X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fsys.c;h=304b5410d746ec724afcb4e3ce50bfe65f1bf2ff;hb=7748dbfaa010b12d5fb9ddf80199534c565c6bce;hp=119fb0d9e24ef231e4dda0a9c7c8b20a023c5314;hpb=231bed205879236357171e50bd8965e70797ecdc;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/sys.c b/kernel/sys.c index 119fb0d..304b541 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -4,7 +4,6 @@ * Copyright (C) 1991, 1992 Linus Torvalds */ -#include #include #include #include @@ -13,9 +12,9 @@ #include #include #include -#include #include #include +#include #include #include #include @@ -30,10 +29,15 @@ #include #include #include +#include +#include +#include +#include #include #include #include +#include #include #include @@ -57,6 +61,12 @@ #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 @@ -87,142 +97,14 @@ EXPORT_SYMBOL(fs_overflowgid); */ int C_A_D = 1; -int cad_pid = 1; +struct pid *cad_pid; +EXPORT_SYMBOL(cad_pid); /* - * Notifier list for kernel code which wants to be called - * at shutdown. This is used to stop any idling DMA operations - * and the like. - */ - -static struct notifier_block *reboot_notifier_list; -static DEFINE_RWLOCK(notifier_lock); - -/** - * notifier_chain_register - Add notifier to a notifier chain - * @list: Pointer to root list pointer - * @n: New entry in notifier chain - * - * Adds a notifier to a notifier chain. - * - * Currently always returns zero. - */ - -int notifier_chain_register(struct notifier_block **list, struct notifier_block *n) -{ - write_lock(¬ifier_lock); - while(*list) - { - if(n->priority > (*list)->priority) - break; - list= &((*list)->next); - } - n->next = *list; - *list=n; - write_unlock(¬ifier_lock); - return 0; -} - -EXPORT_SYMBOL(notifier_chain_register); - -/** - * notifier_chain_unregister - Remove notifier from a notifier chain - * @nl: Pointer to root list pointer - * @n: New entry in notifier chain - * - * Removes a notifier from a notifier chain. - * - * Returns zero on success, or %-ENOENT on failure. - */ - -int notifier_chain_unregister(struct notifier_block **nl, struct notifier_block *n) -{ - write_lock(¬ifier_lock); - while((*nl)!=NULL) - { - if((*nl)==n) - { - *nl=n->next; - write_unlock(¬ifier_lock); - return 0; - } - nl=&((*nl)->next); - } - write_unlock(¬ifier_lock); - return -ENOENT; -} - -EXPORT_SYMBOL(notifier_chain_unregister); - -/** - * notifier_call_chain - Call functions in a notifier chain - * @n: Pointer to root pointer of notifier chain - * @val: Value passed unmodified to notifier function - * @v: Pointer passed unmodified to notifier function - * - * Calls each function in a notifier chain in turn. - * - * If the return value of the notifier can be and'd - * with %NOTIFY_STOP_MASK, then notifier_call_chain - * will return immediately, with the return value of - * the notifier function which halted execution. - * Otherwise, the return value is the return value - * of the last notifier function called. - */ - -int __kprobes notifier_call_chain(struct notifier_block **n, unsigned long val, void *v) -{ - int ret=NOTIFY_DONE; - struct notifier_block *nb = *n; - - while(nb) - { - ret=nb->notifier_call(nb,val,v); - if(ret&NOTIFY_STOP_MASK) - { - return ret; - } - nb=nb->next; - } - return ret; -} - -EXPORT_SYMBOL(notifier_call_chain); - -/** - * register_reboot_notifier - Register function to be called at reboot time - * @nb: Info about notifier function to be called - * - * Registers a function with the list of functions - * to be called at reboot time. - * - * Currently always returns zero, as notifier_chain_register - * always returns zero. - */ - -int register_reboot_notifier(struct notifier_block * nb) -{ - return notifier_chain_register(&reboot_notifier_list, nb); -} - -EXPORT_SYMBOL(register_reboot_notifier); - -/** - * unregister_reboot_notifier - Unregister previously registered reboot notifier - * @nb: Hook to be unregistered - * - * Unregisters a previously registered reboot - * notifier function. - * - * Returns zero on success, or %-ENOENT on failure. + * If set, this is used for preparing the system to power off. */ - -int unregister_reboot_notifier(struct notifier_block * nb) -{ - return notifier_chain_unregister(&reboot_notifier_list, nb); -} -EXPORT_SYMBOL(unregister_reboot_notifier); +void (*pm_power_off_prepare)(void); static int set_one_prio(struct task_struct *p, int niceval, int error) { @@ -254,8 +136,9 @@ asmlinkage long sys_setpriority(int which, int who, int niceval) struct task_struct *g, *p; struct user_struct *user; int error = -EINVAL; + struct pid *pgrp; - if (which > 2 || which < 0) + if (which > PRIO_USER || which < PRIO_PROCESS) goto out; /* normalize: avoid signed division (rounding problems) */ @@ -268,18 +151,21 @@ asmlinkage long sys_setpriority(int which, int who, int niceval) read_lock(&tasklist_lock); switch (which) { case PRIO_PROCESS: - if (!who) - who = current->pid; - p = find_task_by_pid(who); + if (who) + p = find_task_by_vpid(who); + else + p = current; if (p) error = set_one_prio(p, niceval, error); break; case PRIO_PGRP: - if (!who) - who = process_group(current); - do_each_task_pid(who, PIDTYPE_PGID, p) { + if (who) + pgrp = find_vpid(who); + else + pgrp = task_pgrp(current); + do_each_pid_task(pgrp, PIDTYPE_PGID, p) { error = set_one_prio(p, niceval, error); - } while_each_task_pid(who, PIDTYPE_PGID, p); + } while_each_pid_task(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: user = current->user; @@ -314,16 +200,18 @@ asmlinkage long sys_getpriority(int which, int who) struct task_struct *g, *p; struct user_struct *user; long niceval, retval = -ESRCH; + struct pid *pgrp; - if (which > 2 || which < 0) + if (which > PRIO_USER || which < PRIO_PROCESS) return -EINVAL; read_lock(&tasklist_lock); switch (which) { case PRIO_PROCESS: - if (!who) - who = current->pid; - p = find_task_by_pid(who); + if (who) + p = find_task_by_vpid(who); + else + p = current; if (p) { niceval = 20 - task_nice(p); if (niceval > retval) @@ -331,13 +219,15 @@ asmlinkage long sys_getpriority(int which, int who) } break; case PRIO_PGRP: - if (!who) - who = process_group(current); - do_each_task_pid(who, PIDTYPE_PGID, p) { + if (who) + pgrp = find_vpid(who); + else + pgrp = task_pgrp(current); + do_each_pid_task(pgrp, PIDTYPE_PGID, p) { niceval = 20 - task_nice(p); if (niceval > retval) retval = niceval; - } while_each_task_pid(who, PIDTYPE_PGID, p); + } while_each_pid_task(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: user = current->user; @@ -378,11 +268,12 @@ void emergency_restart(void) } EXPORT_SYMBOL_GPL(emergency_restart); -void kernel_restart_prepare(char *cmd) +static void kernel_restart_prepare(char *cmd) { - notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd); + blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd); system_state = SYSTEM_RESTART; device_shutdown(); + sysdev_shutdown(); } /** @@ -396,12 +287,10 @@ void kernel_restart_prepare(char *cmd) void kernel_restart(char *cmd) { kernel_restart_prepare(cmd); - if (!cmd) { + if (!cmd) printk(KERN_EMERG "Restarting system.\n"); - } else { + else printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd); - } - printk(".\n"); machine_restart(cmd); } EXPORT_SYMBOL_GPL(kernel_restart); @@ -412,25 +301,23 @@ 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; image = xchg(&kexec_image, NULL); - if (!image) { + if (!image) return; - } kernel_restart_prepare(NULL); printk(KERN_EMERG "Starting new kernel\n"); machine_shutdown(); machine_kexec(image); #endif } -EXPORT_SYMBOL_GPL(kernel_kexec); void kernel_shutdown_prepare(enum system_states state) { - notifier_call_chain(&reboot_notifier_list, + blocking_notifier_call_chain(&reboot_notifier_list, (state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL); system_state = state; device_shutdown(); @@ -443,6 +330,7 @@ void kernel_shutdown_prepare(enum system_states state) void kernel_halt(void) { kernel_shutdown_prepare(SYSTEM_HALT); + sysdev_shutdown(); printk(KERN_EMERG "System halted.\n"); machine_halt(); } @@ -457,6 +345,10 @@ EXPORT_SYMBOL_GPL(kernel_halt); void kernel_power_off(void) { kernel_shutdown_prepare(SYSTEM_POWER_OFF); + if (pm_power_off_prepare) + pm_power_off_prepare(); + disable_nonboot_cpus(); + sysdev_shutdown(); printk(KERN_EMERG "Power down.\n"); machine_power_off(); } @@ -532,10 +424,10 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user unlock_kernel(); return -EINVAL; -#ifdef CONFIG_SOFTWARE_SUSPEND +#ifdef CONFIG_HIBERNATION case LINUX_REBOOT_CMD_SW_SUSPEND: { - int ret = software_suspend(); + int ret = hibernate(); unlock_kernel(); return ret; } @@ -549,7 +441,7 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user return 0; } -static void deferred_cad(void *dummy) +static void deferred_cad(struct work_struct *dummy) { kernel_restart(NULL); } @@ -561,15 +453,14 @@ static void deferred_cad(void *dummy) */ void ctrl_alt_del(void) { - static DECLARE_WORK(cad_work, deferred_cad, NULL); + static DECLARE_WORK(cad_work, deferred_cad); if (C_A_D) schedule_work(&cad_work); else - kill_proc(cad_pid, SIGINT, 1); + kill_cad_pid(SIGINT, 1); } - /* * Unprivileged users may change the real gid to the effective gid * or vice versa. (BSD-style) @@ -614,13 +505,11 @@ asmlinkage long sys_setregid(gid_t rgid, gid_t egid) (current->sgid == egid) || capable(CAP_SETGID)) new_egid = egid; - else { + else return -EPERM; - } } - if (new_egid != old_egid) - { - current->mm->dumpable = suid_dumpable; + if (new_egid != old_egid) { + set_dumpable(current->mm, suid_dumpable); smp_wmb(); } if (rgid != (gid_t) -1 || @@ -648,20 +537,15 @@ asmlinkage long sys_setgid(gid_t gid) if (retval) return retval; - if (capable(CAP_SETGID)) - { - if(old_egid != gid) - { - current->mm->dumpable = suid_dumpable; + if (capable(CAP_SETGID)) { + if (old_egid != gid) { + set_dumpable(current->mm, suid_dumpable); smp_wmb(); } current->gid = current->egid = current->sgid = current->fsgid = gid; - } - else if ((gid == current->gid) || (gid == current->sgid)) - { - if(old_egid != gid) - { - current->mm->dumpable = suid_dumpable; + } else if ((gid == current->gid) || (gid == current->sgid)) { + if (old_egid != gid) { + set_dumpable(current->mm, suid_dumpable); smp_wmb(); } current->egid = current->fsgid = gid; @@ -678,22 +562,21 @@ static int set_user(uid_t new_ruid, int dumpclear) { struct user_struct *new_user; - new_user = alloc_uid(new_ruid); + new_user = alloc_uid(current->nsproxy->user_ns, new_ruid); if (!new_user) return -EAGAIN; if (atomic_read(&new_user->processes) >= current->signal->rlim[RLIMIT_NPROC].rlim_cur && - new_user != &root_user) { + new_user != current->nsproxy->user_ns->root_user) { free_uid(new_user); return -EAGAIN; } switch_uid(new_user); - if(dumpclear) - { - current->mm->dumpable = suid_dumpable; + if (dumpclear) { + set_dumpable(current->mm, suid_dumpable); smp_wmb(); } current->uid = new_ruid; @@ -748,9 +631,8 @@ asmlinkage long sys_setreuid(uid_t ruid, uid_t euid) if (new_ruid != old_ruid && set_user(new_ruid, new_euid != old_euid) < 0) return -EAGAIN; - if (new_euid != old_euid) - { - current->mm->dumpable = suid_dumpable; + if (new_euid != old_euid) { + set_dumpable(current->mm, suid_dumpable); smp_wmb(); } current->fsuid = current->euid = new_euid; @@ -781,14 +663,14 @@ asmlinkage long sys_setreuid(uid_t ruid, uid_t euid) asmlinkage long sys_setuid(uid_t uid) { int old_euid = current->euid; - int old_ruid, old_suid, new_ruid, new_suid; + int old_ruid, old_suid, new_suid; int retval; retval = security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_ID); if (retval) return retval; - old_ruid = new_ruid = current->uid; + old_ruid = current->uid; old_suid = current->suid; new_suid = old_suid; @@ -799,9 +681,8 @@ asmlinkage long sys_setuid(uid_t uid) } else if ((uid != current->uid) && (uid != new_suid)) return -EPERM; - if (old_euid != uid) - { - current->mm->dumpable = suid_dumpable; + if (old_euid != uid) { + set_dumpable(current->mm, suid_dumpable); smp_wmb(); } current->fsuid = current->euid = uid; @@ -845,9 +726,8 @@ asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) return -EAGAIN; } if (euid != (uid_t) -1) { - if (euid != current->euid) - { - current->mm->dumpable = suid_dumpable; + if (euid != current->euid) { + set_dumpable(current->mm, suid_dumpable); smp_wmb(); } current->euid = euid; @@ -896,9 +776,8 @@ asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid) return -EPERM; } if (egid != (gid_t) -1) { - if (egid != current->egid) - { - current->mm->dumpable = suid_dumpable; + if (egid != current->egid) { + set_dumpable(current->mm, suid_dumpable); smp_wmb(); } current->egid = egid; @@ -942,11 +821,9 @@ asmlinkage long sys_setfsuid(uid_t uid) if (uid == current->uid || uid == current->euid || uid == current->suid || uid == current->fsuid || - capable(CAP_SETUID)) - { - if (uid != old_fsuid) - { - current->mm->dumpable = suid_dumpable; + capable(CAP_SETUID)) { + if (uid != old_fsuid) { + set_dumpable(current->mm, suid_dumpable); smp_wmb(); } current->fsuid = uid; @@ -961,7 +838,7 @@ asmlinkage long sys_setfsuid(uid_t uid) } /* - * Samma på svenska.. + * Samma pÃ¥ svenska.. */ asmlinkage long sys_setfsgid(gid_t gid) { @@ -973,11 +850,9 @@ asmlinkage long sys_setfsgid(gid_t gid) if (gid == current->gid || gid == current->egid || gid == current->sgid || gid == current->fsgid || - capable(CAP_SETGID)) - { - if (gid != old_fsgid) - { - current->mm->dumpable = suid_dumpable; + capable(CAP_SETGID)) { + if (gid != old_fsgid) { + set_dumpable(current->mm, suid_dumpable); smp_wmb(); } current->fsgid = gid; @@ -997,69 +872,24 @@ 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); @@ -1082,15 +912,15 @@ asmlinkage long sys_times(struct tms __user * tbuf) * Auch. Had to add the 'did_exec' flag to conform completely to POSIX. * LBT 04.03.94 */ - asmlinkage long sys_setpgid(pid_t pid, pid_t pgid) { struct task_struct *p; struct task_struct *group_leader = current->group_leader; int err = -EINVAL; + struct pid_namespace *ns; if (!pid) - pid = group_leader->pid; + pid = task_pid_vnr(group_leader); if (!pgid) pgid = pid; if (pgid < 0) @@ -1099,10 +929,12 @@ asmlinkage long sys_setpgid(pid_t pid, pid_t pgid) /* From this point forward we keep holding onto the tasklist lock * so that our parent does not change from under us. -DaveM */ + ns = current->nsproxy->pid_ns; + write_lock_irq(&tasklist_lock); err = -ESRCH; - p = find_task_by_pid(pid); + p = find_task_by_pid_ns(pid, ns); if (!p) goto out; @@ -1110,9 +942,9 @@ asmlinkage long sys_setpgid(pid_t pid, pid_t pgid) if (!thread_group_leader(p)) goto out; - if (p->real_parent == group_leader) { + if (p->real_parent->tgid == group_leader->tgid) { err = -EPERM; - if (p->signal->session != group_leader->signal->session) + if (task_session(p) != task_session(group_leader)) goto out; err = -EACCES; if (p->did_exec) @@ -1128,24 +960,24 @@ asmlinkage long sys_setpgid(pid_t pid, pid_t pgid) goto out; if (pgid != pid) { - struct task_struct *p; + struct task_struct *g; - do_each_task_pid(pgid, PIDTYPE_PGID, p) { - if (p->signal->session == group_leader->signal->session) - goto ok_pgid; - } while_each_task_pid(pgid, PIDTYPE_PGID, p); - goto out; + g = find_task_by_pid_type_ns(PIDTYPE_PGID, pgid, ns); + if (!g || task_session(g) != task_session(group_leader)) + goto out; } -ok_pgid: err = security_task_setpgid(p, pgid); if (err) goto out; - if (process_group(p) != pgid) { + if (task_pgrp_nr_ns(p, ns) != pgid) { + struct pid *pid; + detach_pid(p, PIDTYPE_PGID); - p->signal->pgrp = pgid; - attach_pid(p, PIDTYPE_PGID, pgid); + pid = find_vpid(pgid); + attach_pid(p, PIDTYPE_PGID, pid); + set_task_pgrp(p, pid_nr(pid)); } err = 0; @@ -1157,20 +989,22 @@ out: asmlinkage long sys_getpgid(pid_t pid) { - if (!pid) { - return process_group(current); - } else { + if (!pid) + return task_pgrp_vnr(current); + else { int retval; struct task_struct *p; + struct pid_namespace *ns; - read_lock(&tasklist_lock); - p = find_task_by_pid(pid); + ns = current->nsproxy->pid_ns; + read_lock(&tasklist_lock); + p = find_task_by_pid_ns(pid, ns); retval = -ESRCH; if (p) { retval = security_task_getpgid(p); if (!retval) - retval = process_group(p); + retval = task_pgrp_nr_ns(p, ns); } read_unlock(&tasklist_lock); return retval; @@ -1182,27 +1016,29 @@ asmlinkage long sys_getpgid(pid_t pid) asmlinkage long sys_getpgrp(void) { /* SMP - assuming writes are word atomic this is fine */ - return process_group(current); + return task_pgrp_vnr(current); } #endif asmlinkage long sys_getsid(pid_t pid) { - if (!pid) { - return current->signal->session; - } else { + if (!pid) + return task_session_vnr(current); + else { int retval; struct task_struct *p; + struct pid_namespace *ns; - read_lock(&tasklist_lock); - p = find_task_by_pid(pid); + ns = current->nsproxy->pid_ns; + read_lock(&tasklist_lock); + p = find_task_by_pid_ns(pid, ns); retval = -ESRCH; - if(p) { + if (p) { retval = security_task_getsid(p); if (!retval) - retval = p->signal->session; + retval = task_session_nr_ns(p, ns); } read_unlock(&tasklist_lock); return retval; @@ -1212,24 +1048,37 @@ 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_ns(PIDTYPE_PGID, + session, &init_pid_ns)) goto out; group_leader->signal->leader = 1; - __set_special_pids(group_leader->pid, group_leader->pid); + __set_special_pids(session, session); + + spin_lock(&group_leader->sighand->siglock); group_leader->signal->tty = NULL; - group_leader->signal->tty_old_pgrp = 0; - err = process_group(group_leader); + spin_unlock(&group_leader->sighand->siglock); + + err = task_pgrp_vnr(group_leader); out: write_unlock_irq(&tasklist_lock); - mutex_unlock(&tty_mutex); return err; } @@ -1256,9 +1105,9 @@ struct group_info *groups_alloc(int gidsetsize) group_info->nblocks = nblocks; atomic_set(&group_info->usage, 1); - if (gidsetsize <= NGROUPS_SMALL) { + if (gidsetsize <= NGROUPS_SMALL) group_info->blocks[0] = group_info->small_block; - } else { + else { for (i = 0; i < nblocks; i++) { gid_t *b; b = (void *)__get_free_page(GFP_USER); @@ -1314,7 +1163,7 @@ static int groups_to_user(gid_t __user *grouplist, /* fill a group_info from a user-space array - it must be allocated already */ static int groups_from_user(struct group_info *group_info, gid_t __user *grouplist) - { +{ int i; int count = group_info->ngroups; @@ -1363,7 +1212,7 @@ static void groups_sort(struct group_info *group_info) /* a simple bsearch */ int groups_search(struct group_info *group_info, gid_t grp) { - int left, right; + unsigned int left, right; if (!group_info) return 0; @@ -1371,7 +1220,7 @@ int groups_search(struct group_info *group_info, gid_t grp) left = 0; right = group_info->ngroups; while (left < right) { - int mid = (left+right)/2; + unsigned int mid = (left+right)/2; int cmp = grp - GROUP_AT(group_info, mid); if (cmp > 0) left = mid + 1; @@ -1472,9 +1321,8 @@ asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist) int in_group_p(gid_t grp) { int retval = 1; - if (grp != current->fsgid) { + if (grp != current->fsgid) retval = groups_search(current->group_info, grp); - } return retval; } @@ -1483,9 +1331,8 @@ EXPORT_SYMBOL(in_group_p); int in_egroup_p(gid_t grp) { int retval = 1; - if (grp != current->egid) { + if (grp != current->egid) retval = groups_search(current->group_info, grp); - } return retval; } @@ -1500,7 +1347,7 @@ asmlinkage long sys_newuname(struct new_utsname __user * name) int errno = 0; down_read(&uts_sem); - if (copy_to_user(name,&system_utsname,sizeof *name)) + if (copy_to_user(name, utsname(), sizeof *name)) errno = -EFAULT; up_read(&uts_sem); return errno; @@ -1518,8 +1365,8 @@ asmlinkage long sys_sethostname(char __user *name, int len) down_write(&uts_sem); errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { - memcpy(system_utsname.nodename, tmp, len); - system_utsname.nodename[len] = 0; + memcpy(utsname()->nodename, tmp, len); + utsname()->nodename[len] = 0; errno = 0; } up_write(&uts_sem); @@ -1535,11 +1382,11 @@ asmlinkage long sys_gethostname(char __user *name, int len) if (len < 0) return -EINVAL; down_read(&uts_sem); - i = 1 + strlen(system_utsname.nodename); + i = 1 + strlen(utsname()->nodename); if (i > len) i = len; errno = 0; - if (copy_to_user(name, system_utsname.nodename, i)) + if (copy_to_user(name, utsname()->nodename, i)) errno = -EFAULT; up_read(&uts_sem); return errno; @@ -1564,8 +1411,8 @@ asmlinkage long sys_setdomainname(char __user *name, int len) down_write(&uts_sem); errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { - memcpy(system_utsname.domainname, tmp, len); - system_utsname.domainname[len] = 0; + memcpy(utsname()->domainname, tmp, len); + utsname()->domainname[len] = 0; errno = 0; } up_write(&uts_sem); @@ -1600,9 +1447,9 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r task_lock(current->group_leader); x = current->signal->rlim[resource]; task_unlock(current->group_leader); - if(x.rlim_cur > 0x7FFFFFFF) + if (x.rlim_cur > 0x7FFFFFFF) x.rlim_cur = 0x7FFFFFFF; - if(x.rlim_max > 0x7FFFFFFF) + if (x.rlim_max > 0x7FFFFFFF) x.rlim_max = 0x7FFFFFFF; return copy_to_user(rlim, &x, sizeof(x))?-EFAULT:0; } @@ -1632,6 +1479,16 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim) if (retval) return retval; + if (resource == RLIMIT_CPU && new_rlim.rlim_cur == 0) { + /* + * The caller is asking for an immediate RLIMIT_CPU + * expiry. But we use the zero value to mean "it was + * never set". So let's cheat and make it one second + * instead + */ + new_rlim.rlim_cur = 1; + } + task_lock(current->group_leader); *old_rlim = new_rlim; task_unlock(current->group_leader); @@ -1653,15 +1510,6 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim) unsigned long rlim_cur = new_rlim.rlim_cur; cputime_t cputime; - if (rlim_cur == 0) { - /* - * The caller is asking for an immediate RLIMIT_CPU - * expiry. But we use the zero value to mean "it was - * never set". So let's cheat and make it one second - * instead - */ - rlim_cur = 1; - } cputime = secs_to_cputime(rlim_cur); read_lock(&tasklist_lock); spin_lock_irq(¤t->sighand->siglock); @@ -1689,23 +1537,20 @@ 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. * */ @@ -1714,35 +1559,27 @@ 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); + r->ru_inblock = p->signal->cinblock; + r->ru_oublock = p->signal->coublock; if (who == RUSAGE_CHILDREN) break; @@ -1754,6 +1591,8 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) r->ru_nivcsw += p->signal->nivcsw; r->ru_minflt += p->signal->min_flt; r->ru_majflt += p->signal->maj_flt; + r->ru_inblock += p->signal->inblock; + r->ru_oublock += p->signal->oublock; t = p; do { utime = cputime_add(utime, t->utime); @@ -1762,6 +1601,8 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) r->ru_nivcsw += t->nivcsw; r->ru_minflt += t->min_flt; r->ru_majflt += t->maj_flt; + r->ru_inblock += task_io_get_inblock(t); + r->ru_oublock += task_io_get_oublock(t); t = next_thread(t); } while (t != p); break; @@ -1770,8 +1611,9 @@ 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); } @@ -1817,14 +1659,14 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, error = put_user(current->pdeath_signal, (int __user *)arg2); break; case PR_GET_DUMPABLE: - error = current->mm->dumpable; + error = get_dumpable(current->mm); break; case PR_SET_DUMPABLE: - if (arg2 < 0 || arg2 > 2) { + if (arg2 < 0 || arg2 > 1) { error = -EINVAL; break; } - current->mm->dumpable = arg2; + set_dumpable(current->mm, arg2); break; case PR_SET_UNALIGN: @@ -1886,9 +1728,111 @@ 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; + + case PR_GET_SECCOMP: + error = prctl_get_seccomp(); + break; + case PR_SET_SECCOMP: + error = prctl_set_seccomp(arg2); + break; + default: error = -EINVAL; break; } return error; } + +asmlinkage long sys_getcpu(unsigned __user *cpup, unsigned __user *nodep, + struct getcpu_cache __user *cache) +{ + int err = 0; + int cpu = raw_smp_processor_id(); + if (cpup) + err |= put_user(cpu, cpup); + if (nodep) + err |= put_user(cpu_to_node(cpu), nodep); + if (cache) { + /* + * The cache is not needed for this implementation, + * but make sure user programs pass something + * valid. vsyscall implementations can instead make + * good use of the cache. Only use t0 and t1 because + * these are available in both 32bit and 64bit ABI (no + * need for a compat_getcpu). 32bit has enough + * padding + */ + unsigned long t0, t1; + get_user(t0, &cache->blob[0]); + get_user(t1, &cache->blob[1]); + t0++; + t1++; + put_user(t0, &cache->blob[0]); + put_user(t1, &cache->blob[1]); + } + return err ? -EFAULT : 0; +} + +char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff"; + +static void argv_cleanup(char **argv, char **envp) +{ + argv_free(argv); +} + +/** + * orderly_poweroff - Trigger an orderly system poweroff + * @force: force poweroff if command execution fails + * + * This may be called from any context to trigger a system shutdown. + * If the orderly shutdown fails, it will force an immediate shutdown. + */ +int orderly_poweroff(bool force) +{ + int argc; + char **argv = argv_split(GFP_ATOMIC, poweroff_cmd, &argc); + static char *envp[] = { + "HOME=/", + "PATH=/sbin:/bin:/usr/sbin:/usr/bin", + NULL + }; + int ret = -ENOMEM; + struct subprocess_info *info; + + if (argv == NULL) { + printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n", + __func__, poweroff_cmd); + goto out; + } + + info = call_usermodehelper_setup(argv[0], argv, envp); + if (info == NULL) { + argv_free(argv); + goto out; + } + + call_usermodehelper_setcleanup(info, argv_cleanup); + + ret = call_usermodehelper_exec(info, UMH_NO_WAIT); + + out: + if (ret && force) { + printk(KERN_WARNING "Failed to start orderly shutdown: " + "forcing the issue\n"); + + /* I guess this should try to kick off some daemon to + sync and poweroff asap. Or not even bother syncing + if we're doing an emergency shutdown? */ + emergency_sync(); + kernel_power_off(); + } + + return ret; +} +EXPORT_SYMBOL_GPL(orderly_poweroff);