powerpc/32: remove a NOP from memset()

memset() is patched after initialisation to activate the
optimised part which uses cache instructions.

Today we have a 'b 2f' to skip the optimised patch, which then gets
replaced by a NOP, implying a useless cycle consumption.
As we have a 'bne 2f' just before, we could use that instruction
for the live patching, hence removing the need to have a
dedicated 'b 2f' to be replaced by a NOP.

This patch changes the 'bne 2f' by a 'b 2f'. During init, that
'b 2f' is then replaced by 'bne 2f'
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/kernel/setup_32.c

@@ -98,6 +98,9 @@ extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */
 
 notrace void __init machine_init(u64 dt_ptr)
 {
+	unsigned int *addr = &memset_nocache_branch;
+	unsigned long insn;
+
 	/* Configure static keys first, now that we're relocated. */
 	setup_feature_keys();
 
@@ -105,7 +108,9 @@ notrace void __init machine_init(u64 dt_ptr)
 	udbg_early_init();
 
 	patch_instruction((unsigned int *)&memcpy, PPC_INST_NOP);
-	patch_instruction(&memset_nocache_branch, PPC_INST_NOP);
+
+	insn = create_cond_branch(addr, branch_target(addr), 0x820000);
+	patch_instruction(addr, insn);	/* replace b by bne cr0 */
 
 	/* Do some early initialization based on the flat device tree */
 	early_init_devtree(__va(dt_ptr));

arch/powerpc/lib/copy_32.S

@@ -103,9 +103,12 @@ _GLOBAL(memset)
 	add	r5,r0,r5
 	subf	r6,r0,r3
 	cmplwi	0,r4,0
-	bne	2f	/* Use normal procedure if r4 is not zero */
+	/*
+	 * Skip optimised bloc until cache is enabled. Will be replaced
+	 * by 'bne' during boot to use normal procedure if r4 is not zero
+	 */
 _GLOBAL(memset_nocache_branch)
-	b	2f	/* Skip optimised bloc until cache is enabled */
+	b	2f
 
 	clrlwi	r7,r6,32-LG_CACHELINE_BYTES
 	add	r8,r7,r5