diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 04f77214f0502f723613083b43cc058279d2f22e..cabdd8f4a2482e2b2362794b3071173c87431b3a 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -151,6 +151,25 @@
 .L_\@:
 		.endm
 
+		/*
+		 * The kernel build system appends the size of the
+		 * decompressed kernel at the end of the compressed data
+		 * in little-endian form.
+		 */
+		.macro	get_inflated_image_size, res:req, tmp1:req, tmp2:req
+		adr	\res, .Linflated_image_size_offset
+		ldr	\tmp1, [\res]
+		add	\tmp1, \tmp1, \res	@ address of inflated image size
+
+		ldrb	\res, [\tmp1]		@ get_unaligned_le32
+		ldrb	\tmp2, [\tmp1, #1]
+		orr	\res, \res, \tmp2, lsl #8
+		ldrb	\tmp2, [\tmp1, #2]
+		ldrb	\tmp1, [\tmp1, #3]
+		orr	\res, \res, \tmp2, lsl #16
+		orr	\res, \res, \tmp1, lsl #24
+		.endm
+
 		.section ".start", "ax"
 /*
  * sort out different calling conventions
@@ -268,15 +287,15 @@ not_angel:
 		 */
 		mov	r0, pc
 		cmp	r0, r4
-		ldrcc	r0, LC0+32
+		ldrcc	r0, LC0+28
 		addcc	r0, r0, pc
 		cmpcc	r4, r0
 		orrcc	r4, r4, #1		@ remember we skipped cache_on
 		blcs	cache_on
 
 restart:	adr	r0, LC0
-		ldmia	r0, {r1, r2, r3, r6, r10, r11, r12}
-		ldr	sp, [r0, #28]
+		ldmia	r0, {r1, r2, r3, r6, r11, r12}
+		ldr	sp, [r0, #24]
 
 		/*
 		 * We might be running at a different address.  We need
@@ -284,20 +303,8 @@ restart:	adr	r0, LC0
 		 */
 		sub	r0, r0, r1		@ calculate the delta offset
 		add	r6, r6, r0		@ _edata
-		add	r10, r10, r0		@ inflated kernel size location
 
-		/*
-		 * The kernel build system appends the size of the
-		 * decompressed kernel at the end of the compressed data
-		 * in little-endian form.
-		 */
-		ldrb	r9, [r10, #0]
-		ldrb	lr, [r10, #1]
-		orr	r9, r9, lr, lsl #8
-		ldrb	lr, [r10, #2]
-		ldrb	r10, [r10, #3]
-		orr	r9, r9, lr, lsl #16
-		orr	r9, r9, r10, lsl #24
+		get_inflated_image_size	r9, r10, lr
 
 #ifndef CONFIG_ZBOOT_ROM
 		/* malloc space is above the relocated stack (64k max) */
@@ -521,11 +528,8 @@ dtb_check_done:
 		/* Preserve offset to relocated code. */
 		sub	r6, r9, r6
 
-#ifndef CONFIG_ZBOOT_ROM
-		/* cache_clean_flush may use the stack, so relocate it */
-		add	sp, sp, r6
-#endif
-
+		mov	r0, r9			@ start of relocated zImage
+		add	r1, sp, r6		@ end of relocated zImage
 		bl	cache_clean_flush
 
 		badr	r0, restart
@@ -622,6 +626,11 @@ not_relocated:	mov	r0, #0
 		add	r2, sp, #0x10000	@ 64k max
 		mov	r3, r7
 		bl	decompress_kernel
+
+		get_inflated_image_size	r1, r2, r3
+
+		mov	r0, r4			@ start of inflated image
+		add	r1, r1, r0		@ end of inflated image
 		bl	cache_clean_flush
 		bl	cache_off
 
@@ -652,13 +661,15 @@ LC0:		.word	LC0			@ r1
 		.word	__bss_start		@ r2
 		.word	_end			@ r3
 		.word	_edata			@ r6
-		.word	input_data_end - 4	@ r10 (inflated size location)
 		.word	_got_start		@ r11
 		.word	_got_end		@ ip
 		.word	.L_user_stack_end	@ sp
 		.word	_end - restart + 16384 + 1024*1024
 		.size	LC0, . - LC0
 
+.Linflated_image_size_offset:
+		.long	(input_data_end - 4) - .
+
 #ifdef CONFIG_ARCH_RPC
 		.globl	params
 params:		ldr	r0, =0x10000100		@ params_phys for RPC
@@ -667,6 +678,24 @@ params:		ldr	r0, =0x10000100		@ params_phys for RPC
 		.align
 #endif
 
+/*
+ * dcache_line_size - get the minimum D-cache line size from the CTR register
+ * on ARMv7.
+ */
+		.macro	dcache_line_size, reg, tmp
+#ifdef CONFIG_CPU_V7M
+		movw	\tmp, #:lower16:BASEADDR_V7M_SCB + V7M_SCB_CTR
+		movt	\tmp, #:upper16:BASEADDR_V7M_SCB + V7M_SCB_CTR
+		ldr	\tmp, [\tmp]
+#else
+		mrc	p15, 0, \tmp, c0, c0, 1		@ read ctr
+#endif
+		lsr	\tmp, \tmp, #16
+		and	\tmp, \tmp, #0xf		@ cache line size encoding
+		mov	\reg, #4			@ bytes per word
+		mov	\reg, \reg, lsl \tmp		@ actual cache line size
+		.endm
+
 /*
  * Turn on the cache.  We need to setup some page tables so that we
  * can have both the I and D caches on.
@@ -1159,8 +1188,6 @@ __armv7_mmu_cache_off:
 		bic	r0, r0, #0x000c
 #endif
 		mcr	p15, 0, r0, c1, c0	@ turn MMU and cache off
-		mov	r12, lr
-		bl	__armv7_mmu_cache_flush
 		mov	r0, #0
 #ifdef CONFIG_MMU
 		mcr	p15, 0, r0, c8, c7, 0	@ invalidate whole TLB
@@ -1168,11 +1195,14 @@ __armv7_mmu_cache_off:
 		mcr	p15, 0, r0, c7, c5, 6	@ invalidate BTC
 		mcr	p15, 0, r0, c7, c10, 4	@ DSB
 		mcr	p15, 0, r0, c7, c5, 4	@ ISB
-		mov	pc, r12
+		mov	pc, lr
 
 /*
  * Clean and flush the cache to maintain consistency.
  *
+ * On entry,
+ *  r0 = start address
+ *  r1 = end address (exclusive)
  * On exit,
  *  r1, r2, r3, r9, r10, r11, r12 corrupted
  * This routine must preserve:
@@ -1181,6 +1211,7 @@ __armv7_mmu_cache_off:
 		.align	5
 cache_clean_flush:
 		mov	r3, #16
+		mov	r11, r1
 		b	call_cache_fn
 
 __armv4_mpu_cache_flush:
@@ -1231,51 +1262,16 @@ __armv7_mmu_cache_flush:
 		mcr	p15, 0, r10, c7, c14, 0	@ clean+invalidate D
 		b	iflush
 hierarchical:
-		mcr	p15, 0, r10, c7, c10, 5	@ DMB
-		stmfd	sp!, {r0-r7, r9-r11}
-		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	@ isb to sych the new cssr&csidr
-		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:
- ARM(		orr	r11, r10, r9, lsl r5	) @ factor way and cache number into r11
- ARM(		orr	r11, r11, r7, lsl r2	) @ factor index number into r11
- THUMB(		lsl	r6, r9, r5		)
- THUMB(		orr	r11, r10, r6		) @ factor way and cache number into r11
- THUMB(		lsl	r6, r7, r2		)
- THUMB(		orr	r11, r11, r6		) @ 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:
-		ldmfd	sp!, {r0-r7, r9-r11}
-		mov	r10, #0			@ switch back to cache level 0
-		mcr	p15, 2, r10, c0, c0, 0	@ select current cache level in cssr
+		dcache_line_size r1, r2		@ r1 := dcache min line size
+		sub	r2, r1, #1		@ r2 := line size mask
+		bic	r0, r0, r2		@ round down start to line size
+		sub	r11, r11, #1		@ end address is exclusive
+		bic	r11, r11, r2		@ round down end to line size
+0:		cmp	r0, r11			@ finished?
+		bgt	iflush
+		mcr	p15, 0, r0, c7, c14, 1	@ Dcache clean/invalidate by VA
+		add	r0, r0, r1
+		b	0b
 iflush:
 		mcr	p15, 0, r10, c7, c10, 4	@ DSB
 		mcr	p15, 0, r10, c7, c5, 0	@ invalidate I+BTB
diff --git a/arch/arm/boot/compressed/vmlinux.lds.S b/arch/arm/boot/compressed/vmlinux.lds.S
index fc7ed03d8b932daa6387a265f3131eed192680b3..b247f399de711b36a98f9945d51231797e248659 100644
--- a/arch/arm/boot/compressed/vmlinux.lds.S
+++ b/arch/arm/boot/compressed/vmlinux.lds.S
@@ -36,7 +36,6 @@ SECTIONS
     *(.start)
     *(.text)
     *(.text.*)
-    *(.fixup)
     *(.gnu.warning)
     *(.glue_7t)
     *(.glue_7)
diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S
index 7eaa2ae7aff58921607883cb7e6765a22185852a..72a08786e16eb0bbc172e144e9300c75a6b6f988 100644
--- a/arch/arm/kernel/relocate_kernel.S
+++ b/arch/arm/kernel/relocate_kernel.S
@@ -25,26 +25,26 @@ ENTRY(relocate_new_kernel)
 	ldr	r3, [r0],#4
 
 	/* Is it a destination page. Put destination address to r4 */
-	tst	r3,#1,0
+	tst	r3,#1
 	beq	1f
 	bic	r4,r3,#1
 	b	0b
 1:
 	/* Is it an indirection page */
-	tst	r3,#2,0
+	tst	r3,#2
 	beq	1f
 	bic	r0,r3,#2
 	b	0b
 1:
 
 	/* are we done ? */
-	tst	r3,#4,0
+	tst	r3,#4
 	beq	1f
 	b	2f
 
 1:
 	/* is it source ? */
-	tst	r3,#8,0
+	tst	r3,#8
 	beq	0b
 	bic r3,r3,#8
 	mov r6,#1024
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index 4574e6aea0a528836641acd95a9f16377616716a..11a964fd66f474b7090a45cf8f65938c65bd12d2 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -444,7 +444,7 @@ int unwind_frame(struct stackframe *frame)
 		ctrl.vrs[PC] = ctrl.vrs[LR];
 
 	/* check for infinite loop */
-	if (frame->pc == ctrl.vrs[PC])
+	if (frame->pc == ctrl.vrs[PC] && frame->sp == ctrl.vrs[SP])
 		return -URC_FAILURE;
 
 	frame->fp = ctrl.vrs[FP];
diff --git a/arch/arm/mach-ebsa110/core.c b/arch/arm/mach-ebsa110/core.c
index da2ff4f61d6bc1525cb117f488acfde7aed1d1ba..575b2e2b6759f624ddb74e892e6de64fd02b1940 100644
--- a/arch/arm/mach-ebsa110/core.c
+++ b/arch/arm/mach-ebsa110/core.c
@@ -201,17 +201,13 @@ ebsa110_timer_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static struct irqaction ebsa110_timer_irq = {
-	.name		= "EBSA110 Timer Tick",
-	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
-	.handler	= ebsa110_timer_interrupt,
-};
-
 /*
  * Set up timer interrupt.
  */
 void __init ebsa110_timer_init(void)
 {
+	int irq = IRQ_EBSA110_TIMER0;
+
 	arch_gettimeoffset = ebsa110_gettimeoffset;
 
 	/*
@@ -221,7 +217,9 @@ void __init ebsa110_timer_init(void)
 	__raw_writeb(COUNT & 0xff, PIT_T1);
 	__raw_writeb(COUNT >> 8, PIT_T1);
 
-	setup_irq(IRQ_EBSA110_TIMER0, &ebsa110_timer_irq);
+	if (request_irq(irq, ebsa110_timer_interrupt, IRQF_TIMER | IRQF_IRQPOLL,
+			"EBSA110 Timer Tick", NULL))
+		pr_err("Failed to request irq %d (EBSA110 Timer Tick)\n", irq);
 }
 
 static struct plat_serial8250_port serial_platform_data[] = {
diff --git a/arch/arm/mach-footbridge/dc21285-timer.c b/arch/arm/mach-footbridge/dc21285-timer.c
index f76212d2dbf1fed88106325c7fa7f133af01fa6f..2908c9ef3c9b01f1c40f6dbd1b3bb0adf740e4af 100644
--- a/arch/arm/mach-footbridge/dc21285-timer.c
+++ b/arch/arm/mach-footbridge/dc21285-timer.c
@@ -101,13 +101,6 @@ static irqreturn_t timer1_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static struct irqaction footbridge_timer_irq = {
-	.name		= "dc21285_timer1",
-	.handler	= timer1_interrupt,
-	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
-	.dev_id		= &ckevt_dc21285,
-};
-
 /*
  * Set up timer interrupt.
  */
@@ -118,7 +111,9 @@ void __init footbridge_timer_init(void)
 
 	clocksource_register_hz(&cksrc_dc21285, rate);
 
-	setup_irq(ce->irq, &footbridge_timer_irq);
+	if (request_irq(ce->irq, timer1_interrupt, IRQF_TIMER | IRQF_IRQPOLL,
+			"dc21285_timer1", &ckevt_dc21285))
+		pr_err("Failed to request irq %d (dc21285_timer1)", ce->irq);
 
 	ce->cpumask = cpumask_of(smp_processor_id());
 	clockevents_config_and_register(ce, rate, 0x4, 0xffffff);
diff --git a/arch/arm/mach-footbridge/isa-irq.c b/arch/arm/mach-footbridge/isa-irq.c
index 88a553932c331bd6bc8821edcce594e850594810..842ddb4121ef145579999c8e1289a7b5aaa3126f 100644
--- a/arch/arm/mach-footbridge/isa-irq.c
+++ b/arch/arm/mach-footbridge/isa-irq.c
@@ -96,11 +96,6 @@ static void isa_irq_handler(struct irq_desc *desc)
 	generic_handle_irq(isa_irq);
 }
 
-static struct irqaction irq_cascade = {
-	.handler = no_action,
-	.name = "cascade",
-};
-
 static struct resource pic1_resource = {
 	.name	= "pic1",
 	.start	= 0x20,
@@ -160,7 +155,10 @@ void __init isa_init_irq(unsigned int host_irq)
 
 		request_resource(&ioport_resource, &pic1_resource);
 		request_resource(&ioport_resource, &pic2_resource);
-		setup_irq(IRQ_ISA_CASCADE, &irq_cascade);
+
+		irq = IRQ_ISA_CASCADE;
+		if (request_irq(irq, no_action, 0, "cascade", NULL))
+			pr_err("Failed to request irq %u (cascade)\n", irq);
 
 		irq_set_chained_handler(host_irq, isa_irq_handler);
 
diff --git a/arch/arm/mach-footbridge/isa-timer.c b/arch/arm/mach-footbridge/isa-timer.c
index 82f45591fb2cb7ef5e5eb949fe17f356fa342833..723e3eae995d70cfc80d85a2f44969c295b87b2d 100644
--- a/arch/arm/mach-footbridge/isa-timer.c
+++ b/arch/arm/mach-footbridge/isa-timer.c
@@ -25,17 +25,12 @@ static irqreturn_t pit_timer_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static struct irqaction pit_timer_irq = {
-	.name		= "pit",
-	.handler	= pit_timer_interrupt,
-	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
-	.dev_id		= &i8253_clockevent,
-};
-
 void __init isa_timer_init(void)
 {
 	clocksource_i8253_init();
 
-	setup_irq(i8253_clockevent.irq, &pit_timer_irq);
+	if (request_irq(i8253_clockevent.irq, pit_timer_interrupt,
+			IRQF_TIMER | IRQF_IRQPOLL, "pit", &i8253_clockevent))
+		pr_err("Failed to request irq %d(pit)\n", i8253_clockevent.irq);
 	clockevent_i8253_init(false);
 }
diff --git a/arch/arm/mach-rpc/time.c b/arch/arm/mach-rpc/time.c
index 1d750152b160bec69194a923e59eda368e482037..da85cac761ba0fb5893853fe35953d93371188a5 100644
--- a/arch/arm/mach-rpc/time.c
+++ b/arch/arm/mach-rpc/time.c
@@ -85,11 +85,6 @@ ioc_timer_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static struct irqaction ioc_timer_irq = {
-	.name		= "timer",
-	.handler	= ioc_timer_interrupt
-};
-
 /*
  * Set up timer interrupt.
  */
@@ -97,5 +92,6 @@ void __init ioc_timer_init(void)
 {
 	WARN_ON(clocksource_register_hz(&ioctime_clocksource, RPC_CLOCK_FREQ));
 	ioctime_init();
-	setup_irq(IRQ_TIMER0, &ioc_timer_irq);
+	if (request_irq(IRQ_TIMER0, ioc_timer_interrupt, 0, "timer", NULL))
+		pr_err("Failed to request irq %d (timer)\n", IRQ_TIMER0);
 }