diff options
Diffstat (limited to 'include/linux/sched.h')
| -rw-r--r-- | include/linux/sched.h | 550 |
1 files changed, 387 insertions, 163 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h index d07d3645d2d5..d395f2810fac 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -13,7 +13,7 @@ #include <asm/processor.h> #include <linux/thread_info.h> #include <linux/preempt.h> -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/cache.h> #include <linux/irqflags_types.h> @@ -34,19 +34,24 @@ #include <linux/sched/prio.h> #include <linux/sched/types.h> #include <linux/signal_types.h> +#include <linux/spinlock.h> #include <linux/syscall_user_dispatch_types.h> #include <linux/mm_types_task.h> #include <linux/netdevice_xmit.h> #include <linux/task_io_accounting.h> #include <linux/posix-timers_types.h> #include <linux/restart_block.h> -#include <uapi/linux/rseq.h> +#include <linux/rseq_types.h> #include <linux/seqlock_types.h> #include <linux/kcsan.h> #include <linux/rv.h> -#include <linux/livepatch_sched.h> #include <linux/uidgid_types.h> +#include <linux/tracepoint-defs.h> +#include <linux/unwind_deferred_types.h> #include <asm/kmap_size.h> +#ifndef COMPILE_OFFSETS +#include <generated/rq-offsets.h> +#endif /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; @@ -65,6 +70,7 @@ struct mempolicy; struct nameidata; struct nsproxy; struct perf_event_context; +struct perf_ctx_data; struct pid_namespace; struct pipe_inode_info; struct rcu_node; @@ -82,6 +88,8 @@ struct task_group; struct task_struct; struct user_event_mm; +#include <linux/sched/ext.h> + /* * Task state bitmask. NOTE! These bits are also * encoded in fs/proc/array.c: get_task_state(). @@ -149,8 +157,9 @@ struct user_event_mm; * Special states are those that do not use the normal wait-loop pattern. See * the comment with set_special_state(). */ -#define is_special_task_state(state) \ - ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD)) +#define is_special_task_state(state) \ + ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | \ + TASK_DEAD | TASK_FROZEN)) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP # define debug_normal_state_change(state_value) \ @@ -183,6 +192,12 @@ struct user_event_mm; # define debug_rtlock_wait_restore_state() do { } while (0) #endif +#define trace_set_current_state(state_value) \ + do { \ + if (tracepoint_enabled(sched_set_state_tp)) \ + __trace_set_current_state(state_value); \ + } while (0) + /* * set_current_state() includes a barrier so that the write of current->__state * is correctly serialised wrt the caller's subsequent test of whether to @@ -223,12 +238,14 @@ struct user_event_mm; #define __set_current_state(state_value) \ do { \ debug_normal_state_change((state_value)); \ + trace_set_current_state(state_value); \ WRITE_ONCE(current->__state, (state_value)); \ } while (0) #define set_current_state(state_value) \ do { \ debug_normal_state_change((state_value)); \ + trace_set_current_state(state_value); \ smp_store_mb(current->__state, (state_value)); \ } while (0) @@ -244,6 +261,7 @@ struct user_event_mm; \ raw_spin_lock_irqsave(¤t->pi_lock, flags); \ debug_special_state_change((state_value)); \ + trace_set_current_state(state_value); \ WRITE_ONCE(current->__state, (state_value)); \ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) @@ -279,6 +297,7 @@ struct user_event_mm; raw_spin_lock(¤t->pi_lock); \ current->saved_state = current->__state; \ debug_rtlock_wait_set_state(); \ + trace_set_current_state(TASK_RTLOCK_WAIT); \ WRITE_ONCE(current->__state, TASK_RTLOCK_WAIT); \ raw_spin_unlock(¤t->pi_lock); \ } while (0); @@ -288,6 +307,7 @@ struct user_event_mm; lockdep_assert_irqs_disabled(); \ raw_spin_lock(¤t->pi_lock); \ debug_rtlock_wait_restore_state(); \ + trace_set_current_state(current->saved_state); \ WRITE_ONCE(current->__state, current->saved_state); \ current->saved_state = TASK_RUNNING; \ raw_spin_unlock(¤t->pi_lock); \ @@ -324,6 +344,12 @@ extern void io_schedule_finish(int token); extern long io_schedule_timeout(long timeout); extern void io_schedule(void); +/* wrapper functions to trace from this header file */ +DECLARE_TRACEPOINT(sched_set_state_tp); +extern void __trace_set_current_state(int state_value); +DECLARE_TRACEPOINT(sched_set_need_resched_tp); +extern void __trace_set_need_resched(struct task_struct *curr, int tif); + /** * struct prev_cputime - snapshot of system and user cputime * @utime: time spent in user mode @@ -376,10 +402,10 @@ enum uclamp_id { UCLAMP_CNT }; -#ifdef CONFIG_SMP extern struct root_domain def_root_domain; extern struct mutex sched_domains_mutex; -#endif +extern void sched_domains_mutex_lock(void); +extern void sched_domains_mutex_unlock(void); struct sched_param { int sched_priority; @@ -395,6 +421,12 @@ struct sched_info { /* Time spent waiting on a runqueue: */ unsigned long long run_delay; + /* Max time spent waiting on a runqueue: */ + unsigned long long max_run_delay; + + /* Min time spent waiting on a runqueue: */ + unsigned long long min_run_delay; + /* Timestamps: */ /* When did we last run on a CPU? */ @@ -541,15 +573,28 @@ struct sched_entity { struct rb_node run_node; u64 deadline; u64 min_vruntime; + u64 min_slice; struct list_head group_node; - unsigned int on_rq; + unsigned char on_rq; + unsigned char sched_delayed; + unsigned char rel_deadline; + unsigned char custom_slice; + /* hole */ u64 exec_start; u64 sum_exec_runtime; u64 prev_sum_exec_runtime; u64 vruntime; - s64 vlag; + union { + /* + * When !@on_rq this field is vlag. + * When cfs_rq->curr == se (which implies @on_rq) + * this field is vprot. See protect_slice(). + */ + s64 vlag; + u64 vprot; + }; u64 slice; u64 nr_migrations; @@ -565,7 +610,6 @@ struct sched_entity { unsigned long runnable_weight; #endif -#ifdef CONFIG_SMP /* * Per entity load average tracking. * @@ -573,7 +617,6 @@ struct sched_entity { * collide with read-mostly values above. */ struct sched_avg avg; -#endif }; struct sched_rt_entity { @@ -594,8 +637,8 @@ struct sched_rt_entity { #endif } __randomize_layout; -typedef bool (*dl_server_has_tasks_f)(struct sched_dl_entity *); -typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *); +struct rq_flags; +typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *, struct rq_flags *rf); struct sched_dl_entity { struct rb_node rb_node; @@ -639,12 +682,36 @@ struct sched_dl_entity { * * @dl_overrun tells if the task asked to be informed about runtime * overruns. + * + * @dl_server tells if this is a server entity. + * + * @dl_server_active tells if the dlserver is active(started). + * dlserver is started on first cfs enqueue on an idle runqueue + * and is stopped when a dequeue results in 0 cfs tasks on the + * runqueue. In other words, dlserver is active only when cpu's + * runqueue has atleast one cfs task. + * + * @dl_defer tells if this is a deferred or regular server. For + * now only defer server exists. + * + * @dl_defer_armed tells if the deferrable server is waiting + * for the replenishment timer to activate it. + * + * @dl_defer_running tells if the deferrable server is actually + * running, skipping the defer phase. + * + * @dl_defer_idle tracks idle state */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; unsigned int dl_server : 1; + unsigned int dl_server_active : 1; + unsigned int dl_defer : 1; + unsigned int dl_defer_armed : 1; + unsigned int dl_defer_running : 1; + unsigned int dl_defer_idle : 1; /* * Bandwidth enforcement timer. Each -deadline task has its @@ -666,13 +733,9 @@ struct sched_dl_entity { * dl_server_update(). * * @rq the runqueue this server is for - * - * @server_has_tasks() returns true if @server_pick return a - * runnable task. */ struct rq *rq; - dl_server_has_tasks_f server_has_tasks; - dl_server_pick_f server_pick; + dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES /* @@ -736,6 +799,12 @@ enum perf_event_task_context { perf_nr_task_contexts, }; +/* + * Number of contexts where an event can trigger: + * task, softirq, hardirq, nmi. + */ +#define PERF_NR_CONTEXTS 4 + struct wake_q_node { struct wake_q_node *next; }; @@ -776,7 +845,6 @@ struct task_struct { struct alloc_tag *alloc_tag; #endif -#ifdef CONFIG_SMP int on_cpu; struct __call_single_node wake_entry; unsigned int wakee_flips; @@ -792,7 +860,6 @@ struct task_struct { */ int recent_used_cpu; int wake_cpu; -#endif int on_rq; int prio; @@ -804,6 +871,9 @@ struct task_struct { struct sched_rt_entity rt; struct sched_dl_entity dl; struct sched_dl_entity *dl_server; +#ifdef CONFIG_SCHED_CLASS_EXT + struct sched_ext_entity scx; +#endif const struct sched_class *sched_class; #ifdef CONFIG_SCHED_CORE @@ -814,6 +884,11 @@ struct task_struct { #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; +#ifdef CONFIG_CFS_BANDWIDTH + struct callback_head sched_throttle_work; + struct list_head throttle_node; + bool throttled; +#endif #endif @@ -848,9 +923,7 @@ struct task_struct { cpumask_t *user_cpus_ptr; cpumask_t cpus_mask; void *migration_pending; -#ifdef CONFIG_SMP unsigned short migration_disabled; -#endif unsigned short migration_flags; #ifdef CONFIG_PREEMPT_RCU @@ -882,10 +955,8 @@ struct task_struct { struct sched_info sched_info; struct list_head tasks; -#ifdef CONFIG_SMP struct plist_node pushable_tasks; struct rb_node pushable_dl_tasks; -#endif struct mm_struct *mm; struct mm_struct *active_mm; @@ -906,6 +977,7 @@ struct task_struct { unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; + unsigned sched_task_hot:1; /* Force alignment to the next boundary: */ unsigned :0; @@ -936,7 +1008,7 @@ struct task_struct { #ifndef TIF_RESTORE_SIGMASK unsigned restore_sigmask:1; #endif -#ifdef CONFIG_MEMCG +#ifdef CONFIG_MEMCG_V1 unsigned in_user_fault:1; #endif #ifdef CONFIG_LRU_GEN @@ -970,13 +1042,14 @@ struct task_struct { #ifdef CONFIG_ARCH_HAS_CPU_PASID unsigned pasid_activated:1; #endif -#ifdef CONFIG_CPU_SUP_INTEL +#ifdef CONFIG_X86_BUS_LOCK_DETECT unsigned reported_split_lock:1; #endif #ifdef CONFIG_TASK_DELAY_ACCT /* delay due to memory thrashing */ unsigned in_thrashing:1; #endif + unsigned in_nf_duplicate:1; #ifdef CONFIG_PREEMPT_RT struct netdev_xmit net_xmit; #endif @@ -1090,9 +1163,12 @@ struct task_struct { /* * executable name, excluding path. * - * - normally initialized setup_new_exec() - * - access it with [gs]et_task_comm() - * - lock it with task_lock() + * - normally initialized begin_new_exec() + * - set it with set_task_comm() + * - strscpy_pad() to ensure it is always NUL-terminated and + * zero-padded + * - task_lock() to ensure the operation is atomic and the name is + * fully updated. */ char comm[TASK_COMM_LEN]; @@ -1164,9 +1240,14 @@ struct task_struct { struct rt_mutex_waiter *pi_blocked_on; #endif -#ifdef CONFIG_DEBUG_MUTEXES - /* Mutex deadlock detection: */ - struct mutex_waiter *blocked_on; + struct mutex *blocked_on; /* lock we're blocked on */ + +#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER + /* + * Encoded lock address causing task block (lower 2 bits = type from + * <linux/hung_task.h>). Accessed via hung_task_*() helpers. + */ + unsigned long blocker; #endif #ifdef CONFIG_DEBUG_ATOMIC_SLEEP @@ -1237,14 +1318,16 @@ struct task_struct { /* Sequence number to catch updates: */ seqcount_spinlock_t mems_allowed_seq; int cpuset_mem_spread_rotor; - int cpuset_slab_spread_rotor; #endif #ifdef CONFIG_CGROUPS /* Control Group info protected by css_set_lock: */ struct css_set __rcu *cgroups; /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; -#endif +#ifdef CONFIG_PREEMPT_RT + struct llist_node cg_dead_lnode; +#endif /* CONFIG_PREEMPT_RT */ +#endif /* CONFIG_CGROUPS */ #ifdef CONFIG_X86_CPU_RESCTRL u32 closid; u32 rmid; @@ -1260,9 +1343,11 @@ struct task_struct { unsigned int futex_state; #endif #ifdef CONFIG_PERF_EVENTS + u8 perf_recursion[PERF_NR_CONTEXTS]; struct perf_event_context *perf_event_ctxp; struct mutex perf_event_mutex; struct list_head perf_event_list; + struct perf_ctx_data __rcu *perf_ctx_data; #endif #ifdef CONFIG_DEBUG_PREEMPT unsigned long preempt_disable_ip; @@ -1324,24 +1409,8 @@ struct task_struct { unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ -#ifdef CONFIG_RSEQ - struct rseq __user *rseq; - u32 rseq_len; - u32 rseq_sig; - /* - * RmW on rseq_event_mask must be performed atomically - * with respect to preemption. - */ - unsigned long rseq_event_mask; -#endif - -#ifdef CONFIG_SCHED_MM_CID - int mm_cid; /* Current cid in mm */ - int last_mm_cid; /* Most recent cid in mm */ - int migrate_from_cpu; - int mm_cid_active; /* Whether cid bitmap is active */ - struct callback_head cid_work; -#endif + struct rseq_data rseq; + struct sched_mm_cid mm_cid; struct tlbflush_unmap_batch tlb_ubc; @@ -1406,10 +1475,11 @@ struct task_struct { int curr_ret_depth; /* Stack of return addresses for return function tracing: */ - struct ftrace_ret_stack *ret_stack; + unsigned long *ret_stack; /* Timestamp for last schedule: */ unsigned long long ftrace_timestamp; + unsigned long long ftrace_sleeptime; /* * Number of functions that haven't been traced @@ -1451,17 +1521,18 @@ struct task_struct { unsigned int kcov_softirq; #endif -#ifdef CONFIG_MEMCG +#ifdef CONFIG_MEMCG_V1 struct mem_cgroup *memcg_in_oom; +#endif +#ifdef CONFIG_MEMCG /* Number of pages to reclaim on returning to userland: */ unsigned int memcg_nr_pages_over_high; /* Used by memcontrol for targeted memcg charge: */ struct mem_cgroup *active_memcg; -#endif -#ifdef CONFIG_MEMCG_KMEM + /* Cache for current->cgroups->memcg->objcg lookups: */ struct obj_cgroup *objcg; #endif @@ -1513,8 +1584,10 @@ struct task_struct { /* Used by BPF for per-TASK xdp storage */ struct bpf_net_context *bpf_net_context; -#ifdef CONFIG_GCC_PLUGIN_STACKLEAK +#ifdef CONFIG_KSTACK_ERASE unsigned long lowest_stack; +#endif +#ifdef CONFIG_KSTACK_ERASE_METRICS unsigned long prev_lowest_stack; #endif @@ -1548,34 +1621,42 @@ struct task_struct { #ifdef CONFIG_RV /* - * Per-task RV monitor. Nowadays fixed in RV_PER_TASK_MONITORS. - * If we find justification for more monitors, we can think - * about adding more or developing a dynamic method. So far, - * none of these are justified. + * Per-task RV monitor, fixed in CONFIG_RV_PER_TASK_MONITORS. + * If memory becomes a concern, we can think about a dynamic method. */ - union rv_task_monitor rv[RV_PER_TASK_MONITORS]; + union rv_task_monitor rv[CONFIG_RV_PER_TASK_MONITORS]; #endif #ifdef CONFIG_USER_EVENTS struct user_event_mm *user_event_mm; #endif - /* - * New fields for task_struct should be added above here, so that - * they are included in the randomized portion of task_struct. - */ - randomized_struct_fields_end +#ifdef CONFIG_UNWIND_USER + struct unwind_task_info unwind_info; +#endif /* CPU-specific state of this task: */ struct thread_struct thread; /* - * WARNING: on x86, 'thread_struct' contains a variable-sized - * structure. It *MUST* be at the end of 'task_struct'. - * - * Do not put anything below here! + * New fields for task_struct should be added above here, so that + * they are included in the randomized portion of task_struct. */ -}; + randomized_struct_fields_end +} __attribute__ ((aligned (64))); + +#ifdef CONFIG_SCHED_PROXY_EXEC +DECLARE_STATIC_KEY_TRUE(__sched_proxy_exec); +static inline bool sched_proxy_exec(void) +{ + return static_branch_likely(&__sched_proxy_exec); +} +#else +static inline bool sched_proxy_exec(void) +{ + return false; +} +#endif #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) @@ -1594,8 +1675,9 @@ static inline unsigned int __task_state_index(unsigned int tsk_state, * We're lying here, but rather than expose a completely new task state * to userspace, we can make this appear as if the task has gone through * a regular rt_mutex_lock() call. + * Report frozen tasks as uninterruptible. */ - if (tsk_state & TASK_RTLOCK_WAIT) + if ((tsk_state & TASK_RTLOCK_WAIT) || (tsk_state & TASK_FROZEN)) state = TASK_UNINTERRUPTIBLE; return fls(state); @@ -1610,7 +1692,7 @@ static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; - BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1); + BUILD_BUG_ON(TASK_REPORT_MAX * 2 != 1 << (sizeof(state_char) - 1)); return state_char[state]; } @@ -1641,7 +1723,7 @@ extern struct pid *cad_pid; #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ #define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ -#define PF__HOLE__00010000 0x00010000 +#define PF_KCOMPACTD 0x00010000 /* I am kcompactd */ #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */ @@ -1649,8 +1731,8 @@ 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_MEMALLOC_NORECLAIM 0x00800000 /* All allocation requests will clear __GFP_DIRECT_RECLAIM */ -#define PF_MEMALLOC_NOWARN 0x01000000 /* All allocation requests will inherit __GFP_NOWARN */ +#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 */ @@ -1690,12 +1772,8 @@ extern struct pid *cad_pid; static __always_inline bool is_percpu_thread(void) { -#ifdef CONFIG_SMP return (current->flags & PF_NO_SETAFFINITY) && (current->nr_cpus_allowed == 1); -#else - return true; -#endif } /* Per-process atomic flags. */ @@ -1760,10 +1838,9 @@ extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpu extern int task_can_attach(struct task_struct *p); extern int dl_bw_alloc(int cpu, u64 dl_bw); extern void dl_bw_free(int cpu, u64 dl_bw); -#ifdef CONFIG_SMP -/* do_set_cpus_allowed() - consider using set_cpus_allowed_ptr() instead */ -extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); +/* set_cpus_allowed_force() - consider using set_cpus_allowed_ptr() instead */ +extern void set_cpus_allowed_force(struct task_struct *p, const struct cpumask *new_mask); /** * set_cpus_allowed_ptr - set CPU affinity mask of a task @@ -1778,32 +1855,6 @@ extern void release_user_cpus_ptr(struct task_struct *p); extern int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask); extern void force_compatible_cpus_allowed_ptr(struct task_struct *p); extern void relax_compatible_cpus_allowed_ptr(struct task_struct *p); -#else -static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) -{ -} -static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) -{ - if (!cpumask_test_cpu(0, new_mask)) - return -EINVAL; - return 0; -} -static inline int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node) -{ - if (src->user_cpus_ptr) - return -EINVAL; - return 0; -} -static inline void release_user_cpus_ptr(struct task_struct *p) -{ - WARN_ON(p->user_cpus_ptr); -} - -static inline int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask) -{ - return 0; -} -#endif extern int yield_to(struct task_struct *p, bool preempt); extern void set_user_nice(struct task_struct *p, long nice); @@ -1828,6 +1879,7 @@ extern int sched_setscheduler(struct task_struct *, int, const struct sched_para extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern void sched_set_fifo(struct task_struct *p); extern void sched_set_fifo_low(struct task_struct *p); +extern void sched_set_fifo_secondary(struct task_struct *p); extern void sched_set_normal(struct task_struct *p, int nice); extern int sched_setattr(struct task_struct *, const struct sched_attr *); extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *); @@ -1865,7 +1917,7 @@ extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)]; #ifdef CONFIG_THREAD_INFO_IN_TASK # define task_thread_info(task) (&(task)->thread_info) -#elif !defined(__HAVE_THREAD_FUNCTIONS) +#else # define task_thread_info(task) ((struct thread_info *)(task)->stack) #endif @@ -1892,26 +1944,33 @@ extern int wake_up_state(struct task_struct *tsk, unsigned int state); extern int wake_up_process(struct task_struct *tsk); extern void wake_up_new_task(struct task_struct *tsk); -#ifdef CONFIG_SMP extern void kick_process(struct task_struct *tsk); -#else -static inline void kick_process(struct task_struct *tsk) { } -#endif extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec); +#define set_task_comm(tsk, from) ({ \ + BUILD_BUG_ON(sizeof(from) != TASK_COMM_LEN); \ + __set_task_comm(tsk, from, false); \ +}) -static inline void set_task_comm(struct task_struct *tsk, const char *from) -{ - __set_task_comm(tsk, from, false); -} - -extern char *__get_task_comm(char *to, size_t len, struct task_struct *tsk); +/* + * - Why not use task_lock()? + * User space can randomly change their names anyway, so locking for readers + * doesn't make sense. For writers, locking is probably necessary, as a race + * condition could lead to long-term mixed results. + * The strscpy_pad() in __set_task_comm() can ensure that the task comm is + * always NUL-terminated and zero-padded. Therefore the race condition between + * reader and writer is not an issue. + * + * - BUILD_BUG_ON() can help prevent the buf from being truncated. + * Since the callers don't perform any return value checks, this safeguard is + * necessary. + */ #define get_task_comm(buf, tsk) ({ \ - BUILD_BUG_ON(sizeof(buf) != TASK_COMM_LEN); \ - __get_task_comm(buf, sizeof(buf), tsk); \ + BUILD_BUG_ON(sizeof(buf) < TASK_COMM_LEN); \ + strscpy_pad(buf, (tsk)->comm); \ + buf; \ }) -#ifdef CONFIG_SMP static __always_inline void scheduler_ipi(void) { /* @@ -1921,9 +1980,6 @@ static __always_inline void scheduler_ipi(void) */ preempt_fold_need_resched(); } -#else -static inline void scheduler_ipi(void) { } -#endif extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state); @@ -1964,12 +2020,16 @@ static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag) static inline void set_tsk_need_resched(struct task_struct *tsk) { + if (tracepoint_enabled(sched_set_need_resched_tp) && + !test_tsk_thread_flag(tsk, TIF_NEED_RESCHED)) + __trace_set_need_resched(tsk, TIF_NEED_RESCHED); set_tsk_thread_flag(tsk,TIF_NEED_RESCHED); } static inline void clear_tsk_need_resched(struct task_struct *tsk) { - clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED); + atomic_long_andnot(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY, + (atomic_long_t *)&task_thread_info(tsk)->flags); } static inline int test_tsk_need_resched(struct task_struct *tsk) @@ -1977,6 +2037,13 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); } +static inline void set_need_resched_current(void) +{ + lockdep_assert_irqs_disabled(); + set_tsk_need_resched(current); + set_preempt_need_resched(); +} + /* * cond_resched() and cond_resched_lock(): latency reduction via * explicit rescheduling in places that are safe. The return @@ -1988,9 +2055,6 @@ extern int __cond_resched(void); #if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) -void sched_dynamic_klp_enable(void); -void sched_dynamic_klp_disable(void); - DECLARE_STATIC_CALL(cond_resched, __cond_resched); static __always_inline int _cond_resched(void) @@ -2011,7 +2075,6 @@ static __always_inline int _cond_resched(void) static inline int _cond_resched(void) { - klp_sched_try_switch(); return __cond_resched(); } @@ -2021,7 +2084,6 @@ static inline int _cond_resched(void) static inline int _cond_resched(void) { - klp_sched_try_switch(); return 0; } @@ -2070,46 +2132,71 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock); __cond_resched_rwlock_write(lock); \ }) -#ifdef CONFIG_PREEMPT_DYNAMIC - -extern bool preempt_model_none(void); -extern bool preempt_model_voluntary(void); -extern bool preempt_model_full(void); +#ifndef CONFIG_PREEMPT_RT +static inline struct mutex *__get_task_blocked_on(struct task_struct *p) +{ + struct mutex *m = p->blocked_on; -#else + if (m) + lockdep_assert_held_once(&m->wait_lock); + return m; +} -static inline bool preempt_model_none(void) +static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m) { - return IS_ENABLED(CONFIG_PREEMPT_NONE); + struct mutex *blocked_on = READ_ONCE(p->blocked_on); + + 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); + /* + * 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(blocked_on && blocked_on != m); + WRITE_ONCE(p->blocked_on, m); } -static inline bool preempt_model_voluntary(void) + +static inline void set_task_blocked_on(struct task_struct *p, struct mutex *m) { - return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY); + guard(raw_spinlock_irqsave)(&m->wait_lock); + __set_task_blocked_on(p, m); } -static inline bool preempt_model_full(void) + +static inline void __clear_task_blocked_on(struct task_struct *p, struct mutex *m) { - return IS_ENABLED(CONFIG_PREEMPT); + if (m) { + struct mutex *blocked_on = READ_ONCE(p->blocked_on); + + /* Currently we serialize blocked_on under the mutex::wait_lock */ + lockdep_assert_held_once(&m->wait_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(blocked_on && blocked_on != m); + } + WRITE_ONCE(p->blocked_on, NULL); } -#endif - -static inline bool preempt_model_rt(void) +static inline void clear_task_blocked_on(struct task_struct *p, struct mutex *m) +{ + guard(raw_spinlock_irqsave)(&m->wait_lock); + __clear_task_blocked_on(p, m); +} +#else +static inline void __clear_task_blocked_on(struct task_struct *p, struct rt_mutex *m) { - return IS_ENABLED(CONFIG_PREEMPT_RT); } -/* - * Does the preemption model allow non-cooperative preemption? - * - * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with - * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the - * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the - * PREEMPT_NONE model. - */ -static inline bool preempt_model_preemptible(void) +static inline void clear_task_blocked_on(struct task_struct *p, struct rt_mutex *m) { - return preempt_model_full() || preempt_model_rt(); } +#endif /* !CONFIG_PREEMPT_RT */ static __always_inline bool need_resched(void) { @@ -2141,12 +2228,15 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) #endif /* CONFIG_SMP */ +static inline bool task_is_runnable(struct task_struct *p) +{ + return p->on_rq && !p->se.sched_delayed; +} + extern bool sched_task_on_rq(struct task_struct *p); extern unsigned long get_wchan(struct task_struct *p); extern struct task_struct *cpu_curr_snapshot(int cpu); -#include <linux/spinlock.h> - /* * In order to reduce various lock holder preemption latencies provide an * interface to see if a vCPU is currently running or not. @@ -2169,7 +2259,6 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #define TASK_SIZE_OF(tsk) TASK_SIZE #endif -#ifdef CONFIG_SMP static inline bool owner_on_cpu(struct task_struct *owner) { /* @@ -2181,7 +2270,6 @@ static inline bool owner_on_cpu(struct task_struct *owner) /* Returns effective CPU energy utilization, as seen by the scheduler */ unsigned long sched_cpu_util(int cpu); -#endif /* CONFIG_SMP */ #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); @@ -2216,4 +2304,140 @@ static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct allo #define alloc_tag_restore(_tag, _old) do {} while (0) #endif +/* Avoids recursive inclusion hell */ +#ifdef CONFIG_SCHED_MM_CID +void sched_mm_cid_before_execve(struct task_struct *t); +void sched_mm_cid_after_execve(struct task_struct *t); +void sched_mm_cid_fork(struct task_struct *t); +void sched_mm_cid_exit(struct task_struct *t); +static __always_inline int task_mm_cid(struct task_struct *t) +{ + return t->mm_cid.cid & ~(MM_CID_ONCPU | MM_CID_TRANSIT); +} +#else +static inline void sched_mm_cid_before_execve(struct task_struct *t) { } +static inline void sched_mm_cid_after_execve(struct task_struct *t) { } +static inline void sched_mm_cid_fork(struct task_struct *t) { } +static inline void sched_mm_cid_exit(struct task_struct *t) { } +static __always_inline int task_mm_cid(struct task_struct *t) +{ + /* + * Use the processor id as a fall-back when the mm cid feature is + * disabled. This provides functional per-cpu data structure accesses + * in user-space, althrough it won't provide the memory usage benefits. + */ + return task_cpu(t); +} +#endif + +#ifndef MODULE +#ifndef COMPILE_OFFSETS + +extern void ___migrate_enable(void); + +struct rq; +DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); + +/* + * The "struct rq" is not available here, so we can't access the + * "runqueues" with this_cpu_ptr(), as the compilation will fail in + * this_cpu_ptr() -> raw_cpu_ptr() -> __verify_pcpu_ptr(): + * typeof((ptr) + 0) + * + * So use arch_raw_cpu_ptr()/PERCPU_PTR() directly here. + */ +#ifdef CONFIG_SMP +#define this_rq_raw() arch_raw_cpu_ptr(&runqueues) +#else +#define this_rq_raw() PERCPU_PTR(&runqueues) +#endif +#define this_rq_pinned() (*(unsigned int *)((void *)this_rq_raw() + RQ_nr_pinned)) + +static inline void __migrate_enable(void) +{ + struct task_struct *p = current; + +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Check both overflow from migrate_disable() and superfluous + * migrate_enable(). + */ + if (WARN_ON_ONCE((s16)p->migration_disabled <= 0)) + return; +#endif + + if (p->migration_disabled > 1) { + p->migration_disabled--; + return; + } + + /* + * Ensure stop_task runs either before or after this, and that + * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule(). + */ + guard(preempt)(); + if (unlikely(p->cpus_ptr != &p->cpus_mask)) + ___migrate_enable(); + /* + * Mustn't clear migration_disabled() until cpus_ptr points back at the + * regular cpus_mask, otherwise things that race (eg. + * select_fallback_rq) get confused. + */ + barrier(); + p->migration_disabled = 0; + this_rq_pinned()--; +} + +static inline void __migrate_disable(void) +{ + struct task_struct *p = current; + + if (p->migration_disabled) { +#ifdef CONFIG_DEBUG_PREEMPT + /* + *Warn about overflow half-way through the range. + */ + WARN_ON_ONCE((s16)p->migration_disabled < 0); +#endif + p->migration_disabled++; + return; + } + + guard(preempt)(); + this_rq_pinned()++; + p->migration_disabled = 1; +} +#else /* !COMPILE_OFFSETS */ +static inline void __migrate_disable(void) { } +static inline void __migrate_enable(void) { } +#endif /* !COMPILE_OFFSETS */ + +/* + * So that it is possible to not export the runqueues variable, define and + * export migrate_enable/migrate_disable in kernel/sched/core.c too, and use + * them for the modules. The macro "INSTANTIATE_EXPORTED_MIGRATE_DISABLE" will + * be defined in kernel/sched/core.c. + */ +#ifndef INSTANTIATE_EXPORTED_MIGRATE_DISABLE +static __always_inline void migrate_disable(void) +{ + __migrate_disable(); +} + +static __always_inline void migrate_enable(void) +{ + __migrate_enable(); +} +#else /* INSTANTIATE_EXPORTED_MIGRATE_DISABLE */ +extern void migrate_disable(void); +extern void migrate_enable(void); +#endif /* INSTANTIATE_EXPORTED_MIGRATE_DISABLE */ + +#else /* MODULE */ +extern void migrate_disable(void); +extern void migrate_enable(void); +#endif /* MODULE */ + +DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable()) + #endif |