[PATCH v3 03/16] drm/amdkfd: CRIU Implement KFD process_info ioctl

[David Yat Sin]

From: Rajneesh Bhardwaj <rajneesh.bhardwaj at amd.com>

This IOCTL is expected to be called as a precursor to the actual
Checkpoint operation. This does the basic discovery into the target
process seized by CRIU and relays the information to the userspace that
utilizes it to start the Checkpoint operation via another dedicated
IOCTL.

The process_info IOCTL determines the number of GPUs, buffer objects
that are associated with the target process, its process id in
caller's namespace since /proc/pid/mem interface maybe used to drain
the contents of the discovered buffer objects in userspace and getpid
returns the pid of CRIU dumper process. Also the pid of a process
inside a container might be different than its global pid so return
the ns pid.

Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj at amd.com>
Signed-off-by: David Yat Sin <david.yatsin at amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 44 +++++++++++++++++++++++-
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h    |  2 ++
 drivers/gpu/drm/amd/amdkfd/kfd_process.c | 14 ++++++++
 3 files changed, 59 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 231f8e3b43f6..1906ded40698 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1841,6 +1841,26 @@ static int kfd_ioctl_svm(struct file *filep, struct kfd_process *p, void *data)
 	return -EPERM;
 }
 #endif
+uint64_t get_process_num_bos(struct kfd_process *p)
+{
+	uint64_t num_of_bos = 0, i;
+
+	/* Run over all PDDs of the process */
+	for (i = 0; i < p->n_pdds; i++) {
+		struct kfd_process_device *pdd = p->pdds[i];
+		void *mem;
+		int id;
+
+		idr_for_each_entry(&pdd->alloc_idr, mem, id) {
+			struct kgd_mem *kgd_mem = (struct kgd_mem *)mem;
+
+			if ((uint64_t)kgd_mem->va > pdd->gpuvm_base)
+				num_of_bos++;
+		}
+	}
+	return num_of_bos;
+}
+
 static int kfd_ioctl_criu_dumper(struct file *filep,
 				struct kfd_process *p, void *data)
 {
@@ -1867,7 +1887,29 @@ static int kfd_ioctl_criu_resume(struct file *filep,
 static int kfd_ioctl_criu_process_info(struct file *filep,
 				struct kfd_process *p, void *data)
 {
-	return 0;
+	struct kfd_ioctl_criu_process_info_args *args = data;
+	int ret = 0;
+
+	mutex_lock(&p->mutex);
+
+	if (!kfd_has_process_device_data(p)) {
+		pr_err("No pdd for given process\n");
+		ret = -ENODEV;
+		goto err_unlock;
+	}
+
+	args->task_pid = task_pid_nr_ns(p->lead_thread,
+					task_active_pid_ns(p->lead_thread));
+
+	args->process_priv_data_size = sizeof(struct kfd_criu_process_priv_data);
+
+	args->total_bos = get_process_num_bos(p);
+	args->bos_priv_data_size = args->total_bos * sizeof(struct kfd_criu_bo_priv_data);
+
+	dev_dbg(kfd_device, "Num of bos:%llu\n", args->total_bos);
+err_unlock:
+	mutex_unlock(&p->mutex);
+	return ret;
 }
 
 #define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index da70c96e5bb0..914306209c9c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -943,6 +943,8 @@ void *kfd_process_device_translate_handle(struct kfd_process_device *p,
 void kfd_process_device_remove_obj_handle(struct kfd_process_device *pdd,
 					int handle);
 
+bool kfd_has_process_device_data(struct kfd_process *p);
+
 /* PASIDs */
 int kfd_pasid_init(void);
 void kfd_pasid_exit(void);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 21ec8a18cad2..9f2b4d8a5247 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1406,6 +1406,20 @@ static int init_doorbell_bitmap(struct qcm_process_device *qpd,
 	return 0;
 }
 
+bool kfd_has_process_device_data(struct kfd_process *p)
+{
+	int i;
+
+	for (i = 0; i < p->n_pdds; i++) {
+		struct kfd_process_device *pdd = p->pdds[i];
+
+		if (pdd)
+			return true;
+	}
+
+	return false;
+}
+
 struct kfd_process_device *kfd_get_process_device_data(struct kfd_dev *dev,
 							struct kfd_process *p)
 {
-- 
2.17.1