/openbmc/qemu/docs/devel/ |
H A D | vfio-iommufd.rst | 38 | iommufd | | vfio legacy | 42 | /dev/iommu | /dev/vfio/vfio 43 | /dev/vfio/devices/vfioX | /dev/vfio/$group_id 52 iommufd | | vfio | 57 | iommfd core | | device | | vfio iommu | 64 - vfio legacy BE: uses group fd and container fd to setup secure context 69 - iommufd BE: device fd is opened through ``/dev/vfio/devices/vfioX`` 70 - vfio legacy BE: device fd is retrieved from group fd ioctl 77 * vfio legacy BE: uses container fd 95 named iommufd which allows to pass an iommufd object. Take ``vfio-pci`` [all …]
|
/openbmc/linux/drivers/vfio/ |
H A D | Makefile | 2 obj-$(CONFIG_VFIO) += vfio.o 4 vfio-y += vfio_main.o \ 6 vfio-$(CONFIG_VFIO_DEVICE_CDEV) += device_cdev.o 7 vfio-$(CONFIG_VFIO_GROUP) += group.o 8 vfio-$(CONFIG_IOMMUFD) += iommufd.o 9 vfio-$(CONFIG_VFIO_CONTAINER) += container.o 10 vfio-$(CONFIG_VFIO_VIRQFD) += virqfd.o
|
H A D | group.c | 18 static struct vfio { struct 24 } vfio; argument 513 lockdep_assert_held(&vfio.group_lock); in vfio_group_find_from_iommu() 519 list_for_each_entry(group, &vfio.group_list, vfio_next) { in vfio_group_find_from_iommu() 534 ida_free(&vfio.group_ida, MINOR(group->dev.devt)); in vfio_group_release() 548 minor = ida_alloc_max(&vfio.group_ida, MINORMASK, GFP_KERNEL); in vfio_group_alloc() 555 group->dev.devt = MKDEV(MAJOR(vfio.group_devt), minor); in vfio_group_alloc() 556 group->dev.class = vfio.class; in vfio_group_alloc() 582 lockdep_assert_held(&vfio.group_lock); in vfio_create_group() 602 list_add(&group->vfio_next, &vfio.group_list); in vfio_create_group() [all …]
|
H A D | container.c | 27 static struct vfio { struct 30 } vfio; variable 104 mutex_lock(&vfio.iommu_drivers_lock); in vfio_register_iommu_driver() 107 list_for_each_entry(tmp, &vfio.iommu_drivers_list, vfio_next) { in vfio_register_iommu_driver() 109 mutex_unlock(&vfio.iommu_drivers_lock); in vfio_register_iommu_driver() 115 list_add(&driver->vfio_next, &vfio.iommu_drivers_list); in vfio_register_iommu_driver() 117 mutex_unlock(&vfio.iommu_drivers_lock); in vfio_register_iommu_driver() 127 mutex_lock(&vfio.iommu_drivers_lock); in vfio_unregister_iommu_driver() 128 list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) { in vfio_unregister_iommu_driver() 131 mutex_unlock(&vfio.iommu_drivers_lock); in vfio_unregister_iommu_driver() [all …]
|
H A D | Kconfig | 12 See Documentation/driver-api/vfio.rst for more details. 18 bool "Support for the VFIO cdev /dev/vfio/devices/vfioX" 24 /dev/vfio/devices/vfioX, and then bind the device fd with an iommufd 31 bool "Support for the VFIO group /dev/vfio/$group_id" 41 bool "Support for the VFIO container /dev/vfio/vfio" 83 source "drivers/vfio/pci/Kconfig" 84 source "drivers/vfio/platform/Kconfig" 85 source "drivers/vfio/mdev/Kconfig" 86 source "drivers/vfio/fsl-mc/Kconfig" 87 source "drivers/vfio/cdx/Kconfig"
|
/openbmc/linux/drivers/vfio/platform/ |
H A D | Makefile | 2 vfio-platform-base-y := vfio_platform_common.o vfio_platform_irq.o 3 obj-$(CONFIG_VFIO_PLATFORM_BASE) += vfio-platform-base.o 6 vfio-platform-y := vfio_platform.o 7 obj-$(CONFIG_VFIO_PLATFORM) += vfio-platform.o 9 vfio-amba-y := vfio_amba.o 10 obj-$(CONFIG_VFIO_AMBA) += vfio-amba.o
|
/openbmc/linux/drivers/vfio/pci/ |
H A D | Makefile | 3 vfio-pci-core-y := vfio_pci_core.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o 4 vfio-pci-core-$(CONFIG_VFIO_PCI_ZDEV_KVM) += vfio_pci_zdev.o 5 obj-$(CONFIG_VFIO_PCI_CORE) += vfio-pci-core.o 7 vfio-pci-y := vfio_pci.o 8 vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o 9 obj-$(CONFIG_VFIO_PCI) += vfio-pci.o
|
H A D | Kconfig | 48 To enable Intel IGD assignment through vfio-pci, say Y. 60 To enable s390x KVM vfio-pci extensions, say Y. 62 source "drivers/vfio/pci/mlx5/Kconfig" 64 source "drivers/vfio/pci/hisilicon/Kconfig" 66 source "drivers/vfio/pci/pds/Kconfig"
|
/openbmc/linux/Documentation/arch/s390/ |
H A D | vfio-ccw.rst | 2 vfio-ccw: the basic infrastructure 8 Here we describe the vfio support for I/O subchannel devices for 9 Linux/s390. Motivation for vfio-ccw is to passthrough subchannels to a 10 virtual machine, while vfio is the means. 20 Thus when we introduce vfio support for these devices, we realize it 21 with a mediated device (mdev) implementation. The vfio mdev will be 23 vfio framework. And we add read/write callbacks for special vfio I/O 40 For vfio mediated device framework: 41 - Documentation/driver-api/vfio-mediated-device.rst 43 Motivation of vfio-ccw [all …]
|
H A D | index.rst | 14 vfio-ap 15 vfio-ap-locking 16 vfio-ccw
|
/openbmc/linux/Documentation/networking/device_drivers/ethernet/amd/ |
H A D | pds_vfio_pci.rst | 14 The ``pds-vfio-pci`` module is a PCI driver that supports Live Migration 20 The pds-vfio-pci device is enabled via multiple configuration steps and 26 example assumes the pds_core and pds-vfio-pci modules are already 38 # Prevent non-vfio VF driver from probing the VF device 44 # Allow the VF to be bound to the pds-vfio-pci driver 45 echo "pds-vfio-pci" > /sys/class/pci_bus/$PF_BUS/device/$VF_BDF/driver_override 47 # Bind the VF to the pds-vfio-pci driver 48 echo "$VF_BDF" > /sys/bus/pci/drivers/pds-vfio-pci/bind 50 After performing the steps above, a file in /dev/vfio/<iommu_group>
|
/openbmc/linux/Documentation/driver-api/ |
H A D | vfio-pci-device-specific-driver-acceptance.rst | 3 Acceptance criteria for vfio-pci device specific driver variants 8 The vfio-pci driver exists as a device agnostic driver using the 11 vfio-pci driver does include some device specific support, further 13 sustainable. The vfio-pci driver has therefore split out 14 vfio-pci-core as a library that may be reused to implement features 21 accessible via the vfio-pci base driver. Authors of such drivers 32 available to the user via vfio-pci, what safeguards exist to validate 35 to the overall vfio maintainer.
|
H A D | vfio.rst | 81 is created by simply opening the /dev/vfio/vfio character device. 90 VFIO group will appear for the group as /dev/vfio/$GROUP, where 100 the VFIO group character device (/dev/vfio/$GROUP) and using the 127 pci bus, therefore the user will make use of vfio-pci to manage the 130 # modprobe vfio-pci 132 Binding this device to the vfio-pci driver creates the VFIO group 138 # echo 1102 0002 > /sys/bus/pci/drivers/vfio-pci/new_id 156 bind this device to the vfio-pci driver (vfio-pci does not currently 160 unprivileged operation is desired (note that /dev/vfio/vfio provides 164 # chown user:user /dev/vfio/26 [all …]
|
/openbmc/linux/drivers/vfio/platform/reset/ |
H A D | Makefile | 2 vfio-platform-calxedaxgmac-y := vfio_platform_calxedaxgmac.o 3 vfio-platform-amdxgbe-y := vfio_platform_amdxgbe.o 5 obj-$(CONFIG_VFIO_PLATFORM_CALXEDAXGMAC_RESET) += vfio-platform-calxedaxgmac.o 6 obj-$(CONFIG_VFIO_PLATFORM_AMDXGBE_RESET) += vfio-platform-amdxgbe.o
|
/openbmc/qemu/docs/system/ |
H A D | target-s390x.rst | 21 the available devices. Passthrough of host devices via vfio-pci, vfio-ccw, 22 or vfio-ap is also available. 25 s390x/vfio-ap 28 s390x/vfio-ccw
|
/openbmc/qemu/docs/ |
H A D | igd-assign.txt | 1 Intel Graphics Device (IGD) assignment with vfio-pci 4 IGD has two different modes for assignment using vfio-pci: 18 theoretically has no device specific handling dependencies on vfio-pci or 30 * The host kernel must support vfio extensions for IGD (v4.6) 31 * vfio VGA support very likely needs to be enabled in the host kernel 35 ISA/LPC bridge device (vfio-pci-igd-lpc-bridge) on the root bus at 38 option or loaded automatically through vfio (standard). rombar=0 48 the driver_override option can be used to ensure that only vfio-pci can bind 50 device to vfio drivers and then managed='no' set in the VM xml to prevent 53 blacklisting i915 or using pci-stub/vfio-pci to take ownership of IGD as a [all …]
|
/openbmc/qemu/migration/ |
H A D | target.c | 21 info->vfio = g_malloc0(sizeof(*info->vfio)); in migration_populate_vfio_info() 22 info->vfio->transferred = vfio_mig_bytes_transferred(); in migration_populate_vfio_info()
|
/openbmc/linux/Documentation/ABI/testing/ |
H A D | sysfs-devices-vfio-dev | 1 What: /sys/.../<device>/vfio-dev/vfioX/ 6 vfio driver. The layout under this directory matches what 8 index marking this device in vfio.
|
/openbmc/qemu/docs/system/s390x/ |
H A D | vfio-ccw.rst | 1 Subchannel passthrough via vfio-ccw 4 vfio-ccw (based upon the mediated vfio device infrastructure) allows to 8 Note that while vfio-ccw should work with most non-QDIO devices, only ECKD 43 I/O subchannel driver and bind it to the vfio-ccw driver:: 60 -device vfio-ccw,devno=fe.0.1234,sysfsdev=\
|
/openbmc/linux/drivers/iommu/iommufd/ |
H A D | Kconfig | 16 bool "IOMMUFD provides the VFIO container /dev/vfio/vfio" 20 IOMMUFD will provide /dev/vfio/vfio instead of VFIO. This relies on
|
/openbmc/linux/drivers/vfio/cdx/ |
H A D | Makefile | 6 obj-$(CONFIG_VFIO_CDX) += vfio-cdx.o 8 vfio-cdx-objs := main.o
|
/openbmc/linux/drivers/vfio/pci/hisilicon/ |
H A D | Makefile | 2 obj-$(CONFIG_HISI_ACC_VFIO_PCI) += hisi-acc-vfio-pci.o 3 hisi-acc-vfio-pci-y := hisi_acc_vfio_pci.o
|
/openbmc/linux/drivers/vfio/fsl-mc/ |
H A D | Makefile | 3 vfio-fsl-mc-y := vfio_fsl_mc.o vfio_fsl_mc_intr.o 4 obj-$(CONFIG_VFIO_FSL_MC) += vfio-fsl-mc.o
|
/openbmc/linux/drivers/vfio/pci/mlx5/ |
H A D | Makefile | 2 obj-$(CONFIG_MLX5_VFIO_PCI) += mlx5-vfio-pci.o 3 mlx5-vfio-pci-y := main.o cmd.o
|
/openbmc/linux/drivers/vfio/pci/pds/ |
H A D | Makefile | 4 obj-$(CONFIG_PDS_VFIO_PCI) += pds-vfio-pci.o 6 pds-vfio-pci-y := \
|