Merge drm/drm-next into drm-misc-next

Jernej needs some patches that got merged in -rc5.

Signed-off-by: Maxime Ripard <maxime@cerno.tech>

8 files changed, 92 insertions, 49 deletions

diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index ef7c74cff28a..43912e9b683d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -570,7 +570,7 @@ static bool assert_mmap_offset(struct drm_i915_private *i915,
 
 	obj = i915_gem_object_create_internal(i915, size);
 	if (IS_ERR(obj))
-		return PTR_ERR(obj);
+		return false;
 
 	mmo = mmap_offset_attach(obj, I915_MMAP_OFFSET_GTT, NULL);
 	i915_gem_object_put(obj);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index 8a5054f21bf8..24c99d0838af 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -147,24 +147,32 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 
 			fence = i915_active_fence_get(&tl->last_request);
 			if (fence) {
+				mutex_unlock(&tl->mutex);
+
 				timeout = dma_fence_wait_timeout(fence,
 								 interruptible,
 								 timeout);
 				dma_fence_put(fence);
+
+				/* Retirement is best effort */
+				if (!mutex_trylock(&tl->mutex)) {
+					active_count++;
+					goto out_active;
+				}
 			}
 		}
 
 		if (!retire_requests(tl) || flush_submission(gt))
 			active_count++;
+		mutex_unlock(&tl->mutex);
 
-		spin_lock(&timelines->lock);
+out_active:	spin_lock(&timelines->lock);
 
-		/* Resume iteration after dropping lock */
+		/* Resume list iteration after reacquiring spinlock */
 		list_safe_reset_next(tl, tn, link);
 		if (atomic_dec_and_test(&tl->active_count))
 			list_del(&tl->link);
 
-		mutex_unlock(&tl->mutex);
 
 		/* Defer the final release to after the spinlock */
 		if (refcount_dec_and_test(&tl->kref.refcount)) {
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 887e0dc701f7..06cef3c18f26 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -580,24 +580,19 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 				     struct i915_wa_list *wal)
 {
-	u32 val;
-
 	/* Wa_1409142259:tgl */
 	WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
 			  GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
 
-	/* Wa_1604555607:tgl */
-	val = intel_uncore_read(engine->uncore, FF_MODE2);
-	val &= ~FF_MODE2_TDS_TIMER_MASK;
-	val |= FF_MODE2_TDS_TIMER_128;
 	/*
-	 * FIXME: FF_MODE2 register is not readable till TGL B0. We can
-	 * enable verification of WA from the later steppings, which enables
-	 * the read of FF_MODE2.
+	 * Wa_1604555607:gen12 and Wa_1608008084:gen12
+	 * FF_MODE2 register will return the wrong value when read. The default
+	 * value for this register is zero for all fields and there are no bit
+	 * masks. So instead of doing a RMW we should just write the TDS timer
+	 * value for Wa_1604555607.
 	 */
-	wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK, val,
-	       IS_TGL_REVID(engine->i915, TGL_REVID_A0, TGL_REVID_A0) ? 0 :
-			    FF_MODE2_TDS_TIMER_MASK);
+	wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK,
+	       FF_MODE2_TDS_TIMER_128, 0);
 }
 
 static void
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 2477a1e5a166..ae139f0877ae 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -151,12 +151,12 @@ static void dmabuf_gem_object_free(struct kref *kref)
 			dmabuf_obj = container_of(pos,
 					struct intel_vgpu_dmabuf_obj, list);
 			if (dmabuf_obj == obj) {
+				list_del(pos);
 				intel_gvt_hypervisor_put_vfio_device(vgpu);
 				idr_remove(&vgpu->object_idr,
 					   dmabuf_obj->dmabuf_id);
 				kfree(dmabuf_obj->info);
 				kfree(dmabuf_obj);
-				list_del(pos);
 				break;
 			}
 		}
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 85bd9bf4f6ee..487af6ea9972 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -560,9 +560,9 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
 
 		intel_vgpu_reset_mmio(vgpu, dmlr);
 		populate_pvinfo_page(vgpu);
-		intel_vgpu_reset_display(vgpu);
 
 		if (dmlr) {
+			intel_vgpu_reset_display(vgpu);
 			intel_vgpu_reset_cfg_space(vgpu);
 			/* only reset the failsafe mode when dmlr reset */
 			vgpu->failsafe = false;
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index e34c79df6ebc..79391d92ab7e 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1970,9 +1970,10 @@ out:
 	return i915_vma_get(oa_bo->vma);
 }
 
-static int emit_oa_config(struct i915_perf_stream *stream,
-			  struct i915_oa_config *oa_config,
-			  struct intel_context *ce)
+static struct i915_request *
+emit_oa_config(struct i915_perf_stream *stream,
+	       struct i915_oa_config *oa_config,
+	       struct intel_context *ce)
 {
 	struct i915_request *rq;
 	struct i915_vma *vma;
@@ -1980,7 +1981,7 @@ static int emit_oa_config(struct i915_perf_stream *stream,
 
 	vma = get_oa_vma(stream, oa_config);
 	if (IS_ERR(vma))
-		return PTR_ERR(vma);
+		return ERR_CAST(vma);
 
 	err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
 	if (err)
@@ -2005,13 +2006,17 @@ static int emit_oa_config(struct i915_perf_stream *stream,
 	err = rq->engine->emit_bb_start(rq,
 					vma->node.start, 0,
 					I915_DISPATCH_SECURE);
+	if (err)
+		goto err_add_request;
+
+	i915_request_get(rq);
 err_add_request:
 	i915_request_add(rq);
 err_vma_unpin:
 	i915_vma_unpin(vma);
 err_vma_put:
 	i915_vma_put(vma);
-	return err;
+	return err ? ERR_PTR(err) : rq;
 }
 
 static struct intel_context *oa_context(struct i915_perf_stream *stream)
@@ -2019,7 +2024,8 @@ static struct intel_context *oa_context(struct i915_perf_stream *stream)
 	return stream->pinned_ctx ?: stream->engine->kernel_context;
 }
 
-static int hsw_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+hsw_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 
@@ -2422,7 +2428,8 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream,
 	return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs));
 }
 
-static int gen8_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+gen8_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 	struct i915_oa_config *oa_config = stream->oa_config;
@@ -2464,7 +2471,7 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 	 */
 	ret = lrc_configure_all_contexts(stream, oa_config);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
 	return emit_oa_config(stream, oa_config, oa_context(stream));
 }
@@ -2476,7 +2483,8 @@ static u32 oag_report_ctx_switches(const struct i915_perf_stream *stream)
 			     0 : GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS);
 }
 
-static int gen12_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+gen12_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 	struct i915_oa_config *oa_config = stream->oa_config;
@@ -2507,7 +2515,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 	 */
 	ret = gen12_configure_all_contexts(stream, oa_config);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
 	/*
 	 * For Gen12, performance counters are context
@@ -2517,7 +2525,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 	if (stream->ctx) {
 		ret = gen12_configure_oar_context(stream, true);
 		if (ret)
-			return ret;
+			return ERR_PTR(ret);
 	}
 
 	return emit_oa_config(stream, oa_config, oa_context(stream));
@@ -2715,6 +2723,20 @@ static const struct i915_perf_stream_ops i915_oa_stream_ops = {
 	.read = i915_oa_read,
 };
 
+static int i915_perf_stream_enable_sync(struct i915_perf_stream *stream)
+{
+	struct i915_request *rq;
+
+	rq = stream->perf->ops.enable_metric_set(stream);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT);
+	i915_request_put(rq);
+
+	return 0;
+}
+
 /**
  * i915_oa_stream_init - validate combined props for OA stream and init
  * @stream: An i915 perf stream
@@ -2849,7 +2871,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	stream->ops = &i915_oa_stream_ops;
 	perf->exclusive_stream = stream;
 
-	ret = perf->ops.enable_metric_set(stream);
+	ret = i915_perf_stream_enable_sync(stream);
 	if (ret) {
 		DRM_DEBUG("Unable to enable metric set\n");
 		goto err_enable;
@@ -3167,7 +3189,7 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream,
 		return -EINVAL;
 
 	if (config != stream->oa_config) {
-		int err;
+		struct i915_request *rq;
 
 		/*
 		 * If OA is bound to a specific context, emit the
@@ -3178,11 +3200,13 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream,
 		 * When set globally, we use a low priority kernel context,
 		 * so it will effectively take effect when idle.
 		 */
-		err = emit_oa_config(stream, config, oa_context(stream));
-		if (err == 0)
+		rq = emit_oa_config(stream, config, oa_context(stream));
+		if (!IS_ERR(rq)) {
 			config = xchg(&stream->oa_config, config);
-		else
-			ret = err;
+			i915_request_put(rq);
+		} else {
+			ret = PTR_ERR(rq);
+		}
 	}
 
 	i915_oa_config_put(config);
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index 45e581455f5d..a0e22f00f6cf 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -339,7 +339,8 @@ struct i915_oa_ops {
 	 * counter reports being sampled. May apply system constraints such as
 	 * disabling EU clock gating as required.
 	 */
-	int (*enable_metric_set)(struct i915_perf_stream *stream);
+	struct i915_request *
+		(*enable_metric_set)(struct i915_perf_stream *stream);
 
 	/**
 	 * @disable_metric_set: Remove system constraints associated with using
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index d53af93b919b..e5a55801f753 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -290,7 +290,7 @@ bool i915_request_retire(struct i915_request *rq)
 	spin_unlock_irq(&rq->lock);
 
 	remove_from_client(rq);
-	list_del(&rq->link);
+	list_del_rcu(&rq->link);
 
 	intel_context_exit(rq->context);
 	intel_context_unpin(rq->context);
@@ -736,6 +736,8 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq->infix = rq->ring->emit; /* end of header; start of user payload */
 
 	intel_context_mark_active(ce);
+	list_add_tail_rcu(&rq->link, &tl->requests);
+
 	return rq;
 
 err_unwind:
@@ -792,13 +794,23 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 	GEM_BUG_ON(i915_request_timeline(rq) ==
 		   rcu_access_pointer(signal->timeline));
 
+	if (i915_request_started(signal))
+		return 0;
+
 	fence = NULL;
 	rcu_read_lock();
 	spin_lock_irq(&signal->lock);
-	if (!i915_request_started(signal) &&
-	    !list_is_first(&signal->link,
-			   &rcu_dereference(signal->timeline)->requests)) {
-		struct i915_request *prev = list_prev_entry(signal, link);
+	do {
+		struct list_head *pos = READ_ONCE(signal->link.prev);
+		struct i915_request *prev;
+
+		/* Confirm signal has not been retired, the link is valid */
+		if (unlikely(i915_request_started(signal)))
+			break;
+
+		/* Is signal the earliest request on its timeline? */
+		if (pos == &rcu_dereference(signal->timeline)->requests)
+			break;
 
 		/*
 		 * Peek at the request before us in the timeline. That
@@ -806,13 +818,18 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 		 * after acquiring a reference to it, confirm that it is
 		 * still part of the signaler's timeline.
 		 */
-		if (i915_request_get_rcu(prev)) {
-			if (list_next_entry(prev, link) == signal)
-				fence = &prev->fence;
-			else
-				i915_request_put(prev);
+		prev = list_entry(pos, typeof(*prev), link);
+		if (!i915_request_get_rcu(prev))
+			break;
+
+		/* After the strong barrier, confirm prev is still attached */
+		if (unlikely(READ_ONCE(prev->link.next) != &signal->link)) {
+			i915_request_put(prev);
+			break;
 		}
-	}
+
+		fence = &prev->fence;
+	} while (0);
 	spin_unlock_irq(&signal->lock);
 	rcu_read_unlock();
 	if (!fence)
@@ -1253,8 +1270,6 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 							 0);
 	}
 
-	list_add_tail(&rq->link, &timeline->requests);
-
 	/*
 	 * Make sure that no request gazumped us - if it was allocated after
 	 * our i915_request_alloc() and called __i915_request_add() before