blob: 9fce78ecfc5562629a17f15d866f06a9af28fb83 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
|
From 871a45729603c20acb9a0927eb549b667c9b68ba Mon Sep 17 00:00:00 2001
From: Alex Sierra <alex.sierra@amd.com>
Date: Mon, 18 Nov 2019 15:33:07 -0600
Subject: [PATCH 4554/4736] amd/amdgpu: force to trigger a no-retry-fault after
a retry-fault
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Only for the debugger use case.
[why]
Avoid endless translation retries, after an invalid address access has
been issued to the GPU. Instead, the trap handler is forced to enter by
generating a no-retry-fault.
A s_trap instruction is inserted in the debugger case to let the wave to
enter trap handler to save context.
[how]
Intentionally using an invalid flag combination (F and P set at the same
time) to trigger a no-retry-fault, after a retry-fault happens. This is
only valid under compute context.
Change-Id: I4180c30e2631dc0401cbd6171f8a6776e4733c9a
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index c3e87ca13c53..90ac5390ecdf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -3204,11 +3204,20 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid,
flags = AMDGPU_PTE_VALID | AMDGPU_PTE_SNOOPED |
AMDGPU_PTE_SYSTEM;
- if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_NEVER) {
+ if (vm->is_compute_context) {
+ /* Intentionally setting invalid PTE flag
+ * combination to force a no-retry-fault
+ */
+ flags = AMDGPU_PTE_EXECUTABLE | AMDGPU_PDE_PTE |
+ AMDGPU_PTE_TF;
+ value = 0;
+
+ } else if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_NEVER) {
/* Redirect the access to the dummy page */
value = adev->dummy_page_addr;
flags |= AMDGPU_PTE_EXECUTABLE | AMDGPU_PTE_READABLE |
AMDGPU_PTE_WRITEABLE;
+
} else {
/* Let the hw retry silently on the PTE */
value = 0;
--
2.17.1
|