Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (33 commits) IPVS: Use global mutex in ip_vs_app.c ipvs: fix a typo in __ip_vs_control_init() veth: Fix the byte counters net ipv6: Fix duplicate /proc/sys/net/ipv6/neigh directory entries. macvlan: Fix use after free of struct macvlan_port. net: fix incorrect spelling in drop monitor protocol can: c_can: Do basic c_can configuration _before_ enabling the interrupts net/appletalk: fix atalk_release use after free ipx: fix ipx_release() snmp: SNMP_UPD_PO_STATS_BH() always called from softirq l2tp: fix possible oops on l2tp_eth module unload xfrm: Fix initialize repl field of struct xfrm_state netfilter: ipt_CLUSTERIP: fix buffer overflow netfilter: xtables: fix reentrancy netfilter: ipset: fix checking the type revision at create command netfilter: ipset: fix address ranges at hash:*port* types niu: Rename NIU parent platform device name to fix conflict. r8169: fix a bug in rtl8169_init_phy() bonding: fix a typo in a comment ftmac100: use resource_size() ...
2026-05-01 15:00:59 -07:00 · 2011-03-22 09:25:34 -07:00
parent eddecbb601 736561a01f
commit c62b389863
42 changed files with 383 additions and 324 deletions
@@ -2130,7 +2130,7 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev)
 }

 /*
-* First release a slave and than destroy the bond if no more slaves are left.
+* First release a slave and then destroy the bond if no more slaves are left.
 * Must be under rtnl_lock when this function is called.
 */
 static int  bond_release_and_destroy(struct net_device *bond_dev,
@@ -633,9 +633,6 @@ static void c_can_start(struct net_device *dev)
 {
 	struct c_can_priv *priv = netdev_priv(dev);

-	/* enable status change, error and module interrupts */
-	c_can_enable_all_interrupts(priv, ENABLE_ALL_INTERRUPTS);
-
 	/* basic c_can configuration */
 	c_can_chip_config(dev);

@@ -643,6 +640,9 @@ static void c_can_start(struct net_device *dev)

 	/* reset tx helper pointers */
 	priv->tx_next = priv->tx_echo = 0;
+
+	/* enable status change, error and module interrupts */
+	c_can_enable_all_interrupts(priv, ENABLE_ALL_INTERRUPTS);
 }

 static void c_can_stop(struct net_device *dev)
@@ -1102,7 +1102,7 @@ static int ftmac100_probe(struct platform_device *pdev)
 		goto err_req_mem;
 	}

-	priv->base = ioremap(res->start, res->end - res->start);
+	priv->base = ioremap(res->start, resource_size(res));
 	if (!priv->base) {
 		dev_err(&pdev->dev, "Failed to ioremap ethernet registers\n");
 		err = -EIO;
@@ -949,6 +949,11 @@ static void gfar_detect_errata(struct gfar_private *priv)
 			(pvr == 0x80861010 && (mod & 0xfff9) == 0x80c0))
 		priv->errata |= GFAR_ERRATA_A002;

+	/* MPC8313 Rev < 2.0, MPC8548 rev 2.0 */
+	if ((pvr == 0x80850010 && mod == 0x80b0 && rev < 0x0020) ||
+			(pvr == 0x80210020 && mod == 0x8030 && rev == 0x0020))
+		priv->errata |= GFAR_ERRATA_12;
+
 	if (priv->errata)
 		dev_info(dev, "enabled errata workarounds, flags: 0x%x\n",
 			 priv->errata);
@@ -2154,8 +2159,15 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Set up checksumming */
 	if (CHECKSUM_PARTIAL == skb->ip_summed) {
 		fcb = gfar_add_fcb(skb);
-		lstatus |= BD_LFLAG(TXBD_TOE);
-		gfar_tx_checksum(skb, fcb);
+		/* as specified by errata */
+		if (unlikely(gfar_has_errata(priv, GFAR_ERRATA_12)
+			     && ((unsigned long)fcb % 0x20) > 0x18)) {
+			__skb_pull(skb, GMAC_FCB_LEN);
+			skb_checksum_help(skb);
+		} else {
+			lstatus |= BD_LFLAG(TXBD_TOE);
+			gfar_tx_checksum(skb, fcb);
+		}
 	}

 	if (vlan_tx_tag_present(skb)) {
@@ -1039,6 +1039,7 @@ enum gfar_errata {
 	GFAR_ERRATA_74		= 0x01,
 	GFAR_ERRATA_76		= 0x02,
 	GFAR_ERRATA_A002	= 0x04,
+	GFAR_ERRATA_12		= 0x08, /* a.k.a errata eTSEC49 */
 };

 /* Struct stolen almost completely (and shamelessly) from the FCC enet source
@@ -39,8 +39,11 @@ struct macvlan_port {
 	struct list_head	vlans;
 	struct rcu_head		rcu;
 	bool 			passthru;
+	int			count;
 };

+static void macvlan_port_destroy(struct net_device *dev);
+
 #define macvlan_port_get_rcu(dev) \
 	((struct macvlan_port *) rcu_dereference(dev->rx_handler_data))
 #define macvlan_port_get(dev) ((struct macvlan_port *) dev->rx_handler_data)
@@ -457,8 +460,13 @@ static int macvlan_init(struct net_device *dev)
 static void macvlan_uninit(struct net_device *dev)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
+	struct macvlan_port *port = vlan->port;

 	free_percpu(vlan->pcpu_stats);
+
+	port->count -= 1;
+	if (!port->count)
+		macvlan_port_destroy(port->dev);
 }

 static struct rtnl_link_stats64 *macvlan_dev_get_stats64(struct net_device *dev,
@@ -691,12 +699,13 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 		vlan->mode = nla_get_u32(data[IFLA_MACVLAN_MODE]);

 	if (vlan->mode == MACVLAN_MODE_PASSTHRU) {
-		if (!list_empty(&port->vlans))
+		if (port->count)
 			return -EINVAL;
 		port->passthru = true;
 		memcpy(dev->dev_addr, lowerdev->dev_addr, ETH_ALEN);
 	}

+	port->count += 1;
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto destroy_port;
@@ -707,7 +716,8 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 	return 0;

 destroy_port:
-	if (list_empty(&port->vlans))
+	port->count -= 1;
+	if (!port->count)
 		macvlan_port_destroy(lowerdev);

 	return err;
@@ -725,13 +735,9 @@ static int macvlan_newlink(struct net *src_net, struct net_device *dev,
 void macvlan_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
-	struct macvlan_port *port = vlan->port;

 	list_del(&vlan->list);
 	unregister_netdevice_queue(dev, head);
-
-	if (list_empty(&port->vlans))
-		macvlan_port_destroy(port->dev);
 }
 EXPORT_SYMBOL_GPL(macvlan_dellink);

@@ -9501,7 +9501,7 @@ static struct niu_parent * __devinit niu_new_parent(struct niu *np,
 	struct niu_parent *p;
 	int i;

-	plat_dev = platform_device_register_simple("niu", niu_parent_index,
+	plat_dev = platform_device_register_simple("niu-board", niu_parent_index,
 						   NULL, 0);
 	if (IS_ERR(plat_dev))
 		return NULL;
@@ -171,7 +171,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (skb->ip_summed == CHECKSUM_NONE)
 		skb->ip_summed = rcv_priv->ip_summed;

-	length = skb->len + ETH_HLEN;
+	length = skb->len;
 	if (dev_forward_skb(rcv, skb) != NET_RX_SUCCESS)
 		goto rx_drop;

@@ -60,6 +60,7 @@ static int move_iovec_hdr(struct iovec *from, struct iovec *to,
 {
 	int seg = 0;
 	size_t size;
+
 	while (len && seg < iov_count) {
 		size = min(from->iov_len, len);
 		to->iov_base = from->iov_base;
@@ -79,6 +80,7 @@ static void copy_iovec_hdr(const struct iovec *from, struct iovec *to,
 {
 	int seg = 0;
 	size_t size;
+
 	while (len && seg < iovcount) {
 		size = min(from->iov_len, len);
 		to->iov_base = from->iov_base;
@@ -211,12 +213,13 @@ static int peek_head_len(struct sock *sk)
 {
 	struct sk_buff *head;
 	int len = 0;
+	unsigned long flags;

-	lock_sock(sk);
+	spin_lock_irqsave(&sk->sk_receive_queue.lock, flags);
 	head = skb_peek(&sk->sk_receive_queue);
-	if (head)
+	if (likely(head))
 		len = head->len;
-	release_sock(sk);
+	spin_unlock_irqrestore(&sk->sk_receive_queue.lock, flags);
 	return len;
 }

@@ -227,6 +230,7 @@ static int peek_head_len(struct sock *sk)
 * @iovcount	- returned count of io vectors we fill
 * @log		- vhost log
 * @log_num	- log offset
+ * @quota       - headcount quota, 1 for big buffer
 *	returns number of buffer heads allocated, negative on error
 */
 static int get_rx_bufs(struct vhost_virtqueue *vq,
@@ -234,7 +238,8 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 		       int datalen,
 		       unsigned *iovcount,
 		       struct vhost_log *log,
-		       unsigned *log_num)
+		       unsigned *log_num,
+		       unsigned int quota)
 {
 	unsigned int out, in;
 	int seg = 0;
@@ -242,7 +247,7 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 	unsigned d;
 	int r, nlogs = 0;

-	while (datalen > 0) {
+	while (datalen > 0 && headcount < quota) {
 		if (unlikely(seg >= UIO_MAXIOV)) {
 			r = -ENOBUFS;
 			goto err;
@@ -282,117 +287,7 @@ err:

 /* Expects to be always run from workqueue - which acts as
 * read-size critical section for our kind of RCU. */
-static void handle_rx_big(struct vhost_net *net)
-{
-	struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
-	unsigned out, in, log, s;
-	int head;
-	struct vhost_log *vq_log;
-	struct msghdr msg = {
-		.msg_name = NULL,
-		.msg_namelen = 0,
-		.msg_control = NULL, /* FIXME: get and handle RX aux data. */
-		.msg_controllen = 0,
-		.msg_iov = vq->iov,
-		.msg_flags = MSG_DONTWAIT,
-	};
-
-	struct virtio_net_hdr hdr = {
-		.flags = 0,
-		.gso_type = VIRTIO_NET_HDR_GSO_NONE
-	};
-
-	size_t len, total_len = 0;
-	int err;
-	size_t hdr_size;
-	/* TODO: check that we are running from vhost_worker? */
-	struct socket *sock = rcu_dereference_check(vq->private_data, 1);
-	if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
-		return;
-
-	mutex_lock(&vq->mutex);
-	vhost_disable_notify(vq);
-	hdr_size = vq->vhost_hlen;
-
-	vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
-		vq->log : NULL;
-
-	for (;;) {
-		head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
-					 ARRAY_SIZE(vq->iov),
-					 &out, &in,
-					 vq_log, &log);
-		/* On error, stop handling until the next kick. */
-		if (unlikely(head < 0))
-			break;
-		/* OK, now we need to know about added descriptors. */
-		if (head == vq->num) {
-			if (unlikely(vhost_enable_notify(vq))) {
-				/* They have slipped one in as we were
-				 * doing that: check again. */
-				vhost_disable_notify(vq);
-				continue;
-			}
-			/* Nothing new?  Wait for eventfd to tell us
-			 * they refilled. */
-			break;
-		}
-		/* We don't need to be notified again. */
-		if (out) {
-			vq_err(vq, "Unexpected descriptor format for RX: "
-			       "out %d, int %d\n",
-			       out, in);
-			break;
-		}
-		/* Skip header. TODO: support TSO/mergeable rx buffers. */
-		s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, in);
-		msg.msg_iovlen = in;
-		len = iov_length(vq->iov, in);
-		/* Sanity check */
-		if (!len) {
-			vq_err(vq, "Unexpected header len for RX: "
-			       "%zd expected %zd\n",
-			       iov_length(vq->hdr, s), hdr_size);
-			break;
-		}
-		err = sock->ops->recvmsg(NULL, sock, &msg,
-					 len, MSG_DONTWAIT | MSG_TRUNC);
-		/* TODO: Check specific error and bomb out unless EAGAIN? */
-		if (err < 0) {
-			vhost_discard_vq_desc(vq, 1);
-			break;
-		}
-		/* TODO: Should check and handle checksum. */
-		if (err > len) {
-			pr_debug("Discarded truncated rx packet: "
-				 " len %d > %zd\n", err, len);
-			vhost_discard_vq_desc(vq, 1);
-			continue;
-		}
-		len = err;
-		err = memcpy_toiovec(vq->hdr, (unsigned char *)&hdr, hdr_size);
-		if (err) {
-			vq_err(vq, "Unable to write vnet_hdr at addr %p: %d\n",
-			       vq->iov->iov_base, err);
-			break;
-		}
-		len += hdr_size;
-		vhost_add_used_and_signal(&net->dev, vq, head, len);
-		if (unlikely(vq_log))
-			vhost_log_write(vq, vq_log, log, len);
-		total_len += len;
-		if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
-			vhost_poll_queue(&vq->poll);
-			break;
-		}
-	}
-
-	mutex_unlock(&vq->mutex);
-}
-
-/* Expects to be always run from workqueue - which acts as
- * read-size critical section for our kind of RCU. */
-static void handle_rx_mergeable(struct vhost_net *net)
+static void handle_rx(struct vhost_net *net)
 {
 	struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
 	unsigned uninitialized_var(in), log;
@@ -405,19 +300,18 @@ static void handle_rx_mergeable(struct vhost_net *net)
 		.msg_iov = vq->iov,
 		.msg_flags = MSG_DONTWAIT,
 	};
-
 	struct virtio_net_hdr_mrg_rxbuf hdr = {
 		.hdr.flags = 0,
 		.hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE
 	};
-
 	size_t total_len = 0;
-	int err, headcount;
+	int err, headcount, mergeable;
 	size_t vhost_hlen, sock_hlen;
 	size_t vhost_len, sock_len;
 	/* TODO: check that we are running from vhost_worker? */
 	struct socket *sock = rcu_dereference_check(vq->private_data, 1);
-	if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
+
+	if (!sock)
 		return;

 	mutex_lock(&vq->mutex);
@@ -427,12 +321,14 @@ static void handle_rx_mergeable(struct vhost_net *net)

 	vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
 		vq->log : NULL;
+	mergeable = vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF);

 	while ((sock_len = peek_head_len(sock->sk))) {
 		sock_len += sock_hlen;
 		vhost_len = sock_len + vhost_hlen;
 		headcount = get_rx_bufs(vq, vq->heads, vhost_len,
-					&in, vq_log, &log);
+					&in, vq_log, &log,
+					likely(mergeable) ? UIO_MAXIOV : 1);
 		/* On error, stop handling until the next kick. */
 		if (unlikely(headcount < 0))
 			break;
@@ -476,7 +372,7 @@ static void handle_rx_mergeable(struct vhost_net *net)
 			break;
 		}
 		/* TODO: Should check and handle checksum. */
-		if (vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF) &&
+		if (likely(mergeable) &&
 		    memcpy_toiovecend(vq->hdr, (unsigned char *)&headcount,
 				      offsetof(typeof(hdr), num_buffers),
 				      sizeof hdr.num_buffers)) {
@@ -498,14 +394,6 @@ static void handle_rx_mergeable(struct vhost_net *net)
 	mutex_unlock(&vq->mutex);
 }

-static void handle_rx(struct vhost_net *net)
-{
-	if (vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF))
-		handle_rx_mergeable(net);
-	else
-		handle_rx_big(net);
-}
-
 static void handle_tx_kick(struct vhost_work *work)
 {
 	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
@@ -654,6 +542,7 @@ static struct socket *get_raw_socket(int fd)
 	} uaddr;
 	int uaddr_len = sizeof uaddr, r;
 	struct socket *sock = sockfd_lookup(fd, &r);
+
 	if (!sock)
 		return ERR_PTR(-ENOTSOCK);

@@ -682,6 +571,7 @@ static struct socket *get_tap_socket(int fd)
 {
 	struct file *file = fget(fd);
 	struct socket *sock;
+
 	if (!file)
 		return ERR_PTR(-EBADF);
 	sock = tun_get_socket(file);
@@ -696,6 +586,7 @@ static struct socket *get_tap_socket(int fd)
 static struct socket *get_socket(int fd)
 {
 	struct socket *sock;
+
 	/* special case to disable backend */
 	if (fd == -1)
 		return NULL;
@@ -741,9 +632,9 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
 	oldsock = rcu_dereference_protected(vq->private_data,
 					    lockdep_is_held(&vq->mutex));
 	if (sock != oldsock) {
-                vhost_net_disable_vq(n, vq);
-                rcu_assign_pointer(vq->private_data, sock);
-                vhost_net_enable_vq(n, vq);
+		vhost_net_disable_vq(n, vq);
+		rcu_assign_pointer(vq->private_data, sock);
+		vhost_net_enable_vq(n, vq);
 	}

 	mutex_unlock(&vq->mutex);
@@ -768,6 +659,7 @@ static long vhost_net_reset_owner(struct vhost_net *n)
 	struct socket *tx_sock = NULL;
 	struct socket *rx_sock = NULL;
 	long err;
+
 	mutex_lock(&n->dev.mutex);
 	err = vhost_dev_check_owner(&n->dev);
 	if (err)
@@ -829,6 +721,7 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
 	struct vhost_vring_file backend;
 	u64 features;
 	int r;
+
 	switch (ioctl) {
 	case VHOST_NET_SET_BACKEND:
 		if (copy_from_user(&backend, argp, sizeof backend))
@@ -41,8 +41,8 @@ static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
 			    poll_table *pt)
 {
 	struct vhost_poll *poll;
-	poll = container_of(pt, struct vhost_poll, table);

+	poll = container_of(pt, struct vhost_poll, table);
 	poll->wqh = wqh;
 	add_wait_queue(wqh, &poll->wait);
 }
@@ -85,6 +85,7 @@ void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
 void vhost_poll_start(struct vhost_poll *poll, struct file *file)
 {
 	unsigned long mask;
+
 	mask = file->f_op->poll(file, &poll->table);
 	if (mask)
 		vhost_poll_wakeup(&poll->wait, 0, 0, (void *)mask);
@@ -101,6 +102,7 @@ static bool vhost_work_seq_done(struct vhost_dev *dev, struct vhost_work *work,
 				unsigned seq)
 {
 	int left;
+
 	spin_lock_irq(&dev->work_lock);
 	left = seq - work->done_seq;
 	spin_unlock_irq(&dev->work_lock);
@@ -222,6 +224,7 @@ static int vhost_worker(void *data)
 static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
 {
 	int i;
+
 	for (i = 0; i < dev->nvqs; ++i) {
 		dev->vqs[i].indirect = kmalloc(sizeof *dev->vqs[i].indirect *
 					       UIO_MAXIOV, GFP_KERNEL);
@@ -235,6 +238,7 @@ static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
 			goto err_nomem;
 	}
 	return 0;
+
 err_nomem:
 	for (; i >= 0; --i) {
 		kfree(dev->vqs[i].indirect);
@@ -247,6 +251,7 @@ err_nomem:
 static void vhost_dev_free_iovecs(struct vhost_dev *dev)
 {
 	int i;
+
 	for (i = 0; i < dev->nvqs; ++i) {
 		kfree(dev->vqs[i].indirect);
 		dev->vqs[i].indirect = NULL;
@@ -296,26 +301,28 @@ long vhost_dev_check_owner(struct vhost_dev *dev)
 }

 struct vhost_attach_cgroups_struct {
-        struct vhost_work work;
-        struct task_struct *owner;
-        int ret;
+	struct vhost_work work;
+	struct task_struct *owner;
+	int ret;
 };

 static void vhost_attach_cgroups_work(struct vhost_work *work)
 {
-        struct vhost_attach_cgroups_struct *s;
-        s = container_of(work, struct vhost_attach_cgroups_struct, work);
-        s->ret = cgroup_attach_task_all(s->owner, current);
+	struct vhost_attach_cgroups_struct *s;
+
+	s = container_of(work, struct vhost_attach_cgroups_struct, work);
+	s->ret = cgroup_attach_task_all(s->owner, current);
 }

 static int vhost_attach_cgroups(struct vhost_dev *dev)
 {
-        struct vhost_attach_cgroups_struct attach;
-        attach.owner = current;
-        vhost_work_init(&attach.work, vhost_attach_cgroups_work);
-        vhost_work_queue(dev, &attach.work);
-        vhost_work_flush(dev, &attach.work);
-        return attach.ret;
+	struct vhost_attach_cgroups_struct attach;
+
+	attach.owner = current;
+	vhost_work_init(&attach.work, vhost_attach_cgroups_work);
+	vhost_work_queue(dev, &attach.work);
+	vhost_work_flush(dev, &attach.work);
+	return attach.ret;
 }

 /* Caller should have device mutex */
@@ -323,11 +330,13 @@ static long vhost_dev_set_owner(struct vhost_dev *dev)
 {
 	struct task_struct *worker;
 	int err;
+
 	/* Is there an owner already? */
 	if (dev->mm) {
 		err = -EBUSY;
 		goto err_mm;
 	}
+
 	/* No owner, become one */
 	dev->mm = get_task_mm(current);
 	worker = kthread_create(vhost_worker, dev, "vhost-%d", current->pid);
@@ -380,6 +389,7 @@ long vhost_dev_reset_owner(struct vhost_dev *dev)
 void vhost_dev_cleanup(struct vhost_dev *dev)
 {
 	int i;
+
 	for (i = 0; i < dev->nvqs; ++i) {
 		if (dev->vqs[i].kick && dev->vqs[i].handle_kick) {
 			vhost_poll_stop(&dev->vqs[i].poll);
@@ -421,6 +431,7 @@ void vhost_dev_cleanup(struct vhost_dev *dev)
 static int log_access_ok(void __user *log_base, u64 addr, unsigned long sz)
 {
 	u64 a = addr / VHOST_PAGE_SIZE / 8;
+
 	/* Make sure 64 bit math will not overflow. */
 	if (a > ULONG_MAX - (unsigned long)log_base ||
 	    a + (unsigned long)log_base > ULONG_MAX)
@@ -461,6 +472,7 @@ static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem,
 			    int log_all)
 {
 	int i;
+
 	for (i = 0; i < d->nvqs; ++i) {
 		int ok;
 		mutex_lock(&d->vqs[i].mutex);
@@ -527,6 +539,7 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 {
 	struct vhost_memory mem, *newmem, *oldmem;
 	unsigned long size = offsetof(struct vhost_memory, regions);
+
 	if (copy_from_user(&mem, m, size))
 		return -EFAULT;
 	if (mem.padding)
@@ -544,7 +557,8 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 		return -EFAULT;
 	}

-	if (!memory_access_ok(d, newmem, vhost_has_feature(d, VHOST_F_LOG_ALL))) {
+	if (!memory_access_ok(d, newmem,
+			      vhost_has_feature(d, VHOST_F_LOG_ALL))) {
 		kfree(newmem);
 		return -EFAULT;
 	}
@@ -560,6 +574,7 @@ static int init_used(struct vhost_virtqueue *vq,
 		     struct vring_used __user *used)
 {
 	int r = put_user(vq->used_flags, &used->flags);
+
 	if (r)
 		return r;
 	return get_user(vq->last_used_idx, &used->idx);
@@ -849,6 +864,7 @@ static const struct vhost_memory_region *find_region(struct vhost_memory *mem,
 {
 	struct vhost_memory_region *reg;
 	int i;
+
 	/* linear search is not brilliant, but we really have on the order of 6
 	 * regions in practice */
 	for (i = 0; i < mem->nregions; ++i) {
@@ -871,6 +887,7 @@ static int set_bit_to_user(int nr, void __user *addr)
 	void *base;
 	int bit = nr + (log % PAGE_SIZE) * 8;
 	int r;
+
 	r = get_user_pages_fast(log, 1, 1, &page);
 	if (r < 0)
 		return r;
@@ -888,6 +905,7 @@ static int log_write(void __user *log_base,
 {
 	u64 write_page = write_address / VHOST_PAGE_SIZE;
 	int r;
+
 	if (!write_length)
 		return 0;
 	write_length += write_address % VHOST_PAGE_SIZE;
@@ -1037,8 +1055,8 @@ static int get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 			       i, count);
 			return -EINVAL;
 		}
-		if (unlikely(memcpy_fromiovec((unsigned char *)&desc, vq->indirect,
-					      sizeof desc))) {
+		if (unlikely(memcpy_fromiovec((unsigned char *)&desc,
+					      vq->indirect, sizeof desc))) {
 			vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n",
 			       i, (size_t)indirect->addr + i * sizeof desc);
 			return -EINVAL;
@@ -1153,7 +1171,7 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 			       i, vq->num, head);
 			return -EINVAL;
 		}
-		ret = copy_from_user(&desc, vq->desc + i, sizeof desc);
+		ret = __copy_from_user(&desc, vq->desc + i, sizeof desc);
 		if (unlikely(ret)) {
 			vq_err(vq, "Failed to get descriptor: idx %d addr %p\n",
 			       i, vq->desc + i);
@@ -1317,6 +1335,7 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
 void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
 	__u16 flags;
+
 	/* Flush out used index updates. This is paired
 	 * with the barrier that the Guest executes when enabling
 	 * interrupts. */
@@ -1361,6 +1380,7 @@ bool vhost_enable_notify(struct vhost_virtqueue *vq)
 {
 	u16 avail_idx;
 	int r;
+
 	if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY))
 		return false;
 	vq->used_flags &= ~VRING_USED_F_NO_NOTIFY;
@@ -1387,6 +1407,7 @@ bool vhost_enable_notify(struct vhost_virtqueue *vq)
 void vhost_disable_notify(struct vhost_virtqueue *vq)
 {
 	int r;
+
 	if (vq->used_flags & VRING_USED_F_NO_NOTIFY)
 		return;
 	vq->used_flags |= VRING_USED_F_NO_NOTIFY;
@@ -13,6 +13,9 @@
 #ifndef _LINUX_ETHTOOL_H
 #define _LINUX_ETHTOOL_H

+#ifdef __KERNEL__
+#include <linux/compat.h>
+#endif
 #include <linux/types.h>
 #include <linux/if_ether.h>

@@ -450,6 +453,37 @@ struct ethtool_rxnfc {
 	__u32				rule_locs[0];
 };

+#ifdef __KERNEL__
+#ifdef CONFIG_COMPAT
+
+struct compat_ethtool_rx_flow_spec {
+	u32		flow_type;
+	union {
+		struct ethtool_tcpip4_spec		tcp_ip4_spec;
+		struct ethtool_tcpip4_spec		udp_ip4_spec;
+		struct ethtool_tcpip4_spec		sctp_ip4_spec;
+		struct ethtool_ah_espip4_spec		ah_ip4_spec;
+		struct ethtool_ah_espip4_spec		esp_ip4_spec;
+		struct ethtool_usrip4_spec		usr_ip4_spec;
+		struct ethhdr				ether_spec;
+		u8					hdata[72];
+	} h_u, m_u;
+	compat_u64	ring_cookie;
+	u32		location;
+};
+
+struct compat_ethtool_rxnfc {
+	u32				cmd;
+	u32				flow_type;
+	compat_u64			data;
+	struct compat_ethtool_rx_flow_spec fs;
+	u32				rule_cnt;
+	u32				rule_locs[0];
+};
+
+#endif /* CONFIG_COMPAT */
+#endif /* __KERNEL__ */
+
 /**
 * struct ethtool_rxfh_indir - command to get or set RX flow hash indirection
 * @cmd: Specific command number - %ETHTOOL_GRXFHINDIR or %ETHTOOL_SRXFHINDIR
@@ -114,14 +114,14 @@ struct pppol2tp_ioc_stats {
 	__u16		tunnel_id;	/* redundant */
 	__u16		session_id;	/* if zero, get tunnel stats */
 	__u32		using_ipsec:1;	/* valid only for session_id == 0 */
-	aligned_u64	tx_packets;
-	aligned_u64	tx_bytes;
-	aligned_u64	tx_errors;
-	aligned_u64	rx_packets;
-	aligned_u64	rx_bytes;
-	aligned_u64	rx_seq_discards;
-	aligned_u64	rx_oos_packets;
-	aligned_u64	rx_errors;
+	__aligned_u64	tx_packets;
+	__aligned_u64	tx_bytes;
+	__aligned_u64	tx_errors;
+	__aligned_u64	rx_packets;
+	__aligned_u64	rx_bytes;
+	__aligned_u64	rx_seq_discards;
+	__aligned_u64	rx_oos_packets;
+	__aligned_u64	rx_errors;
 };

 #define ifr__name       b.ifr_ifrn.ifrn_name
@@ -18,4 +18,14 @@ static inline bool ip_set_get_ip6_port(const struct sk_buff *skb, bool src,
 extern bool ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src,
 				__be16 *port);

+static inline bool ip_set_proto_with_ports(u8 proto)
+{
+	switch (proto) {
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+		return true;
+	}
+	return false;
+}
+
 #endif /*_IP_SET_GETPORT_H*/
@@ -28,8 +28,8 @@ struct nfulnl_msg_packet_hw {
 };

 struct nfulnl_msg_packet_timestamp {
-	aligned_be64	sec;
-	aligned_be64	usec;
+	__aligned_be64	sec;
+	__aligned_be64	usec;
 };

 enum nfulnl_attr_type {
@@ -25,8 +25,8 @@ struct nfqnl_msg_packet_hw {
 };

 struct nfqnl_msg_packet_timestamp {
-	aligned_be64	sec;
-	aligned_be64	usec;
+	__aligned_be64	sec;
+	__aligned_be64	usec;
 };

 enum nfqnl_attr_type {
@@ -17,8 +17,8 @@ enum xt_connbytes_direction {

 struct xt_connbytes_info {
 	struct {
-		aligned_u64 from;	/* count to be matched */
-		aligned_u64 to;		/* count to be matched */
+		__aligned_u64 from;	/* count to be matched */
+		__aligned_u64 to;	/* count to be matched */
 	} count;
 	__u8 what;		/* ipt_connbytes_what */
 	__u8 direction;	/* ipt_connbytes_direction */
@@ -13,7 +13,7 @@ struct xt_quota_priv;
 struct xt_quota_info {
 	__u32 flags;
 	__u32 pad;
-	aligned_u64 quota;
+	__aligned_u64 quota;

 	/* Used internally by the kernel */
 	struct xt_quota_priv	*master;
@@ -801,8 +801,6 @@ struct netns_ipvs {
 	struct list_head	rs_table[IP_VS_RTAB_SIZE];
 	/* ip_vs_app */
 	struct list_head	app_list;
-	struct mutex		app_mutex;
-	struct lock_class_key	app_key;	/* mutex debuging */

 	/* ip_vs_proto */
 	#define IP_VS_PROTO_TAB_SIZE	32	/* must be power of 2 */
@@ -150,7 +150,7 @@ struct linux_xfrm_mib {
 #define SNMP_UPD_PO_STATS_BH(mib, basefield, addend)	\
 	do { \
 		__typeof__(*mib[0]) *ptr = \
-			__this_cpu_ptr((mib)[!in_softirq()]); \
+			__this_cpu_ptr((mib)[0]); \
 		ptr->mibs[basefield##PKTS]++; \
 		ptr->mibs[basefield##OCTETS] += addend;\
 	} while (0)
@@ -202,7 +202,7 @@ struct linux_xfrm_mib {
 #define SNMP_UPD_PO_STATS64_BH(mib, basefield, addend)			\
 	do {								\
 		__typeof__(*mib[0]) *ptr;				\
-		ptr = __this_cpu_ptr((mib)[!in_softirq()]);		\
+		ptr = __this_cpu_ptr((mib)[0]);				\
 		u64_stats_update_begin(&ptr->syncp);			\
 		ptr->mibs[basefield##PKTS]++;				\
 		ptr->mibs[basefield##OCTETS] += addend;			\
@@ -1430,6 +1430,7 @@ extern void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si);
 extern u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq);
 extern int xfrm_init_replay(struct xfrm_state *x);
 extern int xfrm_state_mtu(struct xfrm_state *x, int mtu);
+extern int __xfrm_init_state(struct xfrm_state *x, bool init_replay);
 extern int xfrm_init_state(struct xfrm_state *x);
 extern int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb);
 extern int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi,
--- a/Show More
+++ b/Show More