spl: Allow performing BSS init early before board_init_f()

On some platform we have sufficient memory available early on to allow
setting up and using a basic BSS prior to entering board_init_f(). Doing
so can for example be used to carry state over to board_init_r() without
having to resort to extending U-Boot's global data structure.

To support such scenarios add a Kconfig option called CONFIG_SPL_EARLY_BSS
to allow moving the initialization of BSS prior to entering board_init_f(),
if enabled. Note that using this option usually should go along with using
CONFIG_SPL_SEPARATE_BSS and configuring BSS to be located in memory
actually available prior to board_init_f().

Signed-off-by: Andreas Dannenberg <dannenberg@ti.com>
diff --git a/arch/arm/lib/crt0.S b/arch/arm/lib/crt0.S
index 30fba20..c74641d 100644
--- a/arch/arm/lib/crt0.S
+++ b/arch/arm/lib/crt0.S
@@ -58,6 +58,33 @@
  */
 
 /*
+ * Macro for clearing BSS during SPL execution. Usually called during the
+ * relocation process for most boards before entering board_init_r(), but
+ * can also be done early before entering board_init_f() on plaforms that
+ * can afford it due to sufficient memory being available early.
+ */
+
+.macro SPL_CLEAR_BSS
+	ldr	r0, =__bss_start	/* this is auto-relocated! */
+
+#ifdef CONFIG_USE_ARCH_MEMSET
+	ldr	r3, =__bss_end		/* this is auto-relocated! */
+	mov	r1, #0x00000000		/* prepare zero to clear BSS */
+
+	subs	r2, r3, r0		/* r2 = memset len */
+	bl	memset
+#else
+	ldr	r1, =__bss_end		/* this is auto-relocated! */
+	mov	r2, #0x00000000		/* prepare zero to clear BSS */
+
+clbss_l:cmp	r0, r1			/* while not at end of BSS */
+	strlo	r2, [r0]		/* clear 32-bit BSS word */
+	addlo	r0, r0, #4		/* move to next */
+	blo	clbss_l
+#endif
+.endm
+
+/*
  * entry point of crt0 sequence
  */
 
@@ -82,6 +109,10 @@
 	mov	r9, r0
 	bl	board_init_f_init_reserve
 
+#if defined(CONFIG_SPL_EARLY_BSS)
+	SPL_CLEAR_BSS
+#endif
+
 	mov	r0, #0
 	bl	board_init_f
 
@@ -119,6 +150,11 @@
 	bl	c_runtime_cpu_setup	/* we still call old routine here */
 #endif
 #if !defined(CONFIG_SPL_BUILD) || defined(CONFIG_SPL_FRAMEWORK)
+
+#if !defined(CONFIG_SPL_EARLY_BSS)
+	SPL_CLEAR_BSS
+#endif
+
 # ifdef CONFIG_SPL_BUILD
 	/* Use a DRAM stack for the rest of SPL, if requested */
 	bl	spl_relocate_stack_gd
@@ -126,23 +162,6 @@
 	movne	sp, r0
 	movne	r9, r0
 # endif
-	ldr	r0, =__bss_start	/* this is auto-relocated! */
-
-#ifdef CONFIG_USE_ARCH_MEMSET
-	ldr	r3, =__bss_end		/* this is auto-relocated! */
-	mov	r1, #0x00000000		/* prepare zero to clear BSS */
-
-	subs	r2, r3, r0		/* r2 = memset len */
-	bl	memset
-#else
-	ldr	r1, =__bss_end		/* this is auto-relocated! */
-	mov	r2, #0x00000000		/* prepare zero to clear BSS */
-
-clbss_l:cmp	r0, r1			/* while not at end of BSS */
-	strlo	r2, [r0]		/* clear 32-bit BSS word */
-	addlo	r0, r0, #4		/* move to next */
-	blo	clbss_l
-#endif
 
 #if ! defined(CONFIG_SPL_BUILD)
 	bl coloured_LED_init