*/
#include <linux/capability.h>
-#include <linux/slab.h>
#include <linux/msg.h>
#include <linux/spinlock.h>
#include <linux/init.h>
+#include <linux/mm.h>
#include <linux/proc_fs.h>
#include <linux/list.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/audit.h>
#include <linux/seq_file.h>
-#include <linux/mutex.h>
+#include <linux/rwsem.h>
#include <linux/nsproxy.h>
+#include <linux/ipc_namespace.h>
#include <asm/current.h>
#include <asm/uaccess.h>
#define SEARCH_NOTEQUAL 3
#define SEARCH_LESSEQUAL 4
-static atomic_t msg_bytes = ATOMIC_INIT(0);
-static atomic_t msg_hdrs = ATOMIC_INIT(0);
-
-static struct ipc_ids init_msg_ids;
-
-#define msg_ids(ns) (*((ns)->ids[IPC_MSG_IDS]))
+#define msg_ids(ns) ((ns)->ids[IPC_MSG_IDS])
#define msg_unlock(msq) ipc_unlock(&(msq)->q_perm)
-#define msg_buildid(ns, id, seq) \
- ipc_buildid(&msg_ids(ns), id, seq)
-static void freeque(struct ipc_namespace *, struct msg_queue *);
+static void freeque(struct ipc_namespace *, struct kern_ipc_perm *);
static int newque(struct ipc_namespace *, struct ipc_params *);
#ifdef CONFIG_PROC_FS
static int sysvipc_msg_proc_show(struct seq_file *s, void *it);
#endif
-static void __msg_init_ns(struct ipc_namespace *ns, struct ipc_ids *ids)
+/*
+ * Scale msgmni with the available lowmem size: the memory dedicated to msg
+ * queues should occupy at most 1/MSG_MEM_SCALE of lowmem.
+ * Also take into account the number of nsproxies created so far.
+ * This should be done staying within the (MSGMNI , IPCMNI/nr_ipc_ns) range.
+ */
+void recompute_msgmni(struct ipc_namespace *ns)
{
- ns->ids[IPC_MSG_IDS] = ids;
- ns->msg_ctlmax = MSGMAX;
- ns->msg_ctlmnb = MSGMNB;
- ns->msg_ctlmni = MSGMNI;
- ipc_init_ids(ids);
+ struct sysinfo i;
+ unsigned long allowed;
+ int nb_ns;
+
+ si_meminfo(&i);
+ allowed = (((i.totalram - i.totalhigh) / MSG_MEM_SCALE) * i.mem_unit)
+ / MSGMNB;
+ nb_ns = atomic_read(&nr_ipc_ns);
+ allowed /= nb_ns;
+
+ if (allowed < MSGMNI) {
+ ns->msg_ctlmni = MSGMNI;
+ return;
+ }
+
+ if (allowed > IPCMNI / nb_ns) {
+ ns->msg_ctlmni = IPCMNI / nb_ns;
+ return;
+ }
+
+ ns->msg_ctlmni = allowed;
}
-int msg_init_ns(struct ipc_namespace *ns)
+void msg_init_ns(struct ipc_namespace *ns)
{
- struct ipc_ids *ids;
+ ns->msg_ctlmax = MSGMAX;
+ ns->msg_ctlmnb = MSGMNB;
- ids = kmalloc(sizeof(struct ipc_ids), GFP_KERNEL);
- if (ids == NULL)
- return -ENOMEM;
+ recompute_msgmni(ns);
- __msg_init_ns(ns, ids);
- return 0;
+ atomic_set(&ns->msg_bytes, 0);
+ atomic_set(&ns->msg_hdrs, 0);
+ ipc_init_ids(&ns->ids[IPC_MSG_IDS]);
}
+#ifdef CONFIG_IPC_NS
void msg_exit_ns(struct ipc_namespace *ns)
{
- struct msg_queue *msq;
- int next_id;
- int total, in_use;
-
- mutex_lock(&msg_ids(ns).mutex);
-
- in_use = msg_ids(ns).in_use;
-
- for (total = 0, next_id = 0; total < in_use; next_id++) {
- msq = idr_find(&msg_ids(ns).ipcs_idr, next_id);
- if (msq == NULL)
- continue;
- ipc_lock_by_ptr(&msq->q_perm);
- freeque(ns, msq);
- total++;
- }
- mutex_unlock(&msg_ids(ns).mutex);
-
- kfree(ns->ids[IPC_MSG_IDS]);
- ns->ids[IPC_MSG_IDS] = NULL;
+ free_ipcs(ns, &msg_ids(ns), freeque);
+ idr_destroy(&ns->ids[IPC_MSG_IDS].ipcs_idr);
}
+#endif
void __init msg_init(void)
{
- __msg_init_ns(&init_ipc_ns, &init_msg_ids);
+ msg_init_ns(&init_ipc_ns);
+
+ printk(KERN_INFO "msgmni has been set to %d\n",
+ init_ipc_ns.msg_ctlmni);
+
ipc_init_proc_interface("sysvipc/msg",
" key msqid perms cbytes qnum lspid lrpid uid gid cuid cgid stime rtime ctime\n",
IPC_MSG_IDS, sysvipc_msg_proc_show);
}
+/*
+ * msg_lock_(check_) routines are called in the paths where the rw_mutex
+ * is not held.
+ */
static inline struct msg_queue *msg_lock(struct ipc_namespace *ns, int id)
{
struct kern_ipc_perm *ipcp = ipc_lock(&msg_ids(ns), id);
+ if (IS_ERR(ipcp))
+ return (struct msg_queue *)ipcp;
+
return container_of(ipcp, struct msg_queue, q_perm);
}
{
struct kern_ipc_perm *ipcp = ipc_lock_check(&msg_ids(ns), id);
+ if (IS_ERR(ipcp))
+ return (struct msg_queue *)ipcp;
+
return container_of(ipcp, struct msg_queue, q_perm);
}
ipc_rmid(&msg_ids(ns), &s->q_perm);
}
+/**
+ * newque - Create a new msg queue
+ * @ns: namespace
+ * @params: ptr to the structure that contains the key and msgflg
+ *
+ * Called with msg_ids.rw_mutex held (writer)
+ */
static int newque(struct ipc_namespace *ns, struct ipc_params *params)
{
struct msg_queue *msq;
* ipc_addid() locks msq
*/
id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
- if (id == -1) {
+ if (id < 0) {
security_msg_queue_free(msq);
ipc_rcu_putref(msq);
- return -ENOSPC;
+ return id;
}
- msq->q_perm.id = msg_buildid(ns, id, msq->q_perm.seq);
msq->q_stime = msq->q_rtime = 0;
msq->q_ctime = get_seconds();
msq->q_cbytes = msq->q_qnum = 0;
/*
* 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.
+ * removes the message queue from message queue ID IDR, and cleans up all the
+ * messages associated with this queue.
*
- * msg_ids.mutex and the spinlock for this message queue are held
- * before freeque() is called. msg_ids.mutex remains locked on exit.
+ * 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 msg_queue *msq)
+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);
struct msg_msg *msg = list_entry(tmp, struct msg_msg, m_list);
tmp = tmp->next;
- atomic_dec(&msg_hdrs);
+ atomic_dec(&ns->msg_hdrs);
free_msg(msg);
}
- atomic_sub(msq->q_cbytes, &msg_bytes);
+ atomic_sub(msq->q_cbytes, &ns->msg_bytes);
security_msg_queue_free(msq);
ipc_rcu_putref(msq);
}
+/*
+ * Called with msg_ids.rw_mutex and ipcp locked.
+ */
static inline int msg_security(struct kern_ipc_perm *ipcp, int msgflg)
{
struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm);
return security_msg_queue_associate(msq, msgflg);
}
-asmlinkage long sys_msgget(key_t key, int msgflg)
+SYSCALL_DEFINE2(msgget, key_t, key, int, msgflg)
{
struct ipc_namespace *ns;
struct ipc_ops msg_ops;
out.msg_rtime = in->msg_rtime;
out.msg_ctime = in->msg_ctime;
- if (in->msg_cbytes > USHRT_MAX)
- out.msg_cbytes = USHRT_MAX;
+ if (in->msg_cbytes > USHORT_MAX)
+ out.msg_cbytes = USHORT_MAX;
else
out.msg_cbytes = in->msg_cbytes;
out.msg_lcbytes = in->msg_cbytes;
- if (in->msg_qnum > USHRT_MAX)
- out.msg_qnum = USHRT_MAX;
+ if (in->msg_qnum > USHORT_MAX)
+ out.msg_qnum = USHORT_MAX;
else
out.msg_qnum = in->msg_qnum;
- if (in->msg_qbytes > USHRT_MAX)
- out.msg_qbytes = USHRT_MAX;
+ if (in->msg_qbytes > USHORT_MAX)
+ out.msg_qbytes = USHORT_MAX;
else
out.msg_qbytes = in->msg_qbytes;
out.msg_lqbytes = in->msg_qbytes;
}
}
-struct msq_setbuf {
- unsigned long qbytes;
- uid_t uid;
- gid_t gid;
- mode_t mode;
-};
-
static inline unsigned long
-copy_msqid_from_user(struct msq_setbuf *out, void __user *buf, int version)
+copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version)
{
switch(version) {
case IPC_64:
- {
- struct msqid64_ds tbuf;
-
- if (copy_from_user(&tbuf, buf, sizeof(tbuf)))
+ if (copy_from_user(out, buf, sizeof(*out)))
return -EFAULT;
-
- out->qbytes = tbuf.msg_qbytes;
- out->uid = tbuf.msg_perm.uid;
- out->gid = tbuf.msg_perm.gid;
- out->mode = tbuf.msg_perm.mode;
-
return 0;
- }
case IPC_OLD:
{
struct msqid_ds tbuf_old;
if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old)))
return -EFAULT;
- out->uid = tbuf_old.msg_perm.uid;
- out->gid = tbuf_old.msg_perm.gid;
- out->mode = tbuf_old.msg_perm.mode;
+ out->msg_perm.uid = tbuf_old.msg_perm.uid;
+ out->msg_perm.gid = tbuf_old.msg_perm.gid;
+ out->msg_perm.mode = tbuf_old.msg_perm.mode;
if (tbuf_old.msg_qbytes == 0)
- out->qbytes = tbuf_old.msg_lqbytes;
+ out->msg_qbytes = tbuf_old.msg_lqbytes;
else
- out->qbytes = tbuf_old.msg_qbytes;
+ out->msg_qbytes = tbuf_old.msg_qbytes;
return 0;
}
}
}
-asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf)
+/*
+ * This function handles some msgctl commands which require the rw_mutex
+ * to be held in write mode.
+ * NOTE: no locks must be held, the rw_mutex is taken inside this function.
+ */
+static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
+ struct msqid_ds __user *buf, int version)
{
struct kern_ipc_perm *ipcp;
- struct msq_setbuf uninitialized_var(setbuf);
+ struct msqid64_ds uninitialized_var(msqid64);
+ struct msg_queue *msq;
+ int err;
+
+ if (cmd == IPC_SET) {
+ if (copy_msqid_from_user(&msqid64, buf, version))
+ return -EFAULT;
+ }
+
+ ipcp = ipcctl_pre_down(&msg_ids(ns), msqid, cmd,
+ &msqid64.msg_perm, msqid64.msg_qbytes);
+ if (IS_ERR(ipcp))
+ return PTR_ERR(ipcp);
+
+ msq = container_of(ipcp, struct msg_queue, q_perm);
+
+ err = security_msg_queue_msgctl(msq, cmd);
+ if (err)
+ goto out_unlock;
+
+ switch (cmd) {
+ case IPC_RMID:
+ 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;
+ }
+
+ msq->q_qbytes = msqid64.msg_qbytes;
+
+ ipc_update_perm(&msqid64.msg_perm, ipcp);
+ msq->q_ctime = get_seconds();
+ /* 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);
+ break;
+ default:
+ err = -EINVAL;
+ }
+out_unlock:
+ msg_unlock(msq);
+out_up:
+ up_write(&msg_ids(ns).rw_mutex);
+ return err;
+}
+
+SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
+{
struct msg_queue *msq;
int err, version;
struct ipc_namespace *ns;
msginfo.msgmnb = ns->msg_ctlmnb;
msginfo.msgssz = MSGSSZ;
msginfo.msgseg = MSGSEG;
- mutex_lock(&msg_ids(ns).mutex);
+ down_read(&msg_ids(ns).rw_mutex);
if (cmd == MSG_INFO) {
msginfo.msgpool = msg_ids(ns).in_use;
- msginfo.msgmap = atomic_read(&msg_hdrs);
- msginfo.msgtql = atomic_read(&msg_bytes);
+ 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));
- mutex_unlock(&msg_ids(ns).mutex);
+ 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;
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;
+ err = msgctl_down(ns, msqid, cmd, buf, version);
+ return err;
default:
return -EINVAL;
}
- mutex_lock(&msg_ids(ns).mutex);
- msq = msg_lock_check(ns, msqid);
- if (IS_ERR(msq)) {
- err = PTR_ERR(msq);
- goto out_up;
- }
-
- ipcp = &msq->q_perm;
-
- err = audit_ipc_obj(ipcp);
- if (err)
- goto out_unlock_up;
- if (cmd == IPC_SET) {
- err = audit_ipc_set_perm(setbuf.qbytes, setbuf.uid, setbuf.gid,
- setbuf.mode);
- if (err)
- goto out_unlock_up;
- }
-
- 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;
-
- err = security_msg_queue_msgctl(msq, cmd);
- if (err)
- goto out_unlock_up;
-
- switch (cmd) {
- case IPC_SET:
- {
- err = -EPERM;
- if (setbuf.qbytes > ns->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 = get_seconds();
- /* 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(msq);
- break;
- }
- case IPC_RMID:
- freeque(ns, msq);
- break;
- }
- err = 0;
-out_up:
- mutex_unlock(&msg_ids(ns).mutex);
- return err;
-out_unlock_up:
- msg_unlock(msq);
- goto out_up;
out_unlock:
msg_unlock(msq);
return err;
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);
+ atomic_add(msgsz, &ns->msg_bytes);
+ atomic_inc(&ns->msg_hdrs);
}
err = 0;
return err;
}
-asmlinkage long
-sys_msgsnd(int msqid, struct msgbuf __user *msgp, size_t msgsz, int msgflg)
+SYSCALL_DEFINE4(msgsnd, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
+ int, msgflg)
{
long mtype;
msq->q_rtime = get_seconds();
msq->q_lrpid = task_tgid_vnr(current);
msq->q_cbytes -= msg->m_ts;
- atomic_sub(msg->m_ts, &msg_bytes);
- atomic_dec(&msg_hdrs);
+ atomic_sub(msg->m_ts, &ns->msg_bytes);
+ atomic_dec(&ns->msg_hdrs);
ss_wakeup(&msq->q_senders, 0);
msg_unlock(msq);
break;
return msgsz;
}
-asmlinkage long sys_msgrcv(int msqid, struct msgbuf __user *msgp, size_t msgsz,
- long msgtyp, int msgflg)
+SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
+ long, msgtyp, int, msgflg)
{
long err, mtype;
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff