On 2024-10-28 16:43, Xiaogang.Chen wrote:
From: Xiaogang Chen <xiaogang.chen@xxxxxxx>
kfd process kref count(process->ref) is initialized to 1 by kref_init. After
it is created not need to increase its kref. Instad add kfd process kref at kfd
process mmu notifier allocation since we already decrease the kref at
free_notifier of mmu_notifier_ops, so pair them.
When user process opens kfd node multiple times the kfd process kref is
increased each time to balance with kfd node close operation.
Signed-off-by: Xiaogang Chen Xiaogang.Chen@xxxxxxx
Reviewed-by: Felix Kuehling <felix.kuehling@xxxxxxx>
---
drivers/gpu/drm/amd/amdkfd/kfd_process.c | 14 ++++++--------
1 file changed, 6 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index d07acf1b2f93..d871d5320297 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -850,8 +850,10 @@ struct kfd_process *kfd_create_process(struct task_struct *thread)
goto out;
}
- /* A prior open of /dev/kfd could have already created the process. */
- process = find_process(thread, false);
+ /* A prior open of /dev/kfd could have already created the process.
+ * find_process will increase process kref in this case
+ */
+ process = find_process(thread, true);
if (process) {
pr_debug("Process already found\n");
} else {
@@ -899,8 +901,6 @@ struct kfd_process *kfd_create_process(struct task_struct *thread)
init_waitqueue_head(&process->wait_irq_drain);
}
out:
- if (!IS_ERR(process))
- kref_get(&process->ref);
mutex_unlock(&kfd_processes_mutex);
mmput(thread->mm);
@@ -1186,10 +1186,8 @@ static void kfd_process_ref_release(struct kref *ref)
static struct mmu_notifier *kfd_process_alloc_notifier(struct mm_struct *mm)
{
- int idx = srcu_read_lock(&kfd_processes_srcu);
- struct kfd_process *p = find_process_by_mm(mm);
-
- srcu_read_unlock(&kfd_processes_srcu, idx);
+ /* This increments p->ref counter if kfd process p exists */
+ struct kfd_process *p = kfd_lookup_process_by_mm(mm);
return p ? &p->mmu_notifier : ERR_PTR(-ESRCH);
}
