asmlinkage long sys_msgget (key_t key, int msgflg)
{
int id, ret = -EPERM;
struct msg_queue *msq;
down(&msg_ids.sem);
if (key == IPC_PRIVATE)
ret = newque(key, msgflg);
else if ((id = ipc_findkey(&msg_ids, key)) == -1) { /* key not used */
if (!(msgflg & IPC_CREAT))
ret = -ENOENT;
else
ret = newque(key, msgflg);
} else if (msgflg & IPC_CREAT && msgflg & IPC_EXCL) {
ret = -EEXIST;
} else {
msq = msg_lock(id);
if(msq==NULL)
BUG();
if (ipcperms(&msq->q_perm, msgflg))
ret = -EACCES;
else
ret = msg_buildid(id, msq->q_perm.seq);
msg_unlock(id);
}
up(&msg_ids.sem);
TRACE_IPC(TRACE_EV_IPC_MSG_CREATE, ret, msgflg);
return ret;
}
static int sysvipc_msg_read_proc(char *buffer, char **start, off_t offset, int length, int *eof, void *data)
{
off_t pos = 0;
off_t begin = 0;
int i, len = 0;
down(&msg_ids.sem);
len += sprintf(buffer, " key msqid perms cbytes qnum lspid lrpid uid gid cuid cgid stime rtime ctime\n");
for(i = 0; i <= msg_ids.max_id; i++) {
struct msg_queue * msq;
msq = msg_lock(i);
if(msq != NULL) {
len += sprintf(buffer + len, "%10d %10d %4o %10lu %10lu %5u %5u %5u %5u %5u %5u %10lu %10lu %10lu\n",
msq->q_perm.key,
msg_buildid(i,msq->q_perm.seq),
msq->q_perm.mode,
msq->q_cbytes,
msq->q_qnum,
msq->q_lspid,
msq->q_lrpid,
msq->q_perm.uid,
msq->q_perm.gid,
msq->q_perm.cuid,
msq->q_perm.cgid,
msq->q_stime,
msq->q_rtime,
msq->q_ctime);
msg_unlock(i);
pos += len;
if(pos < offset) {
len = 0;
begin = pos;
}
if(pos > offset + length)
goto done;
}
}
*eof = 1;
done:
up(&msg_ids.sem);
*start = buffer + (offset - begin);
len -= (offset - begin);
if(len > length)
len = length;
if(len < 0)
len = 0;
return len;
}
void msg_exit_ns(struct ipc_namespace *ns)
{
int i;
struct msg_queue *msq;
mutex_lock(&msg_ids(ns).mutex);
for (i = 0; i <= msg_ids(ns).max_id; i++) {
msq = msg_lock(ns, i);
if (msq == NULL)
continue;
freeque(ns, msq, i);
}
mutex_unlock(&msg_ids(ns).mutex);
ipc_fini_ids(ns->ids[IPC_MSG_IDS]);
kfree(ns->ids[IPC_MSG_IDS]);
ns->ids[IPC_MSG_IDS] = NULL;
}
asmlinkage long sys_msgget(key_t key, int msgflg)
{
struct msg_queue *msq;
int id, ret = -EPERM;
struct ipc_namespace *ns;
ns = current->nsproxy->ipc_ns;
mutex_lock(&msg_ids(ns).mutex);
if (key == IPC_PRIVATE)
ret = newque(ns, key, msgflg);
else if ((id = ipc_findkey(&msg_ids(ns), key)) == -1) { /* key not used */
if (!(msgflg & IPC_CREAT))
ret = -ENOENT;
else
ret = newque(ns, key, msgflg);
} else if (msgflg & IPC_CREAT && msgflg & IPC_EXCL) {
ret = -EEXIST;
} else {
msq = msg_lock(ns, id);
BUG_ON(msq == NULL);
if (ipcperms(&msq->q_perm, msgflg))
ret = -EACCES;
else {
int qid = msg_buildid(ns, id, msq->q_perm.seq);
ret = security_msg_queue_associate(msq, msgflg);
if (!ret)
ret = qid;
}
msg_unlock(msq);
}
mutex_unlock(&msg_ids(ns).mutex);
return ret;
}
int msg_callback(int mode, struct kern_ipc_perm *ipc, struct ipc_namespace *ns)
{
switch(mode) {
case 0:
printf("key msqid owner perms used-bytes messages\n");
break;
case 1:
{
struct msg_queue *msg = msg_lock(ns, ipc->id);
printf("0x%08x %-10d %-10d %-10o %-12ld %-12ld\n",
ipc->key,
ipc->id,
ipc->uid,
ipc->mode & 0777,
msg->q_cbytes,
msg->q_qnum);
}
break;
case 2:
break;
}
return 1;
}
SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
{
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:
case MSG_INFO:
{
struct msginfo msginfo;
int max_id;
if (!buf)
return -EFAULT;
/*
* We must not return kernel stack data.
* due to padding, it's not enough
* to set all member fields.
*/
err = security_msg_queue_msgctl(NULL, cmd);
if (err)
return err;
memset(&msginfo, 0, sizeof(msginfo));
msginfo.msgmni = ns->msg_ctlmni;
msginfo.msgmax = ns->msg_ctlmax;
msginfo.msgmnb = ns->msg_ctlmnb;
msginfo.msgssz = MSGSSZ;
msginfo.msgseg = MSGSEG;
down_read(&msg_ids(ns).rw_mutex);
if (cmd == MSG_INFO) {
msginfo.msgpool = msg_ids(ns).in_use;
msginfo.msgmap = atomic_read(&ns->msg_hdrs);
msginfo.msgtql = atomic_read(&ns->msg_bytes);
} else {
msginfo.msgmap = MSGMAP;
msginfo.msgpool = MSGPOOL;
msginfo.msgtql = MSGTQL;
}
max_id = ipc_get_maxid(&msg_ids(ns));
up_read(&msg_ids(ns).rw_mutex);
if (copy_to_user(buf, &msginfo, sizeof(struct msginfo)))
return -EFAULT;
return (max_id < 0) ? 0 : max_id;
}
case MSG_STAT: /* msqid is an index rather than a msg queue id */
case IPC_STAT:
{
struct msqid64_ds tbuf;
int success_return;
if (!buf)
return -EFAULT;
if (cmd == MSG_STAT) {
msq = msg_lock(ns, msqid);
if (IS_ERR(msq))
return PTR_ERR(msq);
success_return = msq->q_perm.id;
} else {
msq = msg_lock_check(ns, msqid);
if (IS_ERR(msq))
return PTR_ERR(msq);
success_return = 0;
}
err = -EACCES;
if (ipcperms(&msq->q_perm, S_IRUGO))
goto out_unlock;
err = security_msg_queue_msgctl(msq, cmd);
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_ctime = msq->q_ctime;
tbuf.msg_cbytes = msq->q_cbytes;
tbuf.msg_qnum = msq->q_qnum;
tbuf.msg_qbytes = msq->q_qbytes;
tbuf.msg_lspid = msq->q_lspid;
tbuf.msg_lrpid = msq->q_lrpid;
msg_unlock(msq);
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;
}
out_unlock:
msg_unlock(msq);
return err;
}
asmlinkage long sys_msgrcv (int msqid, struct msgbuf *msgp, size_t msgsz,
long msgtyp, int msgflg)
{
struct msg_queue *msq;
struct msg_receiver msr_d;
struct list_head* tmp;
struct msg_msg* msg, *found_msg;
int err;
int mode;
if (msqid < 0 || (long) msgsz < 0)
return -EINVAL;
mode = convert_mode(&msgtyp,msgflg);
msq = msg_lock(msqid);
if(msq==NULL)
return -EINVAL;
retry:
err = -EIDRM;
if (msg_checkid(msq,msqid))
goto out_unlock;
err=-EACCES;
if (ipcperms (&msq->q_perm, S_IRUGO))
goto out_unlock;
tmp = msq->q_messages.next;
found_msg=NULL;
while (tmp != &msq->q_messages) {
msg = list_entry(tmp,struct msg_msg,m_list);
if(testmsg(msg,msgtyp,mode)) {
found_msg = msg;
if(mode == SEARCH_LESSEQUAL && msg->m_type != 1) {
found_msg=msg;
msgtyp=msg->m_type-1;
} else {
found_msg=msg;
break;
}
}
tmp = tmp->next;
}
if(found_msg) {
msg=found_msg;
if ((msgsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) {
err=-E2BIG;
goto out_unlock;
}
list_del(&msg->m_list);
msq->q_qnum--;
msq->q_rtime = CURRENT_TIME;
msq->q_lrpid = current->pid;
msq->q_cbytes -= msg->m_ts;
atomic_sub(msg->m_ts,&msg_bytes);
atomic_dec(&msg_hdrs);
ss_wakeup(&msq->q_senders,0);
msg_unlock(msqid);
out_success:
msgsz = (msgsz > msg->m_ts) ? msg->m_ts : msgsz;
if (put_user (msg->m_type, &msgp->mtype) ||
store_msg(msgp->mtext, msg, msgsz)) {
msgsz = -EFAULT;
}
free_msg(msg);
return msgsz;
} else
{
struct msg_queue *t;
/* no message waiting. Prepare for pipelined
* receive.
*/
if (msgflg & IPC_NOWAIT) {
err=-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(msqid);
schedule();
current->state = TASK_RUNNING;
/* This introduces a race so we must always take
the slow path
msg = (struct msg_msg*) msr_d.r_msg;
if(!IS_ERR(msg))
goto out_success;
*/
t = msg_lock(msqid);
if(t==NULL)
msqid=-1;
msg = (struct msg_msg*)msr_d.r_msg;
if(!IS_ERR(msg)) {
/* our message arived while we waited for
* the spinlock. Process it.
*/
if(msqid!=-1)
msg_unlock(msqid);
goto out_success;
}
err = PTR_ERR(msg);
if(err == -EAGAIN) {
if(msqid==-1)
BUG();
list_del(&msr_d.r_list);
if (signal_pending(current))
err=-EINTR;
else
goto retry;
}
}
out_unlock:
if(msqid!=-1)
msg_unlock(msqid);
return err;
}
asmlinkage long sys_msgsnd (int msqid, struct msgbuf *msgp, size_t msgsz, int msgflg)
{
struct msg_queue *msq;
struct msg_msg *msg;
long mtype;
int err;
if (msgsz > msg_ctlmax || (long) msgsz < 0 || msqid < 0)
return -EINVAL;
if (get_user(mtype, &msgp->mtype))
return -EFAULT;
if (mtype < 1)
return -EINVAL;
msg = load_msg(msgp->mtext, msgsz);
if(IS_ERR(msg))
return PTR_ERR(msg);
msg->m_type = mtype;
msg->m_ts = msgsz;
msq = msg_lock(msqid);
err=-EINVAL;
if(msq==NULL)
goto out_free;
retry:
err= -EIDRM;
if (msg_checkid(msq,msqid))
goto out_unlock_free;
err=-EACCES;
if (ipcperms(&msq->q_perm, S_IWUGO))
goto out_unlock_free;
if(msgsz + msq->q_cbytes > msq->q_qbytes ||
1 + msq->q_qnum > msq->q_qbytes) {
struct msg_sender s;
if(msgflg&IPC_NOWAIT) {
err=-EAGAIN;
goto out_unlock_free;
}
ss_add(msq, &s);
msg_unlock(msqid);
schedule();
current->state= TASK_RUNNING;
msq = msg_lock(msqid);
err = -EIDRM;
if(msq==NULL)
goto out_free;
ss_del(&s);
if (signal_pending(current)) {
err=-EINTR;
goto out_unlock_free;
}
goto retry;
}
msq->q_lspid = current->pid;
msq->q_stime = CURRENT_TIME;
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,&msg_bytes);
atomic_inc(&msg_hdrs);
}
err = 0;
msg = NULL;
out_unlock_free:
msg_unlock(msqid);
out_free:
if(msg!=NULL)
free_msg(msg);
return err;
}
asmlinkage long sys_msgctl (int msqid, int cmd, struct msqid_ds *buf)
{
int err, version;
struct msg_queue *msq;
struct msq_setbuf setbuf;
struct kern_ipc_perm *ipcp;
if (msqid < 0 || cmd < 0)
return -EINVAL;
version = ipc_parse_version(&cmd);
switch (cmd) {
case IPC_INFO:
case MSG_INFO:
{
struct msginfo msginfo;
int max_id;
if (!buf)
return -EFAULT;
/* We must not return kernel stack data.
* due to padding, it's not enough
* to set all member fields.
*/
memset(&msginfo,0,sizeof(msginfo));
msginfo.msgmni = msg_ctlmni;
msginfo.msgmax = msg_ctlmax;
msginfo.msgmnb = msg_ctlmnb;
msginfo.msgssz = MSGSSZ;
msginfo.msgseg = MSGSEG;
down(&msg_ids.sem);
if (cmd == MSG_INFO) {
msginfo.msgpool = msg_ids.in_use;
msginfo.msgmap = atomic_read(&msg_hdrs);
msginfo.msgtql = atomic_read(&msg_bytes);
} else {
msginfo.msgmap = MSGMAP;
msginfo.msgpool = MSGPOOL;
msginfo.msgtql = MSGTQL;
}
max_id = msg_ids.max_id;
up(&msg_ids.sem);
if (copy_to_user (buf, &msginfo, sizeof(struct msginfo)))
return -EFAULT;
return (max_id < 0) ? 0: max_id;
}
case MSG_STAT:
case IPC_STAT:
{
struct msqid64_ds tbuf;
int success_return;
if (!buf)
return -EFAULT;
if(cmd == MSG_STAT && msqid >= msg_ids.size)
return -EINVAL;
memset(&tbuf,0,sizeof(tbuf));
msq = msg_lock(msqid);
if (msq == NULL)
return -EINVAL;
if(cmd == MSG_STAT) {
success_return = msg_buildid(msqid, msq->q_perm.seq);
} else {
err = -EIDRM;
if (msg_checkid(msq,msqid))
goto out_unlock;
success_return = 0;
}
err = -EACCES;
if (ipcperms (&msq->q_perm, S_IRUGO))
goto out_unlock;
kernel_to_ipc64_perm(&msq->q_perm, &tbuf.msg_perm);
tbuf.msg_stime = msq->q_stime;
tbuf.msg_rtime = msq->q_rtime;
tbuf.msg_ctime = msq->q_ctime;
tbuf.msg_cbytes = msq->q_cbytes;
tbuf.msg_qnum = msq->q_qnum;
tbuf.msg_qbytes = msq->q_qbytes;
tbuf.msg_lspid = msq->q_lspid;
tbuf.msg_lrpid = msq->q_lrpid;
msg_unlock(msqid);
if (copy_msqid_to_user(buf, &tbuf, version))
return -EFAULT;
return success_return;
}
case IPC_SET:
if (!buf)
return -EFAULT;
if (copy_msqid_from_user (&setbuf, buf, version))
return -EFAULT;
break;
case IPC_RMID:
break;
default:
return -EINVAL;
}
down(&msg_ids.sem);
msq = msg_lock(msqid);
err=-EINVAL;
if (msq == NULL)
goto out_up;
err = -EIDRM;
if (msg_checkid(msq,msqid))
goto out_unlock_up;
ipcp = &msq->q_perm;
err = -EPERM;
if (current->euid != ipcp->cuid &&
current->euid != ipcp->uid && !capable(CAP_SYS_ADMIN))
/* We _could_ check for CAP_CHOWN above, but we don't */
goto out_unlock_up;
switch (cmd) {
case IPC_SET:
{
if (setbuf.qbytes > msg_ctlmnb && !capable(CAP_SYS_RESOURCE))
goto out_unlock_up;
msq->q_qbytes = setbuf.qbytes;
ipcp->uid = setbuf.uid;
ipcp->gid = setbuf.gid;
ipcp->mode = (ipcp->mode & ~S_IRWXUGO) |
(S_IRWXUGO & setbuf.mode);
msq->q_ctime = CURRENT_TIME;
/* sleeping receivers might be excluded by
* stricter permissions.
*/
expunge_all(msq,-EAGAIN);
/* sleeping senders might be able to send
* due to a larger queue size.
*/
ss_wakeup(&msq->q_senders,0);
msg_unlock(msqid);
break;
}
case IPC_RMID:
freeque (msqid);
break;
}
err = 0;
out_up:
up(&msg_ids.sem);
return err;
out_unlock_up:
msg_unlock(msqid);
goto out_up;
out_unlock:
msg_unlock(msqid);
return err;
}
asmlinkage long sys_msgrcv (int msqid, struct msgbuf __user *msgp, size_t msgsz,
long msgtyp, int msgflg)
{
struct msg_queue *msq;
struct msg_receiver msr_d;
struct list_head* tmp;
struct msg_msg* msg, *found_msg;
int err;
int mode;
if (msqid < 0 || (long) msgsz < 0)
return -EINVAL;
mode = convert_mode(&msgtyp,msgflg);
msq = msg_lock(msqid);
if(msq==NULL)
return -EINVAL;
retry:
err = -EIDRM;
if (msg_checkid(msq,msqid))
goto out_unlock;
err=-EACCES;
if (ipcperms (&msq->q_perm, S_IRUGO))
goto out_unlock;
tmp = msq->q_messages.next;
found_msg=NULL;
while (tmp != &msq->q_messages) {
msg = list_entry(tmp,struct msg_msg,m_list);
if(testmsg(msg,msgtyp,mode) &&
!security_msg_queue_msgrcv(msq, msg, current, msgtyp, mode)) {
found_msg = msg;
if(mode == SEARCH_LESSEQUAL && msg->m_type != 1) {
found_msg=msg;
msgtyp=msg->m_type-1;
} else {
found_msg=msg;
break;
}
}
tmp = tmp->next;
}
if(found_msg) {
msg=found_msg;
if ((msgsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) {
err=-E2BIG;
goto out_unlock;
}
list_del(&msg->m_list);
msq->q_qnum--;
msq->q_rtime = get_seconds();
msq->q_lrpid = current->tgid;
msq->q_cbytes -= msg->m_ts;
atomic_sub(msg->m_ts,&msg_bytes);
atomic_dec(&msg_hdrs);
ss_wakeup(&msq->q_senders,0);
msg_unlock(msq);
out_success:
msgsz = (msgsz > msg->m_ts) ? msg->m_ts : msgsz;
if (put_user (msg->m_type, &msgp->mtype) ||
store_msg(msgp->mtext, msg, msgsz)) {
msgsz = -EFAULT;
}
free_msg(msg);
return msgsz;
} else
{
/* no message waiting. Prepare for pipelined
* receive.
*/
if (msgflg & IPC_NOWAIT) {
err=-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();
/*
* The below optimisation is buggy. A sleeping thread that is
* woken up checks if it got a message and if so, copies it to
* userspace and just returns without taking any locks.
* But this return to user space can be faster than the message
* send, and if the receiver immediately exits the
* wake_up_process performed by the sender will oops.
*/
#if 0
msg = (struct msg_msg*) msr_d.r_msg;
if(!IS_ERR(msg))
goto out_success;
#endif
msq = msg_lock(msqid);
msg = (struct msg_msg*)msr_d.r_msg;
if(!IS_ERR(msg)) {
/* our message arived while we waited for
* the spinlock. Process it.
*/
if(msq)
msg_unlock(msq);
goto out_success;
}
err = PTR_ERR(msg);
if(err == -EAGAIN) {
if(!msq)
BUG();
list_del(&msr_d.r_list);
if (signal_pending(current))
err=-EINTR;
else
goto retry;
}
}
out_unlock:
if(msq)
msg_unlock(msq);
return err;
}
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(ns, msqid);
if (msq == NULL)
return -EINVAL;
msg = ERR_PTR(-EIDRM);
if (msg_checkid(ns, msq, msqid))
goto out_unlock;
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 = current->tgid;
msq->q_cbytes -= msg->m_ts;
atomic_sub(msg->m_ts, &msg_bytes);
atomic_dec(&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(ns, msqid);
err = -EINVAL;
if (msq == NULL)
goto out_free;
err= -EIDRM;
if (msg_checkid(ns, msq, msqid))
goto out_unlock_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 = current->tgid;
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, &msg_bytes);
atomic_inc(&msg_hdrs);
}
err = 0;
msg = NULL;
out_unlock_free:
msg_unlock(msq);
out_free:
if (msg != NULL)
free_msg(msg);
return err;
}