powerpc/32: Reorder instructions to avoid using CTR in syscall entry

Now that we are using rfi instead of mtmsr to reactivate MMU, it is
possible to reorder instructions and avoid the need to use CTR for
stashing SRR0.

null_syscall on 8xx is reduced by 3 cycles (283 => 280 cycles).

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/8fa13a59f73647e058c95fc7e1c7a98f316bd20a.1612796617.git.christophe.leroy@csgroup.eu

diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index 97d8465eb12a3b9abfe7fc9a7331649466f938d7..930377375dc0d76630f36ec5f13f626874798e02 100644 (file)
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -116,30 +116,28 @@
 .endm
 
 .macro SYSCALL_ENTRY trapno
-       mfspr   r12,SPRN_SPRG_THREAD
        mfspr   r9, SPRN_SRR1
-       mfspr   r11, SPRN_SRR0
-       mtctr   r11
+       mfspr   r10, SPRN_SRR0
        andi.   r11, r9, MSR_PR
+       beq-    99f
+       LOAD_REG_IMMEDIATE(r11, MSR_KERNEL)             /* can take exceptions */
+       lis     r12, 1f@h
+       ori     r12, r12, 1f@l
+       mtspr   SPRN_SRR1, r11
+       mtspr   SPRN_SRR0, r12
+       mfspr   r12,SPRN_SPRG_THREAD
        mr      r11, r1
        lwz     r1,TASK_STACK-THREAD(r12)
-       beq-    99f
+       tovirt(r12, r12)
        addi    r1, r1, THREAD_SIZE - INT_FRAME_SIZE
-       LOAD_REG_IMMEDIATE(r10, MSR_KERNEL)             /* can take exceptions */
-       mtspr   SPRN_SRR1, r10
-       lis     r10, 1f@h
-       ori     r10, r10, 1f@l
-       mtspr   SPRN_SRR0, r10
        rfi
 1:
-       tovirt(r12, r12)
        stw     r11,GPR1(r1)
        stw     r11,0(r1)
        mr      r11, r1
+       stw     r10,_NIP(r11)
        mflr    r10
        stw     r10, _LINK(r11)
-       mfctr   r10
-       stw     r10,_NIP(r11)
        mfcr    r10
        rlwinm  r10,r10,0,4,2   /* Clear SO bit in CR */
        stw     r10,_CCR(r11)           /* save registers */