From: Yong Zhao <yong.zhao@amd.com>
Date: Fri, 13 Jul 2018 16:17:43 -0400
Subject: drm/amdkfd: Consolidate duplicate memory banks info in topology
Git-commit: f3ed5df84c268235fb1d489ab8979af423da02de
Patch-mainline: v4.19-rc1
References: FATE#326289 FATE#326079 FATE#326049 FATE#322398 FATE#326166

If there are several memory banks that has the same properties in CRAT,
we aggregate them into one memory bank. This cleans up memory banks on
APUs (e.g. Raven) where the CRAT reports each memory channel as a
separate bank. This only confuses user mode, which only deals with
virtual memory.

Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Acked-by: Petr Tesarik <ptesarik@suse.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_crat.c |   57 +++++++++++++++++++++++++++-------
 1 file changed, 46 insertions(+), 11 deletions(-)

--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -189,6 +189,21 @@ static int kfd_parse_subtype_cu(struct c
 	return 0;
 }
 
+static struct kfd_mem_properties *
+find_subtype_mem(uint32_t heap_type, uint32_t flags, uint32_t width,
+		struct kfd_topology_device *dev)
+{
+	struct kfd_mem_properties *props;
+
+	list_for_each_entry(props, &dev->mem_props, list) {
+		if (props->heap_type == heap_type
+				&& props->flags == flags
+				&& props->width == width)
+			return props;
+	}
+
+	return NULL;
+}
 /* kfd_parse_subtype_mem - parse memory subtypes and attach it to correct
  * topology device present in the device_list
  */
@@ -197,36 +212,56 @@ static int kfd_parse_subtype_mem(struct
 {
 	struct kfd_mem_properties *props;
 	struct kfd_topology_device *dev;
+	uint32_t heap_type;
+	uint64_t size_in_bytes;
+	uint32_t flags = 0;
+	uint32_t width;
 
 	pr_debug("Found memory entry in CRAT table with proximity_domain=%d\n",
 			mem->proximity_domain);
 	list_for_each_entry(dev, device_list, list) {
 		if (mem->proximity_domain == dev->proximity_domain) {
-			props = kfd_alloc_struct(props);
-			if (!props)
-				return -ENOMEM;
-
 			/* We're on GPU node */
 			if (dev->node_props.cpu_cores_count == 0) {
 				/* APU */
 				if (mem->visibility_type == 0)
-					props->heap_type =
+					heap_type =
 						HSA_MEM_HEAP_TYPE_FB_PRIVATE;
 				/* dGPU */
 				else
-					props->heap_type = mem->visibility_type;
+					heap_type = mem->visibility_type;
 			} else
-				props->heap_type = HSA_MEM_HEAP_TYPE_SYSTEM;
+				heap_type = HSA_MEM_HEAP_TYPE_SYSTEM;
 
 			if (mem->flags & CRAT_MEM_FLAGS_HOT_PLUGGABLE)
-				props->flags |= HSA_MEM_FLAGS_HOT_PLUGGABLE;
+				flags |= HSA_MEM_FLAGS_HOT_PLUGGABLE;
 			if (mem->flags & CRAT_MEM_FLAGS_NON_VOLATILE)
-				props->flags |= HSA_MEM_FLAGS_NON_VOLATILE;
+				flags |= HSA_MEM_FLAGS_NON_VOLATILE;
 
-			props->size_in_bytes =
+			size_in_bytes =
 				((uint64_t)mem->length_high << 32) +
 							mem->length_low;
-			props->width = mem->width;
+			width = mem->width;
+
+			/* Multiple banks of the same type are aggregated into
+			 * one. User mode doesn't care about multiple physical
+			 * memory segments. It's managed as a single virtual
+			 * heap for user mode.
+			 */
+			props = find_subtype_mem(heap_type, flags, width, dev);
+			if (props) {
+				props->size_in_bytes += size_in_bytes;
+				break;
+			}
+
+			props = kfd_alloc_struct(props);
+			if (!props)
+				return -ENOMEM;
+
+			props->heap_type = heap_type;
+			props->flags = flags;
+			props->size_in_bytes = size_in_bytes;
+			props->width = width;
 
 			dev->node_props.mem_banks_count++;
 			list_add_tail(&props->list, &dev->mem_props);