19 files changed, 219 insertions, 106 deletions

diff --git a/arch/arm/kernel/arch_timer.c b/arch/arm/kernel/arch_timer.c
index d957a51435d8..59dcdced6e30 100644
--- a/arch/arm/kernel/arch_timer.c
+++ b/arch/arm/kernel/arch_timer.c
@@ -22,9 +22,11 @@ static unsigned long arch_timer_read_counter_long(void)
 	return arch_timer_read_counter();
 }
 
-static u32 arch_timer_read_counter_u32(void)
+static u32 sched_clock_mult __read_mostly;
+
+static unsigned long long notrace arch_timer_sched_clock(void)
 {
-	return arch_timer_read_counter();
+	return arch_timer_read_counter() * sched_clock_mult;
 }
 
 static struct delay_timer arch_delay_timer;
@@ -37,25 +39,20 @@ static void __init arch_timer_delay_timer_register(void)
 	register_current_timer_delay(&arch_delay_timer);
 }
 
-int __init arch_timer_of_register(void)
+int __init arch_timer_arch_init(void)
 {
-	int ret;
+        u32 arch_timer_rate = arch_timer_get_rate();
 
-	ret = arch_timer_init();
-	if (ret)
-		return ret;
+	if (arch_timer_rate == 0)
+		return -ENXIO;
 
 	arch_timer_delay_timer_register();
 
-	return 0;
-}
-
-int __init arch_timer_sched_clock_init(void)
-{
-	if (arch_timer_get_rate() == 0)
-		return -ENXIO;
+	/* Cache the sched_clock multiplier to save a divide in the hot path. */
+	sched_clock_mult = NSEC_PER_SEC / arch_timer_rate;
+	sched_clock_func = arch_timer_sched_clock;
+	pr_info("sched_clock: ARM arch timer >56 bits at %ukHz, resolution %uns\n",
+		arch_timer_rate / 1000, sched_clock_mult);
 
-	setup_sched_clock(arch_timer_read_counter_u32,
-			  32, arch_timer_get_rate());
 	return 0;
 }
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 923eec7105cf..ee68cce6b48e 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -149,12 +149,16 @@ int main(void)
   DEFINE(DMA_BIDIRECTIONAL,	DMA_BIDIRECTIONAL);
   DEFINE(DMA_TO_DEVICE,		DMA_TO_DEVICE);
   DEFINE(DMA_FROM_DEVICE,	DMA_FROM_DEVICE);
+  BLANK();
+  DEFINE(CACHE_WRITEBACK_ORDER, __CACHE_WRITEBACK_ORDER);
+  DEFINE(CACHE_WRITEBACK_GRANULE, __CACHE_WRITEBACK_GRANULE);
+  BLANK();
 #ifdef CONFIG_KVM_ARM_HOST
   DEFINE(VCPU_KVM,		offsetof(struct kvm_vcpu, kvm));
   DEFINE(VCPU_MIDR,		offsetof(struct kvm_vcpu, arch.midr));
   DEFINE(VCPU_CP15,		offsetof(struct kvm_vcpu, arch.cp15));
   DEFINE(VCPU_VFP_GUEST,	offsetof(struct kvm_vcpu, arch.vfp_guest));
-  DEFINE(VCPU_VFP_HOST,		offsetof(struct kvm_vcpu, arch.vfp_host));
+  DEFINE(VCPU_VFP_HOST,		offsetof(struct kvm_vcpu, arch.host_cpu_context));
   DEFINE(VCPU_REGS,		offsetof(struct kvm_vcpu, arch.regs));
   DEFINE(VCPU_USR_REGS,		offsetof(struct kvm_vcpu, arch.regs.usr_regs));
   DEFINE(VCPU_SVC_REGS,		offsetof(struct kvm_vcpu, arch.regs.svc_regs));
@@ -165,10 +169,10 @@ int main(void)
   DEFINE(VCPU_PC,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_pc));
   DEFINE(VCPU_CPSR,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_cpsr));
   DEFINE(VCPU_IRQ_LINES,	offsetof(struct kvm_vcpu, arch.irq_lines));
-  DEFINE(VCPU_HSR,		offsetof(struct kvm_vcpu, arch.hsr));
-  DEFINE(VCPU_HxFAR,		offsetof(struct kvm_vcpu, arch.hxfar));
-  DEFINE(VCPU_HPFAR,		offsetof(struct kvm_vcpu, arch.hpfar));
-  DEFINE(VCPU_HYP_PC,		offsetof(struct kvm_vcpu, arch.hyp_pc));
+  DEFINE(VCPU_HSR,		offsetof(struct kvm_vcpu, arch.fault.hsr));
+  DEFINE(VCPU_HxFAR,		offsetof(struct kvm_vcpu, arch.fault.hxfar));
+  DEFINE(VCPU_HPFAR,		offsetof(struct kvm_vcpu, arch.fault.hpfar));
+  DEFINE(VCPU_HYP_PC,		offsetof(struct kvm_vcpu, arch.fault.hyp_pc));
 #ifdef CONFIG_KVM_ARM_VGIC
   DEFINE(VCPU_VGIC_CPU,		offsetof(struct kvm_vcpu, arch.vgic_cpu));
   DEFINE(VGIC_CPU_HCR,		offsetof(struct vgic_cpu, vgic_hcr));
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index a1f73b502ef0..b2ed73c45489 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -462,6 +462,7 @@ static void pcibios_init_hw(struct hw_pci *hw, struct list_head *head)
 		sys->busnr   = busnr;
 		sys->swizzle = hw->swizzle;
 		sys->map_irq = hw->map_irq;
+		sys->align_resource = hw->align_resource;
 		INIT_LIST_HEAD(&sys->resources);
 
 		if (hw->private_data)
@@ -574,6 +575,8 @@ char * __init pcibios_setup(char *str)
 resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 				resource_size_t size, resource_size_t align)
 {
+	struct pci_dev *dev = data;
+	struct pci_sys_data *sys = dev->sysdata;
 	resource_size_t start = res->start;
 
 	if (res->flags & IORESOURCE_IO && start & 0x300)
@@ -581,6 +584,9 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 
 	start = (start + align - 1) & ~(align - 1);
 
+	if (sys->align_resource)
+		return sys->align_resource(dev, res, start, size, align);
+
 	return start;
 }
 
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 70f1bdeb241b..5af04f6daa33 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -180,6 +180,13 @@ struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
 	unsigned long dt_root;
 	const char *model;
 
+#ifdef CONFIG_ARCH_MULTIPLATFORM
+	DT_MACHINE_START(GENERIC_DT, "Generic DT based system")
+	MACHINE_END
+
+	mdesc_best = (struct machine_desc *)&__mach_desc_GENERIC_DT;
+#endif
+
 	if (!dt_phys)
 		return NULL;
 
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 0f82098c9bfe..582b405befc5 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -192,18 +192,6 @@ __dabt_svc:
 	svc_entry
 	mov	r2, sp
 	dabt_helper
-
-	@
-	@ IRQs off again before pulling preserved data off the stack
-	@
-	disable_irq_notrace
-
-#ifdef CONFIG_TRACE_IRQFLAGS
-	tst	r5, #PSR_I_BIT
-	bleq	trace_hardirqs_on
-	tst	r5, #PSR_I_BIT
-	blne	trace_hardirqs_off
-#endif
 	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__dabt_svc)
@@ -223,12 +211,7 @@ __irq_svc:
 	blne	svc_preempt
 #endif
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-	@ The parent context IRQs must have been enabled to get here in
-	@ the first place, so there's no point checking the PSR I bit.
-	bl	trace_hardirqs_on
-#endif
-	svc_exit r5				@ return from exception
+	svc_exit r5, irq = 1			@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__irq_svc)
 
@@ -295,22 +278,8 @@ __und_svc_fault:
 	mov	r0, sp				@ struct pt_regs *regs
 	bl	__und_fault
 
-	@
-	@ IRQs off again before pulling preserved data off the stack
-	@
 __und_svc_finish:
-	disable_irq_notrace
-
-	@
-	@ restore SPSR and restart the instruction
-	@
 	ldr	r5, [sp, #S_PSR]		@ Get SVC cpsr
-#ifdef CONFIG_TRACE_IRQFLAGS
-	tst	r5, #PSR_I_BIT
-	bleq	trace_hardirqs_on
-	tst	r5, #PSR_I_BIT
-	blne	trace_hardirqs_off
-#endif
 	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__und_svc)
@@ -320,18 +289,6 @@ __pabt_svc:
 	svc_entry
 	mov	r2, sp				@ regs
 	pabt_helper
-
-	@
-	@ IRQs off again before pulling preserved data off the stack
-	@
-	disable_irq_notrace
-
-#ifdef CONFIG_TRACE_IRQFLAGS
-	tst	r5, #PSR_I_BIT
-	bleq	trace_hardirqs_on
-	tst	r5, #PSR_I_BIT
-	blne	trace_hardirqs_off
-#endif
 	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__pabt_svc)
@@ -396,6 +353,7 @@ ENDPROC(__pabt_svc)
 #ifdef CONFIG_IRQSOFF_TRACER
 	bl	trace_hardirqs_off
 #endif
+	ct_user_exit save = 0
 	.endm
 
 	.macro	kuser_cmpxchg_check
@@ -562,21 +520,21 @@ ENDPROC(__und_usr)
 	@ Fall-through from Thumb-2 __und_usr
 	@
 #ifdef CONFIG_NEON
+	get_thread_info r10			@ get current thread
 	adr	r6, .LCneon_thumb_opcodes
 	b	2f
 #endif
 call_fpe:
+	get_thread_info r10			@ get current thread
 #ifdef CONFIG_NEON
 	adr	r6, .LCneon_arm_opcodes
-2:
-	ldr	r7, [r6], #4			@ mask value
-	cmp	r7, #0				@ end mask?
-	beq	1f
-	and	r8, r0, r7
+2:	ldr	r5, [r6], #4			@ mask value
 	ldr	r7, [r6], #4			@ opcode bits matching in mask
+	cmp	r5, #0				@ end mask?
+	beq	1f
+	and	r8, r0, r5
 	cmp	r8, r7				@ NEON instruction?
 	bne	2b
-	get_thread_info r10
 	mov	r7, #1
 	strb	r7, [r10, #TI_USED_CP + 10]	@ mark CP#10 as used
 	strb	r7, [r10, #TI_USED_CP + 11]	@ mark CP#11 as used
@@ -586,7 +544,6 @@ call_fpe:
 	tst	r0, #0x08000000			@ only CDP/CPRT/LDC/STC have bit 27
 	tstne	r0, #0x04000000			@ bit 26 set on both ARM and Thumb-2
 	moveq	pc, lr
-	get_thread_info r10			@ get current thread
 	and	r8, r0, #0x00000f00		@ mask out CP number
  THUMB(	lsr	r8, r8, #8		)
 	mov	r7, #1
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index fefd7f971437..bc5bc0a97131 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -35,12 +35,11 @@ ret_fast_syscall:
 	ldr	r1, [tsk, #TI_FLAGS]
 	tst	r1, #_TIF_WORK_MASK
 	bne	fast_work_pending
-#if defined(CONFIG_IRQSOFF_TRACER)
 	asm_trace_hardirqs_on
-#endif
 
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
+	ct_user_enter
 
 	restore_user_regs fast = 1, offset = S_OFF
  UNWIND(.fnend		)
@@ -71,11 +70,11 @@ ENTRY(ret_to_user_from_irq)
 	tst	r1, #_TIF_WORK_MASK
 	bne	work_pending
 no_work_pending:
-#if defined(CONFIG_IRQSOFF_TRACER)
 	asm_trace_hardirqs_on
-#endif
+
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
+	ct_user_enter save = 0
 
 	restore_user_regs fast = 0, offset = 0
 ENDPROC(ret_to_user_from_irq)
@@ -406,6 +405,7 @@ ENTRY(vector_swi)
 	mcr	p15, 0, ip, c1, c0		@ update control register
 #endif
 	enable_irq
+	ct_user_exit
 
 	get_thread_info tsk
 	adr	tbl, sys_call_table		@ load syscall table pointer
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 9a8531eadd3d..160f3376ba6d 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -74,7 +74,24 @@
 	.endm
 
 #ifndef CONFIG_THUMB2_KERNEL
-	.macro	svc_exit, rpsr
+	.macro	svc_exit, rpsr, irq = 0
+	.if	\irq != 0
+	@ IRQs already off
+#ifdef CONFIG_TRACE_IRQFLAGS
+	@ The parent context IRQs must have been enabled to get here in
+	@ the first place, so there's no point checking the PSR I bit.
+	bl	trace_hardirqs_on
+#endif
+	.else
+	@ IRQs off again before pulling preserved data off the stack
+	disable_irq_notrace
+#ifdef CONFIG_TRACE_IRQFLAGS
+	tst	\rpsr, #PSR_I_BIT
+	bleq	trace_hardirqs_on
+	tst	\rpsr, #PSR_I_BIT
+	blne	trace_hardirqs_off
+#endif
+	.endif
 	msr	spsr_cxsf, \rpsr
 #if defined(CONFIG_CPU_V6)
 	ldr	r0, [sp]
@@ -120,7 +137,24 @@
 	mov	pc, \reg
 	.endm
 #else	/* CONFIG_THUMB2_KERNEL */
-	.macro	svc_exit, rpsr
+	.macro	svc_exit, rpsr, irq = 0
+	.if	\irq != 0
+	@ IRQs already off
+#ifdef CONFIG_TRACE_IRQFLAGS
+	@ The parent context IRQs must have been enabled to get here in
+	@ the first place, so there's no point checking the PSR I bit.
+	bl	trace_hardirqs_on
+#endif
+	.else
+	@ IRQs off again before pulling preserved data off the stack
+	disable_irq_notrace
+#ifdef CONFIG_TRACE_IRQFLAGS
+	tst	\rpsr, #PSR_I_BIT
+	bleq	trace_hardirqs_on
+	tst	\rpsr, #PSR_I_BIT
+	blne	trace_hardirqs_off
+#endif
+	.endif
 	ldr	lr, [sp, #S_SP]			@ top of the stack
 	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
 	clrex					@ clear the exclusive monitor
@@ -164,6 +198,34 @@
 #endif	/* !CONFIG_THUMB2_KERNEL */
 
 /*
+ * Context tracking subsystem.  Used to instrument transitions
+ * between user and kernel mode.
+ */
+	.macro ct_user_exit, save = 1
+#ifdef CONFIG_CONTEXT_TRACKING
+	.if	\save
+	stmdb   sp!, {r0-r3, ip, lr}
+	bl	user_exit
+	ldmia	sp!, {r0-r3, ip, lr}
+	.else
+	bl	user_exit
+	.endif
+#endif
+	.endm
+
+	.macro ct_user_enter, save = 1
+#ifdef CONFIG_CONTEXT_TRACKING
+	.if	\save
+	stmdb   sp!, {r0-r3, ip, lr}
+	bl	user_enter
+	ldmia	sp!, {r0-r3, ip, lr}
+	.else
+	bl	user_enter
+	.endif
+#endif
+	.endm
+
+/*
  * These are the registers used in the syscall handler, and allow us to
  * have in theory up to 7 arguments to a function - r0 to r6.
  *
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 854bd22380d3..5b391a689b47 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -98,8 +98,9 @@ __mmap_switched:
 	str	r9, [r4]			@ Save processor ID
 	str	r1, [r5]			@ Save machine type
 	str	r2, [r6]			@ Save atags pointer
-	bic	r4, r0, #CR_A			@ Clear 'A' bit
-	stmia	r7, {r0, r4}			@ Save control register values
+	cmp	r7, #0
+	bicne	r4, r0, #CR_A			@ Clear 'A' bit
+	stmneia	r7, {r0, r4}			@ Save control register values
 	b	start_kernel
 ENDPROC(__mmap_switched)
 
@@ -113,7 +114,11 @@ __mmap_switched_data:
 	.long	processor_id			@ r4
 	.long	__machine_arch_type		@ r5
 	.long	__atags_pointer			@ r6
+#ifdef CONFIG_CPU_CP15
 	.long	cr_alignment			@ r7
+#else
+	.long	0				@ r7
+#endif
 	.long	init_thread_union + THREAD_START_SP @ sp
 	.size	__mmap_switched_data, . - __mmap_switched_data
 
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 2c228a07e58c..6a2e09c952c7 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -32,15 +32,21 @@
  * numbers for r1.
  *
  */
-	.arm
 
 	__HEAD
+
+#ifdef CONFIG_CPU_THUMBONLY
+	.thumb
+ENTRY(stext)
+#else
+	.arm
 ENTRY(stext)
 
  THUMB(	adr	r9, BSYM(1f)	)	@ Kernel is always entered in ARM.
  THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
  THUMB(	.thumb			)	@ switch to Thumb now.
  THUMB(1:			)
+#endif
 
 	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
 						@ and irqs disabled
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index ae58d3b37d9d..f21970316836 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -407,15 +407,16 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
  * atomic helpers and the signal restart code. Insert it into the
  * gate_vma so that it is visible through ptrace and /proc/<pid>/mem.
  */
-static struct vm_area_struct gate_vma;
+static struct vm_area_struct gate_vma = {
+	.vm_start	= 0xffff0000,
+	.vm_end		= 0xffff0000 + PAGE_SIZE,
+	.vm_flags	= VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYEXEC,
+	.vm_mm		= &init_mm,
+};
 
 static int __init gate_vma_init(void)
 {
-	gate_vma.vm_start	= 0xffff0000;
-	gate_vma.vm_end		= 0xffff0000 + PAGE_SIZE;
-	gate_vma.vm_page_prot	= PAGE_READONLY_EXEC;
-	gate_vma.vm_flags	= VM_READ | VM_EXEC |
-				  VM_MAYREAD | VM_MAYEXEC;
+	gate_vma.vm_page_prot = PAGE_READONLY_EXEC;
 	return 0;
 }
 arch_initcall(gate_vma_init);
diff --git a/arch/arm/kernel/return_address.c b/arch/arm/kernel/return_address.c
index 8085417555dd..fafedd86885d 100644
--- a/arch/arm/kernel/return_address.c
+++ b/arch/arm/kernel/return_address.c
@@ -26,7 +26,7 @@ static int save_return_addr(struct stackframe *frame, void *d)
 	struct return_address_data *data = d;
 
 	if (!data->level) {
-		data->addr = (void *)frame->lr;
+		data->addr = (void *)frame->pc;
 
 		return 1;
 	} else {
@@ -41,7 +41,8 @@ void *return_address(unsigned int level)
 	struct stackframe frame;
 	register unsigned long current_sp asm ("sp");
 
-	data.level = level + 1;
+	data.level = level + 2;
+	data.addr = NULL;
 
 	frame.fp = (unsigned long)__builtin_frame_address(0);
 	frame.sp = current_sp;
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index 59d2adb764a9..e8edcaa0e432 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -20,6 +20,7 @@ struct clock_data {
 	u64 epoch_ns;
 	u32 epoch_cyc;
 	u32 epoch_cyc_copy;
+	unsigned long rate;
 	u32 mult;
 	u32 shift;
 	bool suspended;
@@ -113,11 +114,14 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
 	u64 res, wrap;
 	char r_unit;
 
+	if (cd.rate > rate)
+		return;
+
 	BUG_ON(bits > 32);
 	WARN_ON(!irqs_disabled());
-	WARN_ON(read_sched_clock != jiffy_sched_clock_read);
 	read_sched_clock = read;
 	sched_clock_mask = (1 << bits) - 1;
+	cd.rate = rate;
 
 	/* calculate the mult/shift to convert counter ticks to ns. */
 	clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 0);
@@ -161,12 +165,19 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
 	pr_debug("Registered %pF as sched_clock source\n", read);
 }
 
-unsigned long long notrace sched_clock(void)
+static unsigned long long notrace sched_clock_32(void)
 {
 	u32 cyc = read_sched_clock();
 	return cyc_to_sched_clock(cyc, sched_clock_mask);
 }
 
+unsigned long long __read_mostly (*sched_clock_func)(void) = sched_clock_32;
+
+unsigned long long notrace sched_clock(void)
+{
+	return sched_clock_func();
+}
+
 void __init sched_clock_postinit(void)
 {
 	/*
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 234e339196c0..1522c7ae31b0 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -18,6 +18,7 @@
 #include <linux/bootmem.h>
 #include <linux/seq_file.h>
 #include <linux/screen_info.h>
+#include <linux/of_platform.h>
 #include <linux/init.h>
 #include <linux/kexec.h>
 #include <linux/of_fdt.h>
@@ -290,10 +291,10 @@ static int cpu_has_aliasing_icache(unsigned int arch)
 
 static void __init cacheid_init(void)
 {
-	unsigned int cachetype = read_cpuid_cachetype();
 	unsigned int arch = cpu_architecture();
 
 	if (arch >= CPU_ARCH_ARMv6) {
+		unsigned int cachetype = read_cpuid_cachetype();
 		if ((cachetype & (7 << 29)) == 4 << 29) {
 			/* ARMv7 register format */
 			arch = CPU_ARCH_ARMv7;
@@ -389,7 +390,7 @@ static void __init feat_v6_fixup(void)
  *
  * cpu_init sets up the per-CPU stacks.
  */
-void cpu_init(void)
+void notrace cpu_init(void)
 {
 	unsigned int cpu = smp_processor_id();
 	struct stack *stk = &stacks[cpu];
@@ -659,9 +660,19 @@ struct screen_info screen_info = {
 
 static int __init customize_machine(void)
 {
-	/* customizes platform devices, or adds new ones */
+	/*
+	 * customizes platform devices, or adds new ones
+	 * On DT based machines, we fall back to populating the
+	 * machine from the device tree, if no callback is provided,
+	 * otherwise we would always need an init_machine callback.
+	 */
 	if (machine_desc->init_machine)
 		machine_desc->init_machine();
+#ifdef CONFIG_OF
+	else
+		of_platform_populate(NULL, of_default_bus_match_table,
+					NULL, NULL);
+#endif
 	return 0;
 }
 arch_initcall(customize_machine);
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 4619177bcfe6..47ab90563bf4 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -211,6 +211,13 @@ void __cpuinit __cpu_die(unsigned int cpu)
 	}
 	printk(KERN_NOTICE "CPU%u: shutdown\n", cpu);
 
+	/*
+	 * platform_cpu_kill() is generally expected to do the powering off
+	 * and/or cutting of clocks to the dying CPU.  Optionally, this may
+	 * be done by the CPU which is dying in preference to supporting
+	 * this call, but that means there is _no_ synchronisation between
+	 * the requesting CPU and the dying CPU actually losing power.
+	 */
 	if (!platform_cpu_kill(cpu))
 		printk("CPU%u: unable to kill\n", cpu);
 }
@@ -230,14 +237,41 @@ void __ref cpu_die(void)
 	idle_task_exit();
 
 	local_irq_disable();
-	mb();
 
-	/* Tell __cpu_die() that this CPU is now safe to dispose of */
+	/*
+	 * Flush the data out of the L1 cache for this CPU.  This must be
+	 * before the completion to ensure that data is safely written out
+	 * before platform_cpu_kill() gets called - which may disable
+	 * *this* CPU and power down its cache.
+	 */
+	flush_cache_louis();
+
+	/*
+	 * Tell __cpu_die() that this CPU is now safe to dispose of.  Once
+	 * this returns, power and/or clocks can be removed at any point
+	 * from this CPU and its cache by platform_cpu_kill().
+	 */
 	RCU_NONIDLE(complete(&cpu_died));
 
 	/*
-	 * actual CPU shutdown procedure is at least platform (if not
-	 * CPU) specific.
+	 * Ensure that the cache lines associated with that completion are
+	 * written out.  This covers the case where _this_ CPU is doing the
+	 * powering down, to ensure that the completion is visible to the
+	 * CPU waiting for this one.
+	 */
+	flush_cache_louis();
+
+	/*
+	 * The actual CPU shutdown procedure is at least platform (if not
+	 * CPU) specific.  This may remove power, or it may simply spin.
+	 *
+	 * Platforms are generally expected *NOT* to return from this call,
+	 * although there are some which do because they have no way to
+	 * power down the CPU.  These platforms are the _only_ reason we
+	 * have a return path which uses the fragment of assembly below.
+	 *
+	 * The return path should not be used for platforms which can
+	 * power off the CPU.
 	 */
 	if (smp_ops.cpu_die)
 		smp_ops.cpu_die(cpu);
diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c
index 45eac87ed66a..5bc1a63284e3 100644
--- a/arch/arm/kernel/smp_scu.c
+++ b/arch/arm/kernel/smp_scu.c
@@ -41,7 +41,7 @@ void scu_enable(void __iomem *scu_base)
 
 #ifdef CONFIG_ARM_ERRATA_764369
 	/* Cortex-A9 only */
-	if ((read_cpuid(CPUID_ID) & 0xff0ffff0) == 0x410fc090) {
+	if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc090) {
 		scu_ctrl = __raw_readl(scu_base + 0x30);
 		if (!(scu_ctrl & 1))
 			__raw_writel(scu_ctrl | 0x1, scu_base + 0x30);
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index e82e1d248772..9a52a07aa40e 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -98,21 +98,21 @@ static void broadcast_tlb_a15_erratum(void)
 		return;
 
 	dummy_flush_tlb_a15_erratum();
-	smp_call_function_many(cpu_online_mask, ipi_flush_tlb_a15_erratum,
-			       NULL, 1);
+	smp_call_function(ipi_flush_tlb_a15_erratum, NULL, 1);
 }
 
 static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm)
 {
-	int cpu;
+	int cpu, this_cpu;
 	cpumask_t mask = { CPU_BITS_NONE };
 
 	if (!erratum_a15_798181())
 		return;
 
 	dummy_flush_tlb_a15_erratum();
+	this_cpu = get_cpu();
 	for_each_online_cpu(cpu) {
-		if (cpu == smp_processor_id())
+		if (cpu == this_cpu)
 			continue;
 		/*
 		 * We only need to send an IPI if the other CPUs are running
@@ -127,6 +127,7 @@ static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm)
 			cpumask_set_cpu(cpu, &mask);
 	}
 	smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1);
+	put_cpu();
 }
 
 void flush_tlb_all(void)
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index 087fc321e9e5..b1b89882b113 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/arch/arm/kernel/swp_emulate.c
@@ -99,7 +99,7 @@ static const struct file_operations proc_status_fops = {
 	.open		= proc_status_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release,
+	.release	= single_release,
 };
 #endif
 
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index 955d92d265e5..abff4e9aaee0 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -22,6 +22,7 @@
 #include <linux/errno.h>
 #include <linux/profile.h>
 #include <linux/timer.h>
+#include <linux/clocksource.h>
 #include <linux/irq.h>
 
 #include <asm/thread_info.h>
@@ -115,6 +116,10 @@ int __init register_persistent_clock(clock_access_fn read_boot,
 
 void __init time_init(void)
 {
-	machine_desc->init_time();
+	if (machine_desc->init_time)
+		machine_desc->init_time();
+	else
+		clocksource_of_init();
+
 	sched_clock_postinit();
 }
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index b571484e9f03..a871b8e00fca 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -20,7 +20,7 @@
 	VMLINUX_SYMBOL(__idmap_text_start) = .;				\
 	*(.idmap.text)							\
 	VMLINUX_SYMBOL(__idmap_text_end) = .;				\
-	ALIGN_FUNCTION();						\
+	. = ALIGN(32);							\
 	VMLINUX_SYMBOL(__hyp_idmap_text_start) = .;			\
 	*(.hyp.idmap.text)						\
 	VMLINUX_SYMBOL(__hyp_idmap_text_end) = .;
@@ -315,3 +315,8 @@ SECTIONS
  */
 ASSERT((__proc_info_end - __proc_info_begin), "missing CPU support")
 ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined")
+/*
+ * The HYP init code can't be more than a page long.
+ * The above comment applies as well.
+ */
+ASSERT(((__hyp_idmap_text_end - __hyp_idmap_text_start) <= PAGE_SIZE), "HYP init code too big")