Merge tag 'v6.6-vfs.fchmodat2' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull fchmodat2 system call from Christian Brauner:
 "This adds the fchmodat2() system call. It is a revised version of the
  fchmodat() system call, adding a missing flag argument. Support for
  both AT_SYMLINK_NOFOLLOW and AT_EMPTY_PATH are included.

  Adding this system call revision has been a longstanding request but
  so far has always fallen through the cracks. While the kernel
  implementation of fchmodat() does not have a flag argument the libc
  provided POSIX-compliant fchmodat(3) version does. Both glibc and musl
  have to implement a workaround in order to support AT_SYMLINK_NOFOLLOW
  (see [1] and [2]).

  The workaround is brittle because it relies not just on O_PATH and
  O_NOFOLLOW semantics and procfs magic links but also on our rather
  inconsistent symlink semantics.

  This gives userspace a proper fchmodat2() system call that libcs can
  use to properly implement fchmodat(3) and allows them to get rid of
  their hacks. In this case it will immediately benefit them as the
  current workaround is already defunct because of aformentioned
  inconsistencies.

  In addition to AT_SYMLINK_NOFOLLOW, give userspace the ability to use
  AT_EMPTY_PATH with fchmodat2(). This is already possible with
  fchownat() so there's no reason to not also support it for
  fchmodat2().

  The implementation is simple and comes with selftests. Implementation
  of the system call and wiring up the system call are done as separate
  patches even though they could arguably be one patch. But in case
  there are merge conflicts from other system call additions it can be
  beneficial to have separate patches"

Link: https://sourceware.org/git/?p=glibc.git;a=blob;f=sysdeps/unix/sysv/linux/fchmodat.c;h=17eca54051ee28ba1ec3f9aed170a62630959143;hb=a492b1e5ef7ab50c6fdd4e4e9879ea5569ab0a6c#l35 [1]
Link: https://git.musl-libc.org/cgit/musl/tree/src/stat/fchmodat.c?id=718f363bc2067b6487900eddc9180c84e7739f80#n28 [2]

* tag 'v6.6-vfs.fchmodat2' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  selftests: fchmodat2: remove duplicate unneeded defines
  fchmodat2: add support for AT_EMPTY_PATH
  selftests: Add fchmodat2 selftest
  arch: Register fchmodat2, usually as syscall 452
  fs: Add fchmodat2()
  Non-functional cleanup of a "__user * filename"

25 files changed, 196 insertions, 7 deletions

diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 1f13995d00d7..ad37569d0507 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -491,3 +491,4 @@
 559	common  futex_waitv                     sys_futex_waitv
 560	common	set_mempolicy_home_node		sys_ni_syscall
 561	common	cachestat			sys_cachestat
+562	common	fchmodat2			sys_fchmodat2
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 8ebed8a13874..c572d6c3dee0 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -465,3 +465,4 @@
 449	common	futex_waitv			sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	fchmodat2			sys_fchmodat2
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 64a514f90131..bd77253b62e0 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -39,7 +39,7 @@
 #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		452
+#define __NR_compat_syscalls		453
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index d952a28463e0..78b68311ec81 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -909,6 +909,8 @@ __SYSCALL(__NR_futex_waitv, sys_futex_waitv)
 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
 #define __NR_cachestat 451
 __SYSCALL(__NR_cachestat, sys_cachestat)
+#define __NR_fchmodat2 452
+__SYSCALL(__NR_fchmodat2, sys_fchmodat2)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index f8c74ffeeefb..83d8609aec03 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -372,3 +372,4 @@
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	fchmodat2			sys_fchmodat2
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 4f504783371f..259ceb125367 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -451,3 +451,4 @@
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	fchmodat2			sys_fchmodat2
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 858d22bf275c..a3798c2637fd 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -457,3 +457,4 @@
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	fchmodat2			sys_fchmodat2
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 1976317d4e8b..152034b8e0a0 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -390,3 +390,4 @@
 449	n32	futex_waitv			sys_futex_waitv
 450	n32	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	n32	cachestat			sys_cachestat
+452	n32	fchmodat2			sys_fchmodat2
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index cfda2511badf..cb5e757f6621 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -366,3 +366,4 @@
 449	n64	futex_waitv			sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	n64	cachestat			sys_cachestat
+452	n64	fchmodat2			sys_fchmodat2
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 7692234c3768..1a646813afdc 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -439,3 +439,4 @@
 449	o32	futex_waitv			sys_futex_waitv
 450	o32	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	o32	cachestat			sys_cachestat
+452	o32	fchmodat2			sys_fchmodat2
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index a0a9145b6dd4..e97c175b56f9 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -450,3 +450,4 @@
 449	common	futex_waitv			sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	fchmodat2			sys_fchmodat2
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 8c0b08b7a80e..20e50586e8a2 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -538,3 +538,4 @@
 449	common  futex_waitv                     sys_futex_waitv
 450 	nospu	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	fchmodat2			sys_fchmodat2
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index a6935af2235c..0122cc156952 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -454,3 +454,4 @@
 449  common	futex_waitv		sys_futex_waitv			sys_futex_waitv
 450  common	set_mempolicy_home_node	sys_set_mempolicy_home_node	sys_set_mempolicy_home_node
 451  common	cachestat		sys_cachestat			sys_cachestat
+452  common	fchmodat2		sys_fchmodat2			sys_fchmodat2
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 97377e8c5025..e90d585c4d3e 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -454,3 +454,4 @@
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	fchmodat2			sys_fchmodat2
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index faa835f3c54a..4ed06c71c43f 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -497,3 +497,4 @@
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	fchmodat2			sys_fchmodat2
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index bc0a3c941b35..2d0b1bd866ea 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -456,3 +456,4 @@
 449	i386	futex_waitv		sys_futex_waitv
 450	i386	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	i386	cachestat		sys_cachestat
+452	i386	fchmodat2		sys_fchmodat2
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 227538b0ce80..814768249eae 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -373,6 +373,7 @@
 449	common	futex_waitv		sys_futex_waitv
 450	common	set_mempolicy_home_node	sys_set_mempolicy_home_node
 451	common	cachestat		sys_cachestat
+452	common	fchmodat2		sys_fchmodat2
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 2b69c3c035b6..fc1a4f3c81d9 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -422,3 +422,4 @@
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	fchmodat2			sys_fchmodat2
diff --git a/fs/open.c b/fs/open.c
index 023a20322f11..98f6601fbac6 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -671,11 +671,20 @@ SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode)
 	return err;
 }
 
-static int do_fchmodat(int dfd, const char __user *filename, umode_t mode)
+static int do_fchmodat(int dfd, const char __user *filename, umode_t mode,
+		       unsigned int flags)
 {
 	struct path path;
 	int error;
-	unsigned int lookup_flags = LOOKUP_FOLLOW;
+	unsigned int lookup_flags;
+
+	if (unlikely(flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)))
+		return -EINVAL;
+
+	lookup_flags = (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
+	if (flags & AT_EMPTY_PATH)
+		lookup_flags |= LOOKUP_EMPTY;
+
 retry:
 	error = user_path_at(dfd, filename, lookup_flags, &path);
 	if (!error) {
@@ -689,15 +698,21 @@ retry:
 	return error;
 }
 
+SYSCALL_DEFINE4(fchmodat2, int, dfd, const char __user *, filename,
+		umode_t, mode, unsigned int, flags)
+{
+	return do_fchmodat(dfd, filename, mode, flags);
+}
+
 SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename,
 		umode_t, mode)
 {
-	return do_fchmodat(dfd, filename, mode);
+	return do_fchmodat(dfd, filename, mode, 0);
 }
 
 SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode)
 {
-	return do_fchmodat(AT_FDCWD, filename, mode);
+	return do_fchmodat(AT_FDCWD, filename, mode, 0);
 }
 
 /*
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 03e3d0121d5e..5690aef7b3a8 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -438,8 +438,10 @@ asmlinkage long sys_chdir(const char __user *filename);
 asmlinkage long sys_fchdir(unsigned int fd);
 asmlinkage long sys_chroot(const char __user *filename);
 asmlinkage long sys_fchmod(unsigned int fd, umode_t mode);
-asmlinkage long sys_fchmodat(int dfd, const char __user * filename,
+asmlinkage long sys_fchmodat(int dfd, const char __user *filename,
 			     umode_t mode);
+asmlinkage long sys_fchmodat2(int dfd, const char __user *filename,
+			     umode_t mode, unsigned int flags);
 asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user,
 			     gid_t group, int flag);
 asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index fd6c1cb585db..abe087c53b4b 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -820,8 +820,11 @@ __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
 #define __NR_cachestat 451
 __SYSCALL(__NR_cachestat, sys_cachestat)
 
+#define __NR_fchmodat2 452
+__SYSCALL(__NR_fchmodat2, sys_fchmodat2)
+
 #undef __NR_syscalls
-#define __NR_syscalls 452
+#define __NR_syscalls 453
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 666b56f22a41..8dca8acdb671 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -18,6 +18,7 @@ TARGETS += drivers/net/bonding
 TARGETS += drivers/net/team
 TARGETS += efivarfs
 TARGETS += exec
+TARGETS += fchmodat2
 TARGETS += filesystems
 TARGETS += filesystems/binderfs
 TARGETS += filesystems/epoll
diff --git a/tools/testing/selftests/fchmodat2/.gitignore b/tools/testing/selftests/fchmodat2/.gitignore
new file mode 100644
index 000000000000..82a4846cbc4b
--- /dev/null
+++ b/tools/testing/selftests/fchmodat2/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+/*_test
diff --git a/tools/testing/selftests/fchmodat2/Makefile b/tools/testing/selftests/fchmodat2/Makefile
new file mode 100644
index 000000000000..20839f8e43f2
--- /dev/null
+++ b/tools/testing/selftests/fchmodat2/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined $(KHDR_INCLUDES)
+TEST_GEN_PROGS := fchmodat2_test
+
+include ../lib.mk
diff --git a/tools/testing/selftests/fchmodat2/fchmodat2_test.c b/tools/testing/selftests/fchmodat2/fchmodat2_test.c
new file mode 100644
index 000000000000..e0319417124d
--- /dev/null
+++ b/tools/testing/selftests/fchmodat2/fchmodat2_test.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <syscall.h>
+#include <unistd.h>
+
+#include "../kselftest.h"
+
+int sys_fchmodat2(int dfd, const char *filename, mode_t mode, int flags)
+{
+	int ret = syscall(__NR_fchmodat2, dfd, filename, mode, flags);
+
+	return ret >= 0 ? ret : -errno;
+}
+
+int setup_testdir(void)
+{
+	int dfd, ret;
+	char dirname[] = "/tmp/ksft-fchmodat2.XXXXXX";
+
+	/* Make the top-level directory. */
+	if (!mkdtemp(dirname))
+		ksft_exit_fail_msg("%s: failed to create tmpdir\n", __func__);
+
+	dfd = open(dirname, O_PATH | O_DIRECTORY);
+	if (dfd < 0)
+		ksft_exit_fail_msg("%s: failed to open tmpdir\n", __func__);
+
+	ret = openat(dfd, "regfile", O_CREAT | O_WRONLY | O_TRUNC, 0644);
+	if (ret < 0)
+		ksft_exit_fail_msg("%s: failed to create file in tmpdir\n",
+				__func__);
+	close(ret);
+
+	ret = symlinkat("regfile", dfd, "symlink");
+	if (ret < 0)
+		ksft_exit_fail_msg("%s: failed to create symlink in tmpdir\n",
+				__func__);
+
+	return dfd;
+}
+
+int expect_mode(int dfd, const char *filename, mode_t expect_mode)
+{
+	struct stat st;
+	int ret = fstatat(dfd, filename, &st, AT_SYMLINK_NOFOLLOW);
+
+	if (ret)
+		ksft_exit_fail_msg("%s: %s: fstatat failed\n",
+				__func__, filename);
+
+	return (st.st_mode == expect_mode);
+}
+
+void test_regfile(void)
+{
+	int dfd, ret;
+
+	dfd = setup_testdir();
+
+	ret = sys_fchmodat2(dfd, "regfile", 0640, 0);
+
+	if (ret < 0)
+		ksft_exit_fail_msg("%s: fchmodat2(noflag) failed\n", __func__);
+
+	if (!expect_mode(dfd, "regfile", 0100640))
+		ksft_exit_fail_msg("%s: wrong file mode bits after fchmodat2\n",
+				__func__);
+
+	ret = sys_fchmodat2(dfd, "regfile", 0600, AT_SYMLINK_NOFOLLOW);
+
+	if (ret < 0)
+		ksft_exit_fail_msg("%s: fchmodat2(AT_SYMLINK_NOFOLLOW) failed\n",
+				__func__);
+
+	if (!expect_mode(dfd, "regfile", 0100600))
+		ksft_exit_fail_msg("%s: wrong file mode bits after fchmodat2 with nofollow\n",
+				__func__);
+
+	ksft_test_result_pass("fchmodat2(regfile)\n");
+}
+
+void test_symlink(void)
+{
+	int dfd, ret;
+
+	dfd = setup_testdir();
+
+	ret = sys_fchmodat2(dfd, "symlink", 0640, 0);
+
+	if (ret < 0)
+		ksft_exit_fail_msg("%s: fchmodat2(noflag) failed\n", __func__);
+
+	if (!expect_mode(dfd, "regfile", 0100640))
+		ksft_exit_fail_msg("%s: wrong file mode bits after fchmodat2\n",
+				__func__);
+
+	if (!expect_mode(dfd, "symlink", 0120777))
+		ksft_exit_fail_msg("%s: wrong symlink mode bits after fchmodat2\n",
+				__func__);
+
+	ret = sys_fchmodat2(dfd, "symlink", 0600, AT_SYMLINK_NOFOLLOW);
+
+	/*
+	 * On certain filesystems (xfs or btrfs), chmod operation fails. So we
+	 * first check the symlink target but if the operation fails we mark the
+	 * test as skipped.
+	 *
+	 * https://sourceware.org/legacy-ml/libc-alpha/2020-02/msg00467.html
+	 */
+	if (ret == 0 && !expect_mode(dfd, "symlink", 0120600))
+		ksft_exit_fail_msg("%s: wrong symlink mode bits after fchmodat2 with nofollow\n",
+				__func__);
+
+	if (!expect_mode(dfd, "regfile", 0100640))
+		ksft_exit_fail_msg("%s: wrong file mode bits after fchmodat2 with nofollow\n",
+				__func__);
+
+	if (ret != 0)
+		ksft_test_result_skip("fchmodat2(symlink)\n");
+	else
+		ksft_test_result_pass("fchmodat2(symlink)\n");
+}
+
+#define NUM_TESTS 2
+
+int main(int argc, char **argv)
+{
+	ksft_print_header();
+	ksft_set_plan(NUM_TESTS);
+
+	test_regfile();
+	test_symlink();
+
+	if (ksft_get_fail_cnt() + ksft_get_error_cnt() > 0)
+		ksft_exit_fail();
+	else
+		ksft_exit_pass();
+}