€•þÏŒsphinx.addnodes”Œdocument”“”)”}”(Œ rawsource”Œ”Œchildren”]”(Œ translations”Œ LanguagesNode”“”)”}”(hhh]”(hŒ pending_xref”“”)”}”(hhh]”Œdocutils.nodes”ŒText”“”ŒChinese (Simplified)”…””}”Œparent”hsbaŒ attributes”}”(Œids”]”Œclasses”]”Œnames”]”Œdupnames”]”Œbackrefs”]”Œ refdomain”Œstd”Œreftype”Œdoc”Œ reftarget”Œ*/translations/zh_CN/trace/rv/monitor_sched”Œmodname”NŒ classname”NŒ refexplicit”ˆuŒtagname”hhh ubh)”}”(hhh]”hŒChinese (Traditional)”…””}”hh2sbah}”(h]”h ]”h"]”h$]”h&]”Œ refdomain”h)Œreftype”h+Œ reftarget”Œ*/translations/zh_TW/trace/rv/monitor_sched”Œmodname”NŒ classname”NŒ refexplicit”ˆuh1hhh ubh)”}”(hhh]”hŒItalian”…””}”hhFsbah}”(h]”h ]”h"]”h$]”h&]”Œ refdomain”h)Œreftype”h+Œ reftarget”Œ*/translations/it_IT/trace/rv/monitor_sched”Œmodname”NŒ classname”NŒ refexplicit”ˆuh1hhh ubh)”}”(hhh]”hŒJapanese”…””}”hhZsbah}”(h]”h ]”h"]”h$]”h&]”Œ refdomain”h)Œreftype”h+Œ reftarget”Œ*/translations/ja_JP/trace/rv/monitor_sched”Œmodname”NŒ classname”NŒ refexplicit”ˆuh1hhh ubh)”}”(hhh]”hŒKorean”…””}”hhnsbah}”(h]”h ]”h"]”h$]”h&]”Œ refdomain”h)Œreftype”h+Œ reftarget”Œ*/translations/ko_KR/trace/rv/monitor_sched”Œmodname”NŒ classname”NŒ refexplicit”ˆuh1hhh ubh)”}”(hhh]”hŒPortuguese (Brazilian)”…””}”hh‚sbah}”(h]”h ]”h"]”h$]”h&]”Œ refdomain”h)Œreftype”h+Œ reftarget”Œ*/translations/pt_BR/trace/rv/monitor_sched”Œmodname”NŒ classname”NŒ refexplicit”ˆuh1hhh ubh)”}”(hhh]”hŒSpanish”…””}”hh–sbah}”(h]”h ]”h"]”h$]”h&]”Œ refdomain”h)Œreftype”h+Œ reftarget”Œ*/translations/sp_SP/trace/rv/monitor_sched”Œmodname”NŒ classname”NŒ refexplicit”ˆuh1hhh ubeh}”(h]”h ]”h"]”h$]”h&]”Œcurrent_language”ŒEnglish”uh1h hhŒ _document”hŒsource”NŒline”NubhŒsection”“”)”}”(hhh]”(hŒtitle”“”)”}”(hŒScheduler monitors”h]”hŒScheduler monitors”…””}”(hh¼h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hºhh·h²hh³ŒD/var/lib/git/docbuild/linux/Documentation/trace/rv/monitor_sched.rst”h´KubhŒ bullet_list”“”)”}”(hhh]”(hŒ list_item”“”)”}”(hŒ Name: sched”h]”hŒ paragraph”“”)”}”(hhÔh]”hŒ Name: sched”…””}”(hhØh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´KhhÒubah}”(h]”h ]”h"]”h$]”h&]”uh1hÐhhÍh²hh³hÊh´NubhÑ)”}”(hŒ%Type: container for multiple monitors”h]”h×)”}”(hhíh]”hŒ%Type: container for multiple monitors”…””}”(hhïh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´Khhëubah}”(h]”h ]”h"]”h$]”h&]”uh1hÐhhÍh²hh³hÊh´NubhÑ)”}”(hŒ^Author: Gabriele Monaco , Daniel Bristot de Oliveira ”h]”h×)”}”(hŒ]Author: Gabriele Monaco , Daniel Bristot de Oliveira ”h]”(hŒAuthor: Gabriele Monaco <”…””}”(hjh²hh³Nh´NubhŒ reference”“”)”}”(hŒgmonaco@redhat.com”h]”hŒgmonaco@redhat.com”…””}”(hjh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”Œrefuri”Œmailto:gmonaco@redhat.com”uh1jhjubhŒ>, Daniel Bristot de Oliveira <”…””}”(hjh²hh³Nh´Nubj)”}”(hŒbristot@kernel.org”h]”hŒbristot@kernel.org”…””}”(hj$h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”Œrefuri”Œmailto:bristot@kernel.org”uh1jhjubhŒ>”…””}”(hjh²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´Khjubah}”(h]”h ]”h"]”h$]”h&]”uh1hÐhhÍh²hh³hÊh´Nubeh}”(h]”h ]”h"]”h$]”h&]”Œbullet”Œ-”uh1hËh³hÊh´Khh·h²hubh¶)”}”(hhh]”(h»)”}”(hŒ Description”h]”hŒ Description”…””}”(hjOh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hºhjLh²hh³hÊh´K ubh×)”}”(hXMonitors describing complex systems, such as the scheduler, can easily grow to the point where they are just hard to understand because of the many possible state transitions. Often it is possible to break such descriptions into smaller monitors, sharing some or all events. Enabling those smaller monitors concurrently is, in fact, testing the system as if we had one single larger monitor. Splitting models into multiple specification is not only easier to understand, but gives some more clues when we see errors.”h]”hXMonitors describing complex systems, such as the scheduler, can easily grow to the point where they are just hard to understand because of the many possible state transitions. Often it is possible to break such descriptions into smaller monitors, sharing some or all events. Enabling those smaller monitors concurrently is, in fact, testing the system as if we had one single larger monitor. Splitting models into multiple specification is not only easier to understand, but gives some more clues when we see errors.”…””}”(hj]h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´K hjLh²hubh×)”}”(hŒÛThe sched monitor is a set of specifications to describe the scheduler behaviour. It includes several per-cpu and per-task monitors that work independently to verify different specifications the scheduler should follow.”h]”hŒÛThe sched monitor is a set of specifications to describe the scheduler behaviour. It includes several per-cpu and per-task monitors that work independently to verify different specifications the scheduler should follow.”…””}”(hjkh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´KhjLh²hubh×)”}”(hXkTo make this system as straightforward as possible, sched specifications are *nested* monitors, whereas sched itself is a *container*. From the interface perspective, sched includes other monitors as sub-directories, enabling/disabling or setting reactors to sched, propagates the change to all monitors, however single monitors can be used independently as well.”h]”(hŒMTo make this system as straightforward as possible, sched specifications are ”…””}”(hjyh²hh³Nh´NubhŒemphasis”“”)”}”(hŒ*nested*”h]”hŒnested”…””}”(hjƒh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjyubhŒ% monitors, whereas sched itself is a ”…””}”(hjyh²hh³Nh´Nubj‚)”}”(hŒ *container*”h]”hŒ container”…””}”(hj•h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjyubhŒæ. From the interface perspective, sched includes other monitors as sub-directories, enabling/disabling or setting reactors to sched, propagates the change to all monitors, however single monitors can be used independently as well.”…””}”(hjyh²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´KhjLh²hubh×)”}”(hŒíIt is important that future modules are built after their container (sched, in this case), otherwise the linker would not respect the order and the nesting wouldn't work as expected. To do so, simply add them after sched in the Makefile.”h]”hŒïIt is important that future modules are built after their container (sched, in this case), otherwise the linker would not respect the order and the nesting wouldn’t work as expected. To do so, simply add them after sched in the Makefile.”…””}”(hj­h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´KhjLh²hubeh}”(h]”Œ description”ah ]”h"]”Œ description”ah$]”h&]”uh1hµhh·h²hh³hÊh´K ubh¶)”}”(hhh]”(h»)”}”(hŒSpecifications”h]”hŒSpecifications”…””}”(hjÆh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hºhjÃh²hh³hÊh´K$ubh×)”}”(hŒ}The specifications included in sched are currently a work in progress, adapting the ones defined in by Daniel Bristot in [1].”h]”hŒ}The specifications included in sched are currently a work in progress, adapting the ones defined in by Daniel Bristot in [1].”…””}”(hjÔh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´K&hjÃh²hubh×)”}”(hŒ$Currently we included the following:”h]”hŒ$Currently we included the following:”…””}”(hjâh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´K)hjÃh²hubh¶)”}”(hhh]”(h»)”}”(hŒ Monitor sco”h]”hŒ Monitor sco”…””}”(hjóh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hºhjðh²hh³hÊh´K,ubh×)”}”(hŒoThe scheduling context operations (sco) monitor ensures changes in a task state happen only in thread context::”h]”hŒnThe scheduling context operations (sco) monitor ensures changes in a task state happen only in thread context:”…””}”(hjh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´K.hjðh²hubhŒ literal_block”“”)”}”(hX | | v sched_set_state +------------------+ +------------------ | | | | thread_context | +-----------------> | | <+ +------------------+ | | | | schedule_entry | schedule_exit v | | scheduling_context -+”h]”hX | | v sched_set_state +------------------+ +------------------ | | | | thread_context | +-----------------> | | <+ +------------------+ | | | | schedule_entry | schedule_exit v | | scheduling_context -+”…””}”hjsbah}”(h]”h ]”h"]”h$]”h&]”Œ xml:space”Œpreserve”uh1jh³hÊh´K2hjðh²hubeh}”(h]”Œ monitor-sco”ah ]”h"]”Œ monitor sco”ah$]”h&]”uh1hµhjÃh²hh³hÊh´K,ubh¶)”}”(hhh]”(h»)”}”(hŒ Monitor snroc”h]”hŒ Monitor snroc”…””}”(hj,h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hºhj)h²hh³hÊh´KAubh×)”}”(hŒ£The set non runnable on its own context (snroc) monitor ensures changes in a task state happens only in the respective task's context. This is a per-task monitor::”h]”hŒ¤The set non runnable on its own context (snroc) monitor ensures changes in a task state happens only in the respective task’s context. This is a per-task monitor:”…””}”(hj:h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´KChj)h²hubj)”}”(hX  | | v +------------------+ | other_context | <+ +------------------+ | | | | sched_switch_in | sched_switch_out v | sched_set_state | +------------------ | | own_context | +-----------------> -+”h]”hX  | | v +------------------+ | other_context | <+ +------------------+ | | | | sched_switch_in | sched_switch_out v | sched_set_state | +------------------ | | own_context | +-----------------> -+”…””}”hjHsbah}”(h]”h ]”h"]”h$]”h&]”jj uh1jh³hÊh´KGhj)h²hubeh}”(h]”Œ monitor-snroc”ah ]”h"]”Œ monitor snroc”ah$]”h&]”uh1hµhjÃh²hh³hÊh´KAubh¶)”}”(hhh]”(h»)”}”(hŒ Monitor scpd”h]”hŒ Monitor scpd”…””}”(hjah²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hºhj^h²hh³hÊh´KVubh×)”}”(hŒqThe schedule called with preemption disabled (scpd) monitor ensures schedule is called with preemption disabled::”h]”hŒpThe schedule called with preemption disabled (scpd) monitor ensures schedule is called with preemption disabled:”…””}”(hjoh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´KXhj^h²hubj)”}”(hX) | | v +------------------+ | cant_sched | <+ +------------------+ | | | | preempt_disable | preempt_enable v | schedule_entry | schedule_exit | +----------------- can_sched | | | +----------------> -+”h]”hX) | | v +------------------+ | cant_sched | <+ +------------------+ | | | | preempt_disable | preempt_enable v | schedule_entry | schedule_exit | +----------------- can_sched | | | +----------------> -+”…””}”hj}sbah}”(h]”h ]”h"]”h$]”h&]”jj uh1jh³hÊh´K[hj^h²hubeh}”(h]”Œ monitor-scpd”ah ]”h"]”Œ monitor scpd”ah$]”h&]”uh1hµhjÃh²hh³hÊh´KVubh¶)”}”(hhh]”(h»)”}”(hŒ Monitor snep”h]”hŒ Monitor snep”…””}”(hj–h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hºhj“h²hh³hÊh´Kkubh×)”}”(hŒhThe schedule does not enable preempt (snep) monitor ensures a schedule call does not enable preemption::”h]”hŒgThe schedule does not enable preempt (snep) monitor ensures a schedule call does not enable preemption:”…””}”(hj¤h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´Kmhj“h²hubj)”}”(hXo | | v preempt_disable +------------------------+ preempt_enable | | +------------------ | non_scheduling_context | | | | +-----------------> | | <+ +------------------------+ | | | | schedule_entry | schedule_exit v | | scheduling_contex -+”h]”hXo | | v preempt_disable +------------------------+ preempt_enable | | +------------------ | non_scheduling_context | | | | +-----------------> | | <+ +------------------------+ | | | | schedule_entry | schedule_exit v | | scheduling_contex -+”…””}”hj²sbah}”(h]”h ]”h"]”h$]”h&]”jj uh1jh³hÊh´Kphj“h²hubeh}”(h]”Œ monitor-snep”ah ]”h"]”Œ monitor snep”ah$]”h&]”uh1hµhjÃh²hh³hÊh´Kkubh¶)”}”(hhh]”(h»)”}”(hŒ Monitor sts”h]”hŒ Monitor sts”…””}”(hjËh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hºhjÈh²hh³hÊh´K€ubh×)”}”(hX‚The schedule implies task switch (sts) monitor ensures a task switch happens only in scheduling context and up to once, as well as scheduling occurs with interrupts enabled but no task switch can happen before interrupts are disabled. When the next task picked for execution is the same as the previously running one, no real task switch occurs but interrupts are disabled nonetheless::”h]”hXThe schedule implies task switch (sts) monitor ensures a task switch happens only in scheduling context and up to once, as well as scheduling occurs with interrupts enabled but no task switch can happen before interrupts are disabled. When the next task picked for execution is the same as the previously running one, no real task switch occurs but interrupts are disabled nonetheless:”…””}”(hjÙh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´K‚hjÈh²hubj)”}”(hXÞ irq_entry | +----+ | v | v +------------+ irq_enable #===================# irq_disable | | ------------> H H irq_entry | cant_sched | <------------ H H irq_enable | | irq_disable H can_sched H --------------+ +------------+ H H | H H | +---------------> H H <-------------+ | #===================# | | schedule_exit | schedule_entry | v | +-------------------+ irq_enable | | scheduling | <---------------+ | +-------------------+ | | | | | | irq_disable +--------+ irq_entry | v | | --------+ | +-------------------+ irq_entry | in_irq | | | | | -----------> | | <-------+ | | disable_to_switch | +--------+ | | | --+ | +-------------------+ | | | | | | sched_switch | | v | | +-------------------+ | | | switching | | irq_enable | +-------------------+ | | | | | | irq_enable | | v | | +-------------------+ | +-- | enable_to_exit | <-+ +-------------------+ ^ | irq_disable | | irq_entry +---------------+ irq_enable”h]”hXÞ irq_entry | +----+ | v | v +------------+ irq_enable #===================# irq_disable | | ------------> H H irq_entry | cant_sched | <------------ H H irq_enable | | irq_disable H can_sched H --------------+ +------------+ H H | H H | +---------------> H H <-------------+ | #===================# | | schedule_exit | schedule_entry | v | +-------------------+ irq_enable | | scheduling | <---------------+ | +-------------------+ | | | | | | irq_disable +--------+ irq_entry | v | | --------+ | +-------------------+ irq_entry | in_irq | | | | | -----------> | | <-------+ | | disable_to_switch | +--------+ | | | --+ | +-------------------+ | | | | | | sched_switch | | v | | +-------------------+ | | | switching | | irq_enable | +-------------------+ | | | | | | irq_enable | | v | | +-------------------+ | +-- | enable_to_exit | <-+ +-------------------+ ^ | irq_disable | | irq_entry +---------------+ irq_enable”…””}”hjçsbah}”(h]”h ]”h"]”h$]”h&]”jj uh1jh³hÊh´KˆhjÈh²hubeh}”(h]”Œ monitor-sts”ah ]”h"]”Œ monitor sts”ah$]”h&]”uh1hµhjÃh²hh³hÊh´K€ubeh}”(h]”Œspecifications”ah ]”h"]”Œspecifications”ah$]”h&]”uh1hµhh·h²hh³hÊh´K$ubh¶)”}”(hhh]”(h»)”}”(hŒ Monitor nrp”h]”hŒ Monitor nrp”…””}”(hjh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hºhjh²hh³hÊh´K²ubh×)”}”(hXÕThe need resched preempts (nrp) monitor ensures preemption requires ``need_resched``. Only kernel preemption is considered, since preemption while returning to userspace, for this monitor, is indistinguishable from ``sched_switch_yield`` (described in the sssw monitor). A kernel preemption is whenever ``__schedule`` is called with the preemption flag set to true (e.g. from preempt_enable or exiting from interrupts). This type of preemption occurs after the need for ``rescheduling`` has been set. This is not valid for the *lazy* variant of the flag, which causes only userspace preemption. A ``schedule_entry_preempt`` may involve a task switch or not, in the latter case, a task goes through the scheduler from a preemption context but it is picked as the next task to run. Since the scheduler runs, this clears the need to reschedule. The ``any_thread_running`` state does not imply the monitored task is not running as this monitor does not track the outcome of scheduling.”h]”(hŒDThe need resched preempts (nrp) monitor ensures preemption requires ”…””}”(hjh²hh³Nh´NubhŒliteral”“”)”}”(hŒ``need_resched``”h]”hŒ need_resched”…””}”(hj h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjubhŒƒ. Only kernel preemption is considered, since preemption while returning to userspace, for this monitor, is indistinguishable from ”…””}”(hjh²hh³Nh´Nubj)”}”(hŒ``sched_switch_yield``”h]”hŒsched_switch_yield”…””}”(hj2h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjubhŒB (described in the sssw monitor). A kernel preemption is whenever ”…””}”(hjh²hh³Nh´Nubj)”}”(hŒ``__schedule``”h]”hŒ __schedule”…””}”(hjDh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjubhŒ™ is called with the preemption flag set to true (e.g. from preempt_enable or exiting from interrupts). This type of preemption occurs after the need for ”…””}”(hjh²hh³Nh´Nubj)”}”(hŒ``rescheduling``”h]”hŒ rescheduling”…””}”(hjVh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjubhŒ) has been set. This is not valid for the ”…””}”(hjh²hh³Nh´Nubj‚)”}”(hŒ*lazy*”h]”hŒlazy”…””}”(hjhh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjubhŒ@ variant of the flag, which causes only userspace preemption. A ”…””}”(hjh²hh³Nh´Nubj)”}”(hŒ``schedule_entry_preempt``”h]”hŒschedule_entry_preempt”…””}”(hjzh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjubhŒß may involve a task switch or not, in the latter case, a task goes through the scheduler from a preemption context but it is picked as the next task to run. Since the scheduler runs, this clears the need to reschedule. The ”…””}”(hjh²hh³Nh´Nubj)”}”(hŒ``any_thread_running``”h]”hŒany_thread_running”…””}”(hjŒh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjubhŒq state does not imply the monitored task is not running as this monitor does not track the outcome of scheduling.”…””}”(hjh²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´K´hjh²hubh×)”}”(hŒÎIn theory, a preemption can only occur after the ``need_resched`` flag is set. In practice, however, it is possible to see a preemption where the flag is not set. This can happen in one specific condition::”h]”(hŒ1In theory, a preemption can only occur after the ”…””}”(hj¤h²hh³Nh´Nubj)”}”(hŒ``need_resched``”h]”hŒ need_resched”…””}”(hj¬h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj¤ubhŒŒ flag is set. In practice, however, it is possible to see a preemption where the flag is not set. This can happen in one specific condition:”…””}”(hj¤h²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´KÃhjh²hubj)”}”(hŒâneed_resched preempt_schedule() preempt_schedule_irq() __schedule() !need_resched __schedule()”h]”hŒâneed_resched preempt_schedule() preempt_schedule_irq() __schedule() !need_resched __schedule()”…””}”hjÄsbah}”(h]”h ]”h"]”h$]”h&]”jj uh1jh³hÊh´KÇhjh²hubh×)”}”(hXþIn the situation above, standard preemption starts (e.g. from preempt_enable when the flag is set), an interrupt occurs before scheduling and, on its exit path, it schedules, which clears the ``need_resched`` flag. When the preempted task runs again, the standard preemption started earlier resumes, although the flag is no longer set. The monitor considers this a ``nested_preemption``, this allows another preemption without re-setting the flag. This condition relaxes the monitor constraints and may catch false negatives (i.e. no real ``nested_preemptions``) but makes the monitor more robust and able to validate other scenarios. For simplicity, the monitor starts in ``preempt_irq``, although no interrupt occurred, as the situation above is hard to pinpoint::”h]”(hŒÀIn the situation above, standard preemption starts (e.g. from preempt_enable when the flag is set), an interrupt occurs before scheduling and, on its exit path, it schedules, which clears the ”…””}”(hjÒh²hh³Nh´Nubj)”}”(hŒ``need_resched``”h]”hŒ need_resched”…””}”(hjÚh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjÒubhŒ flag. When the preempted task runs again, the standard preemption started earlier resumes, although the flag is no longer set. The monitor considers this a ”…””}”(hjÒh²hh³Nh´Nubj)”}”(hŒ``nested_preemption``”h]”hŒnested_preemption”…””}”(hjìh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjÒubhŒ™, this allows another preemption without re-setting the flag. This condition relaxes the monitor constraints and may catch false negatives (i.e. no real ”…””}”(hjÒh²hh³Nh´Nubj)”}”(hŒ``nested_preemptions``”h]”hŒnested_preemptions”…””}”(hjþh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjÒubhŒp) but makes the monitor more robust and able to validate other scenarios. For simplicity, the monitor starts in ”…””}”(hjÒh²hh³Nh´Nubj)”}”(hŒ``preempt_irq``”h]”hŒ preempt_irq”…””}”(hjh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjÒubhŒM, although no interrupt occurred, as the situation above is hard to pinpoint:”…””}”(hjÒh²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´KÎhjh²hubj)”}”(hXö schedule_entry irq_entry #===========================================# +-------------------------- H H | H H +-------------------------> H any_thread_running H H H +-------------------------> H H | #===========================================# | schedule_entry | ^ | schedule_entry_preempt | sched_need_resched | schedule_entry | | schedule_entry_preempt | v | | +----------------------+ | | +--- | | | | sched_need_resched | | rescheduling | -+ | +--> | | | +----------------------+ | | irq_entry | v | +----------------------+ | | | ---+ | ---> | | | sched_need_resched | | preempt_irq | | irq_entry | | | <--+ | | | <--+ | +----------------------+ | | | schedule_entry | sched_need_resched | | schedule_entry_preempt | | v | | +-----------------------+ | +-------------------------- | nested_preempt | --+ +-----------------------+ ^ irq_entry | +-------------------+”h]”hXö schedule_entry irq_entry #===========================================# +-------------------------- H H | H H +-------------------------> H any_thread_running H H H +-------------------------> H H | #===========================================# | schedule_entry | ^ | schedule_entry_preempt | sched_need_resched | schedule_entry | | schedule_entry_preempt | v | | +----------------------+ | | +--- | | | | sched_need_resched | | rescheduling | -+ | +--> | | | +----------------------+ | | irq_entry | v | +----------------------+ | | | ---+ | ---> | | | sched_need_resched | | preempt_irq | | irq_entry | | | <--+ | | | <--+ | +----------------------+ | | | schedule_entry | sched_need_resched | | schedule_entry_preempt | | v | | +-----------------------+ | +-------------------------- | nested_preempt | --+ +-----------------------+ ^ irq_entry | +-------------------+”…””}”hj(sbah}”(h]”h ]”h"]”h$]”h&]”jj uh1jh³hÊh´KÚhjh²hubh×)”}”(hXDue to how the ``need_resched`` flag on the preemption count works on arm64, this monitor is unstable on that architecture, as it often records preemption when the flag is not set, even in presence of the workaround above. For the time being, the monitor is disabled by default on arm64.”h]”(hŒDue to how the ”…””}”(hj6h²hh³Nh´Nubj)”}”(hŒ``need_resched``”h]”hŒ need_resched”…””}”(hj>h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj6ubhX flag on the preemption count works on arm64, this monitor is unstable on that architecture, as it often records preemption when the flag is not set, even in presence of the workaround above. For the time being, the monitor is disabled by default on arm64.”…””}”(hj6h²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´Kýhjh²hubeh}”(h]”Œ monitor-nrp”ah ]”h"]”Œ monitor nrp”ah$]”h&]”uh1hµhh·h²hh³hÊh´K²ubh¶)”}”(hhh]”(h»)”}”(hŒ Monitor sssw”h]”hŒ Monitor sssw”…””}”(hjah²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hºhj^h²hh³hÊh´Mubh×)”}”(hŒ°The set state sleep and wakeup (sssw) monitor ensures ``set_state`` to sleepable leads to sleeping and sleeping tasks require wakeup. It includes the following types of switch:”h]”(hŒ6The set state sleep and wakeup (sssw) monitor ensures ”…””}”(hjoh²hh³Nh´Nubj)”}”(hŒ ``set_state``”h]”hŒ set_state”…””}”(hjwh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjoubhŒm to sleepable leads to sleeping and sleeping tasks require wakeup. It includes the following types of switch:”…””}”(hjoh²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´Mhj^h²hubhÌ)”}”(hhh]”(hÑ)”}”(hXT``switch_suspend``: a task puts itself to sleep, this can happen only after explicitly setting the task to ``sleepable``. After a task is suspended, it needs to be woken up (``waking`` state) before being switched in again. Setting the task's state to ``sleepable`` can be reverted before switching if it is woken up or set to ``runnable``.”h]”h×)”}”(hXT``switch_suspend``: a task puts itself to sleep, this can happen only after explicitly setting the task to ``sleepable``. After a task is suspended, it needs to be woken up (``waking`` state) before being switched in again. Setting the task's state to ``sleepable`` can be reverted before switching if it is woken up or set to ``runnable``.”h]”(j)”}”(hŒ``switch_suspend``”h]”hŒswitch_suspend”…””}”(hjšh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj–ubhŒY: a task puts itself to sleep, this can happen only after explicitly setting the task to ”…””}”(hj–h²hh³Nh´Nubj)”}”(hŒ ``sleepable``”h]”hŒ sleepable”…””}”(hj¬h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj–ubhŒ6. After a task is suspended, it needs to be woken up (”…””}”(hj–h²hh³Nh´Nubj)”}”(hŒ ``waking``”h]”hŒwaking”…””}”(hj¾h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj–ubhŒF state) before being switched in again. Setting the task’s state to ”…””}”(hj–h²hh³Nh´Nubj)”}”(hŒ ``sleepable``”h]”hŒ sleepable”…””}”(hjÐh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj–ubhŒ> can be reverted before switching if it is woken up or set to ”…””}”(hj–h²hh³Nh´Nubj)”}”(hŒ ``runnable``”h]”hŒrunnable”…””}”(hjâh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj–ubhŒ.”…””}”(hj–h²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´M hj’ubah}”(h]”h ]”h"]”h$]”h&]”uh1hÐhjh²hh³hÊh´NubhÑ)”}”(hXƒ``switch_blocking``: a special case of a ``switch_suspend`` where the task is waiting on a sleeping RT lock (``PREEMPT_RT`` only), it is common to see wakeup and set state events racing with each other and this leads the model to perceive this type of switch when the task is not set to sleepable. This is a limitation of the model in SMP system and workarounds may slow down the system.”h]”h×)”}”(hXƒ``switch_blocking``: a special case of a ``switch_suspend`` where the task is waiting on a sleeping RT lock (``PREEMPT_RT`` only), it is common to see wakeup and set state events racing with each other and this leads the model to perceive this type of switch when the task is not set to sleepable. This is a limitation of the model in SMP system and workarounds may slow down the system.”h]”(j)”}”(hŒ``switch_blocking``”h]”hŒswitch_blocking”…””}”(hjh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjubhŒ: a special case of a ”…””}”(hjh²hh³Nh´Nubj)”}”(hŒ``switch_suspend``”h]”hŒswitch_suspend”…””}”(hjh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjubhŒ2 where the task is waiting on a sleeping RT lock (”…””}”(hjh²hh³Nh´Nubj)”}”(hŒ``PREEMPT_RT``”h]”hŒ PREEMPT_RT”…””}”(hj,h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjubhX only), it is common to see wakeup and set state events racing with each other and this leads the model to perceive this type of switch when the task is not set to sleepable. This is a limitation of the model in SMP system and workarounds may slow down the system.”…””}”(hjh²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´Mhjubah}”(h]”h ]”h"]”h$]”h&]”uh1hÐhjh²hh³hÊh´NubhÑ)”}”(hŒq``switch_preempt``: a task switch as a result of kernel preemption (``schedule_entry_preempt`` in the nrp model).”h]”h×)”}”(hŒq``switch_preempt``: a task switch as a result of kernel preemption (``schedule_entry_preempt`` in the nrp model).”h]”(j)”}”(hŒ``switch_preempt``”h]”hŒswitch_preempt”…””}”(hjRh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjNubhŒ2: a task switch as a result of kernel preemption (”…””}”(hjNh²hh³Nh´Nubj)”}”(hŒ``schedule_entry_preempt``”h]”hŒschedule_entry_preempt”…””}”(hjdh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhjNubhŒ in the nrp model).”…””}”(hjNh²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´MhjJubah}”(h]”h ]”h"]”h$]”h&]”uh1hÐhjh²hh³hÊh´NubhÑ)”}”(hXê``switch_yield``: a task explicitly calls the scheduler or is preempted while returning to userspace. It can happen after a ``yield`` system call, from the idle task or if the ``need_resched`` flag is set. By definition, a task cannot yield while ``sleepable`` as that would be a suspension. A special case of a yield occurs when a task in ``TASK_INTERRUPTIBLE`` calls the scheduler while a signal is pending. The task doesn't go through the usual blocking/waking and is set back to runnable, the resulting switch (if there) looks like a yield to the ``signal_wakeup`` state and is followed by the signal delivery. From this state, the monitor expects a signal even if it sees a wakeup event, although not necessary, to rule out false negatives. ”h]”h×)”}”(hXé``switch_yield``: a task explicitly calls the scheduler or is preempted while returning to userspace. It can happen after a ``yield`` system call, from the idle task or if the ``need_resched`` flag is set. By definition, a task cannot yield while ``sleepable`` as that would be a suspension. A special case of a yield occurs when a task in ``TASK_INTERRUPTIBLE`` calls the scheduler while a signal is pending. The task doesn't go through the usual blocking/waking and is set back to runnable, the resulting switch (if there) looks like a yield to the ``signal_wakeup`` state and is followed by the signal delivery. From this state, the monitor expects a signal even if it sees a wakeup event, although not necessary, to rule out false negatives.”h]”(j)”}”(hŒ``switch_yield``”h]”hŒ switch_yield”…””}”(hjŠh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj†ubhŒl: a task explicitly calls the scheduler or is preempted while returning to userspace. It can happen after a ”…””}”(hj†h²hh³Nh´Nubj)”}”(hŒ ``yield``”h]”hŒyield”…””}”(hjœh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj†ubhŒ+ system call, from the idle task or if the ”…””}”(hj†h²hh³Nh´Nubj)”}”(hŒ``need_resched``”h]”hŒ need_resched”…””}”(hj®h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj†ubhŒ7 flag is set. By definition, a task cannot yield while ”…””}”(hj†h²hh³Nh´Nubj)”}”(hŒ ``sleepable``”h]”hŒ sleepable”…””}”(hjÀh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj†ubhŒP as that would be a suspension. A special case of a yield occurs when a task in ”…””}”(hj†h²hh³Nh´Nubj)”}”(hŒ``TASK_INTERRUPTIBLE``”h]”hŒTASK_INTERRUPTIBLE”…””}”(hjÒh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj†ubhŒ¿ calls the scheduler while a signal is pending. The task doesn’t go through the usual blocking/waking and is set back to runnable, the resulting switch (if there) looks like a yield to the ”…””}”(hj†h²hh³Nh´Nubj)”}”(hŒ``signal_wakeup``”h]”hŒ signal_wakeup”…””}”(hjäh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj†ubhŒ± state and is followed by the signal delivery. From this state, the monitor expects a signal even if it sees a wakeup event, although not necessary, to rule out false negatives.”…””}”(hj†h²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´Mhj‚ubah}”(h]”h ]”h"]”h$]”h&]”uh1hÐhjh²hh³hÊh´Nubeh}”(h]”h ]”h"]”h$]”h&]”jJŒ*”uh1hËh³hÊh´M hj^h²hubh×)”}”(hXœThis monitor doesn't include a running state, ``sleepable`` and ``runnable`` are only referring to the task's desired state, which could be scheduled out (e.g. due to preemption). However, it does include the event ``sched_switch_in`` to represent when a task is allowed to become running. This can be triggered also by preemption, but cannot occur after the task got to ``sleeping`` before a ``wakeup`` occurs::”h]”(hŒ0This monitor doesn’t include a running state, ”…””}”(hj h²hh³Nh´Nubj)”}”(hŒ ``sleepable``”h]”hŒ sleepable”…””}”(hjh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj ubhŒ and ”…””}”(hj h²hh³Nh´Nubj)”}”(hŒ ``runnable``”h]”hŒrunnable”…””}”(hj#h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj ubhŒ are only referring to the task’s desired state, which could be scheduled out (e.g. due to preemption). However, it does include the event ”…””}”(hj h²hh³Nh´Nubj)”}”(hŒ``sched_switch_in``”h]”hŒsched_switch_in”…””}”(hj5h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj ubhŒ‰ to represent when a task is allowed to become running. This can be triggered also by preemption, but cannot occur after the task got to ”…””}”(hj h²hh³Nh´Nubj)”}”(hŒ ``sleeping``”h]”hŒsleeping”…””}”(hjGh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj ubhŒ before a ”…””}”(hj h²hh³Nh´Nubj)”}”(hŒ ``wakeup``”h]”hŒwakeup”…””}”(hjYh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj ubhŒ occurs:”…””}”(hj h²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´M$hj^h²hubj)”}”(hXü +--------------------------------------------------------------------------+ | | | | | switch_suspend | | | switch_blocking | | v v | +----------+ #==========================# set_state_runnable | | | H H wakeup | | | H H switch_in | | | H H switch_yield | | sleeping | H H switch_preempt | | | H H signal_deliver | | | switch_ H H ------+ | | | _blocking H runnable H | | | | <----------- H H <-----+ | +----------+ H H | | wakeup H H | +---------------------> H H | H H | +---------> H H | | #==========================# | | | ^ | | | | set_state_runnable | | | | wakeup | | set_state_sleepable | +------------------------+ | v | | | +--------------------------+ set_state_sleepable | | | switch_in | | | switch_preempt signal_deliver | sleepable | signal_deliver | | | ------+ | | | | | | | <-----+ | +--------------------------+ | | ^ | switch_yield | set_state_sleepable | v | | +---------------+ | +---------- | signal_wakeup | -+ +---------------+ ^ | switch_in | | switch_preempt | | switch_yield +-----------+ wakeup”h]”hXü +--------------------------------------------------------------------------+ | | | | | switch_suspend | | | switch_blocking | | v v | +----------+ #==========================# set_state_runnable | | | H H wakeup | | | H H switch_in | | | H H switch_yield | | sleeping | H H switch_preempt | | | H H signal_deliver | | | switch_ H H ------+ | | | _blocking H runnable H | | | | <----------- H H <-----+ | +----------+ H H | | wakeup H H | +---------------------> H H | H H | +---------> H H | | #==========================# | | | ^ | | | | set_state_runnable | | | | wakeup | | set_state_sleepable | +------------------------+ | v | | | +--------------------------+ set_state_sleepable | | | switch_in | | | switch_preempt signal_deliver | sleepable | signal_deliver | | | ------+ | | | | | | | <-----+ | +--------------------------+ | | ^ | switch_yield | set_state_sleepable | v | | +---------------+ | +---------- | signal_wakeup | -+ +---------------+ ^ | switch_in | | switch_preempt | | switch_yield +-----------+ wakeup”…””}”hjqsbah}”(h]”h ]”h"]”h$]”h&]”jj uh1jh³hÊh´M+hj^h²hubeh}”(h]”Œ monitor-sssw”ah ]”h"]”Œ monitor sssw”ah$]”h&]”uh1hµhh·h²hh³hÊh´Mubh¶)”}”(hhh]”(h»)”}”(hŒ Monitor opid”h]”hŒ Monitor opid”…””}”(hjŠh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hºhj‡h²hh³hÊh´MYubh×)”}”(hX±The operations with preemption and irq disabled (opid) monitor ensures operations like ``wakeup`` and ``need_resched`` occur with interrupts and preemption disabled. ``need_resched`` can be set by some RCU internals functions, in which case it doesn't match a task wakeup and might occur with only interrupts disabled. The interrupt and preemption status are validated by the hybrid automaton constraints when processing the events::”h]”(hŒWThe operations with preemption and irq disabled (opid) monitor ensures operations like ”…””}”(hj˜h²hh³Nh´Nubj)”}”(hŒ ``wakeup``”h]”hŒwakeup”…””}”(hj h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj˜ubhŒ and ”…””}”(hj˜h²hh³Nh´Nubj)”}”(hŒ``need_resched``”h]”hŒ need_resched”…””}”(hj²h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj˜ubhŒ0 occur with interrupts and preemption disabled. ”…””}”(hj˜h²hh³Nh´Nubj)”}”(hŒ``need_resched``”h]”hŒ need_resched”…””}”(hjÄh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jhj˜ubhŒü can be set by some RCU internals functions, in which case it doesn’t match a task wakeup and might occur with only interrupts disabled. The interrupt and preemption status are validated by the hybrid automaton constraints when processing the events:”…””}”(hj˜h²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´M[hj‡h²hubj)”}”(hX; | | v #=========# sched_need_resched;irq_off == 1 H H sched_waking;irq_off == 1 && preempt_off == 1 H any H ------------------------------------------------+ H H | H H <-----------------------------------------------+ #=========#”h]”hX; | | v #=========# sched_need_resched;irq_off == 1 H H sched_waking;irq_off == 1 && preempt_off == 1 H any H ------------------------------------------------+ H H | H H <-----------------------------------------------+ #=========#”…””}”hjÜsbah}”(h]”h ]”h"]”h$]”h&]”jj uh1jh³hÊh´Mchj‡h²hubeh}”(h]”Œ monitor-opid”ah ]”h"]”Œ monitor opid”ah$]”h&]”uh1hµhh·h²hh³hÊh´MYubh¶)”}”(hhh]”(h»)”}”(hŒ References”h]”hŒ References”…””}”(hjõh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hºhjòh²hh³hÊh´Mnubh×)”}”(hŒ)[1] - https://bristot.me/linux-task-model”h]”(hŒ[1] - ”…””}”(hjh²hh³Nh´Nubj)”}”(hŒ#https://bristot.me/linux-task-model”h]”hŒ#https://bristot.me/linux-task-model”…””}”(hj h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”Œrefuri”j uh1jhjubeh}”(h]”h ]”h"]”h$]”h&]”uh1hÖh³hÊh´Mphjòh²hubeh}”(h]”Œ references”ah ]”h"]”Œ references”ah$]”h&]”uh1hµhh·h²hh³hÊh´Mnubeh}”(h]”Œscheduler-monitors”ah ]”h"]”Œscheduler monitors”ah$]”h&]”uh1hµhhh²hh³hÊh´Kubeh}”(h]”h ]”h"]”h$]”h&]”Œsource”hÊuh1hŒcurrent_source”NŒ current_line”NŒsettings”Œdocutils.frontend”ŒValues”“”)”}”(hºNŒ generator”NŒ datestamp”NŒ source_link”NŒ source_url”NŒ toc_backlinks”Œentry”Œfootnote_backlinks”KŒ sectnum_xform”KŒstrip_comments”NŒstrip_elements_with_classes”NŒ strip_classes”NŒ report_level”KŒ halt_level”KŒexit_status_level”KŒdebug”NŒwarning_stream”NŒ traceback”ˆŒinput_encoding”Œ utf-8-sig”Œinput_encoding_error_handler”Œstrict”Œoutput_encoding”Œutf-8”Œoutput_encoding_error_handler”jSŒerror_encoding”Œutf-8”Œerror_encoding_error_handler”Œbackslashreplace”Œ language_code”Œen”Œrecord_dependencies”NŒconfig”NŒ id_prefix”hŒauto_id_prefix”Œid”Œ dump_settings”NŒdump_internals”NŒdump_transforms”NŒdump_pseudo_xml”NŒexpose_internals”NŒstrict_visitor”NŒ_disable_config”NŒ_source”hÊŒ _destination”NŒ _config_files”]”Œ7/var/lib/git/docbuild/linux/Documentation/docutils.conf”aŒfile_insertion_enabled”ˆŒ raw_enabled”KŒline_length_limit”M'Œpep_references”NŒ pep_base_url”Œhttps://peps.python.org/”Œpep_file_url_template”Œpep-%04d”Œrfc_references”NŒ rfc_base_url”Œ&https://datatracker.ietf.org/doc/html/”Œ tab_width”KŒtrim_footnote_reference_space”‰Œsyntax_highlight”Œlong”Œ smart_quotes”ˆŒsmartquotes_locales”]”Œcharacter_level_inline_markup”‰Œdoctitle_xform”‰Œ docinfo_xform”KŒsectsubtitle_xform”‰Œ image_loading”Œlink”Œembed_stylesheet”‰Œcloak_email_addresses”ˆŒsection_self_link”‰Œenv”NubŒreporter”NŒindirect_targets”]”Œsubstitution_defs”}”Œsubstitution_names”}”Œrefnames”}”Œrefids”}”Œnameids”}”(j-j*jÀj½jjÿj&j#j[jXjjjÅjÂjúj÷j[jXj„jjïjìj%j"uŒ nametypes”}”(j-‰jÀ‰j‰j&‰j[‰j‰jʼnjú‰j[‰j„‰jï‰j%‰uh}”(j*h·j½jLjÿjÃj#jðjXj)jj^jÂj“j÷jÈjXjjj^jìj‡j"jòuŒ footnote_refs”}”Œ citation_refs”}”Œ autofootnotes”]”Œautofootnote_refs”]”Œsymbol_footnotes”]”Œsymbol_footnote_refs”]”Œ footnotes”]”Œ citations”]”Œautofootnote_start”KŒsymbol_footnote_start”KŒ id_counter”Œ collections”ŒCounter”“”}”…”R”Œparse_messages”]”Œtransform_messages”]”Œ transformer”NŒ include_log”]”Œ decoration”Nh²hub.