X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fsys.c;h=51dbb55604e847991023697267d26c9216497ce7;hb=bb9e63e27117b469a151c61fb0045a8ec4cced5d;hp=5a9d6b075016546d0d72ec590a17cd77985a8947;hpb=71a2224d7d1cefc23a1ac80bba421cc069cc3257;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/sys.c b/kernel/sys.c index 5a9d6b0..51dbb55 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -4,7 +4,6 @@ * Copyright (C) 1991, 1992 Linus Torvalds */ -#include #include #include #include @@ -13,10 +12,13 @@ #include #include #include -#include #include #include +#include +#include +#include #include +#include #include #include #include @@ -26,9 +28,18 @@ #include #include #include +#include +#include +#include +#include +#include +#include +#include #include #include +#include +#include #include #include @@ -52,6 +63,18 @@ #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 +#ifndef GET_TSC_CTL +# define GET_TSC_CTL(a) (-EINVAL) +#endif +#ifndef SET_TSC_CTL +# define SET_TSC_CTL(a) (-EINVAL) +#endif /* * this is where the system-wide overflow UID and GID are defined, for @@ -82,149 +105,26 @@ 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. + * If set, this is used for preparing the system to power off. */ - -int 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); +void (*pm_power_off_prepare)(void); -/** - * 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. +/* + * set the priority of a task + * - the caller must hold the RCU read lock */ - -int unregister_reboot_notifier(struct notifier_block * nb) -{ - return notifier_chain_unregister(&reboot_notifier_list, nb); -} - -EXPORT_SYMBOL(unregister_reboot_notifier); - static int set_one_prio(struct task_struct *p, int niceval, int error) { + const struct cred *cred = current_cred(), *pcred = __task_cred(p); int no_nice; - if (p->uid != current->euid && - p->euid != current->euid && !capable(CAP_SYS_NICE)) { + if (pcred->uid != cred->euid && + pcred->euid != cred->euid && !capable(CAP_SYS_NICE)) { error = -EPERM; goto out; } @@ -244,13 +144,15 @@ out: return error; } -asmlinkage long sys_setpriority(int which, int who, int niceval) +SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) { struct task_struct *g, *p; struct user_struct *user; + const struct cred *cred = current_cred(); 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) */ @@ -263,32 +165,35 @@ 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_thread(pgrp, PIDTYPE_PGID, p) { error = set_one_prio(p, niceval, error); - } while_each_task_pid(who, PIDTYPE_PGID, p); + } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: - user = current->user; + user = (struct user_struct *) cred->user; if (!who) - who = current->uid; - else - if ((who != current->uid) && !(user = find_user(who))) - goto out_unlock; /* No processes for this user */ + who = cred->uid; + else if ((who != cred->uid) && + !(user = find_user(who))) + goto out_unlock; /* No processes for this user */ do_each_thread(g, p) - if (p->uid == who) + if (__task_cred(p)->uid == who) error = set_one_prio(p, niceval, error); while_each_thread(g, p); - if (who != current->uid) + if (who != cred->uid) free_uid(user); /* For find_user() */ break; } @@ -304,21 +209,24 @@ out: * has been offset by 20 (ie it returns 40..1 instead of -20..19) * to stay compatible. */ -asmlinkage long sys_getpriority(int which, int who) +SYSCALL_DEFINE2(getpriority, int, which, int, who) { struct task_struct *g, *p; struct user_struct *user; + const struct cred *cred = current_cred(); 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) @@ -326,30 +234,32 @@ 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_thread(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_thread(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: - user = current->user; + user = (struct user_struct *) cred->user; if (!who) - who = current->uid; - else - if ((who != current->uid) && !(user = find_user(who))) - goto out_unlock; /* No processes for this user */ + who = cred->uid; + else if ((who != cred->uid) && + !(user = find_user(who))) + goto out_unlock; /* No processes for this user */ do_each_thread(g, p) - if (p->uid == who) { + if (__task_cred(p)->uid == who) { niceval = 20 - task_nice(p); if (niceval > retval) retval = niceval; } while_each_thread(g, p); - if (who != current->uid) + if (who != cred->uid) free_uid(user); /* for find_user() */ break; } @@ -359,7 +269,85 @@ out_unlock: return retval; } +/** + * emergency_restart - reboot the system + * + * Without shutting down any hardware or taking any locks + * reboot the system. This is called when we know we are in + * trouble so this is our best effort to reboot. This is + * safe to call in interrupt context. + */ +void emergency_restart(void) +{ + machine_emergency_restart(); +} +EXPORT_SYMBOL_GPL(emergency_restart); + +void kernel_restart_prepare(char *cmd) +{ + blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd); + system_state = SYSTEM_RESTART; + device_shutdown(); + sysdev_shutdown(); +} + +/** + * kernel_restart - reboot the system + * @cmd: pointer to buffer containing command to execute for restart + * or %NULL + * + * Shutdown everything and perform a clean reboot. + * This is not safe to call in interrupt context. + */ +void kernel_restart(char *cmd) +{ + kernel_restart_prepare(cmd); + if (!cmd) + printk(KERN_EMERG "Restarting system.\n"); + else + printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd); + machine_restart(cmd); +} +EXPORT_SYMBOL_GPL(kernel_restart); +static void kernel_shutdown_prepare(enum system_states state) +{ + blocking_notifier_call_chain(&reboot_notifier_list, + (state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL); + system_state = state; + device_shutdown(); +} +/** + * kernel_halt - halt the system + * + * Shutdown everything and perform a clean system halt. + */ +void kernel_halt(void) +{ + kernel_shutdown_prepare(SYSTEM_HALT); + sysdev_shutdown(); + printk(KERN_EMERG "System halted.\n"); + machine_halt(); +} + +EXPORT_SYMBOL_GPL(kernel_halt); + +/** + * kernel_power_off - power_off the system + * + * Shutdown everything and perform a clean system power_off. + */ +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(); +} +EXPORT_SYMBOL_GPL(kernel_power_off); /* * Reboot system call: for obvious reasons only root may call it, * and even root needs to set up some magic numbers in the registers @@ -368,7 +356,8 @@ out_unlock: * * reboot doesn't sync: do that yourself before calling this. */ -asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user * arg) +SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, + void __user *, arg) { char buffer[256]; @@ -384,14 +373,16 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user magic2 != LINUX_REBOOT_MAGIC2C)) return -EINVAL; + /* Instead of trying to make the power_off code look like + * halt when pm_power_off is not set do it the easy way. + */ + if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off) + cmd = LINUX_REBOOT_CMD_HALT; + lock_kernel(); switch (cmd) { case LINUX_REBOOT_CMD_RESTART: - notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL); - system_state = SYSTEM_RESTART; - device_shutdown(); - printk(KERN_EMERG "Restarting system.\n"); - machine_restart(NULL); + kernel_restart(NULL); break; case LINUX_REBOOT_CMD_CAD_ON: @@ -403,21 +394,13 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user break; case LINUX_REBOOT_CMD_HALT: - notifier_call_chain(&reboot_notifier_list, SYS_HALT, NULL); - system_state = SYSTEM_HALT; - device_shutdown(); - printk(KERN_EMERG "System halted.\n"); - machine_halt(); + kernel_halt(); unlock_kernel(); do_exit(0); break; case LINUX_REBOOT_CMD_POWER_OFF: - notifier_call_chain(&reboot_notifier_list, SYS_POWER_OFF, NULL); - system_state = SYSTEM_POWER_OFF; - device_shutdown(); - printk(KERN_EMERG "Power down.\n"); - machine_power_off(); + kernel_power_off(); unlock_kernel(); do_exit(0); break; @@ -429,17 +412,23 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user } buffer[sizeof(buffer) - 1] = '\0'; - notifier_call_chain(&reboot_notifier_list, SYS_RESTART, buffer); - system_state = SYSTEM_RESTART; - device_shutdown(); - printk(KERN_EMERG "Restarting system with command '%s'.\n", buffer); - machine_restart(buffer); + kernel_restart(buffer); break; -#ifdef CONFIG_SOFTWARE_SUSPEND +#ifdef CONFIG_KEXEC + case LINUX_REBOOT_CMD_KEXEC: + { + int ret; + ret = kernel_kexec(); + unlock_kernel(); + return ret; + } +#endif + +#ifdef CONFIG_HIBERNATION case LINUX_REBOOT_CMD_SW_SUSPEND: { - int ret = software_suspend(); + int ret = hibernate(); unlock_kernel(); return ret; } @@ -453,10 +442,9 @@ 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) { - notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL); - machine_restart(NULL); + kernel_restart(NULL); } /* @@ -466,15 +454,14 @@ 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) @@ -493,49 +480,50 @@ void ctrl_alt_del(void) * SMP: There are not races, the GIDs are checked only by filesystem * operations (as far as semantic preservation is concerned). */ -asmlinkage long sys_setregid(gid_t rgid, gid_t egid) +SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid) { - int old_rgid = current->gid; - int old_egid = current->egid; - int new_rgid = old_rgid; - int new_egid = old_egid; + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + retval = security_task_setgid(rgid, egid, (gid_t)-1, LSM_SETID_RE); if (retval) - return retval; + goto error; + retval = -EPERM; if (rgid != (gid_t) -1) { - if ((old_rgid == rgid) || - (current->egid==rgid) || + if (old->gid == rgid || + old->egid == rgid || capable(CAP_SETGID)) - new_rgid = rgid; + new->gid = rgid; else - return -EPERM; + goto error; } if (egid != (gid_t) -1) { - if ((old_rgid == egid) || - (current->egid == egid) || - (current->sgid == egid) || + if (old->gid == egid || + old->egid == egid || + old->sgid == egid || capable(CAP_SETGID)) - new_egid = egid; - else { - return -EPERM; - } - } - if (new_egid != old_egid) - { - current->mm->dumpable = suid_dumpable; - smp_wmb(); + new->egid = egid; + else + goto error; } + if (rgid != (gid_t) -1 || - (egid != (gid_t) -1 && egid != old_rgid)) - current->sgid = new_egid; - current->fsgid = new_egid; - current->egid = new_egid; - current->gid = new_rgid; - key_fsgid_changed(current); - return 0; + (egid != (gid_t) -1 && egid != old->gid)) + new->sgid = new->egid; + new->fsgid = new->egid; + + return commit_creds(new); + +error: + abort_creds(new); + return retval; } /* @@ -543,63 +531,61 @@ asmlinkage long sys_setregid(gid_t rgid, gid_t egid) * * SMP: Same implicit races as above. */ -asmlinkage long sys_setgid(gid_t gid) +SYSCALL_DEFINE1(setgid, gid_t, gid) { - int old_egid = current->egid; + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + retval = security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_ID); if (retval) - return retval; + goto error; + retval = -EPERM; if (capable(CAP_SETGID)) - { - if(old_egid != gid) - { - current->mm->dumpable = 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; - smp_wmb(); - } - current->egid = current->fsgid = gid; - } + new->gid = new->egid = new->sgid = new->fsgid = gid; + else if (gid == old->gid || gid == old->sgid) + new->egid = new->fsgid = gid; else - return -EPERM; + goto error; - key_fsgid_changed(current); - return 0; + return commit_creds(new); + +error: + abort_creds(new); + return retval; } - -static int set_user(uid_t new_ruid, int dumpclear) + +/* + * change the user struct in a credentials set to match the new UID + */ +static int set_user(struct cred *new) { struct user_struct *new_user; - new_user = alloc_uid(new_ruid); + new_user = alloc_uid(current_user_ns(), new->uid); if (!new_user) return -EAGAIN; + if (!task_can_switch_user(new_user, current)) { + free_uid(new_user); + return -EINVAL; + } + if (atomic_read(&new_user->processes) >= current->signal->rlim[RLIMIT_NPROC].rlim_cur && - new_user != &root_user) { + new_user != INIT_USER) { free_uid(new_user); return -EAGAIN; } - switch_uid(new_user); - - if(dumpclear) - { - current->mm->dumpable = suid_dumpable; - smp_wmb(); - } - current->uid = new_ruid; + free_uid(new->user); + new->user = new_user; return 0; } @@ -618,56 +604,59 @@ static int set_user(uid_t new_ruid, int dumpclear) * 100% compatible with BSD. A program which uses just setuid() will be * 100% compatible with POSIX with saved IDs. */ -asmlinkage long sys_setreuid(uid_t ruid, uid_t euid) +SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) { - int old_ruid, old_euid, old_suid, new_ruid, new_euid; + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + retval = security_task_setuid(ruid, euid, (uid_t)-1, LSM_SETID_RE); if (retval) - return retval; - - new_ruid = old_ruid = current->uid; - new_euid = old_euid = current->euid; - old_suid = current->suid; + goto error; + retval = -EPERM; if (ruid != (uid_t) -1) { - new_ruid = ruid; - if ((old_ruid != ruid) && - (current->euid != ruid) && + new->uid = ruid; + if (old->uid != ruid && + old->euid != ruid && !capable(CAP_SETUID)) - return -EPERM; + goto error; } if (euid != (uid_t) -1) { - new_euid = euid; - if ((old_ruid != euid) && - (current->euid != euid) && - (current->suid != euid) && + new->euid = euid; + if (old->uid != euid && + old->euid != euid && + old->suid != euid && !capable(CAP_SETUID)) - return -EPERM; + goto error; } - 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; - smp_wmb(); + if (new->uid != old->uid) { + retval = set_user(new); + if (retval < 0) + goto error; } - current->fsuid = current->euid = new_euid; if (ruid != (uid_t) -1 || - (euid != (uid_t) -1 && euid != old_ruid)) - current->suid = current->euid; - current->fsuid = current->euid; + (euid != (uid_t) -1 && euid != old->uid)) + new->suid = new->euid; + new->fsuid = new->euid; - key_fsuid_changed(current); - - return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RE); -} + retval = security_task_fix_setuid(new, old, LSM_SETID_RE); + if (retval < 0) + goto error; + return commit_creds(new); +error: + abort_creds(new); + return retval; +} /* * setuid() is implemented like SysV with SAVED_IDS @@ -680,38 +669,44 @@ asmlinkage long sys_setreuid(uid_t ruid, uid_t euid) * will allow a root program to temporarily drop privileges and be able to * regain them by swapping the real and effective uid. */ -asmlinkage long sys_setuid(uid_t uid) +SYSCALL_DEFINE1(setuid, uid_t, uid) { - int old_euid = current->euid; - int old_ruid, old_suid, new_ruid, new_suid; + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + retval = security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_ID); if (retval) - return retval; + goto error; - old_ruid = new_ruid = current->uid; - old_suid = current->suid; - new_suid = old_suid; - + retval = -EPERM; if (capable(CAP_SETUID)) { - if (uid != old_ruid && set_user(uid, old_euid != uid) < 0) - return -EAGAIN; - new_suid = uid; - } else if ((uid != current->uid) && (uid != new_suid)) - return -EPERM; - - if (old_euid != uid) - { - current->mm->dumpable = suid_dumpable; - smp_wmb(); + new->suid = new->uid = uid; + if (uid != old->uid) { + retval = set_user(new); + if (retval < 0) + goto error; + } + } else if (uid != old->uid && uid != new->suid) { + goto error; } - current->fsuid = current->euid = uid; - current->suid = new_suid; - key_fsuid_changed(current); + new->fsuid = new->euid = uid; - return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_ID); + retval = security_task_fix_setuid(new, old, LSM_SETID_ID); + if (retval < 0) + goto error; + + return commit_creds(new); + +error: + abort_creds(new); + return retval; } @@ -719,56 +714,67 @@ asmlinkage long sys_setuid(uid_t uid) * This function implements a generic ability to update ruid, euid, * and suid. This allows you to implement the 4.4 compatible seteuid(). */ -asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) +SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) { - int old_ruid = current->uid; - int old_euid = current->euid; - int old_suid = current->suid; + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + retval = security_task_setuid(ruid, euid, suid, LSM_SETID_RES); if (retval) - return retval; + goto error; + old = current_cred(); + retval = -EPERM; if (!capable(CAP_SETUID)) { - if ((ruid != (uid_t) -1) && (ruid != current->uid) && - (ruid != current->euid) && (ruid != current->suid)) - return -EPERM; - if ((euid != (uid_t) -1) && (euid != current->uid) && - (euid != current->euid) && (euid != current->suid)) - return -EPERM; - if ((suid != (uid_t) -1) && (suid != current->uid) && - (suid != current->euid) && (suid != current->suid)) - return -EPERM; + if (ruid != (uid_t) -1 && ruid != old->uid && + ruid != old->euid && ruid != old->suid) + goto error; + if (euid != (uid_t) -1 && euid != old->uid && + euid != old->euid && euid != old->suid) + goto error; + if (suid != (uid_t) -1 && suid != old->uid && + suid != old->euid && suid != old->suid) + goto error; } + if (ruid != (uid_t) -1) { - if (ruid != current->uid && set_user(ruid, euid != current->euid) < 0) - return -EAGAIN; - } - if (euid != (uid_t) -1) { - if (euid != current->euid) - { - current->mm->dumpable = suid_dumpable; - smp_wmb(); + new->uid = ruid; + if (ruid != old->uid) { + retval = set_user(new); + if (retval < 0) + goto error; } - current->euid = euid; } - current->fsuid = current->euid; + if (euid != (uid_t) -1) + new->euid = euid; if (suid != (uid_t) -1) - current->suid = suid; + new->suid = suid; + new->fsuid = new->euid; + + retval = security_task_fix_setuid(new, old, LSM_SETID_RES); + if (retval < 0) + goto error; - key_fsuid_changed(current); + return commit_creds(new); - return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RES); +error: + abort_creds(new); + return retval; } -asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid) +SYSCALL_DEFINE3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid) { + const struct cred *cred = current_cred(); int retval; - if (!(retval = put_user(current->uid, ruid)) && - !(retval = put_user(current->euid, euid))) - retval = put_user(current->suid, suid); + if (!(retval = put_user(cred->uid, ruid)) && + !(retval = put_user(cred->euid, euid))) + retval = put_user(cred->suid, suid); return retval; } @@ -776,50 +782,57 @@ asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __us /* * Same as above, but for rgid, egid, sgid. */ -asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid) +SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid) { + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + retval = security_task_setgid(rgid, egid, sgid, LSM_SETID_RES); if (retval) - return retval; + goto error; + retval = -EPERM; if (!capable(CAP_SETGID)) { - if ((rgid != (gid_t) -1) && (rgid != current->gid) && - (rgid != current->egid) && (rgid != current->sgid)) - return -EPERM; - if ((egid != (gid_t) -1) && (egid != current->gid) && - (egid != current->egid) && (egid != current->sgid)) - return -EPERM; - if ((sgid != (gid_t) -1) && (sgid != current->gid) && - (sgid != current->egid) && (sgid != current->sgid)) - return -EPERM; - } - if (egid != (gid_t) -1) { - if (egid != current->egid) - { - current->mm->dumpable = suid_dumpable; - smp_wmb(); - } - current->egid = egid; + if (rgid != (gid_t) -1 && rgid != old->gid && + rgid != old->egid && rgid != old->sgid) + goto error; + if (egid != (gid_t) -1 && egid != old->gid && + egid != old->egid && egid != old->sgid) + goto error; + if (sgid != (gid_t) -1 && sgid != old->gid && + sgid != old->egid && sgid != old->sgid) + goto error; } - current->fsgid = current->egid; + if (rgid != (gid_t) -1) - current->gid = rgid; + new->gid = rgid; + if (egid != (gid_t) -1) + new->egid = egid; if (sgid != (gid_t) -1) - current->sgid = sgid; + new->sgid = sgid; + new->fsgid = new->egid; - key_fsgid_changed(current); - return 0; + return commit_creds(new); + +error: + abort_creds(new); + return retval; } -asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid) +SYSCALL_DEFINE3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid) { + const struct cred *cred = current_cred(); int retval; - if (!(retval = put_user(current->gid, rgid)) && - !(retval = put_user(current->egid, egid))) - retval = put_user(current->sgid, sgid); + if (!(retval = put_user(cred->gid, rgid)) && + !(retval = put_user(cred->egid, egid))) + retval = put_user(cred->sgid, sgid); return retval; } @@ -831,139 +844,102 @@ asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __us * whatever uid it wants to). It normally shadows "euid", except when * explicitly set by setfsuid() or for access.. */ -asmlinkage long sys_setfsuid(uid_t uid) +SYSCALL_DEFINE1(setfsuid, uid_t, uid) { - int old_fsuid; - - old_fsuid = current->fsuid; - if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS)) - return old_fsuid; - - 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; - smp_wmb(); + const struct cred *old; + struct cred *new; + uid_t old_fsuid; + + new = prepare_creds(); + if (!new) + return current_fsuid(); + old = current_cred(); + old_fsuid = old->fsuid; + + if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS) < 0) + goto error; + + if (uid == old->uid || uid == old->euid || + uid == old->suid || uid == old->fsuid || + capable(CAP_SETUID)) { + if (uid != old_fsuid) { + new->fsuid = uid; + if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0) + goto change_okay; } - current->fsuid = uid; } - key_fsuid_changed(current); - - security_task_post_setuid(old_fsuid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS); +error: + abort_creds(new); + return old_fsuid; +change_okay: + commit_creds(new); return old_fsuid; } /* - * Samma på svenska.. + * Samma pÃ¥ svenska.. */ -asmlinkage long sys_setfsgid(gid_t gid) +SYSCALL_DEFINE1(setfsgid, gid_t, gid) { - int old_fsgid; + const struct cred *old; + struct cred *new; + gid_t old_fsgid; - old_fsgid = current->fsgid; - if (security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_FS)) - return old_fsgid; + new = prepare_creds(); + if (!new) + return current_fsgid(); + old = current_cred(); + old_fsgid = old->fsgid; - 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; - smp_wmb(); + if (security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_FS)) + goto error; + + if (gid == old->gid || gid == old->egid || + gid == old->sgid || gid == old->fsgid || + capable(CAP_SETGID)) { + if (gid != old_fsgid) { + new->fsgid = gid; + goto change_okay; } - current->fsgid = gid; - key_fsgid_changed(current); } + +error: + abort_creds(new); + return old_fsgid; + +change_okay: + commit_creds(new); return old_fsgid; } -asmlinkage long sys_times(struct tms __user * tbuf) +void do_sys_times(struct tms *tms) +{ + struct task_cputime cputime; + cputime_t cutime, cstime; + + thread_group_cputime(current, &cputime); + spin_lock_irq(¤t->sighand->siglock); + cutime = current->signal->cutime; + cstime = current->signal->cstime; + spin_unlock_irq(¤t->sighand->siglock); + tms->tms_utime = cputime_to_clock_t(cputime.utime); + tms->tms_stime = cputime_to_clock_t(cputime.stime); + tms->tms_cutime = cputime_to_clock_t(cutime); + tms->tms_cstime = cputime_to_clock_t(cstime); +} + +SYSCALL_DEFINE1(times, struct tms __user *, tbuf) { - /* - * In the SMP world we might just be unlucky and have one of - * the times increment as we use it. Since the value is an - * atomically safe type this is just fine. Conceptually its - * as if the syscall took an instant longer to occur. - */ if (tbuf) { struct tms tmp; - 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 - { - - /* Process with multiple threads */ - struct task_struct *tsk = current; - struct task_struct *t; - 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); - tmp.tms_cstime = cputime_to_clock_t(cstime); + do_sys_times(&tmp); if (copy_to_user(tbuf, &tmp, sizeof(struct tms))) return -EFAULT; } + force_successful_syscall_return(); return (long) jiffies_64_to_clock_t(get_jiffies_64()); } @@ -979,14 +955,15 @@ 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) +SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) { struct task_struct *p; - int err = -EINVAL; + struct task_struct *group_leader = current->group_leader; + struct pid *pgrp; + int err; if (!pid) - pid = current->pid; + pid = task_pid_vnr(group_leader); if (!pgid) pgid = pid; if (pgid < 0) @@ -998,7 +975,7 @@ asmlinkage long sys_setpgid(pid_t pid, pid_t pgid) write_lock_irq(&tasklist_lock); err = -ESRCH; - p = find_task_by_pid(pid); + p = find_task_by_vpid(pid); if (!p) goto out; @@ -1006,16 +983,16 @@ asmlinkage long sys_setpgid(pid_t pid, pid_t pgid) if (!thread_group_leader(p)) goto out; - if (p->parent == current || p->real_parent == current) { + if (same_thread_group(p->real_parent, group_leader)) { err = -EPERM; - if (p->signal->session != current->signal->session) + if (task_session(p) != task_session(group_leader)) goto out; err = -EACCES; if (p->did_exec) goto out; } else { err = -ESRCH; - if (p != current) + if (p != group_leader) goto out; } @@ -1023,26 +1000,22 @@ asmlinkage long sys_setpgid(pid_t pid, pid_t pgid) if (p->signal->leader) goto out; + pgrp = task_pid(p); if (pgid != pid) { - struct task_struct *p; + struct task_struct *g; - do_each_task_pid(pgid, PIDTYPE_PGID, p) { - if (p->signal->session == current->signal->session) - goto ok_pgid; - } while_each_task_pid(pgid, PIDTYPE_PGID, p); - goto out; + pgrp = find_vpid(pgid); + g = pid_task(pgrp, PIDTYPE_PGID); + 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) { - detach_pid(p, PIDTYPE_PGID); - p->signal->pgrp = pgid; - attach_pid(p, PIDTYPE_PGID, pgid); - } + if (task_pgrp(p) != pgrp) + change_pid(p, PIDTYPE_PGID, pgrp); err = 0; out: @@ -1051,83 +1024,97 @@ out: return err; } -asmlinkage long sys_getpgid(pid_t pid) +SYSCALL_DEFINE1(getpgid, pid_t, pid) { - if (!pid) { - return process_group(current); - } else { - int retval; - struct task_struct *p; - - read_lock(&tasklist_lock); - p = find_task_by_pid(pid); + struct task_struct *p; + struct pid *grp; + int retval; + rcu_read_lock(); + if (!pid) + grp = task_pgrp(current); + else { retval = -ESRCH; - if (p) { - retval = security_task_getpgid(p); - if (!retval) - retval = process_group(p); - } - read_unlock(&tasklist_lock); - return retval; + p = find_task_by_vpid(pid); + if (!p) + goto out; + grp = task_pgrp(p); + if (!grp) + goto out; + + retval = security_task_getpgid(p); + if (retval) + goto out; } + retval = pid_vnr(grp); +out: + rcu_read_unlock(); + return retval; } #ifdef __ARCH_WANT_SYS_GETPGRP -asmlinkage long sys_getpgrp(void) +SYSCALL_DEFINE0(getpgrp) { - /* SMP - assuming writes are word atomic this is fine */ - return process_group(current); + return sys_getpgid(0); } #endif -asmlinkage long sys_getsid(pid_t pid) +SYSCALL_DEFINE1(getsid, pid_t, pid) { - if (!pid) { - return current->signal->session; - } else { - int retval; - struct task_struct *p; - - read_lock(&tasklist_lock); - p = find_task_by_pid(pid); + struct task_struct *p; + struct pid *sid; + int retval; + rcu_read_lock(); + if (!pid) + sid = task_session(current); + else { retval = -ESRCH; - if(p) { - retval = security_task_getsid(p); - if (!retval) - retval = p->signal->session; - } - read_unlock(&tasklist_lock); - return retval; + p = find_task_by_vpid(pid); + if (!p) + goto out; + sid = task_session(p); + if (!sid) + goto out; + + retval = security_task_getsid(p); + if (retval) + goto out; } + retval = pid_vnr(sid); +out: + rcu_read_unlock(); + return retval; } -asmlinkage long sys_setsid(void) +SYSCALL_DEFINE0(setsid) { - struct pid *pid; + struct task_struct *group_leader = current->group_leader; + struct pid *sid = task_pid(group_leader); + pid_t session = pid_vnr(sid); int err = -EPERM; - if (!thread_group_leader(current)) - return -EINVAL; - - down(&tty_sem); write_lock_irq(&tasklist_lock); + /* Fail if I am already a session leader */ + if (group_leader->signal->leader) + goto out; - pid = find_pid(PIDTYPE_PGID, current->pid); - if (pid) + /* Fail if a process group id already exists that equals the + * proposed session id. + */ + if (pid_task(sid, PIDTYPE_PGID)) goto out; - current->signal->leader = 1; - __set_special_pids(current->pid, current->pid); - current->signal->tty = NULL; - current->signal->tty_old_pgrp = 0; - err = process_group(current); + group_leader->signal->leader = 1; + __set_special_pids(sid); + + proc_clear_tty(group_leader); + + err = session; out: write_unlock_irq(&tasklist_lock); - up(&tty_sem); return err; } @@ -1154,9 +1141,9 @@ 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); @@ -1191,19 +1178,19 @@ EXPORT_SYMBOL(groups_free); /* export the group_info to a user-space array */ static int groups_to_user(gid_t __user *grouplist, - struct group_info *group_info) + const struct group_info *group_info) { int i; - int count = group_info->ngroups; + unsigned int count = group_info->ngroups; for (i = 0; i < group_info->nblocks; i++) { - int cp_count = min(NGROUPS_PER_BLOCK, count); - int off = i * NGROUPS_PER_BLOCK; - int len = cp_count * sizeof(*grouplist); + unsigned int cp_count = min(NGROUPS_PER_BLOCK, count); + unsigned int len = cp_count * sizeof(*grouplist); - if (copy_to_user(grouplist+off, group_info->blocks[i], len)) + if (copy_to_user(grouplist, group_info->blocks[i], len)) return -EFAULT; + grouplist += NGROUPS_PER_BLOCK; count -= cp_count; } return 0; @@ -1212,18 +1199,18 @@ 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; + unsigned int count = group_info->ngroups; for (i = 0; i < group_info->nblocks; i++) { - int cp_count = min(NGROUPS_PER_BLOCK, count); - int off = i * NGROUPS_PER_BLOCK; - int len = cp_count * sizeof(*grouplist); + unsigned int cp_count = min(NGROUPS_PER_BLOCK, count); + unsigned int len = cp_count * sizeof(*grouplist); - if (copy_from_user(group_info->blocks[i], grouplist+off, len)) + if (copy_from_user(group_info->blocks[i], grouplist, len)) return -EFAULT; + grouplist += NGROUPS_PER_BLOCK; count -= cp_count; } return 0; @@ -1259,9 +1246,9 @@ static void groups_sort(struct group_info *group_info) } /* a simple bsearch */ -static int groups_search(struct group_info *group_info, gid_t grp) +int groups_search(const struct group_info *group_info, gid_t grp) { - int left, right; + unsigned int left, right; if (!group_info) return 0; @@ -1269,7 +1256,7 @@ static 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; @@ -1281,58 +1268,79 @@ static int groups_search(struct group_info *group_info, gid_t grp) return 0; } -/* validate and set current->group_info */ -int set_current_groups(struct group_info *group_info) +/** + * set_groups - Change a group subscription in a set of credentials + * @new: The newly prepared set of credentials to alter + * @group_info: The group list to install + * + * Validate a group subscription and, if valid, insert it into a set + * of credentials. + */ +int set_groups(struct cred *new, struct group_info *group_info) { int retval; - struct group_info *old_info; retval = security_task_setgroups(group_info); if (retval) return retval; + put_group_info(new->group_info); groups_sort(group_info); get_group_info(group_info); + new->group_info = group_info; + return 0; +} - task_lock(current); - old_info = current->group_info; - current->group_info = group_info; - task_unlock(current); +EXPORT_SYMBOL(set_groups); - put_group_info(old_info); +/** + * set_current_groups - Change current's group subscription + * @group_info: The group list to impose + * + * Validate a group subscription and, if valid, impose it upon current's task + * security record. + */ +int set_current_groups(struct group_info *group_info) +{ + struct cred *new; + int ret; - return 0; + new = prepare_creds(); + if (!new) + return -ENOMEM; + + ret = set_groups(new, group_info); + if (ret < 0) { + abort_creds(new); + return ret; + } + + return commit_creds(new); } EXPORT_SYMBOL(set_current_groups); -asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist) +SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist) { - int i = 0; - - /* - * SMP: Nobody else can change our grouplist. Thus we are - * safe. - */ + const struct cred *cred = current_cred(); + int i; if (gidsetsize < 0) return -EINVAL; /* no need to grab task_lock here; it cannot change */ - get_group_info(current->group_info); - i = current->group_info->ngroups; + i = cred->group_info->ngroups; if (gidsetsize) { if (i > gidsetsize) { i = -EINVAL; goto out; } - if (groups_to_user(grouplist, current->group_info)) { + if (groups_to_user(grouplist, cred->group_info)) { i = -EFAULT; goto out; } } out: - put_group_info(current->group_info); return i; } @@ -1341,7 +1349,7 @@ out: * without another task interfering. */ -asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist) +SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist) { struct group_info *group_info; int retval; @@ -1371,12 +1379,11 @@ asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist) */ int in_group_p(gid_t grp) { + const struct cred *cred = current_cred(); int retval = 1; - if (grp != current->fsgid) { - get_group_info(current->group_info); - retval = groups_search(current->group_info, grp); - put_group_info(current->group_info); - } + + if (grp != cred->fsgid) + retval = groups_search(cred->group_info, grp); return retval; } @@ -1384,12 +1391,11 @@ EXPORT_SYMBOL(in_group_p); int in_egroup_p(gid_t grp) { + const struct cred *cred = current_cred(); int retval = 1; - if (grp != current->egid) { - get_group_info(current->group_info); - retval = groups_search(current->group_info, grp); - put_group_info(current->group_info); - } + + if (grp != cred->egid) + retval = groups_search(cred->group_info, grp); return retval; } @@ -1397,20 +1403,18 @@ EXPORT_SYMBOL(in_egroup_p); DECLARE_RWSEM(uts_sem); -EXPORT_SYMBOL(uts_sem); - -asmlinkage long sys_newuname(struct new_utsname __user * name) +SYSCALL_DEFINE1(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; } -asmlinkage long sys_sethostname(char __user *name, int len) +SYSCALL_DEFINE2(sethostname, char __user *, name, int, len) { int errno; char tmp[__NEW_UTS_LEN]; @@ -1422,8 +1426,10 @@ 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; + struct new_utsname *u = utsname(); + + memcpy(u->nodename, tmp, len); + memset(u->nodename + len, 0, sizeof(u->nodename) - len); errno = 0; } up_write(&uts_sem); @@ -1432,18 +1438,20 @@ asmlinkage long sys_sethostname(char __user *name, int len) #ifdef __ARCH_WANT_SYS_GETHOSTNAME -asmlinkage long sys_gethostname(char __user *name, int len) +SYSCALL_DEFINE2(gethostname, char __user *, name, int, len) { int i, errno; + struct new_utsname *u; if (len < 0) return -EINVAL; down_read(&uts_sem); - i = 1 + strlen(system_utsname.nodename); + u = utsname(); + i = 1 + strlen(u->nodename); if (i > len) i = len; errno = 0; - if (copy_to_user(name, system_utsname.nodename, i)) + if (copy_to_user(name, u->nodename, i)) errno = -EFAULT; up_read(&uts_sem); return errno; @@ -1455,7 +1463,7 @@ asmlinkage long sys_gethostname(char __user *name, int len) * Only setdomainname; getdomainname can be implemented by calling * uname() */ -asmlinkage long sys_setdomainname(char __user *name, int len) +SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len) { int errno; char tmp[__NEW_UTS_LEN]; @@ -1468,15 +1476,17 @@ 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; + struct new_utsname *u = utsname(); + + memcpy(u->domainname, tmp, len); + memset(u->domainname + len, 0, sizeof(u->domainname) - len); errno = 0; } up_write(&uts_sem); return errno; } -asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim) +SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim) { if (resource >= RLIM_NLIMITS) return -EINVAL; @@ -1495,7 +1505,8 @@ asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim) * Back compatibility for getrlimit. Needed for some apps. */ -asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim) +SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, + struct rlimit __user *, rlim) { struct rlimit x; if (resource >= RLIM_NLIMITS) @@ -1504,54 +1515,65 @@ 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; } #endif -asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim) +SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim) { struct rlimit new_rlim, *old_rlim; int retval; if (resource >= RLIM_NLIMITS) return -EINVAL; - if(copy_from_user(&new_rlim, rlim, sizeof(*rlim))) + if (copy_from_user(&new_rlim, rlim, sizeof(*rlim))) return -EFAULT; - if (new_rlim.rlim_cur > new_rlim.rlim_max) - return -EINVAL; + if (new_rlim.rlim_cur > new_rlim.rlim_max) + return -EINVAL; old_rlim = current->signal->rlim + resource; if ((new_rlim.rlim_max > old_rlim->rlim_max) && !capable(CAP_SYS_RESOURCE)) return -EPERM; - if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > NR_OPEN) - return -EPERM; + if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open) + return -EPERM; retval = security_task_setrlimit(resource, &new_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); - if (resource == RLIMIT_CPU && new_rlim.rlim_cur != RLIM_INFINITY && - (cputime_eq(current->signal->it_prof_expires, cputime_zero) || - new_rlim.rlim_cur <= cputime_to_secs( - current->signal->it_prof_expires))) { - cputime_t cputime = secs_to_cputime(new_rlim.rlim_cur); - read_lock(&tasklist_lock); - spin_lock_irq(¤t->sighand->siglock); - set_process_cpu_timer(current, CPUCLOCK_PROF, - &cputime, NULL); - spin_unlock_irq(¤t->sighand->siglock); - read_unlock(&tasklist_lock); - } + if (resource != RLIMIT_CPU) + goto out; + /* + * RLIMIT_CPU handling. Note that the kernel fails to return an error + * code if it rejected the user's attempt to set RLIMIT_CPU. This is a + * very long-standing error, and fixing it now risks breakage of + * applications, so we live with it + */ + if (new_rlim.rlim_cur == RLIM_INFINITY) + goto out; + + update_rlimit_cpu(new_rlim.rlim_cur); +out: return 0; } @@ -1563,9 +1585,6 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim) * a lot simpler! (Which we're not doing right now because we're not * measuring them yet). * - * This expects to be called with tasklist_lock read-locked or better, - * and the siglock not locked. It may momentarily take the siglock. - * * When sampling multiple threads for RUSAGE_SELF, under SMP we might have * races with threads incrementing their own counters. But since word * reads are atomic, we either get new values or old values and we don't @@ -1573,188 +1592,297 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim) * the c* fields from p->signal from races with exit.c updating those * 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. + * + * 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. + * */ +static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r) +{ + r->ru_nvcsw += t->nvcsw; + 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); +} + static void k_getrusage(struct task_struct *p, int who, struct rusage *r) { struct task_struct *t; unsigned long flags; cputime_t utime, stime; + struct task_cputime cputime; memset((char *) r, 0, sizeof *r); + utime = stime = cputime_zero; - if (unlikely(!p->signal)) + if (who == RUSAGE_THREAD) { + utime = task_utime(current); + stime = task_stime(current); + accumulate_thread_rusage(p, r); + goto out; + } + + if (!lock_task_sighand(p, &flags)) 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); - cputime_to_timeval(utime, &r->ru_utime); - cputime_to_timeval(stime, &r->ru_stime); - break; + r->ru_inblock = p->signal->cinblock; + r->ru_oublock = p->signal->coublock; + + if (who == RUSAGE_CHILDREN) + break; + case RUSAGE_SELF: - spin_lock_irqsave(&p->sighand->siglock, flags); - utime = stime = cputime_zero; - goto sum_group; - case RUSAGE_BOTH: - 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; - sum_group: - utime = cputime_add(utime, p->signal->utime); - stime = cputime_add(stime, p->signal->stime); + thread_group_cputime(p, &cputime); + utime = cputime_add(utime, cputime.utime); + stime = cputime_add(stime, cputime.stime); r->ru_nvcsw += p->signal->nvcsw; 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); - stime = cputime_add(stime, t->stime); - r->ru_nvcsw += t->nvcsw; - r->ru_nivcsw += t->nivcsw; - r->ru_minflt += t->min_flt; - r->ru_majflt += t->maj_flt; + accumulate_thread_rusage(t, r); t = next_thread(t); } while (t != p); - spin_unlock_irqrestore(&p->sighand->siglock, flags); - cputime_to_timeval(utime, &r->ru_utime); - cputime_to_timeval(stime, &r->ru_stime); break; + default: BUG(); } + unlock_task_sighand(p, &flags); + +out: + cputime_to_timeval(utime, &r->ru_utime); + cputime_to_timeval(stime, &r->ru_stime); } int getrusage(struct task_struct *p, int who, struct rusage __user *ru) { struct rusage r; - read_lock(&tasklist_lock); k_getrusage(p, who, &r); - read_unlock(&tasklist_lock); return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0; } -asmlinkage long sys_getrusage(int who, struct rusage __user *ru) +SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) { - if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN) + if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && + who != RUSAGE_THREAD) return -EINVAL; return getrusage(current, who, ru); } -asmlinkage long sys_umask(int mask) +SYSCALL_DEFINE1(umask, int, mask) { mask = xchg(¤t->fs->umask, mask & S_IRWXUGO); return mask; } - -asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, - unsigned long arg4, unsigned long arg5) + +SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, + unsigned long, arg4, unsigned long, arg5) { + struct task_struct *me = current; + unsigned char comm[sizeof(me->comm)]; long error; - int sig; error = security_task_prctl(option, arg2, arg3, arg4, arg5); - if (error) + if (error != -ENOSYS) return error; + error = 0; switch (option) { case PR_SET_PDEATHSIG: - sig = arg2; - if (!valid_signal(sig)) { + if (!valid_signal(arg2)) { error = -EINVAL; break; } - current->pdeath_signal = sig; + me->pdeath_signal = arg2; + error = 0; break; case PR_GET_PDEATHSIG: - error = put_user(current->pdeath_signal, (int __user *)arg2); + error = put_user(me->pdeath_signal, (int __user *)arg2); break; case PR_GET_DUMPABLE: - if (current->mm->dumpable) - error = 1; + error = get_dumpable(me->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(me->mm, arg2); + error = 0; break; case PR_SET_UNALIGN: - error = SET_UNALIGN_CTL(current, arg2); + error = SET_UNALIGN_CTL(me, arg2); break; case PR_GET_UNALIGN: - error = GET_UNALIGN_CTL(current, arg2); + error = GET_UNALIGN_CTL(me, arg2); break; case PR_SET_FPEMU: - error = SET_FPEMU_CTL(current, arg2); + error = SET_FPEMU_CTL(me, arg2); break; case PR_GET_FPEMU: - error = GET_FPEMU_CTL(current, arg2); + error = GET_FPEMU_CTL(me, arg2); break; case PR_SET_FPEXC: - error = SET_FPEXC_CTL(current, arg2); + error = SET_FPEXC_CTL(me, arg2); break; case PR_GET_FPEXC: - error = GET_FPEXC_CTL(current, arg2); + error = GET_FPEXC_CTL(me, arg2); break; case PR_GET_TIMING: error = PR_TIMING_STATISTICAL; break; case PR_SET_TIMING: - if (arg2 == PR_TIMING_STATISTICAL) - error = 0; - else - error = -EINVAL; - break; - - case PR_GET_KEEPCAPS: - if (current->keep_capabilities) - error = 1; - break; - case PR_SET_KEEPCAPS: - if (arg2 != 0 && arg2 != 1) { + if (arg2 != PR_TIMING_STATISTICAL) error = -EINVAL; - break; - } - current->keep_capabilities = arg2; + else + error = 0; break; - case PR_SET_NAME: { - struct task_struct *me = current; - unsigned char ncomm[sizeof(me->comm)]; - ncomm[sizeof(me->comm)-1] = 0; - if (strncpy_from_user(ncomm, (char __user *)arg2, - sizeof(me->comm)-1) < 0) + case PR_SET_NAME: + comm[sizeof(me->comm)-1] = 0; + if (strncpy_from_user(comm, (char __user *)arg2, + sizeof(me->comm) - 1) < 0) return -EFAULT; - set_task_comm(me, ncomm); + set_task_comm(me, comm); return 0; - } - case PR_GET_NAME: { - struct task_struct *me = current; - unsigned char tcomm[sizeof(me->comm)]; - - get_task_comm(tcomm, me); - if (copy_to_user((char __user *)arg2, tcomm, sizeof(tcomm))) + case PR_GET_NAME: + get_task_comm(comm, me); + if (copy_to_user((char __user *)arg2, comm, + sizeof(comm))) return -EFAULT; return 0; - } + case PR_GET_ENDIAN: + error = GET_ENDIAN(me, arg2); + break; + case PR_SET_ENDIAN: + error = SET_ENDIAN(me, arg2); + break; + + case PR_GET_SECCOMP: + error = prctl_get_seccomp(); + break; + case PR_SET_SECCOMP: + error = prctl_set_seccomp(arg2); + break; + case PR_GET_TSC: + error = GET_TSC_CTL(arg2); + break; + case PR_SET_TSC: + error = SET_TSC_CTL(arg2); + break; + case PR_GET_TIMERSLACK: + error = current->timer_slack_ns; + break; + case PR_SET_TIMERSLACK: + if (arg2 <= 0) + current->timer_slack_ns = + current->default_timer_slack_ns; + else + current->timer_slack_ns = arg2; + error = 0; + break; default: error = -EINVAL; break; } return error; } + +SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep, + struct getcpu_cache __user *, unused) +{ + 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); + 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, GFP_ATOMIC); + 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);