Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 345 insertions, 0 deletions

diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c
new file mode 100644
index 000000000..9e2e25d02
--- /dev/null
+++ b/drivers/net/can/vxcan.c
@@ -0,0 +1,345 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vxcan.c - Virtual CAN Tunnel for cross namespace communication
+ *
+ * This code is derived from drivers/net/can/vcan.c for the virtual CAN
+ * specific parts and from drivers/net/veth.c to implement the netlink API
+ * for network interface pairs in a common and established way.
+ *
+ * Copyright (c) 2017 Oliver Hartkopp <socketcan@hartkopp.net>
+ */
+
+#include <linux/ethtool.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+#include <linux/if_ether.h>
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/skb.h>
+#include <linux/can/vxcan.h>
+#include <linux/can/can-ml.h>
+#include <linux/slab.h>
+#include <net/can.h>
+#include <net/rtnetlink.h>
+
+#define DRV_NAME "vxcan"
+
+MODULE_DESCRIPTION("Virtual CAN Tunnel");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Oliver Hartkopp <socketcan@hartkopp.net>");
+MODULE_ALIAS_RTNL_LINK(DRV_NAME);
+
+struct vxcan_priv {
+	struct net_device __rcu	*peer;
+	netdevice_tracker peer_tracker;
+};
+
+static netdev_tx_t vxcan_xmit(struct sk_buff *oskb, struct net_device *dev)
+{
+	struct vxcan_priv *priv = netdev_priv(dev);
+	struct net_device *peer;
+	struct net_device_stats *peerstats, *srcstats = &dev->stats;
+	struct can_skb_ext *csx;
+	struct sk_buff *skb;
+	unsigned int len;
+
+	if (can_dropped_invalid_skb(dev, oskb))
+		return NETDEV_TX_OK;
+
+	rcu_read_lock();
+	peer = rcu_dereference(priv->peer);
+	if (unlikely(!peer)) {
+		kfree_skb(oskb);
+		dev->stats.tx_dropped++;
+		goto out_unlock;
+	}
+
+	skb_tx_timestamp(oskb);
+
+	skb = skb_clone(oskb, GFP_ATOMIC);
+	if (skb) {
+		consume_skb(oskb);
+	} else {
+		kfree_skb(oskb);
+		goto out_unlock;
+	}
+
+	/* the cloned skb points to the skb extension of the already cloned
+	 * oskb with an increased refcount. skb_ext_add() creates a copy to
+	 * separate the skb extension data which is needed to start with a
+	 * fresh can_gw_hops counter in the other namespace.
+	 */
+	csx = skb_ext_add(skb, SKB_EXT_CAN);
+	if (!csx) {
+		kfree_skb(skb);
+		goto out_unlock;
+	}
+
+	/* reset CAN GW hop counter */
+	csx->can_gw_hops = 0;
+	skb->pkt_type   = PACKET_BROADCAST;
+	skb->dev        = peer;
+	skb->ip_summed  = CHECKSUM_UNNECESSARY;
+
+	len = can_skb_get_data_len(skb);
+	if (netif_rx(skb) == NET_RX_SUCCESS) {
+		srcstats->tx_packets++;
+		srcstats->tx_bytes += len;
+		peerstats = &peer->stats;
+		peerstats->rx_packets++;
+		peerstats->rx_bytes += len;
+	}
+
+out_unlock:
+	rcu_read_unlock();
+	return NETDEV_TX_OK;
+}
+
+
+static int vxcan_open(struct net_device *dev)
+{
+	struct vxcan_priv *priv = netdev_priv(dev);
+	struct net_device *peer = rtnl_dereference(priv->peer);
+
+	if (!peer)
+		return -ENOTCONN;
+
+	if (peer->flags & IFF_UP) {
+		netif_carrier_on(dev);
+		netif_carrier_on(peer);
+	}
+	return 0;
+}
+
+static int vxcan_close(struct net_device *dev)
+{
+	struct vxcan_priv *priv = netdev_priv(dev);
+	struct net_device *peer = rtnl_dereference(priv->peer);
+
+	netif_carrier_off(dev);
+	if (peer)
+		netif_carrier_off(peer);
+
+	return 0;
+}
+
+static int vxcan_get_iflink(const struct net_device *dev)
+{
+	struct vxcan_priv *priv = netdev_priv(dev);
+	struct net_device *peer;
+	int iflink;
+
+	rcu_read_lock();
+	peer = rcu_dereference(priv->peer);
+	iflink = peer ? READ_ONCE(peer->ifindex) : 0;
+	rcu_read_unlock();
+
+	return iflink;
+}
+
+static void vxcan_set_cap_info(struct net_device *dev)
+{
+	u32 can_cap = CAN_CAP_CC;
+
+	if (dev->mtu > CAN_MTU)
+		can_cap |= CAN_CAP_FD;
+
+	if (dev->mtu >= CANXL_MIN_MTU)
+		can_cap |= CAN_CAP_XL;
+
+	can_set_cap(dev, can_cap);
+}
+
+static int vxcan_change_mtu(struct net_device *dev, int new_mtu)
+{
+	/* Do not allow changing the MTU while running */
+	if (dev->flags & IFF_UP)
+		return -EBUSY;
+
+	if (new_mtu != CAN_MTU && new_mtu != CANFD_MTU &&
+	    !can_is_canxl_dev_mtu(new_mtu))
+		return -EINVAL;
+
+	WRITE_ONCE(dev->mtu, new_mtu);
+	vxcan_set_cap_info(dev);
+	return 0;
+}
+
+static const struct net_device_ops vxcan_netdev_ops = {
+	.ndo_open	= vxcan_open,
+	.ndo_stop	= vxcan_close,
+	.ndo_start_xmit	= vxcan_xmit,
+	.ndo_get_iflink	= vxcan_get_iflink,
+	.ndo_change_mtu = vxcan_change_mtu,
+};
+
+static const struct ethtool_ops vxcan_ethtool_ops = {
+	.get_ts_info = ethtool_op_get_ts_info,
+};
+
+static void vxcan_setup(struct net_device *dev)
+{
+	struct can_ml_priv *can_ml;
+
+	dev->type		= ARPHRD_CAN;
+	dev->mtu		= CANXL_MTU;
+	dev->hard_header_len	= 0;
+	dev->addr_len		= 0;
+	dev->tx_queue_len	= 0;
+	dev->flags		= IFF_NOARP;
+	dev->netdev_ops		= &vxcan_netdev_ops;
+	dev->ethtool_ops	= &vxcan_ethtool_ops;
+	dev->needs_free_netdev	= true;
+
+	can_ml = netdev_priv(dev) + ALIGN(sizeof(struct vxcan_priv), NETDEV_ALIGN);
+	can_set_ml_priv(dev, can_ml);
+	vxcan_set_cap_info(dev);
+}
+
+/* forward declaration for rtnl_create_link() */
+static struct rtnl_link_ops vxcan_link_ops;
+
+static int vxcan_newlink(struct net_device *dev,
+			 struct rtnl_newlink_params *params,
+			 struct netlink_ext_ack *extack)
+{
+	struct net *peer_net = rtnl_newlink_peer_net(params);
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
+	struct vxcan_priv *priv;
+	struct net_device *peer;
+
+	struct nlattr *peer_tb[IFLA_MAX + 1], **tbp = tb;
+	char ifname[IFNAMSIZ];
+	unsigned char name_assign_type;
+	struct ifinfomsg *ifmp = NULL;
+	int err;
+
+	/* register peer device */
+	if (data && data[VXCAN_INFO_PEER]) {
+		struct nlattr *nla_peer = data[VXCAN_INFO_PEER];
+
+		ifmp = nla_data(nla_peer);
+		rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack);
+		tbp = peer_tb;
+	}
+
+	if (ifmp && tbp[IFLA_IFNAME]) {
+		nla_strscpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
+		name_assign_type = NET_NAME_USER;
+	} else {
+		snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d");
+		name_assign_type = NET_NAME_ENUM;
+	}
+
+	peer = rtnl_create_link(peer_net, ifname, name_assign_type,
+				&vxcan_link_ops, tbp, extack);
+	if (IS_ERR(peer))
+		return PTR_ERR(peer);
+
+	if (ifmp && dev->ifindex)
+		peer->ifindex = ifmp->ifi_index;
+
+	err = register_netdevice(peer);
+	if (err < 0) {
+		free_netdev(peer);
+		return err;
+	}
+
+	netif_carrier_off(peer);
+
+	err = rtnl_configure_link(peer, ifmp, 0, NULL);
+	if (err < 0)
+		goto unregister_network_device;
+
+	/* register first device */
+	if (tb[IFLA_IFNAME])
+		nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
+	else
+		snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d");
+
+	err = register_netdevice(dev);
+	if (err < 0)
+		goto unregister_network_device;
+
+	netif_carrier_off(dev);
+
+	/* cross link the device pair */
+	priv = netdev_priv(dev);
+	rcu_assign_pointer(priv->peer, peer);
+	netdev_hold(peer, &priv->peer_tracker, GFP_KERNEL);
+
+	priv = netdev_priv(peer);
+	rcu_assign_pointer(priv->peer, dev);
+	netdev_hold(dev, &priv->peer_tracker, GFP_KERNEL);
+
+	return 0;
+
+unregister_network_device:
+	unregister_netdevice(peer);
+	return err;
+}
+
+static void vxcan_dellink(struct net_device *dev, struct list_head *head)
+{
+	netdevice_tracker *peer_tracker;
+	struct vxcan_priv *priv;
+	struct net_device *peer;
+
+	priv = netdev_priv(dev);
+	peer_tracker = &priv->peer_tracker;
+	peer = unrcu_pointer(xchg(&priv->peer, NULL));
+	if (!peer)
+		return;
+
+	unregister_netdevice_queue(dev, head);
+
+	priv = netdev_priv(peer);
+	dev = unrcu_pointer(xchg(&priv->peer, NULL));
+	if (dev)
+		unregister_netdevice_queue_net(dev_net(dev), peer, head);
+
+	netdev_put(peer, peer_tracker);
+	netdev_put(dev, &priv->peer_tracker);
+}
+
+static const struct nla_policy vxcan_policy[VXCAN_INFO_MAX + 1] = {
+	[VXCAN_INFO_PEER] = { .len = sizeof(struct ifinfomsg) },
+};
+
+static struct net *vxcan_get_link_net(const struct net_device *dev)
+{
+	struct vxcan_priv *priv = netdev_priv(dev);
+	struct net_device *peer = rtnl_dereference(priv->peer);
+
+	return peer ? dev_net(peer) : dev_net(dev);
+}
+
+static struct rtnl_link_ops vxcan_link_ops = {
+	.kind		= DRV_NAME,
+	.priv_size	= ALIGN(sizeof(struct vxcan_priv), NETDEV_ALIGN) + sizeof(struct can_ml_priv),
+	.setup		= vxcan_setup,
+	.newlink	= vxcan_newlink,
+	.dellink	= vxcan_dellink,
+	.policy		= vxcan_policy,
+	.peer_type	= VXCAN_INFO_PEER,
+	.maxtype	= VXCAN_INFO_MAX,
+	.get_link_net	= vxcan_get_link_net,
+};
+
+static __init int vxcan_init(void)
+{
+	pr_info("vxcan: Virtual CAN Tunnel driver\n");
+
+	return rtnl_link_register(&vxcan_link_ops);
+}
+
+static __exit void vxcan_exit(void)
+{
+	rtnl_link_unregister(&vxcan_link_ops);
+}
+
+module_init(vxcan_init);
+module_exit(vxcan_exit);