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

Pull arm64 updates from Will Deacon:
 "Mostly just incremental improvements here:

   - Introduce AT_HWCAP2 for advertising CPU features to userspace

   - Expose SVE2 availability to userspace

   - Support for "data cache clean to point of deep persistence" (DC PODP)

   - Honour "mitigations=off" on the cmdline and advertise status via
     sysfs

   - CPU timer erratum workaround (Neoverse-N1 #1188873)

   - Introduce perf PMU driver for the SMMUv3 performance counters

   - Add config option to disable the kuser helpers page for AArch32 tasks

   - Futex modifications to ensure liveness under contention

   - Rework debug exception handling to seperate kernel and user
     handlers

   - Non-critical fixes and cleanup"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (92 commits)
  Documentation: Add ARM64 to kernel-parameters.rst
  arm64/speculation: Support 'mitigations=' cmdline option
  arm64: ssbs: Don't treat CPUs with SSBS as unaffected by SSB
  arm64: enable generic CPU vulnerabilites support
  arm64: add sysfs vulnerability show for speculative store bypass
  arm64: Fix size of __early_cpu_boot_status
  clocksource/arm_arch_timer: Use arch_timer_read_counter to access stable counters
  clocksource/arm_arch_timer: Remove use of workaround static key
  clocksource/arm_arch_timer: Drop use of static key in arch_timer_reg_read_stable
  clocksource/arm_arch_timer: Direcly assign set_next_event workaround
  arm64: Use arch_timer_read_counter instead of arch_counter_get_cntvct
  watchdog/sbsa: Use arch_timer_read_counter instead of arch_counter_get_cntvct
  ARM: vdso: Remove dependency with the arch_timer driver internals
  arm64: Apply ARM64_ERRATUM_1188873 to Neoverse-N1
  arm64: Add part number for Neoverse N1
  arm64: Make ARM64_ERRATUM_1188873 depend on COMPAT
  arm64: Restrict ARM64_ERRATUM_1188873 mitigation to AArch32
  arm64: mm: Remove pte_unmap_nested()
  arm64: Fix compiler warning from pte_unmap() with -Wunused-but-set-variable
  arm64: compat: Reduce address limit for 64K pages
  ...

10 files changed, 1093 insertions, 127 deletions

diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index e48894e002ba..adbf7cbedf80 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -356,7 +356,8 @@ static 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_SMMU_V3) {
+		    node->type == ACPI_IORT_NODE_SMMU_V3 ||
+		    node->type == ACPI_IORT_NODE_PMCG) {
 			*id_out = map->output_base;
 			return parent;
 		}
@@ -394,6 +395,8 @@ static int iort_get_id_mapping_index(struct acpi_iort_node *node)
 		}
 
 		return smmu->id_mapping_index;
+	case ACPI_IORT_NODE_PMCG:
+		return 0;
 	default:
 		return -EINVAL;
 	}
@@ -1218,32 +1221,47 @@ static void __init arm_smmu_v3_init_resources(struct resource *res,
 	}
 }
 
-static bool __init arm_smmu_v3_is_coherent(struct acpi_iort_node *node)
+static void __init arm_smmu_v3_dma_configure(struct device *dev,
+					     struct acpi_iort_node *node)
 {
 	struct acpi_iort_smmu_v3 *smmu;
+	enum dev_dma_attr attr;
 
 	/* Retrieve SMMUv3 specific data */
 	smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
 
-	return smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE;
+	attr = (smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE) ?
+			DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT;
+
+	/* We expect the dma masks to be equivalent for all SMMUv3 set-ups */
+	dev->dma_mask = &dev->coherent_dma_mask;
+
+	/* Configure DMA for the page table walker */
+	acpi_dma_configure(dev, attr);
 }
 
 #if defined(CONFIG_ACPI_NUMA)
 /*
  * set numa proximity domain for smmuv3 device
  */
-static void  __init arm_smmu_v3_set_proximity(struct device *dev,
+static int  __init arm_smmu_v3_set_proximity(struct device *dev,
 					      struct acpi_iort_node *node)
 {
 	struct acpi_iort_smmu_v3 *smmu;
 
 	smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
 	if (smmu->flags & ACPI_IORT_SMMU_V3_PXM_VALID) {
-		set_dev_node(dev, acpi_map_pxm_to_node(smmu->pxm));
+		int node = acpi_map_pxm_to_node(smmu->pxm);
+
+		if (node != NUMA_NO_NODE && !node_online(node))
+			return -EINVAL;
+
+		set_dev_node(dev, node);
 		pr_info("SMMU-v3[%llx] Mapped to Proximity domain %d\n",
 			smmu->base_address,
 			smmu->pxm);
 	}
+	return 0;
 }
 #else
 #define arm_smmu_v3_set_proximity NULL
@@ -1301,30 +1319,96 @@ static void __init arm_smmu_init_resources(struct resource *res,
 	}
 }
 
-static bool __init arm_smmu_is_coherent(struct acpi_iort_node *node)
+static void __init arm_smmu_dma_configure(struct device *dev,
+					  struct acpi_iort_node *node)
 {
 	struct acpi_iort_smmu *smmu;
+	enum dev_dma_attr attr;
 
 	/* Retrieve SMMU specific data */
 	smmu = (struct acpi_iort_smmu *)node->node_data;
 
-	return smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK;
+	attr = (smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK) ?
+			DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT;
+
+	/* We expect the dma masks to be equivalent for SMMU set-ups */
+	dev->dma_mask = &dev->coherent_dma_mask;
+
+	/* Configure DMA for the page table walker */
+	acpi_dma_configure(dev, attr);
+}
+
+static int __init arm_smmu_v3_pmcg_count_resources(struct acpi_iort_node *node)
+{
+	struct acpi_iort_pmcg *pmcg;
+
+	/* Retrieve PMCG specific data */
+	pmcg = (struct acpi_iort_pmcg *)node->node_data;
+
+	/*
+	 * There are always 2 memory resources.
+	 * If the overflow_gsiv is present then add that for a total of 3.
+	 */
+	return pmcg->overflow_gsiv ? 3 : 2;
+}
+
+static void __init arm_smmu_v3_pmcg_init_resources(struct resource *res,
+						   struct acpi_iort_node *node)
+{
+	struct acpi_iort_pmcg *pmcg;
+
+	/* Retrieve PMCG specific data */
+	pmcg = (struct acpi_iort_pmcg *)node->node_data;
+
+	res[0].start = pmcg->page0_base_address;
+	res[0].end = pmcg->page0_base_address + SZ_4K - 1;
+	res[0].flags = IORESOURCE_MEM;
+	res[1].start = pmcg->page1_base_address;
+	res[1].end = pmcg->page1_base_address + SZ_4K - 1;
+	res[1].flags = IORESOURCE_MEM;
+
+	if (pmcg->overflow_gsiv)
+		acpi_iort_register_irq(pmcg->overflow_gsiv, "overflow",
+				       ACPI_EDGE_SENSITIVE, &res[2]);
+}
+
+static struct acpi_platform_list pmcg_plat_info[] __initdata = {
+	/* HiSilicon Hip08 Platform */
+	{"HISI  ", "HIP08   ", 0, ACPI_SIG_IORT, greater_than_or_equal,
+	 "Erratum #162001800", IORT_SMMU_V3_PMCG_HISI_HIP08},
+	{ }
+};
+
+static int __init arm_smmu_v3_pmcg_add_platdata(struct platform_device *pdev)
+{
+	u32 model;
+	int idx;
+
+	idx = acpi_match_platform_list(pmcg_plat_info);
+	if (idx >= 0)
+		model = pmcg_plat_info[idx].data;
+	else
+		model = IORT_SMMU_V3_PMCG_GENERIC;
+
+	return platform_device_add_data(pdev, &model, sizeof(model));
 }
 
 struct iort_dev_config {
 	const char *name;
 	int (*dev_init)(struct acpi_iort_node *node);
-	bool (*dev_is_coherent)(struct acpi_iort_node *node);
+	void (*dev_dma_configure)(struct device *dev,
+				  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 (*dev_set_proximity)(struct device *dev,
+	int (*dev_set_proximity)(struct device *dev,
 				    struct acpi_iort_node *node);
+	int (*dev_add_platdata)(struct platform_device *pdev);
 };
 
 static const struct iort_dev_config iort_arm_smmu_v3_cfg __initconst = {
 	.name = "arm-smmu-v3",
-	.dev_is_coherent = arm_smmu_v3_is_coherent,
+	.dev_dma_configure = arm_smmu_v3_dma_configure,
 	.dev_count_resources = arm_smmu_v3_count_resources,
 	.dev_init_resources = arm_smmu_v3_init_resources,
 	.dev_set_proximity = arm_smmu_v3_set_proximity,
@@ -1332,9 +1416,16 @@ static const struct iort_dev_config iort_arm_smmu_v3_cfg __initconst = {
 
 static const struct iort_dev_config iort_arm_smmu_cfg __initconst = {
 	.name = "arm-smmu",
-	.dev_is_coherent = arm_smmu_is_coherent,
+	.dev_dma_configure = arm_smmu_dma_configure,
 	.dev_count_resources = arm_smmu_count_resources,
-	.dev_init_resources = arm_smmu_init_resources
+	.dev_init_resources = arm_smmu_init_resources,
+};
+
+static const struct iort_dev_config iort_arm_smmu_v3_pmcg_cfg __initconst = {
+	.name = "arm-smmu-v3-pmcg",
+	.dev_count_resources = arm_smmu_v3_pmcg_count_resources,
+	.dev_init_resources = arm_smmu_v3_pmcg_init_resources,
+	.dev_add_platdata = arm_smmu_v3_pmcg_add_platdata,
 };
 
 static __init const struct iort_dev_config *iort_get_dev_cfg(
@@ -1345,6 +1436,8 @@ static __init const struct iort_dev_config *iort_get_dev_cfg(
 		return &iort_arm_smmu_v3_cfg;
 	case ACPI_IORT_NODE_SMMU:
 		return &iort_arm_smmu_cfg;
+	case ACPI_IORT_NODE_PMCG:
+		return &iort_arm_smmu_v3_pmcg_cfg;
 	default:
 		return NULL;
 	}
@@ -1362,15 +1455,17 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node,
 	struct fwnode_handle *fwnode;
 	struct platform_device *pdev;
 	struct resource *r;
-	enum dev_dma_attr attr;
 	int ret, count;
 
 	pdev = platform_device_alloc(ops->name, PLATFORM_DEVID_AUTO);
 	if (!pdev)
 		return -ENOMEM;
 
-	if (ops->dev_set_proximity)
-		ops->dev_set_proximity(&pdev->dev, node);
+	if (ops->dev_set_proximity) {
+		ret = ops->dev_set_proximity(&pdev->dev, node);
+		if (ret)
+			goto dev_put;
+	}
 
 	count = ops->dev_count_resources(node);
 
@@ -1393,19 +1488,19 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node,
 		goto dev_put;
 
 	/*
-	 * Add a copy of IORT node pointer to platform_data to
-	 * be used to retrieve IORT data information.
+	 * Platform devices based on PMCG nodes uses platform_data to
+	 * pass the hardware model info to the driver. For others, add
+	 * a copy of IORT node pointer to platform_data to be used to
+	 * retrieve IORT data information.
 	 */
-	ret = platform_device_add_data(pdev, &node, sizeof(node));
+	if (ops->dev_add_platdata)
+		ret = ops->dev_add_platdata(pdev);
+	else
+		ret = platform_device_add_data(pdev, &node, sizeof(node));
+
 	if (ret)
 		goto dev_put;
 
-	/*
-	 * We expect the dma masks to be equivalent for
-	 * all SMMUs set-ups
-	 */
-	pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask;
-
 	fwnode = iort_get_fwnode(node);
 
 	if (!fwnode) {
@@ -1415,11 +1510,8 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node,
 
 	pdev->dev.fwnode = fwnode;
 
-	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);
+	if (ops->dev_dma_configure)
+		ops->dev_dma_configure(&pdev->dev, node);
 
 	iort_set_device_domain(&pdev->dev, node);
 
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index ea373cfbcecb..b2a951a798e2 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -149,6 +149,26 @@ u32 arch_timer_reg_read(int access, enum arch_timer_reg reg,
 	return val;
 }
 
+static u64 arch_counter_get_cntpct_stable(void)
+{
+	return __arch_counter_get_cntpct_stable();
+}
+
+static u64 arch_counter_get_cntpct(void)
+{
+	return __arch_counter_get_cntpct();
+}
+
+static u64 arch_counter_get_cntvct_stable(void)
+{
+	return __arch_counter_get_cntvct_stable();
+}
+
+static u64 arch_counter_get_cntvct(void)
+{
+	return __arch_counter_get_cntvct();
+}
+
 /*
  * Default to cp15 based access because arm64 uses this function for
  * sched_clock() before DT is probed and the cp15 method is guaranteed
@@ -316,13 +336,6 @@ static u64 notrace arm64_858921_read_cntvct_el0(void)
 }
 #endif
 
-#ifdef CONFIG_ARM64_ERRATUM_1188873
-static u64 notrace arm64_1188873_read_cntvct_el0(void)
-{
-	return read_sysreg(cntvct_el0);
-}
-#endif
-
 #ifdef CONFIG_SUN50I_ERRATUM_UNKNOWN1
 /*
  * The low bits of the counter registers are indeterminate while bit 10 or
@@ -369,8 +382,7 @@ static u32 notrace sun50i_a64_read_cntv_tval_el0(void)
 DEFINE_PER_CPU(const struct arch_timer_erratum_workaround *, timer_unstable_counter_workaround);
 EXPORT_SYMBOL_GPL(timer_unstable_counter_workaround);
 
-DEFINE_STATIC_KEY_FALSE(arch_timer_read_ool_enabled);
-EXPORT_SYMBOL_GPL(arch_timer_read_ool_enabled);
+static atomic_t timer_unstable_counter_workaround_in_use = ATOMIC_INIT(0);
 
 static void erratum_set_next_event_tval_generic(const int access, unsigned long evt,
 						struct clock_event_device *clk)
@@ -454,14 +466,6 @@ static const struct arch_timer_erratum_workaround ool_workarounds[] = {
 		.read_cntvct_el0 = arm64_858921_read_cntvct_el0,
 	},
 #endif
-#ifdef CONFIG_ARM64_ERRATUM_1188873
-	{
-		.match_type = ate_match_local_cap_id,
-		.id = (void *)ARM64_WORKAROUND_1188873,
-		.desc = "ARM erratum 1188873",
-		.read_cntvct_el0 = arm64_1188873_read_cntvct_el0,
-	},
-#endif
 #ifdef CONFIG_SUN50I_ERRATUM_UNKNOWN1
 	{
 		.match_type = ate_match_dt,
@@ -549,11 +553,8 @@ void arch_timer_enable_workaround(const struct arch_timer_erratum_workaround *wa
 			per_cpu(timer_unstable_counter_workaround, i) = wa;
 	}
 
-	/*
-	 * Use the locked version, as we're called from the CPU
-	 * hotplug framework. Otherwise, we end-up in deadlock-land.
-	 */
-	static_branch_enable_cpuslocked(&arch_timer_read_ool_enabled);
+	if (wa->read_cntvct_el0 || wa->read_cntpct_el0)
+		atomic_set(&timer_unstable_counter_workaround_in_use, 1);
 
 	/*
 	 * Don't use the vdso fastpath if errata require using the
@@ -570,7 +571,7 @@ void arch_timer_enable_workaround(const struct arch_timer_erratum_workaround *wa
 static void arch_timer_check_ool_workaround(enum arch_timer_erratum_match_type type,
 					    void *arg)
 {
-	const struct arch_timer_erratum_workaround *wa;
+	const struct arch_timer_erratum_workaround *wa, *__wa;
 	ate_match_fn_t match_fn = NULL;
 	bool local = false;
 
@@ -594,53 +595,32 @@ static void arch_timer_check_ool_workaround(enum arch_timer_erratum_match_type t
 	if (!wa)
 		return;
 
-	if (needs_unstable_timer_counter_workaround()) {
-		const struct arch_timer_erratum_workaround *__wa;
-		__wa = __this_cpu_read(timer_unstable_counter_workaround);
-		if (__wa && wa != __wa)
-			pr_warn("Can't enable workaround for %s (clashes with %s\n)",
-				wa->desc, __wa->desc);
+	__wa = __this_cpu_read(timer_unstable_counter_workaround);
+	if (__wa && wa != __wa)
+		pr_warn("Can't enable workaround for %s (clashes with %s\n)",
+			wa->desc, __wa->desc);
 
-		if (__wa)
-			return;
-	}
+	if (__wa)
+		return;
 
 	arch_timer_enable_workaround(wa, local);
 	pr_info("Enabling %s workaround for %s\n",
 		local ? "local" : "global", wa->desc);
 }
 
-#define erratum_handler(fn, r, ...)					\
-({									\
-	bool __val;							\
-	if (needs_unstable_timer_counter_workaround()) {		\
-		const struct arch_timer_erratum_workaround *__wa;	\
-		__wa = __this_cpu_read(timer_unstable_counter_workaround); \
-		if (__wa && __wa->fn) {					\
-			r = __wa->fn(__VA_ARGS__);			\
-			__val = true;					\
-		} else {						\
-			__val = false;					\
-		}							\
-	} else {							\
-		__val = false;						\
-	}								\
-	__val;								\
-})
-
 static bool arch_timer_this_cpu_has_cntvct_wa(void)
 {
-	const struct arch_timer_erratum_workaround *wa;
+	return has_erratum_handler(read_cntvct_el0);
+}
 
-	wa = __this_cpu_read(timer_unstable_counter_workaround);
-	return wa && wa->read_cntvct_el0;
+static bool arch_timer_counter_has_wa(void)
+{
+	return atomic_read(&timer_unstable_counter_workaround_in_use);
 }
 #else
 #define arch_timer_check_ool_workaround(t,a)		do { } while(0)
-#define erratum_set_next_event_tval_virt(...)		({BUG(); 0;})
-#define erratum_set_next_event_tval_phys(...)		({BUG(); 0;})
-#define erratum_handler(fn, r, ...)			({false;})
 #define arch_timer_this_cpu_has_cntvct_wa()		({false;})
+#define arch_timer_counter_has_wa()			({false;})
 #endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */
 
 static __always_inline irqreturn_t timer_handler(const int access,
@@ -733,11 +713,6 @@ static __always_inline void set_next_event(const int access, unsigned long evt,
 static int arch_timer_set_next_event_virt(unsigned long evt,
 					  struct clock_event_device *clk)
 {
-	int ret;
-
-	if (erratum_handler(set_next_event_virt, ret, evt, clk))
-		return ret;
-
 	set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk);
 	return 0;
 }
@@ -745,11 +720,6 @@ static int arch_timer_set_next_event_virt(unsigned long evt,
 static int arch_timer_set_next_event_phys(unsigned long evt,
 					  struct clock_event_device *clk)
 {
-	int ret;
-
-	if (erratum_handler(set_next_event_phys, ret, evt, clk))
-		return ret;
-
 	set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk);
 	return 0;
 }
@@ -774,6 +744,10 @@ static void __arch_timer_setup(unsigned type,
 	clk->features = CLOCK_EVT_FEAT_ONESHOT;
 
 	if (type == ARCH_TIMER_TYPE_CP15) {
+		typeof(clk->set_next_event) sne;
+
+		arch_timer_check_ool_workaround(ate_match_local_cap_id, NULL);
+
 		if (arch_timer_c3stop)
 			clk->features |= CLOCK_EVT_FEAT_C3STOP;
 		clk->name = "arch_sys_timer";
@@ -784,20 +758,20 @@ static void __arch_timer_setup(unsigned type,
 		case ARCH_TIMER_VIRT_PPI:
 			clk->set_state_shutdown = arch_timer_shutdown_virt;
 			clk->set_state_oneshot_stopped = arch_timer_shutdown_virt;
-			clk->set_next_event = arch_timer_set_next_event_virt;
+			sne = erratum_handler(set_next_event_virt);
 			break;
 		case ARCH_TIMER_PHYS_SECURE_PPI:
 		case ARCH_TIMER_PHYS_NONSECURE_PPI:
 		case ARCH_TIMER_HYP_PPI:
 			clk->set_state_shutdown = arch_timer_shutdown_phys;
 			clk->set_state_oneshot_stopped = arch_timer_shutdown_phys;
-			clk->set_next_event = arch_timer_set_next_event_phys;
+			sne = erratum_handler(set_next_event_phys);
 			break;
 		default:
 			BUG();
 		}
 
-		arch_timer_check_ool_workaround(ate_match_local_cap_id, NULL);
+		clk->set_next_event = sne;
 	} else {
 		clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
 		clk->name = "arch_mem_timer";
@@ -830,7 +804,11 @@ static void arch_timer_evtstrm_enable(int divider)
 	cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT)
 			| ARCH_TIMER_VIRT_EVT_EN;
 	arch_timer_set_cntkctl(cntkctl);
+#ifdef CONFIG_ARM64
+	cpu_set_named_feature(EVTSTRM);
+#else
 	elf_hwcap |= HWCAP_EVTSTRM;
+#endif
 #ifdef CONFIG_COMPAT
 	compat_elf_hwcap |= COMPAT_HWCAP_EVTSTRM;
 #endif
@@ -995,12 +973,22 @@ static void __init arch_counter_register(unsigned type)
 
 	/* Register the CP15 based counter if we have one */
 	if (type & ARCH_TIMER_TYPE_CP15) {
+		u64 (*rd)(void);
+
 		if ((IS_ENABLED(CONFIG_ARM64) && !is_hyp_mode_available()) ||
-		    arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI)
-			arch_timer_read_counter = arch_counter_get_cntvct;
-		else
-			arch_timer_read_counter = arch_counter_get_cntpct;
+		    arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI) {
+			if (arch_timer_counter_has_wa())
+				rd = arch_counter_get_cntvct_stable;
+			else
+				rd = arch_counter_get_cntvct;
+		} else {
+			if (arch_timer_counter_has_wa())
+				rd = arch_counter_get_cntpct_stable;
+			else
+				rd = arch_counter_get_cntpct;
+		}
 
+		arch_timer_read_counter = rd;
 		clocksource_counter.archdata.vdso_direct = vdso_default;
 	} else {
 		arch_timer_read_counter = arch_counter_get_cntvct_mem;
@@ -1052,7 +1040,11 @@ static int arch_timer_cpu_pm_notify(struct notifier_block *self,
 	} else if (action == CPU_PM_ENTER_FAILED || action == CPU_PM_EXIT) {
 		arch_timer_set_cntkctl(__this_cpu_read(saved_cntkctl));
 
+#ifdef CONFIG_ARM64
+		if (cpu_have_named_feature(EVTSTRM))
+#else
 		if (elf_hwcap & HWCAP_EVTSTRM)
+#endif
 			cpumask_set_cpu(smp_processor_id(), &evtstrm_available);
 	}
 	return NOTIFY_OK;
diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
index e6376f985ef7..9cd70d1a5622 100644
--- a/drivers/firmware/arm_sdei.c
+++ b/drivers/firmware/arm_sdei.c
@@ -165,6 +165,7 @@ static int invoke_sdei_fn(unsigned long function_id, unsigned long arg0,
 
 	return err;
 }
+NOKPROBE_SYMBOL(invoke_sdei_fn);
 
 static struct sdei_event *sdei_event_find(u32 event_num)
 {
@@ -879,6 +880,7 @@ static void sdei_smccc_smc(unsigned long function_id,
 {
 	arm_smccc_smc(function_id, arg0, arg1, arg2, arg3, arg4, 0, 0, res);
 }
+NOKPROBE_SYMBOL(sdei_smccc_smc);
 
 static void sdei_smccc_hvc(unsigned long function_id,
 			   unsigned long arg0, unsigned long arg1,
@@ -887,6 +889,7 @@ static void sdei_smccc_hvc(unsigned long function_id,
 {
 	arm_smccc_hvc(function_id, arg0, arg1, arg2, arg3, arg4, 0, 0, res);
 }
+NOKPROBE_SYMBOL(sdei_smccc_hvc);
 
 int sdei_register_ghes(struct ghes *ghes, sdei_event_callback *normal_cb,
 		       sdei_event_callback *critical_cb)
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index b1f7b64652db..0460c7581220 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -16,9 +16,9 @@ cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ -O2 \
 
 # arm64 uses the full KBUILD_CFLAGS so it's necessary to explicitly
 # disable the stackleak plugin
-cflags-$(CONFIG_ARM64)		:= $(subst -pg,,$(KBUILD_CFLAGS)) -fpie \
-				   $(DISABLE_STACKLEAK_PLUGIN)
-cflags-$(CONFIG_ARM)		:= $(subst -pg,,$(KBUILD_CFLAGS)) \
+cflags-$(CONFIG_ARM64)		:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
+				   -fpie $(DISABLE_STACKLEAK_PLUGIN)
+cflags-$(CONFIG_ARM)		:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
 				   -fno-builtin -fpic \
 				   $(call cc-option,-mno-single-pic-base)
 
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index af9bc178495d..a94e586a58b2 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -52,6 +52,15 @@ config ARM_PMU_ACPI
 	depends on ARM_PMU && ACPI
 	def_bool y
 
+config ARM_SMMU_V3_PMU
+	 tristate "ARM SMMUv3 Performance Monitors Extension"
+	 depends on ARM64 && ACPI && ARM_SMMU_V3
+	   help
+	   Provides support for the ARM SMMUv3 Performance Monitor Counter
+	   Groups (PMCG), which provide monitoring of transactions passing
+	   through the SMMU and allow the resulting information to be filtered
+	   based on the Stream ID of the corresponding master.
+
 config ARM_DSU_PMU
 	tristate "ARM DynamIQ Shared Unit (DSU) PMU"
 	depends on ARM64
diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
index 909f27fd9db3..30489941f3d6 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -4,6 +4,7 @@ obj-$(CONFIG_ARM_CCN) += arm-ccn.o
 obj-$(CONFIG_ARM_DSU_PMU) += arm_dsu_pmu.o
 obj-$(CONFIG_ARM_PMU) += arm_pmu.o arm_pmu_platform.o
 obj-$(CONFIG_ARM_PMU_ACPI) += arm_pmu_acpi.o
+obj-$(CONFIG_ARM_SMMU_V3_PMU) += arm_smmuv3_pmu.o
 obj-$(CONFIG_HISI_PMU) += hisilicon/
 obj-$(CONFIG_QCOM_L2_PMU)	+= qcom_l2_pmu.o
 obj-$(CONFIG_QCOM_L3_PMU) += qcom_l3_pmu.o
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index bfd03e023308..8f8606b9bc9e 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -1684,21 +1684,24 @@ static int cci_pmu_probe(struct platform_device *pdev)
 	raw_spin_lock_init(&cci_pmu->hw_events.pmu_lock);
 	mutex_init(&cci_pmu->reserve_mutex);
 	atomic_set(&cci_pmu->active_events, 0);
-	cci_pmu->cpu = get_cpu();
-
-	ret = cci_pmu_init(cci_pmu, pdev);
-	if (ret) {
-		put_cpu();
-		return ret;
-	}
 
+	cci_pmu->cpu = raw_smp_processor_id();
+	g_cci_pmu = cci_pmu;
 	cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_CCI_ONLINE,
 				  "perf/arm/cci:online", NULL,
 				  cci_pmu_offline_cpu);
-	put_cpu();
-	g_cci_pmu = cci_pmu;
+
+	ret = cci_pmu_init(cci_pmu, pdev);
+	if (ret)
+		goto error_pmu_init;
+
 	pr_info("ARM %s PMU driver probed", cci_pmu->model->name);
 	return 0;
+
+error_pmu_init:
+	cpuhp_remove_state(CPUHP_AP_PERF_ARM_CCI_ONLINE);
+	g_cci_pmu = NULL;
+	return ret;
 }
 
 static int cci_pmu_remove(struct platform_device *pdev)
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index 2ae76026e947..0bb52d9bdcf7 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -167,7 +167,7 @@ struct arm_ccn_dt {
 
 	struct hrtimer hrtimer;
 
-	cpumask_t cpu;
+	unsigned int cpu;
 	struct hlist_node node;
 
 	struct pmu pmu;
@@ -559,7 +559,7 @@ static ssize_t arm_ccn_pmu_cpumask_show(struct device *dev,
 {
 	struct arm_ccn *ccn = pmu_to_arm_ccn(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, &ccn->dt.cpu);
+	return cpumap_print_to_pagebuf(true, buf, cpumask_of(ccn->dt.cpu));
 }
 
 static struct device_attribute arm_ccn_pmu_cpumask_attr =
@@ -759,7 +759,7 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
 	 * mitigate this, we enforce CPU assignment to one, selected
 	 * processor (the one described in the "cpumask" attribute).
 	 */
-	event->cpu = cpumask_first(&ccn->dt.cpu);
+	event->cpu = ccn->dt.cpu;
 
 	node_xp = CCN_CONFIG_NODE(event->attr.config);
 	type = CCN_CONFIG_TYPE(event->attr.config);
@@ -1215,15 +1215,15 @@ static int arm_ccn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 	struct arm_ccn *ccn = container_of(dt, struct arm_ccn, dt);
 	unsigned int target;
 
-	if (!cpumask_test_and_clear_cpu(cpu, &dt->cpu))
+	if (cpu != dt->cpu)
 		return 0;
 	target = cpumask_any_but(cpu_online_mask, cpu);
 	if (target >= nr_cpu_ids)
 		return 0;
 	perf_pmu_migrate_context(&dt->pmu, cpu, target);
-	cpumask_set_cpu(target, &dt->cpu);
+	dt->cpu = target;
 	if (ccn->irq)
-		WARN_ON(irq_set_affinity_hint(ccn->irq, &dt->cpu) != 0);
+		WARN_ON(irq_set_affinity_hint(ccn->irq, cpumask_of(dt->cpu)));
 	return 0;
 }
 
@@ -1299,29 +1299,30 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 	}
 
 	/* Pick one CPU which we will use to collect data from CCN... */
-	cpumask_set_cpu(get_cpu(), &ccn->dt.cpu);
+	ccn->dt.cpu = raw_smp_processor_id();
 
 	/* Also make sure that the overflow interrupt is handled by this CPU */
 	if (ccn->irq) {
-		err = irq_set_affinity_hint(ccn->irq, &ccn->dt.cpu);
+		err = irq_set_affinity_hint(ccn->irq, cpumask_of(ccn->dt.cpu));
 		if (err) {
 			dev_err(ccn->dev, "Failed to set interrupt affinity!\n");
 			goto error_set_affinity;
 		}
 	}
 
+	cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+					 &ccn->dt.node);
+
 	err = perf_pmu_register(&ccn->dt.pmu, name, -1);
 	if (err)
 		goto error_pmu_register;
 
-	cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
-					 &ccn->dt.node);
-	put_cpu();
 	return 0;
 
 error_pmu_register:
+	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+					    &ccn->dt.node);
 error_set_affinity:
-	put_cpu();
 error_choose_name:
 	ida_simple_remove(&arm_ccn_pmu_ida, ccn->dt.id);
 	for (i = 0; i < ccn->num_xps; i++)
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
new file mode 100644
index 000000000000..da71c741cb46
--- /dev/null
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -0,0 +1,865 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * This driver adds support for perf events to use the Performance
+ * Monitor Counter Groups (PMCG) associated with an SMMUv3 node
+ * to monitor that node.
+ *
+ * SMMUv3 PMCG devices are named as smmuv3_pmcg_<phys_addr_page> where
+ * <phys_addr_page> is the physical page address of the SMMU PMCG wrapped
+ * to 4K boundary. For example, the PMCG at 0xff88840000 is named
+ * smmuv3_pmcg_ff88840
+ *
+ * Filtering by stream id is done by specifying filtering parameters
+ * with the event. options are:
+ *   filter_enable    - 0 = no filtering, 1 = filtering enabled
+ *   filter_span      - 0 = exact match, 1 = pattern match
+ *   filter_stream_id - pattern to filter against
+ *
+ * To match a partial StreamID where the X most-significant bits must match
+ * but the Y least-significant bits might differ, STREAMID is programmed
+ * with a value that contains:
+ *  STREAMID[Y - 1] == 0.
+ *  STREAMID[Y - 2:0] == 1 (where Y > 1).
+ * The remainder of implemented bits of STREAMID (X bits, from bit Y upwards)
+ * contain a value to match from the corresponding bits of event StreamID.
+ *
+ * Example: perf stat -e smmuv3_pmcg_ff88840/transaction,filter_enable=1,
+ *                    filter_span=1,filter_stream_id=0x42/ -a netperf
+ * Applies filter pattern 0x42 to transaction events, which means events
+ * matching stream ids 0x42 and 0x43 are counted. Further filtering
+ * information is available in the SMMU documentation.
+ *
+ * SMMU events are not attributable to a CPU, so task mode and sampling
+ * are not supported.
+ */
+
+#include <linux/acpi.h>
+#include <linux/acpi_iort.h>
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/cpuhotplug.h>
+#include <linux/cpumask.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/msi.h>
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+#include <linux/smp.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
+
+#define SMMU_PMCG_EVCNTR0               0x0
+#define SMMU_PMCG_EVCNTR(n, stride)     (SMMU_PMCG_EVCNTR0 + (n) * (stride))
+#define SMMU_PMCG_EVTYPER0              0x400
+#define SMMU_PMCG_EVTYPER(n)            (SMMU_PMCG_EVTYPER0 + (n) * 4)
+#define SMMU_PMCG_SID_SPAN_SHIFT        29
+#define SMMU_PMCG_SMR0                  0xA00
+#define SMMU_PMCG_SMR(n)                (SMMU_PMCG_SMR0 + (n) * 4)
+#define SMMU_PMCG_CNTENSET0             0xC00
+#define SMMU_PMCG_CNTENCLR0             0xC20
+#define SMMU_PMCG_INTENSET0             0xC40
+#define SMMU_PMCG_INTENCLR0             0xC60
+#define SMMU_PMCG_OVSCLR0               0xC80
+#define SMMU_PMCG_OVSSET0               0xCC0
+#define SMMU_PMCG_CFGR                  0xE00
+#define SMMU_PMCG_CFGR_SID_FILTER_TYPE  BIT(23)
+#define SMMU_PMCG_CFGR_MSI              BIT(21)
+#define SMMU_PMCG_CFGR_RELOC_CTRS       BIT(20)
+#define SMMU_PMCG_CFGR_SIZE             GENMASK(13, 8)
+#define SMMU_PMCG_CFGR_NCTR             GENMASK(5, 0)
+#define SMMU_PMCG_CR                    0xE04
+#define SMMU_PMCG_CR_ENABLE             BIT(0)
+#define SMMU_PMCG_CEID0                 0xE20
+#define SMMU_PMCG_CEID1                 0xE28
+#define SMMU_PMCG_IRQ_CTRL              0xE50
+#define SMMU_PMCG_IRQ_CTRL_IRQEN        BIT(0)
+#define SMMU_PMCG_IRQ_CFG0              0xE58
+#define SMMU_PMCG_IRQ_CFG1              0xE60
+#define SMMU_PMCG_IRQ_CFG2              0xE64
+
+/* MSI config fields */
+#define MSI_CFG0_ADDR_MASK              GENMASK_ULL(51, 2)
+#define MSI_CFG2_MEMATTR_DEVICE_nGnRE   0x1
+
+#define SMMU_PMCG_DEFAULT_FILTER_SPAN   1
+#define SMMU_PMCG_DEFAULT_FILTER_SID    GENMASK(31, 0)
+
+#define SMMU_PMCG_MAX_COUNTERS          64
+#define SMMU_PMCG_ARCH_MAX_EVENTS       128
+
+#define SMMU_PMCG_PA_SHIFT              12
+
+#define SMMU_PMCG_EVCNTR_RDONLY         BIT(0)
+
+static int cpuhp_state_num;
+
+struct smmu_pmu {
+	struct hlist_node node;
+	struct perf_event *events[SMMU_PMCG_MAX_COUNTERS];
+	DECLARE_BITMAP(used_counters, SMMU_PMCG_MAX_COUNTERS);
+	DECLARE_BITMAP(supported_events, SMMU_PMCG_ARCH_MAX_EVENTS);
+	unsigned int irq;
+	unsigned int on_cpu;
+	struct pmu pmu;
+	unsigned int num_counters;
+	struct device *dev;
+	void __iomem *reg_base;
+	void __iomem *reloc_base;
+	u64 counter_mask;
+	u32 options;
+	bool global_filter;
+	u32 global_filter_span;
+	u32 global_filter_sid;
+};
+
+#define to_smmu_pmu(p) (container_of(p, struct smmu_pmu, pmu))
+
+#define SMMU_PMU_EVENT_ATTR_EXTRACTOR(_name, _config, _start, _end)        \
+	static inline u32 get_##_name(struct perf_event *event)            \
+	{                                                                  \
+		return FIELD_GET(GENMASK_ULL(_end, _start),                \
+				 event->attr._config);                     \
+	}                                                                  \
+
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(event, config, 0, 15);
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_stream_id, config1, 0, 31);
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_span, config1, 32, 32);
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_enable, config1, 33, 33);
+
+static inline void smmu_pmu_enable(struct pmu *pmu)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);
+
+	writel(SMMU_PMCG_IRQ_CTRL_IRQEN,
+	       smmu_pmu->reg_base + SMMU_PMCG_IRQ_CTRL);
+	writel(SMMU_PMCG_CR_ENABLE, smmu_pmu->reg_base + SMMU_PMCG_CR);
+}
+
+static inline void smmu_pmu_disable(struct pmu *pmu)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);
+
+	writel(0, smmu_pmu->reg_base + SMMU_PMCG_CR);
+	writel(0, smmu_pmu->reg_base + SMMU_PMCG_IRQ_CTRL);
+}
+
+static inline void smmu_pmu_counter_set_value(struct smmu_pmu *smmu_pmu,
+					      u32 idx, u64 value)
+{
+	if (smmu_pmu->counter_mask & BIT(32))
+		writeq(value, smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 8));
+	else
+		writel(value, smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 4));
+}
+
+static inline u64 smmu_pmu_counter_get_value(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+	u64 value;
+
+	if (smmu_pmu->counter_mask & BIT(32))
+		value = readq(smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 8));
+	else
+		value = readl(smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 4));
+
+	return value;
+}
+
+static inline void smmu_pmu_counter_enable(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+	writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_CNTENSET0);
+}
+
+static inline void smmu_pmu_counter_disable(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+	writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_CNTENCLR0);
+}
+
+static inline void smmu_pmu_interrupt_enable(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+	writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_INTENSET0);
+}
+
+static inline void smmu_pmu_interrupt_disable(struct smmu_pmu *smmu_pmu,
+					      u32 idx)
+{
+	writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_INTENCLR0);
+}
+
+static inline void smmu_pmu_set_evtyper(struct smmu_pmu *smmu_pmu, u32 idx,
+					u32 val)
+{
+	writel(val, smmu_pmu->reg_base + SMMU_PMCG_EVTYPER(idx));
+}
+
+static inline void smmu_pmu_set_smr(struct smmu_pmu *smmu_pmu, u32 idx, u32 val)
+{
+	writel(val, smmu_pmu->reg_base + SMMU_PMCG_SMR(idx));
+}
+
+static void smmu_pmu_event_update(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	u64 delta, prev, now;
+	u32 idx = hwc->idx;
+
+	do {
+		prev = local64_read(&hwc->prev_count);
+		now = smmu_pmu_counter_get_value(smmu_pmu, idx);
+	} while (local64_cmpxchg(&hwc->prev_count, prev, now) != prev);
+
+	/* handle overflow. */
+	delta = now - prev;
+	delta &= smmu_pmu->counter_mask;
+
+	local64_add(delta, &event->count);
+}
+
+static void smmu_pmu_set_period(struct smmu_pmu *smmu_pmu,
+				struct hw_perf_event *hwc)
+{
+	u32 idx = hwc->idx;
+	u64 new;
+
+	if (smmu_pmu->options & SMMU_PMCG_EVCNTR_RDONLY) {
+		/*
+		 * On platforms that require this quirk, if the counter starts
+		 * at < half_counter value and wraps, the current logic of
+		 * handling the overflow may not work. It is expected that,
+		 * those platforms will have full 64 counter bits implemented
+		 * so that such a possibility is remote(eg: HiSilicon HIP08).
+		 */
+		new = smmu_pmu_counter_get_value(smmu_pmu, idx);
+	} else {
+		/*
+		 * We limit the max period to half the max counter value
+		 * of the counter size, so that even in the case of extreme
+		 * interrupt latency the counter will (hopefully) not wrap
+		 * past its initial value.
+		 */
+		new = smmu_pmu->counter_mask >> 1;
+		smmu_pmu_counter_set_value(smmu_pmu, idx, new);
+	}
+
+	local64_set(&hwc->prev_count, new);
+}
+
+static void smmu_pmu_set_event_filter(struct perf_event *event,
+				      int idx, u32 span, u32 sid)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	u32 evtyper;
+
+	evtyper = get_event(event) | span << SMMU_PMCG_SID_SPAN_SHIFT;
+	smmu_pmu_set_evtyper(smmu_pmu, idx, evtyper);
+	smmu_pmu_set_smr(smmu_pmu, idx, sid);
+}
+
+static int smmu_pmu_apply_event_filter(struct smmu_pmu *smmu_pmu,
+				       struct perf_event *event, int idx)
+{
+	u32 span, sid;
+	unsigned int num_ctrs = smmu_pmu->num_counters;
+	bool filter_en = !!get_filter_enable(event);
+
+	span = filter_en ? get_filter_span(event) :
+			   SMMU_PMCG_DEFAULT_FILTER_SPAN;
+	sid = filter_en ? get_filter_stream_id(event) :
+			   SMMU_PMCG_DEFAULT_FILTER_SID;
+
+	/* Support individual filter settings */
+	if (!smmu_pmu->global_filter) {
+		smmu_pmu_set_event_filter(event, idx, span, sid);
+		return 0;
+	}
+
+	/* Requested settings same as current global settings*/
+	if (span == smmu_pmu->global_filter_span &&
+	    sid == smmu_pmu->global_filter_sid)
+		return 0;
+
+	if (!bitmap_empty(smmu_pmu->used_counters, num_ctrs))
+		return -EAGAIN;
+
+	smmu_pmu_set_event_filter(event, 0, span, sid);
+	smmu_pmu->global_filter_span = span;
+	smmu_pmu->global_filter_sid = sid;
+	return 0;
+}
+
+static int smmu_pmu_get_event_idx(struct smmu_pmu *smmu_pmu,
+				  struct perf_event *event)
+{
+	int idx, err;
+	unsigned int num_ctrs = smmu_pmu->num_counters;
+
+	idx = find_first_zero_bit(smmu_pmu->used_counters, num_ctrs);
+	if (idx == num_ctrs)
+		/* The counters are all in use. */
+		return -EAGAIN;
+
+	err = smmu_pmu_apply_event_filter(smmu_pmu, event, idx);
+	if (err)
+		return err;
+
+	set_bit(idx, smmu_pmu->used_counters);
+
+	return idx;
+}
+
+/*
+ * Implementation of abstract pmu functionality required by
+ * the core perf events code.
+ */
+
+static int smmu_pmu_event_init(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	struct device *dev = smmu_pmu->dev;
+	struct perf_event *sibling;
+	u16 event_id;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	if (hwc->sample_period) {
+		dev_dbg(dev, "Sampling not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (event->cpu < 0) {
+		dev_dbg(dev, "Per-task mode not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* Verify specified event is supported on this PMU */
+	event_id = get_event(event);
+	if (event_id < SMMU_PMCG_ARCH_MAX_EVENTS &&
+	    (!test_bit(event_id, smmu_pmu->supported_events))) {
+		dev_dbg(dev, "Invalid event %d for this PMU\n", event_id);
+		return -EINVAL;
+	}
+
+	/* Don't allow groups with mixed PMUs, except for s/w events */
+	if (event->group_leader->pmu != event->pmu &&
+	    !is_software_event(event->group_leader)) {
+		dev_dbg(dev, "Can't create mixed PMU group\n");
+		return -EINVAL;
+	}
+
+	for_each_sibling_event(sibling, event->group_leader) {
+		if (sibling->pmu != event->pmu &&
+		    !is_software_event(sibling)) {
+			dev_dbg(dev, "Can't create mixed PMU group\n");
+			return -EINVAL;
+		}
+	}
+
+	hwc->idx = -1;
+
+	/*
+	 * Ensure all events are on the same cpu so all events are in the
+	 * same cpu context, to avoid races on pmu_enable etc.
+	 */
+	event->cpu = smmu_pmu->on_cpu;
+
+	return 0;
+}
+
+static void smmu_pmu_event_start(struct perf_event *event, int flags)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	hwc->state = 0;
+
+	smmu_pmu_set_period(smmu_pmu, hwc);
+
+	smmu_pmu_counter_enable(smmu_pmu, idx);
+}
+
+static void smmu_pmu_event_stop(struct perf_event *event, int flags)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	if (hwc->state & PERF_HES_STOPPED)
+		return;
+
+	smmu_pmu_counter_disable(smmu_pmu, idx);
+	/* As the counter gets updated on _start, ignore PERF_EF_UPDATE */
+	smmu_pmu_event_update(event);
+	hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+}
+
+static int smmu_pmu_event_add(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx;
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+
+	idx = smmu_pmu_get_event_idx(smmu_pmu, event);
+	if (idx < 0)
+		return idx;
+
+	hwc->idx = idx;
+	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	smmu_pmu->events[idx] = event;
+	local64_set(&hwc->prev_count, 0);
+
+	smmu_pmu_interrupt_enable(smmu_pmu, idx);
+
+	if (flags & PERF_EF_START)
+		smmu_pmu_event_start(event, flags);
+
+	/* Propagate changes to the userspace mapping. */
+	perf_event_update_userpage(event);
+
+	return 0;
+}
+
+static void smmu_pmu_event_del(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	int idx = hwc->idx;
+
+	smmu_pmu_event_stop(event, flags | PERF_EF_UPDATE);
+	smmu_pmu_interrupt_disable(smmu_pmu, idx);
+	smmu_pmu->events[idx] = NULL;
+	clear_bit(idx, smmu_pmu->used_counters);
+
+	perf_event_update_userpage(event);
+}
+
+static void smmu_pmu_event_read(struct perf_event *event)
+{
+	smmu_pmu_event_update(event);
+}
+
+/* cpumask */
+
+static ssize_t smmu_pmu_cpumask_show(struct device *dev,
+				     struct device_attribute *attr,
+				     char *buf)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(dev_get_drvdata(dev));
+
+	return cpumap_print_to_pagebuf(true, buf, cpumask_of(smmu_pmu->on_cpu));
+}
+
+static struct device_attribute smmu_pmu_cpumask_attr =
+		__ATTR(cpumask, 0444, smmu_pmu_cpumask_show, NULL);
+
+static struct attribute *smmu_pmu_cpumask_attrs[] = {
+	&smmu_pmu_cpumask_attr.attr,
+	NULL
+};
+
+static struct attribute_group smmu_pmu_cpumask_group = {
+	.attrs = smmu_pmu_cpumask_attrs,
+};
+
+/* Events */
+
+static ssize_t smmu_pmu_event_show(struct device *dev,
+				   struct device_attribute *attr, char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+
+	return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+}
+
+#define SMMU_EVENT_ATTR(name, config) \
+	PMU_EVENT_ATTR(name, smmu_event_attr_##name, \
+		       config, smmu_pmu_event_show)
+SMMU_EVENT_ATTR(cycles, 0);
+SMMU_EVENT_ATTR(transaction, 1);
+SMMU_EVENT_ATTR(tlb_miss, 2);
+SMMU_EVENT_ATTR(config_cache_miss, 3);
+SMMU_EVENT_ATTR(trans_table_walk_access, 4);
+SMMU_EVENT_ATTR(config_struct_access, 5);
+SMMU_EVENT_ATTR(pcie_ats_trans_rq, 6);
+SMMU_EVENT_ATTR(pcie_ats_trans_passed, 7);
+
+static struct attribute *smmu_pmu_events[] = {
+	&smmu_event_attr_cycles.attr.attr,
+	&smmu_event_attr_transaction.attr.attr,
+	&smmu_event_attr_tlb_miss.attr.attr,
+	&smmu_event_attr_config_cache_miss.attr.attr,
+	&smmu_event_attr_trans_table_walk_access.attr.attr,
+	&smmu_event_attr_config_struct_access.attr.attr,
+	&smmu_event_attr_pcie_ats_trans_rq.attr.attr,
+	&smmu_event_attr_pcie_ats_trans_passed.attr.attr,
+	NULL
+};
+
+static umode_t smmu_pmu_event_is_visible(struct kobject *kobj,
+					 struct attribute *attr, int unused)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(dev_get_drvdata(dev));
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr);
+
+	if (test_bit(pmu_attr->id, smmu_pmu->supported_events))
+		return attr->mode;
+
+	return 0;
+}
+
+static struct attribute_group smmu_pmu_events_group = {
+	.name = "events",
+	.attrs = smmu_pmu_events,
+	.is_visible = smmu_pmu_event_is_visible,
+};
+
+/* Formats */
+PMU_FORMAT_ATTR(event,		   "config:0-15");
+PMU_FORMAT_ATTR(filter_stream_id,  "config1:0-31");
+PMU_FORMAT_ATTR(filter_span,	   "config1:32");
+PMU_FORMAT_ATTR(filter_enable,	   "config1:33");
+
+static struct attribute *smmu_pmu_formats[] = {
+	&format_attr_event.attr,
+	&format_attr_filter_stream_id.attr,
+	&format_attr_filter_span.attr,
+	&format_attr_filter_enable.attr,
+	NULL
+};
+
+static struct attribute_group smmu_pmu_format_group = {
+	.name = "format",
+	.attrs = smmu_pmu_formats,
+};
+
+static const struct attribute_group *smmu_pmu_attr_grps[] = {
+	&smmu_pmu_cpumask_group,
+	&smmu_pmu_events_group,
+	&smmu_pmu_format_group,
+	NULL
+};
+
+/*
+ * Generic device handlers
+ */
+
+static int smmu_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
+{
+	struct smmu_pmu *smmu_pmu;
+	unsigned int target;
+
+	smmu_pmu = hlist_entry_safe(node, struct smmu_pmu, node);
+	if (cpu != smmu_pmu->on_cpu)
+		return 0;
+
+	target = cpumask_any_but(cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
+		return 0;
+
+	perf_pmu_migrate_context(&smmu_pmu->pmu, cpu, target);
+	smmu_pmu->on_cpu = target;
+	WARN_ON(irq_set_affinity_hint(smmu_pmu->irq, cpumask_of(target)));
+
+	return 0;
+}
+
+static irqreturn_t smmu_pmu_handle_irq(int irq_num, void *data)
+{
+	struct smmu_pmu *smmu_pmu = data;
+	u64 ovsr;
+	unsigned int idx;
+
+	ovsr = readq(smmu_pmu->reloc_base + SMMU_PMCG_OVSSET0);
+	if (!ovsr)
+		return IRQ_NONE;
+
+	writeq(ovsr, smmu_pmu->reloc_base + SMMU_PMCG_OVSCLR0);
+
+	for_each_set_bit(idx, (unsigned long *)&ovsr, smmu_pmu->num_counters) {
+		struct perf_event *event = smmu_pmu->events[idx];
+		struct hw_perf_event *hwc;
+
+		if (WARN_ON_ONCE(!event))
+			continue;
+
+		smmu_pmu_event_update(event);
+		hwc = &event->hw;
+
+		smmu_pmu_set_period(smmu_pmu, hwc);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void smmu_pmu_free_msis(void *data)
+{
+	struct device *dev = data;
+
+	platform_msi_domain_free_irqs(dev);
+}
+
+static void smmu_pmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
+{
+	phys_addr_t doorbell;
+	struct device *dev = msi_desc_to_dev(desc);
+	struct smmu_pmu *pmu = dev_get_drvdata(dev);
+
+	doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo;
+	doorbell &= MSI_CFG0_ADDR_MASK;
+
+	writeq_relaxed(doorbell, pmu->reg_base + SMMU_PMCG_IRQ_CFG0);
+	writel_relaxed(msg->data, pmu->reg_base + SMMU_PMCG_IRQ_CFG1);
+	writel_relaxed(MSI_CFG2_MEMATTR_DEVICE_nGnRE,
+		       pmu->reg_base + SMMU_PMCG_IRQ_CFG2);
+}
+
+static void smmu_pmu_setup_msi(struct smmu_pmu *pmu)
+{
+	struct msi_desc *desc;
+	struct device *dev = pmu->dev;
+	int ret;
+
+	/* Clear MSI address reg */
+	writeq_relaxed(0, pmu->reg_base + SMMU_PMCG_IRQ_CFG0);
+
+	/* MSI supported or not */
+	if (!(readl(pmu->reg_base + SMMU_PMCG_CFGR) & SMMU_PMCG_CFGR_MSI))
+		return;
+
+	ret = platform_msi_domain_alloc_irqs(dev, 1, smmu_pmu_write_msi_msg);
+	if (ret) {
+		dev_warn(dev, "failed to allocate MSIs\n");
+		return;
+	}
+
+	desc = first_msi_entry(dev);
+	if (desc)
+		pmu->irq = desc->irq;
+
+	/* Add callback to free MSIs on teardown */
+	devm_add_action(dev, smmu_pmu_free_msis, dev);
+}
+
+static int smmu_pmu_setup_irq(struct smmu_pmu *pmu)
+{
+	unsigned long flags = IRQF_NOBALANCING | IRQF_SHARED | IRQF_NO_THREAD;
+	int irq, ret = -ENXIO;
+
+	smmu_pmu_setup_msi(pmu);
+
+	irq = pmu->irq;
+	if (irq)
+		ret = devm_request_irq(pmu->dev, irq, smmu_pmu_handle_irq,
+				       flags, "smmuv3-pmu", pmu);
+	return ret;
+}
+
+static void smmu_pmu_reset(struct smmu_pmu *smmu_pmu)
+{
+	u64 counter_present_mask = GENMASK_ULL(smmu_pmu->num_counters - 1, 0);
+
+	smmu_pmu_disable(&smmu_pmu->pmu);
+
+	/* Disable counter and interrupt */
+	writeq_relaxed(counter_present_mask,
+		       smmu_pmu->reg_base + SMMU_PMCG_CNTENCLR0);
+	writeq_relaxed(counter_present_mask,
+		       smmu_pmu->reg_base + SMMU_PMCG_INTENCLR0);
+	writeq_relaxed(counter_present_mask,
+		       smmu_pmu->reloc_base + SMMU_PMCG_OVSCLR0);
+}
+
+static void smmu_pmu_get_acpi_options(struct smmu_pmu *smmu_pmu)
+{
+	u32 model;
+
+	model = *(u32 *)dev_get_platdata(smmu_pmu->dev);
+
+	switch (model) {
+	case IORT_SMMU_V3_PMCG_HISI_HIP08:
+		/* HiSilicon Erratum 162001800 */
+		smmu_pmu->options |= SMMU_PMCG_EVCNTR_RDONLY;
+		break;
+	}
+
+	dev_notice(smmu_pmu->dev, "option mask 0x%x\n", smmu_pmu->options);
+}
+
+static int smmu_pmu_probe(struct platform_device *pdev)
+{
+	struct smmu_pmu *smmu_pmu;
+	struct resource *res_0, *res_1;
+	u32 cfgr, reg_size;
+	u64 ceid_64[2];
+	int irq, err;
+	char *name;
+	struct device *dev = &pdev->dev;
+
+	smmu_pmu = devm_kzalloc(dev, sizeof(*smmu_pmu), GFP_KERNEL);
+	if (!smmu_pmu)
+		return -ENOMEM;
+
+	smmu_pmu->dev = dev;
+	platform_set_drvdata(pdev, smmu_pmu);
+
+	smmu_pmu->pmu = (struct pmu) {
+		.task_ctx_nr    = perf_invalid_context,
+		.pmu_enable	= smmu_pmu_enable,
+		.pmu_disable	= smmu_pmu_disable,
+		.event_init	= smmu_pmu_event_init,
+		.add		= smmu_pmu_event_add,
+		.del		= smmu_pmu_event_del,
+		.start		= smmu_pmu_event_start,
+		.stop		= smmu_pmu_event_stop,
+		.read		= smmu_pmu_event_read,
+		.attr_groups	= smmu_pmu_attr_grps,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
+	};
+
+	res_0 = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	smmu_pmu->reg_base = devm_ioremap_resource(dev, res_0);
+	if (IS_ERR(smmu_pmu->reg_base))
+		return PTR_ERR(smmu_pmu->reg_base);
+
+	cfgr = readl_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CFGR);
+
+	/* Determine if page 1 is present */
+	if (cfgr & SMMU_PMCG_CFGR_RELOC_CTRS) {
+		res_1 = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+		smmu_pmu->reloc_base = devm_ioremap_resource(dev, res_1);
+		if (IS_ERR(smmu_pmu->reloc_base))
+			return PTR_ERR(smmu_pmu->reloc_base);
+	} else {
+		smmu_pmu->reloc_base = smmu_pmu->reg_base;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq > 0)
+		smmu_pmu->irq = irq;
+
+	ceid_64[0] = readq_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CEID0);
+	ceid_64[1] = readq_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CEID1);
+	bitmap_from_arr32(smmu_pmu->supported_events, (u32 *)ceid_64,
+			  SMMU_PMCG_ARCH_MAX_EVENTS);
+
+	smmu_pmu->num_counters = FIELD_GET(SMMU_PMCG_CFGR_NCTR, cfgr) + 1;
+
+	smmu_pmu->global_filter = !!(cfgr & SMMU_PMCG_CFGR_SID_FILTER_TYPE);
+
+	reg_size = FIELD_GET(SMMU_PMCG_CFGR_SIZE, cfgr);
+	smmu_pmu->counter_mask = GENMASK_ULL(reg_size, 0);
+
+	smmu_pmu_reset(smmu_pmu);
+
+	err = smmu_pmu_setup_irq(smmu_pmu);
+	if (err) {
+		dev_err(dev, "Setup irq failed, PMU @%pa\n", &res_0->start);
+		return err;
+	}
+
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "smmuv3_pmcg_%llx",
+			      (res_0->start) >> SMMU_PMCG_PA_SHIFT);
+	if (!name) {
+		dev_err(dev, "Create name failed, PMU @%pa\n", &res_0->start);
+		return -EINVAL;
+	}
+
+	smmu_pmu_get_acpi_options(smmu_pmu);
+
+	/* Pick one CPU to be the preferred one to use */
+	smmu_pmu->on_cpu = raw_smp_processor_id();
+	WARN_ON(irq_set_affinity_hint(smmu_pmu->irq,
+				      cpumask_of(smmu_pmu->on_cpu)));
+
+	err = cpuhp_state_add_instance_nocalls(cpuhp_state_num,
+					       &smmu_pmu->node);
+	if (err) {
+		dev_err(dev, "Error %d registering hotplug, PMU @%pa\n",
+			err, &res_0->start);
+		goto out_cpuhp_err;
+	}
+
+	err = perf_pmu_register(&smmu_pmu->pmu, name, -1);
+	if (err) {
+		dev_err(dev, "Error %d registering PMU @%pa\n",
+			err, &res_0->start);
+		goto out_unregister;
+	}
+
+	dev_info(dev, "Registered PMU @ %pa using %d counters with %s filter settings\n",
+		 &res_0->start, smmu_pmu->num_counters,
+		 smmu_pmu->global_filter ? "Global(Counter0)" :
+		 "Individual");
+
+	return 0;
+
+out_unregister:
+	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
+out_cpuhp_err:
+	put_cpu();
+	return err;
+}
+
+static int smmu_pmu_remove(struct platform_device *pdev)
+{
+	struct smmu_pmu *smmu_pmu = platform_get_drvdata(pdev);
+
+	perf_pmu_unregister(&smmu_pmu->pmu);
+	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
+
+	return 0;
+}
+
+static void smmu_pmu_shutdown(struct platform_device *pdev)
+{
+	struct smmu_pmu *smmu_pmu = platform_get_drvdata(pdev);
+
+	smmu_pmu_disable(&smmu_pmu->pmu);
+}
+
+static struct platform_driver smmu_pmu_driver = {
+	.driver = {
+		.name = "arm-smmu-v3-pmcg",
+	},
+	.probe = smmu_pmu_probe,
+	.remove = smmu_pmu_remove,
+	.shutdown = smmu_pmu_shutdown,
+};
+
+static int __init arm_smmu_pmu_init(void)
+{
+	cpuhp_state_num = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+						  "perf/arm/pmcg:online",
+						  NULL,
+						  smmu_pmu_offline_cpu);
+	if (cpuhp_state_num < 0)
+		return cpuhp_state_num;
+
+	return platform_driver_register(&smmu_pmu_driver);
+}
+module_init(arm_smmu_pmu_init);
+
+static void __exit arm_smmu_pmu_exit(void)
+{
+	platform_driver_unregister(&smmu_pmu_driver);
+	cpuhp_remove_multi_state(cpuhp_state_num);
+}
+
+module_exit(arm_smmu_pmu_exit);
+
+MODULE_DESCRIPTION("PMU driver for ARM SMMUv3 Performance Monitors Extension");
+MODULE_AUTHOR("Neil Leeder <nleeder@codeaurora.org>");
+MODULE_AUTHOR("Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c
index e8bd9887c566..e221e47396ab 100644
--- a/drivers/watchdog/sbsa_gwdt.c
+++ b/drivers/watchdog/sbsa_gwdt.c
@@ -161,7 +161,7 @@ static unsigned int sbsa_gwdt_get_timeleft(struct watchdog_device *wdd)
 		timeleft += readl(gwdt->control_base + SBSA_GWDT_WOR);
 
 	timeleft += lo_hi_readq(gwdt->control_base + SBSA_GWDT_WCV) -
-		    arch_counter_get_cntvct();
+		    arch_timer_read_counter();
 
 	do_div(timeleft, gwdt->clk);