powerpc/pseries: Optimise hcall tracepoints

Now that we execute the hcall tracepoint entry and exit code out of
line, we can use the same stack across both functions.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

arch/powerpc/platforms/pseries/hvCall.S

@@ -46,33 +46,27 @@ hcall_tracepoint_refcount:
 	addi	r4,r1,STK_PARAM(FIRST_REG);			\
 	stdu	r1,-STACK_FRAME_OVERHEAD(r1);			\
 	bl	__trace_hcall_entry;				\
-	addi	r1,r1,STACK_FRAME_OVERHEAD;			\
-	ld	r0,16(r1);					\
-	ld	r3,STK_PARAM(R3)(r1);				\
-	ld	r4,STK_PARAM(R4)(r1);				\
-	ld	r5,STK_PARAM(R5)(r1);				\
-	ld	r6,STK_PARAM(R6)(r1);				\
-	ld	r7,STK_PARAM(R7)(r1);				\
-	ld	r8,STK_PARAM(R8)(r1);				\
-	ld	r9,STK_PARAM(R9)(r1);				\
-	ld	r10,STK_PARAM(R10)(r1);				\
-	mtlr	r0
+	ld	r3,STACK_FRAME_OVERHEAD+STK_PARAM(R3)(r1);	\
+	ld	r4,STACK_FRAME_OVERHEAD+STK_PARAM(R4)(r1);	\
+	ld	r5,STACK_FRAME_OVERHEAD+STK_PARAM(R5)(r1);	\
+	ld	r6,STACK_FRAME_OVERHEAD+STK_PARAM(R6)(r1);	\
+	ld	r7,STACK_FRAME_OVERHEAD+STK_PARAM(R7)(r1);	\
+	ld	r8,STACK_FRAME_OVERHEAD+STK_PARAM(R8)(r1);	\
+	ld	r9,STACK_FRAME_OVERHEAD+STK_PARAM(R9)(r1);	\
+	ld	r10,STACK_FRAME_OVERHEAD+STK_PARAM(R10)(r1)
 
 /*
  * postcall is performed immediately before function return which
  * allows liberal use of volatile registers.
  */
 #define __HCALL_INST_POSTCALL					\
-	mflr	r0;						\
-	ld	r6,STK_PARAM(R3)(r1);				\
-	std	r3,STK_PARAM(R3)(r1);				\
+	ld	r0,STACK_FRAME_OVERHEAD+STK_PARAM(R3)(r1);	\
+	std	r3,STACK_FRAME_OVERHEAD+STK_PARAM(R3)(r1);	\
 	mr	r4,r3;						\
-	mr	r3,r6;						\
-	std	r0,16(r1);					\
-	stdu	r1,-STACK_FRAME_OVERHEAD(r1);			\
+	mr	r3,r0;						\
 	bl	__trace_hcall_exit;				\
+	ld	r0,STACK_FRAME_OVERHEAD+16(r1);			\
 	addi	r1,r1,STACK_FRAME_OVERHEAD;			\
-	ld	r0,16(r1);					\
 	ld	r3,STK_PARAM(R3)(r1);				\
 	mtlr	r0
 
@@ -279,14 +273,14 @@ plpar_hcall9_trace:
 	mr	r7,r8
 	mr	r8,r9
 	mr	r9,r10
-	ld	r10,STK_PARAM(R11)(r1)
-	ld	r11,STK_PARAM(R12)(r1)
-	ld	r12,STK_PARAM(R13)(r1)
+	ld	r10,STACK_FRAME_OVERHEAD+STK_PARAM(R11)(r1)
+	ld	r11,STACK_FRAME_OVERHEAD+STK_PARAM(R12)(r1)
+	ld	r12,STACK_FRAME_OVERHEAD+STK_PARAM(R13)(r1)
 
 	HVSC
 
 	mr	r0,r12
-	ld	r12,STK_PARAM(R4)(r1)
+	ld	r12,STACK_FRAME_OVERHEAD+STK_PARAM(R4)(r1)
 	std	r4,0(r12)
 	std	r5,8(r12)
 	std	r6,16(r12)