STATIC int
xfs_vn_getattr(
struct vfsmount *mnt,
struct dentry *dentry,
struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
xfs_itrace_entry(ip);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
stat->size = XFS_ISIZE(ip);
stat->dev = inode->i_sb->s_dev;
stat->mode = ip->i_d.di_mode;
stat->nlink = ip->i_d.di_nlink;
stat->uid = ip->i_d.di_uid;
stat->gid = ip->i_d.di_gid;
stat->ino = ip->i_ino;
#if XFS_BIG_INUMS
stat->ino += mp->m_inoadd;
#endif
stat->atime = inode->i_atime;
stat->mtime.tv_sec = ip->i_d.di_mtime.t_sec;
stat->mtime.tv_nsec = ip->i_d.di_mtime.t_nsec;
stat->ctime.tv_sec = ip->i_d.di_ctime.t_sec;
stat->ctime.tv_nsec = ip->i_d.di_ctime.t_nsec;
stat->blocks =
XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks);
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
case S_IFCHR:
stat->blksize = BLKDEV_IOSIZE;
stat->rdev = MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff,
sysv_minor(ip->i_df.if_u2.if_rdev));
break;
default:
if (XFS_IS_REALTIME_INODE(ip)) {
/*
* If the file blocks are being allocated from a
* realtime volume, then return the inode's realtime
* extent size or the realtime volume's extent size.
*/
stat->blksize =
xfs_get_extsz_hint(ip) << mp->m_sb.sb_blocklog;
} else
stat->blksize = xfs_preferred_iosize(mp);
stat->rdev = 0;
break;
}
return 0;
}
STATIC int
xfs_inode_free_eofblocks(
struct xfs_inode *ip,
int flags,
void *args)
{
int ret;
struct xfs_eofblocks *eofb = args;
bool need_iolock = true;
int match;
ASSERT(!eofb || (eofb && eofb->eof_scan_owner != 0));
if (!xfs_can_free_eofblocks(ip, false)) {
/* inode could be preallocated or append-only */
trace_xfs_inode_free_eofblocks_invalid(ip);
xfs_inode_clear_eofblocks_tag(ip);
return 0;
}
/*
* If the mapping is dirty the operation can block and wait for some
* time. Unless we are waiting, skip it.
*/
if (!(flags & SYNC_WAIT) &&
mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY))
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;
/*
* A scan owner implies we already hold the iolock. Skip it in
* xfs_free_eofblocks() to avoid deadlock. This also eliminates
* the possibility of EAGAIN being returned.
*/
if (eofb->eof_scan_owner == ip->i_ino)
need_iolock = false;
}
ret = xfs_free_eofblocks(ip->i_mount, ip, need_iolock);
/* don't revisit the inode if we're not waiting */
if (ret == -EAGAIN && !(flags & SYNC_WAIT))
ret = 0;
return ret;
}
/*
* 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;
}
/*
* Pull the link count and size up from the xfs inode to the linux inode
*/
STATIC void
xfs_validate_fields(
struct inode *inode)
{
struct xfs_inode *ip = XFS_I(inode);
loff_t size;
/* we're under i_sem so i_size can't change under us */
size = XFS_ISIZE(ip);
if (i_size_read(inode) != size)
i_size_write(inode, size);
}
STATIC int
xfs_inode_free_eofblocks(
struct xfs_inode *ip,
int flags,
void *args)
{
int ret = 0;
struct xfs_eofblocks *eofb = args;
int match;
if (!xfs_can_free_eofblocks(ip, false)) {
/* inode could be preallocated or append-only */
trace_xfs_inode_free_eofblocks_invalid(ip);
xfs_inode_clear_eofblocks_tag(ip);
return 0;
}
/*
* If the mapping is dirty the operation can block and wait for some
* time. Unless we are waiting, skip it.
*/
if (!(flags & SYNC_WAIT) &&
mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY))
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;
}
/*
* If the caller is waiting, return -EAGAIN to keep the background
* scanner moving and revisit the inode in a subsequent pass.
*/
if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
if (flags & SYNC_WAIT)
ret = -EAGAIN;
return ret;
}
ret = xfs_free_eofblocks(ip);
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
}
int
xfs_wait_on_pages(
xfs_inode_t *ip,
xfs_off_t first,
xfs_off_t last)
{
struct address_space *mapping = VFS_I(ip)->i_mapping;
if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) {
return -filemap_fdatawait_range(mapping, first,
last == -1 ? XFS_ISIZE(ip) - 1 : last);
}
return 0;
}
STATIC int
xfs_vn_getattr(
struct vfsmount *mnt,
struct dentry *dentry,
struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
trace_xfs_getattr(ip);
if (XFS_FORCED_SHUTDOWN(mp))
return -XFS_ERROR(EIO);
stat->size = XFS_ISIZE(ip);
stat->dev = inode->i_sb->s_dev;
stat->mode = ip->i_d.di_mode;
stat->nlink = ip->i_d.di_nlink;
stat->uid = ip->i_d.di_uid;
stat->gid = ip->i_d.di_gid;
stat->ino = ip->i_ino;
stat->atime = inode->i_atime;
stat->mtime = inode->i_mtime;
stat->ctime = inode->i_ctime;
stat->blocks =
XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks);
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
case S_IFCHR:
stat->blksize = BLKDEV_IOSIZE;
stat->rdev = MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff,
sysv_minor(ip->i_df.if_u2.if_rdev));
break;
default:
if (XFS_IS_REALTIME_INODE(ip)) {
stat->blksize =
xfs_get_extsz_hint(ip) << mp->m_sb.sb_blocklog;
} else
stat->blksize = xfs_preferred_iosize(mp);
stat->rdev = 0;
break;
}
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)
{
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;
}
STATIC int
xfs_inode_free_eofblocks(
struct xfs_inode *ip,
struct xfs_perag *pag,
int flags,
void *args)
{
int ret;
struct xfs_eofblocks *eofb = args;
if (!xfs_can_free_eofblocks(ip, false)) {
/* inode could be preallocated or append-only */
trace_xfs_inode_free_eofblocks_invalid(ip);
xfs_inode_clear_eofblocks_tag(ip);
return 0;
}
/*
* If the mapping is dirty the operation can block and wait for some
* time. Unless we are waiting, skip it.
*/
if (!(flags & SYNC_WAIT) &&
mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY))
return 0;
if (eofb) {
if (!xfs_inode_match_id(ip, eofb))
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;
}
ret = xfs_free_eofblocks(ip->i_mount, ip, true);
/* don't revisit the inode if we're not waiting */
if (ret == EAGAIN && !(flags & SYNC_WAIT))
ret = 0;
return ret;
}
/*
* 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;
}
int
xfs_ioc_space(
struct xfs_inode *ip,
struct inode *inode,
struct file *filp,
int ioflags,
unsigned int cmd,
xfs_flock64_t *bf)
{
struct iattr iattr;
enum xfs_prealloc_flags flags = 0;
uint iolock = XFS_IOLOCK_EXCL;
int error;
/*
* Only allow the sys admin to reserve space unless
* unwritten extents are enabled.
*/
if (!xfs_sb_version_hasextflgbit(&ip->i_mount->m_sb) &&
!capable(CAP_SYS_ADMIN))
return -EPERM;
if (inode->i_flags & (S_IMMUTABLE|S_APPEND))
return -EPERM;
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
if (filp->f_flags & O_DSYNC)
flags |= XFS_PREALLOC_SYNC;
if (ioflags & XFS_IO_INVIS)
flags |= XFS_PREALLOC_INVISIBLE;
error = mnt_want_write_file(filp);
if (error)
return error;
xfs_ilock(ip, iolock);
error = xfs_break_layouts(inode, &iolock, false);
if (error)
goto out_unlock;
xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
iolock |= XFS_MMAPLOCK_EXCL;
switch (bf->l_whence) {
case 0: /*SEEK_SET*/
break;
case 1: /*SEEK_CUR*/
bf->l_start += filp->f_pos;
break;
case 2: /*SEEK_END*/
bf->l_start += XFS_ISIZE(ip);
break;
default:
error = -EINVAL;
goto out_unlock;
}
/*
* length of <= 0 for resv/unresv/zero is invalid. length for
* alloc/free is ignored completely and we have no idea what userspace
* might have set it to, so set it to zero to allow range
* checks to pass.
*/
switch (cmd) {
case XFS_IOC_ZERO_RANGE:
case XFS_IOC_RESVSP:
case XFS_IOC_RESVSP64:
case XFS_IOC_UNRESVSP:
case XFS_IOC_UNRESVSP64:
if (bf->l_len <= 0) {
error = -EINVAL;
goto out_unlock;
}
break;
default:
bf->l_len = 0;
break;
}
if (bf->l_start < 0 ||
bf->l_start > inode->i_sb->s_maxbytes ||
bf->l_start + bf->l_len < 0 ||
bf->l_start + bf->l_len >= inode->i_sb->s_maxbytes) {
error = -EINVAL;
goto out_unlock;
}
switch (cmd) {
case XFS_IOC_ZERO_RANGE:
flags |= XFS_PREALLOC_SET;
error = xfs_zero_file_space(ip, bf->l_start, bf->l_len);
break;
case XFS_IOC_RESVSP:
case XFS_IOC_RESVSP64:
flags |= XFS_PREALLOC_SET;
error = xfs_alloc_file_space(ip, bf->l_start, bf->l_len,
XFS_BMAPI_PREALLOC);
break;
case XFS_IOC_UNRESVSP:
case XFS_IOC_UNRESVSP64:
error = xfs_free_file_space(ip, bf->l_start, bf->l_len);
break;
case XFS_IOC_ALLOCSP:
case XFS_IOC_ALLOCSP64:
case XFS_IOC_FREESP:
case XFS_IOC_FREESP64:
flags |= XFS_PREALLOC_CLEAR;
if (bf->l_start > XFS_ISIZE(ip)) {
error = xfs_alloc_file_space(ip, XFS_ISIZE(ip),
bf->l_start - XFS_ISIZE(ip), 0);
if (error)
goto out_unlock;
}
iattr.ia_valid = ATTR_SIZE;
iattr.ia_size = bf->l_start;
error = xfs_setattr_size(ip, &iattr);
break;
default:
ASSERT(0);
error = -EINVAL;
}
if (error)
goto out_unlock;
error = xfs_update_prealloc_flags(ip, flags);
out_unlock:
xfs_iunlock(ip, iolock);
mnt_drop_write_file(filp);
return error;
}
/*
* This is called by xfs_inactive to free any blocks beyond eof
* when the link count isn't zero and by xfs_dm_punch_hole() when
* punching a hole to EOF.
*/
int
xfs_free_eofblocks(
xfs_mount_t *mp,
xfs_inode_t *ip,
bool need_iolock)
{
xfs_trans_t *tp;
int error;
xfs_fileoff_t end_fsb;
xfs_fileoff_t last_fsb;
xfs_filblks_t map_len;
int nimaps;
xfs_bmbt_irec_t imap;
/*
* Figure out if there are any blocks beyond the end
* of the file. If not, then there is nothing to do.
*/
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
if (last_fsb <= end_fsb)
return 0;
map_len = last_fsb - end_fsb;
nimaps = 1;
xfs_ilock(ip, XFS_ILOCK_SHARED);
error = xfs_bmapi_read(ip, end_fsb, map_len, &imap, &nimaps, 0);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (!error && (nimaps != 0) &&
(imap.br_startblock != HOLESTARTBLOCK ||
ip->i_delayed_blks)) {
/*
* Attach the dquots to the inode up front.
*/
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
/*
* There are blocks after the end of file.
* Free them up now by truncating the file to
* its current size.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
if (need_iolock) {
if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
xfs_trans_cancel(tp, 0);
return EAGAIN;
}
}
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
if (error) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
xfs_trans_cancel(tp, 0);
if (need_iolock)
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
return error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* Do not update the on-disk file size. If we update the
* on-disk file size and then the system crashes before the
* contents of the file are flushed to disk then the files
* may be full of holes (ie NULL files bug).
*/
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK,
XFS_ISIZE(ip));
if (error) {
/*
* If we get an error at this point we simply don't
* bother truncating the file.
*/
xfs_trans_cancel(tp,
(XFS_TRANS_RELEASE_LOG_RES |
XFS_TRANS_ABORT));
} else {
error = xfs_trans_commit(tp,
XFS_TRANS_RELEASE_LOG_RES);
if (!error)
xfs_inode_clear_eofblocks_tag(ip);
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (need_iolock)
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
}
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;
}
/*
* Prepare two files for range cloning. Upon a successful return both inodes
* will have the iolock and mmaplock held, the page cache of the out file will
* be truncated, and any leases on the out file will have been broken. This
* function borrows heavily from xfs_file_aio_write_checks.
*
* The VFS allows partial EOF blocks to "match" for dedupe even though it hasn't
* checked that the bytes beyond EOF physically match. Hence we cannot use the
* EOF block in the source dedupe range because it's not a complete block match,
* hence can introduce a corruption into the file that has it's block replaced.
*
* In similar fashion, the VFS file cloning also allows partial EOF blocks to be
* "block aligned" for the purposes of cloning entire files. However, if the
* source file range includes the EOF block and it lands within the existing EOF
* of the destination file, then we can expose stale data from beyond the source
* file EOF in the destination file.
*
* XFS doesn't support partial block sharing, so in both cases we have check
* these cases ourselves. For dedupe, we can simply round the length to dedupe
* down to the previous whole block and ignore the partial EOF block. While this
* means we can't dedupe the last block of a file, this is an acceptible
* tradeoff for simplicity on implementation.
*
* For cloning, we want to share the partial EOF block if it is also the new EOF
* block of the destination file. If the partial EOF block lies inside the
* existing destination EOF, then we have to abort the clone to avoid exposing
* stale data in the destination file. Hence we reject these clone attempts with
* -EINVAL in this case.
*/
int
xfs_reflink_remap_prep(
struct file *file_in,
loff_t pos_in,
struct file *file_out,
loff_t pos_out,
loff_t *len,
unsigned int remap_flags)
{
struct inode *inode_in = file_inode(file_in);
struct xfs_inode *src = XFS_I(inode_in);
struct inode *inode_out = file_inode(file_out);
struct xfs_inode *dest = XFS_I(inode_out);
bool same_inode = (inode_in == inode_out);
ssize_t ret;
/* Lock both files against IO */
ret = xfs_iolock_two_inodes_and_break_layout(inode_in, inode_out);
if (ret)
return ret;
if (same_inode)
xfs_ilock(src, XFS_MMAPLOCK_EXCL);
else
xfs_lock_two_inodes(src, XFS_MMAPLOCK_SHARED, dest,
XFS_MMAPLOCK_EXCL);
/* Check file eligibility and prepare for block sharing. */
ret = -EINVAL;
/* Don't reflink realtime inodes */
if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
goto out_unlock;
/* Don't share DAX file data for now. */
if (IS_DAX(inode_in) || IS_DAX(inode_out))
goto out_unlock;
ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
len, remap_flags);
if (ret < 0 || *len == 0)
goto out_unlock;
/* Attach dquots to dest inode before changing block map */
ret = xfs_qm_dqattach(dest);
if (ret)
goto out_unlock;
/*
* Zero existing post-eof speculative preallocations in the destination
* file.
*/
ret = xfs_reflink_zero_posteof(dest, pos_out);
if (ret)
goto out_unlock;
/* Set flags and remap blocks. */
ret = xfs_reflink_set_inode_flag(src, dest);
if (ret)
goto out_unlock;
/*
* If pos_out > EOF, we may have dirtied blocks between EOF and
* pos_out. In that case, we need to extend the flush and unmap to cover
* from EOF to the end of the copy length.
*/
if (pos_out > XFS_ISIZE(dest)) {
loff_t flen = *len + (pos_out - XFS_ISIZE(dest));
ret = xfs_flush_unmap_range(dest, XFS_ISIZE(dest), flen);
} else {
ret = xfs_flush_unmap_range(dest, pos_out, *len);
}
if (ret)
goto out_unlock;
return 1;
out_unlock:
xfs_reflink_remap_unlock(file_in, file_out);
return ret;
}
int
xfs_ioc_space(
struct xfs_inode *ip,
struct inode *inode,
struct file *filp,
int ioflags,
unsigned int cmd,
xfs_flock64_t *bf)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
struct iattr iattr;
bool setprealloc = false;
bool clrprealloc = false;
int error;
/*
* Only allow the sys admin to reserve space unless
* unwritten extents are enabled.
*/
if (!xfs_sb_version_hasextflgbit(&ip->i_mount->m_sb) &&
!capable(CAP_SYS_ADMIN))
return -XFS_ERROR(EPERM);
if (inode->i_flags & (S_IMMUTABLE|S_APPEND))
return -XFS_ERROR(EPERM);
if (!(filp->f_mode & FMODE_WRITE))
return -XFS_ERROR(EBADF);
if (!S_ISREG(inode->i_mode))
return -XFS_ERROR(EINVAL);
error = mnt_want_write_file(filp);
if (error)
return error;
xfs_ilock(ip, XFS_IOLOCK_EXCL);
switch (bf->l_whence) {
case 0: /*SEEK_SET*/
break;
case 1: /*SEEK_CUR*/
bf->l_start += filp->f_pos;
break;
case 2: /*SEEK_END*/
bf->l_start += XFS_ISIZE(ip);
break;
default:
error = XFS_ERROR(EINVAL);
goto out_unlock;
}
/*
* length of <= 0 for resv/unresv/zero is invalid. length for
* alloc/free is ignored completely and we have no idea what userspace
* might have set it to, so set it to zero to allow range
* checks to pass.
*/
switch (cmd) {
case XFS_IOC_ZERO_RANGE:
case XFS_IOC_RESVSP:
case XFS_IOC_RESVSP64:
case XFS_IOC_UNRESVSP:
case XFS_IOC_UNRESVSP64:
if (bf->l_len <= 0) {
error = XFS_ERROR(EINVAL);
goto out_unlock;
}
break;
default:
bf->l_len = 0;
break;
}
if (bf->l_start < 0 ||
bf->l_start > mp->m_super->s_maxbytes ||
bf->l_start + bf->l_len < 0 ||
bf->l_start + bf->l_len >= mp->m_super->s_maxbytes) {
error = XFS_ERROR(EINVAL);
goto out_unlock;
}
switch (cmd) {
case XFS_IOC_ZERO_RANGE:
error = xfs_zero_file_space(ip, bf->l_start, bf->l_len);
if (!error)
setprealloc = true;
break;
case XFS_IOC_RESVSP:
case XFS_IOC_RESVSP64:
error = xfs_alloc_file_space(ip, bf->l_start, bf->l_len,
XFS_BMAPI_PREALLOC);
if (!error)
setprealloc = true;
break;
case XFS_IOC_UNRESVSP:
case XFS_IOC_UNRESVSP64:
error = xfs_free_file_space(ip, bf->l_start, bf->l_len);
break;
case XFS_IOC_ALLOCSP:
case XFS_IOC_ALLOCSP64:
case XFS_IOC_FREESP:
case XFS_IOC_FREESP64:
if (bf->l_start > XFS_ISIZE(ip)) {
error = xfs_alloc_file_space(ip, XFS_ISIZE(ip),
bf->l_start - XFS_ISIZE(ip), 0);
if (error)
goto out_unlock;
}
iattr.ia_valid = ATTR_SIZE;
iattr.ia_size = bf->l_start;
error = xfs_setattr_size(ip, &iattr);
if (!error)
clrprealloc = true;
break;
default:
ASSERT(0);
error = XFS_ERROR(EINVAL);
}
if (error)
goto out_unlock;
tp = xfs_trans_alloc(mp, XFS_TRANS_WRITEID);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_writeid, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
goto out_unlock;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
if (!(ioflags & IO_INVIS)) {
ip->i_d.di_mode &= ~S_ISUID;
if (ip->i_d.di_mode & S_IXGRP)
ip->i_d.di_mode &= ~S_ISGID;
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
}
if (setprealloc)
ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
else if (clrprealloc)
ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (filp->f_flags & O_DSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, 0);
out_unlock:
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
mnt_drop_write_file(filp);
return -error;
}
STATIC xfs_fsize_t
xfs_size_fn(
xfs_inode_t *ip)
{
return XFS_ISIZE(ip);
}
/*
* 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;
bool need_iolock = true;
int match;
ASSERT(!eofb || (eofb && eofb->eof_scan_owner != 0));
if (!xfs_reflink_has_real_cow_blocks(ip)) {
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 (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;
/*
* A scan owner implies we already hold the iolock. Skip it in
* xfs_free_eofblocks() to avoid deadlock. This also eliminates
* the possibility of EAGAIN being returned.
*/
if (eofb->eof_scan_owner == ip->i_ino)
need_iolock = false;
}
/* Free the CoW blocks */
if (need_iolock) {
xfs_ilock(ip, XFS_IOLOCK_EXCL);
xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
}
ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF);
if (need_iolock) {
xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
}
return ret;
}
