[PATCH v3] powerpc32: memset: only use dcbz once cache is enabled

[Christophe Leroy <christophe.leroy@c-s.fr>]

memset() uses instruction dcbz to speed up clearing 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 memset(). Allthough no part of the code
explicitly uses memset(), GCC may makes calls to it.

This patch modifies memset() such that at startup, memset()
unconditionally jumps to simple_memset() which doesn't use
the dcbz instruction.

Once the initial MMU is set up, in machine_init() we patch memset()
by replacing this inconditional jump by a NOP

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
This patch goes on to of [v3] powerpc32: memcpy: only use dcbz once cache is enabled

Changes in v2:
   was part of [v2] powerpc32: memcpy/memset: only use dcbz once cache is enabled
changes in v3:
  Not using anymore feature-fixups
  Handling of memcpy() and memset() split in two patches
  
 arch/powerpc/kernel/setup_32.c |  1 +
 arch/powerpc/lib/copy_32.S     | 15 +++++++++++++++
 2 files changed, 16 insertions(+)

diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 362495f..345ec3a 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -124,6 +124,7 @@ notrace void __init machine_init(u64 dt_ptr)
 	udbg_early_init();
 
 	patch_instruction((unsigned int *)&memcpy, PPC_INST_NOP);
+	patch_instruction((unsigned int *)&memset, 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 da5847d..68a59d4 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -73,8 +73,13 @@ CACHELINE_MASK = (L1_CACHE_BYTES-1)
  * Use dcbz on the complete cache lines in the destination
  * to set them to zero.  This requires that the destination
  * area is cacheable.  -- paulus
+ *
+ * During early init, cache might not be active yet, so dcbz cannot be used.
+ * We therefore jump to simple_memset which doesn't use dcbz. This jump is
+ * replaced by a nop once cache is active. This is done in machine_init()
  */
 _GLOBAL(memset)
+	b	simple_memset
 	rlwimi	r4,r4,8,16,23
 	rlwimi	r4,r4,16,0,15
 
@@ -122,6 +127,16 @@ _GLOBAL(memset)
 	bdnz	8b
 	blr
 
+/* Simple version of memset used during early boot until cache is enabled */
+simple_memset:
+	cmplwi	cr0,r5,0
+	addi	r6,r3,-1
+	beqlr
+	mtctr	r5
+1:	stbu	r4,1(r6)
+	bdnz	1b
+	blr
+
 /*
  * This version uses dcbz on the complete cache lines in the
  * destination area to reduce memory traffic.  This requires that
-- 
2.1.0