Patch "drm/amdkfd: reduce stack size in kfd_topology_add_device()" has been added to the 6.6-stable tree

[Sasha Levin <sashal@xxxxxxxxxx>]

This is a note to let you know that I've just added the patch titled

    drm/amdkfd: reduce stack size in kfd_topology_add_device()

to the 6.6-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     drm-amdkfd-reduce-stack-size-in-kfd_topology_add_dev.patch
and it can be found in the queue-6.6 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.



commit ab1340181dfcfc6f075850be02610fbc6673eea2
Author: Alex Deucher <alexander.deucher@xxxxxxx>
Date:   Thu Sep 21 10:32:09 2023 -0400

    drm/amdkfd: reduce stack size in kfd_topology_add_device()
    
    [ Upstream commit 4ff91f218547bfc3d230c00e46725b71a625acbc ]
    
    kfd_topology.c:2082:1: warning: the frame size of 1440 bytes is larger than 1024 bytes
    
    Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2866
    Cc: Arnd Bergmann <arnd@xxxxxxxxxx>
    Acked-by: Arnd Bergmann <arnd@xxxxxxxx>
    Acked-by: Christian König <christian.koenig@xxxxxxx>
    Reviewed-by: Felix Kuehling <Felix.Kuehling@xxxxxxx>
    Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
    Stable-dep-of: 438b39ac74e2 ("drm/amdkfd: pause autosuspend when creating pdd")
    Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 8362a71ab707..a51363e25624 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1922,7 +1922,7 @@ int kfd_topology_add_device(struct kfd_node *gpu)
 {
 	uint32_t gpu_id;
 	struct kfd_topology_device *dev;
-	struct kfd_cu_info cu_info;
+	struct kfd_cu_info *cu_info;
 	int res = 0;
 	int i;
 	const char *asic_name = amdgpu_asic_name[gpu->adev->asic_type];
@@ -1963,8 +1963,11 @@ int kfd_topology_add_device(struct kfd_node *gpu)
 	/* Fill-in additional information that is not available in CRAT but
 	 * needed for the topology
 	 */
+	cu_info = kzalloc(sizeof(struct kfd_cu_info), GFP_KERNEL);
+	if (!cu_info)
+		return -ENOMEM;
 
-	amdgpu_amdkfd_get_cu_info(dev->gpu->adev, &cu_info);
+	amdgpu_amdkfd_get_cu_info(dev->gpu->adev, cu_info);
 
 	for (i = 0; i < KFD_TOPOLOGY_PUBLIC_NAME_SIZE-1; i++) {
 		dev->node_props.name[i] = __tolower(asic_name[i]);
@@ -1974,7 +1977,7 @@ int kfd_topology_add_device(struct kfd_node *gpu)
 	dev->node_props.name[i] = '\0';
 
 	dev->node_props.simd_arrays_per_engine =
-		cu_info.num_shader_arrays_per_engine;
+		cu_info->num_shader_arrays_per_engine;
 
 	dev->node_props.gfx_target_version =
 				gpu->kfd->device_info.gfx_target_version;
@@ -2055,7 +2058,7 @@ int kfd_topology_add_device(struct kfd_node *gpu)
 	 */
 	if (dev->gpu->adev->asic_type == CHIP_CARRIZO) {
 		dev->node_props.simd_count =
-			cu_info.simd_per_cu * cu_info.cu_active_number;
+			cu_info->simd_per_cu * cu_info->cu_active_number;
 		dev->node_props.max_waves_per_simd = 10;
 	}
 
@@ -2082,6 +2085,8 @@ int kfd_topology_add_device(struct kfd_node *gpu)
 
 	kfd_notify_gpu_change(gpu_id, 1);
 
+	kfree(cu_info);
+
 	return 0;
 }