drm/radeon: compute ring fix hibernation (CI GPU family) v2.

In order for hibernation to reliably work we need to cleanup more
thoroughly the compute ring. Hibernation is different from suspend
resume as when we resume from hibernation the hardware is first
fully initialize by regular kernel then freeze callback happens
(which correspond to a suspend inside the radeon kernel driver)
and turn off each of the block. It turns out we were not cleanly
shutting down the compute ring. This patch fix that.

Hibernation and suspend to ram were tested (several times) on :
Bonaire
Hawaii
Mullins
Kaveri
Kabini

Changed since v1:
  - Factor the ring stop logic into a function taking ring as arg.

Cc: stable@vger.kernel.org
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/radeon/cik.c

@@ -4604,6 +4604,31 @@ void cik_compute_set_wptr(struct radeon_device *rdev,
 	WDOORBELL32(ring->doorbell_index, ring->wptr);
 }
 
+static void cik_compute_stop(struct radeon_device *rdev,
+			     struct radeon_ring *ring)
+{
+	u32 j, tmp;
+
+	cik_srbm_select(rdev, ring->me, ring->pipe, ring->queue, 0);
+	/* Disable wptr polling. */
+	tmp = RREG32(CP_PQ_WPTR_POLL_CNTL);
+	tmp &= ~WPTR_POLL_EN;
+	WREG32(CP_PQ_WPTR_POLL_CNTL, tmp);
+	/* Disable HQD. */
+	if (RREG32(CP_HQD_ACTIVE) & 1) {
+		WREG32(CP_HQD_DEQUEUE_REQUEST, 1);
+		for (j = 0; j < rdev->usec_timeout; j++) {
+			if (!(RREG32(CP_HQD_ACTIVE) & 1))
+				break;
+			udelay(1);
+		}
+		WREG32(CP_HQD_DEQUEUE_REQUEST, 0);
+		WREG32(CP_HQD_PQ_RPTR, 0);
+		WREG32(CP_HQD_PQ_WPTR, 0);
+	}
+	cik_srbm_select(rdev, 0, 0, 0, 0);
+}
+
 /**
  * cik_cp_compute_enable - enable/disable the compute CP MEs
  *
@@ -4617,6 +4642,15 @@ static void cik_cp_compute_enable(struct radeon_device *rdev, bool enable)
 	if (enable)
 		WREG32(CP_MEC_CNTL, 0);
 	else {
+		/*
+		 * To make hibernation reliable we need to clear compute ring
+		 * configuration before halting the compute ring.
+		 */
+		mutex_lock(&rdev->srbm_mutex);
+		cik_compute_stop(rdev,&rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX]);
+		cik_compute_stop(rdev,&rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX]);
+		mutex_unlock(&rdev->srbm_mutex);
+
 		WREG32(CP_MEC_CNTL, (MEC_ME1_HALT | MEC_ME2_HALT));
 		rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX].ready = false;
 		rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX].ready = false;