From f881b5d46241aadcf79f958bb5a17661388d23b4 Mon Sep 17 00:00:00 2001
From: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Date: Wed, 3 Nov 2021 02:40:27 -0400
Subject: drm/amdkfd: CRIU Save Shared Virtual Memory ranges
Git-commit: 9d5dabfeff3ca63925cfc9c427f2d1fe8929402b
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

During checkpoint stage, save the shared virtual memory ranges and
attributes for the target process. A process may contain a number of svm
ranges and each range might contain a number of attributes. While not
all attributes may be applicable for a given prange but during
checkpoint we store all possible values for the max possible attribute
types.

Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@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 |  4 +-
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c     | 95 ++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_svm.h     | 10 +++
 3 files changed, 108 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index a755ea68a428..721c86ceba22 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -2196,7 +2196,9 @@ static int criu_checkpoint(struct file *filep,
 		if (ret)
 			goto close_bo_fds;
 
-		/* TODO: Dump SVM-Ranges */
+		ret = kfd_criu_checkpoint_svm(p, (uint8_t __user *)args->priv_data, &priv_offset);
+		if (ret)
+			goto close_bo_fds;
 	}
 
 close_bo_fds:
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 64cd7712c098..7cf63995c079 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -3540,6 +3540,101 @@ int svm_range_get_info(struct kfd_process *p, uint32_t *num_svm_ranges,
 	return 0;
 }
 
+int kfd_criu_checkpoint_svm(struct kfd_process *p,
+			    uint8_t __user *user_priv_data,
+			    uint64_t *priv_data_offset)
+{
+	struct kfd_criu_svm_range_priv_data *svm_priv = NULL;
+	struct kfd_ioctl_svm_attribute *query_attr = NULL;
+	uint64_t svm_priv_data_size, query_attr_size = 0;
+	int index, nattr_common = 4, ret = 0;
+	struct svm_range_list *svms;
+	int num_devices = p->n_pdds;
+	struct svm_range *prange;
+	struct mm_struct *mm;
+
+	svms = &p->svms;
+	if (!svms)
+		return -EINVAL;
+
+	mm = get_task_mm(p->lead_thread);
+	if (!mm) {
+		pr_err("failed to get mm for the target process\n");
+		return -ESRCH;
+	}
+
+	query_attr_size = sizeof(struct kfd_ioctl_svm_attribute) *
+				(nattr_common + num_devices);
+
+	query_attr = kzalloc(query_attr_size, GFP_KERNEL);
+	if (!query_attr) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	query_attr[0].type = KFD_IOCTL_SVM_ATTR_PREFERRED_LOC;
+	query_attr[1].type = KFD_IOCTL_SVM_ATTR_PREFETCH_LOC;
+	query_attr[2].type = KFD_IOCTL_SVM_ATTR_SET_FLAGS;
+	query_attr[3].type = KFD_IOCTL_SVM_ATTR_GRANULARITY;
+
+	for (index = 0; index < num_devices; index++) {
+		struct kfd_process_device *pdd = p->pdds[index];
+
+		query_attr[index + nattr_common].type =
+			KFD_IOCTL_SVM_ATTR_ACCESS;
+		query_attr[index + nattr_common].value = pdd->user_gpu_id;
+	}
+
+	svm_priv_data_size = sizeof(*svm_priv) + query_attr_size;
+
+	svm_priv = kzalloc(svm_priv_data_size, GFP_KERNEL);
+	if (!svm_priv) {
+		ret = -ENOMEM;
+		goto exit_query;
+	}
+
+	index = 0;
+	list_for_each_entry(prange, &svms->list, list) {
+
+		svm_priv->object_type = KFD_CRIU_OBJECT_TYPE_SVM_RANGE;
+		svm_priv->start_addr = prange->start;
+		svm_priv->size = prange->npages;
+		memcpy(&svm_priv->attrs, query_attr, query_attr_size);
+		pr_debug("CRIU: prange: 0x%p start: 0x%lx\t npages: 0x%llx end: 0x%llx\t size: 0x%llx\n",
+			 prange, prange->start, prange->npages,
+			 prange->start + prange->npages - 1,
+			 prange->npages * PAGE_SIZE);
+
+		ret = svm_range_get_attr(p, mm, svm_priv->start_addr,
+					 svm_priv->size,
+					 (nattr_common + num_devices),
+					 svm_priv->attrs);
+		if (ret) {
+			pr_err("CRIU: failed to obtain range attributes\n");
+			goto exit_priv;
+		}
+
+		ret = copy_to_user(user_priv_data + *priv_data_offset,
+				   svm_priv, svm_priv_data_size);
+		if (ret) {
+			pr_err("Failed to copy svm priv to user\n");
+			goto exit_priv;
+		}
+
+		*priv_data_offset += svm_priv_data_size;
+
+	}
+
+
+exit_priv:
+	kfree(svm_priv);
+exit_query:
+	kfree(query_attr);
+exit:
+	mmput(mm);
+	return ret;
+}
+
 int
 svm_ioctl(struct kfd_process *p, enum kfd_ioctl_svm_op op, uint64_t start,
 	  uint64_t size, uint32_t nattrs, struct kfd_ioctl_svm_attribute *attrs)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
index f052b6022e76..f36c2fa8469a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
@@ -185,6 +185,9 @@ void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm,
 			void *owner);
 int svm_range_get_info(struct kfd_process *p, uint32_t *num_svm_ranges,
 		       uint64_t *svm_priv_data_size);
+int kfd_criu_checkpoint_svm(struct kfd_process *p,
+			    uint8_t __user *user_priv_data,
+			    uint64_t *priv_offset);
 struct kfd_process_device *
 svm_range_get_pdd_by_adev(struct svm_range *prange, struct amdgpu_device *adev);
 void svm_range_list_lock_and_flush_work(struct svm_range_list *svms, struct mm_struct *mm);
@@ -231,6 +234,13 @@ static inline int svm_range_get_info(struct kfd_process *p,
 	return 0;
 }
 
+static inline int kfd_criu_checkpoint_svm(struct kfd_process *p,
+					  uint8_t __user *user_priv_data,
+					  uint64_t *priv_offset)
+{
+	return 0;
+}
+
 #define KFD_IS_SVM_API_SUPPORTED(dev) false
 
 #endif /* IS_ENABLED(CONFIG_HSA_AMD_SVM) */
-- 
2.38.1