Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux

Pull drm merge (part 1) from Dave Airlie:
 "So first of all my tree and uapi stuff has a conflict mess, its my
  fault as the nouveau stuff didn't hit -next as were trying to rebase
  regressions out of it before we merged.

  Highlights:
   - SH mobile modesetting driver and associated helpers
   - some DRM core documentation
   - i915 modesetting rework, haswell hdmi, haswell and vlv fixes, write
     combined pte writing, ilk rc6 support,
   - nouveau: major driver rework into a hw core driver, makes features
     like SLI a lot saner to implement,
   - psb: add eDP/DP support for Cedarview
   - radeon: 2 layer page tables, async VM pte updates, better PLL
     selection for > 2 screens, better ACPI interactions

  The rest is general grab bag of fixes.

  So why part 1? well I have the exynos pull req which came in a bit
  late but was waiting for me to do something they shouldn't have and it
  looks fairly safe, and David Howells has some more header cleanups
  he'd like me to pull, that seem like a good idea, but I'd like to get
  this merge out of the way so -next dosen't get blocked."

Tons of conflicts mostly due to silly include line changes, but mostly
mindless.  A few other small semantic conflicts too, noted from Dave's
pre-merged branch.

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (447 commits)
  drm/nv98/crypt: fix fuc build with latest envyas
  drm/nouveau/devinit: fixup various issues with subdev ctor/init ordering
  drm/nv41/vm: fix and enable use of "real" pciegart
  drm/nv44/vm: fix and enable use of "real" pciegart
  drm/nv04/dmaobj: fixup vm target handling in preparation for nv4x pcie
  drm/nouveau: store supported dma mask in vmmgr
  drm/nvc0/ibus: initial implementation of subdev
  drm/nouveau/therm: add support for fan-control modes
  drm/nouveau/hwmon: rename pwm0* to pmw1* to follow hwmon's rules
  drm/nouveau/therm: calculate the pwm divisor on nv50+
  drm/nouveau/fan: rewrite the fan tachometer driver to get more precision, faster
  drm/nouveau/therm: move thermal-related functions to the therm subdev
  drm/nouveau/bios: parse the pwm divisor from the perf table
  drm/nouveau/therm: use the EXTDEV table to detect i2c monitoring devices
  drm/nouveau/therm: rework thermal table parsing
  drm/nouveau/gpio: expose the PWM/TOGGLE parameter found in the gpio vbios table
  drm/nouveau: fix pm initialization order
  drm/nouveau/bios: check that fixed tvdac gpio data is valid before using it
  drm/nouveau: log channel debug/error messages from client object rather than drm client
  drm/nouveau: have drm debugging macros build on top of core macros
  ...

1 files changed, 133 insertions, 19 deletions

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 1aef516cc6f..ecbc5c5dbbb 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -261,6 +261,83 @@ gen6_render_ring_flush(struct intel_ring_buffer *ring,
 	return 0;
 }
 
+static int
+gen7_render_ring_cs_stall_wa(struct intel_ring_buffer *ring)
+{
+	int ret;
+
+	ret = intel_ring_begin(ring, 4);
+	if (ret)
+		return ret;
+
+	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4));
+	intel_ring_emit(ring, PIPE_CONTROL_CS_STALL |
+			      PIPE_CONTROL_STALL_AT_SCOREBOARD);
+	intel_ring_emit(ring, 0);
+	intel_ring_emit(ring, 0);
+	intel_ring_advance(ring);
+
+	return 0;
+}
+
+static int
+gen7_render_ring_flush(struct intel_ring_buffer *ring,
+		       u32 invalidate_domains, u32 flush_domains)
+{
+	u32 flags = 0;
+	struct pipe_control *pc = ring->private;
+	u32 scratch_addr = pc->gtt_offset + 128;
+	int ret;
+
+	/*
+	 * Ensure that any following seqno writes only happen when the render
+	 * cache is indeed flushed.
+	 *
+	 * Workaround: 4th PIPE_CONTROL command (except the ones with only
+	 * read-cache invalidate bits set) must have the CS_STALL bit set. We
+	 * don't try to be clever and just set it unconditionally.
+	 */
+	flags |= PIPE_CONTROL_CS_STALL;
+
+	/* Just flush everything.  Experiments have shown that reducing the
+	 * number of bits based on the write domains has little performance
+	 * impact.
+	 */
+	if (flush_domains) {
+		flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
+		flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
+	}
+	if (invalidate_domains) {
+		flags |= PIPE_CONTROL_TLB_INVALIDATE;
+		flags |= PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
+		/*
+		 * TLB invalidate requires a post-sync write.
+		 */
+		flags |= PIPE_CONTROL_QW_WRITE;
+
+		/* Workaround: we must issue a pipe_control with CS-stall bit
+		 * set before a pipe_control command that has the state cache
+		 * invalidate bit set. */
+		gen7_render_ring_cs_stall_wa(ring);
+	}
+
+	ret = intel_ring_begin(ring, 4);
+	if (ret)
+		return ret;
+
+	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4));
+	intel_ring_emit(ring, flags);
+	intel_ring_emit(ring, scratch_addr | PIPE_CONTROL_GLOBAL_GTT);
+	intel_ring_emit(ring, 0);
+	intel_ring_advance(ring);
+
+	return 0;
+}
+
 static void ring_write_tail(struct intel_ring_buffer *ring,
 			    u32 value)
 {
@@ -381,12 +458,12 @@ init_pipe_control(struct intel_ring_buffer *ring)
 
 	i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
 
-	ret = i915_gem_object_pin(obj, 4096, true);
+	ret = i915_gem_object_pin(obj, 4096, true, false);
 	if (ret)
 		goto err_unref;
 
 	pc->gtt_offset = obj->gtt_offset;
-	pc->cpu_page =  kmap(obj->pages[0]);
+	pc->cpu_page =  kmap(sg_page(obj->pages->sgl));
 	if (pc->cpu_page == NULL)
 		goto err_unpin;
 
@@ -413,7 +490,8 @@ cleanup_pipe_control(struct intel_ring_buffer *ring)
 		return;
 
 	obj = pc->obj;
-	kunmap(obj->pages[0]);
+
+	kunmap(sg_page(obj->pages->sgl));
 	i915_gem_object_unpin(obj);
 	drm_gem_object_unreference(&obj->base);
 
@@ -461,7 +539,7 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 	if (INTEL_INFO(dev)->gen >= 6)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
-	if (IS_IVYBRIDGE(dev))
+	if (HAS_L3_GPU_CACHE(dev))
 		I915_WRITE_IMR(ring, ~GEN6_RENDER_L3_PARITY_ERROR);
 
 	return ret;
@@ -627,26 +705,24 @@ pc_render_add_request(struct intel_ring_buffer *ring,
 }
 
 static u32
-gen6_ring_get_seqno(struct intel_ring_buffer *ring)
+gen6_ring_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency)
 {
-	struct drm_device *dev = ring->dev;
-
 	/* Workaround to force correct ordering between irq and seqno writes on
 	 * ivb (and maybe also on snb) by reading from a CS register (like
 	 * ACTHD) before reading the status page. */
-	if (IS_GEN6(dev) || IS_GEN7(dev))
+	if (!lazy_coherency)
 		intel_ring_get_active_head(ring);
 	return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
 }
 
 static u32
-ring_get_seqno(struct intel_ring_buffer *ring)
+ring_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency)
 {
 	return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
 }
 
 static u32
-pc_render_get_seqno(struct intel_ring_buffer *ring)
+pc_render_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency)
 {
 	struct pipe_control *pc = ring->private;
 	return pc->cpu_page[0];
@@ -851,7 +927,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (ring->irq_refcount++ == 0) {
-		if (IS_IVYBRIDGE(dev) && ring->id == RCS)
+		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring, ~(ring->irq_enable_mask |
 						GEN6_RENDER_L3_PARITY_ERROR));
 		else
@@ -874,7 +950,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
-		if (IS_IVYBRIDGE(dev) && ring->id == RCS)
+		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring, ~GEN6_RENDER_L3_PARITY_ERROR);
 		else
 			I915_WRITE_IMR(ring, ~0);
@@ -950,7 +1026,7 @@ static void cleanup_status_page(struct intel_ring_buffer *ring)
 	if (obj == NULL)
 		return;
 
-	kunmap(obj->pages[0]);
+	kunmap(sg_page(obj->pages->sgl));
 	i915_gem_object_unpin(obj);
 	drm_gem_object_unreference(&obj->base);
 	ring->status_page.obj = NULL;
@@ -971,13 +1047,13 @@ static int init_status_page(struct intel_ring_buffer *ring)
 
 	i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
 
-	ret = i915_gem_object_pin(obj, 4096, true);
+	ret = i915_gem_object_pin(obj, 4096, true, false);
 	if (ret != 0) {
 		goto err_unref;
 	}
 
 	ring->status_page.gfx_addr = obj->gtt_offset;
-	ring->status_page.page_addr = kmap(obj->pages[0]);
+	ring->status_page.page_addr = kmap(sg_page(obj->pages->sgl));
 	if (ring->status_page.page_addr == NULL) {
 		ret = -ENOMEM;
 		goto err_unpin;
@@ -1009,7 +1085,6 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 	ring->dev = dev;
 	INIT_LIST_HEAD(&ring->active_list);
 	INIT_LIST_HEAD(&ring->request_list);
-	INIT_LIST_HEAD(&ring->gpu_write_list);
 	ring->size = 32 * PAGE_SIZE;
 
 	init_waitqueue_head(&ring->irq_queue);
@@ -1029,7 +1104,7 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 
 	ring->obj = obj;
 
-	ret = i915_gem_object_pin(obj, PAGE_SIZE, true);
+	ret = i915_gem_object_pin(obj, PAGE_SIZE, true, false);
 	if (ret)
 		goto err_unref;
 
@@ -1378,7 +1453,9 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 
 	if (INTEL_INFO(dev)->gen >= 6) {
 		ring->add_request = gen6_add_request;
-		ring->flush = gen6_render_ring_flush;
+		ring->flush = gen7_render_ring_flush;
+		if (INTEL_INFO(dev)->gen == 6)
+			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;
@@ -1480,7 +1557,6 @@ int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size)
 	ring->dev = dev;
 	INIT_LIST_HEAD(&ring->active_list);
 	INIT_LIST_HEAD(&ring->request_list);
-	INIT_LIST_HEAD(&ring->gpu_write_list);
 
 	ring->size = size;
 	ring->effective_size = ring->size;
@@ -1573,3 +1649,41 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 
 	return intel_init_ring_buffer(dev, ring);
 }
+
+int
+intel_ring_flush_all_caches(struct intel_ring_buffer *ring)
+{
+	int ret;
+
+	if (!ring->gpu_caches_dirty)
+		return 0;
+
+	ret = ring->flush(ring, 0, I915_GEM_GPU_DOMAINS);
+	if (ret)
+		return ret;
+
+	trace_i915_gem_ring_flush(ring, 0, I915_GEM_GPU_DOMAINS);
+
+	ring->gpu_caches_dirty = false;
+	return 0;
+}
+
+int
+intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring)
+{
+	uint32_t flush_domains;
+	int ret;
+
+	flush_domains = 0;
+	if (ring->gpu_caches_dirty)
+		flush_domains = I915_GEM_GPU_DOMAINS;
+
+	ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, flush_domains);
+	if (ret)
+		return ret;
+
+	trace_i915_gem_ring_flush(ring, I915_GEM_GPU_DOMAINS, flush_domains);
+
+	ring->gpu_caches_dirty = false;
+	return 0;
+}