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, 456 insertions, 0 deletions

diff --git a/include/net/ndisc.h b/include/net/ndisc.h
new file mode 100644
index 000000000..9e5379ad2
--- /dev/null
+++ b/include/net/ndisc.h
@@ -0,0 +1,456 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NDISC_H
+#define _NDISC_H
+
+/*
+ *	ICMP codes for neighbour discovery messages
+ */
+
+#define NDISC_ROUTER_SOLICITATION	133
+#define NDISC_ROUTER_ADVERTISEMENT	134
+#define NDISC_NEIGHBOUR_SOLICITATION	135
+#define NDISC_NEIGHBOUR_ADVERTISEMENT	136
+#define NDISC_REDIRECT			137
+
+/*
+ * Router type: cross-layer information from link-layer to
+ * IPv6 layer reported by certain link types (e.g., RFC4214).
+ */
+#define NDISC_NODETYPE_UNSPEC		0	/* unspecified (default) */
+#define NDISC_NODETYPE_HOST		1	/* host or unauthorized router */
+#define NDISC_NODETYPE_NODEFAULT	2	/* non-default router */
+#define NDISC_NODETYPE_DEFAULT		3	/* default router */
+
+/*
+ *	ndisc options
+ */
+
+enum {
+	__ND_OPT_PREFIX_INFO_END = 0,
+	ND_OPT_SOURCE_LL_ADDR = 1,	/* RFC2461 */
+	ND_OPT_TARGET_LL_ADDR = 2,	/* RFC2461 */
+	ND_OPT_PREFIX_INFO = 3,		/* RFC2461 */
+	ND_OPT_REDIRECT_HDR = 4,	/* RFC2461 */
+	ND_OPT_MTU = 5,			/* RFC2461 */
+	ND_OPT_NONCE = 14,              /* RFC7527 */
+	__ND_OPT_ARRAY_MAX,
+	ND_OPT_ROUTE_INFO = 24,		/* RFC4191 */
+	ND_OPT_RDNSS = 25,		/* RFC5006 */
+	ND_OPT_DNSSL = 31,		/* RFC6106 */
+	ND_OPT_6CO = 34,		/* RFC6775 */
+	ND_OPT_CAPTIVE_PORTAL = 37,	/* RFC7710 */
+	ND_OPT_PREF64 = 38,		/* RFC8781 */
+	__ND_OPT_MAX
+};
+
+#define MAX_RTR_SOLICITATION_DELAY	HZ
+
+#define ND_REACHABLE_TIME		(30*HZ)
+#define ND_RETRANS_TIMER		HZ
+
+#include <linux/compiler.h>
+#include <linux/icmpv6.h>
+#include <linux/in6.h>
+#include <linux/types.h>
+#include <linux/if_arp.h>
+#include <linux/netdevice.h>
+#include <linux/hash.h>
+
+#include <net/neighbour.h>
+
+struct ctl_table;
+struct inet6_dev;
+struct net_device;
+struct net_proto_family;
+struct sk_buff;
+struct prefix_info;
+
+extern struct neigh_table nd_tbl;
+
+struct nd_msg {
+        struct icmp6hdr	icmph;
+        struct in6_addr	target;
+	__u8		opt[];
+};
+
+struct rs_msg {
+	struct icmp6hdr	icmph;
+	__u8		opt[];
+};
+
+struct ra_msg {
+        struct icmp6hdr		icmph;
+	__be32			reachable_time;
+	__be32			retrans_timer;
+};
+
+struct rd_msg {
+	struct icmp6hdr icmph;
+	struct in6_addr	target;
+	struct in6_addr	dest;
+	__u8		opt[];
+};
+
+struct nd_opt_hdr {
+	__u8		nd_opt_type;
+	__u8		nd_opt_len;
+} __packed;
+
+/* ND options */
+struct ndisc_options {
+	struct nd_opt_hdr *nd_opt_array[__ND_OPT_ARRAY_MAX];
+#ifdef CONFIG_IPV6_ROUTE_INFO
+	struct nd_opt_hdr *nd_opts_ri;
+	struct nd_opt_hdr *nd_opts_ri_end;
+#endif
+	struct nd_opt_hdr *nd_useropts;
+	struct nd_opt_hdr *nd_useropts_end;
+#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
+	struct nd_opt_hdr *nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR + 1];
+#endif
+};
+
+#define nd_opts_src_lladdr		nd_opt_array[ND_OPT_SOURCE_LL_ADDR]
+#define nd_opts_tgt_lladdr		nd_opt_array[ND_OPT_TARGET_LL_ADDR]
+#define nd_opts_pi			nd_opt_array[ND_OPT_PREFIX_INFO]
+#define nd_opts_pi_end			nd_opt_array[__ND_OPT_PREFIX_INFO_END]
+#define nd_opts_rh			nd_opt_array[ND_OPT_REDIRECT_HDR]
+#define nd_opts_mtu			nd_opt_array[ND_OPT_MTU]
+#define nd_opts_nonce			nd_opt_array[ND_OPT_NONCE]
+#define nd_802154_opts_src_lladdr	nd_802154_opt_array[ND_OPT_SOURCE_LL_ADDR]
+#define nd_802154_opts_tgt_lladdr	nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR]
+
+#define NDISC_OPT_SPACE(len) (((len)+2+7)&~7)
+
+struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
+					  u8 *opt, int opt_len,
+					  struct ndisc_options *ndopts);
+
+void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data,
+			      int data_len, int pad);
+
+#define NDISC_OPS_REDIRECT_DATA_SPACE	2
+
+/*
+ * This structure defines the hooks for IPv6 neighbour discovery.
+ * The following hooks can be defined; unless noted otherwise, they are
+ * optional and can be filled with a null pointer.
+ *
+ * int (*parse_options)(const struct net_device *dev,
+ *			struct nd_opt_hdr *nd_opt,
+ *			struct ndisc_options *ndopts):
+ *     This function is called while parsing ndisc ops and put each position
+ *     as pointer into ndopts. If this function return unequal 0, then this
+ *     function took care about the ndisc option, if 0 then the IPv6 ndisc
+ *     option parser will take care about that option.
+ *
+ * void (*update)(const struct net_device *dev, struct neighbour *n,
+ *		  u32 flags, u8 icmp6_type,
+ *		  const struct ndisc_options *ndopts):
+ *     This function is called when IPv6 ndisc updates the neighbour cache
+ *     entry. Additional options which can be updated may be previously
+ *     parsed by parse_opts callback and accessible over ndopts parameter.
+ *
+ * int (*opt_addr_space)(const struct net_device *dev, u8 icmp6_type,
+ *			 struct neighbour *neigh, u8 *ha_buf,
+ *			 u8 **ha):
+ *     This function is called when the necessary option space will be
+ *     calculated before allocating a skb. The parameters neigh, ha_buf
+ *     abd ha are available on NDISC_REDIRECT messages only.
+ *
+ * void (*fill_addr_option)(const struct net_device *dev,
+ *			    struct sk_buff *skb, u8 icmp6_type,
+ *			    const u8 *ha):
+ *     This function is called when the skb will finally fill the option
+ *     fields inside skb. NOTE: this callback should fill the option
+ *     fields to the skb which are previously indicated by opt_space
+ *     parameter. That means the decision to add such option should
+ *     not lost between these two callbacks, e.g. protected by interface
+ *     up state.
+ *
+ * void (*prefix_rcv_add_addr)(struct net *net, struct net_device *dev,
+ *			       const struct prefix_info *pinfo,
+ *			       struct inet6_dev *in6_dev,
+ *			       struct in6_addr *addr,
+ *			       int addr_type, u32 addr_flags,
+ *			       bool sllao, bool tokenized,
+ *			       __u32 valid_lft, u32 prefered_lft,
+ *			       bool dev_addr_generated):
+ *     This function is called when a RA messages is received with valid
+ *     PIO option fields and an IPv6 address will be added to the interface
+ *     for autoconfiguration. The parameter dev_addr_generated reports about
+ *     if the address was based on dev->dev_addr or not. This can be used
+ *     to add a second address if link-layer operates with two link layer
+ *     addresses. E.g. 802.15.4 6LoWPAN.
+ */
+struct ndisc_ops {
+	int	(*parse_options)(const struct net_device *dev,
+				 struct nd_opt_hdr *nd_opt,
+				 struct ndisc_options *ndopts);
+	void	(*update)(const struct net_device *dev, struct neighbour *n,
+			  u32 flags, u8 icmp6_type,
+			  const struct ndisc_options *ndopts);
+	int	(*opt_addr_space)(const struct net_device *dev, u8 icmp6_type,
+				  struct neighbour *neigh, u8 *ha_buf,
+				  u8 **ha);
+	void	(*fill_addr_option)(const struct net_device *dev,
+				    struct sk_buff *skb, u8 icmp6_type,
+				    const u8 *ha);
+	void	(*prefix_rcv_add_addr)(struct net *net, struct net_device *dev,
+				       const struct prefix_info *pinfo,
+				       struct inet6_dev *in6_dev,
+				       struct in6_addr *addr,
+				       int addr_type, u32 addr_flags,
+				       bool sllao, bool tokenized,
+				       __u32 valid_lft, u32 prefered_lft,
+				       bool dev_addr_generated);
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+static inline int ndisc_ops_parse_options(const struct net_device *dev,
+					  struct nd_opt_hdr *nd_opt,
+					  struct ndisc_options *ndopts)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->parse_options)
+		return dev->ndisc_ops->parse_options(dev, nd_opt, ndopts);
+	else
+		return 0;
+}
+
+static inline void ndisc_ops_update(const struct net_device *dev,
+					  struct neighbour *n, u32 flags,
+					  u8 icmp6_type,
+					  const struct ndisc_options *ndopts)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->update)
+		dev->ndisc_ops->update(dev, n, flags, icmp6_type, ndopts);
+}
+
+static inline int ndisc_ops_opt_addr_space(const struct net_device *dev,
+					   u8 icmp6_type)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space &&
+	    icmp6_type != NDISC_REDIRECT)
+		return dev->ndisc_ops->opt_addr_space(dev, icmp6_type, NULL,
+						      NULL, NULL);
+	else
+		return 0;
+}
+
+static inline int ndisc_ops_redirect_opt_addr_space(const struct net_device *dev,
+						    struct neighbour *neigh,
+						    u8 *ha_buf, u8 **ha)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space)
+		return dev->ndisc_ops->opt_addr_space(dev, NDISC_REDIRECT,
+						      neigh, ha_buf, ha);
+	else
+		return 0;
+}
+
+static inline void ndisc_ops_fill_addr_option(const struct net_device *dev,
+					      struct sk_buff *skb,
+					      u8 icmp6_type)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option &&
+	    icmp6_type != NDISC_REDIRECT)
+		dev->ndisc_ops->fill_addr_option(dev, skb, icmp6_type, NULL);
+}
+
+static inline void ndisc_ops_fill_redirect_addr_option(const struct net_device *dev,
+						       struct sk_buff *skb,
+						       const u8 *ha)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option)
+		dev->ndisc_ops->fill_addr_option(dev, skb, NDISC_REDIRECT, ha);
+}
+
+static inline void ndisc_ops_prefix_rcv_add_addr(struct net *net,
+						 struct net_device *dev,
+						 const struct prefix_info *pinfo,
+						 struct inet6_dev *in6_dev,
+						 struct in6_addr *addr,
+						 int addr_type, u32 addr_flags,
+						 bool sllao, bool tokenized,
+						 __u32 valid_lft,
+						 u32 prefered_lft,
+						 bool dev_addr_generated)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->prefix_rcv_add_addr)
+		dev->ndisc_ops->prefix_rcv_add_addr(net, dev, pinfo, in6_dev,
+						    addr, addr_type,
+						    addr_flags, sllao,
+						    tokenized, valid_lft,
+						    prefered_lft,
+						    dev_addr_generated);
+}
+#endif
+
+/*
+ * Return the padding between the option length and the start of the
+ * link addr.  Currently only IP-over-InfiniBand needs this, although
+ * if RFC 3831 IPv6-over-Fibre Channel is ever implemented it may
+ * also need a pad of 2.
+ */
+static inline int ndisc_addr_option_pad(unsigned short type)
+{
+	switch (type) {
+	case ARPHRD_INFINIBAND: return 2;
+	default:                return 0;
+	}
+}
+
+static inline int __ndisc_opt_addr_space(unsigned char addr_len, int pad)
+{
+	return NDISC_OPT_SPACE(addr_len + pad);
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static inline int ndisc_opt_addr_space(struct net_device *dev, u8 icmp6_type)
+{
+	return __ndisc_opt_addr_space(dev->addr_len,
+				      ndisc_addr_option_pad(dev->type)) +
+		ndisc_ops_opt_addr_space(dev, icmp6_type);
+}
+
+static inline int ndisc_redirect_opt_addr_space(struct net_device *dev,
+						struct neighbour *neigh,
+						u8 *ops_data_buf,
+						u8 **ops_data)
+{
+	return __ndisc_opt_addr_space(dev->addr_len,
+				      ndisc_addr_option_pad(dev->type)) +
+		ndisc_ops_redirect_opt_addr_space(dev, neigh, ops_data_buf,
+						  ops_data);
+}
+#endif
+
+static inline u8 *__ndisc_opt_addr_data(struct nd_opt_hdr *p,
+					unsigned char addr_len, int prepad)
+{
+	u8 *lladdr = (u8 *)(p + 1);
+	int lladdrlen = p->nd_opt_len << 3;
+	if (lladdrlen != __ndisc_opt_addr_space(addr_len, prepad))
+		return NULL;
+	return lladdr + prepad;
+}
+
+static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p,
+				      struct net_device *dev)
+{
+	return __ndisc_opt_addr_data(p, dev->addr_len,
+				     ndisc_addr_option_pad(dev->type));
+}
+
+static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, __u32 *hash_rnd)
+{
+	const u32 *p32 = pkey;
+
+	return (((p32[0] ^ hash32_ptr(dev)) * hash_rnd[0]) +
+		(p32[1] * hash_rnd[1]) +
+		(p32[2] * hash_rnd[2]) +
+		(p32[3] * hash_rnd[3]));
+}
+
+static inline struct neighbour *__ipv6_neigh_lookup_noref(struct net_device *dev, const void *pkey)
+{
+	return ___neigh_lookup_noref(&nd_tbl, neigh_key_eq128, ndisc_hashfn, pkey, dev);
+}
+
+static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, const void *pkey)
+{
+	struct neighbour *n;
+
+	rcu_read_lock();
+	n = __ipv6_neigh_lookup_noref(dev, pkey);
+	if (n && !refcount_inc_not_zero(&n->refcnt))
+		n = NULL;
+	rcu_read_unlock();
+
+	return n;
+}
+
+static inline void __ipv6_confirm_neigh(struct net_device *dev,
+					const void *pkey)
+{
+	struct neighbour *n;
+
+	rcu_read_lock();
+	n = __ipv6_neigh_lookup_noref(dev, pkey);
+	neigh_confirm(n);
+	rcu_read_unlock();
+}
+
+static inline struct neighbour *ip_neigh_gw6(struct net_device *dev,
+					     const void *addr)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	struct neighbour *neigh;
+
+	neigh = __ipv6_neigh_lookup_noref(dev, addr);
+	if (unlikely(!neigh))
+		neigh = __neigh_create(&nd_tbl, addr, dev, false);
+
+	return neigh;
+#else
+	return ERR_PTR(-EAFNOSUPPORT);
+#endif
+}
+
+int ndisc_init(void);
+int ndisc_late_init(void);
+
+void ndisc_late_cleanup(void);
+void ndisc_cleanup(void);
+
+enum skb_drop_reason ndisc_rcv(struct sk_buff *skb);
+
+struct sk_buff *ndisc_ns_create(struct net_device *dev, const struct in6_addr *solicit,
+				const struct in6_addr *saddr, u64 nonce);
+void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
+		   const struct in6_addr *daddr, const struct in6_addr *saddr,
+		   u64 nonce);
+
+void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr,
+		    const struct in6_addr *saddr);
+
+void ndisc_send_rs(struct net_device *dev,
+		   const struct in6_addr *saddr, const struct in6_addr *daddr);
+
+void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr,
+		   const struct in6_addr *solicited_addr,
+		   bool router, bool solicited, bool override, bool inc_opt);
+
+void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target);
+
+int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev,
+		 int dir);
+
+void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
+		  const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type,
+		  struct ndisc_options *ndopts);
+
+int ndisc_check_ns_na(struct sk_buff *skb);
+
+/*
+ *	IGMP
+ */
+int igmp6_init(void);
+int igmp6_late_init(void);
+
+void igmp6_cleanup(void);
+void igmp6_late_cleanup(void);
+
+void igmp6_event_query(struct sk_buff *skb);
+
+void igmp6_event_report(struct sk_buff *skb);
+
+
+#ifdef CONFIG_SYSCTL
+int ndisc_ifinfo_sysctl_change(const struct ctl_table *ctl, int write,
+			       void *buffer, size_t *lenp, loff_t *ppos);
+#endif
+
+void inet6_ifinfo_notify(int event, struct inet6_dev *idev);
+
+#endif