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

* for-next/perf: (30 commits)
  arm: perf: Fix ARCH=arm build with GCC
  MAINTAINERS: add maintainers for DesignWare PCIe PMU driver
  drivers/perf: add DesignWare PCIe PMU driver
  PCI: Move pci_clear_and_set_dword() helper to PCI header
  PCI: Add Alibaba Vendor ID to linux/pci_ids.h
  docs: perf: Add description for Synopsys DesignWare PCIe PMU driver
  Revert "perf/arm_dmc620: Remove duplicate format attribute #defines"
  Documentation: arm64: Document the PMU event counting threshold feature
  arm64: perf: Add support for event counting threshold
  arm: pmu: Move error message and -EOPNOTSUPP to individual PMUs
  KVM: selftests: aarch64: Update tools copy of arm_pmuv3.h
  perf/arm_dmc620: Remove duplicate format attribute #defines
  arm: pmu: Share user ABI format mechanism with SPE
  arm64: perf: Include threshold control fields in PMEVTYPER mask
  arm: perf: Convert remaining fields to use GENMASK
  arm: perf: Use GENMASK for PMMIR fields
  arm: perf/kvm: Use GENMASK for ARMV8_PMU_PMCR_N
  arm: perf: Remove inlines from arm_pmuv3.c
  drivers/perf: arm_dsu_pmu: Remove kerneldoc-style comment syntax
  drivers/perf: Remove usage of the deprecated ida_simple_xx() API
  ...

Documentation/admin-guide/perf/dwc_pcie_pmu.rst

+======================================================================
+Synopsys DesignWare Cores (DWC) PCIe Performance Monitoring Unit (PMU)
+======================================================================
+
+DesignWare Cores (DWC) PCIe PMU
+===============================
+
+The PMU is a PCIe configuration space register block provided by each PCIe Root
+Port in a Vendor-Specific Extended Capability named RAS D.E.S (Debug, Error
+injection, and Statistics).
+
+As the name indicates, the RAS DES capability supports system level
+debugging, AER error injection, and collection of statistics. To facilitate
+collection of statistics, Synopsys DesignWare Cores PCIe controller
+provides the following two features:
+
+- one 64-bit counter for Time Based Analysis (RX/TX data throughput and
+  time spent in each low-power LTSSM state) and
+- one 32-bit counter for Event Counting (error and non-error events for
+  a specified lane)
+
+Note: There is no interrupt for counter overflow.
+
+Time Based Analysis
+-------------------
+
+Using this feature you can obtain information regarding RX/TX data
+throughput and time spent in each low-power LTSSM state by the controller.
+The PMU measures data in two categories:
+
+- Group#0: Percentage of time the controller stays in LTSSM states.
+- Group#1: Amount of data processed (Units of 16 bytes).
+
+Lane Event counters
+-------------------
+
+Using this feature you can obtain Error and Non-Error information in
+specific lane by the controller. The PMU event is selected by all of:
+
+- Group i
+- Event j within the Group i
+- Lane k
+
+Some of the events only exist for specific configurations.
+
+DesignWare Cores (DWC) PCIe PMU Driver
+=======================================
+
+This driver adds PMU devices for each PCIe Root Port named based on the BDF of
+the Root Port. For example,
+
+    30:03.0 PCI bridge: Device 1ded:8000 (rev 01)
+
+the PMU device name for this Root Port is dwc_rootport_3018.
+
+The DWC PCIe PMU driver registers a perf PMU driver, which provides
+description of available events and configuration options in sysfs, see
+/sys/bus/event_source/devices/dwc_rootport_{bdf}.
+
+The "format" directory describes format of the config fields of the
+perf_event_attr structure. The "events" directory provides configuration
+templates for all documented events.  For example,
+"Rx_PCIe_TLP_Data_Payload" is an equivalent of "eventid=0x22,type=0x1".
+
+The "perf list" command shall list the available events from sysfs, e.g.::
+
+    $# perf list | grep dwc_rootport
+    <...>
+    dwc_rootport_3018/Rx_PCIe_TLP_Data_Payload/        [Kernel PMU event]
+    <...>
+    dwc_rootport_3018/rx_memory_read,lane=?/               [Kernel PMU event]
+
+Time Based Analysis Event Usage
+-------------------------------
+
+Example usage of counting PCIe RX TLP data payload (Units of bytes)::
+
+    $# perf stat -a -e dwc_rootport_3018/Rx_PCIe_TLP_Data_Payload/
+
+The average RX/TX bandwidth can be calculated using the following formula:
+
+    PCIe RX Bandwidth = Rx_PCIe_TLP_Data_Payload / Measure_Time_Window
+    PCIe TX Bandwidth = Tx_PCIe_TLP_Data_Payload / Measure_Time_Window
+
+Lane Event Usage
+-------------------------------
+
+Each lane has the same event set and to avoid generating a list of hundreds
+of events, the user need to specify the lane ID explicitly, e.g.::
+
+    $# perf stat -a -e dwc_rootport_3018/rx_memory_read,lane=4/
+
+The driver does not support sampling, therefore "perf record" will not
+work. Per-task (without "-a") perf sessions are not supported.

Documentation/admin-guide/perf/imx-ddr.rst

@@ -13,8 +13,8 @@ is one register for each counter. Counter 0 is special in that it always counts
 interrupt is raised. If any other counter overflows, it continues counting, and
 no interrupt is raised.
 
-The "format" directory describes format of the config (event ID) and config1
-(AXI filtering) fields of the perf_event_attr structure, see /sys/bus/event_source/
+The "format" directory describes format of the config (event ID) and config1/2
+(AXI filter setting) fields of the perf_event_attr structure, see /sys/bus/event_source/
 devices/imx8_ddr0/format/. The "events" directory describes the events types
 hardware supported that can be used with perf tool, see /sys/bus/event_source/
 devices/imx8_ddr0/events/. The "caps" directory describes filter features implemented
@@ -28,12 +28,11 @@ in DDR PMU, see /sys/bus/events_source/devices/imx8_ddr0/caps/.
 AXI filtering is only used by CSV modes 0x41 (axid-read) and 0x42 (axid-write)
 to count reading or writing matches filter setting. Filter setting is various
 from different DRAM controller implementations, which is distinguished by quirks
-in the driver. You also can dump info from userspace, filter in "caps" directory
-indicates whether PMU supports AXI ID filter or not; enhanced_filter indicates
-whether PMU supports enhanced AXI ID filter or not. Value 0 for un-supported, and
-value 1 for supported.
+in the driver. You also can dump info from userspace, "caps" directory show the
+type of AXI filter (filter, enhanced_filter and super_filter). Value 0 for
+un-supported, and value 1 for supported.
 
-* With DDR_CAP_AXI_ID_FILTER quirk(filter: 1, enhanced_filter: 0).
+* With DDR_CAP_AXI_ID_FILTER quirk(filter: 1, enhanced_filter: 0, super_filter: 0).
   Filter is defined with two configuration parts:
   --AXI_ID defines AxID matching value.
   --AXI_MASKING defines which bits of AxID are meaningful for the matching.
@@ -65,7 +64,37 @@ value 1 for supported.
 
         perf stat -a -e imx8_ddr0/axid-read,axi_id=0x12/ cmd, which will monitor ARID=0x12
 
-* With DDR_CAP_AXI_ID_FILTER_ENHANCED quirk(filter: 1, enhanced_filter: 1).
+* With DDR_CAP_AXI_ID_FILTER_ENHANCED quirk(filter: 1, enhanced_filter: 1, super_filter: 0).
   This is an extension to the DDR_CAP_AXI_ID_FILTER quirk which permits
   counting the number of bytes (as opposed to the number of bursts) from DDR
   read and write transactions concurrently with another set of data counters.
+
+* With DDR_CAP_AXI_ID_PORT_CHANNEL_FILTER quirk(filter: 0, enhanced_filter: 0, super_filter: 1).
+  There is a limitation in previous AXI filter, it cannot filter different IDs
+  at the same time as the filter is shared between counters. This quirk is the
+  extension of AXI ID filter. One improvement is that counter 1-3 has their own
+  filter, means that it supports concurrently filter various IDs. Another
+  improvement is that counter 1-3 supports AXI PORT and CHANNEL selection. Support
+  selecting address channel or data channel.
+
+  Filter is defined with 2 configuration registers per counter 1-3.
+  --Counter N MASK COMP register - including AXI_ID and AXI_MASKING.
+  --Counter N MUX CNTL register - including AXI CHANNEL and AXI PORT.
+
+      - 0: address channel
+      - 1: data channel
+
+  PMU in DDR subsystem, only one single port0 exists, so axi_port is reserved
+  which should be 0.
+
+  .. code-block:: bash
+
+      perf stat -a -e imx8_ddr0/axid-read,axi_mask=0xMMMM,axi_id=0xDDDD,axi_channel=0xH/ cmd
+      perf stat -a -e imx8_ddr0/axid-write,axi_mask=0xMMMM,axi_id=0xDDDD,axi_channel=0xH/ cmd
+
+  .. note::
+
+      axi_channel is inverted in userspace, and it will be reverted in driver
+      automatically. So that users do not need specify axi_channel if want to
+      monitor data channel from DDR transactions, since data channel is more
+      meaningful.

Documentation/admin-guide/perf/index.rst

@@ -19,6 +19,7 @@ Performance monitor support
    arm_dsu_pmu
    thunderx2-pmu
    alibaba_pmu
+   dwc_pcie_pmu
    nvidia-pmu
    meson-ddr-pmu
    cxl

Documentation/arch/arm64/perf.rst

@@ -164,3 +164,75 @@ and should be used to mask the upper bits as needed.
    https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/perf/arch/arm64/tests/user-events.c
 .. _tools/lib/perf/tests/test-evsel.c:
    https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/lib/perf/tests/test-evsel.c
+
+Event Counting Threshold
+==========================================
+
+Overview
+--------
+
+FEAT_PMUv3_TH (Armv8.8) permits a PMU counter to increment only on
+events whose count meets a specified threshold condition. For example if
+threshold_compare is set to 2 ('Greater than or equal'), and the
+threshold is set to 2, then the PMU counter will now only increment by
+when an event would have previously incremented the PMU counter by 2 or
+more on a single processor cycle.
+
+To increment by 1 after passing the threshold condition instead of the
+number of events on that cycle, add the 'threshold_count' option to the
+commandline.
+
+How-to
+------
+
+These are the parameters for controlling the feature:
+
+.. list-table::
+   :header-rows: 1
+
+   * - Parameter
+     - Description
+   * - threshold
+     - Value to threshold the event by. A value of 0 means that
+       thresholding is disabled and the other parameters have no effect.
+   * - threshold_compare
+     - | Comparison function to use, with the following values supported:
+       |
+       | 0: Not-equal
+       | 1: Equals
+       | 2: Greater-than-or-equal
+       | 3: Less-than
+   * - threshold_count
+     - If this is set, count by 1 after passing the threshold condition
+       instead of the value of the event on this cycle.
+
+The threshold, threshold_compare and threshold_count values can be
+provided per event, for example:
+
+.. code-block:: sh
+
+  perf stat -e stall_slot/threshold=2,threshold_compare=2/ \
+            -e dtlb_walk/threshold=10,threshold_compare=3,threshold_count/
+
+In this example the stall_slot event will count by 2 or more on every
+cycle where 2 or more stalls happen. And dtlb_walk will count by 1 on
+every cycle where the number of dtlb walks were less than 10.
+
+The maximum supported threshold value can be read from the caps of each
+PMU, for example:
+
+.. code-block:: sh
+
+  cat /sys/bus/event_source/devices/armv8_pmuv3/caps/threshold_max
+
+  0x000000ff
+
+If a value higher than this is given, then opening the event will result
+in an error. The highest possible maximum is 4095, as the config field
+for threshold is limited to 12 bits, and the Perf tool will refuse to
+parse higher values.
+
+If the PMU doesn't support FEAT_PMUv3_TH, then threshold_max will read
+0, and attempting to set a threshold value will also result in an error.
+threshold_max will also read as 0 on aarch32 guests, even if the host
+is running on hardware with the feature.

Documentation/devicetree/bindings/perf/fsl-imx-ddr.yaml

@@ -27,6 +27,9 @@ properties:
               - fsl,imx8mq-ddr-pmu
               - fsl,imx8mp-ddr-pmu
           - const: fsl,imx8m-ddr-pmu
+      - items:
+          - const: fsl,imx8dxl-ddr-pmu
+          - const: fsl,imx8-ddr-pmu
 
   reg:
     maxItems: 1

MAINTAINERS

@@ -21090,6 +21090,13 @@ L:	linux-mmc@vger.kernel.org
 S:	Maintained
 F:	drivers/mmc/host/dw_mmc*
 
+SYNOPSYS DESIGNWARE PCIE PMU DRIVER
+M:	Shuai Xue <xueshuai@linux.alibaba.com>
+M:	Jing Zhang <renyu.zj@linux.alibaba.com>
+S:	Supported
+F:	Documentation/admin-guide/perf/dwc_pcie_pmu.rst
+F:	drivers/perf/dwc_pcie_pmu.c
+
 SYNOPSYS HSDK RESET CONTROLLER DRIVER
 M:	Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
 S:	Supported

arch/arm/kernel/perf_event_v6.c

@@ -268,10 +268,8 @@ static inline void armv6pmu_write_counter(struct perf_event *event, u64 value)
 
 static void armv6pmu_enable_event(struct perf_event *event)
 {
-	unsigned long val, mask, evt, flags;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	unsigned long val, mask, evt;
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
@@ -294,12 +292,10 @@ static void armv6pmu_enable_event(struct perf_event *event)
 	 * Mask out the current event and set the counter to count the event
 	 * that we're interested in.
 	 */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~mask;
 	val |= evt;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static irqreturn_t
@@ -362,26 +358,20 @@ armv6pmu_handle_irq(struct arm_pmu *cpu_pmu)
 
 static void armv6pmu_start(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags, val;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+	unsigned long val;
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val |= ARMV6_PMCR_ENABLE;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void armv6pmu_stop(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags, val;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+	unsigned long val;
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~ARMV6_PMCR_ENABLE;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int
@@ -419,10 +409,8 @@ static void armv6pmu_clear_event_idx(struct pmu_hw_events *cpuc,
 
 static void armv6pmu_disable_event(struct perf_event *event)
 {
-	unsigned long val, mask, evt, flags;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	unsigned long val, mask, evt;
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
@@ -444,20 +432,16 @@ static void armv6pmu_disable_event(struct perf_event *event)
 	 * of ETM bus signal assertion cycles. The external reporting should
 	 * be disabled and so this should never increment.
 	 */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~mask;
 	val |= evt;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void armv6mpcore_pmu_disable_event(struct perf_event *event)
 {
-	unsigned long val, mask, flags, evt = 0;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	unsigned long val, mask, evt = 0;
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	if (ARMV6_CYCLE_COUNTER == idx) {
@@ -475,12 +459,10 @@ static void armv6mpcore_pmu_disable_event(struct perf_event *event)
 	 * Unlike UP ARMv6, we don't have a way of stopping the counters. We
 	 * simply disable the interrupt reporting.
 	 */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = armv6_pmcr_read();
 	val &= ~mask;
 	val |= evt;
 	armv6_pmcr_write(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int armv6_map_event(struct perf_event *event)

arch/arm/kernel/perf_event_v7.c

@@ -870,10 +870,8 @@ static void armv7_pmnc_dump_regs(struct arm_pmu *cpu_pmu)
 
 static void armv7pmu_enable_event(struct perf_event *event)
 {
-	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	if (!armv7_pmnc_counter_valid(cpu_pmu, idx)) {
@@ -886,7 +884,6 @@ static void armv7pmu_enable_event(struct perf_event *event)
 	 * Enable counter and interrupt, and set the counter to count
 	 * the event that we're interested in.
 	 */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/*
 	 * Disable counter
@@ -910,16 +907,12 @@ static void armv7pmu_enable_event(struct perf_event *event)
 	 * Enable counter
 	 */
 	armv7_pmnc_enable_counter(idx);
-
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void armv7pmu_disable_event(struct perf_event *event)
 {
-	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	if (!armv7_pmnc_counter_valid(cpu_pmu, idx)) {
@@ -931,7 +924,6 @@ static void armv7pmu_disable_event(struct perf_event *event)
 	/*
 	 * Disable counter and interrupt
 	 */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/*
 	 * Disable counter
@@ -942,8 +934,6 @@ static void armv7pmu_disable_event(struct perf_event *event)
 	 * Disable interrupt for this counter
 	 */
 	armv7_pmnc_disable_intens(idx);
-
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static irqreturn_t armv7pmu_handle_irq(struct arm_pmu *cpu_pmu)
@@ -1009,24 +999,14 @@ static irqreturn_t armv7pmu_handle_irq(struct arm_pmu *cpu_pmu)
 
 static void armv7pmu_start(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
-
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	/* Enable all counters */
 	armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void armv7pmu_stop(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
-
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	/* Disable all counters */
 	armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int armv7pmu_get_event_idx(struct pmu_hw_events *cpuc,
@@ -1072,8 +1052,10 @@ static int armv7pmu_set_event_filter(struct hw_perf_event *event,
 {
 	unsigned long config_base = 0;
 
-	if (attr->exclude_idle)
-		return -EPERM;
+	if (attr->exclude_idle) {
+		pr_debug("ARM performance counters do not support mode exclusion\n");
+		return -EOPNOTSUPP;
+	}
 	if (attr->exclude_user)
 		config_base |= ARMV7_EXCLUDE_USER;
 	if (attr->exclude_kernel)
@@ -1492,14 +1474,10 @@ static void krait_clearpmu(u32 config_base)
 
 static void krait_pmu_disable_event(struct perf_event *event)
 {
-	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	/* Disable counter and interrupt */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/* Disable counter */
 	armv7_pmnc_disable_counter(idx);
@@ -1512,23 +1490,17 @@ static void krait_pmu_disable_event(struct perf_event *event)
 
 	/* Disable interrupt for this counter */
 	armv7_pmnc_disable_intens(idx);
-
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void krait_pmu_enable_event(struct perf_event *event)
 {
-	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	/*
 	 * Enable counter and interrupt, and set the counter to count
 	 * the event that we're interested in.
 	 */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/* Disable counter */
 	armv7_pmnc_disable_counter(idx);
@@ -1548,8 +1520,6 @@ static void krait_pmu_enable_event(struct perf_event *event)
 
 	/* Enable counter */
 	armv7_pmnc_enable_counter(idx);
-
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void krait_pmu_reset(void *info)
@@ -1825,14 +1795,10 @@ static void scorpion_clearpmu(u32 config_base)
 
 static void scorpion_pmu_disable_event(struct perf_event *event)
 {
-	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	/* Disable counter and interrupt */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/* Disable counter */
 	armv7_pmnc_disable_counter(idx);
@@ -1845,23 +1811,17 @@ static void scorpion_pmu_disable_event(struct perf_event *event)
 
 	/* Disable interrupt for this counter */
 	armv7_pmnc_disable_intens(idx);
-
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void scorpion_pmu_enable_event(struct perf_event *event)
 {
-	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 
 	/*
 	 * Enable counter and interrupt, and set the counter to count
 	 * the event that we're interested in.
 	 */
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 
 	/* Disable counter */
 	armv7_pmnc_disable_counter(idx);
@@ -1881,8 +1841,6 @@ static void scorpion_pmu_enable_event(struct perf_event *event)
 
 	/* Enable counter */
 	armv7_pmnc_enable_counter(idx);
-
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void scorpion_pmu_reset(void *info)

arch/arm/kernel/perf_event_xscale.c

@@ -203,10 +203,8 @@ xscale1pmu_handle_irq(struct arm_pmu *cpu_pmu)
 
 static void xscale1pmu_enable_event(struct perf_event *event)
 {
-	unsigned long val, mask, evt, flags;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	unsigned long val, mask, evt;
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	switch (idx) {
@@ -229,20 +227,16 @@ static void xscale1pmu_enable_event(struct perf_event *event)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val &= ~mask;
 	val |= evt;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void xscale1pmu_disable_event(struct perf_event *event)
 {
-	unsigned long val, mask, evt, flags;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	unsigned long val, mask, evt;
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	switch (idx) {
@@ -263,12 +257,10 @@ static void xscale1pmu_disable_event(struct perf_event *event)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val &= ~mask;
 	val |= evt;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int
@@ -300,26 +292,20 @@ static void xscalepmu_clear_event_idx(struct pmu_hw_events *cpuc,
 
 static void xscale1pmu_start(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags, val;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+	unsigned long val;
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val |= XSCALE_PMU_ENABLE;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void xscale1pmu_stop(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags, val;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+	unsigned long val;
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale1pmu_read_pmnc();
 	val &= ~XSCALE_PMU_ENABLE;
 	xscale1pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static inline u64 xscale1pmu_read_counter(struct perf_event *event)
@@ -549,10 +535,8 @@ xscale2pmu_handle_irq(struct arm_pmu *cpu_pmu)
 
 static void xscale2pmu_enable_event(struct perf_event *event)
 {
-	unsigned long flags, ien, evtsel;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	unsigned long ien, evtsel;
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	ien = xscale2pmu_read_int_enable();
@@ -587,18 +571,14 @@ static void xscale2pmu_enable_event(struct perf_event *event)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	xscale2pmu_write_event_select(evtsel);
 	xscale2pmu_write_int_enable(ien);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void xscale2pmu_disable_event(struct perf_event *event)
 {
-	unsigned long flags, ien, evtsel, of_flags;
-	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	unsigned long ien, evtsel, of_flags;
 	struct hw_perf_event *hwc = &event->hw;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
 	int idx = hwc->idx;
 
 	ien = xscale2pmu_read_int_enable();
@@ -638,11 +618,9 @@ static void xscale2pmu_disable_event(struct perf_event *event)
 		return;
 	}
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	xscale2pmu_write_event_select(evtsel);
 	xscale2pmu_write_int_enable(ien);
 	xscale2pmu_write_overflow_flags(of_flags);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static int
@@ -663,26 +641,20 @@ xscale2pmu_get_event_idx(struct pmu_hw_events *cpuc,
 
 static void xscale2pmu_start(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags, val;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+	unsigned long val;
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64;
 	val |= XSCALE_PMU_ENABLE;
 	xscale2pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static void xscale2pmu_stop(struct arm_pmu *cpu_pmu)
 {
-	unsigned long flags, val;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+	unsigned long val;
 
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
 	val = xscale2pmu_read_pmnc();
 	val &= ~XSCALE_PMU_ENABLE;
 	xscale2pmu_write_pmnc(val);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
 static inline u64 xscale2pmu_read_counter(struct perf_event *event)

arch/arm64/kvm/pmu-emul.c

@@ -267,9 +267,8 @@ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
 {
-	u64 val = kvm_vcpu_read_pmcr(vcpu) >> ARMV8_PMU_PMCR_N_SHIFT;
+	u64 val = FIELD_GET(ARMV8_PMU_PMCR_N, kvm_vcpu_read_pmcr(vcpu));
 
-	val &= ARMV8_PMU_PMCR_N_MASK;
 	if (val == 0)
 		return BIT(ARMV8_PMU_CYCLE_IDX);
 	else
@@ -1136,8 +1135,7 @@ u8 kvm_arm_pmu_get_pmuver_limit(void)
  */
 u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
 {
-	u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0) &
-			~(ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
+	u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0);
 
-	return pmcr | ((u64)vcpu->kvm->arch.pmcr_n << ARMV8_PMU_PMCR_N_SHIFT);
+	return u64_replace_bits(pmcr, vcpu->kvm->arch.pmcr_n, ARMV8_PMU_PMCR_N);
 }

arch/arm64/kvm/sys_regs.c

@@ -877,7 +877,7 @@ static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx)
 	u64 pmcr, val;
 
 	pmcr = kvm_vcpu_read_pmcr(vcpu);
-	val = (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
+	val = FIELD_GET(ARMV8_PMU_PMCR_N, pmcr);
 	if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX) {
 		kvm_inject_undefined(vcpu);
 		return false;
@@ -1143,7 +1143,7 @@ static int get_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 		    u64 val)
 {
-	u8 new_n = (val >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
+	u8 new_n = FIELD_GET(ARMV8_PMU_PMCR_N, val);
 	struct kvm *kvm = vcpu->kvm;
 
 	mutex_lock(&kvm->arch.config_lock);

drivers/infiniband/hw/erdma/erdma_hw.h

@@ -11,8 +11,6 @@
 #include <linux/types.h>
 
 /* PCIe device related definition. */
-#define PCI_VENDOR_ID_ALIBABA 0x1ded
-
 #define ERDMA_PCI_WIDTH 64
 #define ERDMA_FUNC_BAR 0
 #define ERDMA_MISX_BAR 2

drivers/pci/access.c

@@ -598,3 +598,15 @@ int pci_write_config_dword(const struct pci_dev *dev, int where,
 	return pci_bus_write_config_dword(dev->bus, dev->devfn, where, val);
 }
 EXPORT_SYMBOL(pci_write_config_dword);
+
+void pci_clear_and_set_config_dword(const struct pci_dev *dev, int pos,
+				    u32 clear, u32 set)
+{
+	u32 val;
+
+	pci_read_config_dword(dev, pos, &val);
+	val &= ~clear;
+	val |= set;
+	pci_write_config_dword(dev, pos, val);
+}
+EXPORT_SYMBOL(pci_clear_and_set_config_dword);

drivers/pci/pcie/aspm.c

@@ -426,17 +426,6 @@ static void pcie_aspm_check_latency(struct pci_dev *endpoint)
 	}
 }
 
-static void pci_clear_and_set_dword(struct pci_dev *pdev, int pos,
-				    u32 clear, u32 set)
-{
-	u32 val;
-
-	pci_read_config_dword(pdev, pos, &val);
-	val &= ~clear;
-	val |= set;
-	pci_write_config_dword(pdev, pos, val);
-}
-
 /* Calculate L1.2 PM substate timing parameters */
 static void aspm_calc_l12_info(struct pcie_link_state *link,
 				u32 parent_l1ss_cap, u32 child_l1ss_cap)
@@ -501,10 +490,12 @@ static void aspm_calc_l12_info(struct pcie_link_state *link,
 	cl1_2_enables = cctl1 & PCI_L1SS_CTL1_L1_2_MASK;
 
 	if (pl1_2_enables || cl1_2_enables) {
-		pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-					PCI_L1SS_CTL1_L1_2_MASK, 0);
-		pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-					PCI_L1SS_CTL1_L1_2_MASK, 0);
+		pci_clear_and_set_config_dword(child,
+					       child->l1ss + PCI_L1SS_CTL1,
+					       PCI_L1SS_CTL1_L1_2_MASK, 0);
+		pci_clear_and_set_config_dword(parent,
+					       parent->l1ss + PCI_L1SS_CTL1,
+					       PCI_L1SS_CTL1_L1_2_MASK, 0);
 	}
 
 	/* Program T_POWER_ON times in both ports */
@@ -512,22 +503,26 @@ static void aspm_calc_l12_info(struct pcie_link_state *link,
 	pci_write_config_dword(child, child->l1ss + PCI_L1SS_CTL2, ctl2);
 
 	/* Program Common_Mode_Restore_Time in upstream device */
-	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_CM_RESTORE_TIME, ctl1);
+	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_CM_RESTORE_TIME, ctl1);
 
 	/* Program LTR_L1.2_THRESHOLD time in both ports */
-	pci_clear_and_set_dword(parent,	parent->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
-				PCI_L1SS_CTL1_LTR_L12_TH_SCALE, ctl1);
-	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
-				PCI_L1SS_CTL1_LTR_L12_TH_SCALE, ctl1);
+	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
+				       PCI_L1SS_CTL1_LTR_L12_TH_SCALE,
+				       ctl1);
+	pci_clear_and_set_config_dword(child, child->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
+				       PCI_L1SS_CTL1_LTR_L12_TH_SCALE,
+				       ctl1);
 
 	if (pl1_2_enables || cl1_2_enables) {
-		pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1, 0,
-					pl1_2_enables);
-		pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1, 0,
-					cl1_2_enables);
+		pci_clear_and_set_config_dword(parent,
+					       parent->l1ss + PCI_L1SS_CTL1, 0,
+					       pl1_2_enables);
+		pci_clear_and_set_config_dword(child,
+					       child->l1ss + PCI_L1SS_CTL1, 0,
+					       cl1_2_enables);
 	}
 }
 
@@ -687,10 +682,10 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 	 */
 
 	/* Disable all L1 substates */
-	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_L1SS_MASK, 0);
-	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_L1SS_MASK, 0);
+	pci_clear_and_set_config_dword(child, child->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_L1SS_MASK, 0);
+	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_L1SS_MASK, 0);
 	/*
 	 * If needed, disable L1, and it gets enabled later
 	 * in pcie_config_aspm_link().
@@ -713,10 +708,10 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 		val |= PCI_L1SS_CTL1_PCIPM_L1_2;
 
 	/* Enable what we need to enable */
-	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_L1SS_MASK, val);
-	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_L1SS_MASK, val);
+	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_L1SS_MASK, val);
+	pci_clear_and_set_config_dword(child, child->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_L1SS_MASK, val);
 }
 
 static void pcie_config_aspm_dev(struct pci_dev *pdev, u32 val)

drivers/perf/Kconfig

@@ -217,6 +217,13 @@ config MARVELL_CN10K_DDR_PMU
 	  Enable perf support for Marvell DDR Performance monitoring
 	  event on CN10K platform.
 
+config DWC_PCIE_PMU
+	tristate "Synopsys DesignWare PCIe PMU"
+	depends on PCI
+	help
+	  Enable perf support for Synopsys DesignWare PCIe PMU Performance
+	  monitoring event on platform including the Alibaba Yitian 710.
+
 source "drivers/perf/arm_cspmu/Kconfig"
 
 source "drivers/perf/amlogic/Kconfig"

drivers/perf/Makefile

@@ -23,6 +23,7 @@ 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-$(CONFIG_DWC_PCIE_PMU) += dwc_pcie_pmu.o
 obj-$(CONFIG_ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += arm_cspmu/
 obj-$(CONFIG_MESON_DDR_PMU) += amlogic/
 obj-$(CONFIG_CXL_PMU) += cxl_pmu.o

drivers/perf/apple_m1_cpu_pmu.c

@@ -524,8 +524,10 @@ static int m1_pmu_set_event_filter(struct hw_perf_event *event,
 {
 	unsigned long config_base = 0;
 
-	if (!attr->exclude_guest)
-		return -EINVAL;
+	if (!attr->exclude_guest) {
+		pr_debug("ARM performance counters do not support mode exclusion\n");
+		return -EOPNOTSUPP;
+	}
 	if (!attr->exclude_kernel)
 		config_base |= M1_PMU_CFG_COUNT_KERNEL;
 	if (!attr->exclude_user)

drivers/perf/arm-cmn.c

@@ -811,7 +811,7 @@ static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj,
 #define CMN_EVENT_HNF_OCC(_model, _name, _event)			\
 	CMN_EVENT_HN_OCC(_model, hnf_##_name, CMN_TYPE_HNF, _event)
 #define CMN_EVENT_HNF_CLS(_model, _name, _event)			\
-	CMN_EVENT_HN_CLS(_model, hnf_##_name, CMN_TYPE_HNS, _event)
+	CMN_EVENT_HN_CLS(_model, hnf_##_name, CMN_TYPE_HNF, _event)
 #define CMN_EVENT_HNF_SNT(_model, _name, _event)			\
 	CMN_EVENT_HN_SNT(_model, hnf_##_name, CMN_TYPE_HNF, _event)
 

drivers/perf/arm_dsu_pmu.c

@@ -371,7 +371,7 @@ static inline u32 dsu_pmu_get_reset_overflow(void)
 	return __dsu_pmu_get_reset_overflow();
 }
 
-/**
+/*
  * dsu_pmu_set_event_period: Set the period for the counter.
  *
  * All DSU PMU event counters, except the cycle counter are 32bit
@@ -602,7 +602,7 @@ static struct dsu_pmu *dsu_pmu_alloc(struct platform_device *pdev)
 	return dsu_pmu;
 }
 
-/**
+/*
  * dsu_pmu_dt_get_cpus: Get the list of CPUs in the cluster
  * from device tree.
  */
@@ -632,7 +632,7 @@ static int dsu_pmu_dt_get_cpus(struct device *dev, cpumask_t *mask)
 	return 0;
 }
 
-/**
+/*
  * dsu_pmu_acpi_get_cpus: Get the list of CPUs in the cluster
  * from ACPI.
  */

drivers/perf/arm_pmu.c

@@ -445,7 +445,7 @@ __hw_perf_event_init(struct perf_event *event)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
-	int mapping;
+	int mapping, ret;
 
 	hwc->flags = 0;
 	mapping = armpmu->map_event(event);
@@ -470,11 +470,10 @@ __hw_perf_event_init(struct perf_event *event)
 	/*
 	 * Check whether we need to exclude the counter from certain modes.
 	 */
-	if (armpmu->set_event_filter &&
-	    armpmu->set_event_filter(hwc, &event->attr)) {
-		pr_debug("ARM performance counters do not support "
-			 "mode exclusion\n");
-		return -EOPNOTSUPP;
+	if (armpmu->set_event_filter) {
+		ret = armpmu->set_event_filter(hwc, &event->attr);
+		if (ret)
+			return ret;
 	}
 
 	/*
@@ -893,7 +892,6 @@ struct arm_pmu *armpmu_alloc(void)
 		struct pmu_hw_events *events;
 
 		events = per_cpu_ptr(pmu->hw_events, cpu);
-		raw_spin_lock_init(&events->pmu_lock);
 		events->percpu_pmu = pmu;
 	}
 

drivers/perf/arm_spe_pmu.c

@@ -206,28 +206,6 @@ static const struct attribute_group arm_spe_pmu_cap_group = {
 #define ATTR_CFG_FLD_inv_event_filter_LO	0
 #define ATTR_CFG_FLD_inv_event_filter_HI	63
 
-/* Why does everything I do descend into this? */
-#define __GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\
-	(lo) == (hi) ? #cfg ":" #lo "\n" : #cfg ":" #lo "-" #hi
-
-#define _GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\
-	__GEN_PMU_FORMAT_ATTR(cfg, lo, hi)
-
-#define GEN_PMU_FORMAT_ATTR(name)					\
-	PMU_FORMAT_ATTR(name,						\
-	_GEN_PMU_FORMAT_ATTR(ATTR_CFG_FLD_##name##_CFG,			\
-			     ATTR_CFG_FLD_##name##_LO,			\
-			     ATTR_CFG_FLD_##name##_HI))
-
-#define _ATTR_CFG_GET_FLD(attr, cfg, lo, hi)				\
-	((((attr)->cfg) >> lo) & GENMASK(hi - lo, 0))
-
-#define ATTR_CFG_GET_FLD(attr, name)					\
-	_ATTR_CFG_GET_FLD(attr,						\
-			  ATTR_CFG_FLD_##name##_CFG,			\
-			  ATTR_CFG_FLD_##name##_LO,			\
-			  ATTR_CFG_FLD_##name##_HI)
-
 GEN_PMU_FORMAT_ATTR(ts_enable);
 GEN_PMU_FORMAT_ATTR(pa_enable);
 GEN_PMU_FORMAT_ATTR(pct_enable);

drivers/perf/fsl_imx8_ddr_perf.c

@@ -19,6 +19,8 @@
 #define COUNTER_READ		0x20
 
 #define COUNTER_DPCR1		0x30
+#define COUNTER_MUX_CNTL	0x50
+#define COUNTER_MASK_COMP	0x54
 
 #define CNTL_OVER		0x1
 #define CNTL_CLEAR		0x2
@@ -32,6 +34,13 @@
 #define CNTL_CSV_SHIFT		24
 #define CNTL_CSV_MASK		(0xFFU << CNTL_CSV_SHIFT)
 
+#define READ_PORT_SHIFT		0
+#define READ_PORT_MASK		(0x7 << READ_PORT_SHIFT)
+#define READ_CHANNEL_REVERT	0x00000008	/* bit 3 for read channel select */
+#define WRITE_PORT_SHIFT	8
+#define WRITE_PORT_MASK		(0x7 << WRITE_PORT_SHIFT)
+#define WRITE_CHANNEL_REVERT	0x00000800	/* bit 11 for write channel select */
+
 #define EVENT_CYCLES_ID		0
 #define EVENT_CYCLES_COUNTER	0
 #define NUM_COUNTERS		4
@@ -50,6 +59,7 @@ static DEFINE_IDA(ddr_ida);
 /* DDR Perf hardware feature */
 #define DDR_CAP_AXI_ID_FILTER			0x1     /* support AXI ID filter */
 #define DDR_CAP_AXI_ID_FILTER_ENHANCED		0x3     /* support enhanced AXI ID filter */
+#define DDR_CAP_AXI_ID_PORT_CHANNEL_FILTER	0x4	/* support AXI ID PORT CHANNEL filter */
 
 struct fsl_ddr_devtype_data {
 	unsigned int quirks;    /* quirks needed for different DDR Perf core */
@@ -82,6 +92,11 @@ static const struct fsl_ddr_devtype_data imx8mp_devtype_data = {
 	.identifier = "i.MX8MP",
 };
 
+static const struct fsl_ddr_devtype_data imx8dxl_devtype_data = {
+	.quirks = DDR_CAP_AXI_ID_PORT_CHANNEL_FILTER,
+	.identifier = "i.MX8DXL",
+};
+
 static const struct of_device_id imx_ddr_pmu_dt_ids[] = {
 	{ .compatible = "fsl,imx8-ddr-pmu", .data = &imx8_devtype_data},
 	{ .compatible = "fsl,imx8m-ddr-pmu", .data = &imx8m_devtype_data},
@@ -89,6 +104,7 @@ static const struct of_device_id imx_ddr_pmu_dt_ids[] = {
 	{ .compatible = "fsl,imx8mm-ddr-pmu", .data = &imx8mm_devtype_data},
 	{ .compatible = "fsl,imx8mn-ddr-pmu", .data = &imx8mn_devtype_data},
 	{ .compatible = "fsl,imx8mp-ddr-pmu", .data = &imx8mp_devtype_data},
+	{ .compatible = "fsl,imx8dxl-ddr-pmu", .data = &imx8dxl_devtype_data},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, imx_ddr_pmu_dt_ids);
@@ -144,6 +160,7 @@ static const struct attribute_group ddr_perf_identifier_attr_group = {
 enum ddr_perf_filter_capabilities {
 	PERF_CAP_AXI_ID_FILTER = 0,
 	PERF_CAP_AXI_ID_FILTER_ENHANCED,
+	PERF_CAP_AXI_ID_PORT_CHANNEL_FILTER,
 	PERF_CAP_AXI_ID_FEAT_MAX,
 };
 
@@ -157,6 +174,8 @@ static u32 ddr_perf_filter_cap_get(struct ddr_pmu *pmu, int cap)
 	case PERF_CAP_AXI_ID_FILTER_ENHANCED:
 		quirks &= DDR_CAP_AXI_ID_FILTER_ENHANCED;
 		return quirks == DDR_CAP_AXI_ID_FILTER_ENHANCED;
+	case PERF_CAP_AXI_ID_PORT_CHANNEL_FILTER:
+		return !!(quirks & DDR_CAP_AXI_ID_PORT_CHANNEL_FILTER);
 	default:
 		WARN(1, "unknown filter cap %d\n", cap);
 	}
@@ -187,6 +206,7 @@ static ssize_t ddr_perf_filter_cap_show(struct device *dev,
 static struct attribute *ddr_perf_filter_cap_attr[] = {
 	PERF_FILTER_EXT_ATTR_ENTRY(filter, PERF_CAP_AXI_ID_FILTER),
 	PERF_FILTER_EXT_ATTR_ENTRY(enhanced_filter, PERF_CAP_AXI_ID_FILTER_ENHANCED),
+	PERF_FILTER_EXT_ATTR_ENTRY(super_filter, PERF_CAP_AXI_ID_PORT_CHANNEL_FILTER),
 	NULL,
 };
 
@@ -272,11 +292,15 @@ static const struct attribute_group ddr_perf_events_attr_group = {
 PMU_FORMAT_ATTR(event, "config:0-7");
 PMU_FORMAT_ATTR(axi_id, "config1:0-15");
 PMU_FORMAT_ATTR(axi_mask, "config1:16-31");
+PMU_FORMAT_ATTR(axi_port, "config2:0-2");
+PMU_FORMAT_ATTR(axi_channel, "config2:3-3");
 
 static struct attribute *ddr_perf_format_attrs[] = {
 	&format_attr_event.attr,
 	&format_attr_axi_id.attr,
 	&format_attr_axi_mask.attr,
+	&format_attr_axi_port.attr,
+	&format_attr_axi_channel.attr,
 	NULL,
 };
 
@@ -530,6 +554,7 @@ static int ddr_perf_event_add(struct perf_event *event, int flags)
 	int counter;
 	int cfg = event->attr.config;
 	int cfg1 = event->attr.config1;
+	int cfg2 = event->attr.config2;
 
 	if (pmu->devtype_data->quirks & DDR_CAP_AXI_ID_FILTER) {
 		int i;
@@ -553,6 +578,26 @@ static int ddr_perf_event_add(struct perf_event *event, int flags)
 		return -EOPNOTSUPP;
 	}
 
+	if (pmu->devtype_data->quirks & DDR_CAP_AXI_ID_PORT_CHANNEL_FILTER) {
+		if (ddr_perf_is_filtered(event)) {
+			/* revert axi id masking(axi_mask) value */
+			cfg1 ^= AXI_MASKING_REVERT;
+			writel(cfg1, pmu->base + COUNTER_MASK_COMP + ((counter - 1) << 4));
+
+			if (cfg == 0x41) {
+				/* revert axi read channel(axi_channel) value */
+				cfg2 ^= READ_CHANNEL_REVERT;
+				cfg2 |= FIELD_PREP(READ_PORT_MASK, cfg2);
+			} else {
+				/* revert axi write channel(axi_channel) value */
+				cfg2 ^= WRITE_CHANNEL_REVERT;
+				cfg2 |= FIELD_PREP(WRITE_PORT_MASK, cfg2);
+			}
+
+			writel(cfg2, pmu->base + COUNTER_MUX_CNTL + ((counter - 1) << 4));
+		}
+	}
+
 	pmu->events[counter] = event;
 	hwc->idx = counter;
 

drivers/perf/fsl_imx9_ddr_perf.c

@@ -617,7 +617,7 @@ static int ddr_perf_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, pmu);
 
-	pmu->id = ida_simple_get(&ddr_ida, 0, 0, GFP_KERNEL);
+	pmu->id = ida_alloc(&ddr_ida, GFP_KERNEL);
 	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, DDR_PERF_DEV_NAME "%d", pmu->id);
 	if (!name) {
 		ret = -ENOMEM;
@@ -674,7 +674,7 @@ static int ddr_perf_probe(struct platform_device *pdev)
 	cpuhp_remove_multi_state(pmu->cpuhp_state);
 cpuhp_state_err:
 format_string_err:
-	ida_simple_remove(&ddr_ida, pmu->id);
+	ida_free(&ddr_ida, pmu->id);
 	dev_warn(&pdev->dev, "i.MX9 DDR Perf PMU failed (%d), disabled\n", ret);
 	return ret;
 }
@@ -688,7 +688,7 @@ static int ddr_perf_remove(struct platform_device *pdev)
 
 	perf_pmu_unregister(&pmu->pmu);
 
-	ida_simple_remove(&ddr_ida, pmu->id);
+	ida_free(&ddr_ida, pmu->id);
 
 	return 0;
 }

drivers/perf/hisilicon/hisi_uncore_uc_pmu.c

@@ -383,8 +383,8 @@ static struct attribute *hisi_uc_pmu_events_attr[] = {
 	HISI_PMU_EVENT_ATTR(cpu_rd,		0x10),
 	HISI_PMU_EVENT_ATTR(cpu_rd64,		0x17),
 	HISI_PMU_EVENT_ATTR(cpu_rs64,		0x19),
-	HISI_PMU_EVENT_ATTR(cpu_mru,		0x1a),
-	HISI_PMU_EVENT_ATTR(cycles,		0x9c),
+	HISI_PMU_EVENT_ATTR(cpu_mru,		0x1c),
+	HISI_PMU_EVENT_ATTR(cycles,		0x95),
 	HISI_PMU_EVENT_ATTR(spipe_hit,		0xb3),
 	HISI_PMU_EVENT_ATTR(hpipe_hit,		0xdb),
 	HISI_PMU_EVENT_ATTR(cring_rxdat_cnt,	0xfa),

include/linux/pci.h

@@ -1239,6 +1239,8 @@ int pci_read_config_dword(const struct pci_dev *dev, int where, u32 *val);
 int pci_write_config_byte(const struct pci_dev *dev, int where, u8 val);
 int pci_write_config_word(const struct pci_dev *dev, int where, u16 val);
 int pci_write_config_dword(const struct pci_dev *dev, int where, u32 val);
+void pci_clear_and_set_config_dword(const struct pci_dev *dev, int pos,
+				    u32 clear, u32 set);
 
 int pcie_capability_read_word(struct pci_dev *dev, int pos, u16 *val);
 int pcie_capability_read_dword(struct pci_dev *dev, int pos, u32 *val);

include/linux/pci_ids.h

@@ -2605,6 +2605,8 @@
 #define PCI_VENDOR_ID_TEKRAM		0x1de1
 #define PCI_DEVICE_ID_TEKRAM_DC290	0xdc29
 
+#define PCI_VENDOR_ID_ALIBABA		0x1ded
+
 #define PCI_VENDOR_ID_TEHUTI		0x1fc9
 #define PCI_DEVICE_ID_TEHUTI_3009	0x3009
 #define PCI_DEVICE_ID_TEHUTI_3010	0x3010

include/linux/perf/arm_pmu.h

@@ -59,12 +59,6 @@ struct pmu_hw_events {
 	 */
 	DECLARE_BITMAP(used_mask, ARMPMU_MAX_HWEVENTS);
 
-	/*
-	 * Hardware lock to serialize accesses to PMU registers. Needed for the
-	 * read/modify/write sequences.
-	 */
-	raw_spinlock_t		pmu_lock;
-
 	/*
 	 * When using percpu IRQs, we need a percpu dev_id. Place it here as we
 	 * already have to allocate this struct per cpu.
@@ -189,4 +183,26 @@ void armpmu_free_irq(int irq, int cpu);
 #define ARMV8_SPE_PDEV_NAME "arm,spe-v1"
 #define ARMV8_TRBE_PDEV_NAME "arm,trbe"
 
+/* Why does everything I do descend into this? */
+#define __GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\
+	(lo) == (hi) ? #cfg ":" #lo "\n" : #cfg ":" #lo "-" #hi
+
+#define _GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\
+	__GEN_PMU_FORMAT_ATTR(cfg, lo, hi)
+
+#define GEN_PMU_FORMAT_ATTR(name)					\
+	PMU_FORMAT_ATTR(name,						\
+	_GEN_PMU_FORMAT_ATTR(ATTR_CFG_FLD_##name##_CFG,			\
+			     ATTR_CFG_FLD_##name##_LO,			\
+			     ATTR_CFG_FLD_##name##_HI))
+
+#define _ATTR_CFG_GET_FLD(attr, cfg, lo, hi)				\
+	((((attr)->cfg) >> lo) & GENMASK_ULL(hi - lo, 0))
+
+#define ATTR_CFG_GET_FLD(attr, name)					\
+	_ATTR_CFG_GET_FLD(attr,						\
+			  ATTR_CFG_FLD_##name##_CFG,			\
+			  ATTR_CFG_FLD_##name##_LO,			\
+			  ATTR_CFG_FLD_##name##_HI)
+
 #endif /* __ARM_PMU_H__ */

include/linux/perf/arm_pmuv3.h

@@ -215,21 +215,27 @@
 #define ARMV8_PMU_PMCR_DP	(1 << 5) /* Disable CCNT if non-invasive debug*/
 #define ARMV8_PMU_PMCR_LC	(1 << 6) /* Overflow on 64 bit cycle counter */
 #define ARMV8_PMU_PMCR_LP	(1 << 7) /* Long event counter enable */
-#define ARMV8_PMU_PMCR_N_SHIFT	11  /* Number of counters supported */
-#define ARMV8_PMU_PMCR_N_MASK	0x1f
-#define ARMV8_PMU_PMCR_MASK	0xff    /* Mask for writable bits */
+#define ARMV8_PMU_PMCR_N	GENMASK(15, 11) /* Number of counters supported */
+/* Mask for writable bits */
+#define ARMV8_PMU_PMCR_MASK	(ARMV8_PMU_PMCR_E | ARMV8_PMU_PMCR_P | \
+				 ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_D | \
+				 ARMV8_PMU_PMCR_X | ARMV8_PMU_PMCR_DP | \
+				 ARMV8_PMU_PMCR_LC | ARMV8_PMU_PMCR_LP)
 
 /*
  * PMOVSR: counters overflow flag status reg
  */
-#define ARMV8_PMU_OVSR_MASK		0xffffffff	/* Mask for writable bits */
-#define ARMV8_PMU_OVERFLOWED_MASK	ARMV8_PMU_OVSR_MASK
+#define ARMV8_PMU_OVSR_P		GENMASK(30, 0)
+#define ARMV8_PMU_OVSR_C		BIT(31)
+/* Mask for writable bits is both P and C fields */
+#define ARMV8_PMU_OVERFLOWED_MASK	(ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C)
 
 /*
  * PMXEVTYPER: Event selection reg
  */
-#define ARMV8_PMU_EVTYPE_MASK	0xc800ffff	/* Mask for writable bits */
-#define ARMV8_PMU_EVTYPE_EVENT	0xffff		/* Mask for EVENT bits */
+#define ARMV8_PMU_EVTYPE_EVENT	GENMASK(15, 0)	/* Mask for EVENT bits */
+#define ARMV8_PMU_EVTYPE_TH	GENMASK_ULL(43, 32) /* arm64 only */
+#define ARMV8_PMU_EVTYPE_TC	GENMASK_ULL(63, 61) /* arm64 only */
 
 /*
  * Event filters for PMUv3
@@ -244,19 +250,19 @@
 /*
  * PMUSERENR: user enable reg
  */
-#define ARMV8_PMU_USERENR_MASK	0xf		/* Mask for writable bits */
 #define ARMV8_PMU_USERENR_EN	(1 << 0) /* PMU regs can be accessed at EL0 */
 #define ARMV8_PMU_USERENR_SW	(1 << 1) /* PMSWINC can be written at EL0 */
 #define ARMV8_PMU_USERENR_CR	(1 << 2) /* Cycle counter can be read at EL0 */
 #define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
+/* Mask for writable bits */
+#define ARMV8_PMU_USERENR_MASK	(ARMV8_PMU_USERENR_EN | ARMV8_PMU_USERENR_SW | \
+				 ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_ER)
 
 /* PMMIR_EL1.SLOTS mask */
-#define ARMV8_PMU_SLOTS_MASK	0xff
-
-#define ARMV8_PMU_BUS_SLOTS_SHIFT 8
-#define ARMV8_PMU_BUS_SLOTS_MASK 0xff
-#define ARMV8_PMU_BUS_WIDTH_SHIFT 16
-#define ARMV8_PMU_BUS_WIDTH_MASK 0xf
+#define ARMV8_PMU_SLOTS		GENMASK(7, 0)
+#define ARMV8_PMU_BUS_SLOTS	GENMASK(15, 8)
+#define ARMV8_PMU_BUS_WIDTH	GENMASK(19, 16)
+#define ARMV8_PMU_THWIDTH	GENMASK(23, 20)
 
 /*
  * This code is really good

tools/include/perf/arm_pmuv3.h

@@ -218,45 +218,54 @@
 #define ARMV8_PMU_PMCR_DP	(1 << 5) /* Disable CCNT if non-invasive debug*/
 #define ARMV8_PMU_PMCR_LC	(1 << 6) /* Overflow on 64 bit cycle counter */
 #define ARMV8_PMU_PMCR_LP	(1 << 7) /* Long event counter enable */
-#define ARMV8_PMU_PMCR_N_SHIFT	11  /* Number of counters supported */
-#define ARMV8_PMU_PMCR_N_MASK	0x1f
-#define ARMV8_PMU_PMCR_MASK	0xff    /* Mask for writable bits */
+#define ARMV8_PMU_PMCR_N	GENMASK(15, 11) /* Number of counters supported */
+/* Mask for writable bits */
+#define ARMV8_PMU_PMCR_MASK	(ARMV8_PMU_PMCR_E | ARMV8_PMU_PMCR_P | \
+				 ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_D | \
+				 ARMV8_PMU_PMCR_X | ARMV8_PMU_PMCR_DP | \
+				 ARMV8_PMU_PMCR_LC | ARMV8_PMU_PMCR_LP)
 
 /*
  * PMOVSR: counters overflow flag status reg
  */
-#define ARMV8_PMU_OVSR_MASK		0xffffffff	/* Mask for writable bits */
-#define ARMV8_PMU_OVERFLOWED_MASK	ARMV8_PMU_OVSR_MASK
+#define ARMV8_PMU_OVSR_P		GENMASK(30, 0)
+#define ARMV8_PMU_OVSR_C		BIT(31)
+/* Mask for writable bits is both P and C fields */
+#define ARMV8_PMU_OVERFLOWED_MASK	(ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C)
 
 /*
  * PMXEVTYPER: Event selection reg
  */
-#define ARMV8_PMU_EVTYPE_MASK	0xc800ffff	/* Mask for writable bits */
-#define ARMV8_PMU_EVTYPE_EVENT	0xffff		/* Mask for EVENT bits */
+#define ARMV8_PMU_EVTYPE_EVENT	GENMASK(15, 0)	/* Mask for EVENT bits */
+#define ARMV8_PMU_EVTYPE_TH	GENMASK(43, 32)
+#define ARMV8_PMU_EVTYPE_TC	GENMASK(63, 61)
 
 /*
  * Event filters for PMUv3
  */
-#define ARMV8_PMU_EXCLUDE_EL1	(1U << 31)
-#define ARMV8_PMU_EXCLUDE_EL0	(1U << 30)
-#define ARMV8_PMU_INCLUDE_EL2	(1U << 27)
+#define ARMV8_PMU_EXCLUDE_EL1		(1U << 31)
+#define ARMV8_PMU_EXCLUDE_EL0		(1U << 30)
+#define ARMV8_PMU_EXCLUDE_NS_EL1	(1U << 29)
+#define ARMV8_PMU_EXCLUDE_NS_EL0	(1U << 28)
+#define ARMV8_PMU_INCLUDE_EL2		(1U << 27)
+#define ARMV8_PMU_EXCLUDE_EL3		(1U << 26)
 
 /*
  * PMUSERENR: user enable reg
  */
-#define ARMV8_PMU_USERENR_MASK	0xf		/* Mask for writable bits */
 #define ARMV8_PMU_USERENR_EN	(1 << 0) /* PMU regs can be accessed at EL0 */
 #define ARMV8_PMU_USERENR_SW	(1 << 1) /* PMSWINC can be written at EL0 */
 #define ARMV8_PMU_USERENR_CR	(1 << 2) /* Cycle counter can be read at EL0 */
 #define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
+/* Mask for writable bits */
+#define ARMV8_PMU_USERENR_MASK	(ARMV8_PMU_USERENR_EN | ARMV8_PMU_USERENR_SW | \
+				 ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_ER)
 
 /* PMMIR_EL1.SLOTS mask */
-#define ARMV8_PMU_SLOTS_MASK	0xff
-
-#define ARMV8_PMU_BUS_SLOTS_SHIFT 8
-#define ARMV8_PMU_BUS_SLOTS_MASK 0xff
-#define ARMV8_PMU_BUS_WIDTH_SHIFT 16
-#define ARMV8_PMU_BUS_WIDTH_MASK 0xf
+#define ARMV8_PMU_SLOTS		GENMASK(7, 0)
+#define ARMV8_PMU_BUS_SLOTS	GENMASK(15, 8)
+#define ARMV8_PMU_BUS_WIDTH	GENMASK(19, 16)
+#define ARMV8_PMU_THWIDTH	GENMASK(23, 20)
 
 /*
  * This code is really good

tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c

@@ -42,13 +42,12 @@ struct pmreg_sets {
 
 static uint64_t get_pmcr_n(uint64_t pmcr)
 {
-	return (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
+	return FIELD_GET(ARMV8_PMU_PMCR_N, pmcr);
 }
 
 static void set_pmcr_n(uint64_t *pmcr, uint64_t pmcr_n)
 {
-	*pmcr = *pmcr & ~(ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
-	*pmcr |= (pmcr_n << ARMV8_PMU_PMCR_N_SHIFT);
+	u64p_replace_bits((__u64 *) pmcr, pmcr_n, ARMV8_PMU_PMCR_N);
 }
 
 static uint64_t get_counters_mask(uint64_t n)