aboutsummaryrefslogtreecommitdiff
path: root/ipc/msg.c
diff options
context:
space:
mode:
Diffstat (limited to 'ipc/msg.c')
-rw-r--r--ipc/msg.c706
1 files changed, 420 insertions, 286 deletions
diff --git a/ipc/msg.c b/ipc/msg.c
index 747b65507a9..c5d8e374998 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -39,12 +39,10 @@
#include <linux/ipc_namespace.h>
#include <asm/current.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
#include "util.h"
-/*
- * one msg_receiver structure for each sleeping receiver:
- */
+/* one msg_receiver structure for each sleeping receiver */
struct msg_receiver {
struct list_head r_list;
struct task_struct *r_tsk;
@@ -53,6 +51,12 @@ struct msg_receiver {
long r_msgtype;
long r_maxsize;
+ /*
+ * Mark r_msg volatile so that the compiler
+ * does not try to get smart and optimize
+ * it. We rely on this for the lockless
+ * receive algorithm.
+ */
struct msg_msg *volatile r_msg;
};
@@ -66,101 +70,27 @@ struct msg_sender {
#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])
-#define msg_unlock(msq) ipc_unlock(&(msq)->q_perm)
-
-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
-
-/*
- * 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)
-{
- 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;
-}
-
-void msg_init_ns(struct ipc_namespace *ns)
-{
- ns->msg_ctlmax = MSGMAX;
- ns->msg_ctlmnb = MSGMNB;
-
- recompute_msgmni(ns);
-
- 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)
+static inline struct msg_queue *msq_obtain_object(struct ipc_namespace *ns, int id)
{
- 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);
-
- 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);
+ struct kern_ipc_perm *ipcp = ipc_obtain_object(&msg_ids(ns), id);
if (IS_ERR(ipcp))
- return (struct msg_queue *)ipcp;
+ return ERR_CAST(ipcp);
return container_of(ipcp, struct msg_queue, q_perm);
}
-static inline struct msg_queue *msg_lock_check(struct ipc_namespace *ns,
- int id)
+static inline struct msg_queue *msq_obtain_object_check(struct ipc_namespace *ns,
+ int id)
{
- struct kern_ipc_perm *ipcp = ipc_lock_check(&msg_ids(ns), id);
+ struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&msg_ids(ns), id);
if (IS_ERR(ipcp))
- return (struct msg_queue *)ipcp;
+ return ERR_CAST(ipcp);
return container_of(ipcp, struct msg_queue, q_perm);
}
@@ -170,12 +100,21 @@ static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s)
ipc_rmid(&msg_ids(ns), &s->q_perm);
}
+static void msg_rcu_free(struct rcu_head *head)
+{
+ struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+ struct msg_queue *msq = ipc_rcu_to_struct(p);
+
+ security_msg_queue_free(msq);
+ ipc_rcu_free(head);
+}
+
/**
* 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)
+ * Called with msg_ids.rwsem held (writer)
*/
static int newque(struct ipc_namespace *ns, struct ipc_params *params)
{
@@ -194,17 +133,14 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params)
msq->q_perm.security = NULL;
retval = security_msg_queue_alloc(msq);
if (retval) {
- ipc_rcu_putref(msq);
+ ipc_rcu_putref(msq, ipc_rcu_free);
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);
- ipc_rcu_putref(msq);
+ ipc_rcu_putref(msq, msg_rcu_free);
return id;
}
@@ -217,7 +153,8 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params)
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;
}
@@ -225,7 +162,7 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params)
static inline void ss_add(struct msg_queue *msq, struct msg_sender *mss)
{
mss->tsk = current;
- current->state = TASK_INTERRUPTIBLE;
+ __set_current_state(TASK_INTERRUPTIBLE);
list_add_tail(&mss->list, &msq->q_senders);
}
@@ -237,14 +174,9 @@ static inline void ss_del(struct msg_sender *mss)
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);
@@ -253,16 +185,17 @@ static void ss_wakeup(struct list_head *h, int kill)
static void expunge_all(struct msg_queue *msq, int res)
{
- 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;
- msr->r_msg = NULL;
+ list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) {
+ msr->r_msg = NULL; /* initialize expunge ordering */
wake_up_process(msr->r_tsk);
+ /*
+ * Ensure that the wakeup is visible before setting r_msg as
+ * the receiving end depends on it: either spinning on a nil,
+ * or dealing with -EAGAIN cases. See lockless receive part 1
+ * and 2 in do_msgrcv().
+ */
smp_mb();
msr->r_msg = ERR_PTR(res);
}
@@ -273,34 +206,30 @@ static void expunge_all(struct msg_queue *msq, int res)
* 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.
+ * msg_ids.rwsem (writer) and the spinlock for this message queue are held
+ * before freeque() is called. msg_ids.rwsem remains locked on exit.
*/
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);
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);
+ ipc_unlock_object(&msq->q_perm);
+ rcu_read_unlock();
- tmp = tmp->next;
+ list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) {
atomic_dec(&ns->msg_hdrs);
free_msg(msg);
}
atomic_sub(msq->q_cbytes, &ns->msg_bytes);
- security_msg_queue_free(msq);
- ipc_rcu_putref(msq);
+ ipc_rcu_putref(msq, msg_rcu_free);
}
/*
- * Called with msg_ids.rw_mutex and ipcp locked.
+ * Called with msg_ids.rwsem and ipcp locked.
*/
static inline int msg_security(struct kern_ipc_perm *ipcp, int msgflg)
{
@@ -312,15 +241,14 @@ static inline int msg_security(struct kern_ipc_perm *ipcp, int msgflg)
SYSCALL_DEFINE2(msgget, key_t, key, int, msgflg)
{
struct ipc_namespace *ns;
- struct ipc_ops msg_ops;
+ static const struct ipc_ops msg_ops = {
+ .getnew = newque,
+ .associate = msg_security,
+ };
struct ipc_params msg_params;
ns = current->nsproxy->ipc_ns;
- msg_ops.getnew = newque;
- msg_ops.associate = msg_security;
- msg_ops.more_checks = NULL;
-
msg_params.key = key;
msg_params.flg = msgflg;
@@ -330,7 +258,7 @@ SYSCALL_DEFINE2(msgget, key_t, key, int, msgflg)
static inline unsigned long
copy_msqid_to_user(void __user *buf, struct msqid64_ds *in, int version)
{
- switch(version) {
+ switch (version) {
case IPC_64:
return copy_to_user(buf, in, sizeof(*in));
case IPC_OLD:
@@ -375,7 +303,7 @@ copy_msqid_to_user(void __user *buf, struct msqid64_ds *in, int version)
static inline unsigned long
copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version)
{
- switch(version) {
+ switch (version) {
case IPC_64:
if (copy_from_user(out, buf, sizeof(*out)))
return -EFAULT;
@@ -387,9 +315,9 @@ copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version)
if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old)))
return -EFAULT;
- 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;
+ 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->msg_qbytes = tbuf_old.msg_lqbytes;
@@ -404,9 +332,9 @@ copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version)
}
/*
- * This function handles some msgctl commands which require the rw_mutex
+ * This function handles some msgctl commands which require the rwsem
* to be held in write mode.
- * NOTE: no locks must be held, the rw_mutex is taken inside this function.
+ * NOTE: no locks must be held, the rwsem is taken inside this function.
*/
static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
struct msqid_ds __user *buf, int version)
@@ -421,31 +349,42 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
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);
+ down_write(&msg_ids(ns).rwsem);
+ 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_unlock0;
+
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.
@@ -458,25 +397,23 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
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);
+ up_write(&msg_ids(ns).rwsem);
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:
@@ -487,6 +424,7 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
if (!buf)
return -EFAULT;
+
/*
* We must not return kernel stack data.
* due to padding, it's not enough
@@ -502,7 +440,7 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
msginfo.msgmnb = ns->msg_ctlmnb;
msginfo.msgssz = MSGSSZ;
msginfo.msgseg = MSGSEG;
- down_read(&msg_ids(ns).rw_mutex);
+ down_read(&msg_ids(ns).rwsem);
if (cmd == MSG_INFO) {
msginfo.msgpool = msg_ids(ns).in_use;
msginfo.msgmap = atomic_read(&ns->msg_hdrs);
@@ -513,12 +451,13 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
msginfo.msgtql = MSGTQL;
}
max_id = ipc_get_maxid(&msg_ids(ns));
- up_read(&msg_ids(ns).rw_mutex);
+ up_read(&msg_ids(ns).rwsem);
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 MSG_STAT:
case IPC_STAT:
{
struct msqid64_ds tbuf;
@@ -527,27 +466,33 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
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(&msq->q_perm, S_IRUGO))
+ if (ipcperms(ns, &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;
@@ -557,71 +502,97 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
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:
+ switch (mode) {
+ case SEARCH_ANY:
+ case SEARCH_NUMBER:
+ return 1;
+ case SEARCH_LESSEQUAL:
+ if (msg->m_type <= type)
return 1;
- case SEARCH_LESSEQUAL:
- if (msg->m_type <=type)
- return 1;
- break;
- case SEARCH_EQUAL:
- if (msg->m_type == type)
- return 1;
- break;
- case SEARCH_NOTEQUAL:
- if (msg->m_type != type)
- return 1;
- break;
+ break;
+ case SEARCH_EQUAL:
+ if (msg->m_type == type)
+ return 1;
+ break;
+ case SEARCH_NOTEQUAL:
+ if (msg->m_type != type)
+ return 1;
+ break;
}
return 0;
}
static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg)
{
- 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) {
if (testmsg(msg, msr->r_msgtype, msr->r_mode) &&
!security_msg_queue_msgrcv(msq, msg, msr->r_tsk,
msr->r_msgtype, msr->r_mode)) {
list_del(&msr->r_list);
if (msr->r_maxsize < msg->m_ts) {
+ /* initialize pipelined send ordering */
msr->r_msg = NULL;
wake_up_process(msr->r_tsk);
- smp_mb();
+ smp_mb(); /* see barrier comment below */
msr->r_msg = ERR_PTR(-E2BIG);
} else {
msr->r_msg = NULL;
msq->q_lrpid = task_pid_vnr(msr->r_tsk);
msq->q_rtime = get_seconds();
wake_up_process(msr->r_tsk);
+ /*
+ * Ensure that the wakeup is visible before
+ * setting r_msg, as the receiving end depends
+ * on it. See lockless receive part 1 and 2 in
+ * do_msgrcv().
+ */
smp_mb();
msr->r_msg = msg;
@@ -629,6 +600,7 @@ static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg)
}
}
}
+
return 0;
}
@@ -654,22 +626,31 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
msg->m_type = mtype;
msg->m_ts = msgsz;
- msq = msg_lock_check(ns, msqid);
+ rcu_read_lock();
+ msq = msq_obtain_object_check(ns, msqid);
if (IS_ERR(msq)) {
err = PTR_ERR(msq);
- goto out_free;
+ goto out_unlock1;
}
+ ipc_lock_object(&msq->q_perm);
+
for (;;) {
struct msg_sender s;
err = -EACCES;
- if (ipcperms(&msq->q_perm, S_IWUGO))
- goto out_unlock_free;
+ if (ipcperms(ns, &msq->q_perm, S_IWUGO))
+ goto out_unlock0;
+
+ /* raced with RMID? */
+ if (!ipc_valid_object(&msq->q_perm)) {
+ err = -EIDRM;
+ goto out_unlock0;
+ }
err = security_msg_queue_msgsnd(msq, msg, msgflg);
if (err)
- goto out_unlock_free;
+ goto out_unlock0;
if (msgsz + msq->q_cbytes <= msq->q_qbytes &&
1 + msq->q_qnum <= msq->q_qbytes) {
@@ -679,32 +660,44 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
/* queue full, wait: */
if (msgflg & IPC_NOWAIT) {
err = -EAGAIN;
- goto out_unlock_free;
+ goto out_unlock0;
}
+
+ /* enqueue the sender and prepare to block */
ss_add(msq, &s);
- ipc_rcu_getref(msq);
- msg_unlock(msq);
+
+ if (!ipc_rcu_getref(msq)) {
+ err = -EIDRM;
+ goto out_unlock0;
+ }
+
+ ipc_unlock_object(&msq->q_perm);
+ rcu_read_unlock();
schedule();
- ipc_lock_by_ptr(&msq->q_perm);
- ipc_rcu_putref(msq);
- if (msq->q_perm.deleted) {
+ rcu_read_lock();
+ ipc_lock_object(&msq->q_perm);
+
+ ipc_rcu_putref(msq, ipc_rcu_free);
+ /* raced with RMID? */
+ if (!ipc_valid_object(&msq->q_perm)) {
err = -EIDRM;
- goto out_unlock_free;
+ goto out_unlock0;
}
+
ss_del(&s);
if (signal_pending(current)) {
err = -ERESTARTNOHAND;
- goto out_unlock_free;
+ goto out_unlock0;
}
- }
+ }
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 */
+ /* no one is waiting for this message, enqueue it */
list_add_tail(&msg->m_list, &msq->q_messages);
msq->q_cbytes += msgsz;
msq->q_qnum++;
@@ -715,9 +708,10 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
err = 0;
msg = NULL;
-out_unlock_free:
- msg_unlock(msq);
-out_free:
+out_unlock0:
+ ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+ rcu_read_unlock();
if (msg != NULL)
free_msg(msg);
return err;
@@ -735,6 +729,8 @@ SYSCALL_DEFINE4(msgsnd, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
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.
@@ -752,62 +748,142 @@ static inline int convert_mode(long *msgtyp, int msgflg)
return SEARCH_EQUAL;
}
-long do_msgrcv(int msqid, long *pmtype, void __user *mtext,
- size_t msgsz, long msgtyp, int msgflg)
+static long do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz)
+{
+ struct msgbuf __user *msgp = dest;
+ size_t msgsz;
+
+ if (put_user(msg->m_type, &msgp->mtype))
+ return -EFAULT;
+
+ msgsz = (bufsz > msg->m_ts) ? msg->m_ts : bufsz;
+ if (store_msg(msgp->mtext, msg, msgsz))
+ return -EFAULT;
+ return msgsz;
+}
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
+/*
+ * 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)
+{
+ struct msg_msg *copy;
+
+ /*
+ * Create dummy message to copy real message to.
+ */
+ copy = load_msg(buf, bufsz);
+ if (!IS_ERR(copy))
+ copy->m_ts = bufsz;
+ return copy;
+}
+
+static inline void free_copy(struct msg_msg *copy)
+{
+ if (copy)
+ free_msg(copy);
+}
+#else
+static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz)
+{
+ return ERR_PTR(-ENOSYS);
+}
+
+static inline void free_copy(struct msg_msg *copy)
+{
+}
+#endif
+
+static struct msg_msg *find_msg(struct msg_queue *msq, long *msgtyp, int mode)
+{
+ struct msg_msg *msg, *found = NULL;
+ 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;
+ found = msg;
+ } else if (mode == SEARCH_NUMBER) {
+ if (*msgtyp == count)
+ return msg;
+ } else
+ return msg;
+ count++;
+ }
+ }
+
+ return found ?: 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))
{
- struct msg_queue *msq;
- struct msg_msg *msg;
int mode;
+ struct msg_queue *msq;
struct ipc_namespace *ns;
+ struct msg_msg *msg, *copy = NULL;
+
+ ns = current->nsproxy->ipc_ns;
- if (msqid < 0 || (long) msgsz < 0)
+ if (msqid < 0 || (long) bufsz < 0)
return -EINVAL;
+
+ if (msgflg & MSG_COPY) {
+ if ((msgflg & MSG_EXCEPT) || !(msgflg & IPC_NOWAIT))
+ return -EINVAL;
+ copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax));
+ if (IS_ERR(copy))
+ return PTR_ERR(copy);
+ }
mode = convert_mode(&msgtyp, msgflg);
- ns = current->nsproxy->ipc_ns;
- msq = msg_lock_check(ns, msqid);
- if (IS_ERR(msq))
+ rcu_read_lock();
+ msq = msq_obtain_object_check(ns, msqid);
+ if (IS_ERR(msq)) {
+ rcu_read_unlock();
+ free_copy(copy);
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;
+ if (ipcperms(ns, &msq->q_perm, S_IRUGO))
+ goto out_unlock1;
- 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;
+ ipc_lock_object(&msq->q_perm);
+
+ /* raced with RMID? */
+ if (!ipc_valid_object(&msq->q_perm)) {
+ msg = ERR_PTR(-EIDRM);
+ goto out_unlock0;
}
+
+ msg = find_msg(msq, &msgtyp, mode);
if (!IS_ERR(msg)) {
/*
* Found a suitable message.
* Unlink it from the queue.
*/
- if ((msgsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) {
+ if ((bufsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) {
msg = ERR_PTR(-E2BIG);
- goto out_unlock;
+ goto out_unlock0;
}
+ /*
+ * If we are copying, then do not unlink message and do
+ * not update queue parameters.
+ */
+ if (msgflg & MSG_COPY) {
+ msg = copy_msg(msg, copy);
+ goto out_unlock0;
+ }
+
list_del(&msg->m_list);
msq->q_qnum--;
msq->q_rtime = get_seconds();
@@ -816,14 +892,16 @@ long do_msgrcv(int msqid, long *pmtype, void __user *mtext,
atomic_sub(msg->m_ts, &ns->msg_bytes);
atomic_dec(&ns->msg_hdrs);
ss_wakeup(&msq->q_senders, 0);
- msg_unlock(msq);
- break;
+
+ goto out_unlock0;
}
+
/* No message waiting. Wait for a message */
if (msgflg & IPC_NOWAIT) {
msg = ERR_PTR(-ENOMSG);
- goto out_unlock;
+ goto out_unlock0;
}
+
list_add_tail(&msr_d.r_list, &msq->q_receivers);
msr_d.r_tsk = current;
msr_d.r_msgtype = msgtyp;
@@ -831,22 +909,23 @@ long do_msgrcv(int msqid, long *pmtype, void __user *mtext,
if (msgflg & MSG_NOERROR)
msr_d.r_maxsize = INT_MAX;
else
- msr_d.r_maxsize = msgsz;
+ msr_d.r_maxsize = bufsz;
msr_d.r_msg = ERR_PTR(-EAGAIN);
- current->state = TASK_INTERRUPTIBLE;
- msg_unlock(msq);
+ __set_current_state(TASK_INTERRUPTIBLE);
+ ipc_unlock_object(&msq->q_perm);
+ rcu_read_unlock();
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:
+ * existence 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().
+ * and acquiring the q_perm.lock in ipc_lock_object().
*/
rcu_read_lock();
@@ -855,7 +934,7 @@ long do_msgrcv(int msqid, long *pmtype, void __user *mtext,
* wake_up_process(). There is a race with exit(), see
* ipc/mqueue.c for the details.
*/
- msg = (struct msg_msg*)msr_d.r_msg;
+ msg = (struct msg_msg *)msr_d.r_msg;
while (msg == NULL) {
cpu_relax();
msg = (struct msg_msg *)msr_d.r_msg;
@@ -865,63 +944,106 @@ long do_msgrcv(int msqid, long *pmtype, void __user *mtext,
* If there is a message or an error then accept it without
* locking.
*/
- if (msg != ERR_PTR(-EAGAIN)) {
- rcu_read_unlock();
- break;
- }
+ if (msg != ERR_PTR(-EAGAIN))
+ goto out_unlock1;
/* Lockless receive, part 3:
* Acquire the queue spinlock.
*/
- ipc_lock_by_ptr(&msq->q_perm);
- rcu_read_unlock();
+ ipc_lock_object(&msq->q_perm);
/* Lockless receive, part 4:
* Repeat test after acquiring the spinlock.
*/
- msg = (struct msg_msg*)msr_d.r_msg;
+ msg = (struct msg_msg *)msr_d.r_msg;
if (msg != ERR_PTR(-EAGAIN))
- goto out_unlock;
+ goto out_unlock0;
list_del(&msr_d.r_list);
if (signal_pending(current)) {
msg = ERR_PTR(-ERESTARTNOHAND);
-out_unlock:
- msg_unlock(msq);
- break;
+ goto out_unlock0;
}
+
+ ipc_unlock_object(&msq->q_perm);
}
- 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;
+out_unlock0:
+ ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+ rcu_read_unlock();
+ if (IS_ERR(msg)) {
+ free_copy(copy);
+ return PTR_ERR(msg);
+ }
+ bufsz = msg_handler(buf, msg, bufsz);
free_msg(msg);
- return msgsz;
+ return bufsz;
}
SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
long, msgtyp, int, msgflg)
{
- long err, mtype;
+ return do_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg, do_msg_fill);
+}
- err = do_msgrcv(msqid, &mtype, msgp->mtext, msgsz, msgtyp, msgflg);
- if (err < 0)
- goto out;
+/*
+ * 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)
+{
+ struct sysinfo i;
+ unsigned long allowed;
+ int nb_ns;
- if (put_user(mtype, &msgp->mtype))
- err = -EFAULT;
-out:
- return err;
+ 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;
+}
+
+void msg_init_ns(struct ipc_namespace *ns)
+{
+ ns->msg_ctlmax = MSGMAX;
+ ns->msg_ctlmnb = MSGMNB;
+
+ recompute_msgmni(ns);
+
+ 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)
+{
+ free_ipcs(ns, &msg_ids(ns), freeque);
+ idr_destroy(&ns->ids[IPC_MSG_IDS].ipcs_idr);
}
+#endif
#ifdef CONFIG_PROC_FS
static int sysvipc_msg_proc_show(struct seq_file *s, void *it)
{
+ struct user_namespace *user_ns = seq_user_ns(s);
struct msg_queue *msq = it;
return seq_printf(s,
@@ -933,12 +1055,24 @@ static int sysvipc_msg_proc_show(struct seq_file *s, void *it)
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,
+ from_kuid_munged(user_ns, msq->q_perm.uid),
+ from_kgid_munged(user_ns, msq->q_perm.gid),
+ from_kuid_munged(user_ns, msq->q_perm.cuid),
+ from_kgid_munged(user_ns, msq->q_perm.cgid),
msq->q_stime,
msq->q_rtime,
msq->q_ctime);
}
#endif
+
+void __init msg_init(void)
+{
+ 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);
+}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-04 01:26:37 +0000