1 files changed, 153 insertions, 83 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index a835ceb79ba5..a4f6f034fb81 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -132,7 +132,7 @@ xfs_ilock_attr_map_shared(
 
 /*
  * 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,
@@ -140,23 +140,23 @@ xfs_ilock_attr_map_shared(
  *
  * 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).
  */
@@ -188,10 +188,13 @@ xfs_ilock(
 				 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));
@@ -240,10 +243,10 @@ xfs_ilock_nowait(
 	}
 
 	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;
 	}
 
@@ -258,9 +261,9 @@ xfs_ilock_nowait(
 
 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);
@@ -307,9 +310,9 @@ xfs_iunlock(
 		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);
@@ -335,7 +338,7 @@ xfs_ilock_demote(
 	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);
 
@@ -343,9 +346,29 @@ xfs_ilock_demote(
 }
 
 #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)) {
@@ -355,20 +378,17 @@ xfs_isilocked(
 	}
 
 	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
 
@@ -532,12 +552,10 @@ again:
 }
 
 /*
- * 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(
@@ -555,15 +573,8 @@ 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) {
@@ -663,7 +674,7 @@ xfs_lookup(
 
 	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);
@@ -705,7 +716,7 @@ xfs_inode_inherit_flags(
 			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;
@@ -826,8 +837,7 @@ xfs_init_new_inode(
 	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;
@@ -857,7 +867,7 @@ xfs_init_new_inode(
 	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;
@@ -897,7 +907,7 @@ xfs_init_new_inode(
 	 * 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);
 	}
@@ -976,7 +986,7 @@ xfs_create(
 
 	trace_xfs_create(dp, name);
 
-	if (XFS_FORCED_SHUTDOWN(mp))
+	if (xfs_is_shutdown(mp))
 		return -EIO;
 
 	prid = xfs_get_initial_prid(dp);
@@ -1068,7 +1078,7 @@ xfs_create(
 	 * 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);
 
 	/*
@@ -1130,7 +1140,7 @@ xfs_create_tmpfile(
 	uint			resblks;
 	xfs_ino_t		ino;
 
-	if (XFS_FORCED_SHUTDOWN(mp))
+	if (xfs_is_shutdown(mp))
 		return -EIO;
 
 	prid = xfs_get_initial_prid(dp);
@@ -1160,7 +1170,7 @@ xfs_create_tmpfile(
 	if (error)
 		goto out_trans_cancel;
 
-	if (mp->m_flags & XFS_MOUNT_WSYNC)
+	if (xfs_has_wsync(mp))
 		xfs_trans_set_sync(tp);
 
 	/*
@@ -1220,7 +1230,7 @@ xfs_link(
 
 	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);
@@ -1294,7 +1304,7 @@ xfs_link(
 	 * 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);
@@ -1435,10 +1445,10 @@ xfs_release(
 		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;
 
 		/*
@@ -1521,7 +1531,7 @@ xfs_inactive_truncate(
 
 	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);
@@ -1592,7 +1602,7 @@ xfs_inactive_ifree(
 			"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;
 	}
@@ -1628,7 +1638,7 @@ xfs_inactive_ifree(
 		 * 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);
@@ -1655,6 +1665,59 @@ xfs_inactive_ifree(
 }
 
 /*
+ * 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
  *
  * This is called when the vnode reference count for the vnode
@@ -1683,7 +1746,7 @@ 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. */
@@ -1958,7 +2021,7 @@ xfs_iunlink_destroy(
 	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));
 }
 
 /*
@@ -2703,7 +2766,7 @@ xfs_remove(
 
 	trace_xfs_remove(dp, name);
 
-	if (XFS_FORCED_SHUTDOWN(mp))
+	if (xfs_is_shutdown(mp))
 		return -EIO;
 
 	error = xfs_qm_dqattach(dp);
@@ -2763,6 +2826,19 @@ xfs_remove(
 		error = xfs_droplink(tp, ip);
 		if (error)
 			goto out_trans_cancel;
+
+		/*
+		 * Point the unlinked child directory's ".." entry to the root
+		 * directory to eliminate back-references to inodes that may
+		 * get freed before the child directory is closed.  If the fs
+		 * gets shrunk, this can lead to dirent inode validation errors.
+		 */
+		if (dp->i_ino != tp->t_mountp->m_sb.sb_rootino) {
+			error = xfs_dir_replace(tp, ip, &xfs_name_dotdot,
+					tp->t_mountp->m_sb.sb_rootino, 0);
+			if (error)
+				return error;
+		}
 	} else {
 		/*
 		 * When removing a non-directory we need to log the parent
@@ -2789,7 +2865,7 @@ xfs_remove(
 	 * 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);
@@ -2866,7 +2942,7 @@ xfs_finish_rename(
 	 * 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);
@@ -3449,7 +3525,7 @@ xfs_iflush(
 	 * 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++;
 
 	/*
@@ -3471,7 +3547,7 @@ xfs_iflush(
 	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;
 	}
@@ -3590,7 +3666,7 @@ xfs_iflush_cluster(
 		 * 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);
@@ -3728,11 +3804,8 @@ xfs_ilock2_io_mmap(
 	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;
 }
 
@@ -3742,12 +3815,9 @@ xfs_iunlock2_io_mmap(
 	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));
 }