clone: support passing tls argument via C rather than pt_regs magic

clone has some of the quirkiest syscall handling in the kernel, with a
pile of special cases, historical curiosities, and architecture-specific
calling conventions.  In particular, clone with CLONE_SETTLS accepts a
parameter "tls" that the C entry point completely ignores and some
assembly entry points overwrite; instead, the low-level arch-specific
code pulls the tls parameter out of the arch-specific register captured
as part of pt_regs on entry to the kernel.  That's a massive hack, and
it makes the arch-specific code only work when called via the specific
existing syscall entry points; because of this hack, any new clone-like
system call would have to accept an identical tls argument in exactly
the same arch-specific position, rather than providing a unified system
call entry point across architectures.

The first patch allows architectures to handle the tls argument via
normal C parameter passing, if they opt in by selecting
HAVE_COPY_THREAD_TLS.  The second patch makes 32-bit and 64-bit x86 opt
into this.

These two patches came out of the clone4 series, which isn't ready for
this merge window, but these first two cleanup patches were entirely
uncontroversial and have acks.  I'd like to go ahead and submit these
two so that other architectures can begin building on top of this and
opting into HAVE_COPY_THREAD_TLS.  However, I'm also happy to wait and
send these through the next merge window (along with v3 of clone4) if
anyone would prefer that.

This patch (of 2):

clone with CLONE_SETTLS accepts an argument to set the thread-local
storage area for the new thread.  sys_clone declares an int argument
tls_val in the appropriate point in the argument list (based on the
various CLONE_BACKWARDS variants), but doesn't actually use or pass along
that argument.  Instead, sys_clone calls do_fork, which calls
copy_process, which calls the arch-specific copy_thread, and copy_thread
pulls the corresponding syscall argument out of the pt_regs captured at
kernel entry (knowing what argument of clone that architecture passes tls
in).

Apart from being awful and inscrutable, that also only works because only
one code path into copy_thread can pass the CLONE_SETTLS flag, and that
code path comes from sys_clone with its architecture-specific
argument-passing order.  This prevents introducing a new version of the
clone system call without propagating the same architecture-specific
position of the tls argument.

However, there's no reason to pull the argument out of pt_regs when
sys_clone could just pass it down via C function call arguments.

Introduce a new CONFIG_HAVE_COPY_THREAD_TLS for architectures to opt into,
and a new copy_thread_tls that accepts the tls parameter as an additional
unsigned long (syscall-argument-sized) argument.  Change sys_clone's tls
argument to an unsigned long (which does not change the ABI), and pass
that down to copy_thread_tls.

Architectures that don't opt into copy_thread_tls will continue to ignore
the C argument to sys_clone in favor of the pt_regs captured at kernel
entry, and thus will be unable to introduce new versions of the clone
syscall.

Patch co-authored by Josh Triplett and Thiago Macieira.

Signed-off-by: Josh Triplett <josh@joshtriplett.org>
Acked-by: Andy Lutomirski <luto@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thiago Macieira <thiago.macieira@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 59 insertions, 21 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index a65eafb24997..bec6666a3cc4 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -499,6 +499,13 @@ config ARCH_HAS_ELF_RANDOMIZE
 	  - arch_mmap_rnd()
 	  - arch_randomize_brk()
 
+config HAVE_COPY_THREAD_TLS
+	bool
+	help
+	  Architecture provides copy_thread_tls to accept tls argument via
+	  normal C parameter passing, rather than extracting the syscall
+	  argument from pt_regs.
+
 #
 # ABI hall of shame
 #
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
index d7fa2f0f1425..f8498dde67b1 100644
--- a/arch/s390/kernel/compat_wrapper.c
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -202,7 +202,7 @@ COMPAT_SYSCALL_WRAP1(epoll_create1, int, flags);
 COMPAT_SYSCALL_WRAP2(tkill, int, pid, int, sig);
 COMPAT_SYSCALL_WRAP3(tgkill, int, tgid, int, pid, int, sig);
 COMPAT_SYSCALL_WRAP5(perf_event_open, struct perf_event_attr __user *, attr_uptr, pid_t, pid, int, cpu, int, group_fd, unsigned long, flags);
-COMPAT_SYSCALL_WRAP5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, int, tls_val);
+COMPAT_SYSCALL_WRAP5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls);
 COMPAT_SYSCALL_WRAP2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags);
 COMPAT_SYSCALL_WRAP4(prlimit64, pid_t, pid, unsigned int, resource, const struct rlimit64 __user *, new_rlim, struct rlimit64 __user *, old_rlim);
 COMPAT_SYSCALL_WRAP5(name_to_handle_at, int, dfd, const char __user *, name, struct file_handle __user *, handle, int __user *, mnt_id, int, flag);
diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c
index 36f5d52775a9..9a60bd4d3c49 100644
--- a/drivers/misc/kgdbts.c
+++ b/drivers/misc/kgdbts.c
@@ -220,7 +220,7 @@ static unsigned long lookup_addr(char *arg)
 	else if (!strcmp(arg, "sys_open"))
 		addr = (unsigned long)do_sys_open;
 	else if (!strcmp(arg, "do_fork"))
-		addr = (unsigned long)do_fork;
+		addr = (unsigned long)_do_fork;
 	else if (!strcmp(arg, "hw_break_val"))
 		addr = (unsigned long)&hw_break_val;
 	addr = (unsigned long) dereference_function_descriptor((void *)addr);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6633e83e608a..93ed0b682adb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2556,8 +2556,22 @@ extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode);
 /* Remove the current tasks stale references to the old mm_struct */
 extern void mm_release(struct task_struct *, struct mm_struct *);
 
+#ifdef CONFIG_HAVE_COPY_THREAD_TLS
+extern int copy_thread_tls(unsigned long, unsigned long, unsigned long,
+			struct task_struct *, unsigned long);
+#else
 extern int copy_thread(unsigned long, unsigned long, unsigned long,
 			struct task_struct *);
+
+/* Architectures that haven't opted into copy_thread_tls get the tls argument
+ * via pt_regs, so ignore the tls argument passed via C. */
+static inline int copy_thread_tls(
+		unsigned long clone_flags, unsigned long sp, unsigned long arg,
+		struct task_struct *p, unsigned long tls)
+{
+	return copy_thread(clone_flags, sp, arg, p);
+}
+#endif
 extern void flush_thread(void);
 extern void exit_thread(void);
 
@@ -2576,6 +2590,7 @@ extern int do_execveat(int, struct filename *,
 		       const char __user * const __user *,
 		       const char __user * const __user *,
 		       int);
+extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long);
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 76d1e38aabe1..bb51becf23f8 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -827,15 +827,15 @@ asmlinkage long sys_syncfs(int fd);
 asmlinkage long sys_fork(void);
 asmlinkage long sys_vfork(void);
 #ifdef CONFIG_CLONE_BACKWARDS
-asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, int,
+asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, unsigned long,
 	       int __user *);
 #else
 #ifdef CONFIG_CLONE_BACKWARDS3
 asmlinkage long sys_clone(unsigned long, unsigned long, int, int __user *,
-			  int __user *, int);
+			  int __user *, unsigned long);
 #else
 asmlinkage long sys_clone(unsigned long, unsigned long, int __user *,
-	       int __user *, int);
+	       int __user *, unsigned long);
 #endif
 #endif
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 0bb88b555550..4c95cb34243c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1238,7 +1238,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 					unsigned long stack_size,
 					int __user *child_tidptr,
 					struct pid *pid,
-					int trace)
+					int trace,
+					unsigned long tls)
 {
 	int retval;
 	struct task_struct *p;
@@ -1447,7 +1448,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	retval = copy_io(clone_flags, p);
 	if (retval)
 		goto bad_fork_cleanup_namespaces;
-	retval = copy_thread(clone_flags, stack_start, stack_size, p);
+	retval = copy_thread_tls(clone_flags, stack_start, stack_size, p, tls);
 	if (retval)
 		goto bad_fork_cleanup_io;
 
@@ -1659,7 +1660,7 @@ static inline void init_idle_pids(struct pid_link *links)
 struct task_struct *fork_idle(int cpu)
 {
 	struct task_struct *task;
-	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0);
+	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0);
 	if (!IS_ERR(task)) {
 		init_idle_pids(task->pids);
 		init_idle(task, cpu);
@@ -1674,11 +1675,12 @@ struct task_struct *fork_idle(int cpu)
  * It copies the process, and if successful kick-starts
  * it and waits for it to finish using the VM if required.
  */
-long do_fork(unsigned long clone_flags,
+long _do_fork(unsigned long clone_flags,
 	      unsigned long stack_start,
 	      unsigned long stack_size,
 	      int __user *parent_tidptr,
-	      int __user *child_tidptr)
+	      int __user *child_tidptr,
+	      unsigned long tls)
 {
 	struct task_struct *p;
 	int trace = 0;
@@ -1703,7 +1705,7 @@ long do_fork(unsigned long clone_flags,
 	}
 
 	p = copy_process(clone_flags, stack_start, stack_size,
-			 child_tidptr, NULL, trace);
+			 child_tidptr, NULL, trace, tls);
 	/*
 	 * Do this prior waking up the new thread - the thread pointer
 	 * might get invalid after that point, if the thread exits quickly.
@@ -1744,20 +1746,34 @@ long do_fork(unsigned long clone_flags,
 	return nr;
 }
 
+#ifndef CONFIG_HAVE_COPY_THREAD_TLS
+/* For compatibility with architectures that call do_fork directly rather than
+ * using the syscall entry points below. */
+long do_fork(unsigned long clone_flags,
+	      unsigned long stack_start,
+	      unsigned long stack_size,
+	      int __user *parent_tidptr,
+	      int __user *child_tidptr)
+{
+	return _do_fork(clone_flags, stack_start, stack_size,
+			parent_tidptr, child_tidptr, 0);
+}
+#endif
+
 /*
  * Create a kernel thread.
  */
 pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 {
-	return do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn,
-		(unsigned long)arg, NULL, NULL);
+	return _do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn,
+		(unsigned long)arg, NULL, NULL, 0);
 }
 
 #ifdef __ARCH_WANT_SYS_FORK
 SYSCALL_DEFINE0(fork)
 {
 #ifdef CONFIG_MMU
-	return do_fork(SIGCHLD, 0, 0, NULL, NULL);
+	return _do_fork(SIGCHLD, 0, 0, NULL, NULL, 0);
 #else
 	/* can not support in nommu mode */
 	return -EINVAL;
@@ -1768,8 +1784,8 @@ SYSCALL_DEFINE0(fork)
 #ifdef __ARCH_WANT_SYS_VFORK
 SYSCALL_DEFINE0(vfork)
 {
-	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0,
-			0, NULL, NULL);
+	return _do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0,
+			0, NULL, NULL, 0);
 }
 #endif
 
@@ -1777,27 +1793,27 @@ SYSCALL_DEFINE0(vfork)
 #ifdef CONFIG_CLONE_BACKWARDS
 SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 		 int __user *, parent_tidptr,
-		 int, tls_val,
+		 unsigned long, tls,
 		 int __user *, child_tidptr)
 #elif defined(CONFIG_CLONE_BACKWARDS2)
 SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags,
 		 int __user *, parent_tidptr,
 		 int __user *, child_tidptr,
-		 int, tls_val)
+		 unsigned long, tls)
 #elif defined(CONFIG_CLONE_BACKWARDS3)
 SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp,
 		int, stack_size,
 		int __user *, parent_tidptr,
 		int __user *, child_tidptr,
-		int, tls_val)
+		unsigned long, tls)
 #else
 SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 		 int __user *, parent_tidptr,
 		 int __user *, child_tidptr,
-		 int, tls_val)
+		 unsigned long, tls)
 #endif
 {
-	return do_fork(clone_flags, newsp, 0, parent_tidptr, child_tidptr);
+	return _do_fork(clone_flags, newsp, 0, parent_tidptr, child_tidptr, tls);
 }
 #endif