Re: [PATCH 2/8] drm/i915: Assert that runtime pm is active on user fw access

[Deepak S <deepak.s@linux.intel.com>]

On Monday 08 December 2014 11:57 PM, Mika Kuoppala wrote:
> From: Chris Wilson <chris@chris-wilson.co.uk>
>
> On user forcewake access, assert that runtime pm reference is held.
> Fix and cleanup the callsites accordingly.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
> ---
>   drivers/gpu/drm/i915/i915_debugfs.c  |  2 +
>   drivers/gpu/drm/i915/intel_display.c | 19 +--------
>   drivers/gpu/drm/i915/intel_lrc.c     | 53 ++-----------------------
>   drivers/gpu/drm/i915/intel_uncore.c  | 76 ++++++++++++------------------------
>   4 files changed, 31 insertions(+), 119 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
> index d0e445e..e142629 100644
> --- a/drivers/gpu/drm/i915/i915_debugfs.c
> +++ b/drivers/gpu/drm/i915/i915_debugfs.c
> @@ -4250,6 +4250,7 @@ static int i915_forcewake_open(struct inode *inode, struct file *file)
>   	if (INTEL_INFO(dev)->gen < 6)
>   		return 0;
>   
> +	intel_runtime_pm_get(dev_priv);
>   	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
>   
>   	return 0;
> @@ -4264,6 +4265,7 @@ static int i915_forcewake_release(struct inode *inode, struct file *file)
>   		return 0;
>   
>   	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
> +	intel_runtime_pm_put(dev_priv);
>   
>   	return 0;
>   }
> diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
> index d5153a4..86c2885 100644
> --- a/drivers/gpu/drm/i915/intel_display.c
> +++ b/drivers/gpu/drm/i915/intel_display.c
> @@ -7862,19 +7862,8 @@ static void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
>   	/*
>   	 * Make sure we're not on PC8 state before disabling PC8, otherwise
>   	 * we'll hang the machine. To prevent PC8 state, just enable force_wake.
> -	 *
> -	 * The other problem is that hsw_restore_lcpll() is called as part of
> -	 * the runtime PM resume sequence, so we can't just call
> -	 * gen6_gt_force_wake_get() because that function calls
> -	 * intel_runtime_pm_get(), and we can't change the runtime PM refcount
> -	 * while we are on the resume sequence. So to solve this problem we have
> -	 * to call special forcewake code that doesn't touch runtime PM and
> -	 * doesn't enable the forcewake delayed work.
>   	 */
> -	spin_lock_irq(&dev_priv->uncore.lock);
> -	if (dev_priv->uncore.forcewake_count++ == 0)
> -		dev_priv->uncore.funcs.force_wake_get(dev_priv, FORCEWAKE_ALL);
> -	spin_unlock_irq(&dev_priv->uncore.lock);
> +	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
>   
>   	if (val & LCPLL_POWER_DOWN_ALLOW) {
>   		val &= ~LCPLL_POWER_DOWN_ALLOW;
> @@ -7904,11 +7893,7 @@ static void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
>   			DRM_ERROR("Switching back to LCPLL failed\n");
>   	}
>   
> -	/* See the big comment above. */
> -	spin_lock_irq(&dev_priv->uncore.lock);
> -	if (--dev_priv->uncore.forcewake_count == 0)
> -		dev_priv->uncore.funcs.force_wake_put(dev_priv, FORCEWAKE_ALL);
> -	spin_unlock_irq(&dev_priv->uncore.lock);
> +	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
>   }
>   
>   /*
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index a82020e..fcb5140 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -284,7 +284,6 @@ static void execlists_elsp_write(struct intel_engine_cs *ring,
>   	struct drm_i915_private *dev_priv = dev->dev_private;
>   	uint64_t temp = 0;
>   	uint32_t desc[4];
> -	unsigned long flags;
>   
>   	/* XXX: You must always write both descriptors in the order below. */
>   	if (ctx_obj1)
> @@ -298,63 +297,17 @@ static void execlists_elsp_write(struct intel_engine_cs *ring,
>   	desc[3] = (u32)(temp >> 32);
>   	desc[2] = (u32)temp;
>   
> -	/* Set Force Wakeup bit to prevent GT from entering C6 while ELSP writes
> -	 * are in progress.
> -	 *
> -	 * The other problem is that we can't just call gen6_gt_force_wake_get()
> -	 * because that function calls intel_runtime_pm_get(), which might sleep.
> -	 * Instead, we do the runtime_pm_get/put when creating/destroying requests.
> -	 */
> -	spin_lock_irqsave(&dev_priv->uncore.lock, flags);
> -	if (IS_CHERRYVIEW(dev) || INTEL_INFO(dev)->gen >= 9) {
> -		if (dev_priv->uncore.fw_rendercount++ == 0)
> -			dev_priv->uncore.funcs.force_wake_get(dev_priv,
> -							      FORCEWAKE_RENDER);
> -		if (dev_priv->uncore.fw_mediacount++ == 0)
> -			dev_priv->uncore.funcs.force_wake_get(dev_priv,
> -							      FORCEWAKE_MEDIA);
> -		if (INTEL_INFO(dev)->gen >= 9) {
> -			if (dev_priv->uncore.fw_blittercount++ == 0)
> -				dev_priv->uncore.funcs.force_wake_get(dev_priv,
> -							FORCEWAKE_BLITTER);
> -		}
> -	} else {
> -		if (dev_priv->uncore.forcewake_count++ == 0)
> -			dev_priv->uncore.funcs.force_wake_get(dev_priv,
> -							      FORCEWAKE_ALL);
> -	}
> -	spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
> -
> +	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
>   	I915_WRITE(RING_ELSP(ring), desc[1]);
>   	I915_WRITE(RING_ELSP(ring), desc[0]);
>   	I915_WRITE(RING_ELSP(ring), desc[3]);
> +
>   	/* The context is automatically loaded after the following */
>   	I915_WRITE(RING_ELSP(ring), desc[2]);
>   
>   	/* ELSP is a wo register, so use another nearby reg for posting instead */
>   	POSTING_READ(RING_EXECLIST_STATUS(ring));
> -
> -	/* Release Force Wakeup (see the big comment above). */
> -	spin_lock_irqsave(&dev_priv->uncore.lock, flags);
> -	if (IS_CHERRYVIEW(dev) || INTEL_INFO(dev)->gen >= 9) {
> -		if (--dev_priv->uncore.fw_rendercount == 0)
> -			dev_priv->uncore.funcs.force_wake_put(dev_priv,
> -							      FORCEWAKE_RENDER);
> -		if (--dev_priv->uncore.fw_mediacount == 0)
> -			dev_priv->uncore.funcs.force_wake_put(dev_priv,
> -							      FORCEWAKE_MEDIA);
> -		if (INTEL_INFO(dev)->gen >= 9) {
> -			if (--dev_priv->uncore.fw_blittercount == 0)
> -				dev_priv->uncore.funcs.force_wake_put(dev_priv,
> -							FORCEWAKE_BLITTER);
> -		}
> -	} else {
> -		if (--dev_priv->uncore.forcewake_count == 0)
> -			dev_priv->uncore.funcs.force_wake_put(dev_priv,
> -							      FORCEWAKE_ALL);
> -	}
> -
> -	spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
> +	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
>   }
>   
>   static int execlists_update_context(struct drm_i915_gem_object *ctx_obj,
> diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
> index 38ac389..a1ceb92 100644
> --- a/drivers/gpu/drm/i915/intel_uncore.c
> +++ b/drivers/gpu/drm/i915/intel_uncore.c
> @@ -24,6 +24,8 @@
>   #include "i915_drv.h"
>   #include "intel_drv.h"
>   
> +#include <linux/pm_runtime.h>
> +
>   #define FORCEWAKE_ACK_TIMEOUT_MS 2
>   
>   #define __raw_i915_read8(dev_priv__, reg__) readb((dev_priv__)->regs + (reg__))
> @@ -247,10 +249,6 @@ static void __vlv_force_wake_put(struct drm_i915_private *dev_priv,
>   
>   static void vlv_force_wake_get(struct drm_i915_private *dev_priv, int fw_engine)
>   {
> -	unsigned long irqflags;
> -
> -	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
> -
>   	if (fw_engine & FORCEWAKE_RENDER &&
>   	    dev_priv->uncore.fw_rendercount++ != 0)
>   		fw_engine &= ~FORCEWAKE_RENDER;
> @@ -260,16 +258,10 @@ static void vlv_force_wake_get(struct drm_i915_private *dev_priv, int fw_engine)
>   
>   	if (fw_engine)
>   		dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_engine);
> -
> -	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
>   }
>   
>   static void vlv_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine)
>   {
> -	unsigned long irqflags;
> -
> -	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
> -
>   	if (fw_engine & FORCEWAKE_RENDER) {
>   		WARN_ON(!dev_priv->uncore.fw_rendercount);
>   		if (--dev_priv->uncore.fw_rendercount != 0)
> @@ -284,8 +276,6 @@ static void vlv_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine)
>   
>   	if (fw_engine)
>   		dev_priv->uncore.funcs.force_wake_put(dev_priv, fw_engine);
> -
> -	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
>   }
>   
>   static void __gen9_gt_force_wake_mt_reset(struct drm_i915_private *dev_priv)
> @@ -380,10 +370,6 @@ __gen9_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine)
>   static void
>   gen9_force_wake_get(struct drm_i915_private *dev_priv, int fw_engine)
>   {
> -	unsigned long irqflags;
> -
> -	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
> -
>   	if (FORCEWAKE_RENDER & fw_engine) {
>   		if (dev_priv->uncore.fw_rendercount++ == 0)
>   			dev_priv->uncore.funcs.force_wake_get(dev_priv,
> @@ -401,17 +387,11 @@ gen9_force_wake_get(struct drm_i915_private *dev_priv, int fw_engine)
>   			dev_priv->uncore.funcs.force_wake_get(dev_priv,
>   							FORCEWAKE_BLITTER);
>   	}
> -
> -	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
>   }
>   
>   static void
>   gen9_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine)
>   {
> -	unsigned long irqflags;
> -
> -	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
> -
>   	if (FORCEWAKE_RENDER & fw_engine) {
>   		WARN_ON(dev_priv->uncore.fw_rendercount == 0);
>   		if (--dev_priv->uncore.fw_rendercount == 0)
> @@ -432,8 +412,6 @@ gen9_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine)
>   			dev_priv->uncore.funcs.force_wake_put(dev_priv,
>   							FORCEWAKE_BLITTER);
>   	}
> -
> -	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
>   }
>   
>   static void gen6_force_wake_timer(unsigned long arg)
> @@ -564,17 +542,20 @@ void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv, int fw_engine)
>   
>   	intel_runtime_pm_get(dev_priv);
>   

I think we need to remove "intel_runtime_pm_get" here?
I see runtime_put is removed from "gen6_gt_force_wake_put"

> -	/* Redirect to Gen9 specific routine */
> -	if (IS_GEN9(dev_priv->dev))
> -		return gen9_force_wake_get(dev_priv, fw_engine);
> -
> -	/* Redirect to VLV specific routine */
> -	if (IS_VALLEYVIEW(dev_priv->dev))
> -		return vlv_force_wake_get(dev_priv, fw_engine);
> +	WARN_ON(!pm_runtime_active(&dev_priv->dev->pdev->dev));
>   
>   	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
> -	if (dev_priv->uncore.forcewake_count++ == 0)
> -		dev_priv->uncore.funcs.force_wake_get(dev_priv, FORCEWAKE_ALL);
> +
> +	if (IS_GEN9(dev_priv->dev)) {
> +		gen9_force_wake_get(dev_priv, fw_engine);
> +	} else if (IS_VALLEYVIEW(dev_priv->dev)) {
> +		vlv_force_wake_get(dev_priv, fw_engine);
> +	} else {
> +		if (dev_priv->uncore.forcewake_count++ == 0)
> +			dev_priv->uncore.funcs.force_wake_get(dev_priv,
> +							      FORCEWAKE_ALL);
> +	}
> +
>   	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
>   }
>   
> @@ -588,31 +569,22 @@ void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine)
>   	if (!dev_priv->uncore.funcs.force_wake_put)
>   		return;
>   
> -	/* Redirect to Gen9 specific routine */
> +	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
> +
>   	if (IS_GEN9(dev_priv->dev)) {
>   		gen9_force_wake_put(dev_priv, fw_engine);
> -		goto out;
> -	}
> -
> -	/* Redirect to VLV specific routine */
> -	if (IS_VALLEYVIEW(dev_priv->dev)) {
> +	} else if (IS_VALLEYVIEW(dev_priv->dev)) {
>   		vlv_force_wake_put(dev_priv, fw_engine);
> -		goto out;
> -	}
> -
> -	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
> -	WARN_ON(!dev_priv->uncore.forcewake_count);
> -
> -	if (--dev_priv->uncore.forcewake_count == 0) {
> -		dev_priv->uncore.forcewake_count++;
> -		mod_timer_pinned(&dev_priv->uncore.force_wake_timer,
> -				 jiffies + 1);
> +	} else {
> +		WARN_ON(!dev_priv->uncore.forcewake_count);
> +		if (--dev_priv->uncore.forcewake_count == 0) {
> +			dev_priv->uncore.forcewake_count++;
> +			mod_timer_pinned(&dev_priv->uncore.force_wake_timer,
> +					 jiffies + 1);
> +		}
>   	}
>   
>   	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
> -
> -out:
> -	intel_runtime_pm_put(dev_priv);
>   }
>   
>   void assert_force_wake_inactive(struct drm_i915_private *dev_priv)

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx