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/openvswitch/meter.h | 62 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) create mode 100644 net/openvswitch/meter.h (limited to 'net/openvswitch/meter.h') diff --git a/net/openvswitch/meter.h b/net/openvswitch/meter.h new file mode 100644 index 000000000..8bbf983cd --- /dev/null +++ b/net/openvswitch/meter.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2017 Nicira, Inc. + */ + +#ifndef METER_H +#define METER_H 1 + +#include +#include +#include +#include +#include +#include +#include + +#include "flow.h" +struct datapath; + +#define DP_MAX_BANDS 1 +#define DP_METER_ARRAY_SIZE_MIN BIT_ULL(10) +#define DP_METER_NUM_MAX (200000UL) + +struct dp_meter_band { + u32 type; + u32 rate; + u32 burst_size; + u64 bucket; /* 1/1000 packets, or in bits */ + struct ovs_flow_stats stats; +}; + +struct dp_meter { + spinlock_t lock; /* Per meter lock */ + struct rcu_head rcu; + u32 id; + u16 kbps:1, keep_stats:1; + u16 n_bands; + u32 max_delta_t; + u64 used; + struct ovs_flow_stats stats; + struct dp_meter_band bands[] __counted_by(n_bands); +}; + +struct dp_meter_instance { + struct rcu_head rcu; + u32 n_meters; + struct dp_meter __rcu *dp_meters[] __counted_by(n_meters); +}; + +struct dp_meter_table { + struct dp_meter_instance __rcu *ti; + u32 count; + u32 max_meters_allowed; +}; + +extern struct genl_family dp_meter_genl_family; +int ovs_meters_init(struct datapath *dp); +void ovs_meters_exit(struct datapath *dp); +bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb, + struct sw_flow_key *key, u32 meter_id); + +#endif /* meter.h */ -- cgit v1.3.1