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, 198 insertions, 0 deletions

diff --git a/include/net/kcm.h b/include/net/kcm.h
new file mode 100644
index 000000000..d9c35e71e
--- /dev/null
+++ b/include/net/kcm.h
@@ -0,0 +1,198 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Kernel Connection Multiplexor
+ *
+ * Copyright (c) 2016 Tom Herbert <tom@herbertland.com>
+ */
+
+#ifndef __NET_KCM_H_
+#define __NET_KCM_H_
+
+#include <linux/skbuff.h>
+#include <net/sock.h>
+#include <net/strparser.h>
+#include <uapi/linux/kcm.h>
+
+extern unsigned int kcm_net_id;
+
+#define KCM_STATS_ADD(stat, count) ((stat) += (count))
+#define KCM_STATS_INCR(stat) ((stat)++)
+
+struct kcm_psock_stats {
+	unsigned long long tx_msgs;
+	unsigned long long tx_bytes;
+	unsigned long long reserved;
+	unsigned long long unreserved;
+	unsigned int tx_aborts;
+};
+
+struct kcm_mux_stats {
+	unsigned long long rx_msgs;
+	unsigned long long rx_bytes;
+	unsigned long long tx_msgs;
+	unsigned long long tx_bytes;
+	unsigned int rx_ready_drops;
+	unsigned int tx_retries;
+	unsigned int psock_attach;
+	unsigned int psock_unattach_rsvd;
+	unsigned int psock_unattach;
+};
+
+struct kcm_stats {
+	unsigned long long rx_msgs;
+	unsigned long long rx_bytes;
+	unsigned long long tx_msgs;
+	unsigned long long tx_bytes;
+};
+
+struct kcm_tx_msg {
+	unsigned int sent;
+	unsigned int frag_offset;
+	unsigned int msg_flags;
+	bool started_tx;
+	struct sk_buff *frag_skb;
+	struct sk_buff *last_skb;
+};
+
+/* Socket structure for KCM client sockets */
+struct kcm_sock {
+	struct sock sk;
+	struct kcm_mux *mux;
+	struct list_head kcm_sock_list;
+	int index;
+	u32 done : 1;
+	struct work_struct done_work;
+
+	struct kcm_stats stats;
+
+	/* Transmit */
+	struct kcm_psock *tx_psock;
+	struct work_struct tx_work;
+	struct list_head wait_psock_list;
+	struct sk_buff *seq_skb;
+	struct mutex tx_mutex;
+
+	/* Don't use bit fields here, these are set under different locks */
+	bool tx_wait;
+	bool tx_wait_more;
+
+	/* Receive */
+	struct kcm_psock *rx_psock;
+	struct list_head wait_rx_list; /* KCMs waiting for receiving */
+	bool rx_wait;
+	u32 rx_disabled : 1;
+};
+
+struct bpf_prog;
+
+/* Structure for an attached lower socket */
+struct kcm_psock {
+	struct sock *sk;
+	struct strparser strp;
+	struct kcm_mux *mux;
+	int index;
+
+	u32 tx_stopped : 1;
+	u32 done : 1;
+	u32 unattaching : 1;
+
+	void (*save_state_change)(struct sock *sk);
+	void (*save_data_ready)(struct sock *sk);
+	void (*save_write_space)(struct sock *sk);
+
+	struct list_head psock_list;
+
+	struct kcm_psock_stats stats;
+
+	/* Receive */
+	struct list_head psock_ready_list;
+	struct bpf_prog *bpf_prog;
+	struct kcm_sock *rx_kcm;
+	unsigned long long saved_rx_bytes;
+	unsigned long long saved_rx_msgs;
+	struct sk_buff *ready_rx_msg;
+
+	/* Transmit */
+	struct kcm_sock *tx_kcm;
+	struct list_head psock_avail_list;
+	unsigned long long saved_tx_bytes;
+	unsigned long long saved_tx_msgs;
+};
+
+/* Per net MUX list */
+struct kcm_net {
+	struct mutex mutex;
+	struct kcm_psock_stats aggregate_psock_stats;
+	struct kcm_mux_stats aggregate_mux_stats;
+	struct strp_aggr_stats aggregate_strp_stats;
+	struct list_head mux_list;
+	int count;
+};
+
+/* Structure for a MUX */
+struct kcm_mux {
+	struct list_head kcm_mux_list;
+	struct rcu_head rcu;
+	struct kcm_net *knet;
+
+	struct list_head kcm_socks;	/* All KCM sockets on MUX */
+	int kcm_socks_cnt;		/* Total KCM socket count for MUX */
+	struct list_head psocks;	/* List of all psocks on MUX */
+	int psocks_cnt;		/* Total attached sockets */
+
+	struct kcm_mux_stats stats;
+	struct kcm_psock_stats aggregate_psock_stats;
+	struct strp_aggr_stats aggregate_strp_stats;
+
+	/* Receive */
+	spinlock_t rx_lock ____cacheline_aligned_in_smp;
+	struct list_head kcm_rx_waiters; /* KCMs waiting for receiving */
+	struct list_head psocks_ready;	/* List of psocks with a msg ready */
+	struct sk_buff_head rx_hold_queue;
+
+	/* Transmit */
+	spinlock_t  lock ____cacheline_aligned_in_smp;	/* TX and mux locking */
+	struct list_head psocks_avail;	/* List of available psocks */
+	struct list_head kcm_tx_waiters; /* KCMs waiting for a TX psock */
+};
+
+#ifdef CONFIG_PROC_FS
+int kcm_proc_init(void);
+void kcm_proc_exit(void);
+#else
+static inline int kcm_proc_init(void) { return 0; }
+static inline void kcm_proc_exit(void) { }
+#endif
+
+static inline void aggregate_psock_stats(struct kcm_psock_stats *stats,
+					 struct kcm_psock_stats *agg_stats)
+{
+	/* Save psock statistics in the mux when psock is being unattached. */
+
+#define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += stats->_stat)
+	SAVE_PSOCK_STATS(tx_msgs);
+	SAVE_PSOCK_STATS(tx_bytes);
+	SAVE_PSOCK_STATS(reserved);
+	SAVE_PSOCK_STATS(unreserved);
+	SAVE_PSOCK_STATS(tx_aborts);
+#undef SAVE_PSOCK_STATS
+}
+
+static inline void aggregate_mux_stats(struct kcm_mux_stats *stats,
+				       struct kcm_mux_stats *agg_stats)
+{
+	/* Save psock statistics in the mux when psock is being unattached. */
+
+#define SAVE_MUX_STATS(_stat) (agg_stats->_stat += stats->_stat)
+	SAVE_MUX_STATS(rx_msgs);
+	SAVE_MUX_STATS(rx_bytes);
+	SAVE_MUX_STATS(tx_msgs);
+	SAVE_MUX_STATS(tx_bytes);
+	SAVE_MUX_STATS(rx_ready_drops);
+	SAVE_MUX_STATS(psock_attach);
+	SAVE_MUX_STATS(psock_unattach_rsvd);
+	SAVE_MUX_STATS(psock_unattach);
+#undef SAVE_MUX_STATS
+}
+
+#endif /* __NET_KCM_H_ */