Merge tag 'bdw-stage1-2013-11-08-v2' of git://people.freedesktop.org/~danvet/drm-intel into drm-next

So here's the Broadwell pull request. From a kernel driver pov there's
two areas with big changes in Broadwell:
- Completely new enumerated interrupt bits. On the plus side it now looks
  fairly unform and sane.
- Completely new pagetable layout.

To ensure minimal impact on existing platforms we've refactored both the
irq and low-level gtt handling code a lot in anticipation of the bdw push.
So now bdw enabling in these areas just plugs in a bunch of vfuncs.

Otherwise it's all fairly harmless adjusting of switch cases and
if-ladders to shovel bdw into the right blocks. So minimized impact on
existing platforms. I've also merged the bdw-stage1 branch into our
-nightly integration branch for the past week to make sure we don't break
anything.

Note that there's still quite a flurry or patches floating around, but
I've figured I'll push this out. I plan to keep the bdw fixes separate
from my usual -fixes stream so that you can reject them easily in case it
still looks like too much churn. Also, bdw is for now hidden behind the
preliminary hw enabling module option. So there's no real pressure to get
follow-up patches all into 3.13.

* tag 'bdw-stage1-2013-11-08-v2' of git://people.freedesktop.org/~danvet/drm-intel: (75 commits)
  drm/i915: Mask the vblank interrupt on bdw by default
  drm/i915: Wire up cpu fifo underrun reporting support for bdw
  drm/i915: Optimize gen8_enable|disable_vblank functions
  drm/i915: Wire up pipe CRC support for bdw
  drm/i915: Wire up PCH interrupts for bdw
  drm/i915: Wire up port A aux channel
  drm/i915: Fix up the bdw pipe interrupt enable lists
  drm/i915: Optimize pipe irq handling on bdw
  drm/i915/bdw: Take render error interrupt out of the mask
  drm/i915/bdw: Add BDW PCH check first
  drm/i915: Use hsw_crt_get_config on BDW
  drm/i915/bdw: Change dp aux timeout to 600us on DDIA
  drm/i915/bdw: Enable trickle feed on Broadwell
  drm/i915/bdw: WaSingleSubspanDispatchOnAALinesAndPoints
  drm/i915/bdw: conservative SBE VUE cache mode
  drm/i915/bdw: Limit SDE poly depth FIFO to 2
  drm/i915/bdw: Sampler power bypass disable
  ddrm/i915/bdw: Disable centroid pixel perf optimization
  drm/i915/bdw: BWGTLB clock gate disable
  drm/i915/bdw: Implement edp PSR workarounds
  ...

1 files changed, 55 insertions, 3 deletions

diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index f6fae35c568..f9883ceff94 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -93,7 +93,7 @@ static void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv)
 {
 	u32 forcewake_ack;
 
-	if (IS_HASWELL(dev_priv->dev))
+	if (IS_HASWELL(dev_priv->dev) || IS_GEN8(dev_priv->dev))
 		forcewake_ack = FORCEWAKE_ACK_HSW;
 	else
 		forcewake_ack = FORCEWAKE_MT_ACK;
@@ -112,7 +112,8 @@ static void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv)
 		DRM_ERROR("Timed out waiting for forcewake to ack request.\n");
 
 	/* WaRsForcewakeWaitTC0:ivb,hsw */
-	__gen6_gt_wait_for_thread_c0(dev_priv);
+	if (INTEL_INFO(dev_priv->dev)->gen < 8)
+		__gen6_gt_wait_for_thread_c0(dev_priv);
 }
 
 static void gen6_gt_check_fifodbg(struct drm_i915_private *dev_priv)
@@ -459,6 +460,46 @@ hsw_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace)
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); \
 }
 
+static const u32 gen8_shadowed_regs[] = {
+	FORCEWAKE_MT,
+	GEN6_RPNSWREQ,
+	GEN6_RC_VIDEO_FREQ,
+	RING_TAIL(RENDER_RING_BASE),
+	RING_TAIL(GEN6_BSD_RING_BASE),
+	RING_TAIL(VEBOX_RING_BASE),
+	RING_TAIL(BLT_RING_BASE),
+	/* TODO: Other registers are not yet used */
+};
+
+static bool is_gen8_shadowed(struct drm_i915_private *dev_priv, u32 reg)
+{
+	int i;
+	for (i = 0; i < ARRAY_SIZE(gen8_shadowed_regs); i++)
+		if (reg == gen8_shadowed_regs[i])
+			return true;
+
+	return false;
+}
+
+#define __gen8_write(x) \
+static void \
+gen8_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace) { \
+	bool __needs_put = !is_gen8_shadowed(dev_priv, reg); \
+	REG_WRITE_HEADER; \
+	if (__needs_put) { \
+		dev_priv->uncore.funcs.force_wake_get(dev_priv); \
+	} \
+	__raw_i915_write##x(dev_priv, reg, val); \
+	if (__needs_put) { \
+		dev_priv->uncore.funcs.force_wake_put(dev_priv); \
+	} \
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); \
+}
+
+__gen8_write(8)
+__gen8_write(16)
+__gen8_write(32)
+__gen8_write(64)
 __hsw_write(8)
 __hsw_write(16)
 __hsw_write(32)
@@ -476,6 +517,7 @@ __gen4_write(16)
 __gen4_write(32)
 __gen4_write(64)
 
+#undef __gen8_write
 #undef __hsw_write
 #undef __gen6_write
 #undef __gen5_write
@@ -492,7 +534,7 @@ void intel_uncore_init(struct drm_device *dev)
 	if (IS_VALLEYVIEW(dev)) {
 		dev_priv->uncore.funcs.force_wake_get = vlv_force_wake_get;
 		dev_priv->uncore.funcs.force_wake_put = vlv_force_wake_put;
-	} else if (IS_HASWELL(dev)) {
+	} else if (IS_HASWELL(dev) || IS_GEN8(dev)) {
 		dev_priv->uncore.funcs.force_wake_get = __gen6_gt_force_wake_mt_get;
 		dev_priv->uncore.funcs.force_wake_put = __gen6_gt_force_wake_mt_put;
 	} else if (IS_IVYBRIDGE(dev)) {
@@ -534,6 +576,16 @@ void intel_uncore_init(struct drm_device *dev)
 	}
 
 	switch (INTEL_INFO(dev)->gen) {
+	default:
+		dev_priv->uncore.funcs.mmio_writeb  = gen8_write8;
+		dev_priv->uncore.funcs.mmio_writew  = gen8_write16;
+		dev_priv->uncore.funcs.mmio_writel  = gen8_write32;
+		dev_priv->uncore.funcs.mmio_writeq  = gen8_write64;
+		dev_priv->uncore.funcs.mmio_readb  = gen6_read8;
+		dev_priv->uncore.funcs.mmio_readw  = gen6_read16;
+		dev_priv->uncore.funcs.mmio_readl  = gen6_read32;
+		dev_priv->uncore.funcs.mmio_readq  = gen6_read64;
+		break;
 	case 7:
 	case 6:
 		if (IS_HASWELL(dev)) {