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, 234 insertions, 0 deletions

diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h
new file mode 100644
index 000000000..4f8edf77d
--- /dev/null
+++ b/include/trace/events/devlink.h
@@ -0,0 +1,234 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#if IS_ENABLED(CONFIG_NET_DEVLINK)
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM devlink
+
+#if !defined(_TRACE_DEVLINK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_DEVLINK_H
+
+#include <linux/device.h>
+#include <net/devlink.h>
+#include <linux/tracepoint.h>
+
+/*
+ * Tracepoint for devlink hardware message:
+ */
+TRACE_EVENT(devlink_hwmsg,
+	TP_PROTO(const struct devlink *devlink, bool incoming,
+		 unsigned long type, const u8 *buf, size_t len),
+
+	TP_ARGS(devlink, incoming, type, buf, len),
+
+	TP_STRUCT__entry(
+		__string(bus_name, devlink_bus_name(devlink))
+		__string(dev_name, devlink_dev_name(devlink))
+		__string(driver_name, devlink_dev_driver_name(devlink))
+		__field(bool, incoming)
+		__field(unsigned long, type)
+		__dynamic_array(u8, buf, len)
+		__field(size_t, len)
+	),
+
+	TP_fast_assign(
+		__assign_str(bus_name);
+		__assign_str(dev_name);
+		__assign_str(driver_name);
+		__entry->incoming = incoming;
+		__entry->type = type;
+		memcpy(__get_dynamic_array(buf), buf, len);
+		__entry->len = len;
+	),
+
+	TP_printk("bus_name=%s dev_name=%s driver_name=%s incoming=%d type=%lu buf=0x[%*phD] len=%zu",
+		  __get_str(bus_name), __get_str(dev_name),
+		  __get_str(driver_name), __entry->incoming, __entry->type,
+		  (int) __entry->len, __get_dynamic_array(buf), __entry->len)
+);
+
+/*
+ * Tracepoint for devlink hardware error:
+ */
+TRACE_EVENT(devlink_hwerr,
+	TP_PROTO(const struct devlink *devlink, int err, const char *msg),
+
+	TP_ARGS(devlink, err, msg),
+
+	TP_STRUCT__entry(
+		__string(bus_name, devlink_bus_name(devlink))
+		__string(dev_name, devlink_dev_name(devlink))
+		__string(driver_name, devlink_dev_driver_name(devlink))
+		__field(int, err)
+		__string(msg, msg)
+		),
+
+	TP_fast_assign(
+		__assign_str(bus_name);
+		__assign_str(dev_name);
+		__assign_str(driver_name);
+		__entry->err = err;
+		__assign_str(msg);
+		),
+
+	TP_printk("bus_name=%s dev_name=%s driver_name=%s err=%d %s",
+			__get_str(bus_name), __get_str(dev_name),
+			__get_str(driver_name), __entry->err, __get_str(msg))
+);
+
+/*
+ * Tracepoint for devlink health message:
+ */
+TRACE_EVENT(devlink_health_report,
+	TP_PROTO(const struct devlink *devlink, const char *reporter_name,
+		 const char *msg),
+
+	TP_ARGS(devlink, reporter_name, msg),
+
+	TP_STRUCT__entry(
+		__string(bus_name, devlink_bus_name(devlink))
+		__string(dev_name, devlink_dev_name(devlink))
+		__string(driver_name, devlink_dev_driver_name(devlink))
+		__string(reporter_name, reporter_name)
+		__string(msg, msg)
+	),
+
+	TP_fast_assign(
+		__assign_str(bus_name);
+		__assign_str(dev_name);
+		__assign_str(driver_name);
+		__assign_str(reporter_name);
+		__assign_str(msg);
+	),
+
+	TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: %s",
+		  __get_str(bus_name), __get_str(dev_name),
+		  __get_str(driver_name), __get_str(reporter_name),
+		  __get_str(msg))
+);
+
+/*
+ * Tracepoint for devlink health recover aborted message:
+ */
+TRACE_EVENT(devlink_health_recover_aborted,
+	TP_PROTO(const struct devlink *devlink, const char *reporter_name,
+		 bool health_state, u64 time_since_last_recover),
+
+	TP_ARGS(devlink, reporter_name, health_state, time_since_last_recover),
+
+	TP_STRUCT__entry(
+		__string(bus_name, devlink_bus_name(devlink))
+		__string(dev_name, devlink_dev_name(devlink))
+		__string(driver_name, devlink_dev_driver_name(devlink))
+		__string(reporter_name, reporter_name)
+		__field(bool, health_state)
+		__field(u64, time_since_last_recover)
+	),
+
+	TP_fast_assign(
+		__assign_str(bus_name);
+		__assign_str(dev_name);
+		__assign_str(driver_name);
+		__assign_str(reporter_name);
+		__entry->health_state = health_state;
+		__entry->time_since_last_recover = time_since_last_recover;
+	),
+
+	TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: health_state=%d time_since_last_recover=%llu recover aborted",
+		  __get_str(bus_name), __get_str(dev_name),
+		  __get_str(driver_name), __get_str(reporter_name),
+		  __entry->health_state,
+		  __entry->time_since_last_recover)
+);
+
+/*
+ * Tracepoint for devlink health reporter state update:
+ */
+TRACE_EVENT(devlink_health_reporter_state_update,
+	TP_PROTO(const struct devlink *devlink, const char *reporter_name,
+		 bool new_state),
+
+	TP_ARGS(devlink, reporter_name, new_state),
+
+	TP_STRUCT__entry(
+		__string(bus_name, devlink_bus_name(devlink))
+		__string(dev_name, devlink_dev_name(devlink))
+		__string(driver_name, devlink_dev_driver_name(devlink))
+		__string(reporter_name, reporter_name)
+		__field(u8, new_state)
+	),
+
+	TP_fast_assign(
+		__assign_str(bus_name);
+		__assign_str(dev_name);
+		__assign_str(driver_name);
+		__assign_str(reporter_name);
+		__entry->new_state = new_state;
+	),
+
+	TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: new_state=%d",
+		  __get_str(bus_name), __get_str(dev_name),
+		  __get_str(driver_name), __get_str(reporter_name),
+		  __entry->new_state)
+);
+
+/*
+ * Tracepoint for devlink packet trap:
+ */
+TRACE_EVENT(devlink_trap_report,
+	TP_PROTO(const struct devlink *devlink, struct sk_buff *skb,
+		 const struct devlink_trap_metadata *metadata),
+
+	TP_ARGS(devlink, skb, metadata),
+
+	TP_STRUCT__entry(
+		__string(bus_name, devlink_bus_name(devlink))
+		__string(dev_name, devlink_dev_name(devlink))
+		__string(driver_name, devlink_dev_driver_name(devlink))
+		__string(trap_name, metadata->trap_name)
+		__string(trap_group_name, metadata->trap_group_name)
+		__array(char, input_dev_name, IFNAMSIZ)
+	),
+
+	TP_fast_assign(
+		struct net_device *input_dev = metadata->input_dev;
+
+		__assign_str(bus_name);
+		__assign_str(dev_name);
+		__assign_str(driver_name);
+		__assign_str(trap_name);
+		__assign_str(trap_group_name);
+		strscpy(__entry->input_dev_name, input_dev ? input_dev->name : "NULL", IFNAMSIZ);
+	),
+
+	TP_printk("bus_name=%s dev_name=%s driver_name=%s trap_name=%s "
+		  "trap_group_name=%s input_dev_name=%s", __get_str(bus_name),
+		  __get_str(dev_name), __get_str(driver_name),
+		  __get_str(trap_name), __get_str(trap_group_name),
+		  __entry->input_dev_name)
+);
+
+#endif /* _TRACE_DEVLINK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+
+#else /* CONFIG_NET_DEVLINK */
+
+#if !defined(_TRACE_DEVLINK_H)
+#define _TRACE_DEVLINK_H
+
+#include <net/devlink.h>
+
+static inline void trace_devlink_hwmsg(const struct devlink *devlink,
+				       bool incoming, unsigned long type,
+				       const u8 *buf, size_t len)
+{
+}
+
+static inline void trace_devlink_hwerr(const struct devlink *devlink,
+				       int err, const char *msg)
+{
+}
+#endif /* _TRACE_DEVLINK_H */
+
+#endif