NVIDIA GPU firmware microcontroller (Falcon): MULTI-TENANT ISOLATION: a privileged user can time a DMA write

Impact

MULTI-TENANT ISOLATION: a privileged user can time a DMA write from the GPU's internal microcontroller to land inside a specific window and corrupt code execution, with impact NVIDIA says may extend to other components. A DMA engine writing outside its lane is the mechanism by which a GPU compromises its host.

Who can reach it

A user with elevated privileges on the GPU host, able to time operations precisely.

What to do

NVIDIA shipped the fix in GPU firmware/microcode delivered with the R470 and R450 driver branches and, on some SKUs, in an updated VBIOS. On most datacenter parts the microcontroller image is loaded by the driver at GPU init, so a driver upgrade plus a node reboot applies it; check the bulletin's product table, because a subset of boards also needs an out-of-band VBIOS/InfoROM update, which is an offline per-node flash with the GPU idle. Either way the node has to be drained.

References