Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:
 "Included in this update are both some long term fixes and some new
  features.

  Fixes:

   - An integer overflow in the calculation of ELF_ET_DYN_BASE.

   - Avoiding OOMs for high-order IOMMU allocations

   - SMP requires the data cache to be enabled for synchronisation
     primitives to work, so prevent the CPU_DCACHE_DISABLE option being
     visible on SMP builds.

   - A bug going back 10+ years in the noMMU ARM94* CPU support code,
     where it corrupts registers.  Found by folk getting Linux running
     on their cameras.

   - Versatile Express needs an errata workaround enabled for CPU
     hot-unplug to work.

  Features:

   - Clean up module linker by handling out of range relocations
     separately from relocation cases we don't handle.

   - Fix a long term bug in the pci_mmap_page_range() code, which we
     hope won't impact userspace (we hope there's no users of the
     existing broken interface.)

   - Don't map DMA coherent allocations when we don't have a MMU.

   - Drop experimental status for SMP_ON_UP.

   - Warn when DT doesn't specify ePAPR mandatory cache properties.

   - Add documentation concerning how we find the start of physical
     memory for AUTO_ZRELADDR kernels, detailing why we have chosen the
     mask and the implications of changing it.

   - Updates from Ard Biesheuvel to address some issues with large
     kernels (such as allyesconfig) failing to link.

   - Allow hibernation to work on modern (ARMv7) CPUs - this appears to
     have never worked in the past on these CPUs.

   - Enable IRQ_SHOW_LEVEL, which changes the /proc/interrupts output
     format (hopefully without userspace breaking...  let's hope that if
     it causes someone a problem, they tell us.)

   - Fix tegra-ahb DT offsets.

   - Rework ARM errata 643719 code (and ARMv7 flush_cache_louis()/
     flush_dcache_all()) code to be more efficient, and enable this
     errata workaround by default for ARMv7+SMP CPUs.  This complements
     the Versatile Express fix above.

   - Rework ARMv7 context code for errata 430973, so that only Cortex A8
     CPUs are impacted by the branch target buffer flush when this
     errata is enabled.  Also update the help text to indicate that all
     r1p* A8 CPUs are impacted.

   - Switch ARM to the generic show_mem() implementation, it conveys all
     the information which we were already reporting.

   - Prevent slow timer sources being used for udelay() - timers running
     at less than 1MHz are not useful for this, and can cause udelay()
     to return immediately, without any wait.  Using such a slow timer
     is silly.

   - VDSO support for 32-bit ARM, mainly for gettimeofday() using the
     ARM architected timer.

   - Perf support for Scorpion performance monitoring units"

vdso semantic conflict fixed up as per linux-next.

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (52 commits)
  ARM: update errata 430973 documentation to cover Cortex A8 r1p*
  ARM: ensure delay timer has sufficient accuracy for delays
  ARM: switch to use the generic show_mem() implementation
  ARM: proc-v7: avoid errata 430973 workaround for non-Cortex A8 CPUs
  ARM: enable ARM errata 643719 workaround by default
  ARM: cache-v7: optimise test for Cortex A9 r0pX devices
  ARM: cache-v7: optimise branches in v7_flush_cache_louis
  ARM: cache-v7: consolidate initialisation of cache level index
  ARM: cache-v7: shift CLIDR to extract appropriate field before masking
  ARM: cache-v7: use movw/movt instructions
  ARM: allow 16-bit instructions in ALT_UP()
  ARM: proc-arm94*.S: fix setup function
  ARM: vexpress: fix CPU hotplug with CT9x4 tile.
  ARM: 8276/1: Make CPU_DCACHE_DISABLE depend on !SMP
  ARM: 8335/1: Documentation: DT bindings: Tegra AHB: document the legacy base address
  ARM: 8334/1: amba: tegra-ahb: detect and correct bogus base address
  ARM: 8333/1: amba: tegra-ahb: fix register offsets in the macros
  ARM: 8339/1: Enable CONFIG_GENERIC_IRQ_SHOW_LEVEL
  ARM: 8338/1: kexec: Relax SMP validation to improve DT compatibility
  ARM: 8337/1: mm: Do not invoke OOM for higher order IOMMU DMA allocations
  ...

23 files changed, 1185 insertions, 320 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 902397dd1000..ba5f83226011 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -16,7 +16,7 @@ CFLAGS_REMOVE_return_address.o = -pg
 # Object file lists.
 
 obj-y		:= elf.o entry-common.o irq.o opcodes.o \
-		   process.o ptrace.o return_address.o \
+		   process.o ptrace.o reboot.o return_address.o \
 		   setup.o signal.o sigreturn_codes.o \
 		   stacktrace.o sys_arm.o time.o traps.o
 
@@ -75,6 +75,7 @@ obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o perf_event_cpu.o
 CFLAGS_pj4-cp0.o		:= -marm
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
 obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
+obj-$(CONFIG_VDSO)		+= vdso.o
 
 ifneq ($(CONFIG_ARCH_EBSA110),y)
   obj-y		+= io.o
@@ -86,7 +87,7 @@ obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 
 obj-$(CONFIG_ARM_VIRT_EXT)	+= hyp-stub.o
 ifeq ($(CONFIG_ARM_PSCI),y)
-obj-y				+= psci.o
+obj-y				+= psci.o psci-call.o
 obj-$(CONFIG_SMP)		+= psci_smp.o
 endif
 
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 488eaac56028..61bb5a65eb37 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -25,6 +25,7 @@
 #include <asm/memory.h>
 #include <asm/procinfo.h>
 #include <asm/suspend.h>
+#include <asm/vdso_datapage.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <linux/kbuild.h>
 
@@ -206,5 +207,9 @@ int main(void)
   DEFINE(KVM_VGIC_VCTRL,	offsetof(struct kvm, arch.vgic.vctrl_base));
   DEFINE(KVM_VTTBR,		offsetof(struct kvm, arch.vttbr));
 #endif
+  BLANK();
+#ifdef CONFIG_VDSO
+  DEFINE(VDSO_DATA_SIZE,	sizeof(union vdso_data_store));
+#endif
   return 0; 
 }
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index ab19b7c03423..fcbbbb1b9e95 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -618,21 +618,15 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state, int write_combine)
 {
-	struct pci_sys_data *root = dev->sysdata;
-	unsigned long phys;
-
-	if (mmap_state == pci_mmap_io) {
+	if (mmap_state == pci_mmap_io)
 		return -EINVAL;
-	} else {
-		phys = vma->vm_pgoff + (root->mem_offset >> PAGE_SHIFT);
-	}
 
 	/*
 	 * Mark this as IO
 	 */
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
-	if (remap_pfn_range(vma, vma->vm_start, phys,
+	if (remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
 			     vma->vm_end - vma->vm_start,
 			     vma->vm_page_prot))
 		return -EAGAIN;
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 672b21942fff..570306c49406 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -545,7 +545,7 @@ ENDPROC(__und_usr)
 /*
  * The out of line fixup for the ldrt instructions above.
  */
-	.pushsection .fixup, "ax"
+	.pushsection .text.fixup, "ax"
 	.align	2
 4:	str     r4, [sp, #S_PC]			@ retry current instruction
 	ret	r9
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 01963273c07a..3637973a9708 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -138,9 +138,9 @@ ENTRY(stext)
 						@ mmu has been enabled
 	adr	lr, BSYM(1f)			@ return (PIC) address
 	mov	r8, r4				@ set TTBR1 to swapper_pg_dir
- ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
- THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
- THUMB(	ret	r12				)
+	ldr	r12, [r10, #PROCINFO_INITFUNC]
+	add	r12, r12, r10
+	ret	r12
 1:	b	__enable_mmu
 ENDPROC(stext)
 	.ltorg
@@ -386,10 +386,10 @@ ENTRY(secondary_startup)
 	ldr	r8, [r7, lr]			@ get secondary_data.swapper_pg_dir
 	adr	lr, BSYM(__enable_mmu)		@ return address
 	mov	r13, r12			@ __secondary_switched address
- ARM(	add	pc, r10, #PROCINFO_INITFUNC	) @ initialise processor
-						  @ (return control reg)
- THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
- THUMB(	ret	r12				)
+	ldr	r12, [r10, #PROCINFO_INITFUNC]
+	add	r12, r12, r10			@ initialise processor
+						@ (return control reg)
+	ret	r12
 ENDPROC(secondary_startup)
 ENDPROC(secondary_startup_arm)
 
diff --git a/arch/arm/kernel/hibernate.c b/arch/arm/kernel/hibernate.c
index c4cc50e58c13..a71501ff6f18 100644
--- a/arch/arm/kernel/hibernate.c
+++ b/arch/arm/kernel/hibernate.c
@@ -22,6 +22,7 @@
 #include <asm/suspend.h>
 #include <asm/memory.h>
 #include <asm/sections.h>
+#include "reboot.h"
 
 int pfn_is_nosave(unsigned long pfn)
 {
@@ -61,7 +62,7 @@ static int notrace arch_save_image(unsigned long unused)
 
 	ret = swsusp_save();
 	if (ret == 0)
-		soft_restart(virt_to_phys(cpu_resume));
+		_soft_restart(virt_to_phys(cpu_resume), false);
 	return ret;
 }
 
@@ -86,7 +87,7 @@ static void notrace arch_restore_image(void *unused)
 	for (pbe = restore_pblist; pbe; pbe = pbe->next)
 		copy_page(pbe->orig_address, pbe->address);
 
-	soft_restart(virt_to_phys(cpu_resume));
+	_soft_restart(virt_to_phys(cpu_resume), false);
 }
 
 static u64 resume_stack[PAGE_SIZE/2/sizeof(u64)] __nosavedata;
@@ -99,7 +100,6 @@ static u64 resume_stack[PAGE_SIZE/2/sizeof(u64)] __nosavedata;
  */
 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/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index de2b085ad753..8bf3b7c09888 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -46,7 +46,8 @@ int machine_kexec_prepare(struct kimage *image)
 	 * and implements CPU hotplug for the current HW. If not, we won't be
 	 * able to kexec reliably, so fail the prepare operation.
 	 */
-	if (num_possible_cpus() > 1 && !platform_can_cpu_hotplug())
+	if (num_possible_cpus() > 1 && platform_can_secondary_boot() &&
+	    !platform_can_cpu_hotplug())
 		return -EINVAL;
 
 	/*
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index 2e11961f65ae..af791f4a6205 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -98,14 +98,19 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 		case R_ARM_PC24:
 		case R_ARM_CALL:
 		case R_ARM_JUMP24:
+			if (sym->st_value & 3) {
+				pr_err("%s: section %u reloc %u sym '%s': unsupported interworking call (ARM -> Thumb)\n",
+				       module->name, relindex, i, symname);
+				return -ENOEXEC;
+			}
+
 			offset = __mem_to_opcode_arm(*(u32 *)loc);
 			offset = (offset & 0x00ffffff) << 2;
 			if (offset & 0x02000000)
 				offset -= 0x04000000;
 
 			offset += sym->st_value - loc;
-			if (offset & 3 ||
-			    offset <= (s32)0xfe000000 ||
+			if (offset <= (s32)0xfe000000 ||
 			    offset >= (s32)0x02000000) {
 				pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
 				       module->name, relindex, i, symname,
@@ -155,6 +160,22 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 #ifdef CONFIG_THUMB2_KERNEL
 		case R_ARM_THM_CALL:
 		case R_ARM_THM_JUMP24:
+			/*
+			 * For function symbols, only Thumb addresses are
+			 * allowed (no interworking).
+			 *
+			 * For non-function symbols, the destination
+			 * has no specific ARM/Thumb disposition, so
+			 * the branch is resolved under the assumption
+			 * that interworking is not required.
+			 */
+			if (ELF32_ST_TYPE(sym->st_info) == STT_FUNC &&
+			    !(sym->st_value & 1)) {
+				pr_err("%s: section %u reloc %u sym '%s': unsupported interworking call (Thumb -> ARM)\n",
+				       module->name, relindex, i, symname);
+				return -ENOEXEC;
+			}
+
 			upper = __mem_to_opcode_thumb16(*(u16 *)loc);
 			lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2));
 
@@ -182,18 +203,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 				offset -= 0x02000000;
 			offset += sym->st_value - loc;
 
-			/*
-			 * For function symbols, only Thumb addresses are
-			 * allowed (no interworking).
-			 *
-			 * For non-function symbols, the destination
-			 * has no specific ARM/Thumb disposition, so
-			 * the branch is resolved under the assumption
-			 * that interworking is not required.
-			 */
-			if ((ELF32_ST_TYPE(sym->st_info) == STT_FUNC &&
-				!(offset & 1)) ||
-			    offset <= (s32)0xff000000 ||
+			if (offset <= (s32)0xff000000 ||
 			    offset >= (s32)0x01000000) {
 				pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
 				       module->name, relindex, i, symname,
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 557e128e4df0..4a86a0133ac3 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -259,20 +259,29 @@ out:
 }
 
 static int
-validate_event(struct pmu_hw_events *hw_events,
-	       struct perf_event *event)
+validate_event(struct pmu *pmu, struct pmu_hw_events *hw_events,
+			       struct perf_event *event)
 {
-	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+	struct arm_pmu *armpmu;
 
 	if (is_software_event(event))
 		return 1;
 
+	/*
+	 * Reject groups spanning multiple HW PMUs (e.g. CPU + CCI). The
+	 * core perf code won't check that the pmu->ctx == leader->ctx
+	 * until after pmu->event_init(event).
+	 */
+	if (event->pmu != pmu)
+		return 0;
+
 	if (event->state < PERF_EVENT_STATE_OFF)
 		return 1;
 
 	if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
 		return 1;
 
+	armpmu = to_arm_pmu(event->pmu);
 	return armpmu->get_event_idx(hw_events, event) >= 0;
 }
 
@@ -288,15 +297,15 @@ validate_group(struct perf_event *event)
 	 */
 	memset(&fake_pmu.used_mask, 0, sizeof(fake_pmu.used_mask));
 
-	if (!validate_event(&fake_pmu, leader))
+	if (!validate_event(event->pmu, &fake_pmu, leader))
 		return -EINVAL;
 
 	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
-		if (!validate_event(&fake_pmu, sibling))
+		if (!validate_event(event->pmu, &fake_pmu, sibling))
 			return -EINVAL;
 	}
 
-	if (!validate_event(&fake_pmu, event))
+	if (!validate_event(event->pmu, &fake_pmu, event))
 		return -EINVAL;
 
 	return 0;
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 61b53c46edfa..91c7ba182dcd 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -92,11 +92,16 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
 		free_percpu_irq(irq, &hw_events->percpu_pmu);
 	} else {
 		for (i = 0; i < irqs; ++i) {
-			if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs))
+			int cpu = i;
+
+			if (cpu_pmu->irq_affinity)
+				cpu = cpu_pmu->irq_affinity[i];
+
+			if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs))
 				continue;
 			irq = platform_get_irq(pmu_device, i);
 			if (irq >= 0)
-				free_irq(irq, per_cpu_ptr(&hw_events->percpu_pmu, i));
+				free_irq(irq, per_cpu_ptr(&hw_events->percpu_pmu, cpu));
 		}
 	}
 }
@@ -128,32 +133,37 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 		on_each_cpu(cpu_pmu_enable_percpu_irq, &irq, 1);
 	} else {
 		for (i = 0; i < irqs; ++i) {
+			int cpu = i;
+
 			err = 0;
 			irq = platform_get_irq(pmu_device, i);
 			if (irq < 0)
 				continue;
 
+			if (cpu_pmu->irq_affinity)
+				cpu = cpu_pmu->irq_affinity[i];
+
 			/*
 			 * If we have a single PMU interrupt that we can't shift,
 			 * assume that we're running on a uniprocessor machine and
 			 * continue. Otherwise, continue without this interrupt.
 			 */
-			if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
+			if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) {
 				pr_warn("unable to set irq affinity (irq=%d, cpu=%u)\n",
-					irq, i);
+					irq, cpu);
 				continue;
 			}
 
 			err = request_irq(irq, handler,
 					  IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
-					  per_cpu_ptr(&hw_events->percpu_pmu, i));
+					  per_cpu_ptr(&hw_events->percpu_pmu, cpu));
 			if (err) {
 				pr_err("unable to request IRQ%d for ARM PMU counters\n",
 					irq);
 				return err;
 			}
 
-			cpumask_set_cpu(i, &cpu_pmu->active_irqs);
+			cpumask_set_cpu(cpu, &cpu_pmu->active_irqs);
 		}
 	}
 
@@ -243,6 +253,8 @@ static const struct of_device_id cpu_pmu_of_device_ids[] = {
 	{.compatible = "arm,arm1176-pmu",	.data = armv6_1176_pmu_init},
 	{.compatible = "arm,arm1136-pmu",	.data = armv6_1136_pmu_init},
 	{.compatible = "qcom,krait-pmu",	.data = krait_pmu_init},
+	{.compatible = "qcom,scorpion-pmu",	.data = scorpion_pmu_init},
+	{.compatible = "qcom,scorpion-mp-pmu",	.data = scorpion_mp_pmu_init},
 	{},
 };
 
@@ -289,6 +301,48 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 	return ret;
 }
 
+static int of_pmu_irq_cfg(struct platform_device *pdev)
+{
+	int i;
+	int *irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
+
+	if (!irqs)
+		return -ENOMEM;
+
+	for (i = 0; i < pdev->num_resources; ++i) {
+		struct device_node *dn;
+		int cpu;
+
+		dn = of_parse_phandle(pdev->dev.of_node, "interrupt-affinity",
+				      i);
+		if (!dn) {
+			pr_warn("Failed to parse %s/interrupt-affinity[%d]\n",
+				of_node_full_name(dn), i);
+			break;
+		}
+
+		for_each_possible_cpu(cpu)
+			if (arch_find_n_match_cpu_physical_id(dn, cpu, NULL))
+				break;
+
+		of_node_put(dn);
+		if (cpu >= nr_cpu_ids) {
+			pr_warn("Failed to find logical CPU for %s\n",
+				dn->name);
+			break;
+		}
+
+		irqs[i] = cpu;
+	}
+
+	if (i == pdev->num_resources)
+		cpu_pmu->irq_affinity = irqs;
+	else
+		kfree(irqs);
+
+	return 0;
+}
+
 static int cpu_pmu_device_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id;
@@ -313,7 +367,10 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
 
 	if (node && (of_id = of_match_node(cpu_pmu_of_device_ids, pdev->dev.of_node))) {
 		init_fn = of_id->data;
-		ret = init_fn(pmu);
+
+		ret = of_pmu_irq_cfg(pdev);
+		if (!ret)
+			ret = init_fn(pmu);
 	} else {
 		ret = probe_current_pmu(pmu);
 	}
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 8993770c47de..f4207a4dcb01 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -140,6 +140,23 @@ enum krait_perf_types {
 	KRAIT_PERFCTR_L1_DTLB_ACCESS			= 0x12210,
 };
 
+/* ARMv7 Scorpion specific event types */
+enum scorpion_perf_types {
+	SCORPION_LPM0_GROUP0				= 0x4c,
+	SCORPION_LPM1_GROUP0				= 0x50,
+	SCORPION_LPM2_GROUP0				= 0x54,
+	SCORPION_L2LPM_GROUP0				= 0x58,
+	SCORPION_VLPM_GROUP0				= 0x5c,
+
+	SCORPION_ICACHE_ACCESS				= 0x10053,
+	SCORPION_ICACHE_MISS				= 0x10052,
+
+	SCORPION_DTLB_ACCESS				= 0x12013,
+	SCORPION_DTLB_MISS				= 0x12012,
+
+	SCORPION_ITLB_MISS				= 0x12021,
+};
+
 /*
  * Cortex-A8 HW events mapping
  *
@@ -482,6 +499,49 @@ static const unsigned krait_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 };
 
 /*
+ * Scorpion HW events mapping
+ */
+static const unsigned scorpion_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
+	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV7_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV7_PERFCTR_INSTR_EXECUTED,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
+	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]	    = ARMV7_PERFCTR_CLOCK_CYCLES,
+};
+
+static const unsigned scorpion_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					    [PERF_COUNT_HW_CACHE_OP_MAX]
+					    [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+	/*
+	 * The performance counters don't differentiate between read and write
+	 * accesses/misses so this isn't strictly correct, but it's the best we
+	 * can do. Writes and reads get combined.
+	 */
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = SCORPION_ICACHE_ACCESS,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)] = SCORPION_ICACHE_MISS,
+	/*
+	 * Only ITLB misses and DTLB refills are supported.  If users want the
+	 * DTLB refills misses a raw counter must be used.
+	 */
+	[C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)] = SCORPION_DTLB_ACCESS,
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = SCORPION_DTLB_MISS,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = SCORPION_DTLB_ACCESS,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = SCORPION_DTLB_MISS,
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = SCORPION_ITLB_MISS,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = SCORPION_ITLB_MISS,
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+};
+
+/*
  * Perf Events' indices
  */
 #define	ARMV7_IDX_CYCLE_COUNTER	0
@@ -976,6 +1036,12 @@ static int krait_map_event_no_branch(struct perf_event *event)
 				&krait_perf_cache_map, 0xFFFFF);
 }
 
+static int scorpion_map_event(struct perf_event *event)
+{
+	return armpmu_map_event(event, &scorpion_perf_map,
+				&scorpion_perf_cache_map, 0xFFFFF);
+}
+
 static void armv7pmu_init(struct arm_pmu *cpu_pmu)
 {
 	cpu_pmu->handle_irq	= armv7pmu_handle_irq;
@@ -1103,6 +1169,12 @@ static int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu)
 #define KRAIT_EVENT_MASK	(KRAIT_EVENT | VENUM_EVENT)
 #define PMRESRn_EN		BIT(31)
 
+#define EVENT_REGION(event)	(((event) >> 12) & 0xf)		/* R */
+#define EVENT_GROUP(event)	((event) & 0xf)			/* G */
+#define EVENT_CODE(event)	(((event) >> 4) & 0xff)		/* CC */
+#define EVENT_VENUM(event)	(!!(event & VENUM_EVENT))	/* N=2 */
+#define EVENT_CPU(event)	(!!(event & KRAIT_EVENT))	/* N=1 */
+
 static u32 krait_read_pmresrn(int n)
 {
 	u32 val;
@@ -1141,19 +1213,19 @@ static void krait_write_pmresrn(int n, u32 val)
 	}
 }
 
-static u32 krait_read_vpmresr0(void)
+static u32 venum_read_pmresr(void)
 {
 	u32 val;
 	asm volatile("mrc p10, 7, %0, c11, c0, 0" : "=r" (val));
 	return val;
 }
 
-static void krait_write_vpmresr0(u32 val)
+static void venum_write_pmresr(u32 val)
 {
 	asm volatile("mcr p10, 7, %0, c11, c0, 0" : : "r" (val));
 }
 
-static void krait_pre_vpmresr0(u32 *venum_orig_val, u32 *fp_orig_val)
+static void venum_pre_pmresr(u32 *venum_orig_val, u32 *fp_orig_val)
 {
 	u32 venum_new_val;
 	u32 fp_new_val;
@@ -1170,7 +1242,7 @@ static void krait_pre_vpmresr0(u32 *venum_orig_val, u32 *fp_orig_val)
 	fmxr(FPEXC, fp_new_val);
 }
 
-static void krait_post_vpmresr0(u32 venum_orig_val, u32 fp_orig_val)
+static void venum_post_pmresr(u32 venum_orig_val, u32 fp_orig_val)
 {
 	BUG_ON(preemptible());
 	/* Restore FPEXC */
@@ -1193,16 +1265,11 @@ static void krait_evt_setup(int idx, u32 config_base)
 	u32 val;
 	u32 mask;
 	u32 vval, fval;
-	unsigned int region;
-	unsigned int group;
-	unsigned int code;
+	unsigned int region = EVENT_REGION(config_base);
+	unsigned int group = EVENT_GROUP(config_base);
+	unsigned int code = EVENT_CODE(config_base);
 	unsigned int group_shift;
-	bool venum_event;
-
-	venum_event = !!(config_base & VENUM_EVENT);
-	region = (config_base >> 12) & 0xf;
-	code   = (config_base >> 4) & 0xff;
-	group  = (config_base >> 0)  & 0xf;
+	bool venum_event = EVENT_VENUM(config_base);
 
 	group_shift = group * 8;
 	mask = 0xff << group_shift;
@@ -1217,16 +1284,14 @@ static void krait_evt_setup(int idx, u32 config_base)
 	val |= config_base & (ARMV7_EXCLUDE_USER | ARMV7_EXCLUDE_PL1);
 	armv7_pmnc_write_evtsel(idx, val);
 
-	asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (0));
-
 	if (venum_event) {
-		krait_pre_vpmresr0(&vval, &fval);
-		val = krait_read_vpmresr0();
+		venum_pre_pmresr(&vval, &fval);
+		val = venum_read_pmresr();
 		val &= ~mask;
 		val |= code << group_shift;
 		val |= PMRESRn_EN;
-		krait_write_vpmresr0(val);
-		krait_post_vpmresr0(vval, fval);
+		venum_write_pmresr(val);
+		venum_post_pmresr(vval, fval);
 	} else {
 		val = krait_read_pmresrn(region);
 		val &= ~mask;
@@ -1236,7 +1301,7 @@ static void krait_evt_setup(int idx, u32 config_base)
 	}
 }
 
-static u32 krait_clear_pmresrn_group(u32 val, int group)
+static u32 clear_pmresrn_group(u32 val, int group)
 {
 	u32 mask;
 	int group_shift;
@@ -1256,23 +1321,19 @@ static void krait_clearpmu(u32 config_base)
 {
 	u32 val;
 	u32 vval, fval;
-	unsigned int region;
-	unsigned int group;
-	bool venum_event;
-
-	venum_event = !!(config_base & VENUM_EVENT);
-	region = (config_base >> 12) & 0xf;
-	group  = (config_base >> 0)  & 0xf;
+	unsigned int region = EVENT_REGION(config_base);
+	unsigned int group = EVENT_GROUP(config_base);
+	bool venum_event = EVENT_VENUM(config_base);
 
 	if (venum_event) {
-		krait_pre_vpmresr0(&vval, &fval);
-		val = krait_read_vpmresr0();
-		val = krait_clear_pmresrn_group(val, group);
-		krait_write_vpmresr0(val);
-		krait_post_vpmresr0(vval, fval);
+		venum_pre_pmresr(&vval, &fval);
+		val = venum_read_pmresr();
+		val = clear_pmresrn_group(val, group);
+		venum_write_pmresr(val);
+		venum_post_pmresr(vval, fval);
 	} else {
 		val = krait_read_pmresrn(region);
-		val = krait_clear_pmresrn_group(val, group);
+		val = clear_pmresrn_group(val, group);
 		krait_write_pmresrn(region, val);
 	}
 }
@@ -1342,6 +1403,8 @@ static void krait_pmu_enable_event(struct perf_event *event)
 static void krait_pmu_reset(void *info)
 {
 	u32 vval, fval;
+	struct arm_pmu *cpu_pmu = info;
+	u32 idx, nb_cnt = cpu_pmu->num_events;
 
 	armv7pmu_reset(info);
 
@@ -1350,9 +1413,16 @@ static void krait_pmu_reset(void *info)
 	krait_write_pmresrn(1, 0);
 	krait_write_pmresrn(2, 0);
 
-	krait_pre_vpmresr0(&vval, &fval);
-	krait_write_vpmresr0(0);
-	krait_post_vpmresr0(vval, fval);
+	venum_pre_pmresr(&vval, &fval);
+	venum_write_pmresr(0);
+	venum_post_pmresr(vval, fval);
+
+	/* Reset PMxEVNCTCR to sane default */
+	for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) {
+		armv7_pmnc_select_counter(idx);
+		asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (0));
+	}
+
 }
 
 static int krait_event_to_bit(struct perf_event *event, unsigned int region,
@@ -1386,26 +1456,18 @@ static int krait_pmu_get_event_idx(struct pmu_hw_events *cpuc,
 {
 	int idx;
 	int bit = -1;
-	unsigned int prefix;
-	unsigned int region;
-	unsigned int code;
-	unsigned int group;
-	bool krait_event;
 	struct hw_perf_event *hwc = &event->hw;
+	unsigned int region = EVENT_REGION(hwc->config_base);
+	unsigned int code = EVENT_CODE(hwc->config_base);
+	unsigned int group = EVENT_GROUP(hwc->config_base);
+	bool venum_event = EVENT_VENUM(hwc->config_base);
+	bool krait_event = EVENT_CPU(hwc->config_base);
 
-	region = (hwc->config_base >> 12) & 0xf;
-	code   = (hwc->config_base >> 4) & 0xff;
-	group  = (hwc->config_base >> 0) & 0xf;
-	krait_event = !!(hwc->config_base & KRAIT_EVENT_MASK);
-
-	if (krait_event) {
+	if (venum_event || krait_event) {
 		/* Ignore invalid events */
 		if (group > 3 || region > 2)
 			return -EINVAL;
-		prefix = hwc->config_base & KRAIT_EVENT_MASK;
-		if (prefix != KRAIT_EVENT && prefix != VENUM_EVENT)
-			return -EINVAL;
-		if (prefix == VENUM_EVENT && (code & 0xe0))
+		if (venum_event && (code & 0xe0))
 			return -EINVAL;
 
 		bit = krait_event_to_bit(event, region, group);
@@ -1425,15 +1487,12 @@ static void krait_pmu_clear_event_idx(struct pmu_hw_events *cpuc,
 {
 	int bit;
 	struct hw_perf_event *hwc = &event->hw;
-	unsigned int region;
-	unsigned int group;
-	bool krait_event;
+	unsigned int region = EVENT_REGION(hwc->config_base);
+	unsigned int group = EVENT_GROUP(hwc->config_base);
+	bool venum_event = EVENT_VENUM(hwc->config_base);
+	bool krait_event = EVENT_CPU(hwc->config_base);
 
-	region = (hwc->config_base >> 12) & 0xf;
-	group  = (hwc->config_base >> 0) & 0xf;
-	krait_event = !!(hwc->config_base & KRAIT_EVENT_MASK);
-
-	if (krait_event) {
+	if (venum_event || krait_event) {
 		bit = krait_event_to_bit(event, region, group);
 		clear_bit(bit, cpuc->used_mask);
 	}
@@ -1458,6 +1517,344 @@ static int krait_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->clear_event_idx = krait_pmu_clear_event_idx;
 	return 0;
 }
+
+/*
+ * Scorpion Local Performance Monitor Register (LPMn)
+ *
+ *            31   30     24     16     8      0
+ *            +--------------------------------+
+ *  LPM0      | EN |  CC  |  CC  |  CC  |  CC  |   N = 1, R = 0
+ *            +--------------------------------+
+ *  LPM1      | EN |  CC  |  CC  |  CC  |  CC  |   N = 1, R = 1
+ *            +--------------------------------+
+ *  LPM2      | EN |  CC  |  CC  |  CC  |  CC  |   N = 1, R = 2
+ *            +--------------------------------+
+ *  L2LPM     | EN |  CC  |  CC  |  CC  |  CC  |   N = 1, R = 3
+ *            +--------------------------------+
+ *  VLPM      | EN |  CC  |  CC  |  CC  |  CC  |   N = 2, R = ?
+ *            +--------------------------------+
+ *              EN | G=3  | G=2  | G=1  | G=0
+ *
+ *
+ *  Event Encoding:
+ *
+ *      hwc->config_base = 0xNRCCG
+ *
+ *      N  = prefix, 1 for Scorpion CPU (LPMn/L2LPM), 2 for Venum VFP (VLPM)
+ *      R  = region register
+ *      CC = class of events the group G is choosing from
+ *      G  = group or particular event
+ *
+ *  Example: 0x12021 is a Scorpion CPU event in LPM2's group 1 with code 2
+ *
+ *  A region (R) corresponds to a piece of the CPU (execution unit, instruction
+ *  unit, etc.) while the event code (CC) corresponds to a particular class of
+ *  events (interrupts for example). An event code is broken down into
+ *  groups (G) that can be mapped into the PMU (irq, fiqs, and irq+fiqs for
+ *  example).
+ */
+
+static u32 scorpion_read_pmresrn(int n)
+{
+	u32 val;
+
+	switch (n) {
+	case 0:
+		asm volatile("mrc p15, 0, %0, c15, c0, 0" : "=r" (val));
+		break;
+	case 1:
+		asm volatile("mrc p15, 1, %0, c15, c0, 0" : "=r" (val));
+		break;
+	case 2:
+		asm volatile("mrc p15, 2, %0, c15, c0, 0" : "=r" (val));
+		break;
+	case 3:
+		asm volatile("mrc p15, 3, %0, c15, c2, 0" : "=r" (val));
+		break;
+	default:
+		BUG(); /* Should be validated in scorpion_pmu_get_event_idx() */
+	}
+
+	return val;
+}
+
+static void scorpion_write_pmresrn(int n, u32 val)
+{
+	switch (n) {
+	case 0:
+		asm volatile("mcr p15, 0, %0, c15, c0, 0" : : "r" (val));
+		break;
+	case 1:
+		asm volatile("mcr p15, 1, %0, c15, c0, 0" : : "r" (val));
+		break;
+	case 2:
+		asm volatile("mcr p15, 2, %0, c15, c0, 0" : : "r" (val));
+		break;
+	case 3:
+		asm volatile("mcr p15, 3, %0, c15, c2, 0" : : "r" (val));
+		break;
+	default:
+		BUG(); /* Should be validated in scorpion_pmu_get_event_idx() */
+	}
+}
+
+static u32 scorpion_get_pmresrn_event(unsigned int region)
+{
+	static const u32 pmresrn_table[] = { SCORPION_LPM0_GROUP0,
+					     SCORPION_LPM1_GROUP0,
+					     SCORPION_LPM2_GROUP0,
+					     SCORPION_L2LPM_GROUP0 };
+	return pmresrn_table[region];
+}
+
+static void scorpion_evt_setup(int idx, u32 config_base)
+{
+	u32 val;
+	u32 mask;
+	u32 vval, fval;
+	unsigned int region = EVENT_REGION(config_base);
+	unsigned int group = EVENT_GROUP(config_base);
+	unsigned int code = EVENT_CODE(config_base);
+	unsigned int group_shift;
+	bool venum_event = EVENT_VENUM(config_base);
+
+	group_shift = group * 8;
+	mask = 0xff << group_shift;
+
+	/* Configure evtsel for the region and group */
+	if (venum_event)
+		val = SCORPION_VLPM_GROUP0;
+	else
+		val = scorpion_get_pmresrn_event(region);
+	val += group;
+	/* Mix in mode-exclusion bits */
+	val |= config_base & (ARMV7_EXCLUDE_USER | ARMV7_EXCLUDE_PL1);
+	armv7_pmnc_write_evtsel(idx, val);
+
+	asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (0));
+
+	if (venum_event) {
+		venum_pre_pmresr(&vval, &fval);
+		val = venum_read_pmresr();
+		val &= ~mask;
+		val |= code << group_shift;
+		val |= PMRESRn_EN;
+		venum_write_pmresr(val);
+		venum_post_pmresr(vval, fval);
+	} else {
+		val = scorpion_read_pmresrn(region);
+		val &= ~mask;
+		val |= code << group_shift;
+		val |= PMRESRn_EN;
+		scorpion_write_pmresrn(region, val);
+	}
+}
+
+static void scorpion_clearpmu(u32 config_base)
+{
+	u32 val;
+	u32 vval, fval;
+	unsigned int region = EVENT_REGION(config_base);
+	unsigned int group = EVENT_GROUP(config_base);
+	bool venum_event = EVENT_VENUM(config_base);
+
+	if (venum_event) {
+		venum_pre_pmresr(&vval, &fval);
+		val = venum_read_pmresr();
+		val = clear_pmresrn_group(val, group);
+		venum_write_pmresr(val);
+		venum_post_pmresr(vval, fval);
+	} else {
+		val = scorpion_read_pmresrn(region);
+		val = clear_pmresrn_group(val, group);
+		scorpion_write_pmresrn(region, val);
+	}
+}
+
+static void scorpion_pmu_disable_event(struct perf_event *event)
+{
+	unsigned long flags;
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+
+	/* Disable counter and interrupt */
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
+
+	/* Disable counter */
+	armv7_pmnc_disable_counter(idx);
+
+	/*
+	 * Clear pmresr code (if destined for PMNx counters)
+	 */
+	if (hwc->config_base & KRAIT_EVENT_MASK)
+		scorpion_clearpmu(hwc->config_base);
+
+	/* Disable interrupt for this counter */
+	armv7_pmnc_disable_intens(idx);
+
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static void scorpion_pmu_enable_event(struct perf_event *event)
+{
+	unsigned long flags;
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+
+	/*
+	 * Enable counter and interrupt, and set the counter to count
+	 * the event that we're interested in.
+	 */
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
+
+	/* Disable counter */
+	armv7_pmnc_disable_counter(idx);
+
+	/*
+	 * Set event (if destined for PMNx counters)
+	 * We don't set the event for the cycle counter because we
+	 * don't have the ability to perform event filtering.
+	 */
+	if (hwc->config_base & KRAIT_EVENT_MASK)
+		scorpion_evt_setup(idx, hwc->config_base);
+	else if (idx != ARMV7_IDX_CYCLE_COUNTER)
+		armv7_pmnc_write_evtsel(idx, hwc->config_base);
+
+	/* Enable interrupt for this counter */
+	armv7_pmnc_enable_intens(idx);
+
+	/* Enable counter */
+	armv7_pmnc_enable_counter(idx);
+
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static void scorpion_pmu_reset(void *info)
+{
+	u32 vval, fval;
+	struct arm_pmu *cpu_pmu = info;
+	u32 idx, nb_cnt = cpu_pmu->num_events;
+
+	armv7pmu_reset(info);
+
+	/* Clear all pmresrs */
+	scorpion_write_pmresrn(0, 0);
+	scorpion_write_pmresrn(1, 0);
+	scorpion_write_pmresrn(2, 0);
+	scorpion_write_pmresrn(3, 0);
+
+	venum_pre_pmresr(&vval, &fval);
+	venum_write_pmresr(0);
+	venum_post_pmresr(vval, fval);
+
+	/* Reset PMxEVNCTCR to sane default */
+	for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) {
+		armv7_pmnc_select_counter(idx);
+		asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (0));
+	}
+}
+
+static int scorpion_event_to_bit(struct perf_event *event, unsigned int region,
+			      unsigned int group)
+{
+	int bit;
+	struct hw_perf_event *hwc = &event->hw;
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+
+	if (hwc->config_base & VENUM_EVENT)
+		bit = SCORPION_VLPM_GROUP0;
+	else
+		bit = scorpion_get_pmresrn_event(region);
+	bit -= scorpion_get_pmresrn_event(0);
+	bit += group;
+	/*
+	 * Lower bits are reserved for use by the counters (see
+	 * armv7pmu_get_event_idx() for more info)
+	 */
+	bit += ARMV7_IDX_COUNTER_LAST(cpu_pmu) + 1;
+
+	return bit;
+}
+
+/*
+ * We check for column exclusion constraints here.
+ * Two events cant use the same group within a pmresr register.
+ */
+static int scorpion_pmu_get_event_idx(struct pmu_hw_events *cpuc,
+				   struct perf_event *event)
+{
+	int idx;
+	int bit = -1;
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned int region = EVENT_REGION(hwc->config_base);
+	unsigned int group = EVENT_GROUP(hwc->config_base);
+	bool venum_event = EVENT_VENUM(hwc->config_base);
+	bool scorpion_event = EVENT_CPU(hwc->config_base);
+
+	if (venum_event || scorpion_event) {
+		/* Ignore invalid events */
+		if (group > 3 || region > 3)
+			return -EINVAL;
+
+		bit = scorpion_event_to_bit(event, region, group);
+		if (test_and_set_bit(bit, cpuc->used_mask))
+			return -EAGAIN;
+	}
+
+	idx = armv7pmu_get_event_idx(cpuc, event);
+	if (idx < 0 && bit >= 0)
+		clear_bit(bit, cpuc->used_mask);
+
+	return idx;
+}
+
+static void scorpion_pmu_clear_event_idx(struct pmu_hw_events *cpuc,
+				      struct perf_event *event)
+{
+	int bit;
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned int region = EVENT_REGION(hwc->config_base);
+	unsigned int group = EVENT_GROUP(hwc->config_base);
+	bool venum_event = EVENT_VENUM(hwc->config_base);
+	bool scorpion_event = EVENT_CPU(hwc->config_base);
+
+	if (venum_event || scorpion_event) {
+		bit = scorpion_event_to_bit(event, region, group);
+		clear_bit(bit, cpuc->used_mask);
+	}
+}
+
+static int scorpion_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv7pmu_init(cpu_pmu);
+	cpu_pmu->name		= "armv7_scorpion";
+	cpu_pmu->map_event	= scorpion_map_event;
+	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
+	cpu_pmu->reset		= scorpion_pmu_reset;
+	cpu_pmu->enable		= scorpion_pmu_enable_event;
+	cpu_pmu->disable	= scorpion_pmu_disable_event;
+	cpu_pmu->get_event_idx	= scorpion_pmu_get_event_idx;
+	cpu_pmu->clear_event_idx = scorpion_pmu_clear_event_idx;
+	return 0;
+}
+
+static int scorpion_mp_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv7pmu_init(cpu_pmu);
+	cpu_pmu->name		= "armv7_scorpion_mp";
+	cpu_pmu->map_event	= scorpion_map_event;
+	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
+	cpu_pmu->reset		= scorpion_pmu_reset;
+	cpu_pmu->enable		= scorpion_pmu_enable_event;
+	cpu_pmu->disable	= scorpion_pmu_disable_event;
+	cpu_pmu->get_event_idx	= scorpion_pmu_get_event_idx;
+	cpu_pmu->clear_event_idx = scorpion_pmu_clear_event_idx;
+	return 0;
+}
 #else
 static inline int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
 {
@@ -1498,4 +1895,14 @@ static inline int krait_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	return -ENODEV;
 }
+
+static inline int scorpion_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return -ENODEV;
+}
+
+static inline int scorpion_mp_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return -ENODEV;
+}
 #endif	/* CONFIG_CPU_V7 */
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index fdfa3a78ec8c..f192a2a41719 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -17,12 +17,9 @@
 #include <linux/stddef.h>
 #include <linux/unistd.h>
 #include <linux/user.h>
-#include <linux/delay.h>
-#include <linux/reboot.h>
 #include <linux/interrupt.h>
 #include <linux/kallsyms.h>
 #include <linux/init.h>
-#include <linux/cpu.h>
 #include <linux/elfcore.h>
 #include <linux/pm.h>
 #include <linux/tick.h>
@@ -31,16 +28,14 @@
 #include <linux/random.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/leds.h>
-#include <linux/reboot.h>
 
-#include <asm/cacheflush.h>
-#include <asm/idmap.h>
 #include <asm/processor.h>
 #include <asm/thread_notify.h>
 #include <asm/stacktrace.h>
 #include <asm/system_misc.h>
 #include <asm/mach/time.h>
 #include <asm/tls.h>
+#include <asm/vdso.h>
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 #include <linux/stackprotector.h>
@@ -59,69 +54,6 @@ static const char *isa_modes[] __maybe_unused = {
   "ARM" , "Thumb" , "Jazelle", "ThumbEE"
 };
 
-extern void call_with_stack(void (*fn)(void *), void *arg, void *sp);
-typedef void (*phys_reset_t)(unsigned long);
-
-/*
- * A temporary stack to use for CPU reset. This is static so that we
- * don't clobber it with the identity mapping. When running with this
- * stack, any references to the current task *will not work* so you
- * should really do as little as possible before jumping to your reset
- * code.
- */
-static u64 soft_restart_stack[16];
-
-static void __soft_restart(void *addr)
-{
-	phys_reset_t phys_reset;
-
-	/* Take out a flat memory mapping. */
-	setup_mm_for_reboot();
-
-	/* Clean and invalidate caches */
-	flush_cache_all();
-
-	/* Turn off caching */
-	cpu_proc_fin();
-
-	/* Push out any further dirty data, and ensure cache is empty */
-	flush_cache_all();
-
-	/* Switch to the identity mapping. */
-	phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset);
-	phys_reset((unsigned long)addr);
-
-	/* Should never get here. */
-	BUG();
-}
-
-void soft_restart(unsigned long addr)
-{
-	u64 *stack = soft_restart_stack + ARRAY_SIZE(soft_restart_stack);
-
-	/* Disable interrupts first */
-	raw_local_irq_disable();
-	local_fiq_disable();
-
-	/* Disable the L2 if we're the last man standing. */
-	if (num_online_cpus() == 1)
-		outer_disable();
-
-	/* Change to the new stack and continue with the reset. */
-	call_with_stack(__soft_restart, (void *)addr, (void *)stack);
-
-	/* Should never get here. */
-	BUG();
-}
-
-/*
- * Function pointers to optional machine specific functions
- */
-void (*pm_power_off)(void);
-EXPORT_SYMBOL(pm_power_off);
-
-void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
-
 /*
  * This is our default idle handler.
  */
@@ -166,79 +98,6 @@ void arch_cpu_idle_dead(void)
 }
 #endif
 
-/*
- * Called by kexec, immediately prior to machine_kexec().
- *
- * This must completely disable all secondary CPUs; simply causing those CPUs
- * to execute e.g. a RAM-based pin loop is not sufficient. This allows the
- * kexec'd kernel to use any and all RAM as it sees fit, without having to
- * avoid any code or data used by any SW CPU pin loop. The CPU hotplug
- * functionality embodied in disable_nonboot_cpus() to achieve this.
- */
-void machine_shutdown(void)
-{
-	disable_nonboot_cpus();
-}
-
-/*
- * Halting simply requires that the secondary CPUs stop performing any
- * activity (executing tasks, handling interrupts). smp_send_stop()
- * achieves this.
- */
-void machine_halt(void)
-{
-	local_irq_disable();
-	smp_send_stop();
-
-	local_irq_disable();
-	while (1);
-}
-
-/*
- * Power-off simply requires that the secondary CPUs stop performing any
- * activity (executing tasks, handling interrupts). smp_send_stop()
- * achieves this. When the system power is turned off, it will take all CPUs
- * with it.
- */
-void machine_power_off(void)
-{
-	local_irq_disable();
-	smp_send_stop();
-
-	if (pm_power_off)
-		pm_power_off();
-}
-
-/*
- * Restart requires that the secondary CPUs stop performing any activity
- * while the primary CPU resets the system. Systems with a single CPU can
- * use soft_restart() as their machine descriptor's .restart hook, since that
- * will cause the only available CPU to reset. Systems with multiple CPUs must
- * provide a HW restart implementation, to ensure that all CPUs reset at once.
- * This is required so that any code running after reset on the primary CPU
- * doesn't have to co-ordinate with other CPUs to ensure they aren't still
- * executing pre-reset code, and using RAM that the primary CPU's code wishes
- * to use. Implementing such co-ordination would be essentially impossible.
- */
-void machine_restart(char *cmd)
-{
-	local_irq_disable();
-	smp_send_stop();
-
-	if (arm_pm_restart)
-		arm_pm_restart(reboot_mode, cmd);
-	else
-		do_kernel_restart(cmd);
-
-	/* Give a grace period for failure to restart of 1s */
-	mdelay(1000);
-
-	/* Whoops - the platform was unable to reboot. Tell the user! */
-	printk("Reboot failed -- System halted\n");
-	local_irq_disable();
-	while (1);
-}
-
 void __show_regs(struct pt_regs *regs)
 {
 	unsigned long flags;
@@ -475,7 +334,7 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 }
 
 /* If possible, provide a placement hint at a random offset from the
- * stack for the signal page.
+ * stack for the sigpage and vdso pages.
  */
 static unsigned long sigpage_addr(const struct mm_struct *mm,
 				  unsigned int npages)
@@ -519,6 +378,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
+	unsigned long npages;
 	unsigned long addr;
 	unsigned long hint;
 	int ret = 0;
@@ -528,9 +388,12 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	if (!signal_page)
 		return -ENOMEM;
 
+	npages = 1; /* for sigpage */
+	npages += vdso_total_pages;
+
 	down_write(&mm->mmap_sem);
-	hint = sigpage_addr(mm, 1);
-	addr = get_unmapped_area(NULL, hint, PAGE_SIZE, 0, 0);
+	hint = sigpage_addr(mm, npages);
+	addr = get_unmapped_area(NULL, hint, npages << PAGE_SHIFT, 0, 0);
 	if (IS_ERR_VALUE(addr)) {
 		ret = addr;
 		goto up_fail;
@@ -547,6 +410,12 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 
 	mm->context.sigpage = addr;
 
+	/* Unlike the sigpage, failure to install the vdso is unlikely
+	 * to be fatal to the process, so no error check needed
+	 * here.
+	 */
+	arm_install_vdso(mm, addr + PAGE_SIZE);
+
  up_fail:
 	up_write(&mm->mmap_sem);
 	return ret;
diff --git a/arch/arm/kernel/psci-call.S b/arch/arm/kernel/psci-call.S
new file mode 100644
index 000000000000..a78e9e1e206d
--- /dev/null
+++ b/arch/arm/kernel/psci-call.S
@@ -0,0 +1,31 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2015 ARM Limited
+ *
+ * Author: Mark Rutland <mark.rutland@arm.com>
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/opcodes-sec.h>
+#include <asm/opcodes-virt.h>
+
+/* int __invoke_psci_fn_hvc(u32 function_id, u32 arg0, u32 arg1, u32 arg2) */
+ENTRY(__invoke_psci_fn_hvc)
+	__HVC(0)
+	bx	lr
+ENDPROC(__invoke_psci_fn_hvc)
+
+/* int __invoke_psci_fn_smc(u32 function_id, u32 arg0, u32 arg1, u32 arg2) */
+ENTRY(__invoke_psci_fn_smc)
+	__SMC(0)
+	bx	lr
+ENDPROC(__invoke_psci_fn_smc)
diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c
index f73891b6b730..f90fdf4ce7c7 100644
--- a/arch/arm/kernel/psci.c
+++ b/arch/arm/kernel/psci.c
@@ -23,8 +23,6 @@
 
 #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>
 
@@ -33,6 +31,9 @@ struct psci_operations psci_ops;
 static int (*invoke_psci_fn)(u32, u32, u32, u32);
 typedef int (*psci_initcall_t)(const struct device_node *);
 
+asmlinkage int __invoke_psci_fn_hvc(u32, u32, u32, u32);
+asmlinkage int __invoke_psci_fn_smc(u32, u32, u32, u32);
+
 enum psci_function {
 	PSCI_FN_CPU_SUSPEND,
 	PSCI_FN_CPU_ON,
@@ -71,40 +72,6 @@ static u32 psci_power_state_pack(struct psci_power_state state)
 		 & PSCI_0_2_POWER_STATE_AFFL_MASK);
 }
 
-/*
- * The following two functions are invoked via the invoke_psci_fn pointer
- * and will not be inlined, allowing us to piggyback on the AAPCS.
- */
-static noinline int __invoke_psci_fn_hvc(u32 function_id, u32 arg0, u32 arg1,
-					 u32 arg2)
-{
-	asm volatile(
-			__asmeq("%0", "r0")
-			__asmeq("%1", "r1")
-			__asmeq("%2", "r2")
-			__asmeq("%3", "r3")
-			__HVC(0)
-		: "+r" (function_id)
-		: "r" (arg0), "r" (arg1), "r" (arg2));
-
-	return function_id;
-}
-
-static noinline int __invoke_psci_fn_smc(u32 function_id, u32 arg0, u32 arg1,
-					 u32 arg2)
-{
-	asm volatile(
-			__asmeq("%0", "r0")
-			__asmeq("%1", "r1")
-			__asmeq("%2", "r2")
-			__asmeq("%3", "r3")
-			__SMC(0)
-		: "+r" (function_id)
-		: "r" (arg0), "r" (arg1), "r" (arg2));
-
-	return function_id;
-}
-
 static int psci_get_version(void)
 {
 	int err;
diff --git a/arch/arm/kernel/reboot.c b/arch/arm/kernel/reboot.c
new file mode 100644
index 000000000000..1a4d232796be
--- /dev/null
+++ b/arch/arm/kernel/reboot.c
@@ -0,0 +1,155 @@
+/*
+ *  Copyright (C) 1996-2000 Russell King - Converted to ARM.
+ *  Original Copyright (C) 1995  Linus Torvalds
+ * 
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/reboot.h>
+
+#include <asm/cacheflush.h>
+#include <asm/idmap.h>
+
+#include "reboot.h"
+
+typedef void (*phys_reset_t)(unsigned long);
+
+/*
+ * Function pointers to optional machine specific functions
+ */
+void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
+void (*pm_power_off)(void);
+EXPORT_SYMBOL(pm_power_off);
+
+/*
+ * A temporary stack to use for CPU reset. This is static so that we
+ * don't clobber it with the identity mapping. When running with this
+ * stack, any references to the current task *will not work* so you
+ * should really do as little as possible before jumping to your reset
+ * code.
+ */
+static u64 soft_restart_stack[16];
+
+static void __soft_restart(void *addr)
+{
+	phys_reset_t phys_reset;
+
+	/* Take out a flat memory mapping. */
+	setup_mm_for_reboot();
+
+	/* Clean and invalidate caches */
+	flush_cache_all();
+
+	/* Turn off caching */
+	cpu_proc_fin();
+
+	/* Push out any further dirty data, and ensure cache is empty */
+	flush_cache_all();
+
+	/* Switch to the identity mapping. */
+	phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset);
+	phys_reset((unsigned long)addr);
+
+	/* Should never get here. */
+	BUG();
+}
+
+void _soft_restart(unsigned long addr, bool disable_l2)
+{
+	u64 *stack = soft_restart_stack + ARRAY_SIZE(soft_restart_stack);
+
+	/* Disable interrupts first */
+	raw_local_irq_disable();
+	local_fiq_disable();
+
+	/* Disable the L2 if we're the last man standing. */
+	if (disable_l2)
+		outer_disable();
+
+	/* Change to the new stack and continue with the reset. */
+	call_with_stack(__soft_restart, (void *)addr, (void *)stack);
+
+	/* Should never get here. */
+	BUG();
+}
+
+void soft_restart(unsigned long addr)
+{
+	_soft_restart(addr, num_online_cpus() == 1);
+}
+
+/*
+ * Called by kexec, immediately prior to machine_kexec().
+ *
+ * This must completely disable all secondary CPUs; simply causing those CPUs
+ * to execute e.g. a RAM-based pin loop is not sufficient. This allows the
+ * kexec'd kernel to use any and all RAM as it sees fit, without having to
+ * avoid any code or data used by any SW CPU pin loop. The CPU hotplug
+ * functionality embodied in disable_nonboot_cpus() to achieve this.
+ */
+void machine_shutdown(void)
+{
+	disable_nonboot_cpus();
+}
+
+/*
+ * Halting simply requires that the secondary CPUs stop performing any
+ * activity (executing tasks, handling interrupts). smp_send_stop()
+ * achieves this.
+ */
+void machine_halt(void)
+{
+	local_irq_disable();
+	smp_send_stop();
+
+	local_irq_disable();
+	while (1);
+}
+
+/*
+ * Power-off simply requires that the secondary CPUs stop performing any
+ * activity (executing tasks, handling interrupts). smp_send_stop()
+ * achieves this. When the system power is turned off, it will take all CPUs
+ * with it.
+ */
+void machine_power_off(void)
+{
+	local_irq_disable();
+	smp_send_stop();
+
+	if (pm_power_off)
+		pm_power_off();
+}
+
+/*
+ * Restart requires that the secondary CPUs stop performing any activity
+ * while the primary CPU resets the system. Systems with a single CPU can
+ * use soft_restart() as their machine descriptor's .restart hook, since that
+ * will cause the only available CPU to reset. Systems with multiple CPUs must
+ * provide a HW restart implementation, to ensure that all CPUs reset at once.
+ * This is required so that any code running after reset on the primary CPU
+ * doesn't have to co-ordinate with other CPUs to ensure they aren't still
+ * executing pre-reset code, and using RAM that the primary CPU's code wishes
+ * to use. Implementing such co-ordination would be essentially impossible.
+ */
+void machine_restart(char *cmd)
+{
+	local_irq_disable();
+	smp_send_stop();
+
+	if (arm_pm_restart)
+		arm_pm_restart(reboot_mode, cmd);
+	else
+		do_kernel_restart(cmd);
+
+	/* Give a grace period for failure to restart of 1s */
+	mdelay(1000);
+
+	/* Whoops - the platform was unable to reboot. Tell the user! */
+	printk("Reboot failed -- System halted\n");
+	local_irq_disable();
+	while (1);
+}
diff --git a/arch/arm/kernel/reboot.h b/arch/arm/kernel/reboot.h
new file mode 100644
index 000000000000..bf7a0b1f076e
--- /dev/null
+++ b/arch/arm/kernel/reboot.h
@@ -0,0 +1,7 @@
+#ifndef REBOOT_H
+#define REBOOT_H
+
+extern void call_with_stack(void (*fn)(void *), void *arg, void *sp);
+extern void _soft_restart(unsigned long addr, bool disable_l2);
+
+#endif
diff --git a/arch/arm/kernel/return_address.c b/arch/arm/kernel/return_address.c
index 24b4a04846eb..36ed35073289 100644
--- a/arch/arm/kernel/return_address.c
+++ b/arch/arm/kernel/return_address.c
@@ -56,8 +56,6 @@ void *return_address(unsigned int level)
 		return NULL;
 }
 
-#else /* if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND) */
-
-#endif /* if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND) / else */
+#endif /* if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND) */
 
 EXPORT_SYMBOL_GPL(return_address);
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 1d60bebea4b8..6c777e908a24 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -372,30 +372,48 @@ void __init early_print(const char *str, ...)
 
 static void __init cpuid_init_hwcaps(void)
 {
-	unsigned int divide_instrs, vmsa;
+	int block;
+	u32 isar5;
 
 	if (cpu_architecture() < CPU_ARCH_ARMv7)
 		return;
 
-	divide_instrs = (read_cpuid_ext(CPUID_EXT_ISAR0) & 0x0f000000) >> 24;
-
-	switch (divide_instrs) {
-	case 2:
+	block = cpuid_feature_extract(CPUID_EXT_ISAR0, 24);
+	if (block >= 2)
 		elf_hwcap |= HWCAP_IDIVA;
-	case 1:
+	if (block >= 1)
 		elf_hwcap |= HWCAP_IDIVT;
-	}
 
 	/* LPAE implies atomic ldrd/strd instructions */
-	vmsa = (read_cpuid_ext(CPUID_EXT_MMFR0) & 0xf) >> 0;
-	if (vmsa >= 5)
+	block = cpuid_feature_extract(CPUID_EXT_MMFR0, 0);
+	if (block >= 5)
 		elf_hwcap |= HWCAP_LPAE;
+
+	/* check for supported v8 Crypto instructions */
+	isar5 = read_cpuid_ext(CPUID_EXT_ISAR5);
+
+	block = cpuid_feature_extract_field(isar5, 4);
+	if (block >= 2)
+		elf_hwcap2 |= HWCAP2_PMULL;
+	if (block >= 1)
+		elf_hwcap2 |= HWCAP2_AES;
+
+	block = cpuid_feature_extract_field(isar5, 8);
+	if (block >= 1)
+		elf_hwcap2 |= HWCAP2_SHA1;
+
+	block = cpuid_feature_extract_field(isar5, 12);
+	if (block >= 1)
+		elf_hwcap2 |= HWCAP2_SHA2;
+
+	block = cpuid_feature_extract_field(isar5, 16);
+	if (block >= 1)
+		elf_hwcap2 |= HWCAP2_CRC32;
 }
 
 static void __init elf_hwcap_fixup(void)
 {
 	unsigned id = read_cpuid_id();
-	unsigned sync_prim;
 
 	/*
 	 * HWCAP_TLS is available only on 1136 r1p0 and later,
@@ -416,9 +434,9 @@ static void __init elf_hwcap_fixup(void)
 	 * avoid advertising SWP; it may not be atomic with
 	 * multiprocessing cores.
 	 */
-	sync_prim = ((read_cpuid_ext(CPUID_EXT_ISAR3) >> 8) & 0xf0) |
-		    ((read_cpuid_ext(CPUID_EXT_ISAR4) >> 20) & 0x0f);
-	if (sync_prim >= 0x13)
+	if (cpuid_feature_extract(CPUID_EXT_ISAR3, 12) > 1 ||
+	    (cpuid_feature_extract(CPUID_EXT_ISAR3, 12) == 1 &&
+	     cpuid_feature_extract(CPUID_EXT_ISAR3, 20) >= 3))
 		elf_hwcap &= ~HWCAP_SWP;
 }
 
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index e1e60e5a7a27..7d37bfc50830 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -116,14 +116,7 @@ cpu_resume_after_mmu:
 	ldmfd	sp!, {r4 - r11, pc}
 ENDPROC(cpu_resume_after_mmu)
 
-/*
- * Note: Yes, part of the following code is located into the .data section.
- *       This is to allow sleep_save_sp to be accessed with a relative load
- *       while we can't rely on any MMU translation.  We could have put
- *       sleep_save_sp in the .text section as well, but some setups might
- *       insist on it to be truly read-only.
- */
-	.data
+	.text
 	.align
 ENTRY(cpu_resume)
 ARM_BE8(setend be)			@ ensure we are in BE mode
@@ -145,6 +138,8 @@ ARM_BE8(setend be)			@ ensure we are in BE mode
 	compute_mpidr_hash	r1, r4, r5, r6, r0, r3
 1:
 	adr	r0, _sleep_save_sp
+	ldr	r2, [r0]
+	add	r0, r0, r2
 	ldr	r0, [r0, #SLEEP_SAVE_SP_PHYS]
 	ldr	r0, [r0, r1, lsl #2]
 
@@ -156,10 +151,12 @@ THUMB(	bx	r3			)
 ENDPROC(cpu_resume)
 
 	.align 2
+_sleep_save_sp:
+	.long	sleep_save_sp - .
 mpidr_hash_ptr:
 	.long	mpidr_hash - .			@ mpidr_hash struct offset
 
+	.data
 	.type	sleep_save_sp, #object
 ENTRY(sleep_save_sp)
-_sleep_save_sp:
 	.space	SLEEP_SAVE_SP_SZ		@ struct sleep_save_sp
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 86ef244c5a24..cca5b8758185 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -145,6 +145,11 @@ void __init smp_init_cpus(void)
 		smp_ops.smp_init_cpus();
 }
 
+int platform_can_secondary_boot(void)
+{
+	return !!smp_ops.smp_boot_secondary;
+}
+
 int platform_can_cpu_hotplug(void)
 {
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index afdd51e30bec..1361756782c7 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/arch/arm/kernel/swp_emulate.c
@@ -42,7 +42,7 @@
 	"	cmp		%0, #0\n"			\
 	"	movne		%0, %4\n"			\
 	"2:\n"							\
-	"	.section	 .fixup,\"ax\"\n"		\
+	"	.section	 .text.fixup,\"ax\"\n"		\
 	"	.align		2\n"				\
 	"3:	mov		%0, %5\n"			\
 	"	b		2b\n"				\
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
new file mode 100644
index 000000000000..efe17dd9b921
--- /dev/null
+++ b/arch/arm/kernel/vdso.c
@@ -0,0 +1,337 @@
+/*
+ * Adapted from arm64 version.
+ *
+ * Copyright (C) 2012 ARM Limited
+ * Copyright (C) 2015 Mentor Graphics Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/elf.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/of.h>
+#include <linux/printk.h>
+#include <linux/slab.h>
+#include <linux/timekeeper_internal.h>
+#include <linux/vmalloc.h>
+#include <asm/arch_timer.h>
+#include <asm/barrier.h>
+#include <asm/cacheflush.h>
+#include <asm/page.h>
+#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
+#include <clocksource/arm_arch_timer.h>
+
+#define MAX_SYMNAME	64
+
+static struct page **vdso_text_pagelist;
+
+/* Total number of pages needed for the data and text portions of the VDSO. */
+unsigned int vdso_total_pages __read_mostly;
+
+/*
+ * The VDSO data page.
+ */
+static union vdso_data_store vdso_data_store __page_aligned_data;
+static struct vdso_data *vdso_data = &vdso_data_store.data;
+
+static struct page *vdso_data_page;
+static struct vm_special_mapping vdso_data_mapping = {
+	.name = "[vvar]",
+	.pages = &vdso_data_page,
+};
+
+static struct vm_special_mapping vdso_text_mapping = {
+	.name = "[vdso]",
+};
+
+struct elfinfo {
+	Elf32_Ehdr	*hdr;		/* ptr to ELF */
+	Elf32_Sym	*dynsym;	/* ptr to .dynsym section */
+	unsigned long	dynsymsize;	/* size of .dynsym section */
+	char		*dynstr;	/* ptr to .dynstr section */
+};
+
+/* Cached result of boot-time check for whether the arch timer exists,
+ * and if so, whether the virtual counter is useable.
+ */
+static bool cntvct_ok __read_mostly;
+
+static bool __init cntvct_functional(void)
+{
+	struct device_node *np;
+	bool ret = false;
+
+	if (!IS_ENABLED(CONFIG_ARM_ARCH_TIMER))
+		goto out;
+
+	/* The arm_arch_timer core should export
+	 * arch_timer_use_virtual or similar so we don't have to do
+	 * this.
+	 */
+	np = of_find_compatible_node(NULL, NULL, "arm,armv7-timer");
+	if (!np)
+		goto out_put;
+
+	if (of_property_read_bool(np, "arm,cpu-registers-not-fw-configured"))
+		goto out_put;
+
+	ret = true;
+
+out_put:
+	of_node_put(np);
+out:
+	return ret;
+}
+
+static void * __init find_section(Elf32_Ehdr *ehdr, const char *name,
+				  unsigned long *size)
+{
+	Elf32_Shdr *sechdrs;
+	unsigned int i;
+	char *secnames;
+
+	/* Grab section headers and strings so we can tell who is who */
+	sechdrs = (void *)ehdr + ehdr->e_shoff;
+	secnames = (void *)ehdr + sechdrs[ehdr->e_shstrndx].sh_offset;
+
+	/* Find the section they want */
+	for (i = 1; i < ehdr->e_shnum; i++) {
+		if (strcmp(secnames + sechdrs[i].sh_name, name) == 0) {
+			if (size)
+				*size = sechdrs[i].sh_size;
+			return (void *)ehdr + sechdrs[i].sh_offset;
+		}
+	}
+
+	if (size)
+		*size = 0;
+	return NULL;
+}
+
+static Elf32_Sym * __init find_symbol(struct elfinfo *lib, const char *symname)
+{
+	unsigned int i;
+
+	for (i = 0; i < (lib->dynsymsize / sizeof(Elf32_Sym)); i++) {
+		char name[MAX_SYMNAME], *c;
+
+		if (lib->dynsym[i].st_name == 0)
+			continue;
+		strlcpy(name, lib->dynstr + lib->dynsym[i].st_name,
+			MAX_SYMNAME);
+		c = strchr(name, '@');
+		if (c)
+			*c = 0;
+		if (strcmp(symname, name) == 0)
+			return &lib->dynsym[i];
+	}
+	return NULL;
+}
+
+static void __init vdso_nullpatch_one(struct elfinfo *lib, const char *symname)
+{
+	Elf32_Sym *sym;
+
+	sym = find_symbol(lib, symname);
+	if (!sym)
+		return;
+
+	sym->st_name = 0;
+}
+
+static void __init patch_vdso(void *ehdr)
+{
+	struct elfinfo einfo;
+
+	einfo = (struct elfinfo) {
+		.hdr = ehdr,
+	};
+
+	einfo.dynsym = find_section(einfo.hdr, ".dynsym", &einfo.dynsymsize);
+	einfo.dynstr = find_section(einfo.hdr, ".dynstr", NULL);
+
+	/* If the virtual counter is absent or non-functional we don't
+	 * want programs to incur the slight additional overhead of
+	 * dispatching through the VDSO only to fall back to syscalls.
+	 */
+	if (!cntvct_ok) {
+		vdso_nullpatch_one(&einfo, "__vdso_gettimeofday");
+		vdso_nullpatch_one(&einfo, "__vdso_clock_gettime");
+	}
+}
+
+static int __init vdso_init(void)
+{
+	unsigned int text_pages;
+	int i;
+
+	if (memcmp(&vdso_start, "\177ELF", 4)) {
+		pr_err("VDSO is not a valid ELF object!\n");
+		return -ENOEXEC;
+	}
+
+	text_pages = (&vdso_end - &vdso_start) >> PAGE_SHIFT;
+	pr_debug("vdso: %i text pages at base %p\n", text_pages, &vdso_start);
+
+	/* Allocate the VDSO text pagelist */
+	vdso_text_pagelist = kcalloc(text_pages, sizeof(struct page *),
+				     GFP_KERNEL);
+	if (vdso_text_pagelist == NULL)
+		return -ENOMEM;
+
+	/* Grab the VDSO data page. */
+	vdso_data_page = virt_to_page(vdso_data);
+
+	/* Grab the VDSO text pages. */
+	for (i = 0; i < text_pages; i++) {
+		struct page *page;
+
+		page = virt_to_page(&vdso_start + i * PAGE_SIZE);
+		vdso_text_pagelist[i] = page;
+	}
+
+	vdso_text_mapping.pages = vdso_text_pagelist;
+
+	vdso_total_pages = 1; /* for the data/vvar page */
+	vdso_total_pages += text_pages;
+
+	cntvct_ok = cntvct_functional();
+
+	patch_vdso(&vdso_start);
+
+	return 0;
+}
+arch_initcall(vdso_init);
+
+static int install_vvar(struct mm_struct *mm, unsigned long addr)
+{
+	struct vm_area_struct *vma;
+
+	vma = _install_special_mapping(mm, addr, PAGE_SIZE,
+				       VM_READ | VM_MAYREAD,
+				       &vdso_data_mapping);
+
+	return IS_ERR(vma) ? PTR_ERR(vma) : 0;
+}
+
+/* assumes mmap_sem is write-locked */
+void arm_install_vdso(struct mm_struct *mm, unsigned long addr)
+{
+	struct vm_area_struct *vma;
+	unsigned long len;
+
+	mm->context.vdso = 0;
+
+	if (vdso_text_pagelist == NULL)
+		return;
+
+	if (install_vvar(mm, addr))
+		return;
+
+	/* Account for vvar page. */
+	addr += PAGE_SIZE;
+	len = (vdso_total_pages - 1) << PAGE_SHIFT;
+
+	vma = _install_special_mapping(mm, addr, len,
+		VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC,
+		&vdso_text_mapping);
+
+	if (!IS_ERR(vma))
+		mm->context.vdso = addr;
+}
+
+static void vdso_write_begin(struct vdso_data *vdata)
+{
+	++vdso_data->seq_count;
+	smp_wmb(); /* Pairs with smp_rmb in vdso_read_retry */
+}
+
+static void vdso_write_end(struct vdso_data *vdata)
+{
+	smp_wmb(); /* Pairs with smp_rmb in vdso_read_begin */
+	++vdso_data->seq_count;
+}
+
+static bool tk_is_cntvct(const struct timekeeper *tk)
+{
+	if (!IS_ENABLED(CONFIG_ARM_ARCH_TIMER))
+		return false;
+
+	if (strcmp(tk->tkr_mono.clock->name, "arch_sys_counter") != 0)
+		return false;
+
+	return true;
+}
+
+/**
+ * update_vsyscall - update the vdso data page
+ *
+ * Increment the sequence counter, making it odd, indicating to
+ * userspace that an update is in progress.  Update the fields used
+ * for coarse clocks and, if the architected system timer is in use,
+ * the fields used for high precision clocks.  Increment the sequence
+ * counter again, making it even, indicating to userspace that the
+ * update is finished.
+ *
+ * Userspace is expected to sample seq_count before reading any other
+ * fields from the data page.  If seq_count is odd, userspace is
+ * expected to wait until it becomes even.  After copying data from
+ * the page, userspace must sample seq_count again; if it has changed
+ * from its previous value, userspace must retry the whole sequence.
+ *
+ * Calls to update_vsyscall are serialized by the timekeeping core.
+ */
+void update_vsyscall(struct timekeeper *tk)
+{
+	struct timespec xtime_coarse;
+	struct timespec64 *wtm = &tk->wall_to_monotonic;
+
+	if (!cntvct_ok) {
+		/* The entry points have been zeroed, so there is no
+		 * point in updating the data page.
+		 */
+		return;
+	}
+
+	vdso_write_begin(vdso_data);
+
+	xtime_coarse = __current_kernel_time();
+	vdso_data->tk_is_cntvct			= tk_is_cntvct(tk);
+	vdso_data->xtime_coarse_sec		= xtime_coarse.tv_sec;
+	vdso_data->xtime_coarse_nsec		= xtime_coarse.tv_nsec;
+	vdso_data->wtm_clock_sec		= wtm->tv_sec;
+	vdso_data->wtm_clock_nsec		= wtm->tv_nsec;
+
+	if (vdso_data->tk_is_cntvct) {
+		vdso_data->cs_cycle_last	= tk->tkr_mono.cycle_last;
+		vdso_data->xtime_clock_sec	= tk->xtime_sec;
+		vdso_data->xtime_clock_snsec	= tk->tkr_mono.xtime_nsec;
+		vdso_data->cs_mult		= tk->tkr_mono.mult;
+		vdso_data->cs_shift		= tk->tkr_mono.shift;
+		vdso_data->cs_mask		= tk->tkr_mono.mask;
+	}
+
+	vdso_write_end(vdso_data);
+
+	flush_dcache_page(virt_to_page(vdso_data));
+}
+
+void update_vsyscall_tz(void)
+{
+	vdso_data->tz_minuteswest	= sys_tz.tz_minuteswest;
+	vdso_data->tz_dsttime		= sys_tz.tz_dsttime;
+	flush_dcache_page(virt_to_page(vdso_data));
+}
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index b31aa73e8076..7a301be9ac67 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -74,7 +74,7 @@ SECTIONS
 		ARM_EXIT_DISCARD(EXIT_DATA)
 		EXIT_CALL
 #ifndef CONFIG_MMU
-		*(.fixup)
+		*(.text.fixup)
 		*(__ex_table)
 #endif
 #ifndef CONFIG_SMP_ON_UP
@@ -100,6 +100,7 @@ SECTIONS
 
 	.text : {			/* Real text segment		*/
 		_stext = .;		/* Text and read-only data	*/
+			IDMAP_TEXT
 			__exception_text_start = .;
 			*(.exception.text)
 			__exception_text_end = .;
@@ -108,10 +109,6 @@ SECTIONS
 			SCHED_TEXT
 			LOCK_TEXT
 			KPROBES_TEXT
-			IDMAP_TEXT
-#ifdef CONFIG_MMU
-			*(.fixup)
-#endif
 			*(.gnu.warning)
 			*(.glue_7)
 			*(.glue_7t)