diff --git a/arch/arm/cpu/arm1136/start.S b/arch/arm/cpu/arm1136/start.S
index 494768e..a86114b 100644
--- a/arch/arm/cpu/arm1136/start.S
+++ b/arch/arm/cpu/arm1136/start.S
@@ -89,48 +89,35 @@
 _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.
+ * Subtracting _start from them lets the linker put their
+ * relative position in the executable instead of leaving
+ * them null.
  */
-.globl _bss_start
-_bss_start:
-	.word __bss_start
+.globl _bss_start_ofs
+_bss_start_ofs:
+	.word __bss_start - _start
 
-.globl _bss_end
-_bss_end:
-	.word _end
+.globl _bss_end_ofs
+_bss_end_ofs:
+	.word _end - _start
 
-#if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC)
-.globl _datarel_start
-_datarel_start:
-	.word __datarel_start
+.globl _datarel_start_ofs
+_datarel_start_ofs:
+	.word __datarel_start - _start
 
-.globl _datarelrolocal_start
-_datarelrolocal_start:
-	.word __datarelrolocal_start
+.globl _datarelrolocal_start_ofs
+_datarelrolocal_start_ofs:
+	.word __datarelrolocal_start - _start
 
-.globl _datarellocal_start
-_datarellocal_start:
-	.word __datarellocal_start
+.globl _datarellocal_start_ofs
+_datarellocal_start_ofs:
+	.word __datarellocal_start - _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
+.globl _datarelro_start_ofs
+_datarelro_start_ofs:
+	.word __datarelro_start - _start
 
 #ifdef CONFIG_USE_IRQ
 /* IRQ stack memory (calculated at run-time) */
@@ -225,9 +212,8 @@
 
 	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	    */
+	ldr	r3, _bss_start_ofs
+	add	r2, r0, r3		/* r2 <- source end address	    */
 	cmp	r0, r6
 	beq	clear_bss
 
@@ -239,36 +225,54 @@
 	blo	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
-
+	/*
+	 * fix .rel.dyn relocations
+	 */
+	ldr	r0, _TEXT_BASE		/* r0 <- Text base */
+	sub	r9, r7, r0		/* r9 <- relocation offset */
+	ldr	r10, _dynsym_start_ofs	/* r10 <- sym table ofs */
+	add	r10, r10, r0		/* r10 <- sym table in FLASH */
+	ldr	r2, _rel_dyn_start_ofs	/* r2 <- rel dyn start ofs */
+	add	r2, r2, r0		/* r2 <- rel dyn start in FLASH */
+	ldr	r3, _rel_dyn_end_ofs	/* r3 <- rel dyn end ofs */
+	add	r3, r3, r0		/* r3 <- rel dyn end in FLASH */
 fixloop:
-	ldr	r4, [r2]
-	sub	r4, r4, r1
-	add	r4, r4, r0
-	str	r4, [r2]
-	add	r2, r2, #4
+	ldr	r0, [r2]	/* r0 <- location to fix up, IN FLASH! */
+	add	r0, r9		/* r0 <- location to fix up in RAM */
+	ldr	r1, [r2, #4]
+	and	r8, r1, #0xff
+	cmp	r8, #23		/* relative fixup? */
+	beq	fixrel
+	cmp	r8, #2		/* absolute fixup? */
+	beq	fixabs
+	/* ignore unknown type of fixup */
+	b	fixnext
+fixabs:
+	/* absolute fix: set location to (offset) symbol value */
+	mov	r1, r1, LSR #4		/* r1 <- symbol index in .dynsym */
+	add	r1, r10, r1		/* r1 <- address of symbol in table */
+	ldr	r1, [r1, #4]		/* r1 <- symbol value */
+	add	r1, r9			/* r1 <- relocated sym addr */
+	b	fixnext
+fixrel:
+	/* relative fix: increase location by offset */
+	ldr	r1, [r0]
+	add	r1, r1, r9
+fixnext:
+	str	r1, [r0]
+	add	r2, r2, #8	/* each rel.dyn entry is 8 bytes */
 	cmp	r2, r3
-	bne	fixloop
+	ble	fixloop
 #endif
 #endif	/* #ifndef CONFIG_SKIP_RELOCATE_UBOOT */
 
 clear_bss:
 #ifndef CONFIG_PRELOADER
-	ldr	r0, _bss_start
-	ldr	r1, _bss_end
+	ldr	r0, _bss_start_ofs
+	ldr	r1, _bss_end_ofs
 	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			    */
 
@@ -283,24 +287,34 @@
  * initialization, now running from RAM.
  */
 #ifdef CONFIG_NAND_SPL
-	ldr     pc, _nand_boot
-
-_nand_boot: .word nand_boot
+	ldr     r0, _nand_boot_ofs
+	adr	r1, _start
+	add	pc, r0, r1
+_nand_boot_ofs
+	: .word nand_boot - _start
 #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 */
+	ldr	r0, _board_init_r_ofs
+	adr	r1, _start
+	add	r0, r0, r1
+	add	lr, r0, r9
 	/* 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
+_board_init_r_ofs:
+	.word board_init_r - _start
 #endif
+
+_rel_dyn_start_ofs:
+	.word __rel_dyn_start - _start
+_rel_dyn_end_ofs:
+	.word __rel_dyn_end - _start
+_dynsym_start_ofs:
+	.word __dynsym_start - _start
+
 #else /* #if !defined(CONFIG_SYS_ARM_WITHOUT_RELOC) */
 /*
  * the actual reset code
@@ -375,8 +389,11 @@
 	bic	sp, sp, #7		/* 8-byte alignment for ABI compliance */
 
 clear_bss:
-	ldr	r0, _bss_start		/* find start of bss segment	    */
-	ldr	r1, _bss_end		/* stop here			    */
+	adr	r2, _start
+	ldr	r0, _bss_start_ofs	/* find start of bss segment        */
+	add	r0, r0, r2
+	ldr	r1, _bss_end_ofs	/* stop here                        */
+	add	r1, r1, r2
 	mov	r2, #0x00000000		/* clear			    */
 
 #ifndef CONFIG_PRELOADER
@@ -386,15 +403,19 @@
 	bne	clbss_l
 #endif
 
-	ldr	pc, _start_armboot
+	ldr	r0, _start_armboot_ofs
+	adr	r1, _start
+	add	r0, r0, r1
+	ldr	pc, r0
 
+_start_armboot_ofs:
 #ifdef CONFIG_NAND_SPL
-_start_armboot: .word nand_boot
+	.word nand_boot - _start
 #else
 #ifdef CONFIG_ONENAND_IPL
-_start_armboot: .word start_oneboot
+	.word start_oneboot - _start
 #else
-_start_armboot: .word start_armboot
+	.word start_armboot - _start
 #endif /* CONFIG_ONENAND_IPL */
 #endif /* CONFIG_NAND_SPL */
 
@@ -487,7 +508,7 @@
 #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
+	adr	r2, _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
@@ -524,8 +545,8 @@
 #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
+	adr	r13, _start			@ setup our mode stack (enter in banked mode)
+	sub	r13, r13, #(CONFIG_STACKSIZE+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