Merge branch 'next' of /home/wd/git/u-boot/next

Conflicts:
	include/ppc4xx.h

Signed-off-by: Wolfgang Denk <wd@denx.de>

42 files changed, 3740 insertions, 47 deletions

diff --git a/arch/arm/config.mk b/arch/arm/config.mk
index e10dafca58..6923f6dafa 100644
--- a/arch/arm/config.mk
+++ b/arch/arm/config.mk
@@ -33,6 +33,14 @@ STANDALONE_LOAD_ADDR = 0xc100000
 endif
 endif
 
+ifndef CONFIG_SYS_ARM_WITHOUT_RELOC
+# needed for relocation
+PLATFORM_RELFLAGS += -fPIC
+endif
+
+ifdef CONFIG_SYS_ARM_WITHOUT_RELOC
+PLATFORM_CPPFLAGS += -DCONFIG_SYS_ARM_WITHOUT_RELOC
+endif
 PLATFORM_CPPFLAGS += -DCONFIG_ARM -D__ARM__
 
 # Explicitly specifiy 32-bit ARM ISA since toolchain default can be -mthumb:
diff --git a/arch/arm/cpu/arm1136/start.S b/arch/arm/cpu/arm1136/start.S
index 41eb82dae2..8b631920c9 100644
--- a/arch/arm/cpu/arm1136/start.S
+++ b/arch/arm/cpu/arm1136/start.S
@@ -85,12 +85,15 @@ _end_vect:
  *************************************************************************
  */
 
+.globl _TEXT_BASE
 _TEXT_BASE:
 	.word	TEXT_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.
@@ -103,6 +106,32 @@ _bss_start:
 _bss_end:
 	.word _end
 
+#if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
+.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
+#endif
+
 #ifdef CONFIG_USE_IRQ
 /* IRQ stack memory (calculated at run-time) */
 .globl IRQ_STACK_START
@@ -115,6 +144,164 @@ FIQ_STACK_START:
 	.word 0x0badc0de
 #endif
 
+#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
+#endif
+
+#if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
+/*
+ * the actual reset code
+ */
+
+reset:
+	/*
+	 * set the cpu to SVC32 mode
+	 */
+	mrs	r0,cpsr
+	bic	r0,r0,#0x1f
+	orr	r0,r0,#0xd3
+	msr	cpsr,r0
+
+#ifdef CONFIG_OMAP2420H4
+       /* Copy vectors to mask ROM indirect addr */
+	adr	r0, _start		/* r0 <- current position of code   */
+		add     r0, r0, #4				/* skip reset vector			*/
+	mov	r2, #64			/* r2 <- size to copy  */
+	add	r2, r0, r2		/* r2 <- source end address	    */
+	mov	r1, #SRAM_OFFSET0	  /* build vect addr */
+	mov	r3, #SRAM_OFFSET1
+	add	r1, r1, r3
+	mov	r3, #SRAM_OFFSET2
+	add	r1, r1, r3
+next:
+	ldmia	r0!, {r3-r10}		/* copy from source address [r0]    */
+	stmia	r1!, {r3-r10}		/* copy to   target address [r1]    */
+	cmp	r0, r2			/* until source end address [r2]    */
+	bne	next			/* loop until equal */
+	bl	cpy_clk_code		/* put dpll adjust code behind vectors */
+#endif
+	/* the mask ROM code should have PLL and others stable */
+#ifndef CONFIG_SKIP_LOWLEVEL_INIT
+	bl  cpu_init_crit
+#endif
+
+/* Set stackpointer in internal RAM to call board_init_f */
+call_board_init_f:
+	ldr	sp, =(CONFIG_SYS_INIT_SP_ADDR)
+	ldr	r0,=0x00000000
+
+#ifdef CONFIG_NAND_SPL
+	bl	nand_boot
+#else
+#ifdef CONFIG_ONENAND_IPL
+	bl	start_oneboot
+#else
+	bl	board_init_f
+#endif /* CONFIG_ONENAND_IPL */
+#endif /* CONFIG_NAND_SPL */
+
+/*------------------------------------------------------------------------------*/
+
+/*
+ * 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
+	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 */
+
+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
+#endif	/* #ifndef CONFIG_PRELOADER */
+
+/*
+ * 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
+jump_2_ram:
+	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
  */
@@ -211,6 +398,8 @@ _start_armboot: .word start_armboot
 #endif /* CONFIG_ONENAND_IPL */
 #endif /* CONFIG_NAND_SPL */
 
+#endif /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
+
 /*
  *************************************************************************
  *
@@ -295,9 +484,13 @@ cpu_init_crit:
 	sub	sp, sp, #S_FRAME_SIZE		@ carve out a frame on current user stack
 	stmia	sp, {r0 - r12}			@ Save user registers (now in svc mode) r0-r12
 
+#if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
+	ldr	r2, IRQ_STACK_START_IN		@ set base 2 words into abort stack
+#else
 	ldr	r2, _armboot_start
 	sub	r2, r2, #(CONFIG_SYS_MALLOC_LEN)
 	sub	r2, r2, #(CONFIG_SYS_GBL_DATA_SIZE+8)	@ set base 2 words into abort stack
+#endif
 	ldmia	r2, {r2 - r3}			@ get values for "aborted" pc and cpsr (into parm regs)
 	add	r0, sp, #S_FRAME_SIZE		@ grab pointer to old stack
 
@@ -328,9 +521,13 @@ cpu_init_crit:
 	.endm
 
 	.macro get_bad_stack
+#if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
+	ldr	r13, IRQ_STACK_START_IN		@ setup our mode stack (enter in banked mode)
+#else
 	ldr	r13, _armboot_start		@ setup our mode stack (enter in banked mode)
 	sub	r13, r13, #(CONFIG_SYS_MALLOC_LEN)	@ move past malloc pool
 	sub	r13, r13, #(CONFIG_SYS_GBL_DATA_SIZE+8) @ move to reserved a couple spots for abort stack
+#endif
 
 	str	lr, [r13]			@ save caller lr in position 0 of saved stack
 	mrs	lr, spsr			@ get the spsr
@@ -346,9 +543,13 @@ cpu_init_crit:
 	.macro get_bad_stack_swi
 	sub	r13, r13, #4			@ space on current stack for scratch reg.
 	str	r0, [r13]			@ save R0's value.
+#if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
+	ldr	r0, IRQ_STACK_START_IN		@ get data regions start
+#else
 	ldr	r0, _armboot_start		@ get data regions start
 	sub	r0, r0, #(CONFIG_SYS_MALLOC_LEN)	@ move past malloc pool
 	sub	r0, r0, #(CONFIG_SYS_GBL_DATA_SIZE+8)	@ move past gbl and a couple spots for abort stack
+#endif
 	str	lr, [r0]			@ save caller lr in position 0 of saved stack
 	mrs	r0, spsr			@ get the spsr
 	str	lr, [r0, #4]			@ save spsr in position 1 of saved stack
@@ -439,6 +640,11 @@ fiq:
 	.align 5
 .global arm1136_cache_flush
 arm1136_cache_flush:
+#if !defined(CONFIG_SYS_NO_ICACHE)
 		mcr	p15, 0, r1, c7, c5, 0	@ invalidate I cache
+#endif
+#if !defined(CONFIG_SYS_NO_DCACHE)
+		mcr	p15, 0, r1, c7, c14, 0	@ invalidate D cache
+#endif
 		mov	pc, lr			@ back to caller
 #endif	/* CONFIG_PRELOADER */
diff --git a/arch/arm/cpu/arm1136/u-boot.lds b/arch/arm/cpu/arm1136/u-boot.lds
index e7eefc972c..1db4b49cc7 100644
--- a/arch/arm/cpu/arm1136/u-boot.lds
+++ b/arch/arm/cpu/arm1136/u-boot.lds
@@ -47,11 +47,23 @@ SECTIONS
 	.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) }
diff --git a/arch/arm/cpu/arm1176/start.S b/arch/arm/cpu/arm1176/start.S
index f98a7aa355..e5e7913d94 100644
--- a/arch/arm/cpu/arm1176/start.S
+++ b/arch/arm/cpu/arm1176/start.S
@@ -95,6 +95,7 @@ _end_vect:
  *************************************************************************
  */
 
+.globl _TEXT_BASE
 _TEXT_BASE:
 	.word	TEXT_BASE
 
@@ -106,9 +107,11 @@ _TEXT_BASE:
 _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_start:
 _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 @@ _start_armboot:
 /*	.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 @@ phy_last_jump:
 	/* 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 @@ phy_last_jump:
 	.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 @@ phy_last_jump:
 	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 8969587e8c..fa640eec20 100644
--- a/arch/arm/cpu/arm1176/u-boot.lds
+++ b/arch/arm/cpu/arm1176/u-boot.lds
@@ -39,11 +39,23 @@ SECTIONS
 	.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) }
diff --git a/arch/arm/cpu/arm720t/start.S b/arch/arm/cpu/arm720t/start.S
index d6f2c165c7..0f5f6c4611 100644
--- a/arch/arm/cpu/arm720t/start.S
+++ b/arch/arm/cpu/arm720t/start.S
@@ -75,12 +75,15 @@ _fiq:			.word fiq
  *************************************************************************
  */
 
+.globl _TEXT_BASE
 _TEXT_BASE:
 	.word	TEXT_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.
@@ -105,6 +108,163 @@ FIQ_STACK_START:
 	.word 0x0badc0de
 #endif
 
+#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,#0x1f
+	orr	r0,r0,#0xd3
+	msr	cpsr,r0
+
+	/*
+	 * we do sys-critical inits only at reboot,
+	 * not when booting from ram!
+	 */
+#ifndef CONFIG_SKIP_LOWLEVEL_INIT
+	bl	cpu_init_crit
+#endif
+
+#ifdef CONFIG_LPC2292
+	bl	lowlevel_init
+#endif
+
+/* 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 */
+
+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.
+ */
+	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
+
+#else /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 
 /*
  * the actual reset code
@@ -188,6 +348,8 @@ clbss_l:str	r2, [r0]		/* clear loop...		    */
 
 _start_armboot: .word start_armboot
 
+#endif /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
+
 /*
  *************************************************************************
  *
@@ -444,9 +606,13 @@ lock_loop:
 	stmia	sp, {r0 - r12}			@ Calling r0-r12
 	add	r8, sp, #S_PC
 
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r2, _armboot_start
 	sub	r2, r2, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r2, r2, #(CONFIG_SYS_GBL_DATA_SIZE+8)	@ set base 2 words into abort stack
+#else
+	ldr	r2, IRQ_STACK_START_IN
+#endif
 	ldmia	r2, {r2 - r4}			@ get pc, cpsr, old_r0
 	add	r0, sp, #S_FRAME_SIZE		@ restore sp_SVC
 
@@ -477,9 +643,13 @@ lock_loop:
 	.endm
 
 	.macro get_bad_stack
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r13, _armboot_start		@ setup our mode stack
 	sub	r13, r13, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r13, r13, #(CONFIG_SYS_GBL_DATA_SIZE+8) @ reserved a couple spots in abort stack
+#else
+	ldr	r13, IRQ_STACK_START_IN		@ setup our mode stack
+#endif
 
 	str	lr, [r13]			@ save caller lr / spsr
 	mrs	lr, spsr
diff --git a/arch/arm/cpu/arm720t/u-boot.lds b/arch/arm/cpu/arm720t/u-boot.lds
index c975fc3d5e..4a0bc70c77 100644
--- a/arch/arm/cpu/arm720t/u-boot.lds
+++ b/arch/arm/cpu/arm720t/u-boot.lds
@@ -39,11 +39,23 @@ SECTIONS
 	.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) }
diff --git a/arch/arm/cpu/arm920t/start.S b/arch/arm/cpu/arm920t/start.S
index e532f55bfc..a079bb2727 100644
--- a/arch/arm/cpu/arm920t/start.S
+++ b/arch/arm/cpu/arm920t/start.S
@@ -70,12 +70,15 @@ _fiq:			.word fiq
  *************************************************************************
  */
 
+.globl _TEXT_BASE
 _TEXT_BASE:
 	.word	TEXT_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.
@@ -100,6 +103,35 @@ FIQ_STACK_START:
 	.word 0x0badc0de
 #endif
 
+#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 start code
@@ -176,6 +208,189 @@ copyex:
 	bl	cpu_init_crit
 #endif
 
+/* 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 */
+
+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 start code
+ */
+
+start_code:
+	/*
+	 * set the cpu to SVC32 mode
+	 */
+	mrs	r0, cpsr
+	bic	r0, r0, #0x1f
+	orr	r0, r0, #0xd3
+	msr	cpsr, r0
+
+	bl	coloured_LED_init
+	bl	red_LED_on
+
+#if	defined(CONFIG_AT91RM9200DK) || defined(CONFIG_AT91RM9200EK)
+	/*
+	 * relocate exception table
+	 */
+	ldr	r0, =_start
+	ldr	r1, =0x0
+	mov	r2, #16
+copyex:
+	subs	r2, r2, #1
+	ldr	r3, [r0], #4
+	str	r3, [r1], #4
+	bne	copyex
+#endif
+
+#ifdef CONFIG_S3C24X0
+	/* turn off the watchdog */
+
+# if defined(CONFIG_S3C2400)
+#  define pWTCON	0x15300000
+#  define INTMSK	0x14400008	/* Interupt-Controller base addresses */
+#  define CLKDIVN	0x14800014	/* clock divisor register */
+#else
+#  define pWTCON	0x53000000
+#  define INTMSK	0x4A000008	/* Interupt-Controller base addresses */
+#  define INTSUBMSK	0x4A00001C
+#  define CLKDIVN	0x4C000014	/* clock divisor register */
+# endif
+
+	ldr	r0, =pWTCON
+	mov	r1, #0x0
+	str	r1, [r0]
+
+	/*
+	 * mask all IRQs by setting all bits in the INTMR - default
+	 */
+	mov	r1, #0xffffffff
+	ldr	r0, =INTMSK
+	str	r1, [r0]
+# if defined(CONFIG_S3C2410)
+	ldr	r1, =0x3ff
+	ldr	r0, =INTSUBMSK
+	str	r1, [r0]
+# endif
+
+	/* FCLK:HCLK:PCLK = 1:2:4 */
+	/* default FCLK is 120 MHz ! */
+	ldr	r0, =CLKDIVN
+	mov	r1, #3
+	str	r1, [r0]
+#endif	/* CONFIG_S3C24X0 */
+
+	/*
+	 * we do sys-critical inits only at reboot,
+	 * not when booting from ram!
+	 */
+#ifndef CONFIG_SKIP_LOWLEVEL_INIT
+	bl	cpu_init_crit
+#endif
+
 #ifndef CONFIG_SKIP_RELOCATE_UBOOT
 relocate:				/* relocate U-Boot to RAM	    */
 	adr	r0, _start		/* r0 <- current position of code   */
@@ -219,7 +434,7 @@ clbss_l:str	r2, [r0]		/* clear loop...                    */
 	ldr	pc, _start_armboot
 
 _start_armboot:	.word start_armboot
-
+#endif /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 
 /*
  *************************************************************************
@@ -309,11 +524,15 @@ cpu_init_crit:
 	.macro	bad_save_user_regs
 	sub	sp, sp, #S_FRAME_SIZE
 	stmia	sp, {r0 - r12}			@ Calling r0-r12
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r2, _armboot_start
 	sub	r2, r2, #(CONFIG_STACKSIZE)
 	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
 	ldmia	r2, {r2 - r3}			@ get pc, cpsr
 	add	r0, sp, #S_FRAME_SIZE		@ restore sp_SVC
 
@@ -345,11 +564,15 @@ cpu_init_crit:
 	.endm
 
 	.macro get_bad_stack
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r13, _armboot_start		@ setup our mode stack
 	sub	r13, r13, #(CONFIG_STACKSIZE)
 	sub	r13, r13, #(CONFIG_SYS_MALLOC_LEN)
 	/* reserve a couple spots in abort stack */
 	sub	r13, r13, #(CONFIG_SYS_GBL_DATA_SIZE+8)
+#else
+	ldr	r13, IRQ_STACK_START_IN		@ setup our mode stack
+#endif
 
 	str	lr, [r13]			@ save caller lr / spsr
 	mrs	lr, spsr
diff --git a/arch/arm/cpu/arm920t/u-boot.lds b/arch/arm/cpu/arm920t/u-boot.lds
index a7decfcd7d..6985434795 100644
--- a/arch/arm/cpu/arm920t/u-boot.lds
+++ b/arch/arm/cpu/arm920t/u-boot.lds
@@ -47,11 +47,23 @@ SECTIONS
 	.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) }
diff --git a/arch/arm/cpu/arm925t/start.S b/arch/arm/cpu/arm925t/start.S
index 346615e4b4..c0a856dfe1 100644
--- a/arch/arm/cpu/arm925t/start.S
+++ b/arch/arm/cpu/arm925t/start.S
@@ -81,12 +81,15 @@ _fiq:			.word fiq
  *************************************************************************
  */
 
+.globl _TEXT_BASE
 _TEXT_BASE:
 	.word	TEXT_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.
@@ -111,7 +114,198 @@ FIQ_STACK_START:
 	.word 0x0badc0de
 #endif
 
+#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,#0x1f
+	orr	r0,r0,#0xd3
+	msr	cpsr,r0
+
+	/*
+	 * Set up 925T mode
+	 */
+	mov r1, #0x81               /* Set ARM925T configuration. */
+	mcr p15, 0, r1, c15, c1, 0  /* Write ARM925T configuration register. */
+
+	/*
+	 * turn off the watchdog, unlock/diable sequence
+	 */
+	mov  r1, #0xF5
+	ldr  r0, =WDTIM_MODE
+	strh r1, [r0]
+	mov  r1, #0xA0
+	strh r1, [r0]
+
+	/*
+	 * mask all IRQs by setting all bits in the INTMR - default
+	 */
+	mov r1, #0xffffffff
+	ldr r0, =REG_IHL1_MIR
+	str r1, [r0]
+	ldr r0, =REG_IHL2_MIR
+	str r1, [r0]
+
+	/*
+	 * wait for dpll to lock
+	 */
+	ldr  r0, =CK_DPLL1
+	mov  r1, #0x10
+	strh r1, [r0]
+poll1:
+	ldrh r1, [r0]
+	ands r1, r1, #0x01
+	beq poll1
+
+	/*
+	 * we do sys-critical inits only at reboot,
+	 * not when booting from ram!
+	 */
+#ifndef CONFIG_SKIP_LOWLEVEL_INIT
+	bl  cpu_init_crit
+#endif
+
+/* 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 */
+
+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
 
+#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
  */
@@ -211,7 +405,7 @@ clbss_l:str	r2, [r0]		/* clear loop...                    */
 	ldr	pc, _start_armboot
 
 _start_armboot:	.word start_armboot
-
+#endif /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 
 /*
  *************************************************************************
@@ -295,9 +489,13 @@ cpu_init_crit:
 	sub	sp, sp, #S_FRAME_SIZE           @ carve out a frame on current user stack
 	stmia	sp, {r0 - r12}			@ Save user registers (now in svc mode) r0-r12
 
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r2, _armboot_start
 	sub	r2, r2, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r2, r2, #(CONFIG_SYS_GBL_DATA_SIZE+8)  @ set base 2 words into abort stack
+#else
+	ldr	r2, IRQ_STACK_START_IN
+#endif
 	ldmia	r2, {r2 - r3}                   @ get values for "aborted" pc and cpsr (into parm regs)
 	add	r0, sp, #S_FRAME_SIZE		@ grab pointer to old stack
 
@@ -328,9 +526,13 @@ cpu_init_crit:
 	.endm
 
 	.macro get_bad_stack
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r13, _armboot_start		@ setup our mode stack
 	sub	r13, r13, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r13, r13, #(CONFIG_SYS_GBL_DATA_SIZE+8) @ reserved a couple spots in abort stack
+#else
+	ldr	r13, IRQ_STACK_START_IN
+#endif
 
 	str	lr, [r13]			@ save caller lr in position 0 of saved stack
 	mrs	lr, spsr                        @ get the spsr
diff --git a/arch/arm/cpu/arm925t/u-boot.lds b/arch/arm/cpu/arm925t/u-boot.lds
index e21d6dc5a7..1c4e9bcfb5 100644
--- a/arch/arm/cpu/arm925t/u-boot.lds
+++ b/arch/arm/cpu/arm925t/u-boot.lds
@@ -42,11 +42,23 @@ SECTIONS
 	.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) }
diff --git a/arch/arm/cpu/arm926ejs/orion5x/dram.c b/arch/arm/cpu/arm926ejs/orion5x/dram.c
index c719798a66..c5c8ab7e4d 100644
--- a/arch/arm/cpu/arm926ejs/orion5x/dram.c
+++ b/arch/arm/cpu/arm926ejs/orion5x/dram.c
@@ -49,7 +49,7 @@ u32 orion5x_sdram_bar(enum memory_bank bank)
 	result = winregs[bank].base;
 	return result;
 }
-
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 int dram_init(void)
 {
 	int i;
@@ -62,3 +62,25 @@ int dram_init(void)
 	}
 	return 0;
 }
+#else
+int dram_init (void)
+{
+	/* dram_init must store complete ramsize in gd->ram_size */
+	gd->ram_size = get_ram_size(
+			(volatile long *) orion5x_sdram_bar(0),
+			CONFIG_MAX_RAM_BANK_SIZE);
+	return 0;
+}
+
+void dram_init_banksize (void)
+{
+	int i;
+
+	for (i = 0; i < CONFIG_NR_DRAM_BANKS; i++) {
+		gd->bd->bi_dram[i].start = orion5x_sdram_bar(i);
+		gd->bd->bi_dram[i].size = get_ram_size(
+			(volatile long *) (gd->bd->bi_dram[i].start),
+			CONFIG_MAX_RAM_BANK_SIZE);
+	}
+}
+#endif
diff --git a/arch/arm/cpu/arm926ejs/start.S b/arch/arm/cpu/arm926ejs/start.S
index cf40ce1292..16ee972f2b 100644
--- a/arch/arm/cpu/arm926ejs/start.S
+++ b/arch/arm/cpu/arm926ejs/start.S
@@ -114,12 +114,15 @@ _fiq:
  *************************************************************************
  */
 
+.globl _TEXT_BASE
 _TEXT_BASE:
 	.word	TEXT_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.
@@ -144,6 +147,35 @@ FIQ_STACK_START:
 	.word 0x0badc0de
 #endif
 
+#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
@@ -166,6 +198,135 @@ reset:
 	bl	cpu_init_crit
 #endif
 
+/* 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 */
+
+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
+ */
+
+reset:
+	/*
+	 * set the cpu to SVC32 mode
+	 */
+	mrs	r0,cpsr
+	bic	r0,r0,#0x1f
+	orr	r0,r0,#0xd3
+	msr	cpsr,r0
+
+	/*
+	 * we do sys-critical inits only at reboot,
+	 * not when booting from ram!
+	 */
+#ifndef CONFIG_SKIP_LOWLEVEL_INIT
+	bl	cpu_init_crit
+#endif
+
 #ifndef CONFIG_SKIP_RELOCATE_UBOOT
 relocate:				/* relocate U-Boot to RAM	    */
 	adr	r0, _start		/* r0 <- current position of code   */
@@ -221,7 +382,7 @@ _start_armboot:
 #else
 	.word start_armboot
 #endif /* CONFIG_NAND_SPL */
-
+#endif /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 
 /*
  *************************************************************************
@@ -307,10 +468,13 @@ cpu_init_crit:
 	@ carve out a frame on current user stack
 	sub	sp, sp, #S_FRAME_SIZE
 	stmia	sp, {r0 - r12}	@ Save user registers (now in svc mode) r0-r12
-
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r2, _armboot_start
 	sub	r2, r2, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r2, r2, #(CONFIG_SYS_GBL_DATA_SIZE+8)  @ set base 2 words into abort stack
+#else
+	ldr	r2, IRQ_STACK_START_IN
+#endif
 	@ get values for "aborted" pc and cpsr (into parm regs)
 	ldmia	r2, {r2 - r3}
 	add	r0, sp, #S_FRAME_SIZE		@ grab pointer to old stack
@@ -342,9 +506,13 @@ cpu_init_crit:
 	.endm
 
 	.macro get_bad_stack
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r13, _armboot_start		@ setup our mode stack
 	sub	r13, r13, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r13, r13, #(CONFIG_SYS_GBL_DATA_SIZE+8) @ reserved a couple spots in abort stack
+#else
+	ldr	r13, IRQ_STACK_START_IN		@ setup our mode stack
+#endif
 
 	str	lr, [r13]	@ save caller lr in position 0 of saved stack
 	mrs	lr, spsr	@ get the spsr
diff --git a/arch/arm/cpu/arm926ejs/u-boot.lds b/arch/arm/cpu/arm926ejs/u-boot.lds
index ecbc58c7c2..02eb8ca607 100644
--- a/arch/arm/cpu/arm926ejs/u-boot.lds
+++ b/arch/arm/cpu/arm926ejs/u-boot.lds
@@ -39,11 +39,23 @@ SECTIONS
 	.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) }
diff --git a/arch/arm/cpu/arm946es/start.S b/arch/arm/cpu/arm946es/start.S
index 8844d4438b..18ed0b2da4 100644
--- a/arch/arm/cpu/arm946es/start.S
+++ b/arch/arm/cpu/arm946es/start.S
@@ -85,12 +85,15 @@ _fiq:
  *************************************************************************
  */
 
+.globl _TEXT_BASE
 _TEXT_BASE:
 	.word	TEXT_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.
@@ -115,7 +118,162 @@ FIQ_STACK_START:
 	.word 0x0badc0de
 #endif
 
+#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,#0x1f
+	orr	r0,r0,#0xd3
+	msr	cpsr,r0
+
+	/*
+	 * we do sys-critical inits only at reboot,
+	 * not when booting from ram!
+	 */
+#ifndef CONFIG_SKIP_LOWLEVEL_INIT
+	bl	cpu_init_crit
+#endif
+
+/* 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 */
+
+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
+#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
  */
@@ -179,7 +337,7 @@ clbss_l:str	r2, [r0]		/* clear loop...                    */
 
 _start_armboot:
 	.word start_armboot
-
+#endif /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 
 /*
  *************************************************************************
@@ -266,9 +424,13 @@ cpu_init_crit:
 	sub	sp, sp, #S_FRAME_SIZE
 	stmia	sp, {r0 - r12}	@ Save user registers (now in svc mode) r0-r12
 
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r2, _armboot_start
 	sub	r2, r2, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r2, r2, #(CONFIG_SYS_GBL_DATA_SIZE+8)  @ set base 2 words into abort stack
+#else
+	ldr	r2, IRQ_STACK_START_IN
+#endif
 	@ get values for "aborted" pc and cpsr (into parm regs)
 	ldmia	r2, {r2 - r3}
 	add	r0, sp, #S_FRAME_SIZE		@ grab pointer to old stack
@@ -300,9 +462,13 @@ cpu_init_crit:
 	.endm
 
 	.macro get_bad_stack
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r13, _armboot_start		@ setup our mode stack
 	sub	r13, r13, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r13, r13, #(CONFIG_SYS_GBL_DATA_SIZE+8) @ reserved a couple spots in abort stack
+#else
+	ldr	r13, IRQ_STACK_START_IN		@ setup our mode stack
+#endif
 
 	str	lr, [r13]	@ save caller lr in position 0 of saved stack
 	mrs	lr, spsr	@ get the spsr
diff --git a/arch/arm/cpu/arm946es/u-boot.lds b/arch/arm/cpu/arm946es/u-boot.lds
index fef21c7587..6535963093 100644
--- a/arch/arm/cpu/arm946es/u-boot.lds
+++ b/arch/arm/cpu/arm946es/u-boot.lds
@@ -39,11 +39,23 @@ SECTIONS
 	.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) }
diff --git a/arch/arm/cpu/arm_intcm/start.S b/arch/arm/cpu/arm_intcm/start.S
index 328bae0274..b39fdc64c4 100644
--- a/arch/arm/cpu/arm_intcm/start.S
+++ b/arch/arm/cpu/arm_intcm/start.S
@@ -83,12 +83,15 @@ _fiq:
  *************************************************************************
  */
 
+.globl _TEXT_BASE
 _TEXT_BASE:
 	.word	TEXT_BASE /* address of _start in the linked image */
 
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 .globl _armboot_start
 _armboot_start:
 	.word _start
+#endif
 
 /*
  * These are defined in the board-specific linker script.
@@ -113,6 +116,159 @@ FIQ_STACK_START:
 	.word 0x0badc0de
 #endif
 
+#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,#0x1f
+	orr	r0,r0,#0xd3
+	msr	cpsr,r0
+
+	/*
+	 * we do sys-critical inits only at reboot,
+	 * not when booting from ram!
+	 */
+#ifndef CONFIG_SKIP_LOWLEVEL_INIT
+	bl	cpu_init_crit
+#endif
+
+/* 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 */
+
+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.
+ */
+	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
+
+#else /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 
 /*
  * the actual reset code
@@ -178,6 +334,8 @@ clbss_l:str	r2, [r0]		/* clear loop...                    */
 _start_armboot:
 	.word start_armboot
 
+#endif /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
+
 /*
  *************************************************************************
  *
@@ -242,9 +400,13 @@ cpu_init_crit:
 	sub	sp, sp, #S_FRAME_SIZE
 	stmia	sp, {r0 - r12}	@ Save user registers (now in svc mode) r0-r12
 
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r2, _armboot_start
 	sub	r2, r2, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r2, r2, #(CONFIG_SYS_GBL_DATA_SIZE+8)  @ set base 2 words into abort stack
+#else
+	ldr	r2, IRQ_STACK_START_IN
+#endif
 	@ get values for "aborted" pc and cpsr (into parm regs)
 	ldmia	r2, {r2 - r3}
 	add	r0, sp, #S_FRAME_SIZE		@ grab pointer to old stack
@@ -276,9 +438,13 @@ cpu_init_crit:
 	.endm
 
 	.macro get_bad_stack
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r13, _armboot_start		@ setup our mode stack
 	sub	r13, r13, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r13, r13, #(CONFIG_SYS_GBL_DATA_SIZE+8) @ reserved a couple spots in abort stack
+#else
+	ldr	r13, IRQ_STACK_START_IN		@ setup our mode stack
+#endif
 
 	str	lr, [r13]	@ save caller lr in position 0 of saved stack
 	mrs	lr, spsr	@ get the spsr
diff --git a/arch/arm/cpu/arm_intcm/u-boot.lds b/arch/arm/cpu/arm_intcm/u-boot.lds
index 4ed7d8906d..242c7ece02 100644
--- a/arch/arm/cpu/arm_intcm/u-boot.lds
+++ b/arch/arm/cpu/arm_intcm/u-boot.lds
@@ -39,11 +39,23 @@ SECTIONS
 	.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) }
diff --git a/arch/arm/cpu/armv7/mx51/u-boot.lds b/arch/arm/cpu/armv7/mx51/u-boot.lds
index d66434c95d..55d6599b41 100644
--- a/arch/arm/cpu/armv7/mx51/u-boot.lds
+++ b/arch/arm/cpu/armv7/mx51/u-boot.lds
@@ -44,10 +44,22 @@ SECTIONS
 	.rodata : { *(.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 = .;
diff --git a/arch/arm/cpu/armv7/omap3/cache.S b/arch/arm/cpu/armv7/omap3/cache.S
index fdc1666fe9..cda87ba1af 100644
--- a/arch/arm/cpu/armv7/omap3/cache.S
+++ b/arch/arm/cpu/armv7/omap3/cache.S
@@ -181,3 +181,83 @@ setup_auxcr:
 	orrlt	r0, r0, #1 << 27
 	.word 0xE1600070			@ SMC
 	bx	lr
+
+.align 5
+.global v7_flush_dcache_all
+.global v7_flush_cache_all
+
+/*
+ *	v7_flush_dcache_all()
+ *
+ *	Flush the whole D-cache.
+ *
+ *	Corrupted registers: r0-r7, r9-r11 (r6 only in Thumb mode)
+ *
+ *	- mm    - mm_struct describing address space
+ */
+v7_flush_dcache_all:
+#	dmb					@ ensure ordering with previous memory accesses
+	mrc	p15, 1, r0, c0, c0, 1		@ read clidr
+	ands	r3, r0, #0x7000000		@ extract loc from clidr
+	mov	r3, r3, lsr #23			@ left align loc bit field
+	beq	finished			@ if loc is 0, then no need to clean
+	mov	r10, #0				@ start clean at cache level 0
+loop1:
+	add	r2, r10, r10, lsr #1		@ work out 3x current cache level
+	mov	r1, r0, lsr r2			@ extract cache type bits from clidr
+	and	r1, r1, #7			@ mask of the bits for current cache only
+	cmp	r1, #2				@ see what cache we have at this level
+	blt	skip				@ skip if no cache, or just i-cache
+	mcr	p15, 2, r10, c0, c0, 0		@ select current cache level in cssr
+	mcr	p15, 0, r10, c7, c5, 4		@ flush prefetch buffer,
+						@ with armv7 this is 'isb',
+						@ but we compile with armv5
+	mrc	p15, 1, r1, c0, c0, 0		@ read the new csidr
+	and	r2, r1, #7			@ extract the length of the cache lines
+	add	r2, r2, #4			@ add 4 (line length offset)
+	ldr	r4, =0x3ff
+	ands	r4, r4, r1, lsr #3		@ find maximum number on the way size
+	clz	r5, r4				@ find bit position of way size increment
+	ldr	r7, =0x7fff
+	ands	r7, r7, r1, lsr #13		@ extract max number of the index size
+loop2:
+	mov	r9, r4				@ create working copy of max way size
+loop3:
+	orr	r11, r10, r9, lsl r5		@ factor way and cache number into r11
+	orr	r11, r11, r7, lsl r2		@ factor index number into r11
+	mcr	p15, 0, r11, c7, c14, 2		@ clean & invalidate by set/way
+	subs	r9, r9, #1			@ decrement the way
+	bge	loop3
+	subs	r7, r7, #1			@ decrement the index
+	bge	loop2
+skip:
+	add	r10, r10, #2			@ increment cache number
+	cmp	r3, r10
+	bgt	loop1
+finished:
+	mov	r10, #0				@ swith back to cache level 0
+	mcr	p15, 2, r10, c0, c0, 0		@ select current cache level in cssr
+#	dsb
+	mcr	p15, 0, r10, c7, c5, 4		@ flush prefetch buffer,
+						@ with armv7 this is 'isb',
+						@ but we compile with armv5
+	mov	pc, lr
+
+/*
+ *	v7_flush_cache_all()
+ *
+ *	Flush the entire cache system.
+ *  The data cache flush is now achieved using atomic clean / invalidates
+ *  working outwards from L1 cache. This is done using Set/Way based cache
+ *  maintainance instructions.
+ *  The instruction cache can still be invalidated back to the point of
+ *  unification in a single instruction.
+ *
+ */
+v7_flush_cache_all:
+	stmfd	sp!, {r0-r7, r9-r11, lr}
+	bl	v7_flush_dcache_all
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ I+BTB cache invalidate
+	ldmfd	sp!, {r0-r7, r9-r11, lr}
+	mov	pc, lr
diff --git a/arch/arm/cpu/armv7/omap3/emif4.c b/arch/arm/cpu/armv7/omap3/emif4.c
index fae5b1161b..da2cd90013 100644
--- a/arch/arm/cpu/armv7/omap3/emif4.c
+++ b/arch/arm/cpu/armv7/omap3/emif4.c
@@ -136,6 +136,7 @@ void do_emif4_init(void)
  * dram_init -
  *  - Sets uboots idea of sdram size
  */
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 int dram_init(void)
 {
 	DECLARE_GLOBAL_DATA_PTR;
@@ -157,6 +158,39 @@ int dram_init(void)
 
 	return 0;
 }
+#else
+int dram_init(void)
+{
+	DECLARE_GLOBAL_DATA_PTR;
+	unsigned int size0 = 0, size1 = 0;
+
+	size0 = get_sdr_cs_size(CS0);
+	/*
+	 * If a second bank of DDR is attached to CS1 this is
+	 * where it can be started.  Early init code will init
+	 * memory on CS0.
+	 */
+	if ((sysinfo.mtype == DDR_COMBO) || (sysinfo.mtype == DDR_STACKED))
+		size1 = get_sdr_cs_size(CS1);
+
+	gd->ram_size = size0 + size1;
+	return 0;
+}
+
+void dram_init_banksize (void)
+{
+	DECLARE_GLOBAL_DATA_PTR;
+	unsigned int size0 = 0, size1 = 0;
+
+	size0 = get_sdr_cs_size(CS0);
+	size1 = get_sdr_cs_size(CS1);
+
+	gd->bd->bi_dram[0].start = PHYS_SDRAM_1;
+	gd->bd->bi_dram[0].size = size0;
+	gd->bd->bi_dram[1].start = PHYS_SDRAM_1 + get_sdr_cs_offset(CS1);
+	gd->bd->bi_dram[1].size = size1;
+}
+#endif
 
 /*
  * mem_init() -
diff --git a/arch/arm/cpu/armv7/omap3/sdrc.c b/arch/arm/cpu/armv7/omap3/sdrc.c
index 8905224439..2719bb53a7 100644
--- a/arch/arm/cpu/armv7/omap3/sdrc.c
+++ b/arch/arm/cpu/armv7/omap3/sdrc.c
@@ -163,6 +163,7 @@ void do_sdrc_init(u32 cs, u32 early)
  * dram_init -
  *  - Sets uboots idea of sdram size
  */
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 int dram_init(void)
 {
 	DECLARE_GLOBAL_DATA_PTR;
@@ -188,6 +189,43 @@ int dram_init(void)
 
 	return 0;
 }
+#else
+int dram_init(void)
+{
+	DECLARE_GLOBAL_DATA_PTR;
+	unsigned int size0 = 0, size1 = 0;
+
+	size0 = get_sdr_cs_size(CS0);
+	/*
+	 * If a second bank of DDR is attached to CS1 this is
+	 * where it can be started.  Early init code will init
+	 * memory on CS0.
+	 */
+	if ((sysinfo.mtype == DDR_COMBO) || (sysinfo.mtype == DDR_STACKED)) {
+		do_sdrc_init(CS1, NOT_EARLY);
+		make_cs1_contiguous();
+
+		size1 = get_sdr_cs_size(CS1);
+	}
+	gd->ram_size = size0 + size1;
+
+	return 0;
+}
+
+void dram_init_banksize (void)
+{
+	DECLARE_GLOBAL_DATA_PTR;
+	unsigned int size0 = 0, size1 = 0;
+
+	size0 = get_sdr_cs_size(CS0);
+	size1 = get_sdr_cs_size(CS1);
+
+	gd->bd->bi_dram[0].start = PHYS_SDRAM_1;
+	gd->bd->bi_dram[0].size = size0;
+	gd->bd->bi_dram[1].start = PHYS_SDRAM_1 + get_sdr_cs_offset(CS1);
+	gd->bd->bi_dram[1].size = size1;
+}
+#endif
 
 /*
  * mem_init -
diff --git a/arch/arm/cpu/armv7/start.S b/arch/arm/cpu/armv7/start.S
index 1e0a1504bf..f411c0f4f0 100644
--- a/arch/arm/cpu/armv7/start.S
+++ b/arch/arm/cpu/armv7/start.S
@@ -65,12 +65,15 @@ _end_vect:
  *
  *************************************************************************/
 
+.globl _TEXT_BASE
 _TEXT_BASE:
 	.word	TEXT_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.
@@ -95,6 +98,176 @@ FIQ_STACK_START:
 	.word 0x0badc0de
 #endif
 
+#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, #0x1f
+	orr	r0, r0, #0xd3
+	msr	cpsr,r0
+
+#if (CONFIG_OMAP34XX)
+	/* Copy vectors to mask ROM indirect addr */
+	adr	r0, _start		@ r0 <- current position of code
+	add	r0, r0, #4		@ skip reset vector
+	mov	r2, #64			@ r2 <- size to copy
+	add	r2, r0, r2		@ r2 <- source end address
+	mov	r1, #SRAM_OFFSET0	@ build vect addr
+	mov	r3, #SRAM_OFFSET1
+	add	r1, r1, r3
+	mov	r3, #SRAM_OFFSET2
+	add	r1, r1, r3
+next:
+	ldmia	r0!, {r3 - r10}		@ copy from source address [r0]
+	stmia	r1!, {r3 - r10}		@ copy to   target address [r1]
+	cmp	r0, r2			@ until source end address [r2]
+	bne	next			@ loop until equal */
+#if !defined(CONFIG_SYS_NAND_BOOT) && !defined(CONFIG_SYS_ONENAND_BOOT)
+	/* No need to copy/exec the clock code - DPLL adjust already done
+	 * in NAND/oneNAND Boot.
+	 */
+	bl	cpy_clk_code		@ put dpll adjust code behind vectors
+#endif /* NAND Boot */
+#endif
+	/* the mask ROM code should have PLL and others stable */
+#ifndef CONFIG_SKIP_LOWLEVEL_INIT
+	bl	cpu_init_crit
+#endif
+
+/* 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
+
+#ifndef CONFIG_SKIP_RELOCATE_UBOOT
+	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
+#ifndef CONFIG_PRELOADER
+	beq	jump_2_ram
+#endif
+
+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
+	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
+
+clear_bss:
+	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
+#endif	/* #ifndef CONFIG_PRELOADER */
+#endif	/* #ifndef CONFIG_SKIP_RELOCATE_UBOOT */
+
+/*
+ * We are done. Do not return, instead branch to second part of board
+ * initialization, now running from RAM.
+ */
+jump_2_ram:
+	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
+#else /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 /*
  * the actual reset code
  */
@@ -180,7 +353,7 @@ clbss_l:
 	ldr	pc, _start_armboot	@ jump to C code
 
 _start_armboot: .word start_armboot
-
+#endif /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 
 /*************************************************************************
  *
@@ -263,11 +436,14 @@ cpu_init_crit:
 						@ user stack
 	stmia	sp, {r0 - r12}			@ Save user registers (now in
 						@ svc mode) r0-r12
-
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r2, _armboot_start
 	sub	r2, r2, #(CONFIG_SYS_MALLOC_LEN)
 	sub	r2, r2, #(CONFIG_SYS_GBL_DATA_SIZE + 8)	@ set base 2 words into abort
+#else
+	ldr	r2, IRQ_STACK_START_IN		@ set base 2 words into abort
 						@ stack
+#endif
 	ldmia	r2, {r2 - r3}			@ get values for "aborted" pc
 						@ and cpsr (into parm regs)
 	add	r0, sp, #S_FRAME_SIZE		@ grab pointer to old stack
@@ -303,11 +479,14 @@ cpu_init_crit:
 	.endm
 
 	.macro get_bad_stack
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r13, _armboot_start		@ setup our mode stack (enter
-						@ in banked mode)
 	sub	r13, r13, #(CONFIG_SYS_MALLOC_LEN)	@ move past malloc pool
 	sub	r13, r13, #(CONFIG_SYS_GBL_DATA_SIZE + 8) @ move to reserved a couple
-						@ spots for abort stack
+#else
+	ldr	r13, IRQ_STACK_START_IN		@ setup our mode stack (enter
+						@ in banked mode)
+#endif
 
 	str	lr, [r13]			@ save caller lr in position 0
 						@ of saved stack
@@ -328,10 +507,14 @@ cpu_init_crit:
 	sub	r13, r13, #4			@ space on current stack for
 						@ scratch reg.
 	str	r0, [r13]			@ save R0's value.
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r0, _armboot_start		@ get data regions start
 	sub	r0, r0, #(CONFIG_SYS_MALLOC_LEN)	@ move past malloc pool
 	sub	r0, r0, #(CONFIG_SYS_GBL_DATA_SIZE + 8)	@ move past gbl and a couple
+#else
+	ldr	r0, IRQ_STACK_START_IN		@ get data regions start
 						@ spots for abort stack
+#endif
 	str	lr, [r0]			@ save caller lr in position 0
 						@ of saved stack
 	mrs	r0, spsr			@ get the spsr
diff --git a/arch/arm/cpu/armv7/u-boot.lds b/arch/arm/cpu/armv7/u-boot.lds
index 9e5b5a97d7..d4fd3fccee 100644
--- a/arch/arm/cpu/armv7/u-boot.lds
+++ b/arch/arm/cpu/armv7/u-boot.lds
@@ -42,10 +42,22 @@ SECTIONS
 	.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) }
diff --git a/arch/arm/cpu/ixp/start.S b/arch/arm/cpu/ixp/start.S
index 6efe333f1a..b2c8255141 100644
--- a/arch/arm/cpu/ixp/start.S
+++ b/arch/arm/cpu/ixp/start.S
@@ -93,12 +93,15 @@ _fiq:			.word fiq
  * - jump to second stage
  */
 
+.globl _TEXT_BASE
 _TEXT_BASE:
 	.word	TEXT_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.
@@ -123,6 +126,274 @@ FIQ_STACK_START:
 	.word 0x0badc0de
 #endif
 
+#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:
+	/* disable mmu, set big-endian */
+	mov	r0, #0xf8
+	mcr	p15, 0, r0, c1, c0, 0
+	CPWAIT  r0
+
+	/* invalidate I & D caches & BTB */
+	mcr	p15, 0, r0, c7, c7, 0
+	CPWAIT	r0
+
+	/* invalidate I & Data TLB */
+	mcr	p15, 0, r0, c8, c7, 0
+	CPWAIT r0
+
+	/* drain write and fill buffers */
+	mcr	p15, 0, r0, c7, c10, 4
+	CPWAIT	r0
+
+	/* disable write buffer coalescing */
+	mrc	p15, 0, r0, c1, c0, 1
+	orr	r0, r0, #1
+	mcr	p15, 0, r0, c1, c0, 1
+	CPWAIT	r0
+
+	/* set EXP CS0 to the optimum timing */
+	ldr	r1, =CONFIG_SYS_EXP_CS0
+	ldr     r2, =IXP425_EXP_CS0
+	str     r1, [r2]
+
+	/* make sure flash is visible at 0 */
+#if 0
+	ldr	r2, =IXP425_EXP_CFG0
+	ldr     r1, [r2]
+	orr     r1, r1, #0x80000000
+	str     r1, [r2]
+#endif
+	mov	r1, #CONFIG_SYS_SDR_CONFIG
+	ldr     r2, =IXP425_SDR_CONFIG
+	str     r1, [r2]
+
+	/* disable refresh cycles */
+	mov	r1, #0
+	ldr     r3, =IXP425_SDR_REFRESH
+	str	r1, [r3]
+
+	/* send nop command */
+	mov	r1, #3
+	ldr	r4, =IXP425_SDR_IR
+	str	r1, [r4]
+	DELAY_FOR 0x4000, r0
+
+	/* set SDRAM internal refresh val */
+	ldr	r1, =CONFIG_SYS_SDRAM_REFRESH_CNT
+	str     r1, [r3]
+	DELAY_FOR 0x4000, r0
+
+	/* send precharge-all command to close all open banks */
+	mov     r1, #2
+	str     r1, [r4]
+	DELAY_FOR 0x4000, r0
+
+	/* provide 8 auto-refresh cycles */
+	mov     r1, #4
+	mov     r5, #8
+111:    str	r1, [r4]
+	DELAY_FOR 0x100, r0
+	subs	r5, r5, #1
+	bne	111b
+
+	/* set mode register in sdram */
+	mov	r1, #CONFIG_SYS_SDR_MODE_CONFIG
+	str	r1, [r4]
+	DELAY_FOR 0x4000, r0
+
+	/* send normal operation command */
+	mov	r1, #6
+	str	r1, [r4]
+	DELAY_FOR 0x4000, r0
+
+	/* copy */
+	mov     r0, #0
+	mov     r4, r0
+	add     r2, r0, #CONFIG_SYS_MONITOR_LEN
+	mov     r1, #0x10000000
+	mov     r5, r1
+
+    30:
+	ldr     r3, [r0], #4
+	str     r3, [r1], #4
+	cmp     r0, r2
+	bne     30b
+
+	/* invalidate I & D caches & BTB */
+	mcr	p15, 0, r0, c7, c7, 0
+	CPWAIT	r0
+
+	/* invalidate I & Data TLB */
+	mcr	p15, 0, r0, c8, c7, 0
+	CPWAIT r0
+
+	/* drain write and fill buffers */
+	mcr	p15, 0, r0, c7, c10, 4
+	CPWAIT	r0
+
+	/* move flash to 0x50000000 */
+	ldr	r2, =IXP425_EXP_CFG0
+	ldr     r1, [r2]
+	bic     r1, r1, #0x80000000
+	str     r1, [r2]
+
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	/* invalidate I & Data TLB */
+	mcr	p15, 0, r0, c8, c7, 0
+	CPWAIT r0
+
+	/* enable I cache */
+	mrc     p15, 0, r0, c1, c0, 0
+	orr     r0, r0, #MMU_Control_I
+	mcr     p15, 0, r0, c1, c0, 0
+	CPWAIT  r0
+
+	mrs	r0,cpsr			/* set the cpu to SVC32 mode	    */
+	bic	r0,r0,#0x1f		/* (superviser mode, M=10011)	    */
+	orr	r0,r0,#0x13
+	msr	cpsr,r0
+
+/* 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 */
+
+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.
+ */
+	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
+
+#else /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 /****************************************************************************/
 /*									    */
 /* the actual reset code						    */
@@ -304,6 +575,7 @@ clbss_l:str	r2, [r0]		/* clear loop...                    */
 	ldr	pc, _start_armboot
 
 _start_armboot: .word start_armboot
+#endif /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 
 
 /****************************************************************************/
@@ -345,9 +617,13 @@ _start_armboot: .word start_armboot
 	stmia	sp, {r0 - r12}			/* Calling r0-r12	    */
 	add	r8, sp, #S_PC
 
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r2, _armboot_start
 	sub	r2, r2, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r2, r2, #(CONFIG_SYS_GBL_DATA_SIZE+8)  @ set base 2 words into abort stack
+#else
+	ldr	r2, IRQ_STACK_START_IN
+#endif
 	ldmia	r2, {r2 - r4}			/* get pc, cpsr, old_r0	    */
 	add	r0, sp, #S_FRAME_SIZE		/* restore sp_SVC	    */
 
@@ -382,9 +658,13 @@ _start_armboot: .word start_armboot
 	.endm
 
 	.macro get_bad_stack
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r13, _armboot_start		@ setup our mode stack
 	sub	r13, r13, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r13, r13, #(CONFIG_SYS_GBL_DATA_SIZE+8) @ reserved a couple spots in abort stack
+#else
+	ldr	r13, IRQ_STACK_START_IN		@ setup our mode stack
+#endif
 
 	str	lr, [r13]			@ save caller lr / spsr
 	mrs	lr, spsr
diff --git a/arch/arm/cpu/ixp/u-boot.lds b/arch/arm/cpu/ixp/u-boot.lds
index b8ff2eed5c..f3d9dc5148 100644
--- a/arch/arm/cpu/ixp/u-boot.lds
+++ b/arch/arm/cpu/ixp/u-boot.lds
@@ -39,11 +39,23 @@ SECTIONS
 	.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) }
diff --git a/arch/arm/cpu/lh7a40x/start.S b/arch/arm/cpu/lh7a40x/start.S
index 14a1fbe121..002116a401 100644
--- a/arch/arm/cpu/lh7a40x/start.S
+++ b/arch/arm/cpu/lh7a40x/start.S
@@ -72,12 +72,15 @@ _fiq:			.word fiq
  *************************************************************************
  */
 
+.globl _TEXT_BASE
 _TEXT_BASE:
 	.word	TEXT_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.
@@ -102,8 +105,182 @@ FIQ_STACK_START:
 	.word 0x0badc0de
 #endif
 
+#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,#0x1f
+	orr	r0,r0,#0xd3
+	msr	cpsr,r0
+
+#define pWDTCTL		0x80001400  /* Watchdog Timer control register */
+#define pINTENC		0x8000050C  /* Interupt-Controller enable clear register */
+#define pCLKSET		0x80000420  /* clock divisor register */
+
+	/* disable watchdog, set watchdog control register to
+	 * all zeros (default reset)
+	 */
+	ldr     r0, =pWDTCTL
+	mov     r1, #0x0
+	str     r1, [r0]
+
+	/*
+	 * mask all IRQs by setting all bits in the INTENC register (default)
+	 */
+	mov	r1, #0xffffffff
+	ldr	r0, =pINTENC
+	str	r1, [r0]
+
+	/* FCLK:HCLK:PCLK = 1:2:2 */
+	/* default FCLK is 200 MHz, using 14.7456 MHz fin */
+	ldr	r0, =pCLKSET
+	ldr r1, =0x0004ee39
+@	ldr r1, =0x0005ee39	@ 1: 2: 4
+	str	r1, [r0]
+
+	/*
+	 * we do sys-critical inits only at reboot,
+	 * not when booting from ram!
+	 */
+#ifndef CONFIG_SKIP_LOWLEVEL_INIT
+	bl	cpu_init_crit
+#endif
+
+/* 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 */
+
+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
+#endif
+
+/*
+ * We are done. Do not return, instead branch to second part of board
+ * initialization, now running from RAM.
+ */
+	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
+
+#else /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
+/*
  * the actual reset code
  */
 
@@ -195,7 +372,7 @@ clbss_l:str	r2, [r0]		/* clear loop...                    */
 	ldr	pc, _start_armboot
 
 _start_armboot:	.word start_armboot
-
+#endif /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 
 /*
  *************************************************************************
@@ -285,9 +462,13 @@ cpu_init_crit:
 	.macro	bad_save_user_regs
 	sub	sp, sp, #S_FRAME_SIZE
 	stmia	sp, {r0 - r12}			@ Calling r0-r12
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r2, _armboot_start
 	sub	r2, r2, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r2, r2, #(CONFIG_SYS_GBL_DATA_SIZE+8)  @ set base 2 words into abort stack
+#else
+	ldr	r2, IRQ_STACK_START_IN
+#endif
 	ldmia	r2, {r2 - r3}			@ get pc, cpsr
 	add	r0, sp, #S_FRAME_SIZE		@ restore sp_SVC
 
@@ -318,9 +499,13 @@ cpu_init_crit:
 	.endm
 
 	.macro get_bad_stack
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r13, _armboot_start		@ setup our mode stack
 	sub	r13, r13, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r13, r13, #(CONFIG_SYS_GBL_DATA_SIZE+8) @ reserved a couple spots in abort stack
+#else
+	ldr	r13, IRQ_STACK_START_IN		@ setup our mode stack
+#endif
 
 	str	lr, [r13]			@ save caller lr / spsr
 	mrs	lr, spsr
diff --git a/arch/arm/cpu/lh7a40x/u-boot.lds b/arch/arm/cpu/lh7a40x/u-boot.lds
index 5a8ccf5888..cb55b0a274 100644
--- a/arch/arm/cpu/lh7a40x/u-boot.lds
+++ b/arch/arm/cpu/lh7a40x/u-boot.lds
@@ -39,11 +39,23 @@ SECTIONS
 	.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) }
diff --git a/arch/arm/cpu/pxa/start.S b/arch/arm/cpu/pxa/start.S
index 8010b0ee17..064ddbcf3f 100644
--- a/arch/arm/cpu/pxa/start.S
+++ b/arch/arm/cpu/pxa/start.S
@@ -82,12 +82,15 @@ _fiq:			.word fiq
  * - jump to second stage
  */
 
+.globl _TEXT_BASE
 _TEXT_BASE:
 	.word	TEXT_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.
@@ -112,6 +115,162 @@ FIQ_STACK_START:
 	.word 0x0badc0de
 #endif /* CONFIG_USE_IRQ */
 
+#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,#0x1f
+	orr	r0,r0,#0xd3
+	msr	cpsr,r0
+
+	/*
+	 * we do sys-critical inits only at reboot,
+	 * not when booting from ram!
+	 */
+#ifndef CONFIG_SKIP_LOWLEVEL_INIT
+	bl	cpu_init_crit
+#endif
+
+/* 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 */
+
+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
+#endif
+
+/*
+ * We are done. Do not return, instead branch to second part of board
+ * initialization, now running from RAM.
+ */
+#ifdef CONFIG_ONENAND_IPL
+	ldr     pc, _start_oneboot
+
+_start_oneboot: .word start_oneboot
+#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) */
 
 /****************************************************************************/
 /*									    */
@@ -188,6 +347,7 @@ _start_armboot: .word start_oneboot
 #else
 _start_armboot: .word start_armboot
 #endif
+#endif /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 
 /****************************************************************************/
 /*									    */
@@ -367,9 +527,13 @@ setspeed_done:
 	stmia	sp, {r0 - r12}			/* Calling r0-r12	    */
 	add	r8, sp, #S_PC
 
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r2, _armboot_start
 	sub	r2, r2, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r2, r2, #(CONFIG_SYS_GBL_DATA_SIZE+8)	@ set base 2 words into abort stack
+#else
+	ldr	r2, IRQ_STACK_START_IN
+#endif
 	ldmia	r2, {r2 - r4}			/* get pc, cpsr, old_r0	    */
 	add	r0, sp, #S_FRAME_SIZE		/* restore sp_SVC	    */
 
@@ -404,9 +568,13 @@ setspeed_done:
 	.endm
 
 	.macro get_bad_stack
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r13, _armboot_start		@ setup our mode stack
 	sub	r13, r13, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r13, r13, #(CONFIG_SYS_GBL_DATA_SIZE+8) @ reserved a couple spots in abort stack
+#else
+	ldr	r13, IRQ_STACK_START_IN		@ setup our mode stack
+#endif
 
 	str	lr, [r13]			@ save caller lr / spsr
 	mrs	lr, spsr
diff --git a/arch/arm/cpu/pxa/u-boot.lds b/arch/arm/cpu/pxa/u-boot.lds
index d4e85ef550..74a4c6e90c 100644
--- a/arch/arm/cpu/pxa/u-boot.lds
+++ b/arch/arm/cpu/pxa/u-boot.lds
@@ -39,11 +39,23 @@ SECTIONS
 	.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) }
diff --git a/arch/arm/cpu/s3c44b0/start.S b/arch/arm/cpu/s3c44b0/start.S
index 0063063f45..e1ab5ccb36 100644
--- a/arch/arm/cpu/s3c44b0/start.S
+++ b/arch/arm/cpu/s3c44b0/start.S
@@ -63,12 +63,15 @@ _start:	b       reset
  *************************************************************************
  */
 
+.globl _TEXT_BASE
 _TEXT_BASE:
 	.word	TEXT_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.
@@ -93,7 +96,177 @@ FIQ_STACK_START:
 	.word 0x0badc0de
 #endif
 
+#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,#0x1f
+	orr	r0,r0,#0xd3
+	msr	cpsr,r0
+
+	/*
+	 * we do sys-critical inits only at reboot,
+	 * not when booting from ram!
+	 */
+#ifndef CONFIG_SKIP_LOWLEVEL_INIT
+	bl	cpu_init_crit
+	/*
+	 * before relocating, we have to setup RAM timing
+	 * because memory timing is board-dependend, you will
+	 * find a lowlevel_init.S in your board directory.
+	 */
+	bl	lowlevel_init
+#endif
+
+/* 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
+/*
+	now copy to sram the interrupt vector
+*/
+	adr	r0, real_vectors
+	add	r2, r0, #1024
+	ldr	r1, =0x0c000000
+	add	r1, r1, #0x08
+vector_copy_loop:
+	ldmia	r0!, {r3-r10}
+	stmia	r1!, {r3-r10}
+	cmp	r0, r2
+	ble	vector_copy_loop
+#endif	/* #ifndef CONFIG_SKIP_RELOCATE_UBOOT */
+
+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.
+ */
+	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
 
+#else /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 /*
  * the actual reset code
  */
@@ -169,6 +342,7 @@ stack_setup:
 
 _start_armboot:	.word start_armboot
 
+#endif /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 
 /*
  *************************************************************************
diff --git a/arch/arm/cpu/s3c44b0/u-boot.lds b/arch/arm/cpu/s3c44b0/u-boot.lds
index 267d94c083..bbc8c3aa55 100644
--- a/arch/arm/cpu/s3c44b0/u-boot.lds
+++ b/arch/arm/cpu/s3c44b0/u-boot.lds
@@ -39,11 +39,23 @@ SECTIONS
 	.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) }
diff --git a/arch/arm/cpu/sa1100/start.S b/arch/arm/cpu/sa1100/start.S
index deb4745e21..4730e5a9ab 100644
--- a/arch/arm/cpu/sa1100/start.S
+++ b/arch/arm/cpu/sa1100/start.S
@@ -73,12 +73,15 @@ _fiq:			.word fiq
  *************************************************************************
  */
 
+.globl _TEXT_BASE
 _TEXT_BASE:
 	.word	TEXT_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.
@@ -103,6 +106,156 @@ FIQ_STACK_START:
 	.word 0x0badc0de
 #endif
 
+#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,#0x1f
+	orr	r0,r0,#0xd3
+	msr	cpsr,r0
+
+	/*
+	 * we do sys-critical inits only at reboot,
+	 * not when booting from ram!
+	 */
+#ifndef CONFIG_SKIP_LOWLEVEL_INIT
+	bl	cpu_init_crit
+#endif
+
+/* 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 */
+
+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
+#endif
+
+/*
+ * We are done. Do not return, instead branch to second part of board
+ * initialization, now running from RAM.
+ */
+	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
+
+#else /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 
 /*
  * the actual reset code
@@ -169,6 +322,7 @@ clbss_l:str	r2, [r0]		/* clear loop...                    */
 
 _start_armboot:	.word start_armboot
 
+#endif /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 
 /*
  *************************************************************************
@@ -288,9 +442,13 @@ cpu_init_crit:
 	stmia	sp, {r0 - r12}			@ Calling r0-r12
 	add     r8, sp, #S_PC
 
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r2, _armboot_start
 	sub	r2, r2, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r2, r2, #(CONFIG_SYS_GBL_DATA_SIZE+8)  @ set base 2 words into abort stack
+#else
+	ldr	r2, IRQ_STACK_START_IN
+#endif
 	ldmia	r2, {r2 - r4}                   @ get pc, cpsr, old_r0
 	add	r0, sp, #S_FRAME_SIZE		@ restore sp_SVC
 
@@ -321,9 +479,13 @@ cpu_init_crit:
 	.endm
 
 	.macro get_bad_stack
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 	ldr	r13, _armboot_start		@ setup our mode stack
 	sub	r13, r13, #(CONFIG_STACKSIZE+CONFIG_SYS_MALLOC_LEN)
 	sub	r13, r13, #(CONFIG_SYS_GBL_DATA_SIZE+8) @ reserved a couple spots in abort stack
+#else
+	ldr	r13, IRQ_STACK_START_IN		@ setup our mode stack
+#endif
 
 	str	lr, [r13]			@ save caller lr / spsr
 	mrs	lr, spsr
diff --git a/arch/arm/cpu/sa1100/u-boot.lds b/arch/arm/cpu/sa1100/u-boot.lds
index f6197acd81..2e29291909 100644
--- a/arch/arm/cpu/sa1100/u-boot.lds
+++ b/arch/arm/cpu/sa1100/u-boot.lds
@@ -42,11 +42,23 @@ SECTIONS
 	.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) }
diff --git a/arch/arm/include/asm/config.h b/arch/arm/include/asm/config.h
index b76fd8eb48..4e8dfd7bc5 100644
--- a/arch/arm/include/asm/config.h
+++ b/arch/arm/include/asm/config.h
@@ -21,7 +21,8 @@
 #ifndef _ASM_CONFIG_H_
 #define _ASM_CONFIG_H_
 
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 /* Relocation to SDRAM works on all ARM boards */
 #define CONFIG_RELOC_FIXUP_WORKS
-
+#endif
 #endif
diff --git a/arch/arm/include/asm/global_data.h b/arch/arm/include/asm/global_data.h
index 02cfe4584a..6152f348f3 100644
--- a/arch/arm/include/asm/global_data.h
+++ b/arch/arm/include/asm/global_data.h
@@ -1,5 +1,5 @@
 /*
- * (C) Copyright 2002
+ * (C) Copyright 2002-2010
  * Wolfgang Denk, DENX Software Engineering, wd@denx.de.
  *
  * See file CREDITS for list of people who contributed to this
@@ -47,25 +47,32 @@ typedef	struct	global_data {
 #ifdef CONFIG_FSL_ESDHC
 	unsigned long	sdhc_clk;
 #endif
-#if 0
-	unsigned long	cpu_clk;	/* CPU clock in Hz!		*/
-	unsigned long	bus_clk;
+#if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
+	unsigned long	relocaddr;	/* Start address of U-Boot in RAM */
 	phys_size_t	ram_size;	/* RAM size */
-	unsigned long	reset_status;	/* reset status register at boot */
+	unsigned long	mon_len;	/* monitor len */
+	unsigned long	irq_sp;		/* irq stack pointer */
+	unsigned long	start_addr_sp;	/* start_addr_stackpointer */
+	unsigned long	reloc_off;
+#if !(defined(CONFIG_SYS_NO_ICACHE) && defined(CONFIG_SYS_NO_DCACHE))
+	unsigned long	tlb_addr;
+#endif
 #endif
 	void		**jt;		/* jump table */
+	char		env_buf[32];	/* buffer for getenv() before reloc. */
 } gd_t;
 
 /*
  * Global Data Flags
  */
-#define	GD_FLG_RELOC	0x00001		/* Code was relocated to RAM		*/
-#define	GD_FLG_DEVINIT	0x00002		/* Devices have been initialized	*/
-#define	GD_FLG_SILENT	0x00004		/* Silent mode				*/
-#define	GD_FLG_POSTFAIL	0x00008		/* Critical POST test failed		*/
-#define	GD_FLG_POSTSTOP	0x00010		/* POST seqeunce aborted		*/
-#define	GD_FLG_LOGINIT	0x00020		/* Log Buffer has been initialized	*/
-#define GD_FLG_DISABLE_CONSOLE	0x00040		/* Disable console (in & out)	 */
+#define	GD_FLG_RELOC		0x00001	/* Code was relocated to RAM		*/
+#define	GD_FLG_DEVINIT		0x00002	/* Devices have been initialized	*/
+#define	GD_FLG_SILENT		0x00004	/* Silent mode				*/
+#define	GD_FLG_POSTFAIL		0x00008	/* Critical POST test failed		*/
+#define	GD_FLG_POSTSTOP		0x00010	/* POST seqeunce aborted		*/
+#define	GD_FLG_LOGINIT		0x00020	/* Log Buffer has been initialized	*/
+#define GD_FLG_DISABLE_CONSOLE	0x00040	/* Disable console (in & out)		*/
+#define GD_FLG_ENV_READY	0x00080	/* Environment imported into hash table	*/
 
 #define DECLARE_GLOBAL_DATA_PTR     register volatile gd_t *gd asm ("r8")
 
diff --git a/arch/arm/include/asm/u-boot-arm.h b/arch/arm/include/asm/u-boot-arm.h
index 6d2f8bccb5..faf800a17b 100644
--- a/arch/arm/include/asm/u-boot-arm.h
+++ b/arch/arm/include/asm/u-boot-arm.h
@@ -30,11 +30,20 @@
 #define _U_BOOT_ARM_H_	1
 
 /* for the following variables, see start.S */
-extern ulong _armboot_start;	/* code start */
 extern ulong _bss_start;	/* code + data end == BSS start */
 extern ulong _bss_end;		/* BSS end */
 extern ulong IRQ_STACK_START;	/* top of IRQ stack */
 extern ulong FIQ_STACK_START;	/* top of FIQ stack */
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
+extern ulong _armboot_start;	/* code start */
+#else
+extern ulong _TEXT_BASE;	/* code start */
+extern ulong _datarel_start;
+extern ulong _datarelrolocal_start;
+extern ulong _datarellocal_start;
+extern ulong _datarelro_start;
+extern ulong IRQ_STACK_START_IN;	/* 8 bytes in IRQ stack */
+#endif
 
 /* cpu/.../cpu.c */
 int	cpu_init(void);
@@ -47,6 +56,9 @@ int	arch_misc_init(void);
 /* board/.../... */
 int	board_init(void);
 int	dram_init (void);
+#if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
+void	dram_init_banksize (void);
+#endif
 void	setup_serial_tag (struct tag **params);
 void	setup_revision_tag (struct tag **params);
 
diff --git a/arch/arm/include/asm/u-boot.h b/arch/arm/include/asm/u-boot.h
index cfd5a9ba45..ed33327094 100644
--- a/arch/arm/include/asm/u-boot.h
+++ b/arch/arm/include/asm/u-boot.h
@@ -39,7 +39,6 @@
 typedef struct bd_info {
     int			bi_baudrate;	/* serial console baudrate */
     unsigned long	bi_ip_addr;	/* IP Address */
-    struct environment_s	       *bi_env;
     ulong	        bi_arch_number;	/* unique id for this board */
     ulong	        bi_boot_params;	/* where this board expects params */
     struct				/* RAM configuration */
@@ -49,7 +48,4 @@ typedef struct bd_info {
     }			bi_dram[CONFIG_NR_DRAM_BANKS];
 } bd_t;
 
-#define bi_env_data bi_env->data
-#define bi_env_crc  bi_env->crc
-
 #endif	/* _U_BOOT_H_ */
diff --git a/arch/arm/lib/board.c b/arch/arm/lib/board.c
index e17f182e18..5f2dfd08ac 100644
--- a/arch/arm/lib/board.c
+++ b/arch/arm/lib/board.c
@@ -126,7 +126,12 @@ static int init_baudrate (void)
 {
 	char tmp[64];	/* long enough for environment variables */
 	int i = getenv_f("baudrate", tmp, sizeof (tmp));
+
+#if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
+	gd->baudrate = (i > 0)
+#else
 	gd->bd->bi_baudrate = gd->baudrate = (i > 0)
+#endif
 			? (int) simple_strtoul (tmp, NULL, 10)
 			: CONFIG_BAUDRATE;
 
@@ -137,7 +142,12 @@ static int display_banner (void)
 {
 	printf ("\n\n%s\n\n", version_string);
 	debug ("U-Boot code: %08lX -> %08lX  BSS: -> %08lX\n",
-	       _armboot_start, _bss_start, _bss_end);
+#if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
+	       _TEXT_BASE,
+#else
+	       _armboot_start,
+#endif
+	       _bss_start, _bss_end);
 #ifdef CONFIG_MODEM_SUPPORT
 	debug ("Modem Support enabled\n");
 #endif
@@ -180,6 +190,7 @@ static int display_dram_config (void)
 	return (0);
 }
 
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 #ifndef CONFIG_SYS_NO_FLASH
 static void display_flash_config (ulong size)
 {
@@ -187,6 +198,7 @@ static void display_flash_config (ulong size)
 	print_size (size, "\n");
 }
 #endif /* CONFIG_SYS_NO_FLASH */
+#endif
 
 #if defined(CONFIG_HARD_I2C) || defined(CONFIG_SOFT_I2C)
 static int init_func_i2c (void)
@@ -234,6 +246,7 @@ typedef int (init_fnc_t) (void);
 
 int print_cpuinfo (void);
 
+#if defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
 init_fnc_t *init_sequence[] = {
 #if defined(CONFIG_ARCH_CPU_INIT)
 	arch_cpu_init,		/* basic arch cpu dependent setup */
@@ -449,6 +462,459 @@ extern void davinci_eth_set_mac_addr (const u_int8_t *addr);
 
 	/* NOTREACHED - no way out of command loop except booting */
 }
+#else
+void __dram_init_banksize(void)
+{
+	gd->bd->bi_dram[0].start = CONFIG_SYS_SDRAM_BASE;
+	gd->bd->bi_dram[0].size =  gd->ram_size;
+}
+void dram_init_banksize(void)
+	__attribute__((weak, alias("__dram_init_banksize")));
+
+init_fnc_t *init_sequence[] = {
+#if defined(CONFIG_ARCH_CPU_INIT)
+	arch_cpu_init,		/* basic arch cpu dependent setup */
+#endif
+#if defined(CONFIG_BOARD_EARLY_INIT_F)
+	board_early_init_f,
+#endif
+	timer_init,		/* initialize timer */
+#ifdef CONFIG_FSL_ESDHC
+	get_clocks,
+#endif
+	env_init,		/* initialize environment */
+	init_baudrate,		/* initialze baudrate settings */
+	serial_init,		/* serial communications setup */
+	console_init_f,		/* stage 1 init of console */
+	display_banner,		/* say that we are here */
+#if defined(CONFIG_DISPLAY_CPUINFO)
+	print_cpuinfo,		/* display cpu info (and speed) */
+#endif
+#if defined(CONFIG_DISPLAY_BOARDINFO)
+	checkboard,		/* display board info */
+#endif
+#if defined(CONFIG_HARD_I2C) || defined(CONFIG_SOFT_I2C)
+	init_func_i2c,
+#endif
+	dram_init,		/* configure available RAM banks */
+#if defined(CONFIG_CMD_PCI) || defined (CONFIG_PCI)
+	arm_pci_init,
+#endif
+	NULL,
+};
+
+void board_init_f (ulong bootflag)
+{
+	bd_t *bd;
+	init_fnc_t **init_fnc_ptr;
+	gd_t *id;
+	ulong addr, addr_sp;
+
+	/* Pointer is writable since we allocated a register for it */
+	gd = (gd_t *) (CONFIG_SYS_INIT_SP_ADDR);
+	/* compiler optimization barrier needed for GCC >= 3.4 */
+	__asm__ __volatile__("": : :"memory");
+
+	memset ((void*)gd, 0, sizeof (gd_t));
+
+	gd->mon_len = _bss_end - _TEXT_BASE;
+
+	for (init_fnc_ptr = init_sequence; *init_fnc_ptr; ++init_fnc_ptr) {
+		if ((*init_fnc_ptr)() != 0) {
+			hang ();
+		}
+	}
+
+	debug ("monitor len: %08lX\n", gd->mon_len);
+	/*
+	 * Ram is setup, size stored in gd !!
+	 */
+	debug ("ramsize: %08lX\n", gd->ram_size);
+#if defined(CONFIG_SYS_MEM_TOP_HIDE)
+	/*
+	 * Subtract specified amount of memory to hide so that it won't
+	 * get "touched" at all by U-Boot. By fixing up gd->ram_size
+	 * the Linux kernel should now get passed the now "corrected"
+	 * memory size and won't touch it either. This should work
+	 * for arch/ppc and arch/powerpc. Only Linux board ports in
+	 * arch/powerpc with bootwrapper support, that recalculate the
+	 * memory size from the SDRAM controller setup will have to
+	 * get fixed.
+	 */
+	gd->ram_size -= CONFIG_SYS_MEM_TOP_HIDE;
+#endif
+
+	addr = CONFIG_SYS_SDRAM_BASE + gd->ram_size;
+
+#ifdef CONFIG_LOGBUFFER
+#ifndef CONFIG_ALT_LB_ADDR
+	/* reserve kernel log buffer */
+	addr -= (LOGBUFF_RESERVE);
+	debug ("Reserving %dk for kernel logbuffer at %08lx\n", LOGBUFF_LEN, addr);
+#endif
+#endif
+
+#ifdef CONFIG_PRAM
+	/*
+	 * reserve protected RAM
+	 */
+	i = getenv_r ("pram", (char *)tmp, sizeof (tmp));
+	reg = (i > 0) ? simple_strtoul ((const char *)tmp, NULL, 10) : CONFIG_PRAM;
+	addr -= (reg << 10);		/* size is in kB */
+	debug ("Reserving %ldk for protected RAM at %08lx\n", reg, addr);
+#endif /* CONFIG_PRAM */
+
+#if !(defined(CONFIG_SYS_NO_ICACHE) && defined(CONFIG_SYS_NO_DCACHE))
+	/* reserve TLB table */
+	addr -= (4096 * 4);
+
+	/* round down to next 64 kB limit */
+	addr &= ~(0x10000 - 1);
+
+	gd->tlb_addr = addr;
+	debug ("TLB table at: %08lx\n", addr);
+#endif
+
+	/* round down to next 4 kB limit */
+	addr &= ~(4096 - 1);
+	debug ("Top of RAM usable for U-Boot at: %08lx\n", addr);
+
+#ifdef CONFIG_VFD
+#	ifndef PAGE_SIZE
+#	  define PAGE_SIZE 4096
+#	endif
+	/*
+	 * reserve memory for VFD display (always full pages)
+	 */
+	addr -= vfd_setmem (addr);
+	gd->fb_base = addr;
+#endif /* CONFIG_VFD */
+
+#ifdef CONFIG_LCD
+	/* reserve memory for LCD display (always full pages) */
+	addr = lcd_setmem (addr);
+	gd->fb_base = addr;
+#endif /* CONFIG_LCD */
+
+	/*
+	 * reserve memory for U-Boot code, data & bss
+	 * round down to next 4 kB limit
+	 */
+	addr -= gd->mon_len;
+	addr &= ~(4096 - 1);
+
+	debug ("Reserving %ldk for U-Boot at: %08lx\n", gd->mon_len >> 10, addr);
+
+#ifndef CONFIG_PRELOADER
+	/*
+	 * reserve memory for malloc() arena
+	 */
+	addr_sp = addr - TOTAL_MALLOC_LEN;
+	debug ("Reserving %dk for malloc() at: %08lx\n",
+			TOTAL_MALLOC_LEN >> 10, addr_sp);
+	/*
+	 * (permanently) allocate a Board Info struct
+	 * and a permanent copy of the "global" data
+	 */
+	addr_sp -= sizeof (bd_t);
+	bd = (bd_t *) addr_sp;
+	gd->bd = bd;
+	debug ("Reserving %zu Bytes for Board Info at: %08lx\n",
+			sizeof (bd_t), addr_sp);
+	addr_sp -= sizeof (gd_t);
+	id = (gd_t *) addr_sp;
+	debug ("Reserving %zu Bytes for Global Data at: %08lx\n",
+			sizeof (gd_t), addr_sp);
+
+	/* setup stackpointer for exeptions */
+	gd->irq_sp = addr_sp;
+#ifdef CONFIG_USE_IRQ
+	addr_sp -= (CONFIG_STACKSIZE_IRQ+CONFIG_STACKSIZE_FIQ);
+	debug ("Reserving %zu Bytes for IRQ stack at: %08lx\n",
+		CONFIG_STACKSIZE_IRQ+CONFIG_STACKSIZE_FIQ, addr_sp);
+#endif
+	/* leave 3 words for abort-stack    */
+	addr_sp -= 3;
+
+	/* 8-byte alignment for ABI compliance */
+	addr_sp &= ~0x07;
+#else
+	addr_sp += 128;	/* leave 32 words for abort-stack   */
+	gd->irq_sp = addr_sp;
+#endif
+
+	debug ("New Stack Pointer is: %08lx\n", addr_sp);
+
+#ifdef CONFIG_POST
+	post_bootmode_init();
+	post_run (NULL, POST_ROM | post_bootmode_get(0));
+#endif
+
+	gd->bd->bi_baudrate = gd->baudrate;
+	/* Ram ist board specific, so move it to board code ... */
+	dram_init_banksize();
+	display_dram_config();	/* and display it */
+
+	gd->relocaddr = addr;
+	gd->start_addr_sp = addr_sp;
+	gd->reloc_off = addr - _TEXT_BASE;
+	debug ("relocation Offset is: %08lx\n", gd->reloc_off);
+	memcpy (id, (void *)gd, sizeof (gd_t));
+
+	relocate_code (addr_sp, id, addr);
+
+	/* NOTREACHED - relocate_code() does not return */
+}
+
+#if !defined(CONFIG_SYS_NO_FLASH)
+static char *failed = "*** failed ***\n";
+#endif
+
+/************************************************************************
+ *
+ * This is the next part if the initialization sequence: we are now
+ * running from RAM and have a "normal" C environment, i. e. global
+ * data can be written, BSS has been cleared, the stack size in not
+ * that critical any more, etc.
+ *
+ ************************************************************************
+ */
+void board_init_r (gd_t *id, ulong dest_addr)
+{
+	char *s;
+	bd_t *bd;
+	ulong malloc_start;
+#if !defined(CONFIG_SYS_NO_FLASH)
+	ulong flash_size;
+#endif
+#if !defined(CONFIG_RELOC_FIXUP_WORKS)
+	extern void malloc_bin_reloc (void);
+#if defined(CONFIG_CMD_BMP)
+	extern void bmp_reloc(void);
+#endif
+#if defined(CONFIG_CMD_I2C)
+	extern void i2c_reloc(void);
+#endif
+#endif
+
+	gd = id;
+	bd = gd->bd;
+
+	gd->flags |= GD_FLG_RELOC;	/* tell others: relocation done */
+
+	monitor_flash_len = _bss_start - _TEXT_BASE;
+	debug ("monitor flash len: %08lX\n", monitor_flash_len);
+	board_init();	/* Setup chipselects */
+
+#ifdef CONFIG_SERIAL_MULTI
+	serial_initialize();
+#endif
+
+	debug ("Now running in RAM - U-Boot at: %08lx\n", dest_addr);
+
+#if !defined(CONFIG_RELOC_FIXUP_WORKS)
+	/*
+	 * We have to relocate the command table manually
+	 */
+	fixup_cmdtable(&__u_boot_cmd_start,
+		(ulong)(&__u_boot_cmd_end - &__u_boot_cmd_start));
+#if defined(CONFIG_CMD_BMP)
+	bmp_reloc();
+#endif
+#if defined(CONFIG_CMD_I2C)
+	i2c_reloc();
+#endif
+#endif /* !defined(CONFIG_RELOC_FIXUP_WORKS) */
+
+#ifdef CONFIG_LOGBUFFER
+	logbuff_init_ptrs ();
+#endif
+#ifdef CONFIG_POST
+	post_output_backlog ();
+#ifndef CONFIG_RELOC_FIXUP_WORKS
+	post_reloc ();
+#endif
+#endif
+
+	/* The Malloc area is immediately below the monitor copy in DRAM */
+	malloc_start = dest_addr - TOTAL_MALLOC_LEN;
+	mem_malloc_init (malloc_start, TOTAL_MALLOC_LEN);
+#if !defined(CONFIG_RELOC_FIXUP_WORKS)
+	malloc_bin_reloc ();
+#endif
+
+#if !defined(CONFIG_SYS_NO_FLASH)
+	puts ("FLASH: ");
+
+	if ((flash_size = flash_init ()) > 0) {
+# ifdef CONFIG_SYS_FLASH_CHECKSUM
+		print_size (flash_size, "");
+		/*
+		 * Compute and print flash CRC if flashchecksum is set to 'y'
+		 *
+		 * NOTE: Maybe we should add some WATCHDOG_RESET()? XXX
+		 */
+		s = getenv ("flashchecksum");
+		if (s && (*s == 'y')) {
+			printf ("  CRC: %08X",
+				crc32 (0, (const unsigned char *) CONFIG_SYS_FLASH_BASE, flash_size)
+			);
+		}
+		putc ('\n');
+# else	/* !CONFIG_SYS_FLASH_CHECKSUM */
+		print_size (flash_size, "\n");
+# endif /* CONFIG_SYS_FLASH_CHECKSUM */
+	} else {
+		puts (failed);
+		hang ();
+	}
+#endif
+
+#if defined(CONFIG_CMD_NAND)
+	puts ("NAND:  ");
+	nand_init();		/* go init the NAND */
+#endif
+
+#if defined(CONFIG_CMD_ONENAND)
+	onenand_init();
+#endif
+
+#ifdef CONFIG_HAS_DATAFLASH
+	AT91F_DataflashInit();
+	dataflash_print_info();
+#endif
+
+	/* initialize environment */
+	env_relocate ();
+
+#ifdef CONFIG_VFD
+	/* must do this after the framebuffer is allocated */
+	drv_vfd_init();
+#endif /* CONFIG_VFD */
+
+	/* IP Address */
+	gd->bd->bi_ip_addr = getenv_IPaddr ("ipaddr");
+
+	stdio_init ();	/* get the devices list going. */
+
+	jumptable_init ();
+
+#if defined(CONFIG_API)
+	/* Initialize API */
+	api_init ();
+#endif
+
+	console_init_r ();	/* fully init console as a device */
+
+#if defined(CONFIG_ARCH_MISC_INIT)
+	/* miscellaneous arch dependent initialisations */
+	arch_misc_init ();
+#endif
+#if defined(CONFIG_MISC_INIT_R)
+	/* miscellaneous platform dependent initialisations */
+	misc_init_r ();
+#endif
+
+	 /* set up exceptions */
+	interrupt_init ();
+	/* enable exceptions */
+	enable_interrupts ();
+
+	/* Perform network card initialisation if necessary */
+#ifdef CONFIG_DRIVER_TI_EMAC
+	/* XXX: this needs to be moved to board init */
+extern void davinci_eth_set_mac_addr (const u_int8_t *addr);
+	if (getenv ("ethaddr")) {
+		uchar enetaddr[6];
+		eth_getenv_enetaddr("ethaddr", enetaddr);
+		davinci_eth_set_mac_addr(enetaddr);
+	}
+#endif
+
+#if defined(CONFIG_DRIVER_SMC91111) || defined (CONFIG_DRIVER_LAN91C96)
+	/* XXX: this needs to be moved to board init */
+	if (getenv ("ethaddr")) {
+		uchar enetaddr[6];
+		eth_getenv_enetaddr("ethaddr", enetaddr);
+		smc_set_mac_addr(enetaddr);
+	}
+#endif /* CONFIG_DRIVER_SMC91111 || CONFIG_DRIVER_LAN91C96 */
+
+	/* Initialize from environment */
+	if ((s = getenv ("loadaddr")) != NULL) {
+		load_addr = simple_strtoul (s, NULL, 16);
+	}
+#if defined(CONFIG_CMD_NET)
+	if ((s = getenv ("bootfile")) != NULL) {
+		copy_filename (BootFile, s, sizeof (BootFile));
+	}
+#endif
+
+#ifdef BOARD_LATE_INIT
+	board_late_init ();
+#endif
+
+#ifdef CONFIG_GENERIC_MMC
+	puts ("MMC:   ");
+	mmc_initialize (gd->bd);
+#endif
+
+#ifdef CONFIG_BITBANGMII
+	bb_miiphy_init();
+#endif
+#if defined(CONFIG_CMD_NET)
+#if defined(CONFIG_NET_MULTI)
+	puts ("Net:   ");
+#endif
+	eth_initialize(gd->bd);
+#if defined(CONFIG_RESET_PHY_R)
+	debug ("Reset Ethernet PHY\n");
+	reset_phy();
+#endif
+#endif
+
+#ifdef CONFIG_POST
+	post_run (NULL, POST_RAM | post_bootmode_get(0));
+#endif
+
+#if defined(CONFIG_PRAM) || defined(CONFIG_LOGBUFFER)
+	/*
+	 * Export available size of memory for Linux,
+	 * taking into account the protected RAM at top of memory
+	 */
+	{
+		ulong pram;
+		uchar memsz[32];
+#ifdef CONFIG_PRAM
+		char *s;
+
+		if ((s = getenv ("pram")) != NULL) {
+			pram = simple_strtoul (s, NULL, 10);
+		} else {
+			pram = CONFIG_PRAM;
+		}
+#else
+		pram=0;
+#endif
+#ifdef CONFIG_LOGBUFFER
+#ifndef CONFIG_ALT_LB_ADDR
+		/* Also take the logbuffer into account (pram is in kB) */
+		pram += (LOGBUFF_LEN+LOGBUFF_OVERHEAD)/1024;
+#endif
+#endif
+		sprintf ((char *)memsz, "%ldk", (bd->bi_memsize / 1024) - pram);
+		setenv ("mem", (char *)memsz);
+	}
+#endif
+
+	/* main_loop() can return to retry autoboot, if so just run it again. */
+	for (;;) {
+		main_loop ();
+	}
+
+	/* NOTREACHED - no way out of command loop except booting */
+}
+#endif /* defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 
 void hang (void)
 {
diff --git a/arch/arm/lib/cache-cp15.c b/arch/arm/lib/cache-cp15.c
index 62ed54fb4d..fe6d45987b 100644
--- a/arch/arm/lib/cache-cp15.c
+++ b/arch/arm/lib/cache-cp15.c
@@ -25,6 +25,15 @@
 #include <asm/system.h>
 
 #if !(defined(CONFIG_SYS_NO_ICACHE) && defined(CONFIG_SYS_NO_DCACHE))
+
+#if defined(CONFIG_SYS_ARM_CACHE_WRITETHROUGH)
+#define CACHE_SETUP	0x1a
+#else
+#define CACHE_SETUP	0x1e
+#endif
+
+DECLARE_GLOBAL_DATA_PTR;
+
 static void cp_delay (void)
 {
 	volatile int i;
@@ -32,6 +41,67 @@ static void cp_delay (void)
 	/* copro seems to need some delay between reading and writing */
 	for (i = 0; i < 100; i++)
 		nop();
+	asm volatile("" : : : "memory");
+}
+
+#if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
+static inline void dram_bank_mmu_setup(int bank)
+{
+	u32 *page_table = (u32 *)gd->tlb_addr;
+	bd_t *bd = gd->bd;
+	int	i;
+
+	debug("%s: bank: %d\n", __func__, bank);
+	for (i = bd->bi_dram[bank].start >> 20;
+	     i < (bd->bi_dram[bank].start + bd->bi_dram[bank].size) >> 20;
+	     i++) {
+		page_table[i] = i << 20 | (3 << 10) | CACHE_SETUP;
+	}
+}
+#endif
+
+/* to activate the MMU we need to set up virtual memory: use 1M areas */
+static inline void mmu_setup(void)
+{
+#if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
+	u32 *page_table = (u32 *)gd->tlb_addr;
+#else
+	static u32 __attribute__((aligned(16384))) page_table[4096];
+	bd_t *bd = gd->bd;
+	int j;
+#endif
+	int i;
+	u32 reg;
+
+	/* Set up an identity-mapping for all 4GB, rw for everyone */
+	for (i = 0; i < 4096; i++)
+		page_table[i] = i << 20 | (3 << 10) | 0x12;
+
+#if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
+	for (i = 0; i < CONFIG_NR_DRAM_BANKS; i++) {
+		dram_bank_mmu_setup(i);
+	}
+#else
+	/* Then, enable cacheable and bufferable for RAM only */
+	for (j = 0; j < CONFIG_NR_DRAM_BANKS; j++) {
+		for (i = bd->bi_dram[j].start >> 20;
+			i < (bd->bi_dram[j].start + bd->bi_dram[j].size) >> 20;
+			i++) {
+			page_table[i] = i << 20 | (3 << 10) | CACHE_SETUP;
+		}
+	}
+#endif
+
+	/* Copy the page table address to cp15 */
+	asm volatile("mcr p15, 0, %0, c2, c0, 0"
+		     : : "r" (page_table) : "memory");
+	/* Set the access control to all-supervisor */
+	asm volatile("mcr p15, 0, %0, c3, c0, 0"
+		     : : "r" (~0));
+	/* and enable the mmu */
+	reg = get_cr();	/* get control reg. */
+	cp_delay();
+	set_cr(reg | CR_M);
 }
 
 /* cache_bit must be either CR_I or CR_C */
@@ -39,6 +109,9 @@ static void cache_enable(uint32_t cache_bit)
 {
 	uint32_t reg;
 
+	/* The data cache is not active unless the mmu is enabled too */
+	if (cache_bit == CR_C)
+		mmu_setup();
 	reg = get_cr();	/* get control reg. */
 	cp_delay();
 	set_cr(reg | cache_bit);
@@ -49,6 +122,15 @@ static void cache_disable(uint32_t cache_bit)
 {
 	uint32_t reg;
 
+	if (cache_bit == CR_C) {
+		/* if cache isn;t enabled no need to disable */
+		reg = get_cr();
+		if ((reg & CR_C) != CR_C)
+			return;
+		/* if disabling data cache, disable mmu too */
+		cache_bit |= CR_M;
+		flush_cache(0, ~0);
+	}
 	reg = get_cr();
 	cp_delay();
 	set_cr(reg & ~cache_bit);
diff --git a/arch/arm/lib/cache.c b/arch/arm/lib/cache.c
index 61ee9d3b13..55b633ee00 100644
--- a/arch/arm/lib/cache.c
+++ b/arch/arm/lib/cache.c
@@ -27,10 +27,21 @@
 
 void  flush_cache (unsigned long dummy1, unsigned long dummy2)
 {
-#ifdef CONFIG_OMAP2420
+#if defined(CONFIG_OMAP2420) || defined(CONFIG_ARM1136)
 	void arm1136_cache_flush(void);
 
 	arm1136_cache_flush();
 #endif
+#ifdef CONFIG_ARM926EJS
+	/* test and clean, page 2-23 of arm926ejs manual */
+	asm("0: mrc p15, 0, r15, c7, c10, 3\n\t" "bne 0b\n" : : : "memory");
+	/* disable write buffer as well (page 2-22) */
+	asm("mcr p15, 0, %0, c7, c10, 4" : : "r" (0));
+#endif
+#ifdef CONFIG_ARMCORTEXA8
+	void v7_flush_cache_all(void);
+
+	v7_flush_cache_all();
+#endif
 	return;
 }
diff --git a/arch/arm/lib/interrupts.c b/arch/arm/lib/interrupts.c
index 1f2b815611..9a21e7b40a 100644
--- a/arch/arm/lib/interrupts.c
+++ b/arch/arm/lib/interrupts.c
@@ -38,15 +38,20 @@
 #include <common.h>
 #include <asm/proc-armv/ptrace.h>
 
-#ifdef CONFIG_USE_IRQ
 DECLARE_GLOBAL_DATA_PTR;
 
+#ifdef CONFIG_USE_IRQ
 int interrupt_init (void)
 {
 	/*
 	 * setup up stacks if necessary
 	 */
+#if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
+	IRQ_STACK_START = gd->irq_sp - 4;
+	IRQ_STACK_START_IN = gd->irq_sp + 8;
+#else
 	IRQ_STACK_START = _armboot_start - CONFIG_SYS_MALLOC_LEN - CONFIG_SYS_GBL_DATA_SIZE - 4;
+#endif
 	FIQ_STACK_START = IRQ_STACK_START - CONFIG_STACKSIZE_IRQ;
 
 	return arch_interrupt_init();
@@ -81,6 +86,18 @@ int disable_interrupts (void)
 	return (old & 0x80) == 0;
 }
 #else
+#if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
+int interrupt_init (void)
+{
+	/*
+	 * setup up stacks if necessary
+	 */
+	IRQ_STACK_START_IN = gd->irq_sp + 8;
+
+	return 0;
+}
+#endif
+
 void enable_interrupts (void)
 {
 	return;