x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

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) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 77 insertions, 0 deletions

diff --git a/include/net/arp.h b/include/net/arp.h
new file mode 100644
index 000000000..e8747e071
--- /dev/null
+++ b/include/net/arp.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* linux/net/inet/arp.h */
+#ifndef _ARP_H
+#define _ARP_H
+
+#include <linux/if_arp.h>
+#include <linux/hash.h>
+#include <net/neighbour.h>
+
+
+extern struct neigh_table arp_tbl;
+
+static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32 *hash_rnd)
+{
+	u32 key = *(const u32 *)pkey;
+	u32 val = key ^ hash32_ptr(dev);
+
+	return val * hash_rnd[0];
+}
+
+#ifdef CONFIG_INET
+static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key)
+{
+	if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
+		key = INADDR_ANY;
+
+	return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev);
+}
+#else
+static inline
+struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key)
+{
+	return NULL;
+}
+#endif
+
+static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 key)
+{
+	struct neighbour *n;
+
+	rcu_read_lock();
+	n = __ipv4_neigh_lookup_noref(dev, key);
+	if (n && !refcount_inc_not_zero(&n->refcnt))
+		n = NULL;
+	rcu_read_unlock();
+
+	return n;
+}
+
+static inline void __ipv4_confirm_neigh(struct net_device *dev, u32 key)
+{
+	struct neighbour *n;
+
+	rcu_read_lock();
+	n = __ipv4_neigh_lookup_noref(dev, key);
+	neigh_confirm(n);
+	rcu_read_unlock();
+}
+
+void arp_init(void);
+int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg);
+void arp_send(int type, int ptype, __be32 dest_ip,
+	      struct net_device *dev, __be32 src_ip,
+	      const unsigned char *dest_hw,
+	      const unsigned char *src_hw, const unsigned char *th);
+int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir);
+void arp_ifdown(struct net_device *dev);
+int arp_invalidate(struct net_device *dev, __be32 ip, bool force);
+
+struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip,
+			   struct net_device *dev, __be32 src_ip,
+			   const unsigned char *dest_hw,
+			   const unsigned char *src_hw,
+			   const unsigned char *target_hw);
+void arp_xmit(struct sk_buff *skb);
+
+#endif	/* _ARP_H */