1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524
use crate::{
error::OciSpecError,
runtime::{Capabilities, Capability},
};
use derive_builder::Builder;
use getset::{CopyGetters, Getters, Setters};
use serde::{Deserialize, Serialize};
use std::path::PathBuf;
#[derive(
Builder, Clone, CopyGetters, Debug, Deserialize, Getters, Setters, Eq, PartialEq, Serialize,
)]
#[serde(rename_all = "camelCase")]
#[builder(
default,
pattern = "owned",
setter(into, strip_option),
build_fn(error = "OciSpecError")
)]
/// Process contains information to start a specific application inside the
/// container.
pub struct Process {
#[serde(default, skip_serializing_if = "Option::is_none")]
#[getset(get_copy = "pub", set = "pub")]
/// Terminal creates an interactive terminal for the container.
terminal: Option<bool>,
#[serde(default, skip_serializing_if = "Option::is_none")]
#[getset(get_copy = "pub", set = "pub")]
/// ConsoleSize specifies the size of the console.
console_size: Option<Box>,
#[getset(get = "pub", set = "pub")]
/// User specifies user information for the process.
user: User,
#[serde(default, skip_serializing_if = "Option::is_none")]
#[getset(get = "pub", set = "pub")]
/// Args specifies the binary and arguments for the application to
/// execute.
args: Option<Vec<String>>,
#[serde(default, skip_serializing_if = "Option::is_none")]
#[getset(get = "pub", set = "pub")]
/// CommandLine specifies the full command line for the application to
/// execute on Windows.
command_line: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
#[getset(get = "pub", set = "pub")]
/// Env populates the process environment for the process.
env: Option<Vec<String>>,
#[getset(get = "pub", set = "pub")]
/// Cwd is the current working directory for the process and must be
/// relative to the container's root.
cwd: PathBuf,
#[serde(default, skip_serializing_if = "Option::is_none")]
#[getset(get = "pub", set = "pub")]
/// Capabilities are Linux capabilities that are kept for the process.
capabilities: Option<LinuxCapabilities>,
#[serde(default, skip_serializing_if = "Option::is_none")]
#[getset(get = "pub", set = "pub")]
/// Rlimits specifies rlimit options to apply to the process.
rlimits: Option<Vec<LinuxRlimit>>,
#[serde(default, skip_serializing_if = "Option::is_none")]
#[getset(get_copy = "pub", set = "pub")]
/// NoNewPrivileges controls whether additional privileges could be
/// gained by processes in the container.
no_new_privileges: Option<bool>,
#[serde(default, skip_serializing_if = "Option::is_none")]
#[getset(get = "pub", set = "pub")]
/// ApparmorProfile specifies the apparmor profile for the container.
apparmor_profile: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
#[getset(get_copy = "pub", set = "pub")]
/// Specify an oom_score_adj for the container.
oom_score_adj: Option<i32>,
#[serde(default, skip_serializing_if = "Option::is_none")]
#[getset(get = "pub", set = "pub")]
/// SelinuxLabel specifies the selinux context that the container
/// process is run as.
selinux_label: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
#[getset(get = "pub", set = "pub")]
/// IOPriority contains the I/O priority settings for the cgroup.
io_priority: Option<LinuxIOPriority>,
#[serde(default, skip_serializing_if = "Option::is_none")]
#[getset(get = "pub", set = "pub")]
/// Scheduler specifies the scheduling attributes for a process
scheduler: Option<Scheduler>,
}
// Default impl for processes in the container
impl Default for Process {
fn default() -> Self {
Process {
// Don't create an interactive terminal for container by default
terminal: false.into(),
// Gives default console size of 0, 0
console_size: Default::default(),
// Gives process a uid and gid of 0 (root)
user: Default::default(),
// By default executes sh command, giving user shell
args: vec!["sh".to_string()].into(),
// Sets linux default enviroment for binaries and default xterm emulator
env: vec![
"PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin".into(),
"TERM=xterm".into(),
]
.into(),
// Sets cwd of process to the container root by default
cwd: "/".into(),
// By default does not allow process to gain additional privileges
no_new_privileges: true.into(),
// Empty String, no default apparmor
apparmor_profile: Default::default(),
// Empty String, no default selinux
selinux_label: Default::default(),
// Empty String, no default scheduler
scheduler: Default::default(),
// See impl Default for LinuxCapabilities
capabilities: Some(Default::default()),
// Sets the default maximum of 1024 files the process can open
// This is the same as the linux kernel default
rlimits: vec![LinuxRlimit {
typ: LinuxRlimitType::RlimitNofile,
hard: 1024,
soft: 1024,
}]
.into(),
oom_score_adj: None,
command_line: None,
// Empty IOPriority, no default iopriority
io_priority: Default::default(),
}
}
}
#[derive(
Builder, Clone, Copy, CopyGetters, Debug, Default, Deserialize, Eq, PartialEq, Serialize,
)]
#[builder(
default,
pattern = "owned",
setter(into, strip_option),
build_fn(error = "OciSpecError")
)]
#[getset(get_copy = "pub", set = "pub")]
/// Box specifies dimensions of a rectangle. Used for specifying the size of
/// a console.
pub struct Box {
#[serde(default)]
/// Height is the vertical dimension of a box.
height: u64,
#[serde(default)]
/// Width is the horizontal dimension of a box.
width: u64,
}
#[derive(Clone, Copy, Debug, Deserialize, Eq, PartialEq, Serialize)]
#[serde(rename_all = "SCREAMING_SNAKE_CASE")]
/// Available rlimit types (see <https://man7.org/linux/man-pages/man2/getrlimit.2.html>)
pub enum LinuxRlimitType {
/// Limit in seconds of the amount of CPU time that the process can consume.
RlimitCpu,
/// Maximum size in bytes of the files that the process creates.
RlimitFsize,
/// Maximum size of the process's data segment (init data, uninit data and
/// heap) in bytes.
RlimitData,
/// Maximum size of the proces stack in bytes.
RlimitStack,
/// Maximum size of a core dump file in bytes.
RlimitCore,
/// Limit on the process's resident set (the number of virtual pages
/// resident in RAM).
RlimitRss,
/// Limit on number of threads for the real uid calling processes.
RlimitNproc,
/// One greator than the maximum number of file descritors that one process
/// may open.
RlimitNofile,
/// Maximum number of bytes of memory that may be locked into RAM.
RlimitMemlock,
/// Maximum size of the process's virtual memory(address space) in bytes.
RlimitAs,
/// Limit on the number of locks and leases for the process.
RlimitLocks,
/// Limit on number of signals that may be queued for the process.
RlimitSigpending,
/// Limit on the number of bytes that can be allocated for POSIX message
/// queue.
RlimitMsgqueue,
/// Specifies a ceiling to which the process's nice value can be raised.
RlimitNice,
/// Specifies a ceiling on the real-time priority.
RlimitRtprio,
/// This is a limit (in microseconds) on the amount of CPU time that a
/// process scheduled under a real-time scheduling policy may consume
/// without making a blocking system call.
RlimitRttime,
}
impl Default for LinuxRlimitType {
fn default() -> Self {
Self::RlimitCpu
}
}
#[derive(
Builder, Clone, Copy, CopyGetters, Debug, Default, Deserialize, Eq, PartialEq, Serialize,
)]
#[builder(
default,
pattern = "owned",
setter(into, strip_option),
build_fn(error = "OciSpecError")
)]
#[getset(get_copy = "pub", set = "pub")]
/// RLimit types and restrictions.
pub struct LinuxRlimit {
#[serde(rename = "type")]
/// Type of Rlimit to set
typ: LinuxRlimitType,
#[serde(default)]
/// Hard limit for specified type
hard: u64,
#[serde(default)]
/// Soft limit for specified type
soft: u64,
}
#[derive(
Builder,
Clone,
CopyGetters,
Debug,
Default,
Deserialize,
Getters,
Setters,
Eq,
PartialEq,
Serialize,
)]
#[serde(rename_all = "camelCase")]
#[builder(
default,
pattern = "owned",
setter(into, strip_option),
build_fn(error = "OciSpecError")
)]
/// User id (uid) and group id (gid) tracks file permssions.
pub struct User {
#[serde(default)]
#[getset(get_copy = "pub", set = "pub")]
/// UID is the user id.
uid: u32,
#[serde(default)]
#[getset(get_copy = "pub", set = "pub")]
/// GID is the group id.
gid: u32,
#[serde(default, skip_serializing_if = "Option::is_none")]
#[getset(get_copy = "pub", set = "pub")]
/// Specifies the umask of the user.
umask: Option<u32>,
#[serde(default, skip_serializing_if = "Option::is_none")]
#[getset(get = "pub", set = "pub")]
/// AdditionalGids are additional group ids set for the container's
/// process.
additional_gids: Option<Vec<u32>>,
#[serde(default, skip_serializing_if = "Option::is_none")]
#[getset(get = "pub", set = "pub")]
/// Username is the user name.
username: Option<String>,
}
#[derive(Builder, Clone, Debug, Deserialize, Getters, Setters, Eq, PartialEq, Serialize)]
#[builder(
default,
pattern = "owned",
setter(into, strip_option),
build_fn(error = "OciSpecError")
)]
#[getset(get = "pub", set = "pub")]
/// LinuxCapabilities specifies the list of allowed capabilities that are
/// kept for a process. <http://man7.org/linux/man-pages/man7/capabilities.7.html>
pub struct LinuxCapabilities {
#[serde(default, skip_serializing_if = "Option::is_none")]
/// Bounding is the set of capabilities checked by the kernel.
bounding: Option<Capabilities>,
#[serde(default, skip_serializing_if = "Option::is_none")]
/// Effective is the set of capabilities checked by the kernel.
effective: Option<Capabilities>,
#[serde(default, skip_serializing_if = "Option::is_none")]
/// Inheritable is the capabilities preserved across execve.
inheritable: Option<Capabilities>,
#[serde(default, skip_serializing_if = "Option::is_none")]
/// Permitted is the limiting superset for effective capabilities.
permitted: Option<Capabilities>,
#[serde(default, skip_serializing_if = "Option::is_none")]
/// Ambient is the ambient set of capabilities that are kept.
ambient: Option<Capabilities>,
}
// Default container's linux capabilities:
// CAP_AUDIT_WRITE gives container ability to write to linux audit logs,
// CAP_KILL gives container ability to kill non root processes
// CAP_NET_BIND_SERVICE allows container to bind to ports below 1024
impl Default for LinuxCapabilities {
fn default() -> Self {
let audit_write = Capability::AuditWrite;
let cap_kill = Capability::Kill;
let net_bind = Capability::NetBindService;
let default_vec = vec![audit_write, cap_kill, net_bind]
.into_iter()
.collect::<Capabilities>();
LinuxCapabilities {
bounding: default_vec.clone().into(),
effective: default_vec.clone().into(),
inheritable: default_vec.clone().into(),
permitted: default_vec.clone().into(),
ambient: default_vec.into(),
}
}
}
#[derive(
Builder, Clone, Copy, CopyGetters, Debug, Default, Deserialize, Eq, PartialEq, Serialize,
)]
#[builder(
default,
pattern = "owned",
setter(into, strip_option),
build_fn(error = "OciSpecError")
)]
#[getset(get_copy = "pub", set = "pub")]
/// RLimit types and restrictions.
pub struct LinuxIOPriority {
#[serde(default)]
/// Class represents an I/O scheduling class.
class: IOPriorityClass,
#[serde(default)]
/// Priority for the io operation
priority: i64,
}
#[derive(Clone, Copy, Debug, Deserialize, Eq, PartialEq, Serialize)]
#[serde(rename_all = "SCREAMING_SNAKE_CASE")]
/// IOPriorityClass represents an I/O scheduling class.
pub enum IOPriorityClass {
/// This is the realtime io class. This scheduling class is given
/// higher priority than any other in the system, processes from this class are
/// given first access to the disk every time. Thus it needs to be used with some
/// care, one io RT process can starve the entire system. Within the RT class,
/// there are 8 levels of class data that determine exactly how much time this
/// process needs the disk for on each service. In the future this might change
/// to be more directly mappable to performance, by passing in a wanted data
/// rate instead
IoprioClassRt,
/// This is the best-effort scheduling class, which is the default
/// for any process that hasn't set a specific io priority. The class data
/// determines how much io bandwidth the process will get, it's directly mappable
/// to the cpu nice levels just more coarsely implemented. 0 is the highest
/// BE prio level, 7 is the lowest. The mapping between cpu nice level and io
/// nice level is determined as: io_nice = (cpu_nice + 20) / 5.
IoprioClassBe,
/// This is the idle scheduling class, processes running at this
/// level only get io time when no one else needs the disk. The idle class has no
/// class data, since it doesn't really apply here.
IoprioClassIdle,
}
impl Default for IOPriorityClass {
fn default() -> Self {
Self::IoprioClassBe
}
}
#[derive(Builder, Clone, Debug, Deserialize, Getters, Setters, Eq, PartialEq, Serialize)]
#[builder(
default,
pattern = "owned",
setter(into, strip_option),
build_fn(error = "OciSpecError")
)]
#[getset(get = "pub", set = "pub")]
/// Scheduler represents the scheduling attributes for a process. It is based on
/// the Linux sched_setattr(2) syscall.
pub struct Scheduler {
/// Policy represents the scheduling policy (e.g., SCHED_FIFO, SCHED_RR, SCHED_OTHER).
policy: LinuxSchedulerPolicy,
#[serde(default, skip_serializing_if = "Option::is_none")]
/// Nice is the nice value for the process, which affects its priority.
nice: Option<i32>,
#[serde(default, skip_serializing_if = "Option::is_none")]
/// Priority represents the static priority of the process.
priority: Option<i32>,
#[serde(default, skip_serializing_if = "Option::is_none")]
/// Flags is an array of scheduling flags.
flags: Option<Vec<LinuxSchedulerFlag>>,
// The following ones are used by the DEADLINE scheduler.
#[serde(default, skip_serializing_if = "Option::is_none")]
/// Runtime is the amount of time in nanoseconds during which the process
/// is allowed to run in a given period.
runtime: Option<u64>,
#[serde(default, skip_serializing_if = "Option::is_none")]
/// Deadline is the absolute deadline for the process to complete its execution.
deadline: Option<u64>,
#[serde(default, skip_serializing_if = "Option::is_none")]
/// Period is the length of the period in nanoseconds used for determining the process runtime.
period: Option<u64>,
}
/// Default scheduler is SCHED_OTHER with no priority.
impl Default for Scheduler {
fn default() -> Self {
Self {
policy: LinuxSchedulerPolicy::default(),
nice: None,
priority: None,
flags: None,
runtime: None,
deadline: None,
period: None,
}
}
}
#[derive(Clone, Copy, Debug, Deserialize, Eq, PartialEq, Serialize)]
#[serde(rename_all = "SCREAMING_SNAKE_CASE")]
/// LinuxSchedulerPolicy represents different scheduling policies used with the Linux Scheduler
pub enum LinuxSchedulerPolicy {
/// SchedOther is the default scheduling policy
SchedOther,
/// SchedFIFO is the First-In-First-Out scheduling policy
SchedFifo,
/// SchedRR is the Round-Robin scheduling policy
SchedRr,
/// SchedBatch is the Batch scheduling policy
SchedBatch,
/// SchedISO is the Isolation scheduling policy
SchedIso,
/// SchedIdle is the Idle scheduling policy
SchedIdle,
/// SchedDeadline is the Deadline scheduling policy
SchedDeadline,
}
/// Default LinuxSchedulerPolicy is SchedOther
impl Default for LinuxSchedulerPolicy {
fn default() -> Self {
LinuxSchedulerPolicy::SchedOther
}
}
#[derive(Clone, Copy, Debug, Deserialize, Eq, PartialEq, Serialize)]
#[serde(rename_all = "SCREAMING_SNAKE_CASE")]
/// LinuxSchedulerFlag represents the flags used by the Linux Scheduler.
pub enum LinuxSchedulerFlag {
/// SchedFlagResetOnFork represents the reset on fork scheduling flag
SchedResetOnFork,
/// SchedFlagReclaim represents the reclaim scheduling flag
SchedFlagReclaim,
/// SchedFlagDLOverrun represents the deadline overrun scheduling flag
SchedFlagDLOverrun,
/// SchedFlagKeepPolicy represents the keep policy scheduling flag
SchedFlagKeepPolicy,
/// SchedFlagKeepParams represents the keep parameters scheduling flag
SchedFlagKeepParams,
/// SchedFlagUtilClampMin represents the utilization clamp minimum scheduling flag
SchedFlagUtilClampMin,
/// SchedFlagUtilClampMin represents the utilization clamp maximum scheduling flag
SchedFlagUtilClampMax,
}
/// Default LinuxSchedulerFlag is SchedResetOnFork
impl Default for LinuxSchedulerFlag {
fn default() -> Self {
LinuxSchedulerFlag::SchedResetOnFork
}
}