Merge tag 'v6.9-rc1' into sched/core, to pick up fixes and to refresh the branch

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 216 insertions, 58 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 1fd94958aa97..ea48774f6b76 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -203,9 +203,9 @@ xfs_ilock(
 	}
 
 	if (lock_flags & XFS_ILOCK_EXCL)
-		mrupdate_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));
+		down_write_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));
 	else if (lock_flags & XFS_ILOCK_SHARED)
-		mraccess_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));
+		down_read_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));
 }
 
 /*
@@ -246,10 +246,10 @@ xfs_ilock_nowait(
 	}
 
 	if (lock_flags & XFS_ILOCK_EXCL) {
-		if (!mrtryupdate(&ip->i_lock))
+		if (!down_write_trylock(&ip->i_lock))
 			goto out_undo_mmaplock;
 	} else if (lock_flags & XFS_ILOCK_SHARED) {
-		if (!mrtryaccess(&ip->i_lock))
+		if (!down_read_trylock(&ip->i_lock))
 			goto out_undo_mmaplock;
 	}
 	return 1;
@@ -298,9 +298,9 @@ xfs_iunlock(
 		up_read(&VFS_I(ip)->i_mapping->invalidate_lock);
 
 	if (lock_flags & XFS_ILOCK_EXCL)
-		mrunlock_excl(&ip->i_lock);
+		up_write(&ip->i_lock);
 	else if (lock_flags & XFS_ILOCK_SHARED)
-		mrunlock_shared(&ip->i_lock);
+		up_read(&ip->i_lock);
 
 	trace_xfs_iunlock(ip, lock_flags, _RET_IP_);
 }
@@ -319,7 +319,7 @@ xfs_ilock_demote(
 		~(XFS_IOLOCK_EXCL|XFS_MMAPLOCK_EXCL|XFS_ILOCK_EXCL)) == 0);
 
 	if (lock_flags & XFS_ILOCK_EXCL)
-		mrdemote(&ip->i_lock);
+		downgrade_write(&ip->i_lock);
 	if (lock_flags & XFS_MMAPLOCK_EXCL)
 		downgrade_write(&VFS_I(ip)->i_mapping->invalidate_lock);
 	if (lock_flags & XFS_IOLOCK_EXCL)
@@ -328,52 +328,30 @@ xfs_ilock_demote(
 	trace_xfs_ilock_demote(ip, lock_flags, _RET_IP_);
 }
 
-#if defined(DEBUG) || defined(XFS_WARN)
-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(
+void
+xfs_assert_ilocked(
 	struct xfs_inode	*ip,
 	uint			lock_flags)
 {
-	if (lock_flags & (XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)) {
-		if (!(lock_flags & XFS_ILOCK_SHARED))
-			return !!ip->i_lock.mr_writer;
-		return rwsem_is_locked(&ip->i_lock.mr_lock);
-	}
-
-	if (lock_flags & (XFS_MMAPLOCK_EXCL|XFS_MMAPLOCK_SHARED)) {
-		return __xfs_rwsem_islocked(&VFS_I(ip)->i_mapping->invalidate_lock,
-				(lock_flags & XFS_MMAPLOCK_SHARED));
-	}
+	/*
+	 * Sometimes we assert the ILOCK is held exclusively, but we're in
+	 * a workqueue, so lockdep doesn't know we're the owner.
+	 */
+	if (lock_flags & XFS_ILOCK_SHARED)
+		rwsem_assert_held(&ip->i_lock);
+	else if (lock_flags & XFS_ILOCK_EXCL)
+		rwsem_assert_held_write_nolockdep(&ip->i_lock);
 
-	if (lock_flags & (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED)) {
-		return __xfs_rwsem_islocked(&VFS_I(ip)->i_rwsem,
-				(lock_flags & XFS_IOLOCK_SHARED));
-	}
+	if (lock_flags & XFS_MMAPLOCK_SHARED)
+		rwsem_assert_held(&VFS_I(ip)->i_mapping->invalidate_lock);
+	else if (lock_flags & XFS_MMAPLOCK_EXCL)
+		rwsem_assert_held_write(&VFS_I(ip)->i_mapping->invalidate_lock);
 
-	ASSERT(0);
-	return false;
+	if (lock_flags & XFS_IOLOCK_SHARED)
+		rwsem_assert_held(&VFS_I(ip)->i_rwsem);
+	else if (lock_flags & XFS_IOLOCK_EXCL)
+		rwsem_assert_held_write(&VFS_I(ip)->i_rwsem);
 }
-#endif
 
 /*
  * xfs_lockdep_subclass_ok() is only used in an ASSERT, so is only called when
@@ -671,7 +649,7 @@ xfs_lookup(
 
 out_free_name:
 	if (ci_name)
-		kmem_free(ci_name->name);
+		kfree(ci_name->name);
 out_unlock:
 	*ipp = NULL;
 	return error;
@@ -802,6 +780,8 @@ xfs_init_new_inode(
 	 */
 	if ((pip && ino == pip->i_ino) || !xfs_verify_dir_ino(mp, ino)) {
 		xfs_alert(mp, "Allocated a known in-use inode 0x%llx!", ino);
+		xfs_agno_mark_sick(mp, XFS_INO_TO_AGNO(mp, ino),
+				XFS_SICK_AG_INOBT);
 		return -EFSCORRUPTED;
 	}
 
@@ -947,6 +927,81 @@ xfs_bumplink(
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 }
 
+#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 */
+
 int
 xfs_create(
 	struct mnt_idmap	*idmap,
@@ -1058,6 +1113,12 @@ xfs_create(
 	}
 
 	/*
+	 * Create ip with a reference from dp, and add '.' and '..' references
+	 * if it's a directory.
+	 */
+	xfs_dir_update_hook(dp, ip, 1, name);
+
+	/*
 	 * If this is a synchronous mount, make sure that the
 	 * create transaction goes to disk before returning to
 	 * the user.
@@ -1271,6 +1332,7 @@ xfs_link(
 	xfs_trans_log_inode(tp, tdp, XFS_ILOG_CORE);
 
 	xfs_bumplink(tp, sip);
+	xfs_dir_update_hook(tdp, sip, 1, target_name);
 
 	/*
 	 * If this is a synchronous mount, make sure that the
@@ -1342,9 +1404,9 @@ xfs_itruncate_extents_flags(
 	xfs_fileoff_t		first_unmap_block;
 	int			error = 0;
 
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-	ASSERT(!atomic_read(&VFS_I(ip)->i_count) ||
-	       xfs_isilocked(ip, XFS_IOLOCK_EXCL));
+	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
+	if (atomic_read(&VFS_I(ip)->i_count))
+		xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL);
 	ASSERT(new_size <= XFS_ISIZE(ip));
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	ASSERT(ip->i_itemp != NULL);
@@ -1596,7 +1658,7 @@ xfs_inactive_ifree(
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
 	error = xfs_ifree(tp, ip);
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
 	if (error) {
 		/*
 		 * If we fail to free the inode, shut down.  The cancel
@@ -1677,6 +1739,39 @@ xfs_inode_needs_inactive(
 }
 
 /*
+ * Save health status somewhere, if we're dumping an inode with uncorrected
+ * errors and online repair isn't running.
+ */
+static inline void
+xfs_inactive_health(
+	struct xfs_inode	*ip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_perag	*pag;
+	unsigned int		sick;
+	unsigned int		checked;
+
+	xfs_inode_measure_sickness(ip, &sick, &checked);
+	if (!sick)
+		return;
+
+	trace_xfs_inode_unfixed_corruption(ip, sick);
+
+	if (sick & XFS_SICK_INO_FORGET)
+		return;
+
+	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
+	if (!pag) {
+		/* There had better still be a perag structure! */
+		ASSERT(0);
+		return;
+	}
+
+	xfs_ag_mark_sick(pag, XFS_SICK_AG_INODES);
+	xfs_perag_put(pag);
+}
+
+/*
  * xfs_inactive
  *
  * This is called when the vnode reference count for the vnode
@@ -1704,6 +1799,8 @@ xfs_inactive(
 	mp = ip->i_mount;
 	ASSERT(!xfs_iflags_test(ip, XFS_IRECOVERY));
 
+	xfs_inactive_health(ip);
+
 	/*
 	 * If this is a read-only mount, don't do this (would generate I/O)
 	 * unless we're in log recovery and cleaning the iunlinked list.
@@ -1910,6 +2007,7 @@ xfs_iunlink_update_bucket(
 	 */
 	if (old_value == new_agino) {
 		xfs_buf_mark_corrupt(agibp);
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
 		return -EFSCORRUPTED;
 	}
 
@@ -1959,11 +2057,14 @@ xfs_iunlink_reload_next(
 	 */
 	ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, next_agino);
 	error = xfs_iget(mp, tp, ino, XFS_IGET_UNTRUSTED, 0, &next_ip);
-	if (error)
+	if (error) {
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
 		return error;
+	}
 
 	/* If this is not an unlinked inode, something is very wrong. */
 	if (VFS_I(next_ip)->i_nlink != 0) {
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
 		error = -EFSCORRUPTED;
 		goto rele;
 	}
@@ -2001,6 +2102,7 @@ xfs_iunlink_insert_inode(
 	if (next_agino == agino ||
 	    !xfs_verify_agino_or_null(pag, next_agino)) {
 		xfs_buf_mark_corrupt(agibp);
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
 		return -EFSCORRUPTED;
 	}
 
@@ -2088,6 +2190,7 @@ xfs_iunlink_remove_inode(
 	if (!xfs_verify_agino(pag, head_agino)) {
 		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
 				agi, sizeof(*agi));
+		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
 		return -EFSCORRUPTED;
 	}
 
@@ -2116,8 +2219,10 @@ xfs_iunlink_remove_inode(
 		struct xfs_inode	*prev_ip;
 
 		prev_ip = xfs_iunlink_lookup(pag, ip->i_prev_unlinked);
-		if (!prev_ip)
+		if (!prev_ip) {
+			xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 			return -EFSCORRUPTED;
+		}
 
 		error = xfs_iunlink_log_inode(tp, prev_ip, pag,
 				ip->i_next_unlinked);
@@ -2350,7 +2455,7 @@ xfs_ifree(
 	struct xfs_inode_log_item *iip = ip->i_itemp;
 	int			error;
 
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
 	ASSERT(VFS_I(ip)->i_nlink == 0);
 	ASSERT(ip->i_df.if_nextents == 0);
 	ASSERT(ip->i_disk_size == 0 || !S_ISREG(VFS_I(ip)->i_mode));
@@ -2378,7 +2483,7 @@ xfs_ifree(
 	 * already been freed by xfs_attr_inactive.
 	 */
 	if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
-		kmem_free(ip->i_df.if_data);
+		kfree(ip->i_df.if_data);
 		ip->i_df.if_data = NULL;
 		ip->i_df.if_bytes = 0;
 	}
@@ -2419,7 +2524,7 @@ static void
 xfs_iunpin(
 	struct xfs_inode	*ip)
 {
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
+	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED);
 
 	trace_xfs_inode_unpin_nowait(ip, _RET_IP_);
 
@@ -2585,6 +2690,12 @@ xfs_remove(
 	}
 
 	/*
+	 * Drop the link from dp to ip, and if ip was a directory, remove the
+	 * '.' and '..' references since we freed the directory.
+	 */
+	xfs_dir_update_hook(dp, ip, -1, name);
+
+	/*
 	 * If this is a synchronous mount, make sure that the
 	 * remove transaction goes to disk before returning to
 	 * the user.
@@ -2774,6 +2885,20 @@ xfs_cross_rename(
 	}
 	xfs_trans_ichgtime(tp, dp1, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, dp1, XFS_ILOG_CORE);
+
+	/*
+	 * 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 xfs_finish_rename(tp);
 
 out_trans_abort:
@@ -3157,6 +3282,21 @@ retry:
 	if (new_parent)
 		xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE);
 
+	/*
+	 * 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 (wip)
+		xfs_dir_update_hook(src_dp, wip, 1, src_name);
+
 	error = xfs_finish_rename(tp);
 	if (wip)
 		xfs_irele(wip);
@@ -3182,7 +3322,7 @@ xfs_iflush(
 	struct xfs_mount	*mp = ip->i_mount;
 	int			error;
 
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
+	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED);
 	ASSERT(xfs_iflags_test(ip, XFS_IFLUSHING));
 	ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
 	       ip->i_df.if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
@@ -3317,6 +3457,8 @@ flush_out:
 
 	/* generate the checksum. */
 	xfs_dinode_calc_crc(mp, dip);
+	if (error)
+		xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
 	return error;
 }
 
@@ -3777,3 +3919,19 @@ xfs_ifork_zapped(
 		return false;
 	}
 }
+
+/* Compute the number of data and realtime blocks used by a file. */
+void
+xfs_inode_count_blocks(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	xfs_filblks_t		*dblocks,
+	xfs_filblks_t		*rblocks)
+{
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
+
+	*rblocks = 0;
+	if (XFS_IS_REALTIME_INODE(ip))
+		xfs_bmap_count_leaves(ifp, rblocks);
+	*dblocks = ip->i_nblocks - *rblocks;
+}