Merge tag 'for-linus-20190715' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull pidfd and clone3 fixes from Christian Brauner:
 "This contains a bugfix for CLONE_PIDFD when used with the legacy clone
  syscall, two fixes to ensure that syscall numbering and clone3
  entrypoint implementations will stay consistent, and an update for the
  maintainers file:

   - The addition of clone3 broke CLONE_PIDFD for legacy clone on all
     architectures that use do_fork() directly instead of calling the
     clone syscall itself. (Fwiw, cleaning do_fork() up is on my todo.)

     The reason this happened was that during conversion of _do_fork()
     to use struct kernel_clone_args we missed that do_fork() is called
     directly by various architectures. This is fixed by making sure
     that the pidfd argument in struct kernel_clone_args is correctly
     initialized with the parent_tidptr argument passed down from
     do_fork(). Additionally, do_fork() missed a check to make
     CLONE_PIDFD and CLONE_PARENT_SETTID mutually exclusive just a
     clone() does. This is now fixed too.

   - When clone3() was introduced we skipped architectures that require
     special handling for fork-like syscalls. Their syscall tables did
     not contain any mention of clone3().

     To make sure that Arnd's work to make syscall numbers on all
     architectures identical (minus alpha) was not for naught we are
     placing a comment in all syscall tables that do not yet implement
     clone3(). The comment makes it clear that 435 is reserved for
     clone3 and should not be used.

   - Also, this contains a patch to make the clone3() syscall definition
     in asm-generic/unist.h conditional on __ARCH_WANT_SYS_CLONE3. This
     lets us catch new architectures that implicitly make use of clone3
     without setting __ARCH_WANT_SYS_CLONE3 which is a good indicator
     that they did not check whether it needs special treatment or not.

   - Finally, this contains a patch to add me as maintainer for pidfd
     stuff so people can start blaming me (more)"

* tag 'for-linus-20190715' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
  MAINTAINERS: add new entry for pidfd api
  unistd: protect clone3 via __ARCH_WANT_SYS_CLONE3
  arch: mark syscall number 435 reserved for clone3
  clone: fix CLONE_PIDFD support

16 files changed, 44 insertions, 2 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 6debe6829716..afba8bf5d716 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12611,6 +12611,17 @@ F:	arch/arm/boot/dts/picoxcell*
 F:	arch/arm/mach-picoxcell/
 F:	drivers/crypto/picoxcell*
 
+PIDFD API
+M:	Christian Brauner <christian@brauner.io>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux.git
+F:	samples/pidfd/
+F:	tools/testing/selftests/pidfd/
+K:	(?i)pidfd
+K:	(?i)clone3
+K:	\b(clone_args|kernel_clone_args)\b
+
 PIN CONTROL SUBSYSTEM
 M:	Linus Walleij <linus.walleij@linaro.org>
 L:	linux-gpio@vger.kernel.org
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 1db9bbcfb84e..728fe028c02c 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -474,3 +474,4 @@
 542	common	fsmount				sys_fsmount
 543	common	fspick				sys_fspick
 544	common	pidfd_open			sys_pidfd_open
+# 545 reserved for clone3
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index ecc44926737b..36d5faf4c86c 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -355,3 +355,4 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
+# 435 reserved for clone3
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 9a3eb2558568..a88a285a0e5f 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -434,3 +434,4 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
+# 435 reserved for clone3
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 97035e19ad03..c9c879ec9b6d 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -373,3 +373,4 @@
 432	n32	fsmount				sys_fsmount
 433	n32	fspick				sys_fspick
 434	n32	pidfd_open			sys_pidfd_open
+# 435 reserved for clone3
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index d7292722d3b0..bbce9159caa1 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -349,3 +349,4 @@
 432	n64	fsmount				sys_fsmount
 433	n64	fspick				sys_fspick
 434	n64	pidfd_open			sys_pidfd_open
+# 435 reserved for clone3
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index dba084c92f14..9653591428ec 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -422,3 +422,4 @@
 432	o32	fsmount				sys_fsmount
 433	o32	fspick				sys_fspick
 434	o32	pidfd_open			sys_pidfd_open
+# 435 reserved for clone3
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index 5022b9e179c2..c7aadfef5386 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -431,3 +431,4 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
+# 435 reserved for clone3
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index f2c3bda2d39f..3331749aab20 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -516,3 +516,4 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
+# 435 reserved for clone3
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 6ebacfeaf853..a90d3e945445 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -437,3 +437,4 @@
 432  common	fsmount			sys_fsmount			sys_fsmount
 433  common	fspick			sys_fspick			sys_fspick
 434  common	pidfd_open		sys_pidfd_open			sys_pidfd_open
+# 435 reserved for clone3
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 834c9c7d79fa..b5ed26c4c005 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -437,3 +437,4 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
+# 435 reserved for clone3
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index c58e71f21129..8c8cc7537fb2 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -480,3 +480,4 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
+# 435 reserved for clone3
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 64a6c952091e..21790307121e 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -239,6 +239,7 @@ COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags,
 {
 	struct kernel_clone_args args = {
 		.flags		= (clone_flags & ~CSIGNAL),
+		.pidfd		= parent_tidptr,
 		.child_tid	= child_tidptr,
 		.parent_tid	= parent_tidptr,
 		.exit_signal	= (clone_flags & CSIGNAL),
@@ -246,5 +247,8 @@ COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags,
 		.tls		= tls_val,
 	};
 
+	if (!legacy_clone_args_valid(&args))
+		return -EINVAL;
+
 	return _do_fork(&args);
 }
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 109a0df5af39..0497091e40c1 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -89,6 +89,7 @@ extern void exit_files(struct task_struct *);
 extern void exit_itimers(struct signal_struct *);
 
 extern long _do_fork(struct kernel_clone_args *kargs);
+extern bool legacy_clone_args_valid(const struct kernel_clone_args *kargs);
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 9acfff0cd153..1be0e798e362 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -846,8 +846,10 @@ __SYSCALL(__NR_fsmount, sys_fsmount)
 __SYSCALL(__NR_fspick, sys_fspick)
 #define __NR_pidfd_open 434
 __SYSCALL(__NR_pidfd_open, sys_pidfd_open)
+#ifdef __ARCH_WANT_SYS_CLONE3
 #define __NR_clone3 435
 __SYSCALL(__NR_clone3, sys_clone3)
+#endif
 
 #undef __NR_syscalls
 #define __NR_syscalls 436
diff --git a/kernel/fork.c b/kernel/fork.c
index dfa78985a6fd..d8ae0f1b4148 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2405,6 +2405,16 @@ long _do_fork(struct kernel_clone_args *args)
 	return nr;
 }
 
+bool legacy_clone_args_valid(const struct kernel_clone_args *kargs)
+{
+	/* clone(CLONE_PIDFD) uses parent_tidptr to return a pidfd */
+	if ((kargs->flags & CLONE_PIDFD) &&
+	    (kargs->flags & CLONE_PARENT_SETTID))
+		return false;
+
+	return true;
+}
+
 #ifndef CONFIG_HAVE_COPY_THREAD_TLS
 /* For compatibility with architectures that call do_fork directly rather than
  * using the syscall entry points below. */
@@ -2416,6 +2426,7 @@ long do_fork(unsigned long clone_flags,
 {
 	struct kernel_clone_args args = {
 		.flags		= (clone_flags & ~CSIGNAL),
+		.pidfd		= parent_tidptr,
 		.child_tid	= child_tidptr,
 		.parent_tid	= parent_tidptr,
 		.exit_signal	= (clone_flags & CSIGNAL),
@@ -2423,6 +2434,9 @@ long do_fork(unsigned long clone_flags,
 		.stack_size	= stack_size,
 	};
 
+	if (!legacy_clone_args_valid(&args))
+		return -EINVAL;
+
 	return _do_fork(&args);
 }
 #endif
@@ -2504,8 +2518,7 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 		.tls		= tls,
 	};
 
-	/* clone(CLONE_PIDFD) uses parent_tidptr to return a pidfd */
-	if ((clone_flags & CLONE_PIDFD) && (clone_flags & CLONE_PARENT_SETTID))
+	if (!legacy_clone_args_valid(&args))
 		return -EINVAL;
 
 	return _do_fork(&args);