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

SDMA FW fixes the hang issue for adding heavy-weight TLB
flush on Arcturus, so we can enable it.

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

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index f9bab963a948aed0ed7a69dedeb02364574f130b..5df387c4d7fbb543369d039d04cd39912b4cc281 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1813,12 +1813,6 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
                                true);
        ret = unreserve_bo_and_vms(&ctx, false, false);
 
-       /* Only apply no TLB flush on Aldebaran to
-        * workaround regressions on other Asics.
-        */
-       if (table_freed && (adev->asic_type != CHIP_ALDEBARAN))
-               *table_freed = true;
-
        goto out;
 
 out_unreserve:

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 4bfc0c8ab764be48fe14f6cb6b44b651a1b22723..337953af7c2fa26ca56fa51c788147e4736ab475 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1416,6 +1416,12 @@ err_unlock:
        return ret;
 }
 
+static bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev) {
+       return KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2) ||
+              (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) &&
+               dev->adev->sdma.instance[0].fw_version >= 18);
+}
+
 static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
                                        struct kfd_process *p, void *data)
 {
@@ -1503,7 +1509,7 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
        }
 
        /* Flush TLBs after waiting for the page table updates to complete */
-       if (table_freed) {
+       if (table_freed || !kfd_flush_tlb_after_unmap(dev)) {
                for (i = 0; i < args->n_devices; i++) {
                        peer = kfd_device_by_id(devices_arr[i]);
                        if (WARN_ON_ONCE(!peer))
@@ -1603,7 +1609,7 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
        }
        mutex_unlock(&p->mutex);
 
-       if (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2)) {
+       if (kfd_flush_tlb_after_unmap(dev)) {
                err = amdgpu_amdkfd_gpuvm_sync_memory(dev->adev,
                                (struct kgd_mem *) mem, true);
                if (err) {