1 files changed, 658 insertions, 3 deletions

diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 457f9a38f850..202468223bf9 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -19,6 +19,11 @@
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_health.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+#include "xfs_parent.h"
+#include "xfs_ag.h"
+#include "xfs_ialloc.h"
 
 const struct xfs_name xfs_name_dotdot = {
 	.name	= (const unsigned char *)"..",
@@ -584,9 +589,9 @@ xfs_dir_replace(
  */
 int
 xfs_dir_canenter(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*dp,
-	struct xfs_name	*name)		/* name of entry to add */
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	const struct xfs_name	*name)		/* name of entry to add */
 {
 	return xfs_dir_createname(tp, dp, name, 0, 0);
 }
@@ -756,3 +761,653 @@ xfs_dir2_compname(
 		return xfs_ascii_ci_compname(args, name, len);
 	return xfs_da_compname(args, name, len);
 }
+
+#ifdef CONFIG_XFS_LIVE_HOOKS
+/*
+ * Use a static key here to reduce the overhead of directory live update hooks.
+ * If the compiler supports jump labels, the static branch will be replaced by
+ * a nop sled when there are no hook users.  Online fsck is currently the only
+ * caller, so this is a reasonable tradeoff.
+ *
+ * Note: Patching the kernel code requires taking the cpu hotplug lock.  Other
+ * parts of the kernel allocate memory with that lock held, which means that
+ * XFS callers cannot hold any locks that might be used by memory reclaim or
+ * writeback when calling the static_branch_{inc,dec} functions.
+ */
+DEFINE_STATIC_XFS_HOOK_SWITCH(xfs_dir_hooks_switch);
+
+void
+xfs_dir_hook_disable(void)
+{
+	xfs_hooks_switch_off(&xfs_dir_hooks_switch);
+}
+
+void
+xfs_dir_hook_enable(void)
+{
+	xfs_hooks_switch_on(&xfs_dir_hooks_switch);
+}
+
+/* Call hooks for a directory update relating to a child dirent update. */
+inline void
+xfs_dir_update_hook(
+	struct xfs_inode		*dp,
+	struct xfs_inode		*ip,
+	int				delta,
+	const struct xfs_name		*name)
+{
+	if (xfs_hooks_switched_on(&xfs_dir_hooks_switch)) {
+		struct xfs_dir_update_params	p = {
+			.dp		= dp,
+			.ip		= ip,
+			.delta		= delta,
+			.name		= name,
+		};
+		struct xfs_mount	*mp = ip->i_mount;
+
+		xfs_hooks_call(&mp->m_dir_update_hooks, 0, &p);
+	}
+}
+
+/* Call the specified function during a directory update. */
+int
+xfs_dir_hook_add(
+	struct xfs_mount	*mp,
+	struct xfs_dir_hook	*hook)
+{
+	return xfs_hooks_add(&mp->m_dir_update_hooks, &hook->dirent_hook);
+}
+
+/* Stop calling the specified function during a directory update. */
+void
+xfs_dir_hook_del(
+	struct xfs_mount	*mp,
+	struct xfs_dir_hook	*hook)
+{
+	xfs_hooks_del(&mp->m_dir_update_hooks, &hook->dirent_hook);
+}
+
+/* Configure directory update hook functions. */
+void
+xfs_dir_hook_setup(
+	struct xfs_dir_hook	*hook,
+	notifier_fn_t		mod_fn)
+{
+	xfs_hook_setup(&hook->dirent_hook, mod_fn);
+}
+#endif /* CONFIG_XFS_LIVE_HOOKS */
+
+/*
+ * Given a directory @dp, a newly allocated inode @ip, and a @name, link @ip
+ * into @dp under the given @name.  If @ip is a directory, it will be
+ * initialized.  Both inodes must have the ILOCK held and the transaction must
+ * have sufficient blocks reserved.
+ */
+int
+xfs_dir_create_child(
+	struct xfs_trans	*tp,
+	unsigned int		resblks,
+	struct xfs_dir_update	*du)
+{
+	struct xfs_inode	*dp = du->dp;
+	const struct xfs_name	*name = du->name;
+	struct xfs_inode	*ip = du->ip;
+	int			error;
+
+	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
+	xfs_assert_ilocked(dp, XFS_ILOCK_EXCL);
+
+	error = xfs_dir_createname(tp, dp, name, ip->i_ino, resblks);
+	if (error) {
+		ASSERT(error != -ENOSPC);
+		return error;
+	}
+
+	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
+
+	if (S_ISDIR(VFS_I(ip)->i_mode)) {
+		error = xfs_dir_init(tp, ip, dp);
+		if (error)
+			return error;
+
+		xfs_bumplink(tp, dp);
+	}
+
+	/*
+	 * If we have parent pointers, we need to add the attribute containing
+	 * the parent information now.
+	 */
+	if (du->ppargs) {
+		error = xfs_parent_addname(tp, du->ppargs, dp, name, ip);
+		if (error)
+			return error;
+	}
+
+	xfs_dir_update_hook(dp, ip, 1, name);
+	return 0;
+}
+
+/*
+ * Given a directory @dp, an existing non-directory inode @ip, and a @name,
+ * link @ip into @dp under the given @name.  Both inodes must have the ILOCK
+ * held.
+ */
+int
+xfs_dir_add_child(
+	struct xfs_trans	*tp,
+	unsigned int		resblks,
+	struct xfs_dir_update	*du)
+{
+	struct xfs_inode	*dp = du->dp;
+	const struct xfs_name	*name = du->name;
+	struct xfs_inode	*ip = du->ip;
+	struct xfs_mount	*mp = tp->t_mountp;
+	int			error;
+
+	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
+	xfs_assert_ilocked(dp, XFS_ILOCK_EXCL);
+	ASSERT(!S_ISDIR(VFS_I(ip)->i_mode));
+
+	if (!resblks) {
+		error = xfs_dir_canenter(tp, dp, name);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * Handle initial link state of O_TMPFILE inode
+	 */
+	if (VFS_I(ip)->i_nlink == 0) {
+		struct xfs_perag	*pag;
+
+		pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
+		error = xfs_iunlink_remove(tp, pag, ip);
+		xfs_perag_put(pag);
+		if (error)
+			return error;
+	}
+
+	error = xfs_dir_createname(tp, dp, name, ip->i_ino, resblks);
+	if (error)
+		return error;
+
+	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
+
+	xfs_bumplink(tp, ip);
+
+	/*
+	 * If we have parent pointers, we now need to add the parent record to
+	 * the attribute fork of the inode. If this is the initial parent
+	 * attribute, we need to create it correctly, otherwise we can just add
+	 * the parent to the inode.
+	 */
+	if (du->ppargs) {
+		error = xfs_parent_addname(tp, du->ppargs, dp, name, ip);
+		if (error)
+			return error;
+	}
+
+	xfs_dir_update_hook(dp, ip, 1, name);
+	return 0;
+}
+
+/*
+ * Given a directory @dp, a child @ip, and a @name, remove the (@name, @ip)
+ * entry from the directory.  Both inodes must have the ILOCK held.
+ */
+int
+xfs_dir_remove_child(
+	struct xfs_trans	*tp,
+	unsigned int		resblks,
+	struct xfs_dir_update	*du)
+{
+	struct xfs_inode	*dp = du->dp;
+	const struct xfs_name	*name = du->name;
+	struct xfs_inode	*ip = du->ip;
+	int			error;
+
+	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
+	xfs_assert_ilocked(dp, XFS_ILOCK_EXCL);
+
+	/*
+	 * If we're removing a directory perform some additional validation.
+	 */
+	if (S_ISDIR(VFS_I(ip)->i_mode)) {
+		ASSERT(VFS_I(ip)->i_nlink >= 2);
+		if (VFS_I(ip)->i_nlink != 2)
+			return -ENOTEMPTY;
+		if (!xfs_dir_isempty(ip))
+			return -ENOTEMPTY;
+
+		/* Drop the link from ip's "..".  */
+		error = xfs_droplink(tp, dp);
+		if (error)
+			return error;
+
+		/* Drop the "." link from ip to self.  */
+		error = xfs_droplink(tp, ip);
+		if (error)
+			return error;
+
+		/*
+		 * 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
+		 * inode here.  For a directory this is done implicitly
+		 * by the xfs_droplink call for the ".." entry.
+		 */
+		xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
+	}
+	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+
+	/* Drop the link from dp to ip. */
+	error = xfs_droplink(tp, ip);
+	if (error)
+		return error;
+
+	error = xfs_dir_removename(tp, dp, name, ip->i_ino, resblks);
+	if (error) {
+		ASSERT(error != -ENOENT);
+		return error;
+	}
+
+	/* Remove parent pointer. */
+	if (du->ppargs) {
+		error = xfs_parent_removename(tp, du->ppargs, dp, name, ip);
+		if (error)
+			return error;
+	}
+
+	xfs_dir_update_hook(dp, ip, -1, name);
+	return 0;
+}
+
+/*
+ * Exchange the entry (@name1, @ip1) in directory @dp1 with the entry (@name2,
+ * @ip2) in directory @dp2, and update '..' @ip1 and @ip2's entries as needed.
+ * @ip1 and @ip2 need not be of the same type.
+ *
+ * All inodes must have the ILOCK held, and both entries must already exist.
+ */
+int
+xfs_dir_exchange_children(
+	struct xfs_trans	*tp,
+	struct xfs_dir_update	*du1,
+	struct xfs_dir_update	*du2,
+	unsigned int		spaceres)
+{
+	struct xfs_inode	*dp1 = du1->dp;
+	const struct xfs_name	*name1 = du1->name;
+	struct xfs_inode	*ip1 = du1->ip;
+	struct xfs_inode	*dp2 = du2->dp;
+	const struct xfs_name	*name2 = du2->name;
+	struct xfs_inode	*ip2 = du2->ip;
+	int			ip1_flags = 0;
+	int			ip2_flags = 0;
+	int			dp2_flags = 0;
+	int			error;
+
+	/* Swap inode number for dirent in first parent */
+	error = xfs_dir_replace(tp, dp1, name1, ip2->i_ino, spaceres);
+	if (error)
+		return error;
+
+	/* Swap inode number for dirent in second parent */
+	error = xfs_dir_replace(tp, dp2, name2, ip1->i_ino, spaceres);
+	if (error)
+		return error;
+
+	/*
+	 * If we're renaming one or more directories across different parents,
+	 * update the respective ".." entries (and link counts) to match the new
+	 * parents.
+	 */
+	if (dp1 != dp2) {
+		dp2_flags = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
+
+		if (S_ISDIR(VFS_I(ip2)->i_mode)) {
+			error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot,
+						dp1->i_ino, spaceres);
+			if (error)
+				return error;
+
+			/* transfer ip2 ".." reference to dp1 */
+			if (!S_ISDIR(VFS_I(ip1)->i_mode)) {
+				error = xfs_droplink(tp, dp2);
+				if (error)
+					return error;
+				xfs_bumplink(tp, dp1);
+			}
+
+			/*
+			 * Although ip1 isn't changed here, userspace needs
+			 * to be warned about the change, so that applications
+			 * relying on it (like backup ones), will properly
+			 * notify the change
+			 */
+			ip1_flags |= XFS_ICHGTIME_CHG;
+			ip2_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
+		}
+
+		if (S_ISDIR(VFS_I(ip1)->i_mode)) {
+			error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot,
+						dp2->i_ino, spaceres);
+			if (error)
+				return error;
+
+			/* transfer ip1 ".." reference to dp2 */
+			if (!S_ISDIR(VFS_I(ip2)->i_mode)) {
+				error = xfs_droplink(tp, dp1);
+				if (error)
+					return error;
+				xfs_bumplink(tp, dp2);
+			}
+
+			/*
+			 * Although ip2 isn't changed here, userspace needs
+			 * to be warned about the change, so that applications
+			 * relying on it (like backup ones), will properly
+			 * notify the change
+			 */
+			ip1_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
+			ip2_flags |= XFS_ICHGTIME_CHG;
+		}
+	}
+
+	if (ip1_flags) {
+		xfs_trans_ichgtime(tp, ip1, ip1_flags);
+		xfs_trans_log_inode(tp, ip1, XFS_ILOG_CORE);
+	}
+	if (ip2_flags) {
+		xfs_trans_ichgtime(tp, ip2, ip2_flags);
+		xfs_trans_log_inode(tp, ip2, XFS_ILOG_CORE);
+	}
+	if (dp2_flags) {
+		xfs_trans_ichgtime(tp, dp2, dp2_flags);
+		xfs_trans_log_inode(tp, dp2, XFS_ILOG_CORE);
+	}
+	xfs_trans_ichgtime(tp, dp1, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	xfs_trans_log_inode(tp, dp1, XFS_ILOG_CORE);
+
+	/* Schedule parent pointer replacements */
+	if (du1->ppargs) {
+		error = xfs_parent_replacename(tp, du1->ppargs, dp1, name1,
+				dp2, name2, ip1);
+		if (error)
+			return error;
+	}
+
+	if (du2->ppargs) {
+		error = xfs_parent_replacename(tp, du2->ppargs, dp2, name2,
+				dp1, name1, ip2);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * Inform our hook clients that we've finished an exchange operation as
+	 * follows: removed the source and target files from their directories;
+	 * added the target to the source directory; and added the source to
+	 * the target directory.  All inodes are locked, so it's ok to model a
+	 * rename this way so long as we say we deleted entries before we add
+	 * new ones.
+	 */
+	xfs_dir_update_hook(dp1, ip1, -1, name1);
+	xfs_dir_update_hook(dp2, ip2, -1, name2);
+	xfs_dir_update_hook(dp1, ip2, 1, name1);
+	xfs_dir_update_hook(dp2, ip1, 1, name2);
+	return 0;
+}
+
+/*
+ * Given an entry (@src_name, @src_ip) in directory @src_dp, make the entry
+ * @target_name in directory @target_dp point to @src_ip and remove the
+ * original entry, cleaning up everything left behind.
+ *
+ * Cleanup involves dropping a link count on @target_ip, and either removing
+ * the (@src_name, @src_ip) entry from @src_dp or simply replacing the entry
+ * with (@src_name, @wip) if a whiteout inode @wip is supplied.
+ *
+ * All inodes must have the ILOCK held.  We assume that if @src_ip is a
+ * directory then its '..' doesn't already point to @target_dp, and that @wip
+ * is a freshly allocated whiteout.
+ */
+int
+xfs_dir_rename_children(
+	struct xfs_trans	*tp,
+	struct xfs_dir_update	*du_src,
+	struct xfs_dir_update	*du_tgt,
+	unsigned int		spaceres,
+	struct xfs_dir_update	*du_wip)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_inode	*src_dp = du_src->dp;
+	const struct xfs_name	*src_name = du_src->name;
+	struct xfs_inode	*src_ip = du_src->ip;
+	struct xfs_inode	*target_dp = du_tgt->dp;
+	const struct xfs_name	*target_name = du_tgt->name;
+	struct xfs_inode	*target_ip = du_tgt->ip;
+	bool			new_parent = (src_dp != target_dp);
+	bool			src_is_directory;
+	int			error;
+
+	src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode);
+
+	/*
+	 * Check for expected errors before we dirty the transaction
+	 * so we can return an error without a transaction abort.
+	 */
+	if (target_ip == NULL) {
+		/*
+		 * If there's no space reservation, check the entry will
+		 * fit before actually inserting it.
+		 */
+		if (!spaceres) {
+			error = xfs_dir_canenter(tp, target_dp, target_name);
+			if (error)
+				return error;
+		}
+	} else {
+		/*
+		 * If target exists and it's a directory, check that whether
+		 * it can be destroyed.
+		 */
+		if (S_ISDIR(VFS_I(target_ip)->i_mode) &&
+		    (!xfs_dir_isempty(target_ip) ||
+		     (VFS_I(target_ip)->i_nlink > 2)))
+			return -EEXIST;
+	}
+
+	/*
+	 * Directory entry creation below may acquire the AGF. Remove
+	 * the whiteout from the unlinked list first to preserve correct
+	 * AGI/AGF locking order. This dirties the transaction so failures
+	 * after this point will abort and log recovery will clean up the
+	 * mess.
+	 *
+	 * For whiteouts, we need to bump the link count on the whiteout
+	 * inode. After this point, we have a real link, clear the tmpfile
+	 * state flag from the inode so it doesn't accidentally get misused
+	 * in future.
+	 */
+	if (du_wip->ip) {
+		struct xfs_perag	*pag;
+
+		ASSERT(VFS_I(du_wip->ip)->i_nlink == 0);
+
+		pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, du_wip->ip->i_ino));
+		error = xfs_iunlink_remove(tp, pag, du_wip->ip);
+		xfs_perag_put(pag);
+		if (error)
+			return error;
+
+		xfs_bumplink(tp, du_wip->ip);
+	}
+
+	/*
+	 * Set up the target.
+	 */
+	if (target_ip == NULL) {
+		/*
+		 * If target does not exist and the rename crosses
+		 * directories, adjust the target directory link count
+		 * to account for the ".." reference from the new entry.
+		 */
+		error = xfs_dir_createname(tp, target_dp, target_name,
+					   src_ip->i_ino, spaceres);
+		if (error)
+			return error;
+
+		xfs_trans_ichgtime(tp, target_dp,
+					XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+
+		if (new_parent && src_is_directory) {
+			xfs_bumplink(tp, target_dp);
+		}
+	} else { /* target_ip != NULL */
+		/*
+		 * Link the source inode under the target name.
+		 * If the source inode is a directory and we are moving
+		 * it across directories, its ".." entry will be
+		 * inconsistent until we replace that down below.
+		 *
+		 * In case there is already an entry with the same
+		 * name at the destination directory, remove it first.
+		 */
+		error = xfs_dir_replace(tp, target_dp, target_name,
+					src_ip->i_ino, spaceres);
+		if (error)
+			return error;
+
+		xfs_trans_ichgtime(tp, target_dp,
+					XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+
+		/*
+		 * Decrement the link count on the target since the target
+		 * dir no longer points to it.
+		 */
+		error = xfs_droplink(tp, target_ip);
+		if (error)
+			return error;
+
+		if (src_is_directory) {
+			/*
+			 * Drop the link from the old "." entry.
+			 */
+			error = xfs_droplink(tp, target_ip);
+			if (error)
+				return error;
+		}
+	} /* target_ip != NULL */
+
+	/*
+	 * Remove the source.
+	 */
+	if (new_parent && src_is_directory) {
+		/*
+		 * Rewrite the ".." entry to point to the new
+		 * directory.
+		 */
+		error = xfs_dir_replace(tp, src_ip, &xfs_name_dotdot,
+					target_dp->i_ino, spaceres);
+		ASSERT(error != -EEXIST);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * We always want to hit the ctime on the source inode.
+	 *
+	 * This isn't strictly required by the standards since the source
+	 * inode isn't really being changed, but old unix file systems did
+	 * it and some incremental backup programs won't work without it.
+	 */
+	xfs_trans_ichgtime(tp, src_ip, XFS_ICHGTIME_CHG);
+	xfs_trans_log_inode(tp, src_ip, XFS_ILOG_CORE);
+
+	/*
+	 * Adjust the link count on src_dp.  This is necessary when
+	 * renaming a directory, either within one parent when
+	 * the target existed, or across two parent directories.
+	 */
+	if (src_is_directory && (new_parent || target_ip != NULL)) {
+
+		/*
+		 * Decrement link count on src_directory since the
+		 * entry that's moved no longer points to it.
+		 */
+		error = xfs_droplink(tp, src_dp);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * For whiteouts, we only need to update the source dirent with the
+	 * inode number of the whiteout inode rather than removing it
+	 * altogether.
+	 */
+	if (du_wip->ip)
+		error = xfs_dir_replace(tp, src_dp, src_name, du_wip->ip->i_ino,
+					spaceres);
+	else
+		error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino,
+					   spaceres);
+	if (error)
+		return error;
+
+	xfs_trans_ichgtime(tp, src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	xfs_trans_log_inode(tp, src_dp, XFS_ILOG_CORE);
+	if (new_parent)
+		xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE);
+
+	/* Schedule parent pointer updates. */
+	if (du_wip->ppargs) {
+		error = xfs_parent_addname(tp, du_wip->ppargs, src_dp,
+				src_name, du_wip->ip);
+		if (error)
+			return error;
+	}
+
+	if (du_src->ppargs) {
+		error = xfs_parent_replacename(tp, du_src->ppargs, src_dp,
+				src_name, target_dp, target_name, src_ip);
+		if (error)
+			return error;
+	}
+
+	if (du_tgt->ppargs) {
+		error = xfs_parent_removename(tp, du_tgt->ppargs, target_dp,
+				target_name, target_ip);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * Inform our hook clients that we've finished a rename operation as
+	 * follows: removed the source and target files from their directories;
+	 * that we've added the source to the target directory; and finally
+	 * that we've added the whiteout, if there was one.  All inodes are
+	 * locked, so it's ok to model a rename this way so long as we say we
+	 * deleted entries before we add new ones.
+	 */
+	if (target_ip)
+		xfs_dir_update_hook(target_dp, target_ip, -1, target_name);
+	xfs_dir_update_hook(src_dp, src_ip, -1, src_name);
+	xfs_dir_update_hook(target_dp, src_ip, 1, target_name);
+	if (du_wip->ip)
+		xfs_dir_update_hook(src_dp, du_wip->ip, 1, src_name);
+	return 0;
+}