nouveau/tu102: flush all pdbs on vmm flush

This is a hack around a bug exposed with the GSP code, I'm not sure
what is happening exactly, but it appears some of our flushes don't
result in proper tlb invalidation for out BAR2 and we get a BAR2
fault from GSP and it all dies.

Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231130010852.4034774-1-airlied@gmail.com
This commit is contained in:
Dave Airlie
2023-11-30 11:08:52 +10:00
committed by Danilo Krummrich
parent 88a2b4d34a
commit cb9c919364
@@ -31,7 +31,7 @@ tu102_vmm_flush(struct nvkm_vmm *vmm, int depth)
type |= 0x00000001; /* PAGE_ALL */
if (atomic_read(&vmm->engref[NVKM_SUBDEV_BAR]))
type |= 0x00000004; /* HUB_ONLY */
type |= 0x00000006; /* HUB_ONLY | ALL PDB (hack) */
mutex_lock(&vmm->mmu->mutex);