diff options
Diffstat (limited to 'kernel/signal.c')
| -rw-r--r-- | kernel/signal.c | 3755 |
1 files changed, 2332 insertions, 1423 deletions
diff --git a/kernel/signal.c b/kernel/signal.c index d3efafd8109..a4077e90f19 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -10,173 +10,91 @@ * to allow signals to be sent reliably. */ -#include <linux/config.h> #include <linux/slab.h> -#include <linux/module.h> -#include <linux/smp_lock.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/tty.h> #include <linux/binfmts.h> +#include <linux/coredump.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/ptrace.h> -#include <linux/posix-timers.h> #include <linux/signal.h> -#include <linux/audit.h> +#include <linux/signalfd.h> +#include <linux/ratelimit.h> +#include <linux/tracehook.h> #include <linux/capability.h> +#include <linux/freezer.h> +#include <linux/pid_namespace.h> +#include <linux/nsproxy.h> +#include <linux/user_namespace.h> +#include <linux/uprobes.h> +#include <linux/compat.h> +#include <linux/cn_proc.h> +#include <linux/compiler.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/signal.h> + #include <asm/param.h> #include <asm/uaccess.h> #include <asm/unistd.h> #include <asm/siginfo.h> +#include <asm/cacheflush.h> +#include "audit.h" /* audit_signal_info() */ /* * SLAB caches for signal bits. */ -static kmem_cache_t *sigqueue_cachep; +static struct kmem_cache *sigqueue_cachep; -/* - * In POSIX a signal is sent either to a specific thread (Linux task) - * or to the process as a whole (Linux thread group). How the signal - * is sent determines whether it's to one thread or the whole group, - * which determines which signal mask(s) are involved in blocking it - * from being delivered until later. When the signal is delivered, - * either it's caught or ignored by a user handler or it has a default - * effect that applies to the whole thread group (POSIX process). - * - * The possible effects an unblocked signal set to SIG_DFL can have are: - * ignore - Nothing Happens - * terminate - kill the process, i.e. all threads in the group, - * similar to exit_group. The group leader (only) reports - * WIFSIGNALED status to its parent. - * coredump - write a core dump file describing all threads using - * the same mm and then kill all those threads - * stop - stop all the threads in the group, i.e. TASK_STOPPED state - * - * SIGKILL and SIGSTOP cannot be caught, blocked, or ignored. - * Other signals when not blocked and set to SIG_DFL behaves as follows. - * The job control signals also have other special effects. - * - * +--------------------+------------------+ - * | POSIX signal | default action | - * +--------------------+------------------+ - * | SIGHUP | terminate | - * | SIGINT | terminate | - * | SIGQUIT | coredump | - * | SIGILL | coredump | - * | SIGTRAP | coredump | - * | SIGABRT/SIGIOT | coredump | - * | SIGBUS | coredump | - * | SIGFPE | coredump | - * | SIGKILL | terminate(+) | - * | SIGUSR1 | terminate | - * | SIGSEGV | coredump | - * | SIGUSR2 | terminate | - * | SIGPIPE | terminate | - * | SIGALRM | terminate | - * | SIGTERM | terminate | - * | SIGCHLD | ignore | - * | SIGCONT | ignore(*) | - * | SIGSTOP | stop(*)(+) | - * | SIGTSTP | stop(*) | - * | SIGTTIN | stop(*) | - * | SIGTTOU | stop(*) | - * | SIGURG | ignore | - * | SIGXCPU | coredump | - * | SIGXFSZ | coredump | - * | SIGVTALRM | terminate | - * | SIGPROF | terminate | - * | SIGPOLL/SIGIO | terminate | - * | SIGSYS/SIGUNUSED | coredump | - * | SIGSTKFLT | terminate | - * | SIGWINCH | ignore | - * | SIGPWR | terminate | - * | SIGRTMIN-SIGRTMAX | terminate | - * +--------------------+------------------+ - * | non-POSIX signal | default action | - * +--------------------+------------------+ - * | SIGEMT | coredump | - * +--------------------+------------------+ - * - * (+) For SIGKILL and SIGSTOP the action is "always", not just "default". - * (*) Special job control effects: - * When SIGCONT is sent, it resumes the process (all threads in the group) - * from TASK_STOPPED state and also clears any pending/queued stop signals - * (any of those marked with "stop(*)"). This happens regardless of blocking, - * catching, or ignoring SIGCONT. When any stop signal is sent, it clears - * any pending/queued SIGCONT signals; this happens regardless of blocking, - * catching, or ignored the stop signal, though (except for SIGSTOP) the - * default action of stopping the process may happen later or never. - */ +int print_fatal_signals __read_mostly; -#ifdef SIGEMT -#define M_SIGEMT M(SIGEMT) -#else -#define M_SIGEMT 0 -#endif - -#if SIGRTMIN > BITS_PER_LONG -#define M(sig) (1ULL << ((sig)-1)) -#else -#define M(sig) (1UL << ((sig)-1)) -#endif -#define T(sig, mask) (M(sig) & (mask)) - -#define SIG_KERNEL_ONLY_MASK (\ - M(SIGKILL) | M(SIGSTOP) ) - -#define SIG_KERNEL_STOP_MASK (\ - M(SIGSTOP) | M(SIGTSTP) | M(SIGTTIN) | M(SIGTTOU) ) +static void __user *sig_handler(struct task_struct *t, int sig) +{ + return t->sighand->action[sig - 1].sa.sa_handler; +} -#define SIG_KERNEL_COREDUMP_MASK (\ - M(SIGQUIT) | M(SIGILL) | M(SIGTRAP) | M(SIGABRT) | \ - M(SIGFPE) | M(SIGSEGV) | M(SIGBUS) | M(SIGSYS) | \ - M(SIGXCPU) | M(SIGXFSZ) | M_SIGEMT ) +static int sig_handler_ignored(void __user *handler, int sig) +{ + /* Is it explicitly or implicitly ignored? */ + return handler == SIG_IGN || + (handler == SIG_DFL && sig_kernel_ignore(sig)); +} -#define SIG_KERNEL_IGNORE_MASK (\ - M(SIGCONT) | M(SIGCHLD) | M(SIGWINCH) | M(SIGURG) ) +static int sig_task_ignored(struct task_struct *t, int sig, bool force) +{ + void __user *handler; -#define sig_kernel_only(sig) \ - (((sig) < SIGRTMIN) && T(sig, SIG_KERNEL_ONLY_MASK)) -#define sig_kernel_coredump(sig) \ - (((sig) < SIGRTMIN) && T(sig, SIG_KERNEL_COREDUMP_MASK)) -#define sig_kernel_ignore(sig) \ - (((sig) < SIGRTMIN) && T(sig, SIG_KERNEL_IGNORE_MASK)) -#define sig_kernel_stop(sig) \ - (((sig) < SIGRTMIN) && T(sig, SIG_KERNEL_STOP_MASK)) + handler = sig_handler(t, sig); -#define sig_user_defined(t, signr) \ - (((t)->sighand->action[(signr)-1].sa.sa_handler != SIG_DFL) && \ - ((t)->sighand->action[(signr)-1].sa.sa_handler != SIG_IGN)) + if (unlikely(t->signal->flags & SIGNAL_UNKILLABLE) && + handler == SIG_DFL && !force) + return 1; -#define sig_fatal(t, signr) \ - (!T(signr, SIG_KERNEL_IGNORE_MASK|SIG_KERNEL_STOP_MASK) && \ - (t)->sighand->action[(signr)-1].sa.sa_handler == SIG_DFL) + return sig_handler_ignored(handler, sig); +} -static int sig_ignored(struct task_struct *t, int sig) +static int sig_ignored(struct task_struct *t, int sig, bool force) { - void __user * handler; - - /* - * Tracers always want to know about signals.. - */ - if (t->ptrace & PT_PTRACED) - return 0; - /* * Blocked signals are never ignored, since the * signal handler may change by the time it is * unblocked. */ - if (sigismember(&t->blocked, sig)) + if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig)) return 0; - /* Is it explicitly or implicitly ignored? */ - handler = t->sighand->action[sig-1].sa.sa_handler; - return handler == SIG_IGN || - (handler == SIG_DFL && sig_kernel_ignore(sig)); + if (!sig_task_ignored(t, sig, force)) + return 0; + + /* + * Tracers may want to know about even ignored signals. + */ + return !t->ptrace; } /* @@ -211,79 +129,270 @@ static inline int has_pending_signals(sigset_t *signal, sigset_t *blocked) #define PENDING(p,b) has_pending_signals(&(p)->signal, (b)) -fastcall void recalc_sigpending_tsk(struct task_struct *t) +static int recalc_sigpending_tsk(struct task_struct *t) { - if (t->signal->group_stop_count > 0 || - (freezing(t)) || + if ((t->jobctl & JOBCTL_PENDING_MASK) || PENDING(&t->pending, &t->blocked) || - PENDING(&t->signal->shared_pending, &t->blocked)) + PENDING(&t->signal->shared_pending, &t->blocked)) { set_tsk_thread_flag(t, TIF_SIGPENDING); - else - clear_tsk_thread_flag(t, TIF_SIGPENDING); + return 1; + } + /* + * We must never clear the flag in another thread, or in current + * when it's possible the current syscall is returning -ERESTART*. + * So we don't clear it here, and only callers who know they should do. + */ + return 0; +} + +/* + * After recalculating TIF_SIGPENDING, we need to make sure the task wakes up. + * This is superfluous when called on current, the wakeup is a harmless no-op. + */ +void recalc_sigpending_and_wake(struct task_struct *t) +{ + if (recalc_sigpending_tsk(t)) + signal_wake_up(t, 0); } void recalc_sigpending(void) { - recalc_sigpending_tsk(current); + if (!recalc_sigpending_tsk(current) && !freezing(current)) + clear_thread_flag(TIF_SIGPENDING); + } /* Given the mask, find the first available signal that should be serviced. */ -static int -next_signal(struct sigpending *pending, sigset_t *mask) +#define SYNCHRONOUS_MASK \ + (sigmask(SIGSEGV) | sigmask(SIGBUS) | sigmask(SIGILL) | \ + sigmask(SIGTRAP) | sigmask(SIGFPE) | sigmask(SIGSYS)) + +int next_signal(struct sigpending *pending, sigset_t *mask) { unsigned long i, *s, *m, x; int sig = 0; - + s = pending->signal.sig; m = mask->sig; + + /* + * Handle the first word specially: it contains the + * synchronous signals that need to be dequeued first. + */ + x = *s &~ *m; + if (x) { + if (x & SYNCHRONOUS_MASK) + x &= SYNCHRONOUS_MASK; + sig = ffz(~x) + 1; + return sig; + } + switch (_NSIG_WORDS) { default: - for (i = 0; i < _NSIG_WORDS; ++i, ++s, ++m) - if ((x = *s &~ *m) != 0) { - sig = ffz(~x) + i*_NSIG_BPW + 1; - break; - } + for (i = 1; i < _NSIG_WORDS; ++i) { + x = *++s &~ *++m; + if (!x) + continue; + sig = ffz(~x) + i*_NSIG_BPW + 1; + break; + } break; - case 2: if ((x = s[0] &~ m[0]) != 0) - sig = 1; - else if ((x = s[1] &~ m[1]) != 0) - sig = _NSIG_BPW + 1; - else + case 2: + x = s[1] &~ m[1]; + if (!x) break; - sig += ffz(~x); + sig = ffz(~x) + _NSIG_BPW + 1; break; - case 1: if ((x = *s &~ *m) != 0) - sig = ffz(~x) + 1; + case 1: + /* Nothing to do */ break; } - + return sig; } -static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags, - int override_rlimit) +static inline void print_dropped_signal(int sig) +{ + static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); + + if (!print_fatal_signals) + return; + + if (!__ratelimit(&ratelimit_state)) + return; + + printk(KERN_INFO "%s/%d: reached RLIMIT_SIGPENDING, dropped signal %d\n", + current->comm, current->pid, sig); +} + +/** + * task_set_jobctl_pending - set jobctl pending bits + * @task: target task + * @mask: pending bits to set + * + * Clear @mask from @task->jobctl. @mask must be subset of + * %JOBCTL_PENDING_MASK | %JOBCTL_STOP_CONSUME | %JOBCTL_STOP_SIGMASK | + * %JOBCTL_TRAPPING. If stop signo is being set, the existing signo is + * cleared. If @task is already being killed or exiting, this function + * becomes noop. + * + * CONTEXT: + * Must be called with @task->sighand->siglock held. + * + * RETURNS: + * %true if @mask is set, %false if made noop because @task was dying. + */ +bool task_set_jobctl_pending(struct task_struct *task, unsigned int mask) +{ + BUG_ON(mask & ~(JOBCTL_PENDING_MASK | JOBCTL_STOP_CONSUME | + JOBCTL_STOP_SIGMASK | JOBCTL_TRAPPING)); + BUG_ON((mask & JOBCTL_TRAPPING) && !(mask & JOBCTL_PENDING_MASK)); + + if (unlikely(fatal_signal_pending(task) || (task->flags & PF_EXITING))) + return false; + + if (mask & JOBCTL_STOP_SIGMASK) + task->jobctl &= ~JOBCTL_STOP_SIGMASK; + + task->jobctl |= mask; + return true; +} + +/** + * task_clear_jobctl_trapping - clear jobctl trapping bit + * @task: target task + * + * If JOBCTL_TRAPPING is set, a ptracer is waiting for us to enter TRACED. + * Clear it and wake up the ptracer. Note that we don't need any further + * locking. @task->siglock guarantees that @task->parent points to the + * ptracer. + * + * CONTEXT: + * Must be called with @task->sighand->siglock held. + */ +void task_clear_jobctl_trapping(struct task_struct *task) +{ + if (unlikely(task->jobctl & JOBCTL_TRAPPING)) { + task->jobctl &= ~JOBCTL_TRAPPING; + smp_mb(); /* advised by wake_up_bit() */ + wake_up_bit(&task->jobctl, JOBCTL_TRAPPING_BIT); + } +} + +/** + * task_clear_jobctl_pending - clear jobctl pending bits + * @task: target task + * @mask: pending bits to clear + * + * Clear @mask from @task->jobctl. @mask must be subset of + * %JOBCTL_PENDING_MASK. If %JOBCTL_STOP_PENDING is being cleared, other + * STOP bits are cleared together. + * + * If clearing of @mask leaves no stop or trap pending, this function calls + * task_clear_jobctl_trapping(). + * + * CONTEXT: + * Must be called with @task->sighand->siglock held. + */ +void task_clear_jobctl_pending(struct task_struct *task, unsigned int mask) +{ + BUG_ON(mask & ~JOBCTL_PENDING_MASK); + + if (mask & JOBCTL_STOP_PENDING) + mask |= JOBCTL_STOP_CONSUME | JOBCTL_STOP_DEQUEUED; + + task->jobctl &= ~mask; + + if (!(task->jobctl & JOBCTL_PENDING_MASK)) + task_clear_jobctl_trapping(task); +} + +/** + * task_participate_group_stop - participate in a group stop + * @task: task participating in a group stop + * + * @task has %JOBCTL_STOP_PENDING set and is participating in a group stop. + * Group stop states are cleared and the group stop count is consumed if + * %JOBCTL_STOP_CONSUME was set. If the consumption completes the group + * stop, the appropriate %SIGNAL_* flags are set. + * + * CONTEXT: + * Must be called with @task->sighand->siglock held. + * + * RETURNS: + * %true if group stop completion should be notified to the parent, %false + * otherwise. + */ +static bool task_participate_group_stop(struct task_struct *task) +{ + struct signal_struct *sig = task->signal; + bool consume = task->jobctl & JOBCTL_STOP_CONSUME; + + WARN_ON_ONCE(!(task->jobctl & JOBCTL_STOP_PENDING)); + + task_clear_jobctl_pending(task, JOBCTL_STOP_PENDING); + + if (!consume) + return false; + + if (!WARN_ON_ONCE(sig->group_stop_count == 0)) + sig->group_stop_count--; + + /* + * Tell the caller to notify completion iff we are entering into a + * fresh group stop. Read comment in do_signal_stop() for details. + */ + if (!sig->group_stop_count && !(sig->flags & SIGNAL_STOP_STOPPED)) { + sig->flags = SIGNAL_STOP_STOPPED; + return true; + } + return false; +} + +/* + * allocate a new signal queue record + * - this may be called without locks if and only if t == current, otherwise an + * appropriate lock must be held to stop the target task from exiting + */ +static struct sigqueue * +__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit) { struct sigqueue *q = NULL; + struct user_struct *user; + + /* + * Protect access to @t credentials. This can go away when all + * callers hold rcu read lock. + */ + rcu_read_lock(); + user = get_uid(__task_cred(t)->user); + atomic_inc(&user->sigpending); + rcu_read_unlock(); - atomic_inc(&t->user->sigpending); if (override_rlimit || - atomic_read(&t->user->sigpending) <= - t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur) + atomic_read(&user->sigpending) <= + task_rlimit(t, RLIMIT_SIGPENDING)) { q = kmem_cache_alloc(sigqueue_cachep, flags); + } else { + print_dropped_signal(sig); + } + if (unlikely(q == NULL)) { - atomic_dec(&t->user->sigpending); + atomic_dec(&user->sigpending); + free_uid(user); } else { INIT_LIST_HEAD(&q->list); q->flags = 0; - q->user = get_uid(t->user); + q->user = user; } - return(q); + + return q; } -static inline void __sigqueue_free(struct sigqueue *q) +static void __sigqueue_free(struct sigqueue *q) { if (q->flags & SIGQUEUE_PREALLOC) return; @@ -292,7 +401,7 @@ static inline void __sigqueue_free(struct sigqueue *q) kmem_cache_free(sigqueue_cachep, q); } -static void flush_sigqueue(struct sigpending *queue) +void flush_sigqueue(struct sigpending *queue) { struct sigqueue *q; @@ -307,120 +416,64 @@ static void flush_sigqueue(struct sigpending *queue) /* * Flush all pending signals for a task. */ +void __flush_signals(struct task_struct *t) +{ + clear_tsk_thread_flag(t, TIF_SIGPENDING); + flush_sigqueue(&t->pending); + flush_sigqueue(&t->signal->shared_pending); +} -void -flush_signals(struct task_struct *t) +void flush_signals(struct task_struct *t) { unsigned long flags; spin_lock_irqsave(&t->sighand->siglock, flags); - clear_tsk_thread_flag(t,TIF_SIGPENDING); - flush_sigqueue(&t->pending); - flush_sigqueue(&t->signal->shared_pending); + __flush_signals(t); spin_unlock_irqrestore(&t->sighand->siglock, flags); } -/* - * This function expects the tasklist_lock write-locked. - */ -void __exit_sighand(struct task_struct *tsk) +static void __flush_itimer_signals(struct sigpending *pending) { - struct sighand_struct * sighand = tsk->sighand; + sigset_t signal, retain; + struct sigqueue *q, *n; - /* Ok, we're done with the signal handlers */ - tsk->sighand = NULL; - if (atomic_dec_and_test(&sighand->count)) - sighand_free(sighand); -} + signal = pending->signal; + sigemptyset(&retain); -void exit_sighand(struct task_struct *tsk) -{ - write_lock_irq(&tasklist_lock); - rcu_read_lock(); - if (tsk->sighand != NULL) { - struct sighand_struct *sighand = rcu_dereference(tsk->sighand); - spin_lock(&sighand->siglock); - __exit_sighand(tsk); - spin_unlock(&sighand->siglock); + list_for_each_entry_safe(q, n, &pending->list, list) { + int sig = q->info.si_signo; + + if (likely(q->info.si_code != SI_TIMER)) { + sigaddset(&retain, sig); + } else { + sigdelset(&signal, sig); + list_del_init(&q->list); + __sigqueue_free(q); + } } - rcu_read_unlock(); - write_unlock_irq(&tasklist_lock); + + sigorsets(&pending->signal, &signal, &retain); } -/* - * This function expects the tasklist_lock write-locked. - */ -void __exit_signal(struct task_struct *tsk) +void flush_itimer_signals(void) { - struct signal_struct * sig = tsk->signal; - struct sighand_struct * sighand; + struct task_struct *tsk = current; + unsigned long flags; - if (!sig) - BUG(); - if (!atomic_read(&sig->count)) - BUG(); - rcu_read_lock(); - sighand = rcu_dereference(tsk->sighand); - spin_lock(&sighand->siglock); - posix_cpu_timers_exit(tsk); - if (atomic_dec_and_test(&sig->count)) { - posix_cpu_timers_exit_group(tsk); - tsk->signal = NULL; - __exit_sighand(tsk); - spin_unlock(&sighand->siglock); - flush_sigqueue(&sig->shared_pending); - } else { - /* - * If there is any task waiting for the group exit - * then notify it: - */ - if (sig->group_exit_task && atomic_read(&sig->count) == sig->notify_count) { - wake_up_process(sig->group_exit_task); - sig->group_exit_task = NULL; - } - if (tsk == sig->curr_target) - sig->curr_target = next_thread(tsk); - tsk->signal = NULL; - /* - * Accumulate here the counters for all threads but the - * group leader as they die, so they can be added into - * the process-wide totals when those are taken. - * The group leader stays around as a zombie as long - * as there are other threads. When it gets reaped, - * the exit.c code will add its counts into these totals. - * We won't ever get here for the group leader, since it - * will have been the last reference on the signal_struct. - */ - sig->utime = cputime_add(sig->utime, tsk->utime); - sig->stime = cputime_add(sig->stime, tsk->stime); - sig->min_flt += tsk->min_flt; - sig->maj_flt += tsk->maj_flt; - sig->nvcsw += tsk->nvcsw; - sig->nivcsw += tsk->nivcsw; - sig->sched_time += tsk->sched_time; - __exit_sighand(tsk); - spin_unlock(&sighand->siglock); - sig = NULL; /* Marker for below. */ - } - rcu_read_unlock(); - clear_tsk_thread_flag(tsk,TIF_SIGPENDING); - flush_sigqueue(&tsk->pending); - if (sig) { - /* - * We are cleaning up the signal_struct here. - */ - exit_thread_group_keys(sig); - kmem_cache_free(signal_cachep, sig); - } + spin_lock_irqsave(&tsk->sighand->siglock, flags); + __flush_itimer_signals(&tsk->pending); + __flush_itimer_signals(&tsk->signal->shared_pending); + spin_unlock_irqrestore(&tsk->sighand->siglock, flags); } -void exit_signal(struct task_struct *tsk) +void ignore_signals(struct task_struct *t) { - atomic_dec(&tsk->signal->live); + int i; + + for (i = 0; i < _NSIG; ++i) + t->sighand->action[i].sa.sa_handler = SIG_IGN; - write_lock_irq(&tasklist_lock); - __exit_signal(tsk); - write_unlock_irq(&tasklist_lock); + flush_signals(t); } /* @@ -436,20 +489,34 @@ flush_signal_handlers(struct task_struct *t, int force_default) if (force_default || ka->sa.sa_handler != SIG_IGN) ka->sa.sa_handler = SIG_DFL; ka->sa.sa_flags = 0; +#ifdef __ARCH_HAS_SA_RESTORER + ka->sa.sa_restorer = NULL; +#endif sigemptyset(&ka->sa.sa_mask); ka++; } } +int unhandled_signal(struct task_struct *tsk, int sig) +{ + void __user *handler = tsk->sighand->action[sig-1].sa.sa_handler; + if (is_global_init(tsk)) + return 1; + if (handler != SIG_IGN && handler != SIG_DFL) + return 0; + /* if ptraced, let the tracer determine */ + return !tsk->ptrace; +} -/* Notify the system that a driver wants to block all signals for this +/* + * Notify the system that a driver wants to block all signals for this * process, and wants to be notified if any signals at all were to be * sent/acted upon. If the notifier routine returns non-zero, then the * signal will be acted upon after all. If the notifier routine returns 0, * then then signal will be blocked. Only one block per process is * allowed. priv is a pointer to private data that the notifier routine - * can use to determine if the signal should be blocked or not. */ - + * can use to determine if the signal should be blocked or not. + */ void block_all_signals(int (*notifier)(void *priv), void *priv, sigset_t *mask) { @@ -476,13 +543,9 @@ unblock_all_signals(void) spin_unlock_irqrestore(¤t->sighand->siglock, flags); } -static int collect_signal(int sig, struct sigpending *list, siginfo_t *info) +static void collect_signal(int sig, struct sigpending *list, siginfo_t *info) { struct sigqueue *q, *first = NULL; - int still_pending = 0; - - if (unlikely(!sigismember(&list->signal, sig))) - return 0; /* * Collect the siginfo appropriate to this signal. Check if @@ -490,41 +553,38 @@ static int collect_signal(int sig, struct sigpending *list, siginfo_t *info) */ list_for_each_entry(q, &list->list, list) { if (q->info.si_signo == sig) { - if (first) { - still_pending = 1; - break; - } + if (first) + goto still_pending; first = q; } } + + sigdelset(&list->signal, sig); + if (first) { +still_pending: list_del_init(&first->list); copy_siginfo(info, &first->info); __sigqueue_free(first); - if (!still_pending) - sigdelset(&list->signal, sig); } else { - - /* Ok, it wasn't in the queue. This must be - a fast-pathed signal or we must have been - out of queue space. So zero out the info. + /* + * Ok, it wasn't in the queue. This must be + * a fast-pathed signal or we must have been + * out of queue space. So zero out the info. */ - sigdelset(&list->signal, sig); info->si_signo = sig; info->si_errno = 0; - info->si_code = 0; + info->si_code = SI_USER; info->si_pid = 0; info->si_uid = 0; } - return 1; } static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, siginfo_t *info) { - int sig = 0; + int sig = next_signal(pending, mask); - sig = next_signal(pending, mask); if (sig) { if (current->notifier) { if (sigismember(current->notifier_mask, sig)) { @@ -535,46 +595,74 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, } } - if (!collect_signal(sig, pending, info)) - sig = 0; - + collect_signal(sig, pending, info); } - recalc_sigpending(); return sig; } /* - * Dequeue a signal and return the element to the caller, which is + * Dequeue a signal and return the element to the caller, which is * expected to free it. * * All callers have to hold the siglock. */ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) { - int signr = __dequeue_signal(&tsk->pending, mask, info); - if (!signr) + int signr; + + /* We only dequeue private signals from ourselves, we don't let + * signalfd steal them + */ + signr = __dequeue_signal(&tsk->pending, mask, info); + if (!signr) { signr = __dequeue_signal(&tsk->signal->shared_pending, mask, info); - if (signr && unlikely(sig_kernel_stop(signr))) { - /* - * Set a marker that we have dequeued a stop signal. Our - * caller might release the siglock and then the pending - * stop signal it is about to process is no longer in the - * pending bitmasks, but must still be cleared by a SIGCONT - * (and overruled by a SIGKILL). So those cases clear this - * shared flag after we've set it. Note that this flag may - * remain set after the signal we return is ignored or - * handled. That doesn't matter because its only purpose - * is to alert stop-signal processing code when another - * processor has come along and cleared the flag. - */ - if (!(tsk->signal->flags & SIGNAL_GROUP_EXIT)) - tsk->signal->flags |= SIGNAL_STOP_DEQUEUED; - } - if ( signr && - ((info->si_code & __SI_MASK) == __SI_TIMER) && - info->si_sys_private){ + /* + * itimer signal ? + * + * itimers are process shared and we restart periodic + * itimers in the signal delivery path to prevent DoS + * attacks in the high resolution timer case. This is + * compliant with the old way of self-restarting + * itimers, as the SIGALRM is a legacy signal and only + * queued once. Changing the restart behaviour to + * restart the timer in the signal dequeue path is + * reducing the timer noise on heavy loaded !highres + * systems too. + */ + if (unlikely(signr == SIGALRM)) { + struct hrtimer *tmr = &tsk->signal->real_timer; + + if (!hrtimer_is_queued(tmr) && + tsk->signal->it_real_incr.tv64 != 0) { + hrtimer_forward(tmr, tmr->base->get_time(), + tsk->signal->it_real_incr); + hrtimer_restart(tmr); + } + } + } + + recalc_sigpending(); + if (!signr) + return 0; + + if (unlikely(sig_kernel_stop(signr))) { + /* + * Set a marker that we have dequeued a stop signal. Our + * caller might release the siglock and then the pending + * stop signal it is about to process is no longer in the + * pending bitmasks, but must still be cleared by a SIGCONT + * (and overruled by a SIGKILL). So those cases clear this + * shared flag after we've set it. Note that this flag may + * remain set after the signal we return is ignored or + * handled. That doesn't matter because its only purpose + * is to alert stop-signal processing code when another + * processor has come along and cleared the flag. + */ + current->jobctl |= JOBCTL_STOP_DEQUEUED; + } + if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) { /* * Release the siglock to ensure proper locking order * of timer locks outside of siglocks. Note, we leave @@ -599,23 +687,17 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) * No need to set need_resched since signal event passing * goes through ->blocked */ -void signal_wake_up(struct task_struct *t, int resume) +void signal_wake_up_state(struct task_struct *t, unsigned int state) { - unsigned int mask; - set_tsk_thread_flag(t, TIF_SIGPENDING); - /* - * For SIGKILL, we want to wake it up in the stopped/traced case. - * We don't check t->state here because there is a race with it + * TASK_WAKEKILL also means wake it up in the stopped/traced/killable + * case. We don't check t->state here because there is a race with it * executing another processor and just now entering stopped state. * By using wake_up_state, we ensure the process will wake up and * handle its death signal. */ - mask = TASK_INTERRUPTIBLE; - if (resume) - mask |= TASK_STOPPED | TASK_TRACED; - if (!wake_up_state(t, mask)) + if (!wake_up_state(t, state | TASK_INTERRUPTIBLE)) kick_process(t); } @@ -624,11 +706,8 @@ void signal_wake_up(struct task_struct *t, int resume) * Returns 1 if any signals were found. * * All callers must be holding the siglock. - * - * This version takes a sigset mask and looks at all signals, - * not just those in the first mask word. */ -static int rm_from_queue_full(sigset_t *mask, struct sigpending *s) +static int flush_sigqueue_mask(sigset_t *mask, struct sigpending *s) { struct sigqueue *q, *n; sigset_t m; @@ -637,7 +716,7 @@ static int rm_from_queue_full(sigset_t *mask, struct sigpending *s) if (sigisemptyset(&m)) return 0; - signandsets(&s->signal, &s->signal, mask); + sigandnsets(&s->signal, &s->signal, mask); list_for_each_entry_safe(q, n, &s->list, list) { if (sigismember(mask, q->info.si_signo)) { list_del_init(&q->list); @@ -646,285 +725,176 @@ static int rm_from_queue_full(sigset_t *mask, struct sigpending *s) } return 1; } + +static inline int is_si_special(const struct siginfo *info) +{ + return info <= SEND_SIG_FORCED; +} + +static inline bool si_fromuser(const struct siginfo *info) +{ + return info == SEND_SIG_NOINFO || + (!is_si_special(info) && SI_FROMUSER(info)); +} + /* - * Remove signals in mask from the pending set and queue. - * Returns 1 if any signals were found. - * - * All callers must be holding the siglock. + * called with RCU read lock from check_kill_permission() */ -static int rm_from_queue(unsigned long mask, struct sigpending *s) +static int kill_ok_by_cred(struct task_struct *t) { - struct sigqueue *q, *n; + const struct cred *cred = current_cred(); + const struct cred *tcred = __task_cred(t); - if (!sigtestsetmask(&s->signal, mask)) - return 0; + if (uid_eq(cred->euid, tcred->suid) || + uid_eq(cred->euid, tcred->uid) || + uid_eq(cred->uid, tcred->suid) || + uid_eq(cred->uid, tcred->uid)) + return 1; - sigdelsetmask(&s->signal, mask); - list_for_each_entry_safe(q, n, &s->list, list) { - if (q->info.si_signo < SIGRTMIN && - (mask & sigmask(q->info.si_signo))) { - list_del_init(&q->list); - __sigqueue_free(q); - } - } - return 1; + if (ns_capable(tcred->user_ns, CAP_KILL)) + return 1; + + return 0; } /* * Bad permissions for sending the signal + * - the caller must hold the RCU read lock */ static int check_kill_permission(int sig, struct siginfo *info, struct task_struct *t) { - int error = -EINVAL; + struct pid *sid; + int error; + if (!valid_signal(sig)) - return error; - error = -EPERM; - if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info))) - && ((sig != SIGCONT) || - (current->signal->session != t->signal->session)) - && (current->euid ^ t->suid) && (current->euid ^ t->uid) - && (current->uid ^ t->suid) && (current->uid ^ t->uid) - && !capable(CAP_KILL)) + return -EINVAL; + + if (!si_fromuser(info)) + return 0; + + error = audit_signal_info(sig, t); /* Let audit system see the signal */ + if (error) return error; - error = security_task_kill(t, info, sig); - if (!error) - audit_signal_info(sig, t); /* Let audit system see the signal */ - return error; + if (!same_thread_group(current, t) && + !kill_ok_by_cred(t)) { + switch (sig) { + case SIGCONT: + sid = task_session(t); + /* + * We don't return the error if sid == NULL. The + * task was unhashed, the caller must notice this. + */ + if (!sid || sid == task_session(current)) + break; + default: + return -EPERM; + } + } + + return security_task_kill(t, info, sig, 0); } -/* forward decl */ -static void do_notify_parent_cldstop(struct task_struct *tsk, - int to_self, - int why); +/** + * ptrace_trap_notify - schedule trap to notify ptracer + * @t: tracee wanting to notify tracer + * + * This function schedules sticky ptrace trap which is cleared on the next + * TRAP_STOP to notify ptracer of an event. @t must have been seized by + * ptracer. + * + * If @t is running, STOP trap will be taken. If trapped for STOP and + * ptracer is listening for events, tracee is woken up so that it can + * re-trap for the new event. If trapped otherwise, STOP trap will be + * eventually taken without returning to userland after the existing traps + * are finished by PTRACE_CONT. + * + * CONTEXT: + * Must be called with @task->sighand->siglock held. + */ +static void ptrace_trap_notify(struct task_struct *t) +{ + WARN_ON_ONCE(!(t->ptrace & PT_SEIZED)); + assert_spin_locked(&t->sighand->siglock); + + task_set_jobctl_pending(t, JOBCTL_TRAP_NOTIFY); + ptrace_signal_wake_up(t, t->jobctl & JOBCTL_LISTENING); +} /* - * Handle magic process-wide effects of stop/continue signals. - * Unlike the signal actions, these happen immediately at signal-generation + * Handle magic process-wide effects of stop/continue signals. Unlike + * the signal actions, these happen immediately at signal-generation * time regardless of blocking, ignoring, or handling. This does the * actual continuing for SIGCONT, but not the actual stopping for stop - * signals. The process stop is done as a signal action for SIG_DFL. + * signals. The process stop is done as a signal action for SIG_DFL. + * + * Returns true if the signal should be actually delivered, otherwise + * it should be dropped. */ -static void handle_stop_signal(int sig, struct task_struct *p) +static bool prepare_signal(int sig, struct task_struct *p, bool force) { + struct signal_struct *signal = p->signal; struct task_struct *t; + sigset_t flush; - if (p->signal->flags & SIGNAL_GROUP_EXIT) + if (signal->flags & (SIGNAL_GROUP_EXIT | SIGNAL_GROUP_COREDUMP)) { + if (signal->flags & SIGNAL_GROUP_COREDUMP) + return sig == SIGKILL; /* - * The process is in the middle of dying already. + * The process is in the middle of dying, nothing to do. */ - return; - - if (sig_kernel_stop(sig)) { + } else if (sig_kernel_stop(sig)) { /* * This is a stop signal. Remove SIGCONT from all queues. */ - rm_from_queue(sigmask(SIGCONT), &p->signal->shared_pending); - t = p; - do { - rm_from_queue(sigmask(SIGCONT), &t->pending); - t = next_thread(t); - } while (t != p); + siginitset(&flush, sigmask(SIGCONT)); + flush_sigqueue_mask(&flush, &signal->shared_pending); + for_each_thread(p, t) + flush_sigqueue_mask(&flush, &t->pending); } else if (sig == SIGCONT) { + unsigned int why; /* - * Remove all stop signals from all queues, - * and wake all threads. + * Remove all stop signals from all queues, wake all threads. */ - if (unlikely(p->signal->group_stop_count > 0)) { - /* - * There was a group stop in progress. We'll - * pretend it finished before we got here. We are - * obliged to report it to the parent: if the - * SIGSTOP happened "after" this SIGCONT, then it - * would have cleared this pending SIGCONT. If it - * happened "before" this SIGCONT, then the parent - * got the SIGCHLD about the stop finishing before - * the continue happened. We do the notification - * now, and it's as if the stop had finished and - * the SIGCHLD was pending on entry to this kill. - */ - p->signal->group_stop_count = 0; - p->signal->flags = SIGNAL_STOP_CONTINUED; - spin_unlock(&p->sighand->siglock); - do_notify_parent_cldstop(p, (p->ptrace & PT_PTRACED), CLD_STOPPED); - spin_lock(&p->sighand->siglock); + siginitset(&flush, SIG_KERNEL_STOP_MASK); + flush_sigqueue_mask(&flush, &signal->shared_pending); + for_each_thread(p, t) { + flush_sigqueue_mask(&flush, &t->pending); + task_clear_jobctl_pending(t, JOBCTL_STOP_PENDING); + if (likely(!(t->ptrace & PT_SEIZED))) + wake_up_state(t, __TASK_STOPPED); + else + ptrace_trap_notify(t); } - rm_from_queue(SIG_KERNEL_STOP_MASK, &p->signal->shared_pending); - t = p; - do { - unsigned int state; - rm_from_queue(SIG_KERNEL_STOP_MASK, &t->pending); - - /* - * If there is a handler for SIGCONT, we must make - * sure that no thread returns to user mode before - * we post the signal, in case it was the only - * thread eligible to run the signal handler--then - * it must not do anything between resuming and - * running the handler. With the TIF_SIGPENDING - * flag set, the thread will pause and acquire the - * siglock that we hold now and until we've queued - * the pending signal. - * - * Wake up the stopped thread _after_ setting - * TIF_SIGPENDING - */ - state = TASK_STOPPED; - if (sig_user_defined(t, SIGCONT) && !sigismember(&t->blocked, SIGCONT)) { - set_tsk_thread_flag(t, TIF_SIGPENDING); - state |= TASK_INTERRUPTIBLE; - } - wake_up_state(t, state); - t = next_thread(t); - } while (t != p); - - if (p->signal->flags & SIGNAL_STOP_STOPPED) { - /* - * We were in fact stopped, and are now continued. - * Notify the parent with CLD_CONTINUED. - */ - p->signal->flags = SIGNAL_STOP_CONTINUED; - p->signal->group_exit_code = 0; - spin_unlock(&p->sighand->siglock); - do_notify_parent_cldstop(p, (p->ptrace & PT_PTRACED), CLD_CONTINUED); - spin_lock(&p->sighand->siglock); - } else { - /* - * We are not stopped, but there could be a stop - * signal in the middle of being processed after - * being removed from the queue. Clear that too. - */ - p->signal->flags = 0; - } - } else if (sig == SIGKILL) { /* - * Make sure that any pending stop signal already dequeued - * is undone by the wakeup for SIGKILL. + * Notify the parent with CLD_CONTINUED if we were stopped. + * + * If we were in the middle of a group stop, we pretend it + * was already finished, and then continued. Since SIGCHLD + * doesn't queue we report only CLD_STOPPED, as if the next + * CLD_CONTINUED was dropped. */ - p->signal->flags = 0; - } -} - -static int send_signal(int sig, struct siginfo *info, struct task_struct *t, - struct sigpending *signals) -{ - struct sigqueue * q = NULL; - int ret = 0; + why = 0; + if (signal->flags & SIGNAL_STOP_STOPPED) + why |= SIGNAL_CLD_CONTINUED; + else if (signal->group_stop_count) + why |= SIGNAL_CLD_STOPPED; - /* - * fast-pathed signals for kernel-internal things like SIGSTOP - * or SIGKILL. - */ - if (info == SEND_SIG_FORCED) - goto out_set; - - /* Real-time signals must be queued if sent by sigqueue, or - some other real-time mechanism. It is implementation - defined whether kill() does so. We attempt to do so, on - the principle of least surprise, but since kill is not - allowed to fail with EAGAIN when low on memory we just - make sure at least one signal gets delivered and don't - pass on the info struct. */ - - q = __sigqueue_alloc(t, GFP_ATOMIC, (sig < SIGRTMIN && - (is_si_special(info) || - info->si_code >= 0))); - if (q) { - list_add_tail(&q->list, &signals->list); - switch ((unsigned long) info) { - case (unsigned long) SEND_SIG_NOINFO: - q->info.si_signo = sig; - q->info.si_errno = 0; - q->info.si_code = SI_USER; - q->info.si_pid = current->pid; - q->info.si_uid = current->uid; - break; - case (unsigned long) SEND_SIG_PRIV: - q->info.si_signo = sig; - q->info.si_errno = 0; - q->info.si_code = SI_KERNEL; - q->info.si_pid = 0; - q->info.si_uid = 0; - break; - default: - copy_siginfo(&q->info, info); - break; + if (why) { + /* + * The first thread which returns from do_signal_stop() + * will take ->siglock, notice SIGNAL_CLD_MASK, and + * notify its parent. See get_signal_to_deliver(). + */ + signal->flags = why | SIGNAL_STOP_CONTINUED; + signal->group_stop_count = 0; + signal->group_exit_code = 0; } - } else if (!is_si_special(info)) { - if (sig >= SIGRTMIN && info->si_code != SI_USER) - /* - * Queue overflow, abort. We may abort if the signal was rt - * and sent by user using something other than kill(). - */ - return -EAGAIN; } -out_set: - sigaddset(&signals->signal, sig); - return ret; -} - -#define LEGACY_QUEUE(sigptr, sig) \ - (((sig) < SIGRTMIN) && sigismember(&(sigptr)->signal, (sig))) - - -static int -specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t) -{ - int ret = 0; - - if (!irqs_disabled()) - BUG(); - assert_spin_locked(&t->sighand->siglock); - - /* Short-circuit ignored signals. */ - if (sig_ignored(t, sig)) - goto out; - - /* Support queueing exactly one non-rt signal, so that we - can get more detailed information about the cause of - the signal. */ - if (LEGACY_QUEUE(&t->pending, sig)) - goto out; - - ret = send_signal(sig, info, t, &t->pending); - if (!ret && !sigismember(&t->blocked, sig)) - signal_wake_up(t, sig == SIGKILL); -out: - return ret; -} - -/* - * Force a signal that the process can't ignore: if necessary - * we unblock the signal and change any SIG_IGN to SIG_DFL. - */ - -int -force_sig_info(int sig, struct siginfo *info, struct task_struct *t) -{ - unsigned long int flags; - int ret; - - spin_lock_irqsave(&t->sighand->siglock, flags); - if (t->sighand->action[sig-1].sa.sa_handler == SIG_IGN) { - t->sighand->action[sig-1].sa.sa_handler = SIG_DFL; - } - if (sigismember(&t->blocked, sig)) { - sigdelset(&t->blocked, sig); - } - recalc_sigpending_tsk(t); - ret = specific_send_sig_info(sig, info, t); - spin_unlock_irqrestore(&t->sighand->siglock, flags); - - return ret; -} - -void -force_sig_specific(int sig, struct task_struct *t) -{ - force_sig_info(sig, SEND_SIG_FORCED, t); + return !sig_ignored(p, sig, force); } /* @@ -943,14 +913,14 @@ static inline int wants_signal(int sig, struct task_struct *p) return 0; if (sig == SIGKILL) return 1; - if (p->state & (TASK_STOPPED | TASK_TRACED)) + if (task_is_stopped_or_traced(p)) return 0; return task_curr(p) || !signal_pending(p); } -static void -__group_complete_signal(int sig, struct task_struct *p) +static void complete_signal(int sig, struct task_struct *p, int group) { + struct signal_struct *signal = p->signal; struct task_struct *t; /* @@ -961,7 +931,7 @@ __group_complete_signal(int sig, struct task_struct *p) */ if (wants_signal(sig, p)) t = p; - else if (thread_group_empty(p)) + else if (!group || thread_group_empty(p)) /* * There is just one thread and it does not need to be woken. * It will dequeue unblocked signals before it runs again. @@ -971,15 +941,10 @@ __group_complete_signal(int sig, struct task_struct *p) /* * Otherwise try to find a suitable thread. */ - t = p->signal->curr_target; - if (t == NULL) - /* restart balancing at this thread */ - t = p->signal->curr_target = p; - BUG_ON(t->tgid != p->tgid); - + t = signal->curr_target; while (!wants_signal(sig, t)) { t = next_thread(t); - if (t == p->signal->curr_target) + if (t == signal->curr_target) /* * No thread needs to be woken. * Any eligible threads will see @@ -987,16 +952,17 @@ __group_complete_signal(int sig, struct task_struct *p) */ return; } - p->signal->curr_target = t; + signal->curr_target = t; } /* * Found a killable thread. If the signal will be fatal, * then start taking the whole group down immediately. */ - if (sig_fatal(p, sig) && !(p->signal->flags & SIGNAL_GROUP_EXIT) && + if (sig_fatal(p, sig) && + !(signal->flags & (SIGNAL_UNKILLABLE | SIGNAL_GROUP_EXIT)) && !sigismember(&t->real_blocked, sig) && - (sig == SIGKILL || !(t->ptrace & PT_PTRACED))) { + (sig == SIGKILL || !t->ptrace)) { /* * This signal will be fatal to the whole group. */ @@ -1007,40 +973,17 @@ __group_complete_signal(int sig, struct task_struct *p) * running and doing things after a slower * thread has the fatal signal pending. */ - p->signal->flags = SIGNAL_GROUP_EXIT; - p->signal->group_exit_code = sig; - p->signal->group_stop_count = 0; + signal->flags = SIGNAL_GROUP_EXIT; + signal->group_exit_code = sig; + signal->group_stop_count = 0; t = p; do { + task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); - t = next_thread(t); - } while (t != p); + } while_each_thread(p, t); return; } - - /* - * There will be a core dump. We make all threads other - * than the chosen one go into a group stop so that nothing - * happens until it gets scheduled, takes the signal off - * the shared queue, and does the core dump. This is a - * little more complicated than strictly necessary, but it - * keeps the signal state that winds up in the core dump - * unchanged from the death state, e.g. which thread had - * the core-dump signal unblocked. - */ - rm_from_queue(SIG_KERNEL_STOP_MASK, &t->pending); - rm_from_queue(SIG_KERNEL_STOP_MASK, &p->signal->shared_pending); - p->signal->group_stop_count = 0; - p->signal->group_exit_task = t; - t = p; - do { - p->signal->group_stop_count++; - signal_wake_up(t, 0); - t = next_thread(t); - } while (t != p); - wake_up_process(p->signal->group_exit_task); - return; } /* @@ -1051,191 +994,414 @@ __group_complete_signal(int sig, struct task_struct *p) return; } -int -__group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) +static inline int legacy_queue(struct sigpending *signals, int sig) { - int ret = 0; + return (sig < SIGRTMIN) && sigismember(&signals->signal, sig); +} - assert_spin_locked(&p->sighand->siglock); - handle_stop_signal(sig, p); +#ifdef CONFIG_USER_NS +static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_struct *t) +{ + if (current_user_ns() == task_cred_xxx(t, user_ns)) + return; - /* Short-circuit ignored signals. */ - if (sig_ignored(p, sig)) - return ret; + if (SI_FROMKERNEL(info)) + return; - if (LEGACY_QUEUE(&p->signal->shared_pending, sig)) - /* This is a non-RT signal and we already have one queued. */ - return ret; + rcu_read_lock(); + info->si_uid = from_kuid_munged(task_cred_xxx(t, user_ns), + make_kuid(current_user_ns(), info->si_uid)); + rcu_read_unlock(); +} +#else +static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_struct *t) +{ + return; +} +#endif + +static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, + int group, int from_ancestor_ns) +{ + struct sigpending *pending; + struct sigqueue *q; + int override_rlimit; + int ret = 0, result; + + assert_spin_locked(&t->sighand->siglock); + result = TRACE_SIGNAL_IGNORED; + if (!prepare_signal(sig, t, + from_ancestor_ns || (info == SEND_SIG_FORCED))) + goto ret; + + pending = group ? &t->signal->shared_pending : &t->pending; /* - * Put this signal on the shared-pending queue, or fail with EAGAIN. - * We always use the shared queue for process-wide signals, - * to avoid several races. + * Short-circuit ignored signals and support queuing + * exactly one non-rt signal, so that we can get more + * detailed information about the cause of the signal. */ - ret = send_signal(sig, info, p, &p->signal->shared_pending); - if (unlikely(ret)) - return ret; + result = TRACE_SIGNAL_ALREADY_PENDING; + if (legacy_queue(pending, sig)) + goto ret; - __group_complete_signal(sig, p); - return 0; + result = TRACE_SIGNAL_DELIVERED; + /* + * fast-pathed signals for kernel-internal things like SIGSTOP + * or SIGKILL. + */ + if (info == SEND_SIG_FORCED) + goto out_set; + + /* + * Real-time signals must be queued if sent by sigqueue, or + * some other real-time mechanism. It is implementation + * defined whether kill() does so. We attempt to do so, on + * the principle of least surprise, but since kill is not + * allowed to fail with EAGAIN when low on memory we just + * make sure at least one signal gets delivered and don't + * pass on the info struct. + */ + if (sig < SIGRTMIN) + override_rlimit = (is_si_special(info) || info->si_code >= 0); + else + override_rlimit = 0; + + q = __sigqueue_alloc(sig, t, GFP_ATOMIC | __GFP_NOTRACK_FALSE_POSITIVE, + override_rlimit); + if (q) { + list_add_tail(&q->list, &pending->list); + switch ((unsigned long) info) { + case (unsigned long) SEND_SIG_NOINFO: + q->info.si_signo = sig; + q->info.si_errno = 0; + q->info.si_code = SI_USER; + q->info.si_pid = task_tgid_nr_ns(current, + task_active_pid_ns(t)); + q->info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); + break; + case (unsigned long) SEND_SIG_PRIV: + q->info.si_signo = sig; + q->info.si_errno = 0; + q->info.si_code = SI_KERNEL; + q->info.si_pid = 0; + q->info.si_uid = 0; + break; + default: + copy_siginfo(&q->info, info); + if (from_ancestor_ns) + q->info.si_pid = 0; + break; + } + + userns_fixup_signal_uid(&q->info, t); + + } else if (!is_si_special(info)) { + if (sig >= SIGRTMIN && info->si_code != SI_USER) { + /* + * Queue overflow, abort. We may abort if the + * signal was rt and sent by user using something + * other than kill(). + */ + result = TRACE_SIGNAL_OVERFLOW_FAIL; + ret = -EAGAIN; + goto ret; + } else { + /* + * This is a silent loss of information. We still + * send the signal, but the *info bits are lost. + */ + result = TRACE_SIGNAL_LOSE_INFO; + } + } + +out_set: + signalfd_notify(t, sig); + sigaddset(&pending->signal, sig); + complete_signal(sig, t, group); +ret: + trace_signal_generate(sig, info, t, group, result); + return ret; +} + +static int send_signal(int sig, struct siginfo *info, struct task_struct *t, + int group) +{ + int from_ancestor_ns = 0; + +#ifdef CONFIG_PID_NS + from_ancestor_ns = si_fromuser(info) && + !task_pid_nr_ns(current, task_active_pid_ns(t)); +#endif + + return __send_signal(sig, info, t, group, from_ancestor_ns); +} + +static void print_fatal_signal(int signr) +{ + struct pt_regs *regs = signal_pt_regs(); + printk(KERN_INFO "potentially unexpected fatal signal %d.\n", signr); + +#if defined(__i386__) && !defined(__arch_um__) + printk(KERN_INFO "code at %08lx: ", regs->ip); + { + int i; + for (i = 0; i < 16; i++) { + unsigned char insn; + + if (get_user(insn, (unsigned char *)(regs->ip + i))) + break; + printk(KERN_CONT "%02x ", insn); + } + } + printk(KERN_CONT "\n"); +#endif + preempt_disable(); + show_regs(regs); + preempt_enable(); +} + +static int __init setup_print_fatal_signals(char *str) +{ + get_option (&str, &print_fatal_signals); + + return 1; +} + +__setup("print-fatal-signals=", setup_print_fatal_signals); + +int +__group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) +{ + return send_signal(sig, info, p, 1); +} + +static int +specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t) +{ + return send_signal(sig, info, t, 0); +} + +int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, + bool group) +{ + unsigned long flags; + int ret = -ESRCH; + + if (lock_task_sighand(p, &flags)) { + ret = send_signal(sig, info, p, group); + unlock_task_sighand(p, &flags); + } + + return ret; +} + +/* + * Force a signal that the process can't ignore: if necessary + * we unblock the signal and change any SIG_IGN to SIG_DFL. + * + * Note: If we unblock the signal, we always reset it to SIG_DFL, + * since we do not want to have a signal handler that was blocked + * be invoked when user space had explicitly blocked it. + * + * We don't want to have recursive SIGSEGV's etc, for example, + * that is why we also clear SIGNAL_UNKILLABLE. + */ +int +force_sig_info(int sig, struct siginfo *info, struct task_struct *t) +{ + unsigned long int flags; + int ret, blocked, ignored; + struct k_sigaction *action; + + spin_lock_irqsave(&t->sighand->siglock, flags); + action = &t->sighand->action[sig-1]; + ignored = action->sa.sa_handler == SIG_IGN; + blocked = sigismember(&t->blocked, sig); + if (blocked || ignored) { + action->sa.sa_handler = SIG_DFL; + if (blocked) { + sigdelset(&t->blocked, sig); + recalc_sigpending_and_wake(t); + } + } + if (action->sa.sa_handler == SIG_DFL) + t->signal->flags &= ~SIGNAL_UNKILLABLE; + ret = specific_send_sig_info(sig, info, t); + spin_unlock_irqrestore(&t->sighand->siglock, flags); + + return ret; } /* * Nuke all other threads in the group. */ -void zap_other_threads(struct task_struct *p) +int zap_other_threads(struct task_struct *p) { - struct task_struct *t; + struct task_struct *t = p; + int count = 0; - p->signal->flags = SIGNAL_GROUP_EXIT; p->signal->group_stop_count = 0; - if (thread_group_empty(p)) - return; + while_each_thread(p, t) { + task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); + count++; - for (t = next_thread(p); t != p; t = next_thread(t)) { - /* - * Don't bother with already dead threads - */ + /* Don't bother with already dead threads */ if (t->exit_state) continue; - - /* - * We don't want to notify the parent, since we are - * killed as part of a thread group due to another - * thread doing an execve() or similar. So set the - * exit signal to -1 to allow immediate reaping of - * the process. But don't detach the thread group - * leader. - */ - if (t != p->group_leader) - t->exit_signal = -1; - - /* SIGKILL will be handled before any pending SIGSTOP */ sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); } + + return count; +} + +struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, + unsigned long *flags) +{ + struct sighand_struct *sighand; + + for (;;) { + local_irq_save(*flags); + rcu_read_lock(); + sighand = rcu_dereference(tsk->sighand); + if (unlikely(sighand == NULL)) { + rcu_read_unlock(); + local_irq_restore(*flags); + break; + } + + spin_lock(&sighand->siglock); + if (likely(sighand == tsk->sighand)) { + rcu_read_unlock(); + break; + } + spin_unlock(&sighand->siglock); + rcu_read_unlock(); + local_irq_restore(*flags); + } + + return sighand; } /* - * Must be called under rcu_read_lock() or with tasklist_lock read-held. + * send signal info to all the members of a group */ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) { - unsigned long flags; - struct sighand_struct *sp; int ret; -retry: + rcu_read_lock(); ret = check_kill_permission(sig, info, p); - if (!ret && sig && (sp = rcu_dereference(p->sighand))) { - spin_lock_irqsave(&sp->siglock, flags); - if (p->sighand != sp) { - spin_unlock_irqrestore(&sp->siglock, flags); - goto retry; - } - if ((atomic_read(&sp->count) == 0) || - (atomic_read(&p->usage) == 0)) { - spin_unlock_irqrestore(&sp->siglock, flags); - return -ESRCH; - } - ret = __group_send_sig_info(sig, info, p); - spin_unlock_irqrestore(&sp->siglock, flags); - } + rcu_read_unlock(); + + if (!ret && sig) + ret = do_send_sig_info(sig, info, p, true); return ret; } /* - * kill_pg_info() sends a signal to a process group: this is what the tty + * __kill_pgrp_info() sends a signal to a process group: this is what the tty * control characters do (^C, ^Z etc) + * - the caller must hold at least a readlock on tasklist_lock */ - -int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp) +int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp) { struct task_struct *p = NULL; int retval, success; - if (pgrp <= 0) - return -EINVAL; - success = 0; retval = -ESRCH; - do_each_task_pid(pgrp, PIDTYPE_PGID, p) { + do_each_pid_task(pgrp, PIDTYPE_PGID, p) { int err = group_send_sig_info(sig, info, p); success |= !err; retval = err; - } while_each_task_pid(pgrp, PIDTYPE_PGID, p); + } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return success ? 0 : retval; } -int -kill_pg_info(int sig, struct siginfo *info, pid_t pgrp) +int kill_pid_info(int sig, struct siginfo *info, struct pid *pid) { - int retval; + int error = -ESRCH; + struct task_struct *p; - read_lock(&tasklist_lock); - retval = __kill_pg_info(sig, info, pgrp); - read_unlock(&tasklist_lock); + rcu_read_lock(); +retry: + p = pid_task(pid, PIDTYPE_PID); + if (p) { + error = group_send_sig_info(sig, info, p); + if (unlikely(error == -ESRCH)) + /* + * The task was unhashed in between, try again. + * If it is dead, pid_task() will return NULL, + * if we race with de_thread() it will find the + * new leader. + */ + goto retry; + } + rcu_read_unlock(); - return retval; + return error; } -int -kill_proc_info(int sig, struct siginfo *info, pid_t pid) +int kill_proc_info(int sig, struct siginfo *info, pid_t pid) { int error; - int acquired_tasklist_lock = 0; - struct task_struct *p; - rcu_read_lock(); - if (unlikely(sig_kernel_stop(sig) || sig == SIGCONT)) { - read_lock(&tasklist_lock); - acquired_tasklist_lock = 1; - } - p = find_task_by_pid(pid); - error = -ESRCH; - if (p) - error = group_send_sig_info(sig, info, p); - if (unlikely(acquired_tasklist_lock)) - read_unlock(&tasklist_lock); + error = kill_pid_info(sig, info, find_vpid(pid)); rcu_read_unlock(); return error; } -/* like kill_proc_info(), but doesn't use uid/euid of "current" */ -int kill_proc_info_as_uid(int sig, struct siginfo *info, pid_t pid, - uid_t uid, uid_t euid) +static int kill_as_cred_perm(const struct cred *cred, + struct task_struct *target) +{ + const struct cred *pcred = __task_cred(target); + if (!uid_eq(cred->euid, pcred->suid) && !uid_eq(cred->euid, pcred->uid) && + !uid_eq(cred->uid, pcred->suid) && !uid_eq(cred->uid, pcred->uid)) + return 0; + return 1; +} + +/* like kill_pid_info(), but doesn't use uid/euid of "current" */ +int kill_pid_info_as_cred(int sig, struct siginfo *info, struct pid *pid, + const struct cred *cred, u32 secid) { int ret = -EINVAL; struct task_struct *p; + unsigned long flags; if (!valid_signal(sig)) return ret; - read_lock(&tasklist_lock); - p = find_task_by_pid(pid); + rcu_read_lock(); + p = pid_task(pid, PIDTYPE_PID); if (!p) { ret = -ESRCH; goto out_unlock; } - if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info))) - && (euid != p->suid) && (euid != p->uid) - && (uid != p->suid) && (uid != p->uid)) { + if (si_fromuser(info) && !kill_as_cred_perm(cred, p)) { ret = -EPERM; goto out_unlock; } - if (sig && p->sighand) { - unsigned long flags; - spin_lock_irqsave(&p->sighand->siglock, flags); - ret = __group_send_sig_info(sig, info, p); - spin_unlock_irqrestore(&p->sighand->siglock, flags); + ret = security_task_kill(p, info, sig, secid); + if (ret) + goto out_unlock; + + if (sig) { + if (lock_task_sighand(p, &flags)) { + ret = __send_signal(sig, info, p, 1, 0); + unlock_task_sighand(p, &flags); + } else + ret = -ESRCH; } out_unlock: - read_unlock(&tasklist_lock); + rcu_read_unlock(); return ret; } -EXPORT_SYMBOL_GPL(kill_proc_info_as_uid); +EXPORT_SYMBOL_GPL(kill_pid_info_as_cred); /* * kill_something_info() interprets pid in interesting ways just like kill(2). @@ -1244,46 +1410,47 @@ EXPORT_SYMBOL_GPL(kill_proc_info_as_uid); * is probably wrong. Should make it like BSD or SYSV. */ -static int kill_something_info(int sig, struct siginfo *info, int pid) +static int kill_something_info(int sig, struct siginfo *info, pid_t pid) { - if (!pid) { - return kill_pg_info(sig, info, process_group(current)); - } else if (pid == -1) { + int ret; + + if (pid > 0) { + rcu_read_lock(); + ret = kill_pid_info(sig, info, find_vpid(pid)); + rcu_read_unlock(); + return ret; + } + + read_lock(&tasklist_lock); + if (pid != -1) { + ret = __kill_pgrp_info(sig, info, + pid ? find_vpid(-pid) : task_pgrp(current)); + } else { int retval = 0, count = 0; struct task_struct * p; - read_lock(&tasklist_lock); for_each_process(p) { - if (p->pid > 1 && p->tgid != current->tgid) { + if (task_pid_vnr(p) > 1 && + !same_thread_group(p, current)) { int err = group_send_sig_info(sig, info, p); ++count; if (err != -EPERM) retval = err; } } - read_unlock(&tasklist_lock); - return count ? retval : -ESRCH; - } else if (pid < 0) { - return kill_pg_info(sig, info, -pid); - } else { - return kill_proc_info(sig, info, pid); + ret = count ? retval : -ESRCH; } + read_unlock(&tasklist_lock); + + return ret; } /* * These are for backward compatibility with the rest of the kernel source. */ -/* - * These two are the most common entry points. They send a signal - * just to the specific thread. - */ -int -send_sig_info(int sig, struct siginfo *info, struct task_struct *p) +int send_sig_info(int sig, struct siginfo *info, struct task_struct *p) { - int ret; - unsigned long flags; - /* * Make sure legacy kernel users don't send in bad values * (normal paths check this in check_kill_permission). @@ -1291,18 +1458,7 @@ send_sig_info(int sig, struct siginfo *info, struct task_struct *p) if (!valid_signal(sig)) return -EINVAL; - /* - * We need the tasklist lock even for the specific - * thread case (when we don't need to follow the group - * lists) in order to avoid races with "p->sighand" - * going away or changing from under us. - */ - read_lock(&tasklist_lock); - spin_lock_irqsave(&p->sighand->siglock, flags); - ret = specific_send_sig_info(sig, info, p); - spin_unlock_irqrestore(&p->sighand->siglock, flags); - read_unlock(&tasklist_lock); - return ret; + return do_send_sig_info(sig, info, p, false); } #define __si_special(priv) \ @@ -1314,20 +1470,6 @@ send_sig(int sig, struct task_struct *p, int priv) return send_sig_info(sig, __si_special(priv), p); } -/* - * This is the entry point for "process-wide" signals. - * They will go to an appropriate thread in the thread group. - */ -int -send_group_sig_info(int sig, struct siginfo *info, struct task_struct *p) -{ - int ret; - read_lock(&tasklist_lock); - ret = group_send_sig_info(sig, info, p); - read_unlock(&tasklist_lock); - return ret; -} - void force_sig(int sig, struct task_struct *p) { @@ -1353,225 +1495,166 @@ force_sigsegv(int sig, struct task_struct *p) return 0; } -int -kill_pg(pid_t pgrp, int sig, int priv) +int kill_pgrp(struct pid *pid, int sig, int priv) { - return kill_pg_info(sig, __si_special(priv), pgrp); + int ret; + + read_lock(&tasklist_lock); + ret = __kill_pgrp_info(sig, __si_special(priv), pid); + read_unlock(&tasklist_lock); + + return ret; } +EXPORT_SYMBOL(kill_pgrp); -int -kill_proc(pid_t pid, int sig, int priv) +int kill_pid(struct pid *pid, int sig, int priv) { - return kill_proc_info(sig, __si_special(priv), pid); + return kill_pid_info(sig, __si_special(priv), pid); } +EXPORT_SYMBOL(kill_pid); /* * These functions support sending signals using preallocated sigqueue * structures. This is needed "because realtime applications cannot * afford to lose notifications of asynchronous events, like timer - * expirations or I/O completions". In the case of Posix Timers + * expirations or I/O completions". In the case of POSIX Timers * we allocate the sigqueue structure from the timer_create. If this * allocation fails we are able to report the failure to the application * with an EAGAIN error. */ - struct sigqueue *sigqueue_alloc(void) { - struct sigqueue *q; + struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0); - if ((q = __sigqueue_alloc(current, GFP_KERNEL, 0))) + if (q) q->flags |= SIGQUEUE_PREALLOC; - return(q); -} -void sigqueue_free(struct sigqueue *q) -{ - unsigned long flags; - BUG_ON(!(q->flags & SIGQUEUE_PREALLOC)); - /* - * If the signal is still pending remove it from the - * pending queue. - */ - if (unlikely(!list_empty(&q->list))) { - spinlock_t *lock = ¤t->sighand->siglock; - read_lock(&tasklist_lock); - spin_lock_irqsave(lock, flags); - if (!list_empty(&q->list)) - list_del_init(&q->list); - spin_unlock_irqrestore(lock, flags); - read_unlock(&tasklist_lock); - } - q->flags &= ~SIGQUEUE_PREALLOC; - __sigqueue_free(q); + return q; } -int -send_sigqueue(int sig, struct sigqueue *q, struct task_struct *p) +void sigqueue_free(struct sigqueue *q) { unsigned long flags; - int ret = 0; - struct sighand_struct *sh; + spinlock_t *lock = ¤t->sighand->siglock; BUG_ON(!(q->flags & SIGQUEUE_PREALLOC)); - /* - * The rcu based delayed sighand destroy makes it possible to - * run this without tasklist lock held. The task struct itself - * cannot go away as create_timer did get_task_struct(). - * - * We return -1, when the task is marked exiting, so - * posix_timer_event can redirect it to the group leader + * We must hold ->siglock while testing q->list + * to serialize with collect_signal() or with + * __exit_signal()->flush_sigqueue(). */ - rcu_read_lock(); - - if (unlikely(p->flags & PF_EXITING)) { - ret = -1; - goto out_err; - } - -retry: - sh = rcu_dereference(p->sighand); - - spin_lock_irqsave(&sh->siglock, flags); - if (p->sighand != sh) { - /* We raced with exec() in a multithreaded process... */ - spin_unlock_irqrestore(&sh->siglock, flags); - goto retry; - } - + spin_lock_irqsave(lock, flags); + q->flags &= ~SIGQUEUE_PREALLOC; /* - * We do the check here again to handle the following scenario: - * - * CPU 0 CPU 1 - * send_sigqueue - * check PF_EXITING - * interrupt exit code running - * __exit_signal - * lock sighand->siglock - * unlock sighand->siglock - * lock sh->siglock - * add(tsk->pending) flush_sigqueue(tsk->pending) - * + * If it is queued it will be freed when dequeued, + * like the "regular" sigqueue. */ + if (!list_empty(&q->list)) + q = NULL; + spin_unlock_irqrestore(lock, flags); - if (unlikely(p->flags & PF_EXITING)) { - ret = -1; - goto out; - } - - if (unlikely(!list_empty(&q->list))) { - /* - * If an SI_TIMER entry is already queue just increment - * the overrun count. - */ - if (q->info.si_code != SI_TIMER) - BUG(); - q->info.si_overrun++; - goto out; - } - /* Short-circuit ignored signals. */ - if (sig_ignored(p, sig)) { - ret = 1; - goto out; - } - - list_add_tail(&q->list, &p->pending.list); - sigaddset(&p->pending.signal, sig); - if (!sigismember(&p->blocked, sig)) - signal_wake_up(p, sig == SIGKILL); - -out: - spin_unlock_irqrestore(&sh->siglock, flags); -out_err: - rcu_read_unlock(); - - return ret; + if (q) + __sigqueue_free(q); } -int -send_group_sigqueue(int sig, struct sigqueue *q, struct task_struct *p) +int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group) { + int sig = q->info.si_signo; + struct sigpending *pending; unsigned long flags; - int ret = 0; + int ret, result; BUG_ON(!(q->flags & SIGQUEUE_PREALLOC)); - read_lock(&tasklist_lock); - /* Since it_lock is held, p->sighand cannot be NULL. */ - spin_lock_irqsave(&p->sighand->siglock, flags); - handle_stop_signal(sig, p); + ret = -1; + if (!likely(lock_task_sighand(t, &flags))) + goto ret; - /* Short-circuit ignored signals. */ - if (sig_ignored(p, sig)) { - ret = 1; + ret = 1; /* the signal is ignored */ + result = TRACE_SIGNAL_IGNORED; + if (!prepare_signal(sig, t, false)) goto out; - } + ret = 0; if (unlikely(!list_empty(&q->list))) { /* * If an SI_TIMER entry is already queue just increment - * the overrun count. Other uses should not try to - * send the signal multiple times. + * the overrun count. */ - if (q->info.si_code != SI_TIMER) - BUG(); + BUG_ON(q->info.si_code != SI_TIMER); q->info.si_overrun++; + result = TRACE_SIGNAL_ALREADY_PENDING; goto out; - } - - /* - * Put this signal on the shared-pending queue. - * We always use the shared queue for process-wide signals, - * to avoid several races. - */ - list_add_tail(&q->list, &p->signal->shared_pending.list); - sigaddset(&p->signal->shared_pending.signal, sig); - - __group_complete_signal(sig, p); + } + q->info.si_overrun = 0; + + signalfd_notify(t, sig); + pending = group ? &t->signal->shared_pending : &t->pending; + list_add_tail(&q->list, &pending->list); + sigaddset(&pending->signal, sig); + complete_signal(sig, t, group); + result = TRACE_SIGNAL_DELIVERED; out: - spin_unlock_irqrestore(&p->sighand->siglock, flags); - read_unlock(&tasklist_lock); + trace_signal_generate(sig, &q->info, t, group, result); + unlock_task_sighand(t, &flags); +ret: return ret; } /* - * Wake up any threads in the parent blocked in wait* syscalls. - */ -static inline void __wake_up_parent(struct task_struct *p, - struct task_struct *parent) -{ - wake_up_interruptible_sync(&parent->signal->wait_chldexit); -} - -/* * Let a parent know about the death of a child. * For a stopped/continued status change, use do_notify_parent_cldstop instead. + * + * Returns true if our parent ignored us and so we've switched to + * self-reaping. */ - -void do_notify_parent(struct task_struct *tsk, int sig) +bool do_notify_parent(struct task_struct *tsk, int sig) { struct siginfo info; unsigned long flags; struct sighand_struct *psig; + bool autoreap = false; + cputime_t utime, stime; BUG_ON(sig == -1); /* do_notify_parent_cldstop should have been called instead. */ - BUG_ON(tsk->state & (TASK_STOPPED|TASK_TRACED)); + BUG_ON(task_is_stopped_or_traced(tsk)); BUG_ON(!tsk->ptrace && (tsk->group_leader != tsk || !thread_group_empty(tsk))); + if (sig != SIGCHLD) { + /* + * This is only possible if parent == real_parent. + * Check if it has changed security domain. + */ + if (tsk->parent_exec_id != tsk->parent->self_exec_id) + sig = SIGCHLD; + } + info.si_signo = sig; info.si_errno = 0; - info.si_pid = tsk->pid; - info.si_uid = tsk->uid; + /* + * We are under tasklist_lock here so our parent is tied to + * us and cannot change. + * + * task_active_pid_ns will always return the same pid namespace + * until a task passes through release_task. + * + * write_lock() currently calls preempt_disable() which is the + * same as rcu_read_lock(), but according to Oleg, this is not + * correct to rely on this + */ + rcu_read_lock(); + info.si_pid = task_pid_nr_ns(tsk, task_active_pid_ns(tsk->parent)); + info.si_uid = from_kuid_munged(task_cred_xxx(tsk->parent, user_ns), + task_uid(tsk)); + rcu_read_unlock(); - /* FIXME: find out whether or not this is supposed to be c*time. */ - info.si_utime = cputime_to_jiffies(cputime_add(tsk->utime, - tsk->signal->utime)); - info.si_stime = cputime_to_jiffies(cputime_add(tsk->stime, - tsk->signal->stime)); + task_cputime(tsk, &utime, &stime); + info.si_utime = cputime_to_clock_t(utime + tsk->signal->utime); + info.si_stime = cputime_to_clock_t(stime + tsk->signal->stime); info.si_status = tsk->exit_code & 0x7f; if (tsk->exit_code & 0x80) @@ -1603,38 +1686,60 @@ void do_notify_parent(struct task_struct *tsk, int sig) * is implementation-defined: we do (if you don't want * it, just use SIG_IGN instead). */ - tsk->exit_signal = -1; + autoreap = true; if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) sig = 0; } - if (valid_signal(sig) && sig > 0) + if (valid_signal(sig) && sig) __group_send_sig_info(sig, &info, tsk->parent); __wake_up_parent(tsk, tsk->parent); spin_unlock_irqrestore(&psig->siglock, flags); + + return autoreap; } -static void do_notify_parent_cldstop(struct task_struct *tsk, int to_self, int why) +/** + * do_notify_parent_cldstop - notify parent of stopped/continued state change + * @tsk: task reporting the state change + * @for_ptracer: the notification is for ptracer + * @why: CLD_{CONTINUED|STOPPED|TRAPPED} to report + * + * Notify @tsk's parent that the stopped/continued state has changed. If + * @for_ptracer is %false, @tsk's group leader notifies to its real parent. + * If %true, @tsk reports to @tsk->parent which should be the ptracer. + * + * CONTEXT: + * Must be called with tasklist_lock at least read locked. + */ +static void do_notify_parent_cldstop(struct task_struct *tsk, + bool for_ptracer, int why) { struct siginfo info; unsigned long flags; struct task_struct *parent; struct sighand_struct *sighand; + cputime_t utime, stime; - if (to_self) + if (for_ptracer) { parent = tsk->parent; - else { + } else { tsk = tsk->group_leader; parent = tsk->real_parent; } info.si_signo = SIGCHLD; info.si_errno = 0; - info.si_pid = tsk->pid; - info.si_uid = tsk->uid; + /* + * see comment in do_notify_parent() about the following 4 lines + */ + rcu_read_lock(); + info.si_pid = task_pid_nr_ns(tsk, task_active_pid_ns(parent)); + info.si_uid = from_kuid_munged(task_cred_xxx(parent, user_ns), task_uid(tsk)); + rcu_read_unlock(); - /* FIXME: find out whether or not this is supposed to be c*time. */ - info.si_utime = cputime_to_jiffies(tsk->utime); - info.si_stime = cputime_to_jiffies(tsk->stime); + task_cputime(tsk, &utime, &stime); + info.si_utime = cputime_to_clock_t(utime); + info.si_stime = cputime_to_clock_t(stime); info.si_code = why; switch (why) { @@ -1663,6 +1768,40 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int to_self, int w spin_unlock_irqrestore(&sighand->siglock, flags); } +static inline int may_ptrace_stop(void) +{ + if (!likely(current->ptrace)) + return 0; + /* + * Are we in the middle of do_coredump? + * If so and our tracer is also part of the coredump stopping + * is a deadlock situation, and pointless because our tracer + * is dead so don't allow us to stop. + * If SIGKILL was already sent before the caller unlocked + * ->siglock we must see ->core_state != NULL. Otherwise it + * is safe to enter schedule(). + * + * This is almost outdated, a task with the pending SIGKILL can't + * block in TASK_TRACED. But PTRACE_EVENT_EXIT can be reported + * after SIGKILL was already dequeued. + */ + if (unlikely(current->mm->core_state) && + unlikely(current->mm == current->parent->mm)) + return 0; + + return 1; +} + +/* + * Return non-zero if there is a SIGKILL that should be waking us up. + * Called with the siglock held. + */ +static int sigkill_pending(struct task_struct *tsk) +{ + return sigismember(&tsk->pending.signal, SIGKILL) || + sigismember(&tsk->signal->shared_pending.signal, SIGKILL); +} + /* * This must be called with current->sighand->siglock held. * @@ -1671,41 +1810,110 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int to_self, int w * That makes it a way to test a stopped process for * being ptrace-stopped vs being job-control-stopped. * - * If we actually decide not to stop at all because the tracer is gone, - * we leave nostop_code in current->exit_code. + * If we actually decide not to stop at all because the tracer + * is gone, we keep current->exit_code unless clear_code. */ -static void ptrace_stop(int exit_code, int nostop_code, siginfo_t *info) +static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) + __releases(¤t->sighand->siglock) + __acquires(¤t->sighand->siglock) { + bool gstop_done = false; + + if (arch_ptrace_stop_needed(exit_code, info)) { + /* + * The arch code has something special to do before a + * ptrace stop. This is allowed to block, e.g. for faults + * on user stack pages. We can't keep the siglock while + * calling arch_ptrace_stop, so we must release it now. + * To preserve proper semantics, we must do this before + * any signal bookkeeping like checking group_stop_count. + * Meanwhile, a SIGKILL could come in before we retake the + * siglock. That must prevent us from sleeping in TASK_TRACED. + * So after regaining the lock, we must check for SIGKILL. + */ + spin_unlock_irq(¤t->sighand->siglock); + arch_ptrace_stop(exit_code, info); + spin_lock_irq(¤t->sighand->siglock); + if (sigkill_pending(current)) + return; + } + /* - * If there is a group stop in progress, - * we must participate in the bookkeeping. + * We're committing to trapping. TRACED should be visible before + * TRAPPING is cleared; otherwise, the tracer might fail do_wait(). + * Also, transition to TRACED and updates to ->jobctl should be + * atomic with respect to siglock and should be done after the arch + * hook as siglock is released and regrabbed across it. */ - if (current->signal->group_stop_count > 0) - --current->signal->group_stop_count; + set_current_state(TASK_TRACED); current->last_siginfo = info; current->exit_code = exit_code; - /* Let the debugger run. */ - set_current_state(TASK_TRACED); + /* + * If @why is CLD_STOPPED, we're trapping to participate in a group + * stop. Do the bookkeeping. Note that if SIGCONT was delievered + * across siglock relocks since INTERRUPT was scheduled, PENDING + * could be clear now. We act as if SIGCONT is received after + * TASK_TRACED is entered - ignore it. + */ + if (why == CLD_STOPPED && (current->jobctl & JOBCTL_STOP_PENDING)) + gstop_done = task_participate_group_stop(current); + + /* any trap clears pending STOP trap, STOP trap clears NOTIFY */ + task_clear_jobctl_pending(current, JOBCTL_TRAP_STOP); + if (info && info->si_code >> 8 == PTRACE_EVENT_STOP) + task_clear_jobctl_pending(current, JOBCTL_TRAP_NOTIFY); + + /* entering a trap, clear TRAPPING */ + task_clear_jobctl_trapping(current); + spin_unlock_irq(¤t->sighand->siglock); read_lock(&tasklist_lock); - if (likely(current->ptrace & PT_PTRACED) && - likely(current->parent != current->real_parent || - !(current->ptrace & PT_ATTACHED)) && - (likely(current->parent->signal != current->signal) || - !unlikely(current->signal->flags & SIGNAL_GROUP_EXIT))) { - do_notify_parent_cldstop(current, 1, CLD_TRAPPED); + if (may_ptrace_stop()) { + /* + * Notify parents of the stop. + * + * While ptraced, there are two parents - the ptracer and + * the real_parent of the group_leader. The ptracer should + * know about every stop while the real parent is only + * interested in the completion of group stop. The states + * for the two don't interact with each other. Notify + * separately unless they're gonna be duplicates. + */ + do_notify_parent_cldstop(current, true, why); + if (gstop_done && ptrace_reparented(current)) + do_notify_parent_cldstop(current, false, why); + + /* + * Don't want to allow preemption here, because + * sys_ptrace() needs this task to be inactive. + * + * XXX: implement read_unlock_no_resched(). + */ + preempt_disable(); read_unlock(&tasklist_lock); - schedule(); + preempt_enable_no_resched(); + freezable_schedule(); } else { /* * By the time we got the lock, our tracer went away. - * Don't stop here. + * Don't drop the lock yet, another tracer may come. + * + * If @gstop_done, the ptracer went away between group stop + * completion and here. During detach, it would have set + * JOBCTL_STOP_PENDING on us and we'll re-enter + * TASK_STOPPED in do_signal_stop() on return, so notifying + * the real parent of the group stop completion is enough. */ + if (gstop_done) + do_notify_parent_cldstop(current, false, why); + + /* tasklist protects us from ptrace_freeze_traced() */ + __set_current_state(TASK_RUNNING); + if (clear_code) + current->exit_code = 0; read_unlock(&tasklist_lock); - set_current_state(TASK_RUNNING); - current->exit_code = nostop_code; } /* @@ -1716,259 +1924,335 @@ static void ptrace_stop(int exit_code, int nostop_code, siginfo_t *info) spin_lock_irq(¤t->sighand->siglock); current->last_siginfo = NULL; + /* LISTENING can be set only during STOP traps, clear it */ + current->jobctl &= ~JOBCTL_LISTENING; + /* * Queued signals ignored us while we were stopped for tracing. * So check for any that we should take before resuming user mode. + * This sets TIF_SIGPENDING, but never clears it. */ - recalc_sigpending(); + recalc_sigpending_tsk(current); } -void ptrace_notify(int exit_code) +static void ptrace_do_notify(int signr, int exit_code, int why) { siginfo_t info; - BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP); - memset(&info, 0, sizeof info); - info.si_signo = SIGTRAP; + info.si_signo = signr; info.si_code = exit_code; - info.si_pid = current->pid; - info.si_uid = current->uid; + info.si_pid = task_pid_vnr(current); + info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); /* Let the debugger run. */ - spin_lock_irq(¤t->sighand->siglock); - ptrace_stop(exit_code, 0, &info); - spin_unlock_irq(¤t->sighand->siglock); + ptrace_stop(exit_code, why, 1, &info); } -static void -finish_stop(int stop_count) +void ptrace_notify(int exit_code) { - int to_self; - - /* - * If there are no other threads in the group, or if there is - * a group stop in progress and we are the last to stop, - * report to the parent. When ptraced, every thread reports itself. - */ - if (stop_count < 0 || (current->ptrace & PT_PTRACED)) - to_self = 1; - else if (stop_count == 0) - to_self = 0; - else - goto out; - - read_lock(&tasklist_lock); - do_notify_parent_cldstop(current, to_self, CLD_STOPPED); - read_unlock(&tasklist_lock); + BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP); + if (unlikely(current->task_works)) + task_work_run(); -out: - schedule(); - /* - * Now we don't run again until continued. - */ - current->exit_code = 0; + spin_lock_irq(¤t->sighand->siglock); + ptrace_do_notify(SIGTRAP, exit_code, CLD_TRAPPED); + spin_unlock_irq(¤t->sighand->siglock); } -/* - * This performs the stopping for SIGSTOP and other stop signals. - * We have to stop all threads in the thread group. - * Returns nonzero if we've actually stopped and released the siglock. - * Returns zero if we didn't stop and still hold the siglock. +/** + * do_signal_stop - handle group stop for SIGSTOP and other stop signals + * @signr: signr causing group stop if initiating + * + * If %JOBCTL_STOP_PENDING is not set yet, initiate group stop with @signr + * and participate in it. If already set, participate in the existing + * group stop. If participated in a group stop (and thus slept), %true is + * returned with siglock released. + * + * If ptraced, this function doesn't handle stop itself. Instead, + * %JOBCTL_TRAP_STOP is scheduled and %false is returned with siglock + * untouched. The caller must ensure that INTERRUPT trap handling takes + * places afterwards. + * + * CONTEXT: + * Must be called with @current->sighand->siglock held, which is released + * on %true return. + * + * RETURNS: + * %false if group stop is already cancelled or ptrace trap is scheduled. + * %true if participated in group stop. */ -static int -do_signal_stop(int signr) +static bool do_signal_stop(int signr) + __releases(¤t->sighand->siglock) { struct signal_struct *sig = current->signal; - struct sighand_struct *sighand = current->sighand; - int stop_count = -1; - if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED)) - return 0; + if (!(current->jobctl & JOBCTL_STOP_PENDING)) { + unsigned int gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME; + struct task_struct *t; - if (sig->group_stop_count > 0) { - /* - * There is a group stop in progress. We don't need to - * start another one. - */ - signr = sig->group_exit_code; - stop_count = --sig->group_stop_count; - current->exit_code = signr; - set_current_state(TASK_STOPPED); - if (stop_count == 0) - sig->flags = SIGNAL_STOP_STOPPED; - spin_unlock_irq(&sighand->siglock); - } - else if (thread_group_empty(current)) { - /* - * Lock must be held through transition to stopped state. - */ - current->exit_code = current->signal->group_exit_code = signr; - set_current_state(TASK_STOPPED); - sig->flags = SIGNAL_STOP_STOPPED; - spin_unlock_irq(&sighand->siglock); - } - else { + /* signr will be recorded in task->jobctl for retries */ + WARN_ON_ONCE(signr & ~JOBCTL_STOP_SIGMASK); + + if (!likely(current->jobctl & JOBCTL_STOP_DEQUEUED) || + unlikely(signal_group_exit(sig))) + return false; /* - * There is no group stop already in progress. - * We must initiate one now, but that requires - * dropping siglock to get both the tasklist lock - * and siglock again in the proper order. Note that - * this allows an intervening SIGCONT to be posted. - * We need to check for that and bail out if necessary. + * There is no group stop already in progress. We must + * initiate one now. + * + * While ptraced, a task may be resumed while group stop is + * still in effect and then receive a stop signal and + * initiate another group stop. This deviates from the + * usual behavior as two consecutive stop signals can't + * cause two group stops when !ptraced. That is why we + * also check !task_is_stopped(t) below. + * + * The condition can be distinguished by testing whether + * SIGNAL_STOP_STOPPED is already set. Don't generate + * group_exit_code in such case. + * + * This is not necessary for SIGNAL_STOP_CONTINUED because + * an intervening stop signal is required to cause two + * continued events regardless of ptrace. */ - struct task_struct *t; + if (!(sig->flags & SIGNAL_STOP_STOPPED)) + sig->group_exit_code = signr; - spin_unlock_irq(&sighand->siglock); + sig->group_stop_count = 0; - /* signals can be posted during this window */ + if (task_set_jobctl_pending(current, signr | gstop)) + sig->group_stop_count++; - read_lock(&tasklist_lock); - spin_lock_irq(&sighand->siglock); - - if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED)) { + t = current; + while_each_thread(current, t) { /* - * Another stop or continue happened while we - * didn't have the lock. We can just swallow this - * signal now. If we raced with a SIGCONT, that - * should have just cleared it now. If we raced - * with another processor delivering a stop signal, - * then the SIGCONT that wakes us up should clear it. + * Setting state to TASK_STOPPED for a group + * stop is always done with the siglock held, + * so this check has no races. */ - read_unlock(&tasklist_lock); - return 0; - } - - if (sig->group_stop_count == 0) { - sig->group_exit_code = signr; - stop_count = 0; - for (t = next_thread(current); t != current; - t = next_thread(t)) - /* - * Setting state to TASK_STOPPED for a group - * stop is always done with the siglock held, - * so this check has no races. - */ - if (!t->exit_state && - !(t->state & (TASK_STOPPED|TASK_TRACED))) { - stop_count++; + if (!task_is_stopped(t) && + task_set_jobctl_pending(t, signr | gstop)) { + sig->group_stop_count++; + if (likely(!(t->ptrace & PT_SEIZED))) signal_wake_up(t, 0); - } - sig->group_stop_count = stop_count; - } - else { - /* A race with another thread while unlocked. */ - signr = sig->group_exit_code; - stop_count = --sig->group_stop_count; + else + ptrace_trap_notify(t); + } } - - current->exit_code = signr; - set_current_state(TASK_STOPPED); - if (stop_count == 0) - sig->flags = SIGNAL_STOP_STOPPED; - - spin_unlock_irq(&sighand->siglock); - read_unlock(&tasklist_lock); } - finish_stop(stop_count); - return 1; -} + if (likely(!current->ptrace)) { + int notify = 0; -/* - * Do appropriate magic when group_stop_count > 0. - * We return nonzero if we stopped, after releasing the siglock. - * We return zero if we still hold the siglock and should look - * for another signal without checking group_stop_count again. - */ -static int handle_group_stop(void) -{ - int stop_count; + /* + * If there are no other threads in the group, or if there + * is a group stop in progress and we are the last to stop, + * report to the parent. + */ + if (task_participate_group_stop(current)) + notify = CLD_STOPPED; + + __set_current_state(TASK_STOPPED); + spin_unlock_irq(¤t->sighand->siglock); - if (current->signal->group_exit_task == current) { /* - * Group stop is so we can do a core dump, - * We are the initiating thread, so get on with it. + * Notify the parent of the group stop completion. Because + * we're not holding either the siglock or tasklist_lock + * here, ptracer may attach inbetween; however, this is for + * group stop and should always be delivered to the real + * parent of the group leader. The new ptracer will get + * its notification when this task transitions into + * TASK_TRACED. */ - current->signal->group_exit_task = NULL; - return 0; - } + if (notify) { + read_lock(&tasklist_lock); + do_notify_parent_cldstop(current, false, notify); + read_unlock(&tasklist_lock); + } - if (current->signal->flags & SIGNAL_GROUP_EXIT) + /* Now we don't run again until woken by SIGCONT or SIGKILL */ + freezable_schedule(); + return true; + } else { /* - * Group stop is so another thread can do a core dump, - * or else we are racing against a death signal. - * Just punt the stop so we can get the next signal. + * While ptraced, group stop is handled by STOP trap. + * Schedule it and let the caller deal with it. */ - return 0; + task_set_jobctl_pending(current, JOBCTL_TRAP_STOP); + return false; + } +} +/** + * do_jobctl_trap - take care of ptrace jobctl traps + * + * When PT_SEIZED, it's used for both group stop and explicit + * SEIZE/INTERRUPT traps. Both generate PTRACE_EVENT_STOP trap with + * accompanying siginfo. If stopped, lower eight bits of exit_code contain + * the stop signal; otherwise, %SIGTRAP. + * + * When !PT_SEIZED, it's used only for group stop trap with stop signal + * number as exit_code and no siginfo. + * + * CONTEXT: + * Must be called with @current->sighand->siglock held, which may be + * released and re-acquired before returning with intervening sleep. + */ +static void do_jobctl_trap(void) +{ + struct signal_struct *signal = current->signal; + int signr = current->jobctl & JOBCTL_STOP_SIGMASK; + + if (current->ptrace & PT_SEIZED) { + if (!signal->group_stop_count && + !(signal->flags & SIGNAL_STOP_STOPPED)) + signr = SIGTRAP; + WARN_ON_ONCE(!signr); + ptrace_do_notify(signr, signr | (PTRACE_EVENT_STOP << 8), + CLD_STOPPED); + } else { + WARN_ON_ONCE(!signr); + ptrace_stop(signr, CLD_STOPPED, 0, NULL); + current->exit_code = 0; + } +} + +static int ptrace_signal(int signr, siginfo_t *info) +{ + ptrace_signal_deliver(); /* - * There is a group stop in progress. We stop - * without any associated signal being in our queue. + * We do not check sig_kernel_stop(signr) but set this marker + * unconditionally because we do not know whether debugger will + * change signr. This flag has no meaning unless we are going + * to stop after return from ptrace_stop(). In this case it will + * be checked in do_signal_stop(), we should only stop if it was + * not cleared by SIGCONT while we were sleeping. See also the + * comment in dequeue_signal(). */ - stop_count = --current->signal->group_stop_count; - if (stop_count == 0) - current->signal->flags = SIGNAL_STOP_STOPPED; - current->exit_code = current->signal->group_exit_code; - set_current_state(TASK_STOPPED); - spin_unlock_irq(¤t->sighand->siglock); - finish_stop(stop_count); - return 1; + current->jobctl |= JOBCTL_STOP_DEQUEUED; + ptrace_stop(signr, CLD_TRAPPED, 0, info); + + /* We're back. Did the debugger cancel the sig? */ + signr = current->exit_code; + if (signr == 0) + return signr; + + current->exit_code = 0; + + /* + * Update the siginfo structure if the signal has + * changed. If the debugger wanted something + * specific in the siginfo structure then it should + * have updated *info via PTRACE_SETSIGINFO. + */ + if (signr != info->si_signo) { + info->si_signo = signr; + info->si_errno = 0; + info->si_code = SI_USER; + rcu_read_lock(); + info->si_pid = task_pid_vnr(current->parent); + info->si_uid = from_kuid_munged(current_user_ns(), + task_uid(current->parent)); + rcu_read_unlock(); + } + + /* If the (new) signal is now blocked, requeue it. */ + if (sigismember(¤t->blocked, signr)) { + specific_send_sig_info(signr, info, current); + signr = 0; + } + + return signr; } int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka, struct pt_regs *regs, void *cookie) { - sigset_t *mask = ¤t->blocked; - int signr = 0; + struct sighand_struct *sighand = current->sighand; + struct signal_struct *signal = current->signal; + int signr; + + if (unlikely(current->task_works)) + task_work_run(); + + if (unlikely(uprobe_deny_signal())) + return 0; + + /* + * Do this once, we can't return to user-mode if freezing() == T. + * do_signal_stop() and ptrace_stop() do freezable_schedule() and + * thus do not need another check after return. + */ + try_to_freeze(); relock: - spin_lock_irq(¤t->sighand->siglock); + spin_lock_irq(&sighand->siglock); + /* + * Every stopped thread goes here after wakeup. Check to see if + * we should notify the parent, prepare_signal(SIGCONT) encodes + * the CLD_ si_code into SIGNAL_CLD_MASK bits. + */ + if (unlikely(signal->flags & SIGNAL_CLD_MASK)) { + int why; + + if (signal->flags & SIGNAL_CLD_CONTINUED) + why = CLD_CONTINUED; + else + why = CLD_STOPPED; + + signal->flags &= ~SIGNAL_CLD_MASK; + + spin_unlock_irq(&sighand->siglock); + + /* + * Notify the parent that we're continuing. This event is + * always per-process and doesn't make whole lot of sense + * for ptracers, who shouldn't consume the state via + * wait(2) either, but, for backward compatibility, notify + * the ptracer of the group leader too unless it's gonna be + * a duplicate. + */ + read_lock(&tasklist_lock); + do_notify_parent_cldstop(current, false, why); + + if (ptrace_reparented(current->group_leader)) + do_notify_parent_cldstop(current->group_leader, + true, why); + read_unlock(&tasklist_lock); + + goto relock; + } + for (;;) { struct k_sigaction *ka; - if (unlikely(current->signal->group_stop_count > 0) && - handle_group_stop()) + if (unlikely(current->jobctl & JOBCTL_STOP_PENDING) && + do_signal_stop(0)) goto relock; - signr = dequeue_signal(current, mask, info); + if (unlikely(current->jobctl & JOBCTL_TRAP_MASK)) { + do_jobctl_trap(); + spin_unlock_irq(&sighand->siglock); + goto relock; + } + + signr = dequeue_signal(current, ¤t->blocked, info); if (!signr) break; /* will return 0 */ - if ((current->ptrace & PT_PTRACED) && signr != SIGKILL) { - ptrace_signal_deliver(regs, cookie); - - /* Let the debugger run. */ - ptrace_stop(signr, signr, info); - - /* We're back. Did the debugger cancel the sig or group_exit? */ - signr = current->exit_code; - if (signr == 0 || current->signal->flags & SIGNAL_GROUP_EXIT) + if (unlikely(current->ptrace) && signr != SIGKILL) { + signr = ptrace_signal(signr, info); + if (!signr) continue; + } - current->exit_code = 0; - - /* Update the siginfo structure if the signal has - changed. If the debugger wanted something - specific in the siginfo structure then it should - have updated *info via PTRACE_SETSIGINFO. */ - if (signr != info->si_signo) { - info->si_signo = signr; - info->si_errno = 0; - info->si_code = SI_USER; - info->si_pid = current->parent->pid; - info->si_uid = current->parent->uid; - } + ka = &sighand->action[signr-1]; - /* If the (new) signal is now blocked, requeue it. */ - if (sigismember(¤t->blocked, signr)) { - specific_send_sig_info(signr, info, current); - continue; - } - } + /* Trace actually delivered signals. */ + trace_signal_deliver(signr, info, ka); - ka = ¤t->sighand->action[signr-1]; if (ka->sa.sa_handler == SIG_IGN) /* Do nothing. */ continue; if (ka->sa.sa_handler != SIG_DFL) { @@ -1987,8 +2271,18 @@ relock: if (sig_kernel_ignore(signr)) /* Default is nothing. */ continue; - /* Init gets no signals it doesn't want. */ - if (current->pid == 1) + /* + * Global init gets no signals it doesn't want. + * Container-init gets no signals it doesn't want from same + * container. + * + * Note that if global/container-init sees a sig_kernel_only() + * signal here, the signal must have been generated internally + * or must have come from an ancestor namespace. In either + * case, the signal cannot be dropped. + */ + if (unlikely(signal->flags & SIGNAL_UNKILLABLE) && + !sig_kernel_only(signr)) continue; if (sig_kernel_stop(signr)) { @@ -2003,17 +2297,17 @@ relock: * We need to check for that and bail out if necessary. */ if (signr != SIGSTOP) { - spin_unlock_irq(¤t->sighand->siglock); + spin_unlock_irq(&sighand->siglock); /* signals can be posted during this window */ - if (is_orphaned_pgrp(process_group(current))) + if (is_current_pgrp_orphaned()) goto relock; - spin_lock_irq(¤t->sighand->siglock); + spin_lock_irq(&sighand->siglock); } - if (likely(do_signal_stop(signr))) { + if (likely(do_signal_stop(info->si_signo))) { /* It released the siglock. */ goto relock; } @@ -2025,13 +2319,17 @@ relock: continue; } - spin_unlock_irq(¤t->sighand->siglock); + spin_unlock_irq(&sighand->siglock); /* * Anything else is fatal, maybe with a core dump. */ current->flags |= PF_SIGNALED; + if (sig_kernel_coredump(signr)) { + if (print_fatal_signals) + print_fatal_signal(info->si_signo); + proc_coredump_connector(current); /* * If it was able to dump core, this kills all * other threads in the group and synchronizes with @@ -2040,26 +2338,145 @@ relock: * first and our do_group_exit call below will use * that value and ignore the one we pass it. */ - do_coredump((long)signr, signr, regs); + do_coredump(info); } /* * Death signals, no core dump. */ - do_group_exit(signr); + do_group_exit(info->si_signo); /* NOTREACHED */ } - spin_unlock_irq(¤t->sighand->siglock); + spin_unlock_irq(&sighand->siglock); return signr; } +/** + * signal_delivered - + * @sig: number of signal being delivered + * @info: siginfo_t of signal being delivered + * @ka: sigaction setting that chose the handler + * @regs: user register state + * @stepping: nonzero if debugger single-step or block-step in use + * + * This function should be called when a signal has successfully been + * delivered. It updates the blocked signals accordingly (@ka->sa.sa_mask + * is always blocked, and the signal itself is blocked unless %SA_NODEFER + * is set in @ka->sa.sa_flags. Tracing is notified. + */ +void signal_delivered(int sig, siginfo_t *info, struct k_sigaction *ka, + struct pt_regs *regs, int stepping) +{ + sigset_t blocked; + + /* A signal was successfully delivered, and the + saved sigmask was stored on the signal frame, + and will be restored by sigreturn. So we can + simply clear the restore sigmask flag. */ + clear_restore_sigmask(); + + sigorsets(&blocked, ¤t->blocked, &ka->sa.sa_mask); + if (!(ka->sa.sa_flags & SA_NODEFER)) + sigaddset(&blocked, sig); + set_current_blocked(&blocked); + tracehook_signal_handler(sig, info, ka, regs, stepping); +} + +void signal_setup_done(int failed, struct ksignal *ksig, int stepping) +{ + if (failed) + force_sigsegv(ksig->sig, current); + else + signal_delivered(ksig->sig, &ksig->info, &ksig->ka, + signal_pt_regs(), stepping); +} + +/* + * It could be that complete_signal() picked us to notify about the + * group-wide signal. Other threads should be notified now to take + * the shared signals in @which since we will not. + */ +static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which) +{ + sigset_t retarget; + struct task_struct *t; + + sigandsets(&retarget, &tsk->signal->shared_pending.signal, which); + if (sigisemptyset(&retarget)) + return; + + t = tsk; + while_each_thread(tsk, t) { + if (t->flags & PF_EXITING) + continue; + + if (!has_pending_signals(&retarget, &t->blocked)) + continue; + /* Remove the signals this thread can handle. */ + sigandsets(&retarget, &retarget, &t->blocked); + + if (!signal_pending(t)) + signal_wake_up(t, 0); + + if (sigisemptyset(&retarget)) + break; + } +} + +void exit_signals(struct task_struct *tsk) +{ + int group_stop = 0; + sigset_t unblocked; + + /* + * @tsk is about to have PF_EXITING set - lock out users which + * expect stable threadgroup. + */ + threadgroup_change_begin(tsk); + + if (thread_group_empty(tsk) || signal_group_exit(tsk->signal)) { + tsk->flags |= PF_EXITING; + threadgroup_change_end(tsk); + return; + } + + spin_lock_irq(&tsk->sighand->siglock); + /* + * From now this task is not visible for group-wide signals, + * see wants_signal(), do_signal_stop(). + */ + tsk->flags |= PF_EXITING; + + threadgroup_change_end(tsk); + + if (!signal_pending(tsk)) + goto out; + + unblocked = tsk->blocked; + signotset(&unblocked); + retarget_shared_pending(tsk, &unblocked); + + if (unlikely(tsk->jobctl & JOBCTL_STOP_PENDING) && + task_participate_group_stop(tsk)) + group_stop = CLD_STOPPED; +out: + spin_unlock_irq(&tsk->sighand->siglock); + + /* + * If group stop has completed, deliver the notification. This + * should always go to the real parent of the group leader. + */ + if (unlikely(group_stop)) { + read_lock(&tasklist_lock); + do_notify_parent_cldstop(tsk, false, group_stop); + read_unlock(&tasklist_lock); + } +} + EXPORT_SYMBOL(recalc_sigpending); EXPORT_SYMBOL_GPL(dequeue_signal); EXPORT_SYMBOL(flush_signals); EXPORT_SYMBOL(force_sig); -EXPORT_SYMBOL(kill_pg); -EXPORT_SYMBOL(kill_proc); -EXPORT_SYMBOL(ptrace_notify); EXPORT_SYMBOL(send_sig); EXPORT_SYMBOL(send_sig_info); EXPORT_SYMBOL(sigprocmask); @@ -2071,7 +2488,10 @@ EXPORT_SYMBOL(unblock_all_signals); * System call entry points. */ -asmlinkage long sys_restart_syscall(void) +/** + * sys_restart_syscall - restart a system call + */ +SYSCALL_DEFINE0(restart_syscall) { struct restart_block *restart = ¤t_thread_info()->restart_block; return restart->fn(restart); @@ -2082,11 +2502,39 @@ long do_no_restart_syscall(struct restart_block *param) return -EINTR; } -/* - * We don't need to get the kernel lock - this is all local to this - * particular thread.. (and that's good, because this is _heavily_ - * used by various programs) +static void __set_task_blocked(struct task_struct *tsk, const sigset_t *newset) +{ + if (signal_pending(tsk) && !thread_group_empty(tsk)) { + sigset_t newblocked; + /* A set of now blocked but previously unblocked signals. */ + sigandnsets(&newblocked, newset, ¤t->blocked); + retarget_shared_pending(tsk, &newblocked); + } + tsk->blocked = *newset; + recalc_sigpending(); +} + +/** + * set_current_blocked - change current->blocked mask + * @newset: new mask + * + * It is wrong to change ->blocked directly, this helper should be used + * to ensure the process can't miss a shared signal we are going to block. */ +void set_current_blocked(sigset_t *newset) +{ + sigdelsetmask(newset, sigmask(SIGKILL) | sigmask(SIGSTOP)); + __set_current_blocked(newset); +} + +void __set_current_blocked(const sigset_t *newset) +{ + struct task_struct *tsk = current; + + spin_lock_irq(&tsk->sighand->siglock); + __set_task_blocked(tsk, newset); + spin_unlock_irq(&tsk->sighand->siglock); +} /* * This is also useful for kernel threads that want to temporarily @@ -2098,101 +2546,161 @@ long do_no_restart_syscall(struct restart_block *param) */ int sigprocmask(int how, sigset_t *set, sigset_t *oldset) { - int error; - sigset_t old_block; + struct task_struct *tsk = current; + sigset_t newset; + + /* Lockless, only current can change ->blocked, never from irq */ + if (oldset) + *oldset = tsk->blocked; - spin_lock_irq(¤t->sighand->siglock); - old_block = current->blocked; - error = 0; switch (how) { case SIG_BLOCK: - sigorsets(¤t->blocked, ¤t->blocked, set); + sigorsets(&newset, &tsk->blocked, set); break; case SIG_UNBLOCK: - signandsets(¤t->blocked, ¤t->blocked, set); + sigandnsets(&newset, &tsk->blocked, set); break; case SIG_SETMASK: - current->blocked = *set; + newset = *set; break; default: - error = -EINVAL; + return -EINVAL; } - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - if (oldset) - *oldset = old_block; - return error; + + __set_current_blocked(&newset); + return 0; } -asmlinkage long -sys_rt_sigprocmask(int how, sigset_t __user *set, sigset_t __user *oset, size_t sigsetsize) +/** + * sys_rt_sigprocmask - change the list of currently blocked signals + * @how: whether to add, remove, or set signals + * @nset: stores pending signals + * @oset: previous value of signal mask if non-null + * @sigsetsize: size of sigset_t type + */ +SYSCALL_DEFINE4(rt_sigprocmask, int, how, sigset_t __user *, nset, + sigset_t __user *, oset, size_t, sigsetsize) { - int error = -EINVAL; sigset_t old_set, new_set; + int error; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) - goto out; + return -EINVAL; - if (set) { - error = -EFAULT; - if (copy_from_user(&new_set, set, sizeof(*set))) - goto out; + old_set = current->blocked; + + if (nset) { + if (copy_from_user(&new_set, nset, sizeof(sigset_t))) + return -EFAULT; sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP)); - error = sigprocmask(how, &new_set, &old_set); + error = sigprocmask(how, &new_set, NULL); if (error) - goto out; - if (oset) - goto set_old; - } else if (oset) { - spin_lock_irq(¤t->sighand->siglock); - old_set = current->blocked; - spin_unlock_irq(¤t->sighand->siglock); + return error; + } - set_old: - error = -EFAULT; - if (copy_to_user(oset, &old_set, sizeof(*oset))) - goto out; + if (oset) { + if (copy_to_user(oset, &old_set, sizeof(sigset_t))) + return -EFAULT; } - error = 0; -out: - return error; + + return 0; } -long do_sigpending(void __user *set, unsigned long sigsetsize) +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE4(rt_sigprocmask, int, how, compat_sigset_t __user *, nset, + compat_sigset_t __user *, oset, compat_size_t, sigsetsize) { - long error = -EINVAL; - sigset_t pending; +#ifdef __BIG_ENDIAN + sigset_t old_set = current->blocked; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + + if (nset) { + compat_sigset_t new32; + sigset_t new_set; + int error; + if (copy_from_user(&new32, nset, sizeof(compat_sigset_t))) + return -EFAULT; + sigset_from_compat(&new_set, &new32); + sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP)); + + error = sigprocmask(how, &new_set, NULL); + if (error) + return error; + } + if (oset) { + compat_sigset_t old32; + sigset_to_compat(&old32, &old_set); + if (copy_to_user(oset, &old32, sizeof(compat_sigset_t))) + return -EFAULT; + } + return 0; +#else + return sys_rt_sigprocmask(how, (sigset_t __user *)nset, + (sigset_t __user *)oset, sigsetsize); +#endif +} +#endif + +static int do_sigpending(void *set, unsigned long sigsetsize) +{ if (sigsetsize > sizeof(sigset_t)) - goto out; + return -EINVAL; spin_lock_irq(¤t->sighand->siglock); - sigorsets(&pending, ¤t->pending.signal, + sigorsets(set, ¤t->pending.signal, ¤t->signal->shared_pending.signal); spin_unlock_irq(¤t->sighand->siglock); /* Outside the lock because only this thread touches it. */ - sigandsets(&pending, ¤t->blocked, &pending); - - error = -EFAULT; - if (!copy_to_user(set, &pending, sigsetsize)) - error = 0; + sigandsets(set, ¤t->blocked, set); + return 0; +} -out: - return error; -} +/** + * sys_rt_sigpending - examine a pending signal that has been raised + * while blocked + * @uset: stores pending signals + * @sigsetsize: size of sigset_t type or larger + */ +SYSCALL_DEFINE2(rt_sigpending, sigset_t __user *, uset, size_t, sigsetsize) +{ + sigset_t set; + int err = do_sigpending(&set, sigsetsize); + if (!err && copy_to_user(uset, &set, sigsetsize)) + err = -EFAULT; + return err; +} -asmlinkage long -sys_rt_sigpending(sigset_t __user *set, size_t sigsetsize) +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE2(rt_sigpending, compat_sigset_t __user *, uset, + compat_size_t, sigsetsize) { - return do_sigpending(set, sigsetsize); +#ifdef __BIG_ENDIAN + sigset_t set; + int err = do_sigpending(&set, sigsetsize); + if (!err) { + compat_sigset_t set32; + sigset_to_compat(&set32, &set); + /* we can get here only if sigsetsize <= sizeof(set) */ + if (copy_to_user(uset, &set32, sigsetsize)) + err = -EFAULT; + } + return err; +#else + return sys_rt_sigpending((sigset_t __user *)uset, sigsetsize); +#endif } +#endif #ifndef HAVE_ARCH_COPY_SIGINFO_TO_USER -int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from) +int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from) { int err; @@ -2204,6 +2712,8 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from) /* * If you change siginfo_t structure, please be sure * this code is fixed accordingly. + * Please remember to update the signalfd_copyinfo() function + * inside fs/signalfd.c too, in case siginfo_t changes. * It should never copy any pad contained in the structure * to avoid security leaks, but must copy the generic * 3 ints plus the relevant union member. @@ -2230,6 +2740,14 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from) #ifdef __ARCH_SI_TRAPNO err |= __put_user(from->si_trapno, &to->si_trapno); #endif +#ifdef BUS_MCEERR_AO + /* + * Other callers might not initialize the si_lsb field, + * so check explicitly for the right codes here. + */ + if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO) + err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb); +#endif break; case __SI_CHLD: err |= __put_user(from->si_pid, &to->si_pid); @@ -2244,6 +2762,13 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from) err |= __put_user(from->si_uid, &to->si_uid); err |= __put_user(from->si_ptr, &to->si_ptr); break; +#ifdef __ARCH_SIGSYS + case __SI_SYS: + err |= __put_user(from->si_call_addr, &to->si_call_addr); + err |= __put_user(from->si_syscall, &to->si_syscall); + err |= __put_user(from->si_arch, &to->si_arch); + break; +#endif default: /* this is just in case for now ... */ err |= __put_user(from->si_pid, &to->si_pid); err |= __put_user(from->si_uid, &to->si_uid); @@ -2254,17 +2779,82 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from) #endif -asmlinkage long -sys_rt_sigtimedwait(const sigset_t __user *uthese, - siginfo_t __user *uinfo, - const struct timespec __user *uts, - size_t sigsetsize) +/** + * do_sigtimedwait - wait for queued signals specified in @which + * @which: queued signals to wait for + * @info: if non-null, the signal's siginfo is returned here + * @ts: upper bound on process time suspension + */ +int do_sigtimedwait(const sigset_t *which, siginfo_t *info, + const struct timespec *ts) +{ + struct task_struct *tsk = current; + long timeout = MAX_SCHEDULE_TIMEOUT; + sigset_t mask = *which; + int sig; + + if (ts) { + if (!timespec_valid(ts)) + return -EINVAL; + timeout = timespec_to_jiffies(ts); + /* + * We can be close to the next tick, add another one + * to ensure we will wait at least the time asked for. + */ + if (ts->tv_sec || ts->tv_nsec) + timeout++; + } + + /* + * Invert the set of allowed signals to get those we want to block. + */ + sigdelsetmask(&mask, sigmask(SIGKILL) | sigmask(SIGSTOP)); + signotset(&mask); + + spin_lock_irq(&tsk->sighand->siglock); + sig = dequeue_signal(tsk, &mask, info); + if (!sig && timeout) { + /* + * None ready, temporarily unblock those we're interested + * while we are sleeping in so that we'll be awakened when + * they arrive. Unblocking is always fine, we can avoid + * set_current_blocked(). + */ + tsk->real_blocked = tsk->blocked; + sigandsets(&tsk->blocked, &tsk->blocked, &mask); + recalc_sigpending(); + spin_unlock_irq(&tsk->sighand->siglock); + + timeout = freezable_schedule_timeout_interruptible(timeout); + + spin_lock_irq(&tsk->sighand->siglock); + __set_task_blocked(tsk, &tsk->real_blocked); + sigemptyset(&tsk->real_blocked); + sig = dequeue_signal(tsk, &mask, info); + } + spin_unlock_irq(&tsk->sighand->siglock); + + if (sig) + return sig; + return timeout ? -EINTR : -EAGAIN; +} + +/** + * sys_rt_sigtimedwait - synchronously wait for queued signals specified + * in @uthese + * @uthese: queued signals to wait for + * @uinfo: if non-null, the signal's siginfo is returned here + * @uts: upper bound on process time suspension + * @sigsetsize: size of sigset_t type + */ +SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, + siginfo_t __user *, uinfo, const struct timespec __user *, uts, + size_t, sigsetsize) { - int ret, sig; sigset_t these; struct timespec ts; siginfo_t info; - long timeout = 0; + int ret; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) @@ -2272,124 +2862,94 @@ sys_rt_sigtimedwait(const sigset_t __user *uthese, if (copy_from_user(&these, uthese, sizeof(these))) return -EFAULT; - - /* - * Invert the set of allowed signals to get those we - * want to block. - */ - sigdelsetmask(&these, sigmask(SIGKILL)|sigmask(SIGSTOP)); - signotset(&these); if (uts) { if (copy_from_user(&ts, uts, sizeof(ts))) return -EFAULT; - if (ts.tv_nsec >= 1000000000L || ts.tv_nsec < 0 - || ts.tv_sec < 0) - return -EINVAL; } - spin_lock_irq(¤t->sighand->siglock); - sig = dequeue_signal(current, &these, &info); - if (!sig) { - timeout = MAX_SCHEDULE_TIMEOUT; - if (uts) - timeout = (timespec_to_jiffies(&ts) - + (ts.tv_sec || ts.tv_nsec)); - - if (timeout) { - /* None ready -- temporarily unblock those we're - * interested while we are sleeping in so that we'll - * be awakened when they arrive. */ - current->real_blocked = current->blocked; - sigandsets(¤t->blocked, ¤t->blocked, &these); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - - timeout = schedule_timeout_interruptible(timeout); - - try_to_freeze(); - spin_lock_irq(¤t->sighand->siglock); - sig = dequeue_signal(current, &these, &info); - current->blocked = current->real_blocked; - siginitset(¤t->real_blocked, 0); - recalc_sigpending(); - } - } - spin_unlock_irq(¤t->sighand->siglock); + ret = do_sigtimedwait(&these, &info, uts ? &ts : NULL); - if (sig) { - ret = sig; - if (uinfo) { - if (copy_siginfo_to_user(uinfo, &info)) - ret = -EFAULT; - } - } else { - ret = -EAGAIN; - if (timeout) - ret = -EINTR; + if (ret > 0 && uinfo) { + if (copy_siginfo_to_user(uinfo, &info)) + ret = -EFAULT; } return ret; } -asmlinkage long -sys_kill(int pid, int sig) +/** + * sys_kill - send a signal to a process + * @pid: the PID of the process + * @sig: signal to be sent + */ +SYSCALL_DEFINE2(kill, pid_t, pid, int, sig) { struct siginfo info; info.si_signo = sig; info.si_errno = 0; info.si_code = SI_USER; - info.si_pid = current->tgid; - info.si_uid = current->uid; + info.si_pid = task_tgid_vnr(current); + info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); return kill_something_info(sig, &info, pid); } -static int do_tkill(int tgid, int pid, int sig) +static int +do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info) { - int error; - struct siginfo info; struct task_struct *p; + int error = -ESRCH; - error = -ESRCH; - info.si_signo = sig; - info.si_errno = 0; - info.si_code = SI_TKILL; - info.si_pid = current->tgid; - info.si_uid = current->uid; - - read_lock(&tasklist_lock); - p = find_task_by_pid(pid); - if (p && (tgid <= 0 || p->tgid == tgid)) { - error = check_kill_permission(sig, &info, p); + rcu_read_lock(); + p = find_task_by_vpid(pid); + if (p && (tgid <= 0 || task_tgid_vnr(p) == tgid)) { + error = check_kill_permission(sig, info, p); /* * The null signal is a permissions and process existence * probe. No signal is actually delivered. */ - if (!error && sig && p->sighand) { - spin_lock_irq(&p->sighand->siglock); - handle_stop_signal(sig, p); - error = specific_send_sig_info(sig, &info, p); - spin_unlock_irq(&p->sighand->siglock); + if (!error && sig) { + error = do_send_sig_info(sig, info, p, false); + /* + * If lock_task_sighand() failed we pretend the task + * dies after receiving the signal. The window is tiny, + * and the signal is private anyway. + */ + if (unlikely(error == -ESRCH)) + error = 0; } } - read_unlock(&tasklist_lock); + rcu_read_unlock(); return error; } +static int do_tkill(pid_t tgid, pid_t pid, int sig) +{ + struct siginfo info = {}; + + info.si_signo = sig; + info.si_errno = 0; + info.si_code = SI_TKILL; + info.si_pid = task_tgid_vnr(current); + info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); + + return do_send_specific(tgid, pid, sig, &info); +} + /** * sys_tgkill - send signal to one specific thread * @tgid: the thread group ID of the thread * @pid: the PID of the thread * @sig: signal to be sent * - * This syscall also checks the tgid and returns -ESRCH even if the PID + * This syscall also checks the @tgid and returns -ESRCH even if the PID * exists but it's not belonging to the target process anymore. This * method solves the problem of threads exiting and PIDs getting reused. */ -asmlinkage long sys_tgkill(int tgid, int pid, int sig) +SYSCALL_DEFINE3(tgkill, pid_t, tgid, pid_t, pid, int, sig) { /* This is only valid for single tasks */ if (pid <= 0 || tgid <= 0) @@ -2398,11 +2958,14 @@ asmlinkage long sys_tgkill(int tgid, int pid, int sig) return do_tkill(tgid, pid, sig); } -/* +/** + * sys_tkill - send signal to one specific task + * @pid: the PID of the task + * @sig: signal to be sent + * * Send a signal to only one task, even if it's a CLONE_THREAD task. */ -asmlinkage long -sys_tkill(int pid, int sig) +SYSCALL_DEFINE2(tkill, pid_t, pid, int, sig) { /* This is only valid for single tasks */ if (pid <= 0) @@ -2411,49 +2974,138 @@ sys_tkill(int pid, int sig) return do_tkill(0, pid, sig); } -asmlinkage long -sys_rt_sigqueueinfo(int pid, int sig, siginfo_t __user *uinfo) +static int do_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t *info) { - siginfo_t info; + /* Not even root can pretend to send signals from the kernel. + * Nor can they impersonate a kill()/tgkill(), which adds source info. + */ + if ((info->si_code >= 0 || info->si_code == SI_TKILL) && + (task_pid_vnr(current) != pid)) { + /* We used to allow any < 0 si_code */ + WARN_ON_ONCE(info->si_code < 0); + return -EPERM; + } + info->si_signo = sig; + + /* POSIX.1b doesn't mention process groups. */ + return kill_proc_info(sig, info, pid); +} +/** + * sys_rt_sigqueueinfo - send signal information to a signal + * @pid: the PID of the thread + * @sig: signal to be sent + * @uinfo: signal info to be sent + */ +SYSCALL_DEFINE3(rt_sigqueueinfo, pid_t, pid, int, sig, + siginfo_t __user *, uinfo) +{ + siginfo_t info; if (copy_from_user(&info, uinfo, sizeof(siginfo_t))) return -EFAULT; + return do_rt_sigqueueinfo(pid, sig, &info); +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE3(rt_sigqueueinfo, + compat_pid_t, pid, + int, sig, + struct compat_siginfo __user *, uinfo) +{ + siginfo_t info; + int ret = copy_siginfo_from_user32(&info, uinfo); + if (unlikely(ret)) + return ret; + return do_rt_sigqueueinfo(pid, sig, &info); +} +#endif + +static int do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, siginfo_t *info) +{ + /* This is only valid for single tasks */ + if (pid <= 0 || tgid <= 0) + return -EINVAL; /* Not even root can pretend to send signals from the kernel. - Nor can they impersonate a kill(), which adds source info. */ - if (info.si_code >= 0) + * Nor can they impersonate a kill()/tgkill(), which adds source info. + */ + if (((info->si_code >= 0 || info->si_code == SI_TKILL)) && + (task_pid_vnr(current) != pid)) { + /* We used to allow any < 0 si_code */ + WARN_ON_ONCE(info->si_code < 0); return -EPERM; - info.si_signo = sig; + } + info->si_signo = sig; - /* POSIX.1b doesn't mention process groups. */ - return kill_proc_info(sig, &info, pid); + return do_send_specific(tgid, pid, sig, info); } -int -do_sigaction(int sig, const struct k_sigaction *act, struct k_sigaction *oact) +SYSCALL_DEFINE4(rt_tgsigqueueinfo, pid_t, tgid, pid_t, pid, int, sig, + siginfo_t __user *, uinfo) +{ + siginfo_t info; + + if (copy_from_user(&info, uinfo, sizeof(siginfo_t))) + return -EFAULT; + + return do_rt_tgsigqueueinfo(tgid, pid, sig, &info); +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE4(rt_tgsigqueueinfo, + compat_pid_t, tgid, + compat_pid_t, pid, + int, sig, + struct compat_siginfo __user *, uinfo) { + siginfo_t info; + + if (copy_siginfo_from_user32(&info, uinfo)) + return -EFAULT; + return do_rt_tgsigqueueinfo(tgid, pid, sig, &info); +} +#endif + +/* + * For kthreads only, must not be used if cloned with CLONE_SIGHAND + */ +void kernel_sigaction(int sig, __sighandler_t action) +{ + spin_lock_irq(¤t->sighand->siglock); + current->sighand->action[sig - 1].sa.sa_handler = action; + if (action == SIG_IGN) { + sigset_t mask; + + sigemptyset(&mask); + sigaddset(&mask, sig); + + flush_sigqueue_mask(&mask, ¤t->signal->shared_pending); + flush_sigqueue_mask(&mask, ¤t->pending); + recalc_sigpending(); + } + spin_unlock_irq(¤t->sighand->siglock); +} +EXPORT_SYMBOL(kernel_sigaction); + +int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact) +{ + struct task_struct *p = current, *t; struct k_sigaction *k; sigset_t mask; if (!valid_signal(sig) || sig < 1 || (act && sig_kernel_only(sig))) return -EINVAL; - k = ¤t->sighand->action[sig-1]; - - spin_lock_irq(¤t->sighand->siglock); - if (signal_pending(current)) { - /* - * If there might be a fatal signal pending on multiple - * threads, make sure we take it before changing the action. - */ - spin_unlock_irq(¤t->sighand->siglock); - return -ERESTARTNOINTR; - } + k = &p->sighand->action[sig-1]; + spin_lock_irq(&p->sighand->siglock); if (oact) *oact = *k; if (act) { + sigdelsetmask(&act->sa.sa_mask, + sigmask(SIGKILL) | sigmask(SIGSTOP)); + *k = *act; /* * POSIX 3.3.1.3: * "Setting a signal action to SIG_IGN for a signal that is @@ -2465,55 +3117,28 @@ do_sigaction(int sig, const struct k_sigaction *act, struct k_sigaction *oact) * (for example, SIGCHLD), shall cause the pending signal to * be discarded, whether or not it is blocked" */ - if (act->sa.sa_handler == SIG_IGN || - (act->sa.sa_handler == SIG_DFL && - sig_kernel_ignore(sig))) { - /* - * This is a fairly rare case, so we only take the - * tasklist_lock once we're sure we'll need it. - * Now we must do this little unlock and relock - * dance to maintain the lock hierarchy. - */ - struct task_struct *t = current; - spin_unlock_irq(&t->sighand->siglock); - read_lock(&tasklist_lock); - spin_lock_irq(&t->sighand->siglock); - *k = *act; - sigdelsetmask(&k->sa.sa_mask, - sigmask(SIGKILL) | sigmask(SIGSTOP)); + if (sig_handler_ignored(sig_handler(p, sig), sig)) { sigemptyset(&mask); sigaddset(&mask, sig); - rm_from_queue_full(&mask, &t->signal->shared_pending); - do { - rm_from_queue_full(&mask, &t->pending); - recalc_sigpending_tsk(t); - t = next_thread(t); - } while (t != current); - spin_unlock_irq(¤t->sighand->siglock); - read_unlock(&tasklist_lock); - return 0; + flush_sigqueue_mask(&mask, &p->signal->shared_pending); + for_each_thread(p, t) + flush_sigqueue_mask(&mask, &t->pending); } - - *k = *act; - sigdelsetmask(&k->sa.sa_mask, - sigmask(SIGKILL) | sigmask(SIGSTOP)); } - spin_unlock_irq(¤t->sighand->siglock); + spin_unlock_irq(&p->sighand->siglock); return 0; } -int +static int do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long sp) { stack_t oss; int error; - if (uoss) { - oss.ss_sp = (void __user *) current->sas_ss_sp; - oss.ss_size = current->sas_ss_size; - oss.ss_flags = sas_ss_flags(sp); - } + oss.ss_sp = (void __user *) current->sas_ss_sp; + oss.ss_size = current->sas_ss_size; + oss.ss_flags = sas_ss_flags(sp); if (uss) { void __user *ss_sp; @@ -2521,10 +3146,12 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s int ss_flags; error = -EFAULT; - if (!access_ok(VERIFY_READ, uss, sizeof(*uss)) - || __get_user(ss_sp, &uss->ss_sp) - || __get_user(ss_flags, &uss->ss_flags) - || __get_user(ss_size, &uss->ss_size)) + if (!access_ok(VERIFY_READ, uss, sizeof(*uss))) + goto out; + error = __get_user(ss_sp, &uss->ss_sp) | + __get_user(ss_flags, &uss->ss_flags) | + __get_user(ss_size, &uss->ss_size); + if (error) goto out; error = -EPERM; @@ -2533,12 +3160,11 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s error = -EINVAL; /* - * - * Note - this code used to test ss_flags incorrectly + * Note - this code used to test ss_flags incorrectly: * old code may have been written using ss_flags==0 * to mean ss_flags==SS_ONSTACK (as this was the only * way that worked) - this fix preserves that older - * mechanism + * mechanism. */ if (ss_flags != SS_DISABLE && ss_flags != SS_ONSTACK && ss_flags != 0) goto out; @@ -2556,87 +3182,166 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s current->sas_ss_size = ss_size; } + error = 0; if (uoss) { error = -EFAULT; - if (copy_to_user(uoss, &oss, sizeof(oss))) + if (!access_ok(VERIFY_WRITE, uoss, sizeof(*uoss))) goto out; + error = __put_user(oss.ss_sp, &uoss->ss_sp) | + __put_user(oss.ss_size, &uoss->ss_size) | + __put_user(oss.ss_flags, &uoss->ss_flags); } - error = 0; out: return error; } +SYSCALL_DEFINE2(sigaltstack,const stack_t __user *,uss, stack_t __user *,uoss) +{ + return do_sigaltstack(uss, uoss, current_user_stack_pointer()); +} + +int restore_altstack(const stack_t __user *uss) +{ + int err = do_sigaltstack(uss, NULL, current_user_stack_pointer()); + /* squash all but EFAULT for now */ + return err == -EFAULT ? err : 0; +} + +int __save_altstack(stack_t __user *uss, unsigned long sp) +{ + struct task_struct *t = current; + return __put_user((void __user *)t->sas_ss_sp, &uss->ss_sp) | + __put_user(sas_ss_flags(sp), &uss->ss_flags) | + __put_user(t->sas_ss_size, &uss->ss_size); +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE2(sigaltstack, + const compat_stack_t __user *, uss_ptr, + compat_stack_t __user *, uoss_ptr) +{ + stack_t uss, uoss; + int ret; + mm_segment_t seg; + + if (uss_ptr) { + compat_stack_t uss32; + + memset(&uss, 0, sizeof(stack_t)); + if (copy_from_user(&uss32, uss_ptr, sizeof(compat_stack_t))) + return -EFAULT; + uss.ss_sp = compat_ptr(uss32.ss_sp); + uss.ss_flags = uss32.ss_flags; + uss.ss_size = uss32.ss_size; + } + seg = get_fs(); + set_fs(KERNEL_DS); + ret = do_sigaltstack((stack_t __force __user *) (uss_ptr ? &uss : NULL), + (stack_t __force __user *) &uoss, + compat_user_stack_pointer()); + set_fs(seg); + if (ret >= 0 && uoss_ptr) { + if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(compat_stack_t)) || + __put_user(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp) || + __put_user(uoss.ss_flags, &uoss_ptr->ss_flags) || + __put_user(uoss.ss_size, &uoss_ptr->ss_size)) + ret = -EFAULT; + } + return ret; +} + +int compat_restore_altstack(const compat_stack_t __user *uss) +{ + int err = compat_sys_sigaltstack(uss, NULL); + /* squash all but -EFAULT for now */ + return err == -EFAULT ? err : 0; +} + +int __compat_save_altstack(compat_stack_t __user *uss, unsigned long sp) +{ + struct task_struct *t = current; + return __put_user(ptr_to_compat((void __user *)t->sas_ss_sp), &uss->ss_sp) | + __put_user(sas_ss_flags(sp), &uss->ss_flags) | + __put_user(t->sas_ss_size, &uss->ss_size); +} +#endif #ifdef __ARCH_WANT_SYS_SIGPENDING -asmlinkage long -sys_sigpending(old_sigset_t __user *set) +/** + * sys_sigpending - examine pending signals + * @set: where mask of pending signal is returned + */ +SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, set) { - return do_sigpending(set, sizeof(*set)); + return sys_rt_sigpending((sigset_t __user *)set, sizeof(old_sigset_t)); } #endif #ifdef __ARCH_WANT_SYS_SIGPROCMASK -/* Some platforms have their own version with special arguments others - support only sys_rt_sigprocmask. */ +/** + * sys_sigprocmask - examine and change blocked signals + * @how: whether to add, remove, or set signals + * @nset: signals to add or remove (if non-null) + * @oset: previous value of signal mask if non-null + * + * Some platforms have their own version with special arguments; + * others support only sys_rt_sigprocmask. + */ -asmlinkage long -sys_sigprocmask(int how, old_sigset_t __user *set, old_sigset_t __user *oset) +SYSCALL_DEFINE3(sigprocmask, int, how, old_sigset_t __user *, nset, + old_sigset_t __user *, oset) { - int error; old_sigset_t old_set, new_set; + sigset_t new_blocked; - if (set) { - error = -EFAULT; - if (copy_from_user(&new_set, set, sizeof(*set))) - goto out; - new_set &= ~(sigmask(SIGKILL) | sigmask(SIGSTOP)); + old_set = current->blocked.sig[0]; - spin_lock_irq(¤t->sighand->siglock); - old_set = current->blocked.sig[0]; + if (nset) { + if (copy_from_user(&new_set, nset, sizeof(*nset))) + return -EFAULT; + + new_blocked = current->blocked; - error = 0; switch (how) { - default: - error = -EINVAL; - break; case SIG_BLOCK: - sigaddsetmask(¤t->blocked, new_set); + sigaddsetmask(&new_blocked, new_set); break; case SIG_UNBLOCK: - sigdelsetmask(¤t->blocked, new_set); + sigdelsetmask(&new_blocked, new_set); break; case SIG_SETMASK: - current->blocked.sig[0] = new_set; + new_blocked.sig[0] = new_set; break; + default: + return -EINVAL; } - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - if (error) - goto out; - if (oset) - goto set_old; - } else if (oset) { - old_set = current->blocked.sig[0]; - set_old: - error = -EFAULT; + set_current_blocked(&new_blocked); + } + + if (oset) { if (copy_to_user(oset, &old_set, sizeof(*oset))) - goto out; + return -EFAULT; } - error = 0; -out: - return error; + + return 0; } #endif /* __ARCH_WANT_SYS_SIGPROCMASK */ -#ifdef __ARCH_WANT_SYS_RT_SIGACTION -asmlinkage long -sys_rt_sigaction(int sig, - const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize) +#ifndef CONFIG_ODD_RT_SIGACTION +/** + * sys_rt_sigaction - alter an action taken by a process + * @sig: signal to be sent + * @act: new sigaction + * @oact: used to save the previous sigaction + * @sigsetsize: size of sigset_t type + */ +SYSCALL_DEFINE4(rt_sigaction, int, sig, + const struct sigaction __user *, act, + struct sigaction __user *, oact, + size_t, sigsetsize) { struct k_sigaction new_sa, old_sa; int ret = -EINVAL; @@ -2659,49 +3364,168 @@ sys_rt_sigaction(int sig, out: return ret; } -#endif /* __ARCH_WANT_SYS_RT_SIGACTION */ +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE4(rt_sigaction, int, sig, + const struct compat_sigaction __user *, act, + struct compat_sigaction __user *, oact, + compat_size_t, sigsetsize) +{ + struct k_sigaction new_ka, old_ka; + compat_sigset_t mask; +#ifdef __ARCH_HAS_SA_RESTORER + compat_uptr_t restorer; +#endif + int ret; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(compat_sigset_t)) + return -EINVAL; + + if (act) { + compat_uptr_t handler; + ret = get_user(handler, &act->sa_handler); + new_ka.sa.sa_handler = compat_ptr(handler); +#ifdef __ARCH_HAS_SA_RESTORER + ret |= get_user(restorer, &act->sa_restorer); + new_ka.sa.sa_restorer = compat_ptr(restorer); +#endif + ret |= copy_from_user(&mask, &act->sa_mask, sizeof(mask)); + ret |= get_user(new_ka.sa.sa_flags, &act->sa_flags); + if (ret) + return -EFAULT; + sigset_from_compat(&new_ka.sa.sa_mask, &mask); + } + + ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); + if (!ret && oact) { + sigset_to_compat(&mask, &old_ka.sa.sa_mask); + ret = put_user(ptr_to_compat(old_ka.sa.sa_handler), + &oact->sa_handler); + ret |= copy_to_user(&oact->sa_mask, &mask, sizeof(mask)); + ret |= put_user(old_ka.sa.sa_flags, &oact->sa_flags); +#ifdef __ARCH_HAS_SA_RESTORER + ret |= put_user(ptr_to_compat(old_ka.sa.sa_restorer), + &oact->sa_restorer); +#endif + } + return ret; +} +#endif +#endif /* !CONFIG_ODD_RT_SIGACTION */ + +#ifdef CONFIG_OLD_SIGACTION +SYSCALL_DEFINE3(sigaction, int, sig, + const struct old_sigaction __user *, act, + struct old_sigaction __user *, oact) +{ + struct k_sigaction new_ka, old_ka; + int ret; -#ifdef __ARCH_WANT_SYS_SGETMASK + if (act) { + old_sigset_t mask; + if (!access_ok(VERIFY_READ, act, sizeof(*act)) || + __get_user(new_ka.sa.sa_handler, &act->sa_handler) || + __get_user(new_ka.sa.sa_restorer, &act->sa_restorer) || + __get_user(new_ka.sa.sa_flags, &act->sa_flags) || + __get_user(mask, &act->sa_mask)) + return -EFAULT; +#ifdef __ARCH_HAS_KA_RESTORER + new_ka.ka_restorer = NULL; +#endif + siginitset(&new_ka.sa.sa_mask, mask); + } + + ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); + + if (!ret && oact) { + if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || + __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || + __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer) || + __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || + __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) + return -EFAULT; + } + + return ret; +} +#endif +#ifdef CONFIG_COMPAT_OLD_SIGACTION +COMPAT_SYSCALL_DEFINE3(sigaction, int, sig, + const struct compat_old_sigaction __user *, act, + struct compat_old_sigaction __user *, oact) +{ + struct k_sigaction new_ka, old_ka; + int ret; + compat_old_sigset_t mask; + compat_uptr_t handler, restorer; + + if (act) { + if (!access_ok(VERIFY_READ, act, sizeof(*act)) || + __get_user(handler, &act->sa_handler) || + __get_user(restorer, &act->sa_restorer) || + __get_user(new_ka.sa.sa_flags, &act->sa_flags) || + __get_user(mask, &act->sa_mask)) + return -EFAULT; + +#ifdef __ARCH_HAS_KA_RESTORER + new_ka.ka_restorer = NULL; +#endif + new_ka.sa.sa_handler = compat_ptr(handler); + new_ka.sa.sa_restorer = compat_ptr(restorer); + siginitset(&new_ka.sa.sa_mask, mask); + } + + ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); + + if (!ret && oact) { + if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || + __put_user(ptr_to_compat(old_ka.sa.sa_handler), + &oact->sa_handler) || + __put_user(ptr_to_compat(old_ka.sa.sa_restorer), + &oact->sa_restorer) || + __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || + __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) + return -EFAULT; + } + return ret; +} +#endif + +#ifdef CONFIG_SGETMASK_SYSCALL /* * For backwards compatibility. Functionality superseded by sigprocmask. */ -asmlinkage long -sys_sgetmask(void) +SYSCALL_DEFINE0(sgetmask) { /* SMP safe */ return current->blocked.sig[0]; } -asmlinkage long -sys_ssetmask(int newmask) +SYSCALL_DEFINE1(ssetmask, int, newmask) { - int old; - - spin_lock_irq(¤t->sighand->siglock); - old = current->blocked.sig[0]; + int old = current->blocked.sig[0]; + sigset_t newset; - siginitset(¤t->blocked, newmask & ~(sigmask(SIGKILL)| - sigmask(SIGSTOP))); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + siginitset(&newset, newmask); + set_current_blocked(&newset); return old; } -#endif /* __ARCH_WANT_SGETMASK */ +#endif /* CONFIG_SGETMASK_SYSCALL */ #ifdef __ARCH_WANT_SYS_SIGNAL /* * For backwards compatibility. Functionality superseded by sigaction. */ -asmlinkage unsigned long -sys_signal(int sig, __sighandler_t handler) +SYSCALL_DEFINE2(signal, int, sig, __sighandler_t, handler) { struct k_sigaction new_sa, old_sa; int ret; new_sa.sa.sa_handler = handler; new_sa.sa.sa_flags = SA_ONESHOT | SA_NOMASK; + sigemptyset(&new_sa.sa.sa_mask); ret = do_sigaction(sig, &new_sa, &old_sa); @@ -2711,18 +3535,35 @@ sys_signal(int sig, __sighandler_t handler) #ifdef __ARCH_WANT_SYS_PAUSE -asmlinkage long -sys_pause(void) +SYSCALL_DEFINE0(pause) { - current->state = TASK_INTERRUPTIBLE; - schedule(); + while (!signal_pending(current)) { + current->state = TASK_INTERRUPTIBLE; + schedule(); + } return -ERESTARTNOHAND; } #endif -#ifdef __ARCH_WANT_SYS_RT_SIGSUSPEND -asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize) +int sigsuspend(sigset_t *set) +{ + current->saved_sigmask = current->blocked; + set_current_blocked(set); + + current->state = TASK_INTERRUPTIBLE; + schedule(); + set_restore_sigmask(); + return -ERESTARTNOHAND; +} + +/** + * sys_rt_sigsuspend - replace the signal mask for a value with the + * @unewset value until a signal is received + * @unewset: new signal mask value + * @sigsetsize: size of sigset_t type + */ +SYSCALL_DEFINE2(rt_sigsuspend, sigset_t __user *, unewset, size_t, sigsetsize) { sigset_t newset; @@ -2732,26 +3573,94 @@ asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize) if (copy_from_user(&newset, unewset, sizeof(newset))) return -EFAULT; - sigdelsetmask(&newset, sigmask(SIGKILL)|sigmask(SIGSTOP)); + return sigsuspend(&newset); +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE2(rt_sigsuspend, compat_sigset_t __user *, unewset, compat_size_t, sigsetsize) +{ +#ifdef __BIG_ENDIAN + sigset_t newset; + compat_sigset_t newset32; - spin_lock_irq(¤t->sighand->siglock); - current->saved_sigmask = current->blocked; - current->blocked = newset; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; - current->state = TASK_INTERRUPTIBLE; - schedule(); - set_thread_flag(TIF_RESTORE_SIGMASK); - return -ERESTARTNOHAND; + if (copy_from_user(&newset32, unewset, sizeof(compat_sigset_t))) + return -EFAULT; + sigset_from_compat(&newset, &newset32); + return sigsuspend(&newset); +#else + /* on little-endian bitmaps don't care about granularity */ + return sys_rt_sigsuspend((sigset_t __user *)unewset, sigsetsize); +#endif +} +#endif + +#ifdef CONFIG_OLD_SIGSUSPEND +SYSCALL_DEFINE1(sigsuspend, old_sigset_t, mask) +{ + sigset_t blocked; + siginitset(&blocked, mask); + return sigsuspend(&blocked); +} +#endif +#ifdef CONFIG_OLD_SIGSUSPEND3 +SYSCALL_DEFINE3(sigsuspend, int, unused1, int, unused2, old_sigset_t, mask) +{ + sigset_t blocked; + siginitset(&blocked, mask); + return sigsuspend(&blocked); +} +#endif + +__weak const char *arch_vma_name(struct vm_area_struct *vma) +{ + return NULL; } -#endif /* __ARCH_WANT_SYS_RT_SIGSUSPEND */ void __init signals_init(void) { - sigqueue_cachep = - kmem_cache_create("sigqueue", - sizeof(struct sigqueue), - __alignof__(struct sigqueue), - SLAB_PANIC, NULL, NULL); + sigqueue_cachep = KMEM_CACHE(sigqueue, SLAB_PANIC); +} + +#ifdef CONFIG_KGDB_KDB +#include <linux/kdb.h> +/* + * kdb_send_sig_info - Allows kdb to send signals without exposing + * signal internals. This function checks if the required locks are + * available before calling the main signal code, to avoid kdb + * deadlocks. + */ +void +kdb_send_sig_info(struct task_struct *t, struct siginfo *info) +{ + static struct task_struct *kdb_prev_t; + int sig, new_t; + if (!spin_trylock(&t->sighand->siglock)) { + kdb_printf("Can't do kill command now.\n" + "The sigmask lock is held somewhere else in " + "kernel, try again later\n"); + return; + } + spin_unlock(&t->sighand->siglock); + new_t = kdb_prev_t != t; + kdb_prev_t = t; + if (t->state != TASK_RUNNING && new_t) { + kdb_printf("Process is not RUNNING, sending a signal from " + "kdb risks deadlock\n" + "on the run queue locks. " + "The signal has _not_ been sent.\n" + "Reissue the kill command if you want to risk " + "the deadlock.\n"); + return; + } + sig = info->si_signo; + if (send_sig_info(sig, info, t)) + kdb_printf("Fail to deliver Signal %d to process %d.\n", + sig, t->pid); + else + kdb_printf("Signal %d is sent to process %d.\n", sig, t->pid); } +#endif /* CONFIG_KGDB_KDB */ |