The private PAT management is to support PPAT entry manipulation. Two
APIs are introduced for dynamically managing PPAT entries: intel_ppat_get
and intel_ppat_put.
intel_ppat_get will search for an existing PPAT entry which perfectly
matches the required PPAT value. If not, it will try to allocate or
return a partially matched PPAT entry if there is any available PPAT
indexes or not.
intel_ppat_put will put back the PPAT entry which comes from
intel_ppat_get. If it's dynamically allocated, the reference count will
be decreased. If the reference count turns into zero, the PPAT index is
freed again.
Besides, another two callbacks are introduced to support the private PAT
management framework. One is ppat->update(), which writes the PPAT
configurations in ppat->entries into HW. Another one is ppat->match, which
will return a score to show how two PPAT values match with each other.
v3:
- Introduce dirty bitmap for PPAT registers. (Chris)
- Change the name of the pointer "dev_priv" to "i915". (Chris)
- intel_ppat_{get, put} returns/takes a const intel_ppat_entry *. (Chris)
v2:
- API re-design. (Chris)
Cc: Ben Widawsky <benjamin.widawsky@xxxxxxxxx>
Cc: Rodrigo Vivi <rodrigo.vivi@xxxxxxxxx>
Cc: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx>
Signed-off-by: Zhi Wang <zhi.a.wang@xxxxxxxxx>
---
drivers/gpu/drm/i915/i915_drv.h | 2 +
drivers/gpu/drm/i915/i915_gem_gtt.c | 280 +++++++++++++++++++++++++++++-------
drivers/gpu/drm/i915/i915_gem_gtt.h | 34 +++++
3 files changed, 267 insertions(+), 49 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 7587ef5..5ffde10 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2312,6 +2312,8 @@ struct drm_i915_private {
DECLARE_HASHTABLE(mm_structs, 7);
struct mutex mm_lock;
+ struct intel_ppat ppat;
+
/* Kernel Modesetting */
struct intel_crtc *plane_to_crtc_mapping[I915_MAX_PIPES];
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index b74fa9d..fee67a0 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2816,41 +2816,209 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
return 0;
}
-static void cnl_setup_private_ppat(struct drm_i915_private *dev_priv)
+static struct intel_ppat_entry *alloc_ppat_entry(struct intel_ppat *ppat,
+ unsigned int index,
+ u8 value)
{
+ struct intel_ppat_entry *entry = &ppat->entries[index];
+
+ entry->ppat = ppat;
+ entry->value = value;
+ kref_init(&entry->ref_count);
+ set_bit(index, ppat->used);
+ set_bit(index, ppat->dirty);
+
+ return entry;
+}
+
+static void free_ppat_entry(struct intel_ppat_entry *entry)
+{
+ struct intel_ppat *ppat = entry->ppat;
+ int index = entry - ppat->entries;
+
+ entry->value = ppat->dummy_value;
+ clear_bit(index, ppat->used);
+ set_bit(index, ppat->dirty);
+}
+
+/**
+ * intel_ppat_get - get a usable PPAT entry
+ * @i915: i915 device instance
+ * @value: the PPAT value required by the caller
+ *
+ * The function tries to search if there is an existing PPAT entry which
+ * matches with the required value. If perfectly matched, the existing PPAT
+ * entry will be used. If only partially matched, it will try to check if
+ * there is any available PPAT index. If yes, it will allocate a new PPAT
+ * index for the required entry and update the HW. If not, the partially
+ * matched entry will be used.
+ */
+const struct intel_ppat_entry *intel_ppat_get(struct drm_i915_private *i915,
+ u8 value)
+{
+ struct intel_ppat *ppat = &i915->ppat;
+ struct intel_ppat_entry *entry;
+ int i, used;
+ unsigned int score, best_score;
+
+ score = best_score = 0;
+ used = 0;
+
+ /* First, find a suitable value from available entries */
+ for_each_set_bit(i, ppat->used, ppat->max_entries) {
+ score = ppat->match(ppat->entries[i].value, value);
+ /* Perfect match */
+ if (score == INTEL_PPAT_PERFECT_MATCH) {
+ entry = &ppat->entries[i];
+ kref_get(&entry->ref_count);
+ return entry;
+ }
+
+ if (score > best_score) {
+ entry = &ppat->entries[i];
+ best_score = score;
+ }
+ used++;
+ }
+
+ /* No matched entry and we can't allocate a new entry. */
+ if (!best_score && used == ppat->max_entries) {
+ DRM_ERROR("Fail to get PPAT entry\n");
+ return ERR_PTR(-ENOSPC);
+ }
+
+ /*
+ * Found a matched entry which is not perfect,
+ * and we can't allocate a new entry.
+ */
+ if (best_score && used == ppat->max_entries) {
+ kref_get(&entry->ref_count);
+ return entry;
+ }
+
+ /* Allocate a new entry */
+ i = find_first_zero_bit(ppat->used, ppat->max_entries);
+ entry = alloc_ppat_entry(ppat, i, value);
+ ppat->update(i915);
+ return entry;
+}
+
+static void put_ppat(struct kref *kref)
+{
+ struct intel_ppat_entry *entry =
+ container_of(kref, struct intel_ppat_entry, ref_count);
+ struct drm_i915_private *i915 = entry->ppat->i915;
+
+ free_ppat_entry(entry);
+ entry->ppat->update(i915);
+}
+
+/**
+ * intel_ppat_put - put back the PPAT entry got from intel_ppat_get()
+ * @entry: an intel PPAT entry
+ *
+ * Put back the PPAT entry got from intel_ppat_get(). If the PPAT index of the
+ * entry is dynamically allocated, its reference count will be decreased. Once
+ * the reference count becomes into zero, the PPAT index becomes free again.
+ */
+void intel_ppat_put(const struct intel_ppat_entry *entry)
+{
+ struct intel_ppat *ppat = entry->ppat;
+ int index = entry - ppat->entries;
+
+ kref_put(&ppat->entries[index].ref_count, put_ppat);
+}
+
+static void cnl_private_pat_update(struct drm_i915_private *dev_priv)
+{
+ struct intel_ppat *ppat = &dev_priv->ppat;
+ int i;
+
+ for_each_set_bit(i, ppat->dirty, ppat->max_entries) {
+ clear_bit(i, ppat->dirty);
+ I915_WRITE(GEN10_PAT_INDEX(i), ppat->entries[i].value);
+ }
+}
+
+static void bdw_private_pat_update(struct drm_i915_private *dev_priv)
+{
+ struct intel_ppat *ppat = &dev_priv->ppat;
+ u64 pat = 0;
+ int i;
+
+ for (i = 0; i < ppat->max_entries; i++)
+ pat |= GEN8_PPAT(i, ppat->entries[i].value);
+
+ bitmap_clear(ppat->dirty, 0, ppat->max_entries);
+
+ I915_WRITE(GEN8_PRIVATE_PAT_LO, pat);
+ I915_WRITE(GEN8_PRIVATE_PAT_HI, pat >> 32);
+}
+
+#define gen8_pat_ca(v) ((v) & 0x3)
+#define gen8_pat_tc(v) (((v) >> 2) & 0x3)
+#define gen8_pat_age(v) (((v) >> 4) & 0x3)
+
+static unsigned int bdw_private_pat_match(u8 src, u8 dst)
+{
+ unsigned int score = 0;
+
+ /* Cache attribute has to be matched. */
+ if (gen8_pat_ca(src) != gen8_pat_ca(dst))
+ return 0;
+
+ if (gen8_pat_age(src) == gen8_pat_age(dst))
+ score += 1;
+
+ if (gen8_pat_tc(src) == gen8_pat_tc(dst))
+ score += 2;
+
+ if (score == 3)
+ return INTEL_PPAT_PERFECT_MATCH;
+
+ return score;
+}
+
+#define chv_get_snoop(v) (((v) >> 6) & 0x1)
+
+static unsigned int chv_private_pat_match(u8 src, u8 dst)
+{
+ if (chv_get_snoop(src) == chv_get_snoop(dst))
+ return INTEL_PPAT_PERFECT_MATCH;
+
+ return 0;
+}
+
+static void cnl_setup_private_ppat(struct intel_ppat *ppat)
+{
+ ppat->max_entries = 8;
+ ppat->update = cnl_private_pat_update;
+ ppat->match = bdw_private_pat_match;
+ ppat->dummy_value = GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3);
+
/* XXX: spec is unclear if this is still needed for CNL+ */
- if (!USES_PPGTT(dev_priv)) {
- I915_WRITE(GEN10_PAT_INDEX(0), GEN8_PPAT_UC);
+ if (!USES_PPGTT(ppat->i915)) {
+ alloc_ppat_entry(ppat, 0, GEN8_PPAT_UC);
return;
}
- I915_WRITE(GEN10_PAT_INDEX(0), GEN8_PPAT_WB | GEN8_PPAT_LLC);
- I915_WRITE(GEN10_PAT_INDEX(1), GEN8_PPAT_WC | GEN8_PPAT_LLCELLC);
- I915_WRITE(GEN10_PAT_INDEX(2), GEN8_PPAT_WT | GEN8_PPAT_LLCELLC);
- I915_WRITE(GEN10_PAT_INDEX(3), GEN8_PPAT_UC);
- I915_WRITE(GEN10_PAT_INDEX(4), GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0));
- I915_WRITE(GEN10_PAT_INDEX(5), GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1));
- I915_WRITE(GEN10_PAT_INDEX(6), GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2));
- I915_WRITE(GEN10_PAT_INDEX(7), GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
+ alloc_ppat_entry(ppat, 0, GEN8_PPAT_WB | GEN8_PPAT_LLC);
+ 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_LLCELLC | GEN8_PPAT_AGE(0));
}
/* The GGTT and PPGTT need a private PPAT setup in order to handle cacheability
* bits. When using advanced contexts each context stores its own PAT, but
* writing this data shouldn't be harmful even in those cases. */
-static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv)
+static void bdw_setup_private_ppat(struct intel_ppat *ppat)
{
- u64 pat;
-
- pat = GEN8_PPAT(0, GEN8_PPAT_WB | GEN8_PPAT_LLC) | /* for normal objects, no eLLC */
- GEN8_PPAT(1, GEN8_PPAT_WC | GEN8_PPAT_LLCELLC) | /* for something pointing to ptes? */
- GEN8_PPAT(2, GEN8_PPAT_WT | GEN8_PPAT_LLCELLC) | /* for scanout with eLLC */
- GEN8_PPAT(3, GEN8_PPAT_UC) | /* Uncached objects, mostly for scanout */
- GEN8_PPAT(4, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0)) |
- GEN8_PPAT(5, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1)) |
- GEN8_PPAT(6, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2)) |
- GEN8_PPAT(7, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
+ ppat->max_entries = 8;
+ ppat->update = bdw_private_pat_update;
+ ppat->match = bdw_private_pat_match;
+ ppat->dummy_value = GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3);
- if (!USES_PPGTT(dev_priv))
+ if (!USES_PPGTT(dev_priv)) {
/* Spec: "For GGTT, there is NO pat_sel[2:0] from the entry,
* so RTL will always use the value corresponding to
* pat_sel = 000".
@@ -2864,17 +3032,22 @@ static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv)
* So we can still hold onto all our assumptions wrt cpu
* clflushing on LLC machines.
*/
- pat = GEN8_PPAT(0, GEN8_PPAT_UC);
+ alloc_ppat_entry(ppat, 0, GEN8_PPAT_UC);
+ return;
+ }
- /* XXX: spec defines this as 2 distinct registers. It's unclear if a 64b
- * write would work. */
- I915_WRITE(GEN8_PRIVATE_PAT_LO, pat);
- I915_WRITE(GEN8_PRIVATE_PAT_HI, pat >> 32);
+ alloc_ppat_entry(ppat, 0, GEN8_PPAT_WB | GEN8_PPAT_LLC); /* for normal objects, no eLLC */
+ 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));
}
-static void chv_setup_private_ppat(struct drm_i915_private *dev_priv)
+static void chv_setup_private_ppat(struct intel_ppat *ppat)
{
- u64 pat;
+ ppat->max_entries = 8;
+ ppat->update = bdw_private_pat_update;
+ ppat->match = chv_private_pat_match;
+ ppat->dummy_value = CHV_PPAT_SNOOP;
/*
* Map WB on BDW to snooped on CHV.
@@ -2894,17 +3067,11 @@ static void chv_setup_private_ppat(struct drm_i915_private *dev_priv)
* Which means we must set the snoop bit in PAT entry 0
* in order to keep the global status page working.
*/
- pat = GEN8_PPAT(0, CHV_PPAT_SNOOP) |
- GEN8_PPAT(1, 0) |
- GEN8_PPAT(2, 0) |
- GEN8_PPAT(3, 0) |
- GEN8_PPAT(4, CHV_PPAT_SNOOP) |
- GEN8_PPAT(5, CHV_PPAT_SNOOP) |
- GEN8_PPAT(6, CHV_PPAT_SNOOP) |
- GEN8_PPAT(7, CHV_PPAT_SNOOP);
- I915_WRITE(GEN8_PRIVATE_PAT_LO, pat);
- I915_WRITE(GEN8_PRIVATE_PAT_HI, pat >> 32);
+ alloc_ppat_entry(ppat, 0, CHV_PPAT_SNOOP);
+ alloc_ppat_entry(ppat, 2, 0);
+ alloc_ppat_entry(ppat, 3, 0);
+ alloc_ppat_entry(ppat, 4, CHV_PPAT_SNOOP);
}
static void gen6_gmch_remove(struct i915_address_space *vm)
@@ -2917,12 +3084,30 @@ static void gen6_gmch_remove(struct i915_address_space *vm)
static void setup_private_pat(struct drm_i915_private *dev_priv)
{
+ struct intel_ppat *ppat = &dev_priv->ppat;
+ int i;
+
+ ppat->i915 = dev_priv;
+
+ /* Load per-platform PPAT configurations */
if (INTEL_GEN(dev_priv) >= 10)
- cnl_setup_private_ppat(dev_priv);
+ cnl_setup_private_ppat(ppat);
else if (IS_CHERRYVIEW(dev_priv) || IS_GEN9_LP(dev_priv))
- chv_setup_private_ppat(dev_priv);
+ chv_setup_private_ppat(ppat);
else
- bdw_setup_private_ppat(dev_priv);
+ bdw_setup_private_ppat(ppat);
+
+ GEM_BUG_ON(ppat->max_entries > INTEL_MAX_PPAT_ENTRIES);
+
+ /* Fill unused PPAT entries with dummy PPAT value */
+ for_each_clear_bit(i, ppat->used, ppat->max_entries) {
+ ppat->entries[i].value = ppat->dummy_value;
+ ppat->entries[i].ppat = ppat;
+ set_bit(i, ppat->dirty);
+ }
+
+ /* Write the HW */
+ ppat->update(dev_priv);
}
static int gen8_gmch_probe(struct i915_ggtt *ggtt)
@@ -3236,13 +3421,10 @@ void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
ggtt->base.closed = false;
if (INTEL_GEN(dev_priv) >= 8) {
- if (INTEL_GEN(dev_priv) >= 10)
- cnl_setup_private_ppat(dev_priv);
- else if (IS_CHERRYVIEW(dev_priv) || IS_GEN9_LP(dev_priv))
- chv_setup_private_ppat(dev_priv);
- else
- bdw_setup_private_ppat(dev_priv);
+ struct intel_ppat *ppat = &dev_priv->ppat;
+ bitmap_set(ppat->dirty, 0, ppat->max_entries);
+ dev_priv->ppat.update(dev_priv);
return;
}
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index b4e3aa7..6bf5521 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -536,6 +536,40 @@ i915_vm_to_ggtt(struct i915_address_space *vm)
return container_of(vm, struct i915_ggtt, base);
}
+#define INTEL_MAX_PPAT_ENTRIES 8
+#define INTEL_PPAT_PERFECT_MATCH (~0U)
+
+struct intel_ppat;
+
+struct intel_ppat_entry {
+ struct intel_ppat *ppat;
+ struct kref ref_count;
+ u8 value;
+};
+
+struct intel_ppat {
+ struct intel_ppat_entry entries[INTEL_MAX_PPAT_ENTRIES];
+ DECLARE_BITMAP(used, INTEL_MAX_PPAT_ENTRIES);
+ DECLARE_BITMAP(dirty, INTEL_MAX_PPAT_ENTRIES);
+
+ unsigned int max_entries;
+
+ u8 dummy_value;
+ /*
+ * Return a score to show how two PPAT values match,
+ * a INTEL_PPAT_PERFECT_MATCH indicates a perfect match
+ */
+ unsigned int (*match)(u8 src, u8 dst);
+ /* Write the PPAT configuration into HW. */
+ void (*update)(struct drm_i915_private *i915);
+
+ struct drm_i915_private *i915;
+};
+
+const struct intel_ppat_entry *intel_ppat_get(struct drm_i915_private *i915,
+ u8 value);
+void intel_ppat_put(const struct intel_ppat_entry *entry);
+
int i915_gem_init_aliasing_ppgtt(struct drm_i915_private *i915);
void i915_gem_fini_aliasing_ppgtt(struct drm_i915_private *i915);
--
2.7.4
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
