€•á>      Œsphinx.addnodes”Œdocument”“”)”}”(Œ	rawsource”Œ ”Œchildren”]”(Œtranslations”ŒLanguagesNode”“”)”}”(hhh]”(h Œpending_xref”“”)”}”(hhh]”Œdocutils.nodes”ŒText”“”ŒChinese (Simplified)”…””}”Œparent”hsbaŒ
attributes”}”(Œids”]”Œclasses”]”Œnames”]”Œdupnames”]”Œbackrefs”]”Œ	refdomain”Œstd”Œreftype”Œdoc”Œ	reftarget”Œ,/translations/zh_CN/locking/futex-requeue-pi”Œmodname”NŒ	classname”NŒrefexplicit”ˆuŒtagname”hhhubh)”}”(hhh]”hŒChinese (Traditional)”…””}”hh2sbah}”(h]”h ]”h"]”h$]”h&]”Œ	refdomain”h)Œreftype”h+Œ	reftarget”Œ,/translations/zh_TW/locking/futex-requeue-pi”Œmodname”NŒ	classname”NŒrefexplicit”ˆuh1hhhubh)”}”(hhh]”hŒItalian”…””}”hhFsbah}”(h]”h ]”h"]”h$]”h&]”Œ	refdomain”h)Œreftype”h+Œ	reftarget”Œ,/translations/it_IT/locking/futex-requeue-pi”Œmodname”NŒ	classname”NŒrefexplicit”ˆuh1hhhubh)”}”(hhh]”hŒJapanese”…””}”hhZsbah}”(h]”h ]”h"]”h$]”h&]”Œ	refdomain”h)Œreftype”h+Œ	reftarget”Œ,/translations/ja_JP/locking/futex-requeue-pi”Œmodname”NŒ	classname”NŒrefexplicit”ˆuh1hhhubh)”}”(hhh]”hŒKorean”…””}”hhnsbah}”(h]”h ]”h"]”h$]”h&]”Œ	refdomain”h)Œreftype”h+Œ	reftarget”Œ,/translations/ko_KR/locking/futex-requeue-pi”Œmodname”NŒ	classname”NŒrefexplicit”ˆuh1hhhubh)”}”(hhh]”hŒSpanish”…””}”hh‚sbah}”(h]”h ]”h"]”h$]”h&]”Œ	refdomain”h)Œreftype”h+Œ	reftarget”Œ,/translations/sp_SP/locking/futex-requeue-pi”Œmodname”NŒ	classname”NŒrefexplicit”ˆuh1hhhubeh}”(h]”h ]”h"]”h$]”h&]”Œcurrent_language”ŒEnglish”uh1h
hhŒ	_document”hŒsource”NŒline”NubhŒsection”“”)”}”(hhh]”(hŒtitle”“”)”}”(hŒFutex Requeue PI”h]”hŒFutex Requeue PI”…””}”(hh¨hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h¦hh£hžhhŸŒF/var/lib/git/docbuild/linux/Documentation/locking/futex-requeue-pi.rst”h KubhŒ	paragraph”“”)”}”(hX‘  Requeueing of tasks from a non-PI futex to a PI futex requires
special handling in order to ensure the underlying rt_mutex is never
left without an owner if it has waiters; doing so would break the PI
boosting logic [see rt-mutex-design.rst] For the purposes of
brevity, this action will be referred to as "requeue_pi" throughout
this document.  Priority inheritance is abbreviated throughout as
"PI".”h]”hX™  Requeueing of tasks from a non-PI futex to a PI futex requires
special handling in order to ensure the underlying rt_mutex is never
left without an owner if it has waiters; doing so would break the PI
boosting logic [see rt-mutex-design.rst] For the purposes of
brevity, this action will be referred to as â€œrequeue_piâ€ throughout
this document.  Priority inheritance is abbreviated throughout as
â€œPIâ€.”…””}”(hh¹hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h·hŸh¶h Khh£hžhubh¢)”}”(hhh]”(h§)”}”(hŒ
Motivation”h]”hŒ
Motivation”…””}”(hhÊhžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h¦hhÇhžhhŸh¶h Kubh¸)”}”(hX”  Without requeue_pi, the glibc implementation of
pthread_cond_broadcast() must resort to waking all the tasks waiting
on a pthread_condvar and letting them try to sort out which task
gets to run first in classic thundering-herd formation.  An ideal
implementation would wake the highest-priority waiter, and leave the
rest to the natural wakeup inherent in unlocking the mutex
associated with the condvar.”h]”hX”  Without requeue_pi, the glibc implementation of
pthread_cond_broadcast() must resort to waking all the tasks waiting
on a pthread_condvar and letting them try to sort out which task
gets to run first in classic thundering-herd formation.  An ideal
implementation would wake the highest-priority waiter, and leave the
rest to the natural wakeup inherent in unlocking the mutex
associated with the condvar.”…””}”(hhØhžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h·hŸh¶h KhhÇhžhubh¸)”}”(hŒ%Consider the simplified glibc calls::”h]”hŒ$Consider the simplified glibc calls:”…””}”(hhæhžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h·hŸh¶h KhhÇhžhubhŒliteral_block”“”)”}”(hXé  /* caller must lock mutex */
pthread_cond_wait(cond, mutex)
{
        lock(cond->__data.__lock);
        unlock(mutex);
        do {
        unlock(cond->__data.__lock);
        futex_wait(cond->__data.__futex);
        lock(cond->__data.__lock);
        } while(...)
        unlock(cond->__data.__lock);
        lock(mutex);
}

pthread_cond_broadcast(cond)
{
        lock(cond->__data.__lock);
        unlock(cond->__data.__lock);
        futex_requeue(cond->data.__futex, cond->mutex);
}”h]”hXé  /* caller must lock mutex */
pthread_cond_wait(cond, mutex)
{
        lock(cond->__data.__lock);
        unlock(mutex);
        do {
        unlock(cond->__data.__lock);
        futex_wait(cond->__data.__futex);
        lock(cond->__data.__lock);
        } while(...)
        unlock(cond->__data.__lock);
        lock(mutex);
}

pthread_cond_broadcast(cond)
{
        lock(cond->__data.__lock);
        unlock(cond->__data.__lock);
        futex_requeue(cond->data.__futex, cond->mutex);
}”…””}”hhösbah}”(h]”h ]”h"]”h$]”h&]”Œ	xml:space”Œpreserve”uh1hôhŸh¶h KhhÇhžhubh¸)”}”(hX0  Once pthread_cond_broadcast() requeues the tasks, the cond->mutex
has waiters. Note that pthread_cond_wait() attempts to lock the
mutex only after it has returned to user space.  This will leave the
underlying rt_mutex with waiters, and no owner, breaking the
previously mentioned PI-boosting algorithms.”h]”hX0  Once pthread_cond_broadcast() requeues the tasks, the cond->mutex
has waiters. Note that pthread_cond_wait() attempts to lock the
mutex only after it has returned to user space.  This will leave the
underlying rt_mutex with waiters, and no owner, breaking the
previously mentioned PI-boosting algorithms.”…””}”(hj  hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h·hŸh¶h K/hhÇhžhubh¸)”}”(hX-  In order to support PI-aware pthread_condvar's, the kernel needs to
be able to requeue tasks to PI futexes.  This support implies that
upon a successful futex_wait system call, the caller would return to
user space already holding the PI futex.  The glibc implementation
would be modified as follows::”h]”hX.  In order to support PI-aware pthread_condvarâ€™s, the kernel needs to
be able to requeue tasks to PI futexes.  This support implies that
upon a successful futex_wait system call, the caller would return to
user space already holding the PI futex.  The glibc implementation
would be modified as follows:”…””}”(hj  hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h·hŸh¶h K5hhÇhžhubhõ)”}”(hX  /* caller must lock mutex */
pthread_cond_wait_pi(cond, mutex)
{
        lock(cond->__data.__lock);
        unlock(mutex);
        do {
        unlock(cond->__data.__lock);
        futex_wait_requeue_pi(cond->__data.__futex);
        lock(cond->__data.__lock);
        } while(...)
        unlock(cond->__data.__lock);
        /* the kernel acquired the mutex for us */
}

pthread_cond_broadcast_pi(cond)
{
        lock(cond->__data.__lock);
        unlock(cond->__data.__lock);
        futex_requeue_pi(cond->data.__futex, cond->mutex);
}”h]”hX  /* caller must lock mutex */
pthread_cond_wait_pi(cond, mutex)
{
        lock(cond->__data.__lock);
        unlock(mutex);
        do {
        unlock(cond->__data.__lock);
        futex_wait_requeue_pi(cond->__data.__futex);
        lock(cond->__data.__lock);
        } while(...)
        unlock(cond->__data.__lock);
        /* the kernel acquired the mutex for us */
}

pthread_cond_broadcast_pi(cond)
{
        lock(cond->__data.__lock);
        unlock(cond->__data.__lock);
        futex_requeue_pi(cond->data.__futex, cond->mutex);
}”…””}”hj"  sbah}”(h]”h ]”h"]”h$]”h&]”j  j  uh1hôhŸh¶h K<hhÇhžhubh¸)”}”(hŒõThe actual glibc implementation will likely test for PI and make the
necessary changes inside the existing calls rather than creating new
calls for the PI cases.  Similar changes are needed for
pthread_cond_timedwait() and pthread_cond_signal().”h]”hŒõThe actual glibc implementation will likely test for PI and make the
necessary changes inside the existing calls rather than creating new
calls for the PI cases.  Similar changes are needed for
pthread_cond_timedwait() and pthread_cond_signal().”…””}”(hj0  hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h·hŸh¶h KQhhÇhžhubeh}”(h]”Œ
motivation”ah ]”h"]”Œ
motivation”ah$]”h&]”uh1h¡hh£hžhhŸh¶h Kubh¢)”}”(hhh]”(h§)”}”(hŒImplementation”h]”hŒImplementation”…””}”(hjI  hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h¦hjF  hžhhŸh¶h KWubh¸)”}”(hXË  In order to ensure the rt_mutex has an owner if it has waiters, it
is necessary for both the requeue code, as well as the waiting code,
to be able to acquire the rt_mutex before returning to user space.
The requeue code cannot simply wake the waiter and leave it to
acquire the rt_mutex as it would open a race window between the
requeue call returning to user space and the waiter waking and
starting to run.  This is especially true in the uncontended case.”h]”hXË  In order to ensure the rt_mutex has an owner if it has waiters, it
is necessary for both the requeue code, as well as the waiting code,
to be able to acquire the rt_mutex before returning to user space.
The requeue code cannot simply wake the waiter and leave it to
acquire the rt_mutex as it would open a race window between the
requeue call returning to user space and the waiter waking and
starting to run.  This is especially true in the uncontended case.”…””}”(hjW  hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h·hŸh¶h KYhjF  hžhubh¸)”}”(hXx  The solution involves two new rt_mutex helper routines,
rt_mutex_start_proxy_lock() and rt_mutex_finish_proxy_lock(), which
allow the requeue code to acquire an uncontended rt_mutex on behalf
of the waiter and to enqueue the waiter on a contended rt_mutex.
Two new system calls provide the kernel<->user interface to
requeue_pi: FUTEX_WAIT_REQUEUE_PI and FUTEX_CMP_REQUEUE_PI.”h]”hXx  The solution involves two new rt_mutex helper routines,
rt_mutex_start_proxy_lock() and rt_mutex_finish_proxy_lock(), which
allow the requeue code to acquire an uncontended rt_mutex on behalf
of the waiter and to enqueue the waiter on a contended rt_mutex.
Two new system calls provide the kernel<->user interface to
requeue_pi: FUTEX_WAIT_REQUEUE_PI and FUTEX_CMP_REQUEUE_PI.”…””}”(hje  hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h·hŸh¶h KahjF  hžhubh¸)”}”(hXV  FUTEX_WAIT_REQUEUE_PI is called by the waiter (pthread_cond_wait()
and pthread_cond_timedwait()) to block on the initial futex and wait
to be requeued to a PI-aware futex.  The implementation is the
result of a high-speed collision between futex_wait() and
futex_lock_pi(), with some extra logic to check for the additional
wake-up scenarios.”h]”hXV  FUTEX_WAIT_REQUEUE_PI is called by the waiter (pthread_cond_wait()
and pthread_cond_timedwait()) to block on the initial futex and wait
to be requeued to a PI-aware futex.  The implementation is the
result of a high-speed collision between futex_wait() and
futex_lock_pi(), with some extra logic to check for the additional
wake-up scenarios.”…””}”(hjs  hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h·hŸh¶h KhhjF  hžhubh¸)”}”(hXá  FUTEX_CMP_REQUEUE_PI is called by the waker
(pthread_cond_broadcast() and pthread_cond_signal()) to requeue and
possibly wake the waiting tasks. Internally, this system call is
still handled by futex_requeue (by passing requeue_pi=1).  Before
requeueing, futex_requeue() attempts to acquire the requeue target
PI futex on behalf of the top waiter.  If it can, this waiter is
woken.  futex_requeue() then proceeds to requeue the remaining
nr_wake+nr_requeue tasks to the PI futex, calling
rt_mutex_start_proxy_lock() prior to each requeue to prepare the
task as a waiter on the underlying rt_mutex.  It is possible that
the lock can be acquired at this stage as well, if so, the next
waiter is woken to finish the acquisition of the lock.”h]”hXá  FUTEX_CMP_REQUEUE_PI is called by the waker
(pthread_cond_broadcast() and pthread_cond_signal()) to requeue and
possibly wake the waiting tasks. Internally, this system call is
still handled by futex_requeue (by passing requeue_pi=1).  Before
requeueing, futex_requeue() attempts to acquire the requeue target
PI futex on behalf of the top waiter.  If it can, this waiter is
woken.  futex_requeue() then proceeds to requeue the remaining
nr_wake+nr_requeue tasks to the PI futex, calling
rt_mutex_start_proxy_lock() prior to each requeue to prepare the
task as a waiter on the underlying rt_mutex.  It is possible that
the lock can be acquired at this stage as well, if so, the next
waiter is woken to finish the acquisition of the lock.”…””}”(hj  hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h·hŸh¶h KohjF  hžhubh¸)”}”(hX)  FUTEX_CMP_REQUEUE_PI accepts nr_wake and nr_requeue as arguments, but
their sum is all that really matters.  futex_requeue() will wake or
requeue up to nr_wake + nr_requeue tasks.  It will wake only as many
tasks as it can acquire the lock for, which in the majority of cases
should be 0 as good programming practice dictates that the caller of
either pthread_cond_broadcast() or pthread_cond_signal() acquire the
mutex prior to making the call. FUTEX_CMP_REQUEUE_PI requires that
nr_wake=1.  nr_requeue should be INT_MAX for broadcast and 0 for
signal.”h]”hX)  FUTEX_CMP_REQUEUE_PI accepts nr_wake and nr_requeue as arguments, but
their sum is all that really matters.  futex_requeue() will wake or
requeue up to nr_wake + nr_requeue tasks.  It will wake only as many
tasks as it can acquire the lock for, which in the majority of cases
should be 0 as good programming practice dictates that the caller of
either pthread_cond_broadcast() or pthread_cond_signal() acquire the
mutex prior to making the call. FUTEX_CMP_REQUEUE_PI requires that
nr_wake=1.  nr_requeue should be INT_MAX for broadcast and 0 for
signal.”…””}”(hj  hžhhŸNh Nubah}”(h]”h ]”h"]”h$]”h&]”uh1h·hŸh¶h K|hjF  hžhubeh}”(h]”Œimplementation”ah ]”h"]”Œimplementation”ah$]”h&]”uh1h¡hh£hžhhŸh¶h KWubeh}”(h]”Œfutex-requeue-pi”ah ]”h"]”Œfutex requeue pi”ah$]”h&]”uh1h¡hhhžhhŸh¶h Kubeh}”(h]”h ]”h"]”h$]”h&]”Œsource”h¶uh1hŒcurrent_source”NŒcurrent_line”NŒsettings”Œdocutils.frontend”ŒValues”“”)”}”(h¦NŒ	generator”NŒ	datestamp”NŒsource_link”NŒ
source_url”NŒtoc_backlinks”Œentry”Œfootnote_backlinks”KŒsectnum_xform”KŒstrip_comments”NŒstrip_elements_with_classes”NŒstrip_classes”NŒreport_level”KŒ
halt_level”KŒexit_status_level”KŒdebug”NŒwarning_stream”NŒ	traceback”ˆŒinput_encoding”Œ	utf-8-sig”Œinput_encoding_error_handler”Œstrict”Œoutput_encoding”Œutf-8”Œoutput_encoding_error_handler”jÐ  Œerror_encoding”Œutf-8”Œerror_encoding_error_handler”Œbackslashreplace”Œlanguage_code”Œen”Œrecord_dependencies”NŒconfig”NŒ	id_prefix”hŒauto_id_prefix”Œid”Œdump_settings”NŒdump_internals”NŒdump_transforms”NŒdump_pseudo_xml”NŒexpose_internals”NŒstrict_visitor”NŒ_disable_config”NŒ_source”h¶Œ_destination”NŒ_config_files”]”Œ7/var/lib/git/docbuild/linux/Documentation/docutils.conf”aŒfile_insertion_enabled”ˆŒraw_enabled”KŒline_length_limit”M'Œpep_references”NŒpep_base_url”Œhttps://peps.python.org/”Œpep_file_url_template”Œpep-%04d”Œrfc_references”NŒrfc_base_url”Œ&https://datatracker.ietf.org/doc/html/”Œ	tab_width”KŒtrim_footnote_reference_space”‰Œsyntax_highlight”Œlong”Œsmart_quotes”ˆŒsmartquotes_locales”]”Œcharacter_level_inline_markup”‰Œdoctitle_xform”‰Œdocinfo_xform”KŒsectsubtitle_xform”‰Œimage_loading”Œlink”Œembed_stylesheet”‰Œcloak_email_addresses”ˆŒsection_self_link”‰Œenv”NubŒreporter”NŒindirect_targets”]”Œsubstitution_defs”}”Œsubstitution_names”}”Œrefnames”}”Œrefids”}”Œnameids”}”(jª  j§  jC  j@  j¢  jŸ  uŒ	nametypes”}”(jª  ‰jC  ‰j¢  ‰uh}”(j§  h£j@  hÇjŸ  jF  uŒfootnote_refs”}”Œcitation_refs”}”Œautofootnotes”]”Œautofootnote_refs”]”Œsymbol_footnotes”]”Œsymbol_footnote_refs”]”Œ	footnotes”]”Œ	citations”]”Œautofootnote_start”KŒsymbol_footnote_start”K Œ
id_counter”Œcollections”ŒCounter”“”}”…”R”Œparse_messages”]”Œtransform_messages”]”Œtransformer”NŒinclude_log”]”Œ
decoration”Nhžhub.