/*
* Read in the in-core dquot's on-disk metadata and return the buffer.
* Returns ENOENT to signal a hole.
*/
STATIC int
xfs_dquot_disk_read(
struct xfs_mount *mp,
struct xfs_dquot *dqp,
struct xfs_buf **bpp)
{
struct xfs_bmbt_irec map;
struct xfs_buf *bp;
struct xfs_inode *quotip = xfs_quota_inode(mp, dqp->dq_flags);
uint lock_mode;
int nmaps = 1;
int error;
lock_mode = xfs_ilock_data_map_shared(quotip);
if (!xfs_this_quota_on(mp, dqp->dq_flags)) {
/*
* Return if this type of quotas is turned off while we
* didn't have the quota inode lock.
*/
xfs_iunlock(quotip, lock_mode);
return -ESRCH;
}
/*
* Find the block map; no allocations yet
*/
error = xfs_bmapi_read(quotip, dqp->q_fileoffset,
XFS_DQUOT_CLUSTER_SIZE_FSB, &map, &nmaps, 0);
xfs_iunlock(quotip, lock_mode);
if (error)
return error;
ASSERT(nmaps == 1);
ASSERT(map.br_blockcount >= 1);
ASSERT(map.br_startblock != DELAYSTARTBLOCK);
if (map.br_startblock == HOLESTARTBLOCK)
return -ENOENT;
trace_xfs_dqtobp_read(dqp);
/*
* store the blkno etc so that we don't have to do the
* mapping all the time
*/
dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno,
mp->m_quotainfo->qi_dqchunklen, 0, &bp,
&xfs_dquot_buf_ops);
if (error) {
ASSERT(bp == NULL);
return error;
}
ASSERT(xfs_buf_islocked(bp));
xfs_buf_set_ref(bp, XFS_DQUOT_REF);
*bpp = bp;
return 0;
}
STATIC loff_t
xfs_seek_hole_data(
struct file *file,
loff_t start,
int whence)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
uint lock;
loff_t offset, end;
int error = 0;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
lock = xfs_ilock_data_map_shared(ip);
end = i_size_read(inode);
offset = __xfs_seek_hole_data(inode, start, end, whence);
if (offset < 0) {
error = offset;
goto out_unlock;
}
offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
out_unlock:
xfs_iunlock(ip, lock);
if (error)
return error;
return offset;
}
/*
* Advance to the next id in the current chunk, or if at the
* end of the chunk, skip ahead to first id in next allocated chunk
* using the SEEK_DATA interface.
*/
static int
xfs_dq_get_next_id(
struct xfs_mount *mp,
uint type,
xfs_dqid_t *id)
{
struct xfs_inode *quotip = xfs_quota_inode(mp, type);
xfs_dqid_t next_id = *id + 1; /* simple advance */
uint lock_flags;
struct xfs_bmbt_irec got;
struct xfs_iext_cursor cur;
xfs_fsblock_t start;
int error = 0;
/* If we'd wrap past the max ID, stop */
if (next_id < *id)
return -ENOENT;
/* If new ID is within the current chunk, advancing it sufficed */
if (next_id % mp->m_quotainfo->qi_dqperchunk) {
*id = next_id;
return 0;
}
/* Nope, next_id is now past the current chunk, so find the next one */
start = (xfs_fsblock_t)next_id / mp->m_quotainfo->qi_dqperchunk;
lock_flags = xfs_ilock_data_map_shared(quotip);
if (!(quotip->i_df.if_flags & XFS_IFEXTENTS)) {
error = xfs_iread_extents(NULL, quotip, XFS_DATA_FORK);
if (error)
return error;
}
if (xfs_iext_lookup_extent(quotip, "ip->i_df, start, &cur, &got)) {
/* contiguous chunk, bump startoff for the id calculation */
if (got.br_startoff < start)
got.br_startoff = start;
*id = got.br_startoff * mp->m_quotainfo->qi_dqperchunk;
} else {
error = -ENOENT;
}
xfs_iunlock(quotip, lock_flags);
return error;
}
STATIC int
xfs_dir_open(
struct inode *inode,
struct file *file)
{
struct xfs_inode *ip = XFS_I(inode);
int mode;
int error;
error = xfs_file_open(inode, file);
if (error)
return error;
/*
* If there are any blocks, read-ahead block 0 as we're almost
* certain to have the next operation be a read there.
*/
mode = xfs_ilock_data_map_shared(ip);
if (ip->i_d.di_nextents > 0)
error = xfs_dir3_data_readahead(ip, 0, -1);
xfs_iunlock(ip, mode);
return error;
}
/*
* Get inode's extents as described in bmv, and format for output.
* Calls formatter to fill the user's buffer until all extents
* are mapped, until the passed-in bmv->bmv_count slots have
* been filled, or until the formatter short-circuits the loop,
* if it is tracking filled-in extents on its own.
*/
int /* error code */
xfs_getbmap(
xfs_inode_t *ip,
struct getbmapx *bmv, /* user bmap structure */
xfs_bmap_format_t formatter, /* format to user */
void *arg) /* formatter arg */
{
__int64_t bmvend; /* last block requested */
int error = 0; /* return value */
__int64_t fixlen; /* length for -1 case */
int i; /* extent number */
int lock; /* lock state */
xfs_bmbt_irec_t *map; /* buffer for user's data */
xfs_mount_t *mp; /* file system mount point */
int nex; /* # of user extents can do */
int nexleft; /* # of user extents left */
int subnex; /* # of bmapi's can do */
int nmap; /* number of map entries */
struct getbmapx *out; /* output structure */
int whichfork; /* data or attr fork */
int prealloced; /* this is a file with
* preallocated data space */
int iflags; /* interface flags */
int bmapi_flags; /* flags for xfs_bmapi */
int cur_ext = 0;
mp = ip->i_mount;
iflags = bmv->bmv_iflags;
whichfork = iflags & BMV_IF_ATTRFORK ? XFS_ATTR_FORK : XFS_DATA_FORK;
if (whichfork == XFS_ATTR_FORK) {
if (XFS_IFORK_Q(ip)) {
if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS &&
ip->i_d.di_aformat != XFS_DINODE_FMT_BTREE &&
ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)
return XFS_ERROR(EINVAL);
} else if (unlikely(
ip->i_d.di_aformat != 0 &&
ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS)) {
XFS_ERROR_REPORT("xfs_getbmap", XFS_ERRLEVEL_LOW,
ip->i_mount);
return XFS_ERROR(EFSCORRUPTED);
}
prealloced = 0;
fixlen = 1LL << 32;
} else {
if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
ip->i_d.di_format != XFS_DINODE_FMT_BTREE &&
ip->i_d.di_format != XFS_DINODE_FMT_LOCAL)
return XFS_ERROR(EINVAL);
if (xfs_get_extsz_hint(ip) ||
ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC|XFS_DIFLAG_APPEND)){
prealloced = 1;
fixlen = mp->m_super->s_maxbytes;
} else {
prealloced = 0;
fixlen = XFS_ISIZE(ip);
}
}
if (bmv->bmv_length == -1) {
fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, fixlen));
bmv->bmv_length =
max_t(__int64_t, fixlen - bmv->bmv_offset, 0);
} else if (bmv->bmv_length == 0) {
bmv->bmv_entries = 0;
return 0;
} else if (bmv->bmv_length < 0) {
return XFS_ERROR(EINVAL);
}
nex = bmv->bmv_count - 1;
if (nex <= 0)
return XFS_ERROR(EINVAL);
bmvend = bmv->bmv_offset + bmv->bmv_length;
if (bmv->bmv_count > ULONG_MAX / sizeof(struct getbmapx))
return XFS_ERROR(ENOMEM);
out = kmem_zalloc_large(bmv->bmv_count * sizeof(struct getbmapx), 0);
if (!out)
return XFS_ERROR(ENOMEM);
xfs_ilock(ip, XFS_IOLOCK_SHARED);
if (whichfork == XFS_DATA_FORK) {
if (!(iflags & BMV_IF_DELALLOC) &&
(ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_d.di_size)) {
error = -filemap_write_and_wait(VFS_I(ip)->i_mapping);
if (error)
goto out_unlock_iolock;
/*
* Even after flushing the inode, there can still be
* delalloc blocks on the inode beyond EOF due to
* speculative preallocation. These are not removed
* until the release function is called or the inode
* is inactivated. Hence we cannot assert here that
* ip->i_delayed_blks == 0.
*/
}
lock = xfs_ilock_data_map_shared(ip);
} else {
lock = xfs_ilock_attr_map_shared(ip);
}
/*
* Don't let nex be bigger than the number of extents
* we can have assuming alternating holes and real extents.
*/
if (nex > XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1)
nex = XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1;
bmapi_flags = xfs_bmapi_aflag(whichfork);
if (!(iflags & BMV_IF_PREALLOC))
bmapi_flags |= XFS_BMAPI_IGSTATE;
/*
* Allocate enough space to handle "subnex" maps at a time.
*/
error = ENOMEM;
subnex = 16;
map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL | KM_NOFS);
if (!map)
goto out_unlock_ilock;
bmv->bmv_entries = 0;
if (XFS_IFORK_NEXTENTS(ip, whichfork) == 0 &&
(whichfork == XFS_ATTR_FORK || !(iflags & BMV_IF_DELALLOC))) {
error = 0;
goto out_free_map;
}
nexleft = nex;
do {
nmap = (nexleft > subnex) ? subnex : nexleft;
error = xfs_bmapi_read(ip, XFS_BB_TO_FSBT(mp, bmv->bmv_offset),
XFS_BB_TO_FSB(mp, bmv->bmv_length),
map, &nmap, bmapi_flags);
if (error)
goto out_free_map;
ASSERT(nmap <= subnex);
for (i = 0; i < nmap && nexleft && bmv->bmv_length; i++) {
out[cur_ext].bmv_oflags = 0;
if (map[i].br_state == XFS_EXT_UNWRITTEN)
out[cur_ext].bmv_oflags |= BMV_OF_PREALLOC;
else if (map[i].br_startblock == DELAYSTARTBLOCK)
out[cur_ext].bmv_oflags |= BMV_OF_DELALLOC;
out[cur_ext].bmv_offset =
XFS_FSB_TO_BB(mp, map[i].br_startoff);
out[cur_ext].bmv_length =
XFS_FSB_TO_BB(mp, map[i].br_blockcount);
out[cur_ext].bmv_unused1 = 0;
out[cur_ext].bmv_unused2 = 0;
/*
* delayed allocation extents that start beyond EOF can
* occur due to speculative EOF allocation when the
* delalloc extent is larger than the largest freespace
* extent at conversion time. These extents cannot be
* converted by data writeback, so can exist here even
* if we are not supposed to be finding delalloc
* extents.
*/
if (map[i].br_startblock == DELAYSTARTBLOCK &&
map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
ASSERT((iflags & BMV_IF_DELALLOC) != 0);
if (map[i].br_startblock == HOLESTARTBLOCK &&
whichfork == XFS_ATTR_FORK) {
/* came to the end of attribute fork */
out[cur_ext].bmv_oflags |= BMV_OF_LAST;
goto out_free_map;
}
if (!xfs_getbmapx_fix_eof_hole(ip, &out[cur_ext],
prealloced, bmvend,
map[i].br_startblock))
goto out_free_map;
bmv->bmv_offset =
out[cur_ext].bmv_offset +
out[cur_ext].bmv_length;
bmv->bmv_length =
max_t(__int64_t, 0, bmvend - bmv->bmv_offset);
/*
* In case we don't want to return the hole,
* don't increase cur_ext so that we can reuse
* it in the next loop.
*/
if ((iflags & BMV_IF_NO_HOLES) &&
map[i].br_startblock == HOLESTARTBLOCK) {
memset(&out[cur_ext], 0, sizeof(out[cur_ext]));
continue;
}
nexleft--;
bmv->bmv_entries++;
cur_ext++;
}
} while (nmap && nexleft && bmv->bmv_length);
out_free_map:
kmem_free(map);
out_unlock_ilock:
xfs_iunlock(ip, lock);
out_unlock_iolock:
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
for (i = 0; i < cur_ext; i++) {
int full = 0; /* user array is full */
/* format results & advance arg */
error = formatter(&arg, &out[i], &full);
if (error || full)
break;
}
kmem_free(out);
return error;
}
/*
* Zero file bytes between startoff and endoff inclusive.
* The iolock is held exclusive and no blocks are buffered.
*
* This function is used by xfs_free_file_space() to zero
* partial blocks when the range to free is not block aligned.
* When unreserving space with boundaries that are not block
* aligned we round up the start and round down the end
* boundaries and then use this function to zero the parts of
* the blocks that got dropped during the rounding.
*/
STATIC int
xfs_zero_remaining_bytes(
xfs_inode_t *ip,
xfs_off_t startoff,
xfs_off_t endoff)
{
xfs_bmbt_irec_t imap;
xfs_fileoff_t offset_fsb;
xfs_off_t lastoffset;
xfs_off_t offset;
xfs_buf_t *bp;
xfs_mount_t *mp = ip->i_mount;
int nimap;
int error = 0;
/*
* Avoid doing I/O beyond eof - it's not necessary
* since nothing can read beyond eof. The space will
* be zeroed when the file is extended anyway.
*/
if (startoff >= XFS_ISIZE(ip))
return 0;
if (endoff > XFS_ISIZE(ip))
endoff = XFS_ISIZE(ip);
bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp,
BTOBB(mp->m_sb.sb_blocksize), 0);
if (!bp)
return XFS_ERROR(ENOMEM);
xfs_buf_unlock(bp);
for (offset = startoff; offset <= endoff; offset = lastoffset + 1) {
uint lock_mode;
offset_fsb = XFS_B_TO_FSBT(mp, offset);
nimap = 1;
lock_mode = xfs_ilock_data_map_shared(ip);
error = xfs_bmapi_read(ip, offset_fsb, 1, &imap, &nimap, 0);
xfs_iunlock(ip, lock_mode);
if (error || nimap < 1)
break;
ASSERT(imap.br_blockcount >= 1);
ASSERT(imap.br_startoff == offset_fsb);
lastoffset = XFS_FSB_TO_B(mp, imap.br_startoff + 1) - 1;
if (lastoffset > endoff)
lastoffset = endoff;
if (imap.br_startblock == HOLESTARTBLOCK)
continue;
ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
if (imap.br_state == XFS_EXT_UNWRITTEN)
continue;
XFS_BUF_UNDONE(bp);
XFS_BUF_UNWRITE(bp);
XFS_BUF_READ(bp);
XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock));
if (XFS_FORCED_SHUTDOWN(mp)) {
error = XFS_ERROR(EIO);
break;
}
xfs_buf_iorequest(bp);
error = xfs_buf_iowait(bp);
if (error) {
xfs_buf_ioerror_alert(bp,
"xfs_zero_remaining_bytes(read)");
break;
}
memset(bp->b_addr +
(offset - XFS_FSB_TO_B(mp, imap.br_startoff)),
0, lastoffset - offset + 1);
XFS_BUF_UNDONE(bp);
XFS_BUF_UNREAD(bp);
XFS_BUF_WRITE(bp);
if (XFS_FORCED_SHUTDOWN(mp)) {
error = XFS_ERROR(EIO);
break;
}
xfs_buf_iorequest(bp);
error = xfs_buf_iowait(bp);
if (error) {
xfs_buf_ioerror_alert(bp,
"xfs_zero_remaining_bytes(write)");
break;
}
}
xfs_buf_free(bp);
return error;
}
int
xfs_dir_lookup(
xfs_trans_t *tp,
xfs_inode_t *dp,
struct xfs_name *name,
xfs_ino_t *inum, /* out: inode number */
struct xfs_name *ci_name) /* out: actual name if CI match */
{
struct xfs_da_args *args;
int rval;
int v; /* type-checking value */
int lock_mode;
ASSERT(S_ISDIR(dp->i_d.di_mode));
XFS_STATS_INC(xs_dir_lookup);
/*
* We need to use KM_NOFS here so that lockdep will not throw false
* positive deadlock warnings on a non-transactional lookup path. It is
* safe to recurse into inode recalim in that case, but lockdep can't
* easily be taught about it. Hence KM_NOFS avoids having to add more
* lockdep Doing this avoids having to add a bunch of lockdep class
* annotations into the reclaim path for the ilock.
*/
args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
args->geo = dp->i_mount->m_dir_geo;
args->name = name->name;
args->namelen = name->len;
args->filetype = name->type;
args->hashval = dp->i_mount->m_dirnameops->hashname(name);
args->dp = dp;
args->whichfork = XFS_DATA_FORK;
args->trans = tp;
args->op_flags = XFS_DA_OP_OKNOENT;
if (ci_name)
args->op_flags |= XFS_DA_OP_CILOOKUP;
lock_mode = xfs_ilock_data_map_shared(dp);
if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
rval = xfs_dir2_sf_lookup(args);
goto out_check_rval;
}
rval = xfs_dir2_isblock(args, &v);
if (rval)
goto out_free;
if (v) {
rval = xfs_dir2_block_lookup(args);
goto out_check_rval;
}
rval = xfs_dir2_isleaf(args, &v);
if (rval)
goto out_free;
if (v)
rval = xfs_dir2_leaf_lookup(args);
else
rval = xfs_dir2_node_lookup(args);
out_check_rval:
if (rval == -EEXIST)
rval = 0;
if (!rval) {
*inum = args->inumber;
if (ci_name) {
ci_name->name = args->value;
ci_name->len = args->valuelen;
}
}
out_free:
xfs_iunlock(dp, lock_mode);
kmem_free(args);
return rval;
}
/*
* Maps a dquot to the buffer containing its on-disk version.
* This returns a ptr to the buffer containing the on-disk dquot
* in the bpp param, and a ptr to the on-disk dquot within that buffer
*/
STATIC int
xfs_qm_dqtobp(
xfs_trans_t **tpp,
xfs_dquot_t *dqp,
xfs_disk_dquot_t **O_ddpp,
xfs_buf_t **O_bpp,
uint flags)
{
struct xfs_bmbt_irec map;
int nmaps = 1, error;
struct xfs_buf *bp;
struct xfs_inode *quotip = xfs_dq_to_quota_inode(dqp);
struct xfs_mount *mp = dqp->q_mount;
xfs_dqid_t id = be32_to_cpu(dqp->q_core.d_id);
struct xfs_trans *tp = (tpp ? *tpp : NULL);
uint lock_mode;
dqp->q_fileoffset = (xfs_fileoff_t)id / mp->m_quotainfo->qi_dqperchunk;
lock_mode = xfs_ilock_data_map_shared(quotip);
if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) {
/*
* Return if this type of quotas is turned off while we
* didn't have the quota inode lock.
*/
xfs_iunlock(quotip, lock_mode);
return ESRCH;
}
/*
* Find the block map; no allocations yet
*/
error = xfs_bmapi_read(quotip, dqp->q_fileoffset,
XFS_DQUOT_CLUSTER_SIZE_FSB, &map, &nmaps, 0);
xfs_iunlock(quotip, lock_mode);
if (error)
return error;
ASSERT(nmaps == 1);
ASSERT(map.br_blockcount == 1);
/*
* Offset of dquot in the (fixed sized) dquot chunk.
*/
dqp->q_bufoffset = (id % mp->m_quotainfo->qi_dqperchunk) *
sizeof(xfs_dqblk_t);
ASSERT(map.br_startblock != DELAYSTARTBLOCK);
if (map.br_startblock == HOLESTARTBLOCK) {
/*
* We don't allocate unless we're asked to
*/
if (!(flags & XFS_QMOPT_DQALLOC))
return ENOENT;
ASSERT(tp);
error = xfs_qm_dqalloc(tpp, mp, dqp, quotip,
dqp->q_fileoffset, &bp);
if (error)
return error;
tp = *tpp;
} else {
trace_xfs_dqtobp_read(dqp);
/*
* store the blkno etc so that we don't have to do the
* mapping all the time
*/
dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
dqp->q_blkno,
mp->m_quotainfo->qi_dqchunklen,
0, &bp, &xfs_dquot_buf_ops);
if (error == EFSCORRUPTED && (flags & XFS_QMOPT_DQREPAIR)) {
xfs_dqid_t firstid = (xfs_dqid_t)map.br_startoff *
mp->m_quotainfo->qi_dqperchunk;
ASSERT(bp == NULL);
error = xfs_qm_dqrepair(mp, tp, dqp, firstid, &bp);
}
if (error) {
ASSERT(bp == NULL);
return XFS_ERROR(error);
}
}
ASSERT(xfs_buf_islocked(bp));
*O_bpp = bp;
*O_ddpp = bp->b_addr + dqp->q_bufoffset;
return (0);
}
STATIC loff_t
xfs_seek_hole(
struct file *file,
loff_t start)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
loff_t uninitialized_var(offset);
xfs_fsize_t isize;
xfs_fileoff_t fsbno;
xfs_filblks_t end;
uint lock;
int error;
if (XFS_FORCED_SHUTDOWN(mp))
return -XFS_ERROR(EIO);
lock = xfs_ilock_data_map_shared(ip);
isize = i_size_read(inode);
if (start >= isize) {
error = ENXIO;
goto out_unlock;
}
fsbno = XFS_B_TO_FSBT(mp, start);
end = XFS_B_TO_FSB(mp, isize);
for (;;) {
struct xfs_bmbt_irec map[2];
int nmap = 2;
unsigned int i;
error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
XFS_BMAPI_ENTIRE);
if (error)
goto out_unlock;
/* No extents at given offset, must be beyond EOF */
if (nmap == 0) {
error = ENXIO;
goto out_unlock;
}
for (i = 0; i < nmap; i++) {
offset = max_t(loff_t, start,
XFS_FSB_TO_B(mp, map[i].br_startoff));
/* Landed in a hole */
if (map[i].br_startblock == HOLESTARTBLOCK)
goto out;
/*
* Landed in an unwritten extent, try to search hole
* from page cache.
*/
if (map[i].br_state == XFS_EXT_UNWRITTEN) {
if (xfs_find_get_desired_pgoff(inode, &map[i],
HOLE_OFF, &offset))
goto out;
}
}
/*
* map[0] contains data or its unwritten but contains
* data in page cache, probably means that we are
* reading after EOF. We should fix offset to point
* to the end of the file(i.e., there is an implicit
* hole at the end of any file).
*/
if (nmap == 1) {
offset = isize;
break;
}
ASSERT(i > 1);
/*
* Both mappings contains data, proceed to the next round of
* search if the current reading offset not beyond or hit EOF.
*/
fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
start = XFS_FSB_TO_B(mp, fsbno);
if (start >= isize) {
offset = isize;
break;
}
}
out:
/*
* At this point, we must have found a hole. However, the returned
* offset may be bigger than the file size as it may be aligned to
* page boundary for unwritten extents, we need to deal with this
* situation in particular.
*/
offset = min_t(loff_t, offset, isize);
offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
out_unlock:
xfs_iunlock(ip, lock);
if (error)
return -error;
return offset;
}
STATIC loff_t
xfs_seek_data(
struct file *file,
loff_t start)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
loff_t uninitialized_var(offset);
xfs_fsize_t isize;
xfs_fileoff_t fsbno;
xfs_filblks_t end;
uint lock;
int error;
lock = xfs_ilock_data_map_shared(ip);
isize = i_size_read(inode);
if (start >= isize) {
error = ENXIO;
goto out_unlock;
}
/*
* Try to read extents from the first block indicated
* by fsbno to the end block of the file.
*/
fsbno = XFS_B_TO_FSBT(mp, start);
end = XFS_B_TO_FSB(mp, isize);
for (;;) {
struct xfs_bmbt_irec map[2];
int nmap = 2;
unsigned int i;
error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
XFS_BMAPI_ENTIRE);
if (error)
goto out_unlock;
/* No extents at given offset, must be beyond EOF */
if (nmap == 0) {
error = ENXIO;
goto out_unlock;
}
for (i = 0; i < nmap; i++) {
offset = max_t(loff_t, start,
XFS_FSB_TO_B(mp, map[i].br_startoff));
/* Landed in a data extent */
if (map[i].br_startblock == DELAYSTARTBLOCK ||
(map[i].br_state == XFS_EXT_NORM &&
!isnullstartblock(map[i].br_startblock)))
goto out;
/*
* Landed in an unwritten extent, try to search data
* from page cache.
*/
if (map[i].br_state == XFS_EXT_UNWRITTEN) {
if (xfs_find_get_desired_pgoff(inode, &map[i],
DATA_OFF, &offset))
goto out;
}
}
/*
* map[0] is hole or its an unwritten extent but
* without data in page cache. Probably means that
* we are reading after EOF if nothing in map[1].
*/
if (nmap == 1) {
error = ENXIO;
goto out_unlock;
}
ASSERT(i > 1);
/*
* Nothing was found, proceed to the next round of search
* if reading offset not beyond or hit EOF.
*/
fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
start = XFS_FSB_TO_B(mp, fsbno);
if (start >= isize) {
error = ENXIO;
goto out_unlock;
}
}
out:
offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
out_unlock:
xfs_iunlock(ip, lock);
if (error)
return -error;
return offset;
}
/*
* Iteratively remap one file's extents (and holes) to another's.
*/
int
xfs_reflink_remap_blocks(
struct xfs_inode *src,
loff_t pos_in,
struct xfs_inode *dest,
loff_t pos_out,
loff_t remap_len,
loff_t *remapped)
{
struct xfs_bmbt_irec imap;
xfs_fileoff_t srcoff;
xfs_fileoff_t destoff;
xfs_filblks_t len;
xfs_filblks_t range_len;
xfs_filblks_t remapped_len = 0;
xfs_off_t new_isize = pos_out + remap_len;
int nimaps;
int error = 0;
destoff = XFS_B_TO_FSBT(src->i_mount, pos_out);
srcoff = XFS_B_TO_FSBT(src->i_mount, pos_in);
len = XFS_B_TO_FSB(src->i_mount, remap_len);
/* drange = (destoff, destoff + len); srange = (srcoff, srcoff + len) */
while (len) {
uint lock_mode;
trace_xfs_reflink_remap_blocks_loop(src, srcoff, len,
dest, destoff);
/* Read extent from the source file */
nimaps = 1;
lock_mode = xfs_ilock_data_map_shared(src);
error = xfs_bmapi_read(src, srcoff, len, &imap, &nimaps, 0);
xfs_iunlock(src, lock_mode);
if (error)
break;
ASSERT(nimaps == 1);
trace_xfs_reflink_remap_imap(src, srcoff, len, XFS_DATA_FORK,
&imap);
/* Translate imap into the destination file. */
range_len = imap.br_startoff + imap.br_blockcount - srcoff;
imap.br_startoff += destoff - srcoff;
/* Clear dest from destoff to the end of imap and map it in. */
error = xfs_reflink_remap_extent(dest, &imap, destoff,
new_isize);
if (error)
break;
if (fatal_signal_pending(current)) {
error = -EINTR;
break;
}
/* Advance drange/srange */
srcoff += range_len;
destoff += range_len;
len -= range_len;
remapped_len += range_len;
}
if (error)
trace_xfs_reflink_remap_blocks_error(dest, error, _RET_IP_);
*remapped = min_t(loff_t, remap_len,
XFS_FSB_TO_B(src->i_mount, remapped_len));
return error;
}
/*
* Iterate over all allocated USR/GRP/PRJ dquots in the system, calling a
* caller supplied function for every chunk of dquots that we find.
*/
STATIC int
xfs_qm_dqiterate(
struct xfs_mount *mp,
struct xfs_inode *qip,
uint flags,
struct list_head *buffer_list)
{
struct xfs_bmbt_irec *map;
int i, nmaps; /* number of map entries */
int error; /* return value */
xfs_fileoff_t lblkno;
xfs_filblks_t maxlblkcnt;
xfs_dqid_t firstid;
xfs_fsblock_t rablkno;
xfs_filblks_t rablkcnt;
error = 0;
/*
* This looks racy, but we can't keep an inode lock across a
* trans_reserve. But, this gets called during quotacheck, and that
* happens only at mount time which is single threaded.
*/
if (qip->i_d.di_nblocks == 0)
return 0;
map = kmem_alloc(XFS_DQITER_MAP_SIZE * sizeof(*map), KM_SLEEP);
lblkno = 0;
maxlblkcnt = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
do {
uint lock_mode;
nmaps = XFS_DQITER_MAP_SIZE;
/*
* We aren't changing the inode itself. Just changing
* some of its data. No new blocks are added here, and
* the inode is never added to the transaction.
*/
lock_mode = xfs_ilock_data_map_shared(qip);
error = xfs_bmapi_read(qip, lblkno, maxlblkcnt - lblkno,
map, &nmaps, 0);
xfs_iunlock(qip, lock_mode);
if (error)
break;
ASSERT(nmaps <= XFS_DQITER_MAP_SIZE);
for (i = 0; i < nmaps; i++) {
ASSERT(map[i].br_startblock != DELAYSTARTBLOCK);
ASSERT(map[i].br_blockcount);
lblkno += map[i].br_blockcount;
if (map[i].br_startblock == HOLESTARTBLOCK)
continue;
firstid = (xfs_dqid_t) map[i].br_startoff *
mp->m_quotainfo->qi_dqperchunk;
/*
* Do a read-ahead on the next extent.
*/
if ((i+1 < nmaps) &&
(map[i+1].br_startblock != HOLESTARTBLOCK)) {
rablkcnt = map[i+1].br_blockcount;
rablkno = map[i+1].br_startblock;
while (rablkcnt--) {
xfs_buf_readahead(mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, rablkno),
mp->m_quotainfo->qi_dqchunklen,
&xfs_dquot_buf_ops);
rablkno++;
}
}
/*
* Iterate thru all the blks in the extent and
* reset the counters of all the dquots inside them.
*/
error = xfs_qm_dqiter_bufs(mp, firstid,
map[i].br_startblock,
map[i].br_blockcount,
flags, buffer_list);
if (error)
goto out;
}
} while (nmaps > 0);
out:
kmem_free(map);
return error;
}
/*
* Readdir for block directories.
*/
STATIC int
xfs_dir2_block_getdents(
struct xfs_da_args *args,
struct dir_context *ctx)
{
struct xfs_inode *dp = args->dp; /* incore directory inode */
xfs_dir2_data_hdr_t *hdr; /* block header */
struct xfs_buf *bp; /* buffer for block */
xfs_dir2_block_tail_t *btp; /* block tail */
xfs_dir2_data_entry_t *dep; /* block data entry */
xfs_dir2_data_unused_t *dup; /* block unused entry */
char *endptr; /* end of the data entries */
int error; /* error return value */
char *ptr; /* current data entry */
int wantoff; /* starting block offset */
xfs_off_t cook;
struct xfs_da_geometry *geo = args->geo;
int lock_mode;
/*
* If the block number in the offset is out of range, we're done.
*/
if (xfs_dir2_dataptr_to_db(geo, ctx->pos) > geo->datablk)
return 0;
lock_mode = xfs_ilock_data_map_shared(dp);
error = xfs_dir3_block_read(NULL, dp, &bp);
xfs_iunlock(dp, lock_mode);
if (error)
return error;
/*
* Extract the byte offset we start at from the seek pointer.
* We'll skip entries before this.
*/
wantoff = xfs_dir2_dataptr_to_off(geo, ctx->pos);
hdr = bp->b_addr;
xfs_dir3_data_check(dp, bp);
/*
* Set up values for the loop.
*/
btp = xfs_dir2_block_tail_p(geo, hdr);
ptr = (char *)dp->d_ops->data_entry_p(hdr);
endptr = (char *)xfs_dir2_block_leaf_p(btp);
/*
* Loop over the data portion of the block.
* Each object is a real entry (dep) or an unused one (dup).
*/
while (ptr < endptr) {
__uint8_t filetype;
dup = (xfs_dir2_data_unused_t *)ptr;
/*
* Unused, skip it.
*/
if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
ptr += be16_to_cpu(dup->length);
continue;
}
dep = (xfs_dir2_data_entry_t *)ptr;
/*
* Bump pointer for the next iteration.
*/
ptr += dp->d_ops->data_entsize(dep->namelen);
/*
* The entry is before the desired starting point, skip it.
*/
if ((char *)dep - (char *)hdr < wantoff)
continue;
cook = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
(char *)dep - (char *)hdr);
ctx->pos = cook & 0x7fffffff;
filetype = dp->d_ops->data_get_ftype(dep);
/*
* If it didn't fit, set the final offset to here & return.
*/
if (!dir_emit(ctx, (char *)dep->name, dep->namelen,
be64_to_cpu(dep->inumber),
xfs_dir3_get_dtype(dp->i_mount, filetype))) {
xfs_trans_brelse(NULL, bp);
return 0;
}
}
/*
* Reached the end of the block.
* Set the offset to a non-existent block 1 and return.
*/
ctx->pos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk + 1, 0) &
0x7fffffff;
xfs_trans_brelse(NULL, bp);
return 0;
}
/*
* Get a layout for the pNFS client.
*/
int
xfs_fs_map_blocks(
struct inode *inode,
loff_t offset,
u64 length,
struct iomap *iomap,
bool write,
u32 *device_generation)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
struct xfs_bmbt_irec imap;
xfs_fileoff_t offset_fsb, end_fsb;
loff_t limit;
int bmapi_flags = XFS_BMAPI_ENTIRE;
int nimaps = 1;
uint lock_flags;
int error = 0;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/*
* We can't export inodes residing on the realtime device. The realtime
* device doesn't have a UUID to identify it, so the client has no way
* to find it.
*/
if (XFS_IS_REALTIME_INODE(ip))
return -ENXIO;
/*
* Lock out any other I/O before we flush and invalidate the pagecache,
* and then hand out a layout to the remote system. This is very
* similar to direct I/O, except that the synchronization is much more
* complicated. See the comment near xfs_break_layouts for a detailed
* explanation.
*/
xfs_ilock(ip, XFS_IOLOCK_EXCL);
error = -EINVAL;
limit = mp->m_super->s_maxbytes;
if (!write)
limit = max(limit, round_up(i_size_read(inode),
inode->i_sb->s_blocksize));
if (offset > limit)
goto out_unlock;
if (offset > limit - length)
length = limit - offset;
error = filemap_write_and_wait(inode->i_mapping);
if (error)
goto out_unlock;
error = invalidate_inode_pages2(inode->i_mapping);
if (WARN_ON_ONCE(error))
return error;
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
lock_flags = xfs_ilock_data_map_shared(ip);
error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
&imap, &nimaps, bmapi_flags);
xfs_iunlock(ip, lock_flags);
if (error)
goto out_unlock;
if (write) {
enum xfs_prealloc_flags flags = 0;
ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
if (!nimaps || imap.br_startblock == HOLESTARTBLOCK) {
/*
* xfs_iomap_write_direct() expects to take ownership of
* the shared ilock.
*/
xfs_ilock(ip, XFS_ILOCK_SHARED);
error = xfs_iomap_write_direct(ip, offset, length,
&imap, nimaps);
if (error)
goto out_unlock;
/*
* Ensure the next transaction is committed
* synchronously so that the blocks allocated and
* handed out to the client are guaranteed to be
* present even after a server crash.
*/
flags |= XFS_PREALLOC_SET | XFS_PREALLOC_SYNC;
}
error = xfs_update_prealloc_flags(ip, flags);
if (error)
goto out_unlock;
}
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
xfs_bmbt_to_iomap(ip, iomap, &imap);
*device_generation = mp->m_generation;
return error;
out_unlock:
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
return error;
}
