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, 331 insertions, 0 deletions

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
new file mode 100644
index 000000000..485d55b66
--- /dev/null
+++ b/include/net/mptcp.h
@@ -0,0 +1,331 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Multipath TCP
+ *
+ * Copyright (c) 2017 - 2019, Intel Corporation.
+ */
+
+#ifndef __NET_MPTCP_H
+#define __NET_MPTCP_H
+
+#include <linux/skbuff.h>
+#include <linux/tcp.h>
+#include <linux/types.h>
+
+struct mptcp_info;
+struct mptcp_sock;
+struct mptcp_pm_addr_entry;
+struct seq_file;
+
+/* MPTCP sk_buff extension data */
+struct mptcp_ext {
+	u64		data_seq;
+	u32		subflow_seq;
+	u16		data_len;
+	__sum16		csum;
+
+	struct_group(flags,
+		u8	use_map:1,
+			dsn64:1,
+			data_fin:1,
+			use_ack:1,
+			ack64:1,
+			mpc_map:1,
+			frozen:1,
+			reset_transient:1;
+		u8	reset_reason:4,
+			csum_reqd:1,
+			infinite_map:1;
+	); /* end of flags group */
+};
+
+#define MPTCPOPT_HMAC_LEN	20
+#define MPTCP_RM_IDS_MAX	8
+
+struct mptcp_rm_list {
+	u8 ids[MPTCP_RM_IDS_MAX];
+	u8 nr;
+};
+
+struct mptcp_addr_info {
+	u8			id;
+	sa_family_t		family;
+	__be16			port;
+	union {
+		struct in_addr	addr;
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+		struct in6_addr	addr6;
+#endif
+	};
+};
+
+struct mptcp_out_options {
+#if IS_ENABLED(CONFIG_MPTCP)
+	u16 suboptions;
+	struct mptcp_rm_list rm_list;
+	u8 join_id;
+	u8 backup;
+	u8 reset_reason:4,
+	   reset_transient:1,
+	   csum_reqd:1,
+	   allow_join_id0:1,
+	   drop_ts:1;
+	union {
+		struct {
+			u64 sndr_key;
+			u64 rcvr_key;
+			u64 data_seq;
+			u32 subflow_seq;
+			u16 data_len;
+			__sum16 csum;
+		};
+		struct {
+			struct mptcp_addr_info addr;
+			u64 ahmac;
+		};
+		struct {
+			struct mptcp_ext ext_copy;
+			u64 fail_seq;
+		};
+		struct {
+			u32 nonce;
+			u32 token;
+			u64 thmac;
+			u8 hmac[MPTCPOPT_HMAC_LEN];
+		};
+	};
+#endif
+};
+
+#define MPTCP_SCHED_NAME_MAX	16
+#define MPTCP_SCHED_MAX		128
+#define MPTCP_SCHED_BUF_MAX	(MPTCP_SCHED_NAME_MAX * MPTCP_SCHED_MAX)
+
+struct mptcp_sched_ops {
+	int (*get_send)(struct mptcp_sock *msk);
+	int (*get_retrans)(struct mptcp_sock *msk);
+
+	char			name[MPTCP_SCHED_NAME_MAX];
+	struct module		*owner;
+	struct list_head	list;
+
+	void (*init)(struct mptcp_sock *msk);
+	void (*release)(struct mptcp_sock *msk);
+} ____cacheline_aligned_in_smp;
+
+#define MPTCP_PM_NAME_MAX	16
+#define MPTCP_PM_MAX		128
+#define MPTCP_PM_BUF_MAX	(MPTCP_PM_NAME_MAX * MPTCP_PM_MAX)
+
+struct mptcp_pm_ops {
+	char			name[MPTCP_PM_NAME_MAX];
+	struct module		*owner;
+	struct list_head	list;
+
+	void (*init)(struct mptcp_sock *msk);
+	void (*release)(struct mptcp_sock *msk);
+} ____cacheline_aligned_in_smp;
+
+#ifdef CONFIG_MPTCP
+void mptcp_init(void);
+
+static inline bool sk_is_mptcp(const struct sock *sk)
+{
+	return tcp_sk(sk)->is_mptcp;
+}
+
+static inline bool rsk_is_mptcp(const struct request_sock *req)
+{
+	return tcp_rsk(req)->is_mptcp;
+}
+
+static inline bool rsk_drop_req(const struct request_sock *req)
+{
+	return tcp_rsk(req)->is_mptcp && tcp_rsk(req)->drop_req;
+}
+
+void mptcp_space(const struct sock *ssk, int *space, int *full_space);
+bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
+		       unsigned int *size, struct mptcp_out_options *opts);
+bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
+			  struct mptcp_out_options *opts);
+int mptcp_established_options(struct sock *sk, struct sk_buff *skb,
+			      unsigned int remaining, bool has_ts,
+			      struct mptcp_out_options *opts);
+bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb);
+
+void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp,
+			 struct mptcp_out_options *opts);
+
+void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info);
+
+/* move the skb extension owership, with the assumption that 'to' is
+ * newly allocated
+ */
+static inline void mptcp_skb_ext_move(struct sk_buff *to,
+				      struct sk_buff *from)
+{
+	if (!skb_ext_exist(from, SKB_EXT_MPTCP))
+		return;
+
+	if (WARN_ON_ONCE(to->active_extensions))
+		skb_ext_put(to);
+
+	to->active_extensions = from->active_extensions;
+	to->extensions = from->extensions;
+	from->active_extensions = 0;
+}
+
+static inline void mptcp_skb_ext_copy(struct sk_buff *to,
+				      struct sk_buff *from)
+{
+	struct mptcp_ext *from_ext;
+
+	from_ext = skb_ext_find(from, SKB_EXT_MPTCP);
+	if (!from_ext)
+		return;
+
+	from_ext->frozen = 1;
+	skb_ext_copy(to, from);
+}
+
+static inline bool mptcp_ext_matches(const struct mptcp_ext *to_ext,
+				     const struct mptcp_ext *from_ext)
+{
+	/* MPTCP always clears the ext when adding it to the skb, so
+	 * holes do not bother us here
+	 */
+	return !from_ext ||
+	       (to_ext && from_ext &&
+	        !memcmp(from_ext, to_ext, sizeof(struct mptcp_ext)));
+}
+
+/* check if skbs can be collapsed.
+ * MPTCP collapse is allowed if neither @to or @from carry an mptcp data
+ * mapping, or if the extension of @to is the same as @from.
+ * Collapsing is not possible if @to lacks an extension, but @from carries one.
+ */
+static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
+					  const struct sk_buff *from)
+{
+	return mptcp_ext_matches(skb_ext_find(to, SKB_EXT_MPTCP),
+				 skb_ext_find(from, SKB_EXT_MPTCP));
+}
+
+void mptcp_seq_show(struct seq_file *seq);
+int mptcp_subflow_init_cookie_req(struct request_sock *req,
+				  const struct sock *sk_listener,
+				  struct sk_buff *skb);
+struct request_sock *mptcp_subflow_reqsk_alloc(const struct request_sock_ops *ops,
+					       struct sock *sk_listener,
+					       bool attach_listener);
+
+__be32 mptcp_get_reset_option(const struct sk_buff *skb);
+
+static inline __be32 mptcp_reset_option(const struct sk_buff *skb)
+{
+	if (skb_ext_exist(skb, SKB_EXT_MPTCP))
+		return mptcp_get_reset_option(skb);
+
+	return htonl(0u);
+}
+
+void mptcp_active_detect_blackhole(struct sock *sk, bool expired);
+#else
+
+static inline void mptcp_init(void)
+{
+}
+
+static inline bool sk_is_mptcp(const struct sock *sk)
+{
+	return false;
+}
+
+static inline bool rsk_is_mptcp(const struct request_sock *req)
+{
+	return false;
+}
+
+static inline bool rsk_drop_req(const struct request_sock *req)
+{
+	return false;
+}
+
+static inline bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
+				     unsigned int *size,
+				     struct mptcp_out_options *opts)
+{
+	return false;
+}
+
+static inline bool mptcp_synack_options(const struct request_sock *req,
+					unsigned int *size,
+					struct mptcp_out_options *opts)
+{
+	return false;
+}
+
+static inline bool mptcp_incoming_options(struct sock *sk,
+					  struct sk_buff *skb)
+{
+	return true;
+}
+
+static inline void mptcp_skb_ext_move(struct sk_buff *to,
+				      const struct sk_buff *from)
+{
+}
+
+static inline void mptcp_skb_ext_copy(struct sk_buff *to,
+				      struct sk_buff *from)
+{
+}
+
+static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
+					  const struct sk_buff *from)
+{
+	return true;
+}
+
+static inline void mptcp_space(const struct sock *ssk, int *s, int *fs) { }
+static inline void mptcp_seq_show(struct seq_file *seq) { }
+
+static inline int mptcp_subflow_init_cookie_req(struct request_sock *req,
+						const struct sock *sk_listener,
+						struct sk_buff *skb)
+{
+	return 0; /* TCP fallback */
+}
+
+static inline struct request_sock *mptcp_subflow_reqsk_alloc(const struct request_sock_ops *ops,
+							     struct sock *sk_listener,
+							     bool attach_listener)
+{
+	return NULL;
+}
+
+static inline __be32 mptcp_reset_option(const struct sk_buff *skb)  { return htonl(0u); }
+
+static inline void mptcp_active_detect_blackhole(struct sock *sk, bool expired) { }
+#endif /* CONFIG_MPTCP */
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+int mptcpv6_init(void);
+void mptcpv6_handle_mapped(struct sock *sk, bool mapped);
+#elif IS_ENABLED(CONFIG_IPV6)
+static inline int mptcpv6_init(void) { return 0; }
+static inline void mptcpv6_handle_mapped(struct sock *sk, bool mapped) { }
+#endif
+
+#if defined(CONFIG_MPTCP) && defined(CONFIG_BPF_SYSCALL)
+struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk);
+#else
+static inline struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk) { return NULL; }
+#endif
+
+#if !IS_ENABLED(CONFIG_MPTCP)
+struct mptcp_sock { };
+#endif
+
+#endif /* __NET_MPTCP_H */