sched/x86: Rewrite the switch_to() code
Move the low-level context switch code to an out-of-line asm stub instead of
using complex inline asm. This allows constructing a new stack frame for the
child process to make it seamlessly flow to ret_from_fork without an extra
test and branch in __switch_to(). It also improves code generation for
__schedule() by using the C calling convention instead of clobbering all
registers.
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/1471106302-10159-5-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 f6b40e5..c1af8ac 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -368,13 +368,48 @@
#include <asm/syscalls_64.h>
/*
+ * %rdi: prev task
+ * %rsi: next task
+ */
+ENTRY(__switch_to_asm)
+ /*
+ * Save callee-saved registers
+ * This must match the order in inactive_task_frame
+ */
+ pushq %rbp
+ pushq %rbx
+ pushq %r12
+ pushq %r13
+ pushq %r14
+ pushq %r15
+
+ /* switch stack */
+ movq %rsp, TASK_threadsp(%rdi)
+ movq TASK_threadsp(%rsi), %rsp
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+ movq TASK_stack_canary(%rsi), %rbx
+ movq %rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset
+#endif
+
+ /* restore callee-saved registers */
+ popq %r15
+ popq %r14
+ popq %r13
+ popq %r12
+ popq %rbx
+ popq %rbp
+
+ jmp __switch_to
+END(__switch_to_asm)
+
+/*
* A newly forked process directly context switches into this address.
*
- * rdi: prev task we switched from
+ * rax: prev task we switched from
*/
ENTRY(ret_from_fork)
- LOCK ; btr $TIF_FORK, TI_flags(%r8)
-
+ movq %rax, %rdi
call schedule_tail /* rdi: 'prev' task parameter */
testb $3, CS(%rsp) /* from kernel_thread? */