1 files changed, 18 insertions, 7 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index fef7d020bc5f..970b066b37bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -98,7 +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);
@@ -118,10 +125,14 @@ 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);
+
+		while (halt_if_hws_hang)
+			schedule();
+
 		return -ETIMEDOUT;
 	}
 
@@ -377,6 +388,7 @@ static int mes_v11_0_set_hw_resources(struct amdgpu_mes *mes)
 	mes_set_hw_res_pkt.disable_reset = 1;
 	mes_set_hw_res_pkt.disable_mes_log = 1;
 	mes_set_hw_res_pkt.use_different_vmid_compute = 1;
+	mes_set_hw_res_pkt.enable_reg_active_poll = 1;
 	mes_set_hw_res_pkt.oversubscription_timer = 50;
 
 	return mes_v11_0_submit_pkt_and_poll_completion(mes,
@@ -478,10 +490,6 @@ static int mes_v11_0_init_microcode(struct amdgpu_device *adev,
 
 	mes_hdr = (const struct mes_firmware_header_v1_0 *)
 		adev->mes.fw[pipe]->data;
-	adev->mes.ucode_fw_version[pipe] =
-		le32_to_cpu(mes_hdr->mes_ucode_version);
-	adev->mes.ucode_fw_version[pipe] =
-		le32_to_cpu(mes_hdr->mes_ucode_data_version);
 	adev->mes.uc_start_addr[pipe] =
 		le32_to_cpu(mes_hdr->mes_uc_start_addr_lo) |
 		((uint64_t)(le32_to_cpu(mes_hdr->mes_uc_start_addr_hi)) << 32);
@@ -1246,7 +1254,9 @@ 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);
+	if (!amdgpu_sriov_vf(adev))
+		mes_v11_0_enable(adev, false);
+
 	return 0;
 }
 
@@ -1332,7 +1342,8 @@ static int mes_v11_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (!amdgpu_in_reset(adev) &&
+	/* it's only intended for use in mes_self_test case, not for s0ix and reset */
+	if (!amdgpu_in_reset(adev) && !adev->in_s0ix &&
 	    (adev->ip_versions[GC_HWIP][0] != IP_VERSION(11, 0, 3)))
 		amdgpu_mes_self_test(adev);