drm/i915/gtt: Replace struct_mutex serialisation for allocation

Instead of relying on the caller holding struct_mutex across the
allocation, push the allocation under a tree of spinlocks stored inside
the page tables. Not only should this allow us to avoid struct_mutex
here, but it will allow multiple users to lock independent ranges for
concurrent allocations, and operate independently. This is vital for
pushing the GTT manipulation into a background thread where dependency
on struct_mutex is verboten, and for allowing other callers to avoid
struct_mutex altogether.

v2: Restore lost GEM_BUG_ON for removing too many PTE from
gen6_ppgtt_clear_range.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190604153830.19096-1-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/i915_gem_gtt.h

@@ -248,25 +248,28 @@ struct i915_page_dma {
 
 struct i915_page_table {
 	struct i915_page_dma base;
-	unsigned int used_ptes;
+	atomic_t used_ptes;
 };
 
 struct i915_page_directory {
 	struct i915_page_dma base;
 
 	struct i915_page_table *page_table[I915_PDES]; /* PDEs */
-	unsigned int used_pdes;
+	atomic_t used_pdes;
+	spinlock_t lock;
 };
 
 struct i915_page_directory_pointer {
 	struct i915_page_dma base;
 	struct i915_page_directory **page_directory;
-	unsigned int used_pdpes;
+	atomic_t used_pdpes;
+	spinlock_t lock;
 };
 
 struct i915_pml4 {
 	struct i915_page_dma base;
 	struct i915_page_directory_pointer *pdps[GEN8_PML4ES_PER_PML4];
+	spinlock_t lock;
 };
 
 struct i915_vma_ops {