drm/i915/bxt: Set DDI PHY lane latency optimization during modeset

So far we configured a static lane latency optimization during driver
loading/resuming. The specification changed at one point and now this
configuration depends on the lane count, so move the configuration
to modeset time accordingly.

It's not clear when this lane configuration takes effect. The
specification only requires that the programming is done before enabling
the port. On CHV OTOH the lanes start to power up already right after
enabling the PLL. To be safe preserve the current order and set things
up already before enabling the PLL.

v2: (Ander)
- Simplify the optimization mask calculation.
- Use the correct pipe_config always during the calculation instead
  of the bogus intel_crtc->config.

CC: Ander Conselvan de Oliveira <ander.conselvan.de.oliveira@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=95476Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>

drivers/gpu/drm/i915/intel_ddi.c

@@ -1789,8 +1789,7 @@ static void broxton_phy_wait_grc_done(struct drm_i915_private *dev_priv,
 
 void bxt_ddi_phy_init(struct drm_i915_private *dev_priv, enum dpio_phy phy)
 {
-	enum port port;
-	u32 ports, val;
+	u32 val;
 
 	if (bxt_ddi_phy_is_enabled(dev_priv, phy)) {
 		/* Still read out the GRC value for state verification */
@@ -1825,28 +1824,6 @@ void bxt_ddi_phy_init(struct drm_i915_private *dev_priv, enum dpio_phy phy)
 		DRM_ERROR("timeout during PHY%d power on\n", phy);
 	}
 
-	if (phy == DPIO_PHY0)
-		ports = BIT(PORT_B) | BIT(PORT_C);
-	else
-		ports = BIT(PORT_A);
-
-	for_each_port_masked(port, ports) {
-		int lane;
-
-		for (lane = 0; lane < 4; lane++) {
-			val = I915_READ(BXT_PORT_TX_DW14_LN(port, lane));
-			/*
-			 * Note that on CHV this flag is called UPAR, but has
-			 * the same function.
-			 */
-			val &= ~LATENCY_OPTIM;
-			if (lane != 1)
-				val |= LATENCY_OPTIM;
-
-			I915_WRITE(BXT_PORT_TX_DW14_LN(port, lane), val);
-		}
-	}
-
 	/* Program PLL Rcomp code offset */
 	val = I915_READ(BXT_PORT_CL1CM_DW9(phy));
 	val &= ~IREF0RC_OFFSET_MASK;
@@ -1956,8 +1933,6 @@ __phy_reg_verify_state(struct drm_i915_private *dev_priv, enum dpio_phy phy,
 bool bxt_ddi_phy_verify_state(struct drm_i915_private *dev_priv,
 			      enum dpio_phy phy)
 {
-	enum port port;
-	u32 ports;
 	uint32_t mask;
 	bool ok;
 
@@ -1970,21 +1945,6 @@ bool bxt_ddi_phy_verify_state(struct drm_i915_private *dev_priv,
 
 	ok = true;
 
-	if (phy == DPIO_PHY0)
-		ports = BIT(PORT_B) | BIT(PORT_C);
-	else
-		ports = BIT(PORT_A);
-
-	for_each_port_masked(port, ports) {
-		int lane;
-
-		for (lane = 0; lane < 4; lane++)
-			ok &= _CHK(BXT_PORT_TX_DW14_LN(port, lane),
-				    LATENCY_OPTIM,
-				    lane != 1 ? LATENCY_OPTIM : 0,
-				    "BXT_PORT_TX_DW14_LN(%d, %d)", port, lane);
-	}
-
 	/* PLL Rcomp code offset */
 	ok &= _CHK(BXT_PORT_CL1CM_DW9(phy),
 		    IREF0RC_OFFSET_MASK, 0xe4 << IREF0RC_OFFSET_SHIFT,
@@ -2028,6 +1988,67 @@ bool bxt_ddi_phy_verify_state(struct drm_i915_private *dev_priv,
 #undef _CHK
 }
 
+static uint8_t
+bxt_ddi_phy_calc_lane_lat_optim_mask(struct intel_encoder *encoder,
+				     struct intel_crtc_state *pipe_config)
+{
+	switch (pipe_config->lane_count) {
+	case 1:
+		return 0;
+	case 2:
+		return BIT(2) | BIT(0);
+	case 4:
+		return BIT(3) | BIT(2) | BIT(0);
+	default:
+		MISSING_CASE(pipe_config->lane_count);
+
+		return 0;
+	}
+}
+
+static void bxt_ddi_pre_pll_enable(struct intel_encoder *encoder)
+{
+	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct drm_i915_private *dev_priv = to_i915(dport->base.base.dev);
+	enum port port = dport->port;
+	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
+	int lane;
+
+	for (lane = 0; lane < 4; lane++) {
+		u32 val = I915_READ(BXT_PORT_TX_DW14_LN(port, lane));
+
+		/*
+		 * Note that on CHV this flag is called UPAR, but has
+		 * the same function.
+		 */
+		val &= ~LATENCY_OPTIM;
+		if (intel_crtc->config->lane_lat_optim_mask & BIT(lane))
+			val |= LATENCY_OPTIM;
+
+		I915_WRITE(BXT_PORT_TX_DW14_LN(port, lane), val);
+	}
+}
+
+static uint8_t
+bxt_ddi_phy_get_lane_lat_optim_mask(struct intel_encoder *encoder)
+{
+	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct drm_i915_private *dev_priv = to_i915(dport->base.base.dev);
+	enum port port = dport->port;
+	int lane;
+	uint8_t mask;
+
+	mask = 0;
+	for (lane = 0; lane < 4; lane++) {
+		u32 val = I915_READ(BXT_PORT_TX_DW14_LN(port, lane));
+
+		if (val & LATENCY_OPTIM)
+			mask |= BIT(lane);
+	}
+
+	return mask;
+}
+
 void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
@@ -2199,13 +2220,19 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 	}
 
 	intel_ddi_clock_get(encoder, pipe_config);
+
+	if (IS_BROXTON(dev_priv))
+		pipe_config->lane_lat_optim_mask =
+			bxt_ddi_phy_get_lane_lat_optim_mask(encoder);
 }
 
 static bool intel_ddi_compute_config(struct intel_encoder *encoder,
 				     struct intel_crtc_state *pipe_config)
 {
+	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
 	int type = encoder->type;
 	int port = intel_ddi_get_encoder_port(encoder);
+	int ret;
 
 	WARN(type == INTEL_OUTPUT_UNKNOWN, "compute_config() on unknown output!\n");
 
@@ -2213,9 +2240,17 @@ static bool intel_ddi_compute_config(struct intel_encoder *encoder,
 		pipe_config->cpu_transcoder = TRANSCODER_EDP;
 
 	if (type == INTEL_OUTPUT_HDMI)
-		return intel_hdmi_compute_config(encoder, pipe_config);
+		ret = intel_hdmi_compute_config(encoder, pipe_config);
 	else
-		return intel_dp_compute_config(encoder, pipe_config);
+		ret = intel_dp_compute_config(encoder, pipe_config);
+
+	if (IS_BROXTON(dev_priv) && ret)
+		pipe_config->lane_lat_optim_mask =
+			bxt_ddi_phy_calc_lane_lat_optim_mask(encoder,
+							     pipe_config);
+
+	return ret;
+
 }
 
 static const struct drm_encoder_funcs intel_ddi_funcs = {
@@ -2314,6 +2349,8 @@ void intel_ddi_init(struct drm_device *dev, enum port port)
 
 	intel_encoder->compute_config = intel_ddi_compute_config;
 	intel_encoder->enable = intel_enable_ddi;
+	if (IS_BROXTON(dev_priv))
+		intel_encoder->pre_pll_enable = bxt_ddi_pre_pll_enable;
 	intel_encoder->pre_enable = intel_ddi_pre_enable;
 	intel_encoder->disable = intel_disable_ddi;
 	intel_encoder->post_disable = intel_ddi_post_disable;

drivers/gpu/drm/i915/intel_display.c

@@ -4841,6 +4841,10 @@ static void haswell_crtc_enable(struct drm_crtc *crtc)
 		intel_set_pch_fifo_underrun_reporting(dev_priv, TRANSCODER_A,
 						      false);
 
+	for_each_encoder_on_crtc(dev, crtc, encoder)
+		if (encoder->pre_pll_enable)
+			encoder->pre_pll_enable(encoder);
+
 	if (intel_crtc->config->shared_dpll)
 		intel_enable_shared_dpll(intel_crtc);
 
@@ -12793,6 +12797,7 @@ intel_pipe_config_compare(struct drm_device *dev,
 
 	PIPE_CONF_CHECK_I(has_dp_encoder);
 	PIPE_CONF_CHECK_I(lane_count);
+	PIPE_CONF_CHECK_X(lane_lat_optim_mask);
 
 	if (INTEL_INFO(dev)->gen < 8) {
 		PIPE_CONF_CHECK_M_N(dp_m_n);

drivers/gpu/drm/i915/intel_drv.h

@@ -579,6 +579,12 @@ struct intel_crtc_state {
 
 	uint8_t lane_count;
 
+	/*
+	 * Used by platforms having DP/HDMI PHY with programmable lane
+	 * latency optimization.
+	 */
+	uint8_t lane_lat_optim_mask;
+
 	/* Panel fitter controls for gen2-gen4 + VLV */
 	struct {
 		u32 control;