/* return EEXIST if the same logger is registered, 0 on success. */
int nf_log_register(u_int8_t pf, struct nf_logger *logger)
{
	int i;
	int ret = 0;

	if (pf >= ARRAY_SIZE(init_net.nf.nf_loggers))
		return -EINVAL;

	mutex_lock(&nf_log_mutex);

	if (pf == NFPROTO_UNSPEC) {
		for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) {
			if (rcu_access_pointer(loggers[i][logger->type])) {
				ret = -EEXIST;
				goto unlock;
			}
		}
		for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++)
			rcu_assign_pointer(loggers[i][logger->type], logger);
	} else {
		if (rcu_access_pointer(loggers[pf][logger->type])) {
			ret = -EEXIST;
			goto unlock;
		}
		rcu_assign_pointer(loggers[pf][logger->type], logger);
	}

unlock:
	mutex_unlock(&nf_log_mutex);
	return ret;
}

/**
 * bus1_queue_relink() - change sequence number of an entry
 * @queue:	queue to operate on
 * @entry:	entry to relink
 * @seq:	sequence number to set
 *
 * This changes the sequence number of @entry to @seq. The caller must
 * guarantee that the entry was already linked with an odd-numbered sequence
 * number. This will unlink the entry, change the sequence number and link it
 * again.
 *
 * The caller must hold the write-side peer-lock of the parent peer.
 *
 * Return: True if the queue became readable with this call.
 */
bool bus1_queue_relink(struct bus1_queue *queue,
		       struct bus1_queue_entry *entry,
		       u64 seq)
{
	struct rb_node *front;

	if (WARN_ON(seq == 0 ||
		    RB_EMPTY_NODE(&entry->rb) ||
		    !(entry->seq & 1)))
		return false;

	bus1_queue_assert_held(queue);

	/* remember front, cannot point to @entry */
	front = rcu_access_pointer(queue->front);
	WARN_ON(front == &entry->rb);

	/* drop from rb-tree and insert again */
	rb_erase(&entry->rb, &queue->messages);
	RB_CLEAR_NODE(&entry->rb);
	bus1_queue_link(queue, entry, seq);

	/* if this uncovered a front, then the queue became readable */
	return !front && rcu_access_pointer(queue->front);
}

static int bnxt_unregister_dev(struct bnxt_en_dev *edev, int ulp_id)
{
	struct net_device *dev = edev->net;
	struct bnxt *bp = netdev_priv(dev);
	struct bnxt_ulp *ulp;
	int i = 0;

	ASSERT_RTNL();
	if (ulp_id >= BNXT_MAX_ULP)
		return -EINVAL;

	ulp = &edev->ulp_tbl[ulp_id];
	if (!rcu_access_pointer(ulp->ulp_ops)) {
		netdev_err(bp->dev, "ulp id %d not registered\n", ulp_id);
		return -EINVAL;
	}
	if (ulp_id == BNXT_ROCE_ULP && ulp->msix_requested)
		edev->en_ops->bnxt_free_msix(edev, ulp_id);

	if (ulp->max_async_event_id)
		bnxt_hwrm_func_rgtr_async_events(bp, NULL, 0);

	RCU_INIT_POINTER(ulp->ulp_ops, NULL);
	synchronize_rcu();
	ulp->max_async_event_id = 0;
	ulp->async_events_bmap = NULL;
	while (atomic_read(&ulp->ref_count) != 0 && i < 10) {
		msleep(100);
		i++;
	}
	return 0;
}

void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
			   const struct sk_buff *skb)
{
	struct flow_stats *stats;
	int node = numa_node_id();

	stats = rcu_dereference(flow->stats[node]);

	/* Check if already have node-specific stats. */
	if (likely(stats)) {
		spin_lock(&stats->lock);
		/* Mark if we write on the pre-allocated stats. */
		if (node == 0 && unlikely(flow->stats_last_writer != node))
			flow->stats_last_writer = node;
	} else {
		stats = rcu_dereference(flow->stats[0]); /* Pre-allocated. */
		spin_lock(&stats->lock);

		/* If the current NUMA-node is the only writer on the
		 * pre-allocated stats keep using them.
		 */
		if (unlikely(flow->stats_last_writer != node)) {
			/* A previous locker may have already allocated the
			 * stats, so we need to check again.  If node-specific
			 * stats were already allocated, we update the pre-
			 * allocated stats as we have already locked them.
			 */
			if (likely(flow->stats_last_writer != NUMA_NO_NODE)
			    && likely(!rcu_access_pointer(flow->stats[node]))) {
				/* Try to allocate node-specific stats. */
				struct flow_stats *new_stats;

				new_stats =
					kmem_cache_alloc_node(flow_stats_cache,
							      GFP_THISNODE |
							      __GFP_NOMEMALLOC,
							      node);
				if (likely(new_stats)) {
					new_stats->used = jiffies;
					new_stats->packet_count = 1;
					new_stats->byte_count = skb->len;
					new_stats->tcp_flags = tcp_flags;
					spin_lock_init(&new_stats->lock);

					rcu_assign_pointer(flow->stats[node],
							   new_stats);
					goto unlock;
				}
			}
			flow->stats_last_writer = node;
		}
	}

	stats->used = jiffies;
	stats->packet_count++;
	stats->byte_count += skb->len;
	stats->tcp_flags |= tcp_flags;
unlock:
	spin_unlock(&stats->lock);
}

static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb)
#endif
{
	struct net_device_context *net_device_ctx = netdev_priv(ndev);
	struct netvsc_device *nvsc_dev = net_device_ctx->nvdev;
	struct sock *sk = skb->sk;
	int q_idx = sk_tx_queue_get(sk);

	if (q_idx < 0 || skb->ooo_okay ||
	    q_idx >= ndev->real_num_tx_queues) {
		u16 hash = __skb_tx_hash(ndev, skb, VRSS_SEND_TAB_SIZE);
		int new_idx;

		new_idx = nvsc_dev->send_table[hash]
			% nvsc_dev->num_chn;

		if (q_idx != new_idx && sk &&
		    sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache))
			sk_tx_queue_set(sk, new_idx);

		q_idx = new_idx;
	}

	if (unlikely(!nvsc_dev->chan_table[q_idx].channel))
		q_idx = 0;
	
	return q_idx;
}

int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog)
{
	struct sock_reuseport *reuse;
	struct bpf_prog *old_prog;

	if (sk_unhashed(sk) && sk->sk_reuseport) {
		int err = reuseport_alloc(sk, false);

		if (err)
			return err;
	} else if (!rcu_access_pointer(sk->sk_reuseport_cb)) {
		/* The socket wasn't bound with SO_REUSEPORT */
		return -EINVAL;
	}

	spin_lock_bh(&reuseport_lock);
	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
					  lockdep_is_held(&reuseport_lock));
	old_prog = rcu_dereference_protected(reuse->prog,
					     lockdep_is_held(&reuseport_lock));
	rcu_assign_pointer(reuse->prog, prog);
	spin_unlock_bh(&reuseport_lock);

	sk_reuseport_prog_free(old_prog);
	return 0;
}

int nf_logger_find_get(int pf, enum nf_log_type type)
{
	struct nf_logger *logger;
	int ret = -ENOENT;

	if (pf == NFPROTO_INET) {
		ret = nf_logger_find_get(NFPROTO_IPV4, type);
		if (ret < 0)
			return ret;

		ret = nf_logger_find_get(NFPROTO_IPV6, type);
		if (ret < 0) {
			nf_logger_put(NFPROTO_IPV4, type);
			return ret;
		}

		return 0;
	}

	if (rcu_access_pointer(loggers[pf][type]) == NULL)
		request_module("nf-logger-%u-%u", pf, type);

	rcu_read_lock();
	logger = rcu_dereference(loggers[pf][type]);
	if (logger == NULL)
		goto out;

	if (try_module_get(logger->me))
		ret = 0;
out:
	rcu_read_unlock();
	return ret;
}

static void bss_free(struct cfg80211_internal_bss *bss)
{
	struct cfg80211_bss_ies *ies;

	if (WARN_ON(atomic_read(&bss->hold)))
		return;

	ies = (void *)rcu_access_pointer(bss->pub.beacon_ies);
	if (ies && !bss->pub.hidden_beacon_bss)
		kfree_rcu(ies, rcu_head);
	ies = (void *)rcu_access_pointer(bss->pub.proberesp_ies);
	if (ies)
		kfree_rcu(ies, rcu_head);

	if (!list_empty(&bss->hidden_list))
		list_del(&bss->hidden_list);

	kfree(bss);
}

static void trie_free(struct bpf_map *map)
{
	struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
	struct lpm_trie_node __rcu **slot;
	struct lpm_trie_node *node;

	raw_spin_lock(&trie->lock);

	/* Always start at the root and walk down to a node that has no
	 * children. Then free that node, nullify its reference in the parent
	 * and start over.
	 */

	for (;;) {
		slot = &trie->root;

		for (;;) {
			node = rcu_dereference_protected(*slot,
					lockdep_is_held(&trie->lock));
			if (!node)
				goto unlock;

			if (rcu_access_pointer(node->child[0])) {
				slot = &node->child[0];
				continue;
			}

			if (rcu_access_pointer(node->child[1])) {
				slot = &node->child[1];
				continue;
			}

			kfree(node);
			RCU_INIT_POINTER(*slot, NULL);
			break;
		}
	}

unlock:
	raw_spin_unlock(&trie->lock);
}

/*
 * release an RxRPC socket
 */
static int rxrpc_release_sock(struct sock *sk)
{
	struct rxrpc_sock *rx = rxrpc_sk(sk);
	struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk));

	_enter("%p{%d,%d}", sk, sk->sk_state, refcount_read(&sk->sk_refcnt));

	/* declare the socket closed for business */
	sock_orphan(sk);
	sk->sk_shutdown = SHUTDOWN_MASK;

	/* We want to kill off all connections from a service socket
	 * as fast as possible because we can't share these; client
	 * sockets, on the other hand, can share an endpoint.
	 */
	switch (sk->sk_state) {
	case RXRPC_SERVER_BOUND:
	case RXRPC_SERVER_BOUND2:
	case RXRPC_SERVER_LISTENING:
	case RXRPC_SERVER_LISTEN_DISABLED:
		rx->local->service_closed = true;
		break;
	}

	spin_lock_bh(&sk->sk_receive_queue.lock);
	sk->sk_state = RXRPC_CLOSE;
	spin_unlock_bh(&sk->sk_receive_queue.lock);

	if (rx->local && rcu_access_pointer(rx->local->service) == rx) {
		write_lock(&rx->local->services_lock);
		rcu_assign_pointer(rx->local->service, NULL);
		write_unlock(&rx->local->services_lock);
	}

	/* try to flush out this socket */
	rxrpc_discard_prealloc(rx);
	rxrpc_release_calls_on_socket(rx);
	flush_workqueue(rxrpc_workqueue);
	rxrpc_purge_queue(&sk->sk_receive_queue);
	rxrpc_queue_work(&rxnet->service_conn_reaper);
	rxrpc_queue_work(&rxnet->client_conn_reaper);

	rxrpc_put_local(rx->local);
	rx->local = NULL;
	key_put(rx->key);
	rx->key = NULL;
	key_put(rx->securities);
	rx->securities = NULL;
	sock_put(sk);

	_leave(" = 0");
	return 0;
}

/* by default VRF devices do not have a qdisc and are expected
 * to be created with only a single queue.
 */
static bool qdisc_tx_is_default(const struct net_device *dev)
{
	struct netdev_queue *txq;
	struct Qdisc *qdisc;

	if (dev->num_tx_queues > 1)
		return false;

	txq = netdev_get_tx_queue(dev, 0);
	qdisc = rcu_access_pointer(txq->qdisc);

	return !qdisc->enqueue;
}

/*
 * Destroy a cell record
 */
static void afs_cell_destroy(struct rcu_head *rcu)
{
	struct afs_cell *cell = container_of(rcu, struct afs_cell, rcu);

	_enter("%p{%s}", cell, cell->name);

	ASSERTCMP(atomic_read(&cell->usage), ==, 0);

	afs_put_vlserverlist(cell->net, rcu_access_pointer(cell->vl_servers));
	key_put(cell->anonymous_key);
	kfree(cell);

	_leave(" [destroyed]");
}

static void bss_free(struct cfg80211_internal_bss *bss)
{
	struct cfg80211_bss_ies *ies;

	if (WARN_ON(atomic_read(&bss->hold)))
		return;

	ies = (void *)rcu_access_pointer(bss->pub.beacon_ies);
	if (ies && !bss->pub.hidden_beacon_bss)
		kfree_rcu(ies, rcu_head);
	ies = (void *)rcu_access_pointer(bss->pub.proberesp_ies);
	if (ies)
		kfree_rcu(ies, rcu_head);

	/*
	 * This happens when the module is removed, it doesn't
	 * really matter any more save for completeness
	 */
	if (!list_empty(&bss->hidden_list))
		list_del(&bss->hidden_list);

	kfree(bss);
}

/*
 * Return the number of omx ifaces.
 */
int
omx_ifaces_get_count(void)
{
	int i, count = 0;

	/* no need to lock since the array of iface is always coherent
	 * and we don't access the internals of the ifaces
	 */
	for (i=0; i<omx_iface_max; i++)
		if (rcu_access_pointer(omx_ifaces[i]) != NULL)
			count++;

	return count;
}

/*
 * Compare new packet with random packet in queue
 * returns true if matched and sets *pidx
 */
static bool choke_match_random(const struct choke_sched_data *q,
			       struct sk_buff *nskb,
			       unsigned int *pidx)
{
	struct sk_buff *oskb;

	if (q->head == q->tail)
		return false;

	oskb = choke_peek_random(q, pidx);
	if (rcu_access_pointer(q->filter_list))
		return choke_get_classid(nskb) == choke_get_classid(oskb);

	return choke_match_flow(oskb, nskb);
}

/*
 * Display the name of the current workstation cell.
 */
static int afs_proc_rootcell_show(struct seq_file *m, void *v)
{
	struct afs_cell *cell;
	struct afs_net *net;

	net = afs_seq2net_single(m);
	if (rcu_access_pointer(net->ws_cell)) {
		rcu_read_lock();
		cell = rcu_dereference(net->ws_cell);
		if (cell)
			seq_printf(m, "%s\n", cell->name);
		rcu_read_unlock();
	}
	return 0;
}

/* Returns null if this device is not attached to a datapath. */
struct vport *netdev_get_vport(struct net_device *dev)
{
#ifdef IFF_BRIDGE_PORT
#if IFF_BRIDGE_PORT != IFF_OVS_DATAPATH
	if (likely(dev->priv_flags & IFF_OVS_DATAPATH))
#else
	if (likely(rcu_access_pointer(dev->rx_handler) == netdev_frame_hook))	
#endif
		return (struct vport *)rcu_dereference_rtnl(dev->rx_handler_data);
	else
		return NULL;
#else
	return (struct vport *)rcu_dereference_rtnl(dev->br_port);
#endif
}

/* Returns null if this device is not attached to a datapath. */
struct vport *ovs_netdev_get_vport(struct net_device *dev)
{
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,36)
#if IFF_OVS_DATAPATH != 0
	if (likely(dev->priv_flags & IFF_OVS_DATAPATH))
#else
	if (likely(rcu_access_pointer(dev->rx_handler) == netdev_frame_hook))
#endif
		return (struct vport *)rcu_dereference_rtnl(dev->rx_handler_data);
	else
		return NULL;
#else
	return (struct vport *)rcu_dereference_rtnl(dev->br_port);
#endif
}

/* Returns null if this device is not attached to a datapath. */
struct vport *ovs_netdev_get_vport(struct net_device *dev)
{
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,36) || \
    defined HAVE_RHEL_OVS_HOOK
#if IFF_OVS_DATAPATH != 0
	if (likely(dev->priv_flags & IFF_OVS_DATAPATH))
#else
	if (likely(rcu_access_pointer(dev->rx_handler) == netdev_frame_hook))
#endif
#ifdef HAVE_RHEL_OVS_HOOK
		return (struct vport *)rcu_dereference_rtnl(dev->ax25_ptr);
#else
		return (struct vport *)rcu_dereference_rtnl(dev->rx_handler_data);
#endif
	else
		return NULL;

/*
 * set the root cell information
 * - can be called with a module parameter string
 * - can be called from a write to /proc/fs/afs/rootcell
 */
int afs_cell_init(struct afs_net *net, const char *rootcell)
{
	struct afs_cell *old_root, *new_root;
	const char *cp, *vllist;
	size_t len;

	_enter("");

	if (!rootcell) {
		/* module is loaded with no parameters, or built statically.
		 * - in the future we might initialize cell DB here.
		 */
		_leave(" = 0 [no root]");
		return 0;
	}

	cp = strchr(rootcell, ':');
	if (!cp) {
		_debug("kAFS: no VL server IP addresses specified");
		vllist = NULL;
		len = strlen(rootcell);
	} else {
		vllist = cp + 1;
		len = cp - rootcell;
	}

	/* allocate a cell record for the root cell */
	new_root = afs_lookup_cell(net, rootcell, len, vllist, false);
	if (IS_ERR(new_root)) {
		_leave(" = %ld", PTR_ERR(new_root));
		return PTR_ERR(new_root);
	}

	if (!test_and_set_bit(AFS_CELL_FL_NO_GC, &new_root->flags))
		afs_get_cell(new_root);

	/* install the new cell */
	write_seqlock(&net->cells_lock);
	old_root = rcu_access_pointer(net->ws_cell);
	rcu_assign_pointer(net->ws_cell, new_root);
	write_sequnlock(&net->cells_lock);

	afs_put_cell(net, old_root);
	_leave(" = 0");
	return 0;
}