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));