From c10c2bf57473b3800219dab2064fc08e6204f1f7 Mon Sep 17 00:00:00 2001
From: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Date: Tue, 24 Aug 2021 16:14:51 -0400
Subject: drm/amdkfd: CRIU Implement KFD process_info ioctl
Git-commit: f185381b64814bb483416e4dd83d85891018a7c5
Patch-mainline: v5.18-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225

This IOCTL op 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 op.

The process_info IOCTL op 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.

Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: David Yat Sin <david.yatsin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 56 +++++++++++++++++++++++-
 1 file changed, 55 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 90e6d9e335a5..29443419bbf0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1860,6 +1860,42 @@ static int kfd_ioctl_svm(struct file *filep, struct kfd_process *p, void *data)
 }
 #endif
 
+uint32_t get_process_num_bos(struct kfd_process *p)
+{
+	uint32_t num_of_bos = 0;
+	int 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 void criu_get_process_object_info(struct kfd_process *p,
+					 uint32_t *num_bos,
+					 uint64_t *objs_priv_size)
+{
+	uint64_t priv_size;
+
+	*num_bos = get_process_num_bos(p);
+
+	if (objs_priv_size) {
+		priv_size = sizeof(struct kfd_criu_process_priv_data);
+		priv_size += *num_bos * sizeof(struct kfd_criu_bo_priv_data);
+		*objs_priv_size = priv_size;
+	}
+}
+
 static int criu_checkpoint(struct file *filep,
 			   struct kfd_process *p,
 			   struct kfd_ioctl_criu_args *args)
@@ -1892,7 +1928,25 @@ static int criu_process_info(struct file *filep,
 				struct kfd_process *p,
 				struct kfd_ioctl_criu_args *args)
 {
-	return 0;
+	int ret = 0;
+
+	mutex_lock(&p->mutex);
+
+	if (!p->n_pdds) {
+		pr_err("No pdd for given process\n");
+		ret = -ENODEV;
+		goto err_unlock;
+	}
+
+	args->pid = task_pid_nr_ns(p->lead_thread,
+					task_active_pid_ns(p->lead_thread));
+
+	criu_get_process_object_info(p, &args->num_bos, &args->priv_data_size);
+
+	dev_dbg(kfd_device, "Num of bos:%u\n", args->num_bos);
+err_unlock:
+	mutex_unlock(&p->mutex);
+	return ret;
 }
 
 static int kfd_ioctl_criu(struct file *filep, struct kfd_process *p, void *data)
-- 
2.38.1