get the limits from the superuser's limits fields.
* This is quite hacky, but it is standard quota practice.
*
* We look at the USR dquot with id == 0 first, but if user quotas
* are not enabled we goto the GRP dquot with id == 0.
* We don't really care to keep separate default limits for user
* and group quotas, at least not at this point.
*
* Since we may not have done a quotacheck by this point, just read
* the dquot without attaching it to any hashtables or lists.
*/
error = xfs_qm_dqread(mp, 0,
XFS_IS_UQUOTA_RUNNING(mp) ? XFS_DQ_USER :
(XFS_IS_GQUOTA_RUNNING(mp) ? XFS_DQ_GROUP :
XFS_DQ_PROJ),
XFS_QMOPT_DOWARN, &dqp);
if (!error) {
xfs_disk_dquot_t *ddqp = &dqp->q_core;
/*
* The warnings and timers set the grace period given to
* a user or group before he or she can not perform any
* more writing. If it is zero, a default is used.
*/
qinf->qi_btimelimit = ddqp->d_btimer ?
be32_to_cpu(ddqp->d_btimer) : XFS_QM_BTIMELIMIT;
qinf->qi_itimelimit = ddqp->d_itimer ?
be32_to_cpu(ddqp->d_itimer) : XFS_QM_ITIMELIMIT;
qinf->qi_rtbtimelimit = ddqp->d_rtbtimer ?
be32_to_cpu(ddqp->d_rtbtimer) : XFS_QM_RTBTIMELIMIT;
qinf->qi_bwarnlimit = ddqp->d_bwarns ?
be16_to_cpu(ddqp->d_bwarns) : XFS_QM_BWARNLIMIT;
qinf->qi_iwarnlimit = ddqp->d_iwarns ?
be16_to_cpu(ddqp->d_iwarns) : XFS_QM_IWARNLIMIT;
qinf->qi_rtbwarnlimit = ddqp->d_rtbwarns ?
be16_to_cpu(ddqp->d_rtbwarns) : XFS_QM_RTBWARNLIMIT;
qinf->qi_bhardlimit = be64_to_cpu(ddqp->d_blk_hardlimit);
qinf->qi_bsoftlimit = be64_to_cpu(ddqp->d_blk_softlimit);
qinf->qi_ihardlimit = be64_to_cpu(ddqp->d_ino_hardlimit);
qinf->qi_isoftlimit = be64_to_cpu(ddqp->d_ino_softlimit);
qinf->qi_rtbhardlimit = be64_to_cpu(ddqp->d_rtb_hardlimit);
qinf->qi_rtbsoftlimit = be64_to_cpu(ddqp->d_rtb_softlimit);
xfs_qm_dqdestroy(dqp);
} else {
qinf->qi_btimelimit = XFS_QM_BTIMELIMIT;
qinf->qi_itimelimit = XFS_QM_ITIMELIMIT;
qinf->qi_rtbtimelimit = XFS_QM_RTBTIMELIMIT;
qinf->qi_bwarnlimit = XFS_QM_BWARNLIMIT;
qinf->qi_iwarnlimit = XFS_QM_IWARNLIMIT;
qinf->qi_rtbwarnlimit = XFS_QM_RTBWARNLIMIT;
}
qinf->qi_shrinker.shrink = xfs_qm_shake;
qinf->qi_shrinker.seeks = DEFAULT_SEEKS;
register_shrinker(&qinf->qi_shrinker);
return 0;
}
