From 1cd03890ea64795e53f17a94928cca22495acb2a Mon Sep 17 00:00:00 2001 From: LEROY Christophe Date: Wed, 16 Sep 2015 12:04:51 +0200 Subject: [PATCH] powerpc32: memcpy: only use dcbz once cache is enabled memcpy() uses instruction dcbz to speed up copy by not wasting time loading cache line with data that will be overwritten. Some platform like mpc52xx do no have cache active at startup and can therefore not use memcpy(). Allthough no part of the code explicitly uses memcpy(), GCC makes calls to it. This patch modifies memcpy() such that at startup, memcpy() unconditionally jumps to generic_memcpy() which doesn't use the dcbz instruction. Once the initial MMU is set up, in machine_init() we patch memcpy() by replacing this inconditional jump by a NOP Reported-by: Michal Sojka Tested-by: Thomas Gleixner Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/setup_32.c | 3 +++ arch/powerpc/lib/copy_32.S | 5 +++++ 2 files changed, 8 insertions(+) diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index bb02e9f6944e..b316ab787a3b 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -38,6 +38,7 @@ #include #include #include +#include #define DBG(fmt...) @@ -116,6 +117,8 @@ notrace void __init machine_init(u64 dt_ptr) /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); + patch_instruction((unsigned int *)&memcpy, PPC_INST_NOP); + /* Do some early initialization based on the flat device tree */ early_init_devtree(__va(dt_ptr)); diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S index 2ef50c629470..da5847d09718 100644 --- a/arch/powerpc/lib/copy_32.S +++ b/arch/powerpc/lib/copy_32.S @@ -128,6 +128,10 @@ _GLOBAL(memset) * the destination area is cacheable. * We only use this version if the source and dest don't overlap. * -- paulus. + * + * During early init, cache might not be active yet, so dcbz cannot be used. + * We therefore jump to generic_memcpy which doesn't use dcbz. This jump is + * replaced by a nop once cache is active. This is done in machine_init() */ _GLOBAL(memmove) cmplw 0,r3,r4 @@ -135,6 +139,7 @@ _GLOBAL(memmove) /* fall through */ _GLOBAL(memcpy) + b generic_memcpy add r7,r3,r5 /* test if the src & dst overlap */ add r8,r4,r5 cmplw 0,r4,r7 -- 2.39.2