drm/i915/bdw: Implement PPGTT enable

Legacy PPGTT on GEN8 requires programming 4 PDP registers per ring.
Since all rings are using the same address space with the current code
the logic is simply to program all the tables we've setup for the PPGTT.

v2: Turn on PPGTT in GFX_MODE

v3: v2 was the wrong patch

v4: Resolve conflicts due to patch series reordering.

v5: Squash in fixup from Ben: Use LRI to write PDPs

The docs (and simulator seems to back up) suggest that we can only
program legacy PPGTT PDPs with LRI commands.

v6: Rebase around context differences conflicts.

v7: Use #defines for per ring PDPs. (Damien)

v8: Don't use typede'f private_t.

Signed-off-by: Ben Widawsky <ben@bwidawsk.net> (up to v3 and v7)
Reviewed-by: NImre Deak <imre.deak@intel.com>
Reviewed-by: NDamien Lespiau <damien.lespiau@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -195,6 +195,55 @@ static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
 	return pte;
 }
 
+/* Broadwell Page Directory Pointer Descriptors */
+static int gen8_write_pdp(struct intel_ring_buffer *ring, unsigned entry,
+			   uint64_t val)
+{
+	int ret;
+
+	BUG_ON(entry >= 4);
+
+	ret = intel_ring_begin(ring, 6);
+	if (ret)
+		return ret;
+
+	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
+	intel_ring_emit(ring, GEN8_RING_PDP_UDW(ring, entry));
+	intel_ring_emit(ring, (u32)(val >> 32));
+	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
+	intel_ring_emit(ring, GEN8_RING_PDP_LDW(ring, entry));
+	intel_ring_emit(ring, (u32)(val));
+	intel_ring_advance(ring);
+
+	return 0;
+}
+
+static int gen8_ppgtt_enable(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_ring_buffer *ring;
+	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
+	int i, j, ret;
+
+	/* bit of a hack to find the actual last used pd */
+	int used_pd = ppgtt->num_pd_entries / GEN8_PDES_PER_PAGE;
+
+	for_each_ring(ring, dev_priv, j) {
+		I915_WRITE(RING_MODE_GEN7(ring),
+			   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
+	}
+
+	for (i = used_pd - 1; i >= 0; i--) {
+		dma_addr_t addr = ppgtt->pd_dma_addr[i];
+		for_each_ring(ring, dev_priv, j) {
+			ret = gen8_write_pdp(ring, i, addr);
+			if (ret)
+				return ret;
+		}
+	}
+	return 0;
+}
+
 static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
 				   unsigned first_entry,
 				   unsigned num_entries,
@@ -326,6 +375,7 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
 	ppgtt->num_pd_pages = 1 << get_order(max_pdp << PAGE_SHIFT);
 	ppgtt->num_pt_pages = 1 << get_order(num_pt_pages << PAGE_SHIFT);
 	ppgtt->num_pd_entries = max_pdp * GEN8_PDES_PER_PAGE;
+	ppgtt->enable = gen8_ppgtt_enable;
 	ppgtt->base.clear_range = gen8_ppgtt_clear_range;
 	ppgtt->base.insert_entries = gen8_ppgtt_insert_entries;
 	ppgtt->base.cleanup = gen8_ppgtt_cleanup;

drivers/gpu/drm/i915/i915_reg.h

@@ -110,6 +110,9 @@
 #define RING_PP_DIR_DCLV(ring)		((ring)->mmio_base+0x220)
 #define   PP_DIR_DCLV_2G		0xffffffff
 
+#define GEN8_RING_PDP_UDW(ring, n)	((ring)->mmio_base+0x270 + ((n) * 8 + 4))
+#define GEN8_RING_PDP_LDW(ring, n)	((ring)->mmio_base+0x270 + (n) * 8)
+
 #define GAM_ECOCHK			0x4090
 #define   ECOCHK_SNB_BIT		(1<<10)
 #define   HSW_ECOCHK_ARB_PRIO_SOL	(1<<6)