X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=kernel%2Fsys.c;h=2d5179c67cec727f40476e2f9e75fbb9eeeb8d8c;hb=913b83944b9e13c60ca4ef95cf262547ff6bf93b;hp=c93d37f71aef98b23a9f43f6ac7d1f37b9ff20fd;hpb=4fa639123d9e6e8dfaa3d116368f4b2478da31af;p=linux-2.6 diff --git a/kernel/sys.c b/kernel/sys.c index c93d37f71a..2d5179c67c 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include @@ -57,6 +56,12 @@ #ifndef GET_FPEXC_CTL # define GET_FPEXC_CTL(a,b) (-EINVAL) #endif +#ifndef GET_ENDIAN +# define GET_ENDIAN(a,b) (-EINVAL) +#endif +#ifndef SET_ENDIAN +# define SET_ENDIAN(a,b) (-EINVAL) +#endif /* * this is where the system-wide overflow UID and GID are defined, for @@ -132,14 +137,15 @@ static int __kprobes notifier_call_chain(struct notifier_block **nl, unsigned long val, void *v) { int ret = NOTIFY_DONE; - struct notifier_block *nb; + struct notifier_block *nb, *next_nb; nb = rcu_dereference(*nl); while (nb) { + next_nb = rcu_dereference(nb->next); ret = nb->notifier_call(nb, val, v); if ((ret & NOTIFY_STOP_MASK) == NOTIFY_STOP_MASK) break; - nb = rcu_dereference(nb->next); + nb = next_nb; } return ret; } @@ -583,7 +589,7 @@ void emergency_restart(void) } EXPORT_SYMBOL_GPL(emergency_restart); -void kernel_restart_prepare(char *cmd) +static void kernel_restart_prepare(char *cmd) { blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd); system_state = SYSTEM_RESTART; @@ -617,7 +623,7 @@ EXPORT_SYMBOL_GPL(kernel_restart); * Move into place and start executing a preloaded standalone * executable. If nothing was preloaded return an error. */ -void kernel_kexec(void) +static void kernel_kexec(void) { #ifdef CONFIG_KEXEC struct kimage *image; @@ -631,7 +637,6 @@ void kernel_kexec(void) machine_kexec(image); #endif } -EXPORT_SYMBOL_GPL(kernel_kexec); void kernel_shutdown_prepare(enum system_states state) { @@ -1202,69 +1207,24 @@ asmlinkage long sys_times(struct tms __user * tbuf) */ if (tbuf) { struct tms tmp; + struct task_struct *tsk = current; + struct task_struct *t; cputime_t utime, stime, cutime, cstime; -#ifdef CONFIG_SMP - if (thread_group_empty(current)) { - /* - * Single thread case without the use of any locks. - * - * We may race with release_task if two threads are - * executing. However, release task first adds up the - * counters (__exit_signal) before removing the task - * from the process tasklist (__unhash_process). - * __exit_signal also acquires and releases the - * siglock which results in the proper memory ordering - * so that the list modifications are always visible - * after the counters have been updated. - * - * If the counters have been updated by the second thread - * but the thread has not yet been removed from the list - * then the other branch will be executing which will - * block on tasklist_lock until the exit handling of the - * other task is finished. - * - * This also implies that the sighand->siglock cannot - * be held by another processor. So we can also - * skip acquiring that lock. - */ - utime = cputime_add(current->signal->utime, current->utime); - stime = cputime_add(current->signal->utime, current->stime); - cutime = current->signal->cutime; - cstime = current->signal->cstime; - } else -#endif - { + spin_lock_irq(&tsk->sighand->siglock); + utime = tsk->signal->utime; + stime = tsk->signal->stime; + t = tsk; + do { + utime = cputime_add(utime, t->utime); + stime = cputime_add(stime, t->stime); + t = next_thread(t); + } while (t != tsk); - /* Process with multiple threads */ - struct task_struct *tsk = current; - struct task_struct *t; + cutime = tsk->signal->cutime; + cstime = tsk->signal->cstime; + spin_unlock_irq(&tsk->sighand->siglock); - read_lock(&tasklist_lock); - utime = tsk->signal->utime; - stime = tsk->signal->stime; - t = tsk; - do { - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); - t = next_thread(t); - } while (t != tsk); - - /* - * While we have tasklist_lock read-locked, no dying thread - * can be updating current->signal->[us]time. Instead, - * we got their counts included in the live thread loop. - * However, another thread can come in right now and - * do a wait call that updates current->signal->c[us]time. - * To make sure we always see that pair updated atomically, - * we take the siglock around fetching them. - */ - spin_lock_irq(&tsk->sighand->siglock); - cutime = tsk->signal->cutime; - cstime = tsk->signal->cstime; - spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); - } tmp.tms_utime = cputime_to_clock_t(utime); tmp.tms_stime = cputime_to_clock_t(stime); tmp.tms_cutime = cputime_to_clock_t(cutime); @@ -1417,18 +1377,29 @@ asmlinkage long sys_getsid(pid_t pid) asmlinkage long sys_setsid(void) { struct task_struct *group_leader = current->group_leader; - struct pid *pid; + pid_t session; int err = -EPERM; mutex_lock(&tty_mutex); write_lock_irq(&tasklist_lock); - pid = find_pid(PIDTYPE_PGID, group_leader->pid); - if (pid) + /* Fail if I am already a session leader */ + if (group_leader->signal->leader) + goto out; + + session = group_leader->pid; + /* Fail if a process group id already exists that equals the + * proposed session id. + * + * Don't check if session id == 1 because kernel threads use this + * session id and so the check will always fail and make it so + * init cannot successfully call setsid. + */ + if (session > 1 && find_task_by_pid_type(PIDTYPE_PGID, session)) goto out; group_leader->signal->leader = 1; - __set_special_pids(group_leader->pid, group_leader->pid); + __set_special_pids(session, session); group_leader->signal->tty = NULL; group_leader->signal->tty_old_pgrp = 0; err = process_group(group_leader); @@ -1894,23 +1865,20 @@ out: * fields when reaping, so a sample either gets all the additions of a * given child after it's reaped, or none so this sample is before reaping. * - * tasklist_lock locking optimisation: - * If we are current and single threaded, we do not need to take the tasklist - * lock or the siglock. No one else can take our signal_struct away, - * no one else can reap the children to update signal->c* counters, and - * no one else can race with the signal-> fields. - * If we do not take the tasklist_lock, the signal-> fields could be read - * out of order while another thread was just exiting. So we place a - * read memory barrier when we avoid the lock. On the writer side, - * write memory barrier is implied in __exit_signal as __exit_signal releases - * the siglock spinlock after updating the signal-> fields. - * - * We don't really need the siglock when we access the non c* fields - * of the signal_struct (for RUSAGE_SELF) even in multithreaded - * case, since we take the tasklist lock for read and the non c* signal-> - * fields are updated only in __exit_signal, which is called with - * tasklist_lock taken for write, hence these two threads cannot execute - * concurrently. + * Locking: + * We need to take the siglock for CHILDEREN, SELF and BOTH + * for the cases current multithreaded, non-current single threaded + * non-current multithreaded. Thread traversal is now safe with + * the siglock held. + * Strictly speaking, we donot need to take the siglock if we are current and + * single threaded, as no one else can take our signal_struct away, no one + * else can reap the children to update signal->c* counters, and no one else + * can race with the signal-> fields. If we do not take any lock, the + * signal-> fields could be read out of order while another thread was just + * exiting. So we should place a read memory barrier when we avoid the lock. + * On the writer side, write memory barrier is implied in __exit_signal + * as __exit_signal releases the siglock spinlock after updating the signal-> + * fields. But we don't do this yet to keep things simple. * */ @@ -1919,35 +1887,25 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) struct task_struct *t; unsigned long flags; cputime_t utime, stime; - int need_lock = 0; memset((char *) r, 0, sizeof *r); utime = stime = cputime_zero; - if (p != current || !thread_group_empty(p)) - need_lock = 1; - - if (need_lock) { - read_lock(&tasklist_lock); - if (unlikely(!p->signal)) { - read_unlock(&tasklist_lock); - return; - } - } else - /* See locking comments above */ - smp_rmb(); + rcu_read_lock(); + if (!lock_task_sighand(p, &flags)) { + rcu_read_unlock(); + return; + } switch (who) { case RUSAGE_BOTH: case RUSAGE_CHILDREN: - spin_lock_irqsave(&p->sighand->siglock, flags); utime = p->signal->cutime; stime = p->signal->cstime; r->ru_nvcsw = p->signal->cnvcsw; r->ru_nivcsw = p->signal->cnivcsw; r->ru_minflt = p->signal->cmin_flt; r->ru_majflt = p->signal->cmaj_flt; - spin_unlock_irqrestore(&p->sighand->siglock, flags); if (who == RUSAGE_CHILDREN) break; @@ -1975,8 +1933,9 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) BUG(); } - if (need_lock) - read_unlock(&tasklist_lock); + unlock_task_sighand(p, &flags); + rcu_read_unlock(); + cputime_to_timeval(utime, &r->ru_utime); cputime_to_timeval(stime, &r->ru_stime); } @@ -2091,6 +2050,13 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, return -EFAULT; return 0; } + case PR_GET_ENDIAN: + error = GET_ENDIAN(current, arg2); + break; + case PR_SET_ENDIAN: + error = SET_ENDIAN(current, arg2); + break; + default: error = -EINVAL; break;