b.liu | e958203 | 2025-04-17 19:18:16 +0800 | [diff] [blame] | 1 | // SPDX-License-Identifier: GPL-2.0-only |
| 2 | /* |
| 3 | * Common framework for low-level network console, dump, and debugger code |
| 4 | * |
| 5 | * Sep 8 2003 Matt Mackall <mpm@selenic.com> |
| 6 | * |
| 7 | * based on the netconsole code from: |
| 8 | * |
| 9 | * Copyright (C) 2001 Ingo Molnar <mingo@redhat.com> |
| 10 | * Copyright (C) 2002 Red Hat, Inc. |
| 11 | */ |
| 12 | |
| 13 | #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt |
| 14 | |
| 15 | #include <linux/moduleparam.h> |
| 16 | #include <linux/kernel.h> |
| 17 | #include <linux/netdevice.h> |
| 18 | #include <linux/etherdevice.h> |
| 19 | #include <linux/string.h> |
| 20 | #include <linux/if_arp.h> |
| 21 | #include <linux/inetdevice.h> |
| 22 | #include <linux/inet.h> |
| 23 | #include <linux/interrupt.h> |
| 24 | #include <linux/netpoll.h> |
| 25 | #include <linux/sched.h> |
| 26 | #include <linux/delay.h> |
| 27 | #include <linux/rcupdate.h> |
| 28 | #include <linux/workqueue.h> |
| 29 | #include <linux/slab.h> |
| 30 | #include <linux/export.h> |
| 31 | #include <linux/if_vlan.h> |
| 32 | #include <net/dsa.h> |
| 33 | #include <net/tcp.h> |
| 34 | #include <net/udp.h> |
| 35 | #include <net/addrconf.h> |
| 36 | #include <net/ndisc.h> |
| 37 | #include <net/ip6_checksum.h> |
| 38 | #include <asm/unaligned.h> |
| 39 | #include <trace/events/napi.h> |
| 40 | |
| 41 | /* |
| 42 | * We maintain a small pool of fully-sized skbs, to make sure the |
| 43 | * message gets out even in extreme OOM situations. |
| 44 | */ |
| 45 | |
| 46 | #define MAX_UDP_CHUNK 1460 |
| 47 | #define MAX_SKBS 32 |
| 48 | |
| 49 | static struct sk_buff_head skb_pool; |
| 50 | |
| 51 | DEFINE_STATIC_SRCU(netpoll_srcu); |
| 52 | |
| 53 | #define USEC_PER_POLL 50 |
| 54 | |
| 55 | #define MAX_SKB_SIZE \ |
| 56 | (sizeof(struct ethhdr) + \ |
| 57 | sizeof(struct iphdr) + \ |
| 58 | sizeof(struct udphdr) + \ |
| 59 | MAX_UDP_CHUNK) |
| 60 | |
| 61 | static void zap_completion_queue(void); |
| 62 | |
| 63 | static unsigned int carrier_timeout = 4; |
| 64 | module_param(carrier_timeout, uint, 0644); |
| 65 | |
| 66 | #define np_info(np, fmt, ...) \ |
| 67 | pr_info("%s: " fmt, np->name, ##__VA_ARGS__) |
| 68 | #define np_err(np, fmt, ...) \ |
| 69 | pr_err("%s: " fmt, np->name, ##__VA_ARGS__) |
| 70 | #define np_notice(np, fmt, ...) \ |
| 71 | pr_notice("%s: " fmt, np->name, ##__VA_ARGS__) |
| 72 | |
| 73 | static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev, |
| 74 | struct netdev_queue *txq) |
| 75 | { |
| 76 | int status = NETDEV_TX_OK; |
| 77 | netdev_features_t features; |
| 78 | |
| 79 | features = netif_skb_features(skb); |
| 80 | |
| 81 | if (skb_vlan_tag_present(skb) && |
| 82 | !vlan_hw_offload_capable(features, skb->vlan_proto)) { |
| 83 | skb = __vlan_hwaccel_push_inside(skb); |
| 84 | if (unlikely(!skb)) { |
| 85 | /* This is actually a packet drop, but we |
| 86 | * don't want the code that calls this |
| 87 | * function to try and operate on a NULL skb. |
| 88 | */ |
| 89 | goto out; |
| 90 | } |
| 91 | } |
| 92 | |
| 93 | status = netdev_start_xmit(skb, dev, txq, false); |
| 94 | |
| 95 | out: |
| 96 | return status; |
| 97 | } |
| 98 | |
| 99 | static void queue_process(struct work_struct *work) |
| 100 | { |
| 101 | struct netpoll_info *npinfo = |
| 102 | container_of(work, struct netpoll_info, tx_work.work); |
| 103 | struct sk_buff *skb; |
| 104 | unsigned long flags; |
| 105 | |
| 106 | while ((skb = skb_dequeue(&npinfo->txq))) { |
| 107 | struct net_device *dev = skb->dev; |
| 108 | struct netdev_queue *txq; |
| 109 | unsigned int q_index; |
| 110 | |
| 111 | if (!netif_device_present(dev) || !netif_running(dev)) { |
| 112 | kfree_skb(skb); |
| 113 | continue; |
| 114 | } |
| 115 | |
| 116 | local_irq_save(flags); |
| 117 | /* check if skb->queue_mapping is still valid */ |
| 118 | q_index = skb_get_queue_mapping(skb); |
| 119 | if (unlikely(q_index >= dev->real_num_tx_queues)) { |
| 120 | q_index = q_index % dev->real_num_tx_queues; |
| 121 | skb_set_queue_mapping(skb, q_index); |
| 122 | } |
| 123 | txq = netdev_get_tx_queue(dev, q_index); |
| 124 | HARD_TX_LOCK(dev, txq, smp_processor_id()); |
| 125 | if (netif_xmit_frozen_or_stopped(txq) || |
| 126 | !dev_xmit_complete(netpoll_start_xmit(skb, dev, txq))) { |
| 127 | skb_queue_head(&npinfo->txq, skb); |
| 128 | HARD_TX_UNLOCK(dev, txq); |
| 129 | local_irq_restore(flags); |
| 130 | |
| 131 | schedule_delayed_work(&npinfo->tx_work, HZ/10); |
| 132 | return; |
| 133 | } |
| 134 | HARD_TX_UNLOCK(dev, txq); |
| 135 | local_irq_restore(flags); |
| 136 | } |
| 137 | } |
| 138 | |
| 139 | static int netif_local_xmit_active(struct net_device *dev) |
| 140 | { |
| 141 | int i; |
| 142 | |
| 143 | for (i = 0; i < dev->num_tx_queues; i++) { |
| 144 | struct netdev_queue *txq = netdev_get_tx_queue(dev, i); |
| 145 | |
| 146 | if (READ_ONCE(txq->xmit_lock_owner) == smp_processor_id()) |
| 147 | return 1; |
| 148 | } |
| 149 | |
| 150 | return 0; |
| 151 | } |
| 152 | |
| 153 | static void poll_one_napi(struct napi_struct *napi) |
| 154 | { |
| 155 | int work; |
| 156 | |
| 157 | /* If we set this bit but see that it has already been set, |
| 158 | * that indicates that napi has been disabled and we need |
| 159 | * to abort this operation |
| 160 | */ |
| 161 | if (test_and_set_bit(NAPI_STATE_NPSVC, &napi->state)) |
| 162 | return; |
| 163 | |
| 164 | /* We explicilty pass the polling call a budget of 0 to |
| 165 | * indicate that we are clearing the Tx path only. |
| 166 | */ |
| 167 | work = napi->poll(napi, 0); |
| 168 | WARN_ONCE(work, "%pS exceeded budget in poll\n", napi->poll); |
| 169 | trace_napi_poll(napi, work, 0); |
| 170 | |
| 171 | clear_bit(NAPI_STATE_NPSVC, &napi->state); |
| 172 | } |
| 173 | |
| 174 | static void poll_napi(struct net_device *dev) |
| 175 | { |
| 176 | struct napi_struct *napi; |
| 177 | int cpu = smp_processor_id(); |
| 178 | |
| 179 | list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { |
| 180 | if (cmpxchg(&napi->poll_owner, -1, cpu) == -1) { |
| 181 | poll_one_napi(napi); |
| 182 | smp_store_release(&napi->poll_owner, -1); |
| 183 | } |
| 184 | } |
| 185 | } |
| 186 | |
| 187 | void netpoll_poll_dev(struct net_device *dev) |
| 188 | { |
| 189 | struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); |
| 190 | const struct net_device_ops *ops; |
| 191 | |
| 192 | /* Don't do any rx activity if the dev_lock mutex is held |
| 193 | * the dev_open/close paths use this to block netpoll activity |
| 194 | * while changing device state |
| 195 | */ |
| 196 | if (!ni || down_trylock(&ni->dev_lock)) |
| 197 | return; |
| 198 | |
| 199 | /* Some drivers will take the same locks in poll and xmit, |
| 200 | * we can't poll if local CPU is already in xmit. |
| 201 | */ |
| 202 | if (!netif_running(dev) || netif_local_xmit_active(dev)) { |
| 203 | up(&ni->dev_lock); |
| 204 | return; |
| 205 | } |
| 206 | |
| 207 | ops = dev->netdev_ops; |
| 208 | if (ops->ndo_poll_controller) |
| 209 | ops->ndo_poll_controller(dev); |
| 210 | |
| 211 | poll_napi(dev); |
| 212 | |
| 213 | up(&ni->dev_lock); |
| 214 | |
| 215 | zap_completion_queue(); |
| 216 | } |
| 217 | EXPORT_SYMBOL(netpoll_poll_dev); |
| 218 | |
| 219 | void netpoll_poll_disable(struct net_device *dev) |
| 220 | { |
| 221 | struct netpoll_info *ni; |
| 222 | int idx; |
| 223 | might_sleep(); |
| 224 | idx = srcu_read_lock(&netpoll_srcu); |
| 225 | ni = srcu_dereference(dev->npinfo, &netpoll_srcu); |
| 226 | if (ni) |
| 227 | down(&ni->dev_lock); |
| 228 | srcu_read_unlock(&netpoll_srcu, idx); |
| 229 | } |
| 230 | EXPORT_SYMBOL(netpoll_poll_disable); |
| 231 | |
| 232 | void netpoll_poll_enable(struct net_device *dev) |
| 233 | { |
| 234 | struct netpoll_info *ni; |
| 235 | rcu_read_lock(); |
| 236 | ni = rcu_dereference(dev->npinfo); |
| 237 | if (ni) |
| 238 | up(&ni->dev_lock); |
| 239 | rcu_read_unlock(); |
| 240 | } |
| 241 | EXPORT_SYMBOL(netpoll_poll_enable); |
| 242 | |
| 243 | static void refill_skbs(void) |
| 244 | { |
| 245 | struct sk_buff *skb; |
| 246 | unsigned long flags; |
| 247 | |
| 248 | spin_lock_irqsave(&skb_pool.lock, flags); |
| 249 | while (skb_pool.qlen < MAX_SKBS) { |
| 250 | skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC); |
| 251 | if (!skb) |
| 252 | break; |
| 253 | |
| 254 | __skb_queue_tail(&skb_pool, skb); |
| 255 | } |
| 256 | spin_unlock_irqrestore(&skb_pool.lock, flags); |
| 257 | } |
| 258 | |
| 259 | static void zap_completion_queue(void) |
| 260 | { |
| 261 | unsigned long flags; |
| 262 | struct softnet_data *sd = &get_cpu_var(softnet_data); |
| 263 | |
| 264 | if (sd->completion_queue) { |
| 265 | struct sk_buff *clist; |
| 266 | |
| 267 | local_irq_save(flags); |
| 268 | clist = sd->completion_queue; |
| 269 | sd->completion_queue = NULL; |
| 270 | local_irq_restore(flags); |
| 271 | |
| 272 | while (clist != NULL) { |
| 273 | struct sk_buff *skb = clist; |
| 274 | clist = clist->next; |
| 275 | if (!skb_irq_freeable(skb)) { |
| 276 | refcount_set(&skb->users, 1); |
| 277 | dev_kfree_skb_any(skb); /* put this one back */ |
| 278 | } else { |
| 279 | __kfree_skb(skb); |
| 280 | } |
| 281 | } |
| 282 | } |
| 283 | |
| 284 | put_cpu_var(softnet_data); |
| 285 | } |
| 286 | |
| 287 | static struct sk_buff *find_skb(struct netpoll *np, int len, int reserve) |
| 288 | { |
| 289 | int count = 0; |
| 290 | struct sk_buff *skb; |
| 291 | |
| 292 | zap_completion_queue(); |
| 293 | refill_skbs(); |
| 294 | repeat: |
| 295 | |
| 296 | skb = alloc_skb(len, GFP_ATOMIC); |
| 297 | if (!skb) |
| 298 | skb = skb_dequeue(&skb_pool); |
| 299 | |
| 300 | if (!skb) { |
| 301 | if (++count < 10) { |
| 302 | netpoll_poll_dev(np->dev); |
| 303 | goto repeat; |
| 304 | } |
| 305 | return NULL; |
| 306 | } |
| 307 | |
| 308 | refcount_set(&skb->users, 1); |
| 309 | skb_reserve(skb, reserve); |
| 310 | return skb; |
| 311 | } |
| 312 | |
| 313 | static int netpoll_owner_active(struct net_device *dev) |
| 314 | { |
| 315 | struct napi_struct *napi; |
| 316 | |
| 317 | list_for_each_entry(napi, &dev->napi_list, dev_list) { |
| 318 | if (napi->poll_owner == smp_processor_id()) |
| 319 | return 1; |
| 320 | } |
| 321 | return 0; |
| 322 | } |
| 323 | |
| 324 | /* call with IRQ disabled */ |
| 325 | void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, |
| 326 | struct net_device *dev) |
| 327 | { |
| 328 | int status = NETDEV_TX_BUSY; |
| 329 | unsigned long tries; |
| 330 | /* It is up to the caller to keep npinfo alive. */ |
| 331 | struct netpoll_info *npinfo; |
| 332 | |
| 333 | lockdep_assert_irqs_disabled(); |
| 334 | |
| 335 | npinfo = rcu_dereference_bh(np->dev->npinfo); |
| 336 | if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) { |
| 337 | dev_kfree_skb_irq(skb); |
| 338 | return; |
| 339 | } |
| 340 | |
| 341 | /* don't get messages out of order, and no recursion */ |
| 342 | if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) { |
| 343 | struct netdev_queue *txq; |
| 344 | |
| 345 | txq = netdev_core_pick_tx(dev, skb, NULL); |
| 346 | |
| 347 | /* try until next clock tick */ |
| 348 | for (tries = jiffies_to_usecs(1)/USEC_PER_POLL; |
| 349 | tries > 0; --tries) { |
| 350 | if (HARD_TX_TRYLOCK(dev, txq)) { |
| 351 | if (!netif_xmit_stopped(txq)) |
| 352 | status = netpoll_start_xmit(skb, dev, txq); |
| 353 | |
| 354 | HARD_TX_UNLOCK(dev, txq); |
| 355 | |
| 356 | if (dev_xmit_complete(status)) |
| 357 | break; |
| 358 | |
| 359 | } |
| 360 | |
| 361 | /* tickle device maybe there is some cleanup */ |
| 362 | netpoll_poll_dev(np->dev); |
| 363 | |
| 364 | udelay(USEC_PER_POLL); |
| 365 | } |
| 366 | |
| 367 | WARN_ONCE(!irqs_disabled(), |
| 368 | "netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pS)\n", |
| 369 | dev->name, dev->netdev_ops->ndo_start_xmit); |
| 370 | |
| 371 | } |
| 372 | |
| 373 | if (!dev_xmit_complete(status)) { |
| 374 | skb_queue_tail(&npinfo->txq, skb); |
| 375 | schedule_delayed_work(&npinfo->tx_work,0); |
| 376 | } |
| 377 | } |
| 378 | EXPORT_SYMBOL(netpoll_send_skb_on_dev); |
| 379 | |
| 380 | void netpoll_send_udp(struct netpoll *np, const char *msg, int len) |
| 381 | { |
| 382 | int total_len, ip_len, udp_len; |
| 383 | struct sk_buff *skb; |
| 384 | struct udphdr *udph; |
| 385 | struct iphdr *iph; |
| 386 | struct ethhdr *eth; |
| 387 | static atomic_t ip_ident; |
| 388 | struct ipv6hdr *ip6h; |
| 389 | |
| 390 | WARN_ON_ONCE(!irqs_disabled()); |
| 391 | |
| 392 | udp_len = len + sizeof(*udph); |
| 393 | if (np->ipv6) |
| 394 | ip_len = udp_len + sizeof(*ip6h); |
| 395 | else |
| 396 | ip_len = udp_len + sizeof(*iph); |
| 397 | |
| 398 | total_len = ip_len + LL_RESERVED_SPACE(np->dev); |
| 399 | |
| 400 | skb = find_skb(np, total_len + np->dev->needed_tailroom, |
| 401 | total_len - len); |
| 402 | if (!skb) |
| 403 | return; |
| 404 | |
| 405 | skb_copy_to_linear_data(skb, msg, len); |
| 406 | skb_put(skb, len); |
| 407 | |
| 408 | skb_push(skb, sizeof(*udph)); |
| 409 | skb_reset_transport_header(skb); |
| 410 | udph = udp_hdr(skb); |
| 411 | udph->source = htons(np->local_port); |
| 412 | udph->dest = htons(np->remote_port); |
| 413 | udph->len = htons(udp_len); |
| 414 | |
| 415 | if (np->ipv6) { |
| 416 | udph->check = 0; |
| 417 | udph->check = csum_ipv6_magic(&np->local_ip.in6, |
| 418 | &np->remote_ip.in6, |
| 419 | udp_len, IPPROTO_UDP, |
| 420 | csum_partial(udph, udp_len, 0)); |
| 421 | if (udph->check == 0) |
| 422 | udph->check = CSUM_MANGLED_0; |
| 423 | |
| 424 | skb_push(skb, sizeof(*ip6h)); |
| 425 | skb_reset_network_header(skb); |
| 426 | ip6h = ipv6_hdr(skb); |
| 427 | |
| 428 | /* ip6h->version = 6; ip6h->priority = 0; */ |
| 429 | put_unaligned(0x60, (unsigned char *)ip6h); |
| 430 | ip6h->flow_lbl[0] = 0; |
| 431 | ip6h->flow_lbl[1] = 0; |
| 432 | ip6h->flow_lbl[2] = 0; |
| 433 | |
| 434 | ip6h->payload_len = htons(sizeof(struct udphdr) + len); |
| 435 | ip6h->nexthdr = IPPROTO_UDP; |
| 436 | ip6h->hop_limit = 32; |
| 437 | ip6h->saddr = np->local_ip.in6; |
| 438 | ip6h->daddr = np->remote_ip.in6; |
| 439 | |
| 440 | eth = skb_push(skb, ETH_HLEN); |
| 441 | skb_reset_mac_header(skb); |
| 442 | skb->protocol = eth->h_proto = htons(ETH_P_IPV6); |
| 443 | } else { |
| 444 | udph->check = 0; |
| 445 | udph->check = csum_tcpudp_magic(np->local_ip.ip, |
| 446 | np->remote_ip.ip, |
| 447 | udp_len, IPPROTO_UDP, |
| 448 | csum_partial(udph, udp_len, 0)); |
| 449 | if (udph->check == 0) |
| 450 | udph->check = CSUM_MANGLED_0; |
| 451 | |
| 452 | skb_push(skb, sizeof(*iph)); |
| 453 | skb_reset_network_header(skb); |
| 454 | iph = ip_hdr(skb); |
| 455 | |
| 456 | /* iph->version = 4; iph->ihl = 5; */ |
| 457 | put_unaligned(0x45, (unsigned char *)iph); |
| 458 | iph->tos = 0; |
| 459 | put_unaligned(htons(ip_len), &(iph->tot_len)); |
| 460 | iph->id = htons(atomic_inc_return(&ip_ident)); |
| 461 | iph->frag_off = 0; |
| 462 | iph->ttl = 64; |
| 463 | iph->protocol = IPPROTO_UDP; |
| 464 | iph->check = 0; |
| 465 | put_unaligned(np->local_ip.ip, &(iph->saddr)); |
| 466 | put_unaligned(np->remote_ip.ip, &(iph->daddr)); |
| 467 | iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); |
| 468 | |
| 469 | eth = skb_push(skb, ETH_HLEN); |
| 470 | skb_reset_mac_header(skb); |
| 471 | skb->protocol = eth->h_proto = htons(ETH_P_IP); |
| 472 | } |
| 473 | |
| 474 | ether_addr_copy(eth->h_source, np->dev->dev_addr); |
| 475 | ether_addr_copy(eth->h_dest, np->remote_mac); |
| 476 | |
| 477 | skb->dev = np->dev; |
| 478 | |
| 479 | netpoll_send_skb(np, skb); |
| 480 | } |
| 481 | EXPORT_SYMBOL(netpoll_send_udp); |
| 482 | |
| 483 | void netpoll_print_options(struct netpoll *np) |
| 484 | { |
| 485 | np_info(np, "local port %d\n", np->local_port); |
| 486 | if (np->ipv6) |
| 487 | np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6); |
| 488 | else |
| 489 | np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip); |
| 490 | np_info(np, "interface '%s'\n", np->dev_name); |
| 491 | np_info(np, "remote port %d\n", np->remote_port); |
| 492 | if (np->ipv6) |
| 493 | np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6); |
| 494 | else |
| 495 | np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip); |
| 496 | np_info(np, "remote ethernet address %pM\n", np->remote_mac); |
| 497 | } |
| 498 | EXPORT_SYMBOL(netpoll_print_options); |
| 499 | |
| 500 | static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr) |
| 501 | { |
| 502 | const char *end; |
| 503 | |
| 504 | if (!strchr(str, ':') && |
| 505 | in4_pton(str, -1, (void *)addr, -1, &end) > 0) { |
| 506 | if (!*end) |
| 507 | return 0; |
| 508 | } |
| 509 | if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) { |
| 510 | #if IS_ENABLED(CONFIG_IPV6) |
| 511 | if (!*end) |
| 512 | return 1; |
| 513 | #else |
| 514 | return -1; |
| 515 | #endif |
| 516 | } |
| 517 | return -1; |
| 518 | } |
| 519 | |
| 520 | int netpoll_parse_options(struct netpoll *np, char *opt) |
| 521 | { |
| 522 | char *cur=opt, *delim; |
| 523 | int ipv6; |
| 524 | bool ipversion_set = false; |
| 525 | |
| 526 | if (*cur != '@') { |
| 527 | if ((delim = strchr(cur, '@')) == NULL) |
| 528 | goto parse_failed; |
| 529 | *delim = 0; |
| 530 | if (kstrtou16(cur, 10, &np->local_port)) |
| 531 | goto parse_failed; |
| 532 | cur = delim; |
| 533 | } |
| 534 | cur++; |
| 535 | |
| 536 | if (*cur != '/') { |
| 537 | ipversion_set = true; |
| 538 | if ((delim = strchr(cur, '/')) == NULL) |
| 539 | goto parse_failed; |
| 540 | *delim = 0; |
| 541 | ipv6 = netpoll_parse_ip_addr(cur, &np->local_ip); |
| 542 | if (ipv6 < 0) |
| 543 | goto parse_failed; |
| 544 | else |
| 545 | np->ipv6 = (bool)ipv6; |
| 546 | cur = delim; |
| 547 | } |
| 548 | cur++; |
| 549 | |
| 550 | if (*cur != ',') { |
| 551 | /* parse out dev name */ |
| 552 | if ((delim = strchr(cur, ',')) == NULL) |
| 553 | goto parse_failed; |
| 554 | *delim = 0; |
| 555 | strlcpy(np->dev_name, cur, sizeof(np->dev_name)); |
| 556 | cur = delim; |
| 557 | } |
| 558 | cur++; |
| 559 | |
| 560 | if (*cur != '@') { |
| 561 | /* dst port */ |
| 562 | if ((delim = strchr(cur, '@')) == NULL) |
| 563 | goto parse_failed; |
| 564 | *delim = 0; |
| 565 | if (*cur == ' ' || *cur == '\t') |
| 566 | np_info(np, "warning: whitespace is not allowed\n"); |
| 567 | if (kstrtou16(cur, 10, &np->remote_port)) |
| 568 | goto parse_failed; |
| 569 | cur = delim; |
| 570 | } |
| 571 | cur++; |
| 572 | |
| 573 | /* dst ip */ |
| 574 | if ((delim = strchr(cur, '/')) == NULL) |
| 575 | goto parse_failed; |
| 576 | *delim = 0; |
| 577 | ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip); |
| 578 | if (ipv6 < 0) |
| 579 | goto parse_failed; |
| 580 | else if (ipversion_set && np->ipv6 != (bool)ipv6) |
| 581 | goto parse_failed; |
| 582 | else |
| 583 | np->ipv6 = (bool)ipv6; |
| 584 | cur = delim + 1; |
| 585 | |
| 586 | if (*cur != 0) { |
| 587 | /* MAC address */ |
| 588 | if (!mac_pton(cur, np->remote_mac)) |
| 589 | goto parse_failed; |
| 590 | } |
| 591 | |
| 592 | netpoll_print_options(np); |
| 593 | |
| 594 | return 0; |
| 595 | |
| 596 | parse_failed: |
| 597 | np_info(np, "couldn't parse config at '%s'!\n", cur); |
| 598 | return -1; |
| 599 | } |
| 600 | EXPORT_SYMBOL(netpoll_parse_options); |
| 601 | |
| 602 | int __netpoll_setup(struct netpoll *np, struct net_device *ndev) |
| 603 | { |
| 604 | struct netpoll_info *npinfo; |
| 605 | const struct net_device_ops *ops; |
| 606 | int err; |
| 607 | |
| 608 | np->dev = ndev; |
| 609 | strlcpy(np->dev_name, ndev->name, IFNAMSIZ); |
| 610 | |
| 611 | if (ndev->priv_flags & IFF_DISABLE_NETPOLL) { |
| 612 | np_err(np, "%s doesn't support polling, aborting\n", |
| 613 | np->dev_name); |
| 614 | err = -ENOTSUPP; |
| 615 | goto out; |
| 616 | } |
| 617 | |
| 618 | if (!rcu_access_pointer(ndev->npinfo)) { |
| 619 | npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL); |
| 620 | if (!npinfo) { |
| 621 | err = -ENOMEM; |
| 622 | goto out; |
| 623 | } |
| 624 | |
| 625 | sema_init(&npinfo->dev_lock, 1); |
| 626 | skb_queue_head_init(&npinfo->txq); |
| 627 | INIT_DELAYED_WORK(&npinfo->tx_work, queue_process); |
| 628 | |
| 629 | refcount_set(&npinfo->refcnt, 1); |
| 630 | |
| 631 | ops = np->dev->netdev_ops; |
| 632 | if (ops->ndo_netpoll_setup) { |
| 633 | err = ops->ndo_netpoll_setup(ndev, npinfo); |
| 634 | if (err) |
| 635 | goto free_npinfo; |
| 636 | } |
| 637 | } else { |
| 638 | npinfo = rtnl_dereference(ndev->npinfo); |
| 639 | refcount_inc(&npinfo->refcnt); |
| 640 | } |
| 641 | |
| 642 | npinfo->netpoll = np; |
| 643 | |
| 644 | /* last thing to do is link it to the net device structure */ |
| 645 | rcu_assign_pointer(ndev->npinfo, npinfo); |
| 646 | |
| 647 | return 0; |
| 648 | |
| 649 | free_npinfo: |
| 650 | kfree(npinfo); |
| 651 | out: |
| 652 | return err; |
| 653 | } |
| 654 | EXPORT_SYMBOL_GPL(__netpoll_setup); |
| 655 | |
| 656 | int netpoll_setup(struct netpoll *np) |
| 657 | { |
| 658 | struct net_device *ndev = NULL, *dev = NULL; |
| 659 | struct net *net = current->nsproxy->net_ns; |
| 660 | struct in_device *in_dev; |
| 661 | int err; |
| 662 | |
| 663 | rtnl_lock(); |
| 664 | if (np->dev_name[0]) |
| 665 | ndev = __dev_get_by_name(net, np->dev_name); |
| 666 | |
| 667 | if (!ndev) { |
| 668 | np_err(np, "%s doesn't exist, aborting\n", np->dev_name); |
| 669 | err = -ENODEV; |
| 670 | goto unlock; |
| 671 | } |
| 672 | dev_hold(ndev); |
| 673 | |
| 674 | /* bring up DSA management network devices up first */ |
| 675 | for_each_netdev(net, dev) { |
| 676 | if (!netdev_uses_dsa(dev)) |
| 677 | continue; |
| 678 | |
| 679 | err = dev_change_flags(dev, dev->flags | IFF_UP, NULL); |
| 680 | if (err < 0) { |
| 681 | np_err(np, "%s failed to open %s\n", |
| 682 | np->dev_name, dev->name); |
| 683 | goto put; |
| 684 | } |
| 685 | } |
| 686 | |
| 687 | if (netdev_master_upper_dev_get(ndev)) { |
| 688 | np_err(np, "%s is a slave device, aborting\n", np->dev_name); |
| 689 | err = -EBUSY; |
| 690 | goto put; |
| 691 | } |
| 692 | |
| 693 | if (!netif_running(ndev)) { |
| 694 | unsigned long atmost, atleast; |
| 695 | |
| 696 | np_info(np, "device %s not up yet, forcing it\n", np->dev_name); |
| 697 | |
| 698 | err = dev_open(ndev, NULL); |
| 699 | |
| 700 | if (err) { |
| 701 | np_err(np, "failed to open %s\n", ndev->name); |
| 702 | goto put; |
| 703 | } |
| 704 | |
| 705 | rtnl_unlock(); |
| 706 | atleast = jiffies + HZ/10; |
| 707 | atmost = jiffies + carrier_timeout * HZ; |
| 708 | while (!netif_carrier_ok(ndev)) { |
| 709 | if (time_after(jiffies, atmost)) { |
| 710 | np_notice(np, "timeout waiting for carrier\n"); |
| 711 | break; |
| 712 | } |
| 713 | msleep(1); |
| 714 | } |
| 715 | |
| 716 | /* If carrier appears to come up instantly, we don't |
| 717 | * trust it and pause so that we don't pump all our |
| 718 | * queued console messages into the bitbucket. |
| 719 | */ |
| 720 | |
| 721 | if (time_before(jiffies, atleast)) { |
| 722 | np_notice(np, "carrier detect appears untrustworthy, waiting 4 seconds\n"); |
| 723 | msleep(4000); |
| 724 | } |
| 725 | rtnl_lock(); |
| 726 | } |
| 727 | |
| 728 | if (!np->local_ip.ip) { |
| 729 | if (!np->ipv6) { |
| 730 | const struct in_ifaddr *ifa; |
| 731 | |
| 732 | in_dev = __in_dev_get_rtnl(ndev); |
| 733 | if (!in_dev) |
| 734 | goto put_noaddr; |
| 735 | |
| 736 | ifa = rtnl_dereference(in_dev->ifa_list); |
| 737 | if (!ifa) { |
| 738 | put_noaddr: |
| 739 | np_err(np, "no IP address for %s, aborting\n", |
| 740 | np->dev_name); |
| 741 | err = -EDESTADDRREQ; |
| 742 | goto put; |
| 743 | } |
| 744 | |
| 745 | np->local_ip.ip = ifa->ifa_local; |
| 746 | np_info(np, "local IP %pI4\n", &np->local_ip.ip); |
| 747 | } else { |
| 748 | #if IS_ENABLED(CONFIG_IPV6) |
| 749 | struct inet6_dev *idev; |
| 750 | |
| 751 | err = -EDESTADDRREQ; |
| 752 | idev = __in6_dev_get(ndev); |
| 753 | if (idev) { |
| 754 | struct inet6_ifaddr *ifp; |
| 755 | |
| 756 | read_lock_bh(&idev->lock); |
| 757 | list_for_each_entry(ifp, &idev->addr_list, if_list) { |
| 758 | if (!!(ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) != |
| 759 | !!(ipv6_addr_type(&np->remote_ip.in6) & IPV6_ADDR_LINKLOCAL)) |
| 760 | continue; |
| 761 | np->local_ip.in6 = ifp->addr; |
| 762 | err = 0; |
| 763 | break; |
| 764 | } |
| 765 | read_unlock_bh(&idev->lock); |
| 766 | } |
| 767 | if (err) { |
| 768 | np_err(np, "no IPv6 address for %s, aborting\n", |
| 769 | np->dev_name); |
| 770 | goto put; |
| 771 | } else |
| 772 | np_info(np, "local IPv6 %pI6c\n", &np->local_ip.in6); |
| 773 | #else |
| 774 | np_err(np, "IPv6 is not supported %s, aborting\n", |
| 775 | np->dev_name); |
| 776 | err = -EINVAL; |
| 777 | goto put; |
| 778 | #endif |
| 779 | } |
| 780 | } |
| 781 | |
| 782 | /* fill up the skb queue */ |
| 783 | refill_skbs(); |
| 784 | |
| 785 | err = __netpoll_setup(np, ndev); |
| 786 | if (err) |
| 787 | goto put; |
| 788 | |
| 789 | rtnl_unlock(); |
| 790 | return 0; |
| 791 | |
| 792 | put: |
| 793 | dev_put(ndev); |
| 794 | unlock: |
| 795 | rtnl_unlock(); |
| 796 | return err; |
| 797 | } |
| 798 | EXPORT_SYMBOL(netpoll_setup); |
| 799 | |
| 800 | static int __init netpoll_init(void) |
| 801 | { |
| 802 | skb_queue_head_init(&skb_pool); |
| 803 | return 0; |
| 804 | } |
| 805 | core_initcall(netpoll_init); |
| 806 | |
| 807 | static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head) |
| 808 | { |
| 809 | struct netpoll_info *npinfo = |
| 810 | container_of(rcu_head, struct netpoll_info, rcu); |
| 811 | |
| 812 | skb_queue_purge(&npinfo->txq); |
| 813 | |
| 814 | /* we can't call cancel_delayed_work_sync here, as we are in softirq */ |
| 815 | cancel_delayed_work(&npinfo->tx_work); |
| 816 | |
| 817 | /* clean after last, unfinished work */ |
| 818 | __skb_queue_purge(&npinfo->txq); |
| 819 | /* now cancel it again */ |
| 820 | cancel_delayed_work(&npinfo->tx_work); |
| 821 | kfree(npinfo); |
| 822 | } |
| 823 | |
| 824 | void __netpoll_cleanup(struct netpoll *np) |
| 825 | { |
| 826 | struct netpoll_info *npinfo; |
| 827 | |
| 828 | npinfo = rtnl_dereference(np->dev->npinfo); |
| 829 | if (!npinfo) |
| 830 | return; |
| 831 | |
| 832 | synchronize_srcu(&netpoll_srcu); |
| 833 | |
| 834 | if (refcount_dec_and_test(&npinfo->refcnt)) { |
| 835 | const struct net_device_ops *ops; |
| 836 | |
| 837 | ops = np->dev->netdev_ops; |
| 838 | if (ops->ndo_netpoll_cleanup) |
| 839 | ops->ndo_netpoll_cleanup(np->dev); |
| 840 | |
| 841 | RCU_INIT_POINTER(np->dev->npinfo, NULL); |
| 842 | call_rcu(&npinfo->rcu, rcu_cleanup_netpoll_info); |
| 843 | } else |
| 844 | RCU_INIT_POINTER(np->dev->npinfo, NULL); |
| 845 | } |
| 846 | EXPORT_SYMBOL_GPL(__netpoll_cleanup); |
| 847 | |
| 848 | void __netpoll_free(struct netpoll *np) |
| 849 | { |
| 850 | ASSERT_RTNL(); |
| 851 | |
| 852 | /* Wait for transmitting packets to finish before freeing. */ |
| 853 | synchronize_rcu(); |
| 854 | __netpoll_cleanup(np); |
| 855 | kfree(np); |
| 856 | } |
| 857 | EXPORT_SYMBOL_GPL(__netpoll_free); |
| 858 | |
| 859 | void netpoll_cleanup(struct netpoll *np) |
| 860 | { |
| 861 | rtnl_lock(); |
| 862 | if (!np->dev) |
| 863 | goto out; |
| 864 | __netpoll_cleanup(np); |
| 865 | dev_put(np->dev); |
| 866 | np->dev = NULL; |
| 867 | out: |
| 868 | rtnl_unlock(); |
| 869 | } |
| 870 | EXPORT_SYMBOL(netpoll_cleanup); |