diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index ba75e3661a4159afa45ac15516db9e16d2fdae29..96dab76da3b3962b8b22899516f47dd3274dcbca 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 cea1c27c29cba2d81aefe19b5b94f94d55b87c85..46e478fb5ea203a7a42650ce4233d801db0c4277 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 b1b4476ddb834ba64a8ba93e55e88d3a7282fed1..e688dfad0b726284e49aec814f84a68d15b6176e 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 2629a68b87244facd78a6ad5e9d4b18ca6ac18ad..5af82587909ef9931d4201f2a2850feb6d25bdcf 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 4703d218663a2ad81e7c8d4fd0749bed8199ef4f..f83a70e07df85ca5029a1e91cde93b8e0dd9fb7e 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 71f788cd2b18772629c4627be979f75753253d08..d54586d5b031f874e7fa70814cd618ac3c16ceca 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 b16237c95ea33bd1fb75f50b91fbd6ae053b1687..0c29d6cb2c8dfd1667e705710475b003fcad1a85 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 ecc5c277120871efe35a6cebc6158397790d1c0e..230a6422b99f369c52a5d90d113a9a9ffd94b77c 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 a31169b02ec060757455b46ece6fde94c2c60beb..fa7dc03459e7f1e7168e9dbef0a3ecf14dae175e 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 95a3031e5c7c9dcfdebaa06ba20f8da31424f905..817cf7b0974ced30d75d536b192b73b4e3c25bdf 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 2a6d04fcb3e91c7e191cec43b7d1e2d6d832819b..6f0edd0c0220f40dac6fd3c89309458e9f0981e6 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 81c647ef9c6c8df98ae917178318a61647d9391e..adf91ef553ae91f215dcf1c457fcf258e8065423 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 263a8f06913341d1b0a9d013d89f12971e928391..17045e7211bfd461d9a055fcee9b0cb1f3ac6fed 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 5bd949da7a4a5deb659f19e849dcd6036a2843ac..ac8eee093f9cd0fa112fe89e945202eb60203a84 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 3a621e0d39253aa30a7d5eadb523cd4a2e1315cb..ebd3855d9b132379b7065222316a948e06b2b72e 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 4a3fa295d8fed4a9427ea8c1eecf9832040d766a..296c5324dacef5cbdf3c003b151c8e34d529ad54 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 9e1c49134c07eca6a172e4b0f43e5ffeeef61f50..3edecc41ef8c36ffefb6a6b6ac1be62c1d9a296d 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);
diff --git a/kernel/fork.c b/kernel/fork.c
index 2508a4f238a3f3b2e41dd78502a5a653f57c221b..080809560072550279595ae05567b4a64cced9d7 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2578,6 +2578,16 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 #endif
 
 #ifdef __ARCH_WANT_SYS_CLONE3
+
+/*
+ * copy_thread implementations handle CLONE_SETTLS by reading the TLS value from
+ * the registers containing the syscall arguments for clone. This doesn't work
+ * with clone3 since the TLS value is passed in clone_args instead.
+ */
+#ifndef CONFIG_HAVE_COPY_THREAD_TLS
+#error clone3 requires copy_thread_tls support in arch
+#endif
+
 noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 					      struct clone_args __user *uargs,
 					      size_t usize)