From 6cdcb5e73fba29bf115f2677c59de63f95039e2b Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Wed, 12 Jun 2013 17:27:29 -0300
Subject: drm/i915: invert the verbosity of intel_enable_fbc

We currently print a DRM_DEBUG_KMS message on the happy path and don't
print anything on the "failed to allocate" path. On some desktop
environments (e.g., Unity) I see the "scheduling delayed FBC enable"
thousands and thousands of times on my dmesg.

So kill the useless message for the happy case, saving a lot of dmesg
space, and properly signal the "kzalloc fail" case.

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Zoltan Nyul <zoltan.nyul@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index ccbdd83f522..346bde1edc0 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -381,6 +381,7 @@ void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 
 	work = kzalloc(sizeof *work, GFP_KERNEL);
 	if (work == NULL) {
+		DRM_ERROR("Failed to allocate FBC work structure\n");
 		dev_priv->display.enable_fbc(crtc, interval);
 		return;
 	}
@@ -392,8 +393,6 @@ void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 
 	dev_priv->fbc_work = work;
 
-	DRM_DEBUG_KMS("scheduling delayed FBC enable\n");
-
 	/* Delay the actual enabling to let pageflipping cease and the
 	 * display to settle before starting the compression. Note that
 	 * this delay also serves a second purpose: it allows for a
-- 
cgit v1.2.3-70-g09d2


From b63fb44c65ac37ceac8acd258939fcdc9f223c42 Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Mon, 24 Jun 2013 16:22:01 +0100
Subject: drm/i915: Make intel_enable_fbc() static

This function has no user outside of intel_pm.c.

Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_drv.h | 1 -
 drivers/gpu/drm/i915/intel_pm.c  | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index c8c9b6f4823..8eeee74f3d9 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -780,7 +780,6 @@ extern int intel_sprite_get_colorkey(struct drm_device *dev, void *data,
 extern void intel_init_pm(struct drm_device *dev);
 /* FBC */
 extern bool intel_fbc_enabled(struct drm_device *dev);
-extern void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval);
 extern void intel_update_fbc(struct drm_device *dev);
 /* IPS */
 extern void intel_gpu_ips_init(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 346bde1edc0..e0de8b3337d 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -368,7 +368,7 @@ static void intel_cancel_fbc_work(struct drm_i915_private *dev_priv)
 	dev_priv->fbc_work = NULL;
 }
 
-void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
+static void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 {
 	struct intel_fbc_work *work;
 	struct drm_device *dev = crtc->dev;
-- 
cgit v1.2.3-70-g09d2


From 8a5729a37375c20a196e14ce49b4390d42bdb87b Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Mon, 24 Jun 2013 16:22:02 +0100
Subject: drm/i915: Fix reason for per-chip disabling of FBC

When running on my snb machine, recent kernels display successively:

[drm:intel_update_fbc], fbc set to per-chip default
[drm:intel_update_fbc], fbc disabled per module param

But no module param is set. This happens because the check for the
module parameter uses a variable that has been overridden inside the
"per-chip default" code.

Fix up the logic and add another reason for the FBC to the be disabled.

Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_debugfs.c |  3 +++
 drivers/gpu/drm/i915/i915_drv.h     |  1 +
 drivers/gpu/drm/i915/intel_pm.c     | 14 ++++++--------
 3 files changed, 10 insertions(+), 8 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 47d6c748057..dca49828e3f 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1518,6 +1518,9 @@ static int i915_fbc_status(struct seq_file *m, void *unused)
 		case FBC_MODULE_PARAM:
 			seq_printf(m, "disabled per module param (default off)");
 			break;
+		case FBC_CHIP_DEFAULT:
+			seq_printf(m, "disabled per chip default");
+			break;
 		default:
 			seq_printf(m, "unknown reason");
 		}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index cc1d6056ab7..59c45f293ec 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -537,6 +537,7 @@ enum no_fbc_reason {
 	FBC_NOT_TILED, /* buffer not tiled */
 	FBC_MULTIPLE_PIPES, /* more than one pipe active */
 	FBC_MODULE_PARAM,
+	FBC_CHIP_DEFAULT, /* disabled by default on this chip */
 };
 
 enum intel_pch {
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index e0de8b3337d..adc7f3eb4ef 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -447,7 +447,6 @@ void intel_update_fbc(struct drm_device *dev)
 	struct drm_framebuffer *fb;
 	struct intel_framebuffer *intel_fb;
 	struct drm_i915_gem_object *obj;
-	int enable_fbc;
 	unsigned int max_hdisplay, max_vdisplay;
 
 	if (!i915_powersave)
@@ -488,14 +487,13 @@ void intel_update_fbc(struct drm_device *dev)
 	intel_fb = to_intel_framebuffer(fb);
 	obj = intel_fb->obj;
 
-	enable_fbc = i915_enable_fbc;
-	if (enable_fbc < 0) {
-		DRM_DEBUG_KMS("fbc set to per-chip default\n");
-		enable_fbc = 1;
-		if (INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev))
-			enable_fbc = 0;
+	if (i915_enable_fbc < 0 &&
+	    INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev)) {
+		DRM_DEBUG_KMS("disabled per chip default\n");
+		dev_priv->no_fbc_reason = FBC_CHIP_DEFAULT;
+		goto out_disable;
 	}
-	if (!enable_fbc) {
+	if (!i915_enable_fbc) {
 		DRM_DEBUG_KMS("fbc disabled per module param\n");
 		dev_priv->no_fbc_reason = FBC_MODULE_PARAM;
 		goto out_disable;
-- 
cgit v1.2.3-70-g09d2


From f4db9321a77258587d70cccdd4ff556df48eba2e Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Mon, 24 Jun 2013 22:59:50 +0100
Subject: drm/i915: Fix a couple of "should it be static?" sparse warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A genuine 'static' omission and 2 other warnings triggered by not
including the header where those functions where defined.

Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index adc7f3eb4ef..aa48fc6ba4d 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -30,6 +30,7 @@
 #include "intel_drv.h"
 #include "../../../platform/x86/intel_ips.h"
 #include <linux/module.h>
+#include <drm/i915_powerwell.h>
 
 #define FORCEWAKE_ACK_TIMEOUT_MS 2
 
@@ -2465,8 +2466,8 @@ static void hsw_compute_wm_results(struct drm_device *dev,
 
 /* Find the result with the highest level enabled. Check for enable_fbc_wm in
  * case both are at the same level. Prefer r1 in case they're the same. */
-struct hsw_wm_values *hsw_find_best_result(struct hsw_wm_values *r1,
-					   struct hsw_wm_values *r2)
+static struct hsw_wm_values *hsw_find_best_result(struct hsw_wm_values *r1,
+						  struct hsw_wm_values *r2)
 {
 	int i, val_r1 = 0, val_r2 = 0;
 
-- 
cgit v1.2.3-70-g09d2


From 5c3fe8b03ea6eb61617edb390d51c08609a495f7 Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Thu, 27 Jun 2013 16:30:21 -0700
Subject: drm/i915: Move fbc members out of line

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Resolve conflict with Damien's FBC_CHIP_DEFAULT no fbc
reason.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_debugfs.c    |  2 +-
 drivers/gpu/drm/i915/i915_drv.h        | 50 +++++++++++++++++++--------------
 drivers/gpu/drm/i915/i915_gem_stolen.c | 20 ++++++-------
 drivers/gpu/drm/i915/intel_display.c   |  6 ++--
 drivers/gpu/drm/i915/intel_drv.h       |  7 -----
 drivers/gpu/drm/i915/intel_pm.c        | 51 +++++++++++++++++-----------------
 6 files changed, 69 insertions(+), 67 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index c16926ca15b..f82134f8e9f 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1492,7 +1492,7 @@ static int i915_fbc_status(struct seq_file *m, void *unused)
 		seq_puts(m, "FBC enabled\n");
 	} else {
 		seq_puts(m, "FBC disabled: ");
-		switch (dev_priv->no_fbc_reason) {
+		switch (dev_priv->fbc.no_fbc_reason) {
 		case FBC_NO_OUTPUT:
 			seq_puts(m, "no outputs");
 			break;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 438cb0ab688..d1db73a5ba0 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -528,18 +528,36 @@ struct i915_hw_context {
 	struct i915_ctx_hang_stats hang_stats;
 };
 
-enum no_fbc_reason {
-	FBC_NO_OUTPUT, /* no outputs enabled to compress */
-	FBC_STOLEN_TOO_SMALL, /* not enough space to hold compressed buffers */
-	FBC_UNSUPPORTED_MODE, /* interlace or doublescanned mode */
-	FBC_MODE_TOO_LARGE, /* mode too large for compression */
-	FBC_BAD_PLANE, /* fbc not supported on plane */
-	FBC_NOT_TILED, /* buffer not tiled */
-	FBC_MULTIPLE_PIPES, /* more than one pipe active */
-	FBC_MODULE_PARAM,
-	FBC_CHIP_DEFAULT, /* disabled by default on this chip */
+struct i915_fbc {
+	unsigned long size;
+	unsigned int fb_id;
+	enum plane plane;
+	int y;
+
+	struct drm_mm_node *compressed_fb;
+	struct drm_mm_node *compressed_llb;
+
+	struct intel_fbc_work {
+		struct delayed_work work;
+		struct drm_crtc *crtc;
+		struct drm_framebuffer *fb;
+		int interval;
+	} *fbc_work;
+
+	enum {
+		FBC_NO_OUTPUT, /* no outputs enabled to compress */
+		FBC_STOLEN_TOO_SMALL, /* not enough space for buffers */
+		FBC_UNSUPPORTED_MODE, /* interlace or doublescanned mode */
+		FBC_MODE_TOO_LARGE, /* mode too large for compression */
+		FBC_BAD_PLANE, /* fbc not supported on plane */
+		FBC_NOT_TILED, /* buffer not tiled */
+		FBC_MULTIPLE_PIPES, /* more than one pipe active */
+		FBC_MODULE_PARAM,
+		FBC_CHIP_DEFAULT, /* disabled by default on this chip */
+	} no_fbc_reason;
 };
 
+
 enum intel_pch {
 	PCH_NONE = 0,	/* No PCH present */
 	PCH_IBX,	/* Ibexpeak PCH */
@@ -1059,12 +1077,7 @@ typedef struct drm_i915_private {
 
 	int num_plane;
 
-	unsigned long cfb_size;
-	unsigned int cfb_fb;
-	enum plane cfb_plane;
-	int cfb_y;
-	struct intel_fbc_work *fbc_work;
-
+	struct i915_fbc fbc;
 	struct intel_opregion opregion;
 	struct intel_vbt_data vbt;
 
@@ -1142,11 +1155,6 @@ typedef struct drm_i915_private {
 	/* Haswell power well */
 	struct i915_power_well power_well;
 
-	enum no_fbc_reason no_fbc_reason;
-
-	struct drm_mm_node *compressed_fb;
-	struct drm_mm_node *compressed_llb;
-
 	struct i915_gpu_error gpu_error;
 
 	struct drm_i915_gem_object *vlv_pctx;
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index f713294618f..8e023447b7e 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -120,7 +120,7 @@ static int i915_setup_compression(struct drm_device *dev, int size)
 		if (!compressed_llb)
 			goto err_fb;
 
-		dev_priv->compressed_llb = compressed_llb;
+		dev_priv->fbc.compressed_llb = compressed_llb;
 
 		I915_WRITE(FBC_CFB_BASE,
 			   dev_priv->mm.stolen_base + compressed_fb->start);
@@ -128,8 +128,8 @@ static int i915_setup_compression(struct drm_device *dev, int size)
 			   dev_priv->mm.stolen_base + compressed_llb->start);
 	}
 
-	dev_priv->compressed_fb = compressed_fb;
-	dev_priv->cfb_size = size;
+	dev_priv->fbc.compressed_fb = compressed_fb;
+	dev_priv->fbc.size = size;
 
 	DRM_DEBUG_KMS("reserved %d bytes of contiguous stolen space for FBC\n",
 		      size);
@@ -150,7 +150,7 @@ int i915_gem_stolen_setup_compression(struct drm_device *dev, int size)
 	if (dev_priv->mm.stolen_base == 0)
 		return -ENODEV;
 
-	if (size < dev_priv->cfb_size)
+	if (size < dev_priv->fbc.size)
 		return 0;
 
 	/* Release any current block */
@@ -163,16 +163,16 @@ void i915_gem_stolen_cleanup_compression(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (dev_priv->cfb_size == 0)
+	if (dev_priv->fbc.size == 0)
 		return;
 
-	if (dev_priv->compressed_fb)
-		drm_mm_put_block(dev_priv->compressed_fb);
+	if (dev_priv->fbc.compressed_fb)
+		drm_mm_put_block(dev_priv->fbc.compressed_fb);
 
-	if (dev_priv->compressed_llb)
-		drm_mm_put_block(dev_priv->compressed_llb);
+	if (dev_priv->fbc.compressed_llb)
+		drm_mm_put_block(dev_priv->fbc.compressed_llb);
 
-	dev_priv->cfb_size = 0;
+	dev_priv->fbc.size = 0;
 }
 
 void i915_gem_cleanup_stolen(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index d60684d9847..112120e909e 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3408,7 +3408,7 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc)
 	intel_crtc_wait_for_pending_flips(crtc);
 	drm_vblank_off(dev, pipe);
 
-	if (dev_priv->cfb_plane == plane)
+	if (dev_priv->fbc.plane == plane)
 		intel_disable_fbc(dev);
 
 	intel_crtc_update_cursor(crtc, false);
@@ -3481,7 +3481,7 @@ static void haswell_crtc_disable(struct drm_crtc *crtc)
 	drm_vblank_off(dev, pipe);
 
 	/* FBC must be disabled before disabling the plane on HSW. */
-	if (dev_priv->cfb_plane == plane)
+	if (dev_priv->fbc.plane == plane)
 		intel_disable_fbc(dev);
 
 	hsw_disable_ips(intel_crtc);
@@ -3720,7 +3720,7 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc)
 	intel_crtc_wait_for_pending_flips(crtc);
 	drm_vblank_off(dev, pipe);
 
-	if (dev_priv->cfb_plane == plane)
+	if (dev_priv->fbc.plane == plane)
 		intel_disable_fbc(dev);
 
 	intel_crtc_dpms_overlay(intel_crtc, false);
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 6f7f33e70e9..5dfc1a0f235 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -549,13 +549,6 @@ struct intel_unpin_work {
 	bool enable_stall_check;
 };
 
-struct intel_fbc_work {
-	struct delayed_work work;
-	struct drm_crtc *crtc;
-	struct drm_framebuffer *fb;
-	int interval;
-};
-
 int intel_pch_rawclk(struct drm_device *dev);
 
 int intel_connector_update_modes(struct drm_connector *connector,
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index aa48fc6ba4d..5b4ade682bd 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -87,7 +87,7 @@ static void i8xx_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	int plane, i;
 	u32 fbc_ctl, fbc_ctl2;
 
-	cfb_pitch = dev_priv->cfb_size / FBC_LL_SIZE;
+	cfb_pitch = dev_priv->fbc.size / FBC_LL_SIZE;
 	if (fb->pitches[0] < cfb_pitch)
 		cfb_pitch = fb->pitches[0];
 
@@ -326,7 +326,7 @@ static void intel_fbc_work_fn(struct work_struct *__work)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	mutex_lock(&dev->struct_mutex);
-	if (work == dev_priv->fbc_work) {
+	if (work == dev_priv->fbc.fbc_work) {
 		/* Double check that we haven't switched fb without cancelling
 		 * the prior work.
 		 */
@@ -334,12 +334,12 @@ static void intel_fbc_work_fn(struct work_struct *__work)
 			dev_priv->display.enable_fbc(work->crtc,
 						     work->interval);
 
-			dev_priv->cfb_plane = to_intel_crtc(work->crtc)->plane;
-			dev_priv->cfb_fb = work->crtc->fb->base.id;
-			dev_priv->cfb_y = work->crtc->y;
+			dev_priv->fbc.plane = to_intel_crtc(work->crtc)->plane;
+			dev_priv->fbc.fb_id = work->crtc->fb->base.id;
+			dev_priv->fbc.y = work->crtc->y;
 		}
 
-		dev_priv->fbc_work = NULL;
+		dev_priv->fbc.fbc_work = NULL;
 	}
 	mutex_unlock(&dev->struct_mutex);
 
@@ -348,25 +348,25 @@ static void intel_fbc_work_fn(struct work_struct *__work)
 
 static void intel_cancel_fbc_work(struct drm_i915_private *dev_priv)
 {
-	if (dev_priv->fbc_work == NULL)
+	if (dev_priv->fbc.fbc_work == NULL)
 		return;
 
 	DRM_DEBUG_KMS("cancelling pending FBC enable\n");
 
 	/* Synchronisation is provided by struct_mutex and checking of
-	 * dev_priv->fbc_work, so we can perform the cancellation
+	 * dev_priv->fbc.fbc_work, so we can perform the cancellation
 	 * entirely asynchronously.
 	 */
-	if (cancel_delayed_work(&dev_priv->fbc_work->work))
+	if (cancel_delayed_work(&dev_priv->fbc.fbc_work->work))
 		/* tasklet was killed before being run, clean up */
-		kfree(dev_priv->fbc_work);
+		kfree(dev_priv->fbc.fbc_work);
 
 	/* Mark the work as no longer wanted so that if it does
 	 * wake-up (because the work was already running and waiting
 	 * for our mutex), it will discover that is no longer
 	 * necessary to run.
 	 */
-	dev_priv->fbc_work = NULL;
+	dev_priv->fbc.fbc_work = NULL;
 }
 
 static void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
@@ -392,7 +392,7 @@ static void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	work->interval = interval;
 	INIT_DELAYED_WORK(&work->work, intel_fbc_work_fn);
 
-	dev_priv->fbc_work = work;
+	dev_priv->fbc.fbc_work = work;
 
 	/* Delay the actual enabling to let pageflipping cease and the
 	 * display to settle before starting the compression. Note that
@@ -418,7 +418,7 @@ void intel_disable_fbc(struct drm_device *dev)
 		return;
 
 	dev_priv->display.disable_fbc(dev);
-	dev_priv->cfb_plane = -1;
+	dev_priv->fbc.plane = -1;
 }
 
 /**
@@ -470,7 +470,8 @@ void intel_update_fbc(struct drm_device *dev)
 		    !to_intel_crtc(tmp_crtc)->primary_disabled) {
 			if (crtc) {
 				DRM_DEBUG_KMS("more than one pipe active, disabling compression\n");
-				dev_priv->no_fbc_reason = FBC_MULTIPLE_PIPES;
+				dev_priv->fbc.no_fbc_reason =
+					FBC_MULTIPLE_PIPES;
 				goto out_disable;
 			}
 			crtc = tmp_crtc;
@@ -479,7 +480,7 @@ void intel_update_fbc(struct drm_device *dev)
 
 	if (!crtc || crtc->fb == NULL) {
 		DRM_DEBUG_KMS("no output, disabling\n");
-		dev_priv->no_fbc_reason = FBC_NO_OUTPUT;
+		dev_priv->fbc.no_fbc_reason = FBC_NO_OUTPUT;
 		goto out_disable;
 	}
 
@@ -491,19 +492,19 @@ void intel_update_fbc(struct drm_device *dev)
 	if (i915_enable_fbc < 0 &&
 	    INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev)) {
 		DRM_DEBUG_KMS("disabled per chip default\n");
-		dev_priv->no_fbc_reason = FBC_CHIP_DEFAULT;
+		dev_priv->fbc.no_fbc_reason = FBC_CHIP_DEFAULT;
 		goto out_disable;
 	}
 	if (!i915_enable_fbc) {
 		DRM_DEBUG_KMS("fbc disabled per module param\n");
-		dev_priv->no_fbc_reason = FBC_MODULE_PARAM;
+		dev_priv->fbc.no_fbc_reason = FBC_MODULE_PARAM;
 		goto out_disable;
 	}
 	if ((crtc->mode.flags & DRM_MODE_FLAG_INTERLACE) ||
 	    (crtc->mode.flags & DRM_MODE_FLAG_DBLSCAN)) {
 		DRM_DEBUG_KMS("mode incompatible with compression, "
 			      "disabling\n");
-		dev_priv->no_fbc_reason = FBC_UNSUPPORTED_MODE;
+		dev_priv->fbc.no_fbc_reason = FBC_UNSUPPORTED_MODE;
 		goto out_disable;
 	}
 
@@ -517,13 +518,13 @@ void intel_update_fbc(struct drm_device *dev)
 	if ((crtc->mode.hdisplay > max_hdisplay) ||
 	    (crtc->mode.vdisplay > max_vdisplay)) {
 		DRM_DEBUG_KMS("mode too large for compression, disabling\n");
-		dev_priv->no_fbc_reason = FBC_MODE_TOO_LARGE;
+		dev_priv->fbc.no_fbc_reason = FBC_MODE_TOO_LARGE;
 		goto out_disable;
 	}
 	if ((IS_I915GM(dev) || IS_I945GM(dev) || IS_HASWELL(dev)) &&
 	    intel_crtc->plane != 0) {
 		DRM_DEBUG_KMS("plane not 0, disabling compression\n");
-		dev_priv->no_fbc_reason = FBC_BAD_PLANE;
+		dev_priv->fbc.no_fbc_reason = FBC_BAD_PLANE;
 		goto out_disable;
 	}
 
@@ -533,7 +534,7 @@ void intel_update_fbc(struct drm_device *dev)
 	if (obj->tiling_mode != I915_TILING_X ||
 	    obj->fence_reg == I915_FENCE_REG_NONE) {
 		DRM_DEBUG_KMS("framebuffer not tiled or fenced, disabling compression\n");
-		dev_priv->no_fbc_reason = FBC_NOT_TILED;
+		dev_priv->fbc.no_fbc_reason = FBC_NOT_TILED;
 		goto out_disable;
 	}
 
@@ -543,7 +544,7 @@ void intel_update_fbc(struct drm_device *dev)
 
 	if (i915_gem_stolen_setup_compression(dev, intel_fb->obj->base.size)) {
 		DRM_DEBUG_KMS("framebuffer too large, disabling compression\n");
-		dev_priv->no_fbc_reason = FBC_STOLEN_TOO_SMALL;
+		dev_priv->fbc.no_fbc_reason = FBC_STOLEN_TOO_SMALL;
 		goto out_disable;
 	}
 
@@ -552,9 +553,9 @@ void intel_update_fbc(struct drm_device *dev)
 	 * cannot be unpinned (and have its GTT offset and fence revoked)
 	 * without first being decoupled from the scanout and FBC disabled.
 	 */
-	if (dev_priv->cfb_plane == intel_crtc->plane &&
-	    dev_priv->cfb_fb == fb->base.id &&
-	    dev_priv->cfb_y == crtc->y)
+	if (dev_priv->fbc.plane == intel_crtc->plane &&
+	    dev_priv->fbc.fb_id == fb->base.id &&
+	    dev_priv->fbc.y == crtc->y)
 		return;
 
 	if (intel_fbc_enabled(dev)) {
-- 
cgit v1.2.3-70-g09d2


From e8474409d7ab6dac38d4a3a6a365504b302f6c16 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 26 Jun 2013 17:43:24 +0300
Subject: drm/i915: Use wait_for() to wait for Punit to change GPU freq on VLV
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use wait_for() instead of the open coded loop to avoid spreading the
same old timeout related bugs.

This changes the loop to use msleep(1) instead of udelay(10) when the
Punit had not yet completed the frequency change. In practice that
doesn't seem to hurt performance as the Punit appears to be ready pretty
much always.

Also give the status bit a name, instead of using the magic number 1.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_reg.h |  1 +
 drivers/gpu/drm/i915/intel_pm.c | 11 ++---------
 2 files changed, 3 insertions(+), 9 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index f2326fc60ac..9b51be80096 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -363,6 +363,7 @@
 #define PUNIT_REG_GPU_LFM			0xd3
 #define PUNIT_REG_GPU_FREQ_REQ			0xd4
 #define PUNIT_REG_GPU_FREQ_STS			0xd8
+#define   GENFREQSTATUS				(1<<0)
 #define PUNIT_REG_MEDIA_TURBO_FREQ_REQ		0xdc
 
 #define PUNIT_FUSE_BUS2				0xf6 /* bits 47:40 */
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 5b4ade682bd..7cfd3b74d9b 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3075,19 +3075,12 @@ void gen6_set_rps(struct drm_device *dev, u8 val)
  */
 static void vlv_update_rps_cur_delay(struct drm_i915_private *dev_priv)
 {
-	unsigned long timeout = jiffies + msecs_to_jiffies(10);
 	u32 pval;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
-	do {
-		pval = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
-		if (time_after(jiffies, timeout)) {
-			DRM_DEBUG_DRIVER("timed out waiting for Punit\n");
-			break;
-		}
-		udelay(10);
-	} while (pval & 1);
+	if (wait_for(((pval = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS)) & GENFREQSTATUS) == 0, 10))
+		DRM_DEBUG_DRIVER("timed out waiting for Punit\n");
 
 	pval >>= 8;
 
-- 
cgit v1.2.3-70-g09d2


From 190d6cd5cd3606dd13a3ca5bf0c23dc520659c15 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 4 Jul 2013 13:06:28 +0200
Subject: drm/i915: less magic for stolen preallocated objects w/o gtt offset

A magic -1 is a obscure, especially since it's actually passed as an
unsigned, so depends upon the magic sign extension rules in C. This has
been added in

commit 3727d55e4d85836aa6cb759a965daaef88074150
Author: Jesse Barnes <jbarnes@virtuousgeek.org>
Date:   Wed May 8 10:45:14 2013 -0700

    drm/i915: allow stolen, pre-allocated objects to avoid GTT allocation v2

Use a proper #define instead. Spotted while reviewing Ben's
drm_mm_create_block changes.

v2: Cast the constant to u32 since otherwise we again have a type
mismatch. Suggested by Chris Wilson.

Cc: Ben Widawsky <ben@bwidawsk.net>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_drv.h        | 1 +
 drivers/gpu/drm/i915/i915_gem_stolen.c | 2 +-
 drivers/gpu/drm/i915/intel_pm.c        | 2 +-
 3 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a7c2cfb3ee9..0a91554e0aa 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1202,6 +1202,7 @@ enum hdmi_force_audio {
 };
 
 #define I915_GTT_RESERVED ((struct drm_mm_node *)0x1)
+#define I915_GTT_OFFSET_NONE ((u32)-1)
 
 struct drm_i915_gem_object_ops {
 	/* Interface between the GEM object and its backing storage.
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 8e023447b7e..0f18d75fa9f 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -360,7 +360,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 	}
 
 	/* Some objects just need physical mem from stolen space */
-	if (gtt_offset == -1)
+	if (gtt_offset == I915_GTT_OFFSET_NONE)
 		return obj;
 
 	/* To simplify the initialisation sequence between KMS and GTT,
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 7cfd3b74d9b..0eed35da3ea 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3474,7 +3474,7 @@ static void valleyview_setup_pctx(struct drm_device *dev)
 		pcbr_offset = (pcbr & (~4095)) - dev_priv->mm.stolen_base;
 		pctx = i915_gem_object_create_stolen_for_preallocated(dev_priv->dev,
 								      pcbr_offset,
-								      -1,
+								      I915_GTT_OFFSET_NONE,
 								      pctx_size);
 		goto out;
 	}
-- 
cgit v1.2.3-70-g09d2


From f343c5f6477354967ee1e331a68a56b9fece2f36 Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Fri, 5 Jul 2013 14:41:04 -0700
Subject: drm/i915: Getter/setter for object attributes

Soon we want to gut a lot of our existing assumptions how many address
spaces an object can live in, and in doing so, embed the drm_mm_node in
the object (and later the VMA).

It's possible in the future we'll want to add more getter/setter
methods, but for now this is enough to enable the VMAs.

v2: Reworked commit message (Ben)
Added comments to the main functions (Ben)
sed -i "s/i915_gem_obj_set_color/i915_gem_obj_ggtt_set_color/" drivers/gpu/drm/i915/*.[ch]
sed -i "s/i915_gem_obj_bound/i915_gem_obj_ggtt_bound/" drivers/gpu/drm/i915/*.[ch]
sed -i "s/i915_gem_obj_size/i915_gem_obj_ggtt_size/" drivers/gpu/drm/i915/*.[ch]
sed -i "s/i915_gem_obj_offset/i915_gem_obj_ggtt_offset/" drivers/gpu/drm/i915/*.[ch]
(Daniel)

v3: Rebased on new reserve_node patch
Changed DRM_DEBUG_KMS to actually work (will need fixing later)

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_debugfs.c        | 26 +++++----
 drivers/gpu/drm/i915/i915_drv.h            | 31 +++++++++++
 drivers/gpu/drm/i915/i915_gem.c            | 89 +++++++++++++++---------------
 drivers/gpu/drm/i915/i915_gem_context.c    |  2 +-
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 19 ++++---
 drivers/gpu/drm/i915/i915_gem_gtt.c        |  8 +--
 drivers/gpu/drm/i915/i915_gem_tiling.c     | 14 ++---
 drivers/gpu/drm/i915/i915_irq.c            | 15 +++--
 drivers/gpu/drm/i915/i915_trace.h          |  8 +--
 drivers/gpu/drm/i915/intel_display.c       | 28 +++++-----
 drivers/gpu/drm/i915/intel_fb.c            |  8 +--
 drivers/gpu/drm/i915/intel_overlay.c       | 14 ++---
 drivers/gpu/drm/i915/intel_pm.c            |  8 +--
 drivers/gpu/drm/i915/intel_ringbuffer.c    | 12 ++--
 drivers/gpu/drm/i915/intel_sprite.c        |  8 ++-
 15 files changed, 164 insertions(+), 126 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 3e36756d043..396387ed207 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -122,9 +122,9 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		seq_printf(m, " (pinned x %d)", obj->pin_count);
 	if (obj->fence_reg != I915_FENCE_REG_NONE)
 		seq_printf(m, " (fence: %d)", obj->fence_reg);
-	if (obj->gtt_space != NULL)
-		seq_printf(m, " (gtt offset: %08x, size: %08x)",
-			   obj->gtt_offset, (unsigned int)obj->gtt_space->size);
+	if (i915_gem_obj_ggtt_bound(obj))
+		seq_printf(m, " (gtt offset: %08lx, size: %08x)",
+			   i915_gem_obj_ggtt_offset(obj), (unsigned int)i915_gem_obj_ggtt_size(obj));
 	if (obj->stolen)
 		seq_printf(m, " (stolen: %08lx)", obj->stolen->start);
 	if (obj->pin_mappable || obj->fault_mappable) {
@@ -175,7 +175,7 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
 		describe_obj(m, obj);
 		seq_putc(m, '\n');
 		total_obj_size += obj->base.size;
-		total_gtt_size += obj->gtt_space->size;
+		total_gtt_size += i915_gem_obj_ggtt_size(obj);
 		count++;
 	}
 	mutex_unlock(&dev->struct_mutex);
@@ -187,10 +187,10 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
 
 #define count_objects(list, member) do { \
 	list_for_each_entry(obj, list, member) { \
-		size += obj->gtt_space->size; \
+		size += i915_gem_obj_ggtt_size(obj); \
 		++count; \
 		if (obj->map_and_fenceable) { \
-			mappable_size += obj->gtt_space->size; \
+			mappable_size += i915_gem_obj_ggtt_size(obj); \
 			++mappable_count; \
 		} \
 	} \
@@ -209,7 +209,7 @@ static int per_file_stats(int id, void *ptr, void *data)
 	stats->count++;
 	stats->total += obj->base.size;
 
-	if (obj->gtt_space) {
+	if (i915_gem_obj_ggtt_bound(obj)) {
 		if (!list_empty(&obj->ring_list))
 			stats->active += obj->base.size;
 		else
@@ -267,11 +267,11 @@ static int i915_gem_object_info(struct seq_file *m, void *data)
 	size = count = mappable_size = mappable_count = 0;
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
 		if (obj->fault_mappable) {
-			size += obj->gtt_space->size;
+			size += i915_gem_obj_ggtt_size(obj);
 			++count;
 		}
 		if (obj->pin_mappable) {
-			mappable_size += obj->gtt_space->size;
+			mappable_size += i915_gem_obj_ggtt_size(obj);
 			++mappable_count;
 		}
 		if (obj->madv == I915_MADV_DONTNEED) {
@@ -333,7 +333,7 @@ static int i915_gem_gtt_info(struct seq_file *m, void *data)
 		describe_obj(m, obj);
 		seq_putc(m, '\n');
 		total_obj_size += obj->base.size;
-		total_gtt_size += obj->gtt_space->size;
+		total_gtt_size += i915_gem_obj_ggtt_size(obj);
 		count++;
 	}
 
@@ -379,12 +379,14 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data)
 			if (work->old_fb_obj) {
 				struct drm_i915_gem_object *obj = work->old_fb_obj;
 				if (obj)
-					seq_printf(m, "Old framebuffer gtt_offset 0x%08x\n", obj->gtt_offset);
+					seq_printf(m, "Old framebuffer gtt_offset 0x%08lx\n",
+						   i915_gem_obj_ggtt_offset(obj));
 			}
 			if (work->pending_flip_obj) {
 				struct drm_i915_gem_object *obj = work->pending_flip_obj;
 				if (obj)
-					seq_printf(m, "New framebuffer gtt_offset 0x%08x\n", obj->gtt_offset);
+					seq_printf(m, "New framebuffer gtt_offset 0x%08lx\n",
+						   i915_gem_obj_ggtt_offset(obj));
 			}
 		}
 		spin_unlock_irqrestore(&dev->event_lock, flags);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0a91554e0aa..8a92174109c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1361,6 +1361,37 @@ struct drm_i915_gem_object {
 
 #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base)
 
+/* Offset of the first PTE pointing to this object */
+static inline unsigned long
+i915_gem_obj_ggtt_offset(struct drm_i915_gem_object *o)
+{
+	return o->gtt_space->start;
+}
+
+/* Whether or not this object is currently mapped by the translation tables */
+static inline bool
+i915_gem_obj_ggtt_bound(struct drm_i915_gem_object *o)
+{
+	return o->gtt_space != NULL;
+}
+
+/* The size used in the translation tables may be larger than the actual size of
+ * the object on GEN2/GEN3 because of the way tiling is handled. See
+ * i915_gem_get_gtt_size() for more details.
+ */
+static inline unsigned long
+i915_gem_obj_ggtt_size(struct drm_i915_gem_object *o)
+{
+	return o->gtt_space->size;
+}
+
+static inline void
+i915_gem_obj_ggtt_set_color(struct drm_i915_gem_object *o,
+			    enum i915_cache_level color)
+{
+	o->gtt_space->color = color;
+}
+
 /**
  * Request queue structure.
  *
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 769f75262fe..b8a0d91f2e2 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -135,7 +135,7 @@ int i915_mutex_lock_interruptible(struct drm_device *dev)
 static inline bool
 i915_gem_object_is_inactive(struct drm_i915_gem_object *obj)
 {
-	return obj->gtt_space && !obj->active;
+	return i915_gem_obj_ggtt_bound(obj) && !obj->active;
 }
 
 int
@@ -178,7 +178,7 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 	mutex_lock(&dev->struct_mutex);
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list)
 		if (obj->pin_count)
-			pinned += obj->gtt_space->size;
+			pinned += i915_gem_obj_ggtt_size(obj);
 	mutex_unlock(&dev->struct_mutex);
 
 	args->aper_size = dev_priv->gtt.total;
@@ -422,7 +422,7 @@ i915_gem_shmem_pread(struct drm_device *dev,
 		 * anyway again before the next pread happens. */
 		if (obj->cache_level == I915_CACHE_NONE)
 			needs_clflush = 1;
-		if (obj->gtt_space) {
+		if (i915_gem_obj_ggtt_bound(obj)) {
 			ret = i915_gem_object_set_to_gtt_domain(obj, false);
 			if (ret)
 				return ret;
@@ -609,7 +609,7 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev,
 	user_data = to_user_ptr(args->data_ptr);
 	remain = args->size;
 
-	offset = obj->gtt_offset + args->offset;
+	offset = i915_gem_obj_ggtt_offset(obj) + args->offset;
 
 	while (remain > 0) {
 		/* Operation in this page
@@ -739,7 +739,7 @@ i915_gem_shmem_pwrite(struct drm_device *dev,
 		 * right away and we therefore have to clflush anyway. */
 		if (obj->cache_level == I915_CACHE_NONE)
 			needs_clflush_after = 1;
-		if (obj->gtt_space) {
+		if (i915_gem_obj_ggtt_bound(obj)) {
 			ret = i915_gem_object_set_to_gtt_domain(obj, true);
 			if (ret)
 				return ret;
@@ -1360,8 +1360,9 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 	obj->fault_mappable = true;
 
-	pfn = ((dev_priv->gtt.mappable_base + obj->gtt_offset) >> PAGE_SHIFT) +
-		page_offset;
+	pfn = dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj);
+	pfn >>= PAGE_SHIFT;
+	pfn += page_offset;
 
 	/* Finally, remap it using the new GTT offset */
 	ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, pfn);
@@ -1667,7 +1668,7 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
 	if (obj->pages == NULL)
 		return 0;
 
-	BUG_ON(obj->gtt_space);
+	BUG_ON(i915_gem_obj_ggtt_bound(obj));
 
 	if (obj->pages_pin_count)
 		return -EBUSY;
@@ -2117,8 +2118,8 @@ i915_gem_request_remove_from_client(struct drm_i915_gem_request *request)
 
 static bool i915_head_inside_object(u32 acthd, struct drm_i915_gem_object *obj)
 {
-	if (acthd >= obj->gtt_offset &&
-	    acthd < obj->gtt_offset + obj->base.size)
+	if (acthd >= i915_gem_obj_ggtt_offset(obj) &&
+	    acthd < i915_gem_obj_ggtt_offset(obj) + obj->base.size)
 		return true;
 
 	return false;
@@ -2176,11 +2177,11 @@ static void i915_set_reset_status(struct intel_ring_buffer *ring,
 
 	if (ring->hangcheck.action != wait &&
 	    i915_request_guilty(request, acthd, &inside)) {
-		DRM_ERROR("%s hung %s bo (0x%x ctx %d) at 0x%x\n",
+		DRM_ERROR("%s hung %s bo (0x%lx ctx %d) at 0x%x\n",
 			  ring->name,
 			  inside ? "inside" : "flushing",
 			  request->batch_obj ?
-			  request->batch_obj->gtt_offset : 0,
+			  i915_gem_obj_ggtt_offset(request->batch_obj) : 0,
 			  request->ctx ? request->ctx->id : 0,
 			  acthd);
 
@@ -2592,7 +2593,7 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj)
 	drm_i915_private_t *dev_priv = obj->base.dev->dev_private;
 	int ret;
 
-	if (obj->gtt_space == NULL)
+	if (!i915_gem_obj_ggtt_bound(obj))
 		return 0;
 
 	if (obj->pin_count)
@@ -2675,11 +2676,11 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
 	}
 
 	if (obj) {
-		u32 size = obj->gtt_space->size;
+		u32 size = i915_gem_obj_ggtt_size(obj);
 
-		val = (uint64_t)((obj->gtt_offset + size - 4096) &
+		val = (uint64_t)((i915_gem_obj_ggtt_offset(obj) + size - 4096) &
 				 0xfffff000) << 32;
-		val |= obj->gtt_offset & 0xfffff000;
+		val |= i915_gem_obj_ggtt_offset(obj) & 0xfffff000;
 		val |= (uint64_t)((obj->stride / 128) - 1) << fence_pitch_shift;
 		if (obj->tiling_mode == I915_TILING_Y)
 			val |= 1 << I965_FENCE_TILING_Y_SHIFT;
@@ -2699,15 +2700,15 @@ static void i915_write_fence_reg(struct drm_device *dev, int reg,
 	u32 val;
 
 	if (obj) {
-		u32 size = obj->gtt_space->size;
+		u32 size = i915_gem_obj_ggtt_size(obj);
 		int pitch_val;
 		int tile_width;
 
-		WARN((obj->gtt_offset & ~I915_FENCE_START_MASK) ||
+		WARN((i915_gem_obj_ggtt_offset(obj) & ~I915_FENCE_START_MASK) ||
 		     (size & -size) != size ||
-		     (obj->gtt_offset & (size - 1)),
-		     "object 0x%08x [fenceable? %d] not 1M or pot-size (0x%08x) aligned\n",
-		     obj->gtt_offset, obj->map_and_fenceable, size);
+		     (i915_gem_obj_ggtt_offset(obj) & (size - 1)),
+		     "object 0x%08lx [fenceable? %d] not 1M or pot-size (0x%08x) aligned\n",
+		     i915_gem_obj_ggtt_offset(obj), obj->map_and_fenceable, size);
 
 		if (obj->tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev))
 			tile_width = 128;
@@ -2718,7 +2719,7 @@ static void i915_write_fence_reg(struct drm_device *dev, int reg,
 		pitch_val = obj->stride / tile_width;
 		pitch_val = ffs(pitch_val) - 1;
 
-		val = obj->gtt_offset;
+		val = i915_gem_obj_ggtt_offset(obj);
 		if (obj->tiling_mode == I915_TILING_Y)
 			val |= 1 << I830_FENCE_TILING_Y_SHIFT;
 		val |= I915_FENCE_SIZE_BITS(size);
@@ -2743,19 +2744,19 @@ static void i830_write_fence_reg(struct drm_device *dev, int reg,
 	uint32_t val;
 
 	if (obj) {
-		u32 size = obj->gtt_space->size;
+		u32 size = i915_gem_obj_ggtt_size(obj);
 		uint32_t pitch_val;
 
-		WARN((obj->gtt_offset & ~I830_FENCE_START_MASK) ||
+		WARN((i915_gem_obj_ggtt_offset(obj) & ~I830_FENCE_START_MASK) ||
 		     (size & -size) != size ||
-		     (obj->gtt_offset & (size - 1)),
-		     "object 0x%08x not 512K or pot-size 0x%08x aligned\n",
-		     obj->gtt_offset, size);
+		     (i915_gem_obj_ggtt_offset(obj) & (size - 1)),
+		     "object 0x%08lx not 512K or pot-size 0x%08x aligned\n",
+		     i915_gem_obj_ggtt_offset(obj), size);
 
 		pitch_val = obj->stride / 128;
 		pitch_val = ffs(pitch_val) - 1;
 
-		val = obj->gtt_offset;
+		val = i915_gem_obj_ggtt_offset(obj);
 		if (obj->tiling_mode == I915_TILING_Y)
 			val |= 1 << I830_FENCE_TILING_Y_SHIFT;
 		val |= I830_FENCE_SIZE_BITS(size);
@@ -3044,8 +3045,8 @@ static void i915_gem_verify_gtt(struct drm_device *dev)
 
 		if (obj->cache_level != obj->gtt_space->color) {
 			printk(KERN_ERR "object reserved space [%08lx, %08lx] with wrong color, cache_level=%x, color=%lx\n",
-			       obj->gtt_space->start,
-			       obj->gtt_space->start + obj->gtt_space->size,
+			       i915_gem_obj_ggtt_offset(obj),
+			       i915_gem_obj_ggtt_offset(obj) + i915_gem_obj_ggtt_size(obj),
 			       obj->cache_level,
 			       obj->gtt_space->color);
 			err++;
@@ -3056,8 +3057,8 @@ static void i915_gem_verify_gtt(struct drm_device *dev)
 					      obj->gtt_space,
 					      obj->cache_level)) {
 			printk(KERN_ERR "invalid GTT space found at [%08lx, %08lx] - color=%x\n",
-			       obj->gtt_space->start,
-			       obj->gtt_space->start + obj->gtt_space->size,
+			       i915_gem_obj_ggtt_offset(obj),
+			       i915_gem_obj_ggtt_offset(obj) + i915_gem_obj_ggtt_size(obj),
 			       obj->cache_level);
 			err++;
 			continue;
@@ -3169,8 +3170,8 @@ search_free:
 		node->size == fence_size &&
 		(node->start & (fence_alignment - 1)) == 0;
 
-	mappable =
-		obj->gtt_offset + obj->base.size <= dev_priv->gtt.mappable_end;
+	mappable = i915_gem_obj_ggtt_offset(obj) + obj->base.size <=
+		dev_priv->gtt.mappable_end;
 
 	obj->map_and_fenceable = mappable && fenceable;
 
@@ -3272,7 +3273,7 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 	int ret;
 
 	/* Not valid to be called on unbound objects. */
-	if (obj->gtt_space == NULL)
+	if (!i915_gem_obj_ggtt_bound(obj))
 		return -EINVAL;
 
 	if (obj->base.write_domain == I915_GEM_DOMAIN_GTT)
@@ -3337,7 +3338,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 			return ret;
 	}
 
-	if (obj->gtt_space) {
+	if (i915_gem_obj_ggtt_bound(obj)) {
 		ret = i915_gem_object_finish_gpu(obj);
 		if (ret)
 			return ret;
@@ -3360,7 +3361,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 			i915_ppgtt_bind_object(dev_priv->mm.aliasing_ppgtt,
 					       obj, cache_level);
 
-		obj->gtt_space->color = cache_level;
+		i915_gem_obj_ggtt_set_color(obj, cache_level);
 	}
 
 	if (cache_level == I915_CACHE_NONE) {
@@ -3641,14 +3642,14 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj,
 	if (WARN_ON(obj->pin_count == DRM_I915_GEM_OBJECT_MAX_PIN_COUNT))
 		return -EBUSY;
 
-	if (obj->gtt_space != NULL) {
-		if ((alignment && obj->gtt_offset & (alignment - 1)) ||
+	if (i915_gem_obj_ggtt_bound(obj)) {
+		if ((alignment && i915_gem_obj_ggtt_offset(obj) & (alignment - 1)) ||
 		    (map_and_fenceable && !obj->map_and_fenceable)) {
 			WARN(obj->pin_count,
 			     "bo is already pinned with incorrect alignment:"
-			     " offset=%x, req.alignment=%x, req.map_and_fenceable=%d,"
+			     " offset=%lx, req.alignment=%x, req.map_and_fenceable=%d,"
 			     " obj->map_and_fenceable=%d\n",
-			     obj->gtt_offset, alignment,
+			     i915_gem_obj_ggtt_offset(obj), alignment,
 			     map_and_fenceable,
 			     obj->map_and_fenceable);
 			ret = i915_gem_object_unbind(obj);
@@ -3657,7 +3658,7 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj,
 		}
 	}
 
-	if (obj->gtt_space == NULL) {
+	if (!i915_gem_obj_ggtt_bound(obj)) {
 		struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
 
 		ret = i915_gem_object_bind_to_gtt(obj, alignment,
@@ -3683,7 +3684,7 @@ void
 i915_gem_object_unpin(struct drm_i915_gem_object *obj)
 {
 	BUG_ON(obj->pin_count == 0);
-	BUG_ON(obj->gtt_space == NULL);
+	BUG_ON(!i915_gem_obj_ggtt_bound(obj));
 
 	if (--obj->pin_count == 0)
 		obj->pin_mappable = false;
@@ -3733,7 +3734,7 @@ i915_gem_pin_ioctl(struct drm_device *dev, void *data,
 	 * as the X server doesn't manage domains yet
 	 */
 	i915_gem_object_flush_cpu_write_domain(obj);
-	args->offset = obj->gtt_offset;
+	args->offset = i915_gem_obj_ggtt_offset(obj);
 out:
 	drm_gem_object_unreference(&obj->base);
 unlock:
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 51b7a2171ca..2074544682c 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -377,7 +377,7 @@ mi_set_context(struct intel_ring_buffer *ring,
 
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_emit(ring, MI_SET_CONTEXT);
-	intel_ring_emit(ring, new_context->obj->gtt_offset |
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(new_context->obj) |
 			MI_MM_SPACE_GTT |
 			MI_SAVE_EXT_STATE_EN |
 			MI_RESTORE_EXT_STATE_EN |
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 87a3227e517..5aeb447ead6 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -188,7 +188,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 		return -ENOENT;
 
 	target_i915_obj = to_intel_bo(target_obj);
-	target_offset = target_i915_obj->gtt_offset;
+	target_offset = i915_gem_obj_ggtt_offset(target_i915_obj);
 
 	/* Sandybridge PPGTT errata: We need a global gtt mapping for MI and
 	 * pipe_control writes because the gpu doesn't properly redirect them
@@ -280,7 +280,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 			return ret;
 
 		/* Map the page containing the relocation we're going to perform.  */
-		reloc->offset += obj->gtt_offset;
+		reloc->offset += i915_gem_obj_ggtt_offset(obj);
 		reloc_page = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
 						      reloc->offset & PAGE_MASK);
 		reloc_entry = (uint32_t __iomem *)
@@ -436,8 +436,8 @@ i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj,
 		obj->has_aliasing_ppgtt_mapping = 1;
 	}
 
-	if (entry->offset != obj->gtt_offset) {
-		entry->offset = obj->gtt_offset;
+	if (entry->offset != i915_gem_obj_ggtt_offset(obj)) {
+		entry->offset = i915_gem_obj_ggtt_offset(obj);
 		*need_reloc = true;
 	}
 
@@ -458,7 +458,7 @@ i915_gem_execbuffer_unreserve_object(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_gem_exec_object2 *entry;
 
-	if (!obj->gtt_space)
+	if (!i915_gem_obj_ggtt_bound(obj))
 		return;
 
 	entry = obj->exec_entry;
@@ -530,7 +530,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 			struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
 			bool need_fence, need_mappable;
 
-			if (!obj->gtt_space)
+			if (!i915_gem_obj_ggtt_bound(obj))
 				continue;
 
 			need_fence =
@@ -539,7 +539,8 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 				obj->tiling_mode != I915_TILING_NONE;
 			need_mappable = need_fence || need_reloc_mappable(obj);
 
-			if ((entry->alignment && obj->gtt_offset & (entry->alignment - 1)) ||
+			if ((entry->alignment &&
+			     i915_gem_obj_ggtt_offset(obj) & (entry->alignment - 1)) ||
 			    (need_mappable && !obj->map_and_fenceable))
 				ret = i915_gem_object_unbind(obj);
 			else
@@ -550,7 +551,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 
 		/* Bind fresh objects */
 		list_for_each_entry(obj, objects, exec_list) {
-			if (obj->gtt_space)
+			if (i915_gem_obj_ggtt_bound(obj))
 				continue;
 
 			ret = i915_gem_execbuffer_reserve_object(obj, ring, need_relocs);
@@ -1058,7 +1059,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 			goto err;
 	}
 
-	exec_start = batch_obj->gtt_offset + args->batch_start_offset;
+	exec_start = i915_gem_obj_ggtt_offset(batch_obj) + args->batch_start_offset;
 	exec_len = args->batch_len;
 	if (cliprects) {
 		for (i = 0; i < args->num_cliprects; i++) {
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index afba7e5e773..6f0a4c09e26 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -378,7 +378,7 @@ void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt,
 			    enum i915_cache_level cache_level)
 {
 	ppgtt->insert_entries(ppgtt, obj->pages,
-			      obj->gtt_space->start >> PAGE_SHIFT,
+			      i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT,
 			      cache_level);
 }
 
@@ -386,7 +386,7 @@ void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt,
 			      struct drm_i915_gem_object *obj)
 {
 	ppgtt->clear_range(ppgtt,
-			   obj->gtt_space->start >> PAGE_SHIFT,
+			   i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT,
 			   obj->base.size >> PAGE_SHIFT);
 }
 
@@ -551,7 +551,7 @@ void i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	dev_priv->gtt.gtt_insert_entries(dev, obj->pages,
-					 obj->gtt_space->start >> PAGE_SHIFT,
+					 i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT,
 					 cache_level);
 
 	obj->has_global_gtt_mapping = 1;
@@ -563,7 +563,7 @@ void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	dev_priv->gtt.gtt_clear_range(obj->base.dev,
-				      obj->gtt_space->start >> PAGE_SHIFT,
+				      i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT,
 				      obj->base.size >> PAGE_SHIFT);
 
 	obj->has_global_gtt_mapping = 0;
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 537545be69d..92a8d279ca3 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -268,18 +268,18 @@ i915_gem_object_fence_ok(struct drm_i915_gem_object *obj, int tiling_mode)
 		return true;
 
 	if (INTEL_INFO(obj->base.dev)->gen == 3) {
-		if (obj->gtt_offset & ~I915_FENCE_START_MASK)
+		if (i915_gem_obj_ggtt_offset(obj) & ~I915_FENCE_START_MASK)
 			return false;
 	} else {
-		if (obj->gtt_offset & ~I830_FENCE_START_MASK)
+		if (i915_gem_obj_ggtt_offset(obj) & ~I830_FENCE_START_MASK)
 			return false;
 	}
 
 	size = i915_gem_get_gtt_size(obj->base.dev, obj->base.size, tiling_mode);
-	if (obj->gtt_space->size != size)
+	if (i915_gem_obj_ggtt_size(obj) != size)
 		return false;
 
-	if (obj->gtt_offset & (size - 1))
+	if (i915_gem_obj_ggtt_offset(obj) & (size - 1))
 		return false;
 
 	return true;
@@ -359,8 +359,8 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		 */
 
 		obj->map_and_fenceable =
-			obj->gtt_space == NULL ||
-			(obj->gtt_offset + obj->base.size <= dev_priv->gtt.mappable_end &&
+			!i915_gem_obj_ggtt_bound(obj) ||
+			(i915_gem_obj_ggtt_offset(obj) + obj->base.size <= dev_priv->gtt.mappable_end &&
 			 i915_gem_object_fence_ok(obj, args->tiling_mode));
 
 		/* Rebind if we need a change of alignment */
@@ -369,7 +369,7 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 				i915_gem_get_gtt_alignment(dev, obj->base.size,
 							    args->tiling_mode,
 							    false);
-			if (obj->gtt_offset & (unfenced_alignment - 1))
+			if (i915_gem_obj_ggtt_offset(obj) & (unfenced_alignment - 1))
 				ret = i915_gem_object_unbind(obj);
 		}
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index c2e11a0fa40..4aedd387c8b 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1520,7 +1520,7 @@ i915_error_object_create_sized(struct drm_i915_private *dev_priv,
 	if (dst == NULL)
 		return NULL;
 
-	reloc_offset = src->gtt_offset;
+	reloc_offset = dst->gtt_offset = i915_gem_obj_ggtt_offset(src);
 	for (i = 0; i < num_pages; i++) {
 		unsigned long flags;
 		void *d;
@@ -1572,7 +1572,6 @@ i915_error_object_create_sized(struct drm_i915_private *dev_priv,
 		reloc_offset += PAGE_SIZE;
 	}
 	dst->page_count = num_pages;
-	dst->gtt_offset = src->gtt_offset;
 
 	return dst;
 
@@ -1626,7 +1625,7 @@ static void capture_bo(struct drm_i915_error_buffer *err,
 	err->name = obj->base.name;
 	err->rseqno = obj->last_read_seqno;
 	err->wseqno = obj->last_write_seqno;
-	err->gtt_offset = obj->gtt_offset;
+	err->gtt_offset = i915_gem_obj_ggtt_offset(obj);
 	err->read_domains = obj->base.read_domains;
 	err->write_domain = obj->base.write_domain;
 	err->fence_reg = obj->fence_reg;
@@ -1724,8 +1723,8 @@ i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
 			return NULL;
 
 		obj = ring->private;
-		if (acthd >= obj->gtt_offset &&
-		    acthd < obj->gtt_offset + obj->base.size)
+		if (acthd >= i915_gem_obj_ggtt_offset(obj) &&
+		    acthd < i915_gem_obj_ggtt_offset(obj) + obj->base.size)
 			return i915_error_object_create(dev_priv, obj);
 	}
 
@@ -1806,7 +1805,7 @@ static void i915_gem_record_active_context(struct intel_ring_buffer *ring,
 		return;
 
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		if ((error->ccid & PAGE_MASK) == obj->gtt_offset) {
+		if ((error->ccid & PAGE_MASK) == i915_gem_obj_ggtt_offset(obj)) {
 			ering->ctx = i915_error_object_create_sized(dev_priv,
 								    obj, 1);
 			break;
@@ -2160,10 +2159,10 @@ static void __always_unused i915_pageflip_stall_check(struct drm_device *dev, in
 	if (INTEL_INFO(dev)->gen >= 4) {
 		int dspsurf = DSPSURF(intel_crtc->plane);
 		stall_detected = I915_HI_DISPBASE(I915_READ(dspsurf)) ==
-					obj->gtt_offset;
+					i915_gem_obj_ggtt_offset(obj);
 	} else {
 		int dspaddr = DSPADDR(intel_crtc->plane);
-		stall_detected = I915_READ(dspaddr) == (obj->gtt_offset +
+		stall_detected = I915_READ(dspaddr) == (i915_gem_obj_ggtt_offset(obj) +
 							crtc->y * crtc->fb->pitches[0] +
 							crtc->x * crtc->fb->bits_per_pixel/8);
 	}
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 3db4a681771..7d283b5fcbf 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -46,8 +46,8 @@ TRACE_EVENT(i915_gem_object_bind,
 
 	    TP_fast_assign(
 			   __entry->obj = obj;
-			   __entry->offset = obj->gtt_space->start;
-			   __entry->size = obj->gtt_space->size;
+			   __entry->offset = i915_gem_obj_ggtt_offset(obj);
+			   __entry->size = i915_gem_obj_ggtt_size(obj);
 			   __entry->mappable = mappable;
 			   ),
 
@@ -68,8 +68,8 @@ TRACE_EVENT(i915_gem_object_unbind,
 
 	    TP_fast_assign(
 			   __entry->obj = obj;
-			   __entry->offset = obj->gtt_space->start;
-			   __entry->size = obj->gtt_space->size;
+			   __entry->offset = i915_gem_obj_ggtt_offset(obj);
+			   __entry->size = i915_gem_obj_ggtt_size(obj);
 			   ),
 
 	    TP_printk("obj=%p, offset=%08x size=%x",
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index aaa9a752b7b..a45bb92f35a 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1980,16 +1980,17 @@ static int i9xx_update_plane(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 		intel_crtc->dspaddr_offset = linear_offset;
 	}
 
-	DRM_DEBUG_KMS("Writing base %08X %08lX %d %d %d\n",
-		      obj->gtt_offset, linear_offset, x, y, fb->pitches[0]);
+	DRM_DEBUG_KMS("Writing base %08lX %08lX %d %d %d\n",
+		      i915_gem_obj_ggtt_offset(obj), linear_offset, x, y,
+		      fb->pitches[0]);
 	I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]);
 	if (INTEL_INFO(dev)->gen >= 4) {
 		I915_MODIFY_DISPBASE(DSPSURF(plane),
-				     obj->gtt_offset + intel_crtc->dspaddr_offset);
+				     i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 		I915_WRITE(DSPTILEOFF(plane), (y << 16) | x);
 		I915_WRITE(DSPLINOFF(plane), linear_offset);
 	} else
-		I915_WRITE(DSPADDR(plane), obj->gtt_offset + linear_offset);
+		I915_WRITE(DSPADDR(plane), i915_gem_obj_ggtt_offset(obj) + linear_offset);
 	POSTING_READ(reg);
 
 	return 0;
@@ -2069,11 +2070,12 @@ static int ironlake_update_plane(struct drm_crtc *crtc,
 					       fb->pitches[0]);
 	linear_offset -= intel_crtc->dspaddr_offset;
 
-	DRM_DEBUG_KMS("Writing base %08X %08lX %d %d %d\n",
-		      obj->gtt_offset, linear_offset, x, y, fb->pitches[0]);
+	DRM_DEBUG_KMS("Writing base %08lX %08lX %d %d %d\n",
+		      i915_gem_obj_ggtt_offset(obj), linear_offset, x, y,
+		      fb->pitches[0]);
 	I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]);
 	I915_MODIFY_DISPBASE(DSPSURF(plane),
-			     obj->gtt_offset + intel_crtc->dspaddr_offset);
+			     i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 	if (IS_HASWELL(dev)) {
 		I915_WRITE(DSPOFFSET(plane), (y << 16) | x);
 	} else {
@@ -6567,7 +6569,7 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc,
 			goto fail_unpin;
 		}
 
-		addr = obj->gtt_offset;
+		addr = i915_gem_obj_ggtt_offset(obj);
 	} else {
 		int align = IS_I830(dev) ? 16 * 1024 : 256;
 		ret = i915_gem_attach_phys_object(dev, obj,
@@ -7339,7 +7341,7 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
-	intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 	intel_ring_emit(ring, 0); /* aux display base address, unused */
 
 	intel_mark_page_flip_active(intel_crtc);
@@ -7380,7 +7382,7 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
-	intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 	intel_ring_emit(ring, MI_NOOP);
 
 	intel_mark_page_flip_active(intel_crtc);
@@ -7420,7 +7422,7 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
 	intel_ring_emit(ring,
-			(obj->gtt_offset + intel_crtc->dspaddr_offset) |
+			(i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset) |
 			obj->tiling_mode);
 
 	/* XXX Enabling the panel-fitter across page-flip is so far
@@ -7463,7 +7465,7 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0] | obj->tiling_mode);
-	intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 
 	/* Contrary to the suggestions in the documentation,
 	 * "Enable Panel Fitter" does not seem to be required when page
@@ -7528,7 +7530,7 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
 
 	intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | plane_bit);
 	intel_ring_emit(ring, (fb->pitches[0] | obj->tiling_mode));
-	intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 	intel_ring_emit(ring, (MI_NOOP));
 
 	intel_mark_page_flip_active(intel_crtc);
diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c
index dff669e2387..f3c97e05b0d 100644
--- a/drivers/gpu/drm/i915/intel_fb.c
+++ b/drivers/gpu/drm/i915/intel_fb.c
@@ -139,11 +139,11 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	info->apertures->ranges[0].base = dev->mode_config.fb_base;
 	info->apertures->ranges[0].size = dev_priv->gtt.mappable_end;
 
-	info->fix.smem_start = dev->mode_config.fb_base + obj->gtt_offset;
+	info->fix.smem_start = dev->mode_config.fb_base + i915_gem_obj_ggtt_offset(obj);
 	info->fix.smem_len = size;
 
 	info->screen_base =
-		ioremap_wc(dev_priv->gtt.mappable_base + obj->gtt_offset,
+		ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj),
 			   size);
 	if (!info->screen_base) {
 		ret = -ENOSPC;
@@ -166,9 +166,9 @@ static int intelfb_create(struct drm_fb_helper *helper,
 
 	/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
 
-	DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08x, bo %p\n",
+	DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08lx, bo %p\n",
 		      fb->width, fb->height,
-		      obj->gtt_offset, obj);
+		      i915_gem_obj_ggtt_offset(obj), obj);
 
 
 	mutex_unlock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index a3698812e9c..81c3ca14fa9 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -196,7 +196,7 @@ intel_overlay_map_regs(struct intel_overlay *overlay)
 		regs = (struct overlay_registers __iomem *)overlay->reg_bo->phys_obj->handle->vaddr;
 	else
 		regs = io_mapping_map_wc(dev_priv->gtt.mappable,
-					 overlay->reg_bo->gtt_offset);
+					 i915_gem_obj_ggtt_offset(overlay->reg_bo));
 
 	return regs;
 }
@@ -740,7 +740,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	swidth = params->src_w;
 	swidthsw = calc_swidthsw(overlay->dev, params->offset_Y, tmp_width);
 	sheight = params->src_h;
-	iowrite32(new_bo->gtt_offset + params->offset_Y, &regs->OBUF_0Y);
+	iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_Y, &regs->OBUF_0Y);
 	ostride = params->stride_Y;
 
 	if (params->format & I915_OVERLAY_YUV_PLANAR) {
@@ -754,8 +754,8 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 				      params->src_w/uv_hscale);
 		swidthsw |= max_t(u32, tmp_U, tmp_V) << 16;
 		sheight |= (params->src_h/uv_vscale) << 16;
-		iowrite32(new_bo->gtt_offset + params->offset_U, &regs->OBUF_0U);
-		iowrite32(new_bo->gtt_offset + params->offset_V, &regs->OBUF_0V);
+		iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_U, &regs->OBUF_0U);
+		iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_V, &regs->OBUF_0V);
 		ostride |= params->stride_UV << 16;
 	}
 
@@ -1355,7 +1355,7 @@ void intel_setup_overlay(struct drm_device *dev)
 			DRM_ERROR("failed to pin overlay register bo\n");
 			goto out_free_bo;
 		}
-		overlay->flip_addr = reg_bo->gtt_offset;
+		overlay->flip_addr = i915_gem_obj_ggtt_offset(reg_bo);
 
 		ret = i915_gem_object_set_to_gtt_domain(reg_bo, true);
 		if (ret) {
@@ -1435,7 +1435,7 @@ intel_overlay_map_regs_atomic(struct intel_overlay *overlay)
 			overlay->reg_bo->phys_obj->handle->vaddr;
 	else
 		regs = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
-						overlay->reg_bo->gtt_offset);
+						i915_gem_obj_ggtt_offset(overlay->reg_bo));
 
 	return regs;
 }
@@ -1468,7 +1468,7 @@ intel_overlay_capture_error_state(struct drm_device *dev)
 	if (OVERLAY_NEEDS_PHYSICAL(overlay->dev))
 		error->base = (__force long)overlay->reg_bo->phys_obj->handle->vaddr;
 	else
-		error->base = overlay->reg_bo->gtt_offset;
+		error->base = i915_gem_obj_ggtt_offset(overlay->reg_bo);
 
 	regs = intel_overlay_map_regs_atomic(overlay);
 	if (!regs)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 0eed35da3ea..125a741eed8 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -218,7 +218,7 @@ static void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 		   (stall_watermark << DPFC_RECOMP_STALL_WM_SHIFT) |
 		   (interval << DPFC_RECOMP_TIMER_COUNT_SHIFT));
 	I915_WRITE(ILK_DPFC_FENCE_YOFF, crtc->y);
-	I915_WRITE(ILK_FBC_RT_BASE, obj->gtt_offset | ILK_FBC_RT_VALID);
+	I915_WRITE(ILK_FBC_RT_BASE, i915_gem_obj_ggtt_offset(obj) | ILK_FBC_RT_VALID);
 	/* enable it... */
 	I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
 
@@ -275,7 +275,7 @@ static void gen7_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	struct drm_i915_gem_object *obj = intel_fb->obj;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
-	I915_WRITE(IVB_FBC_RT_BASE, obj->gtt_offset);
+	I915_WRITE(IVB_FBC_RT_BASE, i915_gem_obj_ggtt_offset(obj));
 
 	I915_WRITE(ILK_DPFC_CONTROL, DPFC_CTL_EN | DPFC_CTL_LIMIT_1X |
 		   IVB_DPFC_CTL_FENCE_EN |
@@ -3700,7 +3700,7 @@ static void ironlake_enable_rc6(struct drm_device *dev)
 
 	intel_ring_emit(ring, MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN);
 	intel_ring_emit(ring, MI_SET_CONTEXT);
-	intel_ring_emit(ring, dev_priv->ips.renderctx->gtt_offset |
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(dev_priv->ips.renderctx) |
 			MI_MM_SPACE_GTT |
 			MI_SAVE_EXT_STATE_EN |
 			MI_RESTORE_EXT_STATE_EN |
@@ -3723,7 +3723,7 @@ static void ironlake_enable_rc6(struct drm_device *dev)
 		return;
 	}
 
-	I915_WRITE(PWRCTXA, dev_priv->ips.pwrctx->gtt_offset | PWRCTX_EN);
+	I915_WRITE(PWRCTXA, i915_gem_obj_ggtt_offset(dev_priv->ips.pwrctx) | PWRCTX_EN);
 	I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index e51ab552046..54495df2403 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -424,14 +424,14 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 	 * registers with the above sequence (the readback of the HEAD registers
 	 * also enforces ordering), otherwise the hw might lose the new ring
 	 * register values. */
-	I915_WRITE_START(ring, obj->gtt_offset);
+	I915_WRITE_START(ring, i915_gem_obj_ggtt_offset(obj));
 	I915_WRITE_CTL(ring,
 			((ring->size - PAGE_SIZE) & RING_NR_PAGES)
 			| RING_VALID);
 
 	/* If the head is still not zero, the ring is dead */
 	if (wait_for((I915_READ_CTL(ring) & RING_VALID) != 0 &&
-		     I915_READ_START(ring) == obj->gtt_offset &&
+		     I915_READ_START(ring) == i915_gem_obj_ggtt_offset(obj) &&
 		     (I915_READ_HEAD(ring) & HEAD_ADDR) == 0, 50)) {
 		DRM_ERROR("%s initialization failed "
 				"ctl %08x head %08x tail %08x start %08x\n",
@@ -489,7 +489,7 @@ init_pipe_control(struct intel_ring_buffer *ring)
 	if (ret)
 		goto err_unref;
 
-	pc->gtt_offset = obj->gtt_offset;
+	pc->gtt_offset = i915_gem_obj_ggtt_offset(obj);
 	pc->cpu_page = kmap(sg_page(obj->pages->sgl));
 	if (pc->cpu_page == NULL) {
 		ret = -ENOMEM;
@@ -1129,7 +1129,7 @@ i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
 		intel_ring_advance(ring);
 	} else {
 		struct drm_i915_gem_object *obj = ring->private;
-		u32 cs_offset = obj->gtt_offset;
+		u32 cs_offset = i915_gem_obj_ggtt_offset(obj);
 
 		if (len > I830_BATCH_LIMIT)
 			return -ENOSPC;
@@ -1214,7 +1214,7 @@ static int init_status_page(struct intel_ring_buffer *ring)
 		goto err_unref;
 	}
 
-	ring->status_page.gfx_addr = obj->gtt_offset;
+	ring->status_page.gfx_addr = i915_gem_obj_ggtt_offset(obj);
 	ring->status_page.page_addr = kmap(sg_page(obj->pages->sgl));
 	if (ring->status_page.page_addr == NULL) {
 		ret = -ENOMEM;
@@ -1308,7 +1308,7 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 		goto err_unpin;
 
 	ring->virtual_start =
-		ioremap_wc(dev_priv->gtt.mappable_base + obj->gtt_offset,
+		ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj),
 			   ring->size);
 	if (ring->virtual_start == NULL) {
 		DRM_ERROR("Failed to map ringbuffer.\n");
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 1fa5612a457..55bdf70b548 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -133,7 +133,7 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_framebuffer *fb,
 
 	I915_WRITE(SPSIZE(pipe, plane), (crtc_h << 16) | crtc_w);
 	I915_WRITE(SPCNTR(pipe, plane), sprctl);
-	I915_MODIFY_DISPBASE(SPSURF(pipe, plane), obj->gtt_offset +
+	I915_MODIFY_DISPBASE(SPSURF(pipe, plane), i915_gem_obj_ggtt_offset(obj) +
 			     sprsurf_offset);
 	POSTING_READ(SPSURF(pipe, plane));
 }
@@ -308,7 +308,8 @@ ivb_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
 	if (intel_plane->can_scale)
 		I915_WRITE(SPRSCALE(pipe), sprscale);
 	I915_WRITE(SPRCTL(pipe), sprctl);
-	I915_MODIFY_DISPBASE(SPRSURF(pipe), obj->gtt_offset + sprsurf_offset);
+	I915_MODIFY_DISPBASE(SPRSURF(pipe),
+			     i915_gem_obj_ggtt_offset(obj) + sprsurf_offset);
 	POSTING_READ(SPRSURF(pipe));
 
 	/* potentially re-enable LP watermarks */
@@ -478,7 +479,8 @@ ilk_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
 	I915_WRITE(DVSSIZE(pipe), (crtc_h << 16) | crtc_w);
 	I915_WRITE(DVSSCALE(pipe), dvsscale);
 	I915_WRITE(DVSCNTR(pipe), dvscntr);
-	I915_MODIFY_DISPBASE(DVSSURF(pipe), obj->gtt_offset + dvssurf_offset);
+	I915_MODIFY_DISPBASE(DVSSURF(pipe),
+			     i915_gem_obj_ggtt_offset(obj) + dvssurf_offset);
 	POSTING_READ(DVSSURF(pipe));
 }
 
-- 
cgit v1.2.3-70-g09d2


From 59cdb63d529c81fc8ac0620ad50f29d5fb4411c9 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 4 Jul 2013 23:35:28 +0200
Subject: drm/i915: kill dev_priv->rps.lock

Now that the rps interrupt locking isn't clearly separated (at elast
conceptually) from all the other interrupt locking having a different
lock stopped making sense: It protects much more than just the rps
workqueue it started out with. But with the addition of VECS the
separation started to blurr and resulted in some more complex locking
for the ring interrupt refcount.

With this we can (again) unifiy the ringbuffer irq refcounts without
causing a massive confusion, but that's for the next patch.

v2: Explain better why the rps.lock once made sense and why no longer,
requested by Ben.

Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_dma.c         |  1 -
 drivers/gpu/drm/i915/i915_drv.h         |  8 ++++----
 drivers/gpu/drm/i915/i915_irq.c         | 12 ++++++------
 drivers/gpu/drm/i915/intel_pm.c         | 16 ++++++++--------
 drivers/gpu/drm/i915/intel_ringbuffer.c |  8 ++++----
 drivers/gpu/drm/i915/intel_ringbuffer.h |  2 +-
 6 files changed, 23 insertions(+), 24 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index bece9973e1b..6ce90330632 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1607,7 +1607,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 
 	spin_lock_init(&dev_priv->irq_lock);
 	spin_lock_init(&dev_priv->gpu_error.lock);
-	spin_lock_init(&dev_priv->rps.lock);
 	spin_lock_init(&dev_priv->backlight.lock);
 	mutex_init(&dev_priv->dpio_lock);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f2f1be11010..846500a8586 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -743,12 +743,12 @@ struct i915_suspend_saved_registers {
 };
 
 struct intel_gen6_power_mgmt {
+	/* work and pm_iir are protected by dev_priv->irq_lock */
 	struct work_struct work;
-	struct delayed_work vlv_work;
 	u32 pm_iir;
-	/* lock - irqsave spinlock that protectects the work_struct and
-	 * pm_iir. */
-	spinlock_t lock;
+
+	/* On vlv we need to manually drop to Vmin with a delayed work. */
+	struct delayed_work vlv_work;
 
 	/* The below variables an all the rps hw state are protected by
 	 * dev->struct mutext. */
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 04861995fe1..f4d5569834c 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -719,13 +719,13 @@ static void gen6_pm_rps_work(struct work_struct *work)
 	u32 pm_iir, pm_imr;
 	u8 new_delay;
 
-	spin_lock_irq(&dev_priv->rps.lock);
+	spin_lock_irq(&dev_priv->irq_lock);
 	pm_iir = dev_priv->rps.pm_iir;
 	dev_priv->rps.pm_iir = 0;
 	pm_imr = I915_READ(GEN6_PMIMR);
 	/* Make sure not to corrupt PMIMR state used by ringbuffer code */
 	I915_WRITE(GEN6_PMIMR, pm_imr & ~GEN6_PM_RPS_EVENTS);
-	spin_unlock_irq(&dev_priv->rps.lock);
+	spin_unlock_irq(&dev_priv->irq_lock);
 
 	if ((pm_iir & GEN6_PM_RPS_EVENTS) == 0)
 		return;
@@ -887,11 +887,11 @@ static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv,
 	 * The mask bit in IMR is cleared by dev_priv->rps.work.
 	 */
 
-	spin_lock(&dev_priv->rps.lock);
+	spin_lock(&dev_priv->irq_lock);
 	dev_priv->rps.pm_iir |= pm_iir;
 	I915_WRITE(GEN6_PMIMR, dev_priv->rps.pm_iir);
 	POSTING_READ(GEN6_PMIMR);
-	spin_unlock(&dev_priv->rps.lock);
+	spin_unlock(&dev_priv->irq_lock);
 
 	queue_work(dev_priv->wq, &dev_priv->rps.work);
 }
@@ -964,12 +964,12 @@ static void hsw_pm_irq_handler(struct drm_i915_private *dev_priv,
 			       u32 pm_iir)
 {
 	if (pm_iir & GEN6_PM_RPS_EVENTS) {
-		spin_lock(&dev_priv->rps.lock);
+		spin_lock(&dev_priv->irq_lock);
 		dev_priv->rps.pm_iir |= pm_iir & GEN6_PM_RPS_EVENTS;
 		I915_WRITE(GEN6_PMIMR, dev_priv->rps.pm_iir);
 		/* never want to mask useful interrupts. (also posting read) */
 		WARN_ON(I915_READ_NOTRACE(GEN6_PMIMR) & ~GEN6_PM_RPS_EVENTS);
-		spin_unlock(&dev_priv->rps.lock);
+		spin_unlock(&dev_priv->irq_lock);
 
 		queue_work(dev_priv->wq, &dev_priv->rps.work);
 	}
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 125a741eed8..a9be0d1c173 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3135,9 +3135,9 @@ static void gen6_disable_rps(struct drm_device *dev)
 	 * register (PMIMR) to mask PM interrupts. The only risk is in leaving
 	 * stale bits in PMIIR and PMIMR which gen6_enable_rps will clean up. */
 
-	spin_lock_irq(&dev_priv->rps.lock);
+	spin_lock_irq(&dev_priv->irq_lock);
 	dev_priv->rps.pm_iir = 0;
-	spin_unlock_irq(&dev_priv->rps.lock);
+	spin_unlock_irq(&dev_priv->irq_lock);
 
 	I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS);
 }
@@ -3154,9 +3154,9 @@ static void valleyview_disable_rps(struct drm_device *dev)
 	 * register (PMIMR) to mask PM interrupts. The only risk is in leaving
 	 * stale bits in PMIIR and PMIMR which gen6_enable_rps will clean up. */
 
-	spin_lock_irq(&dev_priv->rps.lock);
+	spin_lock_irq(&dev_priv->irq_lock);
 	dev_priv->rps.pm_iir = 0;
-	spin_unlock_irq(&dev_priv->rps.lock);
+	spin_unlock_irq(&dev_priv->irq_lock);
 
 	I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR));
 
@@ -3321,13 +3321,13 @@ static void gen6_enable_rps(struct drm_device *dev)
 
 	/* requires MSI enabled */
 	I915_WRITE(GEN6_PMIER, I915_READ(GEN6_PMIER) | GEN6_PM_RPS_EVENTS);
-	spin_lock_irq(&dev_priv->rps.lock);
+	spin_lock_irq(&dev_priv->irq_lock);
 	/* FIXME: Our interrupt enabling sequence is bonghits.
 	 * dev_priv->rps.pm_iir really should be 0 here. */
 	dev_priv->rps.pm_iir = 0;
 	I915_WRITE(GEN6_PMIMR, I915_READ(GEN6_PMIMR) & ~GEN6_PM_RPS_EVENTS);
 	I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS);
-	spin_unlock_irq(&dev_priv->rps.lock);
+	spin_unlock_irq(&dev_priv->irq_lock);
 	/* unmask all PM interrupts */
 	I915_WRITE(GEN6_PMINTRMSK, 0);
 
@@ -3601,10 +3601,10 @@ static void valleyview_enable_rps(struct drm_device *dev)
 
 	/* requires MSI enabled */
 	I915_WRITE(GEN6_PMIER, GEN6_PM_RPS_EVENTS);
-	spin_lock_irq(&dev_priv->rps.lock);
+	spin_lock_irq(&dev_priv->irq_lock);
 	WARN_ON(dev_priv->rps.pm_iir != 0);
 	I915_WRITE(GEN6_PMIMR, 0);
-	spin_unlock_irq(&dev_priv->rps.lock);
+	spin_unlock_irq(&dev_priv->irq_lock);
 	/* enable all PM interrupts */
 	I915_WRITE(GEN6_PMINTRMSK, 0);
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 54495df2403..33a74a80300 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1055,14 +1055,14 @@ hsw_vebox_get_irq(struct intel_ring_buffer *ring)
 	if (!dev->irq_enabled)
 		return false;
 
-	spin_lock_irqsave(&dev_priv->rps.lock, flags);
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (ring->irq_refcount.pm++ == 0) {
 		u32 pm_imr = I915_READ(GEN6_PMIMR);
 		I915_WRITE_IMR(ring, ~ring->irq_enable_mask);
 		I915_WRITE(GEN6_PMIMR, pm_imr & ~ring->irq_enable_mask);
 		POSTING_READ(GEN6_PMIMR);
 	}
-	spin_unlock_irqrestore(&dev_priv->rps.lock, flags);
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
 	return true;
 }
@@ -1077,14 +1077,14 @@ hsw_vebox_put_irq(struct intel_ring_buffer *ring)
 	if (!dev->irq_enabled)
 		return;
 
-	spin_lock_irqsave(&dev_priv->rps.lock, flags);
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount.pm == 0) {
 		u32 pm_imr = I915_READ(GEN6_PMIMR);
 		I915_WRITE_IMR(ring, ~0);
 		I915_WRITE(GEN6_PMIMR, pm_imr | ring->irq_enable_mask);
 		POSTING_READ(GEN6_PMIMR);
 	}
-	spin_unlock_irqrestore(&dev_priv->rps.lock, flags);
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 }
 
 static int
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 799f04c9da4..8a87b3f9974 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -80,7 +80,7 @@ struct  intel_ring_buffer {
 
 	struct {
 		u32	gt; /*  protected by dev_priv->irq_lock */
-		u32	pm; /*  protected by dev_priv->rps.lock (sucks) */
+		u32	pm; /*  protected by dev_priv->irq_lock */
 	} irq_refcount;
 	u32		irq_enable_mask;	/* bitmask to enable ring interrupt */
 	u32		trace_irq_seqno;
-- 
cgit v1.2.3-70-g09d2


From 0a9a8c91a5f9617d6fa319fe052de38691fb29cb Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Fri, 12 Jul 2013 22:43:26 +0200
Subject: drm/i915: unify GT/PM irq postinstall code

Again extract a common helper. For the postinstall hook things are a
bit more complicated since we have more cases on ilk-hsw/vlv here.

But since vlv was clearly broken by failing to initialize
dev_priv->gt_irq_mask correctly the shared code is clearly justified.

Also kill the PMIER setting in the async rps enable work. I should
have been save, but also clearly looked rather fragile. PMIER setup is
now all down in the irq pre/postinstall hooks.

With this we now have the usual interrupt register sequence for GT/PM
irq registers:

- IER is setup once with all the interrupts we ever need in the
  postinstall hook and never touched again. Exceptions are SDEIER,
  which is touched in the preinstall hook (when the irq handler isn't
  enabled) and then only from the irq handler. And DEIER/VLV_IER with
  is used in the irq handler but also written to once in the
  postinstall hook. But since that write is essentially what enables
  the interrupt and we should always have MSI interrupts we should be
  save. In case we ever have non-MSI interrupts we'd be screwed.

- IIR is cleared in the postinstall hook before we enable/unmask the
  respective interrupt sources. Hence we can't steal an interrupt
  event an accidentally trigger the spurious interrupt logic in the
  core kernel. Note that after some discussion with Ben Widawsky we
  think that we actually should clear the IIR registers in the
  preinstall hook. But doing that is a much larger patch series.

- IMR regs are (usually) all masked off. Those are the only regs
  changed at runtime, which is all protected by dev_priv->irq_lock.

This unification also kills the cargo-culted read-modify-write PM
register setup for VECS. Interrupt setup is done without userspace
being able to interfere, so we better know what values we want to put
into those registers. RMW cycles otoh are really good at papering over
races, until stuff magically blows up and no one has a clue why.

v2: Touch the gen6+ PM interrupt registers only on gen6+.

v3: Improve the commit message to more clearly spell out why we want
to unify the code and what exactly changes.

Cc: Ben Widawsky <ben@bwidawsk.net>
Cc: Paulo Zanoni <przanoni@gmail.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Add a comment to explain why the l3 parity interrupt is
special.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_irq.c | 93 +++++++++++++++++++----------------------
 drivers/gpu/drm/i915/intel_pm.c |  4 --
 2 files changed, 43 insertions(+), 54 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 0d54a550ec6..b388641e060 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2196,6 +2196,46 @@ static void ibx_irq_postinstall(struct drm_device *dev)
 	I915_WRITE(SDEIMR, ~mask);
 }
 
+static void gen5_gt_irq_postinstall(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 pm_irqs, gt_irqs;
+
+	pm_irqs = gt_irqs = 0;
+
+	dev_priv->gt_irq_mask = ~0;
+	if (HAS_L3_GPU_CACHE(dev)) {
+		/* L3 parity interrupt is always unmasked. */
+		dev_priv->gt_irq_mask = ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
+		gt_irqs |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
+	}
+
+	gt_irqs |= GT_RENDER_USER_INTERRUPT;
+	if (IS_GEN5(dev)) {
+		gt_irqs |= GT_RENDER_PIPECTL_NOTIFY_INTERRUPT |
+			   ILK_BSD_USER_INTERRUPT;
+	} else {
+		gt_irqs |= GT_BLT_USER_INTERRUPT | GT_BSD_USER_INTERRUPT;
+	}
+
+	I915_WRITE(GTIIR, I915_READ(GTIIR));
+	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
+	I915_WRITE(GTIER, gt_irqs);
+	POSTING_READ(GTIER);
+
+	if (INTEL_INFO(dev)->gen >= 6) {
+		pm_irqs |= GEN6_PM_RPS_EVENTS;
+
+		if (HAS_VEBOX(dev))
+			pm_irqs |= PM_VEBOX_USER_INTERRUPT;
+
+		I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR));
+		I915_WRITE(GEN6_PMIMR, 0xffffffff);
+		I915_WRITE(GEN6_PMIER, pm_irqs);
+		POSTING_READ(GEN6_PMIER);
+	}
+}
+
 static int ironlake_irq_postinstall(struct drm_device *dev)
 {
 	unsigned long irqflags;
@@ -2206,7 +2246,6 @@ static int ironlake_irq_postinstall(struct drm_device *dev)
 			   DE_PLANEA_FLIP_DONE | DE_PLANEB_FLIP_DONE |
 			   DE_AUX_CHANNEL_A | DE_PIPEB_FIFO_UNDERRUN |
 			   DE_PIPEA_FIFO_UNDERRUN | DE_POISON;
-	u32 gt_irqs;
 
 	dev_priv->irq_mask = ~display_mask;
 
@@ -2217,21 +2256,7 @@ static int ironlake_irq_postinstall(struct drm_device *dev)
 			  DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT);
 	POSTING_READ(DEIER);
 
-	dev_priv->gt_irq_mask = ~0;
-
-	I915_WRITE(GTIIR, I915_READ(GTIIR));
-	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-
-	gt_irqs = GT_RENDER_USER_INTERRUPT;
-
-	if (IS_GEN6(dev))
-		gt_irqs |= GT_BLT_USER_INTERRUPT | GT_BSD_USER_INTERRUPT;
-	else
-		gt_irqs |= GT_RENDER_PIPECTL_NOTIFY_INTERRUPT |
-			   ILK_BSD_USER_INTERRUPT;
-
-	I915_WRITE(GTIER, gt_irqs);
-	POSTING_READ(GTIER);
+	gen5_gt_irq_postinstall(dev);
 
 	ibx_irq_postinstall(dev);
 
@@ -2260,8 +2285,6 @@ static int ivybridge_irq_postinstall(struct drm_device *dev)
 		DE_PLANEA_FLIP_DONE_IVB |
 		DE_AUX_CHANNEL_A_IVB |
 		DE_ERR_INT_IVB;
-	u32 pm_irqs = GEN6_PM_RPS_EVENTS;
-	u32 gt_irqs;
 
 	dev_priv->irq_mask = ~display_mask;
 
@@ -2276,30 +2299,7 @@ static int ivybridge_irq_postinstall(struct drm_device *dev)
 		   DE_PIPEA_VBLANK_IVB);
 	POSTING_READ(DEIER);
 
-	dev_priv->gt_irq_mask = ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
-
-	I915_WRITE(GTIIR, I915_READ(GTIIR));
-	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-
-	gt_irqs = GT_RENDER_USER_INTERRUPT | GT_BSD_USER_INTERRUPT |
-		  GT_BLT_USER_INTERRUPT | GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
-	I915_WRITE(GTIER, gt_irqs);
-	POSTING_READ(GTIER);
-
-	I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR));
-	if (HAS_VEBOX(dev))
-		pm_irqs |= PM_VEBOX_USER_INTERRUPT;
-
-	/* Our enable/disable rps functions may touch these registers so
-	 * make sure to set a known state for only the non-RPS bits.
-	 * The RMW is extra paranoia since this should be called after being set
-	 * to a known state in preinstall.
-	 * */
-	I915_WRITE(GEN6_PMIMR,
-		   (I915_READ(GEN6_PMIMR) | ~GEN6_PM_RPS_EVENTS) & ~pm_irqs);
-	I915_WRITE(GEN6_PMIER,
-		   (I915_READ(GEN6_PMIER) & GEN6_PM_RPS_EVENTS) | pm_irqs);
-	POSTING_READ(GEN6_PMIER);
+	gen5_gt_irq_postinstall(dev);
 
 	ibx_irq_postinstall(dev);
 
@@ -2309,7 +2309,6 @@ static int ivybridge_irq_postinstall(struct drm_device *dev)
 static int valleyview_irq_postinstall(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
-	u32 gt_irqs;
 	u32 enable_mask;
 	u32 pipestat_enable = PLANE_FLIP_DONE_INT_EN_VLV;
 	unsigned long irqflags;
@@ -2349,13 +2348,7 @@ static int valleyview_irq_postinstall(struct drm_device *dev)
 	I915_WRITE(VLV_IIR, 0xffffffff);
 	I915_WRITE(VLV_IIR, 0xffffffff);
 
-	I915_WRITE(GTIIR, I915_READ(GTIIR));
-	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-
-	gt_irqs = GT_RENDER_USER_INTERRUPT | GT_BSD_USER_INTERRUPT |
-		GT_BLT_USER_INTERRUPT;
-	I915_WRITE(GTIER, gt_irqs);
-	POSTING_READ(GTIER);
+	gen5_gt_irq_postinstall(dev);
 
 	/* ack & enable invalid PTE error interrupts */
 #if 0 /* FIXME: add support to irq handler for checking these bits */
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index a9be0d1c173..96f08724e49 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3319,8 +3319,6 @@ static void gen6_enable_rps(struct drm_device *dev)
 
 	gen6_set_rps(dev_priv->dev, (gt_perf_status & 0xff00) >> 8);
 
-	/* requires MSI enabled */
-	I915_WRITE(GEN6_PMIER, I915_READ(GEN6_PMIER) | GEN6_PM_RPS_EVENTS);
 	spin_lock_irq(&dev_priv->irq_lock);
 	/* FIXME: Our interrupt enabling sequence is bonghits.
 	 * dev_priv->rps.pm_iir really should be 0 here. */
@@ -3599,8 +3597,6 @@ static void valleyview_enable_rps(struct drm_device *dev)
 
 	valleyview_set_rps(dev_priv->dev, dev_priv->rps.rpe_delay);
 
-	/* requires MSI enabled */
-	I915_WRITE(GEN6_PMIER, GEN6_PM_RPS_EVENTS);
 	spin_lock_irq(&dev_priv->irq_lock);
 	WARN_ON(dev_priv->rps.pm_iir != 0);
 	I915_WRITE(GEN6_PMIMR, 0);
-- 
cgit v1.2.3-70-g09d2


From 44fc7d5cf30723563558715f0794c8389a5c15ba Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Fri, 12 Jul 2013 22:43:27 +0200
Subject: drm/i915: extract rps interrupt enable/disable helpers

The VECS enabling required some changes to how rps interrupts are
enabled/disabled since VECS interrupts are handling with the PM
interrupt registers.

But now that the pre/postinstall sequences is identical for all
platforms with rps support (snb, ivb, hsw, vlv) we can also use the
exact same sequence to actually enable the rps interrupts. Strictly
speaking using spinlocks is overkill on snb/ivb & vlv since they have
no VECS ring, but imo that's more than made up by the common code.

Hence this just unifies the vlv code with the snb-hsw code which
matched exactly before the VECS enabling. See

commit eda63ffb906c2fb3b609a0e87aeb63c0f25b9e6b
Author: Ben Widawsky <ben@bwidawsk.net>
Date:   Tue May 28 19:22:26 2013 -0700

    drm/i915: Add PM regs to pre/post install

and

commit 4848405cced3b46f4ec7d404b8ed5873171ae10a
Author: Ben Widawsky <ben@bwidawsk.net>
Date:   Tue May 28 19:22:27 2013 -0700

    drm/i915: make PM interrupt writes non-destructive

for why the gen6 code (shared between snb, ivb and hsw) needed to be
changed originally.

v3: Improve the commit message to more clearly spell out why we want
to unify the code and what exactly changes.

Cc: Paulo Zanoni <przanoni@gmail.com>
Cc: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 59 ++++++++++++++++++++---------------------
 1 file changed, 29 insertions(+), 30 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 96f08724e49..787a528e720 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3121,13 +3121,10 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
 	trace_intel_gpu_freq_change(vlv_gpu_freq(dev_priv->mem_freq, val));
 }
 
-
-static void gen6_disable_rps(struct drm_device *dev)
+static void gen6_disable_rps_interrupts(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	I915_WRITE(GEN6_RC_CONTROL, 0);
-	I915_WRITE(GEN6_RPNSWREQ, 1 << 31);
 	I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
 	I915_WRITE(GEN6_PMIER, I915_READ(GEN6_PMIER) & ~GEN6_PM_RPS_EVENTS);
 	/* Complete PM interrupt masking here doesn't race with the rps work
@@ -3142,23 +3139,23 @@ static void gen6_disable_rps(struct drm_device *dev)
 	I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS);
 }
 
-static void valleyview_disable_rps(struct drm_device *dev)
+static void gen6_disable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	I915_WRITE(GEN6_RC_CONTROL, 0);
-	I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
-	I915_WRITE(GEN6_PMIER, 0);
-	/* Complete PM interrupt masking here doesn't race with the rps work
-	 * item again unmasking PM interrupts because that is using a different
-	 * register (PMIMR) to mask PM interrupts. The only risk is in leaving
-	 * stale bits in PMIIR and PMIMR which gen6_enable_rps will clean up. */
+	I915_WRITE(GEN6_RPNSWREQ, 1 << 31);
 
-	spin_lock_irq(&dev_priv->irq_lock);
-	dev_priv->rps.pm_iir = 0;
-	spin_unlock_irq(&dev_priv->irq_lock);
+	gen6_disable_rps_interrupts(dev);
+}
+
+static void valleyview_disable_rps(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	I915_WRITE(GEN6_RC_CONTROL, 0);
 
-	I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR));
+	gen6_disable_rps_interrupts(dev);
 
 	if (dev_priv->vlv_pctx) {
 		drm_gem_object_unreference(&dev_priv->vlv_pctx->base);
@@ -3191,6 +3188,21 @@ int intel_enable_rc6(const struct drm_device *dev)
 	return (INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE);
 }
 
+static void gen6_enable_rps_interrupts(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	spin_lock_irq(&dev_priv->irq_lock);
+	/* FIXME: Our interrupt enabling sequence is bonghits.
+	 * dev_priv->rps.pm_iir really should be 0 here. */
+	dev_priv->rps.pm_iir = 0;
+	I915_WRITE(GEN6_PMIMR, I915_READ(GEN6_PMIMR) & ~GEN6_PM_RPS_EVENTS);
+	I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS);
+	spin_unlock_irq(&dev_priv->irq_lock);
+	/* unmask all PM interrupts */
+	I915_WRITE(GEN6_PMINTRMSK, 0);
+}
+
 static void gen6_enable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3319,15 +3331,7 @@ static void gen6_enable_rps(struct drm_device *dev)
 
 	gen6_set_rps(dev_priv->dev, (gt_perf_status & 0xff00) >> 8);
 
-	spin_lock_irq(&dev_priv->irq_lock);
-	/* FIXME: Our interrupt enabling sequence is bonghits.
-	 * dev_priv->rps.pm_iir really should be 0 here. */
-	dev_priv->rps.pm_iir = 0;
-	I915_WRITE(GEN6_PMIMR, I915_READ(GEN6_PMIMR) & ~GEN6_PM_RPS_EVENTS);
-	I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS);
-	spin_unlock_irq(&dev_priv->irq_lock);
-	/* unmask all PM interrupts */
-	I915_WRITE(GEN6_PMINTRMSK, 0);
+	gen6_enable_rps_interrupts(dev);
 
 	rc6vids = 0;
 	ret = sandybridge_pcode_read(dev_priv, GEN6_PCODE_READ_RC6VIDS, &rc6vids);
@@ -3597,12 +3601,7 @@ static void valleyview_enable_rps(struct drm_device *dev)
 
 	valleyview_set_rps(dev_priv->dev, dev_priv->rps.rpe_delay);
 
-	spin_lock_irq(&dev_priv->irq_lock);
-	WARN_ON(dev_priv->rps.pm_iir != 0);
-	I915_WRITE(GEN6_PMIMR, 0);
-	spin_unlock_irq(&dev_priv->irq_lock);
-	/* enable all PM interrupts */
-	I915_WRITE(GEN6_PMINTRMSK, 0);
+	gen6_enable_rps_interrupts(dev);
 
 	gen6_gt_force_wake_put(dev_priv);
 }
-- 
cgit v1.2.3-70-g09d2


From a0b3335a2141aadb8f2398ade97fe574f2ddc875 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 4 Jul 2013 23:35:34 +0200
Subject: drm/i915: simplify rps interrupt enabling/disabling sequence

At the moment we have the following interrupt enabling sequence:
1. irq preinstall hook
2. enabling the interrupt handler and calling irq postinstall hook
3. enable rps interrupts from the async work

And the folliwing disable sequence:
1. disabling the interrupt handler and calling the uninstall hook
2. disabling the rps interrupt

Since the postinstall hook now always sets up PMIIR, PMIER and PMIMR
to known-good states there no way for an interrupt to sneak in in the
enable sequence, so we can reinstate the WARN lost in

commit eda63ffb906c2fb3b609a0e87aeb63c0f25b9e6b
Author: Ben Widawsky <ben@bwidawsk.net>
Date:   Tue May 28 19:22:26 2013 -0700

    drm/i915: Add PM regs to pre/post install

Note that there's some room for future cleanups since most of the
interrupt register clearing in the disable function is rather
redundant. But that's better done in follow-up patches, if at all.

Cc: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 787a528e720..bc5aae08855 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3193,9 +3193,7 @@ static void gen6_enable_rps_interrupts(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	spin_lock_irq(&dev_priv->irq_lock);
-	/* FIXME: Our interrupt enabling sequence is bonghits.
-	 * dev_priv->rps.pm_iir really should be 0 here. */
-	dev_priv->rps.pm_iir = 0;
+	WARN_ON(dev_priv->rps.pm_iir);
 	I915_WRITE(GEN6_PMIMR, I915_READ(GEN6_PMIMR) & ~GEN6_PM_RPS_EVENTS);
 	I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS);
 	spin_unlock_irq(&dev_priv->irq_lock);
-- 
cgit v1.2.3-70-g09d2


From 7457d61748f7939dea49849db442cb3df4c7c3fe Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Fri, 7 Jun 2013 17:41:07 +0100
Subject: drm/i915: We implement WaFbcWaitForVBlankBeforeEnable for ilk and snb

We also wait for that blank on other platforms but the w/a doesn't
apply there. Not an issue at all.

Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index bc5aae08855..cae89fe9b84 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -404,6 +404,8 @@ static void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	 * following the termination of the page-flipping sequence
 	 * and indeed performing the enable as a co-routine and not
 	 * waiting synchronously upon the vblank.
+	 *
+	 * WaFbcWaitForVBlankBeforeEnable:ilk,snb
 	 */
 	schedule_delayed_work(&work->work, msecs_to_jiffies(50));
 }
-- 
cgit v1.2.3-70-g09d2


From 4bb353343dcc2486a1deda87f4c069153dc353c3 Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Fri, 14 Jun 2013 15:23:24 +0100
Subject: drm/i915: We implement WaFbcAsynchFlipDisableFbcQueue on ilk and snb

v2: Put the comment a bit closer to the actual write (Paulo Zanoni)

Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Fix space before tab.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index cae89fe9b84..d212e42638d 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4453,6 +4453,7 @@ static void ironlake_init_clock_gating(struct drm_device *dev)
 	 * The bit 7,8,9 of 0x42020.
 	 */
 	if (IS_IRONLAKE_M(dev)) {
+		/* WaFbcAsynchFlipDisableFbcQueue:ilk */
 		I915_WRITE(ILK_DISPLAY_CHICKEN1,
 			   I915_READ(ILK_DISPLAY_CHICKEN1) |
 			   ILK_FBCQ_DIS);
@@ -4589,6 +4590,8 @@ static void gen6_init_clock_gating(struct drm_device *dev)
 	 * The bit5 and bit7 of 0x42020
 	 * The bit14 of 0x70180
 	 * The bit14 of 0x71180
+	 *
+	 * WaFbcAsynchFlipDisableFbcQueue:snb
 	 */
 	I915_WRITE(ILK_DISPLAY_CHICKEN1,
 		   I915_READ(ILK_DISPLAY_CHICKEN1) |
-- 
cgit v1.2.3-70-g09d2


From f1e8fa56fd650e0a23f64afdf59f3907d9a89615 Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Fri, 7 Jun 2013 17:41:09 +0100
Subject: drm/i915: We implement WaFbcDisableDpfcClockGating on ilk

Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d212e42638d..9b95f78d352 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4416,7 +4416,10 @@ static void ironlake_init_clock_gating(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t dspclk_gate = ILK_VRHUNIT_CLOCK_GATE_DISABLE;
 
-	/* Required for FBC */
+	/*
+	 * Required for FBC
+	 * WaFbcDisableDpfcClockGating:ilk
+	 */
 	dspclk_gate |= ILK_DPFCRUNIT_CLOCK_GATE_DISABLE |
 		   ILK_DPFCUNIT_CLOCK_GATE_DISABLE |
 		   ILK_DPFDUNIT_CLOCK_GATE_ENABLE;
-- 
cgit v1.2.3-70-g09d2


From eb4926e4a6e3922398fd6880f07a84db95aa3741 Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Fri, 7 Jun 2013 17:41:14 +0100
Subject: drm/i915: Don't try to calculate RC6 residency on GEN4 and before

intel_enable_rc6() is used to check if we can compute the RC6 residency
in the sysfs code. Disable this for platforms older than Ironlake.

Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 9b95f78d352..e81d37667bc 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3167,6 +3167,10 @@ static void valleyview_disable_rps(struct drm_device *dev)
 
 int intel_enable_rc6(const struct drm_device *dev)
 {
+	/* No RC6 before Ironlake */
+	if (INTEL_INFO(dev)->gen < 5)
+		return 0;
+
 	/* Respect the kernel parameter if it is set */
 	if (i915_enable_rc6 >= 0)
 		return i915_enable_rc6;
-- 
cgit v1.2.3-70-g09d2


From 907b28c56ea40629aa6595ddfa414ec2fc7da41c Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 19 Jul 2013 20:36:52 +0100
Subject: drm/i915: Colocate all GT access routines in the same file

Currently, the register access code is split between i915_drv.c and
intel_pm.c. It only bares a superficial resemblance to the reset of the
powermanagement code, so move it all into its own file. This is to ease
further patches to enforce serialised register access.

v2: Scan for random abuse of I915_WRITE_NOTRACE
v3: Take the opportunity to rename the GT functions as uncore. Uncore is
the term used by the hardware design (and bspec) for all functions
outside of the GPU (and CPU) cores in what is also known as the System
Agent.
v4: Rebase onto SNB rc6 fixes

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Wrestle patch into applying and inline
intel_uncore_early_sanitize (plus move the old comment to the new
function). Also keep the _santize postfix for intel_uncore_sanitize.]
[danvet: Squash in fixup spotted by Chris on irc: We need to call
intel_pm_init before intel_uncore_sanitize since the later will call
cancel_work on the delayed rps setup work the former initializes.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/Makefile        |   1 +
 drivers/gpu/drm/i915/i915_debugfs.c  |  12 +-
 drivers/gpu/drm/i915/i915_dma.c      |  25 +-
 drivers/gpu/drm/i915/i915_drv.c      | 271 +----------------
 drivers/gpu/drm/i915/i915_drv.h      |  31 +-
 drivers/gpu/drm/i915/i915_irq.c      |   6 +-
 drivers/gpu/drm/i915/intel_display.c |   3 +-
 drivers/gpu/drm/i915/intel_drv.h     |   1 -
 drivers/gpu/drm/i915/intel_pm.c      | 258 +---------------
 drivers/gpu/drm/i915/intel_uncore.c  | 571 +++++++++++++++++++++++++++++++++++
 10 files changed, 614 insertions(+), 565 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/intel_uncore.c

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 9d1da7cceb2..b8449a84a0d 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -38,6 +38,7 @@ i915-y := i915_drv.o i915_dma.o i915_irq.o \
 	  intel_sprite.o \
 	  intel_opregion.o \
 	  intel_sideband.o \
+	  intel_uncore.o \
 	  dvo_ch7xxx.o \
 	  dvo_ch7017.o \
 	  dvo_ivch.o \
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 9d871c7eeae..0e904986f3e 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -989,9 +989,9 @@ static int gen6_drpc_info(struct seq_file *m)
 	if (ret)
 		return ret;
 
-	spin_lock_irq(&dev_priv->gt_lock);
-	forcewake_count = dev_priv->forcewake_count;
-	spin_unlock_irq(&dev_priv->gt_lock);
+	spin_lock_irq(&dev_priv->uncore.lock);
+	forcewake_count = dev_priv->uncore.forcewake_count;
+	spin_unlock_irq(&dev_priv->uncore.lock);
 
 	if (forcewake_count) {
 		seq_puts(m, "RC information inaccurate because somebody "
@@ -1375,9 +1375,9 @@ static int i915_gen6_forcewake_count_info(struct seq_file *m, void *data)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned forcewake_count;
 
-	spin_lock_irq(&dev_priv->gt_lock);
-	forcewake_count = dev_priv->forcewake_count;
-	spin_unlock_irq(&dev_priv->gt_lock);
+	spin_lock_irq(&dev_priv->uncore.lock);
+	forcewake_count = dev_priv->uncore.forcewake_count;
+	spin_unlock_irq(&dev_priv->uncore.lock);
 
 	seq_printf(m, "forcewake count = %u\n", forcewake_count);
 
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 1c5b3973850..8536acd0a85 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1435,22 +1435,6 @@ static void i915_dump_device_info(struct drm_i915_private *dev_priv)
 #undef SEP_COMMA
 }
 
-/**
- * intel_early_sanitize_regs - clean up BIOS state
- * @dev: DRM device
- *
- * This function must be called before we do any I915_READ or I915_WRITE. Its
- * purpose is to clean up any state left by the BIOS that may affect us when
- * reading and/or writing registers.
- */
-static void intel_early_sanitize_regs(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (HAS_FPGA_DBG_UNCLAIMED(dev))
-		I915_WRITE_NOTRACE(FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
-}
-
 /**
  * i915_driver_load - setup chip and create an initial config
  * @dev: DRM device
@@ -1493,7 +1477,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	spin_lock_init(&dev_priv->irq_lock);
 	spin_lock_init(&dev_priv->gpu_error.lock);
 	spin_lock_init(&dev_priv->backlight.lock);
-	spin_lock_init(&dev_priv->gt_lock);
+	spin_lock_init(&dev_priv->uncore.lock);
 	mutex_init(&dev_priv->dpio_lock);
 	mutex_init(&dev_priv->rps.hw_lock);
 	mutex_init(&dev_priv->modeset_restore_lock);
@@ -1529,7 +1513,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 		goto put_bridge;
 	}
 
-	intel_early_sanitize_regs(dev);
+	intel_uncore_early_sanitize(dev);
 
 	if (IS_HASWELL(dev) && (I915_READ(HSW_EDRAM_PRESENT) == 1)) {
 		/* The docs do not explain exactly how the calculation can be
@@ -1602,8 +1586,9 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	intel_detect_pch(dev);
 
 	intel_irq_init(dev);
-	intel_gt_sanitize(dev);
-	intel_gt_init(dev);
+	intel_pm_init(dev);
+	intel_uncore_sanitize(dev);
+	intel_uncore_init(dev);
 
 	/* Try to make sure MCHBAR is enabled before poking at it */
 	intel_setup_mchbar(dev);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 5849b0a91b4..01d63a0435f 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -723,7 +723,7 @@ static int i915_drm_thaw(struct drm_device *dev)
 {
 	int error = 0;
 
-	intel_gt_sanitize(dev);
+	intel_uncore_sanitize(dev);
 
 	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
 		mutex_lock(&dev->struct_mutex);
@@ -749,7 +749,7 @@ int i915_resume(struct drm_device *dev)
 
 	pci_set_master(dev->pdev);
 
-	intel_gt_sanitize(dev);
+	intel_uncore_sanitize(dev);
 
 	/*
 	 * Platforms with opregion should have sane BIOS, older ones (gen3 and
@@ -770,140 +770,6 @@ int i915_resume(struct drm_device *dev)
 	return 0;
 }
 
-static int i8xx_do_reset(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (IS_I85X(dev))
-		return -ENODEV;
-
-	I915_WRITE(D_STATE, I915_READ(D_STATE) | DSTATE_GFX_RESET_I830);
-	POSTING_READ(D_STATE);
-
-	if (IS_I830(dev) || IS_845G(dev)) {
-		I915_WRITE(DEBUG_RESET_I830,
-			   DEBUG_RESET_DISPLAY |
-			   DEBUG_RESET_RENDER |
-			   DEBUG_RESET_FULL);
-		POSTING_READ(DEBUG_RESET_I830);
-		msleep(1);
-
-		I915_WRITE(DEBUG_RESET_I830, 0);
-		POSTING_READ(DEBUG_RESET_I830);
-	}
-
-	msleep(1);
-
-	I915_WRITE(D_STATE, I915_READ(D_STATE) & ~DSTATE_GFX_RESET_I830);
-	POSTING_READ(D_STATE);
-
-	return 0;
-}
-
-static int i965_reset_complete(struct drm_device *dev)
-{
-	u8 gdrst;
-	pci_read_config_byte(dev->pdev, I965_GDRST, &gdrst);
-	return (gdrst & GRDOM_RESET_ENABLE) == 0;
-}
-
-static int i965_do_reset(struct drm_device *dev)
-{
-	int ret;
-
-	/*
-	 * Set the domains we want to reset (GRDOM/bits 2 and 3) as
-	 * well as the reset bit (GR/bit 0).  Setting the GR bit
-	 * triggers the reset; when done, the hardware will clear it.
-	 */
-	pci_write_config_byte(dev->pdev, I965_GDRST,
-			      GRDOM_RENDER | GRDOM_RESET_ENABLE);
-	ret =  wait_for(i965_reset_complete(dev), 500);
-	if (ret)
-		return ret;
-
-	/* We can't reset render&media without also resetting display ... */
-	pci_write_config_byte(dev->pdev, I965_GDRST,
-			      GRDOM_MEDIA | GRDOM_RESET_ENABLE);
-
-	ret =  wait_for(i965_reset_complete(dev), 500);
-	if (ret)
-		return ret;
-
-	pci_write_config_byte(dev->pdev, I965_GDRST, 0);
-
-	return 0;
-}
-
-static int ironlake_do_reset(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 gdrst;
-	int ret;
-
-	gdrst = I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR);
-	gdrst &= ~GRDOM_MASK;
-	I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR,
-		   gdrst | GRDOM_RENDER | GRDOM_RESET_ENABLE);
-	ret = wait_for(I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & 0x1, 500);
-	if (ret)
-		return ret;
-
-	/* We can't reset render&media without also resetting display ... */
-	gdrst = I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR);
-	gdrst &= ~GRDOM_MASK;
-	I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR,
-		   gdrst | GRDOM_MEDIA | GRDOM_RESET_ENABLE);
-	return wait_for(I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & 0x1, 500);
-}
-
-static int gen6_do_reset(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int	ret;
-	unsigned long irqflags;
-
-	/* Hold gt_lock across reset to prevent any register access
-	 * with forcewake not set correctly
-	 */
-	spin_lock_irqsave(&dev_priv->gt_lock, irqflags);
-
-	/* Reset the chip */
-
-	/* GEN6_GDRST is not in the gt power well, no need to check
-	 * for fifo space for the write or forcewake the chip for
-	 * the read
-	 */
-	I915_WRITE_NOTRACE(GEN6_GDRST, GEN6_GRDOM_FULL);
-
-	/* Spin waiting for the device to ack the reset request */
-	ret = wait_for((I915_READ_NOTRACE(GEN6_GDRST) & GEN6_GRDOM_FULL) == 0, 500);
-
-	/* If reset with a user forcewake, try to restore, otherwise turn it off */
-	if (dev_priv->forcewake_count)
-		dev_priv->gt.force_wake_get(dev_priv);
-	else
-		dev_priv->gt.force_wake_put(dev_priv);
-
-	/* Restore fifo count */
-	dev_priv->gt_fifo_count = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES);
-
-	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags);
-	return ret;
-}
-
-int intel_gpu_reset(struct drm_device *dev)
-{
-	switch (INTEL_INFO(dev)->gen) {
-	case 7:
-	case 6: return gen6_do_reset(dev);
-	case 5: return ironlake_do_reset(dev);
-	case 4: return i965_do_reset(dev);
-	case 2: return i8xx_do_reset(dev);
-	default: return -ENODEV;
-	}
-}
-
 /**
  * i915_reset - reset chip after a hang
  * @dev: drm device to reset
@@ -1233,136 +1099,3 @@ module_exit(i915_exit);
 MODULE_AUTHOR(DRIVER_AUTHOR);
 MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL and additional rights");
-
-/* We give fast paths for the really cool registers */
-#define NEEDS_FORCE_WAKE(dev_priv, reg) \
-	((HAS_FORCE_WAKE((dev_priv)->dev)) && \
-	 ((reg) < 0x40000) &&            \
-	 ((reg) != FORCEWAKE))
-static void
-ilk_dummy_write(struct drm_i915_private *dev_priv)
-{
-	/* WaIssueDummyWriteToWakeupFromRC6:ilk Issue a dummy write to wake up
-	 * the chip from rc6 before touching it for real. MI_MODE is masked,
-	 * hence harmless to write 0 into. */
-	I915_WRITE_NOTRACE(MI_MODE, 0);
-}
-
-static void
-hsw_unclaimed_reg_clear(struct drm_i915_private *dev_priv, u32 reg)
-{
-	if (HAS_FPGA_DBG_UNCLAIMED(dev_priv->dev) &&
-	    (I915_READ_NOTRACE(FPGA_DBG) & FPGA_DBG_RM_NOCLAIM)) {
-		DRM_ERROR("Unknown unclaimed register before writing to %x\n",
-			  reg);
-		I915_WRITE_NOTRACE(FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
-	}
-}
-
-static void
-hsw_unclaimed_reg_check(struct drm_i915_private *dev_priv, u32 reg)
-{
-	if (HAS_FPGA_DBG_UNCLAIMED(dev_priv->dev) &&
-	    (I915_READ_NOTRACE(FPGA_DBG) & FPGA_DBG_RM_NOCLAIM)) {
-		DRM_ERROR("Unclaimed write to %x\n", reg);
-		I915_WRITE_NOTRACE(FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
-	}
-}
-
-#define __i915_read(x, y) \
-u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg) { \
-	unsigned long irqflags; \
-	u##x val = 0; \
-	spin_lock_irqsave(&dev_priv->gt_lock, irqflags); \
-	if (IS_GEN5(dev_priv->dev)) \
-		ilk_dummy_write(dev_priv); \
-	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
-		if (dev_priv->forcewake_count == 0) \
-			dev_priv->gt.force_wake_get(dev_priv); \
-		val = read##y(dev_priv->regs + reg); \
-		if (dev_priv->forcewake_count == 0) \
-			dev_priv->gt.force_wake_put(dev_priv); \
-	} else { \
-		val = read##y(dev_priv->regs + reg); \
-	} \
-	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); \
-	trace_i915_reg_rw(false, reg, val, sizeof(val)); \
-	return val; \
-}
-
-__i915_read(8, b)
-__i915_read(16, w)
-__i915_read(32, l)
-__i915_read(64, q)
-#undef __i915_read
-
-#define __i915_write(x, y) \
-void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val) { \
-	unsigned long irqflags; \
-	u32 __fifo_ret = 0; \
-	trace_i915_reg_rw(true, reg, val, sizeof(val)); \
-	spin_lock_irqsave(&dev_priv->gt_lock, irqflags); \
-	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
-		__fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \
-	} \
-	if (IS_GEN5(dev_priv->dev)) \
-		ilk_dummy_write(dev_priv); \
-	hsw_unclaimed_reg_clear(dev_priv, reg); \
-	write##y(val, dev_priv->regs + reg); \
-	if (unlikely(__fifo_ret)) { \
-		gen6_gt_check_fifodbg(dev_priv); \
-	} \
-	hsw_unclaimed_reg_check(dev_priv, reg); \
-	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); \
-}
-__i915_write(8, b)
-__i915_write(16, w)
-__i915_write(32, l)
-__i915_write(64, q)
-#undef __i915_write
-
-static const struct register_whitelist {
-	uint64_t offset;
-	uint32_t size;
-	uint32_t gen_bitmask; /* support gens, 0x10 for 4, 0x30 for 4 and 5, etc. */
-} whitelist[] = {
-	{ RING_TIMESTAMP(RENDER_RING_BASE), 8, 0xF0 },
-};
-
-int i915_reg_read_ioctl(struct drm_device *dev,
-			void *data, struct drm_file *file)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_i915_reg_read *reg = data;
-	struct register_whitelist const *entry = whitelist;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(whitelist); i++, entry++) {
-		if (entry->offset == reg->offset &&
-		    (1 << INTEL_INFO(dev)->gen & entry->gen_bitmask))
-			break;
-	}
-
-	if (i == ARRAY_SIZE(whitelist))
-		return -EINVAL;
-
-	switch (entry->size) {
-	case 8:
-		reg->val = I915_READ64(reg->offset);
-		break;
-	case 4:
-		reg->val = I915_READ(reg->offset);
-		break;
-	case 2:
-		reg->val = I915_READ16(reg->offset);
-		break;
-	case 1:
-		reg->val = I915_READ8(reg->offset);
-		break;
-	default:
-		WARN_ON(1);
-		return -EINVAL;
-	}
-
-	return 0;
-}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 331c00b69f1..a55315a8d5a 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -391,11 +391,20 @@ struct drm_i915_display_funcs {
 	/* pll clock increase/decrease */
 };
 
-struct drm_i915_gt_funcs {
+struct intel_uncore_funcs {
 	void (*force_wake_get)(struct drm_i915_private *dev_priv);
 	void (*force_wake_put)(struct drm_i915_private *dev_priv);
 };
 
+struct intel_uncore {
+	spinlock_t lock; /** lock is also taken in irq contexts. */
+
+	struct intel_uncore_funcs funcs;
+
+	unsigned fifo_count;
+	unsigned forcewake_count;
+};
+
 #define DEV_INFO_FOR_EACH_FLAG(func, sep) \
 	func(is_mobile) sep \
 	func(is_i85x) sep \
@@ -1045,14 +1054,7 @@ typedef struct drm_i915_private {
 
 	void __iomem *regs;
 
-	struct drm_i915_gt_funcs gt;
-	/** gt_fifo_count and the subsequent register write are synchronized
-	 * with dev->struct_mutex. */
-	unsigned gt_fifo_count;
-	/** forcewake_count is protected by gt_lock */
-	unsigned forcewake_count;
-	/** gt_lock is also taken in irq contexts. */
-	spinlock_t gt_lock;
+	struct intel_uncore uncore;
 
 	struct intel_gmbus gmbus[GMBUS_NUM_PORTS];
 
@@ -1670,8 +1672,14 @@ void i915_handle_error(struct drm_device *dev, bool wedged);
 
 extern void intel_irq_init(struct drm_device *dev);
 extern void intel_hpd_init(struct drm_device *dev);
-extern void intel_gt_init(struct drm_device *dev);
-extern void intel_gt_sanitize(struct drm_device *dev);
+extern void intel_pm_init(struct drm_device *dev);
+
+extern void intel_uncore_sanitize(struct drm_device *dev);
+extern void intel_uncore_early_sanitize(struct drm_device *dev);
+extern void intel_uncore_init(struct drm_device *dev);
+extern void intel_uncore_reset(struct drm_device *dev);
+extern void intel_uncore_clear_errors(struct drm_device *dev);
+extern void intel_uncore_check_errors(struct drm_device *dev);
 
 void
 i915_enable_pipestat(drm_i915_private_t *dev_priv, int pipe, u32 mask);
@@ -2107,7 +2115,6 @@ extern void intel_display_print_error_state(struct drm_i915_error_state_buf *e,
  */
 void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv);
 void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv);
-int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv);
 
 int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u8 mbox, u32 *val);
 int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u8 mbox, u32 val);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index f708e4efa1b..ee3e49cc0eb 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1307,11 +1307,7 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 
 	/* We get interrupts on unclaimed registers, so check for this before we
 	 * do any I915_{READ,WRITE}. */
-	if (IS_HASWELL(dev) &&
-	    (I915_READ_NOTRACE(FPGA_DBG) & FPGA_DBG_RM_NOCLAIM)) {
-		DRM_ERROR("Unclaimed register before interrupt\n");
-		I915_WRITE_NOTRACE(FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
-	}
+	intel_uncore_check_errors(dev);
 
 	/* disable master interrupt before clearing iir  */
 	de_ier = I915_READ(DEIER);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index baaefd70cc6..b3389d74d69 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -10453,8 +10453,7 @@ intel_display_capture_error_state(struct drm_device *dev)
 	 * well was on, so here we have to clear the FPGA_DBG_RM_NOCLAIM bit to
 	 * prevent the next I915_WRITE from detecting it and printing an error
 	 * message. */
-	if (HAS_POWER_WELL(dev))
-		I915_WRITE_NOTRACE(FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
+	intel_uncore_clear_errors(dev);
 
 	return error;
 }
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 3fbe80bc36b..d9f50e368fe 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -806,7 +806,6 @@ extern void intel_init_power_well(struct drm_device *dev);
 extern void intel_set_power_well(struct drm_device *dev, bool enable);
 extern void intel_enable_gt_powersave(struct drm_device *dev);
 extern void intel_disable_gt_powersave(struct drm_device *dev);
-extern void gen6_gt_check_fifodbg(struct drm_i915_private *dev_priv);
 extern void ironlake_teardown_rc6(struct drm_device *dev);
 
 extern bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 74d6c4d7836..0a5ba92a4b1 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -32,8 +32,6 @@
 #include <linux/module.h>
 #include <drm/i915_powerwell.h>
 
-#define FORCEWAKE_ACK_TIMEOUT_MS 2
-
 /* FBC, or Frame Buffer Compression, is a technique employed to compress the
  * framebuffer contents in-memory, aiming at reducing the required bandwidth
  * during in-memory transfers and, therefore, reduce the power packet.
@@ -5289,254 +5287,6 @@ void intel_init_pm(struct drm_device *dev)
 	}
 }
 
-static void __gen6_gt_wait_for_thread_c0(struct drm_i915_private *dev_priv)
-{
-	u32 gt_thread_status_mask;
-
-	if (IS_HASWELL(dev_priv->dev))
-		gt_thread_status_mask = GEN6_GT_THREAD_STATUS_CORE_MASK_HSW;
-	else
-		gt_thread_status_mask = GEN6_GT_THREAD_STATUS_CORE_MASK;
-
-	/* w/a for a sporadic read returning 0 by waiting for the GT
-	 * thread to wake up.
-	 */
-	if (wait_for_atomic_us((I915_READ_NOTRACE(GEN6_GT_THREAD_STATUS_REG) & gt_thread_status_mask) == 0, 500))
-		DRM_ERROR("GT thread status wait timed out\n");
-}
-
-static void __gen6_gt_force_wake_reset(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE_NOTRACE(FORCEWAKE, 0);
-	POSTING_READ(ECOBUS); /* something from same cacheline, but !FORCEWAKE */
-}
-
-static void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
-{
-	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK) & 1) == 0,
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
-
-	I915_WRITE_NOTRACE(FORCEWAKE, 1);
-	POSTING_READ(ECOBUS); /* something from same cacheline, but !FORCEWAKE */
-
-	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK) & 1),
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for forcewake to ack request.\n");
-
-	/* WaRsForcewakeWaitTC0:snb */
-	__gen6_gt_wait_for_thread_c0(dev_priv);
-}
-
-static void __gen6_gt_force_wake_mt_reset(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_DISABLE(0xffff));
-	/* something from same cacheline, but !FORCEWAKE_MT */
-	POSTING_READ(ECOBUS);
-}
-
-static void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv)
-{
-	u32 forcewake_ack;
-
-	if (IS_HASWELL(dev_priv->dev))
-		forcewake_ack = FORCEWAKE_ACK_HSW;
-	else
-		forcewake_ack = FORCEWAKE_MT_ACK;
-
-	if (wait_for_atomic((I915_READ_NOTRACE(forcewake_ack) & FORCEWAKE_KERNEL) == 0,
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
-
-	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
-	/* something from same cacheline, but !FORCEWAKE_MT */
-	POSTING_READ(ECOBUS);
-
-	if (wait_for_atomic((I915_READ_NOTRACE(forcewake_ack) & FORCEWAKE_KERNEL),
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for forcewake to ack request.\n");
-
-	/* WaRsForcewakeWaitTC0:ivb,hsw */
-	__gen6_gt_wait_for_thread_c0(dev_priv);
-}
-
-/*
- * Generally this is called implicitly by the register read function. However,
- * if some sequence requires the GT to not power down then this function should
- * be called at the beginning of the sequence followed by a call to
- * gen6_gt_force_wake_put() at the end of the sequence.
- */
-void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
-{
-	unsigned long irqflags;
-
-	spin_lock_irqsave(&dev_priv->gt_lock, irqflags);
-	if (dev_priv->forcewake_count++ == 0)
-		dev_priv->gt.force_wake_get(dev_priv);
-	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags);
-}
-
-void gen6_gt_check_fifodbg(struct drm_i915_private *dev_priv)
-{
-	u32 gtfifodbg;
-	gtfifodbg = I915_READ_NOTRACE(GTFIFODBG);
-	if (WARN(gtfifodbg & GT_FIFO_CPU_ERROR_MASK,
-	     "MMIO read or write has been dropped %x\n", gtfifodbg))
-		I915_WRITE_NOTRACE(GTFIFODBG, GT_FIFO_CPU_ERROR_MASK);
-}
-
-static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE_NOTRACE(FORCEWAKE, 0);
-	/* something from same cacheline, but !FORCEWAKE */
-	POSTING_READ(ECOBUS);
-	gen6_gt_check_fifodbg(dev_priv);
-}
-
-static void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
-	/* something from same cacheline, but !FORCEWAKE_MT */
-	POSTING_READ(ECOBUS);
-	gen6_gt_check_fifodbg(dev_priv);
-}
-
-/*
- * see gen6_gt_force_wake_get()
- */
-void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
-{
-	unsigned long irqflags;
-
-	spin_lock_irqsave(&dev_priv->gt_lock, irqflags);
-	if (--dev_priv->forcewake_count == 0)
-		dev_priv->gt.force_wake_put(dev_priv);
-	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags);
-}
-
-int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
-{
-	int ret = 0;
-
-	if (dev_priv->gt_fifo_count < GT_FIFO_NUM_RESERVED_ENTRIES) {
-		int loop = 500;
-		u32 fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES);
-		while (fifo <= GT_FIFO_NUM_RESERVED_ENTRIES && loop--) {
-			udelay(10);
-			fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES);
-		}
-		if (WARN_ON(loop < 0 && fifo <= GT_FIFO_NUM_RESERVED_ENTRIES))
-			++ret;
-		dev_priv->gt_fifo_count = fifo;
-	}
-	dev_priv->gt_fifo_count--;
-
-	return ret;
-}
-
-static void vlv_force_wake_reset(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE_NOTRACE(FORCEWAKE_VLV, _MASKED_BIT_DISABLE(0xffff));
-	/* something from same cacheline, but !FORCEWAKE_VLV */
-	POSTING_READ(FORCEWAKE_ACK_VLV);
-}
-
-static void vlv_force_wake_get(struct drm_i915_private *dev_priv)
-{
-	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK_VLV) & FORCEWAKE_KERNEL) == 0,
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
-
-	I915_WRITE_NOTRACE(FORCEWAKE_VLV, _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
-	I915_WRITE_NOTRACE(FORCEWAKE_MEDIA_VLV,
-			   _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
-
-	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK_VLV) & FORCEWAKE_KERNEL),
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for GT to ack forcewake request.\n");
-
-	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK_MEDIA_VLV) &
-			     FORCEWAKE_KERNEL),
-			    FORCEWAKE_ACK_TIMEOUT_MS))
-		DRM_ERROR("Timed out waiting for media to ack forcewake request.\n");
-
-	/* WaRsForcewakeWaitTC0:vlv */
-	__gen6_gt_wait_for_thread_c0(dev_priv);
-}
-
-static void vlv_force_wake_put(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE_NOTRACE(FORCEWAKE_VLV, _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
-	I915_WRITE_NOTRACE(FORCEWAKE_MEDIA_VLV,
-			   _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
-	/* The below doubles as a POSTING_READ */
-	gen6_gt_check_fifodbg(dev_priv);
-}
-
-void intel_gt_sanitize(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (IS_VALLEYVIEW(dev)) {
-		vlv_force_wake_reset(dev_priv);
-	} else if (INTEL_INFO(dev)->gen >= 6) {
-		__gen6_gt_force_wake_reset(dev_priv);
-		if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
-			__gen6_gt_force_wake_mt_reset(dev_priv);
-	}
-
-	/* BIOS often leaves RC6 enabled, but disable it for hw init */
-	if (INTEL_INFO(dev)->gen >= 6)
-		intel_disable_gt_powersave(dev);
-}
-
-void intel_gt_init(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (IS_VALLEYVIEW(dev)) {
-		dev_priv->gt.force_wake_get = vlv_force_wake_get;
-		dev_priv->gt.force_wake_put = vlv_force_wake_put;
-	} else if (IS_HASWELL(dev)) {
-		dev_priv->gt.force_wake_get = __gen6_gt_force_wake_mt_get;
-		dev_priv->gt.force_wake_put = __gen6_gt_force_wake_mt_put;
-	} else if (IS_IVYBRIDGE(dev)) {
-		u32 ecobus;
-
-		/* IVB configs may use multi-threaded forcewake */
-
-		/* A small trick here - if the bios hasn't configured
-		 * MT forcewake, and if the device is in RC6, then
-		 * force_wake_mt_get will not wake the device and the
-		 * ECOBUS read will return zero. Which will be
-		 * (correctly) interpreted by the test below as MT
-		 * forcewake being disabled.
-		 */
-		mutex_lock(&dev->struct_mutex);
-		__gen6_gt_force_wake_mt_get(dev_priv);
-		ecobus = I915_READ_NOTRACE(ECOBUS);
-		__gen6_gt_force_wake_mt_put(dev_priv);
-		mutex_unlock(&dev->struct_mutex);
-
-		if (ecobus & FORCEWAKE_MT_ENABLE) {
-			dev_priv->gt.force_wake_get =
-						__gen6_gt_force_wake_mt_get;
-			dev_priv->gt.force_wake_put =
-						__gen6_gt_force_wake_mt_put;
-		} else {
-			DRM_INFO("No MT forcewake available on Ivybridge, this can result in issues\n");
-			DRM_INFO("when using vblank-synced partial screen updates.\n");
-			dev_priv->gt.force_wake_get = __gen6_gt_force_wake_get;
-			dev_priv->gt.force_wake_put = __gen6_gt_force_wake_put;
-		}
-	} else if (IS_GEN6(dev)) {
-		dev_priv->gt.force_wake_get = __gen6_gt_force_wake_get;
-		dev_priv->gt.force_wake_put = __gen6_gt_force_wake_put;
-	}
-	INIT_DELAYED_WORK(&dev_priv->rps.delayed_resume_work,
-			  intel_gen6_powersave_work);
-}
-
 int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u8 mbox, u32 *val)
 {
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
@@ -5639,3 +5389,11 @@ int vlv_freq_opcode(int ddr_freq, int val)
 	return val;
 }
 
+void intel_pm_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	INIT_DELAYED_WORK(&dev_priv->rps.delayed_resume_work,
+			  intel_gen6_powersave_work);
+}
+
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
new file mode 100644
index 00000000000..97e8b1b8647
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -0,0 +1,571 @@
+/*
+ * Copyright © 2013 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include "i915_drv.h"
+#include "intel_drv.h"
+
+#define FORCEWAKE_ACK_TIMEOUT_MS 2
+
+static void __gen6_gt_wait_for_thread_c0(struct drm_i915_private *dev_priv)
+{
+	u32 gt_thread_status_mask;
+
+	if (IS_HASWELL(dev_priv->dev))
+		gt_thread_status_mask = GEN6_GT_THREAD_STATUS_CORE_MASK_HSW;
+	else
+		gt_thread_status_mask = GEN6_GT_THREAD_STATUS_CORE_MASK;
+
+	/* w/a for a sporadic read returning 0 by waiting for the GT
+	 * thread to wake up.
+	 */
+	if (wait_for_atomic_us((I915_READ_NOTRACE(GEN6_GT_THREAD_STATUS_REG) & gt_thread_status_mask) == 0, 500))
+		DRM_ERROR("GT thread status wait timed out\n");
+}
+
+static void __gen6_gt_force_wake_reset(struct drm_i915_private *dev_priv)
+{
+	I915_WRITE_NOTRACE(FORCEWAKE, 0);
+	POSTING_READ(ECOBUS); /* something from same cacheline, but !FORCEWAKE */
+}
+
+static void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
+{
+	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK) & 1) == 0,
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
+
+	I915_WRITE_NOTRACE(FORCEWAKE, 1);
+	POSTING_READ(ECOBUS); /* something from same cacheline, but !FORCEWAKE */
+
+	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK) & 1),
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for forcewake to ack request.\n");
+
+	/* WaRsForcewakeWaitTC0:snb */
+	__gen6_gt_wait_for_thread_c0(dev_priv);
+}
+
+static void __gen6_gt_force_wake_mt_reset(struct drm_i915_private *dev_priv)
+{
+	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_DISABLE(0xffff));
+	/* something from same cacheline, but !FORCEWAKE_MT */
+	POSTING_READ(ECOBUS);
+}
+
+static void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv)
+{
+	u32 forcewake_ack;
+
+	if (IS_HASWELL(dev_priv->dev))
+		forcewake_ack = FORCEWAKE_ACK_HSW;
+	else
+		forcewake_ack = FORCEWAKE_MT_ACK;
+
+	if (wait_for_atomic((I915_READ_NOTRACE(forcewake_ack) & FORCEWAKE_KERNEL) == 0,
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
+
+	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
+	/* something from same cacheline, but !FORCEWAKE_MT */
+	POSTING_READ(ECOBUS);
+
+	if (wait_for_atomic((I915_READ_NOTRACE(forcewake_ack) & FORCEWAKE_KERNEL),
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for forcewake to ack request.\n");
+
+	/* WaRsForcewakeWaitTC0:ivb,hsw */
+	__gen6_gt_wait_for_thread_c0(dev_priv);
+}
+
+static void gen6_gt_check_fifodbg(struct drm_i915_private *dev_priv)
+{
+	u32 gtfifodbg;
+	gtfifodbg = I915_READ_NOTRACE(GTFIFODBG);
+	if (WARN(gtfifodbg & GT_FIFO_CPU_ERROR_MASK,
+	     "MMIO read or write has been dropped %x\n", gtfifodbg))
+		I915_WRITE_NOTRACE(GTFIFODBG, GT_FIFO_CPU_ERROR_MASK);
+}
+
+static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
+{
+	I915_WRITE_NOTRACE(FORCEWAKE, 0);
+	/* something from same cacheline, but !FORCEWAKE */
+	POSTING_READ(ECOBUS);
+	gen6_gt_check_fifodbg(dev_priv);
+}
+
+static void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv)
+{
+	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
+	/* something from same cacheline, but !FORCEWAKE_MT */
+	POSTING_READ(ECOBUS);
+	gen6_gt_check_fifodbg(dev_priv);
+}
+
+static int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
+{
+	int ret = 0;
+
+	if (dev_priv->uncore.fifo_count < GT_FIFO_NUM_RESERVED_ENTRIES) {
+		int loop = 500;
+		u32 fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES);
+		while (fifo <= GT_FIFO_NUM_RESERVED_ENTRIES && loop--) {
+			udelay(10);
+			fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES);
+		}
+		if (WARN_ON(loop < 0 && fifo <= GT_FIFO_NUM_RESERVED_ENTRIES))
+			++ret;
+		dev_priv->uncore.fifo_count = fifo;
+	}
+	dev_priv->uncore.fifo_count--;
+
+	return ret;
+}
+
+static void vlv_force_wake_reset(struct drm_i915_private *dev_priv)
+{
+	I915_WRITE_NOTRACE(FORCEWAKE_VLV, _MASKED_BIT_DISABLE(0xffff));
+	/* something from same cacheline, but !FORCEWAKE_VLV */
+	POSTING_READ(FORCEWAKE_ACK_VLV);
+}
+
+static void vlv_force_wake_get(struct drm_i915_private *dev_priv)
+{
+	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK_VLV) & FORCEWAKE_KERNEL) == 0,
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for forcewake old ack to clear.\n");
+
+	I915_WRITE_NOTRACE(FORCEWAKE_VLV, _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
+	I915_WRITE_NOTRACE(FORCEWAKE_MEDIA_VLV,
+			   _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL));
+
+	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK_VLV) & FORCEWAKE_KERNEL),
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for GT to ack forcewake request.\n");
+
+	if (wait_for_atomic((I915_READ_NOTRACE(FORCEWAKE_ACK_MEDIA_VLV) &
+			     FORCEWAKE_KERNEL),
+			    FORCEWAKE_ACK_TIMEOUT_MS))
+		DRM_ERROR("Timed out waiting for media to ack forcewake request.\n");
+
+	/* WaRsForcewakeWaitTC0:vlv */
+	__gen6_gt_wait_for_thread_c0(dev_priv);
+}
+
+static void vlv_force_wake_put(struct drm_i915_private *dev_priv)
+{
+	I915_WRITE_NOTRACE(FORCEWAKE_VLV, _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
+	I915_WRITE_NOTRACE(FORCEWAKE_MEDIA_VLV,
+			   _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
+	/* The below doubles as a POSTING_READ */
+	gen6_gt_check_fifodbg(dev_priv);
+}
+
+void intel_uncore_early_sanitize(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (HAS_FPGA_DBG_UNCLAIMED(dev))
+		I915_WRITE_NOTRACE(FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
+}
+
+void intel_uncore_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (IS_VALLEYVIEW(dev)) {
+		dev_priv->uncore.funcs.force_wake_get = vlv_force_wake_get;
+		dev_priv->uncore.funcs.force_wake_put = vlv_force_wake_put;
+	} else if (IS_HASWELL(dev)) {
+		dev_priv->uncore.funcs.force_wake_get = __gen6_gt_force_wake_mt_get;
+		dev_priv->uncore.funcs.force_wake_put = __gen6_gt_force_wake_mt_put;
+	} else if (IS_IVYBRIDGE(dev)) {
+		u32 ecobus;
+
+		/* IVB configs may use multi-threaded forcewake */
+
+		/* A small trick here - if the bios hasn't configured
+		 * MT forcewake, and if the device is in RC6, then
+		 * force_wake_mt_get will not wake the device and the
+		 * ECOBUS read will return zero. Which will be
+		 * (correctly) interpreted by the test below as MT
+		 * forcewake being disabled.
+		 */
+		mutex_lock(&dev->struct_mutex);
+		__gen6_gt_force_wake_mt_get(dev_priv);
+		ecobus = I915_READ_NOTRACE(ECOBUS);
+		__gen6_gt_force_wake_mt_put(dev_priv);
+		mutex_unlock(&dev->struct_mutex);
+
+		if (ecobus & FORCEWAKE_MT_ENABLE) {
+			dev_priv->uncore.funcs.force_wake_get =
+				__gen6_gt_force_wake_mt_get;
+			dev_priv->uncore.funcs.force_wake_put =
+				__gen6_gt_force_wake_mt_put;
+		} else {
+			DRM_INFO("No MT forcewake available on Ivybridge, this can result in issues\n");
+			DRM_INFO("when using vblank-synced partial screen updates.\n");
+			dev_priv->uncore.funcs.force_wake_get =
+				__gen6_gt_force_wake_get;
+			dev_priv->uncore.funcs.force_wake_put =
+				__gen6_gt_force_wake_put;
+		}
+	} else if (IS_GEN6(dev)) {
+		dev_priv->uncore.funcs.force_wake_get =
+			__gen6_gt_force_wake_get;
+		dev_priv->uncore.funcs.force_wake_put =
+			__gen6_gt_force_wake_put;
+	}
+}
+
+void intel_uncore_sanitize(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (IS_VALLEYVIEW(dev)) {
+		vlv_force_wake_reset(dev_priv);
+	} else if (INTEL_INFO(dev)->gen >= 6) {
+		__gen6_gt_force_wake_reset(dev_priv);
+		if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
+			__gen6_gt_force_wake_mt_reset(dev_priv);
+	}
+
+	/* BIOS often leaves RC6 enabled, but disable it for hw init */
+	intel_disable_gt_powersave(dev);
+}
+
+/*
+ * Generally this is called implicitly by the register read function. However,
+ * if some sequence requires the GT to not power down then this function should
+ * be called at the beginning of the sequence followed by a call to
+ * gen6_gt_force_wake_put() at the end of the sequence.
+ */
+void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
+{
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+	if (dev_priv->uncore.forcewake_count++ == 0)
+		dev_priv->uncore.funcs.force_wake_get(dev_priv);
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
+}
+
+/*
+ * see gen6_gt_force_wake_get()
+ */
+void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
+{
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+	if (--dev_priv->uncore.forcewake_count == 0)
+		dev_priv->uncore.funcs.force_wake_put(dev_priv);
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
+}
+
+/* We give fast paths for the really cool registers */
+#define NEEDS_FORCE_WAKE(dev_priv, reg) \
+	((HAS_FORCE_WAKE((dev_priv)->dev)) && \
+	 ((reg) < 0x40000) &&            \
+	 ((reg) != FORCEWAKE))
+
+static void
+ilk_dummy_write(struct drm_i915_private *dev_priv)
+{
+	/* WaIssueDummyWriteToWakeupFromRC6:ilk Issue a dummy write to wake up
+	 * the chip from rc6 before touching it for real. MI_MODE is masked,
+	 * hence harmless to write 0 into. */
+	I915_WRITE_NOTRACE(MI_MODE, 0);
+}
+
+static void
+hsw_unclaimed_reg_clear(struct drm_i915_private *dev_priv, u32 reg)
+{
+	if (HAS_FPGA_DBG_UNCLAIMED(dev_priv->dev) &&
+	    (I915_READ_NOTRACE(FPGA_DBG) & FPGA_DBG_RM_NOCLAIM)) {
+		DRM_ERROR("Unknown unclaimed register before writing to %x\n",
+			  reg);
+		I915_WRITE_NOTRACE(FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
+	}
+}
+
+static void
+hsw_unclaimed_reg_check(struct drm_i915_private *dev_priv, u32 reg)
+{
+	if (HAS_FPGA_DBG_UNCLAIMED(dev_priv->dev) &&
+	    (I915_READ_NOTRACE(FPGA_DBG) & FPGA_DBG_RM_NOCLAIM)) {
+		DRM_ERROR("Unclaimed write to %x\n", reg);
+		I915_WRITE_NOTRACE(FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
+	}
+}
+
+#define __i915_read(x, y) \
+u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg) { \
+	unsigned long irqflags; \
+	u##x val = 0; \
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); \
+	if (IS_GEN5(dev_priv->dev)) \
+		ilk_dummy_write(dev_priv); \
+	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
+		if (dev_priv->uncore.forcewake_count == 0) \
+			dev_priv->uncore.funcs.force_wake_get(dev_priv); \
+		val = read##y(dev_priv->regs + reg); \
+		if (dev_priv->uncore.forcewake_count == 0) \
+			dev_priv->uncore.funcs.force_wake_put(dev_priv); \
+	} else { \
+		val = read##y(dev_priv->regs + reg); \
+	} \
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); \
+	trace_i915_reg_rw(false, reg, val, sizeof(val)); \
+	return val; \
+}
+
+__i915_read(8, b)
+__i915_read(16, w)
+__i915_read(32, l)
+__i915_read(64, q)
+#undef __i915_read
+
+#define __i915_write(x, y) \
+void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val) { \
+	unsigned long irqflags; \
+	u32 __fifo_ret = 0; \
+	trace_i915_reg_rw(true, reg, val, sizeof(val)); \
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); \
+	if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
+		__fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \
+	} \
+	if (IS_GEN5(dev_priv->dev)) \
+		ilk_dummy_write(dev_priv); \
+	hsw_unclaimed_reg_clear(dev_priv, reg); \
+	write##y(val, dev_priv->regs + reg); \
+	if (unlikely(__fifo_ret)) { \
+		gen6_gt_check_fifodbg(dev_priv); \
+	} \
+	hsw_unclaimed_reg_check(dev_priv, reg); \
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); \
+}
+__i915_write(8, b)
+__i915_write(16, w)
+__i915_write(32, l)
+__i915_write(64, q)
+#undef __i915_write
+
+static const struct register_whitelist {
+	uint64_t offset;
+	uint32_t size;
+	uint32_t gen_bitmask; /* support gens, 0x10 for 4, 0x30 for 4 and 5, etc. */
+} whitelist[] = {
+	{ RING_TIMESTAMP(RENDER_RING_BASE), 8, 0xF0 },
+};
+
+int i915_reg_read_ioctl(struct drm_device *dev,
+			void *data, struct drm_file *file)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_reg_read *reg = data;
+	struct register_whitelist const *entry = whitelist;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(whitelist); i++, entry++) {
+		if (entry->offset == reg->offset &&
+		    (1 << INTEL_INFO(dev)->gen & entry->gen_bitmask))
+			break;
+	}
+
+	if (i == ARRAY_SIZE(whitelist))
+		return -EINVAL;
+
+	switch (entry->size) {
+	case 8:
+		reg->val = I915_READ64(reg->offset);
+		break;
+	case 4:
+		reg->val = I915_READ(reg->offset);
+		break;
+	case 2:
+		reg->val = I915_READ16(reg->offset);
+		break;
+	case 1:
+		reg->val = I915_READ8(reg->offset);
+		break;
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int i8xx_do_reset(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (IS_I85X(dev))
+		return -ENODEV;
+
+	I915_WRITE(D_STATE, I915_READ(D_STATE) | DSTATE_GFX_RESET_I830);
+	POSTING_READ(D_STATE);
+
+	if (IS_I830(dev) || IS_845G(dev)) {
+		I915_WRITE(DEBUG_RESET_I830,
+			   DEBUG_RESET_DISPLAY |
+			   DEBUG_RESET_RENDER |
+			   DEBUG_RESET_FULL);
+		POSTING_READ(DEBUG_RESET_I830);
+		msleep(1);
+
+		I915_WRITE(DEBUG_RESET_I830, 0);
+		POSTING_READ(DEBUG_RESET_I830);
+	}
+
+	msleep(1);
+
+	I915_WRITE(D_STATE, I915_READ(D_STATE) & ~DSTATE_GFX_RESET_I830);
+	POSTING_READ(D_STATE);
+
+	return 0;
+}
+
+static int i965_reset_complete(struct drm_device *dev)
+{
+	u8 gdrst;
+	pci_read_config_byte(dev->pdev, I965_GDRST, &gdrst);
+	return (gdrst & GRDOM_RESET_ENABLE) == 0;
+}
+
+static int i965_do_reset(struct drm_device *dev)
+{
+	int ret;
+
+	/*
+	 * Set the domains we want to reset (GRDOM/bits 2 and 3) as
+	 * well as the reset bit (GR/bit 0).  Setting the GR bit
+	 * triggers the reset; when done, the hardware will clear it.
+	 */
+	pci_write_config_byte(dev->pdev, I965_GDRST,
+			      GRDOM_RENDER | GRDOM_RESET_ENABLE);
+	ret =  wait_for(i965_reset_complete(dev), 500);
+	if (ret)
+		return ret;
+
+	/* We can't reset render&media without also resetting display ... */
+	pci_write_config_byte(dev->pdev, I965_GDRST,
+			      GRDOM_MEDIA | GRDOM_RESET_ENABLE);
+
+	ret =  wait_for(i965_reset_complete(dev), 500);
+	if (ret)
+		return ret;
+
+	pci_write_config_byte(dev->pdev, I965_GDRST, 0);
+
+	return 0;
+}
+
+static int ironlake_do_reset(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 gdrst;
+	int ret;
+
+	gdrst = I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR);
+	gdrst &= ~GRDOM_MASK;
+	I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR,
+		   gdrst | GRDOM_RENDER | GRDOM_RESET_ENABLE);
+	ret = wait_for(I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & 0x1, 500);
+	if (ret)
+		return ret;
+
+	/* We can't reset render&media without also resetting display ... */
+	gdrst = I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR);
+	gdrst &= ~GRDOM_MASK;
+	I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR,
+		   gdrst | GRDOM_MEDIA | GRDOM_RESET_ENABLE);
+	return wait_for(I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & 0x1, 500);
+}
+
+static int gen6_do_reset(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int	ret;
+	unsigned long irqflags;
+
+	/* Hold uncore.lock across reset to prevent any register access
+	 * with forcewake not set correctly
+	 */
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+
+	/* Reset the chip */
+
+	/* GEN6_GDRST is not in the gt power well, no need to check
+	 * for fifo space for the write or forcewake the chip for
+	 * the read
+	 */
+	I915_WRITE_NOTRACE(GEN6_GDRST, GEN6_GRDOM_FULL);
+
+	/* Spin waiting for the device to ack the reset request */
+	ret = wait_for((I915_READ_NOTRACE(GEN6_GDRST) & GEN6_GRDOM_FULL) == 0, 500);
+
+	/* If reset with a user forcewake, try to restore, otherwise turn it off */
+	if (dev_priv->uncore.forcewake_count)
+		dev_priv->uncore.funcs.force_wake_get(dev_priv);
+	else
+		dev_priv->uncore.funcs.force_wake_put(dev_priv);
+
+	/* Restore fifo count */
+	dev_priv->uncore.fifo_count = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES);
+
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
+	return ret;
+}
+
+int intel_gpu_reset(struct drm_device *dev)
+{
+	switch (INTEL_INFO(dev)->gen) {
+	case 7:
+	case 6: return gen6_do_reset(dev);
+	case 5: return ironlake_do_reset(dev);
+	case 4: return i965_do_reset(dev);
+	case 2: return i8xx_do_reset(dev);
+	default: return -ENODEV;
+	}
+}
+
+void intel_uncore_clear_errors(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (HAS_FPGA_DBG_UNCLAIMED(dev))
+		I915_WRITE_NOTRACE(FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
+}
+
+void intel_uncore_check_errors(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (HAS_FPGA_DBG_UNCLAIMED(dev) &&
+	    (I915_READ_NOTRACE(FPGA_DBG) & FPGA_DBG_RM_NOCLAIM)) {
+		DRM_ERROR("Unclaimed register before interrupt\n");
+		I915_WRITE_NOTRACE(FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
+	}
+}
-- 
cgit v1.2.3-70-g09d2


From 29ebf90f8157f9d01dda2b1555b4a08e9e542b21 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 27 Jul 2013 17:23:55 +0100
Subject: drm/i915: Squelch repeated reasoning for why FBC cannot be activated

Almost invariably the reason why FBC cannot be turned on is the same
every time (disabled via parameter, too many pipes, pipe too large etc)
as modesetting and framebuffer configuration changes less frequently
than trying to enable FBC.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_debugfs.c |  6 ++++
 drivers/gpu/drm/i915/i915_drv.h     |  4 ++-
 drivers/gpu/drm/i915/intel_pm.c     | 59 +++++++++++++++++++++++--------------
 3 files changed, 46 insertions(+), 23 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index ed72fe08217..eed2f4ca9a7 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1099,6 +1099,12 @@ static int i915_fbc_status(struct seq_file *m, void *unused)
 	} else {
 		seq_puts(m, "FBC disabled: ");
 		switch (dev_priv->fbc.no_fbc_reason) {
+		case FBC_OK:
+			seq_puts(m, "FBC actived, but currently disabled in hardware");
+			break;
+		case FBC_UNSUPPORTED:
+			seq_puts(m, "unsupported by this chipset");
+			break;
 		case FBC_NO_OUTPUT:
 			seq_puts(m, "no outputs");
 			break;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 82ea281b218..ace691b2307 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -589,7 +589,9 @@ struct i915_fbc {
 		int interval;
 	} *fbc_work;
 
-	enum {
+	enum no_fbc_reason {
+		FBC_OK, /* FBC is enabled */
+		FBC_UNSUPPORTED, /* FBC is not supported by this chipset */
 		FBC_NO_OUTPUT, /* no outputs enabled to compress */
 		FBC_STOLEN_TOO_SMALL, /* not enough space for buffers */
 		FBC_UNSUPPORTED_MODE, /* interlace or doublescanned mode */
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 0a5ba92a4b1..b503f594205 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -421,6 +421,16 @@ void intel_disable_fbc(struct drm_device *dev)
 	dev_priv->fbc.plane = -1;
 }
 
+static bool set_no_fbc_reason(struct drm_i915_private *dev_priv,
+			      enum no_fbc_reason reason)
+{
+	if (dev_priv->fbc.no_fbc_reason == reason)
+		return false;
+
+	dev_priv->fbc.no_fbc_reason = reason;
+	return true;
+}
+
 /**
  * intel_update_fbc - enable/disable FBC as needed
  * @dev: the drm_device
@@ -450,11 +460,16 @@ void intel_update_fbc(struct drm_device *dev)
 	struct drm_i915_gem_object *obj;
 	unsigned int max_hdisplay, max_vdisplay;
 
-	if (!i915_powersave)
+	if (!I915_HAS_FBC(dev)) {
+		set_no_fbc_reason(dev_priv, FBC_UNSUPPORTED);
 		return;
+	}
 
-	if (!I915_HAS_FBC(dev))
+	if (!i915_powersave) {
+		if (set_no_fbc_reason(dev_priv, FBC_MODULE_PARAM))
+			DRM_DEBUG_KMS("fbc disabled per module param\n");
 		return;
+	}
 
 	/*
 	 * If FBC is already on, we just have to verify that we can
@@ -469,9 +484,8 @@ void intel_update_fbc(struct drm_device *dev)
 		if (intel_crtc_active(tmp_crtc) &&
 		    !to_intel_crtc(tmp_crtc)->primary_disabled) {
 			if (crtc) {
-				DRM_DEBUG_KMS("more than one pipe active, disabling compression\n");
-				dev_priv->fbc.no_fbc_reason =
-					FBC_MULTIPLE_PIPES;
+				if (set_no_fbc_reason(dev_priv, FBC_MULTIPLE_PIPES))
+					DRM_DEBUG_KMS("more than one pipe active, disabling compression\n");
 				goto out_disable;
 			}
 			crtc = tmp_crtc;
@@ -479,8 +493,8 @@ void intel_update_fbc(struct drm_device *dev)
 	}
 
 	if (!crtc || crtc->fb == NULL) {
-		DRM_DEBUG_KMS("no output, disabling\n");
-		dev_priv->fbc.no_fbc_reason = FBC_NO_OUTPUT;
+		if (set_no_fbc_reason(dev_priv, FBC_NO_OUTPUT))
+			DRM_DEBUG_KMS("no output, disabling\n");
 		goto out_disable;
 	}
 
@@ -491,20 +505,20 @@ void intel_update_fbc(struct drm_device *dev)
 
 	if (i915_enable_fbc < 0 &&
 	    INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev)) {
-		DRM_DEBUG_KMS("disabled per chip default\n");
-		dev_priv->fbc.no_fbc_reason = FBC_CHIP_DEFAULT;
+		if (set_no_fbc_reason(dev_priv, FBC_CHIP_DEFAULT))
+			DRM_DEBUG_KMS("disabled per chip default\n");
 		goto out_disable;
 	}
 	if (!i915_enable_fbc) {
-		DRM_DEBUG_KMS("fbc disabled per module param\n");
-		dev_priv->fbc.no_fbc_reason = FBC_MODULE_PARAM;
+		if (set_no_fbc_reason(dev_priv, FBC_MODULE_PARAM))
+			DRM_DEBUG_KMS("fbc disabled per module param\n");
 		goto out_disable;
 	}
 	if ((crtc->mode.flags & DRM_MODE_FLAG_INTERLACE) ||
 	    (crtc->mode.flags & DRM_MODE_FLAG_DBLSCAN)) {
-		DRM_DEBUG_KMS("mode incompatible with compression, "
-			      "disabling\n");
-		dev_priv->fbc.no_fbc_reason = FBC_UNSUPPORTED_MODE;
+		if (set_no_fbc_reason(dev_priv, FBC_UNSUPPORTED_MODE))
+			DRM_DEBUG_KMS("mode incompatible with compression, "
+				      "disabling\n");
 		goto out_disable;
 	}
 
@@ -517,14 +531,14 @@ void intel_update_fbc(struct drm_device *dev)
 	}
 	if ((crtc->mode.hdisplay > max_hdisplay) ||
 	    (crtc->mode.vdisplay > max_vdisplay)) {
-		DRM_DEBUG_KMS("mode too large for compression, disabling\n");
-		dev_priv->fbc.no_fbc_reason = FBC_MODE_TOO_LARGE;
+		if (set_no_fbc_reason(dev_priv, FBC_MODE_TOO_LARGE))
+			DRM_DEBUG_KMS("mode too large for compression, disabling\n");
 		goto out_disable;
 	}
 	if ((IS_I915GM(dev) || IS_I945GM(dev) || IS_HASWELL(dev)) &&
 	    intel_crtc->plane != 0) {
-		DRM_DEBUG_KMS("plane not 0, disabling compression\n");
-		dev_priv->fbc.no_fbc_reason = FBC_BAD_PLANE;
+		if (set_no_fbc_reason(dev_priv, FBC_BAD_PLANE))
+			DRM_DEBUG_KMS("plane not 0, disabling compression\n");
 		goto out_disable;
 	}
 
@@ -533,8 +547,8 @@ void intel_update_fbc(struct drm_device *dev)
 	 */
 	if (obj->tiling_mode != I915_TILING_X ||
 	    obj->fence_reg == I915_FENCE_REG_NONE) {
-		DRM_DEBUG_KMS("framebuffer not tiled or fenced, disabling compression\n");
-		dev_priv->fbc.no_fbc_reason = FBC_NOT_TILED;
+		if (set_no_fbc_reason(dev_priv, FBC_NOT_TILED))
+			DRM_DEBUG_KMS("framebuffer not tiled or fenced, disabling compression\n");
 		goto out_disable;
 	}
 
@@ -543,8 +557,8 @@ void intel_update_fbc(struct drm_device *dev)
 		goto out_disable;
 
 	if (i915_gem_stolen_setup_compression(dev, intel_fb->obj->base.size)) {
-		DRM_DEBUG_KMS("framebuffer too large, disabling compression\n");
-		dev_priv->fbc.no_fbc_reason = FBC_STOLEN_TOO_SMALL;
+		if (set_no_fbc_reason(dev_priv, FBC_STOLEN_TOO_SMALL))
+			DRM_DEBUG_KMS("framebuffer too large, disabling compression\n");
 		goto out_disable;
 	}
 
@@ -587,6 +601,7 @@ void intel_update_fbc(struct drm_device *dev)
 	}
 
 	intel_enable_fbc(crtc, 500);
+	dev_priv->fbc.no_fbc_reason = FBC_OK;
 	return;
 
 out_disable:
-- 
cgit v1.2.3-70-g09d2


From bdd57d0386d892e5c470a3d615c3034389700964 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 5 Jul 2013 11:57:13 +0300
Subject: drm/i915: Add scaled paramater to update_sprite_watermarks()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For calculating watermarks we want to know whether sprites are
scaled. Pass that information to update_sprite_watermarks() so that
eventually we may do some watermark pre-computing.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_drv.h     |  2 +-
 drivers/gpu/drm/i915/intel_drv.h    |  7 ++++---
 drivers/gpu/drm/i915/intel_pm.c     | 13 +++++++------
 drivers/gpu/drm/i915/intel_sprite.c | 11 +++++++----
 4 files changed, 19 insertions(+), 14 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0b7583cafa3..67a15d00d5f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -361,7 +361,7 @@ struct drm_i915_display_funcs {
 	void (*update_wm)(struct drm_device *dev);
 	void (*update_sprite_wm)(struct drm_device *dev, int pipe,
 				 uint32_t sprite_width, int pixel_size,
-				 bool enable);
+				 bool enable, bool scaled);
 	void (*modeset_global_resources)(struct drm_device *dev);
 	/* Returns the active state of the crtc, and if the crtc is active,
 	 * fills out the pipe-config with the hw state. */
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 474797be1fc..ed33976c194 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -349,7 +349,8 @@ struct intel_plane {
 	 * for the watermark calculations. Currently only Haswell uses this.
 	 */
 	struct {
-		bool enable;
+		bool enabled;
+		bool scaled;
 		uint8_t bytes_per_pixel;
 		uint32_t horiz_pixels;
 	} wm;
@@ -770,8 +771,8 @@ extern void intel_ddi_init(struct drm_device *dev, enum port port);
 /* For use by IVB LP watermark workaround in intel_sprite.c */
 extern void intel_update_watermarks(struct drm_device *dev);
 extern void intel_update_sprite_watermarks(struct drm_device *dev, int pipe,
-					   uint32_t sprite_width,
-					   int pixel_size, bool enable);
+					   uint32_t sprite_width, int pixel_size,
+					   bool enabled, bool scaled);
 
 extern unsigned long intel_gen4_compute_page_offset(int *x, int *y,
 						    unsigned int tiling_mode,
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index b503f594205..f9813b3ead3 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2403,7 +2403,7 @@ static void hsw_compute_wm_parameters(struct drm_device *dev,
 		pipe = intel_plane->pipe;
 		p = &params[pipe];
 
-		p->sprite_enabled = intel_plane->wm.enable;
+		p->sprite_enabled = intel_plane->wm.enabled;
 		p->spr_bytes_per_pixel = intel_plane->wm.bytes_per_pixel;
 		p->spr_horiz_pixels = intel_plane->wm.horiz_pixels;
 
@@ -2631,7 +2631,7 @@ static void haswell_update_wm(struct drm_device *dev)
 
 static void haswell_update_sprite_wm(struct drm_device *dev, int pipe,
 				     uint32_t sprite_width, int pixel_size,
-				     bool enable)
+				     bool enabled, bool scaled)
 {
 	struct drm_plane *plane;
 
@@ -2639,7 +2639,8 @@ static void haswell_update_sprite_wm(struct drm_device *dev, int pipe,
 		struct intel_plane *intel_plane = to_intel_plane(plane);
 
 		if (intel_plane->pipe == pipe) {
-			intel_plane->wm.enable = enable;
+			intel_plane->wm.enabled = enabled;
+			intel_plane->wm.scaled = scaled;
 			intel_plane->wm.horiz_pixels = sprite_width + 1;
 			intel_plane->wm.bytes_per_pixel = pixel_size;
 			break;
@@ -2727,7 +2728,7 @@ sandybridge_compute_sprite_srwm(struct drm_device *dev, int plane,
 
 static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
 					 uint32_t sprite_width, int pixel_size,
-					 bool enable)
+					 bool enable, bool scaled)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int latency = SNB_READ_WM0_LATENCY() * 100;	/* In unit 0.1us */
@@ -2850,13 +2851,13 @@ void intel_update_watermarks(struct drm_device *dev)
 
 void intel_update_sprite_watermarks(struct drm_device *dev, int pipe,
 				    uint32_t sprite_width, int pixel_size,
-				    bool enable)
+				    bool enable, bool scaled)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	if (dev_priv->display.update_sprite_wm)
 		dev_priv->display.update_sprite_wm(dev, pipe, sprite_width,
-						   pixel_size, enable);
+						   pixel_size, enable, scaled);
 }
 
 static struct drm_i915_gem_object *
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 55bdf70b548..069155f17ed 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -114,7 +114,8 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_framebuffer *fb,
 	crtc_w--;
 	crtc_h--;
 
-	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true);
+	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true,
+				       src_w != crtc_w || src_h != crtc_h);
 
 	I915_WRITE(SPSTRIDE(pipe, plane), fb->pitches[0]);
 	I915_WRITE(SPPOS(pipe, plane), (crtc_y << 16) | crtc_x);
@@ -268,7 +269,8 @@ ivb_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
 	crtc_w--;
 	crtc_h--;
 
-	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true);
+	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true,
+				       src_w != crtc_w || src_h != crtc_h);
 
 	/*
 	 * IVB workaround: must disable low power watermarks for at least
@@ -336,7 +338,7 @@ ivb_disable_plane(struct drm_plane *plane)
 
 	dev_priv->sprite_scaling_enabled &= ~(1 << pipe);
 
-	intel_update_sprite_watermarks(dev, pipe, 0, 0, false);
+	intel_update_sprite_watermarks(dev, pipe, 0, 0, false, false);
 
 	/* potentially re-enable LP watermarks */
 	if (scaling_was_enabled && !dev_priv->sprite_scaling_enabled)
@@ -456,7 +458,8 @@ ilk_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
 	crtc_w--;
 	crtc_h--;
 
-	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true);
+	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true,
+				       src_w != crtc_w || src_h != crtc_h);
 
 	dvsscale = 0;
 	if (IS_GEN5(dev) || crtc_w != src_w || crtc_h != src_h)
-- 
cgit v1.2.3-70-g09d2


From 67ca28f30af8e7555f40b916c28148b432168eec Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 5 Jul 2013 11:57:14 +0300
Subject: drm/i915: Pass the actual sprite width to watermarks functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Don't subtract one from the sprite width before watermark calculations.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c     |  2 +-
 drivers/gpu/drm/i915/intel_sprite.c | 18 +++++++++---------
 2 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index f9813b3ead3..9ef476b2eee 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2641,7 +2641,7 @@ static void haswell_update_sprite_wm(struct drm_device *dev, int pipe,
 		if (intel_plane->pipe == pipe) {
 			intel_plane->wm.enabled = enabled;
 			intel_plane->wm.scaled = scaled;
-			intel_plane->wm.horiz_pixels = sprite_width + 1;
+			intel_plane->wm.horiz_pixels = sprite_width;
 			intel_plane->wm.bytes_per_pixel = pixel_size;
 			break;
 		}
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 069155f17ed..3e3a6d01cff 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -108,15 +108,15 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_framebuffer *fb,
 
 	sprctl |= SP_ENABLE;
 
+	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true,
+				       src_w != crtc_w || src_h != crtc_h);
+
 	/* Sizes are 0 based */
 	src_w--;
 	src_h--;
 	crtc_w--;
 	crtc_h--;
 
-	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true,
-				       src_w != crtc_w || src_h != crtc_h);
-
 	I915_WRITE(SPSTRIDE(pipe, plane), fb->pitches[0]);
 	I915_WRITE(SPPOS(pipe, plane), (crtc_y << 16) | crtc_x);
 
@@ -263,15 +263,15 @@ ivb_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
 	if (IS_HASWELL(dev))
 		sprctl |= SPRITE_PIPE_CSC_ENABLE;
 
+	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true,
+				       src_w != crtc_w || src_h != crtc_h);
+
 	/* Sizes are 0 based */
 	src_w--;
 	src_h--;
 	crtc_w--;
 	crtc_h--;
 
-	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true,
-				       src_w != crtc_w || src_h != crtc_h);
-
 	/*
 	 * IVB workaround: must disable low power watermarks for at least
 	 * one frame before enabling scaling.  LP watermarks can be re-enabled
@@ -452,15 +452,15 @@ ilk_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
 		dvscntr |= DVS_TRICKLE_FEED_DISABLE; /* must disable */
 	dvscntr |= DVS_ENABLE;
 
+	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true,
+				       src_w != crtc_w || src_h != crtc_h);
+
 	/* Sizes are 0 based */
 	src_w--;
 	src_h--;
 	crtc_w--;
 	crtc_h--;
 
-	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true,
-				       src_w != crtc_w || src_h != crtc_h);
-
 	dvsscale = 0;
 	if (IS_GEN5(dev) || crtc_w != src_w || crtc_h != src_h)
 		dvsscale = DVS_SCALE_ENABLE | (src_w << 16) | src_h;
-- 
cgit v1.2.3-70-g09d2


From 3658729a72b19f5e1cb92bd972939a13db970168 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 5 Jul 2013 11:57:16 +0300
Subject: drm/i915: Rename hsw_wm_get_pixel_rate to ilk_pipe_pixel_rate
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

hsw_wm_get_pixel_rate() isn't specific to HSW. In fact it should be made
to handle all gens, but for now it depends on the PCH panel fitter
state, so give it an ilk_ prefix.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 9ef476b2eee..8505e74e364 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2095,8 +2095,8 @@ static void ivybridge_update_wm(struct drm_device *dev)
 		   cursor_wm);
 }
 
-static uint32_t hsw_wm_get_pixel_rate(struct drm_device *dev,
-				      struct drm_crtc *crtc)
+static uint32_t ilk_pipe_pixel_rate(struct drm_device *dev,
+				    struct drm_crtc *crtc)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	uint32_t pixel_rate, pfit_size;
@@ -2388,7 +2388,7 @@ static void hsw_compute_wm_parameters(struct drm_device *dev,
 		pipes_active++;
 
 		p->pipe_htotal = intel_crtc->config.adjusted_mode.htotal;
-		p->pixel_rate = hsw_wm_get_pixel_rate(dev, crtc);
+		p->pixel_rate = ilk_pipe_pixel_rate(dev, crtc);
 		p->pri_bytes_per_pixel = crtc->fb->bits_per_pixel / 8;
 		p->cur_bytes_per_pixel = 4;
 		p->pri_horiz_pixels =
-- 
cgit v1.2.3-70-g09d2


From 23297044ac70da5c87b1c1ef7d5cf32c84b2fd00 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 5 Jul 2013 11:57:17 +0300
Subject: drm/i915: Rename most wm compute functions to ilk_ prefix
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These functions are appropriate for everything since ILK.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 40 ++++++++++++++++++++--------------------
 1 file changed, 20 insertions(+), 20 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 8505e74e364..6259072a288 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2126,7 +2126,7 @@ static uint32_t ilk_pipe_pixel_rate(struct drm_device *dev,
 	return pixel_rate;
 }
 
-static uint32_t hsw_wm_method1(uint32_t pixel_rate, uint8_t bytes_per_pixel,
+static uint32_t ilk_wm_method1(uint32_t pixel_rate, uint8_t bytes_per_pixel,
 			       uint32_t latency)
 {
 	uint64_t ret;
@@ -2137,7 +2137,7 @@ static uint32_t hsw_wm_method1(uint32_t pixel_rate, uint8_t bytes_per_pixel,
 	return ret;
 }
 
-static uint32_t hsw_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal,
+static uint32_t ilk_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal,
 			       uint32_t horiz_pixels, uint8_t bytes_per_pixel,
 			       uint32_t latency)
 {
@@ -2149,7 +2149,7 @@ static uint32_t hsw_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal,
 	return ret;
 }
 
-static uint32_t hsw_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels,
+static uint32_t ilk_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels,
 			   uint8_t bytes_per_pixel)
 {
 	return DIV_ROUND_UP(pri_val * 64, horiz_pixels * bytes_per_pixel) + 2;
@@ -2198,7 +2198,7 @@ enum hsw_data_buf_partitioning {
 };
 
 /* For both WM_PIPE and WM_LP. */
-static uint32_t hsw_compute_pri_wm(struct hsw_pipe_wm_parameters *params,
+static uint32_t ilk_compute_pri_wm(struct hsw_pipe_wm_parameters *params,
 				   uint32_t mem_value,
 				   bool is_lp)
 {
@@ -2208,14 +2208,14 @@ static uint32_t hsw_compute_pri_wm(struct hsw_pipe_wm_parameters *params,
 	if (!params->active)
 		return 0;
 
-	method1 = hsw_wm_method1(params->pixel_rate,
+	method1 = ilk_wm_method1(params->pixel_rate,
 				 params->pri_bytes_per_pixel,
 				 mem_value);
 
 	if (!is_lp)
 		return method1;
 
-	method2 = hsw_wm_method2(params->pixel_rate,
+	method2 = ilk_wm_method2(params->pixel_rate,
 				 params->pipe_htotal,
 				 params->pri_horiz_pixels,
 				 params->pri_bytes_per_pixel,
@@ -2225,7 +2225,7 @@ static uint32_t hsw_compute_pri_wm(struct hsw_pipe_wm_parameters *params,
 }
 
 /* For both WM_PIPE and WM_LP. */
-static uint32_t hsw_compute_spr_wm(struct hsw_pipe_wm_parameters *params,
+static uint32_t ilk_compute_spr_wm(struct hsw_pipe_wm_parameters *params,
 				   uint32_t mem_value)
 {
 	uint32_t method1, method2;
@@ -2233,10 +2233,10 @@ static uint32_t hsw_compute_spr_wm(struct hsw_pipe_wm_parameters *params,
 	if (!params->active || !params->sprite_enabled)
 		return 0;
 
-	method1 = hsw_wm_method1(params->pixel_rate,
+	method1 = ilk_wm_method1(params->pixel_rate,
 				 params->spr_bytes_per_pixel,
 				 mem_value);
-	method2 = hsw_wm_method2(params->pixel_rate,
+	method2 = ilk_wm_method2(params->pixel_rate,
 				 params->pipe_htotal,
 				 params->spr_horiz_pixels,
 				 params->spr_bytes_per_pixel,
@@ -2245,13 +2245,13 @@ static uint32_t hsw_compute_spr_wm(struct hsw_pipe_wm_parameters *params,
 }
 
 /* For both WM_PIPE and WM_LP. */
-static uint32_t hsw_compute_cur_wm(struct hsw_pipe_wm_parameters *params,
+static uint32_t ilk_compute_cur_wm(struct hsw_pipe_wm_parameters *params,
 				   uint32_t mem_value)
 {
 	if (!params->active)
 		return 0;
 
-	return hsw_wm_method2(params->pixel_rate,
+	return ilk_wm_method2(params->pixel_rate,
 			      params->pipe_htotal,
 			      params->cur_horiz_pixels,
 			      params->cur_bytes_per_pixel,
@@ -2259,14 +2259,14 @@ static uint32_t hsw_compute_cur_wm(struct hsw_pipe_wm_parameters *params,
 }
 
 /* Only for WM_LP. */
-static uint32_t hsw_compute_fbc_wm(struct hsw_pipe_wm_parameters *params,
+static uint32_t ilk_compute_fbc_wm(struct hsw_pipe_wm_parameters *params,
 				   uint32_t pri_val,
 				   uint32_t mem_value)
 {
 	if (!params->active)
 		return 0;
 
-	return hsw_wm_fbc(pri_val,
+	return ilk_wm_fbc(pri_val,
 			  params->pri_horiz_pixels,
 			  params->pri_bytes_per_pixel);
 }
@@ -2281,10 +2281,10 @@ static bool hsw_compute_lp_wm(uint32_t mem_value, struct hsw_wm_maximums *max,
 	for (pipe = PIPE_A; pipe <= PIPE_C; pipe++) {
 		struct hsw_pipe_wm_parameters *p = &params[pipe];
 
-		pri_val[pipe] = hsw_compute_pri_wm(p, mem_value, true);
-		spr_val[pipe] = hsw_compute_spr_wm(p, mem_value);
-		cur_val[pipe] = hsw_compute_cur_wm(p, mem_value);
-		fbc_val[pipe] = hsw_compute_fbc_wm(p, pri_val[pipe], mem_value);
+		pri_val[pipe] = ilk_compute_pri_wm(p, mem_value, true);
+		spr_val[pipe] = ilk_compute_spr_wm(p, mem_value);
+		cur_val[pipe] = ilk_compute_cur_wm(p, mem_value);
+		fbc_val[pipe] = ilk_compute_fbc_wm(p, pri_val[pipe], mem_value);
 	}
 
 	result->pri_val = max3(pri_val[0], pri_val[1], pri_val[2]);
@@ -2311,9 +2311,9 @@ static uint32_t hsw_compute_wm_pipe(struct drm_i915_private *dev_priv,
 {
 	uint32_t pri_val, cur_val, spr_val;
 
-	pri_val = hsw_compute_pri_wm(params, mem_value, false);
-	spr_val = hsw_compute_spr_wm(params, mem_value);
-	cur_val = hsw_compute_cur_wm(params, mem_value);
+	pri_val = ilk_compute_pri_wm(params, mem_value, false);
+	spr_val = ilk_compute_spr_wm(params, mem_value);
+	cur_val = ilk_compute_cur_wm(params, mem_value);
 
 	WARN(pri_val > 127,
 	     "Primary WM error, mode not supported for pipe %c\n",
-- 
cgit v1.2.3-70-g09d2


From 1fda9882ca0ba134134c5bf04b8d4f4f06b52649 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 5 Jul 2013 11:57:19 +0300
Subject: drm/i915: Don't pass "mem_value" to ilk_compute_fbc_wm
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The FBC watermark doesn't depend on the latency value, so no point in
passing it in.

Note: It actually depends upon the latency, but only through priv_val
...

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
[danvet: Add review comment from Paulo to the commit message.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 6259072a288..1a80787f425 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2260,8 +2260,7 @@ static uint32_t ilk_compute_cur_wm(struct hsw_pipe_wm_parameters *params,
 
 /* Only for WM_LP. */
 static uint32_t ilk_compute_fbc_wm(struct hsw_pipe_wm_parameters *params,
-				   uint32_t pri_val,
-				   uint32_t mem_value)
+				   uint32_t pri_val)
 {
 	if (!params->active)
 		return 0;
@@ -2284,7 +2283,7 @@ static bool hsw_compute_lp_wm(uint32_t mem_value, struct hsw_wm_maximums *max,
 		pri_val[pipe] = ilk_compute_pri_wm(p, mem_value, true);
 		spr_val[pipe] = ilk_compute_spr_wm(p, mem_value);
 		cur_val[pipe] = ilk_compute_cur_wm(p, mem_value);
-		fbc_val[pipe] = ilk_compute_fbc_wm(p, pri_val[pipe], mem_value);
+		fbc_val[pipe] = ilk_compute_fbc_wm(p, pri_val[pipe]);
 	}
 
 	result->pri_val = max3(pri_val[0], pri_val[1], pri_val[2]);
-- 
cgit v1.2.3-70-g09d2


From 888fd1594e38c21f8dc5aa28b90a556df32f61e0 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 5 Jul 2013 11:57:20 +0300
Subject: drm/i915: Change the watermark latency type to uint16_t
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The latency values fit in uint16_t, so let's save a few bytes.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 1a80787f425..faa4ef6c33c 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2353,7 +2353,7 @@ hsw_compute_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc)
 
 static void hsw_compute_wm_parameters(struct drm_device *dev,
 				      struct hsw_pipe_wm_parameters *params,
-				      uint32_t *wm,
+				      uint16_t *wm,
 				      struct hsw_wm_maximums *lp_max_1_2,
 				      struct hsw_wm_maximums *lp_max_5_6)
 {
@@ -2426,7 +2426,7 @@ static void hsw_compute_wm_parameters(struct drm_device *dev,
 
 static void hsw_compute_wm_results(struct drm_device *dev,
 				   struct hsw_pipe_wm_parameters *params,
-				   uint32_t *wm,
+				   uint16_t *wm,
 				   struct hsw_wm_maximums *lp_maximums,
 				   struct hsw_wm_values *results)
 {
@@ -2608,7 +2608,7 @@ static void haswell_update_wm(struct drm_device *dev)
 	struct hsw_wm_maximums lp_max_1_2, lp_max_5_6;
 	struct hsw_pipe_wm_parameters params[3];
 	struct hsw_wm_values results_1_2, results_5_6, *best_results;
-	uint32_t wm[5];
+	uint16_t wm[5];
 	enum hsw_data_buf_partitioning partitioning;
 
 	hsw_compute_wm_parameters(dev, params, wm, &lp_max_1_2, &lp_max_5_6);
-- 
cgit v1.2.3-70-g09d2


From 12b134df4e42ea1ac141388e563346777f8a1605 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 5 Jul 2013 11:57:21 +0300
Subject: drm/i915: Split out reading of HSW watermark latency values
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move parsing of MCH_SSKPD to a separate function, we'll add other
platforms there later.

Note: Chris spotted an empty struct initializer and wondered whether
that is hiding a compilier warning. Ville explained that it should
have been part of the patch that extends this function to snb/ivb,
which don't have all levels hsw has. I've figured it's ok to keep it
here with a small note.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
[danvet: Add note about the ominous struct initializer.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 34 ++++++++++++++++++++--------------
 1 file changed, 20 insertions(+), 14 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index faa4ef6c33c..b8ec1433531 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2351,28 +2351,33 @@ hsw_compute_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc)
 	       PIPE_WM_LINETIME_TIME(linetime);
 }
 
+static void intel_read_wm_latency(struct drm_device *dev, uint16_t wm[5])
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (IS_HASWELL(dev)) {
+		uint64_t sskpd = I915_READ64(MCH_SSKPD);
+
+		wm[0] = (sskpd >> 56) & 0xFF;
+		if (wm[0] == 0)
+			wm[0] = sskpd & 0xF;
+		wm[1] = ((sskpd >> 4) & 0xFF) * 5;
+		wm[2] = ((sskpd >> 12) & 0xFF) * 5;
+		wm[3] = ((sskpd >> 20) & 0x1FF) * 5;
+		wm[4] = ((sskpd >> 32) & 0x1FF) * 5;
+	}
+}
+
 static void hsw_compute_wm_parameters(struct drm_device *dev,
 				      struct hsw_pipe_wm_parameters *params,
-				      uint16_t *wm,
 				      struct hsw_wm_maximums *lp_max_1_2,
 				      struct hsw_wm_maximums *lp_max_5_6)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc;
 	struct drm_plane *plane;
-	uint64_t sskpd = I915_READ64(MCH_SSKPD);
 	enum pipe pipe;
 	int pipes_active = 0, sprites_enabled = 0;
 
-	if ((sskpd >> 56) & 0xFF)
-		wm[0] = (sskpd >> 56) & 0xFF;
-	else
-		wm[0] = sskpd & 0xF;
-	wm[1] = ((sskpd >> 4) & 0xFF) * 5;
-	wm[2] = ((sskpd >> 12) & 0xFF) * 5;
-	wm[3] = ((sskpd >> 20) & 0x1FF) * 5;
-	wm[4] = ((sskpd >> 32) & 0x1FF) * 5;
-
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 		struct hsw_pipe_wm_parameters *p;
@@ -2608,10 +2613,11 @@ static void haswell_update_wm(struct drm_device *dev)
 	struct hsw_wm_maximums lp_max_1_2, lp_max_5_6;
 	struct hsw_pipe_wm_parameters params[3];
 	struct hsw_wm_values results_1_2, results_5_6, *best_results;
-	uint16_t wm[5];
+	uint16_t wm[5] = {};
 	enum hsw_data_buf_partitioning partitioning;
 
-	hsw_compute_wm_parameters(dev, params, wm, &lp_max_1_2, &lp_max_5_6);
+	intel_read_wm_latency(dev, wm);
+	hsw_compute_wm_parameters(dev, params, &lp_max_1_2, &lp_max_5_6);
 
 	hsw_compute_wm_results(dev, params, wm, &lp_max_1_2, &results_1_2);
 	if (lp_max_1_2.pri != lp_max_5_6.pri) {
-- 
cgit v1.2.3-70-g09d2


From e5d5019e95415a99b1c0bca3dab6d8fcd39f4c65 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 5 Jul 2013 11:57:22 +0300
Subject: drm/i915: Don't multiply the watermark latency values too early
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The LP1+ watermark latency values need to be multiplied by 5 to
make them suitable for watermark calculations. However on pre-HSW
platforms we're going to need the raw value later when we have to
write it to the WM_LPn registers' latency field. So delay the
multiplication until it's needed.

Note: Paulo complains that the units of wm (now in 100ns) aren't
really clear and I agree. But that can be fixed later on ...

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
[danvet: Add a comment about the unit obfuscation.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index b8ec1433531..b6430bacc7d 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2361,10 +2361,10 @@ static void intel_read_wm_latency(struct drm_device *dev, uint16_t wm[5])
 		wm[0] = (sskpd >> 56) & 0xFF;
 		if (wm[0] == 0)
 			wm[0] = sskpd & 0xF;
-		wm[1] = ((sskpd >> 4) & 0xFF) * 5;
-		wm[2] = ((sskpd >> 12) & 0xFF) * 5;
-		wm[3] = ((sskpd >> 20) & 0x1FF) * 5;
-		wm[4] = ((sskpd >> 32) & 0x1FF) * 5;
+		wm[1] = (sskpd >> 4) & 0xFF;
+		wm[2] = (sskpd >> 12) & 0xFF;
+		wm[3] = (sskpd >> 20) & 0x1FF;
+		wm[4] = (sskpd >> 32) & 0x1FF;
 	}
 }
 
@@ -2442,7 +2442,7 @@ static void hsw_compute_wm_results(struct drm_device *dev,
 	int level, max_level, wm_lp;
 
 	for (level = 1; level <= 4; level++)
-		if (!hsw_compute_lp_wm(wm[level], lp_maximums, params,
+		if (!hsw_compute_lp_wm(wm[level] * 5, lp_maximums, params,
 				       &lp_results[level - 1]))
 			break;
 	max_level = level - 1;
-- 
cgit v1.2.3-70-g09d2


From 63cf9a131ee60fa2458d75f5c0d7a3a5dcaa2b3e Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 5 Jul 2013 11:57:23 +0300
Subject: drm/i915: Add SNB/IVB support to intel_read_wm_latency
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

SNB and IVB have slightly a different way to read out the
watermark latency values.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index b6430bacc7d..da1b6412161 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2365,6 +2365,13 @@ static void intel_read_wm_latency(struct drm_device *dev, uint16_t wm[5])
 		wm[2] = (sskpd >> 12) & 0xFF;
 		wm[3] = (sskpd >> 20) & 0x1FF;
 		wm[4] = (sskpd >> 32) & 0x1FF;
+	} else if (INTEL_INFO(dev)->gen >= 6) {
+		uint32_t sskpd = I915_READ(MCH_SSKPD);
+
+		wm[0] = (sskpd >> SSKPD_WM0_SHIFT) & SSKPD_WM_MASK;
+		wm[1] = (sskpd >> SSKPD_WM1_SHIFT) & SSKPD_WM_MASK;
+		wm[2] = (sskpd >> SSKPD_WM2_SHIFT) & SSKPD_WM_MASK;
+		wm[3] = (sskpd >> SSKPD_WM3_SHIFT) & SSKPD_WM_MASK;
 	}
 }
 
-- 
cgit v1.2.3-70-g09d2


From c37e22046148971a35a89931aa1f951bb99d5514 Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Wed, 31 Jul 2013 16:59:58 -0700
Subject: drm/i915: Add VM to pin

To verbalize it, one can say, "pin an object into the given address
space." The semantics of pinning remain the same otherwise.

Certain objects will always have to be bound into the global GTT.
Therefore, global GTT is a special case, and keep a special interface
around for it (i915_gem_obj_ggtt_pin).

v2: s/i915_gem_ggtt_pin/i915_gem_obj_ggtt_pin

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_drv.h            | 11 +++++++++++
 drivers/gpu/drm/i915/i915_gem.c            |  9 +++++----
 drivers/gpu/drm/i915/i915_gem_context.c    |  4 ++--
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |  4 +++-
 drivers/gpu/drm/i915/intel_overlay.c       |  2 +-
 drivers/gpu/drm/i915/intel_pm.c            |  2 +-
 drivers/gpu/drm/i915/intel_ringbuffer.c    |  8 ++++----
 7 files changed, 27 insertions(+), 13 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 79d4fed9d06..a8b51d525f8 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1710,6 +1710,7 @@ struct i915_vma *i915_gem_vma_create(struct drm_i915_gem_object *obj,
 void i915_gem_vma_destroy(struct i915_vma *vma);
 
 int __must_check i915_gem_object_pin(struct drm_i915_gem_object *obj,
+				     struct i915_address_space *vm,
 				     uint32_t alignment,
 				     bool map_and_fenceable,
 				     bool nonblocking);
@@ -1895,6 +1896,16 @@ i915_gem_obj_ggtt_size(struct drm_i915_gem_object *obj)
 {
 	return i915_gem_obj_size(obj, obj_to_ggtt(obj));
 }
+
+static inline int __must_check
+i915_gem_obj_ggtt_pin(struct drm_i915_gem_object *obj,
+		      uint32_t alignment,
+		      bool map_and_fenceable,
+		      bool nonblocking)
+{
+	return i915_gem_object_pin(obj, obj_to_ggtt(obj), alignment,
+				   map_and_fenceable, nonblocking);
+}
 #undef obj_to_ggtt
 
 /* i915_gem_context.c */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index c9de97ac1d0..8322dbe3ff1 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -592,7 +592,7 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev,
 	char __user *user_data;
 	int page_offset, page_length, ret;
 
-	ret = i915_gem_object_pin(obj, 0, true, true);
+	ret = i915_gem_obj_ggtt_pin(obj, 0, true, true);
 	if (ret)
 		goto out;
 
@@ -1346,7 +1346,7 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 
 	/* Now bind it into the GTT if needed */
-	ret = i915_gem_object_pin(obj, 0, true, false);
+	ret = i915_gem_obj_ggtt_pin(obj,  0, true, false);
 	if (ret)
 		goto unlock;
 
@@ -3488,7 +3488,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	 * (e.g. libkms for the bootup splash), we have to ensure that we
 	 * always use map_and_fenceable for all scanout buffers.
 	 */
-	ret = i915_gem_object_pin(obj, alignment, true, false);
+	ret = i915_gem_obj_ggtt_pin(obj, alignment, true, false);
 	if (ret)
 		return ret;
 
@@ -3631,6 +3631,7 @@ i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file)
 
 int
 i915_gem_object_pin(struct drm_i915_gem_object *obj,
+		    struct i915_address_space *vm,
 		    uint32_t alignment,
 		    bool map_and_fenceable,
 		    bool nonblocking)
@@ -3720,7 +3721,7 @@ i915_gem_pin_ioctl(struct drm_device *dev, void *data,
 	}
 
 	if (obj->user_pin_count == 0) {
-		ret = i915_gem_object_pin(obj, args->alignment, true, false);
+		ret = i915_gem_obj_ggtt_pin(obj, args->alignment, true, false);
 		if (ret)
 			goto out;
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 2470206a4d0..d1cb28cbc71 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -214,7 +214,7 @@ static int create_default_context(struct drm_i915_private *dev_priv)
 	 * default context.
 	 */
 	dev_priv->ring[RCS].default_context = ctx;
-	ret = i915_gem_object_pin(ctx->obj, CONTEXT_ALIGN, false, false);
+	ret = i915_gem_obj_ggtt_pin(ctx->obj, CONTEXT_ALIGN, false, false);
 	if (ret) {
 		DRM_DEBUG_DRIVER("Couldn't pin %d\n", ret);
 		goto err_destroy;
@@ -400,7 +400,7 @@ static int do_switch(struct i915_hw_context *to)
 	if (from == to)
 		return 0;
 
-	ret = i915_gem_object_pin(to->obj, CONTEXT_ALIGN, false, false);
+	ret = i915_gem_obj_ggtt_pin(to->obj, CONTEXT_ALIGN, false, false);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 5b6d764e9bb..7addab31783 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -409,7 +409,9 @@ i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj,
 		obj->tiling_mode != I915_TILING_NONE;
 	need_mappable = need_fence || need_reloc_mappable(obj);
 
-	ret = i915_gem_object_pin(obj, entry->alignment, need_mappable, false);
+	/* FIXME: vm plubming */
+	ret = i915_gem_object_pin(obj, &dev_priv->gtt.base, entry->alignment,
+				  need_mappable, false);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 9ec5a4e12af..ddfd0aefe0c 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -1352,7 +1352,7 @@ void intel_setup_overlay(struct drm_device *dev)
 		}
 		overlay->flip_addr = reg_bo->phys_obj->handle->busaddr;
 	} else {
-		ret = i915_gem_object_pin(reg_bo, PAGE_SIZE, true, false);
+		ret = i915_gem_obj_ggtt_pin(reg_bo, PAGE_SIZE, true, false);
 		if (ret) {
 			DRM_ERROR("failed to pin overlay register bo\n");
 			goto out_free_bo;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index da1b6412161..4c4020631b3 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2886,7 +2886,7 @@ intel_alloc_context_page(struct drm_device *dev)
 		return NULL;
 	}
 
-	ret = i915_gem_object_pin(ctx, 4096, true, false);
+	ret = i915_gem_obj_ggtt_pin(ctx, 4096, true, false);
 	if (ret) {
 		DRM_ERROR("failed to pin power context: %d\n", ret);
 		goto err_unref;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 8527ea05124..74d02a70451 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -501,7 +501,7 @@ init_pipe_control(struct intel_ring_buffer *ring)
 
 	i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
 
-	ret = i915_gem_object_pin(obj, 4096, true, false);
+	ret = i915_gem_obj_ggtt_pin(obj, 4096, true, false);
 	if (ret)
 		goto err_unref;
 
@@ -1224,7 +1224,7 @@ static int init_status_page(struct intel_ring_buffer *ring)
 
 	i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
 
-	ret = i915_gem_object_pin(obj, 4096, true, false);
+	ret = i915_gem_obj_ggtt_pin(obj, 4096, true, false);
 	if (ret != 0) {
 		goto err_unref;
 	}
@@ -1307,7 +1307,7 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 
 	ring->obj = obj;
 
-	ret = i915_gem_object_pin(obj, PAGE_SIZE, true, false);
+	ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, true, false);
 	if (ret)
 		goto err_unref;
 
@@ -1828,7 +1828,7 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 			return -ENOMEM;
 		}
 
-		ret = i915_gem_object_pin(obj, 0, true, false);
+		ret = i915_gem_obj_ggtt_pin(obj, 0, true, false);
 		if (ret != 0) {
 			drm_gem_object_unreference(&obj->base);
 			DRM_ERROR("Failed to ping batch bo\n");
-- 
cgit v1.2.3-70-g09d2


From 3a88d0ac809a7fff315b2404559d90d8e74c716c Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 1 Aug 2013 16:18:49 +0300
Subject: drm/i915: Add ILK support to intel_read_wm_latency
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ILK has a slightly different way to read out the watermark
latency values. On ILK the LP0 latenciy values are in fact
not stored in any register, and instead we must use fixed
values.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 4c4020631b3..e5e0fb2a3e9 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2372,6 +2372,13 @@ static void intel_read_wm_latency(struct drm_device *dev, uint16_t wm[5])
 		wm[1] = (sskpd >> SSKPD_WM1_SHIFT) & SSKPD_WM_MASK;
 		wm[2] = (sskpd >> SSKPD_WM2_SHIFT) & SSKPD_WM_MASK;
 		wm[3] = (sskpd >> SSKPD_WM3_SHIFT) & SSKPD_WM_MASK;
+	} else if (INTEL_INFO(dev)->gen >= 5) {
+		uint32_t mltr = I915_READ(MLTR_ILK);
+
+		/* ILK primary LP0 latency is 700 ns */
+		wm[0] = 7;
+		wm[1] = (mltr >> MLTR_WM1_SHIFT) & ILK_SRLT_MASK;
+		wm[2] = (mltr >> MLTR_WM2_SHIFT) & ILK_SRLT_MASK;
 	}
 }
 
-- 
cgit v1.2.3-70-g09d2


From 53615a5e129534fa161e882fc3c1c4f269166b76 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 1 Aug 2013 16:18:50 +0300
Subject: drm/i915: Store the watermark latency values in dev_priv
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rather than having to read the latency values out every time, just
store them in dev_priv.

On ILK and IVB there is a difference between some of the latency
values for different planes, so store the latency values for each
plane type separately, and apply the necesary fixups during init.

v2: Fix some checkpatch complaints

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_drv.h | 14 ++++++++++
 drivers/gpu/drm/i915/intel_pm.c | 62 +++++++++++++++++++++++++++++++++++------
 2 files changed, 67 insertions(+), 9 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a8b51d525f8..da1827af624 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1216,6 +1216,20 @@ typedef struct drm_i915_private {
 
 	struct i915_suspend_saved_registers regfile;
 
+	struct {
+		/*
+		 * Raw watermark latency values:
+		 * in 0.1us units for WM0,
+		 * in 0.5us units for WM1+.
+		 */
+		/* primary */
+		uint16_t pri_latency[5];
+		/* sprite */
+		uint16_t spr_latency[5];
+		/* cursor */
+		uint16_t cur_latency[5];
+	} wm;
+
 	/* Old dri1 support infrastructure, beware the dragons ya fools entering
 	 * here! */
 	struct i915_dri1_state dri1;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index e5e0fb2a3e9..87db1f064fc 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2382,6 +2382,39 @@ static void intel_read_wm_latency(struct drm_device *dev, uint16_t wm[5])
 	}
 }
 
+static void intel_fixup_spr_wm_latency(struct drm_device *dev, uint16_t wm[5])
+{
+	/* ILK sprite LP0 latency is 1300 ns */
+	if (INTEL_INFO(dev)->gen == 5)
+		wm[0] = 13;
+}
+
+static void intel_fixup_cur_wm_latency(struct drm_device *dev, uint16_t wm[5])
+{
+	/* ILK cursor LP0 latency is 1300 ns */
+	if (INTEL_INFO(dev)->gen == 5)
+		wm[0] = 13;
+
+	/* WaDoubleCursorLP3Latency:ivb */
+	if (IS_IVYBRIDGE(dev))
+		wm[3] *= 2;
+}
+
+static void intel_setup_wm_latency(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	intel_read_wm_latency(dev, dev_priv->wm.pri_latency);
+
+	memcpy(dev_priv->wm.spr_latency, dev_priv->wm.pri_latency,
+	       sizeof(dev_priv->wm.pri_latency));
+	memcpy(dev_priv->wm.cur_latency, dev_priv->wm.pri_latency,
+	       sizeof(dev_priv->wm.pri_latency));
+
+	intel_fixup_spr_wm_latency(dev, dev_priv->wm.spr_latency);
+	intel_fixup_cur_wm_latency(dev, dev_priv->wm.cur_latency);
+}
+
 static void hsw_compute_wm_parameters(struct drm_device *dev,
 				      struct hsw_pipe_wm_parameters *params,
 				      struct hsw_wm_maximums *lp_max_1_2,
@@ -2627,16 +2660,17 @@ static void haswell_update_wm(struct drm_device *dev)
 	struct hsw_wm_maximums lp_max_1_2, lp_max_5_6;
 	struct hsw_pipe_wm_parameters params[3];
 	struct hsw_wm_values results_1_2, results_5_6, *best_results;
-	uint16_t wm[5] = {};
 	enum hsw_data_buf_partitioning partitioning;
 
-	intel_read_wm_latency(dev, wm);
 	hsw_compute_wm_parameters(dev, params, &lp_max_1_2, &lp_max_5_6);
 
-	hsw_compute_wm_results(dev, params, wm, &lp_max_1_2, &results_1_2);
+	hsw_compute_wm_results(dev, params,
+			       dev_priv->wm.pri_latency,
+			       &lp_max_1_2, &results_1_2);
 	if (lp_max_1_2.pri != lp_max_5_6.pri) {
-		hsw_compute_wm_results(dev, params, wm, &lp_max_5_6,
-				       &results_5_6);
+		hsw_compute_wm_results(dev, params,
+				       dev_priv->wm.pri_latency,
+				       &lp_max_5_6, &results_5_6);
 		best_results = hsw_find_best_result(&results_1_2, &results_5_6);
 	} else {
 		best_results = &results_1_2;
@@ -5229,8 +5263,12 @@ void intel_init_pm(struct drm_device *dev)
 
 	/* For FIFO watermark updates */
 	if (HAS_PCH_SPLIT(dev)) {
+		intel_setup_wm_latency(dev);
+
 		if (IS_GEN5(dev)) {
-			if (I915_READ(MLTR_ILK) & ILK_SRLT_MASK)
+			if (dev_priv->wm.pri_latency[1] &&
+			    dev_priv->wm.spr_latency[1] &&
+			    dev_priv->wm.cur_latency[1])
 				dev_priv->display.update_wm = ironlake_update_wm;
 			else {
 				DRM_DEBUG_KMS("Failed to get proper latency. "
@@ -5239,7 +5277,9 @@ void intel_init_pm(struct drm_device *dev)
 			}
 			dev_priv->display.init_clock_gating = ironlake_init_clock_gating;
 		} else if (IS_GEN6(dev)) {
-			if (SNB_READ_WM0_LATENCY()) {
+			if (dev_priv->wm.pri_latency[0] &&
+			    dev_priv->wm.spr_latency[0] &&
+			    dev_priv->wm.cur_latency[0]) {
 				dev_priv->display.update_wm = sandybridge_update_wm;
 				dev_priv->display.update_sprite_wm = sandybridge_update_sprite_wm;
 			} else {
@@ -5249,7 +5289,9 @@ void intel_init_pm(struct drm_device *dev)
 			}
 			dev_priv->display.init_clock_gating = gen6_init_clock_gating;
 		} else if (IS_IVYBRIDGE(dev)) {
-			if (SNB_READ_WM0_LATENCY()) {
+			if (dev_priv->wm.pri_latency[0] &&
+			    dev_priv->wm.spr_latency[0] &&
+			    dev_priv->wm.cur_latency[0]) {
 				dev_priv->display.update_wm = ivybridge_update_wm;
 				dev_priv->display.update_sprite_wm = sandybridge_update_sprite_wm;
 			} else {
@@ -5259,7 +5301,9 @@ void intel_init_pm(struct drm_device *dev)
 			}
 			dev_priv->display.init_clock_gating = ivybridge_init_clock_gating;
 		} else if (IS_HASWELL(dev)) {
-			if (I915_READ64(MCH_SSKPD)) {
+			if (dev_priv->wm.pri_latency[0] &&
+			    dev_priv->wm.spr_latency[0] &&
+			    dev_priv->wm.cur_latency[0]) {
 				dev_priv->display.update_wm = haswell_update_wm;
 				dev_priv->display.update_sprite_wm =
 					haswell_update_sprite_wm;
-- 
cgit v1.2.3-70-g09d2


From 5b77da33c11b72d703382a93c402544186c7721e Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 1 Aug 2013 16:18:51 +0300
Subject: drm/i915: Use the stored cursor and plane latencies properly
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rather than pass around the plane latencies, just grab them from
dev_priv nearer to where they're needed. Do the same for cursor
latencies.

v2: Add some comments about latency units

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 36 +++++++++++++++++++++---------------
 1 file changed, 21 insertions(+), 15 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 87db1f064fc..936c1628075 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2270,7 +2270,8 @@ static uint32_t ilk_compute_fbc_wm(struct hsw_pipe_wm_parameters *params,
 			  params->pri_bytes_per_pixel);
 }
 
-static bool hsw_compute_lp_wm(uint32_t mem_value, struct hsw_wm_maximums *max,
+static bool hsw_compute_lp_wm(struct drm_i915_private *dev_priv,
+			      int level, struct hsw_wm_maximums *max,
 			      struct hsw_pipe_wm_parameters *params,
 			      struct hsw_lp_wm_result *result)
 {
@@ -2279,10 +2280,14 @@ static bool hsw_compute_lp_wm(uint32_t mem_value, struct hsw_wm_maximums *max,
 
 	for (pipe = PIPE_A; pipe <= PIPE_C; pipe++) {
 		struct hsw_pipe_wm_parameters *p = &params[pipe];
-
-		pri_val[pipe] = ilk_compute_pri_wm(p, mem_value, true);
-		spr_val[pipe] = ilk_compute_spr_wm(p, mem_value);
-		cur_val[pipe] = ilk_compute_cur_wm(p, mem_value);
+		/* WM1+ latency values stored in 0.5us units */
+		uint16_t pri_latency = dev_priv->wm.pri_latency[level] * 5;
+		uint16_t spr_latency = dev_priv->wm.spr_latency[level] * 5;
+		uint16_t cur_latency = dev_priv->wm.cur_latency[level] * 5;
+
+		pri_val[pipe] = ilk_compute_pri_wm(p, pri_latency, true);
+		spr_val[pipe] = ilk_compute_spr_wm(p, spr_latency);
+		cur_val[pipe] = ilk_compute_cur_wm(p, cur_latency);
 		fbc_val[pipe] = ilk_compute_fbc_wm(p, pri_val[pipe]);
 	}
 
@@ -2305,14 +2310,18 @@ static bool hsw_compute_lp_wm(uint32_t mem_value, struct hsw_wm_maximums *max,
 }
 
 static uint32_t hsw_compute_wm_pipe(struct drm_i915_private *dev_priv,
-				    uint32_t mem_value, enum pipe pipe,
+				    enum pipe pipe,
 				    struct hsw_pipe_wm_parameters *params)
 {
 	uint32_t pri_val, cur_val, spr_val;
+	/* WM0 latency values stored in 0.1us units */
+	uint16_t pri_latency = dev_priv->wm.pri_latency[0];
+	uint16_t spr_latency = dev_priv->wm.spr_latency[0];
+	uint16_t cur_latency = dev_priv->wm.cur_latency[0];
 
-	pri_val = ilk_compute_pri_wm(params, mem_value, false);
-	spr_val = ilk_compute_spr_wm(params, mem_value);
-	cur_val = ilk_compute_cur_wm(params, mem_value);
+	pri_val = ilk_compute_pri_wm(params, pri_latency, false);
+	spr_val = ilk_compute_spr_wm(params, spr_latency);
+	cur_val = ilk_compute_cur_wm(params, cur_latency);
 
 	WARN(pri_val > 127,
 	     "Primary WM error, mode not supported for pipe %c\n",
@@ -2478,7 +2487,6 @@ static void hsw_compute_wm_parameters(struct drm_device *dev,
 
 static void hsw_compute_wm_results(struct drm_device *dev,
 				   struct hsw_pipe_wm_parameters *params,
-				   uint16_t *wm,
 				   struct hsw_wm_maximums *lp_maximums,
 				   struct hsw_wm_values *results)
 {
@@ -2489,7 +2497,8 @@ static void hsw_compute_wm_results(struct drm_device *dev,
 	int level, max_level, wm_lp;
 
 	for (level = 1; level <= 4; level++)
-		if (!hsw_compute_lp_wm(wm[level] * 5, lp_maximums, params,
+		if (!hsw_compute_lp_wm(dev_priv, level,
+				       lp_maximums, params,
 				       &lp_results[level - 1]))
 			break;
 	max_level = level - 1;
@@ -2521,8 +2530,7 @@ static void hsw_compute_wm_results(struct drm_device *dev,
 	}
 
 	for_each_pipe(pipe)
-		results->wm_pipe[pipe] = hsw_compute_wm_pipe(dev_priv, wm[0],
-							     pipe,
+		results->wm_pipe[pipe] = hsw_compute_wm_pipe(dev_priv, pipe,
 							     &params[pipe]);
 
 	for_each_pipe(pipe) {
@@ -2665,11 +2673,9 @@ static void haswell_update_wm(struct drm_device *dev)
 	hsw_compute_wm_parameters(dev, params, &lp_max_1_2, &lp_max_5_6);
 
 	hsw_compute_wm_results(dev, params,
-			       dev_priv->wm.pri_latency,
 			       &lp_max_1_2, &results_1_2);
 	if (lp_max_1_2.pri != lp_max_5_6.pri) {
 		hsw_compute_wm_results(dev, params,
-				       dev_priv->wm.pri_latency,
 				       &lp_max_5_6, &results_5_6);
 		best_results = hsw_find_best_result(&results_1_2, &results_5_6);
 	} else {
-- 
cgit v1.2.3-70-g09d2


From 26ec971e302c53b44cc5627ffe209a7d33199e28 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 1 Aug 2013 16:18:52 +0300
Subject: drm/i915: Print the watermark latencies during init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Seeing the watermark latency values in dmesg might help sometimes.

v2: Use DRM_ERROR() when expected latency values are missing

Note: We might hit the DRM_ERROR added in this patch and apparently
there's not much we can do about that. But I think it'd be interesting
to figure out whether that actually happens in the real world, so I
didn't apply a s/DRM_ERROR/DRM_DEBUG_KMS/ bikeshed while applying.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
[danvet: Add note about new error dmesg output.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 936c1628075..8358d73ae46 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2409,6 +2409,39 @@ static void intel_fixup_cur_wm_latency(struct drm_device *dev, uint16_t wm[5])
 		wm[3] *= 2;
 }
 
+static void intel_print_wm_latency(struct drm_device *dev,
+				   const char *name,
+				   const uint16_t wm[5])
+{
+	int level, max_level;
+
+	/* how many WM levels are we expecting */
+	if (IS_HASWELL(dev))
+		max_level = 4;
+	else if (INTEL_INFO(dev)->gen >= 6)
+		max_level = 3;
+	else
+		max_level = 2;
+
+	for (level = 0; level <= max_level; level++) {
+		unsigned int latency = wm[level];
+
+		if (latency == 0) {
+			DRM_ERROR("%s WM%d latency not provided\n",
+				  name, level);
+			continue;
+		}
+
+		/* WM1+ latency values in 0.5us units */
+		if (level > 0)
+			latency *= 5;
+
+		DRM_DEBUG_KMS("%s WM%d latency %u (%u.%u usec)\n",
+			      name, level, wm[level],
+			      latency / 10, latency % 10);
+	}
+}
+
 static void intel_setup_wm_latency(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -2422,6 +2455,10 @@ static void intel_setup_wm_latency(struct drm_device *dev)
 
 	intel_fixup_spr_wm_latency(dev, dev_priv->wm.spr_latency);
 	intel_fixup_cur_wm_latency(dev, dev_priv->wm.cur_latency);
+
+	intel_print_wm_latency(dev, "Primary", dev_priv->wm.pri_latency);
+	intel_print_wm_latency(dev, "Sprite", dev_priv->wm.spr_latency);
+	intel_print_wm_latency(dev, "Cursor", dev_priv->wm.cur_latency);
 }
 
 static void hsw_compute_wm_parameters(struct drm_device *dev,
-- 
cgit v1.2.3-70-g09d2


From 3312ba65caa23cf1210cc578755babc394769843 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 1 Aug 2013 16:18:53 +0300
Subject: drm/i915: Disable specific watermark levels when latency is zero
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Return UINT_MAX for the calculated WM level if the latency is zero.
This will lead to marking the WM level as disabled.

I'm not sure if latency==0 should mean that we want to disable the
level. But that's the implication I got from the fact that we don't
even enable the watermark code of the SSKDP register is 0.

v2: Use WARN() to scare people

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 8358d73ae46..856c094a35e 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2131,6 +2131,9 @@ static uint32_t ilk_wm_method1(uint32_t pixel_rate, uint8_t bytes_per_pixel,
 {
 	uint64_t ret;
 
+	if (WARN(latency == 0, "Latency value missing\n"))
+		return UINT_MAX;
+
 	ret = (uint64_t) pixel_rate * bytes_per_pixel * latency;
 	ret = DIV_ROUND_UP_ULL(ret, 64 * 10000) + 2;
 
@@ -2143,6 +2146,9 @@ static uint32_t ilk_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal,
 {
 	uint32_t ret;
 
+	if (WARN(latency == 0, "Latency value missing\n"))
+		return UINT_MAX;
+
 	ret = (latency * pixel_rate) / (pipe_htotal * 10000);
 	ret = (ret + 1) * horiz_pixels * bytes_per_pixel;
 	ret = DIV_ROUND_UP(ret, 64) + 2;
-- 
cgit v1.2.3-70-g09d2


From b0aea5dca064176a626dc2a83727c60ace31ee6d Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 1 Aug 2013 16:18:54 +0300
Subject: drm/i915: Use the watermark latency values from dev_priv for
 ILK/SNB/IVB too
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Adjust the current ILK/SNB/IVB watermark codepaths to use the
pre-populated latency values from dev_priv instead of reading
them out from the registers every time.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_reg.h |  9 -------
 drivers/gpu/drm/i915/intel_pm.c | 57 +++++++++++++++++++----------------------
 2 files changed, 27 insertions(+), 39 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 3aebe5dee4d..fab94be89df 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3196,9 +3196,6 @@
 #define  MLTR_WM2_SHIFT		8
 /* the unit of memory self-refresh latency time is 0.5us */
 #define  ILK_SRLT_MASK		0x3f
-#define ILK_LATENCY(shift)	(I915_READ(MLTR_ILK) >> (shift) & ILK_SRLT_MASK)
-#define ILK_READ_WM1_LATENCY()	ILK_LATENCY(MLTR_WM1_SHIFT)
-#define ILK_READ_WM2_LATENCY()	ILK_LATENCY(MLTR_WM2_SHIFT)
 
 /* define the fifo size on Ironlake */
 #define ILK_DISPLAY_FIFO	128
@@ -3245,12 +3242,6 @@
 #define SSKPD_WM2_SHIFT		16
 #define SSKPD_WM3_SHIFT		24
 
-#define SNB_LATENCY(shift)	(I915_READ(MCHBAR_MIRROR_BASE_SNB + SSKPD) >> (shift) & SSKPD_WM_MASK)
-#define SNB_READ_WM0_LATENCY()		SNB_LATENCY(SSKPD_WM0_SHIFT)
-#define SNB_READ_WM1_LATENCY()		SNB_LATENCY(SSKPD_WM1_SHIFT)
-#define SNB_READ_WM2_LATENCY()		SNB_LATENCY(SSKPD_WM2_SHIFT)
-#define SNB_READ_WM3_LATENCY()		SNB_LATENCY(SSKPD_WM3_SHIFT)
-
 /*
  * The two pipe frame counter registers are not synchronized, so
  * reading a stable value is somewhat tricky. The following code
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 856c094a35e..ccaadc87b6b 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -1680,9 +1680,6 @@ static void i830_update_wm(struct drm_device *dev)
 	I915_WRITE(FW_BLC, fwater_lo);
 }
 
-#define ILK_LP0_PLANE_LATENCY		700
-#define ILK_LP0_CURSOR_LATENCY		1300
-
 /*
  * Check the wm result.
  *
@@ -1797,9 +1794,9 @@ static void ironlake_update_wm(struct drm_device *dev)
 	enabled = 0;
 	if (g4x_compute_wm0(dev, PIPE_A,
 			    &ironlake_display_wm_info,
-			    ILK_LP0_PLANE_LATENCY,
+			    dev_priv->wm.pri_latency[0] * 100,
 			    &ironlake_cursor_wm_info,
-			    ILK_LP0_CURSOR_LATENCY,
+			    dev_priv->wm.cur_latency[0] * 100,
 			    &plane_wm, &cursor_wm)) {
 		I915_WRITE(WM0_PIPEA_ILK,
 			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm);
@@ -1811,9 +1808,9 @@ static void ironlake_update_wm(struct drm_device *dev)
 
 	if (g4x_compute_wm0(dev, PIPE_B,
 			    &ironlake_display_wm_info,
-			    ILK_LP0_PLANE_LATENCY,
+			    dev_priv->wm.pri_latency[0] * 100,
 			    &ironlake_cursor_wm_info,
-			    ILK_LP0_CURSOR_LATENCY,
+			    dev_priv->wm.cur_latency[0] * 100,
 			    &plane_wm, &cursor_wm)) {
 		I915_WRITE(WM0_PIPEB_ILK,
 			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm);
@@ -1837,7 +1834,7 @@ static void ironlake_update_wm(struct drm_device *dev)
 
 	/* WM1 */
 	if (!ironlake_compute_srwm(dev, 1, enabled,
-				   ILK_READ_WM1_LATENCY() * 500,
+				   dev_priv->wm.pri_latency[1] * 500,
 				   &ironlake_display_srwm_info,
 				   &ironlake_cursor_srwm_info,
 				   &fbc_wm, &plane_wm, &cursor_wm))
@@ -1845,14 +1842,14 @@ static void ironlake_update_wm(struct drm_device *dev)
 
 	I915_WRITE(WM1_LP_ILK,
 		   WM1_LP_SR_EN |
-		   (ILK_READ_WM1_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (dev_priv->wm.pri_latency[1] << WM1_LP_LATENCY_SHIFT) |
 		   (fbc_wm << WM1_LP_FBC_SHIFT) |
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
 
 	/* WM2 */
 	if (!ironlake_compute_srwm(dev, 2, enabled,
-				   ILK_READ_WM2_LATENCY() * 500,
+				   dev_priv->wm.pri_latency[2] * 500,
 				   &ironlake_display_srwm_info,
 				   &ironlake_cursor_srwm_info,
 				   &fbc_wm, &plane_wm, &cursor_wm))
@@ -1860,7 +1857,7 @@ static void ironlake_update_wm(struct drm_device *dev)
 
 	I915_WRITE(WM2_LP_ILK,
 		   WM2_LP_EN |
-		   (ILK_READ_WM2_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (dev_priv->wm.pri_latency[2] << WM1_LP_LATENCY_SHIFT) |
 		   (fbc_wm << WM1_LP_FBC_SHIFT) |
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
@@ -1874,7 +1871,7 @@ static void ironlake_update_wm(struct drm_device *dev)
 static void sandybridge_update_wm(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int latency = SNB_READ_WM0_LATENCY() * 100;	/* In unit 0.1us */
+	int latency = dev_priv->wm.pri_latency[0] * 100;	/* In unit 0.1us */
 	u32 val;
 	int fbc_wm, plane_wm, cursor_wm;
 	unsigned int enabled;
@@ -1929,7 +1926,7 @@ static void sandybridge_update_wm(struct drm_device *dev)
 
 	/* WM1 */
 	if (!ironlake_compute_srwm(dev, 1, enabled,
-				   SNB_READ_WM1_LATENCY() * 500,
+				   dev_priv->wm.pri_latency[1] * 500,
 				   &sandybridge_display_srwm_info,
 				   &sandybridge_cursor_srwm_info,
 				   &fbc_wm, &plane_wm, &cursor_wm))
@@ -1937,14 +1934,14 @@ static void sandybridge_update_wm(struct drm_device *dev)
 
 	I915_WRITE(WM1_LP_ILK,
 		   WM1_LP_SR_EN |
-		   (SNB_READ_WM1_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (dev_priv->wm.pri_latency[1] << WM1_LP_LATENCY_SHIFT) |
 		   (fbc_wm << WM1_LP_FBC_SHIFT) |
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
 
 	/* WM2 */
 	if (!ironlake_compute_srwm(dev, 2, enabled,
-				   SNB_READ_WM2_LATENCY() * 500,
+				   dev_priv->wm.pri_latency[2] * 500,
 				   &sandybridge_display_srwm_info,
 				   &sandybridge_cursor_srwm_info,
 				   &fbc_wm, &plane_wm, &cursor_wm))
@@ -1952,14 +1949,14 @@ static void sandybridge_update_wm(struct drm_device *dev)
 
 	I915_WRITE(WM2_LP_ILK,
 		   WM2_LP_EN |
-		   (SNB_READ_WM2_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (dev_priv->wm.pri_latency[2] << WM1_LP_LATENCY_SHIFT) |
 		   (fbc_wm << WM1_LP_FBC_SHIFT) |
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
 
 	/* WM3 */
 	if (!ironlake_compute_srwm(dev, 3, enabled,
-				   SNB_READ_WM3_LATENCY() * 500,
+				   dev_priv->wm.pri_latency[3] * 500,
 				   &sandybridge_display_srwm_info,
 				   &sandybridge_cursor_srwm_info,
 				   &fbc_wm, &plane_wm, &cursor_wm))
@@ -1967,7 +1964,7 @@ static void sandybridge_update_wm(struct drm_device *dev)
 
 	I915_WRITE(WM3_LP_ILK,
 		   WM3_LP_EN |
-		   (SNB_READ_WM3_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (dev_priv->wm.pri_latency[3] << WM1_LP_LATENCY_SHIFT) |
 		   (fbc_wm << WM1_LP_FBC_SHIFT) |
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
@@ -1976,7 +1973,7 @@ static void sandybridge_update_wm(struct drm_device *dev)
 static void ivybridge_update_wm(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int latency = SNB_READ_WM0_LATENCY() * 100;	/* In unit 0.1us */
+	int latency = dev_priv->wm.pri_latency[0] * 100;	/* In unit 0.1us */
 	u32 val;
 	int fbc_wm, plane_wm, cursor_wm;
 	int ignore_fbc_wm, ignore_plane_wm, ignore_cursor_wm;
@@ -2046,7 +2043,7 @@ static void ivybridge_update_wm(struct drm_device *dev)
 
 	/* WM1 */
 	if (!ironlake_compute_srwm(dev, 1, enabled,
-				   SNB_READ_WM1_LATENCY() * 500,
+				   dev_priv->wm.pri_latency[1] * 500,
 				   &sandybridge_display_srwm_info,
 				   &sandybridge_cursor_srwm_info,
 				   &fbc_wm, &plane_wm, &cursor_wm))
@@ -2054,14 +2051,14 @@ static void ivybridge_update_wm(struct drm_device *dev)
 
 	I915_WRITE(WM1_LP_ILK,
 		   WM1_LP_SR_EN |
-		   (SNB_READ_WM1_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (dev_priv->wm.pri_latency[1] << WM1_LP_LATENCY_SHIFT) |
 		   (fbc_wm << WM1_LP_FBC_SHIFT) |
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
 
 	/* WM2 */
 	if (!ironlake_compute_srwm(dev, 2, enabled,
-				   SNB_READ_WM2_LATENCY() * 500,
+				   dev_priv->wm.pri_latency[2] * 500,
 				   &sandybridge_display_srwm_info,
 				   &sandybridge_cursor_srwm_info,
 				   &fbc_wm, &plane_wm, &cursor_wm))
@@ -2069,19 +2066,19 @@ static void ivybridge_update_wm(struct drm_device *dev)
 
 	I915_WRITE(WM2_LP_ILK,
 		   WM2_LP_EN |
-		   (SNB_READ_WM2_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (dev_priv->wm.pri_latency[2] << WM1_LP_LATENCY_SHIFT) |
 		   (fbc_wm << WM1_LP_FBC_SHIFT) |
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
 
 	/* WM3, note we have to correct the cursor latency */
 	if (!ironlake_compute_srwm(dev, 3, enabled,
-				   SNB_READ_WM3_LATENCY() * 500,
+				   dev_priv->wm.pri_latency[3] * 500,
 				   &sandybridge_display_srwm_info,
 				   &sandybridge_cursor_srwm_info,
 				   &fbc_wm, &plane_wm, &ignore_cursor_wm) ||
 	    !ironlake_compute_srwm(dev, 3, enabled,
-				   2 * SNB_READ_WM3_LATENCY() * 500,
+				   dev_priv->wm.cur_latency[3] * 500,
 				   &sandybridge_display_srwm_info,
 				   &sandybridge_cursor_srwm_info,
 				   &ignore_fbc_wm, &ignore_plane_wm, &cursor_wm))
@@ -2089,7 +2086,7 @@ static void ivybridge_update_wm(struct drm_device *dev)
 
 	I915_WRITE(WM3_LP_ILK,
 		   WM3_LP_EN |
-		   (SNB_READ_WM3_LATENCY() << WM1_LP_LATENCY_SHIFT) |
+		   (dev_priv->wm.pri_latency[3] << WM1_LP_LATENCY_SHIFT) |
 		   (fbc_wm << WM1_LP_FBC_SHIFT) |
 		   (plane_wm << WM1_LP_SR_SHIFT) |
 		   cursor_wm);
@@ -2833,7 +2830,7 @@ static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
 					 bool enable, bool scaled)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int latency = SNB_READ_WM0_LATENCY() * 100;	/* In unit 0.1us */
+	int latency = dev_priv->wm.spr_latency[0] * 100;	/* In unit 0.1us */
 	u32 val;
 	int sprite_wm, reg;
 	int ret;
@@ -2873,7 +2870,7 @@ static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
 	ret = sandybridge_compute_sprite_srwm(dev, pipe, sprite_width,
 					      pixel_size,
 					      &sandybridge_display_srwm_info,
-					      SNB_READ_WM1_LATENCY() * 500,
+					      dev_priv->wm.spr_latency[1] * 500,
 					      &sprite_wm);
 	if (!ret) {
 		DRM_DEBUG_KMS("failed to compute sprite lp1 wm on pipe %c\n",
@@ -2889,7 +2886,7 @@ static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
 	ret = sandybridge_compute_sprite_srwm(dev, pipe, sprite_width,
 					      pixel_size,
 					      &sandybridge_display_srwm_info,
-					      SNB_READ_WM2_LATENCY() * 500,
+					      dev_priv->wm.spr_latency[2] * 500,
 					      &sprite_wm);
 	if (!ret) {
 		DRM_DEBUG_KMS("failed to compute sprite lp2 wm on pipe %c\n",
@@ -2901,7 +2898,7 @@ static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
 	ret = sandybridge_compute_sprite_srwm(dev, pipe, sprite_width,
 					      pixel_size,
 					      &sandybridge_display_srwm_info,
-					      SNB_READ_WM3_LATENCY() * 500,
+					      dev_priv->wm.spr_latency[3] * 500,
 					      &sprite_wm);
 	if (!ret) {
 		DRM_DEBUG_KMS("failed to compute sprite lp3 wm on pipe %c\n",
-- 
cgit v1.2.3-70-g09d2


From 37126462a4feadeb3ff08c4b308a28e4db8c83a7 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 1 Aug 2013 16:18:55 +0300
Subject: drm/i915: Add comments about units of latency values
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All the ILK+ WM compute functions take the latency values in 0.1us
units. Add a few comments to remind people about that.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index ccaadc87b6b..c20d6829807 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2123,6 +2123,7 @@ static uint32_t ilk_pipe_pixel_rate(struct drm_device *dev,
 	return pixel_rate;
 }
 
+/* latency must be in 0.1us units. */
 static uint32_t ilk_wm_method1(uint32_t pixel_rate, uint8_t bytes_per_pixel,
 			       uint32_t latency)
 {
@@ -2137,6 +2138,7 @@ static uint32_t ilk_wm_method1(uint32_t pixel_rate, uint8_t bytes_per_pixel,
 	return ret;
 }
 
+/* latency must be in 0.1us units. */
 static uint32_t ilk_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal,
 			       uint32_t horiz_pixels, uint8_t bytes_per_pixel,
 			       uint32_t latency)
@@ -2200,7 +2202,10 @@ enum hsw_data_buf_partitioning {
 	HSW_DATA_BUF_PART_5_6,
 };
 
-/* For both WM_PIPE and WM_LP. */
+/*
+ * For both WM_PIPE and WM_LP.
+ * mem_value must be in 0.1us units.
+ */
 static uint32_t ilk_compute_pri_wm(struct hsw_pipe_wm_parameters *params,
 				   uint32_t mem_value,
 				   bool is_lp)
@@ -2227,7 +2232,10 @@ static uint32_t ilk_compute_pri_wm(struct hsw_pipe_wm_parameters *params,
 	return min(method1, method2);
 }
 
-/* For both WM_PIPE and WM_LP. */
+/*
+ * For both WM_PIPE and WM_LP.
+ * mem_value must be in 0.1us units.
+ */
 static uint32_t ilk_compute_spr_wm(struct hsw_pipe_wm_parameters *params,
 				   uint32_t mem_value)
 {
@@ -2247,7 +2255,10 @@ static uint32_t ilk_compute_spr_wm(struct hsw_pipe_wm_parameters *params,
 	return min(method1, method2);
 }
 
-/* For both WM_PIPE and WM_LP. */
+/*
+ * For both WM_PIPE and WM_LP.
+ * mem_value must be in 0.1us units.
+ */
 static uint32_t ilk_compute_cur_wm(struct hsw_pipe_wm_parameters *params,
 				   uint32_t mem_value)
 {
-- 
cgit v1.2.3-70-g09d2


From 39db4a4d7f9b2809141e5bc0e06f7a5b7daeb356 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 6 Aug 2013 22:24:00 +0300
Subject: drm/i915: Use 'enabled' instead of 'enable' consistently in sprite WM
 code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Let's be consistent and always call our variables 'enabled' insted of
the occasional 'enable'.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
[danvet: Spelling fix in the commit message, spotted by Chris.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index c20d6829807..6761717fe33 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2838,7 +2838,7 @@ sandybridge_compute_sprite_srwm(struct drm_device *dev, int plane,
 
 static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
 					 uint32_t sprite_width, int pixel_size,
-					 bool enable, bool scaled)
+					 bool enabled, bool scaled)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int latency = dev_priv->wm.spr_latency[0] * 100;	/* In unit 0.1us */
@@ -2846,7 +2846,7 @@ static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
 	int sprite_wm, reg;
 	int ret;
 
-	if (!enable)
+	if (!enabled)
 		return;
 
 	switch (pipe) {
@@ -2961,13 +2961,13 @@ void intel_update_watermarks(struct drm_device *dev)
 
 void intel_update_sprite_watermarks(struct drm_device *dev, int pipe,
 				    uint32_t sprite_width, int pixel_size,
-				    bool enable, bool scaled)
+				    bool enabled, bool scaled)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	if (dev_priv->display.update_sprite_wm)
 		dev_priv->display.update_sprite_wm(dev, pipe, sprite_width,
-						   pixel_size, enable, scaled);
+						   pixel_size, enabled, scaled);
 }
 
 static struct drm_i915_gem_object *
-- 
cgit v1.2.3-70-g09d2


From 6f5ddd170453ff44aed1b6efe53ff872295ef538 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 6 Aug 2013 22:24:02 +0300
Subject: drm/i915: Split watermark level computation from the code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Refactor the watermarks computation for one level to a separate
function. This function will now set the ->enable flag to true,
even if the watermark level wasn't actually checked yet. In the
future we will delay the checking so we must consider all unchecked
watermarks as possibly valid.

v2: Preserve comment about latency units

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 51 +++++++++++++++++++++++++++--------------
 1 file changed, 34 insertions(+), 17 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 6761717fe33..fe1992f2002 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2284,31 +2284,45 @@ static uint32_t ilk_compute_fbc_wm(struct hsw_pipe_wm_parameters *params,
 			  params->pri_bytes_per_pixel);
 }
 
+static void ilk_compute_wm_level(struct drm_i915_private *dev_priv,
+				 int level,
+				 struct hsw_pipe_wm_parameters *p,
+				 struct hsw_lp_wm_result *result)
+{
+	uint16_t pri_latency = dev_priv->wm.pri_latency[level];
+	uint16_t spr_latency = dev_priv->wm.spr_latency[level];
+	uint16_t cur_latency = dev_priv->wm.cur_latency[level];
+
+	/* WM1+ latency values stored in 0.5us units */
+	if (level > 0) {
+		pri_latency *= 5;
+		spr_latency *= 5;
+		cur_latency *= 5;
+	}
+
+	result->pri_val = ilk_compute_pri_wm(p, pri_latency, level);
+	result->spr_val = ilk_compute_spr_wm(p, spr_latency);
+	result->cur_val = ilk_compute_cur_wm(p, cur_latency);
+	result->fbc_val = ilk_compute_fbc_wm(p, result->pri_val);
+	result->enable = true;
+}
+
 static bool hsw_compute_lp_wm(struct drm_i915_private *dev_priv,
 			      int level, struct hsw_wm_maximums *max,
 			      struct hsw_pipe_wm_parameters *params,
 			      struct hsw_lp_wm_result *result)
 {
 	enum pipe pipe;
-	uint32_t pri_val[3], spr_val[3], cur_val[3], fbc_val[3];
-
-	for (pipe = PIPE_A; pipe <= PIPE_C; pipe++) {
-		struct hsw_pipe_wm_parameters *p = &params[pipe];
-		/* WM1+ latency values stored in 0.5us units */
-		uint16_t pri_latency = dev_priv->wm.pri_latency[level] * 5;
-		uint16_t spr_latency = dev_priv->wm.spr_latency[level] * 5;
-		uint16_t cur_latency = dev_priv->wm.cur_latency[level] * 5;
+	struct hsw_lp_wm_result res[3];
 
-		pri_val[pipe] = ilk_compute_pri_wm(p, pri_latency, true);
-		spr_val[pipe] = ilk_compute_spr_wm(p, spr_latency);
-		cur_val[pipe] = ilk_compute_cur_wm(p, cur_latency);
-		fbc_val[pipe] = ilk_compute_fbc_wm(p, pri_val[pipe]);
-	}
+	for (pipe = PIPE_A; pipe <= PIPE_C; pipe++)
+		ilk_compute_wm_level(dev_priv, level, &params[pipe], &res[pipe]);
 
-	result->pri_val = max3(pri_val[0], pri_val[1], pri_val[2]);
-	result->spr_val = max3(spr_val[0], spr_val[1], spr_val[2]);
-	result->cur_val = max3(cur_val[0], cur_val[1], cur_val[2]);
-	result->fbc_val = max3(fbc_val[0], fbc_val[1], fbc_val[2]);
+	result->pri_val = max3(res[0].pri_val, res[1].pri_val, res[2].pri_val);
+	result->spr_val = max3(res[0].spr_val, res[1].spr_val, res[2].spr_val);
+	result->cur_val = max3(res[0].cur_val, res[1].cur_val, res[2].cur_val);
+	result->fbc_val = max3(res[0].fbc_val, res[1].fbc_val, res[2].fbc_val);
+	result->enable = true;
 
 	if (result->fbc_val > max->fbc) {
 		result->fbc_enable = false;
@@ -2317,6 +2331,9 @@ static bool hsw_compute_lp_wm(struct drm_i915_private *dev_priv,
 		result->fbc_enable = true;
 	}
 
+	if (!result->enable)
+		return false;
+
 	result->enable = result->pri_val <= max->pri &&
 			 result->spr_val <= max->spr &&
 			 result->cur_val <= max->cur;
-- 
cgit v1.2.3-70-g09d2


From 71fff20ff1bb790f4defe0c880e028581ffab420 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 6 Aug 2013 22:24:03 +0300
Subject: drm/i915: Kill fbc_enable from hsw_lp_wm_results
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We don't need to store the FBC WM enabled status in each watermark
level. We anyway have to reduce it down to a single boolean, so just
delay checking the FBC WM limit until we're computing the final
value.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index fe1992f2002..d5f0b4e1f1c 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2182,7 +2182,6 @@ struct hsw_wm_maximums {
 
 struct hsw_lp_wm_result {
 	bool enable;
-	bool fbc_enable;
 	uint32_t pri_val;
 	uint32_t spr_val;
 	uint32_t cur_val;
@@ -2324,13 +2323,6 @@ static bool hsw_compute_lp_wm(struct drm_i915_private *dev_priv,
 	result->fbc_val = max3(res[0].fbc_val, res[1].fbc_val, res[2].fbc_val);
 	result->enable = true;
 
-	if (result->fbc_val > max->fbc) {
-		result->fbc_enable = false;
-		result->fbc_val = 0;
-	} else {
-		result->fbc_enable = true;
-	}
-
 	if (!result->enable)
 		return false;
 
@@ -2575,9 +2567,9 @@ static void hsw_compute_wm_results(struct drm_device *dev,
 	 * a WM level. */
 	results->enable_fbc_wm = true;
 	for (level = 1; level <= max_level; level++) {
-		if (!lp_results[level - 1].fbc_enable) {
+		if (!lp_results[level - 1].fbc_val > lp_maximums->fbc) {
 			results->enable_fbc_wm = false;
-			break;
+			lp_results[level - 1].fbc_val = 0;
 		}
 	}
 
-- 
cgit v1.2.3-70-g09d2


From 77c122bcc448439af7f5fcb2542406b45b606c51 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 6 Aug 2013 22:24:04 +0300
Subject: drm/i915: Rename hsw_data_buf_partitioning to intel_ddb_partitioning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We're going to use the 1/2 vs. 5/6 split option already on IVB so the
HSW name is not proper. Just give it an intel_ prefix and move it to
i915_drv.h so that we can use it there later.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_drv.h |  5 +++++
 drivers/gpu/drm/i915/intel_pm.c | 17 ++++++-----------
 2 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 2421ad17831..cb4521d9542 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1055,6 +1055,11 @@ struct intel_vbt_data {
 	struct child_device_config *child_dev;
 };
 
+enum intel_ddb_partitioning {
+	INTEL_DDB_PART_1_2,
+	INTEL_DDB_PART_5_6, /* IVB+ */
+};
+
 typedef struct drm_i915_private {
 	struct drm_device *dev;
 	struct kmem_cache *slab;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d5f0b4e1f1c..81d88d04012 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2196,11 +2196,6 @@ struct hsw_wm_values {
 	bool enable_fbc_wm;
 };
 
-enum hsw_data_buf_partitioning {
-	HSW_DATA_BUF_PART_1_2,
-	HSW_DATA_BUF_PART_5_6,
-};
-
 /*
  * For both WM_PIPE and WM_LP.
  * mem_value must be in 0.1us units.
@@ -2631,11 +2626,11 @@ static struct hsw_wm_values *hsw_find_best_result(struct hsw_wm_values *r1,
  */
 static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
 				struct hsw_wm_values *results,
-				enum hsw_data_buf_partitioning partitioning)
+				enum intel_ddb_partitioning partitioning)
 {
 	struct hsw_wm_values previous;
 	uint32_t val;
-	enum hsw_data_buf_partitioning prev_partitioning;
+	enum intel_ddb_partitioning prev_partitioning;
 	bool prev_enable_fbc_wm;
 
 	previous.wm_pipe[0] = I915_READ(WM0_PIPEA_ILK);
@@ -2652,7 +2647,7 @@ static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
 	previous.wm_linetime[2] = I915_READ(PIPE_WM_LINETIME(PIPE_C));
 
 	prev_partitioning = (I915_READ(WM_MISC) & WM_MISC_DATA_PARTITION_5_6) ?
-			    HSW_DATA_BUF_PART_5_6 : HSW_DATA_BUF_PART_1_2;
+				INTEL_DDB_PART_5_6 : INTEL_DDB_PART_1_2;
 
 	prev_enable_fbc_wm = !(I915_READ(DISP_ARB_CTL) & DISP_FBC_WM_DIS);
 
@@ -2691,7 +2686,7 @@ static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
 
 	if (prev_partitioning != partitioning) {
 		val = I915_READ(WM_MISC);
-		if (partitioning == HSW_DATA_BUF_PART_1_2)
+		if (partitioning == INTEL_DDB_PART_1_2)
 			val &= ~WM_MISC_DATA_PARTITION_5_6;
 		else
 			val |= WM_MISC_DATA_PARTITION_5_6;
@@ -2728,7 +2723,7 @@ static void haswell_update_wm(struct drm_device *dev)
 	struct hsw_wm_maximums lp_max_1_2, lp_max_5_6;
 	struct hsw_pipe_wm_parameters params[3];
 	struct hsw_wm_values results_1_2, results_5_6, *best_results;
-	enum hsw_data_buf_partitioning partitioning;
+	enum intel_ddb_partitioning partitioning;
 
 	hsw_compute_wm_parameters(dev, params, &lp_max_1_2, &lp_max_5_6);
 
@@ -2743,7 +2738,7 @@ static void haswell_update_wm(struct drm_device *dev)
 	}
 
 	partitioning = (best_results == &results_1_2) ?
-		       HSW_DATA_BUF_PART_1_2 : HSW_DATA_BUF_PART_5_6;
+		       INTEL_DDB_PART_1_2 : INTEL_DDB_PART_5_6;
 
 	hsw_write_wm_values(dev_priv, best_results, partitioning);
 }
-- 
cgit v1.2.3-70-g09d2


From a9786a119d2cd0f43d5554bddda71a5fd6ee39ff Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 7 Aug 2013 13:24:47 +0300
Subject: drm/i915: Pull watermark level validity check out
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Refactor the code a bit to split the watermark level validity check into
a separate function.

Also add hack there that allows us to use it even for LP0 watermarks.
ATM we don't pre-compute/check the LP0 watermarks, so we just have to
clamp them to the maximum and hope things work out.

v2: Add some debug prints when we exceed max WM0
    Kill pointless ret = false' assignment.
    Include the check for the already disabled 'result' which
    got shuffled around when the patchs got reorderd

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 51 +++++++++++++++++++++++++++++++++++------
 1 file changed, 44 insertions(+), 7 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 81d88d04012..b107d25282e 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2278,6 +2278,49 @@ static uint32_t ilk_compute_fbc_wm(struct hsw_pipe_wm_parameters *params,
 			  params->pri_bytes_per_pixel);
 }
 
+static bool ilk_check_wm(int level,
+			 const struct hsw_wm_maximums *max,
+			 struct hsw_lp_wm_result *result)
+{
+	bool ret;
+
+	/* already determined to be invalid? */
+	if (!result->enable)
+		return false;
+
+	result->enable = result->pri_val <= max->pri &&
+			 result->spr_val <= max->spr &&
+			 result->cur_val <= max->cur;
+
+	ret = result->enable;
+
+	/*
+	 * HACK until we can pre-compute everything,
+	 * and thus fail gracefully if LP0 watermarks
+	 * are exceeded...
+	 */
+	if (level == 0 && !result->enable) {
+		if (result->pri_val > max->pri)
+			DRM_DEBUG_KMS("Primary WM%d too large %u (max %u)\n",
+				      level, result->pri_val, max->pri);
+		if (result->spr_val > max->spr)
+			DRM_DEBUG_KMS("Sprite WM%d too large %u (max %u)\n",
+				      level, result->spr_val, max->spr);
+		if (result->cur_val > max->cur)
+			DRM_DEBUG_KMS("Cursor WM%d too large %u (max %u)\n",
+				      level, result->cur_val, max->cur);
+
+		result->pri_val = min_t(uint32_t, result->pri_val, max->pri);
+		result->spr_val = min_t(uint32_t, result->spr_val, max->spr);
+		result->cur_val = min_t(uint32_t, result->cur_val, max->cur);
+		result->enable = true;
+	}
+
+	DRM_DEBUG_KMS("WM%d: %sabled\n", level, result->enable ? "en" : "dis");
+
+	return ret;
+}
+
 static void ilk_compute_wm_level(struct drm_i915_private *dev_priv,
 				 int level,
 				 struct hsw_pipe_wm_parameters *p,
@@ -2318,13 +2361,7 @@ static bool hsw_compute_lp_wm(struct drm_i915_private *dev_priv,
 	result->fbc_val = max3(res[0].fbc_val, res[1].fbc_val, res[2].fbc_val);
 	result->enable = true;
 
-	if (!result->enable)
-		return false;
-
-	result->enable = result->pri_val <= max->pri &&
-			 result->spr_val <= max->spr &&
-			 result->cur_val <= max->cur;
-	return result->enable;
+	return ilk_check_wm(level, max, result);
 }
 
 static uint32_t hsw_compute_wm_pipe(struct drm_i915_private *dev_priv,
-- 
cgit v1.2.3-70-g09d2


From 1fd527cc34ed44efa4f59c01ad920479f728b707 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 6 Aug 2013 22:24:05 +0300
Subject: drm/i915: Rename hsw_lp_wm_result to intel_wm_level
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Let's call hsw_lp_wm_result intel_wm_level from now on and move it to
i915_drv.h for later use.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_drv.h |  8 ++++++++
 drivers/gpu/drm/i915/intel_pm.c | 20 ++++++--------------
 2 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d0cdec81aac..2cfa21fbedc 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1063,6 +1063,14 @@ enum intel_ddb_partitioning {
 	INTEL_DDB_PART_5_6, /* IVB+ */
 };
 
+struct intel_wm_level {
+	bool enable;
+	uint32_t pri_val;
+	uint32_t spr_val;
+	uint32_t cur_val;
+	uint32_t fbc_val;
+};
+
 typedef struct drm_i915_private {
 	struct drm_device *dev;
 	struct kmem_cache *slab;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index b107d25282e..d7bb61efca2 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2180,14 +2180,6 @@ struct hsw_wm_maximums {
 	uint16_t fbc;
 };
 
-struct hsw_lp_wm_result {
-	bool enable;
-	uint32_t pri_val;
-	uint32_t spr_val;
-	uint32_t cur_val;
-	uint32_t fbc_val;
-};
-
 struct hsw_wm_values {
 	uint32_t wm_pipe[3];
 	uint32_t wm_lp[3];
@@ -2280,7 +2272,7 @@ static uint32_t ilk_compute_fbc_wm(struct hsw_pipe_wm_parameters *params,
 
 static bool ilk_check_wm(int level,
 			 const struct hsw_wm_maximums *max,
-			 struct hsw_lp_wm_result *result)
+			 struct intel_wm_level *result)
 {
 	bool ret;
 
@@ -2324,7 +2316,7 @@ static bool ilk_check_wm(int level,
 static void ilk_compute_wm_level(struct drm_i915_private *dev_priv,
 				 int level,
 				 struct hsw_pipe_wm_parameters *p,
-				 struct hsw_lp_wm_result *result)
+				 struct intel_wm_level *result)
 {
 	uint16_t pri_latency = dev_priv->wm.pri_latency[level];
 	uint16_t spr_latency = dev_priv->wm.spr_latency[level];
@@ -2347,10 +2339,10 @@ static void ilk_compute_wm_level(struct drm_i915_private *dev_priv,
 static bool hsw_compute_lp_wm(struct drm_i915_private *dev_priv,
 			      int level, struct hsw_wm_maximums *max,
 			      struct hsw_pipe_wm_parameters *params,
-			      struct hsw_lp_wm_result *result)
+			      struct intel_wm_level *result)
 {
 	enum pipe pipe;
-	struct hsw_lp_wm_result res[3];
+	struct intel_wm_level res[3];
 
 	for (pipe = PIPE_A; pipe <= PIPE_C; pipe++)
 		ilk_compute_wm_level(dev_priv, level, &params[pipe], &res[pipe]);
@@ -2584,7 +2576,7 @@ static void hsw_compute_wm_results(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc;
-	struct hsw_lp_wm_result lp_results[4] = {};
+	struct intel_wm_level lp_results[4] = {};
 	enum pipe pipe;
 	int level, max_level, wm_lp;
 
@@ -2607,7 +2599,7 @@ static void hsw_compute_wm_results(struct drm_device *dev,
 
 	memset(results, 0, sizeof(*results));
 	for (wm_lp = 1; wm_lp <= 3; wm_lp++) {
-		const struct hsw_lp_wm_result *r;
+		const struct intel_wm_level *r;
 
 		level = (max_level == 4 && wm_lp > 1) ? wm_lp + 1 : wm_lp;
 		if (level > max_level)
-- 
cgit v1.2.3-70-g09d2


From 158ae64f820939473012dacfc0ae1ec782b45b60 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 7 Aug 2013 13:28:19 +0300
Subject: drm/i915: Calculate max watermark levels for ILK+
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are quite a few variables we need to take into account to
determine the maximum watermark levels, so it feels a bit cleaner
to calculate those rather than just have a bunch of what look like
magic numbers.

v2: s/pipes_active/num_pipes_active
    s/othwewise/otherwise

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 119 ++++++++++++++++++++++++++++++++++++----
 1 file changed, 107 insertions(+), 12 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d7bb61efca2..a4c3c549794 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2270,6 +2270,104 @@ static uint32_t ilk_compute_fbc_wm(struct hsw_pipe_wm_parameters *params,
 			  params->pri_bytes_per_pixel);
 }
 
+static unsigned int ilk_display_fifo_size(const struct drm_device *dev)
+{
+	if (INTEL_INFO(dev)->gen >= 7)
+		return 768;
+	else
+		return 512;
+}
+
+/* Calculate the maximum primary/sprite plane watermark */
+static unsigned int ilk_plane_wm_max(const struct drm_device *dev,
+				     int level,
+				     unsigned int num_pipes_active,
+				     bool sprite_enabled,
+				     enum intel_ddb_partitioning ddb_partitioning,
+				     bool is_sprite)
+{
+	unsigned int fifo_size = ilk_display_fifo_size(dev);
+	unsigned int max;
+
+	/* if sprites aren't enabled, sprites get nothing */
+	if (is_sprite && !sprite_enabled)
+		return 0;
+
+	/* HSW allows LP1+ watermarks even with multiple pipes */
+	if (level == 0 || num_pipes_active > 1) {
+		fifo_size /= INTEL_INFO(dev)->num_pipes;
+
+		/*
+		 * For some reason the non self refresh
+		 * FIFO size is only half of the self
+		 * refresh FIFO size on ILK/SNB.
+		 */
+		if (INTEL_INFO(dev)->gen <= 6)
+			fifo_size /= 2;
+	}
+
+	if (sprite_enabled) {
+		/* level 0 is always calculated with 1:1 split */
+		if (level > 0 && ddb_partitioning == INTEL_DDB_PART_5_6) {
+			if (is_sprite)
+				fifo_size *= 5;
+			fifo_size /= 6;
+		} else {
+			fifo_size /= 2;
+		}
+	}
+
+	/* clamp to max that the registers can hold */
+	if (INTEL_INFO(dev)->gen >= 7)
+		/* IVB/HSW primary/sprite plane watermarks */
+		max = level == 0 ? 127 : 1023;
+	else if (!is_sprite)
+		/* ILK/SNB primary plane watermarks */
+		max = level == 0 ? 127 : 511;
+	else
+		/* ILK/SNB sprite plane watermarks */
+		max = level == 0 ? 63 : 255;
+
+	return min(fifo_size, max);
+}
+
+/* Calculate the maximum cursor plane watermark */
+static unsigned int ilk_cursor_wm_max(const struct drm_device *dev,
+				      int level, unsigned int num_pipes_active)
+{
+	/* HSW LP1+ watermarks w/ multiple pipes */
+	if (level > 0 && num_pipes_active > 1)
+		return 64;
+
+	/* otherwise just report max that registers can hold */
+	if (INTEL_INFO(dev)->gen >= 7)
+		return level == 0 ? 63 : 255;
+	else
+		return level == 0 ? 31 : 63;
+}
+
+/* Calculate the maximum FBC watermark */
+static unsigned int ilk_fbc_wm_max(void)
+{
+	/* max that registers can hold */
+	return 15;
+}
+
+static void ilk_wm_max(struct drm_device *dev,
+		       int level,
+		       unsigned int num_pipes_active,
+		       bool sprite_enabled,
+		       enum intel_ddb_partitioning ddb_partitioning,
+		       struct hsw_wm_maximums *max)
+{
+	max->pri = ilk_plane_wm_max(dev, level, num_pipes_active,
+				    sprite_enabled, ddb_partitioning, false);
+	max->spr = ilk_plane_wm_max(dev, level, num_pipes_active,
+				    sprite_enabled, ddb_partitioning, true);
+	max->cur = ilk_cursor_wm_max(dev, level, num_pipes_active);
+	max->fbc = ilk_fbc_wm_max();
+}
+
 static bool ilk_check_wm(int level,
 			 const struct hsw_wm_maximums *max,
 			 struct intel_wm_level *result)
@@ -2555,18 +2653,15 @@ static void hsw_compute_wm_parameters(struct drm_device *dev,
 			sprites_enabled++;
 	}
 
-	if (pipes_active > 1) {
-		lp_max_1_2->pri = lp_max_5_6->pri = sprites_enabled ? 128 : 256;
-		lp_max_1_2->spr = lp_max_5_6->spr = 128;
-		lp_max_1_2->cur = lp_max_5_6->cur = 64;
-	} else {
-		lp_max_1_2->pri = sprites_enabled ? 384 : 768;
-		lp_max_5_6->pri = sprites_enabled ? 128 : 768;
-		lp_max_1_2->spr = 384;
-		lp_max_5_6->spr = 640;
-		lp_max_1_2->cur = lp_max_5_6->cur = 255;
-	}
-	lp_max_1_2->fbc = lp_max_5_6->fbc = 15;
+	ilk_wm_max(dev, 1, pipes_active, sprites_enabled,
+		   INTEL_DDB_PART_1_2, lp_max_1_2);
+
+	/* 5/6 split only in single pipe config on IVB+ */
+	if (INTEL_INFO(dev)->gen >= 7 && pipes_active <= 1)
+		ilk_wm_max(dev, 1, pipes_active, sprites_enabled,
+			   INTEL_DDB_PART_5_6, lp_max_5_6);
+	else
+		*lp_max_5_6 = *lp_max_1_2;
 }
 
 static void hsw_compute_wm_results(struct drm_device *dev,
-- 
cgit v1.2.3-70-g09d2


From 240264f49edbe02eb96b472ae1c518cc413f9d01 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 7 Aug 2013 13:29:12 +0300
Subject: drm/i915: Pull some watermarks state into a separate structure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a bunch of global state that needs to be considered when
checking watermarks for validity. Move most of that to a new
structure intel_wm_config, to avoid having to pass around so
many variables.

One notable thing left out is the DDB partitioning information,
since we often anyway need to check the same watermarks against
both 1/2 and 5/6 DDB partitioning layouts.

v2: s/pipes_active/num_pipes_active

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 48 +++++++++++++++++++++--------------------
 1 file changed, 25 insertions(+), 23 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index a4c3c549794..550f787a3b4 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2188,6 +2188,14 @@ struct hsw_wm_values {
 	bool enable_fbc_wm;
 };
 
+/* used in computing the new watermarks state */
+struct intel_wm_config {
+	unsigned int num_pipes_active;
+	bool sprites_enabled;
+	bool sprites_scaled;
+	bool fbc_wm_enabled;
+};
+
 /*
  * For both WM_PIPE and WM_LP.
  * mem_value must be in 0.1us units.
@@ -2281,8 +2289,7 @@ static unsigned int ilk_display_fifo_size(const struct drm_device *dev)
 /* Calculate the maximum primary/sprite plane watermark */
 static unsigned int ilk_plane_wm_max(const struct drm_device *dev,
 				     int level,
-				     unsigned int num_pipes_active,
-				     bool sprite_enabled,
+				     const struct intel_wm_config *config,
 				     enum intel_ddb_partitioning ddb_partitioning,
 				     bool is_sprite)
 {
@@ -2290,11 +2297,11 @@ static unsigned int ilk_plane_wm_max(const struct drm_device *dev,
 	unsigned int max;
 
 	/* if sprites aren't enabled, sprites get nothing */
-	if (is_sprite && !sprite_enabled)
+	if (is_sprite && !config->sprites_enabled)
 		return 0;
 
 	/* HSW allows LP1+ watermarks even with multiple pipes */
-	if (level == 0 || num_pipes_active > 1) {
+	if (level == 0 || config->num_pipes_active > 1) {
 		fifo_size /= INTEL_INFO(dev)->num_pipes;
 
 		/*
@@ -2306,7 +2313,7 @@ static unsigned int ilk_plane_wm_max(const struct drm_device *dev,
 			fifo_size /= 2;
 	}
 
-	if (sprite_enabled) {
+	if (config->sprites_enabled) {
 		/* level 0 is always calculated with 1:1 split */
 		if (level > 0 && ddb_partitioning == INTEL_DDB_PART_5_6) {
 			if (is_sprite)
@@ -2333,10 +2340,11 @@ static unsigned int ilk_plane_wm_max(const struct drm_device *dev,
 
 /* Calculate the maximum cursor plane watermark */
 static unsigned int ilk_cursor_wm_max(const struct drm_device *dev,
-				      int level, unsigned int num_pipes_active)
+				      int level,
+				      const struct intel_wm_config *config)
 {
 	/* HSW LP1+ watermarks w/ multiple pipes */
-	if (level > 0 && num_pipes_active > 1)
+	if (level > 0 && config->num_pipes_active > 1)
 		return 64;
 
 	/* otherwise just report max that registers can hold */
@@ -2355,16 +2363,13 @@ static unsigned int ilk_fbc_wm_max(void)
 
 static void ilk_wm_max(struct drm_device *dev,
 		       int level,
-		       unsigned int num_pipes_active,
-		       bool sprite_enabled,
+		       const struct intel_wm_config *config,
 		       enum intel_ddb_partitioning ddb_partitioning,
 		       struct hsw_wm_maximums *max)
 {
-	max->pri = ilk_plane_wm_max(dev, level, num_pipes_active,
-				    sprite_enabled, ddb_partitioning, false);
-	max->spr = ilk_plane_wm_max(dev, level, num_pipes_active,
-				    sprite_enabled, ddb_partitioning, true);
-	max->cur = ilk_cursor_wm_max(dev, level, num_pipes_active);
+	max->pri = ilk_plane_wm_max(dev, level, config, ddb_partitioning, false);
+	max->spr = ilk_plane_wm_max(dev, level, config, ddb_partitioning, true);
+	max->cur = ilk_cursor_wm_max(dev, level, config);
 	max->fbc = ilk_fbc_wm_max();
 }
 
@@ -2614,7 +2619,7 @@ static void hsw_compute_wm_parameters(struct drm_device *dev,
 	struct drm_crtc *crtc;
 	struct drm_plane *plane;
 	enum pipe pipe;
-	int pipes_active = 0, sprites_enabled = 0;
+	struct intel_wm_config config = {};
 
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
@@ -2627,7 +2632,7 @@ static void hsw_compute_wm_parameters(struct drm_device *dev,
 		if (!p->active)
 			continue;
 
-		pipes_active++;
+		config.num_pipes_active++;
 
 		p->pipe_htotal = intel_crtc->config.adjusted_mode.htotal;
 		p->pixel_rate = ilk_pipe_pixel_rate(dev, crtc);
@@ -2649,17 +2654,14 @@ static void hsw_compute_wm_parameters(struct drm_device *dev,
 		p->spr_bytes_per_pixel = intel_plane->wm.bytes_per_pixel;
 		p->spr_horiz_pixels = intel_plane->wm.horiz_pixels;
 
-		if (p->sprite_enabled)
-			sprites_enabled++;
+		config.sprites_enabled |= p->sprite_enabled;
 	}
 
-	ilk_wm_max(dev, 1, pipes_active, sprites_enabled,
-		   INTEL_DDB_PART_1_2, lp_max_1_2);
+	ilk_wm_max(dev, 1, &config, INTEL_DDB_PART_1_2, lp_max_1_2);
 
 	/* 5/6 split only in single pipe config on IVB+ */
-	if (INTEL_INFO(dev)->gen >= 7 && pipes_active <= 1)
-		ilk_wm_max(dev, 1, pipes_active, sprites_enabled,
-			   INTEL_DDB_PART_5_6, lp_max_5_6);
+	if (INTEL_INFO(dev)->gen >= 7 && config.num_pipes_active <= 1)
+		ilk_wm_max(dev, 1, &config, INTEL_DDB_PART_5_6, lp_max_5_6);
 	else
 		*lp_max_5_6 = *lp_max_1_2;
 }
-- 
cgit v1.2.3-70-g09d2


From c35426d2bc25b242ee2a9a7a1d62634be1e86bb0 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 7 Aug 2013 13:29:50 +0300
Subject: drm/i915: Split plane watermark parameters into a separate struct
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Give a name to the plane watermark related data we have currently
stored under intel_plane->wm.

We also observe that this data is more or less the same that we have
in the hsw_pipe_wm_parameters structure, so use it there as well.

v2: Make pahole happier

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_drv.h | 14 +++++-----
 drivers/gpu/drm/i915/intel_pm.c  | 57 +++++++++++++++++++---------------------
 2 files changed, 35 insertions(+), 36 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 7df662bab28..3ea8e5fe440 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -331,6 +331,13 @@ struct intel_crtc {
 	bool pch_fifo_underrun_disabled;
 };
 
+struct intel_plane_wm_parameters {
+	uint32_t horiz_pixels;
+	uint8_t bytes_per_pixel;
+	bool enabled;
+	bool scaled;
+};
+
 struct intel_plane {
 	struct drm_plane base;
 	int plane;
@@ -349,12 +356,7 @@ struct intel_plane {
 	 * as the other pieces of the struct may not reflect the values we want
 	 * for the watermark calculations. Currently only Haswell uses this.
 	 */
-	struct {
-		bool enabled;
-		bool scaled;
-		uint8_t bytes_per_pixel;
-		uint32_t horiz_pixels;
-	} wm;
+	struct intel_plane_wm_parameters wm;
 
 	void (*update_plane)(struct drm_plane *plane,
 			     struct drm_framebuffer *fb,
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 550f787a3b4..ed772fecbb0 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2162,15 +2162,11 @@ static uint32_t ilk_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels,
 
 struct hsw_pipe_wm_parameters {
 	bool active;
-	bool sprite_enabled;
-	uint8_t pri_bytes_per_pixel;
-	uint8_t spr_bytes_per_pixel;
-	uint8_t cur_bytes_per_pixel;
-	uint32_t pri_horiz_pixels;
-	uint32_t spr_horiz_pixels;
-	uint32_t cur_horiz_pixels;
 	uint32_t pipe_htotal;
 	uint32_t pixel_rate;
+	struct intel_plane_wm_parameters pri;
+	struct intel_plane_wm_parameters spr;
+	struct intel_plane_wm_parameters cur;
 };
 
 struct hsw_wm_maximums {
@@ -2206,12 +2202,11 @@ static uint32_t ilk_compute_pri_wm(struct hsw_pipe_wm_parameters *params,
 {
 	uint32_t method1, method2;
 
-	/* TODO: for now, assume the primary plane is always enabled. */
-	if (!params->active)
+	if (!params->active || !params->pri.enabled)
 		return 0;
 
 	method1 = ilk_wm_method1(params->pixel_rate,
-				 params->pri_bytes_per_pixel,
+				 params->pri.bytes_per_pixel,
 				 mem_value);
 
 	if (!is_lp)
@@ -2219,8 +2214,8 @@ static uint32_t ilk_compute_pri_wm(struct hsw_pipe_wm_parameters *params,
 
 	method2 = ilk_wm_method2(params->pixel_rate,
 				 params->pipe_htotal,
-				 params->pri_horiz_pixels,
-				 params->pri_bytes_per_pixel,
+				 params->pri.horiz_pixels,
+				 params->pri.bytes_per_pixel,
 				 mem_value);
 
 	return min(method1, method2);
@@ -2235,16 +2230,16 @@ static uint32_t ilk_compute_spr_wm(struct hsw_pipe_wm_parameters *params,
 {
 	uint32_t method1, method2;
 
-	if (!params->active || !params->sprite_enabled)
+	if (!params->active || !params->spr.enabled)
 		return 0;
 
 	method1 = ilk_wm_method1(params->pixel_rate,
-				 params->spr_bytes_per_pixel,
+				 params->spr.bytes_per_pixel,
 				 mem_value);
 	method2 = ilk_wm_method2(params->pixel_rate,
 				 params->pipe_htotal,
-				 params->spr_horiz_pixels,
-				 params->spr_bytes_per_pixel,
+				 params->spr.horiz_pixels,
+				 params->spr.bytes_per_pixel,
 				 mem_value);
 	return min(method1, method2);
 }
@@ -2256,13 +2251,13 @@ static uint32_t ilk_compute_spr_wm(struct hsw_pipe_wm_parameters *params,
 static uint32_t ilk_compute_cur_wm(struct hsw_pipe_wm_parameters *params,
 				   uint32_t mem_value)
 {
-	if (!params->active)
+	if (!params->active || !params->cur.enabled)
 		return 0;
 
 	return ilk_wm_method2(params->pixel_rate,
 			      params->pipe_htotal,
-			      params->cur_horiz_pixels,
-			      params->cur_bytes_per_pixel,
+			      params->cur.horiz_pixels,
+			      params->cur.bytes_per_pixel,
 			      mem_value);
 }
 
@@ -2270,12 +2265,12 @@ static uint32_t ilk_compute_cur_wm(struct hsw_pipe_wm_parameters *params,
 static uint32_t ilk_compute_fbc_wm(struct hsw_pipe_wm_parameters *params,
 				   uint32_t pri_val)
 {
-	if (!params->active)
+	if (!params->active || !params->pri.enabled)
 		return 0;
 
 	return ilk_wm_fbc(pri_val,
-			  params->pri_horiz_pixels,
-			  params->pri_bytes_per_pixel);
+			  params->pri.horiz_pixels,
+			  params->pri.bytes_per_pixel);
 }
 
 static unsigned int ilk_display_fifo_size(const struct drm_device *dev)
@@ -2636,11 +2631,14 @@ static void hsw_compute_wm_parameters(struct drm_device *dev,
 
 		p->pipe_htotal = intel_crtc->config.adjusted_mode.htotal;
 		p->pixel_rate = ilk_pipe_pixel_rate(dev, crtc);
-		p->pri_bytes_per_pixel = crtc->fb->bits_per_pixel / 8;
-		p->cur_bytes_per_pixel = 4;
-		p->pri_horiz_pixels =
+		p->pri.bytes_per_pixel = crtc->fb->bits_per_pixel / 8;
+		p->cur.bytes_per_pixel = 4;
+		p->pri.horiz_pixels =
 			intel_crtc->config.requested_mode.hdisplay;
-		p->cur_horiz_pixels = 64;
+		p->cur.horiz_pixels = 64;
+		/* TODO: for now, assume primary and cursor planes are always enabled. */
+		p->pri.enabled = true;
+		p->cur.enabled = true;
 	}
 
 	list_for_each_entry(plane, &dev->mode_config.plane_list, head) {
@@ -2650,11 +2648,10 @@ static void hsw_compute_wm_parameters(struct drm_device *dev,
 		pipe = intel_plane->pipe;
 		p = &params[pipe];
 
-		p->sprite_enabled = intel_plane->wm.enabled;
-		p->spr_bytes_per_pixel = intel_plane->wm.bytes_per_pixel;
-		p->spr_horiz_pixels = intel_plane->wm.horiz_pixels;
+		p->spr = intel_plane->wm;
 
-		config.sprites_enabled |= p->sprite_enabled;
+		config.sprites_enabled |= p->spr.enabled;
+		config.sprites_scaled |= p->spr.scaled;
 	}
 
 	ilk_wm_max(dev, 1, &config, INTEL_DDB_PART_1_2, lp_max_1_2);
-- 
cgit v1.2.3-70-g09d2


From adf3d35e4aced032f0449c6d69b0a90fea14692f Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 6 Aug 2013 22:24:11 +0300
Subject: drm/i915: Pass plane and crtc to intel_update_sprite_watermarks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We're going to want to know the crtc in the watermark code to avoid
doing more work than we have to. We should also pass the plane we're
disabling so that we know where to stick our watermark parameters
without having to go look the plane up.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_drv.h     |  3 ++-
 drivers/gpu/drm/i915/intel_drv.h    |  3 ++-
 drivers/gpu/drm/i915/intel_pm.c     | 34 ++++++++++++++++------------------
 drivers/gpu/drm/i915/intel_sprite.c |  8 ++++----
 4 files changed, 24 insertions(+), 24 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 2cfa21fbedc..550ad171628 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -359,7 +359,8 @@ struct drm_i915_display_funcs {
 			  struct dpll *match_clock,
 			  struct dpll *best_clock);
 	void (*update_wm)(struct drm_device *dev);
-	void (*update_sprite_wm)(struct drm_device *dev, int pipe,
+	void (*update_sprite_wm)(struct drm_plane *plane,
+				 struct drm_crtc *crtc,
 				 uint32_t sprite_width, int pixel_size,
 				 bool enable, bool scaled);
 	void (*modeset_global_resources)(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index da394f35445..caf8b8dfe17 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -716,7 +716,8 @@ extern void intel_ddi_init(struct drm_device *dev, enum port port);
 
 /* For use by IVB LP watermark workaround in intel_sprite.c */
 extern void intel_update_watermarks(struct drm_device *dev);
-extern void intel_update_sprite_watermarks(struct drm_device *dev, int pipe,
+extern void intel_update_sprite_watermarks(struct drm_plane *plane,
+					   struct drm_crtc *crtc,
 					   uint32_t sprite_width, int pixel_size,
 					   bool enabled, bool scaled);
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index ed772fecbb0..023e287da01 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2866,25 +2866,19 @@ static void haswell_update_wm(struct drm_device *dev)
 	hsw_write_wm_values(dev_priv, best_results, partitioning);
 }
 
-static void haswell_update_sprite_wm(struct drm_device *dev, int pipe,
+static void haswell_update_sprite_wm(struct drm_plane *plane,
+				     struct drm_crtc *crtc,
 				     uint32_t sprite_width, int pixel_size,
 				     bool enabled, bool scaled)
 {
-	struct drm_plane *plane;
-
-	list_for_each_entry(plane, &dev->mode_config.plane_list, head) {
-		struct intel_plane *intel_plane = to_intel_plane(plane);
+	struct intel_plane *intel_plane = to_intel_plane(plane);
 
-		if (intel_plane->pipe == pipe) {
-			intel_plane->wm.enabled = enabled;
-			intel_plane->wm.scaled = scaled;
-			intel_plane->wm.horiz_pixels = sprite_width;
-			intel_plane->wm.bytes_per_pixel = pixel_size;
-			break;
-		}
-	}
+	intel_plane->wm.enabled = enabled;
+	intel_plane->wm.scaled = scaled;
+	intel_plane->wm.horiz_pixels = sprite_width;
+	intel_plane->wm.bytes_per_pixel = pixel_size;
 
-	haswell_update_wm(dev);
+	haswell_update_wm(plane->dev);
 }
 
 static bool
@@ -2963,11 +2957,14 @@ sandybridge_compute_sprite_srwm(struct drm_device *dev, int plane,
 	return *sprite_wm > 0x3ff ? false : true;
 }
 
-static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
+static void sandybridge_update_sprite_wm(struct drm_plane *plane,
+					 struct drm_crtc *crtc,
 					 uint32_t sprite_width, int pixel_size,
 					 bool enabled, bool scaled)
 {
+	struct drm_device *dev = plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	int pipe = to_intel_plane(plane)->pipe;
 	int latency = dev_priv->wm.spr_latency[0] * 100;	/* In unit 0.1us */
 	u32 val;
 	int sprite_wm, reg;
@@ -3086,14 +3083,15 @@ void intel_update_watermarks(struct drm_device *dev)
 		dev_priv->display.update_wm(dev);
 }
 
-void intel_update_sprite_watermarks(struct drm_device *dev, int pipe,
+void intel_update_sprite_watermarks(struct drm_plane *plane,
+				    struct drm_crtc *crtc,
 				    uint32_t sprite_width, int pixel_size,
 				    bool enabled, bool scaled)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = plane->dev->dev_private;
 
 	if (dev_priv->display.update_sprite_wm)
-		dev_priv->display.update_sprite_wm(dev, pipe, sprite_width,
+		dev_priv->display.update_sprite_wm(plane, crtc, sprite_width,
 						   pixel_size, enabled, scaled);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 0a174d7e585..05742f7d700 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -109,7 +109,7 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
 
 	sprctl |= SP_ENABLE;
 
-	intel_update_sprite_watermarks(dev, pipe, src_w, pixel_size, true,
+	intel_update_sprite_watermarks(dplane, crtc, src_w, pixel_size, true,
 				       src_w != crtc_w || src_h != crtc_h);
 
 	/* Sizes are 0 based */
@@ -265,7 +265,7 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	if (IS_HASWELL(dev))
 		sprctl |= SPRITE_PIPE_CSC_ENABLE;
 
-	intel_update_sprite_watermarks(dev, pipe, src_w, pixel_size, true,
+	intel_update_sprite_watermarks(plane, crtc, src_w, pixel_size, true,
 				       src_w != crtc_w || src_h != crtc_h);
 
 	/* Sizes are 0 based */
@@ -340,7 +340,7 @@ ivb_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 
 	dev_priv->sprite_scaling_enabled &= ~(1 << pipe);
 
-	intel_update_sprite_watermarks(dev, pipe, 0, 0, false, false);
+	intel_update_sprite_watermarks(plane, crtc, 0, 0, false, false);
 
 	/* potentially re-enable LP watermarks */
 	if (scaling_was_enabled && !dev_priv->sprite_scaling_enabled)
@@ -455,7 +455,7 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 		dvscntr |= DVS_TRICKLE_FEED_DISABLE; /* must disable */
 	dvscntr |= DVS_ENABLE;
 
-	intel_update_sprite_watermarks(dev, pipe, src_w, pixel_size, true,
+	intel_update_sprite_watermarks(plane, crtc, src_w, pixel_size, true,
 				       src_w != crtc_w || src_h != crtc_h);
 
 	/* Sizes are 0 based */
-- 
cgit v1.2.3-70-g09d2


From 16e54061ecc81df66e80ce96b3f91ae56065ed9e Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 9 Aug 2013 13:07:31 +0300
Subject: drm/i915: fix a limit check in hsw_compute_wm_results()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The '!' here was not intended.  Since '!' has higher precedence than
compare, it means the check is never true.

This regression was introduced in

commit 71fff20ff1bb790f4defe0c880e028581ffab420
Author: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date:   Tue Aug 6 22:24:03 2013 +0300

    drm/i915: Kill fbc_enable from hsw_lp_wm_results

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 023e287da01..6643069eccd 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2685,7 +2685,7 @@ static void hsw_compute_wm_results(struct drm_device *dev,
 	 * a WM level. */
 	results->enable_fbc_wm = true;
 	for (level = 1; level <= max_level; level++) {
-		if (!lp_results[level - 1].fbc_val > lp_maximums->fbc) {
+		if (lp_results[level - 1].fbc_val > lp_maximums->fbc) {
 			results->enable_fbc_wm = false;
 			lp_results[level - 1].fbc_val = 0;
 		}
-- 
cgit v1.2.3-70-g09d2


From 5c536613d8ebda3da0448550d0a997651a6048e2 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 9 Aug 2013 18:02:09 +0300
Subject: drm/i915: Fix FB WM for HSW
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Due to a misplaced memset(), we never actually enabled the FBC WM on HSW.
Move the memset() to happen a bit earlier, so that it won't clobber
results->enable_fbc_wm.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 6643069eccd..3ac5fe9d428 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2681,6 +2681,8 @@ static void hsw_compute_wm_results(struct drm_device *dev,
 			break;
 	max_level = level - 1;
 
+	memset(results, 0, sizeof(*results));
+
 	/* The spec says it is preferred to disable FBC WMs instead of disabling
 	 * a WM level. */
 	results->enable_fbc_wm = true;
@@ -2691,7 +2693,6 @@ static void hsw_compute_wm_results(struct drm_device *dev,
 		}
 	}
 
-	memset(results, 0, sizeof(*results));
 	for (wm_lp = 1; wm_lp <= 3; wm_lp++) {
 		const struct intel_wm_level *r;
 
-- 
cgit v1.2.3-70-g09d2


From 351aa5666d02062b52329bcfe4bcf9d1f882fba9 Mon Sep 17 00:00:00 2001
From: Stéphane Marchesin <marcheu@chromium.org>
Date: Tue, 13 Aug 2013 11:55:17 -0700
Subject: drm/i915: tune the RC6 threshold for stability
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It's basically the same deal as the RC6+ issues on ivy bridge
except this time with RC6 on sandy bridge. Like last time the
core of the issue is that the timings don't work 100% with our
voltage regulator. So from time to time, the kernel will print
a warning message about the GPU not getting out of RC6. In
particular, I found this fairly easy to reproduce during
suspend/resume.

Changing the threshold to 125000 instead of 50000 seems to fix
the issue. The previous patch used 150000 but as it turns out
this doesn't work everywhere. After getting such a machine, I
bisected the highest value which works, which is 125000, so here
it is.

I also measured the idle power usage before/after this patch and
didn't see a difference on a sandy bridge laptop. On haswell and
up, it makes a big difference, so we want to keep it at 50k
there. It also seems like haswell doesn't have the RC6 issues
that sandy bridge has so the 50k value is fine.

Signed-off-by: Stéphane Marchesin <marcheu@chromium.org>
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 3ac5fe9d428..76150818b5c 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3508,7 +3508,10 @@ static void gen6_enable_rps(struct drm_device *dev)
 
 	I915_WRITE(GEN6_RC_SLEEP, 0);
 	I915_WRITE(GEN6_RC1e_THRESHOLD, 1000);
-	I915_WRITE(GEN6_RC6_THRESHOLD, 50000);
+	if (INTEL_INFO(dev)->gen <= 6 || IS_IVYBRIDGE(dev))
+		I915_WRITE(GEN6_RC6_THRESHOLD, 125000);
+	else
+		I915_WRITE(GEN6_RC6_THRESHOLD, 50000);
 	I915_WRITE(GEN6_RC6p_THRESHOLD, 150000);
 	I915_WRITE(GEN6_RC6pp_THRESHOLD, 64000); /* unused */
 
-- 
cgit v1.2.3-70-g09d2


From 6aedd1f539f51b7b0c3d6be0088c3541f9d2c294 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 2 Aug 2013 16:22:25 -0300
Subject: drm/i915: clarify Haswell power well bit names

Whenever I need to work with the HSW_PWER_WELL_* register bits I have
to look at the documentation to find out which bit is to request the
power well and which one shows its current state. Rename the bits so I
won't need to look the docs every time.

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_reg.h      |  4 ++--
 drivers/gpu/drm/i915/intel_display.c |  2 +-
 drivers/gpu/drm/i915/intel_pm.c      | 13 +++++++------
 3 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index fab94be89df..3c652eb7ee6 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4825,8 +4825,8 @@
 #define HSW_PWR_WELL_DRIVER			0x45404 /* CTL2 */
 #define HSW_PWR_WELL_KVMR			0x45408 /* CTL3 */
 #define HSW_PWR_WELL_DEBUG			0x4540C /* CTL4 */
-#define   HSW_PWR_WELL_ENABLE			(1<<31)
-#define   HSW_PWR_WELL_STATE			(1<<30)
+#define   HSW_PWR_WELL_ENABLE_REQUEST		(1<<31)
+#define   HSW_PWR_WELL_STATE_ENABLED		(1<<30)
 #define HSW_PWR_WELL_CTL5			0x45410
 #define   HSW_PWR_WELL_ENABLE_SINGLE_STEP	(1<<31)
 #define   HSW_PWR_WELL_PWR_GATE_OVERRIDE	(1<<20)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index f83316ec0b9..e600e1cfb6e 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -10112,7 +10112,7 @@ void i915_redisable_vga(struct drm_device *dev)
 	 * follow the "don't touch the power well if we don't need it" policy
 	 * the rest of the driver uses. */
 	if (HAS_POWER_WELL(dev) &&
-	    (I915_READ(HSW_PWR_WELL_DRIVER) & HSW_PWR_WELL_STATE) == 0)
+	    (I915_READ(HSW_PWR_WELL_DRIVER) & HSW_PWR_WELL_STATE_ENABLED) == 0)
 		return;
 
 	if (I915_READ(vga_reg) != VGA_DISP_DISABLE) {
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 76150818b5c..0d90064775c 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -5285,7 +5285,7 @@ bool intel_display_power_enabled(struct drm_device *dev,
 	case POWER_DOMAIN_TRANSCODER_B:
 	case POWER_DOMAIN_TRANSCODER_C:
 		return I915_READ(HSW_PWR_WELL_DRIVER) ==
-		       (HSW_PWR_WELL_ENABLE | HSW_PWR_WELL_STATE);
+		     (HSW_PWR_WELL_ENABLE_REQUEST | HSW_PWR_WELL_STATE_ENABLED);
 	default:
 		BUG();
 	}
@@ -5298,17 +5298,18 @@ static void __intel_set_power_well(struct drm_device *dev, bool enable)
 	uint32_t tmp;
 
 	tmp = I915_READ(HSW_PWR_WELL_DRIVER);
-	is_enabled = tmp & HSW_PWR_WELL_STATE;
-	enable_requested = tmp & HSW_PWR_WELL_ENABLE;
+	is_enabled = tmp & HSW_PWR_WELL_STATE_ENABLED;
+	enable_requested = tmp & HSW_PWR_WELL_ENABLE_REQUEST;
 
 	if (enable) {
 		if (!enable_requested)
-			I915_WRITE(HSW_PWR_WELL_DRIVER, HSW_PWR_WELL_ENABLE);
+			I915_WRITE(HSW_PWR_WELL_DRIVER,
+				   HSW_PWR_WELL_ENABLE_REQUEST);
 
 		if (!is_enabled) {
 			DRM_DEBUG_KMS("Enabling power well\n");
 			if (wait_for((I915_READ(HSW_PWR_WELL_DRIVER) &
-				      HSW_PWR_WELL_STATE), 20))
+				      HSW_PWR_WELL_STATE_ENABLED), 20))
 				DRM_ERROR("Timeout enabling power well\n");
 		}
 	} else {
@@ -5410,7 +5411,7 @@ void intel_init_power_well(struct drm_device *dev)
 
 	/* We're taking over the BIOS, so clear any requests made by it since
 	 * the driver is in charge now. */
-	if (I915_READ(HSW_PWR_WELL_BIOS) & HSW_PWR_WELL_ENABLE)
+	if (I915_READ(HSW_PWR_WELL_BIOS) & HSW_PWR_WELL_ENABLE_REQUEST)
 		I915_WRITE(HSW_PWR_WELL_BIOS, 0);
 }
 
-- 
cgit v1.2.3-70-g09d2


From fd547d25a8ac3f390fee4a689de86a64e3d65fe1 Mon Sep 17 00:00:00 2001
From: Vinit Azad <vinit.azad@intel.com>
Date: Wed, 14 Aug 2013 13:34:33 -0700
Subject: drm/i915: Only unmask required PM interrupts

Un-masking all PM interrupts causes hardware to generate
interrupts regardless of whether the interrupts are enabled
on the DE side. Since turbo only need up/down threshold and
rc6 timeout interrupt, mask all other interrupts bits to avoid
unnecessary overhead/wake up.

Note that our interrupt handler isn't being fired since we do set the
IER bits properly (IIR bits aren't set). The overhead isn't because
our driver is reacting to these interrupts, but because hardware keeps
generating internal messages when PMINTRMSK doesn't mask out the
up/down EI interrupts (which happen periodically).

Change-Id: I6c947df6fd5f60584d39b9e8b8c89faa51a5e827
Signed-off-by: Vinit Azad <vinit.azad@intel.com>
[danvet: Add follow-up explanation of the precise effects from Vinit
as a note to the commit message.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 0d90064775c..7bc3f178317 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3453,8 +3453,8 @@ static void gen6_enable_rps_interrupts(struct drm_device *dev)
 	I915_WRITE(GEN6_PMIMR, I915_READ(GEN6_PMIMR) & ~GEN6_PM_RPS_EVENTS);
 	I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS);
 	spin_unlock_irq(&dev_priv->irq_lock);
-	/* unmask all PM interrupts */
-	I915_WRITE(GEN6_PMINTRMSK, 0);
+	/* only unmask PM interrupts we need. Mask all others. */
+	I915_WRITE(GEN6_PMINTRMSK, ~GEN6_PM_RPS_EVENTS);
 }
 
 static void gen6_enable_rps(struct drm_device *dev)
-- 
cgit v1.2.3-70-g09d2


From edbfdb456053d0738e6b06a3827ead4158bfc918 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Tue, 6 Aug 2013 18:57:13 -0300
Subject: drm/i915: wrap GEN6_PMIMR changes

Just like we're doing with the other IMR changes.

One of the functional changes is that not every caller was doing the
POSTING_READ.

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_irq.c         | 47 ++++++++++++++++++++++++++++-----
 drivers/gpu/drm/i915/intel_drv.h        |  3 +++
 drivers/gpu/drm/i915/intel_pm.c         |  2 +-
 drivers/gpu/drm/i915/intel_ringbuffer.c |  8 ++----
 4 files changed, 46 insertions(+), 14 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 6bd4508666d..af5c335a69d 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -132,6 +132,41 @@ void ilk_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask)
 	ilk_update_gt_irq(dev_priv, mask, 0);
 }
 
+/**
+  * snb_update_pm_irq - update GEN6_PMIMR
+  * @dev_priv: driver private
+  * @interrupt_mask: mask of interrupt bits to update
+  * @enabled_irq_mask: mask of interrupt bits to enable
+  */
+static void snb_update_pm_irq(struct drm_i915_private *dev_priv,
+			      uint32_t interrupt_mask,
+			      uint32_t enabled_irq_mask)
+{
+	uint32_t pmimr = I915_READ(GEN6_PMIMR);
+	pmimr &= ~interrupt_mask;
+	pmimr |= (~enabled_irq_mask & interrupt_mask);
+
+	assert_spin_locked(&dev_priv->irq_lock);
+
+	I915_WRITE(GEN6_PMIMR, pmimr);
+	POSTING_READ(GEN6_PMIMR);
+}
+
+void snb_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask)
+{
+	snb_update_pm_irq(dev_priv, mask, mask);
+}
+
+void snb_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask)
+{
+	snb_update_pm_irq(dev_priv, mask, 0);
+}
+
+static void snb_set_pm_irq(struct drm_i915_private *dev_priv, uint32_t val)
+{
+	snb_update_pm_irq(dev_priv, 0xffffffff, ~val);
+}
+
 static bool ivb_can_enable_err_int(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -739,15 +774,14 @@ static void gen6_pm_rps_work(struct work_struct *work)
 {
 	drm_i915_private_t *dev_priv = container_of(work, drm_i915_private_t,
 						    rps.work);
-	u32 pm_iir, pm_imr;
+	u32 pm_iir;
 	u8 new_delay;
 
 	spin_lock_irq(&dev_priv->irq_lock);
 	pm_iir = dev_priv->rps.pm_iir;
 	dev_priv->rps.pm_iir = 0;
-	pm_imr = I915_READ(GEN6_PMIMR);
 	/* Make sure not to corrupt PMIMR state used by ringbuffer code */
-	I915_WRITE(GEN6_PMIMR, pm_imr & ~GEN6_PM_RPS_EVENTS);
+	snb_enable_pm_irq(dev_priv, GEN6_PM_RPS_EVENTS);
 	spin_unlock_irq(&dev_priv->irq_lock);
 
 	if ((pm_iir & GEN6_PM_RPS_EVENTS) == 0)
@@ -921,8 +955,7 @@ static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv,
 
 	spin_lock(&dev_priv->irq_lock);
 	dev_priv->rps.pm_iir |= pm_iir;
-	I915_WRITE(GEN6_PMIMR, dev_priv->rps.pm_iir);
-	POSTING_READ(GEN6_PMIMR);
+	snb_set_pm_irq(dev_priv, dev_priv->rps.pm_iir);
 	spin_unlock(&dev_priv->irq_lock);
 
 	queue_work(dev_priv->wq, &dev_priv->rps.work);
@@ -1005,8 +1038,8 @@ static void hsw_pm_irq_handler(struct drm_i915_private *dev_priv,
 	if (pm_iir & GEN6_PM_RPS_EVENTS) {
 		spin_lock(&dev_priv->irq_lock);
 		dev_priv->rps.pm_iir |= pm_iir & GEN6_PM_RPS_EVENTS;
-		I915_WRITE(GEN6_PMIMR, dev_priv->rps.pm_iir);
-		/* never want to mask useful interrupts. (also posting read) */
+		snb_set_pm_irq(dev_priv, dev_priv->rps.pm_iir);
+		/* never want to mask useful interrupts. */
 		WARN_ON(I915_READ_NOTRACE(GEN6_PMIMR) & ~GEN6_PM_RPS_EVENTS);
 		spin_unlock(&dev_priv->irq_lock);
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index a8462064714..8222f2426b4 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -781,5 +781,8 @@ extern void hsw_restore_lcpll(struct drm_i915_private *dev_priv);
 extern void ilk_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 extern void ilk_disable_gt_irq(struct drm_i915_private *dev_priv,
 			       uint32_t mask);
+extern void snb_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
+extern void snb_disable_pm_irq(struct drm_i915_private *dev_priv,
+			       uint32_t mask);
 
 #endif /* __INTEL_DRV_H__ */
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 7bc3f178317..4f0857346bf 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3450,7 +3450,7 @@ static void gen6_enable_rps_interrupts(struct drm_device *dev)
 
 	spin_lock_irq(&dev_priv->irq_lock);
 	WARN_ON(dev_priv->rps.pm_iir);
-	I915_WRITE(GEN6_PMIMR, I915_READ(GEN6_PMIMR) & ~GEN6_PM_RPS_EVENTS);
+	snb_enable_pm_irq(dev_priv, GEN6_PM_RPS_EVENTS);
 	I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS);
 	spin_unlock_irq(&dev_priv->irq_lock);
 	/* only unmask PM interrupts we need. Mask all others. */
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 2e370804248..7de29d40d1a 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1062,10 +1062,8 @@ hsw_vebox_get_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (ring->irq_refcount++ == 0) {
-		u32 pm_imr = I915_READ(GEN6_PMIMR);
 		I915_WRITE_IMR(ring, ~ring->irq_enable_mask);
-		I915_WRITE(GEN6_PMIMR, pm_imr & ~ring->irq_enable_mask);
-		POSTING_READ(GEN6_PMIMR);
+		snb_enable_pm_irq(dev_priv, ring->irq_enable_mask);
 	}
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
@@ -1084,10 +1082,8 @@ hsw_vebox_put_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
-		u32 pm_imr = I915_READ(GEN6_PMIMR);
 		I915_WRITE_IMR(ring, ~0);
-		I915_WRITE(GEN6_PMIMR, pm_imr | ring->irq_enable_mask);
-		POSTING_READ(GEN6_PMIMR);
+		snb_disable_pm_irq(dev_priv, ring->irq_enable_mask);
 	}
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 }
-- 
cgit v1.2.3-70-g09d2


From 3414caf63421762e57b26aa999e5187b42ee1606 Mon Sep 17 00:00:00 2001
From: Jesse Barnes <jbarnes@virtuousgeek.org>
Date: Wed, 21 Aug 2013 08:08:55 -0700
Subject: drm/i915: drop WaMbcDriverBootEnable workaround
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Turns out the BIOS will do this for us as needed, and if we try to do it
again we risk hangs or other bad behavior.

Note that this seems to break libva on ChromeOS after resumes (but
strangely _not_ after booting up).

This essentially reverts

commit b4ae3f22d238617ca11610b29fde16cf8c0bc6e0
Author: Jesse Barnes <jbarnes@virtuousgeek.org>
Date:   Thu Jun 14 11:04:48 2012 -0700

    drm/i915: load boot context at driver init time

and

commit b3bf076697a68a8577f4a5f7407de0bb2b3b56ac
Author: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date:   Tue Nov 20 13:27:44 2012 -0200

    drm/i915: implement WaMbcDriverBootEnable on Haswell

Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reported-and-Tested-by: Stéphane Marchesin <marcheu@chromium.org>
[danvet: Add note about impact and regression citation.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 17 -----------------
 1 file changed, 17 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 4f0857346bf..cbab95dce35 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4864,10 +4864,6 @@ static void gen6_init_clock_gating(struct drm_device *dev)
 		   ILK_DPARBUNIT_CLOCK_GATE_ENABLE  |
 		   ILK_DPFDUNIT_CLOCK_GATE_ENABLE);
 
-	/* WaMbcDriverBootEnable:snb */
-	I915_WRITE(GEN6_MBCTL, I915_READ(GEN6_MBCTL) |
-		   GEN6_MBCTL_ENABLE_BOOT_FETCH);
-
 	g4x_disable_trickle_feed(dev);
 
 	/* The default value should be 0x200 according to docs, but the two
@@ -4963,10 +4959,6 @@ static void haswell_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(CACHE_MODE_1,
 		   _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
 
-	/* WaMbcDriverBootEnable:hsw */
-	I915_WRITE(GEN6_MBCTL, I915_READ(GEN6_MBCTL) |
-		   GEN6_MBCTL_ENABLE_BOOT_FETCH);
-
 	/* WaSwitchSolVfFArbitrationPriority:hsw */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
 
@@ -5050,10 +5042,6 @@ static void ivybridge_init_clock_gating(struct drm_device *dev)
 
 	g4x_disable_trickle_feed(dev);
 
-	/* WaMbcDriverBootEnable:ivb */
-	I915_WRITE(GEN6_MBCTL, I915_READ(GEN6_MBCTL) |
-		   GEN6_MBCTL_ENABLE_BOOT_FETCH);
-
 	/* WaVSRefCountFullforceMissDisable:ivb */
 	gen7_setup_fixed_func_scheduler(dev_priv);
 
@@ -5113,11 +5101,6 @@ static void valleyview_init_clock_gating(struct drm_device *dev)
 		   I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
 		   GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
 
-	/* WaMbcDriverBootEnable:vlv */
-	I915_WRITE(GEN6_MBCTL, I915_READ(GEN6_MBCTL) |
-		   GEN6_MBCTL_ENABLE_BOOT_FETCH);
-
-
 	/* According to the BSpec vol1g, bit 12 (RCPBUNIT) clock
 	 * gating disable must be set.  Failure to set it results in
 	 * flickering pixels due to Z write ordering failures after
-- 
cgit v1.2.3-70-g09d2


From c67a470b1db781c54be07a87217cff35a91f564e Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Mon, 19 Aug 2013 13:18:09 -0300
Subject: drm/i915: allow package C8+ states on Haswell (disabled)

This patch allows PC8+ states on Haswell. These states can only be
reached when all the display outputs are disabled, and they allow some
more power savings.

The fact that the graphics device is allowing PC8+ doesn't mean that
the machine will actually enter PC8+: all the other devices also need
to allow PC8+.

For now this option is disabled by default. You need i915.allow_pc8=1
if you want it.

This patch adds a big comment inside i915_drv.h explaining how it
works and how it tracks things. Read it.

v2: (this is not really v2, many previous versions were already sent,
     but they had different names)
    - Use the new functions to enable/disable GTIMR and GEN6_PMIMR
    - Rename almost all variables and functions to names suggested by
      Chris
    - More WARNs on the IRQ handling code
    - Also disable PC8 when there's GPU work to do (thanks to Ben for
      the help on this), so apps can run caster
    - Enable PC8 on a delayed work function that is delayed for 5
      seconds. This makes sure we only enable PC8+ if we're really
      idle
    - Make sure we're not in PC8+ when suspending
v3: - WARN if IRQs are disabled on __wait_seqno
    - Replace some DRM_ERRORs with WARNs
    - Fix calls to restore GT and PM interrupts
    - Use intel_mark_busy instead of intel_ring_advance to disable PC8
v4: - Use the force_wake, Luke!
v5: - Remove the "IIR is not zero" WARNs
    - Move the force_wake chunk to its own patch
    - Only restore what's missing from RC6, not everything

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_dma.c      |  10 +++
 drivers/gpu/drm/i915/i915_drv.c      |  11 +++
 drivers/gpu/drm/i915/i915_drv.h      |  72 +++++++++++++++
 drivers/gpu/drm/i915/i915_gem.c      |   2 +
 drivers/gpu/drm/i915/i915_irq.c      | 101 +++++++++++++++++++++
 drivers/gpu/drm/i915/intel_display.c | 170 ++++++++++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/intel_dp.c      |   3 +
 drivers/gpu/drm/i915/intel_drv.h     |   8 ++
 drivers/gpu/drm/i915/intel_i2c.c     |   2 +
 drivers/gpu/drm/i915/intel_pm.c      |  13 ++-
 10 files changed, 390 insertions(+), 2 deletions(-)

(limited to 'drivers/gpu/drm/i915/intel_pm.c')

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 5a051eaab9e..09e8ef910ec 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1486,6 +1486,14 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	mutex_init(&dev_priv->rps.hw_lock);
 	mutex_init(&dev_priv->modeset_restore_lock);
 
+	mutex_init(&dev_priv->pc8.lock);
+	dev_priv->pc8.requirements_met = false;
+	dev_priv->pc8.gpu_idle = false;
+	dev_priv->pc8.irqs_disabled = false;
+	dev_priv->pc8.enabled = false;
+	dev_priv->pc8.disable_count = 2; /* requirements_met + gpu_idle */
+	INIT_DELAYED_WORK(&dev_priv->pc8.enable_work, hsw_enable_pc8_work);
+
 	i915_dump_device_info(dev_priv);
 
 	/* Not all pre-production machines fall into this category, only the
@@ -1740,6 +1748,8 @@ int i915_driver_unload(struct drm_device *dev)
 	cancel_work_sync(&dev_priv->gpu_error.work);
 	i915_destroy_error_state(dev);
 
+	cancel_delayed_work_sync(&dev_priv->pc8.enable_work);
+
 	if (dev->pdev->msi_enabled)
 		pci_disable_msi(dev->pdev);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index fd9fb2c2569..84d48b82e3f 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -141,6 +141,10 @@ module_param_named(fastboot, i915_fastboot, bool, 0600);
 MODULE_PARM_DESC(fastboot, "Try to skip unnecessary mode sets at boot time "
 		 "(default: false)");
 
+int i915_enable_pc8 __read_mostly = 0;
+module_param_named(enable_pc8, i915_enable_pc8, int, 0600);
+MODULE_PARM_DESC(enable_pc8, "Enable support for low power package C states (PC8+) (default: false)");
+
 bool i915_prefault_disable __read_mostly;
 module_param_named(prefault_disable, i915_prefault_disable, bool, 0600);
 MODULE_PARM_DESC(prefault_disable,
@@ -557,6 +561,9 @@ static int i915_drm_freeze(struct drm_device *dev)
 	dev_priv->modeset_restore = MODESET_SUSPENDED;
 	mutex_unlock(&dev_priv->modeset_restore_lock);
 
+	/* We do a lot of poking in a lot of registers, make sure they work
+	 * properly. */
+	hsw_disable_package_c8(dev_priv);
 	intel_set_power_well(dev, true);
 
 	drm_kms_helper_poll_disable(dev);
@@ -713,6 +720,10 @@ static int __i915_drm_thaw(struct drm_device *dev)
 		schedule_work(&dev_priv->console_resume_work);
 	}
 
+	/* Undo what we did at i915_drm_freeze so the refcount goes back to the
+	 * expected level. */
+	hsw_enable_package_c8(dev_priv);
+
 	mutex_lock(&dev_priv->modeset_restore_lock);
 	dev_priv->modeset_restore = MODESET_DONE;
 	mutex_unlock(&dev_priv->modeset_restore_lock);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f423a94c1b2..627c8216db1 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1076,6 +1076,75 @@ struct intel_wm_level {
 	uint32_t fbc_val;
 };
 
+/*
+ * This struct tracks the state needed for the Package C8+ feature.
+ *
+ * Package states C8 and deeper are really deep PC states that can only be
+ * reached when all the devices on the system allow it, so even if the graphics
+ * device allows PC8+, it doesn't mean the system will actually get to these
+ * states.
+ *
+ * Our driver only allows PC8+ when all the outputs are disabled, the power well
+ * is disabled and the GPU is idle. When these conditions are met, we manually
+ * do the other conditions: disable the interrupts, clocks and switch LCPLL
+ * refclk to Fclk.
+ *
+ * When we really reach PC8 or deeper states (not just when we allow it) we lose
+ * the state of some registers, so when we come back from PC8+ we need to
+ * restore this state. We don't get into PC8+ if we're not in RC6, so we don't
+ * need to take care of the registers kept by RC6.
+ *
+ * The interrupt disabling is part of the requirements. We can only leave the
+ * PCH HPD interrupts enabled. If we're in PC8+ and we get another interrupt we
+ * can lock the machine.
+ *
+ * Ideally every piece of our code that needs PC8+ disabled would call
+ * hsw_disable_package_c8, which would increment disable_count and prevent the
+ * system from reaching PC8+. But we don't have a symmetric way to do this for
+ * everything, so we have the requirements_met and gpu_idle variables. When we
+ * switch requirements_met or gpu_idle to true we decrease disable_count, and
+ * increase it in the opposite case. The requirements_met variable is true when
+ * all the CRTCs, encoders and the power well are disabled. The gpu_idle
+ * variable is true when the GPU is idle.
+ *
+ * In addition to everything, we only actually enable PC8+ if disable_count
+ * stays at zero for at least some seconds. This is implemented with the
+ * enable_work variable. We do this so we don't enable/disable PC8 dozens of
+ * consecutive times when all screens are disabled and some background app
+ * queries the state of our connectors, or we have some application constantly
+ * waking up to use the GPU. Only after the enable_work function actually
+ * enables PC8+ the "enable" variable will become true, which means that it can
+ * be false even if disable_count is 0.
+ *
+ * The irqs_disabled variable becomes true exactly after we disable the IRQs and
+ * goes back to false exactly before we reenable the IRQs. We use this variable
+ * to check if someone is trying to enable/disable IRQs while they're supposed
+ * to be disabled. This shouldn't happen and we'll print some error messages in
+ * case it happens, but if it actually happens we'll also update the variables
+ * inside struct regsave so when we restore the IRQs they will contain the
+ * latest expected values.
+ *
+ * For more, read "Display Sequences for Package C8" on our documentation.
+ */
+struct i915_package_c8 {
+	bool requirements_met;
+	bool gpu_idle;
+	bool irqs_disabled;
+	/* Only true after the delayed work task actually enables it. */
+	bool enabled;
+	int disable_count;
+	struct mutex lock;
+	struct delayed_work enable_work;
+
+	struct {
+		uint32_t deimr;
+		uint32_t sdeimr;
+		uint32_t gtimr;
+		uint32_t gtier;
+		uint32_t gen6_pmimr;
+	} regsave;
+};
+
 typedef struct drm_i915_private {
 	struct drm_device *dev;
 	struct kmem_cache *slab;
@@ -1260,6 +1329,8 @@ typedef struct drm_i915_private {
 		uint16_t cur_latency[5];
 	} wm;
 
+	struct i915_package_c8 pc8;
+
 	/* Old dri1 support infrastructure, beware the dragons ya fools entering
 	 * here! */
 	struct i915_dri1_state dri1;
@@ -1635,6 +1706,7 @@ extern unsigned int i915_preliminary_hw_support __read_mostly;
 extern int i915_disable_power_well __read_mostly;
 extern int i915_enable_ips __read_mostly;
 extern bool i915_fastboot __read_mostly;
+extern int i915_enable_pc8 __read_mostly;
 extern bool i915_prefault_disable __read_mostly;
 
 extern int i915_suspend(struct drm_device *dev, pm_message_t state);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 449575b85b3..23c42567631 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1005,6 +1005,8 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
 	bool wait_forever = true;
 	int ret;
 
+	WARN(dev_priv->pc8.irqs_disabled, "IRQs disabled\n");
+
 	if (i915_seqno_passed(ring->get_seqno(ring, true), seqno))
 		return 0;
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index caf83da17bb..a03b445ceb5 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -85,6 +85,12 @@ ironlake_enable_display_irq(drm_i915_private_t *dev_priv, u32 mask)
 {
 	assert_spin_locked(&dev_priv->irq_lock);
 
+	if (dev_priv->pc8.irqs_disabled) {
+		WARN(1, "IRQs disabled\n");
+		dev_priv->pc8.regsave.deimr &= ~mask;
+		return;
+	}
+
 	if ((dev_priv->irq_mask & mask) != 0) {
 		dev_priv->irq_mask &= ~mask;
 		I915_WRITE(DEIMR, dev_priv->irq_mask);
@@ -97,6 +103,12 @@ ironlake_disable_display_irq(drm_i915_private_t *dev_priv, u32 mask)
 {
 	assert_spin_locked(&dev_priv->irq_lock);
 
+	if (dev_priv->pc8.irqs_disabled) {
+		WARN(1, "IRQs disabled\n");
+		dev_priv->pc8.regsave.deimr |= mask;
+		return;
+	}
+
 	if ((dev_priv->irq_mask & mask) != mask) {
 		dev_priv->irq_mask |= mask;
 		I915_WRITE(DEIMR, dev_priv->irq_mask);
@@ -116,6 +128,14 @@ static void ilk_update_gt_irq(struct drm_i915_private *dev_priv,
 {
 	assert_spin_locked(&dev_priv->irq_lock);
 
+	if (dev_priv->pc8.irqs_disabled) {
+		WARN(1, "IRQs disabled\n");
+		dev_priv->pc8.regsave.gtimr &= ~interrupt_mask;
+		dev_priv->pc8.regsave.gtimr |= (~enabled_irq_mask &
+						interrupt_mask);
+		return;
+	}
+
 	dev_priv->gt_irq_mask &= ~interrupt_mask;
 	dev_priv->gt_irq_mask |= (~enabled_irq_mask & interrupt_mask);
 	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
@@ -146,6 +166,14 @@ static void snb_update_pm_irq(struct drm_i915_private *dev_priv,
 
 	assert_spin_locked(&dev_priv->irq_lock);
 
+	if (dev_priv->pc8.irqs_disabled) {
+		WARN(1, "IRQs disabled\n");
+		dev_priv->pc8.regsave.gen6_pmimr &= ~interrupt_mask;
+		dev_priv->pc8.regsave.gen6_pmimr |= (~enabled_irq_mask &
+						     interrupt_mask);
+		return;
+	}
+
 	new_val = dev_priv->pm_irq_mask;
 	new_val &= ~interrupt_mask;
 	new_val |= (~enabled_irq_mask & interrupt_mask);
@@ -257,6 +285,15 @@ static void ibx_display_interrupt_update(struct drm_i915_private *dev_priv,
 
 	assert_spin_locked(&dev_priv->irq_lock);
 
+	if (dev_priv->pc8.irqs_disabled &&
+	    (interrupt_mask & SDE_HOTPLUG_MASK_CPT)) {
+		WARN(1, "IRQs disabled\n");
+		dev_priv->pc8.regsave.sdeimr &= ~interrupt_mask;
+		dev_priv->pc8.regsave.sdeimr |= (~enabled_irq_mask &
+						 interrupt_mask);
+		return;
+	}
+
 	I915_WRITE(SDEIMR, sdeimr);
 	POSTING_READ(SDEIMR);
 }
@@ -3113,3 +3150,67 @@ void intel_hpd_init(struct drm_device *dev)
 		dev_priv->display.hpd_irq_setup(dev);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
+
+/* Disable interrupts so we can allow Package C8+. */
+void hsw_pc8_disable_interrupts(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+
+	dev_priv->pc8.regsave.deimr = I915_READ(DEIMR);
+	dev_priv->pc8.regsave.sdeimr = I915_READ(SDEIMR);
+	dev_priv->pc8.regsave.gtimr = I915_READ(GTIMR);
+	dev_priv->pc8.regsave.gtier = I915_READ(GTIER);
+	dev_priv->pc8.regsave.gen6_pmimr = I915_READ(GEN6_PMIMR);
+
+	ironlake_disable_display_irq(dev_priv, ~DE_PCH_EVENT_IVB);
+	ibx_disable_display_interrupt(dev_priv, ~SDE_HOTPLUG_MASK_CPT);
+	ilk_disable_gt_irq(dev_priv, 0xffffffff);
+	snb_disable_pm_irq(dev_priv, 0xffffffff);
+
+	dev_priv->pc8.irqs_disabled = true;
+
+	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+}
+
+/* Restore interrupts so we can recover from Package C8+. */
+void hsw_pc8_restore_interrupts(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned long irqflags;
+	uint32_t val, expected;
+
+	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+
+	val = I915_READ(DEIMR);
+	expected = ~DE_PCH_EVENT_IVB;
+	WARN(val != expected, "DEIMR is 0x%08x, not 0x%08x\n", val, expected);
+
+	val = I915_READ(SDEIMR) & ~SDE_HOTPLUG_MASK_CPT;
+	expected = ~SDE_HOTPLUG_MASK_CPT;
+	WARN(val != expected, "SDEIMR non-HPD bits are 0x%08x, not 0x%08x\n",
+	     val, expected);
+
+	val = I915_READ(GTIMR);
+	expected = 0xffffffff;
+	WARN(val != expected, "GTIMR is 0x%08x, not 0x%08x\n", val, expected);
+
+	val = I915_READ(GEN6_PMIMR);
+	expected = 0xffffffff;
+	WARN(val != expected, "GEN6_PMIMR is 0x%08x, not 0x%08x\n", val,
+	     expected);
+
+	dev_priv->pc8.irqs_disabled = false;
+
+	ironlake_enable_display_irq(dev_priv, ~dev_priv->pc8.regsave.deimr);
+	ibx_enable_display_interrupt(dev_priv,
+				     ~dev_priv->pc8.regsave.sdeimr &
+				     ~SDE_HOTPLUG_MASK_CPT);
+	ilk_enable_gt_irq(dev_priv, ~dev_priv->pc8.regsave.gtimr);
+	snb_enable_pm_irq(dev_priv, ~dev_priv->pc8.regsave.gen6_pmimr);
+	I915_WRITE(GTIER, dev_priv->pc8.regsave.gtier);
+
+	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+}
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index fc92773ef55..1fad9de3d81 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -6064,6 +6064,166 @@ void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
 	dev_priv->uncore.funcs.force_wake_put(dev_priv);
 }
 
+void hsw_enable_pc8_work(struct work_struct *__work)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(to_delayed_work(__work), struct drm_i915_private,
+			     pc8.enable_work);
+	struct drm_device *dev = dev_priv->dev;
+	uint32_t val;
+
+	if (dev_priv->pc8.enabled)
+		return;
+
+	DRM_DEBUG_KMS("Enabling package C8+\n");
+
+	dev_priv->pc8.enabled = true;
+
+	if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
+		val = I915_READ(SOUTH_DSPCLK_GATE_D);
+		val &= ~PCH_LP_PARTITION_LEVEL_DISABLE;
+		I915_WRITE(SOUTH_DSPCLK_GATE_D, val);
+	}
+
+	lpt_disable_clkout_dp(dev);
+	hsw_pc8_disable_interrupts(dev);
+	hsw_disable_lcpll(dev_priv, true, true);
+}
+
+static void __hsw_enable_package_c8(struct drm_i915_private *dev_priv)
+{
+	WARN_ON(!mutex_is_locked(&dev_priv->pc8.lock));
+	WARN(dev_priv->pc8.disable_count < 1,
+	     "pc8.disable_count: %d\n", dev_priv->pc8.disable_count);
+
+	dev_priv->pc8.disable_count--;
+	if (dev_priv->pc8.disable_count != 0)
+		return;
+
+	schedule_delayed_work(&dev_priv->pc8.enable_work,
+			      msecs_to_jiffies(5 * 1000));
+}
+
+static void __hsw_disable_package_c8(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	uint32_t val;
+
+	WARN_ON(!mutex_is_locked(&dev_priv->pc8.lock));
+	WARN(dev_priv->pc8.disable_count < 0,
+	     "pc8.disable_count: %d\n", dev_priv->pc8.disable_count);
+
+	dev_priv->pc8.disable_count++;
+	if (dev_priv->pc8.disable_count != 1)
+		return;
+
+	cancel_delayed_work_sync(&dev_priv->pc8.enable_work);
+	if (!dev_priv->pc8.enabled)
+		return;
+
+	DRM_DEBUG_KMS("Disabling package C8+\n");
+
+	hsw_restore_lcpll(dev_priv);
+	hsw_pc8_restore_interrupts(dev);
+	lpt_init_pch_refclk(dev);
+
+	if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
+		val = I915_READ(SOUTH_DSPCLK_GATE_D);
+		val |= PCH_LP_PARTITION_LEVEL_DISABLE;
+		I915_WRITE(SOUTH_DSPCLK_GATE_D, val);
+	}
+
+	intel_prepare_ddi(dev);
+	i915_gem_init_swizzling(dev);
+	mutex_lock(&dev_priv->rps.hw_lock);
+	gen6_update_ring_freq(dev);
+	mutex_unlock(&dev_priv->rps.hw_lock);
+	dev_priv->pc8.enabled = false;
+}
+
+void hsw_enable_package_c8(struct drm_i915_private *dev_priv)
+{
+	mutex_lock(&dev_priv->pc8.lock);
+	__hsw_enable_package_c8(dev_priv);
+	mutex_unlock(&dev_priv->pc8.lock);
+}
+
+void hsw_disable_package_c8(struct drm_i915_private *dev_priv)
+{
+	mutex_lock(&dev_priv->pc8.lock);
+	__hsw_disable_package_c8(dev_priv);
+	mutex_unlock(&dev_priv->pc8.lock);
+}
+
+static bool hsw_can_enable_package_c8(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	struct intel_crtc *crtc;
+	uint32_t val;
+
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head)
+		if (crtc->base.enabled)
+			return false;
+
+	/* This case is still possible since we have the i915.disable_power_well
+	 * parameter and also the KVMr or something else might be requesting the
+	 * power well. */
+	val = I915_READ(HSW_PWR_WELL_DRIVER);
+	if (val != 0) {
+		DRM_DEBUG_KMS("Not enabling PC8: power well on\n");
+		return false;
+	}
+
+	return true;
+}
+
+/* Since we're called from modeset_global_resources there's no way to
+ * symmetrically increase and decrease the refcount, so we use
+ * dev_priv->pc8.requirements_met to track whether we already have the refcount
+ * or not.
+ */
+static void hsw_update_package_c8(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	bool allow;
+
+	if (!i915_enable_pc8)
+		return;
+
+	mutex_lock(&dev_priv->pc8.lock);
+
+	allow = hsw_can_enable_package_c8(dev_priv);
+
+	if (allow == dev_priv->pc8.requirements_met)
+		goto done;
+
+	dev_priv->pc8.requirements_met = allow;
+
+	if (allow)
+		__hsw_enable_package_c8(dev_priv);
+	else
+		__hsw_disable_package_c8(dev_priv);
+
+done:
+	mutex_unlock(&dev_priv->pc8.lock);
+}
+
+static void hsw_package_c8_gpu_idle(struct drm_i915_private *dev_priv)
+{
+	if (!dev_priv->pc8.gpu_idle) {
+		dev_priv->pc8.gpu_idle = true;
+		hsw_enable_package_c8(dev_priv);
+	}
+}
+
+static void hsw_package_c8_gpu_busy(struct drm_i915_private *dev_priv)
+{
+	if (dev_priv->pc8.gpu_idle) {
+		dev_priv->pc8.gpu_idle = false;
+		hsw_disable_package_c8(dev_priv);
+	}
+}
+
 static void haswell_modeset_global_resources(struct drm_device *dev)
 {
 	bool enable = false;
@@ -6079,6 +6239,8 @@ static void haswell_modeset_global_resources(struct drm_device *dev)
 	}
 
 	intel_set_power_well(dev, enable);
+
+	hsw_update_package_c8(dev);
 }
 
 static int haswell_crtc_mode_set(struct drm_crtc *crtc,
@@ -7310,13 +7472,19 @@ static void intel_decrease_pllclock(struct drm_crtc *crtc)
 
 void intel_mark_busy(struct drm_device *dev)
 {
-	i915_update_gfx_val(dev->dev_private);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	hsw_package_c8_gpu_busy(dev_priv);
+	i915_update_gfx_val(dev_priv);
 }
 
 void intel_mark_idle(struct drm_device *dev)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc;
 
+	hsw_package_c8_gpu_idle(dev_priv);
+
 	if (!i915_powersave)
 		return;
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 2726d4d4172..2151d13772b 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -344,6 +344,8 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 	else
 		precharge = 5;
 
+	intel_aux_display_runtime_get(dev_priv);
+
 	/* Try to wait for any previous AUX channel activity */
 	for (try = 0; try < 3; try++) {
 		status = I915_READ_NOTRACE(ch_ctl);
@@ -434,6 +436,7 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 	ret = recv_bytes;
 out:
 	pm_qos_update_request(&dev_priv->pm_qos, PM_QOS_DEFAULT_VALUE);
+	intel_aux_display_runtime_put(dev_priv);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 8222f2426b4..176080822a7 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -745,6 +745,7 @@ extern void intel_set_power_well(struct drm_device *dev, bool enable);
 extern void intel_enable_gt_powersave(struct drm_device *dev);
 extern void intel_disable_gt_powersave(struct drm_device *dev);
 extern void ironlake_teardown_rc6(struct drm_device *dev);
+void gen6_update_ring_freq(struct drm_device *dev);
 
 extern bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
 				   enum pipe *pipe);
@@ -784,5 +785,12 @@ extern void ilk_disable_gt_irq(struct drm_i915_private *dev_priv,
 extern void snb_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 extern void snb_disable_pm_irq(struct drm_i915_private *dev_priv,
 			       uint32_t mask);
+extern void hsw_enable_pc8_work(struct work_struct *__work);
+extern void hsw_enable_package_c8(struct drm_i915_private *dev_priv);
+extern void hsw_disable_package_c8(struct drm_i915_private *dev_priv);
+extern void hsw_pc8_disable_interrupts(struct drm_device *dev);
+extern void hsw_pc8_restore_interrupts(struct drm_device *dev);
+extern void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv);
+extern void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv);
 
 #endif /* __INTEL_DRV_H__ */
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 639fe192997..d1c1e0f7f26 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -398,6 +398,7 @@ gmbus_xfer(struct i2c_adapter *adapter,
 	int i, reg_offset;
 	int ret = 0;
 
+	intel_aux_display_runtime_get(dev_priv);
 	mutex_lock(&dev_priv->gmbus_mutex);
 
 	if (bus->force_bit) {
@@ -497,6 +498,7 @@ timeout:
 
 out:
 	mutex_unlock(&dev_priv->gmbus_mutex);
+	intel_aux_display_runtime_put(dev_priv);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index cbab95dce35..0150ba598bf 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3607,7 +3607,7 @@ static void gen6_enable_rps(struct drm_device *dev)
 	gen6_gt_force_wake_put(dev_priv);
 }
 
-static void gen6_update_ring_freq(struct drm_device *dev)
+void gen6_update_ring_freq(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int min_freq = 15;
@@ -5398,6 +5398,17 @@ void intel_init_power_well(struct drm_device *dev)
 		I915_WRITE(HSW_PWR_WELL_BIOS, 0);
 }
 
+/* Disables PC8 so we can use the GMBUS and DP AUX interrupts. */
+void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv)
+{
+	hsw_disable_package_c8(dev_priv);
+}
+
+void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv)
+{
+	hsw_enable_package_c8(dev_priv);
+}
+
 /* Set up chip specific power management-related functions */
 void intel_init_pm(struct drm_device *dev)
 {
-- 
cgit v1.2.3-70-g09d2