int xfs_readfile_btree(xfs_inode_t *ip, void *buffer, off_t offset, size_t len, int *last_extent) {
xfs_extnum_t nextents;
xfs_extnum_t extent;
xfs_ifork_t *dp;
xfs_bmbt_rec_host_t *ep;
xfs_bmbt_irec_t rec;
xfs_mount_t *mp = ip->i_mount; /* filesystem mount point */
xfs_fsize_t size = ip->i_d.di_size;
int error;
if (offset >= size) return 0;
if (offset + len > size)
len = size - offset;
dp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
if (!(dp->if_flags & XFS_IFEXTENTS) &&
(error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK)))
return error;
nextents = XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK);
for (extent=0; extent<nextents; extent++) {
ep = xfs_iext_get_ext(dp, extent);
xfs_bmbt_get_all(ep, &rec);
if (extent_overlaps_buffer(mp, rec, offset, len)) {
error = copy_extent_to_buffer(mp, rec, buffer, offset, len);
if (error) return error;
}
}
return len;
}
/*
* Find the CoW reservation for a given byte offset of a file.
*/
bool
xfs_reflink_find_cow_mapping(
struct xfs_inode *ip,
xfs_off_t offset,
struct xfs_bmbt_irec *imap)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
xfs_fileoff_t offset_fsb;
struct xfs_bmbt_irec got;
xfs_extnum_t idx;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED));
ASSERT(xfs_is_reflink_inode(ip));
offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got))
return false;
if (got.br_startoff > offset_fsb)
return false;
trace_xfs_reflink_find_cow_mapping(ip, offset, 1, XFS_IO_OVERWRITE,
&got);
*imap = got;
return true;
}
/*
* Given a block number in a fork, return the next valid block number
* (not a hole).
* If this is the last block number then NULLFILEOFF is returned.
*
* This was originally in the kernel, but only used in xfs_repair.
*/
int
libxfs_bmap_next_offset(
xfs_trans_t *tp, /* transaction pointer */
xfs_inode_t *ip, /* incore inode */
xfs_fileoff_t *bnop, /* current block */
int whichfork) /* data or attr fork */
{
xfs_fileoff_t bno; /* current block */
int eof; /* hit end of file */
int error; /* error return value */
xfs_bmbt_irec_t got; /* current extent value */
xfs_ifork_t *ifp; /* inode fork pointer */
xfs_extnum_t lastx; /* last extent used */
xfs_bmbt_irec_t prev; /* previous extent value */
if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE &&
XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL)
return XFS_ERROR(EIO);
if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) {
*bnop = NULLFILEOFF;
return 0;
}
ifp = XFS_IFORK_PTR(ip, whichfork);
if (!(ifp->if_flags & XFS_IFEXTENTS) &&
(error = xfs_iread_extents(tp, ip, whichfork)))
return error;
bno = *bnop + 1;
xfs_bmap_search_extents(ip, bno, whichfork, &eof, &lastx, &got, &prev);
if (eof)
*bnop = NULLFILEOFF;
else
*bnop = got.br_startoff < bno ? bno : got.br_startoff;
return 0;
}
/*
* Verify the in-memory consistency of an inline symlink data fork. This
* does not do on-disk format checks.
*/
xfs_failaddr_t
xfs_symlink_shortform_verify(
struct xfs_inode *ip)
{
char *sfp;
char *endp;
struct xfs_ifork *ifp;
int size;
ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_LOCAL);
ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
sfp = (char *)ifp->if_u1.if_data;
size = ifp->if_bytes;
endp = sfp + size;
/*
* Zero length symlinks should never occur in memory as they are
* never alllowed to exist on disk.
*/
if (!size)
return __this_address;
/* No negative sizes or overly long symlink targets. */
if (size < 0 || size > XFS_SYMLINK_MAXLEN)
return __this_address;
/* No NULLs in the target either. */
if (memchr(sfp, 0, size - 1))
return __this_address;
/* We /did/ null-terminate the buffer, right? */
if (*endp != 0)
return __this_address;
return NULL;
}
/*
* Trim an extent to end at the next CoW reservation past offset_fsb.
*/
void
xfs_reflink_trim_irec_to_next_cow(
struct xfs_inode *ip,
xfs_fileoff_t offset_fsb,
struct xfs_bmbt_irec *imap)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got;
xfs_extnum_t idx;
if (!xfs_is_reflink_inode(ip))
return;
/* Find the extent in the CoW fork. */
if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got))
return;
/* This is the extent before; try sliding up one. */
if (got.br_startoff < offset_fsb) {
if (!xfs_iext_get_extent(ifp, idx + 1, &got))
return;
}
if (got.br_startoff >= imap->br_startoff + imap->br_blockcount)
return;
imap->br_blockcount = got.br_startoff - imap->br_startoff;
trace_xfs_reflink_trim_irec(ip, imap);
}
/* Convert all of the unwritten CoW extents in a file's range to real ones. */
int
xfs_reflink_convert_cow(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t count)
{
struct xfs_bmbt_irec got;
struct xfs_defer_ops dfops;
struct xfs_mount *mp = ip->i_mount;
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + count);
xfs_extnum_t idx;
bool found;
int error = 0;
xfs_ilock(ip, XFS_ILOCK_EXCL);
/* Convert all the extents to real from unwritten. */
for (found = xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got);
found && got.br_startoff < end_fsb;
found = xfs_iext_get_extent(ifp, ++idx, &got)) {
error = xfs_reflink_convert_cow_extent(ip, &got, offset_fsb,
end_fsb - offset_fsb, &dfops);
if (error)
break;
}
/* Finish up. */
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
/*
* Trim the passed in imap to the next shared/unshared extent boundary, and
* if imap->br_startoff points to a shared extent reserve space for it in the
* COW fork. In this case *shared is set to true, else to false.
*
* Note that imap will always contain the block numbers for the existing blocks
* in the data fork, as the upper layers need them for read-modify-write
* operations.
*/
int
xfs_reflink_reserve_cow(
struct xfs_inode *ip,
struct xfs_bmbt_irec *imap,
bool *shared)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got;
int error = 0;
bool eof = false, trimmed;
xfs_extnum_t idx;
/*
* Search the COW fork extent list first. This serves two purposes:
* first this implement the speculative preallocation using cowextisze,
* so that we also unshared block adjacent to shared blocks instead
* of just the shared blocks themselves. Second the lookup in the
* extent list is generally faster than going out to the shared extent
* tree.
*/
if (!xfs_iext_lookup_extent(ip, ifp, imap->br_startoff, &idx, &got))
eof = true;
if (!eof && got.br_startoff <= imap->br_startoff) {
trace_xfs_reflink_cow_found(ip, imap);
xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
*shared = true;
return 0;
}
/* Trim the mapping to the nearest shared extent boundary. */
error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
if (error)
return error;
/* Not shared? Just report the (potentially capped) extent. */
if (!*shared)
return 0;
/*
* Fork all the shared blocks from our write offset until the end of
* the extent.
*/
error = xfs_qm_dqattach_locked(ip, 0);
if (error)
return error;
error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, imap->br_startoff,
imap->br_blockcount, 0, &got, &idx, eof);
if (error == -ENOSPC || error == -EDQUOT)
trace_xfs_reflink_cow_enospc(ip, imap);
if (error)
return error;
trace_xfs_reflink_cow_alloc(ip, &got);
return 0;
}
/*
* Automatic CoW Reservation Freeing
*
* These functions automatically garbage collect leftover CoW reservations
* that were made on behalf of a cowextsize hint when we start to run out
* of quota or when the reservations sit around for too long. If the file
* has dirty pages or is undergoing writeback, its CoW reservations will
* be retained.
*
* The actual garbage collection piggybacks off the same code that runs
* the speculative EOF preallocation garbage collector.
*/
STATIC int
xfs_inode_free_cowblocks(
struct xfs_inode *ip,
int flags,
void *args)
{
int ret;
struct xfs_eofblocks *eofb = args;
int match;
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
/*
* Just clear the tag if we have an empty cow fork or none at all. It's
* possible the inode was fully unshared since it was originally tagged.
*/
if (!xfs_is_reflink_inode(ip) || !ifp->if_bytes) {
trace_xfs_inode_free_cowblocks_invalid(ip);
xfs_inode_clear_cowblocks_tag(ip);
return 0;
}
/*
* If the mapping is dirty or under writeback we cannot touch the
* CoW fork. Leave it alone if we're in the midst of a directio.
*/
if ((VFS_I(ip)->i_state & I_DIRTY_PAGES) ||
mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY) ||
mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_WRITEBACK) ||
atomic_read(&VFS_I(ip)->i_dio_count))
return 0;
if (eofb) {
if (eofb->eof_flags & XFS_EOF_FLAGS_UNION)
match = xfs_inode_match_id_union(ip, eofb);
else
match = xfs_inode_match_id(ip, eofb);
if (!match)
return 0;
/* skip the inode if the file size is too small */
if (eofb->eof_flags & XFS_EOF_FLAGS_MINFILESIZE &&
XFS_ISIZE(ip) < eofb->eof_min_file_size)
return 0;
}
/* Free the CoW blocks */
xfs_ilock(ip, XFS_IOLOCK_EXCL);
xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false);
xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
}
/* Does this inode need the reflink flag? */
int
xfs_reflink_inode_has_shared_extents(
struct xfs_trans *tp,
struct xfs_inode *ip,
bool *has_shared)
{
struct xfs_bmbt_irec got;
struct xfs_mount *mp = ip->i_mount;
struct xfs_ifork *ifp;
xfs_agnumber_t agno;
xfs_agblock_t agbno;
xfs_extlen_t aglen;
xfs_agblock_t rbno;
xfs_extlen_t rlen;
xfs_extnum_t idx;
bool found;
int error;
ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
if (!(ifp->if_flags & XFS_IFEXTENTS)) {
error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
if (error)
return error;
}
*has_shared = false;
found = xfs_iext_lookup_extent(ip, ifp, 0, &idx, &got);
while (found) {
if (isnullstartblock(got.br_startblock) ||
got.br_state != XFS_EXT_NORM)
goto next;
agno = XFS_FSB_TO_AGNO(mp, got.br_startblock);
agbno = XFS_FSB_TO_AGBNO(mp, got.br_startblock);
aglen = got.br_blockcount;
error = xfs_reflink_find_shared(mp, tp, agno, agbno, aglen,
&rbno, &rlen, false);
if (error)
return error;
/* Is there still a shared block here? */
if (rbno != NULLAGBLOCK) {
*has_shared = true;
return 0;
}
next:
found = xfs_iext_get_extent(ifp, ++idx, &got);
}
return 0;
}
int xfs_readlink_local(xfs_inode_t *ip, void *buffer, off_t offset, size_t len, int *last_extent) {
xfs_ifork_t *dp;
xfs_fsize_t size = ip->i_d.di_size;
dp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
if (size - offset <= 0)
return 0;
if (size - offset < len)
len = size - offset;
memcpy(buffer, dp->if_u1.if_data + offset, len);
return len;
}
/*
* Automatic CoW Reservation Freeing
*
* These functions automatically garbage collect leftover CoW reservations
* that were made on behalf of a cowextsize hint when we start to run out
* of quota or when the reservations sit around for too long. If the file
* has dirty pages or is undergoing writeback, its CoW reservations will
* be retained.
*
* The actual garbage collection piggybacks off the same code that runs
* the speculative EOF preallocation garbage collector.
*/
STATIC int
xfs_inode_free_cowblocks(
struct xfs_inode *ip,
int flags,
void *args)
{
struct xfs_eofblocks *eofb = args;
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
int match;
int ret = 0;
if (!xfs_prep_free_cowblocks(ip, ifp))
return 0;
if (eofb) {
if (eofb->eof_flags & XFS_EOF_FLAGS_UNION)
match = xfs_inode_match_id_union(ip, eofb);
else
match = xfs_inode_match_id(ip, eofb);
if (!match)
return 0;
/* skip the inode if the file size is too small */
if (eofb->eof_flags & XFS_EOF_FLAGS_MINFILESIZE &&
XFS_ISIZE(ip) < eofb->eof_min_file_size)
return 0;
}
/* Free the CoW blocks */
xfs_ilock(ip, XFS_IOLOCK_EXCL);
xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
/*
* Check again, nobody else should be able to dirty blocks or change
* the reflink iflag now that we have the first two locks held.
*/
if (xfs_prep_free_cowblocks(ip, ifp))
ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false);
xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
}
/*
* Count fsblocks of the given fork.
*/
int /* error */
xfs_bmap_count_blocks(
xfs_trans_t *tp, /* transaction pointer */
xfs_inode_t *ip, /* incore inode */
int whichfork, /* data or attr fork */
int *count) /* out: count of blocks */
{
struct xfs_btree_block *block; /* current btree block */
xfs_fsblock_t bno; /* block # of "block" */
xfs_ifork_t *ifp; /* fork structure */
int level; /* btree level, for checking */
xfs_mount_t *mp; /* file system mount structure */
__be64 *pp; /* pointer to block address */
bno = NULLFSBLOCK;
mp = ip->i_mount;
ifp = XFS_IFORK_PTR(ip, whichfork);
if ( XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ) {
xfs_bmap_count_leaves(ifp, 0,
ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t),
count);
return 0;
}
/*
* Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
*/
block = ifp->if_broot;
level = be16_to_cpu(block->bb_level);
ASSERT(level > 0);
pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
bno = be64_to_cpu(*pp);
ASSERT(bno != NULLDFSBNO);
ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
if (unlikely(xfs_bmap_count_tree(mp, tp, ifp, bno, level, count) < 0)) {
XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)", XFS_ERRLEVEL_LOW,
mp);
return XFS_ERROR(EFSCORRUPTED);
}
return 0;
}
/*
* returns 1 for success, 0 if we failed to map the extent.
*/
STATIC int
xfs_getbmapx_fix_eof_hole(
xfs_inode_t *ip, /* xfs incore inode pointer */
struct getbmapx *out, /* output structure */
int prealloced, /* this is a file with
* preallocated data space */
__int64_t end, /* last block requested */
xfs_fsblock_t startblock)
{
__int64_t fixlen;
xfs_mount_t *mp; /* file system mount point */
xfs_ifork_t *ifp; /* inode fork pointer */
xfs_extnum_t lastx; /* last extent pointer */
xfs_fileoff_t fileblock;
if (startblock == HOLESTARTBLOCK) {
mp = ip->i_mount;
out->bmv_block = -1;
fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, XFS_ISIZE(ip)));
fixlen -= out->bmv_offset;
if (prealloced && out->bmv_offset + out->bmv_length == end) {
/* Came to hole at EOF. Trim it. */
if (fixlen <= 0)
return 0;
out->bmv_length = fixlen;
}
} else {
if (startblock == DELAYSTARTBLOCK)
out->bmv_block = -2;
else
out->bmv_block = xfs_fsb_to_db(ip, startblock);
fileblock = XFS_BB_TO_FSB(ip->i_mount, out->bmv_offset);
ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
if (xfs_iext_bno_to_ext(ifp, fileblock, &lastx) &&
(lastx == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))-1))
out->bmv_oflags |= BMV_OF_LAST;
}
return 1;
}
STATIC int
xfs_qm_get_rtblks(
xfs_inode_t *ip,
xfs_qcnt_t *O_rtblks)
{
xfs_filblks_t rtblks; /* total rt blks */
xfs_extnum_t idx; /* extent record index */
xfs_ifork_t *ifp; /* inode fork pointer */
xfs_extnum_t nextents; /* number of extent entries */
int error;
ASSERT(XFS_IS_REALTIME_INODE(ip));
ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
if (!(ifp->if_flags & XFS_IFEXTENTS)) {
if ((error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK)))
return error;
}
rtblks = 0;
nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
for (idx = 0; idx < nextents; idx++)
rtblks += xfs_bmbt_get_blockcount(xfs_iext_get_ext(ifp, idx));
*O_rtblks = (xfs_qcnt_t)rtblks;
return 0;
}
/*
* Cancel CoW reservations for some block range of an inode.
*
* If cancel_real is true this function cancels all COW fork extents for the
* inode; if cancel_real is false, real extents are not cleared.
*/
int
xfs_reflink_cancel_cow_blocks(
struct xfs_inode *ip,
struct xfs_trans **tpp,
xfs_fileoff_t offset_fsb,
xfs_fileoff_t end_fsb,
bool cancel_real)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got, del;
xfs_extnum_t idx;
xfs_fsblock_t firstfsb;
struct xfs_defer_ops dfops;
int error = 0;
if (!xfs_is_reflink_inode(ip))
return 0;
if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got))
return 0;
while (got.br_startoff < end_fsb) {
del = got;
xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
trace_xfs_reflink_cancel_cow(ip, &del);
if (isnullstartblock(del.br_startblock)) {
error = xfs_bmap_del_extent_delay(ip, XFS_COW_FORK,
&idx, &got, &del);
if (error)
break;
} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
xfs_trans_ijoin(*tpp, ip, 0);
xfs_defer_init(&dfops, &firstfsb);
/* Free the CoW orphan record. */
error = xfs_refcount_free_cow_extent(ip->i_mount,
&dfops, del.br_startblock,
del.br_blockcount);
if (error)
break;
xfs_bmap_add_free(ip->i_mount, &dfops,
del.br_startblock, del.br_blockcount,
NULL);
/* Update quota accounting */
xfs_trans_mod_dquot_byino(*tpp, ip, XFS_TRANS_DQ_BCOUNT,
-(long)del.br_blockcount);
/* Roll the transaction */
xfs_defer_ijoin(&dfops, ip);
error = xfs_defer_finish(tpp, &dfops);
if (error) {
xfs_defer_cancel(&dfops);
break;
}
/* Remove the mapping from the CoW fork. */
xfs_bmap_del_extent_cow(ip, &idx, &got, &del);
}
if (!xfs_iext_get_extent(ifp, ++idx, &got))
break;
}
/* clear tag if cow fork is emptied */
if (!ifp->if_bytes)
xfs_inode_clear_cowblocks_tag(ip);
return error;
}
/*
* Remap part of the CoW fork into the data fork.
*
* We aim to remap the range starting at @offset_fsb and ending at @end_fsb
* into the data fork; this function will remap what it can (at the end of the
* range) and update @end_fsb appropriately. Each remap gets its own
* transaction because we can end up merging and splitting bmbt blocks for
* every remap operation and we'd like to keep the block reservation
* requirements as low as possible.
*/
STATIC int
xfs_reflink_end_cow_extent(
struct xfs_inode *ip,
xfs_fileoff_t offset_fsb,
xfs_fileoff_t *end_fsb)
{
struct xfs_bmbt_irec got, del;
struct xfs_iext_cursor icur;
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
xfs_filblks_t rlen;
unsigned int resblks;
int error;
/* No COW extents? That's easy! */
if (ifp->if_bytes == 0) {
*end_fsb = offset_fsb;
return 0;
}
resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0,
XFS_TRANS_RESERVE | XFS_TRANS_NOFS, &tp);
if (error)
return error;
/*
* Lock the inode. We have to ijoin without automatic unlock because
* the lead transaction is the refcountbt record deletion; the data
* fork update follows as a deferred log item.
*/
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* In case of racing, overlapping AIO writes no COW extents might be
* left by the time I/O completes for the loser of the race. In that
* case we are done.
*/
if (!xfs_iext_lookup_extent_before(ip, ifp, end_fsb, &icur, &got) ||
got.br_startoff + got.br_blockcount <= offset_fsb) {
*end_fsb = offset_fsb;
goto out_cancel;
}
/*
* Structure copy @got into @del, then trim @del to the range that we
* were asked to remap. We preserve @got for the eventual CoW fork
* deletion; from now on @del represents the mapping that we're
* actually remapping.
*/
del = got;
xfs_trim_extent(&del, offset_fsb, *end_fsb - offset_fsb);
ASSERT(del.br_blockcount > 0);
/*
* Only remap real extents that contain data. With AIO, speculative
* preallocations can leak into the range we are called upon, and we
* need to skip them.
*/
if (!xfs_bmap_is_real_extent(&got)) {
*end_fsb = del.br_startoff;
goto out_cancel;
}
/* Unmap the old blocks in the data fork. */
rlen = del.br_blockcount;
error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1);
if (error)
goto out_cancel;
/* Trim the extent to whatever got unmapped. */
xfs_trim_extent(&del, del.br_startoff + rlen, del.br_blockcount - rlen);
trace_xfs_reflink_cow_remap(ip, &del);
/* Free the CoW orphan record. */
error = xfs_refcount_free_cow_extent(tp, del.br_startblock,
del.br_blockcount);
if (error)
goto out_cancel;
/* Map the new blocks into the data fork. */
error = xfs_bmap_map_extent(tp, ip, &del);
if (error)
goto out_cancel;
/* Charge this new data fork mapping to the on-disk quota. */
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_DELBCOUNT,
(long)del.br_blockcount);
/* Remove the mapping from the CoW fork. */
xfs_bmap_del_extent_cow(ip, &icur, &got, &del);
error = xfs_trans_commit(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
return error;
/* Update the caller about how much progress we made. */
*end_fsb = del.br_startoff;
return 0;
out_cancel:
xfs_trans_cancel(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
/*
* Cancel CoW reservations for some block range of an inode.
*
* If cancel_real is true this function cancels all COW fork extents for the
* inode; if cancel_real is false, real extents are not cleared.
*/
int
xfs_reflink_cancel_cow_blocks(
struct xfs_inode *ip,
struct xfs_trans **tpp,
xfs_fileoff_t offset_fsb,
xfs_fileoff_t end_fsb,
bool cancel_real)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got, del;
struct xfs_iext_cursor icur;
xfs_fsblock_t firstfsb;
struct xfs_defer_ops dfops;
int error = 0;
if (!xfs_is_reflink_inode(ip))
return 0;
if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
return 0;
/* Walk backwards until we're out of the I/O range... */
while (got.br_startoff + got.br_blockcount > offset_fsb) {
del = got;
xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
/* Extent delete may have bumped ext forward */
if (!del.br_blockcount) {
xfs_iext_prev(ifp, &icur);
goto next_extent;
}
trace_xfs_reflink_cancel_cow(ip, &del);
if (isnullstartblock(del.br_startblock)) {
error = xfs_bmap_del_extent_delay(ip, XFS_COW_FORK,
&icur, &got, &del);
if (error)
break;
} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
xfs_trans_ijoin(*tpp, ip, 0);
xfs_defer_init(&dfops, &firstfsb);
/* Free the CoW orphan record. */
error = xfs_refcount_free_cow_extent(ip->i_mount,
&dfops, del.br_startblock,
del.br_blockcount);
if (error)
break;
xfs_bmap_add_free(ip->i_mount, &dfops,
del.br_startblock, del.br_blockcount,
NULL);
/* Update quota accounting */
xfs_trans_mod_dquot_byino(*tpp, ip, XFS_TRANS_DQ_BCOUNT,
-(long)del.br_blockcount);
/* Roll the transaction */
xfs_defer_ijoin(&dfops, ip);
error = xfs_defer_finish(tpp, &dfops);
if (error) {
xfs_defer_cancel(&dfops);
break;
}
/* Remove the mapping from the CoW fork. */
xfs_bmap_del_extent_cow(ip, &icur, &got, &del);
} else {
/* Didn't do anything, push cursor back. */
xfs_iext_prev(ifp, &icur);
}
next_extent:
if (!xfs_iext_get_extent(ifp, &icur, &got))
break;
}
/* clear tag if cow fork is emptied */
if (!ifp->if_bytes)
xfs_inode_clear_cowblocks_tag(ip);
return error;
}
xfs_ifork_t *
xfs_ifork_ptr(xfs_inode_t *ip, int w)
{
return XFS_IFORK_PTR(ip, w);
}
/*
* Convert the shortform directory to block form.
*/
int /* error */
xfs_dir2_sf_to_block(
xfs_da_args_t *args) /* operation arguments */
{
xfs_dir2_db_t blkno; /* dir-relative block # (0) */
xfs_dir2_data_hdr_t *hdr; /* block header */
xfs_dir2_leaf_entry_t *blp; /* block leaf entries */
struct xfs_buf *bp; /* block buffer */
xfs_dir2_block_tail_t *btp; /* block tail pointer */
xfs_dir2_data_entry_t *dep; /* data entry pointer */
xfs_inode_t *dp; /* incore directory inode */
int dummy; /* trash */
xfs_dir2_data_unused_t *dup; /* unused entry pointer */
int endoffset; /* end of data objects */
int error; /* error return value */
int i; /* index */
xfs_mount_t *mp; /* filesystem mount point */
int needlog; /* need to log block header */
int needscan; /* need to scan block freespc */
int newoffset; /* offset from current entry */
int offset; /* target block offset */
xfs_dir2_sf_entry_t *sfep; /* sf entry pointer */
xfs_dir2_sf_hdr_t *oldsfp; /* old shortform header */
xfs_dir2_sf_hdr_t *sfp; /* shortform header */
__be16 *tagp; /* end of data entry */
xfs_trans_t *tp; /* transaction pointer */
struct xfs_name name;
struct xfs_ifork *ifp;
trace_xfs_dir2_sf_to_block(args);
dp = args->dp;
tp = args->trans;
mp = dp->i_mount;
ifp = XFS_IFORK_PTR(dp, XFS_DATA_FORK);
ASSERT(ifp->if_flags & XFS_IFINLINE);
/*
* Bomb out if the shortform directory is way too short.
*/
if (dp->i_d.di_size < offsetof(xfs_dir2_sf_hdr_t, parent)) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
return -EIO;
}
oldsfp = (xfs_dir2_sf_hdr_t *)ifp->if_u1.if_data;
ASSERT(ifp->if_bytes == dp->i_d.di_size);
ASSERT(ifp->if_u1.if_data != NULL);
ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(oldsfp->i8count));
ASSERT(dp->i_d.di_nextents == 0);
/*
* Copy the directory into a temporary buffer.
* Then pitch the incore inode data so we can make extents.
*/
sfp = kmem_alloc(ifp->if_bytes, KM_SLEEP);
memcpy(sfp, oldsfp, ifp->if_bytes);
xfs_idata_realloc(dp, -ifp->if_bytes, XFS_DATA_FORK);
xfs_bmap_local_to_extents_empty(dp, XFS_DATA_FORK);
dp->i_d.di_size = 0;
/*
* Add block 0 to the inode.
*/
error = xfs_dir2_grow_inode(args, XFS_DIR2_DATA_SPACE, &blkno);
if (error) {
kmem_free(sfp);
return error;
}
/*
* Initialize the data block, then convert it to block format.
*/
error = xfs_dir3_data_init(args, blkno, &bp);
if (error) {
kmem_free(sfp);
return error;
}
xfs_dir3_block_init(mp, tp, bp, dp);
hdr = bp->b_addr;
/*
* Compute size of block "tail" area.
*/
i = (uint)sizeof(*btp) +
(sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t);
/*
* The whole thing is initialized to free by the init routine.
* Say we're using the leaf and tail area.
*/
dup = dp->d_ops->data_unused_p(hdr);
needlog = needscan = 0;
xfs_dir2_data_use_free(args, bp, dup, args->geo->blksize - i,
i, &needlog, &needscan);
ASSERT(needscan == 0);
/*
* Fill in the tail.
*/
btp = xfs_dir2_block_tail_p(args->geo, hdr);
btp->count = cpu_to_be32(sfp->count + 2); /* ., .. */
btp->stale = 0;
blp = xfs_dir2_block_leaf_p(btp);
endoffset = (uint)((char *)blp - (char *)hdr);
/*
* Remove the freespace, we'll manage it.
*/
xfs_dir2_data_use_free(args, bp, dup,
(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
be16_to_cpu(dup->length), &needlog, &needscan);
/*
* Create entry for .
*/
dep = dp->d_ops->data_dot_entry_p(hdr);
dep->inumber = cpu_to_be64(dp->i_ino);
dep->namelen = 1;
dep->name[0] = '.';
dp->d_ops->data_put_ftype(dep, XFS_DIR3_FT_DIR);
tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
xfs_dir2_data_log_entry(args, bp, dep);
blp[0].hashval = cpu_to_be32(xfs_dir_hash_dot);
blp[0].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
(char *)dep - (char *)hdr));
/*
* Create entry for ..
*/
dep = dp->d_ops->data_dotdot_entry_p(hdr);
dep->inumber = cpu_to_be64(dp->d_ops->sf_get_parent_ino(sfp));
dep->namelen = 2;
dep->name[0] = dep->name[1] = '.';
dp->d_ops->data_put_ftype(dep, XFS_DIR3_FT_DIR);
tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
xfs_dir2_data_log_entry(args, bp, dep);
blp[1].hashval = cpu_to_be32(xfs_dir_hash_dotdot);
blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
(char *)dep - (char *)hdr));
offset = dp->d_ops->data_first_offset;
/*
* Loop over existing entries, stuff them in.
*/
i = 0;
if (!sfp->count)
sfep = NULL;
else
sfep = xfs_dir2_sf_firstentry(sfp);
/*
* Need to preserve the existing offset values in the sf directory.
* Insert holes (unused entries) where necessary.
*/
while (offset < endoffset) {
/*
* sfep is null when we reach the end of the list.
*/
if (sfep == NULL)
newoffset = endoffset;
else
newoffset = xfs_dir2_sf_get_offset(sfep);
/*
* There should be a hole here, make one.
*/
if (offset < newoffset) {
dup = (xfs_dir2_data_unused_t *)((char *)hdr + offset);
dup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
dup->length = cpu_to_be16(newoffset - offset);
*xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16(
((char *)dup - (char *)hdr));
xfs_dir2_data_log_unused(args, bp, dup);
xfs_dir2_data_freeinsert(hdr,
dp->d_ops->data_bestfree_p(hdr),
dup, &dummy);
offset += be16_to_cpu(dup->length);
continue;
}
/*
* Copy a real entry.
*/
dep = (xfs_dir2_data_entry_t *)((char *)hdr + newoffset);
dep->inumber = cpu_to_be64(dp->d_ops->sf_get_ino(sfp, sfep));
dep->namelen = sfep->namelen;
dp->d_ops->data_put_ftype(dep, dp->d_ops->sf_get_ftype(sfep));
memcpy(dep->name, sfep->name, dep->namelen);
tagp = dp->d_ops->data_entry_tag_p(dep);
*tagp = cpu_to_be16((char *)dep - (char *)hdr);
xfs_dir2_data_log_entry(args, bp, dep);
name.name = sfep->name;
name.len = sfep->namelen;
blp[2 + i].hashval = cpu_to_be32(mp->m_dirnameops->
hashname(&name));
blp[2 + i].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
(char *)dep - (char *)hdr));
offset = (int)((char *)(tagp + 1) - (char *)hdr);
if (++i == sfp->count)
sfep = NULL;
else
sfep = dp->d_ops->sf_nextentry(sfp, sfep);
}
/* Done with the temporary buffer */
kmem_free(sfp);
/*
* Sort the leaf entries by hash value.
*/
xfs_sort(blp, be32_to_cpu(btp->count), sizeof(*blp), xfs_dir2_block_sort);
/*
* Log the leaf entry area and tail.
* Already logged the header in data_init, ignore needlog.
*/
ASSERT(needscan == 0);
xfs_dir2_block_log_leaf(tp, bp, 0, be32_to_cpu(btp->count) - 1);
xfs_dir2_block_log_tail(tp, bp);
xfs_dir3_data_check(dp, bp);
return 0;
}
/*
* Cancel CoW reservations for some block range of an inode.
*
* If cancel_real is true this function cancels all COW fork extents for the
* inode; if cancel_real is false, real extents are not cleared.
*
* Caller must have already joined the inode to the current transaction. The
* inode will be joined to the transaction returned to the caller.
*/
int
xfs_reflink_cancel_cow_blocks(
struct xfs_inode *ip,
struct xfs_trans **tpp,
xfs_fileoff_t offset_fsb,
xfs_fileoff_t end_fsb,
bool cancel_real)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got, del;
struct xfs_iext_cursor icur;
int error = 0;
if (!xfs_inode_has_cow_data(ip))
return 0;
if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
return 0;
/* Walk backwards until we're out of the I/O range... */
while (got.br_startoff + got.br_blockcount > offset_fsb) {
del = got;
xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
/* Extent delete may have bumped ext forward */
if (!del.br_blockcount) {
xfs_iext_prev(ifp, &icur);
goto next_extent;
}
trace_xfs_reflink_cancel_cow(ip, &del);
if (isnullstartblock(del.br_startblock)) {
error = xfs_bmap_del_extent_delay(ip, XFS_COW_FORK,
&icur, &got, &del);
if (error)
break;
} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
ASSERT((*tpp)->t_firstblock == NULLFSBLOCK);
/* Free the CoW orphan record. */
error = xfs_refcount_free_cow_extent(*tpp,
del.br_startblock, del.br_blockcount);
if (error)
break;
xfs_bmap_add_free(*tpp, del.br_startblock,
del.br_blockcount, NULL);
/* Roll the transaction */
error = xfs_defer_finish(tpp);
if (error)
break;
/* Remove the mapping from the CoW fork. */
xfs_bmap_del_extent_cow(ip, &icur, &got, &del);
/* Remove the quota reservation */
error = xfs_trans_reserve_quota_nblks(NULL, ip,
-(long)del.br_blockcount, 0,
XFS_QMOPT_RES_REGBLKS);
if (error)
break;
} else {
/* Didn't do anything, push cursor back. */
xfs_iext_prev(ifp, &icur);
}
next_extent:
if (!xfs_iext_get_extent(ifp, &icur, &got))
break;
}
/* clear tag if cow fork is emptied */
if (!ifp->if_bytes)
xfs_inode_clear_cowblocks_tag(ip);
return error;
}
/*
* Remap parts of a file's data fork after a successful CoW.
*/
int
xfs_reflink_end_cow(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t count)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got, del;
struct xfs_trans *tp;
xfs_fileoff_t offset_fsb;
xfs_fileoff_t end_fsb;
xfs_fsblock_t firstfsb;
struct xfs_defer_ops dfops;
int error;
unsigned int resblks;
xfs_filblks_t rlen;
xfs_extnum_t idx;
trace_xfs_reflink_end_cow(ip, offset, count);
/* No COW extents? That's easy! */
if (ifp->if_bytes == 0)
return 0;
offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
/*
* Start a rolling transaction to switch the mappings. We're
* unlikely ever to have to remap 16T worth of single-block
* extents, so just cap the worst case extent count to 2^32-1.
* Stick a warning in just in case, and avoid 64-bit division.
*/
BUILD_BUG_ON(MAX_RW_COUNT > UINT_MAX);
if (end_fsb - offset_fsb > UINT_MAX) {
error = -EFSCORRUPTED;
xfs_force_shutdown(ip->i_mount, SHUTDOWN_CORRUPT_INCORE);
ASSERT(0);
goto out;
}
resblks = XFS_NEXTENTADD_SPACE_RES(ip->i_mount,
(unsigned int)(end_fsb - offset_fsb),
XFS_DATA_FORK);
error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_write,
resblks, 0, 0, &tp);
if (error)
goto out;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/* If there is a hole at end_fsb - 1 go to the previous extent */
if (!xfs_iext_lookup_extent(ip, ifp, end_fsb - 1, &idx, &got) ||
got.br_startoff > end_fsb) {
/*
* In case of racing, overlapping AIO writes no COW extents
* might be left by the time I/O completes for the loser of
* the race. In that case we are done.
*/
if (idx <= 0)
goto out_cancel;
xfs_iext_get_extent(ifp, --idx, &got);
}
/* Walk backwards until we're out of the I/O range... */
while (got.br_startoff + got.br_blockcount > offset_fsb) {
del = got;
xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
/* Extent delete may have bumped idx forward */
if (!del.br_blockcount) {
idx--;
goto next_extent;
}
ASSERT(!isnullstartblock(got.br_startblock));
/*
* Don't remap unwritten extents; these are
* speculatively preallocated CoW extents that have been
* allocated but have not yet been involved in a write.
*/
if (got.br_state == XFS_EXT_UNWRITTEN) {
idx--;
goto next_extent;
}
/* Unmap the old blocks in the data fork. */
xfs_defer_init(&dfops, &firstfsb);
rlen = del.br_blockcount;
error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1,
&firstfsb, &dfops);
if (error)
goto out_defer;
/* Trim the extent to whatever got unmapped. */
if (rlen) {
xfs_trim_extent(&del, del.br_startoff + rlen,
del.br_blockcount - rlen);
}
trace_xfs_reflink_cow_remap(ip, &del);
/* Free the CoW orphan record. */
error = xfs_refcount_free_cow_extent(tp->t_mountp, &dfops,
del.br_startblock, del.br_blockcount);
if (error)
goto out_defer;
/* Map the new blocks into the data fork. */
error = xfs_bmap_map_extent(tp->t_mountp, &dfops, ip, &del);
if (error)
goto out_defer;
/* Remove the mapping from the CoW fork. */
xfs_bmap_del_extent_cow(ip, &idx, &got, &del);
xfs_defer_ijoin(&dfops, ip);
error = xfs_defer_finish(&tp, &dfops);
if (error)
goto out_defer;
next_extent:
if (!xfs_iext_get_extent(ifp, idx, &got))
break;
}
error = xfs_trans_commit(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
goto out;
return 0;
out_defer:
xfs_defer_cancel(&dfops);
out_cancel:
xfs_trans_cancel(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
trace_xfs_reflink_end_cow_error(ip, error, _RET_IP_);
return error;
}