[PATCH] drm/amdkfd: Ensure gpu_id is unique

[Harish Kasiviswanathan <Harish.Kasiviswanathan@xxxxxxx>]

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

Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@xxxxxxx>
---
 drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 26 ++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index b93913934b03..01d4c2e10c6d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1095,6 +1095,8 @@ static uint32_t kfd_generate_gpu_id(struct kfd_node *gpu)
 	uint32_t hashout;
 	uint32_t buf[8];
 	uint64_t local_mem_size;
+	struct kfd_topology_device *dev;
+	bool is_unique;
 	int i;
 
 	if (!gpu)
@@ -1115,6 +1117,28 @@ static uint32_t kfd_generate_gpu_id(struct kfd_node *gpu)
 	for (i = 0, hashout = 0; i < 8; i++)
 		hashout ^= hash_32(buf[i], KFD_GPU_ID_HASH_WIDTH);
 
+	/* hash generated could be non-unique. Check if it is unique.
+	 * If not unique increment till unique one is found. In case
+	 * of overflow, restart from 1
+	*/
+	down_read(&topology_lock);
+	do {
+		is_unique = true;
+		list_for_each_entry(dev, &topology_device_list, list) {
+			if (dev->gpu && dev->gpu_id == hashout) {
+				is_unique = false;
+				break;
+			}
+		}
+		if (unlikely(!is_unique)) {
+			hashout = (hashout + 1) &
+				  ((1 << KFD_GPU_ID_HASH_WIDTH) - 1);
+			if (!hashout)
+				hashout = 1;
+		}
+	} while (!is_unique);
+	up_read(&topology_lock);
+
 	return hashout;
 }
 /* kfd_assign_gpu - Attach @gpu to the correct kfd topology device. If
@@ -1946,7 +1970,6 @@ 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.");
@@ -1969,6 +1992,7 @@ 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;
 
-- 
2.34.1