[PATCH 05/10] drm/amdgpu: update pt shadow while updating pt

[Chunming Zhou]

Change-Id: Ibc8fb4c5c9be38934ebd6d56f1cbd49cb82d53af
Signed-off-by: Chunming Zhou <David1.Zhou at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 30 +++++++++++++++++++++---------
 1 file changed, 21 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 215debb..30a1dcc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -787,13 +787,15 @@ err:
  * @end: end of GPU address range
  * @dst: destination address to map to, the next dst inside the function
  * @flags: mapping flags
+ * @shadow: update shadow or not
  *
  * Update the page tables in the range @start - @end.
  */
 static void amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
 				  struct amdgpu_vm *vm,
 				  uint64_t start, uint64_t end,
-				  uint64_t dst, uint32_t flags)
+				  uint64_t dst, uint32_t flags,
+				  bool shadow)
 {
 	const uint64_t mask = AMDGPU_VM_PTE_COUNT - 1;
 
@@ -807,7 +809,8 @@ static void amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
 	/* initialize the variables */
 	addr = start;
 	pt_idx = addr >> amdgpu_vm_block_size;
-	pt = vm->page_tables[pt_idx].entry.robj;
+	pt = shadow ? vm->page_tables[pt_idx].entry.robj->shadow :
+		vm->page_tables[pt_idx].entry.robj;
 
 	if ((addr & ~mask) == (end & ~mask))
 		nptes = end - addr;
@@ -826,7 +829,8 @@ static void amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
 	/* walk over the address space and update the page tables */
 	while (addr < end) {
 		pt_idx = addr >> amdgpu_vm_block_size;
-		pt = vm->page_tables[pt_idx].entry.robj;
+		pt = shadow ? vm->page_tables[pt_idx].entry.robj->shadow :
+			vm->page_tables[pt_idx].entry.robj;
 
 		if ((addr & ~mask) == (end & ~mask))
 			nptes = end - addr;
@@ -870,11 +874,13 @@ static void amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
  * @end: last PTE to handle
  * @dst: addr those PTEs should point to
  * @flags: hw mapping flags
+ * @shadow: update shaow or not
  */
 static void amdgpu_vm_frag_ptes(struct amdgpu_pte_update_params	*params,
 				struct amdgpu_vm *vm,
 				uint64_t start, uint64_t end,
-				uint64_t dst, uint32_t flags)
+				uint64_t dst, uint32_t flags,
+				bool shadow)
 {
 	/**
 	 * The MC L1 TLB supports variable sized pages, based on a fragment
@@ -906,7 +912,8 @@ static void amdgpu_vm_frag_ptes(struct amdgpu_pte_update_params	*params,
 	if (params->src || params->pages_addr || !(flags & AMDGPU_PTE_VALID) ||
 	    (frag_start >= frag_end)) {
 
-		amdgpu_vm_update_ptes(params, vm, start, end, dst, flags);
+		amdgpu_vm_update_ptes(params, vm, start, end, dst,
+				      flags, shadow);
 		return;
 	}
 
@@ -917,18 +924,19 @@ static void amdgpu_vm_frag_ptes(struct amdgpu_pte_update_params	*params,
 	/* handle the 4K area at the beginning */
 	if (start != frag_start) {
 		amdgpu_vm_update_ptes(params, vm, start, frag_start,
-				      dst, flags);
+				      dst, flags, shadow);
 		dst += (frag_start - start) * AMDGPU_GPU_PAGE_SIZE;
 	}
 
 	/* handle the area in the middle */
 	amdgpu_vm_update_ptes(params, vm, frag_start, frag_end, dst,
-			      flags | AMDGPU_PTE_FRAG(frag));
+			      flags | AMDGPU_PTE_FRAG(frag), shadow);
 
 	/* handle the 4K area at the end */
 	if (frag_end != end) {
 		dst += (frag_end - frag_start) * AMDGPU_GPU_PAGE_SIZE;
-		amdgpu_vm_update_ptes(params, vm, frag_end, end, dst, flags);
+		amdgpu_vm_update_ptes(params, vm, frag_end, end, dst,
+				      flags, shadow);
 	}
 }
 
@@ -1007,6 +1015,9 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 		ndw += 2 * 10;
 	}
 
+	/* double ndw, since need to update shadow pt bo as well */
+	ndw *= 2;
+
 	r = amdgpu_job_alloc_with_ib(adev, ndw * 4, &job);
 	if (r)
 		return r;
@@ -1026,7 +1037,8 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	if (r)
 		goto error_free;
 
-	amdgpu_vm_frag_ptes(&params, vm, start, last + 1, addr, flags);
+	amdgpu_vm_frag_ptes(&params, vm, start, last + 1, addr, flags, true);
+	amdgpu_vm_frag_ptes(&params, vm, start, last + 1, addr, flags, false);
 
 	amdgpu_ring_pad_ib(ring, params.ib);
 	WARN_ON(params.ib->length_dw > ndw);
-- 
1.9.1