#define SEARCH_EQUAL 2
#define SEARCH_NOTEQUAL 3
#define SEARCH_LESSEQUAL 4
+#define SEARCH_NUMBER 5
#define msg_ids(ns) ((ns)->ids[IPC_MSG_IDS])
return container_of(ipcp, struct msg_queue, q_perm);
}
+static inline struct msg_queue *msq_obtain_object(struct ipc_namespace *ns, int id)
+{
+ struct kern_ipc_perm *ipcp = ipc_obtain_object(&msg_ids(ns), id);
+
+ if (IS_ERR(ipcp))
+ return ERR_CAST(ipcp);
+
+ return container_of(ipcp, struct msg_queue, q_perm);
+}
+
+static inline struct msg_queue *msq_obtain_object_check(struct ipc_namespace *ns,
+ int id)
+{
+ struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&msg_ids(ns), id);
+
+ if (IS_ERR(ipcp))
+ return ERR_CAST(ipcp);
+
+ return container_of(ipcp, struct msg_queue, q_perm);
+}
+
static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s)
{
ipc_rmid(&msg_ids(ns), &s->q_perm);
return retval;
}
- /*
- * ipc_addid() locks msq
- */
+ /* ipc_addid() locks msq upon success. */
id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
if (id < 0) {
security_msg_queue_free(msq);
INIT_LIST_HEAD(&msq->q_receivers);
INIT_LIST_HEAD(&msq->q_senders);
- msg_unlock(msq);
+ ipc_unlock_object(&msq->q_perm);
+ rcu_read_unlock();
return msq->q_perm.id;
}
static void ss_wakeup(struct list_head *h, int kill)
{
- struct list_head *tmp;
-
- tmp = h->next;
- while (tmp != h) {
- struct msg_sender *mss;
+ struct msg_sender *mss, *t;
- mss = list_entry(tmp, struct msg_sender, list);
- tmp = tmp->next;
+ list_for_each_entry_safe(mss, t, h, list) {
if (kill)
mss->list.next = NULL;
wake_up_process(mss->tsk);
static void expunge_all(struct msg_queue *msq, int res)
{
- struct list_head *tmp;
-
- tmp = msq->q_receivers.next;
- while (tmp != &msq->q_receivers) {
- struct msg_receiver *msr;
+ struct msg_receiver *msr, *t;
- msr = list_entry(tmp, struct msg_receiver, r_list);
- tmp = tmp->next;
+ list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) {
msr->r_msg = NULL;
wake_up_process(msr->r_tsk);
smp_mb();
*/
static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
{
- struct list_head *tmp;
+ struct msg_msg *msg, *t;
struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm);
expunge_all(msq, -EIDRM);
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;
+ list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) {
atomic_dec(&ns->msg_hdrs);
free_msg(msg);
}
return -EFAULT;
}
- ipcp = ipcctl_pre_down(ns, &msg_ids(ns), msqid, cmd,
- &msqid64.msg_perm, msqid64.msg_qbytes);
- if (IS_ERR(ipcp))
- return PTR_ERR(ipcp);
+ down_write(&msg_ids(ns).rw_mutex);
+ rcu_read_lock();
+
+ ipcp = ipcctl_pre_down_nolock(ns, &msg_ids(ns), msqid, cmd,
+ &msqid64.msg_perm, msqid64.msg_qbytes);
+ if (IS_ERR(ipcp)) {
+ err = PTR_ERR(ipcp);
+ goto out_unlock1;
+ }
msq = container_of(ipcp, struct msg_queue, q_perm);
err = security_msg_queue_msgctl(msq, cmd);
if (err)
- goto out_unlock;
+ goto out_unlock1;
switch (cmd) {
case IPC_RMID:
+ ipc_lock_object(&msq->q_perm);
+ /* freeque unlocks the ipc object and rcu */
freeque(ns, ipcp);
goto out_up;
case IPC_SET:
if (msqid64.msg_qbytes > ns->msg_ctlmnb &&
!capable(CAP_SYS_RESOURCE)) {
err = -EPERM;
- goto out_unlock;
+ goto out_unlock1;
}
+ ipc_lock_object(&msq->q_perm);
err = ipc_update_perm(&msqid64.msg_perm, ipcp);
if (err)
- goto out_unlock;
+ goto out_unlock0;
msq->q_qbytes = msqid64.msg_qbytes;
break;
default:
err = -EINVAL;
+ goto out_unlock1;
}
-out_unlock:
- msg_unlock(msq);
+
+out_unlock0:
+ ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+ rcu_read_unlock();
out_up:
up_write(&msg_ids(ns).rw_mutex);
return err;
}
-SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
+static int msgctl_nolock(struct ipc_namespace *ns, int msqid,
+ int cmd, int version, void __user *buf)
{
+ int err;
struct msg_queue *msq;
- int err, version;
- struct ipc_namespace *ns;
-
- if (msqid < 0 || cmd < 0)
- return -EINVAL;
-
- version = ipc_parse_version(&cmd);
- ns = current->nsproxy->ipc_ns;
switch (cmd) {
case IPC_INFO:
if (!buf)
return -EFAULT;
+
/*
* We must not return kernel stack data.
* due to padding, it's not enough
return -EFAULT;
return (max_id < 0) ? 0 : max_id;
}
- case MSG_STAT: /* msqid is an index rather than a msg queue id */
+
+ case MSG_STAT:
case IPC_STAT:
{
struct msqid64_ds tbuf;
if (!buf)
return -EFAULT;
+ memset(&tbuf, 0, sizeof(tbuf));
+
+ rcu_read_lock();
if (cmd == MSG_STAT) {
- msq = msg_lock(ns, msqid);
- if (IS_ERR(msq))
- return PTR_ERR(msq);
+ msq = msq_obtain_object(ns, msqid);
+ if (IS_ERR(msq)) {
+ err = PTR_ERR(msq);
+ goto out_unlock;
+ }
success_return = msq->q_perm.id;
} else {
- msq = msg_lock_check(ns, msqid);
- if (IS_ERR(msq))
- return PTR_ERR(msq);
+ msq = msq_obtain_object_check(ns, msqid);
+ if (IS_ERR(msq)) {
+ err = PTR_ERR(msq);
+ goto out_unlock;
+ }
success_return = 0;
}
+
err = -EACCES;
if (ipcperms(ns, &msq->q_perm, S_IRUGO))
goto out_unlock;
if (err)
goto out_unlock;
- memset(&tbuf, 0, sizeof(tbuf));
-
kernel_to_ipc64_perm(&msq->q_perm, &tbuf.msg_perm);
tbuf.msg_stime = msq->q_stime;
tbuf.msg_rtime = msq->q_rtime;
tbuf.msg_qbytes = msq->q_qbytes;
tbuf.msg_lspid = msq->q_lspid;
tbuf.msg_lrpid = msq->q_lrpid;
- msg_unlock(msq);
+ rcu_read_unlock();
+
if (copy_msqid_to_user(buf, &tbuf, version))
return -EFAULT;
return success_return;
}
- case IPC_SET:
- case IPC_RMID:
- err = msgctl_down(ns, msqid, cmd, buf, version);
- return err;
+
default:
- return -EINVAL;
+ return -EINVAL;
}
+ return err;
out_unlock:
- msg_unlock(msq);
+ rcu_read_unlock();
return err;
}
+SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
+{
+ int version;
+ struct ipc_namespace *ns;
+
+ if (msqid < 0 || cmd < 0)
+ return -EINVAL;
+
+ version = ipc_parse_version(&cmd);
+ ns = current->nsproxy->ipc_ns;
+
+ switch (cmd) {
+ case IPC_INFO:
+ case MSG_INFO:
+ case MSG_STAT: /* msqid is an index rather than a msg queue id */
+ case IPC_STAT:
+ return msgctl_nolock(ns, msqid, cmd, version, buf);
+ case IPC_SET:
+ case IPC_RMID:
+ return msgctl_down(ns, msqid, cmd, buf, version);
+ default:
+ return -EINVAL;
+ }
+}
+
static int testmsg(struct msg_msg *msg, long type, int mode)
{
switch(mode)
{
case SEARCH_ANY:
+ case SEARCH_NUMBER:
return 1;
case SEARCH_LESSEQUAL:
if (msg->m_type <=type)
static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg)
{
- struct list_head *tmp;
+ struct msg_receiver *msr, *t;
- tmp = msq->q_receivers.next;
- while (tmp != &msq->q_receivers) {
- struct msg_receiver *msr;
-
- msr = list_entry(tmp, struct msg_receiver, r_list);
- tmp = tmp->next;
+ list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) {
if (testmsg(msg, msr->r_msgtype, msr->r_mode) &&
!security_msg_queue_msgrcv(msq, msg, msr->r_tsk,
msr->r_msgtype, msr->r_mode)) {
goto out_unlock_free;
}
ss_add(msq, &s);
- ipc_rcu_getref(msq);
+
+ if (!ipc_rcu_getref(msq)) {
+ err = -EIDRM;
+ goto out_unlock_free;
+ }
+
msg_unlock(msq);
schedule();
static inline int convert_mode(long *msgtyp, int msgflg)
{
+ if (msgflg & MSG_COPY)
+ return SEARCH_NUMBER;
/*
* find message of correct type.
* msgtyp = 0 => get first.
* This function creates new kernel message structure, large enough to store
* bufsz message bytes.
*/
-static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz,
- int msgflg, long *msgtyp,
- unsigned long *copy_number)
+static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz)
{
struct msg_msg *copy;
- *copy_number = *msgtyp;
- *msgtyp = 0;
/*
* Create dummy message to copy real message to.
*/
free_msg(copy);
}
#else
-static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz,
- int msgflg, long *msgtyp,
- unsigned long *copy_number)
+static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz)
{
return ERR_PTR(-ENOSYS);
}
}
#endif
+static struct msg_msg *find_msg(struct msg_queue *msq, long *msgtyp, int mode)
+{
+ struct msg_msg *msg;
+ long count = 0;
+
+ list_for_each_entry(msg, &msq->q_messages, m_list) {
+ if (testmsg(msg, *msgtyp, mode) &&
+ !security_msg_queue_msgrcv(msq, msg, current,
+ *msgtyp, mode)) {
+ if (mode == SEARCH_LESSEQUAL && msg->m_type != 1) {
+ *msgtyp = msg->m_type - 1;
+ } else if (mode == SEARCH_NUMBER) {
+ if (*msgtyp == count)
+ return msg;
+ } else
+ return msg;
+ count++;
+ }
+ }
+
+ return ERR_PTR(-EAGAIN);
+}
+
+
long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
int msgflg,
long (*msg_handler)(void __user *, struct msg_msg *, size_t))
int mode;
struct ipc_namespace *ns;
struct msg_msg *copy = NULL;
- unsigned long copy_number = 0;
ns = current->nsproxy->ipc_ns;
if (msqid < 0 || (long) bufsz < 0)
return -EINVAL;
if (msgflg & MSG_COPY) {
- copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax),
- msgflg, &msgtyp, ©_number);
+ copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax));
if (IS_ERR(copy))
return PTR_ERR(copy);
}
for (;;) {
struct msg_receiver msr_d;
- struct list_head *tmp;
- long msg_counter = 0;
msg = ERR_PTR(-EACCES);
if (ipcperms(ns, &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) {
- msgtyp = walk_msg->m_type - 1;
- } else if (msgflg & MSG_COPY) {
- if (copy_number == msg_counter) {
- /*
- * Found requested message.
- * Copy it.
- */
- msg = copy_msg(msg, copy);
- if (IS_ERR(msg))
- goto out_unlock;
- break;
- }
- msg = ERR_PTR(-EAGAIN);
- } else
- break;
- msg_counter++;
- }
- tmp = tmp->next;
- }
+ msg = find_msg(msq, &msgtyp, mode);
+
if (!IS_ERR(msg)) {
/*
* Found a suitable message.
* If we are copying, then do not unlink message and do
* not update queue parameters.
*/
- if (msgflg & MSG_COPY)
+ if (msgflg & MSG_COPY) {
+ msg = copy_msg(msg, copy);
goto out_unlock;
+ }
list_del(&msg->m_list);
msq->q_qnum--;
msq->q_rtime = get_seconds();