x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

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) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 218 insertions, 0 deletions

diff --git a/tools/lib/subcmd/exec-cmd.c b/tools/lib/subcmd/exec-cmd.c
new file mode 100644
index 000000000..7739b5217
--- /dev/null
+++ b/tools/lib/subcmd/exec-cmd.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+#include <linux/string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "subcmd-util.h"
+#include "exec-cmd.h"
+#include "subcmd-config.h"
+
+#define MAX_ARGS	32
+#define PATH_MAX	4096
+
+static const char *argv_exec_path;
+static const char *argv0_path;
+
+void exec_cmd_init(const char *exec_name, const char *prefix,
+		   const char *exec_path, const char *exec_path_env)
+{
+	subcmd_config.exec_name		= exec_name;
+	subcmd_config.prefix		= prefix;
+	subcmd_config.exec_path		= exec_path;
+	subcmd_config.exec_path_env	= exec_path_env;
+
+	/* Setup environment variable for invoked shell script. */
+	setenv("PREFIX", prefix, 1);
+}
+
+#define is_dir_sep(c) ((c) == '/')
+
+static int is_absolute_path(const char *path)
+{
+	return path[0] == '/';
+}
+
+static const char *get_pwd_cwd(char *buf, size_t sz)
+{
+	char *pwd;
+	struct stat cwd_stat, pwd_stat;
+	if (getcwd(buf, sz) == NULL)
+		return NULL;
+	pwd = getenv("PWD");
+	if (pwd && strcmp(pwd, buf)) {
+		stat(buf, &cwd_stat);
+		if (!stat(pwd, &pwd_stat) &&
+		    pwd_stat.st_dev == cwd_stat.st_dev &&
+		    pwd_stat.st_ino == cwd_stat.st_ino) {
+			strlcpy(buf, pwd, sz);
+		}
+	}
+	return buf;
+}
+
+static const char *make_nonrelative_path(char *buf, size_t sz, const char *path)
+{
+	if (is_absolute_path(path)) {
+		if (strlcpy(buf, path, sz) >= sz)
+			die("Too long path: %.*s", 60, path);
+	} else {
+		const char *cwd = get_pwd_cwd(buf, sz);
+
+		if (!cwd)
+			die("Cannot determine the current working directory");
+
+		if (strlen(cwd) + strlen(path) + 2 >= sz)
+			die("Too long path: %.*s", 60, path);
+
+		strcat(buf, "/");
+		strcat(buf, path);
+	}
+	return buf;
+}
+
+char *system_path(const char *path)
+{
+	char *buf = NULL;
+
+	if (is_absolute_path(path))
+		return strdup(path);
+
+	astrcatf(&buf, "%s/%s", subcmd_config.prefix, path);
+
+	return buf;
+}
+
+const char *extract_argv0_path(const char *argv0)
+{
+	const char *slash;
+
+	if (!argv0 || !*argv0)
+		return NULL;
+	slash = argv0 + strlen(argv0);
+
+	while (argv0 <= slash && !is_dir_sep(*slash))
+		slash--;
+
+	if (slash >= argv0) {
+		argv0_path = strndup(argv0, slash - argv0);
+		return argv0_path ? slash + 1 : NULL;
+	}
+
+	return argv0;
+}
+
+void set_argv_exec_path(const char *exec_path)
+{
+	argv_exec_path = exec_path;
+	/*
+	 * Propagate this setting to external programs.
+	 */
+	setenv(subcmd_config.exec_path_env, exec_path, 1);
+}
+
+
+/* Returns the highest-priority location to look for subprograms. */
+char *get_argv_exec_path(void)
+{
+	char *env;
+
+	if (argv_exec_path)
+		return strdup(argv_exec_path);
+
+	env = getenv(subcmd_config.exec_path_env);
+	if (env && *env)
+		return strdup(env);
+
+	return system_path(subcmd_config.exec_path);
+}
+
+static void add_path(char **out, const char *path)
+{
+	if (path && *path) {
+		if (is_absolute_path(path))
+			astrcat(out, path);
+		else {
+			char buf[PATH_MAX];
+
+			astrcat(out, make_nonrelative_path(buf, sizeof(buf), path));
+		}
+
+		astrcat(out, ":");
+	}
+}
+
+void setup_path(void)
+{
+	const char *old_path = getenv("PATH");
+	char *new_path = NULL;
+	char *tmp = get_argv_exec_path();
+
+	add_path(&new_path, tmp);
+	add_path(&new_path, argv0_path);
+	free(tmp);
+
+	if (old_path)
+		astrcat(&new_path, old_path);
+	else
+		astrcat(&new_path, "/usr/local/bin:/usr/bin:/bin");
+
+	setenv("PATH", new_path, 1);
+
+	free(new_path);
+}
+
+static const char **prepare_exec_cmd(const char **argv)
+{
+	int argc;
+	const char **nargv;
+
+	for (argc = 0; argv[argc]; argc++)
+		; /* just counting */
+	nargv = malloc(sizeof(*nargv) * (argc + 2));
+
+	nargv[0] = subcmd_config.exec_name;
+	for (argc = 0; argv[argc]; argc++)
+		nargv[argc + 1] = argv[argc];
+	nargv[argc + 1] = NULL;
+	return nargv;
+}
+
+int execv_cmd(const char **argv) {
+	const char **nargv = prepare_exec_cmd(argv);
+
+	/* execvp() can only ever return if it fails */
+	execvp(subcmd_config.exec_name, (char **)nargv);
+
+	free(nargv);
+	return -1;
+}
+
+
+int execl_cmd(const char *cmd,...)
+{
+	int argc;
+	const char *argv[MAX_ARGS + 1];
+	const char *arg;
+	va_list param;
+
+	va_start(param, cmd);
+	argv[0] = cmd;
+	argc = 1;
+	while (argc < MAX_ARGS) {
+		arg = argv[argc++] = va_arg(param, char *);
+		if (!arg)
+			break;
+	}
+	va_end(param);
+	if (MAX_ARGS <= argc) {
+		fprintf(stderr, " Error: too many args to run %s\n", cmd);
+		return -1;
+	}
+
+	argv[argc] = NULL;
+	return execv_cmd(argv);
+}