drm/amdkfd: CRIU Implement KFD resume ioctl

This adds support to create userptr BOs on restore and introduces a new
ioctl op to restart memory notifiers for the restored userptr BOs.
When doing CRIU restore MMU notifications can happen anytime after we call
amdgpu_mn_register. Prevent MMU notifications until we reach stage-4 of the
restore process i.e. criu_resume ioctl op is received, and the process is
ready to be resumed. This ioctl is different from other KFD CRIU ioctls
since its called by CRIU master restore process for all the target
processes being resumed by CRIU.

Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: David Yat Sin <david.yatsin@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 30 insertions, 5 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 74f162887d3b..b3198e186622 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -64,7 +64,8 @@ static struct workqueue_struct *kfd_process_wq;
  */
 static struct workqueue_struct *kfd_restore_wq;
 
-static struct kfd_process *find_process(const struct task_struct *thread);
+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 int kfd_process_init_cwsr_apu(struct kfd_process *p, struct file *filep);
@@ -715,7 +716,8 @@ static int kfd_process_alloc_gpuvm(struct kfd_process_device *pdd,
 	int err;
 
 	err = amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(kdev->adev, gpu_va, size,
-						 pdd->drm_priv, mem, NULL, flags);
+						 pdd->drm_priv, mem, NULL,
+						 flags, false);
 	if (err)
 		goto err_alloc_mem;
 
@@ -816,7 +818,7 @@ struct kfd_process *kfd_create_process(struct file *filep)
 	mutex_lock(&kfd_processes_mutex);
 
 	/* A prior open of /dev/kfd could have already created the process. */
-	process = find_process(thread);
+	process = find_process(thread, false);
 	if (process) {
 		pr_debug("Process already found\n");
 	} else {
@@ -884,7 +886,7 @@ struct kfd_process *kfd_get_process(const struct task_struct *thread)
 	if (thread->group_leader->mm != thread->mm)
 		return ERR_PTR(-EINVAL);
 
-	process = find_process(thread);
+	process = find_process(thread, false);
 	if (!process)
 		return ERR_PTR(-EINVAL);
 
@@ -903,13 +905,16 @@ static struct kfd_process *find_process_by_mm(const struct mm_struct *mm)
 	return NULL;
 }
 
-static struct kfd_process *find_process(const struct task_struct *thread)
+static struct kfd_process *find_process(const struct task_struct *thread,
+					bool ref)
 {
 	struct kfd_process *p;
 	int idx;
 
 	idx = srcu_read_lock(&kfd_processes_srcu);
 	p = find_process_by_mm(thread->mm);
+	if (p && ref)
+		kref_get(&p->ref);
 	srcu_read_unlock(&kfd_processes_srcu, idx);
 
 	return p;
@@ -920,6 +925,26 @@ void kfd_unref_process(struct kfd_process *p)
 	kref_put(&p->ref, kfd_process_ref_release);
 }
 
+/* This increments the process->ref counter. */
+struct kfd_process *kfd_lookup_process_by_pid(struct pid *pid)
+{
+	struct task_struct *task = NULL;
+	struct kfd_process *p    = NULL;
+
+	if (!pid) {
+		task = current;
+		get_task_struct(task);
+	} else {
+		task = get_pid_task(pid, PIDTYPE_PID);
+	}
+
+	if (task) {
+		p = find_process(task, true);
+		put_task_struct(task);
+	}
+
+	return p;
+}
 
 static void kfd_process_device_free_bos(struct kfd_process_device *pdd)
 {