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, 110 insertions, 0 deletions

diff --git a/drivers/tty/ttynull.c b/drivers/tty/ttynull.c
new file mode 100644
index 000000000..6b2f7208b
--- /dev/null
+++ b/drivers/tty/ttynull.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Axis Communications AB
+ *
+ * Based on ttyprintk.c:
+ *  Copyright (C) 2010 Samo Pogacnik
+ */
+
+#include <linux/console.h>
+#include <linux/module.h>
+#include <linux/tty.h>
+
+static const struct tty_port_operations ttynull_port_ops;
+static struct tty_driver *ttynull_driver;
+static struct tty_port ttynull_port;
+
+static int ttynull_open(struct tty_struct *tty, struct file *filp)
+{
+	return tty_port_open(&ttynull_port, tty, filp);
+}
+
+static void ttynull_close(struct tty_struct *tty, struct file *filp)
+{
+	tty_port_close(&ttynull_port, tty, filp);
+}
+
+static void ttynull_hangup(struct tty_struct *tty)
+{
+	tty_port_hangup(&ttynull_port);
+}
+
+static ssize_t ttynull_write(struct tty_struct *tty, const u8 *buf,
+			     size_t count)
+{
+	return count;
+}
+
+static unsigned int ttynull_write_room(struct tty_struct *tty)
+{
+	return 65536;
+}
+
+static const struct tty_operations ttynull_ops = {
+	.open = ttynull_open,
+	.close = ttynull_close,
+	.hangup = ttynull_hangup,
+	.write = ttynull_write,
+	.write_room = ttynull_write_room,
+};
+
+static struct tty_driver *ttynull_device(struct console *c, int *index)
+{
+	*index = 0;
+	return ttynull_driver;
+}
+
+static struct console ttynull_console = {
+	.name = "ttynull",
+	.device = ttynull_device,
+};
+
+static int __init ttynull_init(void)
+{
+	struct tty_driver *driver;
+	int ret;
+
+	driver = tty_alloc_driver(1,
+		TTY_DRIVER_RESET_TERMIOS |
+		TTY_DRIVER_REAL_RAW |
+		TTY_DRIVER_UNNUMBERED_NODE);
+	if (IS_ERR(driver))
+		return PTR_ERR(driver);
+
+	tty_port_init(&ttynull_port);
+	ttynull_port.ops = &ttynull_port_ops;
+
+	driver->driver_name = "ttynull";
+	driver->name = "ttynull";
+	driver->type = TTY_DRIVER_TYPE_CONSOLE;
+	driver->init_termios = tty_std_termios;
+	driver->init_termios.c_oflag = OPOST | OCRNL | ONOCR | ONLRET;
+	tty_set_operations(driver, &ttynull_ops);
+	tty_port_link_device(&ttynull_port, driver, 0);
+
+	ret = tty_register_driver(driver);
+	if (ret < 0) {
+		tty_driver_kref_put(driver);
+		tty_port_destroy(&ttynull_port);
+		return ret;
+	}
+
+	ttynull_driver = driver;
+	register_console(&ttynull_console);
+
+	return 0;
+}
+
+static void __exit ttynull_exit(void)
+{
+	unregister_console(&ttynull_console);
+	tty_unregister_driver(ttynull_driver);
+	tty_driver_kref_put(ttynull_driver);
+	tty_port_destroy(&ttynull_port);
+}
+
+module_init(ttynull_init);
+module_exit(ttynull_exit);
+
+MODULE_DESCRIPTION("NULL TTY driver");
+MODULE_LICENSE("GPL v2");