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, 143 insertions, 0 deletions

diff --git a/drivers/rapidio/rio-access.c b/drivers/rapidio/rio-access.c
new file mode 100644
index 000000000..f9e10647f
--- /dev/null
+++ b/drivers/rapidio/rio-access.c
@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * RapidIO configuration space access support
+ *
+ * Copyright 2005 MontaVista Software, Inc.
+ * Matt Porter <mporter@kernel.crashing.org>
+ */
+
+#include <linux/rio.h>
+#include <linux/module.h>
+
+#include <linux/rio_drv.h>
+
+/*
+ *  Wrappers for all RIO configuration access functions.  They just check
+ *  alignment and call the low-level functions pointed to by rio_mport->ops.
+ */
+
+#define RIO_8_BAD 0
+#define RIO_16_BAD (offset & 1)
+#define RIO_32_BAD (offset & 3)
+
+/**
+ * RIO_LOP_READ - Generate rio_local_read_config_* functions
+ * @size: Size of configuration space read (8, 16, 32 bits)
+ * @type: C type of value argument
+ * @len: Length of configuration space read (1, 2, 4 bytes)
+ *
+ * Generates rio_local_read_config_* functions used to access
+ * configuration space registers on the local device.
+ */
+#define RIO_LOP_READ(size,type,len) \
+int __rio_local_read_config_##size \
+	(struct rio_mport *mport, u32 offset, type *value)		\
+{									\
+	int res;							\
+	u32 data = 0;							\
+	if (RIO_##size##_BAD) return RIO_BAD_SIZE;			\
+	res = mport->ops->lcread(mport, mport->id, offset, len, &data);	\
+	*value = (type)data;						\
+	return res;							\
+}
+
+/**
+ * RIO_LOP_WRITE - Generate rio_local_write_config_* functions
+ * @size: Size of configuration space write (8, 16, 32 bits)
+ * @type: C type of value argument
+ * @len: Length of configuration space write (1, 2, 4 bytes)
+ *
+ * Generates rio_local_write_config_* functions used to access
+ * configuration space registers on the local device.
+ */
+#define RIO_LOP_WRITE(size,type,len) \
+int __rio_local_write_config_##size \
+	(struct rio_mport *mport, u32 offset, type value)		\
+{									\
+	if (RIO_##size##_BAD) return RIO_BAD_SIZE;			\
+	return mport->ops->lcwrite(mport, mport->id, offset, len, value);\
+}
+
+RIO_LOP_READ(8, u8, 1)
+RIO_LOP_READ(16, u16, 2)
+RIO_LOP_READ(32, u32, 4)
+RIO_LOP_WRITE(8, u8, 1)
+RIO_LOP_WRITE(16, u16, 2)
+RIO_LOP_WRITE(32, u32, 4)
+
+EXPORT_SYMBOL_GPL(__rio_local_read_config_8);
+EXPORT_SYMBOL_GPL(__rio_local_read_config_16);
+EXPORT_SYMBOL_GPL(__rio_local_read_config_32);
+EXPORT_SYMBOL_GPL(__rio_local_write_config_8);
+EXPORT_SYMBOL_GPL(__rio_local_write_config_16);
+EXPORT_SYMBOL_GPL(__rio_local_write_config_32);
+
+/**
+ * RIO_OP_READ - Generate rio_mport_read_config_* functions
+ * @size: Size of configuration space read (8, 16, 32 bits)
+ * @type: C type of value argument
+ * @len: Length of configuration space read (1, 2, 4 bytes)
+ *
+ * Generates rio_mport_read_config_* functions used to access
+ * configuration space registers on the local device.
+ */
+#define RIO_OP_READ(size,type,len) \
+int rio_mport_read_config_##size \
+	(struct rio_mport *mport, u16 destid, u8 hopcount, u32 offset, type *value)	\
+{									\
+	int res;							\
+	u32 data = 0;							\
+	if (RIO_##size##_BAD) return RIO_BAD_SIZE;			\
+	res = mport->ops->cread(mport, mport->id, destid, hopcount, offset, len, &data); \
+	*value = (type)data;						\
+	return res;							\
+}
+
+/**
+ * RIO_OP_WRITE - Generate rio_mport_write_config_* functions
+ * @size: Size of configuration space write (8, 16, 32 bits)
+ * @type: C type of value argument
+ * @len: Length of configuration space write (1, 2, 4 bytes)
+ *
+ * Generates rio_mport_write_config_* functions used to access
+ * configuration space registers on the local device.
+ */
+#define RIO_OP_WRITE(size,type,len) \
+int rio_mport_write_config_##size \
+	(struct rio_mport *mport, u16 destid, u8 hopcount, u32 offset, type value)	\
+{									\
+	if (RIO_##size##_BAD) return RIO_BAD_SIZE;			\
+	return mport->ops->cwrite(mport, mport->id, destid, hopcount,	\
+			offset, len, value);				\
+}
+
+RIO_OP_READ(8, u8, 1)
+RIO_OP_READ(16, u16, 2)
+RIO_OP_READ(32, u32, 4)
+RIO_OP_WRITE(8, u8, 1)
+RIO_OP_WRITE(16, u16, 2)
+RIO_OP_WRITE(32, u32, 4)
+
+EXPORT_SYMBOL_GPL(rio_mport_read_config_8);
+EXPORT_SYMBOL_GPL(rio_mport_read_config_16);
+EXPORT_SYMBOL_GPL(rio_mport_read_config_32);
+EXPORT_SYMBOL_GPL(rio_mport_write_config_8);
+EXPORT_SYMBOL_GPL(rio_mport_write_config_16);
+EXPORT_SYMBOL_GPL(rio_mport_write_config_32);
+
+/**
+ * rio_mport_send_doorbell - Send a doorbell message
+ *
+ * @mport: RIO master port
+ * @destid: RIO device destination ID
+ * @data: Doorbell message data
+ *
+ * Send a doorbell message to a RIO device. The doorbell message
+ * has a 16-bit info field provided by the data argument.
+ */
+int rio_mport_send_doorbell(struct rio_mport *mport, u16 destid, u16 data)
+{
+	return mport->ops->dsend(mport, mport->id, destid, data);
+}
+
+EXPORT_SYMBOL_GPL(rio_mport_send_doorbell);