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/dsa/user.h | 71 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 71 insertions(+) create mode 100644 net/dsa/user.h (limited to 'net/dsa/user.h') diff --git a/net/dsa/user.h b/net/dsa/user.h new file mode 100644 index 000000000..016884bea --- /dev/null +++ b/net/dsa/user.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_USER_H +#define __DSA_USER_H + +#include +#include +#include +#include +#include +#include +#include + +struct net_device; +struct netlink_ext_ack; + +extern struct notifier_block dsa_user_switchdev_notifier; +extern struct notifier_block dsa_user_switchdev_blocking_notifier; + +struct dsa_user_priv { + /* Copy of CPU port xmit for faster access in user transmit hot path */ + struct sk_buff * (*xmit)(struct sk_buff *skb, + struct net_device *dev); + + struct gro_cells gcells; + + /* DSA port data, such as switch, port index, etc. */ + struct dsa_port *dp; + +#ifdef CONFIG_NET_POLL_CONTROLLER + struct netpoll *netpoll; +#endif + + /* TC context */ + struct list_head mall_tc_list; +}; + +void dsa_user_mii_bus_init(struct dsa_switch *ds); +int dsa_user_create(struct dsa_port *dp); +void dsa_user_destroy(struct net_device *user_dev); +int dsa_user_suspend(struct net_device *user_dev); +int dsa_user_resume(struct net_device *user_dev); +int dsa_user_register_notifier(void); +void dsa_user_unregister_notifier(void); +int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr); +void dsa_user_host_uc_uninstall(struct net_device *dev); +void dsa_user_sync_ha(struct net_device *dev); +void dsa_user_unsync_ha(struct net_device *dev); +void dsa_user_setup_tagger(struct net_device *user); +int dsa_user_change_mtu(struct net_device *dev, int new_mtu); +int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit, + struct netlink_ext_ack *extack); +int dsa_user_manage_vlan_filtering(struct net_device *dev, + bool vlan_filtering); + +static inline struct dsa_port *dsa_user_to_port(const struct net_device *dev) +{ + struct dsa_user_priv *p = netdev_priv(dev); + + return p->dp; +} + +static inline struct net_device * +dsa_user_to_conduit(const struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + + return dsa_port_to_conduit(dp); +} + +#endif -- cgit v1.3.1