Donor Migration for Proxy Execution (v20)
Subsystems (4)
v20 cover Donor Migration for Proxy Execution (v20)
Hey All,
As Peter just queued the Single-RQ portion of the Proxy Execution series, I wanted to start getting some initial review feedback for the next chunk of the series: Donor Migration
v20 is not very different from v19 of the whole series that I’ve shared previously, I’ve only rebased it upon Peter’s sched/core branch, dropping the queued changes, resolving trivial conflicts and making some small tweaks to drop CONFIG_SMP conditionals that have been removed in -tip tree, along with a few minor cleanups.
I’m trying to submit this larger work in smallish digestible pieces, so in this portion of the series, I’m only submitting for review and consideration the logic that allows us to do donor(blocked waiter) migration, allowing us to proxy-execute lock owners that might be on other cpu runqueues. This requires some additional changes to locking and extra state tracking to ensure we don’t accidentally run a migrated donor on a cpu it isn’t affined to, as well as some extra handling to deal with balance callback state that needs to be reset when we decide to pick a different task after doing donor migration.
I’d love to get some initial feedback on any place where these patches are confusing, or could use additional clarifications.
Also you can find the full proxy-exec series here:
https://github.com/johnstultz-work/linux-dev/commits/proxy-exec-v20-peterz-sched-core/
https://github.com/johnstultz-work/linux-dev.git proxy-exec-v20-peterz-sched-core
Issues still to address with the full series:
* There’s a new quirk from recent changes for dl_server that is causing the ksched_football test in the full series to hang at boot. I’ve bisected and reverted the change for now, but I need to better understand what’s going wrong.
* I spent some more time thinking about Peter’s suggestion to avoid using the blocked_on_state == BO_WAKING check to protect against running proxy-migrated tasks on cpus out of their affinity mask. His suggestion to just dequeue the task prior to the wakeup in the unlock-wakeup path is more elegant, but this would be insufficient to protect from other wakeup paths that don’t dequeue. I’m still thinking if there is a clean way around this, but I’ve not yet found it.
* Need to sort out what is needed for sched_ext to be ok with proxy-execution enabled.
* K Prateek Nayak did some testing about a bit over a year ago with an earlier version of the series and saw ~3-5% regressions in some cases. Need to re-evaluate this with the proxy-migration avoidance optimization Suleiman suggested now implemented.
* The chain migration functionality needs further iterations and better validation to ensure it truly maintains the RT/DL load balancing invariants (despite this being broken in vanilla upstream with RT_PUSH_IPI currently)
I’d really appreciate any feedback or review thoughts on the full series as well. I’m trying to keep the chunks small, reviewable and iteratively testable, but if you have any suggestions on how to improve the series, I’m all ears.
Credit/Disclaimer:
--------------------
As always, this Proxy Execution series has a long history with lots of developers that deserve credit:
First described in a paper[1] by Watkins, Straub, Niehaus, then from patches from Peter Zijlstra, extended with lots of work by Juri Lelli, Valentin Schneider, and Connor O'Brien. (and thank you to Steven Rostedt for providing additional details here!)
So again, many thanks to those above, as all the credit for this series really is due to them - while the mistakes are likely mine.
Thanks so much!
-john
[1] https://static.lwn.net/images/conf/rtlws11/papers/proc/p38.pdf
John Stultz (5):
locking: Add task::blocked_lock to serialize blocked_on state kernel/locking: Add blocked_on_state to provide necessary tri-state
for return migration
sched: Add logic to zap balance callbacks if we pick again
sched: Handle blocked-waiter migration (and return migration)
sched: Migrate whole chain in proxy_migrate_task()
Peter Zijlstra (1):
sched: Add blocked_donor link to task for smarter mutex handoffs
include/linux/sched.h | 107 ++++++++----- init/init_task.c | 4 + kernel/fork.c | 4 + kernel/locking/mutex.c | 80 +++++++-- kernel/locking/ww_mutex.h | 17 +- kernel/sched/core.c | 329 +++++++++++++++++++++++++++++++++++--- kernel/sched/fair.c | 3 +- kernel/sched/sched.h | 2 +- 8 files changed, 459 insertions(+), 87 deletions(-)
Signature · 1 line
2.50.0.727.gbf7dc18ff4-goog
RFC PATCH v20 1/6 locking: Add task::blocked_lock to serialize blocked_on state
So far, we have been able to utilize the mutex::wait_lock for serializing the blocked_on state, but when we move to proxying across runqueues, we will need to add more state and a way to serialize changes to this state in contexts where we don't hold the mutex::wait_lock.
So introduce the task::blocked_lock, which nests under the mutex::wait_lock in the locking order, and rework the locking to use it.
---
v15:
* Split back out into later in the series v16:
* Fixups to mark tasks unblocked before sleeping in mutex_optimistic_spin()
* Rework to use guard() as suggested by Peter v19:
* Rework logic for PREEMPT_RT issues reported by K Prateek Nayak
--- include/linux/sched.h | 25 ++++++++++++++++++------- init/init_task.c | 1 + kernel/fork.c | 1 + kernel/locking/mutex.c | 34 ++++++++++++++++++++++------------ kernel/locking/ww_mutex.h | 6 ++++-- kernel/sched/core.c | 4 +++- 6 files changed, 49 insertions(+), 22 deletions(-)
include/linux/sched.h +18 -7
@@ -1232,6 +1232,7 @@ struct task_struct {#endif struct mutex *blocked_on;/* lock we're blocked on */ +raw_spinlock_t blocked_lock;#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER /*
@@ -2145,8 +2146,8 @@ static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m)WARN_ON_ONCE (!m);/* The task should only be setting itself as blocked */ WARN_ON_ONCE (p != current); -/* Currently we serialize blocked_on under the mutex::wait_lock */ -lockdep_assert_held_once (&m->wait_lock); +/* Currently we serialize blocked_on under the task::blocked_lock */ +lockdep_assert_held_once (&p->blocked_lock);/* * Check ensure we don't overwrite existing mutex value * with a different mutex. Note, setting it to the same
@@ -2158,15 +2159,14 @@ static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m)static inline void set_task_blocked_on (struct task_struct *p,struct mutex *m) { -guard (raw_spinlock_irqsave)(&m->wait_lock); +guard (raw_spinlock_irqsave)(&p->blocked_lock);__set_task_blocked_on (p, m); }static inline void __clear_task_blocked_on (struct task_struct *p,struct mutex *m) { -WARN_ON_ONCE (!m); -/* Currently we serialize blocked_on under the mutex::wait_lock */ -lockdep_assert_held_once (&m->wait_lock); +/* Currently we serialize blocked_on under the task::blocked_lock */ +lockdep_assert_held_once (&p->blocked_lock);/* * There may be cases where we re-clear already cleared * blocked_on relationships, but make sure we are not
@@ -2178,8 +2178,15 @@ static inline void __clear_task_blocked_on(struct task_struct *p, struct mutex *static inline void clear_task_blocked_on (struct task_struct *p,struct mutex *m) { -guard (raw_spinlock_irqsave)(&m->wait_lock); +guard (raw_spinlock_irqsave)(&p->blocked_lock); +__clear_task_blocked_on (p, m); +} + +static inline void clear_task_blocked_on_nested (struct task_struct *p,struct mutex *m) +{ +raw_spin_lock_nested (&p->blocked_lock,SINGLE_DEPTH_NESTING );__clear_task_blocked_on (p, m); +raw_spin_unlock (&p->blocked_lock); }#else static inline void __clear_task_blocked_on (struct task_struct *p,struct rt_mutex *m)
@@ -2189,6 +2196,10 @@ static inline void __clear_task_blocked_on(struct task_struct *p, struct rt_mutestatic inline void clear_task_blocked_on (struct task_struct *p,struct rt_mutex *m) { } + +static inline void clear_task_blocked_on_nested (struct task_struct *p,struct rt_mutex *m) +{ +}#endif /* !CONFIG_PREEMPT_RT */ static __always_inline bool need_resched(void)
init/init_task.c +1 -0
@@ -140,6 +140,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = { .journal_info = NULL,INIT_CPU_TIMERS (init_task) .pi_lock =__RAW_SPIN_LOCK_UNLOCKED (init_task.pi_lock), + .blocked_lock = __RAW_SPIN_LOCK_UNLOCKED(init_task.blocked_lock), .timer_slack_ns = 50000, /* 50 usec default slack */ .thread_pid = &init_struct_pid, .thread_node = LIST_HEAD_INIT(init_signals.thread_head),
kernel/fork.c +1 -0
@@ -2025,6 +2025,7 @@ __latent_entropy struct task_struct *copy_process(ftrace_graph_init_task (p);rt_mutex_init_task (p); +raw_spin_lock_init (&p->blocked_lock);lockdep_assert_irqs_enabled ();#ifdef CONFIG_PROVE_LOCKING
kernel/locking/mutex.c +22 -12
@@ -614,6 +614,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas }raw_spin_lock_irqsave (&lock->wait_lock, flags); +raw_spin_lock (¤t->blocked_lock);/* * After waiting to acquire the wait_lock, try again. */
@@ -657,7 +658,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas* the handoff. */ if (__mutex_trylock (lock)) - goto acquired; +break ;/* * Check for signals and kill conditions while holding
@@ -675,18 +676,21 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas goto err; } +raw_spin_unlock (¤t->blocked_lock);raw_spin_unlock_irqrestore_wake (&lock->wait_lock, flags, &wake_q);schedule_preempt_disabled (); first =__mutex_waiter_is_first (lock, &waiter); +raw_spin_lock_irqsave (&lock->wait_lock, flags); +raw_spin_lock (¤t->blocked_lock);/* * As we likely have been woken up by task * that has cleared our blocked_on state, re-set * it to the lock we are trying to acquire. */ -set_task_blocked_on (current, lock); +__set_task_blocked_on (current, lock);set_current_state (state);/* * Here we order against unlock; we must either see it change
@@ -697,23 +701,27 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclasbreak ;if (first) { -trace_contention_begin (lock,LCB_F_MUTEX |LCB_F_SPIN ); +bool opt_acquired; +/* * mutex_optimistic_spin() can call schedule(), so -* clear blocked on so we don't become unselectable +* we need to release these locks before calling it, +* and clear blocked on so we don't become unselectable * to run. */ -clear_task_blocked_on (current, lock); -if (mutex_optimistic_spin (lock, ww_ctx, &waiter)) +__clear_task_blocked_on (current, lock); +raw_spin_unlock (¤t->blocked_lock); +raw_spin_unlock_irqrestore (&lock->wait_lock, flags); +trace_contention_begin (lock,LCB_F_MUTEX |LCB_F_SPIN ); + opt_acquired =mutex_optimistic_spin (lock, ww_ctx, &waiter); +raw_spin_lock_irqsave (&lock->wait_lock, flags); +raw_spin_lock (¤t->blocked_lock); +__set_task_blocked_on (current, lock); +if (opt_acquired)break ; -set_task_blocked_on (current, lock);trace_contention_begin (lock,LCB_F_MUTEX ); } - -raw_spin_lock_irqsave (&lock->wait_lock, flags); } -raw_spin_lock_irqsave (&lock->wait_lock, flags); -acquired:__clear_task_blocked_on (current, lock);__set_current_state (TASK_RUNNING );
@@ -739,6 +747,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclasif (ww_ctx)ww_mutex_lock_acquired (ww, ww_ctx); +raw_spin_unlock (¤t->blocked_lock);raw_spin_unlock_irqrestore_wake (&lock->wait_lock, flags, &wake_q);preempt_enable ();return 0 ;
@@ -750,6 +759,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas err_early_kill:WARN_ON (__get_task_blocked_on (current));trace_contention_end (lock, ret); +raw_spin_unlock (¤t->blocked_lock);raw_spin_unlock_irqrestore_wake (&lock->wait_lock, flags, &wake_q);debug_mutex_free_waiter (&waiter);mutex_release (&lock->dep_map, ip);
@@ -959,7 +969,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne next = waiter->task;debug_mutex_wake_waiter (lock, waiter); -__clear_task_blocked_on (next, lock); +clear_task_blocked_on (next, lock);wake_q_add (&wake_q, next); }
kernel/locking/ww_mutex.h +4 -2
@@ -289,7 +289,8 @@ __ww_mutex_die(struct MUTEX *lock, struct MUTEX_WAITER *waiter,* blocked_on pointer. Otherwise we can see circular * blocked_on relationships that can't resolve. */ -__clear_task_blocked_on (waiter->task, lock); +/* nested as we should hold current->blocked_lock already */ +clear_task_blocked_on_nested (waiter->task, lock);wake_q_add (wake_q, waiter->task); }
@@ -343,7 +344,8 @@ static bool __ww_mutex_wound(struct MUTEX *lock,* blocked_on pointer. Otherwise we can see circular * blocked_on relationships that can't resolve. */ -__clear_task_blocked_on (owner, lock); +/* nested as we should hold current->blocked_lock already */ +clear_task_blocked_on_nested (owner, lock);wake_q_add (wake_q, owner); }return true;
kernel/sched/core.c +3 -1
@@ -6633,6 +6633,7 @@ static struct task_struct *proxy_deactivate(struct rq *rq, struct task_struct *d* p->pi_lock * rq->lock * mutex->wait_lock +* p->blocked_lock * * Returns the task that is going to be used as execution context (the one * that is actually going to be run on cpu_of(rq)).
@@ -6656,8 +6657,9 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)* and ensure @owner sticks around. */ guard (raw_spinlock)(&mutex->wait_lock); +guard (raw_spinlock)(&p->blocked_lock); -/* Check again that p is blocked with wait_lock held */ +/* Check again that p is blocked with blocked_lock held */ if (mutex !=__get_task_blocked_on (p)) {/* * Something changed in the blocked_on chain and
Signature · 1 line
2.50.0.727.gbf7dc18ff4-goog
RFC PATCH v20 2/6 kernel/locking: Add blocked_on_state to provide necessary tri-state for return migration
In reply to John StultzAs we add functionality to proxy execution, we may migrate a donor task to a runqueue where it can't run due to cpu affinity. Thus, we must be careful to ensure we return-migrate the task back to a cpu in its cpumask when it becomes unblocked.
Thus we need more then just a binary concept of the task being blocked on a mutex or not.
So add a blocked_on_state value to the task, that allows the task to move through BO_RUNNING -> BO_BLOCKED -> BO_WAKING and back to BO_RUNNING. This provides a guard state in BO_WAKING so we can know the task is no longer blocked but we don't want to run it until we have potentially done return migration, back to a usable cpu.
---
v15:
* Split blocked_on_state into its own patch later in the series, as the tri-state isn't necessary until we deal with proxy/return migrations
v16:
* Handle case where task in the chain is being set as BO_WAKING by another cpu (usually via ww_mutex die code). Make sure we release the rq lock so the wakeup can complete.
* Rework to use guard() in find_proxy_task() as suggested by Peter
v18:
* Add initialization of blocked_on_state for init_task v19:
* PREEMPT_RT build fixups and rework suggested by
K Prateek Nayak
v20:
* Simplify one of the blocked_on_state changes to avoid extra PREMEPT_RT conditionals
--- include/linux/sched.h | 100 ++++++++++++++++++++++---------------- init/init_task.c | 1 + kernel/fork.c | 1 + kernel/locking/mutex.c | 15 +++--- kernel/locking/ww_mutex.h | 17 +++---- kernel/sched/core.c | 26 +++++++++- kernel/sched/sched.h | 2 +- 7 files changed, 100 insertions(+), 62 deletions(-)
include/linux/sched.h +57 -43
@@ -812,6 +812,12 @@ struct kmap_ctrl {#endif }; +enum blocked_on_state { +BO_RUNNABLE , +BO_BLOCKED , +BO_WAKING , +}; +struct task_struct {#ifdef CONFIG_THREAD_INFO_IN_TASK /*
@@ -1231,6 +1237,7 @@ struct task_struct {struct rt_mutex_waiter *pi_blocked_on;#endif +enum blocked_on_state blocked_on_state;struct mutex *blocked_on;/* lock we're blocked on */ raw_spinlock_t blocked_lock;
@@ -2131,76 +2138,83 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock);__cond_resched_rwlock_write (lock); \ }) -#ifndef CONFIG_PREEMPT_RT -static inline struct mutex *__get_task_blocked_on (struct task_struct *p) +static inline void __force_blocked_on_runnable (struct task_struct *p) { -struct mutex *m = p->blocked_on; +lockdep_assert_held (&p->blocked_lock); + p->blocked_on_state =BO_RUNNABLE ; +} -if (m) -lockdep_assert_held_once (&m->wait_lock); -return m; +static inline void force_blocked_on_runnable (struct task_struct *p) +{ +guard (raw_spinlock_irqsave)(&p->blocked_lock); +__force_blocked_on_runnable (p); } -static inline void __set_task_blocked_on (struct task_struct *p,struct mutex *m) +static inline void __set_blocked_on_runnable (struct task_struct *p) { -WARN_ON_ONCE (!m); -/* The task should only be setting itself as blocked */ -WARN_ON_ONCE (p != current); -/* Currently we serialize blocked_on under the task::blocked_lock */ -lockdep_assert_held_once (&p->blocked_lock); -/* -* Check ensure we don't overwrite existing mutex value -* with a different mutex. Note, setting it to the same -* lock repeatedly is ok. -*/ -WARN_ON_ONCE (p->blocked_on && p->blocked_on != m); - p->blocked_on = m; +lockdep_assert_held (&p->blocked_lock); + +if (p->blocked_on_state ==BO_WAKING ) + p->blocked_on_state =BO_RUNNABLE ; } -static inline void set_task_blocked_on (struct task_struct *p,struct mutex *m) +static inline void set_blocked_on_runnable (struct task_struct *p) { +if (!sched_proxy_exec ()) +return ; +guard (raw_spinlock_irqsave)(&p->blocked_lock); -__set_task_blocked_on (p, m); +__set_blocked_on_runnable (p); } -static inline void __clear_task_blocked_on (struct task_struct *p,struct mutex *m) +static inline void __set_blocked_on_waking (struct task_struct *p) { -/* Currently we serialize blocked_on under the task::blocked_lock */ -lockdep_assert_held_once (&p->blocked_lock); -/* -* There may be cases where we re-clear already cleared -* blocked_on relationships, but make sure we are not -* clearing the relationship with a different lock. -*/ -WARN_ON_ONCE (m && p->blocked_on && p->blocked_on != m); - p->blocked_on =NULL ; +lockdep_assert_held (&p->blocked_lock); + +if (p->blocked_on_state ==BO_BLOCKED ) + p->blocked_on_state =BO_WAKING ; } -static inline void clear_task_blocked_on (struct task_struct *p,struct mutex *m) +static inline struct mutex *__get_task_blocked_on (struct task_struct *p) { -guard (raw_spinlock_irqsave)(&p->blocked_lock); -__clear_task_blocked_on (p, m); +lockdep_assert_held_once (&p->blocked_lock); +return p->blocked_on; } -static inline void clear_task_blocked_on_nested (struct task_struct *p,struct mutex *m) +static inline void set_blocked_on_waking_nested (struct task_struct *p) {raw_spin_lock_nested (&p->blocked_lock,SINGLE_DEPTH_NESTING ); -__clear_task_blocked_on (p, m); +__set_blocked_on_waking (p);raw_spin_unlock (&p->blocked_lock); } -#else -static inline void __clear_task_blocked_on (struct task_struct *p,struct rt_mutex *m) -{ -} -static inline void clear_task_blocked_on (struct task_struct *p,struct rt_mutex *m) +static inline void __set_task_blocked_on (struct task_struct *p,struct mutex *m) { +WARN_ON_ONCE (!m); +/* The task should only be setting itself as blocked */ +WARN_ON_ONCE (p != current); +/* Currently we serialize blocked_on under the task::blocked_lock */ +lockdep_assert_held_once (&p->blocked_lock); +/* +* Check ensure we don't overwrite existing mutex value +* with a different mutex. +*/ +WARN_ON_ONCE (p->blocked_on); + p->blocked_on = m; + p->blocked_on_state =BO_BLOCKED ; } -static inline void clear_task_blocked_on_nested (struct task_struct *p,struct rt_mutex *m) +static inline void __clear_task_blocked_on (struct task_struct *p,struct mutex *m) { +/* The task should only be clearing itself */ +WARN_ON_ONCE (p != current); +/* Currently we serialize blocked_on under the task::blocked_lock */ +lockdep_assert_held_once (&p->blocked_lock); +/* Make sure we are clearing the relationship with the right lock */ +WARN_ON_ONCE (p->blocked_on != m); + p->blocked_on =NULL ; + p->blocked_on_state =BO_RUNNABLE ; } -#endif /* !CONFIG_PREEMPT_RT */ static __always_inline bool need_resched(void) {
init/init_task.c +1 -0
@@ -174,6 +174,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = { .mems_allowed_seq = SEQCNT_SPINLOCK_ZERO(init_task.mems_allowed_seq, &init_task.alloc_lock), #endif + .blocked_on_state =BO_RUNNABLE , #ifdef CONFIG_RT_MUTEXES .pi_waiters =RB_ROOT_CACHED , .pi_top_task = NULL,
kernel/fork.c +1 -0
@@ -2124,6 +2124,7 @@ __latent_entropy struct task_struct *copy_process(lockdep_init_task (p);#endif + p->blocked_on_state =BO_RUNNABLE ; p->blocked_on =NULL ;/* not blocked yet */ #ifdef CONFIG_BCACHE
kernel/locking/mutex.c +8 -7
@@ -686,11 +686,9 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclasraw_spin_lock_irqsave (&lock->wait_lock, flags);raw_spin_lock (¤t->blocked_lock);/* -* As we likely have been woken up by task -* that has cleared our blocked_on state, re-set -* it to the lock we are trying to acquire. +* Re-set blocked_on_state as unlock path set it to WAKING/RUNNABLE */ -__set_task_blocked_on (current, lock); + current->blocked_on_state =BO_BLOCKED ;set_current_state (state);/* * Here we order against unlock; we must either see it change
@@ -709,14 +707,14 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas* and clear blocked on so we don't become unselectable * to run. */ -__clear_task_blocked_on (current, lock); + current->blocked_on_state =BO_RUNNABLE ;raw_spin_unlock (¤t->blocked_lock);raw_spin_unlock_irqrestore (&lock->wait_lock, flags);trace_contention_begin (lock,LCB_F_MUTEX |LCB_F_SPIN ); opt_acquired =mutex_optimistic_spin (lock, ww_ctx, &waiter);raw_spin_lock_irqsave (&lock->wait_lock, flags);raw_spin_lock (¤t->blocked_lock); -__set_task_blocked_on (current, lock); + current->blocked_on_state =BO_BLOCKED ;if (opt_acquired)break ;trace_contention_begin (lock,LCB_F_MUTEX );
@@ -968,8 +966,11 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne next = waiter->task; +raw_spin_lock (&next->blocked_lock);debug_mutex_wake_waiter (lock, waiter); -clear_task_blocked_on (next, lock); +WARN_ON_ONCE (__get_task_blocked_on (next) != lock); +__set_blocked_on_waking (next); +raw_spin_unlock (&next->blocked_lock);wake_q_add (&wake_q, next); }
kernel/locking/ww_mutex.h +8 -9
@@ -285,12 +285,12 @@ __ww_mutex_die(struct MUTEX *lock, struct MUTEX_WAITER *waiter,debug_mutex_wake_waiter (lock, waiter);#endif /* -* When waking up the task to die, be sure to clear the -* blocked_on pointer. Otherwise we can see circular -* blocked_on relationships that can't resolve. +* When waking up the task to die, be sure to set the +* blocked_on_state to BO_WAKING. Otherwise we can see +* circular blocked_on relationships that can't resolve. */ /* nested as we should hold current->blocked_lock already */ -clear_task_blocked_on_nested (waiter->task, lock); +set_blocked_on_waking_nested (waiter->task);wake_q_add (wake_q, waiter->task); }
@@ -340,12 +340,11 @@ static bool __ww_mutex_wound(struct MUTEX *lock,*/ if (owner != current) {/* -* When waking up the task to wound, be sure to clear the -* blocked_on pointer. Otherwise we can see circular -* blocked_on relationships that can't resolve. +* When waking up the task to wound, be sure to set the +* blocked_on_state to BO_WAKING. Otherwise we can see +* circular blocked_on relationships that can't resolve. */ -/* nested as we should hold current->blocked_lock already */ -clear_task_blocked_on_nested (owner, lock); +set_blocked_on_waking_nested (owner);wake_q_add (wake_q, owner); }return true;
kernel/sched/core.c +24 -2
@@ -4322,6 +4322,7 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)ttwu_queue (p, cpu, wake_flags); } out: +set_blocked_on_runnable (p);if (success)ttwu_stat (p,task_cpu (p), wake_flags);
@@ -6617,7 +6618,7 @@ static struct task_struct *proxy_deactivate(struct rq *rq, struct task_struct *d* as unblocked, as we aren't doing proxy-migrations * yet (more logic will be needed then). */ - donor->blocked_on =NULL ; + donor->blocked_on_state =BO_RUNNABLE ; }return NULL ; }
@@ -6670,9 +6671,30 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)return NULL ; } +/* +* If a ww_mutex hits the die/wound case, it marks the task as +* BO_WAKING and calls try_to_wake_up(), so that the mutex +* cycle can be broken and we avoid a deadlock. +* +* However, if at that moment, we are here on the cpu which the +* die/wounded task is enqueued, we might loop on the cycle as +* BO_WAKING still causes task_is_blocked() to return true +* (since we want return migration to occur before we run the +* task). +* +* Unfortunately since we hold the rq lock, it will block +* try_to_wake_up from completing and doing the return +* migration. +* +* So when we hit a !BO_BLOCKED task briefly schedule idle +* so we release the rq and let the wakeup complete. +*/ +if (p->blocked_on_state !=BO_BLOCKED ) +return proxy_resched_idle (rq); + owner =__mutex_owner (mutex);if (!owner) { -__clear_task_blocked_on (p, mutex); +__force_blocked_on_runnable (p);return p; }
kernel/sched/sched.h +1 -1
@@ -2267,7 +2267,7 @@ static inline bool task_is_blocked(struct task_struct *p)if (!sched_proxy_exec ())return false; -return !!p->blocked_on; +return !!p->blocked_on && p->blocked_on_state !=BO_RUNNABLE ; }static inline int task_on_cpu (struct rq *rq,struct task_struct *p)
Signature · 1 line
2.50.0.727.gbf7dc18ff4-goog
RFC PATCH v20 3/6 sched: Add logic to zap balance callbacks if we pick again
In reply to John StultzWith proxy-exec, a task is selected to run via pick_next_task(), and then if it is a mutex blocked task, we call find_proxy_task() to find a runnable owner. If the runnable owner is on another cpu, we will need to migrate the selected donor task away, after which we will pick_again can call pick_next_task() to choose something else.
However, in the first call to pick_next_task(), we may have had a balance_callback setup by the class scheduler. After we pick again, its possible pick_next_task_fair() will be called which calls sched_balance_newidle() and sched_balance_rq().
This will throw a warning:
[ 8.796467] rq->balance_callback && rq->balance_callback != &balance_push_callback [ 8.796467] WARNING: CPU: 32 PID: 458 at kernel/sched/sched.h:1750 sched_balance_rq+0xe92/0x1250 ... [ 8.796467] Call Trace: [ 8.796467] <TASK> [ 8.796467] ? __warn.cold+0xb2/0x14e [ 8.796467] ? sched_balance_rq+0xe92/0x1250 [ 8.796467] ? report_bug+0x107/0x1a0 [ 8.796467] ? handle_bug+0x54/0x90 [ 8.796467] ? exc_invalid_op+0x17/0x70 [ 8.796467] ? asm_exc_invalid_op+0x1a/0x20 [ 8.796467] ? sched_balance_rq+0xe92/0x1250 [ 8.796467] sched_balance_newidle+0x295/0x820 [ 8.796467] pick_next_task_fair+0x51/0x3f0 [ 8.796467] __schedule+0x23a/0x14b0 [ 8.796467] ? lock_release+0x16d/0x2e0 [ 8.796467] schedule+0x3d/0x150 [ 8.796467] worker_thread+0xb5/0x350 [ 8.796467] ? __pfx_worker_thread+0x10/0x10 [ 8.796467] kthread+0xee/0x120 [ 8.796467] ? __pfx_kthread+0x10/0x10 [ 8.796467] ret_from_fork+0x31/0x50 [ 8.796467] ? __pfx_kthread+0x10/0x10 [ 8.796467] ret_from_fork_asm+0x1a/0x30 [ 8.796467] </TASK>
This is because if a RT task was originally picked, it will setup the rq->balance_callback with push_rt_tasks() via set_next_task_rt().
Once the task is migrated away and we pick again, we haven't processed any balance callbacks, so rq->balance_callback is not in the same state as it was the first time pick_next_task was called.
To handle this, add a zap_balance_callbacks() helper function which cleans up the blance callbacks without running them. This should be ok, as we are effectively undoing the state set in the first call to pick_next_task(), and when we pick again, the new callback can be configured for the donor task actually selected.
---
v20:
* Tweaked to avoid build issues with different configs
--- kernel/sched/core.c | 39 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 38 insertions(+), 1 deletion(-)
kernel/sched/core.c +38 -1
@@ -4990,6 +4990,40 @@ static inline void finish_task(struct task_struct *prev)smp_store_release (&prev->on_cpu,0 ); } +#ifdef CONFIG_SCHED_PROXY_EXEC +/* +* Only called from __schedule context +* +* There are some cases where we are going to re-do the action +* that added the balance callbacks. We may not be in a state +* where we can run them, so just zap them so they can be +* properly re-added on the next time around. This is similar +* handling to running the callbacks, except we just don't call +* them. +*/ +static void zap_balance_callbacks (struct rq *rq) +{ +struct balance_callback *next, *head; +bool found = false; + +lockdep_assert_rq_held (rq); + + head = rq->balance_callback; +while (head) { +if (head == &balance_push_callback) + found = true; + next = head->next; + head->next =NULL ; + head = next; + } + rq->balance_callback = found ? &balance_push_callback :NULL ; +} +#else +static inline void zap_balance_callbacks (struct rq *rq) +{ +} +#endif +static void do_balance_callbacks (struct rq *rq,struct balance_callback *head) {void (*func)(struct rq *rq);
@@ -6920,8 +6954,11 @@ static void __sched notrace __schedule(int sched_mode)rq_set_donor (rq, next);if (unlikely (task_is_blocked (next))) { next =find_proxy_task (rq, next, &rf); -if (!next) +if (!next) { +/* zap the balance_callbacks before picking again */ +zap_balance_callbacks (rq); goto pick_again; + }if (next == rq->idle) goto keep_resched; }
Signature · 1 line
2.50.0.727.gbf7dc18ff4-goog
RFC PATCH v20 4/6 sched: Handle blocked-waiter migration (and return migration)
In reply to John StultzAdd logic to handle migrating a blocked waiter to a remote cpu where the lock owner is runnable.
Additionally, as the blocked task may not be able to run on the remote cpu, add logic to handle return migration once the waiting task is given the mutex.
Because tasks may get migrated to where they cannot run, also modify the scheduling classes to avoid sched class migrations on mutex blocked tasks, leaving find_proxy_task() and related logic to do the migrations and return migrations.
This was split out from the larger proxy patch, and significantly reworked.
Credits for the original patch go to:
Peter Zijlstra (Intel) <[email protected]>
Juri Lelli <[email protected]>
Valentin Schneider <[email protected]>
Connor O'Brien <[email protected]>
NOTE: With this patch I've hit a few cases where we seem to miss a BO_WAKING->BO_RUNNING transition (and return migration) that I'd expect to happen in ttwu(). So I have logic in find_proxy_task() to detect and to handle the return migration later. However I'm quite not happy with that as it shouldn't be necessary, and am still trying to understand where I'm losing the wakeup & return migration.
---
v6:
* Integrated sched_proxy_exec() check in proxy_return_migration()
* Minor cleanups to diff
* Unpin the rq before calling __balance_callbacks()
* Tweak proxy migrate to migrate deeper task in chain, to avoid tasks pingponging between rqs
v7:
* Fixup for unused function arguments
* Switch from that_rq -> target_rq, other minor tweaks, and typo fixes suggested by Metin Kaya
* Switch back to doing return migration in the ttwu path, which avoids nasty lock juggling and performance issues
* Fixes for UP builds
v8:
* More simplifications from Metin Kaya
* Fixes for null owner case, including doing return migration
* Cleanup proxy_needs_return logic
v9:
* Narrow logic in ttwu that sets BO_RUNNABLE, to avoid missed return migrations
* Switch to using zap_balance_callbacks rathern then running them when we are dropping rq locks for proxy_migration.
* Drop task_is_blocked check in sched_submit_work as suggested by Metin (may re-add later if this causes trouble)
* Do return migration when we're not on wake_cpu. This avoids bad task placement caused by proxy migrations raised by Xuewen Yan
* Fix to call set_next_task(rq->curr) prior to dropping rq lock to avoid rq->curr getting migrated before we have actually switched from it
* Cleanup to re-use proxy_resched_idle() instead of open coding it in proxy_migrate_task()
* Fix return migration not to use DEQUEUE_SLEEP, so that we properly see the task as task_on_rq_migrating() after it is dequeued but before set_task_cpu() has been called on it
* Fix to broaden find_proxy_task() checks to avoid race where a task is dequeued off the rq due to return migration, but set_task_cpu() and the enqueue on another rq happened after we checked task_cpu(owner). This ensures we don't proxy using a task that is not actually on our runqueue.
* Cleanup to avoid the locked BO_WAKING->BO_RUNNABLE transition in try_to_wake_up() if proxy execution isn't enabled.
* Cleanup to improve comment in proxy_migrate_task() explaining the set_next_task(rq->curr) logic
* Cleanup deadline.c change to stylistically match rt.c change
* Numerous cleanups suggested by Metin
v10:
* Drop WARN_ON(task_is_blocked(p)) in ttwu current case v11:
* Include proxy_set_task_cpu from later in the series to this change so we can use it, rather then reworking logic later in the series.
* Fix problem with return migration, where affinity was changed and wake_cpu was left outside the affinity mask.
* Avoid reading the owner's cpu twice (as it might change inbetween) to avoid occasional migration-to-same-cpu edge cases
* Add extra WARN_ON checks for wake_cpu and return migration edge cases.
* Typo fix from Metin
v13:
* As we set ret, return it, not just NULL (pulling this change in from later patch)
* Avoid deadlock between try_to_wake_up() and find_proxy_task() when blocked_on cycle with ww_mutex is trying a mid-chain wakeup.
* Tweaks to use new __set_blocked_on_runnable() helper
* Potential fix for incorrectly updated task->dl_server issues
* Minor comment improvements
* Add logic to handle missed wakeups, in that case doing return migration from the find_proxy_task() path
* Minor cleanups
v14:
* Improve edge cases where we wouldn't set the task as BO_RUNNABLE v15:
* Added comment to better describe proxy_needs_return() as suggested by Qais
* Build fixes for !CONFIG_SMP reported by
Maciej Żenczykowski <[email protected]>
* Adds fix for re-evaluating proxy_needs_return when sched_proxy_exec() is disabled, reported and diagnosed by:
kuyo chang <[email protected]>
v16:
* Larger rework of needs_return logic in find_proxy_task, in order to avoid problems with cpuhotplug
* Rework to use guard() as suggested by Peter
v18:
* Integrate optimization suggested by Suleiman to do the checks for sleeping owners before checking if the task_cpu is this_cpu, so that we can avoid needlessly proxy-migrating tasks to only then dequeue them. Also check if migrating last.
* Improve comments around guard locking
* Include tweak to ttwu_runnable() as suggested by
hupu <[email protected]>
* Rework the logic releasing the rq->donor reference before letting go of the rqlock. Just use rq->idle.
* Go back to doing return migration on BO_WAKING owners, as I was hitting some softlockups caused by running tasks not making it out of BO_WAKING.
v19:
* Fixed proxy_force_return() logic for !SMP cases
fix for proxy migration logic on !SMP
--- kernel/sched/core.c | 251 ++++++++++++++++++++++++++++++++++++++++---- kernel/sched/fair.c | 3 +- 2 files changed, 230 insertions(+), 24 deletions(-)
kernel/sched/core.c +228 -23
@@ -3151,6 +3151,14 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,__do_set_cpus_allowed (p, ctx); +/* +* It might be that the p->wake_cpu is no longer +* allowed, so set it to the dest_cpu so return +* migration doesn't send it to an invalid cpu +*/ +if (!is_cpu_allowed (p, p->wake_cpu)) + p->wake_cpu = dest_cpu; +return affine_move_task (rq, p, rf, dest_cpu, ctx->flags); out:
@@ -3711,6 +3719,67 @@ static inline void ttwu_do_wakeup(struct task_struct *p)trace_sched_wakeup (p); } +#ifdef CONFIG_SCHED_PROXY_EXEC +static inline void proxy_set_task_cpu (struct task_struct *p,int cpu) +{ +unsigned int wake_cpu; + +/* +* Since we are enqueuing a blocked task on a cpu it may +* not be able to run on, preserve wake_cpu when we +* __set_task_cpu so we can return the task to where it +* was previously runnable. +*/ + wake_cpu = p->wake_cpu; +__set_task_cpu (p, cpu); + p->wake_cpu = wake_cpu; +} + +static bool proxy_task_runnable_but_waking (struct task_struct *p) +{ +if (!sched_proxy_exec ()) +return false; +return (READ_ONCE (p->__state) ==TASK_RUNNING && +READ_ONCE (p->blocked_on_state) ==BO_WAKING ); +} +#else /* !CONFIG_SCHED_PROXY_EXEC */ +static bool proxy_task_runnable_but_waking (struct task_struct *p) +{ +return false; +} +#endif /* CONFIG_SCHED_PROXY_EXEC */ + +/* +* Checks to see if task p has been proxy-migrated to another rq +* and needs to be returned. If so, we deactivate the task here +* so that it can be properly woken up on the p->wake_cpu +* (or whichever cpu select_task_rq() picks at the bottom of +* try_to_wake_up() +*/ +static inline bool proxy_needs_return (struct rq *rq,struct task_struct *p) +{ +bool ret = false; + +if (!sched_proxy_exec ()) +return false; + +raw_spin_lock (&p->blocked_lock); +if (__get_task_blocked_on (p) && p->blocked_on_state ==BO_WAKING ) { +if (!task_current (rq, p) && (p->wake_cpu !=cpu_of (rq))) { +if (task_current_donor (rq, p)) { +put_prev_task (rq, p); +rq_set_donor (rq, rq->idle); + } +deactivate_task (rq, p,DEQUEUE_NOCLOCK ); + ret = true; + } +__set_blocked_on_runnable (p); +resched_curr (rq); + } +raw_spin_unlock (&p->blocked_lock); +return ret; +} +static void ttwu_do_activate (struct rq *rq,struct task_struct *p,int wake_flags,struct rq_flags *rf)
@@ -3796,6 +3865,8 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)update_rq_clock (rq);if (p->se.sched_delayed)enqueue_task (rq, p,ENQUEUE_NOCLOCK |ENQUEUE_DELAYED ); +if (proxy_needs_return (rq, p)) + goto out;if (!task_on_cpu (rq, p)) {/* * When on_rq && !on_cpu the task is preempted, see if
@@ -3806,6 +3877,7 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)ttwu_do_wakeup (p); ret =1 ; } +out:__task_rq_unlock (rq, &rf);return ret;
@@ -4193,6 +4265,8 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)* it disabling IRQs (this allows not taking ->pi_lock). */ WARN_ON_ONCE (p->se.sched_delayed); +/* If current is waking up, we know we can run here, so set BO_RUNNBLE */ +set_blocked_on_runnable (p);if (!ttwu_state_match (p, state, &success)) goto out;
@@ -4209,8 +4283,15 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)*/ scoped_guard (raw_spinlock_irqsave, &p->pi_lock) {smp_mb__after_spinlock (); -if (!ttwu_state_match (p, state, &success)) -break ; +if (!ttwu_state_match (p, state, &success)) { +/* +* If we're already TASK_RUNNING, and BO_WAKING +* continue on to ttwu_runnable check to force +* proxy_needs_return evaluation +*/ +if (!proxy_task_runnable_but_waking (p)) +break ; + }trace_sched_waking (p);
@@ -4272,6 +4353,7 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)* enqueue, such as ttwu_queue_wakelist(). */ WRITE_ONCE (p->__state,TASK_WAKING ); +set_blocked_on_runnable (p);/* * If the owning (remote) CPU is still in the middle of schedule() with
@@ -4322,7 +4404,6 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)ttwu_queue (p, cpu, wake_flags); } out: -set_blocked_on_runnable (p);if (success)ttwu_stat (p,task_cpu (p), wake_flags);
@@ -6624,7 +6705,7 @@ static inline struct task_struct *proxy_resched_idle(struct rq *rq)return rq->idle; } -static bool __proxy_deactivate (struct rq *rq,struct task_struct *donor) +static bool proxy_deactivate (struct rq *rq,struct task_struct *donor) {unsigned long state =READ_ONCE (donor->__state);
@@ -6644,17 +6725,98 @@ static bool __proxy_deactivate(struct rq *rq, struct task_struct *donor)return try_to_block_task (rq, donor, &state, true); } -static struct task_struct *proxy_deactivate (struct rq *rq,struct task_struct *donor) +/* +* If the blocked-on relationship crosses CPUs, migrate @p to the +* owner's CPU. +* +* This is because we must respect the CPU affinity of execution +* contexts (owner) but we can ignore affinity for scheduling +* contexts (@p). So we have to move scheduling contexts towards +* potential execution contexts. +* +* Note: The owner can disappear, but simply migrate to @target_cpu +* and leave that CPU to sort things out. +*/ +static void proxy_migrate_task (struct rq *rq,struct rq_flags *rf, +struct task_struct *p,int target_cpu) { -if (!__proxy_deactivate (rq, donor)) { -/* -* XXX: For now, if deactivation failed, set donor -* as unblocked, as we aren't doing proxy-migrations -* yet (more logic will be needed then). -*/ - donor->blocked_on_state =BO_RUNNABLE ; - } -return NULL ; +struct rq *target_rq =cpu_rq (target_cpu); + +lockdep_assert_rq_held (rq); + +/* +* Since we're going to drop @rq, we have to put(@rq->donor) first, +* otherwise we have a reference that no longer belongs to us. +* +* Additionally, as we put_prev_task(prev) earlier, its possible that +* prev will migrate away as soon as we drop the rq lock, however we +* still have it marked as rq->curr, as we've not yet switched tasks. +* +* After the migration, we are going to pick_again in the __schedule +* logic, so backtrack a bit before we release the lock: +* Put rq->donor, and set rq->curr as rq->donor and set_next_task, +* so that we're close to the situation we had entering __schedule +* the first time. +* +* Then when we re-aquire the lock, we will re-put rq->curr then +* rq_set_donor(rq->idle) and set_next_task(rq->idle), before +* picking again. +*/ +/* XXX - Added to address problems with changed dl_server semantics - double check */ +__put_prev_set_next_dl_server (rq, rq->donor, rq->curr); +put_prev_task (rq, rq->donor); +rq_set_donor (rq, rq->idle); +set_next_task (rq, rq->idle); + +WARN_ON (p == rq->curr); + +deactivate_task (rq, p,0 ); +proxy_set_task_cpu (p, target_cpu); + +zap_balance_callbacks (rq); +rq_unpin_lock (rq, rf); +raw_spin_rq_unlock (rq); +raw_spin_rq_lock (target_rq); + +activate_task (target_rq, p,0 ); +wakeup_preempt (target_rq, p,0 ); + +raw_spin_rq_unlock (target_rq); +raw_spin_rq_lock (rq); +rq_repin_lock (rq, rf); +} + +static void proxy_force_return (struct rq *rq,struct rq_flags *rf, +struct task_struct *p) +{ +lockdep_assert_rq_held (rq); + +put_prev_task (rq, rq->donor); +rq_set_donor (rq, rq->idle); +set_next_task (rq, rq->idle); + +WARN_ON (p == rq->curr); + + p->blocked_on_state =BO_WAKING ; +get_task_struct (p); +block_task (rq, p,0 ); + +zap_balance_callbacks (rq); +rq_unpin_lock (rq, rf); +raw_spin_rq_unlock (rq); + +wake_up_process (p); +put_task_struct (p); + +raw_spin_rq_lock (rq); +rq_repin_lock (rq, rf); +} + +static inline bool proxy_can_run_here (struct rq *rq,struct task_struct *p) +{ +if (p == rq->curr || p->wake_cpu ==cpu_of (rq)) +return true; +return false; }/*
@@ -6677,9 +6839,11 @@ static struct task_struct * find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf) { struct task_struct *owner = NULL; +bool curr_in_chain = false;int this_cpu =cpu_of (rq);struct task_struct *p;struct mutex *mutex; +int owner_cpu;/* Follow blocked_on chain. */ for (p = donor;task_is_blocked (p); p = owner) {
@@ -6705,6 +6869,10 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)return NULL ; } +/* Double check blocked_on_state now we're holding the lock */ +if (p->blocked_on_state ==BO_RUNNABLE ) +return p; +/* * If a ww_mutex hits the die/wound case, it marks the task as * BO_WAKING and calls try_to_wake_up(), so that the mutex
@@ -6720,26 +6888,50 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)* try_to_wake_up from completing and doing the return * migration. * -* So when we hit a !BO_BLOCKED task briefly schedule idle -* so we release the rq and let the wakeup complete. +* So when we hit a BO_WAKING task try to wake it up ourselves. */ -if (p->blocked_on_state !=BO_BLOCKED ) -return proxy_resched_idle (rq); +if (p->blocked_on_state ==BO_WAKING ) { +if (task_current (rq, p)) { +/* If its current just set it runnable */ +__force_blocked_on_runnable (p); +return p; + } + goto needs_return; + } + +if (task_current (rq, p)) + curr_in_chain = true; owner =__mutex_owner (mutex);if (!owner) { +/* If the owner is null, we may have some work to do */ +if (!proxy_can_run_here (rq, p)) + goto needs_return; +__force_blocked_on_runnable (p);return p; }if (!READ_ONCE (owner->on_rq) || owner->se.sched_delayed) { -/* XXX Don't handle blocked owners/delayed dequeue yet */ -return proxy_deactivate (rq, donor); +/* XXX Don't handle blocked owners / delay dequeued yet */ +if (!proxy_deactivate (rq, donor)) { +if (!proxy_can_run_here (rq, p)) + goto needs_return; +__force_blocked_on_runnable (p); +return p; + } +return NULL ; } -if (task_cpu (owner) != this_cpu) { -/* XXX Don't handle migrations yet */ -return proxy_deactivate (rq, donor); + owner_cpu =task_cpu (owner); +if (owner_cpu != this_cpu) { +/* +* @owner can disappear, simply migrate to @owner_cpu +* and leave that CPU to sort things out. +*/ +if (curr_in_chain) +return proxy_resched_idle (rq); + goto migrate; }if (task_on_rq_migrating (owner)) {
@@ -6799,6 +6991,19 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)WARN_ON_ONCE (owner && !owner->on_rq);return owner; + +/* +* NOTE: This logic is down here, because we need to call +* the functions with the mutex wait_lock and task +* blocked_lock released, so we have to get out of the +* guard() scope. +*/ +migrate: +proxy_migrate_task (rq, rf, p, owner_cpu); +return NULL ; +needs_return: +proxy_force_return (rq, rf, p); +return NULL ; }#else /* SCHED_PROXY_EXEC */ static struct task_struct *
kernel/sched/fair.c +2 -1
@@ -8781,7 +8781,8 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf se = &p->se;#ifdef CONFIG_FAIR_GROUP_SCHED -if (prev->sched_class != &fair_sched_class) +if (prev->sched_class != &fair_sched_class || + rq->curr != rq->donor) goto simple;__put_prev_set_next_dl_server (rq, prev, p);
Signature · 1 line
2.50.0.727.gbf7dc18ff4-goog
RFC PATCH v20 5/6 sched: Add blocked_donor link to task for smarter mutex handoffs
In reply to John StultzFrom: Peter Zijlstra <[email protected]>
Add link to the task this task is proxying for, and use it so the mutex owner can do an intelligent hand-off of the mutex to the task that the owner is running on behalf.
---
v5:
* Split out from larger proxy patch
v6:
* Moved proxied value from earlier patch to this one where it is actually used
* Rework logic to check sched_proxy_exec() instead of using ifdefs
* Moved comment change to this patch where it makes sense v7:
* Use more descriptive term then "us" in comments, as suggested by Metin Kaya.
* Minor typo fixup from Metin Kaya
* Reworked proxied variable to prev_not_proxied to simplify usage v8:
* Use helper for donor blocked_on_state transition
v9:
* Re-add mutex lock handoff in the unlock path, but only when we have a blocked donor
* Slight reword of commit message suggested by Metin v18:
* Add task_init initialization for blocked_donor, suggested by Suleiman
--- include/linux/sched.h | 1 + init/init_task.c | 1 + kernel/fork.c | 1 + kernel/locking/mutex.c | 41 ++++++++++++++++++++++++++++++++++++++--- kernel/sched/core.c | 18 ++++++++++++++++-- 5 files changed, 57 insertions(+), 5 deletions(-)
include/linux/sched.h +1 -0
@@ -1239,6 +1239,7 @@ struct task_struct {enum blocked_on_state blocked_on_state;struct mutex *blocked_on;/* lock we're blocked on */ +struct task_struct *blocked_donor;/* task that is boosting this task */ raw_spinlock_t blocked_lock;#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
init/init_task.c +1 -0
@@ -175,6 +175,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = { &init_task.alloc_lock), #endif .blocked_on_state = BO_RUNNABLE, + .blocked_donor =NULL , #ifdef CONFIG_RT_MUTEXES .pi_waiters =RB_ROOT_CACHED , .pi_top_task = NULL,
kernel/fork.c +1 -0
@@ -2126,6 +2126,7 @@ __latent_entropy struct task_struct *copy_process( p->blocked_on_state =BO_RUNNABLE ; p->blocked_on =NULL ;/* not blocked yet */ + p->blocked_donor =NULL ;/* nobody is boosting p yet */ #ifdef CONFIG_BCACHE p->sequential_io =0 ;
kernel/locking/mutex.c +38 -3
71 lines not on this page · raw message
kernel/sched/core.c +16 -2
@@ -6823,7 +6823,17 @@ static inline bool proxy_can_run_here(struct rq *rq, struct task_struct *p)* Find runnable lock owner to proxy for mutex blocked donor * * Follow the blocked-on relation: -* task->blocked_on -> mutex->owner -> task... +* +* ,-> task +* | | blocked-on +* | v +* blocked_donor | mutex +* | | owner +* | v +* `-- task +* +* and set the blocked_donor relation, this latter is used by the mutex +* code to find which (blocked) task to hand-off to. * * Lock order: *
@@ -6987,6 +6997,7 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)* rq, therefore holding @rq->lock is sufficient to * guarantee its existence, as per ttwu_remote(). */ + owner->blocked_donor = p; }WARN_ON_ONCE (owner && !owner->on_rq);
@@ -7083,6 +7094,7 @@ static void __sched notrace __schedule(int sched_mode)unsigned long prev_state;struct rq_flags rf;struct rq *rq; +bool prev_not_proxied;int cpu;trace_sched_entry_tp (preempt,CALLER_ADDR0 );
@@ -7154,9 +7166,11 @@ static void __sched notrace __schedule(int sched_mode) switch_count = &prev->nvcsw; } + prev_not_proxied = !prev->blocked_donor; pick_again: next =pick_next_task (rq, rq->donor, &rf);rq_set_donor (rq, next); + next->blocked_donor =NULL ;if (unlikely (task_is_blocked (next))) { next =find_proxy_task (rq, next, &rf);if (!next) {
@@ -7220,7 +7234,7 @@ static void __sched notrace __schedule(int sched_mode) rq =context_switch (rq, prev, next, &rf); }else {/* In case next was already curr but just got blocked_donor */ -if (!task_current_donor (rq, next)) +if (prev_not_proxied && next->blocked_donor)proxy_tag_curr (rq, next);rq_unpin_lock (rq, &rf);
Signature · 1 line
2.50.0.727.gbf7dc18ff4-goog
RFC PATCH v20 6/6 sched: Migrate whole chain in proxy_migrate_task()
In reply to John StultzInstead of migrating one task each time through find_proxy_task(), we can walk up the blocked_donor ptrs and migrate the entire current chain in one go.
This was broken out of earlier patches and held back while the series was being stabilized, but I wanted to re-introduce it.
---
v12:
* Earlier this was re-using blocked_node, but I hit a race with activating blocked entities, and to avoid it introduced a new migration_node listhead
v18:
* Add init_task initialization of migration_node as suggested by Suleiman
--- include/linux/sched.h | 1 + init/init_task.c | 1 + kernel/fork.c | 1 + kernel/sched/core.c | 25 +++++++++++++++++-------- 4 files changed, 20 insertions(+), 8 deletions(-)
include/linux/sched.h +1 -0
@@ -1240,6 +1240,7 @@ struct task_struct {enum blocked_on_state blocked_on_state;struct mutex *blocked_on;/* lock we're blocked on */ struct task_struct *blocked_donor;/* task that is boosting this task */ +struct list_head migration_node;raw_spinlock_t blocked_lock;#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
init/init_task.c +1 -0
@@ -176,6 +176,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {#endif .blocked_on_state = BO_RUNNABLE, .blocked_donor = NULL, + .migration_node =LIST_HEAD_INIT (init_task.migration_node), #ifdef CONFIG_RT_MUTEXES .pi_waiters =RB_ROOT_CACHED , .pi_top_task = NULL,
kernel/fork.c +1 -0
@@ -2127,6 +2127,7 @@ __latent_entropy struct task_struct *copy_process( p->blocked_on_state =BO_RUNNABLE ; p->blocked_on =NULL ;/* not blocked yet */ p->blocked_donor =NULL ;/* nobody is boosting p yet */ +INIT_LIST_HEAD (&p->migration_node);#ifdef CONFIG_BCACHE p->sequential_io =0 ;
kernel/sched/core.c +17 -8
@@ -6741,6 +6741,7 @@ static void proxy_migrate_task(struct rq *rq, struct rq_flags *rf, struct task_struct *p, int target_cpu) {struct rq *target_rq =cpu_rq (target_cpu); +LIST_HEAD (migrate_list);lockdep_assert_rq_held (rq);
@@ -6768,19 +6769,27 @@ static void proxy_migrate_task(struct rq *rq, struct rq_flags *rf,rq_set_donor (rq, rq->idle);set_next_task (rq, rq->idle); -WARN_ON (p == rq->curr); - -deactivate_task (rq, p,0 ); -proxy_set_task_cpu (p, target_cpu); - +for (; p; p = p->blocked_donor) { +WARN_ON (p == rq->curr); +deactivate_task (rq, p,0 ); +proxy_set_task_cpu (p, target_cpu); +/* +* We can abuse blocked_node to migrate the thing, +* because @p was still on the rq. +*/ +list_add (&p->migration_node, &migrate_list); + }zap_balance_callbacks (rq);rq_unpin_lock (rq, rf);raw_spin_rq_unlock (rq);raw_spin_rq_lock (target_rq); +while (!list_empty (&migrate_list)) { + p = list_first_entry(&migrate_list, struct task_struct, migration_node); +list_del_init (&p->migration_node); -activate_task (target_rq, p,0 ); -wakeup_preempt (target_rq, p,0 ); - +activate_task (target_rq, p,0 ); +wakeup_preempt (target_rq, p,0 ); + }raw_spin_rq_unlock (target_rq);raw_spin_rq_lock (rq);rq_repin_lock (rq, rf);
Signature · 1 line
2.50.0.727.gbf7dc18ff4-goog
Juri Lelli
maintainerHi,
On 22/07/25 07:05, John Stultz wrote:
...
Quoted 5 lines
Issues still to address with the full series:
* There’s a new quirk from recent changes fordl_serverthat is causing theksched_footballtest in the full series to hang at boot. I’ve bisected and reverted the change for now, but I need to better understand what’s going wrong.
After our quick chat on IRC, I remembered that there were additional two fixes for dl-server posted, but still not on tip.
https://lore.kernel.org/lkml/[email protected]/
https://lore.kernel.org/lkml/[email protected]/
So I went ahead and pushed them to
[email protected]:jlelli/linux.git upstream/fix-dlserver
Could you please check if any (or both together) of the two topmost changes do any good to the issue you are seeing?
Thanks!
Juri
Quoted 13 lines · Juri Lelli
Quoted 5 lines · John Stultz
Issues still to address with the full series:
* There’s a new quirk from recent changes fordl_serverthat is causing theksched_footballtest in the full series to hang at boot. I’ve bisected and reverted the change for now, but I need to better understand what’s going wrong.After our quick chat on IRC, I remembered that there were additional two fixes for dl-server posted, but still not on tip.
https://lore.kernel.org/lkml/[email protected]/
https://lore.kernel.org/lkml/[email protected]/
Quoted 6 lines
So I went ahead and pushed them to
[email protected]:jlelli/linux.git upstream/fix-dlserver
Could you please check if any (or both together) of the two topmost changes do any good to the issue you are seeing?
Thanks for sharing these! Unfortunately they don't seem to help. :/
I'm still digging down into the behavior. I'm not 100% sure the problem isn't just my test logic starving itself (after creating NR_CPU RT spinners, its not surprising creating new threads might be tough if the non-RT kthreadd can't get scheduled), but I don't quite see how the dl_server patch cccb45d7c429 ("sched/deadline: Less agressive dl_server handling") would be the cause of the dramatic behavioral change - esp as this test was also functional prior to the dl_server logic landing. Also it's odd just re-adding the dl_server_stop() call removed from dequeue_entities() seems to make it work again. So I clearly need to dig more to understand the behavior.
Thanks again for your suggestions! I'm going to dig further and let folks know when I figure this detail out
thanks
-john