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, 163 insertions, 0 deletions

diff --git a/drivers/input/input-compat.c b/drivers/input/input-compat.c
new file mode 100644
index 000000000..a5043193e
--- /dev/null
+++ b/drivers/input/input-compat.c
@@ -0,0 +1,163 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * 32bit compatibility wrappers for the input subsystem.
+ *
+ * Very heavily based on evdev.c - Copyright (c) 1999-2002 Vojtech Pavlik
+ */
+
+#include <linux/export.h>
+#include <linux/sprintf.h>
+#include <linux/uaccess.h>
+#include "input-compat.h"
+
+#ifdef CONFIG_COMPAT
+
+int input_event_from_user(const char __user *buffer,
+			  struct input_event *event)
+{
+	if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
+		struct input_event_compat compat_event;
+
+		if (copy_from_user(&compat_event, buffer,
+				   sizeof(struct input_event_compat)))
+			return -EFAULT;
+
+		event->input_event_sec = compat_event.sec;
+		event->input_event_usec = compat_event.usec;
+		event->type = compat_event.type;
+		event->code = compat_event.code;
+		event->value = compat_event.value;
+
+	} else {
+		if (copy_from_user(event, buffer, sizeof(struct input_event)))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+int input_event_to_user(char __user *buffer,
+			const struct input_event *event)
+{
+	if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
+		struct input_event_compat compat_event;
+
+		compat_event.sec = event->input_event_sec;
+		compat_event.usec = event->input_event_usec;
+		compat_event.type = event->type;
+		compat_event.code = event->code;
+		compat_event.value = event->value;
+
+		if (copy_to_user(buffer, &compat_event,
+				 sizeof(struct input_event_compat)))
+			return -EFAULT;
+
+	} else {
+		if (copy_to_user(buffer, event, sizeof(struct input_event)))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+int input_ff_effect_from_user(const char __user *buffer, size_t size,
+			      struct ff_effect *effect)
+{
+	if (in_compat_syscall()) {
+		struct ff_effect_compat *compat_effect;
+
+		if (size != sizeof(struct ff_effect_compat))
+			return -EINVAL;
+
+		/*
+		 * It so happens that the pointer which needs to be changed
+		 * is the last field in the structure, so we can retrieve the
+		 * whole thing and replace just the pointer.
+		 */
+		compat_effect = (struct ff_effect_compat *)effect;
+
+		if (copy_from_user(compat_effect, buffer,
+				   sizeof(struct ff_effect_compat)))
+			return -EFAULT;
+
+		if (compat_effect->type == FF_PERIODIC &&
+		    compat_effect->u.periodic.waveform == FF_CUSTOM)
+			effect->u.periodic.custom_data =
+				compat_ptr(compat_effect->u.periodic.custom_data);
+	} else {
+		if (size != sizeof(struct ff_effect))
+			return -EINVAL;
+
+		if (copy_from_user(effect, buffer, sizeof(struct ff_effect)))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+int input_bits_to_string(char *buf, int buf_size, unsigned long bits,
+			 bool skip_empty)
+{
+	int len = 0;
+
+	if (in_compat_syscall()) {
+		u32 dword = bits >> 32;
+		if (dword || !skip_empty)
+			len += snprintf(buf, buf_size, "%x ", dword);
+
+		dword = bits & 0xffffffffUL;
+		if (dword || !skip_empty || len)
+			len += snprintf(buf + len, max(buf_size - len, 0),
+					"%x", dword);
+	} else {
+		if (bits || !skip_empty)
+			len += snprintf(buf, buf_size, "%lx", bits);
+	}
+
+	return len;
+}
+
+#else
+
+int input_event_from_user(const char __user *buffer,
+			 struct input_event *event)
+{
+	if (copy_from_user(event, buffer, sizeof(struct input_event)))
+		return -EFAULT;
+
+	return 0;
+}
+
+int input_event_to_user(char __user *buffer,
+			const struct input_event *event)
+{
+	if (copy_to_user(buffer, event, sizeof(struct input_event)))
+		return -EFAULT;
+
+	return 0;
+}
+
+int input_ff_effect_from_user(const char __user *buffer, size_t size,
+			      struct ff_effect *effect)
+{
+	if (size != sizeof(struct ff_effect))
+		return -EINVAL;
+
+	if (copy_from_user(effect, buffer, sizeof(struct ff_effect)))
+		return -EFAULT;
+
+	return 0;
+}
+
+int input_bits_to_string(char *buf, int buf_size, unsigned long bits,
+			 bool skip_empty)
+{
+	return bits || !skip_empty ?
+		snprintf(buf, buf_size, "%lx", bits) : 0;
+}
+
+#endif /* CONFIG_COMPAT */
+
+EXPORT_SYMBOL_GPL(input_event_from_user);
+EXPORT_SYMBOL_GPL(input_event_to_user);
+EXPORT_SYMBOL_GPL(input_ff_effect_from_user);