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 --- net/packet/internal.h | 159 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 159 insertions(+) create mode 100644 net/packet/internal.h (limited to 'net/packet/internal.h') diff --git a/net/packet/internal.h b/net/packet/internal.h new file mode 100644 index 000000000..b76e645cd --- /dev/null +++ b/net/packet/internal.h @@ -0,0 +1,159 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PACKET_INTERNAL_H__ +#define __PACKET_INTERNAL_H__ + +#include + +struct packet_mclist { + struct packet_mclist *next; + int ifindex; + int count; + unsigned short type; + unsigned short alen; + unsigned char addr[MAX_ADDR_LEN]; + struct list_head remove_list; +}; + +/* kbdq - kernel block descriptor queue */ +struct tpacket_kbdq_core { + struct pgv *pkbdq; + unsigned int feature_req_word; + unsigned int hdrlen; + unsigned char reset_pending_on_curr_blk; + unsigned short kactive_blk_num; + unsigned short blk_sizeof_priv; + + unsigned short version; + + char *pkblk_start; + char *pkblk_end; + int kblk_size; + unsigned int max_frame_len; + unsigned int knum_blocks; + uint64_t knxt_seq_num; + char *prev; + char *nxt_offset; + + struct sk_buff *skb; + + rwlock_t blk_fill_in_prog_lock; + + /* Default is set to 8ms */ +#define DEFAULT_PRB_RETIRE_TOV (8) + + ktime_t interval_ktime; + + /* timer to retire an outstanding block */ + struct hrtimer retire_blk_timer; +}; + +struct pgv { + char *buffer; +}; + +struct packet_ring_buffer { + struct pgv *pg_vec; + + unsigned int head; + unsigned int frames_per_block; + unsigned int frame_size; + unsigned int frame_max; + + unsigned int pg_vec_order; + unsigned int pg_vec_pages; + unsigned int pg_vec_len; + + unsigned int __percpu *pending_refcnt; + + union { + unsigned long *rx_owner_map; + struct tpacket_kbdq_core prb_bdqc; + }; +}; + +extern struct mutex fanout_mutex; +#define PACKET_FANOUT_MAX (1 << 16) + +struct packet_fanout { + possible_net_t net; + unsigned int num_members; + u32 max_num_members; + u16 id; + u8 type; + u8 flags; + union { + atomic_t rr_cur; + struct bpf_prog __rcu *bpf_prog; + }; + struct list_head list; + spinlock_t lock; + refcount_t sk_ref; + struct packet_type prot_hook ____cacheline_aligned_in_smp; + struct sock __rcu *arr[] __counted_by(max_num_members); +}; + +struct packet_rollover { + int sock; + atomic_long_t num; + atomic_long_t num_huge; + atomic_long_t num_failed; +#define ROLLOVER_HLEN (L1_CACHE_BYTES / sizeof(u32)) + u32 history[ROLLOVER_HLEN] ____cacheline_aligned; +} ____cacheline_aligned_in_smp; + +struct packet_sock { + /* struct sock has to be the first member of packet_sock */ + struct sock sk; + struct packet_fanout *fanout; + union tpacket_stats_u stats; + struct packet_ring_buffer rx_ring; + struct packet_ring_buffer tx_ring; + int copy_thresh; + spinlock_t bind_lock; + struct mutex pg_vec_lock; + unsigned long flags; + int ifindex; /* bound device */ + u8 vnet_hdr_sz; + __be16 num; + struct packet_rollover *rollover; + struct packet_mclist *mclist; + atomic_long_t mapped; + enum tpacket_versions tp_version; + unsigned int tp_hdrlen; + unsigned int tp_reserve; + unsigned int tp_tstamp; + struct completion skb_completion; + struct net_device __rcu *cached_dev; + struct packet_type prot_hook ____cacheline_aligned_in_smp; + atomic_t tp_drops ____cacheline_aligned_in_smp; +}; + +#define pkt_sk(ptr) container_of_const(ptr, struct packet_sock, sk) + +enum packet_sock_flags { + PACKET_SOCK_ORIGDEV, + PACKET_SOCK_AUXDATA, + PACKET_SOCK_TX_HAS_OFF, + PACKET_SOCK_TP_LOSS, + PACKET_SOCK_RUNNING, + PACKET_SOCK_PRESSURE, + PACKET_SOCK_QDISC_BYPASS, +}; + +static inline void packet_sock_flag_set(struct packet_sock *po, + enum packet_sock_flags flag, + bool val) +{ + if (val) + set_bit(flag, &po->flags); + else + clear_bit(flag, &po->flags); +} + +static inline bool packet_sock_flag(const struct packet_sock *po, + enum packet_sock_flags flag) +{ + return test_bit(flag, &po->flags); +} + +#endif -- cgit v1.3.1