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, 32 insertions, 14 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
index f2b75078e05f..0d9f29aea6b4 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -159,7 +159,10 @@ struct i915_page_scratch {
 
 struct i915_page_table {
 	struct i915_page_dma base;
-	atomic_t used;
+	union {
+		atomic_t used;
+		struct i915_page_table *stash;
+	};
 };
 
 struct i915_page_directory {
@@ -196,12 +199,18 @@ struct drm_i915_gem_object;
 struct i915_vma;
 struct intel_gt;
 
+struct i915_vm_pt_stash {
+	/* preallocated chains of page tables/directories */
+	struct i915_page_table *pt[2];
+};
+
 struct i915_vma_ops {
 	/* Map an object into an address space with the given cache flags. */
-	int (*bind_vma)(struct i915_address_space *vm,
-			struct i915_vma *vma,
-			enum i915_cache_level cache_level,
-			u32 flags);
+	void (*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);
 	/*
 	 * Unmap an object from an address space. This usually consists of
 	 * setting the valid PTE entries to a reserved scratch page.
@@ -257,9 +266,6 @@ struct i915_address_space {
 #define VM_CLASS_PPGTT 1
 
 	struct i915_page_scratch scratch[4];
-	unsigned int scratch_order;
-	unsigned int top;
-
 	/**
 	 * List of vma currently bound.
 	 */
@@ -276,13 +282,18 @@ struct i915_address_space {
 	/* Some systems support read-only mappings for GGTT and/or PPGTT */
 	bool has_read_only:1;
 
+	u8 top;
+	u8 pd_shift;
+	u8 scratch_order;
+
 	u64 (*pte_encode)(dma_addr_t addr,
 			  enum i915_cache_level level,
 			  u32 flags); /* Create a valid PTE */
 #define PTE_READ_ONLY	BIT(0)
 
-	int (*allocate_va_range)(struct i915_address_space *vm,
-				 u64 start, u64 length);
+	void (*allocate_va_range)(struct i915_address_space *vm,
+				  struct i915_vm_pt_stash *stash,
+				  u64 start, u64 length);
 	void (*clear_range)(struct i915_address_space *vm,
 			    u64 start, u64 length);
 	void (*insert_page)(struct i915_address_space *vm,
@@ -568,10 +579,11 @@ int ggtt_set_pages(struct i915_vma *vma);
 int ppgtt_set_pages(struct i915_vma *vma);
 void clear_pages(struct i915_vma *vma);
 
-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);
 void ppgtt_unbind_vma(struct i915_address_space *vm,
 		      struct i915_vma *vma);
 
@@ -579,6 +591,12 @@ void gtt_write_workarounds(struct intel_gt *gt);
 
 void setup_private_pat(struct intel_uncore *uncore);
 
+int i915_vm_alloc_pt_stash(struct i915_address_space *vm,
+			   struct i915_vm_pt_stash *stash,
+			   u64 size);
+void i915_vm_free_pt_stash(struct i915_address_space *vm,
+			   struct i915_vm_pt_stash *stash);
+
 static inline struct sgt_dma {
 	struct scatterlist *sg;
 	dma_addr_t dma, max;