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, 32 insertions, 3 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 0ce0d47e4b0f..885d595e0e02 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -212,6 +212,7 @@ static int
 relocate_entry_cpu(struct drm_i915_gem_object *obj,
                    struct drm_i915_gem_relocation_entry *reloc)
 {
+        struct drm_device *dev = obj->base.dev;
         uint32_t page_offset = offset_in_page(reloc->offset);
         char *vaddr;
         int ret = -EINVAL;
@@ -223,6 +224,19 @@ relocate_entry_cpu(struct drm_i915_gem_object *obj,
         vaddr = kmap_atomic(i915_gem_object_get_page(obj,
                                 reloc->offset >> PAGE_SHIFT));
         *(uint32_t *)(vaddr + page_offset) = reloc->delta;
+
+        if (INTEL_INFO(dev)->gen >= 8) {
+                page_offset = offset_in_page(page_offset + sizeof(uint32_t));
+
+                if (page_offset == 0) {
+                        kunmap_atomic(vaddr);
+                        vaddr = kmap_atomic(i915_gem_object_get_page(obj,
+                            (reloc->offset + sizeof(uint32_t)) >> PAGE_SHIFT));
+                }
+
+                *(uint32_t *)(vaddr + page_offset) = 0;
+        }
+
         kunmap_atomic(vaddr);
 
         return 0;
@@ -253,6 +267,21 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj,
         reloc_entry = (uint32_t __iomem *)
                 (reloc_page + offset_in_page(reloc->offset));
         iowrite32(reloc->delta, reloc_entry);
+
+        if (INTEL_INFO(dev)->gen >= 8) {
+                reloc_entry += 1;
+
+                if (offset_in_page(reloc->offset + sizeof(uint32_t)) == 0) {
+                        io_mapping_unmap_atomic(reloc_page);
+                        reloc_page = io_mapping_map_atomic_wc(
+                                        dev_priv->gtt.mappable,
+                                        reloc->offset + sizeof(uint32_t));
+                        reloc_entry = reloc_page;
+                }
+
+                iowrite32(0, reloc_entry);
+        }
+
         io_mapping_unmap_atomic(reloc_page);
 
         return 0;
@@ -323,7 +352,8 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
                 return 0;
 
         /* Check that the relocation address is valid... */
-        if (unlikely(reloc->offset > obj->base.size - 4)) {
+        if (unlikely(reloc->offset >
+                obj->base.size - (INTEL_INFO(dev)->gen >= 8 ? 8 : 4))) {
                 DRM_DEBUG("Relocation beyond object bounds: "
                           "obj %p target %d offset %d size %d.\n",
                           obj, reloc->target_handle,
@@ -1116,8 +1146,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 
         /* snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
          * batch" bit. Hence we need to pin secure batches into the global gtt.
-         * hsw should have this fixed, but let's be paranoid and do it
-         * unconditionally for now. */
+         * hsw should have this fixed, but bdw mucks it up again. */
         if (flags & I915_DISPATCH_SECURE && !batch_obj->has_global_gtt_mapping)
                 i915_gem_gtt_bind_object(batch_obj, batch_obj->cache_level);