Merge tag 'ib-mfd-x86-v5.11' into review-hans

Immutable branch between MFD and x86 due for the v5.11 merge window

Documentation/ABI/testing/sysfs-class-intel_pmt

···
+What:		/sys/class/intel_pmt/
+Date:		October 2020
+KernelVersion:	5.10
+Contact:	David Box <[e-mail]>
+Description:
+		The intel_pmt/ class directory contains information for
+		devices that expose hardware telemetry using Intel Platform
+		Monitoring Technology (PMT)
+
+What:		/sys/class/intel_pmt/telem<x>
+Date:		October 2020
+KernelVersion:	5.10
+Contact:	David Box <[e-mail]>
+Description:
+		The telem<x> directory contains files describing an instance of
+		a PMT telemetry device that exposes hardware telemetry. Each
+		telem<x> directory has an associated telem file. This file
+		may be opened and mapped or read to access the telemetry space
+		of the device. The register layout of the telemetry space is
+		determined from an XML file that matches the PCI device id and
+		GUID for the device.
+
+What:		/sys/class/intel_pmt/telem<x>/telem
+Date:		October 2020
+KernelVersion:	5.10
+Contact:	David Box <[e-mail]>
+Description:
+		(RO) The telemetry data for this telemetry device. This file
+		may be mapped or read to obtain the data.
+
+What:		/sys/class/intel_pmt/telem<x>/guid
+Date:		October 2020
+KernelVersion:	5.10
+Contact:	David Box <[e-mail]>
+Description:
+		(RO) The GUID for this telemetry device. The GUID identifies
+		the version of the XML file for the parent device that is to
+		be used to get the register layout.
+
+What:		/sys/class/intel_pmt/telem<x>/size
+Date:		October 2020
+KernelVersion:	5.10
+Contact:	David Box <[e-mail]>
+Description:
+		(RO) The size of telemetry region in bytes that corresponds to
+		the mapping size for the telem file.
+
+What:		/sys/class/intel_pmt/telem<x>/offset
+Date:		October 2020
+KernelVersion:	5.10
+Contact:	David Box <[e-mail]>
+Description:
+		(RO) The offset of telemetry region in bytes that corresponds to
+		the mapping for the telem file.
+
+What:		/sys/class/intel_pmt/crashlog<x>
+Date:		October 2020
+KernelVersion:	5.10
+Contact:	Alexander Duyck <[e-mail]>
+Description:
+		The crashlog<x> directory contains files for configuring an
+		instance of a PMT crashlog device that can perform crash data
+		recording. Each crashlog<x> device has an associated crashlog
+		file. This file can be opened and mapped or read to access the
+		resulting crashlog buffer. The register layout for the buffer
+		can be determined from an XML file of specified GUID for the
+		parent device.
+
+What:		/sys/class/intel_pmt/crashlog<x>/crashlog
+Date:		October 2020
+KernelVersion:	5.10
+Contact:	David Box <[e-mail]>
+Description:
+		(RO) The crashlog buffer for this crashlog device. This file
+		may be mapped or read to obtain the data.
+
+What:		/sys/class/intel_pmt/crashlog<x>/guid
+Date:		October 2020
+KernelVersion:	5.10
+Contact:	Alexander Duyck <[e-mail]>
+Description:
+		(RO) The GUID for this crashlog device. The GUID identifies the
+		version of the XML file for the parent device that should be
+		used to determine the register layout.
+
+What:		/sys/class/intel_pmt/crashlog<x>/size
+Date:		October 2020
+KernelVersion:	5.10
+Contact:	Alexander Duyck <[e-mail]>
+Description:
+		(RO) The length of the result buffer in bytes that corresponds
+		to the size for the crashlog buffer.
+
+What:		/sys/class/intel_pmt/crashlog<x>/offset
+Date:		October 2020
+KernelVersion:	5.10
+Contact:	Alexander Duyck <[e-mail]>
+Description:
+		(RO) The offset of the buffer in bytes that corresponds
+		to the mapping for the crashlog device.
+
+What:		/sys/class/intel_pmt/crashlog<x>/enable
+Date:		October 2020
+KernelVersion:	5.10
+Contact:	Alexander Duyck <[e-mail]>
+Description:
+		(RW) Boolean value controlling if the crashlog functionality
+		is enabled for the crashlog device.
+
+What:		/sys/class/intel_pmt/crashlog<x>/trigger
+Date:		October 2020
+KernelVersion:	5.10
+Contact:	Alexander Duyck <[e-mail]>
+Description:
+		(RW) Boolean value controlling the triggering of the crashlog
+		device node. When read it provides data on if the crashlog has
+		been triggered. When written to it can be used to either clear
+		the current trigger by writing false, or to trigger a new
+		event if the trigger is not currently set.

MAINTAINERS

···
 F:	include/linux/mfd/intel_msic.h
 F:	include/linux/mfd/intel_soc_pmic*
 
+INTEL PMT DRIVER
+M:	"David E. Box" <[e-mail]>
+S:	Maintained
+F:	drivers/mfd/intel_pmt.c
+F:	drivers/platform/x86/intel_pmt_*
+
 INTEL PRO/WIRELESS 2100, 2200BG, 2915ABG NETWORK CONNECTION SUPPORT
 M:	Stanislav Yakovlev <[e-mail]>
 L:	[e-mail]

drivers/mfd/Kconfig

···
 	  Register and P-unit access. In addition this creates devices
 	  for iTCO watchdog and telemetry that are part of the PMC.
 
+config MFD_INTEL_PMT
+	tristate "Intel Platform Monitoring Technology (PMT) support"
+	depends on PCI
+	select MFD_CORE
+	help
+	  The Intel Platform Monitoring Technology (PMT) is an interface that
+	  provides access to hardware monitor registers. This driver supports
+	  Telemetry, Watcher, and Crashlog PMT capabilities/devices for
+	  platforms starting from Tiger Lake.
+
 config MFD_IPAQ_MICRO
 	bool "Atmel Micro ASIC (iPAQ h3100/h3600/h3700) Support"
 	depends on SA1100_H3100 || SA1100_H3600

drivers/mfd/Makefile

···
 obj-$(CONFIG_MFD_INTEL_LPSS_ACPI)	+= intel-lpss-acpi.o
 obj-$(CONFIG_MFD_INTEL_MSIC)	+= intel_msic.o
 obj-$(CONFIG_MFD_INTEL_PMC_BXT)	+= intel_pmc_bxt.o
+obj-$(CONFIG_MFD_INTEL_PMT)	+= intel_pmt.o
 obj-$(CONFIG_MFD_PALMAS)	+= palmas.o
 obj-$(CONFIG_MFD_VIPERBOARD)    += viperboard.o
 obj-$(CONFIG_MFD_RC5T583)	+= rc5t583.o rc5t583-irq.o

drivers/mfd/intel_pmt.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Platform Monitoring Technology PMT driver
+ *
+ * Copyright (c) 2020, Intel Corporation.
+ * All Rights Reserved.
+ *
+ * Author: David E. Box <[e-mail]>
+ */
+
+#include <linux/bits.h>
+#include <linux/kernel.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/types.h>
+
+/* Intel DVSEC capability vendor space offsets */
+#define INTEL_DVSEC_ENTRIES		0xA
+#define INTEL_DVSEC_SIZE		0xB
+#define INTEL_DVSEC_TABLE		0xC
+#define INTEL_DVSEC_TABLE_BAR(x)	((x) & GENMASK(2, 0))
+#define INTEL_DVSEC_TABLE_OFFSET(x)	((x) & GENMASK(31, 3))
+#define INTEL_DVSEC_ENTRY_SIZE		4
+
+/* PMT capabilities */
+#define DVSEC_INTEL_ID_TELEMETRY	2
+#define DVSEC_INTEL_ID_WATCHER		3
+#define DVSEC_INTEL_ID_CRASHLOG		4
+
+struct intel_dvsec_header {
+	u16	length;
+	u16	id;
+	u8	num_entries;
+	u8	entry_size;
+	u8	tbir;
+	u32	offset;
+};
+
+enum pmt_quirks {
+	/* Watcher capability not supported */
+	PMT_QUIRK_NO_WATCHER	= BIT(0),
+
+	/* Crashlog capability not supported */
+	PMT_QUIRK_NO_CRASHLOG	= BIT(1),
+
+	/* Use shift instead of mask to read discovery table offset */
+	PMT_QUIRK_TABLE_SHIFT	= BIT(2),
+};
+
+struct pmt_platform_info {
+	unsigned long quirks;
+};
+
+static const struct pmt_platform_info tgl_info = {
+	.quirks = PMT_QUIRK_NO_WATCHER | PMT_QUIRK_NO_CRASHLOG |
+		  PMT_QUIRK_TABLE_SHIFT,
+};
+
+static int pmt_add_dev(struct pci_dev *pdev, struct intel_dvsec_header *header,
+		       unsigned long quirks)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *res, *tmp;
+	struct mfd_cell *cell;
+	const char *name;
+	int count = header->num_entries;
+	int size = header->entry_size;
+	int id = header->id;
+	int i;
+
+	switch (id) {
+	case DVSEC_INTEL_ID_TELEMETRY:
+		name = "pmt_telemetry";
+		break;
+	case DVSEC_INTEL_ID_WATCHER:
+		if (quirks & PMT_QUIRK_NO_WATCHER) {
+			dev_info(dev, "Watcher not supported\n");
+			return 0;
+		}
+		name = "pmt_watcher";
+		break;
+	case DVSEC_INTEL_ID_CRASHLOG:
+		if (quirks & PMT_QUIRK_NO_CRASHLOG) {
+			dev_info(dev, "Crashlog not supported\n");
+			return 0;
+		}
+		name = "pmt_crashlog";
+		break;
+	default:
+		dev_err(dev, "Unrecognized PMT capability: %d\n", id);
+		return -EINVAL;
+	}
+
+	if (!header->num_entries || !header->entry_size) {
+		dev_err(dev, "Invalid count or size for %s header\n", name);
+		return -EINVAL;
+	}
+
+	cell = devm_kzalloc(dev, sizeof(*cell), GFP_KERNEL);
+	if (!cell)
+		return -ENOMEM;
+
+	res = devm_kcalloc(dev, count, sizeof(*res), GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
+
+	if (quirks & PMT_QUIRK_TABLE_SHIFT)
+		header->offset >>= 3;
+
+	/*
+	 * The PMT DVSEC contains the starting offset and count for a block of
+	 * discovery tables, each providing access to monitoring facilities for
+	 * a section of the device. Create a resource list of these tables to
+	 * provide to the driver.
+	 */
+	for (i = 0, tmp = res; i < count; i++, tmp++) {
+		tmp->start = pdev->resource[header->tbir].start +
+			     header->offset + i * (size << 2);
+		tmp->end = tmp->start + (size << 2) - 1;
+		tmp->flags = IORESOURCE_MEM;
+	}
+
+	cell->resources = res;
+	cell->num_resources = count;
+	cell->name = name;
+
+	return devm_mfd_add_devices(dev, PLATFORM_DEVID_AUTO, cell, 1, NULL, 0,
+				    NULL);
+}
+
+static int pmt_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct pmt_platform_info *info;
+	unsigned long quirks = 0;
+	bool found_devices = false;
+	int ret, pos = 0;
+
+	ret = pcim_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	info = (struct pmt_platform_info *)id->driver_data;
+
+	if (info)
+		quirks = info->quirks;
+
+	do {
+		struct intel_dvsec_header header;
+		u32 table;
+		u16 vid;
+
+		pos = pci_find_next_ext_capability(pdev, pos, PCI_EXT_CAP_ID_DVSEC);
+		if (!pos)
+			break;
+
+		pci_read_config_word(pdev, pos + PCI_DVSEC_HEADER1, &vid);
+		if (vid != PCI_VENDOR_ID_INTEL)
+			continue;
+
+		pci_read_config_word(pdev, pos + PCI_DVSEC_HEADER2,
+				     &header.id);
+		pci_read_config_byte(pdev, pos + INTEL_DVSEC_ENTRIES,
+				     &header.num_entries);
+		pci_read_config_byte(pdev, pos + INTEL_DVSEC_SIZE,
+				     &header.entry_size);
+		pci_read_config_dword(pdev, pos + INTEL_DVSEC_TABLE,
+				      &table);
+
+		header.tbir = INTEL_DVSEC_TABLE_BAR(table);
+		header.offset = INTEL_DVSEC_TABLE_OFFSET(table);
+
+		ret = pmt_add_dev(pdev, &header, quirks);
+		if (ret) {
+			dev_warn(&pdev->dev,
+				 "Failed to add device for DVSEC id %d\n",
+				 header.id);
+			continue;
+		}
+
+		found_devices = true;
+	} while (true);
+
+	if (!found_devices)
+		return -ENODEV;
+
+	pm_runtime_put(&pdev->dev);
+	pm_runtime_allow(&pdev->dev);
+
+	return 0;
+}
+
+static void pmt_pci_remove(struct pci_dev *pdev)
+{
+	pm_runtime_forbid(&pdev->dev);
+	pm_runtime_get_sync(&pdev->dev);
+}
+
+#define PCI_DEVICE_ID_INTEL_PMT_ADL	0x467d
+#define PCI_DEVICE_ID_INTEL_PMT_OOBMSM	0x09a7
+#define PCI_DEVICE_ID_INTEL_PMT_TGL	0x9a0d
+static const struct pci_device_id pmt_pci_ids[] = {
+	{ PCI_DEVICE_DATA(INTEL, PMT_ADL, &tgl_info) },
+	{ PCI_DEVICE_DATA(INTEL, PMT_OOBMSM, NULL) },
+	{ PCI_DEVICE_DATA(INTEL, PMT_TGL, &tgl_info) },
+	{ }
+};
+MODULE_DEVICE_TABLE(pci, pmt_pci_ids);
+
+static struct pci_driver pmt_pci_driver = {
+	.name = "intel-pmt",
+	.id_table = pmt_pci_ids,
+	.probe = pmt_pci_probe,
+	.remove = pmt_pci_remove,
+};
+module_pci_driver(pmt_pci_driver);
+
+MODULE_AUTHOR("David E. Box <[e-mail]>");
+MODULE_DESCRIPTION("Intel Platform Monitoring Technology PMT driver");
+MODULE_LICENSE("GPL v2");

drivers/platform/x86/Kconfig

···
 		- LTR Ignore
 		- MPHY/PLL gating status (Sunrisepoint PCH only)
 
+config INTEL_PMT_CLASS
+	tristate "Intel Platform Monitoring Technology (PMT) Class driver"
+	help
+	  The Intel Platform Monitoring Technology (PMT) class driver provides
+	  the basic sysfs interface and file hierarchy uses by PMT devices.
+
+	  For more information, see:
+	  <file:Documentation/ABI/testing/sysfs-class-intel_pmt>
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called intel_pmt_class.
+
+config INTEL_PMT_TELEMETRY
+	tristate "Intel Platform Monitoring Technology (PMT) Telemetry driver"
+	select INTEL_PMT_CLASS
+	help
+	  The Intel Platform Monitory Technology (PMT) Telemetry driver provides
+	  access to hardware telemetry metrics on devices that support the
+	  feature.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called intel_pmt_telemetry.
+
+config INTEL_PMT_CRASHLOG
+	tristate "Intel Platform Monitoring Technology (PMT) Crashlog driver"
+	select INTEL_PMT_CLASS
+	help
+	  The Intel Platform Monitoring Technology (PMT) crashlog driver provides
+	  access to hardware crashlog capabilities on devices that support the
+	  feature.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called intel_pmt_crashlog.
+
 config INTEL_PUNIT_IPC
 	tristate "Intel P-Unit IPC Driver"
 	help

drivers/platform/x86/Makefile

···
 obj-$(CONFIG_INTEL_MID_POWER_BUTTON)	+= intel_mid_powerbtn.o
 obj-$(CONFIG_INTEL_MRFLD_PWRBTN)	+= intel_mrfld_pwrbtn.o
 obj-$(CONFIG_INTEL_PMC_CORE)		+= intel_pmc_core.o intel_pmc_core_pltdrv.o
+obj-$(CONFIG_INTEL_PMT_CLASS)		+= intel_pmt_class.o
+obj-$(CONFIG_INTEL_PMT_TELEMETRY)	+= intel_pmt_telemetry.o
+obj-$(CONFIG_INTEL_PMT_CRASHLOG)	+= intel_pmt_crashlog.o
 obj-$(CONFIG_INTEL_PUNIT_IPC)		+= intel_punit_ipc.o
 obj-$(CONFIG_INTEL_SCU_IPC)		+= intel_scu_ipc.o
 obj-$(CONFIG_INTEL_SCU_PCI)		+= intel_scu_pcidrv.o

drivers/platform/x86/intel_pmt_class.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Platform Monitory Technology Telemetry driver
+ *
+ * Copyright (c) 2020, Intel Corporation.
+ * All Rights Reserved.
+ *
+ * Author: "Alexander Duyck" <[e-mail]>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/pci.h>
+
+#include "intel_pmt_class.h"
+
+#define PMT_XA_START		0
+#define PMT_XA_MAX		INT_MAX
+#define PMT_XA_LIMIT		XA_LIMIT(PMT_XA_START, PMT_XA_MAX)
+
+/*
+ * sysfs
+ */
+static ssize_t
+intel_pmt_read(struct file *filp, struct kobject *kobj,
+	       struct bin_attribute *attr, char *buf, loff_t off,
+	       size_t count)
+{
+	struct intel_pmt_entry *entry = container_of(attr,
+						     struct intel_pmt_entry,
+						     pmt_bin_attr);
+
+	if (off < 0)
+		return -EINVAL;
+
+	if (off >= entry->size)
+		return 0;
+
+	if (count > entry->size - off)
+		count = entry->size - off;
+
+	memcpy_fromio(buf, entry->base + off, count);
+
+	return count;
+}
+
+static int
+intel_pmt_mmap(struct file *filp, struct kobject *kobj,
+		struct bin_attribute *attr, struct vm_area_struct *vma)
+{
+	struct intel_pmt_entry *entry = container_of(attr,
+						     struct intel_pmt_entry,
+						     pmt_bin_attr);
+	unsigned long vsize = vma->vm_end - vma->vm_start;
+	struct device *dev = kobj_to_dev(kobj);
+	unsigned long phys = entry->base_addr;
+	unsigned long pfn = PFN_DOWN(phys);
+	unsigned long psize;
+
+	if (vma->vm_flags & (VM_WRITE | VM_MAYWRITE))
+		return -EROFS;
+
+	psize = (PFN_UP(entry->base_addr + entry->size) - pfn) * PAGE_SIZE;
+	if (vsize > psize) {
+		dev_err(dev, "Requested mmap size is too large\n");
+		return -EINVAL;
+	}
+
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	if (io_remap_pfn_range(vma, vma->vm_start, pfn,
+		vsize, vma->vm_page_prot))
+		return -EAGAIN;
+
+	return 0;
+}
+
+static ssize_t
+guid_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct intel_pmt_entry *entry = dev_get_drvdata(dev);
+
+	return sprintf(buf, "0x%x\n", entry->guid);
+}
+static DEVICE_ATTR_RO(guid);
+
+static ssize_t size_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct intel_pmt_entry *entry = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%zu\n", entry->size);
+}
+static DEVICE_ATTR_RO(size);
+
+static ssize_t
+offset_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct intel_pmt_entry *entry = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%lu\n", offset_in_page(entry->base_addr));
+}
+static DEVICE_ATTR_RO(offset);
+
+static struct attribute *intel_pmt_attrs[] = {
+	&dev_attr_guid.attr,
+	&dev_attr_size.attr,
+	&dev_attr_offset.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(intel_pmt);
+
+static struct class intel_pmt_class = {
+	.name = "intel_pmt",
+	.owner = THIS_MODULE,
+	.dev_groups = intel_pmt_groups,
+};
+
+static int intel_pmt_populate_entry(struct intel_pmt_entry *entry,
+				    struct intel_pmt_header *header,
+				    struct device *dev,
+				    struct resource *disc_res)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev->parent);
+	u8 bir;
+
+	/*
+	 * The base offset should always be 8 byte aligned.
+	 *
+	 * For non-local access types the lower 3 bits of base offset
+	 * contains the index of the base address register where the
+	 * telemetry can be found.
+	 */
+	bir = GET_BIR(header->base_offset);
+
+	/* Local access and BARID only for now */
+	switch (header->access_type) {
+	case ACCESS_LOCAL:
+		if (bir) {
+			dev_err(dev,
+				"Unsupported BAR index %d for access type %d\n",
+				bir, header->access_type);
+			return -EINVAL;
+		}
+		/*
+		 * For access_type LOCAL, the base address is as follows:
+		 * base address = end of discovery region + base offset
+		 */
+		entry->base_addr = disc_res->end + 1 + header->base_offset;
+		break;
+	case ACCESS_BARID:
+		/*
+		 * If another BAR was specified then the base offset
+		 * represents the offset within that BAR. SO retrieve the
+		 * address from the parent PCI device and add offset.
+		 */
+		entry->base_addr = pci_resource_start(pci_dev, bir) +
+				   GET_ADDRESS(header->base_offset);
+		break;
+	default:
+		dev_err(dev, "Unsupported access type %d\n",
+			header->access_type);
+		return -EINVAL;
+	}
+
+	entry->guid = header->guid;
+	entry->size = header->size;
+
+	return 0;
+}
+
+static int intel_pmt_dev_register(struct intel_pmt_entry *entry,
+				  struct intel_pmt_namespace *ns,
+				  struct device *parent)
+{
+	struct resource res;
+	struct device *dev;
+	int ret;
+
+	ret = xa_alloc(ns->xa, &entry->devid, entry, PMT_XA_LIMIT, GFP_KERNEL);
+	if (ret)
+		return ret;
+
+	dev = device_create(&intel_pmt_class, parent, MKDEV(0, 0), entry,
+			    "%s%d", ns->name, entry->devid);
+
+	if (IS_ERR(dev)) {
+		dev_err(parent, "Could not create %s%d device node\n",
+			ns->name, entry->devid);
+		ret = PTR_ERR(dev);
+		goto fail_dev_create;
+	}
+
+	entry->kobj = &dev->kobj;
+
+	if (ns->attr_grp) {
+		ret = sysfs_create_group(entry->kobj, ns->attr_grp);
+		if (ret)
+			goto fail_sysfs;
+	}
+
+	/* if size is 0 assume no data buffer, so no file needed */
+	if (!entry->size)
+		return 0;
+
+	res.start = entry->base_addr;
+	res.end = res.start + entry->size - 1;
+	res.flags = IORESOURCE_MEM;
+
+	entry->base = devm_ioremap_resource(dev, &res);
+	if (IS_ERR(entry->base)) {
+		ret = PTR_ERR(entry->base);
+		goto fail_ioremap;
+	}
+
+	sysfs_bin_attr_init(&entry->pmt_bin_attr);
+	entry->pmt_bin_attr.attr.name = ns->name;
+	entry->pmt_bin_attr.attr.mode = 0440;
+	entry->pmt_bin_attr.mmap = intel_pmt_mmap;
+	entry->pmt_bin_attr.read = intel_pmt_read;
+	entry->pmt_bin_attr.size = entry->size;
+
+	ret = sysfs_create_bin_file(&dev->kobj, &entry->pmt_bin_attr);
+	if (!ret)
+		return 0;
+
+fail_ioremap:
+	sysfs_remove_group(entry->kobj, ns->attr_grp);
+fail_sysfs:
+	device_unregister(dev);
+fail_dev_create:
+	xa_erase(ns->xa, entry->devid);
+
+	return ret;
+}
+
+int intel_pmt_dev_create(struct intel_pmt_entry *entry,
+			 struct intel_pmt_namespace *ns,
+			 struct platform_device *pdev, int idx)
+{
+	struct intel_pmt_header header;
+	struct resource	*disc_res;
+	int ret = -ENODEV;
+
+	disc_res = platform_get_resource(pdev, IORESOURCE_MEM, idx);
+	if (!disc_res)
+		return ret;
+
+	entry->disc_table = devm_platform_ioremap_resource(pdev, idx);
+	if (IS_ERR(entry->disc_table))
+		return PTR_ERR(entry->disc_table);
+
+	ret = ns->pmt_header_decode(entry, &header, &pdev->dev);
+	if (ret)
+		return ret;
+
+	ret = intel_pmt_populate_entry(entry, &header, &pdev->dev, disc_res);
+	if (ret)
+		return ret;
+
+	return intel_pmt_dev_register(entry, ns, &pdev->dev);
+
+}
+EXPORT_SYMBOL_GPL(intel_pmt_dev_create);
+
+void intel_pmt_dev_destroy(struct intel_pmt_entry *entry,
+			   struct intel_pmt_namespace *ns)
+{
+	struct device *dev = kobj_to_dev(entry->kobj);
+
+	if (entry->size)
+		sysfs_remove_bin_file(entry->kobj, &entry->pmt_bin_attr);
+
+	if (ns->attr_grp)
+		sysfs_remove_group(entry->kobj, ns->attr_grp);
+
+	device_unregister(dev);
+	xa_erase(ns->xa, entry->devid);
+}
+EXPORT_SYMBOL_GPL(intel_pmt_dev_destroy);
+
+static int __init pmt_class_init(void)
+{
+	return class_register(&intel_pmt_class);
+}
+
+static void __exit pmt_class_exit(void)
+{
+	class_unregister(&intel_pmt_class);
+}
+
+module_init(pmt_class_init);
+module_exit(pmt_class_exit);
+
+MODULE_AUTHOR("Alexander Duyck <[e-mail]>");
+MODULE_DESCRIPTION("Intel PMT Class driver");
+MODULE_LICENSE("GPL v2");

drivers/platform/x86/intel_pmt_class.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _INTEL_PMT_CLASS_H
+#define _INTEL_PMT_CLASS_H
+
+#include <linux/platform_device.h>
+#include <linux/xarray.h>
+#include <linux/types.h>
+#include <linux/bits.h>
+#include <linux/err.h>
+#include <linux/io.h>
+
+/* PMT access types */
+#define ACCESS_BARID		2
+#define ACCESS_LOCAL		3
+
+/* PMT discovery base address/offset register layout */
+#define GET_BIR(v)		((v) & GENMASK(2, 0))
+#define GET_ADDRESS(v)		((v) & GENMASK(31, 3))
+
+struct intel_pmt_entry {
+	struct bin_attribute	pmt_bin_attr;
+	struct kobject		*kobj;
+	void __iomem		*disc_table;
+	void __iomem		*base;
+	unsigned long		base_addr;
+	size_t			size;
+	u32			guid;
+	int			devid;
+};
+
+struct intel_pmt_header {
+	u32	base_offset;
+	u32	size;
+	u32	guid;
+	u8	access_type;
+};
+
+struct intel_pmt_namespace {
+	const char *name;
+	struct xarray *xa;
+	const struct attribute_group *attr_grp;
+	int (*pmt_header_decode)(struct intel_pmt_entry *entry,
+				 struct intel_pmt_header *header,
+				 struct device *dev);
+};
+
+int intel_pmt_dev_create(struct intel_pmt_entry *entry,
+			 struct intel_pmt_namespace *ns,
+			 struct platform_device *pdev, int idx);
+void intel_pmt_dev_destroy(struct intel_pmt_entry *entry,
+			   struct intel_pmt_namespace *ns);
+#endif

drivers/platform/x86/intel_pmt_crashlog.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Platform Monitoring Technology Crashlog driver
+ *
+ * Copyright (c) 2020, Intel Corporation.
+ * All Rights Reserved.
+ *
+ * Author: "Alexander Duyck" <[e-mail]>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/overflow.h>
+
+#include "intel_pmt_class.h"
+
+#define DRV_NAME		"pmt_crashlog"
+
+/* Crashlog discovery header types */
+#define CRASH_TYPE_OOBMSM	1
+
+/* Control Flags */
+#define CRASHLOG_FLAG_DISABLE		BIT(27)
+
+/*
+ * Bits 28 and 29 control the state of bit 31.
+ *
+ * Bit 28 will clear bit 31, if set, allowing a new crashlog to be captured.
+ * Bit 29 will immediately trigger a crashlog to be generated, setting bit 31.
+ * Bit 30 is read-only and reserved as 0.
+ * Bit 31 is the read-only status with a 1 indicating log is complete.
+ */
+#define CRASHLOG_FLAG_TRIGGER_CLEAR	BIT(28)
+#define CRASHLOG_FLAG_TRIGGER_EXECUTE	BIT(29)
+#define CRASHLOG_FLAG_TRIGGER_COMPLETE	BIT(31)
+#define CRASHLOG_FLAG_TRIGGER_MASK	GENMASK(31, 28)
+
+/* Crashlog Discovery Header */
+#define CONTROL_OFFSET		0x0
+#define GUID_OFFSET		0x4
+#define BASE_OFFSET		0x8
+#define SIZE_OFFSET		0xC
+#define GET_ACCESS(v)		((v) & GENMASK(3, 0))
+#define GET_TYPE(v)		(((v) & GENMASK(7, 4)) >> 4)
+#define GET_VERSION(v)		(((v) & GENMASK(19, 16)) >> 16)
+/* size is in bytes */
+#define GET_SIZE(v)		((v) * sizeof(u32))
+
+struct crashlog_entry {
+	/* entry must be first member of struct */
+	struct intel_pmt_entry		entry;
+	struct mutex			control_mutex;
+};
+
+struct pmt_crashlog_priv {
+	int			num_entries;
+	struct crashlog_entry	entry[];
+};
+
+/*
+ * I/O
+ */
+static bool pmt_crashlog_complete(struct intel_pmt_entry *entry)
+{
+	u32 control = readl(entry->disc_table + CONTROL_OFFSET);
+
+	/* return current value of the crashlog complete flag */
+	return !!(control & CRASHLOG_FLAG_TRIGGER_COMPLETE);
+}
+
+static bool pmt_crashlog_disabled(struct intel_pmt_entry *entry)
+{
+	u32 control = readl(entry->disc_table + CONTROL_OFFSET);
+
+	/* return current value of the crashlog disabled flag */
+	return !!(control & CRASHLOG_FLAG_DISABLE);
+}
+
+static bool pmt_crashlog_supported(struct intel_pmt_entry *entry)
+{
+	u32 discovery_header = readl(entry->disc_table + CONTROL_OFFSET);
+	u32 crash_type, version;
+
+	crash_type = GET_TYPE(discovery_header);
+	version = GET_VERSION(discovery_header);
+
+	/*
+	 * Currently we only recognize OOBMSM version 0 devices.
+	 * We can ignore all other crashlog devices in the system.
+	 */
+	return crash_type == CRASH_TYPE_OOBMSM && version == 0;
+}
+
+static void pmt_crashlog_set_disable(struct intel_pmt_entry *entry,
+				     bool disable)
+{
+	u32 control = readl(entry->disc_table + CONTROL_OFFSET);
+
+	/* clear trigger bits so we are only modifying disable flag */
+	control &= ~CRASHLOG_FLAG_TRIGGER_MASK;
+
+	if (disable)
+		control |= CRASHLOG_FLAG_DISABLE;
+	else
+		control &= ~CRASHLOG_FLAG_DISABLE;
+
+	writel(control, entry->disc_table + CONTROL_OFFSET);
+}
+
+static void pmt_crashlog_set_clear(struct intel_pmt_entry *entry)
+{
+	u32 control = readl(entry->disc_table + CONTROL_OFFSET);
+
+	control &= ~CRASHLOG_FLAG_TRIGGER_MASK;
+	control |= CRASHLOG_FLAG_TRIGGER_CLEAR;
+
+	writel(control, entry->disc_table + CONTROL_OFFSET);
+}
+
+static void pmt_crashlog_set_execute(struct intel_pmt_entry *entry)
+{
+	u32 control = readl(entry->disc_table + CONTROL_OFFSET);
+
+	control &= ~CRASHLOG_FLAG_TRIGGER_MASK;
+	control |= CRASHLOG_FLAG_TRIGGER_EXECUTE;
+
+	writel(control, entry->disc_table + CONTROL_OFFSET);
+}
+
+/*
+ * sysfs
+ */
+static ssize_t
+enable_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct intel_pmt_entry *entry = dev_get_drvdata(dev);
+	int enabled = !pmt_crashlog_disabled(entry);
+
+	return sprintf(buf, "%d\n", enabled);
+}
+
+static ssize_t
+enable_store(struct device *dev, struct device_attribute *attr,
+	    const char *buf, size_t count)
+{
+	struct crashlog_entry *entry;
+	bool enabled;
+	int result;
+
+	entry = dev_get_drvdata(dev);
+
+	result = kstrtobool(buf, &enabled);
+	if (result)
+		return result;
+
+	mutex_lock(&entry->control_mutex);
+	pmt_crashlog_set_disable(&entry->entry, !enabled);
+	mutex_unlock(&entry->control_mutex);
+
+	return count;
+}
+static DEVICE_ATTR_RW(enable);
+
+static ssize_t
+trigger_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct intel_pmt_entry *entry;
+	int trigger;
+
+	entry = dev_get_drvdata(dev);
+	trigger = pmt_crashlog_complete(entry);
+
+	return sprintf(buf, "%d\n", trigger);
+}
+
+static ssize_t
+trigger_store(struct device *dev, struct device_attribute *attr,
+	    const char *buf, size_t count)
+{
+	struct crashlog_entry *entry;
+	bool trigger;
+	int result;
+
+	entry = dev_get_drvdata(dev);
+
+	result = kstrtobool(buf, &trigger);
+	if (result)
+		return result;
+
+	mutex_lock(&entry->control_mutex);
+
+	if (!trigger) {
+		pmt_crashlog_set_clear(&entry->entry);
+	} else if (pmt_crashlog_complete(&entry->entry)) {
+		/* we cannot trigger a new crash if one is still pending */
+		result = -EEXIST;
+		goto err;
+	} else if (pmt_crashlog_disabled(&entry->entry)) {
+		/* if device is currently disabled, return busy */
+		result = -EBUSY;
+		goto err;
+	} else {
+		pmt_crashlog_set_execute(&entry->entry);
+	}
+
+	result = count;
+err:
+	mutex_unlock(&entry->control_mutex);
+	return result;
+}
+static DEVICE_ATTR_RW(trigger);
+
+static struct attribute *pmt_crashlog_attrs[] = {
+	&dev_attr_enable.attr,
+	&dev_attr_trigger.attr,
+	NULL
+};
+
+static struct attribute_group pmt_crashlog_group = {
+	.attrs	= pmt_crashlog_attrs,
+};
+
+static int pmt_crashlog_header_decode(struct intel_pmt_entry *entry,
+				      struct intel_pmt_header *header,
+				      struct device *dev)
+{
+	void __iomem *disc_table = entry->disc_table;
+	struct crashlog_entry *crashlog;
+
+	if (!pmt_crashlog_supported(entry))
+		return 1;
+
+	/* initialize control mutex */
+	crashlog = container_of(entry, struct crashlog_entry, entry);
+	mutex_init(&crashlog->control_mutex);
+
+	header->access_type = GET_ACCESS(readl(disc_table));
+	header->guid = readl(disc_table + GUID_OFFSET);
+	header->base_offset = readl(disc_table + BASE_OFFSET);
+
+	/* Size is measured in DWORDS, but accessor returns bytes */
+	header->size = GET_SIZE(readl(disc_table + SIZE_OFFSET));
+
+	return 0;
+}
+
+static DEFINE_XARRAY_ALLOC(crashlog_array);
+static struct intel_pmt_namespace pmt_crashlog_ns = {
+	.name = "crashlog",
+	.xa = &crashlog_array,
+	.attr_grp = &pmt_crashlog_group,
+	.pmt_header_decode = pmt_crashlog_header_decode,
+};
+
+/*
+ * initialization
+ */
+static int pmt_crashlog_remove(struct platform_device *pdev)
+{
+	struct pmt_crashlog_priv *priv = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < priv->num_entries; i++)
+		intel_pmt_dev_destroy(&priv->entry[i].entry, &pmt_crashlog_ns);
+
+	return 0;
+}
+
+static int pmt_crashlog_probe(struct platform_device *pdev)
+{
+	struct pmt_crashlog_priv *priv;
+	size_t size;
+	int i, ret;
+
+	size = struct_size(priv, entry, pdev->num_resources);
+	priv = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, priv);
+
+	for (i = 0; i < pdev->num_resources; i++) {
+		struct intel_pmt_entry *entry = &priv->entry[i].entry;
+
+		ret = intel_pmt_dev_create(entry, &pmt_crashlog_ns, pdev, i);
+		if (ret < 0)
+			goto abort_probe;
+		if (ret)
+			continue;
+
+		priv->num_entries++;
+	}
+
+	return 0;
+abort_probe:
+	pmt_crashlog_remove(pdev);
+	return ret;
+}
+
+static struct platform_driver pmt_crashlog_driver = {
+	.driver = {
+		.name   = DRV_NAME,
+	},
+	.remove = pmt_crashlog_remove,
+	.probe  = pmt_crashlog_probe,
+};
+
+static int __init pmt_crashlog_init(void)
+{
+	return platform_driver_register(&pmt_crashlog_driver);
+}
+
+static void __exit pmt_crashlog_exit(void)
+{
+	platform_driver_unregister(&pmt_crashlog_driver);
+	xa_destroy(&crashlog_array);
+}
+
+module_init(pmt_crashlog_init);
+module_exit(pmt_crashlog_exit);
+
+MODULE_AUTHOR("Alexander Duyck <[e-mail]>");
+MODULE_DESCRIPTION("Intel PMT Crashlog driver");
+MODULE_ALIAS("platform:" DRV_NAME);
+MODULE_LICENSE("GPL v2");

drivers/platform/x86/intel_pmt_telemetry.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Platform Monitory Technology Telemetry driver
+ *
+ * Copyright (c) 2020, Intel Corporation.
+ * All Rights Reserved.
+ *
+ * Author: "David E. Box" <[e-mail]>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/overflow.h>
+
+#include "intel_pmt_class.h"
+
+#define TELEM_DEV_NAME		"pmt_telemetry"
+
+#define TELEM_SIZE_OFFSET	0x0
+#define TELEM_GUID_OFFSET	0x4
+#define TELEM_BASE_OFFSET	0x8
+#define TELEM_ACCESS(v)		((v) & GENMASK(3, 0))
+/* size is in bytes */
+#define TELEM_SIZE(v)		(((v) & GENMASK(27, 12)) >> 10)
+
+/* Used by client hardware to identify a fixed telemetry entry*/
+#define TELEM_CLIENT_FIXED_BLOCK_GUID	0x10000000
+
+struct pmt_telem_priv {
+	int				num_entries;
+	struct intel_pmt_entry		entry[];
+};
+
+/*
+ * Early implementations of PMT on client platforms have some
+ * differences from the server platforms (which use the Out Of Band
+ * Management Services Module OOBMSM). This list tracks those
+ * platforms as needed to handle those differences. Newer client
+ * platforms are expected to be fully compatible with server.
+ */
+static const struct pci_device_id pmt_telem_early_client_pci_ids[] = {
+	{ PCI_VDEVICE(INTEL, 0x9a0d) }, /* TGL */
+	{ PCI_VDEVICE(INTEL, 0x467d) }, /* ADL */
+	{ }
+};
+
+static bool intel_pmt_is_early_client_hw(struct device *dev)
+{
+	struct pci_dev *parent = to_pci_dev(dev->parent);
+
+	return !!pci_match_id(pmt_telem_early_client_pci_ids, parent);
+}
+
+static bool pmt_telem_region_overlaps(struct intel_pmt_entry *entry,
+				      struct device *dev)
+{
+	u32 guid = readl(entry->disc_table + TELEM_GUID_OFFSET);
+
+	if (guid != TELEM_CLIENT_FIXED_BLOCK_GUID)
+		return false;
+
+	return intel_pmt_is_early_client_hw(dev);
+}
+
+static int pmt_telem_header_decode(struct intel_pmt_entry *entry,
+				   struct intel_pmt_header *header,
+				   struct device *dev)
+{
+	void __iomem *disc_table = entry->disc_table;
+
+	if (pmt_telem_region_overlaps(entry, dev))
+		return 1;
+
+	header->access_type = TELEM_ACCESS(readl(disc_table));
+	header->guid = readl(disc_table + TELEM_GUID_OFFSET);
+	header->base_offset = readl(disc_table + TELEM_BASE_OFFSET);
+
+	/* Size is measured in DWORDS, but accessor returns bytes */
+	header->size = TELEM_SIZE(readl(disc_table));
+
+	return 0;
+}
+
+static DEFINE_XARRAY_ALLOC(telem_array);
+static struct intel_pmt_namespace pmt_telem_ns = {
+	.name = "telem",
+	.xa = &telem_array,
+	.pmt_header_decode = pmt_telem_header_decode,
+};
+
+static int pmt_telem_remove(struct platform_device *pdev)
+{
+	struct pmt_telem_priv *priv = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < priv->num_entries; i++)
+		intel_pmt_dev_destroy(&priv->entry[i], &pmt_telem_ns);
+
+	return 0;
+}
+
+static int pmt_telem_probe(struct platform_device *pdev)
+{
+	struct pmt_telem_priv *priv;
+	size_t size;
+	int i, ret;
+
+	size = struct_size(priv, entry, pdev->num_resources);
+	priv = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, priv);
+
+	for (i = 0; i < pdev->num_resources; i++) {
+		struct intel_pmt_entry *entry = &priv->entry[i];
+
+		ret = intel_pmt_dev_create(entry, &pmt_telem_ns, pdev, i);
+		if (ret < 0)
+			goto abort_probe;
+		if (ret)
+			continue;
+
+		priv->num_entries++;
+	}
+
+	return 0;
+abort_probe:
+	pmt_telem_remove(pdev);
+	return ret;
+}
+
+static struct platform_driver pmt_telem_driver = {
+	.driver = {
+		.name   = TELEM_DEV_NAME,
+	},
+	.remove = pmt_telem_remove,
+	.probe  = pmt_telem_probe,
+};
+
+static int __init pmt_telem_init(void)
+{
+	return platform_driver_register(&pmt_telem_driver);
+}
+module_init(pmt_telem_init);
+
+static void __exit pmt_telem_exit(void)
+{
+	platform_driver_unregister(&pmt_telem_driver);
+	xa_destroy(&telem_array);
+}
+module_exit(pmt_telem_exit);
+
+MODULE_AUTHOR("David E. Box <[e-mail]>");
+MODULE_DESCRIPTION("Intel PMT Telemetry driver");
+MODULE_ALIAS("platform:" TELEM_DEV_NAME);
+MODULE_LICENSE("GPL v2");

include/uapi/linux/pci_regs.h

···
 #define PCI_EXT_CAP_ID_DPC	0x1D	/* Downstream Port Containment */
 #define PCI_EXT_CAP_ID_L1SS	0x1E	/* L1 PM Substates */
 #define PCI_EXT_CAP_ID_PTM	0x1F	/* Precision Time Measurement */
+#define PCI_EXT_CAP_ID_DVSEC	0x23	/* Designated Vendor-Specific */
 #define PCI_EXT_CAP_ID_DLF	0x25	/* Data Link Feature */
 #define PCI_EXT_CAP_ID_PL_16GT	0x26	/* Physical Layer 16.0 GT/s */
 #define PCI_EXT_CAP_ID_MAX	PCI_EXT_CAP_ID_PL_16GT
···
 #define  PCI_L1SS_CTL1_LTR_L12_TH_VALUE	0x03ff0000  /* LTR_L1.2_THRESHOLD_Value */
 #define  PCI_L1SS_CTL1_LTR_L12_TH_SCALE	0xe0000000  /* LTR_L1.2_THRESHOLD_Scale */
 #define PCI_L1SS_CTL2		0x0c	/* Control 2 Register */
+
+/* Designated Vendor-Specific (DVSEC, PCI_EXT_CAP_ID_DVSEC) */
+#define PCI_DVSEC_HEADER1		0x4 /* Designated Vendor-Specific Header1 */
+#define PCI_DVSEC_HEADER2		0x8 /* Designated Vendor-Specific Header2 */
 
 /* Data Link Feature */
 #define PCI_DLF_CAP		0x04	/* Capabilities Register */