[PATCH] powerpc/64s: optimise syscall entry for virtual, relocatable case

[Nicholas Piggin]

The mflr r10 instruction was left over saving of lr when the code used
lr to branch to system_call_entry from the exception handler. That was
changed by 6a404806d 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 at gmail.com>
---

 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 df6d45e..2cdd64f 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -63,15 +63,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)				\
 	 * is volatile across system calls.
 	 */
 #define SYSCALL_PSERIES_2_DIRECT				\
-	mflr	r10 ;						\
 	ld	r12,PACAKBASE(r13) ; 				\
 	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 */
-- 
2.9.3