drm/i915/gt: Switch to object allocations for page directories

The GEM object is grossly overweight for the practicality of tracking
large numbers of individual pages, yet it is currently our only
abstraction for tracking DMA allocations. Since those allocations need
to be reserved upfront before an operation, and that we need to break
away from simple system memory, we need to ditch using plain struct page
wrappers.

In the process, we drop the WC mapping as we ended up clflushing
everything anyway due to various issues across a wider range of
platforms. Though in a future step, we need to drop the kmap_atomic
approach which suggests we need to pre-map all the pages and keep them
mapped.

v2: Verify our large scratch page is suitably DMA aligned; and manually
clear the scratch since we are allocating plain struct pages full of
prior content.

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/20200729164219.5737-2-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, 13 insertions, 4 deletions

diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 3c3b9842bbbd..1570eb8aa978 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -403,6 +403,14 @@ static void release_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 	wa_ctx->indirect_ctx.shadow_va = NULL;
 }
 
+static void set_dma_address(struct i915_page_directory *pd, dma_addr_t addr)
+{
+	struct scatterlist *sg = pd->pt.base->mm.pages->sgl;
+
+	/* This is not a good idea */
+	sg->dma_address = addr;
+}
+
 static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
 					  struct intel_context *ce)
 {
@@ -411,7 +419,7 @@ static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
 	int i = 0;
 
 	if (mm->ppgtt_mm.root_entry_type == GTT_TYPE_PPGTT_ROOT_L4_ENTRY) {
-		px_dma(ppgtt->pd) = mm->ppgtt_mm.shadow_pdps[0];
+		set_dma_address(ppgtt->pd, mm->ppgtt_mm.shadow_pdps[0]);
 	} else {
 		for (i = 0; i < GVT_RING_CTX_NR_PDPS; i++) {
 			struct i915_page_directory * const pd =
@@ -421,7 +429,8 @@ static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
 			   shadow ppgtt. */
 			if (!pd)
 				break;
-			px_dma(pd) = mm->ppgtt_mm.shadow_pdps[i];
+
+			set_dma_address(pd, mm->ppgtt_mm.shadow_pdps[i]);
 		}
 	}
 }
@@ -1240,13 +1249,13 @@ i915_context_ppgtt_root_restore(struct intel_vgpu_submission *s,
 	int i;
 
 	if (i915_vm_is_4lvl(&ppgtt->vm)) {
-		px_dma(ppgtt->pd) = s->i915_context_pml4;
+		set_dma_address(ppgtt->pd, s->i915_context_pml4);
 	} else {
 		for (i = 0; i < GEN8_3LVL_PDPES; i++) {
 			struct i915_page_directory * const pd =
 				i915_pd_entry(ppgtt->pd, i);
 
-			px_dma(pd) = s->i915_context_pdps[i];
+			set_dma_address(pd, s->i915_context_pdps[i]);
 		}
 	}
 }