diff --git a/arch/arm/cpu/arm720t/start.S b/arch/arm/cpu/arm720t/start.S
index 8cd267b..46050da 100644
--- a/arch/arm/cpu/arm720t/start.S
+++ b/arch/arm/cpu/arm720t/start.S
@@ -81,14 +81,17 @@
 
 /*
  * 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
 
 #ifdef CONFIG_USE_IRQ
 /* IRQ stack memory (calculated at run-time) */
@@ -107,30 +110,6 @@
 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
  */
@@ -184,9 +163,8 @@
 
 	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
 
@@ -197,35 +175,53 @@
 	blo	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
-
+	/*
+	 * 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, 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
 	blo	fixloop
 #endif
 
 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			    */
 
@@ -242,18 +238,25 @@
  * 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 */
+	ldr	r0, _board_init_r_ofs
+	adr	r1, _start
+	add	lr, r0, r1
+	add	lr, lr, 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
+
+_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
 
 /*
  *************************************************************************
diff --git a/arch/arm/cpu/arm720t/u-boot.lds b/arch/arm/cpu/arm720t/u-boot.lds
index 4a0bc70..0686e42 100644
--- a/arch/arm/cpu/arm720t/u-boot.lds
+++ b/arch/arm/cpu/arm720t/u-boot.lds
@@ -40,29 +40,38 @@
 
 	. = ALIGN(4);
 	.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) }
 	__u_boot_cmd_end = .;
 
 	. = ALIGN(4);
-	__bss_start = .;
-	.bss (NOLOAD) : { *(.bss) . = ALIGN(4); }
-	_end = .;
+
+	.rel.dyn : {
+		__rel_dyn_start = .;
+		*(.rel*)
+		__rel_dyn_end = .;
+	}
+
+	.dynsym : {
+		__dynsym_start = .;
+		*(.dynsym)
+	}
+
+	.bss __rel_dyn_start (OVERLAY) : {
+		__bss_start = .;
+		*(.bss)
+		 . = ALIGN(4);
+		_end = .;
+	}
+
+	/DISCARD/ : { *(.dynstr*) }
+	/DISCARD/ : { *(.dynamic*) }
+	/DISCARD/ : { *(.plt*) }
+	/DISCARD/ : { *(.interp*) }
+	/DISCARD/ : { *(.gnu*) }
 }
diff --git a/arch/arm/cpu/arm920t/start.S b/arch/arm/cpu/arm920t/start.S
index d4edde7..01edb9b 100644
--- a/arch/arm/cpu/arm920t/start.S
+++ b/arch/arm/cpu/arm920t/start.S
@@ -77,14 +77,17 @@
 
 /*
  * 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
 
 #ifdef CONFIG_USE_IRQ
 /* IRQ stack memory (calculated at run-time) */
@@ -103,30 +106,6 @@
 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
  */
@@ -230,9 +209,8 @@
 
 	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
 
@@ -243,35 +221,53 @@
 	blo	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
-
+	/*
+	 * 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, 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
 	blo	fixloop
 #endif
 
 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			    */
 
@@ -289,24 +285,33 @@
  * initialization, now running from RAM.
  */
 #ifdef CONFIG_NAND_SPL
-	ldr     pc, _nand_boot
+	ldr     r0, _nand_boot_ofs
+	mov	pc, r0
 
-_nand_boot: .word nand_boot
+_nand_boot_ofs:
+	.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 */
+	ldr	r0, _board_init_r_ofs
+	adr	r1, _start
+	add	lr, r0, r1
+	add	lr, lr, 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
+
 /*
  *************************************************************************
  *
diff --git a/arch/arm/cpu/arm920t/u-boot.lds b/arch/arm/cpu/arm920t/u-boot.lds
index 6985434..a6f8b56 100644
--- a/arch/arm/cpu/arm920t/u-boot.lds
+++ b/arch/arm/cpu/arm920t/u-boot.lds
@@ -49,28 +49,38 @@
 	. = ALIGN(4);
 	.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) }
 	__u_boot_cmd_end = .;
 
 	. = ALIGN(4);
-	__bss_start = .;
-	.bss (NOLOAD) : { *(.bss) . = ALIGN(4); }
-	_end = .;
+
+	.rel.dyn : {
+		__rel_dyn_start = .;
+		*(.rel*)
+		__rel_dyn_end = .;
+	}
+
+	.dynsym : {
+		__dynsym_start = .;
+		*(.dynsym)
+	}
+
+	.bss __rel_dyn_start (OVERLAY) : {
+		__bss_start = .;
+		*(.bss)
+		 . = ALIGN(4);
+		_end = .;
+	}
+
+	/DISCARD/ : { *(.dynstr*) }
+	/DISCARD/ : { *(.dynamic*) }
+	/DISCARD/ : { *(.plt*) }
+	/DISCARD/ : { *(.interp*) }
+	/DISCARD/ : { *(.gnu*) }
 }
diff --git a/arch/arm/cpu/arm925t/start.S b/arch/arm/cpu/arm925t/start.S
index 51229c6..ce590a7 100644
--- a/arch/arm/cpu/arm925t/start.S
+++ b/arch/arm/cpu/arm925t/start.S
@@ -87,14 +87,17 @@
 
 /*
  * 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
 
 #ifdef CONFIG_USE_IRQ
 /* IRQ stack memory (calculated at run-time) */
@@ -113,30 +116,6 @@
 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
  */
@@ -221,9 +200,8 @@
 
 	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
 
@@ -234,35 +212,53 @@
 	blo	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
-
+	/*
+	 * 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, 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
 	blo	fixloop
 #endif
 
 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			    */
 
@@ -271,6 +267,8 @@
 	cmp	r0, r1
 	bne	clbss_l
 
+	bl coloured_LED_init
+	bl red_LED_on
 #endif
 
 /*
@@ -278,24 +276,33 @@
  * initialization, now running from RAM.
  */
 #ifdef CONFIG_NAND_SPL
-	ldr     pc, _nand_boot
+	ldr     r0, _nand_boot_ofs
+	mov	pc, r0
 
-_nand_boot: .word nand_boot
+_nand_boot_ofs:
+	.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 */
+	ldr	r0, _board_init_r_ofs
+	adr	r1, _start
+	add	lr, r0, r1
+	add	lr, lr, 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
+
 /*
  *************************************************************************
  *
diff --git a/arch/arm/cpu/arm925t/u-boot.lds b/arch/arm/cpu/arm925t/u-boot.lds
index 1c4e9bc..7b53edb 100644
--- a/arch/arm/cpu/arm925t/u-boot.lds
+++ b/arch/arm/cpu/arm925t/u-boot.lds
@@ -44,28 +44,38 @@
 	. = ALIGN(4);
 	.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) }
 	__u_boot_cmd_end = .;
 
 	. = ALIGN(4);
-	__bss_start = .;
-	.bss (NOLOAD) : { *(.bss) . = ALIGN(4); }
-	_end = .;
+
+	.rel.dyn : {
+		__rel_dyn_start = .;
+		*(.rel*)
+		__rel_dyn_end = .;
+	}
+
+	.dynsym : {
+		__dynsym_start = .;
+		*(.dynsym)
+	}
+
+	.bss __rel_dyn_start (OVERLAY) : {
+		__bss_start = .;
+		*(.bss)
+		 . = ALIGN(4);
+		_end = .;
+	}
+
+	/DISCARD/ : { *(.dynstr*) }
+	/DISCARD/ : { *(.dynamic*) }
+	/DISCARD/ : { *(.plt*) }
+	/DISCARD/ : { *(.interp*) }
+	/DISCARD/ : { *(.gnu*) }
 }
diff --git a/arch/arm/cpu/arm946es/start.S b/arch/arm/cpu/arm946es/start.S
index cad43ba..f4950f7 100644
--- a/arch/arm/cpu/arm946es/start.S
+++ b/arch/arm/cpu/arm946es/start.S
@@ -10,6 +10,7 @@
  *  Copyright (c) 2002	Gary Jennejohn <garyj@denx.de>
  *  Copyright (c) 2003	Richard Woodruff <r-woodruff2@ti.com>
  *  Copyright (c) 2003	Kshitij <kshitij@ti.com>
+ *  Copyright (c) 2010	Albert Aribaud <albert.aribaud@free.fr>
  *
  * See file CREDITS for list of people who contributed to this
  * project.
@@ -71,6 +72,7 @@
 
 	.balignl 16,0xdeadbeef
 
+_vectors_end:
 
 /*
  *************************************************************************
@@ -91,14 +93,17 @@
 
 /*
  * 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
 
 #ifdef CONFIG_USE_IRQ
 /* IRQ stack memory (calculated at run-time) */
@@ -117,30 +122,6 @@
 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
  */
@@ -190,9 +171,8 @@
 
 	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
 
@@ -203,42 +183,60 @@
 	blo	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
-
+	/*
+	 * 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, 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
 	blo	fixloop
 #endif
 
 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			    */
 
 clbss_l:str	r2, [r0]		/* clear loop...		    */
 	add	r0, r0, #4
 	cmp	r0, r1
-	bne	clbss_l
+	blo	clbss_l
 #endif
 
 /*
@@ -250,20 +248,27 @@
 
 _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 */
+	ldr	r0, _board_init_r_ofs
+	adr	r1, _start
+	add	lr, r0, r1
+	add	lr, lr, 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
+
 /*
  *************************************************************************
  *
diff --git a/arch/arm/cpu/arm946es/u-boot.lds b/arch/arm/cpu/arm946es/u-boot.lds
index 6535963..eb91979 100644
--- a/arch/arm/cpu/arm946es/u-boot.lds
+++ b/arch/arm/cpu/arm946es/u-boot.lds
@@ -41,28 +41,38 @@
 	. = ALIGN(4);
 	.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) }
 	__u_boot_cmd_end = .;
 
 	. = ALIGN(4);
-	__bss_start = .;
-	.bss (NOLOAD) : { *(.bss) . = ALIGN(4); }
-	_end = .;
+
+	.rel.dyn : {
+		__rel_dyn_start = .;
+		*(.rel*)
+		__rel_dyn_end = .;
+	}
+
+	.dynsym : {
+		__dynsym_start = .;
+		*(.dynsym)
+	}
+
+	.bss __rel_dyn_start (OVERLAY) : {
+		__bss_start = .;
+		*(.bss)
+		 . = ALIGN(4);
+		_end = .;
+	}
+
+	/DISCARD/ : { *(.dynstr*) }
+	/DISCARD/ : { *(.dynamic*) }
+	/DISCARD/ : { *(.plt*) }
+	/DISCARD/ : { *(.interp*) }
+	/DISCARD/ : { *(.gnu*) }
 }
diff --git a/arch/arm/cpu/arm_intcm/start.S b/arch/arm/cpu/arm_intcm/start.S
index 957ca34..fcaba30 100644
--- a/arch/arm/cpu/arm_intcm/start.S
+++ b/arch/arm/cpu/arm_intcm/start.S
@@ -89,14 +89,17 @@
 
 /*
  * 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
 
 #ifdef CONFIG_USE_IRQ
 /* IRQ stack memory (calculated at run-time) */
@@ -115,30 +118,6 @@
 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
  */
@@ -188,9 +167,8 @@
 
 	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
 
@@ -201,35 +179,53 @@
 	blo	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
-
+	/*
+	 * 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, 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
 	blo	fixloop
 #endif
 
 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			    */
 
@@ -246,18 +242,33 @@
  * 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 */
+#ifdef CONFIG_NAND_SPL
+	ldr     r0, _nand_boot_ofs
+	mov	pc, r0
+
+_nand_boot_ofs:
+	.word nand_boot
+#else
+	ldr	r0, _board_init_r_ofs
+	adr	r1, _start
+	add	lr, r0, r1
+	add	lr, lr, 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
 
 /*
  *************************************************************************
diff --git a/arch/arm/cpu/arm_intcm/u-boot.lds b/arch/arm/cpu/arm_intcm/u-boot.lds
index 242c7ec..3b5c18d 100644
--- a/arch/arm/cpu/arm_intcm/u-boot.lds
+++ b/arch/arm/cpu/arm_intcm/u-boot.lds
@@ -41,28 +41,38 @@
 	. = ALIGN(4);
 	.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) }
 	__u_boot_cmd_end = .;
 
 	. = ALIGN(4);
-	__bss_start = .;
-	.bss (NOLOAD) : { *(.bss) . = ALIGN(4); }
-	_end = .;
+
+	.rel.dyn : {
+		__rel_dyn_start = .;
+		*(.rel*)
+		__rel_dyn_end = .;
+	}
+
+	.dynsym : {
+		__dynsym_start = .;
+		*(.dynsym)
+	}
+
+	.bss __rel_dyn_start (OVERLAY) : {
+		__bss_start = .;
+		*(.bss)
+		 . = ALIGN(4);
+		_end = .;
+	}
+
+	/DISCARD/ : { *(.dynstr*) }
+	/DISCARD/ : { *(.dynamic*) }
+	/DISCARD/ : { *(.plt*) }
+	/DISCARD/ : { *(.interp*) }
+	/DISCARD/ : { *(.gnu*) }
 }
diff --git a/arch/arm/cpu/ixp/start.S b/arch/arm/cpu/ixp/start.S
index 8d1aebc..d1ab19b 100644
--- a/arch/arm/cpu/ixp/start.S
+++ b/arch/arm/cpu/ixp/start.S
@@ -100,14 +100,17 @@
 
 /*
  * 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
 
 #ifdef CONFIG_USE_IRQ
 /* IRQ stack memory (calculated at run-time) */
@@ -126,30 +129,6 @@
 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
  */
@@ -314,9 +293,8 @@
 
 	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
 
@@ -327,35 +305,53 @@
 	blo	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
-
+	/*
+	 * 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, 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
 	blo	fixloop
 #endif
 
 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			    */
 
@@ -372,19 +368,25 @@
  * 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 */
+	ldr	r0, _board_init_r_ofs
+	adr	r1, _start
+	add	lr, r0, r1
+	add	lr, lr, 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
 
+_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
 
 /****************************************************************************/
 /*									    */
diff --git a/arch/arm/cpu/ixp/u-boot.lds b/arch/arm/cpu/ixp/u-boot.lds
index f3d9dc5..a55eb8a 100644
--- a/arch/arm/cpu/ixp/u-boot.lds
+++ b/arch/arm/cpu/ixp/u-boot.lds
@@ -41,28 +41,38 @@
 	. = ALIGN(4);
 	.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) }
 	__u_boot_cmd_end = .;
 
 	. = ALIGN(4);
-	__bss_start = .;
-	.bss (NOLOAD) : { *(.bss) . = ALIGN(4); }
-	_end = .;
+
+	.rel.dyn : {
+		__rel_dyn_start = .;
+		*(.rel*)
+		__rel_dyn_end = .;
+	}
+
+	.dynsym : {
+		__dynsym_start = .;
+		*(.dynsym)
+	}
+
+	.bss __rel_dyn_start (OVERLAY) : {
+		__bss_start = .;
+		*(.bss)
+		 . = ALIGN(4);
+		_end = .;
+	}
+
+	/DISCARD/ : { *(.dynstr*) }
+	/DISCARD/ : { *(.dynamic*) }
+	/DISCARD/ : { *(.plt*) }
+	/DISCARD/ : { *(.interp*) }
+	/DISCARD/ : { *(.gnu*) }
 }
diff --git a/arch/arm/cpu/lh7a40x/start.S b/arch/arm/cpu/lh7a40x/start.S
index fd8a40b..5cf477b 100644
--- a/arch/arm/cpu/lh7a40x/start.S
+++ b/arch/arm/cpu/lh7a40x/start.S
@@ -77,14 +77,17 @@
 
 /*
  * 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
 
 #ifdef CONFIG_USE_IRQ
 /* IRQ stack memory (calculated at run-time) */
@@ -103,30 +106,6 @@
 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
  */
@@ -201,9 +180,8 @@
 
 	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
 
@@ -214,35 +192,53 @@
 	blo	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
-
+	/*
+	 * 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, 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
 	blo	fixloop
 #endif
 
 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			    */
 
@@ -256,18 +252,25 @@
  * 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 */
+	ldr	r0, _board_init_r_ofs
+	adr	r1, _start
+	add	lr, r0, r1
+	add	lr, lr, 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
+
+_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
 
 /*
  *************************************************************************
diff --git a/arch/arm/cpu/lh7a40x/u-boot.lds b/arch/arm/cpu/lh7a40x/u-boot.lds
index cb55b0a..463237d 100644
--- a/arch/arm/cpu/lh7a40x/u-boot.lds
+++ b/arch/arm/cpu/lh7a40x/u-boot.lds
@@ -41,28 +41,38 @@
 	. = ALIGN(4);
 	.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) }
 	__u_boot_cmd_end = .;
 
 	. = ALIGN(4);
-	__bss_start = .;
-	.bss (NOLOAD) : { *(.bss) . = ALIGN(4); }
-	_end = .;
+
+	.rel.dyn : {
+		__rel_dyn_start = .;
+		*(.rel*)
+		__rel_dyn_end = .;
+	}
+
+	.dynsym : {
+		__dynsym_start = .;
+		*(.dynsym)
+	}
+
+	.bss __rel_dyn_start (OVERLAY) : {
+		__bss_start = .;
+		*(.bss)
+		 . = ALIGN(4);
+		_end = .;
+	}
+
+	/DISCARD/ : { *(.dynstr*) }
+	/DISCARD/ : { *(.dynamic*) }
+	/DISCARD/ : { *(.plt*) }
+	/DISCARD/ : { *(.interp*) }
+	/DISCARD/ : { *(.gnu*) }
 }
diff --git a/arch/arm/cpu/s3c44b0/start.S b/arch/arm/cpu/s3c44b0/start.S
index 67b2c6a..8c7100c 100644
--- a/arch/arm/cpu/s3c44b0/start.S
+++ b/arch/arm/cpu/s3c44b0/start.S
@@ -68,14 +68,17 @@
 
 /*
  * 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
 
 #ifdef CONFIG_USE_IRQ
 /* IRQ stack memory (calculated at run-time) */
@@ -94,30 +97,6 @@
 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
  */
@@ -173,9 +152,8 @@
 
 	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
 
@@ -186,47 +164,53 @@
 	blo	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
-
+	/*
+	 * 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, 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
 	blo	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
-	blo	vector_copy_loop
 
 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			    */
 
@@ -243,18 +227,25 @@
  * 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 */
+	ldr	r0, _board_init_r_ofs
+	adr	r1, _start
+	add	lr, r0, r1
+	add	lr, lr, 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
+
+_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
 
 /*
  *************************************************************************
diff --git a/arch/arm/cpu/s3c44b0/u-boot.lds b/arch/arm/cpu/s3c44b0/u-boot.lds
index bbc8c3a..ac29440 100644
--- a/arch/arm/cpu/s3c44b0/u-boot.lds
+++ b/arch/arm/cpu/s3c44b0/u-boot.lds
@@ -41,28 +41,38 @@
 	. = ALIGN(4);
 	.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) }
 	__u_boot_cmd_end = .;
 
 	. = ALIGN(4);
-	__bss_start = .;
-	.bss (NOLOAD) : { *(.bss) . = ALIGN(4); }
-	_end = .;
+
+	.rel.dyn : {
+		__rel_dyn_start = .;
+		*(.rel*)
+		__rel_dyn_end = .;
+	}
+
+	.dynsym : {
+		__dynsym_start = .;
+		*(.dynsym)
+	}
+
+	.bss __rel_dyn_start (OVERLAY) : {
+		__bss_start = .;
+		*(.bss)
+		 . = ALIGN(4);
+		_end = .;
+	}
+
+	/DISCARD/ : { *(.dynstr*) }
+	/DISCARD/ : { *(.dynamic*) }
+	/DISCARD/ : { *(.plt*) }
+	/DISCARD/ : { *(.interp*) }
+	/DISCARD/ : { *(.gnu*) }
 }
diff --git a/arch/arm/cpu/sa1100/start.S b/arch/arm/cpu/sa1100/start.S
index ace0c07..36d44da 100644
--- a/arch/arm/cpu/sa1100/start.S
+++ b/arch/arm/cpu/sa1100/start.S
@@ -78,14 +78,17 @@
 
 /*
  * 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
 
 #ifdef CONFIG_USE_IRQ
 /* IRQ stack memory (calculated at run-time) */
@@ -104,30 +107,6 @@
 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
  */
@@ -177,9 +156,8 @@
 
 	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
 
@@ -190,35 +168,53 @@
 	blo	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
-
+	/*
+	 * 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, 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
 	blo	fixloop
 #endif
 
 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			    */
 
@@ -232,18 +228,25 @@
  * 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 */
+	ldr	r0, _board_init_r_ofs
+	adr	r1, _start
+	add	lr, r0, r1
+	add	lr, lr, 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
+
+_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
 
 /*
  *************************************************************************
diff --git a/arch/arm/cpu/sa1100/u-boot.lds b/arch/arm/cpu/sa1100/u-boot.lds
index 2e29291..fa6d05c 100644
--- a/arch/arm/cpu/sa1100/u-boot.lds
+++ b/arch/arm/cpu/sa1100/u-boot.lds
@@ -44,28 +44,38 @@
 	. = ALIGN(4);
 	.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) }
 	__u_boot_cmd_end = .;
 
 	. = ALIGN(4);
-	__bss_start = .;
-	.bss (NOLOAD) : { *(.bss) . = ALIGN(4); }
-	_end = .;
+
+	.rel.dyn : {
+		__rel_dyn_start = .;
+		*(.rel*)
+		__rel_dyn_end = .;
+	}
+
+	.dynsym : {
+		__dynsym_start = .;
+		*(.dynsym)
+	}
+
+	.bss __rel_dyn_start (OVERLAY) : {
+		__bss_start = .;
+		*(.bss)
+		 . = ALIGN(4);
+		_end = .;
+	}
+
+	/DISCARD/ : { *(.dynstr*) }
+	/DISCARD/ : { *(.dynamic*) }
+	/DISCARD/ : { *(.plt*) }
+	/DISCARD/ : { *(.interp*) }
+	/DISCARD/ : { *(.gnu*) }
 }