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, 232 insertions, 0 deletions

diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h
new file mode 100644
index 000000000..883cfd7de
--- /dev/null
+++ b/include/uapi/asm-generic/fcntl.h
@@ -0,0 +1,232 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _ASM_GENERIC_FCNTL_H
+#define _ASM_GENERIC_FCNTL_H
+
+#include <linux/types.h>
+
+/*
+ * FMODE_EXEC is 0x20
+ * These cannot be used by userspace O_* until internal and external open
+ * flags are split.
+ * -Eric Paris
+ */
+
+/*
+ * When introducing new O_* bits, please check its uniqueness in fcntl_init().
+ */
+
+#define O_ACCMODE	3
+#define O_RDONLY	0
+#define O_WRONLY	(1 << 0)
+#define O_RDWR		(1 << 1)
+/* (1 << 2) must not be used -- it collides with flags on alpha, sparc */
+/* (1 << 3) must not be used -- it collides with flags on alpha, mips, parisc, sparc */
+/* (1 << 4) must not be used -- it collides with flags on mips */
+/* (1 << 5) is free */
+#ifndef O_CREAT
+#define O_CREAT		(1 << 6)	/* not fcntl */
+#endif
+#ifndef O_EXCL
+#define O_EXCL		(1 << 7)	/* not fcntl */
+#endif
+#ifndef O_NOCTTY
+#define O_NOCTTY	(1 << 8)	/* not fcntl */
+#endif
+#ifndef O_TRUNC
+#define O_TRUNC		(1 << 9)	/* not fcntl */
+#endif
+#ifndef O_APPEND
+#define O_APPEND	(1 << 10)
+#endif
+#ifndef O_NONBLOCK
+#define O_NONBLOCK	(1 << 11)
+#endif
+#ifndef O_DSYNC
+#define O_DSYNC		(1 << 12)	/* used to be O_SYNC, see below */
+#endif
+#ifndef FASYNC
+#define FASYNC		(1 << 13)	/* fcntl, for BSD compatibility */
+#endif
+#ifndef O_DIRECT
+#define O_DIRECT	(1 << 14)	/* direct disk access hint */
+#endif
+#ifndef O_LARGEFILE
+#define O_LARGEFILE	(1 << 15)
+#endif
+#ifndef O_DIRECTORY
+#define O_DIRECTORY	(1 << 16)	/* must be a directory */
+#endif
+#ifndef O_NOFOLLOW
+#define O_NOFOLLOW	(1 << 17)	/* don't follow links */
+#endif
+#ifndef O_NOATIME
+#define O_NOATIME	(1 << 18)
+#endif
+#ifndef O_CLOEXEC
+#define O_CLOEXEC	(1 << 19)	/* set close_on_exec */
+#endif
+
+/*
+ * Before Linux 2.6.33 only O_DSYNC semantics were implemented, but using
+ * the O_SYNC flag.  We continue to use the existing numerical value
+ * for O_DSYNC semantics now, but using the correct symbolic name for it.
+ * This new value is used to request true Posix O_SYNC semantics.  It is
+ * defined in this strange way to make sure applications compiled against
+ * new headers get at least O_DSYNC semantics on older kernels.
+ *
+ * This has the nice side-effect that we can simply test for O_DSYNC
+ * wherever we do not care if O_DSYNC or O_SYNC is used.
+ *
+ * Note: __O_SYNC must never be used directly.
+ */
+#ifndef O_SYNC
+#define __O_SYNC	(1 << 20)
+#define O_SYNC		(__O_SYNC|O_DSYNC)
+#endif
+
+#ifndef O_PATH
+#define O_PATH		(1 << 21)
+#endif
+
+#ifndef __O_TMPFILE
+#define __O_TMPFILE	(1 << 22)
+#endif
+
+#ifndef O_EMPTYPATH
+#define O_EMPTYPATH	(1 << 26)	/* allow empty path */
+#endif
+
+/* a horrid kludge trying to make sure that this will fail on old kernels */
+#define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
+
+#ifndef O_NDELAY
+#define O_NDELAY	O_NONBLOCK
+#endif
+
+/* (1 << 23) must not be used -- it collides with flags on alpha, parisc, sparc */
+/* (1 << 24) must not be used -- it collides with flags on alpha, sparc */
+/* (1 << 25) must not be used -- it collides with flags on sparc */
+
+#define F_DUPFD		0	/* dup */
+#define F_GETFD		1	/* get close_on_exec */
+#define F_SETFD		2	/* set/clear close_on_exec */
+#define F_GETFL		3	/* get file->f_flags */
+#define F_SETFL		4	/* set file->f_flags */
+#ifndef F_GETLK
+#define F_GETLK		5
+#define F_SETLK		6
+#define F_SETLKW	7
+#endif
+#ifndef F_SETOWN
+#define F_SETOWN	8	/* for sockets. */
+#define F_GETOWN	9	/* for sockets. */
+#endif
+#ifndef F_SETSIG
+#define F_SETSIG	10	/* for sockets. */
+#define F_GETSIG	11	/* for sockets. */
+#endif
+
+#if __BITS_PER_LONG == 32 || defined(__KERNEL__)
+#ifndef F_GETLK64
+#define F_GETLK64	12	/*  using 'struct flock64' */
+#define F_SETLK64	13
+#define F_SETLKW64	14
+#endif
+#endif /* __BITS_PER_LONG == 32 || defined(__KERNEL__) */
+
+#ifndef F_SETOWN_EX
+#define F_SETOWN_EX	15
+#define F_GETOWN_EX	16
+#endif
+
+#ifndef F_GETOWNER_UIDS
+#define F_GETOWNER_UIDS	17
+#endif
+
+/*
+ * Open File Description Locks
+ *
+ * Usually record locks held by a process are released on *any* close and are
+ * not inherited across a fork().
+ *
+ * These cmd values will set locks that conflict with process-associated
+ * record  locks, but are "owned" by the open file description, not the
+ * process. This means that they are inherited across fork() like BSD (flock)
+ * locks, and they are only released automatically when the last reference to
+ * the the open file against which they were acquired is put.
+ */
+#define F_OFD_GETLK	36
+#define F_OFD_SETLK	37
+#define F_OFD_SETLKW	38
+
+#define F_OWNER_TID	0
+#define F_OWNER_PID	1
+#define F_OWNER_PGRP	2
+
+struct f_owner_ex {
+	int	type;
+	__kernel_pid_t	pid;
+};
+
+/* for F_[GET|SET]FL */
+#define FD_CLOEXEC	1	/* actually anything with low bit set goes */
+
+/* for posix fcntl() and lockf() */
+#ifndef F_RDLCK
+#define F_RDLCK		0
+#define F_WRLCK		1
+#define F_UNLCK		2
+#endif
+
+/* for old implementation of bsd flock () */
+#ifndef F_EXLCK
+#define F_EXLCK		4	/* or 3 */
+#define F_SHLCK		8	/* or 4 */
+#endif
+
+/* operations for bsd flock(), also used by the kernel implementation */
+#define LOCK_SH		1	/* shared lock */
+#define LOCK_EX		2	/* exclusive lock */
+#define LOCK_NB		4	/* or'd with one of the above to prevent
+				   blocking */
+#define LOCK_UN		8	/* remove lock */
+
+/*
+ * LOCK_MAND support has been removed from the kernel. We leave the symbols
+ * here to not break legacy builds, but these should not be used in new code.
+ */
+#define LOCK_MAND	32	/* This is a mandatory flock ... */
+#define LOCK_READ	64	/* which allows concurrent read operations */
+#define LOCK_WRITE	128	/* which allows concurrent write operations */
+#define LOCK_RW		192	/* which allows concurrent read & write ops */
+
+#define F_LINUX_SPECIFIC_BASE	1024
+
+#ifndef HAVE_ARCH_STRUCT_FLOCK
+struct flock {
+	short	l_type;
+	short	l_whence;
+	__kernel_off_t	l_start;
+	__kernel_off_t	l_len;
+	__kernel_pid_t	l_pid;
+#ifdef	__ARCH_FLOCK_EXTRA_SYSID
+	__ARCH_FLOCK_EXTRA_SYSID
+#endif
+#ifdef	__ARCH_FLOCK_PAD
+	__ARCH_FLOCK_PAD
+#endif
+};
+
+struct flock64 {
+	short  l_type;
+	short  l_whence;
+	__kernel_loff_t l_start;
+	__kernel_loff_t l_len;
+	__kernel_pid_t  l_pid;
+#ifdef	__ARCH_FLOCK64_PAD
+	__ARCH_FLOCK64_PAD
+#endif
+};
+#endif /* HAVE_ARCH_STRUCT_FLOCK */
+
+#endif /* _ASM_GENERIC_FCNTL_H */