Merge tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This seems to have been a comparatively quieter merge window, I assume
  due to holidays etc. The "biggest" change is AMD header cleanups, which
  merge/remove a bunch of them. The AMD gpu scheduler is now being made generic
  with the etnaviv driver wanting to reuse the code, hopefully other drivers
  can go in the same direction.

  Otherwise it's the usual lots of stuff in i915/amdgpu, not so much stuff
  elsewhere.

  Core:
   - Add .last_close and .output_poll_changed helpers to reduce driver footprints
   - Fix plane clipping
   - Improved debug printing support
   - Add panel orientation property
   - Update edid derived properties at edid setting
   - Reduction in fbdev driver footprint
   - Move amdgpu scheduler into core for other drivers to use.

  i915:
   - Selftest and IGT improvements
   - Fast boot prep work on IPS, pipe config
   - HW workarounds for Cannonlake, Geminilake
   - Cannonlake clock and HDMI2.0 fixes
   - GPU cache invalidation and context switch improvements
   - Display planes cleanup
   - New PMU interface for perf queries
   - New firmware support for KBL/SKL
   - Geminilake HW workaround for perforamce
   - Coffeelake stolen memory improvements
   - GPU reset robustness work
   - Cannonlake horizontal plane flipping
   - GVT work

  amdgpu/radeon:
   - RV and Vega header file cleanups (lots of lines gone!)
   - TTM operation context support
   - 48-bit GPUVM support for Vega/RV
   - ECC support for Vega
   - Resizeable BAR support
   - Multi-display sync support
   - Enable swapout for reserved BOs during allocation
   - S3 fixes on Raven
   - GPU reset cleanup and fixes
   - 2+1 level GPU page table

  amdkfd:
   - GFX7/8 SDMA user queues support
   - Hardware scheduling for multiple processes
   - dGPU prep work

  rcar:
   - Added R8A7743/5 support
   - System suspend/resume support

  sun4i:
   - Multi-plane support for YUV formats
   - A83T and LVDS support

  msm:
   - Devfreq support for GPU

  tegra:
   - Prep work for adding Tegra186 support
   - Tegra186 HDMI support
   - HDMI2.0 and zpos support by using generic helpers

  tilcdc:
   - Misc fixes

  omapdrm:
   - Support memory bandwidth limits
   - DSI command mode panel cleanups
   - DMM error handling

  exynos:
   - drop the old IPP subdriver.

  etnaviv:
   - Occlusion query fixes
   - Job handling fixes
   - Prep work for hooking in gpu scheduler

  armada:
   - Move closer to atomic modesetting
   - Allow disabling primary plane if overlay is full screen

  imx:
   - Format modifier support
   - Add tile prefetch to PRE
   - Runtime PM support for PRG

  ast:
   - fix LUT loading"

* tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux: (1471 commits)
  drm/ast: Load lut in crtc_commit
  drm: Check for lessee in DROP_MASTER ioctl
  drm: fix gpu scheduler link order
  drm/amd/display: Demote error print to debug print when ATOM impl missing
  dma-buf: fix reservation_object_wait_timeout_rcu once more v2
  drm/amdgpu: Avoid leaking PM domain on driver unbind (v2)
  drm/amd/amdgpu: Add Polaris version check
  drm/amdgpu: Reenable manual GPU reset from sysfs
  drm/amdgpu: disable MMHUB power gating on raven
  drm/ttm: Don't unreserve swapped BOs that were previously reserved
  drm/ttm: Don't add swapped BOs to swap-LRU list
  drm/amdgpu: only check for ECC on Vega10
  drm/amd/powerplay: Fix smu_table_entry.handle type
  drm/ttm: add VADDR_FLAG_UPDATED_COUNT to correctly update dma_page global count
  drm: Fix PANEL_ORIENTATION_QUIRKS breaking the Kconfig DRM menuconfig
  drm/radeon: fill in rb backend map on evergreen/ni.
  drm/amdgpu/gfx9: fix ngg enablement to clear gds reserved memory (v2)
  drm/ttm: only free pages rather than update global memory count together
  drm/amdgpu: fix CPU based VM updates
  drm/amdgpu: fix typo in amdgpu_vce_validate_bo
  ...

1 files changed, 255 insertions, 76 deletions

diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 71ce06680d66..d1f91a533afa 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -114,14 +114,6 @@ static int emit_recurse_batch(struct hang *h,
 	if (err)
 		goto unpin_vma;
 
-	err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
-	if (err)
-		goto unpin_hws;
-
-	err = i915_switch_context(rq);
-	if (err)
-		goto unpin_hws;
-
 	i915_vma_move_to_active(vma, rq, 0);
 	if (!i915_gem_object_has_active_reference(vma->obj)) {
 		i915_gem_object_get(vma->obj);
@@ -140,6 +132,12 @@ static int emit_recurse_batch(struct hang *h,
 		*batch++ = lower_32_bits(hws_address(hws, rq));
 		*batch++ = upper_32_bits(hws_address(hws, rq));
 		*batch++ = rq->fence.seqno;
+		*batch++ = MI_ARB_CHECK;
+
+		memset(batch, 0, 1024);
+		batch += 1024 / sizeof(*batch);
+
+		*batch++ = MI_ARB_CHECK;
 		*batch++ = MI_BATCH_BUFFER_START | 1 << 8 | 1;
 		*batch++ = lower_32_bits(vma->node.start);
 		*batch++ = upper_32_bits(vma->node.start);
@@ -148,6 +146,12 @@ static int emit_recurse_batch(struct hang *h,
 		*batch++ = 0;
 		*batch++ = lower_32_bits(hws_address(hws, rq));
 		*batch++ = rq->fence.seqno;
+		*batch++ = MI_ARB_CHECK;
+
+		memset(batch, 0, 1024);
+		batch += 1024 / sizeof(*batch);
+
+		*batch++ = MI_ARB_CHECK;
 		*batch++ = MI_BATCH_BUFFER_START | 1 << 8;
 		*batch++ = lower_32_bits(vma->node.start);
 	} else if (INTEL_GEN(i915) >= 4) {
@@ -155,12 +159,24 @@ static int emit_recurse_batch(struct hang *h,
 		*batch++ = 0;
 		*batch++ = lower_32_bits(hws_address(hws, rq));
 		*batch++ = rq->fence.seqno;
+		*batch++ = MI_ARB_CHECK;
+
+		memset(batch, 0, 1024);
+		batch += 1024 / sizeof(*batch);
+
+		*batch++ = MI_ARB_CHECK;
 		*batch++ = MI_BATCH_BUFFER_START | 2 << 6;
 		*batch++ = lower_32_bits(vma->node.start);
 	} else {
 		*batch++ = MI_STORE_DWORD_IMM;
 		*batch++ = lower_32_bits(hws_address(hws, rq));
 		*batch++ = rq->fence.seqno;
+		*batch++ = MI_ARB_CHECK;
+
+		memset(batch, 0, 1024);
+		batch += 1024 / sizeof(*batch);
+
+		*batch++ = MI_ARB_CHECK;
 		*batch++ = MI_BATCH_BUFFER_START | 2 << 6 | 1;
 		*batch++ = lower_32_bits(vma->node.start);
 	}
@@ -173,7 +189,6 @@ static int emit_recurse_batch(struct hang *h,
 
 	err = rq->engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, flags);
 
-unpin_hws:
 	i915_vma_unpin(hws);
 unpin_vma:
 	i915_vma_unpin(vma);
@@ -243,6 +258,16 @@ static void hang_fini(struct hang *h)
 	i915_gem_wait_for_idle(h->i915, I915_WAIT_LOCKED);
 }
 
+static bool wait_for_hang(struct hang *h, struct drm_i915_gem_request *rq)
+{
+	return !(wait_for_us(i915_seqno_passed(hws_seqno(h, rq),
+					       rq->fence.seqno),
+			     10) &&
+		 wait_for(i915_seqno_passed(hws_seqno(h, rq),
+					    rq->fence.seqno),
+			  1000));
+}
+
 static int igt_hang_sanitycheck(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
@@ -305,6 +330,9 @@ static void global_reset_lock(struct drm_i915_private *i915)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
+	pr_debug("%s: current gpu_error=%08lx\n",
+		 __func__, i915->gpu_error.flags);
+
 	while (test_and_set_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags))
 		wait_event(i915->gpu_error.reset_queue,
 			   !test_bit(I915_RESET_BACKOFF,
@@ -362,54 +390,128 @@ static int igt_global_reset(void *arg)
 	return err;
 }
 
-static int igt_reset_engine(void *arg)
+static int __igt_reset_engine(struct drm_i915_private *i915, bool active)
 {
-	struct drm_i915_private *i915 = arg;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	unsigned int reset_count, reset_engine_count;
+	struct hang h;
 	int err = 0;
 
-	/* Check that we can issue a global GPU and engine reset */
+	/* Check that we can issue an engine reset on an idle engine (no-op) */
 
 	if (!intel_has_reset_engine(i915))
 		return 0;
 
+	if (active) {
+		mutex_lock(&i915->drm.struct_mutex);
+		err = hang_init(&h, i915);
+		mutex_unlock(&i915->drm.struct_mutex);
+		if (err)
+			return err;
+	}
+
 	for_each_engine(engine, i915, id) {
-		set_bit(I915_RESET_ENGINE + engine->id, &i915->gpu_error.flags);
+		unsigned int reset_count, reset_engine_count;
+		IGT_TIMEOUT(end_time);
+
+		if (active && !intel_engine_can_store_dword(engine))
+			continue;
+
 		reset_count = i915_reset_count(&i915->gpu_error);
 		reset_engine_count = i915_reset_engine_count(&i915->gpu_error,
 							     engine);
 
-		err = i915_reset_engine(engine, I915_RESET_QUIET);
-		if (err) {
-			pr_err("i915_reset_engine failed\n");
-			break;
-		}
+		set_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+		do {
+			if (active) {
+				struct drm_i915_gem_request *rq;
+
+				mutex_lock(&i915->drm.struct_mutex);
+				rq = hang_create_request(&h, engine,
+							 i915->kernel_context);
+				if (IS_ERR(rq)) {
+					err = PTR_ERR(rq);
+					mutex_unlock(&i915->drm.struct_mutex);
+					break;
+				}
+
+				i915_gem_request_get(rq);
+				__i915_add_request(rq, true);
+				mutex_unlock(&i915->drm.struct_mutex);
+
+				if (!wait_for_hang(&h, rq)) {
+					struct drm_printer p = drm_info_printer(i915->drm.dev);
+
+					pr_err("%s: Failed to start request %x, at %x\n",
+					       __func__, rq->fence.seqno, hws_seqno(&h, rq));
+					intel_engine_dump(engine, &p,
+							  "%s\n", engine->name);
+
+					i915_gem_request_put(rq);
+					err = -EIO;
+					break;
+				}
 
-		if (i915_reset_count(&i915->gpu_error) != reset_count) {
-			pr_err("Full GPU reset recorded! (engine reset expected)\n");
-			err = -EINVAL;
-			break;
-		}
+				i915_gem_request_put(rq);
+			}
+
+			engine->hangcheck.stalled = true;
+			engine->hangcheck.seqno =
+				intel_engine_get_seqno(engine);
+
+			err = i915_reset_engine(engine, I915_RESET_QUIET);
+			if (err) {
+				pr_err("i915_reset_engine failed\n");
+				break;
+			}
+
+			if (i915_reset_count(&i915->gpu_error) != reset_count) {
+				pr_err("Full GPU reset recorded! (engine reset expected)\n");
+				err = -EINVAL;
+				break;
+			}
+
+			reset_engine_count += active;
+			if (i915_reset_engine_count(&i915->gpu_error, engine) !=
+			    reset_engine_count) {
+				pr_err("%s engine reset %srecorded!\n",
+				       engine->name, active ? "not " : "");
+				err = -EINVAL;
+				break;
+			}
+
+			engine->hangcheck.stalled = false;
+		} while (time_before(jiffies, end_time));
+		clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
 
-		if (i915_reset_engine_count(&i915->gpu_error, engine) ==
-		    reset_engine_count) {
-			pr_err("No %s engine reset recorded!\n", engine->name);
-			err = -EINVAL;
+		if (err)
 			break;
-		}
 
-		clear_bit(I915_RESET_ENGINE + engine->id,
-			  &i915->gpu_error.flags);
+		cond_resched();
 	}
 
 	if (i915_terminally_wedged(&i915->gpu_error))
 		err = -EIO;
 
+	if (active) {
+		mutex_lock(&i915->drm.struct_mutex);
+		hang_fini(&h);
+		mutex_unlock(&i915->drm.struct_mutex);
+	}
+
 	return err;
 }
 
+static int igt_reset_idle_engine(void *arg)
+{
+	return __igt_reset_engine(arg, false);
+}
+
+static int igt_reset_active_engine(void *arg)
+{
+	return __igt_reset_engine(arg, true);
+}
+
 static int active_engine(void *data)
 {
 	struct intel_engine_cs *engine = data;
@@ -471,11 +573,12 @@ err_file:
 	return err;
 }
 
-static int igt_reset_active_engines(void *arg)
+static int __igt_reset_engine_others(struct drm_i915_private *i915,
+				     bool active)
 {
-	struct drm_i915_private *i915 = arg;
-	struct intel_engine_cs *engine, *active;
+	struct intel_engine_cs *engine, *other;
 	enum intel_engine_id id, tmp;
+	struct hang h;
 	int err = 0;
 
 	/* Check that issuing a reset on one engine does not interfere
@@ -485,24 +588,36 @@ static int igt_reset_active_engines(void *arg)
 	if (!intel_has_reset_engine(i915))
 		return 0;
 
+	if (active) {
+		mutex_lock(&i915->drm.struct_mutex);
+		err = hang_init(&h, i915);
+		mutex_unlock(&i915->drm.struct_mutex);
+		if (err)
+			return err;
+	}
+
 	for_each_engine(engine, i915, id) {
-		struct task_struct *threads[I915_NUM_ENGINES];
+		struct task_struct *threads[I915_NUM_ENGINES] = {};
 		unsigned long resets[I915_NUM_ENGINES];
 		unsigned long global = i915_reset_count(&i915->gpu_error);
+		unsigned long count = 0;
 		IGT_TIMEOUT(end_time);
 
+		if (active && !intel_engine_can_store_dword(engine))
+			continue;
+
 		memset(threads, 0, sizeof(threads));
-		for_each_engine(active, i915, tmp) {
+		for_each_engine(other, i915, tmp) {
 			struct task_struct *tsk;
 
-			if (active == engine)
-				continue;
-
 			resets[tmp] = i915_reset_engine_count(&i915->gpu_error,
-							      active);
+							      other);
+
+			if (other == engine)
+				continue;
 
-			tsk = kthread_run(active_engine, active,
-					  "igt/%s", active->name);
+			tsk = kthread_run(active_engine, other,
+					  "igt/%s", other->name);
 			if (IS_ERR(tsk)) {
 				err = PTR_ERR(tsk);
 				goto unwind;
@@ -512,20 +627,70 @@ static int igt_reset_active_engines(void *arg)
 			get_task_struct(tsk);
 		}
 
-		set_bit(I915_RESET_ENGINE + engine->id, &i915->gpu_error.flags);
+		set_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
 		do {
+			if (active) {
+				struct drm_i915_gem_request *rq;
+
+				mutex_lock(&i915->drm.struct_mutex);
+				rq = hang_create_request(&h, engine,
+							 i915->kernel_context);
+				if (IS_ERR(rq)) {
+					err = PTR_ERR(rq);
+					mutex_unlock(&i915->drm.struct_mutex);
+					break;
+				}
+
+				i915_gem_request_get(rq);
+				__i915_add_request(rq, true);
+				mutex_unlock(&i915->drm.struct_mutex);
+
+				if (!wait_for_hang(&h, rq)) {
+					struct drm_printer p = drm_info_printer(i915->drm.dev);
+
+					pr_err("%s: Failed to start request %x, at %x\n",
+					       __func__, rq->fence.seqno, hws_seqno(&h, rq));
+					intel_engine_dump(engine, &p,
+							  "%s\n", engine->name);
+
+					i915_gem_request_put(rq);
+					err = -EIO;
+					break;
+				}
+
+				i915_gem_request_put(rq);
+			}
+
+			engine->hangcheck.stalled = true;
+			engine->hangcheck.seqno =
+				intel_engine_get_seqno(engine);
+
 			err = i915_reset_engine(engine, I915_RESET_QUIET);
 			if (err) {
-				pr_err("i915_reset_engine(%s) failed, err=%d\n",
-				       engine->name, err);
+				pr_err("i915_reset_engine(%s:%s) failed, err=%d\n",
+				       engine->name, active ? "active" : "idle", err);
 				break;
 			}
+
+			engine->hangcheck.stalled = false;
+			count++;
 		} while (time_before(jiffies, end_time));
-		clear_bit(I915_RESET_ENGINE + engine->id,
-			  &i915->gpu_error.flags);
+		clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+		pr_info("i915_reset_engine(%s:%s): %lu resets\n",
+			engine->name, active ? "active" : "idle", count);
+
+		if (i915_reset_engine_count(&i915->gpu_error, engine) -
+		    resets[engine->id] != (active ? count : 0)) {
+			pr_err("i915_reset_engine(%s:%s): reset %lu times, but reported %lu\n",
+			       engine->name, active ? "active" : "idle", count,
+			       i915_reset_engine_count(&i915->gpu_error,
+						       engine) - resets[engine->id]);
+			if (!err)
+				err = -EINVAL;
+		}
 
 unwind:
-		for_each_engine(active, i915, tmp) {
+		for_each_engine(other, i915, tmp) {
 			int ret;
 
 			if (!threads[tmp])
@@ -533,27 +698,29 @@ unwind:
 
 			ret = kthread_stop(threads[tmp]);
 			if (ret) {
-				pr_err("kthread for active engine %s failed, err=%d\n",
-				       active->name, ret);
+				pr_err("kthread for other engine %s failed, err=%d\n",
+				       other->name, ret);
 				if (!err)
 					err = ret;
 			}
 			put_task_struct(threads[tmp]);
 
 			if (resets[tmp] != i915_reset_engine_count(&i915->gpu_error,
-								   active)) {
+								   other)) {
 				pr_err("Innocent engine %s was reset (count=%ld)\n",
-				       active->name,
+				       other->name,
 				       i915_reset_engine_count(&i915->gpu_error,
-							       active) - resets[tmp]);
-				err = -EIO;
+							       other) - resets[tmp]);
+				if (!err)
+					err = -EINVAL;
 			}
 		}
 
 		if (global != i915_reset_count(&i915->gpu_error)) {
 			pr_err("Global reset (count=%ld)!\n",
 			       i915_reset_count(&i915->gpu_error) - global);
-			err = -EIO;
+			if (!err)
+				err = -EINVAL;
 		}
 
 		if (err)
@@ -565,9 +732,25 @@ unwind:
 	if (i915_terminally_wedged(&i915->gpu_error))
 		err = -EIO;
 
+	if (active) {
+		mutex_lock(&i915->drm.struct_mutex);
+		hang_fini(&h);
+		mutex_unlock(&i915->drm.struct_mutex);
+	}
+
 	return err;
 }
 
+static int igt_reset_idle_engine_others(void *arg)
+{
+	return __igt_reset_engine_others(arg, false);
+}
+
+static int igt_reset_active_engine_others(void *arg)
+{
+	return __igt_reset_engine_others(arg, true);
+}
+
 static u32 fake_hangcheck(struct drm_i915_gem_request *rq)
 {
 	u32 reset_count;
@@ -583,16 +766,6 @@ static u32 fake_hangcheck(struct drm_i915_gem_request *rq)
 	return reset_count;
 }
 
-static bool wait_for_hang(struct hang *h, struct drm_i915_gem_request *rq)
-{
-	return !(wait_for_us(i915_seqno_passed(hws_seqno(h, rq),
-					       rq->fence.seqno),
-			     10) &&
-		 wait_for(i915_seqno_passed(hws_seqno(h, rq),
-					    rq->fence.seqno),
-			  1000));
-}
-
 static int igt_wait_reset(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
@@ -626,9 +799,9 @@ static int igt_wait_reset(void *arg)
 	if (!wait_for_hang(&h, rq)) {
 		struct drm_printer p = drm_info_printer(i915->drm.dev);
 
-		pr_err("Failed to start request %x, at %x\n",
-		       rq->fence.seqno, hws_seqno(&h, rq));
-		intel_engine_dump(rq->engine, &p);
+		pr_err("%s: Failed to start request %x, at %x\n",
+		       __func__, rq->fence.seqno, hws_seqno(&h, rq));
+		intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name);
 
 		i915_reset(i915, 0);
 		i915_gem_set_wedged(i915);
@@ -721,9 +894,10 @@ static int igt_reset_queue(void *arg)
 			if (!wait_for_hang(&h, prev)) {
 				struct drm_printer p = drm_info_printer(i915->drm.dev);
 
-				pr_err("Failed to start request %x, at %x\n",
-				       prev->fence.seqno, hws_seqno(&h, prev));
-				intel_engine_dump(rq->engine, &p);
+				pr_err("%s: Failed to start request %x, at %x\n",
+				       __func__, prev->fence.seqno, hws_seqno(&h, prev));
+				intel_engine_dump(prev->engine, &p,
+						  "%s\n", prev->engine->name);
 
 				i915_gem_request_put(rq);
 				i915_gem_request_put(prev);
@@ -827,9 +1001,9 @@ static int igt_handle_error(void *arg)
 	if (!wait_for_hang(&h, rq)) {
 		struct drm_printer p = drm_info_printer(i915->drm.dev);
 
-		pr_err("Failed to start request %x, at %x\n",
-		       rq->fence.seqno, hws_seqno(&h, rq));
-		intel_engine_dump(rq->engine, &p);
+		pr_err("%s: Failed to start request %x, at %x\n",
+		       __func__, rq->fence.seqno, hws_seqno(&h, rq));
+		intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name);
 
 		i915_reset(i915, 0);
 		i915_gem_set_wedged(i915);
@@ -872,21 +1046,26 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_global_reset), /* attempt to recover GPU first */
 		SUBTEST(igt_hang_sanitycheck),
-		SUBTEST(igt_reset_engine),
-		SUBTEST(igt_reset_active_engines),
+		SUBTEST(igt_reset_idle_engine),
+		SUBTEST(igt_reset_active_engine),
+		SUBTEST(igt_reset_idle_engine_others),
+		SUBTEST(igt_reset_active_engine_others),
 		SUBTEST(igt_wait_reset),
 		SUBTEST(igt_reset_queue),
 		SUBTEST(igt_handle_error),
 	};
+	bool saved_hangcheck;
 	int err;
 
 	if (!intel_has_gpu_reset(i915))
 		return 0;
 
 	intel_runtime_pm_get(i915);
+	saved_hangcheck = fetch_and_zero(&i915_modparams.enable_hangcheck);
 
 	err = i915_subtests(tests, i915);
 
+	i915_modparams.enable_hangcheck = saved_hangcheck;
 	intel_runtime_pm_put(i915);
 
 	return err;