From 034dd340b08be1f2f0477ad16131d609f9dbd53c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 Aug 2026 09:22:00 -0700 Subject: Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace 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 --- arch/um/os-Linux/util.c | 209 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 209 insertions(+) create mode 100644 arch/um/os-Linux/util.c (limited to 'arch/um/os-Linux/util.c') diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c new file mode 100644 index 000000000..e3ad71a0d --- /dev/null +++ b/arch/um/os-Linux/util.c @@ -0,0 +1,209 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +void stack_protections(unsigned long address) +{ + if (mprotect((void *) address, UM_THREAD_SIZE, PROT_READ | PROT_WRITE) < 0) + panic("protecting stack failed, errno = %d", errno); +} + +int raw(int fd) +{ + struct termios tt; + int err; + + CATCH_EINTR(err = tcgetattr(fd, &tt)); + if (err < 0) + return -errno; + + cfmakeraw(&tt); + + CATCH_EINTR(err = tcsetattr(fd, TCSADRAIN, &tt)); + if (err < 0) + return -errno; + + /* + * XXX tcsetattr could have applied only some changes + * (and cfmakeraw() is a set of changes) + */ + return 0; +} + +void setup_machinename(char *machine_out) +{ + struct utsname host; + + uname(&host); +#if IS_ENABLED(CONFIG_UML_X86) +# if !IS_ENABLED(CONFIG_64BIT) + if (!strcmp(host.machine, "x86_64")) { + strcpy(machine_out, "i686"); + return; + } +# else + if (!strcmp(host.machine, "i686")) { + strcpy(machine_out, "x86_64"); + return; + } +# endif +#endif + strcpy(machine_out, host.machine); +} + +void setup_hostinfo(char *buf, int len) +{ + struct utsname host; + + uname(&host); + snprintf(buf, len, "%s %s %s %s %s", host.sysname, host.nodename, + host.release, host.version, host.machine); +} + +/* + * We cannot use glibc's abort(). It makes use of tgkill() which + * has no effect within UML's kernel threads. + * After that glibc would execute an invalid instruction to kill + * the calling process and UML crashes with SIGSEGV. + */ +static inline void __attribute__ ((noreturn)) uml_abort(void) +{ + sigset_t sig; + + fflush(NULL); + + if (!sigemptyset(&sig) && !sigaddset(&sig, SIGABRT)) + sigprocmask(SIG_UNBLOCK, &sig, 0); + + for (;;) + if (kill(getpid(), SIGABRT) < 0) + exit(127); +} + +ssize_t os_getrandom(void *buf, size_t len, unsigned int flags) +{ + return getrandom(buf, len, flags); +} + +/* + * UML helper threads must not handle SIGWINCH/INT/TERM + */ +void os_fix_helper_signals(void) +{ + signal(SIGWINCH, SIG_IGN); + signal(SIGINT, SIG_DFL); + signal(SIGTERM, SIG_DFL); +} + +void os_dump_core(void) +{ + int pid; + + signal(SIGSEGV, SIG_DFL); + + /* + * We are about to SIGTERM this entire process group to ensure that + * nothing is around to run after the kernel exits. The + * kernel wants to abort, not die through SIGTERM, so we + * ignore it here. + */ + + signal(SIGTERM, SIG_IGN); + kill(0, SIGTERM); + /* + * Most of the other processes associated with this UML are + * likely sTopped, so give them a SIGCONT so they see the + * SIGTERM. + */ + kill(0, SIGCONT); + + /* + * Now, having sent signals to everyone but us, make sure they + * die by ptrace. Processes can survive what's been done to + * them so far - the mechanism I understand is receiving a + * SIGSEGV and segfaulting immediately upon return. There is + * always a SIGSEGV pending, and (I'm guessing) signals are + * processed in numeric order so the SIGTERM (signal 15 vs + * SIGSEGV being signal 11) is never handled. + * + * Run a waitpid loop until we get some kind of error. + * Hopefully, it's ECHILD, but there's not a lot we can do if + * it's something else. Tell os_kill_ptraced_process not to + * wait for the child to report its death because there's + * nothing reasonable to do if that fails. + */ + + while ((pid = waitpid(-1, NULL, WNOHANG | __WALL)) > 0) + os_kill_ptraced_process(pid, 0); + + uml_abort(); +} + +void um_early_printk(const char *s, unsigned int n) +{ + printf("%.*s", n, s); +} + +static int quiet_info; + +static int __init quiet_cmd_param(char *str, int *add) +{ + quiet_info = 1; + return 0; +} + +__uml_setup("quiet", quiet_cmd_param, +"quiet\n" +" Turns off information messages during boot.\n\n"); + +/* + * The os_info/os_warn functions will be called by helper threads. These + * have a very limited stack size and using the libc formatting functions + * may overflow the stack. + * So pull in the kernel vscnprintf and use that instead with a fixed + * on-stack buffer. + */ +int vscnprintf(char *buf, size_t size, const char *fmt, va_list args); + +void os_info(const char *fmt, ...) +{ + char buf[256]; + va_list list; + int len; + + if (quiet_info) + return; + + va_start(list, fmt); + len = vscnprintf(buf, sizeof(buf), fmt, list); + fwrite(buf, len, 1, stderr); + va_end(list); +} + +void os_warn(const char *fmt, ...) +{ + char buf[256]; + va_list list; + int len; + + va_start(list, fmt); + len = vscnprintf(buf, sizeof(buf), fmt, list); + fwrite(buf, len, 1, stderr); + va_end(list); +} -- cgit v1.3.1