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, 123 insertions, 0 deletions

diff --git a/net/dsa/switch.h b/net/dsa/switch.h
new file mode 100644
index 000000000..be0a2749c
--- /dev/null
+++ b/net/dsa/switch.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef __DSA_SWITCH_H
+#define __DSA_SWITCH_H
+
+#include <net/dsa.h>
+
+struct netlink_ext_ack;
+
+enum {
+	DSA_NOTIFIER_AGEING_TIME,
+	DSA_NOTIFIER_BRIDGE_JOIN,
+	DSA_NOTIFIER_BRIDGE_LEAVE,
+	DSA_NOTIFIER_FDB_ADD,
+	DSA_NOTIFIER_FDB_DEL,
+	DSA_NOTIFIER_HOST_FDB_ADD,
+	DSA_NOTIFIER_HOST_FDB_DEL,
+	DSA_NOTIFIER_LAG_FDB_ADD,
+	DSA_NOTIFIER_LAG_FDB_DEL,
+	DSA_NOTIFIER_LAG_CHANGE,
+	DSA_NOTIFIER_LAG_JOIN,
+	DSA_NOTIFIER_LAG_LEAVE,
+	DSA_NOTIFIER_MDB_ADD,
+	DSA_NOTIFIER_MDB_DEL,
+	DSA_NOTIFIER_HOST_MDB_ADD,
+	DSA_NOTIFIER_HOST_MDB_DEL,
+	DSA_NOTIFIER_VLAN_ADD,
+	DSA_NOTIFIER_VLAN_DEL,
+	DSA_NOTIFIER_HOST_VLAN_ADD,
+	DSA_NOTIFIER_HOST_VLAN_DEL,
+	DSA_NOTIFIER_MTU,
+	DSA_NOTIFIER_TAG_PROTO,
+	DSA_NOTIFIER_TAG_PROTO_CONNECT,
+	DSA_NOTIFIER_TAG_PROTO_DISCONNECT,
+	DSA_NOTIFIER_TAG_8021Q_VLAN_ADD,
+	DSA_NOTIFIER_TAG_8021Q_VLAN_DEL,
+	DSA_NOTIFIER_CONDUIT_STATE_CHANGE,
+};
+
+/* DSA_NOTIFIER_AGEING_TIME */
+struct dsa_notifier_ageing_time_info {
+	unsigned int ageing_time;
+};
+
+/* DSA_NOTIFIER_BRIDGE_* */
+struct dsa_notifier_bridge_info {
+	const struct dsa_port *dp;
+	struct dsa_bridge bridge;
+	bool tx_fwd_offload;
+	struct netlink_ext_ack *extack;
+};
+
+/* DSA_NOTIFIER_FDB_* */
+struct dsa_notifier_fdb_info {
+	const struct dsa_port *dp;
+	const unsigned char *addr;
+	u16 vid;
+	struct dsa_db db;
+};
+
+/* DSA_NOTIFIER_LAG_FDB_* */
+struct dsa_notifier_lag_fdb_info {
+	struct dsa_lag *lag;
+	const unsigned char *addr;
+	u16 vid;
+	struct dsa_db db;
+};
+
+/* DSA_NOTIFIER_MDB_* */
+struct dsa_notifier_mdb_info {
+	const struct dsa_port *dp;
+	const struct switchdev_obj_port_mdb *mdb;
+	struct dsa_db db;
+};
+
+/* DSA_NOTIFIER_LAG_* */
+struct dsa_notifier_lag_info {
+	const struct dsa_port *dp;
+	struct dsa_lag lag;
+	struct netdev_lag_upper_info *info;
+	struct netlink_ext_ack *extack;
+};
+
+/* DSA_NOTIFIER_VLAN_* */
+struct dsa_notifier_vlan_info {
+	const struct dsa_port *dp;
+	const struct switchdev_obj_port_vlan *vlan;
+	struct netlink_ext_ack *extack;
+};
+
+/* DSA_NOTIFIER_MTU */
+struct dsa_notifier_mtu_info {
+	const struct dsa_port *dp;
+	int mtu;
+};
+
+/* DSA_NOTIFIER_TAG_PROTO_* */
+struct dsa_notifier_tag_proto_info {
+	const struct dsa_device_ops *tag_ops;
+};
+
+/* DSA_NOTIFIER_TAG_8021Q_VLAN_* */
+struct dsa_notifier_tag_8021q_vlan_info {
+	const struct dsa_port *dp;
+	u16 vid;
+};
+
+/* DSA_NOTIFIER_CONDUIT_STATE_CHANGE */
+struct dsa_notifier_conduit_state_info {
+	const struct net_device *conduit;
+	bool operational;
+};
+
+struct dsa_vlan *dsa_vlan_find(struct list_head *vlan_list,
+			       const struct switchdev_obj_port_vlan *vlan);
+
+int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v);
+int dsa_broadcast(unsigned long e, void *v);
+
+int dsa_switch_register_notifier(struct dsa_switch *ds);
+void dsa_switch_unregister_notifier(struct dsa_switch *ds);
+
+#endif