On GFXIP9.4.3 APU, allow the memory reporting as per the ttm pages
limit in NPS1 mode.
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 23 +++++++++++++++--------
1 file changed, 15 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 005ea719d2fd..fadc4d2ed071 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -25,6 +25,7 @@
#include <linux/pci.h>
#include <drm/drm_cache.h>
+#include <drm/ttm/ttm_tt.h>
#include "amdgpu.h"
#include "gmc_v9_0.h"
@@ -1896,7 +1897,8 @@ static void
gmc_v9_0_init_acpi_mem_ranges(struct amdgpu_device *adev,
struct amdgpu_mem_partition_info *mem_ranges)
{
- int num_ranges = 0, ret, mem_groups;
+ int num_ranges = 0, ret, num_nodes;
+ uint64_t node_size_ttm_override = 0;
struct amdgpu_numa_info numa_info;
int node_ids[MAX_MEM_RANGES];
int num_xcc, xcc_id;
@@ -1904,7 +1906,8 @@ gmc_v9_0_init_acpi_mem_ranges(struct amdgpu_device *adev,
num_xcc = NUM_XCC(adev->gfx.xcc_mask);
xcc_mask = (1U << num_xcc) - 1;
- mem_groups = hweight32(adev->aid_mask);
+ num_nodes = num_online_nodes();
+ node_size_ttm_override = (ttm_tt_pages_limit() << PAGE_SHIFT) / num_nodes;
for_each_inst(xcc_id, xcc_mask) {
ret = amdgpu_acpi_get_mem_info(adev, xcc_id, &numa_info);
@@ -1912,7 +1915,6 @@ gmc_v9_0_init_acpi_mem_ranges(struct amdgpu_device *adev,
continue;
if (numa_info.nid == NUMA_NO_NODE) {
- mem_ranges[0].size = numa_info.size;
mem_ranges[0].numa.node = numa_info.nid;
num_ranges = 1;
break;
@@ -1930,11 +1932,16 @@ gmc_v9_0_init_acpi_mem_ranges(struct amdgpu_device *adev,
adev->gmc.num_mem_partitions = num_ranges;
- /* If there is only partition, don't use entire size */
- if (adev->gmc.num_mem_partitions == 1) {
- mem_ranges[0].size = mem_ranges[0].size * (mem_groups - 1);
- do_div(mem_ranges[0].size, mem_groups);
- }
+ /* In NPS1 mode, we should restrict the vram reporting
+ * tied to the ttm_pages_limit which is 1/2 of the
+ * system memory. For other partition modes, the HBM is
+ * uniformly divided already per numa node reported. If
+ * user wants to go beyond the default ttm limit and
+ * maximize the ROCm allocations, they can go up to max
+ * ttm and sysmem limits.
+ */
+ if (adev->gmc.num_mem_partitions == 1)
+ mem_ranges[0].size = node_size_ttm_override;
}
static void
--
2.34.1
