Merge tag 'drm-next-2020-12-11' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Not a huge amount of big things here, AMD has support for a few new HW
  variants (vangogh, green sardine, dimgrey cavefish), Intel has some
  more DG1 enablement. We have a few big reworks of the TTM layers and
  interfaces, GEM and atomic internal API reworks cross tree. fbdev is
  marked orphaned in here as well to reflect the current reality.

  core:
   - documentation updates
   - deprecate DRM_FORMAT_MOD_NONE
   - atomic crtc enable/disable rework
   - GEM convert drivers to gem object functions
   - remove SCATTER_LIST_MAX_SEGMENT

  sched:
   - avoid infinite waits

  ttm:
   - remove AGP support
   - don't modify caching for swapout
   - ttm pinning rework
   - major TTM reworks
   - new backend allocator
   - multihop support

  vram-helper:
   - top down BO placement fix
   - TTM changes
   - GEM object support

  displayport:
   - DP 2.0 DPCD prep work
   - DP MST extended DPCD caps

  fbdev:
   - mark as orphaned

  amdgpu:
   - Initial Vangogh support
   - Green Sardine support
   - Dimgrey Cavefish support
   - SG display support for renoir
   - SMU7 improvements
   - gfx9+ modiifier support
   - CI BACO fixes

  radeon:
   - expose voltage via hwmon on SUMO

  amdkfd:
   - fix unique id handling

  i915:
   - more DG1 enablement
   - bigjoiner support
   - integer scaling filter support
   - async flip support
   - ICL+ DSI command mode
   - Improve display shutdown
   - Display refactoring
   - eLLC machine fbdev loading fix
   - dma scatterlist fixes
   - TGL hang fixes
   - eLLC display buffer caching on SKL+
   - MOCS PTE seeting for gen9+

  msm:
   - Shutdown hook
   - GPU cooling device support
   - DSI 7nm and 10nm phy/pll updates
   - sm8150/sm2850 DPU support
   - GEM locking re-work
   - LLCC system cache support

  aspeed:
   - sysfs output config support

  ast:
   - LUT fix
   - new display mode

  gma500:
   - remove 2d framebuffer accel

  panfrost:
   - move gpu reset to a worker

  exynos:
   - new HDMI mode support

  mediatek:
   - MT8167 support
   - yaml bindings
   - MIPI DSI phy code moved

  etnaviv:
   - new perf counter
   - more lockdep annotation

  hibmc:
   - i2c DDC support

  ingenic:
   - pixel clock reset fix
   - reserved memory support
   - allow both DMA channels at once
   - different pixel format support
   - 30/24/8-bit palette modes

  tilcdc:
   - don't keep vblank irq enabled

  vc4:
   - new maintainer added
   - DSI registration fix

  virtio:
   - blob resource support
   - host visible and cross-device support
   - uuid api support"

* tag 'drm-next-2020-12-11' of git://anongit.freedesktop.org/drm/drm: (1754 commits)
  drm/amdgpu: Initialise drm_gem_object_funcs for imported BOs
  drm/amdgpu: fix size calculation with stolen vga memory
  drm/amdgpu: remove amdgpu_ttm_late_init  and amdgpu_bo_late_init
  drm/amdgpu: free the pre-OS console framebuffer after the first modeset
  drm/amdgpu: enable runtime pm using BACO on CI dGPUs
  drm/amdgpu/cik: enable BACO reset on Bonaire
  drm/amd/pm: update smu10.h WORKLOAD_PPLIB setting for raven
  drm/amd/pm: remove one unsupported smu function for vangogh
  drm/amd/display: setup system context for APUs
  drm/amd/display: add S/G support for Vangogh
  drm/amdkfd: Fix leak in dmabuf import
  drm/amdgpu: use AMDGPU_NUM_VMID when possible
  drm/amdgpu: fix sdma instance fw version and feature version init
  drm/amd/pm: update driver if version for dimgrey_cavefish
  drm/amd/display: 3.2.115
  drm/amd/display: [FW Promotion] Release 0.0.45
  drm/amd/display: Revert DCN2.1 dram_clock_change_latency update
  drm/amd/display: Enable gpu_vm_support for dcn3.01
  drm/amd/display: Fixed the audio noise during mode switching with HDCP mode on
  drm/amd/display: Add wm table for Renoir
  ...

1 files changed, 110 insertions, 57 deletions

diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 55d16489d0f3..ab7c167b0623 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -14,6 +14,7 @@
 #include <generated/utsrelease.h>
 #include <linux/string_helpers.h>
 #include <linux/devfreq.h>
+#include <linux/devfreq_cooling.h>
 #include <linux/devcoredump.h>
 #include <linux/sched/task.h>
 
@@ -107,9 +108,18 @@ static void msm_devfreq_init(struct msm_gpu *gpu)
 	if (IS_ERR(gpu->devfreq.devfreq)) {
 		DRM_DEV_ERROR(&gpu->pdev->dev, "Couldn't initialize GPU devfreq\n");
 		gpu->devfreq.devfreq = NULL;
+		return;
 	}
 
 	devfreq_suspend_device(gpu->devfreq.devfreq);
+
+	gpu->cooling = of_devfreq_cooling_register(gpu->pdev->dev.of_node,
+			gpu->devfreq.devfreq);
+	if (IS_ERR(gpu->cooling)) {
+		DRM_DEV_ERROR(&gpu->pdev->dev,
+				"Couldn't register GPU cooling device\n");
+		gpu->cooling = NULL;
+	}
 }
 
 static int enable_pwrrail(struct msm_gpu *gpu)
@@ -177,15 +187,12 @@ static int disable_clk(struct msm_gpu *gpu)
 
 static int enable_axi(struct msm_gpu *gpu)
 {
-	if (gpu->ebi1_clk)
-		clk_prepare_enable(gpu->ebi1_clk);
-	return 0;
+	return clk_prepare_enable(gpu->ebi1_clk);
 }
 
 static int disable_axi(struct msm_gpu *gpu)
 {
-	if (gpu->ebi1_clk)
-		clk_disable_unprepare(gpu->ebi1_clk);
+	clk_disable_unprepare(gpu->ebi1_clk);
 	return 0;
 }
 
@@ -265,6 +272,22 @@ int msm_gpu_hw_init(struct msm_gpu *gpu)
 	return ret;
 }
 
+static void update_fences(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
+		uint32_t fence)
+{
+	struct msm_gem_submit *submit;
+
+	spin_lock(&ring->submit_lock);
+	list_for_each_entry(submit, &ring->submits, node) {
+		if (submit->seqno > fence)
+			break;
+
+		msm_update_fence(submit->ring->fctx,
+			submit->fence->seqno);
+	}
+	spin_unlock(&ring->submit_lock);
+}
+
 #ifdef CONFIG_DEV_COREDUMP
 static ssize_t msm_gpu_devcoredump_read(char *buffer, loff_t offset,
 		size_t count, void *data, size_t datalen)
@@ -326,7 +349,9 @@ static void msm_gpu_crashstate_get_bo(struct msm_gpu_state *state,
 		if (!state_bo->data)
 			goto out;
 
+		msm_gem_lock(&obj->base);
 		ptr = msm_gem_get_vaddr_active(&obj->base);
+		msm_gem_unlock(&obj->base);
 		if (IS_ERR(ptr)) {
 			kvfree(state_bo->data);
 			state_bo->data = NULL;
@@ -411,37 +436,26 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
  * Hangcheck detection for locked gpu:
  */
 
-static void update_fences(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
-		uint32_t fence)
-{
-	struct msm_gem_submit *submit;
-
-	list_for_each_entry(submit, &ring->submits, node) {
-		if (submit->seqno > fence)
-			break;
-
-		msm_update_fence(submit->ring->fctx,
-			submit->fence->seqno);
-	}
-}
-
 static struct msm_gem_submit *
 find_submit(struct msm_ringbuffer *ring, uint32_t fence)
 {
 	struct msm_gem_submit *submit;
 
-	WARN_ON(!mutex_is_locked(&ring->gpu->dev->struct_mutex));
-
-	list_for_each_entry(submit, &ring->submits, node)
-		if (submit->seqno == fence)
+	spin_lock(&ring->submit_lock);
+	list_for_each_entry(submit, &ring->submits, node) {
+		if (submit->seqno == fence) {
+			spin_unlock(&ring->submit_lock);
 			return submit;
+		}
+	}
+	spin_unlock(&ring->submit_lock);
 
 	return NULL;
 }
 
 static void retire_submits(struct msm_gpu *gpu);
 
-static void recover_worker(struct work_struct *work)
+static void recover_worker(struct kthread_work *work)
 {
 	struct msm_gpu *gpu = container_of(work, struct msm_gpu, recover_work);
 	struct drm_device *dev = gpu->dev;
@@ -470,14 +484,22 @@ static void recover_worker(struct work_struct *work)
 			put_task_struct(task);
 		}
 
+		/* msm_rd_dump_submit() needs bo locked to dump: */
+		for (i = 0; i < submit->nr_bos; i++)
+			msm_gem_lock(&submit->bos[i].obj->base);
+
 		if (comm && cmd) {
 			DRM_DEV_ERROR(dev->dev, "%s: offending task: %s (%s)\n",
 				gpu->name, comm, cmd);
 
 			msm_rd_dump_submit(priv->hangrd, submit,
 				"offending task: %s (%s)", comm, cmd);
-		} else
+		} else {
 			msm_rd_dump_submit(priv->hangrd, submit, NULL);
+		}
+
+		for (i = 0; i < submit->nr_bos; i++)
+			msm_gem_unlock(&submit->bos[i].obj->base);
 	}
 
 	/* Record the crash state */
@@ -523,8 +545,10 @@ static void recover_worker(struct work_struct *work)
 		for (i = 0; i < gpu->nr_rings; i++) {
 			struct msm_ringbuffer *ring = gpu->rb[i];
 
+			spin_lock(&ring->submit_lock);
 			list_for_each_entry(submit, &ring->submits, node)
 				gpu->funcs->submit(gpu, submit);
+			spin_unlock(&ring->submit_lock);
 		}
 	}
 
@@ -535,7 +559,6 @@ static void recover_worker(struct work_struct *work)
 
 static void hangcheck_timer_reset(struct msm_gpu *gpu)
 {
-	DBG("%s", gpu->name);
 	mod_timer(&gpu->hangcheck_timer,
 			round_jiffies_up(jiffies + DRM_MSM_HANGCHECK_JIFFIES));
 }
@@ -544,7 +567,6 @@ static void hangcheck_handler(struct timer_list *t)
 {
 	struct msm_gpu *gpu = from_timer(gpu, t, hangcheck_timer);
 	struct drm_device *dev = gpu->dev;
-	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_ringbuffer *ring = gpu->funcs->active_ring(gpu);
 	uint32_t fence = ring->memptrs->fence;
 
@@ -561,7 +583,7 @@ static void hangcheck_handler(struct timer_list *t)
 		DRM_DEV_ERROR(dev->dev, "%s:     submitted fence: %u\n",
 				gpu->name, ring->seqno);
 
-		queue_work(priv->wq, &gpu->recover_work);
+		kthread_queue_work(gpu->worker, &gpu->recover_work);
 	}
 
 	/* if still more pending work, reset the hangcheck timer: */
@@ -569,7 +591,7 @@ static void hangcheck_handler(struct timer_list *t)
 		hangcheck_timer_reset(gpu);
 
 	/* workaround for missing irq: */
-	queue_work(priv->wq, &gpu->retire_work);
+	kthread_queue_work(gpu->worker, &gpu->retire_work);
 }
 
 /*
@@ -697,56 +719,70 @@ static void retire_submit(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 		stats->alwayson_start, stats->alwayson_end);
 
 	for (i = 0; i < submit->nr_bos; i++) {
-		struct msm_gem_object *msm_obj = submit->bos[i].obj;
+		struct drm_gem_object *obj = &submit->bos[i].obj->base;
 
-		msm_gem_active_put(&msm_obj->base);
-		msm_gem_unpin_iova(&msm_obj->base, submit->aspace);
-		drm_gem_object_put_locked(&msm_obj->base);
+		msm_gem_lock(obj);
+		msm_gem_active_put(obj);
+		msm_gem_unpin_iova_locked(obj, submit->aspace);
+		msm_gem_unlock(obj);
+		drm_gem_object_put(obj);
 	}
 
 	pm_runtime_mark_last_busy(&gpu->pdev->dev);
 	pm_runtime_put_autosuspend(&gpu->pdev->dev);
-	msm_gem_submit_free(submit);
+
+	spin_lock(&ring->submit_lock);
+	list_del(&submit->node);
+	spin_unlock(&ring->submit_lock);
+
+	msm_gem_submit_put(submit);
 }
 
 static void retire_submits(struct msm_gpu *gpu)
 {
-	struct drm_device *dev = gpu->dev;
-	struct msm_gem_submit *submit, *tmp;
 	int i;
 
-	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
-
 	/* Retire the commits starting with highest priority */
 	for (i = 0; i < gpu->nr_rings; i++) {
 		struct msm_ringbuffer *ring = gpu->rb[i];
 
-		list_for_each_entry_safe(submit, tmp, &ring->submits, node) {
-			if (dma_fence_is_signaled(submit->fence))
+		while (true) {
+			struct msm_gem_submit *submit = NULL;
+
+			spin_lock(&ring->submit_lock);
+			submit = list_first_entry_or_null(&ring->submits,
+					struct msm_gem_submit, node);
+			spin_unlock(&ring->submit_lock);
+
+			/*
+			 * If no submit, we are done.  If submit->fence hasn't
+			 * been signalled, then later submits are not signalled
+			 * either, so we are also done.
+			 */
+			if (submit && dma_fence_is_signaled(submit->fence)) {
 				retire_submit(gpu, ring, submit);
+			} else {
+				break;
+			}
 		}
 	}
 }
 
-static void retire_worker(struct work_struct *work)
+static void retire_worker(struct kthread_work *work)
 {
 	struct msm_gpu *gpu = container_of(work, struct msm_gpu, retire_work);
-	struct drm_device *dev = gpu->dev;
 	int i;
 
 	for (i = 0; i < gpu->nr_rings; i++)
 		update_fences(gpu, gpu->rb[i], gpu->rb[i]->memptrs->fence);
 
-	mutex_lock(&dev->struct_mutex);
 	retire_submits(gpu);
-	mutex_unlock(&dev->struct_mutex);
 }
 
 /* call from irq handler to schedule work to retire bo's */
 void msm_gpu_retire(struct msm_gpu *gpu)
 {
-	struct msm_drm_private *priv = gpu->dev->dev_private;
-	queue_work(priv->wq, &gpu->retire_work);
+	kthread_queue_work(gpu->worker, &gpu->retire_work);
 	update_sw_cntrs(gpu);
 }
 
@@ -766,8 +802,6 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 
 	submit->seqno = ++ring->seqno;
 
-	list_add_tail(&submit->node, &ring->submits);
-
 	msm_rd_dump_submit(priv->rd, submit, NULL);
 
 	update_sw_cntrs(gpu);
@@ -777,14 +811,9 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 		struct drm_gem_object *drm_obj = &msm_obj->base;
 		uint64_t iova;
 
-		/* can't happen yet.. but when we add 2d support we'll have
-		 * to deal w/ cross-ring synchronization:
-		 */
-		WARN_ON(is_active(msm_obj) && (msm_obj->gpu != gpu));
-
 		/* submit takes a reference to the bo and iova until retired: */
 		drm_gem_object_get(&msm_obj->base);
-		msm_gem_get_and_pin_iova(&msm_obj->base, submit->aspace, &iova);
+		msm_gem_get_and_pin_iova_locked(&msm_obj->base, submit->aspace, &iova);
 
 		if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE)
 			dma_resv_add_excl_fence(drm_obj->resv, submit->fence);
@@ -794,6 +823,16 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 		msm_gem_active_get(drm_obj, gpu);
 	}
 
+	/*
+	 * ring->submits holds a ref to the submit, to deal with the case
+	 * that a submit completes before msm_ioctl_gem_submit() returns.
+	 */
+	msm_gem_submit_get(submit);
+
+	spin_lock(&ring->submit_lock);
+	list_add_tail(&submit->node, &ring->submits);
+	spin_unlock(&ring->submit_lock);
+
 	gpu->funcs->submit(gpu, submit);
 	priv->lastctx = submit->queue->ctx;
 
@@ -869,10 +908,18 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	gpu->funcs = funcs;
 	gpu->name = name;
 
-	INIT_LIST_HEAD(&gpu->active_list);
-	INIT_WORK(&gpu->retire_work, retire_worker);
-	INIT_WORK(&gpu->recover_work, recover_worker);
+	gpu->worker = kthread_create_worker(0, "%s-worker", gpu->name);
+	if (IS_ERR(gpu->worker)) {
+		ret = PTR_ERR(gpu->worker);
+		gpu->worker = NULL;
+		goto fail;
+	}
 
+	sched_set_fifo_low(gpu->worker->task);
+
+	INIT_LIST_HEAD(&gpu->active_list);
+	kthread_init_work(&gpu->retire_work, retire_worker);
+	kthread_init_work(&gpu->recover_work, recover_worker);
 
 	timer_setup(&gpu->hangcheck_timer, hangcheck_handler, 0);
 
@@ -1005,4 +1052,10 @@ void msm_gpu_cleanup(struct msm_gpu *gpu)
 		gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu);
 		msm_gem_address_space_put(gpu->aspace);
 	}
+
+	if (gpu->worker) {
+		kthread_destroy_worker(gpu->worker);
+	}
+
+	devfreq_cooling_unregister(gpu->cooling);
 }