Merge patch series "cheaper MAY_EXEC handling for path lookup"

Mateusz Guzik <[e-mail]> says:

In short, MAY_WRITE checks are elided.

This obsoletes the idea of pre-computing if perm checks are necessary as
that turned out to be too hairy. The new code has 2 more branches per
path component compared to that idea, but the perf difference for
typical paths (< 6 components) was basically within noise. To be
revisited if someone(tm) removes other slowdowns.

Instead of the pre-computing thing I added IOP_FASTPERM_MAY_EXEC so that
filesystems like btrfs can still avoid the hard work.

* patches from https://patch.msgid.link/[e-mail]:
fs: retire now stale MAY_WRITE predicts in inode_permission()
btrfs: utilize IOP_FASTPERM_MAY_EXEC
fs: speed up path lookup with cheaper handling of MAY_EXEC

Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Christian Brauner <[e-mail]>

fs/btrfs/inode.c

···
 	if (ret)
 		return ERR_PTR(ret);
 
+	if (S_ISDIR(inode->vfs_inode.i_mode))
+		inode->vfs_inode.i_opflags |= IOP_FASTPERM_MAY_EXEC;
 	unlock_new_inode(&inode->vfs_inode);
 	return inode;
 }
···
 	}
 
 	ret = btrfs_create_new_inode(trans, &new_inode_args);
-	if (!ret)
+	if (!ret) {
+		if (S_ISDIR(inode->i_mode))
+			inode->i_opflags |= IOP_FASTPERM_MAY_EXEC;
 		d_instantiate_new(dentry, inode);
+	}
 
 	btrfs_end_transaction(trans);
 	btrfs_btree_balance_dirty(fs_info);
···
 					   min_size, actual_len, alloc_hint, trans);
 }
 
+/*
+ * NOTE: in case you are adding MAY_EXEC check for directories:
+ * we are marking them with IOP_FASTPERM_MAY_EXEC, allowing path lookup to
+ * elide calls here.
+ */
 static int btrfs_permission(struct mnt_idmap *idmap,
 			    struct inode *inode, int mask)
 {

fs/namei.c

···
  * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
  *
  * Separate out file-system wide checks from inode-specific permission checks.
+ *
+ * Note: lookup_inode_permission_may_exec() does not call here. If you add
+ * MAY_EXEC checks, adjust it.
  */
 static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
 {
-	if (unlikely(mask & MAY_WRITE)) {
+	if (mask & MAY_WRITE) {
 		umode_t mode = inode->i_mode;
 
 		/* Nobody gets write access to a read-only fs. */
···
 	if (unlikely(retval))
 		return retval;
 
-	if (unlikely(mask & MAY_WRITE)) {
+	if (mask & MAY_WRITE) {
 		/*
 		 * Nobody gets write access to an immutable file.
 		 */
···
 	return security_inode_permission(inode, mask);
 }
 EXPORT_SYMBOL(inode_permission);
+
+/*
+ * lookup_inode_permission_may_exec - Check traversal right for given inode
+ *
+ * This is a special case routine for may_lookup() making assumptions specific
+ * to path traversal. Use inode_permission() if you are doing something else.
+ *
+ * Work is shaved off compared to inode_permission() as follows:
+ * - we know for a fact there is no MAY_WRITE to worry about
+ * - it is an invariant the inode is a directory
+ *
+ * Since majority of real-world traversal happens on inodes which grant it for
+ * everyone, we check it upfront and only resort to more expensive work if it
+ * fails.
+ *
+ * Filesystems which have their own ->permission hook and consequently miss out
+ * on IOP_FASTPERM can still get the optimization if they set IOP_FASTPERM_MAY_EXEC
+ * on their directory inodes.
+ */
+static __always_inline int lookup_inode_permission_may_exec(struct mnt_idmap *idmap,
+	struct inode *inode, int mask)
+{
+	/* Lookup already checked this to return -ENOTDIR */
+	VFS_BUG_ON_INODE(!S_ISDIR(inode->i_mode), inode);
+	VFS_BUG_ON((mask & ~MAY_NOT_BLOCK) != 0);
+
+	mask |= MAY_EXEC;
+
+	if (unlikely(!(inode->i_opflags & (IOP_FASTPERM | IOP_FASTPERM_MAY_EXEC))))
+		return inode_permission(idmap, inode, mask);
+
+	if (unlikely(((inode->i_mode & 0111) != 0111) || !no_acl_inode(inode)))
+		return inode_permission(idmap, inode, mask);
+
+	return security_inode_permission(inode, mask);
+}
 
 /**
  * path_get - get a reference to a path
···
 	int err, mask;
 
 	mask = nd->flags & LOOKUP_RCU ? MAY_NOT_BLOCK : 0;
-	err = inode_permission(idmap, nd->inode, mask | MAY_EXEC);
+	err = lookup_inode_permission_may_exec(idmap, nd->inode, mask);
 	if (likely(!err))
 		return 0;
 
···
 	if (err != -ECHILD)	// hard error
 		return err;
 
-	return inode_permission(idmap, nd->inode, MAY_EXEC);
+	return lookup_inode_permission_may_exec(idmap, nd->inode, 0);
 }
 
 static int reserve_stack(struct nameidata *nd, struct path *link)

include/linux/fs.h

···
 	return (long)acl & 1;
 }
 
-#define IOP_FASTPERM	0x0001
-#define IOP_LOOKUP	0x0002
-#define IOP_NOFOLLOW	0x0004
-#define IOP_XATTR	0x0008
+#define IOP_FASTPERM		0x0001
+#define IOP_LOOKUP		0x0002
+#define IOP_NOFOLLOW		0x0004
+#define IOP_XATTR		0x0008
 #define IOP_DEFAULT_READLINK	0x0010
-#define IOP_MGTIME	0x0020
-#define IOP_CACHED_LINK	0x0040
+#define IOP_MGTIME		0x0020
+#define IOP_CACHED_LINK		0x0040
+#define IOP_FASTPERM_MAY_EXEC	0x0080
 
 /*
  * Inode state bits.  Protected by inode->i_lock