Powerpc KVM work is based on a commit after rc4.

Merging master into next to satisfy the dependencies.

Conflicts:
	arch/arm/kvm/reset.c

5 files changed, 200 insertions, 105 deletions

diff --git a/ipc/msg.c b/ipc/msg.c
index b0d541d42677..558aa91186b6 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -165,6 +165,15 @@ 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
@@ -189,15 +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 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;
 	}
 
@@ -276,8 +284,7 @@ static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 		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);
 }
 
 /*
@@ -688,6 +695,12 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
 		if (ipcperms(ns, &msq->q_perm, S_IWUGO))
 			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_unlock0;
@@ -717,7 +730,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
 		rcu_read_lock();
 		ipc_lock_object(&msq->q_perm);
 
-		ipc_rcu_putref(msq);
+		ipc_rcu_putref(msq, ipc_rcu_free);
 		if (msq->q_perm.deleted) {
 			err = -EIDRM;
 			goto out_unlock0;
@@ -894,6 +907,13 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgfl
 			goto out_unlock1;
 
 		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)) {
 			/*
diff --git a/ipc/sem.c b/ipc/sem.c
index 69b6a21f3844..8c4f59b0204a 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -243,71 +243,122 @@ static void merge_queues(struct sem_array *sma)
 	}
 }
 
+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:
-		ipc_lock_object(&sma->sem_perm);
-		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)
@@ -374,12 +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)
@@ -458,14 +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;
@@ -873,6 +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
@@ -922,17 +985,10 @@ static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsop
 			}
 		}
 	}
-	if (otime) {
-		if (sops == NULL) {
-			sma->sem_base[0].sem_otime = get_seconds();
-		} else {
-			sma->sem_base[sops[0].sem_num].sem_otime =
-								get_seconds();
-		}
-	}
+	if (otime)
+		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
@@ -1047,8 +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)
@@ -1292,7 +1347,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 			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;
 			}
 
@@ -1328,20 +1383,20 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		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;
 			}
@@ -1629,7 +1684,7 @@ 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);
 	}
 
@@ -1795,12 +1850,17 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 
 	error = perform_atomic_semop(sma, sops, nsops, un,
 					task_tgid_vnr(current));
-	if (error <= 0) {
-		if (alter && error == 0)
+	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.
@@ -2059,6 +2119,14 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it)
 	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,
diff --git a/ipc/shm.c b/ipc/shm.c
index 2821cdf93adb..d69739610fd4 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -167,6 +167,15 @@ static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp)
 	ipc_lock_object(&ipcp->shm_perm);
 }
 
+static void shm_rcu_free(struct rcu_head *head)
+{
+	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+	struct shmid_kernel *shp = ipc_rcu_to_struct(p);
+
+	security_shm_free(shp);
+	ipc_rcu_free(head);
+}
+
 static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
 {
 	ipc_rmid(&shm_ids(ns), &s->shm_perm);
@@ -208,8 +217,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
 		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);
+	ipc_rcu_putref(shp, shm_rcu_free);
 }
 
 /*
@@ -497,7 +505,7 @@ 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;
 	}
 
@@ -566,8 +574,7 @@ 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;
 }
 
diff --git a/ipc/util.c b/ipc/util.c
index e829da9ed01f..fdb8ae740775 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -474,11 +474,6 @@ void ipc_free(void* ptr, int size)
 		kfree(ptr);
 }
 
-struct ipc_rcu {
-	struct rcu_head rcu;
-	atomic_t refcount;
-} ____cacheline_aligned_in_smp;
-
 /**
  *	ipc_rcu_alloc	-	allocate ipc and rcu space 
  *	@size: size desired
@@ -505,27 +500,24 @@ int ipc_rcu_getref(void *ptr)
 	return atomic_inc_not_zero(&p->refcount);
 }
 
-/**
- * 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));
-}
-
-void ipc_rcu_putref(void *ptr)
+void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head))
 {
 	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);
 }
 
 /**
diff --git a/ipc/util.h b/ipc/util.h
index c5f3338ba1fa..f2f5036f2eed 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)
@@ -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);