vfs: add faccessat2 syscall

POSIX defines faccessat() as having a fourth "flags" argument, while the
linux syscall doesn't have it.  Glibc tries to emulate AT_EACCESS and
AT_SYMLINK_NOFOLLOW, but AT_EACCESS emulation is broken.

Add a new faccessat(2) syscall with the added flags argument and implement
both flags.

The value of AT_EACCESS is defined in glibc headers to be the same as
AT_REMOVEDIR.  Use this value for the kernel interface as well, together
with the explanatory comment.

Also add AT_EMPTY_PATH support, which is not documented by POSIX, but can
be useful and is trivial to implement.

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

arch/alpha/kernel/syscalls/syscall.tbl

@@ -477,3 +477,4 @@
 # 545 reserved for clone3
 547	common	openat2				sys_openat2
 548	common	pidfd_getfd			sys_pidfd_getfd
+549	common	faccessat2			sys_faccessat2

arch/arm/tools/syscall.tbl

@@ -451,3 +451,4 @@
 435	common	clone3				sys_clone3
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

arch/arm64/include/asm/unistd.h

@@ -38,7 +38,7 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		439
+#define __NR_compat_syscalls		440
 #endif
 
 #define __ARCH_WANT_SYS_CLONE

arch/arm64/include/asm/unistd32.h

@@ -883,6 +883,8 @@ __SYSCALL(__NR_clone3, sys_clone3)
 __SYSCALL(__NR_openat2, sys_openat2)
 #define __NR_pidfd_getfd 438
 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
+#define __NR_faccessat2 439
+__SYSCALL(__NR_faccessat2, sys_faccessat2)
 
 /*
  * Please add new compat syscalls above this comment and update

arch/ia64/kernel/syscalls/syscall.tbl

@@ -358,3 +358,4 @@
 # 435 reserved for clone3
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

arch/m68k/kernel/syscalls/syscall.tbl

@@ -437,3 +437,4 @@
 435	common	clone3				__sys_clone3
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

arch/microblaze/kernel/syscalls/syscall.tbl

@@ -443,3 +443,4 @@
 435	common	clone3				sys_clone3
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

arch/mips/kernel/syscalls/syscall_n32.tbl

@@ -376,3 +376,4 @@
 435	n32	clone3				__sys_clone3
 437	n32	openat2				sys_openat2
 438	n32	pidfd_getfd			sys_pidfd_getfd
+439	n32	faccessat2			sys_faccessat2

arch/mips/kernel/syscalls/syscall_n64.tbl

@@ -352,3 +352,4 @@
 435	n64	clone3				__sys_clone3
 437	n64	openat2				sys_openat2
 438	n64	pidfd_getfd			sys_pidfd_getfd
+439	n64	faccessat2			sys_faccessat2

arch/mips/kernel/syscalls/syscall_o32.tbl

@@ -425,3 +425,4 @@
 435	o32	clone3				__sys_clone3
 437	o32	openat2				sys_openat2
 438	o32	pidfd_getfd			sys_pidfd_getfd
+439	o32	faccessat2			sys_faccessat2

arch/parisc/kernel/syscalls/syscall.tbl

@@ -435,3 +435,4 @@
 435	common	clone3				sys_clone3_wrapper
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

arch/powerpc/kernel/syscalls/syscall.tbl

@@ -527,3 +527,4 @@
 435	spu	clone3				sys_ni_syscall
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

arch/s390/kernel/syscalls/syscall.tbl

@@ -440,3 +440,4 @@
 435  common	clone3			sys_clone3			sys_clone3
 437  common	openat2			sys_openat2			sys_openat2
 438  common	pidfd_getfd		sys_pidfd_getfd			sys_pidfd_getfd
+439  common	faccessat2		sys_faccessat2			sys_faccessat2

arch/sh/kernel/syscalls/syscall.tbl

@@ -440,3 +440,4 @@
 # 435 reserved for clone3
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

arch/sparc/kernel/syscalls/syscall.tbl

@@ -483,3 +483,4 @@
 # 435 reserved for clone3
 437	common	openat2			sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

arch/x86/entry/syscalls/syscall_32.tbl

@@ -442,3 +442,4 @@
 435	i386	clone3			sys_clone3
 437	i386	openat2			sys_openat2
 438	i386	pidfd_getfd		sys_pidfd_getfd
+439	i386	faccessat2		sys_faccessat2

arch/x86/entry/syscalls/syscall_64.tbl

@@ -359,6 +359,7 @@
 435	common	clone3			sys_clone3
 437	common	openat2			sys_openat2
 438	common	pidfd_getfd		sys_pidfd_getfd
+439	common	faccessat2		sys_faccessat2
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

arch/xtensa/kernel/syscalls/syscall.tbl

@@ -408,3 +408,4 @@
 435	common	clone3				sys_clone3
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2

fs/internal.h

@@ -126,7 +126,6 @@ extern struct open_how build_open_how(int flags, umode_t mode);
 extern int build_open_flags(const struct open_how *how, struct open_flags *op);
 
 long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
-long do_faccessat(int dfd, const char __user *filename, int mode);
 int do_fchmodat(int dfd, const char __user *filename, umode_t mode);
 int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
 		int flag);

fs/open.c

@@ -394,20 +394,30 @@ static const struct cred *access_override_creds(void)
 	return old_cred;
 }
 
-long do_faccessat(int dfd, const char __user *filename, int mode)
+long do_faccessat(int dfd, const char __user *filename, int mode, int flags)
 {
 	struct path path;
 	struct inode *inode;
 	int res;
 	unsigned int lookup_flags = LOOKUP_FOLLOW;
-	const struct cred *old_cred;
+	const struct cred *old_cred = NULL;
 
 	if (mode & ~S_IRWXO)	/* where's F_OK, X_OK, W_OK, R_OK? */
 		return -EINVAL;
 
-	old_cred = access_override_creds();
-	if (!old_cred)
-		return -ENOMEM;
+	if (flags & ~(AT_EACCESS | AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH))
+		return -EINVAL;
+
+	if (flags & AT_SYMLINK_NOFOLLOW)
+		lookup_flags &= ~LOOKUP_FOLLOW;
+	if (flags & AT_EMPTY_PATH)
+		lookup_flags |= LOOKUP_EMPTY;
+
+	if (!(flags & AT_EACCESS)) {
+		old_cred = access_override_creds();
+		if (!old_cred)
+			return -ENOMEM;
+	}
 
 retry:
 	res = user_path_at(dfd, filename, lookup_flags, &path);
@@ -450,18 +460,26 @@ long do_faccessat(int dfd, const char __user *filename, int mode)
 		goto retry;
 	}
 out:
-	revert_creds(old_cred);
+	if (old_cred)
+		revert_creds(old_cred);
+
 	return res;
 }
 
 SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
 {
-	return do_faccessat(dfd, filename, mode);
+	return do_faccessat(dfd, filename, mode, 0);
+}
+
+SYSCALL_DEFINE4(faccessat2, int, dfd, const char __user *, filename, int, mode,
+		int, flags)
+{
+	return do_faccessat(dfd, filename, mode, flags);
 }
 
 SYSCALL_DEFINE2(access, const char __user *, filename, int, mode)
 {
-	return do_faccessat(AT_FDCWD, filename, mode);
+	return do_faccessat(AT_FDCWD, filename, mode, 0);
 }
 
 int ksys_chdir(const char __user *filename)

include/linux/syscalls.h

@@ -428,6 +428,8 @@ asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length);
 #endif
 asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len);
 asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode);
+asmlinkage long sys_faccessat2(int dfd, const char __user *filename, int mode,
+			       int flags);
 asmlinkage long sys_chdir(const char __user *filename);
 asmlinkage long sys_fchdir(unsigned int fd);
 asmlinkage long sys_chroot(const char __user *filename);
@@ -1333,11 +1335,11 @@ static inline int ksys_chmod(const char __user *filename, umode_t mode)
 	return do_fchmodat(AT_FDCWD, filename, mode);
 }
 
-extern long do_faccessat(int dfd, const char __user *filename, int mode);
+long do_faccessat(int dfd, const char __user *filename, int mode, int flags);
 
 static inline long ksys_access(const char __user *filename, int mode)
 {
-	return do_faccessat(AT_FDCWD, filename, mode);
+	return do_faccessat(AT_FDCWD, filename, mode, 0);
 }
 
 extern int do_fchownat(int dfd, const char __user *filename, uid_t user,

include/uapi/asm-generic/unistd.h

@@ -855,9 +855,11 @@ __SYSCALL(__NR_clone3, sys_clone3)
 __SYSCALL(__NR_openat2, sys_openat2)
 #define __NR_pidfd_getfd 438
 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
+#define __NR_faccessat2 439
+__SYSCALL(__NR_faccessat2, sys_faccessat2)
 
 #undef __NR_syscalls
-#define __NR_syscalls 439
+#define __NR_syscalls 440
 
 /*
  * 32 bit systems traditionally used different

include/uapi/linux/fcntl.h

@@ -84,10 +84,20 @@
 #define DN_ATTRIB	0x00000020	/* File changed attibutes */
 #define DN_MULTISHOT	0x80000000	/* Don't remove notifier */
 
+/*
+ * The constants AT_REMOVEDIR and AT_EACCESS have the same value.  AT_EACCESS is
+ * meaningful only to faccessat, while AT_REMOVEDIR is meaningful only to
+ * unlinkat.  The two functions do completely different things and therefore,
+ * the flags can be allowed to overlap.  For example, passing AT_REMOVEDIR to
+ * faccessat would be undefined behavior and thus treating it equivalent to
+ * AT_EACCESS is valid undefined behavior.
+ */
 #define AT_FDCWD		-100    /* Special value used to indicate
                                            openat should use the current
                                            working directory. */
 #define AT_SYMLINK_NOFOLLOW	0x100   /* Do not follow symbolic links.  */
+#define AT_EACCESS		0x200	/* Test access permitted for
+                                           effective IDs, not real IDs.  */
 #define AT_REMOVEDIR		0x200   /* Remove directory instead of
                                            unlinking file.  */
 #define AT_SYMLINK_FOLLOW	0x400   /* Follow symbolic links.  */