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

Pull arm64 updates from Will Deacon:
 "CPU features:

   - Remove ARM64_HAS_NO_HW_PREFETCH copy_page() optimisation for ye
     olde Thunder-X machines

   - Avoid mapping KPTI trampoline when it is not required

   - Make CPU capability API more robust during early initialisation

  Early idreg overrides:

   - Remove dependencies on core kernel helpers from the early
     command-line parsing logic in preparation for moving this code
     before the kernel is mapped

  FPsimd:

   - Restore kernel-mode fpsimd context lazily, allowing us to run
     fpsimd code sequences in the kernel with pre-emption enabled

  KBuild:

   - Install 'vmlinuz.efi' when CONFIG_EFI_ZBOOT=y

   - Makefile cleanups

  LPA2 prep:

   - Preparatory work for enabling the 'LPA2' extension, which will
     introduce 52-bit virtual and physical addressing even with 4KiB
     pages (including for KVM guests).

  Misc:

   - Remove dead code and fix a typo

  MM:

   - Pass NUMA node information for IRQ stack allocations

  Perf:

   - Add perf support for the Synopsys DesignWare PCIe PMU

   - Add support for event counting thresholds (FEAT_PMUv3_TH)
     introduced in Armv8.8

   - Add support for i.MX8DXL SoCs to the IMX DDR PMU driver.

   - Minor PMU driver fixes and optimisations

  RIP VPIPT:

   - Remove what support we had for the obsolete VPIPT I-cache policy

  Selftests:

   - Improvements to the SVE and SME selftests

  Stacktrace:

   - Refactor kernel unwind logic so that it can used by BPF unwinding
     and, eventually, reliable backtracing

  Sysregs:

   - Update a bunch of register definitions based on the latest XML drop
     from Arm"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (87 commits)
  kselftest/arm64: Don't probe the current VL for unsupported vector types
  efi/libstub: zboot: do not use $(shell ...) in cmd_copy_and_pad
  arm64: properly install vmlinuz.efi
  arm64/sysreg: Add missing system instruction definitions for FGT
  arm64/sysreg: Add missing system register definitions for FGT
  arm64/sysreg: Add missing ExtTrcBuff field definition to ID_AA64DFR0_EL1
  arm64/sysreg: Add missing Pauth_LR field definitions to ID_AA64ISAR1_EL1
  arm64: memory: remove duplicated include
  arm: perf: Fix ARCH=arm build with GCC
  arm64: Align boot cpucap handling with system cpucap handling
  arm64: Cleanup system cpucap handling
  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
  arm64: irq: set the correct node for shadow call stack
  Revert "perf/arm_dmc620: Remove duplicate format attribute #defines"
  arm64: fpsimd: Implement lazy restore for kernel mode FPSIMD
  arm64: fpsimd: Preserve/restore kernel mode NEON at context switch
  ...

Author: torvalds

Documentation/admin-guide/perf/dwc_pcie_pmu.rst

@@ -0,0 +1,94 @@
+======================================================================
+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/arm-acpi.rst

@@ -130,7 +130,7 @@ When an Arm system boots, it can either have DT information, ACPI tables,
 or in some very unusual cases, both.  If no command line parameters are used,
 the kernel will try to use DT for device enumeration; if there is no DT
 present, the kernel will try to use ACPI tables, but only if they are present.
-In neither is available, the kernel will not boot.  If acpi=force is used
+If neither is available, the kernel will not boot.  If acpi=force is used
 on the command line, the kernel will attempt to use ACPI tables first, but
 fall back to DT if there are no ACPI tables present.  The basic idea is that
 the kernel will not fail to boot unless it absolutely has no other choice.

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

@@ -21028,6 +21028,13 @@ 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)