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, 266 insertions, 0 deletions

diff --git a/scripts/tracepoint-update.c b/scripts/tracepoint-update.c
new file mode 100644
index 000000000..5cf43c0aa
--- /dev/null
+++ b/scripts/tracepoint-update.c
@@ -0,0 +1,266 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <getopt.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <pthread.h>
+
+#include "elf-parse.h"
+
+static Elf_Shdr *check_data_sec;
+static Elf_Shdr *tracepoint_data_sec;
+
+static inline void *get_index(void *start, int entsize, int index)
+{
+	return start + (entsize * index);
+}
+
+static int compare_strings(const void *a, const void *b)
+{
+	const char *av = *(const char **)a;
+	const char *bv = *(const char **)b;
+
+	return strcmp(av, bv);
+}
+
+struct elf_tracepoint {
+	Elf_Ehdr *ehdr;
+	const char **array;
+	int count;
+};
+
+#define REALLOC_SIZE (1 << 10)
+#define REALLOC_MASK (REALLOC_SIZE - 1)
+
+static int add_string(const char *str, const char ***vals, int *count)
+{
+	const char **array = *vals;
+
+	if (!(*count & REALLOC_MASK)) {
+		int size = (*count) + REALLOC_SIZE;
+
+		array = realloc(array, sizeof(char *) * size);
+		if (!array) {
+			fprintf(stderr, "Failed memory allocation\n");
+			free(*vals);
+			*vals = NULL;
+			return -1;
+		}
+		*vals = array;
+	}
+
+	array[(*count)++] = str;
+	return 0;
+}
+
+/**
+ * for_each_shdr_str - iterator that reads strings that are in an ELF section.
+ * @len: "int" to hold the length of the current string
+ * @ehdr: A pointer to the ehdr of the ELF file
+ * @sec: The section that has the strings to iterate on
+ *
+ * This is a for loop that iterates over all the nul terminated strings
+ * that are in a given ELF section. The variable "str" will hold
+ * the current string for each iteration and the passed in @len will
+ * contain the strlen() of that string.
+ */
+#define for_each_shdr_str(len, ehdr, sec)				\
+	for (const char *str = (void *)(ehdr) + shdr_offset(sec),	\
+			*end = str + shdr_size(sec);			\
+	     len = strlen(str), str < end;				\
+	     str += (len) + 1)
+
+
+static void make_trace_array(struct elf_tracepoint *etrace)
+{
+	Elf_Ehdr *ehdr = etrace->ehdr;
+	const char **vals = NULL;
+	int count = 0;
+	int len;
+
+	etrace->array = NULL;
+
+	/*
+	 * The __tracepoint_check section is filled with strings of the
+	 * names of tracepoints (in tracepoint_strings). Create an array
+	 * that points to each string and then sort the array.
+	 */
+	for_each_shdr_str(len, ehdr, check_data_sec) {
+		if (!len)
+			continue;
+		if (add_string(str, &vals, &count) < 0)
+			return;
+	}
+
+	/* If CONFIG_TRACEPOINT_VERIFY_USED is not set, there's nothing to do */
+	if (!count)
+		return;
+
+	qsort(vals, count, sizeof(char *), compare_strings);
+
+	etrace->array = vals;
+	etrace->count = count;
+}
+
+static int find_event(const char *str, void *array, size_t size)
+{
+	return bsearch(&str, array, size, sizeof(char *), compare_strings) != NULL;
+}
+
+static void check_tracepoints(struct elf_tracepoint *etrace, const char *fname)
+{
+	Elf_Ehdr *ehdr = etrace->ehdr;
+	int len;
+
+	if (!etrace->array)
+		return;
+
+	/*
+	 * The __tracepoints_strings section holds all the names of the
+	 * defined tracepoints. If any of them are not in the
+	 * __tracepoint_check_section it means they are not used.
+	 */
+	for_each_shdr_str(len, ehdr, tracepoint_data_sec) {
+		if (!len)
+			continue;
+		if (!find_event(str, etrace->array, etrace->count)) {
+			fprintf(stderr, "warning: tracepoint '%s' is unused", str);
+			if (fname)
+				fprintf(stderr, " in module %s\n", fname);
+			else
+				fprintf(stderr, "\n");
+		}
+	}
+
+	free(etrace->array);
+}
+
+static void *tracepoint_check(struct elf_tracepoint *etrace, const char *fname)
+{
+	make_trace_array(etrace);
+	check_tracepoints(etrace, fname);
+
+	return NULL;
+}
+
+static int process_tracepoints(bool mod, void *addr, const char *fname)
+{
+	struct elf_tracepoint etrace = {0};
+	Elf_Ehdr *ehdr = addr;
+	Elf_Shdr *shdr_start;
+	Elf_Shdr *string_sec;
+	const char *secstrings;
+	unsigned int shnum;
+	unsigned int shstrndx;
+	int shentsize;
+	int idx;
+	int done = 2;
+
+	shdr_start = (Elf_Shdr *)((char *)ehdr + ehdr_shoff(ehdr));
+	shentsize = ehdr_shentsize(ehdr);
+
+	shstrndx = ehdr_shstrndx(ehdr);
+	if (shstrndx == SHN_XINDEX)
+		shstrndx = shdr_link(shdr_start);
+	string_sec = get_index(shdr_start, shentsize, shstrndx);
+	secstrings = (const char *)ehdr + shdr_offset(string_sec);
+
+	shnum = ehdr_shnum(ehdr);
+	if (shnum == SHN_UNDEF)
+		shnum = shdr_size(shdr_start);
+
+	for (int i = 0; done && i < shnum; i++) {
+		Elf_Shdr *shdr = get_index(shdr_start, shentsize, i);
+
+		idx = shdr_name(shdr);
+
+		/* locate the __tracepoint_check in vmlinux */
+		if (!strcmp(secstrings + idx, "__tracepoint_check")) {
+			check_data_sec = shdr;
+			done--;
+		}
+
+		/* locate the __tracepoints_ptrs section in vmlinux */
+		if (!strcmp(secstrings + idx, "__tracepoints_strings")) {
+			tracepoint_data_sec = shdr;
+			done--;
+		}
+	}
+
+	/*
+	 * Modules may not have either section. But if it has one section,
+	 * it should have both of them.
+	 */
+	if (mod && !check_data_sec && !tracepoint_data_sec)
+		return 0;
+
+	if (!check_data_sec) {
+		if (mod) {
+			fprintf(stderr, "warning: Module %s has only unused tracepoints\n", fname);
+			/* Do not fail build */
+			return 0;
+		}
+		fprintf(stderr,	"no __tracepoint_check in file: %s\n", fname);
+		return -1;
+	}
+
+	if (!tracepoint_data_sec) {
+		/* A module may reference only exported tracepoints */
+		if (mod)
+			return 0;
+		fprintf(stderr,	"no __tracepoint_strings in file: %s\n", fname);
+		return -1;
+	}
+
+	if (!mod)
+		fname = NULL;
+
+	etrace.ehdr = ehdr;
+	tracepoint_check(&etrace, fname);
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	int n_error = 0;
+	size_t size = 0;
+	void *addr = NULL;
+	bool mod = false;
+
+	if (argc > 1 && strcmp(argv[1], "--module") == 0) {
+		mod = true;
+		argc--;
+		argv++;
+	}
+
+	if (argc < 2) {
+		if (mod)
+			fprintf(stderr, "usage: tracepoint-update --module module...\n");
+		else
+			fprintf(stderr, "usage: tracepoint-update vmlinux...\n");
+		return 0;
+	}
+
+	/* Process each file in turn, allowing deep failure. */
+	for (int i = 1; i < argc; i++) {
+		addr = elf_map(argv[i], &size, 1 << ET_REL);
+		if (!addr) {
+			++n_error;
+			continue;
+		}
+
+		if (process_tracepoints(mod, addr, argv[i]))
+			++n_error;
+
+		elf_unmap(addr, size);
+	}
+
+	return !!n_error;
+}