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, 153 insertions, 0 deletions

diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c
new file mode 100644
index 000000000..5557b5393
--- /dev/null
+++ b/samples/bpf/offwaketime_user.c
@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2016 Facebook
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <linux/perf_event.h>
+#include <errno.h>
+#include <stdbool.h>
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+#include "trace_helpers.h"
+
+#define PRINT_RAW_ADDR 0
+
+/* counts, stackmap */
+static int map_fd[2];
+
+static void print_ksym(__u64 addr)
+{
+	struct ksym *sym;
+
+	if (!addr)
+		return;
+	sym = ksym_search(addr);
+	if (!sym) {
+		printf("ksym not found. Is kallsyms loaded?\n");
+		return;
+	}
+
+	if (PRINT_RAW_ADDR)
+		printf("%s/%llx;", sym->name, addr);
+	else
+		printf("%s;", sym->name);
+}
+
+#define TASK_COMM_LEN 16
+
+struct key_t {
+	char waker[TASK_COMM_LEN];
+	char target[TASK_COMM_LEN];
+	__u32 wret;
+	__u32 tret;
+};
+
+static void print_stack(struct key_t *key, __u64 count)
+{
+	__u64 ip[PERF_MAX_STACK_DEPTH] = {};
+	static bool warned;
+	int i;
+
+	printf("%s;", key->target);
+	if (bpf_map_lookup_elem(map_fd[1], &key->tret, ip) != 0) {
+		printf("---;");
+	} else {
+		for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--)
+			print_ksym(ip[i]);
+	}
+	printf("-;");
+	if (bpf_map_lookup_elem(map_fd[1], &key->wret, ip) != 0) {
+		printf("---;");
+	} else {
+		for (i = 0; i < PERF_MAX_STACK_DEPTH; i++)
+			print_ksym(ip[i]);
+	}
+	printf(";%s %lld\n", key->waker, count);
+
+	if ((key->tret == -EEXIST || key->wret == -EEXIST) && !warned) {
+		printf("stackmap collisions seen. Consider increasing size\n");
+		warned = true;
+	} else if (((int)(key->tret) < 0 || (int)(key->wret) < 0)) {
+		printf("err stackid %d %d\n", key->tret, key->wret);
+	}
+}
+
+static void print_stacks(int fd)
+{
+	struct key_t key = {}, next_key;
+	__u64 value;
+
+	while (bpf_map_get_next_key(fd, &key, &next_key) == 0) {
+		bpf_map_lookup_elem(fd, &next_key, &value);
+		print_stack(&next_key, value);
+		key = next_key;
+	}
+}
+
+static void int_exit(int sig)
+{
+	print_stacks(map_fd[0]);
+	exit(0);
+}
+
+int main(int argc, char **argv)
+{
+	struct bpf_object *obj = NULL;
+	struct bpf_link *links[2];
+	struct bpf_program *prog;
+	int delay = 1, i = 0;
+	char filename[256];
+
+	if (load_kallsyms()) {
+		printf("failed to process /proc/kallsyms\n");
+		return 2;
+	}
+
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		obj = NULL;
+		goto cleanup;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	map_fd[0] = bpf_object__find_map_fd_by_name(obj, "counts");
+	map_fd[1] = bpf_object__find_map_fd_by_name(obj, "stackmap");
+	if (map_fd[0] < 0 || map_fd[1] < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	signal(SIGINT, int_exit);
+	signal(SIGTERM, int_exit);
+
+	bpf_object__for_each_program(prog, obj) {
+		links[i] = bpf_program__attach(prog);
+		if (libbpf_get_error(links[i])) {
+			fprintf(stderr, "ERROR: bpf_program__attach failed\n");
+			links[i] = NULL;
+			goto cleanup;
+		}
+		i++;
+	}
+
+	if (argc > 1)
+		delay = atoi(argv[1]);
+	sleep(delay);
+	print_stacks(map_fd[0]);
+
+cleanup:
+	for (i--; i >= 0; i--)
+		bpf_link__destroy(links[i]);
+
+	bpf_object__close(obj);
+	return 0;
+}