[Intel-gfx] [PATCH 09/17] drm/i915/gtt: Only keep gen6 page directories pinned while active

[Chris Wilson]

In order to be able to evict the gen6 ppgtt, we have to unpin it at some
point. We can simply use our context activity tracking to know when the
ppgtt is no longer in use by hardware, and so only keep it pinned while
being used a request.

For the kernel_context (and thus aliasing_ppgtt), it remains pinned at
all times, as the kernel_context itself is pinned at all times.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Cc: Matthew Auld <matthew.william.auld at gmail.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c     | 36 ++++++++++++++-----------
 drivers/gpu/drm/i915/i915_gem_gtt.h     |  5 ++++
 drivers/gpu/drm/i915/intel_ringbuffer.c | 28 +++++++++++++++++++
 3 files changed, 54 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 28ab76684f99..6aea9caf2f24 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1966,7 +1966,6 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 {
 	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
 
-	i915_vma_unpin(ppgtt->vma);
 	i915_vma_destroy(ppgtt->vma);
 
 	gen6_ppgtt_free_pd(ppgtt);
@@ -2060,10 +2059,19 @@ static struct i915_vma *pd_vma_create(struct gen6_hw_ppgtt *ppgtt, int size)
 	return vma;
 }
 
-static int gen6_ppgtt_pin(struct i915_hw_ppgtt *base)
+int gen6_ppgtt_pin(struct i915_hw_ppgtt *base)
 {
 	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base);
 
+	/*
+	 * Workaround the limited maximum vma->pin_count and the aliasing_ppgtt
+	 * which will be pinned into every active context.
+	 * (When vma->pin_count becomes atomic, I expect we will naturally
+	 * need a larger, unpacked, type and kill this redundancy.)
+	 */
+	if (ppgtt->pin_count++)
+		return 0;
+
 	/*
 	 * PPGTT PDEs reside in the GGTT and consists of 512 entries. The
 	 * allocator works in address space sizes, so it's multiplied by page
@@ -2074,6 +2082,17 @@ static int gen6_ppgtt_pin(struct i915_hw_ppgtt *base)
 			    PIN_GLOBAL | PIN_HIGH);
 }
 
+void gen6_ppgtt_unpin(struct i915_hw_ppgtt *base)
+{
+	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base);
+
+	GEM_BUG_ON(!ppgtt->pin_count);
+	if (--ppgtt->pin_count)
+		return;
+
+	i915_vma_unpin(ppgtt->vma);
+}
+
 static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 {
 	struct i915_ggtt * const ggtt = &i915->ggtt;
@@ -2121,21 +2140,8 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 	if (err)
 		goto err_vma;
 
-	err = gen6_ppgtt_pin(&ppgtt->base);
-	if (err)
-		goto err_pd;
-
-	DRM_DEBUG_DRIVER("Allocated pde space (%lldM) at GTT entry: %llx\n",
-			 ppgtt->vma->node.size >> 20,
-			 ppgtt->vma->node.start / PAGE_SIZE);
-
-	DRM_DEBUG_DRIVER("Adding PPGTT at offset %x\n",
-			 ppgtt->base.pd.base.ggtt_offset << 10);
-
 	return &ppgtt->base;
 
-err_pd:
-	gen6_ppgtt_free_pd(ppgtt);
 err_vma:
 	i915_vma_destroy(ppgtt->vma);
 err_scratch:
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index c2f270c90bea..c20a4f06db37 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -413,6 +413,8 @@ struct gen6_hw_ppgtt {
 	struct i915_vma *vma;
 	gen6_pte_t __iomem *pd_addr;
 
+	unsigned int pin_count;
+
 	int (*switch_mm)(struct gen6_hw_ppgtt *ppgtt, struct i915_request *rq);
 };
 
@@ -627,6 +629,9 @@ static inline void i915_ppgtt_put(struct i915_hw_ppgtt *ppgtt)
 		kref_put(&ppgtt->ref, i915_ppgtt_release);
 }
 
+int gen6_ppgtt_pin(struct i915_hw_ppgtt *base);
+void gen6_ppgtt_unpin(struct i915_hw_ppgtt *base);
+
 void i915_check_and_clear_faults(struct drm_i915_private *dev_priv);
 void i915_gem_suspend_gtt_mappings(struct drm_i915_private *dev_priv);
 void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 7ea4660f13e1..fb8d6217b03c 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1195,6 +1195,27 @@ static void intel_ring_context_destroy(struct intel_context *ce)
 		__i915_gem_object_release_unless_active(ce->state->obj);
 }
 
+static int __context_pin_ppgtt(struct i915_gem_context *ctx)
+{
+	struct i915_hw_ppgtt *ppgtt;
+	int err = 0;
+
+	ppgtt = ctx->ppgtt ?: ctx->i915->mm.aliasing_ppgtt;
+	if (ppgtt)
+		err = gen6_ppgtt_pin(ppgtt);
+
+	return err;
+}
+
+static void __context_unpin_ppgtt(struct i915_gem_context *ctx)
+{
+	struct i915_hw_ppgtt *ppgtt;
+
+	ppgtt = ctx->ppgtt ?: ctx->i915->mm.aliasing_ppgtt;
+	if (ppgtt)
+		gen6_ppgtt_unpin(ppgtt);
+}
+
 static int __context_pin(struct intel_context *ce)
 {
 	struct i915_vma *vma;
@@ -1243,6 +1264,7 @@ static void __context_unpin(struct intel_context *ce)
 
 static void intel_ring_context_unpin(struct intel_context *ce)
 {
+	__context_unpin_ppgtt(ce->gem_context);
 	__context_unpin(ce);
 
 	i915_gem_context_put(ce->gem_context);
@@ -1340,6 +1362,10 @@ __ring_context_pin(struct intel_engine_cs *engine,
 	if (err)
 		goto err;
 
+	err = __context_pin_ppgtt(ce->gem_context);
+	if (err)
+		goto err_unpin;
+
 	i915_gem_context_get(ctx);
 
 	/* One ringbuffer to rule them all */
@@ -1348,6 +1374,8 @@ __ring_context_pin(struct intel_engine_cs *engine,
 
 	return ce;
 
+err_unpin:
+	__context_unpin(ce);
 err:
 	ce->pin_count = 0;
 	return ERR_PTR(err);
-- 
2.17.1