[Intel-gfx] [PATCH 12/17] drm/i915/gtt: Free unused page tables on unbind the context

[Chris Wilson]

As we cannot reliably change used page tables while the context is
active, the earliest opportunity we have to recover excess pages is when
the context becomes idle. So whenever we unbind the context (it must be
idle, and indeed being evicted) free the unused ptes.

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: Matthew Auld <matthew.william.auld at gmail.com>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 44 +++++++++++++++++++++++++----
 drivers/gpu/drm/i915/i915_gem_gtt.h |  1 +
 2 files changed, 40 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 3dc17793afac..8883e75cb594 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1753,20 +1753,28 @@ static void gen6_ppgtt_enable(struct drm_i915_private *dev_priv)
 static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 				   u64 start, u64 length)
 {
-	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
+	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
 	unsigned int first_entry = start >> PAGE_SHIFT;
 	unsigned int pde = first_entry / GEN6_PTES;
 	unsigned int pte = first_entry % GEN6_PTES;
 	unsigned int num_entries = length >> PAGE_SHIFT;
-	gen6_pte_t scratch_pte =
+	const gen6_pte_t scratch_pte =
 		vm->pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
 
 	while (num_entries) {
-		struct i915_page_table *pt = ppgtt->pd.page_table[pde++];
-		unsigned int end = min(pte + num_entries, GEN6_PTES);
+		struct i915_page_table *pt = ppgtt->base.pd.page_table[pde++];
+		const unsigned int end = min(pte + num_entries, GEN6_PTES);
+		const unsigned int count = end - pte;
 		gen6_pte_t *vaddr;
 
-		num_entries -= end - pte;
+		GEM_BUG_ON(pt == vm->scratch_pt);
+
+		num_entries -= count;
+
+		GEM_BUG_ON(count > pt->used_ptes);
+		pt->used_ptes -= count;
+		if (!pt->used_ptes)
+			ppgtt->scan_for_unused_pt = true;
 
 		/*
 		 * Note that the hw doesn't support removing PDE on the fly
@@ -1798,6 +1806,8 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 	struct sgt_dma iter = sgt_dma(vma);
 	gen6_pte_t *vaddr;
 
+	GEM_BUG_ON(ppgtt->pd.page_table[act_pt] == vm->scratch_pt);
+
 	vaddr = kmap_atomic_px(ppgtt->pd.page_table[act_pt]);
 	do {
 		vaddr[act_pte] = pte_encode | GEN6_PTE_ADDR_ENCODE(iter.dma);
@@ -1833,6 +1843,8 @@ static int gen6_alloc_va_range(struct i915_address_space *vm,
 	bool flush = false;
 
 	gen6_for_each_pde(pt, &ppgtt->base.pd, start, length, pde) {
+		const unsigned int count = gen6_pte_count(start, length);
+
 		if (pt == vm->scratch_pt) {
 			pt = alloc_pt(vm);
 			if (IS_ERR(pt))
@@ -1846,7 +1858,11 @@ static int gen6_alloc_va_range(struct i915_address_space *vm,
 				gen6_write_pde(ppgtt, pde, pt);
 				flush = true;
 			}
+
+			GEM_BUG_ON(pt->used_ptes);
 		}
+
+		pt->used_ptes += count;
 	}
 
 	if (flush) {
@@ -1948,6 +1964,24 @@ static int pd_vma_bind(struct i915_vma *vma,
 
 static void pd_vma_unbind(struct i915_vma *vma)
 {
+	struct gen6_hw_ppgtt *ppgtt = vma->private;
+	struct i915_page_table * const scratch_pt = ppgtt->base.vm.scratch_pt;
+	struct i915_page_table *pt;
+	unsigned int pde;
+
+	if (!ppgtt->scan_for_unused_pt)
+		return;
+
+	/* Free all no longer used page tables */
+	gen6_for_all_pdes(pt, &ppgtt->base.pd, pde) {
+		if (pt->used_ptes || pt == scratch_pt)
+			continue;
+
+		free_pt(&ppgtt->base.vm, pt);
+		ppgtt->base.pd.page_table[pde] = scratch_pt;
+	}
+
+	ppgtt->scan_for_unused_pt = false;
 }
 
 static const struct i915_vma_ops pd_vma_ops = {
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index d7b7b4afe060..46c95d188580 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -414,6 +414,7 @@ struct gen6_hw_ppgtt {
 	gen6_pte_t __iomem *pd_addr;
 
 	unsigned int pin_count;
+	bool scan_for_unused_pt;
 };
 
 #define __to_gen6_ppgtt(base) container_of(base, struct gen6_hw_ppgtt, base)
-- 
2.17.1