Merging upstream version 6.7.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

7 files changed, 520 insertions, 71 deletions

diff --git a/drivers/perf/arm_cspmu/Kconfig b/drivers/perf/arm_cspmu/Kconfig
index 25d25ded09..6f4e28fc84 100644
--- a/drivers/perf/arm_cspmu/Kconfig
+++ b/drivers/perf/arm_cspmu/Kconfig
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 #
-# Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# Copyright (c) 2022-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 
 config ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU
 	tristate "ARM Coresight Architecture PMU"
@@ -10,3 +10,20 @@ config ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU
 	  based on ARM CoreSight PMU architecture. Note that this PMU
 	  architecture does not have relationship with the ARM CoreSight
 	  Self-Hosted Tracing.
+
+config NVIDIA_CORESIGHT_PMU_ARCH_SYSTEM_PMU
+	tristate "NVIDIA Coresight Architecture PMU"
+	depends on ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU
+	help
+	  Provides NVIDIA specific attributes for performance monitoring unit
+	  (PMU) devices based on ARM CoreSight PMU architecture.
+
+config AMPERE_CORESIGHT_PMU_ARCH_SYSTEM_PMU
+       tristate "Ampere Coresight Architecture PMU"
+       depends on  ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU
+	help
+	  Provides Ampere specific attributes for performance monitoring unit
+	  (PMU) devices based on ARM CoreSight PMU architecture.
+
+	  In the first phase, the driver enables support on MCU PMU used in
+	  AmpereOne SoC family.
diff --git a/drivers/perf/arm_cspmu/Makefile b/drivers/perf/arm_cspmu/Makefile
index fedb17df98..220a734efd 100644
--- a/drivers/perf/arm_cspmu/Makefile
+++ b/drivers/perf/arm_cspmu/Makefile
@@ -1,6 +1,10 @@
-# Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# Copyright (c) 2022-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 #
 # SPDX-License-Identifier: GPL-2.0
 
 obj-$(CONFIG_ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += arm_cspmu_module.o
-arm_cspmu_module-y := arm_cspmu.o nvidia_cspmu.o
+
+arm_cspmu_module-y := arm_cspmu.o
+
+obj-$(CONFIG_NVIDIA_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += nvidia_cspmu.o
+obj-$(CONFIG_AMPERE_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += ampere_cspmu.o
diff --git a/drivers/perf/arm_cspmu/ampere_cspmu.c b/drivers/perf/arm_cspmu/ampere_cspmu.c
new file mode 100644
index 0000000000..f146a455e8
--- /dev/null
+++ b/drivers/perf/arm_cspmu/ampere_cspmu.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Ampere SoC PMU (Performance Monitor Unit)
+ *
+ * Copyright (c) 2023, Ampere Computing LLC
+ */
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/topology.h>
+
+#include "arm_cspmu.h"
+
+#define PMAUXR0		0xD80
+#define PMAUXR1		0xD84
+#define PMAUXR2		0xD88
+#define PMAUXR3		0xD8C
+
+#define to_ampere_cspmu_ctx(cspmu)	((struct ampere_cspmu_ctx *)(cspmu->impl.ctx))
+
+struct ampere_cspmu_ctx {
+	const char *name;
+	struct attribute **event_attr;
+	struct attribute **format_attr;
+};
+
+static DEFINE_IDA(mcu_pmu_ida);
+
+#define SOC_PMU_EVENT_ATTR_EXTRACTOR(_name, _config, _start, _end)        \
+	static inline u32 get_##_name(const struct perf_event *event)     \
+	{                                                                 \
+		return FIELD_GET(GENMASK_ULL(_end, _start),               \
+				 event->attr._config);                    \
+	}                                                                 \
+
+SOC_PMU_EVENT_ATTR_EXTRACTOR(event, config, 0, 8);
+SOC_PMU_EVENT_ATTR_EXTRACTOR(threshold, config1, 0, 7);
+SOC_PMU_EVENT_ATTR_EXTRACTOR(rank, config1, 8, 23);
+SOC_PMU_EVENT_ATTR_EXTRACTOR(bank, config1, 24, 55);
+
+static struct attribute *ampereone_mcu_pmu_event_attrs[] = {
+	ARM_CSPMU_EVENT_ATTR(cycle_count,		0x00),
+	ARM_CSPMU_EVENT_ATTR(act_sent,			0x01),
+	ARM_CSPMU_EVENT_ATTR(pre_sent,			0x02),
+	ARM_CSPMU_EVENT_ATTR(rd_sent,			0x03),
+	ARM_CSPMU_EVENT_ATTR(rda_sent,			0x04),
+	ARM_CSPMU_EVENT_ATTR(wr_sent,			0x05),
+	ARM_CSPMU_EVENT_ATTR(wra_sent,			0x06),
+	ARM_CSPMU_EVENT_ATTR(pd_entry_vld,		0x07),
+	ARM_CSPMU_EVENT_ATTR(sref_entry_vld,		0x08),
+	ARM_CSPMU_EVENT_ATTR(prea_sent,			0x09),
+	ARM_CSPMU_EVENT_ATTR(pre_sb_sent,		0x0a),
+	ARM_CSPMU_EVENT_ATTR(ref_sent,			0x0b),
+	ARM_CSPMU_EVENT_ATTR(rfm_sent,			0x0c),
+	ARM_CSPMU_EVENT_ATTR(ref_sb_sent,		0x0d),
+	ARM_CSPMU_EVENT_ATTR(rfm_sb_sent,		0x0e),
+	ARM_CSPMU_EVENT_ATTR(rd_rda_sent,		0x0f),
+	ARM_CSPMU_EVENT_ATTR(wr_wra_sent,		0x10),
+	ARM_CSPMU_EVENT_ATTR(raw_hazard,		0x11),
+	ARM_CSPMU_EVENT_ATTR(war_hazard,		0x12),
+	ARM_CSPMU_EVENT_ATTR(waw_hazard,		0x13),
+	ARM_CSPMU_EVENT_ATTR(rar_hazard,		0x14),
+	ARM_CSPMU_EVENT_ATTR(raw_war_waw_hazard,	0x15),
+	ARM_CSPMU_EVENT_ATTR(hprd_lprd_wr_req_vld,	0x16),
+	ARM_CSPMU_EVENT_ATTR(lprd_req_vld,		0x17),
+	ARM_CSPMU_EVENT_ATTR(hprd_req_vld,		0x18),
+	ARM_CSPMU_EVENT_ATTR(hprd_lprd_req_vld,		0x19),
+	ARM_CSPMU_EVENT_ATTR(prefetch_tgt,		0x1a),
+	ARM_CSPMU_EVENT_ATTR(wr_req_vld,		0x1b),
+	ARM_CSPMU_EVENT_ATTR(partial_wr_req_vld,	0x1c),
+	ARM_CSPMU_EVENT_ATTR(rd_retry,			0x1d),
+	ARM_CSPMU_EVENT_ATTR(wr_retry,			0x1e),
+	ARM_CSPMU_EVENT_ATTR(retry_gnt,			0x1f),
+	ARM_CSPMU_EVENT_ATTR(rank_change,		0x20),
+	ARM_CSPMU_EVENT_ATTR(dir_change,		0x21),
+	ARM_CSPMU_EVENT_ATTR(rank_dir_change,		0x22),
+	ARM_CSPMU_EVENT_ATTR(rank_active,		0x23),
+	ARM_CSPMU_EVENT_ATTR(rank_idle,			0x24),
+	ARM_CSPMU_EVENT_ATTR(rank_pd,			0x25),
+	ARM_CSPMU_EVENT_ATTR(rank_sref,			0x26),
+	ARM_CSPMU_EVENT_ATTR(queue_fill_gt_thresh,	0x27),
+	ARM_CSPMU_EVENT_ATTR(queue_rds_gt_thresh,	0x28),
+	ARM_CSPMU_EVENT_ATTR(queue_wrs_gt_thresh,	0x29),
+	ARM_CSPMU_EVENT_ATTR(phy_updt_complt,		0x2a),
+	ARM_CSPMU_EVENT_ATTR(tz_fail,			0x2b),
+	ARM_CSPMU_EVENT_ATTR(dram_errc,			0x2c),
+	ARM_CSPMU_EVENT_ATTR(dram_errd,			0x2d),
+	ARM_CSPMU_EVENT_ATTR(read_data_return,		0x32),
+	ARM_CSPMU_EVENT_ATTR(chi_wr_data_delta,		0x33),
+	ARM_CSPMU_EVENT_ATTR(zq_start,			0x34),
+	ARM_CSPMU_EVENT_ATTR(zq_latch,			0x35),
+	ARM_CSPMU_EVENT_ATTR(wr_fifo_full,		0x36),
+	ARM_CSPMU_EVENT_ATTR(info_fifo_full,		0x37),
+	ARM_CSPMU_EVENT_ATTR(cmd_fifo_full,		0x38),
+	ARM_CSPMU_EVENT_ATTR(dfi_nop,			0x39),
+	ARM_CSPMU_EVENT_ATTR(dfi_cmd,			0x3a),
+	ARM_CSPMU_EVENT_ATTR(rd_run_len,		0x3b),
+	ARM_CSPMU_EVENT_ATTR(wr_run_len,		0x3c),
+
+	ARM_CSPMU_EVENT_ATTR(cycles, ARM_CSPMU_EVT_CYCLES_DEFAULT),
+	NULL,
+};
+
+static struct attribute *ampereone_mcu_format_attrs[] = {
+	ARM_CSPMU_FORMAT_EVENT_ATTR,
+	ARM_CSPMU_FORMAT_ATTR(threshold, "config1:0-7"),
+	ARM_CSPMU_FORMAT_ATTR(rank, "config1:8-23"),
+	ARM_CSPMU_FORMAT_ATTR(bank, "config1:24-55"),
+	NULL,
+};
+
+static struct attribute **
+ampere_cspmu_get_event_attrs(const struct arm_cspmu *cspmu)
+{
+	const struct ampere_cspmu_ctx *ctx = to_ampere_cspmu_ctx(cspmu);
+
+	return ctx->event_attr;
+}
+
+static struct attribute **
+ampere_cspmu_get_format_attrs(const struct arm_cspmu *cspmu)
+{
+	const struct ampere_cspmu_ctx *ctx = to_ampere_cspmu_ctx(cspmu);
+
+	return ctx->format_attr;
+}
+
+static const char *
+ampere_cspmu_get_name(const struct arm_cspmu *cspmu)
+{
+	const struct ampere_cspmu_ctx *ctx = to_ampere_cspmu_ctx(cspmu);
+
+	return ctx->name;
+}
+
+static u32 ampere_cspmu_event_filter(const struct perf_event *event)
+{
+	/*
+	 * PMEVFILTR or PMCCFILTR aren't used in Ampere SoC PMU but are marked
+	 * as RES0. Make sure, PMCCFILTR is written zero.
+	 */
+	return 0;
+}
+
+static void ampere_cspmu_set_ev_filter(struct arm_cspmu *cspmu,
+				       struct hw_perf_event *hwc,
+				       u32 filter)
+{
+	struct perf_event *event;
+	unsigned int idx;
+	u32 threshold, rank, bank;
+
+	/*
+	 * At this point, all the events have the same filter settings.
+	 * Therefore, take the first event and use its configuration.
+	 */
+	idx = find_first_bit(cspmu->hw_events.used_ctrs,
+			     cspmu->cycle_counter_logical_idx);
+
+	event = cspmu->hw_events.events[idx];
+
+	threshold	= get_threshold(event);
+	rank		= get_rank(event);
+	bank		= get_bank(event);
+
+	writel(threshold, cspmu->base0 + PMAUXR0);
+	writel(rank, cspmu->base0 + PMAUXR1);
+	writel(bank, cspmu->base0 + PMAUXR2);
+}
+
+static int ampere_cspmu_validate_configs(struct perf_event *event,
+					 struct perf_event *event2)
+{
+	if (get_threshold(event) != get_threshold(event2) ||
+	    get_rank(event) != get_rank(event2) ||
+	    get_bank(event) != get_bank(event2))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int ampere_cspmu_validate_event(struct arm_cspmu *cspmu,
+				       struct perf_event *new)
+{
+	struct perf_event *curr, *leader = new->group_leader;
+	unsigned int idx;
+	int ret;
+
+	ret = ampere_cspmu_validate_configs(new, leader);
+	if (ret)
+		return ret;
+
+	/* We compare the global filter settings to the existing events */
+	idx = find_first_bit(cspmu->hw_events.used_ctrs,
+			     cspmu->cycle_counter_logical_idx);
+
+	/* This is the first event, thus any configuration is fine */
+	if (idx == cspmu->cycle_counter_logical_idx)
+		return 0;
+
+	curr = cspmu->hw_events.events[idx];
+
+	return ampere_cspmu_validate_configs(curr, new);
+}
+
+static char *ampere_cspmu_format_name(const struct arm_cspmu *cspmu,
+				      const char *name_pattern)
+{
+	struct device *dev = cspmu->dev;
+	int id;
+
+	id = ida_alloc(&mcu_pmu_ida, GFP_KERNEL);
+	if (id < 0)
+		return ERR_PTR(id);
+
+	return devm_kasprintf(dev, GFP_KERNEL, name_pattern, id);
+}
+
+static int ampere_cspmu_init_ops(struct arm_cspmu *cspmu)
+{
+	struct device *dev = cspmu->dev;
+	struct ampere_cspmu_ctx *ctx;
+	struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops;
+
+	ctx = devm_kzalloc(dev, sizeof(struct ampere_cspmu_ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->event_attr	= ampereone_mcu_pmu_event_attrs;
+	ctx->format_attr = ampereone_mcu_format_attrs;
+	ctx->name = ampere_cspmu_format_name(cspmu, "ampere_mcu_pmu_%d");
+	if (IS_ERR_OR_NULL(ctx->name))
+		return ctx->name ? PTR_ERR(ctx->name) : -ENOMEM;
+
+	cspmu->impl.ctx = ctx;
+
+	impl_ops->event_filter		= ampere_cspmu_event_filter;
+	impl_ops->set_ev_filter		= ampere_cspmu_set_ev_filter;
+	impl_ops->validate_event	= ampere_cspmu_validate_event;
+	impl_ops->get_name		= ampere_cspmu_get_name;
+	impl_ops->get_event_attrs	= ampere_cspmu_get_event_attrs;
+	impl_ops->get_format_attrs	= ampere_cspmu_get_format_attrs;
+
+	return 0;
+}
+
+/* Match all Ampere Coresight PMU devices */
+static const struct arm_cspmu_impl_match ampere_cspmu_param = {
+	.pmiidr_val	= ARM_CSPMU_IMPL_ID_AMPERE,
+	.module		= THIS_MODULE,
+	.impl_init_ops	= ampere_cspmu_init_ops
+};
+
+static int __init ampere_cspmu_init(void)
+{
+	int ret;
+
+	ret = arm_cspmu_impl_register(&ampere_cspmu_param);
+	if (ret)
+		pr_err("ampere_cspmu backend registration error: %d\n", ret);
+
+	return ret;
+}
+
+static void __exit ampere_cspmu_exit(void)
+{
+	arm_cspmu_impl_unregister(&ampere_cspmu_param);
+}
+
+module_init(ampere_cspmu_init);
+module_exit(ampere_cspmu_exit);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/perf/arm_cspmu/arm_cspmu.c b/drivers/perf/arm_cspmu/arm_cspmu.c
index 9363c31f31..2cc35dded0 100644
--- a/drivers/perf/arm_cspmu/arm_cspmu.c
+++ b/drivers/perf/arm_cspmu/arm_cspmu.c
@@ -16,7 +16,7 @@
  * The user should refer to the vendor technical documentation to get details
  * about the supported events.
  *
- * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+ * Copyright (c) 2022-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
  *
  */
 
@@ -26,11 +26,11 @@
 #include <linux/interrupt.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/perf_event.h>
 #include <linux/platform_device.h>
 
 #include "arm_cspmu.h"
-#include "nvidia_cspmu.h"
 
 #define PMUNAME "arm_cspmu"
 #define DRVNAME "arm-cs-arch-pmu"
@@ -112,11 +112,13 @@
  */
 #define HILOHI_MAX_POLL	1000
 
-/* JEDEC-assigned JEP106 identification code */
-#define ARM_CSPMU_IMPL_ID_NVIDIA		0x36B
-
 static unsigned long arm_cspmu_cpuhp_state;
 
+static DEFINE_MUTEX(arm_cspmu_lock);
+
+static void arm_cspmu_set_ev_filter(struct arm_cspmu *cspmu,
+				    struct hw_perf_event *hwc, u32 filter);
+
 static struct acpi_apmt_node *arm_cspmu_apmt_node(struct device *dev)
 {
 	return *(struct acpi_apmt_node **)dev_get_platdata(dev);
@@ -373,27 +375,45 @@ static struct attribute_group arm_cspmu_cpumask_attr_group = {
 	.attrs = arm_cspmu_cpumask_attrs,
 };
 
-struct impl_match {
-	u32 pmiidr;
-	u32 mask;
-	int (*impl_init_ops)(struct arm_cspmu *cspmu);
-};
-
-static const struct impl_match impl_match[] = {
+static struct arm_cspmu_impl_match impl_match[] = {
 	{
-	  .pmiidr = ARM_CSPMU_IMPL_ID_NVIDIA,
-	  .mask = ARM_CSPMU_PMIIDR_IMPLEMENTER,
-	  .impl_init_ops = nv_cspmu_init_ops
+		.module_name	= "nvidia_cspmu",
+		.pmiidr_val	= ARM_CSPMU_IMPL_ID_NVIDIA,
+		.pmiidr_mask	= ARM_CSPMU_PMIIDR_IMPLEMENTER,
+		.module		= NULL,
+		.impl_init_ops	= NULL,
 	},
-	{}
+	{
+		.module_name	= "ampere_cspmu",
+		.pmiidr_val	= ARM_CSPMU_IMPL_ID_AMPERE,
+		.pmiidr_mask	= ARM_CSPMU_PMIIDR_IMPLEMENTER,
+		.module		= NULL,
+		.impl_init_ops	= NULL,
+	},
+
+	{0}
 };
 
+static struct arm_cspmu_impl_match *arm_cspmu_impl_match_get(u32 pmiidr)
+{
+	struct arm_cspmu_impl_match *match = impl_match;
+
+	for (; match->pmiidr_val; match++) {
+		u32 mask = match->pmiidr_mask;
+
+		if ((match->pmiidr_val & mask) == (pmiidr & mask))
+			return match;
+	}
+
+	return NULL;
+}
+
 static int arm_cspmu_init_impl_ops(struct arm_cspmu *cspmu)
 {
-	int ret;
+	int ret = 0;
 	struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops;
 	struct acpi_apmt_node *apmt_node = arm_cspmu_apmt_node(cspmu->dev);
-	const struct impl_match *match = impl_match;
+	struct arm_cspmu_impl_match *match;
 
 	/*
 	 * Get PMU implementer and product id from APMT node.
@@ -405,17 +425,36 @@ static int arm_cspmu_init_impl_ops(struct arm_cspmu *cspmu)
 				       readl(cspmu->base0 + PMIIDR);
 
 	/* Find implementer specific attribute ops. */
-	for (; match->pmiidr; match++) {
-		const u32 mask = match->mask;
+	match = arm_cspmu_impl_match_get(cspmu->impl.pmiidr);
+
+	/* Load implementer module and initialize the callbacks. */
+	if (match) {
+		mutex_lock(&arm_cspmu_lock);
+
+		if (match->impl_init_ops) {
+			/* Prevent unload until PMU registration is done. */
+			if (try_module_get(match->module)) {
+				cspmu->impl.module = match->module;
+				cspmu->impl.match = match;
+				ret = match->impl_init_ops(cspmu);
+				if (ret)
+					module_put(match->module);
+			} else {
+				WARN(1, "arm_cspmu failed to get module: %s\n",
+					match->module_name);
+				ret = -EINVAL;
+			}
+		} else {
+			request_module_nowait(match->module_name);
+			ret = -EPROBE_DEFER;
+		}
 
-		if ((match->pmiidr & mask) == (cspmu->impl.pmiidr & mask)) {
-			ret = match->impl_init_ops(cspmu);
-			if (ret)
-				return ret;
+		mutex_unlock(&arm_cspmu_lock);
 
-			break;
-		}
-	}
+		if (ret)
+			return ret;
+	} else
+		cspmu->impl.module = THIS_MODULE;
 
 	/* Use default callbacks if implementer doesn't provide one. */
 	CHECK_DEFAULT_IMPL_OPS(impl_ops, get_event_attrs);
@@ -426,6 +465,7 @@ static int arm_cspmu_init_impl_ops(struct arm_cspmu *cspmu)
 	CHECK_DEFAULT_IMPL_OPS(impl_ops, event_type);
 	CHECK_DEFAULT_IMPL_OPS(impl_ops, event_filter);
 	CHECK_DEFAULT_IMPL_OPS(impl_ops, event_attr_is_visible);
+	CHECK_DEFAULT_IMPL_OPS(impl_ops, set_ev_filter);
 
 	return 0;
 }
@@ -478,11 +518,6 @@ arm_cspmu_alloc_attr_group(struct arm_cspmu *cspmu)
 	struct attribute_group **attr_groups = NULL;
 	struct device *dev = cspmu->dev;
 	const struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops;
-	int ret;
-
-	ret = arm_cspmu_init_impl_ops(cspmu);
-	if (ret)
-		return NULL;
 
 	cspmu->identifier = impl_ops->get_identifier(cspmu);
 	cspmu->name = impl_ops->get_name(cspmu);
@@ -549,7 +584,7 @@ static void arm_cspmu_disable(struct pmu *pmu)
 static int arm_cspmu_get_event_idx(struct arm_cspmu_hw_events *hw_events,
 				struct perf_event *event)
 {
-	int idx;
+	int idx, ret;
 	struct arm_cspmu *cspmu = to_arm_cspmu(event->pmu);
 
 	if (supports_cycle_counter(cspmu)) {
@@ -583,6 +618,12 @@ static int arm_cspmu_get_event_idx(struct arm_cspmu_hw_events *hw_events,
 	if (idx >= cspmu->num_logical_ctrs)
 		return -EAGAIN;
 
+	if (cspmu->impl.ops.validate_event) {
+		ret = cspmu->impl.ops.validate_event(cspmu, event);
+		if (ret)
+			return ret;
+	}
+
 	set_bit(idx, hw_events->used_ctrs);
 
 	return idx;
@@ -699,7 +740,10 @@ static void arm_cspmu_write_counter(struct perf_event *event, u64 val)
 	if (use_64b_counter_reg(cspmu)) {
 		offset = counter_offset(sizeof(u64), event->hw.idx);
 
-		writeq(val, cspmu->base1 + offset);
+		if (cspmu->has_atomic_dword)
+			writeq(val, cspmu->base1 + offset);
+		else
+			lo_hi_writeq(val, cspmu->base1 + offset);
 	} else {
 		offset = counter_offset(sizeof(u32), event->hw.idx);
 
@@ -792,9 +836,9 @@ static inline void arm_cspmu_set_event(struct arm_cspmu *cspmu,
 	writel(hwc->config, cspmu->base0 + offset);
 }
 
-static inline void arm_cspmu_set_ev_filter(struct arm_cspmu *cspmu,
-					   struct hw_perf_event *hwc,
-					   u32 filter)
+static void arm_cspmu_set_ev_filter(struct arm_cspmu *cspmu,
+					struct hw_perf_event *hwc,
+					u32 filter)
 {
 	u32 offset = PMEVFILTR + (4 * hwc->idx);
 
@@ -826,7 +870,7 @@ static void arm_cspmu_start(struct perf_event *event, int pmu_flags)
 		arm_cspmu_set_cc_filter(cspmu, filter);
 	} else {
 		arm_cspmu_set_event(cspmu, hwc);
-		arm_cspmu_set_ev_filter(cspmu, hwc, filter);
+		cspmu->impl.ops.set_ev_filter(cspmu, hwc, filter);
 	}
 
 	hwc->state = 0;
@@ -1064,7 +1108,7 @@ static int arm_cspmu_request_irq(struct arm_cspmu *cspmu)
 
 static inline int arm_cspmu_find_cpu_container(int cpu, u32 container_uid)
 {
-	u32 acpi_uid;
+	u64 acpi_uid;
 	struct device *cpu_dev;
 	struct acpi_device *acpi_dev;
 
@@ -1074,10 +1118,8 @@ static inline int arm_cspmu_find_cpu_container(int cpu, u32 container_uid)
 
 	acpi_dev = ACPI_COMPANION(cpu_dev);
 	while (acpi_dev) {
-		if (!strcmp(acpi_device_hid(acpi_dev),
-			    ACPI_PROCESSOR_CONTAINER_HID) &&
-		    !kstrtouint(acpi_device_uid(acpi_dev), 0, &acpi_uid) &&
-		    acpi_uid == container_uid)
+		if (acpi_dev_hid_uid_match(acpi_dev, ACPI_PROCESSOR_CONTAINER_HID, NULL) &&
+		    !acpi_dev_uid_to_integer(acpi_dev, &acpi_uid) && acpi_uid == container_uid)
 			return 0;
 
 		acpi_dev = acpi_dev_parent(acpi_dev);
@@ -1152,7 +1194,7 @@ static int arm_cspmu_register_pmu(struct arm_cspmu *cspmu)
 
 	cspmu->pmu = (struct pmu){
 		.task_ctx_nr	= perf_invalid_context,
-		.module		= THIS_MODULE,
+		.module		= cspmu->impl.module,
 		.pmu_enable	= arm_cspmu_enable,
 		.pmu_disable	= arm_cspmu_disable,
 		.event_init	= arm_cspmu_event_init,
@@ -1199,11 +1241,17 @@ static int arm_cspmu_device_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = arm_cspmu_register_pmu(cspmu);
+	ret = arm_cspmu_init_impl_ops(cspmu);
 	if (ret)
 		return ret;
 
-	return 0;
+	ret = arm_cspmu_register_pmu(cspmu);
+
+	/* Matches arm_cspmu_init_impl_ops() above. */
+	if (cspmu->impl.module != THIS_MODULE)
+		module_put(cspmu->impl.module);
+
+	return ret;
 }
 
 static int arm_cspmu_device_remove(struct platform_device *pdev)
@@ -1303,6 +1351,75 @@ static void __exit arm_cspmu_exit(void)
 	cpuhp_remove_multi_state(arm_cspmu_cpuhp_state);
 }
 
+int arm_cspmu_impl_register(const struct arm_cspmu_impl_match *impl_match)
+{
+	struct arm_cspmu_impl_match *match;
+	int ret = 0;
+
+	match = arm_cspmu_impl_match_get(impl_match->pmiidr_val);
+
+	if (match) {
+		mutex_lock(&arm_cspmu_lock);
+
+		if (!match->impl_init_ops) {
+			match->module = impl_match->module;
+			match->impl_init_ops = impl_match->impl_init_ops;
+		} else {
+			/* Broken match table may contain non-unique entries */
+			WARN(1, "arm_cspmu backend already registered for module: %s, pmiidr: 0x%x, mask: 0x%x\n",
+				match->module_name,
+				match->pmiidr_val,
+				match->pmiidr_mask);
+
+			ret = -EINVAL;
+		}
+
+		mutex_unlock(&arm_cspmu_lock);
+
+		if (!ret)
+			ret = driver_attach(&arm_cspmu_driver.driver);
+	} else {
+		pr_err("arm_cspmu reg failed, unable to find a match for pmiidr: 0x%x\n",
+			impl_match->pmiidr_val);
+
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(arm_cspmu_impl_register);
+
+static int arm_cspmu_match_device(struct device *dev, const void *match)
+{
+	struct arm_cspmu *cspmu = platform_get_drvdata(to_platform_device(dev));
+
+	return (cspmu && cspmu->impl.match == match) ? 1 : 0;
+}
+
+void arm_cspmu_impl_unregister(const struct arm_cspmu_impl_match *impl_match)
+{
+	struct device *dev;
+	struct arm_cspmu_impl_match *match;
+
+	match = arm_cspmu_impl_match_get(impl_match->pmiidr_val);
+
+	if (WARN_ON(!match))
+		return;
+
+	/* Unbind the driver from all matching backend devices. */
+	while ((dev = driver_find_device(&arm_cspmu_driver.driver, NULL,
+			match, arm_cspmu_match_device)))
+		device_release_driver(dev);
+
+	mutex_lock(&arm_cspmu_lock);
+
+	match->module = NULL;
+	match->impl_init_ops = NULL;
+
+	mutex_unlock(&arm_cspmu_lock);
+}
+EXPORT_SYMBOL_GPL(arm_cspmu_impl_unregister);
+
 module_init(arm_cspmu_init);
 module_exit(arm_cspmu_exit);
 
diff --git a/drivers/perf/arm_cspmu/arm_cspmu.h b/drivers/perf/arm_cspmu/arm_cspmu.h
index 83df53d1c1..2fe723555a 100644
--- a/drivers/perf/arm_cspmu/arm_cspmu.h
+++ b/drivers/perf/arm_cspmu/arm_cspmu.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0
  *
  * ARM CoreSight Architecture PMU driver.
- * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+ * Copyright (c) 2022-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
  *
  */
 
@@ -69,6 +69,10 @@
 #define ARM_CSPMU_PMIIDR_IMPLEMENTER	GENMASK(11, 0)
 #define ARM_CSPMU_PMIIDR_PRODUCTID	GENMASK(31, 20)
 
+/* JEDEC-assigned JEP106 identification code */
+#define ARM_CSPMU_IMPL_ID_NVIDIA	0x36B
+#define ARM_CSPMU_IMPL_ID_AMPERE	0xA16
+
 struct arm_cspmu;
 
 /* This tracks the events assigned to each counter in the PMU. */
@@ -101,14 +105,34 @@ struct arm_cspmu_impl_ops {
 	u32 (*event_type)(const struct perf_event *event);
 	/* Decode filter value from configs */
 	u32 (*event_filter)(const struct perf_event *event);
+	/* Set event filter */
+	void (*set_ev_filter)(struct arm_cspmu *cspmu,
+			      struct hw_perf_event *hwc, u32 filter);
+	/* Implementation specific event validation */
+	int (*validate_event)(struct arm_cspmu *cspmu,
+			      struct perf_event *event);
 	/* Hide/show unsupported events */
 	umode_t (*event_attr_is_visible)(struct kobject *kobj,
 					 struct attribute *attr, int unused);
 };
 
+/* Vendor/implementer registration parameter. */
+struct arm_cspmu_impl_match {
+	/* Backend module. */
+	struct module *module;
+	const char *module_name;
+	/* PMIIDR value/mask. */
+	u32 pmiidr_val;
+	u32 pmiidr_mask;
+	/* Callback to vendor backend to init arm_cspmu_impl::ops. */
+	int (*impl_init_ops)(struct arm_cspmu *cspmu);
+};
+
 /* Vendor/implementer descriptor. */
 struct arm_cspmu_impl {
 	u32 pmiidr;
+	struct module *module;
+	struct arm_cspmu_impl_match *match;
 	struct arm_cspmu_impl_ops ops;
 	void *ctx;
 };
@@ -147,4 +171,10 @@ ssize_t arm_cspmu_sysfs_format_show(struct device *dev,
 				    struct device_attribute *attr,
 				    char *buf);
 
+/* Register vendor backend. */
+int arm_cspmu_impl_register(const struct arm_cspmu_impl_match *impl_match);
+
+/* Unregister vendor backend. */
+void arm_cspmu_impl_unregister(const struct arm_cspmu_impl_match *impl_match);
+
 #endif /* __ARM_CSPMU_H__ */
diff --git a/drivers/perf/arm_cspmu/nvidia_cspmu.c b/drivers/perf/arm_cspmu/nvidia_cspmu.c
index 72ef80caa3..0382b702f0 100644
--- a/drivers/perf/arm_cspmu/nvidia_cspmu.c
+++ b/drivers/perf/arm_cspmu/nvidia_cspmu.c
@@ -1,14 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+ * Copyright (c) 2022-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
  *
  */
 
 /* Support for NVIDIA specific attributes. */
 
+#include <linux/module.h>
 #include <linux/topology.h>
 
-#include "nvidia_cspmu.h"
+#include "arm_cspmu.h"
 
 #define NV_PCIE_PORT_COUNT           10ULL
 #define NV_PCIE_FILTER_ID_MASK       GENMASK_ULL(NV_PCIE_PORT_COUNT - 1, 0)
@@ -351,7 +352,7 @@ static char *nv_cspmu_format_name(const struct arm_cspmu *cspmu,
 	return name;
 }
 
-int nv_cspmu_init_ops(struct arm_cspmu *cspmu)
+static int nv_cspmu_init_ops(struct arm_cspmu *cspmu)
 {
 	u32 prodid;
 	struct nv_cspmu_ctx *ctx;
@@ -395,6 +396,31 @@ int nv_cspmu_init_ops(struct arm_cspmu *cspmu)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(nv_cspmu_init_ops);
+
+/* Match all NVIDIA Coresight PMU devices */
+static const struct arm_cspmu_impl_match nv_cspmu_param = {
+	.pmiidr_val	= ARM_CSPMU_IMPL_ID_NVIDIA,
+	.module		= THIS_MODULE,
+	.impl_init_ops	= nv_cspmu_init_ops
+};
+
+static int __init nvidia_cspmu_init(void)
+{
+	int ret;
+
+	ret = arm_cspmu_impl_register(&nv_cspmu_param);
+	if (ret)
+		pr_err("nvidia_cspmu backend registration error: %d\n", ret);
+
+	return ret;
+}
+
+static void __exit nvidia_cspmu_exit(void)
+{
+	arm_cspmu_impl_unregister(&nv_cspmu_param);
+}
+
+module_init(nvidia_cspmu_init);
+module_exit(nvidia_cspmu_exit);
 
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/perf/arm_cspmu/nvidia_cspmu.h b/drivers/perf/arm_cspmu/nvidia_cspmu.h
deleted file mode 100644
index 71e18f0dc5..0000000000
--- a/drivers/perf/arm_cspmu/nvidia_cspmu.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0
- *
- * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
- *
- */
-
-/* Support for NVIDIA specific attributes. */
-
-#ifndef __NVIDIA_CSPMU_H__
-#define __NVIDIA_CSPMU_H__
-
-#include "arm_cspmu.h"
-
-/* Allocate NVIDIA descriptor. */
-int nv_cspmu_init_ops(struct arm_cspmu *cspmu);
-
-#endif /* __NVIDIA_CSPMU_H__ */