Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:
 "The big highlight is support for the Scalable Vector Extension (SVE)
  which required extensive ABI work to ensure we don't break existing
  applications by blowing away their signal stack with the rather large
  new vector context (<= 2 kbit per vector register). There's further
  work to be done optimising things like exception return, but the ABI
  is solid now.

  Much of the line count comes from some new PMU drivers we have, but
  they're pretty self-contained and I suspect we'll have more of them in
  future.

  Plenty of acronym soup here:

   - initial support for the Scalable Vector Extension (SVE)

   - improved handling for SError interrupts (required to handle RAS
     events)

   - enable GCC support for 128-bit integer types

   - remove kernel text addresses from backtraces and register dumps

   - use of WFE to implement long delay()s

   - ACPI IORT updates from Lorenzo Pieralisi

   - perf PMU driver for the Statistical Profiling Extension (SPE)

   - perf PMU driver for Hisilicon's system PMUs

   - misc cleanups and non-critical fixes"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (97 commits)
  arm64: Make ARMV8_DEPRECATED depend on SYSCTL
  arm64: Implement __lshrti3 library function
  arm64: support __int128 on gcc 5+
  arm64/sve: Add documentation
  arm64/sve: Detect SVE and activate runtime support
  arm64/sve: KVM: Hide SVE from CPU features exposed to guests
  arm64/sve: KVM: Treat guest SVE use as undefined instruction execution
  arm64/sve: KVM: Prevent guests from using SVE
  arm64/sve: Add sysctl to set the default vector length for new processes
  arm64/sve: Add prctl controls for userspace vector length management
  arm64/sve: ptrace and ELF coredump support
  arm64/sve: Preserve SVE registers around EFI runtime service calls
  arm64/sve: Preserve SVE registers around kernel-mode NEON use
  arm64/sve: Probe SVE capabilities and usable vector lengths
  arm64: cpufeature: Move sys_caps_initialised declarations
  arm64/sve: Backend logic for setting the vector length
  arm64/sve: Signal handling support
  arm64/sve: Support vector length resetting for new processes
  arm64/sve: Core task context handling
  arm64/sve: Low-level CPU setup
  ...

17 files changed, 3500 insertions, 72 deletions

diff --git a/drivers/acpi/arm64/gtdt.c b/drivers/acpi/arm64/gtdt.c
index 597a737d538f..92f9edf9d11e 100644
--- a/drivers/acpi/arm64/gtdt.c
+++ b/drivers/acpi/arm64/gtdt.c
@@ -199,7 +199,7 @@ static int __init gtdt_parse_timer_block(struct acpi_gtdt_timer_block *block,
 	struct acpi_gtdt_timer_entry *gtdt_frame;
 
 	if (!block->timer_count) {
-		pr_err(FW_BUG "GT block present, but frame count is zero.");
+		pr_err(FW_BUG "GT block present, but frame count is zero.\n");
 		return -ENODEV;
 	}
 
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index de56394dd161..95255ecfae7c 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -88,8 +88,8 @@ static inline int iort_set_fwnode(struct acpi_iort_node *iort_node,
  *
  * Returns: fwnode_handle pointer on success, NULL on failure
  */
-static inline
-struct fwnode_handle *iort_get_fwnode(struct acpi_iort_node *node)
+static inline struct fwnode_handle *iort_get_fwnode(
+			struct acpi_iort_node *node)
 {
 	struct iort_fwnode *curr;
 	struct fwnode_handle *fwnode = NULL;
@@ -126,6 +126,31 @@ static inline void iort_delete_fwnode(struct acpi_iort_node *node)
 	spin_unlock(&iort_fwnode_lock);
 }
 
+/**
+ * iort_get_iort_node() - Retrieve iort_node associated with an fwnode
+ *
+ * @fwnode: fwnode associated with device to be looked-up
+ *
+ * Returns: iort_node pointer on success, NULL on failure
+ */
+static inline struct acpi_iort_node *iort_get_iort_node(
+			struct fwnode_handle *fwnode)
+{
+	struct iort_fwnode *curr;
+	struct acpi_iort_node *iort_node = NULL;
+
+	spin_lock(&iort_fwnode_lock);
+	list_for_each_entry(curr, &iort_fwnode_list, list) {
+		if (curr->fwnode == fwnode) {
+			iort_node = curr->iort_node;
+			break;
+		}
+	}
+	spin_unlock(&iort_fwnode_lock);
+
+	return iort_node;
+}
+
 typedef acpi_status (*iort_find_node_callback)
 	(struct acpi_iort_node *node, void *context);
 
@@ -306,9 +331,8 @@ static int iort_id_map(struct acpi_iort_id_mapping *map, u8 type, u32 rid_in,
 	return 0;
 }
 
-static
-struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
-					u32 *id_out, int index)
+static struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
+					       u32 *id_out, int index)
 {
 	struct acpi_iort_node *parent;
 	struct acpi_iort_id_mapping *map;
@@ -332,7 +356,8 @@ struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
 
 	if (map->flags & ACPI_IORT_ID_SINGLE_MAPPING) {
 		if (node->type == ACPI_IORT_NODE_NAMED_COMPONENT ||
-		    node->type == ACPI_IORT_NODE_PCI_ROOT_COMPLEX) {
+		    node->type == ACPI_IORT_NODE_PCI_ROOT_COMPLEX ||
+		    node->type == ACPI_IORT_NODE_SMMU_V3) {
 			*id_out = map->output_base;
 			return parent;
 		}
@@ -341,6 +366,47 @@ struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
 	return NULL;
 }
 
+#if (ACPI_CA_VERSION > 0x20170929)
+static int iort_get_id_mapping_index(struct acpi_iort_node *node)
+{
+	struct acpi_iort_smmu_v3 *smmu;
+
+	switch (node->type) {
+	case ACPI_IORT_NODE_SMMU_V3:
+		/*
+		 * SMMUv3 dev ID mapping index was introduced in revision 1
+		 * table, not available in revision 0
+		 */
+		if (node->revision < 1)
+			return -EINVAL;
+
+		smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
+		/*
+		 * ID mapping index is only ignored if all interrupts are
+		 * GSIV based
+		 */
+		if (smmu->event_gsiv && smmu->pri_gsiv && smmu->gerr_gsiv
+		    && smmu->sync_gsiv)
+			return -EINVAL;
+
+		if (smmu->id_mapping_index >= node->mapping_count) {
+			pr_err(FW_BUG "[node %p type %d] ID mapping index overflows valid mappings\n",
+			       node, node->type);
+			return -EINVAL;
+		}
+
+		return smmu->id_mapping_index;
+	default:
+		return -EINVAL;
+	}
+}
+#else
+static inline int iort_get_id_mapping_index(struct acpi_iort_node *node)
+{
+	return -EINVAL;
+}
+#endif
+
 static struct acpi_iort_node *iort_node_map_id(struct acpi_iort_node *node,
 					       u32 id_in, u32 *id_out,
 					       u8 type_mask)
@@ -350,7 +416,7 @@ static struct acpi_iort_node *iort_node_map_id(struct acpi_iort_node *node,
 	/* Parse the ID mapping tree to find specified node type */
 	while (node) {
 		struct acpi_iort_id_mapping *map;
-		int i;
+		int i, index;
 
 		if (IORT_TYPE_MASK(node->type) & type_mask) {
 			if (id_out)
@@ -371,8 +437,19 @@ static struct acpi_iort_node *iort_node_map_id(struct acpi_iort_node *node,
 			goto fail_map;
 		}
 
+		/*
+		 * Get the special ID mapping index (if any) and skip its
+		 * associated ID map to prevent erroneous multi-stage
+		 * IORT ID translations.
+		 */
+		index = iort_get_id_mapping_index(node);
+
 		/* Do the ID translation */
 		for (i = 0; i < node->mapping_count; i++, map++) {
+			/* if it is special mapping index, skip it */
+			if (i == index)
+				continue;
+
 			if (!iort_id_map(map, node->type, id, &id))
 				break;
 		}
@@ -392,10 +469,9 @@ fail_map:
 	return NULL;
 }
 
-static
-struct acpi_iort_node *iort_node_map_platform_id(struct acpi_iort_node *node,
-						 u32 *id_out, u8 type_mask,
-						 int index)
+static struct acpi_iort_node *iort_node_map_platform_id(
+		struct acpi_iort_node *node, u32 *id_out, u8 type_mask,
+		int index)
 {
 	struct acpi_iort_node *parent;
 	u32 id;
@@ -424,9 +500,25 @@ static struct acpi_iort_node *iort_find_dev_node(struct device *dev)
 {
 	struct pci_bus *pbus;
 
-	if (!dev_is_pci(dev))
+	if (!dev_is_pci(dev)) {
+		struct acpi_iort_node *node;
+		/*
+		 * scan iort_fwnode_list to see if it's an iort platform
+		 * device (such as SMMU, PMCG),its iort node already cached
+		 * and associated with fwnode when iort platform devices
+		 * were initialized.
+		 */
+		node = iort_get_iort_node(dev->fwnode);
+		if (node)
+			return node;
+
+		/*
+		 * if not, then it should be a platform device defined in
+		 * DSDT/SSDT (with Named Component node in IORT)
+		 */
 		return iort_scan_node(ACPI_IORT_NODE_NAMED_COMPONENT,
 				      iort_match_node_callback, dev);
+	}
 
 	/* Find a PCI root bus */
 	pbus = to_pci_dev(dev)->bus;
@@ -466,16 +558,24 @@ u32 iort_msi_map_rid(struct device *dev, u32 req_id)
  */
 int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id)
 {
-	int i;
+	int i, index;
 	struct acpi_iort_node *node;
 
 	node = iort_find_dev_node(dev);
 	if (!node)
 		return -ENODEV;
 
-	for (i = 0; i < node->mapping_count; i++) {
-		if (iort_node_map_platform_id(node, dev_id, IORT_MSI_TYPE, i))
+	index = iort_get_id_mapping_index(node);
+	/* if there is a valid index, go get the dev_id directly */
+	if (index >= 0) {
+		if (iort_node_get_id(node, dev_id, index))
 			return 0;
+	} else {
+		for (i = 0; i < node->mapping_count; i++) {
+			if (iort_node_map_platform_id(node, dev_id,
+						      IORT_MSI_TYPE, i))
+				return 0;
+		}
 	}
 
 	return -ENODEV;
@@ -538,6 +638,49 @@ struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id)
 	return irq_find_matching_fwnode(handle, DOMAIN_BUS_PCI_MSI);
 }
 
+static void iort_set_device_domain(struct device *dev,
+				   struct acpi_iort_node *node)
+{
+	struct acpi_iort_its_group *its;
+	struct acpi_iort_node *msi_parent;
+	struct acpi_iort_id_mapping *map;
+	struct fwnode_handle *iort_fwnode;
+	struct irq_domain *domain;
+	int index;
+
+	index = iort_get_id_mapping_index(node);
+	if (index < 0)
+		return;
+
+	map = ACPI_ADD_PTR(struct acpi_iort_id_mapping, node,
+			   node->mapping_offset + index * sizeof(*map));
+
+	/* Firmware bug! */
+	if (!map->output_reference ||
+	    !(map->flags & ACPI_IORT_ID_SINGLE_MAPPING)) {
+		pr_err(FW_BUG "[node %p type %d] Invalid MSI mapping\n",
+		       node, node->type);
+		return;
+	}
+
+	msi_parent = ACPI_ADD_PTR(struct acpi_iort_node, iort_table,
+				  map->output_reference);
+
+	if (!msi_parent || msi_parent->type != ACPI_IORT_NODE_ITS_GROUP)
+		return;
+
+	/* Move to ITS specific data */
+	its = (struct acpi_iort_its_group *)msi_parent->node_data;
+
+	iort_fwnode = iort_find_domain_token(its->identifiers[0]);
+	if (!iort_fwnode)
+		return;
+
+	domain = irq_find_matching_fwnode(iort_fwnode, DOMAIN_BUS_PLATFORM_MSI);
+	if (domain)
+		dev_set_msi_domain(dev, domain);
+}
+
 /**
  * iort_get_platform_device_domain() - Find MSI domain related to a
  * platform device
@@ -623,14 +766,14 @@ static inline bool iort_iommu_driver_enabled(u8 type)
 }
 
 #ifdef CONFIG_IOMMU_API
-static inline
-const struct iommu_ops *iort_fwspec_iommu_ops(struct iommu_fwspec *fwspec)
+static inline const struct iommu_ops *iort_fwspec_iommu_ops(
+				struct iommu_fwspec *fwspec)
 {
 	return (fwspec && fwspec->ops) ? fwspec->ops : NULL;
 }
 
-static inline
-int iort_add_device_replay(const struct iommu_ops *ops, struct device *dev)
+static inline int iort_add_device_replay(const struct iommu_ops *ops,
+					 struct device *dev)
 {
 	int err = 0;
 
@@ -640,11 +783,11 @@ int iort_add_device_replay(const struct iommu_ops *ops, struct device *dev)
 	return err;
 }
 #else
-static inline
-const struct iommu_ops *iort_fwspec_iommu_ops(struct iommu_fwspec *fwspec)
+static inline const struct iommu_ops *iort_fwspec_iommu_ops(
+				struct iommu_fwspec *fwspec)
 { return NULL; }
-static inline
-int iort_add_device_replay(const struct iommu_ops *ops, struct device *dev)
+static inline int iort_add_device_replay(const struct iommu_ops *ops,
+					 struct device *dev)
 { return 0; }
 #endif
 
@@ -968,7 +1111,7 @@ static bool __init arm_smmu_v3_is_coherent(struct acpi_iort_node *node)
 	return smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE;
 }
 
-#if defined(CONFIG_ACPI_NUMA) && defined(ACPI_IORT_SMMU_V3_PXM_VALID)
+#if defined(CONFIG_ACPI_NUMA)
 /*
  * set numa proximity domain for smmuv3 device
  */
@@ -1051,34 +1194,34 @@ static bool __init arm_smmu_is_coherent(struct acpi_iort_node *node)
 	return smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK;
 }
 
-struct iort_iommu_config {
+struct iort_dev_config {
 	const char *name;
-	int (*iommu_init)(struct acpi_iort_node *node);
-	bool (*iommu_is_coherent)(struct acpi_iort_node *node);
-	int (*iommu_count_resources)(struct acpi_iort_node *node);
-	void (*iommu_init_resources)(struct resource *res,
+	int (*dev_init)(struct acpi_iort_node *node);
+	bool (*dev_is_coherent)(struct acpi_iort_node *node);
+	int (*dev_count_resources)(struct acpi_iort_node *node);
+	void (*dev_init_resources)(struct resource *res,
 				     struct acpi_iort_node *node);
-	void (*iommu_set_proximity)(struct device *dev,
+	void (*dev_set_proximity)(struct device *dev,
 				    struct acpi_iort_node *node);
 };
 
-static const struct iort_iommu_config iort_arm_smmu_v3_cfg __initconst = {
+static const struct iort_dev_config iort_arm_smmu_v3_cfg __initconst = {
 	.name = "arm-smmu-v3",
-	.iommu_is_coherent = arm_smmu_v3_is_coherent,
-	.iommu_count_resources = arm_smmu_v3_count_resources,
-	.iommu_init_resources = arm_smmu_v3_init_resources,
-	.iommu_set_proximity = arm_smmu_v3_set_proximity,
+	.dev_is_coherent = arm_smmu_v3_is_coherent,
+	.dev_count_resources = arm_smmu_v3_count_resources,
+	.dev_init_resources = arm_smmu_v3_init_resources,
+	.dev_set_proximity = arm_smmu_v3_set_proximity,
 };
 
-static const struct iort_iommu_config iort_arm_smmu_cfg __initconst = {
+static const struct iort_dev_config iort_arm_smmu_cfg __initconst = {
 	.name = "arm-smmu",
-	.iommu_is_coherent = arm_smmu_is_coherent,
-	.iommu_count_resources = arm_smmu_count_resources,
-	.iommu_init_resources = arm_smmu_init_resources
+	.dev_is_coherent = arm_smmu_is_coherent,
+	.dev_count_resources = arm_smmu_count_resources,
+	.dev_init_resources = arm_smmu_init_resources
 };
 
-static __init
-const struct iort_iommu_config *iort_get_iommu_cfg(struct acpi_iort_node *node)
+static __init const struct iort_dev_config *iort_get_dev_cfg(
+			struct acpi_iort_node *node)
 {
 	switch (node->type) {
 	case ACPI_IORT_NODE_SMMU_V3:
@@ -1091,31 +1234,28 @@ const struct iort_iommu_config *iort_get_iommu_cfg(struct acpi_iort_node *node)
 }
 
 /**
- * iort_add_smmu_platform_device() - Allocate a platform device for SMMU
- * @node: Pointer to SMMU ACPI IORT node
+ * iort_add_platform_device() - Allocate a platform device for IORT node
+ * @node: Pointer to device ACPI IORT node
  *
  * Returns: 0 on success, <0 failure
  */
-static int __init iort_add_smmu_platform_device(struct acpi_iort_node *node)
+static int __init iort_add_platform_device(struct acpi_iort_node *node,
+					   const struct iort_dev_config *ops)
 {
 	struct fwnode_handle *fwnode;
 	struct platform_device *pdev;
 	struct resource *r;
 	enum dev_dma_attr attr;
 	int ret, count;
-	const struct iort_iommu_config *ops = iort_get_iommu_cfg(node);
-
-	if (!ops)
-		return -ENODEV;
 
 	pdev = platform_device_alloc(ops->name, PLATFORM_DEVID_AUTO);
 	if (!pdev)
 		return -ENOMEM;
 
-	if (ops->iommu_set_proximity)
-		ops->iommu_set_proximity(&pdev->dev, node);
+	if (ops->dev_set_proximity)
+		ops->dev_set_proximity(&pdev->dev, node);
 
-	count = ops->iommu_count_resources(node);
+	count = ops->dev_count_resources(node);
 
 	r = kcalloc(count, sizeof(*r), GFP_KERNEL);
 	if (!r) {
@@ -1123,7 +1263,7 @@ static int __init iort_add_smmu_platform_device(struct acpi_iort_node *node)
 		goto dev_put;
 	}
 
-	ops->iommu_init_resources(r, node);
+	ops->dev_init_resources(r, node);
 
 	ret = platform_device_add_resources(pdev, r, count);
 	/*
@@ -1158,12 +1298,14 @@ static int __init iort_add_smmu_platform_device(struct acpi_iort_node *node)
 
 	pdev->dev.fwnode = fwnode;
 
-	attr = ops->iommu_is_coherent(node) ?
-			     DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT;
+	attr = ops->dev_is_coherent && ops->dev_is_coherent(node) ?
+			DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT;
 
 	/* Configure DMA for the page table walker */
 	acpi_dma_configure(&pdev->dev, attr);
 
+	iort_set_device_domain(&pdev->dev, node);
+
 	ret = platform_device_add(pdev);
 	if (ret)
 		goto dma_deconfigure;
@@ -1216,6 +1358,7 @@ static void __init iort_init_platform_devices(void)
 	struct fwnode_handle *fwnode;
 	int i, ret;
 	bool acs_enabled = false;
+	const struct iort_dev_config *ops;
 
 	/*
 	 * iort_table and iort both point to the start of IORT table, but
@@ -1238,16 +1381,15 @@ static void __init iort_init_platform_devices(void)
 		if (!acs_enabled)
 			acs_enabled = iort_enable_acs(iort_node);
 
-		if ((iort_node->type == ACPI_IORT_NODE_SMMU) ||
-			(iort_node->type == ACPI_IORT_NODE_SMMU_V3)) {
-
+		ops = iort_get_dev_cfg(iort_node);
+		if (ops) {
 			fwnode = acpi_alloc_fwnode_static();
 			if (!fwnode)
 				return;
 
 			iort_set_fwnode(iort_node, fwnode);
 
-			ret = iort_add_smmu_platform_device(iort_node);
+			ret = iort_add_platform_device(iort_node, ops);
 			if (ret) {
 				iort_delete_fwnode(iort_node);
 				acpi_free_fwnode_static(fwnode);
diff --git a/drivers/bus/arm-ccn.c b/drivers/bus/arm-ccn.c
index e8c6946fed9d..3063f5312397 100644
--- a/drivers/bus/arm-ccn.c
+++ b/drivers/bus/arm-ccn.c
@@ -1276,6 +1276,7 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 
 	/* Perf driver registration */
 	ccn->dt.pmu = (struct pmu) {
+		.module = THIS_MODULE,
 		.attr_groups = arm_ccn_pmu_attr_groups,
 		.task_ctx_nr = perf_invalid_context,
 		.event_init = arm_ccn_pmu_event_init,
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 0ecf5beb56ec..538bfa8ba9b4 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -77,6 +77,7 @@ static bool arch_timer_mem_use_virtual;
 static bool arch_counter_suspend_stop;
 static bool vdso_default = true;
 
+static cpumask_t evtstrm_available = CPU_MASK_NONE;
 static bool evtstrm_enable = IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM);
 
 static int __init early_evtstrm_cfg(char *buf)
@@ -739,6 +740,7 @@ static void arch_timer_evtstrm_enable(int divider)
 #ifdef CONFIG_COMPAT
 	compat_elf_hwcap |= COMPAT_HWCAP_EVTSTRM;
 #endif
+	cpumask_set_cpu(smp_processor_id(), &evtstrm_available);
 }
 
 static void arch_timer_configure_evtstream(void)
@@ -863,6 +865,16 @@ u32 arch_timer_get_rate(void)
 	return arch_timer_rate;
 }
 
+bool arch_timer_evtstrm_available(void)
+{
+	/*
+	 * We might get called from a preemptible context. This is fine
+	 * because availability of the event stream should be always the same
+	 * for a preemptible context and context where we might resume a task.
+	 */
+	return cpumask_test_cpu(raw_smp_processor_id(), &evtstrm_available);
+}
+
 static u64 arch_counter_get_cntvct_mem(void)
 {
 	u32 vct_lo, vct_hi, tmp_hi;
@@ -928,6 +940,8 @@ static int arch_timer_dying_cpu(unsigned int cpu)
 {
 	struct clock_event_device *clk = this_cpu_ptr(arch_timer_evt);
 
+	cpumask_clear_cpu(smp_processor_id(), &evtstrm_available);
+
 	arch_timer_stop(clk);
 	return 0;
 }
@@ -937,10 +951,16 @@ static DEFINE_PER_CPU(unsigned long, saved_cntkctl);
 static int arch_timer_cpu_pm_notify(struct notifier_block *self,
 				    unsigned long action, void *hcpu)
 {
-	if (action == CPU_PM_ENTER)
+	if (action == CPU_PM_ENTER) {
 		__this_cpu_write(saved_cntkctl, arch_timer_get_cntkctl());
-	else if (action == CPU_PM_ENTER_FAILED || action == CPU_PM_EXIT)
+
+		cpumask_clear_cpu(smp_processor_id(), &evtstrm_available);
+	} else if (action == CPU_PM_ENTER_FAILED || action == CPU_PM_EXIT) {
 		arch_timer_set_cntkctl(__this_cpu_read(saved_cntkctl));
+
+		if (elf_hwcap & HWCAP_EVTSTRM)
+			cpumask_set_cpu(smp_processor_id(), &evtstrm_available);
+	}
 	return NOTIFY_OK;
 }
 
@@ -1016,7 +1036,6 @@ static int __init arch_timer_register(void)
 	if (err)
 		goto out_unreg_notify;
 
-
 	/* Register and immediately configure the timer on the boot CPU */
 	err = cpuhp_setup_state(CPUHP_AP_ARM_ARCH_TIMER_STARTING,
 				"clockevents/arm/arch_timer:starting",
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index e5197ffb7422..b8f44b068fc6 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -17,6 +17,13 @@ config ARM_PMU_ACPI
 	depends on ARM_PMU && ACPI
 	def_bool y
 
+config HISI_PMU
+       bool "HiSilicon SoC PMU"
+       depends on ARM64 && ACPI
+       help
+         Support for HiSilicon SoC uncore performance monitoring
+         unit (PMU), such as: L3C, HHA and DDRC.
+
 config QCOM_L2_PMU
 	bool "Qualcomm Technologies L2-cache PMU"
 	depends on ARCH_QCOM && ARM64 && ACPI
@@ -43,4 +50,12 @@ config XGENE_PMU
         help
           Say y if you want to use APM X-Gene SoC performance monitors.
 
+config ARM_SPE_PMU
+	tristate "Enable support for the ARMv8.2 Statistical Profiling Extension"
+	depends on PERF_EVENTS && ARM64
+	help
+	  Enable perf support for the ARMv8.2 Statistical Profiling
+	  Extension, which provides periodic sampling of operations in
+	  the CPU pipeline and reports this via the perf AUX interface.
+
 endmenu
diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
index 9402dc8ff22c..710a0135bd61 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -1,6 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_ARM_PMU) += arm_pmu.o arm_pmu_platform.o
 obj-$(CONFIG_ARM_PMU_ACPI) += arm_pmu_acpi.o
+obj-$(CONFIG_HISI_PMU) += hisilicon/
 obj-$(CONFIG_QCOM_L2_PMU)	+= qcom_l2_pmu.o
 obj-$(CONFIG_QCOM_L3_PMU) += qcom_l3_pmu.o
 obj-$(CONFIG_XGENE_PMU) += xgene_pmu.o
+obj-$(CONFIG_ARM_SPE_PMU) += arm_spe_pmu.o
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index d14fc2e67f93..7bc5eee96b31 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -539,7 +539,7 @@ void armpmu_free_irq(struct arm_pmu *armpmu, int cpu)
 	if (!cpumask_test_and_clear_cpu(cpu, &armpmu->active_irqs))
 		return;
 
-	if (irq_is_percpu(irq)) {
+	if (irq_is_percpu_devid(irq)) {
 		free_percpu_irq(irq, &hw_events->percpu_pmu);
 		cpumask_clear(&armpmu->active_irqs);
 		return;
@@ -565,10 +565,10 @@ int armpmu_request_irq(struct arm_pmu *armpmu, int cpu)
 	if (!irq)
 		return 0;
 
-	if (irq_is_percpu(irq) && cpumask_empty(&armpmu->active_irqs)) {
+	if (irq_is_percpu_devid(irq) && cpumask_empty(&armpmu->active_irqs)) {
 		err = request_percpu_irq(irq, handler, "arm-pmu",
 					 &hw_events->percpu_pmu);
-	} else if (irq_is_percpu(irq)) {
+	} else if (irq_is_percpu_devid(irq)) {
 		int other_cpu = cpumask_first(&armpmu->active_irqs);
 		int other_irq = per_cpu(hw_events->irq, other_cpu);
 
@@ -649,7 +649,7 @@ static int arm_perf_starting_cpu(unsigned int cpu, struct hlist_node *node)
 
 	irq = armpmu_get_cpu_irq(pmu, cpu);
 	if (irq) {
-		if (irq_is_percpu(irq)) {
+		if (irq_is_percpu_devid(irq)) {
 			enable_percpu_irq(irq, IRQ_TYPE_NONE);
 			return 0;
 		}
@@ -667,7 +667,7 @@ static int arm_perf_teardown_cpu(unsigned int cpu, struct hlist_node *node)
 		return 0;
 
 	irq = armpmu_get_cpu_irq(pmu, cpu);
-	if (irq && irq_is_percpu(irq))
+	if (irq && irq_is_percpu_devid(irq))
 		disable_percpu_irq(irq);
 
 	return 0;
diff --git a/drivers/perf/arm_pmu_acpi.c b/drivers/perf/arm_pmu_acpi.c
index 3303dd8d8eb5..705f1a390e31 100644
--- a/drivers/perf/arm_pmu_acpi.c
+++ b/drivers/perf/arm_pmu_acpi.c
@@ -193,9 +193,6 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn)
 	int pmu_idx = 0;
 	int cpu, ret;
 
-	if (acpi_disabled)
-		return 0;
-
 	/*
 	 * Initialise and register the set of PMUs which we know about right
 	 * now. Ideally we'd do this in arm_pmu_acpi_cpu_starting() so that we
diff --git a/drivers/perf/arm_pmu_platform.c b/drivers/perf/arm_pmu_platform.c
index 4428852e1da1..91b224eced18 100644
--- a/drivers/perf/arm_pmu_platform.c
+++ b/drivers/perf/arm_pmu_platform.c
@@ -127,7 +127,7 @@ static int pmu_parse_irqs(struct arm_pmu *pmu)
 
 	if (num_irqs == 1) {
 		int irq = platform_get_irq(pdev, 0);
-		if (irq && irq_is_percpu(irq))
+		if (irq && irq_is_percpu_devid(irq))
 			return pmu_parse_percpu_irq(pmu, irq);
 	}
 
@@ -150,7 +150,7 @@ static int pmu_parse_irqs(struct arm_pmu *pmu)
 		if (WARN_ON(irq <= 0))
 			continue;
 
-		if (irq_is_percpu(irq)) {
+		if (irq_is_percpu_devid(irq)) {
 			pr_warn("multiple PPIs or mismatched SPI/PPI detected\n");
 			return -EINVAL;
 		}
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
new file mode 100644
index 000000000000..8ce262fc2561
--- /dev/null
+++ b/drivers/perf/arm_spe_pmu.c
@@ -0,0 +1,1249 @@
+/*
+ * Perf support for the Statistical Profiling Extension, introduced as
+ * part of ARMv8.2.
+ *
+ * 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/>.
+ *
+ * Copyright (C) 2016 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#define PMUNAME					"arm_spe"
+#define DRVNAME					PMUNAME "_pmu"
+#define pr_fmt(fmt)				DRVNAME ": " fmt
+
+#include <linux/cpuhotplug.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include <asm/sysreg.h>
+
+#define ARM_SPE_BUF_PAD_BYTE			0
+
+struct arm_spe_pmu_buf {
+	int					nr_pages;
+	bool					snapshot;
+	void					*base;
+};
+
+struct arm_spe_pmu {
+	struct pmu				pmu;
+	struct platform_device			*pdev;
+	cpumask_t				supported_cpus;
+	struct hlist_node			hotplug_node;
+
+	int					irq; /* PPI */
+
+	u16					min_period;
+	u16					counter_sz;
+
+#define SPE_PMU_FEAT_FILT_EVT			(1UL << 0)
+#define SPE_PMU_FEAT_FILT_TYP			(1UL << 1)
+#define SPE_PMU_FEAT_FILT_LAT			(1UL << 2)
+#define SPE_PMU_FEAT_ARCH_INST			(1UL << 3)
+#define SPE_PMU_FEAT_LDS			(1UL << 4)
+#define SPE_PMU_FEAT_ERND			(1UL << 5)
+#define SPE_PMU_FEAT_DEV_PROBED			(1UL << 63)
+	u64					features;
+
+	u16					max_record_sz;
+	u16					align;
+	struct perf_output_handle __percpu	*handle;
+};
+
+#define to_spe_pmu(p) (container_of(p, struct arm_spe_pmu, pmu))
+
+/* Convert a free-running index from perf into an SPE buffer offset */
+#define PERF_IDX2OFF(idx, buf)	((idx) % ((buf)->nr_pages << PAGE_SHIFT))
+
+/* Keep track of our dynamic hotplug state */
+static enum cpuhp_state arm_spe_pmu_online;
+
+enum arm_spe_pmu_buf_fault_action {
+	SPE_PMU_BUF_FAULT_ACT_SPURIOUS,
+	SPE_PMU_BUF_FAULT_ACT_FATAL,
+	SPE_PMU_BUF_FAULT_ACT_OK,
+};
+
+/* This sysfs gunk was really good fun to write. */
+enum arm_spe_pmu_capabilities {
+	SPE_PMU_CAP_ARCH_INST = 0,
+	SPE_PMU_CAP_ERND,
+	SPE_PMU_CAP_FEAT_MAX,
+	SPE_PMU_CAP_CNT_SZ = SPE_PMU_CAP_FEAT_MAX,
+	SPE_PMU_CAP_MIN_IVAL,
+};
+
+static int arm_spe_pmu_feat_caps[SPE_PMU_CAP_FEAT_MAX] = {
+	[SPE_PMU_CAP_ARCH_INST]	= SPE_PMU_FEAT_ARCH_INST,
+	[SPE_PMU_CAP_ERND]	= SPE_PMU_FEAT_ERND,
+};
+
+static u32 arm_spe_pmu_cap_get(struct arm_spe_pmu *spe_pmu, int cap)
+{
+	if (cap < SPE_PMU_CAP_FEAT_MAX)
+		return !!(spe_pmu->features & arm_spe_pmu_feat_caps[cap]);
+
+	switch (cap) {
+	case SPE_PMU_CAP_CNT_SZ:
+		return spe_pmu->counter_sz;
+	case SPE_PMU_CAP_MIN_IVAL:
+		return spe_pmu->min_period;
+	default:
+		WARN(1, "unknown cap %d\n", cap);
+	}
+
+	return 0;
+}
+
+static ssize_t arm_spe_pmu_cap_show(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct arm_spe_pmu *spe_pmu = platform_get_drvdata(pdev);
+	struct dev_ext_attribute *ea =
+		container_of(attr, struct dev_ext_attribute, attr);
+	int cap = (long)ea->var;
+
+	return snprintf(buf, PAGE_SIZE, "%u\n",
+		arm_spe_pmu_cap_get(spe_pmu, cap));
+}
+
+#define SPE_EXT_ATTR_ENTRY(_name, _func, _var)				\
+	&((struct dev_ext_attribute[]) {				\
+		{ __ATTR(_name, S_IRUGO, _func, NULL), (void *)_var }	\
+	})[0].attr.attr
+
+#define SPE_CAP_EXT_ATTR_ENTRY(_name, _var)				\
+	SPE_EXT_ATTR_ENTRY(_name, arm_spe_pmu_cap_show, _var)
+
+static struct attribute *arm_spe_pmu_cap_attr[] = {
+	SPE_CAP_EXT_ATTR_ENTRY(arch_inst, SPE_PMU_CAP_ARCH_INST),
+	SPE_CAP_EXT_ATTR_ENTRY(ernd, SPE_PMU_CAP_ERND),
+	SPE_CAP_EXT_ATTR_ENTRY(count_size, SPE_PMU_CAP_CNT_SZ),
+	SPE_CAP_EXT_ATTR_ENTRY(min_interval, SPE_PMU_CAP_MIN_IVAL),
+	NULL,
+};
+
+static struct attribute_group arm_spe_pmu_cap_group = {
+	.name	= "caps",
+	.attrs	= arm_spe_pmu_cap_attr,
+};
+
+/* User ABI */
+#define ATTR_CFG_FLD_ts_enable_CFG		config	/* PMSCR_EL1.TS */
+#define ATTR_CFG_FLD_ts_enable_LO		0
+#define ATTR_CFG_FLD_ts_enable_HI		0
+#define ATTR_CFG_FLD_pa_enable_CFG		config	/* PMSCR_EL1.PA */
+#define ATTR_CFG_FLD_pa_enable_LO		1
+#define ATTR_CFG_FLD_pa_enable_HI		1
+#define ATTR_CFG_FLD_pct_enable_CFG		config	/* PMSCR_EL1.PCT */
+#define ATTR_CFG_FLD_pct_enable_LO		2
+#define ATTR_CFG_FLD_pct_enable_HI		2
+#define ATTR_CFG_FLD_jitter_CFG			config	/* PMSIRR_EL1.RND */
+#define ATTR_CFG_FLD_jitter_LO			16
+#define ATTR_CFG_FLD_jitter_HI			16
+#define ATTR_CFG_FLD_branch_filter_CFG		config	/* PMSFCR_EL1.B */
+#define ATTR_CFG_FLD_branch_filter_LO		32
+#define ATTR_CFG_FLD_branch_filter_HI		32
+#define ATTR_CFG_FLD_load_filter_CFG		config	/* PMSFCR_EL1.LD */
+#define ATTR_CFG_FLD_load_filter_LO		33
+#define ATTR_CFG_FLD_load_filter_HI		33
+#define ATTR_CFG_FLD_store_filter_CFG		config	/* PMSFCR_EL1.ST */
+#define ATTR_CFG_FLD_store_filter_LO		34
+#define ATTR_CFG_FLD_store_filter_HI		34
+
+#define ATTR_CFG_FLD_event_filter_CFG		config1	/* PMSEVFR_EL1 */
+#define ATTR_CFG_FLD_event_filter_LO		0
+#define ATTR_CFG_FLD_event_filter_HI		63
+
+#define ATTR_CFG_FLD_min_latency_CFG		config2	/* PMSLATFR_EL1.MINLAT */
+#define ATTR_CFG_FLD_min_latency_LO		0
+#define ATTR_CFG_FLD_min_latency_HI		11
+
+/* Why does everything I do descend into this? */
+#define __GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\