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, 63 insertions, 0 deletions

diff --git a/drivers/net/wireguard/allowedips.h b/drivers/net/wireguard/allowedips.h
new file mode 100644
index 000000000..931958cb6
--- /dev/null
+++ b/drivers/net/wireguard/allowedips.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#ifndef _WG_ALLOWEDIPS_H
+#define _WG_ALLOWEDIPS_H
+
+#include <linux/mutex.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+
+struct wg_peer;
+
+struct allowedips_node {
+	struct wg_peer __rcu *peer;
+	struct allowedips_node __rcu *bit[2];
+	u8 cidr, bit_at_a, bit_at_b, bitlen;
+	u8 bits[16] __aligned(__alignof(u64));
+
+	/* Keep rarely used members at bottom to be beyond cache line. */
+	unsigned long parent_bit_packed;
+	union {
+		struct list_head peer_list;
+		struct rcu_head rcu;
+	};
+};
+
+struct allowedips {
+	struct allowedips_node __rcu *root4;
+	struct allowedips_node __rcu *root6;
+	u64 seq;
+} __aligned(4); /* We pack the lower 2 bits of &root, but m68k only gives 16-bit alignment. */
+
+void wg_allowedips_init(struct allowedips *table);
+void wg_allowedips_free(struct allowedips *table, struct mutex *mutex);
+int wg_allowedips_insert_v4(struct allowedips *table, const struct in_addr *ip,
+			    u8 cidr, struct wg_peer *peer, struct mutex *lock);
+int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip,
+			    u8 cidr, struct wg_peer *peer, struct mutex *lock);
+int wg_allowedips_remove_v4(struct allowedips *table, const struct in_addr *ip,
+			    u8 cidr, struct wg_peer *peer, struct mutex *lock);
+int wg_allowedips_remove_v6(struct allowedips *table, const struct in6_addr *ip,
+			    u8 cidr, struct wg_peer *peer, struct mutex *lock);
+void wg_allowedips_remove_by_peer(struct allowedips *table,
+				  struct wg_peer *peer, struct mutex *lock);
+/* The ip input pointer should be __aligned(__alignof(u64))) */
+int wg_allowedips_read_node(struct allowedips_node *node, u8 ip[16], u8 *cidr);
+
+/* These return a strong reference to a peer: */
+struct wg_peer *wg_allowedips_lookup_dst(struct allowedips *table,
+					 struct sk_buff *skb);
+struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table,
+					 struct sk_buff *skb);
+
+#ifdef DEBUG
+bool wg_allowedips_selftest(void);
+#endif
+
+int wg_allowedips_slab_init(void);
+void wg_allowedips_slab_uninit(void);
+
+#endif /* _WG_ALLOWEDIPS_H */