drm/i915/gtt: Preallocate Braswell top-level page directory

In order for the Braswell top-level PD to remain the same from the time
of request construction to its submission onto HW, as we may be
asynchronously rewriting the page tables (thus changing the expected
register state after having already stored the old addresses in the
request), the top level PD must be preallocated.

So wave goodbye to our lazy allocation of those 4x2 pages.

v2: A little bit of write-flushing required (presumably it always has
been required, but now we are more susceptible and it is showing up!)

v3: Put back the forced-PD-reload on every batch, we can't survive
without it and explicitly marking the context for PD reload makes
Braswell turn nasty.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823141421.2398-1-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/gem/i915_gem_context.c

@@ -1003,12 +1003,18 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data)
 		intel_ring_advance(rq, cs);
 	} else if (HAS_LOGICAL_RING_CONTEXTS(engine->i915)) {
 		struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
+		int err;
+
+		/* Magic required to prevent forcewake errors! */
+		err = engine->emit_flush(rq, EMIT_INVALIDATE);
+		if (err)
+			return err;
 
 		cs = intel_ring_begin(rq, 4 * GEN8_3LVL_PDPES + 2);
 		if (IS_ERR(cs))
 			return PTR_ERR(cs);
 
-		*cs++ = MI_LOAD_REGISTER_IMM(2 * GEN8_3LVL_PDPES);
+		*cs++ = MI_LOAD_REGISTER_IMM(2 * GEN8_3LVL_PDPES) | MI_LRI_FORCE_POSTED;
 		for (i = GEN8_3LVL_PDPES; i--; ) {
 			const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i);
 

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -168,6 +168,7 @@ static int ppgtt_bind_vma(struct i915_vma *vma,
 		pte_flags |= PTE_READ_ONLY;
 
 	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
+	wmb();
 
 	return 0;
 }
@@ -1426,6 +1427,7 @@ static int gen8_preallocate_top_level_pdp(struct i915_ppgtt *ppgtt)
 		set_pd_entry(pd, idx, pde);
 		atomic_inc(px_used(pde)); /* keep pinned */
 	}
+	wmb();
 
 	return 0;
 }
@@ -1513,12 +1515,10 @@ static struct i915_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 	}
 
 	if (!i915_vm_is_4lvl(&ppgtt->vm)) {
-		if (intel_vgpu_active(i915)) {
 		err = gen8_preallocate_top_level_pdp(ppgtt);
 		if (err)
 			goto err_free_pd;
 	}
-	}
 
 	ppgtt->vm.insert_entries = gen8_ppgtt_insert;
 	ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc;