drm/amdkfd: Add quiesce_mm and resume_mm to kgd2kfd_calls

These interfaces allow KGD to stop and resume all GPU user mode queue
access to a process address space. This is needed for handling MMU
notifiers of userptrs mapped for GPU access in KFD VMs.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

drivers/gpu/drm/amd/amdkfd/kfd_device.c

@@ -541,6 +541,44 @@ void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
 	spin_unlock(&kfd->interrupt_lock);
 }
 
+int kgd2kfd_quiesce_mm(struct mm_struct *mm)
+{
+	struct kfd_process *p;
+	int r;
+
+	/* Because we are called from arbitrary context (workqueue) as opposed
+	 * to process context, kfd_process could attempt to exit while we are
+	 * running so the lookup function increments the process ref count.
+	 */
+	p = kfd_lookup_process_by_mm(mm);
+	if (!p)
+		return -ESRCH;
+
+	r = kfd_process_evict_queues(p);
+
+	kfd_unref_process(p);
+	return r;
+}
+
+int kgd2kfd_resume_mm(struct mm_struct *mm)
+{
+	struct kfd_process *p;
+	int r;
+
+	/* Because we are called from arbitrary context (workqueue) as opposed
+	 * to process context, kfd_process could attempt to exit while we are
+	 * running so the lookup function increments the process ref count.
+	 */
+	p = kfd_lookup_process_by_mm(mm);
+	if (!p)
+		return -ESRCH;
+
+	r = kfd_process_restore_queues(p);
+
+	kfd_unref_process(p);
+	return r;
+}
+
 /** kgd2kfd_schedule_evict_and_restore_process - Schedules work queue that will
  *   prepare for safe eviction of KFD BOs that belong to the specified
  *   process.

drivers/gpu/drm/amd/amdkfd/kfd_module.c

@@ -43,6 +43,8 @@ static const struct kgd2kfd_calls kgd2kfd = {
 	.interrupt	= kgd2kfd_interrupt,
 	.suspend	= kgd2kfd_suspend,
 	.resume		= kgd2kfd_resume,
+	.quiesce_mm	= kgd2kfd_quiesce_mm,
+	.resume_mm	= kgd2kfd_resume_mm,
 	.schedule_evict_and_restore_process =
 			  kgd2kfd_schedule_evict_and_restore_process,
 };

drivers/gpu/drm/amd/amdkfd/kfd_priv.h

@@ -512,6 +512,8 @@ struct qcm_process_device {
 /* Approx. time before evicting the process again */
 #define PROCESS_ACTIVE_TIME_MS 10
 
+int kgd2kfd_quiesce_mm(struct mm_struct *mm);
+int kgd2kfd_resume_mm(struct mm_struct *mm);
 int kgd2kfd_schedule_evict_and_restore_process(struct mm_struct *mm,
 					       struct dma_fence *fence);
 
@@ -681,6 +683,8 @@ struct kfd_process *kfd_get_process(const struct task_struct *);
 struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid);
 struct kfd_process *kfd_lookup_process_by_mm(const struct mm_struct *mm);
 void kfd_unref_process(struct kfd_process *p);
+int kfd_process_evict_queues(struct kfd_process *p);
+int kfd_process_restore_queues(struct kfd_process *p);
 void kfd_suspend_all_processes(void);
 int kfd_resume_all_processes(void);
 

drivers/gpu/drm/amd/amdkfd/kfd_process.c

@@ -808,7 +808,7 @@ struct kfd_process *kfd_lookup_process_by_mm(const struct mm_struct *mm)
  * Eviction is reference-counted per process-device. This means multiple
  * evictions from different sources can be nested safely.
  */
-static int process_evict_queues(struct kfd_process *p)
+int kfd_process_evict_queues(struct kfd_process *p)
 {
 	struct kfd_process_device *pdd;
 	int r = 0;
@@ -844,7 +844,7 @@ static int process_evict_queues(struct kfd_process *p)
 }
 
 /* process_restore_queues - Restore all user queues of a process */
-static  int process_restore_queues(struct kfd_process *p)
+int kfd_process_restore_queues(struct kfd_process *p)
 {
 	struct kfd_process_device *pdd;
 	int r, ret = 0;
@@ -886,7 +886,7 @@ static void evict_process_worker(struct work_struct *work)
 	flush_delayed_work(&p->restore_work);
 
 	pr_debug("Started evicting pasid %d\n", p->pasid);
-	ret = process_evict_queues(p);
+	ret = kfd_process_evict_queues(p);
 	if (!ret) {
 		dma_fence_signal(p->ef);
 		dma_fence_put(p->ef);
@@ -946,7 +946,7 @@ static void restore_process_worker(struct work_struct *work)
 		return;
 	}
 
-	ret = process_restore_queues(p);
+	ret = kfd_process_restore_queues(p);
 	if (!ret)
 		pr_debug("Finished restoring pasid %d\n", p->pasid);
 	else
@@ -963,7 +963,7 @@ void kfd_suspend_all_processes(void)
 		cancel_delayed_work_sync(&p->eviction_work);
 		cancel_delayed_work_sync(&p->restore_work);
 
-		if (process_evict_queues(p))
+		if (kfd_process_evict_queues(p))
 			pr_err("Failed to suspend process %d\n", p->pasid);
 		dma_fence_signal(p->ef);
 		dma_fence_put(p->ef);

drivers/gpu/drm/amd/include/kgd_kfd_interface.h

@@ -382,6 +382,10 @@ struct kfd2kgd_calls {
  *
  * @resume: Notifies amdkfd about a resume action done to a kgd device
  *
+ * @quiesce_mm: Quiesce all user queue access to specified MM address space
+ *
+ * @resume_mm: Resume user queue access to specified MM address space
+ *
  * @schedule_evict_and_restore_process: Schedules work queue that will prepare
  * for safe eviction of KFD BOs that belong to the specified process.
  *
@@ -399,6 +403,8 @@ struct kgd2kfd_calls {
 	void (*interrupt)(struct kfd_dev *kfd, const void *ih_ring_entry);
 	void (*suspend)(struct kfd_dev *kfd);
 	int (*resume)(struct kfd_dev *kfd);
+	int (*quiesce_mm)(struct mm_struct *mm);
+	int (*resume_mm)(struct mm_struct *mm);
 	int (*schedule_evict_and_restore_process)(struct mm_struct *mm,
 			struct dma_fence *fence);
 };