drm/amdkfd: enable heavy-weight TLB flush on Vega20

Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git

kernel os linux

It is to meet the requirement for memory allocation
optimization on MI50.

Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

authored by

Eric Huang and committed by

Alex Deucher 4 years ago 1790b649 039cacd2

+2 -1

1 changed file

expand all

drivers

gpu

drm

amd

amdkfd

kfd_chardev.c

+2 -1

drivers/gpu/drm/amd/amdkfd/kfd_chardev.c

··· 1419 1419 static bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev) { 1420 1420 return KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2) || 1421 1421 (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) && 1422 - dev->adev->sdma.instance[0].fw_version >= 18); 1422 + dev->adev->sdma.instance[0].fw_version >= 18) || 1423 + KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 0); 1423 1424 } 1424 1425 1425 1426 static int kfd_ioctl_map_memory_to_gpu(struct file *filep,