/*
* In addition to i_rwsem in the VFS inode, the xfs inode contains 2
- * multi-reader locks: i_mmap_lock and the i_lock. This routine allows
+ * multi-reader locks: invalidate_lock and the i_lock. This routine allows
* various combinations of the locks to be obtained.
*
* The 3 locks should always be ordered so that the IO lock is obtained first,
*
* Basic locking order:
*
- * i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
+ * i_rwsem -> invalidate_lock -> page_lock -> i_ilock
*
* mmap_lock locking order:
*
* i_rwsem -> page lock -> mmap_lock
- * mmap_lock -> i_mmap_lock -> page_lock
+ * mmap_lock -> invalidate_lock -> page_lock
*
* The difference in mmap_lock locking order mean that we cannot hold the
- * i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can
- * fault in pages during copy in/out (for buffered IO) or require the mmap_lock
- * in get_user_pages() to map the user pages into the kernel address space for
- * direct IO. Similarly the i_rwsem cannot be taken inside a page fault because
- * page faults already hold the mmap_lock.
+ * invalidate_lock over syscall based read(2)/write(2) based IO. These IO paths
+ * can fault in pages during copy in/out (for buffered IO) or require the
+ * mmap_lock in get_user_pages() to map the user pages into the kernel address
+ * space for direct IO. Similarly the i_rwsem cannot be taken inside a page
+ * fault because page faults already hold the mmap_lock.
*
* Hence to serialise fully against both syscall and mmap based IO, we need to
- * take both the i_rwsem and the i_mmap_lock. These locks should *only* be both
- * taken in places where we need to invalidate the page cache in a race
+ * take both the i_rwsem and the invalidate_lock. These locks should *only* be
+ * both taken in places where we need to invalidate the page cache in a race
* free manner (e.g. truncate, hole punch and other extent manipulation
* functions).
*/
XFS_IOLOCK_DEP(lock_flags));
}
- if (lock_flags & XFS_MMAPLOCK_EXCL)
- mrupdate_nested(&ip->i_mmaplock, XFS_MMAPLOCK_DEP(lock_flags));
- else if (lock_flags & XFS_MMAPLOCK_SHARED)
- mraccess_nested(&ip->i_mmaplock, XFS_MMAPLOCK_DEP(lock_flags));
+ if (lock_flags & XFS_MMAPLOCK_EXCL) {
+ down_write_nested(&VFS_I(ip)->i_mapping->invalidate_lock,
+ XFS_MMAPLOCK_DEP(lock_flags));
+ } else if (lock_flags & XFS_MMAPLOCK_SHARED) {
+ down_read_nested(&VFS_I(ip)->i_mapping->invalidate_lock,
+ XFS_MMAPLOCK_DEP(lock_flags));
+ }
if (lock_flags & XFS_ILOCK_EXCL)
mrupdate_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));
}
if (lock_flags & XFS_MMAPLOCK_EXCL) {
- if (!mrtryupdate(&ip->i_mmaplock))
+ if (!down_write_trylock(&VFS_I(ip)->i_mapping->invalidate_lock))
goto out_undo_iolock;
} else if (lock_flags & XFS_MMAPLOCK_SHARED) {
- if (!mrtryaccess(&ip->i_mmaplock))
+ if (!down_read_trylock(&VFS_I(ip)->i_mapping->invalidate_lock))
goto out_undo_iolock;
}
out_undo_mmaplock:
if (lock_flags & XFS_MMAPLOCK_EXCL)
- mrunlock_excl(&ip->i_mmaplock);
+ up_write(&VFS_I(ip)->i_mapping->invalidate_lock);
else if (lock_flags & XFS_MMAPLOCK_SHARED)
- mrunlock_shared(&ip->i_mmaplock);
+ up_read(&VFS_I(ip)->i_mapping->invalidate_lock);
out_undo_iolock:
if (lock_flags & XFS_IOLOCK_EXCL)
up_write(&VFS_I(ip)->i_rwsem);
up_read(&VFS_I(ip)->i_rwsem);
if (lock_flags & XFS_MMAPLOCK_EXCL)
- mrunlock_excl(&ip->i_mmaplock);
+ up_write(&VFS_I(ip)->i_mapping->invalidate_lock);
else if (lock_flags & XFS_MMAPLOCK_SHARED)
- mrunlock_shared(&ip->i_mmaplock);
+ up_read(&VFS_I(ip)->i_mapping->invalidate_lock);
if (lock_flags & XFS_ILOCK_EXCL)
mrunlock_excl(&ip->i_lock);
if (lock_flags & XFS_ILOCK_EXCL)
mrdemote(&ip->i_lock);
if (lock_flags & XFS_MMAPLOCK_EXCL)
- mrdemote(&ip->i_mmaplock);
+ downgrade_write(&VFS_I(ip)->i_mapping->invalidate_lock);
if (lock_flags & XFS_IOLOCK_EXCL)
downgrade_write(&VFS_I(ip)->i_rwsem);
}
#if defined(DEBUG) || defined(XFS_WARN)
-int
+static inline bool
+__xfs_rwsem_islocked(
+ struct rw_semaphore *rwsem,
+ bool shared)
+{
+ if (!debug_locks)
+ return rwsem_is_locked(rwsem);
+
+ if (!shared)
+ return lockdep_is_held_type(rwsem, 0);
+
+ /*
+ * We are checking that the lock is held at least in shared
+ * mode but don't care that it might be held exclusively
+ * (i.e. shared | excl). Hence we check if the lock is held
+ * in any mode rather than an explicit shared mode.
+ */
+ return lockdep_is_held_type(rwsem, -1);
+}
+
+bool
xfs_isilocked(
- xfs_inode_t *ip,
+ struct xfs_inode *ip,
uint lock_flags)
{
if (lock_flags & (XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)) {
}
if (lock_flags & (XFS_MMAPLOCK_EXCL|XFS_MMAPLOCK_SHARED)) {
- if (!(lock_flags & XFS_MMAPLOCK_SHARED))
- return !!ip->i_mmaplock.mr_writer;
- return rwsem_is_locked(&ip->i_mmaplock.mr_lock);
+ return __xfs_rwsem_islocked(&VFS_I(ip)->i_rwsem,
+ (lock_flags & XFS_IOLOCK_SHARED));
}
- if (lock_flags & (XFS_IOLOCK_EXCL|XFS_IOLOCK_SHARED)) {
- if (!(lock_flags & XFS_IOLOCK_SHARED))
- return !debug_locks ||
- lockdep_is_held_type(&VFS_I(ip)->i_rwsem, 0);
- return rwsem_is_locked(&VFS_I(ip)->i_rwsem);
+ if (lock_flags & (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED)) {
+ return __xfs_rwsem_islocked(&VFS_I(ip)->i_rwsem,
+ (lock_flags & XFS_IOLOCK_SHARED));
}
ASSERT(0);
- return 0;
+ return false;
}
#endif
}
/*
- * xfs_lock_two_inodes() can only be used to lock one type of lock at a time -
- * the mmaplock or the ilock, but not more than one type at a time. If we lock
- * more than one at a time, lockdep will report false positives saying we have
- * violated locking orders. The iolock must be double-locked separately since
- * we use i_rwsem for that. We now support taking one lock EXCL and the other
- * SHARED.
+ * xfs_lock_two_inodes() can only be used to lock ilock. The iolock and
+ * mmaplock must be double-locked separately since we use i_rwsem and
+ * invalidate_lock for that. We now support taking one lock EXCL and the
+ * other SHARED.
*/
void
xfs_lock_two_inodes(
ASSERT(hweight32(ip1_mode) == 1);
ASSERT(!(ip0_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)));
ASSERT(!(ip1_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)));
- ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
- !(ip0_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
- ASSERT(!(ip1_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
- !(ip1_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
- ASSERT(!(ip1_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
- !(ip0_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
- ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
- !(ip1_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
-
+ ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)));
+ ASSERT(!(ip1_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)));
ASSERT(ip0->i_ino != ip1->i_ino);
if (ip0->i_ino > ip1->i_ino) {
trace_xfs_lookup(dp, name);
- if (XFS_FORCED_SHUTDOWN(dp->i_mount))
+ if (xfs_is_shutdown(dp->i_mount))
return -EIO;
error = xfs_dir_lookup(NULL, dp, name, &inum, ci_name);
di_flags |= XFS_DIFLAG_PROJINHERIT;
} else if (S_ISREG(mode)) {
if ((pip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
- xfs_sb_version_hasrealtime(&ip->i_mount->m_sb))
+ xfs_has_realtime(ip->i_mount))
di_flags |= XFS_DIFLAG_REALTIME;
if (pip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) {
di_flags |= XFS_DIFLAG_EXTSIZE;
inode->i_rdev = rdev;
ip->i_projid = prid;
- if (dir && !(dir->i_mode & S_ISGID) &&
- (mp->m_flags & XFS_MOUNT_GRPID)) {
+ if (dir && !(dir->i_mode & S_ISGID) && xfs_has_grpid(mp)) {
inode_fsuid_set(inode, mnt_userns);
inode->i_gid = dir->i_gid;
inode->i_mode = mode;
ip->i_extsize = 0;
ip->i_diflags = 0;
- if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
+ if (xfs_has_v3inodes(mp)) {
inode_set_iversion(inode, 1);
ip->i_cowextsize = 0;
ip->i_crtime = tv;
* this saves us from needing to run a separate transaction to set the
* fork offset in the immediate future.
*/
- if (init_xattrs && xfs_sb_version_hasattr(&mp->m_sb)) {
+ if (init_xattrs && xfs_has_attr(mp)) {
ip->i_forkoff = xfs_default_attroffset(ip) >> 3;
ip->i_afp = xfs_ifork_alloc(XFS_DINODE_FMT_EXTENTS, 0);
}
trace_xfs_create(dp, name);
- if (XFS_FORCED_SHUTDOWN(mp))
+ if (xfs_is_shutdown(mp))
return -EIO;
prid = xfs_get_initial_prid(dp);
* create transaction goes to disk before returning to
* the user.
*/
- if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
+ if (xfs_has_wsync(mp) || xfs_has_dirsync(mp))
xfs_trans_set_sync(tp);
/*
uint resblks;
xfs_ino_t ino;
- if (XFS_FORCED_SHUTDOWN(mp))
+ if (xfs_is_shutdown(mp))
return -EIO;
prid = xfs_get_initial_prid(dp);
if (error)
goto out_trans_cancel;
- if (mp->m_flags & XFS_MOUNT_WSYNC)
+ if (xfs_has_wsync(mp))
xfs_trans_set_sync(tp);
/*
ASSERT(!S_ISDIR(VFS_I(sip)->i_mode));
- if (XFS_FORCED_SHUTDOWN(mp))
+ if (xfs_is_shutdown(mp))
return -EIO;
error = xfs_qm_dqattach(sip);
* link transaction goes to disk before returning to
* the user.
*/
- if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
+ if (xfs_has_wsync(mp) || xfs_has_dirsync(mp))
xfs_trans_set_sync(tp);
return xfs_trans_commit(tp);
return 0;
/* If this is a read-only mount, don't do this (would generate I/O) */
- if (mp->m_flags & XFS_MOUNT_RDONLY)
+ if (xfs_is_readonly(mp))
return 0;
- if (!XFS_FORCED_SHUTDOWN(mp)) {
+ if (!xfs_is_shutdown(mp)) {
int truncated;
/*
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
if (error) {
- ASSERT(XFS_FORCED_SHUTDOWN(mp));
+ ASSERT(xfs_is_shutdown(mp));
return error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
"Failed to remove inode(s) from unlinked list. "
"Please free space, unmount and run xfs_repair.");
} else {
- ASSERT(XFS_FORCED_SHUTDOWN(mp));
+ ASSERT(xfs_is_shutdown(mp));
}
return error;
}
* might do that, we need to make sure. Otherwise the
* inode might be lost for a long time or forever.
*/
- if (!XFS_FORCED_SHUTDOWN(mp)) {
+ if (!xfs_is_shutdown(mp)) {
xfs_notice(mp, "%s: xfs_ifree returned error %d",
__func__, error);
xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
return 0;
}
+ /*
+ * Returns true if we need to update the on-disk metadata before we can free
+ * the memory used by this inode. Updates include freeing post-eof
+ * preallocations; freeing COW staging extents; and marking the inode free in
+ * the inobt if it is on the unlinked list.
+ */
+ bool
+ xfs_inode_needs_inactive(
+ struct xfs_inode *ip)
+ {
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_ifork *cow_ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+
+ /*
+ * If the inode is already free, then there can be nothing
+ * to clean up here.
+ */
+ if (VFS_I(ip)->i_mode == 0)
+ return false;
+
+ /* If this is a read-only mount, don't do this (would generate I/O) */
+ if (xfs_is_readonly(mp))
+ return false;
+
+ /* If the log isn't running, push inodes straight to reclaim. */
+ if (xfs_is_shutdown(mp) || xfs_has_norecovery(mp))
+ return false;
+
+ /* Metadata inodes require explicit resource cleanup. */
+ if (xfs_is_metadata_inode(ip))
+ return false;
+
+ /* Want to clean out the cow blocks if there are any. */
+ if (cow_ifp && cow_ifp->if_bytes > 0)
+ return true;
+
+ /* Unlinked files must be freed. */
+ if (VFS_I(ip)->i_nlink == 0)
+ return true;
+
+ /*
+ * This file isn't being freed, so check if there are post-eof blocks
+ * to free. @force is true because we are evicting an inode from the
+ * cache. Post-eof blocks must be freed, lest we end up with broken
+ * free space accounting.
+ *
+ * Note: don't bother with iolock here since lockdep complains about
+ * acquiring it in reclaim context. We have the only reference to the
+ * inode at this point anyways.
+ */
+ return xfs_can_free_eofblocks(ip, true);
+ }
+
/*
* xfs_inactive
*
ASSERT(!xfs_iflags_test(ip, XFS_IRECOVERY));
/* If this is a read-only mount, don't do this (would generate I/O) */
- if (mp->m_flags & XFS_MOUNT_RDONLY)
+ if (xfs_is_readonly(mp))
goto out;
/* Metadata inodes require explicit resource cleanup. */
rhashtable_free_and_destroy(&pag->pagi_unlinked_hash,
xfs_iunlink_free_item, &freed_anything);
- ASSERT(freed_anything == false || XFS_FORCED_SHUTDOWN(pag->pag_mount));
+ ASSERT(freed_anything == false || xfs_is_shutdown(pag->pag_mount));
}
/*
trace_xfs_remove(dp, name);
- if (XFS_FORCED_SHUTDOWN(mp))
+ if (xfs_is_shutdown(mp))
return -EIO;
error = xfs_qm_dqattach(dp);
* remove transaction goes to disk before returning to
* the user.
*/
- if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
+ if (xfs_has_wsync(mp) || xfs_has_dirsync(mp))
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp);
* If this is a synchronous mount, make sure that the rename transaction
* goes to disk before returning to the user.
*/
- if (tp->t_mountp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
+ if (xfs_has_wsync(tp->t_mountp) || xfs_has_dirsync(tp->t_mountp))
xfs_trans_set_sync(tp);
return xfs_trans_commit(tp);
* happen but we need to still do it to ensure backwards compatibility
* with old kernels that predate logging all inode changes.
*/
- if (!xfs_sb_version_has_v3inode(&mp->m_sb))
+ if (!xfs_has_v3inodes(mp))
ip->i_flushiter++;
/*
xfs_inode_to_disk(ip, dip, iip->ili_item.li_lsn);
/* Wrap, we never let the log put out DI_MAX_FLUSH */
- if (!xfs_sb_version_has_v3inode(&mp->m_sb)) {
+ if (!xfs_has_v3inodes(mp)) {
if (ip->i_flushiter == DI_MAX_FLUSH)
ip->i_flushiter = 0;
}
* AIL, leaving a dirty/unpinned inode attached to the buffer
* that otherwise looks like it should be flushed.
*/
- if (XFS_FORCED_SHUTDOWN(mp)) {
+ if (xfs_is_shutdown(mp)) {
xfs_iunpin_wait(ip);
xfs_iflush_abort(ip);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
ret = xfs_iolock_two_inodes_and_break_layout(VFS_I(ip1), VFS_I(ip2));
if (ret)
return ret;
- if (ip1 == ip2)
- xfs_ilock(ip1, XFS_MMAPLOCK_EXCL);
- else
- xfs_lock_two_inodes(ip1, XFS_MMAPLOCK_EXCL,
- ip2, XFS_MMAPLOCK_EXCL);
+ filemap_invalidate_lock_two(VFS_I(ip1)->i_mapping,
+ VFS_I(ip2)->i_mapping);
return 0;
}
struct xfs_inode *ip1,
struct xfs_inode *ip2)
{
- bool same_inode = (ip1 == ip2);
-
- xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL);
- if (!same_inode)
- xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
+ filemap_invalidate_unlock_two(VFS_I(ip1)->i_mapping,
+ VFS_I(ip2)->i_mapping);
inode_unlock(VFS_I(ip2));
- if (!same_inode)
+ if (ip1 != ip2)
inode_unlock(VFS_I(ip1));
}
static struct xfs_kobj xfs_dbg_kobj; /* global debug sysfs attrs */
#endif
+ #ifdef CONFIG_HOTPLUG_CPU
+ static LIST_HEAD(xfs_mount_list);
+ static DEFINE_SPINLOCK(xfs_mount_list_lock);
+
+ static inline void xfs_mount_list_add(struct xfs_mount *mp)
+ {
+ spin_lock(&xfs_mount_list_lock);
+ list_add(&mp->m_mount_list, &xfs_mount_list);
+ spin_unlock(&xfs_mount_list_lock);
+ }
+
+ static inline void xfs_mount_list_del(struct xfs_mount *mp)
+ {
+ spin_lock(&xfs_mount_list_lock);
+ list_del(&mp->m_mount_list);
+ spin_unlock(&xfs_mount_list_lock);
+ }
+ #else /* !CONFIG_HOTPLUG_CPU */
+ static inline void xfs_mount_list_add(struct xfs_mount *mp) {}
+ static inline void xfs_mount_list_del(struct xfs_mount *mp) {}
+ #endif
+
enum xfs_dax_mode {
XFS_DAX_INODE = 0,
XFS_DAX_ALWAYS = 1,
{
switch (mode) {
case XFS_DAX_INODE:
- mp->m_flags &= ~(XFS_MOUNT_DAX_ALWAYS | XFS_MOUNT_DAX_NEVER);
+ mp->m_features &= ~(XFS_FEAT_DAX_ALWAYS | XFS_FEAT_DAX_NEVER);
break;
case XFS_DAX_ALWAYS:
- mp->m_flags |= XFS_MOUNT_DAX_ALWAYS;
- mp->m_flags &= ~XFS_MOUNT_DAX_NEVER;
+ mp->m_features |= XFS_FEAT_DAX_ALWAYS;
+ mp->m_features &= ~XFS_FEAT_DAX_NEVER;
break;
case XFS_DAX_NEVER:
- mp->m_flags |= XFS_MOUNT_DAX_NEVER;
- mp->m_flags &= ~XFS_MOUNT_DAX_ALWAYS;
+ mp->m_features |= XFS_FEAT_DAX_NEVER;
+ mp->m_features &= ~XFS_FEAT_DAX_ALWAYS;
break;
}
}
{
static struct proc_xfs_info xfs_info_set[] = {
/* the few simple ones we can get from the mount struct */
- { XFS_MOUNT_IKEEP, ",ikeep" },
- { XFS_MOUNT_WSYNC, ",wsync" },
- { XFS_MOUNT_NOALIGN, ",noalign" },
- { XFS_MOUNT_SWALLOC, ",swalloc" },
- { XFS_MOUNT_NOUUID, ",nouuid" },
- { XFS_MOUNT_NORECOVERY, ",norecovery" },
- { XFS_MOUNT_ATTR2, ",attr2" },
- { XFS_MOUNT_FILESTREAMS, ",filestreams" },
- { XFS_MOUNT_GRPID, ",grpid" },
- { XFS_MOUNT_DISCARD, ",discard" },
- { XFS_MOUNT_LARGEIO, ",largeio" },
- { XFS_MOUNT_DAX_ALWAYS, ",dax=always" },
- { XFS_MOUNT_DAX_NEVER, ",dax=never" },
+ { XFS_FEAT_IKEEP, ",ikeep" },
+ { XFS_FEAT_WSYNC, ",wsync" },
+ { XFS_FEAT_NOALIGN, ",noalign" },
+ { XFS_FEAT_SWALLOC, ",swalloc" },
+ { XFS_FEAT_NOUUID, ",nouuid" },
+ { XFS_FEAT_NORECOVERY, ",norecovery" },
+ { XFS_FEAT_ATTR2, ",attr2" },
+ { XFS_FEAT_FILESTREAMS, ",filestreams" },
+ { XFS_FEAT_GRPID, ",grpid" },
+ { XFS_FEAT_DISCARD, ",discard" },
+ { XFS_FEAT_LARGE_IOSIZE, ",largeio" },
+ { XFS_FEAT_DAX_ALWAYS, ",dax=always" },
+ { XFS_FEAT_DAX_NEVER, ",dax=never" },
{ 0, NULL }
};
struct xfs_mount *mp = XFS_M(root->d_sb);
struct proc_xfs_info *xfs_infop;
for (xfs_infop = xfs_info_set; xfs_infop->flag; xfs_infop++) {
- if (mp->m_flags & xfs_infop->flag)
+ if (mp->m_features & xfs_infop->flag)
seq_puts(m, xfs_infop->str);
}
- seq_printf(m, ",inode%d",
- (mp->m_flags & XFS_MOUNT_SMALL_INUMS) ? 32 : 64);
+ seq_printf(m, ",inode%d", xfs_has_small_inums(mp) ? 32 : 64);
- if (mp->m_flags & XFS_MOUNT_ALLOCSIZE)
+ if (xfs_has_allocsize(mp))
seq_printf(m, ",allocsize=%dk",
(1 << mp->m_allocsize_log) >> 10);
seq_printf(m, ",swidth=%d",
(int)XFS_FSB_TO_BB(mp, mp->m_swidth));
- if (mp->m_qflags & XFS_UQUOTA_ACCT) {
- if (mp->m_qflags & XFS_UQUOTA_ENFD)
- seq_puts(m, ",usrquota");
- else
- seq_puts(m, ",uqnoenforce");
- }
+ if (mp->m_qflags & XFS_UQUOTA_ENFD)
+ seq_puts(m, ",usrquota");
+ else if (mp->m_qflags & XFS_UQUOTA_ACCT)
+ seq_puts(m, ",uqnoenforce");
- if (mp->m_qflags & XFS_PQUOTA_ACCT) {
- if (mp->m_qflags & XFS_PQUOTA_ENFD)
- seq_puts(m, ",prjquota");
- else
- seq_puts(m, ",pqnoenforce");
- }
- if (mp->m_qflags & XFS_GQUOTA_ACCT) {
- if (mp->m_qflags & XFS_GQUOTA_ENFD)
- seq_puts(m, ",grpquota");
- else
- seq_puts(m, ",gqnoenforce");
- }
+ if (mp->m_qflags & XFS_PQUOTA_ENFD)
+ seq_puts(m, ",prjquota");
+ else if (mp->m_qflags & XFS_PQUOTA_ACCT)
+ seq_puts(m, ",pqnoenforce");
+
+ if (mp->m_qflags & XFS_GQUOTA_ENFD)
+ seq_puts(m, ",grpquota");
+ else if (mp->m_qflags & XFS_GQUOTA_ACCT)
+ seq_puts(m, ",gqnoenforce");
if (!(mp->m_qflags & XFS_ALL_QUOTA_ACCT))
seq_puts(m, ",noquota");
/*
* Set parameters for inode allocation heuristics, taking into account
* filesystem size and inode32/inode64 mount options; i.e. specifically
- * whether or not XFS_MOUNT_SMALL_INUMS is set.
+ * whether or not XFS_FEAT_SMALL_INUMS is set.
*
* Inode allocation patterns are altered only if inode32 is requested
- * (XFS_MOUNT_SMALL_INUMS), and the filesystem is sufficiently large.
- * If altered, XFS_MOUNT_32BITINODES is set as well.
+ * (XFS_FEAT_SMALL_INUMS), and the filesystem is sufficiently large.
+ * If altered, XFS_OPSTATE_INODE32 is set as well.
*
* An agcount independent of that in the mount structure is provided
* because in the growfs case, mp->m_sb.sb_agcount is not yet updated
/*
* If user asked for no more than 32-bit inodes, and the fs is
- * sufficiently large, set XFS_MOUNT_32BITINODES if we must alter
+ * sufficiently large, set XFS_OPSTATE_INODE32 if we must alter
* the allocator to accommodate the request.
*/
- if ((mp->m_flags & XFS_MOUNT_SMALL_INUMS) && ino > XFS_MAXINUMBER_32)
- mp->m_flags |= XFS_MOUNT_32BITINODES;
+ if (xfs_has_small_inums(mp) && ino > XFS_MAXINUMBER_32)
+ set_bit(XFS_OPSTATE_INODE32, &mp->m_opstate);
else
- mp->m_flags &= ~XFS_MOUNT_32BITINODES;
+ clear_bit(XFS_OPSTATE_INODE32, &mp->m_opstate);
for (index = 0; index < agcount; index++) {
struct xfs_perag *pag;
pag = xfs_perag_get(mp, index);
- if (mp->m_flags & XFS_MOUNT_32BITINODES) {
+ if (xfs_is_inode32(mp)) {
if (ino > XFS_MAXINUMBER_32) {
pag->pagi_inodeok = 0;
pag->pagf_metadata = 0;
xfs_perag_put(pag);
}
- return (mp->m_flags & XFS_MOUNT_32BITINODES) ? maxagi : agcount;
+ return xfs_is_inode32(mp) ? maxagi : agcount;
}
STATIC int
if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
unsigned int log_sector_size = BBSIZE;
- if (xfs_sb_version_hassector(&mp->m_sb))
+ if (xfs_has_sector(mp))
log_sector_size = mp->m_sb.sb_logsectsize;
error = xfs_setsize_buftarg(mp->m_logdev_targp,
log_sector_size);
if (!mp->m_unwritten_workqueue)
goto out_destroy_buf;
- mp->m_cil_workqueue = alloc_workqueue("xfs-cil/%s",
- XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_UNBOUND),
- 0, mp->m_super->s_id);
- if (!mp->m_cil_workqueue)
- goto out_destroy_unwritten;
-
mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s",
XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM),
0, mp->m_super->s_id);
if (!mp->m_reclaim_workqueue)
- goto out_destroy_cil;
+ goto out_destroy_unwritten;
- mp->m_gc_workqueue = alloc_workqueue("xfs-gc/%s",
- WQ_SYSFS | WQ_UNBOUND | WQ_FREEZABLE | WQ_MEM_RECLAIM,
+ mp->m_blockgc_wq = alloc_workqueue("xfs-blockgc/%s",
+ XFS_WQFLAGS(WQ_UNBOUND | WQ_FREEZABLE | WQ_MEM_RECLAIM),
0, mp->m_super->s_id);
- if (!mp->m_gc_workqueue)
+ if (!mp->m_blockgc_wq)
goto out_destroy_reclaim;
+ mp->m_inodegc_wq = alloc_workqueue("xfs-inodegc/%s",
+ XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM),
+ 1, mp->m_super->s_id);
+ if (!mp->m_inodegc_wq)
+ goto out_destroy_blockgc;
+
mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s",
XFS_WQFLAGS(WQ_FREEZABLE), 0, mp->m_super->s_id);
if (!mp->m_sync_workqueue)
- goto out_destroy_eofb;
+ goto out_destroy_inodegc;
return 0;
- out_destroy_eofb:
- destroy_workqueue(mp->m_gc_workqueue);
+ out_destroy_inodegc:
+ destroy_workqueue(mp->m_inodegc_wq);
+ out_destroy_blockgc:
+ destroy_workqueue(mp->m_blockgc_wq);
out_destroy_reclaim:
destroy_workqueue(mp->m_reclaim_workqueue);
- out_destroy_cil:
- destroy_workqueue(mp->m_cil_workqueue);
out_destroy_unwritten:
destroy_workqueue(mp->m_unwritten_workqueue);
out_destroy_buf:
struct xfs_mount *mp)
{
destroy_workqueue(mp->m_sync_workqueue);
- destroy_workqueue(mp->m_gc_workqueue);
+ destroy_workqueue(mp->m_blockgc_wq);
+ destroy_workqueue(mp->m_inodegc_wq);
destroy_workqueue(mp->m_reclaim_workqueue);
- destroy_workqueue(mp->m_cil_workqueue);
destroy_workqueue(mp->m_unwritten_workqueue);
destroy_workqueue(mp->m_buf_workqueue);
}
return NULL;
}
- #ifdef DEBUG
- static void
- xfs_check_delalloc(
- struct xfs_inode *ip,
- int whichfork)
- {
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
- struct xfs_bmbt_irec got;
- struct xfs_iext_cursor icur;
-
- if (!ifp || !xfs_iext_lookup_extent(ip, ifp, 0, &icur, &got))
- return;
- do {
- if (isnullstartblock(got.br_startblock)) {
- xfs_warn(ip->i_mount,
- "ino %llx %s fork has delalloc extent at [0x%llx:0x%llx]",
- ip->i_ino,
- whichfork == XFS_DATA_FORK ? "data" : "cow",
- got.br_startoff, got.br_blockcount);
- }
- } while (xfs_iext_next_extent(ifp, &icur, &got));
- }
- #else
- #define xfs_check_delalloc(ip, whichfork) do { } while (0)
- #endif
-
/*
* Now that the generic code is guaranteed not to be accessing
* the linux inode, we can inactivate and reclaim the inode.
ASSERT(!rwsem_is_locked(&inode->i_rwsem));
XFS_STATS_INC(ip->i_mount, vn_rele);
XFS_STATS_INC(ip->i_mount, vn_remove);
-
- xfs_inactive(ip);
-
- if (!XFS_FORCED_SHUTDOWN(ip->i_mount) && ip->i_delayed_blks) {
- xfs_check_delalloc(ip, XFS_DATA_FORK);
- xfs_check_delalloc(ip, XFS_COW_FORK);
- ASSERT(0);
- }
-
- XFS_STATS_INC(ip->i_mount, vn_reclaim);
-
- /*
- * We should never get here with one of the reclaim flags already set.
- */
- ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIMABLE));
- ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIM));
-
- /*
- * We always use background reclaim here because even if the inode is
- * clean, it still may be under IO and hence we have wait for IO
- * completion to occur before we can reclaim the inode. The background
- * reclaim path handles this more efficiently than we can here, so
- * simply let background reclaim tear down all inodes.
- */
xfs_inode_mark_reclaimable(ip);
}
atomic_set(&ip->i_pincount, 0);
spin_lock_init(&ip->i_flags_lock);
- mrlock_init(&ip->i_mmaplock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
- "xfsino", ip->i_ino);
mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
"xfsino", ip->i_ino);
}
* that. See the comment for this inode flag.
*/
if (ip->i_flags & XFS_IRECOVERY) {
- ASSERT(ip->i_mount->m_log->l_flags & XLOG_RECOVERY_NEEDED);
+ ASSERT(xlog_recovery_needed(ip->i_mount->m_log));
return 0;
}
{
struct xfs_mount *mp = XFS_M(sb);
+ trace_xfs_fs_sync_fs(mp, __return_address);
+
/*
* Doing anything during the async pass would be counterproductive.
*/
flush_delayed_work(&mp->m_log->l_work);
}
+ /*
+ * If we are called with page faults frozen out, it means we are about
+ * to freeze the transaction subsystem. Take the opportunity to shut
+ * down inodegc because once SB_FREEZE_FS is set it's too late to
+ * prevent inactivation races with freeze. The fs doesn't get called
+ * again by the freezing process until after SB_FREEZE_FS has been set,
+ * so it's now or never. Same logic applies to speculative allocation
+ * garbage collection.
+ *
+ * We don't care if this is a normal syncfs call that does this or
+ * freeze that does this - we can run this multiple times without issue
+ * and we won't race with a restart because a restart can only occur
+ * when the state is either SB_FREEZE_FS or SB_FREEZE_COMPLETE.
+ */
+ if (sb->s_writers.frozen == SB_FREEZE_PAGEFAULT) {
+ xfs_inodegc_stop(mp);
+ xfs_blockgc_stop(mp);
+ }
+
return 0;
}
xfs_extlen_t lsize;
int64_t ffree;
+ /* Wait for whatever inactivations are in progress. */
+ xfs_inodegc_flush(mp);
+
statp->f_type = XFS_SUPER_MAGIC;
statp->f_namelen = MAXNAMELEN - 1;
* set a GFP_NOFS context here to avoid recursion deadlocks.
*/
flags = memalloc_nofs_save();
- xfs_blockgc_stop(mp);
xfs_save_resvblks(mp);
ret = xfs_log_quiesce(mp);
memalloc_nofs_restore(flags);
+
+ /*
+ * For read-write filesystems, we need to restart the inodegc on error
+ * because we stopped it at SB_FREEZE_PAGEFAULT level and a thaw is not
+ * going to be run to restart it now. We are at SB_FREEZE_FS level
+ * here, so we can restart safely without racing with a stop in
+ * xfs_fs_sync_fs().
+ */
+ if (ret && !xfs_is_readonly(mp)) {
+ xfs_blockgc_start(mp);
+ xfs_inodegc_start(mp);
+ }
+
return ret;
}
xfs_restore_resvblks(mp);
xfs_log_work_queue(mp);
- xfs_blockgc_start(mp);
+
+ /*
+ * Don't reactivate the inodegc worker on a readonly filesystem because
+ * inodes are sent directly to reclaim. Don't reactivate the blockgc
+ * worker because there are no speculative preallocations on a readonly
+ * filesystem.
+ */
+ if (!xfs_is_readonly(mp)) {
+ xfs_blockgc_start(mp);
+ xfs_inodegc_start(mp);
+ }
+
return 0;
}
xfs_finish_flags(
struct xfs_mount *mp)
{
- int ronly = (mp->m_flags & XFS_MOUNT_RDONLY);
-
/* Fail a mount where the logbuf is smaller than the log stripe */
- if (xfs_sb_version_haslogv2(&mp->m_sb)) {
+ if (xfs_has_logv2(mp)) {
if (mp->m_logbsize <= 0 &&
mp->m_sb.sb_logsunit > XLOG_BIG_RECORD_BSIZE) {
mp->m_logbsize = mp->m_sb.sb_logsunit;
/*
* V5 filesystems always use attr2 format for attributes.
*/
- if (xfs_sb_version_hascrc(&mp->m_sb) &&
- (mp->m_flags & XFS_MOUNT_NOATTR2)) {
+ if (xfs_has_crc(mp) && xfs_has_noattr2(mp)) {
xfs_warn(mp, "Cannot mount a V5 filesystem as noattr2. "
"attr2 is always enabled for V5 filesystems.");
return -EINVAL;
}
- /*
- * mkfs'ed attr2 will turn on attr2 mount unless explicitly
- * told by noattr2 to turn it off
- */
- if (xfs_sb_version_hasattr2(&mp->m_sb) &&
- !(mp->m_flags & XFS_MOUNT_NOATTR2))
- mp->m_flags |= XFS_MOUNT_ATTR2;
-
/*
* prohibit r/w mounts of read-only filesystems
*/
- if ((mp->m_sb.sb_flags & XFS_SBF_READONLY) && !ronly) {
+ if ((mp->m_sb.sb_flags & XFS_SBF_READONLY) && !xfs_is_readonly(mp)) {
xfs_warn(mp,
"cannot mount a read-only filesystem as read-write");
return -EROFS;
}
- if ((mp->m_qflags & (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE)) &&
- (mp->m_qflags & (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE)) &&
- !xfs_sb_version_has_pquotino(&mp->m_sb)) {
+ if ((mp->m_qflags & XFS_GQUOTA_ACCT) &&
+ (mp->m_qflags & XFS_PQUOTA_ACCT) &&
+ !xfs_has_pquotino(mp)) {
xfs_warn(mp,
"Super block does not support project and group quota together");
return -EINVAL;
percpu_counter_destroy(&mp->m_icount);
percpu_counter_destroy(&mp->m_ifree);
percpu_counter_destroy(&mp->m_fdblocks);
- ASSERT(XFS_FORCED_SHUTDOWN(mp) ||
+ ASSERT(xfs_is_shutdown(mp) ||
percpu_counter_sum(&mp->m_delalloc_blks) == 0);
percpu_counter_destroy(&mp->m_delalloc_blks);
}
+ static int
+ xfs_inodegc_init_percpu(
+ struct xfs_mount *mp)
+ {
+ struct xfs_inodegc *gc;
+ int cpu;
+
+ mp->m_inodegc = alloc_percpu(struct xfs_inodegc);
+ if (!mp->m_inodegc)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu) {
+ gc = per_cpu_ptr(mp->m_inodegc, cpu);
+ init_llist_head(&gc->list);
+ gc->items = 0;
+ INIT_WORK(&gc->work, xfs_inodegc_worker);
+ }
+ return 0;
+ }
+
+ static void
+ xfs_inodegc_free_percpu(
+ struct xfs_mount *mp)
+ {
+ if (!mp->m_inodegc)
+ return;
+ free_percpu(mp->m_inodegc);
+ }
+
static void
xfs_fs_put_super(
struct super_block *sb)
xfs_freesb(mp);
free_percpu(mp->m_stats.xs_stats);
+ xfs_mount_list_del(mp);
+ xfs_inodegc_free_percpu(mp);
xfs_destroy_percpu_counters(mp);
xfs_destroy_mount_workqueues(mp);
xfs_close_devices(mp);
* already had the flag set
*/
if ((fc->purpose & FS_CONTEXT_FOR_RECONFIGURE) &&
- !!(XFS_M(fc->root->d_sb)->m_flags & flag) == value)
+ !!(XFS_M(fc->root->d_sb)->m_features & flag) == value)
return;
xfs_warn(fc->s_fs_info, "%s mount option is deprecated.", param->key);
}
if (suffix_kstrtoint(param->string, 10, &size))
return -EINVAL;
parsing_mp->m_allocsize_log = ffs(size) - 1;
- parsing_mp->m_flags |= XFS_MOUNT_ALLOCSIZE;
+ parsing_mp->m_features |= XFS_FEAT_ALLOCSIZE;
return 0;
case Opt_grpid:
case Opt_bsdgroups:
- parsing_mp->m_flags |= XFS_MOUNT_GRPID;
+ parsing_mp->m_features |= XFS_FEAT_GRPID;
return 0;
case Opt_nogrpid:
case Opt_sysvgroups:
- parsing_mp->m_flags &= ~XFS_MOUNT_GRPID;
+ parsing_mp->m_features &= ~XFS_FEAT_GRPID;
return 0;
case Opt_wsync:
- parsing_mp->m_flags |= XFS_MOUNT_WSYNC;
+ parsing_mp->m_features |= XFS_FEAT_WSYNC;
return 0;
case Opt_norecovery:
- parsing_mp->m_flags |= XFS_MOUNT_NORECOVERY;
+ parsing_mp->m_features |= XFS_FEAT_NORECOVERY;
return 0;
case Opt_noalign:
- parsing_mp->m_flags |= XFS_MOUNT_NOALIGN;
+ parsing_mp->m_features |= XFS_FEAT_NOALIGN;
return 0;
case Opt_swalloc:
- parsing_mp->m_flags |= XFS_MOUNT_SWALLOC;
+ parsing_mp->m_features |= XFS_FEAT_SWALLOC;
return 0;
case Opt_sunit:
parsing_mp->m_dalign = result.uint_32;
parsing_mp->m_swidth = result.uint_32;
return 0;
case Opt_inode32:
- parsing_mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
+ parsing_mp->m_features |= XFS_FEAT_SMALL_INUMS;
return 0;
case Opt_inode64:
- parsing_mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
+ parsing_mp->m_features &= ~XFS_FEAT_SMALL_INUMS;
return 0;
case Opt_nouuid:
- parsing_mp->m_flags |= XFS_MOUNT_NOUUID;
+ parsing_mp->m_features |= XFS_FEAT_NOUUID;
return 0;
case Opt_largeio:
- parsing_mp->m_flags |= XFS_MOUNT_LARGEIO;
+ parsing_mp->m_features |= XFS_FEAT_LARGE_IOSIZE;
return 0;
case Opt_nolargeio:
- parsing_mp->m_flags &= ~XFS_MOUNT_LARGEIO;
+ parsing_mp->m_features &= ~XFS_FEAT_LARGE_IOSIZE;
return 0;
case Opt_filestreams:
- parsing_mp->m_flags |= XFS_MOUNT_FILESTREAMS;
+ parsing_mp->m_features |= XFS_FEAT_FILESTREAMS;
return 0;
case Opt_noquota:
parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
- parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
return 0;
case Opt_quota:
case Opt_uquota:
case Opt_usrquota:
- parsing_mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
- XFS_UQUOTA_ENFD);
+ parsing_mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ENFD);
return 0;
case Opt_qnoenforce:
case Opt_uqnoenforce:
- parsing_mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
+ parsing_mp->m_qflags |= XFS_UQUOTA_ACCT;
parsing_mp->m_qflags &= ~XFS_UQUOTA_ENFD;
return 0;
case Opt_pquota:
case Opt_prjquota:
- parsing_mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
- XFS_PQUOTA_ENFD);
+ parsing_mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ENFD);
return 0;
case Opt_pqnoenforce:
- parsing_mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
+ parsing_mp->m_qflags |= XFS_PQUOTA_ACCT;
parsing_mp->m_qflags &= ~XFS_PQUOTA_ENFD;
return 0;
case Opt_gquota:
case Opt_grpquota:
- parsing_mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
- XFS_GQUOTA_ENFD);
+ parsing_mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ENFD);
return 0;
case Opt_gqnoenforce:
- parsing_mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
+ parsing_mp->m_qflags |= XFS_GQUOTA_ACCT;
parsing_mp->m_qflags &= ~XFS_GQUOTA_ENFD;
return 0;
case Opt_discard:
- parsing_mp->m_flags |= XFS_MOUNT_DISCARD;
+ parsing_mp->m_features |= XFS_FEAT_DISCARD;
return 0;
case Opt_nodiscard:
- parsing_mp->m_flags &= ~XFS_MOUNT_DISCARD;
+ parsing_mp->m_features &= ~XFS_FEAT_DISCARD;
return 0;
#ifdef CONFIG_FS_DAX
case Opt_dax:
#endif
/* Following mount options will be removed in September 2025 */
case Opt_ikeep:
- xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_IKEEP, true);
- parsing_mp->m_flags |= XFS_MOUNT_IKEEP;
+ xfs_fs_warn_deprecated(fc, param, XFS_FEAT_IKEEP, true);
+ parsing_mp->m_features |= XFS_FEAT_IKEEP;
return 0;
case Opt_noikeep:
- xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_IKEEP, false);
- parsing_mp->m_flags &= ~XFS_MOUNT_IKEEP;
+ xfs_fs_warn_deprecated(fc, param, XFS_FEAT_IKEEP, false);
+ parsing_mp->m_features &= ~XFS_FEAT_IKEEP;
return 0;
case Opt_attr2:
- xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_ATTR2, true);
- parsing_mp->m_flags |= XFS_MOUNT_ATTR2;
+ xfs_fs_warn_deprecated(fc, param, XFS_FEAT_ATTR2, true);
+ parsing_mp->m_features |= XFS_FEAT_ATTR2;
return 0;
case Opt_noattr2:
- xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_NOATTR2, true);
- parsing_mp->m_flags &= ~XFS_MOUNT_ATTR2;
- parsing_mp->m_flags |= XFS_MOUNT_NOATTR2;
+ xfs_fs_warn_deprecated(fc, param, XFS_FEAT_NOATTR2, true);
+ parsing_mp->m_features |= XFS_FEAT_NOATTR2;
return 0;
default:
xfs_warn(parsing_mp, "unknown mount option [%s].", param->key);
xfs_fs_validate_params(
struct xfs_mount *mp)
{
+ /* No recovery flag requires a read-only mount */
+ if (xfs_has_norecovery(mp) && !xfs_is_readonly(mp)) {
+ xfs_warn(mp, "no-recovery mounts must be read-only.");
+ return -EINVAL;
+ }
+
/*
- * no recovery flag requires a read-only mount
+ * We have not read the superblock at this point, so only the attr2
+ * mount option can set the attr2 feature by this stage.
*/
- if ((mp->m_flags & XFS_MOUNT_NORECOVERY) &&
- !(mp->m_flags & XFS_MOUNT_RDONLY)) {
- xfs_warn(mp, "no-recovery mounts must be read-only.");
+ if (xfs_has_attr2(mp) && xfs_has_noattr2(mp)) {
+ xfs_warn(mp, "attr2 and noattr2 cannot both be specified.");
return -EINVAL;
}
- if ((mp->m_flags & XFS_MOUNT_NOALIGN) &&
- (mp->m_dalign || mp->m_swidth)) {
+
+ if (xfs_has_noalign(mp) && (mp->m_dalign || mp->m_swidth)) {
xfs_warn(mp,
"sunit and swidth options incompatible with the noalign option");
return -EINVAL;
return -EINVAL;
}
- if ((mp->m_flags & XFS_MOUNT_ALLOCSIZE) &&
+ if (xfs_has_allocsize(mp) &&
(mp->m_allocsize_log > XFS_MAX_IO_LOG ||
mp->m_allocsize_log < XFS_MIN_IO_LOG)) {
xfs_warn(mp, "invalid log iosize: %d [not %d-%d]",
if (error)
goto out_destroy_workqueues;
+ error = xfs_inodegc_init_percpu(mp);
+ if (error)
+ goto out_destroy_counters;
+
+ /*
+ * All percpu data structures requiring cleanup when a cpu goes offline
+ * must be allocated before adding this @mp to the cpu-dead handler's
+ * mount list.
+ */
+ xfs_mount_list_add(mp);
+
/* Allocate stats memory before we do operations that might use it */
mp->m_stats.xs_stats = alloc_percpu(struct xfsstats);
if (!mp->m_stats.xs_stats) {
error = -ENOMEM;
- goto out_destroy_counters;
+ goto out_destroy_inodegc;
}
error = xfs_readsb(mp, flags);
goto out_free_sb;
/* V4 support is undergoing deprecation. */
- if (!xfs_sb_version_hascrc(&mp->m_sb)) {
+ if (!xfs_has_crc(mp)) {
#ifdef CONFIG_XFS_SUPPORT_V4
xfs_warn_once(mp,
"Deprecated V4 format (crc=0) will not be supported after September 2030.");
}
/* Filesystem claims it needs repair, so refuse the mount. */
- if (xfs_sb_version_needsrepair(&mp->m_sb)) {
+ if (xfs_has_needsrepair(mp)) {
xfs_warn(mp, "Filesystem needs repair. Please run xfs_repair.");
error = -EFSCORRUPTED;
goto out_free_sb;
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_max_links = XFS_MAXLINK;
sb->s_time_gran = 1;
- if (xfs_sb_version_hasbigtime(&mp->m_sb)) {
+ if (xfs_has_bigtime(mp)) {
sb->s_time_min = xfs_bigtime_to_unix(XFS_BIGTIME_TIME_MIN);
sb->s_time_max = xfs_bigtime_to_unix(XFS_BIGTIME_TIME_MAX);
} else {
set_posix_acl_flag(sb);
/* version 5 superblocks support inode version counters. */
- if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
+ if (xfs_has_crc(mp))
sb->s_flags |= SB_I_VERSION;
- if (xfs_sb_version_hasbigtime(&mp->m_sb))
- xfs_warn(mp,
- "EXPERIMENTAL big timestamp feature in use. Use at your own risk!");
-
- if (mp->m_flags & XFS_MOUNT_DAX_ALWAYS) {
+ if (xfs_has_dax_always(mp)) {
bool rtdev_is_dax = false, datadev_is_dax;
xfs_warn(mp,
"DAX unsupported by block device. Turning off DAX.");
xfs_mount_set_dax_mode(mp, XFS_DAX_NEVER);
}
- if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+ if (xfs_has_reflink(mp)) {
xfs_alert(mp,
"DAX and reflink cannot be used together!");
error = -EINVAL;
}
}
- if (mp->m_flags & XFS_MOUNT_DISCARD) {
+ if (xfs_has_discard(mp)) {
struct request_queue *q = bdev_get_queue(sb->s_bdev);
if (!blk_queue_discard(q)) {
xfs_warn(mp, "mounting with \"discard\" option, but "
"the device does not support discard");
- mp->m_flags &= ~XFS_MOUNT_DISCARD;
+ mp->m_features &= ~XFS_FEAT_DISCARD;
}
}
- if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+ if (xfs_has_reflink(mp)) {
if (mp->m_sb.sb_rblocks) {
xfs_alert(mp,
"reflink not compatible with realtime device!");
}
}
- if (xfs_sb_version_hasrmapbt(&mp->m_sb) && mp->m_sb.sb_rblocks) {
+ if (xfs_has_rmapbt(mp) && mp->m_sb.sb_rblocks) {
xfs_alert(mp,
"reverse mapping btree not compatible with realtime device!");
error = -EINVAL;
goto out_filestream_unmount;
}
- if (xfs_sb_version_hasinobtcounts(&mp->m_sb))
- xfs_warn(mp,
- "EXPERIMENTAL inode btree counters feature in use. Use at your own risk!");
-
error = xfs_mountfs(mp);
if (error)
goto out_filestream_unmount;
xfs_freesb(mp);
out_free_stats:
free_percpu(mp->m_stats.xs_stats);
+ out_destroy_inodegc:
+ xfs_mount_list_del(mp);
+ xfs_inodegc_free_percpu(mp);
out_destroy_counters:
xfs_destroy_percpu_counters(mp);
out_destroy_workqueues:
struct xfs_sb *sbp = &mp->m_sb;
int error;
- if (mp->m_flags & XFS_MOUNT_NORECOVERY) {
+ if (xfs_has_norecovery(mp)) {
xfs_warn(mp,
"ro->rw transition prohibited on norecovery mount");
return -EINVAL;
}
- if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 &&
+ if (xfs_sb_is_v5(sbp) &&
xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
xfs_warn(mp,
"ro->rw transition prohibited on unknown (0x%x) ro-compat filesystem",
return -EINVAL;
}
- mp->m_flags &= ~XFS_MOUNT_RDONLY;
+ clear_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);
/*
* If this is the first remount to writeable state we might have some
if (error && error != -ENOSPC)
return error;
+ /* Re-enable the background inode inactivation worker. */
+ xfs_inodegc_start(mp);
+
return 0;
}
return error;
}
+ /*
+ * Stop the inodegc background worker. xfs_fs_reconfigure already
+ * flushed all pending inodegc work when it sync'd the filesystem.
+ * The VFS holds s_umount, so we know that inodes cannot enter
+ * xfs_fs_destroy_inode during a remount operation. In readonly mode
+ * we send inodes straight to reclaim, so no inodes will be queued.
+ */
+ xfs_inodegc_stop(mp);
+
/* Free the per-AG metadata reservation pool. */
error = xfs_fs_unreserve_ag_blocks(mp);
if (error) {
xfs_save_resvblks(mp);
xfs_log_clean(mp);
- mp->m_flags |= XFS_MOUNT_RDONLY;
+ set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);
return 0;
}
{
struct xfs_mount *mp = XFS_M(fc->root->d_sb);
struct xfs_mount *new_mp = fc->s_fs_info;
- xfs_sb_t *sbp = &mp->m_sb;
int flags = fc->sb_flags;
int error;
/* version 5 superblocks always support version counters. */
- if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
+ if (xfs_has_crc(mp))
fc->sb_flags |= SB_I_VERSION;
error = xfs_fs_validate_params(new_mp);
sync_filesystem(mp->m_super);
/* inode32 -> inode64 */
- if ((mp->m_flags & XFS_MOUNT_SMALL_INUMS) &&
- !(new_mp->m_flags & XFS_MOUNT_SMALL_INUMS)) {
- mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
- mp->m_maxagi = xfs_set_inode_alloc(mp, sbp->sb_agcount);
+ if (xfs_has_small_inums(mp) && !xfs_has_small_inums(new_mp)) {
+ mp->m_features &= ~XFS_FEAT_SMALL_INUMS;
+ mp->m_maxagi = xfs_set_inode_alloc(mp, mp->m_sb.sb_agcount);
}
/* inode64 -> inode32 */
- if (!(mp->m_flags & XFS_MOUNT_SMALL_INUMS) &&
- (new_mp->m_flags & XFS_MOUNT_SMALL_INUMS)) {
- mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
- mp->m_maxagi = xfs_set_inode_alloc(mp, sbp->sb_agcount);
+ if (!xfs_has_small_inums(mp) && xfs_has_small_inums(new_mp)) {
+ mp->m_features |= XFS_FEAT_SMALL_INUMS;
+ mp->m_maxagi = xfs_set_inode_alloc(mp, mp->m_sb.sb_agcount);
}
/* ro -> rw */
- if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(flags & SB_RDONLY)) {
+ if (xfs_is_readonly(mp) && !(flags & SB_RDONLY)) {
error = xfs_remount_rw(mp);
if (error)
return error;
}
/* rw -> ro */
- if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (flags & SB_RDONLY)) {
+ if (!xfs_is_readonly(mp) && (flags & SB_RDONLY)) {
error = xfs_remount_ro(mp);
if (error)
return error;
* Copy binary VFS mount flags we are interested in.
*/
if (fc->sb_flags & SB_RDONLY)
- mp->m_flags |= XFS_MOUNT_RDONLY;
+ set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate);
if (fc->sb_flags & SB_DIRSYNC)
- mp->m_flags |= XFS_MOUNT_DIRSYNC;
+ mp->m_features |= XFS_FEAT_DIRSYNC;
if (fc->sb_flags & SB_SYNCHRONOUS)
- mp->m_flags |= XFS_MOUNT_WSYNC;
+ mp->m_features |= XFS_FEAT_WSYNC;
fc->s_fs_info = mp;
fc->ops = &xfs_context_ops;
destroy_workqueue(xfs_alloc_wq);
}
+ #ifdef CONFIG_HOTPLUG_CPU
+ static int
+ xfs_cpu_dead(
+ unsigned int cpu)
+ {
+ struct xfs_mount *mp, *n;
+
+ spin_lock(&xfs_mount_list_lock);
+ list_for_each_entry_safe(mp, n, &xfs_mount_list, m_mount_list) {
+ spin_unlock(&xfs_mount_list_lock);
+ xfs_inodegc_cpu_dead(mp, cpu);
+ spin_lock(&xfs_mount_list_lock);
+ }
+ spin_unlock(&xfs_mount_list_lock);
+ return 0;
+ }
+
+ static int __init
+ xfs_cpu_hotplug_init(void)
+ {
+ int error;
+
+ error = cpuhp_setup_state_nocalls(CPUHP_XFS_DEAD, "xfs:dead", NULL,
+ xfs_cpu_dead);
+ if (error < 0)
+ xfs_alert(NULL,
+ "Failed to initialise CPU hotplug, error %d. XFS is non-functional.",
+ error);
+ return error;
+ }
+
+ static void
+ xfs_cpu_hotplug_destroy(void)
+ {
+ cpuhp_remove_state_nocalls(CPUHP_XFS_DEAD);
+ }
+
+ #else /* !CONFIG_HOTPLUG_CPU */
+ static inline int xfs_cpu_hotplug_init(void) { return 0; }
+ static inline void xfs_cpu_hotplug_destroy(void) {}
+ #endif
+
STATIC int __init
init_xfs_fs(void)
{
xfs_dir_startup();
- error = xfs_init_zones();
+ error = xfs_cpu_hotplug_init();
if (error)
goto out;
+ error = xfs_init_zones();
+ if (error)
+ goto out_destroy_hp;
+
error = xfs_init_workqueues();
if (error)
goto out_destroy_zones;
xfs_destroy_workqueues();
out_destroy_zones:
xfs_destroy_zones();
+ out_destroy_hp:
+ xfs_cpu_hotplug_destroy();
out:
return error;
}
xfs_destroy_workqueues();
xfs_destroy_zones();
xfs_uuid_table_free();
+ xfs_cpu_hotplug_destroy();
}
module_init(init_xfs_fs);
projects / linux.git / commitdiff