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 --- drivers/md/dm-cache-background-tracker.h | 88 ++++++++++++++++++++++++++++++++ 1 file changed, 88 insertions(+) create mode 100644 drivers/md/dm-cache-background-tracker.h (limited to 'drivers/md/dm-cache-background-tracker.h') diff --git a/drivers/md/dm-cache-background-tracker.h b/drivers/md/dm-cache-background-tracker.h new file mode 100644 index 000000000..47156c14a --- /dev/null +++ b/drivers/md/dm-cache-background-tracker.h @@ -0,0 +1,88 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2017 Red Hat. All rights reserved. + * + * This file is released under the GPL. + */ + +#ifndef DM_CACHE_BACKGROUND_WORK_H +#define DM_CACHE_BACKGROUND_WORK_H + +#include +#include "dm-cache-policy.h" + +/*----------------------------------------------------------------*/ + +/* + * The cache policy decides what background work should be performed, + * such as promotions, demotions and writebacks. The core cache target + * is in charge of performing the work, and does so when it sees fit. + * + * The background_tracker acts as a go between. Keeping track of future + * work that the policy has decided upon, and handing (issuing) it to + * the core target when requested. + * + * There is no locking in this, so calls will probably need to be + * protected with a spinlock. + */ + +struct bt_work { + struct list_head list; + struct rb_node node; + struct policy_work work; +}; + +extern struct kmem_cache *btracker_work_cache; + +struct background_work; +struct background_tracker; + +/* + * Create a new tracker, it will not be able to queue more than + * 'max_work' entries. + */ +struct background_tracker *btracker_create(unsigned int max_work); + +/* + * Destroy the tracker. No issued, but not complete, work should + * exist when this is called. It is fine to have queued but unissued + * work. + */ +void btracker_destroy(struct background_tracker *b); + +unsigned int btracker_nr_demotions_queued(struct background_tracker *b); + +/* + * Queue some work within the tracker. 'work' should point to the work + * to queue, this will be copied (ownership doesn't pass). If pwork + * is not NULL then it will be set to point to the tracker's internal + * copy of the work. + * + * returns -EINVAL iff the work is already queued. -ENOMEM if the work + * couldn't be queued for another reason. + */ +int btracker_queue(struct background_tracker *b, + struct policy_work *work, + struct policy_work **pwork); + +/* + * Hands out the next piece of work to be performed. + * Returns -ENODATA if there's no work. + */ +int btracker_issue(struct background_tracker *b, struct policy_work **work); + +/* + * Informs the tracker that the work has been completed and it may forget + * about it. + */ +void btracker_complete(struct background_tracker *b, struct policy_work *op); + +/* + * Predicate to see if an origin block is already scheduled for promotion. + */ +bool btracker_promotion_already_present(struct background_tracker *b, + dm_oblock_t oblock); + +/*----------------------------------------------------------------*/ + +#endif -- cgit v1.3.1