[Intel-gfx] [PATCH 49/68] drm/i915/bdw: Make the pdp switch a bit less hacky

[Ben Widawsky]

One important part of this patch is we now write a scratch page
directory into any unused PDP descriptors. This matters for 2 reasons,
first, it's not clear we're allowed to just use 0, or an invalid
pointer, and second, we must wipe out any previous contents from the last
context.

The latter point only matters with full PPGTT. The former point would
only effect 32b platforms, or platforms with less than 4GB memory.

Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 34 +++++++++++++++++++++-------------
 drivers/gpu/drm/i915/i915_gem_gtt.h |  5 ++++-
 2 files changed, 25 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 0426222..5875071 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -382,8 +382,10 @@ static struct i915_pagedir *alloc_pd_single(struct drm_device *dev)
 }
 
 /* Broadwell Page Directory Pointer Descriptors */
-static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry,
-			   uint64_t val, bool synchronous)
+static int gen8_write_pdp(struct intel_engine_cs *ring,
+			  unsigned entry,
+			  dma_addr_t addr,
+			  bool synchronous)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 	int ret;
@@ -391,8 +393,8 @@ static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry,
 	BUG_ON(entry >= 4);
 
 	if (synchronous) {
-		I915_WRITE(GEN8_RING_PDP_UDW(ring, entry), val >> 32);
-		I915_WRITE(GEN8_RING_PDP_LDW(ring, entry), (u32)val);
+		I915_WRITE(GEN8_RING_PDP_UDW(ring, entry), upper_32_bits(addr));
+		I915_WRITE(GEN8_RING_PDP_LDW(ring, entry), lower_32_bits(addr));
 		return 0;
 	}
 
@@ -402,10 +404,10 @@ static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry,
 
 	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, upper_32_bits(addr));
 	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_emit(ring, lower_32_bits(addr));
 	intel_ring_advance(ring);
 
 	return 0;
@@ -417,12 +419,12 @@ static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt,
 {
 	int i, ret;
 
-	/* bit of a hack to find the actual last used pd */
-	int used_pd = ppgtt->num_pd_entries / I915_PDES_PER_PD;
-
-	for (i = used_pd - 1; i >= 0; i--) {
-		dma_addr_t addr = ppgtt->pdp.pagedirs[i]->daddr;
-		ret = gen8_write_pdp(ring, i, addr, synchronous);
+	for (i = GEN8_LEGACY_PDPES - 1; i >= 0; i--) {
+		struct i915_pagedir *pd = ppgtt->pdp.pagedirs[i];
+		dma_addr_t pd_daddr = pd ? pd->daddr : ppgtt->scratch_pd->daddr;
+		/* The page directory might be NULL, but we need to clear out
+		 * whatever the previous context might have used. */
+		ret = gen8_write_pdp(ring, i, pd_daddr, synchronous);
 		if (ret)
 			return ret;
 	}
@@ -681,10 +683,16 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
 	ppgtt->base.start = 0;
 	ppgtt->base.total = size;
 
+	ppgtt->scratch_pd = alloc_pt_scratch(ppgtt->base.dev);
+	if (IS_ERR(ppgtt->scratch_pd))
+		return PTR_ERR(ppgtt->scratch_pd);
+
 	/* 1. Do all our allocations for page directories and page tables. */
 	ret = gen8_ppgtt_alloc(ppgtt, ppgtt->base.start, ppgtt->base.total);
-	if (ret)
+	if (ret) {
+		free_pt_scratch(ppgtt->scratch_pd, ppgtt->base.dev);
 		return ret;
+	}
 
 	/*
 	 * 2. Map all the page directory entires to point to the page tables
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index d635528..3c28365 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -272,7 +272,10 @@ struct i915_hw_ppgtt {
 		struct i915_pagedir pd;
 	};
 
-	struct i915_pagetab *scratch_pt;
+	union {
+		struct i915_pagetab *scratch_pt;
+		struct i915_pagetab *scratch_pd; /* Just need the daddr */
+	};
 
 	struct intel_context *ctx;
 
-- 
2.0.4