[ARM] Allow CONFIG_ZBOOT_ROM=y image to be relocated to RAM

Since the decompressor supports PIC, even for CONFIG_ZBOOT_ROM,
we can easily allow an image which has been linked to run at
a particular address in ROM to be moved to RAM.  We just need
to make sure that we don't relocate the GOT entries for the
BSS segment.

This cset also implements sa1100-based debugging for the
decompressor.

arch/arm/boot/compressed/head.S

@@ -55,6 +55,18 @@
 		.macro	writeb, rb
 		strb	\rb, [r3, #0]
 		.endm
+#elif defined(CONFIG_ARCH_SA1100)
+		.macro	loadsp, rb
+		mov	\rb, #0x80000000	@ physical base address
+#  if defined(CONFIG_DEBUG_LL_SER3)
+		add	\rb, \rb, #0x00050000	@ Ser3
+#  else
+		add	\rb, \rb, #0x00010000	@ Ser1
+#  endif
+		.endm
+		.macro	writeb, rb
+		str	\rb, [r3, #0x14]	@ UTDR
+		.endm
 #else
 #error no serial architecture defined
 #endif
@@ -151,22 +163,55 @@ not_angel:
 		ldmia	r0, {r1, r2, r3, r4, r5, r6, ip, sp}
 		subs	r0, r0, r1		@ calculate the delta offset
 
-		teq	r0, #0			@ if delta is zero, we're
+						@ if delta is zero, we're
 		beq	not_relocated		@ running at the address we
 						@ were linked at.
 
-		add	r2, r2, r0		@ different address, so we
-		add	r3, r3, r0		@ need to fix up various
-		add	r5, r5, r0		@ pointers.
+		/*
+		 * We're running at a different address.  We need to fix
+		 * up various pointers:
+		 *   r5 - zImage base address
+		 *   r6 - GOT start
+		 *   ip - GOT end
+		 */
+		add	r5, r5, r0
 		add	r6, r6, r0
 		add	ip, ip, r0
+
+#ifndef CONFIG_ZBOOT_ROM
+		/*
+		 * If we're running fully PIC === CONFIG_ZBOOT_ROM = n,
+		 * we need to fix up pointers into the BSS region.
+		 *   r2 - BSS start
+		 *   r3 - BSS end
+		 *   sp - stack pointer
+		 */
+		add	r2, r2, r0
+		add	r3, r3, r0
 		add	sp, sp, r0
 
+		/*
+		 * Relocate all entries in the GOT table.
+		 */
 1:		ldr	r1, [r6, #0]		@ relocate entries in the GOT
 		add	r1, r1, r0		@ table.  This fixes up the
 		str	r1, [r6], #4		@ C references.
 		cmp	r6, ip
 		blo	1b
+#else
+
+		/*
+		 * Relocate entries in the GOT table.  We only relocate
+		 * the entries that are outside the (relocated) BSS region.
+		 */
+1:		ldr	r1, [r6, #0]		@ relocate entries in the GOT
+		cmp	r1, r2			@ entry < bss_start ||
+		cmphs	r3, r1			@ _end < entry
+		addlo	r1, r1, r0		@ table.  This fixes up the
+		str	r1, [r6], #4		@ C references.
+		cmp	r6, ip
+		blo	1b
+#endif
 
 not_relocated:	mov	r0, #0
 1:		str	r0, [r2], #4		@ clear bss
@@ -176,6 +221,11 @@ not_relocated:	mov	r0, #0
 		cmp	r2, r3
 		blo	1b
 
+		/*
+		 * The C runtime environment should now be setup
+		 * sufficiently.  Turn the cache on, set up some
+		 * pointers, and start decompressing.
+		 */
 		bl	cache_on
 
 		mov	r1, sp			@ malloc space above stack