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>

1 files changed, 21 insertions, 118 deletions

diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index ec689c62c01f..886d5ea09dba 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -2,8 +2,12 @@
 #define _ASM_X86_SWITCH_TO_H
 
 struct task_struct; /* one of the stranger aspects of C forward declarations */
+
+struct task_struct *__switch_to_asm(struct task_struct *prev,
+				    struct task_struct *next);
+
 __visible struct task_struct *__switch_to(struct task_struct *prev,
-					   struct task_struct *next);
+					  struct task_struct *next);
 struct tss_struct;
 void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		      struct tss_struct *tss);
@@ -32,131 +36,30 @@ static inline void prepare_switch_to(struct task_struct *prev,
 
 /* data that is pointed to by thread.sp */
 struct inactive_task_frame {
+#ifdef CONFIG_X86_64
+	unsigned long r15;
+	unsigned long r14;
+	unsigned long r13;
+	unsigned long r12;
+#else
+	unsigned long si;
+	unsigned long di;
+#endif
+	unsigned long bx;
 	unsigned long bp;
+	unsigned long ret_addr;
 };
 
-#ifdef CONFIG_X86_32
-
-#ifdef CONFIG_CC_STACKPROTECTOR
-#define __switch_canary							\
-	"movl %P[task_canary](%[next]), %%ebx\n\t"			\
-	"movl %%ebx, "__percpu_arg([stack_canary])"\n\t"
-#define __switch_canary_oparam						\
-	, [stack_canary] "=m" (stack_canary.canary)
-#define __switch_canary_iparam						\
-	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
-#else	/* CC_STACKPROTECTOR */
-#define __switch_canary
-#define __switch_canary_oparam
-#define __switch_canary_iparam
-#endif	/* CC_STACKPROTECTOR */
+struct fork_frame {
+	struct inactive_task_frame frame;
+	struct pt_regs regs;
+};
 
-/*
- * Saving eflags is important. It switches not only IOPL between tasks,
- * it also protects other tasks from NT leaking through sysenter etc.
- */
 #define switch_to(prev, next, last)					\
 do {									\
-	/*								\
-	 * Context-switching clobbers all registers, so we clobber	\
-	 * them explicitly, via unused output variables.		\
-	 * (EAX and EBP is not listed because EBP is saved/restored	\
-	 * explicitly for wchan access and EAX is the return value of	\
-	 * __switch_to())						\
-	 */								\
-	unsigned long ebx, ecx, edx, esi, edi;				\
-									\
 	prepare_switch_to(prev, next);					\
 									\
-	asm volatile("pushl %%ebp\n\t"		/* save    EBP   */	\
-		     "movl %%esp,%[prev_sp]\n\t"	/* save    ESP   */ \
-		     "movl %[next_sp],%%esp\n\t"	/* restore ESP   */ \
-		     "movl $1f,%[prev_ip]\n\t"	/* save    EIP   */	\
-		     "pushl %[next_ip]\n\t"	/* restore EIP   */	\
-		     __switch_canary					\
-		     "jmp __switch_to\n"	/* regparm call  */	\
-		     "1:\t"						\
-		     "popl %%ebp\n\t"		/* restore EBP   */	\
-									\
-		     /* output parameters */				\
-		     : [prev_sp] "=m" (prev->thread.sp),		\
-		       [prev_ip] "=m" (prev->thread.ip),		\
-		       "=a" (last),					\
-									\
-		       /* clobbered output registers: */		\
-		       "=b" (ebx), "=c" (ecx), "=d" (edx),		\
-		       "=S" (esi), "=D" (edi)				\
-		       							\
-		       __switch_canary_oparam				\
-									\
-		       /* input parameters: */				\
-		     : [next_sp]  "m" (next->thread.sp),		\
-		       [next_ip]  "m" (next->thread.ip),		\
-		       							\
-		       /* regparm parameters for __switch_to(): */	\
-		       [prev]     "a" (prev),				\
-		       [next]     "d" (next)				\
-									\
-		       __switch_canary_iparam				\
-									\
-		     : /* reloaded segment registers */			\
-			"memory");					\
+	((last) = __switch_to_asm((prev), (next)));			\
 } while (0)
 
-#else /* CONFIG_X86_32 */
-
-/* frame pointer must be last for get_wchan */
-#define SAVE_CONTEXT    "pushq %%rbp ; movq %%rsi,%%rbp\n\t"
-#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\t"
-
-#define __EXTRA_CLOBBER  \
-	, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
-	  "r12", "r13", "r14", "r15", "flags"
-
-#ifdef CONFIG_CC_STACKPROTECTOR
-#define __switch_canary							  \
-	"movq %P[task_canary](%%rsi),%%r8\n\t"				  \
-	"movq %%r8,"__percpu_arg([gs_canary])"\n\t"
-#define __switch_canary_oparam						  \
-	, [gs_canary] "=m" (irq_stack_union.stack_canary)
-#define __switch_canary_iparam						  \
-	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
-#else	/* CC_STACKPROTECTOR */
-#define __switch_canary
-#define __switch_canary_oparam
-#define __switch_canary_iparam
-#endif	/* CC_STACKPROTECTOR */
-
-/*
- * There is no need to save or restore flags, because flags are always
- * clean in kernel mode, with the possible exception of IOPL.  Kernel IOPL
- * has no effect.
- */
-#define switch_to(prev, next, last)					  \
-	prepare_switch_to(prev, next);					  \
-									  \
-	asm volatile(SAVE_CONTEXT					  \
-	     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */	  \
-	     "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */	  \
-	     "call __switch_to\n\t"					  \
-	     "movq "__percpu_arg([current_task])",%%rsi\n\t"		  \
-	     __switch_canary						  \
-	     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
-	     "movq %%rax,%%rdi\n\t" 					  \
-	     "testl  %[_tif_fork],%P[ti_flags](%%r8)\n\t"		  \
-	     "jnz   ret_from_fork\n\t"					  \
-	     RESTORE_CONTEXT						  \
-	     : "=a" (last)					  	  \
-	       __switch_canary_oparam					  \
-	     : [next] "S" (next), [prev] "D" (prev),			  \
-	       [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
-	       [ti_flags] "i" (offsetof(struct thread_info, flags)),	  \
-	       [_tif_fork] "i" (_TIF_FORK),			  	  \
-	       [thread_info] "i" (offsetof(struct task_struct, stack)),   \
-	       [current_task] "m" (current_task)			  \
-	       __switch_canary_iparam					  \
-	     : "memory", "cc" __EXTRA_CLOBBER)
-
-#endif /* CONFIG_X86_32 */
-
 #endif /* _ASM_X86_SWITCH_TO_H */