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

Pull arm64 updates from Catalin Marinas:

 - MTE asynchronous support for KASan. Previously only synchronous
   (slower) mode was supported. Asynchronous is faster but does not
   allow precise identification of the illegal access.

 - Run kernel mode SIMD with softirqs disabled. This allows using NEON
   in softirq context for crypto performance improvements. The
   conditional yield support is modified to take softirqs into account
   and reduce the latency.

 - Preparatory patches for Apple M1: handle CPUs that only have the VHE
   mode available (host kernel running at EL2), add FIQ support.

 - arm64 perf updates: support for HiSilicon PA and SLLC PMU drivers,
   new functions for the HiSilicon HHA and L3C PMU, cleanups.

 - Re-introduce support for execute-only user permissions but only when
   the EPAN (Enhanced Privileged Access Never) architecture feature is
   available.

 - Disable fine-grained traps at boot and improve the documented boot
   requirements.

 - Support CONFIG_KASAN_VMALLOC on arm64 (only with KASAN_GENERIC).

 - Add hierarchical eXecute Never permissions for all page tables.

 - Add arm64 prctl(PR_PAC_{SET,GET}_ENABLED_KEYS) allowing user programs
   to control which PAC keys are enabled in a particular task.

 - arm64 kselftests for BTI and some improvements to the MTE tests.

 - Minor improvements to the compat vdso and sigpage.

 - Miscellaneous cleanups.

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (86 commits)
  arm64/sve: Add compile time checks for SVE hooks in generic functions
  arm64/kernel/probes: Use BUG_ON instead of if condition followed by BUG.
  arm64: pac: Optimize kernel entry/exit key installation code paths
  arm64: Introduce prctl(PR_PAC_{SET,GET}_ENABLED_KEYS)
  arm64: mte: make the per-task SCTLR_EL1 field usable elsewhere
  arm64/sve: Remove redundant system_supports_sve() tests
  arm64: fpsimd: run kernel mode NEON with softirqs disabled
  arm64: assembler: introduce wxN aliases for wN registers
  arm64: assembler: remove conditional NEON yield macros
  kasan, arm64: tests supports for HW_TAGS async mode
  arm64: mte: Report async tag faults before suspend
  arm64: mte: Enable async tag check fault
  arm64: mte: Conditionally compile mte_enable_kernel_*()
  arm64: mte: Enable TCO in functions that can read beyond buffer limits
  kasan: Add report for async mode
  arm64: mte: Drop arch_enable_tagging()
  kasan: Add KASAN mode kernel parameter
  arm64: mte: Add asynchronous mode support
  arm64: Get rid of CONFIG_ARM64_VHE
  arm64: Cope with CPUs stuck in VHE mode
  ...

21 files changed, 1901 insertions, 421 deletions

diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index f81e2ec90005..666d8a9b557f 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -306,7 +306,7 @@ static ssize_t cci400_pmu_cycle_event_show(struct device *dev,
 {
 	struct dev_ext_attribute *eattr = container_of(attr,
 				struct dev_ext_attribute, attr);
-	return snprintf(buf, PAGE_SIZE, "config=0x%lx\n", (unsigned long)eattr->var);
+	return sysfs_emit(buf, "config=0x%lx\n", (unsigned long)eattr->var);
 }
 
 static int cci400_get_event_idx(struct cci_pmu *cci_pmu,
@@ -525,8 +525,8 @@ static ssize_t cci5xx_pmu_global_event_show(struct device *dev,
 	struct dev_ext_attribute *eattr = container_of(attr,
 					struct dev_ext_attribute, attr);
 	/* Global events have single fixed source code */
-	return snprintf(buf, PAGE_SIZE, "event=0x%lx,source=0x%x\n",
-				(unsigned long)eattr->var, CCI5xx_PORT_GLOBAL);
+	return sysfs_emit(buf, "event=0x%lx,source=0x%x\n",
+			  (unsigned long)eattr->var, CCI5xx_PORT_GLOBAL);
 }
 
 /*
@@ -696,7 +696,7 @@ static ssize_t cci_pmu_format_show(struct device *dev,
 {
 	struct dev_ext_attribute *eattr = container_of(attr,
 				struct dev_ext_attribute, attr);
-	return snprintf(buf, PAGE_SIZE, "%s\n", (char *)eattr->var);
+	return sysfs_emit(buf, "%s\n", (char *)eattr->var);
 }
 
 static ssize_t cci_pmu_event_show(struct device *dev,
@@ -705,8 +705,8 @@ static ssize_t cci_pmu_event_show(struct device *dev,
 	struct dev_ext_attribute *eattr = container_of(attr,
 				struct dev_ext_attribute, attr);
 	/* source parameter is mandatory for normal PMU events */
-	return snprintf(buf, PAGE_SIZE, "source=?,event=0x%lx\n",
-					 (unsigned long)eattr->var);
+	return sysfs_emit(buf, "source=?,event=0x%lx\n",
+			  (unsigned long)eattr->var);
 }
 
 static int pmu_is_valid_counter(struct cci_pmu *cci_pmu, int idx)
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index a0a71c1df042..96d47cb302dd 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -221,7 +221,7 @@ static ssize_t arm_ccn_pmu_format_show(struct device *dev,
 	struct dev_ext_attribute *ea = container_of(attr,
 			struct dev_ext_attribute, attr);
 
-	return snprintf(buf, PAGE_SIZE, "%s\n", (char *)ea->var);
+	return sysfs_emit(buf, "%s\n", (char *)ea->var);
 }
 
 #define CCN_FORMAT_ATTR(_name, _config) \
@@ -326,43 +326,38 @@ static ssize_t arm_ccn_pmu_event_show(struct device *dev,
 	struct arm_ccn *ccn = pmu_to_arm_ccn(dev_get_drvdata(dev));
 	struct arm_ccn_pmu_event *event = container_of(attr,
 			struct arm_ccn_pmu_event, attr);
-	ssize_t res;
+	int res;
 
-	res = scnprintf(buf, PAGE_SIZE, "type=0x%x", event->type);
+	res = sysfs_emit(buf, "type=0x%x", event->type);
 	if (event->event)
-		res += scnprintf(buf + res, PAGE_SIZE - res, ",event=0x%x",
-				event->event);
+		res += sysfs_emit_at(buf, res, ",event=0x%x", event->event);
 	if (event->def)
-		res += scnprintf(buf + res, PAGE_SIZE - res, ",%s",
-				event->def);
+		res += sysfs_emit_at(buf, res, ",%s", event->def);
 	if (event->mask)
-		res += scnprintf(buf + res, PAGE_SIZE - res, ",mask=0x%x",
-				event->mask);
+		res += sysfs_emit_at(buf, res, ",mask=0x%x", event->mask);
 
 	/* Arguments required by an event */
 	switch (event->type) {
 	case CCN_TYPE_CYCLES:
 		break;
 	case CCN_TYPE_XP:
-		res += scnprintf(buf + res, PAGE_SIZE - res,
-				",xp=?,vc=?");
+		res += sysfs_emit_at(buf, res, ",xp=?,vc=?");
 		if (event->event == CCN_EVENT_WATCHPOINT)
-			res += scnprintf(buf + res, PAGE_SIZE - res,
+			res += sysfs_emit_at(buf, res,
 					",port=?,dir=?,cmp_l=?,cmp_h=?,mask=?");
 		else
-			res += scnprintf(buf + res, PAGE_SIZE - res,
-					",bus=?");
+			res += sysfs_emit_at(buf, res, ",bus=?");
 
 		break;
 	case CCN_TYPE_MN:
-		res += scnprintf(buf + res, PAGE_SIZE - res, ",node=%d", ccn->mn_id);
+		res += sysfs_emit_at(buf, res, ",node=%d", ccn->mn_id);
 		break;
 	default:
-		res += scnprintf(buf + res, PAGE_SIZE - res, ",node=?");
+		res += sysfs_emit_at(buf, res, ",node=?");
 		break;
 	}
 
-	res += scnprintf(buf + res, PAGE_SIZE - res, "\n");
+	res += sysfs_emit_at(buf, res, "\n");
 
 	return res;
 }
@@ -476,7 +471,7 @@ static ssize_t arm_ccn_pmu_cmp_mask_show(struct device *dev,
 	struct arm_ccn *ccn = pmu_to_arm_ccn(dev_get_drvdata(dev));
 	u64 *mask = arm_ccn_pmu_get_cmp_mask(ccn, attr->attr.name);
 
-	return mask ? snprintf(buf, PAGE_SIZE, "0x%016llx\n", *mask) : -EINVAL;
+	return mask ? sysfs_emit(buf, "0x%016llx\n", *mask) : -EINVAL;
 }
 
 static ssize_t arm_ccn_pmu_cmp_mask_store(struct device *dev,
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index 1328159fe564..56a5c355701d 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -348,19 +348,19 @@ static ssize_t arm_cmn_event_show(struct device *dev,
 	eattr = container_of(attr, typeof(*eattr), attr);
 
 	if (eattr->type == CMN_TYPE_DTC)
-		return snprintf(buf, PAGE_SIZE, "type=0x%x\n", eattr->type);
+		return sysfs_emit(buf, "type=0x%x\n", eattr->type);
 
 	if (eattr->type == CMN_TYPE_WP)
-		return snprintf(buf, PAGE_SIZE,
-				"type=0x%x,eventid=0x%x,wp_dev_sel=?,wp_chn_sel=?,wp_grp=?,wp_val=?,wp_mask=?\n",
-				eattr->type, eattr->eventid);
+		return sysfs_emit(buf,
+				  "type=0x%x,eventid=0x%x,wp_dev_sel=?,wp_chn_sel=?,wp_grp=?,wp_val=?,wp_mask=?\n",
+				  eattr->type, eattr->eventid);
 
 	if (arm_cmn_is_occup_event(eattr->type, eattr->eventid))
-		return snprintf(buf, PAGE_SIZE, "type=0x%x,eventid=0x%x,occupid=0x%x\n",
-				eattr->type, eattr->eventid, eattr->occupid);
+		return sysfs_emit(buf, "type=0x%x,eventid=0x%x,occupid=0x%x\n",
+				  eattr->type, eattr->eventid, eattr->occupid);
 
-	return snprintf(buf, PAGE_SIZE, "type=0x%x,eventid=0x%x\n",
-			eattr->type, eattr->eventid);
+	return sysfs_emit(buf, "type=0x%x,eventid=0x%x\n", eattr->type,
+			  eattr->eventid);
 }
 
 static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj,
@@ -560,12 +560,12 @@ static ssize_t arm_cmn_format_show(struct device *dev,
 	int lo = __ffs(fmt->field), hi = __fls(fmt->field);
 
 	if (lo == hi)
-		return snprintf(buf, PAGE_SIZE, "config:%d\n", lo);
+		return sysfs_emit(buf, "config:%d\n", lo);
 
 	if (!fmt->config)
-		return snprintf(buf, PAGE_SIZE, "config:%d-%d\n", lo, hi);
+		return sysfs_emit(buf, "config:%d-%d\n", lo, hi);
 
-	return snprintf(buf, PAGE_SIZE, "config%d:%d-%d\n", fmt->config, lo, hi);
+	return sysfs_emit(buf, "config%d:%d-%d\n", fmt->config, lo, hi);
 }
 
 #define _CMN_FORMAT_ATTR(_name, _cfg, _fld)				\
diff --git a/drivers/perf/arm_dmc620_pmu.c b/drivers/perf/arm_dmc620_pmu.c
index f2a85500258d..b6c2511d59af 100644
--- a/drivers/perf/arm_dmc620_pmu.c
+++ b/drivers/perf/arm_dmc620_pmu.c
@@ -113,7 +113,7 @@ dmc620_pmu_event_show(struct device *dev,
 
 	eattr = container_of(attr, typeof(*eattr), attr);
 
-	return sprintf(page, "event=0x%x,clkdiv2=0x%x\n", eattr->eventid, eattr->clkdiv2);
+	return sysfs_emit(page, "event=0x%x,clkdiv2=0x%x\n", eattr->eventid, eattr->clkdiv2);
 }
 
 #define DMC620_PMU_EVENT_ATTR(_name, _eventid, _clkdiv2)		\
diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c
index 0459a3403469..196faea074d0 100644
--- a/drivers/perf/arm_dsu_pmu.c
+++ b/drivers/perf/arm_dsu_pmu.c
@@ -136,8 +136,7 @@ static ssize_t dsu_pmu_sysfs_event_show(struct device *dev,
 {
 	struct dev_ext_attribute *eattr = container_of(attr,
 					struct dev_ext_attribute, attr);
-	return snprintf(buf, PAGE_SIZE, "event=0x%lx\n",
-					 (unsigned long)eattr->var);
+	return sysfs_emit(buf, "event=0x%lx\n", (unsigned long)eattr->var);
 }
 
 static ssize_t dsu_pmu_sysfs_format_show(struct device *dev,
@@ -146,7 +145,7 @@ static ssize_t dsu_pmu_sysfs_format_show(struct device *dev,
 {
 	struct dev_ext_attribute *eattr = container_of(attr,
 					struct dev_ext_attribute, attr);
-	return snprintf(buf, PAGE_SIZE, "%s\n", (char *)eattr->var);
+	return sysfs_emit(buf, "%s\n", (char *)eattr->var);
 }
 
 static ssize_t dsu_pmu_cpumask_show(struct device *dev,
diff --git a/drivers/perf/arm_pmu_platform.c b/drivers/perf/arm_pmu_platform.c
index 933bd8410fc2..513de1f54e2d 100644
--- a/drivers/perf/arm_pmu_platform.c
+++ b/drivers/perf/arm_pmu_platform.c
@@ -6,6 +6,7 @@
  * Copyright (C) 2010 ARM Ltd., Will Deacon <will.deacon@arm.com>
  */
 #define pr_fmt(fmt) "hw perfevents: " fmt
+#define dev_fmt pr_fmt
 
 #include <linux/bug.h>
 #include <linux/cpumask.h>
@@ -62,7 +63,7 @@ static bool pmu_has_irq_affinity(struct device_node *node)
 	return !!of_find_property(node, "interrupt-affinity", NULL);
 }
 
-static int pmu_parse_irq_affinity(struct device_node *node, int i)
+static int pmu_parse_irq_affinity(struct device *dev, int i)
 {
 	struct device_node *dn;
 	int cpu;
@@ -72,19 +73,18 @@ static int pmu_parse_irq_affinity(struct device_node *node, int i)
 	 * affinity matches our logical CPU order, as we used to assume.
 	 * This is fragile, so we'll warn in pmu_parse_irqs().
 	 */
-	if (!pmu_has_irq_affinity(node))
+	if (!pmu_has_irq_affinity(dev->of_node))
 		return i;
 
-	dn = of_parse_phandle(node, "interrupt-affinity", i);
+	dn = of_parse_phandle(dev->of_node, "interrupt-affinity", i);
 	if (!dn) {
-		pr_warn("failed to parse interrupt-affinity[%d] for %pOFn\n",
-			i, node);
+		dev_warn(dev, "failed to parse interrupt-affinity[%d]\n", i);
 		return -EINVAL;
 	}
 
 	cpu = of_cpu_node_to_id(dn);
 	if (cpu < 0) {
-		pr_warn("failed to find logical CPU for %pOFn\n", dn);
+		dev_warn(dev, "failed to find logical CPU for %pOFn\n", dn);
 		cpu = nr_cpu_ids;
 	}
 
@@ -98,19 +98,18 @@ static int pmu_parse_irqs(struct arm_pmu *pmu)
 	int i = 0, num_irqs;
 	struct platform_device *pdev = pmu->plat_device;
 	struct pmu_hw_events __percpu *hw_events = pmu->hw_events;
+	struct device *dev = &pdev->dev;
 
 	num_irqs = platform_irq_count(pdev);
-	if (num_irqs < 0) {
-		pr_err("unable to count PMU IRQs\n");
-		return num_irqs;
-	}
+	if (num_irqs < 0)
+		return dev_err_probe(dev, num_irqs, "unable to count PMU IRQs\n");
 
 	/*
 	 * In this case we have no idea which CPUs are covered by the PMU.
 	 * To match our prior behaviour, we assume all CPUs in this case.
 	 */
 	if (num_irqs == 0) {
-		pr_warn("no irqs for PMU, sampling events not supported\n");
+		dev_warn(dev, "no irqs for PMU, sampling events not supported\n");
 		pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 		cpumask_setall(&pmu->supported_cpus);
 		return 0;
@@ -122,10 +121,8 @@ static int pmu_parse_irqs(struct arm_pmu *pmu)
 			return pmu_parse_percpu_irq(pmu, irq);
 	}
 
-	if (nr_cpu_ids != 1 && !pmu_has_irq_affinity(pdev->dev.of_node)) {
-		pr_warn("no interrupt-affinity property for %pOF, guessing.\n",
-			pdev->dev.of_node);
-	}
+	if (nr_cpu_ids != 1 && !pmu_has_irq_affinity(dev->of_node))
+		dev_warn(dev, "no interrupt-affinity property, guessing.\n");
 
 	for (i = 0; i < num_irqs; i++) {
 		int cpu, irq;
@@ -135,18 +132,18 @@ static int pmu_parse_irqs(struct arm_pmu *pmu)
 			continue;
 
 		if (irq_is_percpu_devid(irq)) {
-			pr_warn("multiple PPIs or mismatched SPI/PPI detected\n");
+			dev_warn(dev, "multiple PPIs or mismatched SPI/PPI detected\n");
 			return -EINVAL;
 		}
 
-		cpu = pmu_parse_irq_affinity(pdev->dev.of_node, i);
+		cpu = pmu_parse_irq_affinity(dev, i);
 		if (cpu < 0)
 			return cpu;
 		if (cpu >= nr_cpu_ids)
 			continue;
 
 		if (per_cpu(hw_events->irq, cpu)) {
-			pr_warn("multiple PMU IRQs for the same CPU detected\n");
+			dev_warn(dev, "multiple PMU IRQs for the same CPU detected\n");
 			return -EINVAL;
 		}
 
@@ -191,9 +188,8 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 			 const struct of_device_id *of_table,
 			 const struct pmu_probe_info *probe_table)
 {
-	const struct of_device_id *of_id;
 	armpmu_init_fn init_fn;
-	struct device_node *node = pdev->dev.of_node;
+	struct device *dev = &pdev->dev;
 	struct arm_pmu *pmu;
 	int ret = -ENODEV;
 
@@ -207,15 +203,14 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 	if (ret)
 		goto out_free;
 
-	if (node && (of_id = of_match_node(of_table, pdev->dev.of_node))) {
-		init_fn = of_id->data;
-
-		pmu->secure_access = of_property_read_bool(pdev->dev.of_node,
+	init_fn = of_device_get_match_data(dev);
+	if (init_fn) {
+		pmu->secure_access = of_property_read_bool(dev->of_node,
 							   "secure-reg-access");
 
 		/* arm64 systems boot only as non-secure */
 		if (IS_ENABLED(CONFIG_ARM64) && pmu->secure_access) {
-			pr_warn("ignoring \"secure-reg-access\" property for arm64\n");
+			dev_warn(dev, "ignoring \"secure-reg-access\" property for arm64\n");
 			pmu->secure_access = false;
 		}
 
@@ -226,7 +221,7 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 	}
 
 	if (ret) {
-		pr_info("%pOF: failed to probe PMU!\n", node);
+		dev_err(dev, "failed to probe PMU!\n");
 		goto out_free;
 	}
 
@@ -235,15 +230,16 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 		goto out_free_irqs;
 
 	ret = armpmu_register(pmu);
-	if (ret)
-		goto out_free;
+	if (ret) {
+		dev_err(dev, "failed to register PMU devices!\n");
+		goto out_free_irqs;
+	}
 
 	return 0;
 
 out_free_irqs:
 	armpmu_free_irqs(pmu);
 out_free:
-	pr_info("%pOF: failed to register PMU devices!\n", node);
 	armpmu_free(pmu);
 	return ret;
 }
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
index 8ff7a67f691c..ff6fab4bae30 100644
--- a/drivers/perf/arm_smmuv3_pmu.c
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -506,30 +506,24 @@ static ssize_t smmu_pmu_event_show(struct device *dev,
 
 	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
 
-	return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+	return sysfs_emit(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);
+#define SMMU_EVENT_ATTR(name, config)					\
+	(&((struct perf_pmu_events_attr) {				\
+		.attr = __ATTR(name, 0444, smmu_pmu_event_show, NULL),	\
+		.id = config,						\
+	}).attr.attr)
 
 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,
+	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),
 	NULL
 };
 
@@ -560,7 +554,7 @@ static ssize_t smmu_pmu_identifier_attr_show(struct device *dev,
 {
 	struct smmu_pmu *smmu_pmu = to_smmu_pmu(dev_get_drvdata(dev));
 
-	return snprintf(page, PAGE_SIZE, "0x%08x\n", smmu_pmu->iidr);
+	return sysfs_emit(page, "0x%08x\n", smmu_pmu->iidr);
 }
 
 static umode_t smmu_pmu_identifier_attr_visible(struct kobject *kobj,
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index d3929ccebfd2..8a1e86ab2d8e 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -126,8 +126,7 @@ static ssize_t arm_spe_pmu_cap_show(struct device *dev,
 		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));
+	return sysfs_emit(buf, "%u\n", arm_spe_pmu_cap_get(spe_pmu, cap));
 }
 
 #define SPE_EXT_ATTR_ENTRY(_name, _func, _var)				\
diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c
index be1f26b62ddb..2bbb93188064 100644
--- a/drivers/perf/fsl_imx8_ddr_perf.c
+++ b/drivers/perf/fsl_imx8_ddr_perf.c
@@ -110,7 +110,7 @@ static ssize_t ddr_perf_identifier_show(struct device *dev,
 {
 	struct ddr_pmu *pmu = dev_get_drvdata(dev);
 
-	return sprintf(page, "%s\n", pmu->devtype_data->identifier);
+	return sysfs_emit(page, "%s\n", pmu->devtype_data->identifier);
 }
 
 static umode_t ddr_perf_identifier_attr_visible(struct kobject *kobj,
@@ -170,8 +170,7 @@ static ssize_t ddr_perf_filter_cap_show(struct device *dev,
 		container_of(attr, struct dev_ext_attribute, attr);
 	int cap = (long)ea->var;
 
-	return snprintf(buf, PAGE_SIZE, "%u\n",
-			ddr_perf_filter_cap_get(pmu, cap));
+	return sysfs_emit(buf, "%u\n", ddr_perf_filter_cap_get(pmu, cap));
 }
 
 #define PERF_EXT_ATTR_ENTRY(_name, _func, _var)				\
@@ -220,7 +219,7 @@ ddr_pmu_event_show(struct device *dev, struct device_attribute *attr,
 	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);
+	return sysfs_emit(page, "event=0x%02llx\n", pmu_attr->id);
 }
 
 #define IMX8_DDR_PMU_EVENT_ATTR(_name, _id)				\
diff --git a/drivers/perf/hisilicon/Makefile b/drivers/perf/hisilicon/Makefile
index e8377061845f..7643c9f93e36 100644
--- a/drivers/perf/hisilicon/Makefile
+++ b/drivers/perf/hisilicon/Makefile
@@ -1,3 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o \
-			  hisi_uncore_hha_pmu.o hisi_uncore_ddrc_pmu.o
+			  hisi_uncore_hha_pmu.o hisi_uncore_ddrc_pmu.o hisi_uncore_sllc_pmu.o \
+			  hisi_uncore_pa_pmu.o
diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
index ac1a8c120a00..7c8a4bc21db4 100644
--- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
@@ -14,12 +14,11 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/list.h>
-#include <linux/platform_device.h>
 #include <linux/smp.h>
 
 #include "hisi_uncore_pmu.h"
 
-/* DDRC register definition */
+/* DDRC register definition in v1 */
 #define DDRC_PERF_CTRL		0x010
 #define DDRC_FLUX_WR		0x380
 #define DDRC_FLUX_RD		0x384
@@ -35,12 +34,24 @@
 #define DDRC_INT_CLEAR		0x6d0
 #define DDRC_VERSION		0x710
 
+/* DDRC register definition in v2 */
+#define DDRC_V2_INT_MASK	0x528
+#define DDRC_V2_INT_STATUS	0x52c
+#define DDRC_V2_INT_CLEAR	0x530
+#define DDRC_V2_EVENT_CNT	0xe00
+#define DDRC_V2_EVENT_CTRL	0xe70
+#define DDRC_V2_EVENT_TYPE	0xe74
+#define DDRC_V2_PERF_CTRL	0xeA0
+
 /* DDRC has 8-counters */
 #define DDRC_NR_COUNTERS	0x8
-#define DDRC_PERF_CTRL_EN	0x2
+#define DDRC_V1_PERF_CTRL_EN	0x2
+#define DDRC_V2_PERF_CTRL_EN	0x1
+#define DDRC_V1_NR_EVENTS	0x7
+#define DDRC_V2_NR_EVENTS	0x90
 
 /*
- * For DDRC PMU, there are eight-events and every event has been mapped
+ * For PMU v1, there are eight-events and every event has been mapped
  * to fixed-purpose counters which register offset is not consistent.
  * Therefore there is no write event type and we assume that event
  * code (0 to 7) is equal to counter index in PMU driver.
@@ -54,73 +65,85 @@ static const u32 ddrc_reg_off[] = {
 
 /*
  * Select the counter register offset using the counter index.
- * In DDRC there are no programmable counter, the count
- * is readed form the statistics counter register itself.
+ * In PMU v1, there are no programmable counter, the count
+ * is read form the statistics counter register itself.
  */
-static u32 hisi_ddrc_pmu_get_counter_offset(int cntr_idx)
+static u32 hisi_ddrc_pmu_v1_get_counter_offset(int cntr_idx)
 {
 	return ddrc_reg_off[cntr_idx];
 }
 
-static u64 hisi_ddrc_pmu_read_counter(struct hisi_pmu *ddrc_pmu,
-				      struct hw_perf_event *hwc)
+static u32 hisi_ddrc_pmu_v2_get_counter_offset(int cntr_idx)
 {
-	/* Use event code as counter index */
-	u32 idx = GET_DDRC_EVENTID(hwc);
-
-	if (!hisi_uncore_pmu_counter_valid(ddrc_pmu, idx)) {
-		dev_err(ddrc_pmu->dev, "Unsupported event index:%d!\n", idx);
-		return 0;
-	}
+	return DDRC_V2_EVENT_CNT + cntr_idx * 8;
+}
 
-	return readl(ddrc_pmu->base + hisi_ddrc_pmu_get_counter_offset(idx));
+static u64 hisi_ddrc_pmu_v1_read_counter(struct hisi_pmu *ddrc_pmu,
+				      struct hw_perf_event *hwc)
+{
+	return readl(ddrc_pmu->base +
+		     hisi_ddrc_pmu_v1_get_counter_offset(hwc->idx));
 }
 
-static void hisi_ddrc_pmu_write_counter(struct hisi_pmu *ddrc_pmu,
+static void hisi_ddrc_pmu_v1_write_counter(struct hisi_pmu *ddrc_pmu,
 					struct hw_perf_event *hwc, u64 val)
 {
-	u32 idx = GET_DDRC_EVENTID(hwc);
+	writel((u32)val,
+	       ddrc_pmu->base + hisi_ddrc_pmu_v1_get_counter_offset(hwc->idx));
+}
 
-	if (!hisi_uncore_pmu_counter_valid(ddrc_pmu, idx)) {
-		dev_err(ddrc_pmu->dev, "Unsupported event index:%d!\n", idx);
-		return;
-	}
+static u64 hisi_ddrc_pmu_v2_read_counter(struct hisi_pmu *ddrc_pmu,
+					 struct hw_perf_event *hwc)
+{
+	return readq(ddrc_pmu->base +
+		     hisi_ddrc_pmu_v2_get_counter_offset(hwc->idx));
+}
 
-	writel((u32)val,
-	       ddrc_pmu->base + hisi_ddrc_pmu_get_counter_offset(idx));
+static void hisi_ddrc_pmu_v2_write_counter(struct hisi_pmu *ddrc_pmu,
+					   struct hw_perf_event *hwc, u64 val)
+{
+	writeq(val,
+	       ddrc_pmu->base + hisi_ddrc_pmu_v2_get_counter_offset(hwc->idx));
 }
 
 /*
- * For DDRC PMU, event has been mapped to fixed-purpose counter by hardware,
- * so there is no need to write event type.
+ * For DDRC PMU v1, event has been mapped to fixed-purpose counter by hardware,
+ * so there is no need to write event type, while it is programmable counter in
+ * PMU v2.
  */
 static void hisi_ddrc_pmu_write_evtype(struct hisi_pmu *hha_pmu, int idx,
 				       u32 type)
 {
+	u32 offset;
+
+	if (hha_pmu->identifier >= HISI_PMU_V2) {
+		offset = DDRC_V2_EVENT_TYPE + 4 * idx;
+		writel(type, hha_pmu->base + offset);
+	}
 }
 
-static void hisi_ddrc_pmu_start_counters(struct hisi_pmu *ddrc_pmu)
+static void hisi_ddrc_pmu_v1_start_counters(struct hisi_pmu *ddrc_pmu)
 {
 	u32 val;
 
 	/* Set perf_enable in DDRC_PERF_CTRL to start event counting */
 	val = readl(ddrc_pmu->base + DDRC_PERF_CTRL);
-	val |= DDRC_PERF_CTRL_EN;
+	val |= DDRC_V1_PERF_CTRL_EN;
 	writel(val, ddrc_pmu->base + DDRC_PERF_CTRL);
 }
 
-static void hisi_ddrc_pmu_stop_counters(struct hisi_pmu *ddrc_pmu)
+static void hisi_ddrc_pmu_v1_stop_counters(struct hisi_pmu *ddrc_pmu)
 {
 	u32 val;
 
 	/* Clear perf_enable in DDRC_PERF_CTRL to stop event counting */
 	val = readl(ddrc_pmu->base + DDRC_PERF_CTRL);
-	val &= ~DDRC_PERF_CTRL_EN;
+	val &= ~DDRC_V1_PERF_CTRL_EN;
 	writel(val, ddrc_pmu->base + DDRC_PERF_CTRL);
 }
 
-static void hisi_ddrc_pmu_enable_counter(struct hisi_pmu *ddrc_pmu,
-					 struct hw_perf_event *hwc)
+static void hisi_ddrc_pmu_v1_enable_counter(struct hisi_pmu *ddrc_pmu,
+					    struct hw_perf_event *hwc)
 {
 	u32 val;
 
@@ -130,8 +153,8 @@ static void hisi_ddrc_pmu_enable_counter(struct hisi_pmu *ddrc_pmu,
 	writel(val, ddrc_pmu->base + DDRC_EVENT_CTRL);
 }
 
-static void hisi_ddrc_pmu_disable_counter(struct hisi_pmu *ddrc_pmu,
-					  struct hw_perf_event *hwc)
+static void hisi_ddrc_pmu_v1_disable_counter(struct hisi_pmu *ddrc_pmu,
+					     struct hw_perf_event *hwc)
 {
 	u32 val;
 
@@ -141,7 +164,7 @@ static void hisi_ddrc_pmu_disable_counter(struct hisi_pmu *ddrc_pmu,
 	writel(val, ddrc_pmu->base + DDRC_EVENT_CTRL);
 }
 
-static int hisi_ddrc_pmu_get_event_idx(struct perf_event *event)
+static int hisi_ddrc_pmu_v1_get_event_idx(struct perf_event *event)
 {
 	struct hisi_pmu *ddrc_pmu = to_hisi_pmu(event->pmu);
 	unsigned long *used_mask = ddrc_pmu->pmu_events.used_mask;
@@ -157,87 +180,117 @@ static int hisi_ddrc_pmu_get_event_idx(struct perf_event *event)
 	return idx;
 }
 
-static void hisi_ddrc_pmu_enable_counter_int(struct hisi_pmu *ddrc_pmu,
+static int hisi_ddrc_pmu_v2_get_event_idx(struct perf_event *event)
+{
+	return hisi_uncore_pmu_get_event_idx(event);
+}
+
+static void hisi_ddrc_pmu_v2_start_counters(struct hisi_pmu *ddrc_pmu)
+{
+	u32 val;
+
+	val = readl(ddrc_pmu->base + DDRC_V2_PERF_CTRL);
+	val |= DDRC_V2_PERF_CTRL_EN;
+	writel(val, ddrc_pmu->base + DDRC_V2_PERF_CTRL);
+}
+
+static void hisi_ddrc_pmu_v2_stop_counters(struct hisi_pmu *ddrc_pmu)
+{
+	u32 val;
+
+	val = readl(ddrc_pmu->base + DDRC_V2_PERF_CTRL);
+	val &= ~DDRC_V2_PERF_CTRL_EN;
+	writel(val, ddrc_pmu->base + DDRC_V2_PERF_CTRL);
+}
+
+static void hisi_ddrc_pmu_v2_enable_counter(struct hisi_pmu *ddrc_pmu,
+					    struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	val = readl(ddrc_pmu->base + DDRC_V2_EVENT_CTRL);
+	val |= 1 << hwc->idx;
+	writel(val, ddrc_pmu->base + DDRC_V2_EVENT_CTRL);
+}
+
+static void hisi_ddrc_pmu_v2_disable_counter(struct hisi_pmu *ddrc_pmu,
 					     struct hw_perf_event *hwc)
 {
 	u32 val;
 
+	val = readl(ddrc_pmu->base + DDRC_V2_EVENT_CTRL);
+	val &= ~(1 << hwc->idx);
+	writel(val, ddrc_pmu->base + DDRC_V2_EVENT_CTRL);
+}
+
+static void hisi_ddrc_pmu_v1_enable_counter_int(struct hisi_pmu *ddrc_pmu,
+						struct hw_perf_event *hwc)
+{
+	u32 val;
+
 	/* Write 0 to enable interrupt */
 	val = readl(ddrc_pmu->base + DDRC_INT_MASK);
-	val &= ~(1 << GET_DDRC_EVENTID(hwc));
+	val &= ~(1 << hwc->idx);
 	writel(val, ddrc_pmu->base + DDRC_INT_MASK);
 }
 
-static void hisi_ddrc_pmu_disable_counter_int(struct hisi_pmu *ddrc_pmu,
-					      struct hw_perf_event *hwc)
+static void hisi_ddrc_pmu_v1_disable_counter_int(struct hisi_pmu *ddrc_pmu,
+						 struct hw_perf_event *hwc)
 {
 	u32 val;
 
 	/* Write 1 to mask interrupt */
 	val = readl(ddrc_pmu->base + DDRC_INT_MASK);
-	val |= (1 << GET_DDRC_EVENTID(hwc));
+	val |= 1 << hwc->idx;
 	writel(val, ddrc_pmu->base + DDRC_INT_MASK);
 }
 
-static irqreturn_t hisi_ddrc_pmu_isr(int irq, void *dev_id)
+static void hisi_ddrc_pmu_v2_enable_counter_int(struct hisi_pmu *ddrc_pmu,
+						struct hw_perf_event *hwc)
 {
-	struct hisi_pmu *ddrc_pmu = dev_id;
-	struct perf_event *event;
-	unsigned long overflown;
-	int idx;
-
-	/* Read the DDRC_INT_STATUS register */
-	overflown = readl(ddrc_pmu->base + DDRC_INT_STATUS);
-	if (!overflown)
-		return IRQ_NONE;
+	u32 val;
 
-	/*
-	 * Find the counter index which overflowed if the bit was set
-	 * and handle it
-	 */
-	for_each_set_bit(idx, &overflown, DDRC_NR_COUNTERS) {
-		/* Write 1 to clear the IRQ status flag */
-		writel((1 << idx), ddrc_pmu->base + DDRC_INT_CLEAR);
+	val = readl(ddrc_pmu->base + DDRC_V2_INT_MASK);
+	val &= ~(1 << hwc->idx);
+	writel(val, ddrc_pmu->base + DDRC_V2_INT_MASK);
+}
 
-		/* Get the corresponding event struct */
-		event = ddrc_pmu->pmu_events.hw_events[idx];
-		if (!event)
-			continue;
+static void hisi_ddrc_pmu_v2_disable_counter_int(struct hisi_pmu *ddrc_pmu,
+						struct hw_perf_event *hwc)
+{
+	u32 val;
 
-		hisi_uncore_pmu_event_update(event);
-		hisi_uncore_pmu_set_event_period(event);
-	}
+	val = readl(ddrc_pmu->base + DDRC_V2_INT_MASK);
+	val |= 1 << hwc->idx;
+	writel(val, ddrc_pmu->base + DDRC_V2_INT_MASK);
+}
 
-	return IRQ_HANDLED;
+static u32 hisi_ddrc_pmu_v1_get_int_status(struct hisi_pmu *ddrc_pmu)
+{
+	return readl(ddrc_pmu->base + DDRC_INT_STATUS);
 }
 
-static int hisi_ddrc_pmu_init_irq(struct hisi_pmu *ddrc_pmu,
-				  struct platform_device *pdev)
+static void hisi_ddrc_pmu_v1_clear_int_status(struct hisi_pmu *ddrc_pmu,
+					      int idx)
 {
-	int irq, ret;
-
-	/* Read and init IRQ */
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0)
-		return irq;
-
-	ret = devm_request_irq(&pdev->dev, irq, hisi_ddrc_pmu_isr,
-			       IRQF_NOBALANCING | IRQF_NO_THREAD,
-			       dev_name(&pdev->dev), ddrc_pmu);
-	if (ret < 0) {
-		dev_err(&pdev->dev,
-			"Fail to request IRQ:%d ret:%d\n", irq, ret);
-		return ret;
-	}
+	writel(1 << idx, ddrc_pmu->base + DDRC_INT_CLEAR);
+}
 
-	ddrc_pmu->irq = irq;
+static u32 hisi_ddrc_pmu_v2_get_int_status(struct hisi_pmu *ddrc_pmu)
+{
+	return readl(ddrc_pmu->base + DDRC_V2_INT_STATUS);
+}
 
-	return 0;
+static void hisi_ddrc_pmu_v2_clear_int_status(struct hisi_pmu *ddrc_pmu,
+					      int idx)
+{
+	writel(1 << idx, ddrc_pmu->base + DDRC_V2_INT_CLEAR);
 }
 
 static const struct acpi_device_id hisi_ddrc_pmu_acpi_match[] = {
 	{ "HISI0233", },
-	{},
+	{ "HISI0234", },
+	{}
 };
 MODULE_DEVICE_TABLE(acpi, hisi_ddrc_pmu_acpi_match);
 
@@ -269,21 +322,38 @@ static int hisi_ddrc_pmu_init_data(struct platform_device *pdev,
 	}
 
 	ddrc_pmu->identifier = readl(ddrc_pmu->base + DDRC_VERSION);
+	if (ddrc_pmu->identifier >= HISI_PMU_V2) {
+		if (device_property_read_u32(&pdev->dev, "hisilicon,sub-id",
+					     &ddrc_pmu->sub_id)) {
+			dev_err(&pdev->dev, "Can not read sub-id!\n");
+			return -EINVAL;
+		}
+	}
 
 	return 0;
 }
 
-static struct attribute *hisi_ddrc_pmu_format_attr[] = {
+static struct attribute *hisi_ddrc_pmu_v1_format_attr[] = {
 	HISI_PMU_FORMAT_ATTR(event, "config:0-4"),
 	NULL,
 };
 
-static const struct attribute_group hisi_ddrc_pmu_format_group = {
+static const struct attribute_group hisi_ddrc_pmu_v1_format_group = {
+	.name = "format",
+	.attrs = hisi_ddrc_pmu_v1_format_attr,
+};
+
+static struct attribute *hisi_ddrc_pmu_v2_format_attr[] = {
+	HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
+	NULL
+};
+
+static const struct attribute_group hisi_ddrc_pmu_v2_format_group = {
 	.name = "format",
-	.attrs = hisi_ddrc_pmu_format_attr,
+	.attrs = hisi_ddrc_pmu_v2_format_attr,
 };
 
-static struct attribute *hisi_ddrc_pmu_events_attr[] = {
+static struct attribute *hisi_ddrc_pmu_v1_events_attr[] = {
 	HISI_PMU_EVENT_ATTR(flux_wr,		0x00),
 	HISI_PMU_EVENT_ATTR(flux_rd,		0x01),
 	HISI_PMU_EVENT_ATTR(flux_wcmd,		0x02),
@@ -295,9 +365,21 @@ static struct attribute *hisi_ddrc_pmu_events_attr[] = {
 	NULL,
 };
 
-static const struct attribute_group hisi_ddrc_pmu_events_group = {
+static const struct attribute_group hisi_ddrc_pmu_v1_events_group = {
 	.name = "events",
-	.attrs = hisi_ddrc_pmu_events_attr,
+	.attrs = hisi_ddrc_pmu_v1_events_attr,
+};
+
+static struct attribute *hisi_ddrc_pmu_v2_events_attr[] = {
+	HISI_PMU_EVENT_ATTR(cycles,		0x00),
+	HISI_PMU_EVENT_ATTR(flux_wr,		0x83),
+	HISI_PMU_EVENT_ATTR(flux_rd,		0x84),
+	NULL
+};
+
+static const struct attribute_group hisi_ddrc_pmu_v2_events_group = {
+	.name = "events",
+	.attrs = hisi_ddrc_pmu_v2_events_attr,
 };
 
 static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL);
@@ -323,25 +405,50 @@ static const struct attribute_group hisi_ddrc_pmu_identifier_group = {
 	.attrs = hisi_ddrc_pmu_identifier_attrs,
 };
 
-static const struct attribute_group *hisi_ddrc_pmu_attr_groups[] = {
-	&hisi_ddrc_pmu_format_group,
-	&hisi_ddrc_pmu_events_group,
+static const struct attribute_group *hisi_ddrc_pmu_v1_attr_groups[] = {
+	&hisi_ddrc_pmu_v1_format_group,
+	&hisi_ddrc_pmu_v1_events_group,
 	&hisi_ddrc_pmu_cpumask_attr_group,
 	&hisi_ddrc_pmu_identifier_group,
 	NULL,
 };
 
-static const struct hisi_uncore_ops hisi_uncore_ddrc_ops = {
+static const struct attribute_group *hisi_ddrc_pmu_v2_attr_groups[] = {
+	&hisi_ddrc_pmu_v2_format_group,
+	&hisi_ddrc_pmu_v2_events_group,
+	&hisi_ddrc_pmu_cpumask_attr_group,
+	&hisi_ddrc_pmu_identifier_group,
+	NULL
+};
+
+static const struct hisi_uncore_ops hisi_uncore_ddrc_v1_ops = {
+	.write_evtype           = hisi_ddrc_pmu_write_evtype,
+	.get_event_idx		= hisi_ddrc_pmu_v1_get_event_idx,
+	.start_counters		= hisi_ddrc_pmu_v1_start_counters,
+	.stop_counters		= hisi_ddrc_pmu_v1_stop_counters,
+	.enable_counter		= hisi_ddrc_pmu_v1_enable_counter,
+	.disable_counter	= hisi_ddrc_pmu_v1_disable_counter,
+	.enable_counter_int	= hisi_ddrc_pmu_v1_enable_counter_int,
+	.disable_counter_int	= hisi_ddrc_pmu_v1_disable_counter_int,
+	.write_counter		= hisi_ddrc_pmu_v1_write_counter,
+	.read_counter		= hisi_ddrc_pmu_v1_read_counter,
+	.get_int_status		= hisi_ddrc_pmu_v1_get_int_status,
+	.clear_int_status	= hisi_ddrc_pmu_v1_clear_int_status,
+};
+
+static const struct hisi_uncore_ops hisi_uncore_ddrc_v2_ops = {
 	.write_evtype           = hisi_ddrc_pmu_write_evtype,
-	.get_event_idx		= hisi_ddrc_pmu_get_event_idx,
-	.start_counters		= hisi_ddrc_pmu_start_counters,
-	.stop_counters		= hisi_ddrc_pmu_stop_counters,
-	.enable_counter		= hisi_ddrc_pmu_enable_counter,
-	.disable_counter	= hisi_ddrc_pmu_disable_counter,
-	.enable_counter_int	= hisi_ddrc_pmu_enable_counter_int,
-	.disable_counter_int	= hisi_ddrc_pmu_disable_counter_int,
-	.write_counter		= hisi_ddrc_pmu_write_counter,
-	.read_counter		= hisi_ddrc_pmu_read_counter,
+	.get_event_idx		= hisi_ddrc_pmu_v2_get_event_idx,
+	.start_counters		= hisi_ddrc_pmu_v2_start_counters,
+	.stop_counters		= hisi_ddrc_pmu_v2_stop_counters,
+	.enable_counter		= hisi_ddrc_pmu_v2_enable_counter,
+	.disable_counter	= hisi_ddrc_pmu_v2_disable_counter,
+	.enable_counter_int	= hisi_ddrc_pmu_v2_enable_counter_int,
+	.disable_counter_int	= hisi_ddrc_pmu_v2_disable_counter_int,
+	.write_counter		= hisi_ddrc_pmu_v2_write_counter,
+	.read_counter		= hisi_ddrc_pmu_v2_read_counter,
+	.get_int_status		= hisi_ddrc_pmu_v2_get_int_status,
+	.clear_int_status	= hisi_ddrc_pmu_v2_clear_int_status,
 };
 
 static int hisi_ddrc_pmu_dev_probe(struct platform_device *pdev,
@@ -353,16 +460,25 @@ static int hisi_ddrc_pmu_dev_probe(struct platform_device *pdev,
 	if (ret)
 		return ret;
 
-	ret = hisi_ddrc_pmu_init_irq(ddrc_pmu, pdev);
+	ret = hisi_uncore_pmu_init_irq(ddrc_pmu, pdev);
 	if (ret)
 		return ret;
 
+	if (ddrc_pmu->identifier >= HISI_PMU_V2) {
+		ddrc_pmu->counter_bits = 48;
+		ddrc_pmu->check_event = DDRC_V2_NR_EVENTS;
+		ddrc_pmu->pmu_events.attr_groups = hisi_ddrc_pmu_v2_attr_groups;
+		ddrc_pmu->ops = &hisi_uncore_ddrc_v2_ops;
+	} else {
+		ddrc_pmu->counter_bits = 32;
+		ddrc_pmu->check_event = DDRC_V1_NR_EVENTS;
+		ddrc_pmu->pmu_events.attr_groups = hisi_ddrc_pmu_v1_attr_groups;
+		ddrc_pmu->ops = &hisi_uncore_ddrc_v1_ops;
+	}
+
 	ddrc_pmu->num_counters = DDRC_NR_COUNTERS;
-	ddrc_pmu->counter_bits = 32;
-	ddrc_pmu->ops = &hisi_uncore_ddrc_ops;
 	ddrc_pmu->dev = &pdev->dev;
 	ddrc_pmu->on_cpu = -1;
-	ddrc_pmu->check_event = 7;
 
 	return 0;
 }
@@ -390,8 +506,16 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_ddrc%u",
-			      ddrc_pmu->sccl_id, ddrc_pmu->index_id);
+	if (ddrc_pmu->identifier >= HISI_PMU_V2)
+		name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+				      "hisi_sccl%u_ddrc%u_%u",
+				      ddrc_pmu->sccl_id, ddrc_pmu->index_id,
+				      ddrc_pmu->sub_id);
+	else
+		name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+				      "hisi_sccl%u_ddrc%u", ddrc_pmu->sccl_id,
+				      ddrc_pmu->index_id);
+
 	ddrc_pmu->pmu = (struct pmu) {
 		.name		= name,
 		.module		= THIS_MODULE,
@@ -404,7 +528,7 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev)
 		.start		= hisi_uncore_pmu_start,
 		.stop		= hisi_uncore_pmu_stop,
 		.read		= hisi_uncore_pmu_read,
-		.attr_groups	= hisi_ddrc_pmu_attr_groups,
+		.attr_groups	= ddrc_pmu->pmu_events.attr_groups,
 		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
index 3402f1a395a8..0316fabe32f1 100644
--- a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
@@ -14,7 +14,6 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/list.h>
-#include <linux/platform_device.h>
 #include <linux/smp.h>
 
 #include "hisi_uncore_pmu.h"
@@ -26,18 +25,136 @@
 #define HHA_VERSION		0x1cf0
 #define HHA_PERF_CTRL		0x1E00
 #define HHA_EVENT_CTRL		0x1E04
+#define HHA_SRCID_CTRL		0x1E08
+#define HHA_DATSRC_CTRL		0x1BF0
 #define HHA_EVENT_TYPE0		0x1E80
 /*
- * Each counter is 48-bits and [48:63] are reserved
- * which are Read-As-Zero and Writes-Ignored.
+ * If the HW version only supports a 48-bit counter, then
+ * bits [63:48] are reserved, which are Read-As-Zero and
+ * Writes-Ignored.
  */
 #define HHA_CNT0_LOWER		0x1F00
 
-/* HHA has 16-counters */
-#define HHA_NR_COUNTERS		0x10
+/* HHA PMU v1 has 16 counters and v2 only has 8 counters */
+#define HHA_V1_NR_COUNTERS	0x10
+#define HHA_V2_NR_COUNTERS	0x8
 
 #define HHA_PERF_CTRL_EN	0x1
+#define HHA_TRACETAG_EN		BIT(31)
+#define HHA_SRCID_EN		BIT(2)
+#define HHA_SRCID_CMD_SHIFT	6
+#define HHA_SRCID_MSK_SHIFT	20
+#define HHA_SRCID_CMD		GENMASK(16, 6)
+#define HHA_SRCID_MSK		GENMASK(30, 20)
+#define HHA_DATSRC_SKT_EN	BIT(23)
 #define HHA_EVTYPE_NONE		0xff
+#define HHA_V1_NR_EVENT		0x65
+#define HHA_V2_NR_EVENT		0xCE
+
+HISI_PMU_EVENT_ATTR_EXTRACTOR(srcid_cmd, config1, 10, 0);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(srcid_msk, config1, 21, 11);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tracetag_en, config1, 22, 22);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(datasrc_skt, config1, 23, 23);
+
+static void hisi_hha_pmu_enable_tracetag(struct perf_event *event)
+{
+	struct hisi_pmu *hha_pmu = to_hisi_pmu(event->pmu);
+	u32 tt_en = hisi_get_tracetag_en(event);
+
+	if (tt_en) {
+		u32 val;
+
+		val = readl(hha_pmu->base + HHA_SRCID_CTRL);
+		val |= HHA_TRACETAG_EN;
+		writel(val, hha_pmu->base + HHA_SRCID_CTRL);
+	}
+}
+
+static void hisi_hha_pmu_clear_tracetag(struct perf_event *event)
+{
+	struct hisi_pmu *hha_pmu = to_hisi_pmu(event->pmu);
+	u32 val;
+
+	val = readl(hha_pmu->base + HHA_SRCID_CTRL);
+	val &= ~HHA_TRACETAG_EN;
+	writel(val, hha_pmu->base + HHA_SRCID_CTRL);
+}
+
+static void hisi_hha_pmu_config_ds(struct perf_event *event)
+{
+	struct hisi_pmu *hha_pmu = to_hisi_pmu(event->pmu);
+	u32 ds_skt = hisi_get_datasrc_skt(event);
+
+	if (ds_skt) {
+		u32 val;
+
+		val = readl(hha_pmu->base + HHA_DATSRC_CTRL);
+		val |= HHA_DATSRC_SKT_EN;
+		writel(ds_skt, hha_pmu->base + HHA_DATSRC_CTRL);
+	}
+}
+
+static void hisi_hha_pmu_clear_ds(struct perf_event *event)
+{
+	struct hisi_pmu *hha_pmu = to_hisi_pmu(event->pmu);
+	u32 ds_skt = hisi_get_datasrc_skt(event);
+
+	if (ds_skt) {
+		u32 val;
+
+		val = readl(hha_pmu->base + HHA_DATSRC_CTRL);
+		val &= ~HHA_DATSRC_SKT_EN;
+		writel(ds_skt, hha_pmu->base + HHA_DATSRC_CTRL);
+	}
+}
+
+static void hisi_hha_pmu_config_srcid(struct perf_event *event)
+{
+	struct hisi_pmu *hha_pmu = to_hisi_pmu(event->pmu);
+	u32 cmd = hisi_get_srcid_cmd(event);
+
+	if (cmd) {
+		u32 val, msk;
+
+		msk = hisi_get_srcid_msk(event);
+		val = readl(hha_pmu->base + HHA_SRCID_CTRL);
+		val |= HHA_SRCID_EN | (cmd << HHA_SRCID_CMD_SHIFT) |
+			(msk << HHA_SRCID_MSK_SHIFT);
+		writel(val, hha_pmu->base + HHA_SRCID_CTRL);
+	}
+}
+
+static void hisi_hha_pmu_disable_srcid(struct perf_event *event)
+{
+	struct hisi_pmu *hha_pmu = to_hisi_pmu(event->pmu);
+	u32 cmd = hisi_get_srcid_cmd(event);
+
+	if (cmd) {
+		u32 val;
+
+		val = readl(hha_pmu->base + HHA_SRCID_CTRL);
+		val &= ~(HHA_SRCID_EN | HHA_SRCID_MSK | HHA_SRCID_CMD);
+		writel(val, hha_pmu->base + HHA_SRCID_CTRL);
+	}
+}
+
+static void hisi_hha_pmu_enable_filter(struct perf_event *event)
+{
+	if (event->attr.config1 != 0x0) {
+		hisi_hha_pmu_enable_tracetag(event);
+		hisi_hha_pmu_config_ds(event);
+		hisi_hha_pmu_config_srcid(event);
+	}
+}
+
+static void hisi_hha_pmu_disable_filter(struct perf_event *event)
+{
+	if (event->attr.config1 != 0x0) {
+		hisi_hha_pmu_disable_srcid(event);
+		hisi_hha_pmu_clear_ds(event);
+		hisi_hha_pmu_clear_tracetag(event);
+	}
+}
 
 /*
  * Select the counter register offset using the counter index
@@ -51,29 +168,15 @@ static u32 hisi_hha_pmu_get_counter_offset(int cntr_idx)
 static u64 hisi_hha_pmu_read_counter(struct hisi_pmu *hha_pmu,
 				     struct hw_perf_event *hwc)
 {
-	u32 idx = hwc->idx;
-
-	if (!hisi_uncore_pmu_counter_valid(hha_pmu, idx)) {
-		dev_err(hha_pmu->dev, "Unsupported event index:%d!\n", idx);
-		return 0;
-	}
-
 	/* Read 64 bits and like L3C, top 16 bits are RAZ */
-	return readq(hha_pmu->base + hisi_hha_pmu_get_counter_offset(idx));
+	return readq(hha_pmu->base + hisi_hha_pmu_get_counter_offset(hwc->idx));
 }
 
 static void hisi_hha_pmu_write_counter(struct hisi_pmu *hha_pmu,
 				       struct hw_perf_event *hwc, u64 val)
 {
-	u32 idx = hwc->idx;
-
-	if (!hisi_uncore_pmu_counter_valid(hha_pmu, idx)) {
-		dev_err(hha_pmu->dev, "Unsupported event index:%d!\n", idx);
-		return;
-	}
-
 	/* Write 64 bits and like L3C, top 16 bits are WI */
-	writeq(val, hha_pmu->base + hisi_hha_pmu_get_counter_offset(idx));
+	writeq(val, hha_pmu->base + hisi_hha_pmu_get_counter_offset(hwc->idx));
 }
 
 static void hisi_hha_pmu_write_evtype(struct hisi_pmu *hha_pmu, int idx,
@@ -169,65 +272,20 @@ static void hisi_hha_pmu_disable_counter_int(struct hisi_pmu *hha_pmu,
 	writel(val, hha_pmu->base + HHA_INT_MASK);
 }
 
-static irqreturn_t hisi_hha_pmu_isr(int irq, void *dev_id)
+static u32 hisi_hha_pmu_get_int_status(struct hisi_pmu *hha_pmu)
 {
-	struct hisi_pmu *hha_pmu = dev_id;
-	struct perf_event *event;
-	unsigned long overflown;
-	int idx;
-
-	/* Read HHA_INT_STATUS register */
-	overflown = readl(hha_pmu->base + HHA_INT_STATUS);
-	if (!overflown)
-		return IRQ_NONE;
-
-	/*
-	 * Find the counter index which overflowed if the bit was set
-	 * and handle it
-	 */
-	for_each_set_bit(idx, &overflown, HHA_NR_COUNTERS) {
-		/* Write 1 to clear the IRQ status flag */
-		writel((1 << idx), hha_pmu->base + HHA_INT_CLEAR);
-
-		/* Get the corresponding event struct */
-		event = hha_pmu->pmu_events.hw_events[idx];
-		if (!event)
-			continue;
-
-		hisi_uncore_pmu_event_update(event);
-		hisi_uncore_pmu_set_event_period(event);
-	}
-
-	return IRQ_HANDLED;
+	return readl(hha_pmu->base + HHA_INT_STATUS);
 }
 
-static int hisi_hha_pmu_init_irq(struct hisi_pmu *hha_pmu,
-				 struct platform_device *pdev)
+static void hisi_hha_pmu_clear_int_status(struct hisi_pmu *hha_pmu, int idx)
 {
-	int irq, ret;
-
-	/* Read and init IRQ */
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0)
-		return irq;
-
-	ret = devm_request_irq(&pdev->dev, irq, hisi_hha_pmu_isr,
-			      IRQF_NOBALANCING | IRQF_NO_THREAD,
-			      dev_name(&pdev->dev), hha_pmu);
-	if (ret < 0) {
-		dev_err(&pdev->dev,
-			"Fail to request IRQ:%d ret:%d\n", irq, ret);
-		return ret;
-	}
-
-	hha_pmu->irq = irq;
-
-	return 0;
+	writel(1 << idx, hha_pmu->base + HHA_INT_CLEAR);
 }
 
 static const struct acpi_device_id hisi_hha_pmu_acpi_match[] = {
 	{ "HISI0243", },
-	{},
+	{ "HISI0244", },
+	{}
 };
 MODULE_DEVICE_TABLE(acpi, hisi_hha_pmu_acpi_match);
 
@@ -237,13 +295,6 @@ static int hisi_hha_pmu_init_data(struct platform_device *pdev,
 	unsigned long long id;
 	acpi_status status;
 
-	status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev),
-				       "_UID", NULL, &id);
-	if (ACPI_FAILURE(status))
-		return -EINVAL;
-
-	hha_pmu->index_id = id;
-
 	/*
 	 * Use SCCL_ID and UID to identify the HHA PMU, while
 	 * SCCL_ID is in MPIDR[aff2].
@@ -253,6 +304,22 @@ static int hisi_hha_pmu_init_data(struct platform_device *pdev,
 		dev_err(&pdev->dev, "Can not read hha sccl-id!\n");
 		return -EINVAL;
 	}
+
+	/*
+	 * Early versions of BIOS support _UID by mistake, so we support
+	 * both "hisilicon, idx-id" as preference, if available.
+	 */
+	if (device_property_read_u32(&pdev->dev, "hisilicon,idx-id",
+				     &hha_pmu->index_id)) {
+		status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev),
+					       "_UID", NULL, &id);
+		if (ACPI_FAILURE(status)) {
+			dev_err(&pdev->dev, "Cannot read idx-id!\n");
+			return -EINVAL;
+		}
+
+		hha_pmu->index_id = id;
+	}
 	/* HHA PMUs only share the same SCCL */
 	hha_pmu->ccl_id = -1;
 
@@ -267,17 +334,31 @@ static int hisi_hha_pmu_init_data(struct platform_device *pdev,
 	return 0;
 }
 
-static struct attribute *hisi_hha_pmu_format_attr[] = {
+static struct attribute *hisi_hha_pmu_v1_format_attr[] = {
 	HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
 	NULL,
 };
 
-static const struct attribute_group hisi_hha_pmu_format_group = {
+static const struct attribute_group hisi_hha_pmu_v1_format_group = {
+	.name = "format",
+	.attrs = hisi_hha_pmu_v1_format_attr,
+};
+
+static struct attribute *hisi_hha_pmu_v2_format_attr[] = {
+	HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
+	HISI_PMU_FORMAT_ATTR(srcid_cmd, "config1:0-10"),
+	HISI_PMU_FORMAT_ATTR(srcid_msk, "config1:11-21"),
+	HISI_PMU_FORMAT_ATTR(tracetag_en, "config1:22"),
+	HISI_PMU_FORMAT_ATTR(datasrc_skt, "config1:23"),
+	NULL
+};
+
+static const struct attribute_group hisi_hha_pmu_v2_format_group = {
 	.name = "format",
-	.attrs = hisi_hha_pmu_format_attr,
+	.attrs = hisi_hha_pmu_v2_format_attr,
 };
 
-static struct attribute *hisi_hha_pmu_events_attr[] = {
+static struct attribute *hisi_hha_pmu_v1_events_attr[] = {
 	HISI_PMU_EVENT_ATTR(rx_ops_num,		0x00),
 	HISI_PMU_EVENT_ATTR(rx_outer,		0x01),
 	HISI_PMU_EVENT_ATTR(rx_sccl,		0x02),
@@ -307,9 +388,23 @@ static struct attribute *hisi_hha_pmu_events_attr[] = {
 	NULL,
 };
 
-static const struct attribute_group hisi_hha_pmu_events_group = {
+static const struct attribute_group hisi_hha_pmu_v1_events_group = {
 	.name = "events",
-	.attrs = hisi_hha_pmu_events_attr,
+	.attrs = hisi_hha_pmu_v1_events_attr,
+};
+
+static struct attribute *hisi_hha_pmu_v2_events_attr[] = {
+	HISI_PMU_EVENT_ATTR(rx_ops_num,		0x00),
+	HISI_PMU_EVENT_ATTR(rx_outer,		0x01),
+	HISI_PMU_EVENT_ATTR(rx_sccl,		0x02),
+	HISI_PMU_EVENT_ATTR(hha_retry,		0x2e),
+	HISI_PMU_EVENT_ATTR(cycles,		0x55),
+	NULL
+};
+
+static const struct attribute_group hisi_hha_pmu_v2_events_group = {
+	.name = "events",
+	.attrs = hisi_hha_pmu_v2_events_attr,
 };
 
 static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL);
@@ -335,14 +430,22 @@ static const struct attribute_group hisi_hha_pmu_identifier_group = {
 	.attrs = hisi_hha_pmu_identifier_attrs,
 };
 
-static const struct attribute_group *hisi_hha_pmu_attr_groups[] = {
-	&hisi_hha_pmu_format_group,
-	&hisi_hha_pmu_events_group,
+static const struct attribute_group *hisi_hha_pmu_v1_attr_groups[] = {
+	&hisi_hha_pmu_v1_format_group,
+	&hisi_hha_pmu_v1_events_group,
 	&hisi_hha_pmu_cpumask_attr_group,
 	&hisi_hha_pmu_identifier_group,
 	NULL,
 };
 
+static const struct attribute_group *hisi_hha_pmu_v2_attr_groups[] = {
+	&hisi_hha_pmu_v2_format_group,
+	&hisi_hha_pmu_v2_events_group,
+	&hisi_hha_pmu_cpumask_attr_group,
+	&hisi_hha_pmu_identifier_group,
+	NULL
+};
+
 static const struct hisi_uncore_ops hisi_uncore_hha_ops = {
 	.write_evtype		= hisi_hha_pmu_write_evtype,
 	.get_event_idx		= hisi_uncore_pmu_get_event_idx,
@@ -354,6 +457,10 @@ static const struct hisi_uncore_ops hisi_uncore_hha_ops = {
 	.disable_counter_int	= hisi_hha_pmu_disable_counter_int,
 	.write_counter		= hisi_hha_pmu_write_counter,
 	.read_counter		= hisi_hha_pmu_read_counter,
+	.get_int_status		= hisi_hha_pmu_get_int_status,
+	.clear_int_status	= hisi_hha_pmu_clear_int_status,
+	.enable_filter		= hisi_hha_pmu_enable_filter,
+	.disable_filter		= hisi_hha_pmu_disable_filter,
 };
 
 static int hisi_hha_pmu_dev_probe(struct platform_device *pdev,
@@ -365,16 +472,24 @@ static int hisi_hha_pmu_dev_probe(struct platform_device *pdev,
 	if (ret)
 		return ret;
 
-	ret = hisi_hha_pmu_init_irq(hha_pmu, pdev);
+	ret = hisi_uncore_pmu_init_irq(hha_pmu, pdev);
 	if (ret)
 		return ret;
 
-	hha_pmu->num_counters = HHA_NR_COUNTERS;
-	hha_pmu->counter_bits = 48;
+	if (hha_pmu->identifier >= HISI_PMU_V2) {
+		hha_pmu->counter_bits = 64;
+		hha_pmu->check_event = HHA_V2_NR_EVENT;
+		hha_pmu->pmu_events.attr_groups = hisi_hha_pmu_v2_attr_groups;
+		hha_pmu->num_counters = HHA_V2_NR_COUNTERS;
+	} else {
+		hha_pmu->counter_bits = 48;
+		hha_pmu->check_event = HHA_V1_NR_EVENT;
+		hha_pmu->pmu_events.attr_groups = hisi_hha_pmu_v1_attr_groups;
+		hha_pmu->num_counters = HHA_V1_NR_COUNTERS;
+	}
 	hha_pmu->ops = &hisi_uncore_hha_ops;
 	hha_pmu->dev = &pdev->dev;
 	hha_pmu->on_cpu = -1;
-	hha_pmu->check_event = 0x65;
 
 	return 0;
 }
@@ -416,7 +531,7 @@ static int hisi_hha_pmu_probe(struct platform_device *pdev)
 		.start		= hisi_uncore_pmu_start,
 		.stop		= hisi_uncore_pmu_stop,
 		.read		= hisi_uncore_pmu_read,
-		.attr_groups	= hisi_hha_pmu_attr_groups,
+		.attr_groups	= hha_pmu->pmu_events.attr_groups,
 		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
index 7d792435c2aa..bf9f7772cac9 100644
--- a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
@@ -14,7 +14,6 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/list.h>
-#include <linux/platform_device.h>
 #include <linux/smp.h>
 
 #include "hisi_uncore_pmu.h"
@@ -24,12 +23,17 @@
 #define L3C_INT_MASK		0x0800
 #define L3C_INT_STATUS		0x0808
 #define L3C_INT_CLEAR		0x080c
+#define L3C_CORE_CTRL           0x1b04
+#define L3C_TRACETAG_CTRL       0x1b20
+#define L3C_DATSRC_TYPE         0x1b48
+#define L3C_DATSRC_CTRL         0x1bf0
 #define L3C_EVENT_CTRL	        0x1c00
 #define L3C_VERSION		0x1cf0
 #define L3C_EVENT_TYPE0		0x1d00
 /*
- * Each counter is 48-bits and [48:63] are reserved
- * which are Read-As-Zero and Writes-Ignored.
+ * If the HW version only supports a 48-bit counter, then
+ * bits [63:48] are reserved, which are Read-As-Zero and
+ * Writes-Ignored.
  */
 #define L3C_CNTR0_LOWER		0x1e00
 
@@ -37,7 +41,186 @@
 #define L3C_NR_COUNTERS		0x8
 
 #define L3C_PERF_CTRL_EN	0x10000
+#define L3C_TRACETAG_EN		BIT(31)
+#define L3C_TRACETAG_REQ_SHIFT	7
+#define L3C_TRACETAG_MARK_EN	BIT(0)
+#define L3C_TRACETAG_REQ_EN	(L3C_TRACETAG_MARK_EN | BIT(2))
+#define L3C_TRACETAG_CORE_EN	(L3C_TRACETAG_MARK_EN | BIT(3))
+#define L3C_CORE_EN		BIT(20)
+#define L3C_COER_NONE		0x0
+#define L3C_DATSRC_MASK		0xFF
+#define L3C_DATSRC_SKT_EN	BIT(23)
+#define L3C_DATSRC_NONE		0x0
 #define L3C_EVTYPE_NONE		0xff
+#define L3C_V1_NR_EVENTS	0x59
+#define L3C_V2_NR_EVENTS	0xFF
+
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tt_core, config1, 7, 0);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tt_req, config1, 10, 8);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(datasrc_cfg, config1, 15, 11);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(datasrc_skt, config1, 16, 16);
+
+static void hisi_l3c_pmu_config_req_tracetag(struct perf_event *event)
+{
+	struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu);
+	u32 tt_req = hisi_get_tt_req(event);
+
+	if (tt_req) {
+		u32 val;
+
+		/* Set request-type for tracetag */
+		val = readl(l3c_pmu->base + L3C_TRACETAG_CTRL);
+		val |= tt_req << L3C_TRACETAG_REQ_SHIFT;
+		val |= L3C_TRACETAG_REQ_EN;
+		writel(val, l3c_pmu->base + L3C_TRACETAG_CTRL);
+
+		/* Enable request-tracetag statistics */
+		val = readl(l3c_pmu->base + L3C_PERF_CTRL);
+		val |= L3C_TRACETAG_EN;
+		writel(val, l3c_pmu->base + L3C_PERF_CTRL);
+	}
+}
+
+static void hisi_l3c_pmu_clear_req_tracetag(struct perf_event *event)
+{
+	struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu);
+	u32 tt_req = hisi_get_tt_req(event);
+
+	if (tt_req) {
+		u32 val;
+
+		/* Clear request-type */
+		val = readl(l3c_pmu->base + L3C_TRACETAG_CTRL);
+		val &= ~(tt_req << L3C_TRACETAG_REQ_SHIFT);
+		val &= ~L3C_TRACETAG_REQ_EN;
+		writel(val, l3c_pmu->base + L3C_TRACETAG_CTRL);
+
+		/* Disable request-tracetag statistics */
+		val = readl(l3c_pmu->base + L3C_PERF_CTRL);
+		val &= ~L3C_TRACETAG_EN;
+		writel(val, l3c_pmu->base + L3C_PERF_CTRL);
+	}
+}
+
+static void hisi_l3c_pmu_write_ds(struct perf_event *event, u32 ds_cfg)
+{
+	struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	u32 reg, reg_idx, shift, val;
+	int idx = hwc->idx;
+
+	/*
+	 * Select the appropriate datasource register(L3C_DATSRC_TYPE0/1).
+	 * There are 2 datasource ctrl register for the 8 hardware counters.
+	 * Datasrc is 8-bits and for the former 4 hardware counters,
+	 * L3C_DATSRC_TYPE0 is chosen. For the latter 4 hardware counters,
+	 * L3C_DATSRC_TYPE1 is chosen.
+	 */
+	reg = L3C_DATSRC_TYPE + (idx / 4) * 4;
+	reg_idx = idx % 4;
+	shift = 8 * reg_idx;
+
+	val = readl(l3c_pmu->base + reg);
+	val &= ~(L3C_DATSRC_MASK << shift);
+	val |= ds_cfg << shift;
+	writel(val, l3c_pmu->base + reg);
+}
+
+static void hisi_l3c_pmu_config_ds(struct perf_event *event)
+{
+	struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu);
+	u32 ds_cfg = hisi_get_datasrc_cfg(event);
+	u32 ds_skt = hisi_get_datasrc_skt(event);
+
+	if (ds_cfg)
+		hisi_l3c_pmu_write_ds(event, ds_cfg);
+
+	if (ds_skt) {
+		u32 val;
+
+		val = readl(l3c_pmu->base + L3C_DATSRC_CTRL);
+		val |= L3C_DATSRC_SKT_EN;
+		writel(val, l3c_pmu->base + L3C_DATSRC_CTRL);
+	}
+}
+
+static void hisi_l3c_pmu_clear_ds(struct perf_event *event)
+{
+	struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu);
+	u32 ds_cfg = hisi_get_datasrc_cfg(event);
+	u32 ds_skt = hisi_get_datasrc_skt(event);
+
+	if (ds_cfg)
+		hisi_l3c_pmu_write_ds(event, L3C_DATSRC_NONE);
+
+	if (ds_skt) {
+		u32 val;
+
+		val = readl(l3c_pmu->base + L3C_DATSRC_CTRL);
+		val &= ~L3C_DATSRC_SKT_EN;
+		writel(val, l3c_pmu->base + L3C_DATSRC_CTRL);
+	}
+}
+
+static void hisi_l3c_pmu_config_core_tracetag(struct perf_event *event)
+{
+	struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu);
+	u32 core = hisi_get_tt_core(event);
+
+	if (core) {
+		u32 val;
+
+		/* Config and enable core information */
+		writel(core, l3c_pmu->base + L3C_CORE_CTRL);
+		val = readl(l3c_pmu->base + L3C_PERF_CTRL);
+		val |= L3C_CORE_EN;
+		writel(val, l3c_pmu->base + L3C_PERF_CTRL);
+
+		/* Enable core-tracetag statistics */
+		val = readl(l3c_pmu->base + L3C_TRACETAG_CTRL);
+		val |= L3C_TRACETAG_CORE_EN;
+		writel(val, l3c_pmu->base + L3C_TRACETAG_CTRL);
+	}
+}
+
+static void hisi_l3c_pmu_clear_core_tracetag(struct perf_event *event)
+{
+	struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu);
+	u32 core = hisi_get_tt_core(event);
+
+	if (core) {
+		u32 val;
+
+		/* Clear core information */
+		writel(L3C_COER_NONE, l3c_pmu->base + L3C_CORE_CTRL);
+		val = readl(l3c_pmu->base + L3C_PERF_CTRL);
+		val &= ~L3C_CORE_EN;
+		writel(val, l3c_pmu->base + L3C_PERF_CTRL);
+
+		/* Disable core-tracetag statistics */
+		val = readl(l3c_pmu->base + L3C_TRACETAG_CTRL);
+		val &= ~L3C_TRACETAG_CORE_EN;
+		writel(val, l3c_pmu->base + L3C_TRACETAG_CTRL);
+	}
+}
+
+static void hisi_l3c_pmu_enable_filter(struct perf_event *event)
+{
+	if (event->attr.config1 != 0x0) {
+		hisi_l3c_pmu_config_req_tracetag(event);
+		hisi_l3c_pmu_config_core_tracetag(event);
+		hisi_l3c_pmu_config_ds(event);
+	}
+}
+
+static void hisi_l3c_pmu_disable_filter(struct perf_event *event)
+{
+	if (event->attr.config1 != 0x0) {
+		hisi_l3c_pmu_clear_ds(event);
+		hisi_l3c_pmu_clear_core_tracetag(event);
+		hisi_l3c_pmu_clear_req_tracetag(event);
+	}
+}
 
 /*
  * Select the counter register offset using the counter index
@@ -50,29 +233,13 @@ static u32 hisi_l3c_pmu_get_counter_offset(int cntr_idx)
 static u64 hisi_l3c_pmu_read_counter(struct hisi_pmu *l3c_pmu,
 				     struct hw_perf_event *hwc)
 {
-	u32 idx = hwc->idx;
-
-	if (!hisi_uncore_pmu_counter_valid(l3c_pmu, idx)) {
-		dev_err(l3c_pmu->dev, "Unsupported event index:%d!\n", idx);
-		return 0;
-	}
-
-	/* Read 64-bits and the upper 16 bits are RAZ */
-	return readq(l3c_pmu->base + hisi_l3c_pmu_get_counter_offset(idx));
+	return readq(l3c_pmu->base + hisi_l3c_pmu_get_counter_offset(hwc->idx));
 }
 
 static void hisi_l3c_pmu_write_counter(struct hisi_pmu *l3c_pmu,
 				       struct hw_perf_event *hwc, u64 val)
 {
-	u32 idx = hwc->idx;
-
-	if (!hisi_uncore_pmu_counter_valid(l3c_pmu, idx)) {
-		dev_err(l3c_pmu->dev, "Unsupported event index:%d!\n", idx);
-		return;
-	}
-
-	/* Write 64-bits and the upper 16 bits are WI */
-	writeq(val, l3c_pmu->base + hisi_l3c_pmu_get_counter_offset(idx));
+	writeq(val, l3c_pmu->base + hisi_l3c_pmu_get_counter_offset(hwc->idx));
 }
 
 static void hisi_l3c_pmu_write_evtype(struct hisi_pmu *l3c_pmu, int idx,
@@ -168,81 +335,26 @@ static void hisi_l3c_pmu_disable_counter_int(struct hisi_pmu *l3c_pmu,
 	writel(val, l3c_pmu->base + L3C_INT_MASK);
 }
 
-static irqreturn_t hisi_l3c_pmu_isr(int irq, void *dev_id)
+static u32 hisi_l3c_pmu_get_int_status(struct hisi_pmu *l3c_pmu)
 {
-	struct hisi_pmu *l3c_pmu = dev_id;
-	struct perf_event *event;
-	unsigned long overflown;
-	int idx;
-
-	/* Read L3C_INT_STATUS register */
-	overflown = readl(l3c_pmu->base + L3C_INT_STATUS);
-	if (!overflown)
-		return IRQ_NONE;
-
-	/*
-	 * Find the counter index which overflowed if the bit was set
-	 * and handle it.
-	 */
-	for_each_set_bit(idx, &overflown, L3C_NR_COUNTERS) {
-		/* Write 1 to clear the IRQ status flag */
-		writel((1 << idx), l3c_pmu->base + L3C_INT_CLEAR);
-
-		/* Get the corresponding event struct */
-		event = l3c_pmu->pmu_events.hw_events[idx];
-		if (!event)
-			continue;
-
-		hisi_uncore_pmu_event_update(event);
-		hisi_uncore_pmu_set_event_period(event);
-	}
-
-	return IRQ_HANDLED;
+	return readl(l3c_pmu->base + L3C_INT_STATUS);
 }
 
-static int hisi_l3c_pmu_init_irq(struct hisi_pmu *l3c_pmu,
-				 struct platform_device *pdev)
+static void hisi_l3c_pmu_clear_int_status(struct hisi_pmu *l3c_pmu, int idx)
 {
-	int irq, ret;
-
-	/* Read and init IRQ */
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0)
-		return irq;
-
-	ret = devm_request_irq(&pdev->dev, irq, hisi_l3c_pmu_isr,
-			       IRQF_NOBALANCING | IRQF_NO_THREAD,
-			       dev_name(&pdev->dev), l3c_pmu);
-	if (ret < 0) {
-		dev_err(&pdev->dev,
-			"Fail to request IRQ:%d ret:%d\n", irq, ret);
-		return ret;
-	}
-
-	l3c_pmu->irq = irq;
-
-	return 0;
+	writel(1 << idx, l3c_pmu->base + L3C_INT_CLEAR);
 }
 
 static const struct acpi_device_id hisi_l3c_pmu_acpi_match[] = {
 	{ "HISI0213", },
-	{},
+	{ "HISI0214", },
+	{}
 };
 MODULE_DEVICE_TABLE(acpi, hisi_l3c_pmu_acpi_match);
 
 static int hisi_l3c_pmu_init_data(struct platform_device *pdev,
 				  struct hisi_pmu *l3c_pmu)
 {
-	unsigned long long id;
-	acpi_status status;
-
-	status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev),
-				       "_UID", NULL, &id);
-	if (ACPI_FAILURE(status))
-		return -EINVAL;
-
-	l3c_pmu->index_id = id;
-
 	/*
 	 * Use the SCCL_ID and CCL_ID to identify the L3C PMU, while
 	 * SCCL_ID is in MPIDR[aff2] and CCL_ID is in MPIDR[aff1].
@@ -270,17 +382,31 @@ static int hisi_l3c_pmu_init_data(struct platform_device *pdev,
 	return 0;
 }
 
-static struct attribute *hisi_l3c_pmu_format_attr[] = {
+static struct attribute *hisi_l3c_pmu_v1_format_attr[] = {
 	HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
 	NULL,
 };
 
-static const struct attribute_group hisi_l3c_pmu_format_group = {
+static const struct attribute_group hisi_l3c_pmu_v1_format_group = {
+	.name = "format",
+	.attrs = hisi_l3c_pmu_v1_format_attr,
+};
+
+static struct attribute *hisi_l3c_pmu_v2_format_attr[] = {
+	HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
+	HISI_PMU_FORMAT_ATTR(tt_core, "config1:0-7"),
+	HISI_PMU_FORMAT_ATTR(tt_req, "config1:8-10"),
+	HISI_PMU_FORMAT_ATTR(datasrc_cfg, "config1:11-15"),
+	HISI_PMU_FORMAT_ATTR(datasrc_skt, "config1:16"),
+	NULL
+};
+
+static const struct attribute_group hisi_l3c_pmu_v2_format_group = {
 	.name = "format",
-	.attrs = hisi_l3c_pmu_format_attr,
+	.attrs = hisi_l3c_pmu_v2_format_attr,
 };
 
-static struct attribute *hisi_l3c_pmu_events_attr[] = {
+static struct attribute *hisi_l3c_pmu_v1_events_attr[] = {
 	HISI_PMU_EVENT_ATTR(rd_cpipe,		0x00),
 	HISI_PMU_EVENT_ATTR(wr_cpipe,		0x01),
 	HISI_PMU_EVENT_ATTR(rd_hit_cpipe,	0x02),
@@ -297,9 +423,22 @@ static struct attribute *hisi_l3c_pmu_events_attr[] = {
 	NULL,
 };
 
-static const struct attribute_group hisi_l3c_pmu_events_group = {
+static const struct attribute_group hisi_l3c_pmu_v1_events_group = {
+	.name = "events",
+	.attrs = hisi_l3c_pmu_v1_events_attr,
+};
+
+static struct attribute *hisi_l3c_pmu_v2_events_attr[] = {
+	HISI_PMU_EVENT_ATTR(l3c_hit,		0x48),
+	HISI_PMU_EVENT_ATTR(cycles,		0x7f),
+	HISI_PMU_EVENT_ATTR(l3c_ref,		0xb8),
+	HISI_PMU_EVENT_ATTR(dat_access,		0xb9),
+	NULL
+};
+
+static const struct attribute_group hisi_l3c_pmu_v2_events_group = {
 	.name = "events",
-	.attrs = hisi_l3c_pmu_events_attr,
+	.attrs = hisi_l3c_pmu_v2_events_attr,
 };
 
 static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL);
@@ -325,14 +464,22 @@ static const struct attribute_group hisi_l3c_pmu_identifier_group = {
 	.attrs = hisi_l3c_pmu_identifier_attrs,
 };
 
-static const struct attribute_group *hisi_l3c_pmu_attr_groups[] = {
-	&hisi_l3c_pmu_format_group,
-	&hisi_l3c_pmu_events_group,
+static const struct attribute_group *hisi_l3c_pmu_v1_attr_groups[] = {
+	&hisi_l3c_pmu_v1_format_group,
+	&hisi_l3c_pmu_v1_events_group,
 	&hisi_l3c_pmu_cpumask_attr_group,
 	&hisi_l3c_pmu_identifier_group,
 	NULL,
 };
 
+static const struct attribute_group *hisi_l3c_pmu_v2_attr_groups[] = {
+	&hisi_l3c_pmu_v2_format_group,
+	&hisi_l3c_pmu_v2_events_group,
+	&hisi_l3c_pmu_cpumask_attr_group,
+	&hisi_l3c_pmu_identifier_group,
+	NULL
+};
+
 static const struct hisi_uncore_ops hisi_uncore_l3c_ops = {
 	.write_evtype		= hisi_l3c_pmu_write_evtype,
 	.get_event_idx		= hisi_uncore_pmu_get_event_idx,
@@ -344,6 +491,10 @@ static const struct hisi_uncore_ops hisi_uncore_l3c_ops = {
 	.disable_counter_int	= hisi_l3c_pmu_disable_counter_int,
 	.write_counter		= hisi_l3c_pmu_write_counter,
 	.read_counter		= hisi_l3c_pmu_read_counter,
+	.get_int_status		= hisi_l3c_pmu_get_int_status,
+	.clear_int_status	= hisi_l3c_pmu_clear_int_status,
+	.enable_filter		= hisi_l3c_pmu_enable_filter,
+	.disable_filter		= hisi_l3c_pmu_disable_filter,
 };
 
 static int hisi_l3c_pmu_dev_probe(struct platform_device *pdev,
@@ -355,16 +506,24 @@ static int hisi_l3c_pmu_dev_probe(struct platform_device *pdev,
 	if (ret)
 		return ret;
 
-	ret = hisi_l3c_pmu_init_irq(l3c_pmu, pdev);
+	ret = hisi_uncore_pmu_init_irq(l3c_pmu, pdev);
 	if (ret)
 		return ret;
 
+	if (l3c_pmu->identifier >= HISI_PMU_V2) {
+		l3c_pmu->counter_bits = 64;
+		l3c_pmu->check_event = L3C_V2_NR_EVENTS;
+		l3c_pmu->pmu_events.attr_groups = hisi_l3c_pmu_v2_attr_groups;
+	} else {
+		l3c_pmu->counter_bits = 48;
+		l3c_pmu->check_event = L3C_V1_NR_EVENTS;
+		l3c_pmu->pmu_events.attr_groups = hisi_l3c_pmu_v1_attr_groups;
+	}
+
 	l3c_pmu->num_counters = L3C_NR_COUNTERS;
-	l3c_pmu->counter_bits = 48;
 	l3c_pmu->ops = &hisi_uncore_l3c_ops;
 	l3c_pmu->dev = &pdev->dev;
 	l3c_pmu->on_cpu = -1;
-	l3c_pmu->check_event = 0x59;
 
 	return 0;
 }
@@ -392,8 +551,12 @@ static int hisi_l3c_pmu_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	/*
+	 * CCL_ID is used to identify the L3C in the same SCCL which was
+	 * used _UID by mistake.
+	 */
 	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_l3c%u",
-			      l3c_pmu->sccl_id, l3c_pmu->index_id);
+			      l3c_pmu->sccl_id, l3c_pmu->ccl_id);
 	l3c_pmu->pmu = (struct pmu) {
 		.name		= name,
 		.module		= THIS_MODULE,
@@ -406,7 +569,7 @@ static int hisi_l3c_pmu_probe(struct platform_device *pdev)
 		.start		= hisi_uncore_pmu_start,
 		.stop		= hisi_uncore_pmu_stop,
 		.read		= hisi_uncore_pmu_read,
-		.attr_groups	= hisi_l3c_pmu_attr_groups,
+		.attr_groups	= l3c_pmu->pmu_events.attr_groups,
 		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
diff --git a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c
new file mode 100644
index 000000000000..14f23eb31248
--- /dev/null
+++ b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c
@@ -0,0 +1,500 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * HiSilicon PA uncore Hardware event counters support
+ *
+ * Copyright (C) 2020 HiSilicon Limited
+ * Author: Shaokun Zhang <zhangshaokun@hisilicon.com>
+ *
+ * This code is based on the uncore PMUs like arm-cci and arm-ccn.
+ */
+#include <linux/acpi.h>
+#include <linux/cpuhotplug.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/list.h>
+#include <linux/smp.h>
+
+#include "hisi_uncore_pmu.h"
+
+/* PA register definition */
+#define PA_PERF_CTRL			0x1c00
+#define PA_EVENT_CTRL			0x1c04
+#define PA_TT_CTRL			0x1c08
+#define PA_TGTID_CTRL			0x1c14
+#define PA_SRCID_CTRL			0x1c18
+#define PA_INT_MASK			0x1c70
+#define PA_INT_STATUS			0x1c78
+#define PA_INT_CLEAR			0x1c7c
+#define PA_EVENT_TYPE0			0x1c80
+#define PA_PMU_VERSION			0x1cf0
+#define PA_EVENT_CNT0_L			0x1f00
+
+#define PA_EVTYPE_MASK			0xff
+#define PA_NR_COUNTERS			0x8
+#define PA_PERF_CTRL_EN			BIT(0)
+#define PA_TRACETAG_EN			BIT(4)
+#define PA_TGTID_EN			BIT(11)
+#define PA_SRCID_EN			BIT(11)
+#define PA_TGTID_NONE			0
+#define PA_SRCID_NONE			0
+#define PA_TGTID_MSK_SHIFT		12
+#define PA_SRCID_MSK_SHIFT		12
+
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tgtid_cmd, config1, 10, 0);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tgtid_msk, config1, 21, 11);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(srcid_cmd, config1, 32, 22);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(srcid_msk, config1, 43, 33);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tracetag_en, config1, 44, 44);
+
+static void hisi_pa_pmu_enable_tracetag(struct perf_event *event)
+{
+	struct hisi_pmu *pa_pmu = to_hisi_pmu(event->pmu);
+	u32 tt_en = hisi_get_tracetag_en(event);
+
+	if (tt_en) {
+		u32 val;
+
+		val = readl(pa_pmu->base + PA_TT_CTRL);
+		val |= PA_TRACETAG_EN;
+		writel(val, pa_pmu->base + PA_TT_CTRL);
+	}
+}
+
+static void hisi_pa_pmu_clear_tracetag(struct perf_event *event)
+{
+	struct hisi_pmu *pa_pmu = to_hisi_pmu(event->pmu);
+	u32 tt_en = hisi_get_tracetag_en(event);
+
+	if (tt_en) {
+		u32 val;
+
+		val = readl(pa_pmu->base + PA_TT_CTRL);
+		val &= ~PA_TRACETAG_EN;
+		writel(val, pa_pmu->base + PA_TT_CTRL);
+	}
+}
+
+static void hisi_pa_pmu_config_tgtid(struct perf_event *event)
+{
+	struct hisi_pmu *pa_pmu = to_hisi_pmu(event->pmu);
+	u32 cmd = hisi_get_tgtid_cmd(event);
+
+	if (cmd) {
+		u32 msk = hisi_get_tgtid_msk(event);
+		u32 val = cmd | PA_TGTID_EN | (msk << PA_TGTID_MSK_SHIFT);
+
+		writel(val, pa_pmu->base + PA_TGTID_CTRL);
+	}
+}
+
+static void hisi_pa_pmu_clear_tgtid(struct perf_event *event)
+{
+	struct hisi_pmu *pa_pmu = to_hisi_pmu(event->pmu);
+	u32 cmd = hisi_get_tgtid_cmd(event);
+
+	if (cmd)
+		writel(PA_TGTID_NONE, pa_pmu->base + PA_TGTID_CTRL);
+}
+
+static void hisi_pa_pmu_config_srcid(struct perf_event *event)
+{
+	struct hisi_pmu *pa_pmu = to_hisi_pmu(event->pmu);
+	u32 cmd = hisi_get_srcid_cmd(event);
+
+	if (cmd) {
+		u32 msk = hisi_get_srcid_msk(event);
+		u32 val = cmd | PA_SRCID_EN | (msk << PA_SRCID_MSK_SHIFT);
+
+		writel(val, pa_pmu->base + PA_SRCID_CTRL);
+	}
+}
+
+static void hisi_pa_pmu_clear_srcid(struct perf_event *event)
+{
+	struct hisi_pmu *pa_pmu = to_hisi_pmu(event->pmu);
+	u32 cmd = hisi_get_srcid_cmd(event);
+
+	if (cmd)
+		writel(PA_SRCID_NONE, pa_pmu->base + PA_SRCID_CTRL);
+}
+
+static void hisi_pa_pmu_enable_filter(struct perf_event *event)
+{
+	if (event->attr.config1 != 0x0) {
+		hisi_pa_pmu_enable_tracetag(event);
+		hisi_pa_pmu_config_srcid(event);
+		hisi_pa_pmu_config_tgtid(event);
+	}
+}
+
+static void hisi_pa_pmu_disable_filter(struct perf_event *event)
+{
+	if (event->attr.config1 != 0x0) {
+		hisi_pa_pmu_clear_tgtid(event);
+		hisi_pa_pmu_clear_srcid(event);
+		hisi_pa_pmu_clear_tracetag(event);
+	}
+}
+
+static u32 hisi_pa_pmu_get_counter_offset(int idx)
+{
+	return (PA_EVENT_CNT0_L + idx * 8);
+}
+
+static u64 hisi_pa_pmu_read_counter(struct hisi_pmu *pa_pmu,
+				    struct hw_perf_event *hwc)
+{
+	return readq(pa_pmu->base + hisi_pa_pmu_get_counter_offset(hwc->idx));
+}
+
+static void hisi_pa_pmu_write_counter(struct hisi_pmu *pa_pmu,
+				      struct hw_perf_event *hwc, u64 val)
+{
+	writeq(val, pa_pmu->base + hisi_pa_pmu_get_counter_offset(hwc->idx));
+}
+
+static void hisi_pa_pmu_write_evtype(struct hisi_pmu *pa_pmu, int idx,
+				     u32 type)
+{
+	u32 reg, reg_idx, shift, val;
+
+	/*
+	 * Select the appropriate event select register(PA_EVENT_TYPE0/1).
+	 * There are 2 event select registers for the 8 hardware counters.
+	 * Event code is 8-bits and for the former 4 hardware counters,
+	 * PA_EVENT_TYPE0 is chosen. For the latter 4 hardware counters,
+	 * PA_EVENT_TYPE1 is chosen.
+	 */
+	reg = PA_EVENT_TYPE0 + (idx / 4) * 4;
+	reg_idx = idx % 4;
+	shift = 8 * reg_idx;
+
+	/* Write event code to pa_EVENT_TYPEx Register */
+	val = readl(pa_pmu->base + reg);
+	val &= ~(PA_EVTYPE_MASK << shift);
+	val |= (type << shift);
+	writel(val, pa_pmu->base + reg);
+}
+
+static void hisi_pa_pmu_start_counters(struct hisi_pmu *pa_pmu)
+{
+	u32 val;
+
+	val = readl(pa_pmu->base + PA_PERF_CTRL);
+	val |= PA_PERF_CTRL_EN;
+	writel(val, pa_pmu->base + PA_PERF_CTRL);
+}
+
+static void hisi_pa_pmu_stop_counters(struct hisi_pmu *pa_pmu)
+{
+	u32 val;
+
+	val = readl(pa_pmu->base + PA_PERF_CTRL);
+	val &= ~(PA_PERF_CTRL_EN);
+	writel(val, pa_pmu->base + PA_PERF_CTRL);
+}
+
+static void hisi_pa_pmu_enable_counter(struct hisi_pmu *pa_pmu,
+				       struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Enable counter index in PA_EVENT_CTRL register */
+	val = readl(pa_pmu->base + PA_EVENT_CTRL);
+	val |= 1 << hwc->idx;
+	writel(val, pa_pmu->base + PA_EVENT_CTRL);
+}
+
+static void hisi_pa_pmu_disable_counter(struct hisi_pmu *pa_pmu,
+					struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Clear counter index in PA_EVENT_CTRL register */
+	val = readl(pa_pmu->base + PA_EVENT_CTRL);
+	val &= ~(1 << hwc->idx);
+	writel(val, pa_pmu->base + PA_EVENT_CTRL);
+}
+
+static void hisi_pa_pmu_enable_counter_int(struct hisi_pmu *pa_pmu,
+					   struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Write 0 to enable interrupt */
+	val = readl(pa_pmu->base + PA_INT_MASK);
+	val &= ~(1 << hwc->idx);
+	writel(val, pa_pmu->base + PA_INT_MASK);
+}
+
+static void hisi_pa_pmu_disable_counter_int(struct hisi_pmu *pa_pmu,
+					    struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	/* Write 1 to mask interrupt */
+	val = readl(pa_pmu->base + PA_INT_MASK);
+	val |= 1 << hwc->idx;
+	writel(val, pa_pmu->base + PA_INT_MASK);
+}
+
+static u32 hisi_pa_pmu_get_int_status(struct hisi_pmu *pa_pmu)
+{
+	return readl(pa_pmu->base + PA_INT_STATUS);
+}
+
+static void hisi_pa_pmu_clear_int_status(struct hisi_pmu *pa_pmu, int idx)
+{
+	writel(1 << idx, pa_pmu->base + PA_INT_CLEAR);
+}
+
+static const struct acpi_device_id hisi_pa_pmu_acpi_match[] = {
+	{ "HISI0273", },
+	{}
+};
+MODULE_DEVICE_TABLE(acpi, hisi_pa_pmu_acpi_match);
+
+static int hisi_pa_pmu_init_data(struct platform_device *pdev,
+				   struct hisi_pmu *pa_pmu)
+{
+	/*
+	 * Use the SCCL_ID and the index ID to identify the PA PMU,
+	 * while SCCL_ID is the nearst SCCL_ID from this SICL and
+	 * CPU core is chosen from this SCCL to manage this PMU.
+	 */
+	if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id",
+				     &pa_pmu->sccl_id)) {
+		dev_err(&pdev->dev, "Cannot read sccl-id!\n");
+		return -EINVAL;
+	}
+
+	if (device_property_read_u32(&pdev->dev, "hisilicon,idx-id",
+				     &pa_pmu->index_id)) {
+		dev_err(&pdev->dev, "Cannot read idx-id!\n");
+		return -EINVAL;
+	}
+
+	pa_pmu->ccl_id = -1;
+
+	pa_pmu->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(pa_pmu->base)) {
+		dev_err(&pdev->dev, "ioremap failed for pa_pmu resource.\n");
+		return PTR_ERR(pa_pmu->base);
+	}
+
+	pa_pmu->identifier = readl(pa_pmu->base + PA_PMU_VERSION);
+
+	return 0;
+}
+
+static struct attribute *hisi_pa_pmu_v2_format_attr[] = {
+	HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
+	HISI_PMU_FORMAT_ATTR(tgtid_cmd, "config1:0-10"),
+	HISI_PMU_FORMAT_ATTR(tgtid_msk, "config1:11-21"),
+	HISI_PMU_FORMAT_ATTR(srcid_cmd, "config1:22-32"),
+	HISI_PMU_FORMAT_ATTR(srcid_msk, "config1:33-43"),
+	HISI_PMU_FORMAT_ATTR(tracetag_en, "config1:44"),
+	NULL,
+};
+
+static const struct attribute_group hisi_pa_pmu_v2_format_group = {
+	.name = "format",
+	.attrs = hisi_pa_pmu_v2_format_attr,
+};
+
+static struct attribute *hisi_pa_pmu_v2_events_attr[] = {
+	HISI_PMU_EVENT_ATTR(rx_req,		0x40),
+	HISI_PMU_EVENT_ATTR(tx_req,             0x5c),
+	HISI_PMU_EVENT_ATTR(cycle,		0x78),
+	NULL
+};
+
+static const struct attribute_group hisi_pa_pmu_v2_events_group = {
+	.name = "events",
+	.attrs = hisi_pa_pmu_v2_events_attr,
+};
+
+static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL);
+
+static struct attribute *hisi_pa_pmu_cpumask_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL
+};
+
+static const struct attribute_group hisi_pa_pmu_cpumask_attr_group = {
+	.attrs = hisi_pa_pmu_cpumask_attrs,
+};
+
+static struct device_attribute hisi_pa_pmu_identifier_attr =
+	__ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL);
+
+static struct attribute *hisi_pa_pmu_identifier_attrs[] = {
+	&hisi_pa_pmu_identifier_attr.attr,
+	NULL
+};
+
+static struct attribute_group hisi_pa_pmu_identifier_group = {
+	.attrs = hisi_pa_pmu_identifier_attrs,
+};
+
+static const struct attribute_group *hisi_pa_pmu_v2_attr_groups[] = {
+	&hisi_pa_pmu_v2_format_group,
+	&hisi_pa_pmu_v2_events_group,
+	&hisi_pa_pmu_cpumask_attr_group,
+	&hisi_pa_pmu_identifier_group,
+	NULL
+};
+
+static const struct hisi_uncore_ops hisi_uncore_pa_ops = {
+	.write_evtype		= hisi_pa_pmu_write_evtype,
+	.get_event_idx		= hisi_uncore_pmu_get_event_idx,
+	.start_counters		= hisi_pa_pmu_start_counters,
+	.stop_counters		= hisi_pa_pmu_stop_counters,
+	.enable_counter		= hisi_pa_pmu_enable_counter,
+	.disable_counter	= hisi_pa_pmu_disable_counter,
+	.enable_counter_int	= hisi_pa_pmu_enable_counter_int,
+	.disable_counter_int	= hisi_pa_pmu_disable_counter_int,
+	.write_counter		= hisi_pa_pmu_write_counter,
+	.read_counter		= hisi_pa_pmu_read_counter,
+	.get_int_status		= hisi_pa_pmu_get_int_status,
+	.clear_int_status	= hisi_pa_pmu_clear_int_status,
+	.enable_filter		= hisi_pa_pmu_enable_filter,
+	.disable_filter		= hisi_pa_pmu_disable_filter,
+};
+
+static int hisi_pa_pmu_dev_probe(struct platform_device *pdev,
+				 struct hisi_pmu *pa_pmu)
+{
+	int ret;
+
+	ret = hisi_pa_pmu_init_data(pdev, pa_pmu);
+	if (ret)
+		return ret;
+
+	ret = hisi_uncore_pmu_init_irq(pa_pmu, pdev);
+	if (ret)
+		return ret;
+
+	pa_pmu->pmu_events.attr_groups = hisi_pa_pmu_v2_attr_groups;
+	pa_pmu->num_counters = PA_NR_COUNTERS;
+	pa_pmu->ops = &hisi_uncore_pa_ops;
+	pa_pmu->check_event = 0xB0;
+	pa_pmu->counter_bits = 64;
+	pa_pmu->dev = &pdev->dev;
+	pa_pmu->on_cpu = -1;
+
+	return 0;
+}
+
+static int hisi_pa_pmu_probe(struct platform_device *pdev)
+{
+	struct hisi_pmu *pa_pmu;
+	char *name;
+	int ret;
+
+	pa_pmu = devm_kzalloc(&pdev->dev, sizeof(*pa_pmu), GFP_KERNEL);
+	if (!pa_pmu)
+		return -ENOMEM;
+
+	ret = hisi_pa_pmu_dev_probe(pdev, pa_pmu);
+	if (ret)
+		return ret;
+	/*
+	 * PA is attached in SICL and the CPU core is chosen to manage this
+	 * PMU which is the nearest SCCL, while its SCCL_ID is greater than
+	 * one with the SICL_ID.
+	 */
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sicl%u_pa%u",
+			      pa_pmu->sccl_id - 1, pa_pmu->index_id);
+	if (!name)
+		return -ENOMEM;
+
+	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE,
+				       &pa_pmu->node);
+	if (ret) {
+		dev_err(&pdev->dev, "Error %d registering hotplug\n", ret);
+		return ret;
+	}
+
+	pa_pmu->pmu = (struct pmu) {
+		.module		= THIS_MODULE,
+		.task_ctx_nr	= perf_invalid_context,
+		.event_init	= hisi_uncore_pmu_event_init,
+		.pmu_enable	= hisi_uncore_pmu_enable,
+		.pmu_disable	= hisi_uncore_pmu_disable,
+		.add		= hisi_uncore_pmu_add,
+		.del		= hisi_uncore_pmu_del,
+		.start		= hisi_uncore_pmu_start,
+		.stop		= hisi_uncore_pmu_stop,
+		.read		= hisi_uncore_pmu_read,
+		.attr_groups    = pa_pmu->pmu_events.attr_groups,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
+	};
+
+	ret = perf_pmu_register(&pa_pmu->pmu, name, -1);
+	if (ret) {
+		dev_err(pa_pmu->dev, "PMU register failed, ret = %d\n", ret);
+		cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE,
+					    &pa_pmu->node);
+		irq_set_affinity_hint(pa_pmu->irq, NULL);
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, pa_pmu);
+	return ret;
+}
+
+static int hisi_pa_pmu_remove(struct platform_device *pdev)
+{
+	struct hisi_pmu *pa_pmu = platform_get_drvdata(pdev);
+
+	perf_pmu_unregister(&pa_pmu->pmu);
+	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE,
+					    &pa_pmu->node);
+	irq_set_affinity_hint(pa_pmu->irq, NULL);
+
+	return 0;
+}
+
+static struct platform_driver hisi_pa_pmu_driver = {
+	.driver = {
+		.name = "hisi_pa_pmu",
+		.acpi_match_table = hisi_pa_pmu_acpi_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe = hisi_pa_pmu_probe,
+	.remove = hisi_pa_pmu_remove,
+};
+
+static int __init hisi_pa_pmu_module_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE,
+				      "AP_PERF_ARM_HISI_PA_ONLINE",
+				      hisi_uncore_pmu_online_cpu,
+				      hisi_uncore_pmu_offline_cpu);
+	if (ret) {
+		pr_err("PA PMU: cpuhp state setup failed, ret = %d\n", ret);
+		return ret;
+	}
+
+	ret = platform_driver_register(&hisi_pa_pmu_driver);
+	if (ret)
+		cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE);
+
+	return ret;
+}
+module_init(hisi_pa_pmu_module_init);
+
+static void __exit hisi_pa_pmu_module_exit(void)
+{
+	platform_driver_unregister(&hisi_pa_pmu_driver);
+	cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE);
+}
+module_exit(hisi_pa_pmu_module_exit);
+
+MODULE_DESCRIPTION("HiSilicon Protocol Adapter uncore PMU driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Shaokun Zhang <zhangshaokun@hisilicon.com>");
+MODULE_AUTHOR("Qi Liu <liuqi115@huawei.com>");
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c
index 9dbdc3fc3bb4..13c68b5e39c4 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c
@@ -21,7 +21,7 @@
 #include "hisi_uncore_pmu.h"
 
 #define HISI_GET_EVENTID(ev) (ev->hw.config_base & 0xff)
-#define HISI_MAX_PERIOD(nr) (BIT_ULL(nr) - 1)
+#define HISI_MAX_PERIOD(nr) (GENMASK_ULL((nr) - 1, 0))
 
 /*
  * PMU format attributes
@@ -33,7 +33,7 @@ ssize_t hisi_format_sysfs_show(struct device *dev,
 
 	eattr = container_of(attr, struct dev_ext_attribute, attr);
 
-	return sprintf(buf, "%s\n", (char *)eattr->var);
+	return sysfs_emit(buf, "%s\n", (char *)eattr->var);
 }
 EXPORT_SYMBOL_GPL(hisi_format_sysfs_show);
 
@@ -47,7 +47,7 @@ ssize_t hisi_event_sysfs_show(struct device *dev,
 
 	eattr = container_of(attr, struct dev_ext_attribute, attr);
 
-	return sprintf(page, "config=0x%lx\n", (unsigned long)eattr->var);
+	return sysfs_emit(page, "config=0x%lx\n", (unsigned long)eattr->var);
 }
 EXPORT_SYMBOL_GPL(hisi_event_sysfs_show);
 
@@ -59,7 +59,7 @@ ssize_t hisi_cpumask_sysfs_show(struct device *dev,
 {
 	struct hisi_pmu *hisi_pmu = to_hisi_pmu(dev_get_drvdata(dev));
 
-	return sprintf(buf, "%d\n", hisi_pmu->on_cpu);
+	return sysfs_emit(buf, "%d\n", hisi_pmu->on_cpu);
 }
 EXPORT_SYMBOL_GPL(hisi_cpumask_sysfs_show);
 
@@ -96,12 +96,6 @@ static bool hisi_validate_event_group(struct perf_event *event)
 	return counters <= hisi_pmu->num_counters;
 }
 
-int hisi_uncore_pmu_counter_valid(struct hisi_pmu *hisi_pmu, int idx)
-{
-	return idx >= 0 && idx < hisi_pmu->num_counters;
-}
-EXPORT_SYMBOL_GPL(hisi_uncore_pmu_counter_valid);
-
 int hisi_uncore_pmu_get_event_idx(struct perf_event *event)
 {
 	struct hisi_pmu *hisi_pmu = to_hisi_pmu(event->pmu);
@@ -125,19 +119,68 @@ ssize_t hisi_uncore_pmu_identifier_attr_show(struct device *dev,
 {
 	struct hisi_pmu *hisi_pmu = to_hisi_pmu(dev_get_drvdata(dev));
 
-	return snprintf(page, PAGE_SIZE, "0x%08x\n", hisi_pmu->identifier);
+	return sysfs_emit(page, "0x%08x\n", hisi_pmu->identifier);
 }
 EXPORT_SYMBOL_GPL(hisi_uncore_pmu_identifier_attr_show);
 
 static void hisi_uncore_pmu_clear_event_idx(struct hisi_pmu *hisi_pmu, int idx)
 {
-	if (!hisi_uncore_pmu_counter_valid(hisi_pmu, idx)) {
-		dev_err(hisi_pmu->dev, "Unsupported event index:%d!\n", idx);
-		return;
+	clear_bit(idx, hisi_pmu->pmu_events.used_mask);
+}
+
+static irqreturn_t hisi_uncore_pmu_isr(int irq, void *data)
+{
+	struct hisi_pmu *hisi_pmu = data;
+	struct perf_event *event;
+	unsigned long overflown;
+	int idx;
+
+	overflown = hisi_pmu->ops->get_int_status(hisi_pmu);
+	if (!overflown)
+		return IRQ_NONE;
+
+	/*
+	 * Find the counter index which overflowed if the bit was set
+	 * and handle it.
+	 */
+	for_each_set_bit(idx, &overflown, hisi_pmu->num_counters) {
+		/* Write 1 to clear the IRQ status flag */
+		hisi_pmu->ops->clear_int_status(hisi_pmu, idx);
+		/* Get the corresponding event struct */
+		event = hisi_pmu->pmu_events.hw_events[idx];
+		if (!event)
+			continue;
+
+		hisi_uncore_pmu_event_update(event);
+		hisi_uncore_pmu_set_event_period(event);
 	}
 
-	clear_bit(idx, hisi_pmu->pmu_events.used_mask);
+	return IRQ_HANDLED;
+}
+
+int hisi_uncore_pmu_init_irq(struct hisi_pmu *hisi_pmu,
+			     struct platform_device *pdev)
+{
+	int irq, ret;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	ret = devm_request_irq(&pdev->dev, irq, hisi_uncore_pmu_isr,
+			       IRQF_NOBALANCING | IRQF_NO_THREAD,
+			       dev_name(&pdev->dev), hisi_pmu);
+	if (ret < 0) {
+		dev_err(&pdev->dev,
+			"Fail to request IRQ: %d ret: %d.\n", irq, ret);
+		return ret;
+	}
+
+	hisi_pmu->irq = irq;
+
+	return 0;
 }
+EXPORT_SYMBOL_GPL(hisi_uncore_pmu_init_irq);
 
 int hisi_uncore_pmu_event_init(struct perf_event *event)
 {
@@ -202,6 +245,9 @@ static void hisi_uncore_pmu_enable_event(struct perf_event *event)
 	hisi_pmu->ops->write_evtype(hisi_pmu, hwc->idx,
 				    HISI_GET_EVENTID(event));
 
+	if (hisi_pmu->ops->enable_filter)
+		hisi_pmu->ops->enable_filter(event);
+
 	hisi_pmu->ops->enable_counter_int(hisi_pmu, hwc);
 	hisi_pmu->ops->enable_counter(hisi_pmu, hwc);
 }
@@ -216,6 +262,9 @@ static void hisi_uncore_pmu_disable_event(struct perf_event *event)
 
 	hisi_pmu->ops->disable_counter(hisi_pmu, hwc);
 	hisi_pmu->ops->disable_counter_int(hisi_pmu, hwc);
+
+	if (hisi_pmu->ops->disable_filter)
+		hisi_pmu->ops->disable_filter(event);
 }
 
 void hisi_uncore_pmu_set_event_period(struct perf_event *event)
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.h b/drivers/perf/hisilicon/hisi_uncore_pmu.h
index 25b7cbe1f818..ea9d89bbc1ea 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.h
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.h
@@ -11,16 +11,19 @@
 #ifndef __HISI_UNCORE_PMU_H__
 #define __HISI_UNCORE_PMU_H__
 
+#include <linux/bitfield.h>
 #include <linux/cpumask.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/perf_event.h>
+#include <linux/platform_device.h>
 #include <linux/types.h>
 
 #undef pr_fmt
 #define pr_fmt(fmt)     "hisi_pmu: " fmt
 
+#define HISI_PMU_V2		0x30
 #define HISI_MAX_COUNTERS 0x10
 #define to_hisi_pmu(p)	(container_of(p, struct hisi_pmu, pmu))
 
@@ -34,6 +37,12 @@
 #define HISI_PMU_EVENT_ATTR(_name, _config)		\
 	HISI_PMU_ATTR(_name, hisi_event_sysfs_show, (unsigned long)_config)
 
+#define HISI_PMU_EVENT_ATTR_EXTRACTOR(name, config, hi, lo)        \
+	static inline u32 hisi_get_##name(struct perf_event *event)            \
+	{                                                                  \
+		return FIELD_GET(GENMASK_ULL(hi, lo), event->attr.config);  \
+	}
+
 struct hisi_pmu;
 
 struct hisi_uncore_ops {
@@ -47,11 +56,16 @@ struct hisi_uncore_ops {
 	void (*disable_counter_int)(struct hisi_pmu *, struct hw_perf_event *);
 	void (*start_counters)(struct hisi_pmu *);
 	void (*stop_counters)(struct hisi_pmu *);
+	u32 (*get_int_status)(struct hisi_pmu *hisi_pmu);
+	void (*clear_int_status)(struct hisi_pmu *hisi_pmu, int idx);
+	void (*enable_filter)(struct perf_event *event);
+	void (*disable_filter)(struct perf_event *event);
 };
 
 struct hisi_pmu_hwevents {
 	struct perf_event *hw_events[HISI_MAX_COUNTERS];
 	DECLARE_BITMAP(used_mask, HISI_MAX_COUNTERS);
+	const struct attribute_group **attr_groups;
 };
 
 /* Generic pmu struct for different pmu types */
@@ -71,6 +85,8 @@ struct hisi_pmu {
 	void __iomem *base;
 	/* the ID of the PMU modules */
 	u32 index_id;
+	/* For DDRC PMU v2: each DDRC has more than one DMC */
+	u32 sub_id;
 	int num_counters;
 	int counter_bits;
 	/* check event code range */
@@ -78,7 +94,6 @@ struct hisi_pmu {
 	u32 identifier;
 };
 
-int hisi_uncore_pmu_counter_valid(struct hisi_pmu *hisi_pmu, int idx);
 int hisi_uncore_pmu_get_event_idx(struct perf_event *event);
 void hisi_uncore_pmu_read(struct perf_event *event);
 int hisi_uncore_pmu_add(struct perf_event *event, int flags);
@@ -102,6 +117,7 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node);
 ssize_t hisi_uncore_pmu_identifier_attr_show(struct device *dev,
 					     struct device_attribute *attr,
 					     char *page);
-
+int hisi_uncore_pmu_init_irq(struct hisi_pmu *hisi_pmu,
+			     struct platform_device *pdev);
 
 #endif /* __HISI_UNCORE_PMU_H__ */
diff --git a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c
new file mode 100644
index 000000000000..46be312fa126
--- /dev/null
+++ b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c
@@ -0,0 +1,530 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * HiSilicon SLLC uncore Hardware event counters support
+ *
+ * Copyright (C) 2020 Hisilicon Limited
+ * Author: Shaokun Zhang <zhangshaokun@hisilicon.com>
+ *
+ * This code is based on the uncore PMUs like arm-cci and arm-ccn.
+ */
+#include <linux/acpi.h>
+#include <linux/cpuhotplug.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/list.h>
+#include <linux/smp.h>
+
+#include "hisi_uncore_pmu.h"
+
+/* SLLC register definition */
+#define SLLC_INT_MASK			0x0814
+#define SLLC_INT_STATUS			0x0818
+#define SLLC_INT_CLEAR			0x081c
+#define SLLC_PERF_CTRL			0x1c00
+#define SLLC_SRCID_CTRL			0x1c04
+#define SLLC_TGTID_CTRL			0x1c08
+#define SLLC_EVENT_CTRL			0x1c14
+#define SLLC_EVENT_TYPE0		0x1c18
+#define SLLC_VERSION			0x1cf0
+#define SLLC_EVENT_CNT0_L		0x1d00
+
+#define SLLC_EVTYPE_MASK		0xff
+#define SLLC_PERF_CTRL_EN		BIT(0)
+#define SLLC_FILT_EN			BIT(1)
+#define SLLC_TRACETAG_EN		BIT(2)
+#define SLLC_SRCID_EN			BIT(4)
+#define SLLC_SRCID_NONE			0x0
+#define SLLC_TGTID_EN			BIT(5)
+#define SLLC_TGTID_NONE			0x0
+#define SLLC_TGTID_MIN_SHIFT		1
+#define SLLC_TGTID_MAX_SHIFT		12
+#define SLLC_SRCID_CMD_SHIFT		1
+#define SLLC_SRCID_MSK_SHIFT		12
+#define SLLC_NR_EVENTS			0x80
+
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tgtid_min, config1, 10, 0);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tgtid_max, config1, 21, 11);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(srcid_cmd, config1, 32, 22);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(srcid_msk, config1, 43, 33);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tracetag_en, config1, 44, 44);
+
+static bool tgtid_is_valid(u32 max, u32 min)
+{
+	return max > 0 && max >= min;
+}
+
+static void hisi_sllc_pmu_enable_tracetag(struct perf_event *event)
+{
+	struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu);
+	u32 tt_en = hisi_get_tracetag_en(event);
+
+	if (tt_en) {
+		u32 val;
+
+		val = readl(sllc_pmu->base + SLLC_PERF_CTRL);
+		val |= SLLC_TRACETAG_EN | SLLC_FILT_EN;
+		writel(val, sllc_pmu->base + SLLC_PERF_CTRL);
+	}
+}
+
+static void hisi_sllc_pmu_disable_tracetag(struct perf_event *event)
+{
+	struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu);
+	u32 tt_en = hisi_get_tracetag_en(event);
+
+	if (tt_en) {
+		u32 val;
+
+		val = readl(sllc_pmu->base + SLLC_PERF_CTRL);
+		val &= ~(SLLC_TRACETAG_EN | SLLC_FILT_EN);
+		writel(val, sllc_pmu->base + SLLC_PERF_CTRL);
+	}
+}
+
+static void hisi_sllc_pmu_config_tgtid(struct perf_event *event)
+{
+	struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu);
+	u32 min = hisi_get_tgtid_min(event);
+	u32 max = hisi_get_tgtid_max(event);
+
+	if (tgtid_is_valid(max, min)) {
+		u32 val = (max << SLLC_TGTID_MAX_SHIFT) | (min << SLLC_TGTID_MIN_SHIFT);
+
+		writel(val, sllc_pmu->base + SLLC_TGTID_CTRL);
+		/* Enable the tgtid */
+		val = readl(sllc_pmu->base + SLLC_PERF_CTRL);
+		val |= SLLC_TGTID_EN | SLLC_FILT_EN;
+		writel(val, sllc_pmu->base + SLLC_PERF_CTRL);
+	}
+}
+
+static void hisi_sllc_pmu_clear_tgtid(struct perf_event *event)
+{
+	struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu);
+	u32 min = hisi_get_tgtid_min(event);
+	u32 max = hisi_get_tgtid_max(event);
+
+	if (tgtid_is_valid(max, min)) {
+		u32 val;
+
+		writel(SLLC_TGTID_NONE, sllc_pmu->base + SLLC_TGTID_CTRL);
+		/* Disable the tgtid */
+		val = readl(sllc_pmu->base + SLLC_PERF_CTRL);
+		val &= ~(SLLC_TGTID_EN | SLLC_FILT_EN);
+		writel(val, sllc_pmu->base + SLLC_PERF_CTRL);
+	}
+}
+
+static void hisi_sllc_pmu_config_srcid(struct perf_event *event)
+{
+	struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu);
+	u32 cmd = hisi_get_srcid_cmd(event);
+
+	if (cmd) {
+		u32 val, msk;
+
+		msk = hisi_get_srcid_msk(event);
+		val = (cmd << SLLC_SRCID_CMD_SHIFT) | (msk << SLLC_SRCID_MSK_SHIFT);
+		writel(val, sllc_pmu->base + SLLC_SRCID_CTRL);
+		/* Enable the srcid */
+		val = readl(sllc_pmu->base + SLLC_PERF_CTRL);
+		val |= SLLC_SRCID_EN | SLLC_FILT_EN;
+		writel(val, sllc_pmu->base + SLLC_PERF_CTRL);
+	}
+}
+
+static void hisi_sllc_pmu_clear_srcid(struct perf_event *event)
+{
+	struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu);
+	u32 cmd = hisi_get_srcid_cmd(event);
+
+	if (cmd) {
+		u32 val;
+
+		writel(SLLC_SRCID_NONE, sllc_pmu->base + SLLC_SRCID_CTRL);
+		/* Disable the srcid */
+		val = readl(sllc_pmu->base + SLLC_PERF_CTRL);
+		val &= ~(SLLC_SRCID_EN | SLLC_FILT_EN);
+		writel(val, sllc_pmu->base + SLLC_PERF_CTRL);
+	}
+}
+
+static void hisi_sllc_pmu_enable_filter(struct perf_event *event)
+{
+	if (event->attr.config1 != 0x0) {
+		hisi_sllc_pmu_enable_tracetag(event);
+		hisi_sllc_pmu_config_srcid(event);
+		hisi_sllc_pmu_config_tgtid(event);
+	}
+}
+
+static void hisi_sllc_pmu_clear_filter(struct perf_event *event)
+{
+	if (event->attr.config1 != 0x0) {
+		hisi_sllc_pmu_disable_tracetag(event);
+		hisi_sllc_pmu_clear_srcid(event);
+		hisi_sllc_pmu_clear_tgtid(event);
+	}
+}
+
+static u32 hisi_sllc_pmu_get_counter_offset(int idx)
+{
+	return (SLLC_EVENT_CNT0_L + idx * 8);
+}
+
+static u64 hisi_sllc_pmu_read_counter(struct hisi_pmu *sllc_pmu,
+				      struct hw_perf_event *hwc)
+{
+	return readq(sllc_pmu->base +
+		     hisi_sllc_pmu_get_counter_offset(hwc->idx));
+}
+
+static void hisi_sllc_pmu_write_counter(struct hisi_pmu *sllc_pmu,
+					struct hw_perf_event *hwc, u64 val)
+{
+	writeq(val, sllc_pmu->base +
+	       hisi_sllc_pmu_get_counter_offset(hwc->idx));
+}
+
+static void hisi_sllc_pmu_write_evtype(struct hisi_pmu *sllc_pmu, int idx,
+				       u32 type)
+{
+	u32 reg, reg_idx, shift, val;
+
+	/*
+	 * Select the appropriate event select register(SLLC_EVENT_TYPE0/1).
+	 * There are 2 event select registers for the 8 hardware counters.
+	 * Event code is 8-bits and for the former 4 hardware counters,
+	 * SLLC_EVENT_TYPE0 is chosen. For the latter 4 hardware counters,
+	 * SLLC_EVENT_TYPE1 is chosen.
+	 */
+	reg = SLLC_EVENT_TYPE0 + (idx / 4) * 4;
+	reg_idx = idx % 4;
+	shift = 8 * reg_idx;
+
+	/* Write event code to SLLC_EVENT_TYPEx Register */
+	val = readl(sllc_pmu->base + reg);
+	val &= ~(SLLC_EVTYPE_MASK << shift);
+	val |= (type << shift);
+	writel(val, sllc_pmu->base + reg);
+}
+
+static void hisi_sllc_pmu_start_counters(struct hisi_pmu *sllc_pmu)
+{
+	u32 val;
+
+	val = readl(sllc_pmu->base + SLLC_PERF_CTRL);
+	val |= SLLC_PERF_CTRL_EN;
+	writel(val, sllc_pmu->base + SLLC_PERF_CTRL);
+}
+
+static void hisi_sllc_pmu_stop_counters(struct hisi_pmu *sllc_pmu)
+{
+	u32 val;
+
+	val = readl(sllc_pmu->base + SLLC_PERF_CTRL);
+	val &= ~(SLLC_PERF_CTRL_EN);
+	writel(val, sllc_pmu->base + SLLC_PERF_CTRL);
+}
+
+static void hisi_sllc_pmu_enable_counter(struct hisi_pmu *sllc_pmu,
+					 struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	val = readl(sllc_pmu->base + SLLC_EVENT_CTRL);
+	val |= 1 << hwc->idx;
+	writel(val, sllc_pmu->base + SLLC_EVENT_CTRL);
+}
+
+static void hisi_sllc_pmu_disable_counter(struct hisi_pmu *sllc_pmu,
+					  struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	val = readl(sllc_pmu->base + SLLC_EVENT_CTRL);
+	val &= ~(1 << hwc->idx);
+	writel(val, sllc_pmu->base + SLLC_EVENT_CTRL);
+}
+
+static void hisi_sllc_pmu_enable_counter_int(struct hisi_pmu *sllc_pmu,
+					     struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	val = readl(sllc_pmu->base + SLLC_INT_MASK);
+	/* Write 0 to enable interrupt */
+	val &= ~(1 << hwc->idx);
+	writel(val, sllc_pmu->base + SLLC_INT_MASK);
+}
+
+static void hisi_sllc_pmu_disable_counter_int(struct hisi_pmu *sllc_pmu,
+					      struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	val = readl(sllc_pmu->base + SLLC_INT_MASK);
+	/* Write 1 to mask interrupt */
+	val |= 1 << hwc->idx;
+	writel(val, sllc_pmu->base + SLLC_INT_MASK);
+}
+
+static u32 hisi_sllc_pmu_get_int_status(struct hisi_pmu *sllc_pmu)
+{
+	return readl(sllc_pmu->base + SLLC_INT_STATUS);
+}
+
+static void hisi_sllc_pmu_clear_int_status(struct hisi_pmu *sllc_pmu, int idx)
+{
+	writel(1 << idx, sllc_pmu->base + SLLC_INT_CLEAR);
+}
+
+static const struct acpi_device_id hisi_sllc_pmu_acpi_match[] = {
+	{ "HISI0263", },
+	{}
+};
+MODULE_DEVICE_TABLE(acpi, hisi_sllc_pmu_acpi_match);
+
+static int hisi_sllc_pmu_init_data(struct platform_device *pdev,
+				   struct hisi_pmu *sllc_pmu)
+{
+	/*
+	 * Use the SCCL_ID and the index ID to identify the SLLC PMU,
+	 * while SCCL_ID is from MPIDR_EL1 by CPU.
+	 */
+	if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id",
+				     &sllc_pmu->sccl_id)) {
+		dev_err(&pdev->dev, "Cannot read sccl-id!\n");
+		return -EINVAL;
+	}
+
+	if (device_property_read_u32(&pdev->dev, "hisilicon,idx-id",
+				     &sllc_pmu->index_id)) {
+		dev_err(&pdev->dev, "Cannot read idx-id!\n");
+		return -EINVAL;
+	}
+
+	/* SLLC PMUs only share the same SCCL */
+	sllc_pmu->ccl_id = -1;
+
+	sllc_pmu->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(sllc_pmu->base)) {
+		dev_err(&pdev->dev, "ioremap failed for sllc_pmu resource.\n");
+		return PTR_ERR(sllc_pmu->base);
+	}
+
+	sllc_pmu->identifier = readl(sllc_pmu->base + SLLC_VERSION);
+
+	return 0;
+}
+
+static struct attribute *hisi_sllc_pmu_v2_format_attr[] = {
+	HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
+	HISI_PMU_FORMAT_ATTR(tgtid_min, "config1:0-10"),
+	HISI_PMU_FORMAT_ATTR(tgtid_max, "config1:11-21"),
+	HISI_PMU_FORMAT_ATTR(srcid_cmd, "config1:22-32"),
+	HISI_PMU_FORMAT_ATTR(srcid_msk, "config1:33-43"),
+	HISI_PMU_FORMAT_ATTR(tracetag_en, "config1:44"),
+	NULL
+};
+
+static const struct attribute_group hisi_sllc_pmu_v2_format_group = {
+	.name = "format",
+	.attrs = hisi_sllc_pmu_v2_format_attr,
+};
+
+static struct attribute *hisi_sllc_pmu_v2_events_attr[] = {
+	HISI_PMU_EVENT_ATTR(rx_req,             0x30),
+	HISI_PMU_EVENT_ATTR(rx_data,            0x31),
+	HISI_PMU_EVENT_ATTR(tx_req,             0x34),
+	HISI_PMU_EVENT_ATTR(tx_data,            0x35),
+	HISI_PMU_EVENT_ATTR(cycles,             0x09),
+	NULL
+};
+
+static const struct attribute_group hisi_sllc_pmu_v2_events_group = {
+	.name = "events",
+	.attrs = hisi_sllc_pmu_v2_events_attr,
+};
+
+static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL);
+
+static struct attribute *hisi_sllc_pmu_cpumask_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL
+};
+
+static const struct attribute_group hisi_sllc_pmu_cpumask_attr_group = {
+	.attrs = hisi_sllc_pmu_cpumask_attrs,
+};
+
+static struct device_attribute hisi_sllc_pmu_identifier_attr =
+	__ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL);
+
+static struct attribute *hisi_sllc_pmu_identifier_attrs[] = {
+	&hisi_sllc_pmu_identifier_attr.attr,
+	NULL
+};
+
+static struct attribute_group hisi_sllc_pmu_identifier_group = {
+	.attrs = hisi_sllc_pmu_identifier_attrs,
+};
+
+static const struct attribute_group *hisi_sllc_pmu_v2_attr_groups[] = {
+	&hisi_sllc_pmu_v2_format_group,
+	&hisi_sllc_pmu_v2_events_group,
+	&hisi_sllc_pmu_cpumask_attr_group,
+	&hisi_sllc_pmu_identifier_group,
+	NULL
+};
+
+static const struct hisi_uncore_ops hisi_uncore_sllc_ops = {
+	.write_evtype		= hisi_sllc_pmu_write_evtype,
+	.get_event_idx		= hisi_uncore_pmu_get_event_idx,
+	.start_counters		= hisi_sllc_pmu_start_counters,
+	.stop_counters		= hisi_sllc_pmu_stop_counters,
+	.enable_counter		= hisi_sllc_pmu_enable_counter,
+	.disable_counter	= hisi_sllc_pmu_disable_counter,
+	.enable_counter_int	= hisi_sllc_pmu_enable_counter_int,
+	.disable_counter_int	= hisi_sllc_pmu_disable_counter_int,
+	.write_counter		= hisi_sllc_pmu_write_counter,
+	.read_counter		= hisi_sllc_pmu_read_counter,
+	.get_int_status		= hisi_sllc_pmu_get_int_status,
+	.clear_int_status	= hisi_sllc_pmu_clear_int_status,
+	.enable_filter		= hisi_sllc_pmu_enable_filter,
+	.disable_filter		= hisi_sllc_pmu_clear_filter,
+};
+
+static int hisi_sllc_pmu_dev_probe(struct platform_device *pdev,
+				   struct hisi_pmu *sllc_pmu)
+{
+	int ret;
+
+	ret = hisi_sllc_pmu_init_data(pdev, sllc_pmu);
+	if (ret)
+		return ret;
+
+	ret = hisi_uncore_pmu_init_irq(sllc_pmu, pdev);
+	if (ret)
+		return ret;
+
+	sllc_pmu->pmu_events.attr_groups = hisi_sllc_pmu_v2_attr_groups;
+	sllc_pmu->ops = &hisi_uncore_sllc_ops;
+	sllc_pmu->check_event = SLLC_NR_EVENTS;
+	sllc_pmu->counter_bits = 64;
+	sllc_pmu->num_counters = 8;
+	sllc_pmu->dev = &pdev->dev;
+	sllc_pmu->on_cpu = -1;
+
+	return 0;
+}
+
+static int hisi_sllc_pmu_probe(struct platform_device *pdev)
+{
+	struct hisi_pmu *sllc_pmu;
+	char *name;
+	int ret;
+
+	sllc_pmu = devm_kzalloc(&pdev->dev, sizeof(*sllc_pmu), GFP_KERNEL);
+	if (!sllc_pmu)
+		return -ENOMEM;
+
+	ret = hisi_sllc_pmu_dev_probe(pdev, sllc_pmu);
+	if (ret)
+		return ret;
+
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_sllc%u",
+			      sllc_pmu->sccl_id, sllc_pmu->index_id);
+	if (!name)
+		return -ENOMEM;
+
+	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE,
+				       &sllc_pmu->node);
+	if (ret) {
+		dev_err(&pdev->dev, "Error %d registering hotplug\n", ret);
+		return ret;
+	}
+
+	sllc_pmu->pmu = (struct pmu) {
+		.module		= THIS_MODULE,
+		.task_ctx_nr	= perf_invalid_context,
+		.event_init	= hisi_uncore_pmu_event_init,
+		.pmu_enable	= hisi_uncore_pmu_enable,
+		.pmu_disable	= hisi_uncore_pmu_disable,
+		.add		= hisi_uncore_pmu_add,
+		.del		= hisi_uncore_pmu_del,
+		.start		= hisi_uncore_pmu_start,
+		.stop		= hisi_uncore_pmu_stop,
+		.read		= hisi_uncore_pmu_read,
+		.attr_groups    = sllc_pmu->pmu_events.attr_groups,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
+	};
+
+	ret = perf_pmu_register(&sllc_pmu->pmu, name, -1);
+	if (ret) {
+		dev_err(sllc_pmu->dev, "PMU register failed, ret = %d\n", ret);
+		cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE,
+					    &sllc_pmu->node);
+		irq_set_affinity_hint(sllc_pmu->irq, NULL);
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, sllc_pmu);
+
+	return ret;
+}
+
+static int hisi_sllc_pmu_remove(struct platform_device *pdev)
+{
+	struct hisi_pmu *sllc_pmu = platform_get_drvdata(pdev);
+
+	perf_pmu_unregister(&sllc_pmu->pmu);
+	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE,
+					    &sllc_pmu->node);
+	irq_set_affinity_hint(sllc_pmu->irq, NULL);
+
+	return 0;
+}
+
+static struct platform_driver hisi_sllc_pmu_driver = {
+	.driver = {
+		.name = "hisi_sllc_pmu",
+		.acpi_match_table = hisi_sllc_pmu_acpi_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe = hisi_sllc_pmu_probe,
+	.remove = hisi_sllc_pmu_remove,
+};
+
+static int __init hisi_sllc_pmu_module_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE,
+				      "AP_PERF_ARM_HISI_SLLC_ONLINE",
+				      hisi_uncore_pmu_online_cpu,
+				      hisi_uncore_pmu_offline_cpu);
+	if (ret) {
+		pr_err("SLLC PMU: cpuhp state setup failed, ret = %d\n", ret);
+		return ret;
+	}
+
+	ret = platform_driver_register(&hisi_sllc_pmu_driver);
+	if (ret)
+		cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE);
+
+	return ret;
+}
+module_init(hisi_sllc_pmu_module_init);
+
+static void __exit hisi_sllc_pmu_module_exit(void)
+{
+	platform_driver_unregister(&hisi_sllc_pmu_driver);
+	cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE);
+}
+module_exit(hisi_sllc_pmu_module_exit);
+
+MODULE_DESCRIPTION("HiSilicon SLLC uncore PMU driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Shaokun Zhang <zhangshaokun@hisilicon.com>");
+MODULE_AUTHOR("Qi Liu <liuqi115@huawei.com>");
diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c
index 8883af955a2a..fc54a80f9c5c 100644
--- a/drivers/perf/qcom_l2_pmu.c
+++ b/drivers/perf/qcom_l2_pmu.c
@@ -676,7 +676,7 @@ static ssize_t l2cache_pmu_event_show(struct device *dev,
 	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);
+	return sysfs_emit(page, "event=0x%02llx\n", pmu_attr->id);
 }
 
 #define L2CACHE_EVENT_ATTR(_name, _id)					     \
diff --git a/drivers/perf/qcom_l3_pmu.c b/drivers/perf/qcom_l3_pmu.c
index fb34b87b9471..bba078077c93 100644
--- a/drivers/perf/qcom_l3_pmu.c
+++ b/drivers/perf/qcom_l3_pmu.c
@@ -615,7 +615,7 @@ static ssize_t l3cache_pmu_format_show(struct device *dev,
 	struct dev_ext_attribute *eattr;
 
 	eattr = container_of(attr, struct dev_ext_attribute, attr);
-	return sprintf(buf, "%s\n", (char *) eattr->var);
+	return sysfs_emit(buf, "%s\n", (char *) eattr->var);
 }
 
 #define L3CACHE_PMU_FORMAT_ATTR(_name, _config)				      \
@@ -643,7 +643,7 @@ static ssize_t l3cache_pmu_event_show(struct device *dev,
 	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);
+	return sysfs_emit(page, "event=0x%02llx\n", pmu_attr->id);
 }
 
 #define L3CACHE_EVENT_ATTR(_name, _id)					     \
diff --git a/drivers/perf/thunderx2_pmu.c b/drivers/perf/thunderx2_pmu.c
index e116815fa809..06a6d569b0b5 100644
--- a/drivers/perf/thunderx2_pmu.c
+++ b/drivers/perf/thunderx2_pmu.c
@@ -128,7 +128,7 @@ __tx2_pmu_##_var##_show(struct device *dev,				\
 			       char *page)				\
 {									\
 	BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE);			\
-	return sprintf(page, _format "\n");				\
+	return sysfs_emit(page, _format "\n");				\
 }									\
 									\
 static struct device_attribute format_attr_##_var =			\
@@ -176,7 +176,7 @@ static ssize_t tx2_pmu_event_show(struct device *dev,
 	struct dev_ext_attribute *eattr;
 
 	eattr = container_of(attr, struct dev_ext_attribute, attr);
-	return sprintf(buf, "event=0x%lx\n", (unsigned long) eattr->var);
+	return sysfs_emit(buf, "event=0x%lx\n", (unsigned long) eattr->var);
 }
 
 #define TX2_EVENT_ATTR(name, config) \
diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c
index 44faa51ba799..ffe3bdeec845 100644
--- a/drivers/perf/xgene_pmu.c
+++ b/drivers/perf/xgene_pmu.c
@@ -170,7 +170,7 @@ static ssize_t xgene_pmu_format_show(struct device *dev,
 	struct dev_ext_attribute *eattr;
 
 	eattr = container_of(attr, struct dev_ext_attribute, attr);
-	return sprintf(buf, "%s\n", (char *) eattr->var);
+	return sysfs_emit(buf, "%s\n", (char *) eattr->var);
 }
 
 #define XGENE_PMU_FORMAT_ATTR(_name, _config)		\
@@ -281,7 +281,7 @@ static ssize_t xgene_pmu_event_show(struct device *dev,
 	struct dev_ext_attribute *eattr;
 
 	eattr = container_of(attr, struct dev_ext_attribute, attr);
-	return sprintf(buf, "config=0x%lx\n", (unsigned long) eattr->var);
+	return sysfs_emit(buf, "config=0x%lx\n", (unsigned long) eattr->var);
 }
 
 #define XGENE_PMU_EVENT_ATTR(_name, _config)		\