ipc_rcu_free(head);
}
+/*
+ * spin_unlock_wait() and !spin_is_locked() are not memory barriers, they
+ * are only control barriers.
+ * The code must pair with spin_unlock(&sem->lock) or
+ * spin_unlock(&sem_perm.lock), thus just the control barrier is insufficient.
+ *
+ * smp_rmb() is sufficient, as writes cannot pass the control barrier.
+ */
+#define ipc_smp_acquire__after_spin_is_unlocked() smp_rmb()
+
/*
* Wait until all currently ongoing simple ops have completed.
* Caller must own sem_perm.lock.
* New simple ops cannot start, because simple ops first check
* that sem_perm.lock is free.
+ * that a) sem_perm.lock is free and b) complex_count is 0.
*/
static void sem_wait_array(struct sem_array *sma)
{
int i;
struct sem *sem;
+ if (sma->complex_count) {
+ /* The thread that increased sma->complex_count waited on
+ * all sem->lock locks. Thus we don't need to wait again.
+ */
+ return;
+ }
+
for (i = 0; i < sma->sem_nsems; i++) {
sem = sma->sem_base + i;
spin_unlock_wait(&sem->lock);
}
+ ipc_smp_acquire__after_spin_is_unlocked();
}
/*
/* Then check that the global lock is free */
if (!spin_is_locked(&sma->sem_perm.lock)) {
- /* spin_is_locked() is not a memory barrier */
- smp_mb();
+ /*
+ * We need a memory barrier with acquire semantics,
+ * otherwise we can race with another thread that does:
+ * complex_count++;
+ * spin_unlock(sem_perm.lock);
+ */
+ ipc_smp_acquire__after_spin_is_unlocked();
/* Now repeat the test of complex_count:
* It can't change anymore until we drop sem->lock.
return semop_completed;
}
+/**
+ * set_semotime(sma, sops) - set sem_otime
+ * @sma: semaphore array
+ * @sops: operations that modified the array, may be NULL
+ *
+ * sem_otime is replicated to avoid cache line trashing.
+ * This function sets one instance to the current time.
+ */
+static void set_semotime(struct sem_array *sma, struct sembuf *sops)
+{
+ if (sops == NULL) {
+ sma->sem_base[0].sem_otime = get_seconds();
+ } else {
+ sma->sem_base[sops[0].sem_num].sem_otime =
+ get_seconds();
+ }
+}
+
/**
* do_smart_update(sma, sops, nsops, otime, pt) - optimized update_queue
* @sma: semaphore array
}
}
}
- if (otime) {
- if (sops == NULL) {
- sma->sem_base[0].sem_otime = get_seconds();
- } else {
- sma->sem_base[sops[0].sem_num].sem_otime =
- get_seconds();
- }
- }
+ if (otime)
+ set_semotime(sma, sops);
}
-
/* The following counts are associated to each semaphore:
* semncnt number of tasks waiting on semval being nonzero
* semzcnt number of tasks waiting on semval being zero
sem_lock(sma, NULL, -1);
+ if (sma->sem_perm.deleted) {
+ sem_unlock(sma, -1);
+ rcu_read_unlock();
+ return -EIDRM;
+ }
+
curr = &sma->sem_base[semnum];
ipc_assert_locked_object(&sma->sem_perm);
int i;
sem_lock(sma, NULL, -1);
+ if (sma->sem_perm.deleted) {
+ err = -EIDRM;
+ goto out_unlock;
+ }
if(nsems > SEMMSL_FAST) {
if (!ipc_rcu_getref(sma)) {
- sem_unlock(sma, -1);
- rcu_read_unlock();
err = -EIDRM;
- goto out_free;
+ goto out_unlock;
}
sem_unlock(sma, -1);
rcu_read_unlock();
rcu_read_lock();
sem_lock_and_putref(sma);
if (sma->sem_perm.deleted) {
- sem_unlock(sma, -1);
- rcu_read_unlock();
err = -EIDRM;
- goto out_free;
+ goto out_unlock;
}
}
for (i = 0; i < sma->sem_nsems; i++)
struct sem_undo *un;
if (!ipc_rcu_getref(sma)) {
- rcu_read_unlock();
- return -EIDRM;
+ err = -EIDRM;
+ goto out_rcu_wakeup;
}
rcu_read_unlock();
rcu_read_lock();
sem_lock_and_putref(sma);
if (sma->sem_perm.deleted) {
- sem_unlock(sma, -1);
- rcu_read_unlock();
err = -EIDRM;
- goto out_free;
+ goto out_unlock;
}
for (i = 0; i < nsems; i++)
goto out_rcu_wakeup;
sem_lock(sma, NULL, -1);
+ if (sma->sem_perm.deleted) {
+ err = -EIDRM;
+ goto out_unlock;
+ }
curr = &sma->sem_base[semnum];
switch (cmd) {
if (error)
goto out_rcu_wakeup;
+ error = -EIDRM;
+ locknum = sem_lock(sma, sops, nsops);
+ if (sma->sem_perm.deleted)
+ goto out_unlock_free;
/*
* semid identifiers are not unique - find_alloc_undo may have
* allocated an undo structure, it was invalidated by an RMID
* This case can be detected checking un->semid. The existence of
* "un" itself is guaranteed by rcu.
*/
- error = -EIDRM;
- locknum = sem_lock(sma, sops, nsops);
if (un && un->semid == -1)
goto out_unlock_free;
error = perform_atomic_semop(sma, sops, nsops, un,
task_tgid_vnr(current));
- if (error <= 0) {
- if (alter && error == 0)
+ if (error == 0) {
+ /* If the operation was successful, then do
+ * the required updates.
+ */
+ if (alter)
do_smart_update(sma, sops, nsops, 1, &tasks);
-
- goto out_unlock_free;
+ else
+ set_semotime(sma, sops);
}
+ if (error <= 0)
+ goto out_unlock_free;
/* We need to sleep on this operation, so we put the current
* task into the pending queue and go to sleep.
rcu_read_lock();
un = list_entry_rcu(ulp->list_proc.next,
struct sem_undo, list_proc);
- if (&un->list_proc == &ulp->list_proc)
- semid = -1;
- else
- semid = un->semid;
+ if (&un->list_proc == &ulp->list_proc) {
+ /*
+ * We must wait for freeary() before freeing this ulp,
+ * in case we raced with last sem_undo. There is a small
+ * possibility where we exit while freeary() didn't
+ * finish unlocking sem_undo_list.
+ */
+ spin_unlock_wait(&ulp->lock);
+ rcu_read_unlock();
+ break;
+ }
+ spin_lock(&ulp->lock);
+ semid = un->semid;
+ spin_unlock(&ulp->lock);
+ /* exit_sem raced with IPC_RMID, nothing to do */
if (semid == -1) {
rcu_read_unlock();
- break;
+ continue;
}
- sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, un->semid);
+ sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, semid);
/* exit_sem raced with IPC_RMID, nothing to do */
if (IS_ERR(sma)) {
rcu_read_unlock();
}
sem_lock(sma, NULL, -1);
+ /* exit_sem raced with IPC_RMID, nothing to do */
+ if (sma->sem_perm.deleted) {
+ sem_unlock(sma, -1);
+ rcu_read_unlock();
+ continue;
+ }
un = __lookup_undo(ulp, semid);
if (un == NULL) {
/* exit_sem raced with IPC_RMID+semget() that created
struct sem_array *sma = it;
time_t sem_otime;
+ /*
+ * The proc interface isn't aware of sem_lock(), it calls
+ * ipc_lock_object() directly (in sysvipc_find_ipc).
+ * In order to stay compatible with sem_lock(), we must wait until
+ * all simple semop() calls have left their critical regions.
+ */
+ sem_wait_array(sma);
+
sem_otime = get_semotime(sma);
return seq_printf(s,