From a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255 Mon Sep 17 00:00:00 2001 From: Jinke Han Date: Tue, 8 Sep 2026 15:37:42 +0800 Subject: x86/kprobes: Fix crash when probing CS CALL instructions 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) Signed-off-by: Jinke Han Signed-off-by: Ingo Molnar Reviewed-by: Masami Hiramatsu (Google) Acked-by: Yafang Shao Acked-by: Borislav Petkov Cc: Peter Zijlstra Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000 --- include/net/raw.h | 100 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 100 insertions(+) create mode 100644 include/net/raw.h (limited to 'include/net/raw.h') diff --git a/include/net/raw.h b/include/net/raw.h new file mode 100644 index 000000000..66c0ffead --- /dev/null +++ b/include/net/raw.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Definitions for the RAW-IP module. + * + * Version: @(#)raw.h 1.0.2 05/07/93 + * + * Author: Fred N. van Kempen, + */ +#ifndef _RAW_H +#define _RAW_H + +#include +#include +#include +#include +#include + +extern struct proto raw_prot; + +extern struct raw_hashinfo raw_v4_hashinfo; +bool raw_v4_match(struct net *net, const struct sock *sk, unsigned short num, + __be32 raddr, __be32 laddr, int dif, int sdif); + +int raw_abort(struct sock *sk, int err); +void raw_icmp_error(struct sk_buff *, int, u32); +int raw_local_deliver(struct sk_buff *, int); + +int raw_rcv(struct sock *, struct sk_buff *); + +#define RAW_HTABLE_LOG 8 +#define RAW_HTABLE_SIZE (1U << RAW_HTABLE_LOG) + +struct raw_hashinfo { + spinlock_t lock; + + struct hlist_head ht[RAW_HTABLE_SIZE] ____cacheline_aligned; +}; + +static inline u32 raw_hashfunc(const struct net *net, u32 proto) +{ + return hash_32(net_hash_mix(net) ^ proto, RAW_HTABLE_LOG); +} + +static inline void raw_hashinfo_init(struct raw_hashinfo *hashinfo) +{ + int i; + + spin_lock_init(&hashinfo->lock); + for (i = 0; i < RAW_HTABLE_SIZE; i++) + INIT_HLIST_HEAD(&hashinfo->ht[i]); +} + +#ifdef CONFIG_PROC_FS +int raw_proc_init(void); +void raw_proc_exit(void); + +struct raw_iter_state { + struct seq_net_private p; + int bucket; +}; + +static inline struct raw_iter_state *raw_seq_private(struct seq_file *seq) +{ + return seq->private; +} +void *raw_seq_start(struct seq_file *seq, loff_t *pos); +void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos); +void raw_seq_stop(struct seq_file *seq, void *v); +#endif + +int raw_hash_sk(struct sock *sk); +void raw_unhash_sk(struct sock *sk); +void raw_init(void); + +struct raw_sock { + /* inet_sock has to be the first member */ + struct inet_sock inet; + struct icmp_filter filter; + u32 ipmr_table; + struct numa_drop_counters drop_counters; +}; + +#define raw_sk(ptr) container_of_const(ptr, struct raw_sock, inet.sk) + +static inline bool raw_sk_bound_dev_eq(struct net *net, int bound_dev_if, + int dif, int sdif) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + return inet_bound_dev_eq(READ_ONCE(net->ipv4.sysctl_raw_l3mdev_accept), + bound_dev_if, dif, sdif); +#else + return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); +#endif +} + +#endif /* _RAW_H */ -- cgit v1.3.1