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, 53 insertions, 0 deletions

diff --git a/drivers/siox/siox.h b/drivers/siox/siox.h
new file mode 100644
index 000000000..513f2c831
--- /dev/null
+++ b/drivers/siox/siox.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2015-2017 Pengutronix, Uwe Kleine-König <kernel@pengutronix.de>
+ */
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/siox.h>
+
+#define to_siox_master(_dev)	container_of((_dev), struct siox_master, dev)
+struct siox_master {
+	/* these fields should be initialized by the driver */
+	int busno;
+	int (*pushpull)(struct siox_master *smaster,
+			size_t setbuf_len, const u8 setbuf[],
+			size_t getbuf_len, u8 getbuf[]);
+
+	/* might be initialized by the driver, if 0 it is set to HZ / 40 */
+	unsigned long poll_interval; /* in jiffies */
+
+	/* framework private stuff */
+	struct mutex lock;
+	bool active;
+	struct module *owner;
+	struct device dev;
+	unsigned int num_devices;
+	struct list_head devices;
+
+	size_t setbuf_len, getbuf_len;
+	size_t buf_len;
+	u8 *buf;
+	u8 status;
+
+	unsigned long last_poll;
+	struct task_struct *poll_thread;
+};
+
+static inline void *siox_master_get_devdata(struct siox_master *smaster)
+{
+	return dev_get_drvdata(&smaster->dev);
+}
+
+struct siox_master *siox_master_alloc(struct device *dev, size_t size);
+static inline void siox_master_put(struct siox_master *smaster)
+{
+	put_device(&smaster->dev);
+}
+
+struct siox_master *devm_siox_master_alloc(struct device *dev, size_t size);
+
+int siox_master_register(struct siox_master *smaster);
+void siox_master_unregister(struct siox_master *smaster);
+
+int devm_siox_master_register(struct device *dev, struct siox_master *smaster);