[PATCH v3 07/16] drm/amdkfd: CRIU Implement KFD pause ioctl

[David Yat Sin <david.yatsin@xxxxxxx>]

Introducing pause IOCTL. The CRIU amdgpu plugin is needs
to call AMDKFD_IOC_CRIU_PAUSE(pause = 1) before starting dump and
AMDKFD_IOC_CRIU_PAUSE(pause = 0) when dump is complete. This ensures
that the queues are not modified between each CRIU dump ioctl.

Signed-off-by: David Yat Sin <david.yatsin@xxxxxxx>
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 23 ++++++++++++++++++++++-
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h    |  3 +++
 drivers/gpu/drm/amd/amdkfd/kfd_process.c |  1 +
 3 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 668772a67f7a..791cb1555413 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -2027,6 +2027,14 @@ static int kfd_ioctl_criu_dumper(struct file *filep,
 		goto err_unlock;
 	}
 
+	/* Confirm all process queues are evicted */
+	if (!p->queues_paused) {
+		pr_err("Cannot dump process when queues are not in evicted state\n");
+		/* CRIU plugin did not call AMDKFD_IOC_CRIU_PAUSE before dumping */
+		ret = -EINVAL;
+		goto err_unlock;
+	}
+
 	switch (args->type) {
 	case KFD_CRIU_OBJECT_TYPE_PROCESS:
 		ret = criu_dump_process(p, args);
@@ -2363,7 +2371,20 @@ static int kfd_ioctl_criu_restorer(struct file *filep,
 
 static int kfd_ioctl_criu_pause(struct file *filep, struct kfd_process *p, void *data)
 {
-	return 0;
+	int ret;
+	struct kfd_ioctl_criu_pause_args *args = data;
+
+	if (args->pause)
+		ret = kfd_process_evict_queues(p);
+	else
+		ret = kfd_process_restore_queues(p);
+
+	if (ret)
+		pr_err("Failed to %s queues ret:%d\n", args->pause ? "evict" : "restore", ret);
+	else
+		p->queues_paused = !!(args->pause);
+
+	return ret;
 }
 
 static int kfd_ioctl_criu_resume(struct file *filep,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 881af8e1b06c..e0601bfbcbf2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -868,6 +868,9 @@ struct kfd_process {
 	struct svm_range_list svms;
 
 	bool xnack_enabled;
+
+	/* Queues are in paused stated because we are in the process of doing a CRIU checkpoint */
+	bool queues_paused;
 };
 
 #define KFD_PROCESS_TABLE_SIZE 5 /* bits: 32 entries */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 65a389fb97ce..0f7c4c63ee99 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1314,6 +1314,7 @@ static struct kfd_process *create_process(const struct task_struct *thread)
 	process->mm = thread->mm;
 	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();
-- 
2.17.1