Merge branch 'for-next/perf' into for-next/core

* for-next/perf: (21 commits)
  arm_pmu: Drop redundant armpmu->map_event() in armpmu_event_init()
  drivers/perf: hisi: Add TLP filter support
  Documentation: perf: Indent filter options list of hisi-pcie-pmu
  docs: perf: Fix PMU instance name of hisi-pcie-pmu
  drivers/perf: hisi: Fix some event id for hisi-pcie-pmu
  arm64/perf: Replace PMU version number '0' with ID_AA64DFR0_EL1_PMUVer_NI
  perf/amlogic: Remove unused header inclusions of  <linux/version.h>
  perf/amlogic: Fix build error for x86_64 allmodconfig
  dt-binding: perf: Add Amlogic DDR PMU
  docs/perf: Add documentation for the Amlogic G12 DDR PMU
  perf/amlogic: Add support for Amlogic meson G12 SoC DDR PMU driver
  MAINTAINERS: Update HiSilicon PMU maintainers
  perf: arm_cspmu: Fix module cyclic dependency
  perf: arm_cspmu: Fix build failure on x86_64
  perf: arm_cspmu: Fix modular builds due to missing MODULE_LICENSE()s
  perf: arm_cspmu: Add support for NVIDIA SCF and MCF attribute
  perf: arm_cspmu: Add support for ARM CoreSight PMU driver
  perf/smmuv3: Fix hotplug callback leak in arm_smmu_pmu_init()
  perf/arm_dmc620: Fix hotplug callback leak in dmc620_pmu_init()
  drivers: perf: marvell_cn10k: Fix hotplug callback leak in tad_pmu_init()
  ...

Documentation/admin-guide/perf/hisi-pcie-pmu.rst

@@ -15,10 +15,10 @@ HiSilicon PCIe PMU driver
 The PCIe PMU driver registers a perf PMU with the name of its sicl-id and PCIe
 Core id.::
 
-  /sys/bus/event_source/hisi_pcie<sicl>_<core>
+  /sys/bus/event_source/hisi_pcie<sicl>_core<core>
 
 PMU driver provides description of available events and filter options in sysfs,
-see /sys/bus/event_source/devices/hisi_pcie<sicl>_<core>.
+see /sys/bus/event_source/devices/hisi_pcie<sicl>_core<core>.
 
 The "format" directory describes all formats of the config (events) and config1
 (filter options) fields of the perf_event_attr structure. The "events" directory
@@ -33,13 +33,13 @@ monitored by PMU.
 Example usage of perf::
 
   $# perf list
-  hisi_pcie0_0/rx_mwr_latency/ [kernel PMU event]
-  hisi_pcie0_0/rx_mwr_cnt/ [kernel PMU event]
+  hisi_pcie0_core0/rx_mwr_latency/ [kernel PMU event]
+  hisi_pcie0_core0/rx_mwr_cnt/ [kernel PMU event]
   ------------------------------------------
 
-  $# perf stat -e hisi_pcie0_0/rx_mwr_latency/
-  $# perf stat -e hisi_pcie0_0/rx_mwr_cnt/
-  $# perf stat -g -e hisi_pcie0_0/rx_mwr_latency/ -e hisi_pcie0_0/rx_mwr_cnt/
+  $# perf stat -e hisi_pcie0_core0/rx_mwr_latency/
+  $# perf stat -e hisi_pcie0_core0/rx_mwr_cnt/
+  $# perf stat -g -e hisi_pcie0_core0/rx_mwr_latency/ -e hisi_pcie0_core0/rx_mwr_cnt/
 
 The current driver does not support sampling. So "perf record" is unsupported.
 Also attach to a task is unsupported for PCIe PMU.
@@ -48,59 +48,83 @@ Filter options
 --------------
 
 1. Target filter
-PMU could only monitor the performance of traffic downstream target Root Ports
-or downstream target Endpoint. PCIe PMU driver support "port" and "bdf"
-interfaces for users, and these two interfaces aren't supported at the same
-time.
 
--port
-"port" filter can be used in all PCIe PMU events, target Root Port can be
-selected by configuring the 16-bits-bitmap "port". Multi ports can be selected
-for AP-layer-events, and only one port can be selected for TL/DL-layer-events.
+   PMU could only monitor the performance of traffic downstream target Root
+   Ports or downstream target Endpoint. PCIe PMU driver support "port" and
+   "bdf" interfaces for users, and these two interfaces aren't supported at the
+   same time.
 
-For example, if target Root Port is 0000:00:00.0 (x8 lanes), bit0 of bitmap
-should be set, port=0x1; if target Root Port is 0000:00:04.0 (x4 lanes),
-bit8 is set, port=0x100; if these two Root Ports are both monitored, port=0x101.
+   - port
 
-Example usage of perf::
+     "port" filter can be used in all PCIe PMU events, target Root Port can be
+     selected by configuring the 16-bits-bitmap "port". Multi ports can be
+     selected for AP-layer-events, and only one port can be selected for
+     TL/DL-layer-events.
 
-  $# perf stat -e hisi_pcie0_0/rx_mwr_latency,port=0x1/ sleep 5
+     For example, if target Root Port is 0000:00:00.0 (x8 lanes), bit0 of
+     bitmap should be set, port=0x1; if target Root Port is 0000:00:04.0 (x4
+     lanes), bit8 is set, port=0x100; if these two Root Ports are both
+     monitored, port=0x101.
 
--bdf
+     Example usage of perf::
 
-"bdf" filter can only be used in bandwidth events, target Endpoint is selected
-by configuring BDF to "bdf". Counter only counts the bandwidth of message
-requested by target Endpoint.
+       $# perf stat -e hisi_pcie0_core0/rx_mwr_latency,port=0x1/ sleep 5
 
-For example, "bdf=0x3900" means BDF of target Endpoint is 0000:39:00.0.
+   - bdf
 
-Example usage of perf::
+     "bdf" filter can only be used in bandwidth events, target Endpoint is
+     selected by configuring BDF to "bdf". Counter only counts the bandwidth of
+     message requested by target Endpoint.
+
+     For example, "bdf=0x3900" means BDF of target Endpoint is 0000:39:00.0.
+
+     Example usage of perf::
 
-  $# perf stat -e hisi_pcie0_0/rx_mrd_flux,bdf=0x3900/ sleep 5
+       $# perf stat -e hisi_pcie0_core0/rx_mrd_flux,bdf=0x3900/ sleep 5
 
 2. Trigger filter
-Event statistics start when the first time TLP length is greater/smaller
-than trigger condition. You can set the trigger condition by writing "trig_len",
-and set the trigger mode by writing "trig_mode". This filter can only be used
-in bandwidth events.
 
-For example, "trig_len=4" means trigger condition is 2^4 DW, "trig_mode=0"
-means statistics start when TLP length > trigger condition, "trig_mode=1"
-means start when TLP length < condition.
+   Event statistics start when the first time TLP length is greater/smaller
+   than trigger condition. You can set the trigger condition by writing
+   "trig_len", and set the trigger mode by writing "trig_mode". This filter can
+   only be used in bandwidth events.
 
-Example usage of perf::
+   For example, "trig_len=4" means trigger condition is 2^4 DW, "trig_mode=0"
+   means statistics start when TLP length > trigger condition, "trig_mode=1"
+   means start when TLP length < condition.
+
+   Example usage of perf::
 
-  $# perf stat -e hisi_pcie0_0/rx_mrd_flux,trig_len=0x4,trig_mode=1/ sleep 5
+     $# perf stat -e hisi_pcie0_core0/rx_mrd_flux,trig_len=0x4,trig_mode=1/ sleep 5
 
 3. Threshold filter
-Counter counts when TLP length within the specified range. You can set the
-threshold by writing "thr_len", and set the threshold mode by writing
-"thr_mode". This filter can only be used in bandwidth events.
 
-For example, "thr_len=4" means threshold is 2^4 DW, "thr_mode=0" means
-counter counts when TLP length >= threshold, and "thr_mode=1" means counts
-when TLP length < threshold.
+   Counter counts when TLP length within the specified range. You can set the
+   threshold by writing "thr_len", and set the threshold mode by writing
+   "thr_mode". This filter can only be used in bandwidth events.
 
-Example usage of perf::
+   For example, "thr_len=4" means threshold is 2^4 DW, "thr_mode=0" means
+   counter counts when TLP length >= threshold, and "thr_mode=1" means counts
+   when TLP length < threshold.
+
+   Example usage of perf::
+
+     $# perf stat -e hisi_pcie0_core0/rx_mrd_flux,thr_len=0x4,thr_mode=1/ sleep 5
+
+4. TLP Length filter
+
+   When counting bandwidth, the data can be composed of certain parts of TLP
+   packets. You can specify it through "len_mode":
+
+   - 2'b00: Reserved (Do not use this since the behaviour is undefined)
+   - 2'b01: Bandwidth of TLP payloads
+   - 2'b10: Bandwidth of TLP headers
+   - 2'b11: Bandwidth of both TLP payloads and headers
+
+   For example, "len_mode=2" means only counting the bandwidth of TLP headers
+   and "len_mode=3" means the final bandwidth data is composed of both TLP
+   headers and payloads. Default value if not specified is 2'b11.
+
+   Example usage of perf::
 
-  $# perf stat -e hisi_pcie0_0/rx_mrd_flux,thr_len=0x4,thr_mode=1/ sleep 5
+     $# perf stat -e hisi_pcie0_core0/rx_mrd_flux,len_mode=0x1/ sleep 5

Documentation/admin-guide/perf/index.rst

@@ -19,3 +19,5 @@ Performance monitor support
    arm_dsu_pmu
    thunderx2-pmu
    alibaba_pmu
+   nvidia-pmu
+   meson-ddr-pmu

Documentation/admin-guide/perf/meson-ddr-pmu.rst

+.. SPDX-License-Identifier: GPL-2.0
+
+===========================================================
+Amlogic SoC DDR Bandwidth Performance Monitoring Unit (PMU)
+===========================================================
+
+The Amlogic Meson G12 SoC contains a bandwidth monitor inside DRAM controller.
+The monitor includes 4 channels. Each channel can count the request accessing
+DRAM. The channel can count up to 3 AXI port simultaneously. It can be helpful
+to show if the performance bottleneck is on DDR bandwidth.
+
+Currently, this driver supports the following 5 perf events:
+
++ meson_ddr_bw/total_rw_bytes/
++ meson_ddr_bw/chan_1_rw_bytes/
++ meson_ddr_bw/chan_2_rw_bytes/
++ meson_ddr_bw/chan_3_rw_bytes/
++ meson_ddr_bw/chan_4_rw_bytes/
+
+meson_ddr_bw/chan_{1,2,3,4}_rw_bytes/ events are channel-specific events.
+Each channel support filtering, which can let the channel to monitor
+individual IP module in SoC.
+
+Below are DDR access request event filter keywords:
+
++ arm             - from CPU
++ vpu_read1       - from OSD + VPP read
++ gpu             - from 3D GPU
++ pcie            - from PCIe controller
++ hdcp            - from HDCP controller
++ hevc_front      - from HEVC codec front end
++ usb3_0          - from USB3.0 controller
++ hevc_back       - from HEVC codec back end
++ h265enc         - from HEVC encoder
++ vpu_read2       - from DI read
++ vpu_write1      - from VDIN write
++ vpu_write2      - from di write
++ vdec            - from legacy codec video decoder
++ hcodec          - from H264 encoder
++ ge2d            - from ge2d
++ spicc1          - from SPI controller 1
++ usb0            - from USB2.0 controller 0
++ dma             - from system DMA controller 1
++ arb0            - from arb0
++ sd_emmc_b       - from SD eMMC b controller
++ usb1            - from USB2.0 controller 1
++ audio           - from Audio module
++ sd_emmc_c       - from SD eMMC c controller
++ spicc2          - from SPI controller 2
++ ethernet        - from Ethernet controller
+
+
+Examples:
+
+  + Show the total DDR bandwidth per seconds:
+
+    .. code-block:: bash
+
+       perf stat -a -e meson_ddr_bw/total_rw_bytes/ -I 1000 sleep 10
+
+
+  + Show individual DDR bandwidth from CPU and GPU respectively, as well as
+    sum of them:
+
+    .. code-block:: bash
+
+       perf stat -a -e meson_ddr_bw/chan_1_rw_bytes,arm=1/ -I 1000 sleep 10
+       perf stat -a -e meson_ddr_bw/chan_2_rw_bytes,gpu=1/ -I 1000 sleep 10
+       perf stat -a -e meson_ddr_bw/chan_3_rw_bytes,arm=1,gpu=1/ -I 1000 sleep 10
+

Documentation/devicetree/bindings/perf/amlogic,g12-ddr-pmu.yaml

+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/perf/amlogic,g12-ddr-pmu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Amlogic G12 DDR performance monitor
+
+maintainers:
+  - Jiucheng Xu <jiucheng.xu@amlogic.com>
+
+description: |
+  Amlogic G12 series SoC integrate DDR bandwidth monitor.
+  A timer is inside and can generate interrupt when timeout.
+  The bandwidth is counted in the timer ISR. Different platform
+  has different subset of event format attribute.
+
+properties:
+  compatible:
+    enum:
+      - amlogic,g12a-ddr-pmu
+      - amlogic,g12b-ddr-pmu
+      - amlogic,sm1-ddr-pmu
+
+  reg:
+    items:
+      - description: DMC bandwidth register space.
+      - description: DMC PLL register space.
+
+  interrupts:
+    items:
+      - description: The IRQ of the inside timer timeout.
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    pmu {
+        #address-cells=<2>;
+        #size-cells=<2>;
+
+        pmu@ff638000 {
+            compatible = "amlogic,g12a-ddr-pmu";
+            reg = <0x0 0xff638000 0x0 0x100>,
+                  <0x0 0xff638c00 0x0 0x100>;
+            interrupts = <GIC_SPI 52 IRQ_TYPE_EDGE_RISING>;
+        };
+    };

MAINTAINERS

@@ -1093,6 +1093,16 @@ S:	Maintained
 F:	Documentation/hid/amd-sfh*
 F:	drivers/hid/amd-sfh-hid/
 
+AMLOGIC DDR PMU DRIVER
+M:	Jiucheng Xu <jiucheng.xu@amlogic.com>
+L:	linux-amlogic@lists.infradead.org
+S:	Supported
+W:	http://www.amlogic.com
+F:	Documentation/admin-guide/perf/meson-ddr-pmu.rst
+F:	Documentation/devicetree/bindings/perf/amlogic,g12-ddr-pmu.yaml
+F:	drivers/perf/amlogic/
+F:	include/soc/amlogic/
+
 AMPHION VPU CODEC V4L2 DRIVER
 M:	Ming Qian <ming.qian@nxp.com>
 M:	Shijie Qin <shijie.qin@nxp.com>
@@ -9248,7 +9258,7 @@ F:	drivers/misc/hisi_hikey_usb.c
 
 HISILICON PMU DRIVER
 M:	Shaokun Zhang <zhangshaokun@hisilicon.com>
-M:	Qi Liu <liuqi115@huawei.com>
+M:	Jonathan Cameron <jonathan.cameron@huawei.com>
 S:	Supported
 W:	http://www.hisilicon.com
 F:	Documentation/admin-guide/perf/hisi-pcie-pmu.rst

arch/arm64/kernel/perf_event.c

@@ -1146,7 +1146,8 @@ static void __armv8pmu_probe_pmu(void *info)
 	dfr0 = read_sysreg(id_aa64dfr0_el1);
 	pmuver = cpuid_feature_extract_unsigned_field(dfr0,
 			ID_AA64DFR0_EL1_PMUVer_SHIFT);
-	if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF || pmuver == 0)
+	if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF ||
+	    pmuver == ID_AA64DFR0_EL1_PMUVer_NI)
 		return;
 
 	cpu_pmu->pmuver = pmuver;

drivers/perf/Kconfig

@@ -199,4 +199,8 @@ config MARVELL_CN10K_DDR_PMU
 	  Enable perf support for Marvell DDR Performance monitoring
 	  event on CN10K platform.
 
+source "drivers/perf/arm_cspmu/Kconfig"
+
+source "drivers/perf/amlogic/Kconfig"
+
 endmenu

drivers/perf/Makefile

@@ -21,3 +21,5 @@ obj-$(CONFIG_MARVELL_CN10K_TAD_PMU) += marvell_cn10k_tad_pmu.o
 obj-$(CONFIG_MARVELL_CN10K_DDR_PMU) += marvell_cn10k_ddr_pmu.o
 obj-$(CONFIG_APPLE_M1_CPU_PMU) += apple_m1_cpu_pmu.o
 obj-$(CONFIG_ALIBABA_UNCORE_DRW_PMU) += alibaba_uncore_drw_pmu.o
+obj-$(CONFIG_ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += arm_cspmu/
+obj-$(CONFIG_MESON_DDR_PMU) += amlogic/

drivers/perf/amlogic/Kconfig

+# SPDX-License-Identifier: GPL-2.0-only
+config MESON_DDR_PMU
+	tristate "Amlogic DDR Bandwidth Performance Monitor"
+	depends on ARCH_MESON || COMPILE_TEST
+	help
+          Provides support for the DDR performance monitor
+          in Amlogic SoCs, which can give information about
+          memory throughput and other related events. It
+          supports multiple channels to monitor the memory
+          bandwidth simultaneously.

drivers/perf/amlogic/Makefile

+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_MESON_DDR_PMU) += meson_ddr_pmu_g12.o
+
+meson_ddr_pmu_g12-y	:= meson_ddr_pmu_core.o meson_g12_ddr_pmu.o

drivers/perf/arm_cspmu/Kconfig

+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+
+config ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU
+	tristate "ARM Coresight Architecture PMU"
+	depends on ARM64 && ACPI
+	depends on ACPI_APMT || COMPILE_TEST
+	help
+	  Provides support for performance monitoring unit (PMU) devices
+	  based on ARM CoreSight PMU architecture. Note that this PMU
+	  architecture does not have relationship with the ARM CoreSight
+	  Self-Hosted Tracing.

drivers/perf/arm_cspmu/Makefile

+# Copyright (c) 2022, 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

drivers/perf/arm_cspmu/arm_cspmu.h

+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * ARM CoreSight Architecture PMU driver.
+ * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+ *
+ */
+
+#ifndef __ARM_CSPMU_H__
+#define __ARM_CSPMU_H__
+
+#include <linux/acpi.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>
+
+#define to_arm_cspmu(p) (container_of(p, struct arm_cspmu, pmu))
+
+#define ARM_CSPMU_EXT_ATTR(_name, _func, _config)			\
+	(&((struct dev_ext_attribute[]){				\
+		{							\
+			.attr = __ATTR(_name, 0444, _func, NULL),	\
+			.var = (void *)_config				\
+		}							\
+	})[0].attr.attr)
+
+#define ARM_CSPMU_FORMAT_ATTR(_name, _config)				\
+	ARM_CSPMU_EXT_ATTR(_name, arm_cspmu_sysfs_format_show, (char *)_config)
+
+#define ARM_CSPMU_EVENT_ATTR(_name, _config)				\
+	PMU_EVENT_ATTR_ID(_name, arm_cspmu_sysfs_event_show, _config)
+
+
+/* Default event id mask */
+#define ARM_CSPMU_EVENT_MASK	GENMASK_ULL(63, 0)
+
+/* Default filter value mask */
+#define ARM_CSPMU_FILTER_MASK	GENMASK_ULL(63, 0)
+
+/* Default event format */
+#define ARM_CSPMU_FORMAT_EVENT_ATTR	\
+	ARM_CSPMU_FORMAT_ATTR(event, "config:0-32")
+
+/* Default filter format */
+#define ARM_CSPMU_FORMAT_FILTER_ATTR	\
+	ARM_CSPMU_FORMAT_ATTR(filter, "config1:0-31")
+
+/*
+ * This is the default event number for cycle count, if supported, since the
+ * ARM Coresight PMU specification does not define a standard event code
+ * for cycle count.
+ */
+#define ARM_CSPMU_EVT_CYCLES_DEFAULT	(0x1ULL << 32)
+
+/*
+ * The ARM Coresight PMU supports up to 256 event counters.
+ * If the counters are larger-than 32-bits, then the PMU includes at
+ * most 128 counters.
+ */
+#define ARM_CSPMU_MAX_HW_CNTRS		256
+
+/* The cycle counter, if implemented, is located at counter[31]. */
+#define ARM_CSPMU_CYCLE_CNTR_IDX	31
+
+/* PMIIDR register field */
+#define ARM_CSPMU_PMIIDR_IMPLEMENTER	GENMASK(11, 0)
+#define ARM_CSPMU_PMIIDR_PRODUCTID	GENMASK(31, 20)
+
+struct arm_cspmu;
+
+/* This tracks the events assigned to each counter in the PMU. */
+struct arm_cspmu_hw_events {
+	/* The events that are active on the PMU for a given logical index. */
+	struct perf_event **events;
+
+	/*
+	 * Each bit indicates a logical counter is being used (or not) for an
+	 * event. If cycle counter is supported and there is a gap between
+	 * regular and cycle counter, the last logical counter is mapped to
+	 * cycle counter. Otherwise, logical and physical have 1-to-1 mapping.
+	 */
+	DECLARE_BITMAP(used_ctrs, ARM_CSPMU_MAX_HW_CNTRS);
+};
+
+/* Contains ops to query vendor/implementer specific attribute. */
+struct arm_cspmu_impl_ops {
+	/* Get event attributes */
+	struct attribute **(*get_event_attrs)(const struct arm_cspmu *cspmu);
+	/* Get format attributes */
+	struct attribute **(*get_format_attrs)(const struct arm_cspmu *cspmu);
+	/* Get string identifier */
+	const char *(*get_identifier)(const struct arm_cspmu *cspmu);
+	/* Get PMU name to register to core perf */
+	const char *(*get_name)(const struct arm_cspmu *cspmu);
+	/* Check if the event corresponds to cycle count event */
+	bool (*is_cycle_counter_event)(const struct perf_event *event);
+	/* Decode event type/id from configs */
+	u32 (*event_type)(const struct perf_event *event);
+	/* Decode filter value from configs */
+	u32 (*event_filter)(const struct perf_event *event);
+	/* Hide/show unsupported events */
+	umode_t (*event_attr_is_visible)(struct kobject *kobj,
+					 struct attribute *attr, int unused);
+};
+
+/* Vendor/implementer descriptor. */
+struct arm_cspmu_impl {
+	u32 pmiidr;
+	struct arm_cspmu_impl_ops ops;
+	void *ctx;
+};
+
+/* Coresight PMU descriptor. */
+struct arm_cspmu {
+	struct pmu pmu;
+	struct device *dev;
+	struct acpi_apmt_node *apmt_node;
+	const char *name;
+	const char *identifier;
+	void __iomem *base0;
+	void __iomem *base1;
+	int irq;
+	cpumask_t associated_cpus;
+	cpumask_t active_cpu;
+	struct hlist_node cpuhp_node;
+
+	u32 pmcfgr;
+	u32 num_logical_ctrs;
+	u32 num_set_clr_reg;
+	int cycle_counter_logical_idx;
+
+	struct arm_cspmu_hw_events hw_events;
+
+	struct arm_cspmu_impl impl;
+};
+
+/* Default function to show event attribute in sysfs. */
+ssize_t arm_cspmu_sysfs_event_show(struct device *dev,
+				   struct device_attribute *attr,
+				   char *buf);
+
+/* Default function to show format attribute in sysfs. */
+ssize_t arm_cspmu_sysfs_format_show(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf);
+
+#endif /* __ARM_CSPMU_H__ */

drivers/perf/arm_cspmu/nvidia_cspmu.h

+/* 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__ */

drivers/perf/arm_dmc620_pmu.c

@@ -725,6 +725,8 @@ static struct platform_driver dmc620_pmu_driver = {
 
 static int __init dmc620_pmu_init(void)
 {
+	int ret;
+
 	cpuhp_state_num = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
 				      DMC620_DRVNAME,
 				      NULL,
@@ -732,7 +734,11 @@ static int __init dmc620_pmu_init(void)
 	if (cpuhp_state_num < 0)
 		return cpuhp_state_num;
 
-	return platform_driver_register(&dmc620_pmu_driver);
+	ret = platform_driver_register(&dmc620_pmu_driver);
+	if (ret)
+		cpuhp_remove_multi_state(cpuhp_state_num);
+
+	return ret;
 }
 
 static void __exit dmc620_pmu_exit(void)

drivers/perf/arm_dsu_pmu.c

@@ -858,7 +858,11 @@ static int __init dsu_pmu_init(void)
 	if (ret < 0)
 		return ret;
 	dsu_pmu_cpuhp_state = ret;
-	return platform_driver_register(&dsu_pmu_driver);
+	ret = platform_driver_register(&dsu_pmu_driver);
+	if (ret)
+		cpuhp_remove_multi_state(dsu_pmu_cpuhp_state);
+
+	return ret;
 }
 
 static void __exit dsu_pmu_exit(void)

drivers/perf/arm_pmu.c

@@ -514,9 +514,6 @@ static int armpmu_event_init(struct perf_event *event)
 	if (has_branch_stack(event))
 		return -EOPNOTSUPP;
 
-	if (armpmu->map_event(event) == -ENOENT)
-		return -ENOENT;
-
 	return __hw_perf_event_init(event);
 }
 

drivers/perf/arm_smmuv3_pmu.c

@@ -959,6 +959,8 @@ static struct platform_driver smmu_pmu_driver = {
 
 static int __init arm_smmu_pmu_init(void)
 {
+	int ret;
+
 	cpuhp_state_num = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
 						  "perf/arm/pmcg:online",
 						  NULL,
@@ -966,7 +968,11 @@ static int __init arm_smmu_pmu_init(void)
 	if (cpuhp_state_num < 0)
 		return cpuhp_state_num;
 
-	return platform_driver_register(&smmu_pmu_driver);
+	ret = platform_driver_register(&smmu_pmu_driver);
+	if (ret)
+		cpuhp_remove_multi_state(cpuhp_state_num);
+
+	return ret;
 }
 module_init(arm_smmu_pmu_init);
 

drivers/perf/hisilicon/hisi_pcie_pmu.c

@@ -47,10 +47,14 @@
 #define HISI_PCIE_EVENT_M		GENMASK_ULL(15, 0)
 #define HISI_PCIE_THR_MODE_M		GENMASK_ULL(27, 27)
 #define HISI_PCIE_THR_M			GENMASK_ULL(31, 28)
+#define HISI_PCIE_LEN_M			GENMASK_ULL(35, 34)
 #define HISI_PCIE_TARGET_M		GENMASK_ULL(52, 36)
 #define HISI_PCIE_TRIG_MODE_M		GENMASK_ULL(53, 53)
 #define HISI_PCIE_TRIG_M		GENMASK_ULL(59, 56)
 
+/* Default config of TLP length mode, will count both TLP headers and payloads */
+#define HISI_PCIE_LEN_M_DEFAULT		3ULL
+
 #define HISI_PCIE_MAX_COUNTERS		8
 #define HISI_PCIE_REG_STEP		8
 #define HISI_PCIE_THR_MAX_VAL		10
@@ -91,6 +95,7 @@ HISI_PCIE_PMU_FILTER_ATTR(thr_len, config1, 3, 0);
 HISI_PCIE_PMU_FILTER_ATTR(thr_mode, config1, 4, 4);
 HISI_PCIE_PMU_FILTER_ATTR(trig_len, config1, 8, 5);
 HISI_PCIE_PMU_FILTER_ATTR(trig_mode, config1, 9, 9);
+HISI_PCIE_PMU_FILTER_ATTR(len_mode, config1, 11, 10);
 HISI_PCIE_PMU_FILTER_ATTR(port, config2, 15, 0);
 HISI_PCIE_PMU_FILTER_ATTR(bdf, config2, 31, 16);
 
@@ -215,8 +220,8 @@ static void hisi_pcie_pmu_config_filter(struct perf_event *event)
 {
 	struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
+	u64 port, trig_len, thr_len, len_mode;
 	u64 reg = HISI_PCIE_INIT_SET;
-	u64 port, trig_len, thr_len;
 
 	/* Config HISI_PCIE_EVENT_CTRL according to event. */
 	reg |= FIELD_PREP(HISI_PCIE_EVENT_M, hisi_pcie_get_real_event(event));
@@ -245,6 +250,12 @@ static void hisi_pcie_pmu_config_filter(struct perf_event *event)
 		reg |= HISI_PCIE_THR_EN;
 	}
 
+	len_mode = hisi_pcie_get_len_mode(event);
+	if (len_mode)
+		reg |= FIELD_PREP(HISI_PCIE_LEN_M, len_mode);
+	else
+		reg |= FIELD_PREP(HISI_PCIE_LEN_M, HISI_PCIE_LEN_M_DEFAULT);
+
 	hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EVENT_CTRL, hwc->idx, reg);
 }
 
@@ -693,10 +704,10 @@ static struct attribute *hisi_pcie_pmu_events_attr[] = {
 	HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_cnt, 0x10210),
 	HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_latency, 0x0011),
 	HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_cnt, 0x10011),
-	HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_flux, 0x1005),
-	HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_time, 0x11005),
-	HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_flux, 0x2004),
-	HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_time, 0x12004),
+	HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_flux, 0x0804),
+	HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_time, 0x10804),
+	HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_flux, 0x0405),
+	HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_time, 0x10405),
 	NULL
 };
 
@@ -711,6 +722,7 @@ static struct attribute *hisi_pcie_pmu_format_attr[] = {
 	HISI_PCIE_PMU_FORMAT_ATTR(thr_mode, "config1:4"),
 	HISI_PCIE_PMU_FORMAT_ATTR(trig_len, "config1:5-8"),
 	HISI_PCIE_PMU_FORMAT_ATTR(trig_mode, "config1:9"),
+	HISI_PCIE_PMU_FORMAT_ATTR(len_mode, "config1:10-11"),
 	HISI_PCIE_PMU_FORMAT_ATTR(port, "config2:0-15"),
 	HISI_PCIE_PMU_FORMAT_ATTR(bdf, "config2:16-31"),
 	NULL

drivers/perf/marvell_cn10k_tad_pmu.c

@@ -408,7 +408,11 @@ static int __init tad_pmu_init(void)
 	if (ret < 0)
 		return ret;
 	tad_pmu_cpuhp_state = ret;
-	return platform_driver_register(&tad_pmu_driver);
+	ret = platform_driver_register(&tad_pmu_driver);
+	if (ret)
+		cpuhp_remove_multi_state(tad_pmu_cpuhp_state);
+
+	return ret;
 }
 
 static void __exit tad_pmu_exit(void)

include/soc/amlogic/meson_ddr_pmu.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2022 Amlogic, Inc. All rights reserved.
+ */
+
+#ifndef __MESON_DDR_PMU_H__
+#define __MESON_DDR_PMU_H__
+
+#define MAX_CHANNEL_NUM		8
+
+enum {
+	ALL_CHAN_COUNTER_ID,
+	CHAN1_COUNTER_ID,
+	CHAN2_COUNTER_ID,
+	CHAN3_COUNTER_ID,
+	CHAN4_COUNTER_ID,
+	CHAN5_COUNTER_ID,
+	CHAN6_COUNTER_ID,
+	CHAN7_COUNTER_ID,
+	CHAN8_COUNTER_ID,
+	COUNTER_MAX_ID,
+};
+
+struct dmc_info;
+
+struct dmc_counter {
+	u64 all_cnt;	/* The count of all requests come in/out ddr controller */
+	union {
+		u64 all_req;
+		struct {
+			u64 all_idle_cnt;
+			u64 all_16bit_cnt;
+		};
+	};
+	u64 channel_cnt[MAX_CHANNEL_NUM]; /* To save a DMC bandwidth-monitor channel counter */
+};
+
+struct dmc_hw_info {
+	void (*enable)(struct dmc_info *info);
+	void (*disable)(struct dmc_info *info);
+	/* Bind an axi line to a bandwidth-monitor channel */
+	void (*set_axi_filter)(struct dmc_info *info, int axi_id, int chann);
+	int (*irq_handler)(struct dmc_info *info,
+			   struct dmc_counter *counter);
+	void (*get_counters)(struct dmc_info *info,
+			     struct dmc_counter *counter);
+
+	int dmc_nr;			/* The number of dmc controller */
+	int chann_nr;			/* The number of dmc bandwidth monitor channels */
+	struct attribute **fmt_attr;
+	const u64 capability[2];
+};
+
+struct dmc_info {
+	const struct dmc_hw_info *hw_info;
+
+	void __iomem *ddr_reg[4];
+	unsigned long timer_value;	/* Timer value in TIMER register */
+	void __iomem *pll_reg;
+	int irq_num;			/* irq vector number */
+};
+
+int meson_ddr_pmu_create(struct platform_device *pdev);
+int meson_ddr_pmu_remove(struct platform_device *pdev);
+
+#endif /* __MESON_DDR_PMU_H__ */