/*
* If we are allocating a new inode, then check what was returned is
* actually a free, empty inode. If we are not allocating an inode,
* then check we didn't find a free inode.
*
* Returns:
* 0 if the inode free state matches the lookup context
* -ENOENT if the inode is free and we are not allocating
* -EFSCORRUPTED if there is any state mismatch at all
*/
static int
xfs_iget_check_free_state(
struct xfs_inode *ip,
int flags)
{
if (flags & XFS_IGET_CREATE) {
/* should be a free inode */
if (VFS_I(ip)->i_mode != 0) {
xfs_warn(ip->i_mount,
"Corruption detected! Free inode 0x%llx not marked free! (mode 0x%x)",
ip->i_ino, VFS_I(ip)->i_mode);
return -EFSCORRUPTED;
}
if (ip->i_d.di_nblocks != 0) {
xfs_warn(ip->i_mount,
"Corruption detected! Free inode 0x%llx has blocks allocated!",
ip->i_ino);
return -EFSCORRUPTED;
}
return 0;
}
/* should be an allocated inode */
if (VFS_I(ip)->i_mode == 0)
return -ENOENT;
return 0;
}
int
xfs_errortag_add(int error_tag, xfs_mount_t *mp)
{
int i;
int len;
int64_t fsid;
memcpy(&fsid, mp->m_fixedfsid, sizeof(xfs_fsid_t));
for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) {
if (xfs_etest_fsid[i] == fsid && xfs_etest[i] == error_tag) {
xfs_warn(mp, "error tag #%d on", error_tag);
return 0;
}
}
for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) {
if (xfs_etest[i] == 0) {
xfs_warn(mp, "Turned on XFS error tag #%d",
error_tag);
xfs_etest[i] = error_tag;
xfs_etest_fsid[i] = fsid;
len = strlen(mp->m_fsname);
xfs_etest_fsname[i] = kmem_alloc(len + 1, KM_SLEEP);
strcpy(xfs_etest_fsname[i], mp->m_fsname);
xfs_error_test_active++;
return 0;
}
}
xfs_warn(mp, "error tag overflow, too many turned on");
return 1;
}
int
xfs_errortag_clearall(xfs_mount_t *mp, int loud)
{
int64_t fsid;
int cleared = 0;
int i;
memcpy(&fsid, mp->m_fixedfsid, sizeof(xfs_fsid_t));
for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) {
if ((fsid == 0LL || xfs_etest_fsid[i] == fsid) &&
xfs_etest[i] != 0) {
cleared = 1;
xfs_warn(mp, "Clearing XFS error tag #%d",
xfs_etest[i]);
xfs_etest[i] = 0;
xfs_etest_fsid[i] = 0LL;
kmem_free(xfs_etest_fsname[i]);
xfs_etest_fsname[i] = NULL;
xfs_error_test_active--;
}
}
if (loud || cleared)
xfs_warn(mp, "Cleared all XFS error tags for filesystem");
return 0;
}
/*
* Second stage of a quiesce. The data is already synced, now we have to take
* care of the metadata. New transactions are already blocked, so we need to
* wait for any remaining transactions to drain out before proceeding.
*/
void
xfs_quiesce_attr(
struct xfs_mount *mp)
{
int error = 0;
/* wait for all modifications to complete */
while (atomic_read(&mp->m_active_trans) > 0)
delay(100);
/* flush inodes and push all remaining buffers out to disk */
xfs_quiesce_fs(mp);
/*
* Just warn here till VFS can correctly support
* read-only remount without racing.
*/
WARN_ON(atomic_read(&mp->m_active_trans) != 0);
/* Push the superblock and write an unmount record */
error = xfs_log_sbcount(mp, 1);
if (error)
xfs_warn(mp, "xfs_attr_quiesce: failed to log sb changes. "
"Frozen image may not be consistent.");
xfs_log_unmount_write(mp);
xfs_unmountfs_writesb(mp);
}
/*
* Given the logitem, this writes the corresponding dquot entry to disk
* asynchronously. This is called with the dquot entry securely locked;
* we simply get xfs_qm_dqflush() to do the work, and unlock the dquot
* at the end.
*/
STATIC void
xfs_qm_dquot_logitem_push(
struct xfs_log_item *lip)
{
struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot;
int error;
ASSERT(XFS_DQ_IS_LOCKED(dqp));
ASSERT(!completion_done(&dqp->q_flush));
/*
* Since we were able to lock the dquot's flush lock and
* we found it on the AIL, the dquot must be dirty. This
* is because the dquot is removed from the AIL while still
* holding the flush lock in xfs_dqflush_done(). Thus, if
* we found it in the AIL and were able to obtain the flush
* lock without sleeping, then there must not have been
* anyone in the process of flushing the dquot.
*/
error = xfs_qm_dqflush(dqp, 0);
if (error)
xfs_warn(dqp->q_mount, "%s: push error %d on dqp %p",
__func__, error, dqp);
xfs_dqunlock(dqp);
}
/*
* Validate a given inode number.
*/
int
xfs_dir_ino_validate(
xfs_mount_t *mp,
xfs_ino_t ino)
{
xfs_agblock_t agblkno;
xfs_agino_t agino;
xfs_agnumber_t agno;
int ino_ok;
int ioff;
agno = XFS_INO_TO_AGNO(mp, ino);
agblkno = XFS_INO_TO_AGBNO(mp, ino);
ioff = XFS_INO_TO_OFFSET(mp, ino);
agino = XFS_OFFBNO_TO_AGINO(mp, agblkno, ioff);
ino_ok =
agno < mp->m_sb.sb_agcount &&
agblkno < mp->m_sb.sb_agblocks &&
agblkno != 0 &&
ioff < (1 << mp->m_sb.sb_inopblog) &&
XFS_AGINO_TO_INO(mp, agno, agino) == ino;
if (unlikely(XFS_TEST_ERROR(!ino_ok, mp, XFS_ERRTAG_DIR_INO_VALIDATE,
XFS_RANDOM_DIR_INO_VALIDATE))) {
xfs_warn(mp, "Invalid inode number 0x%Lx",
(unsigned long long) ino);
XFS_ERROR_REPORT("xfs_dir_ino_validate", XFS_ERRLEVEL_LOW, mp);
return XFS_ERROR(EFSCORRUPTED);
}
return 0;
}
void
asswarn(char *expr, char *file, int line)
{
xfs_warn(NULL, "Assertion failed: %s, file: %s, line: %d",
expr, file, line);
WARN_ON(1);
}
/*
* This routine is called to map an inode to the buffer containing the on-disk
* version of the inode. It returns a pointer to the buffer containing the
* on-disk inode in the bpp parameter, and in the dipp parameter it returns a
* pointer to the on-disk inode within that buffer.
*
* If a non-zero error is returned, then the contents of bpp and dipp are
* undefined.
*/
int
xfs_imap_to_bp(
struct xfs_mount *mp,
struct xfs_trans *tp,
struct xfs_imap *imap,
struct xfs_dinode **dipp,
struct xfs_buf **bpp,
uint buf_flags,
uint iget_flags)
{
struct xfs_buf *bp;
int error;
buf_flags |= XBF_UNMAPPED;
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
(int)imap->im_len, buf_flags, &bp,
&xfs_inode_buf_ops);
if (error) {
if (error == -EAGAIN) {
ASSERT(buf_flags & XBF_TRYLOCK);
return error;
}
xfs_warn(mp, "%s: xfs_trans_read_buf() returned error %d.",
__func__, error);
return error;
}
*bpp = bp;
*dipp = xfs_buf_offset(bp, imap->im_boffset);
return 0;
}
/*
* Second stage of a quiesce. The data is already synced, now we have to take
* care of the metadata. New transactions are already blocked, so we need to
* wait for any remaining transactions to drain out before proceeding.
*/
void
xfs_quiesce_attr(
struct xfs_mount *mp)
{
int error = 0;
/* wait for all modifications to complete */
while (atomic_read(&mp->m_active_trans) > 0)
delay(100);
/* reclaim inodes to do any IO before the freeze completes */
xfs_reclaim_inodes(mp, 0);
xfs_reclaim_inodes(mp, SYNC_WAIT);
/* flush all pending changes from the AIL */
xfs_ail_push_all_sync(mp->m_ail);
/*
* Just warn here till VFS can correctly support
* read-only remount without racing.
*/
WARN_ON(atomic_read(&mp->m_active_trans) != 0);
/* Push the superblock and write an unmount record */
error = xfs_log_sbcount(mp);
if (error)
xfs_warn(mp, "xfs_attr_quiesce: failed to log sb changes. "
"Frozen image may not be consistent.");
xfs_log_unmount_write(mp);
/*
* At this point we might have modified the superblock again and thus
* added an item to the AIL, thus flush it again.
*/
xfs_ail_push_all_sync(mp->m_ail);
/*
* The superblock buffer is uncached and xfsaild_push() will lock and
* set the XBF_ASYNC flag on the buffer. We cannot do xfs_buf_iowait()
* here but a lock on the superblock buffer will block until iodone()
* has completed.
*/
xfs_buf_lock(mp->m_sb_bp);
xfs_buf_unlock(mp->m_sb_bp);
}
static int
__xfs_ag_resv_init(
struct xfs_perag *pag,
enum xfs_ag_resv_type type,
xfs_extlen_t ask,
xfs_extlen_t used)
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_ag_resv *resv;
int error;
xfs_extlen_t reserved;
if (used > ask)
ask = used;
reserved = ask - used;
error = xfs_mod_fdblocks(mp, -(int64_t)reserved, true);
if (error) {
trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno,
error, _RET_IP_);
xfs_warn(mp,
"Per-AG reservation for AG %u failed. Filesystem may run out of space.",
pag->pag_agno);
return error;
}
/*
* Reduce the maximum per-AG allocation length by however much we're
* trying to reserve for an AG. Since this is a filesystem-wide
* counter, we only make the adjustment for AG 0. This assumes that
* there aren't any AGs hungrier for per-AG reservation than AG 0.
*/
if (pag->pag_agno == 0)
mp->m_ag_max_usable -= ask;
resv = xfs_perag_resv(pag, type);
resv->ar_asked = ask;
resv->ar_reserved = resv->ar_orig_reserved = reserved;
trace_xfs_ag_resv_init(pag, type, ask);
return 0;
}
STATIC int
xfs_qm_shake(
struct shrinker *shrink,
struct shrink_control *sc)
{
struct xfs_quotainfo *qi =
container_of(shrink, struct xfs_quotainfo, qi_shrinker);
int nr_to_scan = sc->nr_to_scan;
LIST_HEAD (buffer_list);
LIST_HEAD (dispose_list);
struct xfs_dquot *dqp;
int error;
if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT))
return 0;
if (!nr_to_scan)
goto out;
mutex_lock(&qi->qi_lru_lock);
while (!list_empty(&qi->qi_lru_list)) {
if (nr_to_scan-- <= 0)
break;
dqp = list_first_entry(&qi->qi_lru_list, struct xfs_dquot,
q_lru);
xfs_qm_dqreclaim_one(dqp, &buffer_list, &dispose_list);
}
mutex_unlock(&qi->qi_lru_lock);
error = xfs_buf_delwri_submit(&buffer_list);
if (error)
xfs_warn(NULL, "%s: dquot reclaim failed", __func__);
while (!list_empty(&dispose_list)) {
dqp = list_first_entry(&dispose_list, struct xfs_dquot, q_lru);
list_del_init(&dqp->q_lru);
xfs_qm_dqfree_one(dqp);
}
out:
return (qi->qi_lru_count / 100) * sysctl_vfs_cache_pressure;
}
STATIC uint
xfs_buf_item_push(
struct xfs_log_item *lip,
struct list_head *buffer_list)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
struct xfs_buf *bp = bip->bli_buf;
uint rval = XFS_ITEM_SUCCESS;
if (xfs_buf_ispinned(bp))
return XFS_ITEM_PINNED;
if (!xfs_buf_trylock(bp)) {
/*
* If we have just raced with a buffer being pinned and it has
* been marked stale, we could end up stalling until someone else
* issues a log force to unpin the stale buffer. Check for the
* race condition here so xfsaild recognizes the buffer is pinned
* and queues a log force to move it along.
*/
if (xfs_buf_ispinned(bp))
return XFS_ITEM_PINNED;
return XFS_ITEM_LOCKED;
}
ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
trace_xfs_buf_item_push(bip);
/* has a previous flush failed due to IO errors? */
if ((bp->b_flags & XBF_WRITE_FAIL) &&
___ratelimit(&xfs_buf_write_fail_rl_state, "XFS:")) {
xfs_warn(bp->b_target->bt_mount,
"Detected failing async write on buffer block 0x%llx. Retrying async write.\n",
(long long)bp->b_bn);
}
if (!xfs_buf_delwri_queue(bp, buffer_list))
rval = XFS_ITEM_FLUSHING;
xfs_buf_unlock(bp);
return rval;
}
int
xfs_error_test(int error_tag, int *fsidp, char *expression,
int line, char *file, unsigned long randfactor)
{
int i;
int64_t fsid;
if (prandom_u32() % randfactor)
return 0;
memcpy(&fsid, fsidp, sizeof(xfs_fsid_t));
for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) {
if (xfs_etest[i] == error_tag && xfs_etest_fsid[i] == fsid) {
xfs_warn(NULL,
"Injecting error (%s) at file %s, line %d, on filesystem \"%s\"",
expression, file, line, xfs_etest_fsname[i]);
return 1;
}
}
return 0;
}
void
xfs_quiesce_attr(
struct xfs_mount *mp)
{
int error = 0;
while (atomic_read(&mp->m_active_trans) > 0)
delay(100);
xfs_quiesce_fs(mp);
WARN_ON(atomic_read(&mp->m_active_trans) != 0);
error = xfs_log_sbcount(mp);
if (error)
xfs_warn(mp, "xfs_attr_quiesce: failed to log sb changes. "
"Frozen image may not be consistent.");
xfs_log_unmount_write(mp);
xfs_unmountfs_writesb(mp);
}
/*
* Inodes in different states need to be treated differently, and the return
* value of xfs_iflush is not sufficient to get this right. The following table
* lists the inode states and the reclaim actions necessary for non-blocking
* reclaim:
*
*
* inode state iflush ret required action
* --------------- ---------- ---------------
* bad - reclaim
* shutdown EIO unpin and reclaim
* clean, unpinned 0 reclaim
* stale, unpinned 0 reclaim
* clean, pinned(*) 0 requeue
* stale, pinned EAGAIN requeue
* dirty, delwri ok 0 requeue
* dirty, delwri blocked EAGAIN requeue
* dirty, sync flush 0 reclaim
*
* (*) dgc: I don't think the clean, pinned state is possible but it gets
* handled anyway given the order of checks implemented.
*
* As can be seen from the table, the return value of xfs_iflush() is not
* sufficient to correctly decide the reclaim action here. The checks in
* xfs_iflush() might look like duplicates, but they are not.
*
* Also, because we get the flush lock first, we know that any inode that has
* been flushed delwri has had the flush completed by the time we check that
* the inode is clean. The clean inode check needs to be done before flushing
* the inode delwri otherwise we would loop forever requeuing clean inodes as
* we cannot tell apart a successful delwri flush and a clean inode from the
* return value of xfs_iflush().
*
* Note that because the inode is flushed delayed write by background
* writeback, the flush lock may already be held here and waiting on it can
* result in very long latencies. Hence for sync reclaims, where we wait on the
* flush lock, the caller should push out delayed write inodes first before
* trying to reclaim them to minimise the amount of time spent waiting. For
* background relaim, we just requeue the inode for the next pass.
*
* Hence the order of actions after gaining the locks should be:
* bad => reclaim
* shutdown => unpin and reclaim
* pinned, delwri => requeue
* pinned, sync => unpin
* stale => reclaim
* clean => reclaim
* dirty, delwri => flush and requeue
* dirty, sync => flush, wait and reclaim
*/
STATIC int
xfs_reclaim_inode(
struct xfs_inode *ip,
struct xfs_perag *pag,
int sync_mode)
{
int error;
restart:
error = 0;
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (!xfs_iflock_nowait(ip)) {
if (!(sync_mode & SYNC_WAIT))
goto out;
/*
* If we only have a single dirty inode in a cluster there is
* a fair chance that the AIL push may have pushed it into
* the buffer, but xfsbufd won't touch it until 30 seconds
* from now, and thus we will lock up here.
*
* Promote the inode buffer to the front of the delwri list
* and wake up xfsbufd now.
*/
xfs_promote_inode(ip);
xfs_iflock(ip);
}
if (is_bad_inode(VFS_I(ip)))
goto reclaim;
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_iunpin_wait(ip);
goto reclaim;
}
if (xfs_ipincount(ip)) {
if (!(sync_mode & SYNC_WAIT)) {
xfs_ifunlock(ip);
goto out;
}
xfs_iunpin_wait(ip);
}
if (xfs_iflags_test(ip, XFS_ISTALE))
goto reclaim;
if (xfs_inode_clean(ip))
goto reclaim;
/*
* Now we have an inode that needs flushing.
*
* We do a nonblocking flush here even if we are doing a SYNC_WAIT
* reclaim as we can deadlock with inode cluster removal.
* xfs_ifree_cluster() can lock the inode buffer before it locks the
* ip->i_lock, and we are doing the exact opposite here. As a result,
* doing a blocking xfs_itobp() to get the cluster buffer will result
* in an ABBA deadlock with xfs_ifree_cluster().
*
* As xfs_ifree_cluser() must gather all inodes that are active in the
* cache to mark them stale, if we hit this case we don't actually want
* to do IO here - we want the inode marked stale so we can simply
* reclaim it. Hence if we get an EAGAIN error on a SYNC_WAIT flush,
* just unlock the inode, back off and try again. Hopefully the next
* pass through will see the stale flag set on the inode.
*/
error = xfs_iflush(ip, SYNC_TRYLOCK | sync_mode);
if (sync_mode & SYNC_WAIT) {
if (error == EAGAIN) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/* backoff longer than in xfs_ifree_cluster */
delay(2);
goto restart;
}
xfs_iflock(ip);
goto reclaim;
}
/*
* When we have to flush an inode but don't have SYNC_WAIT set, we
* flush the inode out using a delwri buffer and wait for the next
* call into reclaim to find it in a clean state instead of waiting for
* it now. We also don't return errors here - if the error is transient
* then the next reclaim pass will flush the inode, and if the error
* is permanent then the next sync reclaim will reclaim the inode and
* pass on the error.
*/
if (error && error != EAGAIN && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_warn(ip->i_mount,
"inode 0x%llx background reclaim flush failed with %d",
(long long)ip->i_ino, error);
}
out:
xfs_iflags_clear(ip, XFS_IRECLAIM);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/*
* We could return EAGAIN here to make reclaim rescan the inode tree in
* a short while. However, this just burns CPU time scanning the tree
* waiting for IO to complete and xfssyncd never goes back to the idle
* state. Instead, return 0 to let the next scheduled background reclaim
* attempt to reclaim the inode again.
*/
return 0;
reclaim:
xfs_ifunlock(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
XFS_STATS_INC(xs_ig_reclaims);
/*
* Remove the inode from the per-AG radix tree.
*
* Because radix_tree_delete won't complain even if the item was never
* added to the tree assert that it's been there before to catch
* problems with the inode life time early on.
*/
spin_lock(&pag->pag_ici_lock);
if (!radix_tree_delete(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino)))
ASSERT(0);
__xfs_inode_clear_reclaim(pag, ip);
spin_unlock(&pag->pag_ici_lock);
/*
* Here we do an (almost) spurious inode lock in order to coordinate
* with inode cache radix tree lookups. This is because the lookup
* can reference the inodes in the cache without taking references.
*
* We make that OK here by ensuring that we wait until the inode is
* unlocked after the lookup before we go ahead and free it. We get
* both the ilock and the iolock because the code may need to drop the
* ilock one but will still hold the iolock.
*/
xfs_ilock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_qm_dqdetach(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_inode_free(ip);
return error;
}
STATIC int
xfs_reclaim_inode(
struct xfs_inode *ip,
struct xfs_perag *pag,
int sync_mode)
{
int error;
restart:
error = 0;
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (!xfs_iflock_nowait(ip)) {
if (!(sync_mode & SYNC_WAIT))
goto out;
xfs_promote_inode(ip);
xfs_iflock(ip);
}
if (is_bad_inode(VFS_I(ip)))
goto reclaim;
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_iunpin_wait(ip);
goto reclaim;
}
if (xfs_ipincount(ip)) {
if (!(sync_mode & SYNC_WAIT)) {
xfs_ifunlock(ip);
goto out;
}
xfs_iunpin_wait(ip);
}
if (xfs_iflags_test(ip, XFS_ISTALE))
goto reclaim;
if (xfs_inode_clean(ip))
goto reclaim;
error = xfs_iflush(ip, SYNC_TRYLOCK | sync_mode);
if (sync_mode & SYNC_WAIT) {
if (error == EAGAIN) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
delay(2);
goto restart;
}
xfs_iflock(ip);
goto reclaim;
}
if (error && error != EAGAIN && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_warn(ip->i_mount,
"inode 0x%llx background reclaim flush failed with %d",
(long long)ip->i_ino, error);
}
out:
xfs_iflags_clear(ip, XFS_IRECLAIM);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return 0;
reclaim:
xfs_ifunlock(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
XFS_STATS_INC(xs_ig_reclaims);
spin_lock(&pag->pag_ici_lock);
if (!radix_tree_delete(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino)))
ASSERT(0);
__xfs_inode_clear_reclaim(pag, ip);
spin_unlock(&pag->pag_ici_lock);
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_qm_dqdetach(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_inode_free(ip);
return error;
}
/*
* This is called from xfs_mountfs to start quotas and initialize all
* necessary data structures like quotainfo. This is also responsible for
* running a quotacheck as necessary. We are guaranteed that the superblock
* is consistently read in at this point.
*
* If we fail here, the mount will continue with quota turned off. We don't
* need to inidicate success or failure at all.
*/
void
xfs_qm_mount_quotas(
xfs_mount_t *mp)
{
int error = 0;
uint sbf;
/*
* If quotas on realtime volumes is not supported, we disable
* quotas immediately.
*/
if (mp->m_sb.sb_rextents) {
xfs_notice(mp, "Cannot turn on quotas for realtime filesystem");
mp->m_qflags = 0;
goto write_changes;
}
ASSERT(XFS_IS_QUOTA_RUNNING(mp));
/*
* Allocate the quotainfo structure inside the mount struct, and
* create quotainode(s), and change/rev superblock if necessary.
*/
error = xfs_qm_init_quotainfo(mp);
if (error) {
/*
* We must turn off quotas.
*/
ASSERT(mp->m_quotainfo == NULL);
mp->m_qflags = 0;
goto write_changes;
}
/*
* If any of the quotas are not consistent, do a quotacheck.
*/
if (XFS_QM_NEED_QUOTACHECK(mp)) {
error = xfs_qm_quotacheck(mp);
if (error) {
/* Quotacheck failed and disabled quotas. */
return;
}
}
/*
* If one type of quotas is off, then it will lose its
* quotachecked status, since we won't be doing accounting for
* that type anymore.
*/
if (!XFS_IS_UQUOTA_ON(mp))
mp->m_qflags &= ~XFS_UQUOTA_CHKD;
if (!(XFS_IS_GQUOTA_ON(mp) || XFS_IS_PQUOTA_ON(mp)))
mp->m_qflags &= ~XFS_OQUOTA_CHKD;
write_changes:
/*
* We actually don't have to acquire the m_sb_lock at all.
* This can only be called from mount, and that's single threaded. XXX
*/
spin_lock(&mp->m_sb_lock);
sbf = mp->m_sb.sb_qflags;
mp->m_sb.sb_qflags = mp->m_qflags & XFS_MOUNT_QUOTA_ALL;
spin_unlock(&mp->m_sb_lock);
if (sbf != (mp->m_qflags & XFS_MOUNT_QUOTA_ALL)) {
if (xfs_qm_write_sb_changes(mp, XFS_SB_QFLAGS)) {
/*
* We could only have been turning quotas off.
* We aren't in very good shape actually because
* the incore structures are convinced that quotas are
* off, but the on disk superblock doesn't know that !
*/
ASSERT(!(XFS_IS_QUOTA_RUNNING(mp)));
xfs_alert(mp, "%s: Superblock update failed!",
__func__);
}
}
if (error) {
xfs_warn(mp, "Failed to initialize disk quotas.");
return;
}
}
STATIC void
xfs_qm_dqreclaim_one(
struct xfs_dquot *dqp,
struct list_head *buffer_list,
struct list_head *dispose_list)
{
struct xfs_mount *mp = dqp->q_mount;
struct xfs_quotainfo *qi = mp->m_quotainfo;
int error;
if (!xfs_dqlock_nowait(dqp))
goto out_move_tail;
/*
* This dquot has acquired a reference in the meantime remove it from
* the freelist and try again.
*/
if (dqp->q_nrefs) {
xfs_dqunlock(dqp);
trace_xfs_dqreclaim_want(dqp);
XFS_STATS_INC(xs_qm_dqwants);
list_del_init(&dqp->q_lru);
qi->qi_lru_count--;
XFS_STATS_DEC(xs_qm_dquot_unused);
return;
}
/*
* Try to grab the flush lock. If this dquot is in the process of
* getting flushed to disk, we don't want to reclaim it.
*/
if (!xfs_dqflock_nowait(dqp))
goto out_unlock_move_tail;
if (XFS_DQ_IS_DIRTY(dqp)) {
struct xfs_buf *bp = NULL;
trace_xfs_dqreclaim_dirty(dqp);
error = xfs_qm_dqflush(dqp, &bp);
if (error) {
xfs_warn(mp, "%s: dquot %p flush failed",
__func__, dqp);
goto out_unlock_move_tail;
}
xfs_buf_delwri_queue(bp, buffer_list);
xfs_buf_relse(bp);
/*
* Give the dquot another try on the freelist, as the
* flushing will take some time.
*/
goto out_unlock_move_tail;
}
xfs_dqfunlock(dqp);
/*
* Prevent lookups now that we are past the point of no return.
*/
dqp->dq_flags |= XFS_DQ_FREEING;
xfs_dqunlock(dqp);
ASSERT(dqp->q_nrefs == 0);
list_move_tail(&dqp->q_lru, dispose_list);
qi->qi_lru_count--;
XFS_STATS_DEC(xs_qm_dquot_unused);
trace_xfs_dqreclaim_done(dqp);
XFS_STATS_INC(xs_qm_dqreclaims);
return;
/*
* Move the dquot to the tail of the list so that we don't spin on it.
*/
out_unlock_move_tail:
xfs_dqunlock(dqp);
out_move_tail:
list_move_tail(&dqp->q_lru, &qi->qi_lru_list);
trace_xfs_dqreclaim_busy(dqp);
XFS_STATS_INC(xs_qm_dqreclaim_misses);
}
/*
* Purge a dquot from all tracking data structures and free it.
*/
STATIC int
xfs_qm_dqpurge(
struct xfs_dquot *dqp,
void *data)
{
struct xfs_mount *mp = dqp->q_mount;
struct xfs_quotainfo *qi = mp->m_quotainfo;
struct xfs_dquot *gdqp = NULL;
xfs_dqlock(dqp);
if ((dqp->dq_flags & XFS_DQ_FREEING) || dqp->q_nrefs != 0) {
xfs_dqunlock(dqp);
return EAGAIN;
}
/*
* If this quota has a group hint attached, prepare for releasing it
* now.
*/
gdqp = dqp->q_gdquot;
if (gdqp) {
xfs_dqlock(gdqp);
dqp->q_gdquot = NULL;
}
dqp->dq_flags |= XFS_DQ_FREEING;
xfs_dqflock(dqp);
/*
* If we are turning this type of quotas off, we don't care
* about the dirty metadata sitting in this dquot. OTOH, if
* we're unmounting, we do care, so we flush it and wait.
*/
if (XFS_DQ_IS_DIRTY(dqp)) {
struct xfs_buf *bp = NULL;
int error;
/*
* We don't care about getting disk errors here. We need
* to purge this dquot anyway, so we go ahead regardless.
*/
error = xfs_qm_dqflush(dqp, &bp);
if (error) {
xfs_warn(mp, "%s: dquot %p flush failed",
__func__, dqp);
} else {
error = xfs_bwrite(bp);
xfs_buf_relse(bp);
}
xfs_dqflock(dqp);
}
ASSERT(atomic_read(&dqp->q_pincount) == 0);
ASSERT(XFS_FORCED_SHUTDOWN(mp) ||
!(dqp->q_logitem.qli_item.li_flags & XFS_LI_IN_AIL));
xfs_dqfunlock(dqp);
xfs_dqunlock(dqp);
radix_tree_delete(XFS_DQUOT_TREE(qi, dqp->q_core.d_flags),
be32_to_cpu(dqp->q_core.d_id));
qi->qi_dquots--;
/*
* We move dquots to the freelist as soon as their reference count
* hits zero, so it really should be on the freelist here.
*/
mutex_lock(&qi->qi_lru_lock);
ASSERT(!list_empty(&dqp->q_lru));
list_del_init(&dqp->q_lru);
qi->qi_lru_count--;
XFS_STATS_DEC(xs_qm_dquot_unused);
mutex_unlock(&qi->qi_lru_lock);
xfs_qm_dqdestroy(dqp);
if (gdqp)
xfs_qm_dqput(gdqp);
return 0;
}
/*
* Walk thru all the filesystem inodes and construct a consistent view
* of the disk quota world. If the quotacheck fails, disable quotas.
*/
int
xfs_qm_quotacheck(
xfs_mount_t *mp)
{
int done, count, error, error2;
xfs_ino_t lastino;
size_t structsz;
xfs_inode_t *uip, *gip;
uint flags;
LIST_HEAD (buffer_list);
count = INT_MAX;
structsz = 1;
lastino = 0;
flags = 0;
ASSERT(mp->m_quotainfo->qi_uquotaip || mp->m_quotainfo->qi_gquotaip);
ASSERT(XFS_IS_QUOTA_RUNNING(mp));
xfs_notice(mp, "Quotacheck needed: Please wait.");
/*
* First we go thru all the dquots on disk, USR and GRP/PRJ, and reset
* their counters to zero. We need a clean slate.
* We don't log our changes till later.
*/
uip = mp->m_quotainfo->qi_uquotaip;
if (uip) {
error = xfs_qm_dqiterate(mp, uip, XFS_QMOPT_UQUOTA,
&buffer_list);
if (error)
goto error_return;
flags |= XFS_UQUOTA_CHKD;
}
gip = mp->m_quotainfo->qi_gquotaip;
if (gip) {
error = xfs_qm_dqiterate(mp, gip, XFS_IS_GQUOTA_ON(mp) ?
XFS_QMOPT_GQUOTA : XFS_QMOPT_PQUOTA,
&buffer_list);
if (error)
goto error_return;
flags |= XFS_OQUOTA_CHKD;
}
do {
/*
* Iterate thru all the inodes in the file system,
* adjusting the corresponding dquot counters in core.
*/
error = xfs_bulkstat(mp, &lastino, &count,
xfs_qm_dqusage_adjust,
structsz, NULL, &done);
if (error)
break;
} while (!done);
/*
* We've made all the changes that we need to make incore. Flush them
* down to disk buffers if everything was updated successfully.
*/
if (XFS_IS_UQUOTA_ON(mp)) {
error = xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_flush_one,
&buffer_list);
}
if (XFS_IS_GQUOTA_ON(mp)) {
error2 = xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_flush_one,
&buffer_list);
if (!error)
error = error2;
}
if (XFS_IS_PQUOTA_ON(mp)) {
error2 = xfs_qm_dquot_walk(mp, XFS_DQ_PROJ, xfs_qm_flush_one,
&buffer_list);
if (!error)
error = error2;
}
error2 = xfs_buf_delwri_submit(&buffer_list);
if (!error)
error = error2;
/*
* We can get this error if we couldn't do a dquot allocation inside
* xfs_qm_dqusage_adjust (via bulkstat). We don't care about the
* dirty dquots that might be cached, we just want to get rid of them
* and turn quotaoff. The dquots won't be attached to any of the inodes
* at this point (because we intentionally didn't in dqget_noattach).
*/
if (error) {
xfs_qm_dqpurge_all(mp, XFS_QMOPT_QUOTALL);
goto error_return;
}
/*
* If one type of quotas is off, then it will lose its
* quotachecked status, since we won't be doing accounting for
* that type anymore.
*/
mp->m_qflags &= ~XFS_ALL_QUOTA_CHKD;
mp->m_qflags |= flags;
error_return:
while (!list_empty(&buffer_list)) {
struct xfs_buf *bp =
list_first_entry(&buffer_list, struct xfs_buf, b_list);
list_del_init(&bp->b_list);
xfs_buf_relse(bp);
}
if (error) {
xfs_warn(mp,
"Quotacheck: Unsuccessful (Error %d): Disabling quotas.",
error);
/*
* We must turn off quotas.
*/
ASSERT(mp->m_quotainfo != NULL);
xfs_qm_destroy_quotainfo(mp);
if (xfs_mount_reset_sbqflags(mp)) {
xfs_warn(mp,
"Quotacheck: Failed to reset quota flags.");
}
} else
xfs_notice(mp, "Quotacheck: Done.");
return (error);
}
/*
* Check the validity of the SB found.
*/
STATIC int
xfs_mount_validate_sb(
xfs_mount_t *mp,
xfs_sb_t *sbp,
bool check_inprogress,
bool check_version)
{
/*
* If the log device and data device have the
* same device number, the log is internal.
* Consequently, the sb_logstart should be non-zero. If
* we have a zero sb_logstart in this case, we may be trying to mount
* a volume filesystem in a non-volume manner.
*/
if (sbp->sb_magicnum != XFS_SB_MAGIC) {
xfs_warn(mp, "bad magic number");
return -EWRONGFS;
}
if (!xfs_sb_good_version(sbp)) {
xfs_warn(mp, "bad version");
return -EWRONGFS;
}
/*
* Version 5 superblock feature mask validation. Reject combinations the
* kernel cannot support up front before checking anything else. For
* write validation, we don't need to check feature masks.
*/
if (check_version && XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) {
if (xfs_sb_has_compat_feature(sbp,
XFS_SB_FEAT_COMPAT_UNKNOWN)) {
xfs_warn(mp,
"Superblock has unknown compatible features (0x%x) enabled.\n"
"Using a more recent kernel is recommended.",
(sbp->sb_features_compat &
XFS_SB_FEAT_COMPAT_UNKNOWN));
}
if (xfs_sb_has_ro_compat_feature(sbp,
XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
xfs_alert(mp,
"Superblock has unknown read-only compatible features (0x%x) enabled.",
(sbp->sb_features_ro_compat &
XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
xfs_warn(mp,
"Attempted to mount read-only compatible filesystem read-write.\n"
"Filesystem can only be safely mounted read only.");
return -EINVAL;
}
}
if (xfs_sb_has_incompat_feature(sbp,
XFS_SB_FEAT_INCOMPAT_UNKNOWN)) {
xfs_warn(mp,
"Superblock has unknown incompatible features (0x%x) enabled.\n"
"Filesystem can not be safely mounted by this kernel.",
(sbp->sb_features_incompat &
XFS_SB_FEAT_INCOMPAT_UNKNOWN));
return -EINVAL;
}
}
if (xfs_sb_version_has_pquotino(sbp)) {
if (sbp->sb_qflags & (XFS_OQUOTA_ENFD | XFS_OQUOTA_CHKD)) {
xfs_notice(mp,
"Version 5 of Super block has XFS_OQUOTA bits.");
return -EFSCORRUPTED;
}
} else if (sbp->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD |
XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) {
xfs_notice(mp,
"Superblock earlier than Version 5 has XFS_[PQ]UOTA_{ENFD|CHKD} bits.");
return -EFSCORRUPTED;
}
if (unlikely(
sbp->sb_logstart == 0 && mp->m_logdev_targp == mp->m_ddev_targp)) {
xfs_warn(mp,
"filesystem is marked as having an external log; "
"specify logdev on the mount command line.");
return -EINVAL;
}
if (unlikely(
sbp->sb_logstart != 0 && mp->m_logdev_targp != mp->m_ddev_targp)) {
xfs_warn(mp,
"filesystem is marked as having an internal log; "
"do not specify logdev on the mount command line.");
return -EINVAL;
}
/*
* More sanity checking. Most of these were stolen directly from
* xfs_repair.
*/
if (unlikely(
sbp->sb_agcount <= 0 ||
sbp->sb_sectsize < XFS_MIN_SECTORSIZE ||
sbp->sb_sectsize > XFS_MAX_SECTORSIZE ||
sbp->sb_sectlog < XFS_MIN_SECTORSIZE_LOG ||
sbp->sb_sectlog > XFS_MAX_SECTORSIZE_LOG ||
sbp->sb_sectsize != (1 << sbp->sb_sectlog) ||
sbp->sb_blocksize < XFS_MIN_BLOCKSIZE ||
sbp->sb_blocksize > XFS_MAX_BLOCKSIZE ||
sbp->sb_blocklog < XFS_MIN_BLOCKSIZE_LOG ||
sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG ||
sbp->sb_blocksize != (1 << sbp->sb_blocklog) ||
sbp->sb_inodesize < XFS_DINODE_MIN_SIZE ||
sbp->sb_inodesize > XFS_DINODE_MAX_SIZE ||
sbp->sb_inodelog < XFS_DINODE_MIN_LOG ||
sbp->sb_inodelog > XFS_DINODE_MAX_LOG ||
sbp->sb_inodesize != (1 << sbp->sb_inodelog) ||
sbp->sb_inopblock != howmany(sbp->sb_blocksize,sbp->sb_inodesize) ||
(sbp->sb_blocklog - sbp->sb_inodelog != sbp->sb_inopblog) ||
(sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE) ||
(sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) ||
(sbp->sb_imax_pct > 100 /* zero sb_imax_pct is valid */) ||
sbp->sb_dblocks == 0 ||
sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp) ||
sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp) ||
sbp->sb_shared_vn != 0)) {
xfs_notice(mp, "SB sanity check failed");
return -EFSCORRUPTED;
}
/*
* Until this is fixed only page-sized or smaller data blocks work.
*/
if (unlikely(sbp->sb_blocksize > PAGE_SIZE)) {
xfs_warn(mp,
"File system with blocksize %d bytes. "
"Only pagesize (%ld) or less will currently work.",
sbp->sb_blocksize, PAGE_SIZE);
return -ENOSYS;
}
/*
* Currently only very few inode sizes are supported.
*/
switch (sbp->sb_inodesize) {
case 256:
case 512:
case 1024:
case 2048:
break;
default:
xfs_warn(mp, "inode size of %d bytes not supported",
sbp->sb_inodesize);
return -ENOSYS;
}
if (xfs_sb_validate_fsb_count(sbp, sbp->sb_dblocks) ||
xfs_sb_validate_fsb_count(sbp, sbp->sb_rblocks)) {
xfs_warn(mp,
"file system too large to be mounted on this system.");
return -EFBIG;
}
if (check_inprogress && sbp->sb_inprogress) {
xfs_warn(mp, "Offline file system operation in progress!");
return -EFSCORRUPTED;
}
return 0;
}
int
xfs_qm_newmount(
xfs_mount_t *mp,
uint *needquotamount,
uint *quotaflags)
{
uint quotaondisk;
uint uquotaondisk = 0, gquotaondisk = 0, pquotaondisk = 0;
quotaondisk = xfs_sb_version_hasquota(&mp->m_sb) &&
(mp->m_sb.sb_qflags & XFS_ALL_QUOTA_ACCT);
if (quotaondisk) {
uquotaondisk = mp->m_sb.sb_qflags & XFS_UQUOTA_ACCT;
pquotaondisk = mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT;
gquotaondisk = mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT;
}
/*
* If the device itself is read-only, we can't allow
* the user to change the state of quota on the mount -
* this would generate a transaction on the ro device,
* which would lead to an I/O error and shutdown
*/
if (((uquotaondisk && !XFS_IS_UQUOTA_ON(mp)) ||
(!uquotaondisk && XFS_IS_UQUOTA_ON(mp)) ||
(gquotaondisk && !XFS_IS_GQUOTA_ON(mp)) ||
(!gquotaondisk && XFS_IS_GQUOTA_ON(mp)) ||
(pquotaondisk && !XFS_IS_PQUOTA_ON(mp)) ||
(!pquotaondisk && XFS_IS_PQUOTA_ON(mp))) &&
xfs_dev_is_read_only(mp, "changing quota state")) {
xfs_warn(mp, "please mount with%s%s%s%s.",
(!quotaondisk ? "out quota" : ""),
(uquotaondisk ? " usrquota" : ""),
(gquotaondisk ? " grpquota" : ""),
(pquotaondisk ? " prjquota" : ""));
return XFS_ERROR(EPERM);
}
if (XFS_IS_QUOTA_ON(mp) || quotaondisk) {
/*
* Call mount_quotas at this point only if we won't have to do
* a quotacheck.
*/
if (quotaondisk && !XFS_QM_NEED_QUOTACHECK(mp)) {
/*
* If an error occurred, qm_mount_quotas code
* has already disabled quotas. So, just finish
* mounting, and get on with the boring life
* without disk quotas.
*/
xfs_qm_mount_quotas(mp);
} else {
/*
* Clear the quota flags, but remember them. This
* is so that the quota code doesn't get invoked
* before we're ready. This can happen when an
* inode goes inactive and wants to free blocks,
* or via xfs_log_mount_finish.
*/
*needquotamount = true;
*quotaflags = mp->m_qflags;
mp->m_qflags = 0;
}
}
return 0;
}
/*
* This function fills in xfs_mount_t fields based on mount args.
* Note: the superblock has _not_ yet been read in.
*
* Note that this function leaks the various device name allocations on
* failure. The caller takes care of them.
*/
STATIC int
xfs_parseargs(
struct xfs_mount *mp,
char *options)
{
struct super_block *sb = mp->m_super;
char *this_char, *value;
int dsunit = 0;
int dswidth = 0;
int iosize = 0;
__uint8_t iosizelog = 0;
/*
* set up the mount name first so all the errors will refer to the
* correct device.
*/
mp->m_fsname = kstrndup(sb->s_id, MAXNAMELEN, GFP_KERNEL);
if (!mp->m_fsname)
return -ENOMEM;
mp->m_fsname_len = strlen(mp->m_fsname) + 1;
/*
* Copy binary VFS mount flags we are interested in.
*/
if (sb->s_flags & MS_RDONLY)
mp->m_flags |= XFS_MOUNT_RDONLY;
if (sb->s_flags & MS_DIRSYNC)
mp->m_flags |= XFS_MOUNT_DIRSYNC;
if (sb->s_flags & MS_SYNCHRONOUS)
mp->m_flags |= XFS_MOUNT_WSYNC;
/*
* Set some default flags that could be cleared by the mount option
* parsing.
*/
mp->m_flags |= XFS_MOUNT_BARRIER;
mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
/*
* These can be overridden by the mount option parsing.
*/
mp->m_logbufs = -1;
mp->m_logbsize = -1;
if (!options)
goto done;
while ((this_char = strsep(&options, ",")) != NULL) {
if (!*this_char)
continue;
if ((value = strchr(this_char, '=')) != NULL)
*value++ = 0;
if (!strcmp(this_char, MNTOPT_LOGBUFS)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return -EINVAL;
}
if (kstrtoint(value, 10, &mp->m_logbufs))
return -EINVAL;
} else if (!strcmp(this_char, MNTOPT_LOGBSIZE)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return -EINVAL;
}
if (suffix_kstrtoint(value, 10, &mp->m_logbsize))
return -EINVAL;
} else if (!strcmp(this_char, MNTOPT_LOGDEV)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return -EINVAL;
}
mp->m_logname = kstrndup(value, MAXNAMELEN, GFP_KERNEL);
if (!mp->m_logname)
return -ENOMEM;
} else if (!strcmp(this_char, MNTOPT_MTPT)) {
xfs_warn(mp, "%s option not allowed on this system",
this_char);
return -EINVAL;
} else if (!strcmp(this_char, MNTOPT_RTDEV)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return -EINVAL;
}
mp->m_rtname = kstrndup(value, MAXNAMELEN, GFP_KERNEL);
if (!mp->m_rtname)
return -ENOMEM;
} else if (!strcmp(this_char, MNTOPT_BIOSIZE)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return -EINVAL;
}
if (kstrtoint(value, 10, &iosize))
return -EINVAL;
iosizelog = ffs(iosize) - 1;
} else if (!strcmp(this_char, MNTOPT_ALLOCSIZE)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return -EINVAL;
}
if (suffix_kstrtoint(value, 10, &iosize))
return -EINVAL;
iosizelog = ffs(iosize) - 1;
} else if (!strcmp(this_char, MNTOPT_GRPID) ||
!strcmp(this_char, MNTOPT_BSDGROUPS)) {
mp->m_flags |= XFS_MOUNT_GRPID;
} else if (!strcmp(this_char, MNTOPT_NOGRPID) ||
!strcmp(this_char, MNTOPT_SYSVGROUPS)) {
mp->m_flags &= ~XFS_MOUNT_GRPID;
} else if (!strcmp(this_char, MNTOPT_WSYNC)) {
mp->m_flags |= XFS_MOUNT_WSYNC;
} else if (!strcmp(this_char, MNTOPT_NORECOVERY)) {
mp->m_flags |= XFS_MOUNT_NORECOVERY;
} else if (!strcmp(this_char, MNTOPT_NOALIGN)) {
mp->m_flags |= XFS_MOUNT_NOALIGN;
} else if (!strcmp(this_char, MNTOPT_SWALLOC)) {
mp->m_flags |= XFS_MOUNT_SWALLOC;
} else if (!strcmp(this_char, MNTOPT_SUNIT)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return -EINVAL;
}
if (kstrtoint(value, 10, &dsunit))
return -EINVAL;
} else if (!strcmp(this_char, MNTOPT_SWIDTH)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return -EINVAL;
}
if (kstrtoint(value, 10, &dswidth))
return -EINVAL;
} else if (!strcmp(this_char, MNTOPT_32BITINODE)) {
mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
} else if (!strcmp(this_char, MNTOPT_64BITINODE)) {
mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
} else if (!strcmp(this_char, MNTOPT_NOUUID)) {
mp->m_flags |= XFS_MOUNT_NOUUID;
} else if (!strcmp(this_char, MNTOPT_BARRIER)) {
mp->m_flags |= XFS_MOUNT_BARRIER;
} else if (!strcmp(this_char, MNTOPT_NOBARRIER)) {
mp->m_flags &= ~XFS_MOUNT_BARRIER;
} else if (!strcmp(this_char, MNTOPT_IKEEP)) {
mp->m_flags |= XFS_MOUNT_IKEEP;
} else if (!strcmp(this_char, MNTOPT_NOIKEEP)) {
mp->m_flags &= ~XFS_MOUNT_IKEEP;
} else if (!strcmp(this_char, MNTOPT_LARGEIO)) {
mp->m_flags &= ~XFS_MOUNT_COMPAT_IOSIZE;
} else if (!strcmp(this_char, MNTOPT_NOLARGEIO)) {
mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
} else if (!strcmp(this_char, MNTOPT_ATTR2)) {
mp->m_flags |= XFS_MOUNT_ATTR2;
} else if (!strcmp(this_char, MNTOPT_NOATTR2)) {
mp->m_flags &= ~XFS_MOUNT_ATTR2;
mp->m_flags |= XFS_MOUNT_NOATTR2;
} else if (!strcmp(this_char, MNTOPT_FILESTREAM)) {
mp->m_flags |= XFS_MOUNT_FILESTREAMS;
} else if (!strcmp(this_char, MNTOPT_NOQUOTA)) {
mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
} else if (!strcmp(this_char, MNTOPT_QUOTA) ||
!strcmp(this_char, MNTOPT_UQUOTA) ||
!strcmp(this_char, MNTOPT_USRQUOTA)) {
mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
XFS_UQUOTA_ENFD);
} else if (!strcmp(this_char, MNTOPT_QUOTANOENF) ||
!strcmp(this_char, MNTOPT_UQUOTANOENF)) {
mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_UQUOTA_ENFD;
} else if (!strcmp(this_char, MNTOPT_PQUOTA) ||
!strcmp(this_char, MNTOPT_PRJQUOTA)) {
mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
XFS_PQUOTA_ENFD);
} else if (!strcmp(this_char, MNTOPT_PQUOTANOENF)) {
mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_PQUOTA_ENFD;
} else if (!strcmp(this_char, MNTOPT_GQUOTA) ||
!strcmp(this_char, MNTOPT_GRPQUOTA)) {
mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
XFS_GQUOTA_ENFD);
} else if (!strcmp(this_char, MNTOPT_GQUOTANOENF)) {
mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_GQUOTA_ENFD;
} else if (!strcmp(this_char, MNTOPT_DISCARD)) {
mp->m_flags |= XFS_MOUNT_DISCARD;
} else if (!strcmp(this_char, MNTOPT_NODISCARD)) {
mp->m_flags &= ~XFS_MOUNT_DISCARD;
} else {
xfs_warn(mp, "unknown mount option [%s].", this_char);
return -EINVAL;
}
}
/*
* no recovery flag requires a read-only mount
*/
if ((mp->m_flags & XFS_MOUNT_NORECOVERY) &&
!(mp->m_flags & XFS_MOUNT_RDONLY)) {
xfs_warn(mp, "no-recovery mounts must be read-only.");
return -EINVAL;
}
if ((mp->m_flags & XFS_MOUNT_NOALIGN) && (dsunit || dswidth)) {
xfs_warn(mp,
"sunit and swidth options incompatible with the noalign option");
return -EINVAL;
}
#ifndef CONFIG_XFS_QUOTA
if (XFS_IS_QUOTA_RUNNING(mp)) {
xfs_warn(mp, "quota support not available in this kernel.");
return -EINVAL;
}
#endif
if ((dsunit && !dswidth) || (!dsunit && dswidth)) {
xfs_warn(mp, "sunit and swidth must be specified together");
return -EINVAL;
}
if (dsunit && (dswidth % dsunit != 0)) {
xfs_warn(mp,
"stripe width (%d) must be a multiple of the stripe unit (%d)",
dswidth, dsunit);
return -EINVAL;
}
done:
if (dsunit && !(mp->m_flags & XFS_MOUNT_NOALIGN)) {
/*
* At this point the superblock has not been read
* in, therefore we do not know the block size.
* Before the mount call ends we will convert
* these to FSBs.
*/
mp->m_dalign = dsunit;
mp->m_swidth = dswidth;
}
if (mp->m_logbufs != -1 &&
mp->m_logbufs != 0 &&
(mp->m_logbufs < XLOG_MIN_ICLOGS ||
mp->m_logbufs > XLOG_MAX_ICLOGS)) {
xfs_warn(mp, "invalid logbufs value: %d [not %d-%d]",
mp->m_logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS);
return -EINVAL;
}
if (mp->m_logbsize != -1 &&
mp->m_logbsize != 0 &&
(mp->m_logbsize < XLOG_MIN_RECORD_BSIZE ||
mp->m_logbsize > XLOG_MAX_RECORD_BSIZE ||
!is_power_of_2(mp->m_logbsize))) {
xfs_warn(mp,
"invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]",
mp->m_logbsize);
return -EINVAL;
}
if (iosizelog) {
if (iosizelog > XFS_MAX_IO_LOG ||
iosizelog < XFS_MIN_IO_LOG) {
xfs_warn(mp, "invalid log iosize: %d [not %d-%d]",
iosizelog, XFS_MIN_IO_LOG,
XFS_MAX_IO_LOG);
return -EINVAL;
}
mp->m_flags |= XFS_MOUNT_DFLT_IOSIZE;
mp->m_readio_log = iosizelog;
mp->m_writeio_log = iosizelog;
}
return 0;
}
/*
* This function fills in xfs_mount_t fields based on mount args.
* Note: the superblock has _not_ yet been read in.
*
* Note that this function leaks the various device name allocations on
* failure. The caller takes care of them.
*
* *sb is const because this is also used to test options on the remount
* path, and we don't want this to have any side effects at remount time.
* Today this function does not change *sb, but just to future-proof...
*/
STATIC int
xfs_parseargs(
struct xfs_mount *mp,
char *options)
{
const struct super_block *sb = mp->m_super;
char *p;
substring_t args[MAX_OPT_ARGS];
int dsunit = 0;
int dswidth = 0;
int iosize = 0;
__uint8_t iosizelog = 0;
/*
* set up the mount name first so all the errors will refer to the
* correct device.
*/
mp->m_fsname = kstrndup(sb->s_id, MAXNAMELEN, GFP_KERNEL);
if (!mp->m_fsname)
return -ENOMEM;
mp->m_fsname_len = strlen(mp->m_fsname) + 1;
/*
* Copy binary VFS mount flags we are interested in.
*/
if (sb->s_flags & MS_RDONLY)
mp->m_flags |= XFS_MOUNT_RDONLY;
if (sb->s_flags & MS_DIRSYNC)
mp->m_flags |= XFS_MOUNT_DIRSYNC;
if (sb->s_flags & MS_SYNCHRONOUS)
mp->m_flags |= XFS_MOUNT_WSYNC;
/*
* Set some default flags that could be cleared by the mount option
* parsing.
*/
mp->m_flags |= XFS_MOUNT_BARRIER;
mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
/*
* These can be overridden by the mount option parsing.
*/
mp->m_logbufs = -1;
mp->m_logbsize = -1;
if (!options)
goto done;
while ((p = strsep(&options, ",")) != NULL) {
int token;
if (!*p)
continue;
token = match_token(p, tokens, args);
switch (token) {
case Opt_logbufs:
if (match_int(args, &mp->m_logbufs))
return -EINVAL;
break;
case Opt_logbsize:
if (suffix_kstrtoint(args, 10, &mp->m_logbsize))
return -EINVAL;
break;
case Opt_logdev:
mp->m_logname = match_strdup(args);
if (!mp->m_logname)
return -ENOMEM;
break;
case Opt_mtpt:
xfs_warn(mp, "%s option not allowed on this system", p);
return -EINVAL;
case Opt_rtdev:
mp->m_rtname = match_strdup(args);
if (!mp->m_rtname)
return -ENOMEM;
break;
case Opt_allocsize:
case Opt_biosize:
if (suffix_kstrtoint(args, 10, &iosize))
return -EINVAL;
iosizelog = ffs(iosize) - 1;
break;
case Opt_grpid:
case Opt_bsdgroups:
mp->m_flags |= XFS_MOUNT_GRPID;
break;
case Opt_nogrpid:
case Opt_sysvgroups:
mp->m_flags &= ~XFS_MOUNT_GRPID;
break;
case Opt_wsync:
mp->m_flags |= XFS_MOUNT_WSYNC;
break;
case Opt_norecovery:
mp->m_flags |= XFS_MOUNT_NORECOVERY;
break;
case Opt_noalign:
mp->m_flags |= XFS_MOUNT_NOALIGN;
break;
case Opt_swalloc:
mp->m_flags |= XFS_MOUNT_SWALLOC;
break;
case Opt_sunit:
if (match_int(args, &dsunit))
return -EINVAL;
break;
case Opt_swidth:
if (match_int(args, &dswidth))
return -EINVAL;
break;
case Opt_inode32:
mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
break;
case Opt_inode64:
mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
break;
case Opt_nouuid:
mp->m_flags |= XFS_MOUNT_NOUUID;
break;
case Opt_barrier:
mp->m_flags |= XFS_MOUNT_BARRIER;
break;
case Opt_nobarrier:
mp->m_flags &= ~XFS_MOUNT_BARRIER;
break;
case Opt_ikeep:
mp->m_flags |= XFS_MOUNT_IKEEP;
break;
case Opt_noikeep:
mp->m_flags &= ~XFS_MOUNT_IKEEP;
break;
case Opt_largeio:
mp->m_flags &= ~XFS_MOUNT_COMPAT_IOSIZE;
break;
case Opt_nolargeio:
mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
break;
case Opt_attr2:
mp->m_flags |= XFS_MOUNT_ATTR2;
break;
case Opt_noattr2:
mp->m_flags &= ~XFS_MOUNT_ATTR2;
mp->m_flags |= XFS_MOUNT_NOATTR2;
break;
case Opt_filestreams:
mp->m_flags |= XFS_MOUNT_FILESTREAMS;
break;
case Opt_noquota:
mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
break;
case Opt_quota:
case Opt_uquota:
case Opt_usrquota:
mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
XFS_UQUOTA_ENFD);
break;
case Opt_qnoenforce:
case Opt_uqnoenforce:
mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_UQUOTA_ENFD;
break;
case Opt_pquota:
case Opt_prjquota:
mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
XFS_PQUOTA_ENFD);
break;
case Opt_pqnoenforce:
mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_PQUOTA_ENFD;
break;
case Opt_gquota:
case Opt_grpquota:
mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
XFS_GQUOTA_ENFD);
break;
case Opt_gqnoenforce:
mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_GQUOTA_ENFD;
break;
case Opt_discard:
mp->m_flags |= XFS_MOUNT_DISCARD;
break;
case Opt_nodiscard:
mp->m_flags &= ~XFS_MOUNT_DISCARD;
break;
#ifdef CONFIG_FS_DAX
case Opt_dax:
mp->m_flags |= XFS_MOUNT_DAX;
break;
#endif
default:
xfs_warn(mp, "unknown mount option [%s].", p);
return -EINVAL;
}
}
/*
* no recovery flag requires a read-only mount
*/
if ((mp->m_flags & XFS_MOUNT_NORECOVERY) &&
!(mp->m_flags & XFS_MOUNT_RDONLY)) {
xfs_warn(mp, "no-recovery mounts must be read-only.");
return -EINVAL;
}
if ((mp->m_flags & XFS_MOUNT_NOALIGN) && (dsunit || dswidth)) {
xfs_warn(mp,
"sunit and swidth options incompatible with the noalign option");
return -EINVAL;
}
#ifndef CONFIG_XFS_QUOTA
if (XFS_IS_QUOTA_RUNNING(mp)) {
xfs_warn(mp, "quota support not available in this kernel.");
return -EINVAL;
}
#endif
if ((dsunit && !dswidth) || (!dsunit && dswidth)) {
xfs_warn(mp, "sunit and swidth must be specified together");
return -EINVAL;
}
if (dsunit && (dswidth % dsunit != 0)) {
xfs_warn(mp,
"stripe width (%d) must be a multiple of the stripe unit (%d)",
dswidth, dsunit);
return -EINVAL;
}
done:
if (dsunit && !(mp->m_flags & XFS_MOUNT_NOALIGN)) {
/*
* At this point the superblock has not been read
* in, therefore we do not know the block size.
* Before the mount call ends we will convert
* these to FSBs.
*/
mp->m_dalign = dsunit;
mp->m_swidth = dswidth;
}
if (mp->m_logbufs != -1 &&
mp->m_logbufs != 0 &&
(mp->m_logbufs < XLOG_MIN_ICLOGS ||
mp->m_logbufs > XLOG_MAX_ICLOGS)) {
xfs_warn(mp, "invalid logbufs value: %d [not %d-%d]",
mp->m_logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS);
return -EINVAL;
}
if (mp->m_logbsize != -1 &&
mp->m_logbsize != 0 &&
(mp->m_logbsize < XLOG_MIN_RECORD_BSIZE ||
mp->m_logbsize > XLOG_MAX_RECORD_BSIZE ||
!is_power_of_2(mp->m_logbsize))) {
xfs_warn(mp,
"invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]",
mp->m_logbsize);
return -EINVAL;
}
if (iosizelog) {
if (iosizelog > XFS_MAX_IO_LOG ||
iosizelog < XFS_MIN_IO_LOG) {
xfs_warn(mp, "invalid log iosize: %d [not %d-%d]",
iosizelog, XFS_MIN_IO_LOG,
XFS_MAX_IO_LOG);
return -EINVAL;
}
mp->m_flags |= XFS_MOUNT_DFLT_IOSIZE;
mp->m_readio_log = iosizelog;
mp->m_writeio_log = iosizelog;
}
return 0;
}
