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, 128 insertions, 0 deletions

diff --git a/drivers/net/wireguard/messages.h b/drivers/net/wireguard/messages.h
new file mode 100644
index 000000000..208da7267
--- /dev/null
+++ b/drivers/net/wireguard/messages.h
@@ -0,0 +1,128 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#ifndef _WG_MESSAGES_H
+#define _WG_MESSAGES_H
+
+#include <crypto/curve25519.h>
+#include <crypto/chacha20poly1305.h>
+#include <crypto/blake2s.h>
+
+#include <linux/kernel.h>
+#include <linux/param.h>
+#include <linux/skbuff.h>
+
+enum noise_lengths {
+	NOISE_PUBLIC_KEY_LEN = CURVE25519_KEY_SIZE,
+	NOISE_SYMMETRIC_KEY_LEN = CHACHA20POLY1305_KEY_SIZE,
+	NOISE_TIMESTAMP_LEN = sizeof(u64) + sizeof(u32),
+	NOISE_AUTHTAG_LEN = CHACHA20POLY1305_AUTHTAG_SIZE,
+	NOISE_HASH_LEN = BLAKE2S_HASH_SIZE
+};
+
+#define noise_encrypted_len(plain_len) ((plain_len) + NOISE_AUTHTAG_LEN)
+
+enum cookie_values {
+	COOKIE_SECRET_MAX_AGE = 2 * 60,
+	COOKIE_SECRET_LATENCY = 5,
+	COOKIE_NONCE_LEN = XCHACHA20POLY1305_NONCE_SIZE,
+	COOKIE_LEN = 16
+};
+
+enum counter_values {
+	COUNTER_BITS_TOTAL = 8192,
+	COUNTER_REDUNDANT_BITS = BITS_PER_LONG,
+	COUNTER_WINDOW_SIZE = COUNTER_BITS_TOTAL - COUNTER_REDUNDANT_BITS
+};
+
+enum limits {
+	REKEY_AFTER_MESSAGES = 1ULL << 60,
+	REJECT_AFTER_MESSAGES = U64_MAX - COUNTER_WINDOW_SIZE - 1,
+	REKEY_TIMEOUT = 5,
+	REKEY_TIMEOUT_JITTER_MAX_JIFFIES = HZ / 3,
+	REKEY_AFTER_TIME = 120,
+	REJECT_AFTER_TIME = 180,
+	INITIATIONS_PER_SECOND = 50,
+	MAX_PEERS_PER_DEVICE = 1U << 20,
+	KEEPALIVE_TIMEOUT = 10,
+	MAX_TIMER_HANDSHAKES = 90 / REKEY_TIMEOUT,
+	MAX_QUEUED_INCOMING_HANDSHAKES = 4096, /* TODO: replace this with DQL */
+	MAX_STAGED_PACKETS = 128,
+	MAX_QUEUED_PACKETS = 1024 /* TODO: replace this with DQL */
+};
+
+enum message_type {
+	MESSAGE_INVALID = 0,
+	MESSAGE_HANDSHAKE_INITIATION = 1,
+	MESSAGE_HANDSHAKE_RESPONSE = 2,
+	MESSAGE_HANDSHAKE_COOKIE = 3,
+	MESSAGE_DATA = 4
+};
+
+struct message_header {
+	/* The actual layout of this that we want is:
+	 * u8 type
+	 * u8 reserved_zero[3]
+	 *
+	 * But it turns out that by encoding this as little endian,
+	 * we achieve the same thing, and it makes checking faster.
+	 */
+	__le32 type;
+};
+
+struct message_macs {
+	u8 mac1[COOKIE_LEN];
+	u8 mac2[COOKIE_LEN];
+};
+
+struct message_handshake_initiation {
+	struct message_header header;
+	__le32 sender_index;
+	u8 unencrypted_ephemeral[NOISE_PUBLIC_KEY_LEN];
+	u8 encrypted_static[noise_encrypted_len(NOISE_PUBLIC_KEY_LEN)];
+	u8 encrypted_timestamp[noise_encrypted_len(NOISE_TIMESTAMP_LEN)];
+	struct message_macs macs;
+};
+
+struct message_handshake_response {
+	struct message_header header;
+	__le32 sender_index;
+	__le32 receiver_index;
+	u8 unencrypted_ephemeral[NOISE_PUBLIC_KEY_LEN];
+	u8 encrypted_nothing[noise_encrypted_len(0)];
+	struct message_macs macs;
+};
+
+struct message_handshake_cookie {
+	struct message_header header;
+	__le32 receiver_index;
+	u8 nonce[COOKIE_NONCE_LEN];
+	u8 encrypted_cookie[noise_encrypted_len(COOKIE_LEN)];
+};
+
+struct message_data {
+	struct message_header header;
+	__le32 key_idx;
+	__le64 counter;
+	u8 encrypted_data[];
+};
+
+#define message_data_len(plain_len) \
+	(noise_encrypted_len(plain_len) + sizeof(struct message_data))
+
+enum message_alignments {
+	MESSAGE_PADDING_MULTIPLE = 16,
+	MESSAGE_MINIMUM_LENGTH = message_data_len(0)
+};
+
+#define SKB_HEADER_LEN                                       \
+	(max(sizeof(struct iphdr), sizeof(struct ipv6hdr)) + \
+	 sizeof(struct udphdr) + NET_SKB_PAD)
+#define DATA_PACKET_HEAD_ROOM \
+	ALIGN(sizeof(struct message_data) + SKB_HEADER_LEN, 4)
+
+enum { HANDSHAKE_DSCP = 0x88 /* AF41, plus 00 ECN */ };
+
+#endif /* _WG_MESSAGES_H */