drm/amdkfd: Add heavy-weight TLB flush after unmapping

It is a part of memory mapping optimization.

Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Eric Huang 2021-06-01 18:26:07 -04:00 committed by Alex Deucher
parent 3543b055b8
commit 1098d658be

View File

@ -1563,6 +1563,7 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
i, args->n_devices);
goto unmap_memory_from_gpu_failed;
}
kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT);
args->n_success = i+1;
}
kfree(devices_arr);