Debian Codegraph @

Documentation/trace/rv/monitor_sched.rst

raw
1 Scheduler monitors
2 ==================
3
4 - Name: sched
5 - Type: container for multiple monitors
6 - Author: Gabriele Monaco <[email protected]>, Daniel Bristot de Oliveira <[email protected]>
7
8 Description
9 -----------
10
11 Monitors describing complex systems, such as the scheduler, can easily grow to
12 the point where they are just hard to understand because of the many possible
13 state transitions.
14 Often it is possible to break such descriptions into smaller monitors,
15 sharing some or all events. Enabling those smaller monitors concurrently is,
16 in fact, testing the system as if we had one single larger monitor.
17 Splitting models into multiple specification is not only easier to
18 understand, but gives some more clues when we see errors.
19
20 The sched monitor is a set of specifications to describe the scheduler behaviour.
21 It includes several per-cpu and per-task monitors that work independently to verify
22 different specifications the scheduler should follow.
23
24 To make this system as straightforward as possible, sched specifications are *nested*
25 monitors, whereas sched itself is a *container*.
26 From the interface perspective, sched includes other monitors as sub-directories,
27 enabling/disabling or setting reactors to sched, propagates the change to all monitors,
28 however single monitors can be used independently as well.
29
30 It is important that future modules are built after their container (sched, in
31 this case), otherwise the linker would not respect the order and the nesting
32 wouldn't work as expected.
33 To do so, simply add them after sched in the Makefile.
34
35 Specifications
36 --------------
37
38 The specifications included in sched are currently a work in progress, adapting the ones
39 defined in by Daniel Bristot in [1].
40
41 Currently we included the following:
42
43 Monitor sco
44 ~~~~~~~~~~~
45
46 The scheduling context operations (sco) monitor ensures changes in a task state
47 happen only in thread context::
48
49
50 |
51 |
52 v
53 sched_set_state +------------------+
54 +------------------ | |
55 | | thread_context |
56 +-----------------> | | <+
57 +------------------+ |
58 | |
59 | schedule_entry | schedule_exit
60 v |
61 |
62 scheduling_context -+
63
64 Monitor snroc
65 ~~~~~~~~~~~~~
66
67 The set non runnable on its own context (snroc) monitor ensures changes in a
68 task state happens only in the respective task's context. This is a per-task
69 monitor::
70
71 |
72 |
73 v
74 +------------------+
75 | other_context | <+
76 +------------------+ |
77 | |
78 | sched_switch_in | sched_switch_out
79 v |
80 sched_set_state |
81 +------------------ |
82 | own_context |
83 +-----------------> -+
84
85 Monitor scpd
86 ~~~~~~~~~~~~
87
88 The schedule called with preemption disabled (scpd) monitor ensures schedule is
89 called with preemption disabled::
90
91 |
92 |
93 v
94 +------------------+
95 | cant_sched | <+
96 +------------------+ |
97 | |
98 | preempt_disable | preempt_enable
99 v |
100 schedule_entry |
101 schedule_exit |
102 +----------------- can_sched |
103 | |
104 +----------------> -+
105
106 Monitor snep
107 ~~~~~~~~~~~~
108
109 The schedule does not enable preempt (snep) monitor ensures a schedule call
110 does not enable preemption::
111
112 |
113 |
114 v
115 preempt_disable +------------------------+
116 preempt_enable | |
117 +------------------ | non_scheduling_context |
118 | | |
119 +-----------------> | | <+
120 +------------------------+ |
121 | |
122 | schedule_entry | schedule_exit
123 v |
124 |
125 scheduling_contex -+
126
127 Monitor sts
128 ~~~~~~~~~~~
129
130 The schedule implies task switch (sts) monitor ensures a task switch happens
131 only in scheduling context and up to once, as well as scheduling occurs with
132 interrupts enabled but no task switch can happen before interrupts are
133 disabled. When the next task picked for execution is the same as the previously
134 running one, no real task switch occurs but interrupts are disabled nonetheless::
135
136 irq_entry |
137 +----+ |
138 v | v
139 +------------+ irq_enable #===================# irq_disable
140 | | ------------> H H irq_entry
141 | cant_sched | <------------ H H irq_enable
142 | | irq_disable H can_sched H --------------+
143 +------------+ H H |
144 H H |
145 +---------------> H H <-------------+
146 | #===================#
147 | |
148 schedule_exit | schedule_entry
149 | v
150 | +-------------------+ irq_enable
151 | | scheduling | <---------------+
152 | +-------------------+ |
153 | | |
154 | | irq_disable +--------+ irq_entry
155 | v | | --------+
156 | +-------------------+ irq_entry | in_irq | |
157 | | | -----------> | | <-------+
158 | | disable_to_switch | +--------+
159 | | | --+
160 | +-------------------+ |
161 | | |
162 | | sched_switch |
163 | v |
164 | +-------------------+ |
165 | | switching | | irq_enable
166 | +-------------------+ |
167 | | |
168 | | irq_enable |
169 | v |
170 | +-------------------+ |
171 +-- | enable_to_exit | <-+
172 +-------------------+
173 ^ | irq_disable
174 | | irq_entry
175 +---------------+ irq_enable
176
177 Monitor nrp
178 -----------
179
180 The need resched preempts (nrp) monitor ensures preemption requires
181 ``need_resched``. Only kernel preemption is considered, since preemption
182 while returning to userspace, for this monitor, is indistinguishable from
183 ``sched_switch_yield`` (described in the sssw monitor).
184 A kernel preemption is whenever ``__schedule`` is called with the preemption
185 flag set to true (e.g. from preempt_enable or exiting from interrupts). This
186 type of preemption occurs after the need for ``rescheduling`` has been set.
187 This is not valid for the *lazy* variant of the flag, which causes only
188 userspace preemption.
189 A ``schedule_entry_preempt`` may involve a task switch or not, in the latter
190 case, a task goes through the scheduler from a preemption context but it is
191 picked as the next task to run. Since the scheduler runs, this clears the need
192 to reschedule. The ``any_thread_running`` state does not imply the monitored
193 task is not running as this monitor does not track the outcome of scheduling.
194
195 In theory, a preemption can only occur after the ``need_resched`` flag is set. In
196 practice, however, it is possible to see a preemption where the flag is not
197 set. This can happen in one specific condition::
198
199 need_resched
200 preempt_schedule()
201 preempt_schedule_irq()
202 __schedule()
203 !need_resched
204 __schedule()
205
206 In the situation above, standard preemption starts (e.g. from preempt_enable
207 when the flag is set), an interrupt occurs before scheduling and, on its exit
208 path, it schedules, which clears the ``need_resched`` flag.
209 When the preempted task runs again, the standard preemption started earlier
210 resumes, although the flag is no longer set. The monitor considers this a
211 ``nested_preemption``, this allows another preemption without re-setting the
212 flag. This condition relaxes the monitor constraints and may catch false
213 negatives (i.e. no real ``nested_preemptions``) but makes the monitor more
214 robust and able to validate other scenarios.
215 For simplicity, the monitor starts in ``preempt_irq``, although no interrupt
216 occurred, as the situation above is hard to pinpoint::
217
218 schedule_entry
219 irq_entry #===========================================#
220 +-------------------------- H H
221 | H H
222 +-------------------------> H any_thread_running H
223 H H
224 +-------------------------> H H
225 | #===========================================#
226 | schedule_entry | ^
227 | schedule_entry_preempt | sched_need_resched | schedule_entry
228 | | schedule_entry_preempt
229 | v |
230 | +----------------------+ |
231 | +--- | | |
232 | sched_need_resched | | rescheduling | -+
233 | +--> | |
234 | +----------------------+
235 | | irq_entry
236 | v
237 | +----------------------+
238 | | | ---+
239 | ---> | | | sched_need_resched
240 | | preempt_irq | | irq_entry
241 | | | <--+
242 | | | <--+
243 | +----------------------+ |
244 | | schedule_entry | sched_need_resched
245 | | schedule_entry_preempt |
246 | v |
247 | +-----------------------+ |
248 +-------------------------- | nested_preempt | --+
249 +-----------------------+
250 ^ irq_entry |
251 +-------------------+
252
253 Due to how the ``need_resched`` flag on the preemption count works on arm64,
254 this monitor is unstable on that architecture, as it often records preemption
255 when the flag is not set, even in presence of the workaround above.
256 For the time being, the monitor is disabled by default on arm64.
257
258 Monitor sssw
259 ------------
260
261 The set state sleep and wakeup (sssw) monitor ensures ``set_state`` to
262 sleepable leads to sleeping and sleeping tasks require wakeup. It includes the
263 following types of switch:
264
265 * ``switch_suspend``:
266 a task puts itself to sleep, this can happen only after explicitly setting
267 the task to ``sleepable``. After a task is suspended, it needs to be woken up
268 (``waking`` state) before being switched in again.
269 Setting the task's state to ``sleepable`` can be reverted before switching if it
270 is woken up or set to ``runnable``.
271 * ``switch_blocking``:
272 a special case of a ``switch_suspend`` where the task is waiting on a
273 sleeping RT lock (``PREEMPT_RT`` only), it is common to see wakeup and set
274 state events racing with each other and this leads the model to perceive this
275 type of switch when the task is not set to sleepable. This is a limitation of
276 the model in SMP system and workarounds may slow down the system.
277 * ``switch_preempt``:
278 a task switch as a result of kernel preemption (``schedule_entry_preempt`` in
279 the nrp model).
280 * ``switch_yield``:
281 a task explicitly calls the scheduler or is preempted while returning to
282 userspace. It can happen after a ``yield`` system call, from the idle task or
283 if the ``need_resched`` flag is set. By definition, a task cannot yield while
284 ``sleepable`` as that would be a suspension. A special case of a yield occurs
285 when a task in ``TASK_INTERRUPTIBLE`` calls the scheduler while a signal is
286 pending. The task doesn't go through the usual blocking/waking and is set
287 back to runnable, the resulting switch (if there) looks like a yield to the
288 ``signal_wakeup`` state and is followed by the signal delivery. From this
289 state, the monitor expects a signal even if it sees a wakeup event, although
290 not necessary, to rule out false negatives.
291
292 This monitor doesn't include a running state, ``sleepable`` and ``runnable``
293 are only referring to the task's desired state, which could be scheduled out
294 (e.g. due to preemption). However, it does include the event
295 ``sched_switch_in`` to represent when a task is allowed to become running. This
296 can be triggered also by preemption, but cannot occur after the task got to
297 ``sleeping`` before a ``wakeup`` occurs::
298
299 +--------------------------------------------------------------------------+
300 | |
301 | |
302 | switch_suspend | |
303 | switch_blocking | |
304 v v |
305 +----------+ #==========================# set_state_runnable |
306 | | H H wakeup |
307 | | H H switch_in |
308 | | H H switch_yield |
309 | sleeping | H H switch_preempt |
310 | | H H signal_deliver |
311 | | switch_ H H ------+ |
312 | | _blocking H runnable H | |
313 | | <----------- H H <-----+ |
314 +----------+ H H |
315 | wakeup H H |
316 +---------------------> H H |
317 H H |
318 +---------> H H |
319 | #==========================# |
320 | | ^ |
321 | | | set_state_runnable |
322 | | | wakeup |
323 | set_state_sleepable | +------------------------+
324 | v | |
325 | +--------------------------+ set_state_sleepable
326 | | | switch_in
327 | | | switch_preempt
328 signal_deliver | sleepable | signal_deliver
329 | | | ------+
330 | | | |
331 | | | <-----+
332 | +--------------------------+
333 | | ^
334 | switch_yield | set_state_sleepable
335 | v |
336 | +---------------+ |
337 +---------- | signal_wakeup | -+
338 +---------------+
339 ^ | switch_in
340 | | switch_preempt
341 | | switch_yield
342 +-----------+ wakeup
343
344 Monitor opid
345 ------------
346
347 The operations with preemption and irq disabled (opid) monitor ensures
348 operations like ``wakeup`` and ``need_resched`` occur with interrupts and
349 preemption disabled or during interrupt context, in such case preemption may
350 not be disabled explicitly.
351 ``need_resched`` can be set by some RCU internals functions, in which case it
352 doesn't match a task wakeup and might occur with only interrupts disabled::
353
354 | sched_need_resched
355 | sched_waking
356 | irq_entry
357 | +--------------------+
358 v v |
359 +------------------------------------------------------+
360 +----------- | disabled | <+
361 | +------------------------------------------------------+ |
362 | | ^ |
363 | | preempt_disable sched_need_resched |
364 | preempt_enable | +--------------------+ |
365 | v | v | |
366 | +------------------------------------------------------+ |
367 | | irq_disabled | |
368 | +------------------------------------------------------+ |
369 | | | ^ |
370 | irq_entry irq_entry | | |
371 | sched_need_resched v | irq_disable |
372 | sched_waking +--------------+ | | |
373 | +----- | | irq_enable | |
374 | | | in_irq | | | |
375 | +----> | | | | |
376 | +--------------+ | | irq_disable
377 | | | | |
378 | irq_enable | irq_enable | | |
379 | v v | |
380 | #======================================================# |
381 | H enabled H |
382 | #======================================================# |
383 | | ^ ^ preempt_enable | |
384 | preempt_disable preempt_enable +--------------------+ |
385 | v | |
386 | +------------------+ | |
387 +----------> | preempt_disabled | -+ |
388 +------------------+ |
389 | |
390 +-------------------------------------------------------+
391
392 This monitor is designed to work on ``PREEMPT_RT`` kernels, the special case of
393 events occurring in interrupt context is a shortcut to identify valid scenarios
394 where the preemption tracepoints might not be visible, during interrupts
395 preemption is always disabled. On non- ``PREEMPT_RT`` kernels, the interrupts
396 might invoke a softirq to set ``need_resched`` and wake up a task. This is
397 another special case that is currently not supported by the monitor.
398
399 References
400 ----------
401
402 [1] - https://bristot.me/linux-task-model