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/request_sock.h | 253 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 253 insertions(+) create mode 100644 include/net/request_sock.h (limited to 'include/net/request_sock.h') diff --git a/include/net/request_sock.h b/include/net/request_sock.h new file mode 100644 index 000000000..5a9c826a7 --- /dev/null +++ b/include/net/request_sock.h @@ -0,0 +1,253 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * NET Generic infrastructure for Network protocols. + * + * Definitions for request_sock + * + * Authors: Arnaldo Carvalho de Melo + * + * From code originally in include/net/tcp.h + */ +#ifndef _REQUEST_SOCK_H +#define _REQUEST_SOCK_H + +#include +#include +#include +#include +#include + +#include +#include + +struct request_sock; +struct sk_buff; +struct dst_entry; +struct proto; + +struct request_sock_ops { + int family; + unsigned int obj_size; + struct kmem_cache *slab; + char *slab_name; + void (*send_ack)(const struct sock *sk, struct sk_buff *skb, + struct request_sock *req); + void (*send_reset)(const struct sock *sk, + struct sk_buff *skb, + enum sk_rst_reason reason); + void (*destructor)(struct request_sock *req); +}; + +struct saved_syn { + u32 mac_hdrlen; + u32 network_hdrlen; + u32 tcp_hdrlen; + u8 data[]; +}; + +/* struct request_sock - mini sock to represent a connection request + */ +struct request_sock { + struct sock_common __req_common; +#define rsk_refcnt __req_common.skc_refcnt +#define rsk_hash __req_common.skc_hash +#define rsk_listener __req_common.skc_listener +#define rsk_window_clamp __req_common.skc_window_clamp +#define rsk_rcv_wnd __req_common.skc_rcv_wnd + + struct request_sock *dl_next; + u16 mss; + u8 num_retrans; /* number of retransmits */ + u8 syncookie:1; /* True if + * 1) tcpopts needs to be encoded in + * TS of SYN+ACK + * 2) ACK is validated by BPF kfunc. + */ + u8 num_timeout:7; /* number of timeouts */ + u32 ts_recent; + struct timer_list rsk_timer; + const struct request_sock_ops *rsk_ops; + struct sock *sk; + struct saved_syn *saved_syn; + u32 secid; + u32 peer_secid; + u32 timeout; +}; + +static inline struct request_sock *inet_reqsk(const struct sock *sk) +{ + return (struct request_sock *)sk; +} + +static inline struct sock *req_to_sk(struct request_sock *req) +{ + return (struct sock *)req; +} + +/** + * skb_steal_sock - steal a socket from an sk_buff + * @skb: sk_buff to steal the socket from + * @refcounted: is set to true if the socket is reference-counted + * @prefetched: is set to true if the socket was assigned from bpf + */ +static inline struct sock *skb_steal_sock(struct sk_buff *skb, + bool *refcounted, bool *prefetched) +{ + struct sock *sk = skb->sk; + + if (!sk) { + *prefetched = false; + *refcounted = false; + return NULL; + } + + *prefetched = skb_sk_is_prefetched(skb); + if (*prefetched) { +#if IS_ENABLED(CONFIG_SYN_COOKIES) + if (sk->sk_state == TCP_NEW_SYN_RECV && inet_reqsk(sk)->syncookie) { + struct request_sock *req = inet_reqsk(sk); + + *refcounted = false; + sk = req->rsk_listener; + req->rsk_listener = NULL; + return sk; + } +#endif + *refcounted = sk_is_refcounted(sk); + } else { + *refcounted = true; + } + + skb->destructor = NULL; + skb->sk = NULL; + return sk; +} + +void __reqsk_free(struct request_sock *req); + +static inline void reqsk_free(struct request_sock *req) +{ + DEBUG_NET_WARN_ON_ONCE(refcount_read(&req->rsk_refcnt) != 0); + __reqsk_free(req); +} + +static inline void reqsk_put(struct request_sock *req) +{ + if (refcount_dec_and_test(&req->rsk_refcnt)) + __reqsk_free(req); +} + +/* + * For a TCP Fast Open listener - + * lock - protects the access to all the reqsk, which is co-owned by + * the listener and the child socket. + * qlen - pending TFO requests (still in TCP_SYN_RECV). + * max_qlen - max TFO reqs allowed before TFO is disabled. + * + * XXX (TFO) - ideally these fields can be made as part of "listen_sock" + * structure above. But there is some implementation difficulty due to + * listen_sock being part of request_sock_queue hence will be freed when + * a listener is stopped. But TFO related fields may continue to be + * accessed even after a listener is closed, until its sk_refcnt drops + * to 0 implying no more outstanding TFO reqs. One solution is to keep + * listen_opt around until sk_refcnt drops to 0. But there is some other + * complexity that needs to be resolved. E.g., a listener can be disabled + * temporarily through shutdown()->tcp_disconnect(), and re-enabled later. + */ +struct fastopen_queue { + struct request_sock *rskq_rst_head; /* Keep track of past TFO */ + struct request_sock *rskq_rst_tail; /* requests that caused RST. + * This is part of the defense + * against spoofing attack. + */ + spinlock_t lock; + int qlen; /* # of pending (TCP_SYN_RECV) reqs */ + int max_qlen; /* != 0 iff TFO is currently enabled */ + + struct tcp_fastopen_context __rcu *ctx; /* cipher context for cookie */ +}; + +/** struct request_sock_queue - queue of request_socks + * + * @rskq_accept_head - FIFO head of established children + * @rskq_accept_tail - FIFO tail of established children + * @rskq_defer_accept - User waits for some data after accept() + * + */ +struct request_sock_queue { + spinlock_t rskq_lock; + u8 rskq_defer_accept; + u8 synflood_warned; + + atomic_t qlen; + atomic_t young; + + struct request_sock *rskq_accept_head; + struct request_sock *rskq_accept_tail; + struct fastopen_queue fastopenq; /* Check max_qlen != 0 to determine + * if TFO is enabled. + */ +}; + +void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, + bool reset); + +static inline bool reqsk_queue_empty(const struct request_sock_queue *queue) +{ + return READ_ONCE(queue->rskq_accept_head) == NULL; +} + +static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue, + struct sock *parent) +{ + struct request_sock *req; + + spin_lock_bh(&queue->rskq_lock); + req = queue->rskq_accept_head; + if (req) { + sk_acceptq_removed(parent); + WRITE_ONCE(queue->rskq_accept_head, req->dl_next); + if (queue->rskq_accept_head == NULL) + queue->rskq_accept_tail = NULL; + } + spin_unlock_bh(&queue->rskq_lock); + return req; +} + +static inline void reqsk_queue_removed(struct request_sock_queue *queue, + const struct request_sock *req) +{ + if (req->num_timeout == 0) + atomic_dec(&queue->young); + atomic_dec(&queue->qlen); +} + +static inline void reqsk_queue_added(struct request_sock_queue *queue) +{ + atomic_inc(&queue->young); + atomic_inc(&queue->qlen); +} + +static inline int reqsk_queue_len(const struct request_sock_queue *queue) +{ + return atomic_read(&queue->qlen); +} + +static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) +{ + return atomic_read(&queue->young); +} + +/* RFC 7323 2.3 Using the Window Scale Option + * The window field (SEG.WND) of every outgoing segment, with the + * exception of segments, MUST be right-shifted by + * Rcv.Wind.Shift bits. + * + * This means the SEG.WND carried in SYNACK can not exceed 65535. + * We use this property to harden TCP stack while in NEW_SYN_RECV state. + */ +static inline u32 tcp_synack_window(const struct request_sock *req) +{ + return min(req->rsk_rcv_wnd, 65535U); +} +#endif /* _REQUEST_SOCK_H */ -- cgit v1.3.1