sched/headers: Move task_struct::signal and task_struct::sighand types and accessors into <linux/sched/signal.h>
task_struct::signal and task_struct::sighand are pointers, which would normally make it
straightforward to not define those types in sched.h.
That is not so, because the types are accompanied by a myriad of APIs (macros and inline
functions) that dereference them.
Split the types and the APIs out of sched.h and move them into a new header, <linux/sched/signal.h>.
With this change sched.h does not know about 'struct signal' and 'struct sighand' anymore,
trying to put accessors into sched.h as a test fails the following way:
./include/linux/sched.h: In function ‘test_signal_types’:
./include/linux/sched.h:2461:18: error: dereferencing pointer to incomplete type ‘struct signal_struct’
^
This reduces the size and complexity of sched.h significantly.
Update all headers and .c code that relied on getting the signal handling
functionality from <linux/sched.h> to include <linux/sched/signal.h>.
The list of affected files in the preparatory patch was partly generated by
grepping for the APIs, and partly by doing coverage build testing, both
all[yes|mod|def|no]config builds on 64-bit and 32-bit x86, and an array of
cross-architecture builds.
Nevertheless some (trivial) build breakage is still expected related to rare
Kconfig combinations and in-flight patches to various kernel code, but most
of it should be handled by this patch.
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index c6958a5..53fe545 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -8,4 +8,506 @@
#include <linux/sched/jobctl.h>
#include <linux/sched/task.h>
+/*
+ * Types defining task->signal and task->sighand and APIs using them:
+ */
+
+struct sighand_struct {
+ atomic_t count;
+ struct k_sigaction action[_NSIG];
+ spinlock_t siglock;
+ wait_queue_head_t signalfd_wqh;
+};
+
+/*
+ * NOTE! "signal_struct" does not have its own
+ * locking, because a shared signal_struct always
+ * implies a shared sighand_struct, so locking
+ * sighand_struct is always a proper superset of
+ * the locking of signal_struct.
+ */
+struct signal_struct {
+ atomic_t sigcnt;
+ atomic_t live;
+ int nr_threads;
+ struct list_head thread_head;
+
+ wait_queue_head_t wait_chldexit; /* for wait4() */
+
+ /* current thread group signal load-balancing target: */
+ struct task_struct *curr_target;
+
+ /* shared signal handling: */
+ struct sigpending shared_pending;
+
+ /* thread group exit support */
+ int group_exit_code;
+ /* overloaded:
+ * - notify group_exit_task when ->count is equal to notify_count
+ * - everyone except group_exit_task is stopped during signal delivery
+ * of fatal signals, group_exit_task processes the signal.
+ */
+ int notify_count;
+ struct task_struct *group_exit_task;
+
+ /* thread group stop support, overloads group_exit_code too */
+ int group_stop_count;
+ unsigned int flags; /* see SIGNAL_* flags below */
+
+ /*
+ * PR_SET_CHILD_SUBREAPER marks a process, like a service
+ * manager, to re-parent orphan (double-forking) child processes
+ * to this process instead of 'init'. The service manager is
+ * able to receive SIGCHLD signals and is able to investigate
+ * the process until it calls wait(). All children of this
+ * process will inherit a flag if they should look for a
+ * child_subreaper process at exit.
+ */
+ unsigned int is_child_subreaper:1;
+ unsigned int has_child_subreaper:1;
+
+#ifdef CONFIG_POSIX_TIMERS
+
+ /* POSIX.1b Interval Timers */
+ int posix_timer_id;
+ struct list_head posix_timers;
+
+ /* ITIMER_REAL timer for the process */
+ struct hrtimer real_timer;
+ ktime_t it_real_incr;
+
+ /*
+ * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use
+ * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these
+ * values are defined to 0 and 1 respectively
+ */
+ struct cpu_itimer it[2];
+
+ /*
+ * Thread group totals for process CPU timers.
+ * See thread_group_cputimer(), et al, for details.
+ */
+ struct thread_group_cputimer cputimer;
+
+ /* Earliest-expiration cache. */
+ struct task_cputime cputime_expires;
+
+ struct list_head cpu_timers[3];
+
+#endif
+
+ struct pid *leader_pid;
+
+#ifdef CONFIG_NO_HZ_FULL
+ atomic_t tick_dep_mask;
+#endif
+
+ struct pid *tty_old_pgrp;
+
+ /* boolean value for session group leader */
+ int leader;
+
+ struct tty_struct *tty; /* NULL if no tty */
+
+#ifdef CONFIG_SCHED_AUTOGROUP
+ struct autogroup *autogroup;
+#endif
+ /*
+ * Cumulative resource counters for dead threads in the group,
+ * and for reaped dead child processes forked by this group.
+ * Live threads maintain their own counters and add to these
+ * in __exit_signal, except for the group leader.
+ */
+ seqlock_t stats_lock;
+ u64 utime, stime, cutime, cstime;
+ u64 gtime;
+ u64 cgtime;
+ struct prev_cputime prev_cputime;
+ unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
+ unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
+ unsigned long inblock, oublock, cinblock, coublock;
+ unsigned long maxrss, cmaxrss;
+ struct task_io_accounting ioac;
+
+ /*
+ * Cumulative ns of schedule CPU time fo dead threads in the
+ * group, not including a zombie group leader, (This only differs
+ * from jiffies_to_ns(utime + stime) if sched_clock uses something
+ * other than jiffies.)
+ */
+ unsigned long long sum_sched_runtime;
+
+ /*
+ * We don't bother to synchronize most readers of this at all,
+ * because there is no reader checking a limit that actually needs
+ * to get both rlim_cur and rlim_max atomically, and either one
+ * alone is a single word that can safely be read normally.
+ * getrlimit/setrlimit use task_lock(current->group_leader) to
+ * protect this instead of the siglock, because they really
+ * have no need to disable irqs.
+ */
+ struct rlimit rlim[RLIM_NLIMITS];
+
+#ifdef CONFIG_BSD_PROCESS_ACCT
+ struct pacct_struct pacct; /* per-process accounting information */
+#endif
+#ifdef CONFIG_TASKSTATS
+ struct taskstats *stats;
+#endif
+#ifdef CONFIG_AUDIT
+ unsigned audit_tty;
+ struct tty_audit_buf *tty_audit_buf;
+#endif
+
+ /*
+ * Thread is the potential origin of an oom condition; kill first on
+ * oom
+ */
+ bool oom_flag_origin;
+ short oom_score_adj; /* OOM kill score adjustment */
+ short oom_score_adj_min; /* OOM kill score adjustment min value.
+ * Only settable by CAP_SYS_RESOURCE. */
+ struct mm_struct *oom_mm; /* recorded mm when the thread group got
+ * killed by the oom killer */
+
+ struct mutex cred_guard_mutex; /* guard against foreign influences on
+ * credential calculations
+ * (notably. ptrace) */
+};
+
+/*
+ * Bits in flags field of signal_struct.
+ */
+#define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */
+#define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */
+#define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */
+#define SIGNAL_GROUP_COREDUMP 0x00000008 /* coredump in progress */
+/*
+ * Pending notifications to parent.
+ */
+#define SIGNAL_CLD_STOPPED 0x00000010
+#define SIGNAL_CLD_CONTINUED 0x00000020
+#define SIGNAL_CLD_MASK (SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED)
+
+#define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */
+
+#define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \
+ SIGNAL_STOP_CONTINUED)
+
+static inline void signal_set_stop_flags(struct signal_struct *sig,
+ unsigned int flags)
+{
+ WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP));
+ sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags;
+}
+
+/* If true, all threads except ->group_exit_task have pending SIGKILL */
+static inline int signal_group_exit(const struct signal_struct *sig)
+{
+ return (sig->flags & SIGNAL_GROUP_EXIT) ||
+ (sig->group_exit_task != NULL);
+}
+
+extern void flush_signals(struct task_struct *);
+extern void ignore_signals(struct task_struct *);
+extern void flush_signal_handlers(struct task_struct *, int force_default);
+extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);
+
+static inline int kernel_dequeue_signal(siginfo_t *info)
+{
+ struct task_struct *tsk = current;
+ siginfo_t __info;
+ int ret;
+
+ spin_lock_irq(&tsk->sighand->siglock);
+ ret = dequeue_signal(tsk, &tsk->blocked, info ?: &__info);
+ spin_unlock_irq(&tsk->sighand->siglock);
+
+ return ret;
+}
+
+static inline void kernel_signal_stop(void)
+{
+ spin_lock_irq(¤t->sighand->siglock);
+ if (current->jobctl & JOBCTL_STOP_DEQUEUED)
+ __set_current_state(TASK_STOPPED);
+ spin_unlock_irq(¤t->sighand->siglock);
+
+ schedule();
+}
+extern int send_sig_info(int, struct siginfo *, struct task_struct *);
+extern int force_sigsegv(int, struct task_struct *);
+extern int force_sig_info(int, struct siginfo *, struct task_struct *);
+extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp);
+extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid);
+extern int kill_pid_info_as_cred(int, struct siginfo *, struct pid *,
+ const struct cred *, u32);
+extern int kill_pgrp(struct pid *pid, int sig, int priv);
+extern int kill_pid(struct pid *pid, int sig, int priv);
+extern int kill_proc_info(int, struct siginfo *, pid_t);
+extern __must_check bool do_notify_parent(struct task_struct *, int);
+extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
+extern void force_sig(int, struct task_struct *);
+extern int send_sig(int, struct task_struct *, int);
+extern int zap_other_threads(struct task_struct *p);
+extern struct sigqueue *sigqueue_alloc(void);
+extern void sigqueue_free(struct sigqueue *);
+extern int send_sigqueue(struct sigqueue *, struct task_struct *, int group);
+extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
+
+#ifdef TIF_RESTORE_SIGMASK
+/*
+ * Legacy restore_sigmask accessors. These are inefficient on
+ * SMP architectures because they require atomic operations.
+ */
+
+/**
+ * set_restore_sigmask() - make sure saved_sigmask processing gets done
+ *
+ * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code
+ * will run before returning to user mode, to process the flag. For
+ * all callers, TIF_SIGPENDING is already set or it's no harm to set
+ * it. TIF_RESTORE_SIGMASK need not be in the set of bits that the
+ * arch code will notice on return to user mode, in case those bits
+ * are scarce. We set TIF_SIGPENDING here to ensure that the arch
+ * signal code always gets run when TIF_RESTORE_SIGMASK is set.
+ */
+static inline void set_restore_sigmask(void)
+{
+ set_thread_flag(TIF_RESTORE_SIGMASK);
+ WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+}
+static inline void clear_restore_sigmask(void)
+{
+ clear_thread_flag(TIF_RESTORE_SIGMASK);
+}
+static inline bool test_restore_sigmask(void)
+{
+ return test_thread_flag(TIF_RESTORE_SIGMASK);
+}
+static inline bool test_and_clear_restore_sigmask(void)
+{
+ return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK);
+}
+
+#else /* TIF_RESTORE_SIGMASK */
+
+/* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */
+static inline void set_restore_sigmask(void)
+{
+ current->restore_sigmask = true;
+ WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+}
+static inline void clear_restore_sigmask(void)
+{
+ current->restore_sigmask = false;
+}
+static inline bool test_restore_sigmask(void)
+{
+ return current->restore_sigmask;
+}
+static inline bool test_and_clear_restore_sigmask(void)
+{
+ if (!current->restore_sigmask)
+ return false;
+ current->restore_sigmask = false;
+ return true;
+}
+#endif
+
+static inline void restore_saved_sigmask(void)
+{
+ if (test_and_clear_restore_sigmask())
+ __set_current_blocked(¤t->saved_sigmask);
+}
+
+static inline sigset_t *sigmask_to_save(void)
+{
+ sigset_t *res = ¤t->blocked;
+ if (unlikely(test_restore_sigmask()))
+ res = ¤t->saved_sigmask;
+ return res;
+}
+
+static inline int kill_cad_pid(int sig, int priv)
+{
+ return kill_pid(cad_pid, sig, priv);
+}
+
+/* These can be the second arg to send_sig_info/send_group_sig_info. */
+#define SEND_SIG_NOINFO ((struct siginfo *) 0)
+#define SEND_SIG_PRIV ((struct siginfo *) 1)
+#define SEND_SIG_FORCED ((struct siginfo *) 2)
+
+/*
+ * True if we are on the alternate signal stack.
+ */
+static inline int on_sig_stack(unsigned long sp)
+{
+ /*
+ * If the signal stack is SS_AUTODISARM then, by construction, we
+ * can't be on the signal stack unless user code deliberately set
+ * SS_AUTODISARM when we were already on it.
+ *
+ * This improves reliability: if user state gets corrupted such that
+ * the stack pointer points very close to the end of the signal stack,
+ * then this check will enable the signal to be handled anyway.
+ */
+ if (current->sas_ss_flags & SS_AUTODISARM)
+ return 0;
+
+#ifdef CONFIG_STACK_GROWSUP
+ return sp >= current->sas_ss_sp &&
+ sp - current->sas_ss_sp < current->sas_ss_size;
+#else
+ return sp > current->sas_ss_sp &&
+ sp - current->sas_ss_sp <= current->sas_ss_size;
+#endif
+}
+
+static inline int sas_ss_flags(unsigned long sp)
+{
+ if (!current->sas_ss_size)
+ return SS_DISABLE;
+
+ return on_sig_stack(sp) ? SS_ONSTACK : 0;
+}
+
+static inline void sas_ss_reset(struct task_struct *p)
+{
+ p->sas_ss_sp = 0;
+ p->sas_ss_size = 0;
+ p->sas_ss_flags = SS_DISABLE;
+}
+
+static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig)
+{
+ if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp))
+#ifdef CONFIG_STACK_GROWSUP
+ return current->sas_ss_sp;
+#else
+ return current->sas_ss_sp + current->sas_ss_size;
+#endif
+ return sp;
+}
+
+extern void __cleanup_sighand(struct sighand_struct *);
+extern void flush_itimer_signals(void);
+
+#define tasklist_empty() \
+ list_empty(&init_task.tasks)
+
+#define next_task(p) \
+ list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
+
+#define for_each_process(p) \
+ for (p = &init_task ; (p = next_task(p)) != &init_task ; )
+
+extern bool current_is_single_threaded(void);
+
+/*
+ * Careful: do_each_thread/while_each_thread is a double loop so
+ * 'break' will not work as expected - use goto instead.
+ */
+#define do_each_thread(g, t) \
+ for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do
+
+#define while_each_thread(g, t) \
+ while ((t = next_thread(t)) != g)
+
+#define __for_each_thread(signal, t) \
+ list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node)
+
+#define for_each_thread(p, t) \
+ __for_each_thread((p)->signal, t)
+
+/* Careful: this is a double loop, 'break' won't work as expected. */
+#define for_each_process_thread(p, t) \
+ for_each_process(p) for_each_thread(p, t)
+
+typedef int (*proc_visitor)(struct task_struct *p, void *data);
+void walk_process_tree(struct task_struct *top, proc_visitor, void *);
+
+static inline int get_nr_threads(struct task_struct *tsk)
+{
+ return tsk->signal->nr_threads;
+}
+
+static inline bool thread_group_leader(struct task_struct *p)
+{
+ return p->exit_signal >= 0;
+}
+
+/* Do to the insanities of de_thread it is possible for a process
+ * to have the pid of the thread group leader without actually being
+ * the thread group leader. For iteration through the pids in proc
+ * all we care about is that we have a task with the appropriate
+ * pid, we don't actually care if we have the right task.
+ */
+static inline bool has_group_leader_pid(struct task_struct *p)
+{
+ return task_pid(p) == p->signal->leader_pid;
+}
+
+static inline
+bool same_thread_group(struct task_struct *p1, struct task_struct *p2)
+{
+ return p1->signal == p2->signal;
+}
+
+static inline struct task_struct *next_thread(const struct task_struct *p)
+{
+ return list_entry_rcu(p->thread_group.next,
+ struct task_struct, thread_group);
+}
+
+static inline int thread_group_empty(struct task_struct *p)
+{
+ return list_empty(&p->thread_group);
+}
+
+#define delay_group_leader(p) \
+ (thread_group_leader(p) && !thread_group_empty(p))
+
+extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
+ unsigned long *flags);
+
+static inline struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
+ unsigned long *flags)
+{
+ struct sighand_struct *ret;
+
+ ret = __lock_task_sighand(tsk, flags);
+ (void)__cond_lock(&tsk->sighand->siglock, ret);
+ return ret;
+}
+
+static inline void unlock_task_sighand(struct task_struct *tsk,
+ unsigned long *flags)
+{
+ spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
+}
+
+static inline unsigned long task_rlimit(const struct task_struct *tsk,
+ unsigned int limit)
+{
+ return READ_ONCE(tsk->signal->rlim[limit].rlim_cur);
+}
+
+static inline unsigned long task_rlimit_max(const struct task_struct *tsk,
+ unsigned int limit)
+{
+ return READ_ONCE(tsk->signal->rlim[limit].rlim_max);
+}
+
+static inline unsigned long rlimit(unsigned int limit)
+{
+ return task_rlimit(current, limit);
+}
+
+static inline unsigned long rlimit_max(unsigned int limit)
+{
+ return task_rlimit_max(current, limit);
+}
+
#endif /* _LINUX_SCHED_SIGNAL_H */