git/linux-cryptodev-2.6
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/herbert/cryptodev-2.6.git synced 2026-05-02 18:17:50 -04:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdkfd: CRIU Introduce Checkpoint-Restore APIs

Browse Source 
Checkpoint-Restore in userspace (CRIU) is a powerful tool that can
snapshot a running process and later restore it on same or a remote
machine but expects the processes that have a device file (e.g. GPU)
associated with them, provide necessary driver support to assist CRIU
and its extensible plugin interface. Thus, In order to support the
Checkpoint-Restore of any ROCm process, the AMD Radeon Open Compute
Kernel driver, needs to provide a set of new APIs that provide
necessary VRAM metadata and its contents to a userspace component
(CRIU plugin) that can store it in form of image files.

This introduces some new ioctls which will be used to checkpoint-Restore
any KFD bound user process. KFD only allows ioctl calls from the same
process that opened the KFD file descriptor. Since these ioctls are
expected to be called from a KFD criu plugin which has elevated ptrace
attached privileges and CAP_CHECKPOINT_RESTORE capabilities attached with
the file descriptors so modify KFD to allow such calls.

(API redesigned by David Yat Sin)
Suggested-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: David Yat Sin <david.yatsin@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Rajneesh Bhardwaj
2021-08-24 16:13:41 -04:00
committed by Alex Deucher
parent afa3731591
commit 3698807094
3 changed files with 241 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

81
include/uapi/linux/kfd_ioctl.h
View File

@@ -468,6 +468,82 @@ struct kfd_ioctl_smi_events_args {
__u32 anon_fd; /* from KFD */
};
/**************************************************************************************************
* CRIU IOCTLs (Checkpoint Restore In Userspace)
*
* When checkpointing a process, the userspace application will perform:
* 1. PROCESS_INFO op to determine current process information. This pauses execution and evicts
* all the queues.
* 2. CHECKPOINT op to checkpoint process contents (BOs, queues, events, svm-ranges)
* 3. UNPAUSE op to un-evict all the queues
*
* When restoring a process, the CRIU userspace application will perform:
*
* 1. RESTORE op to restore process contents
* 2. RESUME op to start the process
*
* Note: Queues are forced into an evicted state after a successful PROCESS_INFO. User
* application needs to perform an UNPAUSE operation after calling PROCESS_INFO.
*/
enum kfd_criu_op {
KFD_CRIU_OP_PROCESS_INFO,
KFD_CRIU_OP_CHECKPOINT,
KFD_CRIU_OP_UNPAUSE,
KFD_CRIU_OP_RESTORE,
KFD_CRIU_OP_RESUME,
};
/**
* kfd_ioctl_criu_args - Arguments perform CRIU operation
* @devices: [in/out] User pointer to memory location for devices information.
* This is an array of type kfd_criu_device_bucket.
* @bos: [in/out] User pointer to memory location for BOs information
* This is an array of type kfd_criu_bo_bucket.
* @priv_data: [in/out] User pointer to memory location for private data
* @priv_data_size: [in/out] Size of priv_data in bytes
* @num_devices: [in/out] Number of GPUs used by process. Size of @devices array.
* @num_bos [in/out] Number of BOs used by process. Size of @bos array.
* @num_objects: [in/out] Number of objects used by process. Objects are opaque to
* user application.
* @pid: [in/out] PID of the process being checkpointed
* @op [in] Type of operation (kfd_criu_op)
*
* Return: 0 on success, -errno on failure
*/
struct kfd_ioctl_criu_args {
__u64 devices; /* Used during ops: CHECKPOINT, RESTORE */
__u64 bos; /* Used during ops: CHECKPOINT, RESTORE */
__u64 priv_data; /* Used during ops: CHECKPOINT, RESTORE */
__u64 priv_data_size; /* Used during ops: PROCESS_INFO, RESTORE */
__u32 num_devices; /* Used during ops: PROCESS_INFO, RESTORE */
__u32 num_bos; /* Used during ops: PROCESS_INFO, RESTORE */
__u32 num_objects; /* Used during ops: PROCESS_INFO, RESTORE */
__u32 pid; /* Used during ops: PROCESS_INFO, RESUME */
__u32 op;
};
struct kfd_criu_device_bucket {
__u32 user_gpu_id;
__u32 actual_gpu_id;
__u32 drm_fd;
__u32 pad;
};
struct kfd_criu_bo_bucket {
__u64 addr;
__u64 size;
__u64 offset;
__u64 restored_offset; /* During restore, updated offset for BO */
__u32 gpu_id; /* This is the user_gpu_id */
__u32 alloc_flags;
__u32 dmabuf_fd;
__u32 pad;
};
/* CRIU IOCTLs - END */
/**************************************************************************************************/
/* Register offset inside the remapped mmio page
*/
enum kfd_mmio_remap {
@@ -742,7 +818,10 @@ struct kfd_ioctl_set_xnack_mode_args {
#define AMDKFD_IOC_SET_XNACK_MODE \
AMDKFD_IOWR(0x21, struct kfd_ioctl_set_xnack_mode_args)
#define AMDKFD_IOC_CRIU_OP \
AMDKFD_IOWR(0x22, struct kfd_ioctl_criu_args)
#define AMDKFD_COMMAND_START 0x01
#define AMDKFD_COMMAND_END 0x22
#define AMDKFD_COMMAND_END 0x23
#endif