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, 282 insertions, 0 deletions

diff --git a/scripts/checksyscalls.sh b/scripts/checksyscalls.sh
new file mode 100755
index 000000000..e2970421c
--- /dev/null
+++ b/scripts/checksyscalls.sh
@@ -0,0 +1,282 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Check if current architecture are missing any function calls compared
+# to i386.
+# i386 define a number of legacy system calls that are i386 specific
+# and listed below so they are ignored.
+#
+# Usage:
+# checksyscalls.sh gcc gcc-options
+#
+
+set -e
+
+reference_table="$(dirname $0)/../arch/x86/entry/syscalls/syscall_32.tbl"
+
+ignore_list() {
+cat << EOF
+#include <asm/types.h>
+#include <asm/unistd.h>
+
+/* *at */
+#define __IGNORE_open		/* openat */
+#define __IGNORE_link		/* linkat */
+#define __IGNORE_unlink		/* unlinkat */
+#define __IGNORE_mknod		/* mknodat */
+#define __IGNORE_chmod		/* fchmodat */
+#define __IGNORE_chown		/* fchownat */
+#define __IGNORE_mkdir		/* mkdirat */
+#define __IGNORE_rmdir		/* unlinkat */
+#define __IGNORE_lchown		/* fchownat */
+#define __IGNORE_access		/* faccessat */
+#define __IGNORE_rename		/* renameat2 */
+#define __IGNORE_readlink	/* readlinkat */
+#define __IGNORE_symlink	/* symlinkat */
+#define __IGNORE_utimes		/* futimesat */
+#define __IGNORE_stat		/* fstatat */
+#define __IGNORE_lstat		/* fstatat */
+#define __IGNORE_stat64		/* fstatat64 */
+#define __IGNORE_lstat64	/* fstatat64 */
+
+#ifndef __ARCH_WANT_SET_GET_RLIMIT
+#define __IGNORE_getrlimit	/* getrlimit */
+#define __IGNORE_setrlimit	/* setrlimit */
+#endif
+
+#ifndef __ARCH_WANT_MEMFD_SECRET
+#define __IGNORE_memfd_secret
+#endif
+
+/* Missing flags argument */
+#define __IGNORE_renameat	/* renameat2 */
+
+/* CLOEXEC flag */
+#define __IGNORE_pipe		/* pipe2 */
+#define __IGNORE_dup2		/* dup3 */
+#define __IGNORE_epoll_create	/* epoll_create1 */
+#define __IGNORE_inotify_init	/* inotify_init1 */
+#define __IGNORE_eventfd	/* eventfd2 */
+#define __IGNORE_signalfd	/* signalfd4 */
+
+/* MMU */
+#ifndef CONFIG_MMU
+#define __IGNORE_madvise
+#define __IGNORE_mbind
+#define __IGNORE_mincore
+#define __IGNORE_mlock
+#define __IGNORE_mlockall
+#define __IGNORE_munlock
+#define __IGNORE_munlockall
+#define __IGNORE_mprotect
+#define __IGNORE_msync
+#define __IGNORE_migrate_pages
+#define __IGNORE_move_pages
+#define __IGNORE_remap_file_pages
+#define __IGNORE_get_mempolicy
+#define __IGNORE_set_mempolicy
+#define __IGNORE_swapoff
+#define __IGNORE_swapon
+#endif
+
+/* System calls for 32-bit kernels only */
+#if BITS_PER_LONG == 64
+#define __IGNORE_sendfile64
+#define __IGNORE_ftruncate64
+#define __IGNORE_truncate64
+#define __IGNORE_stat64
+#define __IGNORE_lstat64
+#define __IGNORE_fcntl64
+#define __IGNORE_fadvise64_64
+#define __IGNORE_fstatfs64
+#define __IGNORE_statfs64
+#define __IGNORE_llseek
+#define __IGNORE_mmap2
+#define __IGNORE_clock_gettime64
+#define __IGNORE_clock_settime64
+#define __IGNORE_clock_adjtime64
+#define __IGNORE_clock_getres_time64
+#define __IGNORE_clock_nanosleep_time64
+#define __IGNORE_timer_gettime64
+#define __IGNORE_timer_settime64
+#define __IGNORE_timerfd_gettime64
+#define __IGNORE_timerfd_settime64
+#define __IGNORE_utimensat_time64
+#define __IGNORE_pselect6_time64
+#define __IGNORE_ppoll_time64
+#define __IGNORE_io_pgetevents_time64
+#define __IGNORE_recvmmsg_time64
+#define __IGNORE_mq_timedsend_time64
+#define __IGNORE_mq_timedreceive_time64
+#define __IGNORE_semtimedop_time64
+#define __IGNORE_rt_sigtimedwait_time64
+#define __IGNORE_futex_time64
+#define __IGNORE_sched_rr_get_interval_time64
+#else
+#define __IGNORE_sendfile
+#define __IGNORE_ftruncate
+#define __IGNORE_truncate
+#define __IGNORE_stat
+#define __IGNORE_lstat
+#define __IGNORE_fcntl
+#define __IGNORE_fadvise64
+#define __IGNORE_newfstatat
+#define __IGNORE_fstatfs
+#define __IGNORE_statfs
+#define __IGNORE_lseek
+#define __IGNORE_mmap
+#define __IGNORE_clock_gettime
+#define __IGNORE_clock_settime
+#define __IGNORE_clock_adjtime
+#define __IGNORE_clock_getres
+#define __IGNORE_clock_nanosleep
+#define __IGNORE_timer_gettime
+#define __IGNORE_timer_settime
+#define __IGNORE_timerfd_gettime
+#define __IGNORE_timerfd_settime
+#define __IGNORE_utimensat
+#define __IGNORE_pselect6
+#define __IGNORE_ppoll
+#define __IGNORE_io_pgetevents
+#define __IGNORE_recvmmsg
+#define __IGNORE_mq_timedsend
+#define __IGNORE_mq_timedreceive
+#define __IGNORE_semtimedop
+#define __IGNORE_rt_sigtimedwait
+#define __IGNORE_futex
+#define __IGNORE_sched_rr_get_interval
+#define __IGNORE_gettimeofday
+#define __IGNORE_settimeofday
+#define __IGNORE_wait4
+#define __IGNORE_adjtimex
+#define __IGNORE_nanosleep
+#define __IGNORE_io_getevents
+#define __IGNORE_recvmmsg
+#endif
+
+/* i386-specific or historical system calls */
+#define __IGNORE_break
+#define __IGNORE_stty
+#define __IGNORE_gtty
+#define __IGNORE_ftime
+#define __IGNORE_prof
+#define __IGNORE_lock
+#define __IGNORE_mpx
+#define __IGNORE_ulimit
+#define __IGNORE_profil
+#define __IGNORE_ioperm
+#define __IGNORE_iopl
+#define __IGNORE_idle
+#define __IGNORE_modify_ldt
+#define __IGNORE_ugetrlimit
+#define __IGNORE_vm86
+#define __IGNORE_vm86old
+#define __IGNORE_set_thread_area
+#define __IGNORE_get_thread_area
+#define __IGNORE_madvise1
+#define __IGNORE_oldstat
+#define __IGNORE_oldfstat
+#define __IGNORE_oldlstat
+#define __IGNORE_oldolduname
+#define __IGNORE_olduname
+#define __IGNORE_umount
+#define __IGNORE_waitpid
+#define __IGNORE_stime
+#define __IGNORE_nice
+#define __IGNORE_signal
+#define __IGNORE_sigaction
+#define __IGNORE_sgetmask
+#define __IGNORE_sigsuspend
+#define __IGNORE_sigpending
+#define __IGNORE_ssetmask
+#define __IGNORE_readdir
+#define __IGNORE_socketcall
+#define __IGNORE_ipc
+#define __IGNORE_sigreturn
+#define __IGNORE_sigprocmask
+#define __IGNORE_bdflush
+#define __IGNORE__llseek
+#define __IGNORE__newselect
+#define __IGNORE_create_module
+#define __IGNORE_query_module
+#define __IGNORE_get_kernel_syms
+#define __IGNORE_sysfs
+#define __IGNORE_uselib
+#define __IGNORE__sysctl
+#define __IGNORE_arch_prctl
+#define __IGNORE_nfsservctl
+
+/* ... including the "new" 32-bit uid syscalls */
+#define __IGNORE_lchown32
+#define __IGNORE_getuid32
+#define __IGNORE_getgid32
+#define __IGNORE_geteuid32
+#define __IGNORE_getegid32
+#define __IGNORE_setreuid32
+#define __IGNORE_setregid32
+#define __IGNORE_getgroups32
+#define __IGNORE_setgroups32
+#define __IGNORE_fchown32
+#define __IGNORE_setresuid32
+#define __IGNORE_getresuid32
+#define __IGNORE_setresgid32
+#define __IGNORE_getresgid32
+#define __IGNORE_chown32
+#define __IGNORE_setuid32
+#define __IGNORE_setgid32
+#define __IGNORE_setfsuid32
+#define __IGNORE_setfsgid32
+
+/* these can be expressed using other calls */
+#define __IGNORE_alarm		/* setitimer */
+#define __IGNORE_creat		/* open */
+#define __IGNORE_fork		/* clone */
+#define __IGNORE_futimesat	/* utimensat */
+#define __IGNORE_getpgrp	/* getpgid */
+#define __IGNORE_getdents	/* getdents64 */
+#define __IGNORE_pause		/* sigsuspend */
+#define __IGNORE_poll		/* ppoll */
+#define __IGNORE_select		/* pselect6 */
+#define __IGNORE_epoll_wait	/* epoll_pwait */
+#define __IGNORE_time		/* gettimeofday */
+#define __IGNORE_uname		/* newuname */
+#define __IGNORE_ustat		/* statfs */
+#define __IGNORE_utime		/* utimes */
+#define __IGNORE_vfork		/* clone */
+
+/* sync_file_range had a stupid ABI. Allow sync_file_range2 instead */
+#ifdef __NR_sync_file_range2
+#define __IGNORE_sync_file_range
+#endif
+
+/* Unmerged syscalls for AFS, STREAMS, etc. */
+#define __IGNORE_afs_syscall
+#define __IGNORE_getpmsg
+#define __IGNORE_putpmsg
+#define __IGNORE_vserver
+
+/* 64-bit ports never needed these, and new 32-bit ports can use statx */
+#define __IGNORE_fstat64
+#define __IGNORE_fstatat64
+
+/* Newer ports are not required to provide fstat in favor of statx */
+#define __IGNORE_fstat
+EOF
+}
+
+syscall_list() {
+    grep '^[0-9]' "$1" | sort -n |
+	while read nr abi name entry ; do
+		echo "#if !defined(__NR_${name}) && !defined(__IGNORE_${name})"
+		echo "#warning syscall ${name} not implemented"
+		echo "#endif"
+	done
+}
+
+(ignore_list && syscall_list ${reference_table}) | \
+$* -Wno-error -Wno-unused-macros -E -x c - > /dev/null
+
+# For fixdep
+if [ -n "${DEPFILE}" ]; then
+	echo "${0}: ${0} ${reference_table}" >> "${DEPFILE}"
+fi