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, 159 insertions, 0 deletions

diff --git a/net/packet/internal.h b/net/packet/internal.h
new file mode 100644
index 000000000..b76e645cd
--- /dev/null
+++ b/net/packet/internal.h
@@ -0,0 +1,159 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PACKET_INTERNAL_H__
+#define __PACKET_INTERNAL_H__
+
+#include <linux/refcount.h>
+
+struct packet_mclist {
+	struct packet_mclist	*next;
+	int			ifindex;
+	int			count;
+	unsigned short		type;
+	unsigned short		alen;
+	unsigned char		addr[MAX_ADDR_LEN];
+	struct list_head	remove_list;
+};
+
+/* kbdq - kernel block descriptor queue */
+struct tpacket_kbdq_core {
+	struct pgv	*pkbdq;
+	unsigned int	feature_req_word;
+	unsigned int	hdrlen;
+	unsigned char	reset_pending_on_curr_blk;
+	unsigned short	kactive_blk_num;
+	unsigned short	blk_sizeof_priv;
+
+	unsigned short  version;
+
+	char		*pkblk_start;
+	char		*pkblk_end;
+	int		kblk_size;
+	unsigned int	max_frame_len;
+	unsigned int	knum_blocks;
+	uint64_t	knxt_seq_num;
+	char		*prev;
+	char		*nxt_offset;
+
+	struct sk_buff	*skb;
+
+	rwlock_t	blk_fill_in_prog_lock;
+
+	/* Default is set to 8ms */
+#define DEFAULT_PRB_RETIRE_TOV	(8)
+
+	ktime_t		interval_ktime;
+
+	/* timer to retire an outstanding block */
+	struct hrtimer  retire_blk_timer;
+};
+
+struct pgv {
+	char *buffer;
+};
+
+struct packet_ring_buffer {
+	struct pgv		*pg_vec;
+
+	unsigned int		head;
+	unsigned int		frames_per_block;
+	unsigned int		frame_size;
+	unsigned int		frame_max;
+
+	unsigned int		pg_vec_order;
+	unsigned int		pg_vec_pages;
+	unsigned int		pg_vec_len;
+
+	unsigned int __percpu	*pending_refcnt;
+
+	union {
+		unsigned long			*rx_owner_map;
+		struct tpacket_kbdq_core	prb_bdqc;
+	};
+};
+
+extern struct mutex fanout_mutex;
+#define PACKET_FANOUT_MAX	(1 << 16)
+
+struct packet_fanout {
+	possible_net_t		net;
+	unsigned int		num_members;
+	u32			max_num_members;
+	u16			id;
+	u8			type;
+	u8			flags;
+	union {
+		atomic_t		rr_cur;
+		struct bpf_prog __rcu	*bpf_prog;
+	};
+	struct list_head	list;
+	spinlock_t		lock;
+	refcount_t		sk_ref;
+	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
+	struct sock	__rcu	*arr[] __counted_by(max_num_members);
+};
+
+struct packet_rollover {
+	int			sock;
+	atomic_long_t		num;
+	atomic_long_t		num_huge;
+	atomic_long_t		num_failed;
+#define ROLLOVER_HLEN	(L1_CACHE_BYTES / sizeof(u32))
+	u32			history[ROLLOVER_HLEN] ____cacheline_aligned;
+} ____cacheline_aligned_in_smp;
+
+struct packet_sock {
+	/* struct sock has to be the first member of packet_sock */
+	struct sock		sk;
+	struct packet_fanout	*fanout;
+	union  tpacket_stats_u	stats;
+	struct packet_ring_buffer	rx_ring;
+	struct packet_ring_buffer	tx_ring;
+	int			copy_thresh;
+	spinlock_t		bind_lock;
+	struct mutex		pg_vec_lock;
+	unsigned long		flags;
+	int			ifindex;	/* bound device		*/
+	u8			vnet_hdr_sz;
+	__be16			num;
+	struct packet_rollover	*rollover;
+	struct packet_mclist	*mclist;
+	atomic_long_t		mapped;
+	enum tpacket_versions	tp_version;
+	unsigned int		tp_hdrlen;
+	unsigned int		tp_reserve;
+	unsigned int		tp_tstamp;
+	struct completion	skb_completion;
+	struct net_device __rcu	*cached_dev;
+	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
+	atomic_t		tp_drops ____cacheline_aligned_in_smp;
+};
+
+#define pkt_sk(ptr) container_of_const(ptr, struct packet_sock, sk)
+
+enum packet_sock_flags {
+	PACKET_SOCK_ORIGDEV,
+	PACKET_SOCK_AUXDATA,
+	PACKET_SOCK_TX_HAS_OFF,
+	PACKET_SOCK_TP_LOSS,
+	PACKET_SOCK_RUNNING,
+	PACKET_SOCK_PRESSURE,
+	PACKET_SOCK_QDISC_BYPASS,
+};
+
+static inline void packet_sock_flag_set(struct packet_sock *po,
+					enum packet_sock_flags flag,
+					bool val)
+{
+	if (val)
+		set_bit(flag, &po->flags);
+	else
+		clear_bit(flag, &po->flags);
+}
+
+static inline bool packet_sock_flag(const struct packet_sock *po,
+				    enum packet_sock_flags flag)
+{
+	return test_bit(flag, &po->flags);
+}
+
+#endif