Merge branch 'exit-cleanups-for-v5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull exit cleanups from Eric Biederman:
 "While looking at some issues related to the exit path in the kernel I
  found several instances where the code is not using the existing
  abstractions properly.

  This set of changes introduces force_fatal_sig a way of sending a
  signal and not allowing it to be caught, and corrects the misuse of
  the existing abstractions that I found.

  A lot of the misuse of the existing abstractions are silly things such
  as doing something after calling a no return function, rolling BUG by
  hand, doing more work than necessary to terminate a kernel thread, or
  calling do_exit(SIGKILL) instead of calling force_sig(SIGKILL).

  In the review a deficiency in force_fatal_sig and force_sig_seccomp
  where ptrace or sigaction could prevent the delivery of the signal was
  found. I have added a change that adds SA_IMMUTABLE to change that
  makes it impossible to interrupt the delivery of those signals, and
  allows backporting to fix force_sig_seccomp

  And Arnd found an issue where a function passed to kthread_run had the
  wrong prototype, and after my cleanup was failing to build."

* 'exit-cleanups-for-v5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (23 commits)
  soc: ti: fix wkup_m3_rproc_boot_thread return type
  signal: Add SA_IMMUTABLE to ensure forced siganls do not get changed
  signal: Replace force_sigsegv(SIGSEGV) with force_fatal_sig(SIGSEGV)
  exit/r8188eu: Replace the macro thread_exit with a simple return 0
  exit/rtl8712: Replace the macro thread_exit with a simple return 0
  exit/rtl8723bs: Replace the macro thread_exit with a simple return 0
  signal/x86: In emulate_vsyscall force a signal instead of calling do_exit
  signal/sparc32: In setup_rt_frame and setup_fram use force_fatal_sig
  signal/sparc32: Exit with a fatal signal when try_to_clear_window_buffer fails
  exit/syscall_user_dispatch: Send ordinary signals on failure
  signal: Implement force_fatal_sig
  exit/kthread: Have kernel threads return instead of calling do_exit
  signal/s390: Use force_sigsegv in default_trap_handler
  signal/vm86_32: Properly send SIGSEGV when the vm86 state cannot be saved.
  signal/vm86_32: Replace open coded BUG_ON with an actual BUG_ON
  signal/sparc: In setup_tsb_params convert open coded BUG into BUG
  signal/powerpc: On swapcontext failure force SIGSEGV
  signal/sh: Use force_sig(SIGKILL) instead of do_group_exit(SIGKILL)
  signal/mips: Update (_save|_restore)_fp_context to fail with -EFAULT
  signal/sparc32: Remove unreachable do_exit in do_sparc_fault
  ...

47 files changed, 97 insertions, 96 deletions

diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 3793876f42d9..8e90052f6f05 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -294,7 +294,7 @@ int elf_check_arch(const struct elf32_hdr *x)
 	eflags = x->e_flags;
 	if ((eflags & EF_ARC_OSABI_MSK) != EF_ARC_OSABI_CURRENT) {
 		pr_err("ABI mismatch - you need newer toolchain\n");
-		force_sigsegv(SIGSEGV);
+		force_fatal_sig(SIGSEGV);
 		return 0;
 	}
 
diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c
index 9718ce94cc84..99058a6da956 100644
--- a/arch/m68k/kernel/traps.c
+++ b/arch/m68k/kernel/traps.c
@@ -1145,7 +1145,7 @@ asmlinkage void set_esp0(unsigned long ssp)
  */
 asmlinkage void fpsp040_die(void)
 {
-	force_sigsegv(SIGSEGV);
+	force_fatal_sig(SIGSEGV);
 }
 
 #ifdef CONFIG_M68KFPU_EMU
diff --git a/arch/mips/kernel/r2300_fpu.S b/arch/mips/kernel/r2300_fpu.S
index 12e58053544f..cbf6db98cfb3 100644
--- a/arch/mips/kernel/r2300_fpu.S
+++ b/arch/mips/kernel/r2300_fpu.S
@@ -29,8 +29,8 @@
 #define EX2(a,b)						\
 9:	a,##b;							\
 	.section __ex_table,"a";				\
-	PTR	9b,bad_stack;					\
-	PTR	9b+4,bad_stack;					\
+	PTR	9b,fault;					\
+	PTR	9b+4,fault;					\
 	.previous
 
 	.set	mips1
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index 2afa3eef486a..5512cd586e6e 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -240,12 +240,3 @@ SYSCALL_DEFINE3(cachectl, char *, addr, int, nbytes, int, op)
 {
 	return -ENOSYS;
 }
-
-/*
- * If we ever come here the user sp is bad.  Zap the process right away.
- * Due to the bad stack signaling wouldn't work.
- */
-asmlinkage void bad_stack(void)
-{
-	do_exit(SIGSEGV);
-}
diff --git a/arch/nds32/kernel/traps.c b/arch/nds32/kernel/traps.c
index f06421c645af..ca75d475eda4 100644
--- a/arch/nds32/kernel/traps.c
+++ b/arch/nds32/kernel/traps.c
@@ -118,7 +118,7 @@ DEFINE_SPINLOCK(die_lock);
 /*
  * This function is protected against re-entrancy.
  */
-void die(const char *str, struct pt_regs *regs, int err)
+void __noreturn die(const char *str, struct pt_regs *regs, int err)
 {
 	struct task_struct *tsk = current;
 	static int die_counter;
diff --git a/arch/nds32/mm/fault.c b/arch/nds32/mm/fault.c
index f02524eb6d56..1d139b117168 100644
--- a/arch/nds32/mm/fault.c
+++ b/arch/nds32/mm/fault.c
@@ -13,7 +13,7 @@
 
 #include <asm/tlbflush.h>
 
-extern void die(const char *str, struct pt_regs *regs, long err);
+extern void __noreturn die(const char *str, struct pt_regs *regs, long err);
 
 /*
  * This is useful to dump out the page tables associated with
@@ -299,10 +299,6 @@ no_context:
 
 	show_pte(mm, addr);
 	die("Oops", regs, error_code);
-	bust_spinlocks(0);
-	do_exit(SIGKILL);
-
-	return;
 
 	/*
 	 * We ran out of memory, or some other thing happened to us that made
diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c
index aa1e709405ac..0898cb159fac 100644
--- a/arch/openrisc/kernel/traps.c
+++ b/arch/openrisc/kernel/traps.c
@@ -197,7 +197,7 @@ void nommu_dump_state(struct pt_regs *regs,
 }
 
 /* This is normally the 'Oops' routine */
-void die(const char *str, struct pt_regs *regs, long err)
+void __noreturn die(const char *str, struct pt_regs *regs, long err)
 {
 
 	console_verbose();
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index c730d1a51686..f0fa6394a58e 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -32,7 +32,7 @@ unsigned long pte_errors;	/* updated by do_page_fault() */
  */
 volatile pgd_t *current_pgd[NR_CPUS];
 
-extern void die(char *, struct pt_regs *, long);
+extern void __noreturn die(char *, struct pt_regs *, long);
 
 /*
  * This routine handles page faults.  It determines the address,
@@ -248,8 +248,6 @@ no_context:
 
 	die("Oops", regs, write_acc);
 
-	do_exit(SIGKILL);
-
 	/*
 	 * We ran out of memory, or some other thing happened to us that made
 	 * us unable to handle the page fault gracefully.
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 38c3eae40c14..00a9c9cd6d42 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -1062,8 +1062,10 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
 	 * or if another thread unmaps the region containing the context.
 	 * We kill the task with a SIGSEGV in this situation.
 	 */
-	if (do_setcontext(new_ctx, regs, 0))
-		do_exit(SIGSEGV);
+	if (do_setcontext(new_ctx, regs, 0)) {
+		force_fatal_sig(SIGSEGV);
+		return -EFAULT;
+	}
 
 	set_thread_flag(TIF_RESTOREALL);
 	return 0;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 9f471b4a11e3..ef518535d436 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -703,15 +703,18 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
 	 * We kill the task with a SIGSEGV in this situation.
 	 */
 
-	if (__get_user_sigset(&set, &new_ctx->uc_sigmask))
-		do_exit(SIGSEGV);
+	if (__get_user_sigset(&set, &new_ctx->uc_sigmask)) {
+		force_fatal_sig(SIGSEGV);
+		return -EFAULT;
+	}
 	set_current_blocked(&set);
 
 	if (!user_read_access_begin(new_ctx, ctx_size))
 		return -EFAULT;
 	if (__unsafe_restore_sigcontext(current, NULL, 0, &new_ctx->uc_mcontext)) {
 		user_read_access_end();
-		do_exit(SIGSEGV);
+		force_fatal_sig(SIGSEGV);
+		return -EFAULT;
 	}
 	user_read_access_end();
 
diff --git a/arch/s390/include/asm/kdebug.h b/arch/s390/include/asm/kdebug.h
index d5327f064799..4377238e4752 100644
--- a/arch/s390/include/asm/kdebug.h
+++ b/arch/s390/include/asm/kdebug.h
@@ -23,6 +23,6 @@ enum die_val {
 	DIE_NMI_IPI,
 };
 
-extern void die(struct pt_regs *, const char *);
+extern void __noreturn die(struct pt_regs *, const char *);
 
 #endif
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 85f326e258df..0681c55e831d 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -192,7 +192,7 @@ void show_regs(struct pt_regs *regs)
 
 static DEFINE_SPINLOCK(die_lock);
 
-void die(struct pt_regs *regs, const char *str)
+void __noreturn die(struct pt_regs *regs, const char *str)
 {
 	static int die_counter;
 
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 6c6f7dcce1a5..035705c9f23e 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -84,7 +84,7 @@ static void default_trap_handler(struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
 		report_user_fault(regs, SIGSEGV, 0);
-		do_exit(SIGSEGV);
+		force_fatal_sig(SIGSEGV);
 	} else
 		die(regs, "Unknown program exception");
 }
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 212632d57db9..d30f5986fa85 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -260,7 +260,6 @@ static noinline void do_no_context(struct pt_regs *regs)
 		       " in virtual user address space\n");
 	dump_fault_info(regs);
 	die(regs, "Oops");
-	do_exit(SIGKILL);
 }
 
 static noinline void do_low_address(struct pt_regs *regs)
@@ -270,7 +269,6 @@ static noinline void do_low_address(struct pt_regs *regs)
 	if (regs->psw.mask & PSW_MASK_PSTATE) {
 		/* Low-address protection hit in user mode 'cannot happen'. */
 		die (regs, "Low-address protection");
-		do_exit(SIGKILL);
 	}
 
 	do_no_context(regs);
diff --git a/arch/sh/kernel/cpu/fpu.c b/arch/sh/kernel/cpu/fpu.c
index ae354a2931e7..fd6db0ab1928 100644
--- a/arch/sh/kernel/cpu/fpu.c
+++ b/arch/sh/kernel/cpu/fpu.c
@@ -62,18 +62,20 @@ void fpu_state_restore(struct pt_regs *regs)
 	}
 
 	if (!tsk_used_math(tsk)) {
-		local_irq_enable();
+		int ret;
 		/*
 		 * does a slab alloc which can sleep
 		 */
-		if (init_fpu(tsk)) {
+		local_irq_enable();
+		ret = init_fpu(tsk);
+		local_irq_disable();
+		if (ret) {
 			/*
 			 * ran out of memory!
 			 */
-			do_group_exit(SIGKILL);
+			force_sig(SIGKILL);
 			return;
 		}
-		local_irq_disable();
 	}
 
 	grab_fpu(regs);
diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c
index e76b22157099..cbe3201d4f21 100644
--- a/arch/sh/kernel/traps.c
+++ b/arch/sh/kernel/traps.c
@@ -20,7 +20,7 @@
 
 static DEFINE_SPINLOCK(die_lock);
 
-void die(const char *str, struct pt_regs *regs, long err)
+void __noreturn die(const char *str, struct pt_regs *regs, long err)
 {
 	static int die_counter;
 
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 88a1f453d73e..1e1aa75df3ca 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -238,8 +238,6 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 	show_fault_oops(regs, address);
 
 	die("Oops", regs, error_code);
-	bust_spinlocks(0);
-	do_exit(SIGKILL);
 }
 
 static void
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 02f3ad55dfe3..cd677bc564a7 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -244,7 +244,7 @@ static int setup_frame(struct ksignal *ksig, struct pt_regs *regs,
 		get_sigframe(ksig, regs, sigframe_size);
 
 	if (invalid_frame_pointer(sf, sigframe_size)) {
-		do_exit(SIGILL);
+		force_fatal_sig(SIGILL);
 		return -EINVAL;
 	}
 
@@ -336,7 +336,7 @@ static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs,
 	sf = (struct rt_signal_frame __user *)
 		get_sigframe(ksig, regs, sigframe_size);
 	if (invalid_frame_pointer(sf, sigframe_size)) {
-		do_exit(SIGILL);
+		force_fatal_sig(SIGILL);
 		return -EINVAL;
 	}
 
diff --git a/arch/sparc/kernel/windows.c b/arch/sparc/kernel/windows.c
index 69a6ba6e9293..bbbd40cc6b28 100644
--- a/arch/sparc/kernel/windows.c
+++ b/arch/sparc/kernel/windows.c
@@ -121,8 +121,10 @@ void try_to_clear_window_buffer(struct pt_regs *regs, int who)
 
 		if ((sp & 7) ||
 		    copy_to_user((char __user *) sp, &tp->reg_window[window],
-				 sizeof(struct reg_window32)))
-			do_exit(SIGILL);
+				 sizeof(struct reg_window32))) {
+			force_fatal_sig(SIGILL);
+			return;
+		}
 	}
 	tp->w_saved = 0;
 }
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index fa858626b85b..90dc4ae315c8 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -248,7 +248,6 @@ no_context:
 	}
 
 	unhandled_fault(address, tsk, regs);
-	do_exit(SIGKILL);
 
 /*
  * We ran out of memory, or some other thing happened to us that made
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 0dce4b7ff73e..912205787161 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -266,7 +266,7 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign
 	default:
 		printk(KERN_ERR "TSB[%s:%d]: Impossible TSB size %lu, killing process.\n",
 		       current->comm, current->pid, tsb_bytes);
-		do_exit(SIGSEGV);
+		BUG();
 	}
 	tte |= pte_sz_bits(page_sz);
 
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 3198c4767387..c32efb09db21 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -158,7 +158,7 @@ static void bad_segv(struct faultinfo fi, unsigned long ip)
 
 void fatal_sigsegv(void)
 {
-	force_sigsegv(SIGSEGV);
+	force_fatal_sig(SIGSEGV);
 	do_signal(&current->thread.regs);
 	/*
 	 * This is to tell gcc that we're not returning - do_signal
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 1b40b9297083..0b6b277ee050 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -226,7 +226,8 @@ bool emulate_vsyscall(unsigned long error_code,
 	if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) {
 		warn_bad_vsyscall(KERN_DEBUG, regs,
 				  "seccomp tried to change syscall nr or ip");
-		do_exit(SIGSYS);
+		force_fatal_sig(SIGSYS);
+		return true;
 	}
 	regs->orig_ax = -1;
 	if (tmp)
diff --git a/arch/x86/kernel/doublefault_32.c b/arch/x86/kernel/doublefault_32.c
index d1d49e3d536b..3b58d8703094 100644
--- a/arch/x86/kernel/doublefault_32.c
+++ b/arch/x86/kernel/doublefault_32.c
@@ -77,9 +77,6 @@ asmlinkage noinstr void __noreturn doublefault_shim(void)
 	 * some way to reconstruct CR3.  We could make a credible guess based
 	 * on cpu_tlbstate, but that would be racy and would not account for
 	 * PTI.
-	 *
-	 * Instead, don't bother.  We can return through
-	 * rewind_stack_do_exit() instead.
 	 */
 	panic("cannot return from double fault\n");
 }
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index e5a7a10a0164..f14f69d7aa3c 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -106,10 +106,8 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 	 */
 	local_irq_enable();
 
-	if (!vm86 || !vm86->user_vm86) {
-		pr_alert("no user_vm86: BAD\n");
-		do_exit(SIGSEGV);
-	}
+	BUG_ON(!vm86 || !vm86->user_vm86);
+
 	set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | vm86->veflags_mask);
 	user = vm86->user_vm86;
 
@@ -142,6 +140,7 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 
 	user_access_end();
 
+exit_vm86:
 	preempt_disable();
 	tsk->thread.sp0 = vm86->saved_sp0;
 	tsk->thread.sysenter_cs = __KERNEL_CS;
@@ -161,7 +160,8 @@ Efault_end:
 	user_access_end();
 Efault:
 	pr_alert("could not access userspace vm86 info\n");
-	do_exit(SIGSEGV);
+	force_fatal_sig(SIGSEGV);
+	goto exit_vm86;
 }
 
 static int do_vm86_irq_handling(int subfunction, int irqnumber);
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index 35a7d47f28cf..4b4dbeb2d612 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -527,7 +527,7 @@ void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl)
 
 DEFINE_SPINLOCK(die_lock);
 
-void die(const char * str, struct pt_regs * regs, long err)
+void __noreturn die(const char * str, struct pt_regs * regs, long err)
 {
 	static int die_counter;
 	const char *pr = "";
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 95a74890c7e9..fd6a70635962 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -238,7 +238,7 @@ bad_page_fault:
 void
 bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 {
-	extern void die(const char*, struct pt_regs*, long);
+	extern void __noreturn die(const char*, struct pt_regs*, long);
 	const struct exception_table_entry *entry;
 
 	/* Are we prepared to handle this kernel fault?  */
@@ -257,5 +257,4 @@ bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 		 "address %08lx\n pc = %08lx, ra = %08lx\n",
 		 address, regs->pc, regs->areg[0]);
 	die("Oops", regs, sig);
-	do_exit(sig);
 }
diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c
index 2a7687911c09..29c0a616b317 100644
--- a/drivers/firmware/stratix10-svc.c
+++ b/drivers/firmware/stratix10-svc.c
@@ -520,7 +520,7 @@ static int svc_normal_to_secure_thread(void *data)
  * physical address of memory block reserved by secure monitor software at
  * secure world.
  *
- * svc_normal_to_secure_shm_thread() calls do_exit() directly since it is a
+ * svc_normal_to_secure_shm_thread() terminates directly since it is a
  * standlone thread for which no one will call kthread_stop() or return when
  * 'kthread_should_stop()' is true.
  */
@@ -544,7 +544,7 @@ static int svc_normal_to_secure_shm_thread(void *data)
 	}
 
 	complete(&sh_mem->sync_complete);
-	do_exit(0);
+	return 0;
 }
 
 /**
diff --git a/drivers/soc/ti/wkup_m3_ipc.c b/drivers/soc/ti/wkup_m3_ipc.c
index 09abd17065ba..72386bd393fe 100644
--- a/drivers/soc/ti/wkup_m3_ipc.c
+++ b/drivers/soc/ti/wkup_m3_ipc.c
@@ -413,8 +413,9 @@ void wkup_m3_ipc_put(struct wkup_m3_ipc *m3_ipc)
 }
 EXPORT_SYMBOL_GPL(wkup_m3_ipc_put);
 
-static void wkup_m3_rproc_boot_thread(struct wkup_m3_ipc *m3_ipc)
+static int wkup_m3_rproc_boot_thread(void *arg)
 {
+	struct wkup_m3_ipc *m3_ipc = arg;
 	struct device *dev = m3_ipc->dev;
 	int ret;
 
@@ -426,7 +427,7 @@ static void wkup_m3_rproc_boot_thread(struct wkup_m3_ipc *m3_ipc)
 	else
 		m3_ipc_state = m3_ipc;
 
-	do_exit(0);
+	return 0;
 }
 
 static int wkup_m3_ipc_probe(struct platform_device *pdev)
@@ -500,7 +501,7 @@ static int wkup_m3_ipc_probe(struct platform_device *pdev)
 	 * can boot the wkup_m3 as soon as it's ready without holding
 	 * up kernel boot
 	 */
-	task = kthread_run((void *)wkup_m3_rproc_boot_thread, m3_ipc,
+	task = kthread_run(wkup_m3_rproc_boot_thread, m3_ipc,
 			   "wkup_m3_rproc_loader");
 
 	if (IS_ERR(task)) {
diff --git a/drivers/staging/r8188eu/core/rtw_cmd.c b/drivers/staging/r8188eu/core/rtw_cmd.c
index 5d5f25364b2f..48869a7056fd 100644
--- a/drivers/staging/r8188eu/core/rtw_cmd.c
+++ b/drivers/staging/r8188eu/core/rtw_cmd.c
@@ -323,7 +323,7 @@ post_process:
 
 	complete(&pcmdpriv->stop_cmd_thread);
 
-	thread_exit();
+	return 0;
 }
 
 /*
diff --git a/drivers/staging/r8188eu/include/osdep_service.h b/drivers/staging/r8188eu/include/osdep_service.h
index efab3a97eb46..f6f5e4581212 100644
--- a/drivers/staging/r8188eu/include/osdep_service.h
+++ b/drivers/staging/r8188eu/include/osdep_service.h
@@ -49,8 +49,6 @@ struct	__queue	{
 	spinlock_t lock;
 };
 
-#define thread_exit() complete_and_exit(NULL, 0)
-
 static inline struct list_head *get_list_head(struct __queue *queue)
 {
 	return (&(queue->queue));
diff --git a/drivers/staging/rtl8712/osdep_service.h b/drivers/staging/rtl8712/osdep_service.h
index d33ddffb7ad9..0d9bb42cbc58 100644
--- a/drivers/staging/rtl8712/osdep_service.h
+++ b/drivers/staging/rtl8712/osdep_service.h
@@ -37,7 +37,6 @@ struct	__queue	{
 
 #define _pkt struct sk_buff
 #define _buffer unsigned char
-#define thread_exit() complete_and_exit(NULL, 0)
 
 #define _init_queue(pqueue)				\
 	do {						\
diff --git a/drivers/staging/rtl8712/rtl8712_cmd.c b/drivers/staging/rtl8712/rtl8712_cmd.c
index e9294e1ed06e..2326aae6709e 100644
--- a/drivers/staging/rtl8712/rtl8712_cmd.c
+++ b/drivers/staging/rtl8712/rtl8712_cmd.c
@@ -393,7 +393,7 @@ _next:
 		r8712_free_cmd_obj(pcmd);
 	} while (1);
 	complete(&pcmdpriv->terminate_cmdthread_comp);
-	thread_exit();
+	return 0;
 }
 
 void r8712_event_handle(struct _adapter *padapter, __le32 *peventbuf)
diff --git a/drivers/staging/rtl8723bs/core/rtw_cmd.c b/drivers/staging/rtl8723bs/core/rtw_cmd.c
index 639459d52261..bd24d913b464 100644
--- a/drivers/staging/rtl8723bs/core/rtw_cmd.c
+++ b/drivers/staging/rtl8723bs/core/rtw_cmd.c
@@ -518,7 +518,7 @@ post_process:
 	complete(&pcmdpriv->terminate_cmdthread_comp);
 	atomic_set(&pcmdpriv->cmdthd_running, false);
 
-	thread_exit();
+	return 0;
 }
 
 /*
diff --git a/drivers/staging/rtl8723bs/core/rtw_xmit.c b/drivers/staging/rtl8723bs/core/rtw_xmit.c
index 46054d6a1fb5..13b8bd5ffabc 100644
--- a/drivers/staging/rtl8723bs/core/rtw_xmit.c
+++ b/drivers/staging/rtl8723bs/core/rtw_xmit.c
@@ -2500,7 +2500,7 @@ int rtw_xmit_thread(void *context)
 
 	complete(&padapter->xmitpriv.terminate_xmitthread_comp);
 
-	thread_exit();
+	return 0;
 }
 
 void rtw_sctx_init(struct submit_ctx *sctx, int timeout_ms)
diff --git a/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c b/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c
index 5f5c4719b586..7fe3df863fe1 100644
--- a/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c
+++ b/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c
@@ -435,7 +435,7 @@ int rtl8723bs_xmit_thread(void *context)
 
 	complete(&pxmitpriv->SdioXmitTerminate);
 
-	thread_exit();
+	return 0;
 }
 
 s32 rtl8723bs_mgnt_xmit(
diff --git a/drivers/staging/rtl8723bs/include/osdep_service_linux.h b/drivers/staging/rtl8723bs/include/osdep_service_linux.h
index 3492ec1efd1e..188ed7e26550 100644
--- a/drivers/staging/rtl8723bs/include/osdep_service_linux.h
+++ b/drivers/staging/rtl8723bs/include/osdep_service_linux.h
@@ -45,8 +45,6 @@
 		spinlock_t	lock;
 	};
 
-	#define thread_exit() complete_and_exit(NULL, 0)
-
 static inline struct list_head *get_next(struct list_head	*list)
 {
 	return list->next;
diff --git a/fs/exec.c b/fs/exec.c
index b6079f1a098e..537d92c41105 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1850,7 +1850,7 @@ out:
 	 * SIGSEGV.
 	 */
 	if (bprm->point_of_no_return && !fatal_signal_pending(current))
-		force_sigsegv(SIGSEGV);
+		force_fatal_sig(SIGSEGV);
 
 out_unmark:
 	current->fs->in_exec = 0;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index b9c339335a53..dbf9b9e97d74 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1513,10 +1513,7 @@ bail:
 	if (quota_enabled)
 		kfree(rm_quota);
 
-	/* no one is callint kthread_stop() for us so the kthread() api
-	 * requires that we call do_exit().  And it isn't exported, but
-	 * complete_and_exit() seems to be a minimal wrapper around it. */
-	complete_and_exit(NULL, status);
+	return status;
 }
 
 void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num)
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index a8fe2a593a3a..23505394ef70 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -351,6 +351,7 @@ extern int kill_pid(struct pid *pid, int sig, int priv);
 extern __must_check bool do_notify_parent(struct task_struct *, int);
 extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
 extern void force_sig(int);
+extern void force_fatal_sig(int);
 extern int send_sig(int, struct task_struct *, int);
 extern int zap_other_threads(struct task_struct *p);
 extern struct sigqueue *sigqueue_alloc(void);
diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h
index 34cb28b8f16c..a70b2bdbf4d9 100644
--- a/include/linux/signal_types.h
+++ b/include/linux/signal_types.h
@@ -70,6 +70,9 @@ struct ksignal {
 	int sig;
 };
 
+/* Used to kill the race between sigaction and forced signals */
+#define SA_IMMUTABLE		0x00800000
+
 #ifndef __ARCH_UAPI_SA_FLAGS
 #ifdef SA_RESTORER
 #define __ARCH_UAPI_SA_FLAGS	SA_RESTORER
diff --git a/include/uapi/asm-generic/signal-defs.h b/include/uapi/asm-generic/signal-defs.h
index fe929e7b77ca..7572f2f46ee8 100644
--- a/include/uapi/asm-generic/signal-defs.h
+++ b/include/uapi/asm-generic/signal-defs.h
@@ -45,6 +45,7 @@
 #define SA_UNSUPPORTED	0x00000400
 #define SA_EXPOSE_TAGBITS	0x00000800
 /* 0x00010000 used on mips */
+/* 0x00800000 used for internal SA_IMMUTABLE */
 /* 0x01000000 used on x86 */
 /* 0x02000000 used on x86 */
 /*
diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c
index c240302f56e2..4508201847d2 100644
--- a/kernel/entry/syscall_user_dispatch.c
+++ b/kernel/entry/syscall_user_dispatch.c
@@ -47,14 +47,18 @@ bool syscall_user_dispatch(struct pt_regs *regs)
 		 * access_ok() is performed once, at prctl time, when
 		 * the selector is loaded by userspace.
 		 */
-		if (unlikely(__get_user(state, sd->selector)))
-			do_exit(SIGSEGV);
+		if (unlikely(__get_user(state, sd->selector))) {
+			force_fatal_sig(SIGSEGV);
+			return true;
+		}
 
 		if (likely(state == SYSCALL_DISPATCH_FILTER_ALLOW))
 			return false;
 
-		if (state != SYSCALL_DISPATCH_FILTER_BLOCK)
-			do_exit(SIGSYS);
+		if (state != SYSCALL_DISPATCH_FILTER_BLOCK) {
+			force_fatal_sig(SIGSYS);
+			return true;
+		}
 	}
 
 	sd->on_dispatch = true;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 4a4d7092a2d8..7113003fab63 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -433,7 +433,7 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
  * If thread is going to be bound on a particular cpu, give its node
  * in @node, to get NUMA affinity for kthread stack, or else give NUMA_NO_NODE.
  * When woken, the thread will run @threadfn() with @data as its
- * argument. @threadfn() can either call do_exit() directly if it is a
+ * argument. @threadfn() can either return directly if it is a
  * standalone thread for which no one will call kthread_stop(), or
  * return when 'kthread_should_stop()' is true (which means
  * kthread_stop() has been called).  The return value should be zero
diff --git a/kernel/reboot.c b/kernel/reboot.c
index f7440c0c7e43..d6e0f9fb7f04 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -359,7 +359,6 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 	case LINUX_REBOOT_CMD_HALT:
 		kernel_halt();
 		do_exit(0);
-		panic("cannot halt");
 
 	case LINUX_REBOOT_CMD_POWER_OFF:
 		kernel_power_off();
diff --git a/kernel/signal.c b/kernel/signal.c
index 6f3476dc7873..7c4b7ae714d4 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1323,6 +1323,7 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool
 	blocked = sigismember(&t->blocked, sig);
 	if (blocked || ignored || sigdfl) {
 		action->sa.sa_handler = SIG_DFL;
+		action->sa.sa_flags |= SA_IMMUTABLE;
 		if (blocked) {
 			sigdelset(&t->blocked, sig);
 			recalc_sigpending_and_wake(t);
@@ -1649,6 +1650,19 @@ void force_sig(int sig)
 }
 EXPORT_SYMBOL(force_sig);
 
+void force_fatal_sig(int sig)
+{
+	struct kernel_siginfo info;
+
+	clear_siginfo(&info);
+	info.si_signo = sig;
+	info.si_errno = 0;
+	info.si_code = SI_KERNEL;
+	info.si_pid = 0;
+	info.si_uid = 0;
+	force_sig_info_to_task(&info, current, true);
+}
+
 /*
  * When things go south during signal handling, we
  * will force a SIGSEGV. And if the signal that caused
@@ -1657,15 +1671,10 @@ EXPORT_SYMBOL(force_sig);
  */
 void force_sigsegv(int sig)
 {
-	struct task_struct *p = current;
-
-	if (sig == SIGSEGV) {
-		unsigned long flags;
-		spin_lock_irqsave(&p->sighand->siglock, flags);
-		p->sighand->action[sig - 1].sa.sa_handler = SIG_DFL;
-		spin_unlock_irqrestore(&p->sighand->siglock, flags);
-	}
-	force_sig(SIGSEGV);
+	if (sig == SIGSEGV)
+		force_fatal_sig(SIGSEGV);
+	else
+		force_sig(SIGSEGV);
 }
 
 int force_sig_fault_to_task(int sig, int code, void __user *addr
@@ -2704,7 +2713,8 @@ relock:
 		if (!signr)
 			break; /* will return 0 */
 
-		if (unlikely(current->ptrace) && signr != SIGKILL) {
+		if (unlikely(current->ptrace) && (signr != SIGKILL) &&
+		    !(sighand->action[signr -1].sa.sa_flags & SA_IMMUTABLE)) {
 			signr = ptrace_signal(signr, &ksig->info);
 			if (!signr)
 				continue;
@@ -4054,6 +4064,10 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
 	k = &p->sighand->action[sig-1];
 
 	spin_lock_irq(&p->sighand->siglock);
+	if (k->sa.sa_flags & SA_IMMUTABLE) {
+		spin_unlock_irq(&p->sighand->siglock);
+		return -EINVAL;
+	}
 	if (oact)
 		*oact = *k;
 
diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c
index fbcb15c7c29b..93730d30af54 100644
--- a/net/batman-adv/tp_meter.c
+++ b/net/batman-adv/tp_meter.c
@@ -890,7 +890,7 @@ out:
 
 	batadv_tp_vars_put(tp_vars);
 
-	do_exit(0);
+	return 0;
 }
 
 /**