Blame view
drivers/xen/pvcalls-back.c
29.9 KB
72e59c30d xen/pvcalls: intr... |
1 2 3 4 5 6 7 8 9 10 11 12 13 |
/* * (c) 2017 Stefano Stabellini <stefano@aporeto.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ |
fb0298754 xen/pvcalls: impl... |
14 |
#include <linux/inet.h> |
72e59c30d xen/pvcalls: intr... |
15 16 17 18 19 20 |
#include <linux/kthread.h> #include <linux/list.h> #include <linux/radix-tree.h> #include <linux/module.h> #include <linux/semaphore.h> #include <linux/wait.h> |
fb0298754 xen/pvcalls: impl... |
21 22 23 24 |
#include <net/sock.h> #include <net/inet_common.h> #include <net/inet_connection_sock.h> #include <net/request_sock.h> |
72e59c30d xen/pvcalls: intr... |
25 26 27 28 29 30 |
#include <xen/events.h> #include <xen/grant_table.h> #include <xen/xen.h> #include <xen/xenbus.h> #include <xen/interface/io/pvcalls.h> |
0a9c75c2c xen/pvcalls: xenb... |
31 32 |
#define PVCALLS_VERSIONS "1" #define MAX_RING_ORDER XENBUS_MAX_RING_GRANT_ORDER |
9be07334f xen/pvcalls: init... |
33 34 35 36 |
struct pvcalls_back_global { struct list_head frontends; struct semaphore frontends_lock; } pvcalls_back_global; |
d0e4d560c xen/pvcalls: conn... |
37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 |
/* * Per-frontend data structure. It contains pointers to the command * ring, its event channel, a list of active sockets and a tree of * passive sockets. */ struct pvcalls_fedata { struct list_head list; struct xenbus_device *dev; struct xen_pvcalls_sring *sring; struct xen_pvcalls_back_ring ring; int irq; struct list_head socket_mappings; struct radix_tree_root socketpass_mappings; struct semaphore socket_lock; }; |
5db4d286a xen/pvcalls: impl... |
52 53 54 55 56 57 58 59 |
struct pvcalls_ioworker { struct work_struct register_work; struct workqueue_struct *wq; }; struct sock_mapping { struct list_head list; struct pvcalls_fedata *fedata; |
6f474e711 xen/pvcalls: impl... |
60 |
struct sockpass_mapping *sockpass; |
5db4d286a xen/pvcalls: impl... |
61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 |
struct socket *sock; uint64_t id; grant_ref_t ref; struct pvcalls_data_intf *ring; void *bytes; struct pvcalls_data data; uint32_t ring_order; int irq; atomic_t read; atomic_t write; atomic_t io; atomic_t release; void (*saved_data_ready)(struct sock *sk); struct pvcalls_ioworker ioworker; }; |
331a63e6f xen/pvcalls: impl... |
76 77 78 79 80 81 82 83 84 85 86 |
struct sockpass_mapping { struct list_head list; struct pvcalls_fedata *fedata; struct socket *sock; uint64_t id; struct xen_pvcalls_request reqcopy; spinlock_t copy_lock; struct workqueue_struct *wq; struct work_struct register_work; void (*saved_data_ready)(struct sock *sk); }; |
5db4d286a xen/pvcalls: impl... |
87 88 89 90 |
static irqreturn_t pvcalls_back_conn_event(int irq, void *sock_map); static int pvcalls_back_release_active(struct xenbus_device *dev, struct pvcalls_fedata *fedata, struct sock_mapping *map); |
5d520d858 xen/pvcalls: impl... |
91 92 |
static void pvcalls_conn_back_read(void *opaque) { |
b3f9f773a xen/pvcalls: impl... |
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 |
struct sock_mapping *map = (struct sock_mapping *)opaque; struct msghdr msg; struct kvec vec[2]; RING_IDX cons, prod, size, wanted, array_size, masked_prod, masked_cons; int32_t error; struct pvcalls_data_intf *intf = map->ring; struct pvcalls_data *data = &map->data; unsigned long flags; int ret; array_size = XEN_FLEX_RING_SIZE(map->ring_order); cons = intf->in_cons; prod = intf->in_prod; error = intf->in_error; /* read the indexes first, then deal with the data */ virt_mb(); if (error) return; size = pvcalls_queued(prod, cons, array_size); if (size >= array_size) return; spin_lock_irqsave(&map->sock->sk->sk_receive_queue.lock, flags); if (skb_queue_empty(&map->sock->sk->sk_receive_queue)) { atomic_set(&map->read, 0); spin_unlock_irqrestore(&map->sock->sk->sk_receive_queue.lock, flags); return; } spin_unlock_irqrestore(&map->sock->sk->sk_receive_queue.lock, flags); wanted = array_size - size; masked_prod = pvcalls_mask(prod, array_size); masked_cons = pvcalls_mask(cons, array_size); memset(&msg, 0, sizeof(msg)); msg.msg_iter.type = ITER_KVEC|WRITE; msg.msg_iter.count = wanted; if (masked_prod < masked_cons) { vec[0].iov_base = data->in + masked_prod; vec[0].iov_len = wanted; msg.msg_iter.kvec = vec; msg.msg_iter.nr_segs = 1; } else { vec[0].iov_base = data->in + masked_prod; vec[0].iov_len = array_size - masked_prod; vec[1].iov_base = data->in; vec[1].iov_len = wanted - vec[0].iov_len; msg.msg_iter.kvec = vec; msg.msg_iter.nr_segs = 2; } atomic_set(&map->read, 0); ret = inet_recvmsg(map->sock, &msg, wanted, MSG_DONTWAIT); WARN_ON(ret > wanted); if (ret == -EAGAIN) /* shouldn't happen */ return; if (!ret) ret = -ENOTCONN; spin_lock_irqsave(&map->sock->sk->sk_receive_queue.lock, flags); if (ret > 0 && !skb_queue_empty(&map->sock->sk->sk_receive_queue)) atomic_inc(&map->read); spin_unlock_irqrestore(&map->sock->sk->sk_receive_queue.lock, flags); /* write the data, then modify the indexes */ virt_wmb(); if (ret < 0) intf->in_error = ret; else intf->in_prod = prod + ret; /* update the indexes, then notify the other end */ virt_wmb(); notify_remote_via_irq(map->irq); return; |
5d520d858 xen/pvcalls: impl... |
168 169 170 171 |
} static void pvcalls_conn_back_write(struct sock_mapping *map) { |
5ad9918ff xen/pvcalls: impl... |
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 |
struct pvcalls_data_intf *intf = map->ring; struct pvcalls_data *data = &map->data; struct msghdr msg; struct kvec vec[2]; RING_IDX cons, prod, size, array_size; int ret; cons = intf->out_cons; prod = intf->out_prod; /* read the indexes before dealing with the data */ virt_mb(); array_size = XEN_FLEX_RING_SIZE(map->ring_order); size = pvcalls_queued(prod, cons, array_size); if (size == 0) return; memset(&msg, 0, sizeof(msg)); msg.msg_flags |= MSG_DONTWAIT; msg.msg_iter.type = ITER_KVEC|READ; msg.msg_iter.count = size; if (pvcalls_mask(prod, array_size) > pvcalls_mask(cons, array_size)) { vec[0].iov_base = data->out + pvcalls_mask(cons, array_size); vec[0].iov_len = size; msg.msg_iter.kvec = vec; msg.msg_iter.nr_segs = 1; } else { vec[0].iov_base = data->out + pvcalls_mask(cons, array_size); vec[0].iov_len = array_size - pvcalls_mask(cons, array_size); vec[1].iov_base = data->out; vec[1].iov_len = size - vec[0].iov_len; msg.msg_iter.kvec = vec; msg.msg_iter.nr_segs = 2; } atomic_set(&map->write, 0); ret = inet_sendmsg(map->sock, &msg, size); if (ret == -EAGAIN || (ret >= 0 && ret < size)) { atomic_inc(&map->write); atomic_inc(&map->io); } if (ret == -EAGAIN) return; /* write the data, then update the indexes */ virt_wmb(); if (ret < 0) { intf->out_error = ret; } else { intf->out_error = 0; intf->out_cons = cons + ret; prod = intf->out_prod; } /* update the indexes, then notify the other end */ virt_wmb(); if (prod != cons + ret) atomic_inc(&map->write); notify_remote_via_irq(map->irq); |
5d520d858 xen/pvcalls: impl... |
230 |
} |
5db4d286a xen/pvcalls: impl... |
231 232 |
static void pvcalls_back_ioworker(struct work_struct *work) { |
5d520d858 xen/pvcalls: impl... |
233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 |
struct pvcalls_ioworker *ioworker = container_of(work, struct pvcalls_ioworker, register_work); struct sock_mapping *map = container_of(ioworker, struct sock_mapping, ioworker); while (atomic_read(&map->io) > 0) { if (atomic_read(&map->release) > 0) { atomic_set(&map->release, 0); return; } if (atomic_read(&map->read) > 0) pvcalls_conn_back_read(map); if (atomic_read(&map->write) > 0) pvcalls_conn_back_write(map); atomic_dec(&map->io); } |
5db4d286a xen/pvcalls: impl... |
251 |
} |
b1efa6931 xen/pvcalls: hand... |
252 253 254 |
static int pvcalls_back_socket(struct xenbus_device *dev, struct xen_pvcalls_request *req) { |
fb0298754 xen/pvcalls: impl... |
255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 |
struct pvcalls_fedata *fedata; int ret; struct xen_pvcalls_response *rsp; fedata = dev_get_drvdata(&dev->dev); if (req->u.socket.domain != AF_INET || req->u.socket.type != SOCK_STREAM || (req->u.socket.protocol != IPPROTO_IP && req->u.socket.protocol != AF_INET)) ret = -EAFNOSUPPORT; else ret = 0; /* leave the actual socket allocation for later */ rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++); rsp->req_id = req->req_id; rsp->cmd = req->cmd; rsp->u.socket.id = req->u.socket.id; rsp->ret = ret; |
b1efa6931 xen/pvcalls: hand... |
276 277 |
return 0; } |
5db4d286a xen/pvcalls: impl... |
278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 |
static void pvcalls_sk_state_change(struct sock *sock) { struct sock_mapping *map = sock->sk_user_data; struct pvcalls_data_intf *intf; if (map == NULL) return; intf = map->ring; intf->in_error = -ENOTCONN; notify_remote_via_irq(map->irq); } static void pvcalls_sk_data_ready(struct sock *sock) { |
b3f9f773a xen/pvcalls: impl... |
293 294 295 296 297 298 299 300 301 302 |
struct sock_mapping *map = sock->sk_user_data; struct pvcalls_ioworker *iow; if (map == NULL) return; iow = &map->ioworker; atomic_inc(&map->read); atomic_inc(&map->io); queue_work(iow->wq, &iow->register_work); |
5db4d286a xen/pvcalls: impl... |
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 |
} static struct sock_mapping *pvcalls_new_active_socket( struct pvcalls_fedata *fedata, uint64_t id, grant_ref_t ref, uint32_t evtchn, struct socket *sock) { int ret; struct sock_mapping *map; void *page; map = kzalloc(sizeof(*map), GFP_KERNEL); if (map == NULL) return NULL; map->fedata = fedata; map->sock = sock; map->id = id; map->ref = ref; ret = xenbus_map_ring_valloc(fedata->dev, &ref, 1, &page); if (ret < 0) goto out; map->ring = page; map->ring_order = map->ring->ring_order; /* first read the order, then map the data ring */ virt_rmb(); if (map->ring_order > MAX_RING_ORDER) { pr_warn("%s frontend requested ring_order %u, which is > MAX (%u) ", __func__, map->ring_order, MAX_RING_ORDER); goto out; } ret = xenbus_map_ring_valloc(fedata->dev, map->ring->ref, (1 << map->ring_order), &page); if (ret < 0) goto out; map->bytes = page; ret = bind_interdomain_evtchn_to_irqhandler(fedata->dev->otherend_id, evtchn, pvcalls_back_conn_event, 0, "pvcalls-backend", map); if (ret < 0) goto out; map->irq = ret; map->data.in = map->bytes; map->data.out = map->bytes + XEN_FLEX_RING_SIZE(map->ring_order); map->ioworker.wq = alloc_workqueue("pvcalls_io", WQ_UNBOUND, 1); if (!map->ioworker.wq) goto out; atomic_set(&map->io, 1); INIT_WORK(&map->ioworker.register_work, pvcalls_back_ioworker); down(&fedata->socket_lock); list_add_tail(&map->list, &fedata->socket_mappings); up(&fedata->socket_lock); write_lock_bh(&map->sock->sk->sk_callback_lock); map->saved_data_ready = map->sock->sk->sk_data_ready; map->sock->sk->sk_user_data = map; map->sock->sk->sk_data_ready = pvcalls_sk_data_ready; map->sock->sk->sk_state_change = pvcalls_sk_state_change; write_unlock_bh(&map->sock->sk->sk_callback_lock); return map; out: down(&fedata->socket_lock); list_del(&map->list); pvcalls_back_release_active(fedata->dev, fedata, map); up(&fedata->socket_lock); return NULL; } |
b1efa6931 xen/pvcalls: hand... |
382 383 384 |
static int pvcalls_back_connect(struct xenbus_device *dev, struct xen_pvcalls_request *req) { |
5db4d286a xen/pvcalls: impl... |
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 |
struct pvcalls_fedata *fedata; int ret = -EINVAL; struct socket *sock; struct sock_mapping *map; struct xen_pvcalls_response *rsp; struct sockaddr *sa = (struct sockaddr *)&req->u.connect.addr; fedata = dev_get_drvdata(&dev->dev); if (req->u.connect.len < sizeof(sa->sa_family) || req->u.connect.len > sizeof(req->u.connect.addr) || sa->sa_family != AF_INET) goto out; ret = sock_create(AF_INET, SOCK_STREAM, 0, &sock); if (ret < 0) goto out; ret = inet_stream_connect(sock, sa, req->u.connect.len, 0); if (ret < 0) { sock_release(sock); goto out; } map = pvcalls_new_active_socket(fedata, req->u.connect.id, req->u.connect.ref, req->u.connect.evtchn, sock); if (!map) { ret = -EFAULT; |
3ecb681cc xen/pvcalls: fix ... |
415 |
sock_release(sock); |
5db4d286a xen/pvcalls: impl... |
416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 |
} out: rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++); rsp->req_id = req->req_id; rsp->cmd = req->cmd; rsp->u.connect.id = req->u.connect.id; rsp->ret = ret; return 0; } static int pvcalls_back_release_active(struct xenbus_device *dev, struct pvcalls_fedata *fedata, struct sock_mapping *map) { |
a51729cb9 xen/pvcalls: impl... |
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 |
disable_irq(map->irq); if (map->sock->sk != NULL) { write_lock_bh(&map->sock->sk->sk_callback_lock); map->sock->sk->sk_user_data = NULL; map->sock->sk->sk_data_ready = map->saved_data_ready; write_unlock_bh(&map->sock->sk->sk_callback_lock); } atomic_set(&map->release, 1); flush_work(&map->ioworker.register_work); xenbus_unmap_ring_vfree(dev, map->bytes); xenbus_unmap_ring_vfree(dev, (void *)map->ring); unbind_from_irqhandler(map->irq, map); sock_release(map->sock); kfree(map); return 0; } static int pvcalls_back_release_passive(struct xenbus_device *dev, struct pvcalls_fedata *fedata, struct sockpass_mapping *mappass) { if (mappass->sock->sk != NULL) { write_lock_bh(&mappass->sock->sk->sk_callback_lock); mappass->sock->sk->sk_user_data = NULL; mappass->sock->sk->sk_data_ready = mappass->saved_data_ready; write_unlock_bh(&mappass->sock->sk->sk_callback_lock); } sock_release(mappass->sock); flush_workqueue(mappass->wq); destroy_workqueue(mappass->wq); kfree(mappass); |
b1efa6931 xen/pvcalls: hand... |
467 468 469 470 471 472 |
return 0; } static int pvcalls_back_release(struct xenbus_device *dev, struct xen_pvcalls_request *req) { |
a51729cb9 xen/pvcalls: impl... |
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 |
struct pvcalls_fedata *fedata; struct sock_mapping *map, *n; struct sockpass_mapping *mappass; int ret = 0; struct xen_pvcalls_response *rsp; fedata = dev_get_drvdata(&dev->dev); down(&fedata->socket_lock); list_for_each_entry_safe(map, n, &fedata->socket_mappings, list) { if (map->id == req->u.release.id) { list_del(&map->list); up(&fedata->socket_lock); ret = pvcalls_back_release_active(dev, fedata, map); goto out; } } mappass = radix_tree_lookup(&fedata->socketpass_mappings, req->u.release.id); if (mappass != NULL) { radix_tree_delete(&fedata->socketpass_mappings, mappass->id); up(&fedata->socket_lock); ret = pvcalls_back_release_passive(dev, fedata, mappass); } else up(&fedata->socket_lock); out: rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++); rsp->req_id = req->req_id; rsp->u.release.id = req->u.release.id; rsp->cmd = req->cmd; rsp->ret = ret; |
b1efa6931 xen/pvcalls: hand... |
505 506 |
return 0; } |
331a63e6f xen/pvcalls: impl... |
507 508 |
static void __pvcalls_back_accept(struct work_struct *work) { |
6f474e711 xen/pvcalls: impl... |
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 |
struct sockpass_mapping *mappass = container_of( work, struct sockpass_mapping, register_work); struct sock_mapping *map; struct pvcalls_ioworker *iow; struct pvcalls_fedata *fedata; struct socket *sock; struct xen_pvcalls_response *rsp; struct xen_pvcalls_request *req; int notify; int ret = -EINVAL; unsigned long flags; fedata = mappass->fedata; /* * __pvcalls_back_accept can race against pvcalls_back_accept. * We only need to check the value of "cmd" on read. It could be * done atomically, but to simplify the code on the write side, we * use a spinlock. */ spin_lock_irqsave(&mappass->copy_lock, flags); req = &mappass->reqcopy; if (req->cmd != PVCALLS_ACCEPT) { spin_unlock_irqrestore(&mappass->copy_lock, flags); return; } spin_unlock_irqrestore(&mappass->copy_lock, flags); sock = sock_alloc(); if (sock == NULL) goto out_error; sock->type = mappass->sock->type; sock->ops = mappass->sock->ops; ret = inet_accept(mappass->sock, sock, O_NONBLOCK, true); if (ret == -EAGAIN) { sock_release(sock); goto out_error; } map = pvcalls_new_active_socket(fedata, req->u.accept.id_new, req->u.accept.ref, req->u.accept.evtchn, sock); if (!map) { ret = -EFAULT; sock_release(sock); goto out_error; } map->sockpass = mappass; iow = &map->ioworker; atomic_inc(&map->read); atomic_inc(&map->io); queue_work(iow->wq, &iow->register_work); out_error: rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++); rsp->req_id = req->req_id; rsp->cmd = req->cmd; rsp->u.accept.id = req->u.accept.id; rsp->ret = ret; RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&fedata->ring, notify); if (notify) notify_remote_via_irq(fedata->irq); mappass->reqcopy.cmd = 0; |
331a63e6f xen/pvcalls: impl... |
576 577 578 579 |
} static void pvcalls_pass_sk_data_ready(struct sock *sock) { |
6f474e711 xen/pvcalls: impl... |
580 |
struct sockpass_mapping *mappass = sock->sk_user_data; |
3cf33a587 xen/pvcalls: impl... |
581 582 583 584 |
struct pvcalls_fedata *fedata; struct xen_pvcalls_response *rsp; unsigned long flags; int notify; |
6f474e711 xen/pvcalls: impl... |
585 586 587 |
if (mappass == NULL) return; |
3cf33a587 xen/pvcalls: impl... |
588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 |
fedata = mappass->fedata; spin_lock_irqsave(&mappass->copy_lock, flags); if (mappass->reqcopy.cmd == PVCALLS_POLL) { rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++); rsp->req_id = mappass->reqcopy.req_id; rsp->u.poll.id = mappass->reqcopy.u.poll.id; rsp->cmd = mappass->reqcopy.cmd; rsp->ret = 0; mappass->reqcopy.cmd = 0; spin_unlock_irqrestore(&mappass->copy_lock, flags); RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&fedata->ring, notify); if (notify) notify_remote_via_irq(mappass->fedata->irq); } else { spin_unlock_irqrestore(&mappass->copy_lock, flags); queue_work(mappass->wq, &mappass->register_work); } |
331a63e6f xen/pvcalls: impl... |
608 |
} |
b1efa6931 xen/pvcalls: hand... |
609 610 611 |
static int pvcalls_back_bind(struct xenbus_device *dev, struct xen_pvcalls_request *req) { |
331a63e6f xen/pvcalls: impl... |
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 |
struct pvcalls_fedata *fedata; int ret; struct sockpass_mapping *map; struct xen_pvcalls_response *rsp; fedata = dev_get_drvdata(&dev->dev); map = kzalloc(sizeof(*map), GFP_KERNEL); if (map == NULL) { ret = -ENOMEM; goto out; } INIT_WORK(&map->register_work, __pvcalls_back_accept); spin_lock_init(&map->copy_lock); map->wq = alloc_workqueue("pvcalls_wq", WQ_UNBOUND, 1); if (!map->wq) { ret = -ENOMEM; goto out; } ret = sock_create(AF_INET, SOCK_STREAM, 0, &map->sock); if (ret < 0) goto out; ret = inet_bind(map->sock, (struct sockaddr *)&req->u.bind.addr, req->u.bind.len); if (ret < 0) goto out; map->fedata = fedata; map->id = req->u.bind.id; down(&fedata->socket_lock); ret = radix_tree_insert(&fedata->socketpass_mappings, map->id, map); up(&fedata->socket_lock); if (ret) goto out; write_lock_bh(&map->sock->sk->sk_callback_lock); map->saved_data_ready = map->sock->sk->sk_data_ready; map->sock->sk->sk_user_data = map; map->sock->sk->sk_data_ready = pvcalls_pass_sk_data_ready; write_unlock_bh(&map->sock->sk->sk_callback_lock); out: if (ret) { if (map && map->sock) sock_release(map->sock); if (map && map->wq) destroy_workqueue(map->wq); kfree(map); } rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++); rsp->req_id = req->req_id; rsp->cmd = req->cmd; rsp->u.bind.id = req->u.bind.id; rsp->ret = ret; |
b1efa6931 xen/pvcalls: hand... |
671 672 673 674 675 676 |
return 0; } static int pvcalls_back_listen(struct xenbus_device *dev, struct xen_pvcalls_request *req) { |
8ce3f7626 xen/pvcalls: impl... |
677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 |
struct pvcalls_fedata *fedata; int ret = -EINVAL; struct sockpass_mapping *map; struct xen_pvcalls_response *rsp; fedata = dev_get_drvdata(&dev->dev); down(&fedata->socket_lock); map = radix_tree_lookup(&fedata->socketpass_mappings, req->u.listen.id); up(&fedata->socket_lock); if (map == NULL) goto out; ret = inet_listen(map->sock, req->u.listen.backlog); out: rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++); rsp->req_id = req->req_id; rsp->cmd = req->cmd; rsp->u.listen.id = req->u.listen.id; rsp->ret = ret; |
b1efa6931 xen/pvcalls: hand... |
698 699 700 701 702 703 |
return 0; } static int pvcalls_back_accept(struct xenbus_device *dev, struct xen_pvcalls_request *req) { |
6f474e711 xen/pvcalls: impl... |
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 |
struct pvcalls_fedata *fedata; struct sockpass_mapping *mappass; int ret = -EINVAL; struct xen_pvcalls_response *rsp; unsigned long flags; fedata = dev_get_drvdata(&dev->dev); down(&fedata->socket_lock); mappass = radix_tree_lookup(&fedata->socketpass_mappings, req->u.accept.id); up(&fedata->socket_lock); if (mappass == NULL) goto out_error; /* * Limitation of the current implementation: only support one * concurrent accept or poll call on one socket. */ spin_lock_irqsave(&mappass->copy_lock, flags); if (mappass->reqcopy.cmd != 0) { spin_unlock_irqrestore(&mappass->copy_lock, flags); ret = -EINTR; goto out_error; } mappass->reqcopy = *req; spin_unlock_irqrestore(&mappass->copy_lock, flags); queue_work(mappass->wq, &mappass->register_work); /* Tell the caller we don't need to send back a notification yet */ return -1; out_error: rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++); rsp->req_id = req->req_id; rsp->cmd = req->cmd; rsp->u.accept.id = req->u.accept.id; rsp->ret = ret; |
b1efa6931 xen/pvcalls: hand... |
743 744 745 746 747 748 |
return 0; } static int pvcalls_back_poll(struct xenbus_device *dev, struct xen_pvcalls_request *req) { |
3cf33a587 xen/pvcalls: impl... |
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 |
struct pvcalls_fedata *fedata; struct sockpass_mapping *mappass; struct xen_pvcalls_response *rsp; struct inet_connection_sock *icsk; struct request_sock_queue *queue; unsigned long flags; int ret; bool data; fedata = dev_get_drvdata(&dev->dev); down(&fedata->socket_lock); mappass = radix_tree_lookup(&fedata->socketpass_mappings, req->u.poll.id); up(&fedata->socket_lock); if (mappass == NULL) return -EINVAL; /* * Limitation of the current implementation: only support one * concurrent accept or poll call on one socket. */ spin_lock_irqsave(&mappass->copy_lock, flags); if (mappass->reqcopy.cmd != 0) { ret = -EINTR; goto out; } mappass->reqcopy = *req; icsk = inet_csk(mappass->sock->sk); queue = &icsk->icsk_accept_queue; data = queue->rskq_accept_head != NULL; if (data) { mappass->reqcopy.cmd = 0; ret = 0; goto out; } spin_unlock_irqrestore(&mappass->copy_lock, flags); /* Tell the caller we don't need to send back a notification yet */ return -1; out: spin_unlock_irqrestore(&mappass->copy_lock, flags); rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++); rsp->req_id = req->req_id; rsp->cmd = req->cmd; rsp->u.poll.id = req->u.poll.id; rsp->ret = ret; |
b1efa6931 xen/pvcalls: hand... |
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 |
return 0; } static int pvcalls_back_handle_cmd(struct xenbus_device *dev, struct xen_pvcalls_request *req) { int ret = 0; switch (req->cmd) { case PVCALLS_SOCKET: ret = pvcalls_back_socket(dev, req); break; case PVCALLS_CONNECT: ret = pvcalls_back_connect(dev, req); break; case PVCALLS_RELEASE: ret = pvcalls_back_release(dev, req); break; case PVCALLS_BIND: ret = pvcalls_back_bind(dev, req); break; case PVCALLS_LISTEN: ret = pvcalls_back_listen(dev, req); break; case PVCALLS_ACCEPT: ret = pvcalls_back_accept(dev, req); break; case PVCALLS_POLL: ret = pvcalls_back_poll(dev, req); break; default: { struct pvcalls_fedata *fedata; struct xen_pvcalls_response *rsp; fedata = dev_get_drvdata(&dev->dev); rsp = RING_GET_RESPONSE( &fedata->ring, fedata->ring.rsp_prod_pvt++); rsp->req_id = req->req_id; rsp->cmd = req->cmd; rsp->ret = -ENOTSUPP; break; } } return ret; } static void pvcalls_back_work(struct pvcalls_fedata *fedata) { int notify, notify_all = 0, more = 1; struct xen_pvcalls_request req; struct xenbus_device *dev = fedata->dev; while (more) { while (RING_HAS_UNCONSUMED_REQUESTS(&fedata->ring)) { RING_COPY_REQUEST(&fedata->ring, fedata->ring.req_cons++, &req); if (!pvcalls_back_handle_cmd(dev, &req)) { RING_PUSH_RESPONSES_AND_CHECK_NOTIFY( &fedata->ring, notify); notify_all += notify; } } if (notify_all) { notify_remote_via_irq(fedata->irq); notify_all = 0; } RING_FINAL_CHECK_FOR_REQUESTS(&fedata->ring, more); } } |
d0e4d560c xen/pvcalls: conn... |
873 874 |
static irqreturn_t pvcalls_back_event(int irq, void *dev_id) { |
b1efa6931 xen/pvcalls: hand... |
875 876 877 878 879 880 881 882 883 884 885 |
struct xenbus_device *dev = dev_id; struct pvcalls_fedata *fedata = NULL; if (dev == NULL) return IRQ_HANDLED; fedata = dev_get_drvdata(&dev->dev); if (fedata == NULL) return IRQ_HANDLED; pvcalls_back_work(fedata); |
d0e4d560c xen/pvcalls: conn... |
886 887 |
return IRQ_HANDLED; } |
5db4d286a xen/pvcalls: impl... |
888 889 |
static irqreturn_t pvcalls_back_conn_event(int irq, void *sock_map) { |
5ad9918ff xen/pvcalls: impl... |
890 891 892 893 894 895 896 897 898 899 900 901 |
struct sock_mapping *map = sock_map; struct pvcalls_ioworker *iow; if (map == NULL || map->sock == NULL || map->sock->sk == NULL || map->sock->sk->sk_user_data != map) return IRQ_HANDLED; iow = &map->ioworker; atomic_inc(&map->write); atomic_inc(&map->io); queue_work(iow->wq, &iow->register_work); |
5db4d286a xen/pvcalls: impl... |
902 903 |
return IRQ_HANDLED; } |
0a9c75c2c xen/pvcalls: xenb... |
904 905 |
static int backend_connect(struct xenbus_device *dev) { |
d0e4d560c xen/pvcalls: conn... |
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 |
int err, evtchn; grant_ref_t ring_ref; struct pvcalls_fedata *fedata = NULL; fedata = kzalloc(sizeof(struct pvcalls_fedata), GFP_KERNEL); if (!fedata) return -ENOMEM; fedata->irq = -1; err = xenbus_scanf(XBT_NIL, dev->otherend, "port", "%u", &evtchn); if (err != 1) { err = -EINVAL; xenbus_dev_fatal(dev, err, "reading %s/event-channel", dev->otherend); goto error; } err = xenbus_scanf(XBT_NIL, dev->otherend, "ring-ref", "%u", &ring_ref); if (err != 1) { err = -EINVAL; xenbus_dev_fatal(dev, err, "reading %s/ring-ref", dev->otherend); goto error; } err = bind_interdomain_evtchn_to_irq(dev->otherend_id, evtchn); if (err < 0) goto error; fedata->irq = err; err = request_threaded_irq(fedata->irq, NULL, pvcalls_back_event, IRQF_ONESHOT, "pvcalls-back", dev); if (err < 0) goto error; err = xenbus_map_ring_valloc(dev, &ring_ref, 1, (void **)&fedata->sring); if (err < 0) goto error; BACK_RING_INIT(&fedata->ring, fedata->sring, XEN_PAGE_SIZE * 1); fedata->dev = dev; INIT_LIST_HEAD(&fedata->socket_mappings); INIT_RADIX_TREE(&fedata->socketpass_mappings, GFP_KERNEL); sema_init(&fedata->socket_lock, 1); dev_set_drvdata(&dev->dev, fedata); down(&pvcalls_back_global.frontends_lock); list_add_tail(&fedata->list, &pvcalls_back_global.frontends); up(&pvcalls_back_global.frontends_lock); |
0a9c75c2c xen/pvcalls: xenb... |
958 |
return 0; |
d0e4d560c xen/pvcalls: conn... |
959 960 961 962 963 964 965 966 |
error: if (fedata->irq >= 0) unbind_from_irqhandler(fedata->irq, dev); if (fedata->sring != NULL) xenbus_unmap_ring_vfree(dev, fedata->sring); kfree(fedata); return err; |
0a9c75c2c xen/pvcalls: xenb... |
967 968 969 970 |
} static int backend_disconnect(struct xenbus_device *dev) { |
0a85d23b8 xen/pvcalls: disc... |
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 |
struct pvcalls_fedata *fedata; struct sock_mapping *map, *n; struct sockpass_mapping *mappass; struct radix_tree_iter iter; void **slot; fedata = dev_get_drvdata(&dev->dev); down(&fedata->socket_lock); list_for_each_entry_safe(map, n, &fedata->socket_mappings, list) { list_del(&map->list); pvcalls_back_release_active(dev, fedata, map); } radix_tree_for_each_slot(slot, &fedata->socketpass_mappings, &iter, 0) { mappass = radix_tree_deref_slot(slot); if (!mappass) continue; if (radix_tree_exception(mappass)) { if (radix_tree_deref_retry(mappass)) slot = radix_tree_iter_retry(&iter); } else { radix_tree_delete(&fedata->socketpass_mappings, mappass->id); pvcalls_back_release_passive(dev, fedata, mappass); } } up(&fedata->socket_lock); unbind_from_irqhandler(fedata->irq, dev); xenbus_unmap_ring_vfree(dev, fedata->sring); list_del(&fedata->list); kfree(fedata); dev_set_drvdata(&dev->dev, NULL); |
0a9c75c2c xen/pvcalls: xenb... |
1007 1008 |
return 0; } |
72e59c30d xen/pvcalls: intr... |
1009 1010 1011 |
static int pvcalls_back_probe(struct xenbus_device *dev, const struct xenbus_device_id *id) { |
0a9c75c2c xen/pvcalls: xenb... |
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 |
int err, abort; struct xenbus_transaction xbt; again: abort = 1; err = xenbus_transaction_start(&xbt); if (err) { pr_warn("%s cannot create xenstore transaction ", __func__); return err; } err = xenbus_printf(xbt, dev->nodename, "versions", "%s", PVCALLS_VERSIONS); if (err) { pr_warn("%s write out 'versions' failed ", __func__); goto abort; } err = xenbus_printf(xbt, dev->nodename, "max-page-order", "%u", MAX_RING_ORDER); if (err) { pr_warn("%s write out 'max-page-order' failed ", __func__); goto abort; } err = xenbus_printf(xbt, dev->nodename, "function-calls", XENBUS_FUNCTIONS_CALLS); if (err) { pr_warn("%s write out 'function-calls' failed ", __func__); goto abort; } abort = 0; abort: err = xenbus_transaction_end(xbt, abort); if (err) { if (err == -EAGAIN && !abort) goto again; pr_warn("%s cannot complete xenstore transaction ", __func__); return err; } if (abort) return -EFAULT; xenbus_switch_state(dev, XenbusStateInitWait); |
72e59c30d xen/pvcalls: intr... |
1064 1065 |
return 0; } |
0a9c75c2c xen/pvcalls: xenb... |
1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 |
static void set_backend_state(struct xenbus_device *dev, enum xenbus_state state) { while (dev->state != state) { switch (dev->state) { case XenbusStateClosed: switch (state) { case XenbusStateInitWait: case XenbusStateConnected: xenbus_switch_state(dev, XenbusStateInitWait); break; case XenbusStateClosing: xenbus_switch_state(dev, XenbusStateClosing); break; default: |
fefcfb993 xen/pvcalls: use ... |
1081 |
WARN_ON(1); |
0a9c75c2c xen/pvcalls: xenb... |
1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 |
} break; case XenbusStateInitWait: case XenbusStateInitialised: switch (state) { case XenbusStateConnected: backend_connect(dev); xenbus_switch_state(dev, XenbusStateConnected); break; case XenbusStateClosing: case XenbusStateClosed: xenbus_switch_state(dev, XenbusStateClosing); break; default: |
fefcfb993 xen/pvcalls: use ... |
1096 |
WARN_ON(1); |
0a9c75c2c xen/pvcalls: xenb... |
1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 |
} break; case XenbusStateConnected: switch (state) { case XenbusStateInitWait: case XenbusStateClosing: case XenbusStateClosed: down(&pvcalls_back_global.frontends_lock); backend_disconnect(dev); up(&pvcalls_back_global.frontends_lock); xenbus_switch_state(dev, XenbusStateClosing); break; default: |
fefcfb993 xen/pvcalls: use ... |
1110 |
WARN_ON(1); |
0a9c75c2c xen/pvcalls: xenb... |
1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 |
} break; case XenbusStateClosing: switch (state) { case XenbusStateInitWait: case XenbusStateConnected: case XenbusStateClosed: xenbus_switch_state(dev, XenbusStateClosed); break; default: |
fefcfb993 xen/pvcalls: use ... |
1121 |
WARN_ON(1); |
0a9c75c2c xen/pvcalls: xenb... |
1122 1123 1124 |
} break; default: |
fefcfb993 xen/pvcalls: use ... |
1125 |
WARN_ON(1); |
0a9c75c2c xen/pvcalls: xenb... |
1126 1127 1128 |
} } } |
72e59c30d xen/pvcalls: intr... |
1129 1130 1131 |
static void pvcalls_back_changed(struct xenbus_device *dev, enum xenbus_state frontend_state) { |
0a9c75c2c xen/pvcalls: xenb... |
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 |
switch (frontend_state) { case XenbusStateInitialising: set_backend_state(dev, XenbusStateInitWait); break; case XenbusStateInitialised: case XenbusStateConnected: set_backend_state(dev, XenbusStateConnected); break; case XenbusStateClosing: set_backend_state(dev, XenbusStateClosing); break; case XenbusStateClosed: set_backend_state(dev, XenbusStateClosed); if (xenbus_dev_is_online(dev)) break; device_unregister(&dev->dev); break; case XenbusStateUnknown: set_backend_state(dev, XenbusStateClosed); device_unregister(&dev->dev); break; default: xenbus_dev_fatal(dev, -EINVAL, "saw state %d at frontend", frontend_state); break; } |
72e59c30d xen/pvcalls: intr... |
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 |
} static int pvcalls_back_remove(struct xenbus_device *dev) { return 0; } static int pvcalls_back_uevent(struct xenbus_device *xdev, struct kobj_uevent_env *env) { return 0; } static const struct xenbus_device_id pvcalls_back_ids[] = { { "pvcalls" }, { "" } }; static struct xenbus_driver pvcalls_back_driver = { .ids = pvcalls_back_ids, .probe = pvcalls_back_probe, .remove = pvcalls_back_remove, .uevent = pvcalls_back_uevent, .otherend_changed = pvcalls_back_changed, }; |
9be07334f xen/pvcalls: init... |
1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 |
static int __init pvcalls_back_init(void) { int ret; if (!xen_domain()) return -ENODEV; ret = xenbus_register_backend(&pvcalls_back_driver); if (ret < 0) return ret; sema_init(&pvcalls_back_global.frontends_lock, 1); INIT_LIST_HEAD(&pvcalls_back_global.frontends); return 0; } module_init(pvcalls_back_init); |
0a85d23b8 xen/pvcalls: disc... |
1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 |
static void __exit pvcalls_back_fin(void) { struct pvcalls_fedata *fedata, *nfedata; down(&pvcalls_back_global.frontends_lock); list_for_each_entry_safe(fedata, nfedata, &pvcalls_back_global.frontends, list) { backend_disconnect(fedata->dev); } up(&pvcalls_back_global.frontends_lock); xenbus_unregister_driver(&pvcalls_back_driver); } module_exit(pvcalls_back_fin); |