Merge tag 'amd-drm-next-5.15-2021-07-29' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.15-2021-07-29:

amdgpu:
- VCN/JPEG power down sequencing fixes
- Various navi pcie link handling fixes
- Clockgating fixes
- Yellow Carp fixes
- Beige Goby fixes
- Misc code cleanups
- S0ix fixes
- SMU i2c bus rework
- EEPROM handling rework
- PSP ucode handling cleanup
- SMU error handling rework
- AMD HDMI freesync fixes
- USB PD firmware update rework
- MMIO based vram access rework
- Misc display fixes
- Backlight fixes
- Add initial Cyan Skillfish support
- Overclocking fixes suspend/resume

amdkfd:
- Sysfs leak fix
- Add counters for vm faults and migration
- GPUVM TLB optimizations

radeon:
- Misc fixes

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210730033455.3852-1-alexander.deucher@amd.com

1 files changed, 23 insertions, 16 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 16a1713808c2..a972ef5eae68 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -260,7 +260,7 @@ static int allocate_vmid(struct device_queue_manager *dqm,
 static int flush_texture_cache_nocpsch(struct kfd_dev *kdev,
 				struct qcm_process_device *qpd)
 {
-	const struct packet_manager_funcs *pmf = qpd->dqm->packets.pmf;
+	const struct packet_manager_funcs *pmf = qpd->dqm->packet_mgr.pmf;
 	int ret;
 
 	if (!qpd->ib_kaddr)
@@ -1000,7 +1000,7 @@ static int start_nocpsch(struct device_queue_manager *dqm)
 	init_interrupts(dqm);
 	
 	if (dqm->dev->device_info->asic_family == CHIP_HAWAII)
-		return pm_init(&dqm->packets, dqm);
+		return pm_init(&dqm->packet_mgr, dqm);
 	dqm->sched_running = true;
 
 	return 0;
@@ -1009,7 +1009,7 @@ static int start_nocpsch(struct device_queue_manager *dqm)
 static int stop_nocpsch(struct device_queue_manager *dqm)
 {
 	if (dqm->dev->device_info->asic_family == CHIP_HAWAII)
-		pm_uninit(&dqm->packets, false);
+		pm_uninit(&dqm->packet_mgr, false);
 	dqm->sched_running = false;
 
 	return 0;
@@ -1124,7 +1124,7 @@ static int set_sched_resources(struct device_queue_manager *dqm)
 			"queue mask: 0x%8llX\n",
 			res.vmid_mask, res.queue_mask);
 
-	return pm_send_set_resources(&dqm->packets, &res);
+	return pm_send_set_resources(&dqm->packet_mgr, &res);
 }
 
 static int initialize_cpsch(struct device_queue_manager *dqm)
@@ -1164,7 +1164,8 @@ static int start_cpsch(struct device_queue_manager *dqm)
 
 	retval = 0;
 
-	retval = pm_init(&dqm->packets, dqm);
+	dqm_lock(dqm);
+	retval = pm_init(&dqm->packet_mgr, dqm);
 	if (retval)
 		goto fail_packet_manager_init;
 
@@ -1186,7 +1187,6 @@ static int start_cpsch(struct device_queue_manager *dqm)
 
 	init_interrupts(dqm);
 
-	dqm_lock(dqm);
 	/* clear hang status when driver try to start the hw scheduler */
 	dqm->is_hws_hang = false;
 	dqm->is_resetting = false;
@@ -1197,8 +1197,9 @@ static int start_cpsch(struct device_queue_manager *dqm)
 	return 0;
 fail_allocate_vidmem:
 fail_set_sched_resources:
-	pm_uninit(&dqm->packets, false);
+	pm_uninit(&dqm->packet_mgr, false);
 fail_packet_manager_init:
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -1211,12 +1212,12 @@ static int stop_cpsch(struct device_queue_manager *dqm)
 		unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
 	hanging = dqm->is_hws_hang || dqm->is_resetting;
 	dqm->sched_running = false;
-	dqm_unlock(dqm);
 
-	pm_release_ib(&dqm->packets);
+	pm_release_ib(&dqm->packet_mgr);
 
 	kfd_gtt_sa_free(dqm->dev, dqm->fence_mem);
-	pm_uninit(&dqm->packets, hanging);
+	pm_uninit(&dqm->packet_mgr, hanging);
+	dqm_unlock(dqm);
 
 	return 0;
 }
@@ -1390,7 +1391,7 @@ static int map_queues_cpsch(struct device_queue_manager *dqm)
 	if (dqm->active_runlist)
 		return 0;
 
-	retval = pm_send_runlist(&dqm->packets, &dqm->queues);
+	retval = pm_send_runlist(&dqm->packet_mgr, &dqm->queues);
 	pr_debug("%s sent runlist\n", __func__);
 	if (retval) {
 		pr_err("failed to execute runlist\n");
@@ -1416,13 +1417,13 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 	if (!dqm->active_runlist)
 		return retval;
 
-	retval = pm_send_unmap_queue(&dqm->packets, KFD_QUEUE_TYPE_COMPUTE,
+	retval = pm_send_unmap_queue(&dqm->packet_mgr, KFD_QUEUE_TYPE_COMPUTE,
 			filter, filter_param, false, 0);
 	if (retval)
 		return retval;
 
 	*dqm->fence_addr = KFD_FENCE_INIT;
-	pm_send_query_status(&dqm->packets, dqm->fence_gpu_addr,
+	pm_send_query_status(&dqm->packet_mgr, dqm->fence_gpu_addr,
 				KFD_FENCE_COMPLETED);
 	/* should be timed out */
 	retval = amdkfd_fence_wait_timeout(dqm->fence_addr, KFD_FENCE_COMPLETED,
@@ -1448,14 +1449,14 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 	 * check those fields
 	 */
 	mqd_mgr = dqm->mqd_mgrs[KFD_MQD_TYPE_HIQ];
-	if (mqd_mgr->read_doorbell_id(dqm->packets.priv_queue->queue->mqd)) {
+	if (mqd_mgr->read_doorbell_id(dqm->packet_mgr.priv_queue->queue->mqd)) {
 		pr_err("HIQ MQD's queue_doorbell_id0 is not 0, Queue preemption time out\n");
 		while (halt_if_hws_hang)
 			schedule();
 		return -ETIME;
 	}
 
-	pm_release_ib(&dqm->packets);
+	pm_release_ib(&dqm->packet_mgr);
 	dqm->active_runlist = false;
 
 	return retval;
@@ -1946,6 +1947,7 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 	case CHIP_DIMGREY_CAVEFISH:
 	case CHIP_BEIGE_GOBY:
 	case CHIP_YELLOW_CARP:
+	case CHIP_CYAN_SKILLFISH:
 		device_queue_manager_init_v10_navi10(&dqm->asic_ops);
 		break;
 	default:
@@ -2099,11 +2101,16 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data)
 	return r;
 }
 
-int dqm_debugfs_execute_queues(struct device_queue_manager *dqm)
+int dqm_debugfs_hang_hws(struct device_queue_manager *dqm)
 {
 	int r = 0;
 
 	dqm_lock(dqm);
+	r = pm_debugfs_hang_hws(&dqm->packet_mgr);
+	if (r) {
+		dqm_unlock(dqm);
+		return r;
+	}
 	dqm->active_runlist = true;
 	r = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
 	dqm_unlock(dqm);