Merge tag 'vfio-v6.5-rc1' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Adjust log levels for common messages (Oleksandr Natalenko, Alex
   Williamson)

 - Support for dynamic MSI-X allocation (Reinette Chatre)

 - Enable and report PCIe AtomicOp Completer capabilities (Alex
   Williamson)

 - Cleanup Kconfigs for vfio bus drivers (Alex Williamson)

 - Add support for CDX bus based devices (Nipun Gupta)

 - Fix race with concurrent mdev initialization (Eric Farman)

* tag 'vfio-v6.5-rc1' of https://github.com/awilliam/linux-vfio:
  vfio/mdev: Move the compat_class initialization to module init
  vfio/cdx: add support for CDX bus
  vfio/fsl: Create Kconfig sub-menu
  vfio/platform: Cleanup Kconfig
  vfio/pci: Cleanup Kconfig
  vfio/pci-core: Add capability for AtomicOp completer support
  vfio/pci: Also demote hiding standard cap messages
  vfio/pci: Clear VFIO_IRQ_INFO_NORESIZE for MSI-X
  vfio/pci: Support dynamic MSI-X
  vfio/pci: Probe and store ability to support dynamic MSI-X
  vfio/pci: Use bitfield for struct vfio_pci_core_device flags
  vfio/pci: Update stale comment
  vfio/pci: Remove interrupt context counter
  vfio/pci: Use xarray for interrupt context storage
  vfio/pci: Move to single error path
  vfio/pci: Prepare for dynamic interrupt context storage
  vfio/pci: Remove negative check on unsigned vector
  vfio/pci: Consolidate irq cleanup on MSI/MSI-X disable
  vfio/pci: demote hiding ecap messages to debug level

MAINTAINERS

@@ -22254,6 +22254,13 @@ F:	Documentation/filesystems/vfat.rst
 F:	fs/fat/
 F:	tools/testing/selftests/filesystems/fat/
 
+VFIO CDX DRIVER
+M:	Nipun Gupta <nipun.gupta@amd.com>
+M:	Nikhil Agarwal <nikhil.agarwal@amd.com>
+L:	kvm@vger.kernel.org
+S:	Maintained
+F:	drivers/vfio/cdx/*
+
 VFIO DRIVER
 M:	Alex Williamson <alex.williamson@redhat.com>
 L:	kvm@vger.kernel.org

drivers/vfio/Kconfig

@@ -57,6 +57,7 @@ source "drivers/vfio/pci/Kconfig"
 source "drivers/vfio/platform/Kconfig"
 source "drivers/vfio/mdev/Kconfig"
 source "drivers/vfio/fsl-mc/Kconfig"
+source "drivers/vfio/cdx/Kconfig"
 endif
 
 source "virt/lib/Kconfig"

drivers/vfio/Makefile

@@ -10,7 +10,8 @@ vfio-$(CONFIG_VFIO_VIRQFD) += virqfd.o
 
 obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
 obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
-obj-$(CONFIG_VFIO_PCI) += pci/
-obj-$(CONFIG_VFIO_PLATFORM) += platform/
+obj-$(CONFIG_VFIO_PCI_CORE) += pci/
+obj-$(CONFIG_VFIO_PLATFORM_BASE) += platform/
 obj-$(CONFIG_VFIO_MDEV) += mdev/
 obj-$(CONFIG_VFIO_FSL_MC) += fsl-mc/
+obj-$(CONFIG_VFIO_CDX) += cdx/

drivers/vfio/cdx/Kconfig

@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# VFIO CDX configuration
+#
+# Copyright (C) 2022-2023, Advanced Micro Devices, Inc.
+#
+
+config VFIO_CDX
+	tristate "VFIO support for CDX bus devices"
+	depends on CDX_BUS
+	select EVENTFD
+	help
+	  Driver to enable VFIO support for the devices on CDX bus.
+	  This is required to make use of CDX devices present in
+	  the system using the VFIO framework.
+
+	  If you don't know what to do here, say N.

drivers/vfio/cdx/Makefile

@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2022-2023, Advanced Micro Devices, Inc.
+#
+
+obj-$(CONFIG_VFIO_CDX) += vfio-cdx.o
+
+vfio-cdx-objs := main.o

drivers/vfio/cdx/main.c

@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2023, Advanced Micro Devices, Inc.
+ */
+
+#include <linux/vfio.h>
+#include <linux/cdx/cdx_bus.h>
+
+#include "private.h"
+
+static int vfio_cdx_open_device(struct vfio_device *core_vdev)
+{
+	struct vfio_cdx_device *vdev =
+		container_of(core_vdev, struct vfio_cdx_device, vdev);
+	struct cdx_device *cdx_dev = to_cdx_device(core_vdev->dev);
+	int count = cdx_dev->res_count;
+	int i;
+
+	vdev->regions = kcalloc(count, sizeof(struct vfio_cdx_region),
+				GFP_KERNEL_ACCOUNT);
+	if (!vdev->regions)
+		return -ENOMEM;
+
+	for (i = 0; i < count; i++) {
+		struct resource *res = &cdx_dev->res[i];
+
+		vdev->regions[i].addr = res->start;
+		vdev->regions[i].size = resource_size(res);
+		vdev->regions[i].type = res->flags;
+		/*
+		 * Only regions addressed with PAGE granularity may be
+		 * MMAP'ed securely.
+		 */
+		if (!(vdev->regions[i].addr & ~PAGE_MASK) &&
+		    !(vdev->regions[i].size & ~PAGE_MASK))
+			vdev->regions[i].flags |=
+					VFIO_REGION_INFO_FLAG_MMAP;
+		vdev->regions[i].flags |= VFIO_REGION_INFO_FLAG_READ;
+		if (!(cdx_dev->res[i].flags & IORESOURCE_READONLY))
+			vdev->regions[i].flags |= VFIO_REGION_INFO_FLAG_WRITE;
+	}
+
+	return 0;
+}
+
+static void vfio_cdx_close_device(struct vfio_device *core_vdev)
+{
+	struct vfio_cdx_device *vdev =
+		container_of(core_vdev, struct vfio_cdx_device, vdev);
+
+	kfree(vdev->regions);
+	cdx_dev_reset(core_vdev->dev);
+}
+
+static int vfio_cdx_ioctl_get_info(struct vfio_cdx_device *vdev,
+				   struct vfio_device_info __user *arg)
+{
+	unsigned long minsz = offsetofend(struct vfio_device_info, num_irqs);
+	struct cdx_device *cdx_dev = to_cdx_device(vdev->vdev.dev);
+	struct vfio_device_info info;
+
+	if (copy_from_user(&info, arg, minsz))
+		return -EFAULT;
+
+	if (info.argsz < minsz)
+		return -EINVAL;
+
+	info.flags = VFIO_DEVICE_FLAGS_CDX;
+	info.flags |= VFIO_DEVICE_FLAGS_RESET;
+
+	info.num_regions = cdx_dev->res_count;
+	info.num_irqs = 0;
+
+	return copy_to_user(arg, &info, minsz) ? -EFAULT : 0;
+}
+
+static int vfio_cdx_ioctl_get_region_info(struct vfio_cdx_device *vdev,
+					  struct vfio_region_info __user *arg)
+{
+	unsigned long minsz = offsetofend(struct vfio_region_info, offset);
+	struct cdx_device *cdx_dev = to_cdx_device(vdev->vdev.dev);
+	struct vfio_region_info info;
+
+	if (copy_from_user(&info, arg, minsz))
+		return -EFAULT;
+
+	if (info.argsz < minsz)
+		return -EINVAL;
+
+	if (info.index >= cdx_dev->res_count)
+		return -EINVAL;
+
+	/* map offset to the physical address */
+	info.offset = vfio_cdx_index_to_offset(info.index);
+	info.size = vdev->regions[info.index].size;
+	info.flags = vdev->regions[info.index].flags;
+
+	return copy_to_user(arg, &info, minsz) ? -EFAULT : 0;
+}
+
+static long vfio_cdx_ioctl(struct vfio_device *core_vdev,
+			   unsigned int cmd, unsigned long arg)
+{
+	struct vfio_cdx_device *vdev =
+		container_of(core_vdev, struct vfio_cdx_device, vdev);
+	void __user *uarg = (void __user *)arg;
+
+	switch (cmd) {
+	case VFIO_DEVICE_GET_INFO:
+		return vfio_cdx_ioctl_get_info(vdev, uarg);
+	case VFIO_DEVICE_GET_REGION_INFO:
+		return vfio_cdx_ioctl_get_region_info(vdev, uarg);
+	case VFIO_DEVICE_RESET:
+		return cdx_dev_reset(core_vdev->dev);
+	default:
+		return -ENOTTY;
+	}
+}
+
+static int vfio_cdx_mmap_mmio(struct vfio_cdx_region region,
+			      struct vm_area_struct *vma)
+{
+	u64 size = vma->vm_end - vma->vm_start;
+	u64 pgoff, base;
+
+	pgoff = vma->vm_pgoff &
+		((1U << (VFIO_CDX_OFFSET_SHIFT - PAGE_SHIFT)) - 1);
+	base = pgoff << PAGE_SHIFT;
+
+	if (base + size > region.size)
+		return -EINVAL;
+
+	vma->vm_pgoff = (region.addr >> PAGE_SHIFT) + pgoff;
+	vma->vm_page_prot = pgprot_device(vma->vm_page_prot);
+
+	return io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+				  size, vma->vm_page_prot);
+}
+
+static int vfio_cdx_mmap(struct vfio_device *core_vdev,
+			 struct vm_area_struct *vma)
+{
+	struct vfio_cdx_device *vdev =
+		container_of(core_vdev, struct vfio_cdx_device, vdev);
+	struct cdx_device *cdx_dev = to_cdx_device(core_vdev->dev);
+	unsigned int index;
+
+	index = vma->vm_pgoff >> (VFIO_CDX_OFFSET_SHIFT - PAGE_SHIFT);
+
+	if (index >= cdx_dev->res_count)
+		return -EINVAL;
+
+	if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_MMAP))
+		return -EINVAL;
+
+	if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_READ) &&
+	    (vma->vm_flags & VM_READ))
+		return -EPERM;
+
+	if (!(vdev->regions[index].flags & VFIO_REGION_INFO_FLAG_WRITE) &&
+	    (vma->vm_flags & VM_WRITE))
+		return -EPERM;
+
+	return vfio_cdx_mmap_mmio(vdev->regions[index], vma);
+}
+
+static const struct vfio_device_ops vfio_cdx_ops = {
+	.name		= "vfio-cdx",
+	.open_device	= vfio_cdx_open_device,
+	.close_device	= vfio_cdx_close_device,
+	.ioctl		= vfio_cdx_ioctl,
+	.mmap		= vfio_cdx_mmap,
+	.bind_iommufd	= vfio_iommufd_physical_bind,
+	.unbind_iommufd	= vfio_iommufd_physical_unbind,
+	.attach_ioas	= vfio_iommufd_physical_attach_ioas,
+};
+
+static int vfio_cdx_probe(struct cdx_device *cdx_dev)
+{
+	struct vfio_cdx_device *vdev;
+	struct device *dev = &cdx_dev->dev;
+	int ret;
+
+	vdev = vfio_alloc_device(vfio_cdx_device, vdev, dev,
+				 &vfio_cdx_ops);
+	if (IS_ERR(vdev))
+		return PTR_ERR(vdev);
+
+	ret = vfio_register_group_dev(&vdev->vdev);
+	if (ret)
+		goto out_uninit;
+
+	dev_set_drvdata(dev, vdev);
+	return 0;
+
+out_uninit:
+	vfio_put_device(&vdev->vdev);
+	return ret;
+}
+
+static int vfio_cdx_remove(struct cdx_device *cdx_dev)
+{
+	struct device *dev = &cdx_dev->dev;
+	struct vfio_cdx_device *vdev = dev_get_drvdata(dev);
+
+	vfio_unregister_group_dev(&vdev->vdev);
+	vfio_put_device(&vdev->vdev);
+
+	return 0;
+}
+
+static const struct cdx_device_id vfio_cdx_table[] = {
+	{ CDX_DEVICE_DRIVER_OVERRIDE(CDX_ANY_ID, CDX_ANY_ID,
+				     CDX_ID_F_VFIO_DRIVER_OVERRIDE) }, /* match all by default */
+	{}
+};
+
+MODULE_DEVICE_TABLE(cdx, vfio_cdx_table);
+
+static struct cdx_driver vfio_cdx_driver = {
+	.probe		= vfio_cdx_probe,
+	.remove		= vfio_cdx_remove,
+	.match_id_table	= vfio_cdx_table,
+	.driver	= {
+		.name	= "vfio-cdx",
+		.owner	= THIS_MODULE,
+	},
+	.driver_managed_dma = true,
+};
+
+module_driver(vfio_cdx_driver, cdx_driver_register, cdx_driver_unregister);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("VFIO for CDX devices - User Level meta-driver");

drivers/vfio/cdx/private.h

@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2022-2023, Advanced Micro Devices, Inc.
+ */
+
+#ifndef VFIO_CDX_PRIVATE_H
+#define VFIO_CDX_PRIVATE_H
+
+#define VFIO_CDX_OFFSET_SHIFT    40
+
+static inline u64 vfio_cdx_index_to_offset(u32 index)
+{
+	return ((u64)(index) << VFIO_CDX_OFFSET_SHIFT);
+}
+
+struct vfio_cdx_region {
+	u32			flags;
+	u32			type;
+	u64			addr;
+	resource_size_t		size;
+};
+
+struct vfio_cdx_device {
+	struct vfio_device	vdev;
+	struct vfio_cdx_region	*regions;
+};
+
+#endif /* VFIO_CDX_PRIVATE_H */

drivers/vfio/fsl-mc/Kconfig

@@ -1,10 +1,14 @@
+menu "VFIO support for FSL_MC bus devices"
+	depends on FSL_MC_BUS
+
 config VFIO_FSL_MC
 	tristate "VFIO support for QorIQ DPAA2 fsl-mc bus devices"
-	depends on FSL_MC_BUS
 	select EVENTFD
 	help
 	  Driver to enable support for the VFIO QorIQ DPAA2 fsl-mc
 	  (Management Complex) devices. This is required to passthrough
 	  fsl-mc bus devices using the VFIO framework.
 
 	  If you don't know what to do here, say N.
+
+endmenu

drivers/vfio/mdev/mdev_core.c

@@ -72,12 +72,6 @@ int mdev_register_parent(struct mdev_parent *parent, struct device *dev,
 	parent->nr_types = nr_types;
 	atomic_set(&parent->available_instances, mdev_driver->max_instances);
 
-	if (!mdev_bus_compat_class) {
-		mdev_bus_compat_class = class_compat_register("mdev_bus");
-		if (!mdev_bus_compat_class)
-			return -ENOMEM;
-	}
-
 	ret = parent_create_sysfs_files(parent);
 	if (ret)
 		return ret;
@@ -251,13 +245,24 @@ int mdev_device_remove(struct mdev_device *mdev)
 
 static int __init mdev_init(void)
 {
-	return bus_register(&mdev_bus_type);
+	int ret;
+
+	ret = bus_register(&mdev_bus_type);
+	if (ret)
+		return ret;
+
+	mdev_bus_compat_class = class_compat_register("mdev_bus");
+	if (!mdev_bus_compat_class) {
+		bus_unregister(&mdev_bus_type);
+		return -ENOMEM;
+	}
+
+	return 0;
 }
 
 static void __exit mdev_exit(void)
 {
-	if (mdev_bus_compat_class)
-		class_compat_unregister(mdev_bus_compat_class);
+	class_compat_unregister(mdev_bus_compat_class);
 	bus_unregister(&mdev_bus_type);
 }