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/rapidio/rio.h b/drivers/rapidio/rio.h
new file mode 100644
index 000000000..a0e2a09dd
--- /dev/null
+++ b/drivers/rapidio/rio.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * RapidIO interconnect services
+ *
+ * Copyright 2005 MontaVista Software, Inc.
+ * Matt Porter <mporter@kernel.crashing.org>
+ */
+
+#include <linux/device.h>
+#include <linux/list.h>
+#include <linux/rio.h>
+
+#define RIO_MAX_CHK_RETRY	3
+#define RIO_MPORT_ANY		(-1)
+
+/* Functions internal to the RIO core code */
+
+extern u32 rio_mport_get_feature(struct rio_mport *mport, int local, u16 destid,
+				 u8 hopcount, int ftr);
+extern u32 rio_mport_get_physefb(struct rio_mport *port, int local,
+				 u16 destid, u8 hopcount, u32 *rmap);
+extern u32 rio_mport_get_efb(struct rio_mport *port, int local, u16 destid,
+			     u8 hopcount, u32 from);
+extern int rio_mport_chk_dev_access(struct rio_mport *mport, u16 destid,
+				    u8 hopcount);
+extern int rio_lock_device(struct rio_mport *port, u16 destid,
+			u8 hopcount, int wait_ms);
+extern int rio_unlock_device(struct rio_mport *port, u16 destid, u8 hopcount);
+extern int rio_route_add_entry(struct rio_dev *rdev,
+			u16 table, u16 route_destid, u8 route_port, int lock);
+extern int rio_route_get_entry(struct rio_dev *rdev, u16 table,
+			u16 route_destid, u8 *route_port, int lock);
+extern int rio_route_clr_table(struct rio_dev *rdev, u16 table, int lock);
+extern int rio_set_port_lockout(struct rio_dev *rdev, u32 pnum, int lock);
+extern struct rio_dev *rio_get_comptag(u32 comp_tag, struct rio_dev *from);
+extern struct rio_net *rio_alloc_net(struct rio_mport *mport);
+extern int rio_add_net(struct rio_net *net);
+extern void rio_free_net(struct rio_net *net);
+extern int rio_add_device(struct rio_dev *rdev);
+extern void rio_del_device(struct rio_dev *rdev, enum rio_device_state state);
+extern int rio_enable_rx_tx_port(struct rio_mport *port, int local, u16 destid,
+				 u8 hopcount, u8 port_num);
+extern int rio_register_scan(int mport_id, struct rio_scan *scan_ops);
+extern void rio_attach_device(struct rio_dev *rdev);
+extern int rio_mport_scan(int mport_id);
+
+/* Structures internal to the RIO core code */
+extern const struct attribute_group *rio_dev_groups[];
+extern const struct attribute_group *rio_bus_groups[];
+extern const struct attribute_group *rio_mport_groups[];
+
+#define RIO_GET_DID(size, x)	(size ? (x & 0xffff) : ((x & 0x00ff0000) >> 16))
+#define RIO_SET_DID(size, x)	(size ? (x & 0xffff) : ((x & 0x000000ff) << 16))