drm/i915: Preallocate stashes for vma page-directories

We need to make the DMA allocations used for page directories to be
performed up front so that we can include those allocations in our
memory reservation pass. The downside is that we have to assume the
worst case, even before we know the final layout, and always allocate
enough page directories for this object, even when there will be overlap.
This unfortunately can be quite expensive, especially as we have to
clear/reset the page directories and DMA pages, but it should only be
required during early phases of a workload when new objects are being
discovered, or after memory/eviction pressure when we need to rebind.
Once we reach steady state, the objects should not be moved and we no
longer need to preallocating the pages tables.

It should be noted that the lifetime for the page directories DMA is
more or less decoupled from individual fences as they will be shared
across objects across timelines.

v2: Only allocate enough PD space for the PTE we may use, we do not need
to allocate PD that will be left as scratch.
v3: Store the shift unto the first PD level to encapsulate the different
PTE counts for gen6/gen8.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200729164219.5737-1-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

1 files changed, 71 insertions, 12 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
index f0862e924d11..09056544bc29 100644
--- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
@@ -155,19 +155,16 @@ struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt)
 	return ppgtt;
 }
 
-int ppgtt_bind_vma(struct i915_address_space *vm,
-		   struct i915_vma *vma,
-		   enum i915_cache_level cache_level,
-		   u32 flags)
+void ppgtt_bind_vma(struct i915_address_space *vm,
+		    struct i915_vm_pt_stash *stash,
+		    struct i915_vma *vma,
+		    enum i915_cache_level cache_level,
+		    u32 flags)
 {
 	u32 pte_flags;
-	int err;
 
 	if (!test_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma))) {
-		err = vm->allocate_va_range(vm, vma->node.start, vma->size);
-		if (err)
-			return err;
-
+		vm->allocate_va_range(vm, stash, vma->node.start, vma->size);
 		set_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma));
 	}
 
@@ -178,8 +175,6 @@ int ppgtt_bind_vma(struct i915_address_space *vm,
 
 	vm->insert_entries(vm, vma, cache_level, pte_flags);
 	wmb();
-
-	return 0;
 }
 
 void ppgtt_unbind_vma(struct i915_address_space *vm, struct i915_vma *vma)
@@ -188,12 +183,76 @@ void ppgtt_unbind_vma(struct i915_address_space *vm, struct i915_vma *vma)
 		vm->clear_range(vm, vma->node.start, vma->size);
 }
 
+static unsigned long pd_count(u64 size, int shift)
+{
+	/* Beware later misalignment */
+	return (size + 2 * (BIT_ULL(shift) - 1)) >> shift;
+}
+
+int i915_vm_alloc_pt_stash(struct i915_address_space *vm,
+			   struct i915_vm_pt_stash *stash,
+			   u64 size)
+{
+	unsigned long count;
+	int shift, n;
+
+	shift = vm->pd_shift;
+	if (!shift)
+		return 0;
+
+	count = pd_count(size, shift);
+	while (count--) {
+		struct i915_page_table *pt;
+
+		pt = alloc_pt(vm);
+		if (IS_ERR(pt)) {
+			i915_vm_free_pt_stash(vm, stash);
+			return PTR_ERR(pt);
+		}
+
+		pt->stash = stash->pt[0];
+		stash->pt[0] = pt;
+	}
+
+	for (n = 1; n < vm->top; n++) {
+		shift += ilog2(I915_PDES); /* Each PD holds 512 entries */
+		count = pd_count(size, shift);
+		while (count--) {
+			struct i915_page_directory *pd;
+
+			pd = alloc_pd(vm);
+			if (IS_ERR(pd)) {
+				i915_vm_free_pt_stash(vm, stash);
+				return PTR_ERR(pd);
+			}
+
+			pd->pt.stash = stash->pt[1];
+			stash->pt[1] = &pd->pt;
+		}
+	}
+
+	return 0;
+}
+
+void i915_vm_free_pt_stash(struct i915_address_space *vm,
+			   struct i915_vm_pt_stash *stash)
+{
+	struct i915_page_table *pt;
+	int n;
+
+	for (n = 0; n < ARRAY_SIZE(stash->pt); n++) {
+		while ((pt = stash->pt[n])) {
+			stash->pt[n] = pt->stash;
+			free_px(vm, pt);
+		}
+	}
+}
+
 int ppgtt_set_pages(struct i915_vma *vma)
 {
 	GEM_BUG_ON(vma->pages);
 
 	vma->pages = vma->obj->mm.pages;
-
 	vma->page_sizes = vma->obj->mm.page_sizes;
 
 	return 0;