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
  ...

1 files changed, 45 insertions, 0 deletions

diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c
index 92611c98120f..7dbfaee372c7 100644
--- a/drivers/perf/fsl_imx8_ddr_perf.c
+++ b/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;