[Intel-gfx] [PATCH v6 14/32] drm/i915/bdw: Update pdp switch and point unused PDPs to scratch page

[Michel Thierry]

From: Ben Widawsky <benjamin.widawsky at intel.com>

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, we're not 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 only
effect platforms with less than 4GB memory.

v2: Updated commit message to point that we must set unused PDPs to the
scratch page.

Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
Signed-off-by: Michel Thierry <michel.thierry at intel.com> (v2)
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 29 ++++++++++++++++++-----------
 drivers/gpu/drm/i915/i915_gem_gtt.h |  5 ++++-
 2 files changed, 22 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 762c535..2e4db77 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -442,8 +442,9 @@ static struct i915_page_directory_entry *alloc_pd_single(void)
 }
 
 /* Broadwell Page Directory Pointer Descriptors */
-static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry,
-			   uint64_t val)
+static int gen8_write_pdp(struct intel_engine_cs *ring,
+			  unsigned entry,
+			  dma_addr_t addr)
 {
 	int ret;
 
@@ -455,10 +456,10 @@ 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;
@@ -469,12 +470,12 @@ 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 / GEN8_PDES_PER_PAGE;
-
-	for (i = used_pd - 1; i >= 0; i--) {
-		dma_addr_t addr = ppgtt->pdp.page_directory[i]->daddr;
-		ret = gen8_write_pdp(ring, i, addr);
+	for (i = GEN8_LEGACY_PDPES - 1; i >= 0; i--) {
+		struct i915_page_directory_entry *pd = ppgtt->pdp.page_directory[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);
 		if (ret)
 			return ret;
 	}
@@ -816,10 +817,16 @@ 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) {
+		unmap_and_free_pt(ppgtt->scratch_pd, ppgtt->base.dev);
 		return ret;
+	}
 
 	/*
 	 * 2. Create DMA mappings for the page directories and page tables.
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 1f5c136..7a16627 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -306,7 +306,10 @@ struct i915_hw_ppgtt {
 		struct i915_page_directory_entry pd;
 	};
 
-	struct i915_page_table_entry *scratch_pt;
+	union {
+		struct i915_page_table_entry *scratch_pt;
+		struct i915_page_table_entry *scratch_pd; /* Just need the daddr */
+	};
 
 	struct drm_i915_file_private *file_priv;
 
-- 
2.1.1