diff options
Diffstat (limited to 'meta-amd-bsp/recipes-kernel/linux/linux-yocto-4.14.71/3052-drm-amdkfd-Consolidate-duplicate-memory-banks-info-i.patch')
| -rw-r--r-- | meta-amd-bsp/recipes-kernel/linux/linux-yocto-4.14.71/3052-drm-amdkfd-Consolidate-duplicate-memory-banks-info-i.patch | 112 |
1 files changed, 112 insertions, 0 deletions
diff --git a/meta-amd-bsp/recipes-kernel/linux/linux-yocto-4.14.71/3052-drm-amdkfd-Consolidate-duplicate-memory-banks-info-i.patch b/meta-amd-bsp/recipes-kernel/linux/linux-yocto-4.14.71/3052-drm-amdkfd-Consolidate-duplicate-memory-banks-info-i.patch new file mode 100644 index 00000000..b044eb52 --- /dev/null +++ b/meta-amd-bsp/recipes-kernel/linux/linux-yocto-4.14.71/3052-drm-amdkfd-Consolidate-duplicate-memory-banks-info-i.patch @@ -0,0 +1,112 @@ +From 49b0461e86d2ae3044f3ae6296831d170e9ad126 Mon Sep 17 00:00:00 2001 +From: Yong Zhao <yong.zhao@amd.com> +Date: Wed, 3 Jan 2018 15:44:36 -0500 +Subject: [PATCH 3052/4131] drm/amdkfd: Consolidate duplicate memory banks info + in topology + +If there are several memory banks that has the same properties in CRAT, +we aggregate them into one memory bank. + +Change-Id: I37978351fcf32b598164200f2b33ebdf82ac39d7 +Signed-off-by: Yong Zhao <yong.zhao@amd.com> +--- + drivers/gpu/drm/amd/amdkfd/kfd_crat.c | 57 ++++++++++++++++++++++++++++------- + 1 file changed, 46 insertions(+), 11 deletions(-) + +diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +index 1664ba3..8c254328 100644 +--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c ++++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +@@ -173,6 +173,21 @@ static int kfd_parse_subtype_cu(struct crat_subtype_computeunit *cu, + 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 + */ +@@ -181,36 +196,56 @@ static int kfd_parse_subtype_mem(struct crat_subtype_memory *mem, + { + 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); +-- +2.7.4 + |