aboutsummaryrefslogtreecommitdiff
path: root/ipc
diff options
context:
space:
mode:
Diffstat (limited to 'ipc')
-rw-r--r--ipc/ipc_sysctl.c20
-rw-r--r--ipc/mq_sysctl.c18
-rw-r--r--ipc/mqueue.c8
-rw-r--r--ipc/msg.c288
-rw-r--r--ipc/msgutil.c20
-rw-r--r--ipc/namespace.c7
-rw-r--r--ipc/sem.c702
-rw-r--r--ipc/shm.c325
-rw-r--r--ipc/util.c155
-rw-r--r--ipc/util.h38
10 files changed, 996 insertions, 585 deletions
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index 130dfece27a..b0e99deb6d0 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -62,7 +62,7 @@ static int proc_ipc_dointvec_minmax_orphans(ctl_table *table, int write,
return err;
}
-static int proc_ipc_callback_dointvec(ctl_table *table, int write,
+static int proc_ipc_callback_dointvec_minmax(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table ipc_table;
@@ -72,7 +72,7 @@ static int proc_ipc_callback_dointvec(ctl_table *table, int write,
memcpy(&ipc_table, table, sizeof(ipc_table));
ipc_table.data = get_ipc(table);
- rc = proc_dointvec(&ipc_table, write, buffer, lenp, ppos);
+ rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
if (write && !rc && lenp_bef == *lenp)
/*
@@ -152,15 +152,13 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write,
#define proc_ipc_dointvec NULL
#define proc_ipc_dointvec_minmax NULL
#define proc_ipc_dointvec_minmax_orphans NULL
-#define proc_ipc_callback_dointvec NULL
+#define proc_ipc_callback_dointvec_minmax NULL
#define proc_ipcauto_dointvec_minmax NULL
#endif
static int zero;
static int one = 1;
-#ifdef CONFIG_CHECKPOINT_RESTORE
static int int_max = INT_MAX;
-#endif
static struct ctl_table ipc_kern_table[] = {
{
@@ -198,21 +196,27 @@ static struct ctl_table ipc_kern_table[] = {
.data = &init_ipc_ns.msg_ctlmax,
.maxlen = sizeof (init_ipc_ns.msg_ctlmax),
.mode = 0644,
- .proc_handler = proc_ipc_dointvec,
+ .proc_handler = proc_ipc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &int_max,
},
{
.procname = "msgmni",
.data = &init_ipc_ns.msg_ctlmni,
.maxlen = sizeof (init_ipc_ns.msg_ctlmni),
.mode = 0644,
- .proc_handler = proc_ipc_callback_dointvec,
+ .proc_handler = proc_ipc_callback_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &int_max,
},
{
.procname = "msgmnb",
.data = &init_ipc_ns.msg_ctlmnb,
.maxlen = sizeof (init_ipc_ns.msg_ctlmnb),
.mode = 0644,
- .proc_handler = proc_ipc_dointvec,
+ .proc_handler = proc_ipc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &int_max,
},
{
.procname = "sem",
diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c
index 383d638340b..5bb8bfe6714 100644
--- a/ipc/mq_sysctl.c
+++ b/ipc/mq_sysctl.c
@@ -22,6 +22,16 @@ static void *get_mq(ctl_table *table)
return which;
}
+static int proc_mq_dointvec(ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct ctl_table mq_table;
+ memcpy(&mq_table, table, sizeof(mq_table));
+ mq_table.data = get_mq(table);
+
+ return proc_dointvec(&mq_table, write, buffer, lenp, ppos);
+}
+
static int proc_mq_dointvec_minmax(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
@@ -33,12 +43,10 @@ static int proc_mq_dointvec_minmax(ctl_table *table, int write,
lenp, ppos);
}
#else
+#define proc_mq_dointvec NULL
#define proc_mq_dointvec_minmax NULL
#endif
-static int msg_queues_limit_min = MIN_QUEUESMAX;
-static int msg_queues_limit_max = HARD_QUEUESMAX;
-
static int msg_max_limit_min = MIN_MSGMAX;
static int msg_max_limit_max = HARD_MSGMAX;
@@ -51,9 +59,7 @@ static ctl_table mq_sysctls[] = {
.data = &init_ipc_ns.mq_queues_max,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_mq_dointvec_minmax,
- .extra1 = &msg_queues_limit_min,
- .extra2 = &msg_queues_limit_max,
+ .proc_handler = proc_mq_dointvec,
},
{
.procname = "msg_max",
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index e4e47f64744..bb0248fc518 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -433,9 +433,9 @@ static int mqueue_create(struct inode *dir, struct dentry *dentry,
error = -EACCES;
goto out_unlock;
}
- if (ipc_ns->mq_queues_count >= HARD_QUEUESMAX ||
- (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
- !capable(CAP_SYS_RESOURCE))) {
+
+ if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
+ !capable(CAP_SYS_RESOURCE)) {
error = -ENOSPC;
goto out_unlock;
}
@@ -823,6 +823,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode,
error = ro;
goto out;
}
+ audit_inode_parent_hidden(name, root);
filp = do_create(ipc_ns, root->d_inode,
&path, oflag, mode,
u_attr ? &attr : NULL);
@@ -868,6 +869,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
if (IS_ERR(name))
return PTR_ERR(name);
+ audit_inode_parent_hidden(name, mnt->mnt_root);
err = mnt_want_write(mnt);
if (err)
goto out_name;
diff --git a/ipc/msg.c b/ipc/msg.c
index d0c6d967b39..52770bfde2a 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -70,8 +70,6 @@ struct msg_sender {
#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
@@ -141,27 +139,23 @@ void __init msg_init(void)
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)
+static inline struct msg_queue *msq_obtain_object(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);
}
@@ -171,12 +165,21 @@ 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)
{
@@ -195,17 +198,14 @@ 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;
}
@@ -218,7 +218,8 @@ 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;
}
@@ -264,8 +265,8 @@ 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)
{
@@ -275,19 +276,19 @@ static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
expunge_all(msq, -EIDRM);
ss_wakeup(&msq->q_senders, 1);
msg_rmid(ns, msq);
- msg_unlock(msq);
+ ipc_unlock_object(&msq->q_perm);
+ rcu_read_unlock();
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)
{
@@ -391,9 +392,9 @@ 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)
@@ -408,31 +409,39 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
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).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_unlock;
+ goto out_unlock0;
msq->q_qbytes = msqid64.msg_qbytes;
@@ -448,25 +457,23 @@ 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:
@@ -477,6 +484,7 @@ 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
@@ -492,7 +500,7 @@ 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);
@@ -503,12 +511,13 @@ 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;
@@ -517,17 +526,25 @@ 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(ns, &msq->q_perm, S_IRUGO))
goto out_unlock;
@@ -536,8 +553,6 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
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;
@@ -547,24 +562,48 @@ 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)
@@ -640,22 +679,31 @@ 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(ns, &msq->q_perm, S_IWUGO))
- goto out_unlock_free;
+ goto out_unlock0;
+
+ /* raced with RMID? */
+ if (msq->q_perm.deleted) {
+ 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) {
@@ -665,32 +713,37 @@ 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;
}
+
ss_add(msq, &s);
if (!ipc_rcu_getref(msq)) {
err = -EIDRM;
- goto out_unlock_free;
+ goto out_unlock0;
}
- msg_unlock(msq);
+ ipc_unlock_object(&msq->q_perm);
+ rcu_read_unlock();
schedule();
- ipc_lock_by_ptr(&msq->q_perm);
- ipc_rcu_putref(msq);
+ rcu_read_lock();
+ ipc_lock_object(&msq->q_perm);
+
+ ipc_rcu_putref(msq, ipc_rcu_free);
if (msq->q_perm.deleted) {
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();
@@ -706,9 +759,10 @@ 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;
@@ -795,7 +849,7 @@ static inline void free_copy(struct msg_msg *copy)
static struct msg_msg *find_msg(struct msg_queue *msq, long *msgtyp, int mode)
{
- struct msg_msg *msg;
+ struct msg_msg *msg, *found = NULL;
long count = 0;
list_for_each_entry(msg, &msq->q_messages, m_list) {
@@ -804,6 +858,7 @@ static struct msg_msg *find_msg(struct msg_queue *msq, long *msgtyp, int mode)
*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;
@@ -813,33 +868,35 @@ static struct msg_msg *find_msg(struct msg_queue *msq, long *msgtyp, int mode)
}
}
- return ERR_PTR(-EAGAIN);
+ return found ?: ERR_PTR(-EAGAIN);
}
-
-long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
- int msgflg,
+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 *copy = NULL;
+ struct msg_msg *msg, *copy = NULL;
ns = current->nsproxy->ipc_ns;
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);
- msq = msg_lock_check(ns, msqid);
+ rcu_read_lock();
+ msq = msq_obtain_object_check(ns, msqid);
if (IS_ERR(msq)) {
+ rcu_read_unlock();
free_copy(copy);
return PTR_ERR(msq);
}
@@ -849,10 +906,17 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
msg = ERR_PTR(-EACCES);
if (ipcperms(ns, &msq->q_perm, S_IRUGO))
- goto out_unlock;
+ goto out_unlock1;
- msg = find_msg(msq, &msgtyp, mode);
+ ipc_lock_object(&msq->q_perm);
+
+ /* raced with RMID? */
+ if (msq->q_perm.deleted) {
+ msg = ERR_PTR(-EIDRM);
+ goto out_unlock0;
+ }
+ msg = find_msg(msq, &msgtyp, mode);
if (!IS_ERR(msg)) {
/*
* Found a suitable message.
@@ -860,7 +924,7 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
*/
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
@@ -868,8 +932,9 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
*/
if (msgflg & MSG_COPY) {
msg = copy_msg(msg, copy);
- goto out_unlock;
+ goto out_unlock0;
}
+
list_del(&msg->m_list);
msq->q_qnum--;
msq->q_rtime = get_seconds();
@@ -878,14 +943,16 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
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;
@@ -896,8 +963,9 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
msr_d.r_maxsize = bufsz;
msr_d.r_msg = ERR_PTR(-EAGAIN);
current->state = TASK_INTERRUPTIBLE;
- msg_unlock(msq);
+ ipc_unlock_object(&msq->q_perm);
+ rcu_read_unlock();
schedule();
/* Lockless receive, part 1:
@@ -908,7 +976,7 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
* 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();
@@ -927,32 +995,34 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
* 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;
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);
}
+
+out_unlock0:
+ ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+ rcu_read_unlock();
if (IS_ERR(msg)) {
free_copy(copy);
return PTR_ERR(msg);
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
index 491e71f2a1b..7e7095974d5 100644
--- a/ipc/msgutil.c
+++ b/ipc/msgutil.c
@@ -41,15 +41,15 @@ struct msg_msgseg {
/* the next part of the message follows immediately */
};
-#define DATALEN_MSG (int)(PAGE_SIZE-sizeof(struct msg_msg))
-#define DATALEN_SEG (int)(PAGE_SIZE-sizeof(struct msg_msgseg))
+#define DATALEN_MSG ((size_t)PAGE_SIZE-sizeof(struct msg_msg))
+#define DATALEN_SEG ((size_t)PAGE_SIZE-sizeof(struct msg_msgseg))
-static struct msg_msg *alloc_msg(int len)
+static struct msg_msg *alloc_msg(size_t len)
{
struct msg_msg *msg;
struct msg_msgseg **pseg;
- int alen;
+ size_t alen;
alen = min(len, DATALEN_MSG);
msg = kmalloc(sizeof(*msg) + alen, GFP_KERNEL);
@@ -80,12 +80,12 @@ out_err:
return NULL;
}
-struct msg_msg *load_msg(const void __user *src, int len)
+struct msg_msg *load_msg(const void __user *src, size_t len)
{
struct msg_msg *msg;
struct msg_msgseg *seg;
int err = -EFAULT;
- int alen;
+ size_t alen;
msg = alloc_msg(len);
if (msg == NULL)
@@ -117,8 +117,8 @@ out_err:
struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst)
{
struct msg_msgseg *dst_pseg, *src_pseg;
- int len = src->m_ts;
- int alen;
+ size_t len = src->m_ts;
+ size_t alen;
BUG_ON(dst == NULL);
if (src->m_ts > dst->m_ts)
@@ -147,9 +147,9 @@ struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst)
return ERR_PTR(-ENOSYS);
}
#endif
-int store_msg(void __user *dest, struct msg_msg *msg, int len)
+int store_msg(void __user *dest, struct msg_msg *msg, size_t len)
{
- int alen;
+ size_t alen;
struct msg_msgseg *seg;
alen = min(len, DATALEN_MSG);
diff --git a/ipc/namespace.c b/ipc/namespace.c
index 7ee61bf4493..aba9a586c66 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -81,7 +81,7 @@ void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
int next_id;
int total, in_use;
- down_write(&ids->rw_mutex);
+ down_write(&ids->rwsem);
in_use = ids->in_use;
@@ -89,11 +89,12 @@ void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
perm = idr_find(&ids->ipcs_idr, next_id);
if (perm == NULL)
continue;
- ipc_lock_by_ptr(perm);
+ rcu_read_lock();
+ ipc_lock_object(perm);
free(ns, perm);
total++;
}
- up_write(&ids->rw_mutex);
+ up_write(&ids->rwsem);
}
static void free_ipc_ns(struct ipc_namespace *ns)
diff --git a/ipc/sem.c b/ipc/sem.c
index 70480a3aa69..db9d241af13 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -95,8 +95,12 @@ struct sem {
int semval; /* current value */
int sempid; /* pid of last operation */
spinlock_t lock; /* spinlock for fine-grained semtimedop */
- struct list_head sem_pending; /* pending single-sop operations */
-};
+ struct list_head pending_alter; /* pending single-sop operations */
+ /* that alter the semaphore */
+ struct list_head pending_const; /* pending single-sop operations */
+ /* that do not alter the semaphore*/
+ time_t sem_otime; /* candidate for sem_otime */
+} ____cacheline_aligned_in_smp;
/* One queue for each sleeping process in the system. */
struct sem_queue {
@@ -150,12 +154,15 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it);
#define SEMOPM_FAST 64 /* ~ 372 bytes on stack */
/*
- * linked list protection:
+ * Locking:
* sem_undo.id_next,
- * sem_array.sem_pending{,last},
- * sem_array.sem_undo: sem_lock() for read/write
+ * sem_array.complex_count,
+ * sem_array.pending{_alter,_cont},
+ * sem_array.sem_undo: global sem_lock() for read/write
* sem_undo.proc_next: only "current" is allowed to read/write that field.
*
+ * sem_array.sem_base[i].pending_{const,alter}:
+ * global or semaphore sem_lock() for read/write
*/
#define sc_semmsl sem_ctls[0]
@@ -189,77 +196,176 @@ void __init sem_init (void)
IPC_SEM_IDS, sysvipc_sem_proc_show);
}
+/**
+ * unmerge_queues - unmerge queues, if possible.
+ * @sma: semaphore array
+ *
+ * The function unmerges the wait queues if complex_count is 0.
+ * It must be called prior to dropping the global semaphore array lock.
+ */
+static void unmerge_queues(struct sem_array *sma)
+{
+ struct sem_queue *q, *tq;
+
+ /* complex operations still around? */
+ if (sma->complex_count)
+ return;
+ /*
+ * We will switch back to simple mode.
+ * Move all pending operation back into the per-semaphore
+ * queues.
+ */
+ list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
+ struct sem *curr;
+ curr = &sma->sem_base[q->sops[0].sem_num];
+
+ list_add_tail(&q->list, &curr->pending_alter);
+ }
+ INIT_LIST_HEAD(&sma->pending_alter);
+}
+
+/**
+ * merge_queues - Merge single semop queues into global queue
+ * @sma: semaphore array
+ *
+ * This function merges all per-semaphore queues into the global queue.
+ * It is necessary to achieve FIFO ordering for the pending single-sop
+ * operations when a multi-semop operation must sleep.
+ * Only the alter operations must be moved, the const operations can stay.
+ */
+static void merge_queues(struct sem_array *sma)
+{
+ int i;
+ for (i = 0; i < sma->sem_nsems; i++) {
+ struct sem *sem = sma->sem_base + i;
+
+ list_splice_init(&sem->pending_alter, &sma->pending_alter);
+ }
+}
+
+static void sem_rcu_free(struct rcu_head *head)
+{
+ struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+ struct sem_array *sma = ipc_rcu_to_struct(p);
+
+ security_sem_free(sma);
+ ipc_rcu_free(head);
+}
+
+/*
+ * Wait until all currently ongoing simple ops have completed.
+ * Caller must own sem_perm.lock.
+ * New simple ops cannot start, because simple ops first check
+ * that sem_perm.lock is free.
+ * that a) sem_perm.lock is free and b) complex_count is 0.
+ */
+static void sem_wait_array(struct sem_array *sma)
+{
+ int i;
+ struct sem *sem;
+
+ if (sma->complex_count) {
+ /* The thread that increased sma->complex_count waited on
+ * all sem->lock locks. Thus we don't need to wait again.
+ */
+ return;
+ }
+
+ for (i = 0; i < sma->sem_nsems; i++) {
+ sem = sma->sem_base + i;
+ spin_unlock_wait(&sem->lock);
+ }
+}
+
/*
* If the request contains only one semaphore operation, and there are
* no complex transactions pending, lock only the semaphore involved.
* Otherwise, lock the entire semaphore array, since we either have
* multiple semaphores in our own semops, or we need to look at
* semaphores from other pending complex operations.
- *
- * Carefully guard against sma->complex_count changing between zero
- * and non-zero while we are spinning for the lock. The value of
- * sma->complex_count cannot change while we are holding the lock,
- * so sem_unlock should be fine.
- *
- * The global lock path checks that all the local locks have been released,
- * checking each local lock once. This means that the local lock paths
- * cannot start their critical sections while the global lock is held.
*/
static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
int nsops)
{
- int locknum;
- again:
- if (nsops == 1 && !sma->complex_count) {
- struct sem *sem = sma->sem_base + sops->sem_num;
+ struct sem *sem;
- /* Lock just the semaphore we are interested in. */
- spin_lock(&sem->lock);
+ if (nsops != 1) {
+ /* Complex operation - acquire a full lock */
+ ipc_lock_object(&sma->sem_perm);
- /*
- * If sma->complex_count was set while we were spinning,
- * we may need to look at things we did not lock here.
+ /* And wait until all simple ops that are processed
+ * right now have dropped their locks.
*/
- if (unlikely(sma->complex_count)) {
- spin_unlock(&sem->lock);
- goto lock_array;
- }
+ sem_wait_array(sma);
+ return -1;
+ }
+ /*
+ * Only one semaphore affected - try to optimize locking.
+ * The rules are:
+ * - optimized locking is possible if no complex operation
+ * is either enqueued or processed right now.
+ * - The test for enqueued complex ops is simple:
+ * sma->complex_count != 0
+ * - Testing for complex ops that are processed right now is
+ * a bit more difficult. Complex ops acquire the full lock
+ * and first wait that the running simple ops have completed.
+ * (see above)
+ * Thus: If we own a simple lock and the global lock is free
+ * and complex_count is now 0, then it will stay 0 and
+ * thus just locking sem->lock is sufficient.
+ */
+ sem = sma->sem_base + sops->sem_num;
+
+ if (sma->complex_count == 0) {
/*
- * Another process is holding the global lock on the
- * sem_array; we cannot enter our critical section,
- * but have to wait for the global lock to be released.
+ * It appears that no complex operation is around.
+ * Acquire the per-semaphore lock.
*/
- if (unlikely(spin_is_locked(&sma->sem_perm.lock))) {
- spin_unlock(&sem->lock);
- spin_unlock_wait(&sma->sem_perm.lock);
- goto again;
+ spin_lock(&sem->lock);
+
+ /* Then check that the global lock is free */
+ if (!spin_is_locked(&sma->sem_perm.lock)) {
+ /* spin_is_locked() is not a memory barrier */
+ smp_mb();
+
+ /* Now repeat the test of complex_count:
+ * It can't change anymore until we drop sem->lock.
+ * Thus: if is now 0, then it will stay 0.
+ */
+ if (sma->complex_count == 0) {
+ /* fast path successful! */
+ return sops->sem_num;
+ }
}
+ spin_unlock(&sem->lock);
+ }
- locknum = sops->sem_num;
+ /* slow path: acquire the full lock */
+ ipc_lock_object(&sma->sem_perm);
+
+ if (sma->complex_count == 0) {
+ /* False alarm:
+ * There is no complex operation, thus we can switch
+ * back to the fast path.
+ */
+ spin_lock(&sem->lock);
+ ipc_unlock_object(&sma->sem_perm);
+ return sops->sem_num;
} else {
- int i;
- /*
- * Lock the semaphore array, and wait for all of the
- * individual semaphore locks to go away. The code
- * above ensures no new single-lock holders will enter
- * their critical section while the array lock is held.
+ /* Not a false alarm, thus complete the sequence for a
+ * full lock.
*/
- lock_array:
- spin_lock(&sma->sem_perm.lock);
- for (i = 0; i < sma->sem_nsems; i++) {
- struct sem *sem = sma->sem_base + i;
- spin_unlock_wait(&sem->lock);
- }
- locknum = -1;
+ sem_wait_array(sma);
+ return -1;
}
- return locknum;
}
static inline void sem_unlock(struct sem_array *sma, int locknum)
{
if (locknum == -1) {
- spin_unlock(&sma->sem_perm.lock);
+ unmerge_queues(sma);
+ ipc_unlock_object(&sma->sem_perm);
} else {
struct sem *sem = sma->sem_base + locknum;
spin_unlock(&sem->lock);
@@ -267,7 +373,7 @@ static inline void sem_unlock(struct sem_array *sma, int locknum)
}
/*
- * sem_lock_(check_) routines are called in the paths where the rw_mutex
+ * sem_lock_(check_) routines are called in the paths where the rwsem
* is not held.
*
* The caller holds the RCU read lock.
@@ -319,12 +425,7 @@ static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns
static inline void sem_lock_and_putref(struct sem_array *sma)
{
sem_lock(sma, NULL, -1);
- ipc_rcu_putref(sma);
-}
-
-static inline void sem_putref(struct sem_array *sma)
-{
- ipc_rcu_putref(sma);
+ ipc_rcu_putref(sma, ipc_rcu_free);
}
static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
@@ -337,7 +438,7 @@ static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
* Without the check/retry algorithm a lockless wakeup is possible:
* - queue.status is initialized to -EINTR before blocking.
* - wakeup is performed by
- * * unlinking the queue entry from sma->sem_pending
+ * * unlinking the queue entry from the pending list
* * setting queue.status to IN_WAKEUP
* This is the notification for the blocked thread that a
* result value is imminent.
@@ -371,7 +472,7 @@ static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
* @ns: namespace
* @params: ptr to the structure that contains key, semflg and nsems
*
- * Called with sem_ids.rw_mutex held (as a writer)
+ * Called with sem_ids.rwsem held (as a writer)
*/
static int newary(struct ipc_namespace *ns, struct ipc_params *params)
@@ -403,14 +504,13 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
sma->sem_perm.security = NULL;
retval = security_sem_alloc(sma);
if (retval) {
- ipc_rcu_putref(sma);
+ ipc_rcu_putref(sma, ipc_rcu_free);
return retval;
}
id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni);
if (id < 0) {
- security_sem_free(sma);
- ipc_rcu_putref(sma);
+ ipc_rcu_putref(sma, sem_rcu_free);
return id;
}
ns->used_sems += nsems;
@@ -418,12 +518,14 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
sma->sem_base = (struct sem *) &sma[1];
for (i = 0; i < nsems; i++) {
- INIT_LIST_HEAD(&sma->sem_base[i].sem_pending);
+ INIT_LIST_HEAD(&sma->sem_base[i].pending_alter);
+ INIT_LIST_HEAD(&sma->sem_base[i].pending_const);
spin_lock_init(&sma->sem_base[i].lock);
}
sma->complex_count = 0;
- INIT_LIST_HEAD(&sma->sem_pending);
+ INIT_LIST_HEAD(&sma->pending_alter);
+ INIT_LIST_HEAD(&sma->pending_const);
INIT_LIST_HEAD(&sma->list_id);
sma->sem_nsems = nsems;
sma->sem_ctime = get_seconds();
@@ -435,7 +537,7 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
/*
- * Called with sem_ids.rw_mutex and ipcp locked.
+ * Called with sem_ids.rwsem and ipcp locked.
*/
static inline int sem_security(struct kern_ipc_perm *ipcp, int semflg)
{
@@ -446,7 +548,7 @@ static inline int sem_security(struct kern_ipc_perm *ipcp, int semflg)
}
/*
- * Called with sem_ids.rw_mutex and ipcp locked.
+ * Called with sem_ids.rwsem and ipcp locked.
*/
static inline int sem_more_checks(struct kern_ipc_perm *ipcp,
struct ipc_params *params)
@@ -482,12 +584,19 @@ SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg)
return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params);
}
-/*
- * Determine whether a sequence of semaphore operations would succeed
- * all at once. Return 0 if yes, 1 if need to sleep, else return error code.
+/** perform_atomic_semop - Perform (if possible) a semaphore operation
+ * @sma: semaphore array
+ * @sops: array with operations that should be checked
+ * @nsems: number of sops
+ * @un: undo array
+ * @pid: pid that did the change
+ *
+ * Returns 0 if the operation was possible.
+ * Returns 1 if the operation is impossible, the caller must sleep.
+ * Negative values are error codes.
*/
-static int try_atomic_semop (struct sem_array * sma, struct sembuf * sops,
+static int perform_atomic_semop(struct sem_array *sma, struct sembuf *sops,
int nsops, struct sem_undo *un, int pid)
{
int result, sem_op;
@@ -609,60 +718,132 @@ static void unlink_queue(struct sem_array *sma, struct sem_queue *q)
* update_queue is O(N^2) when it restarts scanning the whole queue of
* waiting operations. Therefore this function checks if the restart is
* really necessary. It is called after a previously waiting operation
- * was completed.
+ * modified the array.
+ * Note that wait-for-zero operations are handled without restart.
*/
static int check_restart(struct sem_array *sma, struct sem_queue *q)
{
- struct sem *curr;
- struct sem_queue *h;
-
- /* if the operation didn't modify the array, then no restart */
- if (q->alter == 0)
- return 0;
-
- /* pending complex operations are too difficult to analyse */
- if (sma->complex_count)
+ /* pending complex alter operations are too difficult to analyse */
+ if (!list_empty(&sma->pending_alter))
return 1;
/* we were a sleeping complex operation. Too difficult */
if (q->nsops > 1)
return 1;
- curr = sma->sem_base + q->sops[0].sem_num;
+ /* It is impossible that someone waits for the new value:
+ * - complex operations always restart.
+ * - wait-for-zero are handled seperately.
+ * - q is a previously sleeping simple operation that
+ * altered the array. It must be a decrement, because
+ * simple increments never sleep.
+ * - If there are older (higher priority) decrements
+ * in the queue, then they have observed the original
+ * semval value and couldn't proceed. The operation
+ * decremented to value - thus they won't proceed either.
+ */
+ return 0;
+}
- /* No-one waits on this queue */
- if (list_empty(&curr->sem_pending))
- return 0;
+/**
+ * wake_const_ops(sma, semnum, pt) - Wake up non-alter tasks
+ * @sma: semaphore array.
+ * @semnum: semaphore that was modified.
+ * @pt: list head for the tasks that must be woken up.
+ *
+ * wake_const_ops must be called after a semaphore in a semaphore array
+ * was set to 0. If complex const operations are pending, wake_const_ops must
+ * be called with semnum = -1, as well as with the number of each modified
+ * semaphore.
+ * The tasks that must be woken up are added to @pt. The return code
+ * is stored in q->pid.
+ * The function returns 1 if at least one operation was completed successfully.
+ */
+static int wake_const_ops(struct sem_array *sma, int semnum,
+ struct list_head *pt)
+{
+ struct sem_queue *q;
+ struct list_head *walk;
+ struct list_head *pending_list;
+ int semop_completed = 0;
+
+ if (semnum == -1)
+ pending_list = &sma->pending_const;
+ else
+ pending_list = &sma->sem_base[semnum].pending_const;
+
+ walk = pending_list->next;
+ while (walk != pending_list) {
+ int error;
+
+ q = container_of(walk, struct sem_queue, list);
+ walk = walk->next;
+
+ error = perform_atomic_semop(sma, q->sops, q->nsops,
+ q->undo, q->pid);
+
+ if (error <= 0) {
+ /* operation completed, remove from queue & wakeup */
+
+ unlink_queue(sma, q);
+
+ wake_up_sem_queue_prepare(pt, q, error);
+ if (error == 0)
+ semop_completed = 1;
+ }
+ }
+ return semop_completed;
+}
+
+/**
+ * do_smart_wakeup_zero(sma, sops, nsops, pt) - wakeup all wait for zero tasks
+ * @sma: semaphore array
+ * @sops: operations that were performed
+ * @nsops: number of operations
+ * @pt: list head of the tasks that must be woken up.
+ *
+ * do_smart_wakeup_zero() checks all required queue for wait-for-zero
+ * operations, based on the actual changes that were performed on the
+ * semaphore array.
+ * The function returns 1 if at least one operation was completed successfully.
+ */
+static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
+ int nsops, struct list_head *pt)
+{
+ int i;
+ int semop_completed = 0;
+ int got_zero = 0;
+
+ /* first: the per-semaphore queues, if known */
+ if (sops) {
+ for (i = 0; i < nsops; i++) {
+ int num = sops[i].sem_num;
- /* the new semaphore value */
- if (curr->semval) {
- /* It is impossible that someone waits for the new value:
- * - q is a previously sleeping simple operation that
- * altered the array. It must be a decrement, because
- * simple increments never sleep.
- * - The value is not 0, thus wait-for-zero won't proceed.
- * - If there are older (higher priority) decrements
- * in the queue, then they have observed the original
- * semval value and couldn't proceed. The operation
- * decremented to value - thus they won't proceed either.
+ if (sma->sem_base[num].semval == 0) {
+ got_zero = 1;
+ semop_completed |= wake_const_ops(sma, num, pt);
+ }
+ }
+ } else {
+ /*
+ * No sops means modified semaphores not known.
+ * Assume all were changed.
*/
- BUG_ON(q->sops[0].sem_op >= 0);
- return 0;
+ for (i = 0; i < sma->sem_nsems; i++) {
+ if (sma->sem_base[i].semval == 0) {
+ got_zero = 1;
+ semop_completed |= wake_const_ops(sma, i, pt);
+ }
+ }
}
/*
- * semval is 0. Check if there are wait-for-zero semops.
- * They must be the first entries in the per-semaphore queue
+ * If one of the modified semaphores got 0,
+ * then check the global queue, too.
*/
- h = list_first_entry(&curr->sem_pending, struct sem_queue, list);
- BUG_ON(h->nsops != 1);
- BUG_ON(h->sops[0].sem_num != q->sops[0].sem_num);
-
- /* Yes, there is a wait-for-zero semop. Restart */
- if (h->sops[0].sem_op == 0)
- return 1;
+ if (got_zero)
+ semop_completed |= wake_const_ops(sma, -1, pt);
- /* Again - no-one is waiting for the new value. */
- return 0;
+ return semop_completed;
}
@@ -678,6 +859,8 @@ static int check_restart(struct sem_array *sma, struct sem_queue *q)
* semaphore.
* The tasks that must be woken up are added to @pt. The return code
* is stored in q->pid.
+ * The function internally checks if const operations can now succeed.
+ *
* The function return 1 if at least one semop was completed successfully.
*/
static int update_queue(struct sem_array *sma, int semnum, struct list_head *pt)
@@ -688,9 +871,9 @@ static int update_queue(struct sem_array *sma, int semnum, struct list_head *pt)
int semop_completed = 0;
if (semnum == -1)
- pending_list = &sma->sem_pending;
+ pending_list = &sma->pending_alter;
else
- pending_list = &sma->sem_base[semnum].sem_pending;
+ pending_list = &sma->sem_base[semnum].pending_alter;
again:
walk = pending_list->next;
@@ -702,16 +885,15 @@ again:
/* If we are scanning the single sop, per-semaphore list of
* one semaphore and that semaphore is 0, then it is not
- * necessary to scan the "alter" entries: simple increments
+ * necessary to scan further: simple increments
* that affect only one entry succeed immediately and cannot
* be in the per semaphore pending queue, and decrements
* cannot be successful if the value is already 0.
*/
- if (semnum != -1 && sma->sem_base[semnum].semval == 0 &&
- q->alter)
+ if (semnum != -1 && sma->sem_base[semnum].semval == 0)
break;
- error = try_atomic_semop(sma, q->sops, q->nsops,
+ error = perform_atomic_semop(sma, q->sops, q->nsops,
q->undo, q->pid);
/* Does q->sleeper still need to sleep? */
@@ -724,6 +906,7 @@ again:
restart = 0;
} else {
semop_completed = 1;
+ do_smart_wakeup_zero(sma, q->sops, q->nsops, pt);
restart = check_restart(sma, q);
}
@@ -735,6 +918,24 @@ again:
}
/**
+ * set_semotime(sma, sops) - set sem_otime
+ * @sma: semaphore array
+ * @sops: operations that modified the array, may be NULL
+ *
+ * sem_otime is replicated to avoid cache line trashing.
+ * This function sets one instance to the current time.
+ */
+static void set_semotime(struct sem_array *sma, struct sembuf *sops)
+{
+ if (sops == NULL) {
+ sma->sem_base[0].sem_otime = get_seconds();
+ } else {
+ sma->sem_base[sops[0].sem_num].sem_otime =
+ get_seconds();
+ }
+}
+
+/**
* do_smart_update(sma, sops, nsops, otime, pt) - optimized update_queue
* @sma: semaphore array
* @sops: operations that were performed
@@ -742,8 +943,8 @@ again:
* @otime: force setting otime
* @pt: list head of the tasks that must be woken up.
*
- * do_smart_update() does the required called to update_queue, based on the
- * actual changes that were performed on the semaphore array.
+ * do_smart_update() does the required calls to update_queue and wakeup_zero,
+ * based on the actual changes that were performed on the semaphore array.
* Note that the function does not do the actual wake-up: the caller is
* responsible for calling wake_up_sem_queue_do(@pt).
* It is safe to perform this call after dropping all locks.
@@ -752,52 +953,42 @@ static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsop
int otime, struct list_head *pt)
{
int i;
- int progress;
-
- progress = 1;
-retry_global:
- if (sma->complex_count) {
- if (update_queue(sma, -1, pt)) {
- progress = 1;
- otime = 1;
- sops = NULL;
- }
- }
- if (!progress)
- goto done;
- if (!sops) {
- /* No semops; something special is going on. */
- for (i = 0; i < sma->sem_nsems; i++) {
- if (update_queue(sma, i, pt)) {
- otime = 1;
- progress = 1;
- }
- }
- goto done_checkretry;
- }
+ otime |= do_smart_wakeup_zero(sma, sops, nsops, pt);
- /* Check the semaphores that were modified. */
- for (i = 0; i < nsops; i++) {
- if (sops[i].sem_op > 0 ||
- (sops[i].sem_op < 0 &&
- sma->sem_base[sops[i].sem_num].semval == 0))
- if (update_queue(sma, sops[i].sem_num, pt)) {
- otime = 1;
- progress = 1;
+ if (!list_empty(&sma->pending_alter)) {
+ /* semaphore array uses the global queue - just process it. */
+ otime |= update_queue(sma, -1, pt);
+ } else {
+ if (!sops) {
+ /*
+ * No sops, thus the modified semaphores are not
+ * known. Check all.
+ */
+ for (i = 0; i < sma->sem_nsems; i++)
+ otime |= update_queue(sma, i, pt);
+ } else {
+ /*
+ * Check the semaphores that were increased:
+ * - No complex ops, thus all sleeping ops are
+ * decrease.
+ * - if we decreased the value, then any sleeping
+ * semaphore ops wont be able to run: If the
+ * previous value was too small, then the new
+ * value will be too small, too.
+ */
+ for (i = 0; i < nsops; i++) {
+ if (sops[i].sem_op > 0) {
+ otime |= update_queue(sma,
+ sops[i].sem_num, pt);
+ }
}
+ }
}
-done_checkretry:
- if (progress) {
- progress = 0;
- goto retry_global;
- }
-done:
if (otime)
- sma->sem_otime = get_seconds();
+ set_semotime(sma, sops);
}
-
/* The following counts are associated to each semaphore:
* semncnt number of tasks waiting on semval being nonzero
* semzcnt number of tasks waiting on semval being zero
@@ -813,14 +1004,14 @@ static int count_semncnt (struct sem_array * sma, ushort semnum)
struct sem_queue * q;
semncnt = 0;
- list_for_each_entry(q, &sma->sem_base[semnum].sem_pending, list) {
+ list_for_each_entry(q, &sma->sem_base[semnum].pending_alter, list) {
struct sembuf * sops = q->sops;
BUG_ON(sops->sem_num != semnum);
if ((sops->sem_op < 0) && !(sops->sem_flg & IPC_NOWAIT))
semncnt++;
}
- list_for_each_entry(q, &sma->sem_pending, list) {
+ list_for_each_entry(q, &sma->pending_alter, list) {
struct sembuf * sops = q->sops;
int nsops = q->nsops;
int i;
@@ -839,14 +1030,14 @@ static int count_semzcnt (struct sem_array * sma, ushort semnum)
struct sem_queue * q;
semzcnt = 0;
- list_for_each_entry(q, &sma->sem_base[semnum].sem_pending, list) {
+ list_for_each_entry(q, &sma->sem_base[semnum].pending_const, list) {
struct sembuf * sops = q->sops;
BUG_ON(sops->sem_num != semnum);
if ((sops->sem_op == 0) && !(sops->sem_flg & IPC_NOWAIT))
semzcnt++;
}
- list_for_each_entry(q, &sma->sem_pending, list) {
+ list_for_each_entry(q, &sma->pending_const, list) {
struct sembuf * sops = q->sops;
int nsops = q->nsops;
int i;
@@ -859,8 +1050,8 @@ static int count_semzcnt (struct sem_array * sma, ushort semnum)
return semzcnt;
}
-/* Free a semaphore set. freeary() is called with sem_ids.rw_mutex locked
- * as a writer and the spinlock for this semaphore set hold. sem_ids.rw_mutex
+/* Free a semaphore set. freeary() is called with sem_ids.rwsem locked
+ * as a writer and the spinlock for this semaphore set hold. sem_ids.rwsem
* remains locked on exit.
*/
static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
@@ -872,7 +1063,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
int i;
/* Free the existing undo structures for this semaphore set. */
- assert_spin_locked(&sma->sem_perm.lock);
+ ipc_assert_locked_object(&sma->sem_perm);
list_for_each_entry_safe(un, tu, &sma->list_id, list_id) {
list_del(&un->list_id);
spin_lock(&un->ulp->lock);
@@ -884,13 +1075,22 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
/* Wake up all pending processes and let them fail with EIDRM. */
INIT_LIST_HEAD(&tasks);
- list_for_each_entry_safe(q, tq, &sma->sem_pending, list) {
+ list_for_each_entry_safe(q, tq, &sma->pending_const, list) {
+ unlink_queue(sma, q);
+ wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+ }
+
+ list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
unlink_queue(sma, q);
wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
}
for (i = 0; i < sma->sem_nsems; i++) {
struct sem *sem = sma->sem_base + i;
- list_for_each_entry_safe(q, tq, &sem->sem_pending, list) {
+ list_for_each_entry_safe(q, tq, &sem->pending_const, list) {
+ unlink_queue(sma, q);
+ wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+ }
+ list_for_each_entry_safe(q, tq, &sem->pending_alter, list) {
unlink_queue(sma, q);
wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
}
@@ -903,8 +1103,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
wake_up_sem_queue_do(&tasks);
ns->used_sems -= sma->sem_nsems;
- security_sem_free(sma);
- ipc_rcu_putref(sma);
+ ipc_rcu_putref(sma, sem_rcu_free);
}
static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version)
@@ -931,6 +1130,21 @@ static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in,
}
}
+static time_t get_semotime(struct sem_array *sma)
+{
+ int i;
+ time_t res;
+
+ res = sma->sem_base[0].sem_otime;
+ for (i = 1; i < sma->sem_nsems; i++) {
+ time_t to = sma->sem_base[i].sem_otime;
+
+ if (to > res)
+ res = to;
+ }
+ return res;
+}
+
static int semctl_nolock(struct ipc_namespace *ns, int semid,
int cmd, int version, void __user *p)
{
@@ -957,7 +1171,7 @@ static int semctl_nolock(struct ipc_namespace *ns, int semid,
seminfo.semmnu = SEMMNU;
seminfo.semmap = SEMMAP;
seminfo.semume = SEMUME;
- down_read(&sem_ids(ns).rw_mutex);
+ down_read(&sem_ids(ns).rwsem);
if (cmd == SEM_INFO) {
seminfo.semusz = sem_ids(ns).in_use;
seminfo.semaem = ns->used_sems;
@@ -966,7 +1180,7 @@ static int semctl_nolock(struct ipc_namespace *ns, int semid,
seminfo.semaem = SEMAEM;
}
max_id = ipc_get_maxid(&sem_ids(ns));
- up_read(&sem_ids(ns).rw_mutex);
+ up_read(&sem_ids(ns).rwsem);
if (copy_to_user(p, &seminfo, sizeof(struct seminfo)))
return -EFAULT;
return (max_id < 0) ? 0: max_id;
@@ -1004,9 +1218,9 @@ static int semctl_nolock(struct ipc_namespace *ns, int semid,
goto out_unlock;
kernel_to_ipc64_perm(&sma->sem_perm, &tbuf.sem_perm);
- tbuf.sem_otime = sma->sem_otime;
- tbuf.sem_ctime = sma->sem_ctime;
- tbuf.sem_nsems = sma->sem_nsems;
+ tbuf.sem_otime = get_semotime(sma);
+ tbuf.sem_ctime = sma->sem_ctime;
+ tbuf.sem_nsems = sma->sem_nsems;
rcu_read_unlock();
if (copy_semid_to_user(p, &tbuf, version))
return -EFAULT;
@@ -1068,9 +1282,15 @@ static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum,
sem_lock(sma, NULL, -1);
+ if (sma->sem_perm.deleted) {
+ sem_unlock(sma, -1);
+ rcu_read_unlock();
+ return -EIDRM;
+ }
+
curr = &sma->sem_base[semnum];
- assert_spin_locked(&sma->sem_perm.lock);
+ ipc_assert_locked_object(&sma->sem_perm);
list_for_each_entry(un, &sma->list_id, list_id)
un->semadj[semnum] = 0;
@@ -1122,28 +1342,28 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
int i;
sem_lock(sma, NULL, -1);
+ if (sma->sem_perm.deleted) {
+ err = -EIDRM;
+ goto out_unlock;
+ }
if(nsems > SEMMSL_FAST) {
if (!ipc_rcu_getref(sma)) {
- sem_unlock(sma, -1);
- rcu_read_unlock();
err = -EIDRM;
- goto out_free;
+ goto out_unlock;
}
sem_unlock(sma, -1);
rcu_read_unlock();
sem_io = ipc_alloc(sizeof(ushort)*nsems);
if(sem_io == NULL) {
- sem_putref(sma);
+ ipc_rcu_putref(sma, ipc_rcu_free);
return -ENOMEM;
}
rcu_read_lock();
sem_lock_and_putref(sma);
if (sma->sem_perm.deleted) {
- sem_unlock(sma, -1);
- rcu_read_unlock();
err = -EIDRM;
- goto out_free;
+ goto out_unlock;
}
}
for (i = 0; i < sma->sem_nsems; i++)
@@ -1161,28 +1381,28 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
struct sem_undo *un;
if (!ipc_rcu_getref(sma)) {
- rcu_read_unlock();
- return -EIDRM;
+ err = -EIDRM;
+ goto out_rcu_wakeup;
}
rcu_read_unlock();
if(nsems > SEMMSL_FAST) {
sem_io = ipc_alloc(sizeof(ushort)*nsems);
if(sem_io == NULL) {
- sem_putref(sma);
+ ipc_rcu_putref(sma, ipc_rcu_free);
return -ENOMEM;
}
}
if (copy_from_user (sem_io, p, nsems*sizeof(ushort))) {
- sem_putref(sma);
+ ipc_rcu_putref(sma, ipc_rcu_free);
err = -EFAULT;
goto out_free;
}
for (i = 0; i < nsems; i++) {
if (sem_io[i] > SEMVMX) {
- sem_putref(sma);
+ ipc_rcu_putref(sma, ipc_rcu_free);
err = -ERANGE;
goto out_free;
}
@@ -1190,16 +1410,14 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
rcu_read_lock();
sem_lock_and_putref(sma);
if (sma->sem_perm.deleted) {
- sem_unlock(sma, -1);
- rcu_read_unlock();
err = -EIDRM;
- goto out_free;
+ goto out_unlock;
}
for (i = 0; i < nsems; i++)
sma->sem_base[i].semval = sem_io[i];
- assert_spin_locked(&sma->sem_perm.lock);
+ ipc_assert_locked_object(&sma->sem_perm);
list_for_each_entry(un, &sma->list_id, list_id) {
for (i = 0; i < nsems; i++)
un->semadj[i] = 0;
@@ -1217,6 +1435,10 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
goto out_rcu_wakeup;
sem_lock(sma, NULL, -1);
+ if (sma->sem_perm.deleted) {
+ err = -EIDRM;
+ goto out_unlock;
+ }
curr = &sma->sem_base[semnum];
switch (cmd) {
@@ -1272,9 +1494,9 @@ copy_semid_from_user(struct semid64_ds *out, void __user *buf, int version)
}
/*
- * This function handles some semctl commands which require the rw_mutex
+ * This function handles some semctl 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 semctl_down(struct ipc_namespace *ns, int semid,
int cmd, int version, void __user *p)
@@ -1289,42 +1511,46 @@ static int semctl_down(struct ipc_namespace *ns, int semid,
return -EFAULT;
}
+ down_write(&sem_ids(ns).rwsem);
+ rcu_read_lock();
+
ipcp = ipcctl_pre_down_nolock(ns, &sem_ids(ns), semid, cmd,
&semid64.sem_perm, 0);
- if (IS_ERR(ipcp))
- return PTR_ERR(ipcp);
+ if (IS_ERR(ipcp)) {
+ err = PTR_ERR(ipcp);
+ goto out_unlock1;
+ }
sma = container_of(ipcp, struct sem_array, sem_perm);
err = security_sem_semctl(sma, cmd);
- if (err) {
- rcu_read_unlock();
- goto out_up;
- }
+ if (err)
+ goto out_unlock1;
- switch(cmd){
+ switch (cmd) {
case IPC_RMID:
sem_lock(sma, NULL, -1);
+ /* freeary unlocks the ipc object and rcu */
freeary(ns, ipcp);
goto out_up;
case IPC_SET:
sem_lock(sma, NULL, -1);
err = ipc_update_perm(&semid64.sem_perm, ipcp);
if (err)
- goto out_unlock;
+ goto out_unlock0;
sma->sem_ctime = get_seconds();
break;
default:
- rcu_read_unlock();
err = -EINVAL;
- goto out_up;
+ goto out_unlock1;
}
-out_unlock:
+out_unlock0:
sem_unlock(sma, -1);
+out_unlock1:
rcu_read_unlock();
out_up:
- up_write(&sem_ids(ns).rw_mutex);
+ up_write(&sem_ids(ns).rwsem);
return err;
}
@@ -1466,7 +1692,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
/* step 2: allocate new undo structure */
new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL);
if (!new) {
- sem_putref(sma);
+ ipc_rcu_putref(sma, ipc_rcu_free);
return ERR_PTR(-ENOMEM);
}
@@ -1496,7 +1722,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
new->semid = semid;
assert_spin_locked(&ulp->lock);
list_add_rcu(&new->list_proc, &ulp->list_proc);
- assert_spin_locked(&sma->sem_perm.lock);
+ ipc_assert_locked_object(&sma->sem_perm);
list_add(&new->list_id, &sma->list_id);
un = new;
@@ -1533,7 +1759,6 @@ static int get_queue_result(struct sem_queue *q)
return error;
}
-
SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
unsigned, nsops, const struct timespec __user *, timeout)
{
@@ -1619,6 +1844,10 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
if (error)
goto out_rcu_wakeup;
+ error = -EIDRM;
+ locknum = sem_lock(sma, sops, nsops);
+ if (sma->sem_perm.deleted)
+ goto out_unlock_free;
/*
* semid identifiers are not unique - find_alloc_undo may have
* allocated an undo structure, it was invalidated by an RMID
@@ -1626,18 +1855,22 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
* This case can be detected checking un->semid. The existence of
* "un" itself is guaranteed by rcu.
*/
- error = -EIDRM;
- locknum = sem_lock(sma, sops, nsops);
if (un && un->semid == -1)
goto out_unlock_free;
- error = try_atomic_semop (sma, sops, nsops, un, task_tgid_vnr(current));
- if (error <= 0) {
- if (alter && error == 0)
+ error = perform_atomic_semop(sma, sops, nsops, un,
+ task_tgid_vnr(current));
+ if (error == 0) {
+ /* If the operation was successful, then do
+ * the required updates.
+ */
+ if (alter)
do_smart_update(sma, sops, nsops, 1, &tasks);
-
- goto out_unlock_free;
+ else
+ set_semotime(sma, sops);
}
+ if (error <= 0)
+ goto out_unlock_free;
/* We need to sleep on this operation, so we put the current
* task into the pending queue and go to sleep.
@@ -1653,15 +1886,27 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
struct sem *curr;
curr = &sma->sem_base[sops->sem_num];
- if (alter)
- list_add_tail(&queue.list, &curr->sem_pending);
- else
- list_add(&queue.list, &curr->sem_pending);
+ if (alter) {
+ if (sma->complex_count) {
+ list_add_tail(&queue.list,
+ &sma->pending_alter);
+ } else {
+
+ list_add_tail(&queue.list,
+ &curr->pending_alter);
+ }
+ } else {
+ list_add_tail(&queue.list, &curr->pending_const);
+ }
} else {
+ if (!sma->complex_count)
+ merge_queues(sma);
+
if (alter)
- list_add_tail(&queue.list, &sma->sem_pending);
+ list_add_tail(&queue.list, &sma->pending_alter);
else
- list_add(&queue.list, &sma->sem_pending);
+ list_add_tail(&queue.list, &sma->pending_const);
+
sma->complex_count++;
}
@@ -1822,6 +2067,12 @@ void exit_sem(struct task_struct *tsk)
}
sem_lock(sma, NULL, -1);
+ /* exit_sem raced with IPC_RMID, nothing to do */
+ if (sma->sem_perm.deleted) {
+ sem_unlock(sma, -1);
+ rcu_read_unlock();
+ continue;
+ }
un = __lookup_undo(ulp, semid);
if (un == NULL) {
/* exit_sem raced with IPC_RMID+semget() that created
@@ -1833,7 +2084,7 @@ void exit_sem(struct task_struct *tsk)
}
/* remove un from the linked lists */
- assert_spin_locked(&sma->sem_perm.lock);
+ ipc_assert_locked_object(&sma->sem_perm);
list_del(&un->list_id);
spin_lock(&ulp->lock);
@@ -1882,6 +2133,17 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it)
{
struct user_namespace *user_ns = seq_user_ns(s);
struct sem_array *sma = it;
+ time_t sem_otime;
+
+ /*
+ * The proc interface isn't aware of sem_lock(), it calls
+ * ipc_lock_object() directly (in sysvipc_find_ipc).
+ * In order to stay compatible with sem_lock(), we must wait until
+ * all simple semop() calls have left their critical regions.
+ */
+ sem_wait_array(sma);
+
+ sem_otime = get_semotime(sma);
return seq_printf(s,
"%10d %10d %4o %10u %5u %5u %5u %5u %10lu %10lu\n",
@@ -1893,7 +2155,7 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it)
from_kgid_munged(user_ns, sma->sem_perm.gid),
from_kuid_munged(user_ns, sma->sem_perm.cuid),
from_kgid_munged(user_ns, sma->sem_perm.cgid),
- sma->sem_otime,
+ sem_otime,
sma->sem_ctime);
}
#endif
diff --git a/ipc/shm.c b/ipc/shm.c
index 7e199fa1960..6dc55af8a29 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -19,6 +19,9 @@
* namespaces support
* OpenVZ, SWsoft Inc.
* Pavel Emelianov <xemul@openvz.org>
+ *
+ * Better ipc lock (kern_ipc_perm.lock) handling
+ * Davidlohr Bueso <davidlohr.bueso@hp.com>, June 2013.
*/
#include <linux/slab.h>
@@ -80,8 +83,8 @@ void shm_init_ns(struct ipc_namespace *ns)
}
/*
- * Called with shm_ids.rw_mutex (writer) and the shp structure locked.
- * Only shm_ids.rw_mutex remains locked on exit.
+ * Called with shm_ids.rwsem (writer) and the shp structure locked.
+ * Only shm_ids.rwsem remains locked on exit.
*/
static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
{
@@ -124,8 +127,28 @@ void __init shm_init (void)
IPC_SHM_IDS, sysvipc_shm_proc_show);
}
+static inline struct shmid_kernel *shm_obtain_object(struct ipc_namespace *ns, int id)
+{
+ struct kern_ipc_perm *ipcp = ipc_obtain_object(&shm_ids(ns), id);
+
+ if (IS_ERR(ipcp))
+ return ERR_CAST(ipcp);
+
+ return container_of(ipcp, struct shmid_kernel, shm_perm);
+}
+
+static inline struct shmid_kernel *shm_obtain_object_check(struct ipc_namespace *ns, int id)
+{
+ struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&shm_ids(ns), id);
+
+ if (IS_ERR(ipcp))
+ return ERR_CAST(ipcp);
+
+ return container_of(ipcp, struct shmid_kernel, shm_perm);
+}
+
/*
- * shm_lock_(check_) routines are called in the paths where the rw_mutex
+ * shm_lock_(check_) routines are called in the paths where the rwsem
* is not necessarily held.
*/
static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
@@ -141,18 +164,16 @@ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp)
{
rcu_read_lock();
- spin_lock(&ipcp->shm_perm.lock);
+ ipc_lock_object(&ipcp->shm_perm);
}
-static inline struct shmid_kernel *shm_lock_check(struct ipc_namespace *ns,
- int id)
+static void shm_rcu_free(struct rcu_head *head)
{
- struct kern_ipc_perm *ipcp = ipc_lock_check(&shm_ids(ns), id);
-
- if (IS_ERR(ipcp))
- return (struct shmid_kernel *)ipcp;
+ struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+ struct shmid_kernel *shp = ipc_rcu_to_struct(p);
- return container_of(ipcp, struct shmid_kernel, shm_perm);
+ security_shm_free(shp);
+ ipc_rcu_free(head);
}
static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
@@ -182,22 +203,24 @@ static void shm_open(struct vm_area_struct *vma)
* @ns: namespace
* @shp: struct to free
*
- * It has to be called with shp and shm_ids.rw_mutex (writer) locked,
+ * It has to be called with shp and shm_ids.rwsem (writer) locked,
* but returns with shp unlocked and freed.
*/
static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
{
+ struct file *shm_file;
+
+ shm_file = shp->shm_file;
+ shp->shm_file = NULL;
ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT;
shm_rmid(ns, shp);
shm_unlock(shp);
- if (!is_file_hugepages(shp->shm_file))
- shmem_lock(shp->shm_file, 0, shp->mlock_user);
+ if (!is_file_hugepages(shm_file))
+ shmem_lock(shm_file, 0, shp->mlock_user);
else if (shp->mlock_user)
- user_shm_unlock(file_inode(shp->shm_file)->i_size,
- shp->mlock_user);
- fput (shp->shm_file);
- security_shm_free(shp);
- ipc_rcu_putref(shp);
+ user_shm_unlock(file_inode(shm_file)->i_size, shp->mlock_user);
+ fput(shm_file);
+ ipc_rcu_putref(shp, shm_rcu_free);
}
/*
@@ -230,7 +253,7 @@ static void shm_close(struct vm_area_struct *vma)
struct shmid_kernel *shp;
struct ipc_namespace *ns = sfd->ns;
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
/* remove from the list of attaches of the shm segment */
shp = shm_lock(ns, sfd->id);
BUG_ON(IS_ERR(shp));
@@ -241,10 +264,10 @@ static void shm_close(struct vm_area_struct *vma)
shm_destroy(ns, shp);
else
shm_unlock(shp);
- up_write(&shm_ids(ns).rw_mutex);
+ up_write(&shm_ids(ns).rwsem);
}
-/* Called with ns->shm_ids(ns).rw_mutex locked */
+/* Called with ns->shm_ids(ns).rwsem locked */
static int shm_try_destroy_current(int id, void *p, void *data)
{
struct ipc_namespace *ns = data;
@@ -275,7 +298,7 @@ static int shm_try_destroy_current(int id, void *p, void *data)
return 0;
}
-/* Called with ns->shm_ids(ns).rw_mutex locked */
+/* Called with ns->shm_ids(ns).rwsem locked */
static int shm_try_destroy_orphaned(int id, void *p, void *data)
{
struct ipc_namespace *ns = data;
@@ -286,7 +309,7 @@ static int shm_try_destroy_orphaned(int id, void *p, void *data)
* We want to destroy segments without users and with already
* exit'ed originating process.
*
- * As shp->* are changed under rw_mutex, it's safe to skip shp locking.
+ * As shp->* are changed under rwsem, it's safe to skip shp locking.
*/
if (shp->shm_creator != NULL)
return 0;
@@ -300,10 +323,10 @@ static int shm_try_destroy_orphaned(int id, void *p, void *data)
void shm_destroy_orphaned(struct ipc_namespace *ns)
{
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
if (shm_ids(ns).in_use)
idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_orphaned, ns);
- up_write(&shm_ids(ns).rw_mutex);
+ up_write(&shm_ids(ns).rwsem);
}
@@ -315,10 +338,10 @@ void exit_shm(struct task_struct *task)
return;
/* Destroy all already created segments, but not mapped yet */
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
if (shm_ids(ns).in_use)
idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_current, ns);
- up_write(&shm_ids(ns).rw_mutex);
+ up_write(&shm_ids(ns).rwsem);
}
static int shm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
@@ -452,7 +475,7 @@ static const struct vm_operations_struct shm_vm_ops = {
* @ns: namespace
* @params: ptr to the structure that contains key, size and shmflg
*
- * Called with shm_ids.rw_mutex held as a writer.
+ * Called with shm_ids.rwsem held as a writer.
*/
static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
@@ -485,7 +508,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
shp->shm_perm.security = NULL;
error = security_shm_alloc(shp);
if (error) {
- ipc_rcu_putref(shp);
+ ipc_rcu_putref(shp, ipc_rcu_free);
return error;
}
@@ -535,6 +558,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
shp->shm_nattch = 0;
shp->shm_file = file;
shp->shm_creator = current;
+
/*
* shmid gets reported as "inode#" in /proc/pid/maps.
* proc-ps tools use this. Changing this will break them.
@@ -543,7 +567,9 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
ns->shm_tot += numpages;
error = shp->shm_perm.id;
- shm_unlock(shp);
+
+ ipc_unlock_object(&shp->shm_perm);
+ rcu_read_unlock();
return error;
no_id:
@@ -551,13 +577,12 @@ no_id:
user_shm_unlock(size, shp->mlock_user);
fput(file);
no_file:
- security_shm_free(shp);
- ipc_rcu_putref(shp);
+ ipc_rcu_putref(shp, shm_rcu_free);
return error;
}
/*
- * Called with shm_ids.rw_mutex and ipcp locked.
+ * Called with shm_ids.rwsem and ipcp locked.
*/
static inline int shm_security(struct kern_ipc_perm *ipcp, int shmflg)
{
@@ -568,7 +593,7 @@ static inline int shm_security(struct kern_ipc_perm *ipcp, int shmflg)
}
/*
- * Called with shm_ids.rw_mutex and ipcp locked.
+ * Called with shm_ids.rwsem and ipcp locked.
*/
static inline int shm_more_checks(struct kern_ipc_perm *ipcp,
struct ipc_params *params)
@@ -681,7 +706,7 @@ static inline unsigned long copy_shminfo_to_user(void __user *buf, struct shminf
/*
* Calculate and add used RSS and swap pages of a shm.
- * Called with shm_ids.rw_mutex held as a reader
+ * Called with shm_ids.rwsem held as a reader
*/
static void shm_add_rss_swap(struct shmid_kernel *shp,
unsigned long *rss_add, unsigned long *swp_add)
@@ -708,7 +733,7 @@ static void shm_add_rss_swap(struct shmid_kernel *shp,
}
/*
- * Called with shm_ids.rw_mutex held as a reader
+ * Called with shm_ids.rwsem held as a reader
*/
static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss,
unsigned long *swp)
@@ -737,9 +762,9 @@ static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss,
}
/*
- * This function handles some shmctl commands which require the rw_mutex
+ * This function handles some shmctl 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 shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
struct shmid_ds __user *buf, int version)
@@ -754,59 +779,67 @@ static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
return -EFAULT;
}
- ipcp = ipcctl_pre_down(ns, &shm_ids(ns), shmid, cmd,
- &shmid64.shm_perm, 0);
- if (IS_ERR(ipcp))
- return PTR_ERR(ipcp);
+ down_write(&shm_ids(ns).rwsem);
+ rcu_read_lock();
+
+ ipcp = ipcctl_pre_down_nolock(ns, &shm_ids(ns), shmid, cmd,
+ &shmid64.shm_perm, 0);
+ if (IS_ERR(ipcp)) {
+ err = PTR_ERR(ipcp);
+ goto out_unlock1;
+ }
shp = container_of(ipcp, struct shmid_kernel, shm_perm);
err = security_shm_shmctl(shp, cmd);
if (err)
- goto out_unlock;
+ goto out_unlock1;
+
switch (cmd) {
case IPC_RMID:
+ ipc_lock_object(&shp->shm_perm);
+ /* do_shm_rmid unlocks the ipc object and rcu */
do_shm_rmid(ns, ipcp);
goto out_up;
case IPC_SET:
+ ipc_lock_object(&shp->shm_perm);
err = ipc_update_perm(&shmid64.shm_perm, ipcp);
if (err)
- goto out_unlock;
+ goto out_unlock0;
shp->shm_ctim = get_seconds();
break;
default:
err = -EINVAL;
+ goto out_unlock1;
}
-out_unlock:
- shm_unlock(shp);
+
+out_unlock0:
+ ipc_unlock_object(&shp->shm_perm);
+out_unlock1:
+ rcu_read_unlock();
out_up:
- up_write(&shm_ids(ns).rw_mutex);
+ up_write(&shm_ids(ns).rwsem);
return err;
}
-SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
+static int shmctl_nolock(struct ipc_namespace *ns, int shmid,
+ int cmd, int version, void __user *buf)
{
+ int err;
struct shmid_kernel *shp;
- int err, version;
- struct ipc_namespace *ns;
- if (cmd < 0 || shmid < 0) {
- err = -EINVAL;
- goto out;
+ /* preliminary security checks for *_INFO */
+ if (cmd == IPC_INFO || cmd == SHM_INFO) {
+ err = security_shm_shmctl(NULL, cmd);
+ if (err)
+ return err;
}
- version = ipc_parse_version(&cmd);
- ns = current->nsproxy->ipc_ns;
-
- switch (cmd) { /* replace with proc interface ? */
+ switch (cmd) {
case IPC_INFO:
{
struct shminfo64 shminfo;
- err = security_shm_shmctl(NULL, cmd);
- if (err)
- return err;
-
memset(&shminfo, 0, sizeof(shminfo));
shminfo.shmmni = shminfo.shmseg = ns->shm_ctlmni;
shminfo.shmmax = ns->shm_ctlmax;
@@ -816,9 +849,9 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
if(copy_shminfo_to_user (buf, &shminfo, version))
return -EFAULT;
- down_read(&shm_ids(ns).rw_mutex);
+ down_read(&shm_ids(ns).rwsem);
err = ipc_get_maxid(&shm_ids(ns));
- up_read(&shm_ids(ns).rw_mutex);
+ up_read(&shm_ids(ns).rwsem);
if(err<0)
err = 0;
@@ -828,19 +861,15 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
{
struct shm_info shm_info;
- err = security_shm_shmctl(NULL, cmd);
- if (err)
- return err;
-
memset(&shm_info, 0, sizeof(shm_info));
- down_read(&shm_ids(ns).rw_mutex);
+ down_read(&shm_ids(ns).rwsem);
shm_info.used_ids = shm_ids(ns).in_use;
shm_get_stat (ns, &shm_info.shm_rss, &shm_info.shm_swp);
shm_info.shm_tot = ns->shm_tot;
shm_info.swap_attempts = 0;
shm_info.swap_successes = 0;
err = ipc_get_maxid(&shm_ids(ns));
- up_read(&shm_ids(ns).rw_mutex);
+ up_read(&shm_ids(ns).rwsem);
if (copy_to_user(buf, &shm_info, sizeof(shm_info))) {
err = -EFAULT;
goto out;
@@ -855,27 +884,31 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
struct shmid64_ds tbuf;
int result;
+ rcu_read_lock();
if (cmd == SHM_STAT) {
- shp = shm_lock(ns, shmid);
+ shp = shm_obtain_object(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock;
}
result = shp->shm_perm.id;
} else {
- shp = shm_lock_check(ns, shmid);
+ shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock;
}
result = 0;
}
+
err = -EACCES;
if (ipcperms(ns, &shp->shm_perm, S_IRUGO))
goto out_unlock;
+
err = security_shm_shmctl(shp, cmd);
if (err)
goto out_unlock;
+
memset(&tbuf, 0, sizeof(tbuf));
kernel_to_ipc64_perm(&shp->shm_perm, &tbuf.shm_perm);
tbuf.shm_segsz = shp->shm_segsz;
@@ -885,43 +918,86 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
tbuf.shm_cpid = shp->shm_cprid;
tbuf.shm_lpid = shp->shm_lprid;
tbuf.shm_nattch = shp->shm_nattch;
- shm_unlock(shp);
- if(copy_shmid_to_user (buf, &tbuf, version))
+ rcu_read_unlock();
+
+ if (copy_shmid_to_user(buf, &tbuf, version))
err = -EFAULT;
else
err = result;
goto out;
}
+ default:
+ return -EINVAL;
+ }
+
+out_unlock:
+ rcu_read_unlock();
+out:
+ return err;
+}
+
+SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
+{
+ struct shmid_kernel *shp;
+ int err, version;
+ struct ipc_namespace *ns;
+
+ if (cmd < 0 || shmid < 0)
+ return -EINVAL;
+
+ version = ipc_parse_version(&cmd);
+ ns = current->nsproxy->ipc_ns;
+
+ switch (cmd) {
+ case IPC_INFO:
+ case SHM_INFO:
+ case SHM_STAT:
+ case IPC_STAT:
+ return shmctl_nolock(ns, shmid, cmd, version, buf);
+ case IPC_RMID:
+ case IPC_SET:
+ return shmctl_down(ns, shmid, cmd, buf, version);
case SHM_LOCK:
case SHM_UNLOCK:
{
struct file *shm_file;
- shp = shm_lock_check(ns, shmid);
+ rcu_read_lock();
+ shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock1;
}
audit_ipc_obj(&(shp->shm_perm));
+ err = security_shm_shmctl(shp, cmd);
+ if (err)
+ goto out_unlock1;
+ ipc_lock_object(&shp->shm_perm);
if (!ns_capable(ns->user_ns, CAP_IPC_LOCK)) {
kuid_t euid = current_euid();
- err = -EPERM;
if (!uid_eq(euid, shp->shm_perm.uid) &&
- !uid_eq(euid, shp->shm_perm.cuid))
- goto out_unlock;
- if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK))
- goto out_unlock;
+ !uid_eq(euid, shp->shm_perm.cuid)) {
+ err = -EPERM;
+ goto out_unlock0;
+ }
+ if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK)) {
+ err = -EPERM;
+ goto out_unlock0;
+ }
}
- err = security_shm_shmctl(shp, cmd);
- if (err)
- goto out_unlock;
-
shm_file = shp->shm_file;
+
+ /* check if shm_destroy() is tearing down shp */
+ if (shm_file == NULL) {
+ err = -EIDRM;
+ goto out_unlock0;
+ }
+
if (is_file_hugepages(shm_file))
- goto out_unlock;
+ goto out_unlock0;
if (cmd == SHM_LOCK) {
struct user_struct *user = current_user();
@@ -930,32 +1006,31 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
shp->shm_perm.mode |= SHM_LOCKED;
shp->mlock_user = user;
}
- goto out_unlock;
+ goto out_unlock0;
}
/* SHM_UNLOCK */
if (!(shp->shm_perm.mode & SHM_LOCKED))
- goto out_unlock;
+ goto out_unlock0;
shmem_lock(shm_file, 0, shp->mlock_user);
shp->shm_perm.mode &= ~SHM_LOCKED;
shp->mlock_user = NULL;
get_file(shm_file);
- shm_unlock(shp);
+ ipc_unlock_object(&shp->shm_perm);
+ rcu_read_unlock();
shmem_unlock_mapping(shm_file->f_mapping);
+
fput(shm_file);
- goto out;
- }
- case IPC_RMID:
- case IPC_SET:
- err = shmctl_down(ns, shmid, cmd, buf, version);
return err;
+ }
default:
return -EINVAL;
}
-out_unlock:
- shm_unlock(shp);
-out:
+out_unlock0:
+ ipc_unlock_object(&shp->shm_perm);
+out_unlock1:
+ rcu_read_unlock();
return err;
}
@@ -1023,10 +1098,11 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr,
* additional creator id...
*/
ns = current->nsproxy->ipc_ns;
- shp = shm_lock_check(ns, shmid);
+ rcu_read_lock();
+ shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock;
}
err = -EACCES;
@@ -1037,24 +1113,39 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr,
if (err)
goto out_unlock;
+ ipc_lock_object(&shp->shm_perm);
+
+ /* check if shm_destroy() is tearing down shp */
+ if (shp->shm_file == NULL) {
+ ipc_unlock_object(&shp->shm_perm);
+ err = -EIDRM;
+ goto out_unlock;
+ }
+
path = shp->shm_file->f_path;
path_get(&path);
shp->shm_nattch++;
size = i_size_read(path.dentry->d_inode);
- shm_unlock(shp);
+ ipc_unlock_object(&shp->shm_perm);
+ rcu_read_unlock();
err = -ENOMEM;
sfd = kzalloc(sizeof(*sfd), GFP_KERNEL);
- if (!sfd)
- goto out_put_dentry;
+ if (!sfd) {
+ path_put(&path);
+ goto out_nattch;
+ }
file = alloc_file(&path, f_mode,
is_file_hugepages(shp->shm_file) ?
&shm_file_operations_huge :
&shm_file_operations);
err = PTR_ERR(file);
- if (IS_ERR(file))
- goto out_free;
+ if (IS_ERR(file)) {
+ kfree(sfd);
+ path_put(&path);
+ goto out_nattch;
+ }
file->private_data = sfd;
file->f_mapping = shp->shm_file->f_mapping;
@@ -1080,7 +1171,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr,
addr > current->mm->start_stack - size - PAGE_SIZE * 5)
goto invalid;
}
-
+
addr = do_mmap_pgoff(file, addr, size, prot, flags, 0, &populate);
*raddr = addr;
err = 0;
@@ -1095,7 +1186,7 @@ out_fput:
fput(file);
out_nattch:
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
shp = shm_lock(ns, shmid);
BUG_ON(IS_ERR(shp));
shp->shm_nattch--;
@@ -1103,20 +1194,13 @@ out_nattch:
shm_destroy(ns, shp);
else
shm_unlock(shp);
- up_write(&shm_ids(ns).rw_mutex);
-
-out:
+ up_write(&shm_ids(ns).rwsem);
return err;
out_unlock:
- shm_unlock(shp);
- goto out;
-
-out_free:
- kfree(sfd);
-out_put_dentry:
- path_put(&path);
- goto out_nattch;
+ rcu_read_unlock();
+out:
+ return err;
}
SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg)
@@ -1221,8 +1305,7 @@ SYSCALL_DEFINE1(shmdt, char __user *, shmaddr)
#else /* CONFIG_MMU */
/* under NOMMU conditions, the exact address to be destroyed must be
* given */
- retval = -EINVAL;
- if (vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) {
+ if (vma && vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) {
do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start);
retval = 0;
}
diff --git a/ipc/util.c b/ipc/util.c
index 809ec5ec812..7684f41bce7 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -15,6 +15,29 @@
* Jun 2006 - namespaces ssupport
* OpenVZ, SWsoft Inc.
* Pavel Emelianov <xemul@openvz.org>
+ *
+ * General sysv ipc locking scheme:
+ * rcu_read_lock()
+ * obtain the ipc object (kern_ipc_perm) by looking up the id in an idr
+ * tree.
+ * - perform initial checks (capabilities, auditing and permission,
+ * etc).
+ * - perform read-only operations, such as STAT, INFO commands.
+ * acquire the ipc lock (kern_ipc_perm.lock) through
+ * ipc_lock_object()
+ * - perform data updates, such as SET, RMID commands and
+ * mechanism-specific operations (semop/semtimedop,
+ * msgsnd/msgrcv, shmat/shmdt).
+ * drop the ipc lock, through ipc_unlock_object().
+ * rcu_read_unlock()
+ *
+ * The ids->rwsem must be taken when:
+ * - creating, removing and iterating the existing entries in ipc
+ * identifier sets.
+ * - iterating through files under /proc/sysvipc/
+ *
+ * Note that sems have a special fast path that avoids kern_ipc_perm.lock -
+ * see sem_lock().
*/
#include <linux/mm.h>
@@ -119,7 +142,7 @@ __initcall(ipc_init);
void ipc_init_ids(struct ipc_ids *ids)
{
- init_rwsem(&ids->rw_mutex);
+ init_rwsem(&ids->rwsem);
ids->in_use = 0;
ids->seq = 0;
@@ -174,7 +197,7 @@ void __init ipc_init_proc_interface(const char *path, const char *header,
* @ids: Identifier set
* @key: The key to find
*
- * Requires ipc_ids.rw_mutex locked.
+ * Requires ipc_ids.rwsem locked.
* Returns the LOCKED pointer to the ipc structure if found or NULL
* if not.
* If key is found ipc points to the owning ipc structure
@@ -197,7 +220,8 @@ static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key)
continue;
}
- ipc_lock_by_ptr(ipc);
+ rcu_read_lock();
+ ipc_lock_object(ipc);
return ipc;
}
@@ -208,7 +232,7 @@ static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key)
* ipc_get_maxid - get the last assigned id
* @ids: IPC identifier set
*
- * Called with ipc_ids.rw_mutex held.
+ * Called with ipc_ids.rwsem held.
*/
int ipc_get_maxid(struct ipc_ids *ids)
@@ -246,9 +270,8 @@ int ipc_get_maxid(struct ipc_ids *ids)
* is returned. The 'new' entry is returned in a locked state on success.
* On failure the entry is not locked and a negative err-code is returned.
*
- * Called with ipc_ids.rw_mutex held as a writer.
+ * Called with writer ipc_ids.rwsem held.
*/
-
int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
{
kuid_t euid;
@@ -313,9 +336,9 @@ static int ipcget_new(struct ipc_namespace *ns, struct ipc_ids *ids,
{
int err;
- down_write(&ids->rw_mutex);
+ down_write(&ids->rwsem);
err = ops->getnew(ns, params);
- up_write(&ids->rw_mutex);
+ up_write(&ids->rwsem);
return err;
}
@@ -332,7 +355,7 @@ static int ipcget_new(struct ipc_namespace *ns, struct ipc_ids *ids,
*
* On success, the IPC id is returned.
*
- * It is called with ipc_ids.rw_mutex and ipcp->lock held.
+ * It is called with ipc_ids.rwsem and ipcp->lock held.
*/
static int ipc_check_perms(struct ipc_namespace *ns,
struct kern_ipc_perm *ipcp,
@@ -377,7 +400,7 @@ static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
* Take the lock as a writer since we are potentially going to add
* a new entry + read locks are not "upgradable"
*/
- down_write(&ids->rw_mutex);
+ down_write(&ids->rwsem);
ipcp = ipc_findkey(ids, params->key);
if (ipcp == NULL) {
/* key not used */
@@ -403,7 +426,7 @@ static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
}
ipc_unlock(ipcp);
}
- up_write(&ids->rw_mutex);
+ up_write(&ids->rwsem);
return err;
}
@@ -414,7 +437,7 @@ static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
* @ids: IPC identifier set
* @ipcp: ipc perm structure containing the identifier to remove
*
- * ipc_ids.rw_mutex (as a writer) and the spinlock for this ID are held
+ * ipc_ids.rwsem (as a writer) and the spinlock for this ID are held
* before this function is called, and remain locked on the exit.
*/
@@ -466,13 +489,6 @@ void ipc_free(void* ptr, int size)
kfree(ptr);
}
-struct ipc_rcu {
- struct rcu_head rcu;
- atomic_t refcount;
- /* "void *" makes sure alignment of following data is sane. */
- void *data[0];
-};
-
/**
* ipc_rcu_alloc - allocate ipc and rcu space
* @size: size desired
@@ -489,35 +505,34 @@ void *ipc_rcu_alloc(int size)
if (unlikely(!out))
return NULL;
atomic_set(&out->refcount, 1);
- return out->data;
+ return out + 1;
}
int ipc_rcu_getref(void *ptr)
{
- return atomic_inc_not_zero(&container_of(ptr, struct ipc_rcu, data)->refcount);
-}
+ struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1;
-/**
- * ipc_schedule_free - free ipc + rcu space
- * @head: RCU callback structure for queued work
- */
-static void ipc_schedule_free(struct rcu_head *head)
-{
- vfree(container_of(head, struct ipc_rcu, rcu));
+ return atomic_inc_not_zero(&p->refcount);
}
-void ipc_rcu_putref(void *ptr)
+void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head))
{
- struct ipc_rcu *p = container_of(ptr, struct ipc_rcu, data);
+ struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1;
if (!atomic_dec_and_test(&p->refcount))
return;
- if (is_vmalloc_addr(ptr)) {
- call_rcu(&p->rcu, ipc_schedule_free);
- } else {
- kfree_rcu(p, rcu);
- }
+ call_rcu(&p->rcu, func);
+}
+
+void ipc_rcu_free(struct rcu_head *head)
+{
+ struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+
+ if (is_vmalloc_addr(p))
+ vfree(p);
+ else
+ kfree(p);
}
/**
@@ -622,7 +637,7 @@ struct kern_ipc_perm *ipc_obtain_object(struct ipc_ids *ids, int id)
}
/**
- * ipc_lock - Lock an ipc structure without rw_mutex held
+ * ipc_lock - Lock an ipc structure without rwsem held
* @ids: IPC identifier set
* @id: ipc id to look for
*
@@ -678,22 +693,6 @@ out:
return out;
}
-struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id)
-{
- struct kern_ipc_perm *out;
-
- out = ipc_lock(ids, id);
- if (IS_ERR(out))
- return out;
-
- if (ipc_checkid(out, id)) {
- ipc_unlock(out);
- return ERR_PTR(-EIDRM);
- }
-
- return out;
-}
-
/**
* ipcget - Common sys_*get() code
* @ns : namsepace
@@ -734,7 +733,7 @@ int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
}
/**
- * ipcctl_pre_down - retrieve an ipc and check permissions for some IPC_XXX cmd
+ * ipcctl_pre_down_nolock - retrieve an ipc and check permissions for some IPC_XXX cmd
* @ns: the ipc namespace
* @ids: the table of ids where to look for the ipc
* @id: the id of the ipc to retrieve
@@ -747,39 +746,22 @@ int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
* It must be called without any lock held and
* - retrieves the ipc with the given id in the given table.
* - performs some audit and permission check, depending on the given cmd
- * - returns the ipc with both ipc and rw_mutex locks held in case of success
- * or an err-code without any lock held otherwise.
+ * - returns a pointer to the ipc object or otherwise, the corresponding error.
+ *
+ * Call holding the both the rwsem and the rcu read lock.
*/
-struct kern_ipc_perm *ipcctl_pre_down(struct ipc_namespace *ns,
- struct ipc_ids *ids, int id, int cmd,
- struct ipc64_perm *perm, int extra_perm)
-{
- struct kern_ipc_perm *ipcp;
-
- ipcp = ipcctl_pre_down_nolock(ns, ids, id, cmd, perm, extra_perm);
- if (IS_ERR(ipcp))
- goto out;
-
- spin_lock(&ipcp->lock);
-out:
- return ipcp;
-}
-
struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
- struct ipc_ids *ids, int id, int cmd,
- struct ipc64_perm *perm, int extra_perm)
+ struct ipc_ids *ids, int id, int cmd,
+ struct ipc64_perm *perm, int extra_perm)
{
kuid_t euid;
int err = -EPERM;
struct kern_ipc_perm *ipcp;
- down_write(&ids->rw_mutex);
- rcu_read_lock();
-
ipcp = ipc_obtain_object_check(ids, id);
if (IS_ERR(ipcp)) {
err = PTR_ERR(ipcp);
- goto out_up;
+ goto err;
}
audit_ipc_obj(ipcp);
@@ -790,16 +772,8 @@ struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
euid = current_euid();
if (uid_eq(euid, ipcp->cuid) || uid_eq(euid, ipcp->uid) ||
ns_capable(ns->user_ns, CAP_SYS_ADMIN))
- return ipcp;
-
-out_up:
- /*
- * Unsuccessful lookup, unlock and return
- * the corresponding error.
- */
- rcu_read_unlock();
- up_write(&ids->rw_mutex);
-
+ return ipcp; /* successful lookup */
+err:
return ERR_PTR(err);
}
@@ -856,7 +830,8 @@ static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos,
ipc = idr_find(&ids->ipcs_idr, pos);
if (ipc != NULL) {
*new_pos = pos + 1;
- ipc_lock_by_ptr(ipc);
+ rcu_read_lock();
+ ipc_lock_object(ipc);
return ipc;
}
}
@@ -894,7 +869,7 @@ static void *sysvipc_proc_start(struct seq_file *s, loff_t *pos)
* Take the lock - this will be released by the corresponding
* call to stop().
*/
- down_read(&ids->rw_mutex);
+ down_read(&ids->rwsem);
/* pos < 0 is invalid */
if (*pos < 0)
@@ -921,7 +896,7 @@ static void sysvipc_proc_stop(struct seq_file *s, void *it)
ids = &iter->ns->ids[iface->ids];
/* Release the lock we took in start() */
- up_read(&ids->rw_mutex);
+ up_read(&ids->rwsem);
}
static int sysvipc_proc_show(struct seq_file *s, void *it)
diff --git a/ipc/util.h b/ipc/util.h
index 2b0bdd5d92c..59d78aa9498 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -47,6 +47,13 @@ static inline void msg_exit_ns(struct ipc_namespace *ns) { }
static inline void shm_exit_ns(struct ipc_namespace *ns) { }
#endif
+struct ipc_rcu {
+ struct rcu_head rcu;
+ atomic_t refcount;
+} ____cacheline_aligned_in_smp;
+
+#define ipc_rcu_to_struct(p) ((void *)(p+1))
+
/*
* Structure that holds the parameters needed by the ipc operations
* (see after)
@@ -94,10 +101,10 @@ void __init ipc_init_proc_interface(const char *path, const char *header,
#define ipcid_to_idx(id) ((id) % SEQ_MULTIPLIER)
#define ipcid_to_seqx(id) ((id) / SEQ_MULTIPLIER)
-/* must be called with ids->rw_mutex acquired for writing */
+/* must be called with ids->rwsem acquired for writing */
int ipc_addid(struct ipc_ids *, struct kern_ipc_perm *, int);
-/* must be called with ids->rw_mutex acquired for reading */
+/* must be called with ids->rwsem acquired for reading */
int ipc_get_maxid(struct ipc_ids *);
/* must be called with both locks acquired. */
@@ -120,7 +127,8 @@ void ipc_free(void* ptr, int size);
*/
void* ipc_rcu_alloc(int size);
int ipc_rcu_getref(void *ptr);
-void ipc_rcu_putref(void *ptr);
+void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head));
+void ipc_rcu_free(struct rcu_head *head);
struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int);
struct kern_ipc_perm *ipc_obtain_object(struct ipc_ids *ids, int id);
@@ -131,9 +139,6 @@ int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out);
struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
struct ipc_ids *ids, int id, int cmd,
struct ipc64_perm *perm, int extra_perm);
-struct kern_ipc_perm *ipcctl_pre_down(struct ipc_namespace *ns,
- struct ipc_ids *ids, int id, int cmd,
- struct ipc64_perm *perm, int extra_perm);
#ifndef CONFIG_ARCH_WANT_IPC_PARSE_VERSION
/* On IA-64, we always use the "64-bit version" of the IPC structures. */
@@ -143,9 +148,9 @@ int ipc_parse_version (int *cmd);
#endif
extern void free_msg(struct msg_msg *msg);
-extern struct msg_msg *load_msg(const void __user *src, int len);
+extern struct msg_msg *load_msg(const void __user *src, size_t len);
extern struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst);
-extern int store_msg(void __user *dest, struct msg_msg *msg, int len);
+extern int store_msg(void __user *dest, struct msg_msg *msg, size_t len);
extern void recompute_msgmni(struct ipc_namespace *);
@@ -159,24 +164,27 @@ static inline int ipc_checkid(struct kern_ipc_perm *ipcp, int uid)
return uid / SEQ_MULTIPLIER != ipcp->seq;
}
-static inline void ipc_lock_by_ptr(struct kern_ipc_perm *perm)
+static inline void ipc_lock_object(struct kern_ipc_perm *perm)
{
- rcu_read_lock();
spin_lock(&perm->lock);
}
-static inline void ipc_unlock(struct kern_ipc_perm *perm)
+static inline void ipc_unlock_object(struct kern_ipc_perm *perm)
{
spin_unlock(&perm->lock);
- rcu_read_unlock();
}
-static inline void ipc_lock_object(struct kern_ipc_perm *perm)
+static inline void ipc_assert_locked_object(struct kern_ipc_perm *perm)
{
- spin_lock(&perm->lock);
+ assert_spin_locked(&perm->lock);
+}
+
+static inline void ipc_unlock(struct kern_ipc_perm *perm)
+{
+ ipc_unlock_object(perm);
+ rcu_read_unlock();
}
-struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id);
struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id);
int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids,
struct ipc_ops *ops, struct ipc_params *params);
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-07 09:24:26 +0000