summaryrefslogtreecommitdiffstats
path: root/kernel/sys.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sys.c')
-rw-r--r--kernel/sys.c114
1 files changed, 72 insertions, 42 deletions
diff --git a/kernel/sys.c b/kernel/sys.c
index f91218a5463..38bc73ede2b 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -224,18 +224,6 @@ int unregister_reboot_notifier(struct notifier_block * nb)
EXPORT_SYMBOL(unregister_reboot_notifier);
-#ifndef CONFIG_SECURITY
-int capable(int cap)
-{
- if (cap_raised(current->cap_effective, cap)) {
- current->flags |= PF_SUPERPRIV;
- return 1;
- }
- return 0;
-}
-EXPORT_SYMBOL(capable);
-#endif
-
static int set_one_prio(struct task_struct *p, int niceval, int error)
{
int no_nice;
@@ -1227,7 +1215,7 @@ asmlinkage long sys_setsid(void)
struct pid *pid;
int err = -EPERM;
- down(&tty_sem);
+ mutex_lock(&tty_mutex);
write_lock_irq(&tasklist_lock);
pid = find_pid(PIDTYPE_PGID, group_leader->pid);
@@ -1241,7 +1229,7 @@ asmlinkage long sys_setsid(void)
err = process_group(group_leader);
out:
write_unlock_irq(&tasklist_lock);
- up(&tty_sem);
+ mutex_unlock(&tty_mutex);
return err;
}
@@ -1375,7 +1363,7 @@ 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;
@@ -1383,7 +1371,7 @@ 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;
@@ -1433,7 +1421,6 @@ asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist)
return -EINVAL;
/* no need to grab task_lock here; it cannot change */
- get_group_info(current->group_info);
i = current->group_info->ngroups;
if (gidsetsize) {
if (i > gidsetsize) {
@@ -1446,7 +1433,6 @@ asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist)
}
}
out:
- put_group_info(current->group_info);
return i;
}
@@ -1487,9 +1473,7 @@ int in_group_p(gid_t grp)
{
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);
}
return retval;
}
@@ -1500,9 +1484,7 @@ int in_egroup_p(gid_t grp)
{
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);
}
return retval;
}
@@ -1630,20 +1612,21 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r
asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
{
struct rlimit new_rlim, *old_rlim;
+ unsigned long it_prof_secs;
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;
+ return -EPERM;
retval = security_task_setrlimit(resource, &new_rlim);
if (retval)
@@ -1653,19 +1636,40 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
*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);
+ 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;
+
+ it_prof_secs = cputime_to_secs(current->signal->it_prof_expires);
+ if (it_prof_secs == 0 || new_rlim.rlim_cur <= it_prof_secs) {
+ 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(&current->sighand->siglock);
- set_process_cpu_timer(current, CPUCLOCK_PROF,
- &cputime, NULL);
+ set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
spin_unlock_irq(&current->sighand->siglock);
read_unlock(&tasklist_lock);
}
-
+out:
return 0;
}
@@ -1677,9 +1681,6 @@ 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
@@ -1687,6 +1688,25 @@ 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.
+ *
+ * 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.
+ *
*/
static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
@@ -1694,13 +1714,23 @@ 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 (unlikely(!p->signal))
- return;
+ if (p != current || !thread_group_empty(p))
+ need_lock = 1;
- utime = stime = cputime_zero;
+ if (need_lock) {
+ read_lock(&tasklist_lock);
+ if (unlikely(!p->signal)) {
+ read_unlock(&tasklist_lock);
+ return;
+ }
+ } else
+ /* See locking comments above */
+ smp_rmb();
switch (who) {
case RUSAGE_BOTH:
@@ -1740,6 +1770,8 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
BUG();
}
+ if (need_lock)
+ read_unlock(&tasklist_lock);
cputime_to_timeval(utime, &r->ru_utime);
cputime_to_timeval(stime, &r->ru_stime);
}
@@ -1747,9 +1779,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
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;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-02-20 09:23:50 +0000