powerpc: Better scheduling of CR save code in system call path
At the moment system call entry looks like:
crclr so
...
mfcr r9
...
std r9,_CCR(r1)
commit bd19c8994a82 ([POWERPC] system call micro optimisation) put
some space between the crclr and mfcr in order to avoid a stall.
There is still a stall seen between the mfcr and std. We can avoid
the crclr by doing it in a GPR with rlwinm which gives us more room
to better schedule the sequence.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index ba72ddb..fd46046 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -63,15 +63,9 @@
std r0,GPR0(r1)
std r10,GPR1(r1)
ACCOUNT_CPU_USER_ENTRY(r10, r11)
- /*
- * This "crclr so" clears CR0.SO, which is the error indication on
- * return from this system call. There must be no cmp instruction
- * between it and the "mfcr r9" below, otherwise if XER.SO is set,
- * CR0.SO will get set, causing all system calls to appear to fail.
- */
- crclr so
std r2,GPR2(r1)
std r3,GPR3(r1)
+ mfcr r2
std r4,GPR4(r1)
std r5,GPR5(r1)
std r6,GPR6(r1)
@@ -85,13 +79,17 @@
std r11,_XER(r1)
std r11,_CTR(r1)
std r9,GPR13(r1)
- mfcr r9
mflr r10
+ /*
+ * This clears CR0.SO (bit 28), which is the error indication on
+ * return from this system call.
+ */
+ rldimi r2,r11,28,(63-28)
li r11,0xc01
- std r9,_CCR(r1)
std r10,_LINK(r1)
std r11,_TRAP(r1)
std r3,ORIG_GPR3(r1)
+ std r2,_CCR(r1)
ld r2,PACATOC(r13)
addi r9,r1,STACK_FRAME_OVERHEAD
ld r11,exception_marker@toc(r2)