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, 115 insertions, 0 deletions

diff --git a/net/dsa/port.h b/net/dsa/port.h
new file mode 100644
index 000000000..6bc329157
--- /dev/null
+++ b/net/dsa/port.h
@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef __DSA_PORT_H
+#define __DSA_PORT_H
+
+#include <linux/types.h>
+#include <net/dsa.h>
+
+struct ifreq;
+struct netdev_lag_lower_state_info;
+struct netdev_lag_upper_info;
+struct netlink_ext_ack;
+struct switchdev_mst_state;
+struct switchdev_obj_port_mdb;
+struct switchdev_vlan_msti;
+struct phy_device;
+
+bool dsa_port_supports_hwtstamp(struct dsa_port *dp);
+void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp,
+			       const struct dsa_device_ops *tag_ops);
+int dsa_port_set_state(struct dsa_port *dp, u8 state, bool do_fast_age);
+int dsa_port_set_mst_state(struct dsa_port *dp,
+			   const struct switchdev_mst_state *state,
+			   struct netlink_ext_ack *extack);
+int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy);
+int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy);
+void dsa_port_disable_rt(struct dsa_port *dp);
+void dsa_port_disable(struct dsa_port *dp);
+int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br,
+			 struct netlink_ext_ack *extack);
+void dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br);
+void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br);
+int dsa_port_lag_change(struct dsa_port *dp,
+			struct netdev_lag_lower_state_info *linfo);
+int dsa_port_lag_join(struct dsa_port *dp, struct net_device *lag_dev,
+		      struct netdev_lag_upper_info *uinfo,
+		      struct netlink_ext_ack *extack);
+void dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag_dev);
+void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag_dev);
+int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering,
+			    struct netlink_ext_ack *extack);
+bool dsa_port_skip_vlan_configuration(struct dsa_port *dp);
+int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock);
+int dsa_port_mst_enable(struct dsa_port *dp, bool on,
+			struct netlink_ext_ack *extack);
+int dsa_port_vlan_msti(struct dsa_port *dp,
+		       const struct switchdev_vlan_msti *msti);
+int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu);
+int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr,
+		     u16 vid);
+int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr,
+		     u16 vid);
+int dsa_port_standalone_host_fdb_add(struct dsa_port *dp,
+				     const unsigned char *addr, u16 vid);
+int dsa_port_standalone_host_fdb_del(struct dsa_port *dp,
+				     const unsigned char *addr, u16 vid);
+int dsa_port_bridge_host_fdb_add(struct dsa_port *dp, const unsigned char *addr,
+				 u16 vid);
+int dsa_port_bridge_host_fdb_del(struct dsa_port *dp, const unsigned char *addr,
+				 u16 vid);
+int dsa_port_lag_fdb_add(struct dsa_port *dp, const unsigned char *addr,
+			 u16 vid);
+int dsa_port_lag_fdb_del(struct dsa_port *dp, const unsigned char *addr,
+			 u16 vid);
+int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data);
+int dsa_port_mdb_add(const struct dsa_port *dp,
+		     const struct switchdev_obj_port_mdb *mdb);
+int dsa_port_mdb_del(const struct dsa_port *dp,
+		     const struct switchdev_obj_port_mdb *mdb);
+int dsa_port_standalone_host_mdb_add(const struct dsa_port *dp,
+				     const struct switchdev_obj_port_mdb *mdb);
+int dsa_port_standalone_host_mdb_del(const struct dsa_port *dp,
+				     const struct switchdev_obj_port_mdb *mdb);
+int dsa_port_bridge_host_mdb_add(const struct dsa_port *dp,
+				 const struct switchdev_obj_port_mdb *mdb);
+int dsa_port_bridge_host_mdb_del(const struct dsa_port *dp,
+				 const struct switchdev_obj_port_mdb *mdb);
+int dsa_port_pre_bridge_flags(const struct dsa_port *dp,
+			      struct switchdev_brport_flags flags,
+			      struct netlink_ext_ack *extack);
+int dsa_port_bridge_flags(struct dsa_port *dp,
+			  struct switchdev_brport_flags flags,
+			  struct netlink_ext_ack *extack);
+int dsa_port_vlan_add(struct dsa_port *dp,
+		      const struct switchdev_obj_port_vlan *vlan,
+		      struct netlink_ext_ack *extack);
+int dsa_port_vlan_del(struct dsa_port *dp,
+		      const struct switchdev_obj_port_vlan *vlan);
+int dsa_port_host_vlan_add(struct dsa_port *dp,
+			   const struct switchdev_obj_port_vlan *vlan,
+			   struct netlink_ext_ack *extack);
+int dsa_port_host_vlan_del(struct dsa_port *dp,
+			   const struct switchdev_obj_port_vlan *vlan);
+int dsa_port_mrp_add(const struct dsa_port *dp,
+		     const struct switchdev_obj_mrp *mrp);
+int dsa_port_mrp_del(const struct dsa_port *dp,
+		     const struct switchdev_obj_mrp *mrp);
+int dsa_port_mrp_add_ring_role(const struct dsa_port *dp,
+			       const struct switchdev_obj_ring_role_mrp *mrp);
+int dsa_port_mrp_del_ring_role(const struct dsa_port *dp,
+			       const struct switchdev_obj_ring_role_mrp *mrp);
+int dsa_port_phylink_create(struct dsa_port *dp);
+void dsa_port_phylink_destroy(struct dsa_port *dp);
+int dsa_shared_port_link_register_of(struct dsa_port *dp);
+void dsa_shared_port_link_unregister_of(struct dsa_port *dp);
+int dsa_port_hsr_join(struct dsa_port *dp, struct net_device *hsr,
+		      struct netlink_ext_ack *extack);
+void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr);
+int dsa_port_tag_8021q_vlan_add(struct dsa_port *dp, u16 vid, bool broadcast);
+void dsa_port_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid, bool broadcast);
+void dsa_port_set_host_flood(struct dsa_port *dp, bool uc, bool mc);
+int dsa_port_change_conduit(struct dsa_port *dp, struct net_device *conduit,
+			    struct netlink_ext_ack *extack);
+
+#endif