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 --- tools/memory-model/linux-kernel.bell | 99 ++++++++++++++++++++++++++++++++++++ 1 file changed, 99 insertions(+) create mode 100644 tools/memory-model/linux-kernel.bell (limited to 'tools/memory-model/linux-kernel.bell') diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell new file mode 100644 index 000000000..fe6599800 --- /dev/null +++ b/tools/memory-model/linux-kernel.bell @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0+ +(* + * Copyright (C) 2015 Jade Alglave , + * Copyright (C) 2016 Luc Maranget for Inria + * Copyright (C) 2017 Alan Stern , + * Andrea Parri + * + * An earlier version of this file appeared in the companion webpage for + * "Frightening small children and disconcerting grown-ups: Concurrency + * in the Linux kernel" by Alglave, Maranget, McKenney, Parri, and Stern, + * which appeared in ASPLOS 2018. + *) + +"Linux-kernel memory consistency model" + +enum Accesses = 'ONCE (*READ_ONCE,WRITE_ONCE*) || + 'RELEASE (*smp_store_release*) || + 'ACQUIRE (*smp_load_acquire*) || + 'NORETURN (* R of non-return RMW *) || + 'MB (*xchg(),cmpxchg(),...*) +instructions R[Accesses] +instructions W[Accesses] +instructions RMW[Accesses] + +enum Barriers = 'wmb (*smp_wmb*) || + 'rmb (*smp_rmb*) || + 'MB (*smp_mb*) || + 'barrier (*barrier*) || + 'rcu-lock (*rcu_read_lock*) || + 'rcu-unlock (*rcu_read_unlock*) || + 'sync-rcu (*synchronize_rcu*) || + 'before-atomic (*smp_mb__before_atomic*) || + 'after-atomic (*smp_mb__after_atomic*) || + 'after-spinlock (*smp_mb__after_spinlock*) || + 'after-unlock-lock (*smp_mb__after_unlock_lock*) || + 'after-srcu-read-unlock (*smp_mb__after_srcu_read_unlock*) +instructions F[Barriers] + + +(* + * Filter out syntactic annotations that do not provide the corresponding + * semantic ordering, such as Acquire on a store or Mb on a failed RMW. + *) +let FailedRMW = RMW \ (domain(rmw) | range(rmw)) +let Acquire = ACQUIRE \ W \ FailedRMW +let Release = RELEASE \ R \ FailedRMW +let Mb = MB \ FailedRMW +let Noreturn = NORETURN \ W + +(* SRCU *) +enum SRCU = 'srcu-lock || 'srcu-unlock || 'sync-srcu +instructions SRCU[SRCU] +(* All srcu events *) +let Srcu = Srcu-lock | Srcu-unlock | Sync-srcu + +(* Compute matching pairs of nested Rcu-lock and Rcu-unlock *) +let rcu-rscs = let rec + unmatched-locks = Rcu-lock \ domain(matched) + and unmatched-unlocks = Rcu-unlock \ range(matched) + and unmatched = unmatched-locks | unmatched-unlocks + and unmatched-po = [unmatched] ; po ; [unmatched] + and unmatched-locks-to-unlocks = + [unmatched-locks] ; po ; [unmatched-unlocks] + and matched = matched | (unmatched-locks-to-unlocks \ + (unmatched-po ; unmatched-po)) + in matched + +(* Validate nesting *) +flag ~empty Rcu-lock \ domain(rcu-rscs) as unmatched-rcu-lock +flag ~empty Rcu-unlock \ range(rcu-rscs) as unmatched-rcu-unlock + +(* Compute matching pairs of nested Srcu-lock and Srcu-unlock *) +let carry-srcu-data = (data ; [~ Srcu-unlock] ; rf)* +let srcu-rscs = ([Srcu-lock] ; carry-srcu-data ; data ; [Srcu-unlock]) & loc + +(* Validate nesting *) +flag ~empty Srcu-lock \ domain(srcu-rscs) as unmatched-srcu-lock +flag ~empty Srcu-unlock \ range(srcu-rscs) as unmatched-srcu-unlock +flag ~empty (srcu-rscs^-1 ; srcu-rscs) \ id as multiple-srcu-matches + +(* Check for use of synchronize_srcu() inside an RCU critical section *) +flag ~empty rcu-rscs & (po ; [Sync-srcu] ; po) as invalid-sleep + +(* Validate SRCU dynamic match *) +flag ~empty different-values(srcu-rscs) as srcu-bad-value-match + +(* Compute marked and plain memory accesses *) +let Marked = (~M) | IW | ONCE | RELEASE | ACQUIRE | MB | RMW | + LKR | LKW | UL | LF | RL | RU | Srcu-lock | Srcu-unlock +let Plain = M \ Marked + +(* Redefine dependencies to include those carried through plain accesses *) +let carry-dep = (data ; [~ Srcu-unlock] ; rfi)* +let addr = carry-dep ; addr +let ctrl = carry-dep ; ctrl +let data = carry-dep ; data + +flag ~empty (if "lkmmv2" then 0 else _) + as this-model-requires-variant-higher-than-lkmmv1 -- cgit v1.3.1