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, 292 insertions, 0 deletions

diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
new file mode 100644
index 000000000..1fb6ce684
--- /dev/null
+++ b/drivers/net/loopback.c
@@ -0,0 +1,292 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		Pseudo-driver for the loopback interface.
+ *
+ * Version:	@(#)loopback.c	1.0.4b	08/16/93
+ *
+ * Authors:	Ross Biro
+ *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *		Donald Becker, <becker@scyld.com>
+ *
+ *		Alan Cox	:	Fixed oddments for NET3.014
+ *		Alan Cox	:	Rejig for NET3.029 snap #3
+ *		Alan Cox	:	Fixed NET3.029 bugs and sped up
+ *		Larry McVoy	:	Tiny tweak to double performance
+ *		Alan Cox	:	Backed out LMV's tweak - the linux mm
+ *					can't take it...
+ *              Michael Griffith:       Don't bother computing the checksums
+ *                                      on packets received on the loopback
+ *                                      interface.
+ *		Alexey Kuznetsov:	Potential hang under some extreme
+ *					cases removed.
+ */
+#include <linux/kernel.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/fs.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/socket.h>
+#include <linux/errno.h>
+#include <linux/fcntl.h>
+#include <linux/in.h>
+
+#include <linux/uaccess.h>
+#include <linux/io.h>
+
+#include <linux/inet.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/ethtool.h>
+#include <net/sch_generic.h>
+#include <net/sock.h>
+#include <net/checksum.h>
+#include <linux/if_ether.h>	/* For the statistics structure. */
+#include <linux/if_arp.h>	/* For ARPHRD_ETHER */
+#include <linux/ip.h>
+#include <linux/tcp.h>
+#include <linux/percpu.h>
+#include <linux/net_tstamp.h>
+#include <net/net_namespace.h>
+#include <net/netdev_lock.h>
+#include <linux/u64_stats_sync.h>
+
+/* blackhole_netdev - a device used for dsts that are marked expired!
+ * This is global device (instead of per-net-ns) since it's not needed
+ * to be per-ns and gets initialized at boot time.
+ */
+struct net_device *blackhole_netdev;
+EXPORT_SYMBOL(blackhole_netdev);
+
+/* The higher levels take care of making this non-reentrant (it's
+ * called with bh's disabled).
+ */
+static netdev_tx_t loopback_xmit(struct sk_buff *skb,
+				 struct net_device *dev)
+{
+	int len;
+
+	skb_tx_timestamp(skb);
+
+	/* do not fool net_timestamp_check() with various clock bases */
+	skb_clear_tstamp(skb);
+
+	skb_orphan(skb);
+
+	/* Before queueing this packet to __netif_rx(),
+	 * make sure dst is refcounted.
+	 */
+	skb_dst_force(skb);
+
+	skb->protocol = eth_type_trans(skb, dev);
+
+	len = skb->len;
+	if (likely(__netif_rx(skb) == NET_RX_SUCCESS))
+		dev_lstats_add(dev, len);
+
+	return NETDEV_TX_OK;
+}
+
+void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes)
+{
+	int i;
+
+	*packets = 0;
+	*bytes = 0;
+
+	for_each_possible_cpu(i) {
+		const struct pcpu_lstats *lb_stats;
+		u64 tbytes, tpackets;
+		unsigned int start;
+
+		lb_stats = per_cpu_ptr(dev->lstats, i);
+		do {
+			start = u64_stats_fetch_begin(&lb_stats->syncp);
+			tpackets = u64_stats_read(&lb_stats->packets);
+			tbytes = u64_stats_read(&lb_stats->bytes);
+		} while (u64_stats_fetch_retry(&lb_stats->syncp, start));
+		*bytes   += tbytes;
+		*packets += tpackets;
+	}
+}
+EXPORT_SYMBOL(dev_lstats_read);
+
+static void loopback_get_stats64(struct net_device *dev,
+				 struct rtnl_link_stats64 *stats)
+{
+	u64 packets, bytes;
+
+	dev_lstats_read(dev, &packets, &bytes);
+
+	stats->rx_packets = packets;
+	stats->tx_packets = packets;
+	stats->rx_bytes   = bytes;
+	stats->tx_bytes   = bytes;
+}
+
+static u32 always_on(struct net_device *dev)
+{
+	return 1;
+}
+
+static const struct ethtool_ops loopback_ethtool_ops = {
+	.get_link		= always_on,
+	.get_ts_info		= ethtool_op_get_ts_info,
+};
+
+static int loopback_dev_init(struct net_device *dev)
+{
+	netdev_lockdep_set_classes(dev);
+	return 0;
+}
+
+static void loopback_dev_free(struct net_device *dev)
+{
+	dev_net(dev)->loopback_dev = NULL;
+}
+
+static const struct net_device_ops loopback_ops = {
+	.ndo_init        = loopback_dev_init,
+	.ndo_start_xmit  = loopback_xmit,
+	.ndo_get_stats64 = loopback_get_stats64,
+	.ndo_set_mac_address = eth_mac_addr,
+};
+
+static void gen_lo_setup(struct net_device *dev,
+			 unsigned int mtu,
+			 const struct ethtool_ops *eth_ops,
+			 const struct header_ops *hdr_ops,
+			 const struct net_device_ops *dev_ops,
+			 void (*dev_destructor)(struct net_device *dev))
+{
+	dev->mtu		= mtu;
+	dev->hard_header_len	= ETH_HLEN;	/* 14	*/
+	dev->min_header_len	= ETH_HLEN;	/* 14	*/
+	dev->addr_len		= ETH_ALEN;	/* 6	*/
+	dev->type		= ARPHRD_LOOPBACK;	/* 0x0001*/
+	dev->flags		= IFF_LOOPBACK;
+	dev->priv_flags		|= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
+	dev->lltx		= true;
+	dev->netns_immutable	= true;
+	netif_keep_dst(dev);
+	dev->hw_features	= NETIF_F_GSO_SOFTWARE;
+	dev->features		= NETIF_F_SG | NETIF_F_FRAGLIST
+		| NETIF_F_GSO_SOFTWARE
+		| NETIF_F_HW_CSUM
+		| NETIF_F_RXCSUM
+		| NETIF_F_SCTP_CRC
+		| NETIF_F_HIGHDMA
+		| NETIF_F_VLAN_CHALLENGED
+		| NETIF_F_LOOPBACK;
+	dev->ethtool_ops	= eth_ops;
+	dev->header_ops		= hdr_ops;
+	dev->netdev_ops		= dev_ops;
+	dev->needs_free_netdev	= true;
+	dev->pcpu_stat_type	= NETDEV_PCPU_STAT_LSTATS;
+	dev->priv_destructor	= dev_destructor;
+
+	netif_set_tso_max_size(dev, GSO_MAX_SIZE);
+}
+
+/* The loopback device is special. There is only one instance
+ * per network namespace.
+ */
+static void loopback_setup(struct net_device *dev)
+{
+	gen_lo_setup(dev, (64 * 1024), &loopback_ethtool_ops, &eth_header_ops,
+		     &loopback_ops, loopback_dev_free);
+}
+
+/* Setup and register the loopback device. */
+static __net_init int loopback_net_init(struct net *net)
+{
+	struct net_device *dev;
+	int err;
+
+	err = -ENOMEM;
+	dev = alloc_netdev(0, "lo", NET_NAME_PREDICTABLE, loopback_setup);
+	if (!dev)
+		goto out;
+
+	dev_net_set(dev, net);
+	err = register_netdev(dev);
+	if (err)
+		goto out_free_netdev;
+
+	BUG_ON(dev->ifindex != LOOPBACK_IFINDEX);
+	net->loopback_dev = dev;
+	return 0;
+
+out_free_netdev:
+	free_netdev(dev);
+out:
+	if (net_eq(net, &init_net))
+		panic("loopback: Failed to register netdevice: %d\n", err);
+	return err;
+}
+
+/* Registered in net/core/dev.c */
+struct pernet_operations __net_initdata loopback_net_ops = {
+	.init = loopback_net_init,
+};
+
+/* blackhole netdevice */
+static netdev_tx_t blackhole_netdev_xmit(struct sk_buff *skb,
+					 struct net_device *dev)
+{
+	kfree_skb(skb);
+	net_warn_ratelimited("%s(): Dropping skb.\n", __func__);
+	return NETDEV_TX_OK;
+}
+
+static int blackhole_neigh_output(struct neighbour *n, struct sk_buff *skb)
+{
+	kfree_skb(skb);
+	return 0;
+}
+
+static int blackhole_neigh_construct(struct net_device *dev,
+				     struct neighbour *n)
+{
+	n->output = blackhole_neigh_output;
+	return 0;
+}
+
+static const struct net_device_ops blackhole_netdev_ops = {
+	.ndo_start_xmit = blackhole_netdev_xmit,
+	.ndo_neigh_construct = blackhole_neigh_construct,
+};
+
+/* This is a dst-dummy device used specifically for invalidated
+ * DSTs and unlike loopback, this is not per-ns.
+ */
+static void blackhole_netdev_setup(struct net_device *dev)
+{
+	gen_lo_setup(dev, ETH_MIN_MTU, NULL, NULL, &blackhole_netdev_ops, NULL);
+}
+
+/* Setup and register the blackhole_netdev. */
+static int __init blackhole_netdev_init(void)
+{
+	blackhole_netdev = alloc_netdev(0, "blackhole_dev", NET_NAME_UNKNOWN,
+					blackhole_netdev_setup);
+	if (!blackhole_netdev)
+		return -ENOMEM;
+
+	rtnl_net_lock(&init_net);
+	dev_init_scheduler(blackhole_netdev);
+	dev_activate(blackhole_netdev);
+	rtnl_net_unlock(&init_net);
+
+	blackhole_netdev->flags |= IFF_UP | IFF_RUNNING;
+
+	return 0;
+}
+
+device_initcall(blackhole_netdev_init);