From a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255 Mon Sep 17 00:00:00 2001 From: Jinke Han Date: Tue, 8 Sep 2026 15:37:42 +0800 Subject: x86/kprobes: Fix crash when probing CS CALL instructions When using eBPF to probe CS CALL instructions within a function, a crash can be triggered. The eBPF tool probes offset 257 of the __hrtimer_run_queues() function: <__hrtimer_run_queues+249>: nopl 0x0(%rax,%rax,1) <__hrtimer_run_queues+254>: mov %r14,%rdi <__hrtimer_run_queues+257>: cs call <__x86_indirect_thunk_r12> <__hrtimer_run_queues+263>: mov %eax,%r12d <__hrtimer_run_queues+266>: xchg %ax,%ax <__hrtimer_run_queues+268>: mov %r13,%rdi Which triggers this crash: BUG: unable to handle page fault for address: 00000000000f41c9 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP NOPTI CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P RIP: 0010:__hrtimer_run_queues+0x106/0x230 Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is at the 6th byte of the above CS CALL instruction. Since the CS CALL instruction occupies 6 bytes, the exception occurred in the middle of that call instruction. The root cause is that when using eBPF tools to probe in the middle of a function, a kprobe with INT3 is used as the underlying implementation. During single-step emulation of the original CALL instruction, int3_emulate_call() assumes that the probed CALL instruction is 5 bytes long. However, the actual CS-prefixed CALL instruction occupies 6 bytes, so it constructs an incorrect exception return address. When the CPU returns from the kprobe handler, the next instruction to be executed is at the address of the last byte of that CS CALL instruction. Coincidentally, starting from that address, the CPU fetches and decodes a completely different instruction, which ultimately triggers a kernel crash. Fix the issue by using the actual instruction length obtained from the instruction decoder when constructing the exception return address, rather than relying on the hardcoded CALL_INSN_SIZE macro. [ mingo: Refined the changelog ] Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step") Suggested-by: Masami Hiramatsu (Google) Signed-off-by: Jinke Han Signed-off-by: Ingo Molnar Reviewed-by: Masami Hiramatsu (Google) Acked-by: Yafang Shao Acked-by: Borislav Petkov Cc: Peter Zijlstra Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000 --- fs/binfmt_script.c | 159 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 159 insertions(+) create mode 100644 fs/binfmt_script.c (limited to 'fs/binfmt_script.c') diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c new file mode 100644 index 000000000..637daf6e4 --- /dev/null +++ b/fs/binfmt_script.c @@ -0,0 +1,159 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/fs/binfmt_script.c + * + * Copyright (C) 1996 Martin von Löwis + * original #!-checking implemented by tytso. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +static inline bool spacetab(char c) { return c == ' ' || c == '\t'; } +static inline const char *next_non_spacetab(const char *first, const char *last) +{ + for (; first <= last; first++) + if (!spacetab(*first)) + return first; + return NULL; +} +static inline const char *next_terminator(const char *first, const char *last) +{ + for (; first <= last; first++) + if (spacetab(*first) || !*first) + return first; + return NULL; +} + +static int load_script(struct linux_binprm *bprm) +{ + const char *i_name, *i_sep, *i_arg, *i_end, *buf_end; + struct file *file; + int retval; + + /* Not ours to exec if we don't start with "#!". */ + if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!')) + return -ENOEXEC; + + /* + * This section handles parsing the #! line into separate + * interpreter path and argument strings. We must be careful + * because bprm->buf is not yet guaranteed to be NUL-terminated + * (though the buffer will have trailing NUL padding when the + * file size was smaller than the buffer size). + * + * We do not want to exec a truncated interpreter path, so either + * we find a newline (which indicates nothing is truncated), or + * we find a space/tab/NUL after the interpreter path (which + * itself may be preceded by spaces/tabs). Truncating the + * arguments is fine: the interpreter can re-read the script to + * parse them on its own. + */ + buf_end = bprm->buf + sizeof(bprm->buf) - 1; + i_end = strnchr(bprm->buf, sizeof(bprm->buf), '\n'); + if (!i_end) { + i_end = next_non_spacetab(bprm->buf + 2, buf_end); + if (!i_end) + return -ENOEXEC; /* Entire buf is spaces/tabs */ + /* + * If there is no later space/tab/NUL we must assume the + * interpreter path is truncated. + */ + if (!next_terminator(i_end, buf_end)) + return -ENOEXEC; + i_end = buf_end; + } + /* Trim any trailing spaces/tabs from i_end */ + while (spacetab(i_end[-1])) + i_end--; + + /* Skip over leading spaces/tabs */ + i_name = next_non_spacetab(bprm->buf+2, i_end); + if (!i_name || (i_name == i_end)) + return -ENOEXEC; /* No interpreter name found */ + + /* Is there an optional argument? */ + i_arg = NULL; + i_sep = next_terminator(i_name, i_end); + if (i_sep && (*i_sep != '\0')) + i_arg = next_non_spacetab(i_sep, i_end); + + /* + * If the script filename will be inaccessible after exec, typically + * because it is a "/dev/fd//.." path against an O_CLOEXEC fd, give + * up now (on the assumption that the interpreter will want to load + * this file). + */ + if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) + return -ENOENT; + + /* + * OK, we've parsed out the interpreter name and + * (optional) argument. + * Splice in (1) the interpreter's name for argv[0] + * (2) (optional) argument to interpreter + * (3) filename of shell script (replace argv[0]) + * + * This is done in reverse order, because of how the + * user environment and arguments are stored. + */ + retval = remove_arg_zero(bprm); + if (retval) + return retval; + retval = copy_string_kernel(bprm->interp, bprm); + if (retval < 0) + return retval; + bprm->argc++; + *((char *)i_end) = '\0'; + if (i_arg) { + *((char *)i_sep) = '\0'; + retval = copy_string_kernel(i_arg, bprm); + if (retval < 0) + return retval; + bprm->argc++; + } + retval = copy_string_kernel(i_name, bprm); + if (retval) + return retval; + bprm->argc++; + retval = bprm_change_interp(i_name, bprm); + if (retval < 0) + return retval; + + /* + * OK, now restart the process with the interpreter's dentry. + */ + file = open_exec(i_name); + if (IS_ERR(file)) + return PTR_ERR(file); + + bprm->interpreter = file; + return 0; +} + +static struct linux_binfmt script_format = { + .module = THIS_MODULE, + .load_binary = load_script, +}; + +static int __init init_script_binfmt(void) +{ + register_binfmt(&script_format); + return 0; +} + +static void __exit exit_script_binfmt(void) +{ + unregister_binfmt(&script_format); +} + +core_initcall(init_script_binfmt); +module_exit(exit_script_binfmt); +MODULE_DESCRIPTION("Kernel support for scripts starting with #!"); +MODULE_LICENSE("GPL"); -- cgit v1.3.1