Resguardo inicial

linux-7.2.3/drivers/virtio/Kconfig

@@ -0,0 +1,255 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config VIRTIO_ANCHOR
+	bool
+
+config VIRTIO
+	tristate
+	select VIRTIO_ANCHOR
+	help
+	  This option is selected by any driver which implements the virtio
+	  bus, such as CONFIG_VIRTIO_PCI, CONFIG_VIRTIO_MMIO, CONFIG_RPMSG
+	  or CONFIG_S390_GUEST.
+
+config VIRTIO_PCI_LIB
+	tristate
+	help
+	  Modern PCI device implementation. This module implements the
+	  basic probe and control for devices which are based on modern
+	  PCI device with possible vendor specific extensions. Any
+	  module that selects this module must depend on PCI.
+
+config VIRTIO_PCI_LIB_LEGACY
+	tristate
+	help
+	  Legacy PCI device (Virtio PCI Card 0.9.x Draft and older device)
+	  implementation.
+	  This module implements the basic probe and control for devices
+	  which are based on legacy PCI device. Any module that selects this
+	  module must depend on PCI.
+
+menuconfig VIRTIO_MENU
+	bool "Virtio drivers"
+	default y
+
+if VIRTIO_MENU
+
+config VIRTIO_HARDEN_NOTIFICATION
+        bool "Harden virtio notification"
+        depends on BROKEN
+        help
+          Enable this to harden the device notifications and suppress
+          those that happen at a time where notifications are illegal.
+
+          Experimental: Note that several drivers still have issues that
+          may cause crashes or hangs when correct handling of
+          notifications is enforced; depending on the subset of
+          drivers and devices you use, this may or may not work.
+
+          If unsure, say N.
+
+config VIRTIO_PCI
+	tristate "PCI driver for virtio devices"
+	depends on PCI
+	select VIRTIO_PCI_LIB
+	select VIRTIO
+	help
+	  This driver provides support for virtio based paravirtual device
+	  drivers over PCI.  This requires that your VMM has appropriate PCI
+	  virtio backends.  Most QEMU based VMMs should support these devices
+	  (like KVM or Xen).
+
+	  If unsure, say M.
+
+config VIRTIO_PCI_ADMIN_LEGACY
+	bool
+	depends on VIRTIO_PCI && (X86 || COMPILE_TEST)
+	default y
+
+config VIRTIO_PCI_LEGACY
+	bool "Support for legacy virtio draft 0.9.X and older devices"
+	default y
+	depends on VIRTIO_PCI
+	select VIRTIO_PCI_LIB_LEGACY
+	help
+          Virtio PCI Card 0.9.X Draft (circa 2014) and older device support.
+
+	  This option enables building a transitional driver, supporting
+	  both devices conforming to Virtio 1 specification, and legacy devices.
+	  If disabled, you get a slightly smaller, non-transitional driver,
+	  with no legacy compatibility.
+
+          So look out into your driveway.  Do you have a flying car?  If
+          so, you can happily disable this option and virtio will not
+          break.  Otherwise, leave it set.  Unless you're testing what
+          life will be like in The Future.
+
+	  If unsure, say Y.
+
+config VIRTIO_VDPA
+	tristate "vDPA driver for virtio devices"
+	depends on VDPA
+	select VIRTIO
+	help
+	  This driver provides support for virtio based paravirtual
+	  device driver over vDPA bus. For this to be useful, you need
+	  an appropriate vDPA device implementation that operates on a
+	  physical device to allow the datapath of virtio to be
+	  offloaded to hardware.
+
+	  If unsure, say M.
+
+config VIRTIO_PMEM
+	tristate "Support for virtio pmem driver"
+	depends on VIRTIO
+	depends on LIBNVDIMM
+	help
+	  This driver provides access to virtio-pmem devices, storage devices
+	  that are mapped into the physical address space - similar to NVDIMMs
+	   - with a virtio-based flushing interface.
+
+	  If unsure, say Y.
+
+config VIRTIO_BALLOON
+	tristate "Virtio balloon driver"
+	depends on VIRTIO
+	select BALLOON
+	select PAGE_REPORTING
+	help
+	 This driver supports increasing and decreasing the amount
+	 of memory within a KVM guest.
+
+	 If unsure, say M.
+
+config VIRTIO_MEM
+	tristate "Virtio mem driver"
+	depends on X86_64 || ARM64 || RISCV || S390
+	depends on VIRTIO
+	depends on MEMORY_HOTPLUG
+	depends on MEMORY_HOTREMOVE
+	depends on CONTIG_ALLOC
+	depends on EXCLUSIVE_SYSTEM_RAM
+	help
+	 This driver provides access to virtio-mem paravirtualized memory
+	 devices, allowing to hotplug and hotunplug memory.
+
+	 This driver currently supports x86-64, arm64, riscv and s390.
+	 Although it should compile on other architectures that implement
+	 memory hot(un)plug, architecture-specific and/or common
+	 code changes may be required for virtio-mem, kdump and kexec to
+	 work as expected.
+
+	 If unsure, say M.
+
+config VIRTIO_INPUT
+	tristate "Virtio input driver"
+	depends on VIRTIO
+	depends on INPUT
+	help
+	 This driver supports virtio input devices such as
+	 keyboards, mice and tablets.
+
+	 If unsure, say M.
+
+config VIRTIO_MMIO
+	tristate "Platform bus driver for memory mapped virtio devices"
+	depends on HAS_IOMEM && HAS_DMA
+	select VIRTIO
+	help
+	 This drivers provides support for memory mapped virtio
+	 platform device driver.
+
+ 	 If unsure, say N.
+
+config VIRTIO_MMIO_CMDLINE_DEVICES
+	bool "Memory mapped virtio devices parameter parsing"
+	depends on VIRTIO_MMIO
+	help
+	 Allow virtio-mmio devices instantiation via the kernel command line
+	 or module parameters. Be aware that using incorrect parameters (base
+	 address in particular) can crash your system - you have been warned.
+	 See Documentation/admin-guide/kernel-parameters.rst for details.
+
+	 If unsure, say 'N'.
+
+config VIRTIO_DMA_SHARED_BUFFER
+	tristate
+	depends on DMA_SHARED_BUFFER
+	help
+	 This option adds a flavor of dma buffers that are backed by
+	 virtio resources.
+
+config VIRTIO_DEBUG
+	bool "Debug facilities"
+	depends on VIRTIO
+	help
+	  Enable this to expose debug facilities over debugfs.
+	  This allows to debug features, to see what features the device
+	  advertises and to set filter for features used by driver.
+
+	  If unsure, say N.
+
+config VIRTIO_RTC
+	tristate "Virtio RTC driver"
+	depends on VIRTIO
+	depends on PTP_1588_CLOCK_OPTIONAL
+	help
+	 This driver provides current time from a Virtio RTC device. The driver
+	 provides the time through one or more clocks. The Virtio RTC PTP
+	 clocks and/or the Real Time Clock driver for Virtio RTC must be
+	 enabled to expose the clocks to userspace.
+
+	 To compile this code as a module, choose M here: the module will be
+	 called virtio_rtc.
+
+	 If unsure, say M.
+
+if VIRTIO_RTC
+
+comment "WARNING: Consider enabling VIRTIO_RTC_PTP and/or VIRTIO_RTC_CLASS."
+	depends on !VIRTIO_RTC_PTP && !VIRTIO_RTC_CLASS
+
+comment "Enable PTP_1588_CLOCK in order to enable VIRTIO_RTC_PTP."
+	depends on PTP_1588_CLOCK=n
+
+config VIRTIO_RTC_PTP
+	bool "Virtio RTC PTP clocks"
+	default y
+	depends on PTP_1588_CLOCK
+	help
+	 This exposes any Virtio RTC clocks as PTP Hardware Clocks (PHCs) to
+	 userspace. The PHC sysfs attribute "clock_name" describes the clock
+	 type.
+
+	 If unsure, say Y.
+
+config VIRTIO_RTC_ARM
+	bool "Virtio RTC cross-timestamping using Arm Generic Timer"
+	default y
+	depends on VIRTIO_RTC_PTP && ARM_ARCH_TIMER
+	help
+	 This enables Virtio RTC cross-timestamping using the Arm Generic Timer.
+	 It only has an effect if the Virtio RTC device also supports this. The
+	 cross-timestamp is available through the PTP clock driver precise
+	 cross-timestamp ioctl (PTP_SYS_OFFSET_PRECISE2 aka
+	 PTP_SYS_OFFSET_PRECISE).
+
+	 If unsure, say Y.
+
+comment "Enable RTC_CLASS in order to enable VIRTIO_RTC_CLASS."
+	depends on RTC_CLASS=n
+
+config VIRTIO_RTC_CLASS
+	bool "Real Time Clock driver for Virtio RTC"
+	default y
+	depends on RTC_CLASS
+	help
+	 This exposes the Virtio RTC UTC-like clock as a Linux Real Time Clock.
+	 It only has an effect if the Virtio RTC device has a UTC-like clock
+	 which smears leap seconds to avoid steps. The Real Time Clock is
+	 read-only, and may support setting an alarm.
+
+	 If unsure, say Y.
+
+endif # VIRTIO_RTC
+
+endif # VIRTIO_MENU

linux-7.2.3/drivers/virtio/Makefile

@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o
+obj-$(CONFIG_VIRTIO_ANCHOR) += virtio_anchor.o
+obj-$(CONFIG_VIRTIO_PCI_LIB) += virtio_pci_modern_dev.o
+obj-$(CONFIG_VIRTIO_PCI_LIB_LEGACY) += virtio_pci_legacy_dev.o
+obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
+obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
+virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o
+virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o
+virtio_pci-$(CONFIG_VIRTIO_PCI_ADMIN_LEGACY) += virtio_pci_admin_legacy_io.o
+obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
+obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o
+obj-$(CONFIG_VIRTIO_VDPA) += virtio_vdpa.o
+obj-$(CONFIG_VIRTIO_MEM) += virtio_mem.o
+obj-$(CONFIG_VIRTIO_DMA_SHARED_BUFFER) += virtio_dma_buf.o
+obj-$(CONFIG_VIRTIO_DEBUG) += virtio_debug.o
+obj-$(CONFIG_VIRTIO_RTC) += virtio_rtc.o
+virtio_rtc-y := virtio_rtc_driver.o
+virtio_rtc-$(CONFIG_VIRTIO_RTC_PTP) += virtio_rtc_ptp.o
+virtio_rtc-$(CONFIG_VIRTIO_RTC_ARM) += virtio_rtc_arm.o
+virtio_rtc-$(CONFIG_VIRTIO_RTC_CLASS) += virtio_rtc_class.o

linux-7.2.3/drivers/virtio/virtio.c

@@ -0,0 +1,739 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/virtio.h>
+#include <linux/spinlock.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_anchor.h>
+#include <linux/module.h>
+#include <linux/idr.h>
+#include <linux/of.h>
+#include <uapi/linux/virtio_ids.h>
+
+/* Unique numbering for virtio devices. */
+static DEFINE_IDA(virtio_index_ida);
+
+static ssize_t device_show(struct device *_d,
+			   struct device_attribute *attr, char *buf)
+{
+	struct virtio_device *dev = dev_to_virtio(_d);
+	return sysfs_emit(buf, "0x%04x\n", dev->id.device);
+}
+static DEVICE_ATTR_RO(device);
+
+static ssize_t vendor_show(struct device *_d,
+			   struct device_attribute *attr, char *buf)
+{
+	struct virtio_device *dev = dev_to_virtio(_d);
+	return sysfs_emit(buf, "0x%04x\n", dev->id.vendor);
+}
+static DEVICE_ATTR_RO(vendor);
+
+static ssize_t status_show(struct device *_d,
+			   struct device_attribute *attr, char *buf)
+{
+	struct virtio_device *dev = dev_to_virtio(_d);
+	return sysfs_emit(buf, "0x%08x\n", dev->config->get_status(dev));
+}
+static DEVICE_ATTR_RO(status);
+
+static ssize_t modalias_show(struct device *_d,
+			     struct device_attribute *attr, char *buf)
+{
+	struct virtio_device *dev = dev_to_virtio(_d);
+	return sysfs_emit(buf, "virtio:d%08Xv%08X\n",
+		       dev->id.device, dev->id.vendor);
+}
+static DEVICE_ATTR_RO(modalias);
+
+static ssize_t features_show(struct device *_d,
+			     struct device_attribute *attr, char *buf)
+{
+	struct virtio_device *dev = dev_to_virtio(_d);
+	unsigned int i;
+	ssize_t len = 0;
+
+	/* We actually represent this as a bitstring, as it could be
+	 * arbitrary length in future. */
+	for (i = 0; i < VIRTIO_FEATURES_BITS; i++)
+		len += sysfs_emit_at(buf, len, "%c",
+			       __virtio_test_bit(dev, i) ? '1' : '0');
+	len += sysfs_emit_at(buf, len, "\n");
+	return len;
+}
+static DEVICE_ATTR_RO(features);
+
+static struct attribute *virtio_dev_attrs[] = {
+	&dev_attr_device.attr,
+	&dev_attr_vendor.attr,
+	&dev_attr_status.attr,
+	&dev_attr_modalias.attr,
+	&dev_attr_features.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(virtio_dev);
+
+static inline int virtio_id_match(const struct virtio_device *dev,
+				  const struct virtio_device_id *id)
+{
+	if (id->device != dev->id.device && id->device != VIRTIO_DEV_ANY_ID)
+		return 0;
+
+	return id->vendor == VIRTIO_DEV_ANY_ID || id->vendor == dev->id.vendor;
+}
+
+/* This looks through all the IDs a driver claims to support.  If any of them
+ * match, we return 1 and the kernel will call virtio_dev_probe(). */
+static int virtio_dev_match(struct device *_dv, const struct device_driver *_dr)
+{
+	unsigned int i;
+	struct virtio_device *dev = dev_to_virtio(_dv);
+	const struct virtio_device_id *ids;
+
+	ids = drv_to_virtio(_dr)->id_table;
+	for (i = 0; ids[i].device; i++)
+		if (virtio_id_match(dev, &ids[i]))
+			return 1;
+	return 0;
+}
+
+static int virtio_uevent(const struct device *_dv, struct kobj_uevent_env *env)
+{
+	const struct virtio_device *dev = dev_to_virtio(_dv);
+
+	return add_uevent_var(env, "MODALIAS=virtio:d%08Xv%08X",
+			      dev->id.device, dev->id.vendor);
+}
+
+void virtio_check_driver_offered_feature(const struct virtio_device *vdev,
+					 unsigned int fbit)
+{
+	unsigned int i;
+	struct virtio_driver *drv = drv_to_virtio(vdev->dev.driver);
+
+	for (i = 0; i < drv->feature_table_size; i++)
+		if (drv->feature_table[i] == fbit)
+			return;
+
+	if (drv->feature_table_legacy) {
+		for (i = 0; i < drv->feature_table_size_legacy; i++)
+			if (drv->feature_table_legacy[i] == fbit)
+				return;
+	}
+
+	BUG();
+}
+EXPORT_SYMBOL_GPL(virtio_check_driver_offered_feature);
+
+static void __virtio_config_changed(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	if (!dev->config_core_enabled || dev->config_driver_disabled)
+		dev->config_change_pending = true;
+	else if (drv && drv->config_changed) {
+		drv->config_changed(dev);
+		dev->config_change_pending = false;
+	}
+}
+
+void virtio_config_changed(struct virtio_device *dev)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->config_lock, flags);
+	__virtio_config_changed(dev);
+	spin_unlock_irqrestore(&dev->config_lock, flags);
+}
+EXPORT_SYMBOL_GPL(virtio_config_changed);
+
+/**
+ * virtio_config_driver_disable - disable config change reporting by drivers
+ * @dev: the device to disable
+ *
+ * This is only allowed to be called by a driver and disabling can't
+ * be nested.
+ */
+void virtio_config_driver_disable(struct virtio_device *dev)
+{
+	spin_lock_irq(&dev->config_lock);
+	dev->config_driver_disabled = true;
+	spin_unlock_irq(&dev->config_lock);
+}
+EXPORT_SYMBOL_GPL(virtio_config_driver_disable);
+
+/**
+ * virtio_config_driver_enable - enable config change reporting by drivers
+ * @dev: the device to enable
+ *
+ * This is only allowed to be called by a driver and enabling can't
+ * be nested.
+ */
+void virtio_config_driver_enable(struct virtio_device *dev)
+{
+	spin_lock_irq(&dev->config_lock);
+	dev->config_driver_disabled = false;
+	if (dev->config_change_pending)
+		__virtio_config_changed(dev);
+	spin_unlock_irq(&dev->config_lock);
+}
+EXPORT_SYMBOL_GPL(virtio_config_driver_enable);
+
+static void virtio_config_core_disable(struct virtio_device *dev)
+{
+	spin_lock_irq(&dev->config_lock);
+	dev->config_core_enabled = false;
+	spin_unlock_irq(&dev->config_lock);
+}
+
+static void virtio_config_core_enable(struct virtio_device *dev)
+{
+	spin_lock_irq(&dev->config_lock);
+	dev->config_core_enabled = true;
+	if (dev->config_change_pending)
+		__virtio_config_changed(dev);
+	spin_unlock_irq(&dev->config_lock);
+}
+
+void virtio_add_status(struct virtio_device *dev, unsigned int status)
+{
+	might_sleep();
+	dev->config->set_status(dev, dev->config->get_status(dev) | status);
+}
+EXPORT_SYMBOL_GPL(virtio_add_status);
+
+/* Do some validation, then set FEATURES_OK */
+static int virtio_features_ok(struct virtio_device *dev)
+{
+	unsigned int status;
+
+	might_sleep();
+
+	if (virtio_check_mem_acc_cb(dev)) {
+		if (!virtio_has_feature(dev, VIRTIO_F_VERSION_1)) {
+			dev_warn(&dev->dev,
+				 "device must provide VIRTIO_F_VERSION_1\n");
+			return -ENODEV;
+		}
+
+		if (!virtio_has_feature(dev, VIRTIO_F_ACCESS_PLATFORM)) {
+			dev_warn(&dev->dev,
+				 "device must provide VIRTIO_F_ACCESS_PLATFORM\n");
+			return -ENODEV;
+		}
+	}
+
+	if (!virtio_has_feature(dev, VIRTIO_F_VERSION_1))
+		return 0;
+
+	virtio_add_status(dev, VIRTIO_CONFIG_S_FEATURES_OK);
+	status = dev->config->get_status(dev);
+	if (!(status & VIRTIO_CONFIG_S_FEATURES_OK)) {
+		dev_err(&dev->dev, "virtio: device refuses features: %x\n",
+			status);
+		return -ENODEV;
+	}
+	return 0;
+}
+
+/**
+ * virtio_reset_device - quiesce device for removal
+ * @dev: the device to reset
+ *
+ * Prevents device from sending interrupts and accessing memory.
+ *
+ * Generally used for cleanup during driver / device removal.
+ *
+ * Once this has been invoked, caller must ensure that
+ * virtqueue_notify / virtqueue_kick are not in progress.
+ *
+ * Note: this guarantees that vq callbacks are not in progress, however caller
+ * is responsible for preventing access from other contexts, such as a system
+ * call/workqueue/bh.  Invoking virtio_break_device then flushing any such
+ * contexts is one way to handle that.
+ * */
+void virtio_reset_device(struct virtio_device *dev)
+{
+#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
+	/*
+	 * The below virtio_synchronize_cbs() guarantees that any
+	 * interrupt for this line arriving after
+	 * virtio_synchronize_vqs() has completed is guaranteed to see
+	 * vq->broken as true.
+	 */
+	virtio_break_device(dev);
+	virtio_synchronize_cbs(dev);
+#endif
+
+	dev->config->reset(dev);
+}
+EXPORT_SYMBOL_GPL(virtio_reset_device);
+
+static int virtio_dev_probe(struct device *_d)
+{
+	int err, i;
+	struct virtio_device *dev = dev_to_virtio(_d);
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+	u64 device_features[VIRTIO_FEATURES_U64S];
+	u64 driver_features[VIRTIO_FEATURES_U64S];
+	u64 driver_features_legacy;
+
+	/* We have a driver! */
+	virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER);
+
+	/* Figure out what features the device supports. */
+	virtio_get_features(dev, device_features);
+
+	/* Figure out what features the driver supports. */
+	virtio_features_zero(driver_features);
+	for (i = 0; i < drv->feature_table_size; i++) {
+		unsigned int f = drv->feature_table[i];
+		if (!WARN_ON_ONCE(f >= VIRTIO_FEATURES_BITS))
+			virtio_features_set_bit(driver_features, f);
+	}
+
+	/* Some drivers have a separate feature table for virtio v1.0 */
+	if (drv->feature_table_legacy) {
+		driver_features_legacy = 0;
+		for (i = 0; i < drv->feature_table_size_legacy; i++) {
+			unsigned int f = drv->feature_table_legacy[i];
+			if (!WARN_ON_ONCE(f >= 64))
+				driver_features_legacy |= (1ULL << f);
+		}
+	} else {
+		driver_features_legacy = driver_features[0];
+	}
+
+	if (virtio_features_test_bit(device_features, VIRTIO_F_VERSION_1)) {
+		for (i = 0; i < VIRTIO_FEATURES_U64S; ++i)
+			dev->features_array[i] = driver_features[i] &
+						 device_features[i];
+	} else {
+		virtio_features_from_u64(dev->features_array,
+					 driver_features_legacy &
+					 device_features[0]);
+	}
+
+	/* When debugging, user may filter some features by hand. */
+	virtio_debug_device_filter_features(dev);
+
+	/* Transport features always preserved to pass to finalize_features. */
+	for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++)
+		if (virtio_features_test_bit(device_features, i))
+			__virtio_set_bit(dev, i);
+
+	err = dev->config->finalize_features(dev);
+	if (err)
+		goto err;
+
+	if (drv->validate) {
+		u64 features[VIRTIO_FEATURES_U64S];
+
+		virtio_features_copy(features, dev->features_array);
+		err = drv->validate(dev);
+		if (err)
+			goto err;
+
+		/* Did validation change any features? Then write them again. */
+		if (!virtio_features_equal(features, dev->features_array)) {
+			err = dev->config->finalize_features(dev);
+			if (err)
+				goto err;
+		}
+	}
+
+	err = virtio_features_ok(dev);
+	if (err)
+		goto err;
+
+	err = drv->probe(dev);
+	if (err)
+		goto err;
+
+	/* If probe didn't do it, mark device DRIVER_OK ourselves. */
+	if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK))
+		virtio_device_ready(dev);
+
+	if (drv->scan)
+		drv->scan(dev);
+
+	virtio_config_core_enable(dev);
+
+	return 0;
+
+err:
+	virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
+	return err;
+
+}
+
+static void virtio_dev_remove(struct device *_d)
+{
+	struct virtio_device *dev = dev_to_virtio(_d);
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	virtio_config_core_disable(dev);
+
+	drv->remove(dev);
+
+	/* Driver should have reset device. */
+	WARN_ON_ONCE(dev->config->get_status(dev));
+
+	/* Acknowledge the device's existence again. */
+	virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+
+	of_node_put(dev->dev.of_node);
+}
+
+/*
+ * virtio_irq_get_affinity - get IRQ affinity mask for device
+ * @_d: ptr to dev structure
+ * @irq_vec: interrupt vector number
+ *
+ * Return the CPU affinity mask for @_d and @irq_vec.
+ */
+static const struct cpumask *virtio_irq_get_affinity(struct device *_d,
+						     unsigned int irq_vec)
+{
+	struct virtio_device *dev = dev_to_virtio(_d);
+
+	if (!dev->config->get_vq_affinity)
+		return NULL;
+
+	return dev->config->get_vq_affinity(dev, irq_vec);
+}
+
+static void virtio_dev_shutdown(struct device *_d)
+{
+	struct virtio_device *dev = dev_to_virtio(_d);
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	/*
+	 * Stop accesses to or from the device.
+	 * We only need to do it if there's a driver - no accesses otherwise.
+	 */
+	if (!drv)
+		return;
+
+	/* If the driver has its own shutdown method, use that. */
+	if (drv->shutdown) {
+		drv->shutdown(dev);
+		return;
+	}
+
+	/*
+	 * Some devices get wedged if you kick them after they are
+	 * reset. Mark all vqs as broken to make sure we don't.
+	 */
+	virtio_break_device(dev);
+	/*
+	 * Guarantee that any callback will see vq->broken as true.
+	 */
+	virtio_synchronize_cbs(dev);
+	/*
+	 * As IOMMUs are reset on shutdown, this will block device access to memory.
+	 * Some devices get wedged if this happens, so reset to make sure it does not.
+	 */
+	dev->config->reset(dev);
+}
+
+static int virtio_dev_num_vf(struct device *dev)
+{
+	struct virtio_device *vdev = dev_to_virtio(dev);
+
+	return dev_num_vf(vdev->dev.parent);
+}
+
+
+static const struct bus_type virtio_bus = {
+	.name  = "virtio",
+	.match = virtio_dev_match,
+	.dev_groups = virtio_dev_groups,
+	.uevent = virtio_uevent,
+	.probe = virtio_dev_probe,
+	.remove = virtio_dev_remove,
+	.irq_get_affinity = virtio_irq_get_affinity,
+	.shutdown = virtio_dev_shutdown,
+	.num_vf = virtio_dev_num_vf,
+};
+
+int __register_virtio_driver(struct virtio_driver *driver, struct module *owner)
+{
+	/* Catch this early. */
+	BUG_ON(driver->feature_table_size && !driver->feature_table);
+	driver->driver.bus = &virtio_bus;
+	driver->driver.owner = owner;
+
+	return driver_register(&driver->driver);
+}
+EXPORT_SYMBOL_GPL(__register_virtio_driver);
+
+void unregister_virtio_driver(struct virtio_driver *driver)
+{
+	driver_unregister(&driver->driver);
+}
+EXPORT_SYMBOL_GPL(unregister_virtio_driver);
+
+static int virtio_device_of_init(struct virtio_device *dev)
+{
+	struct device_node *np, *pnode = dev_of_node(dev->dev.parent);
+	char compat[] = "virtio,deviceXXXXXXXX";
+	int ret, count;
+
+	if (!pnode)
+		return 0;
+
+	count = of_get_available_child_count(pnode);
+	if (!count)
+		return 0;
+
+	/* There can be only 1 child node */
+	if (WARN_ON(count > 1))
+		return -EINVAL;
+
+	np = of_get_next_available_child(pnode, NULL);
+	if (WARN_ON(!np))
+		return -ENODEV;
+
+	ret = snprintf(compat, sizeof(compat), "virtio,device%x", dev->id.device);
+	BUG_ON(ret >= sizeof(compat));
+
+	/*
+	 * On powerpc/pseries virtio devices are PCI devices so PCI
+	 * vendor/device ids play the role of the "compatible" property.
+	 * Simply don't init of_node in this case.
+	 */
+	if (!of_device_is_compatible(np, compat)) {
+		ret = 0;
+		goto out;
+	}
+
+	dev->dev.of_node = np;
+	return 0;
+
+out:
+	of_node_put(np);
+	return ret;
+}
+
+/**
+ * register_virtio_device - register virtio device
+ * @dev        : virtio device to be registered
+ *
+ * On error, the caller must call put_device on &@dev->dev (and not kfree),
+ * as another code path may have obtained a reference to @dev.
+ *
+ * Returns: 0 on success, -error on failure
+ */
+int register_virtio_device(struct virtio_device *dev)
+{
+	int err;
+
+	dev->dev.bus = &virtio_bus;
+	device_initialize(&dev->dev);
+
+	/* Assign a unique device index and hence name. */
+	err = ida_alloc(&virtio_index_ida, GFP_KERNEL);
+	if (err < 0)
+		goto out;
+
+	dev->index = err;
+	err = dev_set_name(&dev->dev, "virtio%u", dev->index);
+	if (err)
+		goto out_ida_remove;
+
+	err = virtio_device_of_init(dev);
+	if (err)
+		goto out_ida_remove;
+
+	spin_lock_init(&dev->config_lock);
+	dev->config_driver_disabled = false;
+	dev->config_core_enabled = false;
+	dev->config_change_pending = false;
+
+	INIT_LIST_HEAD(&dev->vqs);
+	spin_lock_init(&dev->vqs_list_lock);
+
+	/* We always start by resetting the device, in case a previous
+	 * driver messed it up.  This also tests that code path a little. */
+	virtio_reset_device(dev);
+
+	/* Acknowledge that we've seen the device. */
+	virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+
+	virtio_debug_device_init(dev);
+
+	/*
+	 * device_add() causes the bus infrastructure to look for a matching
+	 * driver.
+	 */
+	err = device_add(&dev->dev);
+	if (err)
+		goto out_of_node_put;
+
+	return 0;
+
+out_of_node_put:
+	of_node_put(dev->dev.of_node);
+out_ida_remove:
+	ida_free(&virtio_index_ida, dev->index);
+out:
+	virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
+	return err;
+}
+EXPORT_SYMBOL_GPL(register_virtio_device);
+
+bool is_virtio_device(struct device *dev)
+{
+	return dev->bus == &virtio_bus;
+}
+EXPORT_SYMBOL_GPL(is_virtio_device);
+
+void unregister_virtio_device(struct virtio_device *dev)
+{
+	int index = dev->index; /* save for after device release */
+
+	device_unregister(&dev->dev);
+	virtio_debug_device_exit(dev);
+	ida_free(&virtio_index_ida, index);
+}
+EXPORT_SYMBOL_GPL(unregister_virtio_device);
+
+static int virtio_device_restore_priv(struct virtio_device *dev, bool restore)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+	int ret;
+
+	/* We always start by resetting the device, in case a previous
+	 * driver messed it up. */
+	virtio_reset_device(dev);
+
+	/* Acknowledge that we've seen the device. */
+	virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+
+	/* Maybe driver failed before freeze.
+	 * Restore the failed status, for debugging. */
+	if (dev->failed)
+		virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
+
+	if (!drv)
+		return 0;
+
+	/* We have a driver! */
+	virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER);
+
+	ret = dev->config->finalize_features(dev);
+	if (ret)
+		goto err;
+
+	ret = virtio_features_ok(dev);
+	if (ret)
+		goto err;
+
+	if (restore) {
+		if (drv->restore) {
+			ret = drv->restore(dev);
+			if (ret)
+				goto err;
+		}
+	} else {
+		ret = drv->reset_done(dev);
+		if (ret)
+			goto err;
+	}
+
+	/* If restore didn't do it, mark device DRIVER_OK ourselves. */
+	if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK))
+		virtio_device_ready(dev);
+
+	virtio_config_core_enable(dev);
+
+	return 0;
+
+err:
+	virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
+	return ret;
+}
+
+#ifdef CONFIG_PM_SLEEP
+int virtio_device_freeze(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+	int ret;
+
+	virtio_config_core_disable(dev);
+
+	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
+
+	if (drv && drv->freeze) {
+		ret = drv->freeze(dev);
+		if (ret) {
+			virtio_config_core_enable(dev);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_device_freeze);
+
+int virtio_device_restore(struct virtio_device *dev)
+{
+	return virtio_device_restore_priv(dev, true);
+}
+EXPORT_SYMBOL_GPL(virtio_device_restore);
+#endif
+
+int virtio_device_reset_prepare(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+	int ret;
+
+	if (!drv || !drv->reset_prepare)
+		return -EOPNOTSUPP;
+
+	virtio_config_core_disable(dev);
+
+	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
+
+	ret = drv->reset_prepare(dev);
+	if (ret) {
+		virtio_config_core_enable(dev);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_device_reset_prepare);
+
+int virtio_device_reset_done(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	if (!drv || !drv->reset_done)
+		return -EOPNOTSUPP;
+
+	return virtio_device_restore_priv(dev, false);
+}
+EXPORT_SYMBOL_GPL(virtio_device_reset_done);
+
+static int virtio_init(void)
+{
+	BUILD_BUG_ON(offsetof(struct virtio_device, features) !=
+		     offsetof(struct virtio_device, features_array[0]));
+
+	if (bus_register(&virtio_bus) != 0)
+		panic("virtio bus registration failed");
+	virtio_debug_init();
+	return 0;
+}
+
+static void __exit virtio_exit(void)
+{
+	virtio_debug_exit();
+	bus_unregister(&virtio_bus);
+	ida_destroy(&virtio_index_ida);
+}
+core_initcall(virtio_init);
+module_exit(virtio_exit);
+
+MODULE_DESCRIPTION("Virtio core interface");
+MODULE_LICENSE("GPL");

linux-7.2.3/drivers/virtio/virtio_anchor.c

@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/virtio.h>
+#include <linux/virtio_anchor.h>
+
+bool virtio_require_restricted_mem_acc(struct virtio_device *dev)
+{
+	return true;
+}
+EXPORT_SYMBOL_GPL(virtio_require_restricted_mem_acc);
+
+static bool virtio_no_restricted_mem_acc(struct virtio_device *dev)
+{
+	return false;
+}
+
+bool (*virtio_check_mem_acc_cb)(struct virtio_device *dev) =
+	virtio_no_restricted_mem_acc;
+EXPORT_SYMBOL_GPL(virtio_check_mem_acc_cb);

linux-7.2.3/drivers/virtio/virtio_debug.c

@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/debugfs.h>
+
+static struct dentry *virtio_debugfs_dir;
+
+static int virtio_debug_device_features_show(struct seq_file *s, void *data)
+{
+	u64 device_features[VIRTIO_FEATURES_U64S];
+	struct virtio_device *dev = s->private;
+	unsigned int i;
+
+	virtio_get_features(dev, device_features);
+	for (i = 0; i < VIRTIO_FEATURES_BITS; i++) {
+		if (virtio_features_test_bit(device_features, i))
+			seq_printf(s, "%u\n", i);
+	}
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(virtio_debug_device_features);
+
+static int virtio_debug_filter_features_show(struct seq_file *s, void *data)
+{
+	struct virtio_device *dev = s->private;
+	unsigned int i;
+
+	for (i = 0; i < VIRTIO_FEATURES_BITS; i++) {
+		if (virtio_features_test_bit(dev->debugfs_filter_features, i))
+			seq_printf(s, "%u\n", i);
+	}
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(virtio_debug_filter_features);
+
+static int virtio_debug_filter_features_clear(void *data, u64 val)
+{
+	struct virtio_device *dev = data;
+
+	if (val == 1)
+		virtio_features_zero(dev->debugfs_filter_features);
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(virtio_debug_filter_features_clear_fops, NULL,
+			 virtio_debug_filter_features_clear, "%llu\n");
+
+static int virtio_debug_filter_feature_add(void *data, u64 val)
+{
+	struct virtio_device *dev = data;
+
+	if (val >= VIRTIO_FEATURES_BITS)
+		return -EINVAL;
+
+	virtio_features_set_bit(dev->debugfs_filter_features, val);
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(virtio_debug_filter_feature_add_fops, NULL,
+			 virtio_debug_filter_feature_add, "%llu\n");
+
+static int virtio_debug_filter_feature_del(void *data, u64 val)
+{
+	struct virtio_device *dev = data;
+
+	if (val >= VIRTIO_FEATURES_BITS)
+		return -EINVAL;
+
+	virtio_features_clear_bit(dev->debugfs_filter_features, val);
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(virtio_debug_filter_feature_del_fops, NULL,
+			 virtio_debug_filter_feature_del, "%llu\n");
+
+void virtio_debug_device_init(struct virtio_device *dev)
+{
+	dev->debugfs_dir = debugfs_create_dir(dev_name(&dev->dev),
+					      virtio_debugfs_dir);
+	debugfs_create_file("device_features", 0400, dev->debugfs_dir, dev,
+			    &virtio_debug_device_features_fops);
+	debugfs_create_file("filter_features", 0400, dev->debugfs_dir, dev,
+			    &virtio_debug_filter_features_fops);
+	debugfs_create_file("filter_features_clear", 0200, dev->debugfs_dir, dev,
+			    &virtio_debug_filter_features_clear_fops);
+	debugfs_create_file("filter_feature_add", 0200, dev->debugfs_dir, dev,
+			    &virtio_debug_filter_feature_add_fops);
+	debugfs_create_file("filter_feature_del", 0200, dev->debugfs_dir, dev,
+			    &virtio_debug_filter_feature_del_fops);
+}
+EXPORT_SYMBOL_GPL(virtio_debug_device_init);
+
+void virtio_debug_device_filter_features(struct virtio_device *dev)
+{
+	virtio_features_andnot(dev->features_array, dev->features_array,
+			       dev->debugfs_filter_features);
+}
+EXPORT_SYMBOL_GPL(virtio_debug_device_filter_features);
+
+void virtio_debug_device_exit(struct virtio_device *dev)
+{
+	debugfs_remove_recursive(dev->debugfs_dir);
+}
+EXPORT_SYMBOL_GPL(virtio_debug_device_exit);
+
+void virtio_debug_init(void)
+{
+	virtio_debugfs_dir = debugfs_create_dir("virtio", NULL);
+}
+EXPORT_SYMBOL_GPL(virtio_debug_init);
+
+void virtio_debug_exit(void)
+{
+	debugfs_remove_recursive(virtio_debugfs_dir);
+}
+EXPORT_SYMBOL_GPL(virtio_debug_exit);

linux-7.2.3/drivers/virtio/virtio_dma_buf.c

@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * dma-bufs for virtio exported objects
+ *
+ * Copyright (C) 2020 Google, Inc.
+ */
+
+#include <linux/module.h>
+#include <linux/virtio_dma_buf.h>
+
+/**
+ * virtio_dma_buf_export - Creates a new dma-buf for a virtio exported object
+ * @exp_info: [in] see dma_buf_export(). ops MUST refer to a dma_buf_ops
+ *	struct embedded in a virtio_dma_buf_ops.
+ *
+ * This wraps dma_buf_export() to allow virtio drivers to create a dma-buf
+ * for an virtio exported object that can be queried by other virtio drivers
+ * for the object's UUID.
+ */
+struct dma_buf *virtio_dma_buf_export
+	(const struct dma_buf_export_info *exp_info)
+{
+	const struct virtio_dma_buf_ops *virtio_ops =
+		container_of(exp_info->ops,
+			     const struct virtio_dma_buf_ops, ops);
+
+	if (!exp_info->ops ||
+	    exp_info->ops->attach != &virtio_dma_buf_attach ||
+	    !virtio_ops->get_uuid) {
+		return ERR_PTR(-EINVAL);
+	}
+
+	return dma_buf_export(exp_info);
+}
+EXPORT_SYMBOL(virtio_dma_buf_export);
+
+/**
+ * virtio_dma_buf_attach - mandatory attach callback for virtio dma-bufs
+ * @dma_buf: [in] buffer to attach
+ * @attach: [in] attachment structure
+ */
+int virtio_dma_buf_attach(struct dma_buf *dma_buf,
+			  struct dma_buf_attachment *attach)
+{
+	int ret;
+	const struct virtio_dma_buf_ops *ops =
+		container_of(dma_buf->ops,
+			     const struct virtio_dma_buf_ops, ops);
+
+	if (ops->device_attach) {
+		ret = ops->device_attach(dma_buf, attach);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(virtio_dma_buf_attach);
+
+/**
+ * is_virtio_dma_buf - returns true if the given dma-buf is a virtio dma-buf
+ * @dma_buf: buffer to query
+ */
+bool is_virtio_dma_buf(struct dma_buf *dma_buf)
+{
+	return dma_buf->ops->attach == &virtio_dma_buf_attach;
+}
+EXPORT_SYMBOL(is_virtio_dma_buf);
+
+/**
+ * virtio_dma_buf_get_uuid - gets a virtio dma-buf's exported object's uuid
+ * @dma_buf: [in] buffer to query
+ * @uuid: [out] the uuid
+ *
+ * Returns: 0 on success, negative on failure.
+ */
+int virtio_dma_buf_get_uuid(struct dma_buf *dma_buf,
+			    uuid_t *uuid)
+{
+	const struct virtio_dma_buf_ops *ops =
+		container_of(dma_buf->ops,
+			     const struct virtio_dma_buf_ops, ops);
+
+	if (!is_virtio_dma_buf(dma_buf))
+		return -EINVAL;
+
+	return ops->get_uuid(dma_buf, uuid);
+}
+EXPORT_SYMBOL(virtio_dma_buf_get_uuid);
+
+MODULE_DESCRIPTION("dma-bufs for virtio exported objects");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS("DMA_BUF");

linux-7.2.3/drivers/virtio/virtio_input.c

@@ -0,0 +1,421 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/module.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/input.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+
+#include <uapi/linux/virtio_ids.h>
+#include <uapi/linux/virtio_input.h>
+#include <linux/input/mt.h>
+
+struct virtio_input {
+	struct virtio_device       *vdev;
+	struct input_dev           *idev;
+	char                       name[64];
+	char                       serial[64];
+	char                       phys[64];
+	struct virtqueue           *evt, *sts;
+	__dma_from_device_group_begin();
+	struct virtio_input_event  evts[64];
+	__dma_from_device_group_end();
+	spinlock_t                 lock;
+	bool                       ready;
+};
+
+static void virtinput_queue_evtbuf(struct virtio_input *vi,
+				   struct virtio_input_event *evtbuf)
+{
+	struct scatterlist sg[1];
+
+	sg_init_one(sg, evtbuf, sizeof(*evtbuf));
+	virtqueue_add_inbuf_cache_clean(vi->evt, sg, 1, evtbuf, GFP_ATOMIC);
+}
+
+static void virtinput_recv_events(struct virtqueue *vq)
+{
+	struct virtio_input *vi = vq->vdev->priv;
+	struct virtio_input_event *event;
+	unsigned long flags;
+	unsigned int len;
+
+	spin_lock_irqsave(&vi->lock, flags);
+	if (vi->ready) {
+		while ((event = virtqueue_get_buf(vi->evt, &len)) != NULL) {
+			spin_unlock_irqrestore(&vi->lock, flags);
+			input_event(vi->idev,
+				    le16_to_cpu(event->type),
+				    le16_to_cpu(event->code),
+				    le32_to_cpu(event->value));
+			spin_lock_irqsave(&vi->lock, flags);
+			virtinput_queue_evtbuf(vi, event);
+		}
+		virtqueue_kick(vq);
+	}
+	spin_unlock_irqrestore(&vi->lock, flags);
+}
+
+/*
+ * On error we are losing the status update, which isn't critical as
+ * this is typically used for stuff like keyboard leds.
+ */
+static int virtinput_send_status(struct virtio_input *vi,
+				 u16 type, u16 code, s32 value)
+{
+	struct virtio_input_event *stsbuf;
+	struct scatterlist sg[1];
+	unsigned long flags;
+	int rc;
+
+	/*
+	 * Since 29cc309d8bf1 (HID: hid-multitouch: forward MSC_TIMESTAMP),
+	 * EV_MSC/MSC_TIMESTAMP is added to each before EV_SYN event.
+	 * EV_MSC is configured as INPUT_PASS_TO_ALL.
+	 * In case of touch device:
+	 *   BE pass EV_MSC/MSC_TIMESTAMP to FE on receiving event from evdev.
+	 *   FE pass EV_MSC/MSC_TIMESTAMP back to BE.
+	 *   BE writes EV_MSC/MSC_TIMESTAMP to evdev due to INPUT_PASS_TO_ALL.
+	 *   BE receives extra EV_MSC/MSC_TIMESTAMP and pass to FE.
+	 *   >>> Each new frame becomes larger and larger.
+	 * Disable EV_MSC/MSC_TIMESTAMP forwarding for MT.
+	 */
+	if (vi->idev->mt && type == EV_MSC && code == MSC_TIMESTAMP)
+		return 0;
+
+	stsbuf = kzalloc_obj(*stsbuf, GFP_ATOMIC);
+	if (!stsbuf)
+		return -ENOMEM;
+
+	stsbuf->type  = cpu_to_le16(type);
+	stsbuf->code  = cpu_to_le16(code);
+	stsbuf->value = cpu_to_le32(value);
+	sg_init_one(sg, stsbuf, sizeof(*stsbuf));
+
+	spin_lock_irqsave(&vi->lock, flags);
+	if (vi->ready) {
+		rc = virtqueue_add_outbuf(vi->sts, sg, 1, stsbuf, GFP_ATOMIC);
+		virtqueue_kick(vi->sts);
+	} else {
+		rc = -ENODEV;
+	}
+	spin_unlock_irqrestore(&vi->lock, flags);
+
+	if (rc != 0)
+		kfree(stsbuf);
+	return rc;
+}
+
+static void virtinput_recv_status(struct virtqueue *vq)
+{
+	struct virtio_input *vi = vq->vdev->priv;
+	struct virtio_input_event *stsbuf;
+	unsigned long flags;
+	unsigned int len;
+
+	spin_lock_irqsave(&vi->lock, flags);
+	while ((stsbuf = virtqueue_get_buf(vi->sts, &len)) != NULL)
+		kfree(stsbuf);
+	spin_unlock_irqrestore(&vi->lock, flags);
+}
+
+static int virtinput_status(struct input_dev *idev, unsigned int type,
+			    unsigned int code, int value)
+{
+	struct virtio_input *vi = input_get_drvdata(idev);
+
+	return virtinput_send_status(vi, type, code, value);
+}
+
+static u8 virtinput_cfg_select(struct virtio_input *vi,
+			       u8 select, u8 subsel)
+{
+	u8 size;
+
+	virtio_cwrite_le(vi->vdev, struct virtio_input_config, select, &select);
+	virtio_cwrite_le(vi->vdev, struct virtio_input_config, subsel, &subsel);
+	virtio_cread_le(vi->vdev, struct virtio_input_config, size, &size);
+	return size;
+}
+
+static void virtinput_cfg_bits(struct virtio_input *vi, int select, int subsel,
+			       unsigned long *bits, unsigned int bitcount)
+{
+	unsigned int bit;
+	u8 *virtio_bits;
+	u8 bytes;
+
+	bytes = virtinput_cfg_select(vi, select, subsel);
+	if (!bytes)
+		return;
+	if (bitcount > bytes * 8)
+		bitcount = bytes * 8;
+
+	/*
+	 * Bitmap in virtio config space is a simple stream of bytes,
+	 * with the first byte carrying bits 0-7, second bits 8-15 and
+	 * so on.
+	 */
+	virtio_bits = kzalloc(bytes, GFP_KERNEL);
+	if (!virtio_bits)
+		return;
+	virtio_cread_bytes(vi->vdev, offsetof(struct virtio_input_config,
+					      u.bitmap),
+			   virtio_bits, bytes);
+	for (bit = 0; bit < bitcount; bit++) {
+		if (virtio_bits[bit / 8] & (1 << (bit % 8)))
+			__set_bit(bit, bits);
+	}
+	kfree(virtio_bits);
+
+	if (select == VIRTIO_INPUT_CFG_EV_BITS)
+		__set_bit(subsel, vi->idev->evbit);
+}
+
+static void virtinput_cfg_abs(struct virtio_input *vi, int abs)
+{
+	u32 mi, ma, re, fu, fl;
+
+	virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_ABS_INFO, abs);
+	virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.min, &mi);
+	virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.max, &ma);
+	virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.res, &re);
+	virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.fuzz, &fu);
+	virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.flat, &fl);
+	input_set_abs_params(vi->idev, abs, mi, ma, fu, fl);
+	input_abs_set_res(vi->idev, abs, re);
+}
+
+static int virtinput_init_vqs(struct virtio_input *vi)
+{
+	struct virtqueue_info vqs_info[] = {
+		{ "events", virtinput_recv_events },
+		{ "status", virtinput_recv_status },
+	};
+	struct virtqueue *vqs[2];
+	int err;
+
+	err = virtio_find_vqs(vi->vdev, 2, vqs, vqs_info, NULL);
+	if (err)
+		return err;
+	vi->evt = vqs[0];
+	vi->sts = vqs[1];
+
+	return 0;
+}
+
+static void virtinput_fill_evt(struct virtio_input *vi)
+{
+	unsigned long flags;
+	int i, size;
+
+	spin_lock_irqsave(&vi->lock, flags);
+	size = virtqueue_get_vring_size(vi->evt);
+	if (size > ARRAY_SIZE(vi->evts))
+		size = ARRAY_SIZE(vi->evts);
+	for (i = 0; i < size; i++)
+		virtinput_queue_evtbuf(vi, &vi->evts[i]);
+	virtqueue_kick(vi->evt);
+	spin_unlock_irqrestore(&vi->lock, flags);
+}
+
+static int virtinput_probe(struct virtio_device *vdev)
+{
+	struct virtio_input *vi;
+	unsigned long flags;
+	size_t size;
+	int abs, err, nslots;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
+		return -ENODEV;
+
+	vi = kzalloc_obj(*vi);
+	if (!vi)
+		return -ENOMEM;
+
+	vdev->priv = vi;
+	vi->vdev = vdev;
+	spin_lock_init(&vi->lock);
+
+	err = virtinput_init_vqs(vi);
+	if (err)
+		goto err_init_vq;
+
+	vi->idev = input_allocate_device();
+	if (!vi->idev) {
+		err = -ENOMEM;
+		goto err_input_alloc;
+	}
+	input_set_drvdata(vi->idev, vi);
+
+	size = virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_ID_NAME, 0);
+	virtio_cread_bytes(vi->vdev, offsetof(struct virtio_input_config,
+					      u.string),
+			   vi->name, min(size, sizeof(vi->name)));
+	size = virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_ID_SERIAL, 0);
+	virtio_cread_bytes(vi->vdev, offsetof(struct virtio_input_config,
+					      u.string),
+			   vi->serial, min(size, sizeof(vi->serial)));
+	snprintf(vi->phys, sizeof(vi->phys),
+		 "virtio%d/input0", vdev->index);
+	vi->idev->name = vi->name;
+	vi->idev->phys = vi->phys;
+	vi->idev->uniq = vi->serial;
+
+	size = virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_ID_DEVIDS, 0);
+	if (size >= sizeof(struct virtio_input_devids)) {
+		virtio_cread_le(vi->vdev, struct virtio_input_config,
+				u.ids.bustype, &vi->idev->id.bustype);
+		virtio_cread_le(vi->vdev, struct virtio_input_config,
+				u.ids.vendor, &vi->idev->id.vendor);
+		virtio_cread_le(vi->vdev, struct virtio_input_config,
+				u.ids.product, &vi->idev->id.product);
+		virtio_cread_le(vi->vdev, struct virtio_input_config,
+				u.ids.version, &vi->idev->id.version);
+	} else {
+		vi->idev->id.bustype = BUS_VIRTUAL;
+	}
+
+	virtinput_cfg_bits(vi, VIRTIO_INPUT_CFG_PROP_BITS, 0,
+			   vi->idev->propbit, INPUT_PROP_CNT);
+	size = virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_EV_BITS, EV_REP);
+	if (size)
+		__set_bit(EV_REP, vi->idev->evbit);
+
+	vi->idev->dev.parent = &vdev->dev;
+	vi->idev->event = virtinput_status;
+
+	/* device -> kernel */
+	virtinput_cfg_bits(vi, VIRTIO_INPUT_CFG_EV_BITS, EV_KEY,
+			   vi->idev->keybit, KEY_CNT);
+	virtinput_cfg_bits(vi, VIRTIO_INPUT_CFG_EV_BITS, EV_REL,
+			   vi->idev->relbit, REL_CNT);
+	virtinput_cfg_bits(vi, VIRTIO_INPUT_CFG_EV_BITS, EV_ABS,
+			   vi->idev->absbit, ABS_CNT);
+	virtinput_cfg_bits(vi, VIRTIO_INPUT_CFG_EV_BITS, EV_MSC,
+			   vi->idev->mscbit, MSC_CNT);
+	virtinput_cfg_bits(vi, VIRTIO_INPUT_CFG_EV_BITS, EV_SW,
+			   vi->idev->swbit,  SW_CNT);
+
+	/* kernel -> device */
+	virtinput_cfg_bits(vi, VIRTIO_INPUT_CFG_EV_BITS, EV_LED,
+			   vi->idev->ledbit, LED_CNT);
+	virtinput_cfg_bits(vi, VIRTIO_INPUT_CFG_EV_BITS, EV_SND,
+			   vi->idev->sndbit, SND_CNT);
+
+	if (test_bit(EV_ABS, vi->idev->evbit)) {
+		for (abs = 0; abs < ABS_CNT; abs++) {
+			if (!test_bit(abs, vi->idev->absbit))
+				continue;
+			virtinput_cfg_abs(vi, abs);
+		}
+
+		if (test_bit(ABS_MT_SLOT, vi->idev->absbit)) {
+			nslots = input_abs_get_max(vi->idev, ABS_MT_SLOT) + 1;
+			err = input_mt_init_slots(vi->idev, nslots, 0);
+			if (err)
+				goto err_mt_init_slots;
+		}
+	}
+
+	virtio_device_ready(vdev);
+	vi->ready = true;
+	err = input_register_device(vi->idev);
+	if (err)
+		goto err_input_register;
+
+	virtinput_fill_evt(vi);
+	return 0;
+
+err_input_register:
+	spin_lock_irqsave(&vi->lock, flags);
+	vi->ready = false;
+	spin_unlock_irqrestore(&vi->lock, flags);
+err_mt_init_slots:
+	input_free_device(vi->idev);
+err_input_alloc:
+	vdev->config->del_vqs(vdev);
+err_init_vq:
+	kfree(vi);
+	return err;
+}
+
+static void virtinput_remove(struct virtio_device *vdev)
+{
+	struct virtio_input *vi = vdev->priv;
+	void *buf;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vi->lock, flags);
+	vi->ready = false;
+	spin_unlock_irqrestore(&vi->lock, flags);
+
+	input_unregister_device(vi->idev);
+	virtio_reset_device(vdev);
+	while ((buf = virtqueue_detach_unused_buf(vi->sts)) != NULL)
+		kfree(buf);
+	vdev->config->del_vqs(vdev);
+	kfree(vi);
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int virtinput_freeze(struct virtio_device *vdev)
+{
+	struct virtio_input *vi = vdev->priv;
+	unsigned long flags;
+	void *buf;
+
+	spin_lock_irqsave(&vi->lock, flags);
+	vi->ready = false;
+	spin_unlock_irqrestore(&vi->lock, flags);
+
+	virtio_reset_device(vdev);
+	while ((buf = virtqueue_detach_unused_buf(vi->sts)) != NULL)
+		kfree(buf);
+	vdev->config->del_vqs(vdev);
+	return 0;
+}
+
+static int virtinput_restore(struct virtio_device *vdev)
+{
+	struct virtio_input *vi = vdev->priv;
+	int err;
+
+	err = virtinput_init_vqs(vi);
+	if (err)
+		return err;
+
+	virtio_device_ready(vdev);
+	vi->ready = true;
+	virtinput_fill_evt(vi);
+	return 0;
+}
+#endif
+
+static unsigned int features[] = {
+	/* none */
+};
+static const struct virtio_device_id id_table[] = {
+	{ VIRTIO_ID_INPUT, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+
+static struct virtio_driver virtio_input_driver = {
+	.driver.name         = KBUILD_MODNAME,
+	.feature_table       = features,
+	.feature_table_size  = ARRAY_SIZE(features),
+	.id_table            = id_table,
+	.probe               = virtinput_probe,
+	.remove              = virtinput_remove,
+#ifdef CONFIG_PM_SLEEP
+	.freeze	             = virtinput_freeze,
+	.restore             = virtinput_restore,
+#endif
+};
+
+module_virtio_driver(virtio_input_driver);
+MODULE_DEVICE_TABLE(virtio, id_table);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Virtio input device driver");
+MODULE_AUTHOR("Gerd Hoffmann <kraxel@redhat.com>");

linux-7.2.3/drivers/virtio/virtio_mmio.c

@@ -0,0 +1,829 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Virtio memory mapped device driver
+ *
+ * Copyright 2011-2014, ARM Ltd.
+ *
+ * This module allows virtio devices to be used over a virtual, memory mapped
+ * platform device.
+ *
+ * The guest device(s) may be instantiated in one of three equivalent ways:
+ *
+ * 1. Static platform device in board's code, eg.:
+ *
+ *	static struct platform_device v2m_virtio_device = {
+ *		.name = "virtio-mmio",
+ *		.id = -1,
+ *		.num_resources = 2,
+ *		.resource = (struct resource []) {
+ *			{
+ *				.start = 0x1001e000,
+ *				.end = 0x1001e0ff,
+ *				.flags = IORESOURCE_MEM,
+ *			}, {
+ *				.start = 42 + 32,
+ *				.end = 42 + 32,
+ *				.flags = IORESOURCE_IRQ,
+ *			},
+ *		}
+ *	};
+ *
+ * 2. Device Tree node, eg.:
+ *
+ *		virtio_block@1e000 {
+ *			compatible = "virtio,mmio";
+ *			reg = <0x1e000 0x100>;
+ *			interrupts = <42>;
+ *		}
+ *
+ * 3. Kernel module (or command line) parameter. Can be used more than once -
+ *    one device will be created for each one. Syntax:
+ *
+ *		[virtio_mmio.]device=<size>@<baseaddr>:<irq>[:<id>]
+ *    where:
+ *		<size>     := size (can use standard suffixes like K, M or G)
+ *		<baseaddr> := physical base address
+ *		<irq>      := interrupt number (as passed to request_irq())
+ *		<id>       := (optional) platform device id
+ *    eg.:
+ *		virtio_mmio.device=0x100@0x100b0000:48 \
+ *				virtio_mmio.device=1K@0x1001e000:74
+ *
+ * Based on Virtio PCI driver by Anthony Liguori, copyright IBM Corp. 2007
+ */
+
+#define pr_fmt(fmt) "virtio-mmio: " fmt
+
+#include <linux/acpi.h>
+#include <linux/dma-mapping.h>
+#include <linux/highmem.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/slab.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <uapi/linux/virtio_mmio.h>
+#include <linux/virtio_ring.h>
+
+
+
+/* The alignment to use between consumer and producer parts of vring.
+ * Currently hardcoded to the page size. */
+#define VIRTIO_MMIO_VRING_ALIGN		PAGE_SIZE
+
+
+
+#define to_virtio_mmio_device(_plat_dev) \
+	container_of(_plat_dev, struct virtio_mmio_device, vdev)
+
+struct virtio_mmio_device {
+	struct virtio_device vdev;
+	struct platform_device *pdev;
+
+	void __iomem *base;
+	unsigned long version;
+};
+
+/* Configuration interface */
+
+static u64 vm_get_features(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	u64 features;
+
+	writel(1, vm_dev->base + VIRTIO_MMIO_DEVICE_FEATURES_SEL);
+	features = readl(vm_dev->base + VIRTIO_MMIO_DEVICE_FEATURES);
+	features <<= 32;
+
+	writel(0, vm_dev->base + VIRTIO_MMIO_DEVICE_FEATURES_SEL);
+	features |= readl(vm_dev->base + VIRTIO_MMIO_DEVICE_FEATURES);
+
+	return features;
+}
+
+static int vm_finalize_features(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	/* Give virtio_ring a chance to accept features. */
+	vring_transport_features(vdev);
+
+	/* Make sure there are no mixed devices */
+	if (vm_dev->version == 2 &&
+			!__virtio_test_bit(vdev, VIRTIO_F_VERSION_1)) {
+		dev_err(&vdev->dev, "New virtio-mmio devices (version 2) must provide VIRTIO_F_VERSION_1 feature!\n");
+		return -EINVAL;
+	}
+
+	writel(1, vm_dev->base + VIRTIO_MMIO_DRIVER_FEATURES_SEL);
+	writel((u32)(vdev->features >> 32),
+			vm_dev->base + VIRTIO_MMIO_DRIVER_FEATURES);
+
+	writel(0, vm_dev->base + VIRTIO_MMIO_DRIVER_FEATURES_SEL);
+	writel((u32)vdev->features,
+			vm_dev->base + VIRTIO_MMIO_DRIVER_FEATURES);
+
+	return 0;
+}
+
+static void vm_get(struct virtio_device *vdev, unsigned int offset,
+		   void *buf, unsigned int len)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	void __iomem *base = vm_dev->base + VIRTIO_MMIO_CONFIG;
+	u8 b;
+	__le16 w;
+	__le32 l;
+
+	if (vm_dev->version == 1) {
+		u8 *ptr = buf;
+		int i;
+
+		for (i = 0; i < len; i++)
+			ptr[i] = readb(base + offset + i);
+		return;
+	}
+
+	switch (len) {
+	case 1:
+		b = readb(base + offset);
+		memcpy(buf, &b, sizeof b);
+		break;
+	case 2:
+		w = cpu_to_le16(readw(base + offset));
+		memcpy(buf, &w, sizeof w);
+		break;
+	case 4:
+		l = cpu_to_le32(readl(base + offset));
+		memcpy(buf, &l, sizeof l);
+		break;
+	case 8:
+		l = cpu_to_le32(readl(base + offset));
+		memcpy(buf, &l, sizeof l);
+		l = cpu_to_le32(ioread32(base + offset + sizeof l));
+		memcpy(buf + sizeof l, &l, sizeof l);
+		break;
+	default:
+		BUG();
+	}
+}
+
+static void vm_set(struct virtio_device *vdev, unsigned int offset,
+		   const void *buf, unsigned int len)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	void __iomem *base = vm_dev->base + VIRTIO_MMIO_CONFIG;
+	u8 b;
+	__le16 w;
+	__le32 l;
+
+	if (vm_dev->version == 1) {
+		const u8 *ptr = buf;
+		int i;
+
+		for (i = 0; i < len; i++)
+			writeb(ptr[i], base + offset + i);
+
+		return;
+	}
+
+	switch (len) {
+	case 1:
+		memcpy(&b, buf, sizeof b);
+		writeb(b, base + offset);
+		break;
+	case 2:
+		memcpy(&w, buf, sizeof w);
+		writew(le16_to_cpu(w), base + offset);
+		break;
+	case 4:
+		memcpy(&l, buf, sizeof l);
+		writel(le32_to_cpu(l), base + offset);
+		break;
+	case 8:
+		memcpy(&l, buf, sizeof l);
+		writel(le32_to_cpu(l), base + offset);
+		memcpy(&l, buf + sizeof l, sizeof l);
+		writel(le32_to_cpu(l), base + offset + sizeof l);
+		break;
+	default:
+		BUG();
+	}
+}
+
+static u32 vm_generation(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	if (vm_dev->version == 1)
+		return 0;
+	else
+		return readl(vm_dev->base + VIRTIO_MMIO_CONFIG_GENERATION);
+}
+
+static u8 vm_get_status(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	return readl(vm_dev->base + VIRTIO_MMIO_STATUS) & 0xff;
+}
+
+static void vm_set_status(struct virtio_device *vdev, u8 status)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	/* We should never be setting status to 0. */
+	BUG_ON(status == 0);
+
+	/*
+	 * Per memory-barriers.txt, wmb() is not needed to guarantee
+	 * that the cache coherent memory writes have completed
+	 * before writing to the MMIO region.
+	 */
+	writel(status, vm_dev->base + VIRTIO_MMIO_STATUS);
+}
+
+static void vm_reset(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	/* 0 status means a reset. */
+	writel(0, vm_dev->base + VIRTIO_MMIO_STATUS);
+}
+
+
+
+/* Transport interface */
+
+/* the notify function used when creating a virt queue */
+static bool vm_notify(struct virtqueue *vq)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
+
+	/* We write the queue's selector into the notification register to
+	 * signal the other end */
+	writel(vq->index, vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY);
+	return true;
+}
+
+static bool vm_notify_with_data(struct virtqueue *vq)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
+	u32 data = vring_notification_data(vq);
+
+	writel(data, vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY);
+
+	return true;
+}
+
+/* Notify all virtqueues on an interrupt. */
+static irqreturn_t vm_interrupt(int irq, void *opaque)
+{
+	struct virtio_mmio_device *vm_dev = opaque;
+	struct virtqueue *vq;
+	unsigned long status;
+	irqreturn_t ret = IRQ_NONE;
+
+	/* Read and acknowledge interrupts */
+	status = readl(vm_dev->base + VIRTIO_MMIO_INTERRUPT_STATUS);
+	writel(status, vm_dev->base + VIRTIO_MMIO_INTERRUPT_ACK);
+
+	if (unlikely(status & VIRTIO_MMIO_INT_CONFIG)) {
+		virtio_config_changed(&vm_dev->vdev);
+		ret = IRQ_HANDLED;
+	}
+
+	if (likely(status & VIRTIO_MMIO_INT_VRING)) {
+		virtio_device_for_each_vq(&vm_dev->vdev, vq)
+			ret |= vring_interrupt(irq, vq);
+	}
+
+	return ret;
+}
+
+
+
+static void vm_del_vq(struct virtqueue *vq)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
+	unsigned int index = vq->index;
+
+	/* Select and deactivate the queue */
+	writel(index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
+	if (vm_dev->version == 1) {
+		writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+	} else {
+		writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_READY);
+		WARN_ON(readl(vm_dev->base + VIRTIO_MMIO_QUEUE_READY));
+	}
+
+	vring_del_virtqueue(vq);
+}
+
+static void vm_del_vqs(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	struct virtqueue *vq, *n;
+
+	list_for_each_entry_safe(vq, n, &vdev->vqs, list)
+		vm_del_vq(vq);
+
+	free_irq(platform_get_irq(vm_dev->pdev, 0), vm_dev);
+}
+
+static void vm_synchronize_cbs(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	synchronize_irq(platform_get_irq(vm_dev->pdev, 0));
+}
+
+static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int index,
+				  void (*callback)(struct virtqueue *vq),
+				  const char *name, bool ctx)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	bool (*notify)(struct virtqueue *vq);
+	struct virtqueue *vq;
+	unsigned int num;
+	int err;
+
+	if (__virtio_test_bit(vdev, VIRTIO_F_NOTIFICATION_DATA))
+		notify = vm_notify_with_data;
+	else
+		notify = vm_notify;
+
+	if (!name)
+		return NULL;
+
+	/* Select the queue we're interested in */
+	writel(index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
+
+	/* Queue shouldn't already be set up. */
+	if (readl(vm_dev->base + (vm_dev->version == 1 ?
+			VIRTIO_MMIO_QUEUE_PFN : VIRTIO_MMIO_QUEUE_READY))) {
+		err = -ENOENT;
+		goto error_available;
+	}
+
+	num = readl(vm_dev->base + VIRTIO_MMIO_QUEUE_NUM_MAX);
+	if (num == 0) {
+		err = -ENOENT;
+		goto error_new_virtqueue;
+	}
+
+	/* Create the vring */
+	vq = vring_create_virtqueue(index, num, VIRTIO_MMIO_VRING_ALIGN, vdev,
+				 true, true, ctx, notify, callback, name);
+	if (!vq) {
+		err = -ENOMEM;
+		goto error_new_virtqueue;
+	}
+
+	vq->num_max = num;
+
+	/* Activate the queue */
+	writel(virtqueue_get_vring_size(vq), vm_dev->base + VIRTIO_MMIO_QUEUE_NUM);
+	if (vm_dev->version == 1) {
+		u64 q_pfn = virtqueue_get_desc_addr(vq) >> PAGE_SHIFT;
+
+		/*
+		 * virtio-mmio v1 uses a 32bit QUEUE PFN. If we have something
+		 * that doesn't fit in 32bit, fail the setup rather than
+		 * pretending to be successful.
+		 */
+		if (q_pfn >> 32) {
+			dev_err(&vdev->dev,
+				"platform bug: legacy virtio-mmio must not be used with RAM above 0x%llxGB\n",
+				0x1ULL << (32 + PAGE_SHIFT - 30));
+			err = -E2BIG;
+			goto error_bad_pfn;
+		}
+
+		writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_QUEUE_ALIGN);
+		writel(q_pfn, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+	} else {
+		u64 addr;
+
+		addr = virtqueue_get_desc_addr(vq);
+		writel((u32)addr, vm_dev->base + VIRTIO_MMIO_QUEUE_DESC_LOW);
+		writel((u32)(addr >> 32),
+				vm_dev->base + VIRTIO_MMIO_QUEUE_DESC_HIGH);
+
+		addr = virtqueue_get_avail_addr(vq);
+		writel((u32)addr, vm_dev->base + VIRTIO_MMIO_QUEUE_AVAIL_LOW);
+		writel((u32)(addr >> 32),
+				vm_dev->base + VIRTIO_MMIO_QUEUE_AVAIL_HIGH);
+
+		addr = virtqueue_get_used_addr(vq);
+		writel((u32)addr, vm_dev->base + VIRTIO_MMIO_QUEUE_USED_LOW);
+		writel((u32)(addr >> 32),
+				vm_dev->base + VIRTIO_MMIO_QUEUE_USED_HIGH);
+
+		writel(1, vm_dev->base + VIRTIO_MMIO_QUEUE_READY);
+	}
+
+	return vq;
+
+error_bad_pfn:
+	vring_del_virtqueue(vq);
+error_new_virtqueue:
+	if (vm_dev->version == 1) {
+		writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+	} else {
+		writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_READY);
+		WARN_ON(readl(vm_dev->base + VIRTIO_MMIO_QUEUE_READY));
+	}
+error_available:
+	return ERR_PTR(err);
+}
+
+static int vm_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
+		       struct virtqueue *vqs[],
+		       struct virtqueue_info vqs_info[],
+		       struct irq_affinity *desc)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	int irq = platform_get_irq(vm_dev->pdev, 0);
+	int i, err, queue_idx = 0;
+
+	if (irq < 0)
+		return irq;
+
+	err = request_irq(irq, vm_interrupt, IRQF_SHARED,
+			dev_name(&vdev->dev), vm_dev);
+	if (err)
+		return err;
+
+	if (of_property_read_bool(vm_dev->pdev->dev.of_node, "wakeup-source"))
+		enable_irq_wake(irq);
+
+	for (i = 0; i < nvqs; ++i) {
+		struct virtqueue_info *vqi = &vqs_info[i];
+
+		if (!vqi->name) {
+			vqs[i] = NULL;
+			continue;
+		}
+
+		vqs[i] = vm_setup_vq(vdev, queue_idx++, vqi->callback,
+				     vqi->name, vqi->ctx);
+		if (IS_ERR(vqs[i])) {
+			vm_del_vqs(vdev);
+			return PTR_ERR(vqs[i]);
+		}
+	}
+
+	return 0;
+}
+
+static const char *vm_bus_name(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	return vm_dev->pdev->name;
+}
+
+static bool vm_get_shm_region(struct virtio_device *vdev,
+			      struct virtio_shm_region *region, u8 id)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	u64 len, addr;
+
+	/* Select the region we're interested in */
+	writel(id, vm_dev->base + VIRTIO_MMIO_SHM_SEL);
+
+	/* Read the region size */
+	len = (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_LEN_LOW);
+	len |= (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_LEN_HIGH) << 32;
+
+	region->len = len;
+
+	/* Check if region length is -1. If that's the case, the shared memory
+	 * region does not exist and there is no need to proceed further.
+	 */
+	if (len == ~(u64)0)
+		return false;
+
+	/* Read the region base address */
+	addr = (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_BASE_LOW);
+	addr |= (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_BASE_HIGH) << 32;
+
+	region->addr = addr;
+
+	return true;
+}
+
+static const struct virtio_config_ops virtio_mmio_config_ops = {
+	.get		= vm_get,
+	.set		= vm_set,
+	.generation	= vm_generation,
+	.get_status	= vm_get_status,
+	.set_status	= vm_set_status,
+	.reset		= vm_reset,
+	.find_vqs	= vm_find_vqs,
+	.del_vqs	= vm_del_vqs,
+	.get_features	= vm_get_features,
+	.finalize_features = vm_finalize_features,
+	.bus_name	= vm_bus_name,
+	.get_shm_region = vm_get_shm_region,
+	.synchronize_cbs = vm_synchronize_cbs,
+};
+
+#ifdef CONFIG_PM_SLEEP
+static int virtio_mmio_freeze(struct device *dev)
+{
+	struct virtio_mmio_device *vm_dev = dev_get_drvdata(dev);
+
+	return virtio_device_freeze(&vm_dev->vdev);
+}
+
+static int virtio_mmio_restore(struct device *dev)
+{
+	struct virtio_mmio_device *vm_dev = dev_get_drvdata(dev);
+
+	if (vm_dev->version == 1)
+		writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_GUEST_PAGE_SIZE);
+
+	return virtio_device_restore(&vm_dev->vdev);
+}
+
+static const struct dev_pm_ops virtio_mmio_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(virtio_mmio_freeze, virtio_mmio_restore)
+};
+#endif
+
+static void virtio_mmio_release_dev(struct device *_d)
+{
+	struct virtio_device *vdev =
+			container_of(_d, struct virtio_device, dev);
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	kfree(vm_dev);
+}
+
+/* Platform device */
+
+static int virtio_mmio_probe(struct platform_device *pdev)
+{
+	struct virtio_mmio_device *vm_dev;
+	unsigned long magic;
+	int rc;
+
+	vm_dev = kzalloc_obj(*vm_dev);
+	if (!vm_dev)
+		return -ENOMEM;
+
+	vm_dev->vdev.dev.parent = &pdev->dev;
+	vm_dev->vdev.dev.release = virtio_mmio_release_dev;
+	vm_dev->vdev.config = &virtio_mmio_config_ops;
+	vm_dev->pdev = pdev;
+
+	vm_dev->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(vm_dev->base)) {
+		rc = PTR_ERR(vm_dev->base);
+		goto free_vm_dev;
+	}
+
+	/* Check magic value */
+	magic = readl(vm_dev->base + VIRTIO_MMIO_MAGIC_VALUE);
+	if (magic != ('v' | 'i' << 8 | 'r' << 16 | 't' << 24)) {
+		dev_warn(&pdev->dev, "Wrong magic value 0x%08lx!\n", magic);
+		rc = -ENODEV;
+		goto free_vm_dev;
+	}
+
+	/* Check device version */
+	vm_dev->version = readl(vm_dev->base + VIRTIO_MMIO_VERSION);
+	if (vm_dev->version < 1 || vm_dev->version > 2) {
+		dev_err(&pdev->dev, "Version %ld not supported!\n",
+				vm_dev->version);
+		rc = -ENXIO;
+		goto free_vm_dev;
+	}
+
+	vm_dev->vdev.id.device = readl(vm_dev->base + VIRTIO_MMIO_DEVICE_ID);
+	if (vm_dev->vdev.id.device == 0) {
+		/*
+		 * virtio-mmio device with an ID 0 is a (dummy) placeholder
+		 * with no function. End probing now with no error reported.
+		 */
+		rc = -ENODEV;
+		goto free_vm_dev;
+	}
+	vm_dev->vdev.id.vendor = readl(vm_dev->base + VIRTIO_MMIO_VENDOR_ID);
+
+	if (vm_dev->version == 1) {
+		writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_GUEST_PAGE_SIZE);
+
+		rc = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
+		/*
+		 * In the legacy case, ensure our coherently-allocated virtio
+		 * ring will be at an address expressable as a 32-bit PFN.
+		 */
+		if (!rc)
+			dma_set_coherent_mask(&pdev->dev,
+					      DMA_BIT_MASK(32 + PAGE_SHIFT));
+	} else {
+		rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	}
+	if (rc)
+		rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+	if (rc)
+		dev_warn(&pdev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
+
+	platform_set_drvdata(pdev, vm_dev);
+
+	rc = register_virtio_device(&vm_dev->vdev);
+	if (rc)
+		put_device(&vm_dev->vdev.dev);
+
+	return rc;
+
+free_vm_dev:
+	kfree(vm_dev);
+	return rc;
+}
+
+static void virtio_mmio_remove(struct platform_device *pdev)
+{
+	struct virtio_mmio_device *vm_dev = platform_get_drvdata(pdev);
+	unregister_virtio_device(&vm_dev->vdev);
+}
+
+
+
+/* Devices list parameter */
+
+#if defined(CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES)
+
+static struct device *vm_cmdline_parent;
+
+static int vm_cmdline_parent_registered;
+static int vm_cmdline_id;
+
+static int vm_cmdline_set(const char *device,
+		const struct kernel_param *kp)
+{
+	struct resource resources[2] = {};
+	char *str;
+	long long base, size;
+	unsigned int irq;
+	int processed, consumed = 0;
+	struct platform_device *pdev;
+
+	/* Consume "size" part of the command line parameter */
+	size = memparse(device, &str);
+
+	/* Get "@<base>:<irq>[:<id>]" chunks */
+	processed = sscanf(str, "@%lli:%u%n:%d%n",
+			&base, &irq, &consumed,
+			&vm_cmdline_id, &consumed);
+
+	/*
+	 * sscanf() must process at least 2 chunks; also there
+	 * must be no extra characters after the last chunk, so
+	 * str[consumed] must be '\0'
+	 */
+	if (processed < 2 || str[consumed] || irq == 0)
+		return -EINVAL;
+
+	resources[0].flags = IORESOURCE_MEM;
+	resources[0].start = base;
+	resources[0].end = base + size - 1;
+
+	resources[1].flags = IORESOURCE_IRQ;
+	resources[1].start = resources[1].end = irq;
+
+	if (!vm_cmdline_parent_registered) {
+		vm_cmdline_parent = __root_device_register("virtio-mmio-cmdline", NULL);
+		if (IS_ERR(vm_cmdline_parent)) {
+			pr_err("Failed to register parent device!\n");
+			return PTR_ERR(vm_cmdline_parent);
+		}
+		vm_cmdline_parent_registered = 1;
+	}
+
+	pr_info("Registering device virtio-mmio.%d at 0x%llx-0x%llx, IRQ %d.\n",
+		       vm_cmdline_id,
+		       (unsigned long long)resources[0].start,
+		       (unsigned long long)resources[0].end,
+		       (int)resources[1].start);
+
+	pdev = platform_device_register_resndata(vm_cmdline_parent,
+			"virtio-mmio", vm_cmdline_id++,
+			resources, ARRAY_SIZE(resources), NULL, 0);
+
+	return PTR_ERR_OR_ZERO(pdev);
+}
+
+static int vm_cmdline_get_device(struct device *dev, void *data)
+{
+	char *buffer = data;
+	unsigned int len = strlen(buffer);
+	struct platform_device *pdev = to_platform_device(dev);
+
+	snprintf(buffer + len, PAGE_SIZE - len, "0x%llx@0x%llx:%llu:%d\n",
+			pdev->resource[0].end - pdev->resource[0].start + 1ULL,
+			(unsigned long long)pdev->resource[0].start,
+			(unsigned long long)pdev->resource[1].start,
+			pdev->id);
+	return 0;
+}
+
+static int vm_cmdline_get(char *buffer, const struct kernel_param *kp)
+{
+	buffer[0] = '\0';
+
+	if (vm_cmdline_parent_registered) {
+		device_for_each_child(vm_cmdline_parent, buffer,
+				vm_cmdline_get_device);
+	}
+
+	return strlen(buffer) + 1;
+}
+
+static const struct kernel_param_ops vm_cmdline_param_ops = {
+	.set = vm_cmdline_set,
+	.get = vm_cmdline_get,
+};
+
+device_param_cb(device, &vm_cmdline_param_ops, NULL, S_IRUSR);
+
+static int vm_unregister_cmdline_device(struct device *dev,
+		void *data)
+{
+	platform_device_unregister(to_platform_device(dev));
+
+	return 0;
+}
+
+static void vm_unregister_cmdline_devices(void)
+{
+	if (vm_cmdline_parent_registered) {
+		device_for_each_child(vm_cmdline_parent, NULL,
+				vm_unregister_cmdline_device);
+		root_device_unregister(vm_cmdline_parent);
+		vm_cmdline_parent_registered = 0;
+	}
+}
+
+#else
+
+static void vm_unregister_cmdline_devices(void)
+{
+}
+
+#endif
+
+/* Platform driver */
+
+static const struct of_device_id virtio_mmio_match[] = {
+	{ .compatible = "virtio,mmio", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, virtio_mmio_match);
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id virtio_mmio_acpi_match[] = {
+	{ "LNRO0005", },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, virtio_mmio_acpi_match);
+#endif
+
+static struct platform_driver virtio_mmio_driver = {
+	.probe		= virtio_mmio_probe,
+	.remove		= virtio_mmio_remove,
+	.driver		= {
+		.name	= "virtio-mmio",
+		.of_match_table	= virtio_mmio_match,
+		.acpi_match_table = ACPI_PTR(virtio_mmio_acpi_match),
+#ifdef CONFIG_PM_SLEEP
+		.pm	= &virtio_mmio_pm_ops,
+#endif
+	},
+};
+
+static int __init virtio_mmio_init(void)
+{
+	return platform_driver_register(&virtio_mmio_driver);
+}
+
+static void __exit virtio_mmio_exit(void)
+{
+	platform_driver_unregister(&virtio_mmio_driver);
+	vm_unregister_cmdline_devices();
+}
+
+module_init(virtio_mmio_init);
+module_exit(virtio_mmio_exit);
+
+MODULE_AUTHOR("Pawel Moll <pawel.moll@arm.com>");
+MODULE_DESCRIPTION("Platform bus driver for memory mapped virtio devices");
+MODULE_LICENSE("GPL");

linux-7.2.3/drivers/virtio/virtio_pci_admin_legacy_io.c

@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#include <linux/virtio_pci_admin.h>
+#include "virtio_pci_common.h"
+
+/*
+ * virtio_pci_admin_has_legacy_io - Checks whether the legacy IO
+ * commands are supported
+ * @dev: VF pci_dev
+ *
+ * Returns true on success.
+ */
+bool virtio_pci_admin_has_legacy_io(struct pci_dev *pdev)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_pci_device *vp_dev;
+
+	if (!virtio_dev)
+		return false;
+
+	if (!virtio_has_feature(virtio_dev, VIRTIO_F_ADMIN_VQ))
+		return false;
+
+	vp_dev = to_vp_device(virtio_dev);
+
+	if ((vp_dev->admin_vq.supported_cmds & VIRTIO_LEGACY_ADMIN_CMD_BITMAP) ==
+		VIRTIO_LEGACY_ADMIN_CMD_BITMAP)
+		return true;
+	return false;
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_has_legacy_io);
+
+static int virtio_pci_admin_legacy_io_write(struct pci_dev *pdev, u16 opcode,
+					    u8 offset, u8 size, u8 *buf)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_legacy_wr_data *data;
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist data_sg;
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	data = kzalloc(sizeof(*data) + size, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->offset = offset;
+	memcpy(data->registers, buf, size);
+	sg_init_one(&data_sg, data, sizeof(*data) + size);
+	cmd.opcode = cpu_to_le16(opcode);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.data_sg = &data_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+
+	kfree(data);
+	return ret;
+}
+
+/*
+ * virtio_pci_admin_legacy_io_write_common - Write legacy common configuration
+ * of a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the common configuration area to write to
+ * @size: size of the data to write
+ * @buf: buffer which holds the data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_common_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_write(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_common_io_write);
+
+/*
+ * virtio_pci_admin_legacy_io_write_device - Write legacy device configuration
+ * of a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the device configuration area to write to
+ * @size: size of the data to write
+ * @buf: buffer which holds the data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_device_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_write(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_device_io_write);
+
+static int virtio_pci_admin_legacy_io_read(struct pci_dev *pdev, u16 opcode,
+					   u8 offset, u8 size, u8 *buf)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_legacy_rd_data *data;
+	struct scatterlist data_sg, result_sg;
+	struct virtio_admin_cmd cmd = {};
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	data = kzalloc_obj(*data);
+	if (!data)
+		return -ENOMEM;
+
+	data->offset = offset;
+	sg_init_one(&data_sg, data, sizeof(*data));
+	sg_init_one(&result_sg, buf, size);
+	cmd.opcode = cpu_to_le16(opcode);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.data_sg = &data_sg;
+	cmd.result_sg = &result_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+
+	kfree(data);
+	return ret;
+}
+
+/*
+ * virtio_pci_admin_legacy_device_io_read - Read legacy device configuration of
+ * a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the device configuration area to read from
+ * @size: size of the data to be read
+ * @buf: buffer to hold the returned data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_device_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_read(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_device_io_read);
+
+/*
+ * virtio_pci_admin_legacy_common_io_read - Read legacy common configuration of
+ * a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the common configuration area to read from
+ * @size: size of the data to be read
+ * @buf: buffer to hold the returned data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_common_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_read(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_common_io_read);
+
+/*
+ * virtio_pci_admin_legacy_io_notify_info - Read the queue notification
+ * information for legacy interface
+ * @dev: VF pci_dev
+ * @req_bar_flags: requested bar flags
+ * @bar: on output the BAR number of the owner or member device
+ * @bar_offset: on output the offset within bar
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_io_notify_info(struct pci_dev *pdev,
+					   u8 req_bar_flags, u8 *bar,
+					   u64 *bar_offset)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_notify_info_result *result;
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist result_sg;
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	result = kzalloc_obj(*result);
+	if (!result)
+		return -ENOMEM;
+
+	sg_init_one(&result_sg, result, sizeof(*result));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.result_sg = &result_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (!ret) {
+		struct virtio_admin_cmd_notify_info_data *entry;
+		int i;
+
+		ret = -ENOENT;
+		for (i = 0; i < VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO; i++) {
+			entry = &result->entries[i];
+			if (entry->flags == VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_END)
+				break;
+			if (entry->flags != req_bar_flags)
+				continue;
+			*bar = entry->bar;
+			*bar_offset = le64_to_cpu(entry->offset);
+			ret = 0;
+			break;
+		}
+	}
+
+	kfree(result);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_io_notify_info);

linux-7.2.3/drivers/virtio/virtio_pci_common.c

@@ -0,0 +1,864 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Virtio PCI driver - common functionality for all device versions
+ *
+ * This module allows virtio devices to be used over a virtual PCI device.
+ * This can be used with QEMU based VMMs like KVM or Xen.
+ *
+ * Copyright IBM Corp. 2007
+ * Copyright Red Hat, Inc. 2014
+ *
+ * Authors:
+ *  Anthony Liguori  <aliguori@us.ibm.com>
+ *  Rusty Russell <rusty@rustcorp.com.au>
+ *  Michael S. Tsirkin <mst@redhat.com>
+ */
+
+#include "virtio_pci_common.h"
+
+static bool force_legacy = false;
+
+#if IS_ENABLED(CONFIG_VIRTIO_PCI_LEGACY)
+module_param(force_legacy, bool, 0444);
+MODULE_PARM_DESC(force_legacy,
+		 "Force legacy mode for transitional virtio 1 devices");
+#endif
+
+bool vp_is_avq(struct virtio_device *vdev, unsigned int index)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return false;
+
+	return index == vp_dev->admin_vq.vq_index;
+}
+
+/* wait for pending irq handlers */
+void vp_synchronize_vectors(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	int i;
+
+	if (vp_dev->intx_enabled)
+		synchronize_irq(vp_dev->pci_dev->irq);
+
+	for (i = 0; i < vp_dev->msix_vectors; ++i)
+		synchronize_irq(pci_irq_vector(vp_dev->pci_dev, i));
+}
+
+/* the notify function used when creating a virt queue */
+bool vp_notify(struct virtqueue *vq)
+{
+	/* we write the queue's selector into the notification register to
+	 * signal the other end */
+	iowrite16(vq->index, (void __iomem *)vq->priv);
+	return true;
+}
+
+/* Notify all slow path virtqueues on an interrupt. */
+static void vp_vring_slow_path_interrupt(int irq,
+					 struct virtio_pci_device *vp_dev)
+{
+	struct virtio_pci_vq_info *info;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vp_dev->lock, flags);
+	list_for_each_entry(info, &vp_dev->slow_virtqueues, node)
+		vring_interrupt(irq, info->vq);
+	spin_unlock_irqrestore(&vp_dev->lock, flags);
+}
+
+/* Handle a configuration change: Tell driver if it wants to know. */
+static irqreturn_t vp_config_changed(int irq, void *opaque)
+{
+	struct virtio_pci_device *vp_dev = opaque;
+
+	virtio_config_changed(&vp_dev->vdev);
+	vp_vring_slow_path_interrupt(irq, vp_dev);
+	return IRQ_HANDLED;
+}
+
+/* Notify all virtqueues on an interrupt. */
+static irqreturn_t vp_vring_interrupt(int irq, void *opaque)
+{
+	struct virtio_pci_device *vp_dev = opaque;
+	struct virtio_pci_vq_info *info;
+	irqreturn_t ret = IRQ_NONE;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vp_dev->lock, flags);
+	list_for_each_entry(info, &vp_dev->virtqueues, node) {
+		if (vring_interrupt(irq, info->vq) == IRQ_HANDLED)
+			ret = IRQ_HANDLED;
+	}
+	spin_unlock_irqrestore(&vp_dev->lock, flags);
+
+	return ret;
+}
+
+/* A small wrapper to also acknowledge the interrupt when it's handled.
+ * I really need an EIO hook for the vring so I can ack the interrupt once we
+ * know that we'll be handling the IRQ but before we invoke the callback since
+ * the callback may notify the host which results in the host attempting to
+ * raise an interrupt that we would then mask once we acknowledged the
+ * interrupt. */
+static irqreturn_t vp_interrupt(int irq, void *opaque)
+{
+	struct virtio_pci_device *vp_dev = opaque;
+	u8 isr;
+
+	/* reading the ISR has the effect of also clearing it so it's very
+	 * important to save off the value. */
+	isr = ioread8(vp_dev->isr);
+
+	/* It's definitely not us if the ISR was not high */
+	if (!isr)
+		return IRQ_NONE;
+
+	/* Configuration change?  Tell driver if it wants to know. */
+	if (isr & VIRTIO_PCI_ISR_CONFIG)
+		vp_config_changed(irq, opaque);
+
+	return vp_vring_interrupt(irq, opaque);
+}
+
+static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
+				   bool per_vq_vectors, struct irq_affinity *desc)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	const char *name = dev_name(&vp_dev->vdev.dev);
+	unsigned int flags = PCI_IRQ_MSIX;
+	unsigned int i, v;
+	int err = -ENOMEM;
+
+	vp_dev->msix_vectors = nvectors;
+
+	vp_dev->msix_names = kmalloc_objs(*vp_dev->msix_names, nvectors);
+	if (!vp_dev->msix_names)
+		goto error;
+	vp_dev->msix_affinity_masks
+		= kzalloc_objs(*vp_dev->msix_affinity_masks, nvectors);
+	if (!vp_dev->msix_affinity_masks)
+		goto error;
+	for (i = 0; i < nvectors; ++i)
+		if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
+					GFP_KERNEL))
+			goto error;
+
+	if (!per_vq_vectors)
+		desc = NULL;
+
+	if (desc) {
+		flags |= PCI_IRQ_AFFINITY;
+		desc->pre_vectors++; /* virtio config vector */
+	}
+
+	err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors,
+					     nvectors, flags, desc);
+	if (err < 0)
+		goto error;
+	vp_dev->msix_enabled = 1;
+
+	/* Set the vector used for configuration */
+	v = vp_dev->msix_used_vectors;
+	snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
+		 "%s-config", name);
+	err = request_irq(pci_irq_vector(vp_dev->pci_dev, v),
+			  vp_config_changed, 0, vp_dev->msix_names[v],
+			  vp_dev);
+	if (err)
+		goto error;
+	++vp_dev->msix_used_vectors;
+
+	v = vp_dev->config_vector(vp_dev, v);
+	/* Verify we had enough resources to assign the vector */
+	if (v == VIRTIO_MSI_NO_VECTOR) {
+		err = -EBUSY;
+		goto error;
+	}
+
+	if (!per_vq_vectors) {
+		/* Shared vector for all VQs */
+		v = vp_dev->msix_used_vectors;
+		snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
+			 "%s-virtqueues", name);
+		err = request_irq(pci_irq_vector(vp_dev->pci_dev, v),
+				  vp_vring_interrupt, 0, vp_dev->msix_names[v],
+				  vp_dev);
+		if (err)
+			goto error;
+		++vp_dev->msix_used_vectors;
+	}
+	return 0;
+error:
+	return err;
+}
+
+static bool vp_is_slow_path_vector(u16 msix_vec)
+{
+	return msix_vec == VP_MSIX_CONFIG_VECTOR;
+}
+
+static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned int index,
+				     void (*callback)(struct virtqueue *vq),
+				     const char *name,
+				     bool ctx,
+				     u16 msix_vec,
+				     struct virtio_pci_vq_info **p_info)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_vq_info *info = kmalloc_obj(*info);
+	struct virtqueue *vq;
+	unsigned long flags;
+
+	/* fill out our structure that represents an active queue */
+	if (!info)
+		return ERR_PTR(-ENOMEM);
+
+	vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, ctx,
+			      msix_vec);
+	if (IS_ERR(vq))
+		goto out_info;
+
+	info->vq = vq;
+	if (callback) {
+		spin_lock_irqsave(&vp_dev->lock, flags);
+		if (!vp_is_slow_path_vector(msix_vec))
+			list_add(&info->node, &vp_dev->virtqueues);
+		else
+			list_add(&info->node, &vp_dev->slow_virtqueues);
+		spin_unlock_irqrestore(&vp_dev->lock, flags);
+	} else {
+		INIT_LIST_HEAD(&info->node);
+	}
+
+	*p_info = info;
+	return vq;
+
+out_info:
+	kfree(info);
+	return vq;
+}
+
+static void vp_del_vq(struct virtqueue *vq, struct virtio_pci_vq_info *info)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+	unsigned long flags;
+
+	/*
+	 * If it fails during re-enable reset vq. This way we won't rejoin
+	 * info->node to the queue. Prevent unexpected irqs.
+	 */
+	if (!vq->reset) {
+		spin_lock_irqsave(&vp_dev->lock, flags);
+		list_del(&info->node);
+		spin_unlock_irqrestore(&vp_dev->lock, flags);
+	}
+
+	vp_dev->del_vq(info);
+	kfree(info);
+}
+
+/* the config->del_vqs() implementation */
+void vp_del_vqs(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_vq_info *info;
+	struct virtqueue *vq, *n;
+	int i;
+
+	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
+		info = vp_is_avq(vdev, vq->index) ? vp_dev->admin_vq.info :
+						    vp_dev->vqs[vq->index];
+
+		if (vp_dev->per_vq_vectors) {
+			int v = info->msix_vector;
+			if (v != VIRTIO_MSI_NO_VECTOR &&
+			    !vp_is_slow_path_vector(v)) {
+				int irq = pci_irq_vector(vp_dev->pci_dev, v);
+
+				irq_update_affinity_hint(irq, NULL);
+				free_irq(irq, vq);
+			}
+		}
+		vp_del_vq(vq, info);
+	}
+	vp_dev->per_vq_vectors = false;
+
+	if (vp_dev->intx_enabled) {
+		free_irq(vp_dev->pci_dev->irq, vp_dev);
+		vp_dev->intx_enabled = 0;
+	}
+
+	for (i = 0; i < vp_dev->msix_used_vectors; ++i)
+		free_irq(pci_irq_vector(vp_dev->pci_dev, i), vp_dev);
+
+	if (vp_dev->msix_affinity_masks) {
+		for (i = 0; i < vp_dev->msix_vectors; i++)
+			free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+	}
+
+	if (vp_dev->msix_enabled) {
+		/* Disable the vector used for configuration */
+		vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR);
+
+		pci_free_irq_vectors(vp_dev->pci_dev);
+		vp_dev->msix_enabled = 0;
+	}
+
+	vp_dev->msix_vectors = 0;
+	vp_dev->msix_used_vectors = 0;
+	kfree(vp_dev->msix_names);
+	vp_dev->msix_names = NULL;
+	kfree(vp_dev->msix_affinity_masks);
+	vp_dev->msix_affinity_masks = NULL;
+	kfree(vp_dev->vqs);
+	vp_dev->vqs = NULL;
+}
+
+enum vp_vq_vector_policy {
+	VP_VQ_VECTOR_POLICY_EACH,
+	VP_VQ_VECTOR_POLICY_SHARED_SLOW,
+	VP_VQ_VECTOR_POLICY_SHARED,
+};
+
+static struct virtqueue *
+vp_find_one_vq_msix(struct virtio_device *vdev, int queue_idx,
+		    vq_callback_t *callback, const char *name, bool ctx,
+		    bool slow_path, int *allocated_vectors,
+		    enum vp_vq_vector_policy vector_policy,
+		    struct virtio_pci_vq_info **p_info)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtqueue *vq;
+	u16 msix_vec;
+	int err;
+
+	if (!callback)
+		msix_vec = VIRTIO_MSI_NO_VECTOR;
+	else if (vector_policy == VP_VQ_VECTOR_POLICY_EACH ||
+		 (vector_policy == VP_VQ_VECTOR_POLICY_SHARED_SLOW &&
+		 !slow_path))
+		msix_vec = (*allocated_vectors)++;
+	else if (vector_policy != VP_VQ_VECTOR_POLICY_EACH &&
+		 slow_path)
+		msix_vec = VP_MSIX_CONFIG_VECTOR;
+	else
+		msix_vec = VP_MSIX_VQ_VECTOR;
+	vq = vp_setup_vq(vdev, queue_idx, callback, name, ctx, msix_vec,
+			 p_info);
+	if (IS_ERR(vq))
+		return vq;
+
+	if (vector_policy == VP_VQ_VECTOR_POLICY_SHARED ||
+	    msix_vec == VIRTIO_MSI_NO_VECTOR ||
+	    vp_is_slow_path_vector(msix_vec))
+		return vq;
+
+	/* allocate per-vq irq if available and necessary */
+	snprintf(vp_dev->msix_names[msix_vec], sizeof(*vp_dev->msix_names),
+		 "%s-%s", dev_name(&vp_dev->vdev.dev), name);
+	err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec),
+			  vring_interrupt, 0,
+			  vp_dev->msix_names[msix_vec], vq);
+	if (err) {
+		vp_del_vq(vq, *p_info);
+		return ERR_PTR(err);
+	}
+
+	return vq;
+}
+
+static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs,
+			    struct virtqueue *vqs[],
+			    struct virtqueue_info vqs_info[],
+			    enum vp_vq_vector_policy vector_policy,
+			    struct irq_affinity *desc)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *avq = &vp_dev->admin_vq;
+	struct virtqueue_info *vqi;
+	int i, err, nvectors, allocated_vectors, queue_idx = 0;
+	struct virtqueue *vq;
+	bool per_vq_vectors;
+	u16 avq_num = 0;
+
+	vp_dev->vqs = kzalloc_objs(*vp_dev->vqs, nvqs);
+	if (!vp_dev->vqs)
+		return -ENOMEM;
+
+	if (vp_dev->avq_index) {
+		err = vp_dev->avq_index(vdev, &avq->vq_index, &avq_num);
+		if (err)
+			goto error_find;
+	}
+
+	per_vq_vectors = vector_policy != VP_VQ_VECTOR_POLICY_SHARED;
+
+	if (per_vq_vectors) {
+		/* Best option: one for change interrupt, one per vq. */
+		nvectors = 1;
+		for (i = 0; i < nvqs; ++i) {
+			vqi = &vqs_info[i];
+			if (vqi->name && vqi->callback)
+				++nvectors;
+		}
+		if (avq_num && vector_policy == VP_VQ_VECTOR_POLICY_EACH)
+			++nvectors;
+	} else {
+		/* Second best: one for change, shared for all vqs. */
+		nvectors = 2;
+	}
+
+	err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors, desc);
+	if (err)
+		goto error_find;
+
+	vp_dev->per_vq_vectors = per_vq_vectors;
+	allocated_vectors = vp_dev->msix_used_vectors;
+	for (i = 0; i < nvqs; ++i) {
+		vqi = &vqs_info[i];
+		if (!vqi->name) {
+			vqs[i] = NULL;
+			continue;
+		}
+		vqs[i] = vp_find_one_vq_msix(vdev, queue_idx, vqi->callback,
+					     vqi->name, vqi->ctx, false,
+					     &allocated_vectors, vector_policy,
+					     &vp_dev->vqs[queue_idx]);
+		queue_idx++;
+		if (IS_ERR(vqs[i])) {
+			err = PTR_ERR(vqs[i]);
+			goto error_find;
+		}
+	}
+
+	if (!avq_num)
+		return 0;
+	sprintf(avq->name, "avq.%u", avq->vq_index);
+	vq = vp_find_one_vq_msix(vdev, avq->vq_index, vp_modern_avq_done,
+				 avq->name, false, true, &allocated_vectors,
+				 vector_policy, &vp_dev->admin_vq.info);
+	if (IS_ERR(vq)) {
+		err = PTR_ERR(vq);
+		goto error_find;
+	}
+
+	return 0;
+
+error_find:
+	vp_del_vqs(vdev);
+	return err;
+}
+
+static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs,
+			    struct virtqueue *vqs[],
+			    struct virtqueue_info vqs_info[])
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *avq = &vp_dev->admin_vq;
+	int i, err, queue_idx = 0;
+	struct virtqueue *vq;
+	u16 avq_num = 0;
+
+	vp_dev->vqs = kzalloc_objs(*vp_dev->vqs, nvqs);
+	if (!vp_dev->vqs)
+		return -ENOMEM;
+
+	if (vp_dev->avq_index) {
+		err = vp_dev->avq_index(vdev, &avq->vq_index, &avq_num);
+		if (err)
+			goto out_del_vqs;
+	}
+
+	err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED,
+			dev_name(&vdev->dev), vp_dev);
+	if (err)
+		goto out_del_vqs;
+
+	vp_dev->intx_enabled = 1;
+	vp_dev->per_vq_vectors = false;
+	for (i = 0; i < nvqs; ++i) {
+		struct virtqueue_info *vqi = &vqs_info[i];
+
+		if (!vqi->name) {
+			vqs[i] = NULL;
+			continue;
+		}
+		vqs[i] = vp_setup_vq(vdev, queue_idx, vqi->callback,
+				     vqi->name, vqi->ctx,
+				     VIRTIO_MSI_NO_VECTOR, &vp_dev->vqs[queue_idx]);
+		queue_idx++;
+		if (IS_ERR(vqs[i])) {
+			err = PTR_ERR(vqs[i]);
+			goto out_del_vqs;
+		}
+	}
+
+	if (!avq_num)
+		return 0;
+	sprintf(avq->name, "avq.%u", avq->vq_index);
+	vq = vp_setup_vq(vdev, queue_idx++, vp_modern_avq_done, avq->name,
+			 false, VIRTIO_MSI_NO_VECTOR,
+			 &vp_dev->admin_vq.info);
+	if (IS_ERR(vq)) {
+		err = PTR_ERR(vq);
+		goto out_del_vqs;
+	}
+
+	return 0;
+out_del_vqs:
+	vp_del_vqs(vdev);
+	return err;
+}
+
+/* the config->find_vqs() implementation */
+int vp_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
+		struct virtqueue *vqs[], struct virtqueue_info vqs_info[],
+		struct irq_affinity *desc)
+{
+	int err;
+
+	/* Try MSI-X with one vector per queue. */
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, vqs_info,
+			       VP_VQ_VECTOR_POLICY_EACH, desc);
+	if (!err)
+		return 0;
+	/* Fallback: MSI-X with one shared vector for config and
+	 * slow path queues, one vector per queue for the rest.
+	 */
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, vqs_info,
+			       VP_VQ_VECTOR_POLICY_SHARED_SLOW, desc);
+	if (!err)
+		return 0;
+	/* Fallback: MSI-X with one vector for config, one shared for queues. */
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, vqs_info,
+			       VP_VQ_VECTOR_POLICY_SHARED, desc);
+	if (!err)
+		return 0;
+	/* Is there an interrupt? If not give up. */
+	if (!(to_vp_device(vdev)->pci_dev->irq))
+		return err;
+	/* Finally fall back to regular interrupts. */
+	return vp_find_vqs_intx(vdev, nvqs, vqs, vqs_info);
+}
+
+const char *vp_bus_name(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	return pci_name(vp_dev->pci_dev);
+}
+
+/* Setup the affinity for a virtqueue:
+ * - force the affinity for per vq vector
+ * - OR over all affinities for shared MSI
+ * - ignore the affinity request if we're using INTX
+ */
+int vp_set_vq_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask)
+{
+	struct virtio_device *vdev = vq->vdev;
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index];
+	struct cpumask *mask;
+	unsigned int irq;
+
+	if (!vq->callback)
+		return -EINVAL;
+
+	if (vp_dev->msix_enabled) {
+		mask = vp_dev->msix_affinity_masks[info->msix_vector];
+		irq = pci_irq_vector(vp_dev->pci_dev, info->msix_vector);
+		if (!cpu_mask)
+			irq_update_affinity_hint(irq, NULL);
+		else {
+			cpumask_copy(mask, cpu_mask);
+			irq_set_affinity_and_hint(irq, mask);
+		}
+	}
+	return 0;
+}
+
+const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	if (!vp_dev->per_vq_vectors ||
+	    vp_dev->vqs[index]->msix_vector == VIRTIO_MSI_NO_VECTOR ||
+	    vp_is_slow_path_vector(vp_dev->vqs[index]->msix_vector))
+		return NULL;
+
+	return pci_irq_get_affinity(vp_dev->pci_dev,
+				    vp_dev->vqs[index]->msix_vector);
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int virtio_pci_freeze(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	int ret;
+
+	ret = virtio_device_freeze(&vp_dev->vdev);
+
+	if (!ret)
+		pci_disable_device(pci_dev);
+	return ret;
+}
+
+static int virtio_pci_restore(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	int ret;
+
+	ret = pci_enable_device(pci_dev);
+	if (ret)
+		return ret;
+
+	pci_set_master(pci_dev);
+	return virtio_device_restore(&vp_dev->vdev);
+}
+
+static bool vp_supports_pm_no_reset(struct device *dev)
+{
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	u16 pmcsr;
+
+	if (!pci_dev->pm_cap)
+		return false;
+
+	pci_read_config_word(pci_dev, pci_dev->pm_cap + PCI_PM_CTRL, &pmcsr);
+	if (PCI_POSSIBLE_ERROR(pmcsr)) {
+		dev_err(dev, "Unable to query pmcsr");
+		return false;
+	}
+
+	return pmcsr & PCI_PM_CTRL_NO_SOFT_RESET;
+}
+
+static int virtio_pci_suspend(struct device *dev)
+{
+	return vp_supports_pm_no_reset(dev) ? 0 : virtio_pci_freeze(dev);
+}
+
+static int virtio_pci_resume(struct device *dev)
+{
+	return vp_supports_pm_no_reset(dev) ? 0 : virtio_pci_restore(dev);
+}
+
+static const struct dev_pm_ops virtio_pci_pm_ops = {
+	.suspend = virtio_pci_suspend,
+	.resume = virtio_pci_resume,
+	.freeze = virtio_pci_freeze,
+	.thaw = virtio_pci_restore,
+	.poweroff = virtio_pci_freeze,
+	.restore = virtio_pci_restore,
+};
+#endif
+
+
+/* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */
+static const struct pci_device_id virtio_pci_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_REDHAT_QUMRANET, PCI_ANY_ID) },
+	{ 0 }
+};
+
+MODULE_DEVICE_TABLE(pci, virtio_pci_id_table);
+
+static void virtio_pci_release_dev(struct device *_d)
+{
+	struct virtio_device *vdev = dev_to_virtio(_d);
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	/* As struct device is a kobject, it's not safe to
+	 * free the memory (including the reference counter itself)
+	 * until it's release callback. */
+	kfree(vp_dev);
+}
+
+static int virtio_pci_probe(struct pci_dev *pci_dev,
+			    const struct pci_device_id *id)
+{
+	struct virtio_pci_device *vp_dev, *reg_dev = NULL;
+	int rc;
+
+	/* allocate our structure and fill it out */
+	vp_dev = kzalloc_obj(struct virtio_pci_device);
+	if (!vp_dev)
+		return -ENOMEM;
+
+	pci_set_drvdata(pci_dev, vp_dev);
+	vp_dev->vdev.dev.parent = &pci_dev->dev;
+	vp_dev->vdev.dev.release = virtio_pci_release_dev;
+	vp_dev->pci_dev = pci_dev;
+	INIT_LIST_HEAD(&vp_dev->virtqueues);
+	INIT_LIST_HEAD(&vp_dev->slow_virtqueues);
+	spin_lock_init(&vp_dev->lock);
+
+	/* enable the device */
+	rc = pci_enable_device(pci_dev);
+	if (rc)
+		goto err_enable_device;
+
+	if (force_legacy) {
+		rc = virtio_pci_legacy_probe(vp_dev);
+		/* Also try modern mode if we can't map BAR0 (no IO space). */
+		if (rc == -ENODEV || rc == -ENOMEM)
+			rc = virtio_pci_modern_probe(vp_dev);
+		if (rc)
+			goto err_probe;
+	} else {
+		rc = virtio_pci_modern_probe(vp_dev);
+		if (rc == -ENODEV)
+			rc = virtio_pci_legacy_probe(vp_dev);
+		if (rc)
+			goto err_probe;
+	}
+
+	pci_set_master(pci_dev);
+
+	rc = register_virtio_device(&vp_dev->vdev);
+	reg_dev = vp_dev;
+	if (rc)
+		goto err_register;
+
+	return 0;
+
+err_register:
+	if (vp_dev->is_legacy)
+		virtio_pci_legacy_remove(vp_dev);
+	else
+		virtio_pci_modern_remove(vp_dev);
+err_probe:
+	pci_disable_device(pci_dev);
+err_enable_device:
+	if (reg_dev)
+		put_device(&vp_dev->vdev.dev);
+	else
+		kfree(vp_dev);
+	return rc;
+}
+
+static void virtio_pci_remove(struct pci_dev *pci_dev)
+{
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	struct device *dev = get_device(&vp_dev->vdev.dev);
+
+	/*
+	 * Device is marked broken on surprise removal so that virtio upper
+	 * layers can abort any ongoing operation.
+	 */
+	if (!pci_device_is_present(pci_dev))
+		virtio_break_device(&vp_dev->vdev);
+
+	pci_disable_sriov(pci_dev);
+
+	unregister_virtio_device(&vp_dev->vdev);
+
+	if (vp_dev->is_legacy)
+		virtio_pci_legacy_remove(vp_dev);
+	else
+		virtio_pci_modern_remove(vp_dev);
+
+	pci_disable_device(pci_dev);
+	put_device(dev);
+}
+
+static int virtio_pci_sriov_configure(struct pci_dev *pci_dev, int num_vfs)
+{
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	struct virtio_device *vdev = &vp_dev->vdev;
+	int ret;
+
+	if (!(vdev->config->get_status(vdev) & VIRTIO_CONFIG_S_DRIVER_OK))
+		return -EBUSY;
+
+	if (!__virtio_test_bit(vdev, VIRTIO_F_SR_IOV))
+		return -EINVAL;
+
+	if (pci_vfs_assigned(pci_dev))
+		return -EPERM;
+
+	if (num_vfs == 0) {
+		pci_disable_sriov(pci_dev);
+		return 0;
+	}
+
+	ret = pci_enable_sriov(pci_dev, num_vfs);
+	if (ret < 0)
+		return ret;
+
+	return num_vfs;
+}
+
+static void virtio_pci_reset_prepare(struct pci_dev *pci_dev)
+{
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	int ret = 0;
+
+	ret = virtio_device_reset_prepare(&vp_dev->vdev);
+	if (ret) {
+		if (ret != -EOPNOTSUPP)
+			dev_warn(&pci_dev->dev, "Reset prepare failure: %d",
+				 ret);
+		return;
+	}
+
+	if (pci_is_enabled(pci_dev))
+		pci_disable_device(pci_dev);
+}
+
+static void virtio_pci_reset_done(struct pci_dev *pci_dev)
+{
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	int ret;
+
+	if (pci_is_enabled(pci_dev))
+		return;
+
+	ret = pci_enable_device(pci_dev);
+	if (!ret) {
+		pci_set_master(pci_dev);
+		ret = virtio_device_reset_done(&vp_dev->vdev);
+	}
+
+	if (ret && ret != -EOPNOTSUPP)
+		dev_warn(&pci_dev->dev, "Reset done failure: %d", ret);
+}
+
+static const struct pci_error_handlers virtio_pci_err_handler = {
+	.reset_prepare  = virtio_pci_reset_prepare,
+	.reset_done     = virtio_pci_reset_done,
+};
+
+static struct pci_driver virtio_pci_driver = {
+	.name		= "virtio-pci",
+	.id_table	= virtio_pci_id_table,
+	.probe		= virtio_pci_probe,
+	.remove		= virtio_pci_remove,
+#ifdef CONFIG_PM_SLEEP
+	.driver.pm	= &virtio_pci_pm_ops,
+#endif
+	.sriov_configure = virtio_pci_sriov_configure,
+	.err_handler	= &virtio_pci_err_handler,
+};
+
+struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev)
+{
+	struct virtio_pci_device *pf_vp_dev;
+
+	pf_vp_dev = pci_iov_get_pf_drvdata(pdev, &virtio_pci_driver);
+	if (IS_ERR(pf_vp_dev))
+		return NULL;
+
+	return &pf_vp_dev->vdev;
+}
+
+module_pci_driver(virtio_pci_driver);
+
+MODULE_AUTHOR("Anthony Liguori <aliguori@us.ibm.com>");
+MODULE_DESCRIPTION("virtio-pci");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1");

linux-7.2.3/drivers/virtio/virtio_pci_common.h

@@ -0,0 +1,201 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _DRIVERS_VIRTIO_VIRTIO_PCI_COMMON_H
+#define _DRIVERS_VIRTIO_VIRTIO_PCI_COMMON_H
+/*
+ * Virtio PCI driver - APIs for common functionality for all device versions
+ *
+ * This module allows virtio devices to be used over a virtual PCI device.
+ * This can be used with QEMU based VMMs like KVM or Xen.
+ *
+ * Copyright IBM Corp. 2007
+ * Copyright Red Hat, Inc. 2014
+ *
+ * Authors:
+ *  Anthony Liguori  <aliguori@us.ibm.com>
+ *  Rusty Russell <rusty@rustcorp.com.au>
+ *  Michael S. Tsirkin <mst@redhat.com>
+ */
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+#include <linux/virtio_pci.h>
+#include <linux/virtio_pci_legacy.h>
+#include <linux/virtio_pci_modern.h>
+#include <linux/highmem.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+
+struct virtio_pci_vq_info {
+	/* the actual virtqueue */
+	struct virtqueue *vq;
+
+	/* the list node for the virtqueues or slow_virtqueues list */
+	struct list_head node;
+
+	/* MSI-X vector (or none) */
+	unsigned int msix_vector;
+};
+
+struct virtio_pci_admin_vq {
+	/* Virtqueue info associated with this admin queue. */
+	struct virtio_pci_vq_info *info;
+	/* Protects virtqueue access. */
+	spinlock_t lock;
+	u64 supported_cmds;
+	u64 supported_caps;
+	u8 max_dev_parts_objects;
+	struct ida dev_parts_ida;
+	/* Name of the admin queue: avq.$vq_index. */
+	char name[10];
+	u16 vq_index;
+};
+
+/* Our device structure */
+struct virtio_pci_device {
+	struct virtio_device vdev;
+	struct pci_dev *pci_dev;
+	union {
+		struct virtio_pci_legacy_device ldev;
+		struct virtio_pci_modern_device mdev;
+	};
+	bool is_legacy;
+
+	/* Where to read and clear interrupt */
+	u8 __iomem *isr;
+
+	/* Lists of queues and potentially slow path queues
+	 * so we can dispatch IRQs.
+	 */
+	spinlock_t lock;
+	struct list_head virtqueues;
+	struct list_head slow_virtqueues;
+
+	/* Array of all virtqueues reported in the
+	 * PCI common config num_queues field
+	 */
+	struct virtio_pci_vq_info **vqs;
+
+	struct virtio_pci_admin_vq admin_vq;
+
+	/* MSI-X support */
+	int msix_enabled;
+	int intx_enabled;
+	cpumask_var_t *msix_affinity_masks;
+	/* Name strings for interrupts. This size should be enough,
+	 * and I'm too lazy to allocate each name separately. */
+	char (*msix_names)[256];
+	/* Number of available vectors */
+	unsigned int msix_vectors;
+	/* Vectors allocated, excluding per-vq vectors if any */
+	unsigned int msix_used_vectors;
+
+	/* Whether we have vector per vq */
+	bool per_vq_vectors;
+
+	struct virtqueue *(*setup_vq)(struct virtio_pci_device *vp_dev,
+				      struct virtio_pci_vq_info *info,
+				      unsigned int idx,
+				      void (*callback)(struct virtqueue *vq),
+				      const char *name,
+				      bool ctx,
+				      u16 msix_vec);
+	void (*del_vq)(struct virtio_pci_vq_info *info);
+
+	u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
+	int (*avq_index)(struct virtio_device *vdev, u16 *index, u16 *num);
+};
+
+/* Constants for MSI-X */
+/* Use first vector for configuration changes, second and the rest for
+ * virtqueues Thus, we need at least 2 vectors for MSI. */
+enum {
+	VP_MSIX_CONFIG_VECTOR = 0,
+	VP_MSIX_VQ_VECTOR = 1,
+};
+
+/* Convert a generic virtio device to our structure */
+static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
+{
+	return container_of(vdev, struct virtio_pci_device, vdev);
+}
+
+/* wait for pending irq handlers */
+void vp_synchronize_vectors(struct virtio_device *vdev);
+/* the notify function used when creating a virt queue */
+bool vp_notify(struct virtqueue *vq);
+/* the config->del_vqs() implementation */
+void vp_del_vqs(struct virtio_device *vdev);
+/* the config->find_vqs() implementation */
+int vp_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
+		struct virtqueue *vqs[], struct virtqueue_info vqs_info[],
+		struct irq_affinity *desc);
+const char *vp_bus_name(struct virtio_device *vdev);
+
+/* Setup the affinity for a virtqueue:
+ * - force the affinity for per vq vector
+ * - OR over all affinities for shared MSI
+ * - ignore the affinity request if we're using INTX
+ */
+int vp_set_vq_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask);
+
+const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index);
+
+#if IS_ENABLED(CONFIG_VIRTIO_PCI_LEGACY)
+int virtio_pci_legacy_probe(struct virtio_pci_device *);
+void virtio_pci_legacy_remove(struct virtio_pci_device *);
+#else
+static inline int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev)
+{
+	return -ENODEV;
+}
+static inline void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev)
+{
+}
+#endif
+int virtio_pci_modern_probe(struct virtio_pci_device *);
+void virtio_pci_modern_remove(struct virtio_pci_device *);
+
+struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev);
+
+#define VIRTIO_LEGACY_ADMIN_CMD_BITMAP \
+	(BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO))
+
+#define VIRTIO_DEV_PARTS_ADMIN_CMD_BITMAP \
+	(BIT_ULL(VIRTIO_ADMIN_CMD_CAP_ID_LIST_QUERY) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_DRIVER_CAP_SET) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_DEVICE_CAP_GET) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_RESOURCE_OBJ_CREATE) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_RESOURCE_OBJ_DESTROY) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_DEV_PARTS_METADATA_GET) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_DEV_PARTS_GET) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_DEV_PARTS_SET) | \
+	 BIT_ULL(VIRTIO_ADMIN_CMD_DEV_MODE_SET))
+
+/* Unlike modern drivers which support hardware virtio devices, legacy drivers
+ * assume software-based devices: e.g. they don't use proper memory barriers
+ * on ARM, use big endian on PPC, etc. X86 drivers are mostly ok though, more
+ * or less by chance. For now, only support legacy IO on X86.
+ */
+#ifdef CONFIG_VIRTIO_PCI_ADMIN_LEGACY
+#define VIRTIO_ADMIN_CMD_BITMAP (VIRTIO_LEGACY_ADMIN_CMD_BITMAP | \
+				 VIRTIO_DEV_PARTS_ADMIN_CMD_BITMAP)
+#else
+#define VIRTIO_ADMIN_CMD_BITMAP VIRTIO_DEV_PARTS_ADMIN_CMD_BITMAP
+#endif
+
+bool vp_is_avq(struct virtio_device *vdev, unsigned int index);
+void vp_modern_avq_done(struct virtqueue *vq);
+int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
+			     struct virtio_admin_cmd *cmd);
+
+#endif

linux-7.2.3/drivers/virtio/virtio_pci_legacy.c

@@ -0,0 +1,236 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Virtio PCI driver - legacy device support
+ *
+ * This module allows virtio devices to be used over a virtual PCI device.
+ * This can be used with QEMU based VMMs like KVM or Xen.
+ *
+ * Copyright IBM Corp. 2007
+ * Copyright Red Hat, Inc. 2014
+ *
+ * Authors:
+ *  Anthony Liguori  <aliguori@us.ibm.com>
+ *  Rusty Russell <rusty@rustcorp.com.au>
+ *  Michael S. Tsirkin <mst@redhat.com>
+ */
+
+#include "linux/virtio_pci_legacy.h"
+#include "virtio_pci_common.h"
+
+/* virtio config->get_features() implementation */
+static u64 vp_get_features(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	/* When someone needs more than 32 feature bits, we'll need to
+	 * steal a bit to indicate that the rest are somewhere else. */
+	return vp_legacy_get_features(&vp_dev->ldev);
+}
+
+/* virtio config->finalize_features() implementation */
+static int vp_finalize_features(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	/* Give virtio_ring a chance to accept features. */
+	vring_transport_features(vdev);
+
+	/* Make sure we don't have any features > 32 bits! */
+	BUG_ON((u32)vdev->features != vdev->features);
+
+	/* We only support 32 feature bits. */
+	vp_legacy_set_features(&vp_dev->ldev, vdev->features);
+
+	return 0;
+}
+
+/* virtio config->get() implementation */
+static void vp_get(struct virtio_device *vdev, unsigned int offset,
+		   void *buf, unsigned int len)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	void __iomem *ioaddr = vp_dev->ldev.ioaddr +
+			VIRTIO_PCI_CONFIG_OFF(vp_dev->msix_enabled) +
+			offset;
+	u8 *ptr = buf;
+	int i;
+
+	for (i = 0; i < len; i++)
+		ptr[i] = ioread8(ioaddr + i);
+}
+
+/* the config->set() implementation.  it's symmetric to the config->get()
+ * implementation */
+static void vp_set(struct virtio_device *vdev, unsigned int offset,
+		   const void *buf, unsigned int len)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	void __iomem *ioaddr = vp_dev->ldev.ioaddr +
+			VIRTIO_PCI_CONFIG_OFF(vp_dev->msix_enabled) +
+			offset;
+	const u8 *ptr = buf;
+	int i;
+
+	for (i = 0; i < len; i++)
+		iowrite8(ptr[i], ioaddr + i);
+}
+
+/* config->{get,set}_status() implementations */
+static u8 vp_get_status(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	return vp_legacy_get_status(&vp_dev->ldev);
+}
+
+static void vp_set_status(struct virtio_device *vdev, u8 status)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	/* We should never be setting status to 0. */
+	BUG_ON(status == 0);
+	vp_legacy_set_status(&vp_dev->ldev, status);
+}
+
+static void vp_reset(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	/* 0 status means a reset. */
+	vp_legacy_set_status(&vp_dev->ldev, 0);
+	/* Flush out the status write, and flush in device writes,
+	 * including MSi-X interrupts, if any. */
+	vp_legacy_get_status(&vp_dev->ldev);
+	/* Flush pending VQ/configuration callbacks. */
+	vp_synchronize_vectors(vdev);
+}
+
+static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
+{
+	return vp_legacy_config_vector(&vp_dev->ldev, vector);
+}
+
+static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
+				  struct virtio_pci_vq_info *info,
+				  unsigned int index,
+				  void (*callback)(struct virtqueue *vq),
+				  const char *name,
+				  bool ctx,
+				  u16 msix_vec)
+{
+	struct virtqueue *vq;
+	u16 num;
+	int err;
+	u64 q_pfn;
+
+	/* Check if queue is either not available or already active. */
+	num = vp_legacy_get_queue_size(&vp_dev->ldev, index);
+	if (!num || vp_legacy_get_queue_enable(&vp_dev->ldev, index))
+		return ERR_PTR(-ENOENT);
+
+	info->msix_vector = msix_vec;
+
+	/* create the vring */
+	vq = vring_create_virtqueue(index, num,
+				    VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
+				    true, false, ctx,
+				    vp_notify, callback, name);
+	if (!vq)
+		return ERR_PTR(-ENOMEM);
+
+	vq->num_max = num;
+
+	q_pfn = virtqueue_get_desc_addr(vq) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT;
+	if (q_pfn >> 32) {
+		dev_err(&vp_dev->pci_dev->dev,
+			"platform bug: legacy virtio-pci must not be used with RAM above 0x%llxGB\n",
+			0x1ULL << (32 + PAGE_SHIFT - 30));
+		err = -E2BIG;
+		goto out_del_vq;
+	}
+
+	/* activate the queue */
+	vp_legacy_set_queue_address(&vp_dev->ldev, index, q_pfn);
+
+	vq->priv = (void __force *)vp_dev->ldev.ioaddr + VIRTIO_PCI_QUEUE_NOTIFY;
+
+	if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
+		msix_vec = vp_legacy_queue_vector(&vp_dev->ldev, index, msix_vec);
+		if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
+			err = -EBUSY;
+			goto out_deactivate;
+		}
+	}
+
+	return vq;
+
+out_deactivate:
+	vp_legacy_set_queue_address(&vp_dev->ldev, index, 0);
+out_del_vq:
+	vring_del_virtqueue(vq);
+	return ERR_PTR(err);
+}
+
+static void del_vq(struct virtio_pci_vq_info *info)
+{
+	struct virtqueue *vq = info->vq;
+	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+
+	if (vp_dev->msix_enabled) {
+		vp_legacy_queue_vector(&vp_dev->ldev, vq->index,
+				VIRTIO_MSI_NO_VECTOR);
+		/* Flush the write out to device */
+		ioread8(vp_dev->ldev.ioaddr + VIRTIO_PCI_ISR);
+	}
+
+	/* Select and deactivate the queue */
+	vp_legacy_set_queue_address(&vp_dev->ldev, vq->index, 0);
+
+	vring_del_virtqueue(vq);
+}
+
+static const struct virtio_config_ops virtio_pci_config_ops = {
+	.get		= vp_get,
+	.set		= vp_set,
+	.get_status	= vp_get_status,
+	.set_status	= vp_set_status,
+	.reset		= vp_reset,
+	.find_vqs	= vp_find_vqs,
+	.del_vqs	= vp_del_vqs,
+	.synchronize_cbs = vp_synchronize_vectors,
+	.get_features	= vp_get_features,
+	.finalize_features = vp_finalize_features,
+	.bus_name	= vp_bus_name,
+	.set_vq_affinity = vp_set_vq_affinity,
+	.get_vq_affinity = vp_get_vq_affinity,
+};
+
+/* the PCI probing function */
+int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev)
+{
+	struct virtio_pci_legacy_device *ldev = &vp_dev->ldev;
+	struct pci_dev *pci_dev = vp_dev->pci_dev;
+	int rc;
+
+	ldev->pci_dev = pci_dev;
+
+	rc = vp_legacy_probe(ldev);
+	if (rc)
+		return rc;
+
+	vp_dev->isr = ldev->isr;
+	vp_dev->vdev.id = ldev->id;
+
+	vp_dev->vdev.config = &virtio_pci_config_ops;
+
+	vp_dev->config_vector = vp_config_vector;
+	vp_dev->setup_vq = setup_vq;
+	vp_dev->del_vq = del_vq;
+	vp_dev->is_legacy = true;
+
+	return 0;
+}
+
+void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev)
+{
+	struct virtio_pci_legacy_device *ldev = &vp_dev->ldev;
+
+	vp_legacy_remove(ldev);
+}

linux-7.2.3/drivers/virtio/virtio_pci_legacy_dev.c

@@ -0,0 +1,222 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include "linux/virtio_pci.h"
+#include <linux/virtio_pci_legacy.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+
+/*
+ * vp_legacy_probe: probe the legacy virtio pci device, note that the
+ * caller is required to enable PCI device before calling this function.
+ * @ldev: the legacy virtio-pci device
+ *
+ * Return 0 on succeed otherwise fail
+ */
+int vp_legacy_probe(struct virtio_pci_legacy_device *ldev)
+{
+	struct pci_dev *pci_dev = ldev->pci_dev;
+	int rc;
+
+	/* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */
+	if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f)
+		return -ENODEV;
+
+	if (pci_dev->revision != VIRTIO_PCI_ABI_VERSION)
+		return -ENODEV;
+
+	rc = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(64));
+	if (rc) {
+		rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32));
+	} else {
+		/*
+		 * The virtio ring base address is expressed as a 32-bit PFN,
+		 * with a page size of 1 << VIRTIO_PCI_QUEUE_ADDR_SHIFT.
+		 */
+		dma_set_coherent_mask(&pci_dev->dev,
+				DMA_BIT_MASK(32 + VIRTIO_PCI_QUEUE_ADDR_SHIFT));
+	}
+
+	if (rc)
+		dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
+
+	rc = pci_request_region(pci_dev, 0, "virtio-pci-legacy");
+	if (rc)
+		return rc;
+
+	ldev->ioaddr = pci_iomap(pci_dev, 0, 0);
+	if (!ldev->ioaddr) {
+		rc = -EIO;
+		goto err_iomap;
+	}
+
+	ldev->isr = ldev->ioaddr + VIRTIO_PCI_ISR;
+
+	ldev->id.vendor = pci_dev->subsystem_vendor;
+	ldev->id.device = pci_dev->subsystem_device;
+
+	return 0;
+err_iomap:
+	pci_release_region(pci_dev, 0);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(vp_legacy_probe);
+
+/*
+ * vp_legacy_probe: remove and cleanup the legacy virtio pci device
+ * @ldev: the legacy virtio-pci device
+ */
+void vp_legacy_remove(struct virtio_pci_legacy_device *ldev)
+{
+	struct pci_dev *pci_dev = ldev->pci_dev;
+
+	pci_iounmap(pci_dev, ldev->ioaddr);
+	pci_release_region(pci_dev, 0);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_remove);
+
+/*
+ * vp_legacy_get_features - get features from device
+ * @ldev: the legacy virtio-pci device
+ *
+ * Returns the features read from the device
+ */
+u64 vp_legacy_get_features(struct virtio_pci_legacy_device *ldev)
+{
+
+	return ioread32(ldev->ioaddr + VIRTIO_PCI_HOST_FEATURES);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_get_features);
+
+/*
+ * vp_legacy_get_driver_features - get driver features from device
+ * @ldev: the legacy virtio-pci device
+ *
+ * Returns the driver features read from the device
+ */
+u64 vp_legacy_get_driver_features(struct virtio_pci_legacy_device *ldev)
+{
+	return ioread32(ldev->ioaddr + VIRTIO_PCI_GUEST_FEATURES);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_get_driver_features);
+
+/*
+ * vp_legacy_set_features - set features to device
+ * @ldev: the legacy virtio-pci device
+ * @features: the features set to device
+ */
+void vp_legacy_set_features(struct virtio_pci_legacy_device *ldev,
+			    u32 features)
+{
+	iowrite32(features, ldev->ioaddr + VIRTIO_PCI_GUEST_FEATURES);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_set_features);
+
+/*
+ * vp_legacy_get_status - get the device status
+ * @ldev: the legacy virtio-pci device
+ *
+ * Returns the status read from device
+ */
+u8 vp_legacy_get_status(struct virtio_pci_legacy_device *ldev)
+{
+	return ioread8(ldev->ioaddr + VIRTIO_PCI_STATUS);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_get_status);
+
+/*
+ * vp_legacy_set_status - set status to device
+ * @ldev: the legacy virtio-pci device
+ * @status: the status set to device
+ */
+void vp_legacy_set_status(struct virtio_pci_legacy_device *ldev,
+				 u8 status)
+{
+	iowrite8(status, ldev->ioaddr + VIRTIO_PCI_STATUS);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_set_status);
+
+/*
+ * vp_legacy_queue_vector - set the MSIX vector for a specific virtqueue
+ * @ldev: the legacy virtio-pci device
+ * @index: queue index
+ * @vector: the queue vector
+ *
+ * Returns the queue vector read from the device
+ */
+u16 vp_legacy_queue_vector(struct virtio_pci_legacy_device *ldev,
+			   u16 index, u16 vector)
+{
+	iowrite16(index, ldev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+	iowrite16(vector, ldev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+	/* Flush the write out to device */
+	return ioread16(ldev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_queue_vector);
+
+/*
+ * vp_legacy_config_vector - set the vector for config interrupt
+ * @ldev: the legacy virtio-pci device
+ * @vector: the config vector
+ *
+ * Returns the config vector read from the device
+ */
+u16 vp_legacy_config_vector(struct virtio_pci_legacy_device *ldev,
+			    u16 vector)
+{
+	/* Setup the vector used for configuration events */
+	iowrite16(vector, ldev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+	/* Verify we had enough resources to assign the vector */
+	/* Will also flush the write out to device */
+	return ioread16(ldev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_config_vector);
+
+/*
+ * vp_legacy_set_queue_address - set the virtqueue address
+ * @ldev: the legacy virtio-pci device
+ * @index: the queue index
+ * @queue_pfn: pfn of the virtqueue
+ */
+void vp_legacy_set_queue_address(struct virtio_pci_legacy_device *ldev,
+			     u16 index, u32 queue_pfn)
+{
+	iowrite16(index, ldev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+	iowrite32(queue_pfn, ldev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_set_queue_address);
+
+/*
+ * vp_legacy_get_queue_enable - enable a virtqueue
+ * @ldev: the legacy virtio-pci device
+ * @index: the queue index
+ *
+ * Returns whether a virtqueue is enabled or not
+ */
+bool vp_legacy_get_queue_enable(struct virtio_pci_legacy_device *ldev,
+				u16 index)
+{
+	iowrite16(index, ldev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+	return ioread32(ldev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_get_queue_enable);
+
+/*
+ * vp_legacy_get_queue_size - get size for a virtqueue
+ * @ldev: the legacy virtio-pci device
+ * @index: the queue index
+ *
+ * Returns the size of the virtqueue
+ */
+u16 vp_legacy_get_queue_size(struct virtio_pci_legacy_device *ldev,
+			     u16 index)
+{
+	iowrite16(index, ldev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+	return ioread16(ldev->ioaddr + VIRTIO_PCI_QUEUE_NUM);
+}
+EXPORT_SYMBOL_GPL(vp_legacy_get_queue_size);
+
+MODULE_VERSION("0.1");
+MODULE_DESCRIPTION("Legacy Virtio PCI Device");
+MODULE_AUTHOR("Wu Zongyong <wuzongyong@linux.alibaba.com>");
+MODULE_LICENSE("GPL");

linux-7.2.3/drivers/virtio/virtio_pci_modern_dev.c

@@ -0,0 +1,758 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/virtio_pci_modern.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+
+/*
+ * vp_modern_map_capability - map a part of virtio pci capability
+ * @mdev: the modern virtio-pci device
+ * @off: offset of the capability
+ * @minlen: minimal length of the capability
+ * @align: align requirement
+ * @start: start from the capability
+ * @size: map size
+ * @len: the length that is actually mapped
+ * @pa: physical address of the capability
+ *
+ * Returns the io address of for the part of the capability
+ */
+static void __iomem *
+vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off,
+			 size_t minlen, u32 align, u32 start, u32 size,
+			 size_t *len, resource_size_t *pa)
+{
+	struct pci_dev *dev = mdev->pci_dev;
+	u8 bar;
+	u32 offset, length;
+	void __iomem *p;
+
+	pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap,
+						 bar),
+			     &bar);
+	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset),
+			     &offset);
+	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length),
+			      &length);
+
+	/* Check if the BAR may have changed since we requested the region. */
+	if (bar >= PCI_STD_NUM_BARS || !(mdev->modern_bars & (1 << bar))) {
+		dev_err(&dev->dev,
+			"virtio_pci: bar unexpectedly changed to %u\n", bar);
+		return NULL;
+	}
+
+	if (length <= start) {
+		dev_err(&dev->dev,
+			"virtio_pci: bad capability len %u (>%u expected)\n",
+			length, start);
+		return NULL;
+	}
+
+	if (length - start < minlen) {
+		dev_err(&dev->dev,
+			"virtio_pci: bad capability len %u (>=%zu expected)\n",
+			length, minlen);
+		return NULL;
+	}
+
+	length -= start;
+
+	if (start + offset < offset) {
+		dev_err(&dev->dev,
+			"virtio_pci: map wrap-around %u+%u\n",
+			start, offset);
+		return NULL;
+	}
+
+	offset += start;
+
+	if (offset & (align - 1)) {
+		dev_err(&dev->dev,
+			"virtio_pci: offset %u not aligned to %u\n",
+			offset, align);
+		return NULL;
+	}
+
+	if (length > size)
+		length = size;
+
+	if (len)
+		*len = length;
+
+	if (minlen + offset < minlen ||
+	    minlen + offset > pci_resource_len(dev, bar)) {
+		dev_err(&dev->dev,
+			"virtio_pci: map virtio %zu@%u "
+			"out of range on bar %i length %lu\n",
+			minlen, offset,
+			bar, (unsigned long)pci_resource_len(dev, bar));
+		return NULL;
+	}
+
+	p = pci_iomap_range(dev, bar, offset, length);
+	if (!p)
+		dev_err(&dev->dev,
+			"virtio_pci: unable to map virtio %u@%u on bar %i\n",
+			length, offset, bar);
+	else if (pa)
+		*pa = pci_resource_start(dev, bar) + offset;
+
+	return p;
+}
+
+/**
+ * virtio_pci_find_capability - walk capabilities to find device info.
+ * @dev: the pci device
+ * @cfg_type: the VIRTIO_PCI_CAP_* value we seek
+ * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
+ * @bars: the bitmask of BARs
+ *
+ * Returns offset of the capability, or 0.
+ */
+static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
+					     u32 ioresource_types, int *bars)
+{
+	int pos;
+
+	for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR);
+	     pos > 0;
+	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
+		u8 type, bar;
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+							 cfg_type),
+				     &type);
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+							 bar),
+				     &bar);
+
+		/* Ignore structures with reserved BAR values */
+		if (bar >= PCI_STD_NUM_BARS)
+			continue;
+
+		if (type == cfg_type) {
+			if (pci_resource_len(dev, bar) &&
+			    pci_resource_flags(dev, bar) & ioresource_types) {
+				*bars |= (1 << bar);
+				return pos;
+			}
+		}
+	}
+	return 0;
+}
+
+/* This is part of the ABI.  Don't screw with it. */
+static inline void check_offsets(void)
+{
+	/* Note: disk space was harmed in compilation of this function. */
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR !=
+		     offsetof(struct virtio_pci_cap, cap_vndr));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT !=
+		     offsetof(struct virtio_pci_cap, cap_next));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN !=
+		     offsetof(struct virtio_pci_cap, cap_len));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_CFG_TYPE !=
+		     offsetof(struct virtio_pci_cap, cfg_type));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_BAR !=
+		     offsetof(struct virtio_pci_cap, bar));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET !=
+		     offsetof(struct virtio_pci_cap, offset));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH !=
+		     offsetof(struct virtio_pci_cap, length));
+	BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT !=
+		     offsetof(struct virtio_pci_notify_cap,
+			      notify_off_multiplier));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT !=
+		     offsetof(struct virtio_pci_common_cfg,
+			      device_feature_select));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF !=
+		     offsetof(struct virtio_pci_common_cfg, device_feature));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT !=
+		     offsetof(struct virtio_pci_common_cfg,
+			      guest_feature_select));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF !=
+		     offsetof(struct virtio_pci_common_cfg, guest_feature));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX !=
+		     offsetof(struct virtio_pci_common_cfg, msix_config));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ !=
+		     offsetof(struct virtio_pci_common_cfg, num_queues));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS !=
+		     offsetof(struct virtio_pci_common_cfg, device_status));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION !=
+		     offsetof(struct virtio_pci_common_cfg, config_generation));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT !=
+		     offsetof(struct virtio_pci_common_cfg, queue_select));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE !=
+		     offsetof(struct virtio_pci_common_cfg, queue_size));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX !=
+		     offsetof(struct virtio_pci_common_cfg, queue_msix_vector));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE !=
+		     offsetof(struct virtio_pci_common_cfg, queue_enable));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF !=
+		     offsetof(struct virtio_pci_common_cfg, queue_notify_off));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO !=
+		     offsetof(struct virtio_pci_common_cfg, queue_desc_lo));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI !=
+		     offsetof(struct virtio_pci_common_cfg, queue_desc_hi));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO !=
+		     offsetof(struct virtio_pci_common_cfg, queue_avail_lo));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI !=
+		     offsetof(struct virtio_pci_common_cfg, queue_avail_hi));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO !=
+		     offsetof(struct virtio_pci_common_cfg, queue_used_lo));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI !=
+		     offsetof(struct virtio_pci_common_cfg, queue_used_hi));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NDATA !=
+		     offsetof(struct virtio_pci_modern_common_cfg, queue_notify_data));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_RESET !=
+		     offsetof(struct virtio_pci_modern_common_cfg, queue_reset));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_ADM_Q_IDX !=
+		     offsetof(struct virtio_pci_modern_common_cfg, admin_queue_index));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_ADM_Q_NUM !=
+		     offsetof(struct virtio_pci_modern_common_cfg, admin_queue_num));
+}
+
+/*
+ * vp_modern_probe: probe the modern virtio pci device, note that the
+ * caller is required to enable PCI device before calling this function.
+ * @mdev: the modern virtio-pci device
+ *
+ * Return 0 on succeed otherwise fail
+ */
+int vp_modern_probe(struct virtio_pci_modern_device *mdev)
+{
+	struct pci_dev *pci_dev = mdev->pci_dev;
+	int err, common, isr, notify, device;
+	u32 notify_length;
+	u32 notify_offset;
+	int devid;
+
+	check_offsets();
+
+	if (mdev->device_id_check) {
+		devid = mdev->device_id_check(pci_dev);
+		if (devid < 0)
+			return devid;
+		mdev->id.device = devid;
+	} else {
+		/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
+		if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
+			return -ENODEV;
+
+		if (pci_dev->device < 0x1040) {
+			/* Transitional devices: use the PCI subsystem device id as
+			 * virtio device id, same as legacy driver always did.
+			 */
+			mdev->id.device = pci_dev->subsystem_device;
+		} else {
+			/* Modern devices: simply use PCI device id, but start from 0x1040. */
+			mdev->id.device = pci_dev->device - 0x1040;
+		}
+	}
+	mdev->id.vendor = pci_dev->subsystem_vendor;
+
+	/* check for a common config: if not, use legacy mode (bar 0). */
+	common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
+					    IORESOURCE_IO | IORESOURCE_MEM,
+					    &mdev->modern_bars);
+	if (!common) {
+		dev_info(&pci_dev->dev,
+			 "virtio_pci: leaving for legacy driver\n");
+		return -ENODEV;
+	}
+
+	/* If common is there, these should be too... */
+	isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
+					 IORESOURCE_IO | IORESOURCE_MEM,
+					 &mdev->modern_bars);
+	notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
+					    IORESOURCE_IO | IORESOURCE_MEM,
+					    &mdev->modern_bars);
+	if (!isr || !notify) {
+		dev_err(&pci_dev->dev,
+			"virtio_pci: missing capabilities %i/%i/%i\n",
+			common, isr, notify);
+		return -EINVAL;
+	}
+
+	err = dma_set_mask_and_coherent(&pci_dev->dev,
+					mdev->dma_mask ? : DMA_BIT_MASK(64));
+	if (err)
+		err = dma_set_mask_and_coherent(&pci_dev->dev,
+						DMA_BIT_MASK(32));
+	if (err)
+		dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
+
+	/* Device capability is only mandatory for devices that have
+	 * device-specific configuration.
+	 */
+	device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
+					    IORESOURCE_IO | IORESOURCE_MEM,
+					    &mdev->modern_bars);
+
+	err = pci_request_selected_regions(pci_dev, mdev->modern_bars,
+					   "virtio-pci-modern");
+	if (err)
+		return err;
+
+	err = -EINVAL;
+	mdev->common = vp_modern_map_capability(mdev, common,
+			      sizeof(struct virtio_pci_common_cfg), 4, 0,
+			      offsetofend(struct virtio_pci_modern_common_cfg,
+					  admin_queue_num),
+			      &mdev->common_len, NULL);
+	if (!mdev->common)
+		goto err_map_common;
+	mdev->isr = vp_modern_map_capability(mdev, isr, sizeof(u8), 1,
+					     0, 1,
+					     NULL, NULL);
+	if (!mdev->isr)
+		goto err_map_isr;
+
+	/* Read notify_off_multiplier from config space. */
+	pci_read_config_dword(pci_dev,
+			      notify + offsetof(struct virtio_pci_notify_cap,
+						notify_off_multiplier),
+			      &mdev->notify_offset_multiplier);
+	/* Read notify length and offset from config space. */
+	pci_read_config_dword(pci_dev,
+			      notify + offsetof(struct virtio_pci_notify_cap,
+						cap.length),
+			      &notify_length);
+
+	pci_read_config_dword(pci_dev,
+			      notify + offsetof(struct virtio_pci_notify_cap,
+						cap.offset),
+			      &notify_offset);
+
+	/* We don't know how many VQs we'll map, ahead of the time.
+	 * If notify length is small, map it all now.
+	 * Otherwise, map each VQ individually later.
+	 */
+	if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) {
+		mdev->notify_base = vp_modern_map_capability(mdev, notify,
+							     2, 2,
+							     0, notify_length,
+							     &mdev->notify_len,
+							     &mdev->notify_pa);
+		if (!mdev->notify_base)
+			goto err_map_notify;
+	} else {
+		mdev->notify_map_cap = notify;
+	}
+
+	/* Again, we don't know how much we should map, but PAGE_SIZE
+	 * is more than enough for all existing devices.
+	 */
+	if (device) {
+		mdev->device = vp_modern_map_capability(mdev, device, 0, 4,
+							0, PAGE_SIZE,
+							&mdev->device_len,
+							NULL);
+		if (!mdev->device)
+			goto err_map_device;
+	}
+
+	return 0;
+
+err_map_device:
+	if (mdev->notify_base)
+		pci_iounmap(pci_dev, mdev->notify_base);
+err_map_notify:
+	pci_iounmap(pci_dev, mdev->isr);
+err_map_isr:
+	pci_iounmap(pci_dev, mdev->common);
+err_map_common:
+	pci_release_selected_regions(pci_dev, mdev->modern_bars);
+	return err;
+}
+EXPORT_SYMBOL_GPL(vp_modern_probe);
+
+/*
+ * vp_modern_remove: remove and cleanup the modern virtio pci device
+ * @mdev: the modern virtio-pci device
+ */
+void vp_modern_remove(struct virtio_pci_modern_device *mdev)
+{
+	struct pci_dev *pci_dev = mdev->pci_dev;
+
+	if (mdev->device)
+		pci_iounmap(pci_dev, mdev->device);
+	if (mdev->notify_base)
+		pci_iounmap(pci_dev, mdev->notify_base);
+	pci_iounmap(pci_dev, mdev->isr);
+	pci_iounmap(pci_dev, mdev->common);
+	pci_release_selected_regions(pci_dev, mdev->modern_bars);
+}
+EXPORT_SYMBOL_GPL(vp_modern_remove);
+
+/*
+ * vp_modern_get_extended_features - get features from device
+ * @mdev: the modern virtio-pci device
+ * @features: the features array to be filled
+ *
+ * Fill the specified features array with the features read from the device
+ */
+void vp_modern_get_extended_features(struct virtio_pci_modern_device *mdev,
+				     u64 *features)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+	int i;
+
+	virtio_features_zero(features);
+	for (i = 0; i < VIRTIO_FEATURES_BITS / 32; i++) {
+		u64 cur;
+
+		vp_iowrite32(i, &cfg->device_feature_select);
+		cur = vp_ioread32(&cfg->device_feature);
+		features[i >> 1] |= cur << (32 * (i & 1));
+	}
+}
+EXPORT_SYMBOL_GPL(vp_modern_get_extended_features);
+
+/*
+ * vp_modern_get_driver_features - get driver features from device
+ * @mdev: the modern virtio-pci device
+ * @features: the features array to be filled
+ *
+ * Fill the specified features array with the driver features read from the
+ * device
+ */
+void
+vp_modern_get_driver_extended_features(struct virtio_pci_modern_device *mdev,
+				       u64 *features)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+	int i;
+
+	virtio_features_zero(features);
+	for (i = 0; i < VIRTIO_FEATURES_BITS / 32; i++) {
+		u64 cur;
+
+		vp_iowrite32(i, &cfg->guest_feature_select);
+		cur = vp_ioread32(&cfg->guest_feature);
+		features[i >> 1] |= cur << (32 * (i & 1));
+	}
+}
+EXPORT_SYMBOL_GPL(vp_modern_get_driver_extended_features);
+
+/*
+ * vp_modern_set_extended_features - set features to device
+ * @mdev: the modern virtio-pci device
+ * @features: the features set to device
+ */
+void vp_modern_set_extended_features(struct virtio_pci_modern_device *mdev,
+				     const u64 *features)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+	int i;
+
+	for (i = 0; i < VIRTIO_FEATURES_BITS / 32; i++) {
+		u32 cur = features[i >> 1] >> (32 * (i & 1));
+
+		vp_iowrite32(i, &cfg->guest_feature_select);
+		vp_iowrite32(cur, &cfg->guest_feature);
+	}
+}
+EXPORT_SYMBOL_GPL(vp_modern_set_extended_features);
+
+/*
+ * vp_modern_generation - get the device genreation
+ * @mdev: the modern virtio-pci device
+ *
+ * Returns the genreation read from device
+ */
+u32 vp_modern_generation(struct virtio_pci_modern_device *mdev)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	return vp_ioread8(&cfg->config_generation);
+}
+EXPORT_SYMBOL_GPL(vp_modern_generation);
+
+/*
+ * vp_modern_get_status - get the device status
+ * @mdev: the modern virtio-pci device
+ *
+ * Returns the status read from device
+ */
+u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	return vp_ioread8(&cfg->device_status);
+}
+EXPORT_SYMBOL_GPL(vp_modern_get_status);
+
+/*
+ * vp_modern_set_status - set status to device
+ * @mdev: the modern virtio-pci device
+ * @status: the status set to device
+ */
+void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
+				 u8 status)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	/*
+	 * Per memory-barriers.txt, wmb() is not needed to guarantee
+	 * that the cache coherent memory writes have completed
+	 * before writing to the MMIO region.
+	 */
+	vp_iowrite8(status, &cfg->device_status);
+}
+EXPORT_SYMBOL_GPL(vp_modern_set_status);
+
+/*
+ * vp_modern_get_queue_reset - get the queue reset status
+ * @mdev: the modern virtio-pci device
+ * @index: queue index
+ */
+int vp_modern_get_queue_reset(struct virtio_pci_modern_device *mdev, u16 index)
+{
+	struct virtio_pci_modern_common_cfg __iomem *cfg;
+
+	cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common;
+
+	vp_iowrite16(index, &cfg->cfg.queue_select);
+	return vp_ioread16(&cfg->queue_reset);
+}
+EXPORT_SYMBOL_GPL(vp_modern_get_queue_reset);
+
+/*
+ * vp_modern_set_queue_reset - reset the queue
+ * @mdev: the modern virtio-pci device
+ * @index: queue index
+ */
+void vp_modern_set_queue_reset(struct virtio_pci_modern_device *mdev, u16 index)
+{
+	struct virtio_pci_modern_common_cfg __iomem *cfg;
+
+	cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common;
+
+	vp_iowrite16(index, &cfg->cfg.queue_select);
+	vp_iowrite16(1, &cfg->queue_reset);
+
+	while (vp_ioread16(&cfg->queue_reset))
+		msleep(1);
+
+	while (vp_ioread16(&cfg->cfg.queue_enable))
+		msleep(1);
+}
+EXPORT_SYMBOL_GPL(vp_modern_set_queue_reset);
+
+/*
+ * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: queue index
+ * @vector: the queue vector
+ *
+ * Returns the queue vector read from the device
+ */
+u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
+			   u16 index, u16 vector)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	vp_iowrite16(index, &cfg->queue_select);
+	vp_iowrite16(vector, &cfg->queue_msix_vector);
+	/* Flush the write out to device */
+	return vp_ioread16(&cfg->queue_msix_vector);
+}
+EXPORT_SYMBOL_GPL(vp_modern_queue_vector);
+
+/*
+ * vp_modern_config_vector - set the vector for config interrupt
+ * @mdev: the modern virtio-pci device
+ * @vector: the config vector
+ *
+ * Returns the config vector read from the device
+ */
+u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev,
+			    u16 vector)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	/* Setup the vector used for configuration events */
+	vp_iowrite16(vector, &cfg->msix_config);
+	/* Verify we had enough resources to assign the vector */
+	/* Will also flush the write out to device */
+	return vp_ioread16(&cfg->msix_config);
+}
+EXPORT_SYMBOL_GPL(vp_modern_config_vector);
+
+/*
+ * vp_modern_queue_address - set the virtqueue address
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ * @desc_addr: address of the descriptor area
+ * @driver_addr: address of the driver area
+ * @device_addr: address of the device area
+ */
+void vp_modern_queue_address(struct virtio_pci_modern_device *mdev,
+			     u16 index, u64 desc_addr, u64 driver_addr,
+			     u64 device_addr)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+
+	vp_iowrite16(index, &cfg->queue_select);
+
+	vp_iowrite64_twopart(desc_addr, &cfg->queue_desc_lo,
+			     &cfg->queue_desc_hi);
+	vp_iowrite64_twopart(driver_addr, &cfg->queue_avail_lo,
+			     &cfg->queue_avail_hi);
+	vp_iowrite64_twopart(device_addr, &cfg->queue_used_lo,
+			     &cfg->queue_used_hi);
+}
+EXPORT_SYMBOL_GPL(vp_modern_queue_address);
+
+/*
+ * vp_modern_set_queue_enable - enable a virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ * @enable: whether the virtqueue is enable or not
+ */
+void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev,
+				u16 index, bool enable)
+{
+	vp_iowrite16(index, &mdev->common->queue_select);
+	vp_iowrite16(enable, &mdev->common->queue_enable);
+}
+EXPORT_SYMBOL_GPL(vp_modern_set_queue_enable);
+
+/*
+ * vp_modern_get_queue_enable - enable a virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ *
+ * Returns whether a virtqueue is enabled or not
+ */
+bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev,
+				u16 index)
+{
+	vp_iowrite16(index, &mdev->common->queue_select);
+
+	return vp_ioread16(&mdev->common->queue_enable);
+}
+EXPORT_SYMBOL_GPL(vp_modern_get_queue_enable);
+
+/*
+ * vp_modern_set_queue_size - set size for a virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ * @size: the size of the virtqueue
+ */
+void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev,
+			      u16 index, u16 size)
+{
+	vp_iowrite16(index, &mdev->common->queue_select);
+	vp_iowrite16(size, &mdev->common->queue_size);
+
+}
+EXPORT_SYMBOL_GPL(vp_modern_set_queue_size);
+
+/*
+ * vp_modern_get_queue_size - get size for a virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ *
+ * Returns the size of the virtqueue
+ */
+u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev,
+			     u16 index)
+{
+	vp_iowrite16(index, &mdev->common->queue_select);
+
+	return vp_ioread16(&mdev->common->queue_size);
+
+}
+EXPORT_SYMBOL_GPL(vp_modern_get_queue_size);
+
+/*
+ * vp_modern_get_num_queues - get the number of virtqueues
+ * @mdev: the modern virtio-pci device
+ *
+ * Returns the number of virtqueues
+ */
+u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev)
+{
+	return vp_ioread16(&mdev->common->num_queues);
+}
+EXPORT_SYMBOL_GPL(vp_modern_get_num_queues);
+
+/*
+ * vp_modern_get_queue_notify_off - get notification offset for a virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ *
+ * Returns the notification offset for a virtqueue
+ */
+static u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev,
+					  u16 index)
+{
+	vp_iowrite16(index, &mdev->common->queue_select);
+
+	return vp_ioread16(&mdev->common->queue_notify_off);
+}
+
+/*
+ * vp_modern_map_vq_notify - map notification area for a
+ * specific virtqueue
+ * @mdev: the modern virtio-pci device
+ * @index: the queue index
+ * @pa: the pointer to the physical address of the nofity area
+ *
+ * Returns the address of the notification area
+ */
+void __iomem *vp_modern_map_vq_notify(struct virtio_pci_modern_device *mdev,
+				      u16 index, resource_size_t *pa)
+{
+	u16 off = vp_modern_get_queue_notify_off(mdev, index);
+
+	if (mdev->notify_base) {
+		/* offset should not wrap */
+		if ((u64)off * mdev->notify_offset_multiplier + 2
+			> mdev->notify_len) {
+			dev_warn(&mdev->pci_dev->dev,
+				 "bad notification offset %u (x %u) "
+				 "for queue %u > %zd",
+				 off, mdev->notify_offset_multiplier,
+				 index, mdev->notify_len);
+			return NULL;
+		}
+		if (pa)
+			*pa = mdev->notify_pa +
+			      off * mdev->notify_offset_multiplier;
+		return mdev->notify_base + off * mdev->notify_offset_multiplier;
+	} else {
+		return vp_modern_map_capability(mdev,
+				       mdev->notify_map_cap, 2, 2,
+				       off * mdev->notify_offset_multiplier, 2,
+				       NULL, pa);
+	}
+}
+EXPORT_SYMBOL_GPL(vp_modern_map_vq_notify);
+
+u16 vp_modern_avq_num(struct virtio_pci_modern_device *mdev)
+{
+	struct virtio_pci_modern_common_cfg __iomem *cfg;
+
+	cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common;
+	return vp_ioread16(&cfg->admin_queue_num);
+}
+EXPORT_SYMBOL_GPL(vp_modern_avq_num);
+
+u16 vp_modern_avq_index(struct virtio_pci_modern_device *mdev)
+{
+	struct virtio_pci_modern_common_cfg __iomem *cfg;
+
+	cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common;
+	return vp_ioread16(&cfg->admin_queue_index);
+}
+EXPORT_SYMBOL_GPL(vp_modern_avq_index);
+
+MODULE_VERSION("0.1");
+MODULE_DESCRIPTION("Modern Virtio PCI Device");
+MODULE_AUTHOR("Jason Wang <jasowang@redhat.com>");
+MODULE_LICENSE("GPL");

linux-7.2.3/drivers/virtio/virtio_rtc_arm.c

@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Provides cross-timestamp params for Arm.
+ *
+ * Copyright (C) 2022-2023 OpenSynergy GmbH
+ * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/clocksource_ids.h>
+
+#include <uapi/linux/virtio_rtc.h>
+
+#include "virtio_rtc_internal.h"
+
+/* see header for doc */
+
+int viortc_hw_xtstamp_params(u8 *hw_counter, enum clocksource_ids *cs_id)
+{
+	*hw_counter = VIRTIO_RTC_COUNTER_ARM_VCT;
+	*cs_id = CSID_ARM_ARCH_COUNTER;
+
+	return 0;
+}

linux-7.2.3/drivers/virtio/virtio_rtc_class.c

@@ -0,0 +1,262 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * virtio_rtc RTC class driver
+ *
+ * Copyright (C) 2023 OpenSynergy GmbH
+ * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/math64.h>
+#include <linux/overflow.h>
+#include <linux/rtc.h>
+#include <linux/time64.h>
+
+#include <uapi/linux/virtio_rtc.h>
+
+#include "virtio_rtc_internal.h"
+
+/**
+ * struct viortc_class - RTC class wrapper
+ * @viortc: virtio_rtc device data
+ * @rtc: RTC device
+ * @vio_clk_id: virtio_rtc clock id
+ * @stopped: Whether RTC ops are disallowed. Access protected by rtc_lock().
+ */
+struct viortc_class {
+	struct viortc_dev *viortc;
+	struct rtc_device *rtc;
+	u16 vio_clk_id;
+	bool stopped;
+};
+
+/**
+ * viortc_class_get_locked() - get RTC class wrapper, if ops allowed
+ * @dev: virtio device
+ *
+ * Gets the RTC class wrapper from the virtio device, if it is available and
+ * ops are allowed.
+ *
+ * Context: Caller must hold rtc_lock().
+ * Return: RTC class wrapper if available and ops allowed, ERR_PTR otherwise.
+ */
+static struct viortc_class *viortc_class_get_locked(struct device *dev)
+{
+	struct viortc_class *viortc_class;
+
+	viortc_class = viortc_class_from_dev(dev);
+	if (IS_ERR(viortc_class))
+		return viortc_class;
+
+	if (viortc_class->stopped)
+		return ERR_PTR(-EBUSY);
+
+	return viortc_class;
+}
+
+/**
+ * viortc_class_read_time() - RTC class op read_time
+ * @dev: virtio device
+ * @tm: read time
+ *
+ * Context: Process context.
+ * Return: Zero on success, negative error code otherwise.
+ */
+static int viortc_class_read_time(struct device *dev, struct rtc_time *tm)
+{
+	struct viortc_class *viortc_class;
+	time64_t sec;
+	int ret;
+	u64 ns;
+
+	viortc_class = viortc_class_get_locked(dev);
+	if (IS_ERR(viortc_class))
+		return PTR_ERR(viortc_class);
+
+	ret = viortc_read(viortc_class->viortc, viortc_class->vio_clk_id, &ns);
+	if (ret)
+		return ret;
+
+	sec = div_u64(ns, NSEC_PER_SEC);
+
+	rtc_time64_to_tm(sec, tm);
+
+	return 0;
+}
+
+/**
+ * viortc_class_read_alarm() - RTC class op read_alarm
+ * @dev: virtio device
+ * @alrm: alarm read out
+ *
+ * Context: Process context.
+ * Return: Zero on success, negative error code otherwise.
+ */
+static int viortc_class_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct viortc_class *viortc_class;
+	time64_t alarm_time_sec;
+	u64 alarm_time_ns;
+	bool enabled;
+	int ret;
+
+	viortc_class = viortc_class_get_locked(dev);
+	if (IS_ERR(viortc_class))
+		return PTR_ERR(viortc_class);
+
+	ret = viortc_read_alarm(viortc_class->viortc, viortc_class->vio_clk_id,
+				&alarm_time_ns, &enabled);
+	if (ret)
+		return ret;
+
+	alarm_time_sec = div_u64(alarm_time_ns, NSEC_PER_SEC);
+	rtc_time64_to_tm(alarm_time_sec, &alrm->time);
+
+	alrm->enabled = enabled;
+
+	return 0;
+}
+
+/**
+ * viortc_class_set_alarm() - RTC class op set_alarm
+ * @dev: virtio device
+ * @alrm: alarm to set
+ *
+ * Context: Process context.
+ * Return: Zero on success, negative error code otherwise.
+ */
+static int viortc_class_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct viortc_class *viortc_class;
+	time64_t alarm_time_sec;
+	u64 alarm_time_ns;
+
+	viortc_class = viortc_class_get_locked(dev);
+	if (IS_ERR(viortc_class))
+		return PTR_ERR(viortc_class);
+
+	alarm_time_sec = rtc_tm_to_time64(&alrm->time);
+
+	if (alarm_time_sec < 0)
+		return -EINVAL;
+
+	if (check_mul_overflow((u64)alarm_time_sec, (u64)NSEC_PER_SEC,
+			       &alarm_time_ns))
+		return -EINVAL;
+
+	return viortc_set_alarm(viortc_class->viortc, viortc_class->vio_clk_id,
+				alarm_time_ns, alrm->enabled);
+}
+
+/**
+ * viortc_class_alarm_irq_enable() - RTC class op alarm_irq_enable
+ * @dev: virtio device
+ * @enabled: enable or disable alarm IRQ
+ *
+ * Context: Process context.
+ * Return: Zero on success, negative error code otherwise.
+ */
+static int viortc_class_alarm_irq_enable(struct device *dev,
+					 unsigned int enabled)
+{
+	struct viortc_class *viortc_class;
+
+	viortc_class = viortc_class_get_locked(dev);
+	if (IS_ERR(viortc_class))
+		return PTR_ERR(viortc_class);
+
+	return viortc_set_alarm_enabled(viortc_class->viortc,
+					viortc_class->vio_clk_id, enabled);
+}
+
+static const struct rtc_class_ops viortc_class_ops = {
+	.read_time = viortc_class_read_time,
+	.read_alarm = viortc_class_read_alarm,
+	.set_alarm = viortc_class_set_alarm,
+	.alarm_irq_enable = viortc_class_alarm_irq_enable,
+};
+
+/**
+ * viortc_class_alarm() - propagate alarm notification as alarm interrupt
+ * @viortc_class: RTC class wrapper
+ * @vio_clk_id: virtio_rtc clock id
+ *
+ * Context: Any context.
+ */
+void viortc_class_alarm(struct viortc_class *viortc_class, u16 vio_clk_id)
+{
+	if (vio_clk_id != viortc_class->vio_clk_id) {
+		dev_warn_ratelimited(&viortc_class->rtc->dev,
+				     "ignoring alarm for clock id %d, expected id %d\n",
+				     vio_clk_id, viortc_class->vio_clk_id);
+		return;
+	}
+
+	rtc_update_irq(viortc_class->rtc, 1, RTC_AF | RTC_IRQF);
+}
+
+/**
+ * viortc_class_stop() - disallow RTC class ops
+ * @viortc_class: RTC class wrapper
+ *
+ * Context: Process context. Caller must NOT hold rtc_lock().
+ */
+void viortc_class_stop(struct viortc_class *viortc_class)
+{
+	rtc_lock(viortc_class->rtc);
+
+	viortc_class->stopped = true;
+
+	rtc_unlock(viortc_class->rtc);
+}
+
+/**
+ * viortc_class_register() - register RTC class device
+ * @viortc_class: RTC class wrapper
+ *
+ * Context: Process context.
+ * Return: Zero on success, negative error code otherwise.
+ */
+int viortc_class_register(struct viortc_class *viortc_class)
+{
+	return devm_rtc_register_device(viortc_class->rtc);
+}
+
+/**
+ * viortc_class_init() - init RTC class wrapper and device
+ * @viortc: device data
+ * @vio_clk_id: virtio_rtc clock id
+ * @have_alarm: have alarm feature
+ * @parent_dev: virtio device
+ *
+ * Context: Process context.
+ * Return: RTC class wrapper on success, ERR_PTR otherwise.
+ */
+struct viortc_class *viortc_class_init(struct viortc_dev *viortc,
+				       u16 vio_clk_id, bool have_alarm,
+				       struct device *parent_dev)
+{
+	struct viortc_class *viortc_class;
+	struct rtc_device *rtc;
+
+	viortc_class =
+		devm_kzalloc(parent_dev, sizeof(*viortc_class), GFP_KERNEL);
+	if (!viortc_class)
+		return ERR_PTR(-ENOMEM);
+
+	rtc = devm_rtc_allocate_device(parent_dev);
+	if (IS_ERR(rtc))
+		return ERR_CAST(rtc);
+
+	viortc_class->viortc = viortc;
+	viortc_class->rtc = rtc;
+	viortc_class->vio_clk_id = vio_clk_id;
+
+	if (!have_alarm)
+		clear_bit(RTC_FEATURE_ALARM, rtc->features);
+	clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features);
+
+	rtc->ops = &viortc_class_ops;
+	rtc->range_max = div_u64(U64_MAX, NSEC_PER_SEC);
+
+	return viortc_class;
+}

linux-7.2.3/drivers/virtio/virtio_rtc_internal.h

@@ -0,0 +1,122 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * virtio_rtc internal interfaces
+ *
+ * Copyright (C) 2022-2023 OpenSynergy GmbH
+ * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef _VIRTIO_RTC_INTERNAL_H_
+#define _VIRTIO_RTC_INTERNAL_H_
+
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/ptp_clock_kernel.h>
+#include <linux/types.h>
+
+/* driver core IFs */
+
+struct viortc_dev;
+
+int viortc_read(struct viortc_dev *viortc, u16 vio_clk_id, u64 *reading);
+int viortc_read_cross(struct viortc_dev *viortc, u16 vio_clk_id, u8 hw_counter,
+		      u64 *reading, u64 *cycles);
+int viortc_cross_cap(struct viortc_dev *viortc, u16 vio_clk_id, u8 hw_counter,
+		     bool *supported);
+int viortc_read_alarm(struct viortc_dev *viortc, u16 vio_clk_id,
+		      u64 *alarm_time, bool *enabled);
+int viortc_set_alarm(struct viortc_dev *viortc, u16 vio_clk_id, u64 alarm_time,
+		     bool alarm_enable);
+int viortc_set_alarm_enabled(struct viortc_dev *viortc, u16 vio_clk_id,
+			     bool alarm_enable);
+
+struct viortc_class;
+
+struct viortc_class *viortc_class_from_dev(struct device *dev);
+
+/* PTP IFs */
+
+struct viortc_ptp_clock;
+
+#if IS_ENABLED(CONFIG_VIRTIO_RTC_PTP)
+
+struct viortc_ptp_clock *viortc_ptp_register(struct viortc_dev *viortc,
+					     struct device *parent_dev,
+					     u16 vio_clk_id,
+					     const char *ptp_clock_name);
+int viortc_ptp_unregister(struct viortc_ptp_clock *vio_ptp,
+			  struct device *parent_dev);
+
+#else
+
+static inline struct viortc_ptp_clock *
+viortc_ptp_register(struct viortc_dev *viortc, struct device *parent_dev,
+		    u16 vio_clk_id, const char *ptp_clock_name)
+{
+	return NULL;
+}
+
+static inline int viortc_ptp_unregister(struct viortc_ptp_clock *vio_ptp,
+					struct device *parent_dev)
+{
+	return -ENODEV;
+}
+
+#endif
+
+/* HW counter IFs */
+
+/**
+ * viortc_hw_xtstamp_params() - get HW-specific xtstamp params
+ * @hw_counter: virtio_rtc HW counter type
+ * @cs_id: clocksource id corresponding to hw_counter
+ *
+ * Gets the HW-specific xtstamp params. Returns an error if the driver cannot
+ * support xtstamp.
+ *
+ * Context: Process context.
+ * Return: Zero on success, negative error code otherwise.
+ */
+int viortc_hw_xtstamp_params(u8 *hw_counter, enum clocksource_ids *cs_id);
+
+/* RTC class IFs */
+
+#if IS_ENABLED(CONFIG_VIRTIO_RTC_CLASS)
+
+void viortc_class_alarm(struct viortc_class *viortc_class, u16 vio_clk_id);
+
+void viortc_class_stop(struct viortc_class *viortc_class);
+
+int viortc_class_register(struct viortc_class *viortc_class);
+
+struct viortc_class *viortc_class_init(struct viortc_dev *viortc,
+				       u16 vio_clk_id, bool have_alarm,
+				       struct device *parent_dev);
+
+#else /* CONFIG_VIRTIO_RTC_CLASS */
+
+static inline void viortc_class_alarm(struct viortc_class *viortc_class,
+				      u16 vio_clk_id)
+{
+}
+
+static inline void viortc_class_stop(struct viortc_class *viortc_class)
+{
+}
+
+static inline int viortc_class_register(struct viortc_class *viortc_class)
+{
+	return -ENODEV;
+}
+
+static inline struct viortc_class *viortc_class_init(struct viortc_dev *viortc,
+						     u16 vio_clk_id,
+						     bool have_alarm,
+						     struct device *parent_dev)
+{
+	return ERR_PTR(-ENODEV);
+}
+
+#endif /* CONFIG_VIRTIO_RTC_CLASS */
+
+#endif /* _VIRTIO_RTC_INTERNAL_H_ */

linux-7.2.3/drivers/virtio/virtio_rtc_ptp.c

@@ -0,0 +1,347 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Expose virtio_rtc clocks as PTP clocks.
+ *
+ * Copyright (C) 2022-2023 OpenSynergy GmbH
+ * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ *
+ * Derived from ptp_kvm_common.c, virtual PTP 1588 clock for use with KVM
+ * guests.
+ *
+ * Copyright (C) 2017 Red Hat Inc.
+ */
+
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/ptp_clock_kernel.h>
+
+#include <uapi/linux/virtio_rtc.h>
+
+#include "virtio_rtc_internal.h"
+
+/**
+ * struct viortc_ptp_clock - PTP clock abstraction
+ * @ptp_clock: PTP clock handle for unregistering
+ * @viortc: virtio_rtc device data
+ * @ptp_info: PTP clock description
+ * @vio_clk_id: virtio_rtc clock id
+ * @have_cross: device supports crosststamp with available HW counter
+ */
+struct viortc_ptp_clock {
+	struct ptp_clock *ptp_clock;
+	struct viortc_dev *viortc;
+	struct ptp_clock_info ptp_info;
+	u16 vio_clk_id;
+	bool have_cross;
+};
+
+/**
+ * struct viortc_ptp_cross_ctx - context for get_device_system_crosststamp()
+ * @device_time: device clock reading
+ * @system_counterval: HW counter value at device_time
+ *
+ * Provides the already obtained crosststamp to get_device_system_crosststamp().
+ */
+struct viortc_ptp_cross_ctx {
+	ktime_t device_time;
+	struct system_counterval_t system_counterval;
+};
+
+/* Weak function in case get_device_system_crosststamp() is not supported */
+int __weak viortc_hw_xtstamp_params(u8 *hw_counter, enum clocksource_ids *cs_id)
+{
+	return -EOPNOTSUPP;
+}
+
+/**
+ * viortc_ptp_get_time_fn() - callback for get_device_system_crosststamp()
+ * @device_time: device clock reading
+ * @system_counterval: HW counter value at device_time
+ * @ctx: context with already obtained crosststamp
+ *
+ * Return: zero (success).
+ */
+static int viortc_ptp_get_time_fn(ktime_t *device_time,
+				  struct system_counterval_t *system_counterval,
+				  void *ctx)
+{
+	struct viortc_ptp_cross_ctx *vio_ctx = ctx;
+
+	*device_time = vio_ctx->device_time;
+	*system_counterval = vio_ctx->system_counterval;
+
+	return 0;
+}
+
+/**
+ * viortc_ptp_do_xtstamp() - get crosststamp from device
+ * @vio_ptp: virtio_rtc PTP clock
+ * @hw_counter: virtio_rtc HW counter type
+ * @cs_id: clocksource id corresponding to hw_counter
+ * @ctx: context for get_device_system_crosststamp()
+ *
+ * Reads HW-specific crosststamp from device.
+ *
+ * Context: Process context.
+ * Return: Zero on success, negative error code otherwise.
+ */
+static int viortc_ptp_do_xtstamp(struct viortc_ptp_clock *vio_ptp,
+				 u8 hw_counter, enum clocksource_ids cs_id,
+				 struct viortc_ptp_cross_ctx *ctx)
+{
+	u64 max_ns, ns;
+	int ret;
+
+	ctx->system_counterval.cs_id = cs_id;
+
+	ret = viortc_read_cross(vio_ptp->viortc, vio_ptp->vio_clk_id,
+				hw_counter, &ns,
+				&ctx->system_counterval.cycles);
+	if (ret)
+		return ret;
+
+	max_ns = (u64)ktime_to_ns(KTIME_MAX);
+	if (ns > max_ns)
+		return -EINVAL;
+
+	ctx->device_time = ns_to_ktime(ns);
+
+	return 0;
+}
+
+/*
+ * PTP clock operations
+ */
+
+/**
+ * viortc_ptp_getcrosststamp() - PTP clock getcrosststamp op
+ * @ptp: PTP clock info
+ * @xtstamp: crosststamp
+ *
+ * Context: Process context.
+ * Return: Zero on success, negative error code otherwise.
+ */
+static int viortc_ptp_getcrosststamp(struct ptp_clock_info *ptp,
+				     struct system_device_crosststamp *xtstamp)
+{
+	struct viortc_ptp_clock *vio_ptp =
+		container_of(ptp, struct viortc_ptp_clock, ptp_info);
+	struct system_time_snapshot history_begin;
+	struct viortc_ptp_cross_ctx ctx;
+	enum clocksource_ids cs_id;
+	u8 hw_counter;
+	int ret;
+
+	if (!vio_ptp->have_cross)
+		return -EOPNOTSUPP;
+
+	ret = viortc_hw_xtstamp_params(&hw_counter, &cs_id);
+	if (ret)
+		return ret;
+
+	ktime_get_snapshot_id(xtstamp->clock_id, &history_begin);
+	if (history_begin.cs_id != cs_id)
+		return -EOPNOTSUPP;
+
+	/*
+	 * Getting the timestamp can take many milliseconds with a slow Virtio
+	 * device. This is too long for viortc_ptp_get_time_fn() passed to
+	 * get_device_system_crosststamp(), which has to usually return before
+	 * the timekeeper seqcount increases (every tick or so).
+	 *
+	 * So, get the actual cross-timestamp first.
+	 */
+	ret = viortc_ptp_do_xtstamp(vio_ptp, hw_counter, cs_id, &ctx);
+	if (ret)
+		return ret;
+
+	ret = get_device_system_crosststamp(viortc_ptp_get_time_fn, &ctx,
+					    &history_begin, xtstamp);
+	if (ret)
+		pr_debug("%s: get_device_system_crosststamp() returned %d\n",
+			 __func__, ret);
+
+	return ret;
+}
+
+/* viortc_ptp_adjfine() - unsupported PTP clock adjfine op */
+static int viortc_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
+{
+	return -EOPNOTSUPP;
+}
+
+/* viortc_ptp_adjtime() - unsupported PTP clock adjtime op */
+static int viortc_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	return -EOPNOTSUPP;
+}
+
+/* viortc_ptp_settime64() - unsupported PTP clock settime64 op */
+static int viortc_ptp_settime64(struct ptp_clock_info *ptp,
+				const struct timespec64 *ts)
+{
+	return -EOPNOTSUPP;
+}
+
+/*
+ * viortc_ptp_gettimex64() - PTP clock gettimex64 op
+ *
+ * Context: Process context.
+ */
+static int viortc_ptp_gettimex64(struct ptp_clock_info *ptp,
+				 struct timespec64 *ts,
+				 struct ptp_system_timestamp *sts)
+{
+	struct viortc_ptp_clock *vio_ptp =
+		container_of(ptp, struct viortc_ptp_clock, ptp_info);
+	int ret;
+	u64 ns;
+
+	ptp_read_system_prets(sts);
+	ret = viortc_read(vio_ptp->viortc, vio_ptp->vio_clk_id, &ns);
+	ptp_read_system_postts(sts);
+
+	if (ret)
+		return ret;
+
+	if (ns > (u64)S64_MAX)
+		return -EINVAL;
+
+	*ts = ns_to_timespec64((s64)ns);
+
+	return 0;
+}
+
+/* viortc_ptp_enable() - unsupported PTP clock enable op */
+static int viortc_ptp_enable(struct ptp_clock_info *ptp,
+			     struct ptp_clock_request *rq, int on)
+{
+	return -EOPNOTSUPP;
+}
+
+/*
+ * viortc_ptp_info_template - ptp_clock_info template
+ *
+ * The .name member will be set for individual virtio_rtc PTP clocks.
+ *
+ * The .getcrosststamp member will be cleared for PTP clocks not supporting
+ * crosststamp.
+ */
+static const struct ptp_clock_info viortc_ptp_info_template = {
+	.owner = THIS_MODULE,
+	/* .name is set according to clock type */
+	.adjfine = viortc_ptp_adjfine,
+	.adjtime = viortc_ptp_adjtime,
+	.gettimex64 = viortc_ptp_gettimex64,
+	.settime64 = viortc_ptp_settime64,
+	.enable = viortc_ptp_enable,
+	.getcrosststamp = viortc_ptp_getcrosststamp,
+};
+
+/**
+ * viortc_ptp_unregister() - PTP clock unregistering wrapper
+ * @vio_ptp: virtio_rtc PTP clock
+ * @parent_dev: parent device of PTP clock
+ *
+ * Return: Zero on success, negative error code otherwise.
+ */
+int viortc_ptp_unregister(struct viortc_ptp_clock *vio_ptp,
+			  struct device *parent_dev)
+{
+	int ret = ptp_clock_unregister(vio_ptp->ptp_clock);
+
+	if (!ret)
+		devm_kfree(parent_dev, vio_ptp);
+
+	return ret;
+}
+
+/**
+ * viortc_ptp_get_cross_cap() - get xtstamp support info from device
+ * @viortc: virtio_rtc device data
+ * @vio_ptp: virtio_rtc PTP clock abstraction
+ *
+ * Context: Process context.
+ * Return: Zero on success, negative error code otherwise.
+ */
+static int viortc_ptp_get_cross_cap(struct viortc_dev *viortc,
+				    struct viortc_ptp_clock *vio_ptp)
+{
+	enum clocksource_ids cs_id;
+	bool xtstamp_supported;
+	u8 hw_counter;
+	int ret;
+
+	ret = viortc_hw_xtstamp_params(&hw_counter, &cs_id);
+	if (ret) {
+		vio_ptp->have_cross = false;
+		return 0;
+	}
+
+	ret = viortc_cross_cap(viortc, vio_ptp->vio_clk_id, hw_counter,
+			       &xtstamp_supported);
+	if (ret)
+		return ret;
+
+	vio_ptp->have_cross = xtstamp_supported;
+
+	return 0;
+}
+
+/**
+ * viortc_ptp_register() - prepare and register PTP clock
+ * @viortc: virtio_rtc device data
+ * @parent_dev: parent device for PTP clock
+ * @vio_clk_id: id of virtio_rtc clock which backs PTP clock
+ * @ptp_clock_name: PTP clock name
+ *
+ * Context: Process context.
+ * Return: Pointer on success, ERR_PTR() otherwise; NULL if PTP clock support
+ *         not available.
+ */
+struct viortc_ptp_clock *viortc_ptp_register(struct viortc_dev *viortc,
+					     struct device *parent_dev,
+					     u16 vio_clk_id,
+					     const char *ptp_clock_name)
+{
+	struct viortc_ptp_clock *vio_ptp;
+	struct ptp_clock *ptp_clock;
+	ssize_t len;
+	int ret;
+
+	vio_ptp = devm_kzalloc(parent_dev, sizeof(*vio_ptp), GFP_KERNEL);
+	if (!vio_ptp)
+		return ERR_PTR(-ENOMEM);
+
+	vio_ptp->viortc = viortc;
+	vio_ptp->vio_clk_id = vio_clk_id;
+	vio_ptp->ptp_info = viortc_ptp_info_template;
+	len = strscpy(vio_ptp->ptp_info.name, ptp_clock_name,
+		      sizeof(vio_ptp->ptp_info.name));
+	if (len < 0) {
+		ret = len;
+		goto err_free_dev;
+	}
+
+	ret = viortc_ptp_get_cross_cap(viortc, vio_ptp);
+	if (ret)
+		goto err_free_dev;
+
+	if (!vio_ptp->have_cross)
+		vio_ptp->ptp_info.getcrosststamp = NULL;
+
+	ptp_clock = ptp_clock_register(&vio_ptp->ptp_info, parent_dev);
+	if (IS_ERR(ptp_clock))
+		goto err_on_register;
+
+	vio_ptp->ptp_clock = ptp_clock;
+
+	return vio_ptp;
+
+err_on_register:
+	ret = PTR_ERR(ptp_clock);
+
+err_free_dev:
+	devm_kfree(parent_dev, vio_ptp);
+	return ERR_PTR(ret);
+}

linux-7.2.3/drivers/virtio/virtio_vdpa.c

@@ -0,0 +1,518 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VIRTIO based driver for vDPA device
+ *
+ * Copyright (c) 2020, Red Hat. All rights reserved.
+ *     Author: Jason Wang <jasowang@redhat.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/uuid.h>
+#include <linux/group_cpus.h>
+#include <linux/virtio.h>
+#include <linux/vdpa.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+
+#define MOD_VERSION  "0.1"
+#define MOD_AUTHOR   "Jason Wang <jasowang@redhat.com>"
+#define MOD_DESC     "vDPA bus driver for virtio devices"
+#define MOD_LICENSE  "GPL v2"
+
+struct virtio_vdpa_device {
+	struct virtio_device vdev;
+	struct vdpa_device *vdpa;
+	u64 features;
+};
+
+static inline struct virtio_vdpa_device *
+to_virtio_vdpa_device(struct virtio_device *dev)
+{
+	return container_of(dev, struct virtio_vdpa_device, vdev);
+}
+
+static struct vdpa_device *vd_get_vdpa(struct virtio_device *vdev)
+{
+	return to_virtio_vdpa_device(vdev)->vdpa;
+}
+
+static void virtio_vdpa_get(struct virtio_device *vdev, unsigned int offset,
+			    void *buf, unsigned int len)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+
+	vdpa_get_config(vdpa, offset, buf, len);
+}
+
+static void virtio_vdpa_set(struct virtio_device *vdev, unsigned int offset,
+			    const void *buf, unsigned int len)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+
+	vdpa_set_config(vdpa, offset, buf, len);
+}
+
+static u32 virtio_vdpa_generation(struct virtio_device *vdev)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	if (ops->get_generation)
+		return ops->get_generation(vdpa);
+
+	return 0;
+}
+
+static u8 virtio_vdpa_get_status(struct virtio_device *vdev)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	return ops->get_status(vdpa);
+}
+
+static void virtio_vdpa_set_status(struct virtio_device *vdev, u8 status)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+
+	vdpa_set_status(vdpa, status);
+}
+
+static void virtio_vdpa_reset(struct virtio_device *vdev)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+
+	vdpa_reset(vdpa, 0);
+}
+
+static bool virtio_vdpa_notify(struct virtqueue *vq)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vq->vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	ops->kick_vq(vdpa, vq->index);
+
+	return true;
+}
+
+static bool virtio_vdpa_notify_with_data(struct virtqueue *vq)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vq->vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+	u32 data = vring_notification_data(vq);
+
+	ops->kick_vq_with_data(vdpa, data);
+
+	return true;
+}
+
+static irqreturn_t virtio_vdpa_config_cb(void *private)
+{
+	struct virtio_vdpa_device *vd_dev = private;
+
+	virtio_config_changed(&vd_dev->vdev);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t virtio_vdpa_virtqueue_cb(void *private)
+{
+	struct virtqueue *vq = private;
+
+	return vring_interrupt(0, vq);
+}
+
+static struct virtqueue *
+virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index,
+		     void (*callback)(struct virtqueue *vq),
+		     const char *name, bool ctx)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+	bool (*notify)(struct virtqueue *vq) = virtio_vdpa_notify;
+	struct vdpa_callback cb;
+	struct virtqueue *vq;
+	u64 desc_addr, driver_addr, device_addr;
+	union virtio_map map = {0};
+	/* Assume split virtqueue, switch to packed if necessary */
+	struct vdpa_vq_state state = {0};
+	u32 align, max_num, min_num = 1;
+	bool may_reduce_num = true;
+	int err;
+
+	if (!name)
+		return NULL;
+
+	if (index >= vdpa->nvqs)
+		return ERR_PTR(-ENOENT);
+
+	/* We cannot accept VIRTIO_F_NOTIFICATION_DATA without kick_vq_with_data */
+	if (__virtio_test_bit(vdev, VIRTIO_F_NOTIFICATION_DATA)) {
+		if (ops->kick_vq_with_data)
+			notify = virtio_vdpa_notify_with_data;
+		else
+			__virtio_clear_bit(vdev, VIRTIO_F_NOTIFICATION_DATA);
+	}
+
+	/* Queue shouldn't already be set up. */
+	if (ops->get_vq_ready(vdpa, index))
+		return ERR_PTR(-ENOENT);
+
+	if (ops->get_vq_size)
+		max_num = ops->get_vq_size(vdpa, index);
+	else
+		max_num = ops->get_vq_num_max(vdpa);
+
+	if (max_num == 0) {
+		err = -ENOENT;
+		goto error_new_virtqueue;
+	}
+
+	if (ops->get_vq_num_min)
+		min_num = ops->get_vq_num_min(vdpa);
+
+	may_reduce_num = (max_num != min_num);
+
+	/* Create the vring */
+	align = ops->get_vq_align(vdpa);
+
+	if (ops->get_vq_map)
+		map = ops->get_vq_map(vdpa, index);
+	else
+		map = vdpa_get_map(vdpa);
+
+	vq = vring_create_virtqueue_map(index, max_num, align, vdev,
+					true, may_reduce_num, ctx,
+					notify, callback, name, map);
+	if (!vq) {
+		err = -ENOMEM;
+		goto error_new_virtqueue;
+	}
+
+	if (index == 0)
+		vdev->vmap = map;
+
+	vq->num_max = max_num;
+
+	/* Setup virtqueue callback */
+	cb.callback = callback ? virtio_vdpa_virtqueue_cb : NULL;
+	cb.private = vq;
+	cb.trigger = NULL;
+	ops->set_vq_cb(vdpa, index, &cb);
+	ops->set_vq_num(vdpa, index, virtqueue_get_vring_size(vq));
+
+	desc_addr = virtqueue_get_desc_addr(vq);
+	driver_addr = virtqueue_get_avail_addr(vq);
+	device_addr = virtqueue_get_used_addr(vq);
+
+	if (ops->set_vq_address(vdpa, index,
+				desc_addr, driver_addr,
+				device_addr)) {
+		err = -EINVAL;
+		goto err_vq;
+	}
+
+	/* reset virtqueue state index */
+	if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED)) {
+		struct vdpa_vq_state_packed *s = &state.packed;
+
+		s->last_avail_counter = 1;
+		s->last_avail_idx = 0;
+		s->last_used_counter = 1;
+		s->last_used_idx = 0;
+	}
+	err = ops->set_vq_state(vdpa, index, &state);
+	if (err)
+		goto err_vq;
+
+	ops->set_vq_ready(vdpa, index, 1);
+
+	return vq;
+
+err_vq:
+	vring_del_virtqueue(vq);
+error_new_virtqueue:
+	ops->set_vq_ready(vdpa, index, 0);
+	/* VDPA driver should make sure vq is stopeed here */
+	WARN_ON(ops->get_vq_ready(vdpa, index));
+	return ERR_PTR(err);
+}
+
+static void virtio_vdpa_del_vq(struct virtqueue *vq)
+{
+	struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vq->vdev);
+	struct vdpa_device *vdpa = vd_dev->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+	unsigned int index = vq->index;
+
+	/* Select and deactivate the queue (best effort) */
+	ops->set_vq_ready(vdpa, index, 0);
+
+	vring_del_virtqueue(vq);
+}
+
+static void virtio_vdpa_del_vqs(struct virtio_device *vdev)
+{
+	struct virtqueue *vq, *n;
+
+	list_for_each_entry_safe(vq, n, &vdev->vqs, list)
+		virtio_vdpa_del_vq(vq);
+}
+
+static void default_calc_sets(struct irq_affinity *affd, unsigned int affvecs)
+{
+	affd->nr_sets = 1;
+	affd->set_size[0] = affvecs;
+}
+
+static struct cpumask *
+create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd)
+{
+	unsigned int affvecs = 0, curvec, usedvecs, i;
+	struct cpumask *masks = NULL;
+
+	if (nvecs > affd->pre_vectors + affd->post_vectors)
+		affvecs = nvecs - affd->pre_vectors - affd->post_vectors;
+
+	if (!affd->calc_sets)
+		affd->calc_sets = default_calc_sets;
+
+	affd->calc_sets(affd, affvecs);
+
+	if (!affvecs)
+		return NULL;
+
+	masks = kzalloc_objs(*masks, nvecs);
+	if (!masks)
+		return NULL;
+
+	/* Fill out vectors at the beginning that don't need affinity */
+	for (curvec = 0; curvec < affd->pre_vectors; curvec++)
+		cpumask_setall(&masks[curvec]);
+
+	for (i = 0, usedvecs = 0; i < affd->nr_sets; i++) {
+		unsigned int this_vecs = affd->set_size[i];
+		unsigned int nr_masks;
+		int j;
+		struct cpumask *result = group_cpus_evenly(this_vecs, &nr_masks);
+
+		if (!result) {
+			kfree(masks);
+			return NULL;
+		}
+
+		for (j = 0; j < nr_masks; j++)
+			cpumask_copy(&masks[curvec + j], &result[j]);
+		kfree(result);
+
+		curvec += nr_masks;
+		usedvecs += nr_masks;
+	}
+
+	/* Fill out vectors at the end that don't need affinity */
+	if (usedvecs >= affvecs)
+		curvec = affd->pre_vectors + affvecs;
+	else
+		curvec = affd->pre_vectors + usedvecs;
+	for (; curvec < nvecs; curvec++)
+		cpumask_setall(&masks[curvec]);
+
+	return masks;
+}
+
+static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
+				struct virtqueue *vqs[],
+				struct virtqueue_info vqs_info[],
+				struct irq_affinity *desc)
+{
+	struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev);
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+	struct cpumask *masks;
+	struct vdpa_callback cb;
+	bool has_affinity = desc && ops->set_vq_affinity;
+	int i, err, queue_idx = 0;
+
+	if (has_affinity) {
+		masks = create_affinity_masks(nvqs, desc);
+		if (!masks)
+			return -ENOMEM;
+	}
+
+	for (i = 0; i < nvqs; ++i) {
+		struct virtqueue_info *vqi = &vqs_info[i];
+
+		if (!vqi->name) {
+			vqs[i] = NULL;
+			continue;
+		}
+
+		vqs[i] = virtio_vdpa_setup_vq(vdev, queue_idx++, vqi->callback,
+					      vqi->name, vqi->ctx);
+		if (IS_ERR(vqs[i])) {
+			err = PTR_ERR(vqs[i]);
+			goto err_setup_vq;
+		}
+
+		if (has_affinity)
+			ops->set_vq_affinity(vdpa, i, &masks[i]);
+	}
+
+	cb.callback = virtio_vdpa_config_cb;
+	cb.private = vd_dev;
+	ops->set_config_cb(vdpa, &cb);
+	if (has_affinity)
+		kfree(masks);
+
+	return 0;
+
+err_setup_vq:
+	virtio_vdpa_del_vqs(vdev);
+	if (has_affinity)
+		kfree(masks);
+	return err;
+}
+
+static u64 virtio_vdpa_get_features(struct virtio_device *vdev)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	return ops->get_device_features(vdpa);
+}
+
+static int virtio_vdpa_finalize_features(struct virtio_device *vdev)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+
+	/* Give virtio_ring a chance to accept features. */
+	vring_transport_features(vdev);
+
+	return vdpa_set_features(vdpa, vdev->features);
+}
+
+static const char *virtio_vdpa_bus_name(struct virtio_device *vdev)
+{
+	struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev);
+	struct vdpa_device *vdpa = vd_dev->vdpa;
+
+	return dev_name(&vdpa->dev);
+}
+
+static int virtio_vdpa_set_vq_affinity(struct virtqueue *vq,
+				       const struct cpumask *cpu_mask)
+{
+	struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vq->vdev);
+	struct vdpa_device *vdpa = vd_dev->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+	unsigned int index = vq->index;
+
+	if (ops->set_vq_affinity)
+		return ops->set_vq_affinity(vdpa, index, cpu_mask);
+
+	return 0;
+}
+
+static const struct cpumask *
+virtio_vdpa_get_vq_affinity(struct virtio_device *vdev, int index)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	if (ops->get_vq_affinity)
+		return ops->get_vq_affinity(vdpa, index);
+
+	return NULL;
+}
+
+static const struct virtio_config_ops virtio_vdpa_config_ops = {
+	.get		= virtio_vdpa_get,
+	.set		= virtio_vdpa_set,
+	.generation	= virtio_vdpa_generation,
+	.get_status	= virtio_vdpa_get_status,
+	.set_status	= virtio_vdpa_set_status,
+	.reset		= virtio_vdpa_reset,
+	.find_vqs	= virtio_vdpa_find_vqs,
+	.del_vqs	= virtio_vdpa_del_vqs,
+	.get_features	= virtio_vdpa_get_features,
+	.finalize_features = virtio_vdpa_finalize_features,
+	.bus_name	= virtio_vdpa_bus_name,
+	.set_vq_affinity = virtio_vdpa_set_vq_affinity,
+	.get_vq_affinity = virtio_vdpa_get_vq_affinity,
+};
+
+static void virtio_vdpa_release_dev(struct device *_d)
+{
+	struct virtio_device *vdev =
+	       container_of(_d, struct virtio_device, dev);
+	struct virtio_vdpa_device *vd_dev =
+	       container_of(vdev, struct virtio_vdpa_device, vdev);
+
+	kfree(vd_dev);
+}
+
+static int virtio_vdpa_probe(struct vdpa_device *vdpa)
+{
+	const struct vdpa_config_ops *ops = vdpa->config;
+	struct virtio_vdpa_device *vd_dev, *reg_dev = NULL;
+	int ret = -EINVAL;
+
+	vd_dev = kzalloc_obj(*vd_dev);
+	if (!vd_dev)
+		return -ENOMEM;
+
+	vd_dev->vdev.dev.parent = vdpa->map ? &vdpa->dev :
+				  vdpa_get_map(vdpa).dma_dev;
+	vd_dev->vdev.dev.release = virtio_vdpa_release_dev;
+	vd_dev->vdev.config = &virtio_vdpa_config_ops;
+	vd_dev->vdev.map = vdpa->map;
+	vd_dev->vdpa = vdpa;
+
+	vd_dev->vdev.id.device = ops->get_device_id(vdpa);
+	if (vd_dev->vdev.id.device == 0)
+		goto err;
+
+	vd_dev->vdev.id.vendor = ops->get_vendor_id(vdpa);
+	ret = register_virtio_device(&vd_dev->vdev);
+	reg_dev = vd_dev;
+	if (ret)
+		goto err;
+
+	vdpa_set_drvdata(vdpa, vd_dev);
+
+	return 0;
+
+err:
+	if (reg_dev)
+		put_device(&vd_dev->vdev.dev);
+	else
+		kfree(vd_dev);
+	return ret;
+}
+
+static void virtio_vdpa_remove(struct vdpa_device *vdpa)
+{
+	struct virtio_vdpa_device *vd_dev = vdpa_get_drvdata(vdpa);
+
+	unregister_virtio_device(&vd_dev->vdev);
+}
+
+static struct vdpa_driver virtio_vdpa_driver = {
+	.driver = {
+		.name	= "virtio_vdpa",
+	},
+	.probe	= virtio_vdpa_probe,
+	.remove = virtio_vdpa_remove,
+};
+
+module_vdpa_driver(virtio_vdpa_driver);
+
+MODULE_VERSION(MOD_VERSION);
+MODULE_LICENSE(MOD_LICENSE);
+MODULE_AUTHOR(MOD_AUTHOR);
+MODULE_DESCRIPTION(MOD_DESC);