Re: [Patch v4 06/24] drm/amdkfd: CRIU Implement KFD restore ioctl
On 2021-12-22 7:36 p.m., Rajneesh Bhardwaj wrote:
This implements the KFD CRIU Restore ioctl that lays the basic
foundation for the CRIU restore operation. It provides support to
create the buffer objects corresponding to Non-Paged system memory
mapped for GPU and/or CPU access and lays basic foundation for the
userptrs buffer objects which will be added in a separate patch.
This ioctl creates various types of buffer objects such as VRAM,
MMIO, Doorbell, GTT based on the date sent from the userspace plugin.
The data mostly contains the previously checkpointed KFD images from
some KFD processs.
While restoring a criu process, attach old IDR values to newly
created BOs. This also adds the minimal gpu mapping support for a single
gpu checkpoint restore use case.
Signed-off-by: David Yat Sin
Signed-off-by: Rajneesh Bhardwaj
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 298 ++-
1 file changed, 297 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index cdbb92972338..c93f74ad073f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -2069,11 +2069,307 @@ static int criu_checkpoint(struct file *filep,
return ret;
}
+static int criu_restore_process(struct kfd_process *p,
+ struct kfd_ioctl_criu_args *args,
+ uint64_t *priv_offset,
+ uint64_t max_priv_data_size)
+{
+ int ret = 0;
+ struct kfd_criu_process_priv_data process_priv;
+
+ if (*priv_offset + sizeof(process_priv) > max_priv_data_size)
+ return -EINVAL;
+
+ ret = copy_from_user(_priv,
+ (void __user *)(args->priv_data + *priv_offset),
+ sizeof(process_priv));
+ if (ret) {
+ pr_err("Failed to copy process private information from
user\n");
+ ret = -EFAULT;
+ goto exit;
+ }
+ *priv_offset += sizeof(process_priv);
+
+ if (process_priv.version != KFD_CRIU_PRIV_VERSION) {
+ pr_err("Invalid CRIU API version (checkpointed:%d
current:%d)\n",
+ process_priv.version, KFD_CRIU_PRIV_VERSION);
+ return -EINVAL;
+ }
+
+exit:
+ return ret;
+}
+
+static int criu_restore_bos(struct kfd_process *p,
+ struct kfd_ioctl_criu_args *args,
+ uint64_t *priv_offset,
+ uint64_t max_priv_data_size)
+{
+ struct kfd_criu_bo_bucket *bo_buckets;
+ struct kfd_criu_bo_priv_data *bo_privs;
+ bool flush_tlbs = false;
+ int ret = 0, j = 0;
+ uint32_t i;
+
+ if (*priv_offset + (args->num_bos * sizeof(*bo_privs)) >
max_priv_data_size)
+ return -EINVAL;
+
+ bo_buckets = kvmalloc_array(args->num_bos, sizeof(*bo_buckets),
GFP_KERNEL);
+ if (!bo_buckets)
+ return -ENOMEM;
+
+ ret = copy_from_user(bo_buckets, (void __user *)args->bos,
+args->num_bos * sizeof(*bo_buckets));
+ if (ret) {
+ pr_err("Failed to copy BOs information from user\n");
+ ret = -EFAULT;
+ goto exit;
+ }
+
+ bo_privs = kvmalloc_array(args->num_bos, sizeof(*bo_privs), GFP_KERNEL);
+ if (!bo_privs) {
+ ret = -ENOMEM;
+ goto exit;
+ }
+
+ ret = copy_from_user(bo_privs, (void __user *)args->priv_data +
*priv_offset,
+args->num_bos * sizeof(*bo_privs));
+ if (ret) {
+ pr_err("Failed to copy BOs information from user\n");
+ ret = -EFAULT;
+ goto exit;
+ }
+ *priv_offset += args->num_bos * sizeof(*bo_privs);
+
+ /* Create and map new BOs */
+ for (i = 0; i < args->num_bos; i++) {
+ struct kfd_criu_bo_bucket *bo_bucket;
+ struct kfd_criu_bo_priv_data *bo_priv;
+ struct kfd_dev *dev;
+ struct kfd_process_device *pdd;
+ void *mem;
+ u64 offset;
+ int idr_handle;
+
+ bo_bucket = _buckets[i];
+ bo_priv = _privs[i];
+
+ dev = kfd_device_by_id(bo_bucket->gpu_id);
+ if (!dev) {
+ ret = -EINVAL;
+ pr_err("Failed to get pdd\n");
+ goto exit;
+ }
+ pdd = kfd_get_process_device_data(dev, p);
+ if (!pdd) {
+ ret = -EINVAL;
+ pr_err("Failed to get pdd\n");
+ goto exit;
+ }
+
+ pr_debug("kfd restore ioctl - bo_bucket[%d]:\n", i);
+ pr_debug("size = 0x%llx, bo_addr = 0x%llx bo_offset = 0x%llx\n"
+
[Patch v4 06/24] drm/amdkfd: CRIU Implement KFD restore ioctl
This implements the KFD CRIU Restore ioctl that lays the basic
foundation for the CRIU restore operation. It provides support to
create the buffer objects corresponding to Non-Paged system memory
mapped for GPU and/or CPU access and lays basic foundation for the
userptrs buffer objects which will be added in a separate patch.
This ioctl creates various types of buffer objects such as VRAM,
MMIO, Doorbell, GTT based on the date sent from the userspace plugin.
The data mostly contains the previously checkpointed KFD images from
some KFD processs.
While restoring a criu process, attach old IDR values to newly
created BOs. This also adds the minimal gpu mapping support for a single
gpu checkpoint restore use case.
Signed-off-by: David Yat Sin
Signed-off-by: Rajneesh Bhardwaj
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 298 ++-
1 file changed, 297 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index cdbb92972338..c93f74ad073f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -2069,11 +2069,307 @@ static int criu_checkpoint(struct file *filep,
return ret;
}
+static int criu_restore_process(struct kfd_process *p,
+ struct kfd_ioctl_criu_args *args,
+ uint64_t *priv_offset,
+ uint64_t max_priv_data_size)
+{
+ int ret = 0;
+ struct kfd_criu_process_priv_data process_priv;
+
+ if (*priv_offset + sizeof(process_priv) > max_priv_data_size)
+ return -EINVAL;
+
+ ret = copy_from_user(_priv,
+ (void __user *)(args->priv_data + *priv_offset),
+ sizeof(process_priv));
+ if (ret) {
+ pr_err("Failed to copy process private information from
user\n");
+ ret = -EFAULT;
+ goto exit;
+ }
+ *priv_offset += sizeof(process_priv);
+
+ if (process_priv.version != KFD_CRIU_PRIV_VERSION) {
+ pr_err("Invalid CRIU API version (checkpointed:%d
current:%d)\n",
+ process_priv.version, KFD_CRIU_PRIV_VERSION);
+ return -EINVAL;
+ }
+
+exit:
+ return ret;
+}
+
+static int criu_restore_bos(struct kfd_process *p,
+ struct kfd_ioctl_criu_args *args,
+ uint64_t *priv_offset,
+ uint64_t max_priv_data_size)
+{
+ struct kfd_criu_bo_bucket *bo_buckets;
+ struct kfd_criu_bo_priv_data *bo_privs;
+ bool flush_tlbs = false;
+ int ret = 0, j = 0;
+ uint32_t i;
+
+ if (*priv_offset + (args->num_bos * sizeof(*bo_privs)) >
max_priv_data_size)
+ return -EINVAL;
+
+ bo_buckets = kvmalloc_array(args->num_bos, sizeof(*bo_buckets),
GFP_KERNEL);
+ if (!bo_buckets)
+ return -ENOMEM;
+
+ ret = copy_from_user(bo_buckets, (void __user *)args->bos,
+args->num_bos * sizeof(*bo_buckets));
+ if (ret) {
+ pr_err("Failed to copy BOs information from user\n");
+ ret = -EFAULT;
+ goto exit;
+ }
+
+ bo_privs = kvmalloc_array(args->num_bos, sizeof(*bo_privs), GFP_KERNEL);
+ if (!bo_privs) {
+ ret = -ENOMEM;
+ goto exit;
+ }
+
+ ret = copy_from_user(bo_privs, (void __user *)args->priv_data +
*priv_offset,
+args->num_bos * sizeof(*bo_privs));
+ if (ret) {
+ pr_err("Failed to copy BOs information from user\n");
+ ret = -EFAULT;
+ goto exit;
+ }
+ *priv_offset += args->num_bos * sizeof(*bo_privs);
+
+ /* Create and map new BOs */
+ for (i = 0; i < args->num_bos; i++) {
+ struct kfd_criu_bo_bucket *bo_bucket;
+ struct kfd_criu_bo_priv_data *bo_priv;
+ struct kfd_dev *dev;
+ struct kfd_process_device *pdd;
+ void *mem;
+ u64 offset;
+ int idr_handle;
+
+ bo_bucket = _buckets[i];
+ bo_priv = _privs[i];
+
+ dev = kfd_device_by_id(bo_bucket->gpu_id);
+ if (!dev) {
+ ret = -EINVAL;
+ pr_err("Failed to get pdd\n");
+ goto exit;
+ }
+ pdd = kfd_get_process_device_data(dev, p);
+ if (!pdd) {
+ ret = -EINVAL;
+ pr_err("Failed to get pdd\n");
+ goto exit;
+ }
+
+ pr_debug("kfd restore ioctl - bo_bucket[%d]:\n", i);
+ pr_debug("size = 0x%llx, bo_addr = 0x%llx bo_offset = 0x%llx\n"
+ "gpu_id = 0x%x alloc_flags = 0x%x\n"
+
