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, 72 insertions, 0 deletions

diff --git a/include/net/ncsi.h b/include/net/ncsi.h
new file mode 100644
index 000000000..e88635820
--- /dev/null
+++ b/include/net/ncsi.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NET_NCSI_H
+#define __NET_NCSI_H
+
+#include <linux/types.h>
+
+/*
+ * The NCSI device states seen from external. More NCSI device states are
+ * only visible internally (in net/ncsi/internal.h). When the NCSI device
+ * is registered, it's in ncsi_dev_state_registered state. The state
+ * ncsi_dev_state_start is used to drive to choose active package and
+ * channel. After that, its state is changed to ncsi_dev_state_functional.
+ *
+ * The state ncsi_dev_state_stop helps to shut down the currently active
+ * package and channel while ncsi_dev_state_config helps to reconfigure
+ * them.
+ */
+enum {
+	ncsi_dev_state_registered	= 0x0000,
+	ncsi_dev_state_functional	= 0x0100,
+	ncsi_dev_state_probe		= 0x0200,
+	ncsi_dev_state_config		= 0x0300,
+	ncsi_dev_state_suspend		= 0x0400,
+};
+
+struct ncsi_dev {
+	int               state;
+	int		  link_up;
+	struct net_device *dev;
+	void		  (*handler)(struct ncsi_dev *ndev);
+};
+
+#ifdef CONFIG_NET_NCSI
+int ncsi_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid);
+int ncsi_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid);
+struct ncsi_dev *ncsi_register_dev(struct net_device *dev,
+				   void (*notifier)(struct ncsi_dev *nd));
+int ncsi_start_dev(struct ncsi_dev *nd);
+void ncsi_stop_dev(struct ncsi_dev *nd);
+void ncsi_unregister_dev(struct ncsi_dev *nd);
+#else /* !CONFIG_NET_NCSI */
+static inline int ncsi_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
+{
+	return -EINVAL;
+}
+
+static inline int ncsi_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
+{
+	return -EINVAL;
+}
+
+static inline struct ncsi_dev *ncsi_register_dev(struct net_device *dev,
+					void (*notifier)(struct ncsi_dev *nd))
+{
+	return NULL;
+}
+
+static inline int ncsi_start_dev(struct ncsi_dev *nd)
+{
+	return -ENOTTY;
+}
+
+static inline void ncsi_stop_dev(struct ncsi_dev *nd)
+{
+}
+
+static inline void ncsi_unregister_dev(struct ncsi_dev *nd)
+{
+}
+#endif /* CONFIG_NET_NCSI */
+
+#endif /* __NET_NCSI_H */