forked from ~ljy/RK356X_SDK_RELEASE
blame | history | patch | commit | commitdiff
hc
2024-10-09 244b2c5ca8b14627e4a17755e5922221e121c771 
 kernel/net/ipv4/esp4.c
....@@ -1,3 +1,4 @@
1
+// SPDX-License-Identifier: GPL-2.0-only
12 #define pr_fmt(fmt) "IPsec: " fmt
23 
34 #include <crypto/aead.h>
....@@ -17,6 +18,8 @@
1718 #include <net/icmp.h>
1819 #include <net/protocol.h>
1920 #include <net/udp.h>
21
+#include <net/tcp.h>
22
+#include <net/espintcp.h>
2023 
2124 #include <linux/highmem.h>
2225 
....@@ -31,8 +34,6 @@
3134 };
3235 
3336 #define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0]))
34
-
35
-static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
3637 
3738 /*
3839  * Allocate an AEAD request structure with extra space for SG and IV.
....@@ -118,6 +119,132 @@
118119 			put_page(sg_page(sg));
119120 }
120121 
122
+#ifdef CONFIG_INET_ESPINTCP
123
+struct esp_tcp_sk {
124
+	struct sock *sk;
125
+	struct rcu_head rcu;
126
+};
127
+
128
+static void esp_free_tcp_sk(struct rcu_head *head)
129
+{
130
+	struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu);
131
+
132
+	sock_put(esk->sk);
133
+	kfree(esk);
134
+}
135
+
136
+static struct sock *esp_find_tcp_sk(struct xfrm_state *x)
137
+{
138
+	struct xfrm_encap_tmpl *encap = x->encap;
139
+	struct esp_tcp_sk *esk;
140
+	__be16 sport, dport;
141
+	struct sock *nsk;
142
+	struct sock *sk;
143
+
144
+	sk = rcu_dereference(x->encap_sk);
145
+	if (sk && sk->sk_state == TCP_ESTABLISHED)
146
+		return sk;
147
+
148
+	spin_lock_bh(&x->lock);
149
+	sport = encap->encap_sport;
150
+	dport = encap->encap_dport;
151
+	nsk = rcu_dereference_protected(x->encap_sk,
152
+					lockdep_is_held(&x->lock));
153
+	if (sk && sk == nsk) {
154
+		esk = kmalloc(sizeof(*esk), GFP_ATOMIC);
155
+		if (!esk) {
156
+			spin_unlock_bh(&x->lock);
157
+			return ERR_PTR(-ENOMEM);
158
+		}
159
+		RCU_INIT_POINTER(x->encap_sk, NULL);
160
+		esk->sk = sk;
161
+		call_rcu(&esk->rcu, esp_free_tcp_sk);
162
+	}
163
+	spin_unlock_bh(&x->lock);
164
+
165
+	sk = inet_lookup_established(xs_net(x), &tcp_hashinfo, x->id.daddr.a4,
166
+				     dport, x->props.saddr.a4, sport, 0);
167
+	if (!sk)
168
+		return ERR_PTR(-ENOENT);
169
+
170
+	if (!tcp_is_ulp_esp(sk)) {
171
+		sock_put(sk);
172
+		return ERR_PTR(-EINVAL);
173
+	}
174
+
175
+	spin_lock_bh(&x->lock);
176
+	nsk = rcu_dereference_protected(x->encap_sk,
177
+					lockdep_is_held(&x->lock));
178
+	if (encap->encap_sport != sport ||
179
+	    encap->encap_dport != dport) {
180
+		sock_put(sk);
181
+		sk = nsk ?: ERR_PTR(-EREMCHG);
182
+	} else if (sk == nsk) {
183
+		sock_put(sk);
184
+	} else {
185
+		rcu_assign_pointer(x->encap_sk, sk);
186
+	}
187
+	spin_unlock_bh(&x->lock);
188
+
189
+	return sk;
190
+}
191
+
192
+static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
193
+{
194
+	struct sock *sk;
195
+	int err;
196
+
197
+	rcu_read_lock();
198
+
199
+	sk = esp_find_tcp_sk(x);
200
+	err = PTR_ERR_OR_ZERO(sk);
201
+	if (err)
202
+		goto out;
203
+
204
+	bh_lock_sock(sk);
205
+	if (sock_owned_by_user(sk))
206
+		err = espintcp_queue_out(sk, skb);
207
+	else
208
+		err = espintcp_push_skb(sk, skb);
209
+	bh_unlock_sock(sk);
210
+
211
+out:
212
+	rcu_read_unlock();
213
+	return err;
214
+}
215
+
216
+static int esp_output_tcp_encap_cb(struct net *net, struct sock *sk,
217
+				   struct sk_buff *skb)
218
+{
219
+	struct dst_entry *dst = skb_dst(skb);
220
+	struct xfrm_state *x = dst->xfrm;
221
+
222
+	return esp_output_tcp_finish(x, skb);
223
+}
224
+
225
+static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb)
226
+{
227
+	int err;
228
+
229
+	local_bh_disable();
230
+	err = xfrm_trans_queue_net(xs_net(x), skb, esp_output_tcp_encap_cb);
231
+	local_bh_enable();
232
+
233
+	/* EINPROGRESS just happens to do the right thing.  It
234
+	 * actually means that the skb has been consumed and
235
+	 * isn't coming back.
236
+	 */
237
+	return err ?: -EINPROGRESS;
238
+}
239
+#else
240
+static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb)
241
+{
242
+	kfree_skb(skb);
243
+
244
+	return -EOPNOTSUPP;
245
+}
246
+#endif
247
+
121248 static void esp_output_done(struct crypto_async_request *base, int err)
122249 {
123250 	struct sk_buff *skb = base->data;
....@@ -125,10 +252,13 @@
125252 	void *tmp;
126253 	struct xfrm_state *x;
127254 
128
-	if (xo && (xo->flags & XFRM_DEV_RESUME))
129
-		x = skb->sp->xvec[skb->sp->len - 1];
130
-	else
255
+	if (xo && (xo->flags & XFRM_DEV_RESUME)) {
256
+		struct sec_path *sp = skb_sec_path(skb);
257
+
258
+		x = sp->xvec[sp->len - 1];
259
+	} else {
131260 		x = skb_dst(skb)->xfrm;
261
+	}
132262 
133263 	tmp = ESP_SKB_CB(skb)->tmp;
134264 	esp_ssg_unref(x, tmp);
....@@ -145,7 +275,11 @@
145275 		secpath_reset(skb);
146276 		xfrm_dev_resume(skb);
147277 	} else {
148
-		xfrm_output_resume(skb, err);
278
+		if (!err &&
279
+		    x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
280
+			esp_output_tail_tcp(x, skb);
281
+		else
282
+			xfrm_output_resume(skb, err);
149283 	}
150284 }
151285 
....@@ -207,31 +341,79 @@
207341 	esp_output_done(base, err);
208342 }
209343 
210
-static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto)
344
+static struct ip_esp_hdr *esp_output_udp_encap(struct sk_buff *skb,
345
+					       int encap_type,
346
+					       struct esp_info *esp,
347
+					       __be16 sport,
348
+					       __be16 dport)
211349 {
212
-	/* Fill padding... */
213
-	if (tfclen) {
214
-		memset(tail, 0, tfclen);
215
-		tail += tfclen;
216
-	}
217
-	do {
218
-		int i;
219
-		for (i = 0; i < plen - 2; i++)
220
-			tail[i] = i + 1;
221
-	} while (0);
222
-	tail[plen - 2] = plen - 2;
223
-	tail[plen - 1] = proto;
224
-}
225
-
226
-static int esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
227
-{
228
-	int encap_type;
229350 	struct udphdr *uh;
230351 	__be32 *udpdata32;
231
-	__be16 sport, dport;
232
-	struct xfrm_encap_tmpl *encap = x->encap;
233
-	struct ip_esp_hdr *esph = esp->esph;
234352 	unsigned int len;
353
+
354
+	len = skb->len + esp->tailen - skb_transport_offset(skb);
355
+	if (len + sizeof(struct iphdr) > IP_MAX_MTU)
356
+		return ERR_PTR(-EMSGSIZE);
357
+
358
+	uh = (struct udphdr *)esp->esph;
359
+	uh->source = sport;
360
+	uh->dest = dport;
361
+	uh->len = htons(len);
362
+	uh->check = 0;
363
+
364
+	*skb_mac_header(skb) = IPPROTO_UDP;
365
+
366
+	if (encap_type == UDP_ENCAP_ESPINUDP_NON_IKE) {
367
+		udpdata32 = (__be32 *)(uh + 1);
368
+		udpdata32[0] = udpdata32[1] = 0;
369
+		return (struct ip_esp_hdr *)(udpdata32 + 2);
370
+	}
371
+
372
+	return (struct ip_esp_hdr *)(uh + 1);
373
+}
374
+
375
+#ifdef CONFIG_INET_ESPINTCP
376
+static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x,
377
+						    struct sk_buff *skb,
378
+						    struct esp_info *esp)
379
+{
380
+	__be16 *lenp = (void *)esp->esph;
381
+	struct ip_esp_hdr *esph;
382
+	unsigned int len;
383
+	struct sock *sk;
384
+
385
+	len = skb->len + esp->tailen - skb_transport_offset(skb);
386
+	if (len > IP_MAX_MTU)
387
+		return ERR_PTR(-EMSGSIZE);
388
+
389
+	rcu_read_lock();
390
+	sk = esp_find_tcp_sk(x);
391
+	rcu_read_unlock();
392
+
393
+	if (IS_ERR(sk))
394
+		return ERR_CAST(sk);
395
+
396
+	*lenp = htons(len);
397
+	esph = (struct ip_esp_hdr *)(lenp + 1);
398
+
399
+	return esph;
400
+}
401
+#else
402
+static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x,
403
+						    struct sk_buff *skb,
404
+						    struct esp_info *esp)
405
+{
406
+	return ERR_PTR(-EOPNOTSUPP);
407
+}
408
+#endif
409
+
410
+static int esp_output_encap(struct xfrm_state *x, struct sk_buff *skb,
411
+			    struct esp_info *esp)
412
+{
413
+	struct xfrm_encap_tmpl *encap = x->encap;
414
+	struct ip_esp_hdr *esph;
415
+	__be16 sport, dport;
416
+	int encap_type;
235417 
236418 	spin_lock_bh(&x->lock);
237419 	sport = encap->encap_sport;
....@@ -239,29 +421,20 @@
239421 	encap_type = encap->encap_type;
240422 	spin_unlock_bh(&x->lock);
241423 
242
-	len = skb->len + esp->tailen - skb_transport_offset(skb);
243
-	if (len + sizeof(struct iphdr) >= IP_MAX_MTU)
244
-		return -EMSGSIZE;
245
-
246
-	uh = (struct udphdr *)esph;
247
-	uh->source = sport;
248
-	uh->dest = dport;
249
-	uh->len = htons(len);
250
-	uh->check = 0;
251
-
252424 	switch (encap_type) {
253425 	default:
254426 	case UDP_ENCAP_ESPINUDP:
255
-		esph = (struct ip_esp_hdr *)(uh + 1);
256
-		break;
257427 	case UDP_ENCAP_ESPINUDP_NON_IKE:
258
-		udpdata32 = (__be32 *)(uh + 1);
259
-		udpdata32[0] = udpdata32[1] = 0;
260
-		esph = (struct ip_esp_hdr *)(udpdata32 + 2);
428
+		esph = esp_output_udp_encap(skb, encap_type, esp, sport, dport);
429
+		break;
430
+	case TCP_ENCAP_ESPINTCP:
431
+		esph = esp_output_tcp_encap(x, skb, esp);
261432 		break;
262433 	}
263434 
264
-	*skb_mac_header(skb) = IPPROTO_UDP;
435
+	if (IS_ERR(esph))
436
+		return PTR_ERR(esph);
437
+
265438 	esp->esph = esph;
266439 
267440 	return 0;
....@@ -276,13 +449,17 @@
276449 	struct sk_buff *trailer;
277450 	int tailen = esp->tailen;
278451 
279
-	/* this is non-NULL only with UDP Encapsulation */
452
+	/* this is non-NULL only with TCP/UDP Encapsulation */
280453 	if (x->encap) {
281
-		int err = esp_output_udp_encap(x, skb, esp);
454
+		int err = esp_output_encap(x, skb, esp);
282455 
283456 		if (err < 0)
284457 			return err;
285458 	}
459
+
460
+	if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE ||
461
+	    ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE)
462
+		goto cow;
286463 
287464 	if (!skb_cloned(skb)) {
288465 		if (tailen <= skb_tailroom(skb)) {
....@@ -467,6 +644,9 @@
467644 	if (sg != dsg)
468645 		esp_ssg_unref(x, tmp);
469646 
647
+	if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
648
+		err = esp_output_tail_tcp(x, skb);
649
+
470650 error_free:
471651 	kfree(tmp);
472652 error:
....@@ -497,7 +677,7 @@
497677 		struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
498678 		u32 padto;
499679 
500
-		padto = min(x->tfcpad, esp4_get_mtu(x, dst->child_mtu_cached));
680
+		padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached));
501681 		if (skb->len < padto)
502682 			esp.tfclen = padto - skb->len;
503683 	}
....@@ -593,7 +773,23 @@
593773 
594774 	if (x->encap) {
595775 		struct xfrm_encap_tmpl *encap = x->encap;
776
+		struct tcphdr *th = (void *)(skb_network_header(skb) + ihl);
596777 		struct udphdr *uh = (void *)(skb_network_header(skb) + ihl);
778
+		__be16 source;
779
+
780
+		switch (x->encap->encap_type) {
781
+		case TCP_ENCAP_ESPINTCP:
782
+			source = th->source;
783
+			break;
784
+		case UDP_ENCAP_ESPINUDP:
785
+		case UDP_ENCAP_ESPINUDP_NON_IKE:
786
+			source = uh->source;
787
+			break;
788
+		default:
789
+			WARN_ON_ONCE(1);
790
+			err = -EINVAL;
791
+			goto out;
792
+		}
597793 
598794 		/*
599795 		 * 1) if the NAT-T peer's IP or port changed then
....@@ -602,11 +798,11 @@
602798 		 *    SRC ports.
603799 		 */
604800 		if (iph->saddr != x->props.saddr.a4 ||
605
-		    uh->source != encap->encap_sport) {
801
+		    source != encap->encap_sport) {
606802 			xfrm_address_t ipaddr;
607803 
608804 			ipaddr.a4 = iph->saddr;
609
-			km_new_mapping(x, &ipaddr, uh->source);
805
+			km_new_mapping(x, &ipaddr, source);
610806 
611807 			/* XXX: perhaps add an extra
612808 			 * policy check here, to see
....@@ -688,12 +884,11 @@
688884  */
689885 static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
690886 {
691
-	struct ip_esp_hdr *esph;
692887 	struct crypto_aead *aead = x->data;
693888 	struct aead_request *req;
694889 	struct sk_buff *trailer;
695890 	int ivlen = crypto_aead_ivsize(aead);
696
-	int elen = skb->len - sizeof(*esph) - ivlen;
891
+	int elen = skb->len - sizeof(struct ip_esp_hdr) - ivlen;
697892 	int nfrags;
698893 	int assoclen;
699894 	int seqhilen;
....@@ -703,13 +898,13 @@
703898 	struct scatterlist *sg;
704899 	int err = -EINVAL;
705900 
706
-	if (!pskb_may_pull(skb, sizeof(*esph) + ivlen))
901
+	if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr) + ivlen))
707902 		goto out;
708903 
709904 	if (elen <= 0)
710905 		goto out;
711906 
712
-	assoclen = sizeof(*esph);
907
+	assoclen = sizeof(struct ip_esp_hdr);
713908 	seqhilen = 0;
714909 
715910 	if (x->props.flags & XFRM_STATE_ESN) {
....@@ -780,28 +975,6 @@
780975 	return err;
781976 }
782977 
783
-static u32 esp4_get_mtu(struct xfrm_state *x, int mtu)
784
-{
785
-	struct crypto_aead *aead = x->data;
786
-	u32 blksize = ALIGN(crypto_aead_blocksize(aead), 4);
787
-	unsigned int net_adj;
788
-
789
-	switch (x->props.mode) {
790
-	case XFRM_MODE_TRANSPORT:
791
-	case XFRM_MODE_BEET:
792
-		net_adj = sizeof(struct iphdr);
793
-		break;
794
-	case XFRM_MODE_TUNNEL:
795
-		net_adj = 0;
796
-		break;
797
-	default:
798
-		BUG();
799
-	}
800
-
801
-	return ((mtu - x->props.header_len - crypto_aead_authsize(aead) -
802
-		 net_adj) & ~(blksize - 1)) + net_adj - 2;
803
-}
804
-
805978 static int esp4_err(struct sk_buff *skb, u32 info)
806979 {
807980 	struct net *net = dev_net(skb->dev);
....@@ -825,9 +998,9 @@
825998 		return 0;
826999 
8271000 	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
828
-		ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0);
1001
+		ipv4_update_pmtu(skb, net, info, 0, IPPROTO_ESP);
8291002 	else
830
-		ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0);
1003
+		ipv4_redirect(skb, net, 0, IPPROTO_ESP);
8311004 	xfrm_state_put(x);
8321005 
8331006 	return 0;
....@@ -961,7 +1134,7 @@
9611134 	err = crypto_aead_setkey(aead, key, keylen);
9621135 
9631136 free_key:
964
-	kfree(key);
1137
+	kfree_sensitive(key);
9651138 
9661139 error:
9671140 	return err;
....@@ -1004,6 +1177,14 @@
10041177 		case UDP_ENCAP_ESPINUDP_NON_IKE:
10051178 			x->props.header_len += sizeof(struct udphdr) + 2 * sizeof(u32);
10061179 			break;
1180
+#ifdef CONFIG_INET_ESPINTCP
1181
+		case TCP_ENCAP_ESPINTCP:
1182
+			/* only the length field, TCP encap is done by
1183
+			 * the socket
1184
+			 */
1185
+			x->props.header_len += 2;
1186
+			break;
1187
+#endif
10071188 		}
10081189 	}
10091190 
....@@ -1027,7 +1208,6 @@
10271208 	.flags		= XFRM_TYPE_REPLAY_PROT,
10281209 	.init_state	= esp_init_state,
10291210 	.destructor	= esp_destroy,
1030
-	.get_mtu	= esp4_get_mtu,
10311211 	.input		= esp_input,
10321212 	.output		= esp_output,
10331213 };
....@@ -1058,8 +1238,7 @@
10581238 {
10591239 	if (xfrm4_protocol_deregister(&esp4_protocol, IPPROTO_ESP) < 0)
10601240 		pr_info("%s: can't remove protocol\n", __func__);
1061
-	if (xfrm_unregister_type(&esp_type, AF_INET) < 0)
1062
-		pr_info("%s: can't remove xfrm type\n", __func__);
1241
+	xfrm_unregister_type(&esp_type, AF_INET);
10631242 }
10641243 
10651244 module_init(esp4_init);