From 18e3f56b1cacb96017e2a66844ceceefabf6e7bc Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Thu, 15 Sep 2016 19:03:21 +1000
Subject: [PATCH] powerpc/64: Optimise syscall entry for virtual, relocatable
 case

The mflr r10 instruction was left over from when the code used LR to
branch to system_call_entry from the exception handler. That was
changed by commit 6a404806dfce ("powerpc: Avoid link stack corruption in
MMU on syscall entry path") to use the count register. The value is
never used now, so mflr can be removed, and r10 can be used for storage
rather than spilling to the SPR scratch register.

The scratch register spill causes a long pipeline stall due to the SPR
read after write. This change brings getppid syscall cost from 406 to
376 cycles on POWER8. getppid for non-relocatable case is 371 cycles.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/exceptions-64s.S | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 21ab5dd54e1e..3d1f3cfe5896 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -62,14 +62,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)				\
 	 * is volatile across system calls.
 	 */
 #define SYSCALL_PSERIES_2_DIRECT				\
-	mflr	r10 ;						\
 	LOAD_HANDLER(r12, system_call_entry) ;			\
 	mtctr	r12 ;						\
 	mfspr	r12,SPRN_SRR1 ;					\
-	/* Re-use of r13... No spare regs to do this */	\
-	li	r13,MSR_RI ;					\
-	mtmsrd 	r13,1 ;						\
-	GET_PACA(r13) ;	/* get r13 back */			\
+	li	r10,MSR_RI ;					\
+	mtmsrd 	r10,1 ;						\
 	bctr ;
 #else
 	/* We can branch directly */
-- 
GitLab