fork: Generalize PF_IO_WORKER handling

Add fn and fn_arg members into struct kernel_clone_args and test for
them in copy_thread (instead of testing for PF_KTHREAD | PF_IO_WORKER).
This allows any task that wants to be a user space task that only runs
in kernel mode to use this functionality.

The code on x86 is an exception and still retains a PF_KTHREAD test
because x86 unlikely everything else handles kthreads slightly
differently than user space tasks that start with a function.

The functions that created tasks that start with a function
have been updated to set ".fn" and ".fn_arg" instead of
".stack" and ".stack_size".  These functions are fork_idle(),
create_io_thread(), kernel_thread(), and user_mode_thread().

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: "Eric W. Biederman" <[email protected]>

Author: ebiederm

arch/alpha/kernel/process.c

@@ -237,7 +237,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long kthread_arg = args->stack_size;
 	unsigned long tls = args->tls;
 	extern void ret_from_fork(void);
 	extern void ret_from_kernel_thread(void);
@@ -251,13 +250,13 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	childti->pcb.ksp = (unsigned long) childstack;
 	childti->pcb.flags = 1;	/* set FEN, clear everything else */
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		/* kernel thread */
 		memset(childstack, 0,
 			sizeof(struct switch_stack) + sizeof(struct pt_regs));
 		childstack->r26 = (unsigned long) ret_from_kernel_thread;
-		childstack->r9 = usp;	/* function */
-		childstack->r10 = kthread_arg;
+		childstack->r9 = (unsigned long) args->fn;
+		childstack->r10 = (unsigned long) args->fn_arg;
 		childregs->hae = alpha_mv.hae_cache;
 		childti->pcb.usp = 0;
 		return 0;

arch/arc/kernel/process.c

@@ -166,7 +166,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long kthread_arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct pt_regs *c_regs;        /* child's pt_regs */
 	unsigned long *childksp;       /* to unwind out of __switch_to() */
@@ -193,11 +192,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	childksp[0] = 0;			/* fp */
 	childksp[1] = (unsigned long)ret_from_fork; /* blink */
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		memset(c_regs, 0, sizeof(struct pt_regs));
 
-		c_callee->r13 = kthread_arg;
-		c_callee->r14 = usp;  /* function */
+		c_callee->r13 = (unsigned long)args->fn_arg;
+		c_callee->r14 = (unsigned long)args->fn;
 
 		return 0;
 	}

arch/arm/kernel/process.c

@@ -242,7 +242,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long stack_start = args->stack;
-	unsigned long stk_sz = args->stack_size;
 	unsigned long tls = args->tls;
 	struct thread_info *thread = task_thread_info(p);
 	struct pt_regs *childregs = task_pt_regs(p);
@@ -259,15 +258,15 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	thread->cpu_domain = get_domain();
 #endif
 
-	if (likely(!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))) {
+	if (likely(!args->fn)) {
 		*childregs = *current_pt_regs();
 		childregs->ARM_r0 = 0;
 		if (stack_start)
 			childregs->ARM_sp = stack_start;
 	} else {
 		memset(childregs, 0, sizeof(struct pt_regs));
-		thread->cpu_context.r4 = stk_sz;
-		thread->cpu_context.r5 = stack_start;
+		thread->cpu_context.r4 = (unsigned long)args->fn_arg;
+		thread->cpu_context.r5 = (unsigned long)args->fn;
 		childregs->ARM_cpsr = SVC_MODE;
 	}
 	thread->cpu_context.pc = (unsigned long)ret_from_fork;

arch/arm64/kernel/process.c

@@ -320,7 +320,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long stack_start = args->stack;
-	unsigned long stk_sz = args->stack_size;
 	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
 
@@ -337,7 +336,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 
 	ptrauth_thread_init_kernel(p);
 
-	if (likely(!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))) {
+	if (likely(!args->fn)) {
 		*childregs = *current_pt_regs();
 		childregs->regs[0] = 0;
 
@@ -371,8 +370,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->pstate = PSR_MODE_EL1h | PSR_IL_BIT;
 
-		p->thread.cpu_context.x19 = stack_start;
-		p->thread.cpu_context.x20 = stk_sz;
+		p->thread.cpu_context.x19 = (unsigned long)args->fn;
+		p->thread.cpu_context.x20 = (unsigned long)args->fn_arg;
 	}
 	p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
 	p->thread.cpu_context.sp = (unsigned long)childregs;

arch/csky/kernel/process.c

@@ -34,7 +34,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long kthread_arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct switch_stack *childstack;
 	struct pt_regs *childregs = task_pt_regs(p);
@@ -49,11 +48,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	/* setup thread.sp for switch_to !!! */
 	p->thread.sp = (unsigned long)childstack;
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childstack->r15 = (unsigned long) ret_from_kernel_thread;
-		childstack->r10 = kthread_arg;
-		childstack->r9 = usp;
+		childstack->r10 = (unsigned long) args->fn_arg;
+		childstack->r9 = (unsigned long) args->fn;
 		childregs->sr = mfcr("psr");
 	} else {
 		*childregs = *(current_pt_regs());

arch/h8300/kernel/process.c

@@ -108,16 +108,15 @@ void flush_thread(void)
 int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long usp = args->stack;
-	unsigned long topstk = args->stack_size;
 	struct pt_regs *childregs;
 
 	childregs = (struct pt_regs *) (THREAD_SIZE + task_stack_page(p)) - 1;
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->retpc = (unsigned long) ret_from_kernel_thread;
-		childregs->er4 = topstk; /* arg */
-		childregs->er5 = usp; /* fn */
+		childregs->er4 = (unsigned long) args->fn_arg;
+		childregs->er5 = (unsigned long) args->fn;
 	}  else {
 		*childregs = *current_pt_regs();
 		childregs->er0 = 0;

arch/hexagon/kernel/process.c

@@ -54,7 +54,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct thread_info *ti = task_thread_info(p);
 	struct hexagon_switch_stack *ss;
@@ -76,11 +75,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 						    sizeof(*ss));
 	ss->lr = (unsigned long)ret_from_fork;
 	p->thread.switch_sp = ss;
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		memset(childregs, 0, sizeof(struct pt_regs));
 		/* r24 <- fn, r25 <- arg */
-		ss->r24 = usp;
-		ss->r25 = arg;
+		ss->r24 = (unsigned long)args->fn;
+		ss->r25 = (unsigned long)args->fn_arg;
 		pt_set_kmode(childregs);
 		return 0;
 	}

arch/ia64/kernel/process.c

@@ -341,14 +341,14 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 
 	ia64_drop_fpu(p);	/* don't pick up stale state from a CPU's fph */
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		if (unlikely(args->idle)) {
 			/* fork_idle() called us */
 			return 0;
 		}
 		memset(child_stack, 0, sizeof(*child_ptregs) + sizeof(*child_stack));
-		child_stack->r4 = user_stack_base;	/* payload */
-		child_stack->r5 = user_stack_size;	/* argument */
+		child_stack->r4 = (unsigned long) args->fn;
+		child_stack->r5 = (unsigned long) args->fn_arg;
 		/*
 		 * Preserve PSR bits, except for bits 32-34 and 37-45,
 		 * which we can't read.

arch/m68k/kernel/process.c

@@ -142,7 +142,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct fork_frame {
 		struct switch_stack sw;
@@ -160,12 +159,12 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	 */
 	p->thread.fc = USER_DATA;
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		/* kernel thread */
 		memset(frame, 0, sizeof(struct fork_frame));
 		frame->regs.sr = PS_S;
-		frame->sw.a3 = usp; /* function */
-		frame->sw.d7 = arg;
+		frame->sw.a3 = (unsigned long)args->fn;
+		frame->sw.d7 = (unsigned long)args->fn_arg;
 		frame->sw.retpc = (unsigned long)ret_from_kernel_thread;
 		p->thread.usp = 0;
 		return 0;

arch/microblaze/kernel/process.c

@@ -56,19 +56,18 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
 	unsigned long usp = args->stack;
-	unsigned long arg = args->stack_size;
 	unsigned long tls = args->tls;
 	struct pt_regs *childregs = task_pt_regs(p);
 	struct thread_info *ti = task_thread_info(p);
 
-	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
+	if (unlikely(args->fn)) {
 		/* if we're creating a new kernel thread then just zeroing all
 		 * the registers. That's OK for a brand new thread.*/
 		memset(childregs, 0, sizeof(struct pt_regs));
 		memset(&ti->cpu_context, 0, sizeof(struct cpu_context));
 		ti->cpu_context.r1  = (unsigned long)childregs;
-		ti->cpu_context.r20 = (unsigned long)usp; /* fn */
-		ti->cpu_context.r19 = (unsigned long)arg;
+		ti->cpu_context.r20 = (unsigned long)args->fn;
+		ti->cpu_context.r19 = (unsigned long)args->fn_arg;
 		childregs->pt_mode = 1;
 		local_save_flags(childregs->msr);
 		ti->cpu_context.msr = childregs->msr & ~MSR_IE;