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 --- samples/vfs/test-statx.c | 271 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 271 insertions(+) create mode 100644 samples/vfs/test-statx.c (limited to 'samples/vfs/test-statx.c') diff --git a/samples/vfs/test-statx.c b/samples/vfs/test-statx.c new file mode 100644 index 000000000..424a6fa15 --- /dev/null +++ b/samples/vfs/test-statx.c @@ -0,0 +1,271 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Test the statx() system call. + * + * Note that the output of this program is intended to look like the output of + * /bin/stat where possible. + * + * Copyright (C) 2015 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define _GNU_SOURCE +#define _ATFILE_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include + +// Work around glibc header silliness +#undef AT_RENAME_NOREPLACE +#undef AT_RENAME_EXCHANGE +#undef AT_RENAME_WHITEOUT + +#include +#include +#define statx foo +#define statx_timestamp foo_timestamp +struct statx; +struct statx_timestamp; +#include +#undef statx +#undef statx_timestamp + +#define AT_STATX_SYNC_TYPE 0x6000 +#define AT_STATX_SYNC_AS_STAT 0x0000 +#define AT_STATX_FORCE_SYNC 0x2000 +#define AT_STATX_DONT_SYNC 0x4000 + +#ifndef __NR_statx +#define __NR_statx -1 +#endif + +static __attribute__((unused)) +ssize_t statx(int dfd, const char *filename, unsigned flags, + unsigned int mask, struct statx *buffer) +{ + return syscall(__NR_statx, dfd, filename, flags, mask, buffer); +} + +static void print_time(const char *field, struct statx_timestamp *ts) +{ + struct tm tm; + time_t tim; + char buffer[100]; + int len; + + tim = ts->tv_sec; + if (!localtime_r(&tim, &tm)) { + perror("localtime_r"); + exit(1); + } + len = strftime(buffer, 100, "%F %T", &tm); + if (len == 0) { + perror("strftime"); + exit(1); + } + printf("%s", field); + fwrite(buffer, 1, len, stdout); + printf(".%09u", ts->tv_nsec); + len = strftime(buffer, 100, "%z", &tm); + if (len == 0) { + perror("strftime2"); + exit(1); + } + fwrite(buffer, 1, len, stdout); + printf("\n"); +} + +static void dump_statx(struct statx *stx) +{ + char buffer[256], ft = '?'; + + printf("results=%x\n", stx->stx_mask); + + printf(" "); + if (stx->stx_mask & STATX_SIZE) + printf(" Size: %-15llu", (unsigned long long)stx->stx_size); + if (stx->stx_mask & STATX_BLOCKS) + printf(" Blocks: %-10llu", (unsigned long long)stx->stx_blocks); + printf(" IO Block: %-6llu", (unsigned long long)stx->stx_blksize); + if (stx->stx_mask & STATX_TYPE) { + switch (stx->stx_mode & S_IFMT) { + case S_IFIFO: printf(" FIFO\n"); ft = 'p'; break; + case S_IFCHR: printf(" character special file\n"); ft = 'c'; break; + case S_IFDIR: printf(" directory\n"); ft = 'd'; break; + case S_IFBLK: printf(" block special file\n"); ft = 'b'; break; + case S_IFREG: printf(" regular file\n"); ft = '-'; break; + case S_IFLNK: printf(" symbolic link\n"); ft = 'l'; break; + case S_IFSOCK: printf(" socket\n"); ft = 's'; break; + default: + printf(" unknown type (%o)\n", stx->stx_mode & S_IFMT); + break; + } + } else { + printf(" no type\n"); + } + + sprintf(buffer, "%02x:%02x", stx->stx_dev_major, stx->stx_dev_minor); + printf("Device: %-15s", buffer); + if (stx->stx_mask & STATX_INO) + printf(" Inode: %-11llu", (unsigned long long) stx->stx_ino); + if (stx->stx_mask & STATX_NLINK) + printf(" Links: %-5u", stx->stx_nlink); + if (stx->stx_mask & STATX_TYPE) { + switch (stx->stx_mode & S_IFMT) { + case S_IFBLK: + case S_IFCHR: + printf(" Device type: %u,%u", + stx->stx_rdev_major, stx->stx_rdev_minor); + break; + } + } + printf("\n"); + + if (stx->stx_mask & STATX_MODE) + printf("Access: (%04o/%c%c%c%c%c%c%c%c%c%c) ", + stx->stx_mode & 07777, + ft, + stx->stx_mode & S_IRUSR ? 'r' : '-', + stx->stx_mode & S_IWUSR ? 'w' : '-', + stx->stx_mode & S_IXUSR ? 'x' : '-', + stx->stx_mode & S_IRGRP ? 'r' : '-', + stx->stx_mode & S_IWGRP ? 'w' : '-', + stx->stx_mode & S_IXGRP ? 'x' : '-', + stx->stx_mode & S_IROTH ? 'r' : '-', + stx->stx_mode & S_IWOTH ? 'w' : '-', + stx->stx_mode & S_IXOTH ? 'x' : '-'); + if (stx->stx_mask & STATX_UID) + printf("Uid: %5d ", stx->stx_uid); + if (stx->stx_mask & STATX_GID) + printf("Gid: %5d\n", stx->stx_gid); + + if (stx->stx_mask & STATX_ATIME) + print_time("Access: ", &stx->stx_atime); + if (stx->stx_mask & STATX_MTIME) + print_time("Modify: ", &stx->stx_mtime); + if (stx->stx_mask & STATX_CTIME) + print_time("Change: ", &stx->stx_ctime); + if (stx->stx_mask & STATX_BTIME) + print_time(" Birth: ", &stx->stx_btime); + + if (stx->stx_attributes_mask) { + unsigned char bits, mbits; + int loop, byte; + + static char attr_representation[64 + 1] = + /* STATX_ATTR_ flags: */ + "????????" /* 63-56 */ + "????????" /* 55-48 */ + "????????" /* 47-40 */ + "????????" /* 39-32 */ + "????????" /* 31-24 0x00000000-ff000000 */ + "????????" /* 23-16 0x00000000-00ff0000 */ + "???me???" /* 15- 8 0x00000000-0000ff00 */ + "?dai?c??" /* 7- 0 0x00000000-000000ff */ + ; + + printf("Attributes: %016llx (", + (unsigned long long)stx->stx_attributes); + for (byte = 64 - 8; byte >= 0; byte -= 8) { + bits = stx->stx_attributes >> byte; + mbits = stx->stx_attributes_mask >> byte; + for (loop = 7; loop >= 0; loop--) { + int bit = byte + loop; + + if (!(mbits & 0x80)) + putchar('.'); /* Not supported */ + else if (bits & 0x80) + putchar(attr_representation[63 - bit]); + else + putchar('-'); /* Not set */ + bits <<= 1; + mbits <<= 1; + } + if (byte) + putchar(' '); + } + printf(")\n"); + } +} + +static void dump_hex(unsigned long long *data, int from, int to) +{ + unsigned offset, print_offset = 1, col = 0; + + from /= 8; + to = (to + 7) / 8; + + for (offset = from; offset < to; offset++) { + if (print_offset) { + printf("%04x: ", offset * 8); + print_offset = 0; + } + printf("%016llx", data[offset]); + col++; + if ((col & 3) == 0) { + printf("\n"); + print_offset = 1; + } else { + printf(" "); + } + } + + if (!print_offset) + printf("\n"); +} + +int main(int argc, char **argv) +{ + struct statx stx; + int ret, raw = 0, atflag = AT_SYMLINK_NOFOLLOW; + + unsigned int mask = STATX_BASIC_STATS | STATX_BTIME; + + for (argv++; *argv; argv++) { + if (strcmp(*argv, "-F") == 0) { + atflag &= ~AT_STATX_SYNC_TYPE; + atflag |= AT_STATX_FORCE_SYNC; + continue; + } + if (strcmp(*argv, "-D") == 0) { + atflag &= ~AT_STATX_SYNC_TYPE; + atflag |= AT_STATX_DONT_SYNC; + continue; + } + if (strcmp(*argv, "-L") == 0) { + atflag &= ~AT_SYMLINK_NOFOLLOW; + continue; + } + if (strcmp(*argv, "-O") == 0) { + mask &= ~STATX_BASIC_STATS; + continue; + } + if (strcmp(*argv, "-A") == 0) { + atflag |= AT_NO_AUTOMOUNT; + continue; + } + if (strcmp(*argv, "-R") == 0) { + raw = 1; + continue; + } + + memset(&stx, 0xbf, sizeof(stx)); + ret = statx(AT_FDCWD, *argv, atflag, mask, &stx); + printf("statx(%s) = %d\n", *argv, ret); + if (ret < 0) { + perror(*argv); + exit(1); + } + + if (raw) + dump_hex((unsigned long long *)&stx, 0, sizeof(stx)); + + dump_statx(&stx); + } + return 0; +} -- cgit v1.3.1