Merge branch 'master' into for-3.9-async

To receive f56c3196f251012de9b3ebaff55732a9074fdaae ("async: fix
__lowest_in_progress()").

Signed-off-by: Tejun Heo <tj@kernel.org>

7 files changed, 207 insertions, 58 deletions

diff --git a/ipc/compat.c b/ipc/compat.c
index ad9518eb26e0..2547f29dcd1b 100644
--- a/ipc/compat.c
+++ b/ipc/compat.c
@@ -306,6 +306,20 @@ static long do_compat_semctl(int first, int second, int third, u32 pad)
 	return err;
 }
 
+long compat_do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz)
+{
+	struct compat_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_ARCH_WANT_OLD_COMPAT_IPC
 long compat_sys_semctl(int first, int second, int third, void __user *uptr)
 {
@@ -337,10 +351,6 @@ long compat_sys_msgsnd(int first, int second, int third, void __user *uptr)
 long compat_sys_msgrcv(int first, int second, int msgtyp, int third,
 			   int version, void __user *uptr)
 {
-	struct compat_msgbuf __user *up;
-	long type;
-	int err;
-
 	if (first < 0)
 		return -EINVAL;
 	if (second < 0)
@@ -348,23 +358,15 @@ long compat_sys_msgrcv(int first, int second, int msgtyp, int third,
 
 	if (!version) {
 		struct compat_ipc_kludge ipck;
-		err = -EINVAL;
 		if (!uptr)
-			goto out;
-		err = -EFAULT;
+			return -EINVAL;
 		if (copy_from_user (&ipck, uptr, sizeof(ipck)))
-			goto out;
+			return -EFAULT;
 		uptr = compat_ptr(ipck.msgp);
 		msgtyp = ipck.msgtyp;
 	}
-	up = uptr;
-	err = do_msgrcv(first, &type, up->mtext, second, msgtyp, third);
-	if (err < 0)
-		goto out;
-	if (put_user(type, &up->mtype))
-		err = -EFAULT;
-out:
-	return err;
+	return do_msgrcv(first, uptr, second, msgtyp, third,
+			 compat_do_msg_fill);
 }
 #else
 long compat_sys_semctl(int semid, int semnum, int cmd, int arg)
@@ -385,16 +387,8 @@ long compat_sys_msgsnd(int msqid, struct compat_msgbuf __user *msgp,
 long compat_sys_msgrcv(int msqid, struct compat_msgbuf __user *msgp,
 		       compat_ssize_t msgsz, long msgtyp, int msgflg)
 {
-	long err, mtype;
-
-	err =  do_msgrcv(msqid, &mtype, msgp->mtext, (ssize_t)msgsz, msgtyp, msgflg);
-	if (err < 0)
-		goto out;
-
-	if (put_user(mtype, &msgp->mtype))
-		err = -EFAULT;
- out:
-	return err;
+	return do_msgrcv(msqid, msgp, (ssize_t)msgsz, msgtyp, msgflg,
+			 compat_do_msg_fill);
 }
 #endif
 
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index 00fba2bab87d..130dfece27ac 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -158,6 +158,9 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write,
 
 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[] = {
 	{
@@ -227,6 +230,35 @@ static struct ctl_table ipc_kern_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	{
+		.procname	= "sem_next_id",
+		.data		= &init_ipc_ns.ids[IPC_SEM_IDS].next_id,
+		.maxlen		= sizeof(init_ipc_ns.ids[IPC_SEM_IDS].next_id),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
+	},
+	{
+		.procname	= "msg_next_id",
+		.data		= &init_ipc_ns.ids[IPC_MSG_IDS].next_id,
+		.maxlen		= sizeof(init_ipc_ns.ids[IPC_MSG_IDS].next_id),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
+	},
+	{
+		.procname	= "shm_next_id",
+		.data		= &init_ipc_ns.ids[IPC_SHM_IDS].next_id,
+		.maxlen		= sizeof(init_ipc_ns.ids[IPC_SHM_IDS].next_id),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
+	},
+#endif
 	{}
 };
 
diff --git a/ipc/msg.c b/ipc/msg.c
index a71af5a65abf..950572f9d796 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -755,26 +755,91 @@ 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,
+					   int msgflg, long *msgtyp,
+					   unsigned long *copy_number)
+{
+	struct msg_msg *copy;
+
+	*copy_number = *msgtyp;
+	*msgtyp = 0;
+	/*
+	 * 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,
+					   int msgflg, long *msgtyp,
+					   unsigned long *copy_number)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline void free_copy(struct msg_msg *copy)
+{
+}
+#endif
+
+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 ipc_namespace *ns;
+	struct msg_msg *copy = NULL;
+	unsigned long copy_number = 0;
 
-	if (msqid < 0 || (long) msgsz < 0)
+	if (msqid < 0 || (long) bufsz < 0)
 		return -EINVAL;
+	if (msgflg & MSG_COPY) {
+		copy = prepare_copy(buf, bufsz, msgflg, &msgtyp, &copy_number);
+		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))
+	if (IS_ERR(msq)) {
+		free_copy(copy);
 		return PTR_ERR(msq);
+	}
 
 	for (;;) {
 		struct msg_receiver msr_d;
 		struct list_head *tmp;
+		long msg_counter = 0;
 
 		msg = ERR_PTR(-EACCES);
 		if (ipcperms(ns, &msq->q_perm, S_IRUGO))
@@ -793,12 +858,21 @@ long do_msgrcv(int msqid, long *pmtype, void __user *mtext,
 				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;
+				} else if (msgflg & MSG_COPY) {
+					if (copy_number == msg_counter) {
+						/*
+						 * Found requested message.
+						 * Copy it.
+						 */
+						msg = copy_msg(msg, copy);
+						if (IS_ERR(msg))
+							goto out_unlock;
+						break;
+					}
+				} else
 					break;
-				}
+				msg_counter++;
 			}
 			tmp = tmp->next;
 		}
@@ -807,10 +881,16 @@ long do_msgrcv(int msqid, long *pmtype, void __user *mtext,
 			 * 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;
 			}
+			/*
+			 * If we are copying, then do not unlink message and do
+			 * not update queue parameters.
+			 */
+			if (msgflg & MSG_COPY)
+				goto out_unlock;
 			list_del(&msg->m_list);
 			msq->q_qnum--;
 			msq->q_rtime = get_seconds();
@@ -834,7 +914,7 @@ 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);
@@ -894,32 +974,21 @@ out_unlock:
 			break;
 		}
 	}
-	if (IS_ERR(msg))
+	if (IS_ERR(msg)) {
+		free_copy(copy);
 		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;
-
+	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;
-
-	err =  do_msgrcv(msqid, &mtype, msgp->mtext, msgsz, msgtyp, msgflg);
-	if (err < 0)
-		goto out;
-
-	if (put_user(mtype, &msgp->mtype))
-		err = -EFAULT;
-out:
-	return err;
+	return do_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg, do_msg_fill);
 }
 
 #ifdef CONFIG_PROC_FS
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
index 6471f1bdae96..ebfcbfa8b7f2 100644
--- a/ipc/msgutil.c
+++ b/ipc/msgutil.c
@@ -102,7 +102,50 @@ out_err:
 	free_msg(msg);
 	return ERR_PTR(err);
 }
+#ifdef CONFIG_CHECKPOINT_RESTORE
+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;
+
+	BUG_ON(dst == NULL);
+	if (src->m_ts > dst->m_ts)
+		return ERR_PTR(-EINVAL);
 
+	alen = len;
+	if (alen > DATALEN_MSG)
+		alen = DATALEN_MSG;
+
+	dst->next = NULL;
+	dst->security = NULL;
+
+	memcpy(dst + 1, src + 1, alen);
+
+	len -= alen;
+	dst_pseg = dst->next;
+	src_pseg = src->next;
+	while (len > 0) {
+		alen = len;
+		if (alen > DATALEN_SEG)
+			alen = DATALEN_SEG;
+		memcpy(dst_pseg + 1, src_pseg + 1, alen);
+		dst_pseg = dst_pseg->next;
+		len -= alen;
+		src_pseg = src_pseg->next;
+	}
+
+	dst->m_type = src->m_type;
+	dst->m_ts = src->m_ts;
+
+	return dst;
+}
+#else
+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 alen;
diff --git a/ipc/namespace.c b/ipc/namespace.c
index cf3386a51de2..7c1fa451b0b0 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -170,7 +170,8 @@ static void ipcns_put(void *ns)
 static int ipcns_install(struct nsproxy *nsproxy, void *new)
 {
 	struct ipc_namespace *ns = new;
-	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
+	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
+	    !nsown_capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
 	/* Ditch state from the old ipc namespace */
diff --git a/ipc/util.c b/ipc/util.c
index 72fd0785ac94..74e1d9c7a98a 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -122,6 +122,7 @@ void ipc_init_ids(struct ipc_ids *ids)
 
 	ids->in_use = 0;
 	ids->seq = 0;
+	ids->next_id = -1;
 	{
 		int seq_limit = INT_MAX/SEQ_MULTIPLIER;
 		if (seq_limit > USHRT_MAX)
@@ -252,6 +253,7 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
 	kuid_t euid;
 	kgid_t egid;
 	int id, err;
+	int next_id = ids->next_id;
 
 	if (size > IPCMNI)
 		size = IPCMNI;
@@ -264,7 +266,8 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
 	rcu_read_lock();
 	spin_lock(&new->lock);
 
-	err = idr_get_new(&ids->ipcs_idr, new, &id);
+	err = idr_get_new_above(&ids->ipcs_idr, new,
+				(next_id < 0) ? 0 : ipcid_to_idx(next_id), &id);
 	if (err) {
 		spin_unlock(&new->lock);
 		rcu_read_unlock();
@@ -277,9 +280,14 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
 	new->cuid = new->uid = euid;
 	new->gid = new->cgid = egid;
 
-	new->seq = ids->seq++;
-	if(ids->seq > ids->seq_max)
-		ids->seq = 0;
+	if (next_id < 0) {
+		new->seq = ids->seq++;
+		if (ids->seq > ids->seq_max)
+			ids->seq = 0;
+	} else {
+		new->seq = ipcid_to_seqx(next_id);
+		ids->next_id = -1;
+	}
 
 	new->id = ipc_buildid(id, new->seq);
 	return id;
diff --git a/ipc/util.h b/ipc/util.h
index c8fe2f7631e9..eeb79a1fbd83 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -92,6 +92,7 @@ void __init ipc_init_proc_interface(const char *path, const char *header,
 #define IPC_SHM_IDS	2
 
 #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 */
 int ipc_addid(struct ipc_ids *, struct kern_ipc_perm *, int);
@@ -139,6 +140,7 @@ int ipc_parse_version (int *cmd);
 
 extern void free_msg(struct msg_msg *msg);
 extern struct msg_msg *load_msg(const void __user *src, int 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 void recompute_msgmni(struct ipc_namespace *);