powerpc/32: Don't use lmw/stmw for saving/restoring non volatile regs

[ Upstream commit a85c728cb5e12216c19ae5878980c2cbbbf8616d ]

Instructions lmw/stmw are interesting for functions that are rarely
used and not in the cache, because only one instruction is to be
copied into the instruction cache instead of 19. However those
instruction are less performant than 19x raw lwz/stw as they require
synchronisation plus one additional cycle.

SAVE_NVGPRS / REST_NVGPRS are used in only a few places which are
mostly in interrupts entries/exits and in task switch so they are
likely already in the cache.

Using standard lwz improves null_syscall selftest by:
- 10 cycles on mpc832x.
- 2 cycles on mpc8xx.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/316c543b8906712c108985c8463eec09c8db577b.1629732542.git.christophe.leroy@csgroup.eu
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 1c538a9..7be2404 100644 (file)
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -28,8 +28,8 @@
 #else
 #define SAVE_GPR(n, base)      stw     n,GPR0+4*(n)(base)
 #define REST_GPR(n, base)      lwz     n,GPR0+4*(n)(base)
-#define SAVE_NVGPRS(base)      stmw    13, GPR0+4*13(base)
-#define REST_NVGPRS(base)      lmw     13, GPR0+4*13(base)
+#define SAVE_NVGPRS(base)      SAVE_GPR(13, base); SAVE_8GPRS(14, base); SAVE_10GPRS(22, base)
+#define REST_NVGPRS(base)      REST_GPR(13, base); REST_8GPRS(14, base); REST_10GPRS(22, base)
 #endif
 
 #define SAVE_2GPRS(n, base)    SAVE_GPR(n, base); SAVE_GPR(n+1, base)