[PATCH] drm/radeon: Always flush VM again on < CIK

[Alex Deucher]

On Fri, Aug 8, 2014 at 4:50 AM, Michel Dänzer <michel at daenzer.net> wrote:
> On 08.08.2014 17:44, Christian König wrote:
>>>>> On Thu, Aug 7, 2014 at 3:59 PM, Alex Deucher <alexdeucher at gmail.com>
>>>>> wrote:
>>>>>> We should be using PFP as much as possible.  Does the attached
>>>>>> patch help?
>>> Unfortunately not.
>>
>> Maybe add a readback of the VM base addr pointer to make sure that the
>> write has really reached the SBRM?
>
> I'm not sure what exactly you're thinking of, but I'm happy to test any
> patches you guys come up with. :)
>

Maybe some variant of this patch?

Alex
-------------- next part --------------
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index dbd9d81..0855da0 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -5007,6 +5007,7 @@ static void si_vm_decode_fault(struct radeon_device *rdev,
 void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 {
 	struct radeon_ring *ring = &rdev->ring[ridx];
+	u32 reg;
 
 	if (vm == NULL)
 		return;
@@ -5017,15 +5018,23 @@ void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 				 WRITE_DATA_DST_SEL(0)));
 
 	if (vm->id < 8) {
-		radeon_ring_write(ring,
-				  (VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2)) >> 2);
+		reg = (VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (vm->id << 2)) >> 2;
 	} else {
-		radeon_ring_write(ring,
-				  (VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm->id - 8) << 2)) >> 2);
+		reg = (VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((vm->id - 8) << 2)) >> 2;
 	}
+	radeon_ring_write(ring, reg);
 	radeon_ring_write(ring, 0);
 	radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
 
+	/* wait for the address change to go through */
+	radeon_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
+	radeon_ring_write(ring, 3); /* == */
+	radeon_ring_write(ring, reg);
+	radeon_ring_write(ring, 0);
+	radeon_ring_write(ring, vm->pd_gpu_addr >> 12);
+	radeon_ring_write(ring, 0x0fffffff);
+	radeon_ring_write(ring, 10);
+
 	/* flush hdp cache */
 	radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
 	radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(1) |
@@ -5034,6 +5043,14 @@ void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 	radeon_ring_write(ring, 0);
 	radeon_ring_write(ring, 0x1);
 
+	/* clear the response reg */
+	radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
+	radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(1) |
+				 WRITE_DATA_DST_SEL(0)));
+	radeon_ring_write(ring, VM_INVALIDATE_RESPONSE >> 2);
+	radeon_ring_write(ring, 0);
+	radeon_ring_write(ring, 1 << vm->id);
+
 	/* bits 0-15 are the VM contexts0-15 */
 	radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
 	radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(1) |
@@ -5042,6 +5059,15 @@ void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 	radeon_ring_write(ring, 0);
 	radeon_ring_write(ring, 1 << vm->id);
 
+	/* wait for the invalidate */
+	radeon_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
+	radeon_ring_write(ring, 3); /* == */
+	radeon_ring_write(ring, VM_INVALIDATE_RESPONSE >> 2);
+	radeon_ring_write(ring, 0);
+	radeon_ring_write(ring, 1 << vm->id);
+	radeon_ring_write(ring, 1 << vm->id);
+	radeon_ring_write(ring, 10);
+
 	/* sync PFP to ME, otherwise we might get invalid PFP reads */
 	radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0));
 	radeon_ring_write(ring, 0x0);