[PATCH 03/63] drm/i915: Defer enabling rc6 til after we submit the first batch/context

Chris Wilson chris at chris-wilson.co.uk
Fri Jun 24 18:09:25 UTC 2016


Some hardware requires a valid render context before it can initiate
rc6 power gating of the GPU; the default state of the GPU is not
sufficient and may lead to undefined behaviour. The first execution of
any batch will load the "golden render state", at which point it is safe
to enable rc6. As we do not forcibly load the kernel context at resume,
we have to hook into the batch submission to be sure that the render
state is setup before enabling rc6.

However, since we don't enable powersaving until that first batch, we
queued a delayed task in order to guarantee that the batch is indeed
submitted.

v2: Rearrange intel_disable_gt_powersave() to match.
v3: Apply user specified cur_freq (or idle_freq if not set).
v4: Give in, and supply a delayed work to autoenable rc6

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at intel.com>
Cc: Ville Syrjälä <ville.syrjala at linux.intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c      |   7 +-
 drivers/gpu/drm/i915/intel_display.c |   3 +-
 drivers/gpu/drm/i915/intel_drv.h     |   2 +
 drivers/gpu/drm/i915/intel_pm.c      | 151 +++++++++++++++++++++--------------
 drivers/gpu/drm/i915/intel_uncore.c  |   2 +-
 5 files changed, 98 insertions(+), 67 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index b98afbd33235..e5f2551a2fd7 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -2021,6 +2021,7 @@ static int i915_drm_resume(struct drm_device *dev)
 
 	intel_opregion_notify_adapter(dev_priv, PCI_D0);
 
+	intel_autoenable_gt_powersave(dev_priv);
 	drm_kms_helper_poll_enable(dev);
 
 	enable_rpm_wakeref_asserts(dev_priv);
@@ -2217,8 +2218,7 @@ int i915_reset(struct drm_i915_private *dev_priv)
 	 * previous concerns that it doesn't respond well to some forms
 	 * of re-init after reset.
 	 */
-	if (INTEL_INFO(dev)->gen > 5)
-		intel_enable_gt_powersave(dev_priv);
+	intel_autoenable_gt_powersave(dev_priv);
 
 	return 0;
 
@@ -2841,7 +2841,6 @@ static int intel_runtime_resume(struct device *device)
 	 * we can do is to hope that things will still work (and disable RPM).
 	 */
 	i915_gem_init_swizzling(dev);
-	gen6_update_ring_freq(dev_priv);
 
 	intel_runtime_pm_enable_interrupts(dev_priv);
 
@@ -2853,7 +2852,7 @@ static int intel_runtime_resume(struct device *device)
 	if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv))
 		intel_hpd_init(dev_priv);
 
-	intel_enable_gt_powersave(dev_priv);
+	intel_autoenable_gt_powersave(dev_priv);
 
 	enable_rpm_wakeref_asserts(dev_priv);
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index c3b5dc8f5e80..699da067bb85 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -10976,6 +10976,7 @@ void intel_mark_busy(struct drm_i915_private *dev_priv)
 		return;
 
 	intel_runtime_pm_get(dev_priv);
+	intel_enable_gt_powersave(dev_priv);
 	i915_update_gfx_val(dev_priv);
 	if (INTEL_GEN(dev_priv) >= 6)
 		gen6_rps_busy(dev_priv);
@@ -15545,7 +15546,6 @@ void intel_modeset_init_hw(struct drm_device *dev)
 	dev_priv->atomic_cdclk_freq = dev_priv->cdclk_freq;
 
 	intel_init_clock_gating(dev);
-	intel_enable_gt_powersave(dev_priv);
 }
 
 /*
@@ -16340,6 +16340,7 @@ void intel_modeset_cleanup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	intel_suspend_gt_powersave(dev_priv);
 	intel_disable_gt_powersave(dev_priv);
 
 	/*
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 3156d8df7921..1f06e7ff5931 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1662,7 +1662,9 @@ void intel_gpu_ips_init(struct drm_i915_private *dev_priv);
 void intel_gpu_ips_teardown(void);
 void intel_init_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv);
+void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_enable_gt_powersave(struct drm_i915_private *dev_priv);
+void intel_autoenable_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_disable_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_suspend_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_reset_gt_powersave(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 78b35b86e80d..4f612b96224e 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -6522,13 +6522,6 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
 		intel_runtime_pm_put(dev_priv);
 }
 
-static void gen6_suspend_rps(struct drm_i915_private *dev_priv)
-{
-	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
-
-	gen6_disable_rps_interrupts(dev_priv);
-}
-
 /**
  * intel_suspend_gt_powersave - suspend PM work and helper threads
  * @dev_priv: i915 device
@@ -6542,50 +6535,65 @@ void intel_suspend_gt_powersave(struct drm_i915_private *dev_priv)
 	if (INTEL_GEN(dev_priv) < 6)
 		return;
 
-	gen6_suspend_rps(dev_priv);
+	cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work);
+
+	gen6_disable_rps_interrupts(dev_priv);
 
 	/* Force GPU to min freq during suspend */
 	gen6_rps_idle(dev_priv);
 }
 
+void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv)
+{
+	dev_priv->rps.enabled = true; /* force disabling */
+	intel_disable_gt_powersave(dev_priv);
+
+	gen6_reset_rps_interrupts(dev_priv);
+}
+
 void intel_disable_gt_powersave(struct drm_i915_private *dev_priv)
 {
-	if (IS_IRONLAKE_M(dev_priv)) {
-		ironlake_disable_drps(dev_priv);
-	} else if (INTEL_INFO(dev_priv)->gen >= 6) {
-		intel_suspend_gt_powersave(dev_priv);
+	if (!READ_ONCE(dev_priv->rps.enabled))
+		return;
 
-		mutex_lock(&dev_priv->rps.hw_lock);
-		if (INTEL_INFO(dev_priv)->gen >= 9) {
-			gen9_disable_rc6(dev_priv);
-			gen9_disable_rps(dev_priv);
-		} else if (IS_CHERRYVIEW(dev_priv))
-			cherryview_disable_rps(dev_priv);
-		else if (IS_VALLEYVIEW(dev_priv))
-			valleyview_disable_rps(dev_priv);
-		else
-			gen6_disable_rps(dev_priv);
+	mutex_lock(&dev_priv->rps.hw_lock);
 
-		dev_priv->rps.enabled = false;
-		mutex_unlock(&dev_priv->rps.hw_lock);
+	if (INTEL_GEN(dev_priv) >= 9) {
+		gen9_disable_rc6(dev_priv);
+		gen9_disable_rps(dev_priv);
+	} else if (IS_CHERRYVIEW(dev_priv)) {
+		cherryview_disable_rps(dev_priv);
+	} else if (IS_VALLEYVIEW(dev_priv)) {
+		valleyview_disable_rps(dev_priv);
+	} else if (INTEL_GEN(dev_priv) >= 6) {
+		gen6_disable_rps(dev_priv);
+	}  else if (IS_IRONLAKE_M(dev_priv)) {
+		ironlake_disable_drps(dev_priv);
 	}
+
+	dev_priv->rps.enabled = false;
+	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
-static void intel_gen6_powersave_work(struct work_struct *work)
+void intel_enable_gt_powersave(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv =
-		container_of(work, struct drm_i915_private,
-			     rps.delayed_resume_work.work);
+	/* We shouldn't be disabling as we submit, so this should be less
+	 * racy than it appears!
+	 */
+	if (READ_ONCE(dev_priv->rps.enabled))
+		return;
 
-	mutex_lock(&dev_priv->rps.hw_lock);
+	/* Powersaving is controlled by the host when inside a VM */
+	if (intel_vgpu_active(dev_priv))
+		return;
 
-	gen6_reset_rps_interrupts(dev_priv);
+	mutex_lock(&dev_priv->rps.hw_lock);
 
 	if (IS_CHERRYVIEW(dev_priv)) {
 		cherryview_enable_rps(dev_priv);
 	} else if (IS_VALLEYVIEW(dev_priv)) {
 		valleyview_enable_rps(dev_priv);
-	} else if (INTEL_INFO(dev_priv)->gen >= 9) {
+	} else if (INTEL_GEN(dev_priv) >= 9) {
 		gen9_enable_rc6(dev_priv);
 		gen9_enable_rps(dev_priv);
 		if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
@@ -6593,9 +6601,12 @@ static void intel_gen6_powersave_work(struct work_struct *work)
 	} else if (IS_BROADWELL(dev_priv)) {
 		gen8_enable_rps(dev_priv);
 		__gen6_update_ring_freq(dev_priv);
-	} else {
+	} else if (INTEL_GEN(dev_priv) >= 6) {
 		gen6_enable_rps(dev_priv);
 		__gen6_update_ring_freq(dev_priv);
+	} else if (IS_IRONLAKE_M(dev_priv)) {
+		ironlake_enable_drps(dev_priv);
+		intel_init_emon(dev_priv);
 	}
 
 	WARN_ON(dev_priv->rps.max_freq < dev_priv->rps.min_freq);
@@ -6604,43 +6615,61 @@ static void intel_gen6_powersave_work(struct work_struct *work)
 	WARN_ON(dev_priv->rps.efficient_freq < dev_priv->rps.min_freq);
 	WARN_ON(dev_priv->rps.efficient_freq > dev_priv->rps.max_freq);
 
+	if (INTEL_GEN(dev_priv) >= 6)
+		gen6_enable_rps_interrupts(dev_priv);
+
 	dev_priv->rps.enabled = true;
+	mutex_unlock(&dev_priv->rps.hw_lock);
+}
 
-	gen6_enable_rps_interrupts(dev_priv);
+static void __intel_autoenable_gt_powersave(struct work_struct *work)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(work, typeof(*dev_priv), rps.delayed_resume_work.work);
+	struct intel_engine_cs *rcs;
+	struct drm_i915_gem_request *req;
+	int ret;
 
-	mutex_unlock(&dev_priv->rps.hw_lock);
+	if (READ_ONCE(dev_priv->rps.enabled))
+		return;
+
+	rcs = &dev_priv->engine[RCS];
+	if (rcs->last_context)
+		return;
+
+	if (!rcs->init_context)
+		return;
+
+	intel_runtime_pm_get(dev_priv);
+	mutex_lock(&dev_priv->dev->struct_mutex);
+
+	req = i915_gem_request_alloc(rcs, dev_priv->kernel_context);
+	if (IS_ERR(req))
+		goto unlock;
+
+	ret = 0;
+	if (!i915.enable_execlists)
+		ret = i915_switch_context(req);
+	if (ret == 0)
+		rcs->init_context(req);
+	i915_add_request_no_flush(req);
 
+unlock:
+	mutex_unlock(&dev_priv->dev->struct_mutex);
 	intel_runtime_pm_put(dev_priv);
 }
 
-void intel_enable_gt_powersave(struct drm_i915_private *dev_priv)
+void intel_autoenable_gt_powersave(struct drm_i915_private *dev_priv)
 {
-	/* Powersaving is controlled by the host when inside a VM */
-	if (intel_vgpu_active(dev_priv))
+	if (READ_ONCE(dev_priv->rps.enabled))
 		return;
 
-	if (IS_IRONLAKE_M(dev_priv)) {
-		ironlake_enable_drps(dev_priv);
-		mutex_lock(&dev_priv->dev->struct_mutex);
-		intel_init_emon(dev_priv);
-		mutex_unlock(&dev_priv->dev->struct_mutex);
-	} else if (INTEL_INFO(dev_priv)->gen >= 6) {
-		/*
-		 * PCU communication is slow and this doesn't need to be
-		 * done at any specific time, so do this out of our fast path
-		 * to make resume and init faster.
-		 *
-		 * We depend on the HW RC6 power context save/restore
-		 * mechanism when entering D3 through runtime PM suspend. So
-		 * disable RPM until RPS/RC6 is properly setup. We can only
-		 * get here via the driver load/system resume/runtime resume
-		 * paths, so the _noresume version is enough (and in case of
-		 * runtime resume it's necessary).
-		 */
-		if (schedule_delayed_work(&dev_priv->rps.delayed_resume_work,
-					   round_jiffies_up_relative(HZ)))
-			intel_runtime_pm_get_noresume(dev_priv);
-	}
+	if (INTEL_GEN(dev_priv) < 6)
+		return;
+
+	queue_delayed_work(dev_priv->wq,
+			   &dev_priv->rps.delayed_resume_work,
+			   round_jiffies_up_relative(2*HZ));
 }
 
 void intel_reset_gt_powersave(struct drm_i915_private *dev_priv)
@@ -6648,7 +6677,7 @@ void intel_reset_gt_powersave(struct drm_i915_private *dev_priv)
 	if (INTEL_INFO(dev_priv)->gen < 6)
 		return;
 
-	gen6_suspend_rps(dev_priv);
+	gen6_disable_rps_interrupts(dev_priv);
 	dev_priv->rps.enabled = false;
 }
 
@@ -7746,7 +7775,7 @@ void intel_pm_setup(struct drm_device *dev)
 	spin_lock_init(&dev_priv->rps.client_lock);
 
 	INIT_DELAYED_WORK(&dev_priv->rps.delayed_resume_work,
-			  intel_gen6_powersave_work);
+			  __intel_autoenable_gt_powersave);
 	INIT_LIST_HEAD(&dev_priv->rps.clients);
 	INIT_LIST_HEAD(&dev_priv->rps.semaphores.link);
 	INIT_LIST_HEAD(&dev_priv->rps.mmioflips.link);
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index c1ca458d688e..1c7ae9dd8cae 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -435,7 +435,7 @@ void intel_uncore_sanitize(struct drm_i915_private *dev_priv)
 	i915.enable_rc6 = sanitize_rc6_option(dev_priv, i915.enable_rc6);
 
 	/* BIOS often leaves RC6 enabled, but disable it for hw init */
-	intel_disable_gt_powersave(dev_priv);
+	intel_sanitize_gt_powersave(dev_priv);
 }
 
 static void __intel_uncore_forcewake_get(struct drm_i915_private *dev_priv,
-- 
2.8.1



More information about the Intel-gfx-trybot mailing list