summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorSrinivasan Shanmugam <srinivasan.shanmugam@amd.com>2024-10-04 06:42:39 +0300
committerAlex Deucher <alexander.deucher@amd.com>2024-11-04 20:05:29 +0300
commit922f0e00017b09d9d47e3efac008c8b20ed546a0 (patch)
treeebf0280b697ddbbbe30e30805178cdff09e2e097
parent136ce12bd5907388cb4e9aa63ee5c9c8c441640b (diff)
downloadlinux-922f0e00017b09d9d47e3efac008c8b20ed546a0.tar.xz
drm/amdkfd: Use dynamic allocation for CU occupancy array in 'kfd_get_cu_occupancy()'
The `kfd_get_cu_occupancy` function previously declared a large `cu_occupancy` array as a local variable, which could lead to stack overflows due to excessive stack usage. This commit replaces the static array allocation with dynamic memory allocation using `kcalloc`, thereby reducing the stack size. This change avoids the risk of stack overflows in kernel space, in scenarios where `AMDGPU_MAX_QUEUES` is large. The allocated memory is freed using `kfree` before the function returns to prevent memory leaks. Fixes the below with gcc W=1: drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_process.c: In function ‘kfd_get_cu_occupancy’: drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_process.c:322:1: warning: the frame size of 1056 bytes is larger than 1024 bytes [-Wframe-larger-than=] 322 | } | ^ Fixes: 6ae9e1aba97e ("drm/amdkfd: Update logic for CU occupancy calculations") Cc: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Cc: Felix Kuehling <felix.kuehling@amd.com> Cc: Christian König <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com> Suggested-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Mukul Joshi <mukul.joshi@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_process.c9
1 files changed, 6 insertions, 3 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index d4aa843aacfd..6bab6fc6a35d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -271,11 +271,9 @@ static int kfd_get_cu_occupancy(struct attribute *attr, char *buffer)
struct kfd_process *proc = NULL;
struct kfd_process_device *pdd = NULL;
int i;
- struct kfd_cu_occupancy cu_occupancy[AMDGPU_MAX_QUEUES];
+ struct kfd_cu_occupancy *cu_occupancy;
u32 queue_format;
- memset(cu_occupancy, 0x0, sizeof(cu_occupancy));
-
pdd = container_of(attr, struct kfd_process_device, attr_cu_occupancy);
dev = pdd->dev;
if (dev->kfd2kgd->get_cu_occupancy == NULL)
@@ -293,6 +291,10 @@ static int kfd_get_cu_occupancy(struct attribute *attr, char *buffer)
wave_cnt = 0;
max_waves_per_cu = 0;
+ cu_occupancy = kcalloc(AMDGPU_MAX_QUEUES, sizeof(*cu_occupancy), GFP_KERNEL);
+ if (!cu_occupancy)
+ return -ENOMEM;
+
/*
* For GFX 9.4.3, fetch the CU occupancy from the first XCC in the partition.
* For AQL queues, because of cooperative dispatch we multiply the wave count
@@ -318,6 +320,7 @@ static int kfd_get_cu_occupancy(struct attribute *attr, char *buffer)
/* Translate wave count to number of compute units */
cu_cnt = (wave_cnt + (max_waves_per_cu - 1)) / max_waves_per_cu;
+ kfree(cu_occupancy);
return snprintf(buffer, PAGE_SIZE, "%d\n", cu_cnt);
}