Editing Hypervisors
Jump to navigation
Jump to search
Warning: You are not logged in. Your IP address will be publicly visible if you make any edits. If you log in or create an account, your edits will be attributed to your username, along with other benefits.
The edit can be undone.
Please check the comparison below to verify that this is what you want to do, and then save the changes below to finish undoing the edit.
Latest revision | Your text | ||
Line 94: | Line 94: | ||
VFIO (short for Virtual Function I/O) is a Linux kernel driver for PCI passthrough. Its appeal is that it works with graphics cards, meaning hypervisors on Linux can bypass graphics emulation for modern Windows games as opposed to having to use compatibility layers and wrappers. The catch is that the system needs; | VFIO (short for Virtual Function I/O) is a Linux kernel driver for PCI passthrough. Its appeal is that it works with graphics cards, meaning hypervisors on Linux can bypass graphics emulation for modern Windows games as opposed to having to use compatibility layers and wrappers. The catch is that the system needs; | ||
* An IOMMU (outlined in the VT-d and AMD-Vi specs) with processor and motherboard support | * An IOMMU (outlined in the VT-d and AMD-Vi specs) with processor and motherboard support | ||
+ | * A custom kernel build | ||
And because the graphics card doesn't get utilized until the guest powers on, that also means; | And because the graphics card doesn't get utilized until the guest powers on, that also means; | ||
− | * A dedicated monitor | + | * A dedicated monitor |
If you're using an NVIDIA card, you also need to configure how the graphics card appears to the VM so that NVIDIA's driver doesn't reject the card. | If you're using an NVIDIA card, you also need to configure how the graphics card appears to the VM so that NVIDIA's driver doesn't reject the card. |