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, 265 insertions, 0 deletions

diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c
new file mode 100644
index 000000000..7e114862a
--- /dev/null
+++ b/arch/um/os-Linux/main.c
@@ -0,0 +1,265 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de)
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <errno.h>
+#include <signal.h>
+#include <string.h>
+#include <sys/resource.h>
+#include <sys/personality.h>
+#include <as-layout.h>
+#include <init.h>
+#include <kern_util.h>
+#include <os.h>
+#include <um_malloc.h>
+#include "internal.h"
+
+#define STACKSIZE (8 * 1024 * 1024)
+
+static void __init set_stklim(void)
+{
+	struct rlimit lim;
+
+	if (getrlimit(RLIMIT_STACK, &lim) < 0) {
+		perror("getrlimit");
+		exit(1);
+	}
+	if ((lim.rlim_cur == RLIM_INFINITY) || (lim.rlim_cur > STACKSIZE)) {
+		lim.rlim_cur = STACKSIZE;
+		if (setrlimit(RLIMIT_STACK, &lim) < 0) {
+			perror("setrlimit");
+			exit(1);
+		}
+	}
+}
+
+static void last_ditch_exit(int sig)
+{
+	uml_cleanup();
+	exit(1);
+}
+
+static void __init install_fatal_handler(int sig)
+{
+	struct sigaction action;
+
+	/* All signals are enabled in this handler ... */
+	sigemptyset(&action.sa_mask);
+
+	/*
+	 * ... including the signal being handled, plus we want the
+	 * handler reset to the default behavior, so that if an exit
+	 * handler is hanging for some reason, the UML will just die
+	 * after this signal is sent a second time.
+	 */
+	action.sa_flags = SA_RESETHAND | SA_NODEFER;
+	action.sa_restorer = NULL;
+	action.sa_handler = last_ditch_exit;
+	if (sigaction(sig, &action, NULL) < 0) {
+		os_warn("failed to install handler for signal %d "
+			"- errno = %d\n", sig, errno);
+		exit(1);
+	}
+}
+
+#define UML_LIB_PATH	":" OS_LIB_PATH "/uml"
+
+static void __init setup_env_path(void)
+{
+	char *new_path = NULL;
+	char *old_path = NULL;
+	int path_len = 0;
+
+	old_path = getenv("PATH");
+	/*
+	 * if no PATH variable is set or it has an empty value
+	 * just use the default + /usr/lib/uml
+	 */
+	if (!old_path || (path_len = strlen(old_path)) == 0) {
+		if (putenv("PATH=:/bin:/usr/bin/" UML_LIB_PATH))
+			perror("couldn't putenv");
+		return;
+	}
+
+	/* append /usr/lib/uml to the existing path */
+	path_len += strlen("PATH=" UML_LIB_PATH) + 1;
+	new_path = malloc(path_len);
+	if (!new_path) {
+		perror("couldn't malloc to set a new PATH");
+		return;
+	}
+	snprintf(new_path, path_len, "PATH=%s" UML_LIB_PATH, old_path);
+	if (putenv(new_path)) {
+		perror("couldn't putenv to set a new PATH");
+		free(new_path);
+	}
+}
+
+int __init main(int argc, char **argv, char **envp)
+{
+	char **new_argv;
+	int ret, i, err;
+
+	/* Disable randomization and re-exec if it was changed successfully */
+	ret = personality(PER_LINUX | ADDR_NO_RANDOMIZE);
+	if (ret >= 0 && (ret & (PER_LINUX | ADDR_NO_RANDOMIZE)) !=
+			 (PER_LINUX | ADDR_NO_RANDOMIZE)) {
+		char buf[4096] = {};
+		ssize_t ret;
+
+		ret = readlink("/proc/self/exe", buf, sizeof(buf));
+		if (ret < 0 || ret >= sizeof(buf)) {
+			perror("readlink failure");
+			exit(1);
+		}
+		execve(buf, argv, envp);
+	}
+
+	set_stklim();
+
+	setup_env_path();
+
+	setsid();
+
+	new_argv = malloc((argc + 1) * sizeof(char *));
+	if (new_argv == NULL) {
+		perror("Mallocing argv");
+		exit(1);
+	}
+	for (i = 0; i < argc; i++) {
+		new_argv[i] = strdup(argv[i]);
+		if (new_argv[i] == NULL) {
+			perror("Mallocing an arg");
+			exit(1);
+		}
+	}
+	new_argv[argc] = NULL;
+
+	/*
+	 * Allow these signals to bring down a UML if all other
+	 * methods of control fail.
+	 */
+	install_fatal_handler(SIGINT);
+	install_fatal_handler(SIGTERM);
+
+	scan_elf_aux(envp);
+
+	change_sig(SIGPIPE, 0);
+	ret = linux_main(argc, argv, envp);
+
+	/*
+	 * Disable SIGPROF - I have no idea why libc doesn't do this or turn
+	 * off the profiling time, but UML dies with a SIGPROF just before
+	 * exiting when profiling is active.
+	 */
+	change_sig(SIGPROF, 0);
+
+	/*
+	 * This signal stuff used to be in the reboot case.  However,
+	 * sometimes a timer signal can come in when we're halting (reproducably
+	 * when writing out gcov information, presumably because that takes
+	 * some time) and cause a segfault.
+	 */
+
+	/* stop timers and set timer signal to be ignored */
+	os_timer_disable(0);
+
+	/* disable SIGIO for the fds and set SIGIO to be ignored */
+	err = deactivate_all_fds();
+	if (err)
+		os_warn("deactivate_all_fds failed, errno = %d\n", -err);
+
+	/*
+	 * Let any pending signals fire now.  This ensures
+	 * that they won't be delivered after the exec, when
+	 * they are definitely not expected.
+	 */
+	unblock_signals();
+
+	os_info("\n");
+	/* Reboot */
+	if (ret) {
+		execvp(new_argv[0], new_argv);
+		perror("Failed to exec kernel");
+		ret = 1;
+	}
+	return uml_exitcode;
+}
+
+extern void *__real_malloc(int);
+extern void __real_free(void *);
+
+/* workaround for -Wmissing-prototypes warnings */
+void *__wrap_malloc(int size);
+void *__wrap_calloc(int n, int size);
+void __wrap_free(void *ptr);
+
+void *__wrap_malloc(int size)
+{
+	void *ret;
+
+	if (!kmalloc_ok)
+		return __real_malloc(size);
+	else if (size <= UM_KERN_PAGE_SIZE)
+		/* finding contiguous pages can be hard*/
+		ret = uml_kmalloc(size, UM_GFP_KERNEL);
+	else ret = vmalloc(size);
+
+	/*
+	 * glibc people insist that if malloc fails, errno should be
+	 * set by malloc as well. So we do.
+	 */
+	if (ret == NULL)
+		errno = ENOMEM;
+
+	return ret;
+}
+
+void *__wrap_calloc(int n, int size)
+{
+	void *ptr = __wrap_malloc(n * size);
+
+	if (ptr == NULL)
+		return NULL;
+	memset(ptr, 0, n * size);
+	return ptr;
+}
+
+void __wrap_free(void *ptr)
+{
+	unsigned long addr = (unsigned long) ptr;
+
+	/*
+	 * We need to know how the allocation happened, so it can be correctly
+	 * freed.  This is done by seeing what region of memory the pointer is
+	 * in -
+	 * 	physical memory - kmalloc/kfree
+	 *	kernel virtual memory - vmalloc/vfree
+	 * 	anywhere else - malloc/free
+	 * If kmalloc is not yet possible, then either high_physmem and/or
+	 * end_vm are still 0 (as at startup), in which case we call free, or
+	 * we have set them, but anyway addr has not been allocated from those
+	 * areas. So, in both cases __real_free is called.
+	 *
+	 * CAN_KMALLOC is checked because it would be bad to free a buffer
+	 * with kmalloc/vmalloc after they have been turned off during
+	 * shutdown.
+	 * XXX: However, we sometimes shutdown CAN_KMALLOC temporarily, so
+	 * there is a possibility for memory leaks.
+	 */
+
+	if ((addr >= uml_physmem) && (addr < high_physmem)) {
+		if (kmalloc_ok)
+			kfree(ptr);
+	}
+	else if ((addr >= start_vm) && (addr < end_vm)) {
+		if (kmalloc_ok)
+			vfree(ptr);
+	}
+	else __real_free(ptr);
+}