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, 121 insertions, 0 deletions

diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c
new file mode 100644
index 000000000..ca08c91f4
--- /dev/null
+++ b/arch/um/drivers/random.c
@@ -0,0 +1,121 @@
+/* Copyright (C) 2005 - 2008 Jeff Dike <jdike@{linux.intel,addtoit}.com> */
+
+/* Much of this ripped from drivers/char/hw_random.c, see there for other
+ * copyright.
+ *
+ * This software may be used and distributed according to the terms
+ * of the GNU General Public License, incorporated herein by reference.
+ */
+#include <linux/sched/signal.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/interrupt.h>
+#include <linux/miscdevice.h>
+#include <linux/hw_random.h>
+#include <linux/delay.h>
+#include <linux/uaccess.h>
+#include <init.h>
+#include <irq_kern.h>
+#include <os.h>
+
+/*
+ * core module information
+ */
+#define RNG_MODULE_NAME "hw_random"
+
+/* Changed at init time, in the non-modular case, and at module load
+ * time, in the module case.  Presumably, the module subsystem
+ * protects against a module being loaded twice at the same time.
+ */
+static int random_fd = -1;
+static struct hwrng hwrng;
+static DECLARE_COMPLETION(have_data);
+
+static int rng_dev_read(struct hwrng *rng, void *buf, size_t max, bool block)
+{
+	int ret;
+
+	for (;;) {
+		ret = os_read_file(random_fd, buf, max);
+		if (block && ret == -EAGAIN) {
+			add_sigio_fd(random_fd);
+
+			ret = wait_for_completion_killable(&have_data);
+
+			ignore_sigio_fd(random_fd);
+			deactivate_fd(random_fd, RANDOM_IRQ);
+
+			if (ret < 0)
+				break;
+		} else {
+			break;
+		}
+	}
+
+	return ret != -EAGAIN ? ret : 0;
+}
+
+static irqreturn_t random_interrupt(int irq, void *data)
+{
+	complete(&have_data);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * rng_init - initialize RNG module
+ */
+static int __init rng_init (void)
+{
+	int err;
+
+	err = os_open_file("/dev/random", of_read(OPENFLAGS()), 0);
+	if (err < 0)
+		goto out;
+
+	random_fd = err;
+	err = um_request_irq(RANDOM_IRQ, random_fd, IRQ_READ, random_interrupt,
+			     0, "random", NULL);
+	if (err < 0)
+		goto err_out_cleanup_hw;
+
+	sigio_broken();
+	hwrng.name = RNG_MODULE_NAME;
+	hwrng.read = rng_dev_read;
+
+	err = hwrng_register(&hwrng);
+	if (err) {
+		pr_err(RNG_MODULE_NAME " registering failed (%d)\n", err);
+		goto err_out_cleanup_hw;
+	}
+out:
+	return err;
+
+err_out_cleanup_hw:
+	os_close_file(random_fd);
+	random_fd = -1;
+	goto out;
+}
+
+/*
+ * rng_cleanup - shutdown RNG module
+ */
+
+static void cleanup(void)
+{
+	free_irq_by_fd(random_fd);
+	os_close_file(random_fd);
+}
+
+static void __exit rng_cleanup(void)
+{
+	hwrng_unregister(&hwrng);
+	os_close_file(random_fd);
+}
+
+module_init (rng_init);
+module_exit (rng_cleanup);
+__uml_exitcall(cleanup);
+
+MODULE_DESCRIPTION("UML Host Random Number Generator (RNG) driver");
+MODULE_LICENSE("GPL");