KVM: PPC: Book3S: PR: Optimize entry path

By shuffling a few instructions around we can execute more memory
loads in parallel, giving us a small performance boost.

With this patch and a simple priviledged SPR access loop guest, I get
a speed bump from 2013052 to 2035607 exits per second.

Signed-off-by: Alexander Graf <agraf@suse.de>

1 files changed, 7 insertions, 6 deletions

diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index 0676ae249b9f..6bae0a9414ba 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -128,24 +128,25 @@ no_dcbz32_on:
         /* First clear RI in our current MSR value */
         li      r0, MSR_RI
         andc    r6, r6, r0
-        MTMSR_EERI(r6)
-        mtsrr0  r9
-        mtsrr1  r4
 
         PPC_LL  r0, SVCPU_R0(r3)
         PPC_LL  r1, SVCPU_R1(r3)
         PPC_LL  r2, SVCPU_R2(r3)
-        PPC_LL  r4, SVCPU_R4(r3)
         PPC_LL  r5, SVCPU_R5(r3)
-        PPC_LL  r6, SVCPU_R6(r3)
         PPC_LL  r7, SVCPU_R7(r3)
         PPC_LL  r8, SVCPU_R8(r3)
-        PPC_LL  r9, SVCPU_R9(r3)
         PPC_LL  r10, SVCPU_R10(r3)
         PPC_LL  r11, SVCPU_R11(r3)
         PPC_LL  r12, SVCPU_R12(r3)
         PPC_LL  r13, SVCPU_R13(r3)
 
+        MTMSR_EERI(r6)
+        mtsrr0  r9
+        mtsrr1  r4
+
+        PPC_LL  r4, SVCPU_R4(r3)
+        PPC_LL  r6, SVCPU_R6(r3)
+        PPC_LL  r9, SVCPU_R9(r3)
         PPC_LL  r3, (SVCPU_R3)(r3)
 
         RFI