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>
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index c1af8ac..c0373d6 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -407,37 +407,34 @@
* 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? */
- jnz 1f
+ testq %rbx, %rbx /* from kernel_thread? */
+ jnz 1f /* kernel threads are uncommon */
- /*
- * 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:
+2:
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)
/*
