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 --- include/net/netdev_lock.h | 155 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 155 insertions(+) create mode 100644 include/net/netdev_lock.h (limited to 'include/net/netdev_lock.h') diff --git a/include/net/netdev_lock.h b/include/net/netdev_lock.h new file mode 100644 index 000000000..9fb3e9385 --- /dev/null +++ b/include/net/netdev_lock.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _NET_NETDEV_LOCK_H +#define _NET_NETDEV_LOCK_H + +#include +#include +#include + +static inline bool netdev_trylock(struct net_device *dev) +{ + return mutex_trylock(&dev->lock); +} + +static inline void netdev_assert_locked(const struct net_device *dev) +{ + lockdep_assert_held(&dev->lock); +} + +static inline void +netdev_assert_locked_or_invisible(const struct net_device *dev) +{ + if (dev->reg_state == NETREG_REGISTERED || + dev->reg_state == NETREG_UNREGISTERING) + netdev_assert_locked(dev); +} + +static inline bool netdev_need_ops_lock(const struct net_device *dev) +{ + bool ret = dev->request_ops_lock || !!dev->queue_mgmt_ops; + +#if IS_ENABLED(CONFIG_NET_SHAPER) + ret |= !!dev->netdev_ops->net_shaper_ops; +#endif + + return ret; +} + +static inline void netdev_lock_ops(struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + netdev_lock(dev); +} + +static inline void netdev_unlock_ops(struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + netdev_unlock(dev); +} + +static inline void netdev_lock_ops_to_full(struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + netdev_assert_locked(dev); + else + netdev_lock(dev); +} + +static inline void netdev_unlock_full_to_ops(struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + netdev_assert_locked(dev); + else + netdev_unlock(dev); +} + +static inline void netdev_assert_locked_ops_compat(const struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + lockdep_assert_held(&dev->lock); + else + ASSERT_RTNL(); +} + +static inline void +netdev_assert_locked_ops_compat_or_invisible(const struct net_device *dev) +{ + if (dev->reg_state == NETREG_REGISTERED || + dev->reg_state == NETREG_UNREGISTERING) + netdev_assert_locked_ops_compat(dev); +} + +static inline void netdev_assert_locked_ops(const struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + netdev_assert_locked(dev); +} + +static inline void netdev_lock_ops_compat(struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + netdev_lock(dev); + else + rtnl_lock(); +} + +static inline void netdev_unlock_ops_compat(struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + netdev_unlock(dev); + else + rtnl_unlock(); +} + +/* Matching "ops protected" category from netdevice.h */ +static inline int netdev_is_locked_ops_compat(const struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + return lockdep_is_held(&dev->lock); + return lockdep_rtnl_is_held(); +} + +static inline int netdev_lock_cmp_fn(const struct lockdep_map *a, + const struct lockdep_map *b) +{ + if (a == b) + return 0; + + /* Allow locking multiple devices only under rtnl_lock, + * the exact order doesn't matter. + * Note that upper devices don't lock their ops, so nesting + * mostly happens in batched device removal for now. + */ + return lockdep_rtnl_is_held() ? -1 : 1; +} + +#define netdev_lockdep_set_classes(dev) \ +{ \ + static struct lock_class_key qdisc_tx_busylock_key; \ + static struct lock_class_key qdisc_xmit_lock_key; \ + static struct lock_class_key dev_addr_list_lock_key; \ + static struct lock_class_key dev_instance_lock_key; \ + unsigned int i; \ + \ + (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ + lockdep_set_class(&(dev)->addr_list_lock, \ + &dev_addr_list_lock_key); \ + lockdep_set_class(&(dev)->lock, \ + &dev_instance_lock_key); \ + lock_set_cmp_fn(&dev->lock, netdev_lock_cmp_fn, NULL); \ + for (i = 0; i < (dev)->num_tx_queues; i++) \ + lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \ + &qdisc_xmit_lock_key); \ +} + +#define netdev_lock_dereference(p, dev) \ + rcu_dereference_protected(p, lockdep_is_held(&(dev)->lock)) + +#define netdev_ops_lock_dereference(p, dev) \ + rcu_dereference_protected(p, netdev_is_locked_ops_compat(dev)) + +int netdev_debug_event(struct notifier_block *nb, unsigned long event, + void *ptr); + +#endif -- cgit v1.3.1