diff options
Diffstat (limited to 'include/linux/sched')
| -rw-r--r-- | include/linux/sched/coredump.h | 18 | ||||
| -rw-r--r-- | include/linux/sched/cputime.h | 18 | ||||
| -rw-r--r-- | include/linux/sched/deadline.h | 42 | ||||
| -rw-r--r-- | include/linux/sched/debug.h | 2 | ||||
| -rw-r--r-- | include/linux/sched/ext.h | 156 | ||||
| -rw-r--r-- | include/linux/sched/idle.h | 27 | ||||
| -rw-r--r-- | include/linux/sched/isolation.h | 22 | ||||
| -rw-r--r-- | include/linux/sched/mm.h | 26 | ||||
| -rw-r--r-- | include/linux/sched/nohz.h | 4 | ||||
| -rw-r--r-- | include/linux/sched/sd_flags.h | 8 | ||||
| -rw-r--r-- | include/linux/sched/signal.h | 24 | ||||
| -rw-r--r-- | include/linux/sched/smt.h | 2 | ||||
| -rw-r--r-- | include/linux/sched/task.h | 44 | ||||
| -rw-r--r-- | include/linux/sched/task_stack.h | 4 | ||||
| -rw-r--r-- | include/linux/sched/topology.h | 105 | ||||
| -rw-r--r-- | include/linux/sched/wake_q.h | 3 |
16 files changed, 305 insertions, 200 deletions
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 6eb65ceed213..624fda17a785 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -8,6 +8,20 @@ #define SUID_DUMP_USER 1 /* Dump as user of process */ #define SUID_DUMP_ROOT 2 /* Dump as root */ +static inline unsigned long __mm_flags_get_dumpable(const struct mm_struct *mm) +{ + /* + * By convention, dumpable bits are contained in first 32 bits of the + * bitmap, so we can simply access this first unsigned long directly. + */ + return __mm_flags_get_word(mm); +} + +static inline void __mm_flags_set_mask_dumpable(struct mm_struct *mm, int value) +{ + __mm_flags_set_mask_bits_word(mm, MMF_DUMPABLE_MASK, value); +} + extern void set_dumpable(struct mm_struct *mm, int value); /* * This returns the actual value of the suid_dumpable flag. For things @@ -22,7 +36,9 @@ static inline int __get_dumpable(unsigned long mm_flags) static inline int get_dumpable(struct mm_struct *mm) { - return __get_dumpable(mm->flags); + unsigned long flags = __mm_flags_get_dumpable(mm); + + return __get_dumpable(flags); } #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h index 5f8fd5b24a2e..e90efaf6d26e 100644 --- a/include/linux/sched/cputime.h +++ b/include/linux/sched/cputime.h @@ -2,6 +2,7 @@ #ifndef _LINUX_SCHED_CPUTIME_H #define _LINUX_SCHED_CPUTIME_H +#include <linux/static_call_types.h> #include <linux/sched/signal.h> /* @@ -180,4 +181,21 @@ static inline void prev_cputime_init(struct prev_cputime *prev) extern unsigned long long task_sched_runtime(struct task_struct *task); +#ifdef CONFIG_PARAVIRT +struct static_key; +extern struct static_key paravirt_steal_enabled; +extern struct static_key paravirt_steal_rq_enabled; + +#ifdef CONFIG_HAVE_PV_STEAL_CLOCK_GEN +u64 dummy_steal_clock(int cpu); + +DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock); + +static inline u64 paravirt_steal_clock(int cpu) +{ + return static_call(pv_steal_clock)(cpu); +} +#endif +#endif + #endif /* _LINUX_SCHED_CPUTIME_H */ diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 3a912ab42bb5..273538200a44 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -29,12 +29,48 @@ static inline bool dl_time_before(u64 a, u64 b) return (s64)(a - b) < 0; } -#ifdef CONFIG_SMP - struct root_domain; extern void dl_add_task_root_domain(struct task_struct *p); extern void dl_clear_root_domain(struct root_domain *rd); +extern void dl_clear_root_domain_cpu(int cpu); +/* + * Return whether moving DL task @p to @new_mask requires moving DL + * bandwidth accounting between root domains. This helper is specific to + * DL bandwidth move accounting semantics and is shared by + * cpuset_can_attach() and set_cpus_allowed_dl() so both paths use the + * same source root-domain test. + */ +extern bool dl_task_needs_bw_move(struct task_struct *p, + const struct cpumask *new_mask); + +extern u64 dl_cookie; +extern bool dl_bw_visited(int cpu, u64 cookie); + +static inline bool dl_server(struct sched_dl_entity *dl_se) +{ + return dl_se->dl_server; +} -#endif /* CONFIG_SMP */ +static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se) +{ + BUG_ON(dl_server(dl_se)); + return container_of(dl_se, struct task_struct, dl); +} + +/* + * Regarding the deadline, a task with implicit deadline has a relative + * deadline == relative period. A task with constrained deadline has a + * relative deadline <= relative period. + * + * We support constrained deadline tasks. However, there are some restrictions + * applied only for tasks which do not have an implicit deadline. See + * update_dl_entity() to know more about such restrictions. + * + * The dl_is_implicit() returns true if the task has an implicit deadline. + */ +static inline bool dl_is_implicit(struct sched_dl_entity *dl_se) +{ + return dl_se->dl_deadline == dl_se->dl_period; +} #endif /* _LINUX_SCHED_DEADLINE_H */ diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h index b5035afa2396..35ed4577a6cc 100644 --- a/include/linux/sched/debug.h +++ b/include/linux/sched/debug.h @@ -35,12 +35,10 @@ extern void show_stack(struct task_struct *task, unsigned long *sp, extern void sched_show_task(struct task_struct *p); -#ifdef CONFIG_SCHED_DEBUG struct seq_file; extern void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, struct seq_file *m); extern void proc_sched_set_task(struct task_struct *p); -#endif /* Attach to any functions which should be ignored in wchan output. */ #define __sched __section(".sched.text") diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 1d70a9867fb1..2129e18ada58 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -17,7 +17,18 @@ enum scx_public_consts { SCX_OPS_NAME_LEN = 128, + /* + * %SCX_SLICE_DFL is used to refill slices when the BPF scheduler misses + * to set the slice for a task that is selected for execution. + * %SCX_EV_REFILL_SLICE_DFL counts the number of times the default slice + * refill has been triggered. + * + * %SCX_SLICE_BYPASS is used as the slice for all tasks in the bypass + * mode. As making forward progress for all tasks is the main goal of + * the bypass mode, a shorter slice is used. + */ SCX_SLICE_DFL = 20 * 1000000, /* 20ms */ + SCX_SLICE_BYPASS = 5 * 1000000, /* 5ms */ SCX_SLICE_INF = U64_MAX, /* infinite, implies nohz */ }; @@ -46,10 +57,21 @@ enum scx_dsq_id_flags { SCX_DSQ_INVALID = SCX_DSQ_FLAG_BUILTIN | 0, SCX_DSQ_GLOBAL = SCX_DSQ_FLAG_BUILTIN | 1, SCX_DSQ_LOCAL = SCX_DSQ_FLAG_BUILTIN | 2, + SCX_DSQ_BYPASS = SCX_DSQ_FLAG_BUILTIN | 3, SCX_DSQ_LOCAL_ON = SCX_DSQ_FLAG_BUILTIN | SCX_DSQ_FLAG_LOCAL_ON, SCX_DSQ_LOCAL_CPU_MASK = 0xffffffffLLU, }; +struct scx_deferred_reenq_user { + struct list_head node; + u64 flags; +}; + +struct scx_dsq_pcpu { + struct scx_dispatch_q *dsq; + struct scx_deferred_reenq_user deferred_reenq_user; +}; + /* * A dispatch queue (DSQ) can be either a FIFO or p->scx.dsq_vtime ordered * queue. A built-in DSQ is always a FIFO. The built-in local DSQs are used to @@ -58,6 +80,7 @@ enum scx_dsq_id_flags { */ struct scx_dispatch_q { raw_spinlock_t lock; + struct task_struct __rcu *first_task; /* lockless peek at head */ struct list_head list; /* tasks in dispatch order */ struct rb_root priq; /* used to order by p->scx.dsq_vtime */ u32 nr; @@ -65,30 +88,62 @@ struct scx_dispatch_q { u64 id; struct rhash_head hash_node; struct llist_node free_node; + struct scx_sched *sched; + struct scx_dsq_pcpu __percpu *pcpu; struct rcu_head rcu; }; -/* scx_entity.flags */ +/* sched_ext_entity.flags */ enum scx_ent_flags { SCX_TASK_QUEUED = 1 << 0, /* on ext runqueue */ + SCX_TASK_IN_CUSTODY = 1 << 1, /* in custody, needs ops.dequeue() when leaving */ SCX_TASK_RESET_RUNNABLE_AT = 1 << 2, /* runnable_at should be reset */ SCX_TASK_DEQD_FOR_SLEEP = 1 << 3, /* last dequeue was for SLEEP */ + SCX_TASK_SUB_INIT = 1 << 4, /* task being initialized for a sub sched */ + SCX_TASK_IMMED = 1 << 5, /* task is on local DSQ with %SCX_ENQ_IMMED */ - SCX_TASK_STATE_SHIFT = 8, /* bit 8 and 9 are used to carry scx_task_state */ - SCX_TASK_STATE_BITS = 2, + /* + * Bits 8 to 10 are used to carry task state: + * + * NONE ops.init_task() not called yet + * INIT_BEGIN ops.init_task() in flight; see sched_ext_dead() + * INIT ops.init_task() succeeded, but task can be cancelled + * READY fully initialized, but not in sched_ext + * ENABLED fully initialized and in sched_ext + * DEAD terminal state set by sched_ext_dead() + */ + SCX_TASK_STATE_SHIFT = 8, + SCX_TASK_STATE_BITS = 3, SCX_TASK_STATE_MASK = ((1 << SCX_TASK_STATE_BITS) - 1) << SCX_TASK_STATE_SHIFT, - SCX_TASK_CURSOR = 1 << 31, /* iteration cursor, not a task */ -}; + SCX_TASK_NONE = 0 << SCX_TASK_STATE_SHIFT, + SCX_TASK_INIT_BEGIN = 1 << SCX_TASK_STATE_SHIFT, + SCX_TASK_INIT = 2 << SCX_TASK_STATE_SHIFT, + SCX_TASK_READY = 3 << SCX_TASK_STATE_SHIFT, + SCX_TASK_ENABLED = 4 << SCX_TASK_STATE_SHIFT, + SCX_TASK_DEAD = 5 << SCX_TASK_STATE_SHIFT, -/* scx_entity.flags & SCX_TASK_STATE_MASK */ -enum scx_task_state { - SCX_TASK_NONE, /* ops.init_task() not called yet */ - SCX_TASK_INIT, /* ops.init_task() succeeded, but task can be cancelled */ - SCX_TASK_READY, /* fully initialized, but not in sched_ext */ - SCX_TASK_ENABLED, /* fully initialized and in sched_ext */ + /* + * Bits 12 and 13 are used to carry reenqueue reason. In addition to + * %SCX_ENQ_REENQ flag, ops.enqueue() can also test for + * %SCX_TASK_REENQ_REASON_NONE to distinguish reenqueues. + * + * NONE not being reenqueued + * KFUNC reenqueued by scx_bpf_dsq_reenq() and friends + * IMMED reenqueued due to failed ENQ_IMMED + * PREEMPTED preempted while running + */ + SCX_TASK_REENQ_REASON_SHIFT = 12, + SCX_TASK_REENQ_REASON_BITS = 2, + SCX_TASK_REENQ_REASON_MASK = ((1 << SCX_TASK_REENQ_REASON_BITS) - 1) << SCX_TASK_REENQ_REASON_SHIFT, + + SCX_TASK_REENQ_NONE = 0 << SCX_TASK_REENQ_REASON_SHIFT, + SCX_TASK_REENQ_KFUNC = 1 << SCX_TASK_REENQ_REASON_SHIFT, + SCX_TASK_REENQ_IMMED = 2 << SCX_TASK_REENQ_REASON_SHIFT, + SCX_TASK_REENQ_PREEMPTED = 3 << SCX_TASK_REENQ_REASON_SHIFT, - SCX_TASK_NR_STATES, + /* iteration cursor, not a task */ + SCX_TASK_CURSOR = 1 << 31, }; /* scx_entity.dsq_flags */ @@ -96,29 +151,6 @@ enum scx_ent_dsq_flags { SCX_TASK_DSQ_ON_PRIQ = 1 << 0, /* task is queued on the priority queue of a dsq */ }; -/* - * Mask bits for scx_entity.kf_mask. Not all kfuncs can be called from - * everywhere and the following bits track which kfunc sets are currently - * allowed for %current. This simple per-task tracking works because SCX ops - * nest in a limited way. BPF will likely implement a way to allow and disallow - * kfuncs depending on the calling context which will replace this manual - * mechanism. See scx_kf_allow(). - */ -enum scx_kf_mask { - SCX_KF_UNLOCKED = 0, /* sleepable and not rq locked */ - /* ENQUEUE and DISPATCH may be nested inside CPU_RELEASE */ - SCX_KF_CPU_RELEASE = 1 << 0, /* ops.cpu_release() */ - /* ops.dequeue (in REST) may be nested inside DISPATCH */ - SCX_KF_DISPATCH = 1 << 1, /* ops.dispatch() */ - SCX_KF_ENQUEUE = 1 << 2, /* ops.enqueue() and ops.select_cpu() */ - SCX_KF_SELECT_CPU = 1 << 3, /* ops.select_cpu() */ - SCX_KF_REST = 1 << 4, /* other rq-locked operations */ - - __SCX_KF_RQ_LOCKED = SCX_KF_CPU_RELEASE | SCX_KF_DISPATCH | - SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, - __SCX_KF_TERMINAL = SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, -}; - enum scx_dsq_lnode_flags { SCX_DSQ_LNODE_ITER_CURSOR = 1 << 0, @@ -132,12 +164,31 @@ struct scx_dsq_list_node { u32 priv; /* can be used by iter cursor */ }; +#define INIT_DSQ_LIST_CURSOR(__cursor, __dsq, __flags) \ + (struct scx_dsq_list_node) { \ + .node = LIST_HEAD_INIT((__cursor).node), \ + .flags = SCX_DSQ_LNODE_ITER_CURSOR | (__flags), \ + .priv = READ_ONCE((__dsq)->seq), \ + } + +struct scx_sched; + /* * The following is embedded in task_struct and contains all fields necessary * for a task to be scheduled by SCX. */ struct sched_ext_entity { +#ifdef CONFIG_CGROUPS + /* + * Associated scx_sched. Updated either during fork or while holding + * both p->pi_lock and rq lock. + */ + struct scx_sched __rcu *sched; +#endif struct scx_dispatch_q *dsq; + atomic_long_t ops_state; + u64 ddsp_dsq_id; + u64 ddsp_enq_flags; struct scx_dsq_list_node dsq_list; /* dispatch order */ struct rb_node dsq_priq; /* p->scx.dsq_vtime order */ u32 dsq_seq; @@ -146,9 +197,8 @@ struct sched_ext_entity { u32 weight; s32 sticky_cpu; s32 holding_cpu; - u32 kf_mask; /* see scx_kf_mask above */ + s32 selected_cpu; struct task_struct *kf_tasks[2]; /* see SCX_CALL_OP_TASK() */ - atomic_long_t ops_state; struct list_head runnable_node; /* rq->scx.runnable_list */ unsigned long runnable_at; @@ -156,14 +206,12 @@ struct sched_ext_entity { #ifdef CONFIG_SCHED_CORE u64 core_sched_at; /* see scx_prio_less() */ #endif - u64 ddsp_dsq_id; - u64 ddsp_enq_flags; /* BPF scheduler modifiable fields */ /* * Runtime budget in nsecs. This is usually set through - * scx_bpf_dispatch() but can also be modified directly by the BPF + * scx_bpf_dsq_insert() but can also be modified directly by the BPF * scheduler. Automatically decreased by SCX as the task executes. On * depletion, a scheduling event is triggered. * @@ -175,10 +223,10 @@ struct sched_ext_entity { /* * Used to order tasks when dispatching to the vtime-ordered priority - * queue of a dsq. This is usually set through scx_bpf_dispatch_vtime() - * but can also be modified directly by the BPF scheduler. Modifying it - * while a task is queued on a dsq may mangle the ordering and is not - * recommended. + * queue of a dsq. This is usually set through + * scx_bpf_dsq_insert_vtime() but can also be modified directly by the + * BPF scheduler. Modifying it while a task is queued on a dsq may + * mangle the ordering and is not recommended. */ u64 dsq_vtime; @@ -202,15 +250,31 @@ struct sched_ext_entity { struct list_head tasks_node; }; -void sched_ext_free(struct task_struct *p); +void sched_ext_dead(struct task_struct *p); void print_scx_info(const char *log_lvl, struct task_struct *p); void scx_softlockup(u32 dur_s); +bool scx_hardlockup(int cpu); +bool scx_rcu_cpu_stall(void); #else /* !CONFIG_SCHED_CLASS_EXT */ -static inline void sched_ext_free(struct task_struct *p) {} +static inline void sched_ext_dead(struct task_struct *p) {} static inline void print_scx_info(const char *log_lvl, struct task_struct *p) {} static inline void scx_softlockup(u32 dur_s) {} +static inline bool scx_hardlockup(int cpu) { return false; } +static inline bool scx_rcu_cpu_stall(void) { return false; } #endif /* CONFIG_SCHED_CLASS_EXT */ + +struct scx_task_group { +#ifdef CONFIG_EXT_GROUP_SCHED + u32 flags; /* SCX_TG_* */ + u32 weight; + u64 bw_period_us; + u64 bw_quota_us; + u64 bw_burst_us; + bool idle; +#endif +}; + #endif /* _LINUX_SCHED_EXT_H */ diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h index e670ac282333..8465ff1f20d1 100644 --- a/include/linux/sched/idle.h +++ b/include/linux/sched/idle.h @@ -11,11 +11,7 @@ enum cpu_idle_type { CPU_MAX_IDLE_TYPES }; -#ifdef CONFIG_SMP extern void wake_up_if_idle(int cpu); -#else -static inline void wake_up_if_idle(int cpu) { } -#endif /* * Idle thread specific functions to determine the need_resched @@ -79,6 +75,21 @@ static __always_inline bool __must_check current_clr_polling_and_test(void) return unlikely(tif_need_resched()); } +static __always_inline void current_clr_polling(void) +{ + __current_clr_polling(); + + /* + * Ensure we check TIF_NEED_RESCHED after we clear the polling bit. + * Once the bit is cleared, we'll get IPIs with every new + * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also + * fold. + */ + smp_mb__after_atomic(); /* paired with resched_curr() */ + + preempt_fold_need_resched(); +} + #else static inline void __current_set_polling(void) { } static inline void __current_clr_polling(void) { } @@ -91,21 +102,15 @@ static inline bool __must_check current_clr_polling_and_test(void) { return unlikely(tif_need_resched()); } -#endif static __always_inline void current_clr_polling(void) { __current_clr_polling(); - /* - * Ensure we check TIF_NEED_RESCHED after we clear the polling bit. - * Once the bit is cleared, we'll get IPIs with every new - * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also - * fold. - */ smp_mb(); /* paired with resched_curr() */ preempt_fold_need_resched(); } +#endif #endif /* _LINUX_SCHED_IDLE_H */ diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index d8501f4709b5..cf0fd03dd7a2 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -2,17 +2,30 @@ #define _LINUX_SCHED_ISOLATION_H #include <linux/cpumask.h> -#include <linux/cpuset.h> #include <linux/init.h> #include <linux/tick.h> enum hk_type { + /* Inverse of boot-time isolcpus= argument */ + HK_TYPE_DOMAIN_BOOT, + /* + * Same as HK_TYPE_DOMAIN_BOOT but also includes the + * inverse of cpuset isolated partitions. As such it + * is always a subset of HK_TYPE_DOMAIN_BOOT. + */ HK_TYPE_DOMAIN, + /* Inverse of boot-time isolcpus=managed_irq argument */ HK_TYPE_MANAGED_IRQ, + /* Inverse of boot-time nohz_full= or isolcpus=nohz arguments */ HK_TYPE_KERNEL_NOISE, HK_TYPE_MAX, /* + * HK_TYPE_KTHREAD is now an alias of HK_TYPE_DOMAIN + */ + HK_TYPE_KTHREAD = HK_TYPE_DOMAIN, + + /* * The following housekeeping types are only set by the nohz_full * boot commandline option. So they can share the same value. */ @@ -21,7 +34,6 @@ enum hk_type { HK_TYPE_RCU = HK_TYPE_KERNEL_NOISE, HK_TYPE_MISC = HK_TYPE_KERNEL_NOISE, HK_TYPE_WQ = HK_TYPE_KERNEL_NOISE, - HK_TYPE_KTHREAD = HK_TYPE_KERNEL_NOISE }; #ifdef CONFIG_CPU_ISOLATION @@ -31,6 +43,7 @@ extern const struct cpumask *housekeeping_cpumask(enum hk_type type); extern bool housekeeping_enabled(enum hk_type type); extern void housekeeping_affine(struct task_struct *t, enum hk_type type); extern bool housekeeping_test_cpu(int cpu, enum hk_type type); +extern int housekeeping_update(struct cpumask *isol_mask); extern void __init housekeeping_init(void); #else @@ -58,6 +71,7 @@ static inline bool housekeeping_test_cpu(int cpu, enum hk_type type) return true; } +static inline int housekeeping_update(struct cpumask *isol_mask) { return 0; } static inline void housekeeping_init(void) { } #endif /* CONFIG_CPU_ISOLATION */ @@ -72,9 +86,7 @@ static inline bool housekeeping_cpu(int cpu, enum hk_type type) static inline bool cpu_is_isolated(int cpu) { - return !housekeeping_test_cpu(cpu, HK_TYPE_DOMAIN) || - !housekeeping_test_cpu(cpu, HK_TYPE_TICK) || - cpuset_cpu_is_isolated(cpu); + return !housekeeping_test_cpu(cpu, HK_TYPE_DOMAIN); } #endif /* _LINUX_SCHED_ISOLATION_H */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 928a626725e6..95d0040df584 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -140,7 +140,7 @@ static inline bool mmget_not_zero(struct mm_struct *mm) /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); -#ifdef CONFIG_MMU +#if defined(CONFIG_MMU) || defined(CONFIG_FUTEX_PRIVATE_HASH) /* same as above but performs the slow path from the async context. Can * be called from the atomic context as well */ @@ -178,7 +178,7 @@ static inline void mm_update_next_owner(struct mm_struct *mm) #endif extern void arch_pick_mmap_layout(struct mm_struct *mm, - struct rlimit *rlim_stack); + const struct rlimit *rlim_stack); unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, @@ -189,12 +189,11 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t); -unsigned long mm_get_unmapped_area(struct mm_struct *mm, struct file *filp, - unsigned long addr, unsigned long len, - unsigned long pgoff, unsigned long flags); +unsigned long mm_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); -unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, - struct file *filp, +unsigned long mm_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, @@ -211,7 +210,7 @@ generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long flags, vm_flags_t vm_flags); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm, - struct rlimit *rlim_stack) {} + const struct rlimit *rlim_stack) {} #endif static inline bool in_vfork(struct task_struct *tsk) @@ -318,11 +317,15 @@ static inline void might_alloc(gfp_t gfp_mask) fs_reclaim_acquire(gfp_mask); fs_reclaim_release(gfp_mask); + if (current->flags & PF_MEMALLOC) + return; + might_sleep_if(gfpflags_allow_blocking(gfp_mask)); } /** * memalloc_flags_save - Add a PF_* flag to current->flags, save old value + * @flags: Flags to add. * * This allows PF_* flags to be conveniently added, irrespective of current * value, and then the old version restored with memalloc_flags_restore(). @@ -531,6 +534,13 @@ enum { static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { + /* + * The atomic_read() below prevents CSE. The following should + * help the compiler generate more efficient code on architectures + * where sync_core_before_usermode() is a no-op. + */ + if (!IS_ENABLED(CONFIG_ARCH_HAS_SYNC_CORE_BEFORE_USERMODE)) + return; if (current->mm != mm) return; if (likely(!(atomic_read(&mm->membarrier_state) & diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h index 6d67e9a5af6b..0db7f67935fe 100644 --- a/include/linux/sched/nohz.h +++ b/include/linux/sched/nohz.h @@ -6,7 +6,7 @@ * This is the interface between the scheduler and nohz/dynticks: */ -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +#ifdef CONFIG_NO_HZ_COMMON extern void nohz_balance_enter_idle(int cpu); extern int get_nohz_timer_target(void); #else @@ -23,7 +23,7 @@ static inline void calc_load_nohz_remote(struct rq *rq) { } static inline void calc_load_nohz_stop(void) { } #endif /* CONFIG_NO_HZ_COMMON */ -#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP) +#ifdef CONFIG_NO_HZ_COMMON extern void wake_up_nohz_cpu(int cpu); #else static inline void wake_up_nohz_cpu(int cpu) { } diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index b04a5d04dee9..42839cfa2778 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -154,14 +154,6 @@ SD_FLAG(SD_ASYM_PACKING, SDF_NEEDS_GROUPS) SD_FLAG(SD_PREFER_SIBLING, SDF_NEEDS_GROUPS) /* - * sched_groups of this level overlap - * - * SHARED_PARENT: Set for all NUMA levels above NODE. - * NEEDS_GROUPS: Overlaps can only exist with more than one group. - */ -SD_FLAG(SD_OVERLAP, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS) - -/* * Cross-node balancing * * SHARED_PARENT: Set for all NUMA levels above NODE. diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index d5d03d919df8..584ae88b435e 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -132,11 +132,13 @@ struct signal_struct { */ unsigned int is_child_subreaper:1; unsigned int has_child_subreaper:1; + unsigned int autoreap:1; #ifdef CONFIG_POSIX_TIMERS /* POSIX.1b Interval Timers */ - unsigned int next_posix_timer_id; + unsigned int timer_create_restore_ids:1; + atomic_t next_posix_timer_id; struct hlist_head posix_timers; struct hlist_head ignored_posix_timers; @@ -225,6 +227,10 @@ struct signal_struct { struct tty_audit_buf *tty_audit_buf; #endif +#ifdef CONFIG_CGROUPS + struct rw_semaphore cgroup_threadgroup_rwsem; +#endif + /* * Thread is the potential origin of an oom condition; kill first on * oom @@ -732,21 +738,13 @@ static inline int thread_group_empty(struct task_struct *p) #define delay_group_leader(p) \ (thread_group_leader(p) && !thread_group_empty(p)) -extern struct sighand_struct *__lock_task_sighand(struct task_struct *task, - unsigned long *flags); - -static inline struct sighand_struct *lock_task_sighand(struct task_struct *task, - unsigned long *flags) -{ - struct sighand_struct *ret; - - ret = __lock_task_sighand(task, flags); - (void)__cond_lock(&task->sighand->siglock, ret); - return ret; -} +extern struct sighand_struct *lock_task_sighand(struct task_struct *task, + unsigned long *flags) + __cond_acquires(nonnull, &task->sighand->siglock); static inline void unlock_task_sighand(struct task_struct *task, unsigned long *flags) + __releases(&task->sighand->siglock) { spin_unlock_irqrestore(&task->sighand->siglock, *flags); } diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h index fb1e295e7e63..166b19af956f 100644 --- a/include/linux/sched/smt.h +++ b/include/linux/sched/smt.h @@ -12,7 +12,7 @@ static __always_inline bool sched_smt_active(void) return static_branch_likely(&sched_smt_present); } #else -static inline bool sched_smt_active(void) { return false; } +static __always_inline bool sched_smt_active(void) { return false; } #endif void arch_smt_update(void); diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index ca1db4b92c32..41ed884cffc9 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -63,7 +63,7 @@ extern int lockdep_tasklist_lock_is_held(void); extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); -extern int sched_fork(unsigned long clone_flags, struct task_struct *p); +extern int sched_fork(u64 clone_flags, struct task_struct *p); extern int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void sched_cancel_fork(struct task_struct *p); extern void sched_post_fork(struct task_struct *p); @@ -109,11 +109,7 @@ int kernel_wait(pid_t pid, int *stat); extern void free_task(struct task_struct *tsk); /* sched_exec is called by processes performing an exec */ -#ifdef CONFIG_SMP extern void sched_exec(void); -#else -#define sched_exec() {} -#endif static inline struct task_struct *get_task_struct(struct task_struct *t) { @@ -135,24 +131,17 @@ static inline void put_task_struct(struct task_struct *t) return; /* - * In !RT, it is always safe to call __put_task_struct(). - * Under RT, we can only call it in preemptible context. - */ - if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) { - static DEFINE_WAIT_OVERRIDE_MAP(put_task_map, LD_WAIT_SLEEP); - - lock_map_acquire_try(&put_task_map); - __put_task_struct(t); - lock_map_release(&put_task_map); - return; - } - - /* - * under PREEMPT_RT, we can't call put_task_struct + * Under PREEMPT_RT, we can't call __put_task_struct * in atomic context because it will indirectly - * acquire sleeping locks. + * acquire sleeping locks. The same is true if the + * current process has a mutex enqueued (blocked on + * a PI chain). + * + * In !RT, it is always safe to call __put_task_struct(). + * Though, in order to simplify the code, resort to the + * deferred call too. * - * call_rcu() will schedule delayed_put_task_struct_rcu() + * call_rcu() will schedule __put_task_struct_rcu_cb() * to be called in process context. * * __put_task_struct() is called when @@ -165,7 +154,7 @@ static inline void put_task_struct(struct task_struct *t) * * delayed_free_task() also uses ->rcu, but it is only called * when it fails to fork a process. Therefore, there is no - * way it can conflict with put_task_struct(). + * way it can conflict with __put_task_struct(). */ call_rcu(&t->rcu, __put_task_struct_rcu_cb); } @@ -221,20 +210,23 @@ static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) * pins the final release of task.io_context. Also protects ->cpuset and * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist. * - * Nests both inside and outside of read_lock(&tasklist_lock). - * It must not be nested with write_lock_irq(&tasklist_lock), - * neither inside nor outside. + * Nests inside of read_lock(&tasklist_lock). It must not be nested with + * write_lock_irq(&tasklist_lock), neither inside nor outside. */ static inline void task_lock(struct task_struct *p) + __acquires(&p->alloc_lock) { spin_lock(&p->alloc_lock); } static inline void task_unlock(struct task_struct *p) + __releases(&p->alloc_lock) { spin_unlock(&p->alloc_lock); } -DEFINE_GUARD(task_lock, struct task_struct *, task_lock(_T), task_unlock(_T)) +DEFINE_LOCK_GUARD_1(task_lock, struct task_struct, task_lock(_T->lock), task_unlock(_T->lock)) +DECLARE_LOCK_GUARD_1_ATTRS(task_lock, __acquires(&_T->alloc_lock), __releases(&(*(struct task_struct **)_T)->alloc_lock)) +#define class_task_lock_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(task_lock, _T) #endif /* _LINUX_SCHED_TASK_H */ diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index cffad65bdc6a..1fab7e9043a3 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -53,7 +53,7 @@ static inline void setup_thread_stack(struct task_struct *p, struct task_struct * When the stack grows up, this is the highest address. * Beyond that position, we corrupt data on the next page. */ -static inline unsigned long *end_of_stack(struct task_struct *p) +static inline unsigned long *end_of_stack(const struct task_struct *p) { #ifdef CONFIG_STACK_GROWSUP return (unsigned long *)((unsigned long)task_thread_info(p) + THREAD_SIZE) - 1; @@ -106,7 +106,6 @@ static inline unsigned long stack_not_used(struct task_struct *p) #endif extern void set_task_stack_end_magic(struct task_struct *tsk); -#ifndef __HAVE_ARCH_KSTACK_END static inline int kstack_end(void *addr) { /* Reliable end of stack detection: @@ -114,6 +113,5 @@ static inline int kstack_end(void *addr) */ return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*))); } -#endif #endif /* _LINUX_SCHED_TASK_STACK_H */ diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 7f3dbafe1817..36553e14866d 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -9,7 +9,6 @@ /* * sched-domains (multiprocessor balancing) declarations: */ -#ifdef CONFIG_SMP /* Generate SD flag indexes */ #define SD_FLAG(name, mflags) __##name, @@ -25,43 +24,30 @@ enum { }; #undef SD_FLAG -#ifdef CONFIG_SCHED_DEBUG - struct sd_flag_debug { unsigned int meta_flags; char *name; }; extern const struct sd_flag_debug sd_flag_debug[]; -#endif +struct sched_domain_topology_level; #ifdef CONFIG_SCHED_SMT -static inline int cpu_smt_flags(void) -{ - return SD_SHARE_CPUCAPACITY | SD_SHARE_LLC; -} +extern int cpu_smt_flags(void); +extern const struct cpumask *tl_smt_mask(struct sched_domain_topology_level *tl, int cpu); #endif #ifdef CONFIG_SCHED_CLUSTER -static inline int cpu_cluster_flags(void) -{ - return SD_CLUSTER | SD_SHARE_LLC; -} +extern int cpu_cluster_flags(void); +extern const struct cpumask *tl_cls_mask(struct sched_domain_topology_level *tl, int cpu); #endif #ifdef CONFIG_SCHED_MC -static inline int cpu_core_flags(void) -{ - return SD_SHARE_LLC; -} +extern int cpu_core_flags(void); +extern const struct cpumask *tl_mc_mask(struct sched_domain_topology_level *tl, int cpu); #endif -#ifdef CONFIG_NUMA -static inline int cpu_numa_flags(void) -{ - return SD_NUMA; -} -#endif +extern const struct cpumask *tl_pkg_mask(struct sched_domain_topology_level *tl, int cpu); extern int arch_asym_cpu_priority(int cpu); @@ -106,6 +92,10 @@ struct sched_domain { unsigned int nr_balance_failed; /* initialise to 0 */ /* idle_balance() stats */ + unsigned int newidle_call; + unsigned int newidle_success; + unsigned int newidle_ratio; + u64 newidle_stamp; u64 max_newidle_lb_cost; unsigned long last_decay_max_lb_cost; @@ -152,24 +142,32 @@ struct sched_domain { unsigned int span_weight; /* - * Span of all CPUs in this domain. + * See sched_domain_span(), on why flex arrays are broken. * - * NOTE: this field is variable length. (Allocated dynamically - * by attaching extra space to the end of the structure, - * depending on how many CPUs the kernel has booted up with) - */ unsigned long span[]; + */ }; static inline struct cpumask *sched_domain_span(struct sched_domain *sd) { - return to_cpumask(sd->span); + /* + * Turns out that C flexible arrays are fundamentally broken since it + * is allowed for offsetof(*sd, span) < sizeof(*sd), this means that + * structure initialzation *sd = { ... }; which writes every byte + * inside sizeof(*type), will over-write the start of the flexible + * array. + * + * Luckily, the way we allocate sched_domain is by: + * + * sizeof(*sd) + cpumask_size() + * + * this means that we have sufficient space for the whole flex array + * *outside* of sizeof(*sd). So use that, and avoid using sd->span. + */ + unsigned long *bitmap = (void *)sd + sizeof(*sd); + return to_cpumask(bitmap); } -extern void partition_sched_domains_locked(int ndoms_new, - cpumask_var_t doms_new[], - struct sched_domain_attr *dattr_new); - extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new); @@ -181,14 +179,11 @@ bool cpus_equal_capacity(int this_cpu, int that_cpu); bool cpus_share_cache(int this_cpu, int that_cpu); bool cpus_share_resources(int this_cpu, int that_cpu); -typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); +typedef const struct cpumask *(*sched_domain_mask_f)(struct sched_domain_topology_level *tl, int cpu); typedef int (*sched_domain_flags_f)(void); -#define SDTL_OVERLAP 0x01 - struct sd_data { struct sched_domain *__percpu *sd; - struct sched_domain_shared *__percpu *sds; struct sched_group *__percpu *sg; struct sched_group_capacity *__percpu *sgc; }; @@ -196,48 +191,16 @@ struct sd_data { struct sched_domain_topology_level { sched_domain_mask_f mask; sched_domain_flags_f sd_flags; - int flags; int numa_level; struct sd_data data; char *name; }; extern void __init set_sched_topology(struct sched_domain_topology_level *tl); +extern void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio); -# define SD_INIT_NAME(type) .name = #type - -#else /* CONFIG_SMP */ - -struct sched_domain_attr; - -static inline void -partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[], - struct sched_domain_attr *dattr_new) -{ -} - -static inline void -partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], - struct sched_domain_attr *dattr_new) -{ -} - -static inline bool cpus_equal_capacity(int this_cpu, int that_cpu) -{ - return true; -} - -static inline bool cpus_share_cache(int this_cpu, int that_cpu) -{ - return true; -} - -static inline bool cpus_share_resources(int this_cpu, int that_cpu) -{ - return true; -} - -#endif /* !CONFIG_SMP */ +#define SDTL_INIT(maskfn, flagsfn, dname) ((struct sched_domain_topology_level) \ + { .mask = maskfn, .sd_flags = flagsfn, .name = #dname }) #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) extern void rebuild_sched_domains_energy(void); diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h index 0f28b4623ad4..765bbc3d54be 100644 --- a/include/linux/sched/wake_q.h +++ b/include/linux/sched/wake_q.h @@ -66,6 +66,7 @@ extern void wake_up_q(struct wake_q_head *head); /* Spin unlock helpers to unlock and call wake_up_q with preempt disabled */ static inline void raw_spin_unlock_wake(raw_spinlock_t *lock, struct wake_q_head *wake_q) + __releases(lock) { guard(preempt)(); raw_spin_unlock(lock); @@ -77,6 +78,7 @@ void raw_spin_unlock_wake(raw_spinlock_t *lock, struct wake_q_head *wake_q) static inline void raw_spin_unlock_irq_wake(raw_spinlock_t *lock, struct wake_q_head *wake_q) + __releases(lock) { guard(preempt)(); raw_spin_unlock_irq(lock); @@ -89,6 +91,7 @@ void raw_spin_unlock_irq_wake(raw_spinlock_t *lock, struct wake_q_head *wake_q) static inline void raw_spin_unlock_irqrestore_wake(raw_spinlock_t *lock, unsigned long flags, struct wake_q_head *wake_q) + __releases(lock) { guard(preempt)(); raw_spin_unlock_irqrestore(lock, flags); |