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, 89 insertions, 0 deletions

diff --git a/drivers/ps3/vuart.h b/drivers/ps3/vuart.h
new file mode 100644
index 000000000..64d34efef
--- /dev/null
+++ b/drivers/ps3/vuart.h
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  PS3 virtual uart
+ *
+ *  Copyright (C) 2006 Sony Computer Entertainment Inc.
+ *  Copyright 2006 Sony Corp.
+ */
+
+#if !defined(_PS3_VUART_H)
+#define _PS3_VUART_H
+
+#include <asm/ps3.h>
+
+struct ps3_vuart_stats {
+	unsigned long bytes_written;
+	unsigned long bytes_read;
+	unsigned long tx_interrupts;
+	unsigned long rx_interrupts;
+	unsigned long disconnect_interrupts;
+};
+
+struct ps3_vuart_work {
+	struct work_struct work;
+	unsigned long trigger;
+	struct ps3_system_bus_device *dev; /* to convert work to device */
+};
+
+/**
+ * struct ps3_vuart_port_driver - a driver for a device on a vuart port
+ */
+
+struct ps3_vuart_port_driver {
+	struct ps3_system_bus_driver core;
+	int (*probe)(struct ps3_system_bus_device *);
+	int (*remove)(struct ps3_system_bus_device *);
+	void (*shutdown)(struct ps3_system_bus_device *);
+	void (*work)(struct ps3_system_bus_device *);
+	/* int (*tx_event)(struct ps3_system_bus_device *dev); */
+	/* int (*rx_event)(struct ps3_system_bus_device *dev); */
+	/* int (*disconnect_event)(struct ps3_system_bus_device *dev); */
+	/* int (*suspend)(struct ps3_system_bus_device *, pm_message_t); */
+	/* int (*resume)(struct ps3_system_bus_device *); */
+};
+
+int ps3_vuart_port_driver_register(struct ps3_vuart_port_driver *drv);
+void ps3_vuart_port_driver_unregister(struct ps3_vuart_port_driver *drv);
+
+static inline struct ps3_vuart_port_driver *
+	ps3_system_bus_dev_to_vuart_drv(struct ps3_system_bus_device *_dev)
+{
+	struct ps3_system_bus_driver *sbd =
+		ps3_system_bus_dev_to_system_bus_drv(_dev);
+	BUG_ON(!sbd);
+	return container_of(sbd, struct ps3_vuart_port_driver, core);
+}
+static inline struct ps3_system_bus_device *ps3_vuart_work_to_system_bus_dev(
+	struct work_struct *_work)
+{
+	struct ps3_vuart_work *vw = container_of(_work, struct ps3_vuart_work,
+		work);
+	return vw->dev;
+}
+
+int ps3_vuart_write(struct ps3_system_bus_device *dev, const void *buf,
+	unsigned int bytes);
+int ps3_vuart_read(struct ps3_system_bus_device *dev, void *buf,
+	unsigned int bytes);
+int ps3_vuart_read_async(struct ps3_system_bus_device *dev, unsigned int bytes);
+void ps3_vuart_cancel_async(struct ps3_system_bus_device *dev);
+void ps3_vuart_clear_rx_bytes(struct ps3_system_bus_device *dev,
+	unsigned int bytes);
+
+struct vuart_triggers {
+	unsigned long rx;
+	unsigned long tx;
+};
+
+int ps3_vuart_get_triggers(struct ps3_system_bus_device *dev,
+	struct vuart_triggers *trig);
+int ps3_vuart_set_triggers(struct ps3_system_bus_device *dev, unsigned int tx,
+	unsigned int rx);
+int ps3_vuart_enable_interrupt_tx(struct ps3_system_bus_device *dev);
+int ps3_vuart_disable_interrupt_tx(struct ps3_system_bus_device *dev);
+int ps3_vuart_enable_interrupt_rx(struct ps3_system_bus_device *dev);
+int ps3_vuart_disable_interrupt_rx(struct ps3_system_bus_device *dev);
+int ps3_vuart_enable_interrupt_disconnect(struct ps3_system_bus_device *dev);
+int ps3_vuart_disable_interrupt_disconnect(struct ps3_system_bus_device *dev);
+
+#endif