From 045ac3b5629d9711531a408e92f9074db6afe7ce Mon Sep 17 00:00:00 2001
From: Jesse Barnes <jbarnes@virtuousgeek.org>
Date: Tue, 14 May 2013 17:08:26 -0700
Subject: [PATCH 01/70] drm/i915: add encoder get_config function v5
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We can use this for fetching encoder specific pipe_config state, like
mode flags, adjusted clock, etc.

Just used for mode flags atm, so we can check the pipe config state at
mode set time.

v2: get_config when checking hw state too
v3: fix DVO and LVDS mode flags (Ville)
    get SDVO DTD for flag fetch (Ville)
v4: use input timings (Ville)
    correct command used (Ville)
    remove gen4 check (Ville)
v5: get DDI flag config too

Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com> (v4)
Tested-by: Paulo Zanoni <przanoni@gmail.com> (the new hsw ddi stuff)
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_crt.c     | 23 +++++++++++++++
 drivers/gpu/drm/i915/intel_ddi.c     | 23 +++++++++++++++
 drivers/gpu/drm/i915/intel_display.c | 20 +++++++++++--
 drivers/gpu/drm/i915/intel_dp.c      | 23 +++++++++++++++
 drivers/gpu/drm/i915/intel_drv.h     |  4 +++
 drivers/gpu/drm/i915/intel_dvo.c     | 21 ++++++++++++++
 drivers/gpu/drm/i915/intel_hdmi.c    | 23 +++++++++++++++
 drivers/gpu/drm/i915/intel_lvds.c    | 26 +++++++++++++++++
 drivers/gpu/drm/i915/intel_sdvo.c    | 42 ++++++++++++++++++++++++++++
 9 files changed, 202 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 66a0c6f0bb81..5e9f93e53255 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -84,6 +84,28 @@ static bool intel_crt_get_hw_state(struct intel_encoder *encoder,
 	return true;
 }
 
+static void intel_crt_get_config(struct intel_encoder *encoder,
+				 struct intel_crtc_config *pipe_config)
+{
+	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct intel_crt *crt = intel_encoder_to_crt(encoder);
+	u32 tmp, flags = 0;
+
+	tmp = I915_READ(crt->adpa_reg);
+
+	if (tmp & ADPA_HSYNC_ACTIVE_HIGH)
+		flags |= DRM_MODE_FLAG_PHSYNC;
+	else
+		flags |= DRM_MODE_FLAG_NHSYNC;
+
+	if (tmp & ADPA_VSYNC_ACTIVE_HIGH)
+		flags |= DRM_MODE_FLAG_PVSYNC;
+	else
+		flags |= DRM_MODE_FLAG_NVSYNC;
+
+	pipe_config->adjusted_mode.flags |= flags;
+}
+
 /* Note: The caller is required to filter out dpms modes not supported by the
  * platform. */
 static void intel_crt_set_dpms(struct intel_encoder *encoder, int mode)
@@ -778,6 +800,7 @@ void intel_crt_init(struct drm_device *dev)
 	crt->base.compute_config = intel_crt_compute_config;
 	crt->base.disable = intel_disable_crt;
 	crt->base.enable = intel_enable_crt;
+	crt->base.get_config = intel_crt_get_config;
 	if (I915_HAS_HOTPLUG(dev))
 		crt->base.hpd_pin = HPD_CRT;
 	if (HAS_DDI(dev))
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 062de679f38f..e66852186751 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1259,6 +1259,28 @@ static void intel_ddi_hot_plug(struct intel_encoder *intel_encoder)
 		intel_dp_check_link_status(intel_dp);
 }
 
+static void intel_ddi_get_config(struct intel_encoder *encoder,
+				 struct intel_crtc_config *pipe_config)
+{
+	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
+	enum transcoder cpu_transcoder = intel_crtc->config.cpu_transcoder;
+	u32 temp, flags = 0;
+
+	temp = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
+	if (temp & TRANS_DDI_PHSYNC)
+		flags |= DRM_MODE_FLAG_PHSYNC;
+	else
+		flags |= DRM_MODE_FLAG_NHSYNC;
+	if (temp & TRANS_DDI_PVSYNC)
+		flags |= DRM_MODE_FLAG_PVSYNC;
+	else
+		flags |= DRM_MODE_FLAG_NVSYNC;
+
+	pipe_config->adjusted_mode.flags |= flags;
+	pipe_config->pixel_multiplier = 1;
+}
+
 static void intel_ddi_destroy(struct drm_encoder *encoder)
 {
 	/* HDMI has nothing special to destroy, so we can go with this. */
@@ -1318,6 +1340,7 @@ void intel_ddi_init(struct drm_device *dev, enum port port)
 	intel_encoder->disable = intel_disable_ddi;
 	intel_encoder->post_disable = intel_ddi_post_disable;
 	intel_encoder->get_hw_state = intel_ddi_get_hw_state;
+	intel_encoder->get_config = intel_ddi_get_config;
 
 	intel_dig_port->port = port;
 	intel_dig_port->port_reversal = I915_READ(DDI_BUF_CTL(port)) &
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 2d90594016d9..4196155cf964 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -8067,6 +8067,15 @@ intel_pipe_config_compare(struct drm_device *dev,
 	PIPE_CONF_CHECK_FLAGS(adjusted_mode.flags,
 			      DRM_MODE_FLAG_INTERLACE);
 
+	PIPE_CONF_CHECK_FLAGS(adjusted_mode.flags,
+			      DRM_MODE_FLAG_PHSYNC);
+	PIPE_CONF_CHECK_FLAGS(adjusted_mode.flags,
+			      DRM_MODE_FLAG_NHSYNC);
+	PIPE_CONF_CHECK_FLAGS(adjusted_mode.flags,
+			      DRM_MODE_FLAG_PVSYNC);
+	PIPE_CONF_CHECK_FLAGS(adjusted_mode.flags,
+			      DRM_MODE_FLAG_NVSYNC);
+
 	PIPE_CONF_CHECK_I(requested_mode.hdisplay);
 	PIPE_CONF_CHECK_I(requested_mode.vdisplay);
 
@@ -8159,6 +8168,8 @@ intel_modeset_check_state(struct drm_device *dev)
 		bool enabled = false;
 		bool active = false;
 
+		memset(&pipe_config, 0, sizeof(pipe_config));
+
 		DRM_DEBUG_KMS("[CRTC:%d]\n",
 			      crtc->base.base.id);
 
@@ -8172,6 +8183,8 @@ intel_modeset_check_state(struct drm_device *dev)
 			enabled = true;
 			if (encoder->connectors_active)
 				active = true;
+			if (encoder->get_config)
+				encoder->get_config(encoder, &pipe_config);
 		}
 		WARN(active != crtc->active,
 		     "crtc's computed active state doesn't match tracked active state "
@@ -8180,7 +8193,6 @@ intel_modeset_check_state(struct drm_device *dev)
 		     "crtc's computed enabled state doesn't match tracked enabled state "
 		     "(expected %i, found %i)\n", enabled, crtc->base.enabled);
 
-		memset(&pipe_config, 0, sizeof(pipe_config));
 		pipe_config.cpu_transcoder = crtc->config.cpu_transcoder;
 		active = dev_priv->display.get_pipe_config(crtc,
 							   &pipe_config);
@@ -9589,8 +9601,10 @@ setup_pipes:
 		pipe = 0;
 
 		if (encoder->get_hw_state(encoder, &pipe)) {
-			encoder->base.crtc =
-				dev_priv->pipe_to_crtc_mapping[pipe];
+			crtc = to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
+			encoder->base.crtc = &crtc->base;
+			if (encoder->get_config)
+				encoder->get_config(encoder, &crtc->config);
 		} else {
 			encoder->base.crtc = NULL;
 		}
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 6ba9f09fe21a..7c5eb2f6208f 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1346,6 +1346,28 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 	return true;
 }
 
+static void intel_dp_get_config(struct intel_encoder *encoder,
+				struct intel_crtc_config *pipe_config)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	u32 tmp, flags = 0;
+
+	tmp = I915_READ(intel_dp->output_reg);
+
+	if (tmp & DP_SYNC_HS_HIGH)
+		flags |= DRM_MODE_FLAG_PHSYNC;
+	else
+		flags |= DRM_MODE_FLAG_NHSYNC;
+
+	if (tmp & DP_SYNC_VS_HIGH)
+		flags |= DRM_MODE_FLAG_PVSYNC;
+	else
+		flags |= DRM_MODE_FLAG_NVSYNC;
+
+	pipe_config->adjusted_mode.flags |= flags;
+}
+
 static void intel_disable_dp(struct intel_encoder *encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
@@ -3184,6 +3206,7 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port)
 	intel_encoder->disable = intel_disable_dp;
 	intel_encoder->post_disable = intel_post_disable_dp;
 	intel_encoder->get_hw_state = intel_dp_get_hw_state;
+	intel_encoder->get_config = intel_dp_get_config;
 	if (IS_VALLEYVIEW(dev))
 		intel_encoder->pre_pll_enable = intel_dp_pre_pll_enable;
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 9b0af7e27c82..a435ce1d075e 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -139,6 +139,10 @@ struct intel_encoder {
 	 * the encoder is active. If the encoder is enabled it also set the pipe
 	 * it is connected to in the pipe parameter. */
 	bool (*get_hw_state)(struct intel_encoder *, enum pipe *pipe);
+	/* Reconstructs the equivalent mode flags for the current hardware
+	 * state. */
+	void (*get_config)(struct intel_encoder *,
+			   struct intel_crtc_config *pipe_config);
 	int crtc_mask;
 	enum hpd_pin hpd_pin;
 };
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index 2c0be924e9a9..9e80d487b5cb 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -136,6 +136,26 @@ static bool intel_dvo_get_hw_state(struct intel_encoder *encoder,
 	return true;
 }
 
+static void intel_dvo_get_config(struct intel_encoder *encoder,
+				 struct intel_crtc_config *pipe_config)
+{
+	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	struct intel_dvo *intel_dvo = enc_to_intel_dvo(&encoder->base);
+	u32 tmp, flags = 0;
+
+	tmp = I915_READ(intel_dvo->dev.dvo_reg);
+	if (tmp & DVO_HSYNC_ACTIVE_HIGH)
+		flags |= DRM_MODE_FLAG_PHSYNC;
+	else
+		flags |= DRM_MODE_FLAG_NHSYNC;
+	if (tmp & DVO_VSYNC_ACTIVE_HIGH)
+		flags |= DRM_MODE_FLAG_PVSYNC;
+	else
+		flags |= DRM_MODE_FLAG_NVSYNC;
+
+	pipe_config->adjusted_mode.flags |= flags;
+}
+
 static void intel_disable_dvo(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
@@ -447,6 +467,7 @@ void intel_dvo_init(struct drm_device *dev)
 	intel_encoder->disable = intel_disable_dvo;
 	intel_encoder->enable = intel_enable_dvo;
 	intel_encoder->get_hw_state = intel_dvo_get_hw_state;
+	intel_encoder->get_config = intel_dvo_get_config;
 	intel_connector->get_hw_state = intel_dvo_connector_get_hw_state;
 
 	/* Now, try to find a controller */
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 2b727f0d201f..18f8ce0404c6 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -658,6 +658,28 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder,
 	return true;
 }
 
+static void intel_hdmi_get_config(struct intel_encoder *encoder,
+				  struct intel_crtc_config *pipe_config)
+{
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
+	u32 tmp, flags = 0;
+
+	tmp = I915_READ(intel_hdmi->hdmi_reg);
+
+	if (tmp & SDVO_HSYNC_ACTIVE_HIGH)
+		flags |= DRM_MODE_FLAG_PHSYNC;
+	else
+		flags |= DRM_MODE_FLAG_NHSYNC;
+
+	if (tmp & SDVO_VSYNC_ACTIVE_HIGH)
+		flags |= DRM_MODE_FLAG_PVSYNC;
+	else
+		flags |= DRM_MODE_FLAG_NVSYNC;
+
+	pipe_config->adjusted_mode.flags |= flags;
+}
+
 static void intel_enable_hdmi(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
@@ -1216,6 +1238,7 @@ void intel_hdmi_init(struct drm_device *dev, int hdmi_reg, enum port port)
 	intel_encoder->enable = intel_enable_hdmi;
 	intel_encoder->disable = intel_disable_hdmi;
 	intel_encoder->get_hw_state = intel_hdmi_get_hw_state;
+	intel_encoder->get_config = intel_hdmi_get_config;
 	if (IS_VALLEYVIEW(dev)) {
 		intel_encoder->pre_enable = intel_hdmi_pre_enable;
 		intel_encoder->pre_pll_enable = intel_hdmi_pre_pll_enable;
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 36fe291172ee..655486099b76 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -86,6 +86,31 @@ static bool intel_lvds_get_hw_state(struct intel_encoder *encoder,
 	return true;
 }
 
+static void intel_lvds_get_config(struct intel_encoder *encoder,
+				  struct intel_crtc_config *pipe_config)
+{
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 lvds_reg, tmp, flags = 0;
+
+	if (HAS_PCH_SPLIT(dev))
+		lvds_reg = PCH_LVDS;
+	else
+		lvds_reg = LVDS;
+
+	tmp = I915_READ(lvds_reg);
+	if (tmp & LVDS_HSYNC_POLARITY)
+		flags |= DRM_MODE_FLAG_NHSYNC;
+	else
+		flags |= DRM_MODE_FLAG_PHSYNC;
+	if (tmp & LVDS_VSYNC_POLARITY)
+		flags |= DRM_MODE_FLAG_NVSYNC;
+	else
+		flags |= DRM_MODE_FLAG_PVSYNC;
+
+	pipe_config->adjusted_mode.flags |= flags;
+}
+
 /* The LVDS pin pair needs to be on before the DPLLs are enabled.
  * This is an exception to the general rule that mode_set doesn't turn
  * things on.
@@ -921,6 +946,7 @@ bool intel_lvds_init(struct drm_device *dev)
 	intel_encoder->compute_config = intel_lvds_compute_config;
 	intel_encoder->disable = intel_disable_lvds;
 	intel_encoder->get_hw_state = intel_lvds_get_hw_state;
+	intel_encoder->get_config = intel_lvds_get_config;
 	intel_connector->get_hw_state = intel_connector_get_hw_state;
 
 	intel_connector_attach_encoder(intel_connector, intel_encoder);
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 78f0631b1c43..4d4a3f0cadfb 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -712,6 +712,13 @@ static bool intel_sdvo_set_timing(struct intel_sdvo *intel_sdvo, u8 cmd,
 		intel_sdvo_set_value(intel_sdvo, cmd + 1, &dtd->part2, sizeof(dtd->part2));
 }
 
+static bool intel_sdvo_get_timing(struct intel_sdvo *intel_sdvo, u8 cmd,
+				  struct intel_sdvo_dtd *dtd)
+{
+	return intel_sdvo_get_value(intel_sdvo, cmd, &dtd->part1, sizeof(dtd->part1)) &&
+		intel_sdvo_get_value(intel_sdvo, cmd + 1, &dtd->part2, sizeof(dtd->part2));
+}
+
 static bool intel_sdvo_set_input_timing(struct intel_sdvo *intel_sdvo,
 					 struct intel_sdvo_dtd *dtd)
 {
@@ -726,6 +733,13 @@ static bool intel_sdvo_set_output_timing(struct intel_sdvo *intel_sdvo,
 				     SDVO_CMD_SET_OUTPUT_TIMINGS_PART1, dtd);
 }
 
+static bool intel_sdvo_get_input_timing(struct intel_sdvo *intel_sdvo,
+					struct intel_sdvo_dtd *dtd)
+{
+	return intel_sdvo_get_timing(intel_sdvo,
+				     SDVO_CMD_GET_INPUT_TIMINGS_PART1, dtd);
+}
+
 static bool
 intel_sdvo_create_preferred_input_timing(struct intel_sdvo *intel_sdvo,
 					 uint16_t clock,
@@ -1295,6 +1309,33 @@ static bool intel_sdvo_get_hw_state(struct intel_encoder *encoder,
 	return true;
 }
 
+static void intel_sdvo_get_config(struct intel_encoder *encoder,
+				  struct intel_crtc_config *pipe_config)
+{
+	struct intel_sdvo *intel_sdvo = to_intel_sdvo(&encoder->base);
+	struct intel_sdvo_dtd dtd;
+	u32 flags = 0;
+	bool ret;
+
+	ret = intel_sdvo_get_input_timing(intel_sdvo, &dtd);
+	if (!ret) {
+		DRM_DEBUG_DRIVER("failed to retrieve SDVO DTD\n");
+		return;
+	}
+
+	if (dtd.part2.dtd_flags & DTD_FLAG_HSYNC_POSITIVE)
+		flags |= DRM_MODE_FLAG_PHSYNC;
+	else
+		flags |= DRM_MODE_FLAG_NHSYNC;
+
+	if (dtd.part2.dtd_flags & DTD_FLAG_VSYNC_POSITIVE)
+		flags |= DRM_MODE_FLAG_PVSYNC;
+	else
+		flags |= DRM_MODE_FLAG_NVSYNC;
+
+	pipe_config->adjusted_mode.flags |= flags;
+}
+
 static void intel_disable_sdvo(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
@@ -2827,6 +2868,7 @@ bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg, bool is_sdvob)
 	intel_encoder->mode_set = intel_sdvo_mode_set;
 	intel_encoder->enable = intel_enable_sdvo;
 	intel_encoder->get_hw_state = intel_sdvo_get_hw_state;
+	intel_encoder->get_config = intel_sdvo_get_config;
 
 	/* In default case sdvo lvds is false */
 	if (!intel_sdvo_get_capabilities(intel_sdvo, &intel_sdvo->caps))

From 5a41254eac1137d0335c0aed7b00f1f3138ee9ca Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 3 May 2013 17:23:37 -0300
Subject: [PATCH 02/70] drm/i915: ILK, SNB and IVB don't have linetime
 watermarks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

So don't call intel_update_linetime_watermarks from
ironlake_crtc_mode_set. Only Haswell has these watermarks.

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@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_display.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 4196155cf964..c7bdbcb6a675 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5841,8 +5841,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc,
 
 	intel_update_watermarks(dev);
 
-	intel_update_linetime_watermarks(dev, pipe, adjusted_mode);
-
 	return ret;
 }
 

From 1011d8c4373b229012208b5aedad4f46396bdd94 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Thu, 9 May 2013 16:55:50 -0300
Subject: [PATCH 03/70] drm/i915: remove intel_update_linetime_watermarks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The spec says the linetime watermarks must be programmed before
enabling any display low power watermarks, but we're currently
updating the linetime watermarks after we call intel_update_watermarks
(and only at crtc_mode_set, not at crtc_{enable,disable}). So IMHO the
best way guarantee the linetime watermarks will be updated before the
low power watermarks is inside the update_wm function, because it's
the function that enables low power watermarks. And since Haswell is
the only platform that has linetime watermarks, let's completely kill
the "intel_update_linetime_watermarks" abstraction and just use the
intel_update_watermarks abstraction by creating haswell_update_wm.

For now haswell_update_wm is still calling sandybridge_update_wm, but
in the future I plan to implement a function specific to Haswell.

v2: - Rename patch
    - Disable LP watermarks before changing linetime WMs (Chris)
    - Add a comment explaining that this is just temporary code.

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_drv.h      |  2 --
 drivers/gpu/drm/i915/intel_display.c |  2 --
 drivers/gpu/drm/i915/intel_drv.h     |  2 --
 drivers/gpu/drm/i915/intel_pm.c      | 43 +++++++++++++++++++---------
 4 files changed, 30 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 14817de37405..639ec0b61450 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -316,8 +316,6 @@ 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);
-	void (*update_linetime_wm)(struct drm_device *dev, int pipe,
-				 struct drm_display_mode *mode);
 	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_display.c b/drivers/gpu/drm/i915/intel_display.c
index c7bdbcb6a675..684ab6417dd4 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -6008,8 +6008,6 @@ static int haswell_crtc_mode_set(struct drm_crtc *crtc,
 
 	intel_update_watermarks(dev);
 
-	intel_update_linetime_watermarks(dev, pipe, adjusted_mode);
-
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index a435ce1d075e..75a7f22262d4 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -732,8 +732,6 @@ 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);
-extern void intel_update_linetime_watermarks(struct drm_device *dev, int pipe,
-			 struct drm_display_mode *mode);
 
 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 e2255ed97894..2ae4e459faa5 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2073,12 +2073,19 @@ static void ivybridge_update_wm(struct drm_device *dev)
 }
 
 static void
-haswell_update_linetime_wm(struct drm_device *dev, int pipe,
-				 struct drm_display_mode *mode)
+haswell_update_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	enum pipe pipe = intel_crtc->pipe;
+	struct drm_display_mode *mode = &intel_crtc->config.adjusted_mode;
 	u32 temp;
 
+	if (!intel_crtc_active(crtc)) {
+		I915_WRITE(PIPE_WM_LINETIME(pipe), 0);
+		return;
+	}
+
 	temp = I915_READ(PIPE_WM_LINETIME(pipe));
 	temp &= ~PIPE_WM_LINETIME_MASK;
 
@@ -2099,6 +2106,26 @@ haswell_update_linetime_wm(struct drm_device *dev, int pipe,
 	I915_WRITE(PIPE_WM_LINETIME(pipe), temp);
 }
 
+static void haswell_update_wm(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_crtc *crtc;
+	enum pipe pipe;
+
+	/* Disable the LP WMs before changine the linetime registers. This is
+	 * just a temporary code that will be replaced soon. */
+	I915_WRITE(WM3_LP_ILK, 0);
+	I915_WRITE(WM2_LP_ILK, 0);
+	I915_WRITE(WM1_LP_ILK, 0);
+
+	for_each_pipe(pipe) {
+		crtc = dev_priv->pipe_to_crtc_mapping[pipe];
+		haswell_update_linetime_wm(dev, crtc);
+	}
+
+	sandybridge_update_wm(dev);
+}
+
 static bool
 sandybridge_compute_sprite_wm(struct drm_device *dev, int plane,
 			      uint32_t sprite_width, int pixel_size,
@@ -2294,15 +2321,6 @@ void intel_update_watermarks(struct drm_device *dev)
 		dev_priv->display.update_wm(dev);
 }
 
-void intel_update_linetime_watermarks(struct drm_device *dev,
-		int pipe, struct drm_display_mode *mode)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (dev_priv->display.update_linetime_wm)
-		dev_priv->display.update_linetime_wm(dev, pipe, mode);
-}
-
 void intel_update_sprite_watermarks(struct drm_device *dev, int pipe,
 				    uint32_t sprite_width, int pixel_size)
 {
@@ -4624,9 +4642,8 @@ void intel_init_pm(struct drm_device *dev)
 			dev_priv->display.init_clock_gating = ivybridge_init_clock_gating;
 		} else if (IS_HASWELL(dev)) {
 			if (SNB_READ_WM0_LATENCY()) {
-				dev_priv->display.update_wm = sandybridge_update_wm;
+				dev_priv->display.update_wm = haswell_update_wm;
 				dev_priv->display.update_sprite_wm = sandybridge_update_sprite_wm;
-				dev_priv->display.update_linetime_wm = haswell_update_linetime_wm;
 			} else {
 				DRM_DEBUG_KMS("Failed to read display plane latency. "
 					      "Disable CxSR\n");

From 7366937312d4e406539b1cf70e1562358bdd560e Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 3 May 2013 17:23:39 -0300
Subject: [PATCH 04/70] drm/i915: use the mode->htotal to calculate linetime
 watermarks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

... instead of mode->crtc_display. The spec says "pipe horizontal
total number of pixels" and the "Haswell Watermark Calculator" tool
uses the "Pipe H Total" instead of "Pipe H Src" as the value.

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@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 | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 2ae4e459faa5..198d9c9ada68 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2093,7 +2093,7 @@ haswell_update_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc)
 	 * row at the given clock rate, multiplied by 8.
 	 * */
 	temp |= PIPE_WM_LINETIME_TIME(
-		((mode->crtc_hdisplay * 1000) / mode->clock) * 8);
+		((mode->htotal * 1000) / mode->clock) * 8);
 
 	/* IPS watermarks are only used by pipe A, and are ignored by
 	 * pipes B and C.  They are calculated similarly to the common

From eaa591ec528ad75bb4c77606c5cb671f05e04db6 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 3 May 2013 17:23:40 -0300
Subject: [PATCH 05/70] drm/i915: fix haswell linetime watermarks calculation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move the "*8"  calculation to the left side so we don't propagate
rounding errors. Also use DIV_ROUND_CLOSEST because that's what the
spec says we need to do.

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@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 | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 198d9c9ada68..2c406ddc6354 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2093,7 +2093,7 @@ haswell_update_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc)
 	 * row at the given clock rate, multiplied by 8.
 	 * */
 	temp |= PIPE_WM_LINETIME_TIME(
-		((mode->htotal * 1000) / mode->clock) * 8);
+		DIV_ROUND_CLOSEST(mode->htotal * 1000 * 8, mode->clock));
 
 	/* IPS watermarks are only used by pipe A, and are ignored by
 	 * pipes B and C.  They are calculated similarly to the common

From b2b877ffe37d699f77f45e993590b66010491c52 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 3 May 2013 17:23:42 -0300
Subject: [PATCH 06/70] drm/i915: make intel_ddi_get_cdclk_freq return values
 in KHz
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With this, that 338 can finally become the correct 337500.

Due to the change we need to adjust the intel_dp_aux_ch function to
set the correct value, so adjust the division and also use
DIV_ROUND_CLOSEST instead of the old "round down" behavior because the
spec says the value "should be programmed to get as close as possible
to the ideal rate of 2MHz".

Quoting Paulo's follow-up to a question from Chris Wilson to explain
what exactly will change:

I use the 337500 value on the next patch, when setting the
ips_linetime value. The correct frequency is 337500, not 338000.

ips_linetime = DIV_ROUND_CLOSEST(mode->htotal * 1000 * 8,
intel_ddi_get_cdclk_freq);
For a mode with htotal of 2640 [0] we'll have: (i) (2640 * 1000 * 8) /
338000 = 62.48, resulting in 62 and (ii) (2640 * 1000 * 8) / 337500 =
62.57 resulting in 63.

For the case inside intel_dp.c:
Previously we were using 338. So with the old formula we were writing
338/2 = 169 to the register. And 337500 / 169 = 1997.04 (we use 337500
here because it's the real clock value). With the new value of
337500/2000 we'll have 168.75, which is 168 on the round-down case and
169 on the round-closest case. If we write 168 to the register, 337500
/ 168 = 2008.92, and 2008.92 is more distant from 2000 than 1997.04.
So with this patch we're changing the formula but still writing the
same correct value to the DP AUX register.

[0]: That's 1920x1080@50Hz on my DP monitor.

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
[danvet: Pimp the commit message with Paulo's follow-up.]
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_ddi.c | 10 +++++-----
 drivers/gpu/drm/i915/intel_dp.c  |  3 ++-
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index e66852186751..1fdd3b0b7040 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1153,14 +1153,14 @@ static void intel_disable_ddi(struct intel_encoder *intel_encoder)
 int intel_ddi_get_cdclk_freq(struct drm_i915_private *dev_priv)
 {
 	if (I915_READ(HSW_FUSE_STRAP) & HSW_CDCLK_LIMIT)
-		return 450;
+		return 450000;
 	else if ((I915_READ(LCPLL_CTL) & LCPLL_CLK_FREQ_MASK) ==
 		 LCPLL_CLK_FREQ_450)
-		return 450;
+		return 450000;
 	else if (IS_ULT(dev_priv->dev))
-		return 338;
+		return 337500;
 	else
-		return 540;
+		return 540000;
 }
 
 void intel_ddi_pll_init(struct drm_device *dev)
@@ -1173,7 +1173,7 @@ void intel_ddi_pll_init(struct drm_device *dev)
 	 * Don't even try to turn it on.
 	 */
 
-	DRM_DEBUG_KMS("CDCLK running at %dMHz\n",
+	DRM_DEBUG_KMS("CDCLK running at %dKHz\n",
 		      intel_ddi_get_cdclk_freq(dev_priv));
 
 	if (val & LCPLL_CD_SOURCE_FCLK)
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 7c5eb2f6208f..3426a6183188 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -319,7 +319,8 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 	 */
 	if (is_cpu_edp(intel_dp)) {
 		if (HAS_DDI(dev))
-			aux_clock_divider = intel_ddi_get_cdclk_freq(dev_priv) >> 1;
+			aux_clock_divider = DIV_ROUND_CLOSEST(
+				intel_ddi_get_cdclk_freq(dev_priv), 2000);
 		else if (IS_VALLEYVIEW(dev))
 			aux_clock_divider = 100;
 		else if (IS_GEN6(dev) || IS_GEN7(dev))

From 85a02deb4ca5a7e1e39e8538b6eb3c7066469720 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 3 May 2013 17:23:43 -0300
Subject: [PATCH 07/70] drm/i915: set the IPS linetime watermark
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove the "placeholder" comment and set the actual value described by
the specification. We still don't enable IPS, but it won't hurt to
already have the value set here.

While at it, fully set the register value instead of just masking the
values we're changing.

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
[danvet: Resolve conflict due to reordered patches.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_pm.c | 22 +++++++---------------
 1 file changed, 7 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 2c406ddc6354..ad1d35526a8f 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2079,31 +2079,23 @@ haswell_update_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc)
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	enum pipe pipe = intel_crtc->pipe;
 	struct drm_display_mode *mode = &intel_crtc->config.adjusted_mode;
-	u32 temp;
+	u32 linetime, ips_linetime;
 
 	if (!intel_crtc_active(crtc)) {
 		I915_WRITE(PIPE_WM_LINETIME(pipe), 0);
 		return;
 	}
 
-	temp = I915_READ(PIPE_WM_LINETIME(pipe));
-	temp &= ~PIPE_WM_LINETIME_MASK;
-
 	/* The WM are computed with base on how long it takes to fill a single
 	 * row at the given clock rate, multiplied by 8.
 	 * */
-	temp |= PIPE_WM_LINETIME_TIME(
-		DIV_ROUND_CLOSEST(mode->htotal * 1000 * 8, mode->clock));
+	linetime = DIV_ROUND_CLOSEST(mode->htotal * 1000 * 8, mode->clock);
+	ips_linetime = DIV_ROUND_CLOSEST(mode->htotal * 1000 * 8,
+					 intel_ddi_get_cdclk_freq(dev_priv));
 
-	/* IPS watermarks are only used by pipe A, and are ignored by
-	 * pipes B and C.  They are calculated similarly to the common
-	 * linetime values, except that we are using CD clock frequency
-	 * in MHz instead of pixel rate for the division.
-	 *
-	 * This is a placeholder for the IPS watermark calculation code.
-	 */
-
-	I915_WRITE(PIPE_WM_LINETIME(pipe), temp);
+	I915_WRITE(PIPE_WM_LINETIME(pipe),
+		   PIPE_WM_LINETIME_IPS_LINETIME(ips_linetime) |
+		   PIPE_WM_LINETIME_TIME(linetime));
 }
 
 static void haswell_update_wm(struct drm_device *dev)

From 3e1f72664e0a8a31e9b90c48459deb6642fd52f3 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 3 May 2013 17:23:44 -0300
Subject: [PATCH 08/70] drm/i915: MCH_SSKPD is a 64 bit register on Haswell
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

And the SNB_READ_WM0_LATENCY macro is not valid anymore because we
have the "New WM0" at 63:56, so the "Old WM0" could maybe be zero if
the new one is not zero.

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@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 | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index ad1d35526a8f..912ab4d8d722 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4633,7 +4633,7 @@ void intel_init_pm(struct drm_device *dev)
 			}
 			dev_priv->display.init_clock_gating = ivybridge_init_clock_gating;
 		} else if (IS_HASWELL(dev)) {
-			if (SNB_READ_WM0_LATENCY()) {
+			if (I915_READ64(MCH_SSKPD)) {
 				dev_priv->display.update_wm = haswell_update_wm;
 				dev_priv->display.update_sprite_wm = sandybridge_update_sprite_wm;
 			} else {

From 90a8864320b2a9f91e5b5d561924a4bb70b90dcc Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 3 May 2013 17:23:45 -0300
Subject: [PATCH 09/70] drm/i915: set FORCE_ARB_IDLE_PLANES workaround
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 1544d9d57396d5c0c6b7644ed5ae1f4d6caad07a added a workaround
inside haswell_init_clock_gating and mentioned it is "a workaround for
early silicon revisions and should be removed later". This workaround
is documented in bit 31 of PRI_CTL. I asked Arthur and he mentioned
that setting FORCE_ARB_IDLE_PLANES replaces that workaround for the
newer machines. So use the new one.

Also notice that there's still another workaround for PRI_CTL that
involves WM_DBG, but it's not the one we're reverting. And notice that
we were previously setting WM_DBG_DISALLOW_MULTIPIPE_LP which disables
the LP watermarks when more than one pipe is used, and we really don't
want this because we need the LP watermarks if we want to reach deeper
PC states.

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
[danvet: Add a comment for the w/a name Ville dug out of Bspec.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_reg.h |  3 +++
 drivers/gpu/drm/i915/intel_pm.c | 11 +++--------
 2 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index e4cf382f0b75..55caedba53d1 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3711,6 +3711,9 @@
 # define CHICKEN3_DGMG_REQ_OUT_FIX_DISABLE	(1 << 5)
 # define CHICKEN3_DGMG_DONE_FIX_DISABLE		(1 << 2)
 
+#define CHICKEN_PAR1_1		0x42080
+#define  FORCE_ARB_IDLE_PLANES	(1 << 14)
+
 #define DISP_ARB_CTL	0x45000
 #define  DISP_TILE_SURFACE_SWIZZLING	(1<<13)
 #define  DISP_FBC_WM_DIS		(1<<15)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 912ab4d8d722..e198f3881f9a 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4172,14 +4172,9 @@ static void haswell_init_clock_gating(struct drm_device *dev)
 	/* WaSwitchSolVfFArbitrationPriority:hsw */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
 
-	/* XXX: This is a workaround for early silicon revisions and should be
-	 * removed later.
-	 */
-	I915_WRITE(WM_DBG,
-			I915_READ(WM_DBG) |
-			WM_DBG_DISALLOW_MULTIPLE_LP |
-			WM_DBG_DISALLOW_SPRITE |
-			WM_DBG_DISALLOW_MAXFIFO);
+	/* WaRsPkgCStateDisplayPMReq:hsw */
+	I915_WRITE(CHICKEN_PAR1_1,
+		   I915_READ(CHICKEN_PAR1_1) | FORCE_ARB_IDLE_PLANES);
 
 	lpt_init_clock_gating(dev);
 }

From a36689cb771f06819c3fa8139c3d3716dfdf6d53 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 21 May 2013 16:58:49 +0100
Subject: [PATCH 10/70] drm/i915: Be more informative when reporting "too large
 for aperture" error

This should help debugging the truly unexpected cases where it occurs -
in particular to see which value is garbage.

References: https://bugzilla.kernel.org/show_bug.cgi?id=58511
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: s/%ld/%zd/ as spotted by Wu Fengguang's autobuilder.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_gem.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index a1a282ce2466..39a9828cdff9 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2975,7 +2975,10 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 	 */
 	if (obj->base.size >
 	    (map_and_fenceable ? dev_priv->gtt.mappable_end : dev_priv->gtt.total)) {
-		DRM_ERROR("Attempting to bind an object larger than the aperture\n");
+		DRM_ERROR("Attempting to bind an object larger than the aperture: object=%zd > %s aperture=%ld\n",
+			  obj->base.size,
+			  map_and_fenceable ? "mappable" : "total",
+			  map_and_fenceable ? dev_priv->gtt.mappable_end : dev_priv->gtt.total);
 		return -E2BIG;
 	}
 

From df0a67979543e716d411eb11406848dcb50abd0a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Wed, 22 May 2013 11:36:40 +0300
Subject: [PATCH 11/70] drm/i915: Fix WARN_ON() on UP machines
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

WARN_ON(!spin_is_locked()) is not a good idea on a UP system w/o
spinlock debugging. Use WARN_ON_SMP() instead.

This check has been added in

commit 8ba2d18520ce380cf572e9902d9b3b91ece6c2c0
Author: Jani Nikula <jani.nikula@intel.com>
Date:   Fri Apr 12 15:18:37 2013 +0300

    drm/i915: protect backlight registers and data with a spinlock

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_panel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 56f17b2382fc..80bea1d3209f 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -332,7 +332,7 @@ static u32 i915_read_blc_pwm_ctl(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 val;
 
-	WARN_ON(!spin_is_locked(&dev_priv->backlight.lock));
+	WARN_ON_SMP(!spin_is_locked(&dev_priv->backlight.lock));
 
 	/* Restore the CTL value if it lost, e.g. GPU reset */
 

From 2dc8aae06d53458dd3624dc0accd4f81100ee631 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 22 May 2013 17:08:06 +0100
Subject: [PATCH 12/70] drm/i915: Workaround incoherence with fence updates on
 Valleyview

In commit 25ff1195f8a0b3724541ae7bbe331b4296de9c06
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date:   Thu Apr 4 21:31:03 2013 +0100

    drm/i915: Workaround incoherence between fences and LLC across multiple CPUs

we introduced an empirical workaround for memory corruption when using
fences from multiple CPUs. At the time, we did not have any results for
Valleyview, so the presumption was that it was limited to recent
generations using LLC. Now we have evidence that Valleyview also suffers
incoherence and requires a similar but different workaround. For
Valleyview, the wbinvd instruction is insufficient and we require the
serialising register write per-CPU. Conversely, that serialising
register write is not enough for SNB/IVB/HSW. To compromise and keep the
code relatively clean, employ both serialisation techniques in the same
workaround.

Reported-by: Jon Bloomfield <jon.bloomfield@intel.com>
Tested-by: Jon Bloomfield <jon.bloomfield@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=62191
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_gem.c | 35 ++++++++++++++++++++++++++-------
 1 file changed, 28 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 39a9828cdff9..1b735a4a2873 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2693,18 +2693,33 @@ static inline int fence_number(struct drm_i915_private *dev_priv,
 	return fence - dev_priv->fence_regs;
 }
 
+struct write_fence {
+	struct drm_device *dev;
+	struct drm_i915_gem_object *obj;
+	int fence;
+};
+
 static void i915_gem_write_fence__ipi(void *data)
 {
+	struct write_fence *args = data;
+
+	/* Required for SNB+ with LLC */
 	wbinvd();
+
+	/* Required for VLV */
+	i915_gem_write_fence(args->dev, args->fence, args->obj);
 }
 
 static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj,
 					 struct drm_i915_fence_reg *fence,
 					 bool enable)
 {
-	struct drm_device *dev = obj->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int fence_reg = fence_number(dev_priv, fence);
+	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+	struct write_fence args = {
+		.dev = obj->base.dev,
+		.fence = fence_number(dev_priv, fence),
+		.obj = enable ? obj : NULL,
+	};
 
 	/* In order to fully serialize access to the fenced region and
 	 * the update to the fence register we need to take extreme
@@ -2715,13 +2730,19 @@ static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj,
 	 * SNB+ we need to take a step further and emit an explicit wbinvd()
 	 * on each processor in order to manually flush all memory
 	 * transactions before updating the fence register.
+	 *
+	 * However, Valleyview complicates matter. There the wbinvd is
+	 * insufficient and unlike SNB/IVB requires the serialising
+	 * register write. (Note that that register write by itself is
+	 * conversely not sufficient for SNB+.) To compromise, we do both.
 	 */
-	if (HAS_LLC(obj->base.dev))
-		on_each_cpu(i915_gem_write_fence__ipi, NULL, 1);
-	i915_gem_write_fence(dev, fence_reg, enable ? obj : NULL);
+	if (INTEL_INFO(args.dev)->gen >= 6)
+		on_each_cpu(i915_gem_write_fence__ipi, &args, 1);
+	else
+		i915_gem_write_fence(args.dev, args.fence, args.obj);
 
 	if (enable) {
-		obj->fence_reg = fence_reg;
+		obj->fence_reg = args.fence;
 		fence->obj = obj;
 		list_move_tail(&fence->lru_list, &dev_priv->mm.fence_list);
 	} else {

From edbe1581c5f94f7fba39cd9a5b2facd624aab661 Mon Sep 17 00:00:00 2001
From: Thomas Meyer <thomas@m3y3r.de>
Date: Wed, 22 May 2013 23:07:09 +0200
Subject: [PATCH 13/70] drm/i915: Cocci spatch "memdup.spatch"

Signed-off-by: Thomas Meyer <thomas@m3y3r.de>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_dp.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 3426a6183188..9332558fc3dc 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -2511,11 +2511,10 @@ intel_dp_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter)
 			return NULL;
 
 		size = (intel_connector->edid->extensions + 1) * EDID_LENGTH;
-		edid = kmalloc(size, GFP_KERNEL);
+		edid = kmemdup(intel_connector->edid, size, GFP_KERNEL);
 		if (!edid)
 			return NULL;
 
-		memcpy(edid, intel_connector->edid, size);
 		return edid;
 	}
 

From 039735369c8fb105d0a090c949b7f894425121d8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Wed, 8 May 2013 17:16:45 +0300
Subject: [PATCH 14/70] drm: Fix drm_rect documentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The 'struct' keyword was missing so struct drm_rect documentation never
ended up in the generated docs.

Also move the drm_rect documentations to a new section alognside the
various helper functions and add a short description about the intended
purpose of drm_rect.

v2: Move to new section and add general description

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 Documentation/DocBook/drm.tmpl | 8 ++++++--
 include/drm/drm_rect.h         | 9 ++++++++-
 2 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index 7c7af25b330c..91ee107d5d0e 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -1653,8 +1653,6 @@ void intel_crt_init(struct drm_device *dev)
     <sect2>
       <title>KMS API Functions</title>
 !Edrivers/gpu/drm/drm_crtc.c
-!Edrivers/gpu/drm/drm_rect.c
-!Finclude/drm/drm_rect.h
     </sect2>
   </sect1>
 
@@ -2163,6 +2161,12 @@ void intel_crt_init(struct drm_device *dev)
       <title>EDID Helper Functions Reference</title>
 !Edrivers/gpu/drm/drm_edid.c
     </sect2>
+    <sect2>
+      <title>Rectangle Utilities Reference</title>
+!Pinclude/drm/drm_rect.h rect utils
+!Iinclude/drm/drm_rect.h
+!Edrivers/gpu/drm/drm_rect.c
+    </sect2>
   </sect1>
 
   <!-- Internals: vertical blanking -->
diff --git a/include/drm/drm_rect.h b/include/drm/drm_rect.h
index 64fa265c6ffb..d1286297567b 100644
--- a/include/drm/drm_rect.h
+++ b/include/drm/drm_rect.h
@@ -25,7 +25,14 @@
 #define DRM_RECT_H
 
 /**
- * drm_rect - two dimensional rectangle
+ * DOC: rect utils
+ *
+ * Utility functions to help manage rectangular areas for
+ * clipping, scaling, etc. calculations.
+ */
+
+/**
+ * struct drm_rect - two dimensional rectangle
  * @x1: horizontal starting coordinate (inclusive)
  * @x2: horizontal ending coordinate (exclusive)
  * @y1: vertical starting coordinate (inclusive)

From edc3d8848dc9fe2a470316363dab8ef211d77e01 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Thu, 23 May 2013 13:55:35 +0300
Subject: [PATCH 15/70] drm/i915: avoid big kmallocs on reading error state

Sometimes when user is trying to get error state out from
debugfs after gpu hang, the memory is low and/or fragmented
enough that kmalloc in seq_file will fail.

Prevent big kmalloc by avoiding seq_file and instead convert
error state to string in smaller chunks.

v2: better alloc flags, better truncate, correct
locking, and error handling improvements (Chris Wilson)

v3: printf annotations (Daniel Vetter)

Signed-off-by: Mika Kuoppala <mika.kuoppala@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_debugfs.c  | 242 ++++++++++++++++++++-------
 drivers/gpu/drm/i915/i915_drv.h      |  16 +-
 drivers/gpu/drm/i915/intel_display.c |  52 +++---
 drivers/gpu/drm/i915/intel_overlay.c |  13 +-
 4 files changed, 231 insertions(+), 92 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index a55630a80f83..3a8409a31266 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -604,15 +604,80 @@ static const char *purgeable_flag(int purgeable)
 	return purgeable ? " purgeable" : "";
 }
 
-static void print_error_buffers(struct seq_file *m,
+static void i915_error_vprintf(struct drm_i915_error_state_buf *e,
+			       const char *f, va_list args)
+{
+	unsigned len;
+
+	if (!e->err && WARN(e->bytes > (e->size - 1), "overflow")) {
+		e->err = -ENOSPC;
+		return;
+	}
+
+	if (e->bytes == e->size - 1 || e->err)
+		return;
+
+	/* Seek the first printf which is hits start position */
+	if (e->pos < e->start) {
+		len = vsnprintf(NULL, 0, f, args);
+		if (e->pos + len <= e->start) {
+			e->pos += len;
+			return;
+		}
+
+		/* First vsnprintf needs to fit in full for memmove*/
+		if (len >= e->size) {
+			e->err = -EIO;
+			return;
+		}
+	}
+
+	len = vsnprintf(e->buf + e->bytes, e->size - e->bytes, f, args);
+	if (len >= e->size - e->bytes)
+		len = e->size - e->bytes - 1;
+
+	/* If this is first printf in this window, adjust it so that
+	 * start position matches start of the buffer
+	 */
+	if (e->pos < e->start) {
+		const size_t off = e->start - e->pos;
+
+		/* Should not happen but be paranoid */
+		if (off > len || e->bytes) {
+			e->err = -EIO;
+			return;
+		}
+
+		memmove(e->buf, e->buf + off, len - off);
+		e->bytes = len - off;
+		e->pos = e->start;
+		return;
+	}
+
+	e->bytes += len;
+	e->pos += len;
+}
+
+void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
+{
+	va_list args;
+
+	va_start(args, f);
+	i915_error_vprintf(e, f, args);
+	va_end(args);
+}
+
+#define err_printf(e, ...) i915_error_printf(e, __VA_ARGS__)
+
+static void print_error_buffers(struct drm_i915_error_state_buf *m,
 				const char *name,
 				struct drm_i915_error_buffer *err,
 				int count)
 {
-	seq_printf(m, "%s [%d]:\n", name, count);
+	err_printf(m, "%s [%d]:\n", name, count);
 
 	while (count--) {
-		seq_printf(m, "  %08x %8u %02x %02x %x %x%s%s%s%s%s%s%s",
+		err_printf(m, "  %08x %8u %02x %02x %x %x%s%s%s%s%s%s%s",
 			   err->gtt_offset,
 			   err->size,
 			   err->read_domains,
@@ -627,50 +692,50 @@ static void print_error_buffers(struct seq_file *m,
 			   cache_level_str(err->cache_level));
 
 		if (err->name)
-			seq_printf(m, " (name: %d)", err->name);
+			err_printf(m, " (name: %d)", err->name);
 		if (err->fence_reg != I915_FENCE_REG_NONE)
-			seq_printf(m, " (fence: %d)", err->fence_reg);
+			err_printf(m, " (fence: %d)", err->fence_reg);
 
-		seq_printf(m, "\n");
+		err_printf(m, "\n");
 		err++;
 	}
 }
 
-static void i915_ring_error_state(struct seq_file *m,
+static void i915_ring_error_state(struct drm_i915_error_state_buf *m,
 				  struct drm_device *dev,
 				  struct drm_i915_error_state *error,
 				  unsigned ring)
 {
 	BUG_ON(ring >= I915_NUM_RINGS); /* shut up confused gcc */
-	seq_printf(m, "%s command stream:\n", ring_str(ring));
-	seq_printf(m, "  HEAD: 0x%08x\n", error->head[ring]);
-	seq_printf(m, "  TAIL: 0x%08x\n", error->tail[ring]);
-	seq_printf(m, "  CTL: 0x%08x\n", error->ctl[ring]);
-	seq_printf(m, "  ACTHD: 0x%08x\n", error->acthd[ring]);
-	seq_printf(m, "  IPEIR: 0x%08x\n", error->ipeir[ring]);
-	seq_printf(m, "  IPEHR: 0x%08x\n", error->ipehr[ring]);
-	seq_printf(m, "  INSTDONE: 0x%08x\n", error->instdone[ring]);
+	err_printf(m, "%s command stream:\n", ring_str(ring));
+	err_printf(m, "  HEAD: 0x%08x\n", error->head[ring]);
+	err_printf(m, "  TAIL: 0x%08x\n", error->tail[ring]);
+	err_printf(m, "  CTL: 0x%08x\n", error->ctl[ring]);
+	err_printf(m, "  ACTHD: 0x%08x\n", error->acthd[ring]);
+	err_printf(m, "  IPEIR: 0x%08x\n", error->ipeir[ring]);
+	err_printf(m, "  IPEHR: 0x%08x\n", error->ipehr[ring]);
+	err_printf(m, "  INSTDONE: 0x%08x\n", error->instdone[ring]);
 	if (ring == RCS && INTEL_INFO(dev)->gen >= 4)
-		seq_printf(m, "  BBADDR: 0x%08llx\n", error->bbaddr);
+		err_printf(m, "  BBADDR: 0x%08llx\n", error->bbaddr);
 
 	if (INTEL_INFO(dev)->gen >= 4)
-		seq_printf(m, "  INSTPS: 0x%08x\n", error->instps[ring]);
-	seq_printf(m, "  INSTPM: 0x%08x\n", error->instpm[ring]);
-	seq_printf(m, "  FADDR: 0x%08x\n", error->faddr[ring]);
+		err_printf(m, "  INSTPS: 0x%08x\n", error->instps[ring]);
+	err_printf(m, "  INSTPM: 0x%08x\n", error->instpm[ring]);
+	err_printf(m, "  FADDR: 0x%08x\n", error->faddr[ring]);
 	if (INTEL_INFO(dev)->gen >= 6) {
-		seq_printf(m, "  RC PSMI: 0x%08x\n", error->rc_psmi[ring]);
-		seq_printf(m, "  FAULT_REG: 0x%08x\n", error->fault_reg[ring]);
-		seq_printf(m, "  SYNC_0: 0x%08x [last synced 0x%08x]\n",
+		err_printf(m, "  RC PSMI: 0x%08x\n", error->rc_psmi[ring]);
+		err_printf(m, "  FAULT_REG: 0x%08x\n", error->fault_reg[ring]);
+		err_printf(m, "  SYNC_0: 0x%08x [last synced 0x%08x]\n",
 			   error->semaphore_mboxes[ring][0],
 			   error->semaphore_seqno[ring][0]);
-		seq_printf(m, "  SYNC_1: 0x%08x [last synced 0x%08x]\n",
+		err_printf(m, "  SYNC_1: 0x%08x [last synced 0x%08x]\n",
 			   error->semaphore_mboxes[ring][1],
 			   error->semaphore_seqno[ring][1]);
 	}
-	seq_printf(m, "  seqno: 0x%08x\n", error->seqno[ring]);
-	seq_printf(m, "  waiting: %s\n", yesno(error->waiting[ring]));
-	seq_printf(m, "  ring->head: 0x%08x\n", error->cpu_ring_head[ring]);
-	seq_printf(m, "  ring->tail: 0x%08x\n", error->cpu_ring_tail[ring]);
+	err_printf(m, "  seqno: 0x%08x\n", error->seqno[ring]);
+	err_printf(m, "  waiting: %s\n", yesno(error->waiting[ring]));
+	err_printf(m, "  ring->head: 0x%08x\n", error->cpu_ring_head[ring]);
+	err_printf(m, "  ring->tail: 0x%08x\n", error->cpu_ring_tail[ring]);
 }
 
 struct i915_error_state_file_priv {
@@ -678,9 +743,11 @@ struct i915_error_state_file_priv {
 	struct drm_i915_error_state *error;
 };
 
-static int i915_error_state(struct seq_file *m, void *unused)
+
+static int i915_error_state(struct i915_error_state_file_priv *error_priv,
+			    struct drm_i915_error_state_buf *m)
+
 {
-	struct i915_error_state_file_priv *error_priv = m->private;
 	struct drm_device *dev = error_priv->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct drm_i915_error_state *error = error_priv->error;
@@ -688,34 +755,35 @@ static int i915_error_state(struct seq_file *m, void *unused)
 	int i, j, page, offset, elt;
 
 	if (!error) {
-		seq_printf(m, "no error state collected\n");
+		err_printf(m, "no error state collected\n");
 		return 0;
 	}
 
-	seq_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec,
+	err_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec,
 		   error->time.tv_usec);
-	seq_printf(m, "Kernel: " UTS_RELEASE "\n");
-	seq_printf(m, "PCI ID: 0x%04x\n", dev->pci_device);
-	seq_printf(m, "EIR: 0x%08x\n", error->eir);
-	seq_printf(m, "IER: 0x%08x\n", error->ier);
-	seq_printf(m, "PGTBL_ER: 0x%08x\n", error->pgtbl_er);
-	seq_printf(m, "FORCEWAKE: 0x%08x\n", error->forcewake);
-	seq_printf(m, "DERRMR: 0x%08x\n", error->derrmr);
-	seq_printf(m, "CCID: 0x%08x\n", error->ccid);
+	err_printf(m, "Kernel: " UTS_RELEASE "\n");
+	err_printf(m, "PCI ID: 0x%04x\n", dev->pci_device);
+	err_printf(m, "EIR: 0x%08x\n", error->eir);
+	err_printf(m, "IER: 0x%08x\n", error->ier);
+	err_printf(m, "PGTBL_ER: 0x%08x\n", error->pgtbl_er);
+	err_printf(m, "FORCEWAKE: 0x%08x\n", error->forcewake);
+	err_printf(m, "DERRMR: 0x%08x\n", error->derrmr);
+	err_printf(m, "CCID: 0x%08x\n", error->ccid);
 
 	for (i = 0; i < dev_priv->num_fence_regs; i++)
-		seq_printf(m, "  fence[%d] = %08llx\n", i, error->fence[i]);
+		err_printf(m, "  fence[%d] = %08llx\n", i, error->fence[i]);
 
 	for (i = 0; i < ARRAY_SIZE(error->extra_instdone); i++)
-		seq_printf(m, "  INSTDONE_%d: 0x%08x\n", i, error->extra_instdone[i]);
+		err_printf(m, "  INSTDONE_%d: 0x%08x\n", i,
+			   error->extra_instdone[i]);
 
 	if (INTEL_INFO(dev)->gen >= 6) {
-		seq_printf(m, "ERROR: 0x%08x\n", error->error);
-		seq_printf(m, "DONE_REG: 0x%08x\n", error->done_reg);
+		err_printf(m, "ERROR: 0x%08x\n", error->error);
+		err_printf(m, "DONE_REG: 0x%08x\n", error->done_reg);
 	}
 
 	if (INTEL_INFO(dev)->gen == 7)
-		seq_printf(m, "ERR_INT: 0x%08x\n", error->err_int);
+		err_printf(m, "ERR_INT: 0x%08x\n", error->err_int);
 
 	for_each_ring(ring, dev_priv, i)
 		i915_ring_error_state(m, dev, error, i);
@@ -734,24 +802,25 @@ static int i915_error_state(struct seq_file *m, void *unused)
 		struct drm_i915_error_object *obj;
 
 		if ((obj = error->ring[i].batchbuffer)) {
-			seq_printf(m, "%s --- gtt_offset = 0x%08x\n",
+			err_printf(m, "%s --- gtt_offset = 0x%08x\n",
 				   dev_priv->ring[i].name,
 				   obj->gtt_offset);
 			offset = 0;
 			for (page = 0; page < obj->page_count; page++) {
 				for (elt = 0; elt < PAGE_SIZE/4; elt++) {
-					seq_printf(m, "%08x :  %08x\n", offset, obj->pages[page][elt]);
+					err_printf(m, "%08x :  %08x\n", offset,
+						   obj->pages[page][elt]);
 					offset += 4;
 				}
 			}
 		}
 
 		if (error->ring[i].num_requests) {
-			seq_printf(m, "%s --- %d requests\n",
+			err_printf(m, "%s --- %d requests\n",
 				   dev_priv->ring[i].name,
 				   error->ring[i].num_requests);
 			for (j = 0; j < error->ring[i].num_requests; j++) {
-				seq_printf(m, "  seqno 0x%08x, emitted %ld, tail 0x%08x\n",
+				err_printf(m, "  seqno 0x%08x, emitted %ld, tail 0x%08x\n",
 					   error->ring[i].requests[j].seqno,
 					   error->ring[i].requests[j].jiffies,
 					   error->ring[i].requests[j].tail);
@@ -759,13 +828,13 @@ static int i915_error_state(struct seq_file *m, void *unused)
 		}
 
 		if ((obj = error->ring[i].ringbuffer)) {
-			seq_printf(m, "%s --- ringbuffer = 0x%08x\n",
+			err_printf(m, "%s --- ringbuffer = 0x%08x\n",
 				   dev_priv->ring[i].name,
 				   obj->gtt_offset);
 			offset = 0;
 			for (page = 0; page < obj->page_count; page++) {
 				for (elt = 0; elt < PAGE_SIZE/4; elt++) {
-					seq_printf(m, "%08x :  %08x\n",
+					err_printf(m, "%08x :  %08x\n",
 						   offset,
 						   obj->pages[page][elt]);
 					offset += 4;
@@ -775,12 +844,12 @@ static int i915_error_state(struct seq_file *m, void *unused)
 
 		obj = error->ring[i].ctx;
 		if (obj) {
-			seq_printf(m, "%s --- HW Context = 0x%08x\n",
+			err_printf(m, "%s --- HW Context = 0x%08x\n",
 				   dev_priv->ring[i].name,
 				   obj->gtt_offset);
 			offset = 0;
 			for (elt = 0; elt < PAGE_SIZE/16; elt += 4) {
-				seq_printf(m, "[%04x] %08x %08x %08x %08x\n",
+				err_printf(m, "[%04x] %08x %08x %08x %08x\n",
 					   offset,
 					   obj->pages[0][elt],
 					   obj->pages[0][elt+1],
@@ -806,8 +875,7 @@ i915_error_state_write(struct file *filp,
 		       size_t cnt,
 		       loff_t *ppos)
 {
-	struct seq_file *m = filp->private_data;
-	struct i915_error_state_file_priv *error_priv = m->private;
+	struct i915_error_state_file_priv *error_priv = filp->private_data;
 	struct drm_device *dev = error_priv->dev;
 	int ret;
 
@@ -842,25 +910,81 @@ static int i915_error_state_open(struct inode *inode, struct file *file)
 		kref_get(&error_priv->error->ref);
 	spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags);
 
-	return single_open(file, i915_error_state, error_priv);
+	file->private_data = error_priv;
+
+	return 0;
 }
 
 static int i915_error_state_release(struct inode *inode, struct file *file)
 {
-	struct seq_file *m = file->private_data;
-	struct i915_error_state_file_priv *error_priv = m->private;
+	struct i915_error_state_file_priv *error_priv = file->private_data;
 
 	if (error_priv->error)
 		kref_put(&error_priv->error->ref, i915_error_state_free);
 	kfree(error_priv);
 
-	return single_release(inode, file);
+	return 0;
+}
+
+static ssize_t i915_error_state_read(struct file *file, char __user *userbuf,
+				     size_t count, loff_t *pos)
+{
+	struct i915_error_state_file_priv *error_priv = file->private_data;
+	struct drm_i915_error_state_buf error_str;
+	loff_t tmp_pos = 0;
+	ssize_t ret_count = 0;
+	int ret = 0;
+
+	memset(&error_str, 0, sizeof(error_str));
+
+	/* We need to have enough room to store any i915_error_state printf
+	 * so that we can move it to start position.
+	 */
+	error_str.size = count + 1 > PAGE_SIZE ? count + 1 : PAGE_SIZE;
+	error_str.buf = kmalloc(error_str.size,
+				GFP_TEMPORARY | __GFP_NORETRY | __GFP_NOWARN);
+
+	if (error_str.buf == NULL) {
+		error_str.size = PAGE_SIZE;
+		error_str.buf = kmalloc(error_str.size, GFP_TEMPORARY);
+	}
+
+	if (error_str.buf == NULL) {
+		error_str.size = 128;
+		error_str.buf = kmalloc(error_str.size, GFP_TEMPORARY);
+	}
+
+	if (error_str.buf == NULL)
+		return -ENOMEM;
+
+	error_str.start = *pos;
+
+	ret = i915_error_state(error_priv, &error_str);
+	if (ret)
+		goto out;
+
+	if (error_str.bytes == 0 && error_str.err) {
+		ret = error_str.err;
+		goto out;
+	}
+
+	ret_count = simple_read_from_buffer(userbuf, count, &tmp_pos,
+					    error_str.buf,
+					    error_str.bytes);
+
+	if (ret_count < 0)
+		ret = ret_count;
+	else
+		*pos = error_str.start + ret_count;
+out:
+	kfree(error_str.buf);
+	return ret ?: ret_count;
 }
 
 static const struct file_operations i915_error_state_fops = {
 	.owner = THIS_MODULE,
 	.open = i915_error_state_open,
-	.read = seq_read,
+	.read = i915_error_state_read,
 	.write = i915_error_state_write,
 	.llseek = default_llseek,
 	.release = i915_error_state_release,
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 639ec0b61450..7772bb6f73ba 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -826,6 +826,15 @@ struct i915_gem_mm {
 	u32 object_count;
 };
 
+struct drm_i915_error_state_buf {
+	unsigned bytes;
+	unsigned size;
+	int err;
+	u8 *buf;
+	loff_t start;
+	loff_t pos;
+};
+
 struct i915_gpu_error {
 	/* For hangcheck timer */
 #define DRM_I915_HANGCHECK_PERIOD 1500 /* in ms */
@@ -1818,6 +1827,8 @@ void i915_gem_dump_object(struct drm_i915_gem_object *obj, int len,
 /* i915_debugfs.c */
 int i915_debugfs_init(struct drm_minor *minor);
 void i915_debugfs_cleanup(struct drm_minor *minor);
+__printf(2, 3)
+void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...);
 
 /* i915_suspend.c */
 extern int i915_save_state(struct drm_device *dev);
@@ -1899,10 +1910,11 @@ int i915_reg_read_ioctl(struct drm_device *dev, void *data,
 /* overlay */
 #ifdef CONFIG_DEBUG_FS
 extern struct intel_overlay_error_state *intel_overlay_capture_error_state(struct drm_device *dev);
-extern void intel_overlay_print_error_state(struct seq_file *m, struct intel_overlay_error_state *error);
+extern void intel_overlay_print_error_state(struct drm_i915_error_state_buf *e,
+					    struct intel_overlay_error_state *error);
 
 extern struct intel_display_error_state *intel_display_capture_error_state(struct drm_device *dev);
-extern void intel_display_print_error_state(struct seq_file *m,
+extern void intel_display_print_error_state(struct drm_i915_error_state_buf *e,
 					    struct drm_device *dev,
 					    struct intel_display_error_state *error);
 #endif
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 684ab6417dd4..1c0d6d3bfe83 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -9858,48 +9858,50 @@ intel_display_capture_error_state(struct drm_device *dev)
 	return error;
 }
 
+#define err_printf(e, ...) i915_error_printf(e, __VA_ARGS__)
+
 void
-intel_display_print_error_state(struct seq_file *m,
+intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 				struct drm_device *dev,
 				struct intel_display_error_state *error)
 {
 	int i;
 
-	seq_printf(m, "Num Pipes: %d\n", INTEL_INFO(dev)->num_pipes);
+	err_printf(m, "Num Pipes: %d\n", INTEL_INFO(dev)->num_pipes);
 	if (HAS_POWER_WELL(dev))
-		seq_printf(m, "PWR_WELL_CTL2: %08x\n",
+		err_printf(m, "PWR_WELL_CTL2: %08x\n",
 			   error->power_well_driver);
 	for_each_pipe(i) {
-		seq_printf(m, "Pipe [%d]:\n", i);
-		seq_printf(m, "  CPU transcoder: %c\n",
+		err_printf(m, "Pipe [%d]:\n", i);
+		err_printf(m, "  CPU transcoder: %c\n",
 			   transcoder_name(error->pipe[i].cpu_transcoder));
-		seq_printf(m, "  CONF: %08x\n", error->pipe[i].conf);
-		seq_printf(m, "  SRC: %08x\n", error->pipe[i].source);
-		seq_printf(m, "  HTOTAL: %08x\n", error->pipe[i].htotal);
-		seq_printf(m, "  HBLANK: %08x\n", error->pipe[i].hblank);
-		seq_printf(m, "  HSYNC: %08x\n", error->pipe[i].hsync);
-		seq_printf(m, "  VTOTAL: %08x\n", error->pipe[i].vtotal);
-		seq_printf(m, "  VBLANK: %08x\n", error->pipe[i].vblank);
-		seq_printf(m, "  VSYNC: %08x\n", error->pipe[i].vsync);
+		err_printf(m, "  CONF: %08x\n", error->pipe[i].conf);
+		err_printf(m, "  SRC: %08x\n", error->pipe[i].source);
+		err_printf(m, "  HTOTAL: %08x\n", error->pipe[i].htotal);
+		err_printf(m, "  HBLANK: %08x\n", error->pipe[i].hblank);
+		err_printf(m, "  HSYNC: %08x\n", error->pipe[i].hsync);
+		err_printf(m, "  VTOTAL: %08x\n", error->pipe[i].vtotal);
+		err_printf(m, "  VBLANK: %08x\n", error->pipe[i].vblank);
+		err_printf(m, "  VSYNC: %08x\n", error->pipe[i].vsync);
 
-		seq_printf(m, "Plane [%d]:\n", i);
-		seq_printf(m, "  CNTR: %08x\n", error->plane[i].control);
-		seq_printf(m, "  STRIDE: %08x\n", error->plane[i].stride);
+		err_printf(m, "Plane [%d]:\n", i);
+		err_printf(m, "  CNTR: %08x\n", error->plane[i].control);
+		err_printf(m, "  STRIDE: %08x\n", error->plane[i].stride);
 		if (INTEL_INFO(dev)->gen <= 3) {
-			seq_printf(m, "  SIZE: %08x\n", error->plane[i].size);
-			seq_printf(m, "  POS: %08x\n", error->plane[i].pos);
+			err_printf(m, "  SIZE: %08x\n", error->plane[i].size);
+			err_printf(m, "  POS: %08x\n", error->plane[i].pos);
 		}
 		if (INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev))
-			seq_printf(m, "  ADDR: %08x\n", error->plane[i].addr);
+			err_printf(m, "  ADDR: %08x\n", error->plane[i].addr);
 		if (INTEL_INFO(dev)->gen >= 4) {
-			seq_printf(m, "  SURF: %08x\n", error->plane[i].surface);
-			seq_printf(m, "  TILEOFF: %08x\n", error->plane[i].tile_offset);
+			err_printf(m, "  SURF: %08x\n", error->plane[i].surface);
+			err_printf(m, "  TILEOFF: %08x\n", error->plane[i].tile_offset);
 		}
 
-		seq_printf(m, "Cursor [%d]:\n", i);
-		seq_printf(m, "  CNTR: %08x\n", error->cursor[i].control);
-		seq_printf(m, "  POS: %08x\n", error->cursor[i].position);
-		seq_printf(m, "  BASE: %08x\n", error->cursor[i].base);
+		err_printf(m, "Cursor [%d]:\n", i);
+		err_printf(m, "  CNTR: %08x\n", error->cursor[i].control);
+		err_printf(m, "  POS: %08x\n", error->cursor[i].position);
+		err_printf(m, "  BASE: %08x\n", error->cursor[i].base);
 	}
 }
 #endif
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 67a2501d519d..836794b68fc6 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -1485,14 +1485,15 @@ err:
 }
 
 void
-intel_overlay_print_error_state(struct seq_file *m, struct intel_overlay_error_state *error)
+intel_overlay_print_error_state(struct drm_i915_error_state_buf *m,
+				struct intel_overlay_error_state *error)
 {
-	seq_printf(m, "Overlay, status: 0x%08x, interrupt: 0x%08x\n",
-		   error->dovsta, error->isr);
-	seq_printf(m, "  Register file at 0x%08lx:\n",
-		   error->base);
+	i915_error_printf(m, "Overlay, status: 0x%08x, interrupt: 0x%08x\n",
+			  error->dovsta, error->isr);
+	i915_error_printf(m, "  Register file at 0x%08lx:\n",
+			  error->base);
 
-#define P(x) seq_printf(m, "    " #x ":	0x%08x\n", error->regs.x)
+#define P(x) i915_error_printf(m, "    " #x ":	0x%08x\n", error->regs.x)
 	P(OBUF_0Y);
 	P(OBUF_1Y);
 	P(OBUF_0U);

From 59de08136f0c8d91bfd607d03cf722c5b6c60d1b Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 22 May 2013 15:36:16 +0300
Subject: [PATCH 16/70] drm/i915: group sideband register accessors to a new
 file

Group both the HSW/LPT SBI interface and VLV IOSF sideband register
accessor functions into a new file. No functional changes.

v2: also move intel_sbi_{read,write} (Daniel)

Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/Makefile         |   1 +
 drivers/gpu/drm/i915/i915_drv.h       |   8 ++
 drivers/gpu/drm/i915/intel_display.c  |  98 --------------
 drivers/gpu/drm/i915/intel_drv.h      |   4 -
 drivers/gpu/drm/i915/intel_pm.c       |  60 ---------
 drivers/gpu/drm/i915/intel_sideband.c | 183 ++++++++++++++++++++++++++
 6 files changed, 192 insertions(+), 162 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/intel_sideband.c

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 91f3ac6cef35..40034ecefd3b 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -36,6 +36,7 @@ i915-y := i915_drv.o i915_dma.o i915_irq.o \
 	  intel_overlay.o \
 	  intel_sprite.o \
 	  intel_opregion.o \
+	  intel_sideband.o \
 	  dvo_ch7xxx.o \
 	  dvo_ch7017.o \
 	  dvo_ivch.o \
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 7772bb6f73ba..5a0dfca88668 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1929,9 +1929,17 @@ 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);
+
+/* intel_sideband.c */
 int valleyview_punit_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val);
 int valleyview_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val);
 int valleyview_nc_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val);
+u32 intel_dpio_read(struct drm_i915_private *dev_priv, int reg);
+void intel_dpio_write(struct drm_i915_private *dev_priv, int reg, u32 val);
+u32 intel_sbi_read(struct drm_i915_private *dev_priv, u16 reg,
+		   enum intel_sbi_destination destination);
+void intel_sbi_write(struct drm_i915_private *dev_priv, u16 reg, u32 value,
+		     enum intel_sbi_destination destination);
 
 int vlv_gpu_freq(int ddr_freq, int val);
 int vlv_freq_opcode(int ddr_freq, int val);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 1c0d6d3bfe83..e07ee4c73592 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -381,43 +381,6 @@ static const intel_limit_t intel_limits_vlv_dp = {
 	.find_pll = intel_vlv_find_best_pll,
 };
 
-u32 intel_dpio_read(struct drm_i915_private *dev_priv, int reg)
-{
-	WARN_ON(!mutex_is_locked(&dev_priv->dpio_lock));
-
-	if (wait_for_atomic_us((I915_READ(DPIO_PKT) & DPIO_BUSY) == 0, 100)) {
-		DRM_ERROR("DPIO idle wait timed out\n");
-		return 0;
-	}
-
-	I915_WRITE(DPIO_REG, reg);
-	I915_WRITE(DPIO_PKT, DPIO_RID | DPIO_OP_READ | DPIO_PORTID |
-		   DPIO_BYTE);
-	if (wait_for_atomic_us((I915_READ(DPIO_PKT) & DPIO_BUSY) == 0, 100)) {
-		DRM_ERROR("DPIO read wait timed out\n");
-		return 0;
-	}
-
-	return I915_READ(DPIO_DATA);
-}
-
-void intel_dpio_write(struct drm_i915_private *dev_priv, int reg, u32 val)
-{
-	WARN_ON(!mutex_is_locked(&dev_priv->dpio_lock));
-
-	if (wait_for_atomic_us((I915_READ(DPIO_PKT) & DPIO_BUSY) == 0, 100)) {
-		DRM_ERROR("DPIO idle wait timed out\n");
-		return;
-	}
-
-	I915_WRITE(DPIO_DATA, val);
-	I915_WRITE(DPIO_REG, reg);
-	I915_WRITE(DPIO_PKT, DPIO_RID | DPIO_OP_WRITE | DPIO_PORTID |
-		   DPIO_BYTE);
-	if (wait_for_atomic_us((I915_READ(DPIO_PKT) & DPIO_BUSY) == 0, 100))
-		DRM_ERROR("DPIO write wait timed out\n");
-}
-
 static const intel_limit_t *intel_ironlake_limit(struct drm_crtc *crtc,
 						int refclk)
 {
@@ -1404,67 +1367,6 @@ static void intel_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
 	POSTING_READ(reg);
 }
 
-/* SBI access */
-static void
-intel_sbi_write(struct drm_i915_private *dev_priv, u16 reg, u32 value,
-		enum intel_sbi_destination destination)
-{
-	u32 tmp;
-
-	WARN_ON(!mutex_is_locked(&dev_priv->dpio_lock));
-
-	if (wait_for((I915_READ(SBI_CTL_STAT) & SBI_BUSY) == 0,
-				100)) {
-		DRM_ERROR("timeout waiting for SBI to become ready\n");
-		return;
-	}
-
-	I915_WRITE(SBI_ADDR, (reg << 16));
-	I915_WRITE(SBI_DATA, value);
-
-	if (destination == SBI_ICLK)
-		tmp = SBI_CTL_DEST_ICLK | SBI_CTL_OP_CRWR;
-	else
-		tmp = SBI_CTL_DEST_MPHY | SBI_CTL_OP_IOWR;
-	I915_WRITE(SBI_CTL_STAT, SBI_BUSY | tmp);
-
-	if (wait_for((I915_READ(SBI_CTL_STAT) & (SBI_BUSY | SBI_RESPONSE_FAIL)) == 0,
-				100)) {
-		DRM_ERROR("timeout waiting for SBI to complete write transaction\n");
-		return;
-	}
-}
-
-static u32
-intel_sbi_read(struct drm_i915_private *dev_priv, u16 reg,
-	       enum intel_sbi_destination destination)
-{
-	u32 value = 0;
-	WARN_ON(!mutex_is_locked(&dev_priv->dpio_lock));
-
-	if (wait_for((I915_READ(SBI_CTL_STAT) & SBI_BUSY) == 0,
-				100)) {
-		DRM_ERROR("timeout waiting for SBI to become ready\n");
-		return 0;
-	}
-
-	I915_WRITE(SBI_ADDR, (reg << 16));
-
-	if (destination == SBI_ICLK)
-		value = SBI_CTL_DEST_ICLK | SBI_CTL_OP_CRRD;
-	else
-		value = SBI_CTL_DEST_MPHY | SBI_CTL_OP_IORD;
-	I915_WRITE(SBI_CTL_STAT, value | SBI_BUSY);
-
-	if (wait_for((I915_READ(SBI_CTL_STAT) & (SBI_BUSY | SBI_RESPONSE_FAIL)) == 0,
-				100)) {
-		DRM_ERROR("timeout waiting for SBI to complete read transaction\n");
-		return 0;
-	}
-
-	return I915_READ(SBI_DATA);
-}
-
 void vlv_wait_port_ready(struct drm_i915_private *dev_priv, int port)
 {
 	u32 port_mask;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 75a7f22262d4..83b4fe4b7be0 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -743,10 +743,6 @@ extern int intel_sprite_set_colorkey(struct drm_device *dev, void *data,
 extern int intel_sprite_get_colorkey(struct drm_device *dev, void *data,
 				     struct drm_file *file_priv);
 
-extern u32 intel_dpio_read(struct drm_i915_private *dev_priv, int reg);
-extern void intel_dpio_write(struct drm_i915_private *dev_priv, int reg,
-			     u32 val);
-
 /* Power-related functions, located in intel_pm.c */
 extern void intel_init_pm(struct drm_device *dev);
 /* FBC */
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index e198f3881f9a..cd5bd88980bb 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4956,66 +4956,6 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u8 mbox, u32 val)
 	return 0;
 }
 
-static int vlv_punit_rw(struct drm_i915_private *dev_priv, u32 port, u8 opcode,
-			u8 addr, u32 *val)
-{
-	u32 cmd, devfn, be, bar;
-
-	bar = 0;
-	be = 0xf;
-	devfn = PCI_DEVFN(2, 0);
-
-	cmd = (devfn << IOSF_DEVFN_SHIFT) | (opcode << IOSF_OPCODE_SHIFT) |
-		(port << IOSF_PORT_SHIFT) | (be << IOSF_BYTE_ENABLES_SHIFT) |
-		(bar << IOSF_BAR_SHIFT);
-
-	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
-
-	if (I915_READ(VLV_IOSF_DOORBELL_REQ) & IOSF_SB_BUSY) {
-		DRM_DEBUG_DRIVER("warning: pcode (%s) mailbox access failed\n",
-				 opcode == PUNIT_OPCODE_REG_READ ?
-				 "read" : "write");
-		return -EAGAIN;
-	}
-
-	I915_WRITE(VLV_IOSF_ADDR, addr);
-	if (opcode == PUNIT_OPCODE_REG_WRITE)
-		I915_WRITE(VLV_IOSF_DATA, *val);
-	I915_WRITE(VLV_IOSF_DOORBELL_REQ, cmd);
-
-	if (wait_for((I915_READ(VLV_IOSF_DOORBELL_REQ) & IOSF_SB_BUSY) == 0,
-		     5)) {
-		DRM_ERROR("timeout waiting for pcode %s (%d) to finish\n",
-			  opcode == PUNIT_OPCODE_REG_READ ? "read" : "write",
-			  addr);
-		return -ETIMEDOUT;
-	}
-
-	if (opcode == PUNIT_OPCODE_REG_READ)
-		*val = I915_READ(VLV_IOSF_DATA);
-	I915_WRITE(VLV_IOSF_DATA, 0);
-
-	return 0;
-}
-
-int valleyview_punit_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val)
-{
-	return vlv_punit_rw(dev_priv, IOSF_PORT_PUNIT, PUNIT_OPCODE_REG_READ,
-			    addr, val);
-}
-
-int valleyview_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val)
-{
-	return vlv_punit_rw(dev_priv, IOSF_PORT_PUNIT, PUNIT_OPCODE_REG_WRITE,
-			    addr, &val);
-}
-
-int valleyview_nc_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val)
-{
-	return vlv_punit_rw(dev_priv, IOSF_PORT_NC, PUNIT_OPCODE_REG_READ,
-			    addr, val);
-}
-
 int vlv_gpu_freq(int ddr_freq, int val)
 {
 	int mult, base;
diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c
new file mode 100644
index 000000000000..81af8857857d
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_sideband.c
@@ -0,0 +1,183 @@
+/*
+ * 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"
+
+/* IOSF sideband */
+static int vlv_punit_rw(struct drm_i915_private *dev_priv, u32 port, u8 opcode,
+			u8 addr, u32 *val)
+{
+	u32 cmd, devfn, be, bar;
+
+	bar = 0;
+	be = 0xf;
+	devfn = PCI_DEVFN(2, 0);
+
+	cmd = (devfn << IOSF_DEVFN_SHIFT) | (opcode << IOSF_OPCODE_SHIFT) |
+		(port << IOSF_PORT_SHIFT) | (be << IOSF_BYTE_ENABLES_SHIFT) |
+		(bar << IOSF_BAR_SHIFT);
+
+	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+
+	if (I915_READ(VLV_IOSF_DOORBELL_REQ) & IOSF_SB_BUSY) {
+		DRM_DEBUG_DRIVER("warning: pcode (%s) mailbox access failed\n",
+				 opcode == PUNIT_OPCODE_REG_READ ?
+				 "read" : "write");
+		return -EAGAIN;
+	}
+
+	I915_WRITE(VLV_IOSF_ADDR, addr);
+	if (opcode == PUNIT_OPCODE_REG_WRITE)
+		I915_WRITE(VLV_IOSF_DATA, *val);
+	I915_WRITE(VLV_IOSF_DOORBELL_REQ, cmd);
+
+	if (wait_for((I915_READ(VLV_IOSF_DOORBELL_REQ) & IOSF_SB_BUSY) == 0,
+		     5)) {
+		DRM_ERROR("timeout waiting for pcode %s (%d) to finish\n",
+			  opcode == PUNIT_OPCODE_REG_READ ? "read" : "write",
+			  addr);
+		return -ETIMEDOUT;
+	}
+
+	if (opcode == PUNIT_OPCODE_REG_READ)
+		*val = I915_READ(VLV_IOSF_DATA);
+	I915_WRITE(VLV_IOSF_DATA, 0);
+
+	return 0;
+}
+
+int valleyview_punit_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val)
+{
+	return vlv_punit_rw(dev_priv, IOSF_PORT_PUNIT, PUNIT_OPCODE_REG_READ,
+			    addr, val);
+}
+
+int valleyview_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val)
+{
+	return vlv_punit_rw(dev_priv, IOSF_PORT_PUNIT, PUNIT_OPCODE_REG_WRITE,
+			    addr, &val);
+}
+
+int valleyview_nc_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val)
+{
+	return vlv_punit_rw(dev_priv, IOSF_PORT_NC, PUNIT_OPCODE_REG_READ,
+			    addr, val);
+}
+
+u32 intel_dpio_read(struct drm_i915_private *dev_priv, int reg)
+{
+	WARN_ON(!mutex_is_locked(&dev_priv->dpio_lock));
+
+	if (wait_for_atomic_us((I915_READ(DPIO_PKT) & DPIO_BUSY) == 0, 100)) {
+		DRM_ERROR("DPIO idle wait timed out\n");
+		return 0;
+	}
+
+	I915_WRITE(DPIO_REG, reg);
+	I915_WRITE(DPIO_PKT, DPIO_RID | DPIO_OP_READ | DPIO_PORTID |
+		   DPIO_BYTE);
+	if (wait_for_atomic_us((I915_READ(DPIO_PKT) & DPIO_BUSY) == 0, 100)) {
+		DRM_ERROR("DPIO read wait timed out\n");
+		return 0;
+	}
+
+	return I915_READ(DPIO_DATA);
+}
+
+void intel_dpio_write(struct drm_i915_private *dev_priv, int reg, u32 val)
+{
+	WARN_ON(!mutex_is_locked(&dev_priv->dpio_lock));
+
+	if (wait_for_atomic_us((I915_READ(DPIO_PKT) & DPIO_BUSY) == 0, 100)) {
+		DRM_ERROR("DPIO idle wait timed out\n");
+		return;
+	}
+
+	I915_WRITE(DPIO_DATA, val);
+	I915_WRITE(DPIO_REG, reg);
+	I915_WRITE(DPIO_PKT, DPIO_RID | DPIO_OP_WRITE | DPIO_PORTID |
+		   DPIO_BYTE);
+	if (wait_for_atomic_us((I915_READ(DPIO_PKT) & DPIO_BUSY) == 0, 100))
+		DRM_ERROR("DPIO write wait timed out\n");
+}
+
+/* SBI access */
+u32 intel_sbi_read(struct drm_i915_private *dev_priv, u16 reg,
+		   enum intel_sbi_destination destination)
+{
+	u32 value = 0;
+	WARN_ON(!mutex_is_locked(&dev_priv->dpio_lock));
+
+	if (wait_for((I915_READ(SBI_CTL_STAT) & SBI_BUSY) == 0,
+				100)) {
+		DRM_ERROR("timeout waiting for SBI to become ready\n");
+		return 0;
+	}
+
+	I915_WRITE(SBI_ADDR, (reg << 16));
+
+	if (destination == SBI_ICLK)
+		value = SBI_CTL_DEST_ICLK | SBI_CTL_OP_CRRD;
+	else
+		value = SBI_CTL_DEST_MPHY | SBI_CTL_OP_IORD;
+	I915_WRITE(SBI_CTL_STAT, value | SBI_BUSY);
+
+	if (wait_for((I915_READ(SBI_CTL_STAT) & (SBI_BUSY | SBI_RESPONSE_FAIL)) == 0,
+				100)) {
+		DRM_ERROR("timeout waiting for SBI to complete read transaction\n");
+		return 0;
+	}
+
+	return I915_READ(SBI_DATA);
+}
+
+void intel_sbi_write(struct drm_i915_private *dev_priv, u16 reg, u32 value,
+		     enum intel_sbi_destination destination)
+{
+	u32 tmp;
+
+	WARN_ON(!mutex_is_locked(&dev_priv->dpio_lock));
+
+	if (wait_for((I915_READ(SBI_CTL_STAT) & SBI_BUSY) == 0,
+				100)) {
+		DRM_ERROR("timeout waiting for SBI to become ready\n");
+		return;
+	}
+
+	I915_WRITE(SBI_ADDR, (reg << 16));
+	I915_WRITE(SBI_DATA, value);
+
+	if (destination == SBI_ICLK)
+		tmp = SBI_CTL_DEST_ICLK | SBI_CTL_OP_CRWR;
+	else
+		tmp = SBI_CTL_DEST_MPHY | SBI_CTL_OP_IOWR;
+	I915_WRITE(SBI_CTL_STAT, SBI_BUSY | tmp);
+
+	if (wait_for((I915_READ(SBI_CTL_STAT) & (SBI_BUSY | SBI_RESPONSE_FAIL)) == 0,
+				100)) {
+		DRM_ERROR("timeout waiting for SBI to complete write transaction\n");
+		return;
+	}
+}

From 5a09ae9fd509d7dded34e0d599e1afa5142c6987 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 22 May 2013 15:36:17 +0300
Subject: [PATCH 17/70] drm/i915: refactor VLV IOSF sideband accessors to use
 one helper

Both the intel_dpio_{read,write} and valleyview_{punit,nc}_{read,write}
use the IOSF sideband interface. They access the same registers and do
mostly the same stuff, but no shared code. There are even duplicate
register defines for the same registers. Both have locking, but the
former use dpio_lock and the latter rps.hw_lock. It's racy.

This patch refactors the sideband access to a single function that
expects dpio_lock to be held. The dpio_lock is only used for sideband
stuff, so it's a better match than rps.hw_lock for the purpose. The rps
stuff still needs rps.hw_lock, since it's used to protect more than just
the register access, so rps code will need to hold both locks.

Based on the work by Shobhit Kumar <shobhit.kumar@intel.com> and Yogesh
Mohan Marimuthu <yogesh.mohan.marimuthu@intel.com>.

Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_reg.h       |  93 +++++++++++------------
 drivers/gpu/drm/i915/intel_sideband.c | 102 +++++++++++++-------------
 2 files changed, 93 insertions(+), 102 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 55caedba53d1..dbd9de5abde0 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -342,27 +342,54 @@
 #define  DEBUG_RESET_DISPLAY		(1<<9)
 
 /*
- * DPIO - a special bus for various display related registers to hide behind:
- *  0x800c: m1, m2, n, p1, p2, k dividers
- *  0x8014: REF and SFR select
- *  0x8014: N divider, VCO select
- *  0x801c/3c: core clock bits
- *  0x8048/68: low pass filter coefficients
- *  0x8100: fast clock controls
+ * IOSF sideband
+ */
+#define VLV_IOSF_DOORBELL_REQ			(VLV_DISPLAY_BASE + 0x2100)
+#define   IOSF_DEVFN_SHIFT			24
+#define   IOSF_OPCODE_SHIFT			16
+#define   IOSF_PORT_SHIFT			8
+#define   IOSF_BYTE_ENABLES_SHIFT		4
+#define   IOSF_BAR_SHIFT			1
+#define   IOSF_SB_BUSY				(1<<0)
+#define   IOSF_PORT_PUNIT			0x4
+#define   IOSF_PORT_NC				0x11
+#define   IOSF_PORT_DPIO			0x12
+#define VLV_IOSF_DATA				(VLV_DISPLAY_BASE + 0x2104)
+#define VLV_IOSF_ADDR				(VLV_DISPLAY_BASE + 0x2108)
+
+#define PUNIT_OPCODE_REG_READ			6
+#define PUNIT_OPCODE_REG_WRITE			7
+
+#define PUNIT_REG_GPU_LFM			0xd3
+#define PUNIT_REG_GPU_FREQ_REQ			0xd4
+#define PUNIT_REG_GPU_FREQ_STS			0xd8
+#define PUNIT_REG_MEDIA_TURBO_FREQ_REQ		0xdc
+
+#define PUNIT_FUSE_BUS2				0xf6 /* bits 47:40 */
+#define PUNIT_FUSE_BUS1				0xf5 /* bits 55:48 */
+
+#define IOSF_NC_FB_GFX_FREQ_FUSE		0x1c
+#define   FB_GFX_MAX_FREQ_FUSE_SHIFT		3
+#define   FB_GFX_MAX_FREQ_FUSE_MASK		0x000007f8
+#define   FB_GFX_FGUARANTEED_FREQ_FUSE_SHIFT	11
+#define   FB_GFX_FGUARANTEED_FREQ_FUSE_MASK	0x0007f800
+#define IOSF_NC_FB_GFX_FMAX_FUSE_HI		0x34
+#define   FB_FMAX_VMIN_FREQ_HI_MASK		0x00000007
+#define IOSF_NC_FB_GFX_FMAX_FUSE_LO		0x30
+#define   FB_FMAX_VMIN_FREQ_LO_SHIFT		27
+#define   FB_FMAX_VMIN_FREQ_LO_MASK		0xf8000000
+
+/*
+ * DPIO - a special bus for various display related registers to hide behind
  *
  * DPIO is VLV only.
  *
  * Note: digital port B is DDI0, digital pot C is DDI1
  */
-#define DPIO_PKT			(VLV_DISPLAY_BASE + 0x2100)
-#define  DPIO_RID			(0<<24)
-#define  DPIO_OP_WRITE			(1<<16)
-#define  DPIO_OP_READ			(0<<16)
-#define  DPIO_PORTID			(0x12<<8)
-#define  DPIO_BYTE			(0xf<<4)
-#define  DPIO_BUSY			(1<<0) /* status only */
-#define DPIO_DATA			(VLV_DISPLAY_BASE + 0x2104)
-#define DPIO_REG			(VLV_DISPLAY_BASE + 0x2108)
+#define DPIO_DEVFN			0
+#define DPIO_OPCODE_REG_WRITE		1
+#define DPIO_OPCODE_REG_READ		0
+
 #define DPIO_CTL			(VLV_DISPLAY_BASE + 0x2110)
 #define  DPIO_MODSEL1			(1<<3) /* if ref clk b == 27 */
 #define  DPIO_MODSEL0			(1<<2) /* if ref clk a == 27 */
@@ -4541,40 +4568,6 @@
 #define   GEN6_PCODE_FREQ_IA_RATIO_SHIFT	8
 #define   GEN6_PCODE_FREQ_RING_RATIO_SHIFT	16
 
-#define VLV_IOSF_DOORBELL_REQ			0x182100
-#define   IOSF_DEVFN_SHIFT			24
-#define   IOSF_OPCODE_SHIFT			16
-#define   IOSF_PORT_SHIFT			8
-#define   IOSF_BYTE_ENABLES_SHIFT		4
-#define   IOSF_BAR_SHIFT			1
-#define   IOSF_SB_BUSY				(1<<0)
-#define   IOSF_PORT_PUNIT			0x4
-#define   IOSF_PORT_NC				0x11
-#define VLV_IOSF_DATA				0x182104
-#define VLV_IOSF_ADDR				0x182108
-
-#define PUNIT_OPCODE_REG_READ			6
-#define PUNIT_OPCODE_REG_WRITE			7
-
-#define PUNIT_REG_GPU_LFM			0xd3
-#define PUNIT_REG_GPU_FREQ_REQ			0xd4
-#define PUNIT_REG_GPU_FREQ_STS			0xd8
-#define PUNIT_REG_MEDIA_TURBO_FREQ_REQ		0xdc
-
-#define PUNIT_FUSE_BUS2				0xf6 /* bits 47:40 */
-#define PUNIT_FUSE_BUS1				0xf5 /* bits 55:48 */
-
-#define IOSF_NC_FB_GFX_FREQ_FUSE		0x1c
-#define   FB_GFX_MAX_FREQ_FUSE_SHIFT		3
-#define   FB_GFX_MAX_FREQ_FUSE_MASK		0x000007f8
-#define   FB_GFX_FGUARANTEED_FREQ_FUSE_SHIFT	11
-#define   FB_GFX_FGUARANTEED_FREQ_FUSE_MASK	0x0007f800
-#define IOSF_NC_FB_GFX_FMAX_FUSE_HI		0x34
-#define   FB_FMAX_VMIN_FREQ_HI_MASK		0x00000007
-#define IOSF_NC_FB_GFX_FMAX_FUSE_LO		0x30
-#define   FB_FMAX_VMIN_FREQ_LO_SHIFT		27
-#define   FB_FMAX_VMIN_FREQ_LO_MASK		0xf8000000
-
 #define GEN6_GT_CORE_STATUS		0x138060
 #define   GEN6_CORE_CPD_STATE_MASK	(7<<4)
 #define   GEN6_RCn_MASK			7
diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c
index 81af8857857d..a7c4b61e9c30 100644
--- a/drivers/gpu/drm/i915/intel_sideband.c
+++ b/drivers/gpu/drm/i915/intel_sideband.c
@@ -26,42 +26,37 @@
 #include "intel_drv.h"
 
 /* IOSF sideband */
-static int vlv_punit_rw(struct drm_i915_private *dev_priv, u32 port, u8 opcode,
-			u8 addr, u32 *val)
+static int vlv_sideband_rw(struct drm_i915_private *dev_priv, u32 devfn,
+			   u32 port, u32 opcode, u32 addr, u32 *val)
 {
-	u32 cmd, devfn, be, bar;
-
-	bar = 0;
-	be = 0xf;
-	devfn = PCI_DEVFN(2, 0);
+	u32 cmd, be = 0xf, bar = 0;
+	bool is_read = (opcode == PUNIT_OPCODE_REG_READ ||
+			opcode == DPIO_OPCODE_REG_READ);
 
 	cmd = (devfn << IOSF_DEVFN_SHIFT) | (opcode << IOSF_OPCODE_SHIFT) |
 		(port << IOSF_PORT_SHIFT) | (be << IOSF_BYTE_ENABLES_SHIFT) |
 		(bar << IOSF_BAR_SHIFT);
 
-	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+	WARN_ON(!mutex_is_locked(&dev_priv->dpio_lock));
 
-	if (I915_READ(VLV_IOSF_DOORBELL_REQ) & IOSF_SB_BUSY) {
-		DRM_DEBUG_DRIVER("warning: pcode (%s) mailbox access failed\n",
-				 opcode == PUNIT_OPCODE_REG_READ ?
-				 "read" : "write");
+	if (wait_for((I915_READ(VLV_IOSF_DOORBELL_REQ) & IOSF_SB_BUSY) == 0, 5)) {
+		DRM_DEBUG_DRIVER("IOSF sideband idle wait (%s) timed out\n",
+				 is_read ? "read" : "write");
 		return -EAGAIN;
 	}
 
 	I915_WRITE(VLV_IOSF_ADDR, addr);
-	if (opcode == PUNIT_OPCODE_REG_WRITE)
+	if (!is_read)
 		I915_WRITE(VLV_IOSF_DATA, *val);
 	I915_WRITE(VLV_IOSF_DOORBELL_REQ, cmd);
 
-	if (wait_for((I915_READ(VLV_IOSF_DOORBELL_REQ) & IOSF_SB_BUSY) == 0,
-		     5)) {
-		DRM_ERROR("timeout waiting for pcode %s (%d) to finish\n",
-			  opcode == PUNIT_OPCODE_REG_READ ? "read" : "write",
-			  addr);
+	if (wait_for((I915_READ(VLV_IOSF_DOORBELL_REQ) & IOSF_SB_BUSY) == 0, 5)) {
+		DRM_DEBUG_DRIVER("IOSF sideband finish wait (%s) timed out\n",
+				 is_read ? "read" : "write");
 		return -ETIMEDOUT;
 	}
 
-	if (opcode == PUNIT_OPCODE_REG_READ)
+	if (is_read)
 		*val = I915_READ(VLV_IOSF_DATA);
 	I915_WRITE(VLV_IOSF_DATA, 0);
 
@@ -70,57 +65,60 @@ static int vlv_punit_rw(struct drm_i915_private *dev_priv, u32 port, u8 opcode,
 
 int valleyview_punit_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val)
 {
-	return vlv_punit_rw(dev_priv, IOSF_PORT_PUNIT, PUNIT_OPCODE_REG_READ,
-			    addr, val);
+	int ret;
+
+	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+
+	mutex_lock(&dev_priv->dpio_lock);
+	ret = vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_PUNIT,
+			      PUNIT_OPCODE_REG_READ, addr, val);
+	mutex_unlock(&dev_priv->dpio_lock);
+
+	return ret;
 }
 
 int valleyview_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val)
 {
-	return vlv_punit_rw(dev_priv, IOSF_PORT_PUNIT, PUNIT_OPCODE_REG_WRITE,
-			    addr, &val);
+	int ret;
+
+	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+
+	mutex_lock(&dev_priv->dpio_lock);
+	ret = vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_PUNIT,
+			      PUNIT_OPCODE_REG_WRITE, addr, &val);
+	mutex_unlock(&dev_priv->dpio_lock);
+
+	return ret;
 }
 
 int valleyview_nc_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val)
 {
-	return vlv_punit_rw(dev_priv, IOSF_PORT_NC, PUNIT_OPCODE_REG_READ,
-			    addr, val);
+	int ret;
+
+	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+
+	mutex_lock(&dev_priv->dpio_lock);
+	ret = vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_NC,
+			      PUNIT_OPCODE_REG_READ, addr, val);
+	mutex_unlock(&dev_priv->dpio_lock);
+
+	return ret;
 }
 
 u32 intel_dpio_read(struct drm_i915_private *dev_priv, int reg)
 {
-	WARN_ON(!mutex_is_locked(&dev_priv->dpio_lock));
+	u32 val = 0;
 
-	if (wait_for_atomic_us((I915_READ(DPIO_PKT) & DPIO_BUSY) == 0, 100)) {
-		DRM_ERROR("DPIO idle wait timed out\n");
-		return 0;
-	}
+	vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_DPIO,
+			DPIO_OPCODE_REG_READ, reg, &val);
 
-	I915_WRITE(DPIO_REG, reg);
-	I915_WRITE(DPIO_PKT, DPIO_RID | DPIO_OP_READ | DPIO_PORTID |
-		   DPIO_BYTE);
-	if (wait_for_atomic_us((I915_READ(DPIO_PKT) & DPIO_BUSY) == 0, 100)) {
-		DRM_ERROR("DPIO read wait timed out\n");
-		return 0;
-	}
-
-	return I915_READ(DPIO_DATA);
+	return val;
 }
 
 void intel_dpio_write(struct drm_i915_private *dev_priv, int reg, u32 val)
 {
-	WARN_ON(!mutex_is_locked(&dev_priv->dpio_lock));
-
-	if (wait_for_atomic_us((I915_READ(DPIO_PKT) & DPIO_BUSY) == 0, 100)) {
-		DRM_ERROR("DPIO idle wait timed out\n");
-		return;
-	}
-
-	I915_WRITE(DPIO_DATA, val);
-	I915_WRITE(DPIO_REG, reg);
-	I915_WRITE(DPIO_PKT, DPIO_RID | DPIO_OP_WRITE | DPIO_PORTID |
-		   DPIO_BYTE);
-	if (wait_for_atomic_us((I915_READ(DPIO_PKT) & DPIO_BUSY) == 0, 100))
-		DRM_ERROR("DPIO write wait timed out\n");
+	vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_DPIO,
+			DPIO_OPCODE_REG_WRITE, reg, &val);
 }
 
 /* SBI access */

From a1ca802d98acbc5fd87cc399b6aaf38f54be33e1 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 22 May 2013 15:36:18 +0300
Subject: [PATCH 18/70] drm/i915: drop redundant warnings on not holding
 dpio_lock

The lower level sideband read/write functions already do this.

Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_dp.c   | 6 ------
 drivers/gpu/drm/i915/intel_hdmi.c | 4 ----
 2 files changed, 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 9332558fc3dc..098e7c25f4ef 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1442,8 +1442,6 @@ static void intel_pre_enable_dp(struct intel_encoder *encoder)
 		int pipe = intel_crtc->pipe;
 		u32 val;
 
-		WARN_ON(!mutex_is_locked(&dev_priv->dpio_lock));
-
 		val = intel_dpio_read(dev_priv, DPIO_DATA_LANE_A(port));
 		val = 0;
 		if (pipe)
@@ -1470,8 +1468,6 @@ static void intel_dp_pre_pll_enable(struct intel_encoder *encoder)
 	if (!IS_VALLEYVIEW(dev))
 		return;
 
-	WARN_ON(!mutex_is_locked(&dev_priv->dpio_lock));
-
 	/* Program Tx lane resets to default */
 	intel_dpio_write(dev_priv, DPIO_PCS_TX(port),
 			 DPIO_PCS_TX_LANE2_RESET |
@@ -1622,8 +1618,6 @@ static uint32_t intel_vlv_signal_levels(struct intel_dp *intel_dp)
 	uint8_t train_set = intel_dp->train_set[0];
 	int port = vlv_dport_to_channel(dport);
 
-	WARN_ON(!mutex_is_locked(&dev_priv->dpio_lock));
-
 	switch (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) {
 	case DP_TRAIN_PRE_EMPHASIS_0:
 		preemph_reg_value = 0x0004000;
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 18f8ce0404c6..83b63d72af83 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1018,8 +1018,6 @@ static void intel_hdmi_pre_enable(struct intel_encoder *encoder)
 	if (!IS_VALLEYVIEW(dev))
 		return;
 
-	WARN_ON(!mutex_is_locked(&dev_priv->dpio_lock));
-
 	/* Enable clock channels for this port */
 	val = intel_dpio_read(dev_priv, DPIO_DATA_LANE_A(port));
 	val = 0;
@@ -1063,8 +1061,6 @@ static void intel_hdmi_pre_pll_enable(struct intel_encoder *encoder)
 	if (!IS_VALLEYVIEW(dev))
 		return;
 
-	WARN_ON(!mutex_is_locked(&dev_priv->dpio_lock));
-
 	/* Program Tx lane resets to default */
 	intel_dpio_write(dev_priv, DPIO_PCS_TX(port),
 			 DPIO_PCS_TX_LANE2_RESET |

From ae99258f02fe189c008af94f26140ed691258e9f Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 22 May 2013 15:36:19 +0300
Subject: [PATCH 19/70] drm/i915: rename VLV IOSF sideband functions logically

Rename all VLV IOSF sideband register accessor functions to
vlv_<port>_{read,write}. No functional changes.

Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_debugfs.c   | 24 +++++++-------
 drivers/gpu/drm/i915/i915_drv.h       | 10 +++---
 drivers/gpu/drm/i915/i915_sysfs.c     |  2 +-
 drivers/gpu/drm/i915/intel_display.c  | 46 +++++++++++++--------------
 drivers/gpu/drm/i915/intel_dp.c       | 32 +++++++++----------
 drivers/gpu/drm/i915/intel_hdmi.c     | 42 ++++++++++++------------
 drivers/gpu/drm/i915/intel_pm.c       | 16 +++++-----
 drivers/gpu/drm/i915/intel_sideband.c | 10 +++---
 8 files changed, 91 insertions(+), 91 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 3a8409a31266..bc0f6a55c74b 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1137,16 +1137,16 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 		u32 freq_sts, val;
 
 		mutex_lock(&dev_priv->rps.hw_lock);
-		valleyview_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS,
+		vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS,
 				      &freq_sts);
 		seq_printf(m, "PUNIT_REG_GPU_FREQ_STS: 0x%08x\n", freq_sts);
 		seq_printf(m, "DDR freq: %d MHz\n", dev_priv->mem_freq);
 
-		valleyview_punit_read(dev_priv, PUNIT_FUSE_BUS1, &val);
+		vlv_punit_read(dev_priv, PUNIT_FUSE_BUS1, &val);
 		seq_printf(m, "max GPU freq: %d MHz\n",
 			   vlv_gpu_freq(dev_priv->mem_freq, val));
 
-		valleyview_punit_read(dev_priv, PUNIT_REG_GPU_LFM, &val);
+		vlv_punit_read(dev_priv, PUNIT_REG_GPU_LFM, &val);
 		seq_printf(m, "min GPU freq: %d MHz\n",
 			   vlv_gpu_freq(dev_priv->mem_freq, val));
 
@@ -1787,27 +1787,27 @@ static int i915_dpio_info(struct seq_file *m, void *data)
 	seq_printf(m, "DPIO_CTL: 0x%08x\n", I915_READ(DPIO_CTL));
 
 	seq_printf(m, "DPIO_DIV_A: 0x%08x\n",
-		   intel_dpio_read(dev_priv, _DPIO_DIV_A));
+		   vlv_dpio_read(dev_priv, _DPIO_DIV_A));
 	seq_printf(m, "DPIO_DIV_B: 0x%08x\n",
-		   intel_dpio_read(dev_priv, _DPIO_DIV_B));
+		   vlv_dpio_read(dev_priv, _DPIO_DIV_B));
 
 	seq_printf(m, "DPIO_REFSFR_A: 0x%08x\n",
-		   intel_dpio_read(dev_priv, _DPIO_REFSFR_A));
+		   vlv_dpio_read(dev_priv, _DPIO_REFSFR_A));
 	seq_printf(m, "DPIO_REFSFR_B: 0x%08x\n",
-		   intel_dpio_read(dev_priv, _DPIO_REFSFR_B));
+		   vlv_dpio_read(dev_priv, _DPIO_REFSFR_B));
 
 	seq_printf(m, "DPIO_CORE_CLK_A: 0x%08x\n",
-		   intel_dpio_read(dev_priv, _DPIO_CORE_CLK_A));
+		   vlv_dpio_read(dev_priv, _DPIO_CORE_CLK_A));
 	seq_printf(m, "DPIO_CORE_CLK_B: 0x%08x\n",
-		   intel_dpio_read(dev_priv, _DPIO_CORE_CLK_B));
+		   vlv_dpio_read(dev_priv, _DPIO_CORE_CLK_B));
 
 	seq_printf(m, "DPIO_LFP_COEFF_A: 0x%08x\n",
-		   intel_dpio_read(dev_priv, _DPIO_LFP_COEFF_A));
+		   vlv_dpio_read(dev_priv, _DPIO_LFP_COEFF_A));
 	seq_printf(m, "DPIO_LFP_COEFF_B: 0x%08x\n",
-		   intel_dpio_read(dev_priv, _DPIO_LFP_COEFF_B));
+		   vlv_dpio_read(dev_priv, _DPIO_LFP_COEFF_B));
 
 	seq_printf(m, "DPIO_FASTCLK_DISABLE: 0x%08x\n",
-		   intel_dpio_read(dev_priv, DPIO_FASTCLK_DISABLE));
+		   vlv_dpio_read(dev_priv, DPIO_FASTCLK_DISABLE));
 
 	mutex_unlock(&dev_priv->dpio_lock);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 5a0dfca88668..28d14d6cf4cc 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1931,11 +1931,11 @@ 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);
 
 /* intel_sideband.c */
-int valleyview_punit_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val);
-int valleyview_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val);
-int valleyview_nc_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val);
-u32 intel_dpio_read(struct drm_i915_private *dev_priv, int reg);
-void intel_dpio_write(struct drm_i915_private *dev_priv, int reg, u32 val);
+int vlv_punit_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val);
+int vlv_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val);
+int vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val);
+u32 vlv_dpio_read(struct drm_i915_private *dev_priv, int reg);
+void vlv_dpio_write(struct drm_i915_private *dev_priv, int reg, u32 val);
 u32 intel_sbi_read(struct drm_i915_private *dev_priv, u16 reg,
 		   enum intel_sbi_destination destination);
 void intel_sbi_write(struct drm_i915_private *dev_priv, u16 reg, u32 value,
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index c0d7875b475c..588fa00e6938 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -214,7 +214,7 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
 	mutex_lock(&dev_priv->rps.hw_lock);
 	if (IS_VALLEYVIEW(dev_priv->dev)) {
 		u32 freq;
-		valleyview_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS, &freq);
+		vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS, &freq);
 		ret = vlv_gpu_freq(dev_priv->mem_freq, (freq >> 8) & 0xff);
 	} else {
 		ret = dev_priv->rps.cur_delay * GT_FREQUENCY_MULTIPLIER;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index e07ee4c73592..2a9d0671f8c3 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -4245,24 +4245,24 @@ static void vlv_pllb_recal_opamp(struct drm_i915_private *dev_priv)
 	 * PLLB opamp always calibrates to max value of 0x3f, force enable it
 	 * and set it to a reasonable value instead.
 	 */
-	reg_val = intel_dpio_read(dev_priv, DPIO_IREF(1));
+	reg_val = vlv_dpio_read(dev_priv, DPIO_IREF(1));
 	reg_val &= 0xffffff00;
 	reg_val |= 0x00000030;
-	intel_dpio_write(dev_priv, DPIO_IREF(1), reg_val);
+	vlv_dpio_write(dev_priv, DPIO_IREF(1), reg_val);
 
-	reg_val = intel_dpio_read(dev_priv, DPIO_CALIBRATION);
+	reg_val = vlv_dpio_read(dev_priv, DPIO_CALIBRATION);
 	reg_val &= 0x8cffffff;
 	reg_val = 0x8c000000;
-	intel_dpio_write(dev_priv, DPIO_CALIBRATION, reg_val);
+	vlv_dpio_write(dev_priv, DPIO_CALIBRATION, reg_val);
 
-	reg_val = intel_dpio_read(dev_priv, DPIO_IREF(1));
+	reg_val = vlv_dpio_read(dev_priv, DPIO_IREF(1));
 	reg_val &= 0xffffff00;
-	intel_dpio_write(dev_priv, DPIO_IREF(1), reg_val);
+	vlv_dpio_write(dev_priv, DPIO_IREF(1), reg_val);
 
-	reg_val = intel_dpio_read(dev_priv, DPIO_CALIBRATION);
+	reg_val = vlv_dpio_read(dev_priv, DPIO_CALIBRATION);
 	reg_val &= 0x00ffffff;
 	reg_val |= 0xb0000000;
-	intel_dpio_write(dev_priv, DPIO_CALIBRATION, reg_val);
+	vlv_dpio_write(dev_priv, DPIO_CALIBRATION, reg_val);
 }
 
 static void intel_pch_transcoder_set_m_n(struct intel_crtc *crtc,
@@ -4337,15 +4337,15 @@ static void vlv_update_pll(struct intel_crtc *crtc)
 		vlv_pllb_recal_opamp(dev_priv);
 
 	/* Set up Tx target for periodic Rcomp update */
-	intel_dpio_write(dev_priv, DPIO_IREF_BCAST, 0x0100000f);
+	vlv_dpio_write(dev_priv, DPIO_IREF_BCAST, 0x0100000f);
 
 	/* Disable target IRef on PLL */
-	reg_val = intel_dpio_read(dev_priv, DPIO_IREF_CTL(pipe));
+	reg_val = vlv_dpio_read(dev_priv, DPIO_IREF_CTL(pipe));
 	reg_val &= 0x00ffffff;
-	intel_dpio_write(dev_priv, DPIO_IREF_CTL(pipe), reg_val);
+	vlv_dpio_write(dev_priv, DPIO_IREF_CTL(pipe), reg_val);
 
 	/* Disable fast lock */
-	intel_dpio_write(dev_priv, DPIO_FASTCLK_DISABLE, 0x610);
+	vlv_dpio_write(dev_priv, DPIO_FASTCLK_DISABLE, 0x610);
 
 	/* Set idtafcrecal before PLL is enabled */
 	mdiv = ((bestm1 << DPIO_M1DIV_SHIFT) | (bestm2 & DPIO_M2DIV_MASK));
@@ -4359,47 +4359,47 @@ static void vlv_update_pll(struct intel_crtc *crtc)
 	 * Note: don't use the DAC post divider as it seems unstable.
 	 */
 	mdiv |= (DPIO_POST_DIV_HDMIDP << DPIO_POST_DIV_SHIFT);
-	intel_dpio_write(dev_priv, DPIO_DIV(pipe), mdiv);
+	vlv_dpio_write(dev_priv, DPIO_DIV(pipe), mdiv);
 
 	mdiv |= DPIO_ENABLE_CALIBRATION;
-	intel_dpio_write(dev_priv, DPIO_DIV(pipe), mdiv);
+	vlv_dpio_write(dev_priv, DPIO_DIV(pipe), mdiv);
 
 	/* Set HBR and RBR LPF coefficients */
 	if (adjusted_mode->clock == 162000 ||
 	    intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_HDMI))
-		intel_dpio_write(dev_priv, DPIO_LFP_COEFF(pipe),
+		vlv_dpio_write(dev_priv, DPIO_LFP_COEFF(pipe),
 				 0x005f0021);
 	else
-		intel_dpio_write(dev_priv, DPIO_LFP_COEFF(pipe),
+		vlv_dpio_write(dev_priv, DPIO_LFP_COEFF(pipe),
 				 0x00d0000f);
 
 	if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_EDP) ||
 	    intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DISPLAYPORT)) {
 		/* Use SSC source */
 		if (!pipe)
-			intel_dpio_write(dev_priv, DPIO_REFSFR(pipe),
+			vlv_dpio_write(dev_priv, DPIO_REFSFR(pipe),
 					 0x0df40000);
 		else
-			intel_dpio_write(dev_priv, DPIO_REFSFR(pipe),
+			vlv_dpio_write(dev_priv, DPIO_REFSFR(pipe),
 					 0x0df70000);
 	} else { /* HDMI or VGA */
 		/* Use bend source */
 		if (!pipe)
-			intel_dpio_write(dev_priv, DPIO_REFSFR(pipe),
+			vlv_dpio_write(dev_priv, DPIO_REFSFR(pipe),
 					 0x0df70000);
 		else
-			intel_dpio_write(dev_priv, DPIO_REFSFR(pipe),
+			vlv_dpio_write(dev_priv, DPIO_REFSFR(pipe),
 					 0x0df40000);
 	}
 
-	coreclk = intel_dpio_read(dev_priv, DPIO_CORE_CLK(pipe));
+	coreclk = vlv_dpio_read(dev_priv, DPIO_CORE_CLK(pipe));
 	coreclk = (coreclk & 0x0000ff00) | 0x01c00000;
 	if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DISPLAYPORT) ||
 	    intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_EDP))
 		coreclk |= 0x01000000;
-	intel_dpio_write(dev_priv, DPIO_CORE_CLK(pipe), coreclk);
+	vlv_dpio_write(dev_priv, DPIO_CORE_CLK(pipe), coreclk);
 
-	intel_dpio_write(dev_priv, DPIO_PLL_CML(pipe), 0x87871000);
+	vlv_dpio_write(dev_priv, DPIO_PLL_CML(pipe), 0x87871000);
 
 	for_each_encoder_on_crtc(dev, &crtc->base, encoder)
 		if (encoder->pre_pll_enable)
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 098e7c25f4ef..cdb1c2a6d2b2 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1442,18 +1442,18 @@ static void intel_pre_enable_dp(struct intel_encoder *encoder)
 		int pipe = intel_crtc->pipe;
 		u32 val;
 
-		val = intel_dpio_read(dev_priv, DPIO_DATA_LANE_A(port));
+		val = vlv_dpio_read(dev_priv, DPIO_DATA_LANE_A(port));
 		val = 0;
 		if (pipe)
 			val |= (1<<21);
 		else
 			val &= ~(1<<21);
 		val |= 0x001000c4;
-		intel_dpio_write(dev_priv, DPIO_DATA_CHANNEL(port), val);
+		vlv_dpio_write(dev_priv, DPIO_DATA_CHANNEL(port), val);
 
-		intel_dpio_write(dev_priv, DPIO_PCS_CLOCKBUF0(port),
+		vlv_dpio_write(dev_priv, DPIO_PCS_CLOCKBUF0(port),
 				 0x00760018);
-		intel_dpio_write(dev_priv, DPIO_PCS_CLOCKBUF8(port),
+		vlv_dpio_write(dev_priv, DPIO_PCS_CLOCKBUF8(port),
 				 0x00400888);
 	}
 }
@@ -1469,19 +1469,19 @@ static void intel_dp_pre_pll_enable(struct intel_encoder *encoder)
 		return;
 
 	/* Program Tx lane resets to default */
-	intel_dpio_write(dev_priv, DPIO_PCS_TX(port),
+	vlv_dpio_write(dev_priv, DPIO_PCS_TX(port),
 			 DPIO_PCS_TX_LANE2_RESET |
 			 DPIO_PCS_TX_LANE1_RESET);
-	intel_dpio_write(dev_priv, DPIO_PCS_CLK(port),
+	vlv_dpio_write(dev_priv, DPIO_PCS_CLK(port),
 			 DPIO_PCS_CLK_CRI_RXEB_EIOS_EN |
 			 DPIO_PCS_CLK_CRI_RXDIGFILTSG_EN |
 			 (1<<DPIO_PCS_CLK_DATAWIDTH_SHIFT) |
 				 DPIO_PCS_CLK_SOFT_RESET);
 
 	/* Fix up inter-pair skew failure */
-	intel_dpio_write(dev_priv, DPIO_PCS_STAGGER1(port), 0x00750f00);
-	intel_dpio_write(dev_priv, DPIO_TX_CTL(port), 0x00001500);
-	intel_dpio_write(dev_priv, DPIO_TX_LANE(port), 0x40400000);
+	vlv_dpio_write(dev_priv, DPIO_PCS_STAGGER1(port), 0x00750f00);
+	vlv_dpio_write(dev_priv, DPIO_TX_CTL(port), 0x00001500);
+	vlv_dpio_write(dev_priv, DPIO_TX_LANE(port), 0x40400000);
 }
 
 /*
@@ -1691,14 +1691,14 @@ static uint32_t intel_vlv_signal_levels(struct intel_dp *intel_dp)
 		return 0;
 	}
 
-	intel_dpio_write(dev_priv, DPIO_TX_OCALINIT(port), 0x00000000);
-	intel_dpio_write(dev_priv, DPIO_TX_SWING_CTL4(port), demph_reg_value);
-	intel_dpio_write(dev_priv, DPIO_TX_SWING_CTL2(port),
+	vlv_dpio_write(dev_priv, DPIO_TX_OCALINIT(port), 0x00000000);
+	vlv_dpio_write(dev_priv, DPIO_TX_SWING_CTL4(port), demph_reg_value);
+	vlv_dpio_write(dev_priv, DPIO_TX_SWING_CTL2(port),
 			 uniqtranscale_reg_value);
-	intel_dpio_write(dev_priv, DPIO_TX_SWING_CTL3(port), 0x0C782040);
-	intel_dpio_write(dev_priv, DPIO_PCS_STAGGER0(port), 0x00030000);
-	intel_dpio_write(dev_priv, DPIO_PCS_CTL_OVER1(port), preemph_reg_value);
-	intel_dpio_write(dev_priv, DPIO_TX_OCALINIT(port), 0x80000000);
+	vlv_dpio_write(dev_priv, DPIO_TX_SWING_CTL3(port), 0x0C782040);
+	vlv_dpio_write(dev_priv, DPIO_PCS_STAGGER0(port), 0x00030000);
+	vlv_dpio_write(dev_priv, DPIO_PCS_CTL_OVER1(port), preemph_reg_value);
+	vlv_dpio_write(dev_priv, DPIO_TX_OCALINIT(port), 0x80000000);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 83b63d72af83..8062a92e6e80 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1019,35 +1019,35 @@ static void intel_hdmi_pre_enable(struct intel_encoder *encoder)
 		return;
 
 	/* Enable clock channels for this port */
-	val = intel_dpio_read(dev_priv, DPIO_DATA_LANE_A(port));
+	val = vlv_dpio_read(dev_priv, DPIO_DATA_LANE_A(port));
 	val = 0;
 	if (pipe)
 		val |= (1<<21);
 	else
 		val &= ~(1<<21);
 	val |= 0x001000c4;
-	intel_dpio_write(dev_priv, DPIO_DATA_CHANNEL(port), val);
+	vlv_dpio_write(dev_priv, DPIO_DATA_CHANNEL(port), val);
 
 	/* HDMI 1.0V-2dB */
-	intel_dpio_write(dev_priv, DPIO_TX_OCALINIT(port), 0);
-	intel_dpio_write(dev_priv, DPIO_TX_SWING_CTL4(port),
+	vlv_dpio_write(dev_priv, DPIO_TX_OCALINIT(port), 0);
+	vlv_dpio_write(dev_priv, DPIO_TX_SWING_CTL4(port),
 			 0x2b245f5f);
-	intel_dpio_write(dev_priv, DPIO_TX_SWING_CTL2(port),
+	vlv_dpio_write(dev_priv, DPIO_TX_SWING_CTL2(port),
 			 0x5578b83a);
-	intel_dpio_write(dev_priv, DPIO_TX_SWING_CTL3(port),
+	vlv_dpio_write(dev_priv, DPIO_TX_SWING_CTL3(port),
 			 0x0c782040);
-	intel_dpio_write(dev_priv, DPIO_TX3_SWING_CTL4(port),
+	vlv_dpio_write(dev_priv, DPIO_TX3_SWING_CTL4(port),
 			 0x2b247878);
-	intel_dpio_write(dev_priv, DPIO_PCS_STAGGER0(port), 0x00030000);
-	intel_dpio_write(dev_priv, DPIO_PCS_CTL_OVER1(port),
+	vlv_dpio_write(dev_priv, DPIO_PCS_STAGGER0(port), 0x00030000);
+	vlv_dpio_write(dev_priv, DPIO_PCS_CTL_OVER1(port),
 			 0x00002000);
-	intel_dpio_write(dev_priv, DPIO_TX_OCALINIT(port),
+	vlv_dpio_write(dev_priv, DPIO_TX_OCALINIT(port),
 			 DPIO_TX_OCALINIT_EN);
 
 	/* Program lane clock */
-	intel_dpio_write(dev_priv, DPIO_PCS_CLOCKBUF0(port),
+	vlv_dpio_write(dev_priv, DPIO_PCS_CLOCKBUF0(port),
 			 0x00760018);
-	intel_dpio_write(dev_priv, DPIO_PCS_CLOCKBUF8(port),
+	vlv_dpio_write(dev_priv, DPIO_PCS_CLOCKBUF8(port),
 			 0x00400888);
 }
 
@@ -1062,23 +1062,23 @@ static void intel_hdmi_pre_pll_enable(struct intel_encoder *encoder)
 		return;
 
 	/* Program Tx lane resets to default */
-	intel_dpio_write(dev_priv, DPIO_PCS_TX(port),
+	vlv_dpio_write(dev_priv, DPIO_PCS_TX(port),
 			 DPIO_PCS_TX_LANE2_RESET |
 			 DPIO_PCS_TX_LANE1_RESET);
-	intel_dpio_write(dev_priv, DPIO_PCS_CLK(port),
+	vlv_dpio_write(dev_priv, DPIO_PCS_CLK(port),
 			 DPIO_PCS_CLK_CRI_RXEB_EIOS_EN |
 			 DPIO_PCS_CLK_CRI_RXDIGFILTSG_EN |
 			 (1<<DPIO_PCS_CLK_DATAWIDTH_SHIFT) |
 			 DPIO_PCS_CLK_SOFT_RESET);
 
 	/* Fix up inter-pair skew failure */
-	intel_dpio_write(dev_priv, DPIO_PCS_STAGGER1(port), 0x00750f00);
-	intel_dpio_write(dev_priv, DPIO_TX_CTL(port), 0x00001500);
-	intel_dpio_write(dev_priv, DPIO_TX_LANE(port), 0x40400000);
+	vlv_dpio_write(dev_priv, DPIO_PCS_STAGGER1(port), 0x00750f00);
+	vlv_dpio_write(dev_priv, DPIO_TX_CTL(port), 0x00001500);
+	vlv_dpio_write(dev_priv, DPIO_TX_LANE(port), 0x40400000);
 
-	intel_dpio_write(dev_priv, DPIO_PCS_CTL_OVER1(port),
+	vlv_dpio_write(dev_priv, DPIO_PCS_CTL_OVER1(port),
 			 0x00002000);
-	intel_dpio_write(dev_priv, DPIO_TX_OCALINIT(port),
+	vlv_dpio_write(dev_priv, DPIO_TX_OCALINIT(port),
 			 DPIO_TX_OCALINIT_EN);
 }
 
@@ -1090,8 +1090,8 @@ static void intel_hdmi_post_disable(struct intel_encoder *encoder)
 
 	/* Reset lanes to avoid HDMI flicker (VLV w/a) */
 	mutex_lock(&dev_priv->dpio_lock);
-	intel_dpio_write(dev_priv, DPIO_PCS_TX(port), 0x00000000);
-	intel_dpio_write(dev_priv, DPIO_PCS_CLK(port), 0x00e00060);
+	vlv_dpio_write(dev_priv, DPIO_PCS_TX(port), 0x00000000);
+	vlv_dpio_write(dev_priv, DPIO_PCS_CLK(port), 0x00e00060);
 	mutex_unlock(&dev_priv->dpio_lock);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index cd5bd88980bb..52f1b39148c0 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2566,10 +2566,10 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
 	if (val == dev_priv->rps.cur_delay)
 		return;
 
-	valleyview_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
+	vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
 
 	do {
-		valleyview_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS, &pval);
+		vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS, &pval);
 		if (time_after(jiffies, timeout)) {
 			DRM_DEBUG_DRIVER("timed out waiting for Punit\n");
 			break;
@@ -2577,7 +2577,7 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
 		udelay(10);
 	} while (pval & 1);
 
-	valleyview_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS, &pval);
+	vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS, &pval);
 	if ((pval >> 8) != val)
 		DRM_DEBUG_DRIVER("punit overrode freq: %d requested, but got %d\n",
 			  val, pval >> 8);
@@ -2882,7 +2882,7 @@ int valleyview_rps_max_freq(struct drm_i915_private *dev_priv)
 {
 	u32 val, rp0;
 
-	valleyview_nc_read(dev_priv, IOSF_NC_FB_GFX_FREQ_FUSE, &val);
+	vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FREQ_FUSE, &val);
 
 	rp0 = (val & FB_GFX_MAX_FREQ_FUSE_MASK) >> FB_GFX_MAX_FREQ_FUSE_SHIFT;
 	/* Clamp to max */
@@ -2895,9 +2895,9 @@ static int valleyview_rps_rpe_freq(struct drm_i915_private *dev_priv)
 {
 	u32 val, rpe;
 
-	valleyview_nc_read(dev_priv, IOSF_NC_FB_GFX_FMAX_FUSE_LO, &val);
+	vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FMAX_FUSE_LO, &val);
 	rpe = (val & FB_FMAX_VMIN_FREQ_LO_MASK) >> FB_FMAX_VMIN_FREQ_LO_SHIFT;
-	valleyview_nc_read(dev_priv, IOSF_NC_FB_GFX_FMAX_FUSE_HI, &val);
+	vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FMAX_FUSE_HI, &val);
 	rpe |= (val & FB_FMAX_VMIN_FREQ_HI_MASK) << 5;
 
 	return rpe;
@@ -2907,7 +2907,7 @@ int valleyview_rps_min_freq(struct drm_i915_private *dev_priv)
 {
 	u32 val;
 
-	valleyview_punit_read(dev_priv, PUNIT_REG_GPU_LFM, &val);
+	vlv_punit_read(dev_priv, PUNIT_REG_GPU_LFM, &val);
 
 	return val & 0xff;
 }
@@ -3018,7 +3018,7 @@ static void valleyview_enable_rps(struct drm_device *dev)
 	I915_WRITE(GEN6_RC_CONTROL,
 		   GEN7_RC_CTL_TO_MODE);
 
-	valleyview_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS, &val);
+	vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS, &val);
 	switch ((val >> 6) & 3) {
 	case 0:
 	case 1:
diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c
index a7c4b61e9c30..d150972da048 100644
--- a/drivers/gpu/drm/i915/intel_sideband.c
+++ b/drivers/gpu/drm/i915/intel_sideband.c
@@ -63,7 +63,7 @@ static int vlv_sideband_rw(struct drm_i915_private *dev_priv, u32 devfn,
 	return 0;
 }
 
-int valleyview_punit_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val)
+int vlv_punit_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val)
 {
 	int ret;
 
@@ -77,7 +77,7 @@ int valleyview_punit_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val)
 	return ret;
 }
 
-int valleyview_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val)
+int vlv_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val)
 {
 	int ret;
 
@@ -91,7 +91,7 @@ int valleyview_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val)
 	return ret;
 }
 
-int valleyview_nc_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val)
+int vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val)
 {
 	int ret;
 
@@ -105,7 +105,7 @@ int valleyview_nc_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val)
 	return ret;
 }
 
-u32 intel_dpio_read(struct drm_i915_private *dev_priv, int reg)
+u32 vlv_dpio_read(struct drm_i915_private *dev_priv, int reg)
 {
 	u32 val = 0;
 
@@ -115,7 +115,7 @@ u32 intel_dpio_read(struct drm_i915_private *dev_priv, int reg)
 	return val;
 }
 
-void intel_dpio_write(struct drm_i915_private *dev_priv, int reg, u32 val)
+void vlv_dpio_write(struct drm_i915_private *dev_priv, int reg, u32 val)
 {
 	vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_DPIO,
 			DPIO_OPCODE_REG_WRITE, reg, &val);

From 64936258d7e426bee5f2392269b1b20172db9ffb Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 22 May 2013 15:36:20 +0300
Subject: [PATCH 20/70] drm/i915: change VLV IOSF sideband accessors to not
 return error code

We never check the return values, and there's not much we could do on
errors anyway. Just simplify the signatures. No functional changes.

Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_debugfs.c   |  7 +++----
 drivers/gpu/drm/i915/i915_drv.h       |  6 +++---
 drivers/gpu/drm/i915/i915_sysfs.c     |  2 +-
 drivers/gpu/drm/i915/intel_pm.c       | 18 +++++++---------
 drivers/gpu/drm/i915/intel_sideband.c | 30 ++++++++++++---------------
 5 files changed, 27 insertions(+), 36 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index bc0f6a55c74b..2eb572afbcd3 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1137,16 +1137,15 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 		u32 freq_sts, val;
 
 		mutex_lock(&dev_priv->rps.hw_lock);
-		vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS,
-				      &freq_sts);
+		freq_sts = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
 		seq_printf(m, "PUNIT_REG_GPU_FREQ_STS: 0x%08x\n", freq_sts);
 		seq_printf(m, "DDR freq: %d MHz\n", dev_priv->mem_freq);
 
-		vlv_punit_read(dev_priv, PUNIT_FUSE_BUS1, &val);
+		val = vlv_punit_read(dev_priv, PUNIT_FUSE_BUS1);
 		seq_printf(m, "max GPU freq: %d MHz\n",
 			   vlv_gpu_freq(dev_priv->mem_freq, val));
 
-		vlv_punit_read(dev_priv, PUNIT_REG_GPU_LFM, &val);
+		val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_LFM);
 		seq_printf(m, "min GPU freq: %d MHz\n",
 			   vlv_gpu_freq(dev_priv->mem_freq, val));
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 28d14d6cf4cc..f6419f40df38 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1931,9 +1931,9 @@ 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);
 
 /* intel_sideband.c */
-int vlv_punit_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val);
-int vlv_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val);
-int vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val);
+u32 vlv_punit_read(struct drm_i915_private *dev_priv, u8 addr);
+void vlv_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val);
+u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr);
 u32 vlv_dpio_read(struct drm_i915_private *dev_priv, int reg);
 void vlv_dpio_write(struct drm_i915_private *dev_priv, int reg, u32 val);
 u32 intel_sbi_read(struct drm_i915_private *dev_priv, u16 reg,
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 588fa00e6938..6875b5654c63 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -214,7 +214,7 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
 	mutex_lock(&dev_priv->rps.hw_lock);
 	if (IS_VALLEYVIEW(dev_priv->dev)) {
 		u32 freq;
-		vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS, &freq);
+		freq = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
 		ret = vlv_gpu_freq(dev_priv->mem_freq, (freq >> 8) & 0xff);
 	} else {
 		ret = dev_priv->rps.cur_delay * GT_FREQUENCY_MULTIPLIER;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 52f1b39148c0..fa4c818d4b00 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2569,7 +2569,7 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
 	vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
 
 	do {
-		vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS, &pval);
+		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;
@@ -2577,7 +2577,7 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
 		udelay(10);
 	} while (pval & 1);
 
-	vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS, &pval);
+	pval = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
 	if ((pval >> 8) != val)
 		DRM_DEBUG_DRIVER("punit overrode freq: %d requested, but got %d\n",
 			  val, pval >> 8);
@@ -2882,7 +2882,7 @@ int valleyview_rps_max_freq(struct drm_i915_private *dev_priv)
 {
 	u32 val, rp0;
 
-	vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FREQ_FUSE, &val);
+	val = vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FREQ_FUSE);
 
 	rp0 = (val & FB_GFX_MAX_FREQ_FUSE_MASK) >> FB_GFX_MAX_FREQ_FUSE_SHIFT;
 	/* Clamp to max */
@@ -2895,9 +2895,9 @@ static int valleyview_rps_rpe_freq(struct drm_i915_private *dev_priv)
 {
 	u32 val, rpe;
 
-	vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FMAX_FUSE_LO, &val);
+	val = vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FMAX_FUSE_LO);
 	rpe = (val & FB_FMAX_VMIN_FREQ_LO_MASK) >> FB_FMAX_VMIN_FREQ_LO_SHIFT;
-	vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FMAX_FUSE_HI, &val);
+	val = vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FMAX_FUSE_HI);
 	rpe |= (val & FB_FMAX_VMIN_FREQ_HI_MASK) << 5;
 
 	return rpe;
@@ -2905,11 +2905,7 @@ static int valleyview_rps_rpe_freq(struct drm_i915_private *dev_priv)
 
 int valleyview_rps_min_freq(struct drm_i915_private *dev_priv)
 {
-	u32 val;
-
-	vlv_punit_read(dev_priv, PUNIT_REG_GPU_LFM, &val);
-
-	return val & 0xff;
+	return vlv_punit_read(dev_priv, PUNIT_REG_GPU_LFM) & 0xff;
 }
 
 static void vlv_rps_timer_work(struct work_struct *work)
@@ -3018,7 +3014,7 @@ static void valleyview_enable_rps(struct drm_device *dev)
 	I915_WRITE(GEN6_RC_CONTROL,
 		   GEN7_RC_CTL_TO_MODE);
 
-	vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS, &val);
+	val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
 	switch ((val >> 6) & 3) {
 	case 0:
 	case 1:
diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c
index d150972da048..9a0e6c5ea540 100644
--- a/drivers/gpu/drm/i915/intel_sideband.c
+++ b/drivers/gpu/drm/i915/intel_sideband.c
@@ -63,46 +63,42 @@ static int vlv_sideband_rw(struct drm_i915_private *dev_priv, u32 devfn,
 	return 0;
 }
 
-int vlv_punit_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val)
+u32 vlv_punit_read(struct drm_i915_private *dev_priv, u8 addr)
 {
-	int ret;
+	u32 val = 0;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
 	mutex_lock(&dev_priv->dpio_lock);
-	ret = vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_PUNIT,
-			      PUNIT_OPCODE_REG_READ, addr, val);
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_PUNIT,
+			PUNIT_OPCODE_REG_READ, addr, &val);
 	mutex_unlock(&dev_priv->dpio_lock);
 
-	return ret;
+	return val;
 }
 
-int vlv_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val)
+void vlv_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val)
 {
-	int ret;
-
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
 	mutex_lock(&dev_priv->dpio_lock);
-	ret = vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_PUNIT,
-			      PUNIT_OPCODE_REG_WRITE, addr, &val);
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_PUNIT,
+			PUNIT_OPCODE_REG_WRITE, addr, &val);
 	mutex_unlock(&dev_priv->dpio_lock);
-
-	return ret;
 }
 
-int vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr, u32 *val)
+u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr)
 {
-	int ret;
+	u32 val = 0;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
 
 	mutex_lock(&dev_priv->dpio_lock);
-	ret = vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_NC,
-			      PUNIT_OPCODE_REG_READ, addr, val);
+	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_NC,
+			PUNIT_OPCODE_REG_READ, addr, &val);
 	mutex_unlock(&dev_priv->dpio_lock);
 
-	return ret;
+	return val;
 }
 
 u32 vlv_dpio_read(struct drm_i915_private *dev_priv, int reg)

From 4c4ff43a692b44c6e326f9f28208f3d78ea51f7e Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 24 May 2013 11:59:17 -0300
Subject: [PATCH 21/70] drm/i915: add "enable" argument to
 intel_update_sprite_watermarks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Because we want to call it from the "sprite disable" paths, since on
Haswell we need to update the sprite watermarks when we disable
sprites.

For now, all this patch does is to add the "enable" argument and call
intel_update_sprite_watermarks from inside ivb_disable_plane. This
shouldn't change how the code behaves because on
sandybridge_update_sprite_wm we just ignore the "!enable" case. The
patches that implement Haswell watermarks will make use of the changes
introduced by this patch.

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_drv.h     |  3 ++-
 drivers/gpu/drm/i915/intel_drv.h    |  2 +-
 drivers/gpu/drm/i915/intel_pm.c     | 11 ++++++++---
 drivers/gpu/drm/i915/intel_sprite.c |  8 +++++---
 4 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f6419f40df38..e09c54c73a22 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -315,7 +315,8 @@ struct drm_i915_display_funcs {
 	int (*get_fifo_size)(struct drm_device *dev, int plane);
 	void (*update_wm)(struct drm_device *dev);
 	void (*update_sprite_wm)(struct drm_device *dev, int pipe,
-				 uint32_t sprite_width, int pixel_size);
+				 uint32_t sprite_width, int pixel_size,
+				 bool enable);
 	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 83b4fe4b7be0..3e6e5e7b089f 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -731,7 +731,7 @@ extern void intel_ddi_init(struct drm_device *dev, enum port port);
 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);
+					   int pixel_size, bool enable);
 
 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 fa4c818d4b00..3515efd049dd 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2195,7 +2195,8 @@ 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)
+					 uint32_t sprite_width, int pixel_size,
+					 bool enable)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int latency = SNB_READ_WM0_LATENCY() * 100;	/* In unit 0.1us */
@@ -2203,6 +2204,9 @@ static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
 	int sprite_wm, reg;
 	int ret;
 
+	if (!enable)
+		return;
+
 	switch (pipe) {
 	case 0:
 		reg = WM0_PIPEA_ILK;
@@ -2314,13 +2318,14 @@ 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)
+				    uint32_t sprite_width, int pixel_size,
+				    bool enable)
 {
 	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);
+						   pixel_size, enable);
 }
 
 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 19b9cb961b5a..04d38d4d811a 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -114,7 +114,7 @@ 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);
+	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true);
 
 	I915_WRITE(SPSTRIDE(pipe, plane), fb->pitches[0]);
 	I915_WRITE(SPPOS(pipe, plane), (crtc_y << 16) | crtc_x);
@@ -268,7 +268,7 @@ 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);
+	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true);
 
 	/*
 	 * IVB workaround: must disable low power watermarks for at least
@@ -335,6 +335,8 @@ ivb_disable_plane(struct drm_plane *plane)
 
 	dev_priv->sprite_scaling_enabled &= ~(1 << pipe);
 
+	intel_update_sprite_watermarks(dev, pipe, 0, 0, false);
+
 	/* potentially re-enable LP watermarks */
 	if (scaling_was_enabled && !dev_priv->sprite_scaling_enabled)
 		intel_update_watermarks(dev);
@@ -453,7 +455,7 @@ 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);
+	intel_update_sprite_watermarks(dev, pipe, crtc_w, pixel_size, true);
 
 	dvsscale = 0;
 	if (IS_GEN5(dev) || crtc_w != src_w || crtc_h != src_h)

From 526682e9fabf22e82a02383e8f864a7330b73b25 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 24 May 2013 11:59:18 -0300
Subject: [PATCH 22/70] drm/i915: add haswell_update_sprite_wm
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On Haswell, whenever we change the sprites we need to completely
recalculate all the watermarks, because the sprites are one of the
parameters to the LP watermarks, so a change on the sprites may
trigger a change on which LP levels are enabled.

So on this commit we store all the parameters we need to store for
proper recalculation of the Haswell WMs and then call
haswell_update_wm.

Notice that for now our haswell_update_wm function is not really using
these parameters we're storing, but on the next commits we'll use
these parameters.

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@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_drv.h | 12 ++++++++++++
 drivers/gpu/drm/i915/intel_pm.c  | 23 ++++++++++++++++++++++-
 2 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 3e6e5e7b089f..bb4c50b57085 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -326,6 +326,18 @@ struct intel_plane {
 	unsigned int crtc_w, crtc_h;
 	uint32_t src_x, src_y;
 	uint32_t src_w, src_h;
+
+	/* Since we need to change the watermarks before/after
+	 * enabling/disabling the planes, we need to store the parameters here
+	 * 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 enable;
+		uint8_t bytes_per_pixel;
+		uint32_t horiz_pixels;
+	} wm;
+
 	void (*update_plane)(struct drm_plane *plane,
 			     struct drm_framebuffer *fb,
 			     struct drm_i915_gem_object *obj,
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 3515efd049dd..9328ed98ce2f 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2118,6 +2118,26 @@ static void haswell_update_wm(struct drm_device *dev)
 	sandybridge_update_wm(dev);
 }
 
+static void haswell_update_sprite_wm(struct drm_device *dev, int pipe,
+				     uint32_t sprite_width, int pixel_size,
+				     bool enable)
+{
+	struct drm_plane *plane;
+
+	list_for_each_entry(plane, &dev->mode_config.plane_list, head) {
+		struct intel_plane *intel_plane = to_intel_plane(plane);
+
+		if (intel_plane->pipe == pipe) {
+			intel_plane->wm.enable = enable;
+			intel_plane->wm.horiz_pixels = sprite_width + 1;
+			intel_plane->wm.bytes_per_pixel = pixel_size;
+			break;
+		}
+	}
+
+	haswell_update_wm(dev);
+}
+
 static bool
 sandybridge_compute_sprite_wm(struct drm_device *dev, int plane,
 			      uint32_t sprite_width, int pixel_size,
@@ -4631,7 +4651,8 @@ void intel_init_pm(struct drm_device *dev)
 		} else if (IS_HASWELL(dev)) {
 			if (I915_READ64(MCH_SSKPD)) {
 				dev_priv->display.update_wm = haswell_update_wm;
-				dev_priv->display.update_sprite_wm = sandybridge_update_sprite_wm;
+				dev_priv->display.update_sprite_wm =
+					haswell_update_sprite_wm;
 			} else {
 				DRM_DEBUG_KMS("Failed to read display plane latency. "
 					      "Disable CxSR\n");

From 79ee20dc85072b0edfb5e461799d192a9cc9d422 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Mon, 13 May 2013 16:32:09 +0300
Subject: [PATCH 23/70] drm/i915: pass seqno to i915_hangcheck_ring_idle

In preparation for next commit, pass seqno as a parameter
to i915_hangcheck_ring_idle as it will be used inside
i915_hangcheck_elapsed.

Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_irq.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 879c4ccb00db..0e5c9b0cc5a6 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2274,11 +2274,11 @@ ring_last_seqno(struct intel_ring_buffer *ring)
 			  struct drm_i915_gem_request, list)->seqno;
 }
 
-static bool i915_hangcheck_ring_idle(struct intel_ring_buffer *ring, bool *err)
+static bool i915_hangcheck_ring_idle(struct intel_ring_buffer *ring,
+				     u32 ring_seqno, bool *err)
 {
 	if (list_empty(&ring->request_list) ||
-	    i915_seqno_passed(ring->get_seqno(ring, false),
-			      ring_last_seqno(ring))) {
+	    i915_seqno_passed(ring_seqno, ring_last_seqno(ring))) {
 		/* Issue a wake-up to catch stuck h/w. */
 		if (waitqueue_active(&ring->irq_queue)) {
 			DRM_ERROR("Hangcheck timer elapsed... %s idle\n",
@@ -2395,7 +2395,10 @@ void i915_hangcheck_elapsed(unsigned long data)
 	memset(acthd, 0, sizeof(acthd));
 	idle = true;
 	for_each_ring(ring, dev_priv, i) {
-	    idle &= i915_hangcheck_ring_idle(ring, &err);
+		u32 seqno;
+
+		seqno = ring->get_seqno(ring, false);
+		idle &= i915_hangcheck_ring_idle(ring, seqno, &err);
 	    acthd[i] = intel_ring_get_active_head(ring);
 	}
 

From 92cab7345131db7af18f630a799ce6b2e8e624c5 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Fri, 24 May 2013 17:16:07 +0300
Subject: [PATCH 24/70] drm/i915: track ring progression using seqnos

Instead of relying in acthd, track ring seqno progression
to detect if ring has hung.

v2: put hangcheck stuff inside struct (Chris Wilson)

v3: initialize hangcheck.seqno (Ben Widawsky)

Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_drv.h         |  2 --
 drivers/gpu/drm/i915/i915_irq.c         | 30 +++++++++++--------------
 drivers/gpu/drm/i915/intel_ringbuffer.c |  1 +
 drivers/gpu/drm/i915/intel_ringbuffer.h |  6 +++++
 4 files changed, 20 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e09c54c73a22..e417049ea581 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -842,8 +842,6 @@ struct i915_gpu_error {
 #define DRM_I915_HANGCHECK_JIFFIES msecs_to_jiffies(DRM_I915_HANGCHECK_PERIOD)
 	struct timer_list hangcheck_timer;
 	int hangcheck_count;
-	uint32_t last_acthd[I915_NUM_RINGS];
-	uint32_t prev_instdone[I915_NUM_INSTDONE_REG];
 
 	/* For reset and error_state handling. */
 	spinlock_t lock;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 0e5c9b0cc5a6..004ad3455992 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2384,22 +2384,19 @@ void i915_hangcheck_elapsed(unsigned long data)
 {
 	struct drm_device *dev = (struct drm_device *)data;
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	uint32_t acthd[I915_NUM_RINGS], instdone[I915_NUM_INSTDONE_REG];
 	struct intel_ring_buffer *ring;
 	bool err = false, idle;
 	int i;
+	u32 seqno[I915_NUM_RINGS];
+	bool work_done;
 
 	if (!i915_enable_hangcheck)
 		return;
 
-	memset(acthd, 0, sizeof(acthd));
 	idle = true;
 	for_each_ring(ring, dev_priv, i) {
-		u32 seqno;
-
-		seqno = ring->get_seqno(ring, false);
-		idle &= i915_hangcheck_ring_idle(ring, seqno, &err);
-	    acthd[i] = intel_ring_get_active_head(ring);
+		seqno[i] = ring->get_seqno(ring, false);
+		idle &= i915_hangcheck_ring_idle(ring, seqno[i], &err);
 	}
 
 	/* If all work is done then ACTHD clearly hasn't advanced. */
@@ -2415,20 +2412,19 @@ void i915_hangcheck_elapsed(unsigned long data)
 		return;
 	}
 
-	i915_get_extra_instdone(dev, instdone);
-	if (memcmp(dev_priv->gpu_error.last_acthd, acthd,
-		   sizeof(acthd)) == 0 &&
-	    memcmp(dev_priv->gpu_error.prev_instdone, instdone,
-		   sizeof(instdone)) == 0) {
+	work_done = false;
+	for_each_ring(ring, dev_priv, i) {
+		if (ring->hangcheck.seqno != seqno[i]) {
+			work_done = true;
+			ring->hangcheck.seqno = seqno[i];
+		}
+	}
+
+	if (!work_done) {
 		if (i915_hangcheck_hung(dev))
 			return;
 	} else {
 		dev_priv->gpu_error.hangcheck_count = 0;
-
-		memcpy(dev_priv->gpu_error.last_acthd, acthd,
-		       sizeof(acthd));
-		memcpy(dev_priv->gpu_error.prev_instdone, instdone,
-		       sizeof(instdone));
 	}
 
 repeat:
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 3d2c236e15ab..5698faeee6f6 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1502,6 +1502,7 @@ void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno)
 	}
 
 	ring->set_seqno(ring, seqno);
+	ring->hangcheck.seqno = seqno;
 }
 
 void intel_ring_advance(struct intel_ring_buffer *ring)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index dac1614a1bca..ef374a892105 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -37,6 +37,10 @@ struct  intel_hw_status_page {
 #define I915_READ_SYNC_0(ring) I915_READ(RING_SYNC_0((ring)->mmio_base))
 #define I915_READ_SYNC_1(ring) I915_READ(RING_SYNC_1((ring)->mmio_base))
 
+struct intel_ring_hangcheck {
+	u32 seqno;
+};
+
 struct  intel_ring_buffer {
 	const char	*name;
 	enum intel_ring_id {
@@ -137,6 +141,8 @@ struct  intel_ring_buffer {
 	struct i915_hw_context *default_context;
 	struct i915_hw_context *last_context;
 
+	struct intel_ring_hangcheck hangcheck;
+
 	void *private;
 };
 

From ed5cbb0355779dc5516b2f7b62cedce185b00439 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Mon, 13 May 2013 16:32:11 +0300
Subject: [PATCH 25/70] drm/i915: introduce i915_hangcheck_ring_hung

In preparation to track per ring progress in hangcheck,
add i915_hangcheck_ring_hung.

v2: omit dev parameter (Ben Widawsky)

Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_irq.c | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 004ad3455992..6efe3b0d3e84 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2345,28 +2345,33 @@ static bool kick_ring(struct intel_ring_buffer *ring)
 	return false;
 }
 
+static bool i915_hangcheck_ring_hung(struct intel_ring_buffer *ring)
+{
+	if (IS_GEN2(ring->dev))
+		return false;
+
+	/* Is the chip hanging on a WAIT_FOR_EVENT?
+	 * If so we can simply poke the RB_WAIT bit
+	 * and break the hang. This should work on
+	 * all but the second generation chipsets.
+	 */
+	return !kick_ring(ring);
+}
+
 static bool i915_hangcheck_hung(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 
 	if (dev_priv->gpu_error.hangcheck_count++ > 1) {
 		bool hung = true;
+		struct intel_ring_buffer *ring;
+		int i;
 
 		DRM_ERROR("Hangcheck timer elapsed... GPU hung\n");
 		i915_handle_error(dev, true);
 
-		if (!IS_GEN2(dev)) {
-			struct intel_ring_buffer *ring;
-			int i;
-
-			/* Is the chip hanging on a WAIT_FOR_EVENT?
-			 * If so we can simply poke the RB_WAIT bit
-			 * and break the hang. This should work on
-			 * all but the second generation chipsets.
-			 */
-			for_each_ring(ring, dev_priv, i)
-				hung &= !kick_ring(ring);
-		}
+		for_each_ring(ring, dev_priv, i)
+			hung &= i915_hangcheck_ring_hung(ring);
 
 		return hung;
 	}

From 7ed73da0eac4e2e06c06e8baf518e124fc1f6a17 Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Sat, 25 May 2013 14:42:54 -0700
Subject: [PATCH 26/70] drm/i915: Fix error state memory leaks

Found with kmemleak.

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_irq.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 6efe3b0d3e84..4df2b3fa4ebd 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1564,11 +1564,13 @@ i915_error_state_free(struct kref *error_ref)
 	for (i = 0; i < ARRAY_SIZE(error->ring); i++) {
 		i915_error_object_free(error->ring[i].batchbuffer);
 		i915_error_object_free(error->ring[i].ringbuffer);
+		i915_error_object_free(error->ring[i].ctx);
 		kfree(error->ring[i].requests);
 	}
 
 	kfree(error->active_bo);
 	kfree(error->overlay);
+	kfree(error->display);
 	kfree(error);
 }
 static void capture_bo(struct drm_i915_error_buffer *err,

From 0a9ae0d7f8249da5906c8cac7d56768975c38de4 Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Sat, 25 May 2013 12:26:35 -0700
Subject: [PATCH 27/70] drm/i915: pre-fixes for checkpatch

Since I'll need to modify i915_gem_object_bind_to_gtt(), fix the errors
now to get checkpatch to not complain.

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Resolve conflict with Chris' improved debug output, and
bikeshed the new variable with s/max/gtt_max/ a bit while at it.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_gem.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 1b735a4a2873..9496fb5f2fe1 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2968,6 +2968,8 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 	struct drm_mm_node *node;
 	u32 size, fence_size, fence_alignment, unfenced_alignment;
 	bool mappable, fenceable;
+	size_t gtt_max = map_and_fenceable ?
+		dev_priv->gtt.mappable_end : dev_priv->gtt.total;
 	int ret;
 
 	fence_size = i915_gem_get_gtt_size(dev,
@@ -2994,12 +2996,11 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 	/* If the object is bigger than the entire aperture, reject it early
 	 * before evicting everything in a vain attempt to find space.
 	 */
-	if (obj->base.size >
-	    (map_and_fenceable ? dev_priv->gtt.mappable_end : dev_priv->gtt.total)) {
+	if (obj->base.size > gtt_max) {
 		DRM_ERROR("Attempting to bind an object larger than the aperture: object=%zd > %s aperture=%ld\n",
 			  obj->base.size,
 			  map_and_fenceable ? "mappable" : "total",
-			  map_and_fenceable ? dev_priv->gtt.mappable_end : dev_priv->gtt.total);
+			  gtt_max);
 		return -E2BIG;
 	}
 
@@ -3015,14 +3016,10 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 		return -ENOMEM;
 	}
 
- search_free:
-	if (map_and_fenceable)
-		ret = drm_mm_insert_node_in_range_generic(&dev_priv->mm.gtt_space, node,
-							  size, alignment, obj->cache_level,
-							  0, dev_priv->gtt.mappable_end);
-	else
-		ret = drm_mm_insert_node_generic(&dev_priv->mm.gtt_space, node,
-						 size, alignment, obj->cache_level);
+search_free:
+	ret = drm_mm_insert_node_in_range_generic(&dev_priv->mm.gtt_space, node,
+						  size, alignment,
+						  obj->cache_level, 0, gtt_max);
 	if (ret) {
 		ret = i915_gem_evict_something(dev, size, alignment,
 					       obj->cache_level,

From f64e29227d80cc15c37c7dbf7030ffc8c415cbd4 Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Sat, 25 May 2013 12:26:36 -0700
Subject: [PATCH 28/70] drm/i915: use mappable size for fb kickout

The GTT start is either 0 in the KMS case, or some value which is set
only after the init IOCTL in the UMS case. In both cases, we don't have
this information until after we've tried to kick out the firmware fb.

This patch should have no functional change since we kzalloc the GTT
struct anyway. It only clarifies the situation for people who end up
having to look at that code.

This weirdness was introduced in:

commit 93d187993b783c68383a884091a600d9ad499ea6
Author: Ben Widawsky <ben@bwidawsk.net>
Date:   Thu Jan 17 12:45:17 2013 -0800

    drm/i915: Remove use of gtt_mappable_entries

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_dma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index f5addac7c154..3cda7521e8d7 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1431,7 +1431,7 @@ static void i915_kick_out_firmware_fb(struct drm_i915_private *dev_priv)
 		return;
 
 	ap->ranges[0].base = dev_priv->gtt.mappable_base;
-	ap->ranges[0].size = dev_priv->gtt.mappable_end - dev_priv->gtt.start;
+	ap->ranges[0].size = dev_priv->gtt.mappable_end;
 
 	primary =
 		pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW;

From dd62eabd1d54336a2d5d3758ab4393cd13254102 Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Sat, 25 May 2013 12:26:37 -0700
Subject: [PATCH 29/70] drm/i915: use drm_mm_takedown

I noticed this while doing the VMA abstraction. AFAICT, it won't
actually fix anything, but it is the correct thing to do.

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_dma.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 3cda7521e8d7..45283679ac87 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1361,6 +1361,7 @@ cleanup_gem:
 	i915_gem_cleanup_ringbuffer(dev);
 	mutex_unlock(&dev->struct_mutex);
 	i915_gem_cleanup_aliasing_ppgtt(dev);
+	drm_mm_takedown(&dev_priv->mm.gtt_space);
 cleanup_irq:
 	drm_irq_uninstall(dev);
 cleanup_gem_stolen:
@@ -1778,6 +1779,7 @@ int i915_driver_unload(struct drm_device *dev)
 			i915_free_hws(dev);
 	}
 
+	drm_mm_takedown(&dev_priv->mm.gtt_space);
 	if (dev_priv->regs != NULL)
 		pci_iounmap(dev->pdev, dev_priv->regs);
 

From bb0364130fb0d272c838149b2ffe698a6c7afbfc Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Sat, 25 May 2013 12:26:38 -0700
Subject: [PATCH 30/70] drm/i915: context debug messages

Add some debug messages to help figure out what goes wrong on context
initialization.

Later in the PPGTT series, I ended up having a lot of failures after
reset. In many cases it was extra difficult to debug because I hadn't
even realized that contexts failed to reinitialize after reset (again an
artifact of some later patches).

This fairly benign patch does help debug some potential issues which
arise later.

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_gem_context.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 64cb1909a0ce..39bcc087db96 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -156,7 +156,8 @@ create_hw_context(struct drm_device *dev,
 	if (INTEL_INFO(dev)->gen >= 7) {
 		ret = i915_gem_object_set_cache_level(ctx->obj,
 						      I915_CACHE_LLC_MLC);
-		if (ret)
+		/* Failure shouldn't ever happen this early */
+		if (WARN_ON(ret))
 			goto err_out;
 	}
 
@@ -214,12 +215,16 @@ static int create_default_context(struct drm_i915_private *dev_priv)
 	 */
 	dev_priv->ring[RCS].default_context = ctx;
 	ret = i915_gem_object_pin(ctx->obj, CONTEXT_ALIGN, false, false);
-	if (ret)
+	if (ret) {
+		DRM_DEBUG_DRIVER("Couldn't pin %d\n", ret);
 		goto err_destroy;
+	}
 
 	ret = do_switch(ctx);
-	if (ret)
+	if (ret) {
+		DRM_DEBUG_DRIVER("Switch failed %d\n", ret);
 		goto err_unpin;
+	}
 
 	DRM_DEBUG_DRIVER("Default HW context loaded\n");
 	return 0;
@@ -237,6 +242,7 @@ void i915_gem_context_init(struct drm_device *dev)
 
 	if (!HAS_HW_CONTEXTS(dev)) {
 		dev_priv->hw_contexts_disabled = true;
+		DRM_DEBUG_DRIVER("Disabling HW Contexts; old hardware\n");
 		return;
 	}
 
@@ -249,11 +255,13 @@ void i915_gem_context_init(struct drm_device *dev)
 
 	if (dev_priv->hw_context_size > (1<<20)) {
 		dev_priv->hw_contexts_disabled = true;
+		DRM_DEBUG_DRIVER("Disabling HW Contexts; invalid size\n");
 		return;
 	}
 
 	if (create_default_context(dev_priv)) {
 		dev_priv->hw_contexts_disabled = true;
+		DRM_DEBUG_DRIVER("Disabling HW Contexts; create failed\n");
 		return;
 	}
 

From 55d23285745b1be7bd25a2a4ba5ba79e05ab843a Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Sat, 25 May 2013 12:26:39 -0700
Subject: [PATCH 31/70] drm/i915: Call context fini at cleanup

If contexts were actually initialized, and we fail somewhere later during
init this would possibly leak memory, and lead to some error messages
about unclean takedown. As the odds of this occurring, and someone
actually caring/noticing are pretty slim, the patch isn't terribly
important.

Found by code inspection while working on something else.

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_dma.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 45283679ac87..bd56c5560fa0 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1359,6 +1359,7 @@ static int i915_load_modeset_init(struct drm_device *dev)
 cleanup_gem:
 	mutex_lock(&dev->struct_mutex);
 	i915_gem_cleanup_ringbuffer(dev);
+	i915_gem_context_fini(dev);
 	mutex_unlock(&dev->struct_mutex);
 	i915_gem_cleanup_aliasing_ppgtt(dev);
 	drm_mm_takedown(&dev_priv->mm.gtt_space);

From 6640aab6f2aed89470bc44c7450b7573659e651e Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Wed, 22 May 2013 17:47:13 +0300
Subject: [PATCH 32/70] drm/i915: release scratch page at module unload

Signed-off-by: Imre Deak <imre.deak@intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_dma.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index bd56c5560fa0..3cd2b606aaba 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1790,6 +1790,8 @@ int i915_driver_unload(struct drm_device *dev)
 	destroy_workqueue(dev_priv->wq);
 	pm_qos_remove_request(&dev_priv->pm_qos);
 
+	dev_priv->gtt.gtt_remove(dev);
+
 	if (dev_priv->slab)
 		kmem_cache_destroy(dev_priv->slab);
 

From 982a38667dd9f175f8dd8a78651426ae6baac463 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Thu, 23 May 2013 19:39:40 +0300
Subject: [PATCH 33/70] drm/i915: stop using is_cpu_edp() in
 intel_disable/post_disable_dp

Based on 3739850b46f - "drm/i915: disable the cpu edp port after the
cpu pipe" and the bspec disabling sequence for IVB and older it seems we
have to distinguish only the CPU vs. PCH port case, whether it's a DP or
eDP doesn't seem to matter. For IVB and older on the CPU side we can
only have eDP on port A, DP ports can only be on the PCH side. On VLV we
have only CPU side eDP/DP ports, no PCH. So the condition for the
disabling sequence we need for CPU ports is port == A || IS_VLV.

This allows us to remove is_cpu_edp() completely in a later patch.

v2:
- simplify (and fix) the condition for CPU side ports and adjust the
  commit message accordingly (Daniel)

Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_dp.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index cdb1c2a6d2b2..ee157091f92e 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1372,6 +1372,8 @@ static void intel_dp_get_config(struct intel_encoder *encoder,
 static void intel_disable_dp(struct intel_encoder *encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	enum port port = dp_to_dig_port(intel_dp)->port;
+	struct drm_device *dev = encoder->base.dev;
 
 	/* Make sure the panel is off before trying to change the mode. But also
 	 * ensure that we have vdd while we switch off the panel. */
@@ -1381,16 +1383,17 @@ static void intel_disable_dp(struct intel_encoder *encoder)
 	ironlake_edp_panel_off(intel_dp);
 
 	/* cpu edp my only be disable _after_ the cpu pipe/plane is disabled. */
-	if (!is_cpu_edp(intel_dp))
+	if (!(port == PORT_A || IS_VALLEYVIEW(dev)))
 		intel_dp_link_down(intel_dp);
 }
 
 static void intel_post_disable_dp(struct intel_encoder *encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	enum port port = dp_to_dig_port(intel_dp)->port;
 	struct drm_device *dev = encoder->base.dev;
 
-	if (is_cpu_edp(intel_dp)) {
+	if (port == PORT_A || IS_VALLEYVIEW(dev)) {
 		intel_dp_link_down(intel_dp);
 		if (!IS_VALLEYVIEW(dev))
 			ironlake_edp_pll_off(intel_dp);

From a62d0834dee83994e41fcd0e5b7f10aad3d80de0 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Thu, 16 May 2013 14:40:35 +0300
Subject: [PATCH 34/70] drm/i915: merge VLV eDP and DP AUX clock divider
 calculation

On ValleyView for both eDP and DP the AUX input clock is 200MHz, so we
can calculate for both the clock divider for the 2MHz target rate at the
same place. Afterwards we can also replace the is_cpu_edp() check with a
check for port A.

Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_dp.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index ee157091f92e..320bd61ea2f2 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -317,12 +317,12 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 	 * Note that PCH attached eDP panels should use a 125MHz input
 	 * clock divider.
 	 */
-	if (is_cpu_edp(intel_dp)) {
+	if (IS_VALLEYVIEW(dev)) {
+		aux_clock_divider = 100;
+	} else if (intel_dig_port->port == PORT_A) {
 		if (HAS_DDI(dev))
 			aux_clock_divider = DIV_ROUND_CLOSEST(
 				intel_ddi_get_cdclk_freq(dev_priv), 2000);
-		else if (IS_VALLEYVIEW(dev))
-			aux_clock_divider = 100;
 		else if (IS_GEN6(dev) || IS_GEN7(dev))
 			aux_clock_divider = 200; /* SNB & IVB eDP input clock at 400Mhz */
 		else

From bc7d38a43ab1af4cad1c235c3aa30426b6c7d6c5 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Thu, 16 May 2013 14:40:36 +0300
Subject: [PATCH 35/70] drm/i915: replace is_cpu_edp() with a check for port A

The patch changes all remaining is_cpu_edp() check with a check for port
A. We can do this, since in all these cases ValleyView is handled
separately and port A is always a CPU side eDP port.

Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_dp.c | 49 ++++++++++++++++++---------------
 1 file changed, 27 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 320bd61ea2f2..91918f99611e 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -685,6 +685,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_display_mode *adjusted_mode = &pipe_config->adjusted_mode;
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	enum port port = dp_to_dig_port(intel_dp)->port;
 	struct intel_crtc *intel_crtc = encoder->new_crtc;
 	struct intel_connector *intel_connector = intel_dp->attached_connector;
 	int lane_count, clock;
@@ -694,7 +695,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	static int bws[2] = { DP_LINK_BW_1_62, DP_LINK_BW_2_7 };
 	int target_clock, link_avail, link_clock;
 
-	if (HAS_PCH_SPLIT(dev) && !HAS_DDI(dev) && !is_cpu_edp(intel_dp))
+	if (HAS_PCH_SPLIT(dev) && !HAS_DDI(dev) && port != PORT_A)
 		pipe_config->has_pch_encoder = true;
 
 	pipe_config->has_dp_encoder = true;
@@ -828,6 +829,7 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	enum port port = dp_to_dig_port(intel_dp)->port;
 	struct drm_crtc *crtc = encoder->crtc;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
@@ -868,7 +870,7 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 
 	/* Split out the IBX/CPU vs CPT settings */
 
-	if (is_cpu_edp(intel_dp) && IS_GEN7(dev) && !IS_VALLEYVIEW(dev)) {
+	if (port == PORT_A && IS_GEN7(dev) && !IS_VALLEYVIEW(dev)) {
 		if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
 			intel_dp->DP |= DP_SYNC_HS_HIGH;
 		if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
@@ -885,7 +887,7 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 			intel_dp->DP |= DP_PLL_FREQ_160MHZ;
 		else
 			intel_dp->DP |= DP_PLL_FREQ_270MHZ;
-	} else if (!HAS_PCH_CPT(dev) || is_cpu_edp(intel_dp)) {
+	} else if (!HAS_PCH_CPT(dev) || port == PORT_A) {
 		if (!HAS_PCH_SPLIT(dev) && !IS_VALLEYVIEW(dev))
 			intel_dp->DP |= intel_dp->color_range;
 
@@ -901,7 +903,7 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 		if (intel_crtc->pipe == 1)
 			intel_dp->DP |= DP_PIPEB_SELECT;
 
-		if (is_cpu_edp(intel_dp) && !IS_VALLEYVIEW(dev)) {
+		if (port == PORT_A && !IS_VALLEYVIEW(dev)) {
 			/* don't miss out required setting for eDP */
 			if (adjusted_mode->clock < 200000)
 				intel_dp->DP |= DP_PLL_FREQ_160MHZ;
@@ -912,7 +914,7 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 		intel_dp->DP |= DP_LINK_TRAIN_OFF_CPT;
 	}
 
-	if (is_cpu_edp(intel_dp) && !IS_VALLEYVIEW(dev))
+	if (port == PORT_A && !IS_VALLEYVIEW(dev))
 		ironlake_set_pll_edp(crtc, adjusted_mode->clock);
 }
 
@@ -1302,6 +1304,7 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 				  enum pipe *pipe)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	enum port port = dp_to_dig_port(intel_dp)->port;
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 tmp = I915_READ(intel_dp->output_reg);
@@ -1309,9 +1312,9 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 	if (!(tmp & DP_PORT_EN))
 		return false;
 
-	if (is_cpu_edp(intel_dp) && IS_GEN7(dev) && !IS_VALLEYVIEW(dev)) {
+	if (port == PORT_A && IS_GEN7(dev) && !IS_VALLEYVIEW(dev)) {
 		*pipe = PORT_TO_PIPE_CPT(tmp);
-	} else if (!HAS_PCH_CPT(dev) || is_cpu_edp(intel_dp)) {
+	} else if (!HAS_PCH_CPT(dev) || port == PORT_A) {
 		*pipe = PORT_TO_PIPE(tmp);
 	} else {
 		u32 trans_sel;
@@ -1431,14 +1434,14 @@ static void intel_enable_dp(struct intel_encoder *encoder)
 static void intel_pre_enable_dp(struct intel_encoder *encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (is_cpu_edp(intel_dp) && !IS_VALLEYVIEW(dev))
+	if (dport->port == PORT_A && !IS_VALLEYVIEW(dev))
 		ironlake_edp_pll_on(intel_dp);
 
 	if (IS_VALLEYVIEW(dev)) {
-		struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
 		struct intel_crtc *intel_crtc =
 			to_intel_crtc(encoder->base.crtc);
 		int port = vlv_dport_to_channel(dport);
@@ -1546,12 +1549,13 @@ static uint8_t
 intel_dp_voltage_max(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	enum port port = dp_to_dig_port(intel_dp)->port;
 
 	if (IS_VALLEYVIEW(dev))
 		return DP_TRAIN_VOLTAGE_SWING_1200;
-	else if (IS_GEN7(dev) && is_cpu_edp(intel_dp))
+	else if (IS_GEN7(dev) && port == PORT_A)
 		return DP_TRAIN_VOLTAGE_SWING_800;
-	else if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
+	else if (HAS_PCH_CPT(dev) && port != PORT_A)
 		return DP_TRAIN_VOLTAGE_SWING_1200;
 	else
 		return DP_TRAIN_VOLTAGE_SWING_800;
@@ -1561,6 +1565,7 @@ static uint8_t
 intel_dp_pre_emphasis_max(struct intel_dp *intel_dp, uint8_t voltage_swing)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	enum port port = dp_to_dig_port(intel_dp)->port;
 
 	if (HAS_DDI(dev)) {
 		switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
@@ -1586,7 +1591,7 @@ intel_dp_pre_emphasis_max(struct intel_dp *intel_dp, uint8_t voltage_swing)
 		default:
 			return DP_TRAIN_PRE_EMPHASIS_0;
 		}
-	} else if (IS_GEN7(dev) && is_cpu_edp(intel_dp)) {
+	} else if (IS_GEN7(dev) && port == PORT_A) {
 		switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
 		case DP_TRAIN_VOLTAGE_SWING_400:
 			return DP_TRAIN_PRE_EMPHASIS_6;
@@ -1873,6 +1878,7 @@ static void
 intel_dp_set_signal_levels(struct intel_dp *intel_dp, uint32_t *DP)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	enum port port = intel_dig_port->port;
 	struct drm_device *dev = intel_dig_port->base.base.dev;
 	uint32_t signal_levels, mask;
 	uint8_t train_set = intel_dp->train_set[0];
@@ -1883,10 +1889,10 @@ intel_dp_set_signal_levels(struct intel_dp *intel_dp, uint32_t *DP)
 	} else if (IS_VALLEYVIEW(dev)) {
 		signal_levels = intel_vlv_signal_levels(intel_dp);
 		mask = 0;
-	} else if (IS_GEN7(dev) && is_cpu_edp(intel_dp)) {
+	} else if (IS_GEN7(dev) && port == PORT_A) {
 		signal_levels = intel_gen7_edp_signal_levels(train_set);
 		mask = EDP_LINK_TRAIN_VOL_EMP_MASK_IVB;
-	} else if (IS_GEN6(dev) && is_cpu_edp(intel_dp)) {
+	} else if (IS_GEN6(dev) && port == PORT_A) {
 		signal_levels = intel_gen6_edp_signal_levels(train_set);
 		mask = EDP_LINK_TRAIN_VOL_EMP_MASK_SNB;
 	} else {
@@ -1936,8 +1942,7 @@ intel_dp_set_link_train(struct intel_dp *intel_dp,
 		}
 		I915_WRITE(DP_TP_CTL(port), temp);
 
-	} else if (HAS_PCH_CPT(dev) &&
-		   (IS_GEN7(dev) || !is_cpu_edp(intel_dp))) {
+	} else if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || port != PORT_A)) {
 		dp_reg_value &= ~DP_LINK_TRAIN_MASK_CPT;
 
 		switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
@@ -2188,6 +2193,7 @@ static void
 intel_dp_link_down(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	enum port port = intel_dig_port->port;
 	struct drm_device *dev = intel_dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc =
@@ -2217,7 +2223,7 @@ intel_dp_link_down(struct intel_dp *intel_dp)
 
 	DRM_DEBUG_KMS("\n");
 
-	if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp))) {
+	if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || port != PORT_A)) {
 		DP &= ~DP_LINK_TRAIN_MASK_CPT;
 		I915_WRITE(intel_dp->output_reg, DP | DP_LINK_TRAIN_PAT_IDLE_CPT);
 	} else {
@@ -2944,9 +2950,6 @@ intel_dp_init_panel_power_sequencer_registers(struct drm_device *dev,
 		pp_div_reg = PIPEA_PP_DIVISOR;
 	}
 
-	if (IS_VALLEYVIEW(dev))
-		port_sel = I915_READ(pp_on_reg) & 0xc0000000;
-
 	/* And finally store the new values in the power sequencer. */
 	pp_on = (seq->t1_t3 << PANEL_POWER_UP_DELAY_SHIFT) |
 		(seq->t8 << PANEL_LIGHT_ON_DELAY_SHIFT);
@@ -2960,8 +2963,10 @@ intel_dp_init_panel_power_sequencer_registers(struct drm_device *dev,
 
 	/* Haswell doesn't have any port selection bits for the panel
 	 * power sequencer any more. */
-	if (HAS_PCH_IBX(dev) || HAS_PCH_CPT(dev)) {
-		if (is_cpu_edp(intel_dp))
+	if (IS_VALLEYVIEW(dev)) {
+		port_sel = I915_READ(pp_on_reg) & 0xc0000000;
+	} else if (HAS_PCH_IBX(dev) || HAS_PCH_CPT(dev)) {
+		if (dp_to_dig_port(intel_dp)->port == PORT_A)
 			port_sel = PANEL_POWER_PORT_DP_A;
 		else
 			port_sel = PANEL_POWER_PORT_DP_D;

From 55aab33e898eb61d6187b18c2446e2cb1b06b910 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Thu, 16 May 2013 14:40:37 +0300
Subject: [PATCH 36/70] drm/i915: remove unused is_cpu_edp()

Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_dp.c | 16 ----------------
 1 file changed, 16 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 91918f99611e..a899f93cb0ee 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -59,22 +59,6 @@ static struct drm_device *intel_dp_to_dev(struct intel_dp *intel_dp)
 	return intel_dig_port->base.base.dev;
 }
 
-/**
- * is_cpu_edp - is the port on the CPU and attached to an eDP panel?
- * @intel_dp: DP struct
- *
- * Returns true if the given DP struct corresponds to a CPU eDP port.
- */
-static bool is_cpu_edp(struct intel_dp *intel_dp)
-{
-	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	enum port port = intel_dig_port->port;
-
-	return is_edp(intel_dp) &&
-		(port == PORT_A || (port == PORT_C && IS_VALLEYVIEW(dev)));
-}
-
 static struct intel_dp *intel_attached_dp(struct drm_connector *connector)
 {
 	return enc_to_intel_dp(&intel_attached_encoder(connector)->base);

From a01025afa89ccaf1b0521f5862cbfcc73f970481 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 22 May 2013 00:50:23 +0200
Subject: [PATCH 37/70] drm/i915: fixup i915_pipe_enabled check in i915_irq.c

Well, as well as we can without completely revamping the drm vblank
code. The issue are that
- The vblank code needs to work on both ums and kms.
- It deals always deals with pipes.
- It doesn't take any of the kms locks.

The last part is not really fixable without revamping the drm vblank
code, since the drm core <-> driver interactions is a veritable pile
of spaghettis. But the other pieces can be fixed by switching on the
MODESET driver flag and either checking the hw state directly (ums
case) or just querying our sw tracking (with broken locking, but
that's not worse than what we've had).

Note that this essentially reverts

commit 702e7a56af3780d8b3a717f698209bef44187bb0
Author: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date:   Tue Oct 23 18:29:59 2012 -0200

    drm/i915: convert PIPECONF to use transcoder instead of pipe

for the ums case, which will fix a NULL deref (since we really don't
have any crtcs set up).

But the real reason to do this is to drop our reliance on the
cpu_transcoder: By only checking intel_crtc->active we don't need to
make sure that the pipe_config (or at least the cpu_transcoder)
contain safe values even when the pipe is off.

Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: 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/i915_irq.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 4df2b3fa4ebd..557acd37c788 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -381,14 +381,16 @@ static int
 i915_pipe_enabled(struct drm_device *dev, int pipe)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
-	enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv,
-								      pipe);
 
-	if (!intel_display_power_enabled(dev,
-		POWER_DOMAIN_TRANSCODER(cpu_transcoder)))
-		return false;
+	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
+		/* Locking is horribly broken here, but whatever. */
+		struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
+		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
-	return I915_READ(PIPECONF(cpu_transcoder)) & PIPECONF_ENABLE;
+		return intel_crtc->active;
+	} else {
+		return I915_READ(PIPECONF(pipe)) & PIPECONF_ENABLE;
+	}
 }
 
 /* Called from drm generic code, passed a 'crtc', which

From eccb140bca6727f2ef849e8811d5fe4c9fbfd5dd Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 22 May 2013 00:50:22 +0200
Subject: [PATCH 38/70] drm/i915: hw state readout&check support for
 cpu_transcoder

This allows us to drop a bunch of ugly hacks and finally implement
what

commit cc464b2a17c59adedbdc02cc54341d630354edc3
Author: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date:   Fri Jan 25 16:59:16 2013 -0200

    drm/i915: set TRANSCODER_EDP even earlier

tried to achieve, but that was reverted again in

commit bba2181c49f1dddf8b592804a1b53cc1a3cf408a
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date:   Fri Mar 22 10:53:40 2013 +0100

    Revert "drm/i915: set TRANSCODER_EDP even earlier"

Now we should always have a consistent cpu_transcoder in the
pipe_config.

v2: Fix up the code as spotted by Paulo:
- read the register for real
- assign the right pipes
- break out if the hw state doesn't make sense

v3: Shut up gcc.

Cc: Paulo Zanoni <paulo.r.zanoni@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_ddi.c     |  4 ++
 drivers/gpu/drm/i915/intel_display.c | 90 ++++++++++------------------
 2 files changed, 37 insertions(+), 57 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 1fdd3b0b7040..9649df806079 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1291,9 +1291,13 @@ static bool intel_ddi_compute_config(struct intel_encoder *encoder,
 				     struct intel_crtc_config *pipe_config)
 {
 	int type = encoder->type;
+	int port = intel_ddi_get_encoder_port(encoder);
 
 	WARN(type == INTEL_OUTPUT_UNKNOWN, "compute_config() on unknown output!\n");
 
+	if (port == PORT_A)
+		pipe_config->cpu_transcoder = TRANSCODER_EDP;
+
 	if (type == INTEL_OUTPUT_HDMI)
 		return intel_hdmi_compute_config(encoder, pipe_config);
 	else
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 2a9d0671f8c3..cb2437d1e0ea 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3469,12 +3469,6 @@ static void ironlake_crtc_off(struct drm_crtc *crtc)
 
 static void haswell_crtc_off(struct drm_crtc *crtc)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-
-	/* Stop saying we're using TRANSCODER_EDP because some other CRTC might
-	 * start using it. */
-	intel_crtc->config.cpu_transcoder = (enum transcoder) intel_crtc->pipe;
-
 	intel_ddi_put_crtc_pll(crtc);
 }
 
@@ -4925,6 +4919,8 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t tmp;
 
+	pipe_config->cpu_transcoder = crtc->pipe;
+
 	tmp = I915_READ(PIPECONF(crtc->pipe));
 	if (!(tmp & PIPECONF_ENABLE))
 		return false;
@@ -5647,8 +5643,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc,
 	WARN(!(HAS_PCH_IBX(dev) || HAS_PCH_CPT(dev)),
 	     "Unexpected PCH type %d\n", INTEL_PCH_TYPE(dev));
 
-	intel_crtc->config.cpu_transcoder = pipe;
-
 	ok = ironlake_compute_clocks(crtc, adjusted_mode, &clock,
 				     &has_reduced_clock, &reduced_clock);
 	if (!ok) {
@@ -5784,6 +5778,8 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t tmp;
 
+	pipe_config->cpu_transcoder = crtc->pipe;
+
 	tmp = I915_READ(PIPECONF(crtc->pipe));
 	if (!(tmp & PIPECONF_ENABLE))
 		return false;
@@ -5860,11 +5856,6 @@ static int haswell_crtc_mode_set(struct drm_crtc *crtc,
 		num_connectors++;
 	}
 
-	if (is_cpu_edp)
-		intel_crtc->config.cpu_transcoder = TRANSCODER_EDP;
-	else
-		intel_crtc->config.cpu_transcoder = pipe;
-
 	/* We are not sure yet this won't happen. */
 	WARN(!HAS_PCH_LPT(dev), "Unexpected PCH type %d\n",
 	     INTEL_PCH_TYPE(dev));
@@ -5918,15 +5909,37 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	enum transcoder cpu_transcoder = crtc->config.cpu_transcoder;
 	enum intel_display_power_domain pfit_domain;
 	uint32_t tmp;
 
+	pipe_config->cpu_transcoder = crtc->pipe;
+	tmp = I915_READ(TRANS_DDI_FUNC_CTL(TRANSCODER_EDP));
+	if (tmp & TRANS_DDI_FUNC_ENABLE) {
+		enum pipe trans_edp_pipe;
+		switch (tmp & TRANS_DDI_EDP_INPUT_MASK) {
+		default:
+			WARN(1, "unknown pipe linked to edp transcoder\n");
+		case TRANS_DDI_EDP_INPUT_A_ONOFF:
+		case TRANS_DDI_EDP_INPUT_A_ON:
+			trans_edp_pipe = PIPE_A;
+			break;
+		case TRANS_DDI_EDP_INPUT_B_ONOFF:
+			trans_edp_pipe = PIPE_B;
+			break;
+		case TRANS_DDI_EDP_INPUT_C_ONOFF:
+			trans_edp_pipe = PIPE_C;
+			break;
+		}
+
+		if (trans_edp_pipe == crtc->pipe)
+			pipe_config->cpu_transcoder = TRANSCODER_EDP;
+	}
+
 	if (!intel_display_power_enabled(dev,
-			POWER_DOMAIN_TRANSCODER(cpu_transcoder)))
+			POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder)))
 		return false;
 
-	tmp = I915_READ(PIPECONF(cpu_transcoder));
+	tmp = I915_READ(PIPECONF(pipe_config->cpu_transcoder));
 	if (!(tmp & PIPECONF_ENABLE))
 		return false;
 
@@ -5935,7 +5948,7 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 	 * DDI E. So just check whether this pipe is wired to DDI E and whether
 	 * the PCH transcoder is on.
 	 */
-	tmp = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
+	tmp = I915_READ(TRANS_DDI_FUNC_CTL(pipe_config->cpu_transcoder));
 	if ((tmp & TRANS_DDI_PORT_MASK) == TRANS_DDI_SELECT_PORT(PORT_E) &&
 	    I915_READ(LPT_TRANSCONF) & TRANS_ENABLE) {
 		pipe_config->has_pch_encoder = true;
@@ -7690,6 +7703,7 @@ intel_modeset_pipe_config(struct drm_crtc *crtc,
 
 	drm_mode_copy(&pipe_config->adjusted_mode, mode);
 	drm_mode_copy(&pipe_config->requested_mode, mode);
+	pipe_config->cpu_transcoder = to_intel_crtc(crtc)->pipe;
 
 	plane_bpp = pipe_config_set_bpp(crtc, fb, pipe_config);
 	if (plane_bpp < 0)
@@ -7940,6 +7954,8 @@ intel_pipe_config_compare(struct drm_device *dev,
 		return false; \
 	}
 
+	PIPE_CONF_CHECK_I(cpu_transcoder);
+
 	PIPE_CONF_CHECK_I(has_pch_encoder);
 	PIPE_CONF_CHECK_I(fdi_lanes);
 	PIPE_CONF_CHECK_I(fdi_m_n.gmch_m);
@@ -8091,7 +8107,6 @@ intel_modeset_check_state(struct drm_device *dev)
 		     "crtc's computed enabled state doesn't match tracked enabled state "
 		     "(expected %i, found %i)\n", enabled, crtc->base.enabled);
 
-		pipe_config.cpu_transcoder = crtc->config.cpu_transcoder;
 		active = dev_priv->display.get_pipe_config(crtc,
 							   &pipe_config);
 		WARN(crtc->active != active,
@@ -8154,12 +8169,10 @@ static int __intel_set_mode(struct drm_crtc *crtc,
 	 * to set it here already despite that we pass it down the callchain.
 	 */
 	if (modeset_pipes) {
-		enum transcoder tmp = to_intel_crtc(crtc)->config.cpu_transcoder;
 		crtc->mode = *mode;
 		/* mode_set/enable/disable functions rely on a correct pipe
 		 * config. */
 		to_intel_crtc(crtc)->config = *pipe_config;
-		to_intel_crtc(crtc)->config.cpu_transcoder = tmp;
 	}
 
 	/* Only after disabling all output pipelines that will be changed can we
@@ -8570,7 +8583,6 @@ static void intel_crtc_init(struct drm_device *dev, int pipe)
 	/* Swap pipes & planes for FBC on pre-965 */
 	intel_crtc->pipe = pipe;
 	intel_crtc->plane = pipe;
-	intel_crtc->config.cpu_transcoder = pipe;
 	if (IS_MOBILE(dev) && IS_GEN3(dev)) {
 		DRM_DEBUG_KMS("swapping pipes & planes for FBC\n");
 		intel_crtc->plane = !pipe;
@@ -9436,50 +9448,14 @@ void intel_modeset_setup_hw_state(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum pipe pipe;
-	u32 tmp;
 	struct drm_plane *plane;
 	struct intel_crtc *crtc;
 	struct intel_encoder *encoder;
 	struct intel_connector *connector;
 
-	if (HAS_DDI(dev)) {
-		tmp = I915_READ(TRANS_DDI_FUNC_CTL(TRANSCODER_EDP));
-
-		if (tmp & TRANS_DDI_FUNC_ENABLE) {
-			switch (tmp & TRANS_DDI_EDP_INPUT_MASK) {
-			case TRANS_DDI_EDP_INPUT_A_ON:
-			case TRANS_DDI_EDP_INPUT_A_ONOFF:
-				pipe = PIPE_A;
-				break;
-			case TRANS_DDI_EDP_INPUT_B_ONOFF:
-				pipe = PIPE_B;
-				break;
-			case TRANS_DDI_EDP_INPUT_C_ONOFF:
-				pipe = PIPE_C;
-				break;
-			default:
-				/* A bogus value has been programmed, disable
-				 * the transcoder */
-				WARN(1, "Bogus eDP source %08x\n", tmp);
-				intel_ddi_disable_transcoder_func(dev_priv,
-						TRANSCODER_EDP);
-				goto setup_pipes;
-			}
-
-			crtc = to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
-			crtc->config.cpu_transcoder = TRANSCODER_EDP;
-
-			DRM_DEBUG_KMS("Pipe %c using transcoder EDP\n",
-				      pipe_name(pipe));
-		}
-	}
-
-setup_pipes:
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list,
 			    base.head) {
-		enum transcoder tmp = crtc->config.cpu_transcoder;
 		memset(&crtc->config, 0, sizeof(crtc->config));
-		crtc->config.cpu_transcoder = tmp;
 
 		crtc->active = dev_priv->display.get_pipe_config(crtc,
 								 &crtc->config);

From 6b1c087ba5789aceb25a2170b217055ce2476f67 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 28 May 2013 12:35:02 +0300
Subject: [PATCH 39/70] drm/i915: document why dvo/sdvo/crt need a special dpms
 function

In the cloned case, changing just one output but keeping the other, the
pipe state won't change and intel_crtc_update_dpms will be a nop, but we
still need to update the dpms state of the output being changed.

Only dvo, sdvo and crt are cloneable, so only those three have special
dpms functions.

Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_crt.c  | 4 +++-
 drivers/gpu/drm/i915/intel_dvo.c  | 3 +++
 drivers/gpu/drm/i915/intel_sdvo.c | 3 +++
 3 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 5e9f93e53255..3acec8c48166 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -149,7 +149,7 @@ static void intel_enable_crt(struct intel_encoder *encoder)
 	intel_crt_set_dpms(encoder, crt->connector->base.dpms);
 }
 
-
+/* Special dpms function to support cloning between dvo/sdvo/crt. */
 static void intel_crt_dpms(struct drm_connector *connector, int mode)
 {
 	struct drm_device *dev = connector->dev;
@@ -180,6 +180,8 @@ static void intel_crt_dpms(struct drm_connector *connector, int mode)
 	else
 		encoder->connectors_active = true;
 
+	/* We call connector dpms manually below in case pipe dpms doesn't
+	 * change due to cloning. */
 	if (mode < old_dpms) {
 		/* From off to on, enable the pipe first. */
 		intel_crtc_update_dpms(crtc);
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index 9e80d487b5cb..eb2020eb2b7e 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -180,6 +180,7 @@ static void intel_enable_dvo(struct intel_encoder *encoder)
 	intel_dvo->dev.dev_ops->dpms(&intel_dvo->dev, true);
 }
 
+/* Special dpms function to support cloning between dvo/sdvo/crt. */
 static void intel_dvo_dpms(struct drm_connector *connector, int mode)
 {
 	struct intel_dvo *intel_dvo = intel_attached_dvo(connector);
@@ -201,6 +202,8 @@ static void intel_dvo_dpms(struct drm_connector *connector, int mode)
 		return;
 	}
 
+	/* We call connector dpms manually below in case pipe dpms doesn't
+	 * change due to cloning. */
 	if (mode == DRM_MODE_DPMS_ON) {
 		intel_dvo->base.connectors_active = true;
 
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 4d4a3f0cadfb..7068195376ef 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1416,6 +1416,7 @@ static void intel_enable_sdvo(struct intel_encoder *encoder)
 	intel_sdvo_set_active_outputs(intel_sdvo, intel_sdvo->attached_output);
 }
 
+/* Special dpms function to support cloning between dvo/sdvo/crt. */
 static void intel_sdvo_dpms(struct drm_connector *connector, int mode)
 {
 	struct drm_crtc *crtc;
@@ -1437,6 +1438,8 @@ static void intel_sdvo_dpms(struct drm_connector *connector, int mode)
 		return;
 	}
 
+	/* We set active outputs manually below in case pipe dpms doesn't change
+	 * due to cloning. */
 	if (mode != DRM_MODE_DPMS_ON) {
 		intel_sdvo_set_active_outputs(intel_sdvo, 0);
 		if (0)

From 56b085a01befc7907d270e9acb349580015e7bad Mon Sep 17 00:00:00 2001
From: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Date: Tue, 28 May 2013 17:51:44 +0800
Subject: [PATCH 40/70] drm/i915: fix error return code in init_pipe_control()

Fix to return -ENOMEM in the kmap() error handling case
instead of 0, as done elsewhere in this function.

Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 5698faeee6f6..9b97cf66a5ae 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -464,9 +464,11 @@ init_pipe_control(struct intel_ring_buffer *ring)
 		goto err_unref;
 
 	pc->gtt_offset = obj->gtt_offset;
-	pc->cpu_page =  kmap(sg_page(obj->pages->sgl));
-	if (pc->cpu_page == NULL)
+	pc->cpu_page = kmap(sg_page(obj->pages->sgl));
+	if (pc->cpu_page == NULL) {
+		ret = -ENOMEM;
 		goto err_unpin;
+	}
 
 	DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08x\n",
 			 ring->name, pc->gtt_offset);

From c0b0341121f2e2b329e60986aee766e4d1d80fde Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue, 28 May 2013 12:05:54 +0200
Subject: [PATCH 41/70] drm/i915: add basic pipe config dump support

All this pipe config abstraction adds another layer of complexity, so
it's good to have better visibility into what's going on exactly.
Doesn't dump out everything yet, and some bits are a bit duplicated
but this should be a good start.

Note that at boot-up a lot of the fields are 0 even for enabled pipes,
this is simply because our hw state readout code doesn't support
everything.

v2: Remove a few more now redudant debug output lines.

v3: Review from Paulo
- use transcoder_name
- fix up format specifiers
- add missing ':' in debug output

Cc: Paulo Zanoni <przanoni@gmail.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_display.c | 74 +++++++++++++++++-----------
 1 file changed, 44 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index cb2437d1e0ea..21cbb3d0e1d8 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3523,19 +3523,13 @@ static void i9xx_pfit_enable(struct intel_crtc *crtc)
 	if (!crtc->config.gmch_pfit.control)
 		return;
 
+	/*
+	 * The panel fitter should only be adjusted whilst the pipe is disabled,
+	 * according to register description and PRM.
+	 */
 	WARN_ON(I915_READ(PFIT_CONTROL) & PFIT_ENABLE);
 	assert_pipe_disabled(dev_priv, crtc->pipe);
 
-	/*
-	 * Enable automatic panel scaling so that non-native modes
-	 * fill the screen.  The panel fitter should only be
-	 * adjusted whilst the pipe is disabled, according to
-	 * register description and PRM.
-	 */
-	DRM_DEBUG_KMS("applying panel-fitter: %x, %x\n",
-		      pipe_config->gmch_pfit.control,
-		      pipe_config->gmch_pfit.pgm_ratios);
-
 	I915_WRITE(PFIT_PGM_RATIOS, pipe_config->gmch_pfit.pgm_ratios);
 	I915_WRITE(PFIT_CONTROL, pipe_config->gmch_pfit.control);
 
@@ -4857,9 +4851,6 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc,
 			dspcntr |= DISPPLANE_SEL_PIPE_B;
 	}
 
-	DRM_DEBUG_KMS("Mode for pipe %c:\n", pipe_name(pipe));
-	drm_mode_debug_printmodeline(mode);
-
 	intel_set_pipe_timings(intel_crtc, mode, adjusted_mode);
 
 	/* pipesrc and dspsize control the size that is scaled from,
@@ -5661,9 +5652,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc,
 	/* Ensure that the cursor is valid for the new mode before changing... */
 	intel_crtc_update_cursor(crtc, true);
 
-	DRM_DEBUG_KMS("Mode for pipe %c:\n", pipe_name(pipe));
-	drm_mode_debug_printmodeline(mode);
-
 	/* CPU eDP is the only output that doesn't need a PCH PLL of its own. */
 	if (intel_crtc->config.has_pch_encoder) {
 		struct intel_pch_pll *pll;
@@ -5874,9 +5862,6 @@ static int haswell_crtc_mode_set(struct drm_crtc *crtc,
 	/* Ensure that the cursor is valid for the new mode before changing... */
 	intel_crtc_update_cursor(crtc, true);
 
-	DRM_DEBUG_KMS("Mode for pipe %c:\n", pipe_name(pipe));
-	drm_mode_debug_printmodeline(mode);
-
 	if (intel_crtc->config.has_dp_encoder)
 		intel_dp_set_m_n(intel_crtc);
 
@@ -7685,6 +7670,35 @@ pipe_config_set_bpp(struct drm_crtc *crtc,
 	return bpp;
 }
 
+static void intel_dump_pipe_config(struct intel_crtc *crtc,
+				   struct intel_crtc_config *pipe_config,
+				   const char *context)
+{
+	DRM_DEBUG_KMS("[CRTC:%d]%s config for pipe %c\n", crtc->base.base.id,
+		      context, pipe_name(crtc->pipe));
+
+	DRM_DEBUG_KMS("cpu_transcoder: %c\n", transcoder_name(pipe_config->cpu_transcoder));
+	DRM_DEBUG_KMS("pipe bpp: %i, dithering: %i\n",
+		      pipe_config->pipe_bpp, pipe_config->dither);
+	DRM_DEBUG_KMS("fdi/pch: %i, lanes: %i, gmch_m: %u, gmch_n: %u, link_m: %u, link_n: %u, tu: %u\n",
+		      pipe_config->has_pch_encoder,
+		      pipe_config->fdi_lanes,
+		      pipe_config->fdi_m_n.gmch_m, pipe_config->fdi_m_n.gmch_n,
+		      pipe_config->fdi_m_n.link_m, pipe_config->fdi_m_n.link_n,
+		      pipe_config->fdi_m_n.tu);
+	DRM_DEBUG_KMS("requested mode:\n");
+	drm_mode_debug_printmodeline(&pipe_config->requested_mode);
+	DRM_DEBUG_KMS("adjusted mode:\n");
+	drm_mode_debug_printmodeline(&pipe_config->adjusted_mode);
+	DRM_DEBUG_KMS("gmch pfit: control: 0x%08x, ratios: 0x%08x, lvds border: 0x%08x\n",
+		      pipe_config->gmch_pfit.control,
+		      pipe_config->gmch_pfit.pgm_ratios,
+		      pipe_config->gmch_pfit.lvds_border_bits);
+	DRM_DEBUG_KMS("pch pfit: pos: 0x%08x, size: 0x%08x\n",
+		      pipe_config->pch_pfit.pos,
+		      pipe_config->pch_pfit.size);
+}
+
 static struct intel_crtc_config *
 intel_modeset_pipe_config(struct drm_crtc *crtc,
 			  struct drm_framebuffer *fb,
@@ -7755,8 +7769,6 @@ encoder_retry:
 		goto encoder_retry;
 	}
 
-	DRM_DEBUG_KMS("[CRTC:%d]\n", crtc->base.id);
-
 	pipe_config->dither = pipe_config->pipe_bpp != plane_bpp;
 	DRM_DEBUG_KMS("plane bpp: %i, pipe bpp: %i, dithering: %i\n",
 		      plane_bpp, pipe_config->pipe_bpp, pipe_config->dither);
@@ -8113,9 +8125,14 @@ intel_modeset_check_state(struct drm_device *dev)
 		     "crtc active state doesn't match with hw state "
 		     "(expected %i, found %i)\n", crtc->active, active);
 
-		WARN(active &&
-		     !intel_pipe_config_compare(dev, &crtc->config, &pipe_config),
-		     "pipe state doesn't match!\n");
+		if (active &&
+		    !intel_pipe_config_compare(dev, &crtc->config, &pipe_config)) {
+			WARN(1, "pipe state doesn't match!\n");
+			intel_dump_pipe_config(crtc, &pipe_config,
+					       "[hw state]");
+			intel_dump_pipe_config(crtc, &crtc->config,
+					       "[sw state]");
+		}
 	}
 }
 
@@ -8155,6 +8172,8 @@ static int __intel_set_mode(struct drm_crtc *crtc,
 
 			goto out;
 		}
+		intel_dump_pipe_config(to_intel_crtc(crtc), pipe_config,
+				       "[modeset]");
 	}
 
 	for_each_intel_crtc_masked(dev, disable_pipes, intel_crtc)
@@ -8491,12 +8510,6 @@ static int intel_crtc_set_config(struct drm_mode_set *set)
 		goto fail;
 
 	if (config->mode_changed) {
-		if (set->mode) {
-			DRM_DEBUG_KMS("attempting to set mode from"
-					" userspace\n");
-			drm_mode_debug_printmodeline(set->mode);
-		}
-
 		ret = intel_set_mode(set->crtc, set->mode,
 				     set->x, set->y, set->fb);
 		if (ret) {
@@ -9516,6 +9529,7 @@ void intel_modeset_setup_hw_state(struct drm_device *dev,
 	for_each_pipe(pipe) {
 		crtc = to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
 		intel_sanitize_crtc(crtc);
+		intel_dump_pipe_config(crtc, &crtc->config, "[setup_hw_state]");
 	}
 
 	if (force_restore) {

From 64eae94134d2fd0a0f1cf2162fb91e46da4ec75f Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue, 28 May 2013 16:28:55 +0200
Subject: [PATCH 42/70] drm/i915: drop a few really redundant WARNs in hsw
 mode_set

- Correct cpu->pch display matching is already check when we detect
  the PCH type at driver load.
- Plane/pipe state is already checked both when a) enabling, b)
  disabling and in c) the modeset state checker. No need to go
  overboard and also check it in in between a) and b).

Cc: Paulo Zanoni <przanoni@gmail.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_display.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 21cbb3d0e1d8..a45309130a34 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5844,18 +5844,9 @@ static int haswell_crtc_mode_set(struct drm_crtc *crtc,
 		num_connectors++;
 	}
 
-	/* We are not sure yet this won't happen. */
-	WARN(!HAS_PCH_LPT(dev), "Unexpected PCH type %d\n",
-	     INTEL_PCH_TYPE(dev));
-
 	WARN(num_connectors != 1, "%d connectors attached to pipe %c\n",
 	     num_connectors, pipe_name(pipe));
 
-	WARN_ON(I915_READ(PIPECONF(intel_crtc->config.cpu_transcoder)) &
-		(PIPECONF_ENABLE | I965_PIPECONF_ACTIVE));
-
-	WARN_ON(I915_READ(DSPCNTR(plane)) & DISPLAY_PLANE_ENABLE);
-
 	if (!intel_ddi_pll_mode_set(crtc, adjusted_mode->clock))
 		return -EINVAL;
 

From 2e7c8ee7a6bf3440478120f14cbf597d416f88b2 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 28 May 2013 10:38:44 +0100
Subject: [PATCH 43/70] drm/i915: Avoid promoting a simulated hang to 'wedged'

It appears that a beneficial side-effect of Mika's more accurate hangman
work is to speed up hang detection and execution. This exposes a bug in
the reset code that then treats repeated simulated hangs as an
indication that the machine is wedged. Jiggle the code around so that we
only do the simulation processing from the hangcheck and avoid confusing
it with a real hang.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=65060
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_drv.c | 55 ++++++++++++++-------------------
 1 file changed, 23 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index a1a936fd34e0..af224501b4ec 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -839,37 +839,14 @@ static int gen6_do_reset(struct drm_device *dev)
 
 int intel_gpu_reset(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int ret = -ENODEV;
-
 	switch (INTEL_INFO(dev)->gen) {
 	case 7:
-	case 6:
-		ret = gen6_do_reset(dev);
-		break;
-	case 5:
-		ret = ironlake_do_reset(dev);
-		break;
-	case 4:
-		ret = i965_do_reset(dev);
-		break;
-	case 2:
-		ret = i8xx_do_reset(dev);
-		break;
+	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;
 	}
-
-	/* Also reset the gpu hangman. */
-	if (dev_priv->gpu_error.stop_rings) {
-		DRM_INFO("Simulated gpu hang, resetting stop_rings\n");
-		dev_priv->gpu_error.stop_rings = 0;
-		if (ret == -ENODEV) {
-			DRM_ERROR("Reset not implemented, but ignoring "
-				  "error for simulated gpu hangs\n");
-			ret = 0;
-		}
-	}
-
-	return ret;
 }
 
 /**
@@ -890,6 +867,7 @@ int intel_gpu_reset(struct drm_device *dev)
 int i915_reset(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
+	bool simulated;
 	int ret;
 
 	if (!i915_try_reset)
@@ -899,13 +877,26 @@ int i915_reset(struct drm_device *dev)
 
 	i915_gem_reset(dev);
 
-	ret = -ENODEV;
-	if (get_seconds() - dev_priv->gpu_error.last_reset < 5)
+	simulated = dev_priv->gpu_error.stop_rings != 0;
+
+	if (!simulated && get_seconds() - dev_priv->gpu_error.last_reset < 5) {
 		DRM_ERROR("GPU hanging too fast, declaring wedged!\n");
-	else
+		ret = -ENODEV;
+	} else {
 		ret = intel_gpu_reset(dev);
 
-	dev_priv->gpu_error.last_reset = get_seconds();
+		/* Also reset the gpu hangman. */
+		if (simulated) {
+			DRM_INFO("Simulated gpu hang, resetting stop_rings\n");
+			dev_priv->gpu_error.stop_rings = 0;
+			if (ret == -ENODEV) {
+				DRM_ERROR("Reset not implemented, but ignoring "
+					  "error for simulated gpu hangs\n");
+				ret = 0;
+			}
+		} else
+			dev_priv->gpu_error.last_reset = get_seconds();
+	}
 	if (ret) {
 		DRM_ERROR("Failed to reset chip.\n");
 		mutex_unlock(&dev->struct_mutex);

From 40ccc72b84a848e6fcbdb38fe716f0ac6939609e Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Tue, 23 Apr 2013 17:27:08 +0300
Subject: [PATCH 44/70] drm/i915: release cursor when crtc is destroyed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

crtc is holding a reference to a cursor bo and it needs
to be released when crtc is destroyed so that we don't leak
the cursor bo.

v2: Enhance set and move cursor so that disabled
cursor is handled correctly (Ville Syrjälä)

Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_display.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index a45309130a34..161b064592af 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -6509,7 +6509,7 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc,
 	intel_crtc->cursor_width = width;
 	intel_crtc->cursor_height = height;
 
-	intel_crtc_update_cursor(crtc, true);
+	intel_crtc_update_cursor(crtc, intel_crtc->cursor_bo != NULL);
 
 	return 0;
 fail_unpin:
@@ -6528,7 +6528,7 @@ static int intel_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
 	intel_crtc->cursor_x = x;
 	intel_crtc->cursor_y = y;
 
-	intel_crtc_update_cursor(crtc, true);
+	intel_crtc_update_cursor(crtc, intel_crtc->cursor_bo != NULL);
 
 	return 0;
 }
@@ -7042,6 +7042,8 @@ static void intel_crtc_destroy(struct drm_crtc *crtc)
 		kfree(work);
 	}
 
+	intel_crtc_cursor_set(crtc, NULL, 0, 0, 0);
+
 	drm_crtc_cleanup(crtc);
 
 	kfree(intel_crtc);

From 5586181fce2b2e89a0e281d78ffbdfa103bb0dde Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Tue, 28 May 2013 19:22:17 -0700
Subject: [PATCH 45/70] drm/i915: Comments for semaphore clarification

Semaphores are tied very closely to the rings in the GPU. Trivial patch
adds comments to the existing code so that when we add new rings we can
include comments there as well. It also helps distinguish the ring to
semaphore mailbox interactions by using the ringname in the semaphore
data structures.

This patch should have no functional impact.

v2: The English parts (as opposed to register names) of the comments
were reversed. (Damien)

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_reg.h         | 12 ++++++------
 drivers/gpu/drm/i915/intel_ringbuffer.c | 18 +++++++++---------
 drivers/gpu/drm/i915/intel_ringbuffer.h |  4 ++--
 3 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index dbd9de5abde0..6579d0c0d2f1 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -265,12 +265,12 @@
 #define  MI_SEMAPHORE_UPDATE	    (1<<21)
 #define  MI_SEMAPHORE_COMPARE	    (1<<20)
 #define  MI_SEMAPHORE_REGISTER	    (1<<18)
-#define  MI_SEMAPHORE_SYNC_RV	    (2<<16)
-#define  MI_SEMAPHORE_SYNC_RB	    (0<<16)
-#define  MI_SEMAPHORE_SYNC_VR	    (0<<16)
-#define  MI_SEMAPHORE_SYNC_VB	    (2<<16)
-#define  MI_SEMAPHORE_SYNC_BR	    (2<<16)
-#define  MI_SEMAPHORE_SYNC_BV	    (0<<16)
+#define  MI_SEMAPHORE_SYNC_RB	    (0<<16) /* BCS wait for RCS  (BRSYNC) */
+#define  MI_SEMAPHORE_SYNC_RV	    (2<<16) /* VCS wait for RCS  (VRSYNC) */
+#define  MI_SEMAPHORE_SYNC_VR	    (0<<16) /* RCS wait for VCS  (RVSYNC) */
+#define  MI_SEMAPHORE_SYNC_VB	    (2<<16) /* BCS wait for VCS  (BVSYNC) */
+#define  MI_SEMAPHORE_SYNC_BV	    (0<<16) /* VCS wait for BCS  (VBSYNC) */
+#define  MI_SEMAPHORE_SYNC_BR	    (2<<16) /* RCS wait for BCS  (RBSYNC) */
 #define  MI_SEMAPHORE_SYNC_INVALID  (1<<0)
 /*
  * 3D instructions used by the kernel
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 9b97cf66a5ae..2d2a3622639c 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1671,9 +1671,9 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 		ring->get_seqno = gen6_ring_get_seqno;
 		ring->set_seqno = ring_set_seqno;
 		ring->sync_to = gen6_ring_sync;
-		ring->semaphore_register[0] = MI_SEMAPHORE_SYNC_INVALID;
-		ring->semaphore_register[1] = MI_SEMAPHORE_SYNC_RV;
-		ring->semaphore_register[2] = MI_SEMAPHORE_SYNC_RB;
+		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_INVALID;
+		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_RV;
+		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_RB;
 		ring->signal_mbox[0] = GEN6_VRSYNC;
 		ring->signal_mbox[1] = GEN6_BRSYNC;
 	} else if (IS_GEN5(dev)) {
@@ -1830,9 +1830,9 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 		ring->irq_put = gen6_ring_put_irq;
 		ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
 		ring->sync_to = gen6_ring_sync;
-		ring->semaphore_register[0] = MI_SEMAPHORE_SYNC_VR;
-		ring->semaphore_register[1] = MI_SEMAPHORE_SYNC_INVALID;
-		ring->semaphore_register[2] = MI_SEMAPHORE_SYNC_VB;
+		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_VR;
+		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_INVALID;
+		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_VB;
 		ring->signal_mbox[0] = GEN6_RVSYNC;
 		ring->signal_mbox[1] = GEN6_BVSYNC;
 	} else {
@@ -1876,9 +1876,9 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 	ring->irq_put = gen6_ring_put_irq;
 	ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
 	ring->sync_to = gen6_ring_sync;
-	ring->semaphore_register[0] = MI_SEMAPHORE_SYNC_BR;
-	ring->semaphore_register[1] = MI_SEMAPHORE_SYNC_BV;
-	ring->semaphore_register[2] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_BR;
+	ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_BV;
+	ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_INVALID;
 	ring->signal_mbox[0] = GEN6_RBSYNC;
 	ring->signal_mbox[1] = GEN6_VBSYNC;
 	ring->init = init_ring_common;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index ef374a892105..24268fbe6855 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -105,8 +105,8 @@ struct  intel_ring_buffer {
 	int		(*sync_to)(struct intel_ring_buffer *ring,
 				   struct intel_ring_buffer *to,
 				   u32 seqno);
-
-	u32		semaphore_register[3]; /*our mbox written by others */
+	/* our mbox written by others */
+	u32		semaphore_register[I915_NUM_RINGS];
 	u32		signal_mbox[2]; /* mboxes this ring signals to */
 	/**
 	 * List of objects currently involved in rendering from the

From ad776f8b09d66e0145479fdbde2a710e5892441f Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Tue, 28 May 2013 19:22:18 -0700
Subject: [PATCH 46/70] drm/i915: Semaphore MBOX update generalization

This replaces the existing MBOX update code with a more generalized
calculation for emitting mbox updates. We also create a sentinel for
doing the updates so we can more abstractly deal with the rings.

When doing MBOX updates the code must be aware of the /other/ rings.
Until now the platforms which supported semaphores had a fixed number of
rings and so it made sense for the code to be very specialized
(hardcoded).

The patch does contain a functional change, but should have no
behavioral changes.

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_reg.h         |  1 +
 drivers/gpu/drm/i915/intel_ringbuffer.c | 43 +++++++++++++++++--------
 drivers/gpu/drm/i915/intel_ringbuffer.h |  5 ++-
 3 files changed, 34 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 6579d0c0d2f1..19f8e51d2bdc 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -593,6 +593,7 @@
 #define GEN6_VRSYNC (RING_SYNC_1(GEN6_BSD_RING_BASE))
 #define GEN6_VBSYNC (RING_SYNC_0(GEN6_BSD_RING_BASE))
 #define GEN6_BRSYNC (RING_SYNC_0(BLT_RING_BASE))
+#define GEN6_NOSYNC 0
 #define GEN6_BVSYNC (RING_SYNC_1(BLT_RING_BASE))
 #define RING_MAX_IDLE(base)	((base)+0x54)
 #define RING_HWS_PGA(base)	((base)+0x80)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 2d2a3622639c..5df179127e8b 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -582,9 +582,16 @@ static void
 update_mboxes(struct intel_ring_buffer *ring,
 	      u32 mmio_offset)
 {
+/* NB: In order to be able to do semaphore MBOX updates for varying number
+ * of rings, it's easiest if we round up each individual update to a
+ * multiple of 2 (since ring updates must always be a multiple of 2)
+ * even though the actual update only requires 3 dwords.
+ */
+#define MBOX_UPDATE_DWORDS 4
 	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
 	intel_ring_emit(ring, mmio_offset);
 	intel_ring_emit(ring, ring->outstanding_lazy_request);
+	intel_ring_emit(ring, MI_NOOP);
 }
 
 /**
@@ -599,19 +606,24 @@ update_mboxes(struct intel_ring_buffer *ring,
 static int
 gen6_add_request(struct intel_ring_buffer *ring)
 {
-	u32 mbox1_reg;
-	u32 mbox2_reg;
-	int ret;
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_ring_buffer *useless;
+	int i, ret;
 
-	ret = intel_ring_begin(ring, 10);
+	ret = intel_ring_begin(ring, ((I915_NUM_RINGS-1) *
+				      MBOX_UPDATE_DWORDS) +
+				      4);
 	if (ret)
 		return ret;
+#undef MBOX_UPDATE_DWORDS
 
-	mbox1_reg = ring->signal_mbox[0];
-	mbox2_reg = ring->signal_mbox[1];
+	for_each_ring(useless, dev_priv, i) {
+		u32 mbox_reg = ring->signal_mbox[i];
+		if (mbox_reg != GEN6_NOSYNC)
+			update_mboxes(ring, mbox_reg);
+	}
 
-	update_mboxes(ring, mbox1_reg);
-	update_mboxes(ring, mbox2_reg);
 	intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
 	intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
 	intel_ring_emit(ring, ring->outstanding_lazy_request);
@@ -1674,8 +1686,9 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_INVALID;
 		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_RV;
 		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_RB;
-		ring->signal_mbox[0] = GEN6_VRSYNC;
-		ring->signal_mbox[1] = GEN6_BRSYNC;
+		ring->signal_mbox[RCS] = GEN6_NOSYNC;
+		ring->signal_mbox[VCS] = GEN6_VRSYNC;
+		ring->signal_mbox[BCS] = GEN6_BRSYNC;
 	} else if (IS_GEN5(dev)) {
 		ring->add_request = pc_render_add_request;
 		ring->flush = gen4_render_ring_flush;
@@ -1833,8 +1846,9 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_VR;
 		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_INVALID;
 		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_VB;
-		ring->signal_mbox[0] = GEN6_RVSYNC;
-		ring->signal_mbox[1] = GEN6_BVSYNC;
+		ring->signal_mbox[RCS] = GEN6_RVSYNC;
+		ring->signal_mbox[VCS] = GEN6_NOSYNC;
+		ring->signal_mbox[BCS] = GEN6_BVSYNC;
 	} else {
 		ring->mmio_base = BSD_RING_BASE;
 		ring->flush = bsd_ring_flush;
@@ -1879,8 +1893,9 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 	ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_BR;
 	ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_BV;
 	ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_INVALID;
-	ring->signal_mbox[0] = GEN6_RBSYNC;
-	ring->signal_mbox[1] = GEN6_VBSYNC;
+	ring->signal_mbox[RCS] = GEN6_RBSYNC;
+	ring->signal_mbox[VCS] = GEN6_VBSYNC;
+	ring->signal_mbox[BCS] = GEN6_NOSYNC;
 	ring->init = init_ring_common;
 
 	return intel_init_ring_buffer(dev, ring);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 24268fbe6855..f55d92eb6c2a 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -105,9 +105,12 @@ struct  intel_ring_buffer {
 	int		(*sync_to)(struct intel_ring_buffer *ring,
 				   struct intel_ring_buffer *to,
 				   u32 seqno);
+
 	/* our mbox written by others */
 	u32		semaphore_register[I915_NUM_RINGS];
-	u32		signal_mbox[2]; /* mboxes this ring signals to */
+	/* mboxes this ring signals to */
+	u32		signal_mbox[I915_NUM_RINGS];
+
 	/**
 	 * List of objects currently involved in rendering from the
 	 * ringbuffer.

From 4a3dd19d94c65323d71b2ffc7e63940f00acfb47 Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Tue, 28 May 2013 19:22:19 -0700
Subject: [PATCH 47/70] drm/i915: Introduce VECS: the 4th ring

The video enhancement command streamer is a new ring on HSW which does
what it sounds like it does. This patch provides the most minimal
inception of the ring.

In order to support a new ring, we need to bump the number. The patch
may look trivial to the untrained eye, but bumping the number of rings
is a bit scary. As such the patch is not terribly useful by itself, but
a pretty nice place to find issues during a bisection.

Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 2 ++
 drivers/gpu/drm/i915/intel_ringbuffer.h | 3 ++-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 5df179127e8b..ead979a94105 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -915,6 +915,8 @@ void intel_ring_setup_status_page(struct intel_ring_buffer *ring)
 		case VCS:
 			mmio = BSD_HWS_PGA_GEN7;
 			break;
+		case VECS:
+			BUG();
 		}
 	} else if (IS_GEN6(ring->dev)) {
 		mmio = RING_HWS_PGA_GEN6(ring->mmio_base);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index f55d92eb6c2a..73619cb34631 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -47,8 +47,9 @@ struct  intel_ring_buffer {
 		RCS = 0x0,
 		VCS,
 		BCS,
+		VECS,
 	} id;
-#define I915_NUM_RINGS 3
+#define I915_NUM_RINGS 4
 	u32		mmio_base;
 	void		__iomem *virtual_start;
 	struct		drm_device *dev;

From 1950de14fd1b8ea27a411929156c7eccee2ad7c3 Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Tue, 28 May 2013 19:22:20 -0700
Subject: [PATCH 48/70] drm/i915: Add VECS semaphore bits

Like the other rings, the VECS supports semaphores. The semaphore stuff
is a bit wonky so this patch on it's own should be nice for review.

This patch should have no functional impact.

v2: Fix the English parts of clarification (again, register names were
right, text was reversed) (Damien)
Restore the still valid invariant. (Damien)
The bsd semaphore register should be MI_SEMAPHORE_SYNC_VVE (Damien)

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_reg.h         | 40 +++++++++++++++++--------
 drivers/gpu/drm/i915/intel_ringbuffer.c |  6 ++++
 2 files changed, 33 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 19f8e51d2bdc..41c5d45362b2 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -265,13 +265,19 @@
 #define  MI_SEMAPHORE_UPDATE	    (1<<21)
 #define  MI_SEMAPHORE_COMPARE	    (1<<20)
 #define  MI_SEMAPHORE_REGISTER	    (1<<18)
-#define  MI_SEMAPHORE_SYNC_RB	    (0<<16) /* BCS wait for RCS  (BRSYNC) */
-#define  MI_SEMAPHORE_SYNC_RV	    (2<<16) /* VCS wait for RCS  (VRSYNC) */
-#define  MI_SEMAPHORE_SYNC_VR	    (0<<16) /* RCS wait for VCS  (RVSYNC) */
-#define  MI_SEMAPHORE_SYNC_VB	    (2<<16) /* BCS wait for VCS  (BVSYNC) */
-#define  MI_SEMAPHORE_SYNC_BV	    (0<<16) /* VCS wait for BCS  (VBSYNC) */
-#define  MI_SEMAPHORE_SYNC_BR	    (2<<16) /* RCS wait for BCS  (RBSYNC) */
-#define  MI_SEMAPHORE_SYNC_INVALID  (1<<0)
+#define  MI_SEMAPHORE_SYNC_VR	    (0<<16) /* RCS  wait for VCS  (RVSYNC) */
+#define  MI_SEMAPHORE_SYNC_VER	    (1<<16) /* RCS  wait for VECS (RVESYNC) */
+#define  MI_SEMAPHORE_SYNC_BR	    (2<<16) /* RCS  wait for BCS  (RBSYNC) */
+#define  MI_SEMAPHORE_SYNC_BV	    (0<<16) /* VCS  wait for BCS  (VBSYNC) */
+#define  MI_SEMAPHORE_SYNC_VEV	    (1<<16) /* VCS  wait for VECS (VVESYNC) */
+#define  MI_SEMAPHORE_SYNC_RV	    (2<<16) /* VCS  wait for RCS  (VRSYNC) */
+#define  MI_SEMAPHORE_SYNC_RB	    (0<<16) /* BCS  wait for RCS  (BRSYNC) */
+#define  MI_SEMAPHORE_SYNC_VEB	    (1<<16) /* BCS  wait for VECS (BVESYNC) */
+#define  MI_SEMAPHORE_SYNC_VB	    (2<<16) /* BCS  wait for VCS  (BVSYNC) */
+#define  MI_SEMAPHORE_SYNC_BVE	    (0<<16) /* VECS wait for BCS  (VEBSYNC) */
+#define  MI_SEMAPHORE_SYNC_VVE	    (1<<16) /* VECS wait for VCS  (VEVSYNC) */
+#define  MI_SEMAPHORE_SYNC_RVE	    (2<<16) /* VECS wait for RCS  (VERSYNC) */
+#define  MI_SEMAPHORE_SYNC_INVALID  (3<<16)
 /*
  * 3D instructions used by the kernel
  */
@@ -581,6 +587,7 @@
 #define RENDER_RING_BASE	0x02000
 #define BSD_RING_BASE		0x04000
 #define GEN6_BSD_RING_BASE	0x12000
+#define VEBOX_RING_BASE		0x1a000
 #define BLT_RING_BASE		0x22000
 #define RING_TAIL(base)		((base)+0x30)
 #define RING_HEAD(base)		((base)+0x34)
@@ -588,13 +595,20 @@
 #define RING_CTL(base)		((base)+0x3c)
 #define RING_SYNC_0(base)	((base)+0x40)
 #define RING_SYNC_1(base)	((base)+0x44)
-#define GEN6_RVSYNC (RING_SYNC_0(RENDER_RING_BASE))
-#define GEN6_RBSYNC (RING_SYNC_1(RENDER_RING_BASE))
-#define GEN6_VRSYNC (RING_SYNC_1(GEN6_BSD_RING_BASE))
-#define GEN6_VBSYNC (RING_SYNC_0(GEN6_BSD_RING_BASE))
-#define GEN6_BRSYNC (RING_SYNC_0(BLT_RING_BASE))
+#define RING_SYNC_2(base)	((base)+0x48)
+#define GEN6_RVSYNC	(RING_SYNC_0(RENDER_RING_BASE))
+#define GEN6_RBSYNC	(RING_SYNC_1(RENDER_RING_BASE))
+#define GEN6_RVESYNC	(RING_SYNC_2(RENDER_RING_BASE))
+#define GEN6_VBSYNC	(RING_SYNC_0(GEN6_BSD_RING_BASE))
+#define GEN6_VRSYNC	(RING_SYNC_1(GEN6_BSD_RING_BASE))
+#define GEN6_VVESYNC	(RING_SYNC_2(GEN6_BSD_RING_BASE))
+#define GEN6_BRSYNC	(RING_SYNC_0(BLT_RING_BASE))
+#define GEN6_BVSYNC	(RING_SYNC_1(BLT_RING_BASE))
+#define GEN6_BVESYNC	(RING_SYNC_2(BLT_RING_BASE))
+#define GEN6_VEBSYNC	(RING_SYNC_0(VEBOX_RING_BASE))
+#define GEN6_VERSYNC	(RING_SYNC_1(VEBOX_RING_BASE))
+#define GEN6_VEVSYNC	(RING_SYNC_2(VEBOX_RING_BASE))
 #define GEN6_NOSYNC 0
-#define GEN6_BVSYNC (RING_SYNC_1(BLT_RING_BASE))
 #define RING_MAX_IDLE(base)	((base)+0x54)
 #define RING_HWS_PGA(base)	((base)+0x80)
 #define RING_HWS_PGA_GEN6(base)	((base)+0x2080)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index ead979a94105..93ccd1e982e0 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1688,9 +1688,11 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_INVALID;
 		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_RV;
 		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_RB;
+		ring->semaphore_register[VECS] = MI_SEMAPHORE_SYNC_RVE;
 		ring->signal_mbox[RCS] = GEN6_NOSYNC;
 		ring->signal_mbox[VCS] = GEN6_VRSYNC;
 		ring->signal_mbox[BCS] = GEN6_BRSYNC;
+		ring->signal_mbox[VECS] = GEN6_VERSYNC;
 	} else if (IS_GEN5(dev)) {
 		ring->add_request = pc_render_add_request;
 		ring->flush = gen4_render_ring_flush;
@@ -1848,9 +1850,11 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_VR;
 		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_INVALID;
 		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_VB;
+		ring->semaphore_register[VECS] = MI_SEMAPHORE_SYNC_VVE;
 		ring->signal_mbox[RCS] = GEN6_RVSYNC;
 		ring->signal_mbox[VCS] = GEN6_NOSYNC;
 		ring->signal_mbox[BCS] = GEN6_BVSYNC;
+		ring->signal_mbox[VECS] = GEN6_VEVSYNC;
 	} else {
 		ring->mmio_base = BSD_RING_BASE;
 		ring->flush = bsd_ring_flush;
@@ -1895,9 +1899,11 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 	ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_BR;
 	ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_BV;
 	ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore_register[VECS] = MI_SEMAPHORE_SYNC_BVE;
 	ring->signal_mbox[RCS] = GEN6_RBSYNC;
 	ring->signal_mbox[VCS] = GEN6_VBSYNC;
 	ring->signal_mbox[BCS] = GEN6_NOSYNC;
+	ring->signal_mbox[VECS] = GEN6_VEBSYNC;
 	ring->init = init_ring_common;
 
 	return intel_init_ring_buffer(dev, ring);

From ea251324cac6c1e0402db073e5193f33aedd94f3 Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Tue, 28 May 2013 19:22:21 -0700
Subject: [PATCH 49/70] drm/i915: Rename ring flush functions

Historically we considered the render ring to have special flush
semantics and everything else to fall under a more general umbrella.
Probably by coincidence more than anything we decided to make the bsd
ring have the default *other* flush. As the new vebox ring exposes, the
bsd ring is actually the weird one. Doing this allows us to call
gen6_ring_flush for the vebox because calling blt_ring_flush would be
weird...

This patch should have no functional change.

Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 93ccd1e982e0..3022e1579e58 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1565,8 +1565,8 @@ static void gen6_bsd_ring_write_tail(struct intel_ring_buffer *ring,
 		   _MASKED_BIT_DISABLE(GEN6_BSD_SLEEP_MSG_DISABLE));
 }
 
-static int gen6_ring_flush(struct intel_ring_buffer *ring,
-			   u32 invalidate, u32 flush)
+static int gen6_bsd_ring_flush(struct intel_ring_buffer *ring,
+			       u32 invalidate, u32 flush)
 {
 	uint32_t cmd;
 	int ret;
@@ -1637,8 +1637,8 @@ gen6_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
 
 /* Blitter support (SandyBridge+) */
 
-static int blt_ring_flush(struct intel_ring_buffer *ring,
-			  u32 invalidate, u32 flush)
+static int gen6_ring_flush(struct intel_ring_buffer *ring,
+			   u32 invalidate, u32 flush)
 {
 	uint32_t cmd;
 	int ret;
@@ -1838,7 +1838,7 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 		/* gen6 bsd needs a special wa for tail updates */
 		if (IS_GEN6(dev))
 			ring->write_tail = gen6_bsd_ring_write_tail;
-		ring->flush = gen6_ring_flush;
+		ring->flush = gen6_bsd_ring_flush;
 		ring->add_request = gen6_add_request;
 		ring->get_seqno = gen6_ring_get_seqno;
 		ring->set_seqno = ring_set_seqno;
@@ -1887,7 +1887,7 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 
 	ring->mmio_base = BLT_RING_BASE;
 	ring->write_tail = ring_write_tail;
-	ring->flush = blt_ring_flush;
+	ring->flush = gen6_ring_flush;
 	ring->add_request = gen6_add_request;
 	ring->get_seqno = gen6_ring_get_seqno;
 	ring->set_seqno = ring_set_seqno;

From f72a1183b31cd1bebf926f904c1f025a90d153a1 Mon Sep 17 00:00:00 2001
From: "Xiang, Haihao" <haihao.xiang@intel.com>
Date: Tue, 28 May 2013 19:22:22 -0700
Subject: [PATCH 50/70] drm/i915: add HAS_VEBOX

The flag will be useful to help share code between IVB, and HSW as the
programming is similar in many places with this as one of the major
differences.

Signed-off-by: Xiang, Haihao <haihao.xiang@intel.com>
[Commit message + small fix by]
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_drv.c | 2 ++
 drivers/gpu/drm/i915/i915_drv.h | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index af224501b4ec..a4e8f16a38e8 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -311,6 +311,7 @@ static const struct intel_device_info intel_haswell_d_info = {
 	.is_haswell = 1,
 	.has_ddi = 1,
 	.has_fpga_dbg = 1,
+	.has_vebox_ring = 1,
 };
 
 static const struct intel_device_info intel_haswell_m_info = {
@@ -320,6 +321,7 @@ static const struct intel_device_info intel_haswell_m_info = {
 	.has_ddi = 1,
 	.has_fpga_dbg = 1,
 	.has_fbc = 1,
+	.has_vebox_ring = 1,
 };
 
 static const struct pci_device_id pciidlist[] = {		/* aka */
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e417049ea581..a18da3c6c96e 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -374,6 +374,7 @@ struct drm_i915_gt_funcs {
 	func(supports_tv) sep \
 	func(has_bsd_ring) sep \
 	func(has_blt_ring) sep \
+	func(has_vebox_ring) sep \
 	func(has_llc) sep \
 	func(has_ddi) sep \
 	func(has_fpga_dbg)
@@ -1373,6 +1374,7 @@ struct drm_i915_file_private {
 
 #define HAS_BSD(dev)            (INTEL_INFO(dev)->has_bsd_ring)
 #define HAS_BLT(dev)            (INTEL_INFO(dev)->has_blt_ring)
+#define HAS_VEBOX(dev)          (INTEL_INFO(dev)->has_vebox_ring)
 #define HAS_LLC(dev)            (INTEL_INFO(dev)->has_llc)
 #define I915_NEED_GFX_HWS(dev)	(INTEL_INFO(dev)->need_gfx_hws)
 

From 9a8a2213a778509b724c8fda04be70528a1f7130 Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Tue, 28 May 2013 19:22:23 -0700
Subject: [PATCH 51/70] drm/i915: Vebox ringbuffer init

v2: Add set_seqno which didn't exist before rebase (Haihao)

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Xiang, Haihao <haihao.xiang@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_gem.c         | 11 +++++++-
 drivers/gpu/drm/i915/i915_reg.h         |  1 +
 drivers/gpu/drm/i915/intel_ringbuffer.c | 35 ++++++++++++++++++++++++-
 drivers/gpu/drm/i915/intel_ringbuffer.h |  1 +
 4 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 9496fb5f2fe1..84d2aa21435a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4013,12 +4013,21 @@ static int i915_gem_init_rings(struct drm_device *dev)
 			goto cleanup_bsd_ring;
 	}
 
+	if (HAS_VEBOX(dev)) {
+		ret = intel_init_vebox_ring_buffer(dev);
+		if (ret)
+			goto cleanup_blt_ring;
+	}
+
+
 	ret = i915_gem_set_seqno(dev, ((u32)~0 - 0x1000));
 	if (ret)
-		goto cleanup_blt_ring;
+		goto cleanup_vebox_ring;
 
 	return 0;
 
+cleanup_vebox_ring:
+	intel_cleanup_ring_buffer(&dev_priv->ring[VECS]);
 cleanup_blt_ring:
 	intel_cleanup_ring_buffer(&dev_priv->ring[BCS]);
 cleanup_bsd_ring:
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 41c5d45362b2..a5717f179332 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -620,6 +620,7 @@
 #define DONE_REG		0x40b0
 #define BSD_HWS_PGA_GEN7	(0x04180)
 #define BLT_HWS_PGA_GEN7	(0x04280)
+#define VEBOX_HWS_PGA_GEN7	(0x04380)
 #define RING_ACTHD(base)	((base)+0x74)
 #define RING_NOPID(base)	((base)+0x94)
 #define RING_IMR(base)		((base)+0xa8)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 3022e1579e58..89dfc63677ad 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -916,7 +916,8 @@ void intel_ring_setup_status_page(struct intel_ring_buffer *ring)
 			mmio = BSD_HWS_PGA_GEN7;
 			break;
 		case VECS:
-			BUG();
+			mmio = VEBOX_HWS_PGA_GEN7;
+			break;
 		}
 	} else if (IS_GEN6(ring->dev)) {
 		mmio = RING_HWS_PGA_GEN6(ring->mmio_base);
@@ -1909,6 +1910,38 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 	return intel_init_ring_buffer(dev, ring);
 }
 
+int intel_init_vebox_ring_buffer(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct intel_ring_buffer *ring = &dev_priv->ring[VECS];
+
+	ring->name = "video enhancement ring";
+	ring->id = VECS;
+
+	ring->mmio_base = VEBOX_RING_BASE;
+	ring->write_tail = ring_write_tail;
+	ring->flush = gen6_ring_flush;
+	ring->add_request = gen6_add_request;
+	ring->get_seqno = gen6_ring_get_seqno;
+	ring->set_seqno = ring_set_seqno;
+	ring->irq_enable_mask = 0;
+	ring->irq_get = NULL;
+	ring->irq_put = NULL;
+	ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
+	ring->sync_to = gen6_ring_sync;
+	ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_VER;
+	ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_VEV;
+	ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_VEB;
+	ring->semaphore_register[VECS] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->signal_mbox[RCS] = GEN6_RVESYNC;
+	ring->signal_mbox[VCS] = GEN6_VVESYNC;
+	ring->signal_mbox[BCS] = GEN6_BVESYNC;
+	ring->signal_mbox[VECS] = GEN6_NOSYNC;
+	ring->init = init_ring_common;
+
+	return intel_init_ring_buffer(dev, ring);
+}
+
 int
 intel_ring_flush_all_caches(struct intel_ring_buffer *ring)
 {
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 73619cb34631..1c79520c7e45 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -234,6 +234,7 @@ int intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring);
 int intel_init_render_ring_buffer(struct drm_device *dev);
 int intel_init_bsd_ring_buffer(struct drm_device *dev);
 int intel_init_blt_ring_buffer(struct drm_device *dev);
+int intel_init_vebox_ring_buffer(struct drm_device *dev);
 
 u32 intel_ring_get_active_head(struct intel_ring_buffer *ring);
 void intel_ring_setup_status_page(struct intel_ring_buffer *ring);

From 692a04cf77e6073a60a9eaa87b7c409b6cf0283b Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 29 May 2013 21:43:05 +0200
Subject: [PATCH 52/70] drm/i915: fix pch_nop support

This was accidentally broken in the south error interrupt handling
work:

commit 8664281b64c457705db72fc60143d03827e75ca9
Author: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date:   Fri Apr 12 17:57:57 2013 -0300

    drm/i915: report Gen5+ CPU and PCH FIFO underruns

Cc: Paulo Zanoni <paulo.r.zanoni@intel.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/i915_irq.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 557acd37c788..338e726f4ef5 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2551,6 +2551,9 @@ static void ibx_irq_postinstall(struct drm_device *dev)
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 	u32 mask;
 
+	if (HAS_PCH_NOP(dev))
+		return;
+
 	if (HAS_PCH_IBX(dev)) {
 		mask = SDE_GMBUS | SDE_AUX_MASK | SDE_TRANSB_FIFO_UNDER |
 		       SDE_TRANSA_FIFO_UNDER | SDE_POISON;
@@ -2560,9 +2563,6 @@ static void ibx_irq_postinstall(struct drm_device *dev)
 		I915_WRITE(SERR_INT, I915_READ(SERR_INT));
 	}
 
-	if (HAS_PCH_NOP(dev))
-		return;
-
 	I915_WRITE(SDEIIR, I915_READ(SDEIIR));
 	I915_WRITE(SDEIMR, ~mask);
 }

From 801bcfffbb0721d7131e930f9a46103e539c43a4 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 31 May 2013 10:08:35 -0300
Subject: [PATCH 53/70] drm/i915: properly set HSW WM_PIPE registers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We were previously calling sandybridge_update_wm on HSW, but the SNB
function didn't really match the HSW specification, so we were just
writing the wrong values.

With this patch, the haswell_update_wm function will set the correct
values for the WM_PIPE registers, but it will still keep all the LP
watermarks disabled.

The patch may look a little bit over-complicated for now, but it's
because much of the infrastructure for setting the LP watermarks is
already in place, so we won't have too much code churn on the patch
that sets the LP watermarks.

v2: - Fix pixel_rate on panel fitter case (Ville)
    - Try to not overflow (Ville)
    - Remove useless variable (Ville)
    - Fix p->pri_horiz_pixels (Paulo)
v3: - Fix rounding errors on hsw_wm_method2 (Ville)
v4: - Fix memcmp bug (Paulo)

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_reg.h |   3 +
 drivers/gpu/drm/i915/intel_pm.c | 342 ++++++++++++++++++++++++++++++--
 2 files changed, 327 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index a5717f179332..19021bd8b030 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4947,6 +4947,9 @@
 #define  SFUSE_STRAP_DDIC_DETECTED	(1<<1)
 #define  SFUSE_STRAP_DDID_DETECTED	(1<<0)
 
+#define WM_MISC				0x45260
+#define  WM_MISC_DATA_PARTITION_5_6	(1 << 0)
+
 #define WM_DBG				0x45280
 #define  WM_DBG_DISALLOW_MULTIPLE_LP	(1<<0)
 #define  WM_DBG_DISALLOW_MAXFIFO	(1<<1)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 9328ed98ce2f..fda727921748 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2072,19 +2072,170 @@ static void ivybridge_update_wm(struct drm_device *dev)
 		   cursor_wm);
 }
 
-static void
-haswell_update_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc)
+static uint32_t hsw_wm_get_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;
+
+	if (intel_crtc->config.pixel_target_clock)
+		pixel_rate = intel_crtc->config.pixel_target_clock;
+	else
+		pixel_rate = intel_crtc->config.adjusted_mode.clock;
+
+	/* We only use IF-ID interlacing. If we ever use PF-ID we'll need to
+	 * adjust the pixel_rate here. */
+
+	pfit_size = intel_crtc->config.pch_pfit.size;
+	if (pfit_size) {
+		uint64_t pipe_w, pipe_h, pfit_w, pfit_h;
+
+		pipe_w = intel_crtc->config.requested_mode.hdisplay;
+		pipe_h = intel_crtc->config.requested_mode.vdisplay;
+		pfit_w = (pfit_size >> 16) & 0xFFFF;
+		pfit_h = pfit_size & 0xFFFF;
+		if (pipe_w < pfit_w)
+			pipe_w = pfit_w;
+		if (pipe_h < pfit_h)
+			pipe_h = pfit_h;
+
+		pixel_rate = div_u64((uint64_t) pixel_rate * pipe_w * pipe_h,
+				     pfit_w * pfit_h);
+	}
+
+	return pixel_rate;
+}
+
+static uint32_t hsw_wm_method1(uint32_t pixel_rate, uint8_t bytes_per_pixel,
+			       uint32_t latency)
+{
+	uint64_t ret;
+
+	ret = (uint64_t) pixel_rate * bytes_per_pixel * latency;
+	ret = DIV_ROUND_UP_ULL(ret, 64 * 10000) + 2;
+
+	return ret;
+}
+
+static uint32_t hsw_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal,
+			       uint32_t horiz_pixels, uint8_t bytes_per_pixel,
+			       uint32_t latency)
+{
+	uint32_t ret;
+
+	ret = (latency * pixel_rate) / (pipe_htotal * 10000);
+	ret = (ret + 1) * horiz_pixels * bytes_per_pixel;
+	ret = DIV_ROUND_UP(ret, 64) + 2;
+	return ret;
+}
+
+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 hsw_wm_values {
+	uint32_t wm_pipe[3];
+	uint32_t wm_lp[3];
+	uint32_t wm_lp_spr[3];
+	uint32_t wm_linetime[3];
+};
+
+enum hsw_data_buf_partitioning {
+	HSW_DATA_BUF_PART_1_2,
+	HSW_DATA_BUF_PART_5_6,
+};
+
+/* Only for WM_PIPE. */
+static uint32_t hsw_compute_pri_wm_pipe(struct hsw_pipe_wm_parameters *params,
+					uint32_t mem_value)
+{
+	/* TODO: for now, assume the primary plane is always enabled. */
+	if (!params->active)
+		return 0;
+
+	return hsw_wm_method1(params->pixel_rate,
+			      params->pri_bytes_per_pixel,
+			      mem_value);
+}
+
+/* For both WM_PIPE and WM_LP. */
+static uint32_t hsw_compute_spr_wm(struct hsw_pipe_wm_parameters *params,
+				   uint32_t mem_value)
+{
+	uint32_t method1, method2;
+
+	if (!params->active || !params->sprite_enabled)
+		return 0;
+
+	method1 = hsw_wm_method1(params->pixel_rate,
+				 params->spr_bytes_per_pixel,
+				 mem_value);
+	method2 = hsw_wm_method2(params->pixel_rate,
+				 params->pipe_htotal,
+				 params->spr_horiz_pixels,
+				 params->spr_bytes_per_pixel,
+				 mem_value);
+	return min(method1, method2);
+}
+
+/* For both WM_PIPE and WM_LP. */
+static uint32_t hsw_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,
+			      params->pipe_htotal,
+			      params->cur_horiz_pixels,
+			      params->cur_bytes_per_pixel,
+			      mem_value);
+}
+
+static uint32_t hsw_compute_wm_pipe(struct drm_i915_private *dev_priv,
+				    uint32_t mem_value, enum pipe pipe,
+				    struct hsw_pipe_wm_parameters *params)
+{
+	uint32_t pri_val, cur_val, spr_val;
+
+	pri_val = hsw_compute_pri_wm_pipe(params, mem_value);
+	spr_val = hsw_compute_spr_wm(params, mem_value);
+	cur_val = hsw_compute_cur_wm(params, mem_value);
+
+	WARN(pri_val > 127,
+	     "Primary WM error, mode not supported for pipe %c\n",
+	     pipe_name(pipe));
+	WARN(spr_val > 127,
+	     "Sprite WM error, mode not supported for pipe %c\n",
+	     pipe_name(pipe));
+	WARN(cur_val > 63,
+	     "Cursor WM error, mode not supported for pipe %c\n",
+	     pipe_name(pipe));
+
+	return (pri_val << WM0_PIPE_PLANE_SHIFT) |
+	       (spr_val << WM0_PIPE_SPRITE_SHIFT) |
+	       cur_val;
+}
+
+static uint32_t
+hsw_compute_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
 	struct drm_display_mode *mode = &intel_crtc->config.adjusted_mode;
 	u32 linetime, ips_linetime;
 
-	if (!intel_crtc_active(crtc)) {
-		I915_WRITE(PIPE_WM_LINETIME(pipe), 0);
-		return;
-	}
+	if (!intel_crtc_active(crtc))
+		return 0;
 
 	/* The WM are computed with base on how long it takes to fill a single
 	 * row at the given clock rate, multiplied by 8.
@@ -2093,29 +2244,184 @@ haswell_update_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc)
 	ips_linetime = DIV_ROUND_CLOSEST(mode->htotal * 1000 * 8,
 					 intel_ddi_get_cdclk_freq(dev_priv));
 
-	I915_WRITE(PIPE_WM_LINETIME(pipe),
-		   PIPE_WM_LINETIME_IPS_LINETIME(ips_linetime) |
-		   PIPE_WM_LINETIME_TIME(linetime));
+	return PIPE_WM_LINETIME_IPS_LINETIME(ips_linetime) |
+	       PIPE_WM_LINETIME_TIME(linetime);
 }
 
-static void haswell_update_wm(struct drm_device *dev)
+static void hsw_compute_wm_parameters(struct drm_device *dev,
+				      struct hsw_pipe_wm_parameters *params,
+				      uint32_t *wm)
+{
+	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;
+
+	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;
+
+		pipe = intel_crtc->pipe;
+		p = &params[pipe];
+
+		p->active = intel_crtc_active(crtc);
+		if (!p->active)
+			continue;
+
+		p->pipe_htotal = intel_crtc->config.adjusted_mode.htotal;
+		p->pixel_rate = hsw_wm_get_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 =
+			intel_crtc->config.requested_mode.hdisplay;
+		p->cur_horiz_pixels = 64;
+	}
+
+	list_for_each_entry(plane, &dev->mode_config.plane_list, head) {
+		struct intel_plane *intel_plane = to_intel_plane(plane);
+		struct hsw_pipe_wm_parameters *p;
+
+		pipe = intel_plane->pipe;
+		p = &params[pipe];
+
+		p->sprite_enabled = intel_plane->wm.enable;
+		p->spr_bytes_per_pixel = intel_plane->wm.bytes_per_pixel;
+		p->spr_horiz_pixels = intel_plane->wm.horiz_pixels;
+	}
+}
+
+static void hsw_compute_wm_results(struct drm_device *dev,
+				   struct hsw_pipe_wm_parameters *params,
+				   uint32_t *wm,
+				   struct hsw_wm_values *results)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc;
 	enum pipe pipe;
 
-	/* Disable the LP WMs before changine the linetime registers. This is
-	 * just a temporary code that will be replaced soon. */
-	I915_WRITE(WM3_LP_ILK, 0);
-	I915_WRITE(WM2_LP_ILK, 0);
-	I915_WRITE(WM1_LP_ILK, 0);
+	/* No support for LP WMs yet. */
+	results->wm_lp[2] = 0;
+	results->wm_lp[1] = 0;
+	results->wm_lp[0] = 0;
+	results->wm_lp_spr[2] = 0;
+	results->wm_lp_spr[1] = 0;
+	results->wm_lp_spr[0] = 0;
+
+	for_each_pipe(pipe)
+		results->wm_pipe[pipe] = hsw_compute_wm_pipe(dev_priv, wm[0],
+							     pipe,
+							     &params[pipe]);
 
 	for_each_pipe(pipe) {
 		crtc = dev_priv->pipe_to_crtc_mapping[pipe];
-		haswell_update_linetime_wm(dev, crtc);
+		results->wm_linetime[pipe] = hsw_compute_linetime_wm(dev, crtc);
+	}
+}
+
+/*
+ * The spec says we shouldn't write when we don't need, because every write
+ * causes WMs to be re-evaluated, expending some power.
+ */
+static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
+				struct hsw_wm_values *results,
+				enum hsw_data_buf_partitioning partitioning)
+{
+	struct hsw_wm_values previous;
+	uint32_t val;
+	enum hsw_data_buf_partitioning prev_partitioning;
+
+	previous.wm_pipe[0] = I915_READ(WM0_PIPEA_ILK);
+	previous.wm_pipe[1] = I915_READ(WM0_PIPEB_ILK);
+	previous.wm_pipe[2] = I915_READ(WM0_PIPEC_IVB);
+	previous.wm_lp[0] = I915_READ(WM1_LP_ILK);
+	previous.wm_lp[1] = I915_READ(WM2_LP_ILK);
+	previous.wm_lp[2] = I915_READ(WM3_LP_ILK);
+	previous.wm_lp_spr[0] = I915_READ(WM1S_LP_ILK);
+	previous.wm_lp_spr[1] = I915_READ(WM2S_LP_IVB);
+	previous.wm_lp_spr[2] = I915_READ(WM3S_LP_IVB);
+	previous.wm_linetime[0] = I915_READ(PIPE_WM_LINETIME(PIPE_A));
+	previous.wm_linetime[1] = I915_READ(PIPE_WM_LINETIME(PIPE_B));
+	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;
+
+	if (memcmp(results->wm_pipe, previous.wm_pipe,
+		   sizeof(results->wm_pipe)) == 0 &&
+	    memcmp(results->wm_lp, previous.wm_lp,
+		   sizeof(results->wm_lp)) == 0 &&
+	    memcmp(results->wm_lp_spr, previous.wm_lp_spr,
+		   sizeof(results->wm_lp_spr)) == 0 &&
+	    memcmp(results->wm_linetime, previous.wm_linetime,
+		   sizeof(results->wm_linetime)) == 0 &&
+	    partitioning == prev_partitioning)
+		return;
+
+	if (previous.wm_lp[2] != 0)
+		I915_WRITE(WM3_LP_ILK, 0);
+	if (previous.wm_lp[1] != 0)
+		I915_WRITE(WM2_LP_ILK, 0);
+	if (previous.wm_lp[0] != 0)
+		I915_WRITE(WM1_LP_ILK, 0);
+
+	if (previous.wm_pipe[0] != results->wm_pipe[0])
+		I915_WRITE(WM0_PIPEA_ILK, results->wm_pipe[0]);
+	if (previous.wm_pipe[1] != results->wm_pipe[1])
+		I915_WRITE(WM0_PIPEB_ILK, results->wm_pipe[1]);
+	if (previous.wm_pipe[2] != results->wm_pipe[2])
+		I915_WRITE(WM0_PIPEC_IVB, results->wm_pipe[2]);
+
+	if (previous.wm_linetime[0] != results->wm_linetime[0])
+		I915_WRITE(PIPE_WM_LINETIME(PIPE_A), results->wm_linetime[0]);
+	if (previous.wm_linetime[1] != results->wm_linetime[1])
+		I915_WRITE(PIPE_WM_LINETIME(PIPE_B), results->wm_linetime[1]);
+	if (previous.wm_linetime[2] != results->wm_linetime[2])
+		I915_WRITE(PIPE_WM_LINETIME(PIPE_C), results->wm_linetime[2]);
+
+	if (prev_partitioning != partitioning) {
+		val = I915_READ(WM_MISC);
+		if (partitioning == HSW_DATA_BUF_PART_1_2)
+			val &= ~WM_MISC_DATA_PARTITION_5_6;
+		else
+			val |= WM_MISC_DATA_PARTITION_5_6;
+		I915_WRITE(WM_MISC, val);
 	}
 
-	sandybridge_update_wm(dev);
+	if (previous.wm_lp_spr[0] != results->wm_lp_spr[0])
+		I915_WRITE(WM1S_LP_ILK, results->wm_lp_spr[0]);
+	if (previous.wm_lp_spr[1] != results->wm_lp_spr[1])
+		I915_WRITE(WM2S_LP_IVB, results->wm_lp_spr[1]);
+	if (previous.wm_lp_spr[2] != results->wm_lp_spr[2])
+		I915_WRITE(WM3S_LP_IVB, results->wm_lp_spr[2]);
+
+	if (results->wm_lp[0] != 0)
+		I915_WRITE(WM1_LP_ILK, results->wm_lp[0]);
+	if (results->wm_lp[1] != 0)
+		I915_WRITE(WM2_LP_ILK, results->wm_lp[1]);
+	if (results->wm_lp[2] != 0)
+		I915_WRITE(WM3_LP_ILK, results->wm_lp[2]);
+}
+
+static void haswell_update_wm(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct hsw_pipe_wm_parameters params[3];
+	struct hsw_wm_values results;
+	uint32_t wm[5];
+
+	hsw_compute_wm_parameters(dev, params, wm);
+	hsw_compute_wm_results(dev, params, wm, &results);
+	hsw_write_wm_values(dev_priv, &results, HSW_DATA_BUF_PART_1_2);
 }
 
 static void haswell_update_sprite_wm(struct drm_device *dev, int pipe,

From cca32e9ad372172c808b93eebff536459ce37d85 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 31 May 2013 11:45:06 -0300
Subject: [PATCH 54/70] drm/i915: properly set HSW WM_LP watermarks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We were previously only setting the WM_PIPE registers, now we are
setting the LP watermark registers. This should allow deeper PC
states, resulting in power savings.

We're only using 1/2 data buffer partitioning for now.

v2: Merge both hsw_compute_pri_wm_* functions (Ville)
v3: - Simplify hsw_compute_wm_results (Ville)
    - Rebase due to changes on the previous patch
v4: Unconfuse wm_lp/level (Ville)

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_reg.h |   4 +
 drivers/gpu/drm/i915/intel_pm.c | 179 ++++++++++++++++++++++++++++----
 2 files changed, 165 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 19021bd8b030..e00422128a0a 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3100,6 +3100,10 @@
 #define WM3S_LP_IVB		0x45128
 #define  WM1S_LP_EN		(1<<31)
 
+#define HSW_WM_LP_VAL(lat, fbc, pri, cur) \
+	(WM3_LP_EN | ((lat) << WM1_LP_LATENCY_SHIFT) | \
+	 ((fbc) << WM1_LP_FBC_SHIFT) | ((pri) << WM1_LP_SR_SHIFT) | (cur))
+
 /* Memory latency timer register */
 #define MLTR_ILK		0x11222
 #define  MLTR_WM1_SHIFT		0
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index fda727921748..1373552732e6 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2129,6 +2129,12 @@ 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,
+			   uint8_t bytes_per_pixel)
+{
+	return DIV_ROUND_UP(pri_val * 64, horiz_pixels * bytes_per_pixel) + 2;
+}
+
 struct hsw_pipe_wm_parameters {
 	bool active;
 	bool sprite_enabled;
@@ -2142,11 +2148,28 @@ struct hsw_pipe_wm_parameters {
 	uint32_t pixel_rate;
 };
 
+struct hsw_wm_maximums {
+	uint16_t pri;
+	uint16_t spr;
+	uint16_t cur;
+	uint16_t fbc;
+};
+
+struct hsw_lp_wm_result {
+	bool enable;
+	bool fbc_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];
 	uint32_t wm_lp_spr[3];
 	uint32_t wm_linetime[3];
+	bool enable_fbc_wm;
 };
 
 enum hsw_data_buf_partitioning {
@@ -2154,17 +2177,31 @@ enum hsw_data_buf_partitioning {
 	HSW_DATA_BUF_PART_5_6,
 };
 
-/* Only for WM_PIPE. */
-static uint32_t hsw_compute_pri_wm_pipe(struct hsw_pipe_wm_parameters *params,
-					uint32_t mem_value)
+/* For both WM_PIPE and WM_LP. */
+static uint32_t hsw_compute_pri_wm(struct hsw_pipe_wm_parameters *params,
+				   uint32_t mem_value,
+				   bool is_lp)
 {
+	uint32_t method1, method2;
+
 	/* TODO: for now, assume the primary plane is always enabled. */
 	if (!params->active)
 		return 0;
 
-	return hsw_wm_method1(params->pixel_rate,
-			      params->pri_bytes_per_pixel,
-			      mem_value);
+	method1 = hsw_wm_method1(params->pixel_rate,
+				 params->pri_bytes_per_pixel,
+				 mem_value);
+
+	if (!is_lp)
+		return method1;
+
+	method2 = hsw_wm_method2(params->pixel_rate,
+				 params->pipe_htotal,
+				 params->pri_horiz_pixels,
+				 params->pri_bytes_per_pixel,
+				 mem_value);
+
+	return min(method1, method2);
 }
 
 /* For both WM_PIPE and WM_LP. */
@@ -2201,13 +2238,60 @@ static uint32_t hsw_compute_cur_wm(struct hsw_pipe_wm_parameters *params,
 			      mem_value);
 }
 
+/* Only for WM_LP. */
+static uint32_t hsw_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,
+			  params->pri_horiz_pixels,
+			  params->pri_bytes_per_pixel);
+}
+
+static bool hsw_compute_lp_wm(uint32_t mem_value, 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];
+
+		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);
+	}
+
+	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]);
+
+	if (result->fbc_val > max->fbc) {
+		result->fbc_enable = false;
+		result->fbc_val = 0;
+	} else {
+		result->fbc_enable = true;
+	}
+
+	result->enable = result->pri_val <= max->pri &&
+			 result->spr_val <= max->spr &&
+			 result->cur_val <= max->cur;
+	return result->enable;
+}
+
 static uint32_t hsw_compute_wm_pipe(struct drm_i915_private *dev_priv,
 				    uint32_t mem_value, enum pipe pipe,
 				    struct hsw_pipe_wm_parameters *params)
 {
 	uint32_t pri_val, cur_val, spr_val;
 
-	pri_val = hsw_compute_pri_wm_pipe(params, mem_value);
+	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);
 
@@ -2250,13 +2334,15 @@ 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)
+				      uint32_t *wm,
+				      struct hsw_wm_maximums *lp_max_1_2)
 {
 	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;
@@ -2278,6 +2364,8 @@ static void hsw_compute_wm_parameters(struct drm_device *dev,
 		if (!p->active)
 			continue;
 
+		pipes_active++;
+
 		p->pipe_htotal = intel_crtc->config.adjusted_mode.htotal;
 		p->pixel_rate = hsw_wm_get_pixel_rate(dev, crtc);
 		p->pri_bytes_per_pixel = crtc->fb->bits_per_pixel / 8;
@@ -2297,25 +2385,66 @@ static void hsw_compute_wm_parameters(struct drm_device *dev,
 		p->sprite_enabled = intel_plane->wm.enable;
 		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++;
 	}
+
+	if (pipes_active > 1) {
+		lp_max_1_2->pri = sprites_enabled ? 128 : 256;
+		lp_max_1_2->spr = 128;
+		lp_max_1_2->cur = 64;
+	} else {
+		lp_max_1_2->pri = sprites_enabled ? 384 : 768;
+		lp_max_1_2->spr = 384;
+		lp_max_1_2->cur = 255;
+	}
+	lp_max_1_2->fbc = 15;
 }
 
 static void hsw_compute_wm_results(struct drm_device *dev,
 				   struct hsw_pipe_wm_parameters *params,
 				   uint32_t *wm,
+				   struct hsw_wm_maximums *lp_maximums,
 				   struct hsw_wm_values *results)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc;
+	struct hsw_lp_wm_result lp_results[4] = {};
 	enum pipe pipe;
+	int level, max_level, wm_lp;
 
-	/* No support for LP WMs yet. */
-	results->wm_lp[2] = 0;
-	results->wm_lp[1] = 0;
-	results->wm_lp[0] = 0;
-	results->wm_lp_spr[2] = 0;
-	results->wm_lp_spr[1] = 0;
-	results->wm_lp_spr[0] = 0;
+	for (level = 1; level <= 4; level++)
+		if (!hsw_compute_lp_wm(wm[level], lp_maximums, params,
+				       &lp_results[level - 1]))
+			break;
+	max_level = level - 1;
+
+	/* The spec says it is preferred to disable FBC WMs instead of disabling
+	 * a WM level. */
+	results->enable_fbc_wm = true;
+	for (level = 1; level <= max_level; level++) {
+		if (!lp_results[level - 1].fbc_enable) {
+			results->enable_fbc_wm = false;
+			break;
+		}
+	}
+
+	memset(results, 0, sizeof(*results));
+	for (wm_lp = 1; wm_lp <= 3; wm_lp++) {
+		const struct hsw_lp_wm_result *r;
+
+		level = (max_level == 4 && wm_lp > 1) ? wm_lp + 1 : wm_lp;
+		if (level > max_level)
+			break;
+
+		r = &lp_results[level - 1];
+		results->wm_lp[wm_lp - 1] = HSW_WM_LP_VAL(level * 2,
+							  r->fbc_val,
+							  r->pri_val,
+							  r->cur_val);
+		results->wm_lp_spr[wm_lp - 1] = r->spr_val;
+	}
 
 	for_each_pipe(pipe)
 		results->wm_pipe[pipe] = hsw_compute_wm_pipe(dev_priv, wm[0],
@@ -2339,6 +2468,7 @@ static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
 	struct hsw_wm_values previous;
 	uint32_t val;
 	enum hsw_data_buf_partitioning prev_partitioning;
+	bool prev_enable_fbc_wm;
 
 	previous.wm_pipe[0] = I915_READ(WM0_PIPEA_ILK);
 	previous.wm_pipe[1] = I915_READ(WM0_PIPEB_ILK);
@@ -2356,6 +2486,8 @@ static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
 	prev_partitioning = (I915_READ(WM_MISC) & WM_MISC_DATA_PARTITION_5_6) ?
 			    HSW_DATA_BUF_PART_5_6 : HSW_DATA_BUF_PART_1_2;
 
+	prev_enable_fbc_wm = !(I915_READ(DISP_ARB_CTL) & DISP_FBC_WM_DIS);
+
 	if (memcmp(results->wm_pipe, previous.wm_pipe,
 		   sizeof(results->wm_pipe)) == 0 &&
 	    memcmp(results->wm_lp, previous.wm_lp,
@@ -2364,7 +2496,8 @@ static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
 		   sizeof(results->wm_lp_spr)) == 0 &&
 	    memcmp(results->wm_linetime, previous.wm_linetime,
 		   sizeof(results->wm_linetime)) == 0 &&
-	    partitioning == prev_partitioning)
+	    partitioning == prev_partitioning &&
+	    results->enable_fbc_wm == prev_enable_fbc_wm)
 		return;
 
 	if (previous.wm_lp[2] != 0)
@@ -2397,6 +2530,15 @@ static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
 		I915_WRITE(WM_MISC, val);
 	}
 
+	if (prev_enable_fbc_wm != results->enable_fbc_wm) {
+		val = I915_READ(DISP_ARB_CTL);
+		if (results->enable_fbc_wm)
+			val &= ~DISP_FBC_WM_DIS;
+		else
+			val |= DISP_FBC_WM_DIS;
+		I915_WRITE(DISP_ARB_CTL, val);
+	}
+
 	if (previous.wm_lp_spr[0] != results->wm_lp_spr[0])
 		I915_WRITE(WM1S_LP_ILK, results->wm_lp_spr[0]);
 	if (previous.wm_lp_spr[1] != results->wm_lp_spr[1])
@@ -2415,12 +2557,13 @@ static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
 static void haswell_update_wm(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct hsw_wm_maximums lp_max_1_2;
 	struct hsw_pipe_wm_parameters params[3];
 	struct hsw_wm_values results;
 	uint32_t wm[5];
 
-	hsw_compute_wm_parameters(dev, params, wm);
-	hsw_compute_wm_results(dev, params, wm, &results);
+	hsw_compute_wm_parameters(dev, params, wm, &lp_max_1_2);
+	hsw_compute_wm_results(dev, params, wm, &lp_max_1_2, &results);
 	hsw_write_wm_values(dev_priv, &results, HSW_DATA_BUF_PART_1_2);
 }
 

From 861f3389c6627460bcd19d1442eb650001f15c9b Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 31 May 2013 10:19:21 -0300
Subject: [PATCH 55/70] drm/i915: add support for 5/6 data buffer partitioning
 on Haswell
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now we compute the results for both 1/2 and 5/6 partitioning and then
use hsw_find_best_result to choose which one to use.

With this patch, Haswell watermarks support should be in good shape.
The only improvement we're missing is the case where the primary plane
is disabled: we always assume it's enabled, so we take it into
consideration when calculating the watermarks.

v2: - Check the latency when finding the best result

Signed-off-by: Paulo Zanoni <paulo.r.zanoni@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 | 64 +++++++++++++++++++++++++++------
 1 file changed, 53 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 1373552732e6..b676b578f70f 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2335,7 +2335,8 @@ 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,
-				      struct hsw_wm_maximums *lp_max_1_2)
+				      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;
@@ -2391,15 +2392,17 @@ static void hsw_compute_wm_parameters(struct drm_device *dev,
 	}
 
 	if (pipes_active > 1) {
-		lp_max_1_2->pri = sprites_enabled ? 128 : 256;
-		lp_max_1_2->spr = 128;
-		lp_max_1_2->cur = 64;
+		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_1_2->cur = 255;
+		lp_max_5_6->spr = 640;
+		lp_max_1_2->cur = lp_max_5_6->cur = 255;
 	}
-	lp_max_1_2->fbc = 15;
+	lp_max_1_2->fbc = lp_max_5_6->fbc = 15;
 }
 
 static void hsw_compute_wm_results(struct drm_device *dev,
@@ -2457,6 +2460,32 @@ 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)
+{
+	int i, val_r1 = 0, val_r2 = 0;
+
+	for (i = 0; i < 3; i++) {
+		if (r1->wm_lp[i] & WM3_LP_EN)
+			val_r1 = r1->wm_lp[i] & WM1_LP_LATENCY_MASK;
+		if (r2->wm_lp[i] & WM3_LP_EN)
+			val_r2 = r2->wm_lp[i] & WM1_LP_LATENCY_MASK;
+	}
+
+	if (val_r1 == val_r2) {
+		if (r2->enable_fbc_wm && !r1->enable_fbc_wm)
+			return r2;
+		else
+			return r1;
+	} else if (val_r1 > val_r2) {
+		return r1;
+	} else {
+		return r2;
+	}
+}
+
 /*
  * The spec says we shouldn't write when we don't need, because every write
  * causes WMs to be re-evaluated, expending some power.
@@ -2557,14 +2586,27 @@ static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
 static void haswell_update_wm(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct hsw_wm_maximums lp_max_1_2;
+	struct hsw_wm_maximums lp_max_1_2, lp_max_5_6;
 	struct hsw_pipe_wm_parameters params[3];
-	struct hsw_wm_values results;
+	struct hsw_wm_values results_1_2, results_5_6, *best_results;
 	uint32_t wm[5];
+	enum hsw_data_buf_partitioning partitioning;
 
-	hsw_compute_wm_parameters(dev, params, wm, &lp_max_1_2);
-	hsw_compute_wm_results(dev, params, wm, &lp_max_1_2, &results);
-	hsw_write_wm_values(dev_priv, &results, HSW_DATA_BUF_PART_1_2);
+	hsw_compute_wm_parameters(dev, params, wm, &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) {
+		hsw_compute_wm_results(dev, params, wm, &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;
+	}
+
+	partitioning = (best_results == &results_1_2) ?
+		       HSW_DATA_BUF_PART_1_2 : HSW_DATA_BUF_PART_5_6;
+
+	hsw_write_wm_values(dev_priv, best_results, partitioning);
 }
 
 static void haswell_update_sprite_wm(struct drm_device *dev, int pipe,

From baf02a1fb0485b0cca8666241577b4ef87914d87 Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Tue, 28 May 2013 19:22:24 -0700
Subject: [PATCH 56/70] drm/i915: Create a more generic pm handler for hsw+

HSW has some special requirements for the VEBOX. Splitting out the
interrupt handler will make the code a bit nicer and less error prone
when we begin to handle those.

The slight functional change in this patch (queueing work while holding
the spinlock) is intentional as it makes a subsequent patch a bit nicer.
The change should also only effect HSW platforms.

Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_irq.c | 30 +++++++++++++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 338e726f4ef5..0f052f90f39a 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -842,6 +842,7 @@ static void snb_gt_irq_handler(struct drm_device *dev,
 		ivybridge_handle_parity_error(dev);
 }
 
+/* Legacy way of handling PM interrupts */
 static void gen6_queue_rps_work(struct drm_i915_private *dev_priv,
 				u32 pm_iir)
 {
@@ -921,6 +922,31 @@ static void dp_aux_irq_handler(struct drm_device *dev)
 	wake_up_all(&dev_priv->gmbus_wait_queue);
 }
 
+/* Unlike gen6_queue_rps_work() from which this function is originally derived,
+ * we must be able to deal with other PM interrupts. This is complicated because
+ * of the way in which we use the masks to defer the RPS work (which for
+ * posterity is necessary because of forcewake).
+ */
+static void hsw_pm_irq_handler(struct drm_i915_private *dev_priv,
+			       u32 pm_iir)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev_priv->rps.lock, flags);
+	dev_priv->rps.pm_iir |= pm_iir & GEN6_PM_DEFERRED_EVENTS;
+	if (dev_priv->rps.pm_iir) {
+		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_DEFERRED_EVENTS);
+		/* TODO: if queue_work is slow, move it out of the spinlock */
+		queue_work(dev_priv->wq, &dev_priv->rps.work);
+	}
+	spin_unlock_irqrestore(&dev_priv->rps.lock, flags);
+
+	if (pm_iir & ~GEN6_PM_DEFERRED_EVENTS)
+		DRM_ERROR("Unexpected PM interrupted\n");
+}
+
 static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = (struct drm_device *) arg;
@@ -1231,7 +1257,9 @@ static irqreturn_t ivybridge_irq_handler(int irq, void *arg)
 
 	pm_iir = I915_READ(GEN6_PMIIR);
 	if (pm_iir) {
-		if (pm_iir & GEN6_PM_DEFERRED_EVENTS)
+		if (IS_HASWELL(dev))
+			hsw_pm_irq_handler(dev_priv, pm_iir);
+		else if (pm_iir & GEN6_PM_DEFERRED_EVENTS)
 			gen6_queue_rps_work(dev_priv, pm_iir);
 		I915_WRITE(GEN6_PMIIR, pm_iir);
 		ret = IRQ_HANDLED;

From 7d99163da69e04ccae0b52093f716167ed71d66d Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Tue, 28 May 2013 19:22:25 -0700
Subject: [PATCH 57/70] drm/i915: Create an ivybridge_irq_preinstall

Just duplicates ironlake_irq_preinstall for now.

v2: Add new PCH_NOP check (Damien)
Add SDEIMR comment (Damien)

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Update now outdated comment.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_irq.c | 35 +++++++++++++++++++++++++++++++--
 1 file changed, 33 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 0f052f90f39a..5d5bb8ce0fb4 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2491,6 +2491,37 @@ static void ironlake_irq_preinstall(struct drm_device *dev)
 	I915_WRITE(GTIER, 0x0);
 	POSTING_READ(GTIER);
 
+	/* south display irq */
+	I915_WRITE(SDEIMR, 0xffffffff);
+	/*
+	 * SDEIER is also touched by the interrupt handler to work around missed
+	 * PCH interrupts. Hence we can't update it after the interrupt handler
+	 * is enabled - instead we unconditionally enable all PCH interrupt
+	 * sources here, but then only unmask them as needed with SDEIMR.
+	 */
+	I915_WRITE(SDEIER, 0xffffffff);
+	POSTING_READ(SDEIER);
+}
+
+static void ivybridge_irq_preinstall(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
+
+	atomic_set(&dev_priv->irq_received, 0);
+
+	I915_WRITE(HWSTAM, 0xeffe);
+
+	/* XXX hotplug from PCH */
+
+	I915_WRITE(DEIMR, 0xffffffff);
+	I915_WRITE(DEIER, 0x0);
+	POSTING_READ(DEIER);
+
+	/* and GT */
+	I915_WRITE(GTIMR, 0xffffffff);
+	I915_WRITE(GTIER, 0x0);
+	POSTING_READ(GTIER);
+
 	if (HAS_PCH_NOP(dev))
 		return;
 
@@ -3494,9 +3525,9 @@ void intel_irq_init(struct drm_device *dev)
 		dev->driver->disable_vblank = valleyview_disable_vblank;
 		dev_priv->display.hpd_irq_setup = i915_hpd_irq_setup;
 	} else if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev)) {
-		/* Share pre & uninstall handlers with ILK/SNB */
+		/* Share uninstall handlers with ILK/SNB */
 		dev->driver->irq_handler = ivybridge_irq_handler;
-		dev->driver->irq_preinstall = ironlake_irq_preinstall;
+		dev->driver->irq_preinstall = ivybridge_irq_preinstall;
 		dev->driver->irq_postinstall = ivybridge_irq_postinstall;
 		dev->driver->irq_uninstall = ironlake_irq_uninstall;
 		dev->driver->enable_vblank = ivybridge_enable_vblank;

From eda63ffb906c2fb3b609a0e87aeb63c0f25b9e6b Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Tue, 28 May 2013 19:22:26 -0700
Subject: [PATCH 58/70] drm/i915: Add PM regs to pre/post install

At the moment, these values are wiped out anyway by the rps
enable/disable. That will be changed in the next patch though.

v2: Add post install setup to address issue found by Damien in the next
patch.
replaced
WARN_ON(dev_priv->rps.pm_iir != 0);
with rps.pm_iir = 0;

With the v2 of this patch and the deferred pm enabling (which changed
since the original patches) we're now able to get PM interrupts before
we've brought up enabled rps. At this point in boot, we don't want to do
anything about it, so we simply ignore it. Since writing the original
assertion, the code has changed quite a bit, and I believe removing this
assertion is perfectly safe.

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: I don't agree with the justification to drop the WARN and
added a FIXME to that effect.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_irq.c | 10 ++++++++++
 drivers/gpu/drm/i915/intel_pm.c |  4 +++-
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 5d5bb8ce0fb4..b7e096008a9f 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2522,6 +2522,11 @@ static void ivybridge_irq_preinstall(struct drm_device *dev)
 	I915_WRITE(GTIER, 0x0);
 	POSTING_READ(GTIER);
 
+	/* Power management */
+	I915_WRITE(GEN6_PMIMR, 0xffffffff);
+	I915_WRITE(GEN6_PMIER, 0x0);
+	POSTING_READ(GEN6_PMIER);
+
 	if (HAS_PCH_NOP(dev))
 		return;
 
@@ -2710,6 +2715,11 @@ static int ivybridge_irq_postinstall(struct drm_device *dev)
 	I915_WRITE(GTIER, render_irqs);
 	POSTING_READ(GTIER);
 
+	/* Power management */
+	I915_WRITE(GEN6_PMIMR, ~GEN6_PM_DEFERRED_EVENTS);
+	I915_WRITE(GEN6_PMIER, GEN6_PM_DEFERRED_EVENTS);
+	POSTING_READ(GEN6_PMIMR);
+
 	ibx_irq_postinstall(dev);
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index b676b578f70f..b1d0d0366fdf 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3309,7 +3309,9 @@ static void gen6_enable_rps(struct drm_device *dev)
 	/* requires MSI enabled */
 	I915_WRITE(GEN6_PMIER, GEN6_PM_DEFERRED_EVENTS);
 	spin_lock_irq(&dev_priv->rps.lock);
-	WARN_ON(dev_priv->rps.pm_iir != 0);
+	/* 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, 0);
 	spin_unlock_irq(&dev_priv->rps.lock);
 	/* enable all PM interrupts */

From 4848405cced3b46f4ec7d404b8ed5873171ae10a Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Tue, 28 May 2013 19:22:27 -0700
Subject: [PATCH 59/70] drm/i915: make PM interrupt writes non-destructive

PM interrupts have an expanded role on HSW. It helps route the EBOX
interrupts. This patch is necessary to make the existing code which
touches the mask, and enable registers more friendly to other code paths
that also will need these registers.

To be more explicit:
At preinstall all interrupts are masked and disabled. This implies that
preinstall should always happen before any enabling/disabling of RPS or
other interrupts.

The PMIMR is touched by the workqueue, so enable/disable touch IER and
IIR. Similarly, the code currently expects IMR has no use outside of the
RPS related interrupts so they unconditionally set 0, or ~0. We could
use IER in the workqueue, and IMR elsewhere, but since the workqueue
use-case is more transient the existing usage makes sense.

Disable RPS events:
IER := IER & ~GEN6_PM_RPS_EVENTS // Disable RPS related interrupts
IIR := GEN6_PM_RPS_EVENTS // Disable any outstanding interrupts

Enable RPS events:
IER := IER | GEN6_PM_RPS_EVENTS // Enable the RPS related interrupts
IIR := GEN6_PM_RPS_EVENTS // Make sure there were no leftover events
(really shouldn't happen)

v2: Shouldn't destroy PMIIR or PMIMR VEBOX interrupt state in
enable/disable rps functions (Haihao)

v3: Bug found by Chris where we were clearing the wrong bits at rps
disable.
    expanded commit message

v4: v3 was based off the wrong branch

v5: Added the setting of PMIMR because of previous patch update

CC: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_irq.c | 21 +++++++++++----------
 drivers/gpu/drm/i915/i915_reg.h |  2 +-
 drivers/gpu/drm/i915/intel_pm.c | 13 +++++++------
 3 files changed, 19 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index b7e096008a9f..953060dc9ff0 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -700,10 +700,11 @@ static void gen6_pm_rps_work(struct work_struct *work)
 	pm_iir = dev_priv->rps.pm_iir;
 	dev_priv->rps.pm_iir = 0;
 	pm_imr = I915_READ(GEN6_PMIMR);
-	I915_WRITE(GEN6_PMIMR, 0);
+	/* 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);
 
-	if ((pm_iir & GEN6_PM_DEFERRED_EVENTS) == 0)
+	if ((pm_iir & GEN6_PM_RPS_EVENTS) == 0)
 		return;
 
 	mutex_lock(&dev_priv->rps.hw_lock);
@@ -933,17 +934,17 @@ static void hsw_pm_irq_handler(struct drm_i915_private *dev_priv,
 	unsigned long flags;
 
 	spin_lock_irqsave(&dev_priv->rps.lock, flags);
-	dev_priv->rps.pm_iir |= pm_iir & GEN6_PM_DEFERRED_EVENTS;
+	dev_priv->rps.pm_iir |= pm_iir & GEN6_PM_RPS_EVENTS;
 	if (dev_priv->rps.pm_iir) {
 		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_DEFERRED_EVENTS);
+		WARN_ON(I915_READ_NOTRACE(GEN6_PMIMR) & ~GEN6_PM_RPS_EVENTS);
 		/* TODO: if queue_work is slow, move it out of the spinlock */
 		queue_work(dev_priv->wq, &dev_priv->rps.work);
 	}
 	spin_unlock_irqrestore(&dev_priv->rps.lock, flags);
 
-	if (pm_iir & ~GEN6_PM_DEFERRED_EVENTS)
+	if (pm_iir & ~GEN6_PM_RPS_EVENTS)
 		DRM_ERROR("Unexpected PM interrupted\n");
 }
 
@@ -1018,7 +1019,7 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 		if (pipe_stats[0] & PIPE_GMBUS_INTERRUPT_STATUS)
 			gmbus_irq_handler(dev);
 
-		if (pm_iir & GEN6_PM_DEFERRED_EVENTS)
+		if (pm_iir & GEN6_PM_RPS_EVENTS)
 			gen6_queue_rps_work(dev_priv, pm_iir);
 
 		I915_WRITE(GTIIR, gt_iir);
@@ -1259,7 +1260,7 @@ static irqreturn_t ivybridge_irq_handler(int irq, void *arg)
 	if (pm_iir) {
 		if (IS_HASWELL(dev))
 			hsw_pm_irq_handler(dev_priv, pm_iir);
-		else if (pm_iir & GEN6_PM_DEFERRED_EVENTS)
+		else if (pm_iir & GEN6_PM_RPS_EVENTS)
 			gen6_queue_rps_work(dev_priv, pm_iir);
 		I915_WRITE(GEN6_PMIIR, pm_iir);
 		ret = IRQ_HANDLED;
@@ -1374,7 +1375,7 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	if (IS_GEN5(dev) &&  de_iir & DE_PCU_EVENT)
 		ironlake_handle_rps_change(dev);
 
-	if (IS_GEN6(dev) && pm_iir & GEN6_PM_DEFERRED_EVENTS)
+	if (IS_GEN6(dev) && pm_iir & GEN6_PM_RPS_EVENTS)
 		gen6_queue_rps_work(dev_priv, pm_iir);
 
 	I915_WRITE(GTIIR, gt_iir);
@@ -2716,8 +2717,8 @@ static int ivybridge_irq_postinstall(struct drm_device *dev)
 	POSTING_READ(GTIER);
 
 	/* Power management */
-	I915_WRITE(GEN6_PMIMR, ~GEN6_PM_DEFERRED_EVENTS);
-	I915_WRITE(GEN6_PMIER, GEN6_PM_DEFERRED_EVENTS);
+	I915_WRITE(GEN6_PMIMR, ~GEN6_PM_RPS_EVENTS);
+	I915_WRITE(GEN6_PMIER, GEN6_PM_RPS_EVENTS);
 	POSTING_READ(GEN6_PMIMR);
 
 	ibx_irq_postinstall(dev);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index e00422128a0a..8fced1914178 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4566,7 +4566,7 @@
 #define  GEN6_PM_RP_DOWN_THRESHOLD		(1<<4)
 #define  GEN6_PM_RP_UP_EI_EXPIRED		(1<<2)
 #define  GEN6_PM_RP_DOWN_EI_EXPIRED		(1<<1)
-#define  GEN6_PM_DEFERRED_EVENTS		(GEN6_PM_RP_UP_THRESHOLD | \
+#define  GEN6_PM_RPS_EVENTS			(GEN6_PM_RP_UP_THRESHOLD | \
 						 GEN6_PM_RP_DOWN_THRESHOLD | \
 						 GEN6_PM_RP_DOWN_TIMEOUT)
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index b1d0d0366fdf..49a188718f9d 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3116,7 +3116,7 @@ static void gen6_disable_rps(struct drm_device *dev)
 	I915_WRITE(GEN6_RC_CONTROL, 0);
 	I915_WRITE(GEN6_RPNSWREQ, 1 << 31);
 	I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
-	I915_WRITE(GEN6_PMIER, 0);
+	I915_WRITE(GEN6_PMIER, I915_READ(GEN6_PMIER) & ~GEN6_PM_RPS_EVENTS);
 	/* 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
@@ -3126,7 +3126,7 @@ static void gen6_disable_rps(struct drm_device *dev)
 	dev_priv->rps.pm_iir = 0;
 	spin_unlock_irq(&dev_priv->rps.lock);
 
-	I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR));
+	I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS);
 }
 
 static void valleyview_disable_rps(struct drm_device *dev)
@@ -3307,14 +3307,15 @@ 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, GEN6_PM_DEFERRED_EVENTS);
+	I915_WRITE(GEN6_PMIER, I915_READ(GEN6_PMIER) | GEN6_PM_RPS_EVENTS);
 	spin_lock_irq(&dev_priv->rps.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, 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);
-	/* enable all PM interrupts */
+	/* unmask all PM interrupts */
 	I915_WRITE(GEN6_PMINTRMSK, 0);
 
 	rc6vids = 0;
@@ -3577,7 +3578,7 @@ static void valleyview_enable_rps(struct drm_device *dev)
 	valleyview_set_rps(dev_priv->dev, rpe);
 
 	/* requires MSI enabled */
-	I915_WRITE(GEN6_PMIER, GEN6_PM_DEFERRED_EVENTS);
+	I915_WRITE(GEN6_PMIER, GEN6_PM_RPS_EVENTS);
 	spin_lock_irq(&dev_priv->rps.lock);
 	WARN_ON(dev_priv->rps.pm_iir != 0);
 	I915_WRITE(GEN6_PMIMR, 0);

From aeb0659338793746b8a4e482fa588ba1dd9ee559 Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Tue, 28 May 2013 19:22:28 -0700
Subject: [PATCH 60/70] drm/i915: Convert irq_refounct to struct

It's overkill on older gens, but it's useful for newer gens.

Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 16 ++++++++--------
 drivers/gpu/drm/i915/intel_ringbuffer.h |  4 +++-
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 89dfc63677ad..c7a89bb051a0 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -795,7 +795,7 @@ gen5_ring_get_irq(struct intel_ring_buffer *ring)
 		return false;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (ring->irq_refcount++ == 0) {
+	if (ring->irq_refcount.gt++ == 0) {
 		dev_priv->gt_irq_mask &= ~ring->irq_enable_mask;
 		I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
 		POSTING_READ(GTIMR);
@@ -813,7 +813,7 @@ gen5_ring_put_irq(struct intel_ring_buffer *ring)
 	unsigned long flags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (--ring->irq_refcount == 0) {
+	if (--ring->irq_refcount.gt == 0) {
 		dev_priv->gt_irq_mask |= ring->irq_enable_mask;
 		I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
 		POSTING_READ(GTIMR);
@@ -832,7 +832,7 @@ i9xx_ring_get_irq(struct intel_ring_buffer *ring)
 		return false;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (ring->irq_refcount++ == 0) {
+	if (ring->irq_refcount.gt++ == 0) {
 		dev_priv->irq_mask &= ~ring->irq_enable_mask;
 		I915_WRITE(IMR, dev_priv->irq_mask);
 		POSTING_READ(IMR);
@@ -850,7 +850,7 @@ i9xx_ring_put_irq(struct intel_ring_buffer *ring)
 	unsigned long flags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (--ring->irq_refcount == 0) {
+	if (--ring->irq_refcount.gt == 0) {
 		dev_priv->irq_mask |= ring->irq_enable_mask;
 		I915_WRITE(IMR, dev_priv->irq_mask);
 		POSTING_READ(IMR);
@@ -869,7 +869,7 @@ i8xx_ring_get_irq(struct intel_ring_buffer *ring)
 		return false;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (ring->irq_refcount++ == 0) {
+	if (ring->irq_refcount.gt++ == 0) {
 		dev_priv->irq_mask &= ~ring->irq_enable_mask;
 		I915_WRITE16(IMR, dev_priv->irq_mask);
 		POSTING_READ16(IMR);
@@ -887,7 +887,7 @@ i8xx_ring_put_irq(struct intel_ring_buffer *ring)
 	unsigned long flags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (--ring->irq_refcount == 0) {
+	if (--ring->irq_refcount.gt == 0) {
 		dev_priv->irq_mask |= ring->irq_enable_mask;
 		I915_WRITE16(IMR, dev_priv->irq_mask);
 		POSTING_READ16(IMR);
@@ -980,7 +980,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 	gen6_gt_force_wake_get(dev_priv);
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (ring->irq_refcount++ == 0) {
+	if (ring->irq_refcount.gt++ == 0) {
 		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring, ~(ring->irq_enable_mask |
 						GEN6_RENDER_L3_PARITY_ERROR));
@@ -1003,7 +1003,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 	unsigned long flags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	if (--ring->irq_refcount == 0) {
+	if (--ring->irq_refcount.gt == 0) {
 		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring, ~GEN6_RENDER_L3_PARITY_ERROR);
 		else
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 1c79520c7e45..153b87f67aae 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -72,7 +72,9 @@ struct  intel_ring_buffer {
 	 */
 	u32		last_retired_head;
 
-	u32		irq_refcount;		/* protected by dev_priv->irq_lock */
+	struct {
+		u32	gt;
+	} irq_refcount;	/* protected by dev_priv->irq_lock */
 	u32		irq_enable_mask;	/* bitmask to enable ring interrupt */
 	u32		trace_irq_seqno;
 	u32		sync_seqno[I915_NUM_RINGS-1];

From cc609d5da5c78c92a2e2565604b2603a0965b494 Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Tue, 28 May 2013 19:22:29 -0700
Subject: [PATCH 61/70] drm/i915: consolidate interrupt naming scheme

The motivation here is we're going to add some new interrupt definitions
and handling outside of the GT interrupts which is all we've managed so
far (with some RPS exceptions). By consolidating the names in the future
we can make thing a bit cleaner as we don't need to define register
names twice, and we can leverage pretty decent overlap in HW registers
since ILK.

To explain briefly what is in the comments: there are two sets of
interrupt masking/enabling registers. At least so far, the definitions
of the two sets overlap. The old code setup distinct names for
interrupts in each set, ie. one for global, and one for ring. This made
things confusing when using the wrong defines in the wrong places.

rebase: Modified VLV bits

v2: Renamed GT_RENDER_MASTER to GT_RENDER_CS_MASTER (Damien)

Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_irq.c         |  61 +++++++-------
 drivers/gpu/drm/i915/i915_reg.h         | 101 ++++++++++--------------
 drivers/gpu/drm/i915/intel_ringbuffer.c |  21 ++---
 3 files changed, 85 insertions(+), 98 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 953060dc9ff0..90ed599611cb 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -780,7 +780,7 @@ static void ivybridge_parity_work(struct work_struct *work)
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	dev_priv->gt_irq_mask &= ~GT_GEN7_L3_PARITY_ERROR_INTERRUPT;
+	dev_priv->gt_irq_mask &= ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
 	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
@@ -812,7 +812,7 @@ static void ivybridge_handle_parity_error(struct drm_device *dev)
 		return;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	dev_priv->gt_irq_mask |= GT_GEN7_L3_PARITY_ERROR_INTERRUPT;
+	dev_priv->gt_irq_mask |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
 	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
@@ -824,22 +824,22 @@ static void snb_gt_irq_handler(struct drm_device *dev,
 			       u32 gt_iir)
 {
 
-	if (gt_iir & (GEN6_RENDER_USER_INTERRUPT |
-		      GEN6_RENDER_PIPE_CONTROL_NOTIFY_INTERRUPT))
+	if (gt_iir &
+	    (GT_RENDER_USER_INTERRUPT | GT_RENDER_PIPECTL_NOTIFY_INTERRUPT))
 		notify_ring(dev, &dev_priv->ring[RCS]);
-	if (gt_iir & GEN6_BSD_USER_INTERRUPT)
+	if (gt_iir & GT_BSD_USER_INTERRUPT)
 		notify_ring(dev, &dev_priv->ring[VCS]);
-	if (gt_iir & GEN6_BLITTER_USER_INTERRUPT)
+	if (gt_iir & GT_BLT_USER_INTERRUPT)
 		notify_ring(dev, &dev_priv->ring[BCS]);
 
-	if (gt_iir & (GT_GEN6_BLT_CS_ERROR_INTERRUPT |
-		      GT_GEN6_BSD_CS_ERROR_INTERRUPT |
-		      GT_RENDER_CS_ERROR_INTERRUPT)) {
+	if (gt_iir & (GT_BLT_CS_ERROR_INTERRUPT |
+		      GT_BSD_CS_ERROR_INTERRUPT |
+		      GT_RENDER_CS_MASTER_ERROR_INTERRUPT)) {
 		DRM_ERROR("GT error interrupt 0x%08x\n", gt_iir);
 		i915_handle_error(dev, false);
 	}
 
-	if (gt_iir & GT_GEN7_L3_PARITY_ERROR_INTERRUPT)
+	if (gt_iir & GT_RENDER_L3_PARITY_ERROR_INTERRUPT)
 		ivybridge_handle_parity_error(dev);
 }
 
@@ -1283,9 +1283,10 @@ static void ilk_gt_irq_handler(struct drm_device *dev,
 			       struct drm_i915_private *dev_priv,
 			       u32 gt_iir)
 {
-	if (gt_iir & (GT_USER_INTERRUPT | GT_PIPE_NOTIFY))
+	if (gt_iir &
+	    (GT_RENDER_USER_INTERRUPT | GT_RENDER_PIPECTL_NOTIFY_INTERRUPT))
 		notify_ring(dev, &dev_priv->ring[RCS]);
-	if (gt_iir & GT_BSD_USER_INTERRUPT)
+	if (gt_iir & ILK_BSD_USER_INTERRUPT)
 		notify_ring(dev, &dev_priv->ring[VCS]);
 }
 
@@ -2640,7 +2641,7 @@ 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 render_irqs;
+	u32 gt_irqs;
 
 	dev_priv->irq_mask = ~display_mask;
 
@@ -2655,17 +2656,15 @@ static int ironlake_irq_postinstall(struct drm_device *dev)
 	I915_WRITE(GTIIR, I915_READ(GTIIR));
 	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
 
+	gt_irqs = GT_RENDER_USER_INTERRUPT;
+
 	if (IS_GEN6(dev))
-		render_irqs =
-			GT_USER_INTERRUPT |
-			GEN6_BSD_USER_INTERRUPT |
-			GEN6_BLITTER_USER_INTERRUPT;
+		gt_irqs |= GT_BLT_USER_INTERRUPT | GT_BSD_USER_INTERRUPT;
 	else
-		render_irqs =
-			GT_USER_INTERRUPT |
-			GT_PIPE_NOTIFY |
-			GT_BSD_USER_INTERRUPT;
-	I915_WRITE(GTIER, render_irqs);
+		gt_irqs |= GT_RENDER_PIPECTL_NOTIFY_INTERRUPT |
+			   ILK_BSD_USER_INTERRUPT;
+
+	I915_WRITE(GTIER, gt_irqs);
 	POSTING_READ(GTIER);
 
 	ibx_irq_postinstall(dev);
@@ -2691,7 +2690,7 @@ static int ivybridge_irq_postinstall(struct drm_device *dev)
 		DE_PLANEA_FLIP_DONE_IVB |
 		DE_AUX_CHANNEL_A_IVB |
 		DE_ERR_INT_IVB;
-	u32 render_irqs;
+	u32 gt_irqs;
 
 	dev_priv->irq_mask = ~display_mask;
 
@@ -2706,14 +2705,14 @@ static int ivybridge_irq_postinstall(struct drm_device *dev)
 		   DE_PIPEA_VBLANK_IVB);
 	POSTING_READ(DEIER);
 
-	dev_priv->gt_irq_mask = ~GT_GEN7_L3_PARITY_ERROR_INTERRUPT;
+	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);
 
-	render_irqs = GT_USER_INTERRUPT | GEN6_BSD_USER_INTERRUPT |
-		GEN6_BLITTER_USER_INTERRUPT | GT_GEN7_L3_PARITY_ERROR_INTERRUPT;
-	I915_WRITE(GTIER, render_irqs);
+	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);
 
 	/* Power management */
@@ -2729,9 +2728,9 @@ 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;
-	u32 render_irqs;
 
 	enable_mask = I915_DISPLAY_PORT_INTERRUPT;
 	enable_mask |= I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
@@ -2767,9 +2766,9 @@ static int valleyview_irq_postinstall(struct drm_device *dev)
 	I915_WRITE(GTIIR, I915_READ(GTIIR));
 	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
 
-	render_irqs = GT_USER_INTERRUPT | GEN6_BSD_USER_INTERRUPT |
-		GEN6_BLITTER_USER_INTERRUPT;
-	I915_WRITE(GTIER, render_irqs);
+	gt_irqs = GT_RENDER_USER_INTERRUPT | GT_BSD_USER_INTERRUPT |
+		GT_BLT_USER_INTERRUPT;
+	I915_WRITE(GTIER, gt_irqs);
 	POSTING_READ(GTIER);
 
 	/* ack & enable invalid PTE error interrupts */
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 8fced1914178..bdb2c1734da8 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -742,24 +742,6 @@
 #define VLV_IMR		(VLV_DISPLAY_BASE + 0x20a8)
 #define VLV_ISR		(VLV_DISPLAY_BASE + 0x20ac)
 #define VLV_PCBR	(VLV_DISPLAY_BASE + 0x2120)
-#define   I915_PIPE_CONTROL_NOTIFY_INTERRUPT		(1<<18)
-#define   I915_DISPLAY_PORT_INTERRUPT			(1<<17)
-#define   I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT	(1<<15)
-#define   I915_GMCH_THERMAL_SENSOR_EVENT_INTERRUPT	(1<<14) /* p-state */
-#define   I915_HWB_OOM_INTERRUPT			(1<<13)
-#define   I915_SYNC_STATUS_INTERRUPT			(1<<12)
-#define   I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT	(1<<11)
-#define   I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT	(1<<10)
-#define   I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT	(1<<9)
-#define   I915_DISPLAY_PLANE_C_FLIP_PENDING_INTERRUPT	(1<<8)
-#define   I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT		(1<<7)
-#define   I915_DISPLAY_PIPE_A_EVENT_INTERRUPT		(1<<6)
-#define   I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT		(1<<5)
-#define   I915_DISPLAY_PIPE_B_EVENT_INTERRUPT		(1<<4)
-#define   I915_DEBUG_INTERRUPT				(1<<2)
-#define   I915_USER_INTERRUPT				(1<<1)
-#define   I915_ASLE_INTERRUPT				(1<<0)
-#define   I915_BSD_USER_INTERRUPT                      (1<<25)
 #define   DISPLAY_PLANE_FLIP_PENDING(plane) (1<<(11-(plane))) /* A and B only */
 #define EIR		0x020b0
 #define EMR		0x020b4
@@ -871,28 +853,6 @@
 #define CACHE_MODE_1		0x7004 /* IVB+ */
 #define   PIXEL_SUBSPAN_COLLECT_OPT_DISABLE (1<<6)
 
-/* GEN6 interrupt control
- * Note that the per-ring interrupt bits do alias with the global interrupt bits
- * in GTIMR. */
-#define GEN6_RENDER_HWSTAM	0x2098
-#define GEN6_RENDER_IMR		0x20a8
-#define   GEN6_RENDER_CONTEXT_SWITCH_INTERRUPT		(1 << 8)
-#define   GEN6_RENDER_PPGTT_PAGE_FAULT			(1 << 7)
-#define   GEN6_RENDER_TIMEOUT_COUNTER_EXPIRED		(1 << 6)
-#define   GEN6_RENDER_L3_PARITY_ERROR			(1 << 5)
-#define   GEN6_RENDER_PIPE_CONTROL_NOTIFY_INTERRUPT	(1 << 4)
-#define   GEN6_RENDER_COMMAND_PARSER_MASTER_ERROR	(1 << 3)
-#define   GEN6_RENDER_SYNC_STATUS			(1 << 2)
-#define   GEN6_RENDER_DEBUG_INTERRUPT			(1 << 1)
-#define   GEN6_RENDER_USER_INTERRUPT			(1 << 0)
-
-#define GEN6_BLITTER_HWSTAM	0x22098
-#define GEN6_BLITTER_IMR	0x220a8
-#define   GEN6_BLITTER_MI_FLUSH_DW_NOTIFY_INTERRUPT	(1 << 26)
-#define   GEN6_BLITTER_COMMAND_PARSER_MASTER_ERROR	(1 << 25)
-#define   GEN6_BLITTER_SYNC_STATUS			(1 << 24)
-#define   GEN6_BLITTER_USER_INTERRUPT			(1 << 22)
-
 #define GEN6_BLITTER_ECOSKPD	0x221d0
 #define   GEN6_BLITTER_LOCK_SHIFT			16
 #define   GEN6_BLITTER_FBC_NOTIFY			(1<<3)
@@ -903,9 +863,49 @@
 #define   GEN6_BSD_SLEEP_INDICATOR	(1 << 3)
 #define   GEN6_BSD_GO_INDICATOR		(1 << 4)
 
-#define GEN6_BSD_HWSTAM			0x12098
-#define GEN6_BSD_IMR			0x120a8
-#define   GEN6_BSD_USER_INTERRUPT	(1 << 12)
+/* On modern GEN architectures interrupt control consists of two sets
+ * of registers. The first set pertains to the ring generating the
+ * interrupt. The second control is for the functional block generating the
+ * interrupt. These are PM, GT, DE, etc.
+ *
+ * Luckily *knocks on wood* all the ring interrupt bits match up with the
+ * GT interrupt bits, so we don't need to duplicate the defines.
+ *
+ * These defines should cover us well from SNB->HSW with minor exceptions
+ * it can also work on ILK.
+ */
+#define GT_BLT_FLUSHDW_NOTIFY_INTERRUPT		(1 << 26)
+#define GT_BLT_CS_ERROR_INTERRUPT		(1 << 25)
+#define GT_BLT_USER_INTERRUPT			(1 << 22)
+#define GT_BSD_CS_ERROR_INTERRUPT		(1 << 15)
+#define GT_BSD_USER_INTERRUPT			(1 << 12)
+#define GT_RENDER_L3_PARITY_ERROR_INTERRUPT	(1 <<  5) /* !snb */
+#define GT_RENDER_PIPECTL_NOTIFY_INTERRUPT	(1 <<  4)
+#define GT_RENDER_CS_MASTER_ERROR_INTERRUPT	(1 <<  3)
+#define GT_RENDER_SYNC_STATUS_INTERRUPT		(1 <<  2)
+#define GT_RENDER_DEBUG_INTERRUPT		(1 <<  1)
+#define GT_RENDER_USER_INTERRUPT		(1 <<  0)
+
+/* These are all the "old" interrupts */
+#define ILK_BSD_USER_INTERRUPT				(1<<5)
+#define I915_PIPE_CONTROL_NOTIFY_INTERRUPT		(1<<18)
+#define I915_DISPLAY_PORT_INTERRUPT			(1<<17)
+#define I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT	(1<<15)
+#define I915_GMCH_THERMAL_SENSOR_EVENT_INTERRUPT	(1<<14) /* p-state */
+#define I915_HWB_OOM_INTERRUPT				(1<<13)
+#define I915_SYNC_STATUS_INTERRUPT			(1<<12)
+#define I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT	(1<<11)
+#define I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT	(1<<10)
+#define I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT	(1<<9)
+#define I915_DISPLAY_PLANE_C_FLIP_PENDING_INTERRUPT	(1<<8)
+#define I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT		(1<<7)
+#define I915_DISPLAY_PIPE_A_EVENT_INTERRUPT		(1<<6)
+#define I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT		(1<<5)
+#define I915_DISPLAY_PIPE_B_EVENT_INTERRUPT		(1<<4)
+#define I915_DEBUG_INTERRUPT				(1<<2)
+#define I915_USER_INTERRUPT				(1<<1)
+#define I915_ASLE_INTERRUPT				(1<<0)
+#define I915_BSD_USER_INTERRUPT				(1 << 25)
 
 #define GEN6_BSD_RNCID			0x12198
 
@@ -3714,21 +3714,6 @@
 #define DEIIR   0x44008
 #define DEIER   0x4400c
 
-/* GT interrupt.
- * Note that for gen6+ the ring-specific interrupt bits do alias with the
- * corresponding bits in the per-ring interrupt control registers. */
-#define GT_GEN6_BLT_FLUSHDW_NOTIFY_INTERRUPT	(1 << 26)
-#define GT_GEN6_BLT_CS_ERROR_INTERRUPT		(1 << 25)
-#define GT_GEN6_BLT_USER_INTERRUPT		(1 << 22)
-#define GT_GEN6_BSD_CS_ERROR_INTERRUPT		(1 << 15)
-#define GT_GEN6_BSD_USER_INTERRUPT		(1 << 12)
-#define GT_BSD_USER_INTERRUPT			(1 << 5) /* ilk only */
-#define GT_GEN7_L3_PARITY_ERROR_INTERRUPT	(1 << 5)
-#define GT_PIPE_NOTIFY				(1 << 4)
-#define GT_RENDER_CS_ERROR_INTERRUPT		(1 << 3)
-#define GT_SYNC_STATUS				(1 << 2)
-#define GT_USER_INTERRUPT			(1 << 0)
-
 #define GTISR   0x44010
 #define GTIMR   0x44014
 #define GTIIR   0x44018
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index c7a89bb051a0..5ab8cc2cafe2 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -560,7 +560,7 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
 	if (HAS_L3_GPU_CACHE(dev))
-		I915_WRITE_IMR(ring, ~GEN6_RENDER_L3_PARITY_ERROR);
+		I915_WRITE_IMR(ring, ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
 
 	return ret;
 }
@@ -982,8 +982,9 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (ring->irq_refcount.gt++ == 0) {
 		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
-			I915_WRITE_IMR(ring, ~(ring->irq_enable_mask |
-						GEN6_RENDER_L3_PARITY_ERROR));
+			I915_WRITE_IMR(ring,
+				       ~(ring->irq_enable_mask |
+					 GT_RENDER_L3_PARITY_ERROR_INTERRUPT));
 		else
 			I915_WRITE_IMR(ring, ~ring->irq_enable_mask);
 		dev_priv->gt_irq_mask &= ~ring->irq_enable_mask;
@@ -1005,7 +1006,8 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount.gt == 0) {
 		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
-			I915_WRITE_IMR(ring, ~GEN6_RENDER_L3_PARITY_ERROR);
+			I915_WRITE_IMR(ring,
+				       ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
 		else
 			I915_WRITE_IMR(ring, ~0);
 		dev_priv->gt_irq_mask |= ring->irq_enable_mask;
@@ -1682,7 +1684,7 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 			ring->flush = gen6_render_ring_flush;
 		ring->irq_get = gen6_ring_get_irq;
 		ring->irq_put = gen6_ring_put_irq;
-		ring->irq_enable_mask = GT_USER_INTERRUPT;
+		ring->irq_enable_mask = GT_RENDER_USER_INTERRUPT;
 		ring->get_seqno = gen6_ring_get_seqno;
 		ring->set_seqno = ring_set_seqno;
 		ring->sync_to = gen6_ring_sync;
@@ -1701,7 +1703,8 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 		ring->set_seqno = pc_render_set_seqno;
 		ring->irq_get = gen5_ring_get_irq;
 		ring->irq_put = gen5_ring_put_irq;
-		ring->irq_enable_mask = GT_USER_INTERRUPT | GT_PIPE_NOTIFY;
+		ring->irq_enable_mask = GT_RENDER_USER_INTERRUPT |
+					GT_RENDER_PIPECTL_NOTIFY_INTERRUPT;
 	} else {
 		ring->add_request = i9xx_add_request;
 		if (INTEL_INFO(dev)->gen < 4)
@@ -1843,7 +1846,7 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 		ring->add_request = gen6_add_request;
 		ring->get_seqno = gen6_ring_get_seqno;
 		ring->set_seqno = ring_set_seqno;
-		ring->irq_enable_mask = GEN6_BSD_USER_INTERRUPT;
+		ring->irq_enable_mask = GT_BSD_USER_INTERRUPT;
 		ring->irq_get = gen6_ring_get_irq;
 		ring->irq_put = gen6_ring_put_irq;
 		ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
@@ -1863,7 +1866,7 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 		ring->get_seqno = ring_get_seqno;
 		ring->set_seqno = ring_set_seqno;
 		if (IS_GEN5(dev)) {
-			ring->irq_enable_mask = GT_BSD_USER_INTERRUPT;
+			ring->irq_enable_mask = ILK_BSD_USER_INTERRUPT;
 			ring->irq_get = gen5_ring_get_irq;
 			ring->irq_put = gen5_ring_put_irq;
 		} else {
@@ -1892,7 +1895,7 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 	ring->add_request = gen6_add_request;
 	ring->get_seqno = gen6_ring_get_seqno;
 	ring->set_seqno = ring_set_seqno;
-	ring->irq_enable_mask = GEN6_BLITTER_USER_INTERRUPT;
+	ring->irq_enable_mask = GT_BLT_USER_INTERRUPT;
 	ring->irq_get = gen6_ring_get_irq;
 	ring->irq_put = gen6_ring_put_irq;
 	ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;

From a19d2933cbc4c7b8e3d72e9fd2d48847c25bb41d Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Tue, 28 May 2013 19:22:30 -0700
Subject: [PATCH 62/70] drm/i915: vebox interrupt get/put

v2: Use the correct lock to protect PM interrupt regs, this was
accidentally lost from earlier (Haihao)
Fix return types (Ben)

Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 46 +++++++++++++++++++++++--
 drivers/gpu/drm/i915/intel_ringbuffer.h |  5 +--
 2 files changed, 47 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 5ab8cc2cafe2..8a6a0ee6d350 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1019,6 +1019,48 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 	gen6_gt_force_wake_put(dev_priv);
 }
 
+static bool
+hsw_vebox_get_irq(struct intel_ring_buffer *ring)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned long flags;
+
+	if (!dev->irq_enabled)
+		return false;
+
+	spin_lock_irqsave(&dev_priv->rps.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);
+
+	return true;
+}
+
+static void
+hsw_vebox_put_irq(struct intel_ring_buffer *ring)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned long flags;
+
+	if (!dev->irq_enabled)
+		return;
+
+	spin_lock_irqsave(&dev_priv->rps.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);
+}
+
 static int
 i965_dispatch_execbuffer(struct intel_ring_buffer *ring,
 			 u32 offset, u32 length,
@@ -1928,8 +1970,8 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev)
 	ring->get_seqno = gen6_ring_get_seqno;
 	ring->set_seqno = ring_set_seqno;
 	ring->irq_enable_mask = 0;
-	ring->irq_get = NULL;
-	ring->irq_put = NULL;
+	ring->irq_get = hsw_vebox_get_irq;
+	ring->irq_put = hsw_vebox_put_irq;
 	ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
 	ring->sync_to = gen6_ring_sync;
 	ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_VER;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 153b87f67aae..022d07e43d12 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -73,8 +73,9 @@ struct  intel_ring_buffer {
 	u32		last_retired_head;
 
 	struct {
-		u32	gt;
-	} irq_refcount;	/* protected by dev_priv->irq_lock */
+		u32	gt; /*  protected by dev_priv->irq_lock */
+		u32	pm; /*  protected by dev_priv->rps.lock (sucks) */
+	} irq_refcount;
 	u32		irq_enable_mask;	/* bitmask to enable ring interrupt */
 	u32		trace_irq_seqno;
 	u32		sync_seqno[I915_NUM_RINGS-1];

From 12638c57f31952127c734c26315e1348fa1334c2 Mon Sep 17 00:00:00 2001
From: Ben Widawsky <ben@bwidawsk.net>
Date: Tue, 28 May 2013 19:22:31 -0700
Subject: [PATCH 63/70] drm/i915: Enable vebox interrupts

Similar to a patch originally written by:

v2: Reversed the meanings of masked and enabled (Haihao)
Made non-destructive writes in case enable/disabler rps runs first
(Haihao)

v3: Reword error message (Damien)
Modify postinstall to do the right thing based on previous fixup. (Ben)

CC: Xiang, Haihao <haihao.xiang@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_irq.c         | 31 ++++++++++++++++++++-----
 drivers/gpu/drm/i915/i915_reg.h         |  3 +++
 drivers/gpu/drm/i915/intel_ringbuffer.c |  3 ++-
 3 files changed, 30 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 90ed599611cb..e17bbe201195 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -944,8 +944,15 @@ static void hsw_pm_irq_handler(struct drm_i915_private *dev_priv,
 	}
 	spin_unlock_irqrestore(&dev_priv->rps.lock, flags);
 
-	if (pm_iir & ~GEN6_PM_RPS_EVENTS)
-		DRM_ERROR("Unexpected PM interrupted\n");
+	if (pm_iir & ~GEN6_PM_RPS_EVENTS) {
+		if (pm_iir & PM_VEBOX_USER_INTERRUPT)
+			notify_ring(dev_priv->dev, &dev_priv->ring[VECS]);
+
+		if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT) {
+			DRM_ERROR("VEBOX CS error interrupt 0x%08x\n", pm_iir);
+			i915_handle_error(dev_priv->dev, false);
+		}
+	}
 }
 
 static irqreturn_t valleyview_irq_handler(int irq, void *arg)
@@ -2690,6 +2697,7 @@ 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;
@@ -2715,10 +2723,21 @@ static int ivybridge_irq_postinstall(struct drm_device *dev)
 	I915_WRITE(GTIER, gt_irqs);
 	POSTING_READ(GTIER);
 
-	/* Power management */
-	I915_WRITE(GEN6_PMIMR, ~GEN6_PM_RPS_EVENTS);
-	I915_WRITE(GEN6_PMIER, GEN6_PM_RPS_EVENTS);
-	POSTING_READ(GEN6_PMIMR);
+	I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR));
+	if (HAS_VEBOX(dev))
+		pm_irqs |= PM_VEBOX_USER_INTERRUPT |
+			PM_VEBOX_CS_ERROR_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);
 
 	ibx_irq_postinstall(dev);
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index bdb2c1734da8..89fac19d3249 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -886,6 +886,9 @@
 #define GT_RENDER_DEBUG_INTERRUPT		(1 <<  1)
 #define GT_RENDER_USER_INTERRUPT		(1 <<  0)
 
+#define PM_VEBOX_CS_ERROR_INTERRUPT		(1 << 12) /* hsw+ */
+#define PM_VEBOX_USER_INTERRUPT			(1 << 10) /* hsw+ */
+
 /* These are all the "old" interrupts */
 #define ILK_BSD_USER_INTERRUPT				(1<<5)
 #define I915_PIPE_CONTROL_NOTIFY_INTERRUPT		(1<<18)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 8a6a0ee6d350..0e72da6ad0fa 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1969,7 +1969,8 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev)
 	ring->add_request = gen6_add_request;
 	ring->get_seqno = gen6_ring_get_seqno;
 	ring->set_seqno = ring_set_seqno;
-	ring->irq_enable_mask = 0;
+	ring->irq_enable_mask = PM_VEBOX_USER_INTERRUPT |
+		PM_VEBOX_CS_ERROR_INTERRUPT;
 	ring->irq_get = hsw_vebox_get_irq;
 	ring->irq_put = hsw_vebox_put_irq;
 	ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;

From 9010ebfd2b803ebab6c2fc70b9004b2a59e7937a Mon Sep 17 00:00:00 2001
From: "Xiang, Haihao" <haihao.xiang@intel.com>
Date: Wed, 29 May 2013 09:22:36 -0700
Subject: [PATCH 64/70] drm/i915: add VEBOX into debugfs

v2: Removed rebase relic VECS ring from i915_gem_request_info (Damien)

v3: s/hsw/hws in debugfs which I introduced in v2 (Jon)

Signed-off-by: Xiang, Haihao <haihao.xiang@intel.com>
[Order changed, and modified by]
CC:  "Bloomfield, Jon" <jon.bloomfield@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_debugfs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 2eb572afbcd3..2b4a6fa6350e 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -570,6 +570,7 @@ static const char *ring_str(int ring)
 	case RCS: return "render";
 	case VCS: return "bsd";
 	case BCS: return "blt";
+	case VECS: return "vebox";
 	default: return "";
 	}
 }
@@ -2222,6 +2223,7 @@ static struct drm_info_list i915_debugfs_list[] = {
 	{"i915_gem_hws", i915_hws_info, 0, (void *)RCS},
 	{"i915_gem_hws_blt", i915_hws_info, 0, (void *)BCS},
 	{"i915_gem_hws_bsd", i915_hws_info, 0, (void *)VCS},
+	{"i915_gem_hws_vebox", i915_hws_info, 0, (void *)VECS},
 	{"i915_rstdby_delays", i915_rstdby_delays, 0},
 	{"i915_cur_delayinfo", i915_cur_delayinfo, 0},
 	{"i915_delayfreq_table", i915_delayfreq_table, 0},

From 82f91b6e93e2138c7e02b5a866f63d04cf040c86 Mon Sep 17 00:00:00 2001
From: "Xiang, Haihao" <haihao.xiang@intel.com>
Date: Tue, 28 May 2013 19:22:33 -0700
Subject: [PATCH 65/70] drm/i915: add I915_EXEC_VEBOX to
 i915_gem_do_execbuffer()

A user can run batchbuffer via VEBOX ring.

Signed-off-by: Xiang, Haihao <haihao.xiang@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 9 +++++++++
 include/uapi/drm/i915_drm.h                | 1 +
 2 files changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 117ce3813681..a8bb62ca8756 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -885,6 +885,15 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 			return -EPERM;
 		}
 		break;
+	case I915_EXEC_VEBOX:
+		ring = &dev_priv->ring[VECS];
+		if (ctx_id != 0) {
+			DRM_DEBUG("Ring %s doesn't support contexts\n",
+				  ring->name);
+			return -EPERM;
+		}
+		break;
+
 	default:
 		DRM_DEBUG("execbuf with unknown ring: %d\n",
 			  (int)(args->flags & I915_EXEC_RING_MASK));
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 07d59419fe6b..81b99817198e 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -660,6 +660,7 @@ struct drm_i915_gem_execbuffer2 {
 #define I915_EXEC_RENDER                 (1<<0)
 #define I915_EXEC_BSD                    (2<<0)
 #define I915_EXEC_BLT                    (3<<0)
+#define I915_EXEC_VEBOX                  (4<<0)
 
 /* Used for switching the constants addressing mode on gen4+ RENDER ring.
  * Gen6+ only supports relative addressing to dynamic state (default) and

From a1f2cc73c762868435ae6ec9126bb2240337c61c Mon Sep 17 00:00:00 2001
From: "Xiang, Haihao" <haihao.xiang@intel.com>
Date: Tue, 28 May 2013 19:22:34 -0700
Subject: [PATCH 66/70] drm/i915: add I915_PARAM_HAS_VEBOX to i915_getparam

This will let userland only try to use the new ring
when the appropriate kernel is present

Signed-off-by: Xiang, Haihao <haihao.xiang@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_dma.c | 3 +++
 include/uapi/drm/i915_drm.h     | 2 +-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 3cd2b606aaba..03ee1936e737 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -956,6 +956,9 @@ static int i915_getparam(struct drm_device *dev, void *data,
 	case I915_PARAM_HAS_BLT:
 		value = intel_ring_initialized(&dev_priv->ring[BCS]);
 		break;
+	case I915_PARAM_HAS_VEBOX:
+		value = intel_ring_initialized(&dev_priv->ring[VECS]);
+		break;
 	case I915_PARAM_HAS_RELAXED_FENCING:
 		value = 1;
 		break;
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 81b99817198e..923ed7fe5775 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -305,7 +305,7 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_HAS_WAIT_TIMEOUT	 19
 #define I915_PARAM_HAS_SEMAPHORES	 20
 #define I915_PARAM_HAS_PRIME_VMAP_FLUSH	 21
-#define I915_PARAM_RSVD_FOR_FUTURE_USE	 22
+#define I915_PARAM_HAS_VEBOX		 22
 #define I915_PARAM_HAS_SECURE_BATCHES	 23
 #define I915_PARAM_HAS_PINNED_BATCHES	 24
 #define I915_PARAM_HAS_EXEC_NO_RELOC	 25

From e7a639c445e1f7c44adc1665539fa8e3af0b8e30 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Fri, 31 May 2013 17:49:17 +0200
Subject: [PATCH 67/70] drm/i915: fix up the edp power well check

Now that we track the cpu transcoder we need accurately in the pipe
config we can finally fix up the transcoder check. With the current
code eDP on port D will be broken since we'd errornously cut the
power.

For reference see

commit 2124b72e6283c4e84a55e71077fee91793f4c801
Author: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date:   Fri Mar 22 14:07:23 2013 -0300

    drm/i915: don't disable the power well yet

v2:
- Kill the now outdated comment (Paulo)
- Add the missing crtc->base.enabled check and consolidate it (Paulo)
- Smash all checks together, looks neater that way.

v3: Kill the unused encoder variable.

Cc: Takashi Iwai <tiwai@suse.de>
Cc: Paulo Zanoni <paulo.r.zanoni@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_display.c | 18 ++++--------------
 1 file changed, 4 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 161b064592af..2e2c6a370f52 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5793,23 +5793,13 @@ static void haswell_modeset_global_resources(struct drm_device *dev)
 {
 	bool enable = false;
 	struct intel_crtc *crtc;
-	struct intel_encoder *encoder;
 
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
-		if (crtc->pipe != PIPE_A && crtc->base.enabled)
-			enable = true;
-		/* XXX: Should check for edp transcoder here, but thanks to init
-		 * sequence that's not yet available. Just in case desktop eDP
-		 * on PORT D is possible on haswell, too. */
-		/* Even the eDP panel fitter is outside the always-on well. */
-		if (crtc->config.pch_pfit.size && crtc->base.enabled)
-			enable = true;
-	}
+		if (!crtc->base.enabled)
+			continue;
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
-			    base.head) {
-		if (encoder->type != INTEL_OUTPUT_EDP &&
-		    encoder->connectors_active)
+		if (crtc->pipe != PIPE_A || crtc->config.pch_pfit.size ||
+		    crtc->config.cpu_transcoder != TRANSCODER_EDP)
 			enable = true;
 	}
 

From 42db64efcd95014570835c7b0a08277c60486f07 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 31 May 2013 16:33:22 -0300
Subject: [PATCH 68/70] drm/i915: implement IPS feature

Intermediate Pixel Storage is a feature that should reduce the number
of times the display engine wakes up memory to read pixels, so it
should allow deeper PC states. IPS can only be enabled on ULT pipe A
with 8:8:8 pipe pixel formats.

With eDP 1920x1080 and correct watermarks but without FBC this moves
my PC7 residency from 2.5% to around 38%.

v2: - It's tied to pipe A, not port A
    - Add pipe_config support (Chris)
    - Add some assertions (Chris)
    - Rebase against latest dinq
v3: - Don't ever set ips_enabled to false (Daniel)
    - Only check for ips_enabled at hsw_disable_ips (Daniel)
v4: - Add hsw_compute_ips_config (Daniel)
    - Use the new dump_pipe_config (Daniel)

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_reg.h      | 11 ++++
 drivers/gpu/drm/i915/intel_display.c | 78 ++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/intel_drv.h     |  2 +
 3 files changed, 88 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 89fac19d3249..5a593d20036c 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1023,6 +1023,8 @@
 /* Framebuffer compression for Ivybridge */
 #define IVB_FBC_RT_BASE			0x7020
 
+#define IPS_CTL		0x43408
+#define   IPS_ENABLE	(1 << 31)
 
 #define _HSW_PIPE_SLICE_CHICKEN_1_A	0x420B0
 #define _HSW_PIPE_SLICE_CHICKEN_1_B	0x420B4
@@ -3666,6 +3668,15 @@
 #define _LGC_PALETTE_B           0x4a800
 #define LGC_PALETTE(pipe) _PIPE(pipe, _LGC_PALETTE_A, _LGC_PALETTE_B)
 
+#define _GAMMA_MODE_A		0x4a480
+#define _GAMMA_MODE_B		0x4ac80
+#define GAMMA_MODE(pipe) _PIPE(pipe, _GAMMA_MODE_A, _GAMMA_MODE_B)
+#define GAMMA_MODE_MODE_MASK	(3 << 0)
+#define GAMMA_MODE_MODE_8bit	(0 << 0)
+#define GAMMA_MODE_MODE_10bit	(1 << 0)
+#define GAMMA_MODE_MODE_12bit	(2 << 0)
+#define GAMMA_MODE_MODE_SPLIT	(3 << 0)
+
 /* interrupts */
 #define DE_MASTER_IRQ_CONTROL   (1 << 31)
 #define DE_SPRITEB_FLIP_DONE    (1 << 29)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 2e2c6a370f52..acfc6a164a59 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3242,6 +3242,42 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 	intel_wait_for_vblank(dev, intel_crtc->pipe);
 }
 
+/* IPS only exists on ULT machines and is tied to pipe A. */
+static bool hsw_crtc_supports_ips(struct intel_crtc *crtc)
+{
+	return IS_ULT(crtc->base.dev) && crtc->pipe == PIPE_A;
+}
+
+static void hsw_enable_ips(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+
+	if (!crtc->config.ips_enabled)
+		return;
+
+	/* We can only enable IPS after we enable a plane and wait for a vblank.
+	 * We guarantee that the plane is enabled by calling intel_enable_ips
+	 * only after intel_enable_plane. And intel_enable_plane already waits
+	 * for a vblank, so all we need to do here is to enable the IPS bit. */
+	assert_plane_enabled(dev_priv, crtc->plane);
+	I915_WRITE(IPS_CTL, IPS_ENABLE);
+}
+
+static void hsw_disable_ips(struct intel_crtc *crtc)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (!crtc->config.ips_enabled)
+		return;
+
+	assert_plane_enabled(dev_priv, crtc->plane);
+	I915_WRITE(IPS_CTL, 0);
+
+	/* We need to wait for a vblank before we can disable the plane. */
+	intel_wait_for_vblank(dev, crtc->pipe);
+}
+
 static void haswell_crtc_enable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
@@ -3289,6 +3325,8 @@ static void haswell_crtc_enable(struct drm_crtc *crtc)
 			  intel_crtc->config.has_pch_encoder);
 	intel_enable_plane(dev_priv, plane, pipe);
 
+	hsw_enable_ips(intel_crtc);
+
 	if (intel_crtc->config.has_pch_encoder)
 		lpt_pch_enable(crtc);
 
@@ -3431,6 +3469,8 @@ static void haswell_crtc_disable(struct drm_crtc *crtc)
 	if (dev_priv->cfb_plane == plane)
 		intel_disable_fbc(dev);
 
+	hsw_disable_ips(intel_crtc);
+
 	intel_disable_plane(dev_priv, plane, pipe);
 
 	if (intel_crtc->config.has_pch_encoder)
@@ -3991,11 +4031,19 @@ retry:
 	return setup_ok ? 0 : -EINVAL;
 }
 
+static void hsw_compute_ips_config(struct intel_crtc *crtc,
+				   struct intel_crtc_config *pipe_config)
+{
+	pipe_config->ips_enabled = hsw_crtc_supports_ips(crtc) &&
+				   pipe_config->pipe_bpp == 24;
+}
+
 static int intel_crtc_compute_config(struct drm_crtc *crtc,
 				     struct intel_crtc_config *pipe_config)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_display_mode *adjusted_mode = &pipe_config->adjusted_mode;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
 	if (HAS_PCH_SPLIT(dev)) {
 		/* FDI link clock is fixed at 2.7G */
@@ -4025,8 +4073,11 @@ static int intel_crtc_compute_config(struct drm_crtc *crtc,
 		pipe_config->pipe_bpp = 8*3;
 	}
 
+	if (IS_HASWELL(dev))
+		hsw_compute_ips_config(intel_crtc, pipe_config);
+
 	if (pipe_config->has_pch_encoder)
-		return ironlake_fdi_compute_config(to_intel_crtc(crtc), pipe_config);
+		return ironlake_fdi_compute_config(intel_crtc, pipe_config);
 
 	return 0;
 }
@@ -5932,6 +5983,9 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 	if (intel_display_power_enabled(dev, pfit_domain))
 		ironlake_get_pfit_config(crtc, pipe_config);
 
+	pipe_config->ips_enabled = hsw_crtc_supports_ips(crtc) &&
+				   (I915_READ(IPS_CTL) & IPS_ENABLE);
+
 	return true;
 }
 
@@ -6236,8 +6290,10 @@ void intel_crtc_load_lut(struct drm_crtc *crtc)
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int palreg = PALETTE(intel_crtc->pipe);
+	enum pipe pipe = intel_crtc->pipe;
+	int palreg = PALETTE(pipe);
 	int i;
+	bool reenable_ips = false;
 
 	/* The clocks have to be on to load the palette. */
 	if (!crtc->enabled || !intel_crtc->active)
@@ -6245,7 +6301,17 @@ void intel_crtc_load_lut(struct drm_crtc *crtc)
 
 	/* use legacy palette for Ironlake */
 	if (HAS_PCH_SPLIT(dev))
-		palreg = LGC_PALETTE(intel_crtc->pipe);
+		palreg = LGC_PALETTE(pipe);
+
+	/* Workaround : Do not read or write the pipe palette/gamma data while
+	 * GAMMA_MODE is configured for split gamma and IPS_CTL has IPS enabled.
+	 */
+	if (intel_crtc->config.ips_enabled &&
+	    ((I915_READ(GAMMA_MODE(pipe)) & GAMMA_MODE_MODE_MASK) ==
+	     GAMMA_MODE_MODE_SPLIT)) {
+		hsw_disable_ips(intel_crtc);
+		reenable_ips = true;
+	}
 
 	for (i = 0; i < 256; i++) {
 		I915_WRITE(palreg + 4 * i,
@@ -6253,6 +6319,9 @@ void intel_crtc_load_lut(struct drm_crtc *crtc)
 			   (intel_crtc->lut_g[i] << 8) |
 			   intel_crtc->lut_b[i]);
 	}
+
+	if (reenable_ips)
+		hsw_enable_ips(intel_crtc);
 }
 
 static void i845_update_cursor(struct drm_crtc *crtc, u32 base)
@@ -7680,6 +7749,7 @@ static void intel_dump_pipe_config(struct intel_crtc *crtc,
 	DRM_DEBUG_KMS("pch pfit: pos: 0x%08x, size: 0x%08x\n",
 		      pipe_config->pch_pfit.pos,
 		      pipe_config->pch_pfit.size);
+	DRM_DEBUG_KMS("ips: %i\n", pipe_config->ips_enabled);
 }
 
 static struct intel_crtc_config *
@@ -7996,6 +8066,8 @@ intel_pipe_config_compare(struct drm_device *dev,
 	PIPE_CONF_CHECK_I(pch_pfit.pos);
 	PIPE_CONF_CHECK_I(pch_pfit.size);
 
+	PIPE_CONF_CHECK_I(ips_enabled);
+
 #undef PIPE_CONF_CHECK_I
 #undef PIPE_CONF_CHECK_FLAGS
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index bb4c50b57085..fdf6303be0a9 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -268,6 +268,8 @@ struct intel_crtc_config {
 	/* FDI configuration, only valid if has_pch_encoder is set. */
 	int fdi_lanes;
 	struct intel_link_m_n fdi_m_n;
+
+	bool ips_enabled;
 };
 
 struct intel_crtc {

From 3c4ca58c12a3bf71433425df534dfbb85d8a5dc5 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 31 May 2013 16:33:23 -0300
Subject: [PATCH 69/70] drm/i915: add enable_ips module option

IPS is still enabled by default. Feature requested by the power
management team.

This should also help testing the feature on some early pre-production
hardware where there were relationship problems between IPS and PSR.

v2: Rebase on top of the newest IPS implementation.
v3: Check i915_enable_ips at compute_config, not supports_ips, so the
    kernel parameter will be ignored at haswell_get_pipe_config.

Requested-by: Kristen Accardi <kristen.c.accardi@intel.com>
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_drv.c      | 4 ++++
 drivers/gpu/drm/i915/i915_drv.h      | 1 +
 drivers/gpu/drm/i915/intel_display.c | 3 ++-
 3 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index a4e8f16a38e8..b23cd63b9fda 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -128,6 +128,10 @@ module_param_named(disable_power_well, i915_disable_power_well, int, 0600);
 MODULE_PARM_DESC(disable_power_well,
 		 "Disable the power well when possible (default: false)");
 
+int i915_enable_ips __read_mostly = 1;
+module_param_named(enable_ips, i915_enable_ips, int, 0600);
+MODULE_PARM_DESC(enable_ips, "Enable IPS (default: true)");
+
 static struct drm_driver driver;
 extern int intel_agp_enabled;
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a18da3c6c96e..be869f261993 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1470,6 +1470,7 @@ extern bool i915_enable_hangcheck __read_mostly;
 extern int i915_enable_ppgtt __read_mostly;
 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 int i915_suspend(struct drm_device *dev, pm_message_t state);
 extern int i915_resume(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index acfc6a164a59..c112466bb769 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -4034,7 +4034,8 @@ retry:
 static void hsw_compute_ips_config(struct intel_crtc *crtc,
 				   struct intel_crtc_config *pipe_config)
 {
-	pipe_config->ips_enabled = hsw_crtc_supports_ips(crtc) &&
+	pipe_config->ips_enabled = i915_enable_ips &&
+				   hsw_crtc_supports_ips(crtc) &&
 				   pipe_config->pipe_bpp == 24;
 }
 

From 92d44621ad2d083bc03920c904ca0a5eb10d9ded Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 31 May 2013 16:33:24 -0300
Subject: [PATCH 70/70] drm/i915: add i915_ips_status debugfs entry

It just prints whether it's supported/enabled/disabled. Feature
requested by the power management team.

v2: Checkpatch started complaining about seq_printf with 1 argument.

Requested-by: Kristen Accardi <kristen.c.accardi@intel.com>
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_debugfs.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 2b4a6fa6350e..76255a69752a 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1435,6 +1435,25 @@ static int i915_fbc_status(struct seq_file *m, void *unused)
 	return 0;
 }
 
+static int i915_ips_status(struct seq_file *m, void *unused)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (!IS_ULT(dev)) {
+		seq_puts(m, "not supported\n");
+		return 0;
+	}
+
+	if (I915_READ(IPS_CTL) & IPS_ENABLE)
+		seq_puts(m, "enabled\n");
+	else
+		seq_puts(m, "disabled\n");
+
+	return 0;
+}
+
 static int i915_sr_status(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
@@ -2233,6 +2252,7 @@ static struct drm_info_list i915_debugfs_list[] = {
 	{"i915_ring_freq_table", i915_ring_freq_table, 0},
 	{"i915_gfxec", i915_gfxec, 0},
 	{"i915_fbc_status", i915_fbc_status, 0},
+	{"i915_ips_status", i915_ips_status, 0},
 	{"i915_sr_status", i915_sr_status, 0},
 	{"i915_opregion", i915_opregion, 0},
 	{"i915_gem_framebuffer", i915_gem_framebuffer_info, 0},