1// SPDX-License-Identifier: GPL-2.0-only 2#define pr_fmt(fmt) "IPsec: " fmt 3 4#include <crypto/aead.h> 5#include <crypto/authenc.h> 6#include <linux/err.h> 7#include <linux/module.h> 8#include <net/ip.h> 9#include <net/xfrm.h> 10#include <net/esp.h> 11#include <linux/scatterlist.h> 12#include <linux/kernel.h> 13#include <linux/pfkeyv2.h> 14#include <linux/rtnetlink.h> 15#include <linux/slab.h> 16#include <linux/spinlock.h> 17#include <linux/in6.h> 18#include <net/icmp.h> 19#include <net/protocol.h> 20#include <net/udp.h> 21#include <net/tcp.h> 22#include <net/espintcp.h> 23 24#include <linux/highmem.h> 25 26struct esp_skb_cb { 27 struct xfrm_skb_cb xfrm; 28 void *tmp; 29}; 30 31struct esp_output_extra { 32 __be32 seqhi; 33 u32 esphoff; 34}; 35 36#define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0])) 37 38/* 39 * Allocate an AEAD request structure with extra space for SG and IV. 40 * 41 * For alignment considerations the IV is placed at the front, followed 42 * by the request and finally the SG list. 43 * 44 * TODO: Use spare space in skb for this where possible. 45 */ 46static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int extralen) 47{ 48 unsigned int len; 49 50 len = extralen; 51 52 len += crypto_aead_ivsize(aead); 53 54 if (len) { 55 len += crypto_aead_alignmask(aead) & 56 ~(crypto_tfm_ctx_alignment() - 1); 57 len = ALIGN(len, crypto_tfm_ctx_alignment()); 58 } 59 60 len += sizeof(struct aead_request) + crypto_aead_reqsize(aead); 61 len = ALIGN(len, __alignof__(struct scatterlist)); 62 63 len += sizeof(struct scatterlist) * nfrags; 64 65 return kmalloc(len, GFP_ATOMIC); 66} 67 68static inline void *esp_tmp_extra(void *tmp) 69{ 70 return PTR_ALIGN(tmp, __alignof__(struct esp_output_extra)); 71} 72 73static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int extralen) 74{ 75 return crypto_aead_ivsize(aead) ? 76 PTR_ALIGN((u8 *)tmp + extralen, 77 crypto_aead_alignmask(aead) + 1) : tmp + extralen; 78} 79 80static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv) 81{ 82 struct aead_request *req; 83 84 req = (void *)PTR_ALIGN(iv + crypto_aead_ivsize(aead), 85 crypto_tfm_ctx_alignment()); 86 aead_request_set_tfm(req, aead); 87 return req; 88} 89 90static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead, 91 struct aead_request *req) 92{ 93 return (void *)ALIGN((unsigned long)(req + 1) + 94 crypto_aead_reqsize(aead), 95 __alignof__(struct scatterlist)); 96} 97 98static void esp_ssg_unref(struct xfrm_state *x, void *tmp) 99{ 100 struct esp_output_extra *extra = esp_tmp_extra(tmp); 101 struct crypto_aead *aead = x->data; 102 int extralen = 0; 103 u8 *iv; 104 struct aead_request *req; 105 struct scatterlist *sg; 106 107 if (x->props.flags & XFRM_STATE_ESN) 108 extralen += sizeof(*extra); 109 110 extra = esp_tmp_extra(tmp); 111 iv = esp_tmp_iv(aead, tmp, extralen); 112 req = esp_tmp_req(aead, iv); 113 114 /* Unref skb_frag_pages in the src scatterlist if necessary. 115 * Skip the first sg which comes from skb->data. 116 */ 117 if (req->src != req->dst) 118 for (sg = sg_next(req->src); sg; sg = sg_next(sg)) 119 put_page(sg_page(sg)); 120} 121 122#ifdef CONFIG_INET_ESPINTCP 123struct esp_tcp_sk { 124 struct sock *sk; 125 struct rcu_head rcu; 126}; 127 128static 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 136static 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 192static 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 211out: 212 rcu_read_unlock(); 213 return err; 214} 215 216static 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 225static 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 240static 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 248static void esp_output_done(struct crypto_async_request *base, int err) 249{ 250 struct sk_buff *skb = base->data; 251 struct xfrm_offload *xo = xfrm_offload(skb); 252 void *tmp; 253 struct xfrm_state *x; 254 255 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 { 260 x = skb_dst(skb)->xfrm; 261 } 262 263 tmp = ESP_SKB_CB(skb)->tmp; 264 esp_ssg_unref(x, tmp); 265 kfree(tmp); 266 267 if (xo && (xo->flags & XFRM_DEV_RESUME)) { 268 if (err) { 269 XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR); 270 kfree_skb(skb); 271 return; 272 } 273 274 skb_push(skb, skb->data - skb_mac_header(skb)); 275 secpath_reset(skb); 276 xfrm_dev_resume(skb); 277 } else { 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->sk, skb, err); 283 } 284} 285 286/* Move ESP header back into place. */ 287static void esp_restore_header(struct sk_buff *skb, unsigned int offset) 288{ 289 struct ip_esp_hdr *esph = (void *)(skb->data + offset); 290 void *tmp = ESP_SKB_CB(skb)->tmp; 291 __be32 *seqhi = esp_tmp_extra(tmp); 292 293 esph->seq_no = esph->spi; 294 esph->spi = *seqhi; 295} 296 297static void esp_output_restore_header(struct sk_buff *skb) 298{ 299 void *tmp = ESP_SKB_CB(skb)->tmp; 300 struct esp_output_extra *extra = esp_tmp_extra(tmp); 301 302 esp_restore_header(skb, skb_transport_offset(skb) + extra->esphoff - 303 sizeof(__be32)); 304} 305 306static struct ip_esp_hdr *esp_output_set_extra(struct sk_buff *skb, 307 struct xfrm_state *x, 308 struct ip_esp_hdr *esph, 309 struct esp_output_extra *extra) 310{ 311 /* For ESN we move the header forward by 4 bytes to 312 * accomodate the high bits. We will move it back after 313 * encryption. 314 */ 315 if ((x->props.flags & XFRM_STATE_ESN)) { 316 __u32 seqhi; 317 struct xfrm_offload *xo = xfrm_offload(skb); 318 319 if (xo) 320 seqhi = xo->seq.hi; 321 else 322 seqhi = XFRM_SKB_CB(skb)->seq.output.hi; 323 324 extra->esphoff = (unsigned char *)esph - 325 skb_transport_header(skb); 326 esph = (struct ip_esp_hdr *)((unsigned char *)esph - 4); 327 extra->seqhi = esph->spi; 328 esph->seq_no = htonl(seqhi); 329 } 330 331 esph->spi = x->id.spi; 332 333 return esph; 334} 335 336static void esp_output_done_esn(struct crypto_async_request *base, int err) 337{ 338 struct sk_buff *skb = base->data; 339 340 esp_output_restore_header(skb); 341 esp_output_done(base, err); 342} 343 344static 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) 349{ 350 struct udphdr *uh; 351 __be32 *udpdata32; 352 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 376static 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 402static 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 410static 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; 417 418 spin_lock_bh(&x->lock); 419 sport = encap->encap_sport; 420 dport = encap->encap_dport; 421 encap_type = encap->encap_type; 422 spin_unlock_bh(&x->lock); 423 424 switch (encap_type) { 425 default: 426 case UDP_ENCAP_ESPINUDP: 427 case UDP_ENCAP_ESPINUDP_NON_IKE: 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); 432 break; 433 } 434 435 if (IS_ERR(esph)) 436 return PTR_ERR(esph); 437 438 esp->esph = esph; 439 440 return 0; 441} 442 443int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) 444{ 445 u8 *tail; 446 int nfrags; 447 int esph_offset; 448 struct page *page; 449 struct sk_buff *trailer; 450 int tailen = esp->tailen; 451 452 /* this is non-NULL only with TCP/UDP Encapsulation */ 453 if (x->encap) { 454 int err = esp_output_encap(x, skb, esp); 455 456 if (err < 0) 457 return err; 458 } 459 460 if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE || 461 ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE) 462 goto cow; 463 464 if (!skb_cloned(skb)) { 465 if (tailen <= skb_tailroom(skb)) { 466 nfrags = 1; 467 trailer = skb; 468 tail = skb_tail_pointer(trailer); 469 470 goto skip_cow; 471 } else if ((skb_shinfo(skb)->nr_frags < MAX_SKB_FRAGS) 472 && !skb_has_frag_list(skb)) { 473 int allocsize; 474 struct sock *sk = skb->sk; 475 struct page_frag *pfrag = &x->xfrag; 476 477 esp->inplace = false; 478 479 allocsize = ALIGN(tailen, L1_CACHE_BYTES); 480 481 spin_lock_bh(&x->lock); 482 483 if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) { 484 spin_unlock_bh(&x->lock); 485 goto cow; 486 } 487 488 page = pfrag->page; 489 get_page(page); 490 491 tail = page_address(page) + pfrag->offset; 492 493 esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto); 494 495 nfrags = skb_shinfo(skb)->nr_frags; 496 497 __skb_fill_page_desc(skb, nfrags, page, pfrag->offset, 498 tailen); 499 skb_shinfo(skb)->nr_frags = ++nfrags; 500 501 pfrag->offset = pfrag->offset + allocsize; 502 503 spin_unlock_bh(&x->lock); 504 505 nfrags++; 506 507 skb->len += tailen; 508 skb->data_len += tailen; 509 skb->truesize += tailen; 510 if (sk && sk_fullsock(sk)) 511 refcount_add(tailen, &sk->sk_wmem_alloc); 512 513 goto out; 514 } 515 } 516 517cow: 518 esph_offset = (unsigned char *)esp->esph - skb_transport_header(skb); 519 520 nfrags = skb_cow_data(skb, tailen, &trailer); 521 if (nfrags < 0) 522 goto out; 523 tail = skb_tail_pointer(trailer); 524 esp->esph = (struct ip_esp_hdr *)(skb_transport_header(skb) + esph_offset); 525 526skip_cow: 527 esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto); 528 pskb_put(skb, trailer, tailen); 529 530out: 531 return nfrags; 532} 533EXPORT_SYMBOL_GPL(esp_output_head); 534 535int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) 536{ 537 u8 *iv; 538 int alen; 539 void *tmp; 540 int ivlen; 541 int assoclen; 542 int extralen; 543 struct page *page; 544 struct ip_esp_hdr *esph; 545 struct crypto_aead *aead; 546 struct aead_request *req; 547 struct scatterlist *sg, *dsg; 548 struct esp_output_extra *extra; 549 int err = -ENOMEM; 550 551 assoclen = sizeof(struct ip_esp_hdr); 552 extralen = 0; 553 554 if (x->props.flags & XFRM_STATE_ESN) { 555 extralen += sizeof(*extra); 556 assoclen += sizeof(__be32); 557 } 558 559 aead = x->data; 560 alen = crypto_aead_authsize(aead); 561 ivlen = crypto_aead_ivsize(aead); 562 563 tmp = esp_alloc_tmp(aead, esp->nfrags + 2, extralen); 564 if (!tmp) 565 goto error; 566 567 extra = esp_tmp_extra(tmp); 568 iv = esp_tmp_iv(aead, tmp, extralen); 569 req = esp_tmp_req(aead, iv); 570 sg = esp_req_sg(aead, req); 571 572 if (esp->inplace) 573 dsg = sg; 574 else 575 dsg = &sg[esp->nfrags]; 576 577 esph = esp_output_set_extra(skb, x, esp->esph, extra); 578 esp->esph = esph; 579 580 sg_init_table(sg, esp->nfrags); 581 err = skb_to_sgvec(skb, sg, 582 (unsigned char *)esph - skb->data, 583 assoclen + ivlen + esp->clen + alen); 584 if (unlikely(err < 0)) 585 goto error_free; 586 587 if (!esp->inplace) { 588 int allocsize; 589 struct page_frag *pfrag = &x->xfrag; 590 591 allocsize = ALIGN(skb->data_len, L1_CACHE_BYTES); 592 593 spin_lock_bh(&x->lock); 594 if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) { 595 spin_unlock_bh(&x->lock); 596 goto error_free; 597 } 598 599 skb_shinfo(skb)->nr_frags = 1; 600 601 page = pfrag->page; 602 get_page(page); 603 /* replace page frags in skb with new page */ 604 __skb_fill_page_desc(skb, 0, page, pfrag->offset, skb->data_len); 605 pfrag->offset = pfrag->offset + allocsize; 606 spin_unlock_bh(&x->lock); 607 608 sg_init_table(dsg, skb_shinfo(skb)->nr_frags + 1); 609 err = skb_to_sgvec(skb, dsg, 610 (unsigned char *)esph - skb->data, 611 assoclen + ivlen + esp->clen + alen); 612 if (unlikely(err < 0)) 613 goto error_free; 614 } 615 616 if ((x->props.flags & XFRM_STATE_ESN)) 617 aead_request_set_callback(req, 0, esp_output_done_esn, skb); 618 else 619 aead_request_set_callback(req, 0, esp_output_done, skb); 620 621 aead_request_set_crypt(req, sg, dsg, ivlen + esp->clen, iv); 622 aead_request_set_ad(req, assoclen); 623 624 memset(iv, 0, ivlen); 625 memcpy(iv + ivlen - min(ivlen, 8), (u8 *)&esp->seqno + 8 - min(ivlen, 8), 626 min(ivlen, 8)); 627 628 ESP_SKB_CB(skb)->tmp = tmp; 629 err = crypto_aead_encrypt(req); 630 631 switch (err) { 632 case -EINPROGRESS: 633 goto error; 634 635 case -ENOSPC: 636 err = NET_XMIT_DROP; 637 break; 638 639 case 0: 640 if ((x->props.flags & XFRM_STATE_ESN)) 641 esp_output_restore_header(skb); 642 } 643 644 if (sg != dsg) 645 esp_ssg_unref(x, tmp); 646 647 if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) 648 err = esp_output_tail_tcp(x, skb); 649 650error_free: 651 kfree(tmp); 652error: 653 return err; 654} 655EXPORT_SYMBOL_GPL(esp_output_tail); 656 657static int esp_output(struct xfrm_state *x, struct sk_buff *skb) 658{ 659 int alen; 660 int blksize; 661 struct ip_esp_hdr *esph; 662 struct crypto_aead *aead; 663 struct esp_info esp; 664 665 esp.inplace = true; 666 667 esp.proto = *skb_mac_header(skb); 668 *skb_mac_header(skb) = IPPROTO_ESP; 669 670 /* skb is pure payload to encrypt */ 671 672 aead = x->data; 673 alen = crypto_aead_authsize(aead); 674 675 esp.tfclen = 0; 676 if (x->tfcpad) { 677 struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb); 678 u32 padto; 679 680 padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached)); 681 if (skb->len < padto) 682 esp.tfclen = padto - skb->len; 683 } 684 blksize = ALIGN(crypto_aead_blocksize(aead), 4); 685 esp.clen = ALIGN(skb->len + 2 + esp.tfclen, blksize); 686 esp.plen = esp.clen - skb->len - esp.tfclen; 687 esp.tailen = esp.tfclen + esp.plen + alen; 688 689 esp.esph = ip_esp_hdr(skb); 690 691 esp.nfrags = esp_output_head(x, skb, &esp); 692 if (esp.nfrags < 0) 693 return esp.nfrags; 694 695 esph = esp.esph; 696 esph->spi = x->id.spi; 697 698 esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); 699 esp.seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low + 700 ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32)); 701 702 skb_push(skb, -skb_network_offset(skb)); 703 704 return esp_output_tail(x, skb, &esp); 705} 706 707static inline int esp_remove_trailer(struct sk_buff *skb) 708{ 709 struct xfrm_state *x = xfrm_input_state(skb); 710 struct xfrm_offload *xo = xfrm_offload(skb); 711 struct crypto_aead *aead = x->data; 712 int alen, hlen, elen; 713 int padlen, trimlen; 714 __wsum csumdiff; 715 u8 nexthdr[2]; 716 int ret; 717 718 alen = crypto_aead_authsize(aead); 719 hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead); 720 elen = skb->len - hlen; 721 722 if (xo && (xo->flags & XFRM_ESP_NO_TRAILER)) { 723 ret = xo->proto; 724 goto out; 725 } 726 727 if (skb_copy_bits(skb, skb->len - alen - 2, nexthdr, 2)) 728 BUG(); 729 730 ret = -EINVAL; 731 padlen = nexthdr[0]; 732 if (padlen + 2 + alen >= elen) { 733 net_dbg_ratelimited("ipsec esp packet is garbage padlen=%d, elen=%d\n", 734 padlen + 2, elen - alen); 735 goto out; 736 } 737 738 trimlen = alen + padlen + 2; 739 if (skb->ip_summed == CHECKSUM_COMPLETE) { 740 csumdiff = skb_checksum(skb, skb->len - trimlen, trimlen, 0); 741 skb->csum = csum_block_sub(skb->csum, csumdiff, 742 skb->len - trimlen); 743 } 744 ret = pskb_trim(skb, skb->len - trimlen); 745 if (unlikely(ret)) 746 return ret; 747 748 ret = nexthdr[1]; 749 750out: 751 return ret; 752} 753 754int esp_input_done2(struct sk_buff *skb, int err) 755{ 756 const struct iphdr *iph; 757 struct xfrm_state *x = xfrm_input_state(skb); 758 struct xfrm_offload *xo = xfrm_offload(skb); 759 struct crypto_aead *aead = x->data; 760 int hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead); 761 int ihl; 762 763 if (!xo || (xo && !(xo->flags & CRYPTO_DONE))) 764 kfree(ESP_SKB_CB(skb)->tmp); 765 766 if (unlikely(err)) 767 goto out; 768 769 err = esp_remove_trailer(skb); 770 if (unlikely(err < 0)) 771 goto out; 772 773 iph = ip_hdr(skb); 774 ihl = iph->ihl * 4; 775 776 if (x->encap) { 777 struct xfrm_encap_tmpl *encap = x->encap; 778 struct tcphdr *th = (void *)(skb_network_header(skb) + ihl); 779 struct udphdr *uh = (void *)(skb_network_header(skb) + ihl); 780 __be16 source; 781 782 switch (x->encap->encap_type) { 783 case TCP_ENCAP_ESPINTCP: 784 source = th->source; 785 break; 786 case UDP_ENCAP_ESPINUDP: 787 case UDP_ENCAP_ESPINUDP_NON_IKE: 788 source = uh->source; 789 break; 790 default: 791 WARN_ON_ONCE(1); 792 err = -EINVAL; 793 goto out; 794 } 795 796 /* 797 * 1) if the NAT-T peer's IP or port changed then 798 * advertize the change to the keying daemon. 799 * This is an inbound SA, so just compare 800 * SRC ports. 801 */ 802 if (iph->saddr != x->props.saddr.a4 || 803 source != encap->encap_sport) { 804 xfrm_address_t ipaddr; 805 806 ipaddr.a4 = iph->saddr; 807 km_new_mapping(x, &ipaddr, source); 808 809 /* XXX: perhaps add an extra 810 * policy check here, to see 811 * if we should allow or 812 * reject a packet from a 813 * different source 814 * address/port. 815 */ 816 } 817 818 /* 819 * 2) ignore UDP/TCP checksums in case 820 * of NAT-T in Transport Mode, or 821 * perform other post-processing fixes 822 * as per draft-ietf-ipsec-udp-encaps-06, 823 * section 3.1.2 824 */ 825 if (x->props.mode == XFRM_MODE_TRANSPORT) 826 skb->ip_summed = CHECKSUM_UNNECESSARY; 827 } 828 829 skb_pull_rcsum(skb, hlen); 830 if (x->props.mode == XFRM_MODE_TUNNEL) 831 skb_reset_transport_header(skb); 832 else 833 skb_set_transport_header(skb, -ihl); 834 835 /* RFC4303: Drop dummy packets without any error */ 836 if (err == IPPROTO_NONE) 837 err = -EINVAL; 838 839out: 840 return err; 841} 842EXPORT_SYMBOL_GPL(esp_input_done2); 843 844static void esp_input_done(struct crypto_async_request *base, int err) 845{ 846 struct sk_buff *skb = base->data; 847 848 xfrm_input_resume(skb, esp_input_done2(skb, err)); 849} 850 851static void esp_input_restore_header(struct sk_buff *skb) 852{ 853 esp_restore_header(skb, 0); 854 __skb_pull(skb, 4); 855} 856 857static void esp_input_set_header(struct sk_buff *skb, __be32 *seqhi) 858{ 859 struct xfrm_state *x = xfrm_input_state(skb); 860 struct ip_esp_hdr *esph; 861 862 /* For ESN we move the header forward by 4 bytes to 863 * accomodate the high bits. We will move it back after 864 * decryption. 865 */ 866 if ((x->props.flags & XFRM_STATE_ESN)) { 867 esph = skb_push(skb, 4); 868 *seqhi = esph->spi; 869 esph->spi = esph->seq_no; 870 esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi; 871 } 872} 873 874static void esp_input_done_esn(struct crypto_async_request *base, int err) 875{ 876 struct sk_buff *skb = base->data; 877 878 esp_input_restore_header(skb); 879 esp_input_done(base, err); 880} 881 882/* 883 * Note: detecting truncated vs. non-truncated authentication data is very 884 * expensive, so we only support truncated data, which is the recommended 885 * and common case. 886 */ 887static int esp_input(struct xfrm_state *x, struct sk_buff *skb) 888{ 889 struct crypto_aead *aead = x->data; 890 struct aead_request *req; 891 struct sk_buff *trailer; 892 int ivlen = crypto_aead_ivsize(aead); 893 int elen = skb->len - sizeof(struct ip_esp_hdr) - ivlen; 894 int nfrags; 895 int assoclen; 896 int seqhilen; 897 __be32 *seqhi; 898 void *tmp; 899 u8 *iv; 900 struct scatterlist *sg; 901 int err = -EINVAL; 902 903 if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr) + ivlen)) 904 goto out; 905 906 if (elen <= 0) 907 goto out; 908 909 assoclen = sizeof(struct ip_esp_hdr); 910 seqhilen = 0; 911 912 if (x->props.flags & XFRM_STATE_ESN) { 913 seqhilen += sizeof(__be32); 914 assoclen += seqhilen; 915 } 916 917 if (!skb_cloned(skb)) { 918 if (!skb_is_nonlinear(skb)) { 919 nfrags = 1; 920 921 goto skip_cow; 922 } else if (!skb_has_frag_list(skb)) { 923 nfrags = skb_shinfo(skb)->nr_frags; 924 nfrags++; 925 926 goto skip_cow; 927 } 928 } 929 930 err = skb_cow_data(skb, 0, &trailer); 931 if (err < 0) 932 goto out; 933 934 nfrags = err; 935 936skip_cow: 937 err = -ENOMEM; 938 tmp = esp_alloc_tmp(aead, nfrags, seqhilen); 939 if (!tmp) 940 goto out; 941 942 ESP_SKB_CB(skb)->tmp = tmp; 943 seqhi = esp_tmp_extra(tmp); 944 iv = esp_tmp_iv(aead, tmp, seqhilen); 945 req = esp_tmp_req(aead, iv); 946 sg = esp_req_sg(aead, req); 947 948 esp_input_set_header(skb, seqhi); 949 950 sg_init_table(sg, nfrags); 951 err = skb_to_sgvec(skb, sg, 0, skb->len); 952 if (unlikely(err < 0)) { 953 kfree(tmp); 954 goto out; 955 } 956 957 skb->ip_summed = CHECKSUM_NONE; 958 959 if ((x->props.flags & XFRM_STATE_ESN)) 960 aead_request_set_callback(req, 0, esp_input_done_esn, skb); 961 else 962 aead_request_set_callback(req, 0, esp_input_done, skb); 963 964 aead_request_set_crypt(req, sg, sg, elen + ivlen, iv); 965 aead_request_set_ad(req, assoclen); 966 967 err = crypto_aead_decrypt(req); 968 if (err == -EINPROGRESS) 969 goto out; 970 971 if ((x->props.flags & XFRM_STATE_ESN)) 972 esp_input_restore_header(skb); 973 974 err = esp_input_done2(skb, err); 975 976out: 977 return err; 978} 979 980static int esp4_err(struct sk_buff *skb, u32 info) 981{ 982 struct net *net = dev_net(skb->dev); 983 const struct iphdr *iph = (const struct iphdr *)skb->data; 984 struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); 985 struct xfrm_state *x; 986 987 switch (icmp_hdr(skb)->type) { 988 case ICMP_DEST_UNREACH: 989 if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) 990 return 0; 991 case ICMP_REDIRECT: 992 break; 993 default: 994 return 0; 995 } 996 997 x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, 998 esph->spi, IPPROTO_ESP, AF_INET); 999 if (!x) 1000 return 0; 1001 1002 if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) 1003 ipv4_update_pmtu(skb, net, info, 0, IPPROTO_ESP); 1004 else 1005 ipv4_redirect(skb, net, 0, IPPROTO_ESP); 1006 xfrm_state_put(x); 1007 1008 return 0; 1009} 1010 1011static void esp_destroy(struct xfrm_state *x) 1012{ 1013 struct crypto_aead *aead = x->data; 1014 1015 if (!aead) 1016 return; 1017 1018 crypto_free_aead(aead); 1019} 1020 1021static int esp_init_aead(struct xfrm_state *x) 1022{ 1023 char aead_name[CRYPTO_MAX_ALG_NAME]; 1024 struct crypto_aead *aead; 1025 int err; 1026 1027 err = -ENAMETOOLONG; 1028 if (snprintf(aead_name, CRYPTO_MAX_ALG_NAME, "%s(%s)", 1029 x->geniv, x->aead->alg_name) >= CRYPTO_MAX_ALG_NAME) 1030 goto error; 1031 1032 aead = crypto_alloc_aead(aead_name, 0, 0); 1033 err = PTR_ERR(aead); 1034 if (IS_ERR(aead)) 1035 goto error; 1036 1037 x->data = aead; 1038 1039 err = crypto_aead_setkey(aead, x->aead->alg_key, 1040 (x->aead->alg_key_len + 7) / 8); 1041 if (err) 1042 goto error; 1043 1044 err = crypto_aead_setauthsize(aead, x->aead->alg_icv_len / 8); 1045 if (err) 1046 goto error; 1047 1048error: 1049 return err; 1050} 1051 1052static int esp_init_authenc(struct xfrm_state *x) 1053{ 1054 struct crypto_aead *aead; 1055 struct crypto_authenc_key_param *param; 1056 struct rtattr *rta; 1057 char *key; 1058 char *p; 1059 char authenc_name[CRYPTO_MAX_ALG_NAME]; 1060 unsigned int keylen; 1061 int err; 1062 1063 err = -EINVAL; 1064 if (!x->ealg) 1065 goto error; 1066 1067 err = -ENAMETOOLONG; 1068 1069 if ((x->props.flags & XFRM_STATE_ESN)) { 1070 if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME, 1071 "%s%sauthencesn(%s,%s)%s", 1072 x->geniv ?: "", x->geniv ? "(" : "", 1073 x->aalg ? x->aalg->alg_name : "digest_null", 1074 x->ealg->alg_name, 1075 x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME) 1076 goto error; 1077 } else { 1078 if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME, 1079 "%s%sauthenc(%s,%s)%s", 1080 x->geniv ?: "", x->geniv ? "(" : "", 1081 x->aalg ? x->aalg->alg_name : "digest_null", 1082 x->ealg->alg_name, 1083 x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME) 1084 goto error; 1085 } 1086 1087 aead = crypto_alloc_aead(authenc_name, 0, 0); 1088 err = PTR_ERR(aead); 1089 if (IS_ERR(aead)) 1090 goto error; 1091 1092 x->data = aead; 1093 1094 keylen = (x->aalg ? (x->aalg->alg_key_len + 7) / 8 : 0) + 1095 (x->ealg->alg_key_len + 7) / 8 + RTA_SPACE(sizeof(*param)); 1096 err = -ENOMEM; 1097 key = kmalloc(keylen, GFP_KERNEL); 1098 if (!key) 1099 goto error; 1100 1101 p = key; 1102 rta = (void *)p; 1103 rta->rta_type = CRYPTO_AUTHENC_KEYA_PARAM; 1104 rta->rta_len = RTA_LENGTH(sizeof(*param)); 1105 param = RTA_DATA(rta); 1106 p += RTA_SPACE(sizeof(*param)); 1107 1108 if (x->aalg) { 1109 struct xfrm_algo_desc *aalg_desc; 1110 1111 memcpy(p, x->aalg->alg_key, (x->aalg->alg_key_len + 7) / 8); 1112 p += (x->aalg->alg_key_len + 7) / 8; 1113 1114 aalg_desc = xfrm_aalg_get_byname(x->aalg->alg_name, 0); 1115 BUG_ON(!aalg_desc); 1116 1117 err = -EINVAL; 1118 if (aalg_desc->uinfo.auth.icv_fullbits / 8 != 1119 crypto_aead_authsize(aead)) { 1120 pr_info("ESP: %s digestsize %u != %hu\n", 1121 x->aalg->alg_name, 1122 crypto_aead_authsize(aead), 1123 aalg_desc->uinfo.auth.icv_fullbits / 8); 1124 goto free_key; 1125 } 1126 1127 err = crypto_aead_setauthsize( 1128 aead, x->aalg->alg_trunc_len / 8); 1129 if (err) 1130 goto free_key; 1131 } 1132 1133 param->enckeylen = cpu_to_be32((x->ealg->alg_key_len + 7) / 8); 1134 memcpy(p, x->ealg->alg_key, (x->ealg->alg_key_len + 7) / 8); 1135 1136 err = crypto_aead_setkey(aead, key, keylen); 1137 1138free_key: 1139 kfree_sensitive(key); 1140 1141error: 1142 return err; 1143} 1144 1145static int esp_init_state(struct xfrm_state *x) 1146{ 1147 struct crypto_aead *aead; 1148 u32 align; 1149 int err; 1150 1151 x->data = NULL; 1152 1153 if (x->aead) 1154 err = esp_init_aead(x); 1155 else 1156 err = esp_init_authenc(x); 1157 1158 if (err) 1159 goto error; 1160 1161 aead = x->data; 1162 1163 x->props.header_len = sizeof(struct ip_esp_hdr) + 1164 crypto_aead_ivsize(aead); 1165 if (x->props.mode == XFRM_MODE_TUNNEL) 1166 x->props.header_len += sizeof(struct iphdr); 1167 else if (x->props.mode == XFRM_MODE_BEET && x->sel.family != AF_INET6) 1168 x->props.header_len += IPV4_BEET_PHMAXLEN; 1169 if (x->encap) { 1170 struct xfrm_encap_tmpl *encap = x->encap; 1171 1172 switch (encap->encap_type) { 1173 default: 1174 err = -EINVAL; 1175 goto error; 1176 case UDP_ENCAP_ESPINUDP: 1177 x->props.header_len += sizeof(struct udphdr); 1178 break; 1179 case UDP_ENCAP_ESPINUDP_NON_IKE: 1180 x->props.header_len += sizeof(struct udphdr) + 2 * sizeof(u32); 1181 break; 1182#ifdef CONFIG_INET_ESPINTCP 1183 case TCP_ENCAP_ESPINTCP: 1184 /* only the length field, TCP encap is done by 1185 * the socket 1186 */ 1187 x->props.header_len += 2; 1188 break; 1189#endif 1190 } 1191 } 1192 1193 align = ALIGN(crypto_aead_blocksize(aead), 4); 1194 x->props.trailer_len = align + 1 + crypto_aead_authsize(aead); 1195 1196error: 1197 return err; 1198} 1199 1200static int esp4_rcv_cb(struct sk_buff *skb, int err) 1201{ 1202 return 0; 1203} 1204 1205static const struct xfrm_type esp_type = 1206{ 1207 .description = "ESP4", 1208 .owner = THIS_MODULE, 1209 .proto = IPPROTO_ESP, 1210 .flags = XFRM_TYPE_REPLAY_PROT, 1211 .init_state = esp_init_state, 1212 .destructor = esp_destroy, 1213 .input = esp_input, 1214 .output = esp_output, 1215}; 1216 1217static struct xfrm4_protocol esp4_protocol = { 1218 .handler = xfrm4_rcv, 1219 .input_handler = xfrm_input, 1220 .cb_handler = esp4_rcv_cb, 1221 .err_handler = esp4_err, 1222 .priority = 0, 1223}; 1224 1225static int __init esp4_init(void) 1226{ 1227 if (xfrm_register_type(&esp_type, AF_INET) < 0) { 1228 pr_info("%s: can't add xfrm type\n", __func__); 1229 return -EAGAIN; 1230 } 1231 if (xfrm4_protocol_register(&esp4_protocol, IPPROTO_ESP) < 0) { 1232 pr_info("%s: can't add protocol\n", __func__); 1233 xfrm_unregister_type(&esp_type, AF_INET); 1234 return -EAGAIN; 1235 } 1236 return 0; 1237} 1238 1239static void __exit esp4_fini(void) 1240{ 1241 if (xfrm4_protocol_deregister(&esp4_protocol, IPPROTO_ESP) < 0) 1242 pr_info("%s: can't remove protocol\n", __func__); 1243 xfrm_unregister_type(&esp_type, AF_INET); 1244} 1245 1246module_init(esp4_init); 1247module_exit(esp4_fini); 1248MODULE_LICENSE("GPL"); 1249MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_ESP); 1250