From: Zhu Lingshan <lingshan.zhu@amd.com>
Date: Mon, 21 Apr 2025 07:47:54 +0000 (+0800)
Subject: amdkfd: mark the first kfd_process as the primary one
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=3272cd887f2bc27825a6c053ca174dbb6eabc636;p=thirdparty%2Fkernel%2Flinux.git

amdkfd: mark the first kfd_process as the primary one

The first kfd_process is created through open(),
this commit marks it as the primary kfd_process
by assigning a primary id for its context_id.

Only the primary process should register the mmu_notifier.

Signed-off-by: Zhu Lingshan <lingshan.zhu@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index ced5a84c4328..c29e085dcef7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1017,9 +1017,14 @@ struct kfd_process {
 
 	/* if gpu page fault sent to KFD */
 	bool gpu_page_fault;
+
+	/*kfd context id */
+	u16 context_id;
 };
 
 #define KFD_PROCESS_TABLE_SIZE 8 /* bits: 256 entries */
+#define KFD_CONTEXT_ID_PRIMARY	0xFFFF
+
 extern DECLARE_HASHTABLE(kfd_processes_table, KFD_PROCESS_TABLE_SIZE);
 extern struct srcu_struct kfd_processes_srcu;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index a085faac9fe1..307cf4ccc2a3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -68,7 +68,7 @@ static struct workqueue_struct *kfd_restore_wq;
 static struct kfd_process *find_process(const struct task_struct *thread,
 					bool ref);
 static void kfd_process_ref_release(struct kref *ref);
-static struct kfd_process *create_process(const struct task_struct *thread);
+static struct kfd_process *create_process(const struct task_struct *thread, bool primary);
 
 static void evict_process_worker(struct work_struct *work);
 static void restore_process_worker(struct work_struct *work);
@@ -867,7 +867,7 @@ struct kfd_process *kfd_create_process(struct task_struct *thread)
 	if (process) {
 		pr_debug("Process already found\n");
 	} else {
-		process = create_process(thread);
+		process = create_process(thread, true);
 		if (IS_ERR(process))
 			goto out;
 
@@ -1516,7 +1516,7 @@ void kfd_process_set_trap_debug_flag(struct qcm_process_device *qpd,
  * On return the kfd_process is fully operational and will be freed when the
  * mm is released
  */
-static struct kfd_process *create_process(const struct task_struct *thread)
+static struct kfd_process *create_process(const struct task_struct *thread, bool primary)
 {
 	struct kfd_process *process;
 	struct mmu_notifier *mn;
@@ -1532,6 +1532,7 @@ static struct kfd_process *create_process(const struct task_struct *thread)
 	process->lead_thread = thread->group_leader;
 	process->n_pdds = 0;
 	process->queues_paused = false;
+
 	INIT_DELAYED_WORK(&process->eviction_work, evict_process_worker);
 	INIT_DELAYED_WORK(&process->restore_work, restore_process_worker);
 	process->last_restore_timestamp = get_jiffies_64();
@@ -1575,12 +1576,15 @@ static struct kfd_process *create_process(const struct task_struct *thread)
 	 * After this point, mmu_notifier_put will trigger the cleanup by
 	 * dropping the last process reference in the free_notifier.
 	 */
-	mn = mmu_notifier_get(&kfd_process_mmu_notifier_ops, process->mm);
-	if (IS_ERR(mn)) {
-		err = PTR_ERR(mn);
-		goto err_register_notifier;
+	if (primary) {
+		process->context_id = KFD_CONTEXT_ID_PRIMARY;
+		mn = mmu_notifier_get(&kfd_process_mmu_notifier_ops, process->mm);
+		if (IS_ERR(mn)) {
+			err = PTR_ERR(mn);
+			goto err_register_notifier;
+		}
+		BUG_ON(mn != &process->mmu_notifier);
 	}
-	BUG_ON(mn != &process->mmu_notifier);
 
 	kfd_unref_process(process);
 	get_task_struct(process->lead_thread);