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, 318 insertions, 0 deletions

diff --git a/net/mac80211/fils_aead.c b/net/mac80211/fils_aead.c
new file mode 100644
index 000000000..293590976
--- /dev/null
+++ b/net/mac80211/fils_aead.c
@@ -0,0 +1,318 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * FILS AEAD for (Re)Association Request/Response frames
+ * Copyright 2016, Qualcomm Atheros, Inc.
+ */
+
+#include <crypto/aes-cbc-macs.h>
+#include <crypto/skcipher.h>
+#include <crypto/utils.h>
+
+#include "ieee80211_i.h"
+#include "fils_aead.h"
+
+static void gf_mulx(u8 *pad)
+{
+	u64 a = get_unaligned_be64(pad);
+	u64 b = get_unaligned_be64(pad + 8);
+
+	put_unaligned_be64((a << 1) | (b >> 63), pad);
+	put_unaligned_be64((b << 1) ^ ((a >> 63) ? 0x87 : 0), pad + 8);
+}
+
+static int aes_s2v(const u8 *in_key, size_t key_len,
+		   size_t num_elem, const u8 *addr[], size_t len[], u8 *v)
+{
+	u8 d[AES_BLOCK_SIZE], tmp[AES_BLOCK_SIZE] = {};
+	struct aes_cmac_key key __cleanup(aes_cmac_zeroize_key);
+	struct aes_cmac_ctx ctx;
+	size_t i;
+	int res;
+
+	res = aes_cmac_preparekey(&key, in_key, key_len);
+	if (res)
+		return res;
+
+	/* D = AES-CMAC(K, <zero>) */
+	aes_cmac(&key, tmp, AES_BLOCK_SIZE, d);
+
+	for (i = 0; i < num_elem - 1; i++) {
+		/* D = dbl(D) xor AES_CMAC(K, Si) */
+		gf_mulx(d); /* dbl */
+		aes_cmac(&key, addr[i], len[i], tmp);
+		crypto_xor(d, tmp, AES_BLOCK_SIZE);
+	}
+
+	aes_cmac_init(&ctx, &key);
+
+	if (len[i] >= AES_BLOCK_SIZE) {
+		/* len(Sn) >= 128 */
+		/* T = Sn xorend D */
+		aes_cmac_update(&ctx, addr[i], len[i] - AES_BLOCK_SIZE);
+		crypto_xor(d, addr[i] + len[i] - AES_BLOCK_SIZE,
+			   AES_BLOCK_SIZE);
+	} else {
+		/* len(Sn) < 128 */
+		/* T = dbl(D) xor pad(Sn) */
+		gf_mulx(d); /* dbl */
+		crypto_xor(d, addr[i], len[i]);
+		d[len[i]] ^= 0x80;
+	}
+	/* V = AES-CMAC(K, T) */
+	aes_cmac_update(&ctx, d, AES_BLOCK_SIZE);
+	aes_cmac_final(&ctx, v);
+
+	return 0;
+}
+
+/* Note: addr[] and len[] needs to have one extra slot at the end. */
+static int aes_siv_encrypt(const u8 *key, size_t key_len,
+			   const u8 *plain, size_t plain_len,
+			   size_t num_elem, const u8 *addr[],
+			   size_t len[], u8 *out)
+{
+	u8 v[AES_BLOCK_SIZE];
+	struct crypto_skcipher *tfm2;
+	struct skcipher_request *req;
+	int res;
+	struct scatterlist src[1], dst[1];
+	u8 *tmp;
+
+	key_len /= 2; /* S2V key || CTR key */
+
+	addr[num_elem] = plain;
+	len[num_elem] = plain_len;
+	num_elem++;
+
+	/* S2V */
+	res = aes_s2v(key /* K1 */, key_len, num_elem, addr, len, v);
+	if (res)
+		return res;
+
+	/* Use a temporary buffer of the plaintext to handle need for
+	 * overwriting this during AES-CTR.
+	 */
+	tmp = kmemdup(plain, plain_len, GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	/* IV for CTR before encrypted data */
+	memcpy(out, v, AES_BLOCK_SIZE);
+
+	/* Synthetic IV to be used as the initial counter in CTR:
+	 * Q = V bitand (1^64 || 0^1 || 1^31 || 0^1 || 1^31)
+	 */
+	v[8] &= 0x7f;
+	v[12] &= 0x7f;
+
+	/* CTR */
+
+	tfm2 = crypto_alloc_skcipher("ctr(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm2)) {
+		kfree(tmp);
+		return PTR_ERR(tfm2);
+	}
+	/* K2 for CTR */
+	res = crypto_skcipher_setkey(tfm2, key + key_len, key_len);
+	if (res)
+		goto fail;
+
+	req = skcipher_request_alloc(tfm2, GFP_KERNEL);
+	if (!req) {
+		res = -ENOMEM;
+		goto fail;
+	}
+
+	sg_init_one(src, tmp, plain_len);
+	sg_init_one(dst, out + AES_BLOCK_SIZE, plain_len);
+	skcipher_request_set_crypt(req, src, dst, plain_len, v);
+	res = crypto_skcipher_encrypt(req);
+	skcipher_request_free(req);
+fail:
+	kfree(tmp);
+	crypto_free_skcipher(tfm2);
+	return res;
+}
+
+/* Note: addr[] and len[] needs to have one extra slot at the end. */
+static int aes_siv_decrypt(const u8 *key, size_t key_len,
+			   const u8 *iv_crypt, size_t iv_c_len,
+			   size_t num_elem, const u8 *addr[], size_t len[],
+			   u8 *out)
+{
+	struct crypto_skcipher *tfm2;
+	struct skcipher_request *req;
+	struct scatterlist src[1], dst[1];
+	size_t crypt_len;
+	int res;
+	u8 frame_iv[AES_BLOCK_SIZE], iv[AES_BLOCK_SIZE];
+	u8 check[AES_BLOCK_SIZE];
+
+	crypt_len = iv_c_len - AES_BLOCK_SIZE;
+	key_len /= 2; /* S2V key || CTR key */
+	addr[num_elem] = out;
+	len[num_elem] = crypt_len;
+	num_elem++;
+
+	memcpy(iv, iv_crypt, AES_BLOCK_SIZE);
+	memcpy(frame_iv, iv_crypt, AES_BLOCK_SIZE);
+
+	/* Synthetic IV to be used as the initial counter in CTR:
+	 * Q = V bitand (1^64 || 0^1 || 1^31 || 0^1 || 1^31)
+	 */
+	iv[8] &= 0x7f;
+	iv[12] &= 0x7f;
+
+	/* CTR */
+
+	tfm2 = crypto_alloc_skcipher("ctr(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm2))
+		return PTR_ERR(tfm2);
+	/* K2 for CTR */
+	res = crypto_skcipher_setkey(tfm2, key + key_len, key_len);
+	if (res) {
+		crypto_free_skcipher(tfm2);
+		return res;
+	}
+
+	req = skcipher_request_alloc(tfm2, GFP_KERNEL);
+	if (!req) {
+		crypto_free_skcipher(tfm2);
+		return -ENOMEM;
+	}
+
+	sg_init_one(src, iv_crypt + AES_BLOCK_SIZE, crypt_len);
+	sg_init_one(dst, out, crypt_len);
+	skcipher_request_set_crypt(req, src, dst, crypt_len, iv);
+	res = crypto_skcipher_decrypt(req);
+	skcipher_request_free(req);
+	crypto_free_skcipher(tfm2);
+	if (res)
+		return res;
+
+	/* S2V */
+	res = aes_s2v(key /* K1 */, key_len, num_elem, addr, len, check);
+	if (res)
+		return res;
+	if (memcmp(check, frame_iv, AES_BLOCK_SIZE) != 0)
+		return -EINVAL;
+	return 0;
+}
+
+int fils_encrypt_assoc_req(struct sk_buff *skb,
+			   struct ieee80211_mgd_assoc_data *assoc_data)
+{
+	struct ieee80211_mgmt *mgmt = (void *)skb->data;
+	u8 *capab, *ies, *encr;
+	const u8 *addr[5 + 1];
+	const struct element *session;
+	size_t len[5 + 1];
+	size_t crypt_len;
+
+	if (ieee80211_is_reassoc_req(mgmt->frame_control)) {
+		capab = (u8 *)&mgmt->u.reassoc_req.capab_info;
+		ies = mgmt->u.reassoc_req.variable;
+	} else {
+		capab = (u8 *)&mgmt->u.assoc_req.capab_info;
+		ies = mgmt->u.assoc_req.variable;
+	}
+
+	session = cfg80211_find_ext_elem(WLAN_EID_EXT_FILS_SESSION,
+					 ies, skb->data + skb->len - ies);
+	if (!session || session->datalen != 1 + 8)
+		return -EINVAL;
+	/* encrypt after FILS Session element */
+	encr = (u8 *)session->data + 1 + 8;
+
+	/* AES-SIV AAD vectors */
+
+	/* The STA's MAC address */
+	addr[0] = mgmt->sa;
+	len[0] = ETH_ALEN;
+	/* The AP's BSSID */
+	addr[1] = mgmt->da;
+	len[1] = ETH_ALEN;
+	/* The STA's nonce */
+	addr[2] = assoc_data->fils_nonces;
+	len[2] = FILS_NONCE_LEN;
+	/* The AP's nonce */
+	addr[3] = &assoc_data->fils_nonces[FILS_NONCE_LEN];
+	len[3] = FILS_NONCE_LEN;
+	/* The (Re)Association Request frame from the Capability Information
+	 * field to the FILS Session element (both inclusive).
+	 */
+	addr[4] = capab;
+	len[4] = encr - capab;
+
+	crypt_len = skb->data + skb->len - encr;
+	skb_put(skb, AES_BLOCK_SIZE);
+	return aes_siv_encrypt(assoc_data->fils_kek, assoc_data->fils_kek_len,
+			       encr, crypt_len, 5, addr, len, encr);
+}
+
+int fils_decrypt_assoc_resp(struct ieee80211_sub_if_data *sdata,
+			    u8 *frame, size_t *frame_len,
+			    struct ieee80211_mgd_assoc_data *assoc_data)
+{
+	struct ieee80211_mgmt *mgmt = (void *)frame;
+	u8 *capab, *ies, *encr;
+	const u8 *addr[5 + 1];
+	const struct element *session;
+	size_t len[5 + 1];
+	int res;
+	size_t crypt_len;
+
+	if (*frame_len < 24 + 6)
+		return -EINVAL;
+
+	capab = (u8 *)&mgmt->u.assoc_resp.capab_info;
+	ies = mgmt->u.assoc_resp.variable;
+	session = cfg80211_find_ext_elem(WLAN_EID_EXT_FILS_SESSION,
+					 ies, frame + *frame_len - ies);
+	if (!session || session->datalen != 1 + 8) {
+		mlme_dbg(sdata,
+			 "No (valid) FILS Session element in (Re)Association Response frame from %pM",
+			 mgmt->sa);
+		return -EINVAL;
+	}
+	/* decrypt after FILS Session element */
+	encr = (u8 *)session->data + 1 + 8;
+
+	/* AES-SIV AAD vectors */
+
+	/* The AP's BSSID */
+	addr[0] = mgmt->sa;
+	len[0] = ETH_ALEN;
+	/* The STA's MAC address */
+	addr[1] = mgmt->da;
+	len[1] = ETH_ALEN;
+	/* The AP's nonce */
+	addr[2] = &assoc_data->fils_nonces[FILS_NONCE_LEN];
+	len[2] = FILS_NONCE_LEN;
+	/* The STA's nonce */
+	addr[3] = assoc_data->fils_nonces;
+	len[3] = FILS_NONCE_LEN;
+	/* The (Re)Association Response frame from the Capability Information
+	 * field to the FILS Session element (both inclusive).
+	 */
+	addr[4] = capab;
+	len[4] = encr - capab;
+
+	crypt_len = frame + *frame_len - encr;
+	if (crypt_len < AES_BLOCK_SIZE) {
+		mlme_dbg(sdata,
+			 "Not enough room for AES-SIV data after FILS Session element in (Re)Association Response frame from %pM",
+			 mgmt->sa);
+		return -EINVAL;
+	}
+	res = aes_siv_decrypt(assoc_data->fils_kek, assoc_data->fils_kek_len,
+			      encr, crypt_len, 5, addr, len, encr);
+	if (res != 0) {
+		mlme_dbg(sdata,
+			 "AES-SIV decryption of (Re)Association Response frame from %pM failed",
+			 mgmt->sa);
+		return res;
+	}
+	*frame_len -= AES_BLOCK_SIZE;
+	return 0;
+}