ARM: implement relocation for arm1176

Change the implementation for arm1176 to relocate the code to
an arbitrary address in RAM.

Portions of this work were supported by funding from
the CE Linux Forum.

Signed-off-by: Heiko Schocher <hs@denx.de>
diff --git a/arch/arm/cpu/arm1176/start.S b/arch/arm/cpu/arm1176/start.S
index f98a7aa..e5e7913 100644
--- a/arch/arm/cpu/arm1176/start.S
+++ b/arch/arm/cpu/arm1176/start.S
@@ -95,6 +95,7 @@
  *************************************************************************
  */
 
+.globl _TEXT_BASE
 _TEXT_BASE:
 	.word	TEXT_BASE
 
@@ -106,9 +107,11 @@
 _TEXT_PHY_BASE:
 	.word	CONFIG_SYS_PHY_UBOOT_BASE
 
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 .globl _armboot_start
 _armboot_start:
 	.word _start
+#endif
 
 /*
  * These are defined in the board-specific linker script.
@@ -121,6 +124,275 @@
 _bss_end:
 	.word _end
 
+#if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
+/* IRQ stack memory (calculated at run-time) + 8 bytes */
+.globl IRQ_STACK_START_IN
+IRQ_STACK_START_IN:
+	.word	0x0badc0de
+
+.globl _datarel_start
+_datarel_start:
+	.word __datarel_start
+
+.globl _datarelrolocal_start
+_datarelrolocal_start:
+	.word __datarelrolocal_start
+
+.globl _datarellocal_start
+_datarellocal_start:
+	.word __datarellocal_start
+
+.globl _datarelro_start
+_datarelro_start:
+	.word __datarelro_start
+
+.globl _got_start
+_got_start:
+	.word __got_start
+
+.globl _got_end
+_got_end:
+	.word __got_end
+
+/*
+ * the actual reset code
+ */
+
+reset:
+	/*
+	 * set the cpu to SVC32 mode
+	 */
+	mrs	r0, cpsr
+	bic	r0, r0, #0x3f
+	orr	r0, r0, #0xd3
+	msr	cpsr, r0
+
+/*
+ *************************************************************************
+ *
+ * CPU_init_critical registers
+ *
+ * setup important registers
+ * setup memory timing
+ *
+ *************************************************************************
+ */
+	/*
+	 * we do sys-critical inits only at reboot,
+	 * not when booting from ram!
+	 */
+cpu_init_crit:
+	/*
+	 * When booting from NAND - it has definitely been a reset, so, no need
+	 * to flush caches and disable the MMU
+	 */
+#ifndef CONFIG_NAND_SPL
+	/*
+	 * flush v4 I/D caches
+	 */
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c7, 0	/* flush v3/v4 cache */
+	mcr	p15, 0, r0, c8, c7, 0	/* flush v4 TLB */
+
+	/*
+	 * disable MMU stuff and caches
+	 */
+	mrc	p15, 0, r0, c1, c0, 0
+	bic	r0, r0, #0x00002300	@ clear bits 13, 9:8 (--V- --RS)
+	bic	r0, r0, #0x00000087	@ clear bits 7, 2:0 (B--- -CAM)
+	orr	r0, r0, #0x00000002	@ set bit 2 (A) Align
+	orr	r0, r0, #0x00001000	@ set bit 12 (I) I-Cache
+
+	/* Prepare to disable the MMU */
+	adr	r2, mmu_disable_phys
+	sub	r2, r2, #(CONFIG_SYS_PHY_UBOOT_BASE - TEXT_BASE)
+	b	mmu_disable
+
+	.align 5
+	/* Run in a single cache-line */
+mmu_disable:
+	mcr	p15, 0, r0, c1, c0, 0
+	nop
+	nop
+	mov	pc, r2
+mmu_disable_phys:
+
+#ifdef CONFIG_DISABLE_TCM
+	/*
+	 * Disable the TCMs
+	 */
+	mrc	p15, 0, r0, c0, c0, 2	/* Return TCM details */
+	cmp	r0, #0
+	beq	skip_tcmdisable
+	mov	r1, #0
+	mov	r2, #1
+	tst	r0, r2
+	mcrne	p15, 0, r1, c9, c1, 1	/* Disable Instruction TCM if present*/
+	tst	r0, r2, LSL #16
+	mcrne	p15, 0, r1, c9, c1, 0	/* Disable Data TCM if present*/
+skip_tcmdisable:
+#endif
+#endif
+
+#ifdef CONFIG_PERIPORT_REMAP
+	/* Peri port setup */
+	ldr	r0, =CONFIG_PERIPORT_BASE
+	orr	r0, r0, #CONFIG_PERIPORT_SIZE
+	mcr	p15,0,r0,c15,c2,4
+#endif
+
+	/*
+	 * Go setup Memory and board specific bits prior to relocation.
+	 */
+	bl	lowlevel_init		/* go setup pll,mux,memory */
+
+/* Set stackpointer in internal RAM to call board_init_f */
+call_board_init_f:
+	ldr	sp, =(CONFIG_SYS_INIT_SP_ADDR)
+	ldr	r0,=0x00000000
+	bl	board_init_f
+
+/*------------------------------------------------------------------------------*/
+
+/*
+ * void relocate_code (addr_sp, gd, addr_moni)
+ *
+ * This "function" does not return, instead it continues in RAM
+ * after relocating the monitor code.
+ *
+ */
+	.globl	relocate_code
+relocate_code:
+	mov	r4, r0	/* save addr_sp */
+	mov	r5, r1	/* save addr of gd */
+	mov	r6, r2	/* save addr of destination */
+	mov	r7, r2	/* save addr of destination */
+
+	/* Set up the stack						    */
+stack_setup:
+	mov	sp, r4
+
+	adr	r0, _start
+	ldr	r2, _TEXT_BASE
+	ldr	r3, _bss_start
+	sub	r2, r3, r2		/* r2 <- size of armboot	    */
+	add	r2, r0, r2		/* r2 <- source end address	    */
+	cmp	r0, r6
+	beq	clear_bss
+
+#ifndef CONFIG_SKIP_RELOCATE_UBOOT
+copy_loop:
+	ldmia	r0!, {r9-r10}		/* copy from source address [r0]    */
+	stmia	r6!, {r9-r10}		/* copy to   target address [r1]    */
+	cmp	r0, r2			/* until source end addreee [r2]    */
+	ble	copy_loop
+
+#ifndef CONFIG_PRELOADER
+	/* fix got entries */
+	ldr	r1, _TEXT_BASE		/* Text base */
+	mov	r0, r7			/* reloc addr */
+	ldr	r2, _got_start		/* addr in Flash */
+	ldr	r3, _got_end		/* addr in Flash */
+	sub	r3, r3, r1
+	add	r3, r3, r0
+	sub	r2, r2, r1
+	add	r2, r2, r0
+
+fixloop:
+	ldr	r4, [r2]
+	sub	r4, r4, r1
+	add	r4, r4, r0
+	str	r4, [r2]
+	add	r2, r2, #4
+	cmp	r2, r3
+	bne	fixloop
+#endif
+#endif	/* #ifndef CONFIG_SKIP_RELOCATE_UBOOT */
+
+#ifdef CONFIG_ENABLE_MMU
+enable_mmu:
+	/* enable domain access */
+	ldr	r5, =0x0000ffff
+	mcr	p15, 0, r5, c3, c0, 0	/* load domain access register */
+
+	/* Set the TTB register */
+	ldr	r0, _mmu_table_base
+	ldr	r1, =CONFIG_SYS_PHY_UBOOT_BASE
+	ldr	r2, =0xfff00000
+	bic	r0, r0, r2
+	orr	r1, r0, r1
+	mcr	p15, 0, r1, c2, c0, 0
+
+	/* Enable the MMU */
+	mrc	p15, 0, r0, c1, c0, 0
+	orr	r0, r0, #1		/* Set CR_M to enable MMU */
+
+	/* Prepare to enable the MMU */
+	adr	r1, skip_hw_init
+	and	r1, r1, #0x3fc
+	ldr	r2, _TEXT_BASE
+	ldr	r3, =0xfff00000
+	and	r2, r2, r3
+	orr	r2, r2, r1
+	b	mmu_enable
+
+	.align 5
+	/* Run in a single cache-line */
+mmu_enable:
+
+	mcr	p15, 0, r0, c1, c0, 0
+	nop
+	nop
+	mov	pc, r2
+skip_hw_init:
+#endif
+
+clear_bss:
+#ifndef CONFIG_PRELOADER
+	ldr	r0, _bss_start
+	ldr	r1, _bss_end
+	ldr	r3, _TEXT_BASE		/* Text base */
+	mov	r4, r7			/* reloc addr */
+	sub	r0, r0, r3
+	add	r0, r0, r4
+	sub	r1, r1, r3
+	add	r1, r1, r4
+	mov	r2, #0x00000000		/* clear			    */
+
+clbss_l:str	r2, [r0]		/* clear loop...		    */
+	add	r0, r0, #4
+	cmp	r0, r1
+	bne	clbss_l
+
+	bl coloured_LED_init
+	bl red_LED_on
+#endif
+
+/*
+ * We are done. Do not return, instead branch to second part of board
+ * initialization, now running from RAM.
+ */
+#ifdef CONFIG_NAND_SPL
+	ldr     pc, _nand_boot
+
+_nand_boot: .word nand_boot
+#else
+	ldr	r0, _TEXT_BASE
+	ldr	r2, _board_init_r
+	sub	r2, r2, r0
+	add	r2, r2, r7	/* position from board_init_r in RAM */
+	/* setup parameters for board_init_r */
+	mov	r0, r5		/* gd_t */
+	mov	r1, r7		/* dest_addr */
+	/* jump to it ... */
+	mov	lr, r2
+	mov	pc, lr
+
+_board_init_r: .word board_init_r
+#endif
+
+#else /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
+
 /*
  * the actual reset code
  */
@@ -299,6 +571,8 @@
 /*	.word nand_boot*/
 #endif
 
+#endif /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
+
 #ifdef CONFIG_ENABLE_MMU
 _mmu_table_base:
 	.word mmu_table
@@ -385,10 +659,14 @@
 	/* Save user registers (now in svc mode) r0-r12 */
 	stmia	sp, {r0 - r12}
 
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r2, _armboot_start
 	sub	r2, r2, #(CONFIG_SYS_MALLOC_LEN)
 	/* set base 2 words into abort stack */
 	sub	r2, r2, #(CONFIG_SYS_GBL_DATA_SIZE+8)
+#else
+	ldr	r2, IRQ_STACK_START_IN
+#endif
 	/* get values for "aborted" pc and cpsr (into parm regs) */
 	ldmia	r2, {r2 - r3}
 	/* grab pointer to old stack */
@@ -403,12 +681,16 @@
 	.endm
 
 	.macro get_bad_stack
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	/* setup our mode stack (enter in banked mode) */
 	ldr	r13, _armboot_start
 	/* move past malloc pool */
 	sub	r13, r13, #(CONFIG_SYS_MALLOC_LEN)
 	/* move to reserved a couple spots for abort stack */
 	sub	r13, r13, #(CONFIG_SYS_GBL_DATA_SIZE + 8)
+#else
+	ldr	r13, IRQ_STACK_START_IN		@ setup our mode stack
+#endif
 
 	/* save caller lr in position 0 of saved stack */
 	str	lr, [r13]
@@ -433,12 +715,16 @@
 	sub	r13, r13, #4
 	/* save R0's value. */
 	str	r0, [r13]
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	/* get data regions start */
 	ldr	r0, _armboot_start
 	/* move past malloc pool */
 	sub	r0, r0, #(CONFIG_SYS_MALLOC_LEN)
 	/* move past gbl and a couple spots for abort stack */
 	sub	r0, r0, #(CONFIG_SYS_GBL_DATA_SIZE + 8)
+#else
+	ldr	r13, IRQ_STACK_START_IN		@ setup our mode stack
+#endif
 	/* save caller lr in position 0 of saved stack */
 	str	lr, [r0]
 	/* get the spsr */
diff --git a/arch/arm/cpu/arm1176/u-boot.lds b/arch/arm/cpu/arm1176/u-boot.lds
index 8969587..fa640ee 100644
--- a/arch/arm/cpu/arm1176/u-boot.lds
+++ b/arch/arm/cpu/arm1176/u-boot.lds
@@ -39,11 +39,23 @@
 	.rodata : { *(SORT_BY_ALIGNMENT(SORT_BY_NAME(.rodata*))) }
 
 	. = ALIGN(4);
-	.data : { *(.data) }
+	.data : {
+		*(.data)
+	__datarel_start = .;
+		*(.data.rel)
+	__datarelrolocal_start = .;
+		*(.data.rel.ro.local)
+	__datarellocal_start = .;
+		*(.data.rel.local)
+	__datarelro_start = .;
+		*(.data.rel.ro)
+	}
 
+	__got_start = .;
 	. = ALIGN(4);
 	.got : { *(.got) }
 
+	__got_end = .;
 	. = .;
 	__u_boot_cmd_start = .;
 	.u_boot_cmd : { *(.u_boot_cmd) }