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 --- lib/llist.c | 94 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 94 insertions(+) create mode 100644 lib/llist.c (limited to 'lib/llist.c') diff --git a/lib/llist.c b/lib/llist.c new file mode 100644 index 000000000..f574c17a2 --- /dev/null +++ b/lib/llist.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Lock-less NULL terminated single linked list + * + * The basic atomic operation of this list is cmpxchg on long. On + * architectures that don't have NMI-safe cmpxchg implementation, the + * list can NOT be used in NMI handlers. So code that uses the list in + * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. + * + * Copyright 2010,2011 Intel Corp. + * Author: Huang Ying + */ +#include +#include +#include + +/** + * llist_del_first - delete the first entry of lock-less list + * @head: the head for your lock-less list + * + * If list is empty, return NULL, otherwise, return the first entry + * deleted, this is the newest added one. + * + * Only one llist_del_first user can be used simultaneously with + * multiple llist_add users without lock. Because otherwise + * llist_del_first, llist_add, llist_add (or llist_del_all, llist_add, + * llist_add) sequence in another user may change @head->first->next, + * but keep @head->first. If multiple consumers are needed, please + * use llist_del_all or use lock between consumers. + */ +struct llist_node *llist_del_first(struct llist_head *head) +{ + struct llist_node *entry, *next; + + entry = smp_load_acquire(&head->first); + do { + if (entry == NULL) + return NULL; + next = READ_ONCE(entry->next); + } while (!try_cmpxchg(&head->first, &entry, next)); + + return entry; +} +EXPORT_SYMBOL_GPL(llist_del_first); + +/** + * llist_del_first_this - delete given entry of lock-less list if it is first + * @head: the head for your lock-less list + * @this: a list entry. + * + * If head of the list is given entry, delete and return %true else + * return %false. + * + * Multiple callers can safely call this concurrently with multiple + * llist_add() callers, providing all the callers offer a different @this. + */ +bool llist_del_first_this(struct llist_head *head, + struct llist_node *this) +{ + struct llist_node *entry, *next; + + /* acquire ensures orderig wrt try_cmpxchg() is llist_del_first() */ + entry = smp_load_acquire(&head->first); + do { + if (entry != this) + return false; + next = READ_ONCE(entry->next); + } while (!try_cmpxchg(&head->first, &entry, next)); + + return true; +} +EXPORT_SYMBOL_GPL(llist_del_first_this); + +/** + * llist_reverse_order - reverse order of a llist chain + * @head: first item of the list to be reversed + * + * Reverse the order of a chain of llist entries and return the + * new first entry. + */ +struct llist_node *llist_reverse_order(struct llist_node *head) +{ + struct llist_node *new_head = NULL; + + while (head) { + struct llist_node *tmp = head; + head = head->next; + tmp->next = new_head; + new_head = tmp; + } + + return new_head; +} +EXPORT_SYMBOL_GPL(llist_reverse_order); -- cgit v1.3.1