#include <linux/time.h>
#include <linux/mm.h>
#include <linux/mman.h>
+#include <linux/ptrace.h>
#include <linux/dma-buf.h>
#include <asm/processor.h>
#include "kfd_priv.h"
}
#endif
+static int criu_checkpoint(struct file *filep,
+ struct kfd_process *p,
+ struct kfd_ioctl_criu_args *args)
+{
+ return 0;
+}
+
+static int criu_restore(struct file *filep,
+ struct kfd_process *p,
+ struct kfd_ioctl_criu_args *args)
+{
+ return 0;
+}
+
+static int criu_unpause(struct file *filep,
+ struct kfd_process *p,
+ struct kfd_ioctl_criu_args *args)
+{
+ return 0;
+}
+
+static int criu_resume(struct file *filep,
+ struct kfd_process *p,
+ struct kfd_ioctl_criu_args *args)
+{
+ return 0;
+}
+
+static int criu_process_info(struct file *filep,
+ struct kfd_process *p,
+ struct kfd_ioctl_criu_args *args)
+{
+ return 0;
+}
+
+static int kfd_ioctl_criu(struct file *filep, struct kfd_process *p, void *data)
+{
+ struct kfd_ioctl_criu_args *args = data;
+ int ret;
+
+ dev_dbg(kfd_device, "CRIU operation: %d\n", args->op);
+ switch (args->op) {
+ case KFD_CRIU_OP_PROCESS_INFO:
+ ret = criu_process_info(filep, p, args);
+ break;
+ case KFD_CRIU_OP_CHECKPOINT:
+ ret = criu_checkpoint(filep, p, args);
+ break;
+ case KFD_CRIU_OP_UNPAUSE:
+ ret = criu_unpause(filep, p, args);
+ break;
+ case KFD_CRIU_OP_RESTORE:
+ ret = criu_restore(filep, p, args);
+ break;
+ case KFD_CRIU_OP_RESUME:
+ ret = criu_resume(filep, p, args);
+ break;
+ default:
+ dev_dbg(kfd_device, "Unsupported CRIU operation:%d\n", args->op);
+ ret = -EINVAL;
+ break;
+ }
+
+ if (ret)
+ dev_dbg(kfd_device, "CRIU operation:%d err:%d\n", args->op, ret);
+
+ return ret;
+}
+
#define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \
[_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \
.cmd_drv = 0, .name = #ioctl}
AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_XNACK_MODE,
kfd_ioctl_set_xnack_mode, 0),
+
+ AMDKFD_IOCTL_DEF(AMDKFD_IOC_CRIU_OP,
+ kfd_ioctl_criu, KFD_IOC_FLAG_CHECKPOINT_RESTORE),
+
};
#define AMDKFD_CORE_IOCTL_COUNT ARRAY_SIZE(amdkfd_ioctls)
char *kdata = NULL;
unsigned int usize, asize;
int retcode = -EINVAL;
+ bool ptrace_attached = false;
if (nr >= AMDKFD_CORE_IOCTL_COUNT)
goto err_i1;
* processes need to create their own KFD device context.
*/
process = filep->private_data;
- if (process->lead_thread != current->group_leader) {
+
+ rcu_read_lock();
+ if ((ioctl->flags & KFD_IOC_FLAG_CHECKPOINT_RESTORE) &&
+ ptrace_parent(process->lead_thread) == current)
+ ptrace_attached = true;
+ rcu_read_unlock();
+
+ if (process->lead_thread != current->group_leader
+ && !ptrace_attached) {
dev_dbg(kfd_device, "Using KFD FD in wrong process\n");
retcode = -EBADF;
goto err_i1;
goto err_i1;
}
+ /*
+ * Versions of docker shipped in Ubuntu 18.xx and 20.xx do not support
+ * CAP_CHECKPOINT_RESTORE, so we also allow access if CAP_SYS_ADMIN as CAP_SYS_ADMIN is a
+ * more priviledged access.
+ */
+ if (unlikely(ioctl->flags & KFD_IOC_FLAG_CHECKPOINT_RESTORE)) {
+ if (!capable(CAP_CHECKPOINT_RESTORE) &&
+ !capable(CAP_SYS_ADMIN)) {
+ retcode = -EACCES;
+ goto err_i1;
+ }
+ }
+
if (cmd & (IOC_IN | IOC_OUT)) {
if (asize <= sizeof(stack_kdata)) {
kdata = stack_kdata;
*/
#define KFD_QUEUE_DOORBELL_MIRROR_OFFSET 512
-
+/**
+ * enum kfd_ioctl_flags - KFD ioctl flags
+ * Various flags that can be set in &amdkfd_ioctl_desc.flags to control how
+ * userspace can use a given ioctl.
+ */
+enum kfd_ioctl_flags {
+ /*
+ * @KFD_IOC_FLAG_CHECKPOINT_RESTORE:
+ * Certain KFD ioctls such as AMDKFD_IOC_CRIU_OP can potentially
+ * perform privileged operations and load arbitrary data into MQDs and
+ * eventually HQD registers when the queue is mapped by HWS. In order to
+ * prevent this we should perform additional security checks.
+ *
+ * This is equivalent to callers with the CHECKPOINT_RESTORE capability.
+ *
+ * Note: Since earlier versions of docker do not support CHECKPOINT_RESTORE,
+ * we also allow ioctls with SYS_ADMIN capability.
+ */
+ KFD_IOC_FLAG_CHECKPOINT_RESTORE = BIT(0),
+};
/*
* Kernel module parameter to specify maximum number of supported queues per
* device
uint64_t tba_addr,
uint64_t tma_addr);
+/* CRIU */
+/*
+ * Need to increment KFD_CRIU_PRIV_VERSION each time a change is made to any of the CRIU private
+ * structures:
+ * kfd_criu_process_priv_data
+ * kfd_criu_device_priv_data
+ * kfd_criu_bo_priv_data
+ * kfd_criu_queue_priv_data
+ * kfd_criu_event_priv_data
+ * kfd_criu_svm_range_priv_data
+ */
+
+#define KFD_CRIU_PRIV_VERSION 1
+
+struct kfd_criu_process_priv_data {
+ uint32_t version;
+};
+
+struct kfd_criu_device_priv_data {
+ /* For future use */
+ uint64_t reserved;
+};
+
+struct kfd_criu_bo_priv_data {
+ uint64_t reserved;
+};
+
+struct kfd_criu_svm_range_priv_data {
+ uint32_t object_type;
+ uint32_t reserved;
+};
+
+struct kfd_criu_queue_priv_data {
+ uint32_t object_type;
+ uint32_t reserved;
+};
+
+struct kfd_criu_event_priv_data {
+ uint32_t object_type;
+ uint32_t reserved;
+};
+
+/* CRIU - End */
+
/* Queue Context Management */
int init_queue(struct queue **q, const struct queue_properties *properties);
void uninit_queue(struct queue *q);
__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 {
#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
projects / linux.git / commitdiff