1/* SPDX-License-Identifier: GPL-2.0 */ 2/* 3 * net/dst.h Protocol independent destination cache definitions. 4 * 5 * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> 6 * 7 */ 8 9#ifndef _NET_DST_H 10#define _NET_DST_H 11 12#include <net/dst_ops.h> 13#include <linux/netdevice.h> 14#include <linux/rtnetlink.h> 15#include <linux/rcupdate.h> 16#include <linux/bug.h> 17#include <linux/jiffies.h> 18#include <linux/refcount.h> 19#include <linux/rcuref.h> 20#include <net/neighbour.h> 21#include <asm/processor.h> 22#include <linux/indirect_call_wrapper.h> 23 24struct sk_buff; 25 26struct dst_entry { 27 struct net_device *dev; 28 struct dst_ops *ops; 29 unsigned long _metrics; 30 unsigned long expires; 31#ifdef CONFIG_XFRM 32 struct xfrm_state *xfrm; 33#else 34 void *__pad1; 35#endif 36 int (*input)(struct sk_buff *); 37 int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); 38 39 unsigned short flags; 40#define DST_NOXFRM 0x0002 41#define DST_NOPOLICY 0x0004 42#define DST_NOCOUNT 0x0008 43#define DST_FAKE_RTABLE 0x0010 44#define DST_XFRM_TUNNEL 0x0020 45#define DST_XFRM_QUEUE 0x0040 46#define DST_METADATA 0x0080 47 48 /* A non-zero value of dst->obsolete forces by-hand validation 49 * of the route entry. Positive values are set by the generic 50 * dst layer to indicate that the entry has been forcefully 51 * destroyed. 52 * 53 * Negative values are used by the implementation layer code to 54 * force invocation of the dst_ops->check() method. 55 */ 56 short obsolete; 57#define DST_OBSOLETE_NONE 0 58#define DST_OBSOLETE_DEAD 2 59#define DST_OBSOLETE_FORCE_CHK -1 60#define DST_OBSOLETE_KILL -2 61 unsigned short header_len; /* more space at head required */ 62 unsigned short trailer_len; /* space to reserve at tail */ 63 64 /* 65 * __rcuref wants to be on a different cache line from 66 * input/output/ops or performance tanks badly 67 */ 68#ifdef CONFIG_64BIT 69 rcuref_t __rcuref; /* 64-bit offset 64 */ 70#endif 71 int __use; 72 unsigned long lastuse; 73 struct rcu_head rcu_head; 74 short error; 75 short __pad; 76 __u32 tclassid; 77#ifndef CONFIG_64BIT 78 struct lwtunnel_state *lwtstate; 79 rcuref_t __rcuref; /* 32-bit offset 64 */ 80#endif 81 netdevice_tracker dev_tracker; 82 83 /* 84 * Used by rtable and rt6_info. Moves lwtstate into the next cache 85 * line on 64bit so that lwtstate does not cause false sharing with 86 * __rcuref under contention of __rcuref. This also puts the 87 * frequently accessed members of rtable and rt6_info out of the 88 * __rcuref cache line. 89 */ 90 struct list_head rt_uncached; 91 struct uncached_list *rt_uncached_list; 92#ifdef CONFIG_64BIT 93 struct lwtunnel_state *lwtstate; 94#endif 95}; 96 97struct dst_metrics { 98 u32 metrics[RTAX_MAX]; 99 refcount_t refcnt; 100} __aligned(4); /* Low pointer bits contain DST_METRICS_FLAGS */ 101extern const struct dst_metrics dst_default_metrics; 102 103u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); 104 105#define DST_METRICS_READ_ONLY 0x1UL 106#define DST_METRICS_REFCOUNTED 0x2UL 107#define DST_METRICS_FLAGS 0x3UL 108#define __DST_METRICS_PTR(Y) \ 109 ((u32 *)((Y) & ~DST_METRICS_FLAGS)) 110#define DST_METRICS_PTR(X) __DST_METRICS_PTR((X)->_metrics) 111 112static inline bool dst_metrics_read_only(const struct dst_entry *dst) 113{ 114 return dst->_metrics & DST_METRICS_READ_ONLY; 115} 116 117void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old); 118 119static inline void dst_destroy_metrics_generic(struct dst_entry *dst) 120{ 121 unsigned long val = dst->_metrics; 122 if (!(val & DST_METRICS_READ_ONLY)) 123 __dst_destroy_metrics_generic(dst, val); 124} 125 126static inline u32 *dst_metrics_write_ptr(struct dst_entry *dst) 127{ 128 unsigned long p = dst->_metrics; 129 130 BUG_ON(!p); 131 132 if (p & DST_METRICS_READ_ONLY) 133 return dst->ops->cow_metrics(dst, p); 134 return __DST_METRICS_PTR(p); 135} 136 137/* This may only be invoked before the entry has reached global 138 * visibility. 139 */ 140static inline void dst_init_metrics(struct dst_entry *dst, 141 const u32 *src_metrics, 142 bool read_only) 143{ 144 dst->_metrics = ((unsigned long) src_metrics) | 145 (read_only ? DST_METRICS_READ_ONLY : 0); 146} 147 148static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) 149{ 150 u32 *dst_metrics = dst_metrics_write_ptr(dest); 151 152 if (dst_metrics) { 153 u32 *src_metrics = DST_METRICS_PTR(src); 154 155 memcpy(dst_metrics, src_metrics, RTAX_MAX * sizeof(u32)); 156 } 157} 158 159static inline u32 *dst_metrics_ptr(struct dst_entry *dst) 160{ 161 return DST_METRICS_PTR(dst); 162} 163 164static inline u32 165dst_metric_raw(const struct dst_entry *dst, const int metric) 166{ 167 u32 *p = DST_METRICS_PTR(dst); 168 169 return p[metric-1]; 170} 171 172static inline u32 173dst_metric(const struct dst_entry *dst, const int metric) 174{ 175 WARN_ON_ONCE(metric == RTAX_HOPLIMIT || 176 metric == RTAX_ADVMSS || 177 metric == RTAX_MTU); 178 return dst_metric_raw(dst, metric); 179} 180 181static inline u32 182dst_metric_advmss(const struct dst_entry *dst) 183{ 184 u32 advmss = dst_metric_raw(dst, RTAX_ADVMSS); 185 186 if (!advmss) 187 advmss = dst->ops->default_advmss(dst); 188 189 return advmss; 190} 191 192static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) 193{ 194 u32 *p = dst_metrics_write_ptr(dst); 195 196 if (p) 197 p[metric-1] = val; 198} 199 200/* Kernel-internal feature bits that are unallocated in user space. */ 201#define DST_FEATURE_ECN_CA (1U << 31) 202 203#define DST_FEATURE_MASK (DST_FEATURE_ECN_CA) 204#define DST_FEATURE_ECN_MASK (DST_FEATURE_ECN_CA | RTAX_FEATURE_ECN) 205 206static inline u32 207dst_feature(const struct dst_entry *dst, u32 feature) 208{ 209 return dst_metric(dst, RTAX_FEATURES) & feature; 210} 211 212INDIRECT_CALLABLE_DECLARE(unsigned int ip6_mtu(const struct dst_entry *)); 213INDIRECT_CALLABLE_DECLARE(unsigned int ipv4_mtu(const struct dst_entry *)); 214static inline u32 dst_mtu(const struct dst_entry *dst) 215{ 216 return INDIRECT_CALL_INET(dst->ops->mtu, ip6_mtu, ipv4_mtu, dst); 217} 218 219/* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */ 220static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metric) 221{ 222 return msecs_to_jiffies(dst_metric(dst, metric)); 223} 224 225static inline u32 226dst_allfrag(const struct dst_entry *dst) 227{ 228 int ret = dst_feature(dst, RTAX_FEATURE_ALLFRAG); 229 return ret; 230} 231 232static inline int 233dst_metric_locked(const struct dst_entry *dst, int metric) 234{ 235 return dst_metric(dst, RTAX_LOCK) & (1 << metric); 236} 237 238static inline void dst_hold(struct dst_entry *dst) 239{ 240 /* 241 * If your kernel compilation stops here, please check 242 * the placement of __rcuref in struct dst_entry 243 */ 244 BUILD_BUG_ON(offsetof(struct dst_entry, __rcuref) & 63); 245 WARN_ON(!rcuref_get(&dst->__rcuref)); 246} 247 248static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) 249{ 250 if (unlikely(time != dst->lastuse)) { 251 dst->__use++; 252 dst->lastuse = time; 253 } 254} 255 256static inline struct dst_entry *dst_clone(struct dst_entry *dst) 257{ 258 if (dst) 259 dst_hold(dst); 260 return dst; 261} 262 263void dst_release(struct dst_entry *dst); 264 265void dst_release_immediate(struct dst_entry *dst); 266 267static inline void refdst_drop(unsigned long refdst) 268{ 269 if (!(refdst & SKB_DST_NOREF)) 270 dst_release((struct dst_entry *)(refdst & SKB_DST_PTRMASK)); 271} 272 273/** 274 * skb_dst_drop - drops skb dst 275 * @skb: buffer 276 * 277 * Drops dst reference count if a reference was taken. 278 */ 279static inline void skb_dst_drop(struct sk_buff *skb) 280{ 281 if (skb->_skb_refdst) { 282 refdst_drop(skb->_skb_refdst); 283 skb->_skb_refdst = 0UL; 284 } 285} 286 287static inline void __skb_dst_copy(struct sk_buff *nskb, unsigned long refdst) 288{ 289 nskb->slow_gro |= !!refdst; 290 nskb->_skb_refdst = refdst; 291 if (!(nskb->_skb_refdst & SKB_DST_NOREF)) 292 dst_clone(skb_dst(nskb)); 293} 294 295static inline void skb_dst_copy(struct sk_buff *nskb, const struct sk_buff *oskb) 296{ 297 __skb_dst_copy(nskb, oskb->_skb_refdst); 298} 299 300/** 301 * dst_hold_safe - Take a reference on a dst if possible 302 * @dst: pointer to dst entry 303 * 304 * This helper returns false if it could not safely 305 * take a reference on a dst. 306 */ 307static inline bool dst_hold_safe(struct dst_entry *dst) 308{ 309 return rcuref_get(&dst->__rcuref); 310} 311 312/** 313 * skb_dst_force - makes sure skb dst is refcounted 314 * @skb: buffer 315 * 316 * If dst is not yet refcounted and not destroyed, grab a ref on it. 317 * Returns true if dst is refcounted. 318 */ 319static inline bool skb_dst_force(struct sk_buff *skb) 320{ 321 if (skb_dst_is_noref(skb)) { 322 struct dst_entry *dst = skb_dst(skb); 323 324 WARN_ON(!rcu_read_lock_held()); 325 if (!dst_hold_safe(dst)) 326 dst = NULL; 327 328 skb->_skb_refdst = (unsigned long)dst; 329 skb->slow_gro |= !!dst; 330 } 331 332 return skb->_skb_refdst != 0UL; 333} 334 335 336/** 337 * __skb_tunnel_rx - prepare skb for rx reinsert 338 * @skb: buffer 339 * @dev: tunnel device 340 * @net: netns for packet i/o 341 * 342 * After decapsulation, packet is going to re-enter (netif_rx()) our stack, 343 * so make some cleanups. (no accounting done) 344 */ 345static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, 346 struct net *net) 347{ 348 skb->dev = dev; 349 350 /* 351 * Clear hash so that we can recalulate the hash for the 352 * encapsulated packet, unless we have already determine the hash 353 * over the L4 4-tuple. 354 */ 355 skb_clear_hash_if_not_l4(skb); 356 skb_set_queue_mapping(skb, 0); 357 skb_scrub_packet(skb, !net_eq(net, dev_net(dev))); 358} 359 360/** 361 * skb_tunnel_rx - prepare skb for rx reinsert 362 * @skb: buffer 363 * @dev: tunnel device 364 * @net: netns for packet i/o 365 * 366 * After decapsulation, packet is going to re-enter (netif_rx()) our stack, 367 * so make some cleanups, and perform accounting. 368 * Note: this accounting is not SMP safe. 369 */ 370static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, 371 struct net *net) 372{ 373 DEV_STATS_INC(dev, rx_packets); 374 DEV_STATS_ADD(dev, rx_bytes, skb->len); 375 __skb_tunnel_rx(skb, dev, net); 376} 377 378static inline u32 dst_tclassid(const struct sk_buff *skb) 379{ 380#ifdef CONFIG_IP_ROUTE_CLASSID 381 const struct dst_entry *dst; 382 383 dst = skb_dst(skb); 384 if (dst) 385 return dst->tclassid; 386#endif 387 return 0; 388} 389 390int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); 391static inline int dst_discard(struct sk_buff *skb) 392{ 393 return dst_discard_out(&init_net, skb->sk, skb); 394} 395void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref, 396 int initial_obsolete, unsigned short flags); 397void dst_init(struct dst_entry *dst, struct dst_ops *ops, 398 struct net_device *dev, int initial_ref, int initial_obsolete, 399 unsigned short flags); 400struct dst_entry *dst_destroy(struct dst_entry *dst); 401void dst_dev_put(struct dst_entry *dst); 402 403static inline void dst_confirm(struct dst_entry *dst) 404{ 405} 406 407static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, const void *daddr) 408{ 409 struct neighbour *n = dst->ops->neigh_lookup(dst, NULL, daddr); 410 return IS_ERR(n) ? NULL : n; 411} 412 413static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst, 414 struct sk_buff *skb) 415{ 416 struct neighbour *n; 417 418 if (WARN_ON_ONCE(!dst->ops->neigh_lookup)) 419 return NULL; 420 421 n = dst->ops->neigh_lookup(dst, skb, NULL); 422 423 return IS_ERR(n) ? NULL : n; 424} 425 426static inline void dst_confirm_neigh(const struct dst_entry *dst, 427 const void *daddr) 428{ 429 if (dst->ops->confirm_neigh) 430 dst->ops->confirm_neigh(dst, daddr); 431} 432 433static inline void dst_link_failure(struct sk_buff *skb) 434{ 435 struct dst_entry *dst = skb_dst(skb); 436 if (dst && dst->ops && dst->ops->link_failure) 437 dst->ops->link_failure(skb); 438} 439 440static inline void dst_set_expires(struct dst_entry *dst, int timeout) 441{ 442 unsigned long expires = jiffies + timeout; 443 444 if (expires == 0) 445 expires = 1; 446 447 if (dst->expires == 0 || time_before(expires, dst->expires)) 448 dst->expires = expires; 449} 450 451INDIRECT_CALLABLE_DECLARE(int ip6_output(struct net *, struct sock *, 452 struct sk_buff *)); 453INDIRECT_CALLABLE_DECLARE(int ip_output(struct net *, struct sock *, 454 struct sk_buff *)); 455/* Output packet to network from transport. */ 456static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb) 457{ 458 return INDIRECT_CALL_INET(skb_dst(skb)->output, 459 ip6_output, ip_output, 460 net, sk, skb); 461} 462 463INDIRECT_CALLABLE_DECLARE(int ip6_input(struct sk_buff *)); 464INDIRECT_CALLABLE_DECLARE(int ip_local_deliver(struct sk_buff *)); 465/* Input packet from network to transport. */ 466static inline int dst_input(struct sk_buff *skb) 467{ 468 return INDIRECT_CALL_INET(skb_dst(skb)->input, 469 ip6_input, ip_local_deliver, skb); 470} 471 472INDIRECT_CALLABLE_DECLARE(struct dst_entry *ip6_dst_check(struct dst_entry *, 473 u32)); 474INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, 475 u32)); 476static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie) 477{ 478 if (dst->obsolete) 479 dst = INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, 480 ipv4_dst_check, dst, cookie); 481 return dst; 482} 483 484/* Flags for xfrm_lookup flags argument. */ 485enum { 486 XFRM_LOOKUP_ICMP = 1 << 0, 487 XFRM_LOOKUP_QUEUE = 1 << 1, 488 XFRM_LOOKUP_KEEP_DST_REF = 1 << 2, 489}; 490 491struct flowi; 492#ifndef CONFIG_XFRM 493static inline struct dst_entry *xfrm_lookup(struct net *net, 494 struct dst_entry *dst_orig, 495 const struct flowi *fl, 496 const struct sock *sk, 497 int flags) 498{ 499 return dst_orig; 500} 501 502static inline struct dst_entry * 503xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig, 504 const struct flowi *fl, const struct sock *sk, 505 int flags, u32 if_id) 506{ 507 return dst_orig; 508} 509 510static inline struct dst_entry *xfrm_lookup_route(struct net *net, 511 struct dst_entry *dst_orig, 512 const struct flowi *fl, 513 const struct sock *sk, 514 int flags) 515{ 516 return dst_orig; 517} 518 519static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) 520{ 521 return NULL; 522} 523 524#else 525struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, 526 const struct flowi *fl, const struct sock *sk, 527 int flags); 528 529struct dst_entry *xfrm_lookup_with_ifid(struct net *net, 530 struct dst_entry *dst_orig, 531 const struct flowi *fl, 532 const struct sock *sk, int flags, 533 u32 if_id); 534 535struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, 536 const struct flowi *fl, const struct sock *sk, 537 int flags); 538 539/* skb attached with this dst needs transformation if dst->xfrm is valid */ 540static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) 541{ 542 return dst->xfrm; 543} 544#endif 545 546static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu) 547{ 548 struct dst_entry *dst = skb_dst(skb); 549 550 if (dst && dst->ops->update_pmtu) 551 dst->ops->update_pmtu(dst, NULL, skb, mtu, true); 552} 553 554/* update dst pmtu but not do neighbor confirm */ 555static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu) 556{ 557 struct dst_entry *dst = skb_dst(skb); 558 559 if (dst && dst->ops->update_pmtu) 560 dst->ops->update_pmtu(dst, NULL, skb, mtu, false); 561} 562 563struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie); 564void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, 565 struct sk_buff *skb, u32 mtu, bool confirm_neigh); 566void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk, 567 struct sk_buff *skb); 568u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old); 569struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst, 570 struct sk_buff *skb, 571 const void *daddr); 572unsigned int dst_blackhole_mtu(const struct dst_entry *dst); 573 574#endif /* _NET_DST_H */ 575