/*
* free_ipcs - free all ipcs of one type
* @ns: the namespace to remove the ipcs from
* @ids: the table of ipcs to free
* @free: the function called to free each individual ipc
*
* Called for each kind of ipc when an ipc_namespace exits.
*/
void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
void (*free)(struct ipc_namespace *, struct kern_ipc_perm *))
{
struct kern_ipc_perm *perm;
int next_id;
int total, in_use;
down_write(&ids->rw_mutex);
in_use = ids->in_use;
for (total = 0, next_id = 0; total < in_use; next_id++) {
perm = idr_find(&ids->ipcs_idr, next_id);
if (perm == NULL)
continue;
ipc_lock_by_ptr(perm);
free(ns, perm);
total++;
}
up_write(&ids->rw_mutex);
}
static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key)
{
struct kern_ipc_perm *ipc;
int next_id;
int total;
for (total = 0, next_id = 0; total < ids->in_use; next_id++) {
ipc = idr_find(&ids->ipcs_idr, next_id);
if (ipc == NULL)
continue;
if (ipc->key != key) {
total++;
continue;
}
ipc_lock_by_ptr(ipc);
return ipc;
}
return NULL;
}
void shm_exit_ns(struct ipc_namespace *ns)
{
struct shmid_kernel *shp;
int next_id;
int total, in_use;
down_write(&shm_ids(ns).rw_mutex);
in_use = shm_ids(ns).in_use;
for (total = 0, next_id = 0; total < in_use; next_id++) {
shp = idr_find(&shm_ids(ns).ipcs_idr, next_id);
if (shp == NULL)
continue;
ipc_lock_by_ptr(&shp->shm_perm);
do_shm_rmid(ns, shp);
total++;
}
up_write(&shm_ids(ns).rw_mutex);
kfree(ns->ids[IPC_SHM_IDS]);
ns->ids[IPC_SHM_IDS] = NULL;
}
/*
* freeque() wakes up waiters on the sender and receiver waiting queue,
* removes the message queue from message queue ID IDR, and cleans up all the
* messages associated with this queue.
*
* msg_ids.rw_mutex (writer) and the spinlock for this message queue are held
* before freeque() is called. msg_ids.rw_mutex remains locked on exit.
*/
static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
{
struct list_head *tmp;
struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm);
expunge_all(msq, -EIDRM);
ss_wakeup(&msq->q_senders, 1);
msg_rmid(ns, msq);
msg_unlock(msq);
tmp = msq->q_messages.next;
while (tmp != &msq->q_messages) {
struct msg_msg *msg = list_entry(tmp, struct msg_msg, m_list);
tmp = tmp->next;
atomic_dec(&ns->msg_hdrs);
free_msg(msg);
}
atomic_sub(msq->q_cbytes, &ns->msg_bytes);
security_msg_queue_free(msq);
ipc_lock_by_ptr(&msq->q_perm);
ipc_rcu_putref(msq);
ipc_unlock(&msq->q_perm);
}
long do_msgrcv(int msqid, long *pmtype, void __user *mtext,
size_t msgsz, long msgtyp, int msgflg)
{
struct msg_queue *msq;
struct msg_msg *msg;
int mode;
struct ipc_namespace *ns;
if (msqid < 0 || (long) msgsz < 0)
return -EINVAL;
mode = convert_mode(&msgtyp, msgflg);
ns = current->nsproxy->ipc_ns;
msq = msg_lock_check(ns, msqid);
if (IS_ERR(msq))
return PTR_ERR(msq);
for (;;) {
struct msg_receiver msr_d;
struct list_head *tmp;
msg = ERR_PTR(-EACCES);
if (ipcperms(&msq->q_perm, S_IRUGO))
goto out_unlock;
msg = ERR_PTR(-EAGAIN);
tmp = msq->q_messages.next;
while (tmp != &msq->q_messages) {
struct msg_msg *walk_msg;
walk_msg = list_entry(tmp, struct msg_msg, m_list);
if (testmsg(walk_msg, msgtyp, mode) &&
!security_msg_queue_msgrcv(msq, walk_msg, current,
msgtyp, mode)) {
msg = walk_msg;
if (mode == SEARCH_LESSEQUAL &&
walk_msg->m_type != 1) {
msg = walk_msg;
msgtyp = walk_msg->m_type - 1;
} else {
msg = walk_msg;
break;
}
}
tmp = tmp->next;
}
if (!IS_ERR(msg)) {
/*
* Found a suitable message.
* Unlink it from the queue.
*/
if ((msgsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) {
msg = ERR_PTR(-E2BIG);
goto out_unlock;
}
list_del(&msg->m_list);
msq->q_qnum--;
msq->q_rtime = get_seconds();
msq->q_lrpid = task_tgid_vnr(current);
msq->q_cbytes -= msg->m_ts;
atomic_sub(msg->m_ts, &ns->msg_bytes);
atomic_dec(&ns->msg_hdrs);
ss_wakeup(&msq->q_senders, 0);
msg_unlock(msq);
break;
}
/* No message waiting. Wait for a message */
if (msgflg & IPC_NOWAIT) {
msg = ERR_PTR(-ENOMSG);
goto out_unlock;
}
list_add_tail(&msr_d.r_list, &msq->q_receivers);
msr_d.r_tsk = current;
msr_d.r_msgtype = msgtyp;
msr_d.r_mode = mode;
if (msgflg & MSG_NOERROR)
msr_d.r_maxsize = INT_MAX;
else
msr_d.r_maxsize = msgsz;
msr_d.r_msg = ERR_PTR(-EAGAIN);
current->state = TASK_INTERRUPTIBLE;
msg_unlock(msq);
schedule();
/* Lockless receive, part 1:
* Disable preemption. We don't hold a reference to the queue
* and getting a reference would defeat the idea of a lockless
* operation, thus the code relies on rcu to guarantee the
* existance of msq:
* Prior to destruction, expunge_all(-EIRDM) changes r_msg.
* Thus if r_msg is -EAGAIN, then the queue not yet destroyed.
* rcu_read_lock() prevents preemption between reading r_msg
* and the spin_lock() inside ipc_lock_by_ptr().
*/
rcu_read_lock();
/* Lockless receive, part 2:
* Wait until pipelined_send or expunge_all are outside of
* wake_up_process(). There is a race with exit(), see
* ipc/mqueue.c for the details.
*/
msg = (struct msg_msg*)msr_d.r_msg;
while (msg == NULL) {
cpu_relax();
msg = (struct msg_msg *)msr_d.r_msg;
}
/* Lockless receive, part 3:
* If there is a message or an error then accept it without
* locking.
*/
if (msg != ERR_PTR(-EAGAIN)) {
rcu_read_unlock();
break;
}
/* Lockless receive, part 3:
* Acquire the queue spinlock.
*/
ipc_lock_by_ptr(&msq->q_perm);
rcu_read_unlock();
/* Lockless receive, part 4:
* Repeat test after acquiring the spinlock.
*/
msg = (struct msg_msg*)msr_d.r_msg;
if (msg != ERR_PTR(-EAGAIN))
goto out_unlock;
list_del(&msr_d.r_list);
if (signal_pending(current)) {
msg = ERR_PTR(-ERESTARTNOHAND);
out_unlock:
msg_unlock(msq);
break;
}
}
if (IS_ERR(msg))
return PTR_ERR(msg);
msgsz = (msgsz > msg->m_ts) ? msg->m_ts : msgsz;
*pmtype = msg->m_type;
if (store_msg(mtext, msg, msgsz))
msgsz = -EFAULT;
free_msg(msg);
return msgsz;
}
long do_msgsnd(int msqid, long mtype, void __user *mtext,
size_t msgsz, int msgflg)
{
struct msg_queue *msq;
struct msg_msg *msg;
int err;
struct ipc_namespace *ns;
ns = current->nsproxy->ipc_ns;
if (msgsz > ns->msg_ctlmax || (long) msgsz < 0 || msqid < 0)
return -EINVAL;
if (mtype < 1)
return -EINVAL;
msg = load_msg(mtext, msgsz);
if (IS_ERR(msg))
return PTR_ERR(msg);
msg->m_type = mtype;
msg->m_ts = msgsz;
msq = msg_lock_check(ns, msqid);
if (IS_ERR(msq)) {
err = PTR_ERR(msq);
goto out_free;
}
for (;;) {
struct msg_sender s;
err = -EACCES;
if (ipcperms(&msq->q_perm, S_IWUGO))
goto out_unlock_free;
err = security_msg_queue_msgsnd(msq, msg, msgflg);
if (err)
goto out_unlock_free;
if (msgsz + msq->q_cbytes <= msq->q_qbytes &&
1 + msq->q_qnum <= msq->q_qbytes) {
break;
}
/* queue full, wait: */
if (msgflg & IPC_NOWAIT) {
err = -EAGAIN;
goto out_unlock_free;
}
ss_add(msq, &s);
ipc_rcu_getref(msq);
msg_unlock(msq);
schedule();
ipc_lock_by_ptr(&msq->q_perm);
ipc_rcu_putref(msq);
if (msq->q_perm.deleted) {
err = -EIDRM;
goto out_unlock_free;
}
ss_del(&s);
if (signal_pending(current)) {
err = -ERESTARTNOHAND;
goto out_unlock_free;
}
}
msq->q_lspid = task_tgid_vnr(current);
msq->q_stime = get_seconds();
if (!pipelined_send(msq, msg)) {
/* noone is waiting for this message, enqueue it */
list_add_tail(&msg->m_list, &msq->q_messages);
msq->q_cbytes += msgsz;
msq->q_qnum++;
atomic_add(msgsz, &ns->msg_bytes);
atomic_inc(&ns->msg_hdrs);
}
err = 0;
msg = NULL;
out_unlock_free:
msg_unlock(msq);
out_free:
if (msg != NULL)
free_msg(msg);
return err;
}
static inline void sem_putref(struct sem_array *sma)
{
ipc_lock_by_ptr(&sma->sem_perm);
ipc_rcu_putref(sma);
ipc_unlock(&(sma)->sem_perm);
}
