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, 185 insertions, 0 deletions

diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
new file mode 100644
index 000000000..b99805ee2
--- /dev/null
+++ b/include/net/ip6_tunnel.h
@@ -0,0 +1,185 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NET_IP6_TUNNEL_H
+#define _NET_IP6_TUNNEL_H
+
+#include <linux/ipv6.h>
+#include <linux/netdevice.h>
+#include <linux/if_tunnel.h>
+#include <linux/ip6_tunnel.h>
+#include <net/ip_tunnels.h>
+#include <net/dst_cache.h>
+
+#define IP6TUNNEL_ERR_TIMEO (30*HZ)
+
+/* capable of sending packets */
+#define IP6_TNL_F_CAP_XMIT 0x10000
+/* capable of receiving packets */
+#define IP6_TNL_F_CAP_RCV 0x20000
+/* determine capability on a per-packet basis */
+#define IP6_TNL_F_CAP_PER_PACKET 0x40000
+
+struct __ip6_tnl_parm {
+	char name[IFNAMSIZ];	/* name of tunnel device */
+	int link;		/* ifindex of underlying L2 interface */
+	__u8 proto;		/* tunnel protocol */
+	__u8 encap_limit;	/* encapsulation limit for tunnel */
+	__u8 hop_limit;		/* hop limit for tunnel */
+	bool collect_md;
+	__be32 flowinfo;	/* traffic class and flowlabel for tunnel */
+	__u32 flags;		/* tunnel flags */
+	struct in6_addr laddr;	/* local tunnel end-point address */
+	struct in6_addr raddr;	/* remote tunnel end-point address */
+
+	IP_TUNNEL_DECLARE_FLAGS(i_flags);
+	IP_TUNNEL_DECLARE_FLAGS(o_flags);
+	__be32			i_key;
+	__be32			o_key;
+
+	__u32			fwmark;
+	__u32			index;	/* ERSPAN type II index */
+	__u8			erspan_ver;	/* ERSPAN version */
+	__u8			dir;	/* direction */
+	__u16			hwid;	/* hwid */
+};
+
+/* IPv6 tunnel */
+struct ip6_tnl {
+	struct ip6_tnl __rcu *next;	/* next tunnel in list */
+	struct net_device *dev;	/* virtual device associated with tunnel */
+	netdevice_tracker dev_tracker;
+	struct net *net;	/* netns for packet i/o */
+	struct __ip6_tnl_parm parms;	/* tunnel configuration parameters */
+	struct flowi fl;	/* flowi template for xmit */
+	struct dst_cache dst_cache;	/* cached dst */
+	struct gro_cells gro_cells;
+
+	int err_count;
+	unsigned long err_time;
+
+	/* These fields used only by GRE */
+	__u32 i_seqno;	/* The last seen seqno	*/
+	atomic_t o_seqno;	/* The last output seqno */
+	int hlen;       /* tun_hlen + encap_hlen */
+	int tun_hlen;	/* Precalculated header length */
+	int encap_hlen; /* Encap header length (FOU,GUE) */
+	struct ip_tunnel_encap encap;
+	int mlink;
+};
+
+struct ip6_tnl_encap_ops {
+	size_t (*encap_hlen)(struct ip_tunnel_encap *e);
+	int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
+			    u8 *protocol, struct flowi6 *fl6);
+	int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
+			   u8 type, u8 code, int offset, __be32 info);
+};
+
+#ifdef CONFIG_INET
+
+extern const struct ip6_tnl_encap_ops __rcu *
+		ip6tun_encaps[MAX_IPTUN_ENCAP_OPS];
+
+int ip6_tnl_encap_add_ops(const struct ip6_tnl_encap_ops *ops,
+			  unsigned int num);
+int ip6_tnl_encap_del_ops(const struct ip6_tnl_encap_ops *ops,
+			  unsigned int num);
+int ip6_tnl_encap_setup(struct ip6_tnl *t,
+			struct ip_tunnel_encap *ipencap);
+
+static inline int ip6_encap_hlen(struct ip_tunnel_encap *e)
+{
+	const struct ip6_tnl_encap_ops *ops;
+	int hlen = -EINVAL;
+
+	if (e->type == TUNNEL_ENCAP_NONE)
+		return 0;
+
+	if (e->type >= MAX_IPTUN_ENCAP_OPS)
+		return -EINVAL;
+
+	rcu_read_lock();
+	ops = rcu_dereference(ip6tun_encaps[e->type]);
+	if (likely(ops && ops->encap_hlen))
+		hlen = ops->encap_hlen(e);
+	rcu_read_unlock();
+
+	return hlen;
+}
+
+static inline int ip6_tnl_encap(struct sk_buff *skb, struct ip6_tnl *t,
+				u8 *protocol, struct flowi6 *fl6)
+{
+	const struct ip6_tnl_encap_ops *ops;
+	int ret = -EINVAL;
+
+	if (t->encap.type == TUNNEL_ENCAP_NONE)
+		return 0;
+
+	if (t->encap.type >= MAX_IPTUN_ENCAP_OPS)
+		return -EINVAL;
+
+	rcu_read_lock();
+	ops = rcu_dereference(ip6tun_encaps[t->encap.type]);
+	if (likely(ops && ops->build_header))
+		ret = ops->build_header(skb, &t->encap, protocol, fl6);
+	rcu_read_unlock();
+
+	return ret;
+}
+
+/* Tunnel encapsulation limit destination sub-option */
+
+struct ipv6_tlv_tnl_enc_lim {
+	__u8 type;		/* type-code for option         */
+	__u8 length;		/* option length                */
+	__u8 encap_limit;	/* tunnel encapsulation limit   */
+} __packed;
+
+int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
+		const struct in6_addr *raddr);
+int ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
+		const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst,
+		bool log_ecn_error);
+int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
+		     const struct in6_addr *raddr);
+int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
+		 struct flowi6 *fl6, int encap_limit, __u32 *pmtu, __u8 proto);
+__u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw);
+__u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr,
+			     const struct in6_addr *raddr);
+struct net *ip6_tnl_get_link_net(const struct net_device *dev);
+int ip6_tnl_get_iflink(const struct net_device *dev);
+int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu);
+
+static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
+				  struct net_device *dev, u16 ip6cb_flags)
+{
+	int pkt_len, err;
+
+	if (unlikely(dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT)) {
+		if (dev) {
+			net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
+					     dev->name);
+			DEV_STATS_INC(dev, tx_errors);
+		}
+		kfree_skb_reason(skb, SKB_DROP_REASON_RECURSION_LIMIT);
+		return;
+	}
+
+	dev_xmit_recursion_inc();
+
+	memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
+	IP6CB(skb)->flags = ip6cb_flags;
+	pkt_len = skb->len - skb_inner_network_offset(skb);
+	err = ip6_local_out(skb_dst_dev_net(skb), sk, skb);
+
+	if (dev) {
+		if (unlikely(net_xmit_eval(err)))
+			pkt_len = -1;
+		iptunnel_xmit_stats(dev, pkt_len);
+	}
+
+	dev_xmit_recursion_dec();
+}
+#endif
+#endif