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, 160 insertions, 0 deletions

diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h
new file mode 100644
index 000000000..a70e0e476
--- /dev/null
+++ b/net/devlink/netlink_gen.h
@@ -0,0 +1,160 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/devlink.yaml */
+/* YNL-GEN kernel header */
+/* To regenerate run: tools/net/ynl/ynl-regen.sh */
+
+#ifndef _LINUX_DEVLINK_GEN_H
+#define _LINUX_DEVLINK_GEN_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include <uapi/linux/devlink.h>
+
+/* Common nested types */
+extern const struct nla_policy devlink_dl_parent_dev_nl_policy[DEVLINK_ATTR_INDEX + 1];
+extern const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_CAPS + 1];
+extern const struct nla_policy devlink_dl_rate_tc_bws_nl_policy[DEVLINK_RATE_TC_ATTR_BW + 1];
+extern const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1];
+
+/* Ops table for devlink */
+extern const struct genl_split_ops devlink_nl_ops[75];
+
+int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
+			struct genl_info *info);
+int devlink_nl_pre_doit_port(const struct genl_split_ops *ops,
+			     struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_pre_doit_port_optional(const struct genl_split_ops *ops,
+				      struct sk_buff *skb,
+				      struct genl_info *info);
+int devlink_nl_pre_doit_dev_lock(const struct genl_split_ops *ops,
+				 struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_pre_doit_parent_dev_optional(const struct genl_split_ops *ops,
+					    struct sk_buff *skb,
+					    struct genl_info *info);
+void
+devlink_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
+		     struct genl_info *info);
+void
+devlink_nl_post_doit_dev_lock(const struct genl_split_ops *ops,
+			      struct sk_buff *skb, struct genl_info *info);
+void
+devlink_nl_post_doit_parent_dev_optional(const struct genl_split_ops *ops,
+					 struct sk_buff *skb,
+					 struct genl_info *info);
+
+int devlink_nl_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_get_dumpit(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+int devlink_nl_port_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_new_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_del_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_split_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_unsplit_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_sb_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_sb_pool_get_dumpit(struct sk_buff *skb,
+				  struct netlink_callback *cb);
+int devlink_nl_sb_pool_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_sb_port_pool_get_dumpit(struct sk_buff *skb,
+				       struct netlink_callback *cb);
+int devlink_nl_sb_port_pool_set_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb,
+					struct genl_info *info);
+int devlink_nl_sb_tc_pool_bind_get_dumpit(struct sk_buff *skb,
+					  struct netlink_callback *cb);
+int devlink_nl_sb_tc_pool_bind_set_doit(struct sk_buff *skb,
+					struct genl_info *info);
+int devlink_nl_sb_occ_snapshot_doit(struct sk_buff *skb,
+				    struct genl_info *info);
+int devlink_nl_sb_occ_max_clear_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_dpipe_table_get_doit(struct sk_buff *skb,
+				    struct genl_info *info);
+int devlink_nl_dpipe_entries_get_doit(struct sk_buff *skb,
+				      struct genl_info *info);
+int devlink_nl_dpipe_headers_get_doit(struct sk_buff *skb,
+				      struct genl_info *info);
+int devlink_nl_dpipe_table_counters_set_doit(struct sk_buff *skb,
+					     struct genl_info *info);
+int devlink_nl_resource_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_resource_dump_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_resource_dump_dumpit(struct sk_buff *skb,
+				    struct netlink_callback *cb);
+int devlink_nl_reload_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_param_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_param_get_dumpit(struct sk_buff *skb,
+				struct netlink_callback *cb);
+int devlink_nl_param_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_region_get_dumpit(struct sk_buff *skb,
+				 struct netlink_callback *cb);
+int devlink_nl_region_new_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_region_del_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_region_read_dumpit(struct sk_buff *skb,
+				  struct netlink_callback *cb);
+int devlink_nl_port_param_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_port_param_get_dumpit(struct sk_buff *skb,
+				     struct netlink_callback *cb);
+int devlink_nl_port_param_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_info_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_info_get_dumpit(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+int devlink_nl_health_reporter_get_doit(struct sk_buff *skb,
+					struct genl_info *info);
+int devlink_nl_health_reporter_get_dumpit(struct sk_buff *skb,
+					  struct netlink_callback *cb);
+int devlink_nl_health_reporter_set_doit(struct sk_buff *skb,
+					struct genl_info *info);
+int devlink_nl_health_reporter_recover_doit(struct sk_buff *skb,
+					    struct genl_info *info);
+int devlink_nl_health_reporter_diagnose_doit(struct sk_buff *skb,
+					     struct genl_info *info);
+int devlink_nl_health_reporter_dump_get_dumpit(struct sk_buff *skb,
+					       struct netlink_callback *cb);
+int devlink_nl_health_reporter_dump_clear_doit(struct sk_buff *skb,
+					       struct genl_info *info);
+int devlink_nl_flash_update_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_trap_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_trap_get_dumpit(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+int devlink_nl_trap_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_trap_group_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_trap_group_get_dumpit(struct sk_buff *skb,
+				     struct netlink_callback *cb);
+int devlink_nl_trap_group_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_trap_policer_get_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_trap_policer_get_dumpit(struct sk_buff *skb,
+				       struct netlink_callback *cb);
+int devlink_nl_trap_policer_set_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int devlink_nl_health_reporter_test_doit(struct sk_buff *skb,
+					 struct genl_info *info);
+int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_rate_get_dumpit(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+int devlink_nl_rate_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_rate_new_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_rate_del_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_linecard_get_dumpit(struct sk_buff *skb,
+				   struct netlink_callback *cb);
+int devlink_nl_linecard_set_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_selftests_get_dumpit(struct sk_buff *skb,
+				    struct netlink_callback *cb);
+int devlink_nl_selftests_run_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_notify_filter_set_doit(struct sk_buff *skb,
+				      struct genl_info *info);
+
+#endif /* _LINUX_DEVLINK_GEN_H */