1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2016 Qualcomm Atheros, Inc * * Based on net/sched/sch_fq_codel.c */ #ifndef __NET_SCHED_FQ_IMPL_H #define __NET_SCHED_FQ_IMPL_H #include <net/fq.h> /* functions that are embedded into includer */ static void fq_adjust_removal(struct fq *fq, struct fq_flow *flow, struct sk_buff *skb) { struct fq_tin *tin = flow->tin; tin->backlog_bytes -= skb->len; tin->backlog_packets--; flow->backlog -= skb->len; fq->backlog--; fq->memory_usage -= skb->truesize; } static void fq_rejigger_backlog(struct fq *fq, struct fq_flow *flow) { struct fq_flow *i; if (flow->backlog == 0) { list_del_init(&flow->backlogchain); } else { i = flow; list_for_each_entry_continue(i, &fq->backlogs, backlogchain) if (i->backlog < flow->backlog) break; list_move_tail(&flow->backlogchain, &i->backlogchain); } } static struct sk_buff *fq_flow_dequeue(struct fq *fq, struct fq_flow *flow) { struct sk_buff *skb; lockdep_assert_held(&fq->lock); skb = __skb_dequeue(&flow->queue); if (!skb) return NULL; fq_adjust_removal(fq, flow, skb); fq_rejigger_backlog(fq, flow); return skb; } static struct sk_buff *fq_tin_dequeue(struct fq *fq, struct fq_tin *tin, fq_tin_dequeue_t dequeue_func) { struct fq_flow *flow; struct list_head *head; struct sk_buff *skb; lockdep_assert_held(&fq->lock); begin: head = &tin->new_flows; if (list_empty(head)) { head = &tin->old_flows; if (list_empty(head)) return NULL; } flow = list_first_entry(head, struct fq_flow, flowchain); if (flow->deficit <= 0) { flow->deficit += fq->quantum; list_move_tail(&flow->flowchain, &tin->old_flows); goto begin; } skb = dequeue_func(fq, tin, flow); if (!skb) { /* force a pass through old_flows to prevent starvation */ if ((head == &tin->new_flows) && !list_empty(&tin->old_flows)) { list_move_tail(&flow->flowchain, &tin->old_flows); } else { list_del_init(&flow->flowchain); flow->tin = NULL; } goto begin; } flow->deficit -= skb->len; tin->tx_bytes += skb->len; tin->tx_packets++; return skb; } static u32 fq_flow_idx(struct fq *fq, struct sk_buff *skb) { u32 hash = skb_get_hash(skb); return reciprocal_scale(hash, fq->flows_cnt); } static struct fq_flow *fq_flow_classify(struct fq *fq, struct fq_tin *tin, u32 idx, struct sk_buff *skb, fq_flow_get_default_t get_default_func) { struct fq_flow *flow; lockdep_assert_held(&fq->lock); flow = &fq->flows[idx]; if (flow->tin && flow->tin != tin) { flow = get_default_func(fq, tin, idx, skb); tin->collisions++; fq->collisions++; } if (!flow->tin) tin->flows++; return flow; } static void fq_recalc_backlog(struct fq *fq, struct fq_tin *tin, struct fq_flow *flow) { struct fq_flow *i; if (list_empty(&flow->backlogchain)) list_add_tail(&flow->backlogchain, &fq->backlogs); i = flow; list_for_each_entry_continue_reverse(i, &fq->backlogs, backlogchain) if (i->backlog > flow->backlog) break; list_move(&flow->backlogchain, &i->backlogchain); } static void fq_tin_enqueue(struct fq *fq, struct fq_tin *tin, u32 idx, struct sk_buff *skb, fq_skb_free_t free_func, fq_flow_get_default_t get_default_func) { struct fq_flow *flow; bool oom; lockdep_assert_held(&fq->lock); flow = fq_flow_classify(fq, tin, idx, skb, get_default_func); flow->tin = tin; flow->backlog += skb->len; tin->backlog_bytes += skb->len; tin->backlog_packets++; fq->memory_usage += skb->truesize; fq->backlog++; fq_recalc_backlog(fq, tin, flow); if (list_empty(&flow->flowchain)) { flow->deficit = fq->quantum; list_add_tail(&flow->flowchain, &tin->new_flows); } __skb_queue_tail(&flow->queue, skb); oom = (fq->memory_usage > fq->memory_limit); while (fq->backlog > fq->limit || oom) { flow = list_first_entry_or_null(&fq->backlogs, struct fq_flow, backlogchain); if (!flow) return; skb = fq_flow_dequeue(fq, flow); if (!skb) return; free_func(fq, flow->tin, flow, skb); flow->tin->overlimit++; fq->overlimit++; if (oom) { fq->overmemory++; oom = (fq->memory_usage > fq->memory_limit); } } } static void fq_flow_filter(struct fq *fq, struct fq_flow *flow, fq_skb_filter_t filter_func, void *filter_data, fq_skb_free_t free_func) { struct fq_tin *tin = flow->tin; struct sk_buff *skb, *tmp; lockdep_assert_held(&fq->lock); skb_queue_walk_safe(&flow->queue, skb, tmp) { if (!filter_func(fq, tin, flow, skb, filter_data)) continue; __skb_unlink(skb, &flow->queue); fq_adjust_removal(fq, flow, skb); free_func(fq, tin, flow, skb); } fq_rejigger_backlog(fq, flow); } static void fq_tin_filter(struct fq *fq, struct fq_tin *tin, fq_skb_filter_t filter_func, void *filter_data, fq_skb_free_t free_func) { struct fq_flow *flow; lockdep_assert_held(&fq->lock); list_for_each_entry(flow, &tin->new_flows, flowchain) fq_flow_filter(fq, flow, filter_func, filter_data, free_func); list_for_each_entry(flow, &tin->old_flows, flowchain) fq_flow_filter(fq, flow, filter_func, filter_data, free_func); } static void fq_flow_reset(struct fq *fq, struct fq_flow *flow, fq_skb_free_t free_func) { struct sk_buff *skb; while ((skb = fq_flow_dequeue(fq, flow))) free_func(fq, flow->tin, flow, skb); if (!list_empty(&flow->flowchain)) list_del_init(&flow->flowchain); if (!list_empty(&flow->backlogchain)) list_del_init(&flow->backlogchain); flow->tin = NULL; WARN_ON_ONCE(flow->backlog); } static void fq_tin_reset(struct fq *fq, struct fq_tin *tin, fq_skb_free_t free_func) { struct list_head *head; struct fq_flow *flow; for (;;) { head = &tin->new_flows; if (list_empty(head)) { head = &tin->old_flows; if (list_empty(head)) break; } flow = list_first_entry(head, struct fq_flow, flowchain); fq_flow_reset(fq, flow, free_func); } WARN_ON_ONCE(tin->backlog_bytes); WARN_ON_ONCE(tin->backlog_packets); } static void fq_flow_init(struct fq_flow *flow) { INIT_LIST_HEAD(&flow->flowchain); INIT_LIST_HEAD(&flow->backlogchain); __skb_queue_head_init(&flow->queue); } static void fq_tin_init(struct fq_tin *tin) { INIT_LIST_HEAD(&tin->new_flows); INIT_LIST_HEAD(&tin->old_flows); } static int fq_init(struct fq *fq, int flows_cnt) { int i; memset(fq, 0, sizeof(fq[0])); INIT_LIST_HEAD(&fq->backlogs); spin_lock_init(&fq->lock); fq->flows_cnt = max_t(u32, flows_cnt, 1); fq->quantum = 300; fq->limit = 8192; fq->memory_limit = 16 << 20; /* 16 MBytes */ fq->flows = kvcalloc(fq->flows_cnt, sizeof(fq->flows[0]), GFP_KERNEL); if (!fq->flows) return -ENOMEM; for (i = 0; i < fq->flows_cnt; i++) fq_flow_init(&fq->flows[i]); return 0; } static void fq_reset(struct fq *fq, fq_skb_free_t free_func) { int i; for (i = 0; i < fq->flows_cnt; i++) fq_flow_reset(fq, &fq->flows[i], free_func); kvfree(fq->flows); fq->flows = NULL; } #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 /* SPDX-License-Identifier: GPL-2.0 */ /* * Definitions for the UDP-Lite (RFC 3828) code. */ #ifndef _UDPLITE_H #define _UDPLITE_H #include <net/ip6_checksum.h> /* UDP-Lite socket options */ #define UDPLITE_SEND_CSCOV 10 /* sender partial coverage (as sent) */ #define UDPLITE_RECV_CSCOV 11 /* receiver partial coverage (threshold ) */ extern struct proto udplite_prot; extern struct udp_table udplite_table; /* * Checksum computation is all in software, hence simpler getfrag. */ static __inline__ int udplite_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct msghdr *msg = from; return copy_from_iter_full(to, len, &msg->msg_iter) ? 0 : -EFAULT; } /* Designate sk as UDP-Lite socket */ static inline int udplite_sk_init(struct sock *sk) { udp_init_sock(sk); udp_sk(sk)->pcflag = UDPLITE_BIT; return 0; } /* * Checksumming routines */ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh) { u16 cscov; /* In UDPv4 a zero checksum means that the transmitter generated no * checksum. UDP-Lite (like IPv6) mandates checksums, hence packets * with a zero checksum field are illegal. */ if (uh->check == 0) { net_dbg_ratelimited("UDPLite: zeroed checksum field\n"); return 1; } cscov = ntohs(uh->len); if (cscov == 0) /* Indicates that full coverage is required. */ ; else if (cscov < 8 || cscov > skb->len) { /* * Coverage length violates RFC 3828: log and discard silently. */ net_dbg_ratelimited("UDPLite: bad csum coverage %d/%d\n", cscov, skb->len); return 1; } else if (cscov < skb->len) { UDP_SKB_CB(skb)->partial_cov = 1; UDP_SKB_CB(skb)->cscov = cscov; if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; skb->csum_valid = 0; } return 0; } /* Slow-path computation of checksum. Socket is locked. */ static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb) { const struct udp_sock *up = udp_sk(skb->sk); int cscov = up->len; __wsum csum = 0; if (up->pcflag & UDPLITE_SEND_CC) { /* * Sender has set `partial coverage' option on UDP-Lite socket. * The special case "up->pcslen == 0" signifies full coverage. */ if (up->pcslen < up->len) { if (0 < up->pcslen) cscov = up->pcslen; udp_hdr(skb)->len = htons(up->pcslen); } /* * NOTE: Causes for the error case `up->pcslen > up->len': * (i) Application error (will not be penalized). * (ii) Payload too big for send buffer: data is split * into several packets, each with its own header. * In this case (e.g. last segment), coverage may * exceed packet length. * Since packets with coverage length > packet length are * illegal, we fall back to the defaults here. */ } skb->ip_summed = CHECKSUM_NONE; /* no HW support for checksumming */ skb_queue_walk(&sk->sk_write_queue, skb) { const int off = skb_transport_offset(skb); const int len = skb->len - off; csum = skb_checksum(skb, off, (cscov > len)? len : cscov, csum); if ((cscov -= len) <= 0) break; } return csum; } /* Fast-path computation of checksum. Socket may not be locked. */ static inline __wsum udplite_csum(struct sk_buff *skb) { const struct udp_sock *up = udp_sk(skb->sk); const int off = skb_transport_offset(skb); int len = skb->len - off; if ((up->pcflag & UDPLITE_SEND_CC) && up->pcslen < len) { if (0 < up->pcslen) len = up->pcslen; udp_hdr(skb)->len = htons(up->pcslen); } skb->ip_summed = CHECKSUM_NONE; /* no HW support for checksumming */ return skb_checksum(skb, off, len, 0); } void udplite4_register(void); int udplite_get_port(struct sock *sk, unsigned short snum, int (*scmp)(const struct sock *, const struct sock *)); #endif /* _UDPLITE_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 // SPDX-License-Identifier: GPL-2.0 /* * hrtimers - High-resolution kernel timers * * Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005, Red Hat, Inc., Ingo Molnar * * data type definitions, declarations, prototypes * * Started by: Thomas Gleixner and Ingo Molnar */ #ifndef _LINUX_HRTIMER_H #define _LINUX_HRTIMER_H #include <linux/hrtimer_defs.h> #include <linux/rbtree.h> #include <linux/init.h> #include <linux/list.h> #include <linux/percpu.h> #include <linux/seqlock.h> #include <linux/timer.h> #include <linux/timerqueue.h> struct hrtimer_clock_base; struct hrtimer_cpu_base; /* * Mode arguments of xxx_hrtimer functions: * * HRTIMER_MODE_ABS - Time value is absolute * HRTIMER_MODE_REL - Time value is relative to now * HRTIMER_MODE_PINNED - Timer is bound to CPU (is only considered * when starting the timer) * HRTIMER_MODE_SOFT - Timer callback function will be executed in * soft irq context * HRTIMER_MODE_HARD - Timer callback function will be executed in * hard irq context even on PREEMPT_RT. */ enum hrtimer_mode { HRTIMER_MODE_ABS = 0x00, HRTIMER_MODE_REL = 0x01, HRTIMER_MODE_PINNED = 0x02, HRTIMER_MODE_SOFT = 0x04, HRTIMER_MODE_HARD = 0x08, HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED, HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED, HRTIMER_MODE_ABS_SOFT = HRTIMER_MODE_ABS | HRTIMER_MODE_SOFT, HRTIMER_MODE_REL_SOFT = HRTIMER_MODE_REL | HRTIMER_MODE_SOFT, HRTIMER_MODE_ABS_PINNED_SOFT = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_SOFT, HRTIMER_MODE_REL_PINNED_SOFT = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_SOFT, HRTIMER_MODE_ABS_HARD = HRTIMER_MODE_ABS | HRTIMER_MODE_HARD, HRTIMER_MODE_REL_HARD = HRTIMER_MODE_REL | HRTIMER_MODE_HARD, HRTIMER_MODE_ABS_PINNED_HARD = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_HARD, HRTIMER_MODE_REL_PINNED_HARD = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_HARD, }; /* * Return values for the callback function */ enum hrtimer_restart { HRTIMER_NORESTART, /* Timer is not restarted */ HRTIMER_RESTART, /* Timer must be restarted */ }; /* * Values to track state of the timer * * Possible states: * * 0x00 inactive * 0x01 enqueued into rbtree * * The callback state is not part of the timer->state because clearing it would * mean touching the timer after the callback, this makes it impossible to free * the timer from the callback function. * * Therefore we track the callback state in: * * timer->base->cpu_base->running == timer * * On SMP it is possible to have a "callback function running and enqueued" * status. It happens for example when a posix timer expired and the callback * queued a signal. Between dropping the lock which protects the posix timer * and reacquiring the base lock of the hrtimer, another CPU can deliver the * signal and rearm the timer. * * All state transitions are protected by cpu_base->lock. */ #define HRTIMER_STATE_INACTIVE 0x00 #define HRTIMER_STATE_ENQUEUED 0x01 /** * struct hrtimer - the basic hrtimer structure * @node: timerqueue node, which also manages node.expires, * the absolute expiry time in the hrtimers internal * representation. The time is related to the clock on * which the timer is based. Is setup by adding * slack to the _softexpires value. For non range timers * identical to _softexpires. * @_softexpires: the absolute earliest expiry time of the hrtimer. * The time which was given as expiry time when the timer * was armed. * @function: timer expiry callback function * @base: pointer to the timer base (per cpu and per clock) * @state: state information (See bit values above) * @is_rel: Set if the timer was armed relative * @is_soft: Set if hrtimer will be expired in soft interrupt context. * @is_hard: Set if hrtimer will be expired in hard interrupt context * even on RT. * * The hrtimer structure must be initialized by hrtimer_init() */ struct hrtimer { struct timerqueue_node node; ktime_t _softexpires; enum hrtimer_restart (*function)(struct hrtimer *); struct hrtimer_clock_base *base; u8 state; u8 is_rel; u8 is_soft; u8 is_hard; }; /** * struct hrtimer_sleeper - simple sleeper structure * @timer: embedded timer structure * @task: task to wake up * * task is set to NULL, when the timer expires. */ struct hrtimer_sleeper { struct hrtimer timer; struct task_struct *task; }; #ifdef CONFIG_64BIT # define __hrtimer_clock_base_align ____cacheline_aligned #else # define __hrtimer_clock_base_align #endif /** * struct hrtimer_clock_base - the timer base for a specific clock * @cpu_base: per cpu clock base * @index: clock type index for per_cpu support when moving a * timer to a base on another cpu. * @clockid: clock id for per_cpu support * @seq: seqcount around __run_hrtimer * @running: pointer to the currently running hrtimer * @active: red black tree root node for the active timers * @get_time: function to retrieve the current time of the clock * @offset: offset of this clock to the monotonic base */ struct hrtimer_clock_base { struct hrtimer_cpu_base *cpu_base; unsigned int index; clockid_t clockid; seqcount_raw_spinlock_t seq; struct hrtimer *running; struct timerqueue_head active; ktime_t (*get_time)(void); ktime_t offset; } __hrtimer_clock_base_align; enum hrtimer_base_type { HRTIMER_BASE_MONOTONIC, HRTIMER_BASE_REALTIME, HRTIMER_BASE_BOOTTIME, HRTIMER_BASE_TAI, HRTIMER_BASE_MONOTONIC_SOFT, HRTIMER_BASE_REALTIME_SOFT, HRTIMER_BASE_BOOTTIME_SOFT, HRTIMER_BASE_TAI_SOFT, HRTIMER_MAX_CLOCK_BASES, }; /** * struct hrtimer_cpu_base - the per cpu clock bases * @lock: lock protecting the base and associated clock bases * and timers * @cpu: cpu number * @active_bases: Bitfield to mark bases with active timers * @clock_was_set_seq: Sequence counter of clock was set events * @hres_active: State of high resolution mode * @in_hrtirq: hrtimer_interrupt() is currently executing * @hang_detected: The last hrtimer interrupt detected a hang * @softirq_activated: displays, if the softirq is raised - update of softirq * related settings is not required then. * @nr_events: Total number of hrtimer interrupt events * @nr_retries: Total number of hrtimer interrupt retries * @nr_hangs: Total number of hrtimer interrupt hangs * @max_hang_time: Maximum time spent in hrtimer_interrupt * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are * expired * @timer_waiters: A hrtimer_cancel() invocation waits for the timer * callback to finish. * @expires_next: absolute time of the next event, is required for remote * hrtimer enqueue; it is the total first expiry time (hard * and soft hrtimer are taken into account) * @next_timer: Pointer to the first expiring timer * @softirq_expires_next: Time to check, if soft queues needs also to be expired * @softirq_next_timer: Pointer to the first expiring softirq based timer * @clock_base: array of clock bases for this cpu * * Note: next_timer is just an optimization for __remove_hrtimer(). * Do not dereference the pointer because it is not reliable on * cross cpu removals. */ struct hrtimer_cpu_base { raw_spinlock_t lock; unsigned int cpu; unsigned int active_bases; unsigned int clock_was_set_seq; unsigned int hres_active : 1, in_hrtirq : 1, hang_detected : 1, softirq_activated : 1; #ifdef CONFIG_HIGH_RES_TIMERS unsigned int nr_events; unsigned short nr_retries; unsigned short nr_hangs; unsigned int max_hang_time; #endif #ifdef CONFIG_PREEMPT_RT spinlock_t softirq_expiry_lock; atomic_t timer_waiters; #endif ktime_t expires_next; struct hrtimer *next_timer; ktime_t softirq_expires_next; struct hrtimer *softirq_next_timer; struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; } ____cacheline_aligned; static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time) { timer->node.expires = time; timer->_softexpires = time; } static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time, ktime_t delta) { timer->_softexpires = time; timer->node.expires = ktime_add_safe(time, delta); } static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, u64 delta) { timer->_softexpires = time; timer->node.expires = ktime_add_safe(time, ns_to_ktime(delta)); } static inline void hrtimer_set_expires_tv64(struct hrtimer *timer, s64 tv64) { timer->node.expires = tv64; timer->_softexpires = tv64; } static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time) { timer->node.expires = ktime_add_safe(timer->node.expires, time); timer->_softexpires = ktime_add_safe(timer->_softexpires, time); } static inline void hrtimer_add_expires_ns(struct hrtimer *timer, u64 ns) { timer->node.expires = ktime_add_ns(timer->node.expires, ns); timer->_softexpires = ktime_add_ns(timer->_softexpires, ns); } static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer) { return timer->node.expires; } static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer) { return timer->_softexpires; } static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer) { return timer->node.expires; } static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer) { return timer->_softexpires; } static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer) { return ktime_to_ns(timer->node.expires); } static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer) { return ktime_sub(timer->node.expires, timer->base->get_time()); } static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer) { return timer->base->get_time(); } static inline int hrtimer_is_hres_active(struct hrtimer *timer) { return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ? timer->base->cpu_base->hres_active : 0; } #ifdef CONFIG_HIGH_RES_TIMERS struct clock_event_device; extern void hrtimer_interrupt(struct clock_event_device *dev); extern unsigned int hrtimer_resolution; #else #define hrtimer_resolution (unsigned int)LOW_RES_NSEC #endif static inline ktime_t __hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now) { ktime_t rem = ktime_sub(timer->node.expires, now); /* * Adjust relative timers for the extra we added in * hrtimer_start_range_ns() to prevent short timeouts. */ if (IS_ENABLED(CONFIG_TIME_LOW_RES) && timer->is_rel) rem -= hrtimer_resolution; return rem; } static inline ktime_t hrtimer_expires_remaining_adjusted(const struct hrtimer *timer) { return __hrtimer_expires_remaining_adjusted(timer, timer->base->get_time()); } #ifdef CONFIG_TIMERFD extern void timerfd_clock_was_set(void); #else static inline void timerfd_clock_was_set(void) { } #endif extern void hrtimers_resume(void); DECLARE_PER_CPU(struct tick_device, tick_cpu_device); #ifdef CONFIG_PREEMPT_RT void hrtimer_cancel_wait_running(const struct hrtimer *timer); #else static inline void hrtimer_cancel_wait_running(struct hrtimer *timer) { cpu_relax(); } #endif /* Exported timer functions: */ /* Initialize timers: */ extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode); extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode); extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode); extern void destroy_hrtimer_on_stack(struct hrtimer *timer); #else static inline void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode) { hrtimer_init(timer, which_clock, mode); } static inline void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { hrtimer_init_sleeper(sl, clock_id, mode); } static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } #endif /* Basic timer operations: */ extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 range_ns, const enum hrtimer_mode mode); /** * hrtimer_start - (re)start an hrtimer * @timer: the timer to be added * @tim: expiry time * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED); * softirq based mode is considered for debug purpose only! */ static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) { hrtimer_start_range_ns(timer, tim, 0, mode); } extern int hrtimer_cancel(struct hrtimer *timer); extern int hrtimer_try_to_cancel(struct hrtimer *timer); static inline void hrtimer_start_expires(struct hrtimer *timer, enum hrtimer_mode mode) { u64 delta; ktime_t soft, hard; soft = hrtimer_get_softexpires(timer); hard = hrtimer_get_expires(timer); delta = ktime_to_ns(ktime_sub(hard, soft)); hrtimer_start_range_ns(timer, soft, delta, mode); } void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, enum hrtimer_mode mode); static inline void hrtimer_restart(struct hrtimer *timer) { hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } /* Query timers: */ extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer) { return __hrtimer_get_remaining(timer, false); } extern u64 hrtimer_get_next_event(void); extern u64 hrtimer_next_event_without(const struct hrtimer *exclude); extern bool hrtimer_active(const struct hrtimer *timer); /** * hrtimer_is_queued = check, whether the timer is on one of the queues * @timer: Timer to check * * Returns: True if the timer is queued, false otherwise * * The function can be used lockless, but it gives only a current snapshot. */ static inline bool hrtimer_is_queued(struct hrtimer *timer) { /* The READ_ONCE pairs with the update functions of timer->state */ return !!(READ_ONCE(timer->state) & HRTIMER_STATE_ENQUEUED); } /* * Helper function to check, whether the timer is running the callback * function */ static inline int hrtimer_callback_running(struct hrtimer *timer) { return timer->base->running == timer; } /* Forward a hrtimer so it expires after now: */ extern u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval); /** * hrtimer_forward_now - forward the timer expiry so it expires after now * @timer: hrtimer to forward * @interval: the interval to forward * * Forward the timer expiry so it will expire after the current time * of the hrtimer clock base. Returns the number of overruns. * * Can be safely called from the callback function of @timer. If * called from other contexts @timer must neither be enqueued nor * running the callback and the caller needs to take care of * serialization. * * Note: This only updates the timer expiry value and does not requeue * the timer. */ static inline u64 hrtimer_forward_now(struct hrtimer *timer, ktime_t interval) { return hrtimer_forward(timer, timer->base->get_time(), interval); } /* Precise sleep: */ extern int nanosleep_copyout(struct restart_block *, struct timespec64 *); extern long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, const clockid_t clockid); extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode); extern int schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, const enum hrtimer_mode mode, clockid_t clock_id); extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode); /* Soft interrupt function to run the hrtimer queues: */ extern void hrtimer_run_queues(void); /* Bootup initialization: */ extern void __init hrtimers_init(void); /* Show pending timers: */ extern void sysrq_timer_list_show(void); int hrtimers_prepare_cpu(unsigned int cpu); #ifdef CONFIG_HOTPLUG_CPU int hrtimers_dead_cpu(unsigned int cpu); #else #define hrtimers_dead_cpu NULL #endif #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_DAX_H #define _LINUX_DAX_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/radix-tree.h> /* Flag for synchronous flush */ #define DAXDEV_F_SYNC (1UL << 0) typedef unsigned long dax_entry_t; struct iomap_ops; struct iomap; struct dax_device; struct dax_operations { /* * direct_access: translate a device-relative * logical-page-offset into an absolute physical pfn. Return the * number of pages available for DAX at that pfn. */ long (*direct_access)(struct dax_device *, pgoff_t, long, void **, pfn_t *); /* * Validate whether this device is usable as an fsdax backing * device. */ bool (*dax_supported)(struct dax_device *, struct block_device *, int, sector_t, sector_t); /* copy_from_iter: required operation for fs-dax direct-i/o */ size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t, struct iov_iter *); /* copy_to_iter: required operation for fs-dax direct-i/o */ size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t, struct iov_iter *); /* zero_page_range: required operation. Zero page range */ int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); }; extern struct attribute_group dax_attribute_group; #if IS_ENABLED(CONFIG_DAX) struct dax_device *dax_get_by_host(const char *host); struct dax_device *alloc_dax(void *private, const char *host, const struct dax_operations *ops, unsigned long flags); void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); bool __dax_synchronous(struct dax_device *dax_dev); static inline bool dax_synchronous(struct dax_device *dax_dev) { return __dax_synchronous(dax_dev); } void __set_dax_synchronous(struct dax_device *dax_dev); static inline void set_dax_synchronous(struct dax_device *dax_dev) { __set_dax_synchronous(dax_dev); } bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t len); /* * Check if given mapping is supported by the file / underlying device. */ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { if (!(vma->vm_flags & VM_SYNC)) return true; if (!IS_DAX(file_inode(vma->vm_file))) return false; return dax_synchronous(dax_dev); } #else static inline struct dax_device *dax_get_by_host(const char *host) { return NULL; } static inline struct dax_device *alloc_dax(void *private, const char *host, const struct dax_operations *ops, unsigned long flags) { /* * Callers should check IS_ENABLED(CONFIG_DAX) to know if this * NULL is an error or expected. */ return NULL; } static inline void put_dax(struct dax_device *dax_dev) { } static inline void kill_dax(struct dax_device *dax_dev) { } static inline void dax_write_cache(struct dax_device *dax_dev, bool wc) { } static inline bool dax_write_cache_enabled(struct dax_device *dax_dev) { return false; } static inline bool dax_synchronous(struct dax_device *dax_dev) { return true; } static inline void set_dax_synchronous(struct dax_device *dax_dev) { } static inline bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t len) { return false; } static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { return !(vma->vm_flags & VM_SYNC); } #endif struct writeback_control; int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); #if IS_ENABLED(CONFIG_FS_DAX) bool __bdev_dax_supported(struct block_device *bdev, int blocksize); static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize) { return __bdev_dax_supported(bdev, blocksize); } bool __generic_fsdax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t sectors); static inline bool generic_fsdax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t sectors) { return __generic_fsdax_supported(dax_dev, bdev, blocksize, start, sectors); } static inline void fs_put_dax(struct dax_device *dax_dev) { put_dax(dax_dev); } struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev); int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc); struct page *dax_layout_busy_page(struct address_space *mapping); struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); dax_entry_t dax_lock_page(struct page *page); void dax_unlock_page(struct page *page, dax_entry_t cookie); #else static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize) { return false; } static inline bool generic_fsdax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t sectors) { return false; } static inline void fs_put_dax(struct dax_device *dax_dev) { } static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) { return NULL; } static inline struct page *dax_layout_busy_page(struct address_space *mapping) { return NULL; } static inline struct page *dax_layout_busy_page_range(struct address_space *mapping, pgoff_t start, pgoff_t nr_pages) { return NULL; } static inline int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc) { return -EOPNOTSUPP; } static inline dax_entry_t dax_lock_page(struct page *page) { if (IS_DAX(page->mapping->host)) return ~0UL; return 0; } static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) { } #endif #if IS_ENABLED(CONFIG_DAX) int dax_read_lock(void); void dax_read_unlock(int id); #else static inline int dax_read_lock(void) { return 0; } static inline void dax_read_unlock(int id) { } #endif /* CONFIG_DAX */ bool dax_alive(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops); vm_fault_t dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, pfn_t *pfnp, int *errp, const struct iomap_ops *ops); vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, enum page_entry_size pe_size, pfn_t pfn); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); } #ifdef CONFIG_DEV_DAX_HMEM_DEVICES void hmem_register_device(int target_nid, struct resource *r); #else static inline void hmem_register_device(int target_nid, struct resource *r) { } #endif #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 1999-2002 Vojtech Pavlik */ #ifndef _INPUT_H #define _INPUT_H #include <linux/time.h> #include <linux/list.h> #include <uapi/linux/input.h> /* Implementation details, userspace should not care about these */ #define ABS_MT_FIRST ABS_MT_TOUCH_MAJOR #define ABS_MT_LAST ABS_MT_TOOL_Y /* * In-kernel definitions. */ #include <linux/device.h> #include <linux/fs.h> #include <linux/timer.h> #include <linux/mod_devicetable.h> struct input_dev_poller; /** * struct input_value - input value representation * @type: type of value (EV_KEY, EV_ABS, etc) * @code: the value code * @value: the value */ struct input_value { __u16 type; __u16 code; __s32 value; }; enum input_clock_type { INPUT_CLK_REAL = 0, INPUT_CLK_MONO, INPUT_CLK_BOOT, INPUT_CLK_MAX }; /** * struct input_dev - represents an input device * @name: name of the device * @phys: physical path to the device in the system hierarchy * @uniq: unique identification code for the device (if device has it) * @id: id of the device (struct input_id) * @propbit: bitmap of device properties and quirks * @evbit: bitmap of types of events supported by the device (EV_KEY, * EV_REL, etc.) * @keybit: bitmap of keys/buttons this device has * @relbit: bitmap of relative axes for the device * @absbit: bitmap of absolute axes for the device * @mscbit: bitmap of miscellaneous events supported by the device * @ledbit: bitmap of leds present on the device * @sndbit: bitmap of sound effects supported by the device * @ffbit: bitmap of force feedback effects supported by the device * @swbit: bitmap of switches present on the device * @hint_events_per_packet: average number of events generated by the * device in a packet (between EV_SYN/SYN_REPORT events). Used by * event handlers to estimate size of the buffer needed to hold * events. * @keycodemax: size of keycode table * @keycodesize: size of elements in keycode table * @keycode: map of scancodes to keycodes for this device * @getkeycode: optional legacy method to retrieve current keymap. * @setkeycode: optional method to alter current keymap, used to implement * sparse keymaps. If not supplied default mechanism will be used. * The method is being called while holding event_lock and thus must * not sleep * @ff: force feedback structure associated with the device if device * supports force feedback effects * @poller: poller structure associated with the device if device is * set up to use polling mode * @repeat_key: stores key code of the last key pressed; used to implement * software autorepeat * @timer: timer for software autorepeat * @rep: current values for autorepeat parameters (delay, rate) * @mt: pointer to multitouch state * @absinfo: array of &struct input_absinfo elements holding information * about absolute axes (current value, min, max, flat, fuzz, * resolution) * @key: reflects current state of device's keys/buttons * @led: reflects current state of device's LEDs * @snd: reflects current state of sound effects * @sw: reflects current state of device's switches * @open: this method is called when the very first user calls * input_open_device(). The driver must prepare the device * to start generating events (start polling thread, * request an IRQ, submit URB, etc.) * @close: this method is called when the very last user calls * input_close_device(). * @flush: purges the device. Most commonly used to get rid of force * feedback effects loaded into the device when disconnecting * from it * @event: event handler for events sent _to_ the device, like EV_LED * or EV_SND. The device is expected to carry out the requested * action (turn on a LED, play sound, etc.) The call is protected * by @event_lock and must not sleep * @grab: input handle that currently has the device grabbed (via * EVIOCGRAB ioctl). When a handle grabs a device it becomes sole * recipient for all input events coming from the device * @event_lock: this spinlock is taken when input core receives * and processes a new event for the device (in input_event()). * Code that accesses and/or modifies parameters of a device * (such as keymap or absmin, absmax, absfuzz, etc.) after device * has been registered with input core must take this lock. * @mutex: serializes calls to open(), close() and flush() methods * @users: stores number of users (input handlers) that opened this * device. It is used by input_open_device() and input_close_device() * to make sure that dev->open() is only called when the first * user opens device and dev->close() is called when the very * last user closes the device * @going_away: marks devices that are in a middle of unregistering and * causes input_open_device*() fail with -ENODEV. * @dev: driver model's view of this device * @h_list: list of input handles associated with the device. When * accessing the list dev->mutex must be held * @node: used to place the device onto input_dev_list * @num_vals: number of values queued in the current frame * @max_vals: maximum number of values queued in a frame * @vals: array of values queued in the current frame * @devres_managed: indicates that devices is managed with devres framework * and needs not be explicitly unregistered or freed. * @timestamp: storage for a timestamp set by input_set_timestamp called * by a driver */ struct input_dev { const char *name; const char *phys; const char *uniq; struct input_id id; unsigned long propbit[BITS_TO_LONGS(INPUT_PROP_CNT)]; unsigned long evbit[BITS_TO_LONGS(EV_CNT)]; unsigned long keybit[BITS_TO_LONGS(KEY_CNT)]; unsigned long relbit[BITS_TO_LONGS(REL_CNT)]; unsigned long absbit[BITS_TO_LONGS(ABS_CNT)]; unsigned long mscbit[BITS_TO_LONGS(MSC_CNT)]; unsigned long ledbit[BITS_TO_LONGS(LED_CNT)]; unsigned long sndbit[BITS_TO_LONGS(SND_CNT)]; unsigned long ffbit[BITS_TO_LONGS(FF_CNT)]; unsigned long swbit[BITS_TO_LONGS(SW_CNT)]; unsigned int hint_events_per_packet; unsigned int keycodemax; unsigned int keycodesize; void *keycode; int (*setkeycode)(struct input_dev *dev, const struct input_keymap_entry *ke, unsigned int *old_keycode); int (*getkeycode)(struct input_dev *dev, struct input_keymap_entry *ke); struct ff_device *ff; struct input_dev_poller *poller; unsigned int repeat_key; struct timer_list timer; int rep[REP_CNT]; struct input_mt *mt; struct input_absinfo *absinfo; unsigned long key[BITS_TO_LONGS(KEY_CNT)]; unsigned long led[BITS_TO_LONGS(LED_CNT)]; unsigned long snd[BITS_TO_LONGS(SND_CNT)]; unsigned long sw[BITS_TO_LONGS(SW_CNT)]; int (*open)(struct input_dev *dev); void (*close)(struct input_dev *dev); int (*flush)(struct input_dev *dev, struct file *file); int (*event)(struct input_dev *dev, unsigned int type, unsigned int code, int value); struct input_handle __rcu *grab; spinlock_t event_lock; struct mutex mutex; unsigned int users; bool going_away; struct device dev; struct list_head h_list; struct list_head node; unsigned int num_vals; unsigned int max_vals; struct input_value *vals; bool devres_managed; ktime_t timestamp[INPUT_CLK_MAX]; }; #define to_input_dev(d) container_of(d, struct input_dev, dev) /* * Verify that we are in sync with input_device_id mod_devicetable.h #defines */ #if EV_MAX != INPUT_DEVICE_ID_EV_MAX #error "EV_MAX and INPUT_DEVICE_ID_EV_MAX do not match" #endif #if KEY_MIN_INTERESTING != INPUT_DEVICE_ID_KEY_MIN_INTERESTING #error "KEY_MIN_INTERESTING and INPUT_DEVICE_ID_KEY_MIN_INTERESTING do not match" #endif #if KEY_MAX != INPUT_DEVICE_ID_KEY_MAX #error "KEY_MAX and INPUT_DEVICE_ID_KEY_MAX do not match" #endif #if REL_MAX != INPUT_DEVICE_ID_REL_MAX #error "REL_MAX and INPUT_DEVICE_ID_REL_MAX do not match" #endif #if ABS_MAX != INPUT_DEVICE_ID_ABS_MAX #error "ABS_MAX and INPUT_DEVICE_ID_ABS_MAX do not match" #endif #if MSC_MAX != INPUT_DEVICE_ID_MSC_MAX #error "MSC_MAX and INPUT_DEVICE_ID_MSC_MAX do not match" #endif #if LED_MAX != INPUT_DEVICE_ID_LED_MAX #error "LED_MAX and INPUT_DEVICE_ID_LED_MAX do not match" #endif #if SND_MAX != INPUT_DEVICE_ID_SND_MAX #error "SND_MAX and INPUT_DEVICE_ID_SND_MAX do not match" #endif #if FF_MAX != INPUT_DEVICE_ID_FF_MAX #error "FF_MAX and INPUT_DEVICE_ID_FF_MAX do not match" #endif #if SW_MAX != INPUT_DEVICE_ID_SW_MAX #error "SW_MAX and INPUT_DEVICE_ID_SW_MAX do not match" #endif #if INPUT_PROP_MAX != INPUT_DEVICE_ID_PROP_MAX #error "INPUT_PROP_MAX and INPUT_DEVICE_ID_PROP_MAX do not match" #endif #define INPUT_DEVICE_ID_MATCH_DEVICE \ (INPUT_DEVICE_ID_MATCH_BUS | INPUT_DEVICE_ID_MATCH_VENDOR | INPUT_DEVICE_ID_MATCH_PRODUCT) #define INPUT_DEVICE_ID_MATCH_DEVICE_AND_VERSION \ (INPUT_DEVICE_ID_MATCH_DEVICE | INPUT_DEVICE_ID_MATCH_VERSION) struct input_handle; /** * struct input_handler - implements one of interfaces for input devices * @private: driver-specific data * @event: event handler. This method is being called by input core with * interrupts disabled and dev->event_lock spinlock held and so * it may not sleep * @events: event sequence handler. This method is being called by * input core with interrupts disabled and dev->event_lock * spinlock held and so it may not sleep * @filter: similar to @event; separates normal event handlers from * "filters". * @match: called after comparing device's id with handler's id_table * to perform fine-grained matching between device and handler * @connect: called when attaching a handler to an input device * @disconnect: disconnects a handler from input device * @start: starts handler for given handle. This function is called by * input core right after connect() method and also when a process * that "grabbed" a device releases it * @legacy_minors: set to %true by drivers using legacy minor ranges * @minor: beginning of range of 32 legacy minors for devices this driver * can provide * @name: name of the handler, to be shown in /proc/bus/input/handlers * @id_table: pointer to a table of input_device_ids this driver can * handle * @h_list: list of input handles associated with the handler * @node: for placing the driver onto input_handler_list * * Input handlers attach to input devices and create input handles. There * are likely several handlers attached to any given input device at the * same time. All of them will get their copy of input event generated by * the device. * * The very same structure is used to implement input filters. Input core * allows filters to run first and will not pass event to regular handlers * if any of the filters indicate that the event should be filtered (by * returning %true from their filter() method). * * Note that input core serializes calls to connect() and disconnect() * methods. */ struct input_handler { void *private; void (*event)(struct input_handle *handle, unsigned int type, unsigned int code, int value); void (*events)(struct input_handle *handle, const struct input_value *vals, unsigned int count); bool (*filter)(struct input_handle *handle, unsigned int type, unsigned int code, int value); bool (*match)(struct input_handler *handler, struct input_dev *dev); int (*connect)(struct input_handler *handler, struct input_dev *dev, const struct input_device_id *id); void (*disconnect)(struct input_handle *handle); void (*start)(struct input_handle *handle); bool legacy_minors; int minor; const char *name; const struct input_device_id *id_table; struct list_head h_list; struct list_head node; }; /** * struct input_handle - links input device with an input handler * @private: handler-specific data * @open: counter showing whether the handle is 'open', i.e. should deliver * events from its device * @name: name given to the handle by handler that created it * @dev: input device the handle is attached to * @handler: handler that works with the device through this handle * @d_node: used to put the handle on device's list of attached handles * @h_node: used to put the handle on handler's list of handles from which * it gets events */ struct input_handle { void *private; int open; const char *name; struct input_dev *dev; struct input_handler *handler; struct list_head d_node; struct list_head h_node; }; struct input_dev __must_check *input_allocate_device(void); struct input_dev __must_check *devm_input_allocate_device(struct device *); void input_free_device(struct input_dev *dev); static inline struct input_dev *input_get_device(struct input_dev *dev) { return dev ? to_input_dev(get_device(&dev->dev)) : NULL; } static inline void input_put_device(struct input_dev *dev) { if (dev) put_device(&dev->dev); } static inline void *input_get_drvdata(struct input_dev *dev) { return dev_get_drvdata(&dev->dev); } static inline void input_set_drvdata(struct input_dev *dev, void *data) { dev_set_drvdata(&dev->dev, data); } int __must_check input_register_device(struct input_dev *); void input_unregister_device(struct input_dev *); void input_reset_device(struct input_dev *); int input_setup_polling(struct input_dev *dev, void (*poll_fn)(struct input_dev *dev)); void input_set_poll_interval(struct input_dev *dev, unsigned int interval); void input_set_min_poll_interval(struct input_dev *dev, unsigned int interval); void input_set_max_poll_interval(struct input_dev *dev, unsigned int interval); int input_get_poll_interval(struct input_dev *dev); int __must_check input_register_handler(struct input_handler *); void input_unregister_handler(struct input_handler *); int __must_check input_get_new_minor(int legacy_base, unsigned int legacy_num, bool allow_dynamic); void input_free_minor(unsigned int minor); int input_handler_for_each_handle(struct input_handler *, void *data, int (*fn)(struct input_handle *, void *)); int input_register_handle(struct input_handle *); void input_unregister_handle(struct input_handle *); int input_grab_device(struct input_handle *); void input_release_device(struct input_handle *); int input_open_device(struct input_handle *); void input_close_device(struct input_handle *); int input_flush_device(struct input_handle *handle, struct file *file); void input_set_timestamp(struct input_dev *dev, ktime_t timestamp); ktime_t *input_get_timestamp(struct input_dev *dev); void input_event(struct input_dev *dev, unsigned int type, unsigned int code, int value); void input_inject_event(struct input_handle *handle, unsigned int type, unsigned int code, int value); static inline void input_report_key(struct input_dev *dev, unsigned int code, int value) { input_event(dev, EV_KEY, code, !!value); } static inline void input_report_rel(struct input_dev *dev, unsigned int code, int value) { input_event(dev, EV_REL, code, value); } static inline void input_report_abs(struct input_dev *dev, unsigned int code, int value) { input_event(dev, EV_ABS, code, value); } static inline void input_report_ff_status(struct input_dev *dev, unsigned int code, int value) { input_event(dev, EV_FF_STATUS, code, value); } static inline void input_report_switch(struct input_dev *dev, unsigned int code, int value) { input_event(dev, EV_SW, code, !!value); } static inline void input_sync(struct input_dev *dev) { input_event(dev, EV_SYN, SYN_REPORT, 0); } static inline void input_mt_sync(struct input_dev *dev) { input_event(dev, EV_SYN, SYN_MT_REPORT, 0); } void input_set_capability(struct input_dev *dev, unsigned int type, unsigned int code); /** * input_set_events_per_packet - tell handlers about the driver event rate * @dev: the input device used by the driver * @n_events: the average number of events between calls to input_sync() * * If the event rate sent from a device is unusually large, use this * function to set the expected event rate. This will allow handlers * to set up an appropriate buffer size for the event stream, in order * to minimize information loss. */ static inline void input_set_events_per_packet(struct input_dev *dev, int n_events) { dev->hint_events_per_packet = n_events; } void input_alloc_absinfo(struct input_dev *dev); void input_set_abs_params(struct input_dev *dev, unsigned int axis, int min, int max, int fuzz, int flat); #define INPUT_GENERATE_ABS_ACCESSORS(_suffix, _item) \ static inline int input_abs_get_##_suffix(struct input_dev *dev, \ unsigned int axis) \ { \ return dev->absinfo ? dev->absinfo[axis]._item : 0; \ } \ \ static inline void input_abs_set_##_suffix(struct input_dev *dev, \ unsigned int axis, int val) \ { \ input_alloc_absinfo(dev); \ if (dev->absinfo) \ dev->absinfo[axis]._item = val; \ } INPUT_GENERATE_ABS_ACCESSORS(val, value) INPUT_GENERATE_ABS_ACCESSORS(min, minimum) INPUT_GENERATE_ABS_ACCESSORS(max, maximum) INPUT_GENERATE_ABS_ACCESSORS(fuzz, fuzz) INPUT_GENERATE_ABS_ACCESSORS(flat, flat) INPUT_GENERATE_ABS_ACCESSORS(res, resolution) int input_scancode_to_scalar(const struct input_keymap_entry *ke, unsigned int *scancode); int input_get_keycode(struct input_dev *dev, struct input_keymap_entry *ke); int input_set_keycode(struct input_dev *dev, const struct input_keymap_entry *ke); bool input_match_device_id(const struct input_dev *dev, const struct input_device_id *id); void input_enable_softrepeat(struct input_dev *dev, int delay, int period); extern struct class input_class; /** * struct ff_device - force-feedback part of an input device * @upload: Called to upload an new effect into device * @erase: Called to erase an effect from device * @playback: Called to request device to start playing specified effect * @set_gain: Called to set specified gain * @set_autocenter: Called to auto-center device * @destroy: called by input core when parent input device is being * destroyed * @private: driver-specific data, will be freed automatically * @ffbit: bitmap of force feedback capabilities truly supported by * device (not emulated like ones in input_dev->ffbit) * @mutex: mutex for serializing access to the device * @max_effects: maximum number of effects supported by device * @effects: pointer to an array of effects currently loaded into device * @effect_owners: array of effect owners; when file handle owning * an effect gets closed the effect is automatically erased * * Every force-feedback device must implement upload() and playback() * methods; erase() is optional. set_gain() and set_autocenter() need * only be implemented if driver sets up FF_GAIN and FF_AUTOCENTER * bits. * * Note that playback(), set_gain() and set_autocenter() are called with * dev->event_lock spinlock held and interrupts off and thus may not * sleep. */ struct ff_device { int (*upload)(struct input_dev *dev, struct ff_effect *effect, struct ff_effect *old); int (*erase)(struct input_dev *dev, int effect_id); int (*playback)(struct input_dev *dev, int effect_id, int value); void (*set_gain)(struct input_dev *dev, u16 gain); void (*set_autocenter)(struct input_dev *dev, u16 magnitude); void (*destroy)(struct ff_device *); void *private; unsigned long ffbit[BITS_TO_LONGS(FF_CNT)]; struct mutex mutex; int max_effects; struct ff_effect *effects; struct file *effect_owners[]; }; int input_ff_create(struct input_dev *dev, unsigned int max_effects); void input_ff_destroy(struct input_dev *dev); int input_ff_event(struct input_dev *dev, unsigned int type, unsigned int code, int value); int input_ff_upload(struct input_dev *dev, struct ff_effect *effect, struct file *file); int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file); int input_ff_flush(struct input_dev *dev, struct file *file); int input_ff_create_memless(struct input_dev *dev, void *data, int (*play_effect)(struct input_dev *, void *, struct ff_effect *)); #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the RAW-IP module. * * Version: @(#)raw.h 1.0.2 05/07/93 * * Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _RAW_H #define _RAW_H #include <net/inet_sock.h> #include <net/protocol.h> #include <linux/icmp.h> extern struct proto raw_prot; extern struct raw_hashinfo raw_v4_hashinfo; struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, unsigned short num, __be32 raddr, __be32 laddr, int dif, int sdif); int raw_abort(struct sock *sk, int err); void raw_icmp_error(struct sk_buff *, int, u32); int raw_local_deliver(struct sk_buff *, int); int raw_rcv(struct sock *, struct sk_buff *); #define RAW_HTABLE_SIZE MAX_INET_PROTOS struct raw_hashinfo { rwlock_t lock; struct hlist_head ht[RAW_HTABLE_SIZE]; }; #ifdef CONFIG_PROC_FS int raw_proc_init(void); void raw_proc_exit(void); struct raw_iter_state { struct seq_net_private p; int bucket; }; static inline struct raw_iter_state *raw_seq_private(struct seq_file *seq) { return seq->private; } void *raw_seq_start(struct seq_file *seq, loff_t *pos); void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos); void raw_seq_stop(struct seq_file *seq, void *v); #endif int raw_hash_sk(struct sock *sk); void raw_unhash_sk(struct sock *sk); void raw_init(void); struct raw_sock { /* inet_sock has to be the first member */ struct inet_sock inet; struct icmp_filter filter; u32 ipmr_table; }; static inline struct raw_sock *raw_sk(const struct sock *sk) { return (struct raw_sock *)sk; } static inline bool raw_sk_bound_dev_eq(struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) return inet_bound_dev_eq(!!net->ipv4.sysctl_raw_l3mdev_accept, bound_dev_if, dif, sdif); #else return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); #endif } #endif /* _RAW_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CLEANCACHE_H #define _LINUX_CLEANCACHE_H #include <linux/fs.h> #include <linux/exportfs.h> #include <linux/mm.h> #define CLEANCACHE_NO_POOL -1 #define CLEANCACHE_NO_BACKEND -2 #define CLEANCACHE_NO_BACKEND_SHARED -3 #define CLEANCACHE_KEY_MAX 6 /* * cleancache requires every file with a page in cleancache to have a * unique key unless/until the file is removed/truncated. For some * filesystems, the inode number is unique, but for "modern" filesystems * an exportable filehandle is required (see exportfs.h) */ struct cleancache_filekey { union { ino_t ino; __u32 fh[CLEANCACHE_KEY_MAX]; u32 key[CLEANCACHE_KEY_MAX]; } u; }; struct cleancache_ops { int (*init_fs)(size_t); int (*init_shared_fs)(uuid_t *uuid, size_t); int (*get_page)(int, struct cleancache_filekey, pgoff_t, struct page *); void (*put_page)(int, struct cleancache_filekey, pgoff_t, struct page *); void (*invalidate_page)(int, struct cleancache_filekey, pgoff_t); void (*invalidate_inode)(int, struct cleancache_filekey); void (*invalidate_fs)(int); }; extern int cleancache_register_ops(const struct cleancache_ops *ops); extern void __cleancache_init_fs(struct super_block *); extern void __cleancache_init_shared_fs(struct super_block *); extern int __cleancache_get_page(struct page *); extern void __cleancache_put_page(struct page *); extern void __cleancache_invalidate_page(struct address_space *, struct page *); extern void __cleancache_invalidate_inode(struct address_space *); extern void __cleancache_invalidate_fs(struct super_block *); #ifdef CONFIG_CLEANCACHE #define cleancache_enabled (1) static inline bool cleancache_fs_enabled_mapping(struct address_space *mapping) { return mapping->host->i_sb->cleancache_poolid >= 0; } static inline bool cleancache_fs_enabled(struct page *page) { return cleancache_fs_enabled_mapping(page->mapping); } #else #define cleancache_enabled (0) #define cleancache_fs_enabled(_page) (0) #define cleancache_fs_enabled_mapping(_page) (0) #endif /* * The shim layer provided by these inline functions allows the compiler * to reduce all cleancache hooks to nothingness if CONFIG_CLEANCACHE * is disabled, to a single global variable check if CONFIG_CLEANCACHE * is enabled but no cleancache "backend" has dynamically enabled it, * and, for the most frequent cleancache ops, to a single global variable * check plus a superblock element comparison if CONFIG_CLEANCACHE is enabled * and a cleancache backend has dynamically enabled cleancache, but the * filesystem referenced by that cleancache op has not enabled cleancache. * As a result, CONFIG_CLEANCACHE can be enabled by default with essentially * no measurable performance impact. */ static inline void cleancache_init_fs(struct super_block *sb) { if (cleancache_enabled) __cleancache_init_fs(sb); } static inline void cleancache_init_shared_fs(struct super_block *sb) { if (cleancache_enabled) __cleancache_init_shared_fs(sb); } static inline int cleancache_get_page(struct page *page) { if (cleancache_enabled && cleancache_fs_enabled(page)) return __cleancache_get_page(page); return -1; } static inline void cleancache_put_page(struct page *page) { if (cleancache_enabled && cleancache_fs_enabled(page)) __cleancache_put_page(page); } static inline void cleancache_invalidate_page(struct address_space *mapping, struct page *page) { /* careful... page->mapping is NULL sometimes when this is called */ if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping)) __cleancache_invalidate_page(mapping, page); } static inline void cleancache_invalidate_inode(struct address_space *mapping) { if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping)) __cleancache_invalidate_inode(mapping); } static inline void cleancache_invalidate_fs(struct super_block *sb) { if (cleancache_enabled) __cleancache_invalidate_fs(sb); } #endif /* _LINUX_CLEANCACHE_H */
1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 // SPDX-License-Identifier: GPL-2.0-only /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Implementation of the Transmission Control Protocol(TCP). * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche, <flla@stud.uni-sb.de> * Charles Hedrick, <hedrick@klinzhai.rutgers.edu> * Linus Torvalds, <torvalds@cs.helsinki.fi> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Matthew Dillon, <dillon@apollo.west.oic.com> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Jorge Cwik, <jorge@laser.satlink.net> */ /* * Changes: Pedro Roque : Retransmit queue handled by TCP. * : Fragmentation on mtu decrease * : Segment collapse on retransmit * : AF independence * * Linus Torvalds : send_delayed_ack * David S. Miller : Charge memory using the right skb * during syn/ack processing. * David S. Miller : Output engine completely rewritten. * Andrea Arcangeli: SYNACK carry ts_recent in tsecr. * Cacophonix Gaul : draft-minshall-nagle-01 * J Hadi Salim : ECN support * */ #define pr_fmt(fmt) "TCP: " fmt #include <net/tcp.h> #include <net/mptcp.h> #include <linux/compiler.h> #include <linux/gfp.h> #include <linux/module.h> #include <linux/static_key.h> #include <trace/events/tcp.h> /* Refresh clocks of a TCP socket, * ensuring monotically increasing values. */ void tcp_mstamp_refresh(struct tcp_sock *tp) { u64 val = tcp_clock_ns(); tp->tcp_clock_cache = val; tp->tcp_mstamp = div_u64(val, NSEC_PER_USEC); } static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp); /* Account for new data that has been sent to the network. */ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out; WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(skb)->end_seq); __skb_unlink(skb, &sk->sk_write_queue); tcp_rbtree_insert(&sk->tcp_rtx_queue, skb); if (tp->highest_sack == NULL) tp->highest_sack = skb; tp->packets_out += tcp_skb_pcount(skb); if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, tcp_skb_pcount(skb)); } /* SND.NXT, if window was not shrunk or the amount of shrunk was less than one * window scaling factor due to loss of precision. * If window has been shrunk, what should we make? It is not clear at all. * Using SND.UNA we will fail to open window, SND.NXT is out of window. :-( * Anything in between SND.UNA...SND.UNA+SND.WND also can be already * invalid. OK, let's make this for now: */ static inline __u32 tcp_acceptable_seq(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); if (!before(tcp_wnd_end(tp), tp->snd_nxt) || (tp->rx_opt.wscale_ok && ((tp->snd_nxt - tcp_wnd_end(tp)) < (1 << tp->rx_opt.rcv_wscale)))) return tp->snd_nxt; else return tcp_wnd_end(tp); } /* Calculate mss to advertise in SYN segment. * RFC1122, RFC1063, draft-ietf-tcpimpl-pmtud-01 state that: * * 1. It is independent of path mtu. * 2. Ideally, it is maximal possible segment size i.e. 65535-40. * 3. For IPv4 it is reasonable to calculate it from maximal MTU of * attached devices, because some buggy hosts are confused by * large MSS. * 4. We do not make 3, we advertise MSS, calculated from first * hop device mtu, but allow to raise it to ip_rt_min_advmss. * This may be overridden via information stored in routing table. * 5. Value 65535 for MSS is valid in IPv6 and means "as large as possible, * probably even Jumbo". */ static __u16 tcp_advertise_mss(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); const struct dst_entry *dst = __sk_dst_get(sk); int mss = tp->advmss; if (dst) { unsigned int metric = dst_metric_advmss(dst); if (metric < mss) { mss = metric; tp->advmss = mss; } } return (__u16)mss; } /* RFC2861. Reset CWND after idle period longer RTO to "restart window". * This is the first part of cwnd validation mechanism. */ void tcp_cwnd_restart(struct sock *sk, s32 delta) { struct tcp_sock *tp = tcp_sk(sk); u32 restart_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk)); u32 cwnd = tp->snd_cwnd; tcp_ca_event(sk, CA_EVENT_CWND_RESTART); tp->snd_ssthresh = tcp_current_ssthresh(sk); restart_cwnd = min(restart_cwnd, cwnd); while ((delta -= inet_csk(sk)->icsk_rto) > 0 && cwnd > restart_cwnd) cwnd >>= 1; tp->snd_cwnd = max(cwnd, restart_cwnd); tp->snd_cwnd_stamp = tcp_jiffies32; tp->snd_cwnd_used = 0; } /* Congestion state accounting after a packet has been sent. */ static void tcp_event_data_sent(struct tcp_sock *tp, struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); const u32 now = tcp_jiffies32; if (tcp_packets_in_flight(tp) == 0) tcp_ca_event(sk, CA_EVENT_TX_START); /* If this is the first data packet sent in response to the * previous received data, * and it is a reply for ato after last received packet, * increase pingpong count. */ if (before(tp->lsndtime, icsk->icsk_ack.lrcvtime) && (u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) inet_csk_inc_pingpong_cnt(sk); tp->lsndtime = now; } /* Account for an ACK we sent. */ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, u32 rcv_nxt) { struct tcp_sock *tp = tcp_sk(sk); if (unlikely(tp->compressed_ack)) { NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED, tp->compressed_ack); tp->compressed_ack = 0; if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1) __sock_put(sk); } if (unlikely(rcv_nxt != tp->rcv_nxt)) return; /* Special ACK sent by DCTCP to reflect ECN */ tcp_dec_quickack_mode(sk, pkts); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } /* Determine a window scaling and initial window to offer. * Based on the assumption that the given amount of space * will be offered. Store the results in the tp structure. * NOTE: for smooth operation initial space offering should * be a multiple of mss if possible. We assume here that mss >= 1. * This MUST be enforced by all callers. */ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, __u32 *rcv_wnd, __u32 *window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd) { unsigned int space = (__space < 0 ? 0 : __space); /* If no clamp set the clamp to the max possible scaled window */ if (*window_clamp == 0) (*window_clamp) = (U16_MAX << TCP_MAX_WSCALE); space = min(*window_clamp, space); /* Quantize space offering to a multiple of mss if possible. */ if (space > mss) space = rounddown(space, mss); /* NOTE: offering an initial window larger than 32767 * will break some buggy TCP stacks. If the admin tells us * it is likely we could be speaking with such a buggy stack * we will truncate our initial window offering to 32K-1 * unless the remote has sent us a window scaling option, * which we interpret as a sign the remote TCP is not * misinterpreting the window field as a signed quantity. */ if (sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows) (*rcv_wnd) = min(space, MAX_TCP_WINDOW); else (*rcv_wnd) = min_t(u32, space, U16_MAX); if (init_rcv_wnd) *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); *rcv_wscale = 0; if (wscale_ok) { /* Set window scaling on max possible window */ space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); space = max_t(u32, space, sysctl_rmem_max); space = min_t(u32, space, *window_clamp); *rcv_wscale = clamp_t(int, ilog2(space) - 15, 0, TCP_MAX_WSCALE); } /* Set the clamp no higher than max representable value */ (*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp); } EXPORT_SYMBOL(tcp_select_initial_window); /* Chose a new window to advertise, update state in tcp_sock for the * socket, and return result with RFC1323 scaling applied. The return * value can be stuffed directly into th->window for an outgoing * frame. */ static u16 tcp_select_window(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); u32 old_win = tp->rcv_wnd; u32 cur_win = tcp_receive_window(tp); u32 new_win = __tcp_select_window(sk); /* Never shrink the offered window */ if (new_win < cur_win) { /* Danger Will Robinson! * Don't update rcv_wup/rcv_wnd here or else * we will not be able to advertise a zero * window in time. --DaveM * * Relax Will Robinson. */ if (new_win == 0) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWANTZEROWINDOWADV); new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale); } tp->rcv_wnd = new_win; tp->rcv_wup = tp->rcv_nxt; /* Make sure we do not exceed the maximum possible * scaled window. */ if (!tp->rx_opt.rcv_wscale && sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows) new_win = min(new_win, MAX_TCP_WINDOW); else new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale)); /* RFC1323 scaling applied */ new_win >>= tp->rx_opt.rcv_wscale; /* If we advertise zero window, disable fast path. */ if (new_win == 0) { tp->pred_flags = 0; if (old_win) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTOZEROWINDOWADV); } else if (old_win == 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFROMZEROWINDOWADV); } return new_win; } /* Packet ECN state for a SYN-ACK */ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) { const struct tcp_sock *tp = tcp_sk(sk); TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR; if (!(tp->ecn_flags & TCP_ECN_OK)) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE; else if (tcp_ca_needs_ecn(sk) || tcp_bpf_ca_needs_ecn(sk)) INET_ECN_xmit(sk); } /* Packet ECN state for a SYN. */ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk); bool use_ecn = sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 || tcp_ca_needs_ecn(sk) || bpf_needs_ecn; if (!use_ecn) { const struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst_feature(dst, RTAX_FEATURE_ECN)) use_ecn = true; } tp->ecn_flags = 0; if (use_ecn) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; tp->ecn_flags = TCP_ECN_OK; if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn) INET_ECN_xmit(sk); } } static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb) { if (sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback) /* tp->ecn_flags are cleared at a later point in time when * SYN ACK is ultimatively being received. */ TCP_SKB_CB(skb)->tcp_flags &= ~(TCPHDR_ECE | TCPHDR_CWR); } static void tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th) { if (inet_rsk(req)->ecn_ok) th->ece = 1; } /* Set up ECN state for a packet on a ESTABLISHED socket that is about to * be sent. */ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb, struct tcphdr *th, int tcp_header_len) { struct tcp_sock *tp = tcp_sk(sk); if (tp->ecn_flags & TCP_ECN_OK) { /* Not-retransmitted data segment: set ECT and inject CWR. */ if (skb->len != tcp_header_len && !before(TCP_SKB_CB(skb)->seq, tp->snd_nxt)) { INET_ECN_xmit(sk); if (tp->ecn_flags & TCP_ECN_QUEUE_CWR) { tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR; th->cwr = 1; skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; } } else if (!tcp_ca_needs_ecn(sk)) { /* ACK or retransmitted segment: clear ECT|CE */ INET_ECN_dontxmit(sk); } if (tp->ecn_flags & TCP_ECN_DEMAND_CWR) th->ece = 1; } } /* Constructs common control bits of non-data skb. If SYN/FIN is present, * auto increment end seqno. */ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags) { skb->ip_summed = CHECKSUM_PARTIAL; TCP_SKB_CB(skb)->tcp_flags = flags; TCP_SKB_CB(skb)->sacked = 0; tcp_skb_pcount_set(skb, 1); TCP_SKB_CB(skb)->seq = seq; if (flags & (TCPHDR_SYN | TCPHDR_FIN)) seq++; TCP_SKB_CB(skb)->end_seq = seq; } static inline bool tcp_urg_mode(const struct tcp_sock *tp) { return tp->snd_una != tp->snd_up; } #define OPTION_SACK_ADVERTISE (1 << 0) #define OPTION_TS (1 << 1) #define OPTION_MD5 (1 << 2) #define OPTION_WSCALE (1 << 3) #define OPTION_FAST_OPEN_COOKIE (1 << 8) #define OPTION_SMC (1 << 9) #define OPTION_MPTCP (1 << 10) static void smc_options_write(__be32 *ptr, u16 *options) { #if IS_ENABLED(CONFIG_SMC) if (static_branch_unlikely(&tcp_have_smc)) { if (unlikely(OPTION_SMC & *options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_EXP << 8) | (TCPOLEN_EXP_SMC_BASE)); *ptr++ = htonl(TCPOPT_SMC_MAGIC); } } #endif } struct tcp_out_options { u16 options; /* bit field of OPTION_* */ u16 mss; /* 0 to disable */ u8 ws; /* window scale, 0 to disable */ u8 num_sack_blocks; /* number of SACK blocks to include */ u8 hash_size; /* bytes in hash_location */ u8 bpf_opt_len; /* length of BPF hdr option */ __u8 *hash_location; /* temporary pointer, overloaded */ __u32 tsval, tsecr; /* need to include OPTION_TS */ struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */ struct mptcp_out_options mptcp; }; static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts) { #if IS_ENABLED(CONFIG_MPTCP) if (unlikely(OPTION_MPTCP & opts->options)) mptcp_write_options(ptr, &opts->mptcp); #endif } #ifdef CONFIG_CGROUP_BPF static int bpf_skops_write_hdr_opt_arg0(struct sk_buff *skb, enum tcp_synack_type synack_type) { if (unlikely(!skb)) return BPF_WRITE_HDR_TCP_CURRENT_MSS; if (unlikely(synack_type == TCP_SYNACK_COOKIE)) return BPF_WRITE_HDR_TCP_SYNACK_COOKIE; return 0; } /* req, syn_skb and synack_type are used when writing synack */ static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct sk_buff *syn_skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts, unsigned int *remaining) { struct bpf_sock_ops_kern sock_ops; int err; if (likely(!BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG)) || !*remaining) return; /* *remaining has already been aligned to 4 bytes, so *remaining >= 4 */ /* init sock_ops */ memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); sock_ops.op = BPF_SOCK_OPS_HDR_OPT_LEN_CB; if (req) { /* The listen "sk" cannot be passed here because * it is not locked. It would not make too much * sense to do bpf_setsockopt(listen_sk) based * on individual connection request also. * * Thus, "req" is passed here and the cgroup-bpf-progs * of the listen "sk" will be run. * * "req" is also used here for fastopen even the "sk" here is * a fullsock "child" sk. It is to keep the behavior * consistent between fastopen and non-fastopen on * the bpf programming side. */ sock_ops.sk = (struct sock *)req; sock_ops.syn_skb = syn_skb; } else { sock_owned_by_me(sk); sock_ops.is_fullsock = 1; sock_ops.sk = sk; } sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type); sock_ops.remaining_opt_len = *remaining; /* tcp_current_mss() does not pass a skb */ if (skb) bpf_skops_init_skb(&sock_ops, skb, 0); err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk); if (err || sock_ops.remaining_opt_len == *remaining) return; opts->bpf_opt_len = *remaining - sock_ops.remaining_opt_len; /* round up to 4 bytes */ opts->bpf_opt_len = (opts->bpf_opt_len + 3) & ~3; *remaining -= opts->bpf_opt_len; } static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct sk_buff *syn_skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts) { u8 first_opt_off, nr_written, max_opt_len = opts->bpf_opt_len; struct bpf_sock_ops_kern sock_ops; int err; if (likely(!max_opt_len)) return; memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); sock_ops.op = BPF_SOCK_OPS_WRITE_HDR_OPT_CB; if (req) { sock_ops.sk = (struct sock *)req; sock_ops.syn_skb = syn_skb; } else { sock_owned_by_me(sk); sock_ops.is_fullsock = 1; sock_ops.sk = sk; } sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type); sock_ops.remaining_opt_len = max_opt_len; first_opt_off = tcp_hdrlen(skb) - max_opt_len; bpf_skops_init_skb(&sock_ops, skb, first_opt_off); err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk); if (err) nr_written = 0; else nr_written = max_opt_len - sock_ops.remaining_opt_len; if (nr_written < max_opt_len) memset(skb->data + first_opt_off + nr_written, TCPOPT_NOP, max_opt_len - nr_written); } #else static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct sk_buff *syn_skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts, unsigned int *remaining) { } static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct sk_buff *syn_skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts) { } #endif /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of * TCP options, we learned this through the hard way, so be careful here. * Luckily we can at least blame others for their non-compliance but from * inter-operability perspective it seems that we're somewhat stuck with * the ordering which we have been using if we want to keep working with * those broken things (not that it currently hurts anybody as there isn't * particular reason why the ordering would need to be changed). * * At least SACK_PERM as the first option is known to lead to a disaster * (but it may well be that other scenarios fail similarly). */ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, struct tcp_out_options *opts) { u16 options = opts->options; /* mungable copy */ if (unlikely(OPTION_MD5 & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); /* overload cookie hash location */ opts->hash_location = (__u8 *)ptr; ptr += 4; } if (unlikely(opts->mss)) { *ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | opts->mss); } if (likely(OPTION_TS & options)) { if (unlikely(OPTION_SACK_ADVERTISE & options)) { *ptr++ = htonl((TCPOPT_SACK_PERM << 24) | (TCPOLEN_SACK_PERM << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); options &= ~OPTION_SACK_ADVERTISE; } else { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); } *ptr++ = htonl(opts->tsval); *ptr++ = htonl(opts->tsecr); } if (unlikely(OPTION_SACK_ADVERTISE & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM); } if (unlikely(OPTION_WSCALE & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | opts->ws); } if (unlikely(opts->num_sack_blocks)) { struct tcp_sack_block *sp = tp->rx_opt.dsack ? tp->duplicate_sack : tp->selective_acks; int this_sack; *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_SACK << 8) | (TCPOLEN_SACK_BASE + (opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK))); for (this_sack = 0; this_sack < opts->num_sack_blocks; ++this_sack) { *ptr++ = htonl(sp[this_sack].start_seq); *ptr++ = htonl(sp[this_sack].end_seq); } tp->rx_opt.dsack = 0; } if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) { struct tcp_fastopen_cookie *foc = opts->fastopen_cookie; u8 *p = (u8 *)ptr; u32 len; /* Fast Open option length */ if (foc->exp) { len = TCPOLEN_EXP_FASTOPEN_BASE + foc->len; *ptr = htonl((TCPOPT_EXP << 24) | (len << 16) | TCPOPT_FASTOPEN_MAGIC); p += TCPOLEN_EXP_FASTOPEN_BASE; } else { len = TCPOLEN_FASTOPEN_BASE + foc->len; *p++ = TCPOPT_FASTOPEN; *p++ = len; } memcpy(p, foc->val, foc->len); if ((len & 3) == 2) { p[foc->len] = TCPOPT_NOP; p[foc->len + 1] = TCPOPT_NOP; } ptr += (len + 3) >> 2; } smc_options_write(ptr, &options); mptcp_options_write(ptr, opts); } static void smc_set_option(const struct tcp_sock *tp, struct tcp_out_options *opts, unsigned int *remaining) { #if IS_ENABLED(CONFIG_SMC) if (static_branch_unlikely(&tcp_have_smc)) { if (tp->syn_smc) { if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { opts->options |= OPTION_SMC; *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; } } } #endif } static void smc_set_option_cond(const struct tcp_sock *tp, const struct inet_request_sock *ireq, struct tcp_out_options *opts, unsigned int *remaining) { #if IS_ENABLED(CONFIG_SMC) if (static_branch_unlikely(&tcp_have_smc)) { if (tp->syn_smc && ireq->smc_ok) { if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { opts->options |= OPTION_SMC; *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; } } } #endif } static void mptcp_set_option_cond(const struct request_sock *req, struct tcp_out_options *opts, unsigned int *remaining) { if (rsk_is_mptcp(req)) { unsigned int size; if (mptcp_synack_options(req, &size, &opts->mptcp)) { if (*remaining >= size) { opts->options |= OPTION_MPTCP; *remaining -= size; } } } } /* Compute TCP options for SYN packets. This is not the final * network wire format yet. */ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5) { struct tcp_sock *tp = tcp_sk(sk); unsigned int remaining = MAX_TCP_OPTION_SPACE; struct tcp_fastopen_request *fastopen = tp->fastopen_req; *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG if (static_branch_unlikely(&tcp_md5_needed) && rcu_access_pointer(tp->md5sig_info)) { *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { opts->options |= OPTION_MD5; remaining -= TCPOLEN_MD5SIG_ALIGNED; } } #endif /* We always get an MSS option. The option bytes which will be seen in * normal data packets should timestamps be used, must be in the MSS * advertised. But we subtract them from tp->mss_cache so that * calculations in tcp_sendmsg are simpler etc. So account for this * fact here if necessary. If we don't do this correctly, as a * receiver we won't recognize data packets as being full sized when we * should, and thus we won't abide by the delayed ACK rules correctly. * SACKs don't matter, we never delay an ACK when we have any of those * going out. */ opts->mss = tcp_advertise_mss(sk); remaining -= TCPOLEN_MSS_ALIGNED; if (likely(sock_net(sk)->ipv4.sysctl_tcp_timestamps && !*md5)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(sock_net(sk)->ipv4.sysctl_tcp_window_scaling)) { opts->ws = tp->rx_opt.rcv_wscale; opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } if (likely(sock_net(sk)->ipv4.sysctl_tcp_sack)) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!(OPTION_TS & opts->options))) remaining -= TCPOLEN_SACKPERM_ALIGNED; } if (fastopen && fastopen->cookie.len >= 0) { u32 need = fastopen->cookie.len; need += fastopen->cookie.exp ? TCPOLEN_EXP_FASTOPEN_BASE : TCPOLEN_FASTOPEN_BASE; need = (need + 3) & ~3U; /* Align to 32 bits */ if (remaining >= need) { opts->options |= OPTION_FAST_OPEN_COOKIE; opts->fastopen_cookie = &fastopen->cookie; remaining -= need; tp->syn_fastopen = 1; tp->syn_fastopen_exp = fastopen->cookie.exp ? 1 : 0; } } smc_set_option(tp, opts, &remaining); if (sk_is_mptcp(sk)) { unsigned int size; if (mptcp_syn_options(sk, skb, &size, &opts->mptcp)) { opts->options |= OPTION_MPTCP; remaining -= size; } } bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining); return MAX_TCP_OPTION_SPACE - remaining; } /* Set up TCP options for SYN-ACKs. */ static unsigned int tcp_synack_options(const struct sock *sk, struct request_sock *req, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, const struct tcp_md5sig_key *md5, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; #ifdef CONFIG_TCP_MD5SIG if (md5) { opts->options |= OPTION_MD5; remaining -= TCPOLEN_MD5SIG_ALIGNED; /* We can't fit any SACK blocks in a packet with MD5 + TS * options. There was discussion about disabling SACK * rather than TS in order to fit in better with old, * buggy kernels, but that was deemed to be unnecessary. */ if (synack_type != TCP_SYNACK_COOKIE) ireq->tstamp_ok &= !ireq->sack_ok; } #endif /* We always send an MSS option. */ opts->mss = mss; remaining -= TCPOLEN_MSS_ALIGNED; if (likely(ireq->wscale_ok)) { opts->ws = ireq->rcv_wscale; opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } if (likely(ireq->tstamp_ok)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off; opts->tsecr = req->ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(ireq->sack_ok)) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!ireq->tstamp_ok)) remaining -= TCPOLEN_SACKPERM_ALIGNED; } if (foc != NULL && foc->len >= 0) { u32 need = foc->len; need += foc->exp ? TCPOLEN_EXP_FASTOPEN_BASE : TCPOLEN_FASTOPEN_BASE; need = (need + 3) & ~3U; /* Align to 32 bits */ if (remaining >= need) { opts->options |= OPTION_FAST_OPEN_COOKIE; opts->fastopen_cookie = foc; remaining -= need; } } mptcp_set_option_cond(req, opts, &remaining); smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining); bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb, synack_type, opts, &remaining); return MAX_TCP_OPTION_SPACE - remaining; } /* Compute TCP options for ESTABLISHED sockets. This is not the * final wire format yet. */ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5) { struct tcp_sock *tp = tcp_sk(sk); unsigned int size = 0; unsigned int eff_sacks; opts->options = 0; *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG if (static_branch_unlikely(&tcp_md5_needed) && rcu_access_pointer(tp->md5sig_info)) { *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { opts->options |= OPTION_MD5; size += TCPOLEN_MD5SIG_ALIGNED; } } #endif if (likely(tp->rx_opt.tstamp_ok)) { opts->options |= OPTION_TS; opts->tsval = skb ? tcp_skb_timestamp(skb) + tp->tsoffset : 0; opts->tsecr = tp->rx_opt.ts_recent; size += TCPOLEN_TSTAMP_ALIGNED; } /* MPTCP options have precedence over SACK for the limited TCP * option space because a MPTCP connection would be forced to * fall back to regular TCP if a required multipath option is * missing. SACK still gets a chance to use whatever space is * left. */ if (sk_is_mptcp(sk)) { unsigned int remaining = MAX_TCP_OPTION_SPACE - size; unsigned int opt_size = 0; if (mptcp_established_options(sk, skb, &opt_size, remaining, &opts->mptcp)) { opts->options |= OPTION_MPTCP; size += opt_size; } } eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack; if (unlikely(eff_sacks)) { const unsigned int remaining = MAX_TCP_OPTION_SPACE - size; if (unlikely(remaining < TCPOLEN_SACK_BASE_ALIGNED + TCPOLEN_SACK_PERBLOCK)) return size; opts->num_sack_blocks = min_t(unsigned int, eff_sacks, (remaining - TCPOLEN_SACK_BASE_ALIGNED) / TCPOLEN_SACK_PERBLOCK); size += TCPOLEN_SACK_BASE_ALIGNED + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; } if (unlikely(BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG))) { unsigned int remaining = MAX_TCP_OPTION_SPACE - size; bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining); size = MAX_TCP_OPTION_SPACE - remaining; } return size; } /* TCP SMALL QUEUES (TSQ) * * TSQ goal is to keep small amount of skbs per tcp flow in tx queues (qdisc+dev) * to reduce RTT and bufferbloat. * We do this using a special skb destructor (tcp_wfree). * * Its important tcp_wfree() can be replaced by sock_wfree() in the event skb * needs to be reallocated in a driver. * The invariant being skb->truesize subtracted from sk->sk_wmem_alloc * * Since transmit from skb destructor is forbidden, we use a tasklet * to process all sockets that eventually need to send more skbs. * We use one tasklet per cpu, with its own queue of sockets. */ struct tsq_tasklet { struct tasklet_struct tasklet; struct list_head head; /* queue of tcp sockets */ }; static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet); static void tcp_tsq_write(struct sock *sk) { if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) { struct tcp_sock *tp = tcp_sk(sk); if (tp->lost_out > tp->retrans_out && tp->snd_cwnd > tcp_packets_in_flight(tp)) { tcp_mstamp_refresh(tp); tcp_xmit_retransmit_queue(sk); } tcp_write_xmit(sk, tcp_current_mss(sk), tp->nonagle, 0, GFP_ATOMIC); } } static void tcp_tsq_handler(struct sock *sk) { bh_lock_sock(sk); if (!sock_owned_by_user(sk)) tcp_tsq_write(sk); else if (!test_and_set_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); bh_unlock_sock(sk); } /* * One tasklet per cpu tries to send more skbs. * We run in tasklet context but need to disable irqs when * transferring tsq->head because tcp_wfree() might * interrupt us (non NAPI drivers) */ static void tcp_tasklet_func(unsigned long data) { struct tsq_tasklet *tsq = (struct tsq_tasklet *)data; LIST_HEAD(list); unsigned long flags; struct list_head *q, *n; struct tcp_sock *tp; struct sock *sk; local_irq_save(flags); list_splice_init(&tsq->head, &list); local_irq_restore(flags); list_for_each_safe(q, n, &list) { tp = list_entry(q, struct tcp_sock, tsq_node); list_del(&tp->tsq_node); sk = (struct sock *)tp; smp_mb__before_atomic(); clear_bit(TSQ_QUEUED, &sk->sk_tsq_flags); tcp_tsq_handler(sk); sk_free(sk); } } #define TCP_DEFERRED_ALL (TCPF_TSQ_DEFERRED | \ TCPF_WRITE_TIMER_DEFERRED | \ TCPF_DELACK_TIMER_DEFERRED | \ TCPF_MTU_REDUCED_DEFERRED) /** * tcp_release_cb - tcp release_sock() callback * @sk: socket * * called from release_sock() to perform protocol dependent * actions before socket release. */ void tcp_release_cb(struct sock *sk) { unsigned long flags, nflags; /* perform an atomic operation only if at least one flag is set */ do { flags = sk->sk_tsq_flags; if (!(flags & TCP_DEFERRED_ALL)) return; nflags = flags & ~TCP_DEFERRED_ALL; } while (cmpxchg(&sk->sk_tsq_flags, flags, nflags) != flags); if (flags & TCPF_TSQ_DEFERRED) { tcp_tsq_write(sk); __sock_put(sk); } /* Here begins the tricky part : * We are called from release_sock() with : * 1) BH disabled * 2) sk_lock.slock spinlock held * 3) socket owned by us (sk->sk_lock.owned == 1) * * But following code is meant to be called from BH handlers, * so we should keep BH disabled, but early release socket ownership */ sock_release_ownership(sk); if (flags & TCPF_WRITE_TIMER_DEFERRED) { tcp_write_timer_handler(sk); __sock_put(sk); } if (flags & TCPF_DELACK_TIMER_DEFERRED) { tcp_delack_timer_handler(sk); __sock_put(sk); } if (flags & TCPF_MTU_REDUCED_DEFERRED) { inet_csk(sk)->icsk_af_ops->mtu_reduced(sk); __sock_put(sk); } } EXPORT_SYMBOL(tcp_release_cb); void __init tcp_tasklet_init(void) { int i; for_each_possible_cpu(i) { struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i); INIT_LIST_HEAD(&tsq->head); tasklet_init(&tsq->tasklet, tcp_tasklet_func, (unsigned long)tsq); } } /* * Write buffer destructor automatically called from kfree_skb. * We can't xmit new skbs from this context, as we might already * hold qdisc lock. */ void tcp_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; struct tcp_sock *tp = tcp_sk(sk); unsigned long flags, nval, oval; /* Keep one reference on sk_wmem_alloc. * Will be released by sk_free() from here or tcp_tasklet_func() */ WARN_ON(refcount_sub_and_test(skb->truesize - 1, &sk->sk_wmem_alloc)); /* If this softirq is serviced by ksoftirqd, we are likely under stress. * Wait until our queues (qdisc + devices) are drained. * This gives : * - less callbacks to tcp_write_xmit(), reducing stress (batches) * - chance for incoming ACK (processed by another cpu maybe) * to migrate this flow (skb->ooo_okay will be eventually set) */ if (refcount_read(&sk->sk_wmem_alloc) >= SKB_TRUESIZE(1) && this_cpu_ksoftirqd() == current) goto out; for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) { struct tsq_tasklet *tsq; bool empty; if (!(oval & TSQF_THROTTLED) || (oval & TSQF_QUEUED)) goto out; nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED; nval = cmpxchg(&sk->sk_tsq_flags, oval, nval); if (nval != oval) continue; /* queue this socket to tasklet queue */ local_irq_save(flags); tsq = this_cpu_ptr(&tsq_tasklet); empty = list_empty(&tsq->head); list_add(&tp->tsq_node, &tsq->head); if (empty) tasklet_schedule(&tsq->tasklet); local_irq_restore(flags); return; } out: sk_free(sk); } /* Note: Called under soft irq. * We can call TCP stack right away, unless socket is owned by user. */ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer) { struct tcp_sock *tp = container_of(timer, struct tcp_sock, pacing_timer); struct sock *sk = (struct sock *)tp; tcp_tsq_handler(sk); sock_put(sk); return HRTIMER_NORESTART; } static void tcp_update_skb_after_send(struct sock *sk, struct sk_buff *skb, u64 prior_wstamp) { struct tcp_sock *tp = tcp_sk(sk); if (sk->sk_pacing_status != SK_PACING_NONE) { unsigned long rate = sk->sk_pacing_rate; /* Original sch_fq does not pace first 10 MSS * Note that tp->data_segs_out overflows after 2^32 packets, * this is a minor annoyance. */ if (rate != ~0UL && rate && tp->data_segs_out >= 10) { u64 len_ns = div64_ul((u64)skb->len * NSEC_PER_SEC, rate); u64 credit = tp->tcp_wstamp_ns - prior_wstamp; /* take into account OS jitter */ len_ns -= min_t(u64, len_ns / 2, credit); tp->tcp_wstamp_ns += len_ns; } } list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); } INDIRECT_CALLABLE_DECLARE(int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)); INDIRECT_CALLABLE_DECLARE(int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)); INDIRECT_CALLABLE_DECLARE(void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)); /* This routine actually transmits TCP packets queued in by * tcp_do_sendmsg(). This is used by both the initial * transmission and possible later retransmissions. * All SKB's seen here are completely headerless. It is our * job to build the TCP header, and pass the packet down to * IP so it can do the same plus pass the packet off to the * device. * * We are working here with either a clone of the original * SKB, or a fresh unique copy made by the retransmit engine. */ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, gfp_t gfp_mask, u32 rcv_nxt) { const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet; struct tcp_sock *tp; struct tcp_skb_cb *tcb; struct tcp_out_options opts; unsigned int tcp_options_size, tcp_header_size; struct sk_buff *oskb = NULL; struct tcp_md5sig_key *md5; struct tcphdr *th; u64 prior_wstamp; int err; BUG_ON(!skb || !tcp_skb_pcount(skb)); tp = tcp_sk(sk); prior_wstamp = tp->tcp_wstamp_ns; tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache); skb->skb_mstamp_ns = tp->tcp_wstamp_ns; if (clone_it) { TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq - tp->snd_una; oskb = skb; tcp_skb_tsorted_save(oskb) { if (unlikely(skb_cloned(oskb))) skb = pskb_copy(oskb, gfp_mask); else skb = skb_clone(oskb, gfp_mask); } tcp_skb_tsorted_restore(oskb); if (unlikely(!skb)) return -ENOBUFS; /* retransmit skbs might have a non zero value in skb->dev * because skb->dev is aliased with skb->rbnode.rb_left */ skb->dev = NULL; } inet = inet_sk(sk); tcb = TCP_SKB_CB(skb); memset(&opts, 0, sizeof(opts)); if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) { tcp_options_size = tcp_syn_options(sk, skb, &opts, &md5); } else { tcp_options_size = tcp_established_options(sk, skb, &opts, &md5); /* Force a PSH flag on all (GSO) packets to expedite GRO flush * at receiver : This slightly improve GRO performance. * Note that we do not force the PSH flag for non GSO packets, * because they might be sent under high congestion events, * and in this case it is better to delay the delivery of 1-MSS * packets and thus the corresponding ACK packet that would * release the following packet. */ if (tcp_skb_pcount(skb) > 1) tcb->tcp_flags |= TCPHDR_PSH; } tcp_header_size = tcp_options_size + sizeof(struct tcphdr); /* if no packet is in qdisc/device queue, then allow XPS to select * another queue. We can be called from tcp_tsq_handler() * which holds one reference to sk. * * TODO: Ideally, in-flight pure ACK packets should not matter here. * One way to get this would be to set skb->truesize = 2 on them. */ skb->ooo_okay = sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1); /* If we had to use memory reserve to allocate this skb, * this might cause drops if packet is looped back : * Other socket might not have SOCK_MEMALLOC. * Packets not looped back do not care about pfmemalloc. */ skb->pfmemalloc = 0; skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); skb_orphan(skb); skb->sk = sk; skb->destructor = skb_is_tcp_pure_ack(skb) ? __sock_wfree : tcp_wfree; skb_set_hash_from_sk(skb, sk); refcount_add(skb->truesize, &sk->sk_wmem_alloc); skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm); /* Build TCP header and checksum it. */ th = (struct tcphdr *)skb->data; th->source = inet->inet_sport; th->dest = inet->inet_dport; th->seq = htonl(tcb->seq); th->ack_seq = htonl(rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | tcb->tcp_flags); th->check = 0; th->urg_ptr = 0; /* The urg_mode check is necessary during a below snd_una win probe */ if (unlikely(tcp_urg_mode(tp) && before(tcb->seq, tp->snd_up))) { if (before(tp->snd_up, tcb->seq + 0x10000)) { th->urg_ptr = htons(tp->snd_up - tcb->seq); th->urg = 1; } else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) { th->urg_ptr = htons(0xFFFF); th->urg = 1; } } tcp_options_write((__be32 *)(th + 1), tp, &opts); skb_shinfo(skb)->gso_type = sk->sk_gso_type; if (likely(!(tcb->tcp_flags & TCPHDR_SYN))) { th->window = htons(tcp_select_window(sk)); tcp_ecn_send(sk, skb, th, tcp_header_size); } else { /* RFC1323: The window in SYN & SYN/ACK segments * is never scaled. */ th->window = htons(min(tp->rcv_wnd, 65535U)); } #ifdef CONFIG_TCP_MD5SIG /* Calculate the MD5 hash, as we have all we need now */ if (md5) { sk_nocaps_add(sk, NETIF_F_GSO_MASK); tp->af_specific->calc_md5_hash(opts.hash_location, md5, sk, skb); } #endif /* BPF prog is the last one writing header option */ bpf_skops_write_hdr_opt(sk, skb, NULL, NULL, 0, &opts); INDIRECT_CALL_INET(icsk->icsk_af_ops->send_check, tcp_v6_send_check, tcp_v4_send_check, sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); tp->data_segs_out += tcp_skb_pcount(skb); tp->bytes_sent += skb->len - tcp_header_size; } if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb)); tp->segs_out += tcp_skb_pcount(skb); /* OK, its time to fill skb_shinfo(skb)->gso_{segs|size} */ skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb); skb_shinfo(skb)->gso_size = tcp_skb_mss(skb); /* Leave earliest departure time in skb->tstamp (skb->skb_mstamp_ns) */ /* Cleanup our debris for IP stacks */ memset(skb->cb, 0, max(sizeof(struct inet_skb_parm), sizeof(struct inet6_skb_parm))); tcp_add_tx_delay(skb, tp); err = INDIRECT_CALL_INET(icsk->icsk_af_ops->queue_xmit, inet6_csk_xmit, ip_queue_xmit, sk, skb, &inet->cork.fl); if (unlikely(err > 0)) { tcp_enter_cwr(sk); err = net_xmit_eval(err); } if (!err && oskb) { tcp_update_skb_after_send(sk, oskb, prior_wstamp); tcp_rate_skb_sent(sk, oskb); } return err; } static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, gfp_t gfp_mask) { return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask, tcp_sk(sk)->rcv_nxt); } /* This routine just queues the buffer for sending. * * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames, * otherwise socket can stall. */ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); /* Advance write_seq and place onto the write_queue. */ WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq); __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); } /* Initialize TSO segments for a packet. */ static void tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now) { if (skb->len <= mss_now) { /* Avoid the costly divide in the normal * non-TSO case. */ tcp_skb_pcount_set(skb, 1); TCP_SKB_CB(skb)->tcp_gso_size = 0; } else { tcp_skb_pcount_set(skb, DIV_ROUND_UP(skb->len, mss_now)); TCP_SKB_CB(skb)->tcp_gso_size = mss_now; } } /* Pcount in the middle of the write queue got changed, we need to do various * tweaks to fix counters */ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int decr) { struct tcp_sock *tp = tcp_sk(sk); tp->packets_out -= decr; if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) tp->sacked_out -= decr; if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) tp->retrans_out -= decr; if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) tp->lost_out -= decr; /* Reno case is special. Sigh... */ if (tcp_is_reno(tp) && decr > 0) tp->sacked_out -= min_t(u32, tp->sacked_out, decr); if (tp->lost_skb_hint && before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) tp->lost_cnt_hint -= decr; tcp_verify_left_out(tp); } static bool tcp_has_tx_tstamp(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->txstamp_ack || (skb_shinfo(skb)->tx_flags & SKBTX_ANY_TSTAMP); } static void tcp_fragment_tstamp(struct sk_buff *skb, struct sk_buff *skb2) { struct skb_shared_info *shinfo = skb_shinfo(skb); if (unlikely(tcp_has_tx_tstamp(skb)) && !before(shinfo->tskey, TCP_SKB_CB(skb2)->seq)) { struct skb_shared_info *shinfo2 = skb_shinfo(skb2); u8 tsflags = shinfo->tx_flags & SKBTX_ANY_TSTAMP; shinfo->tx_flags &= ~tsflags; shinfo2->tx_flags |= tsflags; swap(shinfo->tskey, shinfo2->tskey); TCP_SKB_CB(skb2)->txstamp_ack = TCP_SKB_CB(skb)->txstamp_ack; TCP_SKB_CB(skb)->txstamp_ack = 0; } } static void tcp_skb_fragment_eor(struct sk_buff *skb, struct sk_buff *skb2) { TCP_SKB_CB(skb2)->eor = TCP_SKB_CB(skb)->eor; TCP_SKB_CB(skb)->eor = 0; } /* Insert buff after skb on the write or rtx queue of sk. */ static void tcp_insert_write_queue_after(struct sk_buff *skb, struct sk_buff *buff, struct sock *sk, enum tcp_queue tcp_queue) { if (tcp_queue == TCP_FRAG_IN_WRITE_QUEUE) __skb_queue_after(&sk->sk_write_queue, skb, buff); else tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); } /* Function to create two new TCP segments. Shrinks the given segment * to the specified size and appends a new segment with the rest of the * packet to the list. This won't be called frequently, I hope. * Remember, these are still headerless SKBs at this point. */ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, struct sk_buff *skb, u32 len, unsigned int mss_now, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; int nsize, old_factor; long limit; int nlen; u8 flags; if (WARN_ON(len > skb->len)) return -EINVAL; nsize = skb_headlen(skb) - len; if (nsize < 0) nsize = 0; /* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb. * We need some allowance to not penalize applications setting small * SO_SNDBUF values. * Also allow first and last skb in retransmit queue to be split. */ limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE); if (unlikely((sk->sk_wmem_queued >> 1) > limit && tcp_queue != TCP_FRAG_IN_WRITE_QUEUE && skb != tcp_rtx_queue_head(sk) && skb != tcp_rtx_queue_tail(sk))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG); return -ENOMEM; } if (skb_unclone(skb, gfp)) return -ENOMEM; /* Get a new skb... force flag on. */ buff = sk_stream_alloc_skb(sk, nsize, gfp, true); if (!buff) return -ENOMEM; /* We'll just try again later. */ skb_copy_decrypted(buff, skb); sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); nlen = skb->len - len - nsize; buff->truesize += nlen; skb->truesize -= nlen; /* Correct the sequence numbers. */ TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len; TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq; TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq; /* PSH and FIN should only be set in the second packet. */ flags = TCP_SKB_CB(skb)->tcp_flags; TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH); TCP_SKB_CB(buff)->tcp_flags = flags; TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked; tcp_skb_fragment_eor(skb, buff); skb_split(skb, buff, len); buff->ip_summed = CHECKSUM_PARTIAL; buff->tstamp = skb->tstamp; tcp_fragment_tstamp(skb, buff); old_factor = tcp_skb_pcount(skb); /* Fix up tso_factor for both original and new SKB. */ tcp_set_skb_tso_segs(skb, mss_now); tcp_set_skb_tso_segs(buff, mss_now); /* Update delivered info for the new segment */ TCP_SKB_CB(buff)->tx = TCP_SKB_CB(skb)->tx; /* If this packet has been sent out already, we must * adjust the various packet counters. */ if (!before(tp->snd_nxt, TCP_SKB_CB(buff)->end_seq)) { int diff = old_factor - tcp_skb_pcount(skb) - tcp_skb_pcount(buff); if (diff) tcp_adjust_pcount(sk, skb, diff); } /* Link BUFF into the send queue. */ __skb_header_release(buff); tcp_insert_write_queue_after(skb, buff, sk, tcp_queue); if (tcp_queue == TCP_FRAG_IN_RTX_QUEUE) list_add(&buff->tcp_tsorted_anchor, &skb->tcp_tsorted_anchor); return 0; } /* This is similar to __pskb_pull_tail(). The difference is that pulled * data is not copied, but immediately discarded. */ static int __pskb_trim_head(struct sk_buff *skb, int len) { struct skb_shared_info *shinfo; int i, k, eat; eat = min_t(int, len, skb_headlen(skb)); if (eat) { __skb_pull(skb, eat); len -= eat; if (!len) return 0; } eat = len; k = 0; shinfo = skb_shinfo(skb); for (i = 0; i < shinfo->nr_frags; i++) { int size = skb_frag_size(&shinfo->frags[i]); if (size <= eat) { skb_frag_unref(skb, i); eat -= size; } else { shinfo->frags[k] = shinfo->frags[i]; if (eat) { skb_frag_off_add(&shinfo->frags[k], eat); skb_frag_size_sub(&shinfo->frags[k], eat); eat = 0; } k++; } } shinfo->nr_frags = k; skb->data_len -= len; skb->len = skb->data_len; return len; } /* Remove acked data from a packet in the transmit queue. */ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) { u32 delta_truesize; if (skb_unclone(skb, GFP_ATOMIC)) return -ENOMEM; delta_truesize = __pskb_trim_head(skb, len); TCP_SKB_CB(skb)->seq += len; skb->ip_summed = CHECKSUM_PARTIAL; if (delta_truesize) { skb->truesize -= delta_truesize; sk_wmem_queued_add(sk, -delta_truesize); sk_mem_uncharge(sk, delta_truesize); } /* Any change of skb->len requires recalculation of tso factor. */ if (tcp_skb_pcount(skb) > 1) tcp_set_skb_tso_segs(skb, tcp_skb_mss(skb)); return 0; } /* Calculate MSS not accounting any TCP options. */ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); int mss_now; /* Calculate base mss without TCP options: It is MMS_S - sizeof(tcphdr) of rfc1122 */ mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr); /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ if (icsk->icsk_af_ops->net_frag_header_len) { const struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst_allfrag(dst)) mss_now -= icsk->icsk_af_ops->net_frag_header_len; } /* Clamp it (mss_clamp does not include tcp options) */ if (mss_now > tp->rx_opt.mss_clamp) mss_now = tp->rx_opt.mss_clamp; /* Now subtract optional transport overhead */ mss_now -= icsk->icsk_ext_hdr_len; /* Then reserve room for full set of TCP options and 8 bytes of data */ mss_now = max(mss_now, sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss); return mss_now; } /* Calculate MSS. Not accounting for SACKs here. */ int tcp_mtu_to_mss(struct sock *sk, int pmtu) { /* Subtract TCP options size, not including SACKs */ return __tcp_mtu_to_mss(sk, pmtu) - (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr)); } EXPORT_SYMBOL(tcp_mtu_to_mss); /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); int mtu; mtu = mss + tp->tcp_header_len + icsk->icsk_ext_hdr_len + icsk->icsk_af_ops->net_header_len; /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ if (icsk->icsk_af_ops->net_frag_header_len) { const struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst_allfrag(dst)) mtu += icsk->icsk_af_ops->net_frag_header_len; } return mtu; } EXPORT_SYMBOL(tcp_mss_to_mtu); /* MTU probing init per socket */ void tcp_mtup_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); icsk->icsk_mtup.enabled = net->ipv4.sysctl_tcp_mtu_probing > 1; icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) + icsk->icsk_af_ops->net_header_len; icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss); icsk->icsk_mtup.probe_size = 0; if (icsk->icsk_mtup.enabled) icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } EXPORT_SYMBOL(tcp_mtup_init); /* This function synchronize snd mss to current pmtu/exthdr set. tp->rx_opt.user_mss is mss set by user by TCP_MAXSEG. It does NOT counts for TCP options, but includes only bare TCP header. tp->rx_opt.mss_clamp is mss negotiated at connection setup. It is minimum of user_mss and mss received with SYN. It also does not include TCP options. inet_csk(sk)->icsk_pmtu_cookie is last pmtu, seen by this function. tp->mss_cache is current effective sending mss, including all tcp options except for SACKs. It is evaluated, taking into account current pmtu, but never exceeds tp->rx_opt.mss_clamp. NOTE1. rfc1122 clearly states that advertised MSS DOES NOT include either tcp or ip options. NOTE2. inet_csk(sk)->icsk_pmtu_cookie and tp->mss_cache are READ ONLY outside this function. --ANK (980731) */ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); int mss_now; if (icsk->icsk_mtup.search_high > pmtu) icsk->icsk_mtup.search_high = pmtu; mss_now = tcp_mtu_to_mss(sk, pmtu); mss_now = tcp_bound_to_half_wnd(tp, mss_now); /* And store cached results */ icsk->icsk_pmtu_cookie = pmtu; if (icsk->icsk_mtup.enabled) mss_now = min(mss_now, tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low)); tp->mss_cache = mss_now; return mss_now; } EXPORT_SYMBOL(tcp_sync_mss); /* Compute the current effective MSS, taking SACKs and IP options, * and even PMTU discovery events into account. */ unsigned int tcp_current_mss(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); const struct dst_entry *dst = __sk_dst_get(sk); u32 mss_now; unsigned int header_len; struct tcp_out_options opts; struct tcp_md5sig_key *md5; mss_now = tp->mss_cache; if (dst) { u32 mtu = dst_mtu(dst); if (mtu != inet_csk(sk)->icsk_pmtu_cookie) mss_now = tcp_sync_mss(sk, mtu); } header_len = tcp_established_options(sk, NULL, &opts, &md5) + sizeof(struct tcphdr); /* The mss_cache is sized based on tp->tcp_header_len, which assumes * some common options. If this is an odd packet (because we have SACK * blocks etc) then our calculated header_len will be different, and * we have to adjust mss_now correspondingly */ if (header_len != tp->tcp_header_len) { int delta = (int) header_len - tp->tcp_header_len; mss_now -= delta; } return mss_now; } /* RFC2861, slow part. Adjust cwnd, after it was not full during one rto. * As additional protections, we do not touch cwnd in retransmission phases, * and if application hit its sndbuf limit recently. */ static void tcp_cwnd_application_limited(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open && sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { /* Limited by application or receiver window. */ u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk)); u32 win_used = max(tp->snd_cwnd_used, init_win); if (win_used < tp->snd_cwnd) { tp->snd_ssthresh = tcp_current_ssthresh(sk); tp->snd_cwnd = (tp->snd_cwnd + win_used) >> 1; } tp->snd_cwnd_used = 0; } tp->snd_cwnd_stamp = tcp_jiffies32; } static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; struct tcp_sock *tp = tcp_sk(sk); /* Track the maximum number of outstanding packets in each * window, and remember whether we were cwnd-limited then. */ if (!before(tp->snd_una, tp->max_packets_seq) || tp->packets_out > tp->max_packets_out || is_cwnd_limited) { tp->max_packets_out = tp->packets_out; tp->max_packets_seq = tp->snd_nxt; tp->is_cwnd_limited = is_cwnd_limited; } if (tcp_is_cwnd_limited(sk)) { /* Network is feed fully. */ tp->snd_cwnd_used = 0; tp->snd_cwnd_stamp = tcp_jiffies32; } else { /* Network starves. */ if (tp->packets_out > tp->snd_cwnd_used) tp->snd_cwnd_used = tp->packets_out; if (sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle && (s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto && !ca_ops->cong_control) tcp_cwnd_application_limited(sk); /* The following conditions together indicate the starvation * is caused by insufficient sender buffer: * 1) just sent some data (see tcp_write_xmit) * 2) not cwnd limited (this else condition) * 3) no more data to send (tcp_write_queue_empty()) * 4) application is hitting buffer limit (SOCK_NOSPACE) */ if (tcp_write_queue_empty(sk) && sk->sk_socket && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags) && (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) tcp_chrono_start(sk, TCP_CHRONO_SNDBUF_LIMITED); } } /* Minshall's variant of the Nagle send check. */ static bool tcp_minshall_check(const struct tcp_sock *tp) { return after(tp->snd_sml, tp->snd_una) && !after(tp->snd_sml, tp->snd_nxt); } /* Update snd_sml if this skb is under mss * Note that a TSO packet might end with a sub-mss segment * The test is really : * if ((skb->len % mss) != 0) * tp->snd_sml = TCP_SKB_CB(skb)->end_seq; * But we can avoid doing the divide again given we already have * skb_pcount = skb->len / mss_now */ static void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss_now, const struct sk_buff *skb) { if (skb->len < tcp_skb_pcount(skb) * mss_now) tp->snd_sml = TCP_SKB_CB(skb)->end_seq; } /* Return false, if packet can be sent now without violation Nagle's rules: * 1. It is full sized. (provided by caller in %partial bool) * 2. Or it contains FIN. (already checked by caller) * 3. Or TCP_CORK is not set, and TCP_NODELAY is set. * 4. Or TCP_CORK is not set, and all sent packets are ACKed. * With Minshall's modification: all sent small packets are ACKed. */ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp, int nonagle) { return partial && ((nonagle & TCP_NAGLE_CORK) || (!nonagle && tp->packets_out && tcp_minshall_check(tp))); } /* Return how many segs we'd like on a TSO packet, * to send one TSO packet per ms */ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, int min_tso_segs) { u32 bytes, segs; bytes = min_t(unsigned long, sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), sk->sk_gso_max_size - 1 - MAX_TCP_HEADER); /* Goal is to send at least one packet per ms, * not one big TSO packet every 100 ms. * This preserves ACK clocking and is consistent * with tcp_tso_should_defer() heuristic. */ segs = max_t(u32, bytes / mss_now, min_tso_segs); return segs; } /* Return the number of segments we want in the skb we are transmitting. * See if congestion control module wants to decide; otherwise, autosize. */ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; u32 min_tso, tso_segs; min_tso = ca_ops->min_tso_segs ? ca_ops->min_tso_segs(sk) : sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs; tso_segs = tcp_tso_autosize(sk, mss_now, min_tso); return min_t(u32, tso_segs, sk->sk_gso_max_segs); } /* Returns the portion of skb which can be sent right away */ static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_buff *skb, unsigned int mss_now, unsigned int max_segs, int nonagle) { const struct tcp_sock *tp = tcp_sk(sk); u32 partial, needed, window, max_len; window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; max_len = mss_now * max_segs; if (likely(max_len <= window && skb != tcp_write_queue_tail(sk))) return max_len; needed = min(skb->len, window); if (max_len <= needed) return max_len; partial = needed % mss_now; /* If last segment is not a full MSS, check if Nagle rules allow us * to include this last segment in this skb. * Otherwise, we'll split the skb at last MSS boundary */ if (tcp_nagle_check(partial != 0, tp, nonagle)) return needed - partial; return needed; } /* Can at least one segment of SKB be sent right now, according to the * congestion window rules? If so, return how many segments are allowed. */ static inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp, const struct sk_buff *skb) { u32 in_flight, cwnd, halfcwnd; /* Don't be strict about the congestion window for the final FIN. */ if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) && tcp_skb_pcount(skb) == 1) return 1; in_flight = tcp_packets_in_flight(tp); cwnd = tp->snd_cwnd; if (in_flight >= cwnd) return 0; /* For better scheduling, ensure we have at least * 2 GSO packets in flight. */ halfcwnd = max(cwnd >> 1, 1U); return min(halfcwnd, cwnd - in_flight); } /* Initialize TSO state of a skb. * This must be invoked the first time we consider transmitting * SKB onto the wire. */ static int tcp_init_tso_segs(struct sk_buff *skb, unsigned int mss_now) { int tso_segs = tcp_skb_pcount(skb); if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) { tcp_set_skb_tso_segs(skb, mss_now); tso_segs = tcp_skb_pcount(skb); } return tso_segs; } /* Return true if the Nagle test allows this packet to be * sent now. */ static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff *skb, unsigned int cur_mss, int nonagle) { /* Nagle rule does not apply to frames, which sit in the middle of the * write_queue (they have no chances to get new data). * * This is implemented in the callers, where they modify the 'nonagle' * argument based upon the location of SKB in the send queue. */ if (nonagle & TCP_NAGLE_PUSH) return true; /* Don't use the nagle rule for urgent data (or for the final FIN). */ if (tcp_urg_mode(tp) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) return true; if (!tcp_nagle_check(skb->len < cur_mss, tp, nonagle)) return true; return false; } /* Does at least the first segment of SKB fit into the send window? */ static bool tcp_snd_wnd_test(const struct tcp_sock *tp, const struct sk_buff *skb, unsigned int cur_mss) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; if (skb->len > cur_mss) end_seq = TCP_SKB_CB(skb)->seq + cur_mss; return !after(end_seq, tcp_wnd_end(tp)); } /* Trim TSO SKB to LEN bytes, put the remaining data into a new packet * which is put after SKB on the list. It is very much like * tcp_fragment() except that it may make several kinds of assumptions * in order to speed up the splitting operation. In particular, we * know that all the data is in scatter-gather pages, and that the * packet has never been sent out before (and thus is not cloned). */ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, unsigned int mss_now, gfp_t gfp) { int nlen = skb->len - len; struct sk_buff *buff; u8 flags; /* All of a TSO frame must be composed of paged data. */ if (skb->len != skb->data_len) return tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE, skb, len, mss_now, gfp); buff = sk_stream_alloc_skb(sk, 0, gfp, true); if (unlikely(!buff)) return -ENOMEM; skb_copy_decrypted(buff, skb); sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); buff->truesize += nlen; skb->truesize -= nlen; /* Correct the sequence numbers. */ TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len; TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq; TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq; /* PSH and FIN should only be set in the second packet. */ flags = TCP_SKB_CB(skb)->tcp_flags; TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH); TCP_SKB_CB(buff)->tcp_flags = flags; /* This packet was never sent out yet, so no SACK bits. */ TCP_SKB_CB(buff)->sacked = 0; tcp_skb_fragment_eor(skb, buff); buff->ip_summed = CHECKSUM_PARTIAL; skb_split(skb, buff, len); tcp_fragment_tstamp(skb, buff); /* Fix up tso_factor for both original and new SKB. */ tcp_set_skb_tso_segs(skb, mss_now); tcp_set_skb_tso_segs(buff, mss_now); /* Link BUFF into the send queue. */ __skb_header_release(buff); tcp_insert_write_queue_after(skb, buff, sk, TCP_FRAG_IN_WRITE_QUEUE); return 0; } /* Try to defer sending, if possible, in order to minimize the amount * of TSO splitting we do. View it as a kind of TSO Nagle test. * * This algorithm is from John Heffner. */ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, bool *is_cwnd_limited, bool *is_rwnd_limited, u32 max_segs) { const struct inet_connection_sock *icsk = inet_csk(sk); u32 send_win, cong_win, limit, in_flight; struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *head; int win_divisor; s64 delta; if (icsk->icsk_ca_state >= TCP_CA_Recovery) goto send_now; /* Avoid bursty behavior by allowing defer * only if the last write was recent (1 ms). * Note that tp->tcp_wstamp_ns can be in the future if we have * packets waiting in a qdisc or device for EDT delivery. */ delta = tp->tcp_clock_cache - tp->tcp_wstamp_ns - NSEC_PER_MSEC; if (delta > 0) goto send_now; in_flight = tcp_packets_in_flight(tp); BUG_ON(tcp_skb_pcount(skb) <= 1); BUG_ON(tp->snd_cwnd <= in_flight); send_win = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; /* From in_flight test above, we know that cwnd > in_flight. */ cong_win = (tp->snd_cwnd - in_flight) * tp->mss_cache; limit = min(send_win, cong_win); /* If a full-sized TSO skb can be sent, do it. */ if (limit >= max_segs * tp->mss_cache) goto send_now; /* Middle in queue won't get any more data, full sendable already? */ if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len)) goto send_now; win_divisor = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_win_divisor); if (win_divisor) { u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache); /* If at least some fraction of a window is available, * just use it. */ chunk /= win_divisor; if (limit >= chunk) goto send_now; } else { /* Different approach, try not to defer past a single * ACK. Receiver should ACK every other full sized * frame, so if we have space for more than 3 frames * then send now. */ if (limit > tcp_max_tso_deferred_mss(tp) * tp->mss_cache) goto send_now; } /* TODO : use tsorted_sent_queue ? */ head = tcp_rtx_queue_head(sk); if (!head) goto send_now; delta = tp->tcp_clock_cache - head->tstamp; /* If next ACK is likely to come too late (half srtt), do not defer */ if ((s64)(delta - (u64)NSEC_PER_USEC * (tp->srtt_us >> 4)) < 0) goto send_now; /* Ok, it looks like it is advisable to defer. * Three cases are tracked : * 1) We are cwnd-limited * 2) We are rwnd-limited * 3) We are application limited. */ if (cong_win < send_win) { if (cong_win <= skb->len) { *is_cwnd_limited = true; return true; } } else { if (send_win <= skb->len) { *is_rwnd_limited = true; return true; } } /* If this packet won't get more data, do not wait. */ if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) || TCP_SKB_CB(skb)->eor) goto send_now; return true; send_now: return false; } static inline void tcp_mtu_check_reprobe(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); u32 interval; s32 delta; interval = net->ipv4.sysctl_tcp_probe_interval; delta = tcp_jiffies32 - icsk->icsk_mtup.probe_timestamp; if (unlikely(delta >= interval * HZ)) { int mss = tcp_current_mss(sk); /* Update current search range */ icsk->icsk_mtup.probe_size = 0; icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) + icsk->icsk_af_ops->net_header_len; icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); /* Update probe time stamp */ icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } } static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) { struct sk_buff *skb, *next; skb = tcp_send_head(sk); tcp_for_write_queue_from_safe(skb, next, sk) { if (len <= skb->len) break; if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb)) return false; len -= skb->len; } return true; } /* Create a new MTU probe if we are ready. * MTU probe is regularly attempting to increase the path MTU by * deliberately sending larger packets. This discovers routing * changes resulting in larger path MTUs. * * Returns 0 if we should wait to probe (no cwnd available), * 1 if a probe was sent, * -1 otherwise */ static int tcp_mtu_probe(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb, *nskb, *next; struct net *net = sock_net(sk); int probe_size; int size_needed; int copy, len; int mss_now; int interval; /* Not currently probing/verifying, * not in recovery, * have enough cwnd, and * not SACKing (the variable headers throw things off) */ if (likely(!icsk->icsk_mtup.enabled || icsk->icsk_mtup.probe_size || inet_csk(sk)->icsk_ca_state != TCP_CA_Open || tp->snd_cwnd < 11 || tp->rx_opt.num_sacks || tp->rx_opt.dsack)) return -1; /* Use binary search for probe_size between tcp_mss_base, * and current mss_clamp. if (search_high - search_low) * smaller than a threshold, backoff from probing. */ mss_now = tcp_current_mss(sk); probe_size = tcp_mtu_to_mss(sk, (icsk->icsk_mtup.search_high + icsk->icsk_mtup.search_low) >> 1); size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache; interval = icsk->icsk_mtup.search_high - icsk->icsk_mtup.search_low; /* When misfortune happens, we are reprobing actively, * and then reprobe timer has expired. We stick with current * probing process by not resetting search range to its orignal. */ if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) || interval < net->ipv4.sysctl_tcp_probe_threshold) { /* Check whether enough time has elaplased for * another round of probing. */ tcp_mtu_check_reprobe(sk); return -1; } /* Have enough data in the send queue to probe? */ if (tp->write_seq - tp->snd_nxt < size_needed) return -1; if (tp->snd_wnd < size_needed) return -1; if (after(tp->snd_nxt + size_needed, tcp_wnd_end(tp))) return 0; /* Do we need to wait to drain cwnd? With none in flight, don't stall */ if (tcp_packets_in_flight(tp) + 2 > tp->snd_cwnd) { if (!tcp_packets_in_flight(tp)) return -1; else return 0; } if (!tcp_can_coalesce_send_queue_head(sk, probe_size)) return -1; /* We're allowed to probe. Build it now. */ nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false); if (!nskb) return -1; sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); skb = tcp_send_head(sk); skb_copy_decrypted(nskb, skb); TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq; TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size; TCP_SKB_CB(nskb)->tcp_flags = TCPHDR_ACK; TCP_SKB_CB(nskb)->sacked = 0; nskb->csum = 0; nskb->ip_summed = CHECKSUM_PARTIAL; tcp_insert_write_queue_before(nskb, skb, sk); tcp_highest_sack_replace(sk, skb, nskb); len = 0; tcp_for_write_queue_from_safe(skb, next, sk) { copy = min_t(int, skb->len, probe_size - len); skb_copy_bits(skb, 0, skb_put(nskb, copy), copy); if (skb->len <= copy) { /* We've eaten all the data from this skb. * Throw it away. */ TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; /* If this is the last SKB we copy and eor is set * we need to propagate it to the new skb. */ TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor; tcp_skb_collapse_tstamp(nskb, skb); tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); } else { TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags & ~(TCPHDR_FIN|TCPHDR_PSH); if (!skb_shinfo(skb)->nr_frags) { skb_pull(skb, copy); } else { __pskb_trim_head(skb, copy); tcp_set_skb_tso_segs(skb, mss_now); } TCP_SKB_CB(skb)->seq += copy; } len += copy; if (len >= probe_size) break; } tcp_init_tso_segs(nskb, nskb->len); /* We're ready to send. If this fails, the probe will * be resegmented into mss-sized pieces by tcp_write_xmit(). */ if (!tcp_transmit_skb(sk, nskb, 1, GFP_ATOMIC)) { /* Decrement cwnd here because we are sending * effectively two packets. */ tp->snd_cwnd--; tcp_event_new_data_sent(sk, nskb); icsk->icsk_mtup.probe_size = tcp_mss_to_mtu(sk, nskb->len); tp->mtu_probe.probe_seq_start = TCP_SKB_CB(nskb)->seq; tp->mtu_probe.probe_seq_end = TCP_SKB_CB(nskb)->end_seq; return 1; } return -1; } static bool tcp_pacing_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (!tcp_needs_internal_pacing(sk)) return false; if (tp->tcp_wstamp_ns <= tp->tcp_clock_cache) return false; if (!hrtimer_is_queued(&tp->pacing_timer)) { hrtimer_start(&tp->pacing_timer, ns_to_ktime(tp->tcp_wstamp_ns), HRTIMER_MODE_ABS_PINNED_SOFT); sock_hold(sk); } return true; } /* TCP Small Queues : * Control number of packets in qdisc/devices to two packets / or ~1 ms. * (These limits are doubled for retransmits) * This allows for : * - better RTT estimation and ACK scheduling * - faster recovery * - high rates * Alas, some drivers / subsystems require a fair amount * of queued bytes to ensure line rate. * One example is wifi aggregation (802.11 AMPDU) */ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, unsigned int factor) { unsigned long limit; limit = max_t(unsigned long, 2 * skb->truesize, sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift)); if (sk->sk_pacing_status == SK_PACING_NONE) limit = min_t(unsigned long, limit, sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes); limit <<= factor; if (static_branch_unlikely(&tcp_tx_delay_enabled) && tcp_sk(sk)->tcp_tx_delay) { u64 extra_bytes = (u64)sk->sk_pacing_rate * tcp_sk(sk)->tcp_tx_delay; /* TSQ is based on skb truesize sum (sk_wmem_alloc), so we * approximate our needs assuming an ~100% skb->truesize overhead. * USEC_PER_SEC is approximated by 2^20. * do_div(extra_bytes, USEC_PER_SEC/2) is replaced by a right shift. */ extra_bytes >>= (20 - 1); limit += extra_bytes; } if (refcount_read(&sk->sk_wmem_alloc) > limit) { /* Always send skb if rtx queue is empty. * No need to wait for TX completion to call us back, * after softirq/tasklet schedule. * This helps when TX completions are delayed too much. */ if (tcp_rtx_queue_empty(sk)) return false; set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); /* It is possible TX completion already happened * before we set TSQ_THROTTLED, so we must * test again the condition. */ smp_mb__after_atomic(); if (refcount_read(&sk->sk_wmem_alloc) > limit) return true; } return false; } static void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new) { const u32 now = tcp_jiffies32; enum tcp_chrono old = tp->chrono_type; if (old > TCP_CHRONO_UNSPEC) tp->chrono_stat[old - 1] += now - tp->chrono_start; tp->chrono_start = now; tp->chrono_type = new; } void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type) { struct tcp_sock *tp = tcp_sk(sk); /* If there are multiple conditions worthy of tracking in a * chronograph then the highest priority enum takes precedence * over the other conditions. So that if something "more interesting" * starts happening, stop the previous chrono and start a new one. */ if (type > tp->chrono_type) tcp_chrono_set(tp, type); } void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type) { struct tcp_sock *tp = tcp_sk(sk); /* There are multiple conditions worthy of tracking in a * chronograph, so that the highest priority enum takes * precedence over the other conditions (see tcp_chrono_start). * If a condition stops, we only stop chrono tracking if * it's the "most interesting" or current chrono we are * tracking and starts busy chrono if we have pending data. */ if (tcp_rtx_and_write_queues_empty(sk)) tcp_chrono_set(tp, TCP_CHRONO_UNSPEC); else if (type == tp->chrono_type) tcp_chrono_set(tp, TCP_CHRONO_BUSY); } /* This routine writes packets to the network. It advances the * send_head. This happens as incoming acks open up the remote * window for us. * * LARGESEND note: !tcp_urg_mode is overkill, only frames between * snd_up-64k-mss .. snd_up cannot be large. However, taking into * account rare use of URG, this is not a big flaw. * * Send at most one packet when push_one > 0. Temporarily ignore * cwnd limit to force at most one packet out when push_one == 2. * Returns true, if no segments are in flight and we have queued segments, * but cannot send anything now because of SWS or another problem. */ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; unsigned int tso_segs, sent_pkts; int cwnd_quota; int result; bool is_cwnd_limited = false, is_rwnd_limited = false; u32 max_segs; sent_pkts = 0; tcp_mstamp_refresh(tp); if (!push_one) { /* Do MTU probing. */ result = tcp_mtu_probe(sk); if (!result) { return false; } else if (result > 0) { sent_pkts = 1; } } max_segs = tcp_tso_segs(sk, mss_now); while ((skb = tcp_send_head(sk))) { unsigned int limit; if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { /* "skb_mstamp_ns" is used as a start point for the retransmit timer */ skb->skb_mstamp_ns = tp->tcp_wstamp_ns = tp->tcp_clock_cache; list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); tcp_init_tso_segs(skb, mss_now); goto repair; /* Skip network transmission */ } if (tcp_pacing_check(sk)) break; tso_segs = tcp_init_tso_segs(skb, mss_now); BUG_ON(!tso_segs); cwnd_quota = tcp_cwnd_test(tp, skb); if (!cwnd_quota) { if (push_one == 2) /* Force out a loss probe pkt. */ cwnd_quota = 1; else break; } if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) { is_rwnd_limited = true; break; } if (tso_segs == 1) { if (unlikely(!tcp_nagle_test(tp, skb, mss_now, (tcp_skb_is_last(sk, skb) ? nonagle : TCP_NAGLE_PUSH)))) break; } else { if (!push_one && tcp_tso_should_defer(sk, skb, &is_cwnd_limited, &is_rwnd_limited, max_segs)) break; } limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, min_t(unsigned int, cwnd_quota, max_segs), nonagle); if (skb->len > limit && unlikely(tso_fragment(sk, skb, limit, mss_now, gfp))) break; if (tcp_small_queue_check(sk, skb, 0)) break; /* Argh, we hit an empty skb(), presumably a thread * is sleeping in sendmsg()/sk_stream_wait_memory(). * We do not want to send a pure-ack packet and have * a strange looking rtx queue with empty packet(s). */ if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) break; if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; repair: /* Advance the send_head. This one is sent out. * This call will increment packets_out. */ tcp_event_new_data_sent(sk, skb); tcp_minshall_update(tp, mss_now, skb); sent_pkts += tcp_skb_pcount(skb); if (push_one) break; } if (is_rwnd_limited) tcp_chrono_start(sk, TCP_CHRONO_RWND_LIMITED); else tcp_chrono_stop(sk, TCP_CHRONO_RWND_LIMITED); is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd); if (likely(sent_pkts || is_cwnd_limited)) tcp_cwnd_validate(sk, is_cwnd_limited); if (likely(sent_pkts)) { if (tcp_in_cwnd_reduction(sk)) tp->prr_out += sent_pkts; /* Send one loss probe per tail loss episode. */ if (push_one != 2) tcp_schedule_loss_probe(sk, false); return false; } return !tp->packets_out && !tcp_write_queue_empty(sk); } bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); u32 timeout, rto_delta_us; int early_retrans; /* Don't do any loss probe on a Fast Open connection before 3WHS * finishes. */ if (rcu_access_pointer(tp->fastopen_rsk)) return false; early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans; /* Schedule a loss probe in 2*RTT for SACK capable connections * not in loss recovery, that are either limited by cwnd or application. */ if ((early_retrans != 3 && early_retrans != 4) || !tp->packets_out || !tcp_is_sack(tp) || (icsk->icsk_ca_state != TCP_CA_Open && icsk->icsk_ca_state != TCP_CA_CWR)) return false; /* Probe timeout is 2*rtt. Add minimum RTO to account * for delayed ack when there's one outstanding packet. If no RTT * sample is available then probe after TCP_TIMEOUT_INIT. */ if (tp->srtt_us) { timeout = usecs_to_jiffies(tp->srtt_us >> 2); if (tp->packets_out == 1) timeout += TCP_RTO_MIN; else timeout += TCP_TIMEOUT_MIN; } else { timeout = TCP_TIMEOUT_INIT; } /* If the RTO formula yields an earlier time, then use that time. */ rto_delta_us = advancing_rto ? jiffies_to_usecs(inet_csk(sk)->icsk_rto) : tcp_rto_delta_us(sk); /* How far in future is RTO? */ if (rto_delta_us > 0) timeout = min_t(u32, timeout, usecs_to_jiffies(rto_delta_us)); tcp_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, TCP_RTO_MAX); return true; } /* Thanks to skb fast clones, we can detect if a prior transmit of * a packet is still in a qdisc or driver queue. * In this case, there is very little point doing a retransmit ! */ static bool skb_still_in_host_queue(const struct sock *sk, const struct sk_buff *skb) { if (unlikely(skb_fclone_busy(sk, skb))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); return true; } return false; } /* When probe timeout (PTO) fires, try send a new segment if possible, else * retransmit the last segment. */ void tcp_send_loss_probe(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; int pcount; int mss = tcp_current_mss(sk); /* At most one outstanding TLP */ if (tp->tlp_high_seq) goto rearm_timer; tp->tlp_retrans = 0; skb = tcp_send_head(sk); if (skb && tcp_snd_wnd_test(tp, skb, mss)) { pcount = tp->packets_out; tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); if (tp->packets_out > pcount) goto probe_sent; goto rearm_timer; } skb = skb_rb_last(&sk->tcp_rtx_queue); if (unlikely(!skb)) { WARN_ONCE(tp->packets_out, "invalid inflight: %u state %u cwnd %u mss %d\n", tp->packets_out, sk->sk_state, tp->snd_cwnd, mss); inet_csk(sk)->icsk_pending = 0; return; } if (skb_still_in_host_queue(sk, skb)) goto rearm_timer; pcount = tcp_skb_pcount(skb); if (WARN_ON(!pcount)) goto rearm_timer; if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) { if (unlikely(tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, (pcount - 1) * mss, mss, GFP_ATOMIC))) goto rearm_timer; skb = skb_rb_next(skb); } if (WARN_ON(!skb || !tcp_skb_pcount(skb))) goto rearm_timer; if (__tcp_retransmit_skb(sk, skb, 1)) goto rearm_timer; tp->tlp_retrans = 1; probe_sent: /* Record snd_nxt for loss detection. */ tp->tlp_high_seq = tp->snd_nxt; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); /* Reset s.t. tcp_rearm_rto will restart timer from now */ inet_csk(sk)->icsk_pending = 0; rearm_timer: tcp_rearm_rto(sk); } /* Push out any pending frames which were held back due to * TCP_CORK or attempt at coalescing tiny packets. * The socket must be locked by the caller. */ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle) { /* If we are closed, the bytes will have to remain here. * In time closedown will finish, we empty the write queue and * all will be happy. */ if (unlikely(sk->sk_state == TCP_CLOSE)) return; if (tcp_write_xmit(sk, cur_mss, nonagle, 0, sk_gfp_mask(sk, GFP_ATOMIC))) tcp_check_probe_timer(sk); } /* Send _single_ skb sitting at the send head. This function requires * true push pending frames to setup probe timer etc. */ void tcp_push_one(struct sock *sk, unsigned int mss_now) { struct sk_buff *skb = tcp_send_head(sk); BUG_ON(!skb || skb->len < mss_now); tcp_write_xmit(sk, mss_now, TCP_NAGLE_PUSH, 1, sk->sk_allocation); } /* This function returns the amount that we can raise the * usable window based on the following constraints * * 1. The window can never be shrunk once it is offered (RFC 793) * 2. We limit memory per socket * * RFC 1122: * "the suggested [SWS] avoidance algorithm for the receiver is to keep * RECV.NEXT + RCV.WIN fixed until: * RCV.BUFF - RCV.USER - RCV.WINDOW >= min(1/2 RCV.BUFF, MSS)" * * i.e. don't raise the right edge of the window until you can raise * it at least MSS bytes. * * Unfortunately, the recommended algorithm breaks header prediction, * since header prediction assumes th->window stays fixed. * * Strictly speaking, keeping th->window fixed violates the receiver * side SWS prevention criteria. The problem is that under this rule * a stream of single byte packets will cause the right side of the * window to always advance by a single byte. * * Of course, if the sender implements sender side SWS prevention * then this will not be a problem. * * BSD seems to make the following compromise: * * If the free space is less than the 1/4 of the maximum * space available and the free space is less than 1/2 mss, * then set the window to 0. * [ Actually, bsd uses MSS and 1/4 of maximal _window_ ] * Otherwise, just prevent the window from shrinking * and from being larger than the largest representable value. * * This prevents incremental opening of the window in the regime * where TCP is limited by the speed of the reader side taking * data out of the TCP receive queue. It does nothing about * those cases where the window is constrained on the sender side * because the pipeline is full. * * BSD also seems to "accidentally" limit itself to windows that are a * multiple of MSS, at least until the free space gets quite small. * This would appear to be a side effect of the mbuf implementation. * Combining these two algorithms results in the observed behavior * of having a fixed window size at almost all times. * * Below we obtain similar behavior by forcing the offered window to * a multiple of the mss when it is feasible to do so. * * Note, we don't "adjust" for TIMESTAMP or SACK option bytes. * Regular options like TIMESTAMP are taken into account. */ u32 __tcp_select_window(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); /* MSS for the peer's data. Previous versions used mss_clamp * here. I don't know if the value based on our guesses * of peer's MSS is better for the performance. It's more correct * but may be worse for the performance because of rcv_mss * fluctuations. --SAW 1998/11/1 */ int mss = icsk->icsk_ack.rcv_mss; int free_space = tcp_space(sk); int allowed_space = tcp_full_space(sk); int full_space, window; if (sk_is_mptcp(sk)) mptcp_space(sk, &free_space, &allowed_space); full_space = min_t(int, tp->window_clamp, allowed_space); if (unlikely(mss > full_space)) { mss = full_space; if (mss <= 0) return 0; } if (free_space < (full_space >> 1)) { icsk->icsk_ack.quick = 0; if (tcp_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); /* free_space might become our new window, make sure we don't * increase it due to wscale. */ free_space = round_down(free_space, 1 << tp->rx_opt.rcv_wscale); /* if free space is less than mss estimate, or is below 1/16th * of the maximum allowed, try to move to zero-window, else * tcp_clamp_window() will grow rcv buf up to tcp_rmem[2], and * new incoming data is dropped due to memory limits. * With large window, mss test triggers way too late in order * to announce zero window in time before rmem limit kicks in. */ if (free_space < (allowed_space >> 4) || free_space < mss) return 0; } if (free_space > tp->rcv_ssthresh) free_space = tp->rcv_ssthresh; /* Don't do rounding if we are using window scaling, since the * scaled window will not line up with the MSS boundary anyway. */ if (tp->rx_opt.rcv_wscale) { window = free_space; /* Advertise enough space so that it won't get scaled away. * Import case: prevent zero window announcement if * 1<<rcv_wscale > mss. */ window = ALIGN(window, (1 << tp->rx_opt.rcv_wscale)); } else { window = tp->rcv_wnd; /* Get the largest window that is a nice multiple of mss. * Window clamp already applied above. * If our current window offering is within 1 mss of the * free space we just keep it. This prevents the divide * and multiply from happening most of the time. * We also don't do any window rounding when the free space * is too small. */ if (window <= free_space - mss || window > free_space) window = rounddown(free_space, mss); else if (mss == full_space && free_space > window + (full_space >> 1)) window = free_space; } return window; } void tcp_skb_collapse_tstamp(struct sk_buff *skb, const struct sk_buff *next_skb) { if (unlikely(tcp_has_tx_tstamp(next_skb))) { const struct skb_shared_info *next_shinfo = skb_shinfo(next_skb); struct skb_shared_info *shinfo = skb_shinfo(skb); shinfo->tx_flags |= next_shinfo->tx_flags & SKBTX_ANY_TSTAMP; shinfo->tskey = next_shinfo->tskey; TCP_SKB_CB(skb)->txstamp_ack |= TCP_SKB_CB(next_skb)->txstamp_ack; } } /* Collapses two adjacent SKB's during retransmission. */ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *next_skb = skb_rb_next(skb); int next_skb_size; next_skb_size = next_skb->len; BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1); if (next_skb_size) { if (next_skb_size <= skb_availroom(skb)) skb_copy_bits(next_skb, 0, skb_put(skb, next_skb_size), next_skb_size); else if (!tcp_skb_shift(skb, next_skb, 1, next_skb_size)) return false; } tcp_highest_sack_replace(sk, next_skb, skb); /* Update sequence range on original skb. */ TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq; /* Merge over control information. This moves PSH/FIN etc. over */ TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(next_skb)->tcp_flags; /* All done, get rid of second SKB and account for it so * packet counting does not break. */ TCP_SKB_CB(skb)->sacked |= TCP_SKB_CB(next_skb)->sacked & TCPCB_EVER_RETRANS; TCP_SKB_CB(skb)->eor = TCP_SKB_CB(next_skb)->eor; /* changed transmit queue under us so clear hints */ tcp_clear_retrans_hints_partial(tp); if (next_skb == tp->retransmit_skb_hint) tp->retransmit_skb_hint = skb; tcp_adjust_pcount(sk, next_skb, tcp_skb_pcount(next_skb)); tcp_skb_collapse_tstamp(skb, next_skb); tcp_rtx_queue_unlink_and_free(next_skb, sk); return true; } /* Check if coalescing SKBs is legal. */ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) { if (tcp_skb_pcount(skb) > 1) return false; if (skb_cloned(skb)) return false; /* Some heuristics for collapsing over SACK'd could be invented */ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) return false; return true; } /* Collapse packets in the retransmit queue to make to create * less packets on the wire. This is only done on retransmission. */ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, int space) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb = to, *tmp; bool first = true; if (!sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse) return; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) return; skb_rbtree_walk_from_safe(skb, tmp) { if (!tcp_can_collapse(sk, skb)) break; if (!tcp_skb_can_collapse(to, skb)) break; space -= skb->len; if (first) { first = false; continue; } if (space < 0) break; if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp))) break; if (!tcp_collapse_retrans(sk, to)) break; } } /* This retransmits one SKB. Policy decisions and retransmit queue * state updates are done by the caller. Returns non-zero if an * error occurred which prevented the send. */ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned int cur_mss; int diff, len, err; /* Inconclusive MTU probe */ if (icsk->icsk_mtup.probe_size) icsk->icsk_mtup.probe_size = 0; /* Do not sent more than we queued. 1/4 is reserved for possible * copying overhead: fragmentation, tunneling, mangling etc. */ if (refcount_read(&sk->sk_wmem_alloc) > min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf)) return -EAGAIN; if (skb_still_in_host_queue(sk, skb)) return -EBUSY; if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) { WARN_ON_ONCE(1); return -EINVAL; } if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) return -ENOMEM; } if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) return -EHOSTUNREACH; /* Routing failure or similar. */ cur_mss = tcp_current_mss(sk); /* If receiver has shrunk his window, and skb is out of * new window, do not retransmit it. The exception is the * case, when window is shrunk to zero. In this case * our retransmit serves as a zero window probe. */ if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp)) && TCP_SKB_CB(skb)->seq != tp->snd_una) return -EAGAIN; len = cur_mss * segs; if (skb->len > len) { if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len, cur_mss, GFP_ATOMIC)) return -ENOMEM; /* We'll try again later. */ } else { if (skb_unclone(skb, GFP_ATOMIC)) return -ENOMEM; diff = tcp_skb_pcount(skb); tcp_set_skb_tso_segs(skb, cur_mss); diff -= tcp_skb_pcount(skb); if (diff) tcp_adjust_pcount(sk, skb, diff); if (skb->len < cur_mss) tcp_retrans_try_collapse(sk, skb, cur_mss); } /* RFC3168, section 6.1.1.1. ECN fallback */ if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN) tcp_ecn_clear_syn(sk, skb); /* Update global and local TCP statistics. */ segs = tcp_skb_pcount(skb); TCP_ADD_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS, segs); if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); tp->total_retrans += segs; tp->bytes_retrans += skb->len; /* make sure skb->data is aligned on arches that require it * and check if ack-trimming & collapsing extended the headroom * beyond what csum_start can cover. */ if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) || skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb; tcp_skb_tsorted_save(skb) { nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); if (nskb) { nskb->dev = NULL; err = tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC); } else { err = -ENOBUFS; } } tcp_skb_tsorted_restore(skb); if (!err) { tcp_update_skb_after_send(sk, skb, tp->tcp_wstamp_ns); tcp_rate_skb_sent(sk, skb); } } else { err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } /* To avoid taking spuriously low RTT samples based on a timestamp * for a transmit that never happened, always mark EVER_RETRANS */ TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG)) tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB, TCP_SKB_CB(skb)->seq, segs, err); if (likely(!err)) { trace_tcp_retransmit_skb(sk, skb); } else if (err != -EBUSY) { NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs); } return err; } int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) { struct tcp_sock *tp = tcp_sk(sk); int err = __tcp_retransmit_skb(sk, skb, segs); if (err == 0) { #if FASTRETRANS_DEBUG > 0 if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { net_dbg_ratelimited("retrans_out leaked\n"); } #endif TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS; tp->retrans_out += tcp_skb_pcount(skb); } /* Save stamp of the first (attempted) retransmit. */ if (!tp->retrans_stamp) tp->retrans_stamp = tcp_skb_timestamp(skb); if (tp->undo_retrans < 0) tp->undo_retrans = 0; tp->undo_retrans += tcp_skb_pcount(skb); return err; } /* This gets called after a retransmit timeout, and the initially * retransmitted data is acknowledged. It tries to continue * resending the rest of the retransmit queue, until either * we've sent it all or the congestion window limit is reached. */ void tcp_xmit_retransmit_queue(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); struct sk_buff *skb, *rtx_head, *hole = NULL; struct tcp_sock *tp = tcp_sk(sk); bool rearm_timer = false; u32 max_segs; int mib_idx; if (!tp->packets_out) return; rtx_head = tcp_rtx_queue_head(sk); skb = tp->retransmit_skb_hint ?: rtx_head; max_segs = tcp_tso_segs(sk, tcp_current_mss(sk)); skb_rbtree_walk_from(skb) { __u8 sacked; int segs; if (tcp_pacing_check(sk)) break; /* we could do better than to assign each time */ if (!hole) tp->retransmit_skb_hint = skb; segs = tp->snd_cwnd - tcp_packets_in_flight(tp); if (segs <= 0) break; sacked = TCP_SKB_CB(skb)->sacked; /* In case tcp_shift_skb_data() have aggregated large skbs, * we need to make sure not sending too bigs TSO packets */ segs = min_t(int, segs, max_segs); if (tp->retrans_out >= tp->lost_out) { break; } else if (!(sacked & TCPCB_LOST)) { if (!hole && !(sacked & (TCPCB_SACKED_RETRANS|TCPCB_SACKED_ACKED))) hole = skb; continue; } else { if (icsk->icsk_ca_state != TCP_CA_Loss) mib_idx = LINUX_MIB_TCPFASTRETRANS; else mib_idx = LINUX_MIB_TCPSLOWSTARTRETRANS; } if (sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS)) continue; if (tcp_small_queue_check(sk, skb, 1)) break; if (tcp_retransmit_skb(sk, skb, segs)) break; NET_ADD_STATS(sock_net(sk), mib_idx, tcp_skb_pcount(skb)); if (tcp_in_cwnd_reduction(sk)) tp->prr_out += tcp_skb_pcount(skb); if (skb == rtx_head && icsk->icsk_pending != ICSK_TIME_REO_TIMEOUT) rearm_timer = true; } if (rearm_timer) tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, TCP_RTO_MAX); } /* We allow to exceed memory limits for FIN packets to expedite * connection tear down and (memory) recovery. * Otherwise tcp_send_fin() could be tempted to either delay FIN * or even be forced to close flow without any FIN. * In general, we want to allow one skb per socket to avoid hangs * with edge trigger epoll() */ void sk_forced_mem_schedule(struct sock *sk, int size) { int amt; if (size <= sk->sk_forward_alloc) return; amt = sk_mem_pages(size); sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; sk_memory_allocated_add(sk, amt); if (mem_cgroup_sockets_enabled && sk->sk_memcg) mem_cgroup_charge_skmem(sk->sk_memcg, amt); } /* Send a FIN. The caller locks the socket for us. * We should try to send a FIN packet really hard, but eventually give up. */ void tcp_send_fin(struct sock *sk) { struct sk_buff *skb, *tskb, *tail = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); /* Optimization, tack on the FIN if we have one skb in write queue and * this skb was not yet sent, or we are under memory pressure. * Note: in the latter case, FIN packet will be sent after a timeout, * as TCP stack thinks it has already been transmitted. */ tskb = tail; if (!tskb && tcp_under_memory_pressure(sk)) tskb = skb_rb_last(&sk->tcp_rtx_queue); if (tskb) { TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; if (!tail) { /* This means tskb was already sent. * Pretend we included the FIN on previous transmit. * We need to set tp->snd_nxt to the value it would have * if FIN had been sent. This is because retransmit path * does not change tp->snd_nxt. */ WRITE_ONCE(tp->snd_nxt, tp->snd_nxt + 1); return; } } else { skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); if (unlikely(!skb)) return; INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); skb_reserve(skb, MAX_TCP_HEADER); sk_forced_mem_schedule(sk, skb->truesize); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ tcp_init_nondata_skb(skb, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); tcp_queue_skb(sk, skb); } __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF); } /* We get here when a process closes a file descriptor (either due to * an explicit close() or as a byproduct of exit()'ing) and there * was unread data in the receive queue. This behavior is recommended * by RFC 2525, section 2.17. -DaveM */ void tcp_send_active_reset(struct sock *sk, gfp_t priority) { struct sk_buff *skb; TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS); /* NOTE: No TCP options attached and we never retransmit this. */ skb = alloc_skb(MAX_TCP_HEADER, priority); if (!skb) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); return; } /* Reserve space for headers and prepare control bits. */ skb_reserve(skb, MAX_TCP_HEADER); tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk), TCPHDR_ACK | TCPHDR_RST); tcp_mstamp_refresh(tcp_sk(sk)); /* Send it off. */ if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); /* skb of trace_tcp_send_reset() keeps the skb that caused RST, * skb here is different to the troublesome skb, so use NULL */ trace_tcp_send_reset(sk, NULL); } /* Send a crossed SYN-ACK during socket establishment. * WARNING: This routine must only be called when we have already sent * a SYN packet that crossed the incoming SYN that caused this routine * to get called. If this assumption fails then the initial rcv_wnd * and rcv_wscale values will not be correct. */ int tcp_send_synack(struct sock *sk) { struct sk_buff *skb; skb = tcp_rtx_queue_head(sk); if (!skb || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { pr_err("%s: wrong queue state\n", __func__); return -EFAULT; } if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) { if (skb_cloned(skb)) { struct sk_buff *nskb; tcp_skb_tsorted_save(skb) { nskb = skb_copy(skb, GFP_ATOMIC); } tcp_skb_tsorted_restore(skb); if (!nskb) return -ENOMEM; INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor); tcp_highest_sack_replace(sk, skb, nskb); tcp_rtx_queue_unlink_and_free(skb, sk); __skb_header_release(nskb); tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb); sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); skb = nskb; } TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ACK; tcp_ecn_send_synack(sk, skb); } return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } /** * tcp_make_synack - Allocate one skb and build a SYNACK packet. * @sk: listener socket * @dst: dst entry attached to the SYNACK. It is consumed and caller * should not use it again. * @req: request_sock pointer * @foc: cookie for tcp fast open * @synack_type: Type of synack to prepare * @syn_skb: SYN packet just received. It could be NULL for rtx case. */ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *md5 = NULL; struct tcp_out_options opts; struct sk_buff *skb; int tcp_header_size; struct tcphdr *th; int mss; u64 now; skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); if (unlikely(!skb)) { dst_release(dst); return NULL; } /* Reserve space for headers. */ skb_reserve(skb, MAX_TCP_HEADER); switch (synack_type) { case TCP_SYNACK_NORMAL: skb_set_owner_w(skb, req_to_sk(req)); break; case TCP_SYNACK_COOKIE: /* Under synflood, we do not attach skb to a socket, * to avoid false sharing. */ break; case TCP_SYNACK_FASTOPEN: /* sk is a const pointer, because we want to express multiple * cpu might call us concurrently. * sk->sk_wmem_alloc in an atomic, we can promote to rw. */ skb_set_owner_w(skb, (struct sock *)sk); break; } skb_dst_set(skb, dst); mss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); memset(&opts, 0, sizeof(opts)); now = tcp_clock_ns(); #ifdef CONFIG_SYN_COOKIES if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok)) skb->skb_mstamp_ns = cookie_init_timestamp(req, now); else #endif { skb->skb_mstamp_ns = now; if (!tcp_rsk(req)->snt_synack) /* Timestamp first SYNACK */ tcp_rsk(req)->snt_synack = tcp_skb_timestamp_us(skb); } #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); #endif skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); /* bpf program will be interested in the tcp_flags */ TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK; tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, foc, synack_type, syn_skb) + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); th = (struct tcphdr *)skb->data; memset(th, 0, sizeof(struct tcphdr)); th->syn = 1; th->ack = 1; tcp_ecn_make_synack(req, th); th->source = htons(ireq->ir_num); th->dest = ireq->ir_rmt_port; skb->mark = ireq->ir_mark; skb->ip_summed = CHECKSUM_PARTIAL; th->seq = htonl(tcp_rsk(req)->snt_isn); /* XXX data is queued and acked as is. No buffer/window check */ th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt); /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(min(req->rsk_rcv_wnd, 65535U)); tcp_options_write((__be32 *)(th + 1), NULL, &opts); th->doff = (tcp_header_size >> 2); __TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ if (md5) tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location, md5, req_to_sk(req), skb); rcu_read_unlock(); #endif bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb, synack_type, &opts); skb->skb_mstamp_ns = now; tcp_add_tx_delay(skb, tp); return skb; } EXPORT_SYMBOL(tcp_make_synack); static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst) { struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_congestion_ops *ca; u32 ca_key = dst_metric(dst, RTAX_CC_ALGO); if (ca_key == TCP_CA_UNSPEC) return; rcu_read_lock(); ca = tcp_ca_find_key(ca_key); if (likely(ca && bpf_try_module_get(ca, ca->owner))) { bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); icsk->icsk_ca_ops = ca; } rcu_read_unlock(); } /* Do all connect socket setups that can be done AF independent. */ static void tcp_connect_init(struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); __u8 rcv_wscale; u32 rcv_wnd; /* We'll fix this up when we get a response from the other end. * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT. */ tp->tcp_header_len = sizeof(struct tcphdr); if (sock_net(sk)->ipv4.sysctl_tcp_timestamps) tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED; #ifdef CONFIG_TCP_MD5SIG if (tp->af_specific->md5_lookup(sk, sk)) tp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif /* If user gave his TCP_MAXSEG, record it to clamp */ if (tp->rx_opt.user_mss) tp->rx_opt.mss_clamp = tp->rx_opt.user_mss; tp->max_window = 0; tcp_mtup_init(sk); tcp_sync_mss(sk, dst_mtu(dst)); tcp_ca_dst_init(sk, dst); if (!tp->window_clamp) tp->window_clamp = dst_metric(dst, RTAX_WINDOW); tp->advmss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); tcp_initialize_rcv_mss(sk); /* limit the window selection if the user enforce a smaller rx buffer */ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0)) tp->window_clamp = tcp_full_space(sk); rcv_wnd = tcp_rwnd_init_bpf(sk); if (rcv_wnd == 0) rcv_wnd = dst_metric(dst, RTAX_INITRWND); tcp_select_initial_window(sk, tcp_full_space(sk), tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, sock_net(sk)->ipv4.sysctl_tcp_window_scaling, &rcv_wscale, rcv_wnd); tp->rx_opt.rcv_wscale = rcv_wscale; tp->rcv_ssthresh = tp->rcv_wnd; sk->sk_err = 0; sock_reset_flag(sk, SOCK_DONE); tp->snd_wnd = 0; tcp_init_wl(tp, 0); tcp_write_queue_purge(sk); tp->snd_una = tp->write_seq; tp->snd_sml = tp->write_seq; tp->snd_up = tp->write_seq; WRITE_ONCE(tp->snd_nxt, tp->write_seq); if (likely(!tp->repair)) tp->rcv_nxt = 0; else tp->rcv_tstamp = tcp_jiffies32; tp->rcv_wup = tp->rcv_nxt; WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); inet_csk(sk)->icsk_rto = tcp_timeout_init(sk); inet_csk(sk)->icsk_retransmits = 0; tcp_clear_retrans(tp); } static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); tcb->end_seq += skb->len; __skb_header_release(skb); sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); WRITE_ONCE(tp->write_seq, tcb->end_seq); tp->packets_out += tcp_skb_pcount(skb); } /* Build and send a SYN with data and (cached) Fast Open cookie. However, * queue a data-only packet after the regular SYN, such that regular SYNs * are retransmitted on timeouts. Also if the remote SYN-ACK acknowledges * only the SYN sequence, the data are retransmitted in the first ACK. * If cookie is not cached or other error occurs, falls back to send a * regular SYN with Fast Open cookie request option. */ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_request *fo = tp->fastopen_req; int space, err = 0; struct sk_buff *syn_data; tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */ if (!tcp_fastopen_cookie_check(sk, &tp->rx_opt.mss_clamp, &fo->cookie)) goto fallback; /* MSS for SYN-data is based on cached MSS and bounded by PMTU and * user-MSS. Reserve maximum option space for middleboxes that add * private TCP options. The cost is reduced data space in SYN :( */ tp->rx_opt.mss_clamp = tcp_mss_clamp(tp, tp->rx_opt.mss_clamp); space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - MAX_TCP_OPTION_SPACE; space = min_t(size_t, space, fo->size); /* limit to order-0 allocations */ space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER)); syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation, false); if (!syn_data) goto fallback; syn_data->ip_summed = CHECKSUM_PARTIAL; memcpy(syn_data->cb, syn->cb, sizeof(syn->cb)); if (space) { int copied = copy_from_iter(skb_put(syn_data, space), space, &fo->data->msg_iter); if (unlikely(!copied)) { tcp_skb_tsorted_anchor_cleanup(syn_data); kfree_skb(syn_data); goto fallback; } if (copied != space) { skb_trim(syn_data, copied); space = copied; } skb_zcopy_set(syn_data, fo->uarg, NULL); } /* No more data pending in inet_wait_for_connect() */ if (space == fo->size) fo->data = NULL; fo->copied = space; tcp_connect_queue_skb(sk, syn_data); if (syn_data->len) tcp_chrono_start(sk, TCP_CHRONO_BUSY); err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation); syn->skb_mstamp_ns = syn_data->skb_mstamp_ns; /* Now full SYN+DATA was cloned and sent (or not), * remove the SYN from the original skb (syn_data) * we keep in write queue in case of a retransmit, as we * also have the SYN packet (with no data) in the same queue. */ TCP_SKB_CB(syn_data)->seq++; TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH; if (!err) { tp->syn_data = (fo->copied > 0); tcp_rbtree_insert(&sk->tcp_rtx_queue, syn_data); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT); goto done; } /* data was not sent, put it in write_queue */ __skb_queue_tail(&sk->sk_write_queue, syn_data); tp->packets_out -= tcp_skb_pcount(syn_data); fallback: /* Send a regular SYN with Fast Open cookie request option */ if (fo->cookie.len > 0) fo->cookie.len = 0; err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation); if (err) tp->syn_fastopen = 0; done: fo->cookie.len = -1; /* Exclude Fast Open option for SYN retries */ return err; } /* Build a SYN and send it off. */ int tcp_connect(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; int err; tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB, 0, NULL); if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) return -EHOSTUNREACH; /* Routing failure or similar. */ tcp_connect_init(sk); if (unlikely(tp->repair)) { tcp_finish_connect(sk, NULL); return 0; } buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, true); if (unlikely(!buff)) return -ENOBUFS; tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); tcp_mstamp_refresh(tp); tp->retrans_stamp = tcp_time_stamp(tp); tcp_connect_queue_skb(sk, buff); tcp_ecn_send_syn(sk, buff); tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); /* Send off SYN; include data in Fast Open. */ err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) : tcp_transmit_skb(sk, buff, 1, sk->sk_allocation); if (err == -ECONNREFUSED) return err; /* We change tp->snd_nxt after the tcp_transmit_skb() call * in order to make this packet get counted in tcpOutSegs. */ WRITE_ONCE(tp->snd_nxt, tp->write_seq); tp->pushed_seq = tp->write_seq; buff = tcp_send_head(sk); if (unlikely(buff)) { WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(buff)->seq); tp->pushed_seq = TCP_SKB_CB(buff)->seq; } TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS); /* Timer for repeating the SYN until an answer. */ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, TCP_RTO_MAX); return 0; } EXPORT_SYMBOL(tcp_connect); /* Send out a delayed ack, the caller does the policy checking * to see if we should even be here. See tcp_input.c:tcp_ack_snd_check() * for details. */ void tcp_send_delayed_ack(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); int ato = icsk->icsk_ack.ato; unsigned long timeout; if (ato > TCP_DELACK_MIN) { const struct tcp_sock *tp = tcp_sk(sk); int max_ato = HZ / 2; if (inet_csk_in_pingpong_mode(sk) || (icsk->icsk_ack.pending & ICSK_ACK_PUSHED)) max_ato = TCP_DELACK_MAX; /* Slow path, intersegment interval is "high". */ /* If some rtt estimate is known, use it to bound delayed ack. * Do not use inet_csk(sk)->icsk_rto here, use results of rtt measurements * directly. */ if (tp->srtt_us) { int rtt = max_t(int, usecs_to_jiffies(tp->srtt_us >> 3), TCP_DELACK_MIN); if (rtt < max_ato) max_ato = rtt; } ato = min(ato, max_ato); } ato = min_t(u32, ato, inet_csk(sk)->icsk_delack_max); /* Stay within the limit we were given */ timeout = jiffies + ato; /* Use new timeout only if there wasn't a older one earlier. */ if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) { /* If delack timer is about to expire, send ACK now. */ if (time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) { tcp_send_ack(sk); return; } if (!time_before(timeout, icsk->icsk_ack.timeout)) timeout = icsk->icsk_ack.timeout; } icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; icsk->icsk_ack.timeout = timeout; sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout); } /* This routine sends an ack and also updates the window. */ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) { struct sk_buff *buff; /* If we have been reset, we may not send again. */ if (sk->sk_state == TCP_CLOSE) return; /* We are not putting this on the write queue, so * tcp_transmit_skb() will set the ownership to this * sock. */ buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN)); if (unlikely(!buff)) { struct inet_connection_sock *icsk = inet_csk(sk); unsigned long delay; delay = TCP_DELACK_MAX << icsk->icsk_ack.retry; if (delay < TCP_RTO_MAX) icsk->icsk_ack.retry++; inet_csk_schedule_ack(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, delay, TCP_RTO_MAX); return; } /* Reserve space for headers and prepare control bits. */ skb_reserve(buff, MAX_TCP_HEADER); tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK); /* We do not want pure acks influencing TCP Small Queues or fq/pacing * too much. * SKB_TRUESIZE(max(1 .. 66, MAX_TCP_HEADER)) is unfortunately ~784 */ skb_set_tcp_pure_ack(buff); /* Send it off, this clears delayed acks for us. */ __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt); } EXPORT_SYMBOL_GPL(__tcp_send_ack); void tcp_send_ack(struct sock *sk) { __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt); } /* This routine sends a packet with an out of date sequence * number. It assumes the other end will try to ack it. * * Question: what should we make while urgent mode? * 4.4BSD forces sending single byte of data. We cannot send * out of window data, because we have SND.NXT==SND.MAX... * * Current solution: to send TWO zero-length segments in urgent mode: * one is with SEG.SEQ=SND.UNA to deliver urgent pointer, another is * out-of-date with SND.UNA-1 to probe window. */ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; /* We don't queue it, tcp_transmit_skb() sets ownership. */ skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN)); if (!skb) return -1; /* Reserve space for headers and set control bits. */ skb_reserve(skb, MAX_TCP_HEADER); /* Use a previous sequence. This should cause the other * end to send an ack. Don't queue or clone SKB, just * send it. */ tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK); NET_INC_STATS(sock_net(sk), mib); return tcp_transmit_skb(sk, skb, 0, (__force gfp_t)0); } /* Called from setsockopt( ... TCP_REPAIR ) */ void tcp_send_window_probe(struct sock *sk) { if (sk->sk_state == TCP_ESTABLISHED) { tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1; tcp_mstamp_refresh(tcp_sk(sk)); tcp_xmit_probe_skb(sk, 0, LINUX_MIB_TCPWINPROBE); } } /* Initiate keepalive or window probe from timer. */ int tcp_write_wakeup(struct sock *sk, int mib) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; if (sk->sk_state == TCP_CLOSE) return -1; skb = tcp_send_head(sk); if (skb && before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) { int err; unsigned int mss = tcp_current_mss(sk); unsigned int seg_size = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; if (before(tp->pushed_seq, TCP_SKB_CB(skb)->end_seq)) tp->pushed_seq = TCP_SKB_CB(skb)->end_seq; /* We are probing the opening of a window * but the window size is != 0 * must have been a result SWS avoidance ( sender ) */ if (seg_size < TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq || skb->len > mss) { seg_size = min(seg_size, mss); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; if (tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE, skb, seg_size, mss, GFP_ATOMIC)) return -1; } else if (!tcp_skb_pcount(skb)) tcp_set_skb_tso_segs(skb, mss); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); if (!err) tcp_event_new_data_sent(sk, skb); return err; } else { if (between(tp->snd_up, tp->snd_una + 1, tp->snd_una + 0xFFFF)) tcp_xmit_probe_skb(sk, 1, mib); return tcp_xmit_probe_skb(sk, 0, mib); } } /* A window probe timeout has occurred. If window is not closed send * a partial packet else a zero probe. */ void tcp_send_probe0(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); unsigned long timeout; int err; err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE); if (tp->packets_out || tcp_write_queue_empty(sk)) { /* Cancel probe timer, if it is not required. */ icsk->icsk_probes_out = 0; icsk->icsk_backoff = 0; icsk->icsk_probes_tstamp = 0; return; } icsk->icsk_probes_out++; if (err <= 0) { if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2) icsk->icsk_backoff++; timeout = tcp_probe0_when(sk, TCP_RTO_MAX); } else { /* If packet was not sent due to local congestion, * Let senders fight for local resources conservatively. */ timeout = TCP_RESOURCE_PROBE_INTERVAL; } timeout = tcp_clamp_probe0_to_user_timeout(sk, timeout); tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX); } int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) { const struct tcp_request_sock_ops *af_ops = tcp_rsk(req)->af_specific; struct flowi fl; int res; tcp_rsk(req)->txhash = net_tx_rndhash(); res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, NULL); if (!res) { __TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); if (unlikely(tcp_passive_fastopen(sk))) tcp_sk(sk)->total_retrans++; trace_tcp_retransmit_synack(sk, req); } return res; } EXPORT_SYMBOL(tcp_rtx_synack);
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_CLOCK_H #define _LINUX_SCHED_CLOCK_H #include <linux/smp.h> /* * Do not use outside of architecture code which knows its limitations. * * sched_clock() has no promise of monotonicity or bounded drift between * CPUs, use (which you should not) requires disabling IRQs. * * Please use one of the three interfaces below. */ extern unsigned long long notrace sched_clock(void); /* * See the comment in kernel/sched/clock.c */ extern u64 running_clock(void); extern u64 sched_clock_cpu(int cpu); extern void sched_clock_init(void); #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK static inline void sched_clock_tick(void) { } static inline void clear_sched_clock_stable(void) { } static inline void sched_clock_idle_sleep_event(void) { } static inline void sched_clock_idle_wakeup_event(void) { } static inline u64 cpu_clock(int cpu) { return sched_clock(); } static inline u64 local_clock(void) { return sched_clock(); } #else extern int sched_clock_stable(void); extern void clear_sched_clock_stable(void); /* * When sched_clock_stable(), __sched_clock_offset provides the offset * between local_clock() and sched_clock(). */ extern u64 __sched_clock_offset; extern void sched_clock_tick(void); extern void sched_clock_tick_stable(void); extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(void); /* * As outlined in clock.c, provides a fast, high resolution, nanosecond * time source that is monotonic per cpu argument and has bounded drift * between cpus. * * ######################### BIG FAT WARNING ########################## * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can # * # go backwards !! # * #################################################################### */ static inline u64 cpu_clock(int cpu) { return sched_clock_cpu(cpu); } static inline u64 local_clock(void) { return sched_clock_cpu(raw_smp_processor_id()); } #endif #ifdef CONFIG_IRQ_TIME_ACCOUNTING /* * An i/f to runtime opt-in for irq time accounting based off of sched_clock. * The reason for this explicit opt-in is not to have perf penalty with * slow sched_clocks. */ extern void enable_sched_clock_irqtime(void); extern void disable_sched_clock_irqtime(void); #else static inline void enable_sched_clock_irqtime(void) {} static inline void disable_sched_clock_irqtime(void) {} #endif #endif /* _LINUX_SCHED_CLOCK_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _NET_ETHTOOL_NETLINK_H #define _NET_ETHTOOL_NETLINK_H #include <linux/ethtool_netlink.h> #include <linux/netdevice.h> #include <net/genetlink.h> #include <net/sock.h> struct ethnl_req_info; int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, const struct nlattr *nest, struct net *net, struct netlink_ext_ack *extack, bool require_dev); int ethnl_fill_reply_header(struct sk_buff *skb, struct net_device *dev, u16 attrtype); struct sk_buff *ethnl_reply_init(size_t payload, struct net_device *dev, u8 cmd, u16 hdr_attrtype, struct genl_info *info, void **ehdrp); void *ethnl_dump_put(struct sk_buff *skb, struct netlink_callback *cb, u8 cmd); void *ethnl_bcastmsg_put(struct sk_buff *skb, u8 cmd); int ethnl_multicast(struct sk_buff *skb, struct net_device *dev); /** * ethnl_strz_size() - calculate attribute length for fixed size string * @s: ETH_GSTRING_LEN sized string (may not be null terminated) * * Return: total length of an attribute with null terminated string from @s */ static inline int ethnl_strz_size(const char *s) { return nla_total_size(strnlen(s, ETH_GSTRING_LEN) + 1); } /** * ethnl_put_strz() - put string attribute with fixed size string * @skb: skb with the message * @attrype: attribute type * @s: ETH_GSTRING_LEN sized string (may not be null terminated) * * Puts an attribute with null terminated string from @s into the message. * * Return: 0 on success, negative error code on failure */ static inline int ethnl_put_strz(struct sk_buff *skb, u16 attrtype, const char *s) { unsigned int len = strnlen(s, ETH_GSTRING_LEN); struct nlattr *attr; attr = nla_reserve(skb, attrtype, len + 1); if (!attr) return -EMSGSIZE; memcpy(nla_data(attr), s, len); ((char *)nla_data(attr))[len] = '\0'; return 0; } /** * ethnl_update_u32() - update u32 value from NLA_U32 attribute * @dst: value to update * @attr: netlink attribute with new value or null * @mod: pointer to bool for modification tracking * * Copy the u32 value from NLA_U32 netlink attribute @attr into variable * pointed to by @dst; do nothing if @attr is null. Bool pointed to by @mod * is set to true if this function changed the value of *dst, otherwise it * is left as is. */ static inline void ethnl_update_u32(u32 *dst, const struct nlattr *attr, bool *mod) { u32 val; if (!attr) return; val = nla_get_u32(attr); if (*dst == val) return; *dst = val; *mod = true; } /** * ethnl_update_u8() - update u8 value from NLA_U8 attribute * @dst: value to update * @attr: netlink attribute with new value or null * @mod: pointer to bool for modification tracking * * Copy the u8 value from NLA_U8 netlink attribute @attr into variable * pointed to by @dst; do nothing if @attr is null. Bool pointed to by @mod * is set to true if this function changed the value of *dst, otherwise it * is left as is. */ static inline void ethnl_update_u8(u8 *dst, const struct nlattr *attr, bool *mod) { u8 val; if (!attr) return; val = nla_get_u8(attr); if (*dst == val) return; *dst = val; *mod = true; } /** * ethnl_update_bool32() - update u32 used as bool from NLA_U8 attribute * @dst: value to update * @attr: netlink attribute with new value or null * @mod: pointer to bool for modification tracking * * Use the u8 value from NLA_U8 netlink attribute @attr to set u32 variable * pointed to by @dst to 0 (if zero) or 1 (if not); do nothing if @attr is * null. Bool pointed to by @mod is set to true if this function changed the * logical value of *dst, otherwise it is left as is. */ static inline void ethnl_update_bool32(u32 *dst, const struct nlattr *attr, bool *mod) { u8 val; if (!attr) return; val = !!nla_get_u8(attr); if (!!*dst == val) return; *dst = val; *mod = true; } /** * ethnl_update_binary() - update binary data from NLA_BINARY atribute * @dst: value to update * @len: destination buffer length * @attr: netlink attribute with new value or null * @mod: pointer to bool for modification tracking * * Use the u8 value from NLA_U8 netlink attribute @attr to rewrite data block * of length @len at @dst by attribute payload; do nothing if @attr is null. * Bool pointed to by @mod is set to true if this function changed the logical * value of *dst, otherwise it is left as is. */ static inline void ethnl_update_binary(void *dst, unsigned int len, const struct nlattr *attr, bool *mod) { if (!attr) return; if (nla_len(attr) < len) len = nla_len(attr); if (!memcmp(dst, nla_data(attr), len)) return; memcpy(dst, nla_data(attr), len); *mod = true; } /** * ethnl_update_bitfield32() - update u32 value from NLA_BITFIELD32 attribute * @dst: value to update * @attr: netlink attribute with new value or null * @mod: pointer to bool for modification tracking * * Update bits in u32 value which are set in attribute's mask to values from * attribute's value. Do nothing if @attr is null or the value wouldn't change; * otherwise, set bool pointed to by @mod to true. */ static inline void ethnl_update_bitfield32(u32 *dst, const struct nlattr *attr, bool *mod) { struct nla_bitfield32 change; u32 newval; if (!attr) return; change = nla_get_bitfield32(attr); newval = (*dst & ~change.selector) | (change.value & change.selector); if (*dst == newval) return; *dst = newval; *mod = true; } /** * ethnl_reply_header_size() - total size of reply header * * This is an upper estimate so that we do not need to hold RTNL lock longer * than necessary (to prevent rename between size estimate and composing the * message). Accounts only for device ifindex and name as those are the only * attributes ethnl_fill_reply_header() puts into the reply header. */ static inline unsigned int ethnl_reply_header_size(void) { return nla_total_size(nla_total_size(sizeof(u32)) + nla_total_size(IFNAMSIZ)); } /* GET request handling */ /* Unified processing of GET requests uses two data structures: request info * and reply data. Request info holds information parsed from client request * and its stays constant through all request processing. Reply data holds data * retrieved from ethtool_ops callbacks or other internal sources which is used * to compose the reply. When processing a dump request, request info is filled * only once (when the request message is parsed) but reply data is filled for * each reply message. * * Both structures consist of part common for all request types (struct * ethnl_req_info and struct ethnl_reply_data defined below) and optional * parts specific for each request type. Common part always starts at offset 0. */ /** * struct ethnl_req_info - base type of request information for GET requests * @dev: network device the request is for (may be null) * @flags: request flags common for all request types * * This is a common base for request specific structures holding data from * parsed userspace request. These always embed struct ethnl_req_info at * zero offset. */ struct ethnl_req_info { struct net_device *dev; u32 flags; }; /** * struct ethnl_reply_data - base type of reply data for GET requests * @dev: device for current reply message; in single shot requests it is * equal to &ethnl_req_info.dev; in dumps it's different for each * reply message * * This is a common base for request specific structures holding data for * kernel reply message. These always embed struct ethnl_reply_data at zero * offset. */ struct ethnl_reply_data { struct net_device *dev; }; static inline int ethnl_ops_begin(struct net_device *dev) { if (dev && dev->reg_state == NETREG_UNREGISTERING) return -ENODEV; if (dev && dev->ethtool_ops->begin) return dev->ethtool_ops->begin(dev); else return 0; } static inline void ethnl_ops_complete(struct net_device *dev) { if (dev && dev->ethtool_ops->complete) dev->ethtool_ops->complete(dev); } /** * struct ethnl_request_ops - unified handling of GET requests * @request_cmd: command id for request (GET) * @reply_cmd: command id for reply (GET_REPLY) * @hdr_attr: attribute type for request header * @req_info_size: size of request info * @reply_data_size: size of reply data * @allow_nodev_do: allow non-dump request with no device identification * @parse_request: * Parse request except common header (struct ethnl_req_info). Common * header is already filled on entry, the rest up to @repdata_offset * is zero initialized. This callback should only modify type specific * request info by parsed attributes from request message. * @prepare_data: * Retrieve and prepare data needed to compose a reply message. Calls to * ethtool_ops handlers are limited to this callback. Common reply data * (struct ethnl_reply_data) is filled on entry, type specific part after * it is zero initialized. This callback should only modify the type * specific part of reply data. Device identification from struct * ethnl_reply_data is to be used as for dump requests, it iterates * through network devices while dev member of struct ethnl_req_info * points to the device from client request. * @reply_size: * Estimate reply message size. Returned value must be sufficient for * message payload without common reply header. The callback may returned * estimate higher than actual message size if exact calculation would * not be worth the saved memory space. * @fill_reply: * Fill reply message payload (except for common header) from reply data. * The callback must not generate more payload than previously called * ->reply_size() estimated. * @cleanup_data: * Optional cleanup called when reply data is no longer needed. Can be * used e.g. to free any additional data structures outside the main * structure which were allocated by ->prepare_data(). When processing * dump requests, ->cleanup() is called for each message. * * Description of variable parts of GET request handling when using the * unified infrastructure. When used, a pointer to an instance of this * structure is to be added to &ethnl_default_requests array and generic * handlers ethnl_default_doit(), ethnl_default_dumpit(), * ethnl_default_start() and ethnl_default_done() used in @ethtool_genl_ops; * ethnl_default_notify() can be used in @ethnl_notify_handlers to send * notifications of the corresponding type. */ struct ethnl_request_ops { u8 request_cmd; u8 reply_cmd; u16 hdr_attr; unsigned int req_info_size; unsigned int reply_data_size; bool allow_nodev_do; int (*parse_request)(struct ethnl_req_info *req_info, struct nlattr **tb, struct netlink_ext_ack *extack); int (*prepare_data)(const struct ethnl_req_info *req_info, struct ethnl_reply_data *reply_data, struct genl_info *info); int (*reply_size)(const struct ethnl_req_info *req_info, const struct ethnl_reply_data *reply_data); int (*fill_reply)(struct sk_buff *skb, const struct ethnl_req_info *req_info, const struct ethnl_reply_data *reply_data); void (*cleanup_data)(struct ethnl_reply_data *reply_data); }; /* request handlers */ extern const struct ethnl_request_ops ethnl_strset_request_ops; extern const struct ethnl_request_ops ethnl_linkinfo_request_ops; extern const struct ethnl_request_ops ethnl_linkmodes_request_ops; extern const struct ethnl_request_ops ethnl_linkstate_request_ops; extern const struct ethnl_request_ops ethnl_debug_request_ops; extern const struct ethnl_request_ops ethnl_wol_request_ops; extern const struct ethnl_request_ops ethnl_features_request_ops; extern const struct ethnl_request_ops ethnl_privflags_request_ops; extern const struct ethnl_request_ops ethnl_rings_request_ops; extern const struct ethnl_request_ops ethnl_channels_request_ops; extern const struct ethnl_request_ops ethnl_coalesce_request_ops; extern const struct ethnl_request_ops ethnl_pause_request_ops; extern const struct ethnl_request_ops ethnl_eee_request_ops; extern const struct ethnl_request_ops ethnl_tsinfo_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_strset_get_policy[ETHTOOL_A_STRSET_COUNTS_ONLY + 1]; extern const struct nla_policy ethnl_linkinfo_get_policy[ETHTOOL_A_LINKINFO_HEADER + 1]; extern const struct nla_policy ethnl_linkinfo_set_policy[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL + 1]; extern const struct nla_policy ethnl_linkmodes_get_policy[ETHTOOL_A_LINKMODES_HEADER + 1]; extern const struct nla_policy ethnl_linkmodes_set_policy[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG + 1]; extern const struct nla_policy ethnl_linkstate_get_policy[ETHTOOL_A_LINKSTATE_HEADER + 1]; extern const struct nla_policy ethnl_debug_get_policy[ETHTOOL_A_DEBUG_HEADER + 1]; extern const struct nla_policy ethnl_debug_set_policy[ETHTOOL_A_DEBUG_MSGMASK + 1]; extern const struct nla_policy ethnl_wol_get_policy[ETHTOOL_A_WOL_HEADER + 1]; extern const struct nla_policy ethnl_wol_set_policy[ETHTOOL_A_WOL_SOPASS + 1]; extern const struct nla_policy ethnl_features_get_policy[ETHTOOL_A_FEATURES_HEADER + 1]; extern const struct nla_policy ethnl_features_set_policy[ETHTOOL_A_FEATURES_WANTED + 1]; extern const struct nla_policy ethnl_privflags_get_policy[ETHTOOL_A_PRIVFLAGS_HEADER + 1]; extern const struct nla_policy ethnl_privflags_set_policy[ETHTOOL_A_PRIVFLAGS_FLAGS + 1]; extern const struct nla_policy ethnl_rings_get_policy[ETHTOOL_A_RINGS_HEADER + 1]; extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_TX + 1]; extern const struct nla_policy ethnl_channels_get_policy[ETHTOOL_A_CHANNELS_HEADER + 1]; extern const struct nla_policy ethnl_channels_set_policy[ETHTOOL_A_CHANNELS_COMBINED_COUNT + 1]; extern const struct nla_policy ethnl_coalesce_get_policy[ETHTOOL_A_COALESCE_HEADER + 1]; extern const struct nla_policy ethnl_coalesce_set_policy[ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL + 1]; extern const struct nla_policy ethnl_pause_get_policy[ETHTOOL_A_PAUSE_HEADER + 1]; extern const struct nla_policy ethnl_pause_set_policy[ETHTOOL_A_PAUSE_TX + 1]; extern const struct nla_policy ethnl_eee_get_policy[ETHTOOL_A_EEE_HEADER + 1]; extern const struct nla_policy ethnl_eee_set_policy[ETHTOOL_A_EEE_TX_LPI_TIMER + 1]; extern const struct nla_policy ethnl_tsinfo_get_policy[ETHTOOL_A_TSINFO_HEADER + 1]; extern const struct nla_policy ethnl_cable_test_act_policy[ETHTOOL_A_CABLE_TEST_HEADER + 1]; extern const struct nla_policy ethnl_cable_test_tdr_act_policy[ETHTOOL_A_CABLE_TEST_TDR_CFG + 1]; extern const struct nla_policy ethnl_tunnel_info_get_policy[ETHTOOL_A_TUNNEL_INFO_HEADER + 1]; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info); int ethnl_set_debug(struct sk_buff *skb, struct genl_info *info); int ethnl_set_wol(struct sk_buff *skb, struct genl_info *info); int ethnl_set_features(struct sk_buff *skb, struct genl_info *info); int ethnl_set_privflags(struct sk_buff *skb, struct genl_info *info); int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info); int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info); int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info); int ethnl_set_pause(struct sk_buff *skb, struct genl_info *info); int ethnl_set_eee(struct sk_buff *skb, struct genl_info *info); int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info); int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info); int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info); int ethnl_tunnel_info_start(struct netlink_callback *cb); int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb); #endif /* _NET_ETHTOOL_NETLINK_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _SCSI_DISK_H #define _SCSI_DISK_H /* * More than enough for everybody ;) The huge number of majors * is a leftover from 16bit dev_t days, we don't really need that * much numberspace. */ #define SD_MAJORS 16 /* * Time out in seconds for disks and Magneto-opticals (which are slower). */ #define SD_TIMEOUT (30 * HZ) #define SD_MOD_TIMEOUT (75 * HZ) /* * Flush timeout is a multiplier over the standard device timeout which is * user modifiable via sysfs but initially set to SD_TIMEOUT */ #define SD_FLUSH_TIMEOUT_MULTIPLIER 2 #define SD_WRITE_SAME_TIMEOUT (120 * HZ) /* * Number of allowed retries */ #define SD_MAX_RETRIES 5 #define SD_PASSTHROUGH_RETRIES 1 #define SD_MAX_MEDIUM_TIMEOUTS 2 /* * Size of the initial data buffer for mode and read capacity data */ #define SD_BUF_SIZE 512 /* * Number of sectors at the end of the device to avoid multi-sector * accesses to in the case of last_sector_bug */ #define SD_LAST_BUGGY_SECTORS 8 enum { SD_EXT_CDB_SIZE = 32, /* Extended CDB size */ SD_MEMPOOL_SIZE = 2, /* CDB pool size */ }; enum { SD_DEF_XFER_BLOCKS = 0xffff, SD_MAX_XFER_BLOCKS = 0xffffffff, SD_MAX_WS10_BLOCKS = 0xffff, SD_MAX_WS16_BLOCKS = 0x7fffff, }; enum { SD_LBP_FULL = 0, /* Full logical block provisioning */ SD_LBP_UNMAP, /* Use UNMAP command */ SD_LBP_WS16, /* Use WRITE SAME(16) with UNMAP bit */ SD_LBP_WS10, /* Use WRITE SAME(10) with UNMAP bit */ SD_LBP_ZERO, /* Use WRITE SAME(10) with zero payload */ SD_LBP_DISABLE, /* Discard disabled due to failed cmd */ }; enum { SD_ZERO_WRITE = 0, /* Use WRITE(10/16) command */ SD_ZERO_WS, /* Use WRITE SAME(10/16) command */ SD_ZERO_WS16_UNMAP, /* Use WRITE SAME(16) with UNMAP */ SD_ZERO_WS10_UNMAP, /* Use WRITE SAME(10) with UNMAP */ }; struct scsi_disk { struct scsi_driver *driver; /* always &sd_template */ struct scsi_device *device; struct device dev; struct gendisk *disk; struct opal_dev *opal_dev; #ifdef CONFIG_BLK_DEV_ZONED u32 nr_zones; u32 rev_nr_zones; u32 zone_blocks; u32 rev_zone_blocks; u32 zones_optimal_open; u32 zones_optimal_nonseq; u32 zones_max_open; u32 *zones_wp_offset; spinlock_t zones_wp_offset_lock; u32 *rev_wp_offset; struct mutex rev_mutex; struct work_struct zone_wp_offset_work; char *zone_wp_update_buf; #endif atomic_t openers; sector_t capacity; /* size in logical blocks */ int max_retries; u32 max_xfer_blocks; u32 opt_xfer_blocks; u32 max_ws_blocks; u32 max_unmap_blocks; u32 unmap_granularity; u32 unmap_alignment; u32 index; unsigned int physical_block_size; unsigned int max_medium_access_timeouts; unsigned int medium_access_timed_out; u8 media_present; u8 write_prot; u8 protection_type;/* Data Integrity Field */ u8 provisioning_mode; u8 zeroing_mode; unsigned ATO : 1; /* state of disk ATO bit */ unsigned cache_override : 1; /* temp override of WCE,RCD */ unsigned WCE : 1; /* state of disk WCE bit */ unsigned RCD : 1; /* state of disk RCD bit, unused */ unsigned DPOFUA : 1; /* state of disk DPOFUA bit */ unsigned first_scan : 1; unsigned lbpme : 1; unsigned lbprz : 1; unsigned lbpu : 1; unsigned lbpws : 1; unsigned lbpws10 : 1; unsigned lbpvpd : 1; unsigned ws10 : 1; unsigned ws16 : 1; unsigned rc_basis: 2; unsigned zoned: 2; unsigned urswrz : 1; unsigned security : 1; unsigned ignore_medium_access_errors : 1; }; #define to_scsi_disk(obj) container_of(obj,struct scsi_disk,dev) static inline struct scsi_disk *scsi_disk(struct gendisk *disk) { return container_of(disk->private_data, struct scsi_disk, driver); } #define sd_printk(prefix, sdsk, fmt, a...) \ (sdsk)->disk ? \ sdev_prefix_printk(prefix, (sdsk)->device, \ (sdsk)->disk->disk_name, fmt, ##a) : \ sdev_printk(prefix, (sdsk)->device, fmt, ##a) #define sd_first_printk(prefix, sdsk, fmt, a...) \ do { \ if ((sdsk)->first_scan) \ sd_printk(prefix, sdsk, fmt, ##a); \ } while (0) static inline int scsi_medium_access_command(struct scsi_cmnd *scmd) { switch (scmd->cmnd[0]) { case READ_6: case READ_10: case READ_12: case READ_16: case SYNCHRONIZE_CACHE: case VERIFY: case VERIFY_12: case VERIFY_16: case WRITE_6: case WRITE_10: case WRITE_12: case WRITE_16: case WRITE_SAME: case WRITE_SAME_16: case UNMAP: return 1; case VARIABLE_LENGTH_CMD: switch (scmd->cmnd[9]) { case READ_32: case VERIFY_32: case WRITE_32: case WRITE_SAME_32: return 1; } } return 0; } static inline sector_t logical_to_sectors(struct scsi_device *sdev, sector_t blocks) { return blocks << (ilog2(sdev->sector_size) - 9); } static inline unsigned int logical_to_bytes(struct scsi_device *sdev, sector_t blocks) { return blocks * sdev->sector_size; } static inline sector_t bytes_to_logical(struct scsi_device *sdev, unsigned int bytes) { return bytes >> ilog2(sdev->sector_size); } static inline sector_t sectors_to_logical(struct scsi_device *sdev, sector_t sector) { return sector >> (ilog2(sdev->sector_size) - 9); } #ifdef CONFIG_BLK_DEV_INTEGRITY extern void sd_dif_config_host(struct scsi_disk *); #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline void sd_dif_config_host(struct scsi_disk *disk) { } #endif /* CONFIG_BLK_DEV_INTEGRITY */ static inline int sd_is_zoned(struct scsi_disk *sdkp) { return sdkp->zoned == 1 || sdkp->device->type == TYPE_ZBC; } #ifdef CONFIG_BLK_DEV_ZONED void sd_zbc_release_disk(struct scsi_disk *sdkp); int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer); int sd_zbc_revalidate_zones(struct scsi_disk *sdkp); blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, unsigned char op, bool all); unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr); int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba, unsigned int nr_blocks); #else /* CONFIG_BLK_DEV_ZONED */ static inline void sd_zbc_release_disk(struct scsi_disk *sdkp) {} static inline int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf) { return 0; } static inline int sd_zbc_revalidate_zones(struct scsi_disk *sdkp) { return 0; } static inline blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, unsigned char op, bool all) { return BLK_STS_TARGET; } static inline unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr) { return good_bytes; } static inline blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba, unsigned int nr_blocks) { return BLK_STS_TARGET; } #define sd_zbc_report_zones NULL #endif /* CONFIG_BLK_DEV_ZONED */ void sd_print_sense_hdr(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr); void sd_print_result(const struct scsi_disk *sdkp, const char *msg, int result); #endif /* _SCSI_DISK_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * SR-IPv6 implementation * * Author: * David Lebrun <david.lebrun@uclouvain.be> */ #ifndef _NET_SEG6_H #define _NET_SEG6_H #include <linux/net.h> #include <linux/ipv6.h> #include <linux/seg6.h> #include <linux/rhashtable-types.h> static inline void update_csum_diff4(struct sk_buff *skb, __be32 from, __be32 to) { __be32 diff[] = { ~from, to }; skb->csum = ~csum_partial((char *)diff, sizeof(diff), ~skb->csum); } static inline void update_csum_diff16(struct sk_buff *skb, __be32 *from, __be32 *to) { __be32 diff[] = { ~from[0], ~from[1], ~from[2], ~from[3], to[0], to[1], to[2], to[3], }; skb->csum = ~csum_partial((char *)diff, sizeof(diff), ~skb->csum); } struct seg6_pernet_data { struct mutex lock; struct in6_addr __rcu *tun_src; #ifdef CONFIG_IPV6_SEG6_HMAC struct rhashtable hmac_infos; #endif }; static inline struct seg6_pernet_data *seg6_pernet(struct net *net) { #if IS_ENABLED(CONFIG_IPV6) return net->ipv6.seg6_data; #else return NULL; #endif } extern int seg6_init(void); extern void seg6_exit(void); extern int seg6_iptunnel_init(void); extern void seg6_iptunnel_exit(void); extern int seg6_local_init(void); extern void seg6_local_exit(void); extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced); extern int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto); extern int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh); extern int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, u32 tbl_id); #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 /* SPDX-License-Identifier: GPL-2.0 */ /* * Variant of atomic_t specialized for reference counts. * * The interface matches the atomic_t interface (to aid in porting) but only * provides the few functions one should use for reference counting. * * Saturation semantics * ==================== * * refcount_t differs from atomic_t in that the counter saturates at * REFCOUNT_SATURATED and will not move once there. This avoids wrapping the * counter and causing 'spurious' use-after-free issues. In order to avoid the * cost associated with introducing cmpxchg() loops into all of the saturating * operations, we temporarily allow the counter to take on an unchecked value * and then explicitly set it to REFCOUNT_SATURATED on detecting that underflow * or overflow has occurred. Although this is racy when multiple threads * access the refcount concurrently, by placing REFCOUNT_SATURATED roughly * equidistant from 0 and INT_MAX we minimise the scope for error: * * INT_MAX REFCOUNT_SATURATED UINT_MAX * 0 (0x7fff_ffff) (0xc000_0000) (0xffff_ffff) * +--------------------------------+----------------+----------------+ * <---------- bad value! ----------> * * (in a signed view of the world, the "bad value" range corresponds to * a negative counter value). * * As an example, consider a refcount_inc() operation that causes the counter * to overflow: * * int old = atomic_fetch_add_relaxed(r); * // old is INT_MAX, refcount now INT_MIN (0x8000_0000) * if (old < 0) * atomic_set(r, REFCOUNT_SATURATED); * * If another thread also performs a refcount_inc() operation between the two * atomic operations, then the count will continue to edge closer to 0. If it * reaches a value of 1 before /any/ of the threads reset it to the saturated * value, then a concurrent refcount_dec_and_test() may erroneously free the * underlying object. * Linux limits the maximum number of tasks to PID_MAX_LIMIT, which is currently * 0x400000 (and can't easily be raised in the future beyond FUTEX_TID_MASK). * With the current PID limit, if no batched refcounting operations are used and * the attacker can't repeatedly trigger kernel oopses in the middle of refcount * operations, this makes it impossible for a saturated refcount to leave the * saturation range, even if it is possible for multiple uses of the same * refcount to nest in the context of a single task: * * (UINT_MAX+1-REFCOUNT_SATURATED) / PID_MAX_LIMIT = * 0x40000000 / 0x400000 = 0x100 = 256 * * If hundreds of references are added/removed with a single refcounting * operation, it may potentially be possible to leave the saturation range; but * given the precise timing details involved with the round-robin scheduling of * each thread manipulating the refcount and the need to hit the race multiple * times in succession, there doesn't appear to be a practical avenue of attack * even if using refcount_add() operations with larger increments. * * Memory ordering * =============== * * Memory ordering rules are slightly relaxed wrt regular atomic_t functions * and provide only what is strictly required for refcounts. * * The increments are fully relaxed; these will not provide ordering. The * rationale is that whatever is used to obtain the object we're increasing the * reference count on will provide the ordering. For locked data structures, * its the lock acquire, for RCU/lockless data structures its the dependent * load. * * Do note that inc_not_zero() provides a control dependency which will order * future stores against the inc, this ensures we'll never modify the object * if we did not in fact acquire a reference. * * The decrements will provide release order, such that all the prior loads and * stores will be issued before, it also provides a control dependency, which * will order us against the subsequent free(). * * The control dependency is against the load of the cmpxchg (ll/sc) that * succeeded. This means the stores aren't fully ordered, but this is fine * because the 1->0 transition indicates no concurrency. * * Note that the allocator is responsible for ordering things between free() * and alloc(). * * The decrements dec_and_test() and sub_and_test() also provide acquire * ordering on success. * */ #ifndef _LINUX_REFCOUNT_H #define _LINUX_REFCOUNT_H #include <linux/atomic.h> #include <linux/bug.h> #include <linux/compiler.h> #include <linux/limits.h> #include <linux/spinlock_types.h> struct mutex; /** * struct refcount_t - variant of atomic_t specialized for reference counts * @refs: atomic_t counter field * * The counter saturates at REFCOUNT_SATURATED and will not move once * there. This avoids wrapping the counter and causing 'spurious' * use-after-free bugs. */ typedef struct refcount_struct { atomic_t refs; } refcount_t; #define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } #define REFCOUNT_MAX INT_MAX #define REFCOUNT_SATURATED (INT_MIN / 2) enum refcount_saturation_type { REFCOUNT_ADD_NOT_ZERO_OVF, REFCOUNT_ADD_OVF, REFCOUNT_ADD_UAF, REFCOUNT_SUB_UAF, REFCOUNT_DEC_LEAK, }; void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t); /** * refcount_set - set a refcount's value * @r: the refcount * @n: value to which the refcount will be set */ static inline void refcount_set(refcount_t *r, int n) { atomic_set(&r->refs, n); } /** * refcount_read - get a refcount's value * @r: the refcount * * Return: the refcount's value */ static inline unsigned int refcount_read(const refcount_t *r) { return atomic_read(&r->refs); } static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp) { int old = refcount_read(r); do { if (!old) break; } while (!atomic_try_cmpxchg_relaxed(&r->refs, &old, old + i)); if (oldp) *oldp = old; if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF); return old; } /** * refcount_add_not_zero - add a value to a refcount unless it is 0 * @i: the value to add to the refcount * @r: the refcount * * Will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. * * Return: false if the passed refcount is 0, true otherwise */ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) { return __refcount_add_not_zero(i, r, NULL); } static inline void __refcount_add(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_add_relaxed(i, &r->refs); if (oldp) *oldp = old; if (unlikely(!old)) refcount_warn_saturate(r, REFCOUNT_ADD_UAF); else if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_OVF); } /** * refcount_add - add a value to a refcount * @i: the value to add to the refcount * @r: the refcount * * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. */ static inline void refcount_add(int i, refcount_t *r) { __refcount_add(i, r, NULL); } static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp) { return __refcount_add_not_zero(1, r, oldp); } /** * refcount_inc_not_zero - increment a refcount unless it is 0 * @r: the refcount to increment * * Similar to atomic_inc_not_zero(), but will saturate at REFCOUNT_SATURATED * and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Return: true if the increment was successful, false otherwise */ static inline __must_check bool refcount_inc_not_zero(refcount_t *r) { return __refcount_inc_not_zero(r, NULL); } static inline void __refcount_inc(refcount_t *r, int *oldp) { __refcount_add(1, r, oldp); } /** * refcount_inc - increment a refcount * @r: the refcount to increment * * Similar to atomic_inc(), but will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller already has a * reference on the object. * * Will WARN if the refcount is 0, as this represents a possible use-after-free * condition. */ static inline void refcount_inc(refcount_t *r) { __refcount_inc(r, NULL); } static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(i, &r->refs); if (oldp) *oldp = old; if (old == i) { smp_acquire__after_ctrl_dep(); return true; } if (unlikely(old < 0 || old - i < 0)) refcount_warn_saturate(r, REFCOUNT_SUB_UAF); return false; } /** * refcount_sub_and_test - subtract from a refcount and test if it is 0 * @i: amount to subtract from the refcount * @r: the refcount * * Similar to atomic_dec_and_test(), but it will WARN, return false and * ultimately leak on underflow and will fail to decrement when saturated * at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_dec(), or one of its variants, should instead be used to * decrement a reference count. * * Return: true if the resulting refcount is 0, false otherwise */ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) { return __refcount_sub_and_test(i, r, NULL); } static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp) { return __refcount_sub_and_test(1, r, oldp); } /** * refcount_dec_and_test - decrement a refcount and test if it is 0 * @r: the refcount * * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to * decrement when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Return: true if the resulting refcount is 0, false otherwise */ static inline __must_check bool refcount_dec_and_test(refcount_t *r) { return __refcount_dec_and_test(r, NULL); } static inline void __refcount_dec(refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(1, &r->refs); if (oldp) *oldp = old; if (unlikely(old <= 1)) refcount_warn_saturate(r, REFCOUNT_DEC_LEAK); } /** * refcount_dec - decrement a refcount * @r: the refcount * * Similar to atomic_dec(), it will WARN on underflow and fail to decrement * when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before. */ static inline void refcount_dec(refcount_t *r) { __refcount_dec(r, NULL); } extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock); extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock); extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r, spinlock_t *lock, unsigned long *flags); #endif /* _LINUX_REFCOUNT_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 /* SPDX-License-Identifier: GPL-2.0 */ /* * Filesystem access notification for Linux * * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ #ifndef __LINUX_FSNOTIFY_BACKEND_H #define __LINUX_FSNOTIFY_BACKEND_H #ifdef __KERNEL__ #include <linux/idr.h> /* inotify uses this */ #include <linux/fs.h> /* struct inode */ #include <linux/list.h> #include <linux/path.h> /* struct path */ #include <linux/spinlock.h> #include <linux/types.h> #include <linux/atomic.h> #include <linux/user_namespace.h> #include <linux/refcount.h> /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily * convert between them. dnotify only needs conversion at watch creation * so no perf loss there. fanotify isn't defined yet, so it can use the * wholes if it needs more events. */ #define FS_ACCESS 0x00000001 /* File was accessed */ #define FS_MODIFY 0x00000002 /* File was modified */ #define FS_ATTRIB 0x00000004 /* Metadata changed */ #define FS_CLOSE_WRITE 0x00000008 /* Writtable file was closed */ #define FS_CLOSE_NOWRITE 0x00000010 /* Unwrittable file closed */ #define FS_OPEN 0x00000020 /* File was opened */ #define FS_MOVED_FROM 0x00000040 /* File was moved from X */ #define FS_MOVED_TO 0x00000080 /* File was moved to Y */ #define FS_CREATE 0x00000100 /* Subfile was created */ #define FS_DELETE 0x00000200 /* Subfile was deleted */ #define FS_DELETE_SELF 0x00000400 /* Self was deleted */ #define FS_MOVE_SELF 0x00000800 /* Self was moved */ #define FS_OPEN_EXEC 0x00001000 /* File was opened for exec */ #define FS_UNMOUNT 0x00002000 /* inode on umount fs */ #define FS_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ #define FS_IN_IGNORED 0x00008000 /* last inotify event here */ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ #define FS_EXCL_UNLINK 0x04000000 /* do not send events if object is unlinked */ /* * Set on inode mark that cares about things that happen to its children. * Always set for dnotify and inotify. * Set on inode/sb/mount marks that care about parent/name info. */ #define FS_EVENT_ON_CHILD 0x08000000 #define FS_DN_RENAME 0x10000000 /* file renamed */ #define FS_DN_MULTISHOT 0x20000000 /* dnotify multishot */ #define FS_ISDIR 0x40000000 /* event occurred against dir */ #define FS_IN_ONESHOT 0x80000000 /* only send event once */ #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) /* * Directory entry modification events - reported only to directory * where entry is modified and not to a watching parent. * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event * when a directory entry inside a child subdir changes. */ #define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE) #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \ FS_OPEN_EXEC_PERM) /* * This is a list of all events that may get sent to a parent that is watching * with flag FS_EVENT_ON_CHILD based on fs event on a child of that directory. */ #define FS_EVENTS_POSS_ON_CHILD (ALL_FSNOTIFY_PERM_EVENTS | \ FS_ACCESS | FS_MODIFY | FS_ATTRIB | \ FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | \ FS_OPEN | FS_OPEN_EXEC) /* * This is a list of all events that may get sent with the parent inode as the * @to_tell argument of fsnotify(). * It may include events that can be sent to an inode/sb/mount mark, but cannot * be sent to a parent watching children. */ #define FS_EVENTS_POSS_TO_PARENT (FS_EVENTS_POSS_ON_CHILD) /* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ FS_DELETE_SELF | FS_MOVE_SELF | FS_DN_RENAME | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED) /* Extra flags that may be reported with event or control handling of events */ #define ALL_FSNOTIFY_FLAGS (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \ FS_DN_MULTISHOT | FS_EVENT_ON_CHILD) #define ALL_FSNOTIFY_BITS (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS) struct fsnotify_group; struct fsnotify_event; struct fsnotify_mark; struct fsnotify_event_private_data; struct fsnotify_fname; struct fsnotify_iter_info; struct mem_cgroup; /* * Each group much define these ops. The fsnotify infrastructure will call * these operations for each relevant group. * * handle_event - main call for a group to handle an fs event * @group: group to notify * @mask: event type and flags * @data: object that event happened on * @data_type: type of object for fanotify_data_XXX() accessors * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to * @file_name: optional file name associated with event * @cookie: inotify rename cookie * @iter_info: array of marks from this group that are interested in the event * * handle_inode_event - simple variant of handle_event() for groups that only * have inode marks and don't have ignore mask * @mark: mark to notify * @mask: event type and flags * @inode: inode that event happened on * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to. * @file_name: optional file name associated with event * @cookie: inotify rename cookie * * free_group_priv - called when a group refcnt hits 0 to clean up the private union * freeing_mark - called when a mark is being destroyed for some reason. The group * MUST be holding a reference on each mark and that reference must be * dropped in this function. inotify uses this function to send * userspace messages that marks have been removed. */ struct fsnotify_ops { int (*handle_event)(struct fsnotify_group *group, u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info); int (*handle_inode_event)(struct fsnotify_mark *mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *file_name, u32 cookie); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); void (*free_event)(struct fsnotify_event *event); /* called on final put+free to free memory */ void (*free_mark)(struct fsnotify_mark *mark); }; /* * all of the information about the original object we want to now send to * a group. If you want to carry more info from the accessing task to the * listener this structure is where you need to be adding fields. */ struct fsnotify_event { struct list_head list; unsigned long objectid; /* identifier for queue merges */ }; /* * A group is a "thing" that wants to receive notification about filesystem * events. The mask holds the subset of event types this group cares about. * refcnt on a group is up to the implementor and at any moment if it goes 0 * everything will be cleaned up. */ struct fsnotify_group { const struct fsnotify_ops *ops; /* how this group handles things */ /* * How the refcnt is used is up to each group. When the refcnt hits 0 * fsnotify will clean up all of the resources associated with this group. * As an example, the dnotify group will always have a refcnt=1 and that * will never change. Inotify, on the other hand, has a group per * inotify_init() and the refcnt will hit 0 only when that fd has been * closed. */ refcount_t refcnt; /* things with interest in this group */ /* needed to send notification to userspace */ spinlock_t notification_lock; /* protect the notification_list */ struct list_head notification_list; /* list of event_holder this group needs to send to userspace */ wait_queue_head_t notification_waitq; /* read() on the notification file blocks on this waitq */ unsigned int q_len; /* events on the queue */ unsigned int max_events; /* maximum events allowed on the list */ /* * Valid fsnotify group priorities. Events are send in order from highest * priority to lowest priority. We default to the lowest priority. */ #define FS_PRIO_0 0 /* normal notifiers, no permissions */ #define FS_PRIO_1 1 /* fanotify content based access control */ #define FS_PRIO_2 2 /* fanotify pre-content access */ unsigned int priority; bool shutdown; /* group is being shut down, don't queue more events */ /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ atomic_t num_marks; /* 1 for each mark and 1 for not being * past the point of no return when freeing * a group */ atomic_t user_waits; /* Number of tasks waiting for user * response */ struct list_head marks_list; /* all inode marks for this group */ struct fasync_struct *fsn_fa; /* async notification */ struct fsnotify_event *overflow_event; /* Event we queue when the * notification list is too * full */ struct mem_cgroup *memcg; /* memcg to charge allocations */ /* groups can define private fields here or use the void *private */ union { void *private; #ifdef CONFIG_INOTIFY_USER struct inotify_group_private_data { spinlock_t idr_lock; struct idr idr; struct ucounts *ucounts; } inotify_data; #endif #ifdef CONFIG_FANOTIFY struct fanotify_group_private_data { /* allows a group to block waiting for a userspace response */ struct list_head access_list; wait_queue_head_t access_waitq; int flags; /* flags from fanotify_init() */ int f_flags; /* event_f_flags from fanotify_init() */ unsigned int max_marks; struct user_struct *user; } fanotify_data; #endif /* CONFIG_FANOTIFY */ }; }; /* When calling fsnotify tell it if the data is a path or inode */ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, }; static inline struct inode *fsnotify_data_inode(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_INODE: return (struct inode *)data; case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); default: return NULL; } } static inline const struct path *fsnotify_data_path(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_PATH: return data; default: return NULL; } } enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_PARENT, FSNOTIFY_OBJ_TYPE_VFSMOUNT, FSNOTIFY_OBJ_TYPE_SB, FSNOTIFY_OBJ_TYPE_COUNT, FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; #define FSNOTIFY_OBJ_TYPE_INODE_FL (1U << FSNOTIFY_OBJ_TYPE_INODE) #define FSNOTIFY_OBJ_TYPE_PARENT_FL (1U << FSNOTIFY_OBJ_TYPE_PARENT) #define FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL (1U << FSNOTIFY_OBJ_TYPE_VFSMOUNT) #define FSNOTIFY_OBJ_TYPE_SB_FL (1U << FSNOTIFY_OBJ_TYPE_SB) #define FSNOTIFY_OBJ_ALL_TYPES_MASK ((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1) static inline bool fsnotify_valid_obj_type(unsigned int type) { return (type < FSNOTIFY_OBJ_TYPE_COUNT); } struct fsnotify_iter_info { struct fsnotify_mark *marks[FSNOTIFY_OBJ_TYPE_COUNT]; unsigned int report_mask; int srcu_idx; }; static inline bool fsnotify_iter_should_report_type( struct fsnotify_iter_info *iter_info, int type) { return (iter_info->report_mask & (1U << type)); } static inline void fsnotify_iter_set_report_type( struct fsnotify_iter_info *iter_info, int type) { iter_info->report_mask |= (1U << type); } static inline void fsnotify_iter_set_report_type_mark( struct fsnotify_iter_info *iter_info, int type, struct fsnotify_mark *mark) { iter_info->marks[type] = mark; iter_info->report_mask |= (1U << type); } #define FSNOTIFY_ITER_FUNCS(name, NAME) \ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ struct fsnotify_iter_info *iter_info) \ { \ return (iter_info->report_mask & FSNOTIFY_OBJ_TYPE_##NAME##_FL) ? \ iter_info->marks[FSNOTIFY_OBJ_TYPE_##NAME] : NULL; \ } FSNOTIFY_ITER_FUNCS(inode, INODE) FSNOTIFY_ITER_FUNCS(parent, PARENT) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) FSNOTIFY_ITER_FUNCS(sb, SB) #define fsnotify_foreach_obj_type(type) \ for (type = 0; type < FSNOTIFY_OBJ_TYPE_COUNT; type++) /* * fsnotify_connp_t is what we embed in objects which connector can be attached * to. fsnotify_connp_t * is how we refer from connector back to object. */ struct fsnotify_mark_connector; typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t; /* * Inode/vfsmount/sb point to this structure which tracks all marks attached to * the inode/vfsmount/sb. The reference to inode/vfsmount/sb is held by this * structure. We destroy this structure when there are no more marks attached * to it. The structure is protected by fsnotify_mark_srcu. */ struct fsnotify_mark_connector { spinlock_t lock; unsigned short type; /* Type of object [lock] */ #define FSNOTIFY_CONN_FLAG_HAS_FSID 0x01 unsigned short flags; /* flags [lock] */ __kernel_fsid_t fsid; /* fsid of filesystem containing object */ union { /* Object pointer [lock] */ fsnotify_connp_t *obj; /* Used listing heads to free after srcu period expires */ struct fsnotify_mark_connector *destroy_next; }; struct hlist_head list; }; /* * A mark is simply an object attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events * of a type matching mask or only interested in those events. * * These are flushed when an inode is evicted from core and may be flushed * when the inode is modified (as seen by fsnotify_access). Some fsnotify * users (such as dnotify) will flush these when the open fd is closed and not * at inode eviction or modification. * * Text in brackets is showing the lock(s) protecting modifications of a * particular entry. obj_lock means either inode->i_lock or * mnt->mnt_root->d_lock depending on the mark type. */ struct fsnotify_mark { /* Mask this mark is for [mark->lock, group->mark_mutex] */ __u32 mask; /* We hold one for presence in g_list. Also one ref for each 'thing' * in kernel that found and may be using this mark. */ refcount_t refcnt; /* Group this mark is for. Set on mark creation, stable until last ref * is dropped */ struct fsnotify_group *group; /* List of marks by group->marks_list. Also reused for queueing * mark into destroy_list when it's waiting for the end of SRCU period * before it can be freed. [group->mark_mutex] */ struct list_head g_list; /* Protects inode / mnt pointers, flags, masks */ spinlock_t lock; /* List of marks for inode / vfsmount [connector->lock, mark ref] */ struct hlist_node obj_list; /* Head of list of marks for an object [mark ref] */ struct fsnotify_mark_connector *connector; /* Events types to ignore [mark->lock, group->mark_mutex] */ __u32 ignored_mask; #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x01 #define FSNOTIFY_MARK_FLAG_ALIVE 0x02 #define FSNOTIFY_MARK_FLAG_ATTACHED 0x04 unsigned int flags; /* flags [mark->lock] */ }; #ifdef CONFIG_FSNOTIFY /* called from the vfs helpers */ /* main fsnotify call to send events */ extern int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie); extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type); extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); extern void fsnotify_sb_delete(struct super_block *sb); extern u32 fsnotify_get_cookie(void); static inline __u32 fsnotify_parent_needed_mask(__u32 mask) { /* FS_EVENT_ON_CHILD is set on marks that want parent/name info */ if (!(mask & FS_EVENT_ON_CHILD)) return 0; /* * This object might be watched by a mark that cares about parent/name * info, does it care about the specific set of events that can be * reported with parent/name info? */ return mask & FS_EVENTS_POSS_TO_PARENT; } static inline int fsnotify_inode_watches_children(struct inode *inode) { /* FS_EVENT_ON_CHILD is set if the inode may care */ if (!(inode->i_fsnotify_mask & FS_EVENT_ON_CHILD)) return 0; /* this inode might care about child events, does it care about the * specific set of events that can happen on a child? */ return inode->i_fsnotify_mask & FS_EVENTS_POSS_ON_CHILD; } /* * Update the dentry with a flag indicating the interest of its parent to receive * filesystem events when those events happens to this dentry->d_inode. */ static inline void fsnotify_update_flags(struct dentry *dentry) { assert_spin_locked(&dentry->d_lock); /* * Serialisation of setting PARENT_WATCHED on the dentries is provided * by d_lock. If inotify_inode_watched changes after we have taken * d_lock, the following __fsnotify_update_child_dentry_flags call will * find our entry, so it will spin until we complete here, and update * us with the new state. */ if (fsnotify_inode_watches_children(dentry->d_parent->d_inode)) dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; else dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; } /* called from fsnotify listeners, such as fanotify or dnotify */ /* create a new group */ extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops); /* get reference to a group */ extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ extern void fsnotify_put_group(struct fsnotify_group *group); /* group destruction begins, stop queuing new events */ extern void fsnotify_group_stop_queueing(struct fsnotify_group *group); /* destroy group */ extern void fsnotify_destroy_group(struct fsnotify_group *group); /* fasync handler function */ extern int fsnotify_fasync(int fd, struct file *file, int on); /* Free event from memory */ extern void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event); /* attach the event to the group notification queue */ extern int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct list_head *, struct fsnotify_event *)); /* Queue overflow event to a notification group */ static inline void fsnotify_queue_overflow(struct fsnotify_group *group) { fsnotify_add_event(group, group->overflow_event, NULL); } /* true if the group notification queue is empty */ extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ extern struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group); /* return AND dequeue the first event on the notification queue */ extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group); /* Remove event queued in the notification list */ extern void fsnotify_remove_queued_event(struct fsnotify_group *group, struct fsnotify_event *event); /* functions used to manipulate the marks attached to inodes */ /* Get mask of events for a list of marks */ extern __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn); /* Calculate mask of events for a list of marks */ extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn); extern void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* Find mark belonging to given group in the list of marks */ extern struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp, struct fsnotify_group *group); /* Get cached fsid of filesystem containing object */ extern int fsnotify_get_conn_fsid(const struct fsnotify_mark_connector *conn, __kernel_fsid_t *fsid); /* attach the mark to the object */ extern int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int type, int allow_dups, __kernel_fsid_t *fsid); extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int type, int allow_dups, __kernel_fsid_t *fsid); /* attach the mark to the inode */ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct inode *inode, int allow_dups) { return fsnotify_add_mark(mark, &inode->i_fsnotify_marks, FSNOTIFY_OBJ_TYPE_INODE, allow_dups, NULL); } static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, struct inode *inode, int allow_dups) { return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks, FSNOTIFY_OBJ_TYPE_INODE, allow_dups, NULL); } /* given a group and a mark, flag mark to be freed when all references are dropped */ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* detach mark from inode / mount list, group list, drop inode reference */ extern void fsnotify_detach_mark(struct fsnotify_mark *mark); /* free mark */ extern void fsnotify_free_mark(struct fsnotify_mark *mark); /* Wait until all marks queued for destruction are destroyed */ extern void fsnotify_wait_marks_destroyed(void); /* run all the marks in a group, and clear all of the marks attached to given object type */ extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int type); /* run all the marks in a group, and clear all of the vfsmount marks */ static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL); } /* run all the marks in a group, and clear all of the inode marks */ static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE_FL); } /* run all the marks in a group, and clear all of the sn marks */ static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB_FL); } extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info); extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info); static inline void fsnotify_init_event(struct fsnotify_event *event, unsigned long objectid) { INIT_LIST_HEAD(&event->list); event->objectid = objectid; } #else static inline int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie) { return 0; } static inline int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { return 0; } static inline void __fsnotify_inode_delete(struct inode *inode) {} static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) {} static inline void fsnotify_sb_delete(struct super_block *sb) {} static inline void fsnotify_update_flags(struct dentry *dentry) {} static inline u32 fsnotify_get_cookie(void) { return 0; } static inline void fsnotify_unmount_inodes(struct super_block *sb) {} #endif /* CONFIG_FSNOTIFY */ #endif /* __KERNEL __ */ #endif /* __LINUX_FSNOTIFY_BACKEND_H */
1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 #ifdef CONFIG_PREEMPTIRQ_TRACEPOINTS #undef TRACE_SYSTEM #define TRACE_SYSTEM preemptirq #if !defined(_TRACE_PREEMPTIRQ_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PREEMPTIRQ_H #include <linux/ktime.h> #include <linux/tracepoint.h> #include <linux/string.h> #include <asm/sections.h> DECLARE_EVENT_CLASS(preemptirq_template, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip), TP_STRUCT__entry( __field(s32, caller_offs) __field(s32, parent_offs) ), TP_fast_assign( __entry->caller_offs = (s32)(ip - (unsigned long)_stext); __entry->parent_offs = (s32)(parent_ip - (unsigned long)_stext); ), TP_printk("caller=%pS parent=%pS", (void *)((unsigned long)(_stext) + __entry->caller_offs), (void *)((unsigned long)(_stext) + __entry->parent_offs)) ); #ifdef CONFIG_TRACE_IRQFLAGS DEFINE_EVENT(preemptirq_template, irq_disable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); DEFINE_EVENT(preemptirq_template, irq_enable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); #else #define trace_irq_enable(...) #define trace_irq_disable(...) #define trace_irq_enable_rcuidle(...) #define trace_irq_disable_rcuidle(...) #endif #ifdef CONFIG_TRACE_PREEMPT_TOGGLE DEFINE_EVENT(preemptirq_template, preempt_disable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); DEFINE_EVENT(preemptirq_template, preempt_enable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); #else #define trace_preempt_enable(...) #define trace_preempt_disable(...) #define trace_preempt_enable_rcuidle(...) #define trace_preempt_disable_rcuidle(...) #endif #endif /* _TRACE_PREEMPTIRQ_H */ #include <trace/define_trace.h> #else /* !CONFIG_PREEMPTIRQ_TRACEPOINTS */ #define trace_irq_enable(...) #define trace_irq_disable(...) #define trace_irq_enable_rcuidle(...) #define trace_irq_disable_rcuidle(...) #define trace_preempt_enable(...) #define trace_preempt_disable(...) #define trace_preempt_enable_rcuidle(...) #define trace_preempt_disable_rcuidle(...) #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_UDP_TUNNEL_H #define __NET_UDP_TUNNEL_H #include <net/ip_tunnels.h> #include <net/udp.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/ipv6_stubs.h> #endif struct udp_port_cfg { u8 family; /* Used only for kernel-created sockets */ union { struct in_addr local_ip; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr local_ip6; #endif }; union { struct in_addr peer_ip; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr peer_ip6; #endif }; __be16 local_udp_port; __be16 peer_udp_port; int bind_ifindex; unsigned int use_udp_checksums:1, use_udp6_tx_checksums:1, use_udp6_rx_checksums:1, ipv6_v6only:1; }; int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp); #if IS_ENABLED(CONFIG_IPV6) int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp); #else static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { return 0; } #endif static inline int udp_sock_create(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { if (cfg->family == AF_INET) return udp_sock_create4(net, cfg, sockp); if (cfg->family == AF_INET6) return udp_sock_create6(net, cfg, sockp); return -EPFNOSUPPORT; } typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb); typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk, struct sk_buff *skb); typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk); typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk, struct list_head *head, struct sk_buff *skb); typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb, int nhoff); struct udp_tunnel_sock_cfg { void *sk_user_data; /* user data used by encap_rcv call back */ /* Used for setting up udp_sock fields, see udp.h for details */ __u8 encap_type; udp_tunnel_encap_rcv_t encap_rcv; udp_tunnel_encap_err_lookup_t encap_err_lookup; udp_tunnel_encap_destroy_t encap_destroy; udp_tunnel_gro_receive_t gro_receive; udp_tunnel_gro_complete_t gro_complete; }; /* Setup the given (UDP) sock to receive UDP encapsulated packets */ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct udp_tunnel_sock_cfg *sock_cfg); /* -- List of parsable UDP tunnel types -- * * Adding to this list will result in serious debate. The main issue is * that this list is essentially a list of workarounds for either poorly * designed tunnels, or poorly designed device offloads. * * The parsing supported via these types should really be used for Rx * traffic only as the network stack will have already inserted offsets for * the location of the headers in the skb. In addition any ports that are * pushed should be kept within the namespace without leaking to other * devices such as VFs or other ports on the same device. * * It is strongly encouraged to use CHECKSUM_COMPLETE for Rx to avoid the * need to use this for Rx checksum offload. It should not be necessary to * call this function to perform Tx offloads on outgoing traffic. */ enum udp_parsable_tunnel_type { UDP_TUNNEL_TYPE_VXLAN = BIT(0), /* RFC 7348 */ UDP_TUNNEL_TYPE_GENEVE = BIT(1), /* draft-ietf-nvo3-geneve */ UDP_TUNNEL_TYPE_VXLAN_GPE = BIT(2), /* draft-ietf-nvo3-vxlan-gpe */ }; struct udp_tunnel_info { unsigned short type; sa_family_t sa_family; __be16 port; u8 hw_priv; }; /* Notify network devices of offloadable types */ void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock, unsigned short type); void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock, unsigned short type); void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type); void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type); static inline void udp_tunnel_get_rx_info(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev); } static inline void udp_tunnel_drop_rx_info(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_UDP_TUNNEL_DROP_INFO, dev); } /* Transmit the skb using UDP encapsulation. */ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, bool xnet, bool nocheck); int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, __u8 prio, __u8 ttl, __be32 label, __be16 src_port, __be16 dst_port, bool nocheck); void udp_tunnel_sock_release(struct socket *sock); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, __be16 flags, __be64 tunnel_id, int md_size); #ifdef CONFIG_INET static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) { int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; return iptunnel_handle_offloads(skb, type); } #endif static inline void udp_tunnel_encap_enable(struct socket *sock) { struct udp_sock *up = udp_sk(sock->sk); if (up->encap_enabled) return; up->encap_enabled = 1; #if IS_ENABLED(CONFIG_IPV6) if (sock->sk->sk_family == PF_INET6) ipv6_stub->udpv6_encap_enable(); else #endif udp_encap_enable(); } #define UDP_TUNNEL_NIC_MAX_TABLES 4 enum udp_tunnel_nic_info_flags { /* Device callbacks may sleep */ UDP_TUNNEL_NIC_INFO_MAY_SLEEP = BIT(0), /* Device only supports offloads when it's open, all ports * will be removed before close and re-added after open. */ UDP_TUNNEL_NIC_INFO_OPEN_ONLY = BIT(1), /* Device supports only IPv4 tunnels */ UDP_TUNNEL_NIC_INFO_IPV4_ONLY = BIT(2), /* Device has hard-coded the IANA VXLAN port (4789) as VXLAN. * This port must not be counted towards n_entries of any table. * Driver will not receive any callback associated with port 4789. */ UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN = BIT(3), }; struct udp_tunnel_nic; #define UDP_TUNNEL_NIC_MAX_SHARING_DEVICES (U16_MAX / 2) struct udp_tunnel_nic_shared { struct udp_tunnel_nic *udp_tunnel_nic_info; struct list_head devices; }; struct udp_tunnel_nic_shared_node { struct net_device *dev; struct list_head list; }; /** * struct udp_tunnel_nic_info - driver UDP tunnel offload information * @set_port: callback for adding a new port * @unset_port: callback for removing a port * @sync_table: callback for syncing the entire port table at once * @shared: reference to device global state (optional) * @flags: device flags from enum udp_tunnel_nic_info_flags * @tables: UDP port tables this device has * @tables.n_entries: number of entries in this table * @tables.tunnel_types: types of tunnels this table accepts * * Drivers are expected to provide either @set_port and @unset_port callbacks * or the @sync_table callback. Callbacks are invoked with rtnl lock held. * * Devices which (misguidedly) share the UDP tunnel port table across multiple * netdevs should allocate an instance of struct udp_tunnel_nic_shared and * point @shared at it. * There must never be more than %UDP_TUNNEL_NIC_MAX_SHARING_DEVICES devices * sharing a table. * * Known limitations: * - UDP tunnel port notifications are fundamentally best-effort - * it is likely the driver will both see skbs which use a UDP tunnel port, * while not being a tunneled skb, and tunnel skbs from other ports - * drivers should only use these ports for non-critical RX-side offloads, * e.g. the checksum offload; * - none of the devices care about the socket family at present, so we don't * track it. Please extend this code if you care. */ struct udp_tunnel_nic_info { /* one-by-one */ int (*set_port)(struct net_device *dev, unsigned int table, unsigned int entry, struct udp_tunnel_info *ti); int (*unset_port)(struct net_device *dev, unsigned int table, unsigned int entry, struct udp_tunnel_info *ti); /* all at once */ int (*sync_table)(struct net_device *dev, unsigned int table); struct udp_tunnel_nic_shared *shared; unsigned int flags; struct udp_tunnel_nic_table_info { unsigned int n_entries; unsigned int tunnel_types; } tables[UDP_TUNNEL_NIC_MAX_TABLES]; }; /* UDP tunnel module dependencies * * Tunnel drivers are expected to have a hard dependency on the udp_tunnel * module. NIC drivers are not, they just attach their * struct udp_tunnel_nic_info to the netdev and wait for callbacks to come. * Loading a tunnel driver will cause the udp_tunnel module to be loaded * and only then will all the required state structures be allocated. * Since we want a weak dependency from the drivers and the core to udp_tunnel * we call things through the following stubs. */ struct udp_tunnel_nic_ops { void (*get_port)(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti); void (*set_port_priv)(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv); void (*add_port)(struct net_device *dev, struct udp_tunnel_info *ti); void (*del_port)(struct net_device *dev, struct udp_tunnel_info *ti); void (*reset_ntf)(struct net_device *dev); size_t (*dump_size)(struct net_device *dev, unsigned int table); int (*dump_write)(struct net_device *dev, unsigned int table, struct sk_buff *skb); }; #ifdef CONFIG_INET extern const struct udp_tunnel_nic_ops *udp_tunnel_nic_ops; #else #define udp_tunnel_nic_ops ((struct udp_tunnel_nic_ops *)NULL) #endif static inline void udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { /* This helper is used from .sync_table, we indicate empty entries * by zero'ed @ti. Drivers which need to know the details of a port * when it gets deleted should use the .set_port / .unset_port * callbacks. * Zero out here, otherwise !CONFIG_INET causes uninitilized warnings. */ memset(ti, 0, sizeof(*ti)); if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->get_port(dev, table, idx, ti); } static inline void udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->set_port_priv(dev, table, idx, priv); } static inline void udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->add_port(dev, ti); } static inline void udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->del_port(dev, ti); } /** * udp_tunnel_nic_reset_ntf() - device-originating reset notification * @dev: network interface device structure * * Called by the driver to inform the core that the entire UDP tunnel port * state has been lost, usually due to device reset. Core will assume device * forgot all the ports and issue .set_port and .sync_table callbacks as * necessary. * * This function must be called with rtnl lock held, and will issue all * the callbacks before returning. */ static inline void udp_tunnel_nic_reset_ntf(struct net_device *dev) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->reset_ntf(dev); } static inline size_t udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table) { if (!udp_tunnel_nic_ops) return 0; return udp_tunnel_nic_ops->dump_size(dev, table); } static inline int udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, struct sk_buff *skb) { if (!udp_tunnel_nic_ops) return 0; return udp_tunnel_nic_ops->dump_write(dev, table, skb); } #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_DST_METADATA_H #define __NET_DST_METADATA_H 1 #include <linux/skbuff.h> #include <net/ip_tunnels.h> #include <net/dst.h> enum metadata_type { METADATA_IP_TUNNEL, METADATA_HW_PORT_MUX, }; struct hw_port_info { struct net_device *lower_dev; u32 port_id; }; struct metadata_dst { struct dst_entry dst; enum metadata_type type; union { struct ip_tunnel_info tun_info; struct hw_port_info port_info; } u; }; static inline struct metadata_dst *skb_metadata_dst(const struct sk_buff *skb) { struct metadata_dst *md_dst = (struct metadata_dst *) skb_dst(skb); if (md_dst && md_dst->dst.flags & DST_METADATA) return md_dst; return NULL; } static inline struct ip_tunnel_info * skb_tunnel_info(const struct sk_buff *skb) { struct metadata_dst *md_dst = skb_metadata_dst(skb); struct dst_entry *dst; if (md_dst && md_dst->type == METADATA_IP_TUNNEL) return &md_dst->u.tun_info; dst = skb_dst(skb); if (dst && dst->lwtstate && (dst->lwtstate->type == LWTUNNEL_ENCAP_IP || dst->lwtstate->type == LWTUNNEL_ENCAP_IP6)) return lwt_tun_info(dst->lwtstate); return NULL; } static inline bool skb_valid_dst(const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); return dst && !(dst->flags & DST_METADATA); } static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a, const struct sk_buff *skb_b) { const struct metadata_dst *a, *b; if (!(skb_a->_skb_refdst | skb_b->_skb_refdst)) return 0; a = (const struct metadata_dst *) skb_dst(skb_a); b = (const struct metadata_dst *) skb_dst(skb_b); if (!a != !b || a->type != b->type) return 1; switch (a->type) { case METADATA_HW_PORT_MUX: return memcmp(&a->u.port_info, &b->u.port_info, sizeof(a->u.port_info)); case METADATA_IP_TUNNEL: return memcmp(&a->u.tun_info, &b->u.tun_info, sizeof(a->u.tun_info) + a->u.tun_info.options_len); default: return 1; } } void metadata_dst_free(struct metadata_dst *); struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type, gfp_t flags); void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst); struct metadata_dst __percpu * metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags); static inline struct metadata_dst *tun_rx_dst(int md_size) { struct metadata_dst *tun_dst; tun_dst = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC); if (!tun_dst) return NULL; tun_dst->u.tun_info.options_len = 0; tun_dst->u.tun_info.mode = 0; return tun_dst; } static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb) { struct metadata_dst *md_dst = skb_metadata_dst(skb); int md_size; struct metadata_dst *new_md; if (!md_dst || md_dst->type != METADATA_IP_TUNNEL) return ERR_PTR(-EINVAL); md_size = md_dst->u.tun_info.options_len; new_md = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC); if (!new_md) return ERR_PTR(-ENOMEM); memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, sizeof(struct ip_tunnel_info) + md_size); skb_dst_drop(skb); dst_hold(&new_md->dst); skb_dst_set(skb, &new_md->dst); return new_md; } static inline struct ip_tunnel_info *skb_tunnel_info_unclone(struct sk_buff *skb) { struct metadata_dst *dst; dst = tun_dst_unclone(skb); if (IS_ERR(dst)) return NULL; return &dst->u.tun_info; } static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr, __be32 daddr, __u8 tos, __u8 ttl, __be16 tp_dst, __be16 flags, __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; tun_dst = tun_rx_dst(md_size); if (!tun_dst) return NULL; ip_tunnel_key_init(&tun_dst->u.tun_info.key, saddr, daddr, tos, ttl, 0, 0, tp_dst, tunnel_id, flags); return tun_dst; } static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, __be16 flags, __be64 tunnel_id, int md_size) { const struct iphdr *iph = ip_hdr(skb); return __ip_tun_set_dst(iph->saddr, iph->daddr, iph->tos, iph->ttl, 0, flags, tunnel_id, md_size); } static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *saddr, const struct in6_addr *daddr, __u8 tos, __u8 ttl, __be16 tp_dst, __be32 label, __be16 flags, __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; struct ip_tunnel_info *info; tun_dst = tun_rx_dst(md_size); if (!tun_dst) return NULL; info = &tun_dst->u.tun_info; info->mode = IP_TUNNEL_INFO_IPV6; info->key.tun_flags = flags; info->key.tun_id = tunnel_id; info->key.tp_src = 0; info->key.tp_dst = tp_dst; info->key.u.ipv6.src = *saddr; info->key.u.ipv6.dst = *daddr; info->key.tos = tos; info->key.ttl = ttl; info->key.label = label; return tun_dst; } static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb, __be16 flags, __be64 tunnel_id, int md_size) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); return __ipv6_tun_set_dst(&ip6h->saddr, &ip6h->daddr, ipv6_get_dsfield(ip6h), ip6h->hop_limit, 0, ip6_flowlabel(ip6h), flags, tunnel_id, md_size); } #endif /* __NET_DST_METADATA_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 1994 Linus Torvalds * * Pentium III FXSR, SSE support * General FPU state handling cleanups * Gareth Hughes <gareth@valinux.com>, May 2000 */ #include <asm/fpu/internal.h> #include <asm/fpu/regset.h> #include <asm/fpu/signal.h> #include <asm/fpu/types.h> #include <asm/traps.h> #include <asm/irq_regs.h> #include <linux/hardirq.h> #include <linux/pkeys.h> #define CREATE_TRACE_POINTS #include <asm/trace/fpu.h> /* * Represents the initial FPU state. It's mostly (but not completely) zeroes, * depending on the FPU hardware format: */ union fpregs_state init_fpstate __read_mostly; /* * Track whether the kernel is using the FPU state * currently. * * This flag is used: * * - by IRQ context code to potentially use the FPU * if it's unused. * * - to debug kernel_fpu_begin()/end() correctness */ static DEFINE_PER_CPU(bool, in_kernel_fpu); /* * Track which context is using the FPU on the CPU: */ DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); static bool kernel_fpu_disabled(void) { return this_cpu_read(in_kernel_fpu); } static bool interrupted_kernel_fpu_idle(void) { return !kernel_fpu_disabled(); } /* * Were we in user mode (or vm86 mode) when we were * interrupted? * * Doing kernel_fpu_begin/end() is ok if we are running * in an interrupt context from user mode - we'll just * save the FPU state as required. */ static bool interrupted_user_mode(void) { struct pt_regs *regs = get_irq_regs(); return regs && user_mode(regs); } /* * Can we use the FPU in kernel mode with the * whole "kernel_fpu_begin/end()" sequence? * * It's always ok in process context (ie "not interrupt") * but it is sometimes ok even from an irq. */ bool irq_fpu_usable(void) { return !in_interrupt() || interrupted_user_mode() || interrupted_kernel_fpu_idle(); } EXPORT_SYMBOL(irq_fpu_usable); /* * These must be called with preempt disabled. Returns * 'true' if the FPU state is still intact and we can * keep registers active. * * The legacy FNSAVE instruction cleared all FPU state * unconditionally, so registers are essentially destroyed. * Modern FPU state can be kept in registers, if there are * no pending FP exceptions. */ int copy_fpregs_to_fpstate(struct fpu *fpu) { if (likely(use_xsave())) { copy_xregs_to_kernel(&fpu->state.xsave); /* * AVX512 state is tracked here because its use is * known to slow the max clock speed of the core. */ if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512) fpu->avx512_timestamp = jiffies; return 1; } if (likely(use_fxsr())) { copy_fxregs_to_kernel(fpu); return 1; } /* * Legacy FPU register saving, FNSAVE always clears FPU registers, * so we have to mark them inactive: */ asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave)); return 0; } EXPORT_SYMBOL(copy_fpregs_to_fpstate); void kernel_fpu_begin_mask(unsigned int kfpu_mask) { preempt_disable(); WARN_ON_FPU(!irq_fpu_usable()); WARN_ON_FPU(this_cpu_read(in_kernel_fpu)); this_cpu_write(in_kernel_fpu, true); if (!(current->flags & PF_KTHREAD) && !test_thread_flag(TIF_NEED_FPU_LOAD)) { set_thread_flag(TIF_NEED_FPU_LOAD); /* * Ignore return value -- we don't care if reg state * is clobbered. */ copy_fpregs_to_fpstate(&current->thread.fpu); } __cpu_invalidate_fpregs_state(); /* Put sane initial values into the control registers. */ if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM)) ldmxcsr(MXCSR_DEFAULT); if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU)) asm volatile ("fninit"); } EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask); void kernel_fpu_end(void) { WARN_ON_FPU(!this_cpu_read(in_kernel_fpu)); this_cpu_write(in_kernel_fpu, false); preempt_enable(); } EXPORT_SYMBOL_GPL(kernel_fpu_end); /* * Save the FPU state (mark it for reload if necessary): * * This only ever gets called for the current task. */ void fpu__save(struct fpu *fpu) { WARN_ON_FPU(fpu != &current->thread.fpu); fpregs_lock(); trace_x86_fpu_before_save(fpu); if (!test_thread_flag(TIF_NEED_FPU_LOAD)) { if (!copy_fpregs_to_fpstate(fpu)) { copy_kernel_to_fpregs(&fpu->state); } } trace_x86_fpu_after_save(fpu); fpregs_unlock(); } /* * Legacy x87 fpstate state init: */ static inline void fpstate_init_fstate(struct fregs_state *fp) { fp->cwd = 0xffff037fu; fp->swd = 0xffff0000u; fp->twd = 0xffffffffu; fp->fos = 0xffff0000u; } void fpstate_init(union fpregs_state *state) { if (!static_cpu_has(X86_FEATURE_FPU)) { fpstate_init_soft(&state->soft); return; } memset(state, 0, fpu_kernel_xstate_size); if (static_cpu_has(X86_FEATURE_XSAVES)) fpstate_init_xstate(&state->xsave); if (static_cpu_has(X86_FEATURE_FXSR)) fpstate_init_fxstate(&state->fxsave); else fpstate_init_fstate(&state->fsave); } EXPORT_SYMBOL_GPL(fpstate_init); int fpu__copy(struct task_struct *dst, struct task_struct *src) { struct fpu *dst_fpu = &dst->thread.fpu; struct fpu *src_fpu = &src->thread.fpu; dst_fpu->last_cpu = -1; if (!static_cpu_has(X86_FEATURE_FPU)) return 0; WARN_ON_FPU(src_fpu != &current->thread.fpu); /* * Don't let 'init optimized' areas of the XSAVE area * leak into the child task: */ memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size); /* * If the FPU registers are not current just memcpy() the state. * Otherwise save current FPU registers directly into the child's FPU * context, without any memory-to-memory copying. * * ( The function 'fails' in the FNSAVE case, which destroys * register contents so we have to load them back. ) */ fpregs_lock(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) memcpy(&dst_fpu->state, &src_fpu->state, fpu_kernel_xstate_size); else if (!copy_fpregs_to_fpstate(dst_fpu)) copy_kernel_to_fpregs(&dst_fpu->state); fpregs_unlock(); set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD); trace_x86_fpu_copy_src(src_fpu); trace_x86_fpu_copy_dst(dst_fpu); return 0; } /* * Activate the current task's in-memory FPU context, * if it has not been used before: */ static void fpu__initialize(struct fpu *fpu) { WARN_ON_FPU(fpu != &current->thread.fpu); set_thread_flag(TIF_NEED_FPU_LOAD); fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); } /* * This function must be called before we read a task's fpstate. * * There's two cases where this gets called: * * - for the current task (when coredumping), in which case we have * to save the latest FPU registers into the fpstate, * * - or it's called for stopped tasks (ptrace), in which case the * registers were already saved by the context-switch code when * the task scheduled out. * * If the task has used the FPU before then save it. */ void fpu__prepare_read(struct fpu *fpu) { if (fpu == &current->thread.fpu) fpu__save(fpu); } /* * This function must be called before we write a task's fpstate. * * Invalidate any cached FPU registers. * * After this function call, after registers in the fpstate are * modified and the child task has woken up, the child task will * restore the modified FPU state from the modified context. If we * didn't clear its cached status here then the cached in-registers * state pending on its former CPU could be restored, corrupting * the modifications. */ void fpu__prepare_write(struct fpu *fpu) { /* * Only stopped child tasks can be used to modify the FPU * state in the fpstate buffer: */ WARN_ON_FPU(fpu == &current->thread.fpu); /* Invalidate any cached state: */ __fpu_invalidate_fpregs_state(fpu); } /* * Drops current FPU state: deactivates the fpregs and * the fpstate. NOTE: it still leaves previous contents * in the fpregs in the eager-FPU case. * * This function can be used in cases where we know that * a state-restore is coming: either an explicit one, * or a reschedule. */ void fpu__drop(struct fpu *fpu) { preempt_disable(); if (fpu == &current->thread.fpu) { /* Ignore delayed exceptions from user space */ asm volatile("1: fwait\n" "2:\n" _ASM_EXTABLE(1b, 2b)); fpregs_deactivate(fpu); } trace_x86_fpu_dropped(fpu); preempt_enable(); } /* * Clear FPU registers by setting them up from the init fpstate. * Caller must do fpregs_[un]lock() around it. */ static inline void copy_init_fpstate_to_fpregs(u64 features_mask) { if (use_xsave()) copy_kernel_to_xregs(&init_fpstate.xsave, features_mask); else if (static_cpu_has(X86_FEATURE_FXSR)) copy_kernel_to_fxregs(&init_fpstate.fxsave); else copy_kernel_to_fregs(&init_fpstate.fsave); if (boot_cpu_has(X86_FEATURE_OSPKE)) copy_init_pkru_to_fpregs(); } /* * Clear the FPU state back to init state. * * Called by sys_execve(), by the signal handler code and by various * error paths. */ static void fpu__clear(struct fpu *fpu, bool user_only) { WARN_ON_FPU(fpu != &current->thread.fpu); if (!static_cpu_has(X86_FEATURE_FPU)) { fpu__drop(fpu); fpu__initialize(fpu); return; } fpregs_lock(); if (user_only) { if (!fpregs_state_valid(fpu, smp_processor_id()) && xfeatures_mask_supervisor()) copy_kernel_to_xregs(&fpu->state.xsave, xfeatures_mask_supervisor()); copy_init_fpstate_to_fpregs(xfeatures_mask_user()); } else { copy_init_fpstate_to_fpregs(xfeatures_mask_all); } fpregs_mark_activate(); fpregs_unlock(); } void fpu__clear_user_states(struct fpu *fpu) { fpu__clear(fpu, true); } void fpu__clear_all(struct fpu *fpu) { fpu__clear(fpu, false); } /* * Load FPU context before returning to userspace. */ void switch_fpu_return(void) { if (!static_cpu_has(X86_FEATURE_FPU)) return; __fpregs_load_activate(); } EXPORT_SYMBOL_GPL(switch_fpu_return); #ifdef CONFIG_X86_DEBUG_FPU /* * If current FPU state according to its tracking (loaded FPU context on this * CPU) is not valid then we must have TIF_NEED_FPU_LOAD set so the context is * loaded on return to userland. */ void fpregs_assert_state_consistent(void) { struct fpu *fpu = &current->thread.fpu; if (test_thread_flag(TIF_NEED_FPU_LOAD)) return; WARN_ON_FPU(!fpregs_state_valid(fpu, smp_processor_id())); } EXPORT_SYMBOL_GPL(fpregs_assert_state_consistent); #endif void fpregs_mark_activate(void) { struct fpu *fpu = &current->thread.fpu; fpregs_activate(fpu); fpu->last_cpu = smp_processor_id(); clear_thread_flag(TIF_NEED_FPU_LOAD); } EXPORT_SYMBOL_GPL(fpregs_mark_activate); /* * x87 math exception handling: */ int fpu__exception_code(struct fpu *fpu, int trap_nr) { int err; if (trap_nr == X86_TRAP_MF) { unsigned short cwd, swd; /* * (~cwd & swd) will mask out exceptions that are not set to unmasked * status. 0x3f is the exception bits in these regs, 0x200 is the * C1 reg you need in case of a stack fault, 0x040 is the stack * fault bit. We should only be taking one exception at a time, * so if this combination doesn't produce any single exception, * then we have a bad program that isn't synchronizing its FPU usage * and it will suffer the consequences since we won't be able to * fully reproduce the context of the exception. */ if (boot_cpu_has(X86_FEATURE_FXSR)) { cwd = fpu->state.fxsave.cwd; swd = fpu->state.fxsave.swd; } else { cwd = (unsigned short)fpu->state.fsave.cwd; swd = (unsigned short)fpu->state.fsave.swd; } err = swd & ~cwd; } else { /* * The SIMD FPU exceptions are handled a little differently, as there * is only a single status/control register. Thus, to determine which * unmasked exception was caught we must mask the exception mask bits * at 0x1f80, and then use these to mask the exception bits at 0x3f. */ unsigned short mxcsr = MXCSR_DEFAULT; if (boot_cpu_has(X86_FEATURE_XMM)) mxcsr = fpu->state.fxsave.mxcsr; err = ~(mxcsr >> 7) & mxcsr; } if (err & 0x001) { /* Invalid op */ /* * swd & 0x240 == 0x040: Stack Underflow * swd & 0x240 == 0x240: Stack Overflow * User must clear the SF bit (0x40) if set */ return FPE_FLTINV; } else if (err & 0x004) { /* Divide by Zero */ return FPE_FLTDIV; } else if (err & 0x008) { /* Overflow */ return FPE_FLTOVF; } else if (err & 0x012) { /* Denormal, Underflow */ return FPE_FLTUND; } else if (err & 0x020) { /* Precision */ return FPE_FLTRES; } /* * If we're using IRQ 13, or supposedly even some trap * X86_TRAP_MF implementations, it's possible * we get a spurious trap, which is not an error. */ return 0; }
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef IOCONTEXT_H #define IOCONTEXT_H #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> enum { ICQ_EXITED = 1 << 2, ICQ_DESTROYED = 1 << 3, }; /* * An io_cq (icq) is association between an io_context (ioc) and a * request_queue (q). This is used by elevators which need to track * information per ioc - q pair. * * Elevator can request use of icq by setting elevator_type->icq_size and * ->icq_align. Both size and align must be larger than that of struct * io_cq and elevator can use the tail area for private information. The * recommended way to do this is defining a struct which contains io_cq as * the first member followed by private members and using its size and * align. For example, * * struct snail_io_cq { * struct io_cq icq; * int poke_snail; * int feed_snail; * }; * * struct elevator_type snail_elv_type { * .ops = { ... }, * .icq_size = sizeof(struct snail_io_cq), * .icq_align = __alignof__(struct snail_io_cq), * ... * }; * * If icq_size is set, block core will manage icq's. All requests will * have its ->elv.icq field set before elevator_ops->elevator_set_req_fn() * is called and be holding a reference to the associated io_context. * * Whenever a new icq is created, elevator_ops->elevator_init_icq_fn() is * called and, on destruction, ->elevator_exit_icq_fn(). Both functions * are called with both the associated io_context and queue locks held. * * Elevator is allowed to lookup icq using ioc_lookup_icq() while holding * queue lock but the returned icq is valid only until the queue lock is * released. Elevators can not and should not try to create or destroy * icq's. * * As icq's are linked from both ioc and q, the locking rules are a bit * complex. * * - ioc lock nests inside q lock. * * - ioc->icq_list and icq->ioc_node are protected by ioc lock. * q->icq_list and icq->q_node by q lock. * * - ioc->icq_tree and ioc->icq_hint are protected by ioc lock, while icq * itself is protected by q lock. However, both the indexes and icq * itself are also RCU managed and lookup can be performed holding only * the q lock. * * - icq's are not reference counted. They are destroyed when either the * ioc or q goes away. Each request with icq set holds an extra * reference to ioc to ensure it stays until the request is completed. * * - Linking and unlinking icq's are performed while holding both ioc and q * locks. Due to the lock ordering, q exit is simple but ioc exit * requires reverse-order double lock dance. */ struct io_cq { struct request_queue *q; struct io_context *ioc; /* * q_node and ioc_node link io_cq through icq_list of q and ioc * respectively. Both fields are unused once ioc_exit_icq() is * called and shared with __rcu_icq_cache and __rcu_head which are * used for RCU free of io_cq. */ union { struct list_head q_node; struct kmem_cache *__rcu_icq_cache; }; union { struct hlist_node ioc_node; struct rcu_head __rcu_head; }; unsigned int flags; }; /* * I/O subsystem state of the associated processes. It is refcounted * and kmalloc'ed. These could be shared between processes. */ struct io_context { atomic_long_t refcount; atomic_t active_ref; atomic_t nr_tasks; /* all the fields below are protected by this lock */ spinlock_t lock; unsigned short ioprio; struct radix_tree_root icq_tree; struct io_cq __rcu *icq_hint; struct hlist_head icq_list; struct work_struct release_work; }; /** * get_io_context_active - get active reference on ioc * @ioc: ioc of interest * * Only iocs with active reference can issue new IOs. This function * acquires an active reference on @ioc. The caller must already have an * active reference on @ioc. */ static inline void get_io_context_active(struct io_context *ioc) { WARN_ON_ONCE(atomic_long_read(&ioc->refcount) <= 0); WARN_ON_ONCE(atomic_read(&ioc->active_ref) <= 0); atomic_long_inc(&ioc->refcount); atomic_inc(&ioc->active_ref); } static inline void ioc_task_link(struct io_context *ioc) { get_io_context_active(ioc); WARN_ON_ONCE(atomic_read(&ioc->nr_tasks) <= 0); atomic_inc(&ioc->nr_tasks); } struct task_struct; #ifdef CONFIG_BLOCK void put_io_context(struct io_context *ioc); void put_io_context_active(struct io_context *ioc); void exit_io_context(struct task_struct *task); struct io_context *get_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node); #else struct io_context; static inline void put_io_context(struct io_context *ioc) { } static inline void exit_io_context(struct task_struct *task) { } #endif #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMERQUEUE_H #define _LINUX_TIMERQUEUE_H #include <linux/rbtree.h> #include <linux/ktime.h> struct timerqueue_node { struct rb_node node; ktime_t expires; }; struct timerqueue_head { struct rb_root_cached rb_root; }; extern bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node); extern bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node); extern struct timerqueue_node *timerqueue_iterate_next( struct timerqueue_node *node); /** * timerqueue_getnext - Returns the timer with the earliest expiration time * * @head: head of timerqueue * * Returns a pointer to the timer node that has the earliest expiration time. */ static inline struct timerqueue_node *timerqueue_getnext(struct timerqueue_head *head) { struct rb_node *leftmost = rb_first_cached(&head->rb_root); return rb_entry(leftmost, struct timerqueue_node, node); } static inline void timerqueue_init(struct timerqueue_node *node) { RB_CLEAR_NODE(&node->node); } static inline bool timerqueue_node_queued(struct timerqueue_node *node) { return !RB_EMPTY_NODE(&node->node); } static inline bool timerqueue_node_expires(struct timerqueue_node *node) { return node->expires; } static inline void timerqueue_init_head(struct timerqueue_head *head) { head->rb_root = RB_ROOT_CACHED; } #endif /* _LINUX_TIMERQUEUE_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* audit.h -- Auditing support * * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. * All Rights Reserved. * * Written by Rickard E. (Rik) Faith <faith@redhat.com> */ #ifndef _LINUX_AUDIT_H_ #define _LINUX_AUDIT_H_ #include <linux/sched.h> #include <linux/ptrace.h> #include <uapi/linux/audit.h> #include <uapi/linux/netfilter/nf_tables.h> #define AUDIT_INO_UNSET ((unsigned long)-1) #define AUDIT_DEV_UNSET ((dev_t)-1) struct audit_sig_info { uid_t uid; pid_t pid; char ctx[]; }; struct audit_buffer; struct audit_context; struct inode; struct netlink_skb_parms; struct path; struct linux_binprm; struct mq_attr; struct mqstat; struct audit_watch; struct audit_tree; struct sk_buff; struct audit_krule { u32 pflags; u32 flags; u32 listnr; u32 action; u32 mask[AUDIT_BITMASK_SIZE]; u32 buflen; /* for data alloc on list rules */ u32 field_count; char *filterkey; /* ties events to rules */ struct audit_field *fields; struct audit_field *arch_f; /* quick access to arch field */ struct audit_field *inode_f; /* quick access to an inode field */ struct audit_watch *watch; /* associated watch */ struct audit_tree *tree; /* associated watched tree */ struct audit_fsnotify_mark *exe; struct list_head rlist; /* entry in audit_{watch,tree}.rules list */ struct list_head list; /* for AUDIT_LIST* purposes only */ u64 prio; }; /* Flag to indicate legacy AUDIT_LOGINUID unset usage */ #define AUDIT_LOGINUID_LEGACY 0x1 struct audit_field { u32 type; union { u32 val; kuid_t uid; kgid_t gid; struct { char *lsm_str; void *lsm_rule; }; }; u32 op; }; enum audit_ntp_type { AUDIT_NTP_OFFSET, AUDIT_NTP_FREQ, AUDIT_NTP_STATUS, AUDIT_NTP_TAI, AUDIT_NTP_TICK, AUDIT_NTP_ADJUST, AUDIT_NTP_NVALS /* count */ }; #ifdef CONFIG_AUDITSYSCALL struct audit_ntp_val { long long oldval, newval; }; struct audit_ntp_data { struct audit_ntp_val vals[AUDIT_NTP_NVALS]; }; #else struct audit_ntp_data {}; #endif enum audit_nfcfgop { AUDIT_XT_OP_REGISTER, AUDIT_XT_OP_REPLACE, AUDIT_XT_OP_UNREGISTER, AUDIT_NFT_OP_TABLE_REGISTER, AUDIT_NFT_OP_TABLE_UNREGISTER, AUDIT_NFT_OP_CHAIN_REGISTER, AUDIT_NFT_OP_CHAIN_UNREGISTER, AUDIT_NFT_OP_RULE_REGISTER, AUDIT_NFT_OP_RULE_UNREGISTER, AUDIT_NFT_OP_SET_REGISTER, AUDIT_NFT_OP_SET_UNREGISTER, AUDIT_NFT_OP_SETELEM_REGISTER, AUDIT_NFT_OP_SETELEM_UNREGISTER, AUDIT_NFT_OP_GEN_REGISTER, AUDIT_NFT_OP_OBJ_REGISTER, AUDIT_NFT_OP_OBJ_UNREGISTER, AUDIT_NFT_OP_OBJ_RESET, AUDIT_NFT_OP_FLOWTABLE_REGISTER, AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, AUDIT_NFT_OP_INVALID, }; extern int is_audit_feature_set(int which); extern int __init audit_register_class(int class, unsigned *list); extern int audit_classify_syscall(int abi, unsigned syscall); extern int audit_classify_arch(int arch); /* only for compat system calls */ extern unsigned compat_write_class[]; extern unsigned compat_read_class[]; extern unsigned compat_dir_class[]; extern unsigned compat_chattr_class[]; extern unsigned compat_signal_class[]; extern int audit_classify_compat_syscall(int abi, unsigned syscall); /* audit_names->type values */ #define AUDIT_TYPE_UNKNOWN 0 /* we don't know yet */ #define AUDIT_TYPE_NORMAL 1 /* a "normal" audit record */ #define AUDIT_TYPE_PARENT 2 /* a parent audit record */ #define AUDIT_TYPE_CHILD_DELETE 3 /* a child being deleted */ #define AUDIT_TYPE_CHILD_CREATE 4 /* a child being created */ /* maximized args number that audit_socketcall can process */ #define AUDITSC_ARGS 6 /* bit values for ->signal->audit_tty */ #define AUDIT_TTY_ENABLE BIT(0) #define AUDIT_TTY_LOG_PASSWD BIT(1) struct filename; #define AUDIT_OFF 0 #define AUDIT_ON 1 #define AUDIT_LOCKED 2 #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ extern __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...); extern struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type); extern __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...); extern void audit_log_end(struct audit_buffer *ab); extern bool audit_string_contains_control(const char *string, size_t len); extern void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len); extern void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n); extern void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n); extern void audit_log_untrustedstring(struct audit_buffer *ab, const char *string); extern void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path); extern void audit_log_key(struct audit_buffer *ab, char *key); extern void audit_log_path_denied(int type, const char *operation); extern void audit_log_lost(const char *message); extern int audit_log_task_context(struct audit_buffer *ab); extern void audit_log_task_info(struct audit_buffer *ab); extern int audit_update_lsm_rules(void); /* Private API (for audit.c only) */ extern int audit_rule_change(int type, int seq, void *data, size_t datasz); extern int audit_list_rules_send(struct sk_buff *request_skb, int seq); extern int audit_set_loginuid(kuid_t loginuid); static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return tsk->loginuid; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return tsk->sessionid; } extern u32 audit_enabled; extern int audit_signal_info(int sig, struct task_struct *t); #else /* CONFIG_AUDIT */ static inline __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...) { } static inline struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) { return NULL; } static inline __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) { } static inline void audit_log_end(struct audit_buffer *ab) { } static inline void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len) { } static inline void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n) { } static inline void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n) { } static inline void audit_log_untrustedstring(struct audit_buffer *ab, const char *string) { } static inline void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path) { } static inline void audit_log_key(struct audit_buffer *ab, char *key) { } static inline void audit_log_path_denied(int type, const char *operation) { } static inline int audit_log_task_context(struct audit_buffer *ab) { return 0; } static inline void audit_log_task_info(struct audit_buffer *ab) { } static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return INVALID_UID; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return AUDIT_SID_UNSET; } #define audit_enabled AUDIT_OFF static inline int audit_signal_info(int sig, struct task_struct *t) { return 0; } #endif /* CONFIG_AUDIT */ #ifdef CONFIG_AUDIT_COMPAT_GENERIC #define audit_is_compat(arch) (!((arch) & __AUDIT_ARCH_64BIT)) #else #define audit_is_compat(arch) false #endif #define AUDIT_INODE_PARENT 1 /* dentry represents the parent */ #define AUDIT_INODE_HIDDEN 2 /* audit record should be hidden */ #define AUDIT_INODE_NOEVAL 4 /* audit record incomplete */ #ifdef CONFIG_AUDITSYSCALL #include <asm/syscall.h> /* for syscall_get_arch() */ /* These are defined in auditsc.c */ /* Public API */ extern int audit_alloc(struct task_struct *task); extern void __audit_free(struct task_struct *task); extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); extern struct filename *__audit_reusename(const __user char *uptr); extern void __audit_getname(struct filename *name); extern void __audit_getcwd(void); extern void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags); extern void __audit_file(const struct file *); extern void __audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type); extern void audit_seccomp(unsigned long syscall, long signr, int code); extern void audit_seccomp_actions_logged(const char *names, const char *old_names, int res); extern void __audit_ptrace(struct task_struct *t); static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { task->audit_context = ctx; } static inline struct audit_context *audit_context(void) { return current->audit_context; } static inline bool audit_dummy_context(void) { void *p = audit_context(); return !p || *(int *)p; } static inline void audit_free(struct task_struct *task) { if (unlikely(task->audit_context)) __audit_free(task); } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { if (unlikely(audit_context())) __audit_syscall_entry(major, a0, a1, a2, a3); } static inline void audit_syscall_exit(void *pt_regs) { if (unlikely(audit_context())) { int success = is_syscall_success(pt_regs); long return_code = regs_return_value(pt_regs); __audit_syscall_exit(success, return_code); } } static inline struct filename *audit_reusename(const __user char *name) { if (unlikely(!audit_dummy_context())) return __audit_reusename(name); return NULL; } static inline void audit_getname(struct filename *name) { if (unlikely(!audit_dummy_context())) __audit_getname(name); } static inline void audit_getcwd(void) { if (unlikely(audit_context())) __audit_getcwd(); } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, aflags); } static inline void audit_file(struct file *file) { if (unlikely(!audit_dummy_context())) __audit_file(file); } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, AUDIT_INODE_PARENT | AUDIT_INODE_HIDDEN); } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { if (unlikely(!audit_dummy_context())) __audit_inode_child(parent, dentry, type); } void audit_core_dumps(long signr); static inline void audit_ptrace(struct task_struct *t) { if (unlikely(!audit_dummy_context())) __audit_ptrace(t); } /* Private API (for audit.c only) */ extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); extern void __audit_bprm(struct linux_binprm *bprm); extern int __audit_socketcall(int nargs, unsigned long *args); extern int __audit_sockaddr(int len, void *addr); extern void __audit_fd_pair(int fd1, int fd2); extern void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr); extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout); extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification); extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old); extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); extern void __audit_log_kern_module(char *name); extern void __audit_fanotify(unsigned int response); extern void __audit_tk_injoffset(struct timespec64 offset); extern void __audit_ntp_log(const struct audit_ntp_data *ad); extern void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp); static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { if (unlikely(!audit_dummy_context())) __audit_ipc_obj(ipcp); } static inline void audit_fd_pair(int fd1, int fd2) { if (unlikely(!audit_dummy_context())) __audit_fd_pair(fd1, fd2); } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { if (unlikely(!audit_dummy_context())) __audit_ipc_set_perm(qbytes, uid, gid, mode); } static inline void audit_bprm(struct linux_binprm *bprm) { if (unlikely(!audit_dummy_context())) __audit_bprm(bprm); } static inline int audit_socketcall(int nargs, unsigned long *args) { if (unlikely(!audit_dummy_context())) return __audit_socketcall(nargs, args); return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { unsigned long a[AUDITSC_ARGS]; int i; if (audit_dummy_context()) return 0; for (i = 0; i < nargs; i++) a[i] = (unsigned long)args[i]; return __audit_socketcall(nargs, a); } static inline int audit_sockaddr(int len, void *addr) { if (unlikely(!audit_dummy_context())) return __audit_sockaddr(len, addr); return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { if (unlikely(!audit_dummy_context())) __audit_mq_open(oflag, mode, attr); } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { if (unlikely(!audit_dummy_context())) __audit_mq_sendrecv(mqdes, msg_len, msg_prio, abs_timeout); } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { if (unlikely(!audit_dummy_context())) __audit_mq_notify(mqdes, notification); } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { if (unlikely(!audit_dummy_context())) __audit_mq_getsetattr(mqdes, mqstat); } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) return __audit_log_bprm_fcaps(bprm, new, old); return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) __audit_log_capset(new, old); } static inline void audit_mmap_fd(int fd, int flags) { if (unlikely(!audit_dummy_context())) __audit_mmap_fd(fd, flags); } static inline void audit_log_kern_module(char *name) { if (!audit_dummy_context()) __audit_log_kern_module(name); } static inline void audit_fanotify(unsigned int response) { if (!audit_dummy_context()) __audit_fanotify(response); } static inline void audit_tk_injoffset(struct timespec64 offset) { /* ignore no-op events */ if (offset.tv_sec == 0 && offset.tv_nsec == 0) return; if (!audit_dummy_context()) __audit_tk_injoffset(offset); } static inline void audit_ntp_init(struct audit_ntp_data *ad) { memset(ad, 0, sizeof(*ad)); } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].oldval = val; } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].newval = val; } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { if (!audit_dummy_context()) __audit_ntp_log(ad); } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { if (audit_enabled) __audit_log_nfcfg(name, af, nentries, op, gfp); } extern int audit_n_rules; extern int audit_signals; #else /* CONFIG_AUDITSYSCALL */ static inline int audit_alloc(struct task_struct *task) { return 0; } static inline void audit_free(struct task_struct *task) { } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { } static inline void audit_syscall_exit(void *pt_regs) { } static inline bool audit_dummy_context(void) { return true; } static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { } static inline struct audit_context *audit_context(void) { return NULL; } static inline struct filename *audit_reusename(const __user char *name) { return NULL; } static inline void audit_getname(struct filename *name) { } static inline void audit_getcwd(void) { } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { } static inline void audit_file(struct file *file) { } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { } static inline void audit_core_dumps(long signr) { } static inline void audit_seccomp(unsigned long syscall, long signr, int code) { } static inline void audit_seccomp_actions_logged(const char *names, const char *old_names, int res) { } static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { } static inline void audit_bprm(struct linux_binprm *bprm) { } static inline int audit_socketcall(int nargs, unsigned long *args) { return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { return 0; } static inline void audit_fd_pair(int fd1, int fd2) { } static inline int audit_sockaddr(int len, void *addr) { return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { } static inline void audit_mmap_fd(int fd, int flags) { } static inline void audit_log_kern_module(char *name) { } static inline void audit_fanotify(unsigned int response) { } static inline void audit_tk_injoffset(struct timespec64 offset) { } static inline void audit_ntp_init(struct audit_ntp_data *ad) { } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { } static inline void audit_ptrace(struct task_struct *t) { } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { } #define audit_n_rules 0 #define audit_signals 0 #endif /* CONFIG_AUDITSYSCALL */ static inline bool audit_loginuid_set(struct task_struct *tsk) { return uid_valid(audit_get_loginuid(tsk)); } #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM compaction #if !defined(_TRACE_COMPACTION_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_COMPACTION_H #include <linux/types.h> #include <linux/list.h> #include <linux/tracepoint.h> #include <trace/events/mmflags.h> DECLARE_EVENT_CLASS(mm_compaction_isolate_template, TP_PROTO( unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_scanned, unsigned long nr_taken), TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken), TP_STRUCT__entry( __field(unsigned long, start_pfn) __field(unsigned long, end_pfn) __field(unsigned long, nr_scanned) __field(unsigned long, nr_taken) ), TP_fast_assign( __entry->start_pfn = start_pfn; __entry->end_pfn = end_pfn; __entry->nr_scanned = nr_scanned; __entry->nr_taken = nr_taken; ), TP_printk("range=(0x%lx ~ 0x%lx) nr_scanned=%lu nr_taken=%lu", __entry->start_pfn, __entry->end_pfn, __entry->nr_scanned, __entry->nr_taken) ); DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_migratepages, TP_PROTO( unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_scanned, unsigned long nr_taken), TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken) ); DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_freepages, TP_PROTO( unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_scanned, unsigned long nr_taken), TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken) ); #ifdef CONFIG_COMPACTION TRACE_EVENT(mm_compaction_migratepages, TP_PROTO(unsigned long nr_all, int migrate_rc, struct list_head *migratepages), TP_ARGS(nr_all, migrate_rc, migratepages), TP_STRUCT__entry( __field(unsigned long, nr_migrated) __field(unsigned long, nr_failed) ), TP_fast_assign( unsigned long nr_failed = 0; struct list_head *page_lru; /* * migrate_pages() returns either a non-negative number * with the number of pages that failed migration, or an * error code, in which case we need to count the remaining * pages manually */ if (migrate_rc >= 0) nr_failed = migrate_rc; else list_for_each(page_lru, migratepages) nr_failed++; __entry->nr_migrated = nr_all - nr_failed; __entry->nr_failed = nr_failed; ), TP_printk("nr_migrated=%lu nr_failed=%lu", __entry->nr_migrated, __entry->nr_failed) ); TRACE_EVENT(mm_compaction_begin, TP_PROTO(unsigned long zone_start, unsigned long migrate_pfn, unsigned long free_pfn, unsigned long zone_end, bool sync), TP_ARGS(zone_start, migrate_pfn, free_pfn, zone_end, sync), TP_STRUCT__entry( __field(unsigned long, zone_start) __field(unsigned long, migrate_pfn) __field(unsigned long, free_pfn) __field(unsigned long, zone_end) __field(bool, sync) ), TP_fast_assign( __entry->zone_start = zone_start; __entry->migrate_pfn = migrate_pfn; __entry->free_pfn = free_pfn; __entry->zone_end = zone_end; __entry->sync = sync; ), TP_printk("zone_start=0x%lx migrate_pfn=0x%lx free_pfn=0x%lx zone_end=0x%lx, mode=%s", __entry->zone_start, __entry->migrate_pfn, __entry->free_pfn, __entry->zone_end, __entry->sync ? "sync" : "async") ); TRACE_EVENT(mm_compaction_end, TP_PROTO(unsigned long zone_start, unsigned long migrate_pfn, unsigned long free_pfn, unsigned long zone_end, bool sync, int status), TP_ARGS(zone_start, migrate_pfn, free_pfn, zone_end, sync, status), TP_STRUCT__entry( __field(unsigned long, zone_start) __field(unsigned long, migrate_pfn) __field(unsigned long, free_pfn) __field(unsigned long, zone_end) __field(bool, sync) __field(int, status) ), TP_fast_assign( __entry->zone_start = zone_start; __entry->migrate_pfn = migrate_pfn; __entry->free_pfn = free_pfn; __entry->zone_end = zone_end; __entry->sync = sync; __entry->status = status; ), TP_printk("zone_start=0x%lx migrate_pfn=0x%lx free_pfn=0x%lx zone_end=0x%lx, mode=%s status=%s", __entry->zone_start, __entry->migrate_pfn, __entry->free_pfn, __entry->zone_end, __entry->sync ? "sync" : "async", __print_symbolic(__entry->status, COMPACTION_STATUS)) ); TRACE_EVENT(mm_compaction_try_to_compact_pages, TP_PROTO( int order, gfp_t gfp_mask, int prio), TP_ARGS(order, gfp_mask, prio), TP_STRUCT__entry( __field(int, order) __field(gfp_t, gfp_mask) __field(int, prio) ), TP_fast_assign( __entry->order = order; __entry->gfp_mask = gfp_mask; __entry->prio = prio; ), TP_printk("order=%d gfp_mask=%s priority=%d", __entry->order, show_gfp_flags(__entry->gfp_mask), __entry->prio) ); DECLARE_EVENT_CLASS(mm_compaction_suitable_template, TP_PROTO(struct zone *zone, int order, int ret), TP_ARGS(zone, order, ret), TP_STRUCT__entry( __field(int, nid) __field(enum zone_type, idx) __field(int, order) __field(int, ret) ), TP_fast_assign( __entry->nid = zone_to_nid(zone); __entry->idx = zone_idx(zone); __entry->order = order; __entry->ret = ret; ), TP_printk("node=%d zone=%-8s order=%d ret=%s", __entry->nid, __print_symbolic(__entry->idx, ZONE_TYPE), __entry->order, __print_symbolic(__entry->ret, COMPACTION_STATUS)) ); DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_finished, TP_PROTO(struct zone *zone, int order, int ret), TP_ARGS(zone, order, ret) ); DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_suitable, TP_PROTO(struct zone *zone, int order, int ret), TP_ARGS(zone, order, ret) ); DECLARE_EVENT_CLASS(mm_compaction_defer_template, TP_PROTO(struct zone *zone, int order), TP_ARGS(zone, order), TP_STRUCT__entry( __field(int, nid) __field(enum zone_type, idx) __field(int, order) __field(unsigned int, considered) __field(unsigned int, defer_shift) __field(int, order_failed) ), TP_fast_assign( __entry->nid = zone_to_nid(zone); __entry->idx = zone_idx(zone); __entry->order = order; __entry->considered = zone->compact_considered; __entry->defer_shift = zone->compact_defer_shift; __entry->order_failed = zone->compact_order_failed; ), TP_printk("node=%d zone=%-8s order=%d order_failed=%d consider=%u limit=%lu", __entry->nid, __print_symbolic(__entry->idx, ZONE_TYPE), __entry->order, __entry->order_failed, __entry->considered, 1UL << __entry->defer_shift) ); DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_deferred, TP_PROTO(struct zone *zone, int order), TP_ARGS(zone, order) ); DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_defer_compaction, TP_PROTO(struct zone *zone, int order), TP_ARGS(zone, order) ); DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_defer_reset, TP_PROTO(struct zone *zone, int order), TP_ARGS(zone, order) ); TRACE_EVENT(mm_compaction_kcompactd_sleep, TP_PROTO(int nid), TP_ARGS(nid), TP_STRUCT__entry( __field(int, nid) ), TP_fast_assign( __entry->nid = nid; ), TP_printk("nid=%d", __entry->nid) ); DECLARE_EVENT_CLASS(kcompactd_wake_template, TP_PROTO(int nid, int order, enum zone_type highest_zoneidx), TP_ARGS(nid, order, highest_zoneidx), TP_STRUCT__entry( __field(int, nid) __field(int, order) __field(enum zone_type, highest_zoneidx) ), TP_fast_assign( __entry->nid = nid; __entry->order = order; __entry->highest_zoneidx = highest_zoneidx; ), /* * classzone_idx is previous name of the highest_zoneidx. * Reason not to change it is the ABI requirement of the tracepoint. */ TP_printk("nid=%d order=%d classzone_idx=%-8s", __entry->nid, __entry->order, __print_symbolic(__entry->highest_zoneidx, ZONE_TYPE)) ); DEFINE_EVENT(kcompactd_wake_template, mm_compaction_wakeup_kcompactd, TP_PROTO(int nid, int order, enum zone_type highest_zoneidx), TP_ARGS(nid, order, highest_zoneidx) ); DEFINE_EVENT(kcompactd_wake_template, mm_compaction_kcompactd_wake, TP_PROTO(int nid, int order, enum zone_type highest_zoneidx), TP_ARGS(nid, order, highest_zoneidx) ); #endif #endif /* _TRACE_COMPACTION_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_IVERSION_H #define _LINUX_IVERSION_H #include <linux/fs.h> /* * The inode->i_version field: * --------------------------- * The change attribute (i_version) is mandated by NFSv4 and is mostly for * knfsd, but is also used for other purposes (e.g. IMA). The i_version must * appear different to observers if there was a change to the inode's data or * metadata since it was last queried. * * Observers see the i_version as a 64-bit number that never decreases. If it * remains the same since it was last checked, then nothing has changed in the * inode. If it's different then something has changed. Observers cannot infer * anything about the nature or magnitude of the changes from the value, only * that the inode has changed in some fashion. * * Not all filesystems properly implement the i_version counter. Subsystems that * want to use i_version field on an inode should first check whether the * filesystem sets the SB_I_VERSION flag (usually via the IS_I_VERSION macro). * * Those that set SB_I_VERSION will automatically have their i_version counter * incremented on writes to normal files. If the SB_I_VERSION is not set, then * the VFS will not touch it on writes, and the filesystem can use it how it * wishes. Note that the filesystem is always responsible for updating the * i_version on namespace changes in directories (mkdir, rmdir, unlink, etc.). * We consider these sorts of filesystems to have a kernel-managed i_version. * * It may be impractical for filesystems to keep i_version updates atomic with * respect to the changes that cause them. They should, however, guarantee * that i_version updates are never visible before the changes that caused * them. Also, i_version updates should never be delayed longer than it takes * the original change to reach disk. * * This implementation uses the low bit in the i_version field as a flag to * track when the value has been queried. If it has not been queried since it * was last incremented, we can skip the increment in most cases. * * In the event that we're updating the ctime, we will usually go ahead and * bump the i_version anyway. Since that has to go to stable storage in some * fashion, we might as well increment it as well. * * With this implementation, the value should always appear to observers to * increase over time if the file has changed. It's recommended to use * inode_eq_iversion() helper to compare values. * * Note that some filesystems (e.g. NFS and AFS) just use the field to store * a server-provided value (for the most part). For that reason, those * filesystems do not set SB_I_VERSION. These filesystems are considered to * have a self-managed i_version. * * Persistently storing the i_version * ---------------------------------- * Queries of the i_version field are not gated on them hitting the backing * store. It's always possible that the host could crash after allowing * a query of the value but before it has made it to disk. * * To mitigate this problem, filesystems should always use * inode_set_iversion_queried when loading an existing inode from disk. This * ensures that the next attempted inode increment will result in the value * changing. * * Storing the value to disk therefore does not count as a query, so those * filesystems should use inode_peek_iversion to grab the value to be stored. * There is no need to flag the value as having been queried in that case. */ /* * We borrow the lowest bit in the i_version to use as a flag to tell whether * it has been queried since we last incremented it. If it has, then we must * increment it on the next change. After that, we can clear the flag and * avoid incrementing it again until it has again been queried. */ #define I_VERSION_QUERIED_SHIFT (1) #define I_VERSION_QUERIED (1ULL << (I_VERSION_QUERIED_SHIFT - 1)) #define I_VERSION_INCREMENT (1ULL << I_VERSION_QUERIED_SHIFT) /** * inode_set_iversion_raw - set i_version to the specified raw value * @inode: inode to set * @val: new i_version value to set * * Set @inode's i_version field to @val. This function is for use by * filesystems that self-manage the i_version. * * For example, the NFS client stores its NFSv4 change attribute in this way, * and the AFS client stores the data_version from the server here. */ static inline void inode_set_iversion_raw(struct inode *inode, u64 val) { atomic64_set(&inode->i_version, val); } /** * inode_peek_iversion_raw - grab a "raw" iversion value * @inode: inode from which i_version should be read * * Grab a "raw" inode->i_version value and return it. The i_version is not * flagged or converted in any way. This is mostly used to access a self-managed * i_version. * * With those filesystems, we want to treat the i_version as an entirely * opaque value. */ static inline u64 inode_peek_iversion_raw(const struct inode *inode) { return atomic64_read(&inode->i_version); } /** * inode_set_max_iversion_raw - update i_version new value is larger * @inode: inode to set * @val: new i_version to set * * Some self-managed filesystems (e.g Ceph) will only update the i_version * value if the new value is larger than the one we already have. */ static inline void inode_set_max_iversion_raw(struct inode *inode, u64 val) { u64 cur, old; cur = inode_peek_iversion_raw(inode); for (;;) { if (cur > val) break; old = atomic64_cmpxchg(&inode->i_version, cur, val); if (likely(old == cur)) break; cur = old; } } /** * inode_set_iversion - set i_version to a particular value * @inode: inode to set * @val: new i_version value to set * * Set @inode's i_version field to @val. This function is for filesystems with * a kernel-managed i_version, for initializing a newly-created inode from * scratch. * * In this case, we do not set the QUERIED flag since we know that this value * has never been queried. */ static inline void inode_set_iversion(struct inode *inode, u64 val) { inode_set_iversion_raw(inode, val << I_VERSION_QUERIED_SHIFT); } /** * inode_set_iversion_queried - set i_version to a particular value as quereied * @inode: inode to set * @val: new i_version value to set * * Set @inode's i_version field to @val, and flag it for increment on the next * change. * * Filesystems that persistently store the i_version on disk should use this * when loading an existing inode from disk. * * When loading in an i_version value from a backing store, we can't be certain * that it wasn't previously viewed before being stored. Thus, we must assume * that it was, to ensure that we don't end up handing out the same value for * different versions of the same inode. */ static inline void inode_set_iversion_queried(struct inode *inode, u64 val) { inode_set_iversion_raw(inode, (val << I_VERSION_QUERIED_SHIFT) | I_VERSION_QUERIED); } /** * inode_maybe_inc_iversion - increments i_version * @inode: inode with the i_version that should be updated * @force: increment the counter even if it's not necessary? * * Every time the inode is modified, the i_version field must be seen to have * changed by any observer. * * If "force" is set or the QUERIED flag is set, then ensure that we increment * the value, and clear the queried flag. * * In the common case where neither is set, then we can return "false" without * updating i_version. * * If this function returns false, and no other metadata has changed, then we * can avoid logging the metadata. */ static inline bool inode_maybe_inc_iversion(struct inode *inode, bool force) { u64 cur, old, new; /* * The i_version field is not strictly ordered with any other inode * information, but the legacy inode_inc_iversion code used a spinlock * to serialize increments. * * Here, we add full memory barriers to ensure that any de-facto * ordering with other info is preserved. * * This barrier pairs with the barrier in inode_query_iversion() */ smp_mb(); cur = inode_peek_iversion_raw(inode); for (;;) { /* If flag is clear then we needn't do anything */ if (!force && !(cur & I_VERSION_QUERIED)) return false; /* Since lowest bit is flag, add 2 to avoid it */ new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT; old = atomic64_cmpxchg(&inode->i_version, cur, new); if (likely(old == cur)) break; cur = old; } return true; } /** * inode_inc_iversion - forcibly increment i_version * @inode: inode that needs to be updated * * Forcbily increment the i_version field. This always results in a change to * the observable value. */ static inline void inode_inc_iversion(struct inode *inode) { inode_maybe_inc_iversion(inode, true); } /** * inode_iversion_need_inc - is the i_version in need of being incremented? * @inode: inode to check * * Returns whether the inode->i_version counter needs incrementing on the next * change. Just fetch the value and check the QUERIED flag. */ static inline bool inode_iversion_need_inc(struct inode *inode) { return inode_peek_iversion_raw(inode) & I_VERSION_QUERIED; } /** * inode_inc_iversion_raw - forcibly increment raw i_version * @inode: inode that needs to be updated * * Forcbily increment the raw i_version field. This always results in a change * to the raw value. * * NFS will use the i_version field to store the value from the server. It * mostly treats it as opaque, but in the case where it holds a write * delegation, it must increment the value itself. This function does that. */ static inline void inode_inc_iversion_raw(struct inode *inode) { atomic64_inc(&inode->i_version); } /** * inode_peek_iversion - read i_version without flagging it to be incremented * @inode: inode from which i_version should be read * * Read the inode i_version counter for an inode without registering it as a * query. * * This is typically used by local filesystems that need to store an i_version * on disk. In that situation, it's not necessary to flag it as having been * viewed, as the result won't be used to gauge changes from that point. */ static inline u64 inode_peek_iversion(const struct inode *inode) { return inode_peek_iversion_raw(inode) >> I_VERSION_QUERIED_SHIFT; } /** * inode_query_iversion - read i_version for later use * @inode: inode from which i_version should be read * * Read the inode i_version counter. This should be used by callers that wish * to store the returned i_version for later comparison. This will guarantee * that a later query of the i_version will result in a different value if * anything has changed. * * In this implementation, we fetch the current value, set the QUERIED flag and * then try to swap it into place with a cmpxchg, if it wasn't already set. If * that fails, we try again with the newly fetched value from the cmpxchg. */ static inline u64 inode_query_iversion(struct inode *inode) { u64 cur, old, new; cur = inode_peek_iversion_raw(inode); for (;;) { /* If flag is already set, then no need to swap */ if (cur & I_VERSION_QUERIED) { /* * This barrier (and the implicit barrier in the * cmpxchg below) pairs with the barrier in * inode_maybe_inc_iversion(). */ smp_mb(); break; } new = cur | I_VERSION_QUERIED; old = atomic64_cmpxchg(&inode->i_version, cur, new); if (likely(old == cur)) break; cur = old; } return cur >> I_VERSION_QUERIED_SHIFT; } /** * inode_eq_iversion_raw - check whether the raw i_version counter has changed * @inode: inode to check * @old: old value to check against its i_version * * Compare the current raw i_version counter with a previous one. Returns true * if they are the same or false if they are different. */ static inline bool inode_eq_iversion_raw(const struct inode *inode, u64 old) { return inode_peek_iversion_raw(inode) == old; } /** * inode_eq_iversion - check whether the i_version counter has changed * @inode: inode to check * @old: old value to check against its i_version * * Compare an i_version counter with a previous one. Returns true if they are * the same, and false if they are different. * * Note that we don't need to set the QUERIED flag in this case, as the value * in the inode is not being recorded for later use. */ static inline bool inode_eq_iversion(const struct inode *inode, u64 old) { return inode_peek_iversion(inode) == old; } #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Definitions for the 'struct ptr_ring' datastructure. * * Author: * Michael S. Tsirkin <mst@redhat.com> * * Copyright (C) 2016 Red Hat, Inc. * * This is a limited-size FIFO maintaining pointers in FIFO order, with * one CPU producing entries and another consuming entries from a FIFO. * * This implementation tries to minimize cache-contention when there is a * single producer and a single consumer CPU. */ #ifndef _LINUX_PTR_RING_H #define _LINUX_PTR_RING_H 1 #ifdef __KERNEL__ #include <linux/spinlock.h> #include <linux/cache.h> #include <linux/types.h> #include <linux/compiler.h> #include <linux/slab.h> #include <linux/mm.h> #include <asm/errno.h> #endif struct ptr_ring { int producer ____cacheline_aligned_in_smp; spinlock_t producer_lock; int consumer_head ____cacheline_aligned_in_smp; /* next valid entry */ int consumer_tail; /* next entry to invalidate */ spinlock_t consumer_lock; /* Shared consumer/producer data */ /* Read-only by both the producer and the consumer */ int size ____cacheline_aligned_in_smp; /* max entries in queue */ int batch; /* number of entries to consume in a batch */ void **queue; }; /* Note: callers invoking this in a loop must use a compiler barrier, * for example cpu_relax(). * * NB: this is unlike __ptr_ring_empty in that callers must hold producer_lock: * see e.g. ptr_ring_full. */ static inline bool __ptr_ring_full(struct ptr_ring *r) { return r->queue[r->producer]; } static inline bool ptr_ring_full(struct ptr_ring *r) { bool ret; spin_lock(&r->producer_lock); ret = __ptr_ring_full(r); spin_unlock(&r->producer_lock); return ret; } static inline bool ptr_ring_full_irq(struct ptr_ring *r) { bool ret; spin_lock_irq(&r->producer_lock); ret = __ptr_ring_full(r); spin_unlock_irq(&r->producer_lock); return ret; } static inline bool ptr_ring_full_any(struct ptr_ring *r) { unsigned long flags; bool ret; spin_lock_irqsave(&r->producer_lock, flags); ret = __ptr_ring_full(r); spin_unlock_irqrestore(&r->producer_lock, flags); return ret; } static inline bool ptr_ring_full_bh(struct ptr_ring *r) { bool ret; spin_lock_bh(&r->producer_lock); ret = __ptr_ring_full(r); spin_unlock_bh(&r->producer_lock); return ret; } /* Note: callers invoking this in a loop must use a compiler barrier, * for example cpu_relax(). Callers must hold producer_lock. * Callers are responsible for making sure pointer that is being queued * points to a valid data. */ static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr) { if (unlikely(!r->size) || r->queue[r->producer]) return -ENOSPC; /* Make sure the pointer we are storing points to a valid data. */ /* Pairs with the dependency ordering in __ptr_ring_consume. */ smp_wmb(); WRITE_ONCE(r->queue[r->producer++], ptr); if (unlikely(r->producer >= r->size)) r->producer = 0; return 0; } /* * Note: resize (below) nests producer lock within consumer lock, so if you * consume in interrupt or BH context, you must disable interrupts/BH when * calling this. */ static inline int ptr_ring_produce(struct ptr_ring *r, void *ptr) { int ret; spin_lock(&r->producer_lock); ret = __ptr_ring_produce(r, ptr); spin_unlock(&r->producer_lock); return ret; } static inline int ptr_ring_produce_irq(struct ptr_ring *r, void *ptr) { int ret; spin_lock_irq(&r->producer_lock); ret = __ptr_ring_produce(r, ptr); spin_unlock_irq(&r->producer_lock); return ret; } static inline int ptr_ring_produce_any(struct ptr_ring *r, void *ptr) { unsigned long flags; int ret; spin_lock_irqsave(&r->producer_lock, flags); ret = __ptr_ring_produce(r, ptr); spin_unlock_irqrestore(&r->producer_lock, flags); return ret; } static inline int ptr_ring_produce_bh(struct ptr_ring *r, void *ptr) { int ret; spin_lock_bh(&r->producer_lock); ret = __ptr_ring_produce(r, ptr); spin_unlock_bh(&r->producer_lock); return ret; } static inline void *__ptr_ring_peek(struct ptr_ring *r) { if (likely(r->size)) return READ_ONCE(r->queue[r->consumer_head]); return NULL; } /* * Test ring empty status without taking any locks. * * NB: This is only safe to call if ring is never resized. * * However, if some other CPU consumes ring entries at the same time, the value * returned is not guaranteed to be correct. * * In this case - to avoid incorrectly detecting the ring * as empty - the CPU consuming the ring entries is responsible * for either consuming all ring entries until the ring is empty, * or synchronizing with some other CPU and causing it to * re-test __ptr_ring_empty and/or consume the ring enteries * after the synchronization point. * * Note: callers invoking this in a loop must use a compiler barrier, * for example cpu_relax(). */ static inline bool __ptr_ring_empty(struct ptr_ring *r) { if (likely(r->size)) return !r->queue[READ_ONCE(r->consumer_head)]; return true; } static inline bool ptr_ring_empty(struct ptr_ring *r) { bool ret; spin_lock(&r->consumer_lock); ret = __ptr_ring_empty(r); spin_unlock(&r->consumer_lock); return ret; } static inline bool ptr_ring_empty_irq(struct ptr_ring *r) { bool ret; spin_lock_irq(&r->consumer_lock); ret = __ptr_ring_empty(r); spin_unlock_irq(&r->consumer_lock); return ret; } static inline bool ptr_ring_empty_any(struct ptr_ring *r) { unsigned long flags; bool ret; spin_lock_irqsave(&r->consumer_lock, flags); ret = __ptr_ring_empty(r); spin_unlock_irqrestore(&r->consumer_lock, flags); return ret; } static inline bool ptr_ring_empty_bh(struct ptr_ring *r) { bool ret; spin_lock_bh(&r->consumer_lock); ret = __ptr_ring_empty(r); spin_unlock_bh(&r->consumer_lock); return ret; } /* Must only be called after __ptr_ring_peek returned !NULL */ static inline void __ptr_ring_discard_one(struct ptr_ring *r) { /* Fundamentally, what we want to do is update consumer * index and zero out the entry so producer can reuse it. * Doing it naively at each consume would be as simple as: * consumer = r->consumer; * r->queue[consumer++] = NULL; * if (unlikely(consumer >= r->size)) * consumer = 0; * r->consumer = consumer; * but that is suboptimal when the ring is full as producer is writing * out new entries in the same cache line. Defer these updates until a * batch of entries has been consumed. */ /* Note: we must keep consumer_head valid at all times for __ptr_ring_empty * to work correctly. */ int consumer_head = r->consumer_head; int head = consumer_head++; /* Once we have processed enough entries invalidate them in * the ring all at once so producer can reuse their space in the ring. * We also do this when we reach end of the ring - not mandatory * but helps keep the implementation simple. */ if (unlikely(consumer_head - r->consumer_tail >= r->batch || consumer_head >= r->size)) { /* Zero out entries in the reverse order: this way we touch the * cache line that producer might currently be reading the last; * producer won't make progress and touch other cache lines * besides the first one until we write out all entries. */ while (likely(head >= r->consumer_tail)) r->queue[head--] = NULL; r->consumer_tail = consumer_head; } if (unlikely(consumer_head >= r->size)) { consumer_head = 0; r->consumer_tail = 0; } /* matching READ_ONCE in __ptr_ring_empty for lockless tests */ WRITE_ONCE(r->consumer_head, consumer_head); } static inline void *__ptr_ring_consume(struct ptr_ring *r) { void *ptr; /* The READ_ONCE in __ptr_ring_peek guarantees that anyone * accessing data through the pointer is up to date. Pairs * with smp_wmb in __ptr_ring_produce. */ ptr = __ptr_ring_peek(r); if (ptr) __ptr_ring_discard_one(r); return ptr; } static inline int __ptr_ring_consume_batched(struct ptr_ring *r, void **array, int n) { void *ptr; int i; for (i = 0; i < n; i++) { ptr = __ptr_ring_consume(r); if (!ptr) break; array[i] = ptr; } return i; } /* * Note: resize (below) nests producer lock within consumer lock, so if you * call this in interrupt or BH context, you must disable interrupts/BH when * producing. */ static inline void *ptr_ring_consume(struct ptr_ring *r) { void *ptr; spin_lock(&r->consumer_lock); ptr = __ptr_ring_consume(r); spin_unlock(&r->consumer_lock); return ptr; } static inline void *ptr_ring_consume_irq(struct ptr_ring *r) { void *ptr; spin_lock_irq(&r->consumer_lock); ptr = __ptr_ring_consume(r); spin_unlock_irq(&r->consumer_lock); return ptr; } static inline void *ptr_ring_consume_any(struct ptr_ring *r) { unsigned long flags; void *ptr; spin_lock_irqsave(&r->consumer_lock, flags); ptr = __ptr_ring_consume(r); spin_unlock_irqrestore(&r->consumer_lock, flags); return ptr; } static inline void *ptr_ring_consume_bh(struct ptr_ring *r) { void *ptr; spin_lock_bh(&r->consumer_lock); ptr = __ptr_ring_consume(r); spin_unlock_bh(&r->consumer_lock); return ptr; } static inline int ptr_ring_consume_batched(struct ptr_ring *r, void **array, int n) { int ret; spin_lock(&r->consumer_lock); ret = __ptr_ring_consume_batched(r, array, n); spin_unlock(&r->consumer_lock); return ret; } static inline int ptr_ring_consume_batched_irq(struct ptr_ring *r, void **array, int n) { int ret; spin_lock_irq(&r->consumer_lock); ret = __ptr_ring_consume_batched(r, array, n); spin_unlock_irq(&r->consumer_lock); return ret; } static inline int ptr_ring_consume_batched_any(struct ptr_ring *r, void **array, int n) { unsigned long flags; int ret; spin_lock_irqsave(&r->consumer_lock, flags); ret = __ptr_ring_consume_batched(r, array, n); spin_unlock_irqrestore(&r->consumer_lock, flags); return ret; } static inline int ptr_ring_consume_batched_bh(struct ptr_ring *r, void **array, int n) { int ret; spin_lock_bh(&r->consumer_lock); ret = __ptr_ring_consume_batched(r, array, n); spin_unlock_bh(&r->consumer_lock); return ret; } /* Cast to structure type and call a function without discarding from FIFO. * Function must return a value. * Callers must take consumer_lock. */ #define __PTR_RING_PEEK_CALL(r, f) ((f)(__ptr_ring_peek(r))) #define PTR_RING_PEEK_CALL(r, f) ({ \ typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \ \ spin_lock(&(r)->consumer_lock); \ __PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \ spin_unlock(&(r)->consumer_lock); \ __PTR_RING_PEEK_CALL_v; \ }) #define PTR_RING_PEEK_CALL_IRQ(r, f) ({ \ typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \ \ spin_lock_irq(&(r)->consumer_lock); \ __PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \ spin_unlock_irq(&(r)->consumer_lock); \ __PTR_RING_PEEK_CALL_v; \ }) #define PTR_RING_PEEK_CALL_BH(r, f) ({ \ typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \ \ spin_lock_bh(&(r)->consumer_lock); \ __PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \ spin_unlock_bh(&(r)->consumer_lock); \ __PTR_RING_PEEK_CALL_v; \ }) #define PTR_RING_PEEK_CALL_ANY(r, f) ({ \ typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \ unsigned long __PTR_RING_PEEK_CALL_f;\ \ spin_lock_irqsave(&(r)->consumer_lock, __PTR_RING_PEEK_CALL_f); \ __PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \ spin_unlock_irqrestore(&(r)->consumer_lock, __PTR_RING_PEEK_CALL_f); \ __PTR_RING_PEEK_CALL_v; \ }) /* Not all gfp_t flags (besides GFP_KERNEL) are allowed. See * documentation for vmalloc for which of them are legal. */ static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp) { if (size > KMALLOC_MAX_SIZE / sizeof(void *)) return NULL; return kvmalloc_array(size, sizeof(void *), gfp | __GFP_ZERO); } static inline void __ptr_ring_set_size(struct ptr_ring *r, int size) { r->size = size; r->batch = SMP_CACHE_BYTES * 2 / sizeof(*(r->queue)); /* We need to set batch at least to 1 to make logic * in __ptr_ring_discard_one work correctly. * Batching too much (because ring is small) would cause a lot of * burstiness. Needs tuning, for now disable batching. */ if (r->batch > r->size / 2 || !r->batch) r->batch = 1; } static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp) { r->queue = __ptr_ring_init_queue_alloc(size, gfp); if (!r->queue) return -ENOMEM; __ptr_ring_set_size(r, size); r->producer = r->consumer_head = r->consumer_tail = 0; spin_lock_init(&r->producer_lock); spin_lock_init(&r->consumer_lock); return 0; } /* * Return entries into ring. Destroy entries that don't fit. * * Note: this is expected to be a rare slow path operation. * * Note: producer lock is nested within consumer lock, so if you * resize you must make sure all uses nest correctly. * In particular if you consume ring in interrupt or BH context, you must * disable interrupts/BH when doing so. */ static inline void ptr_ring_unconsume(struct ptr_ring *r, void **batch, int n, void (*destroy)(void *)) { unsigned long flags; int head; spin_lock_irqsave(&r->consumer_lock, flags); spin_lock(&r->producer_lock); if (!r->size) goto done; /* * Clean out buffered entries (for simplicity). This way following code * can test entries for NULL and if not assume they are valid. */ head = r->consumer_head - 1; while (likely(head >= r->consumer_tail)) r->queue[head--] = NULL; r->consumer_tail = r->consumer_head; /* * Go over entries in batch, start moving head back and copy entries. * Stop when we run into previously unconsumed entries. */ while (n) { head = r->consumer_head - 1; if (head < 0) head = r->size - 1; if (r->queue[head]) { /* This batch entry will have to be destroyed. */ goto done; } r->queue[head] = batch[--n]; r->consumer_tail = head; /* matching READ_ONCE in __ptr_ring_empty for lockless tests */ WRITE_ONCE(r->consumer_head, head); } done: /* Destroy all entries left in the batch. */ while (n) destroy(batch[--n]); spin_unlock(&r->producer_lock); spin_unlock_irqrestore(&r->consumer_lock, flags); } static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue, int size, gfp_t gfp, void (*destroy)(void *)) { int producer = 0; void **old; void *ptr; while ((ptr = __ptr_ring_consume(r))) if (producer < size) queue[producer++] = ptr; else if (destroy) destroy(ptr); if (producer >= size) producer = 0; __ptr_ring_set_size(r, size); r->producer = producer; r->consumer_head = 0; r->consumer_tail = 0; old = r->queue; r->queue = queue; return old; } /* * Note: producer lock is nested within consumer lock, so if you * resize you must make sure all uses nest correctly. * In particular if you consume ring in interrupt or BH context, you must * disable interrupts/BH when doing so. */ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, void (*destroy)(void *)) { unsigned long flags; void **queue = __ptr_ring_init_queue_alloc(size, gfp); void **old; if (!queue) return -ENOMEM; spin_lock_irqsave(&(r)->consumer_lock, flags); spin_lock(&(r)->producer_lock); old = __ptr_ring_swap_queue(r, queue, size, gfp, destroy); spin_unlock(&(r)->producer_lock); spin_unlock_irqrestore(&(r)->consumer_lock, flags); kvfree(old); return 0; } /* * Note: producer lock is nested within consumer lock, so if you * resize you must make sure all uses nest correctly. * In particular if you consume ring in interrupt or BH context, you must * disable interrupts/BH when doing so. */ static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, unsigned int nrings, int size, gfp_t gfp, void (*destroy)(void *)) { unsigned long flags; void ***queues; int i; queues = kmalloc_array(nrings, sizeof(*queues), gfp); if (!queues) goto noqueues; for (i = 0; i < nrings; ++i) { queues[i] = __ptr_ring_init_queue_alloc(size, gfp); if (!queues[i]) goto nomem; } for (i = 0; i < nrings; ++i) { spin_lock_irqsave(&(rings[i])->consumer_lock, flags); spin_lock(&(rings[i])->producer_lock); queues[i] = __ptr_ring_swap_queue(rings[i], queues[i], size, gfp, destroy); spin_unlock(&(rings[i])->producer_lock); spin_unlock_irqrestore(&(rings[i])->consumer_lock, flags); } for (i = 0; i < nrings; ++i) kvfree(queues[i]); kfree(queues); return 0; nomem: while (--i >= 0) kvfree(queues[i]); kfree(queues); noqueues: return -ENOMEM; } static inline void ptr_ring_cleanup(struct ptr_ring *r, void (*destroy)(void *)) { void *ptr; if (destroy) while ((ptr = ptr_ring_consume(r))) destroy(ptr); kvfree(r->queue); } #endif /* _LINUX_PTR_RING_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_LWTUNNEL_H #define __NET_LWTUNNEL_H 1 #include <linux/lwtunnel.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/types.h> #include <net/route.h> #define LWTUNNEL_HASH_BITS 7 #define LWTUNNEL_HASH_SIZE (1 << LWTUNNEL_HASH_BITS) /* lw tunnel state flags */ #define LWTUNNEL_STATE_OUTPUT_REDIRECT BIT(0) #define LWTUNNEL_STATE_INPUT_REDIRECT BIT(1) #define LWTUNNEL_STATE_XMIT_REDIRECT BIT(2) enum { LWTUNNEL_XMIT_DONE, LWTUNNEL_XMIT_CONTINUE, }; struct lwtunnel_state { __u16 type; __u16 flags; __u16 headroom; atomic_t refcnt; int (*orig_output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*orig_input)(struct sk_buff *); struct rcu_head rcu; __u8 data[]; }; struct lwtunnel_encap_ops { int (*build_state)(struct net *net, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack); void (*destroy_state)(struct lwtunnel_state *lws); int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*input)(struct sk_buff *skb); int (*fill_encap)(struct sk_buff *skb, struct lwtunnel_state *lwtstate); int (*get_encap_size)(struct lwtunnel_state *lwtstate); int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b); int (*xmit)(struct sk_buff *skb); struct module *owner; }; #ifdef CONFIG_LWTUNNEL void lwtstate_free(struct lwtunnel_state *lws); static inline struct lwtunnel_state * lwtstate_get(struct lwtunnel_state *lws) { if (lws) atomic_inc(&lws->refcnt); return lws; } static inline void lwtstate_put(struct lwtunnel_state *lws) { if (!lws) return; if (atomic_dec_and_test(&lws->refcnt)) lwtstate_free(lws); } static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate) { if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_OUTPUT_REDIRECT)) return true; return false; } static inline bool lwtunnel_input_redirect(struct lwtunnel_state *lwtstate) { if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_INPUT_REDIRECT)) return true; return false; } static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate) { if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_XMIT_REDIRECT)) return true; return false; } static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate, unsigned int mtu) { if ((lwtunnel_xmit_redirect(lwtstate) || lwtunnel_output_redirect(lwtstate)) && lwtstate->headroom < mtu) return lwtstate->headroom; return 0; } int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, unsigned int num); int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, unsigned int num); int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack); int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, struct netlink_ext_ack *extack); int lwtunnel_build_state(struct net *net, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **lws, struct netlink_ext_ack *extack); int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate, int encap_attr, int encap_type_attr); int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate); struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len); int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b); int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb); int lwtunnel_input(struct sk_buff *skb); int lwtunnel_xmit(struct sk_buff *skb); int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress); static inline void lwtunnel_set_redirect(struct dst_entry *dst) { if (lwtunnel_output_redirect(dst->lwtstate)) { dst->lwtstate->orig_output = dst->output; dst->output = lwtunnel_output; } if (lwtunnel_input_redirect(dst->lwtstate)) { dst->lwtstate->orig_input = dst->input; dst->input = lwtunnel_input; } } #else static inline void lwtstate_free(struct lwtunnel_state *lws) { } static inline struct lwtunnel_state * lwtstate_get(struct lwtunnel_state *lws) { return lws; } static inline void lwtstate_put(struct lwtunnel_state *lws) { } static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate) { return false; } static inline bool lwtunnel_input_redirect(struct lwtunnel_state *lwtstate) { return false; } static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate) { return false; } static inline void lwtunnel_set_redirect(struct dst_entry *dst) { } static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate, unsigned int mtu) { return 0; } static inline int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, unsigned int num) { return -EOPNOTSUPP; } static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, unsigned int num) { return -EOPNOTSUPP; } static inline int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "CONFIG_LWTUNNEL is not enabled in this kernel"); return -EOPNOTSUPP; } static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, struct netlink_ext_ack *extack) { /* return 0 since we are not walking attr looking for * RTA_ENCAP_TYPE attribute on nexthops. */ return 0; } static inline int lwtunnel_build_state(struct net *net, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **lws, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } static inline int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate, int encap_attr, int encap_type_attr) { return 0; } static inline int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate) { return 0; } static inline struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len) { return NULL; } static inline int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) { return 0; } static inline int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) { return -EOPNOTSUPP; } static inline int lwtunnel_input(struct sk_buff *skb) { return -EOPNOTSUPP; } static inline int lwtunnel_xmit(struct sk_buff *skb) { return -EOPNOTSUPP; } #endif /* CONFIG_LWTUNNEL */ #define MODULE_ALIAS_RTNL_LWT(encap_type) MODULE_ALIAS("rtnl-lwt-" __stringify(encap_type)) #endif /* __NET_LWTUNNEL_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_COMPAT_H #define _ASM_X86_COMPAT_H /* * Architecture specific compatibility types */ #include <linux/types.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <asm/processor.h> #include <asm/user32.h> #include <asm/unistd.h> #include <asm-generic/compat.h> #define COMPAT_USER_HZ 100 #define COMPAT_UTS_MACHINE "i686\0\0" typedef u16 __compat_uid_t; typedef u16 __compat_gid_t; typedef u32 __compat_uid32_t; typedef u32 __compat_gid32_t; typedef u16 compat_mode_t; typedef u16 compat_dev_t; typedef u16 compat_nlink_t; typedef u16 compat_ipc_pid_t; typedef u32 compat_caddr_t; typedef __kernel_fsid_t compat_fsid_t; struct compat_stat { compat_dev_t st_dev; u16 __pad1; compat_ino_t st_ino; compat_mode_t st_mode; compat_nlink_t st_nlink; __compat_uid_t st_uid; __compat_gid_t st_gid; compat_dev_t st_rdev; u16 __pad2; u32 st_size; u32 st_blksize; u32 st_blocks; u32 st_atime; u32 st_atime_nsec; u32 st_mtime; u32 st_mtime_nsec; u32 st_ctime; u32 st_ctime_nsec; u32 __unused4; u32 __unused5; }; struct compat_flock { short l_type; short l_whence; compat_off_t l_start; compat_off_t l_len; compat_pid_t l_pid; }; #define F_GETLK64 12 /* using 'struct flock64' */ #define F_SETLK64 13 #define F_SETLKW64 14 /* * IA32 uses 4 byte alignment for 64 bit quantities, * so we need to pack this structure. */ struct compat_flock64 { short l_type; short l_whence; compat_loff_t l_start; compat_loff_t l_len; compat_pid_t l_pid; } __attribute__((packed)); struct compat_statfs { int f_type; int f_bsize; int f_blocks; int f_bfree; int f_bavail; int f_files; int f_ffree; compat_fsid_t f_fsid; int f_namelen; /* SunOS ignores this field. */ int f_frsize; int f_flags; int f_spare[4]; }; #define COMPAT_RLIM_INFINITY 0xffffffff typedef u32 compat_old_sigset_t; /* at least 32 bits */ #define _COMPAT_NSIG 64 #define _COMPAT_NSIG_BPW 32 typedef u32 compat_sigset_word; #define COMPAT_OFF_T_MAX 0x7fffffff struct compat_ipc64_perm { compat_key_t key; __compat_uid32_t uid; __compat_gid32_t gid; __compat_uid32_t cuid; __compat_gid32_t cgid; unsigned short mode; unsigned short __pad1; unsigned short seq; unsigned short __pad2; compat_ulong_t unused1; compat_ulong_t unused2; }; struct compat_semid64_ds { struct compat_ipc64_perm sem_perm; compat_ulong_t sem_otime; compat_ulong_t sem_otime_high; compat_ulong_t sem_ctime; compat_ulong_t sem_ctime_high; compat_ulong_t sem_nsems; compat_ulong_t __unused3; compat_ulong_t __unused4; }; struct compat_msqid64_ds { struct compat_ipc64_perm msg_perm; compat_ulong_t msg_stime; compat_ulong_t msg_stime_high; compat_ulong_t msg_rtime; compat_ulong_t msg_rtime_high; compat_ulong_t msg_ctime; compat_ulong_t msg_ctime_high; compat_ulong_t msg_cbytes; compat_ulong_t msg_qnum; compat_ulong_t msg_qbytes; compat_pid_t msg_lspid; compat_pid_t msg_lrpid; compat_ulong_t __unused4; compat_ulong_t __unused5; }; struct compat_shmid64_ds { struct compat_ipc64_perm shm_perm; compat_size_t shm_segsz; compat_ulong_t shm_atime; compat_ulong_t shm_atime_high; compat_ulong_t shm_dtime; compat_ulong_t shm_dtime_high; compat_ulong_t shm_ctime; compat_ulong_t shm_ctime_high; compat_pid_t shm_cpid; compat_pid_t shm_lpid; compat_ulong_t shm_nattch; compat_ulong_t __unused4; compat_ulong_t __unused5; }; /* * The type of struct elf_prstatus.pr_reg in compatible core dumps. */ typedef struct user_regs_struct compat_elf_gregset_t; /* Full regset -- prstatus on x32, otherwise on ia32 */ #define PRSTATUS_SIZE(S, R) (R != sizeof(S.pr_reg) ? 144 : 296) #define SET_PR_FPVALID(S, V, R) \ do { *(int *) (((void *) &((S)->pr_reg)) + R) = (V); } \ while (0) #ifdef CONFIG_X86_X32_ABI #define COMPAT_USE_64BIT_TIME \ (!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)) #endif static inline void __user *arch_compat_alloc_user_space(long len) { compat_uptr_t sp; if (test_thread_flag(TIF_IA32)) { sp = task_pt_regs(current)->sp; } else { /* -128 for the x32 ABI redzone */ sp = task_pt_regs(current)->sp - 128; } return (void __user *)round_down(sp - len, 16); } static inline bool in_x32_syscall(void) { #ifdef CONFIG_X86_X32_ABI if (task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT) return true; #endif return false; } static inline bool in_32bit_syscall(void) { return in_ia32_syscall() || in_x32_syscall(); } #ifdef CONFIG_COMPAT static inline bool in_compat_syscall(void) { return in_32bit_syscall(); } #define in_compat_syscall in_compat_syscall /* override the generic impl */ #define compat_need_64bit_alignment_fixup in_ia32_syscall #endif struct compat_siginfo; #ifdef CONFIG_X86_X32_ABI int copy_siginfo_to_user32(struct compat_siginfo __user *to, const kernel_siginfo_t *from); #define copy_siginfo_to_user32 copy_siginfo_to_user32 #endif /* CONFIG_X86_X32_ABI */ #endif /* _ASM_X86_COMPAT_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MMU_CONTEXT_H #define _ASM_X86_MMU_CONTEXT_H #include <asm/desc.h> #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/pkeys.h> #include <trace/events/tlb.h> #include <asm/tlbflush.h> #include <asm/paravirt.h> #include <asm/debugreg.h> extern atomic64_t last_mm_ctx_id; #ifndef CONFIG_PARAVIRT_XXL static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) { } #endif /* !CONFIG_PARAVIRT_XXL */ #ifdef CONFIG_PERF_EVENTS DECLARE_STATIC_KEY_FALSE(rdpmc_never_available_key); DECLARE_STATIC_KEY_FALSE(rdpmc_always_available_key); void cr4_update_pce(void *ignored); #endif #ifdef CONFIG_MODIFY_LDT_SYSCALL /* * ldt_structs can be allocated, used, and freed, but they are never * modified while live. */ struct ldt_struct { /* * Xen requires page-aligned LDTs with special permissions. This is * needed to prevent us from installing evil descriptors such as * call gates. On native, we could merge the ldt_struct and LDT * allocations, but it's not worth trying to optimize. */ struct desc_struct *entries; unsigned int nr_entries; /* * If PTI is in use, then the entries array is not mapped while we're * in user mode. The whole array will be aliased at the addressed * given by ldt_slot_va(slot). We use two slots so that we can allocate * and map, and enable a new LDT without invalidating the mapping * of an older, still-in-use LDT. * * slot will be -1 if this LDT doesn't have an alias mapping. */ int slot; }; /* * Used for LDT copy/destruction. */ static inline void init_new_context_ldt(struct mm_struct *mm) { mm->context.ldt = NULL; init_rwsem(&mm->context.ldt_usr_sem); } int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm); void destroy_context_ldt(struct mm_struct *mm); void ldt_arch_exit_mmap(struct mm_struct *mm); #else /* CONFIG_MODIFY_LDT_SYSCALL */ static inline void init_new_context_ldt(struct mm_struct *mm) { } static inline int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm) { return 0; } static inline void destroy_context_ldt(struct mm_struct *mm) { } static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { } #endif #ifdef CONFIG_MODIFY_LDT_SYSCALL extern void load_mm_ldt(struct mm_struct *mm); extern void switch_ldt(struct mm_struct *prev, struct mm_struct *next); #else static inline void load_mm_ldt(struct mm_struct *mm) { clear_LDT(); } static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) { DEBUG_LOCKS_WARN_ON(preemptible()); } #endif extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); /* * Init a new mm. Used on mm copies, like at fork() * and on mm's that are brand-new, like at execve(). */ static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { mutex_init(&mm->context.lock); mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); atomic64_set(&mm->context.tlb_gen, 0); #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { /* pkey 0 is the default and allocated implicitly */ mm->context.pkey_allocation_map = 0x1; /* -1 means unallocated or invalid */ mm->context.execute_only_pkey = -1; } #endif init_new_context_ldt(mm); return 0; } static inline void destroy_context(struct mm_struct *mm) { destroy_context_ldt(mm); } extern void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk); extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk); #define switch_mm_irqs_off switch_mm_irqs_off #define activate_mm(prev, next) \ do { \ paravirt_activate_mm((prev), (next)); \ switch_mm((prev), (next), NULL); \ } while (0); #ifdef CONFIG_X86_32 #define deactivate_mm(tsk, mm) \ do { \ lazy_load_gs(0); \ } while (0) #else #define deactivate_mm(tsk, mm) \ do { \ load_gs_index(0); \ loadsegment(fs, 0); \ } while (0) #endif static inline void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm) { #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; /* Duplicate the oldmm pkey state in mm: */ mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map; mm->context.execute_only_pkey = oldmm->context.execute_only_pkey; #endif } static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { arch_dup_pkeys(oldmm, mm); paravirt_arch_dup_mmap(oldmm, mm); return ldt_dup_context(oldmm, mm); } static inline void arch_exit_mmap(struct mm_struct *mm) { paravirt_arch_exit_mmap(mm); ldt_arch_exit_mmap(mm); } #ifdef CONFIG_X86_64 static inline bool is_64bit_mm(struct mm_struct *mm) { return !IS_ENABLED(CONFIG_IA32_EMULATION) || !(mm->context.ia32_compat == TIF_IA32); } #else static inline bool is_64bit_mm(struct mm_struct *mm) { return false; } #endif static inline void arch_unmap(struct mm_struct *mm, unsigned long start, unsigned long end) { } /* * We only want to enforce protection keys on the current process * because we effectively have no access to PKRU for other * processes or any way to tell *which * PKRU in a threaded * process we could use. * * So do not enforce things if the VMA is not from the current * mm, or if we are in a kernel thread. */ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, bool execute, bool foreign) { /* pkeys never affect instruction fetches */ if (execute) return true; /* allow access if the VMA is not one from this process */ if (foreign || vma_is_foreign(vma)) return true; return __pkru_allows_pkey(vma_pkey(vma), write); } unsigned long __get_current_cr3_fast(void); #endif /* _ASM_X86_MMU_CONTEXT_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ #ifndef _NET_IPV6_H #define _NET_IPV6_H #include <linux/ipv6.h> #include <linux/hardirq.h> #include <linux/jhash.h> #include <linux/refcount.h> #include <linux/jump_label_ratelimit.h> #include <net/if_inet6.h> #include <net/ndisc.h> #include <net/flow.h> #include <net/flow_dissector.h> #include <net/snmp.h> #include <net/netns/hash.h> #define SIN6_LEN_RFC2133 24 #define IPV6_MAXPLEN 65535 /* * NextHeader field of IPv6 header */ #define NEXTHDR_HOP 0 /* Hop-by-hop option header. */ #define NEXTHDR_TCP 6 /* TCP segment. */ #define NEXTHDR_UDP 17 /* UDP message. */ #define NEXTHDR_IPV6 41 /* IPv6 in IPv6 */ #define NEXTHDR_ROUTING 43 /* Routing header. */ #define NEXTHDR_FRAGMENT 44 /* Fragmentation/reassembly header. */ #define NEXTHDR_GRE 47 /* GRE header. */ #define NEXTHDR_ESP 50 /* Encapsulating security payload. */ #define NEXTHDR_AUTH 51 /* Authentication header. */ #define NEXTHDR_ICMP 58 /* ICMP for IPv6. */ #define NEXTHDR_NONE 59 /* No next header */ #define NEXTHDR_DEST 60 /* Destination options header. */ #define NEXTHDR_SCTP 132 /* SCTP message. */ #define NEXTHDR_MOBILITY 135 /* Mobility header. */ #define NEXTHDR_MAX 255 #define IPV6_DEFAULT_HOPLIMIT 64 #define IPV6_DEFAULT_MCASTHOPS 1 /* Limits on Hop-by-Hop and Destination options. * * Per RFC8200 there is no limit on the maximum number or lengths of options in * Hop-by-Hop or Destination options other then the packet must fit in an MTU. * We allow configurable limits in order to mitigate potential denial of * service attacks. * * There are three limits that may be set: * - Limit the number of options in a Hop-by-Hop or Destination options * extension header * - Limit the byte length of a Hop-by-Hop or Destination options extension * header * - Disallow unknown options * * The limits are expressed in corresponding sysctls: * * ipv6.sysctl.max_dst_opts_cnt * ipv6.sysctl.max_hbh_opts_cnt * ipv6.sysctl.max_dst_opts_len * ipv6.sysctl.max_hbh_opts_len * * max_*_opts_cnt is the number of TLVs that are allowed for Destination * options or Hop-by-Hop options. If the number is less than zero then unknown * TLVs are disallowed and the number of known options that are allowed is the * absolute value. Setting the value to INT_MAX indicates no limit. * * max_*_opts_len is the length limit in bytes of a Destination or * Hop-by-Hop options extension header. Setting the value to INT_MAX * indicates no length limit. * * If a limit is exceeded when processing an extension header the packet is * silently discarded. */ /* Default limits for Hop-by-Hop and Destination options */ #define IP6_DEFAULT_MAX_DST_OPTS_CNT 8 #define IP6_DEFAULT_MAX_HBH_OPTS_CNT 8 #define IP6_DEFAULT_MAX_DST_OPTS_LEN INT_MAX /* No limit */ #define IP6_DEFAULT_MAX_HBH_OPTS_LEN INT_MAX /* No limit */ /* * Addr type * * type - unicast | multicast * scope - local | site | global * v4 - compat * v4mapped * any * loopback */ #define IPV6_ADDR_ANY 0x0000U #define IPV6_ADDR_UNICAST 0x0001U #define IPV6_ADDR_MULTICAST 0x0002U #define IPV6_ADDR_LOOPBACK 0x0010U #define IPV6_ADDR_LINKLOCAL 0x0020U #define IPV6_ADDR_SITELOCAL 0x0040U #define IPV6_ADDR_COMPATv4 0x0080U #define IPV6_ADDR_SCOPE_MASK 0x00f0U #define IPV6_ADDR_MAPPED 0x1000U /* * Addr scopes */ #define IPV6_ADDR_MC_SCOPE(a) \ ((a)->s6_addr[1] & 0x0f) /* nonstandard */ #define __IPV6_ADDR_SCOPE_INVALID -1 #define IPV6_ADDR_SCOPE_NODELOCAL 0x01 #define IPV6_ADDR_SCOPE_LINKLOCAL 0x02 #define IPV6_ADDR_SCOPE_SITELOCAL 0x05 #define IPV6_ADDR_SCOPE_ORGLOCAL 0x08 #define IPV6_ADDR_SCOPE_GLOBAL 0x0e /* * Addr flags */ #define IPV6_ADDR_MC_FLAG_TRANSIENT(a) \ ((a)->s6_addr[1] & 0x10) #define IPV6_ADDR_MC_FLAG_PREFIX(a) \ ((a)->s6_addr[1] & 0x20) #define IPV6_ADDR_MC_FLAG_RENDEZVOUS(a) \ ((a)->s6_addr[1] & 0x40) /* * fragmentation header */ struct frag_hdr { __u8 nexthdr; __u8 reserved; __be16 frag_off; __be32 identification; }; #define IP6_MF 0x0001 #define IP6_OFFSET 0xFFF8 struct ip6_fraglist_iter { struct ipv6hdr *tmp_hdr; struct sk_buff *frag; int offset; unsigned int hlen; __be32 frag_id; u8 nexthdr; }; int ip6_fraglist_init(struct sk_buff *skb, unsigned int hlen, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_fraglist_iter *iter); void ip6_fraglist_prepare(struct sk_buff *skb, struct ip6_fraglist_iter *iter); static inline struct sk_buff *ip6_fraglist_next(struct ip6_fraglist_iter *iter) { struct sk_buff *skb = iter->frag; iter->frag = skb->next; skb_mark_not_on_list(skb); return skb; } struct ip6_frag_state { u8 *prevhdr; unsigned int hlen; unsigned int mtu; unsigned int left; int offset; int ptr; int hroom; int troom; __be32 frag_id; u8 nexthdr; }; void ip6_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int mtu, unsigned short needed_tailroom, int hdr_room, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_frag_state *state); struct sk_buff *ip6_frag_next(struct sk_buff *skb, struct ip6_frag_state *state); #define IP6_REPLY_MARK(net, mark) \ ((net)->ipv6.sysctl.fwmark_reflect ? (mark) : 0) #include <net/sock.h> /* sysctls */ extern int sysctl_mld_max_msf; extern int sysctl_mld_qrv; #define _DEVINC(net, statname, mod, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ mod##SNMP_INC_STATS64((_idev)->stats.statname, (field));\ mod##SNMP_INC_STATS64((net)->mib.statname##_statistics, (field));\ }) /* per device counters are atomic_long_t */ #define _DEVINCATOMIC(net, statname, mod, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \ mod##SNMP_INC_STATS((net)->mib.statname##_statistics, (field));\ }) /* per device and per net counters are atomic_long_t */ #define _DEVINC_ATOMIC_ATOMIC(net, statname, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \ SNMP_INC_STATS_ATOMIC_LONG((net)->mib.statname##_statistics, (field));\ }) #define _DEVADD(net, statname, mod, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ mod##SNMP_ADD_STATS((_idev)->stats.statname, (field), (val)); \ mod##SNMP_ADD_STATS((net)->mib.statname##_statistics, (field), (val));\ }) #define _DEVUPD(net, statname, mod, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ mod##SNMP_UPD_PO_STATS((_idev)->stats.statname, field, (val)); \ mod##SNMP_UPD_PO_STATS((net)->mib.statname##_statistics, field, (val));\ }) /* MIBs */ #define IP6_INC_STATS(net, idev,field) \ _DEVINC(net, ipv6, , idev, field) #define __IP6_INC_STATS(net, idev,field) \ _DEVINC(net, ipv6, __, idev, field) #define IP6_ADD_STATS(net, idev,field,val) \ _DEVADD(net, ipv6, , idev, field, val) #define __IP6_ADD_STATS(net, idev,field,val) \ _DEVADD(net, ipv6, __, idev, field, val) #define IP6_UPD_PO_STATS(net, idev,field,val) \ _DEVUPD(net, ipv6, , idev, field, val) #define __IP6_UPD_PO_STATS(net, idev,field,val) \ _DEVUPD(net, ipv6, __, idev, field, val) #define ICMP6_INC_STATS(net, idev, field) \ _DEVINCATOMIC(net, icmpv6, , idev, field) #define __ICMP6_INC_STATS(net, idev, field) \ _DEVINCATOMIC(net, icmpv6, __, idev, field) #define ICMP6MSGOUT_INC_STATS(net, idev, field) \ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field +256) #define ICMP6MSGIN_INC_STATS(net, idev, field) \ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field) struct ip6_ra_chain { struct ip6_ra_chain *next; struct sock *sk; int sel; void (*destructor)(struct sock *); }; extern struct ip6_ra_chain *ip6_ra_chain; extern rwlock_t ip6_ra_lock; /* This structure is prepared by protocol, when parsing ancillary data and passed to IPv6. */ struct ipv6_txoptions { refcount_t refcnt; /* Length of this structure */ int tot_len; /* length of extension headers */ __u16 opt_flen; /* after fragment hdr */ __u16 opt_nflen; /* before fragment hdr */ struct ipv6_opt_hdr *hopopt; struct ipv6_opt_hdr *dst0opt; struct ipv6_rt_hdr *srcrt; /* Routing Header */ struct ipv6_opt_hdr *dst1opt; struct rcu_head rcu; /* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */ }; /* flowlabel_reflect sysctl values */ enum flowlabel_reflect { FLOWLABEL_REFLECT_ESTABLISHED = 1, FLOWLABEL_REFLECT_TCP_RESET = 2, FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES = 4, }; struct ip6_flowlabel { struct ip6_flowlabel __rcu *next; __be32 label; atomic_t users; struct in6_addr dst; struct ipv6_txoptions *opt; unsigned long linger; struct rcu_head rcu; u8 share; union { struct pid *pid; kuid_t uid; } owner; unsigned long lastuse; unsigned long expires; struct net *fl_net; }; #define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF) #define IPV6_FLOWLABEL_MASK cpu_to_be32(0x000FFFFF) #define IPV6_FLOWLABEL_STATELESS_FLAG cpu_to_be32(0x00080000) #define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK) #define IPV6_TCLASS_SHIFT 20 struct ipv6_fl_socklist { struct ipv6_fl_socklist __rcu *next; struct ip6_flowlabel *fl; struct rcu_head rcu; }; struct ipcm6_cookie { struct sockcm_cookie sockc; __s16 hlimit; __s16 tclass; __s8 dontfrag; struct ipv6_txoptions *opt; __u16 gso_size; }; static inline void ipcm6_init(struct ipcm6_cookie *ipc6) { *ipc6 = (struct ipcm6_cookie) { .hlimit = -1, .tclass = -1, .dontfrag = -1, }; } static inline void ipcm6_init_sk(struct ipcm6_cookie *ipc6, const struct ipv6_pinfo *np) { *ipc6 = (struct ipcm6_cookie) { .hlimit = -1, .tclass = np->tclass, .dontfrag = np->dontfrag, }; } static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) { struct ipv6_txoptions *opt; rcu_read_lock(); opt = rcu_dereference(np->opt); if (opt) { if (!refcount_inc_not_zero(&opt->refcnt)) opt = NULL; else opt = rcu_pointer_handoff(opt); } rcu_read_unlock(); return opt; } static inline void txopt_put(struct ipv6_txoptions *opt) { if (opt && refcount_dec_and_test(&opt->refcnt)) kfree_rcu(opt, rcu); } struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label); extern struct static_key_false_deferred ipv6_flowlabel_exclusive; static inline struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label) { if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key)) return __fl6_sock_lookup(sk, label) ? : ERR_PTR(-ENOENT); return NULL; } struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, struct ip6_flowlabel *fl, struct ipv6_txoptions *fopt); void fl6_free_socklist(struct sock *sk); int ipv6_flowlabel_opt(struct sock *sk, sockptr_t optval, int optlen); int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq, int flags); int ip6_flowlabel_init(void); void ip6_flowlabel_cleanup(void); bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np); static inline void fl6_sock_release(struct ip6_flowlabel *fl) { if (fl) atomic_dec(&fl->users); } void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info); void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len); int ip6_ra_control(struct sock *sk, int sel); int ipv6_parse_hopopts(struct sk_buff *skb); struct ipv6_txoptions *ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt); struct ipv6_txoptions *ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, int newtype, struct ipv6_opt_hdr *newopt); struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt); bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, const struct inet6_skb_parm *opt); struct ipv6_txoptions *ipv6_update_options(struct sock *sk, struct ipv6_txoptions *opt); static inline bool ipv6_accept_ra(struct inet6_dev *idev) { /* If forwarding is enabled, RA are not accepted unless the special * hybrid mode (accept_ra=2) is enabled. */ return idev->cnf.forwarding ? idev->cnf.accept_ra == 2 : idev->cnf.accept_ra; } #define IPV6_FRAG_HIGH_THRESH (4 * 1024*1024) /* 4194304 */ #define IPV6_FRAG_LOW_THRESH (3 * 1024*1024) /* 3145728 */ #define IPV6_FRAG_TIMEOUT (60 * HZ) /* 60 seconds */ int __ipv6_addr_type(const struct in6_addr *addr); static inline int ipv6_addr_type(const struct in6_addr *addr) { return __ipv6_addr_type(addr) & 0xffff; } static inline int ipv6_addr_scope(const struct in6_addr *addr) { return __ipv6_addr_type(addr) & IPV6_ADDR_SCOPE_MASK; } static inline int __ipv6_addr_src_scope(int type) { return (type == IPV6_ADDR_ANY) ? __IPV6_ADDR_SCOPE_INVALID : (type >> 16); } static inline int ipv6_addr_src_scope(const struct in6_addr *addr) { return __ipv6_addr_src_scope(__ipv6_addr_type(addr)); } static inline bool __ipv6_addr_needs_scope_id(int type) { return type & IPV6_ADDR_LINKLOCAL || (type & IPV6_ADDR_MULTICAST && (type & (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL))); } static inline __u32 ipv6_iface_scope_id(const struct in6_addr *addr, int iface) { return __ipv6_addr_needs_scope_id(__ipv6_addr_type(addr)) ? iface : 0; } static inline int ipv6_addr_cmp(const struct in6_addr *a1, const struct in6_addr *a2) { return memcmp(a1, a2, sizeof(struct in6_addr)); } static inline bool ipv6_masked_addr_cmp(const struct in6_addr *a1, const struct in6_addr *m, const struct in6_addr *a2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul1 = (const unsigned long *)a1; const unsigned long *ulm = (const unsigned long *)m; const unsigned long *ul2 = (const unsigned long *)a2; return !!(((ul1[0] ^ ul2[0]) & ulm[0]) | ((ul1[1] ^ ul2[1]) & ulm[1])); #else return !!(((a1->s6_addr32[0] ^ a2->s6_addr32[0]) & m->s6_addr32[0]) | ((a1->s6_addr32[1] ^ a2->s6_addr32[1]) & m->s6_addr32[1]) | ((a1->s6_addr32[2] ^ a2->s6_addr32[2]) & m->s6_addr32[2]) | ((a1->s6_addr32[3] ^ a2->s6_addr32[3]) & m->s6_addr32[3])); #endif } static inline void ipv6_addr_prefix(struct in6_addr *pfx, const struct in6_addr *addr, int plen) { /* caller must guarantee 0 <= plen <= 128 */ int o = plen >> 3, b = plen & 0x7; memset(pfx->s6_addr, 0, sizeof(pfx->s6_addr)); memcpy(pfx->s6_addr, addr, o); if (b != 0) pfx->s6_addr[o] = addr->s6_addr[o] & (0xff00 >> b); } static inline void ipv6_addr_prefix_copy(struct in6_addr *addr, const struct in6_addr *pfx, int plen) { /* caller must guarantee 0 <= plen <= 128 */ int o = plen >> 3, b = plen & 0x7; memcpy(addr->s6_addr, pfx, o); if (b != 0) { addr->s6_addr[o] &= ~(0xff00 >> b); addr->s6_addr[o] |= (pfx->s6_addr[o] & (0xff00 >> b)); } } static inline void __ipv6_addr_set_half(__be32 *addr, __be32 wh, __be32 wl) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 #if defined(__BIG_ENDIAN) if (__builtin_constant_p(wh) && __builtin_constant_p(wl)) { *(__force u64 *)addr = ((__force u64)(wh) << 32 | (__force u64)(wl)); return; } #elif defined(__LITTLE_ENDIAN) if (__builtin_constant_p(wl) && __builtin_constant_p(wh)) { *(__force u64 *)addr = ((__force u64)(wl) << 32 | (__force u64)(wh)); return; } #endif #endif addr[0] = wh; addr[1] = wl; } static inline void ipv6_addr_set(struct in6_addr *addr, __be32 w1, __be32 w2, __be32 w3, __be32 w4) { __ipv6_addr_set_half(&addr->s6_addr32[0], w1, w2); __ipv6_addr_set_half(&addr->s6_addr32[2], w3, w4); } static inline bool ipv6_addr_equal(const struct in6_addr *a1, const struct in6_addr *a2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul1 = (const unsigned long *)a1; const unsigned long *ul2 = (const unsigned long *)a2; return ((ul1[0] ^ ul2[0]) | (ul1[1] ^ ul2[1])) == 0UL; #else return ((a1->s6_addr32[0] ^ a2->s6_addr32[0]) | (a1->s6_addr32[1] ^ a2->s6_addr32[1]) | (a1->s6_addr32[2] ^ a2->s6_addr32[2]) | (a1->s6_addr32[3] ^ a2->s6_addr32[3])) == 0; #endif } #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 static inline bool __ipv6_prefix_equal64_half(const __be64 *a1, const __be64 *a2, unsigned int len) { if (len && ((*a1 ^ *a2) & cpu_to_be64((~0UL) << (64 - len)))) return false; return true; } static inline bool ipv6_prefix_equal(const struct in6_addr *addr1, const struct in6_addr *addr2, unsigned int prefixlen) { const __be64 *a1 = (const __be64 *)addr1; const __be64 *a2 = (const __be64 *)addr2; if (prefixlen >= 64) { if (a1[0] ^ a2[0]) return false; return __ipv6_prefix_equal64_half(a1 + 1, a2 + 1, prefixlen - 64); } return __ipv6_prefix_equal64_half(a1, a2, prefixlen); } #else static inline bool ipv6_prefix_equal(const struct in6_addr *addr1, const struct in6_addr *addr2, unsigned int prefixlen) { const __be32 *a1 = addr1->s6_addr32; const __be32 *a2 = addr2->s6_addr32; unsigned int pdw, pbi; /* check complete u32 in prefix */ pdw = prefixlen >> 5; if (pdw && memcmp(a1, a2, pdw << 2)) return false; /* check incomplete u32 in prefix */ pbi = prefixlen & 0x1f; if (pbi && ((a1[pdw] ^ a2[pdw]) & htonl((0xffffffff) << (32 - pbi)))) return false; return true; } #endif static inline bool ipv6_addr_any(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul = (const unsigned long *)a; return (ul[0] | ul[1]) == 0UL; #else return (a->s6_addr32[0] | a->s6_addr32[1] | a->s6_addr32[2] | a->s6_addr32[3]) == 0; #endif } static inline u32 ipv6_addr_hash(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul = (const unsigned long *)a; unsigned long x = ul[0] ^ ul[1]; return (u32)(x ^ (x >> 32)); #else return (__force u32)(a->s6_addr32[0] ^ a->s6_addr32[1] ^ a->s6_addr32[2] ^ a->s6_addr32[3]); #endif } /* more secured version of ipv6_addr_hash() */ static inline u32 __ipv6_addr_jhash(const struct in6_addr *a, const u32 initval) { u32 v = (__force u32)a->s6_addr32[0] ^ (__force u32)a->s6_addr32[1]; return jhash_3words(v, (__force u32)a->s6_addr32[2], (__force u32)a->s6_addr32[3], initval); } static inline bool ipv6_addr_loopback(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const __be64 *be = (const __be64 *)a; return (be[0] | (be[1] ^ cpu_to_be64(1))) == 0UL; #else return (a->s6_addr32[0] | a->s6_addr32[1] | a->s6_addr32[2] | (a->s6_addr32[3] ^ cpu_to_be32(1))) == 0; #endif } /* * Note that we must __force cast these to unsigned long to make sparse happy, * since all of the endian-annotated types are fixed size regardless of arch. */ static inline bool ipv6_addr_v4mapped(const struct in6_addr *a) { return ( #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 *(unsigned long *)a | #else (__force unsigned long)(a->s6_addr32[0] | a->s6_addr32[1]) | #endif (__force unsigned long)(a->s6_addr32[2] ^ cpu_to_be32(0x0000ffff))) == 0UL; } static inline bool ipv6_addr_v4mapped_loopback(const struct in6_addr *a) { return ipv6_addr_v4mapped(a) && ipv4_is_loopback(a->s6_addr32[3]); } static inline u32 ipv6_portaddr_hash(const struct net *net, const struct in6_addr *addr6, unsigned int port) { unsigned int hash, mix = net_hash_mix(net); if (ipv6_addr_any(addr6)) hash = jhash_1word(0, mix); else if (ipv6_addr_v4mapped(addr6)) hash = jhash_1word((__force u32)addr6->s6_addr32[3], mix); else hash = jhash2((__force u32 *)addr6->s6_addr32, 4, mix); return hash ^ port; } /* * Check for a RFC 4843 ORCHID address * (Overlay Routable Cryptographic Hash Identifiers) */ static inline bool ipv6_addr_orchid(const struct in6_addr *a) { return (a->s6_addr32[0] & htonl(0xfffffff0)) == htonl(0x20010010); } static inline bool ipv6_addr_is_multicast(const struct in6_addr *addr) { return (addr->s6_addr32[0] & htonl(0xFF000000)) == htonl(0xFF000000); } static inline void ipv6_addr_set_v4mapped(const __be32 addr, struct in6_addr *v4mapped) { ipv6_addr_set(v4mapped, 0, 0, htonl(0x0000FFFF), addr); } /* * find the first different bit between two addresses * length of address must be a multiple of 32bits */ static inline int __ipv6_addr_diff32(const void *token1, const void *token2, int addrlen) { const __be32 *a1 = token1, *a2 = token2; int i; addrlen >>= 2; for (i = 0; i < addrlen; i++) { __be32 xb = a1[i] ^ a2[i]; if (xb) return i * 32 + 31 - __fls(ntohl(xb)); } /* * we should *never* get to this point since that * would mean the addrs are equal * * However, we do get to it 8) And exacly, when * addresses are equal 8) * * ip route add 1111::/128 via ... * ip route add 1111::/64 via ... * and we are here. * * Ideally, this function should stop comparison * at prefix length. It does not, but it is still OK, * if returned value is greater than prefix length. * --ANK (980803) */ return addrlen << 5; } #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 static inline int __ipv6_addr_diff64(const void *token1, const void *token2, int addrlen) { const __be64 *a1 = token1, *a2 = token2; int i; addrlen >>= 3; for (i = 0; i < addrlen; i++) { __be64 xb = a1[i] ^ a2[i]; if (xb) return i * 64 + 63 - __fls(be64_to_cpu(xb)); } return addrlen << 6; } #endif static inline int __ipv6_addr_diff(const void *token1, const void *token2, int addrlen) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 if (__builtin_constant_p(addrlen) && !(addrlen & 7)) return __ipv6_addr_diff64(token1, token2, addrlen); #endif return __ipv6_addr_diff32(token1, token2, addrlen); } static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_addr *a2) { return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr)); } __be32 ipv6_select_ident(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr); __be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb); int ip6_dst_hoplimit(struct dst_entry *dst); static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6, struct dst_entry *dst) { int hlimit; if (ipv6_addr_is_multicast(&fl6->daddr)) hlimit = np->mcast_hops; else hlimit = np->hop_limit; if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); return hlimit; } /* copy IPv6 saddr & daddr to flow_keys, possibly using 64bit load/store * Equivalent to : flow->v6addrs.src = iph->saddr; * flow->v6addrs.dst = iph->daddr; */ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow, const struct ipv6hdr *iph) { BUILD_BUG_ON(offsetof(typeof(flow->addrs), v6addrs.dst) != offsetof(typeof(flow->addrs), v6addrs.src) + sizeof(flow->addrs.v6addrs.src)); memcpy(&flow->addrs.v6addrs, &iph->saddr, sizeof(flow->addrs.v6addrs)); flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } #if IS_ENABLED(CONFIG_IPV6) static inline bool ipv6_can_nonlocal_bind(struct net *net, struct inet_sock *inet) { return net->ipv6.sysctl.ip_nonlocal_bind || inet->freebind || inet->transparent; } /* Sysctl settings for net ipv6.auto_flowlabels */ #define IP6_AUTO_FLOW_LABEL_OFF 0 #define IP6_AUTO_FLOW_LABEL_OPTOUT 1 #define IP6_AUTO_FLOW_LABEL_OPTIN 2 #define IP6_AUTO_FLOW_LABEL_FORCED 3 #define IP6_AUTO_FLOW_LABEL_MAX IP6_AUTO_FLOW_LABEL_FORCED #define IP6_DEFAULT_AUTO_FLOW_LABELS IP6_AUTO_FLOW_LABEL_OPTOUT static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, __be32 flowlabel, bool autolabel, struct flowi6 *fl6) { u32 hash; /* @flowlabel may include more than a flow label, eg, the traffic class. * Here we want only the flow label value. */ flowlabel &= IPV6_FLOWLABEL_MASK; if (flowlabel || net->ipv6.sysctl.auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF || (!autolabel && net->ipv6.sysctl.auto_flowlabels != IP6_AUTO_FLOW_LABEL_FORCED)) return flowlabel; hash = skb_get_hash_flowi6(skb, fl6); /* Since this is being sent on the wire obfuscate hash a bit * to minimize possbility that any useful information to an * attacker is leaked. Only lower 20 bits are relevant. */ hash = rol32(hash, 16); flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; if (net->ipv6.sysctl.flowlabel_state_ranges) flowlabel |= IPV6_FLOWLABEL_STATELESS_FLAG; return flowlabel; } static inline int ip6_default_np_autolabel(struct net *net) { switch (net->ipv6.sysctl.auto_flowlabels) { case IP6_AUTO_FLOW_LABEL_OFF: case IP6_AUTO_FLOW_LABEL_OPTIN: default: return 0; case IP6_AUTO_FLOW_LABEL_OPTOUT: case IP6_AUTO_FLOW_LABEL_FORCED: return 1; } } #else static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, __be32 flowlabel, bool autolabel, struct flowi6 *fl6) { return flowlabel; } static inline int ip6_default_np_autolabel(struct net *net) { return 0; } #endif #if IS_ENABLED(CONFIG_IPV6) static inline int ip6_multipath_hash_policy(const struct net *net) { return net->ipv6.sysctl.multipath_hash_policy; } #else static inline int ip6_multipath_hash_policy(const struct net *net) { return 0; } #endif /* * Header manipulation */ static inline void ip6_flow_hdr(struct ipv6hdr *hdr, unsigned int tclass, __be32 flowlabel) { *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | flowlabel; } static inline __be32 ip6_flowinfo(const struct ipv6hdr *hdr) { return *(__be32 *)hdr & IPV6_FLOWINFO_MASK; } static inline __be32 ip6_flowlabel(const struct ipv6hdr *hdr) { return *(__be32 *)hdr & IPV6_FLOWLABEL_MASK; } static inline u8 ip6_tclass(__be32 flowinfo) { return ntohl(flowinfo & IPV6_TCLASS_MASK) >> IPV6_TCLASS_SHIFT; } static inline __be32 ip6_make_flowinfo(unsigned int tclass, __be32 flowlabel) { return htonl(tclass << IPV6_TCLASS_SHIFT) | flowlabel; } static inline __be32 flowi6_get_flowlabel(const struct flowi6 *fl6) { return fl6->flowlabel & IPV6_FLOWLABEL_MASK; } /* * Prototypes exported by ipv6 */ /* * rcv function (called from netdevice level) */ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); void ipv6_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *orig_dev); int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb); /* * upper-layer output functions */ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr); int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags); int ip6_push_pending_frames(struct sock *sk); void ip6_flush_pending_frames(struct sock *sk); int ip6_send_skb(struct sk_buff *skb); struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork, struct inet6_cork *v6_cork); struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork); static inline struct sk_buff *ip6_finish_skb(struct sock *sk) { return __ip6_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork, &inet6_sk(sk)->cork); } int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst, bool connected); struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb, struct net_device *dev, struct net *net, struct socket *sock, struct in6_addr *saddr, const struct ip_tunnel_info *info, u8 protocol, bool use_cache); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *orig_dst); /* * skb processing functions */ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr, bool have_final); int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); /* * Extension header (options) processing */ void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto, struct in6_addr **daddr_p, struct in6_addr *saddr); void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto); int ipv6_skip_exthdr(const struct sk_buff *, int start, u8 *nexthdrp, __be16 *frag_offp); bool ipv6_ext_hdr(u8 nexthdr); enum { IP6_FH_F_FRAG = (1 << 0), IP6_FH_F_AUTH = (1 << 1), IP6_FH_F_SKIP_RH = (1 << 2), }; /* find specified header and get offset to it */ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, int target, unsigned short *fragoff, int *fragflg); int ipv6_find_tlv(const struct sk_buff *skb, int offset, int type); struct in6_addr *fl6_update_dst(struct flowi6 *fl6, const struct ipv6_txoptions *opt, struct in6_addr *orig); /* * socket options (ipv6_sockglue.c) */ int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int __ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr); void ip6_datagram_release_cb(struct sock *sk); int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,