Merge tag 'clone3-tls-v5.5-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull thread fixes from Christian Brauner:
 "This contains a series of patches to fix CLONE_SETTLS when used with
  clone3().

  The clone3() syscall passes the tls argument through struct clone_args
  instead of a register. This means, all architectures that do not
  implement copy_thread_tls() but still support CLONE_SETTLS via
  copy_thread() expecting the tls to be located in a register argument
  based on clone() are currently unfortunately broken. Their tls value
  will be garbage.

  The patch series fixes this on all architectures that currently define
  __ARCH_WANT_SYS_CLONE3. It also adds a compile-time check to ensure
  that any architecture that enables clone3() in the future is forced to
  also implement copy_thread_tls().

  My ultimate goal is to get rid of the copy_thread()/copy_thread_tls()
  split and just have copy_thread_tls() at some point in the not too
  distant future (Maybe even renaming copy_thread_tls() back to simply
  copy_thread() once the old function is ripped from all arches). This
  is dependent now on all arches supporting clone3().

  While all relevant arches do that now there are still four missing:
  ia64, m68k, sh and sparc. They have the system call reserved, but not
  implemented. Once they all implement clone3() we can get rid of
  ARCH_WANT_SYS_CLONE3 and HAVE_COPY_THREAD_TLS.

  This series also includes a minor fix for the arm64 uapi headers which
  caused __NR_clone3 to be missing from the exported user headers.

  Unfortunately the series came in a little late especially given that
  it touches a range of architectures. Due to the holidays not all arch
  maintainers responded in time probably due to their backlog. Will and
  Arnd have thankfully acked the arm specific changes.

  Given that the changes are straightforward and rather minimal combined
  with the fact the that clone3() with CLONE_SETTLS is broken I decided
  to send them post rc3 nonetheless"

* tag 'clone3-tls-v5.5-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
  um: Implement copy_thread_tls
  clone3: ensure copy_thread_tls is implemented
  xtensa: Implement copy_thread_tls
  riscv: Implement copy_thread_tls
  parisc: Implement copy_thread_tls
  arm: Implement copy_thread_tls
  arm64: Implement copy_thread_tls
  arm64: Move __ARCH_WANT_SYS_CLONE3 definition to uapi headers

17 files changed, 35 insertions, 32 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index ba75e3661a41..96dab76da3b3 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -72,6 +72,7 @@ config ARM
 	select HAVE_ARM_SMCCC if CPU_V7
 	select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32
 	select HAVE_CONTEXT_TRACKING
+	select HAVE_COPY_THREAD_TLS
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS if MMU
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index cea1c27c29cb..46e478fb5ea2 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -226,8 +226,8 @@ void release_thread(struct task_struct *dead_task)
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
 int
-copy_thread(unsigned long clone_flags, unsigned long stack_start,
-	    unsigned long stk_sz, struct task_struct *p)
+copy_thread_tls(unsigned long clone_flags, unsigned long stack_start,
+	    unsigned long stk_sz, struct task_struct *p, unsigned long tls)
 {
 	struct thread_info *thread = task_thread_info(p);
 	struct pt_regs *childregs = task_pt_regs(p);
@@ -261,7 +261,7 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	clear_ptrace_hw_breakpoint(p);
 
 	if (clone_flags & CLONE_SETTLS)
-		thread->tp_value[0] = childregs->ARM_r3;
+		thread->tp_value[0] = tls;
 	thread->tp_value[1] = get_tpuser();
 
 	thread_notify(THREAD_NOTIFY_COPY, thread);
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index b1b4476ddb83..e688dfad0b72 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -138,6 +138,7 @@ config ARM64
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_CMPXCHG_LOCAL
 	select HAVE_CONTEXT_TRACKING
+	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 2629a68b8724..5af82587909e 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -42,7 +42,6 @@
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
-#define __ARCH_WANT_SYS_CLONE3
 
 #ifndef __COMPAT_SYSCALL_NR
 #include <uapi/asm/unistd.h>
diff --git a/arch/arm64/include/uapi/asm/unistd.h b/arch/arm64/include/uapi/asm/unistd.h
index 4703d218663a..f83a70e07df8 100644
--- a/arch/arm64/include/uapi/asm/unistd.h
+++ b/arch/arm64/include/uapi/asm/unistd.h
@@ -19,5 +19,6 @@
 #define __ARCH_WANT_NEW_STAT
 #define __ARCH_WANT_SET_GET_RLIMIT
 #define __ARCH_WANT_TIME32_SYSCALLS
+#define __ARCH_WANT_SYS_CLONE3
 
 #include <asm-generic/unistd.h>
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 71f788cd2b18..d54586d5b031 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -360,8 +360,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 asmlinkage void ret_from_fork(void) asm("ret_from_fork");
 
-int copy_thread(unsigned long clone_flags, unsigned long stack_start,
-		unsigned long stk_sz, struct task_struct *p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long stack_start,
+		unsigned long stk_sz, struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 
@@ -394,11 +394,11 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 		}
 
 		/*
-		 * If a TLS pointer was passed to clone (4th argument), use it
-		 * for the new thread.
+		 * If a TLS pointer was passed to clone, use it for the new
+		 * thread.
 		 */
 		if (clone_flags & CLONE_SETTLS)
-			p->thread.uw.tp_value = childregs->regs[3];
+			p->thread.uw.tp_value = tls;
 	} else {
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->pstate = PSR_MODE_EL1h;
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index b16237c95ea3..0c29d6cb2c8d 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -62,6 +62,7 @@ config PARISC
 	select HAVE_FTRACE_MCOUNT_RECORD if HAVE_DYNAMIC_FTRACE
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
+	select HAVE_COPY_THREAD_TLS
 
 	help
 	  The PA-RISC microprocessor is designed by Hewlett-Packard and used
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index ecc5c2771208..230a6422b99f 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -208,8 +208,8 @@ arch_initcall(parisc_idle_init);
  * Copy architecture-specific thread state
  */
 int
-copy_thread(unsigned long clone_flags, unsigned long usp,
-	    unsigned long kthread_arg, struct task_struct *p)
+copy_thread_tls(unsigned long clone_flags, unsigned long usp,
+	    unsigned long kthread_arg, struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *cregs = &(p->thread.regs);
 	void *stack = task_stack_page(p);
@@ -254,9 +254,9 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
 		cregs->ksp = (unsigned long)stack + THREAD_SZ_ALGN + FRAME_SIZE;
 		cregs->kpc = (unsigned long) &child_return;
 
-		/* Setup thread TLS area from the 4th parameter in clone */
+		/* Setup thread TLS area */
 		if (clone_flags & CLONE_SETTLS)
-			cregs->cr27 = cregs->gr[23];
+			cregs->cr27 = tls;
 	}
 
 	return 0;
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index a31169b02ec0..fa7dc03459e7 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -65,6 +65,7 @@ config RISCV
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select ARCH_HAS_GCOV_PROFILE_ALL
+	select HAVE_COPY_THREAD_TLS
 
 config ARCH_MMAP_RND_BITS_MIN
 	default 18 if 64BIT
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 95a3031e5c7c..817cf7b0974c 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -99,8 +99,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	return 0;
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long usp,
-	unsigned long arg, struct task_struct *p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
+	unsigned long arg, struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 
@@ -121,7 +121,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 		if (usp) /* User fork */
 			childregs->sp = usp;
 		if (clone_flags & CLONE_SETTLS)
-			childregs->tp = childregs->a5;
+			childregs->tp = tls;
 		childregs->a0 = 0; /* Return value of fork() */
 		p->thread.ra = (unsigned long)ret_from_fork;
 	}
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index 2a6d04fcb3e9..6f0edd0c0220 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -14,6 +14,7 @@ config UML
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DEBUG_BUGVERBOSE
+	select HAVE_COPY_THREAD_TLS
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES
 	select GENERIC_CLOCKEVENTS
diff --git a/arch/um/include/asm/ptrace-generic.h b/arch/um/include/asm/ptrace-generic.h
index 81c647ef9c6c..adf91ef553ae 100644
--- a/arch/um/include/asm/ptrace-generic.h
+++ b/arch/um/include/asm/ptrace-generic.h
@@ -36,7 +36,7 @@ extern long subarch_ptrace(struct task_struct *child, long request,
 extern unsigned long getreg(struct task_struct *child, int regno);
 extern int putreg(struct task_struct *child, int regno, unsigned long value);
 
-extern int arch_copy_tls(struct task_struct *new);
+extern int arch_set_tls(struct task_struct *new, unsigned long tls);
 extern void clear_flushed_tls(struct task_struct *task);
 extern int syscall_trace_enter(struct pt_regs *regs);
 extern void syscall_trace_leave(struct pt_regs *regs);
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 263a8f069133..17045e7211bf 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -153,8 +153,8 @@ void fork_handler(void)
 	userspace(&current->thread.regs.regs, current_thread_info()->aux_fp_regs);
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long sp,
-		unsigned long arg, struct task_struct * p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
+		unsigned long arg, struct task_struct * p, unsigned long tls)
 {
 	void (*handler)(void);
 	int kthread = current->flags & PF_KTHREAD;
@@ -188,7 +188,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 		 * Set a new TLS for the child thread?
 		 */
 		if (clone_flags & CLONE_SETTLS)
-			ret = arch_copy_tls(p);
+			ret = arch_set_tls(p, tls);
 	}
 
 	return ret;
diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c
index 5bd949da7a4a..ac8eee093f9c 100644
--- a/arch/x86/um/tls_32.c
+++ b/arch/x86/um/tls_32.c
@@ -215,14 +215,12 @@ static int set_tls_entry(struct task_struct* task, struct user_desc *info,
 	return 0;
 }
 
-int arch_copy_tls(struct task_struct *new)
+int arch_set_tls(struct task_struct *new, unsigned long tls)
 {
 	struct user_desc info;
 	int idx, ret = -EFAULT;
 
-	if (copy_from_user(&info,
-			   (void __user *) UPT_SI(&new->thread.regs.regs),
-			   sizeof(info)))
+	if (copy_from_user(&info, (void __user *) tls, sizeof(info)))
 		goto out;
 
 	ret = -EINVAL;
diff --git a/arch/x86/um/tls_64.c b/arch/x86/um/tls_64.c
index 3a621e0d3925..ebd3855d9b13 100644
--- a/arch/x86/um/tls_64.c
+++ b/arch/x86/um/tls_64.c
@@ -6,14 +6,13 @@ void clear_flushed_tls(struct task_struct *task)
 {
 }
 
-int arch_copy_tls(struct task_struct *t)
+int arch_set_tls(struct task_struct *t, unsigned long tls)
 {
 	/*
 	 * If CLONE_SETTLS is set, we need to save the thread id
-	 * (which is argument 5, child_tid, of clone) so it can be set
-	 * during context switches.
+	 * so it can be set during context switches.
 	 */
-	t->thread.arch.fs = t->thread.regs.regs.gp[R8 / sizeof(long)];
+	t->thread.arch.fs = tls;
 
 	return 0;
 }
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 4a3fa295d8fe..296c5324dace 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -24,6 +24,7 @@ config XTENSA
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
 	select HAVE_ARCH_KASAN if MMU && !XIP_KERNEL
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_EXIT_THREAD
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index 9e1c49134c07..3edecc41ef8c 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -202,8 +202,9 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
  * involved.  Much simpler to just not copy those live frames across.
  */
 
-int copy_thread(unsigned long clone_flags, unsigned long usp_thread_fn,
-		unsigned long thread_fn_arg, struct task_struct *p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long usp_thread_fn,
+		unsigned long thread_fn_arg, struct task_struct *p,
+		unsigned long tls)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
 
@@ -266,9 +267,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp_thread_fn,
 
 		childregs->syscall = regs->syscall;
 
-		/* The thread pointer is passed in the '4th argument' (= a5) */
 		if (clone_flags & CLONE_SETTLS)
-			childregs->threadptr = childregs->areg[5];
+			childregs->threadptr = tls;
 	} else {
 		p->thread.ra = MAKE_RA_FOR_CALL(
 				(unsigned long)ret_from_kernel_thread, 1);