drm/amdgpu: Update invalid PTE flag setting

Update the invalid PTE flag setting with TF enabled.
This is to ensure, in addition to transitioning the
retry fault to a no-retry fault, it also causes the
wavefront to enter the trap handler. With the current
setting, the fault only transitions to a no-retry fault.
Additionally, have 2 sets of invalid PTE settings, one for
TF enabled, the other for TF disabled. The setting with
TF disabled, doesn't work with TF enabled.

Signed-off-by: Mukul Joshi <[email protected]>
Acked-by: Christian König <[email protected]>
Reviewed-by: Felix Kuehling <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

1 files changed, 31 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
index dea1a64be44d..24ddf6a0512a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
@@ -778,6 +778,27 @@ int amdgpu_vm_pde_update(struct amdgpu_vm_update_params *params,
 					1, 0, flags);
 }
 
+/**
+ * amdgpu_vm_pte_update_noretry_flags - Update PTE no-retry flags
+ *
+ * @adev - amdgpu_device pointer
+ * @flags: pointer to PTE flags
+ *
+ * Update PTE no-retry flags when TF is enabled.
+ */
+static void amdgpu_vm_pte_update_noretry_flags(struct amdgpu_device *adev,
+						uint64_t *flags)
+{
+	/*
+	 * Update no-retry flags with the corresponding TF
+	 * no-retry combination.
+	 */
+	if ((*flags & AMDGPU_VM_NORETRY_FLAGS) == AMDGPU_VM_NORETRY_FLAGS) {
+		*flags &= ~AMDGPU_VM_NORETRY_FLAGS;
+		*flags |= adev->gmc.noretry_flags;
+	}
+}
+
 /*
  * amdgpu_vm_pte_update_flags - figure out flags for PTE updates
  *
@@ -804,6 +825,16 @@ static void amdgpu_vm_pte_update_flags(struct amdgpu_vm_update_params *params,
 		flags |= AMDGPU_PTE_EXECUTABLE;
 	}
 
+	/*
+	 * Update no-retry flags to use the no-retry flag combination
+	 * with TF enabled. The AMDGPU_VM_NORETRY_FLAGS flag combination
+	 * does not work when TF is enabled. So, replace them with
+	 * AMDGPU_VM_NORETRY_FLAGS_TF flag combination which works for
+	 * all cases.
+	 */
+	if (level == AMDGPU_VM_PTB)
+		amdgpu_vm_pte_update_noretry_flags(adev, &flags);
+
 	/* APUs mapping system memory may need different MTYPEs on different
 	 * NUMA nodes. Only do this for contiguous ranges that can be assumed
 	 * to be on the same NUMA node.