The generic inode_permission() routine does work which is known to be of no significance for lookup. There are checks for MAY_WRITE, while the requested permission is MAY_EXEC. Additionally devcgroup_inode_permission() is called to check for devices, but it is an invariant the inode is a directory. Absent a ->permission func, execution lands in generic_permission() which checks upfront if the requested permission is granted for everyone. We can elide the branches which are guaranteed to be false and cut straight to the check if everyone happens to be allowed MAY_EXEC on the inode (which holds true most of the time). Moreover, filesystems which provide their own ->permission routine can take advantage of the optimization by setting the IOP_FASTPERM_MAY_EXEC flag on their inodes, which they can legitimately do if their MAY_EXEC handling matches generic_permission(). As a simple benchmark, as part of compilation gcc issues access(2) on numerous long paths, for example /usr/lib/gcc/x86_64-linux-gnu/12/crtendS.o Issuing access(2) on it in a loop on ext4 on Sapphire Rapids (ops/s): before: 3797556 after: 3987789 (+5%) Note: this depends on the not-yet-landed ext4 patch to mark inodes with cache_no_acl() Signed-off-by: Mateusz Guzik --- fs/namei.c | 43 +++++++++++++++++++++++++++++++++++++++++-- include/linux/fs.h | 13 +++++++------ 2 files changed, 48 insertions(+), 8 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index a9f9d0453425..6b2a5a5478e7 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -540,6 +540,9 @@ static inline int do_inode_permission(struct mnt_idmap *idmap, * @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) { @@ -602,6 +605,42 @@ int inode_permission(struct mnt_idmap *idmap, } 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 * @path: path to get the reference to @@ -1855,7 +1894,7 @@ static inline int may_lookup(struct mnt_idmap *idmap, 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; @@ -1870,7 +1909,7 @@ static inline int may_lookup(struct mnt_idmap *idmap, 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) diff --git a/include/linux/fs.h b/include/linux/fs.h index 03e450dd5211..7d5de647ac7b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -647,13 +647,14 @@ is_uncached_acl(struct posix_acl *acl) 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 -- 2.48.1 Root filesystem was ext4, btrfs was mounted on /testfs. Then issuing access(2) in a loop on /testfs/repos/linux/include/linux/fs.h on Sapphire Rapids (ops/s): before: 3447976 after: 3620879 (+5%) Signed-off-by: Mateusz Guzik --- fs/btrfs/inode.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 42da39c1e5b5..1a560f7298bf 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5852,6 +5852,8 @@ struct btrfs_inode *btrfs_iget(u64 ino, struct btrfs_root *root) 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; } @@ -6803,8 +6805,11 @@ static int btrfs_create_common(struct inode *dir, struct dentry *dentry, } 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); @@ -9163,6 +9168,11 @@ int btrfs_prealloc_file_range_trans(struct inode *inode, 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) { -- 2.48.1 The primary non-MAY_WRITE consumer now uses lookup_inode_permission_may_exec(). Signed-off-by: Mateusz Guzik --- fs/namei.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index 6b2a5a5478e7..2a112b2c0951 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -546,7 +546,7 @@ static inline int do_inode_permission(struct mnt_idmap *idmap, */ 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. */ @@ -577,7 +577,7 @@ int inode_permission(struct mnt_idmap *idmap, if (unlikely(retval)) return retval; - if (unlikely(mask & MAY_WRITE)) { + if (mask & MAY_WRITE) { /* * Nobody gets write access to an immutable file. */ -- 2.48.1