diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-10-10 09:10:28 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-10-10 09:10:28 -0700 |
commit | 30c999937f69abf935b0228b8411713737377d9e (patch) | |
tree | 1ae97b8df4d61e83bdba2388b2254bb407418385 /include | |
parent | 493ffd6605b2d3d4dc7008ab927dba319f36671f (diff) | |
parent | fdf756f7127185eeffe00e918e66dfee797f3625 (diff) |
Merge tag 'sched-core-2022-10-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
"Debuggability:
- Change most occurances of BUG_ON() to WARN_ON_ONCE()
- Reorganize & fix TASK_ state comparisons, turn it into a bitmap
- Update/fix misc scheduler debugging facilities
Load-balancing & regular scheduling:
- Improve the behavior of the scheduler in presence of lot of
SCHED_IDLE tasks - in particular they should not impact other
scheduling classes.
- Optimize task load tracking, cleanups & fixes
- Clean up & simplify misc load-balancing code
Freezer:
- Rewrite the core freezer to behave better wrt thawing and be
simpler in general, by replacing PF_FROZEN with TASK_FROZEN &
fixing/adjusting all the fallout.
Deadline scheduler:
- Fix the DL capacity-aware code
- Factor out dl_task_is_earliest_deadline() &
replenish_dl_new_period()
- Relax/optimize locking in task_non_contending()
Cleanups:
- Factor out the update_current_exec_runtime() helper
- Various cleanups, simplifications"
* tag 'sched-core-2022-10-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
sched: Fix more TASK_state comparisons
sched: Fix TASK_state comparisons
sched/fair: Move call to list_last_entry() in detach_tasks
sched/fair: Cleanup loop_max and loop_break
sched/fair: Make sure to try to detach at least one movable task
sched: Show PF_flag holes
freezer,sched: Rewrite core freezer logic
sched: Widen TAKS_state literals
sched/wait: Add wait_event_state()
sched/completion: Add wait_for_completion_state()
sched: Add TASK_ANY for wait_task_inactive()
sched: Change wait_task_inactive()s match_state
freezer,umh: Clean up freezer/initrd interaction
freezer: Have {,un}lock_system_sleep() save/restore flags
sched: Rename task_running() to task_on_cpu()
sched/fair: Cleanup for SIS_PROP
sched/fair: Default to false in test_idle_cores()
sched/fair: Remove useless check in select_idle_core()
sched/fair: Avoid double search on same cpu
sched/fair: Remove redundant check in select_idle_smt()
...
Diffstat (limited to 'include')
-rw-r--r-- | include/linux/completion.h | 1 | ||||
-rw-r--r-- | include/linux/freezer.h | 245 | ||||
-rw-r--r-- | include/linux/sched.h | 50 | ||||
-rw-r--r-- | include/linux/sunrpc/sched.h | 7 | ||||
-rw-r--r-- | include/linux/suspend.h | 8 | ||||
-rw-r--r-- | include/linux/umh.h | 9 | ||||
-rw-r--r-- | include/linux/wait.h | 42 |
7 files changed, 88 insertions, 274 deletions
diff --git a/include/linux/completion.h b/include/linux/completion.h index 51d9ab079629..62b32b19e0a8 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -103,6 +103,7 @@ extern void wait_for_completion(struct completion *); extern void wait_for_completion_io(struct completion *); extern int wait_for_completion_interruptible(struct completion *x); extern int wait_for_completion_killable(struct completion *x); +extern int wait_for_completion_state(struct completion *x, unsigned int state); extern unsigned long wait_for_completion_timeout(struct completion *x, unsigned long timeout); extern unsigned long wait_for_completion_io_timeout(struct completion *x, diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 0621c5f86c39..b303472255be 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -8,9 +8,11 @@ #include <linux/sched.h> #include <linux/wait.h> #include <linux/atomic.h> +#include <linux/jump_label.h> #ifdef CONFIG_FREEZER -extern atomic_t system_freezing_cnt; /* nr of freezing conds in effect */ +DECLARE_STATIC_KEY_FALSE(freezer_active); + extern bool pm_freezing; /* PM freezing in effect */ extern bool pm_nosig_freezing; /* PM nosig freezing in effect */ @@ -22,10 +24,7 @@ extern unsigned int freeze_timeout_msecs; /* * Check if a process has been frozen */ -static inline bool frozen(struct task_struct *p) -{ - return p->flags & PF_FROZEN; -} +extern bool frozen(struct task_struct *p); extern bool freezing_slow_path(struct task_struct *p); @@ -34,9 +33,10 @@ extern bool freezing_slow_path(struct task_struct *p); */ static inline bool freezing(struct task_struct *p) { - if (likely(!atomic_read(&system_freezing_cnt))) - return false; - return freezing_slow_path(p); + if (static_branch_unlikely(&freezer_active)) + return freezing_slow_path(p); + + return false; } /* Takes and releases task alloc lock using task_lock() */ @@ -48,23 +48,14 @@ extern int freeze_kernel_threads(void); extern void thaw_processes(void); extern void thaw_kernel_threads(void); -/* - * DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION - * If try_to_freeze causes a lockdep warning it means the caller may deadlock - */ -static inline bool try_to_freeze_unsafe(void) +static inline bool try_to_freeze(void) { might_sleep(); if (likely(!freezing(current))) return false; - return __refrigerator(false); -} - -static inline bool try_to_freeze(void) -{ if (!(current->flags & PF_NOFREEZE)) debug_check_no_locks_held(); - return try_to_freeze_unsafe(); + return __refrigerator(false); } extern bool freeze_task(struct task_struct *p); @@ -79,195 +70,6 @@ static inline bool cgroup_freezing(struct task_struct *task) } #endif /* !CONFIG_CGROUP_FREEZER */ -/* - * The PF_FREEZER_SKIP flag should be set by a vfork parent right before it - * calls wait_for_completion(&vfork) and reset right after it returns from this - * function. Next, the parent should call try_to_freeze() to freeze itself - * appropriately in case the child has exited before the freezing of tasks is - * complete. However, we don't want kernel threads to be frozen in unexpected - * places, so we allow them to block freeze_processes() instead or to set - * PF_NOFREEZE if needed. Fortunately, in the ____call_usermodehelper() case the - * parent won't really block freeze_processes(), since ____call_usermodehelper() - * (the child) does a little before exec/exit and it can't be frozen before - * waking up the parent. - */ - - -/** - * freezer_do_not_count - tell freezer to ignore %current - * - * Tell freezers to ignore the current task when determining whether the - * target frozen state is reached. IOW, the current task will be - * considered frozen enough by freezers. - * - * The caller shouldn't do anything which isn't allowed for a frozen task - * until freezer_cont() is called. Usually, freezer[_do_not]_count() pair - * wrap a scheduling operation and nothing much else. - */ -static inline void freezer_do_not_count(void) -{ - current->flags |= PF_FREEZER_SKIP; -} - -/** - * freezer_count - tell freezer to stop ignoring %current - * - * Undo freezer_do_not_count(). It tells freezers that %current should be - * considered again and tries to freeze if freezing condition is already in - * effect. - */ -static inline void freezer_count(void) -{ - current->flags &= ~PF_FREEZER_SKIP; - /* - * If freezing is in progress, the following paired with smp_mb() - * in freezer_should_skip() ensures that either we see %true - * freezing() or freezer_should_skip() sees !PF_FREEZER_SKIP. - */ - smp_mb(); - try_to_freeze(); -} - -/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ -static inline void freezer_count_unsafe(void) -{ - current->flags &= ~PF_FREEZER_SKIP; - smp_mb(); - try_to_freeze_unsafe(); -} - -/** - * freezer_should_skip - whether to skip a task when determining frozen - * state is reached - * @p: task in quesion - * - * This function is used by freezers after establishing %true freezing() to - * test whether a task should be skipped when determining the target frozen - * state is reached. IOW, if this function returns %true, @p is considered - * frozen enough. - */ -static inline bool freezer_should_skip(struct task_struct *p) -{ - /* - * The following smp_mb() paired with the one in freezer_count() - * ensures that either freezer_count() sees %true freezing() or we - * see cleared %PF_FREEZER_SKIP and return %false. This makes it - * impossible for a task to slip frozen state testing after - * clearing %PF_FREEZER_SKIP. - */ - smp_mb(); - return p->flags & PF_FREEZER_SKIP; -} - -/* - * These functions are intended to be used whenever you want allow a sleeping - * task to be frozen. Note that neither return any clear indication of - * whether a freeze event happened while in this function. - */ - -/* Like schedule(), but should not block the freezer. */ -static inline void freezable_schedule(void) -{ - freezer_do_not_count(); - schedule(); - freezer_count(); -} - -/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ -static inline void freezable_schedule_unsafe(void) -{ - freezer_do_not_count(); - schedule(); - freezer_count_unsafe(); -} - -/* - * Like schedule_timeout(), but should not block the freezer. Do not - * call this with locks held. - */ -static inline long freezable_schedule_timeout(long timeout) -{ - long __retval; - freezer_do_not_count(); - __retval = schedule_timeout(timeout); - freezer_count(); - return __retval; -} - -/* - * Like schedule_timeout_interruptible(), but should not block the freezer. Do not - * call this with locks held. - */ -static inline long freezable_schedule_timeout_interruptible(long timeout) -{ - long __retval; - freezer_do_not_count(); - __retval = schedule_timeout_interruptible(timeout); - freezer_count(); - return __retval; -} - -/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ -static inline long freezable_schedule_timeout_interruptible_unsafe(long timeout) -{ - long __retval; - - freezer_do_not_count(); - __retval = schedule_timeout_interruptible(timeout); - freezer_count_unsafe(); - return __retval; -} - -/* Like schedule_timeout_killable(), but should not block the freezer. */ -static inline long freezable_schedule_timeout_killable(long timeout) -{ - long __retval; - freezer_do_not_count(); - __retval = schedule_timeout_killable(timeout); - freezer_count(); - return __retval; -} - -/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ -static inline long freezable_schedule_timeout_killable_unsafe(long timeout) -{ - long __retval; - freezer_do_not_count(); - __retval = schedule_timeout_killable(timeout); - freezer_count_unsafe(); - return __retval; -} - -/* - * Like schedule_hrtimeout_range(), but should not block the freezer. Do not - * call this with locks held. - */ -static inline int freezable_schedule_hrtimeout_range(ktime_t *expires, - u64 delta, const enum hrtimer_mode mode) -{ - int __retval; - freezer_do_not_count(); - __retval = schedule_hrtimeout_range(expires, delta, mode); - freezer_count(); - return __retval; -} - -/* - * Freezer-friendly wrappers around wait_event_interruptible(), - * wait_event_killable() and wait_event_interruptible_timeout(), originally - * defined in <linux/wait.h> - */ - -/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ -#define wait_event_freezekillable_unsafe(wq, condition) \ -({ \ - int __retval; \ - freezer_do_not_count(); \ - __retval = wait_event_killable(wq, (condition)); \ - freezer_count_unsafe(); \ - __retval; \ -}) - #else /* !CONFIG_FREEZER */ static inline bool frozen(struct task_struct *p) { return false; } static inline bool freezing(struct task_struct *p) { return false; } @@ -281,35 +83,8 @@ static inline void thaw_kernel_threads(void) {} static inline bool try_to_freeze(void) { return false; } -static inline void freezer_do_not_count(void) {} -static inline void freezer_count(void) {} -static inline int freezer_should_skip(struct task_struct *p) { return 0; } static inline void set_freezable(void) {} -#define freezable_schedule() schedule() - -#define freezable_schedule_unsafe() schedule() - -#define freezable_schedule_timeout(timeout) schedule_timeout(timeout) - -#define freezable_schedule_timeout_interruptible(timeout) \ - schedule_timeout_interruptible(timeout) - -#define freezable_schedule_timeout_interruptible_unsafe(timeout) \ - schedule_timeout_interruptible(timeout) - -#define freezable_schedule_timeout_killable(timeout) \ - schedule_timeout_killable(timeout) - -#define freezable_schedule_timeout_killable_unsafe(timeout) \ - schedule_timeout_killable(timeout) - -#define freezable_schedule_hrtimeout_range(expires, delta, mode) \ - schedule_hrtimeout_range(expires, delta, mode) - -#define wait_event_freezekillable_unsafe(wq, condition) \ - wait_event_killable(wq, condition) - #endif /* !CONFIG_FREEZER */ #endif /* FREEZER_H_INCLUDED */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 8d82d6d32670..68ec44d6b962 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -81,25 +81,34 @@ struct task_group; */ /* Used in tsk->state: */ -#define TASK_RUNNING 0x0000 -#define TASK_INTERRUPTIBLE 0x0001 -#define TASK_UNINTERRUPTIBLE 0x0002 -#define __TASK_STOPPED 0x0004 -#define __TASK_TRACED 0x0008 +#define TASK_RUNNING 0x00000000 +#define TASK_INTERRUPTIBLE 0x00000001 +#define TASK_UNINTERRUPTIBLE 0x00000002 +#define __TASK_STOPPED 0x00000004 +#define __TASK_TRACED 0x00000008 /* Used in tsk->exit_state: */ -#define EXIT_DEAD 0x0010 -#define EXIT_ZOMBIE 0x0020 +#define EXIT_DEAD 0x00000010 +#define EXIT_ZOMBIE 0x00000020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->state again: */ -#define TASK_PARKED 0x0040 -#define TASK_DEAD 0x0080 -#define TASK_WAKEKILL 0x0100 -#define TASK_WAKING 0x0200 -#define TASK_NOLOAD 0x0400 -#define TASK_NEW 0x0800 -/* RT specific auxilliary flag to mark RT lock waiters */ -#define TASK_RTLOCK_WAIT 0x1000 -#define TASK_STATE_MAX 0x2000 +#define TASK_PARKED 0x00000040 +#define TASK_DEAD 0x00000080 +#define TASK_WAKEKILL 0x00000100 +#define TASK_WAKING 0x00000200 +#define TASK_NOLOAD 0x00000400 +#define TASK_NEW 0x00000800 +#define TASK_RTLOCK_WAIT 0x00001000 +#define TASK_FREEZABLE 0x00002000 +#define __TASK_FREEZABLE_UNSAFE (0x00004000 * IS_ENABLED(CONFIG_LOCKDEP)) +#define TASK_FROZEN 0x00008000 +#define TASK_STATE_MAX 0x00010000 + +#define TASK_ANY (TASK_STATE_MAX-1) + +/* + * DO NOT ADD ANY NEW USERS ! + */ +#define TASK_FREEZABLE_UNSAFE (TASK_FREEZABLE | __TASK_FREEZABLE_UNSAFE) /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) @@ -1713,8 +1722,9 @@ extern struct pid *cad_pid; #define PF_MEMALLOC 0x00000800 /* Allocating memory */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ +#define PF__HOLE__00004000 0x00004000 #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ -#define PF_FROZEN 0x00010000 /* Frozen for system suspend */ +#define PF__HOLE__00010000 0x00010000 #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocation requests will inherit GFP_NOFS */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocation requests will inherit GFP_NOIO */ @@ -1722,10 +1732,14 @@ extern struct pid *cad_pid; * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ +#define PF__HOLE__00800000 0x00800000 +#define PF__HOLE__01000000 0x01000000 +#define PF__HOLE__02000000 0x02000000 #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_PIN 0x10000000 /* Allocation context constrained to zones which allow long term pinning. */ -#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ +#define PF__HOLE__20000000 0x20000000 +#define PF__HOLE__40000000 0x40000000 #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ /* diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index acc62647317c..baeca2f564dc 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -252,7 +252,7 @@ int rpc_malloc(struct rpc_task *); void rpc_free(struct rpc_task *); int rpciod_up(void); void rpciod_down(void); -int __rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *); +int rpc_wait_for_completion_task(struct rpc_task *task); #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct net; void rpc_show_tasks(struct net *); @@ -264,11 +264,6 @@ extern struct workqueue_struct *xprtiod_workqueue; void rpc_prepare_task(struct rpc_task *task); gfp_t rpc_task_gfp_mask(void); -static inline int rpc_wait_for_completion_task(struct rpc_task *task) -{ - return __rpc_wait_for_completion_task(task, NULL); -} - #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS) static inline const char * rpc_qname(const struct rpc_wait_queue *q) { diff --git a/include/linux/suspend.h b/include/linux/suspend.h index be7737262d8f..cfe19a028918 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -511,8 +511,8 @@ extern bool pm_save_wakeup_count(unsigned int count); extern void pm_wakep_autosleep_enabled(bool set); extern void pm_print_active_wakeup_sources(void); -extern void lock_system_sleep(void); -extern void unlock_system_sleep(void); +extern unsigned int lock_system_sleep(void); +extern void unlock_system_sleep(unsigned int); #else /* !CONFIG_PM_SLEEP */ @@ -535,8 +535,8 @@ static inline void pm_system_wakeup(void) {} static inline void pm_wakeup_clear(bool reset) {} static inline void pm_system_irq_wakeup(unsigned int irq_number) {} -static inline void lock_system_sleep(void) {} -static inline void unlock_system_sleep(void) {} +static inline unsigned int lock_system_sleep(void) { return 0; } +static inline void unlock_system_sleep(unsigned int flags) {} #endif /* !CONFIG_PM_SLEEP */ diff --git a/include/linux/umh.h b/include/linux/umh.h index 244aff638220..5d1f6129b847 100644 --- a/include/linux/umh.h +++ b/include/linux/umh.h @@ -11,10 +11,11 @@ struct cred; struct file; -#define UMH_NO_WAIT 0 /* don't wait at all */ -#define UMH_WAIT_EXEC 1 /* wait for the exec, but not the process */ -#define UMH_WAIT_PROC 2 /* wait for the process to complete */ -#define UMH_KILLABLE 4 /* wait for EXEC/PROC killable */ +#define UMH_NO_WAIT 0x00 /* don't wait at all */ +#define UMH_WAIT_EXEC 0x01 /* wait for the exec, but not the process */ +#define UMH_WAIT_PROC 0x02 /* wait for the process to complete */ +#define UMH_KILLABLE 0x04 /* wait for EXEC/PROC killable */ +#define UMH_FREEZABLE 0x08 /* wait for EXEC/PROC freezable */ struct subprocess_info { struct work_struct work; diff --git a/include/linux/wait.h b/include/linux/wait.h index 58cfbf81447c..7f5a51aae0a7 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -281,7 +281,7 @@ static inline void wake_up_pollfree(struct wait_queue_head *wq_head) #define ___wait_is_interruptible(state) \ (!__builtin_constant_p(state) || \ - state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE) \ + (state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags); @@ -361,8 +361,8 @@ do { \ } while (0) #define __wait_event_freezable(wq_head, condition) \ - ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ - freezable_schedule()) + ___wait_event(wq_head, condition, (TASK_INTERRUPTIBLE|TASK_FREEZABLE), \ + 0, 0, schedule()) /** * wait_event_freezable - sleep (or freeze) until a condition gets true @@ -420,8 +420,8 @@ do { \ #define __wait_event_freezable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ - TASK_INTERRUPTIBLE, 0, timeout, \ - __ret = freezable_schedule_timeout(__ret)) + (TASK_INTERRUPTIBLE|TASK_FREEZABLE), 0, timeout, \ + __ret = schedule_timeout(__ret)) /* * like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid @@ -642,8 +642,8 @@ do { \ #define __wait_event_freezable_exclusive(wq, condition) \ - ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ - freezable_schedule()) + ___wait_event(wq, condition, (TASK_INTERRUPTIBLE|TASK_FREEZABLE), 1, 0,\ + schedule()) #define wait_event_freezable_exclusive(wq, condition) \ ({ \ @@ -932,6 +932,34 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *); __ret; \ }) +#define __wait_event_state(wq, condition, state) \ + ___wait_event(wq, condition, state, 0, 0, schedule()) + +/** + * wait_event_state - sleep until a condition gets true + * @wq_head: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @state: state to sleep in + * + * The process is put to sleep (@state) until the @condition evaluates to true + * or a signal is received (when allowed by @state). The @condition is checked + * each time the waitqueue @wq_head is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * The function will return -ERESTARTSYS if it was interrupted by a signal + * (when allowed by @state) and 0 if @condition evaluated to true. + */ +#define wait_event_state(wq_head, condition, state) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_state(wq_head, condition, state); \ + __ret; \ +}) + #define __wait_event_killable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_KILLABLE, 0, timeout, \ |