niansa-misc/linux
1
0
Fork 0
mirror of synced 2025-03-06 20:59:54 +01:00
Code Issues Projects Releases Packages Wiki Activity

drm/amdkfd: Ensure gpu_id is unique

Browse source 
gpu_id needs to be unique for user space to identify GPUs via KFD
interface. In the current implementation there is a very small
probability of having non unique gpu_ids.

v2: Add check to confirm if gpu_id is unique. If not unique, find one
    Changed commit header to reflect the above
v3: Use crc16 as suggested-by: Lijo Lazar <lijo.lazar@amd.com>
    Ensure that gpu_id != 0

Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Harish Kasiviswanathan 2024-05-01 17:07:59 -04:00 • committed by Alex Deucher
parent b712d7c201
commit 3ed181b8ff
1 changed files with 34 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

40
drivers/gpu/drm/amd/amdkfd/kfd_topology.c
View file

@ -31,6 +31,7 @@
#include <linux/log2.h>
#include <linux/dmi.h>
#include <linux/atomic.h>
#include <linux/crc16.h>
#include "kfd_priv.h"
#include "kfd_crat.h"
@ -1091,14 +1092,17 @@ void kfd_topology_shutdown(void)
static uint32_t kfd_generate_gpu_id(struct kfd_node *gpu)
{
uint32_t hashout;
uint32_t gpu_id;
uint32_t buf[8];
uint64_t local_mem_size;
int i;
struct kfd_topology_device *dev;
bool is_unique;
uint8_t *crc_buf;
if (!gpu)
return 0;
crc_buf = (uint8_t *)&buf;
local_mem_size = gpu->local_mem_info.local_mem_size_private +
gpu->local_mem_info.local_mem_size_public;
buf[0] = gpu->adev->pdev->devfn;
@ -1111,10 +1115,34 @@ static uint32_t kfd_generate_gpu_id(struct kfd_node *gpu)
buf[6] = upper_32_bits(local_mem_size);
buf[7] = (ffs(gpu->xcc_mask) - 1) | (NUM_XCC(gpu->xcc_mask) << 16);
for (i = 0, hashout = 0; i < 8; i++)
hashout ^= hash_32(buf[i], KFD_GPU_ID_HASH_WIDTH);
gpu_id = crc16(0, crc_buf, sizeof(buf)) &
((1 << KFD_GPU_ID_HASH_WIDTH) - 1);
return hashout;
/* There is a very small possibility when generating a
* 16 (KFD_GPU_ID_HASH_WIDTH) bit value from 8 word buffer
* that the value could be 0 or non-unique. So, check if
* it is unique and non-zero. If not unique increment till
* unique one is found. In case of overflow, restart from 1
*/
down_read(&topology_lock);
do {
is_unique = true;
if (!gpu_id)
gpu_id = 1;
list_for_each_entry(dev, &topology_device_list, list) {
if (dev->gpu && dev->gpu_id == gpu_id) {
is_unique = false;
break;
}
}
if (unlikely(!is_unique))
gpu_id = (gpu_id + 1) &
((1 << KFD_GPU_ID_HASH_WIDTH) - 1);
} while (!is_unique);
up_read(&topology_lock);
return gpu_id;
}
/* kfd_assign_gpu - Attach @gpu to the correct kfd topology device. If
* the GPU device is not already present in the topology device
@ -1945,7 +1973,6 @@ int kfd_topology_add_device(struct kfd_node *gpu)
struct amdgpu_gfx_config *gfx_info = &gpu->adev->gfx.config;
struct amdgpu_cu_info *cu_info = &gpu->adev->gfx.cu_info;
gpu_id = kfd_generate_gpu_id(gpu);
if (gpu->xcp && !gpu->xcp->ddev) {
dev_warn(gpu->adev->dev,
"Won't add GPU to topology since it has no drm node assigned.");
@ -1968,6 +1995,7 @@ int kfd_topology_add_device(struct kfd_node *gpu)
if (res)
return res;
gpu_id = kfd_generate_gpu_id(gpu);
dev->gpu_id = gpu_id;
gpu->id = gpu_id;