sched/x86: Pass kernel thread parameters in 'struct fork_frame'

Instead of setting up a fake pt_regs context, put the kernel thread
function pointer and arg into the unused callee-restored registers
of 'struct fork_frame'.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1471106302-10159-6-git-send-email-brgerst@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/entry/entry_32.S

@@ -240,35 +240,34 @@ END(__switch_to_asm)
  * A newly forked process directly context switches into this address.
  *
  * eax: prev task we switched from
+ * ebx: kernel thread func (NULL for user thread)
+ * edi: kernel thread arg
  */
 ENTRY(ret_from_fork)
 	pushl	%eax
 	call	schedule_tail
 	popl	%eax
 
+	testl	%ebx, %ebx
+	jnz	1f		/* kernel threads are uncommon */
+
+2:
 	/* When we fork, we trace the syscall return in the child, too. */
 	movl    %esp, %eax
 	call    syscall_return_slowpath
 	jmp     restore_all
-END(ret_from_fork)
-
-ENTRY(ret_from_kernel_thread)
-	pushl	%eax
-	call	schedule_tail
-	popl	%eax
-	movl	PT_EBP(%esp), %eax
-	call	*PT_EBX(%esp)
-	movl	$0, PT_EAX(%esp)
 
+	/* kernel thread */
+1:	movl	%edi, %eax
+	call	*%ebx
 	/*
-	 * Kernel threads return to userspace as if returning from a syscall.
+	 * A kernel thread is allowed to return here after successfully
-	 * We should check whether anything actually uses this path and, if so,
+	 * calling do_execve().  Exit to userspace to complete the execve()
-	 * consider switching it over to ret_from_fork.
+	 * syscall.
 	 */
-	movl    %esp, %eax
+	movl	$0, PT_EAX(%esp)
-	call    syscall_return_slowpath
+	jmp	2b
-	jmp     restore_all
+END(ret_from_fork)
-ENDPROC(ret_from_kernel_thread)
 
 /*
  * Return to user mode is not as complex as all this looks,

arch/x86/entry/entry_64.S

@@ -407,37 +407,34 @@ END(__switch_to_asm)
  * A newly forked process directly context switches into this address.
  *
  * rax: prev task we switched from
+ * rbx: kernel thread func (NULL for user thread)
+ * r12: kernel thread arg
  */
 ENTRY(ret_from_fork)
 	movq	%rax, %rdi
 	call	schedule_tail			/* rdi: 'prev' task parameter */
 
-	testb	$3, CS(%rsp)			/* from kernel_thread? */
+	testq	%rbx, %rbx			/* from kernel_thread? */
-	jnz	1f
+	jnz	1f				/* kernel threads are uncommon */
 
-	/*
+2:
-	 * We came from kernel_thread.  This code path is quite twisted, and
-	 * someone should clean it up.
-	 *
-	 * copy_thread_tls stashes the function pointer in RBX and the
-	 * parameter to be passed in RBP.  The called function is permitted
-	 * to call do_execve and thereby jump to user mode.
-	 */
-	movq	RBP(%rsp), %rdi
-	call	*RBX(%rsp)
-	movl	$0, RAX(%rsp)
-
-	/*
-	 * Fall through as though we're exiting a syscall.  This makes a
-	 * twisted sort of sense if we just called do_execve.
-	 */
-
-1:
 	movq	%rsp, %rdi
 	call	syscall_return_slowpath	/* returns with IRQs disabled */
 	TRACE_IRQS_ON			/* user mode is traced as IRQS on */
 	SWAPGS
 	jmp	restore_regs_and_iret
+
+1:
+	/* kernel thread */
+	movq	%r12, %rdi
+	call	*%rbx
+	/*
+	 * A kernel thread is allowed to return here after successfully
+	 * calling do_execve().  Exit to userspace to complete the execve()
+	 * syscall.
+	 */
+	movq	$0, RAX(%rsp)
+	jmp	2b
 END(ret_from_fork)
 
 /*

arch/x86/include/asm/switch_to.h

@@ -34,6 +34,8 @@ static inline void prepare_switch_to(struct task_struct *prev,
 #endif
 }
 
+asmlinkage void ret_from_fork(void);
+
 /* data that is pointed to by thread.sp */
 struct inactive_task_frame {
 #ifdef CONFIG_X86_64

arch/x86/kernel/process_32.c

@@ -55,9 +55,6 @@
 #include <asm/switch_to.h>
 #include <asm/vm86.h>
 
-asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
-asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread");
-
 /*
  * Return saved PC of a blocked thread.
  */
@@ -139,6 +136,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	int err;
 
 	frame->bp = 0;
+	frame->ret_addr = (unsigned long) ret_from_fork;
 	p->thread.sp = (unsigned long) fork_frame;
 	p->thread.sp0 = (unsigned long) (childregs+1);
 	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
@@ -146,25 +144,17 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		/* kernel thread */
 		memset(childregs, 0, sizeof(struct pt_regs));
-		frame->ret_addr = (unsigned long) ret_from_kernel_thread;
+		frame->bx = sp;		/* function */
-		task_user_gs(p) = __KERNEL_STACK_CANARY;
+		frame->di = arg;
-		childregs->ds = __USER_DS;
-		childregs->es = __USER_DS;
-		childregs->fs = __KERNEL_PERCPU;
-		childregs->bx = sp;	/* function */
-		childregs->bp = arg;
-		childregs->orig_ax = -1;
-		childregs->cs = __KERNEL_CS | get_kernel_rpl();
-		childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
 		p->thread.io_bitmap_ptr = NULL;
 		return 0;
 	}
+	frame->bx = 0;
 	*childregs = *current_pt_regs();
 	childregs->ax = 0;
 	if (sp)
 		childregs->sp = sp;
 
-	frame->ret_addr = (unsigned long) ret_from_fork;
 	task_user_gs(p) = get_user_gs(current_pt_regs());
 
 	p->thread.io_bitmap_ptr = NULL;

arch/x86/kernel/process_64.c

@@ -50,8 +50,6 @@
 #include <asm/switch_to.h>
 #include <asm/xen/hypervisor.h>
 
-asmlinkage extern void ret_from_fork(void);
-
 __visible DEFINE_PER_CPU(unsigned long, rsp_scratch);
 
 /* Prints also some state that isn't saved in the pt_regs */
@@ -165,15 +163,11 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		/* kernel thread */
 		memset(childregs, 0, sizeof(struct pt_regs));
-		childregs->sp = (unsigned long)childregs;
+		frame->bx = sp;		/* function */
-		childregs->ss = __KERNEL_DS;
+		frame->r12 = arg;
-		childregs->bx = sp; /* function */
-		childregs->bp = arg;
-		childregs->orig_ax = -1;
-		childregs->cs = __KERNEL_CS | get_kernel_rpl();
-		childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
 		return 0;
 	}
+	frame->bx = 0;
 	*childregs = *current_pt_regs();
 
 	childregs->ax = 0;