[Intel-gfx] [PATCH v18 1/2] drm/i915: Do not allocate unused PPAT entries

[Zhi Wang]

Only PPAT entries 0/2/3/4 are using. Remove extra PPAT entry allocation
during initialization.

v17:

- Refine ppat_index() and move the comments. (Joonas)

v8:

- Move ppat_index() into i915_gem_gtt.c. (Chris)
- Change the name of ppat_bits_to_index to ppat_index.

Suggested-by: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
Signed-off-by: Zhi Wang <zhi.a.wang at intel.com>
Cc: Ben Widawsky <benjamin.widawsky at intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi at intel.com>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 52 ++++++++++++++++++-------------------
 1 file changed, 26 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 731ce22..43e0d23 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -230,9 +230,11 @@ static gen8_pte_t gen8_pte_encode(dma_addr_t addr,
 
 	switch (level) {
 	case I915_CACHE_NONE:
+		/* Uncached objects, mostly for scanout */
 		pte |= PPAT_UNCACHED;
 		break;
 	case I915_CACHE_WT:
+		/* for scanout with eLLC */
 		pte |= PPAT_DISPLAY_ELLC;
 		break;
 	default:
@@ -249,6 +251,7 @@ static gen8_pde_t gen8_pde_encode(const dma_addr_t addr,
 	gen8_pde_t pde = _PAGE_PRESENT | _PAGE_RW;
 	pde |= addr;
 	if (level != I915_CACHE_NONE)
+		/* for normal objects, no eLLC */
 		pde |= PPAT_CACHED_PDE;
 	else
 		pde |= PPAT_UNCACHED;
@@ -2988,6 +2991,14 @@ static unsigned int chv_private_pat_match(u8 src, u8 dst)
 		INTEL_PPAT_PERFECT_MATCH : 0;
 }
 
+/* PPAT index = 4 * PAT + 2 * PCD + PWT */
+static inline unsigned int ppat_index(unsigned int bits)
+{
+	return (4 * !!(bits & _PAGE_PAT) +
+		2 * !!(bits & _PAGE_PCD) +
+		!!(bits & _PAGE_PWT));
+}
+
 static void cnl_setup_private_ppat(struct intel_ppat *ppat)
 {
 	ppat->max_entries = 8;
@@ -2997,18 +3008,14 @@ static void cnl_setup_private_ppat(struct intel_ppat *ppat)
 
 	/* XXX: spec is unclear if this is still needed for CNL+ */
 	if (!USES_PPGTT(ppat->i915)) {
-		__alloc_ppat_entry(ppat, 0, GEN8_PPAT_UC);
+		__alloc_ppat_entry(ppat, ppat_index(PPAT_CACHED_PDE), GEN8_PPAT_UC);
 		return;
 	}
 
-	__alloc_ppat_entry(ppat, 0, GEN8_PPAT_WB | GEN8_PPAT_LLC);
-	__alloc_ppat_entry(ppat, 1, GEN8_PPAT_WC | GEN8_PPAT_LLCELLC);
-	__alloc_ppat_entry(ppat, 2, GEN8_PPAT_WT | GEN8_PPAT_LLCELLC);
-	__alloc_ppat_entry(ppat, 3, GEN8_PPAT_UC);
-	__alloc_ppat_entry(ppat, 4, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0));
-	__alloc_ppat_entry(ppat, 5, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1));
-	__alloc_ppat_entry(ppat, 6, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2));
-	__alloc_ppat_entry(ppat, 7, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
+	__alloc_ppat_entry(ppat, ppat_index(PPAT_CACHED_PDE), GEN8_PPAT_WB | GEN8_PPAT_LLC);
+	__alloc_ppat_entry(ppat, ppat_index(PPAT_DISPLAY_ELLC), GEN8_PPAT_WT | GEN8_PPAT_LLCELLC);
+	__alloc_ppat_entry(ppat, ppat_index(PPAT_UNCACHED), GEN8_PPAT_UC);
+	__alloc_ppat_entry(ppat, ppat_index(PPAT_CACHED), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0));
 }
 
 /* The GGTT and PPGTT need a private PPAT setup in order to handle cacheability
@@ -3035,18 +3042,14 @@ static void bdw_setup_private_ppat(struct intel_ppat *ppat)
 		 * So we can still hold onto all our assumptions wrt cpu
 		 * clflushing on LLC machines.
 		 */
-		__alloc_ppat_entry(ppat, 0, GEN8_PPAT_UC);
+		__alloc_ppat_entry(ppat, ppat_index(PPAT_CACHED_PDE), GEN8_PPAT_UC);
 		return;
 	}
 
-	__alloc_ppat_entry(ppat, 0, GEN8_PPAT_WB | GEN8_PPAT_LLC);      /* for normal objects, no eLLC */
-	__alloc_ppat_entry(ppat, 1, GEN8_PPAT_WC | GEN8_PPAT_LLCELLC);  /* for something pointing to ptes? */
-	__alloc_ppat_entry(ppat, 2, GEN8_PPAT_WT | GEN8_PPAT_LLCELLC);  /* for scanout with eLLC */
-	__alloc_ppat_entry(ppat, 3, GEN8_PPAT_UC);                      /* Uncached objects, mostly for scanout */
-	__alloc_ppat_entry(ppat, 4, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0));
-	__alloc_ppat_entry(ppat, 5, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1));
-	__alloc_ppat_entry(ppat, 6, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2));
-	__alloc_ppat_entry(ppat, 7, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
+	__alloc_ppat_entry(ppat, ppat_index(PPAT_CACHED_PDE), GEN8_PPAT_WB | GEN8_PPAT_LLC);
+	__alloc_ppat_entry(ppat, ppat_index(PPAT_DISPLAY_ELLC), GEN8_PPAT_WT | GEN8_PPAT_LLCELLC);
+	__alloc_ppat_entry(ppat, ppat_index(PPAT_UNCACHED), GEN8_PPAT_UC);
+	__alloc_ppat_entry(ppat, ppat_index(PPAT_CACHED), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0));
 }
 
 static void chv_setup_private_ppat(struct intel_ppat *ppat)
@@ -3075,14 +3078,11 @@ static void chv_setup_private_ppat(struct intel_ppat *ppat)
 	 * in order to keep the global status page working.
 	 */
 
-	__alloc_ppat_entry(ppat, 0, CHV_PPAT_SNOOP);
-	__alloc_ppat_entry(ppat, 1, 0);
-	__alloc_ppat_entry(ppat, 2, 0);
-	__alloc_ppat_entry(ppat, 3, 0);
-	__alloc_ppat_entry(ppat, 4, CHV_PPAT_SNOOP);
-	__alloc_ppat_entry(ppat, 5, CHV_PPAT_SNOOP);
-	__alloc_ppat_entry(ppat, 6, CHV_PPAT_SNOOP);
-	__alloc_ppat_entry(ppat, 7, CHV_PPAT_SNOOP);
+	/* See gen8_pte_encode() for the mapping from cache-level to PPAT */
+	__alloc_ppat_entry(ppat, ppat_index(PPAT_CACHED_PDE), CHV_PPAT_SNOOP);
+	__alloc_ppat_entry(ppat, ppat_index(PPAT_DISPLAY_ELLC), 0);
+	__alloc_ppat_entry(ppat, ppat_index(PPAT_UNCACHED), 0);
+	__alloc_ppat_entry(ppat, ppat_index(PPAT_CACHED), CHV_PPAT_SNOOP);
 }
 
 static void gen6_gmch_remove(struct i915_address_space *vm)
-- 
2.7.4