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, 99 insertions, 0 deletions

diff --git a/net/mac802154/llsec.h b/net/mac802154/llsec.h
new file mode 100644
index 000000000..ddeb79228
--- /dev/null
+++ b/net/mac802154/llsec.h
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014 Fraunhofer ITWM
+ *
+ * Written by:
+ * Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
+ */
+
+#ifndef MAC802154_LLSEC_H
+#define MAC802154_LLSEC_H
+
+#include <linux/slab.h>
+#include <linux/hashtable.h>
+#include <linux/kref.h>
+#include <linux/spinlock.h>
+#include <net/af_ieee802154.h>
+#include <net/ieee802154_netdev.h>
+
+struct mac802154_llsec_key {
+	struct ieee802154_llsec_key key;
+
+	/* one tfm for each authsize (4/8/16) */
+	struct crypto_aead *tfm[3];
+	struct crypto_sync_skcipher *tfm0;
+
+	struct kref ref;
+};
+
+struct mac802154_llsec_device_key {
+	struct ieee802154_llsec_device_key devkey;
+
+	struct rcu_head rcu;
+};
+
+struct mac802154_llsec_device {
+	struct ieee802154_llsec_device dev;
+
+	struct hlist_node bucket_s;
+	struct hlist_node bucket_hw;
+
+	/* protects dev.frame_counter and the elements of dev.keys */
+	spinlock_t lock;
+
+	struct rcu_head rcu;
+};
+
+struct mac802154_llsec_seclevel {
+	struct ieee802154_llsec_seclevel level;
+
+	struct rcu_head rcu;
+};
+
+struct mac802154_llsec {
+	struct ieee802154_llsec_params params;
+	struct ieee802154_llsec_table table;
+
+	DECLARE_HASHTABLE(devices_short, 6);
+	DECLARE_HASHTABLE(devices_hw, 6);
+
+	/* protects params, all other fields are fine with RCU */
+	rwlock_t lock;
+};
+
+void mac802154_llsec_init(struct mac802154_llsec *sec);
+void mac802154_llsec_destroy(struct mac802154_llsec *sec);
+
+int mac802154_llsec_get_params(struct mac802154_llsec *sec,
+			       struct ieee802154_llsec_params *params);
+int mac802154_llsec_set_params(struct mac802154_llsec *sec,
+			       const struct ieee802154_llsec_params *params,
+			       int changed);
+
+int mac802154_llsec_key_add(struct mac802154_llsec *sec,
+			    const struct ieee802154_llsec_key_id *id,
+			    const struct ieee802154_llsec_key *key);
+int mac802154_llsec_key_del(struct mac802154_llsec *sec,
+			    const struct ieee802154_llsec_key_id *key);
+
+int mac802154_llsec_dev_add(struct mac802154_llsec *sec,
+			    const struct ieee802154_llsec_device *dev);
+int mac802154_llsec_dev_del(struct mac802154_llsec *sec,
+			    __le64 device_addr);
+
+int mac802154_llsec_devkey_add(struct mac802154_llsec *sec,
+			       __le64 dev_addr,
+			       const struct ieee802154_llsec_device_key *key);
+int mac802154_llsec_devkey_del(struct mac802154_llsec *sec,
+			       __le64 dev_addr,
+			       const struct ieee802154_llsec_device_key *key);
+
+int mac802154_llsec_seclevel_add(struct mac802154_llsec *sec,
+				 const struct ieee802154_llsec_seclevel *sl);
+int mac802154_llsec_seclevel_del(struct mac802154_llsec *sec,
+				 const struct ieee802154_llsec_seclevel *sl);
+
+int mac802154_llsec_encrypt(struct mac802154_llsec *sec, struct sk_buff *skb);
+int mac802154_llsec_decrypt(struct mac802154_llsec *sec, struct sk_buff *skb);
+
+#endif /* MAC802154_LLSEC_H */