1 files changed, 64 insertions, 5 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index cc3fdbbcd314..f141fadd2d86 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -38,6 +38,8 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_1_mes.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_1_mes1.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_2_mes.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_2_mes1.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_3_mes.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_3_mes1.bin");
 
 static int mes_v11_0_hw_fini(void *handle);
 static int mes_v11_0_kiq_hw_init(struct amdgpu_device *adev);
@@ -96,7 +98,14 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
 	struct amdgpu_device *adev = mes->adev;
 	struct amdgpu_ring *ring = &mes->ring;
 	unsigned long flags;
+	signed long timeout = adev->usec_timeout;
 
+	if (amdgpu_emu_mode) {
+		timeout *= 100;
+	} else if (amdgpu_sriov_vf(adev)) {
+		/* Worst case in sriov where all other 15 VF timeout, each VF needs about 600ms */
+		timeout = 15 * 600 * 1000;
+	}
 	BUG_ON(size % 4 != 0);
 
 	spin_lock_irqsave(&mes->ring_lock, flags);
@@ -116,7 +125,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
 	DRM_DEBUG("MES msg=%d was emitted\n", x_pkt->header.opcode);
 
 	r = amdgpu_fence_wait_polling(ring, ring->fence_drv.sync_seq,
-		      adev->usec_timeout * (amdgpu_emu_mode ? 100 : 1));
+		      timeout);
 	if (r < 1) {
 		DRM_ERROR("MES failed to response msg=%d\n",
 			  x_pkt->header.opcode);
@@ -185,6 +194,19 @@ static int mes_v11_0_add_hw_queue(struct amdgpu_mes *mes,
 	mes_add_queue_pkt.is_kfd_process = input->is_kfd_process;
 	mes_add_queue_pkt.trap_en = 1;
 
+	/* For KFD, gds_size is re-used for queue size (needed in MES for AQL queues) */
+	mes_add_queue_pkt.is_aql_queue = input->is_aql_queue;
+	mes_add_queue_pkt.gds_size = input->queue_size;
+
+	if (!(((adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 4) &&
+		  (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(11, 0, 0)) &&
+		  (adev->ip_versions[GC_HWIP][0] <= IP_VERSION(11, 0, 3))))
+		mes_add_queue_pkt.trap_en = 1;
+
+	/* For KFD, gds_size is re-used for queue size (needed in MES for AQL queues) */
+	mes_add_queue_pkt.is_aql_queue = input->is_aql_queue;
+	mes_add_queue_pkt.gds_size = input->queue_size;
+
 	return mes_v11_0_submit_pkt_and_poll_completion(mes,
 			&mes_add_queue_pkt, sizeof(mes_add_queue_pkt),
 			offsetof(union MESAPI__ADD_QUEUE, api_status));
@@ -1141,6 +1163,42 @@ static int mes_v11_0_sw_fini(void *handle)
 	return 0;
 }
 
+static void mes_v11_0_kiq_dequeue_sched(struct amdgpu_device *adev)
+{
+	uint32_t data;
+	int i;
+
+	mutex_lock(&adev->srbm_mutex);
+	soc21_grbm_select(adev, 3, AMDGPU_MES_SCHED_PIPE, 0, 0);
+
+	/* disable the queue if it's active */
+	if (RREG32_SOC15(GC, 0, regCP_HQD_ACTIVE) & 1) {
+		WREG32_SOC15(GC, 0, regCP_HQD_DEQUEUE_REQUEST, 1);
+		for (i = 0; i < adev->usec_timeout; i++) {
+			if (!(RREG32_SOC15(GC, 0, regCP_HQD_ACTIVE) & 1))
+				break;
+			udelay(1);
+		}
+	}
+	data = RREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL);
+	data = REG_SET_FIELD(data, CP_HQD_PQ_DOORBELL_CONTROL,
+				DOORBELL_EN, 0);
+	data = REG_SET_FIELD(data, CP_HQD_PQ_DOORBELL_CONTROL,
+				DOORBELL_HIT, 1);
+	WREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL, data);
+
+	WREG32_SOC15(GC, 0, regCP_HQD_PQ_DOORBELL_CONTROL, 0);
+
+	WREG32_SOC15(GC, 0, regCP_HQD_PQ_WPTR_LO, 0);
+	WREG32_SOC15(GC, 0, regCP_HQD_PQ_WPTR_HI, 0);
+	WREG32_SOC15(GC, 0, regCP_HQD_PQ_RPTR, 0);
+
+	soc21_grbm_select(adev, 0, 0, 0, 0);
+	mutex_unlock(&adev->srbm_mutex);
+
+	adev->mes.ring.sched.ready = false;
+}
+
 static void mes_v11_0_kiq_setting(struct amdgpu_ring *ring)
 {
 	uint32_t tmp;
@@ -1192,6 +1250,9 @@ failure:
 
 static int mes_v11_0_kiq_hw_fini(struct amdgpu_device *adev)
 {
+	if (adev->mes.ring.sched.ready)
+		mes_v11_0_kiq_dequeue_sched(adev);
+
 	mes_v11_0_enable(adev, false);
 	return 0;
 }
@@ -1247,9 +1308,6 @@ failure:
 
 static int mes_v11_0_hw_fini(void *handle)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	adev->mes.ring.sched.ready = false;
 	return 0;
 }
 
@@ -1281,7 +1339,8 @@ static int mes_v11_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (!amdgpu_in_reset(adev))
+	if (!amdgpu_in_reset(adev) &&
+	    (adev->ip_versions[GC_HWIP][0] != IP_VERSION(11, 0, 3)))
 		amdgpu_mes_self_test(adev);
 
 	return 0;