*/
#include <linux/config.h>
-#include <linux/compat.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/utsname.h>
#include <linux/init.h>
#include <linux/highuid.h>
#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/kexec.h>
#include <linux/workqueue.h>
+#include <linux/capability.h>
#include <linux/device.h>
+#include <linux/key.h>
#include <linux/times.h>
+#include <linux/posix-timers.h>
#include <linux/security.h>
#include <linux/dcookies.h>
#include <linux/suspend.h>
-#include <linux/ckrm.h>
+#include <linux/tty.h>
+#include <linux/signal.h>
+#include <linux/cn_proc.h>
#include <linux/vs_base.h>
#include <linux/vs_cvirt.h>
+#include <linux/compat.h>
+#include <linux/syscalls.h>
+#include <linux/kprobes.h>
+
#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/unistd.h>
*/
static struct notifier_block *reboot_notifier_list;
-rwlock_t notifier_lock = RW_LOCK_UNLOCKED;
+static DEFINE_RWLOCK(notifier_lock);
/**
* notifier_chain_register - Add notifier to a notifier chain
* of the last notifier function called.
*/
-int notifier_call_chain(struct notifier_block **n, unsigned long val, void *v)
+int __kprobes notifier_call_chain(struct notifier_block **n, unsigned long val, void *v)
{
int ret=NOTIFY_DONE;
struct notifier_block *nb = *n;
EXPORT_SYMBOL(unregister_reboot_notifier);
-asmlinkage long sys_ni_syscall(void)
+#ifndef CONFIG_SECURITY
+int capable(int cap)
{
- return -ENOSYS;
+ if (vx_check_bit(VXC_CAP_MASK, cap) && !vx_mcaps(1L << cap))
+ return 0;
+ if (cap_raised(current->cap_effective, cap)) {
+ current->flags |= PF_SUPERPRIV;
+ return 1;
+ }
+ return 0;
}
-
-cond_syscall(sys_nfsservctl)
-cond_syscall(sys_quotactl)
-cond_syscall(sys_acct)
-cond_syscall(sys_lookup_dcookie)
-cond_syscall(sys_swapon)
-cond_syscall(sys_swapoff)
-cond_syscall(sys_init_module)
-cond_syscall(sys_delete_module)
-cond_syscall(sys_socketpair)
-cond_syscall(sys_bind)
-cond_syscall(sys_listen)
-cond_syscall(sys_accept)
-cond_syscall(sys_connect)
-cond_syscall(sys_getsockname)
-cond_syscall(sys_getpeername)
-cond_syscall(sys_sendto)
-cond_syscall(sys_send)
-cond_syscall(sys_recvfrom)
-cond_syscall(sys_recv)
-cond_syscall(sys_socket)
-cond_syscall(sys_setsockopt)
-cond_syscall(sys_getsockopt)
-cond_syscall(sys_shutdown)
-cond_syscall(sys_sendmsg)
-cond_syscall(sys_recvmsg)
-cond_syscall(sys_socketcall)
-cond_syscall(sys_futex)
-cond_syscall(compat_sys_futex)
-cond_syscall(sys_epoll_create)
-cond_syscall(sys_epoll_ctl)
-cond_syscall(sys_epoll_wait)
-cond_syscall(sys_semget)
-cond_syscall(sys_semop)
-cond_syscall(sys_semtimedop)
-cond_syscall(sys_semctl)
-cond_syscall(sys_msgget)
-cond_syscall(sys_msgsnd)
-cond_syscall(sys_msgrcv)
-cond_syscall(sys_msgctl)
-cond_syscall(sys_shmget)
-cond_syscall(sys_shmdt)
-cond_syscall(sys_shmctl)
-cond_syscall(sys_mq_open)
-cond_syscall(sys_mq_unlink)
-cond_syscall(sys_mq_timedsend)
-cond_syscall(sys_mq_timedreceive)
-cond_syscall(sys_mq_notify)
-cond_syscall(sys_mq_getsetattr)
-cond_syscall(compat_sys_mq_open)
-cond_syscall(compat_sys_mq_timedsend)
-cond_syscall(compat_sys_mq_timedreceive)
-cond_syscall(compat_sys_mq_notify)
-cond_syscall(compat_sys_mq_getsetattr)
-cond_syscall(sys_mbind)
-cond_syscall(sys_get_mempolicy)
-cond_syscall(sys_set_mempolicy)
-cond_syscall(compat_get_mempolicy)
-
-/* arch-specific weak syscall entries */
-cond_syscall(sys_pciconfig_read)
-cond_syscall(sys_pciconfig_write)
-cond_syscall(sys_pciconfig_iobase)
+EXPORT_SYMBOL(capable);
+#endif
static int set_one_prio(struct task_struct *p, int niceval, int error)
{
int no_nice;
if (p->uid != current->euid &&
- p->uid != current->uid && !capable(CAP_SYS_NICE)) {
+ p->euid != current->euid && !capable(CAP_SYS_NICE)) {
error = -EPERM;
goto out;
}
- if (niceval < task_nice(p) && !capable(CAP_SYS_NICE)) {
- error = -EACCES;
+ if (niceval < task_nice(p) && !can_nice(p, niceval)) {
+ if (vx_flags(VXF_IGNEG_NICE, 0))
+ error = 0;
+ else
+ error = -EACCES;
goto out;
}
no_nice = security_task_setnice(p, niceval);
{
struct task_struct *g, *p;
struct user_struct *user;
- struct pid *pid;
- struct list_head *l;
int error = -EINVAL;
if (which > 2 || which < 0)
case PRIO_PGRP:
if (!who)
who = process_group(current);
- for_each_task_pid(who, PIDTYPE_PGID, p, l, pid)
+ do_each_task_pid(who, PIDTYPE_PGID, p) {
error = set_one_prio(p, niceval, error);
+ } while_each_task_pid(who, PIDTYPE_PGID, p);
break;
case PRIO_USER:
+ user = current->user;
if (!who)
- user = current->user;
+ who = current->uid;
else
- user = find_user(vx_current_xid(), who);
-
- if (!user)
- goto out_unlock;
+ if ((who != current->uid) &&
+ !(user = find_user(vx_current_xid(), who)))
+ goto out_unlock; /* No processes for this user */
do_each_thread(g, p)
if (p->uid == who)
error = set_one_prio(p, niceval, error);
while_each_thread(g, p);
- if (who)
+ if (who != current->uid)
free_uid(user); /* For find_user() */
break;
}
asmlinkage long sys_getpriority(int which, int who)
{
struct task_struct *g, *p;
- struct list_head *l;
- struct pid *pid;
struct user_struct *user;
long niceval, retval = -ESRCH;
case PRIO_PGRP:
if (!who)
who = process_group(current);
- for_each_task_pid(who, PIDTYPE_PGID, p, l, pid) {
+ do_each_task_pid(who, PIDTYPE_PGID, p) {
niceval = 20 - task_nice(p);
if (niceval > retval)
retval = niceval;
- }
+ } while_each_task_pid(who, PIDTYPE_PGID, p);
break;
case PRIO_USER:
+ user = current->user;
if (!who)
- user = current->user;
+ who = current->uid;
else
- user = find_user(vx_current_xid(), who);
-
- if (!user)
- goto out_unlock;
+ if ((who != current->uid) &&
+ !(user = find_user(vx_current_xid(), who)))
+ goto out_unlock; /* No processes for this user */
do_each_thread(g, p)
if (p->uid == who) {
retval = niceval;
}
while_each_thread(g, p);
- if (who)
+ if (who != current->uid)
free_uid(user); /* for find_user() */
break;
}
return retval;
}
-long vs_reboot(unsigned int, void *);
+/**
+ * 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)
+{
+ notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
+ system_state = SYSTEM_RESTART;
+ device_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);
+ }
+ printk(".\n");
+ machine_restart(cmd);
+}
+EXPORT_SYMBOL_GPL(kernel_restart);
+
+/**
+ * kernel_kexec - reboot the system
+ *
+ * Move into place and start executing a preloaded standalone
+ * executable. If nothing was preloaded return an error.
+ */
+void kernel_kexec(void)
+{
+#ifdef CONFIG_KEXEC
+ struct kimage *image;
+ image = xchg(&kexec_image, NULL);
+ 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,
+ (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);
+ 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);
+ printk(KERN_EMERG "Power down.\n");
+ machine_power_off();
+}
+EXPORT_SYMBOL_GPL(kernel_power_off);
+
+long vs_reboot(unsigned int, void __user *);
/*
* Reboot system call: for obvious reasons only root may call it,
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;
+
if (!vx_check(0, VX_ADMIN|VX_WATCH))
return vs_reboot(cmd, arg);
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:
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;
}
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;
+ case LINUX_REBOOT_CMD_KEXEC:
+ kernel_kexec();
+ unlock_kernel();
+ return -EINVAL;
+
#ifdef CONFIG_SOFTWARE_SUSPEND
case LINUX_REBOOT_CMD_SW_SUSPEND:
{
static void deferred_cad(void *dummy)
{
- notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL);
- machine_restart(NULL);
+ kernel_restart(NULL);
}
/*
}
if (new_egid != old_egid)
{
- current->mm->dumpable = 0;
- wmb();
+ current->mm->dumpable = suid_dumpable;
+ smp_wmb();
}
if (rgid != (gid_t) -1 ||
(egid != (gid_t) -1 && egid != old_rgid))
current->fsgid = new_egid;
current->egid = new_egid;
current->gid = new_rgid;
-
- ckrm_cb_gid();
-
+ key_fsgid_changed(current);
+ proc_id_connector(current, PROC_EVENT_GID);
return 0;
}
{
if(old_egid != gid)
{
- current->mm->dumpable=0;
- wmb();
+ current->mm->dumpable = suid_dumpable;
+ smp_wmb();
}
current->gid = current->egid = current->sgid = current->fsgid = gid;
}
{
if(old_egid != gid)
{
- current->mm->dumpable=0;
- wmb();
+ current->mm->dumpable = suid_dumpable;
+ smp_wmb();
}
current->egid = current->fsgid = gid;
}
else
return -EPERM;
- ckrm_cb_gid();
-
+ key_fsgid_changed(current);
+ proc_id_connector(current, PROC_EVENT_GID);
return 0;
}
return -EAGAIN;
if (atomic_read(&new_user->processes) >=
- current->rlim[RLIMIT_NPROC].rlim_cur &&
+ current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
new_user != &root_user) {
free_uid(new_user);
return -EAGAIN;
if(dumpclear)
{
- current->mm->dumpable = 0;
- wmb();
+ current->mm->dumpable = suid_dumpable;
+ smp_wmb();
}
current->uid = new_ruid;
return 0;
if (new_euid != old_euid)
{
- current->mm->dumpable=0;
- wmb();
+ current->mm->dumpable = suid_dumpable;
+ smp_wmb();
}
current->fsuid = current->euid = new_euid;
if (ruid != (uid_t) -1 ||
current->suid = current->euid;
current->fsuid = current->euid;
- ckrm_cb_uid();
+ key_fsuid_changed(current);
+ proc_id_connector(current, PROC_EVENT_UID);
return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RE);
}
if (old_euid != uid)
{
- current->mm->dumpable = 0;
- wmb();
+ current->mm->dumpable = suid_dumpable;
+ smp_wmb();
}
current->fsuid = current->euid = uid;
current->suid = new_suid;
- ckrm_cb_uid();
+ key_fsuid_changed(current);
+ proc_id_connector(current, PROC_EVENT_UID);
return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_ID);
}
if (euid != (uid_t) -1) {
if (euid != current->euid)
{
- current->mm->dumpable = 0;
- wmb();
+ current->mm->dumpable = suid_dumpable;
+ smp_wmb();
}
current->euid = euid;
}
if (suid != (uid_t) -1)
current->suid = suid;
- ckrm_cb_uid();
+ key_fsuid_changed(current);
+ proc_id_connector(current, PROC_EVENT_UID);
return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RES);
}
if (egid != (gid_t) -1) {
if (egid != current->egid)
{
- current->mm->dumpable = 0;
- wmb();
+ current->mm->dumpable = suid_dumpable;
+ smp_wmb();
}
current->egid = egid;
}
if (sgid != (gid_t) -1)
current->sgid = sgid;
- ckrm_cb_gid();
-
+ key_fsgid_changed(current);
+ proc_id_connector(current, PROC_EVENT_GID);
return 0;
}
{
if (uid != old_fsuid)
{
- current->mm->dumpable = 0;
- wmb();
+ current->mm->dumpable = suid_dumpable;
+ smp_wmb();
}
current->fsuid = uid;
}
+ key_fsuid_changed(current);
+ proc_id_connector(current, PROC_EVENT_UID);
+
security_task_post_setuid(old_fsuid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS);
return old_fsuid;
{
if (gid != old_fsgid)
{
- current->mm->dumpable = 0;
- wmb();
+ current->mm->dumpable = suid_dumpable;
+ smp_wmb();
}
current->fsgid = gid;
+ key_fsgid_changed(current);
+ proc_id_connector(current, PROC_EVENT_GID);
}
return old_fsgid;
}
*/
if (tbuf) {
struct tms tmp;
- tmp.tms_utime = jiffies_to_clock_t(current->utime);
- tmp.tms_stime = jiffies_to_clock_t(current->stime);
- tmp.tms_cutime = jiffies_to_clock_t(current->cutime);
- tmp.tms_cstime = jiffies_to_clock_t(current->cstime);
+ 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);
if (copy_to_user(tbuf, &tmp, sizeof(struct tms)))
return -EFAULT;
}
asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
{
struct task_struct *p;
+ struct task_struct *group_leader = current->group_leader;
+ pid_t rpgid;
int err = -EINVAL;
if (!pid)
- pid = current->pid;
+ pid = vx_map_pid(group_leader->pid);
if (!pgid)
pgid = pid;
if (pgid < 0)
return -EINVAL;
+ rpgid = vx_rmap_pid(pgid);
+
/* From this point forward we keep holding onto the tasklist lock
* so that our parent does not change from under us. -DaveM
*/
if (!thread_group_leader(p))
goto out;
- if (p->parent == current || p->real_parent == current) {
+ if (p->real_parent == group_leader) {
err = -EPERM;
- if (p->signal->session != current->signal->session)
+ if (p->signal->session != group_leader->signal->session)
goto out;
err = -EACCES;
if (p->did_exec)
goto out;
} else {
err = -ESRCH;
- if (p != current)
+ if (p != group_leader)
goto out;
}
if (pgid != pid) {
struct task_struct *p;
- struct pid *pid;
- struct list_head *l;
- for_each_task_pid(pgid, PIDTYPE_PGID, p, l, pid)
- if (p->signal->session == current->signal->session)
+ do_each_task_pid(rpgid, PIDTYPE_PGID, p) {
+ if (p->signal->session == group_leader->signal->session)
goto ok_pgid;
+ } while_each_task_pid(rpgid, PIDTYPE_PGID, p);
goto out;
}
ok_pgid:
- err = security_task_setpgid(p, pgid);
+ err = security_task_setpgid(p, rpgid);
if (err)
goto out;
- if (process_group(p) != pgid) {
+ if (process_group(p) != rpgid) {
detach_pid(p, PIDTYPE_PGID);
- p->signal->pgrp = pgid;
- attach_pid(p, PIDTYPE_PGID, pgid);
+ p->signal->pgrp = rpgid;
+ attach_pid(p, PIDTYPE_PGID, rpgid);
}
err = 0;
asmlinkage long sys_getpgid(pid_t pid)
{
if (!pid) {
- return process_group(current);
+ return vx_rmap_pid(process_group(current));
} else {
int retval;
struct task_struct *p;
if (p) {
retval = security_task_getpgid(p);
if (!retval)
- retval = process_group(p);
+ retval = vx_rmap_pid(process_group(p));
}
read_unlock(&tasklist_lock);
return retval;
asmlinkage long sys_setsid(void)
{
+ struct task_struct *group_leader = current->group_leader;
struct pid *pid;
int err = -EPERM;
- if (!thread_group_leader(current))
- return -EINVAL;
-
+ down(&tty_sem);
write_lock_irq(&tasklist_lock);
- pid = find_pid(PIDTYPE_PGID, current->pid);
+ pid = find_pid(PIDTYPE_PGID, group_leader->pid);
if (pid)
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(group_leader->pid, group_leader->pid);
+ group_leader->signal->tty = NULL;
+ group_leader->signal->tty_old_pgrp = 0;
+ err = process_group(group_leader);
out:
write_unlock_irq(&tasklist_lock);
+ up(&tty_sem);
return err;
}
return 0;
}
-/* a simple shell-metzner sort */
+/* a simple Shell sort */
static void groups_sort(struct group_info *group_info)
{
int base, max, stride;
}
/* a simple bsearch */
-static int groups_search(struct group_info *group_info, gid_t grp)
+int groups_search(struct group_info *group_info, gid_t grp)
{
int left, right;
int errno;
char tmp[__NEW_UTS_LEN];
- if (!capable(CAP_SYS_ADMIN) && !vx_ccaps(VXC_SET_UTSNAME))
+ if (!vx_capable(CAP_SYS_ADMIN, VXC_SET_UTSNAME))
return -EPERM;
if (len < 0 || len > __NEW_UTS_LEN)
return -EINVAL;
int errno;
char tmp[__NEW_UTS_LEN];
- if (!capable(CAP_SYS_ADMIN) && !vx_ccaps(VXC_SET_UTSNAME))
+ if (!vx_capable(CAP_SYS_ADMIN, VXC_SET_UTSNAME))
return -EPERM;
if (len < 0 || len > __NEW_UTS_LEN)
return -EINVAL;
{
if (resource >= RLIM_NLIMITS)
return -EINVAL;
- else
- return copy_to_user(rlim, current->rlim + resource, sizeof(*rlim))
- ? -EFAULT : 0;
+ else {
+ struct rlimit value;
+ task_lock(current->group_leader);
+ value = current->signal->rlim[resource];
+ task_unlock(current->group_leader);
+ return copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0;
+ }
}
#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT
if (resource >= RLIM_NLIMITS)
return -EINVAL;
- memcpy(&x, current->rlim + resource, sizeof(*rlim));
+ task_lock(current->group_leader);
+ x = current->signal->rlim[resource];
+ task_unlock(current->group_leader);
if(x.rlim_cur > 0x7FFFFFFF)
x.rlim_cur = 0x7FFFFFFF;
if(x.rlim_max > 0x7FFFFFFF)
return -EFAULT;
if (new_rlim.rlim_cur > new_rlim.rlim_max)
return -EINVAL;
- old_rlim = current->rlim + resource;
- if (((new_rlim.rlim_cur > old_rlim->rlim_max) ||
- (new_rlim.rlim_max > old_rlim->rlim_max)) &&
- !capable(CAP_SYS_RESOURCE) && !vx_ccaps(VXC_SET_RLIMIT))
+ old_rlim = current->signal->rlim + resource;
+ if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
+ !vx_capable(CAP_SYS_RESOURCE, VXC_SET_RLIMIT))
return -EPERM;
- if (resource == RLIMIT_NOFILE) {
- if (new_rlim.rlim_cur > NR_OPEN || new_rlim.rlim_max > NR_OPEN)
+ if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > NR_OPEN)
return -EPERM;
- }
retval = security_task_setrlimit(resource, &new_rlim);
if (retval)
return retval;
+ 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))) {
+ 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);
+ set_process_cpu_timer(current, CPUCLOCK_PROF,
+ &cputime, NULL);
+ spin_unlock_irq(¤t->sighand->siglock);
+ read_unlock(&tasklist_lock);
+ }
+
return 0;
}
* a lot simpler! (Which we're not doing right now because we're not
* measuring them yet).
*
- * This is SMP safe. Either we are called from sys_getrusage on ourselves
- * below (we know we aren't going to exit/disappear and only we change our
- * rusage counters), or we are called from wait4() on a process which is
- * either stopped or zombied. In the zombied case the task won't get
- * reaped till shortly after the call to getrusage(), in both cases the
- * task being examined is in a frozen state so the counters won't change.
+ * 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
+ * care which for the sums. We always take the siglock to protect reading
+ * 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.
*/
-int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
+
+static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
{
- struct rusage r;
+ struct task_struct *t;
+ unsigned long flags;
+ cputime_t utime, stime;
+
+ memset((char *) r, 0, sizeof *r);
+
+ if (unlikely(!p->signal))
+ return;
+
+ utime = stime = cputime_zero;
- memset((char *) &r, 0, sizeof(r));
switch (who) {
- case RUSAGE_SELF:
- jiffies_to_timeval(p->utime, &r.ru_utime);
- jiffies_to_timeval(p->stime, &r.ru_stime);
- r.ru_nvcsw = p->nvcsw;
- r.ru_nivcsw = p->nivcsw;
- r.ru_minflt = p->min_flt;
- r.ru_majflt = p->maj_flt;
- break;
+ case RUSAGE_BOTH:
case RUSAGE_CHILDREN:
- jiffies_to_timeval(p->cutime, &r.ru_utime);
- jiffies_to_timeval(p->cstime, &r.ru_stime);
- r.ru_nvcsw = p->cnvcsw;
- r.ru_nivcsw = p->cnivcsw;
- r.ru_minflt = p->cmin_flt;
- r.ru_majflt = p->cmaj_flt;
+ spin_lock_irqsave(&p->sighand->siglock, flags);
+ utime = p->signal->cutime;
+ stime = p->signal->cstime;
+ r->ru_nvcsw = p->signal->cnvcsw;
+ r->ru_nivcsw = p->signal->cnivcsw;
+ r->ru_minflt = p->signal->cmin_flt;
+ r->ru_majflt = p->signal->cmaj_flt;
+ spin_unlock_irqrestore(&p->sighand->siglock, flags);
+
+ if (who == RUSAGE_CHILDREN)
+ break;
+
+ case RUSAGE_SELF:
+ utime = cputime_add(utime, p->signal->utime);
+ stime = cputime_add(stime, p->signal->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;
+ 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;
+ t = next_thread(t);
+ } while (t != p);
break;
+
default:
- jiffies_to_timeval(p->utime + p->cutime, &r.ru_utime);
- jiffies_to_timeval(p->stime + p->cstime, &r.ru_stime);
- r.ru_nvcsw = p->nvcsw + p->cnvcsw;
- r.ru_nivcsw = p->nivcsw + p->cnivcsw;
- r.ru_minflt = p->min_flt + p->cmin_flt;
- r.ru_majflt = p->maj_flt + p->cmaj_flt;
- break;
+ BUG();
}
+
+ 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_prctl(int option, unsigned long arg2, unsigned long arg3,
unsigned long arg4, unsigned long arg5)
{
- int error;
- int sig;
+ long error;
error = security_task_prctl(option, arg2, arg3, arg4, arg5);
if (error)
switch (option) {
case PR_SET_PDEATHSIG:
- sig = arg2;
- if (sig < 0 || sig > _NSIG) {
+ if (!valid_signal(arg2)) {
error = -EINVAL;
break;
}
- current->pdeath_signal = sig;
+ current->pdeath_signal = arg2;
break;
case PR_GET_PDEATHSIG:
error = put_user(current->pdeath_signal, (int __user *)arg2);
break;
case PR_GET_DUMPABLE:
- if (current->mm->dumpable)
- error = 1;
+ error = current->mm->dumpable;
break;
case PR_SET_DUMPABLE:
- if (arg2 != 0 && arg2 != 1) {
+ if (arg2 < 0 || arg2 > 1) {
error = -EINVAL;
break;
}
}
current->keep_capabilities = arg2;
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)
+ return -EFAULT;
+ set_task_comm(me, ncomm);
+ 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)))
+ return -EFAULT;
+ return 0;
+ }
default:
error = -EINVAL;
break;