[Patch v5 08/24] drm/amdkfd: CRIU add queues support
Rajneesh Bhardwaj
rajneesh.bhardwaj at amd.com
Thu Feb 3 09:09:02 UTC 2022
From: David Yat Sin <david.yatsin at amd.com>
Add support to existing CRIU ioctl's to save number of queues and queue
properties for each queue during checkpoint and re-create queues on
restore.
Signed-off-by: David Yat Sin <david.yatsin at amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj at amd.com>
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 110 ++++++++-
drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 43 +++-
.../amd/amdkfd/kfd_process_queue_manager.c | 208 ++++++++++++++++++
3 files changed, 353 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 6af6deeda523..d049f9cbbc79 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -2015,19 +2015,36 @@ static int criu_checkpoint_bos(struct kfd_process *p,
return ret;
}
-static void criu_get_process_object_info(struct kfd_process *p,
- uint32_t *num_bos,
- uint64_t *objs_priv_size)
+static int criu_get_process_object_info(struct kfd_process *p,
+ uint32_t *num_bos,
+ uint32_t *num_objects,
+ uint64_t *objs_priv_size)
{
+ int ret;
uint64_t priv_size;
+ uint32_t num_queues, num_events, num_svm_ranges;
+ uint64_t queues_priv_data_size;
*num_bos = get_process_num_bos(p);
+ ret = kfd_process_get_queue_info(p, &num_queues, &queues_priv_data_size);
+ if (ret)
+ return ret;
+
+ num_events = 0; /* TODO: Implement Events */
+ num_svm_ranges = 0; /* TODO: Implement SVM-Ranges */
+
+ *num_objects = num_queues + num_events + num_svm_ranges;
+
if (objs_priv_size) {
priv_size = sizeof(struct kfd_criu_process_priv_data);
priv_size += *num_bos * sizeof(struct kfd_criu_bo_priv_data);
+ priv_size += queues_priv_data_size;
+ /* TODO: Add Events priv size */
+ /* TODO: Add SVM ranges priv size */
*objs_priv_size = priv_size;
}
+ return 0;
}
static int criu_checkpoint(struct file *filep,
@@ -2035,7 +2052,7 @@ static int criu_checkpoint(struct file *filep,
struct kfd_ioctl_criu_args *args)
{
int ret;
- uint32_t num_bos;
+ uint32_t num_bos, num_objects;
uint64_t priv_size, priv_offset = 0;
if (!args->bos || !args->priv_data)
@@ -2057,9 +2074,12 @@ static int criu_checkpoint(struct file *filep,
goto exit_unlock;
}
- criu_get_process_object_info(p, &num_bos, &priv_size);
+ ret = criu_get_process_object_info(p, &num_bos, &num_objects, &priv_size);
+ if (ret)
+ goto exit_unlock;
if (num_bos != args->num_bos ||
+ num_objects != args->num_objects ||
priv_size != args->priv_data_size) {
ret = -EINVAL;
@@ -2076,6 +2096,17 @@ static int criu_checkpoint(struct file *filep,
if (ret)
goto exit_unlock;
+ if (num_objects) {
+ ret = kfd_criu_checkpoint_queues(p, (uint8_t __user *)args->priv_data,
+ &priv_offset);
+ if (ret)
+ goto exit_unlock;
+
+ /* TODO: Dump Events */
+
+ /* TODO: Dump SVM-Ranges */
+ }
+
exit_unlock:
mutex_unlock(&p->mutex);
if (ret)
@@ -2344,6 +2375,62 @@ static int criu_restore_bos(struct kfd_process *p,
return ret;
}
+static int criu_restore_objects(struct file *filep,
+ struct kfd_process *p,
+ struct kfd_ioctl_criu_args *args,
+ uint64_t *priv_offset,
+ uint64_t max_priv_data_size)
+{
+ int ret = 0;
+ uint32_t i;
+
+ BUILD_BUG_ON(offsetof(struct kfd_criu_queue_priv_data, object_type));
+ BUILD_BUG_ON(offsetof(struct kfd_criu_event_priv_data, object_type));
+ BUILD_BUG_ON(offsetof(struct kfd_criu_svm_range_priv_data, object_type));
+
+ for (i = 0; i < args->num_objects; i++) {
+ uint32_t object_type;
+
+ if (*priv_offset + sizeof(object_type) > max_priv_data_size) {
+ pr_err("Invalid private data size\n");
+ return -EINVAL;
+ }
+
+ ret = get_user(object_type, (uint32_t __user *)(args->priv_data + *priv_offset));
+ if (ret) {
+ pr_err("Failed to copy private information from user\n");
+ goto exit;
+ }
+
+ switch (object_type) {
+ case KFD_CRIU_OBJECT_TYPE_QUEUE:
+ ret = kfd_criu_restore_queue(p, (uint8_t __user *)args->priv_data,
+ priv_offset, max_priv_data_size);
+ if (ret)
+ goto exit;
+ break;
+ case KFD_CRIU_OBJECT_TYPE_EVENT:
+ /* TODO: Implement Events */
+ *priv_offset += sizeof(struct kfd_criu_event_priv_data);
+ if (ret)
+ goto exit;
+ break;
+ case KFD_CRIU_OBJECT_TYPE_SVM_RANGE:
+ /* TODO: Implement SVM range */
+ *priv_offset += sizeof(struct kfd_criu_svm_range_priv_data);
+ if (ret)
+ goto exit;
+ break;
+ default:
+ pr_err("Invalid object type:%u at index:%d\n", object_type, i);
+ ret = -EINVAL;
+ goto exit;
+ }
+ }
+exit:
+ return ret;
+}
+
static int criu_restore(struct file *filep,
struct kfd_process *p,
struct kfd_ioctl_criu_args *args)
@@ -2377,6 +2464,10 @@ static int criu_restore(struct file *filep,
if (ret)
goto exit_unlock;
+ ret = criu_restore_objects(filep, p, args, &priv_offset, args->priv_data_size);
+ if (ret)
+ goto exit_unlock;
+
if (priv_offset != args->priv_data_size) {
pr_err("Invalid private data size\n");
ret = -EINVAL;
@@ -2474,9 +2565,14 @@ static int criu_process_info(struct file *filep,
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);
+ ret = criu_get_process_object_info(p, &args->num_bos, &args->num_objects,
+ &args->priv_data_size);
+ if (ret)
+ goto err_unlock;
+
+ dev_dbg(kfd_device, "Num of bos:%u objects:%u priv_data_size:%lld\n",
+ args->num_bos, args->num_objects, args->priv_data_size);
- dev_dbg(kfd_device, "Num of bos:%u\n", args->num_bos);
err_unlock:
if (ret) {
kfd_process_restore_queues(p);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 677f21447112..41aa7b150a96 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1057,6 +1057,16 @@ struct kfd_criu_bo_priv_data {
uint32_t mapped_gpuids[MAX_GPU_INSTANCE];
};
+/*
+ * The first 4 bytes of kfd_criu_queue_priv_data, kfd_criu_event_priv_data,
+ * kfd_criu_svm_range_priv_data is the object type
+ */
+enum kfd_criu_object_type {
+ KFD_CRIU_OBJECT_TYPE_QUEUE,
+ KFD_CRIU_OBJECT_TYPE_EVENT,
+ KFD_CRIU_OBJECT_TYPE_SVM_RANGE,
+};
+
struct kfd_criu_svm_range_priv_data {
uint32_t object_type;
uint32_t reserved;
@@ -1064,7 +1074,26 @@ struct kfd_criu_svm_range_priv_data {
struct kfd_criu_queue_priv_data {
uint32_t object_type;
- uint32_t reserved;
+ uint64_t q_address;
+ uint64_t q_size;
+ uint64_t read_ptr_addr;
+ uint64_t write_ptr_addr;
+ uint64_t doorbell_off;
+ uint64_t eop_ring_buffer_address;
+ uint64_t ctx_save_restore_area_address;
+ uint32_t gpu_id;
+ uint32_t type;
+ uint32_t format;
+ uint32_t q_id;
+ uint32_t priority;
+ uint32_t q_percent;
+ uint32_t doorbell_id;
+ uint32_t is_gws;
+ uint32_t sdma_id;
+ uint32_t eop_ring_buffer_size;
+ uint32_t ctx_save_restore_area_size;
+ uint32_t ctl_stack_size;
+ uint32_t mqd_size;
};
struct kfd_criu_event_priv_data {
@@ -1072,6 +1101,18 @@ struct kfd_criu_event_priv_data {
uint32_t reserved;
};
+int kfd_process_get_queue_info(struct kfd_process *p,
+ uint32_t *num_queues,
+ uint64_t *priv_data_sizes);
+
+int kfd_criu_checkpoint_queues(struct kfd_process *p,
+ uint8_t __user *user_priv_data,
+ uint64_t *priv_data_offset);
+
+int kfd_criu_restore_queue(struct kfd_process *p,
+ uint8_t __user *user_priv_data,
+ uint64_t *priv_data_offset,
+ uint64_t max_priv_data_size);
/* CRIU - End */
/* Queue Context Management */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 5e5c84a8e1ef..38d3217f0f67 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -497,6 +497,214 @@ int pqm_get_wave_state(struct process_queue_manager *pqm,
save_area_used_size);
}
+int kfd_process_get_queue_info(struct kfd_process *p,
+ uint32_t *num_queues,
+ uint64_t *priv_data_sizes)
+{
+ struct queue *q;
+ int i;
+
+ *num_queues = 0;
+
+ /* Run over all PDDs of the process */
+ for (i = 0; i < p->n_pdds; i++) {
+ struct kfd_process_device *pdd = p->pdds[i];
+
+ list_for_each_entry(q, &pdd->qpd.queues_list, list) {
+ if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
+ q->properties.type == KFD_QUEUE_TYPE_SDMA ||
+ q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
+
+ *num_queues = *num_queues + 1;
+ } else {
+ pr_err("Unsupported queue type (%d)\n", q->properties.type);
+ return -EOPNOTSUPP;
+ }
+ }
+ }
+ *priv_data_sizes = *num_queues * sizeof(struct kfd_criu_queue_priv_data);
+
+ return 0;
+}
+
+static void criu_dump_queue(struct kfd_process_device *pdd,
+ struct queue *q,
+ struct kfd_criu_queue_priv_data *q_data)
+{
+ q_data->gpu_id = pdd->dev->id;
+ q_data->type = q->properties.type;
+ q_data->format = q->properties.format;
+ q_data->q_id = q->properties.queue_id;
+ q_data->q_address = q->properties.queue_address;
+ q_data->q_size = q->properties.queue_size;
+ q_data->priority = q->properties.priority;
+ q_data->q_percent = q->properties.queue_percent;
+ q_data->read_ptr_addr = (uint64_t)q->properties.read_ptr;
+ q_data->write_ptr_addr = (uint64_t)q->properties.write_ptr;
+ q_data->doorbell_id = q->doorbell_id;
+
+ q_data->sdma_id = q->sdma_id;
+
+ q_data->eop_ring_buffer_address =
+ q->properties.eop_ring_buffer_address;
+
+ q_data->eop_ring_buffer_size = q->properties.eop_ring_buffer_size;
+
+ q_data->ctx_save_restore_area_address =
+ q->properties.ctx_save_restore_area_address;
+
+ q_data->ctx_save_restore_area_size =
+ q->properties.ctx_save_restore_area_size;
+
+ pr_debug("Dumping Queue: gpu_id:%x queue_id:%u\n", q_data->gpu_id, q_data->q_id);
+}
+
+static int criu_dump_queues_device(struct kfd_process_device *pdd,
+ uint8_t __user *user_priv,
+ unsigned int *q_index,
+ uint64_t *queues_priv_data_offset)
+{
+ struct kfd_criu_queue_priv_data *q_data;
+ struct queue *q;
+ int ret = 0;
+
+ q_data = kzalloc(sizeof(*q_data), GFP_KERNEL);
+ if (!q_data)
+ return -ENOMEM;
+
+ list_for_each_entry(q, &pdd->qpd.queues_list, list) {
+ if (q->properties.type != KFD_QUEUE_TYPE_COMPUTE &&
+ q->properties.type != KFD_QUEUE_TYPE_SDMA &&
+ q->properties.type != KFD_QUEUE_TYPE_SDMA_XGMI) {
+
+ pr_err("Unsupported queue type (%d)\n", q->properties.type);
+ ret = -EOPNOTSUPP;
+ break;
+ }
+
+ criu_dump_queue(pdd, q, q_data);
+
+ ret = copy_to_user(user_priv + *queues_priv_data_offset, q_data, sizeof(*q_data));
+ if (ret) {
+ ret = -EFAULT;
+ break;
+ }
+ *queues_priv_data_offset += sizeof(*q_data);
+ *q_index = *q_index + 1;
+ }
+
+ kfree(q_data);
+
+ return ret;
+}
+
+int kfd_criu_checkpoint_queues(struct kfd_process *p,
+ uint8_t __user *user_priv_data,
+ uint64_t *priv_data_offset)
+{
+ int ret = 0, pdd_index, q_index = 0;
+
+ for (pdd_index = 0; pdd_index < p->n_pdds; pdd_index++) {
+ struct kfd_process_device *pdd = p->pdds[pdd_index];
+
+ /*
+ * criu_dump_queues_device will copy data to user and update q_index and
+ * queues_priv_data_offset
+ */
+ ret = criu_dump_queues_device(pdd, user_priv_data, &q_index, priv_data_offset);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+static void set_queue_properties_from_criu(struct queue_properties *qp,
+ struct kfd_criu_queue_priv_data *q_data)
+{
+ qp->is_interop = false;
+ qp->is_gws = q_data->is_gws;
+ qp->queue_percent = q_data->q_percent;
+ qp->priority = q_data->priority;
+ qp->queue_address = q_data->q_address;
+ qp->queue_size = q_data->q_size;
+ qp->read_ptr = (uint32_t *) q_data->read_ptr_addr;
+ qp->write_ptr = (uint32_t *) q_data->write_ptr_addr;
+ qp->eop_ring_buffer_address = q_data->eop_ring_buffer_address;
+ qp->eop_ring_buffer_size = q_data->eop_ring_buffer_size;
+ qp->ctx_save_restore_area_address = q_data->ctx_save_restore_area_address;
+ qp->ctx_save_restore_area_size = q_data->ctx_save_restore_area_size;
+ qp->ctl_stack_size = q_data->ctl_stack_size;
+ qp->type = q_data->type;
+ qp->format = q_data->format;
+}
+
+int kfd_criu_restore_queue(struct kfd_process *p,
+ uint8_t __user *user_priv_ptr,
+ uint64_t *priv_data_offset,
+ uint64_t max_priv_data_size)
+{
+ struct kfd_criu_queue_priv_data *q_data;
+ struct kfd_process_device *pdd;
+ struct kfd_dev *dev;
+ struct queue_properties qp;
+ unsigned int queue_id;
+
+ int ret = 0;
+
+ if (*priv_data_offset + sizeof(*q_data) > max_priv_data_size)
+ return -EINVAL;
+
+ q_data = kmalloc(sizeof(*q_data), GFP_KERNEL);
+ if (!q_data)
+ return -ENOMEM;
+
+ ret = copy_from_user(q_data, user_priv_ptr + *priv_data_offset, sizeof(*q_data));
+ if (ret) {
+ ret = -EFAULT;
+ goto exit;
+ }
+
+ *priv_data_offset += sizeof(*q_data);
+
+ dev = kfd_device_by_id(q_data->gpu_id);
+ if (!dev) {
+ pr_err("Could not get kfd_dev from gpu_id = 0x%x\n",
+ q_data->gpu_id);
+
+ ret = -EINVAL;
+ goto exit;
+ }
+
+ pdd = kfd_get_process_device_data(dev, p);
+ if (!pdd) {
+ pr_err("Failed to get pdd\n");
+ ret = -EFAULT;
+ return ret;
+ }
+
+ memset(&qp, 0, sizeof(qp));
+ set_queue_properties_from_criu(&qp, q_data);
+
+ print_queue_properties(&qp);
+
+ ret = pqm_create_queue(&p->pqm, pdd->dev, NULL, &qp, &queue_id, NULL);
+ if (ret) {
+ pr_err("Failed to create new queue err:%d\n", ret);
+ ret = -EINVAL;
+ }
+
+exit:
+ if (ret)
+ pr_err("Failed to create queue (%d)\n", ret);
+ else
+ pr_debug("Queue id %d was restored successfully\n", queue_id);
+
+ kfree(q_data);
+
+ return ret;
+}
+
#if defined(CONFIG_DEBUG_FS)
int pqm_debugfs_mqds(struct seq_file *m, void *data)
--
2.17.1
More information about the amd-gfx
mailing list