23 files changed, 512 insertions, 141 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 040619c32d68..38ddd9f83d0e 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -39,6 +39,7 @@ obj-$(CONFIG_ARTHUR)		+= arthur.o
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
 obj-$(CONFIG_PCI)		+= bios32.o isa.o
 obj-$(CONFIG_ARM_CPU_SUSPEND)	+= sleep.o suspend.o
+obj-$(CONFIG_HIBERNATION)	+= hibernate.o
 obj-$(CONFIG_SMP)		+= smp.o
 ifdef CONFIG_MMU
 obj-$(CONFIG_SMP)		+= smp_tlb.o
diff --git a/arch/arm/kernel/atags_parse.c b/arch/arm/kernel/atags_parse.c
index 8c14de8180c0..7807ef58a2ab 100644
--- a/arch/arm/kernel/atags_parse.c
+++ b/arch/arm/kernel/atags_parse.c
@@ -22,6 +22,7 @@
 #include <linux/fs.h>
 #include <linux/root_dev.h>
 #include <linux/screen_info.h>
+#include <linux/memblock.h>
 
 #include <asm/setup.h>
 #include <asm/system_info.h>
@@ -222,10 +223,10 @@ setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr)
 	}
 
 	if (mdesc->fixup)
-		mdesc->fixup(tags, &from, &meminfo);
+		mdesc->fixup(tags, &from);
 
 	if (tags->hdr.tag == ATAG_CORE) {
-		if (meminfo.nr_banks != 0)
+		if (memblock_phys_mem_size())
 			squash_mem_tags(tags);
 		save_atags(tags);
 		parse_tags(tags);
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index 16d43cd45619..17a26c17f7f5 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -545,6 +545,18 @@ void pci_common_init_dev(struct device *parent, struct hw_pci *hw)
 		 */
 		pci_bus_add_devices(bus);
 	}
+
+	list_for_each_entry(sys, &head, node) {
+		struct pci_bus *bus = sys->bus;
+
+		/* Configure PCI Express settings */
+		if (bus && !pci_has_flag(PCI_PROBE_ONLY)) {
+			struct pci_bus *child;
+
+			list_for_each_entry(child, &bus->children, node)
+				pcie_bus_configure_settings(child);
+		}
+	}
 }
 
 #ifndef CONFIG_PCI_HOST_ITE8152
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index c7419a585ddc..e94a157ddff1 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -27,56 +27,23 @@
 #include <asm/mach/arch.h>
 #include <asm/mach-types.h>
 
-void __init early_init_dt_add_memory_arch(u64 base, u64 size)
-{
-	arm_add_memory(base, size);
-}
-
-void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
-{
-	return memblock_virt_alloc(size, align);
-}
-
-void __init arm_dt_memblock_reserve(void)
-{
-	u64 *reserve_map, base, size;
-
-	if (!initial_boot_params)
-		return;
 
-	/* Reserve the dtb region */
-	memblock_reserve(virt_to_phys(initial_boot_params),
-			 be32_to_cpu(initial_boot_params->totalsize));
+#ifdef CONFIG_SMP
+extern struct of_cpu_method __cpu_method_of_table[];
 
-	/*
-	 * Process the reserve map.  This will probably overlap the initrd
-	 * and dtb locations which are already reserved, but overlaping
-	 * doesn't hurt anything
-	 */
-	reserve_map = ((void*)initial_boot_params) +
-			be32_to_cpu(initial_boot_params->off_mem_rsvmap);
-	while (1) {
-		base = be64_to_cpup(reserve_map++);
-		size = be64_to_cpup(reserve_map++);
-		if (!size)
-			break;
-		memblock_reserve(base, size);
-	}
-}
+static const struct of_cpu_method __cpu_method_of_table_sentinel
+	__used __section(__cpu_method_of_table_end);
 
-#ifdef CONFIG_SMP
-extern struct of_cpu_method __cpu_method_of_table_begin[];
-extern struct of_cpu_method __cpu_method_of_table_end[];
 
 static int __init set_smp_ops_by_method(struct device_node *node)
 {
 	const char *method;
-	struct of_cpu_method *m = __cpu_method_of_table_begin;
+	struct of_cpu_method *m = __cpu_method_of_table;
 
 	if (of_property_read_string(node, "enable-method", &method))
 		return 0;
 
-	for (; m < __cpu_method_of_table_end; m++)
+	for (; m->method; m++)
 		if (!strcmp(m->method, method)) {
 			smp_set_ops(m->ops);
 			return 1;
@@ -252,7 +219,7 @@ const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
 
 	if (!mdesc) {
 		const char *prop;
-		long size;
+		int size;
 		unsigned long dt_root;
 
 		early_print("\nError: unrecognized/unsupported "
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 1879e8dd2acc..52a949a8077d 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -344,7 +344,7 @@ ENDPROC(__pabt_svc)
 	@
 	@ Enable the alignment trap while in kernel mode
 	@
-	alignment_trap r0
+	alignment_trap r0, .LCcralign
 
 	@
 	@ Clear FP to mark the first stack frame
@@ -413,6 +413,11 @@ __und_usr:
 	@
 	adr	r9, BSYM(ret_from_exception)
 
+	@ IRQs must be enabled before attempting to read the instruction from
+	@ user space since that could cause a page/translation fault if the
+	@ page table was modified by another CPU.
+	enable_irq
+
 	tst	r3, #PSR_T_BIT			@ Thumb mode?
 	bne	__und_usr_thumb
 	sub	r4, r2, #4			@ ARM instr at LR - 4
@@ -484,7 +489,8 @@ ENDPROC(__und_usr)
  */
 	.pushsection .fixup, "ax"
 	.align	2
-4:	mov	pc, r9
+4:	str     r4, [sp, #S_PC]			@ retry current instruction
+	mov	pc, r9
 	.popsection
 	.pushsection __ex_table,"a"
 	.long	1b, 4b
@@ -517,7 +523,7 @@ ENDPROC(__und_usr)
  *  r9  = normal "successful" return address
  *  r10 = this threads thread_info structure
  *  lr  = unrecognised instruction return address
- * IRQs disabled, FIQs enabled.
+ * IRQs enabled, FIQs enabled.
  */
 	@
 	@ Fall-through from Thumb-2 __und_usr
@@ -624,7 +630,6 @@ call_fpe:
 #endif
 
 do_fpe:
-	enable_irq
 	ldr	r4, .LCfp
 	add	r10, r10, #TI_FPSTATE		@ r10 = workspace
 	ldr	pc, [r4]			@ Call FP module USR entry point
@@ -652,8 +657,7 @@ __und_usr_fault_32:
 	b	1f
 __und_usr_fault_16:
 	mov	r1, #2
-1:	enable_irq
-	mov	r0, sp
+1:	mov	r0, sp
 	adr	lr, BSYM(ret_from_exception)
 	b	__und_fault
 ENDPROC(__und_usr_fault_32)
@@ -1143,11 +1147,8 @@ __vectors_start:
 	.data
 
 	.globl	cr_alignment
-	.globl	cr_no_alignment
 cr_alignment:
 	.space	4
-cr_no_alignment:
-	.space	4
 
 #ifdef CONFIG_MULTI_IRQ_HANDLER
 	.globl	handle_arch_irq
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index a2dcafdf1bc8..7139d4a7dea7 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -365,13 +365,7 @@ ENTRY(vector_swi)
 	str	r0, [sp, #S_OLD_R0]		@ Save OLD_R0
 #endif
 	zero_fp
-
-#ifdef CONFIG_ALIGNMENT_TRAP
-	ldr	ip, __cr_alignment
-	ldr	ip, [ip]
-	mcr	p15, 0, ip, c1, c0		@ update control register
-#endif
-
+	alignment_trap ip, __cr_alignment
 	enable_irq
 	ct_user_exit
 	get_thread_info tsk
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index efb208de75ec..5d702f8900b1 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -37,9 +37,9 @@
 #endif
 	.endm
 
-	.macro	alignment_trap, rtemp
+	.macro	alignment_trap, rtemp, label
 #ifdef CONFIG_ALIGNMENT_TRAP
-	ldr	\rtemp, .LCcralign
+	ldr	\rtemp, \label
 	ldr	\rtemp, [\rtemp]
 	mcr	p15, 0, \rtemp, c1, c0
 #endif
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index c108ddcb9ba4..af9a8a927a4e 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -14,6 +14,7 @@
 
 #include <linux/ftrace.h>
 #include <linux/uaccess.h>
+#include <linux/module.h>
 
 #include <asm/cacheflush.h>
 #include <asm/opcodes.h>
@@ -63,6 +64,18 @@ static unsigned long adjust_address(struct dyn_ftrace *rec, unsigned long addr)
 }
 #endif
 
+int ftrace_arch_code_modify_prepare(void)
+{
+	set_all_modules_text_rw();
+	return 0;
+}
+
+int ftrace_arch_code_modify_post_process(void)
+{
+	set_all_modules_text_ro();
+	return 0;
+}
+
 static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
 {
 	return arm_gen_branch_link(pc, addr);
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index c96ecacb2021..572a38335c96 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -99,8 +99,7 @@ __mmap_switched:
 	str	r1, [r5]			@ Save machine type
 	str	r2, [r6]			@ Save atags pointer
 	cmp	r7, #0
-	bicne	r4, r0, #CR_A			@ Clear 'A' bit
-	stmneia	r7, {r0, r4}			@ Save control register values
+	strne	r0, [r7]			@ Save control register values
 	b	start_kernel
 ENDPROC(__mmap_switched)
 
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 591d6e4a6492..2c35f0ff2fdc 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -475,7 +475,7 @@ ENDPROC(__turn_mmu_on)
 
 
 #ifdef CONFIG_SMP_ON_UP
-	__INIT
+	__HEAD
 __fixup_smp:
 	and	r3, r9, #0x000f0000	@ architecture version
 	teq	r3, #0x000f0000		@ CPU ID supported?
diff --git a/arch/arm/kernel/hibernate.c b/arch/arm/kernel/hibernate.c
new file mode 100644
index 000000000000..bb8b79648643
--- /dev/null
+++ b/arch/arm/kernel/hibernate.c
@@ -0,0 +1,107 @@
+/*
+ * Hibernation support specific for ARM
+ *
+ * Derived from work on ARM hibernation support by:
+ *
+ * Ubuntu project, hibernation support for mach-dove
+ * Copyright (C) 2010 Nokia Corporation (Hiroshi Doyu)
+ * Copyright (C) 2010 Texas Instruments, Inc. (Teerth Reddy et al.)
+ *  https://lkml.org/lkml/2010/6/18/4
+ *  https://lists.linux-foundation.org/pipermail/linux-pm/2010-June/027422.html
+ *  https://patchwork.kernel.org/patch/96442/
+ *
+ * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
+ *
+ * License terms: GNU General Public License (GPL) version 2
+ */
+
+#include <linux/mm.h>
+#include <linux/suspend.h>
+#include <asm/system_misc.h>
+#include <asm/idmap.h>
+#include <asm/suspend.h>
+#include <asm/memory.h>
+
+extern const void __nosave_begin, __nosave_end;
+
+int pfn_is_nosave(unsigned long pfn)
+{
+	unsigned long nosave_begin_pfn = virt_to_pfn(&__nosave_begin);
+	unsigned long nosave_end_pfn = virt_to_pfn(&__nosave_end - 1);
+
+	return (pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn);
+}
+
+void notrace save_processor_state(void)
+{
+	WARN_ON(num_online_cpus() != 1);
+	local_fiq_disable();
+}
+
+void notrace restore_processor_state(void)
+{
+	local_fiq_enable();
+}
+
+/*
+ * Snapshot kernel memory and reset the system.
+ *
+ * swsusp_save() is executed in the suspend finisher so that the CPU
+ * context pointer and memory are part of the saved image, which is
+ * required by the resume kernel image to restart execution from
+ * swsusp_arch_suspend().
+ *
+ * soft_restart is not technically needed, but is used to get success
+ * returned from cpu_suspend.
+ *
+ * When soft reboot completes, the hibernation snapshot is written out.
+ */
+static int notrace arch_save_image(unsigned long unused)
+{
+	int ret;
+
+	ret = swsusp_save();
+	if (ret == 0)
+		soft_restart(virt_to_phys(cpu_resume));
+	return ret;
+}
+
+/*
+ * Save the current CPU state before suspend / poweroff.
+ */
+int notrace swsusp_arch_suspend(void)
+{
+	return cpu_suspend(0, arch_save_image);
+}
+
+/*
+ * Restore page contents for physical pages that were in use during loading
+ * hibernation image.  Switch to idmap_pgd so the physical page tables
+ * are overwritten with the same contents.
+ */
+static void notrace arch_restore_image(void *unused)
+{
+	struct pbe *pbe;
+
+	cpu_switch_mm(idmap_pgd, &init_mm);
+	for (pbe = restore_pblist; pbe; pbe = pbe->next)
+		copy_page(pbe->orig_address, pbe->address);
+
+	soft_restart(virt_to_phys(cpu_resume));
+}
+
+static u64 resume_stack[PAGE_SIZE/2/sizeof(u64)] __nosavedata;
+
+/*
+ * Resume from the hibernation image.
+ * Due to the kernel heap / data restore, stack contents change underneath
+ * and that would make function calls impossible; switch to a temporary
+ * stack within the nosave region to avoid that problem.
+ */
+int swsusp_arch_resume(void)
+{
+	extern void call_with_stack(void (*fn)(void *), void *arg, void *sp);
+	call_with_stack(arch_restore_image, 0,
+		resume_stack + ARRAY_SIZE(resume_stack));
+	return 0;
+}
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 9723d17b8f38..2c4257604513 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -37,6 +37,7 @@
 #include <linux/proc_fs.h>
 #include <linux/export.h>
 
+#include <asm/hardware/cache-l2x0.h>
 #include <asm/exception.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
@@ -115,10 +116,21 @@ EXPORT_SYMBOL_GPL(set_irq_flags);
 
 void __init init_IRQ(void)
 {
+	int ret;
+
 	if (IS_ENABLED(CONFIG_OF) && !machine_desc->init_irq)
 		irqchip_init();
 	else
 		machine_desc->init_irq();
+
+	if (IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_CACHE_L2X0) &&
+	    (machine_desc->l2c_aux_mask || machine_desc->l2c_aux_val)) {
+		outer_cache.write_sec = machine_desc->l2c_write_sec;
+		ret = l2x0_of_init(machine_desc->l2c_aux_val,
+				   machine_desc->l2c_aux_mask);
+		if (ret)
+			pr_err("L2C: failed to init: %d\n", ret);
+	}
 }
 
 #ifdef CONFIG_MULTI_IRQ_HANDLER
diff --git a/arch/arm/kernel/isa.c b/arch/arm/kernel/isa.c
index 346485910732..9d1cf7156895 100644
--- a/arch/arm/kernel/isa.c
+++ b/arch/arm/kernel/isa.c
@@ -20,7 +20,7 @@
 
 static unsigned int isa_membase, isa_portbase, isa_portshift;
 
-static ctl_table ctl_isa_vars[4] = {
+static struct ctl_table ctl_isa_vars[4] = {
 	{
 		.procname	= "membase",
 		.data		= &isa_membase, 
@@ -44,7 +44,7 @@ static ctl_table ctl_isa_vars[4] = {
 
 static struct ctl_table_header *isa_sysctl_header;
 
-static ctl_table ctl_isa[2] = {
+static struct ctl_table ctl_isa[2] = {
 	{
 		.procname	= "isa",
 		.mode		= 0555,
@@ -52,7 +52,7 @@ static ctl_table ctl_isa[2] = {
 	}, {}
 };
 
-static ctl_table ctl_bus[2] = {
+static struct ctl_table ctl_bus[2] = {
 	{
 		.procname	= "bus",
 		.mode		= 0555,
diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S
index 2452dd1bef53..a5599cfc43cb 100644
--- a/arch/arm/kernel/iwmmxt.S
+++ b/arch/arm/kernel/iwmmxt.S
@@ -18,6 +18,7 @@
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
+#include <asm/assembler.h>
 
 #if defined(CONFIG_CPU_PJ4) || defined(CONFIG_CPU_PJ4B)
 #define PJ4(code...)		code
@@ -65,17 +66,18 @@
  * r9  = ret_from_exception
  * lr  = undefined instr exit
  *
- * called from prefetch exception handler with interrupts disabled
+ * called from prefetch exception handler with interrupts enabled
  */
 
 ENTRY(iwmmxt_task_enable)
+	inc_preempt_count r10, r3
 
 	XSC(mrc	p15, 0, r2, c15, c1, 0)
 	PJ4(mrc p15, 0, r2, c1, c0, 2)
 	@ CP0 and CP1 accessible?
 	XSC(tst	r2, #0x3)
 	PJ4(tst	r2, #0xf)
-	movne	pc, lr				@ if so no business here
+	bne	4f				@ if so no business here
 	@ enable access to CP0 and CP1
 	XSC(orr	r2, r2, #0x3)
 	XSC(mcr	p15, 0, r2, c15, c1, 0)
@@ -136,7 +138,7 @@ concan_dump:
 	wstrd	wR15, [r1, #MMX_WR15]
 
 2:	teq	r0, #0				@ anything to load?
-	moveq	pc, lr
+	beq	3f
 
 concan_load:
 
@@ -169,8 +171,14 @@ concan_load:
 	@ clear CUP/MUP (only if r1 != 0)
 	teq	r1, #0
 	mov 	r2, #0
-	moveq	pc, lr
+	beq	3f
 	tmcr	wCon, r2
+
+3:
+#ifdef CONFIG_PREEMPT_COUNT
+	get_thread_info r10
+#endif
+4:	dec_preempt_count r10, r3
 	mov	pc, lr
 
 /*
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 51798d7854ac..a71ae1523620 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -221,6 +221,7 @@ static struct notifier_block cpu_pmu_hotplug_notifier = {
  * PMU platform driver and devicetree bindings.
  */
 static struct of_device_id cpu_pmu_of_device_ids[] = {
+	{.compatible = "arm,cortex-a17-pmu",	.data = armv7_a17_pmu_init},
 	{.compatible = "arm,cortex-a15-pmu",	.data = armv7_a15_pmu_init},
 	{.compatible = "arm,cortex-a12-pmu",	.data = armv7_a12_pmu_init},
 	{.compatible = "arm,cortex-a9-pmu",	.data = armv7_a9_pmu_init},
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index f4ef3981ed02..2037f7205987 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -1599,6 +1599,13 @@ static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
 	return 0;
 }
 
+static int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv7_a12_pmu_init(cpu_pmu);
+	cpu_pmu->name = "ARMv7 Cortex-A17";
+	return 0;
+}
+
 /*
  * Krait Performance Monitor Region Event Selection Register (PMRESRn)
  *
@@ -2021,6 +2028,11 @@ static inline int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
 	return -ENODEV;
 }
 
+static inline int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return -ENODEV;
+}
+
 static inline int krait_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	return -ENODEV;
diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c
index 46931880093d..f73891b6b730 100644
--- a/arch/arm/kernel/psci.c
+++ b/arch/arm/kernel/psci.c
@@ -17,63 +17,58 @@
 
 #include <linux/init.h>
 #include <linux/of.h>
+#include <linux/reboot.h>
+#include <linux/pm.h>
+#include <uapi/linux/psci.h>
 
 #include <asm/compiler.h>
 #include <asm/errno.h>
 #include <asm/opcodes-sec.h>
 #include <asm/opcodes-virt.h>
 #include <asm/psci.h>
+#include <asm/system_misc.h>
 
 struct psci_operations psci_ops;
 
 static int (*invoke_psci_fn)(u32, u32, u32, u32);
+typedef int (*psci_initcall_t)(const struct device_node *);
 
 enum psci_function {
 	PSCI_FN_CPU_SUSPEND,
 	PSCI_FN_CPU_ON,
 	PSCI_FN_CPU_OFF,
 	PSCI_FN_MIGRATE,
+	PSCI_FN_AFFINITY_INFO,
+	PSCI_FN_MIGRATE_INFO_TYPE,
 	PSCI_FN_MAX,
 };
 
 static u32 psci_function_id[PSCI_FN_MAX];
 
-#define PSCI_RET_SUCCESS		0
-#define PSCI_RET_EOPNOTSUPP		-1
-#define PSCI_RET_EINVAL			-2
-#define PSCI_RET_EPERM			-3
-
 static int psci_to_linux_errno(int errno)
 {
 	switch (errno) {
 	case PSCI_RET_SUCCESS:
 		return 0;
-	case PSCI_RET_EOPNOTSUPP:
+	case PSCI_RET_NOT_SUPPORTED:
 		return -EOPNOTSUPP;
-	case PSCI_RET_EINVAL:
+	case PSCI_RET_INVALID_PARAMS:
 		return -EINVAL;
-	case PSCI_RET_EPERM:
+	case PSCI_RET_DENIED:
 		return -EPERM;
 	};
 
 	return -EINVAL;
 }
 
-#define PSCI_POWER_STATE_ID_MASK	0xffff
-#define PSCI_POWER_STATE_ID_SHIFT	0
-#define PSCI_POWER_STATE_TYPE_MASK	0x1
-#define PSCI_POWER_STATE_TYPE_SHIFT	16
-#define PSCI_POWER_STATE_AFFL_MASK	0x3
-#define PSCI_POWER_STATE_AFFL_SHIFT	24
-
 static u32 psci_power_state_pack(struct psci_power_state state)
 {
-	return	((state.id & PSCI_POWER_STATE_ID_MASK)
-			<< PSCI_POWER_STATE_ID_SHIFT)	|
-		((state.type & PSCI_POWER_STATE_TYPE_MASK)
-			<< PSCI_POWER_STATE_TYPE_SHIFT)	|
-		((state.affinity_level & PSCI_POWER_STATE_AFFL_MASK)
-			<< PSCI_POWER_STATE_AFFL_SHIFT);
+	return ((state.id << PSCI_0_2_POWER_STATE_ID_SHIFT)
+			& PSCI_0_2_POWER_STATE_ID_MASK) |
+		((state.type << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
+		 & PSCI_0_2_POWER_STATE_TYPE_MASK) |
+		((state.affinity_level << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
+		 & PSCI_0_2_POWER_STATE_AFFL_MASK);
 }
 
 /*
@@ -110,6 +105,14 @@ static noinline int __invoke_psci_fn_smc(u32 function_id, u32 arg0, u32 arg1,
 	return function_id;
 }
 
+static int psci_get_version(void)
+{
+	int err;
+
+	err = invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
+	return err;
+}
+
 static int psci_cpu_suspend(struct psci_power_state state,
 			    unsigned long entry_point)
 {
@@ -153,26 +156,36 @@ static int psci_migrate(unsigned long cpuid)
 	return psci_to_linux_errno(err);
 }
 
-static const struct of_device_id psci_of_match[] __initconst = {
-	{ .compatible = "arm,psci",	},
-	{},
-};
+static int psci_affinity_info(unsigned long target_affinity,
+		unsigned long lowest_affinity_level)
+{
+	int err;
+	u32 fn;
+
+	fn = psci_function_id[PSCI_FN_AFFINITY_INFO];
+	err = invoke_psci_fn(fn, target_affinity, lowest_affinity_level, 0);
+	return err;
+}
 
-void __init psci_init(void)
+static int psci_migrate_info_type(void)
 {
-	struct device_node *np;
-	const char *method;
-	u32 id;
+	int err;
+	u32 fn;
 
-	np = of_find_matching_node(NULL, psci_of_match);
-	if (!np)
-		return;
+	fn = psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE];
+	err = invoke_psci_fn(fn, 0, 0, 0);
+	return err;
+}
+
+static int get_set_conduit_method(struct device_node *np)
+{
+	const char *method;
 
-	pr_info("probing function IDs from device-tree\n");
+	pr_info("probing for conduit method from DT.\n");
 
 	if (of_property_read_string(np, "method", &method)) {
-		pr_warning("missing \"method\" property\n");
-		goto out_put_node;
+		pr_warn("missing \"method\" property\n");
+		return -ENXIO;
 	}
 
 	if (!strcmp("hvc", method)) {
@@ -180,10 +193,99 @@ void __init psci_init(void)
 	} else if (!strcmp("smc", method)) {
 		invoke_psci_fn = __invoke_psci_fn_smc;
 	} else {
-		pr_warning("invalid \"method\" property: %s\n", method);
+		pr_warn("invalid \"method\" property: %s\n", method);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd)
+{
+	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0);
+}
+
+static void psci_sys_poweroff(void)
+{
+	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0);
+}
+
+/*
+ * PSCI Function IDs for v0.2+ are well defined so use
+ * standard values.
+ */
+static int psci_0_2_init(struct device_node *np)
+{
+	int err, ver;
+
+	err = get_set_conduit_method(np);
+
+	if (err)
+		goto out_put_node;
+
+	ver = psci_get_version();
+
+	if (ver == PSCI_RET_NOT_SUPPORTED) {
+		/* PSCI v0.2 mandates implementation of PSCI_ID_VERSION. */
+		pr_err("PSCI firmware does not comply with the v0.2 spec.\n");
+		err = -EOPNOTSUPP;
 		goto out_put_node;
+	} else {
+		pr_info("PSCIv%d.%d detected in firmware.\n",
+				PSCI_VERSION_MAJOR(ver),
+				PSCI_VERSION_MINOR(ver));
+
+		if (PSCI_VERSION_MAJOR(ver) == 0 &&
+				PSCI_VERSION_MINOR(ver) < 2) {
+			err = -EINVAL;
+			pr_err("Conflicting PSCI version detected.\n");
+			goto out_put_node;
+		}
 	}
 
+	pr_info("Using standard PSCI v0.2 function IDs\n");
+	psci_function_id[PSCI_FN_CPU_SUSPEND] = PSCI_0_2_FN_CPU_SUSPEND;
+	psci_ops.cpu_suspend = psci_cpu_suspend;
+
+	psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF;
+	psci_ops.cpu_off = psci_cpu_off;
+
+	psci_function_id[PSCI_FN_CPU_ON] = PSCI_0_2_FN_CPU_ON;
+	psci_ops.cpu_on = psci_cpu_on;
+
+	psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN_MIGRATE;
+	psci_ops.migrate = psci_migrate;
+
+	psci_function_id[PSCI_FN_AFFINITY_INFO] = PSCI_0_2_FN_AFFINITY_INFO;
+	psci_ops.affinity_info = psci_affinity_info;
+
+	psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE] =
+		PSCI_0_2_FN_MIGRATE_INFO_TYPE;
+	psci_ops.migrate_info_type = psci_migrate_info_type;
+
+	arm_pm_restart = psci_sys_reset;
+
+	pm_power_off = psci_sys_poweroff;
+
+out_put_node:
+	of_node_put(np);
+	return err;
+}
+
+/*
+ * PSCI < v0.2 get PSCI Function IDs via DT.
+ */
+static int psci_0_1_init(struct device_node *np)
+{
+	u32 id;
+	int err;
+
+	err = get_set_conduit_method(np);
+
+	if (err)
+		goto out_put_node;
+
+	pr_info("Using PSCI v0.1 Function IDs from DT\n");
+
 	if (!of_property_read_u32(np, "cpu_suspend", &id)) {
 		psci_function_id[PSCI_FN_CPU_SUSPEND] = id;
 		psci_ops.cpu_suspend = psci_cpu_suspend;
@@ -206,5 +308,25 @@ void __init psci_init(void)
 
 out_put_node:
 	of_node_put(np);
-	return;
+	return err;
+}
+
+static const struct of_device_id psci_of_match[] __initconst = {
+	{ .compatible = "arm,psci", .data = psci_0_1_init},
+	{ .compatible = "arm,psci-0.2", .data = psci_0_2_init},
+	{},
+};
+
+int __init psci_init(void)
+{
+	struct device_node *np;
+	const struct of_device_id *matched_np;
+	psci_initcall_t init_fn;
+
+	np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np);
+	if (!np)
+		return -ENODEV;
+
+	init_fn = (psci_initcall_t)matched_np->data;
+	return init_fn(np);
 }
diff --git a/arch/arm/kernel/psci_smp.c b/arch/arm/kernel/psci_smp.c
index 570a48cc3d64..28a1db4da704 100644
--- a/arch/arm/kernel/psci_smp.c
+++ b/arch/arm/kernel/psci_smp.c
@@ -16,6 +16,8 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/of.h>
+#include <linux/delay.h>
+#include <uapi/linux/psci.h>
 
 #include <asm/psci.h>
 #include <asm/smp_plat.h>
@@ -66,6 +68,36 @@ void __ref psci_cpu_die(unsigned int cpu)
        /* We should never return */
        panic("psci: cpu %d failed to shutdown\n", cpu);
 }
+
+int __ref psci_cpu_kill(unsigned int cpu)
+{
+	int err, i;
+
+	if (!psci_ops.affinity_info)
+		return 1;
+	/*
+	 * cpu_kill could race with cpu_die and we can
+	 * potentially end up declaring this cpu undead
+	 * while it is dying. So, try again a few times.
+	 */
+
+	for (i = 0; i < 10; i++) {
+		err = psci_ops.affinity_info(cpu_logical_map(cpu), 0);
+		if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) {
+			pr_info("CPU%d killed.\n", cpu);
+			return 1;
+		}
+
+		msleep(10);
+		pr_info("Retrying again to check for CPU kill\n");
+	}
+
+	pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n",
+			cpu, err);
+	/* Make platform_cpu_kill() fail. */
+	return 0;
+}
+
 #endif
 
 bool __init psci_smp_available(void)
@@ -78,5 +110,6 @@ struct smp_operations __initdata psci_smp_ops = {
 	.smp_boot_secondary	= psci_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_die		= psci_cpu_die,
+	.cpu_kill		= psci_cpu_kill,
 #endif
 };
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 50e198c1e9c8..8a16ee5d8a95 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -72,6 +72,7 @@ static int __init fpe_setup(char *line)
 __setup("fpe=", fpe_setup);
 #endif
 
+extern void init_default_cache_policy(unsigned long);
 extern void paging_init(const struct machine_desc *desc);
 extern void early_paging_init(const struct machine_desc *,
 			      struct proc_info_list *);
@@ -590,7 +591,7 @@ static void __init setup_processor(void)
 
 	pr_info("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n",
 		cpu_name, read_cpuid_id(), read_cpuid_id() & 15,
-		proc_arch[cpu_architecture()], cr_alignment);
+		proc_arch[cpu_architecture()], get_cr());
 
 	snprintf(init_utsname()->machine, __NEW_UTS_LEN + 1, "%s%c",
 		 list->arch_name, ENDIANNESS);
@@ -603,7 +604,9 @@ static void __init setup_processor(void)
 #ifndef CONFIG_ARM_THUMB
 	elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT);
 #endif
-
+#ifdef CONFIG_MMU
+	init_default_cache_policy(list->__cpu_mm_mmu_flags);
+#endif
 	erratum_a15_798181_init();
 
 	feat_v6_fixup();
@@ -628,15 +631,8 @@ void __init dump_machine_table(void)
 
 int __init arm_add_memory(u64 start, u64 size)
 {
-	struct membank *bank = &meminfo.bank[meminfo.nr_banks];
 	u64 aligned_start;
 
-	if (meminfo.nr_banks >= NR_BANKS) {
-		pr_crit("NR_BANKS too low, ignoring memory at 0x%08llx\n",
-			(long long)start);
-		return -EINVAL;
-	}
-
 	/*
 	 * Ensure that start/size are aligned to a page boundary.
 	 * Size is appropriately rounded down, start is rounded up.
@@ -677,17 +673,17 @@ int __init arm_add_memory(u64 start, u64 size)
 		aligned_start = PHYS_OFFSET;
 	}
 
-	bank->start = aligned_start;
-	bank->size = size & ~(phys_addr_t)(PAGE_SIZE - 1);
+	start = aligned_start;
+	size = size & ~(phys_addr_t)(PAGE_SIZE - 1);
 
 	/*
 	 * Check whether this memory region has non-zero size or
 	 * invalid node number.
 	 */
-	if (bank->size == 0)
+	if (size == 0)
 		return -EINVAL;
 
-	meminfo.nr_banks++;
+	memblock_add(start, size);
 	return 0;
 }
 
@@ -695,6 +691,7 @@ int __init arm_add_memory(u64 start, u64 size)
  * Pick out the memory size.  We look for mem=size@start,
  * where start and size are "size[KkMm]"
  */
+
 static int __init early_mem(char *p)
 {
 	static int usermem __initdata = 0;
@@ -709,7 +706,8 @@ static int __init early_mem(char *p)
 	 */
 	if (usermem == 0) {
 		usermem = 1;
-		meminfo.nr_banks = 0;
+		memblock_remove(memblock_start_of_DRAM(),
+			memblock_end_of_DRAM() - memblock_start_of_DRAM());
 	}
 
 	start = PHYS_OFFSET;
@@ -854,13 +852,6 @@ static void __init reserve_crashkernel(void)
 static inline void reserve_crashkernel(void) {}
 #endif /* CONFIG_KEXEC */
 
-static int __init meminfo_cmp(const void *_a, const void *_b)
-{
-	const struct membank *a = _a, *b = _b;
-	long cmp = bank_pfn_start(a) - bank_pfn_start(b);
-	return cmp < 0 ? -1 : cmp > 0 ? 1 : 0;
-}
-
 void __init hyp_mode_check(void)
 {
 #ifdef CONFIG_ARM_VIRT_EXT
@@ -903,12 +894,10 @@ void __init setup_arch(char **cmdline_p)
 
 	parse_early_param();
 
-	sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL);
-
 	early_paging_init(mdesc, lookup_processor_type(read_cpuid_id()));
 	setup_dma_zone(mdesc);
 	sanity_check_meminfo();
-	arm_memblock_init(&meminfo, mdesc);
+	arm_memblock_init(mdesc);
 
 	paging_init(mdesc);
 	request_standard_resources(mdesc);
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index b907d9b790ab..1b880db2a033 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -127,6 +127,10 @@ ENDPROC(cpu_resume_after_mmu)
 	.align
 ENTRY(cpu_resume)
 ARM_BE8(setend be)			@ ensure we are in BE mode
+#ifdef CONFIG_ARM_VIRT_EXT
+	bl	__hyp_stub_install_secondary
+#endif
+	safe_svcmode_maskall r1
 	mov	r1, #0
 	ALT_SMP(mrc p15, 0, r0, c0, c0, 5)
 	ALT_UP_B(1f)
@@ -144,7 +148,6 @@ ARM_BE8(setend be)			@ ensure we are in BE mode
 	ldr	r0, [r0, #SLEEP_SAVE_SP_PHYS]
 	ldr	r0, [r0, r1, lsl #2]
 
-	setmode	PSR_I_BIT | PSR_F_BIT | SVC_MODE, r1  @ set SVC, irqs off
 	@ load phys pgd, stack, resume fn
   ARM(	ldmia	r0!, {r1, sp, pc}	)
 THUMB(	ldmia	r0!, {r1, r2, r3}	)
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index af4e8c8a5422..f065eb05d254 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -3,6 +3,7 @@
 #include <linux/stacktrace.h>
 
 #include <asm/stacktrace.h>
+#include <asm/traps.h>
 
 #if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND)
 /*
@@ -61,6 +62,7 @@ EXPORT_SYMBOL(walk_stackframe);
 #ifdef CONFIG_STACKTRACE
 struct stack_trace_data {
 	struct stack_trace *trace;
+	unsigned long last_pc;
 	unsigned int no_sched_functions;
 	unsigned int skip;
 };
@@ -69,6 +71,7 @@ static int save_trace(struct stackframe *frame, void *d)
 {
 	struct stack_trace_data *data = d;
 	struct stack_trace *trace = data->trace;
+	struct pt_regs *regs;
 	unsigned long addr = frame->pc;
 
 	if (data->no_sched_functions && in_sched_functions(addr))
@@ -80,16 +83,39 @@ static int save_trace(struct stackframe *frame, void *d)
 
 	trace->entries[trace->nr_entries++] = addr;
 
+	if (trace->nr_entries >= trace->max_entries)
+		return 1;
+
+	/*
+	 * in_exception_text() is designed to test if the PC is one of
+	 * the functions which has an exception stack above it, but
+	 * unfortunately what is in frame->pc is the return LR value,
+	 * not the saved PC value.  So, we need to track the previous
+	 * frame PC value when doing this.
+	 */
+	addr = data->last_pc;
+	data->last_pc = frame->pc;
+	if (!in_exception_text(addr))
+		return 0;
+
+	regs = (struct pt_regs *)frame->sp;
+
+	trace->entries[trace->nr_entries++] = regs->ARM_pc;
+
 	return trace->nr_entries >= trace->max_entries;
 }
 
-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+/* This must be noinline to so that our skip calculation works correctly */
+static noinline void __save_stack_trace(struct task_struct *tsk,
+	struct stack_trace *trace, unsigned int nosched)
 {
 	struct stack_trace_data data;
 	struct stackframe frame;
 
 	data.trace = trace;
+	data.last_pc = ULONG_MAX;
 	data.skip = trace->skip;
+	data.no_sched_functions = nosched;
 
 	if (tsk != current) {
 #ifdef CONFIG_SMP
@@ -102,7 +128,6 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 			trace->entries[trace->nr_entries++] = ULONG_MAX;
 		return;
 #else
-		data.no_sched_functions = 1;
 		frame.fp = thread_saved_fp(tsk);
 		frame.sp = thread_saved_sp(tsk);
 		frame.lr = 0;		/* recovered from the stack */
@@ -111,11 +136,12 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	} else {
 		register unsigned long current_sp asm ("sp");
 
-		data.no_sched_functions = 0;
+		/* We don't want this function nor the caller */
+		data.skip += 2;
 		frame.fp = (unsigned long)__builtin_frame_address(0);
 		frame.sp = current_sp;
 		frame.lr = (unsigned long)__builtin_return_address(0);
-		frame.pc = (unsigned long)save_stack_trace_tsk;
+		frame.pc = (unsigned long)__save_stack_trace;
 	}
 
 	walk_stackframe(&frame, save_trace, &data);
@@ -123,9 +149,33 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
+void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
+{
+	struct stack_trace_data data;
+	struct stackframe frame;
+
+	data.trace = trace;
+	data.skip = trace->skip;
+	data.no_sched_functions = 0;
+
+	frame.fp = regs->ARM_fp;
+	frame.sp = regs->ARM_sp;
+	frame.lr = regs->ARM_lr;
+	frame.pc = regs->ARM_pc;
+
+	walk_stackframe(&frame, save_trace, &data);
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	__save_stack_trace(tsk, trace, 1);
+}
+
 void save_stack_trace(struct stack_trace *trace)
 {
-	save_stack_trace_tsk(current, trace);
+	__save_stack_trace(current, trace, 0);
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 #endif
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 0bc94b1fd1ae..3997c411c140 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -91,13 +91,13 @@ static void __init parse_dt_topology(void)
 {
 	const struct cpu_efficiency *cpu_eff;
 	struct device_node *cn = NULL;
-	unsigned long min_capacity = (unsigned long)(-1);
+	unsigned long min_capacity = ULONG_MAX;
 	unsigned long max_capacity = 0;
 	unsigned long capacity = 0;
-	int alloc_size, cpu = 0;
+	int cpu = 0;
 
-	alloc_size = nr_cpu_ids * sizeof(*__cpu_capacity);
-	__cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT);
+	__cpu_capacity = kcalloc(nr_cpu_ids, sizeof(*__cpu_capacity),
+				 GFP_NOWAIT);
 
 	for_each_possible_cpu(cpu) {
 		const u32 *rate;
@@ -185,6 +185,15 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 	return &cpu_topology[cpu].core_sibling;
 }
 
+/*
+ * The current assumption is that we can power gate each core independently.
+ * This will be superseded by DT binding once available.
+ */
+const struct cpumask *cpu_corepower_mask(int cpu)
+{
+	return &cpu_topology[cpu].thread_sibling;
+}
+
 static void update_siblings_masks(unsigned int cpuid)
 {
 	struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
@@ -266,6 +275,20 @@ void store_cpu_topology(unsigned int cpuid)
 		cpu_topology[cpuid].socket_id, mpidr);
 }
 
+static inline const int cpu_corepower_flags(void)
+{
+	return SD_SHARE_PKG_RESOURCES  | SD_SHARE_POWERDOMAIN;
+}
+
+static struct sched_domain_topology_level arm_topology[] = {
+#ifdef CONFIG_SCHED_MC
+	{ cpu_corepower_mask, cpu_corepower_flags, SD_INIT_NAME(GMC) },
+	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+#endif
+	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ NULL, },
+};
+
 /*
  * init_cpu_topology is called at boot when only one cpu is running
  * which prevent simultaneous write access to cpu_topology array
@@ -289,4 +312,7 @@ void __init init_cpu_topology(void)
 	smp_wmb();
 
 	parse_dt_topology();
+
+	/* Set scheduler topology descriptor */
+	set_sched_topology(arm_topology);
 }
diff --git a/arch/arm/kernel/uprobes.c b/arch/arm/kernel/uprobes.c
index f9bacee973bf..56adf9c1fde0 100644
--- a/arch/arm/kernel/uprobes.c
+++ b/arch/arm/kernel/uprobes.c
@@ -113,6 +113,26 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	return 0;
 }
 
+void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
+			   void *src, unsigned long len)
+{
+	void *xol_page_kaddr = kmap_atomic(page);
+	void *dst = xol_page_kaddr + (vaddr & ~PAGE_MASK);
+
+	preempt_disable();
+
+	/* Initialize the slot */
+	memcpy(dst, src, len);
+
+	/* flush caches (dcache/icache) */
+	flush_uprobe_xol_access(page, vaddr, dst, len);
+
+	preempt_enable();
+
+	kunmap_atomic(xol_page_kaddr);
+}
+
+
 int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
 	struct uprobe_task *utask = current->utask;